diff --git a/Cargo.lock b/Cargo.lock index d2f4dadad0..c46eac4790 100644 --- a/Cargo.lock +++ b/Cargo.lock @@ -4208,7 +4208,7 @@ dependencies = [ [[package]] name = "pdfcraft" -version = "0.17.0" +version = "0.18.0" dependencies = [ "chrono", "craft-update", @@ -4232,7 +4232,7 @@ dependencies = [ [[package]] name = "pdfcraft-a11y" -version = "0.17.0" +version = "0.18.0" dependencies = [ "pdfcraft-content", "pdfcraft-cos", @@ -4244,7 +4244,7 @@ dependencies = [ [[package]] name = "pdfcraft-annot" -version = "0.17.0" +version = "0.18.0" dependencies = [ "hayro-syntax", "pdfcraft-cos", @@ -4255,7 +4255,7 @@ dependencies = [ [[package]] name = "pdfcraft-audit" -version = "0.17.0" +version = "0.18.0" dependencies = [ "pdfcraft-content", "pdfcraft-cos", @@ -4266,7 +4266,7 @@ dependencies = [ [[package]] name = "pdfcraft-automation" -version = "0.17.0" +version = "0.18.0" dependencies = [ "base64 0.23.1", "flate2", @@ -4288,7 +4288,7 @@ dependencies = [ [[package]] name = "pdfcraft-cli" -version = "0.17.0" +version = "0.18.0" dependencies = [ "base64 0.23.1", "pdfcraft-audit", @@ -4306,11 +4306,11 @@ dependencies = [ [[package]] name = "pdfcraft-compare" -version = "0.17.0" +version = "0.18.0" [[package]] name = "pdfcraft-content" -version = "0.17.0" +version = "0.18.0" dependencies = [ "hayro-syntax", "pdfcraft-cos", @@ -4318,7 +4318,7 @@ dependencies = [ [[package]] name = "pdfcraft-cos" -version = "0.17.0" +version = "0.18.0" dependencies = [ "chrono", "hayro-syntax", @@ -4333,7 +4333,7 @@ dependencies = [ [[package]] name = "pdfcraft-create" -version = "0.17.0" +version = "0.18.0" dependencies = [ "encoding_rs", "hayro-ccitt", @@ -4352,7 +4352,7 @@ dependencies = [ [[package]] name = "pdfcraft-crypt" -version = "0.17.0" +version = "0.18.0" dependencies = [ "aes", "md-5", @@ -4364,7 +4364,7 @@ dependencies = [ [[package]] name = "pdfcraft-edit" -version = "0.17.0" +version = "0.18.0" dependencies = [ "hayro-syntax", "kurbo 0.13.1", @@ -4382,7 +4382,7 @@ dependencies = [ [[package]] name = "pdfcraft-engine" -version = "0.17.0" +version = "0.18.0" dependencies = [ "chrono", "craft-docpath", @@ -4426,14 +4426,14 @@ dependencies = [ [[package]] name = "pdfcraft-export" -version = "0.17.0" +version = "0.18.0" dependencies = [ "flate2", ] [[package]] name = "pdfcraft-filters" -version = "0.17.0" +version = "0.18.0" dependencies = [ "fax", "flate2", @@ -4446,7 +4446,7 @@ dependencies = [ [[package]] name = "pdfcraft-fonts" -version = "0.17.0" +version = "0.18.0" dependencies = [ "harfrust", "pdfcraft-cos", @@ -4456,7 +4456,7 @@ dependencies = [ [[package]] name = "pdfcraft-forms" -version = "0.17.0" +version = "0.18.0" dependencies = [ "hayro-syntax", "pdfcraft-content", @@ -4469,11 +4469,11 @@ dependencies = [ [[package]] name = "pdfcraft-geom" -version = "0.17.0" +version = "0.18.0" [[package]] name = "pdfcraft-js" -version = "0.17.0" +version = "0.18.0" dependencies = [ "boa_engine", "chrono", @@ -4481,7 +4481,7 @@ dependencies = [ [[package]] name = "pdfcraft-measure" -version = "0.17.0" +version = "0.18.0" dependencies = [ "pdfcraft-annot", "pdfcraft-content", @@ -4494,14 +4494,14 @@ dependencies = [ [[package]] name = "pdfcraft-model" -version = "0.17.0" +version = "0.18.0" dependencies = [ "pdfcraft-cos", ] [[package]] name = "pdfcraft-ocr" -version = "0.17.0" +version = "0.18.0" dependencies = [ "ocrs", "pdfcraft-fonts", @@ -4512,7 +4512,7 @@ dependencies = [ [[package]] name = "pdfcraft-optimize" -version = "0.17.0" +version = "0.18.0" dependencies = [ "image", "pdfcraft-annot", @@ -4528,11 +4528,11 @@ dependencies = [ [[package]] name = "pdfcraft-oracle" -version = "0.17.0" +version = "0.18.0" [[package]] name = "pdfcraft-organize" -version = "0.17.0" +version = "0.18.0" dependencies = [ "hayro-syntax", "pdfcraft-content", @@ -4543,7 +4543,7 @@ dependencies = [ [[package]] name = "pdfcraft-platform" -version = "0.17.0" +version = "0.18.0" dependencies = [ "async-channel", "futures-lite", @@ -4553,7 +4553,7 @@ dependencies = [ [[package]] name = "pdfcraft-preflight" -version = "0.17.0" +version = "0.18.0" dependencies = [ "flate2", "pdfcraft-content", @@ -4564,7 +4564,7 @@ dependencies = [ [[package]] name = "pdfcraft-print" -version = "0.17.0" +version = "0.18.0" dependencies = [ "craft-print", "pdfcraft-content", @@ -4576,7 +4576,7 @@ dependencies = [ [[package]] name = "pdfcraft-redact" -version = "0.17.0" +version = "0.18.0" dependencies = [ "pdfcraft-annot", "pdfcraft-content", @@ -4593,7 +4593,7 @@ dependencies = [ [[package]] name = "pdfcraft-render" -version = "0.17.0" +version = "0.18.0" dependencies = [ "bytemuck", "flate2", @@ -4612,7 +4612,7 @@ dependencies = [ [[package]] name = "pdfcraft-sign" -version = "0.17.0" +version = "0.18.0" dependencies = [ "aes", "aws-lc-rs", @@ -4648,11 +4648,11 @@ dependencies = [ [[package]] name = "pdfcraft-testkit" -version = "0.17.0" +version = "0.18.0" [[package]] name = "pdfcraft-ui-egui" -version = "0.17.0" +version = "0.18.0" dependencies = [ "arboard", "base64 0.23.1", @@ -4706,7 +4706,7 @@ dependencies = [ [[package]] name = "pdfcraft-web" -version = "0.17.0" +version = "0.18.0" dependencies = [ "eframe", "egui", @@ -4718,7 +4718,7 @@ dependencies = [ [[package]] name = "pdfcraft-xfa" -version = "0.17.0" +version = "0.18.0" dependencies = [ "base64 0.23.1", "image", @@ -4732,7 +4732,7 @@ dependencies = [ [[package]] name = "pdfcraft-xfdf" -version = "0.17.0" +version = "0.18.0" dependencies = [ "pdfcraft-annot", "pdfcraft-cos", diff --git a/Cargo.toml b/Cargo.toml index edd9e682b7..7be5624db7 100644 --- a/Cargo.toml +++ b/Cargo.toml @@ -5,7 +5,7 @@ exclude = ["vendor"] default-members = ["crates/*", "apps/pdfcraft", "apps/pdfcraft-cli", "xtask"] [workspace.package] -version = "0.17.0" +version = "0.18.0" edition = "2024" license = "MIT OR Apache-2.0" rust-version = "1.95" @@ -26,39 +26,39 @@ craft-docpath = { version = "0.1.0", git = "https://github.com/storytold/craft-l # craft-update: app-specific pretend versions apply to startup and manual checks. craft-update = { git = "https://github.com/storytold/craft-libs", version = "=0.1.0", rev = "787a7a0f972fd1d7a7618fdbeca3a5267a0407ff", features = ["egui"] } # internal -pdfcraft-geom = { path = "crates/geom", version = "0.17.0" } -pdfcraft-filters = { path = "crates/filters", version = "0.17.0" } -pdfcraft-cos = { path = "crates/cos", version = "0.17.0" } -pdfcraft-crypt = { path = "crates/crypt", version = "0.17.0" } -pdfcraft-organize = { path = "crates/organize", version = "0.17.0" } -pdfcraft-measure = { path = "crates/measure", version = "0.17.0" } -pdfcraft-annot = { path = "crates/annot", version = "0.17.0" } -pdfcraft-audit = { path = "crates/audit", version = "0.17.0" } -pdfcraft-fonts = { path = "crates/fonts", version = "0.17.0" } -pdfcraft-model = { path = "crates/model", version = "0.17.0" } -pdfcraft-content = { path = "crates/content", version = "0.17.0" } -pdfcraft-redact = { path = "crates/redact", version = "0.17.0" } -pdfcraft-print = { path = "crates/print", version = "0.17.0" } -pdfcraft-xfdf = { path = "crates/xfdf", version = "0.17.0" } -pdfcraft-sign = { path = "crates/sign", version = "0.17.0" } -pdfcraft-optimize = { path = "crates/optimize", version = "0.17.0" } -pdfcraft-a11y = { path = "crates/a11y", version = "0.17.0" } -pdfcraft-oracle = { path = "crates/oracle", version = "0.17.0" } -pdfcraft-testkit = { path = "crates/testkit", version = "0.17.0" } -pdfcraft-ocr = { path = "crates/ocr", version = "0.17.0" } -pdfcraft-js = { path = "crates/js", version = "0.17.0" } -pdfcraft-compare = { path = "crates/compare", version = "0.17.0" } -pdfcraft-preflight = { path = "crates/preflight", version = "0.17.0" } -pdfcraft-export = { path = "crates/export", version = "0.17.0" } -pdfcraft-edit = { path = "crates/edit", version = "0.17.0" } -pdfcraft-create = { path = "crates/create", version = "0.17.0" } -pdfcraft-forms = { path = "crates/forms", version = "0.17.0" } -pdfcraft-xfa = { path = "crates/xfa", version = "0.17.0" } -pdfcraft-render = { path = "crates/render", version = "0.17.0" } -pdfcraft-engine = { path = "crates/engine", version = "0.17.0" } -pdfcraft-platform = { path = "crates/platform", version = "0.17.0" } -pdfcraft-ui-egui = { path = "crates/ui-egui", version = "0.17.0" } -pdfcraft-automation = { path = "crates/automation", version = "0.17.0", default-features = false } +pdfcraft-geom = { path = "crates/geom", version = "0.18.0" } +pdfcraft-filters = { path = "crates/filters", version = "0.18.0" } +pdfcraft-cos = { path = "crates/cos", version = "0.18.0" } +pdfcraft-crypt = { path = "crates/crypt", version = "0.18.0" } +pdfcraft-organize = { path = "crates/organize", version = "0.18.0" } +pdfcraft-measure = { path = "crates/measure", version = "0.18.0" } +pdfcraft-annot = { path = "crates/annot", version = "0.18.0" } +pdfcraft-audit = { path = "crates/audit", version = "0.18.0" } +pdfcraft-fonts = { path = "crates/fonts", version = "0.18.0" } +pdfcraft-model = { path = "crates/model", version = "0.18.0" } +pdfcraft-content = { path = "crates/content", version = "0.18.0" } +pdfcraft-redact = { path = "crates/redact", version = "0.18.0" } +pdfcraft-print = { path = "crates/print", version = "0.18.0" } +pdfcraft-xfdf = { path = "crates/xfdf", version = "0.18.0" } +pdfcraft-sign = { path = "crates/sign", version = "0.18.0" } +pdfcraft-optimize = { path = "crates/optimize", version = "0.18.0" } +pdfcraft-a11y = { path = "crates/a11y", version = "0.18.0" } +pdfcraft-oracle = { path = "crates/oracle", version = "0.18.0" } +pdfcraft-testkit = { path = "crates/testkit", version = "0.18.0" } +pdfcraft-ocr = { path = "crates/ocr", version = "0.18.0" } +pdfcraft-js = { path = "crates/js", version = "0.18.0" } +pdfcraft-compare = { path = "crates/compare", version = "0.18.0" } +pdfcraft-preflight = { path = "crates/preflight", version = "0.18.0" } +pdfcraft-export = { path = "crates/export", version = "0.18.0" } +pdfcraft-edit = { path = "crates/edit", version = "0.18.0" } +pdfcraft-create = { path = "crates/create", version = "0.18.0" } +pdfcraft-forms = { path = "crates/forms", version = "0.18.0" } +pdfcraft-xfa = { path = "crates/xfa", version = "0.18.0" } +pdfcraft-render = { path = "crates/render", version = "0.18.0" } +pdfcraft-engine = { path = "crates/engine", version = "0.18.0" } +pdfcraft-platform = { path = "crates/platform", version = "0.18.0" } +pdfcraft-ui-egui = { path = "crates/ui-egui", version = "0.18.0" } +pdfcraft-automation = { path = "crates/automation", version = "0.18.0", default-features = false } # pdf hayro = "0.7.1" diff --git a/ROADMAP.md b/ROADMAP.md index a39d6f8b6c..5bfe1fc817 100644 --- a/ROADMAP.md +++ b/ROADMAP.md @@ -1,5 +1,9 @@ # PdfCraft roadmap +> **Last reviewed:** 2026-11-03 | **Last updated:** 2026-11-03 | **Change:** patch (M5 #5850 review: indirect typewriter intent and composer edits preserve outer whitespace; movement regression commits by outside click; estimates unchanged) + +> **Last reviewed:** 2026-11-03 | **Last updated:** 2026-11-03 | **Change:** patch (M5 #5850: Enter adds Fill & Sign line breaks; outside clicks commit, Escape cancels, and saved multiline appearances retain their text and height; estimates unchanged) + > **Last reviewed:** 2026-11-01 | **Last updated:** 2026-11-01 | **Change:** patch (M7, PR #2155 further review: inherited drawing/text state, affine image gestures, paste/selection ownership, no-op scripts and menu permissions; estimates unchanged) > **Last reviewed:** 2026-11-01 | **Last updated:** 2026-11-01 | **Change:** patch (M7, PR #2155 latest comments: explicit image-paste events, mixed-size field refresh, and documented mixed-script normalization with Undo; estimates unchanged) @@ -219,6 +223,14 @@ Ranked; detail and the full milestone table in [docs/roadmap.md](docs/roadmap.md ## Progress log +- **2026-11-03 (M5, #5850 review):** Resolve indirect IT when recognizing typewriter contents and Fill & Sign marks. Comment listing and property lookup retain their existing direct-Subtype behavior. A real double-click Edit composer preserves the typewriter’s text as written; ordinary comment edits keep trimming. Regressions cover direct Subtype with indirect intent, save/reopen, raw posted contents and same-index comments on different pages. The existing live-movement test now commits its setup with an outside click rather than Enter. Estimates unchanged. + +- **2026-11-03 (M5, #5850):** Fill & Sign Enter inserts a line break in a growing editor; clicking outside commits and Escape cancels. Nonempty text keeps leading, internal and trailing line breaks. The headless fill_sign_add path sizes its typewriter box for the same wrapped lines so saved appearances show every row. Production-order keyboard and engine save/reopen/render regressions exercise the UI and headless callers. Estimates unchanged. + +- **2026-11-03 (M7, #5835):** In image crop mode, a right-click on the image, its crop box or its handles keeps the crop and opens no menu, so the menu no longer switches as the pointer moves. A right-click elsewhere clears the selection and opens the page menu. UI tests cover all four page rotations, overlapping images, a 45° image, and a check that the Done/Cancel/Remove Crop pills at a page edge still keep the crop. + +- **2026-11-02 (M10, #5743):** macOS print jobs name their title and owner (`com.apple.print.JobInfo.PMJobName`, `PMJobOwner`), as the system print dialog does, because a Kyocera filter crashes on a job without them. Checked by a test and through `doc_print` against a stand-in `lp`; not yet on a physical printer. + - **2026-11-01 (M7, #5657):** Header/footer, watermark and background additions and replacements stage the complete call before committing. Synthetic later-page failures preserve exact incremental bytes, object count, dirty state and allocation cursor; success controls retain other marks and shared/inherited resources. Estimates unchanged. - **2026-11-01 (M14, #5572):** Preferences ▸ Documents and view sets how many recent files to keep, from 0 to 50 with 12 by default. At 0 Home has no Recent section and File ▸ Open Recent is disabled. The list is cut when Preferences closes, so the number can pass through 0 on its way to another. @@ -745,6 +757,8 @@ Newest first: the date, what moved, and the new overall estimate. | Date | Change | Summary | |---|---|---| +| 2026-11-03 | patch | M5 #5850 review: indirect typewriter intent and composer edits preserve outer whitespace; movement regression commits by outside click; estimates unchanged. | +| 2026-11-03 | patch | M5 #5850: Enter adds Fill & Sign line breaks; outside clicks commit, Escape cancels, and saved multiline appearances retain their text and height; estimates unchanged. | | 2026-11-01 | patch | M7 #5657: header/footer, watermark and background operations commit all selected pages together; later-page errors preserve marks, content, shared/inherited resources and pending edits; estimates unchanged. | | 2026-10-28 | patch | M2, PR #4172: integrate main 5af10276 and retain both roadmap histories; viewer-only CJK and print/output font policies and estimates unchanged. | | 2026-10-27 | minor | M10: OCR stages SHA-256-verified ONNX models after the upstream RTEN URL brownout; discovery prefers a complete ONNX pair per directory, falls back to a complete RTEN pair, and never mixes formats or directories; language/web limits and estimates unchanged. | diff --git a/contributors/people.toml b/contributors/people.toml index a5a47f5c52..fecfb68c90 100644 --- a/contributors/people.toml +++ b/contributors/people.toml @@ -180,3 +180,6 @@ sync_github_name = true [people.dylanmtaylor] sync_github_name = true + +[people.Combiler01] +sync_github_name = true diff --git a/crates/a11y/src/alt.rs b/crates/a11y/src/alt.rs index 720b8a6a1e..fde1048e47 100644 --- a/crates/a11y/src/alt.rs +++ b/crates/a11y/src/alt.rs @@ -125,9 +125,9 @@ pub(crate) fn elements(doc: &Document) -> Vec { } /// The marked-content ids an element owns directly. -fn mcids(d: &Dict) -> Vec { +fn mcids(doc: &Document, d: &Dict) -> Vec { let mut out = Vec::new(); - let mut push = |o: &Object| match o { + let mut push = |o: &Object| match &*doc.resolve(o) { Object::Int(n) => out.push(*n), Object::Dict(m) if m.name(b"Type") == Some(b"MCR") => { if let Some(n) = m.get(b"MCID").and_then(Object::as_int) { @@ -323,7 +323,7 @@ pub fn figures(doc: &Document) -> Vec
{ let mut wanted: HashMap> = HashMap::new(); for (e, page) in &figures { if let Some(p) = page { - wanted.entry(*p).or_default().extend(mcids(&e.dict)); + wanted.entry(*p).or_default().extend(mcids(doc, &e.dict)); } } let bounds: HashMap> = @@ -333,7 +333,7 @@ pub fn figures(doc: &Document) -> Vec
{ .map(|(e, page)| { let alt = e.dict.get(b"Alt").map(|o| doc.resolve(o)).and_then(|o| o.as_string().map(|s| s.to_text())); let on_page = page.and_then(|p| bounds.get(&p)); - let bbox = on_page.and_then(|b| mcids(&e.dict).iter().filter_map(|id| b.get(id)).fold(None, |acc, b| Some(union(acc, *b)))); + let bbox = on_page.and_then(|b| mcids(doc, &e.dict).iter().filter_map(|id| b.get(id)).fold(None, |acc, b| Some(union(acc, *b)))); Figure { obj: e.object, page, alt, bbox } }) .collect() @@ -363,52 +363,73 @@ pub fn set_alt(doc: &mut Document, obj: ObjRef, alt: Option<&str>) -> Result<(), } /// The page's content entries: one stream, or the elements of a contents array. -fn content_entries(doc: &Document, page: &Dict) -> Option> { - let c = page.get(b"Contents")?; - Some(match &*doc.resolve(c) { +fn content_entries(doc: &Document, page: &Dict) -> Vec { + let Some(c) = page.get(b"Contents") else { return Vec::new() }; + match &*doc.resolve(c) { Object::Array(a) => a.clone(), Object::Stream(_) => vec![c.clone()], - _ => return None, - }) + _ => Vec::new(), + } } -fn marked(doc: &Document, props: &Dict, op: &pdfcraft_content::Op, ids: &HashSet) -> bool { - op.op == b"BDC" && bdc_mcid(doc, props, op).is_some_and(|n| ids.contains(&n)) -} +type DecodedStream = (Object, Option<(Stream, Vec)>); -/// Turn the figure's marked-content blocks into artifacts, rewriting only the streams that -/// contain them. Other content streams, and unknown entries on a rewritten stream, stay. -fn artifact_marked_content(doc: &mut Document, page: &pdfcraft_model::Page, ids: &HashSet) -> Result { - let Some(entries) = content_entries(doc, &page.dict) else { return Ok(false) }; - let props = page_properties(doc, &page.dict); - let mut streams: Vec)>> = Vec::with_capacity(entries.len()); +/// Decode the page's content streams within the page decode budget. `None` when a stream is +/// rejected because the budget is exhausted. +fn decode_page_streams(doc: &Document, page: &Dict) -> Option> { + let entries = content_entries(doc, page); + let mut streams = Vec::with_capacity(entries.len()); let mut budget = DecodeBudget::page(); - for entry in &entries { - match &*doc.resolve(entry) { + for entry in entries { + let decoded = match &*doc.resolve(&entry) { Object::Stream(s) => { let data = match budget.decode(s) { Ok(data) => data, - // Content past the budget may hold more of the figure: editing the rest - // would leave that part marked as a figure the tree no longer has. - Err(_) if budget.exhausted() => return Err(AltError::TooLarge), + // Content past the budget may hold more of the tag: editing the rest + // would leave that part marked as a tag the tree no longer has. + Err(_) if budget.exhausted() => return None, Err(_) => Vec::new(), }; - streams.push(Some((s.clone(), data))); + Some((s.clone(), data)) } - _ => streams.push(None), + _ => None, + }; + streams.push((entry, decoded)); + } + Some(streams) +} + +fn marked_id(doc: &Document, props: &Dict, op: &pdfcraft_content::Op, ids: &HashSet) -> Option { + (op.op == b"BDC").then(|| bdc_mcid(doc, props, op)).flatten().filter(|n| ids.contains(n)) +} + +/// Turn the tag's marked-content blocks into artifacts, rewriting only the streams that +/// contain them. Other content streams, and unknown entries on a rewritten stream, stay. +/// With `require_all`, every id in `ids` must appear on the page before any stream is rewritten. +fn artifact_marked_content( + doc: &mut Document, + page: &pdfcraft_model::Page, + streams: Vec, + ids: &HashSet, + require_all: bool, +) -> Result { + let props = page_properties(doc, &page.dict); + let decoded: Vec<&[u8]> = streams.iter().filter_map(|(_, s)| s.as_ref().map(|(_, bytes)| bytes.as_slice())).collect(); + let pieces = pdfcraft_content::Pieces::join(&decoded); + let mut found = HashSet::new(); + let mut edits = Vec::new(); + for op in pieces.parse().ops { + if let Some(id) = marked_id(doc, &props, &op, ids) { + found.insert(id); + edits.push((op.span, b"/Artifact BMC".to_vec())); } } - let decoded: Vec<&[u8]> = streams.iter().flatten().map(|(_, bytes)| bytes.as_slice()).collect(); - let pieces = pdfcraft_content::Pieces::join(&decoded); - let edits: Vec<_> = - pieces.parse().ops.into_iter().filter(|op| marked(doc, &props, op, ids)).map(|op| (op.span, b"/Artifact BMC".to_vec())).collect(); - if edits.is_empty() { + if if require_all { found != *ids } else { found.is_empty() } { return Ok(false); } let mut spliced = pieces.splice(edits).into_iter(); - let mut next = Vec::with_capacity(entries.len()); - let mut changed = false; - for (entry, stream) in entries.into_iter().zip(streams) { + let mut next = Vec::with_capacity(streams.len()); + for (entry, stream) in streams { let Some((stream, old)) = stream else { next.push(entry); continue; @@ -421,7 +442,6 @@ fn artifact_marked_content(doc: &mut Document, page: &pdfcraft_model::Page, ids: next.push(entry); continue; } - changed = true; let mut dict = stream.dict; dict.remove(b"Length"); dict.remove(b"Filter"); @@ -431,28 +451,27 @@ fn artifact_marked_content(doc: &mut Document, page: &pdfcraft_model::Page, ids: // appear elsewhere in this array or on another page, where it must stay unchanged. next.push(Object::Ref(doc.add(stream))); } - if changed { - let contents = match next.as_slice() { - [one] => one.clone(), - _ => Object::Array(next), - }; - doc.update_dict(page.obj, |p| p.set(b"Contents".to_vec(), contents))?; - } - Ok(changed) + let contents = match next.as_slice() { + [one] => one.clone(), + _ => Object::Array(next), + }; + doc.update_dict(page.obj, |p| p.set(b"Contents".to_vec(), contents))?; + Ok(true) } /// Decorative figure: its marked content on the page becomes an artifact, and the element /// leaves the structure tree (and the parent tree). pub fn mark_decorative(doc: &mut Document, obj: ObjRef) -> Result<(), AltError> { let d = check_figure(doc, obj)?; - let ids: HashSet = mcids(&d).into_iter().collect(); + let ids: HashSet = mcids(doc, &d).into_iter().collect(); let pages = pdfcraft_model::pages(doc); let pg = d.get(b"Pg").and_then(Object::as_ref).or_else(|| elements(doc).into_iter().find(|e| e.object == obj).and_then(|e| e.page)); - if let Some(page) = pg.and_then(|p| pages.iter().find(|x| x.obj == p)).filter(|_| !ids.is_empty()) - && artifact_marked_content(doc, page, &ids)? - { + if let Some(page) = pg.and_then(|p| pages.iter().find(|x| x.obj == p)).filter(|_| !ids.is_empty()) { + let streams = decode_page_streams(doc, &page.dict).ok_or(AltError::TooLarge)?; // The parent tree no longer points those ids at the figure. - if let Some(key) = page.dict.get(b"StructParents").and_then(Object::as_int) { + if artifact_marked_content(doc, page, streams, &ids, false)? + && let Some(key) = page.dict.get(b"StructParents").and_then(Object::as_int) + { clear_parent_tree(doc, key, obj)?; } } @@ -484,54 +503,23 @@ pub fn mark_tag_artifact(doc: &mut Document, obj: ObjRef) -> Result<(), Artifact if has_child_structure(doc, &element.dict) { return Err(ArtifactError::HasChildren); } - let ids: HashSet = mcids(&element.dict).into_iter().collect(); + let ids: HashSet = mcids(doc, &element.dict).into_iter().collect(); if ids.is_empty() { return Err(ArtifactError::NoMarkedContent); } let pages = pdfcraft_model::pages(doc); let page_ref = element.page.ok_or(ArtifactError::NoPage)?; let page = pages.iter().find(|page| page.obj == page_ref).ok_or(ArtifactError::NoPage)?; - let mut content = Vec::new(); - if let Some(c) = page.dict.get(b"Contents") { - let mut budget = DecodeBudget::page(); - for data in budget.decode_contents(doc, c) { - match data { - Ok(data) => { - content.extend_from_slice(&data); - content.push(b' '); - } - // The page's /Contents is replaced with what was decoded: content past the - // budget would be dropped from the page. - Err(_) if budget.exhausted() => return Err(ArtifactError::TooLarge), - Err(_) => {} - } - } - } - let mut ops = pdfcraft_content::parse(&content).ops; - let mut found = HashSet::new(); - for op in &mut ops { - let id = (op.op == b"BDC") - .then(|| match op.operands.get(1) { - Some(Object::Dict(mark)) => mark.get(b"MCID").and_then(Object::as_int), - _ => None, - }) - .flatten() - .filter(|id| ids.contains(id)); - if let Some(id) = id { - *op = pdfcraft_content::Op::new("BMC", vec![Object::name("Artifact")]); - found.insert(id); - } - } - if found != ids { + let parent = element.dict.get(b"P").and_then(Object::as_ref).ok_or(ArtifactError::NoParent)?; + let replacement = replacement_kids(doc, parent, obj)?; + let streams = decode_page_streams(doc, &page.dict).ok_or(ArtifactError::TooLarge)?; + if !artifact_marked_content(doc, page, streams, &ids, true)? { return Err(ArtifactError::ContentNotFound); } - let stream = doc.add(Object::Stream(Stream::flate(Dict::new(), &pdfcraft_content::serialize_ops(&ops)))); - doc.update_dict(page.obj, |p| p.set(b"Contents".to_vec(), Object::Ref(stream)))?; if let Some(key) = page.dict.get(b"StructParents").and_then(Object::as_int) { clear_parent_tree(doc, key, obj).map_err(|e| ArtifactError::ParentTree(e.to_string()))?; } - let parent = element.dict.get(b"P").and_then(Object::as_ref).ok_or(ArtifactError::NoParent)?; - remove_from_parent(doc, parent, obj)?; + doc.update_dict(parent, |p| p.set(b"K".to_vec(), replacement))?; // Keep the retired object valid if another object holds an out-of-tree reference to it. doc.update_dict(obj, |d| { d.remove(b"P"); @@ -551,20 +539,18 @@ fn has_child_structure(doc: &Document, tag: &Dict) -> bool { tag.get(b"K").is_some_and(|items| child(doc, items)) } -fn remove_from_parent(doc: &mut Document, parent: ObjRef, obj: ObjRef) -> Result<(), ArtifactError> { +fn replacement_kids(doc: &Document, parent: ObjRef, obj: ObjRef) -> Result { let kids = doc.get(parent).as_dict().and_then(|p| p.get(b"K").cloned()).ok_or(ArtifactError::NoParent)?; - let replacement = match kids { + match kids { Object::Array(items) => { if items.iter().filter(|item| item.as_ref() == Some(obj)).count() != 1 { return Err(ArtifactError::AmbiguousParent); } - Object::Array(items.into_iter().filter(|item| item.as_ref() != Some(obj)).collect()) + Ok(Object::Array(items.into_iter().filter(|item| item.as_ref() != Some(obj)).collect())) } - Object::Ref(r) if r == obj => Object::Array(Vec::new()), - _ => return Err(ArtifactError::NoParent), - }; - doc.update_dict(parent, |p| p.set(b"K".to_vec(), replacement))?; - Ok(()) + Object::Ref(r) if r == obj => Ok(Object::Array(Vec::new())), + _ => Err(ArtifactError::NoParent), + } } /// Replace `obj` by null in the page's parent-tree array (`key`), in a flat /Nums tree. diff --git a/crates/a11y/src/tests.rs b/crates/a11y/src/tests.rs index a70ffbf385..3024319ec3 100644 --- a/crates/a11y/src/tests.rs +++ b/crates/a11y/src/tests.rs @@ -1017,6 +1017,76 @@ fn named_property_lists_are_found_and_marked_decorative_like_inline_ones() { assert!(props.contains(b"P0") && props.contains(b"P1") && props.contains(b"Other"), "resources are left as they were"); } +#[test] +fn mark_tag_artifact_finds_named_property_lists_and_indirect_mcrs() { + use pdfcraft_cos::{Dict, ObjRef, Object}; + let mut doc = named_figures_doc(); + let mcr = doc.add(Object::Dict([(b"Type".to_vec(), Object::name("MCR")), (b"MCID".to_vec(), Object::Int(0))].into_iter().collect::())); + doc.update_dict(ObjRef::new(7, 0), |d| d.set(b"K".to_vec(), Object::Ref(mcr))).unwrap(); + assert_eq!(figures(&doc)[0].bbox, Some([10.0, 150.0, 50.0, 170.0]), "indirect MCR is resolved for figure bounds"); + + for (tag, gone) in [(ObjRef::new(7, 0), "/P0"), (ObjRef::new(8, 0), "/P1")] { + mark_tag_artifact(&mut doc, tag).unwrap(); + let pages = pdfcraft_model::pages(&doc); + let c = doc.resolve(pages[0].dict.get(b"Contents").unwrap()); + let Object::Stream(c) = &*c else { panic!("one content stream") }; + let text = String::from_utf8(c.decoded().unwrap()).unwrap(); + assert!(text.contains("/Artifact BMC") && !text.contains(gone), "{text}"); + } + assert_eq!(tags(&doc).into_iter().map(|t| t.object.num).collect::>(), [6]); + let nums = doc.get(ObjRef::new(9, 0)).as_dict().and_then(|d| d.get(b"Nums").cloned()); + assert_eq!(nums, Some(Object::Array(vec![Object::Int(0), Object::Array(vec![Object::Null, Object::Null])]))); + let r = check(&doc, &Options { rules: [Rule::FiguresAltText, Rule::TaggedContent].into(), pages: None }); + assert_eq!(failed(&r), Vec::::new(), "{:?}", r.results); +} + +#[test] +fn mark_tag_artifact_validates_parent_and_all_mcids_before_mutating_document() { + use pdfcraft_cos::{ObjRef, Object}; + + // Missing /P on the tag must fail before touching /Contents or /ParentTree. + let mut no_parent = figures_doc(); + let before_contents = no_parent.get(ObjRef::new(3, 0)).as_dict().unwrap().get(b"Contents").cloned(); + let before_pt = no_parent.get(ObjRef::new(9, 0)).as_ref().clone(); + no_parent + .update_dict(ObjRef::new(7, 0), |d| { + d.remove(b"P"); + }) + .unwrap(); + assert_eq!(mark_tag_artifact(&mut no_parent, ObjRef::new(7, 0)), Err(ArtifactError::NoParent)); + assert_eq!(no_parent.get(ObjRef::new(3, 0)).as_dict().unwrap().get(b"Contents").cloned(), before_contents); + assert_eq!(*no_parent.get(ObjRef::new(9, 0)), before_pt); + + // Duplicate entry in parent's /K must fail with AmbiguousParent before touching /Contents or /ParentTree. + let mut dup_parent = figures_doc(); + dup_parent + .update_dict(ObjRef::new(6, 0), |d| { + d.set(b"K".to_vec(), Object::Array(vec![Object::Ref(ObjRef::new(7, 0)), Object::Ref(ObjRef::new(8, 0)), Object::Ref(ObjRef::new(7, 0))])); + }) + .unwrap(); + assert_eq!(mark_tag_artifact(&mut dup_parent, ObjRef::new(7, 0)), Err(ArtifactError::AmbiguousParent)); + assert_eq!(dup_parent.get(ObjRef::new(3, 0)).as_dict().unwrap().get(b"Contents").cloned(), before_contents); + assert_eq!(*dup_parent.get(ObjRef::new(9, 0)), before_pt); + + // Partial MCID match (MCID 0 present, MCID 99 absent) must fail with ContentNotFound in + // mark_tag_artifact without mutating /Contents, while mark_decorative still converts MCID 0. + let mut partial = figures_doc(); + partial.update_dict(ObjRef::new(7, 0), |d| d.set(b"K".to_vec(), Object::Array(vec![Object::Int(0), Object::Int(99)]))).unwrap(); + assert_eq!(mark_tag_artifact(&mut partial, ObjRef::new(7, 0)), Err(ArtifactError::ContentNotFound)); + assert_eq!(partial.get(ObjRef::new(3, 0)).as_dict().unwrap().get(b"Contents").cloned(), before_contents); + assert_eq!(*partial.get(ObjRef::new(9, 0)), before_pt); + mark_decorative(&mut partial, ObjRef::new(7, 0)).unwrap(); + assert_ne!(partial.get(ObjRef::new(3, 0)).as_dict().unwrap().get(b"Contents").cloned(), before_contents); + assert_ne!(*partial.get(ObjRef::new(9, 0)), before_pt); + + // When none of a figure's MCIDs appear on the page, mark_decorative leaves /Contents and /ParentTree untouched. + let mut absent = figures_doc(); + absent.update_dict(ObjRef::new(7, 0), |d| d.set(b"K".to_vec(), Object::Int(99))).unwrap(); + mark_decorative(&mut absent, ObjRef::new(7, 0)).unwrap(); + assert_eq!(absent.get(ObjRef::new(3, 0)).as_dict().unwrap().get(b"Contents").cloned(), before_contents); + assert_eq!(*absent.get(ObjRef::new(9, 0)), before_pt); +} + fn ref_(n: u32) -> Option { Some(pdfcraft_cos::ObjRef::new(n, 0)) } diff --git a/crates/a11y/tests/cross_stream.rs b/crates/a11y/tests/cross_stream.rs index ad613a2939..d0a2f48204 100644 --- a/crates/a11y/tests/cross_stream.rs +++ b/crates/a11y/tests/cross_stream.rs @@ -99,14 +99,20 @@ fn shown_strings(ops: &[Op]) -> Vec { #[test] fn mark_decorative_leaves_the_other_stream_untouched() { - let mut doc = tagged_figure_two_streams("0 0 1 rg 300 600 100 50 re f", "BT /F1 12 Tf 72 500 Td (After) Tj ET"); - let before = doc.get(ObjRef::new(11, 0)).clone(); - mark_decorative(&mut doc, ObjRef::new(8, 0)).expect("mark decorative succeeds"); - assert!(figures(&doc).is_empty()); - assert_eq!(*doc.get(ObjRef::new(11, 0)), *before, "the second stream holds no figure and keeps its object"); - let page = doc.get(ObjRef::new(3, 0)); - let contents = page.as_dict().unwrap().get(b"Contents").unwrap().as_array().unwrap(); - assert_eq!(contents[1].as_ref(), Some(ObjRef::new(11, 0)), "the untouched stream must not be replaced by a re-encoded copy"); + for use_artifact in [false, true] { + let mut doc = tagged_figure_two_streams("0 0 1 rg 300 600 100 50 re f", "BT /F1 12 Tf 72 500 Td (After) Tj ET"); + let before = doc.get(ObjRef::new(11, 0)).clone(); + if use_artifact { + mark_tag_artifact(&mut doc, ObjRef::new(8, 0)).expect("mark tag artifact succeeds"); + } else { + mark_decorative(&mut doc, ObjRef::new(8, 0)).expect("mark decorative succeeds"); + } + assert!(figures(&doc).is_empty()); + assert_eq!(*doc.get(ObjRef::new(11, 0)), *before, "the second stream holds no figure and keeps its object"); + let page = doc.get(ObjRef::new(3, 0)); + let contents = page.as_dict().unwrap().get(b"Contents").unwrap().as_array().unwrap(); + assert_eq!(contents[1].as_ref(), Some(ObjRef::new(11, 0)), "the untouched stream must not be replaced by a re-encoded copy"); + } } /// A and B supply different operands to R's BDC. Reusing R must not let the first diff --git a/crates/annot/src/info.rs b/crates/annot/src/info.rs index b56e0de20d..1a54dbc077 100644 --- a/crates/annot/src/info.rs +++ b/crates/annot/src/info.rs @@ -47,8 +47,12 @@ pub(crate) fn text_value(doc: &Document, d: &Dict, key: &[u8]) -> Option Object::Name(n) => String::from_utf8_lossy(n).into_owned(), _ => return None, }; - let s = s.trim_matches('\0').trim().to_string(); - (!s.is_empty()).then_some(s) + let s = s.trim_matches('\0'); + // Typewriter outer whitespace belongs to the text (keep in step with render's inspector). + let name_is = |key: &[u8], expected: &[u8]| d.get(key).is_some_and(|o| doc.resolve(o).as_name() == Some(expected)); + let keep_breaks = key == b"Contents" && name_is(b"Subtype", b"FreeText") && name_is(b"IT", b"FreeTextTypeWriter"); + let s = if keep_breaks { s } else { s.trim() }; + (!s.trim().is_empty()).then(|| s.to_owned()) } /// Whether an annotation subtype is a comment. Links, form widgets, pop-ups and the non-markup diff --git a/crates/annot/src/lookup.rs b/crates/annot/src/lookup.rs index c7a0fd9831..9af83b0542 100644 --- a/crates/annot/src/lookup.rs +++ b/crates/annot/src/lookup.rs @@ -137,11 +137,11 @@ pub fn is_fill_sign(doc: &Document, d: &Dict) -> bool { if matches!(d.get(b"PCFillSign").map(|o| doc.resolve(o)).as_deref(), Some(Object::Bool(true))) { return true; } - let subtype = d.name(b"Subtype").unwrap_or_default(); - if subtype == b"FreeText" && d.name(b"IT") == Some(b"FreeTextTypeWriter") { + let name_is = |key: &[u8], expected: &[u8]| d.get(key).is_some_and(|o| doc.resolve(o).as_name() == Some(expected)); + if name_is(b"Subtype", b"FreeText") && name_is(b"IT", b"FreeTextTypeWriter") { return true; } - if subtype == b"Stamp" { + if name_is(b"Subtype", b"Stamp") { if matches!(d.name(b"Name"), Some(b"PCCheck" | b"PCCross" | b"PCDot" | b"PCLine" | b"PCTypedSignature")) { return true; } @@ -151,7 +151,7 @@ pub fn is_fill_sign(doc: &Document, d: &Dict) -> bool { return true; } } - subtype == b"Ink" && text_value(doc, d, b"Subj").as_deref() == Some("Signature") + name_is(b"Subtype", b"Ink") && text_value(doc, d, b"Subj").as_deref() == Some("Signature") } pub(crate) fn annotation_flags(doc: &Document, d: &Dict) -> i64 { diff --git a/crates/annot/src/tests.rs b/crates/annot/src/tests.rs index cf800fa98a..32d28fc6ec 100644 --- a/crates/annot/src/tests.rs +++ b/crates/annot/src/tests.rs @@ -2250,3 +2250,27 @@ fn freehand_highlight_is_compatible_ink_with_marker_blending() { assert!((a - b).abs() < 1e-4, "expected [10, 90, 130, 110], got {rect_from_border:?}"); } } + +#[test] +fn indirect_typewriter_names_keep_outer_whitespace_in_summaries() { + let mut doc = fixture(); + let intent = Object::Ref(doc.add(Object::name("FreeTextTypeWriter"))); + let page = page_refs(&doc).unwrap()[0]; + let mut entries = annots(&doc, page); + let Object::Dict(annotation) = &mut entries[0] else { panic!("fixture annotation is inline") }; + annotation.set(b"Subtype".to_vec(), Object::name("FreeText")); + annotation.set(b"IT".to_vec(), intent); + let contents = " \nAda\n\nLovelace\n\n "; + annotation.set(b"Contents".to_vec(), PdfString::text(contents)); + set_annots(&mut doc, page, entries).unwrap(); + let check = |doc: &Document| { + let list = summaries(doc); + let summary = list.iter().find(|a| a.page == 0 && a.index == 0).expect("direct Subtype is listed"); + assert_eq!(summary.contents.as_deref(), Some(contents), "indirect typewriter intent preserves outer whitespace"); + assert_eq!(summary.subtype, "FreeText"); + assert_eq!(summary.intent.as_deref(), Some("FreeTextTypeWriter")); + assert!(summary.fill_sign, "indirect intent still identifies a Fill & Sign mark"); + }; + check(&doc); + check(&reopen(&doc)); +} diff --git a/crates/audit/src/cover.rs b/crates/audit/src/cover.rs index 041ba9ddd8..bb5adf7ff8 100644 --- a/crates/audit/src/cover.rs +++ b/crates/audit/src/cover.rs @@ -15,7 +15,7 @@ //! the joined stream)`; rectangles inside a form XObject carry the `Do` operator's position. //! Positions compare lexicographically in paint order. -use pdfcraft_content::{Matrix, Op, Pieces, parse}; +use pdfcraft_content::{Matrix, Op, Pieces, ops}; use pdfcraft_cos::{DecodeBudget, Dict, Document, Object}; use crate::AuditError; @@ -123,12 +123,13 @@ impl<'a> Walker<'a> { Ok(()) } - /// Walk one operator slice with the given graphics state. `at_do` is the `Do` position to + /// Walk one stream's operators, read one at a time (a stream of millions of short operators + /// is never held whole), with the given graphics state. `at_do` is the `Do` position to /// stamp on rectangles found inside a form XObject, or `None` at page level (where each /// fill operator's own position is used). fn walk_ops( &mut self, - ops: &[Op], + ops: impl Iterator, gs: &mut Gs, stack: &mut Vec, resources: &Dict, @@ -136,8 +137,9 @@ impl<'a> Walker<'a> { at_do: Option<(usize, usize)>, ) -> Result<(), AuditError> { let mut path = Path::Empty; - for (i, op) in ops.iter().enumerate() { + for (i, op) in ops.enumerate() { self.bump()?; + let op = &op; // Paint position of this operator: its own `(piece, joined index)` at page level, // the enclosing `Do`'s position inside a form XObject. let pos = match at_do { @@ -257,8 +259,9 @@ impl<'a> Walker<'a> { /// changes inside never leak out; every rectangle found is stamped with the `Do` /// position `pos`. fn walk_xobject(&mut self, name: &[u8], gs: &Gs, resources: &Dict, depth: usize, pos: (usize, usize)) -> Result<(), AuditError> { - let xobjects = resources.get(b"XObject").map(|o| self.doc.resolve(o)).and_then(|o| o.as_dict().cloned()).unwrap_or_default(); - let Some(entry) = xobjects.get(name) else { return Ok(()) }; + // Borrowed, not copied: a `Do` must not cost the size of the whole XObject table. + let xobjects = resources.get(b"XObject").map(|o| self.doc.resolve(o)); + let Some(entry) = xobjects.as_deref().and_then(Object::as_dict).and_then(|d| d.get(name)) else { return Ok(()) }; let resolved = self.doc.resolve(entry); let Object::Stream(stream) = &*resolved else { return Ok(()) }; let dict = &stream.dict; @@ -274,18 +277,18 @@ impl<'a> Walker<'a> { (v.len() == 6 && v.iter().all(|x| x.is_finite())).then(|| Matrix([v[0], v[1], v[2], v[3], v[4], v[5]])) }) .unwrap_or(Matrix::IDENTITY); - let sub_resources = dict.get(b"Resources").map(|o| self.doc.resolve(o)).and_then(|o| o.as_dict().cloned()).unwrap_or_default(); + let (sub_resources, empty) = (dict.get(b"Resources").map(|o| self.doc.resolve(o)), Dict::new()); + let sub_resources = sub_resources.as_deref().and_then(Object::as_dict).unwrap_or(&empty); if !self.budget.enter_form() { return Err(AuditError::TooManyForms); } // A form stream that cannot be decoded fails the audit: it might hide a cover. let data = self.budget.decode_strict(stream)?; - let ops = parse(&data).ops; // The XObject matrix maps form space into the user space active at `Do`. let mut sub_gs = gs.clone(); sub_gs.ctm = matrix.then(&gs.ctm); let mut sub_stack = Vec::new(); - self.walk_ops(&ops, &mut sub_gs, &mut sub_stack, &sub_resources, depth + 1, Some(pos)) + self.walk_ops(ops(&data), &mut sub_gs, &mut sub_stack, sub_resources, depth + 1, Some(pos)) } } @@ -298,13 +301,10 @@ fn user_point(gs: &Gs, op: &Op) -> Option<[f64; 2]> { /// The non-stroking alpha (`/ca`) of a named ExtGState, defaulting to opaque. fn ext_alpha(doc: &Document, resources: &Dict, name: &[u8]) -> f64 { - let alpha = resources - .get(b"ExtGState") - .map(|o| doc.resolve(o)) - .and_then(|o| o.as_dict().cloned()) - .and_then(|d| d.get(name).map(|o| doc.resolve(o))) - .and_then(|o| o.as_dict().cloned()) - .and_then(|d| d.get(b"ca").map(|o| doc.resolve(o)).and_then(|o| o.as_f64())); + // Borrowed, not copied: a `gs` must not cost the size of the whole ExtGState table. + let states = resources.get(b"ExtGState").map(|o| doc.resolve(o)); + let state = states.as_deref().and_then(Object::as_dict).and_then(|d| d.get(name)).map(|o| doc.resolve(o)); + let alpha = state.as_deref().and_then(Object::as_dict).and_then(|d| d.get(b"ca").map(|o| doc.resolve(o)).and_then(|o| o.as_f64())); alpha.filter(|a| a.is_finite()).map(|a| a.clamp(0.0, 1.0)).unwrap_or(1.0) } @@ -330,10 +330,11 @@ pub fn filled_rects(doc: &Document, page: &Dict) -> Result, Audi } } let pieces = Pieces::join(&streams); - let parsed = pieces.parse(); let mut w = Walker { doc, pieces: &pieces, out: Vec::new(), ops_seen: 0, budget }; let mut gs = Gs::default(); let mut stack = Vec::new(); - w.walk_ops(&parsed.ops, &mut gs, &mut stack, &resources, 0, None)?; + // Read one operator at a time: the joined stream can hold millions of them within the + // decode budget, and the walk only ever needs the current one. + w.walk_ops(ops(pieces.data()), &mut gs, &mut stack, &resources, 0, None)?; Ok(w.out) } diff --git a/crates/audit/src/lib.rs b/crates/audit/src/lib.rs index f2bcf63358..97429d4c40 100644 --- a/crates/audit/src/lib.rs +++ b/crates/audit/src/lib.rs @@ -99,6 +99,9 @@ const COVER_FRACTION: f64 = 0.4; const WORD_FRACTION: f64 = 0.5; /// WCAG contrast ratio below which the text is unreadable against the cover. const COVER_CONTRAST: f64 = 3.0; +/// Bytes of a hidden line's text read (copied or trimmed) that cost one comparison: a byte scan +/// is far cheaper than a box comparison, but a long padded line under many covers adds up. +const TEXT_BYTES_PER_COMPARISON: usize = 16; /// Audit every page for faux redactions and unapplied redaction marks. Fails closed: any /// content that cannot be decoded, or that needs more work or report than the audit's bounds, is @@ -157,15 +160,24 @@ impl Budget { cover: &[f64; 4], hides: impl Fn(&TextLine) -> bool, ) -> Result, AuditError> { - self.comparisons = self.comparisons.saturating_add(self.page_cost); - if self.comparisons > self.limits.comparisons { - return Err(AuditError::TooManyComparisons); - } + self.spend(self.page_cost)?; if !copying { - return Ok(lines.iter().any(|line| hides(line) && !line.text.trim().is_empty()).then(String::new)); + let mut hidden = false; + for line in lines.iter().filter(|l| hides(l)) { + // Trimming walks the line's text (padding and all): it costs its bytes. + self.spend(line.text.len() / TEXT_BYTES_PER_COMPARISON)?; + if !line.text.trim().is_empty() { + hidden = true; + break; + } + } + return Ok(hidden.then(String::new)); } let mut covered = String::new(); for line in lines.iter().filter(|l| hides(l)) { + // Copying and trimming the line walks its text once per cover: a long padded + // line under many covers would otherwise be read far more than its runs suggest. + self.spend(line.text.len() / TEXT_BYTES_PER_COMPARISON)?; if !covered.is_empty() { covered.push(' '); } @@ -174,11 +186,21 @@ impl Budget { Ok((!covered.trim().is_empty()).then_some(covered)) } + /// `n` units of work done against the comparison bound. + fn spend(&mut self, n: usize) -> Result<(), AuditError> { + self.comparisons = self.comparisons.saturating_add(n); + if self.comparisons > self.limits.comparisons { + return Err(AuditError::TooManyComparisons); + } + Ok(()) + } + /// The text a finding reports for `covered`: none when copying is withheld. Charges what it - /// reports against the output bound. + /// reports, and the finding's own record, against the output bound: a finding with no text + /// (copying withheld, or a shared annotation list on many pages) still takes memory. fn report_text(&mut self, covered: String, copying: bool) -> Result { let reported = if copying { covered } else { String::new() }; - self.covered_text = self.covered_text.saturating_add(reported.len()); + self.covered_text = self.covered_text.saturating_add(reported.len()).saturating_add(std::mem::size_of::()); if self.covered_text > self.limits.covered_text { return Err(AuditError::TooMuchOutput); } @@ -321,17 +343,14 @@ enum AnnotationCover { fn annots(doc: &Document, page: &Dict) -> Result, AuditError> { let Some(a) = page.get(b"Annots") else { return Ok(Vec::new()) }; let resolved = doc.resolve(a); - let items: Vec = match &*resolved { - pdfcraft_cos::Object::Array(items) => items.clone(), - // A missing /Annots means no marks; a malformed one fails the audit. - _ => return Err(AuditError::BadAnnots), - }; + // A missing /Annots means no marks; a malformed one fails the audit. + let Some(items) = resolved.as_array() else { return Err(AuditError::BadAnnots) }; let mut out = Vec::new(); - for a in &items { - let dict = match &*doc.resolve(a) { - pdfcraft_cos::Object::Dict(d) => d.clone(), - _ => continue, - }; + for a in items { + // Borrowed from the resolved object: one large dictionary listed many times is not + // copied once per listing. + let resolved = doc.resolve(a); + let Some(dict) = resolved.as_dict() else { continue }; let v: Vec = match dict.get(b"Rect") { None => continue, Some(r) => doc.resolve(r).as_array().map(|arr| arr.iter().filter_map(|o| doc.resolve(o).as_f64()).collect()).unwrap_or_default(), @@ -340,7 +359,7 @@ fn annots(doc: &Document, page: &Dict) -> Result, AuditErro continue; } let rect = [v[0].min(v[2]), v[1].min(v[3]), v[0].max(v[2]), v[1].max(v[3])]; - match subtype(doc, &dict)?.as_deref() { + match subtype(doc, dict)?.as_deref() { Some(b"Redact") => out.push(AnnotationCover::Redact(rect)), Some(b"Square") => { let flags = dict.get(b"F").and_then(|f| doc.resolve(f).as_int()).unwrap_or(0); @@ -349,7 +368,7 @@ fn annots(doc: &Document, page: &Dict) -> Result, AuditErro } let alpha = dict.get(b"CA").map(|o| doc.resolve(o)).and_then(|o| o.as_f64()).unwrap_or(1.0); if alpha >= 1.0 - && let Some(rgb) = annotation_color(doc, &dict, b"IC") + && let Some(rgb) = annotation_color(doc, dict, b"IC") { out.push(AnnotationCover::Square { rect, rgb }); } diff --git a/crates/audit/src/tests.rs b/crates/audit/src/tests.rs index e5fb9ab683..074eb39f66 100644 --- a/crates/audit/src/tests.rs +++ b/crates/audit/src/tests.rs @@ -720,9 +720,11 @@ fn runs_without_words_count_against_the_comparison_bound() { let doc = open(one_page(&content, "")); let lines = pdfcraft_edit::glyph_text_lines(&doc, &pdfcraft_model::pages(&doc)[0]).expect("text"); assert_eq!(lines.iter().map(|l| (l.ink.len(), l.runs().count())).collect::>(), [(1, 51)]); - let limits = crate::Limits { comparisons: 50, covered_text: usize::MAX }; + // Plus the hidden line's text, read once to copy it. + let text = lines[0].text.len() / crate::TEXT_BYTES_PER_COMPARISON; + let limits = crate::Limits { comparisons: 50 + text, covered_text: usize::MAX }; assert!(matches!(crate::audit(&doc, limits), Err(crate::AuditError::TooManyComparisons))); - let limits = crate::Limits { comparisons: 51, covered_text: usize::MAX }; + let limits = crate::Limits { comparisons: 51 + text, covered_text: usize::MAX }; assert_eq!(crate::audit(&doc, limits).expect("within the budget").len(), 1); } @@ -746,14 +748,18 @@ fn copy_restricted_documents_withhold_covered_text() { let findings = audit_redactions(&user).expect("audit must run"); assert_eq!(findings.len(), 1, "the cover is still reported: {findings:?}"); assert_eq!(findings[0].covered_text, ""); - // The output bound counts the text reported, so withheld text costs nothing. - let nothing = crate::Limits { comparisons: usize::MAX, covered_text: 0 }; + // The output bound counts the text reported and the finding's record, so withheld text + // costs only the record. + let record = std::mem::size_of::(); + let nothing = crate::Limits { comparisons: usize::MAX, covered_text: record }; assert_eq!(crate::audit(&user, nothing).expect("withheld text is not output").len(), 1); + let none = crate::Limits { covered_text: record - 1, ..nothing }; + assert!(matches!(crate::audit(&user, none), Err(crate::AuditError::TooMuchOutput))); let owner = Document::open_with_password(bytes, Some("owner")).expect("open"); let findings = audit_redactions(&owner).expect("audit must run"); assert_eq!(findings.len(), 1, "{findings:?}"); assert_eq!(findings[0].covered_text, "SECRET DATA 123"); - let exact = crate::Limits { comparisons: usize::MAX, covered_text: "SECRET DATA 123".len() }; + let exact = crate::Limits { comparisons: usize::MAX, covered_text: "SECRET DATA 123".len() + record }; assert!(crate::audit(&owner, exact).is_ok()); let short = crate::Limits { covered_text: exact.covered_text - 1, ..exact }; assert!(matches!(crate::audit(&owner, short), Err(crate::AuditError::TooMuchOutput))); @@ -820,3 +826,52 @@ fn form_entries_past_the_page_allowance_fail_the_audit() { let page: Dict = [(b"Contents".to_vec(), Object::Ref(draws)), (b"Resources".to_vec(), Object::Dict(resources))].into_iter().collect(); assert!(matches!(crate::cover::filled_rects(&doc, &page), Err(crate::AuditError::TooManyForms))); } + +/// Copying a covered line's text walks all of it, padding included, so a long padded line under +/// many covers costs its bytes once per cover, not one run per cover (CodeRabbit). +#[test] +fn covered_text_bytes_count_against_the_comparison_bound() { + // One run: 20 KiB of spaces around a word, which trims to the word alone. + let mut content = b"BT /F1 24 Tf 100 700 Td (".to_vec(); + content.extend_from_slice(&[b' '; 10_000]); + content.extend_from_slice(b"SECRET"); + content.extend_from_slice(&[b' '; 10_000]); + content.extend_from_slice(b") Tj ET\n0 g\n"); + for _ in 0..10 { + content.extend_from_slice(b"-1 688 1000000 32 re f\n"); + } + let doc = open(one_page(&content, "")); + let lines = pdfcraft_edit::glyph_text_lines(&doc, &pdfcraft_model::pages(&doc)[0]).expect("text"); + assert_eq!(lines.len(), 1); + let bytes = lines[0].text.len(); + assert!(bytes > 20_000, "{bytes} bytes of text"); + // Each cover: one comparison for the line, plus its bytes when it is hidden. + let exact = crate::Limits { comparisons: 10 * (1 + bytes / crate::TEXT_BYTES_PER_COMPARISON), covered_text: usize::MAX }; + let findings = crate::audit(&doc, exact).expect("within the budget"); + assert_eq!(findings.len(), 10, "{findings:?}"); + assert!(findings.iter().all(|f| f.covered_text == "SECRET"), "{findings:?}"); + let short = crate::Limits { comparisons: exact.comparisons - 1, ..exact }; + assert!(matches!(crate::audit(&doc, short), Err(crate::AuditError::TooManyComparisons))); +} + +/// One annotation list shared by many pages makes a finding on each: every finding's record +/// counts against the output bound, text or no text (CodeRabbit). +#[test] +fn every_finding_record_counts_against_the_output_bound() { + let content = b"BT /F1 24 Tf 100 700 Td (SECRET) Tj ET\n"; + let mut b = Builder::new(); + b.add("<< /Type /Catalog /Pages 2 0 R >>"); + b.add("<< /Type /Pages /Kids [3 0 R 7 0 R 8 0 R] /Count 3 >>"); + b.add("<< /Type /Page /Parent 2 0 R /MediaBox [0 0 612 792] /Contents 4 0 R /Resources << /Font << /F1 5 0 R >> >> /Annots 6 0 R >>"); + b.add_stream(content); + b.add(FONT); + b.add("[<< /Type /Annot /Subtype /Redact /Rect [95 685 200 725] >>]"); + b.add("<< /Type /Page /Parent 2 0 R /MediaBox [0 0 612 792] /Contents 4 0 R /Resources << /Font << /F1 5 0 R >> >> /Annots 6 0 R >>"); + b.add("<< /Type /Page /Parent 2 0 R /MediaBox [0 0 612 792] /Contents 4 0 R /Resources << /Font << /F1 5 0 R >> >> /Annots 6 0 R >>"); + let doc = open(b.build()); + let one = "SECRET".len() + std::mem::size_of::(); + let exact = crate::Limits { comparisons: usize::MAX, covered_text: 3 * one }; + assert_eq!(crate::audit(&doc, exact).expect("within the budget").len(), 3); + let short = crate::Limits { covered_text: 3 * one - 1, ..exact }; + assert!(matches!(crate::audit(&doc, short), Err(crate::AuditError::TooMuchOutput))); +} diff --git a/crates/automation/README.md b/crates/automation/README.md index 92fd2775c9..8ffa2d0b3e 100644 --- a/crates/automation/README.md +++ b/crates/automation/README.md @@ -5,6 +5,8 @@ Agent control for PdfCraft: a headless tool table over the engine, and an opt-in - **Layer:** L7 (architecture §13), but headless. It depends on `engine`, `render` and `organize`, never on a UI toolkit. - **Status:** over a hundred tools; `pdfcraft-cli tools` lists the current set with their schemas (the count isn't repeated here, so it can't go stale). They cover inspection, rendering, text, page edits and organizing, page labels, bookmarks, comments and their review, form filling and authoring (fields, properties, scripts, data exchange, detection), redaction and sanitizing, password protection and signatures, calibrated 2D measurements and CSV export, adding text, images, links and stamps, optimizing, OCR, printing, export, metadata, undo/redo, save, combine, extract and split. Comment tools take geometry in the same top-left-origin points as everything else, and `comment_add` can mark text by searching for it (`find`). The MCP server also serves the open documents as resources, page images included. The running app's UI is driven separately, through the `ui.*` control channel in `pdfcraft-ui-egui`. +`fill_sign_add` text accepts line breaks, including blank lines. Its typewriter box grows to hold all wrapped rows, and saving/reopening preserves the contents and appearance. + ## API ```rust diff --git a/crates/automation/src/a11y/documents.rs b/crates/automation/src/a11y/documents.rs index e52768d535..5ae3d4fe46 100644 --- a/crates/automation/src/a11y/documents.rs +++ b/crates/automation/src/a11y/documents.rs @@ -6,6 +6,13 @@ impl Automation { let ext = path.extension().map(|e| e.to_string_lossy().into_owned()).unwrap_or_default(); let format = pdfcraft_engine::compare::OfficeFormat::from_extension(&ext) .ok_or_else(|| ToolError::InvalidArgs(format!("unsupported extension {ext:?} (docx, pptx, html, rtf or md)")))?; + let html_mode = a.opt_str("html_mode")?.unwrap_or("rich"); + let format = match (format, html_mode) { + (pdfcraft_engine::compare::OfficeFormat::Html, "rich") => pdfcraft_engine::compare::OfficeFormat::Html, + (pdfcraft_engine::compare::OfficeFormat::Html, "simple") => pdfcraft_engine::compare::OfficeFormat::HtmlSimple, + (_, "rich") => format, + (_, _) => return Err(ToolError::InvalidArgs("html_mode is only available for HTML exports (rich or simple)".into())), + }; let export = self.doc_to_copy(a)?.export_office_checked(format); write_atomic(&path, &export.bytes)?; // Text left out to keep a hostile page bounded is said, not silent (#3120). @@ -15,7 +22,7 @@ impl Automation { if !export.truncated_pages.is_empty() { use pdfcraft_engine::compare::{MAX_FORM_DEPTH, MAX_FORM_VISITS}; out["warnings"] = json!([format!( - "forms nested more than {MAX_FORM_DEPTH} deep, or past the first {MAX_FORM_VISITS} forms of a page (forms the page draws itself count too), were left out on the pages in truncated_pages: their text and images are missing from the export, although the viewer may still show them" + "pictures past what one export may hold or decode, or forms nested more than {MAX_FORM_DEPTH} deep, or past the first {MAX_FORM_VISITS} forms of a page (forms the page draws itself count too), were left out on the pages in truncated_pages: their text and images are missing from the export, although the viewer may still show them" )]); } Ok(out) diff --git a/crates/automation/src/bates.rs b/crates/automation/src/bates.rs new file mode 100644 index 0000000000..3cd1d7849e --- /dev/null +++ b/crates/automation/src/bates.rs @@ -0,0 +1,214 @@ +use std::io::Write; + +use pdfcraft_engine::{Edit, HeaderFooter}; +use serde_json::{Value, json}; + +use super::error::{Result, ToolError, failed}; +use super::json::Args; +use super::paths::read_input; +use super::{Arc, Automation, Path, PathBuf}; + +struct FilePlan { + input: String, + source: PathBuf, + password: Option, + output: PathBuf, + pages: usize, + first: u64, + last: u64, +} + +impl Automation { + pub(crate) fn doc_bates_multi(&mut self, args: &Args) -> Result { + let files = args.0.get("files").and_then(Value::as_array).ok_or_else(|| ToolError::InvalidArgs("files must be an array".into()))?; + if files.is_empty() || files.len() > 1000 { + return Err(ToolError::InvalidArgs("files must contain 1 to 1000 entries".into())); + } + let start = match args.0.get("start_number") { + None | Some(Value::Null) => 1, + Some(value) => value + .as_u64() + .filter(|n| *n >= 1) + .ok_or_else(|| ToolError::InvalidArgs("start_number must be a whole number of at least 1".into()))?, + }; + let digits = args.opt_int("digits")?.unwrap_or(6); + let digits = + u8::try_from(digits).ok().filter(|d| (1..=12).contains(d)).ok_or_else(|| ToolError::InvalidArgs("digits must be from 1 to 12".into()))?; + let prefix = args.opt_str("prefix")?.unwrap_or(""); + let suffix = args.opt_str("suffix")?.unwrap_or(""); + // `#` separates the token's fields and `>>` ends it: either would cut the token short. + if prefix.len() > 128 || suffix.len() > 128 || [prefix, suffix].iter().any(|s| s.contains('#') || s.contains(">>")) { + return Err(ToolError::InvalidArgs("prefix and suffix must be at most 128 bytes and cannot contain # or >>".into())); + } + let dry_run = args.opt_bool("dry_run")?.unwrap_or(false); + + // Resolve and reserve the complete path list before opening or writing anything. + let mut sources = Vec::with_capacity(files.len()); + let mut targets = Vec::with_capacity(files.len()); + let mut passwords = Vec::with_capacity(files.len()); + for entry in files { + let input = entry + .get("input") + .and_then(Value::as_str) + .filter(|s| !s.is_empty()) + .ok_or_else(|| ToolError::InvalidArgs("each file needs a non-empty input path".into()))?; + let output = entry + .get("output") + .and_then(Value::as_str) + .filter(|s| !s.is_empty()) + .ok_or_else(|| ToolError::InvalidArgs("each file needs a non-empty output path".into()))?; + let source = self.resolve(input, false)?; + let target = self.resolve(output, true)?; + if target.exists() { + return Err(failed(format!("output already exists; refusing to replace it: {output}"))); + } + let parent = target.parent().ok_or_else(|| failed(format!("output has no parent directory: {output}")))?; + if !parent.is_dir() { + return Err(failed(format!("output directory does not exist: {}", parent.display()))); + } + sources.push((input.to_string(), source)); + targets.push((output.to_string(), target)); + passwords.push(entry.get("password").and_then(Value::as_str).map(str::to_owned)); + } + let input_paths: std::collections::HashSet<_> = sources.iter().map(|(_, path)| path.clone()).collect(); + let mut output_paths = std::collections::HashSet::new(); + for (name, path) in &targets { + if input_paths.contains(path) { + return Err(failed(format!("output {name} names an input file; choose a separate output path"))); + } + if !output_paths.insert(path.clone()) { + return Err(failed(format!("two files use the same output path: {name}"))); + } + } + + let mut plans = Vec::with_capacity(files.len()); + let mut next = start; + let mut input_bytes = 0u64; + for (index, ((input_name, input_path), (_, output_path))) in sources.iter().zip(&targets).enumerate() { + let size = std::fs::metadata(input_path).map_err(failed)?.len(); + input_bytes = input_bytes + .checked_add(size) + .filter(|total| *total <= 512 * 1024 * 1024) + .ok_or_else(|| failed("combined Bates input exceeds the 512 MiB safety limit"))?; + let bytes = read_input(input_path)?; + input_bytes = input_bytes + .saturating_sub(size) + .checked_add(u64::try_from(bytes.len()).unwrap_or(u64::MAX)) + .filter(|total| *total <= 512 * 1024 * 1024) + .ok_or_else(|| failed("combined Bates input exceeds the 512 MiB safety limit"))?; + let display_name = input_path.file_name().map(|n| n.to_string_lossy().into_owned()).unwrap_or_default(); + let password = passwords.get(index).and_then(Option::as_deref); + let id = self.session.open(display_name, Some(input_path.to_string_lossy().into_owned()), Arc::new(bytes), password).map_err(failed)?; + let pages = + self.session.get(id).map(|doc| doc.info.pages.len()).ok_or_else(|| failed("opened document disappeared during Bates preflight"))?; + self.session.close(id); + if pages == 0 { + return Err(failed(format!("{input_name} has no pages to number"))); + } + let count = u64::try_from(pages).map_err(|_| failed(format!("page count is too large for {input_name}")))?; + let last = next.checked_add(count.saturating_sub(1)).ok_or_else(|| failed(format!("Bates number range overflows for {input_name}")))?; + plans.push(FilePlan { + input: input_name.clone(), + source: input_path.clone(), + password: passwords.get(index).cloned().flatten(), + output: output_path.clone(), + pages, + first: next, + last, + }); + if index + 1 < sources.len() { + next = last.checked_add(1).ok_or_else(|| failed(format!("Bates sequence overflows after {input_name}")))?; + } + } + + let intervals: Vec = plans + .iter() + .zip(&targets) + .map(|(p, (name, _))| json!({"input":p.input,"output":name,"pages":p.pages,"first":p.first,"last":p.last})) + .collect(); + if dry_run { + return Ok(json!({"dry_run":true,"files":intervals})); + } + + let mut staged = Vec::with_capacity(plans.len()); + let mut results = Vec::with_capacity(plans.len()); + let mut output_bytes = 0u64; + for plan in &plans { + let source_bytes = match read_input(&plan.source) { + Ok(bytes) => bytes, + Err(error) => { + results.push(json!({"input":plan.input,"output":plan.output,"status":"error","pages":plan.pages,"first":plan.first,"last":plan.last,"error":error.to_string()})); + continue; + } + }; + let name = plan.source.file_name().map(|n| n.to_string_lossy().into_owned()).unwrap_or_default(); + let id = match self.session.open(name, Some(plan.source.to_string_lossy().into_owned()), Arc::new(source_bytes), plan.password.as_deref()) + { + Ok(id) => id, + Err(error) => { + results.push(json!({"input":plan.input,"output":plan.output,"status":"error","pages":plan.pages,"first":plan.first,"last":plan.last,"error":error.to_string()})); + continue; + } + }; + if self.session.get(id).is_none_or(|doc| doc.info.pages.len() != plan.pages) { + self.session.close(id); + results.push(json!({"input":plan.input,"output":plan.output,"status":"error","pages":plan.pages,"first":plan.first,"last":plan.last,"error":"input changed after preflight; page count differs"})); + continue; + } + let template = format!("<>", plan.first); + let mut settings = HeaderFooter::default(); + settings.text[4] = template; + let pages: Vec = (0..plan.pages).collect(); + let applied = self.session.apply(id, Edit::AddHeaderFooter { pages, settings, replace: false }); + let result = applied.and_then(|()| self.session.save_full_bytes(id)); + match result { + Ok(bytes) => { + let total = output_bytes.saturating_add(u64::try_from(bytes.len()).unwrap_or(u64::MAX)); + if total > 512 * 1024 * 1024 { + results.push(json!({"input":plan.input,"output":plan.output,"status":"error","pages":plan.pages,"first":plan.first,"last":plan.last,"error":"combined Bates output exceeds the 512 MiB safety limit"})); + } else { + output_bytes = total; + staged.push((plan.output.clone(), bytes)); + } + } + Err(error) => results.push(json!({"input":plan.input,"output":plan.output,"status":"error","pages":plan.pages,"first":plan.first,"last":plan.last,"error":error.to_string()})), + } + self.session.close(id); + } + for (path, bytes) in staged { + match publish_new(&path, &bytes) { + Ok(()) => { + let plan = plans.iter().find(|p| p.output == path); + if let Some(plan) = plan { + results.push(json!({"input":plan.input,"output":path,"status":"ok","first":plan.first,"last":plan.last,"pages":plan.pages})); + } + } + Err(error) => { + let plan = plans.iter().find(|p| p.output == path); + if let Some(plan) = plan { + results.push(json!({"input":plan.input,"output":path,"status":"error","pages":plan.pages,"first":plan.first,"last":plan.last,"error":error.to_string()})); + } + } + } + } + results.sort_by_key(|result| plans.iter().position(|plan| result["output"] == json!(plan.output)).unwrap_or(usize::MAX)); + let completed = results.iter().filter(|r| r["status"] == "ok").count(); + let failed_count = results.len().saturating_sub(completed); + Ok(json!({"dry_run":false,"completed":completed,"failed":failed_count,"files":results})) + } +} + +/// Publish a PDF atomically while refusing a target created by another process after preflight. +fn publish_new(path: &Path, bytes: &[u8]) -> Result<()> { + let parent = path.parent().ok_or_else(|| failed("output has no parent directory"))?; + let mut temp = tempfile::NamedTempFile::new_in(parent).map_err(failed)?; + temp.write_all(bytes).map_err(failed)?; + temp.as_file().sync_all().map_err(failed)?; + temp.persist_noclobber(path).map(|_| ()).map_err(|error| { + if error.error.kind() == std::io::ErrorKind::AlreadyExists { + failed(format!("output appeared after preflight; refusing to replace it: {}", path.display())) + } else { + failed(error.error) + } + }) +} diff --git a/crates/automation/src/comments.rs b/crates/automation/src/comments.rs index 5dbd5b8542..ae46be87d0 100644 --- a/crates/automation/src/comments.rs +++ b/crates/automation/src/comments.rs @@ -539,8 +539,10 @@ impl Automation { return self.apply(a, edit); } let text_at = |t: &str| { - let w = (pdfcraft_engine::annot_text::text_width(t, size) + 8.0).clamp(20.0, 600.0); - let h = size * 1.2 + 6.0; + let longest = t.lines().map(|line| pdfcraft_engine::annot_text::text_width(line, size)).fold(0.0, f64::max); + let w = (longest + 8.0).clamp(20.0, 600.0); + let rows = pdfcraft_engine::annot_text::wrap(t, size, w - 4.0).len().max(1); + let h = rows as f64 * size * 1.2 + 6.0; let rect = pdfcraft_engine::text_box_at(i64::from(info.rotation), at, w, h).unwrap_or([at[0], at[1] - h, at[0] + w, at[1]]); Shape::Typewriter { rect, font_size: size } }; diff --git a/crates/automation/src/dispatch.rs b/crates/automation/src/dispatch.rs index 8bc23ff280..f3c51d22e0 100644 --- a/crates/automation/src/dispatch.rs +++ b/crates/automation/src/dispatch.rs @@ -53,6 +53,7 @@ impl Automation { tools::check_args(def, args)?; let a = Args(args); let out = match name { + "doc_bates_multi" => self.doc_bates_multi(&a)?, "doc_open" => self.doc_open(&a)?, "doc_batch" => self.doc_batch(&a)?, "doc_list" => json!({ "documents": self.session.docs().iter().map(summary).collect::>() }), @@ -323,13 +324,13 @@ impl Automation { let id = self.doc(&a)?.id; let before = self.doc(&a)?.bytes.len(); let path = self.resolve(a.str("path")?, true)?; - let (bytes, merged) = self.session.reduced_bytes(id).map_err(failed)?; + let (bytes, merged, images_refused) = self.session.reduced_bytes(id).map_err(failed)?; // As in the app, a copy that isn't smaller is not written (#490). let written = bytes.len() < before; if written { write_atomic(&path, &bytes)?; } - json!({ "path": path.to_string_lossy(), "written": written, "bytes_before": before, "bytes_after": bytes.len(), "merged_objects": merged }) + json!({ "path": path.to_string_lossy(), "written": written, "bytes_before": before, "bytes_after": bytes.len(), "merged_objects": merged, "images_refused": images_refused }) } "doc_optimize" => self.doc_optimize(&a)?, "doc_initial_view" => self.doc_initial_view(&a)?, diff --git a/crates/automation/src/documents.rs b/crates/automation/src/documents.rs index 859c92da48..979b041a73 100644 --- a/crates/automation/src/documents.rs +++ b/crates/automation/src/documents.rs @@ -410,6 +410,7 @@ impl Automation { "images": o.images, "images_resampled": o.images_resampled, "images_recompressed": o.images_recompressed, + "images_refused": o.images_refused, "image_bytes_before": o.image_bytes_before, "image_bytes_after": o.image_bytes_after, "thumbnails": o.thumbnails, diff --git a/crates/automation/src/lib.rs b/crates/automation/src/lib.rs index f1910867c9..5bcb032fce 100644 --- a/crates/automation/src/lib.rs +++ b/crates/automation/src/lib.rs @@ -16,6 +16,7 @@ mod a11y; mod batch; +mod bates; mod comments; mod content; mod conventions; diff --git a/crates/automation/src/redact.rs b/crates/automation/src/redact.rs index e662bcac19..a146f3f8ff 100644 --- a/crates/automation/src/redact.rs +++ b/crates/automation/src/redact.rs @@ -201,8 +201,8 @@ impl Automation { } pub(crate) fn doc_remove_hidden(&mut self, a: &Args) -> Result { - let edit = match a.get("categories") { - None => Edit::Sanitize, + let which = match a.get("categories") { + None => None, Some(_) => { let which = a .strs("categories")? @@ -212,10 +212,24 @@ impl Automation { if which.is_empty() { return Err(ToolError::InvalidArgs("categories is empty".into())); } + Some(which) + } + }; + // One scan, for this check and for what was removed. The removal refuses when it counts + // every listed category as 0 (an AcroForm with no fields counts 1), with an error about + // redaction marks; this reads the same scan, so it refuses exactly then. A document that + // can't be edited has no scan: `apply` says why. + let info = self.doc(a)?.hidden_info(); + let edit = match which { + None => Edit::Sanitize, + Some(which) => { + if !info.is_empty() && which.iter().all(|h| info.iter().find(|c| c.0 == *h).is_none_or(|c| c.1 == 0)) { + return Err(failed("nothing to remove: the listed categories hold nothing (see doc_hidden_info)")); + } Edit::RemoveHidden { which } } }; - let before: usize = self.doc(a)?.hidden_info().iter().map(|c| c.1).sum(); + let before: usize = info.iter().map(|c| c.1).sum(); let mut out = self.apply(a, edit)?; let after: usize = self.doc(a)?.hidden_info().iter().map(|c| c.1).sum(); out["removed"] = json!(before.saturating_sub(after)); diff --git a/crates/automation/src/tools.rs b/crates/automation/src/tools.rs index 866138899d..4672e49886 100644 --- a/crates/automation/src/tools.rs +++ b/crates/automation/src/tools.rs @@ -121,6 +121,14 @@ pub fn tools() -> Vec { let save_out = json!({ "type": "string", "description": "File to write. Omit to open the result as a new unsaved document instead." }); let open = json!({ "type": "boolean", "description": "Also open the result as a new document (default: only when out is omitted)." }); vec![ + t("doc_bates_multi", "Add Bates numbering across files", "Apply one consecutive Bates sequence to an ordered list of PDFs. Each file entry has input and output paths and an optional open or permissions password. The operation first validates every input/output and computes inclusive numeric intervals; dry_run returns that allocation without writing. Existing output files are never replaced. On application, files that cannot be edited or saved are reported individually and later files continue.") + .destructive() + .with(schema(json!({ + "files": {"type":"array","minItems":1,"maxItems":1000,"description":"PDFs in Bates sequence order.","items":{"type":"object","properties":{"input":{"type":"string","minLength":1,"description":"Input PDF path."},"output":{"type":"string","minLength":1,"description":"New output PDF path; must not exist."},"password":{"type":"string","description":"Open or permissions password, if needed."}},"required":["input","output"],"additionalProperties":false}}, + "start_number": {"type":"integer","minimum":1,"description":"First number in the sequence (default 1)."}, "digits": {"type":"integer","minimum":1,"maximum":12,"description":"Zero-padded number width (default 6)."}, + "prefix": {"type":"string","maxLength":128,"description":"Text before the number: at most 128 UTF-8 bytes, without # or >>."}, "suffix": {"type":"string","maxLength":128,"description":"Text after the number: at most 128 UTF-8 bytes, without # or >>."}, + "dry_run": {"type":"boolean","description":"Return each file's inclusive number interval without writing (default false)."} + }), &["files"])), t("doc_batch", "Process files and folders", "Run convert, ocr and/or optimize over files and folders, one file at a time. recursive defaults to false. Preserve paths relative to each selected folder inside out_dir; duplicate inputs run once. Skip unsupported files, links and the output subtree. Existing outputs receive numbered names and are never replaced. Continue after per-file errors unless stop_on_error is true. Return completed/failed/skipped counts and per-file results. Discovery is bounded to 10000 entries and 64 folder levels. Convert must be first; each step can appear once. OCR uses installed models. Optimize uses Reduce File Size settings, optionally overriding target ppi (threshold 1.5 times ppi; black-and-white images go to the larger of ppi and 300) and JPEG quality; a larger candidate keeps the original bytes. Sources and open documents are unchanged.") .with(schema(json!({ "paths": {"type":"array","items":{"type":"string"},"minItems":1,"maxItems":1000}, @@ -562,7 +570,7 @@ pub fn tools() -> Vec { t( "doc_remove_hidden", "Remove hidden information / Sanitize", - "Remove the listed categories (see doc_hidden_info), or every category when none are listed (Sanitize Document). Form fields are flattened so their values stay visible. The next save rewrites the whole file. Undoable until saved.", + "Remove the listed categories (see doc_hidden_info), or every category when none are listed (Sanitize Document). Fails when the listed categories hold nothing. Form fields are flattened so their values stay visible. The next save rewrites the whole file. Undoable until saved.", ) .destructive() .with(schema( @@ -1194,9 +1202,9 @@ pub fn tools() -> Vec { json!({ "doc": doc(), "field": { "type": "string" }, "event": { "type": "string", "enum": ["keystroke", "format", "validate", "calculate", "mouse_up"] }, "script": { "type": "string" } }), &["doc", "field", "event"], )), - t("doc_export_office", "Export to Word, PowerPoint, HTML, RTF or Markdown", "Export a PDF ▸ Word (.docx), PowerPoint (.pptx, one slide per page), HTML (.html, one file with images inline), RTF (.rtf) or Markdown (.md or .markdown: pipe tables, images left out), chosen by path's extension: text, headings, bold and italic. Word uses borderless inferred tables and positioned editable shapes on pages with artwork, rotated or large text; each source page retains its size. Font matching and vector graphics remain limited. Export reads forms 50 deep and up to 50 000 a page, counting forms the page draws itself. Pages that go past either limit are listed in truncated_pages, with a warning; the text and images of the forms left out are missing.") + t("doc_export_office", "Export to Word, PowerPoint, HTML, RTF or Markdown", "Export a PDF ▸ Word (.docx), PowerPoint (.pptx, one slide per page), HTML (.html, one file with images inline), RTF (.rtf) or Markdown (.md or .markdown: pipe tables, images left out), chosen by path's extension: text, headings, bold and italic. HTML uses rich styling by default; set html_mode to simple for CSS-free headings, paragraphs, emphasis and tables. Simple HTML keeps text and inline images but omits colour and layout styling. Word uses borderless inferred tables and positioned editable shapes on pages with artwork, rotated or large text; each source page retains its size. Font matching and vector graphics remain limited. Export reads forms 50 deep and up to 50 000 a page, counting forms the page draws itself. Pages that go past either limit, or that have pictures past what one export may hold or decode, are listed in truncated_pages, with a warning; what was left out is missing.") .cmd("export.docx") - .with(schema(json!({ "doc": doc(), "path": { "type": "string" } }), &["doc", "path"])), + .with(schema(json!({ "doc": doc(), "path": { "type": "string" }, "html_mode": { "type": "string", "enum": ["rich", "simple"], "default": "rich" } }), &["doc", "path"])), t("pdfa_verify", "Verify PDF/A", "Standards ▸ Verify PDF/A compliance: the PDF/A-2b or 3b rules the document breaks (ISO 19005 clause, message, page, whether Save as PDF/A can fix it), plus what it declares.") .ro() .cmd("standards.pdfa") @@ -1281,7 +1289,7 @@ pub fn tools() -> Vec { .ro() .cmd("ocr.recognize") .with(schema(json!({}), &[])), - t("doc_export_all_images", "Export all images", "Write the images that pages use into a folder (`_Page__Image_.jpg|png`, n zero-padded to the page count's digits), each once: JPEG images unchanged, others as PNG with their soft mask as alpha. min_size skips images with fewer pixels on their shorter side. Images that can't be decoded yet (JPEG 2000, separations) are listed under skipped. Includes unsaved edits.") + t("doc_export_all_images", "Export all images", "Write the images that pages use into a folder (`_Page__Image_.jpg|png`, n zero-padded to the page count's digits), each once: JPEG images unchanged, others as PNG with their soft mask as alpha. min_size skips images with fewer pixels on their shorter side. Images that can't be decoded yet (JPEG 2000, separations), or past what one export may decode or hold, are listed under skipped, with the reason. Includes unsaved edits.") .cmd("export.all_images") .with(schema( json!({ @@ -1340,7 +1348,7 @@ pub fn tools() -> Vec { }), &["from"], )), - t("doc_reduce", "Reduce file size", "Write a smaller copy of the document to `path` with Acrobat's Reduce File Size choices: colour and grey images above 225 ppi downsampled to 150 ppi and JPEG-compressed (medium quality), black-and-white images averaged down to 300 ppi above 450 ppi and each stored as CCITT Group 4 (or 1-bit Flate, once resampled or packed from more bits) whenever that is smaller, thumbnails dropped, identical fonts and images merged, unused objects dropped, compressed object streams. If the copy wouldn't be smaller, nothing is written and `written` is false. The open document is unchanged.") + t("doc_reduce", "Reduce file size", "Write a smaller copy of the document to `path` with Acrobat's Reduce File Size choices: colour and grey images above 225 ppi downsampled to 150 ppi and JPEG-compressed (medium quality), black-and-white images averaged down to 300 ppi above 450 ppi and each stored as CCITT Group 4 (or 1-bit Flate, once resampled or packed from more bits) whenever that is smaller, thumbnails dropped, identical fonts and images merged, unused objects dropped, compressed object streams. If the copy wouldn't be smaller, nothing is written and `written` is false. Images past what one run may decode stay as they are, counted in images_refused; streams it only stores with Flate past that stay LZW, uncounted. The open document is unchanged.") .cmd("optimize.reduce") .with(schema(json!({ "doc": doc(), "path": { "type": "string" } }), &["doc", "path"])), t("doc_initial_view", "Initial view", "Read or change how the document opens (Document Properties ▸ Initial View) and its reading options: navigation (page, bookmarks, pages, attachments, layers), layout (default, single, continuous, two_up, two_up_continuous, two_up_cover, two_up_continuous_cover), magnification (default, actual, fit_page, fit_width, fit_height, fit_visible, or a percentage), page, window options (fit_window, center_window, full_screen, display_title), interface options (hide_menubar, hide_toolbar, hide_window_ui), language and binding (left, right). Only the given ones change; returns the result. Undoable.").with(schema( @@ -1451,7 +1459,7 @@ pub fn tools() -> Vec { .with(schema(json!({ "doc": doc() }), &["doc"])), t("doc_open_revision", "Open a revision", "Open saved revision `revision` (1 = the oldest) of a document as a new, unsaved document, to see the file as it was then.") .with(schema(json!({ "doc": doc(), "revision": { "type": "integer", "minimum": 1 } }), &["doc", "revision"])), - t("doc_optimize", "Optimize PDF", "Write an optimized copy to `path` (Acrobat's PDF Optimizer). preset: standard (default; Reduce File Size's choices) or mobile (images to 96 ppi above 144, JPEG high quality); the options below change it. compatibility: retain (default; keeps the document's version, or 1.5 when object streams are written), 1.4, 1.5, 1.6, 1.7 or 2.0. merge_fragments (default true) first puts a page picture drawn as many stacked image strips (as some PDF printers write it) back together into one image, so it can be resampled (merged_images, fragments_merged). color / gray: { downsample, ppi, above_ppi, compression: jpeg|zip|retain, quality 1–100 } (defaults: downsample to 150 ppi above 225, JPEG 60). mono: { downsample, ppi, above_ppi, compression: ccitt_g4|jbig2|retain } for black-and-white images and image masks (default: averaged down to 300 ppi above 450 ppi, counted in images_resampled; stored losslessly as CCITT Group 4 or JBIG2 (or 1-bit Flate, once resampled or packed from more bits) when that is smaller, Group 3 fax images, JBIG2 images, black-and-white RGB and indexed images using only palette entries 0 and 1 among them, counted in images_recompressed; retain resamples only, a CCITT image staying CCITT, a JBIG2 image JBIG2 and any other becoming Flate). Images are measured where pages draw them and replaced only when smaller. discard_*: thumbnails (default true), alternate_images (true), tags, print_settings; flate_unencoded (true); object_streams (default true; always off for 1.4); lzw_to_flate (true) decodes LZW streams and stores them with Flate instead, leaving any it cannot decode unchanged (lzw_streams counts the streams converted); remove_invalid_links and remove_unreferenced_dests (true); images and forms the pages list but never draw are always dropped (unused_xobjects). discard: Remove Hidden Information categories (metadata, attachments, comments, form-fields, hidden-text, hidden-layers, bookmarks, links-actions-scripts, private-data). Signed documents are refused. The open document is unchanged.") + t("doc_optimize", "Optimize PDF", "Write an optimized copy to `path` (Acrobat's PDF Optimizer). preset: standard (default; Reduce File Size's choices) or mobile (images to 96 ppi above 144, JPEG high quality); the options below change it. compatibility: retain (default; keeps the document's version, or 1.5 when object streams are written), 1.4, 1.5, 1.6, 1.7 or 2.0. merge_fragments (default true) first puts a page picture drawn as many stacked image strips (as some PDF printers write it) back together into one image, so it can be resampled (merged_images, fragments_merged). color / gray: { downsample, ppi, above_ppi, compression: jpeg|zip|retain, quality 1–100 } (defaults: downsample to 150 ppi above 225, JPEG 60). mono: { downsample, ppi, above_ppi, compression: ccitt_g4|jbig2|retain } for black-and-white images and image masks (default: averaged down to 300 ppi above 450 ppi, counted in images_resampled; stored losslessly as CCITT Group 4 or JBIG2 (or 1-bit Flate, once resampled or packed from more bits) when that is smaller, Group 3 fax images, JBIG2 images, black-and-white RGB and indexed images using only palette entries 0 and 1 among them, counted in images_recompressed; retain resamples only, a CCITT image staying CCITT, a JBIG2 image JBIG2 and any other becoming Flate). Images past what one run may decode stay as they are, counted in images_refused; streams it only stores with Flate past that stay LZW, uncounted. Images are measured where pages draw them and replaced only when smaller. discard_*: thumbnails (default true), alternate_images (true), tags, print_settings; flate_unencoded (true); object_streams (default true; always off for 1.4); lzw_to_flate (true) decodes LZW streams and stores them with Flate instead, leaving any it cannot decode unchanged (lzw_streams counts the streams converted); remove_invalid_links and remove_unreferenced_dests (true); images and forms the pages list but never draw are always dropped (unused_xobjects). discard: Remove Hidden Information categories (metadata, attachments, comments, form-fields, hidden-text, hidden-layers, bookmarks, links-actions-scripts, private-data). Signed documents are refused. The open document is unchanged.") .cmd("optimize.advanced") .with(schema( json!({ diff --git a/crates/automation/tests/it/automation.rs b/crates/automation/tests/it/automation.rs index 0d73dbb900..13f9af4371 100644 --- a/crates/automation/tests/it/automation.rs +++ b/crates/automation/tests/it/automation.rs @@ -2832,6 +2832,74 @@ fn headers_watermarks_and_backgrounds_through_tools() { assert!(matches!(refused, Err(ToolError::InvalidArgs(e)) if e.contains("Courier"))); } +#[test] +fn bates_numbers_continue_across_files_and_report_preflight_and_permission_failures() { + let dir = workdir("bates-multi"); + let files = json!([ + {"input":"b.pdf","output":"b-numbered.pdf"}, + {"input":"a.pdf","output":"a-numbered.pdf"} + ]); + let mut a = auto(&dir); + let allocation = ok(&mut a, "doc_bates_multi", json!({"files":files,"start_number":50,"dry_run":true})); + assert_eq!(allocation["files"][0]["first"], 50); + assert_eq!(allocation["files"][0]["last"], 51); + assert_eq!(allocation["files"][1]["first"], 52); + assert_eq!(allocation["files"][1]["last"], 54); + assert!(!dir.join("a-numbered.pdf").exists()); + + let applied = ok(&mut a, "doc_bates_multi", json!({"files":files,"start_number":17,"prefix":"CASE-"})); + assert_eq!(applied["completed"], 2); + let mut out = auto(&dir); + let first = ok(&mut out, "doc_open", json!({"path":"a-numbered.pdf"}))["doc"].as_u64().unwrap(); + let second = ok(&mut out, "doc_open", json!({"path":"b-numbered.pdf"}))["doc"].as_u64().unwrap(); + assert!(page_text(&mut out, second)[0].contains("CASE-000017")); + assert!(page_text(&mut out, first)[0].contains("CASE-000019")); + + let overflow = err(&mut a, "doc_bates_multi", json!({"files":[{"input":"b.pdf","output":"overflow.pdf"}],"start_number":u64::MAX})); + assert!(overflow.to_string().contains("overflows")); + assert!(!dir.join("overflow.pdf").exists()); + // A range may end at u64::MAX itself. + let at_max = ok(&mut a, "doc_bates_multi", json!({"files":[{"input":"b.pdf","output":"max.pdf"}],"start_number":u64::MAX - 1,"dry_run":true})); + assert_eq!(at_max["files"][0]["last"], u64::MAX); + for bad in + [json!({"start_number":-3}), json!({"start_number":2.5}), json!({"start_number":"7"}), json!({"prefix":"CASE>>"}), json!({"suffix":"A>>B"})] + { + let mut args = json!({"files":[{"input":"b.pdf","output":"bad.pdf"}],"dry_run":true}); + args.as_object_mut().unwrap().extend(bad.as_object().unwrap().clone()); + assert!(a.call("doc_bates_multi", &args).is_err(), "{bad}"); + } + + use pdfcraft_engine::{Changes, Edit, Protection, Session}; + let mut session = Session::new(); + let id = session.open("locked.pdf", None, std::sync::Arc::new(fixture(1)), None).unwrap(); + session + .apply( + id, + Edit::Protect(Protection { + open_password: Some("open".into()), + permissions_password: Some("owner".into()), + changes: Changes::None, + ..Default::default() + }), + ) + .unwrap(); + std::fs::write(dir.join("locked.pdf"), session.save_bytes(id).unwrap().as_ref()).unwrap(); + let result = ok( + &mut a, + "doc_bates_multi", + json!({"files":[ + {"input":"b.pdf","output":"partial-numbered.pdf"}, + {"input":"locked.pdf","output":"locked-numbered.pdf","password":"open"} + ]}), + ); + assert_eq!(result["completed"], 1); + assert_eq!(result["failed"], 1); + assert_eq!(result["files"][1]["first"], 3); + assert!(result["files"][1]["error"].as_str().unwrap().contains("owner password"), "{result}"); + assert!(dir.join("partial-numbered.pdf").exists()); + assert!(!dir.join("locked-numbered.pdf").exists()); +} + #[test] fn a_shrinking_header_and_footer_moves_the_page_content_out_of_their_way_through_tools() { let dir = workdir("hf-shrink"); @@ -4670,12 +4738,23 @@ fn removing_hidden_information_through_tools() { assert_eq!(r["undo"], "Remove hidden information"); assert_eq!(ok(&mut a, "comment_list", json!({ "doc": doc }))["count"], 0); assert!(count(&ok(&mut a, "doc_hidden_info", json!({ "doc": doc })), "metadata") >= 1, "only comments went"); + // With none left, removing them again says so, and Optimize discarding them still runs. + let again = a.call("doc_remove_hidden", &json!({ "doc": doc, "categories": ["comments"] })); + assert!(matches!(&again, Err(ToolError::Failed(m)) if m.starts_with("nothing to remove")), "{again:?}"); + let optimized = ok(&mut a, "doc_optimize", json!({ "doc": doc, "path": "optimized.pdf", "discard": ["comments", "bookmarks"] })); + assert_eq!(optimized["discarded"], json!([]), "{optimized}"); let r = ok(&mut a, "doc_remove_hidden", json!({ "doc": doc })); assert_eq!(r["undo"], "Sanitize document"); ok(&mut a, "doc_save", json!({ "doc": doc, "path": "clean.pdf" })); let bytes = std::fs::read(dir.join("clean.pdf")).unwrap(); assert!(!bytes.windows(11).any(|w| w == b"Secret plan"), "the old revision is gone"); assert!(matches!(a.call("doc_remove_hidden", &json!({ "doc": doc, "categories": ["nonsense"] })), Err(ToolError::InvalidArgs(_)))); + // A document that can't be edited has no scan: the refusal says why, not that nothing is there. + let junk = [vec![b'x'; 5000], std::fs::read(dir.join("a.pdf")).unwrap()].concat(); + std::fs::write(dir.join("junk.pdf"), junk).unwrap(); + let read_only = ok(&mut a, "doc_open", json!({ "path": "junk.pdf" }))["doc"].as_u64().unwrap(); + let refused = a.call("doc_remove_hidden", &json!({ "doc": read_only, "categories": ["comments"] })); + assert!(matches!(&refused, Err(ToolError::Failed(m)) if m.contains("can't be edited")), "{refused:?}"); } /// A one-page PDF whose text "TOP SECRET" sits under an opaque black rectangle. @@ -6651,10 +6730,12 @@ fn optimizing_through_tools() { let reduced = ok(&mut a, "doc_reduce", json!({ "doc": doc, "path": "reduced.pdf" })); assert!(reduced["bytes_after"].as_u64().unwrap() < reduced["bytes_before"].as_u64().unwrap()); assert_eq!(reduced["written"], true); + assert_eq!(reduced["images_refused"], 0); assert_eq!(std::fs::metadata(dir.join("reduced.pdf")).unwrap().len(), reduced["bytes_after"].as_u64().unwrap()); // Target PDF 1.4 (disables object streams) and PDF 2.0 (with object_streams toggled off). let v14 = ok(&mut a, "doc_optimize", json!({ "doc": doc, "path": "v14.pdf", "compatibility": "1.4" })); + assert_eq!(v14["images_refused"], 0); assert_eq!((v14["pdf_version"].as_str(), v14["object_streams"].as_bool()), (Some("1.4"), Some(false)), "{v14}"); let v14_bytes = std::fs::read(dir.join("v14.pdf")).unwrap(); assert!(v14_bytes.starts_with(b"%PDF-1.4\n") && !v14_bytes.windows(7).any(|w| w == b"/ObjStm")); @@ -7602,6 +7683,17 @@ fn exporting_to_word_html_and_rtf() { } let html = std::fs::read_to_string(dir.join("a.html")).unwrap(); assert!(html.contains("Page 1") && html.contains("Page 3") && html.matches("
").count() == 2, "{html}"); + ok(&mut a, "doc_export_office", json!({ "doc": doc, "path": "simple.html", "html_mode": "simple" })); + let simple_html = std::fs::read_to_string(dir.join("simple.html")).unwrap(); + assert!( + simple_html.contains("Page 1") + && !simple_html.contains("= 66.0, "five text lines need their full height, including blank lines: {:?}", annot.rect); + let pixels = a.render_pixels(doc, 1, 1.0).unwrap(); + // The fixture's page text is at y=150; only the typewriter draws at y=65..80. + assert!( + (65..80).any(|y| (20..80).any(|x| { + let i = (y * pixels.0 as usize + x) * 4; + pixels.2[i..i + 3].iter().all(|v| *v < 100) + })), + "the lower nonempty line appears inside its box" + ); + let rendered = a.call("page_render", &json!({"doc":doc,"page":1,"dpi":72})).unwrap(); + ok(&mut a, "doc_save", json!({"doc":doc,"path":"multiline.pdf"})); + let mut re = auto(&dir); + let reopened = ok(&mut re, "doc_open", json!({"path":"multiline.pdf"}))["doc"].as_u64().unwrap(); + assert_eq!(re.session().get(pdfcraft_engine::DocId(reopened)).unwrap().info.annotations[0].contents.as_deref(), Some(text)); + assert_eq!(rendered, re.call("page_render", &json!({"doc":reopened,"page":1,"dpi":72})).unwrap(), "saved appearances are identical"); + std::fs::remove_dir_all(dir).unwrap(); +} diff --git a/crates/cos/README.md b/crates/cos/README.md index 1e2551036f..7b576f293f 100644 --- a/crates/cos/README.md +++ b/crates/cos/README.md @@ -93,5 +93,8 @@ recognisable in a diff and byte-stable when re-serialized. - Image codecs. `pdfcraft-filters` carries the non-image filters and CCITT fax and JBIG2 decoding (`Document::decoded_image`, a JBIG2 image's `/JBIG2Globals` within `MAX_JBIG2_GLOBALS`, 32 MiB, their filters undone once a document for the images that share them, up to 64 MiB kept, while - their segments are decoded for every image); + their segments are decoded for every image, and `ImageBudget` for an operation over many images, + which share one allowance of decoding, filters, decoders and pixels alike, and are refused past + it: `IMAGE_WORK`, 2^34 steps, or 2 to 5 minutes of JBIG2 and about 1,000 pages scanned at + 300 dpi, plus `IMAGE_WORK_PER_BYTE`, 2^13 steps for each byte of the file); DCT and JPX are still decoded through the bootstrap renderer (`core.image-filters`, M2.6). diff --git a/crates/cos/src/budget.rs b/crates/cos/src/budget.rs index 1ddd42eaf5..376b108be3 100644 --- a/crates/cos/src/budget.rs +++ b/crates/cos/src/budget.rs @@ -6,16 +6,218 @@ use pdfcraft_filters::FilterError; use crate::{CosError, Document, ObjRef, Object, Stream}; +/// The steps of decoding an operation over a document's images may take whatever the file's size. +/// A step of JBIG2 decoding ([`hayro_jbig2::Image::decode_within`]) is about a pixel, and takes 6 to +/// 16 ns, so this is 2 to 5 minutes, and about as long again for what an operation does with the +/// pixels. A page scanned at 300 dpi takes about 17 million, 8.4 for its pixels and that again to +/// decode them, so this alone reads about 1,000 of them. A byte into or out of a filter is a step +/// too, and takes less: 3 ns at most, or up to 19 ns through a predictor on samples of a bit. +const IMAGE_WORK: u64 = 1 << 34; +/// The steps each byte of the file adds to [`IMAGE_WORK`], so that a long scan is read whole: such a +/// page pays for itself with about 2 KB of the file, about the smallest a page of text is stored +/// in, and a stream of any filter this reads can be decoded about 8 times at Flate's best, 1,032 to +/// one. So what a hostile file can ask for grows with its length, by about 14 minutes for 10 MB. +const IMAGE_WORK_PER_BYTE: u64 = 1 << 13; + /// Decoded bytes one page's content walk may produce in all: its `/Contents` streams and every /// form XObject it enters, each occurrence counted again. pub const MAX_PAGE_DECODED: usize = 256 << 20; /// Form XObjects one page's content walk may enter, each entry counted again. pub const MAX_PAGE_FORMS: usize = 50_000; +/// The steps a sample of a JPEG costs: a few bytes can hold a page of one grey, and decoding, +/// resampling and storing it took about 20 to 45 ns a sample. +const JPEG_WORK: u64 = 2; +/// The steps a byte of a JPEG costs to read: its tables took 24 ns a byte before a size was known, +/// and images can share one, so reading it again for each has to count. +const JPEG_READ_WORK: u64 = 4; + /// A stream decode within a byte bound, with the bytes its filter stages decoded: the data or /// the error, each with that count. type Decoder = fn(&Stream, usize) -> Result<(Vec, usize), (FilterError, usize)>; +/// What one operation over a document's images may still spend decoding them: exporting them, +/// optimizing them, and storing LZW streams with Flate as it does, clearing them for redaction. +/// +/// An image has its own limit, which doesn't bound a file of thousands of images made to reach it: +/// a few hundred bytes of JBIG2 can ask for seconds of decoding, 4 KB of Flate inside Flate for a +/// gigabyte, and an image that shares `/JBIG2Globals` decodes them again. So images share this +/// allowance, whatever they do with what they decode and whether or not it works, and past it they +/// aren't decoded. A caller then treats them as it does an image it can't read, and +/// [`ImageBudget::refused`] says how many there were. +/// +/// An image also pays for its pixels once decoded, as what reads it goes through them one by one +/// however few bytes coded them: blank rows of fax or Flate take almost none. It pays for no more +/// than its data holds, a bit a pixel at least, so an image declaring a size its data doesn't fill +/// costs what a smaller one would, not the run's allowance. A JPEG pays for its samples when +/// it is decoded ([`ImageBudget::pay_jpeg`]), and is otherwise not charged, as JPEG 2000 isn't: +/// their decoders don't run here. +#[derive(Debug)] +pub struct ImageBudget { + work: u64, + refused: usize, +} + +impl ImageBudget { + /// The allowance for an operation on `doc`, which a longer file makes larger. The streams made + /// or changed since it was opened count as the file's bytes do, so a document built in memory + /// (combined, created, or given pages of scans) gets what it would once saved and opened again. + pub fn new(doc: &Document) -> Self { + let length = |n: usize| u64::try_from(n).unwrap_or(u64::MAX); + let edited = doc + .scan_objects_subset(doc.modified_objects()) + .filter_map(|(_, object)| match &*object.ok()? { + Object::Stream(s) => Some(length(s.raw.len())), + _ => None, + }) + .fold(0u64, u64::saturating_add); + let bytes = length(doc.bytes().len()).saturating_add(edited); + Self::with_work(IMAGE_WORK.saturating_add(bytes.saturating_mul(IMAGE_WORK_PER_BYTE))) + } + + /// An allowance of `work` steps of decoding. + pub fn with_work(work: u64) -> Self { + Self { work, refused: 0 } + } + + /// The samples of image `s`, decoded and charged to the allowance: the one way to decode an + /// image outside the renderer, so that an operation over many images can't decode them without + /// one. + /// + /// They go through its filters ([`Stream::decoded`]), or, for a CCITT fax or JBIG2 image (its + /// last filter), through the filters before it and then [`pdfcraft_filters::decode_ccitt_within`] + /// with its [`Document::fax_params`], or [`pdfcraft_filters::decode_jbig2_within`] with its + /// `/JBIG2Globals`, as `CCITTFaxDecode` and `JBIG2Decode` give them (ISO 32000-2 §7.4.6, + /// §7.4.7). Parameters given by reference count, for every filter + /// ([`Document::with_direct_parms`]). A fax image's `/Columns` has to be its `/Width`, and a + /// JBIG2 image's page its `/Width` × `/Height`: PdfCraft's renderer draws the whole page into + /// the image. Up to its `/Height` rows are decoded, whatever a fax image's `/Rows` says; damaged + /// fax data gives fewer, so a caller checks it has the rows it needs. Damaged JBIG2 data, and + /// globals that can't be read (within [`MAX_JBIG2_GLOBALS`](crate::MAX_JBIG2_GLOBALS)), are an + /// error. + /// + /// No stage, the filters before a fax or JBIG2 decoder included, may produce more than `max` + /// bytes, nor more than [`MAX_DECODED`](crate::MAX_DECODED). A JBIG2 image's `/JBIG2Globals` + /// are another stream, shared between images, and are decoded within `MAX_JBIG2_GLOBALS` + /// whatever `max` is. Each filter as it runs, the globals when they have to be read, and the fax + /// or JBIG2 decoder spend from the allowance, and the image then pays for its pixels; with + /// nothing left an image is refused before anything is read, its globals included. + /// + /// ``` + /// # let doc = pdfcraft_cos::Document::new_empty(); + /// # let s = pdfcraft_cos::Stream::from_raw(pdfcraft_cos::Dict::new(), Vec::new()); + /// let samples = pdfcraft_cos::ImageBudget::new(&doc).decode(&doc, &s, 1 << 20); + /// assert_eq!(samples.unwrap(), b""); + /// ``` + /// + /// `Document` has no way of its own to decode an image: + /// + /// ```compile_fail + /// # let doc = pdfcraft_cos::Document::new_empty(); + /// # let s = pdfcraft_cos::Stream::from_raw(pdfcraft_cos::Dict::new(), Vec::new()); + /// let _ = doc.decoded_image(&s); + /// ``` + /// + /// ```compile_fail + /// # let doc = pdfcraft_cos::Document::new_empty(); + /// # let s = pdfcraft_cos::Stream::from_raw(pdfcraft_cos::Dict::new(), Vec::new()); + /// let _ = doc.decoded_image_within(&s, 1 << 20); + /// ``` + pub fn decode(&mut self, doc: &Document, s: &Stream, max: usize) -> Result, CosError> { + let decoded = doc.decoded_image_spending(s, max, &mut self.work); + self.count_refused(s, &decoded); + self.pay_size(s, decoded?) + } + + /// Image `s` through its filters alone, charged to the allowance: [`Stream::decoded_within`] + /// with its `/DecodeParms` given by reference read too ([`Document::with_direct_parms`]), for an + /// image that has no fax or JBIG2 decoder to go through. + pub fn decode_filters(&mut self, doc: &Document, s: &Stream, max: usize) -> Result, CosError> { + let decoded = doc.with_direct_parms(s).decoded_spending(max, &mut self.work); + self.count_refused(s, &decoded); + let decoded = decoded?; + if s.filters().iter().all(|(f, _)| f.is_decodable()) { self.pay_size(s, decoded) } else { Ok(decoded) } + } + + /// `data` through `chain`, any corruption being an error ([`pdfcraft_filters::decode_within`]), + /// for a stream a run rewrites rather than an image it reads, charged to the allowance. + pub fn decode_chain( + &mut self, + chain: &[(pdfcraft_filters::Filter, pdfcraft_filters::Params)], + data: &[u8], + max: usize, + ) -> Result, FilterError> { + pdfcraft_filters::decode_within(chain, data, max, &mut self.work) + } + + /// Pays `steps` of other work on decoded data, or spends all there is and says so. + pub fn spend(&mut self, steps: u64) -> bool { + let left = self.work.checked_sub(steps); + self.work = left.unwrap_or(0); + left.is_some() + } + + /// Pays for `pixels` a decode goes on to work through, or spends all there is, and the image + /// is refused. + pub fn pay_pixels(&mut self, pixels: u64) -> bool { + let paid = self.spend(pixels); + self.refused += usize::from(!paid); + paid + } + + /// Pays for reading JPEG `data` and decoding its `samples`, as [`ImageBudget::pay_pixels`] does. + /// A caller pays before its tables are parsed, which can be most of the file. + pub fn pay_jpeg(&mut self, samples: u64, data: &[u8]) -> bool { + let reading = (data.len() as u64).saturating_mul(JPEG_READ_WORK); + self.pay_pixels(samples.saturating_mul(JPEG_WORK).saturating_add(reading)) + } + + /// Pays for the pixels of image `s` that its `decoded` data holds, those of its `/Width` and + /// `/Height` but no more than a bit of the data each, unless it is JBIG2, whose decoder pays for + /// its page, or isn't decoded here. What can't be paid for refuses the image. + fn pay_size(&mut self, s: &Stream, decoded: Vec) -> Result, CosError> { + if !charged(s) || matches!(s.filters().last(), Some((pdfcraft_filters::Filter::Jbig2, _))) { + return Ok(decoded); + } + let side = |key: &[u8]| s.dict.int(key).and_then(|v| u64::try_from(v).ok()).unwrap_or(0); + let held = u64::try_from(decoded.len()).unwrap_or(u64::MAX).saturating_mul(8); + if self.pay_pixels(side(b"Width").saturating_mul(side(b"Height")).min(held)) { + Ok(decoded) + } else { + Err(CosError::Filter(FilterError::Spent.to_string())) + } + } + + /// An image that failed with nothing left was refused, unless it has a filter that costs + /// nothing here, which fails whatever is left. + fn count_refused(&mut self, s: &Stream, decoded: &Result, CosError>) { + if decoded.is_err() && self.work == 0 && charged(s) { + self.refused += 1; + } + } + + /// The decodes refused for lack of allowance: an image read twice over is counted twice. + pub fn refused(&self) -> usize { + self.refused + } + + /// The steps of decoding still allowed. + pub fn work_left(&self) -> u64 { + self.work + } +} + +/// Whether `s` can be decoded here and so charged: general filters, a fax or JBIG2 decoder last at +/// most. Those decoders anywhere else can't run. +fn charged(s: &Stream) -> bool { + use pdfcraft_filters::Filter; + s.readable_filters().is_ok_and(|chain| { + chain.split_last().is_none_or(|((last, _), before)| { + (last.is_decodable() || matches!(last, Filter::Jbig2 | Filter::CcittFax)) && before.iter().all(|(f, _)| f.is_decodable()) + }) + }) +} + /// What one operation may still decode and enter across all the streams it reads. /// /// [`MAX_DECODED`](crate::MAX_DECODED) bounds one decode. It does not bound a page whose @@ -143,6 +345,401 @@ impl DecodeBudget { } } +#[cfg(test)] +mod image_tests { + use super::*; + use crate::Dict; + + fn jbig2(parms: Option) -> Stream { + let mut dict = Dict::new(); + dict.set(b"Width".to_vec(), Object::Int(16)); + dict.set(b"Height".to_vec(), Object::Int(2)); + dict.set(b"Filter".to_vec(), Object::name("JBIG2Decode")); + if let Some(parms) = parms { + dict.set(b"DecodeParms".to_vec(), parms); + } + Stream::from_raw(dict, pdfcraft_filters::encode_jbig2_generic(&[0xFF; 4], 16, 2).unwrap()) + } + + /// Each image spends what it took from one allowance, and those past it are refused and + /// counted, whatever their filters. What can't be decoded here costs nothing, and fails + /// without being one of these. + #[test] + fn the_images_of_an_operation_share_its_allowance() { + let doc = Document::new_empty(); + let image = jbig2(None); + let mut budget = ImageBudget::with_work(u64::MAX); + let samples = budget.decode(&doc, &image, 1 << 20).unwrap(); + let cost = u64::MAX - budget.work_left(); + assert!(cost > 0); + let mut budget = ImageBudget::with_work(3 * cost); + for left in [2, 1, 0] { + assert_eq!(budget.decode(&doc, &image, 1 << 20).unwrap(), samples); + assert_eq!(budget.work_left(), left * cost); + } + assert_eq!(budget.refused(), 0, "the allowance held exactly three"); + for refused in [1, 2] { + assert!(budget.decode(&doc, &image, 1 << 20).is_err()); + assert_eq!(budget.refused(), refused); + } + assert!(budget.decode(&doc, &Stream::flate(Dict::new(), b"samples"), 1 << 20).is_err()); + assert!(budget.decode(&doc, &Stream::from_raw(Dict::new(), b"samples".to_vec()), 1 << 20).is_err()); + assert_eq!(budget.refused(), 4, "other images share it"); + for name in ["NoSuchFilter", "DCTDecode", "JPXDecode"] { + let mut dict = Dict::new(); + dict.set(b"Filter".to_vec(), Object::name(name)); + assert!(budget.decode(&doc, &Stream::from_raw(dict, b"data".to_vec()), 1 << 20).is_err()); + assert_eq!(budget.refused(), 4, "{name} isn't one of these"); + } + let mut dict = Dict::new(); + dict.set(b"Filter".to_vec(), Object::Int(5)); + assert!(budget.decode(&doc, &Stream::from_raw(dict, b"data".to_vec()), 1 << 20).is_err()); + assert_eq!(budget.refused(), 4, "a /Filter that can't be read isn't either"); + } + + /// What a file of images each inflating a megabyte asks for: 4 KB of Flate inside Flate can ask + /// for a gigabyte, and these aren't JBIG2, so without the allowance nothing would stop them. + #[test] + fn filter_bombs_stop_at_the_allowance() { + let doc = Document::new_empty(); + let samples = vec![0; 1 << 20]; + let inner = pdfcraft_filters::encode_flate(&samples); + let mut dict = Dict::new(); + dict.set(b"Filter".to_vec(), Object::Array(vec![Object::name("FlateDecode"), Object::name("FlateDecode")])); + let bomb = Stream::from_raw(dict, pdfcraft_filters::encode_flate(&inner)); + let cost = (bomb.raw.len() + inner.len() + samples.len()) as u64; + let mut budget = ImageBudget::with_work(2 * cost + 1); + for left in [cost + 1, 1] { + assert_eq!(budget.decode(&doc, &bomb, 1 << 20).unwrap(), samples); + assert_eq!(budget.work_left(), left); + } + assert!(budget.decode(&doc, &bomb, 1 << 20).is_err()); + assert_eq!((budget.work_left(), budget.refused()), (0, 1), "the first it can't pay for ends it"); + } + + /// Filters in front of a JBIG2 decoder pay as they run, on top of what the decoder takes, and + /// one that fails has still paid: nothing about the JBIG2 data is known by then, and each image + /// of a file can do this. + #[test] + fn filters_in_front_of_jbig2_pay_whether_or_not_they_work() { + let doc = Document::new_empty(); + let alone = jbig2(None); + let mut budget = ImageBudget::with_work(u64::MAX); + let samples = budget.decode(&doc, &alone, 1 << 20).unwrap(); + let decoding = u64::MAX - budget.work_left(); + let behind = |raw: Vec| { + let mut dict = alone.dict.clone(); + dict.set(b"Filter".to_vec(), Object::Array(vec![Object::name("FlateDecode"), Object::name("JBIG2Decode")])); + Stream::from_raw(dict, raw) + }; + + let image = behind(pdfcraft_filters::encode_flate(&alone.raw)); + let mut budget = ImageBudget::with_work(u64::MAX); + assert_eq!(budget.decode(&doc, &image, 1 << 20).unwrap(), samples); + assert_eq!(u64::MAX - budget.work_left(), decoding + (image.raw.len() + alone.raw.len()) as u64); + + // Past this image's limit: an error, with what finding out took paid and the rest left. + let bomb = behind(pdfcraft_filters::encode_flate(&vec![0; 1 << 16])); + let mut budget = ImageBudget::with_work(u64::MAX); + assert!(budget.decode(&doc, &bomb, 1000).is_err()); + assert_eq!(u64::MAX - budget.work_left(), bomb.raw.len() as u64 + 1000); + assert_eq!(budget.refused(), 0, "that image's limit isn't the run's"); + + // A small allowance is a limit too: it stops there, and the image is refused. + let mut budget = ImageBudget::with_work(bomb.raw.len() as u64 + 10); + assert!(budget.decode(&doc, &bomb, 1 << 20).is_err()); + assert_eq!((budget.work_left(), budget.refused()), (0, 1)); + } + + /// Globals that are read again for every image pay every time, and fail having paid. Kept + /// ones have no filters left to undo, so they pay for being read and nothing more. + #[test] + fn globals_pay_for_their_filters_each_time_they_are_decoded() { + let skipped = [0, 0, 0, 0, 0x3E, 0, 0, 0, 0, 0, 4, 0, 0, 0, 1]; + let raw = pdfcraft_filters::encode_flate(&skipped); + let stream = |doc: &Document, r: ObjRef| match &*doc.get(r) { + Object::Stream(s) => s.clone(), + _ => panic!("not a stream"), + }; + let spent = |doc: &Document, s: &Stream| { + let mut budget = ImageBudget::with_work(u64::MAX); + budget.decode(doc, s, 1 << 20).unwrap(); + u64::MAX - budget.work_left() + }; + let mut doc = Document::new_empty(); + let mut dict = Dict::new(); + dict.set(b"Filter".to_vec(), Object::name("FlateDecode")); + let globals = doc.add(Object::Stream(Stream::from_raw(dict, raw.clone()))); + let mut parms = Dict::new(); + parms.set(b"JBIG2Globals".to_vec(), Object::Ref(globals)); + let image = doc.add(Object::Stream(jbig2(Some(Object::Dict(parms))))); + let root = doc.root().unwrap(); + doc.update_dict(root, |c| c.set(b"Image".to_vec(), Object::Ref(image))).unwrap(); + + // Added in memory, so not kept: the filters are undone for each read. + let s = stream(&doc, image); + let first = spent(&doc, &s); + assert_eq!(spent(&doc, &s), first, "not kept, so paid for again"); + + // Read from a file, so kept: the second read has no filters to undo. + let file = crate::write_full(&doc, &crate::SaveOptions::default()).unwrap(); + let doc = Document::open(std::sync::Arc::new(file)).unwrap(); + let image = doc.get(doc.root().unwrap()).as_dict().unwrap().reference(b"Image").unwrap(); + let s = stream(&doc, image); + let filters = (raw.len() + skipped.len()) as u64; + assert_eq!(spent(&doc, &s), first, "the first read undoes them"); + assert_eq!(spent(&doc, &s), first - filters, "kept"); + + // Globals that fail pay too, with the image not refused: these go past their own limit. + let over = pdfcraft_filters::encode_flate(&vec![0; crate::MAX_JBIG2_GLOBALS + 1]); + let mut doc = Document::new_empty(); + let mut dict = Dict::new(); + dict.set(b"Filter".to_vec(), Object::name("FlateDecode")); + let globals = doc.add(Object::Stream(Stream::from_raw(dict, over.clone()))); + let mut parms = Dict::new(); + parms.set(b"JBIG2Globals".to_vec(), Object::Ref(globals)); + let image = jbig2(Some(Object::Dict(parms))); + let mut budget = ImageBudget::with_work(u64::MAX); + assert!(budget.decode(&doc, &image, 1 << 20).unwrap_err().to_string().contains("globals")); + assert_eq!(u64::MAX - budget.work_left(), (over.len() + crate::MAX_JBIG2_GLOBALS) as u64); + assert_eq!(budget.refused(), 0); + } + + /// A fax image pays for what comes before its decoder and for the rows it asks for, and past + /// the allowance it is refused like any other. + #[test] + fn fax_images_share_the_allowance() { + let doc = Document::new_empty(); + let (w, h) = (4096u32, 64u32); + let coded = pdfcraft_filters::encode_g4(&vec![0xFF; 512 * h as usize], w, h).unwrap(); + let mut parms = Dict::new(); + parms.set(b"K".to_vec(), Object::Int(-1)); + parms.set(b"Columns".to_vec(), Object::Int(i64::from(w))); + let mut dict = Dict::new(); + dict.set(b"Width".to_vec(), Object::Int(i64::from(w))); + dict.set(b"Height".to_vec(), Object::Int(i64::from(h))); + dict.set(b"Filter".to_vec(), Object::Array(vec![Object::name("FlateDecode"), Object::name("CCITTFaxDecode")])); + dict.set(b"DecodeParms".to_vec(), Object::Array(vec![Object::Null, Object::Dict(parms)])); + let image = Stream::from_raw(dict, pdfcraft_filters::encode_flate(&coded)); + let pixels = u64::from(w) * u64::from(h); + let cost = (image.raw.len() + coded.len() + 4 * coded.len() + 512 * h as usize) as u64 + pixels; + let mut budget = ImageBudget::with_work(cost); + assert_eq!(budget.decode(&doc, &image, 1 << 20).unwrap().len(), 512 * h as usize); + assert_eq!(budget.work_left(), 0, "exactly that"); + assert!(budget.decode(&doc, &image, 1 << 20).is_err()); + assert_eq!(budget.refused(), 1); + } + + /// An image pays for its pixels however few bytes hold them, or a blank page of fax or Flate + /// would cost a run a second for a few bytes' worth of allowance; a JBIG2 image doesn't pay + /// twice, and one this doesn't decode pays nothing. Past what is left it isn't read. + #[test] + fn an_image_pays_for_its_pixels() { + let doc = Document::new_empty(); + let blank = |filter: Option<&str>, data: Vec| { + let mut dict = Dict::new(); + dict.set(b"Width".to_vec(), Object::Int(4096)); + dict.set(b"Height".to_vec(), Object::Int(1024)); + if let Some(filter) = filter { + dict.set(b"Filter".to_vec(), Object::name(filter)); + } + Stream::from_raw(dict, data) + }; + let rows = vec![0xFFu8; 512 * 1024]; + let flate = blank(Some("FlateDecode"), pdfcraft_filters::encode_flate(&rows)); + let cost = (flate.raw.len() + rows.len()) as u64 + 4096 * 1024; + let mut budget = ImageBudget::with_work(cost); + assert_eq!(budget.decode(&doc, &flate, 1 << 24).unwrap(), rows); + assert_eq!((budget.work_left(), budget.refused()), (0, 0), "exactly that"); + // Its filters alone pay the same. + let mut budget = ImageBudget::with_work(cost); + assert_eq!(budget.decode_filters(&doc, &flate, 1 << 24).unwrap(), rows); + assert_eq!(budget.work_left(), 0); + // Short of its pixels it is refused, having paid for its filters. + let mut budget = ImageBudget::with_work(4096 * 1024 - 1); + assert!(budget.decode(&doc, &flate, 1 << 24).unwrap_err().to_string().contains("more image decoding than")); + assert_eq!((budget.work_left(), budget.refused()), (0, 1)); + let mut budget = ImageBudget::with_work(4096 * 1024 - 1); + assert!(budget.decode_filters(&doc, &flate, 1 << 24).is_err()); + assert_eq!((budget.work_left(), budget.refused()), (0, 1)); + // What isn't decoded here pays for nothing, and fails as it would. + let mut budget = ImageBudget::with_work(10); + assert!(budget.decode(&doc, &blank(Some("DCTDecode"), b"data".to_vec()), 1 << 24).is_err()); + assert_eq!((budget.work_left(), budget.refused()), (10, 0)); + // Unfiltered data pays too, and a size that isn't one is no size. + let mut budget = ImageBudget::with_work(u64::MAX); + budget.decode(&doc, &blank(None, rows.clone()), 1 << 24).unwrap(); + assert_eq!(u64::MAX - budget.work_left(), rows.len() as u64 + 4096 * 1024); + let mut odd = Dict::new(); + odd.set(b"Width".to_vec(), Object::Int(-4)); + odd.set(b"Height".to_vec(), Object::Int(9)); + let mut budget = ImageBudget::with_work(u64::MAX); + budget.decode(&doc, &Stream::from_raw(odd, vec![1, 2]), 1 << 24).unwrap(); + assert_eq!(u64::MAX - budget.work_left(), 2); + // A JPEG pays twice over for each sample, and four times for each byte it is read from. + let mut budget = ImageBudget::with_work(30); + assert!(budget.pay_jpeg(9, b"ab")); + assert_eq!((budget.work_left(), budget.refused()), (4, 0)); + assert!(!budget.pay_jpeg(0, b"ab")); + assert_eq!((budget.work_left(), budget.refused()), (0, 1)); + } + + /// An image pays for the pixels its data holds, not those its size declares: one claiming + /// 131072 by 131072 pixels with a few bytes of Flate costs what those bytes give, and the + /// images after it are decoded as they would be without it. + #[test] + fn an_image_pays_for_no_more_pixels_than_its_data_holds() { + let doc = Document::new_empty(); + let sized = |side: i64, data: &[u8]| { + let mut dict = Dict::new(); + dict.set(b"Width".to_vec(), Object::Int(side)); + dict.set(b"Height".to_vec(), Object::Int(side)); + Stream::flate(dict, data) + }; + let claims = sized(131_072, &[0; 16]); + let image = sized(64, &[7; 64 * 64]); + let cost = |s: &Stream| { + let mut budget = ImageBudget::with_work(u64::MAX); + budget.decode(&doc, s, 1 << 24).unwrap(); + u64::MAX - budget.work_left() + }; + assert_eq!(cost(&claims), (claims.raw.len() + 16 + 16 * 8) as u64, "its bytes, and a pixel a bit of them"); + assert_eq!(cost(&image), (image.raw.len() + 64 * 64) as u64 + 64 * 64, "its bytes, and its pixels"); + for decode in [ImageBudget::decode, ImageBudget::decode_filters] { + let mut budget = ImageBudget::with_work(cost(&claims) + cost(&image)); + assert_eq!(decode(&mut budget, &doc, &claims, 1 << 24).unwrap(), [0; 16]); + assert_eq!(decode(&mut budget, &doc, &image, 1 << 24).unwrap(), [7; 64 * 64], "the image after it is decoded"); + assert_eq!((budget.work_left(), budget.refused()), (0, 0)); + } + } + + /// A stream a run rewrites is read strictly and charged, and what the caller does with it after + /// comes out of the same allowance: what can't be paid for spends all of it. + #[test] + fn a_rewritten_stream_shares_the_allowance() { + use pdfcraft_filters::{Filter, FilterError, Params}; + let samples = vec![7u8; 1000]; + let raw = pdfcraft_filters::encode_flate(&samples); + let chain = [(Filter::Flate, Params::default())]; + let cost = (raw.len() + samples.len()) as u64; + let mut budget = ImageBudget::with_work(cost + 10); + assert_eq!(budget.decode_chain(&chain, &raw, 1 << 20).unwrap(), samples); + assert_eq!(budget.work_left(), 10); + assert!(budget.spend(4)); + assert_eq!(budget.work_left(), 6); + assert!(budget.spend(6), "exactly what is left"); + assert_eq!(budget.work_left(), 0); + assert!(budget.spend(0)); + let mut budget = ImageBudget::with_work(5); + assert!(!budget.spend(6)); + assert_eq!(budget.work_left(), 0, "spends all of it"); + assert!(matches!(budget.decode_chain(&chain, &raw, 1 << 20), Err(FilterError::Spent))); + let cut = raw.get(..raw.len() / 2).unwrap(); + assert!(matches!(ImageBudget::with_work(u64::MAX).decode_chain(&chain, cut, 1 << 20), Err(FilterError::Corrupt { .. })), "strictly"); + } + + /// An image read through its filters alone reads parameters given by reference, is charged, and + /// is refused like the others. It isn't given to a decoder. + #[test] + fn filters_alone_are_charged_too() { + let mut doc = Document::new_empty(); + let p = pdfcraft_filters::Params { predictor: 12, columns: 4, ..pdfcraft_filters::Params::default() }; + let rows = vec![7u8; 400]; + let mut parms = Dict::new(); + parms.set(b"Predictor".to_vec(), Object::Int(12)); + parms.set(b"Columns".to_vec(), Object::Int(4)); + let parms = doc.add(Object::Dict(parms)); + let mut dict = Dict::new(); + dict.set(b"Filter".to_vec(), Object::name("FlateDecode")); + dict.set(b"DecodeParms".to_vec(), Object::Ref(parms)); + let raw = pdfcraft_filters::encode(&pdfcraft_filters::Filter::Flate, &p, &rows).unwrap(); + let image = Stream::from_raw(dict, raw); + let mut budget = ImageBudget::with_work(u64::MAX); + assert_eq!(budget.decode_filters(&doc, &image, 1 << 20).unwrap(), rows); + let cost = u64::MAX - budget.work_left(); + // The tag byte of each of its 100 rows counts, which the predictor takes off. + assert_eq!(cost, (image.raw.len() + rows.len() + 100) as u64); + let mut budget = ImageBudget::with_work(cost - 1); + assert!(budget.decode_filters(&doc, &image, 1 << 20).is_err()); + assert_eq!((budget.work_left(), budget.refused()), (0, 1)); + let mut budget = ImageBudget::with_work(u64::MAX); + assert!(budget.decode_filters(&doc, &jbig2(None), 1 << 20).is_err()); + assert_eq!(budget.work_left(), u64::MAX, "no decoder here, so nothing was read"); + // Nor for a fax image, nor for a decoder that isn't last, however large they say they are. + for chain in [vec!["CCITTFaxDecode"], vec!["CCITTFaxDecode", "FlateDecode"], vec!["JBIG2Decode", "FlateDecode"]] { + let mut dict = Dict::new(); + dict.set(b"Width".to_vec(), Object::Int(1000)); + dict.set(b"Height".to_vec(), Object::Int(1000)); + dict.set(b"Filter".to_vec(), Object::Array(chain.iter().map(|f| Object::name(f)).collect())); + let image = Stream::from_raw(dict, b"data".to_vec()); + let mut budget = ImageBudget::with_work(u64::MAX); + assert!(budget.decode_filters(&doc, &image, 1 << 20).is_err()); + assert_eq!(budget.work_left(), u64::MAX, "{chain:?}"); + } + // Through `decode` a decoder that isn't last pays nothing either; one that is does. + let mut dict = Dict::new(); + dict.set(b"Width".to_vec(), Object::Int(1000)); + dict.set(b"Height".to_vec(), Object::Int(1000)); + dict.set(b"Filter".to_vec(), Object::Array(vec![Object::name("JBIG2Decode"), Object::name("FlateDecode")])); + let mut budget = ImageBudget::with_work(u64::MAX); + assert!(budget.decode(&doc, &Stream::from_raw(dict, b"data".to_vec()), 1 << 20).is_err()); + assert_eq!(budget.work_left(), u64::MAX); + } + + /// The images of a file share its globals, so an image refused doesn't read them: this one's + /// can't be read, which is how to tell. + #[test] + fn an_image_past_the_allowance_does_not_read_its_globals() { + let mut doc = Document::new_empty(); + let mut unreadable = Dict::new(); + unreadable.set(b"Filter".to_vec(), Object::name("NoSuchFilter")); + let globals = doc.add(Object::Stream(Stream::from_raw(unreadable, b"data".to_vec()))); + let mut parms = Dict::new(); + parms.set(b"JBIG2Globals".to_vec(), Object::Ref(globals)); + let image = jbig2(Some(Object::Dict(parms))); + let read = ImageBudget::with_work(u64::MAX).decode(&doc, &image, 1 << 20).unwrap_err().to_string(); + assert!(read.contains("globals"), "{read}"); + let refused = ImageBudget::with_work(0).decode(&doc, &image, 1 << 20).unwrap_err().to_string(); + assert!(refused.contains("more image decoding than"), "{refused}"); + } + + /// A longer file gets more, by its length, and an empty one the fixed part. + #[test] + fn a_longer_file_allows_more_decoding() { + assert_eq!(ImageBudget::new(&Document::new_empty()).work_left(), IMAGE_WORK); + let pdf = b"%PDF-1.7\n1 0 obj << /Type /Catalog >> endobj\ntrailer << /Root 1 0 R >>\n%%EOF".to_vec(); + let len = pdf.len() as u64; + let doc = Document::open(std::sync::Arc::new(pdf)).unwrap(); + assert_eq!(ImageBudget::new(&doc).work_left(), IMAGE_WORK + len * IMAGE_WORK_PER_BYTE); + } + + /// A document made in memory, as Combine, Create and inserted scans make one, gets for the + /// streams it was given what it would get for them once saved: what isn't a stream adds nothing. + #[test] + fn streams_made_in_memory_allow_more_decoding_too() { + let mut doc = Document::new_empty(); + doc.add(Object::Stream(Stream::from_raw(Dict::new(), vec![0; 3000]))); + doc.add(Object::Dict(Dict::new())); + doc.add(Object::Stream(Stream::flate(Dict::new(), &[1; 100]))); + let flate = pdfcraft_filters::encode_flate(&[1; 100]).len() as u64; + assert_eq!(ImageBudget::new(&doc).work_left(), IMAGE_WORK + (3000 + flate) * IMAGE_WORK_PER_BYTE); + // A stream of an opened file changed in memory counts with the file. + let pdf = b"%PDF-1.7\n1 0 obj << /Type /Catalog >> endobj\ntrailer << /Root 1 0 R >>\n%%EOF".to_vec(); + let len = pdf.len() as u64; + let mut doc = Document::open(std::sync::Arc::new(pdf)).unwrap(); + doc.add(Object::Stream(Stream::from_raw(Dict::new(), vec![0; 500]))); + assert_eq!(ImageBudget::new(&doc).work_left(), IMAGE_WORK + (len + 500) * IMAGE_WORK_PER_BYTE); + } + + // What the constants' comments promise, for a page scanned at 300 dpi: about 1,000 of them + // whatever the file's size, and a page paying for itself with 2 KB of the file. + const PAGE: u64 = 17_000_000; + const _: () = assert!(IMAGE_WORK >= 1_000 * PAGE); + const _: () = assert!(IMAGE_WORK_PER_BYTE * 2_100 >= PAGE); + // And that a stream can be decoded about 8 times at Flate's best, 1,032 to one, and the byte in. + const _: () = assert!(IMAGE_WORK_PER_BYTE >= 7 * 1_033); +} + #[cfg(test)] mod tests { use super::*; @@ -198,6 +795,21 @@ mod tests { assert_eq!(budget.remaining(), (10 << 20) - partial); } + /// A stream that fails its reading as zlib, and then as raw deflate after decoding all of it, + /// gives nothing back, and each reference still pays for what it decoded. + #[test] + fn a_decode_that_gives_nothing_back_still_pays() { + let mut data = vec![0x78, 0x01, 0x06, 0xFE, 0xF9]; + data.extend(vec![0u8; 0x0601]); + data.push(0x07); + let mut dict = Dict::new(); + dict.set(b"Filter".to_vec(), Object::name("FlateDecode")); + let stream = Stream::from_raw(dict, data); + let mut budget = DecodeBudget::new(10 * 0x0601, 1); + assert!(budget.decode(&stream).unwrap().is_empty()); + assert_eq!(budget.remaining(), 9 * 0x0601); + } + /// A chain whose later stage shrinks the data pays for every stage's output: a Flate stage /// that inflates to hex text, which ASCIIHex then halves, charges both. #[test] diff --git a/crates/cos/src/document.rs b/crates/cos/src/document.rs index 082d1910d1..2aaf33ec63 100644 --- a/crates/cos/src/document.rs +++ b/crates/cos/src/document.rs @@ -27,7 +27,7 @@ pub(crate) use state::ObjectReader; use state::{ObjStm, Slot}; pub use state::{ReadState, SourceIdentity}; #[cfg(test)] -use state::{SECTION_READS, objstm_member, owned_bytes}; +use state::{SECTION_READS, held_bytes, objstm_member}; use xref::XrefIndex; pub use xref::{Revision, XrefEntry}; @@ -47,7 +47,7 @@ pub struct Document { /// `fill_xref_gaps`. located: Arc>, repair_log: Arc>, - cache: Arc>>>, + cache: Arc>, objstms: Arc>>>, /// What `/JBIG2Globals` streams of the file decode to, by object number: the images of a scan /// share them, and each would otherwise decode them again (see `Document::jbig2_globals`). diff --git a/crates/cos/src/document/objects.rs b/crates/cos/src/document/objects.rs index bab99ac45e..4efb185f1a 100644 --- a/crates/cos/src/document/objects.rs +++ b/crates/cos/src/document/objects.rs @@ -1,5 +1,5 @@ use super::reader::find; -use super::state::{LENGTHS, LoadGuard, ObjStm, ObjectReader, ReadState, Slot, SourceIdentity, objstm_member, owned_bytes}; +use super::state::{LENGTHS, LoadGuard, ObjStm, ObjectReader, ReadState, Slot, SourceIdentity, held_bytes, objstm_member}; use super::xref::{Revision, XrefEntry}; use super::{ Arc, CosError, Cow, Dict, Document, Lexer, MAX_DECODED, MAX_JBIG2_GLOBALS, ObjRef, Object, Stream, is_whitespace, parse_indirect_shared, @@ -274,34 +274,32 @@ impl Document { .unwrap_or_default() } - /// The samples of image `s`, decoded: through its filters ([`Stream::decoded`]), or, for a - /// CCITT fax or JBIG2 image (its last filter), through the filters before it and then - /// [`pdfcraft_filters::decode_ccitt`] with its [`Document::fax_params`], or - /// [`pdfcraft_filters::decode_jbig2`] with its `/JBIG2Globals`, as `CCITTFaxDecode` and - /// `JBIG2Decode` give them (ISO 32000-2 §7.4.6, §7.4.7). Parameters given by reference count, - /// for every filter ([`Document::with_direct_parms`]). A fax image's `/Columns` has to be its - /// `/Width`, and a JBIG2 image's page its `/Width` × `/Height`: PdfCraft's renderer draws the - /// whole page into the image. Up to its `/Height` rows are decoded, whatever a fax image's `/Rows` says, - /// within [`MAX_DECODED`] bytes; damaged fax data gives fewer, so a caller checks it has the - /// rows it needs. Damaged JBIG2 data, and globals that can't be read (within - /// [`MAX_JBIG2_GLOBALS`]), are an error. - pub fn decoded_image(&self, s: &Stream) -> Result, CosError> { + /// [`Document::decoded_image_spending`] with no limit on the work, for tests of what an image + /// decodes to: everything else decodes images through an [`ImageBudget`](crate::ImageBudget). + #[cfg(test)] + pub(crate) fn decoded_image(&self, s: &Stream) -> Result, CosError> { self.decoded_image_within(s, MAX_DECODED) } - /// [`Document::decoded_image`] for an image whose decoding has a tighter bound than - /// [`MAX_DECODED`]: no stage, the filters before a fax or JBIG2 decoder included, may produce - /// more than `max` bytes. A JBIG2 image's `/JBIG2Globals` are another stream, shared between - /// images, and are decoded within [`MAX_JBIG2_GLOBALS`] whatever `max` is. - pub fn decoded_image_within(&self, s: &Stream, max: usize) -> Result, CosError> { + /// [`Document::decoded_image`] within `max` bytes. + #[cfg(test)] + pub(crate) fn decoded_image_within(&self, s: &Stream, max: usize) -> Result, CosError> { + let mut unbounded = u64::MAX; + self.decoded_image_spending(s, max, &mut unbounded) + } + + /// The samples of image `s`, decoded within `max` bytes ([`MAX_DECODED`] at most), spending from + /// `work`: see [`ImageBudget::decode`](crate::ImageBudget::decode), the way in from outside this + /// crate, which says what this decodes and how. + pub(crate) fn decoded_image_spending(&self, s: &Stream, max: usize, work: &mut u64) -> Result, CosError> { let max = max.min(MAX_DECODED); let s = &*self.with_direct_parms(s); let filter = |e: pdfcraft_filters::FilterError| CosError::Filter(e.to_string()); let chain = s.readable_filters().map_err(filter)?; // The filters before the image codec, such as ASCII85Decode, are undone first. - let undo = |before: &[(pdfcraft_filters::Filter, pdfcraft_filters::Params)]| match before { + let undo = |before: &[(pdfcraft_filters::Filter, pdfcraft_filters::Params)], work: &mut u64| match before { [] => Ok(Cow::Borrowed(&s.raw[..])), - _ => pdfcraft_filters::decode_tolerant(before, &s.raw, max).map(|(data, _)| Cow::Owned(data)).map_err(filter), + _ => pdfcraft_filters::decode_tolerant_within(before, &s.raw, max, work).map(Cow::Owned).map_err(filter), }; // `/Width` and `/Height` are read as given directly, as every caller reads them first: one // given by reference has the image refused there, before it gets here. @@ -310,10 +308,12 @@ impl Document { let (Some(columns), Some(height)) = (s.dict.int(b"Width").and_then(|w| u32::try_from(w).ok()), height) else { return Err(CosError::Filter("a JBIG2 image's /Width or /Height isn't a size".into())); }; - let globals = self.jbig2_globals(s)?; - return pdfcraft_filters::decode_jbig2(&undo(before)?, globals.as_deref().map(Vec::as_slice), columns, height, max).map_err(filter); + // Nothing to read for what can't be decoded: the images of a file share its globals. + let globals = if *work == 0 { None } else { self.jbig2_globals(s, work)? }; + let data = if *work == 0 { Cow::Borrowed(&[][..]) } else { undo(before, work)? }; + return pdfcraft_filters::decode_jbig2_within(&data, globals.as_deref().map(Vec::as_slice), columns, height, max, work).map_err(filter); } - let Some(p) = self.fax_params(s) else { return s.decoded_within(max) }; + let Some(p) = self.fax_params(s) else { return s.decoded_spending(max, work) }; // As many rows as the image has: a /Rows below /Height would cut the picture short, and // rows past /Height aren't drawn. let p = pdfcraft_filters::CcittParams { rows: 0, ..p }; @@ -322,8 +322,8 @@ impl Document { } let stride = usize::try_from(p.columns).unwrap_or(usize::MAX).div_ceil(8).max(1); let rows = u32::try_from(max / stride).unwrap_or(u32::MAX).min(height.unwrap_or(0)); - let data = undo(chain.split_last().map_or(&[][..], |(_, before)| before))?; - pdfcraft_filters::decode_ccitt(&data, &p, rows).map_err(filter) + let data = undo(chain.split_last().map_or(&[][..], |(_, before)| before), work)?; + pdfcraft_filters::decode_ccitt_within(&data, &p, rows, work).map_err(filter) } /// The `/JBIG2Globals` stream a JBIG2 image `s` names by reference in its last filter's @@ -348,8 +348,9 @@ impl Document { /// it was read (the same in every clone) and with its `/DecodeParms` direct (by reference they /// are another object, which can change while this one doesn't), has its filters undone once a /// document and is kept, up to [`JBIG2_GLOBALS_HELD`] in all; others are read each time. That - /// saves the filters only: the segments it holds are decoded again for every image. - fn jbig2_globals(&self, s: &Stream) -> Result>>, CosError> { + /// saves the filters only: the segments it holds are decoded again for every image. Undoing + /// the filters spends from `work`, so globals read for every image pay every time. + fn jbig2_globals(&self, s: &Stream, work: &mut u64) -> Result>>, CosError> { let Some(entry) = self.last_filter_parms(s).get(b"JBIG2Globals").cloned() else { return Ok(None) }; let held = match entry { Object::Ref(r) if !self.overlay.contains_key(&r.num) => Some(r.num), @@ -361,7 +362,7 @@ impl Document { let Object::Stream(g) = &*self.resolve(&entry) else { return Ok(None) }; let readable = self.with_direct_parms(g); let held = held.filter(|_| matches!(readable, Cow::Borrowed(_))); - let mut data = readable.decoded_within(MAX_JBIG2_GLOBALS).map_err(|e| { + let mut data = readable.decoded_spending(MAX_JBIG2_GLOBALS, work).map_err(|e| { let detail = match e { CosError::Filter(detail) => detail, e => e.to_string(), @@ -398,8 +399,9 @@ impl Document { let obj = Arc::new(obj); // The editing cache is bounded like the scan reader's: re-parsing a file-backed view // is cheap, and returned objects outlive eviction. - self.cache.lock().map_err(|_| CosError::Poisoned)?.insert(num, obj.clone()); - self.evict_editor_cache_if_over_budget(num, &obj)?; + let owned = held_bytes(&obj, &self.data, 0); + self.cache.lock().map_err(|_| CosError::Poisoned)?.insert(num, obj.clone(), owned); + self.evict_editor_cache_if_over_budget(num)?; Ok(obj) } @@ -408,10 +410,10 @@ impl Document { /// document cannot pin its whole object graph. Only owned (decrypted/copied) bytes /// count; file-backed views re-parse for free. /// - /// Worst case per document: input bytes + up to `EDITOR_CACHE_OBJECTS` × - /// `EDITOR_LARGE_OBJECT` (1024 × 256 KB = 256 MB) of small objects between full - /// accounting passes + `EDITOR_OBJSTM_BYTES` (32 MB) + unsaved `overlay` edits. - /// The count cap always holds; byte accounting between passes is approximate. + /// Worst case per document: input bytes + `EDITOR_CACHE_BYTES` (32 MB) of owned object + /// data + `EDITOR_OBJSTM_BYTES` (32 MB) + unsaved `overlay` edits. Each object is measured + /// once, as it is cached ([`ObjectCache`](super::state::ObjectCache)), so both caps hold + /// after every insertion. /// Clones share these caches, so one clone's eviction drops another's hot set; /// that only costs re-parsing, never correctness. Eviction keeps just the newcomer: /// file-backed views re-parse cheaply and editor working sets stay far below 1024. @@ -424,37 +426,13 @@ impl Document { const EDITOR_OBJSTM_BYTES: usize = 32 * 1024 * 1024; - /// Newcomers above this force a full accounting pass even below the count cap: - /// `EDITOR_CACHE_BYTES / 128`, so 128 large newcomers always trigger a pass before the - /// byte budget can double. - const EDITOR_LARGE_OBJECT: usize = 256 * 1024; - - fn evict_editor_cache_if_over_budget(&self, fresh_num: u32, fresh: &Object) -> Result<(), CosError> { - // Fast path: the full fold is O(cache) per insert, so skip it for a small newcomer - // below the count cap. `len` is copied out first; nothing here holds the lock. - let len = self.cache.lock().map_err(|_| CosError::Poisoned)?.len(); - if len <= Self::EDITOR_CACHE_OBJECTS && owned_bytes(fresh, &self.data, 0) <= Self::EDITOR_LARGE_OBJECT { - return Ok(()); - } - // Walk a snapshot off-lock; re-lock only to evict. - let live: Vec<(u32, Arc)> = self.cache.lock().map_err(|_| CosError::Poisoned)?.iter().map(|(n, o)| (*n, o.clone())).collect(); - let data = &self.data; - let owned: usize = live.iter().fold(0usize, |n, (_, o)| n.saturating_add(owned_bytes(o, data, 0))); - if live.len() <= Self::EDITOR_CACHE_OBJECTS && owned <= Self::EDITOR_CACHE_BYTES { - return Ok(()); - } - // Re-check under the final lock: another thread may have inserted or evicted since - // the snapshot. Keep its newcomers, and skip the eviction if back within budget. - let snapshot: std::collections::HashSet = live.into_iter().map(|(n, _)| n).collect(); + fn evict_editor_cache_if_over_budget(&self, fresh_num: u32) -> Result<(), CosError> { let mut cache = self.cache.lock().map_err(|_| CosError::Poisoned)?; - if cache.len() <= Self::EDITOR_CACHE_OBJECTS { - let data = &self.data; - let owned: usize = cache.values().fold(0usize, |n, o| n.saturating_add(owned_bytes(o, data, 0))); - if owned <= Self::EDITOR_CACHE_BYTES { - return Ok(()); - } + if cache.len() <= Self::EDITOR_CACHE_OBJECTS && cache.owned() <= Self::EDITOR_CACHE_BYTES { + return Ok(()); } - cache.retain(|n, _| *n == fresh_num || !snapshot.contains(n)); + // Eviction keeps just the newcomer: file-backed views re-parse cheaply. + cache.retain(|n| *n == fresh_num); Ok(()) } diff --git a/crates/cos/src/document/state.rs b/crates/cos/src/document/state.rs index b4323f982e..96dde01c0f 100644 --- a/crates/cos/src/document/state.rs +++ b/crates/cos/src/document/state.rs @@ -163,11 +163,10 @@ impl ObjectReader { // input bytes, which the document keeps anyway, so they don't count; decrypted // streams and strings do. Checked after failed loads too: resolving a /Length may // have cached large objects. - if let Ok(mut cache) = self.document.cache.lock() { - let data = &self.document.data; - if cache.len() >= Self::OBJECTS || cache.values().fold(0usize, |n, o| n.saturating_add(owned_bytes(o, data, 0))) > Self::STREAM_BYTES { - cache.clear(); - } + if let Ok(mut cache) = self.document.cache.lock() + && (cache.len() >= Self::OBJECTS || cache.owned() > Self::STREAM_BYTES) + { + cache.clear(); } object } @@ -179,26 +178,96 @@ thread_local! { pub(super) static SECTION_READS: std::cell::Cell = const { std::cell::Cell::new(0) }; } -/// Nesting [`owned_bytes`] walks: past the parser's own nesting limit, so every parsed object +/// Parsed objects by number, each with what it holds ([`held_bytes`]) measured once, when it goes +/// in, and their sum kept beside them. +/// +/// Both caches are bounded by those bytes. Summing them on every read walked every cached object +/// whole each time: a file whose page dictionaries carry kilobytes of private data (InDesign's +/// `/PieceInfo`) took seconds to open, almost all of it re-measuring objects already measured +/// (#5873). +#[derive(Default)] +pub(crate) struct ObjectCache { + entries: HashMap, usize)>, + owned: usize, +} + +impl ObjectCache { + pub(crate) fn get(&self, num: &u32) -> Option<&Arc> { + self.entries.get(num).map(|(object, _)| object) + } + + #[cfg(test)] + pub(crate) fn contains_key(&self, num: &u32) -> bool { + self.entries.contains_key(num) + } + + /// Keep `object` as `num`, which holds `owned` bytes (what [`held_bytes`] says of it). + pub(crate) fn insert(&mut self, num: u32, object: Arc, owned: usize) { + if let Some((_, before)) = self.entries.insert(num, (object, owned)) { + self.owned = self.owned.saturating_sub(before); + } + self.owned = self.owned.saturating_add(owned); + } + + pub(crate) fn len(&self) -> usize { + self.entries.len() + } + + #[cfg(test)] + pub(crate) fn is_empty(&self) -> bool { + self.entries.is_empty() + } + + /// The bytes the cached objects hold between them. + pub(crate) fn owned(&self) -> usize { + self.owned + } + + pub(crate) fn clear(&mut self) { + self.entries.clear(); + self.owned = 0; + } + + pub(crate) fn retain(&mut self, mut keep: impl FnMut(&u32) -> bool) { + self.entries.retain(|num, _| keep(num)); + self.owned = self.entries.values().fold(0usize, |n, (_, owned)| n.saturating_add(*owned)); + } + + #[cfg(test)] + pub(crate) fn values(&self) -> impl Iterator> { + self.entries.values().map(|(object, _)| object) + } +} + +/// Nesting [`held_bytes`] walks: past the parser's own nesting limit, so every parsed object /// is measured in full. const OWNED_BYTES_DEPTH: usize = 256; -/// Bytes `object` holds of its own: string and stream data that is not a view into `data` -/// (the input file). An object nested deeper than [`OWNED_BYTES_DEPTH`] cannot be measured -/// and counts as too large to keep. -pub(super) fn owned_bytes(object: &Object, data: &Arc>, depth: usize) -> usize { +/// What keeping `object` parsed costs: string and stream data that is not a view into `data` +/// (the input file), and the parsed tree around it -- an [`Object`] per value and a key per +/// dictionary entry. An object nested deeper than [`OWNED_BYTES_DEPTH`] cannot be measured and +/// counts as too large to keep. +/// +/// The tree counts. Measured by its strings and streams alone, a page dictionary carrying +/// InDesign's `/PieceInfo` -- thousands of small numeric arrays, parsed into tens of thousands of +/// values -- weighed nothing, so the caches kept a thousand of them: a 35 MB file held 1.5 GB +/// (#5873). +pub(super) fn held_bytes(object: &Object, data: &Arc>, depth: usize) -> usize { if depth > OWNED_BYTES_DEPTH { return usize::MAX; } + let node = std::mem::size_of::(); + // A key, its slot beside the value, and room in the index a large dictionary keeps. + let entry = |key: &[u8]| key.len().saturating_add(std::mem::size_of::<(crate::Name, Object)>()).saturating_add(16); + let dict = + |d: &crate::Dict, start: usize| d.iter().fold(start, |n, (k, v)| n.saturating_add(entry(k)).saturating_add(held_bytes(v, data, depth + 1))); match object { - Object::String(s) => s.bytes.len(), - Object::Stream(s) => { - let own = if s.raw.shares(data) { 0 } else { s.raw.len() }; - s.dict.iter().fold(own, |n, (_, v)| n.saturating_add(owned_bytes(v, data, depth + 1))) - } - Object::Array(a) => a.iter().fold(0usize, |n, v| n.saturating_add(owned_bytes(v, data, depth + 1))), - Object::Dict(d) => d.iter().fold(0usize, |n, (_, v)| n.saturating_add(owned_bytes(v, data, depth + 1))), - _ => 0, + Object::String(s) => node.saturating_add(s.bytes.len()), + Object::Name(n) => node.saturating_add(n.len()), + Object::Stream(s) => dict(&s.dict, node.saturating_add(if s.raw.shares(data) { 0 } else { s.raw.len() })), + Object::Array(a) => a.iter().fold(node, |n, v| n.saturating_add(held_bytes(v, data, depth + 1))), + Object::Dict(d) => dict(d, node), + _ => node, } } diff --git a/crates/cos/src/document/tests.rs b/crates/cos/src/document/tests.rs index cca4b87326..4c7b3eb652 100644 --- a/crates/cos/src/document/tests.rs +++ b/crates/cos/src/document/tests.rs @@ -1109,7 +1109,8 @@ fn temporary_reader_keeps_file_views_and_evicts_data_of_its_own() { // Data of its own (decrypted streams, strings) counts: past the budget the cache is // cleared after the next read, including a failed one. let owned = Object::Stream(crate::Stream::from_raw(Dict::new(), vec![b'y'; ObjectReader::STREAM_BYTES + 1])); - reader.document.cache.lock().unwrap().insert(3, Arc::new(owned)); + let size = held_bytes(&owned, &reader.document.data, 0); + reader.document.cache.lock().unwrap().insert(3, Arc::new(owned), size); assert_eq!(*reader.get(ObjRef::new(99, 0)), Object::Null); assert!(reader.document.cache.lock().unwrap().is_empty(), "owned data over budget is evicted"); } @@ -1192,13 +1193,14 @@ fn editor_cache_counts_deeply_nested_strings() { source.update_dict(source.root().unwrap(), |d| d.set(b"Extension".to_vec(), Object::Array(objects))).unwrap(); let bytes = Arc::new(crate::write_full(&source, &crate::SaveOptions::default()).unwrap()); let doc = Document::open(bytes).unwrap(); - assert_eq!(owned_bytes(&nested, &doc.data, 0), 1 << 20); + let held = held_bytes(&nested, &doc.data, 0); + assert!((1 << 20..(1 << 20) + 4096).contains(&held), "the string and a little tree: {held}"); let root = doc.get(doc.root().unwrap()); for reference in root.as_dict().unwrap().get(b"Extension").unwrap().as_array().unwrap() { let Object::Ref(reference) = reference else { panic!("indirect object") }; drop(doc.get(*reference)); let cache = doc.cache.lock().unwrap(); - let owned = cache.values().fold(0usize, |n, o| n.saturating_add(owned_bytes(o, &doc.data, 0))); + let owned = cache.values().fold(0usize, |n, o| n.saturating_add(held_bytes(o, &doc.data, 0))); let strings = cache.values().filter(|o| o.as_array().is_some()).count(); assert!(strings << 20 <= Document::EDITOR_CACHE_BYTES + (1 << 20), "{strings} MiB strings cached, {owned} bytes counted"); } @@ -1240,8 +1242,8 @@ fn editor_cache_stays_bounded() { #[test] fn editor_cache_byte_bound_fires() { - // 40 × 1 MB strings: far below the count cap, above the 32 MB byte budget. Each - // newcomer exceeds EDITOR_LARGE_OBJECT, so every insert takes a full accounting pass. + // 40 × 1 MB strings: far below the count cap, above the 32 MB byte budget, which is + // checked after every insertion. let mut source = Document::new_empty(); let objects: Vec<_> = (0..40) .map(|i| { @@ -1701,3 +1703,50 @@ fn a_stream_whose_length_is_itself_and_never_ends_loads_quickly() { }); rx.recv_timeout(std::time::Duration::from_secs(20)).expect("loading must not retry exponentially"); } + +/// The cache keeps the sum of what its objects hold as they come and go, so neither reader has +/// to measure the cache again on every read (#5873). +#[test] +fn the_object_cache_keeps_its_total_as_objects_come_and_go() { + let data = Arc::new(Vec::new()); + let one = Arc::new(Object::String(crate::PdfString::literal(vec![b'x'; 100]))); + let two = Arc::new(Object::Array(vec![Object::Int(1); 10])); + let (a, b) = (held_bytes(&one, &data, 0), held_bytes(&two, &data, 0)); + let mut cache = super::state::ObjectCache::default(); + cache.insert(1, one.clone(), a); + cache.insert(2, two, b); + assert_eq!(cache.owned(), a + b); + cache.insert(2, one, a); + assert_eq!(cache.owned(), a + a, "a replaced object no longer counts"); + cache.retain(|n| *n == 1); + assert_eq!((cache.len(), cache.owned()), (1, a)); + cache.clear(); + assert_eq!((cache.len(), cache.owned()), (0, 0)); +} + +/// A dictionary of numbers owns no string or stream bytes, but parsed it is tens of thousands +/// of values: InDesign's per-page `/PieceInfo`. Counting only strings and streams, the editing +/// cache kept a thousand such pages and a 35 MB book held 1.5 GB (#5873). What the parsed tree +/// holds counts now, so the byte budget bounds them. +#[test] +fn the_editor_cache_charges_a_dictionary_for_the_values_it_holds() { + let entries: String = (0..2000).map(|i| format!("/{i}[{i} 141 3 116.22 -375.993 1.0]")).collect(); + let dict = format!("<< /PieceInfo << /InDesign << /Map << {entries} >> >> >> >>"); + let count = 300; + let refs: String = (0..count).map(|i| format!("{} 0 R ", i + 2)).collect(); + let mut bodies = vec![format!("<< /Type /Catalog /Extension [{refs}] >>")]; + bodies.extend((0..count).map(|_| dict.clone())); + let bodies: Vec<&str> = bodies.iter().map(String::as_str).collect(); + let doc = Document::open(Arc::new(build(&bodies, "/Root 1 0 R"))).unwrap(); + let one = doc.get(crate::ObjRef::new(2, 0)); + let held = held_bytes(&one, &doc.data, 0); + assert!(held > 2000 * std::mem::size_of::(), "the parsed tree counts: {held} bytes"); + for i in 0..count { + drop(doc.get(crate::ObjRef::new(i as u32 + 2, 0))); + } + let cache = doc.cache.lock().unwrap(); + assert!(cache.owned() <= Document::EDITOR_CACHE_BYTES, "{} bytes held", cache.owned()); + assert!(cache.len() < count, "the byte budget evicted some, below the count cap: {} kept", cache.len()); + let sum = cache.values().fold(0usize, |n, o| n.saturating_add(held_bytes(o, &doc.data, 0))); + assert_eq!(cache.owned(), sum, "the kept total is the cache's own"); +} diff --git a/crates/cos/src/lib.rs b/crates/cos/src/lib.rs index a35902a031..6187acb846 100644 --- a/crates/cos/src/lib.rs +++ b/crates/cos/src/lib.rs @@ -22,7 +22,7 @@ mod parser; mod security; mod writer; -pub use budget::{DecodeBudget, MAX_PAGE_DECODED, MAX_PAGE_FORMS}; +pub use budget::{DecodeBudget, ImageBudget, MAX_PAGE_DECODED, MAX_PAGE_FORMS}; pub use bytes::Bytes; pub use document::{Document, ReadState, Revision, SourceIdentity, XrefEntry}; pub use object::{Dict, MAX_DECODED, MAX_JBIG2_GLOBALS, Name, ObjRef, Object, PdfString, Stream}; diff --git a/crates/cos/src/object.rs b/crates/cos/src/object.rs index 400fc29962..5d437faa82 100644 --- a/crates/cos/src/object.rs +++ b/crates/cos/src/object.rs @@ -306,6 +306,14 @@ impl Stream { self.decode_chain(max, decode) } + /// [`Stream::decoded_within`] spending from `work`, what an operation may still do across a + /// document's images ([`pdfcraft_filters::decode_tolerant_within`]). + pub(crate) fn decoded_spending(&self, max: usize, work: &mut u64) -> Result, CosError> { + let filter = |e: pdfcraft_filters::FilterError| CosError::Filter(e.to_string()); + let chain = self.readable_filters().map_err(filter)?; + pdfcraft_filters::decode_tolerant_within(&chain, &self.raw, max.min(MAX_DECODED), work).map_err(filter) + } + /// The stream decoded through its filters by `decode`, or copied when it has none, within /// `max` and [`MAX_DECODED`]. fn decode_chain( diff --git a/crates/cos/src/parser.rs b/crates/cos/src/parser.rs index 1e9b45ad61..709659f537 100644 --- a/crates/cos/src/parser.rs +++ b/crates/cos/src/parser.rs @@ -341,7 +341,11 @@ impl<'a> Lexer<'a> { let s = std::str::from_utf8(tok).map_err(|_| self.err("bad number"))?; if s.contains('.') { // Tolerate forms like "--5", "5-" or "1.2.3" by parsing the longest valid prefix. - let cleaned: String = s.trim_start_matches('+').replacen("--", "-", 1); + // Only a doubled sign needs a cleaned copy: a page of InDesign `/PieceInfo` is + // thousands of plain reals, and building a copy and a substring search for each + // was a large part of reading one (#5873). + let t = s.trim_start_matches('+'); + let cleaned = if t.as_bytes().windows(2).any(|w| w == b"--") { std::borrow::Cow::Owned(t.replacen("--", "-", 1)) } else { t.into() }; let v = cleaned.get(..real_prefix_len(cleaned.as_bytes())).and_then(|p| parse_counted::(p).ok()); return Ok(Object::Real(v.unwrap_or(0.0))); } @@ -707,4 +711,13 @@ mod tests { let mut lx = Lexer::new(two.as_bytes(), 0); assert!(lx.object().is_ok() && lx.object().is_ok()); } + + /// A plain real is read without a cleaned copy of its token; the forms that need one read + /// as they did (#5873). + #[test] + fn reals_read_the_same_with_and_without_a_doubled_sign() { + for (token, want) in [("1.5", 1.5), ("-375.993", -375.993), ("+2.25", 2.25), ("--5.5", -5.5), ("1.2.3", 1.2), ("-.5", -0.5), ("0.0", 0.0)] { + assert_eq!(Lexer::new(token.as_bytes(), 0).object().unwrap(), Object::Real(want), "{token}"); + } + } } diff --git a/crates/create/README.md b/crates/create/README.md index 555d8b3aba..f72f70aa26 100644 --- a/crates/create/README.md +++ b/crates/create/README.md @@ -27,12 +27,14 @@ Layer L4. Create a PDF (Acrobat's Create a PDF tool), execution plan M10.2: Every function returns a `pdfcraft_cos::Document`; the caller writes it. Image export and Save Image As apply each lossless image's Decode pair before converting its color components. -JBIG2 images and masks are decoded through `pdfcraft_cos::Document::decoded_image` (`pdfcraft_filters::decode_jbig2`), behind +JBIG2 images and masks are decoded through `pdfcraft_cos::ImageBudget` (`pdfcraft_filters::decode_jbig2_within`), behind other filters too, with the `/JBIG2Globals` of their own `/DecodeParms` entry, as `JBIG2Decode` gives them: black as 0. An image whose JBIG2 page isn't its size (PdfCraft's renderer draws the whole page into the image; the page is refused before it is decoded), or whose globals can't be read or decode to more than 32 MiB (they are decoded before the page's size is known, so they have a -limit of their own), is skipped; such a mask is left out and the image exported opaque, as JPX and CCITT -masks are. +limit of their own), is skipped, and such a mask is left out and the image exported opaque, as JPX and CCITT masks are. +Past what one export may decode, which its images share, filters, decoders and pixels alike (`ImageBudget`; a JPEG when it has to be +decoded, as a mask, to apply one, or to undo a CMYK file's inversion, and not when it is written as it is), an image is skipped, and so is one whose mask is past it, which would otherwise come out showing what the mask hides. An export also stops at 2 GiB of files held, or twice the document if that +is more, since they stay in memory until it ends. Indexed Decode values select palette entries after rounding and clipping. Color-key masks compare the original samples. Missing, null or malformed Decode arrays keep the default mapping. Soft-mask Decode intervals map samples to opacity before the mask is resized, including reversed ranges and indirect entries. diff --git a/crates/create/src/extract.rs b/crates/create/src/extract.rs index 34d479506b..d5103071e6 100644 --- a/crates/create/src/extract.rs +++ b/crates/create/src/extract.rs @@ -6,7 +6,8 @@ use std::collections::HashSet; -use pdfcraft_cos::{Dict, Document, ObjRef, Object, Stream}; +use pdfcraft_cos::{Dict, Document, ImageBudget, MAX_DECODED, ObjRef, Object, Stream}; +use pdfcraft_filters::FilterError; /// One image, ready to write. #[derive(Clone, Debug, PartialEq)] @@ -31,12 +32,29 @@ pub struct ImageExport { /// Images larger than this many pixels are skipped (memory). const MAX_PIXELS: u64 = 100_000_000; +/// What one export may hold of the files it makes: they are all in memory until it ends, and a file +/// of a few KB can make gigabytes of PNG. Images past it are left out, with the reason. +const MAX_EXPORT_BYTES: usize = 2 << 30; + +/// What an export of a file of `file_bytes` may hold: twice the file if that is more than +/// [`MAX_EXPORT_BYTES`], so that a file of large images is exported whole. +pub(crate) fn export_bytes(file_bytes: usize) -> usize { + MAX_EXPORT_BYTES.max(file_bytes.saturating_mul(2)) +} + /// The images of `pages` (0-based; each image once, on the first page using it), skipping /// those with fewer than `min_side` pixels on their shorter side. pub fn extract_images(doc: &Document, pages: &[usize], min_side: u32) -> ImageExport { + extract_images_within(doc, pages, min_side, &mut ImageBudget::new(doc), export_bytes(doc.bytes().len())) +} + +/// [`extract_images`] within `budget`, and holding `max_bytes` of files. An image past either is +/// left out, with the reason. +pub(crate) fn extract_images_within(doc: &Document, pages: &[usize], min_side: u32, budget: &mut ImageBudget, max_bytes: usize) -> ImageExport { let all = pdfcraft_model::pages(doc); let mut out = ImageExport::default(); let mut seen = HashSet::new(); + let mut held = 0usize; for &p in pages { let Some(page) = all.get(p) else { continue }; let mut refs = Vec::new(); @@ -53,8 +71,15 @@ pub fn extract_images(doc: &Document, pages: &[usize], min_side: u32) -> ImageEx if w <= 0 || h <= 0 || (w.min(h) as u64) < min_side as u64 { continue; } - match image(doc, s) { - Ok((extension, data)) => out.images.push(ExtractedImage { page: p, object: r, width: w as u32, height: h as u32, extension, data }), + if held >= max_bytes { + out.skipped.push((p, r, "more images than one export can hold".into())); + continue; + } + match image(doc, s, budget) { + Ok((extension, data)) => { + held = held.saturating_add(data.len()); + out.images.push(ExtractedImage { page: p, object: r, width: w as u32, height: h as u32, extension, data }); + } Err(why) => out.skipped.push((p, r, why)), } } @@ -64,8 +89,13 @@ pub fn extract_images(doc: &Document, pages: &[usize], min_side: u32) -> ImageEx /// One image XObject as a file: JPEG as is, else PNG ("Save image as"). pub fn image_file(doc: &Document, image: ObjRef) -> Result<(&'static str, Vec), String> { + image_file_within(doc, image, &mut ImageBudget::new(doc)) +} + +/// [`image_file`] within `budget`, for a caller making a file of many images. +pub fn image_file_within(doc: &Document, image: ObjRef, budget: &mut ImageBudget) -> Result<(&'static str, Vec), String> { match &*doc.get(image) { - Object::Stream(s) if s.dict.name(b"Subtype") == Some(b"Image") => self::image(doc, s), + Object::Stream(s) if s.dict.name(b"Subtype") == Some(b"Image") => self::image(doc, s, budget), _ => Err("not an image".into()), } } @@ -100,20 +130,20 @@ fn filters(s: &Stream) -> Vec> { } } -/// The samples of image `s`, decoded ([`Document::decoded_image`]): through its filters, with a +/// The samples of image `s`, decoded ([`ImageBudget::decode`]): through its filters, with a /// `/DecodeParms` dictionary given by reference, or as an array's entry, or with numbers inside by /// reference, read too (a predictor given so would otherwise be lost); a CCITT fax or JBIG2 image /// through its decoder too, behind other filters as well, a JBIG2 image with its `/JBIG2Globals`. /// A JBIG2 page has to be the image's size, which the caller checked against the export's limit, /// before the page is decoded. -fn decoded(doc: &Document, s: &Stream) -> Result, String> { - doc.decoded_image(s).map_err(|e| e.to_string()) +fn decoded(doc: &Document, s: &Stream, budget: &mut ImageBudget) -> Result, String> { + budget.decode(doc, s, MAX_DECODED).map_err(|e| e.to_string()) } /// The file for one image: its JPEG data as is, or a PNG. An image with transparency (a soft /// mask, a stencil `/Mask` or a colour-key `/Mask`) is always a PNG with that transparency as /// alpha, JPEG images included, so cut-out images keep their transparent background. -fn image(doc: &Document, s: &Stream) -> Result<(&'static str, Vec), String> { +fn image(doc: &Document, s: &Stream, budget: &mut ImageBudget) -> Result<(&'static str, Vec), String> { let f = filters(s); let jpeg = matches!(f.last().map(Vec::as_slice), Some(b"DCTDecode" | b"DCT")) && f.len() == 1; match f.last().map(Vec::as_slice) { @@ -132,7 +162,12 @@ fn image(doc: &Document, s: &Stream) -> Result<(&'static str, Vec), String> }; let mask = s.dict.get(b"ImageMask").is_some_and(|m| matches!(&*doc.resolve(m), Object::Bool(true))); // A stencil mask (`ImageMask true`) has no /SMask or /Mask of its own (8.9.6.2). - let mut alpha = if mask { None } else { soft_mask(doc, s, w, h).or_else(|| stencil_mask(doc, s, w, h)) }; + let refused = budget.refused(); + let mut alpha = if mask { None } else { soft_mask(doc, s, w, h, budget).or_else(|| stencil_mask(doc, s, w, h, budget)) }; + // Without its mask the image would come out opaque, showing what the mask hides. + if budget.refused() > refused { + return Err(FilterError::Spent.to_string()); + } let key = if mask { None } else { colour_key(doc, s) }; // Keep the existing JPEG and stencil-mask Decode handling separate from lossless colour images. let endpoint = |value: Option<&Object>| value.map(|v| doc.resolve(v)).and_then(|v| v.as_f64()).filter(|v| v.is_finite()); @@ -155,13 +190,16 @@ fn image(doc: &Document, s: &Stream) -> Result<(&'static str, Vec), String> } let mut space = if mask { Space::Gray } else { space(doc, s.dict.get(b"ColorSpace"))? }; let (samples, bpc) = if jpeg { + if !budget.pay_jpeg((w as u64).saturating_mul(h as u64).saturating_mul(space.components() as u64), &s.raw) { + return Err(FilterError::Spent.to_string()); + } // Grey, RGB or CMYK samples (YCCK is converted); a JPEG that doesn't decode, or an // indexed one (not valid), is written as is, without its transparency. let Some((samples, decoded)) = jpeg_samples(&s.raw, &space, w, h) else { return as_is() }; space = decoded; (samples, 8) } else { - let data = decoded(doc, s)?; + let data = decoded(doc, s, budget)?; let bpc = if mask { 1 } else { s.dict.int(b"BitsPerComponent").unwrap_or(8) }; let bpc = match bpc { 1 => 1, @@ -252,6 +290,32 @@ fn size(w: i64, h: i64) -> Option<(usize, usize)> { (w > 0 && h > 0 && pixels <= MAX_PIXELS).then_some((w, h)) } +#[cfg(test)] +thread_local! { + /// JPEGs decoded whole, for the tests that keep one from being decoded for nothing. + pub(crate) static JPEGS_DECODED: std::cell::Cell = const { std::cell::Cell::new(0) }; +} + +/// The size a JPEG's header gives, which is what decoding it goes by, whatever its dictionary +/// says: an image of one pixel can hold a header of 500 megapixels. +fn jpeg_size(data: &[u8]) -> Option<(usize, usize)> { + use zune_jpeg::zune_core::{bytestream::ZCursor, options::DecoderOptions}; + let options = DecoderOptions::default().set_strict_mode(false).set_max_width(usize::from(u16::MAX)).set_max_height(usize::from(u16::MAX)); + let mut dec = zune_jpeg::JpegDecoder::new_with_options(ZCursor::new(data), options); + dec.decode_headers().ok()?; + dec.dimensions() +} + +/// JPEG `data`, decoded, if its header says it is `w` × `h`. +fn jpeg_of_size(data: &[u8], w: usize, h: usize) -> Option { + if jpeg_size(data)? != (w, h) { + return None; + } + #[cfg(test)] + JPEGS_DECODED.with(|n| n.set(n.get() + 1)); + image::load_from_memory_with_format(data, image::ImageFormat::Jpeg).ok() +} + /// A JPEG's samples (8 bits): grey for a grey image, CMYK as stored for a CMYK one, else RGB, /// with the space they are in. fn jpeg_samples(data: &[u8], space: &Space, w: usize, h: usize) -> Option<(Vec, Space)> { @@ -260,10 +324,7 @@ fn jpeg_samples(data: &[u8], space: &Space, w: usize, h: usize) -> Option<(Vec return cmyk_jpeg_samples(data, w, h).map(|px| (px, Space::Cmyk)), _ => {} } - let img = image::load_from_memory_with_format(data, image::ImageFormat::Jpeg).ok()?; - if img.width() as usize != w || img.height() as usize != h { - return None; - } + let img = jpeg_of_size(data, w, h)?; Some(match space { Space::Gray => (img.into_luma8().into_raw(), Space::Gray), _ => (img.into_rgb8().into_raw(), Space::Rgb), @@ -464,32 +525,35 @@ fn cmyk(c: u8, m: u8, y: u8, k: u8) -> [u8; 3] { } /// The soft mask (`/SMask`) as 8-bit alpha, scaled to the image's size when it has another. -fn soft_mask(doc: &Document, s: &Stream, w: usize, h: usize) -> Option> { +fn soft_mask(doc: &Document, s: &Stream, w: usize, h: usize, budget: &mut ImageBudget) -> Option> { let r = s.dict.get(b"SMask")?.as_ref()?; let obj = doc.get(r); let Object::Stream(m) = &*obj else { return None }; - gray_plane(doc, m, w, h) + gray_plane(doc, m, w, h, budget) } /// A stencil `/Mask` (an image mask stream, 8.9.6.3) as 8-bit alpha: its 1 samples (0 with /// `/Decode [1 0]`) hide the image. -fn stencil_mask(doc: &Document, s: &Stream, w: usize, h: usize) -> Option> { +fn stencil_mask(doc: &Document, s: &Stream, w: usize, h: usize, budget: &mut ImageBudget) -> Option> { let r = s.dict.get(b"Mask")?.as_ref()?; let obj = doc.get(r); let Object::Stream(m) = &*obj else { return None }; - Some(gray_plane(doc, m, w, h)?.into_iter().map(|v| 255 - v).collect()) + Some(gray_plane(doc, m, w, h, budget)?.into_iter().map(|v| 255 - v).collect()) } /// A one-component mask image as 8-bit values (its `/Decode` interval applied), scaled to /// `w` × `h`. `None` when it can't be decoded (JPEG 2000 masks). -fn gray_plane(doc: &Document, m: &Stream, w: usize, h: usize) -> Option> { +fn gray_plane(doc: &Document, m: &Stream, w: usize, h: usize, budget: &mut ImageBudget) -> Option> { let (mw, mh) = size(m.dict.int(b"Width")?, m.dict.int(b"Height")?)?; let stencil = m.dict.get(b"ImageMask").is_some_and(|v| matches!(&*doc.resolve(v), Object::Bool(true))); let f = filters(m); let mut px = match f.last().map(Vec::as_slice) { Some(b"DCTDecode" | b"DCT") if f.len() == 1 => { - let img = image::load_from_memory_with_format(&m.raw, image::ImageFormat::Jpeg).ok()?.into_luma8(); - (img.width() as usize == mw && img.height() as usize == mh).then(|| img.into_raw())? + // Past the allowance the image goes too: `image` sees this one refused. + if !budget.pay_jpeg((mw as u64).saturating_mul(mh as u64), &m.raw) { + return None; + } + jpeg_of_size(&m.raw, mw, mh)?.into_luma8().into_raw() } Some(b"DCTDecode" | b"DCT" | b"JPXDecode") => return None, _ => { @@ -503,7 +567,7 @@ fn gray_plane(doc: &Document, m: &Stream, w: usize, h: usize) -> Option> _ => return None, }; let max = (1u32 << bpc.min(8)) - 1; - unpack(&decoded(doc, m).ok()?, mw, mh, 1, bpc)?.into_iter().map(|v| (v as u32 * 255 / max) as u8).collect() + unpack(&decoded(doc, m, budget).ok()?, mw, mh, 1, bpc)?.into_iter().map(|v| (v as u32 * 255 / max) as u8).collect() } }; if let Some([lo, hi]) = decode(doc, m, 1).and_then(|pairs| pairs.first().copied()) { diff --git a/crates/create/src/lib.rs b/crates/create/src/lib.rs index 36b52d4211..6346e85120 100644 --- a/crates/create/src/lib.rs +++ b/crates/create/src/lib.rs @@ -6,7 +6,7 @@ use pdfcraft_cos::{Dict, Document, ObjRef, Object, PdfString, Stream, serialize} mod extract; mod upright_image; -pub use extract::{ExtractedImage, ImageExport, extract_images, image_file}; +pub use extract::{ExtractedImage, ImageExport, extract_images, image_file, image_file_within}; use pdfcraft_fonts::{literal, win_ansi, wrap}; #[derive(Debug, thiserror::Error, PartialEq)] @@ -23,29 +23,48 @@ pub const LETTER: (f64, f64) = (612.0, 792.0); /// The largest page side PDF allows (ISO 32000-2 Annex C: 14 400 units). const MAX_SIDE: f64 = 14_400.0; -fn add_page(doc: &mut Document, w: f64, h: f64, resources: Dict, content: Option>) -> Result { - // `Document::new_empty` always has a page tree. - let pages = doc - .root() - .and_then(|r| doc.get(r).as_dict().and_then(|d| d.reference(b"Pages"))) - .ok_or_else(|| CreateError::Invalid("the new document has no page tree".into()))?; - let mut page = Dict::new(); - page.set(b"Type".to_vec(), Object::name("Page")); - page.set(b"Parent".to_vec(), Object::Ref(pages)); - page.set(b"MediaBox".to_vec(), Object::Array(vec![0.into(), 0.into(), Object::Real(w), Object::Real(h)])); - page.set(b"Resources".to_vec(), Object::Dict(resources)); - if let Some(c) = content { - let s = doc.add(Object::Stream(Stream::flate(Dict::new(), &c))); - page.set(b"Contents".to_vec(), Object::Ref(s)); +/// The page tree of a document being made, with the pages added to it so far: its `/Kids` are +/// written once, by [`Pages::finish`]. Adding each page to the tree in the document would copy every +/// page before it, which a text of a million form feeds makes quadratic. +struct Pages { + tree: ObjRef, + kids: Vec, +} + +impl Pages { + /// The page tree of `doc`, with the pages it has. + fn of(doc: &Document) -> Result { + // `Document::new_empty` always has a page tree. + let tree = doc + .root() + .and_then(|r| doc.get(r).as_dict().and_then(|d| d.reference(b"Pages"))) + .ok_or_else(|| CreateError::Invalid("the new document has no page tree".into()))?; + let kids = doc.get(tree).as_dict().and_then(|d| d.get(b"Kids")).and_then(|k| k.as_array().cloned()).unwrap_or_default(); + Ok(Self { tree, kids }) + } + + fn add(&mut self, doc: &mut Document, w: f64, h: f64, resources: Dict, content: Option>) { + let mut page = Dict::new(); + page.set(b"Type".to_vec(), Object::name("Page")); + page.set(b"Parent".to_vec(), Object::Ref(self.tree)); + page.set(b"MediaBox".to_vec(), Object::Array(vec![0.into(), 0.into(), Object::Real(w), Object::Real(h)])); + page.set(b"Resources".to_vec(), Object::Dict(resources)); + if let Some(c) = content { + let s = doc.add(Object::Stream(Stream::flate(Dict::new(), &c))); + page.set(b"Contents".to_vec(), Object::Ref(s)); + } + self.kids.push(Object::Ref(doc.add(page))); + } + + /// Writes the pages added into the tree. + fn finish(self, doc: &mut Document) -> Result<(), CreateError> { + let count = i64::try_from(self.kids.len()).map_err(|_| CreateError::Invalid("too many pages".into()))?; + doc.update_dict(self.tree, |d| { + d.set(b"Count".to_vec(), Object::Int(count)); + d.set(b"Kids".to_vec(), Object::Array(self.kids)); + }) + .map_err(|e| CreateError::Invalid(e.to_string())) } - let r = doc.add(page); - let _ = doc.update_dict(pages, |d| { - let mut kids = d.get(b"Kids").and_then(|k| k.as_array().cloned()).unwrap_or_default(); - kids.push(Object::Ref(r)); - d.set(b"Count".to_vec(), Object::Int(kids.len() as i64)); - d.set(b"Kids".to_vec(), Object::Array(kids)); - }); - Ok(r) } fn set_title(doc: &mut Document, title: &str) { @@ -65,9 +84,11 @@ pub fn blank(width: f64, height: f64, pages: usize) -> Result)], resolution: Ima return Err(CreateError::Invalid("no images".into())); } let mut doc = Document::new_empty(); + let mut tree = Pages::of(&doc)?; let mut profiles = Vec::new(); for img in images.iter().map(|(name, bytes)| embed(name, bytes, usize::MAX)).collect::, _>>()?.into_iter().flatten() { let dpi = match resolution { @@ -692,8 +714,9 @@ pub fn from_images_with_resolution(images: &[(String, Vec)], resolution: Ima let mut res = Dict::new(); res.set(b"XObject".to_vec(), Object::Dict(xobj)); let content = format!("q {w:.3} 0 0 {h:.3} 0 0 cm /Im0 Do Q\n").into_bytes(); - add_page(&mut doc, w, h, res, Some(content))?; + tree.add(&mut doc, w, h, res, Some(content)); } + tree.finish(&mut doc)?; if let Some((name, _)) = images.first() { set_title(&mut doc, name.rsplit_once('.').map_or(name.as_str(), |(s, _)| s)); } @@ -787,6 +810,7 @@ fn set_text(title: &str, text: &str, page: (f64, f64), font_size: f64) -> Result font.set(b"BaseFont".to_vec(), Object::name("Helvetica")); font.set(b"Encoding".to_vec(), Object::name("WinAnsiEncoding")); let fr = doc.add(font); + let mut tree = Pages::of(&doc)?; let mut page_lines: Vec> = vec![Vec::new()]; for l in lines.iter().take(lines.len().saturating_sub(1)) { if l == "\u{c}" || page_lines.last().is_some_and(|p| p.len() >= per_page) { @@ -810,8 +834,9 @@ fn set_text(title: &str, text: &str, page: (f64, f64), font_size: f64) -> Result fonts.set(b"F1".to_vec(), Object::Ref(fr)); let mut res = Dict::new(); res.set(b"Font".to_vec(), Object::Dict(fonts)); - add_page(&mut doc, w, h, res, Some(c))?; + tree.add(&mut doc, w, h, res, Some(c)); } + tree.finish(&mut doc)?; set_title(&mut doc, title); Ok(doc) } diff --git a/crates/create/src/tests.rs b/crates/create/src/tests.rs index 6df3ab73b2..9e620c19c3 100644 --- a/crates/create/src/tests.rs +++ b/crates/create/src/tests.rs @@ -124,6 +124,27 @@ fn text_is_wrapped_and_paginated() { assert!(content(p.last().unwrap()).contains("(After a form feed) Tj"), "a form feed starts a page"); } +#[test] +fn text_of_many_form_feeds_makes_its_pages_in_linear_time() { + // Each form feed starts a page: adding each to the page tree copied all the pages before it, + // which made forty thousand of them take over a minute in a debug build, against about two + // seconds when the tree is written once. + let text = "x\u{c}".repeat(40_000); + let start = std::time::Instant::now(); + let doc = from_text("many", &text, LETTER, 11.0).unwrap(); + let took = start.elapsed(); + let tree = doc.get(doc.get(doc.root().unwrap()).as_dict().unwrap().reference(b"Pages").unwrap()); + let tree = tree.as_dict().unwrap(); + assert_eq!(tree.get(b"Kids").and_then(|k| k.as_array()).map(|a| a.len()), Some(40_001)); + assert_eq!(tree.int(b"Count"), Some(40_001)); + assert!(took < std::time::Duration::from_secs(30), "{took:?}"); + // Blank documents and pages made from images keep their pages, in order. + let doc = reopen(&blank(200.0, 300.0, 3).unwrap()); + assert_eq!(pages(&doc).len(), 3); + let doc = reopen(&from_images(&[("a.png".into(), png_bytes(false)), ("b.png".into(), png_bytes(true))]).unwrap()); + assert_eq!(pages(&doc).len(), 2); +} + #[test] fn text_keeps_leading_spaces_and_tabs() { let doc = reopen(&from_text("t", " indented\n\ttabbed\nplain", LETTER, 11.0).unwrap()); @@ -2234,6 +2255,260 @@ fn jbig2_globals_are_decoded_within_a_limit_of_their_own() { } } +/// One allowance for all the images of an export: an image past it is left out, saying so. +#[test] +fn jbig2_images_past_the_exports_allowance_are_left_out_with_the_reason() { + use pdfcraft_cos::{Dict, Document, ImageBudget, Object, Stream}; + let mut dict = Dict::new(); + dict.set(b"Subtype".to_vec(), Object::name("Image")); + dict.set(b"Width".to_vec(), Object::Int(16)); + dict.set(b"Height".to_vec(), Object::Int(2)); + dict.set(b"BitsPerComponent".to_vec(), Object::Int(1)); + dict.set(b"ColorSpace".to_vec(), Object::name("DeviceGray")); + dict.set(b"Filter".to_vec(), Object::name("JBIG2Decode")); + let image = Stream::from_raw(dict, pdfcraft_filters::encode_jbig2_generic(&[0xFF; 4], 16, 2).unwrap()); + let mut cost = ImageBudget::with_work(u64::MAX); + cost.decode(&Document::new_empty(), &image, 1 << 20).unwrap(); + let cost = u64::MAX - cost.work_left(); + + let pdf = b"%PDF-1.7\n1 0 obj << /Type /Catalog /Pages 2 0 R >> endobj\n2 0 obj << /Type /Pages /Kids [3 0 R] /Count 1 >> endobj\n3 0 obj << /Type /Page /Parent 2 0 R /MediaBox [0 0 100 100] >> endobj\ntrailer << /Root 1 0 R >>\n%%EOF".to_vec(); + let mut doc = Document::open(std::sync::Arc::new(pdf)).unwrap(); + let (a, b) = (doc.add(Object::Stream(image.clone())), doc.add(Object::Stream(image))); + let mut xobjects = Dict::new(); + xobjects.set(b"A".to_vec(), Object::Ref(a)); + xobjects.set(b"B".to_vec(), Object::Ref(b)); + let mut resources = Dict::new(); + resources.set(b"XObject".to_vec(), Object::Dict(xobjects)); + let page = pdfcraft_model::pages(&doc).swap_remove(0).obj; + doc.update_dict(page, |p| p.set(b"Resources".to_vec(), Object::Dict(resources))).unwrap(); + + let export = crate::extract::extract_images_within(&doc, &[0], 1, &mut ImageBudget::with_work(cost), usize::MAX); + assert_eq!(export.images.len(), 1); + assert_eq!(export.skipped.len(), 1); + assert!(export.skipped[0].2.contains("more image decoding than"), "{:?}", export.skipped); + // What an export holds is bounded too: the files are all in memory until it ends. + let export = crate::extract::extract_images_within(&doc, &[0], 1, &mut ImageBudget::with_work(u64::MAX), 1); + assert_eq!(export.images.len(), 1, "the first goes past it"); + assert_eq!(export.skipped.len(), 1); + assert!(export.skipped[0].2.contains("than one export can hold"), "{:?}", export.skipped); + // A file of many images shares one allowance too, image by image. + let mut budget = ImageBudget::with_work(cost); + assert!(crate::extract::image_file_within(&doc, a, &mut budget).is_ok()); + assert!(crate::extract::image_file_within(&doc, b, &mut budget).is_err()); +} + +/// An image that isn't JBIG2 shares the allowance too: a file of filter bombs would hold an export +/// as long as one of JBIG2. What isn't decoded here, a JPEG, is still exported. +#[test] +fn flate_images_past_the_exports_allowance_are_left_out_with_the_reason() { + use pdfcraft_cos::{Dict, Document, ImageBudget, Object, Stream}; + let image = |filter: &str, raw: Vec| { + let mut dict = Dict::new(); + dict.set(b"Subtype".to_vec(), Object::name("Image")); + dict.set(b"Width".to_vec(), Object::Int(2)); + dict.set(b"Height".to_vec(), Object::Int(2)); + dict.set(b"BitsPerComponent".to_vec(), Object::Int(8)); + dict.set(b"ColorSpace".to_vec(), Object::name("DeviceGray")); + dict.set(b"Filter".to_vec(), Object::name(filter)); + Stream::from_raw(dict, raw) + }; + let flate = image("FlateDecode", pdfcraft_filters::encode_flate(&[0x80; 4])); + let mut cost = ImageBudget::with_work(u64::MAX); + cost.decode(&Document::new_empty(), &flate, 1 << 20).unwrap(); + let cost = u64::MAX - cost.work_left(); + + let mut doc = Document::new_empty(); + let (a, b) = (doc.add(Object::Stream(flate.clone())), doc.add(Object::Stream(flate))); + let mut budget = ImageBudget::with_work(cost); + assert!(crate::extract::image_file_within(&doc, a, &mut budget).is_ok()); + let refused = crate::extract::image_file_within(&doc, b, &mut budget).unwrap_err(); + assert!(refused.contains("more image decoding than"), "{refused}"); + assert_eq!(budget.refused(), 1); + + let jpeg = image::RgbImage::from_pixel(2, 2, image::Rgb([9, 9, 9])); + let mut bytes = Vec::new(); + jpeg.write_to(&mut std::io::Cursor::new(&mut bytes), image::ImageFormat::Jpeg).unwrap(); + let jpeg = doc.add(Object::Stream(image("DCTDecode", bytes))); + assert!(crate::extract::image_file_within(&doc, jpeg, &mut budget).is_ok(), "nothing charged"); + assert_eq!(budget.refused(), 1); +} + +/// A JPEG is written as it is, at no cost, unless something means decoding it, here a mask: that +/// pays for its samples, and past the allowance the image goes, with the reason, as it would come out without +/// its transparency otherwise. +#[test] +fn a_jpeg_that_has_to_be_decoded_shares_the_allowance() { + use pdfcraft_cos::{Dict, Document, ImageBudget, Object, Stream}; + let mut jpeg = Vec::new(); + image::RgbImage::from_pixel(4, 4, image::Rgb([9, 9, 9])).write_to(&mut std::io::Cursor::new(&mut jpeg), image::ImageFormat::Jpeg).unwrap(); + let image_dict = |extra: Option<(&[u8], Object)>| { + let mut d = Dict::new(); + d.set(b"Subtype".to_vec(), Object::name("Image")); + d.set(b"Width".to_vec(), Object::Int(4)); + d.set(b"Height".to_vec(), Object::Int(4)); + d.set(b"BitsPerComponent".to_vec(), Object::Int(8)); + d.set(b"ColorSpace".to_vec(), Object::name("DeviceRGB")); + d.set(b"Filter".to_vec(), Object::name("DCTDecode")); + if let Some((key, value)) = extra { + d.set(key.to_vec(), value); + } + d + }; + let mut doc = Document::new_empty(); + let mut mask = Dict::new(); + mask.set(b"Subtype".to_vec(), Object::name("Image")); + mask.set(b"Width".to_vec(), Object::Int(4)); + mask.set(b"Height".to_vec(), Object::Int(4)); + mask.set(b"BitsPerComponent".to_vec(), Object::Int(8)); + mask.set(b"ColorSpace".to_vec(), Object::name("DeviceGray")); + let mask = doc.add(Object::Stream(Stream::from_raw(mask, vec![0x80; 16]))); + let doc_jpeg_len = jpeg.len(); + let masked = doc.add(Object::Stream(Stream::from_raw(image_dict(Some((b"SMask", Object::Ref(mask)))), jpeg.clone()))); + let plain = doc.add(Object::Stream(Stream::from_raw(image_dict(None), jpeg))); + + let mut budget = ImageBudget::with_work(0); + assert!(crate::extract::image_file_within(&doc, plain, &mut budget).is_ok(), "written as it is"); + assert_eq!(budget.refused(), 0); + let mut budget = ImageBudget::with_work(u64::MAX); + assert!(crate::extract::image_file_within(&doc, masked, &mut budget).is_ok()); + let cost = u64::MAX - budget.work_left(); + let read = 4 * doc_jpeg_len as u64; + assert_eq!(cost, 16 + 16 + 2 * 4 * 4 * 3 + read, "the mask's bytes and pixels, the JPEG's samples twice and its reading"); + let mut budget = ImageBudget::with_work(cost - 1); + let refused = crate::extract::image_file_within(&doc, masked, &mut budget).unwrap_err(); + assert!(refused.contains("more image decoding than"), "{refused}"); + assert_eq!(budget.refused(), 1); +} + +/// A JPEG that is itself a mask pays for its samples, each time an image reads it: images can +/// share one, and only the images are ever seen once. +#[test] +fn a_jpeg_mask_pays_for_its_samples() { + use pdfcraft_cos::{Dict, Document, ImageBudget, Object, Stream}; + let mut jpeg = Vec::new(); + image::GrayImage::from_pixel(4, 4, image::Luma([90])).write_to(&mut std::io::Cursor::new(&mut jpeg), image::ImageFormat::Jpeg).unwrap(); + let mut mask = Dict::new(); + mask.set(b"Subtype".to_vec(), Object::name("Image")); + mask.set(b"Width".to_vec(), Object::Int(4)); + mask.set(b"Height".to_vec(), Object::Int(4)); + mask.set(b"BitsPerComponent".to_vec(), Object::Int(8)); + mask.set(b"ColorSpace".to_vec(), Object::name("DeviceGray")); + mask.set(b"Filter".to_vec(), Object::name("DCTDecode")); + let mut doc = Document::new_empty(); + let read = 4 * jpeg.len() as u64; + let mask = doc.add(Object::Stream(Stream::from_raw(mask, jpeg))); + let mut image = Dict::new(); + image.set(b"Subtype".to_vec(), Object::name("Image")); + image.set(b"Width".to_vec(), Object::Int(1)); + image.set(b"Height".to_vec(), Object::Int(1)); + image.set(b"BitsPerComponent".to_vec(), Object::Int(8)); + image.set(b"ColorSpace".to_vec(), Object::name("DeviceGray")); + image.set(b"SMask".to_vec(), Object::Ref(mask)); + let image = doc.add(Object::Stream(Stream::from_raw(image, vec![0x80]))); + let mut budget = ImageBudget::with_work(u64::MAX); + assert!(crate::extract::image_file_within(&doc, image, &mut budget).is_ok()); + assert_eq!(u64::MAX - budget.work_left(), 2 * 4 * 4 + read + 2, "its samples twice, its reading, and the image's byte and pixel"); + // Just short of what the mask costs: it isn't decoded, and takes the image with it. + let mut budget = ImageBudget::with_work(2 * 4 * 4 + read - 1); + let refused = crate::extract::image_file_within(&doc, image, &mut budget).unwrap_err(); + assert!(refused.contains("more image decoding than"), "{refused}"); + assert_eq!((budget.work_left(), budget.refused()), (0, 1)); +} + +/// What decoding a JPEG takes goes by its header, so that is what has to agree with the +/// dictionary before it is decoded: one image of a pixel can hold a page of 500 megapixels. The +/// file comes out as it is either way, so what shows is whether it was decoded. +#[test] +fn a_jpeg_larger_than_its_dictionary_says_isnt_decoded() { + use pdfcraft_cos::{Dict, Document, ImageBudget, Object, Stream}; + let mut jpeg = Vec::new(); + image::RgbImage::from_pixel(4, 4, image::Rgb([9, 9, 9])).write_to(&mut std::io::Cursor::new(&mut jpeg), image::ImageFormat::Jpeg).unwrap(); + // A colour key means decoding it, to find the pixels it hides. + let keyed = |side: i64| { + let mut d = Dict::new(); + d.set(b"Subtype".to_vec(), Object::name("Image")); + d.set(b"Width".to_vec(), Object::Int(side)); + d.set(b"Height".to_vec(), Object::Int(side)); + d.set(b"BitsPerComponent".to_vec(), Object::Int(8)); + d.set(b"ColorSpace".to_vec(), Object::name("DeviceRGB")); + d.set(b"Filter".to_vec(), Object::name("DCTDecode")); + d.set(b"Mask".to_vec(), Object::Array(vec![Object::Int(0); 6])); + Stream::from_raw(d, jpeg.clone()) + }; + let decodes = |doc: &Document, image: pdfcraft_cos::ObjRef| { + crate::extract::JPEGS_DECODED.with(|n| n.set(0)); + assert!(crate::extract::image_file_within(doc, image, &mut ImageBudget::with_work(u64::MAX)).is_ok()); + crate::extract::JPEGS_DECODED.with(std::cell::Cell::get) + }; + let mut doc = Document::new_empty(); + let (honest, lying) = (doc.add(Object::Stream(keyed(4))), doc.add(Object::Stream(keyed(1)))); + assert_eq!(decodes(&doc, honest), 1); + assert_eq!(decodes(&doc, lying), 0); + // The same as a mask: read as none, without being decoded. + let mut mask = keyed(1); + mask.dict.remove(b"Mask"); + let mask = doc.add(Object::Stream(mask)); + let mut image = Dict::new(); + image.set(b"Subtype".to_vec(), Object::name("Image")); + image.set(b"Width".to_vec(), Object::Int(1)); + image.set(b"Height".to_vec(), Object::Int(1)); + image.set(b"BitsPerComponent".to_vec(), Object::Int(8)); + image.set(b"ColorSpace".to_vec(), Object::name("DeviceGray")); + image.set(b"SMask".to_vec(), Object::Ref(mask)); + let image = doc.add(Object::Stream(Stream::from_raw(image, vec![0x80]))); + assert_eq!(decodes(&doc, image), 0); + // Reading the header to find that out is paid for: a mask can be mostly tables, shared by + // every image of a file, and with nothing left it isn't read. + let mut budget = ImageBudget::with_work(u64::MAX); + assert!(crate::extract::image_file_within(&doc, image, &mut budget).is_ok()); + assert_eq!(u64::MAX - budget.work_left(), 2 + 4 * jpeg.len() as u64 + 2, "its one declared sample twice, its bytes, the image's byte and pixel"); + let mut budget = ImageBudget::with_work(0); + assert!(crate::extract::image_file_within(&doc, image, &mut budget).is_err()); + assert_eq!(budget.refused(), 1, "the image goes, with its mask unread"); +} + +/// A mask past the allowance can't be left out as an unreadable one is, or the image comes out +/// opaque, showing what the mask hides: the image goes, with the reason. +#[test] +fn an_image_whose_jbig2_mask_is_past_the_allowance_is_left_out() { + use pdfcraft_cos::{Dict, Document, ImageBudget, Object, Stream}; + let mut mask = Dict::new(); + mask.set(b"Subtype".to_vec(), Object::name("Image")); + mask.set(b"Width".to_vec(), Object::Int(16)); + mask.set(b"Height".to_vec(), Object::Int(2)); + mask.set(b"BitsPerComponent".to_vec(), Object::Int(1)); + mask.set(b"ColorSpace".to_vec(), Object::name("DeviceGray")); + mask.set(b"Filter".to_vec(), Object::name("JBIG2Decode")); + let mut doc = Document::new_empty(); + let mask = doc.add(Object::Stream(Stream::from_raw(mask, pdfcraft_filters::encode_jbig2_generic(&[0xFF; 4], 16, 2).unwrap()))); + // A JPEG, read for nothing until its mask is, so only the mask can be what stops it. + let mut jpeg = Vec::new(); + image::RgbImage::from_pixel(1, 1, image::Rgb([9, 9, 9])).write_to(&mut std::io::Cursor::new(&mut jpeg), image::ImageFormat::Jpeg).unwrap(); + let mut image = Dict::new(); + image.set(b"Subtype".to_vec(), Object::name("Image")); + image.set(b"Width".to_vec(), Object::Int(1)); + image.set(b"Height".to_vec(), Object::Int(1)); + image.set(b"BitsPerComponent".to_vec(), Object::Int(8)); + image.set(b"ColorSpace".to_vec(), Object::name("DeviceRGB")); + image.set(b"Filter".to_vec(), Object::name("DCTDecode")); + image.set(b"SMask".to_vec(), Object::Ref(mask)); + let image = doc.add(Object::Stream(Stream::from_raw(image, jpeg))); + assert!(crate::extract::image_file_within(&doc, image, &mut ImageBudget::with_work(u64::MAX)).is_ok()); + let refused = crate::extract::image_file_within(&doc, image, &mut ImageBudget::with_work(0)).unwrap_err(); + assert!(refused.contains("more image decoding than"), "{refused}"); +} + +/// A large honest file keeps its images: what an export may hold grows with the file past the fixed +/// part, and a file too long to double doesn't wrap round to nothing. +#[test] +fn an_export_may_hold_twice_a_large_file() { + let fixed = crate::extract::export_bytes(0); + assert_eq!(fixed, 2 << 30); + assert_eq!(crate::extract::export_bytes(fixed / 2), fixed); + assert_eq!(crate::extract::export_bytes(fixed / 2 + 1), fixed + 2); + assert_eq!(crate::extract::export_bytes(usize::MAX), usize::MAX); +} + /// `/Decode` says which way round a stencil mask is, and its numbers can be given by reference. Read /// as absent, they gave the wrong answer, so the file came out a negative of what the page draws. #[test] diff --git a/crates/edit/src/background.rs b/crates/edit/src/background.rs index 7d745c0c10..376cb5a165 100644 --- a/crates/edit/src/background.rs +++ b/crates/edit/src/background.rs @@ -98,8 +98,13 @@ pub fn page_background(doc: &Document, page: usize) -> Result, EditE } b"sc" | b"scn" => st.fill = colour(st.space, op), b"gs" => { - if let Some(g) = op.name(0).and_then(|n| gstates.get(n)).map(|g| doc.resolve(g)).and_then(|g| g.as_dict().cloned()) { - apply_gstate(doc, &g, &mut st); + let mut held = None; + let gstate = match op.name(0).and_then(|n| gstates.get(n)) { + Some(g) => crate::text::dict_in_place(doc, g, &mut held), + None => None, + }; + if let Some(g) = gstate { + apply_gstate(doc, g, &mut st); } } b"re" => match op.nums::<4>() { diff --git a/crates/edit/src/images.rs b/crates/edit/src/images.rs index 2920a2a9ad..f4680bcc5c 100644 --- a/crates/edit/src/images.rs +++ b/crates/edit/src/images.rs @@ -379,34 +379,34 @@ pub fn reading_images(doc: &Document, page: usize) -> Result, Edi forms: &mut Forms, out: &mut Vec, ) -> Result<(), EditError> { - let xo = resources.get(b"XObject").map(|x| doc.resolve(x)).and_then(|x| x.as_dict().cloned()).unwrap_or_default(); + let mut held = None; + let xo = crate::text::resource_dict(doc, resources, b"XObject", &mut held); for (i, op) in ops.iter().enumerate() { st.apply(op)?; let ctm = st.placement.matrix; if op.is("Do") { let Some(name) = op.name(0) else { continue }; + let drawn = xo.and_then(|xo| xo.get(name)); if let Some(form) = crate::text::form_call(doc, resources, name, ctm, &forms.path, &mut forms.budget) { if let Some(r) = form.obj { forms.path.push(r); } let bounds = - xo.get(name).map(|o| doc.resolve(o)).and_then(|o| o.as_dict().and_then(|d| d.get(b"BBox")).map(|b| doc.resolve(b))).and_then( - |b| { - let a = b.as_array()?; - let [x0, y0, x1, y1] = a.as_slice() else { return None }; - Some(form.ctm.bbox([x0.as_f64()?, y0.as_f64()?, x1.as_f64()?, y1.as_f64()?])) - }, - ); + drawn.map(|o| doc.resolve(o)).and_then(|o| o.as_dict().and_then(|d| d.get(b"BBox")).map(|b| doc.resolve(b))).and_then(|b| { + let a = b.as_array()?; + let [x0, y0, x1, y1] = a.as_slice() else { return None }; + Some(form.ctm.bbox([x0.as_f64()?, y0.as_f64()?, x1.as_f64()?, y1.as_f64()?])) + }); let clip = bounds.map_or(st.placement.clip, |b| intersection(st.placement.clip, b).unwrap_or([0.0; 4])); let mut inner = ImageState::new(form.ctm, clip, st.placement.clips.clone()); let piece = stream(op); - walk(doc, &parse(&form.data).ops, &form.resources, &mut inner, &|_| piece, forms, out)?; + walk(doc, &parse(&form.data).ops, form.resources(resources), &mut inner, &|_| piece, forms, out)?; if form.obj.is_some() { forms.path.pop(); } continue; } - let Some(r) = xo.get(name).and_then(Object::as_ref) else { continue }; + let Some(r) = drawn.and_then(Object::as_ref) else { continue }; let obj = doc.get(r); let Object::Stream(s) = &*obj else { continue }; if s.dict.name(b"Subtype") != Some(b"Image") { @@ -584,6 +584,10 @@ fn sequence_end(ops: &[Op], i: usize, end: usize, opens: &[&str], close: &str) - end } +/// The stacking units of `ops[scan_start..scan_end]` that Arrange moves past one another, in +/// paint order: a `q … Q`, `BT … ET` or marked-content sequence up to its matching close (or the +/// end of the scan), a single `Do`, `sh` or inline image, or a run of other operators that ends +/// at a path-painting operator or before the next unit. Units that paint nothing are left out. pub(crate) fn content_units(ops: &[Op], scan_start: usize, scan_end: usize) -> Vec> { let mut units = Vec::new(); let mut i = scan_start; @@ -598,9 +602,9 @@ pub(crate) fn content_units(ops: &[Op], scan_start: usize, scan_end: usize) -> V sequence_end(ops, i, scan_end, &["q"], "Q") } else if op.is("BT") { sequence_end(ops, i, scan_end, &[], "ET") - } else if op.is("BI") { - sequence_end(ops, i, scan_end, &[], "EI") - } else if op.is("Do") || op.is("sh") { + } else if op.is("BI") || op.is("Do") || op.is("sh") { + // The parser emits a whole inline image (`BI` … `ID` … `EI`) as one `BI` op, so it is a + // unit of its own (#3146). i.saturating_add(1) } else { let mut j = i; diff --git a/crates/edit/src/marks.rs b/crates/edit/src/marks.rs index d936955184..344c76250f 100644 --- a/crates/edit/src/marks.rs +++ b/crates/edit/src/marks.rs @@ -286,7 +286,12 @@ pub fn expand(template: &str, page_number: u32, count: usize, bates: u64, cx: &C let digits = parts.get(1).and_then(|d| d.parse::().ok()).unwrap_or(6).clamp(1, 15); format!("{}{:0digits$}{}", parts.get(3).unwrap_or(&""), bates, parts.get(4).unwrap_or(&"")) } - _ => format!("<<{token}>>"), + _ => { + // Not a token: emit one `<` and retry, so a later token is still found. + out.push('<'); + rest = &rest[start + 1..]; + continue; + } }; out.push_str(&value); rest = &after[end + 2..]; @@ -302,3 +307,16 @@ pub(crate) fn bates_start(template: &str) -> Option { let t = &t[..t.find(">>")?]; t.split('#').nth(2).and_then(|s| s.parse().ok()).or(Some(1)) } + +#[cfg(test)] +mod expand_tests { + use super::*; + + #[test] + fn expand_token_after_extra_angle_brackets() { + let cx = Context::default(); + assert_eq!(expand("<<<1>>>", 3, 9, 1, &cx), "<3>"); + assert_eq!(expand("<< <<1>>", 3, 9, 1, &cx), "<< 3"); + assert_eq!(expand("<> <<1>>", 3, 9, 1, &cx), "<> 3"); + } +} diff --git a/crates/edit/src/tests.rs b/crates/edit/src/tests.rs index 7ec51aa74f..e78da842b8 100644 --- a/crates/edit/src/tests.rs +++ b/crates/edit/src/tests.rs @@ -5575,6 +5575,41 @@ fn reading_follows_form_xobjects() { assert!(own[0].is_form && own[0].object == Some(pdfcraft_cos::ObjRef::new(6, 0)), "{own:?}"); } +/// A page's `/XObject` and a form's `/Resources` are read wherever they are stored, and a form with +/// none of its own, or with something else there, uses the ones it was drawn with (PDF 1.1 files). +/// Each of these pages shows one line of text and one picture through one form. +#[test] +fn reading_follows_forms_however_their_resources_are_stored() { + let body = "BT /F1 12 Tf 72 700 Td (In the form) Tj ET q 20 0 0 10 5 5 cm /Im Do Q"; + let (font, direct) = ("/Font << /F1 5 0 R >>", "/XObject << /Fm 6 0 R /Im 7 0 R >>"); + for (page, form) in [ + (format!("<< {font} {direct} >>"), ""), + (format!("<< {font} /XObject 9 0 R >>"), ""), + (format!("<< /Font 10 0 R {direct} >>"), ""), + (format!("<< {font} {direct} >>"), "/Resources 99 0 R"), + (format!("<< {font} {direct} >>"), "/Resources 12"), + ("<< /XObject << /Fm 6 0 R >> >>".to_string(), "/Resources 8 0 R"), + ("<< /XObject 9 0 R >>".to_string(), "/Resources << /Font << /F1 5 0 R >> /XObject 9 0 R >>"), + ] { + let doc = build(&[ + "<< /Type /Catalog /Pages 2 0 R >>", + "<< /Type /Pages /Kids [3 0 R] /Count 1 >>", + &format!("<< /Type /Page /Parent 2 0 R /MediaBox [0 0 600 800] /Resources {page} /Contents 4 0 R >>"), + &stream("", "/Fm Do"), + "<< /Type /Font /Subtype /Type1 /BaseFont /Courier >>", + &stream(&format!("/Type /XObject /Subtype /Form /BBox [0 0 600 800] {form}"), body), + &stream("/Type /XObject /Subtype /Image /Width 1 /Height 1 /ColorSpace /DeviceGray /BitsPerComponent 8", "A"), + "<< /Font << /F1 5 0 R >> /XObject 9 0 R >>", + "<< /Fm 6 0 R /Im 7 0 R >>", + "<< /F1 5 0 R >>", + ]); + let blocks = text::reading_blocks(&doc, 0).unwrap(); + let texts: Vec<(&str, &str)> = blocks.iter().map(|b| (b.text.as_str(), b.base_font.as_str())).collect(); + assert_eq!(texts, [("In the form", "Courier")], "{page} {form}"); + assert_eq!(images::reading_images(&doc, 0).unwrap().len(), 1, "{page} {form}"); + } +} + /// A chain of forms, each drawing the next twenty times, twelve deep: within the depth cap but /// 20^11 visits without a budget. Reading stops at the page's visit budget instead of hanging. #[test] @@ -9778,6 +9813,133 @@ fn content_units_does_not_swallow_subsequent_units_on_standalone_gs() { assert_eq!(units.len(), 2); } +/// A 1 × 1 grey inline image whose one sample is `data`. +fn inline_image(data: char) -> String { + format!("BI /W 1 /H 1 /CS /G /BPC 8 ID {data} EI") +} + +/// What page 0 paints, in order: `BI x` for an inline image with sample `x`, `Do x,y` for an +/// XObject placed by a `cm` translating to x,y, and `Tj` for text. A `cm` lasts until its `Q`, so an +/// XObject moved out of its `q`/`Q` wrapper shows as a bare `Do `. +fn painted(doc: &Document) -> Vec { + let mut at = vec![String::new()]; + pdfcraft_content::parse(&page_content_bytes(doc, 0)) + .ops + .iter() + .filter_map(|op| match op.op.as_slice() { + b"q" => { + at.push(at.last().unwrap().clone()); + None + } + b"Q" => { + at.pop(); + None + } + b"cm" => { + let m = op.nums::<6>().unwrap(); + *at.last_mut().unwrap() = format!("{},{}", m[4], m[5]); + None + } + b"Do" => Some(format!("Do {}", at.last().unwrap())), + b"BI" => Some(format!("BI {}", String::from_utf8_lossy(&op.inline.as_ref().unwrap().1))), + b"Tj" => Some("Tj".into()), + _ => None, + }) + .collect() +} + +/// The index in [`images::page_images`] of the image whose box starts at `x`,`y`. +fn image_at(doc: &Document, x: f64, y: f64) -> usize { + images::page_images(doc, 0).unwrap().iter().position(|i| (i.rect[0] - x).abs() < 1e-6 && (i.rect[1] - y).abs() < 1e-6).unwrap() +} + +#[test] +fn content_units_keep_each_top_level_inline_image_to_itself() { + // The parser emits a whole inline image as one `BI` op; its unit must not run on to the end + // (#3146). Inline images at the start, side by side and at the end are one unit each. + let content = format!( + "{} q 200 0 0 100 100 100 cm /Im0 Do Q {} {} q 10 0 0 10 300 300 cm /Im0 Do Q {}", + inline_image('a'), + inline_image('b'), + inline_image('c'), + inline_image('d') + ); + let ops = pdfcraft_content::parse(content.as_bytes()).ops; + let units = images::content_units(&ops, 0, ops.len()); + assert_eq!(units, [0..1, 1..5, 5..6, 6..7, 7..11, 11..12]); +} + +#[test] +fn content_units_keep_a_nested_inline_image_inside_its_enclosing_unit() { + // A `BI` inside `q`/`Q` or a marked-content sequence stays part of that sequence's unit. + let content = format!("q {} Q /Span << /MCID 0 >> BDC {} EMC {}", inline_image('a'), inline_image('b'), inline_image('c')); + let ops = pdfcraft_content::parse(content.as_bytes()).ops; + let units = images::content_units(&ops, 0, ops.len()); + assert_eq!(units, [0..3, 3..6, 6..7]); +} + +#[test] +fn send_backward_after_a_top_level_inline_image_moves_one_step() { + // Before #3146 the inline image's unit swallowed everything after it, so SendBackward on a later + // image acted like SendToBack: it must step behind the text only. + let content = format!( + "{} q 100 0 0 100 100 100 cm /Im0 Do Q BT /F1 12 Tf 72 700 Td (Middle Text) Tj ET q 150 0 0 150 200 200 cm /Im0 Do Q", + inline_image('x') + ); + let mut doc = image_page_with(&content); + let front = image_at(&doc, 200.0, 200.0); + arrange(&mut doc, 0, front, images::ArrangeOrder::SendBackward).unwrap(); + let doc = reopen(&doc); + assert_eq!(painted(&doc), ["BI x", "Do 100,100", "Do 200,200", "Tj"]); +} + +#[test] +fn arrange_steps_an_image_past_one_inline_image_at_a_time() { + // Before #3146 BringForward on B, inside the first inline image's unit, put it in front of + // everything. One step forward is past the next inline image only, and one step back again + // is behind that inline image only. + let content = format!( + "q 100 0 0 100 100 100 cm /Im0 Do Q {} q 150 0 0 150 200 200 cm /Im0 Do Q {} BT /F1 12 Tf 72 700 Td (Text) Tj ET q 50 0 0 50 300 300 cm /Im0 Do Q", + inline_image('a'), + inline_image('b') + ); + let mut doc = image_page_with(&content); + let b = image_at(&doc, 200.0, 200.0); + arrange(&mut doc, 0, b, images::ArrangeOrder::BringForward).unwrap(); + let mut doc = reopen(&doc); + assert_eq!(painted(&doc), ["Do 100,100", "BI a", "BI b", "Do 200,200", "Tj", "Do 300,300"]); + let b = image_at(&doc, 200.0, 200.0); + arrange(&mut doc, 0, b, images::ArrangeOrder::SendBackward).unwrap(); + let doc = reopen(&doc); + assert_eq!(painted(&doc), ["Do 100,100", "BI a", "Do 200,200", "BI b", "Tj", "Do 300,300"]); +} + +#[test] +fn arrange_around_inline_images_at_the_ends_of_the_stream() { + // Before #3146 BringToFront on the last image after an inline image "succeeded" without moving + // it. It is already in front, so it is refused and nothing changes. + let content = + format!("{} q 100 0 0 100 100 100 cm /Im0 Do Q BT /F1 12 Tf 72 700 Td (Text) Tj ET q 150 0 0 150 200 200 cm /Im0 Do Q", inline_image('a')); + let mut doc = image_page_with(&content); + let before = page_content_bytes(&doc, 0); + let front = image_at(&doc, 200.0, 200.0); + assert!(arrange(&mut doc, 0, front, images::ArrangeOrder::BringToFront).is_err()); + assert!(arrange(&mut doc, 0, front, images::ArrangeOrder::BringForward).is_err()); + assert_eq!(page_content_bytes(&doc, 0), before); + // Send to back goes behind the inline image that starts the stream. + arrange(&mut doc, 0, front, images::ArrangeOrder::SendToBack).unwrap(); + let doc = reopen(&doc); + assert_eq!(painted(&doc), ["Do 200,200", "BI a", "Do 100,100", "Tj"]); + + // Bring to front goes past the inline image that ends the stream. + let content = format!("q 100 0 0 100 100 100 cm /Im0 Do Q BT /F1 12 Tf 72 700 Td (Text) Tj ET {}", inline_image('z')); + let mut doc = image_page_with(&content); + let back = image_at(&doc, 100.0, 100.0); + arrange(&mut doc, 0, back, images::ArrangeOrder::BringToFront).unwrap(); + let doc = reopen(&doc); + assert_eq!(painted(&doc), ["Tj", "BI z", "Do 100,100"]); +} + #[test] fn different_inline_soft_masks_have_distinct_identities() { let doc = Document::new_empty(); diff --git a/crates/edit/src/text.rs b/crates/edit/src/text.rs index 0599b8ed38..0fb00324b6 100644 --- a/crates/edit/src/text.rs +++ b/crates/edit/src/text.rs @@ -54,7 +54,7 @@ use fallback::{ use fallback::{add_type3_font, is_type3_fallback}; use interp::{Origin, Paint, union}; use lines::page_dict; -pub(crate) use lines::{FormBudget, content_streams, content_streams_within, form_call, rewritten_contents, splice}; +pub(crate) use lines::{FormBudget, content_streams, content_streams_within, dict_in_place, form_call, resource_dict, rewritten_contents, splice}; pub use lines::{MAX_FORM_DEPTH, MAX_FORM_VISITS, glyph_text_lines, text_lines}; pub use rewrite::{LineEdit, replace_line, rewrite_block}; use rewrite::{coincident_ops, rewrite_block_from}; diff --git a/crates/edit/src/text/interp.rs b/crates/edit/src/text/interp.rs index 2b55e51ef8..2a9f6da61a 100644 --- a/crates/edit/src/text/interp.rs +++ b/crates/edit/src/text/interp.rs @@ -773,8 +773,9 @@ pub(super) fn interpret( // `Some(properties)`: read `/ActualText`, looking named property lists up in `properties`. logical_text: Option<&Dict>, ) -> Result, EditError> { - let fonts_res = resources.get(b"Font").map(|f| doc.resolve(f)).and_then(|f| f.as_dict().cloned()).unwrap_or_default(); - let states = resources.get(b"ExtGState").map(|g| doc.resolve(g)).and_then(|g| g.as_dict().cloned()).unwrap_or_default(); + let (mut held_fonts, mut held_states, none) = (None, None, Dict::new()); + let fonts_res = super::resource_dict(doc, resources, b"Font", &mut held_fonts).unwrap_or(&none); + let states = super::resource_dict(doc, resources, b"ExtGState", &mut held_states).unwrap_or(&none); let mut out: Vec = Vec::new(); let mut ts = carry.ts.clone(); let mut at_bt = (0usize, ts.clone()); @@ -881,8 +882,12 @@ pub(super) fn interpret( if let Some(name) = op.name(0) { select_gs(&mut ts.ext_gstate, name); } - let params = op.name(0).and_then(|name| states.get(name)).map(|p| doc.resolve(p)); - if let Some(params) = params.as_deref().and_then(Object::as_dict) { + let mut held = None; + let params = match op.name(0).and_then(|name| states.get(name)) { + Some(p) => super::dict_in_place(doc, p, &mut held), + None => None, + }; + if let Some(params) = params { ts.gs.apply(doc, params); // `/LW` sets the line width as `w` does (ISO 32000-2 §8.4.5). let lw = params.get(b"LW").and_then(|w| doc.resolve(w).as_f64()).filter(|w| w.is_finite()); diff --git a/crates/edit/src/text/lines.rs b/crates/edit/src/text/lines.rs index f811f34ea6..85209a5472 100644 --- a/crates/edit/src/text/lines.rs +++ b/crates/edit/src/text/lines.rs @@ -1,3 +1,5 @@ +use std::sync::Arc; + use super::fallback::{same_font, same_paint}; use super::interp::{Carry, Origin, Pen, Shown, TextState, Ts, direction, interpret, to_frame, union}; use super::{DecodeBudget, Dict, Document, EditError, HashMap, Matrix, Object, Op, Pieces, Stream, TextLine, parse, serialize_ops}; @@ -452,10 +454,41 @@ impl FormBudget { pub(crate) struct FormCall { pub(crate) obj: Option, pub(crate) data: Vec, - pub(crate) resources: Dict, + /// The form, and its `/Resources` when they are an object of their own, which is what + /// [`FormCall::resources`] reads. + form: Arc, + own: Option>, pub(crate) ctm: Matrix, } +impl FormCall { + /// The resources its content is read with: its own, or if it has none, `drawn_with`, the ones + /// it was drawn with (PDF 1.1 files). Read in place, as a page can draw a form thousands of times: + /// a copy for each took time in the square of them. + pub(crate) fn resources<'a>(&'a self, drawn_with: &'a Dict) -> &'a Dict { + let direct = || match &*self.form { + Object::Stream(s) => s.dict.get(b"Resources").and_then(Object::as_dict), + _ => None, + }; + self.own.as_deref().and_then(Object::as_dict).or_else(direct).unwrap_or(drawn_with) + } +} + +/// `o` as a dictionary, read in place for the same reason as [`FormCall::resources`]. `held` keeps it +/// when it is an object of its own. Nothing else is one, and [`Document::resolve`] would copy it. +pub(crate) fn dict_in_place<'a>(doc: &Document, o: &'a Object, held: &'a mut Option>) -> Option<&'a Dict> { + match o { + Object::Dict(dict) => Some(dict), + Object::Ref(_) => held.insert(doc.resolve(o)).as_dict(), + _ => None, + } +} + +/// The dictionary at `key` of `resources`, `/XObject` or `/Font`, say, as each form reads these. +pub(crate) fn resource_dict<'a>(doc: &Document, resources: &'a Dict, key: &[u8], held: &'a mut Option>) -> Option<&'a Dict> { + dict_in_place(doc, resources.get(key)?, held) +} + /// The form XObject `name` in `resources`, drawn with `ctm`. `None` for images, missing names /// and forms already being read (`path`), and for forms nested too deep or past the page's /// budget, which `budget` records as truncated; each form entered counts one visit. @@ -472,13 +505,15 @@ pub(crate) fn form_call( if limited && budget.truncated { return None; } - let xobjects = resources.get(b"XObject").map(|x| doc.resolve(x)).and_then(|x| x.as_dict().cloned())?; - let o = xobjects.get(name)?; - let obj = o.as_ref(); + let mut held = None; + let o = resource_dict(doc, resources, b"XObject", &mut held)?.get(name)?; + // Only a reference can name a stream, so nothing else needs reading, or copying. + let obj = Some(o.as_ref()?); if obj.is_some_and(|r| path.contains(&r)) { return None; } - let Object::Stream(s) = &*doc.resolve(o) else { return None }; + let form = doc.resolve(o); + let Object::Stream(s) = &*form else { return None }; if s.dict.name(b"Subtype") != Some(b"Form") { return None; } @@ -492,8 +527,7 @@ pub(crate) fn form_call( let v: Vec = a.iter().filter_map(|x| doc.resolve(x).as_f64()).collect(); <[f64; 6]>::try_from(v).ok().filter(|v| v.iter().all(|x| x.is_finite())) }); - // A form without its own resources uses the ones it was drawn with (PDF 1.1 files). - let own = s.dict.get(b"Resources").map(|r| doc.resolve(r)).and_then(|r| r.as_dict().cloned()); + let own = s.dict.get(b"Resources").filter(|r| matches!(r, Object::Ref(_))).map(|r| doc.resolve(r)); let data = match budget.decode.decode(s) { Ok(data) => data, Err(_) if budget.decode.remaining() == 0 => { @@ -503,7 +537,7 @@ pub(crate) fn form_call( Err(_) => Vec::new(), }; budget.visits = budget.visits.saturating_add(1); - Some(FormCall { obj, data, resources: own.unwrap_or_else(|| resources.clone()), ctm: m.map_or(ctm, |m| Matrix(m).then(&ctm)) }) + Some(FormCall { obj, data, form, own, ctm: m.map_or(ctm, |m| Matrix(m).then(&ctm)) }) } /// The lines a page shows as it reads, including text drawn by form XObjects (which @@ -522,8 +556,9 @@ pub(super) fn reading_lines(doc: &Document, page: usize) -> Result<(Vec usize) -> Result<(), EditError> { let mut cache = HashMap::new(); let mut invoked = Vec::new(); - let properties = resources.get(b"Properties").and_then(|o| w.doc.dict(o)).unwrap_or_default(); - let shown = interpret(w.doc, ops, resources, &mut cache, carry, Some(&mut invoked), Some(&properties))?; + let (mut held, none) = (None, Dict::new()); + let properties = resource_dict(w.doc, resources, b"Properties", &mut held).unwrap_or(&none); + let shown = interpret(w.doc, ops, resources, &mut cache, carry, Some(&mut invoked), Some(properties))?; let mut last = None; let mut last_stream = None; let mut forms = invoked.into_iter().peekable(); @@ -556,7 +591,7 @@ pub(super) fn reading_lines(doc: &Document, page: usize) -> Result<(Vec, } +/// What an action's log says of the images a Reduce File Size step left, if there are any. +fn images_refused_note(images: usize) -> Option { + (images > 0).then(|| format!("Reduce file size: {images} image(s) stayed as they were, past what one run may decode")) +} + fn apply_step(s: &mut Session, id: DocId, step: &Step, log: &mut Vec) -> Result, EditError> { let pages = s.get(id).map_or(0, |d| d.info.pages.len()); let all: Vec = (0..pages).collect(); @@ -156,9 +161,10 @@ fn apply_step(s: &mut Session, id: DocId, step: &Step, log: &mut Vec) -> return Ok(None); } Step::ReduceFileSize => { - let (bytes, _) = s.optimized_bytes(id, &crate::optimize::Settings::default(), &[])?; + let (bytes, report) = s.optimized_bytes(id, &crate::optimize::Settings::default(), &[])?; let before = s.get(id).map_or(0, |d| d.bytes.len()); log.push(format!("Reduce file size: {} → {} bytes", before, bytes.len())); + log.extend(images_refused_note(report.optimize.images_refused)); let name = s.get(id).map(|d| d.name.clone()).unwrap_or_default(); s.close(id); let new = s.open(name, None, bytes, None).map_err(|e| EditError::Reopen(e.to_string()))?; @@ -222,3 +228,16 @@ pub fn run_on(action: &Action, name: &str, bytes: Arc>, mut progress: im let bytes = if d.is_signed() { s.save_bytes(id) } else { s.save_full_bytes(id) }.map_err(|e| e.to_string())?; Ok(FileResult { name: name.to_string(), bytes, log }) } + +#[cfg(test)] +mod tests { + use super::images_refused_note; + + /// A log line only for images that stayed, saying how many. + #[test] + fn the_log_says_when_images_stayed_as_they_were() { + assert_eq!(images_refused_note(0), None); + assert!(images_refused_note(1).is_some_and(|note| note.contains("1 image(s)"))); + assert!(images_refused_note(3).is_some_and(|note| note.contains("3 image(s)"))); + } +} diff --git a/crates/engine/src/compare.rs b/crates/engine/src/compare.rs index dca1e24af5..9be1954b09 100644 --- a/crates/engine/src/compare.rs +++ b/crates/engine/src/compare.rs @@ -140,6 +140,8 @@ pub enum OfficeFormat { Docx, Pptx, Html, + /// CSS-free HTML that preserves text and inline images but drops colours and layout styling. + HtmlSimple, Rtf, Markdown, } @@ -150,6 +152,7 @@ impl OfficeFormat { OfficeFormat::Docx => "docx", OfficeFormat::Pptx => "pptx", OfficeFormat::Html => "html", + OfficeFormat::HtmlSimple => "html", OfficeFormat::Rtf => "rtf", OfficeFormat::Markdown => "md", } @@ -173,14 +176,15 @@ pub struct OfficeExport { /// The exported file. pub bytes: Vec, /// Pages (0-based) that draw forms nested deeper than [`MAX_FORM_DEPTH`] or more of them - /// than [`MAX_FORM_VISITS`], or pictures past [`MAX_EXPORT_IMAGE_BYTES`]: export stops - /// reading there to stay bounded on hostile files, so the text and images of those forms, or + /// than [`MAX_FORM_VISITS`], or pictures past [`MAX_EXPORT_IMAGE_BYTES`] or past what one export + /// may decode: export stops reading there to stay bounded on hostile files, so the text and images of those forms, or /// those pictures, are missing from `bytes`. pub truncated_pages: Vec, } /// An image object prepared for Office export: its file extension and encoded bytes, or why it is -/// left out (`Err(true)`: past [`MAX_EXPORT_IMAGE_BYTES`]; `Err(false)`: it can't be encoded). +/// left out (`Err(true)`: past [`MAX_EXPORT_IMAGE_BYTES`], or what the export may decode; +/// `Err(false)`: it can't be encoded). type PreparedImage = Result<(&'static str, Arc<[u8]>), bool>; impl crate::Document { @@ -194,6 +198,18 @@ impl crate::Document { /// pictures went past `image_budget` bytes ([`OfficeExport::truncated_pages`]). Without /// `images` no picture is prepared. pub(crate) fn export_pages_checked(&self, images: bool, image_budget: usize) -> (Vec, Vec) { + let Some(editor) = self.editor.as_ref() else { return (Vec::new(), Vec::new()) }; + self.export_pages_within(images, image_budget, &mut pdfcraft_cos::ImageBudget::new(&editor.cos)) + } + + /// [`Self::export_pages_checked`], its pictures decoded within `image_work`, which is shared + /// by the whole export: a picture past it is left out like one past `image_budget`. + pub(crate) fn export_pages_within( + &self, + images: bool, + image_budget: usize, + image_work: &mut pdfcraft_cos::ImageBudget, + ) -> (Vec, Vec) { let Some(cos) = self.editor.as_ref().map(|e| &e.cos) else { return (Vec::new(), Vec::new()) }; let mut truncated = Vec::new(); // Each image object is encoded once and shared by every place that draws it. @@ -244,7 +260,9 @@ impl crate::Document { .filter_map(|im| { let object = im.object?; let prepared = encoded.entry(object).or_insert_with(|| { - let (ext, bytes) = pdfcraft_create::image_file(cos, object).map_err(|_| false)?; + let refused = image_work.refused(); + let (ext, bytes) = + pdfcraft_create::image_file_within(cos, object, &mut *image_work).map_err(|_| image_work.refused() > refused)?; image_bytes = image_bytes.checked_sub(bytes.len()).ok_or(true)?; Ok((if ext == "jpg" { "jpg" } else { "png" }, Arc::from(bytes))) }); @@ -286,6 +304,7 @@ impl crate::Document { OfficeFormat::Docx => pdfcraft_export::docx(&pages, &title), OfficeFormat::Pptx => pdfcraft_export::pptx(&pages, &title), OfficeFormat::Html => pdfcraft_export::html(&pages, &title).into_bytes(), + OfficeFormat::HtmlSimple => pdfcraft_export::html_simple(&pages, &title).into_bytes(), OfficeFormat::Rtf => pdfcraft_export::rtf(&pages).into_bytes(), OfficeFormat::Markdown => pdfcraft_export::markdown(&pages).into_bytes(), }; diff --git a/crates/engine/src/optimizer.rs b/crates/engine/src/optimizer.rs index 42af737bab..30a14c5695 100644 --- a/crates/engine/src/optimizer.rs +++ b/crates/engine/src/optimizer.rs @@ -92,7 +92,24 @@ impl OptimizeJob { pdfcraft_xfa::clear_password_values(&mut cos).map_err(|e| EditError::Write(e.to_string()))?; let mut step = |stage| if progress(stage) { Ok(()) } else { Err(EditError::Cancelled) }; step(OptimizeStage::Discarding)?; - let discarded = if discard.is_empty() { Vec::new() } else { pdfcraft_redact::sanitize::remove_hidden(&mut cos, &discard)? }; + let discarded = if discard.is_empty() { + Vec::new() + } else { + // Every ticked category, as `remove_hidden` decides between them: with form fields + // ticked, discarding hidden text also takes the hidden text the flattened appearances + // bring onto the page, which no scan before flattening counts. It refuses when its scan + // counts every one as 0, which would end the whole optimization, and may have changed + // the copy by then (an empty outline root goes with bookmarks), so the copy from before + // is kept instead: nothing is discarded. + let before = cos.clone(); + match pdfcraft_redact::sanitize::remove_hidden(&mut cos, &discard) { + Err(pdfcraft_redact::RedactError::NothingToApply) => { + cos = before; + Vec::new() + } + r => r?, + } + }; let report = optimize::optimize_with_progress(&mut cos, &settings, &mut |s| { step(match s { optimize::Stage::Fragments => OptimizeStage::Fragments, diff --git a/crates/engine/src/session/files.rs b/crates/engine/src/session/files.rs index 34d75e5c82..553ddd6aa3 100644 --- a/crates/engine/src/session/files.rs +++ b/crates/engine/src/session/files.rs @@ -71,12 +71,12 @@ impl Session { /// Reduce File Size: Acrobat's defaults (colour and grey images above 225 ppi to 150 ppi, /// JPEG medium quality; black-and-white averaged down to 300 ppi above 450 ppi, and stored as /// CCITT Group 4 whenever smaller; thumbnails dropped), identical resources merged, unused - /// objects dropped, objects packed into compressed object streams. Returns the bytes and how - /// many objects were merged. The open document is not changed (Acrobat saves the reduced copy - /// as a new file). - pub fn reduced_bytes(&self, id: DocId) -> Result<(Arc>, usize), EditError> { + /// objects dropped, objects packed into compressed object streams. Returns the bytes, how + /// many objects were merged and how many images stayed as they were, past what one run may + /// decode. The open document is not changed (Acrobat saves the reduced copy as a new file). + pub fn reduced_bytes(&self, id: DocId) -> Result<(Arc>, usize, usize), EditError> { let (bytes, report) = self.optimized_bytes(id, &optimize::Settings::default(), &[])?; - Ok((bytes, report.merged)) + Ok((bytes, report.merged, report.optimize.images_refused)) } /// Optimize PDF ▸ Advanced optimization: `settings` for images and objects, plus Remove diff --git a/crates/engine/src/tests.rs b/crates/engine/src/tests.rs index 15e022f6a3..e16992e7bb 100644 --- a/crates/engine/src/tests.rs +++ b/crates/engine/src/tests.rs @@ -3603,13 +3603,73 @@ fn create_and_reduce() { ) .unwrap(); let full = s2.save_full_bytes(id2).unwrap(); - let (reduced, _) = s2.reduced_bytes(id2).unwrap(); + let (reduced, ..) = s2.reduced_bytes(id2).unwrap(); assert!(reduced.len() <= full.len(), "{} > {}", reduced.len(), full.len()); let mut s3 = Session::new(); let r = s3.open("r.pdf", None, reduced, None).unwrap(); assert_eq!(page_texts(&s3, r), ["Page 1", "Page 1"]); } +/// Discarding a category that holds nothing discards nothing; it used to end the whole +/// optimization with an error about redaction marks. +#[test] +fn optimize_discarding_an_empty_category_still_runs() { + let (s, id) = session_with(2); + let (bytes, report) = s.optimized_bytes(id, &optimize::Settings::default(), &[crate::Hidden::Bookmarks, crate::Hidden::Comments]).unwrap(); + assert!(bytes.starts_with(b"%PDF-")); + assert!(report.discarded.is_empty(), "{:?}", report.discarded); + // An outline root with no entries is no bookmarks: it stays, as Remove Hidden Information, + // which refuses then, leaves it. + let outline = pdfcraft_testkit::Pdf::new() + .obj("<< /Type /Catalog /Pages 2 0 R /Outlines 4 0 R /PageMode /UseOutlines >>") + .obj("<< /Type /Pages /Kids [3 0 R] /Count 1 /MediaBox [0 0 612 792] >>") + .obj("<< /Type /Page /Parent 2 0 R >>") + .obj("<< /Type /Outlines /Count 0 >>") + .build(); + let mut s = Session::new(); + let id = s.open("outline.pdf", None, Arc::new(outline), None).unwrap(); + let (bytes, report) = s.optimized_bytes(id, &optimize::Settings::default(), &[crate::Hidden::Bookmarks]).unwrap(); + assert!(report.discarded.is_empty(), "{:?}", report.discarded); + let saved = pdfcraft_cos::Document::open(bytes).unwrap(); + let catalog = saved.get(saved.root().unwrap()).as_dict().cloned().unwrap(); + assert!(catalog.contains(b"Outlines") && catalog.contains(b"PageMode"), "{catalog:?}"); + // Beside an empty tick, one that holds something is discarded, and only that one. + let noted = pdfcraft_testkit::Pdf::new() + .obj("<< /Type /Catalog /Pages 2 0 R >>") + .obj("<< /Type /Pages /Kids [3 0 R] /Count 1 /MediaBox [0 0 612 792] >>") + .obj("<< /Type /Page /Parent 2 0 R /Annots [4 0 R] >>") + .obj("<< /Type /Annot /Subtype /Text /Rect [20 20 40 40] /Contents (internal note) >>") + .build(); + let mut s = Session::new(); + let id = s.open("noted.pdf", None, Arc::new(noted), None).unwrap(); + let (_, report) = s.optimized_bytes(id, &optimize::Settings::default(), &[crate::Hidden::Bookmarks, crate::Hidden::Comments]).unwrap(); + assert_eq!(report.discarded, vec![(crate::Hidden::Comments, 1)]); + // A field whose appearance draws text invisibly: flattening it brings that text onto the page, + // which no scan before counts as hidden, and discarding hidden text takes it too. + let form = pdfcraft_testkit::Pdf::new() + .obj("<< /Type /Catalog /Pages 2 0 R /AcroForm << /Fields [4 0 R] /DA (/F1 0 Tf 0 g) >> >>") + .obj("<< /Type /Pages /Kids [3 0 R] /Count 1 /MediaBox [0 0 612 792] >>") + .obj("<< /Type /Page /Parent 2 0 R /Annots [4 0 R] /Resources << /Font << /F1 6 0 R >> >> /Contents 7 0 R >>") + .obj("<< /Type /Annot /Subtype /Widget /FT /Tx /T (name) /V (shown) /Rect [100 100 300 130] /P 3 0 R /F 4 /AP << /N 5 0 R >> >>") + .stream( + "/Type /XObject /Subtype /Form /BBox [0 0 200 30] /Resources << /Font << /F1 6 0 R >> >>", + "/Tx BMC BT /F1 12 Tf 2 10 Td (shown) Tj ET BT /F1 12 Tf 3 Tr 2 20 Td (HIDDENSECRET) Tj ET EMC", + ) + .obj("<< /Type /Font /Subtype /Type1 /BaseFont /Helvetica >>") + .stream("", "BT /F1 12 Tf 72 700 Td (Page text) Tj ET") + .build(); + let mut s = Session::new(); + let id = s.open("form.pdf", None, Arc::new(form), None).unwrap(); + let (bytes, _) = s.optimized_bytes(id, &optimize::Settings::default(), &[crate::Hidden::FormFields, crate::Hidden::HiddenText]).unwrap(); + let saved = pdfcraft_cos::Document::open(bytes).unwrap(); + for (r, object) in saved.scan_objects() { + if let pdfcraft_cos::Object::Stream(st) = &*object { + let data = st.decoded().unwrap_or_default(); + assert!(!data.windows(12).any(|w| w == b"HIDDENSECRET"), "the hidden text stays in {r:?}"); + } + } +} + #[test] fn an_optimize_job_reports_its_stages_and_can_be_cancelled() { use crate::optimizer::OptimizeStage; @@ -8357,10 +8417,35 @@ fn copy_image_reads_the_globals_of_a_jbig2_picture() { let (w, h, rgba) = d.page_image_rgba(0, 0).unwrap(); assert_eq!((w, h), (16, 2)); assert!(rgba.chunks(4).all(|p| p == [0, 0, 0, 255]), "the page's default pixel, from the globals"); + // An Office export shares one allowance across its pictures. One past it is left out, and the + // export says the page is missing something, as for a picture past its bytes. + let (pages, truncated) = d.export_pages_within(true, 1 << 20, &mut pdfcraft_cos::ImageBudget::with_work(u64::MAX)); + assert_eq!((pages[0].images.len(), truncated.len()), (1, 0)); + let (pages, truncated) = d.export_pages_within(true, 1 << 20, &mut pdfcraft_cos::ImageBudget::with_work(0)); + assert!(pages[0].images.is_empty()); + assert_eq!(truncated, [0]); +} + +/// An Office export leaves out a picture it can't encode, as it did. That isn't a page cut short: +/// only a picture past what the export may do is reported as one. +#[test] +fn an_office_export_doesnt_call_an_unreadable_picture_truncated() { + let pdf = b"%PDF-1.7\n1 0 obj << /Type /Catalog /Pages 2 0 R >> endobj\n\ + 2 0 obj << /Type /Pages /Kids [3 0 R] /Count 1 /MediaBox [0 0 200 300] >> endobj\n\ + 3 0 obj << /Type /Page /Parent 2 0 R /Contents 4 0 R /Resources << /XObject << /Im1 5 0 R >> >> >> endobj\n\ + 4 0 obj << /Length 31 >> stream\nq 160 0 0 20 20 100 cm /Im1 Do Q\nendstream endobj\n\ + 5 0 obj << /Type /XObject /Subtype /Image /Width 2 /Height 2 /ColorSpace /DeviceGray /BitsPerComponent 8 /Filter /JPXDecode /Length 4 >> stream\nnone\nendstream endobj\n\ + trailer << /Root 1 0 R >>\n%%EOF" + .to_vec(); + let mut s = Session::new(); + let id = s.open("picture.pdf", None, Arc::new(pdf), None).unwrap(); + let (pages, truncated) = s.get(id).unwrap().export_pages_within(true, 1 << 20, &mut pdfcraft_cos::ImageBudget::with_work(u64::MAX)); + assert!(pages[0].images.is_empty()); + assert_eq!(truncated, Vec::::new()); } /// Copy Image takes a JBIG2 picture as its pixels and as a PNG file, behind another filter -/// (ASCIIHexDecode) too: Export's decoding, through `Document::decoded_image`. +/// (ASCIIHexDecode) too: Export's decoding, through `ImageBudget::decode`. #[test] fn copy_image_copies_a_jbig2_picture_behind_another_filter() { // 16 × 2: the left half of the top row black, the rest white. @@ -9328,6 +9413,61 @@ fn a_fields_own_script_may_not_save_as_or_show_a_panel() { assert_eq!(o.requests, [js::Request::SaveAs]); } +/// A page of `count` pictures of one flat grey, `side` pixels square, each an object of its own. +fn page_of_pictures(count: usize, side: usize) -> Vec { + let data = pdfcraft_filters::encode_flate(&vec![0x80; side * side]); + let names: String = (0..count).map(|i| format!("/Im{i} {} 0 R ", 5 + i)).collect(); + let content: String = (0..count).map(|i| format!("q 10 0 0 10 0 0 cm /Im{i} Do Q\n")).collect(); + let mut pdf = format!( + "%PDF-1.7\n1 0 obj << /Type /Catalog /Pages 2 0 R >> endobj\n\ + 2 0 obj << /Type /Pages /Kids [3 0 R] /Count 1 /MediaBox [0 0 200 300] >> endobj\n\ + 3 0 obj << /Type /Page /Parent 2 0 R /Contents 4 0 R /Resources << /XObject << {names}>> >> >> endobj\n\ + 4 0 obj << /Length {} >> stream\n{content}\nendstream endobj\n", + content.len() + ) + .into_bytes(); + for i in 0..count { + let dict = format!( + "{} 0 obj << /Type /XObject /Subtype /Image /Width {side} /Height {side} /ColorSpace /DeviceGray /BitsPerComponent 8 /Filter /FlateDecode /Length {} >> stream\n", + 5 + i, + data.len() + ); + pdf.extend_from_slice(dict.as_bytes()); + pdf.extend_from_slice(&data); + pdf.extend_from_slice(b"\nendstream endobj\n"); + } + pdf.extend_from_slice(b"trailer << /Root 1 0 R >>\n%%EOF"); + pdf +} + +/// The allowance is the export's, not each picture's: a page of many small pictures stops where it +/// runs out, the rest are left out and counted, and the page is listed, which is what the export's +/// warning goes by. A few large pictures are well within it, and all come through. +#[test] +fn a_page_of_many_pictures_stops_at_the_exports_allowance() { + let export = |pdf: Vec, work: &mut pdfcraft_cos::ImageBudget| { + let mut s = Session::new(); + let id = s.open("pictures.pdf", None, Arc::new(pdf), None).unwrap(); + s.get(id).unwrap().export_pages_within(true, 1 << 30, work) + }; + let mut one = pdfcraft_cos::ImageBudget::with_work(u64::MAX); + export(page_of_pictures(1, 2), &mut one); + let cost = u64::MAX - one.work_left(); + assert!(cost > 0); + + let mut work = pdfcraft_cos::ImageBudget::with_work(100 * cost); + let (pages, truncated) = export(page_of_pictures(10_000, 2), &mut work); + assert_eq!(pages[0].images.len(), 100); + assert_eq!(truncated, vec![0]); + assert_eq!(work.refused(), 9_900); + + let mut s = Session::new(); + let id = s.open("large.pdf", None, Arc::new(page_of_pictures(3, 1_000)), None).unwrap(); + let (pages, truncated) = s.get(id).unwrap().export_pages_checked(true, 1 << 30); + assert_eq!(pages[0].images.len(), 3); + assert_eq!(truncated, Vec::::new()); +} + /// A page whose forms go past the reading limit and whose picture goes past the image budget is /// listed once among the truncated pages. #[test] @@ -10397,3 +10537,20 @@ fn xfa_deferred_choice_resets_preserve_the_reset_value_through_reopen() { } assert!(failures.is_empty(), "{}", failures.join("\n")); } + +#[test] +fn fill_sign_multiline_text_survives_engine_save_reopen_and_render() { + let (mut session, id) = rotated_blank(0); + let text = "\nAda\n\nLovelace\n"; + let shape = Shape::Typewriter { rect: text_box_at(0, [20.0, 250.0], 120.0, 66.0).unwrap(), font_size: 10.0 }; + let style = Style::default_for(&shape); + session.apply(id, Edit::AddAnnotation(NewAnnotation { page: 0, shape, style, contents: text.into(), author: "Test".into() })).unwrap(); + assert_eq!(session.get(id).unwrap().info.annotations[0].contents.as_deref(), Some(text), "engine keeps outer typewriter line breaks"); + let before = render_page(&session, id); + assert!(before.rgba.as_chunks::<4>().0.iter().any(|p| p[..3] == [0, 0, 0]), "the appearance contains ink"); + let bytes = session.save_bytes(id).unwrap(); + let mut reopened = Session::new(); + let again = reopened.open("multiline.pdf", None, bytes, None).unwrap(); + assert_eq!(reopened.get(again).unwrap().info.annotations[0].contents.as_deref(), Some(text), "reopening preserves all blank lines"); + assert_eq!(before.rgba, render_page(&reopened, again).rgba, "the saved appearance is identical"); +} diff --git a/crates/export/src/as_html.rs b/crates/export/src/as_html.rs index 7aeea595a8..3bc6709e69 100644 --- a/crates/export/src/as_html.rs +++ b/crates/export/src/as_html.rs @@ -38,11 +38,23 @@ pub(crate) fn base64(data: &[u8]) -> String { /// One HTML file: headings and paragraphs, tables as real `` elements, images inline, a /// rule between pages. pub fn html(pages: &[Page], title: &str) -> String { + html_with_mode(pages, title, false) +} + +/// A simple HTML export with no CSS; page layout and colours are omitted. +pub fn html_simple(pages: &[Page], title: &str) -> String { + html_with_mode(pages, title, true) +} + +fn html_with_mode(pages: &[Page], title: &str, simple: bool) -> String { let mut s = format!( - "\n\n\n\n{}\n\n\n\n", - esc(title) + "\n\n\n\n{}\n{}\n\n\n", + esc(title), + if simple { + "" + } else { + "" + } ); for it in items(pages) { match it { @@ -59,13 +71,13 @@ table{{border-collapse:collapse;margin:1em 0}}td,th{{border:1px solid #999;paddi } // The paragraph has its first run's colour; a run in another colour says so. let colour = rgb8(r.block.color); - if colour != rgb8(first.color) { + if !simple && colour != rgb8(first.color) { let [red, green, blue] = colour; run = format!("{run}"); } t.push_str(&run); } - let style = hex(first.color).map_or(String::new(), |h| format!(" style=\"color:#{h}\"")); + let style = if simple { String::new() } else { hex(first.color).map_or(String::new(), |h| format!(" style=\"color:#{h}\"")) }; match lvl { 0 => s.push_str(&format!("{t}

\n")), l => s.push_str(&format!("{t}\n")), @@ -84,7 +96,7 @@ table{{border-collapse:collapse;margin:1em 0}}td,th{{border:1px solid #999;paddi body = format!("{body}"); } let span = if c.span > 1 { format!(" colspan=\"{}\"", c.span) } else { String::new() }; - let style = hex(c.color).map_or(String::new(), |h| format!(" style=\"color:#{h}\"")); + let style = if simple { String::new() } else { hex(c.color).map_or(String::new(), |h| format!(" style=\"color:#{h}\"")) }; s.push_str(&format!("{body}")); } s.push_str("\n"); diff --git a/crates/export/src/lib.rs b/crates/export/src/lib.rs index db53ee59c8..2b82919bbf 100644 --- a/crates/export/src/lib.rs +++ b/crates/export/src/lib.rs @@ -27,9 +27,9 @@ pub(crate) use as_docx::hex; #[cfg(test)] use as_docx::{MAX_MEDIA, docx_table}; pub(crate) use as_html::esc; -pub use as_html::html; #[cfg(test)] use as_html::{allowed, base64}; +pub use as_html::{html, html_simple}; pub use as_markdown::markdown; #[cfg(test)] use as_markdown::{emphasis, paragraph}; diff --git a/crates/export/src/tests.rs b/crates/export/src/tests.rs index 27cd8264e0..f630d98d5d 100644 --- a/crates/export/src/tests.rs +++ b/crates/export/src/tests.rs @@ -85,6 +85,24 @@ fn html_has_headings_paragraphs_and_images_in_order() { assert_eq!(base64(b"Ma"), "TWE="); } +#[test] +fn simple_html_has_no_css_or_layout_elements() { + let mut p = page(); + let mut unicode = block("naïve 日本語.", 72.0, 300.0, 300.0, 311.0); + unicode.bold = true; + unicode.italic = true; + p.blocks.push(unicode); + let source = html_simple(&[p, table_page()], "Simple export"); + for banned in ["", "", "", " Filter // full names and in Filter::name(&self) -> &str; Filter::is_image_codec(&self) -> bool pub struct Params { predictor, colors, bits_per_component, columns, early_change } // i64s; Default = 1, 1, 8, 1, 1 -pub enum FilterError { Corrupt { filter, detail }, LimitExceeded(usize), Unsupported(String) } +pub enum FilterError { Corrupt { filter, detail }, LimitExceeded(usize), Unsupported(String), Spent } decode(chain, data, max_output) -> Result, FilterError> decode_counted(chain, data, max_output) -> Result<(Vec, usize /*decoded*/), (FilterError, usize /*decoded*/)> decode_tolerant(chain, data, max_output) -> Result<(Vec, bool /*partial*/), FilterError> decode_tolerant_counted(chain, data, max_output) -> Result<(Vec, bool /*partial*/, usize /*decoded*/), (FilterError, usize /*decoded*/)> +decode_tolerant_within(chain, data, max_output, work: &mut u64) -> Result, FilterError> +decode_within(chain, data, max_output, work: &mut u64) -> Result, FilterError> encode(filter, params, data) -> Result, FilterError> encode_flate(data) -> Vec // zlib, level 6 encode_g4(data, columns, rows) -> Result, FilterError> // 1-bit rows as CCITT Group 4; columns <= MAX_G4_COLUMNS @@ -35,6 +37,7 @@ encode_jbig2(data, columns, rows) -> Result, FilterError> // 1-bit row - Image codecs (DCT, JPX, JBIG2, CCITT), `Crypt` and unknown filters anywhere in a chain give `Unsupported`: callers keep such data encoded. So does a chain longer than `MAX_CHAIN` (8) filters, before any stage runs. Decryption belongs to `crypt`. - `max_output` bounds every intermediate buffer (including the pre-predictor buffer) and gives `LimitExceeded(max_output)`. This also holds when Flate retries raw deflate after a misleading zlib header, in both strict and tolerant decoding. - `decode_counted` and `decode_tolerant_counted` are for a caller charging a budget (`pdfcraft_cos::DecodeBudget`). `max_output` bounds all stages together (each stage gets what the earlier ones left), and they give the bytes every stage that ran decoded, on success and on failure. A stage's output counts as its decoder produced it, before a predictor or a later stage shrinks it, and a failed decode pays for what it decoded first. +- `decode_tolerant_within` is for a run of images (`pdfcraft_cos::ImageBudget`), as `decode_within` (its strict form), `decode_jbig2_within` and `decode_ccitt_within` are, all spending from one `work`, in the JBIG2 decoder's steps. `max_output` bounds each stage, as in `decode_tolerant`, and no stage decodes past what `work` has left. It pays a step a byte of `data` first and a step a byte each stage decodes, so a chain that fails has paid for what it did: 0.2 to 3 ns a byte in or out, up to 19 ns through a predictor on samples of a bit, against the 6 to 16 ns of a JBIG2 step. What `work` can't pay for spends all of it, and gives `Spent`; with nothing left nothing is read. A chain that can't be decoded at all costs nothing and gives its usual error. - `decode_tolerant` turns `Corrupt` into "what was decoded so far" plus `partial = true`, then runs the rest of the chain on it (predictors are applied to partial output too). `LimitExceeded` and `Unsupported` are still errors. ## Behaviour diff --git a/crates/filters/src/ccitt.rs b/crates/filters/src/ccitt.rs index 7c188d701c..2a038568ee 100644 --- a/crates/filters/src/ccitt.rs +++ b/crates/filters/src/ccitt.rs @@ -50,7 +50,7 @@ pub fn encode_g4(data: &[u8], columns: u32, rows: u32) -> Result, Filter } } -/// The widest row [`decode_ccitt`] decodes: its row buffer stays within 128 KiB. +/// The widest row [`decode_ccitt_within`] decodes: its row buffer stays within 128 KiB. pub const MAX_CCITT_COLUMNS: u32 = 1 << 20; /// A `CCITTFaxDecode` stream's `/DecodeParms` (ISO 32000-2 Table 11). [`Default`] gives the @@ -74,22 +74,8 @@ impl Default for CcittParams { } } -/// CCITT fax `data` decoded as `CCITTFaxDecode` gives it: rows of `columns` 1-bit samples, most -/// significant bit first, each starting on a new byte, with black as 0 (as 1 with `black_is_1`). -/// -/// At most `max_rows` rows are decoded (fewer when `rows` says so), so the output is bounded by -/// the caller. Damaged data gives the rows decoded before the damage, as viewers show them: a -/// caller that needs a number of rows checks it got them. -/// -/// Group 3 rows on bytes (`k` from 0, `encoded_byte_align`) are read by their end-of-line codes, -/// whether the fill starts each code on a byte or ends it on one, when `data` starts with one (T.4 -/// sends one before the first row when it sends them at all), and on bytes otherwise, whatever -/// `end_of_line` says. Group 4 is read as its parameters say. Data with codes but none before the -/// first row is read on bytes, as PdfCraft's renderer draws it; with `k` 0 and the fill ending each -/// code on a byte, that may be other rows than were coded. -/// -/// Errors: `columns` that aren't from 1 to [`MAX_CCITT_COLUMNS`] ([`FilterError::Unsupported`]). -pub fn decode_ccitt(data: &[u8], p: &CcittParams, max_rows: u32) -> Result, FilterError> { +/// What [`decode_ccitt_within`] decodes once it is paid for. +fn decode_ccitt(data: &[u8], p: &CcittParams, max_rows: u32) -> Result, FilterError> { let columns = u32::try_from(p.columns) .ok() .filter(|c| (1..=MAX_CCITT_COLUMNS).contains(c)) @@ -123,6 +109,39 @@ pub fn decode_ccitt(data: &[u8], p: &CcittParams, max_rows: u32) -> Result Result, FilterError> { + let rows = u32::try_from(p.rows).ok().filter(|r| *r > 0).map_or(max_rows, |r| r.min(max_rows)); + let stride = u64::try_from(p.columns).unwrap_or(0).div_ceil(8); + crate::pay(work, stride.saturating_mul(u64::from(rows)).saturating_add((data.len() as u64).saturating_mul(CODE_WORK)))?; + decode_ccitt(data, p, max_rows) +} + /// Whether CCITT fax `data` starts with an end-of-line code: a 1 after 11 zeros or more, fill /// included. T.4 sends one before the first row when it sends them at all, and no other code starts /// with more than eight zeros. @@ -133,7 +152,7 @@ fn starts_with_end_of_line(data: &[u8]) -> bool { /// Rows of 1-bit samples filled from a decoder's pixels: `columns` a row, each row on a new byte, at /// most `rows` rows. Pixels past a row's end and rows past the last are dropped. The JBIG2 decoder -/// ([`crate::decode_jbig2`]) fills them too. +/// ([`crate::decode_jbig2_within`]) fills them too. pub(crate) struct Rows { pub(crate) out: Vec, row: Vec, @@ -189,6 +208,42 @@ impl hayro_ccitt::Decoder for Rows { mod tests { use super::*; + /// A run pays for the rows an image asks for and the code it reads, before any of it is + /// decoded: rows the data doesn't hold are paid for too, as a few bytes can ask for any number. + #[test] + fn a_run_of_images_pays_for_the_rows_it_asks_for() { + let (w, h) = (4096u32, 64u32); + let stride = (w as usize).div_ceil(8); + let data = encode_g4(&vec![0xFF; stride * h as usize], w, h).unwrap(); + let p = CcittParams { k: -1, columns: i64::from(w), ..CcittParams::default() }; + let whole = decode_ccitt(&data, &p, h).unwrap(); + let cost = (whole.len() + 4 * data.len()) as u64; + let mut work = cost; + assert_eq!(decode_ccitt_within(&data, &p, h, &mut work).unwrap(), whole, "exactly enough"); + assert_eq!(work, 0); + let mut work = cost + 7; + decode_ccitt_within(&data, &p, h, &mut work).unwrap(); + assert_eq!(work, 7, "only what it took"); + let mut work = cost - 1; + let refused = decode_ccitt_within(&data, &p, h, &mut work).unwrap_err(); + assert!(matches!(refused, FilterError::Spent), "a step short: {refused}"); + assert_eq!(work, 0, "spends all that was left"); + // Nothing left: not read at all, so bad columns aren't reported as bad columns. + let bad = CcittParams { columns: 0, ..p }; + assert!(decode_ccitt_within(&data, &bad, h, &mut 0).is_err_and(|e| matches!(e, FilterError::Spent))); + // No code at all, for the same rows. + let mut work = u64::MAX; + decode_ccitt_within(&[], &p, h, &mut work).unwrap(); + assert_eq!(u64::MAX - work, whole.len() as u64); + // `/Rows` below what is asked for, and no rows. + let mut work = u64::MAX; + decode_ccitt_within(&data, &CcittParams { rows: 3, ..p }, h, &mut work).unwrap(); + assert_eq!(u64::MAX - work, (3 * stride + 4 * data.len()) as u64); + let mut work = u64::MAX; + decode_ccitt_within(&data, &p, 0, &mut work).unwrap(); + assert_eq!(u64::MAX - work, 4 * data.len() as u64); + } + /// The rows decoded by an independent decoder (`hayro-ccitt`), as 1 for white and 0 for black. pub(crate) fn decode(data: &[u8], columns: u32, rows: u32) -> Vec> { struct Rows(Vec>, Vec, usize); diff --git a/crates/filters/src/flate.rs b/crates/filters/src/flate.rs index dac0851e07..1c38f72a53 100644 --- a/crates/filters/src/flate.rs +++ b/crates/filters/src/flate.rs @@ -28,8 +28,9 @@ pub(crate) fn decode(data: &[u8], max: usize) -> Step { // A header that only looked valid: retry the whole input as raw deflate. Err(f) if f.partial.is_empty() && matches!(f.error, crate::FilterError::Corrupt { .. }) => match inflate_raw(data, max) { // Keep the original corruption diagnostic only if the retry is corrupt - // too. A limit error must remain fatal even for tolerant decoding. - Err(retry) if matches!(retry.error, crate::FilterError::Corrupt { .. }) => Err(f), + // too. A limit error must remain fatal even for tolerant decoding. What the + // retry decoded isn't kept, but a caller charging for work has to hear of it. + Err(retry) if matches!(retry.error, crate::FilterError::Corrupt { .. }) => Err(Failure { discarded: retry.partial.len(), ..f }), retry => retry, }, r => r, diff --git a/crates/filters/src/jbig2.rs b/crates/filters/src/jbig2.rs index a36a81e1fb..1b705b0c72 100644 --- a/crates/filters/src/jbig2.rs +++ b/crates/filters/src/jbig2.rs @@ -7,7 +7,7 @@ mod decode; mod symbols; -pub use decode::{MAX_JBIG2_PIXELS, decode_jbig2}; +pub use decode::{MAX_JBIG2_PIXELS, decode_jbig2_within}; use crate::FilterError; use crate::mq::{Context, MqEncoder}; diff --git a/crates/filters/src/jbig2/decode.rs b/crates/filters/src/jbig2/decode.rs index 320e02445a..a018e75937 100644 --- a/crates/filters/src/jbig2/decode.rs +++ b/crates/filters/src/jbig2/decode.rs @@ -3,7 +3,7 @@ use crate::FilterError; use crate::ccitt::Rows; -/// The largest JBIG2 page [`decode_jbig2`] decodes, in pixels. The decoder decodes a page whole, +/// The largest JBIG2 page [`decode_jbig2_within`] decodes, in pixels. The decoder decodes a page whole, /// and takes pages of up to about this many (20,000 × 10,000 decodes). pub const MAX_JBIG2_PIXELS: u64 = 1 << 28; @@ -22,10 +22,23 @@ pub const MAX_JBIG2_PIXELS: u64 = 1 << 28; /// ([`FilterError::Corrupt`]); a page past `max` ([`FilterError::LimitExceeded`]) or /// [`MAX_JBIG2_PIXELS`] ([`FilterError::Unsupported`], or `Corrupt` from the decoder, which has the /// same cap and can refuse the page first). -pub fn decode_jbig2(data: &[u8], globals: Option<&[u8]>, columns: u32, rows: u32, max: usize) -> Result, FilterError> { +/// +/// Decoding spends from `work`: what decoding may still cost across a run of images, in the +/// decoder's count of steps. There is no way in without it, so a run of images can't decode them +/// without sharing an allowance. Reading `data` and `globals` is charged first +/// ([`hayro_jbig2::charge_reading`]), so an image that turns out not to decode has paid for that, +/// then what decoding takes ([`hayro_jbig2::Image::decode_within`]). An image takes at most what +/// one decode may on top of its reading and its page, whatever `work` allows, and one that `work` +/// can't pay for spends all of it. With nothing left an image isn't read at all, so the images after +/// that one cost nothing but this check, however large their globals. +pub fn decode_jbig2_within(data: &[u8], globals: Option<&[u8]>, columns: u32, rows: u32, max: usize, work: &mut u64) -> Result, FilterError> { if rows == 0 { return Ok(Vec::new()); } + if *work == 0 { + return Err(FilterError::Spent); + } + hayro_jbig2::charge_reading(work, data.len().saturating_add(globals.map_or(0, <[u8]>::len))).map_err(|_| FilterError::Spent)?; let corrupt = |detail: String| FilterError::Corrupt { filter: "JBIG2Decode", detail }; let image = hayro_jbig2::Image::new_embedded(data, globals).map_err(|e| corrupt(e.to_string()))?; let (width, height) = (image.width(), image.height()); @@ -41,7 +54,8 @@ pub fn decode_jbig2(data: &[u8], globals: Option<&[u8]>, columns: u32, rows: u32 return Err(FilterError::LimitExceeded(max)); } let mut out = Rows::new(width, height, false); - image.decode(&mut out).map_err(|e| corrupt(e.to_string()))?; + // Stopped by what was left, it isn't a damaged image, whatever the decoder calls it. + image.decode_within(&mut out, work).map_err(|e| if *work == 0 { FilterError::Spent } else { corrupt(e.to_string()) })?; Ok(out.out) } @@ -63,6 +77,12 @@ mod tests { use super::*; use crate::{encode_jbig2, encode_jbig2_generic}; + /// [`decode_jbig2_within`] with no limit on the work. + fn decode_jbig2(data: &[u8], globals: Option<&[u8]>, columns: u32, rows: u32, max: usize) -> Result, FilterError> { + let mut unbounded = u64::MAX; + decode_jbig2_within(data, globals, columns, rows, max, &mut unbounded) + } + /// `rows` rows of `columns` samples of noise, the bits that pad each row to a byte 0. fn noise(columns: u32, rows: u32) -> Vec { let stride = (columns as usize).div_ceil(8); @@ -123,6 +143,45 @@ mod tests { assert_eq!(decode_jbig2(&symbols, None, w, h, usize::MAX).unwrap(), marks); } + /// What a page costs is the same however much a run has left. Given exactly that it decodes, + /// and less stops it: spending all that's left, and what comes after isn't read. A page that + /// fails still spends what it took. + #[test] + fn a_run_of_images_spends_its_allowance_down_to_the_step() { + let (w, h) = (203u32, 41u32); + let data = encode_jbig2_generic(&noise(w, h), w, h).unwrap(); + let whole = decode_jbig2(&data, None, w, h, usize::MAX).unwrap(); + let mut work = u64::MAX; + assert_eq!(decode_jbig2_within(&data, None, w, h, usize::MAX, &mut work).unwrap(), whole); + let cost = u64::MAX - work; + assert!(cost >= u64::from(w) * u64::from(h), "a pixel at a time: {cost}"); + let mut work = cost; + assert_eq!(decode_jbig2_within(&data, None, w, h, usize::MAX, &mut work).unwrap(), whole, "exactly enough"); + assert_eq!(work, 0); + let mut work = cost + 7; + decode_jbig2_within(&data, None, w, h, usize::MAX, &mut work).unwrap(); + assert_eq!(work, 7, "only what it took"); + let mut work = cost - 1; + assert!(matches!(decode_jbig2_within(&data, None, w, h, usize::MAX, &mut work), Err(FilterError::Spent)), "a step short"); + assert_eq!(work, 0, "spends all that was left"); + // Nothing left: not read at all, so this garbage isn't reported as garbage. + assert!(matches!(decode_jbig2_within(b"garbage", None, w, h, usize::MAX, &mut work), Err(FilterError::Spent))); + // Too little even for its page. + let mut work = 3; + assert!(decode_jbig2_within(&data, None, w, h, usize::MAX, &mut work).is_err()); + assert_eq!(work, 0); + // A region that can't be read after the one that can: the page fails having spent the + // first, and the segment it fails on, and that isn't being out of allowance. + let bad_region = [0, 0, 0, 9, 38, 0, 1, 0, 0, 0, 1, 0xFF]; + let mut work = u64::MAX; + assert!(decode_jbig2_within(&[&data[..], &bad_region].concat(), None, w, h, usize::MAX, &mut work).is_err()); + assert_eq!(u64::MAX - work, cost + 1 + 4 * bad_region.len() as u64, "the first region, a segment more, and reading it"); + // Not a stream at all: it pays for being read, and globals count with it. + let mut work = u64::MAX; + assert!(matches!(decode_jbig2_within(b"garbage", Some(b"globals"), w, h, usize::MAX, &mut work), Err(FilterError::Corrupt { .. }))); + assert_eq!(u64::MAX - work, 4 * 14); + } + /// The page has to be the image's size, and is bounded before it is decoded, being decoded /// whole: within `max` as rows of one bit, and within [`MAX_JBIG2_PIXELS`]. Globals are given /// to the decoder: ones it skips decode, ones that aren't JBIG2 are an error, as is damaged diff --git a/crates/filters/src/lib.rs b/crates/filters/src/lib.rs index ba455e2bae..181f96ab66 100644 --- a/crates/filters/src/lib.rs +++ b/crates/filters/src/lib.rs @@ -7,9 +7,27 @@ //! Image codecs (`DCTDecode`, `JPXDecode`, `JBIG2Decode`, `CCITTFaxDecode`), //! `Crypt` and unknown filters are reported as [`FilterError::Unsupported`] so //! callers keep such data encoded. CCITT fax and JBIG2 images decode on their own -//! ([`decode_ccitt`], [`decode_jbig2`]), as `pdfcraft_cos::Document::decoded_image` -//! does after the filters before them. 1-bit samples can be encoded as CCITT Group 4 -//! ([`encode_g4`]) or lossless JBIG2 ([`encode_jbig2`]). +//! ([`decode_ccitt_within`], [`decode_jbig2_within`]), each spending from an allowance its caller +//! shares across a run of images, as `pdfcraft_cos::ImageBudget::decode` does after the filters +//! before them. Neither decodes without one: +//! +//! ```compile_fail +//! let _ = pdfcraft_filters::decode_jbig2(&[], None, 1, 1, 1 << 20); +//! ``` +//! +//! ```compile_fail +//! let _ = pdfcraft_filters::decode_ccitt(&[], &pdfcraft_filters::CcittParams::default(), 1); +//! ``` +//! +//! ``` +//! let mut work = 1 << 20; +//! assert!(pdfcraft_filters::decode_jbig2_within(&[], None, 1, 1, 1 << 20, &mut work).is_err()); +//! let p = pdfcraft_filters::CcittParams { columns: 8, ..Default::default() }; +//! assert!(pdfcraft_filters::decode_ccitt_within(&[], &p, 1, &mut work).is_ok()); +//! ``` +//! +//! 1-bit samples can be encoded as CCITT Group 4 ([`encode_g4`]) or lossless JBIG2 +//! ([`encode_jbig2`]). //! //! Every decoder is bounded by a caller-supplied `max_output` (decompression-bomb //! defence) and never panics on malformed input. @@ -28,8 +46,8 @@ mod runlength; use std::borrow::Cow; -pub use ccitt::{CcittParams, MAX_CCITT_COLUMNS, MAX_G4_COLUMNS, decode_ccitt, encode_g4}; -pub use jbig2::{MAX_JBIG2_COLUMNS, MAX_JBIG2_PIXELS, decode_jbig2, encode_jbig2, encode_jbig2_generic}; +pub use ccitt::{CcittParams, MAX_CCITT_COLUMNS, MAX_G4_COLUMNS, decode_ccitt_within, encode_g4}; +pub use jbig2::{MAX_JBIG2_COLUMNS, MAX_JBIG2_PIXELS, decode_jbig2_within, encode_jbig2, encode_jbig2_generic}; /// A PDF stream filter, identified by its `/Filter` name. #[derive(Clone, Debug, PartialEq, Eq, Hash)] @@ -91,7 +109,8 @@ impl Filter { matches!(self, Filter::Dct | Filter::Jpx | Filter::Jbig2 | Filter::CcittFax) } - fn is_decodable(&self) -> bool { + /// True for the general-purpose filters, which a chain can hold ([`decode`]). + pub fn is_decodable(&self) -> bool { matches!(self, Filter::Flate | Filter::Lzw | Filter::AsciiHex | Filter::Ascii85 | Filter::RunLength) } } @@ -123,33 +142,53 @@ pub enum FilterError { LimitExceeded(usize), #[error("unsupported filter: {0}")] Unsupported(String), + /// A run of images has nothing left to spend ([`decode_tolerant_within`]). + #[error("more image decoding than one operation may do")] + Spent, } /// A decoder failure carrying whatever was decoded before the error. pub(crate) struct Failure { pub(crate) error: FilterError, pub(crate) partial: Vec, + /// Bytes decoded on the way that `partial` doesn't hold: they took as long. + pub(crate) discarded: usize, } impl Failure { pub(crate) fn corrupt(filter: &'static str, detail: impl Into, partial: Vec) -> Self { - Failure { error: FilterError::Corrupt { filter, detail: detail.into() }, partial } + Failure { error: FilterError::Corrupt { filter, detail: detail.into() }, partial, discarded: 0 } } pub(crate) fn limit(max: usize) -> Self { - Failure { error: FilterError::LimitExceeded(max), partial: Vec::new() } + Failure { error: FilterError::LimitExceeded(max), partial: Vec::new(), discarded: 0 } } } pub(crate) type Step = Result, Failure>; +/// Takes `steps` from `work`, what a run of images may still cost. What it can't pay for spends +/// all of it. +pub(crate) fn pay(work: &mut u64, steps: u64) -> Result<(), FilterError> { + match work.checked_sub(steps) { + Some(left) => { + *work = left; + Ok(()) + } + None => { + *work = 0; + Err(FilterError::Spent) + } + } +} + /// Decodes `data` through `chain` (first element applied first). /// /// Image codecs, `Crypt` and unknown filters anywhere in the chain give /// [`FilterError::Unsupported`] (callers keep such data encoded), as does a chain longer than /// [`MAX_CHAIN`]. `max_output` bounds every intermediate buffer. pub fn decode(chain: &[(Filter, Params)], data: &[u8], max_output: usize) -> Result, FilterError> { - run(chain, data, max_output, true, false).map(|(v, _, _)| v).map_err(|(e, _)| e) + run(chain, data, max_output, None, true).map(|(v, _, _)| v).map_err(|(e, _)| e) } /// Like [`decode`] for a caller charging an allowance: `max_output` bounds the bytes all stages @@ -157,47 +196,98 @@ pub fn decode(chain: &[(Filter, Params)], data: &[u8], max_output: usize) -> Res /// bytes, on success and on failure. A stage's output counts even when a later stage or its /// predictor shrinks it. pub fn decode_counted(chain: &[(Filter, Params)], data: &[u8], max_output: usize) -> Result<(Vec, usize), (FilterError, usize)> { - run(chain, data, max_output, true, true).map(|(v, _, spent)| (v, spent)) + run(chain, data, max_output, Some(max_output), true).map(|(v, _, spent)| (v, spent)) } /// Like [`decode`], but on corrupt data returns what was decoded before the error and /// reports `partial = true` (the behaviour viewers expect). The remaining filters of the /// chain still run on the partial data. Limit and unsupported errors are still errors. pub fn decode_tolerant(chain: &[(Filter, Params)], data: &[u8], max_output: usize) -> Result<(Vec, bool), FilterError> { - run(chain, data, max_output, false, false).map(|(v, partial, _)| (v, partial)).map_err(|(e, _)| e) + run(chain, data, max_output, None, false).map(|(v, partial, _)| (v, partial)).map_err(|(e, _)| e) } /// [`decode_tolerant`] bounded and counted as [`decode_counted`] is. pub fn decode_tolerant_counted(chain: &[(Filter, Params)], data: &[u8], max_output: usize) -> Result<(Vec, bool, usize), (FilterError, usize)> { - run(chain, data, max_output, false, true) + run(chain, data, max_output, Some(max_output), false) +} + +/// [`decode_tolerant`], spending from `work`, what decoding may still cost across a run of images: +/// a step for each byte of `data`, paid before anything is decoded, and one for each byte a stage +/// decodes, so a chain that fails, or a stage that goes past `max_output`, has paid for what it did. +/// No stage decodes past what is left: a chain that `work` can't pay for spends all of it and stops +/// there, so with nothing left nothing is read. A chain that can't be decoded at all costs nothing, +/// whatever is left, so what an image's filters are is known from the error. +/// +/// Unlike [`decode_tolerant`], no filters at all gives `data` itself, within `max_output`. +pub fn decode_tolerant_within(chain: &[(Filter, Params)], data: &[u8], max_output: usize, work: &mut u64) -> Result, FilterError> { + spending(chain, data, max_output, work, false) +} + +/// [`decode`], spending from `work` as [`decode_tolerant_within`] does: corrupt data is an error, +/// having paid for what was decoded before it. +pub fn decode_within(chain: &[(Filter, Params)], data: &[u8], max_output: usize, work: &mut u64) -> Result, FilterError> { + spending(chain, data, max_output, work, true) +} + +fn spending(chain: &[(Filter, Params)], data: &[u8], max_output: usize, work: &mut u64, strict: bool) -> Result, FilterError> { + decodable(chain)?; + pay(work, data.len() as u64)?; + if chain.is_empty() { + return if data.len() > max_output { Err(FilterError::LimitExceeded(max_output)) } else { Ok(data.to_vec()) }; + } + let left = usize::try_from(*work).unwrap_or(usize::MAX); + match run(chain, data, max_output, Some(left), strict) { + Ok((out, _, decoded)) => pay(work, decoded as u64).map(|()| out), + // The stage stopped at the lower of the two, which took as much to find out. + Err((FilterError::LimitExceeded(_), decoded)) if left.saturating_sub(decoded) > max_output => { + pay(work, (decoded as u64).saturating_add(max_output as u64))?; + Err(FilterError::LimitExceeded(max_output)) + } + Err((FilterError::LimitExceeded(_), _)) => { + *work = 0; + Err(FilterError::Spent) + } + Err((e, decoded)) => pay(work, decoded as u64).and(Err(e)), + } } /// Longest filter chain decoded. Real streams use one to three filters; every stage may produce /// up to the output limit, so the chain length multiplies the work. pub const MAX_CHAIN: usize = 8; -/// The decoded data, whether it is partial and the bytes all stages decoded, or the error and -/// the bytes decoded before it. `max` bounds each stage, or with `cumulative` all of them -/// together. -fn run(chain: &[(Filter, Params)], data: &[u8], max: usize, strict: bool, cumulative: bool) -> Result<(Vec, bool, usize), (FilterError, usize)> { +/// Whether a chain is one [`run`] takes, and if not, the error. +fn decodable(chain: &[(Filter, Params)]) -> Result<(), FilterError> { if chain.len() > MAX_CHAIN { - return Err((FilterError::Unsupported(format!("a chain of {} filters", chain.len())), 0)); + return Err(FilterError::Unsupported(format!("a chain of {} filters", chain.len()))); } - if let Some((f, _)) = chain.iter().find(|(f, _)| !f.is_decodable()) { - return Err((FilterError::Unsupported(f.name().to_owned()), 0)); + match chain.iter().find(|(f, _)| !f.is_decodable()) { + Some((f, _)) => Err(FilterError::Unsupported(f.name().to_owned())), + None => Ok(()), } +} + +/// The decoded data, whether it is partial and the bytes all stages decoded, or the error and +/// the bytes decoded before it. `max` bounds each stage, and `total` all of them together. +fn run( + chain: &[(Filter, Params)], + data: &[u8], + max: usize, + total: Option, + strict: bool, +) -> Result<(Vec, bool, usize), (FilterError, usize)> { + decodable(chain).map_err(|e| (e, 0))?; let mut cur: Cow<[u8]> = Cow::Borrowed(data); let mut partial = false; let mut spent = 0usize; for (filter, params) in chain { #[cfg(test)] STAGE_BYTES.with(|c| c.set(c.get() + cur.len())); - let limit = if cumulative { max.saturating_sub(spent) } else { max }; + let limit = total.map_or(max, |total| max.min(total.saturating_sub(spent))); let (step, work) = decode_one(filter, params, &cur, limit); spent = spent.saturating_add(work); cur = Cow::Owned(match step { Ok(v) => v, - Err(Failure { error: FilterError::Corrupt { .. }, partial: out }) if !strict => { + Err(Failure { error: FilterError::Corrupt { .. }, partial: out, .. }) if !strict => { partial = true; out } @@ -216,15 +306,15 @@ fn decode_one(filter: &Filter, params: &Params, data: &[u8], max: usize) -> (Ste Filter::AsciiHex => counted(asciihex::decode(data, max)), Filter::Ascii85 => counted(ascii85::decode(data, max)), Filter::RunLength => counted(runlength::decode(data, max)), - other => (Err(Failure { error: FilterError::Unsupported(other.name().to_owned()), partial: Vec::new() }), 0), + other => (Err(Failure { error: FilterError::Unsupported(other.name().to_owned()), partial: Vec::new(), discarded: 0 }), 0), } } -/// A step with the bytes it produced, its output or its partial output. +/// A step with the bytes it produced: its output, or its partial output and what it threw away. fn counted(step: Step) -> (Step, usize) { let n = match &step { Ok(v) => v.len(), - Err(f) => f.partial.len(), + Err(f) => f.partial.len().saturating_add(f.discarded), }; (step, n) } @@ -236,12 +326,12 @@ fn with_predictor(step: Step, params: &Params, name: &'static str) -> (Step, usi let (step, n) = counted(step); let step = match step { Ok(v) => predictor::decode(params, v, name), - Err(Failure { error, partial }) => { + Err(Failure { error, partial, discarded }) => { let partial = match predictor::decode(params, partial, name) { Ok(v) => v, Err(f) => f.partial, }; - Err(Failure { error, partial }) + Err(Failure { error, partial, discarded }) } }; (step, n) @@ -428,6 +518,9 @@ mod tests { assert_eq!(decode(&chain, &data, max).map(|d| d.len()).ok(), Some(1 << 19)); assert!(matches!(decode_counted(&chain, &data, max), Err((FilterError::LimitExceeded(m), _)) if m == max)); assert_eq!(decode_counted(&chain, &data, 2 << 20).map(|(_, spent)| spent).ok(), Some((1 << 20) + (1 << 19))); + let tolerant = decode_tolerant_counted(&chain, &data, 2 << 20).map(|(out, partial, spent)| (out.len(), partial, spent)); + assert_eq!(tolerant.ok(), Some((1 << 19, false, (1 << 20) + (1 << 19)))); + assert!(matches!(decode_tolerant_counted(&chain, &data, max), Err((FilterError::LimitExceeded(m), _)) if m == max)); } /// A PNG predictor drops a tag byte per row, but Flate produced it: the count includes it, @@ -446,4 +539,157 @@ mod tests { assert!(matches!(e, FilterError::Corrupt { .. }), "{e}"); assert_eq!(spent, bad.len()); } + + fn refused(e: &FilterError) -> bool { + matches!(e, FilterError::Spent) + } + + /// A chain pays for what it reads and what each stage decodes, down to the byte: Flate inflates + /// hex that ASCIIHex halves, so a stage counts when a later one shrinks it. + #[test] + fn a_chain_spends_down_to_the_byte() { + let hex = b"ab".repeat(1 << 10); + let data = encode_flate(&hex); + let chain = [(Filter::Flate, Params::default()), (Filter::AsciiHex, Params::default())]; + let whole = decode(&chain, &data, 1 << 20).unwrap(); + let cost = (data.len() + hex.len() + whole.len()) as u64; + let mut work = u64::MAX; + assert_eq!(decode_tolerant_within(&chain, &data, 1 << 20, &mut work).unwrap(), whole); + assert_eq!(u64::MAX - work, cost); + let mut work = cost; + assert_eq!(decode_tolerant_within(&chain, &data, 1 << 20, &mut work).unwrap(), whole, "exactly enough"); + assert_eq!(work, 0); + let mut work = cost + 7; + decode_tolerant_within(&chain, &data, 1 << 20, &mut work).unwrap(); + assert_eq!(work, 7, "only what it took"); + let mut work = cost - 1; + assert!(refused(&decode_tolerant_within(&chain, &data, 1 << 20, &mut work).unwrap_err()), "a step short"); + assert_eq!(work, 0, "spends all that was left"); + // Each stage has `max_output` to itself, as in a plain decode: together they are past it. + let mut work = u64::MAX; + assert_eq!(decode_tolerant_within(&chain, &data, hex.len(), &mut work).unwrap(), whole); + } + + /// No stage runs past what is left: the first stage of this bomb stops there, so the second + /// isn't given anything to read, and with too little to read it nothing runs at all. + #[test] + fn a_chain_stops_at_what_is_left() { + let inner = encode_flate(&vec![0; 1 << 20]); + let bomb = encode_flate(&inner); + let chain = [(Filter::Flate, Params::default()), (Filter::Flate, Params::default())]; + let read = |work: u64| { + super::STAGE_BYTES.with(|c| c.set(0)); + let mut work = work; + assert!(refused(&decode_tolerant_within(&chain, &bomb, usize::MAX, &mut work).unwrap_err())); + assert_eq!(work, 0); + super::STAGE_BYTES.with(|c| c.get()) + }; + assert_eq!(read((bomb.len() + inner.len()) as u64 + 10), bomb.len() + inner.len(), "the second stage stops"); + assert_eq!(read(bomb.len() as u64 + 10), bomb.len(), "the first stops, and the second never runs"); + assert_eq!(read(bomb.len() as u64 - 1), 0, "it can't pay to be read"); + } + + /// Past `max_output` the chain has failed, and hasn't run out of anything: it pays what it took + /// to find out, and what is left stays. Whichever limit a stage stops at is the one reported. + #[test] + fn a_stage_past_its_limit_pays_for_finding_out() { + let data = encode_flate(&vec![0; 1 << 16]); + let chain = [(Filter::Flate, Params::default())]; + let mut work = u64::MAX; + assert!(matches!(decode_tolerant_within(&chain, &data, 1000, &mut work), Err(FilterError::LimitExceeded(1000)))); + assert_eq!(u64::MAX - work, data.len() as u64 + 1000); + // The later stage of two, which pays for the first as well. + let bomb = encode_flate(&data); + let two = [(Filter::Flate, Params::default()), (Filter::Flate, Params::default())]; + let mut work = u64::MAX; + assert!(matches!(decode_tolerant_within(&two, &bomb, data.len(), &mut work), Err(FilterError::LimitExceeded(_)))); + assert_eq!(u64::MAX - work, (bomb.len() + 2 * data.len()) as u64); + // Both limits at once: a run that can't go on is what a caller needs to hear. + let mut work = data.len() as u64 + 1000; + assert!(refused(&decode_tolerant_within(&chain, &data, 1000, &mut work).unwrap_err())); + assert_eq!(work, 0); + let mut work = data.len() as u64 + 1001; + assert!(matches!(decode_tolerant_within(&chain, &data, 1000, &mut work), Err(FilterError::LimitExceeded(1000)))); + assert_eq!(work, 1, "the image's limit, with a step to spare"); + } + + /// What a damaged stream decoded is paid for, however the decode ends. + #[test] + fn a_chain_that_fails_has_paid_for_what_it_did() { + let data: Vec = (0..20_000u32).map(|i| (i % 97) as u8 ^ (i / 300) as u8).collect(); + let mut cut = encode_flate(&data); + cut.truncate(cut.len() / 2); + let chain = [(Filter::Flate, Params::default())]; + let (partial, _) = decode_tolerant(&chain, &cut, 1 << 20).unwrap(); + assert!(!partial.is_empty()); + let mut work = u64::MAX; + assert_eq!(decode_tolerant_within(&chain, &cut, 1 << 20, &mut work).unwrap(), partial); + assert_eq!(u64::MAX - work, (cut.len() + partial.len()) as u64); + // Read strictly it is an error, for the same work. + let mut work = u64::MAX; + assert!(matches!(decode_within(&chain, &cut, 1 << 20, &mut work), Err(FilterError::Corrupt { .. }))); + assert_eq!(u64::MAX - work, (cut.len() + partial.len()) as u64); + let whole = encode_flate(&data); + let mut work = u64::MAX; + assert_eq!(decode_within(&chain, &whole, 1 << 20, &mut work).unwrap(), data); + assert_eq!(u64::MAX - work, (whole.len() + data.len()) as u64); + // A predictor that comes to nothing, after all of this was inflated for it. + let p = Params { predictor: 99, ..Params::default() }; + let data = encode_flate(&vec![0; 1 << 16]); + let mut work = u64::MAX; + assert!(decode_tolerant_within(&[(Filter::Flate, p)], &data, 1 << 20, &mut work).unwrap().is_empty()); + assert_eq!(u64::MAX - work, data.len() as u64 + (1 << 16)); + } + + /// A stream that reads as zlib only until it fails, and as raw deflate until that fails too, + /// gives back no data, and has still decoded everything the retry did. + #[test] + fn a_retry_that_fails_pays_for_what_it_decoded() { + // Stored as raw deflate: this many bytes, then a block of a reserved type. As zlib: the + // same reserved type at once, so the first reading fails with nothing. + let mut data = vec![0x78, 0x01, 0x06, 0xFE, 0xF9]; + data.extend(vec![0u8; 0x0601]); + data.push(0x07); + let chain = [(Filter::Flate, Params::default())]; + let (out, partial) = decode_tolerant(&chain, &data, 1 << 20).unwrap(); + assert!(out.is_empty() && partial, "what is read stays as it was"); + let (_, _, spent) = decode_tolerant_counted(&chain, &data, 1 << 20).unwrap(); + assert_eq!(spent, 0x0601); + let (e, spent) = decode_counted(&chain, &data, 1 << 20).unwrap_err(); + assert!(matches!(e, FilterError::Corrupt { .. }), "{e}"); + assert_eq!(spent, 0x0601); + let mut work = u64::MAX; + assert!(decode_tolerant_within(&chain, &data, 1 << 20, &mut work).unwrap().is_empty()); + assert_eq!(u64::MAX - work, (data.len() + 0x0601) as u64); + // Through a predictor, which would otherwise lose the count. + let p = Params { predictor: 12, columns: 4, ..Params::default() }; + let (_, _, spent) = decode_tolerant_counted(&[(Filter::Flate, p)], &data, 1 << 20).unwrap(); + assert_eq!(spent, 0x0601); + } + + /// With nothing left nothing is read. What can't be decoded at all never costs anything, and + /// says so whatever is left. Without filters, what is read is the data. + #[test] + fn what_a_chain_is_shows_whatever_is_left() { + let flate = [(Filter::Flate, Params::default())]; + let mut work = 0; + assert!(refused(&decode_tolerant_within(&flate, b"garbage", 1 << 20, &mut work).unwrap_err())); + let long = vec![(Filter::Flate, Params::default()); MAX_CHAIN + 1]; + for chain in [vec![(Filter::Dct, Params::default())], vec![(Filter::Jbig2, Params::default())], long] { + for left in [0, 100] { + let mut work = left; + let e = decode_tolerant_within(&chain, b"data", 1 << 20, &mut work).unwrap_err(); + assert!(matches!(e, FilterError::Unsupported(_)) && !refused(&e), "{e}"); + assert_eq!(work, left); + } + } + let mut work = 100; + assert_eq!(decode_tolerant_within(&[], b"data", 4, &mut work).unwrap(), b"data"); + assert_eq!(work, 96); + assert!(matches!(decode_tolerant_within(&[], b"data", 3, &mut work), Err(FilterError::LimitExceeded(3)))); + assert_eq!(work, 92); + let mut work = 3; + assert!(refused(&decode_tolerant_within(&[], b"data", 4, &mut work).unwrap_err())); + assert_eq!(work, 0); + } } diff --git a/crates/js/src/formcalc.rs b/crates/js/src/formcalc.rs index ff43bf0837..1d8da96696 100644 --- a/crates/js/src/formcalc.rs +++ b/crates/js/src/formcalc.rs @@ -228,4 +228,22 @@ mod tests { assert_eq!(parse_num("12abc"), Some(12.0)); assert_eq!(parse_num("abc"), None); } + + /// A number prints to at most fifteen significant digits, so the binary noise of a value + /// with six digits before the point (279893.88 is 279893.880000000004656… as a double) stays + /// hidden, while small values keep their twelve decimals. + #[test] + fn num_text_prints_at_most_fifteen_significant_digits() { + assert_eq!(num_text(279_893.88), "279893.88"); + assert_eq!(num_text(-279_893.88), "-279893.88"); + assert_eq!(num_text(279_893.88 + 291_774.12 + 304_171.06 + 317_107.44 + 273_970.85), "1466917.35"); + assert_eq!(num_text(1_000_000.0 / 3.0), "333333.333333333"); + assert_eq!(num_text(1.0 / 3.0), "0.333333333333"); + assert_eq!(num_text(0.3 - 0.1 - 0.2), "0", "noise below twelve decimals is zero"); + // Past fifteen digits before the point no decimals are left, and the integer keeps its zeros. + assert_eq!(num_text(1e15 + 0.5), "1000000000000000"); + assert_eq!(num_text(1e20), "100000000000000000000"); + assert_eq!(num_text(-1e20), "-100000000000000000000"); + assert_eq!(num_text(f64::MAX).len(), 309); + } } diff --git a/crates/js/src/formcalc/value.rs b/crates/js/src/formcalc/value.rs index 16705e67ec..5ea9d4c089 100644 --- a/crates/js/src/formcalc/value.rs +++ b/crates/js/src/formcalc/value.rs @@ -21,7 +21,11 @@ pub(super) enum Val { Sink, } -/// A number as FormCalc prints it: integers without a fraction, otherwise up to 15 digits. +/// A number as FormCalc prints it: integers without a fraction, otherwise to at most 12 +/// decimals and 15 significant digits, without trailing zeros. 15 digits is the most a double +/// holds for every value, so a value typed with up to 15 digits prints back as typed +/// (`279893.88 * 1` is `279893.88`, not `279893.880000000005`), and the binary noise past +/// them never shows. The 12 decimals hide noise left by sums that should be zero. pub(super) fn num_text(n: f64) -> String { if !n.is_finite() { return if n.is_nan() { @@ -35,8 +39,12 @@ pub(super) fn num_text(n: f64) -> String { if n.fract() == 0.0 && n.abs() < 1e15 { return format!("{}", n as i64); } - let s = format!("{n:.12}"); - let s = s.trim_end_matches('0').trim_end_matches('.'); + // Digits before the point (at most 309 for a finite double); 1 for |n| < 1. + let int_digits = format!("{:.0}", n.abs().trunc()).len(); + let decimals = 15usize.saturating_sub(int_digits).min(12); + let s = format!("{n:.decimals$}"); + // Only a fraction loses its trailing zeros: with no decimals left they belong to the integer. + let s = if s.contains('.') { s.trim_end_matches('0').trim_end_matches('.') } else { s.as_str() }; if s.is_empty() || s == "-0" { "0".into() } else { s.to_string() } } diff --git a/crates/js/src/tests.rs b/crates/js/src/tests.rs index c933097330..c8550c98a9 100644 --- a/crates/js/src/tests.rs +++ b/crates/js/src/tests.rs @@ -1026,6 +1026,20 @@ mod formcalc { assert_eq!(calc(r#"Format("9.9", -1.5)"#), "-1.5"); } + /// A calculated amount shows the number it is, not the binary noise past a double's 15 + /// significant digits: 279893.88 is stored as 279893.880000000004656…, which twelve fixed + /// decimals printed as `279893.880000000005`. Small values keep their twelve decimals. + #[test] + fn calculated_numbers_print_at_most_fifteen_significant_digits() { + assert_eq!(calc("1 * 279893.88"), "279893.88"); + assert_eq!(calc("1 * 291774.12"), "291774.12"); + assert_eq!(calc("279893.88 + 291774.12 + 304171.06 + 317107.44 + 273970.85"), "1466917.35"); + assert_eq!(calc("1000000 / 3"), "333333.333333333"); + assert_eq!(calc("1000 / 3"), "333.333333333333"); + assert_eq!(calc("1 / 3"), "0.333333333333"); + assert_eq!(calc("0.1 + 0.2"), "0.3"); + } + /// Assigning one long value to many fields at once stops at the run's byte budget and is /// charged per copy, and a reset list names each field once. #[test] diff --git a/crates/optimize/README.md b/crates/optimize/README.md index 27cada0d2f..2a6c664e6a 100644 --- a/crates/optimize/README.md +++ b/crates/optimize/README.md @@ -28,9 +28,10 @@ let report = optimize_with_progress(&mut doc, &settings, &mut |stage| keep_going If a use can't be measured (forms nested deeper, or drawn too many times), no image is resampled. Colour and grayscale images above a threshold are resampled with a bicubic (Catmull-Rom) filter to a target resolution and - stored as JPEG (Acrobat's quality steps) or ZIP; soft masks are resampled with their image. + stored as JPEG (Acrobat's quality steps) or ZIP; soft masks are resampled with their image. A + stencil `/Mask` has its own resolution, so the picture changes under it and it stays as it is. An image is replaced only if the result is smaller. Left alone by these colour and grey - settings: CMYK and other colour spaces, image masks, decode arrays, more than 8 bits, JPEG 2000, + settings: CMYK and other colour spaces, image masks, colour-key masks, decode arrays, more than 8 bits, JPEG 2000, JBIG2 and CCITT (black-and-white images, CCITT and JBIG2 among them, are below). A JPEG is read with its colour transform (an Adobe marker's, else `/ColorTransform`, ISO 32000-2 §7.4.8), so one stored untransformed keeps its colours; one whose marker and `/ColorTransform` disagree is left @@ -100,13 +101,19 @@ let report = optimize_with_progress(&mut doc, &settings, &mut |stage| keep_going - Lossless JBIG2 uses bounded generic-region encoding or exact-copy symbol dictionaries when smaller. No lossy symbol substitution is used. Export, redaction and this step read JBIG2 - images, with bounded shared globals. + images, with bounded shared globals. All of a run's images share one allowance of decoding + (`pdfcraft_cos::ImageBudget`), filters, decoders and pixels alike, JPEG samples and merged + pictures too: about + 1,000 scanned pages' worth, plus more for each byte of the file, enough to decode a stream + about 8 times at Flate's best. Images past it stay as they are, and `Report::images_refused` + counts those the image step read. Streams it only stores with Flate (below) aren't counted. - **Discard objects:** thumbnails, alternate images, document tags, print settings. - **Clean up:** Flate for streams with no filter; for streams with an outer ASCII85 or ASCIIHex layer, that layer is removed when the result is smaller (the inner filters keep their encoded bytes; streams with `/DecodeParms`, images and object streams keep their ASCII layer. LZW-compressed streams, content and images alike, are decoded and stored with Flate instead (Acrobat's "In - streams that use LZW encoding, use Flate instead"): a predictor carries over to Flate without + streams that use LZW encoding, use Flate instead"), from the run's allowance, past which they + stay LZW: a predictor carries over to Flate without `EarlyChange`, filters applied before the LZW one go with it and those after it keep their bytes. A stream whose LZW data doesn't decode cleanly is left as it is. Not yet: inline images. diff --git a/crates/optimize/src/fragments.rs b/crates/optimize/src/fragments.rs index c069de2f95..f74b091984 100644 --- a/crates/optimize/src/fragments.rs +++ b/crates/optimize/src/fragments.rs @@ -18,7 +18,7 @@ //! drops them. use pdfcraft_content::{Matrix, Op, parse, serialize_ops}; -use pdfcraft_cos::{DecodeBudget, Dict, Document, ObjRef, Object, Stream}; +use pdfcraft_cos::{DecodeBudget, Dict, Document, ImageBudget, ObjRef, Object, Stream}; use crate::images::{components, content_bytes, decodable, page_resources, pixels, resample}; use crate::{OptimizeError, Report, Stage}; @@ -152,7 +152,7 @@ fn run_end(ops: &[Op], i: usize, count: usize) -> usize { } /// The run's pixels as one image, top row first: `(pixels, width, height)`. -fn merge(doc: &Document, run: &[Fragment], n: usize) -> Option<(Vec, u32, u32)> { +fn merge(doc: &Document, run: &[Fragment], n: usize, budget: &mut ImageBudget) -> Option<(Vec, u32, u32)> { let (top, bottom) = (run.first()?.rect[3], run.last()?.rect[1]); let width = run.iter().map(|f| f.width).max()?; // Pixel rows per unit of height: the finest fragment's. @@ -167,7 +167,12 @@ fn merge(doc: &Document, run: &[Fragment], n: usize) -> Option<(Vec, u32, u3 return None; } let row = (width as usize).checked_mul(n)?; - let mut out = vec![255u8; row.checked_mul(height as usize)?]; + // What this builds isn't what its strips cost to read: four small ones can ask for all of it. + let bytes = row.checked_mul(height as usize)?; + if !budget.pay_pixels(u64::try_from(bytes).ok()?) { + return None; + } + let mut out = vec![255u8; bytes]; for f in run { let r0 = (((top - f.rect[3]) * density).round().max(0.0) as u32).min(height); let r1 = (((top - f.rect[1]) * density).round().max(0.0) as u32).min(height); @@ -176,7 +181,7 @@ fn merge(doc: &Document, run: &[Fragment], n: usize) -> Option<(Vec, u32, u3 } let obj = doc.get(f.image); let Object::Stream(s) = &*obj else { return None }; - let px = pixels(doc, s, n)?; + let px = pixels(doc, s, n, budget)?; let px = if (f.width, f.height) == (width, r1 - r0) { px } else { resample(&px, n, f.width, f.height, width, r1 - r0)? }; out.get_mut(r0 as usize * row..r1 as usize * row)?.copy_from_slice(px.get(..(r1 - r0) as usize * row)?); } @@ -230,7 +235,13 @@ fn add_xobject(doc: &mut Document, page: ObjRef, name: &[u8], image: ObjRef) -> } /// Merge the fragment runs of one page; returns how many fragments were merged. -fn merge_page(doc: &mut Document, page: ObjRef, report: &mut Report, progress: &mut dyn FnMut(Stage) -> bool) -> Result { +fn merge_page( + doc: &mut Document, + page: ObjRef, + report: &mut Report, + progress: &mut dyn FnMut(Stage) -> bool, + images: &mut ImageBudget, +) -> Result { let Some(contents) = doc.get(page).as_dict().and_then(|d| d.get(b"Contents").cloned()) else { return Ok(0) }; // A page whose content isn't all known is left alone: rewriting it would drop the rest. let Some(data) = content_bytes(doc, &contents, &mut DecodeBudget::page()) else { return Ok(0) }; @@ -286,7 +297,7 @@ fn merge_page(doc: &mut Document, page: ObjRef, report: &mut Report, progress: & if !progress(Stage::Fragments) { return Err(OptimizeError::Cancelled); } - let Some((px, w, h)) = merge(doc, &run, n) else { + let Some((px, w, h)) = merge(doc, &run, n, images) else { out.extend(ops.get(i..j).unwrap_or_default().iter().cloned()); i = j; continue; @@ -320,9 +331,15 @@ fn merge_page(doc: &mut Document, page: ObjRef, report: &mut Report, progress: & Ok(merged) } -pub(crate) fn run(doc: &mut Document, pages: &[ObjRef], report: &mut Report, progress: &mut dyn FnMut(Stage) -> bool) -> Result<(), OptimizeError> { +pub(crate) fn run( + doc: &mut Document, + pages: &[ObjRef], + report: &mut Report, + progress: &mut dyn FnMut(Stage) -> bool, + budget: &mut ImageBudget, +) -> Result<(), OptimizeError> { for p in pages { - report.fragments_merged += merge_page(doc, *p, report, progress)?; + report.fragments_merged += merge_page(doc, *p, report, progress, budget)?; } Ok(()) } @@ -343,7 +360,49 @@ mod tests { Fragment { image, rect: [0.0, edge, 1.0, 1.0], width: 1 << 16, height: 1 }, Fragment { image, rect: [0.0, 0.0, 1.0, edge], width: 1 << 16, height: 1 }, ]; - assert!(merge(&Document::new_empty(), &run, 3).is_none()); + assert!(merge(&Document::new_empty(), &run, 3, &mut ImageBudget::with_work(u64::MAX)).is_none()); + } + + /// Merging reads the images the pass after it reads, from the same allowance: with nothing + /// left the strips stay as they are, and the budget shows the read it refused. + #[test] + fn merging_spends_the_runs_allowance() { + let mut doc = Document::new_empty(); + let mut image = Dict::new(); + for (k, v) in + [("Subtype", Object::name("Image")), ("Width", Object::Int(8)), ("Height", Object::Int(1)), ("BitsPerComponent", Object::Int(8))] + { + image.set(k.as_bytes().to_vec(), v); + } + image.set(b"ColorSpace".to_vec(), Object::name("DeviceGray")); + let (mut xobjects, mut drawn, mut raw) = (Dict::new(), String::new(), 0); + for row in 0..8 { + let strip = Stream::flate(image.clone(), &[row * 30; 8]); + raw += strip.raw.len() as u64; + let r = doc.add(Object::Stream(strip)); + xobjects.set(format!("I{row}").into_bytes(), Object::Ref(r)); + drawn.push_str(&format!("q 80 0 0 10 0 {} cm /I{row} Do Q\n", 70 - 10 * i32::from(row))); + } + let content = doc.add(Object::Stream(Stream::flate(Dict::new(), drawn.as_bytes()))); + let mut resources = Dict::new(); + resources.set(b"XObject".to_vec(), Object::Dict(xobjects)); + let mut page = Dict::new(); + page.set(b"Type".to_vec(), Object::name("Page")); + page.set(b"Resources".to_vec(), Object::Dict(resources)); + page.set(b"Contents".to_vec(), Object::Ref(content)); + let page = doc.add(Object::Dict(page)); + let mut budget = ImageBudget::with_work(0); + assert_eq!(merge_page(&mut doc.clone(), page, &mut Report::default(), &mut |_| true, &mut budget).unwrap(), 0); + assert_eq!(budget.refused(), 1); + // Reading each strip, and building the picture of 8 rows of 8 they make. + let cost = raw + 8 * (8 + 8) + 8 * 8; + let mut budget = ImageBudget::with_work(u64::MAX); + assert_eq!(merge_page(&mut doc.clone(), page, &mut Report::default(), &mut |_| true, &mut budget).unwrap(), 8); + assert_eq!(u64::MAX - budget.work_left(), cost); + // Enough for the strips and not for the picture: nothing is built. + let mut budget = ImageBudget::with_work(cost - 1); + assert_eq!(merge_page(&mut doc, page, &mut Report::default(), &mut |_| true, &mut budget).unwrap(), 0); + assert_eq!(budget.refused(), 1); } /// Many images drawn on top of each other are not one picture; looking for runs among them reads @@ -370,7 +429,7 @@ mod tests { page.set(b"Resources".to_vec(), Object::Dict(resources)); let page = doc.add(Object::Dict(page)); GROUP_READS.with(|c| c.set(0)); - let merged = merge_page(&mut doc, page, &mut Report::default(), &mut |_| true); + let merged = merge_page(&mut doc, page, &mut Report::default(), &mut |_| true, &mut ImageBudget::with_work(u64::MAX)); assert_eq!(merged.ok(), Some(0)); let reads = GROUP_READS.with(|c| c.get()); assert!(reads <= 40 * 4 * groups, "{reads} group reads"); diff --git a/crates/optimize/src/images.rs b/crates/optimize/src/images.rs index 613cc3f26f..efff394a6f 100644 --- a/crates/optimize/src/images.rs +++ b/crates/optimize/src/images.rs @@ -4,7 +4,7 @@ use std::collections::{HashMap, HashSet}; use std::sync::Arc; use pdfcraft_content::{Matrix, Pieces}; -use pdfcraft_cos::{DecodeBudget, Dict, Document, ObjRef, Object, Stream}; +use pdfcraft_cos::{DecodeBudget, Dict, Document, ImageBudget, ObjRef, Object, Stream}; use crate::{Compression, ImageSettings, MonoCompression, MonoSettings, OptimizeError, Report, Settings, Stage}; @@ -479,7 +479,7 @@ fn count_decoded(_n: u64) { /// every row, and the image would be written back wrong. `None` for a JPEG whose colour transform /// readers may disagree about ([`ycc_encoded`]), and for data that decodes past what the samples /// can need ([`allowance`]). -pub(crate) fn pixels(doc: &Document, s: &Stream, n: usize) -> Option> { +pub(crate) fn pixels(doc: &Document, s: &Stream, n: usize, budget: &mut ImageBudget) -> Option> { let (w, h) = (u32::try_from(s.dict.int(b"Width")?).ok()?, u32::try_from(s.dict.int(b"Height")?).ok()?); if w == 0 || h == 0 || u64::from(w) * u64::from(h) > MAX_PIXELS { return None; @@ -490,11 +490,14 @@ pub(crate) fn pixels(doc: &Document, s: &Stream, n: usize) -> Option> { // never get here: the colour space check excludes them. The JPEG's own size must be the // dictionary's: `jpeg_samples` refuses another from its header, before any pixels. let ycc = n == 3 && ycc_encoded(doc, s)?; + if !budget.pay_jpeg(u64::try_from(bytes).ok()?, &s.raw) { + return None; + } let v = jpeg_samples(&s.raw, usize::try_from(w).ok()?, usize::try_from(h).ok()?, n, ycc)?; count_decoded(u64::from(w) * u64::from(h)); (v.len() == bytes).then_some(v) } else { - let v = doc.with_direct_parms(s).decoded_within(allowance(bytes, h)?).ok()?; + let v = budget.decode_filters(doc, s, allowance(bytes, h)?).ok()?; Some(v.get(..bytes)?.to_vec()) } } @@ -714,12 +717,27 @@ fn image_stream(old: &Dict, px: &[u8], n: usize, w: u32, h: u32, compression: Co } } +/// Whether a `/Mask` value is a stencil mask: an image that says `/ImageMask true`. +fn is_stencil(doc: &Document, mask: &Object) -> bool { + matches!(&*doc.resolve(mask), Object::Stream(s) if matches!(s.dict.get(b"ImageMask"), Some(Object::Bool(true)))) +} + /// One image: resample and/or recompress per `settings`; `ppi` is its effective resolution. /// Returns the new image and its new soft mask, if the result is smaller. -fn process(doc: &Document, s: &Stream, ppi: f64, settings: &ImageSettings, n: usize) -> Option<(Stream, Option<(ObjRef, Stream)>)> { +fn process( + doc: &Document, + s: &Stream, + ppi: f64, + settings: &ImageSettings, + n: usize, + budget: &mut ImageBudget, +) -> Option<(Stream, Option<(ObjRef, Stream)>)> { let d = &s.dict; + // A colour-key mask names sample values, which resampling and JPEG would change. A stencil mask + // is an image of its own, with its own resolution (ISO 32000-2 §8.9.6.3): the picture can change + // under it and its edges stay as they are. if d.get(b"Decode").is_some_and(|a| !is_identity_decode(doc, a, n)) - || d.contains(b"Mask") + || d.get(b"Mask").is_some_and(|m| !is_stencil(doc, m)) || d.name(b"ImageMask").is_some() || matches!(d.get(b"ImageMask"), Some(Object::Bool(true))) { @@ -748,7 +766,7 @@ fn process(doc: &Document, s: &Stream, ppi: f64, settings: &ImageSettings, n: us } else { (w, h) }; - let px = pixels(doc, s, n)?; + let px = pixels(doc, s, n, budget)?; let px = if (nw, nh) != (w, h) { resample(&px, n, w, h, nw, nh)? } else { px }; let new = image_stream(d, &px, n, nw, nh, settings.compression, was_dct)?; // A soft mask must keep the image's dimensions: resample it with the image (lossless). @@ -761,7 +779,7 @@ fn process(doc: &Document, s: &Stream, ppi: f64, settings: &ImageSettings, n: us return None; } let (mw, mh) = (u32::try_from(m.dict.int(b"Width")?).ok()?, u32::try_from(m.dict.int(b"Height")?).ok()?); - let mpx = pixels(doc, m, 1)?; + let mpx = pixels(doc, m, 1, budget)?; let mpx = resample(&mpx, 1, mw, mh, nw, nh)?; smask = Some((mr, image_stream(&m.dict, &mpx, 1, nw, nh, Compression::Flate, false)?)); } @@ -801,7 +819,7 @@ type Pixel = fn(&[u8]) -> Option; /// with its width and height, and, when they were packed from more bits, its dictionary as a 1-bit /// image. These count: /// - one bit per pixel in one colour component, or an image mask, stored with no filter, with -/// general-purpose ones, or with CCITT fax or JBIG2 last ([`Document::decoded_image_within`], no further +/// general-purpose ones, or with CCITT fax or JBIG2 last ([`ImageBudget::decode`], no further /// than its rows can need); /// - with `pack`, and with no colour-key `/Mask` (its ranges are in the image's own values): /// - eight-bit grey (one component, not indexed) whose every sample is 0 or 255. A decode array @@ -815,7 +833,7 @@ type Pixel = fn(&[u8]) -> Option; /// - an indexed image of 2, 4 or 8 bits that uses only palette entries 0 and 1, which stay 0 and /// 1 at one bit, whatever their colours, so the colour space stays. A decode array other than /// the default stops it: in index units it would mean something else at one bit. -fn one_bit(doc: &Document, s: &Stream, pack: bool, defaults: bool) -> Option<(Vec, u32, u32, Option)> { +fn one_bit(doc: &Document, s: &Stream, pack: bool, defaults: bool, budget: &mut ImageBudget) -> Option<(Vec, u32, u32, Option)> { let d = &s.dict; // Through u32 first, as everywhere here, so the product can't overflow. let (w, h) = (u32::try_from(d.int(b"Width")?).ok()?, u32::try_from(d.int(b"Height")?).ok()?); @@ -836,7 +854,7 @@ fn one_bit(doc: &Document, s: &Stream, pack: bool, defaults: bool) -> Option<(Ve _ => allowance(len, h)?, }; count_decoded(u64::from(w) * u64::from(h)); - let mut data = doc.decoded_image_within(s, max).ok()?; + let mut data = budget.decode(doc, s, max).ok()?; if data.len() < len { return None; } @@ -904,7 +922,7 @@ fn one_bit(doc: &Document, s: &Stream, pack: bool, defaults: bool) -> Option<(Ve let row_len = wu.checked_mul(n)?.checked_mul(bpc)?.div_ceil(8); // Through its parameters given by reference too: without a PNG predictor's tag bytes taken // off, rows of 0 and 255 (or palette entries 0 and 1) would still pass below, each shifted. - let samples = doc.with_direct_parms(s).decoded_within(allowance(row_len.checked_mul(hu)?, h)?).ok()?; + let samples = budget.decode_filters(doc, s, allowance(row_len.checked_mul(hu)?, h)?).ok()?; Some((packed_rows(&samples, row_len, wu, hu, (n, bpc, white))?, w, h, Some(packed))) } @@ -1104,7 +1122,7 @@ fn downsample_bits_checked(data: &[u8], w: u32, h: u32, nw: u32, nh: u32, dark_i /// The samples keep their meaning, so the colour space, decode array and `/Mask` stay, but for /// black-and-white RGB, which becomes grey with one decode pair, and an indexed image's default /// decode array, which goes as the default at one bit. -fn mono(doc: &Document, s: &Stream, ppi: f64, defaults: bool, settings: &MonoSettings) -> Option<(Stream, bool)> { +fn mono(doc: &Document, s: &Stream, ppi: f64, defaults: bool, settings: &MonoSettings, budget: &mut ImageBudget) -> Option<(Stream, bool)> { let d = &s.dict; let downsample = settings.downsample && ppi.is_finite() && ppi > settings.above_ppi && settings.target_ppi > 0.0 && !d.contains(b"SMask"); let retain = settings.compression == MonoCompression::Retain; @@ -1118,10 +1136,13 @@ fn mono(doc: &Document, s: &Stream, ppi: f64, defaults: bool, settings: &MonoSet // JBIG2 (whose symbols may be smaller than its own coding) can be smaller stored again alone. let alone_to_g4 = s.filters().len() == 1 && settings.compression == MonoCompression::CcittG4; let only_to_resample = retain || (alone_to_g4 && (jbig2 || fax.is_some_and(|p| p.k < 0))); - if only_to_resample && !downsample { + // What can't be averaged, whatever it holds, comes to the same `None` below, after a decode that + // would spend the run's allowance on it. + let too_wide = d.int(b"Width").is_some_and(|w| w > i64::from(pdfcraft_filters::MAX_CCITT_COLUMNS)); + if only_to_resample && (!downsample || defaults || too_wide || settings.target_ppi >= ppi || (jbig2 && dark_is_one(doc, d).is_none())) { return None; } - let (data, w, h, packed) = one_bit(doc, s, !retain, defaults)?; + let (data, w, h, packed) = one_bit(doc, s, !retain, defaults, budget)?; let packed_from_more = packed.is_some(); let k = settings.target_ppi / ppi; // `downsample_bits` keeps a counter for each column: no more columns than a fax row may have, @@ -1188,12 +1209,15 @@ fn mono(doc: &Document, s: &Stream, ppi: f64, defaults: bool, settings: &MonoSet (best.0 < crate::stored_len(s)?).then_some((best.1, resampled)) } +/// One pass over the document's images, within `budget`. An image past it stays as it is, and is +/// counted in the report. pub(crate) fn run( doc: &mut Document, pages: &[ObjRef], settings: &Settings, report: &mut Report, progress: &mut dyn FnMut(Stage) -> bool, + budget: &mut ImageBudget, ) -> Result<(), OptimizeError> { let (ppi, mut defaults, read) = walk_pages(doc, pages); // Black-and-white RGB becomes grey, which default colour spaces would draw otherwise, and an @@ -1222,10 +1246,11 @@ pub(crate) fn run( let obj = doc.get(r); let Object::Stream(s) = &*obj else { continue }; report.images += 1; + let refused = budget.refused(); // Packed from more bits a sample, it is lossless at one bit, but the grey or colour // settings can make it smaller still (below). let packed_from_more = s.dict.int(b"BitsPerComponent").is_some_and(|b| b > 1); - let (packed, mono) = match mono(doc, s, ppi, defaults.contains(&r.num), &settings.mono) { + let (packed, mono) = match mono(doc, s, ppi, defaults.contains(&r.num), &settings.mono, budget) { Some(m) if packed_from_more => (Some(m), None), m => (None, m), }; @@ -1242,7 +1267,7 @@ pub(crate) fn run( continue; } let n = s.dict.get(b"ColorSpace").and_then(|cs| components(doc, cs)); - let processed = n.and_then(|n| process(doc, s, ppi, if n == 1 { &settings.gray } else { &settings.color }, n)); + let processed = n.and_then(|n| process(doc, s, ppi, if n == 1 { &settings.gray } else { &settings.color }, n, budget)); // A dithered scan, say, downsampled and JPEG-compressed: the smaller wins, counting a soft // mask resampled with it. let smask_len = |smask: Option<&(ObjRef, Stream)>| match smask { @@ -1268,7 +1293,11 @@ pub(crate) fn run( doc.set(r, Object::Stream(new)); continue; } - let Some((new, smask)) = processed else { continue }; + let Some((new, smask)) = processed else { + // Read to be packed and again to be resampled, it is still one image, and it stayed. + report.images_refused += usize::from(budget.refused() > refused); + continue; + }; let resized = new.dict.int(b"Width") != s.dict.int(b"Width") || new.dict.int(b"Height") != s.dict.int(b"Height"); report.image_bytes_before += s.raw.len(); report.image_bytes_after += new.raw.len(); @@ -1316,13 +1345,16 @@ mod dimension_tests { dict.set(b"Width".to_vec(), Object::Int(width)); dict.set(b"Height".to_vec(), Object::Int(height)); let stream = Stream::from_raw(dict, vec![0; 4]); - assert!(pixels(&Document::new_empty(), &stream, channels).is_none(), "{width} x {height} x {channels}"); + assert!( + pixels(&Document::new_empty(), &stream, channels, &mut ImageBudget::with_work(u64::MAX)).is_none(), + "{width} x {height} x {channels}" + ); } let mut dict = Dict::new(); dict.set(b"Width".to_vec(), Object::Int(2)); dict.set(b"Height".to_vec(), Object::Int(2)); let stream = Stream::from_raw(dict, vec![1, 2, 3, 4, 5]); - assert_eq!(pixels(&Document::new_empty(), &stream, 1), Some(vec![1, 2, 3, 4])); + assert_eq!(pixels(&Document::new_empty(), &stream, 1, &mut ImageBudget::with_work(u64::MAX)), Some(vec![1, 2, 3, 4])); } /// JBIG2 alone, with Group 4 asked for, is decoded only to be resampled. A cost guard: dropped, @@ -1344,7 +1376,7 @@ mod dimension_tests { let settings = MonoSettings { compression: MonoCompression::CcittG4, ..MonoSettings::REDUCE }; let decoded = |s: &Stream, settings: &MonoSettings| { DECODED_PIXELS.with(|c| c.set(0)); - mono(&Document::new_empty(), s, 300.0, false, settings); + mono(&Document::new_empty(), s, 300.0, false, settings, &mut ImageBudget::with_work(u64::MAX)); DECODED_PIXELS.with(|c| c.get()) }; let alone = image(Object::name("JBIG2Decode"), coded.clone()); @@ -1355,6 +1387,281 @@ mod dimension_tests { assert!(decoded(&alone, &jbig2) > 0, "stored as JBIG2 its symbols may come out smaller"); } + /// A run has one allowance for all its JBIG2 images. Those past it stay as they are, and the + /// report says how many: a file of thousands of them can't hold a run for hours. + #[test] + fn jbig2_images_past_the_runs_allowance_stay_as_they_are() { + let coded = pdfcraft_filters::encode_jbig2_generic(&[0xF0; 4], 16, 2).unwrap(); + let mut dict = Dict::new(); + dict.set(b"Type".to_vec(), Object::name("XObject")); + dict.set(b"Subtype".to_vec(), Object::name("Image")); + dict.set(b"Width".to_vec(), Object::Int(16)); + dict.set(b"Height".to_vec(), Object::Int(2)); + dict.set(b"BitsPerComponent".to_vec(), Object::Int(1)); + dict.set(b"ColorSpace".to_vec(), Object::name("DeviceGray")); + dict.set(b"Filter".to_vec(), Object::name("JBIG2Decode")); + let image = Stream::from_raw(dict, coded); + let mut cost = ImageBudget::with_work(u64::MAX); + cost.decode(&Document::new_empty(), &image, 1 << 20).unwrap(); + let cost = u64::MAX - cost.work_left(); + + let mut doc = Document::new_empty(); + let refs = [doc.add(Object::Stream(image.clone())), doc.add(Object::Stream(image.clone())), doc.add(Object::Stream(image.clone()))]; + let mut xobjects = Dict::new(); + for (i, r) in refs.iter().enumerate() { + xobjects.set(format!("I{i}").into_bytes(), Object::Ref(*r)); + } + let mut resources = Dict::new(); + resources.set(b"XObject".to_vec(), Object::Dict(xobjects)); + // Drawn small enough, at 720 ppi, for the settings to resample all three. + let content = doc.add(Object::Stream(Stream::flate(Dict::new(), b"q 1.6 0 0 .2 0 0 cm /I0 Do /I1 Do /I2 Do Q"))); + let mut page = Dict::new(); + page.set(b"Type".to_vec(), Object::name("Page")); + page.set(b"Resources".to_vec(), Object::Dict(resources)); + page.set(b"Contents".to_vec(), Object::Ref(content)); + let page = doc.add(Object::Dict(page)); + + let settings = Settings { mono: MonoSettings { compression: MonoCompression::CcittG4, ..MonoSettings::REDUCE }, ..Settings::default() }; + let mut report = Report::default(); + let mut budget = ImageBudget::with_work(2 * cost); + run(&mut doc, &[page], &settings, &mut report, &mut |_| true, &mut budget).unwrap(); + assert_eq!(report.images_refused, 1); + assert_eq!(budget.work_left(), 0, "two decoded and the third refused"); + assert_eq!(report.images_resampled, 2); + let changed = refs.iter().filter(|r| matches!(&*doc.get(**r), Object::Stream(s) if *s != image)).count(); + assert_eq!(changed, 2, "the third is as it was"); + } + + /// Images that aren't JBIG2 share the run's allowance too, both on the way to being resampled + /// and on the way to being packed to a bit a sample: a file of filter bombs would hold a run + /// as long as one of JBIG2, and those past it stay as they are. + #[test] + fn flate_images_past_the_runs_allowance_stay_as_they_are() { + // Noise, resampled, or black and white, packed. + let mut seed = 0x2545_F491_4F6C_DD1Du64; + let noise: Vec = (0..256 * 256) + .map(|_| { + seed ^= seed << 13; + seed ^= seed >> 7; + seed ^= seed << 17; + seed as u8 + }) + .collect(); + let black_and_white: Vec = noise.iter().map(|v| if v & 1 == 0 { 0 } else { 255 }).collect(); + for (name, samples, settings) in [ + ("resampled", &noise, Settings::default()), + ( + "packed", + &black_and_white, + Settings { mono: MonoSettings { compression: MonoCompression::CcittG4, ..MonoSettings::REDUCE }, ..Settings::default() }, + ), + ] { + let page_of = |images: usize| { + let mut doc = Document::new_empty(); + let mut dict = Dict::new(); + dict.set(b"Subtype".to_vec(), Object::name("Image")); + dict.set(b"Width".to_vec(), Object::Int(256)); + dict.set(b"Height".to_vec(), Object::Int(256)); + dict.set(b"BitsPerComponent".to_vec(), Object::Int(8)); + dict.set(b"ColorSpace".to_vec(), Object::name("DeviceGray")); + let image = Stream::flate(dict, samples); + let refs: Vec = (0..images).map(|_| doc.add(Object::Stream(image.clone()))).collect(); + let mut xobjects = Dict::new(); + let mut drawn = String::from("q 10 0 0 10 0 0 cm "); + for (i, r) in refs.iter().enumerate() { + xobjects.set(format!("I{i}").into_bytes(), Object::Ref(*r)); + drawn.push_str(&format!("/I{i} Do ")); + } + drawn.push('Q'); + let mut resources = Dict::new(); + resources.set(b"XObject".to_vec(), Object::Dict(xobjects)); + let content = doc.add(Object::Stream(Stream::flate(Dict::new(), drawn.as_bytes()))); + let mut page = Dict::new(); + page.set(b"Type".to_vec(), Object::name("Page")); + page.set(b"Resources".to_vec(), Object::Dict(resources)); + page.set(b"Contents".to_vec(), Object::Ref(content)); + let page = doc.add(Object::Dict(page)); + (doc, page, refs, image) + }; + let (mut doc, page, ..) = page_of(1); + let mut budget = ImageBudget::with_work(u64::MAX); + let mut report = Report::default(); + run(&mut doc, &[page], &settings, &mut report, &mut |_| true, &mut budget).unwrap(); + let cost = u64::MAX - budget.work_left(); + assert!(cost > 0, "{name}"); + assert_eq!(report.images_refused, 0, "{name}"); + + let (mut doc, page, refs, image) = page_of(3); + let mut budget = ImageBudget::with_work(2 * cost); + let mut report = Report::default(); + run(&mut doc, &[page], &settings, &mut report, &mut |_| true, &mut budget).unwrap(); + assert_eq!(report.images_refused, 1, "{name}: {report:?}"); + assert_eq!(budget.work_left(), 0, "{name}"); + let changed = refs.iter().filter(|r| matches!(&*doc.get(**r), Object::Stream(s) if *s != image)).count(); + assert_eq!(changed, 2, "{name}: the third is as it was"); + } + } + + /// An image the allowance ran out on between being packed and being resampled is rewritten, + /// as the packed one, so it isn't one that stayed as it was. + #[test] + fn a_packed_image_isnt_counted_as_refused() { + let mut seed = 0x2545_F491_4F6C_DD1Du64; + let samples: Vec = (0..256 * 256) + .map(|_| { + seed ^= seed << 13; + seed ^= seed >> 7; + seed ^= seed << 17; + if seed & 1 == 0 { 0 } else { 255 } + }) + .collect(); + let mut doc = Document::new_empty(); + let mut dict = Dict::new(); + dict.set(b"Subtype".to_vec(), Object::name("Image")); + dict.set(b"Width".to_vec(), Object::Int(256)); + dict.set(b"Height".to_vec(), Object::Int(256)); + dict.set(b"BitsPerComponent".to_vec(), Object::Int(8)); + dict.set(b"ColorSpace".to_vec(), Object::name("DeviceGray")); + let image = Stream::flate(dict, &samples); + let read = (image.raw.len() + samples.len()) as u64 + 256 * 256; + let original = doc.add(Object::Stream(image.clone())); + let mut xobjects = Dict::new(); + xobjects.set(b"I0".to_vec(), Object::Ref(original)); + let mut resources = Dict::new(); + resources.set(b"XObject".to_vec(), Object::Dict(xobjects)); + let content = doc.add(Object::Stream(Stream::flate(Dict::new(), b"q 10 0 0 10 0 0 cm /I0 Do Q"))); + let mut page = Dict::new(); + page.set(b"Type".to_vec(), Object::name("Page")); + page.set(b"Resources".to_vec(), Object::Dict(resources)); + page.set(b"Contents".to_vec(), Object::Ref(content)); + let page = doc.add(Object::Dict(page)); + let settings = Settings { mono: MonoSettings { compression: MonoCompression::CcittG4, ..MonoSettings::REDUCE }, ..Settings::default() }; + let mut report = Report::default(); + let mut budget = ImageBudget::with_work(read); + run(&mut doc, &[page], &settings, &mut report, &mut |_| true, &mut budget).unwrap(); + assert_eq!(budget.refused(), 1, "its second read was refused"); + assert_eq!(report.images_refused, 0, "{report:?}"); + assert_eq!(report.images_recompressed + report.images_resampled, 1, "{report:?}"); + assert!(matches!(&*doc.get(original), Object::Stream(s) if *s != image)); + } + + /// An image the run has no use for stayed as it was too, but nothing refused it: this one is + /// too small to compress and drawn at no more than its size. + #[test] + fn an_image_left_alone_isnt_counted_as_refused() { + let mut doc = Document::new_empty(); + let mut dict = Dict::new(); + dict.set(b"Subtype".to_vec(), Object::name("Image")); + dict.set(b"Width".to_vec(), Object::Int(8)); + dict.set(b"Height".to_vec(), Object::Int(8)); + dict.set(b"BitsPerComponent".to_vec(), Object::Int(8)); + dict.set(b"ColorSpace".to_vec(), Object::name("DeviceGray")); + let image = doc.add(Object::Stream(Stream::flate(dict, &[0x80; 64]))); + let mut xobjects = Dict::new(); + xobjects.set(b"I0".to_vec(), Object::Ref(image)); + let mut resources = Dict::new(); + resources.set(b"XObject".to_vec(), Object::Dict(xobjects)); + let content = doc.add(Object::Stream(Stream::flate(Dict::new(), b"q 72 0 0 72 0 0 cm /I0 Do Q"))); + let mut page = Dict::new(); + page.set(b"Type".to_vec(), Object::name("Page")); + page.set(b"Resources".to_vec(), Object::Dict(resources)); + page.set(b"Contents".to_vec(), Object::Ref(content)); + let page = doc.add(Object::Dict(page)); + let mut report = Report::default(); + run(&mut doc, &[page], &Settings::default(), &mut report, &mut |_| true, &mut ImageBudget::with_work(u64::MAX)).unwrap(); + assert_eq!((report.images, report.images_refused), (1, 0), "{report:?}"); + } + + /// A JPEG pays for its samples before it is decoded, however few bytes it takes: past what is + /// left it isn't, and counts as refused. + #[test] + fn a_jpeg_pays_for_its_samples() { + let mut dict = Dict::new(); + dict.set(b"Width".to_vec(), Object::Int(16)); + dict.set(b"Height".to_vec(), Object::Int(8)); + dict.set(b"BitsPerComponent".to_vec(), Object::Int(8)); + dict.set(b"ColorSpace".to_vec(), Object::name("DeviceRGB")); + let jpeg = image_stream(&dict, &[120; 16 * 8 * 3], 3, 16, 8, Compression::Jpeg(60), false).expect("a JPEG"); + let doc = Document::new_empty(); + let cost = 2 * 16 * 8 * 3 + 4 * jpeg.raw.len() as u64; + let mut budget = ImageBudget::with_work(cost); + assert_eq!(pixels(&doc, &jpeg, 3, &mut budget).map(|p| p.len()), Some(16 * 8 * 3)); + assert_eq!((budget.work_left(), budget.refused()), (0, 0), "exactly that"); + let mut budget = ImageBudget::with_work(cost - 1); + assert!(pixels(&doc, &jpeg, 3, &mut budget).is_none()); + assert_eq!((budget.work_left(), budget.refused()), (0, 1)); + } + + /// A soft mask resampled with its image is read from the same allowance as the image. + #[test] + fn a_soft_mask_resampled_with_its_image_spends_the_allowance() { + let mut seed = 0x2545_F491_4F6C_DD1Du64; + let noise: Vec = (0..256 * 256) + .map(|_| { + seed ^= seed << 13; + seed ^= seed >> 7; + seed ^= seed << 17; + seed as u8 + }) + .collect(); + let image = |space: &str| { + let mut dict = Dict::new(); + dict.set(b"Subtype".to_vec(), Object::name("Image")); + dict.set(b"Width".to_vec(), Object::Int(256)); + dict.set(b"Height".to_vec(), Object::Int(256)); + dict.set(b"BitsPerComponent".to_vec(), Object::Int(8)); + dict.set(b"ColorSpace".to_vec(), Object::name(space)); + Stream::flate(dict, &noise) + }; + let mut doc = Document::new_empty(); + let mask = image("DeviceGray"); + let cost = (mask.raw.len() + noise.len()) as u64 + 256 * 256; + let masked = doc.add(Object::Stream(mask)); + let mut with_mask = image("DeviceGray"); + with_mask.dict.set(b"SMask".to_vec(), Object::Ref(masked)); + let spent = |s: &Stream| { + let mut budget = ImageBudget::with_work(u64::MAX); + process(&doc, s, 720.0, &Settings::default().gray, 1, &mut budget).expect("resampled, and smaller"); + u64::MAX - budget.work_left() + }; + assert_eq!(spent(&with_mask), spent(&image("DeviceGray")) + cost); + } + + /// Decoded only to be resampled, what can't be averaged whatever it holds isn't decoded, so it + /// takes nothing from the images that can be, and isn't counted as refused past the allowance. + #[test] + fn a_jbig2_image_that_cant_be_averaged_spends_nothing() { + let image = |edit: &dyn Fn(&mut Dict)| { + let mut dict = Dict::new(); + dict.set(b"Subtype".to_vec(), Object::name("Image")); + dict.set(b"Width".to_vec(), Object::Int(16)); + dict.set(b"Height".to_vec(), Object::Int(2)); + dict.set(b"BitsPerComponent".to_vec(), Object::Int(1)); + dict.set(b"ColorSpace".to_vec(), Object::name("DeviceGray")); + dict.set(b"Filter".to_vec(), Object::name("JBIG2Decode")); + edit(&mut dict); + Stream::from_raw(dict, pdfcraft_filters::encode_jbig2_generic(&[0xF0; 4], 16, 2).unwrap()) + }; + let spent_at = |target_ppi: f64, s: &Stream, defaults: bool| { + let settings = MonoSettings { compression: MonoCompression::Retain, above_ppi: 100.0, target_ppi, ..MonoSettings::REDUCE }; + let mut budget = ImageBudget::with_work(u64::MAX); + let _ = mono(&Document::new_empty(), s, 720.0, defaults, &settings, &mut budget); + u64::MAX - budget.work_left() + }; + let spent = |s: &Stream, defaults: bool| spent_at(300.0, s, defaults); + let plain = image(&|_| {}); + assert_eq!(spent_at(720.0, &plain, false), 0, "already at the target"); + assert!(spent_at(719.0, &plain, false) > 0, "just above it"); + assert!(spent(&plain, false) > 0, "one that can be averaged is decoded"); + assert_eq!(spent(&plain, true), 0, "drawn where a device colour space is remapped"); + let width = |w: i64| image(&move |d| d.set(b"Width".to_vec(), Object::Int(w))); + let widest = i64::from(pdfcraft_filters::MAX_CCITT_COLUMNS); + assert!(spent(&width(widest), false) > 0, "the widest that can be averaged is decoded"); + assert_eq!(spent(&width(widest + 1), false), 0, "too wide to average"); + let tinted = image(&|d| d.set(b"ColorSpace".to_vec(), Object::Array(vec![Object::name("CalGray"), Object::Dict(Dict::new())]))); + assert_eq!(spent(&tinted, false), 0, "no way to tell which sample is dark"); + } + /// A JPEG larger than its dictionary says is refused from its header, before its pixels are decoded. #[test] fn a_jpeg_of_another_size_than_its_dictionary_is_not_decoded() { @@ -1367,9 +1674,9 @@ mod dimension_tests { Stream::from_raw(dict, data.clone()) }; DECODED_PIXELS.with(|c| c.set(0)); - assert!(pixels(&Document::new_empty(), &stream(10, 10), 1).is_none()); + assert!(pixels(&Document::new_empty(), &stream(10, 10), 1, &mut ImageBudget::with_work(u64::MAX)).is_none()); assert_eq!(DECODED_PIXELS.with(|c| c.get()), 0, "pixels decoded"); - assert_eq!(pixels(&Document::new_empty(), &stream(1000, 1000), 1).map(|p| p.len()), Some(1000 * 1000)); + assert_eq!(pixels(&Document::new_empty(), &stream(1000, 1000), 1, &mut ImageBudget::with_work(u64::MAX)).map(|p| p.len()), Some(1000 * 1000)); } /// Resampling goes through no more than one of the two sizes holds, whatever their proportions: diff --git a/crates/optimize/src/lib.rs b/crates/optimize/src/lib.rs index 4c8845c82d..e70aa5e71d 100644 --- a/crates/optimize/src/lib.rs +++ b/crates/optimize/src/lib.rs @@ -36,7 +36,7 @@ mod unused; pub use audit::{SpaceCategory, SpaceUse, audit_space}; -use pdfcraft_cos::{Dict, Document, MAX_PAGE_DECODED, ObjRef, Object, Stream, serialize}; +use pdfcraft_cos::{Dict, Document, ImageBudget, MAX_PAGE_DECODED, ObjRef, Object, Stream, serialize}; use pdfcraft_filters::{Filter, Params}; pub use images::effective_resolutions; @@ -279,6 +279,8 @@ pub struct Report { pub images: usize, pub images_resampled: usize, pub images_recompressed: usize, + /// Images left as they are: decoding them all would take more than one run may spend. + pub images_refused: usize, /// Encoded image bytes before and after (images that changed). pub image_bytes_before: usize, pub image_bytes_after: usize, @@ -329,10 +331,12 @@ pub fn optimize_with_progress(doc: &mut Document, settings: &Settings, progress: } let mut report = Report::default(); let pages = pdfcraft_annot::page_refs(doc).map_err(|_| OptimizeError::NoPages)?; + // Merging fragments, the image pass and the LZW pass read the same images, so they share it. + let mut budget = ImageBudget::new(doc); if settings.merge_fragments { - fragments::run(doc, &pages, &mut report, progress)?; + fragments::run(doc, &pages, &mut report, progress, &mut budget)?; } - images::run(doc, &pages, settings, &mut report, progress)?; + images::run(doc, &pages, settings, &mut report, progress, &mut budget)?; if !progress(Stage::CleanUp) { return Err(OptimizeError::Cancelled); } @@ -428,7 +432,11 @@ pub fn optimize_with_progress(doc: &mut Document, settings: &Settings, progress: let r = ObjRef { num, generation: doc.generation(num) }; let obj = doc.get(r); let Object::Stream(s) = &*obj else { continue }; - if let Some(replacement) = lzw_to_flate(s, MAX_LZW_DECODED) { + // Each can take a second or more, of a pass that has no other way to stop. + if s.filters().iter().any(|(f, _)| *f == Filter::Lzw) && !progress(Stage::CleanUp) { + return Err(OptimizeError::Cancelled); + } + if let Some(replacement) = lzw_to_flate(s, MAX_LZW_DECODED, &mut budget) { doc.set(r, Object::Stream(replacement)); report.lzw_streams += 1; } @@ -463,14 +471,17 @@ pub fn optimize_with_progress(doc: &mut Document, settings: &Settings, progress: /// Largest decoded LZW stream converted, as for a page's content: the data and its check are /// held together, so a few hundred kilobytes of hostile LZW can't ask for gigabytes. const MAX_LZW_DECODED: usize = MAX_PAGE_DECODED; +/// The steps of a run's allowance a decoded byte costs to store with Flate and read back: up to +/// 78 ns a byte to encode and 4 to check, at the 6 to 16 ns of a step. +const LZW_REWRITE_WORK: u64 = 8; /// `s` with its LZW compression replaced by Flate (Acrobat's "In streams that use LZW encoding, /// use Flate instead"). The filters up to the last LZW one are decoded, strictly and with its /// predictor; the result is Flate-encoded under the same predictor, without `EarlyChange`, and /// the filters after it keep their encoded bytes. A stream that doesn't decode cleanly, or -/// whose filters or parameters can't be read for certain, or that decodes past `max` bytes, is -/// left as it is. -fn lzw_to_flate(s: &Stream, max: usize) -> Option { +/// whose filters or parameters can't be read for certain, or that decodes past `max` bytes or +/// what `budget` has left, is left as it is. +fn lzw_to_flate(s: &Stream, max: usize, budget: &mut ImageBudget) -> Option { // An external file's data isn't in `raw`; cross-reference and object streams are rewritten // on save, so converting them would change nothing in the file. if s.dict.contains(b"F") || matches!(s.dict.name(b"Type"), Some(b"XRef" | b"ObjStm")) { @@ -513,7 +524,10 @@ fn lzw_to_flate(s: &Stream, max: usize) -> Option { if !parms.get(..=lzw)?.iter().all(direct) { return None; } - let data = pdfcraft_filters::decode(stages, &s.raw, max).ok()?; + let data = budget.decode_chain(stages, &s.raw, max).ok()?; + if !budget.spend((data.len() as u64).saturating_mul(LZW_REWRITE_WORK)) { + return None; + } let flate = Params { early_change: 1, ..params.clone() }; let raw = pdfcraft_filters::encode(&Filter::Flate, &flate, &data).ok()?; // The predictor's encoder must give back exactly what its decoder read (a short last row, @@ -597,8 +611,31 @@ mod tests { let mut dict = Dict::new(); dict.set(b"Filter".to_vec(), Object::name("LZWDecode")); let s = Stream::from_raw(dict, raw); - assert!(lzw_to_flate(&s, data.len() - 1).is_none()); - let converted = lzw_to_flate(&s, data.len()).unwrap(); + let mut budget = ImageBudget::with_work(u64::MAX); + assert!(lzw_to_flate(&s, data.len() - 1, &mut budget).is_none()); + let converted = lzw_to_flate(&s, data.len(), &mut budget).unwrap(); assert_eq!(converted.decoded_strict().unwrap(), data); } + + /// Rewriting a stream spends the run's allowance: reading it, decoding it, and storing and + /// checking what it decoded. One the allowance can't pay for stays LZW, and ends the rewriting. + #[test] + fn lzw_streams_spend_the_runs_allowance() { + let data = b"0 0 m 612 792 l S\n".repeat(64); + let raw = pdfcraft_filters::encode(&Filter::Lzw, &Params::default(), &data).unwrap(); + let mut dict = Dict::new(); + dict.set(b"Filter".to_vec(), Object::name("LZWDecode")); + let s = Stream::from_raw(dict, raw); + let cost = (s.raw.len() + data.len()) as u64 + data.len() as u64 * LZW_REWRITE_WORK; + let mut budget = ImageBudget::with_work(cost + 7); + assert!(lzw_to_flate(&s, data.len(), &mut budget).is_some()); + assert_eq!(budget.work_left(), 7); + let mut budget = ImageBudget::with_work(cost); + assert!(lzw_to_flate(&s, data.len(), &mut budget).is_some(), "exactly enough"); + assert_eq!(budget.work_left(), 0); + let mut budget = ImageBudget::with_work(cost - 1); + assert!(lzw_to_flate(&s, data.len(), &mut budget).is_none(), "a step short"); + assert_eq!(budget.work_left(), 0, "and the next stream isn't read"); + assert!(lzw_to_flate(&s, data.len(), &mut budget).is_none()); + } } diff --git a/crates/optimize/tests/optimize.rs b/crates/optimize/tests/optimize.rs index 5bfa74aa8b..ad710f3097 100644 --- a/crates/optimize/tests/optimize.rs +++ b/crates/optimize/tests/optimize.rs @@ -9,6 +9,12 @@ use pdfcraft_optimize::{ effective_resolutions, optimize, }; +/// What image `s` decodes to, its fax or JBIG2 data included, with no limit on the work: the +/// samples an operation would read through its `ImageBudget`. +fn decoded_image(doc: &Document, s: &Stream) -> Result, pdfcraft_cos::CosError> { + pdfcraft_cos::ImageBudget::with_work(u64::MAX).decode(doc, s, pdfcraft_cos::MAX_DECODED) +} + fn image(doc: &mut Document, w: u32, h: u32, n: usize, jpeg: bool, smask: Option) -> ObjRef { // A smooth gradient with a little texture (photo-like). let mut px = Vec::with_capacity((w * h) as usize * n); @@ -910,7 +916,7 @@ fn rgb_and_two_colour_indexed_black_and_white_images_become_one_bit() { (Some(1), Some(&b"CCITTFaxDecode"[..]), Some(&cs)), "{i:?}" ); - assert_eq!(doc.decoded_image(&s).unwrap(), text, "{i:?}"); + assert_eq!(decoded_image(&doc, &s).unwrap(), text, "{i:?}"); let decode = if i == rgb_inverted { Some(Object::Array(vec![1.into(), 0.into()])) } else { None }; assert_eq!(s.dict.get(b"Decode").cloned(), decode, "{i:?}"); } @@ -1066,7 +1072,7 @@ fn retain_keeps_a_group_3_halftone_as_it_is() { let fax = doc.add(Object::Stream(Stream::from_raw(d, g3.clone()))); // 7.68 pt for 64 samples is 600 ppi. page(&mut doc, &[("A", fax)], "q 7.68 0 0 7.68 100 600 cm /A Do Q"); - assert_eq!(doc.decoded_image(&stream(&doc, fax)).unwrap().len(), 64 * 8, "the fixture decodes"); + assert_eq!(decoded_image(&doc, &stream(&doc, fax)).unwrap().len(), 64 * 8, "the fixture decodes"); let r = optimize(&mut doc, &Settings { mono: RETAIN, ..Settings::default() }).unwrap(); assert_eq!((r.images_resampled, r.images_recompressed), (0, 0), "{r:?}"); assert_eq!(stream(&doc, fax).raw[..], g3[..]); @@ -1564,7 +1570,7 @@ fn ambiguous_monochrome_text_is_recompressed_without_lossy_reduction() { } assert_eq!(raw(&kept, hex_at_400), raw(&doc, hex_at_400), "and nothing else changes"); for i in [flate, fax, hex_fax] { - assert_eq!((size(&kept, i), kept.decoded_image(&stream(&kept, i)).unwrap()), ((1200, 480), text.clone()), "{i:?}"); + assert_eq!((size(&kept, i), decoded_image(&kept, &stream(&kept, i)).unwrap()), ((1200, 480), text.clone()), "{i:?}"); } let bits = [eight, rgb, rgb_inverted].map(|i| stream(&kept, i).dict.int(b"BitsPerComponent")); assert_eq!(bits, [Some(8); 3], "Retain leaves eight bits to the grey and colour settings"); @@ -1578,7 +1584,7 @@ fn ambiguous_monochrome_text_is_recompressed_without_lossy_reduction() { let s = stream(&doc, i); assert_eq!((size(&doc, i), s.dict.int(b"BitsPerComponent")), ((1200, 480), if i == mask { None } else { Some(1) })); assert!(matches!(s.filters().as_slice(), [(Filter::CcittFax | Filter::Flate, _)]), "{i:?}"); - assert_eq!(doc.decoded_image(&s).unwrap(), text.clone(), "{i:?}"); + assert_eq!(decoded_image(&doc, &s).unwrap(), text.clone(), "{i:?}"); } assert_eq!(stream(&doc, mask).dict.get(b"Decode"), Some(&decode), "the decode array stays"); // Grey now, with grey's decode pair, which makes 1 black: its ties are black too. @@ -1588,12 +1594,12 @@ fn ambiguous_monochrome_text_is_recompressed_without_lossy_reduction() { (size(&doc, rgb_inverted), s.dict.get(b"ColorSpace"), s.dict.get(b"Decode")), ((1200, 480), Some(&Object::name("DeviceGray")), Some(&inverting)) ); - assert_eq!(doc.decoded_image(&s).unwrap(), text.iter().map(|b| !b).collect::>(), "the same picture, ties black"); + assert_eq!(decoded_image(&doc, &s).unwrap(), text.iter().map(|b| !b).collect::>(), "the same picture, ties black"); for i in [at_400, soft, hex_at_400] { assert_eq!((size(&doc, i), stream(&doc, i).dict.name(b"Filter")), ((1200, 480), Some(&b"CCITTFaxDecode"[..])), "{i:?}"); } assert!(raw(&doc, hex_at_400).len() < hex_len, "the ASCIIHexDecode is dropped"); - assert_eq!(doc.decoded_image(&stream(&doc, hex_at_400)).unwrap(), text, "and the picture kept"); + assert_eq!(decoded_image(&doc, &stream(&doc, hex_at_400)).unwrap(), text, "and the picture kept"); assert_eq!([fax_at_400].map(|r| raw(&doc, r)), untouched); let after = render(&doc); assert_eq!(after, before, "conservative retention preserves the rendered page exactly"); @@ -1681,7 +1687,7 @@ fn a_fax_image_behind_a_decompression_bomb_is_left_alone() { let r = optimize(&mut doc, &Settings::default()).unwrap(); if padding == 0 { assert_eq!(r.images_resampled, 0, "ambiguous local tones are retained: {r:?}"); - assert_eq!(doc.decoded_image(&stream(&doc, img)).unwrap(), bilevel(w, h, false)); + assert_eq!(decoded_image(&doc, &stream(&doc, img)).unwrap(), bilevel(w, h, false)); } else { assert_eq!((r.images_resampled, r.images_recompressed), (0, 0), "{r:?}"); assert_eq!(stream(&doc, img).raw, before); @@ -1776,7 +1782,7 @@ fn monochrome_images_keep_what_they_should() { assert_eq!([alone, deep].map(|r| raw(&doc, r)), before, "a Group 4 halftone alone, and sixteen-bit grey"); assert_eq!(filters(&doc, wrapped), 1, "a wrapped Group 4 halftone is stored again alone by default"); assert!(matches!(stream(&doc, scan).filters().as_slice(), [(Filter::CcittFax | Filter::Flate, _)]), "the scan: Group 4 or Flate"); - assert_eq!(doc.decoded_image(&stream(&doc, scan)).unwrap(), ragged, "the scan preserves every sample"); + assert_eq!(decoded_image(&doc, &stream(&doc, scan)).unwrap(), ragged, "the scan preserves every sample"); assert_eq!((stream(&doc, fax).dict.name(b"Filter"), filters(&doc, fax)), (Some(&b"CCITTFaxDecode"[..]), 1), "the busy fax image"); let (mut doc, [_, wrapped, scan, _, _]) = build(); @@ -1785,7 +1791,7 @@ fn monochrome_images_keep_what_they_should() { assert_eq!(raw(&doc, wrapped), before, "Retain: a wrapped Group 4 halftone stays as it is"); let s = stream(&doc, scan); assert_eq!((s.dict.int(b"Width"), s.dict.name(b"Filter")), (Some(1200), Some(&b"FlateDecode"[..])), "Retain: {r:?}"); - assert_eq!(doc.decoded_image(&s).unwrap(), ragged, "Retain preserves every sample"); + assert_eq!(decoded_image(&doc, &s).unwrap(), ragged, "Retain preserves every sample"); } /// `rows` coded as CCITT Group 3, one-dimensional (`/K 0`): each row its runs in turn, white first, @@ -1853,7 +1859,12 @@ fn group_3_fax_images_become_group_4() { let g3 = group_3(&runs, k > 0, on_bytes); let (end_of_line, encoded_byte_align) = (k > 0 && on_bytes.is_none(), on_bytes.is_some()); let p = pdfcraft_filters::CcittParams { k, columns: w.into(), end_of_line, encoded_byte_align, ..Default::default() }; - assert_eq!(pdfcraft_filters::decode_ccitt(&g3, &p, h).unwrap(), bits, "/K {k}, on bytes {on_bytes:?}: the Group 3 data is the picture"); + let mut work = u64::MAX; + assert_eq!( + pdfcraft_filters::decode_ccitt_within(&g3, &p, h, &mut work).unwrap(), + bits, + "/K {k}, on bytes {on_bytes:?}: the Group 3 data is the picture" + ); let mut doc = Document::new_empty(); let mut d = Dict::new(); @@ -1886,7 +1897,7 @@ fn group_3_fax_images_become_group_4() { let s = stream(&doc, fax); assert_eq!(doc.fax_params(&s).map(|p| p.k), Some(-1), "/K {k}, on bytes {on_bytes:?}: Group 4"); assert!(s.raw.len() < g3.len(), "{} bytes, from {}", s.raw.len(), g3.len()); - assert_eq!(doc.decoded_image(&s).unwrap(), bits, "/K {k}, on bytes {on_bytes:?}: the same picture"); + assert_eq!(decoded_image(&doc, &s).unwrap(), bits, "/K {k}, on bytes {on_bytes:?}: the same picture"); assert!(render(&doc) == render(&control), "/K {k}, on bytes {on_bytes:?}: the page looks as the picture does"); } } @@ -2102,14 +2113,14 @@ fn jbig2_scans_are_averaged_and_stored_again() { let im = mono_image(&mut doc, w, h, &squares, None, &grey); page(&mut doc, &[("Im", im)], "q 144 0 0 57.6 20 600 cm /Im Do Q"); assert_eq!(optimize(&mut doc, &settings).unwrap().images_resampled, 1, "Flate, {compression:?}"); - let averaged = doc.decoded_image(&stream(&doc, im)).unwrap(); + let averaged = decoded_image(&doc, &stream(&doc, im)).unwrap(); for (filters, globals) in [(&["JBIG2Decode"][..], false), (&["ASCIIHexDecode", "JBIG2Decode"][..], false), (&["JBIG2Decode"][..], true)] { let (mut doc, im) = jbig2_page(&coded, filters, globals, (w, h), at_600); let r = optimize(&mut doc, &settings).unwrap(); let s = stream(&doc, im); let what = format!("{filters:?}, globals {globals}, {compression:?}: {r:?}"); assert_eq!((r.images_resampled, s.dict.int(b"Width"), s.dict.int(b"Height")), (1, Some(600), Some(240)), "{what}"); - assert_eq!(doc.decoded_image(&s).unwrap(), averaged, "{what}"); + assert_eq!(decoded_image(&doc, &s).unwrap(), averaged, "{what}"); assert!(!s.dict.contains(b"DecodeParms") || s.dict.name(b"Filter") == Some(&b"CCITTFaxDecode"[..]), "{what}"); let filter = s.dict.name(b"Filter").map(<[u8]>::to_vec); // The smallest of what each compression may store; under Retain, JBIG2 again. @@ -2140,13 +2151,13 @@ fn jbig2_scans_are_averaged_and_stored_again() { let s = stream(&doc, im); assert_eq!((r.images_resampled, r.images_recompressed, s.dict.name(b"Filter")), (0, 1, Some(&b"JBIG2Decode"[..])), "{r:?}"); assert!(s.raw.len() * 2 < generic.len(), "symbols {} bytes, the generic region {}", s.raw.len(), generic.len()); - assert_eq!(doc.decoded_image(&s).unwrap(), text); + assert_eq!(decoded_image(&doc, &s).unwrap(), text); // Behind ASCIIHex it is stored again alone, being smaller so. let (mut doc, im) = jbig2_page(&generic, &["ASCIIHexDecode", "JBIG2Decode"], false, (tw, th), at_300); optimize(&mut doc, &jbig2_asked).unwrap(); let s = stream(&doc, im); assert_eq!((s.filters().len(), s.dict.name(b"Filter")), (1, Some(&b"JBIG2Decode"[..]))); - assert_eq!(doc.decoded_image(&s).unwrap(), text); + assert_eq!(decoded_image(&doc, &s).unwrap(), text); // So it is as Group 4 when that is smaller: here the hex digits are spaced out, as ASCIIHex // allows, so that the stream is many times the code. let (mut doc, im) = jbig2_page(&generic, &["ASCIIHexDecode", "JBIG2Decode"], false, (tw, th), at_300); @@ -2156,7 +2167,7 @@ fn jbig2_scans_are_averaged_and_stored_again() { optimize(&mut doc, &Settings::default()).unwrap(); let s = stream(&doc, im); assert_eq!((s.filters().len(), s.dict.name(b"Filter")), (1, Some(&b"CCITTFaxDecode"[..])), "Group 4 alone"); - assert_eq!(doc.decoded_image(&s).unwrap(), text); + assert_eq!(decoded_image(&doc, &s).unwrap(), text); // A JBIG2 page taller than the image: the renderer draws the whole page into it, so it isn't // read, and stays as it is. @@ -3399,6 +3410,42 @@ fn lzw_streams_become_flate_and_decode_to_the_same_bytes() { assert!(!stream(&doc, c_late).dict.contains(b"DecodeParms"), "nothing left to say for the content stream"); } +/// A stream can take a second or more to store again, so a cancel lands between any two of them, +/// and nothing runs after it. +#[test] +fn a_cancel_lands_during_the_lzw_pass() { + use pdfcraft_optimize::{OptimizeError, Stage, optimize_with_progress}; + let build = |streams: usize| { + let mut doc = Document::new_empty(); + let mut d = Dict::new(); + d.set(b"Filter".to_vec(), Object::name("LZWDecode")); + for _ in 0..streams { + doc.add(Object::Stream(Stream::from_raw(d.clone(), lzw(&lzw_ops(), &Params::default())))); + } + page(&mut doc, &[], "0 0 1 1 re f"); + doc + }; + let asked = |streams: usize| { + let mut asked = 0; + optimize_with_progress(&mut build(streams), &Settings::default(), &mut |s| { + asked += usize::from(s == Stage::CleanUp); + true + }) + .unwrap(); + asked + }; + let none = asked(0); + assert_eq!(asked(3), none + 3, "once a stream"); + let mut left = none + 1; + let mut doc = build(3); + let r = optimize_with_progress(&mut doc, &Settings::default(), &mut |s| { + left -= usize::from(s == Stage::CleanUp); + left > 0 + }); + assert!(matches!(r, Err(OptimizeError::Cancelled)), "{r:?}"); + assert_eq!(left, 0, "nothing runs after it"); +} + #[test] fn a_page_drawn_from_lzw_streams_renders_the_same_after_conversion() { let png = Params { predictor: 12, colors: 3, columns: 64, early_change: 0, ..Params::default() }; @@ -3534,7 +3581,7 @@ fn indexed_thin_rules_survive_averaging_for_both_palette_orders_and_decodes() { optimize(&mut gray, &Settings::default()).unwrap(); let gray_after = render(&Document::open(Arc::new(write_full(&gray, &SaveOptions::default()).unwrap())).unwrap()); let gray_stream = stream(&gray, gray_image); - let gray_samples = gray.decoded_image(&gray_stream).unwrap(); + let gray_samples = decoded_image(&gray, &gray_stream).unwrap(); assert_eq!((gray_stream.dict.int(b"Width"), gray_stream.dict.int(b"Height")), (Some(600), Some(240))); assert!(gray_samples.iter().any(|b| *b != 0xFF), "the DeviceGray thin rule survives"); for white_first in [false, true] { @@ -3567,7 +3614,7 @@ fn indexed_thin_rules_survive_averaging_for_both_palette_orders_and_decodes() { assert_eq!((s.dict.int(b"Width"), s.dict.int(b"Height")), (Some(600), Some(240)), "white-first={white_first}, inverted={inverted}"); // The rows are 600 samples, whole bytes: flipping each byte flips each sample. let expected: Vec = gray_samples.iter().map(|b| if white_first != inverted { !b } else { *b }).collect(); - assert_eq!(doc.decoded_image(&s).unwrap(), expected, "white-first={white_first}, inverted={inverted}: the rule is dark"); + assert_eq!(decoded_image(&doc, &s).unwrap(), expected, "white-first={white_first}, inverted={inverted}: the rule is dark"); let saved = Document::open(Arc::new(write_full(&doc, &SaveOptions::default()).unwrap())).unwrap(); assert!(render(&saved) == gray_after, "palette white-first={white_first}, inverted={inverted}"); } @@ -3628,7 +3675,7 @@ fn an_indexed_palette_is_read_by_the_luma_of_its_colours() { page(&mut doc, &[("Im", image)], "q 144 0 0 57.6 20 600 cm /Im Do Q"); optimize(&mut doc, &Settings::default()).unwrap(); let s = stream(&doc, image); - (s.dict.int(b"Width"), doc.decoded_image(&s).unwrap()) + (s.dict.int(b"Width"), decoded_image(&doc, &s).unwrap()) }; let (width, samples) = optimized("Indexed"); assert_eq!(width, Some(600)); @@ -3736,8 +3783,107 @@ fn mixed_text_and_small_halftone_regions_keep_their_tones_with_wide_white_margin optimize(&mut doc, &Settings::default()).unwrap(); let s = stream(&doc, image); assert_eq!((s.dict.int(b"Width"), s.dict.int(b"Height")), (Some(w.into()), Some(h.into()))); - assert_eq!(doc.decoded_image(&s).unwrap(), data, "screened samples survive, not a solid patch"); + assert_eq!(decoded_image(&doc, &s).unwrap(), data, "screened samples survive, not a solid patch"); let saved = Document::open(Arc::new(write_full(&doc, &SaveOptions::default()).unwrap())).unwrap(); assert_eq!(render(&saved), before, "local halftone {side}x{side}"); } } + +/// A one-bit stencil of `w` × `h`, solid but for a hole in its middle. +fn stencil(doc: &mut Document, w: u32, h: u32) -> ObjRef { + let row = (w as usize).div_ceil(8); + let mut bits = vec![0u8; row * h as usize]; + for y in (h as usize / 3)..(2 * h as usize / 3) { + for x in (w as usize / 3)..(2 * w as usize / 3) { + bits[y * row + x / 8] |= 0x80 >> (x % 8); + } + } + let mut d = Dict::new(); + d.set(b"Type".to_vec(), Object::name("XObject")); + d.set(b"Subtype".to_vec(), Object::name("Image")); + d.set(b"ImageMask".to_vec(), Object::Bool(true)); + d.set(b"Width".to_vec(), Object::Int(i64::from(w))); + d.set(b"Height".to_vec(), Object::Int(i64::from(h))); + d.set(b"BitsPerComponent".to_vec(), Object::Int(1)); + doc.add(Object::Stream(Stream::flate(d, &bits))) +} + +/// A picture with a stencil mask is made smaller like any other: the mask has a resolution of its +/// own, so it stays exactly as it was and the hole it cuts stays where it was. +#[test] +fn a_picture_with_a_stencil_mask_is_downsampled_under_its_mask() { + let mut doc = Document::new_empty(); + let mask = stencil(&mut doc, 1200, 1200); + let img = image(&mut doc, 1200, 1200, 3, true, None); + let mut s = stream(&doc, img); + s.dict.set(b"Mask".to_vec(), Object::Ref(mask)); + doc.set(img, Object::Stream(s)); + let mask_before = stream(&doc, mask); + // 1200 pixels over two inches: 600 ppi. + page(&mut doc, &[("Im0", img)], "0 0 1 rg 0 0 612 792 re f q 144 0 0 144 100 100 cm /Im0 Do Q"); + let before = render(&doc); + let report = optimize(&mut doc, &Settings::default()).unwrap(); + assert_eq!(report.images_resampled, 1, "{report:?}"); + let after = stream(&doc, img); + assert_eq!(after.dict.int(b"Width"), Some(300), "150 ppi"); + assert_eq!(after.dict.reference(b"Mask"), Some(mask), "the mask stays on it"); + assert_eq!(stream(&doc, mask), mask_before, "and doesn't change"); + let rendered = render(&doc); + assert_eq!(rendered.len(), before.len()); + let changed = before.iter().zip(&rendered).filter(|(a, b)| a.abs_diff(**b) > 96).count(); + assert!(changed * 200 < before.len(), "the masked picture looks the same: {changed} of {} samples far off", before.len()); + // The hole, the middle third of the picture on the 612 by 792 page, still shows what's behind it. + // Its first pixel all round is left out: the coarser picture blends into that a little. + for y in 597..643 { + for x in 149..195 { + let i = (y * 612 + x) * 4; + assert_eq!(rendered[i..i + 4], before[i..i + 4], "hole pixel ({x}, {y})"); + } + } +} + +/// A colour-key mask names sample values: resampling or JPEG would make holes where there were none +/// and fill those there were, so the picture stays as it is, however the array is written. A mask +/// that can't be read as a stencil is no reason to change the picture either. +#[test] +fn a_picture_whose_mask_is_not_a_stencil_is_left_alone() { + type Mask = fn(&mut Document) -> Object; + fn key() -> Object { + Object::Array([250, 255, 250, 255, 250, 255].map(Object::Int).to_vec()) + } + fn not_a_stencil(doc: &mut Document, change: fn(&mut Dict)) -> Object { + let mask = stencil(doc, 1200, 1200); + let mut s = stream(doc, mask); + change(&mut s.dict); + doc.set(mask, Object::Stream(s)); + Object::Ref(mask) + } + let masks: [(&str, Mask); 5] = [ + ("direct array", |_| key()), + ("array by reference", |doc| Object::Ref(doc.add(key()))), + ("nothing there", |doc| Object::Ref(doc.add(Object::Null))), + ("an image that says it isn't a stencil", |doc| { + not_a_stencil(doc, |d| { + d.set(b"ImageMask".to_vec(), Object::Bool(false)); + }) + }), + ("an image that doesn't say it is one", |doc| { + not_a_stencil(doc, |d| { + d.remove(b"ImageMask"); + }) + }), + ]; + for (what, mask) in masks { + let mut doc = Document::new_empty(); + let img = image(&mut doc, 1200, 1200, 3, true, None); + let mut s = stream(&doc, img); + let mask = mask(&mut doc); + s.dict.set(b"Mask".to_vec(), mask); + doc.set(img, Object::Stream(s)); + let before = stream(&doc, img); + page(&mut doc, &[("Im0", img)], "q 144 0 0 144 100 100 cm /Im0 Do Q"); + let report = optimize(&mut doc, &Settings::default()).unwrap(); + assert_eq!(report.images_resampled + report.images_recompressed, 0, "{what}: {report:?}"); + assert_eq!(stream(&doc, img), before, "{what}"); + } +} diff --git a/crates/print/README.md b/crates/print/README.md index 1379be2b42..5db83312ca 100644 --- a/crates/print/README.md +++ b/crates/print/README.md @@ -46,7 +46,9 @@ Headless `doc_print` defaults are unchanged. `spool` delegates discovery, driver options, preferences and submission to [`craft-print`](https://github.com/storytold/craft-libs/tree/main/crates/print). PdfCraft retains page selection, imposition, annotations and print-permission checks. -CUPS jobs stream through stdin with `fit-to-page=false`. Windows renders sheets through +CUPS jobs stream through stdin with `fit-to-page=false`; on macOS they also carry the job +name and owner (`com.apple.print.JobInfo.PMJobName`, `PMJobOwner`) as the system print dialog +sends them, which some vendors' filters need (#5743). Windows renders sheets through `Windows.Data.Pdf` and spools them at their physical PDF size with per-page paper and orientation, zero added margins and hardware-edge clipping. Long-edge and short-edge duplex use the corresponding Windows binding edges. Random, exclusively created Windows job files diff --git a/crates/print/src/spool.rs b/crates/print/src/spool.rs index 5ce3d9736b..a83da3ed26 100644 --- a/crates/print/src/spool.rs +++ b/crates/print/src/spool.rs @@ -143,14 +143,62 @@ pub(crate) fn printer_options_via_within( options } +/// The keys the macOS print dialog names a job's title and owner under. +#[cfg_attr(not(target_os = "macos"), allow(dead_code))] +const JOB_NAME_KEY: &str = "com.apple.print.JobInfo.PMJobName"; +#[cfg_attr(not(target_os = "macos"), allow(dead_code))] +const JOB_OWNER_KEY: &str = "com.apple.print.JobInfo.PMJobOwner"; + +/// `text` as a job option's value: `lp_args` passes on only printable ASCII, up to 64 bytes, +/// without `/ : = "`, and CUPS would take `'` and `\` as quoting and `{` as the start of a +/// collection, so all of these become `_`. Text with nothing left of it, such as a title in +/// another script, takes `fallback`: the job must still name something. So does a bare `true` or +/// `false`, which CUPS would send as a boolean, not the name a filter reads. +#[cfg_attr(not(target_os = "macos"), allow(dead_code))] +fn job_option_value(text: &str, fallback: &str) -> String { + let kept = |c: char| c.is_ascii_graphic() && !matches!(c, '/' | ':' | '=' | '"' | '\'' | '\\' | '{'); + let value: String = text.chars().take(64).map(|c| if kept(c) { c } else { '_' }).collect(); + if !text.chars().any(kept) || value.eq_ignore_ascii_case("true") || value.eq_ignore_ascii_case("false") { + return fallback.to_string(); + } + value +} + +/// `job` naming its title and `owner` as a job from the macOS print dialog does. `lp` sends +/// neither, and a driver's filter can depend on them: Kyocera's crashes without them, so nothing +/// prints, while the same file sent with both does (#5743). A value the caller set stands: the +/// last of a repeated option wins in CUPS, which compares their names without case. +#[cfg_attr(not(target_os = "macos"), allow(dead_code))] +pub(crate) fn with_job_info(job: &Job, owner: Option<&str>) -> Job { + let mut named = job.clone(); + for (key, value) in [(JOB_NAME_KEY, job.title.as_str()), (JOB_OWNER_KEY, owner.unwrap_or_default())] { + if !job.options.iter().any(|(k, _)| k.eq_ignore_ascii_case(key)) { + named.options.push((key.to_string(), job_option_value(value, "PdfCraft"))); + } + } + named +} + +/// The job as the system spooler takes it. +fn spooled(job: &Job) -> Job { + #[cfg(target_os = "macos")] + { + with_job_info(job, std::env::var("USER").ok().as_deref()) + } + #[cfg(not(target_os = "macos"))] + { + job.clone() + } +} + pub fn submit(pdf: &[u8], job: &Job) -> Result { - craft_print::submit(pdf, job).map_err(|e| crate::PrintError::Spool(e.to_string())) + craft_print::submit(pdf, &spooled(job)).map_err(|e| crate::PrintError::Spool(e.to_string())) } /// [`submit`], told `(sent, sheets)` as each sheet reaches the spooler (Windows; CUPS takes the /// whole PDF at once and reports nothing). pub fn submit_with_progress(pdf: &[u8], job: &Job, progress: &mut dyn FnMut(usize, usize)) -> Result { - craft_print::submit_with_progress(pdf, job, progress).map_err(|e| crate::PrintError::Spool(e.to_string())) + craft_print::submit_with_progress(pdf, &spooled(job), progress).map_err(|e| crate::PrintError::Spool(e.to_string())) } pub fn open_printer_preferences(printer: &str) -> Result<(), crate::PrintError> { diff --git a/crates/print/src/tests.rs b/crates/print/src/tests.rs index 885756e8c6..642af0b8c9 100644 --- a/crates/print/src/tests.rs +++ b/crates/print/src/tests.rs @@ -305,6 +305,107 @@ fn spooler_arguments_and_printer_list() { assert_eq!(lp_args(&Job::default())[0], "-n", "no -d: the default printer"); } +/// The job name and owner, read from the `lp` arguments, since `lp_args` drops a value it can't +/// pass on: the job must reach the spooler named, whatever its title holds (#5743). +#[test] +fn a_job_names_its_title_and_owner_to_the_spooler() { + let args_for = |title: &str, owner: Option<&str>| { + let job = Job { title: title.into(), ..Job::default() }; + lp_args(&spool::with_job_info(&job, owner)) + }; + let option = |args: &[String], key: &str| { + let prefix = format!("com.apple.print.JobInfo.{key}="); + args.iter().find_map(|a| a.strip_prefix(prefix.as_str()).map(str::to_string)) + }; + let args = args_for("memo.pdf", Some("sam")); + assert_eq!(option(&args, "PMJobName").as_deref(), Some("memo.pdf"), "{args:?}"); + assert_eq!(option(&args, "PMJobOwner").as_deref(), Some("sam"), "{args:?}"); + // The title keeps its place as `-t`, in full. + assert!(args_for("Q3 report: a/b=\"c\".pdf", None).windows(2).any(|w| w[0] == "-t" && w[1] == "Q3 report: a/b=\"c\".pdf")); + + let named = args_for("Q3 report: a/b=\"c\".pdf", None); + assert_eq!(option(&named, "PMJobName").as_deref(), Some("Q3_report__a_b__c_.pdf"), "what lp can't be given becomes _"); + assert_eq!(option(&named, "PMJobOwner").as_deref(), Some("PdfCraft"), "no owner known: the filter still gets one"); + + for nothing_left in ["", " ", "見積書", "/:=\""] { + assert_eq!(option(&args_for(nothing_left, Some("")), "PMJobName").as_deref(), Some("PdfCraft"), "{nothing_left:?}"); + } + assert_eq!(option(&args_for("見積書2.pdf", None), "PMJobName").as_deref(), Some("___2.pdf"), "a part of it is kept"); + let long = option(&args_for(&format!("a{}", "é".repeat(200)), None), "PMJobName").unwrap_or_default(); + assert_eq!(long.len(), 64, "cut to what lp_args takes, on a multi-byte title too: {long}"); + + // What CUPS would quote away or send as another type, as this Mac's libcups does. + for (title, name) in [("it's.pdf", "it_s.pdf"), (r"a\b.pdf", "a_b.pdf"), ("{draft}.pdf", "_draft}.pdf"), ("a{b", "a_b")] { + assert_eq!(option(&args_for(title, None), "PMJobName").as_deref(), Some(name), "{title:?}"); + } + for boolean in ["true", "TRUE", "false", "False"] { + assert_eq!(option(&args_for(boolean, Some(boolean)), "PMJobName").as_deref(), Some("PdfCraft"), "{boolean:?}"); + assert_eq!(option(&args_for(boolean, Some(boolean)), "PMJobOwner").as_deref(), Some("PdfCraft"), "{boolean:?}"); + } + assert_eq!(option(&args_for("true.pdf", None), "PMJobName").as_deref(), Some("true.pdf"), "only the bare word is a boolean"); +} + +/// A job's own values stand: CUPS keeps the last of a repeated option, ignoring the case of its +/// name, so a default after them would replace what a `doc_print` caller set (#5743). +#[test] +fn a_job_keeps_the_title_and_owner_it_already_sets() { + let values = |job: &Job, key: &str| -> Vec { + let found = spool::with_job_info(job, Some("sam")).options; + found.into_iter().filter(|(k, _)| k.eq_ignore_ascii_case(key)).map(|(_, v)| v).collect() + }; + let (name, owner) = ("com.apple.print.JobInfo.PMJobName", "com.apple.print.JobInfo.PMJobOwner"); + let job = Job { title: "memo.pdf".into(), options: vec![(name.to_string(), "Mine".to_string())], ..Job::default() }; + assert_eq!(values(&job, name), ["Mine"]); + assert_eq!(values(&job, owner), ["sam"], "the one it left out still gets its default"); + + let job = Job { title: "memo.pdf".into(), options: vec![(owner.to_ascii_uppercase(), "Theirs".to_string())], ..Job::default() }; + assert_eq!(values(&job, owner), ["Theirs"]); + assert_eq!(values(&job, name), ["memo.pdf"]); +} + +/// Both ways to submit reach `lp` with the job named. `lp` comes from `PATH`, which only a child +/// process can change here, so the test runs itself again with a stand-in that records its +/// arguments; no job reaches a real spooler (#5743). +#[cfg(target_os = "macos")] +#[test] +fn a_submitted_job_reaches_lp_named() { + const TEST: &str = "tests::a_submitted_job_reaches_lp_named"; + if let Ok(way) = std::env::var("PDFCRAFT_SUBMIT_TO_STAND_IN") { + let job = Job { title: "memo.pdf".into(), ..Job::default() }; + let sent = match way.as_str() { + "submit" => spool::submit(b"%PDF-1.7", &job), + _ => spool::submit_with_progress(b"%PDF-1.7", &job, &mut |_, _| {}), + }; + assert!(sent.is_ok(), "{sent:?}"); + return; + } + use std::os::unix::fs::PermissionsExt as _; + let dir = std::env::temp_dir().join(format!("pdfcraft-lp-stand-in-{}", std::process::id())); + std::fs::create_dir_all(&dir).expect("temp dir"); + let lp = dir.join("lp"); + let recorded = dir.join("args"); + let script = + format!("#!/bin/sh\nprintf '%s\\n' \"$@\" > '{}'\n/bin/cat > /dev/null\necho 'request id is stand-in-1 (1 file(s))'\n", recorded.display()); + std::fs::write(&lp, script).expect("stand-in"); + std::fs::set_permissions(&lp, std::fs::Permissions::from_mode(0o700)).expect("executable"); + for way in ["submit", "submit_with_progress"] { + let _ = std::fs::remove_file(&recorded); + let this = std::env::current_exe().expect("this test binary"); + let child = std::process::Command::new(this) + .args(["--exact", TEST, "--nocapture"]) + .env("PDFCRAFT_SUBMIT_TO_STAND_IN", way) + .env("PATH", &dir) + .env("USER", "sam") + .output() + .expect("run the test again"); + assert!(child.status.success(), "{way}: {}", String::from_utf8_lossy(&child.stdout)); + let args = std::fs::read_to_string(&recorded).expect("lp was run"); + assert!(args.lines().any(|a| a == "com.apple.print.JobInfo.PMJobName=memo.pdf"), "{way}: {args}"); + assert!(args.lines().any(|a| a == "com.apple.print.JobInfo.PMJobOwner=sam"), "{way}: {args}"); + } + let _ = std::fs::remove_dir_all(&dir); +} + #[test] fn lpstat_output_is_untranslated() { // A localized lpstat (here Polish) is unreadable to parse_lpstat... diff --git a/crates/redact/README.md b/crates/redact/README.md index 9c024d1b55..db9f46b8c9 100644 --- a/crates/redact/README.md +++ b/crates/redact/README.md @@ -37,6 +37,10 @@ clear_marks(&mut doc, None)?; // remove marks without app and a byte per row, plus 4 KiB (ASCIIHex text broken into lines under Flate is a little over twice; for a fax image's code, about a byte per pixel), are removed whole; cleared copies drop `/Alternates` so alternate pixels cannot survive; + A run that would decode more of its images than one redaction may (`pdfcraft_cos::ImageBudget`, + filters, decoders and pixels alike) is refused + and changes nothing: such an image can't be cleared, and removing it whole would take what no mark + covers with it. - **vectors**: covered paths are removed; partly covered paths and shadings are clipped so nothing paints inside the areas; - **form XObjects**: rewritten recursively into new objects (pages sharing the original keep it); diff --git a/crates/redact/src/image.rs b/crates/redact/src/image.rs index a96f4715e6..2e737e2baf 100644 --- a/crates/redact/src/image.rs +++ b/crates/redact/src/image.rs @@ -2,13 +2,13 @@ //! whose footprint intersects a region is set to zero (no ink for image masks), and the result is //! written as a new image, Flate, or for a one-bit image of one component Group 4, or JBIG2 when it //! was JBIG2, whichever is smallest; the original object is untouched (other pages may use it). -//! CCITT fax and JBIG2 images decode through `Document::decoded_image_within`, but for Group 3 on +//! CCITT fax and JBIG2 images decode through `ImageBudget::decode`, but for Group 3 on //! bytes, which PdfCraft's renderer may draw as other rows, and a JBIG2 page of other rows than the //! image's. Images whose codec PdfCraft can't decode (DCT, JPX), and those, return `None`, and the //! caller removes the whole image instead; that is fail-closed. use pdfcraft_content::{Matrix, overlaps}; -use pdfcraft_cos::{Dict, Document, Object, Stream}; +use pdfcraft_cos::{Dict, Document, ImageBudget, Object, Stream}; /// Most pixels an image may have to be cleared in place (larger ones are removed). const MAX_PIXELS: u64 = 64 << 20; @@ -39,11 +39,11 @@ fn components(doc: &Document, s: &Stream) -> Option { /// `Ok(Some(copy))` with the covered pixels cleared, `Ok(None)` when no pixel intersects, /// `Err(())` when the image can't be cleared (the caller removes it). #[allow(clippy::result_unit_err)] -pub(crate) fn clear(doc: &Document, s: &Stream, ctm: &Matrix, rects: &[[f64; 4]]) -> Result, ()> { - decode_and_clear(doc, s, ctm, rects).ok_or(()) +pub(crate) fn clear(doc: &Document, s: &Stream, ctm: &Matrix, rects: &[[f64; 4]], budget: &mut ImageBudget) -> Result, ()> { + decode_and_clear(doc, s, ctm, rects, budget).ok_or(()) } -fn decode_and_clear(doc: &Document, s: &Stream, ctm: &Matrix, rects: &[[f64; 4]]) -> Option> { +fn decode_and_clear(doc: &Document, s: &Stream, ctm: &Matrix, rects: &[[f64; 4]], budget: &mut ImageBudget) -> Option> { // Separate masks can retain the original image data. if s.dict.contains(b"SMask") || s.dict.contains(b"Mask") { return None; @@ -54,19 +54,25 @@ fn decode_and_clear(doc: &Document, s: &Stream, ctm: &Matrix, rects: &[[f64; 4]] b"FlateDecode" | b"Fl" | b"LZWDecode" | b"LZW" | b"ASCII85Decode" | b"A85" | b"ASCIIHexDecode" | b"AHx" | b"RunLengthDecode" | b"RL" ) }; - // A CCITT fax or JBIG2 image (its last filter) decodes through `Document::decoded_image_within`, + // A CCITT fax or JBIG2 image (its last filter) decodes through `ImageBudget::decode`, // after the filters before it, so a scan stored as Group 4 or JBIG2 is cleared like any other // image. let fax = |f: &Object| f.as_name().is_some_and(|n| matches!(n, b"CCITTFaxDecode" | b"CCF")); let jbig2 = |f: &Object| f.as_name() == Some(b"JBIG2Decode".as_slice()); let readable = |f: &Object| f.as_name().is_some_and(supported); + // `/Crypt` was undone when the object was loaded (ISO 32000-2 §7.4.10), and decoding leaves it + // out wherever it stands. + let crypt = |f: &Object| f.as_name() == Some(b"Crypt".as_slice()); let (ok, is_fax, is_jbig2) = match s.dict.get(b"Filter") { None => (true, false, false), - Some(f @ Object::Name(_)) => (readable(f) || fax(f) || jbig2(f), fax(f), jbig2(f)), - Some(Object::Array(a)) => match a.split_last() { - Some((last, before)) if fax(last) || jbig2(last) => (before.iter().all(readable), fax(last), jbig2(last)), - _ => (a.iter().all(readable), false, false), - }, + Some(f @ Object::Name(_)) => (readable(f) || crypt(f) || fax(f) || jbig2(f), fax(f), jbig2(f)), + Some(Object::Array(a)) => { + let chain: Vec<&Object> = a.iter().filter(|f| !crypt(f)).collect(); + match chain.split_last() { + Some((last, before)) if fax(last) || jbig2(last) => (before.iter().all(|f| readable(f)), fax(last), jbig2(last)), + _ => (chain.iter().all(|f| readable(f)), false, false), + } + } _ => (false, false, false), }; if !ok { @@ -112,7 +118,7 @@ fn decode_and_clear(doc: &Document, s: &Stream, ctm: &Matrix, rects: &[[f64; 4]] // alone would skip such a predictor, and the cleared bytes would then miss the covered pixels), // and refuses a JBIG2 page of another size than the image: the renderer draws the whole page // into the image, so the rows cleared wouldn't be the ones a mark covers on screen. - let mut data = doc.decoded_image_within(s, allowance).ok()?; + let mut data = budget.decode(doc, s, allowance).ok()?; if data.len() < bytes { return None; } @@ -205,12 +211,12 @@ fn stored_len(s: &Stream) -> usize { /// JBIG2 image `s` stored again without its `/JBIG2Globals`: decoded through them, as it is drawn, /// and written as the same samples, Flate, Group 4 or JBIG2 coded alone, whichever is smallest -/// (`smallest`), its other entries kept. `None` when it can't -/// be decoded for certain (too large, data that doesn't decode, a JBIG2 page of another size than -/// the image, or not a one-bit image of one component). Redaction does this to every image that +/// (`smallest`), its other entries kept. `None` when it can't be decoded for certain (too large, +/// past what is left of `budget`, data that doesn't decode, a JBIG2 page of another size than the +/// image, or not a one-bit image of one component). Redaction does this to every image that /// shares a redacted image's globals, since their symbol dictionary holds the shapes of marks drawn /// under the area too. -pub(crate) fn without_globals(doc: &Document, s: &Stream) -> Option { +pub(crate) fn without_globals(doc: &Document, s: &Stream, budget: &mut ImageBudget) -> Option { let (w, h) = (s.dict.int(b"Width")?, s.dict.int(b"Height")?); if w <= 0 || h <= 0 || (w as u64) * (h as u64) > MAX_PIXELS { return None; @@ -225,7 +231,7 @@ pub(crate) fn without_globals(doc: &Document, s: &Stream) -> Option { // As for `clear`: the filters before the JBIG2 decoder may give up to three bytes for each one // of the raster and a byte a row. let allowance = bytes.checked_add(h)?.checked_mul(3)?.checked_add(4096)?; - let mut data = doc.decoded_image_within(s, allowance).ok()?; + let mut data = budget.decode(doc, s, allowance).ok()?; if data.len() < bytes { return None; } diff --git a/crates/redact/src/interp.rs b/crates/redact/src/interp.rs index ac69c73acb..460085a320 100644 --- a/crates/redact/src/interp.rs +++ b/crates/redact/src/interp.rs @@ -21,7 +21,7 @@ use std::collections::{HashMap, HashSet}; use std::rc::Rc; use pdfcraft_content::{Matrix, Op, Pieces, contains, num, overlaps, serialize_ops, string}; -use pdfcraft_cos::{CosError, DecodeBudget, Dict, Document, MAX_PAGE_FORMS, ObjRef, Object, Stream}; +use pdfcraft_cos::{CosError, DecodeBudget, Dict, Document, ImageBudget, MAX_PAGE_FORMS, ObjRef, Object, Stream}; use crate::{RedactError, Report, image, page_streams, tags}; use pdfcraft_fonts::pdf::Metrics; @@ -105,6 +105,8 @@ pub(crate) struct Scope<'a> { pub rects: &'a [[f64; 4]], pub mode: Mode, pub report: &'a mut Report, + /// What the images it clears may spend, shared by all the pages of a run. + pub images: &'a mut ImageBudget, /// Sanitize: remove hidden text (invisible render modes, or wholly outside this page box). pub hidden_text: Option<[f64; 4]>, /// Sanitize: optional content groups that are off; content marked with them is removed. @@ -134,11 +136,12 @@ pub(crate) struct Scope<'a> { impl<'a> Scope<'a> { /// A scope whose form walk spends `budget`, what is left of the page's allowance after its /// content streams were decoded. - pub fn new(rects: &'a [[f64; 4]], mode: Mode, report: &'a mut Report, budget: DecodeBudget) -> Self { + pub fn new(rects: &'a [[f64; 4]], mode: Mode, report: &'a mut Report, budget: DecodeBudget, images: &'a mut ImageBudget) -> Self { Scope { rects, mode, report, + images, hidden_text: None, hidden_layers: HashSet::new(), layers_enabled: false, @@ -750,7 +753,7 @@ fn xobject( out.doomed.push(r); return Some(None); } - match image::clear(doc, s, &gs.ctm, scope.rects) { + match image::clear(doc, s, &gs.ctm, scope.rects, &mut *scope.images) { Ok(None) => None, Ok(Some(new)) => { let nr = doc.add(Object::Stream(new)); @@ -858,6 +861,11 @@ fn xobject( } let mut dict = s.dict.clone(); dict.remove(b"Length"); + if new_data.is_some() { + // As for page content streams: the source text of an added item (Edit ▸ Add + // content) would keep what the rewrite removed. + dict.remove(b"PCAdded"); + } let mut cleaned_res = res.clone(); // Install rewritten nested forms before finding live property names: a new form may // still inherit its caller's resources, and its new Do name must resolve here. diff --git a/crates/redact/src/lib.rs b/crates/redact/src/lib.rs index fad55c431f..41ac47357e 100644 --- a/crates/redact/src/lib.rs +++ b/crates/redact/src/lib.rs @@ -70,6 +70,10 @@ pub enum RedactError { /// could not be shown complete. #[error("the document's objects nest too deeply to remove hidden information completely; the operation was refused")] TooDeep, + /// Past what one redaction may decode an image can't be cleared, and removing it whole would + /// take what no mark covers with it, unreported. + #[error("the images under these marks are more than one redaction can decode, so nothing was changed; redact fewer pages at a time")] + ImagesPastAllowance, /// A JBIG2 image shares its `/JBIG2Globals` with a redacted one and can't be stored again /// without them, so the shapes they hold, those of marks under the area included, would stay. #[error( @@ -386,6 +390,12 @@ pub fn apply(doc: &mut Document, pages: Option<&[usize]>) -> Result) -> Result { + let images = pdfcraft_cos::ImageBudget::new(doc); + apply_within(doc, pages, images) +} + +/// [`apply_to`], its images decoded within `images`. +fn apply_within(doc: &mut Document, pages: Option<&[usize]>, images: pdfcraft_cos::ImageBudget) -> Result { let (all_marks, unreadable) = marks_checked(doc); // A mark with no readable area is not applied, and applying the others would look complete: // refuse before anything changes. Only the pages being applied count. @@ -428,6 +438,7 @@ fn apply_to(doc: &mut Document, pages: Option<&[usize]>) -> Result) -> Result 0 { + return Err(RedactError::ImagesPastAllowance); + } + let Applying { mut report, doomed_fields, doomed_xobjects, retired_properties, mut removed_everywhere, mut images, .. } = applying; // 2b. Replies and pop-ups of a removed annotation can be listed on another page than their // parent: their `/IRT` or `/Parent` would keep the removed comment reachable. @@ -518,7 +532,7 @@ fn apply_to(doc: &mut Document, pages: Option<&[usize]>) -> Result) -> Result 0 { @@ -554,8 +570,10 @@ const MAX_JBIG2_WALK: usize = 100_000; /// and stored again in place without them, as a cleared copy is, and a full save then leaves them /// out. An image that can't be stored again refuses the redaction (nothing changes, as `apply` /// works on a copy), but for a removed or replaced one, which is either unlinked or still drawn -/// whole on another page. Returns how many images that weren't removed or replaced were stored again. -fn restore_shared_jbig2(doc: &mut Document, doomed: &[ObjRef]) -> Result { +/// whole on another page. They are decoded within what is left of the run's allowance (`images`); +/// past it the redaction is refused as one clearing too many images is. Returns how many images +/// that weren't removed or replaced were stored again. +fn restore_shared_jbig2(doc: &mut Document, doomed: &[ObjRef], images: &mut pdfcraft_cos::ImageBudget) -> Result { let mut globals = HashSet::new(); let mut seen = HashSet::new(); let mut stack: Vec = doomed.to_vec(); @@ -587,19 +605,24 @@ fn restore_shared_jbig2(doc: &mut Document, doomed: &[ObjRef]) -> Result = doomed.iter().copied().collect(); - let (mut restored, mut stuck) = (0, 0); + let (mut restored, mut stuck, mut past_allowance) = (0, 0, false); for r in sharing { let object = doc.get(r); let Object::Stream(s) = &*object else { continue }; - match image::without_globals(doc, s) { + let refused = images.refused(); + match image::without_globals(doc, s, images) { Some(new) => { doc.set(r, Object::Stream(new)); restored += usize::from(!doomed.contains(&r)); } None if doomed.contains(&r) => {} + None if images.refused() > refused => past_allowance = true, None => stuck += 1, } } + if past_allowance { + return Err(RedactError::ImagesPastAllowance); + } if stuck > 0 { return Err(RedactError::SharedJbig2Globals(stuck)); } @@ -615,6 +638,8 @@ struct Applying { retired_properties: Vec, widget_owner: Vec<(ObjRef, ObjRef)>, removed_everywhere: HashSet, + /// What clearing images may spend, across the run's pages. + images: pdfcraft_cos::ImageBudget, } /// Step 1 for one page: rewrites its content so nothing readable stays under a mark, and cleans the tags it no longer shows. @@ -625,13 +650,13 @@ fn redact_page_content( page: &pdfcraft_model::Page, rects: &[[f64; 4]], ) -> Result<(), RedactError> { - let Applying { report, doomed_xobjects, retired_properties, .. } = applying; + let Applying { report, doomed_xobjects, retired_properties, images, .. } = applying; // 1. Content. let mut budget = pdfcraft_cos::DecodeBudget::page(); let (list, data) = page_streams_within(doc, &page.dict, pi, &mut budget)?; let resources = page.dict.get(b"Resources").and_then(|r| doc.resolve(r).as_dict().cloned()).unwrap_or_default(); let out = { - let mut scope = Scope::new(rects, Mode::Apply, report, budget); + let mut scope = Scope::new(rects, Mode::Apply, report, budget, images); process(doc, &mut scope, &data, &resources, pdfcraft_content::Matrix::IDENTITY) }; // Fail closed: the interpreter lays vertical-writing text out horizontally, so it cannot diff --git a/crates/redact/src/sanitize.rs b/crates/redact/src/sanitize.rs index 98703dfbf2..6fd4354300 100644 --- a/crates/redact/src/sanitize.rs +++ b/crates/redact/src/sanitize.rs @@ -369,7 +369,8 @@ fn content_pass(doc: &mut Document, text: bool, layers: bool, write: bool) -> Re let resources = page.dict.get(b"Resources").and_then(|r| doc.resolve(r).as_dict().cloned()).unwrap_or_default(); let mut report = Report::default(); let mode = if write { Mode::Apply } else { Mode::Verify }; - let mut scope = Scope::new(&[], mode, &mut report, budget); + let mut images = pdfcraft_cos::ImageBudget::new(doc); + let mut scope = Scope::new(&[], mode, &mut report, budget, &mut images); if text { let c = page.crop(doc); scope.hidden_text = Some([c[0].min(c[2]), c[1].min(c[3]), c[0].max(c[2]), c[1].max(c[3])]); diff --git a/crates/redact/src/tags.rs b/crates/redact/src/tags.rs index 961f016e94..648c0c29e5 100644 --- a/crates/redact/src/tags.rs +++ b/crates/redact/src/tags.rs @@ -2,7 +2,7 @@ //! //! Marked content (MCIDs) that applying redactions changed is found by comparing each MCID's //! operators before and after. Elements owning such content lose their alternate text, actual -//! text and expansion (which may spell out the removed words); +//! text, title and expansion (which may spell out the removed words), as do their ancestors; //! references to marked content that is now empty are dropped from the element. use std::collections::{HashMap, HashSet}; @@ -281,7 +281,7 @@ pub(crate) fn clean_within( } doc.update_dict(r, |e| { if sensitive { - for key in [&b"Alt"[..], b"ActualText", b"E"] { + for key in DESCRIPTIONS { e.remove(key); } } @@ -321,8 +321,10 @@ impl Above { } } -/// The keys of an element that describe its content. -const DESCRIPTIONS: [&[u8]; 3] = [b"Alt", b"ActualText", b"E"]; +/// The keys of an element that describe its content, and so may repeat what was removed: one +/// policy for the element that owned it, the elements above it and elements written in place. +/// The title (`/T`) is included, as producers often fill it with the element's text. +const DESCRIPTIONS: [&[u8]; 4] = [b"Alt", b"ActualText", b"T", b"E"]; /// Each element's parents as the walk found them: through `/K`, which `/P` may not agree with. struct Parents(HashMap>); @@ -539,7 +541,7 @@ pub(crate) fn drop_object_refs_within(doc: &mut Document, gone: &HashSet // An element that lost an annotation keeps no text describing it, even with other // kids left: a link's alternate text often repeats the URL, an annotation's its // comment. Elements above it may describe it too. - for key in [&b"Alt"[..], b"ActualText", b"T", b"E"] { + for key in DESCRIPTIONS { e.remove(key); } })?; diff --git a/crates/redact/src/tests.rs b/crates/redact/src/tests.rs index 74b8407056..3c170aba20 100644 --- a/crates/redact/src/tests.rs +++ b/crates/redact/src/tests.rs @@ -52,7 +52,8 @@ fn under(doc: &mut Document, page: usize, rects: &[[f64; 4]]) -> usize { let (_, data) = page_streams_within(doc, &p.dict, page, &mut budget).unwrap(); let res = p.dict.get(b"Resources").and_then(|r| doc.resolve(r).as_dict().cloned()).unwrap_or_default(); let mut rep = Report::default(); - let mut scope = Scope::new(rects, Mode::Verify, &mut rep, budget); + let mut images = pdfcraft_cos::ImageBudget::with_work(0); + let mut scope = Scope::new(rects, Mode::Verify, &mut rep, budget, &mut images); process(doc, &mut scope, &data, &res, pdfcraft_content::Matrix::IDENTITY).residue } @@ -519,10 +520,16 @@ fn two_pages_one_resource_dictionary(inherited: bool, again: bool) -> Document { ]) } +/// What image `s` decodes to, its fax or JBIG2 data included, with no limit on the work: the +/// samples an operation would read through its `ImageBudget`. +fn decoded_image(doc: &Document, s: &pdfcraft_cos::Stream) -> Result, pdfcraft_cos::CosError> { + pdfcraft_cos::ImageBudget::with_work(u64::MAX).decode(doc, s, pdfcraft_cos::MAX_DECODED) +} + /// The samples of the image a page's (possibly inherited) resources name `name`, decoded through -/// its image codec too (`Document::decoded_image`). +/// its image codec too ([`decoded_image`]). fn named_image(doc: &Document, page: usize, name: &[u8]) -> Option> { - named_stream(doc, page, name).and_then(|s| doc.decoded_image(&s).ok()) + named_stream(doc, page, name).and_then(|s| decoded_image(doc, &s).ok()) } /// The image a page's (possibly inherited) resources name `name`. @@ -707,7 +714,8 @@ fn group_3_on_bytes_is_removed_whole_and_other_fax_images_cleared() { (-1, true, "<< /K -1 /Columns 16 /EncodedByteAlign true >>", vec![0x80, 0x80], vec![], false), ] { let p = pdfcraft_filters::CcittParams { k, columns: 16, encoded_byte_align: on_bytes, ..Default::default() }; - assert_eq!(pdfcraft_filters::decode_ccitt(&data, &p, 2).unwrap(), [0xFF; 4], "{parms}: the picture is white"); + let mut work = u64::MAX; + assert_eq!(pdfcraft_filters::decode_ccitt_within(&data, &p, 2, &mut work).unwrap(), [0xFF; 4], "{parms}: the picture is white"); let dict = format!("{image} /DecodeParms {parms}"); let mut objs = vec![stream(&dict, data)]; objs.extend(extra); @@ -769,7 +777,7 @@ fn no_stream_holds_the_pixels_under_a_mark_on_a_jbig2_scan() { } let holds = |doc: &Document, pixels: &[u8]| { doc.scan_objects().any(|(_, object)| match &*object { - Object::Stream(s) => doc.decoded_image(s).is_ok_and(|d| d.windows(pixels.len()).any(|w| w == pixels)), + Object::Stream(s) => decoded_image(doc, s).is_ok_and(|d| d.windows(pixels.len()).any(|w| w == pixels)), _ => false, }) }; @@ -806,6 +814,61 @@ fn jbig2_globals(secret: &[u8]) -> Vec { g } +/// An image the run's allowance can't decode can't be cleared. Removed whole, like an image that +/// can't be read, it would take what no mark covers with it without a word, so the run stops there, +/// and [`apply`] leaves the document as it was. +#[test] +fn a_jbig2_image_past_the_runs_allowance_stops_the_run() { + let mut dict = Dict::new(); + dict.set(b"Width".to_vec(), Object::Int(16)); + dict.set(b"Height".to_vec(), Object::Int(2)); + dict.set(b"BitsPerComponent".to_vec(), Object::Int(1)); + dict.set(b"ColorSpace".to_vec(), Object::name("DeviceGray")); + dict.set(b"Filter".to_vec(), Object::name("JBIG2Decode")); + let image = Stream::from_raw(dict, pdfcraft_filters::encode_jbig2_generic(&[0xFF; 4], 16, 2).unwrap()); + let doc = Document::new_empty(); + let half = [[0.0, 0.0, 0.5, 1.0]]; + let clear = |work| crate::image::clear(&doc, &image, &pdfcraft_content::Matrix::IDENTITY, &half, &mut pdfcraft_cos::ImageBudget::with_work(work)); + assert!(matches!(clear(u64::MAX), Ok(Some(_))), "cleared in a copy"); + assert!(matches!(clear(0), Err(())), "it can't be cleared"); + + let coded = pdfcraft_filters::encode_jbig2_generic(&[0xFF; 4], 16, 2).unwrap(); + let dict = "/Type /XObject /Subtype /Image /Width 16 /Height 2 /BitsPerComponent 1 /ColorSpace /DeviceGray /Filter /JBIG2Decode"; + let mut doc = one_page(b"q 160 0 0 20 0 0 cm /Im Do Q", "/XObject << /Im 7 0 R >>", vec![stream(dict, coded)]); + mark(&mut doc, 0, &[[0.0, 12.0, 75.0, 18.0]], ""); + let refused = crate::apply_within(&mut doc, None, pdfcraft_cos::ImageBudget::with_work(0)); + assert!(matches!(refused, Err(crate::RedactError::ImagesPastAllowance)), "{refused:?}"); + let mut doc = one_page( + b"q 160 0 0 20 0 0 cm /Im Do Q", + "/XObject << /Im 7 0 R >>", + vec![stream(dict, pdfcraft_filters::encode_jbig2_generic(&[0xFF; 4], 16, 2).unwrap())], + ); + mark(&mut doc, 0, &[[0.0, 12.0, 75.0, 18.0]], ""); + assert!(crate::apply_within(&mut doc, None, pdfcraft_cos::ImageBudget::with_work(u64::MAX)).is_ok()); +} + +/// A Flate image past the run's allowance stops the run as a JBIG2 image does: removed whole, it +/// would take what no mark covers with it, unreported. A JPEG, which clearing doesn't read, is +/// removed whole as it always was, and spends nothing. +#[test] +fn a_flate_image_past_the_runs_allowance_stops_the_run() { + let dict = "/Type /XObject /Subtype /Image /Width 2 /Height 2 /BitsPerComponent 8 /ColorSpace /DeviceGray /Filter /FlateDecode"; + let page = || one_page(b"q 160 0 0 20 0 0 cm /Im Do Q", "/XObject << /Im 7 0 R >>", vec![stream(dict, pdfcraft_filters::encode_flate(&[9; 4]))]); + let mut doc = page(); + mark(&mut doc, 0, &[[0.0, 12.0, 75.0, 18.0]], ""); + let refused = crate::apply_within(&mut doc, None, pdfcraft_cos::ImageBudget::with_work(0)); + assert!(matches!(refused, Err(crate::RedactError::ImagesPastAllowance)), "{refused:?}"); + let mut doc = page(); + mark(&mut doc, 0, &[[0.0, 12.0, 75.0, 18.0]], ""); + assert!(crate::apply_within(&mut doc, None, pdfcraft_cos::ImageBudget::with_work(u64::MAX)).is_ok()); + + let dict = "/Type /XObject /Subtype /Image /Width 2 /Height 2 /BitsPerComponent 8 /ColorSpace /DeviceGray /Filter /DCTDecode"; + let mut doc = one_page(b"q 160 0 0 20 0 0 cm /Im Do Q", "/XObject << /Im 7 0 R >>", vec![stream(dict, b"not read")]); + mark(&mut doc, 0, &[[0.0, 12.0, 75.0, 18.0]], ""); + let report = crate::apply_within(&mut doc, None, pdfcraft_cos::ImageBudget::with_work(0)).unwrap(); + assert_eq!(report.images_removed, 1); +} + /// A JBIG2 image (a scan the optimizer stored as JBIG2) has its covered pixels cleared in a copy, /// like a fax image, instead of being removed whole: with `/JBIG2Globals`, its `/DecodeParms` by /// reference, behind another filter with its globals at its own place, or as a mask, its decode @@ -830,6 +893,13 @@ fn a_jbig2_image_has_its_covered_pixels_cleared_instead_of_being_removed() { ( format!("{image} /ColorSpace /DeviceGray /Filter [/ASCIIHexDecode /JBIG2Decode] /DecodeParms [null << /JBIG2Globals 8 0 R >>]"), hex, + vec![globals.clone()], + [0x00, 0xFF, 0xFF, 0xFF], + ), + // `/Crypt` was undone on load, and takes a place in the parameters. + ( + format!("{image} /ColorSpace /DeviceGray /Filter [/Crypt /JBIG2Decode] /DecodeParms [null << /JBIG2Globals 8 0 R >>]"), + white.clone(), vec![globals], [0x00, 0xFF, 0xFF, 0xFF], ), @@ -1199,7 +1269,7 @@ fn globals_a_redacted_jbig2_image_shares_with_another_page_leave_the_file() { let res = doc.resolve(p.dict.get(b"Resources")?).as_dict().cloned()?; let xo = doc.resolve(res.get(b"XObject")?).as_dict().cloned()?; match &*doc.get(xo.get(name)?.as_ref()?) { - Object::Stream(s) => doc.decoded_image(s).ok(), + Object::Stream(s) => decoded_image(doc, s).ok(), _ => None, } }; @@ -1240,6 +1310,15 @@ fn globals_a_redacted_jbig2_image_shares_with_another_page_leave_the_file() { let mut doc = build(&image.replace(&format!("/Height {h}"), &format!("/Height {}", h + 1))); mark(&mut doc, 0, &[[0.25, 113.75, 49.75, 120.0]], ""); assert!(matches!(apply(&mut doc, None), Err(RedactError::SharedJbig2Globals(1)))); + // Storing the second page's image again decodes it, within what is left of the run's + // allowance: with nothing left the redaction is refused as one past the allowance, not + // reported as an image that can't be read. + let mut doc = build(&image); + let first_image = [ObjRef::new(7, 0)]; + let refused = crate::restore_shared_jbig2(&mut doc, &first_image, &mut pdfcraft_cos::ImageBudget::with_work(0)); + assert!(matches!(refused, Err(RedactError::ImagesPastAllowance)), "{refused:?}"); + let restored = crate::restore_shared_jbig2(&mut doc, &first_image, &mut pdfcraft_cos::ImageBudget::with_work(u64::MAX)); + assert_eq!(restored.ok(), Some(1)); } /// Apply Redactions gives the page its own pruned /Resources, but the dictionary it drew through @@ -2884,7 +2963,7 @@ fn assert_no_secret(doc: &Document, secret: &[u8]) { assert!(!bytes.windows(secret.len()).any(|w| w == secret), "secret remains in object {r:?}"); if let Object::Stream(s) = &*object { // Image codecs, a cleared scan coded as Group 4 or JBIG2, decode through the document. - let data = s.decoded().or_else(|_| saved.decoded_image(s)).unwrap(); + let data = s.decoded().or_else(|_| decoded_image(&saved, s)).unwrap(); assert!(!data.windows(secret.len()).any(|w| w == secret), "secret remains in stream {r:?}"); } } @@ -3792,3 +3871,29 @@ fn a_reply_on_another_page_to_a_removed_popup_goes_too() { assert!(!bytes.windows(gone.len()).any(|w| w == gone), "{} survived", String::from_utf8_lossy(gone)); } } + +#[test] +fn a_rewritten_form_xobject_drops_the_source_text_of_added_content() { + // A form drawing invisible text whose dictionary repeats it in /PCAdded. + let form = stream( + "/Type /XObject /Subtype /Form /BBox [0 0 300 300] /Resources << /Font << /F1 5 0 R >> >> /PCMark /Added /PCAdded << /Kind /Text /Text (LEAK_FORM_SOURCE) >>", + b"BT /F1 10 Tf 3 Tr 10 100 Td (HIDDEN) Tj ET BT /F1 10 Tf 10 200 Td (Shown) Tj ET", + ); + let mut doc = one_page(b"/X Do", "/XObject << /X 7 0 R >>", vec![form]); + sanitize::remove_hidden(&mut doc, &[sanitize::Hidden::HiddenText]).unwrap(); + let bytes = write_full(&doc, &SaveOptions { object_streams: false, ..SaveOptions::default() }).unwrap(); + assert!(!bytes.windows(16).any(|w| w == b"LEAK_FORM_SOURCE"), "the form's added-content source text survived"); +} + +#[test] +fn a_redacted_form_xobject_drops_the_source_text_of_added_content() { + let form = stream( + "/Type /XObject /Subtype /Form /BBox [0 0 300 300] /Resources << /Font << /F1 5 0 R >> >> /PCMark /Added /PCAdded << /Kind /Text /Text (AB1234CD) >>", + b"BT /F1 10 Tf 10 100 Td (AB1234CD) Tj ET", + ); + let mut doc = one_page(b"/X Do", "/XObject << /X 7 0 R >>", vec![form]); + mark(&mut doc, 0, &[[20.0, 95.0, 40.0, 110.0]], ""); + apply(&mut doc, None).unwrap(); + let bytes = write_full(&doc, &SaveOptions { object_streams: false, ..SaveOptions::default() }).unwrap(); + assert!(!bytes.windows(4).any(|w| w == b"1234"), "redacted text left in the saved file"); +} diff --git a/crates/redact/src/tests/descriptions.rs b/crates/redact/src/tests/descriptions.rs index df6b8555dc..0495dd1f70 100644 --- a/crates/redact/src/tests/descriptions.rs +++ b/crates/redact/src/tests/descriptions.rs @@ -62,3 +62,61 @@ fn a_link_element_that_keeps_its_text_loses_the_description_of_its_removed_annot let link = doc.get(ObjRef::new(11, 0)).as_dict().cloned().unwrap(); assert_eq!(link.get(b"K"), Some(&Object::Array(vec![Object::Int(0)])), "the element keeps its text"); } + +/// [`sectioned`], with titles that repeat the secret on the paragraph that owns it, on its section +/// and on the document element above both. +fn titled() -> Document { + let mut doc = sectioned("11 0 R"); + let title = |t: &str| Object::String(pdfcraft_cos::PdfString::literal(t.as_bytes().to_vec())); + for (n, t) in [(8, "LEAK_DOC_TITLE"), (9, "LEAK_OWN_TITLE"), (11, "LEAK_SECT_TITLE"), (10, "Public title")] { + doc.update_dict(ObjRef::new(n, 0), |d| d.set(b"T".to_vec(), title(t))).unwrap(); + } + doc +} + +#[test] +fn titles_repeating_redacted_content_go_from_the_owner_and_its_ancestors() { + let mut doc = titled(); + mark(&mut doc, 0, &[[5.0, 195.0, 60.0, 212.0]], ""); + apply(&mut doc, None).unwrap(); + assert!(!full_save_holds(&doc, b"LEAK_"), "a structure title repeating the redacted word survived"); + let public = doc.get(ObjRef::new(10, 0)).as_dict().cloned().unwrap(); + assert!(public.contains(b"T"), "an element beside it keeps its own title"); +} + +#[test] +fn titles_repeating_hidden_text_go_from_the_owner_and_its_ancestors() { + use crate::sanitize::{Hidden, remove_hidden}; + let mut doc = titled(); + let hidden = + b"/P <> BDC BT /F1 10 Tf 3 Tr 10 200 Td (SECRET) Tj ET EMC /P <> BDC BT /F1 10 Tf 0 Tr 10 100 Td (Public) Tj ET EMC"; + doc.set(ObjRef::new(4, 0), Object::Stream(Stream::from_raw(Dict::new(), hidden.to_vec()))); + remove_hidden(&mut doc, &[Hidden::HiddenText]).unwrap(); + assert!(!full_save_holds(&doc, b"SECRET"), "the hidden text survived"); + assert!(!full_save_holds(&doc, b"LEAK_"), "a structure title repeating the hidden text survived"); + let public = doc.get(ObjRef::new(10, 0)).as_dict().cloned().unwrap(); + assert!(public.contains(b"T"), "an element beside it keeps its own title"); +} + +#[test] +fn an_ancestor_title_describing_a_removed_annotation_goes() { + use crate::sanitize::{Hidden, remove_hidden}; + let mut doc = pdf(vec![ + b"<< /Type /Catalog /Pages 2 0 R /MarkInfo << /Marked true >> /StructTreeRoot 8 0 R >>".to_vec(), + b"<< /Type /Pages /Kids [3 0 R] /Count 1 >>".to_vec(), + b"<< /Type /Page /Parent 2 0 R /MediaBox [0 0 300 300] /Contents 4 0 R /Resources << /Font << /F1 5 0 R >> >> /Annots [6 0 R] /StructParents 0 >>" + .to_vec(), + stream("", b"/Link << /MCID 0 >> BDC BT /F1 10 Tf 10 230 Td (See the site) Tj ET EMC"), + FONT.replace("95 0 R", "12 0 R").into_bytes(), + b"<< /Type /Annot /Subtype /Link /Rect [10 228 80 240] /StructParent 1 /A << /S /URI /URI (https://example.org/) >> >>".to_vec(), + b"null".to_vec(), + b"<< /Type /StructTreeRoot /K 9 0 R /ParentTree << /Nums [0 [11 0 R] 1 11 0 R] >> /ParentTreeNextKey 2 >>".to_vec(), + b"<< /Type /StructElem /S /Document /P 8 0 R /K 10 0 R >>".to_vec(), + // Only a title above the link element repeats the address. + b"<< /Type /StructElem /S /P /P 9 0 R /T (LEAK_PARENT_TITLE) /K 11 0 R >>".to_vec(), + b"<< /Type /StructElem /S /Link /P 10 0 R /Pg 3 0 R /K [0 << /Type /OBJR /Obj 6 0 R /Pg 3 0 R >>] >>".to_vec(), + widths(), + ]); + remove_hidden(&mut doc, &[Hidden::LinksActionsScripts]).unwrap(); + assert!(!full_save_holds(&doc, b"LEAK_"), "an ancestor's title describing the removed link survived"); +} diff --git a/crates/render/src/inspect/core.rs b/crates/render/src/inspect/core.rs index c190dc565b..924bfcc51d 100644 --- a/crates/render/src/inspect/core.rs +++ b/crates/render/src/inspect/core.rs @@ -288,11 +288,23 @@ impl<'a> Inspector<'a> { } pub(super) fn text(&self, d: &Dictionary, key: &[u8]) -> Option { - let s = trimmed_text(self.resolve(d.get(key).ok()?))?; - (!s.is_empty()).then_some(s) + // Typewriter outer whitespace belongs to the text (keep in step with annot's summaries). + let s = if key == b"Contents" + && self.name(d, b"Subtype").as_deref() == Some("FreeText") + && self.name(d, b"IT").as_deref() == Some("FreeTextTypeWriter") + { + match self.resolve(d.get(key).ok()?) { + Object::String(bytes, _) => text_string(bytes).trim_matches('\0').to_owned(), + Object::Name(bytes) => String::from_utf8_lossy(bytes).trim_matches('\0').to_owned(), + _ => return None, + } + } else { + trimmed_text(self.resolve(d.get(key).ok()?))? + }; + (!s.trim().is_empty()).then_some(s) } - /// [`Self::text`], converted and spent from `budget` as [`spend`] does, so text that trims + /// Whitespace-trimmed metadata, spent from `budget` as [`spend`] does, so text that trims /// short or to nothing still spends its raw length. pub(super) fn budgeted_text(&self, d: &Dictionary, key: &[u8], budget: &mut usize) -> Option { let o = self.resolve(d.get(key).ok()?); diff --git a/crates/render/src/inspect/tests.rs b/crates/render/src/inspect/tests.rs index a5bfec474d..7221e97d5a 100644 --- a/crates/render/src/inspect/tests.rs +++ b/crates/render/src/inspect/tests.rs @@ -1870,3 +1870,45 @@ trailer << /Root 1 0 R >> assert!((p.width - 3874.96).abs() < 0.1, "width expected ~3874.96, got {}", p.width); assert!((p.height - 5493.54).abs() < 0.1, "height expected ~5493.54, got {}", p.height); } + +/// Inspection keeps every object it reads, converted, for as long as it runs, and nothing it +/// reports comes from `/PieceInfo`. InDesign writes kilobytes of that private data into every +/// page, and a 1,412-page book held over a gigabyte of it (#5873). It is left out of what +/// inspection keeps, and what inspection reports is the same as for the page without it. +#[test] +fn inspection_keeps_no_private_page_data() { + use lopdf::dictionary; + let make = |private: bool| -> Vec { + let mut doc = Document::with_version("1.7"); + let pages_id = doc.new_object_id(); + let mut page = dictionary! { + "Type" => "Page", + "Parent" => pages_id, + "MediaBox" => vec![0.into(), 0.into(), 200.into(), 300.into()], + "Rotate" => 90, + }; + if private { + let map: Dictionary = (0..50).map(|i| (i.to_string(), Object::Array(vec![Object::Integer(i), Object::Real(116.22)]))).collect(); + page.set("PieceInfo", dictionary! { "InDesign" => dictionary! { "PageItemUIDToLocationDataMap" => map } }); + } + let page_id = doc.add_object(page); + doc.objects.insert(pages_id, dictionary! { "Type" => "Pages", "Kids" => vec![page_id.into()], "Count" => 1 }.into()); + let catalog = doc.add_object(dictionary! { "Type" => "Catalog", "Pages" => pages_id }); + doc.trailer.set("Root", catalog); + let mut out = Vec::new(); + doc.save_to(&mut out).unwrap(); + out + }; + let (with, without) = (make(true), make(false)); + let lazy = LazyStructure::new(Arc::new(with.clone()), None).unwrap(); + let page = lazy.get_object((2, 0)).unwrap().as_dict().unwrap(); + assert!(!page.has(b"PieceInfo"), "the private data is not kept"); + assert!(page.has(b"MediaBox") && page.has(b"Rotate") && page.has(b"Parent"), "the rest of the page is"); + + let report = |bytes: Vec| { + let mut info = inspect(Arc::new(bytes), None).unwrap(); + info.file_size = 0; + format!("{info:?}") + }; + assert_eq!(report(with), report(without), "what inspection reports does not change"); +} diff --git a/crates/render/src/raster.rs b/crates/render/src/raster.rs index f973851d26..9331c82ea7 100644 --- a/crates/render/src/raster.rs +++ b/crates/render/src/raster.rs @@ -83,6 +83,10 @@ pub struct RenderConfig { /// viewer and preview rasters: exports, printing and OCR render without it, so nothing drawn with an /// installed font is saved or printed (AGENTS.md §1.2, §1.4). pub system_fonts: bool, + /// Steps of JBIG2 decoding a render may take across the page's images, instead of the usual + /// `hayro_syntax::MAX_PAGE_JBIG2_WORK`. Those past it aren't drawn, like an image that can't + /// be decoded. + pub jbig2_work: Option, } impl RenderConfig { @@ -100,7 +104,8 @@ impl RenderConfig { /// Passwords belong to parser construction; request-specific preview overrides are applied /// by `render_page`, which also preserves the caller's warning and cancellation hooks. fn settings(&self) -> InterpreterSettings { - let standard = InterpreterSettings::default().font_resolver; + let defaults = InterpreterSettings::default(); + let standard = defaults.font_resolver.clone(); let system_fonts = self.system_fonts; InterpreterSettings { ocg_overrides: self.layers.clone(), @@ -108,7 +113,8 @@ impl RenderConfig { font_resolver: Arc::new(move |query| { japanese_fallback(query).or_else(|| system_fonts.then(|| system_fallback(query)).flatten()).or_else(|| standard(query)) }), - ..InterpreterSettings::default() + jbig2_work: self.jbig2_work.unwrap_or(defaults.jbig2_work), + ..defaults } } } diff --git a/crates/render/src/raster/tests.rs b/crates/render/src/raster/tests.rs index 1c24408e1b..9c5d75bfbc 100644 --- a/crates/render/src/raster/tests.rs +++ b/crates/render/src/raster/tests.rs @@ -4058,7 +4058,10 @@ fn jbig2_image_draws_with(stream: &[u8], space: &str, entries: &str, objects: &[ pdf.extend_from_slice(b"\nendstream endobj\n"); pdf.extend_from_slice(objects); pdf.extend_from_slice(b"trailer << /Root 1 0 R >>\n%%EOF\n"); - let mut r = PageRenderer::new(Arc::new(pdf), RenderConfig::default()); + // What one image may take, which the page's allowance, tested on its own, would otherwise reach + // first: it is the same size, and the page itself comes out of it. + let config = RenderConfig { jbig2_work: Some(u64::MAX), ..RenderConfig::default() }; + let mut r = PageRenderer::new(Arc::new(pdf), config); let page = r.render(RenderRequest { page: 0, kind: RequestKind::Pixels, tile: None, scale: 1.0, tag: 0, ..Default::default() }); assert!(page.error.is_none(), "{:?}", page.error); assert_eq!(&page.rgba[((38 * 40 + 1) * 4)..][..4], &[255, 0, 0, 255], "the rest of the page draws"); @@ -4070,6 +4073,217 @@ fn jbig2_image_draws_with(stream: &[u8], space: &str, entries: &str, objects: &[ } } +/// The JBIG2 images of a page share one allowance, down to the step, and the next page starts with +/// its own. The images differ by an extension segment: one image decoded again isn't decoded twice. +#[test] +fn the_jbig2_images_of_a_page_share_one_allowance() { + let image = |number: u8, id: u8| { + let mut stream = black_jbig2_page(); + jbig2_segment(&mut stream, 1, 62, &[], &[0, 0, 0, 0, id]); + let mut object = format!( + "{number} 0 obj << /Type /XObject /Subtype /Image /Width 16 /Height 2 /BitsPerComponent 1 /ColorSpace /DeviceGray /Filter /JBIG2Decode /Length {} >> stream\n", + stream.len() + ) + .into_bytes(); + object.extend_from_slice(&stream); + object.extend_from_slice(b"\nendstream endobj\n"); + object + }; + let page = |number: u8, content: u8, xobjects: &str| { + format!("{number} 0 obj << /Type /Page /Parent 2 0 R /MediaBox [0 0 40 40] /Contents {content} 0 R /Resources << /XObject << {xobjects} >> >> >> endobj\n").into_bytes() + }; + let content = |number: u8, text: &str| format!("{number} 0 obj << /Length {} >> stream\n{text}\nendstream endobj\n", text.len()).into_bytes(); + let mut pdf = + b"%PDF-1.7\n1 0 obj << /Type /Catalog /Pages 2 0 R >> endobj\n2 0 obj << /Type /Pages /Kids [3 0 R 4 0 R] /Count 2 >> endobj\n".to_vec(); + pdf.extend(page(3, 5, "/A 7 0 R /B 8 0 R")); + pdf.extend(page(4, 6, "/C 9 0 R")); + pdf.extend(content(5, "q 20 0 0 40 0 0 cm /A Do Q q 20 0 0 40 20 0 cm /B Do Q")); + pdf.extend(content(6, "q 20 0 0 40 0 0 cm /C Do Q")); + pdf.extend(image(7, 1)); + pdf.extend(image(8, 2)); + pdf.extend(image(9, 3)); + pdf.extend_from_slice(b"trailer << /Root 1 0 R >>\n%%EOF\n"); + let pdf = Arc::new(pdf); + let black = |page: &RenderedPage, x: usize| match &page.rgba[((20 * 40 + x) * 4)..][..4] { + [0, 0, 0, 255] => true, + [255, 255, 255, 255] => false, + other => panic!("neither an image nor the page: {other:?}"), + }; + let pages = |work: u64| { + let mut renderer = PageRenderer::new(pdf.clone(), RenderConfig { jbig2_work: Some(work), ..RenderConfig::default() }); + [0, 1].map(|page| renderer.render(RenderRequest { page, kind: RequestKind::Pixels, tile: None, scale: 1.0, tag: 0, ..Default::default() })) + }; + let drawn = |work: u64| { + let [first, _] = pages(work); + assert!(first.error.is_none(), "{:?}", first.error); + (black(&first, 10), black(&first, 30)) + }; + let one = (1..1_000).find(|work| drawn(*work).0).expect("a small image is cheap"); + assert_eq!(drawn(one - 1), (false, false), "a step short of the first"); + assert_eq!(drawn(one), (true, false), "enough for one"); + assert_eq!(drawn(2 * one - 1), (true, false), "a step short of both"); + assert_eq!(drawn(2 * one), (true, true), "enough for both"); + let [first, second] = pages(one); + assert!(first.warnings.contains(&RenderWarning::ContentTruncated), "the page says it left something out: {:?}", first.warnings); + assert!(pages(2 * one)[0].warnings.is_empty(), "and only then"); + assert!(black(&second, 10), "the next page has its own allowance, though this one spent all of it"); + let usual = PageRenderer::new(pdf.clone(), RenderConfig::default()).render(RenderRequest { + page: 0, + kind: RequestKind::Pixels, + tile: None, + scale: 1.0, + tag: 0, + ..Default::default() + }); + assert!(black(&usual, 10) && black(&usual, 30), "the usual allowance is far above a page like this"); +} + +/// Without its mask a picture would show what the mask hides, so a JBIG2 mask past the page's +/// allowance takes the picture with it, and the page says so. A mask that can't be read for any +/// other reason leaves the picture, as it did. +#[test] +fn a_picture_whose_jbig2_mask_is_past_the_pages_allowance_is_not_drawn() { + let draw = |entry: &str, filter: &str, mask: &[u8], work: u64| { + let content = b"q 20 0 0 20 5 5 cm /Im1 Do Q"; + let mut pdf = b"%PDF-1.7\n1 0 obj << /Type /Catalog /Pages 2 0 R >> endobj\n2 0 obj << /Type /Pages /Kids [3 0 R] /Count 1 >> endobj\n3 0 obj << /Type /Page /Parent 2 0 R /MediaBox [0 0 40 40] /Contents 4 0 R /Resources << /XObject << /Im1 5 0 R >> >> >> endobj\n".to_vec(); + pdf.extend_from_slice(format!("4 0 obj << /Length {} >> stream\n", content.len()).as_bytes()); + pdf.extend_from_slice(content); + pdf.extend_from_slice(b"\nendstream endobj\n"); + pdf.extend_from_slice( + format!("5 0 obj << /Type /XObject /Subtype /Image /Width 1 /Height 1 /BitsPerComponent 8 /ColorSpace /DeviceGray {entry} 6 0 R /Length 1 >> stream\n\0\nendstream endobj\n").as_bytes(), + ); + let kind = if entry == "/Mask" { "/ImageMask true" } else { "/ColorSpace /DeviceGray" }; + pdf.extend_from_slice( + format!( + "6 0 obj << /Type /XObject /Subtype /Image /Width 16 /Height 2 /BitsPerComponent 1 {kind} /Filter {filter} /Length {} >> stream\n", + mask.len() + ) + .as_bytes(), + ); + pdf.extend_from_slice(mask); + pdf.extend_from_slice(b"\nendstream endobj\ntrailer << /Root 1 0 R >>\n%%EOF\n"); + let config = RenderConfig { jbig2_work: Some(work), ..RenderConfig::default() }; + let page = PageRenderer::new(Arc::new(pdf), config).render(RenderRequest { + page: 0, + kind: RequestKind::Pixels, + tile: None, + scale: 1.0, + tag: 0, + ..Default::default() + }); + assert!(page.error.is_none(), "{:?}", page.error); + let shown = match &page.rgba[((25 * 40 + 15) * 4)..][..4] { + [0, 0, 0, 255] => true, + [255, 255, 255, 255] => false, + other => panic!("neither the picture nor the page: {other:?}"), + }; + (shown, page.warnings.contains(&RenderWarning::ContentTruncated)) + }; + let mask = black_jbig2_page(); + let jbig2 = "/JBIG2Decode"; + assert_eq!(draw("/SMask", jbig2, &mask, u64::MAX), (false, false), "the mask hides all of it"); + assert_eq!(draw("/SMask", jbig2, &mask, 0), (false, true), "past the allowance a soft mask hides it too"); + assert_eq!(draw("/Mask", jbig2, &mask, 0), (false, true), "and so does a stencil mask"); + assert_eq!(draw("/SMask", jbig2, b"no JBIG2 here", 1 << 20), (true, false), "any other bad mask is no mask"); + let other = draw("/SMask", "/DCTDecode", b"no JPEG here", 0); + assert_eq!(other, (true, false), "and a page with nothing left says nothing of a mask that isn't JBIG2"); +} + +/// A page's allowance ends with it, so what decodes on its thread afterwards has no page to run out +/// on, and a `Context` used again starts afresh. +#[test] +fn a_pages_jbig2_allowance_ends_with_the_page() { + use hayro::hayro_interpret::font::Glyph; + use hayro::hayro_interpret::hayro_syntax::Pdf; + use hayro::hayro_interpret::{ + BlendMode, ClipPath, Context, Device, GlyphDrawMode, Image, InterpreterCache, InterpreterSettings, Paint, PathDrawMode, SoftMask, + TransformExt, interpret_page, + }; + use hayro_syntax::page_jbig2_work_spent; + use kurbo::{Affine, BezPath, Rect}; + + /// Notes at each path whether the page has run out. + struct Spent(Vec); + impl<'a> Device<'a> for Spent { + fn set_soft_mask(&mut self, _: Option>) {} + fn set_blend_mode(&mut self, _: BlendMode) {} + fn draw_path(&mut self, _: &BezPath, _: Affine, _: &Paint<'a>, _: &PathDrawMode) { + self.0.push(page_jbig2_work_spent()); + } + fn push_clip_path(&mut self, _: &ClipPath) {} + fn push_transparency_group(&mut self, _: f32, _: Option>, _: BlendMode) {} + fn draw_glyph(&mut self, _: &Glyph<'a>, _: Affine, _: Affine, _: &Paint<'a>, _: &GlyphDrawMode) {} + fn draw_image(&mut self, _: Image<'a, '_>, _: Affine) {} + fn pop_clip_path(&mut self) {} + fn pop_transparency_group(&mut self) {} + } + + let content = "0 0 4 4 re f"; + let bytes = format!( + "%PDF-1.7\n1 0 obj << /Type /Catalog /Pages 2 0 R >> endobj\n2 0 obj << /Type /Pages /Kids [3 0 R] /Count 1 >> endobj\n3 0 obj << /Type /Page /Parent 2 0 R /MediaBox [0 0 40 40] /Contents 4 0 R >> endobj\n4 0 obj << /Length {} >> stream\n{content}\nendstream endobj\ntrailer << /Root 1 0 R >>\n%%EOF\n", + content.len() + ); + let pdf = Pdf::new(Arc::new(bytes.into_bytes())).expect("parses"); + let page = &pdf.pages()[0]; + let cache = InterpreterCache::new(); + let settings = InterpreterSettings { jbig2_work: 0, ..InterpreterSettings::default() }; + let mut ctx = Context::new(page.initial_transform(true).to_kurbo(), Rect::new(0.0, 0.0, 40.0, 40.0), &cache, page.xref(), settings); + let mut device = Spent(Vec::new()); + for _ in 0..2 { + interpret_page(page, &mut ctx, &mut device); + assert!(!page_jbig2_work_spent(), "no page is being drawn"); + } + assert_eq!(device.0, [true, true], "each time, the page has what its settings give it"); +} + +/// An image that can't be decoded has still cost its reading, which a page repeats for each time +/// it draws one, since such an image isn't kept. So what it reads comes out of the page's allowance, +/// and an image after it has less. Allowed exactly what the good one takes, it isn't drawn behind +/// the bad one, and is drawn alone. +#[test] +fn an_image_that_fails_spends_the_pages_allowance_too() { + let image = |number: u8, stream: &[u8]| { + let mut object = format!( + "{number} 0 obj << /Type /XObject /Subtype /Image /Width 16 /Height 2 /BitsPerComponent 1 /ColorSpace /DeviceGray /Filter /JBIG2Decode /Length {} >> stream\n", + stream.len() + ) + .into_bytes(); + object.extend_from_slice(stream); + object.extend_from_slice(b"\nendstream endobj\n"); + object + }; + let pdf = |content: &str| { + let mut pdf = format!( + "%PDF-1.7\n1 0 obj << /Type /Catalog /Pages 2 0 R >> endobj\n2 0 obj << /Type /Pages /Kids [3 0 R] /Count 1 >> endobj\n\ + 3 0 obj << /Type /Page /Parent 2 0 R /MediaBox [0 0 40 40] /Contents 4 0 R /Resources << /XObject << /Bad 5 0 R /Good 6 0 R >> >> >> endobj\n\ + 4 0 obj << /Length {} >> stream\n{content}\nendstream endobj\n", + content.len() + ) + .into_bytes(); + pdf.extend(image(5, &[0xFF; 64])); + pdf.extend(image(6, &black_jbig2_page())); + pdf.extend_from_slice(b"trailer << /Root 1 0 R >>\n%%EOF\n"); + Arc::new(pdf) + }; + let good = "q 40 0 0 40 0 0 cm /Good Do Q"; + let drawn = |content: &str, work: u64| { + let config = RenderConfig { jbig2_work: Some(work), ..RenderConfig::default() }; + let page = PageRenderer::new(pdf(content), config).render(RenderRequest { + page: 0, + kind: RequestKind::Pixels, + tile: None, + scale: 1.0, + tag: 0, + ..Default::default() + }); + assert!(page.error.is_none(), "{:?}", page.error); + page.rgba[((20 * 40 + 20) * 4)..][..4] == [0, 0, 0, 255] + }; + let cost = (1..2_000).find(|work| drawn(good, *work)).expect("a small image is cheap"); + assert!(!drawn(&format!("q 1 0 0 1 0 0 cm /Bad Do Q {good}"), cost), "the bad one spent some of it"); + assert!(drawn(&format!("q 1 0 0 1 0 0 cm /Bad Do Q {good}"), cost + 4 * 64), "and what it spent is its reading"); +} + /// Bits written from the top of each byte, as JBIG2's Huffman-coded data is. #[derive(Default)] struct Bits { @@ -8004,6 +8218,61 @@ fn japanese_substitute_spaces_keep_pdf_widths_and_unicode() { } } +/// One code, `<0010>`, in a Type 0 font named `base_font` that the PDF doesn't embed, with a +/// `/ToUnicode` that maps it to the UTF-16 `unicode`. 0x10 is the hyphen's glyph index in Arial, +/// and Identity-H with an identity `/CIDToGIDMap` makes the code that index, as Word writes it. +fn soft_hyphen_pdf(base_font: &str, unicode: &str) -> Vec { + let content = "BT /F1 60 Tf 10 20 Td <0010> Tj ET"; + let cmap = format!( + "/CIDInit /ProcSet findresource begin 12 dict begin begincmap +/CIDSystemInfo << /Registry (Adobe) /Ordering (UCS) /Supplement 0 >> def +/CMapName /Adobe-Identity-UCS def /CMapType 2 def +1 begincodespacerange <0000> endcodespacerange +1 beginbfchar <0010> <{unicode}> endbfchar +endcmap CMapName currentdict /CMap defineresource pop end end" + ); + format!( + "%PDF-1.7 +1 0 obj << /Type /Catalog /Pages 2 0 R >> endobj +2 0 obj << /Type /Pages /Kids [3 0 R] /Count 1 >> endobj +3 0 obj << /Type /Page /Parent 2 0 R /MediaBox [0 0 60 60] /Contents 4 0 R /Resources << /Font << /F1 5 0 R >> >> >> endobj +4 0 obj << /Length {} >> stream +{content} +endstream endobj +5 0 obj << /Type /Font /Subtype /Type0 /BaseFont /{base_font} /Encoding /Identity-H /DescendantFonts [6 0 R] /ToUnicode 8 0 R >> endobj +6 0 obj << /Type /Font /Subtype /CIDFontType2 /BaseFont /{base_font} /CIDSystemInfo << /Registry (Adobe) /Ordering (Identity) /Supplement 0 >> + /FontDescriptor 7 0 R /CIDToGIDMap /Identity /DW 1000 /W [16 [333]] >> endobj +7 0 obj << /Type /FontDescriptor /FontName /{base_font} /Flags 32 /FontBBox [-665 -325 2000 1040] /ItalicAngle 0 /Ascent 728 /Descent -210 /CapHeight 716 /StemV 80 >> endobj +8 0 obj << /Length {} >> stream +{cmap} +endstream endobj +trailer << /Root 1 0 R >> +%%EOF", + content.len(), + cmap.len() + ) + .into_bytes() +} + +/// #5888: Windows exporters map the hyphen glyph of an Arial they don't embed to U+00AD. The +/// standard substitute has no soft hyphen, so code 0x0010 was taken as its glyph 16 and drew +/// `Ë` (`!` in bold). It draws the substitute's hyphen now, and the text keeps the soft hyphen. +#[test] +fn a_soft_hyphen_a_substitute_lacks_draws_its_hyphen() { + for base_font in ["ArialMT", "Arial-BoldMT"] { + let soft = soft_hyphen_pdf(base_font, "00AD"); + let out = render_first_page(soft.clone()); + let expected = render_first_page(soft_hyphen_pdf(base_font, "002D")); + assert!(expected.rgba.as_chunks::<4>().0.iter().any(|pixel| pixel[0] < 128), "{base_font}: the hyphen control must draw ink"); + assert!(out.rgba.as_ref() == expected.rgba.as_ref(), "{base_font}: a soft hyphen draws as the substitute's hyphen"); + let mut renderer = PageRenderer::new(Arc::new(soft), RenderConfig::default()); + let text = renderer.render(RenderRequest { page: 0, kind: RequestKind::Text, ..Default::default() }); + assert!(text.error.is_none(), "{:?}", text.error); + let glyphs: String = text.text.unwrap().glyphs.iter().map(|glyph| glyph.text.as_str()).collect(); + assert_eq!(glyphs, "\u{ad}", "{base_font}: drawing the hyphen must not rewrite Unicode"); + } +} + /// Half-width katakana are common in Japanese documents set in a non-embedded Mincho font /// such as HeiseiMin-W3. The Mincho substitute must have those glyphs: one that lacks them /// (Shippori Mincho) draws them as .notdef. @@ -8491,6 +8760,99 @@ mod devicen_inks; // patch 27). mod isolated_cmyk_groups; +/// The generation-0 stand-in a rebuilt table files an object under must not make the object a +/// second object: enumeration yielded it once per key, so a document recovered without a readable +/// page tree reported the page twice (noted in review of #5580). +/// +/// And a later header for the same object number replaces the stand-in, so `N 0 R` cannot be left +/// pointing at a body the exact key no longer names. +#[cfg_attr(target_arch = "wasm32", wasm_bindgen_test::wasm_bindgen_test)] +#[cfg_attr(not(target_arch = "wasm32"), test)] +fn a_rebuilt_tables_generation_0_stand_in_is_not_a_second_object() { + // No table, no `startxref`, and no readable page tree: the pages are recovered by looking for + // objects that are pages, which is where a doubled object shows up as a doubled page. + let pdf = "%PDF-1.4\n\ + 1 0 obj << /Type /Catalog /Pages 2 0 R >> endobj\n\ + 3 99999 obj << /Type /Page /MediaBox [0 0 200 100] /Contents 4 0 R >> endobj\n\ + 4 0 obj << /Length 0 >> stream\n\nendstream endobj\n\ + trailer << /Root 1 0 R >>\n\ + %%EOF\n"; + let mut r = PageRenderer::new(Arc::new(pdf.to_string().into_bytes()), RenderConfig::default()); + let first = r.render(RenderRequest { page: 0, kind: RequestKind::Pixels, tile: None, scale: 1.0, tag: 0, preview: false }); + assert!(first.error.is_none(), "the page is recovered: {:?}", first.error); + let second = r.render(RenderRequest { page: 1, kind: RequestKind::Pixels, tile: None, scale: 1.0, tag: 0, preview: false }); + assert!(second.error.is_some(), "and it is one page, not two: page 2 must not exist"); + + // Two headers for object 3, the second the one the exact key names: the stand-in follows it. + // `(B)` is drawn by the later body, so the page that comes back says which one was read. + let twice = "%PDF-1.4\n\ + 1 0 obj << /Type /Catalog /Pages 2 0 R >> endobj\n\ + 2 0 obj << /Type /Pages /Kids [3 0 R] /Count 1 >> endobj\n\ + 3 1 obj << /Type /Page /Parent 2 0 R /MediaBox [0 0 200 100] /Contents 5 0 R >> endobj\n\ + 3 1 obj << /Type /Page /Parent 2 0 R /MediaBox [0 0 300 150] /Contents 5 0 R >> endobj\n\ + 5 0 obj << /Length 0 >> stream\n\nendstream endobj\n\ + trailer << /Root 1 0 R >>\n\ + %%EOF\n"; + let mut r = PageRenderer::new(Arc::new(twice.to_string().into_bytes()), RenderConfig::default()); + let page = r.render(RenderRequest { page: 0, kind: RequestKind::Pixels, tile: None, scale: 1.0, tag: 0, preview: false }); + assert!(page.error.is_none(), "the page is found: {:?}", page.error); + assert_eq!((page.width, page.height), (300, 150), "`3 0 R` reads the later body, as `3 1` does"); +} + +/// A file whose cross-reference table has to be rebuilt keeps an object whose header names a +/// generation the reference does not. +/// +/// `poppler-85140-0.pdf` is 340 bytes with no table at all, and its one page's header reads +/// `3 18446744073709551616 obj` while the page tree points at `3 0 R`. Before #427 the digits +/// wrapped, and 2^64 wrapped to exactly 0, so the header read as `3 0 obj` and the file opened by +/// accident; once an overflowing integer became a real the object was unreachable and the file +/// stopped opening at all, which `cargo xtask check` reports as a regression (#5580). +/// +/// A rebuilt table has no revision history to tell two generations of an object apart -- the scan +/// already files objects found in object streams under generation 0 -- so the object number is +/// what identifies one. A readable generation that simply is not the one referenced +/// (`3 99999 obj`) was lost the same way, and is covered here too. +#[cfg_attr(target_arch = "wasm32", wasm_bindgen_test::wasm_bindgen_test)] +#[cfg_attr(not(target_arch = "wasm32"), test)] +fn a_rebuilt_table_finds_an_object_whose_header_names_another_generation() { + for generation in [ + // The generation the reference names, which always worked. + "0", + // One that reads as an integer but is not the one referenced. + "99999", + // And one no generation may be: 2^64, which is what the reported file carries. A + // generation number is at most 65,535 (ISO 32000-2 §7.5.4). + "18446744073709551616", + ] { + // No table and no `startxref`, so the objects are recovered by scanning the file. + let pdf = format!( + "%PDF-1.4\n\ + 1 0 obj << /Type /Catalog /Pages 2 0 R >> endobj\n\ + 2 0 obj << /Type /Pages /Kids [3 0 R] /Count 1 >> endobj\n\ + 3 {generation} obj << /Type /Page /Parent 2 0 R /MediaBox [0 0 200 100] >> endobj\n\ + trailer << /Root 1 0 R >>\n\ + %%EOF\n" + ); + let mut r = PageRenderer::new(Arc::new(pdf.into_bytes()), RenderConfig::default()); + let page = r.render(RenderRequest { page: 0, kind: RequestKind::Pixels, tile: None, scale: 1.0, tag: 0, preview: false }); + assert!(page.error.is_none(), "generation {generation}: the page is found: {:?}", page.error); + assert_eq!((page.width, page.height), (200, 100), "generation {generation}: and it is the page's own size"); + } + + // A stray number before a header (`42 3 0 obj`) is not a header, and must not cost the one + // after it: the lenient read leaves the scan where it was when it fails (noted in review). + let pdf = "%PDF-1.4\n\ + 1 0 obj << /Type /Catalog /Pages 2 0 R >> endobj\n\ + 2 0 obj << /Type /Pages /Kids [3 0 R] /Count 1 >> endobj\n\ + 42 3 0 obj << /Type /Page /Parent 2 0 R /MediaBox [0 0 200 100] >> endobj\n\ + trailer << /Root 1 0 R >>\n\ + %%EOF\n"; + let mut r = PageRenderer::new(Arc::new(pdf.to_string().into_bytes()), RenderConfig::default()); + let page = r.render(RenderRequest { page: 0, kind: RequestKind::Pixels, tile: None, scale: 1.0, tag: 0, preview: false }); + assert!(page.error.is_none(), "the header after a stray number is found: {:?}", page.error); + assert_eq!((page.width, page.height), (200, 100)); +} + /// #3109 / #3116: clipping-only text (`7 Tr`) installs a clip for subsequent painting /// but draws no pixels itself. #[test] diff --git a/crates/render/src/structure.rs b/crates/render/src/structure.rs index bf9c16e23f..effbc87d92 100644 --- a/crates/render/src/structure.rs +++ b/crates/render/src/structure.rs @@ -187,9 +187,20 @@ fn convert_dict(dict: &pdfcraft_cos::Dict, depth: usize) -> Result { if depth > 100 { return Err(Error::RecursionLimit); } - dict.iter().map(|(key, value)| Ok((key.clone(), convert(value, depth + 1)?))).collect::>>().map(|items| items.into_iter().collect()) + dict.iter() + .filter(|(key, _)| key.as_slice() != PRIVATE_DATA) + .map(|(key, value)| Ok((key.clone(), convert(value, depth + 1)?))) + .collect::>>() + .map(|items| items.into_iter().collect()) } +/// `/PieceInfo`: an application's private data about a page, form or document (ISO 32000-1 +/// §14.5), left out of what inspection keeps. Nothing here reads it, and every object read is +/// kept converted for the inspection's lifetime: InDesign writes kilobytes of it into every page, +/// and a 1,412-page book held over a gigabyte of it (#5873). The file and the editing document are +/// untouched; this is the read-only view inspection walks. +const PRIVATE_DATA: &[u8] = b"PieceInfo"; + fn convert(object: &CosObject, depth: usize) -> Result { if depth > 100 { return Err(Error::RecursionLimit); diff --git a/crates/ui-egui/src/app.rs b/crates/ui-egui/src/app.rs index c326b479fe..6ac8ea8783 100644 --- a/crates/ui-egui/src/app.rs +++ b/crates/ui-egui/src/app.rs @@ -99,6 +99,7 @@ impl PdfCraftApp { #[cfg(target_os = "linux")] desktop_theme_enabled: false, scroll_speed: scroll_speed::ScrollSpeed::default(), + invert_middle_drag: false, animation_effects: motion::AnimationEffects::default(), motion: motion::Motion::default(), language: i18n::AUTO.to_string(), diff --git a/crates/ui-egui/src/app/control.rs b/crates/ui-egui/src/app/control.rs index e4078efd13..0309042bf1 100644 --- a/crates/ui-egui/src/app/control.rs +++ b/crates/ui-egui/src/app/control.rs @@ -50,6 +50,9 @@ impl PdfCraftApp { ("scroll_speed", _) => { self.scroll_speed = scroll_speed::ScrollSpeed::parse(value).ok_or("scroll_speed must be slow, normal, or fast")?; } + ("invert_middle_drag", _) => { + self.invert_middle_drag = value.parse::().map_err(|_| "invert_middle_drag must be true or false")?; + } ("animation_effects", _) => { self.animation_effects = motion::AnimationEffects::parse(value).ok_or("animation_effects must be system, on, or off")?; } diff --git a/crates/ui-egui/src/app/prefs.rs b/crates/ui-egui/src/app/prefs.rs index 7eddee0af0..08a20afb45 100644 --- a/crates/ui-egui/src/app/prefs.rs +++ b/crates/ui-egui/src/app/prefs.rs @@ -89,6 +89,7 @@ impl PdfCraftApp { "pinned_folders": self.pinned.folders, "theme": self.theme_preference, "scroll_speed": self.scroll_speed, + "invert_middle_drag": self.invert_middle_drag, "animation_effects": self.animation_effects, "default_mode": self.default_mode, "default_layout": canvas::display_token(self.view_defaults.layout, self.view_defaults.continuous), @@ -159,6 +160,9 @@ impl PdfCraftApp { pub fn restore(&mut self, json: &str) { let Ok(v) = serde_json::from_str::(json) else { return }; if let Ok(mut bar) = serde_json::from_value::(v["hotbar"].clone()) { + if v["hotbar"].get("placed").is_none() { + bar.adopt_legacy(); + } bar.normalize(); self.hotbar = bar; } @@ -237,6 +241,9 @@ impl PdfCraftApp { if let Ok(speed) = serde_json::from_value::(v["scroll_speed"].clone()) { self.scroll_speed = speed; } + if let Some(invert) = v["invert_middle_drag"].as_bool() { + self.invert_middle_drag = invert; + } if let Ok(effects) = serde_json::from_value::(v["animation_effects"].clone()) { self.animation_effects = effects; } diff --git a/crates/ui-egui/src/canvas.rs b/crates/ui-egui/src/canvas.rs index a220644421..49d2c44b03 100644 --- a/crates/ui-egui/src/canvas.rs +++ b/crates/ui-egui/src/canvas.rs @@ -18,8 +18,8 @@ use crate::theme::{self, Tokens}; use crate::{PdfCraftApp, QuickTool, RightPanel, comments, icons, widgets}; mod area; -pub(super) mod autoscroll; -mod bars; +pub(crate) mod autoscroll; +pub(crate) mod bars; mod cache; pub(super) mod crop; mod find; @@ -253,6 +253,22 @@ impl ImageObb { } } +/// Whether pointer `p` is on an image being cropped, its crop box or its handles (#5835). +pub(crate) fn crop_contains_point( + img: &pdfcraft_engine::PageImage, + crop: &crate::edit_text_ui::CropMode, + xf: &PageXform, + info: &DocInfo, + page: usize, + p: Pos2, +) -> bool { + let obb = ImageObb::from_image(img, xf, info, page); + let full_obb = ImageObb::from_matrix(img.matrix, xf, info, page); + crate::edit_text_ui::quad_contains(obb.corners(), p) + || crate::edit_text_ui::quad_contains(full_obb.corners(), p) + || crate::edit_text_ui::crop_controls_contain(img, crop, xf, info, page, p) +} + /// The page display as it was before full screen, put back on leaving it /// ([`DocView::enter_presentation`]). #[derive(Clone, Copy, Debug, PartialEq)] @@ -551,6 +567,8 @@ pub struct DocView { /// Screen rects of the pages drawn last frame (hit-testing, tests, automation). screen_rects: Vec<(usize, Rect)>, screen_xforms: Vec<(usize, PageXform)>, + /// Pixels per point last frame, for telling a rounding sliver of a page from a visible one. + screen_ppp: f32, /// The scroll viewport on screen last frame. viewport_screen: Rect, /// Pending zoom anchor: page, fractional position (also in gutters), and viewport offset. @@ -936,6 +954,7 @@ impl DocView { page_heights: info.pages.iter().map(|p| p.height).collect(), screen_rects: Vec::new(), screen_xforms: Vec::new(), + screen_ppp: 1.0, viewport_screen: Rect::NOTHING, zoom_anchor: None, shown: false, @@ -2401,6 +2420,7 @@ fn draw_pages( let origin = resp_rect.min - vec2(0.0, y_shift); let visible = viewport.translate(resp_rect.min.to_vec2()); view.screen_rects.clear(); + view.screen_ppp = ui.ctx().pixels_per_point(); view.screen_xforms.clear(); // The pointer as the pages see it: nothing over them (a dialog from the frame it opens), // or a press they hold. The page modules read it rather than egui's raw pointer state. @@ -2437,10 +2457,23 @@ fn draw_pages( let xf = PageXform { rect: r, rot: view.rotation, pw: info.pages[page_idx].width.max(1.0), ph: info.pages[page_idx].height.max(1.0) }; let images = cached_edit_images(view, doc, page_idx).to_vec(); + // Crop controls own the click even when another image overlaps them. + if view.image_selection.as_ref().is_some_and(|s| { + s.page == page_idx + && s.crop + .as_ref() + .zip(images.get(s.index)) + .is_some_and(|(crop, img)| crop_contains_point(img, crop, &xf, info, page_idx, p)) + }) { + over_image = true; + break; + } for (idx, img) in images.iter().enumerate().rev() { let obb = ImageObb::from_image(img, &xf, info, page_idx); let b = image_screen_rect(img, &xf, info, page_idx); - if obb.contains(b, p) { + let selected_crop = view.image_selection.as_ref().is_some_and(|s| s.page == page_idx && s.index == idx && s.crop.is_some()); + let hit = if selected_crop { crate::edit_text_ui::quad_contains(obb.corners(), p) } else { obb.contains(b, p) }; + if hit { over_image = true; if view.image_selection.as_ref().is_none_or(|s| s.page != page_idx || s.index != idx) { view.image_selection = Some(crate::edit_text_ui::ImageSelection::at(page_idx, idx)); @@ -2553,6 +2586,22 @@ fn draw_pages( view.current = current; } resp.context_menu(|ui| { + let is_crop_over_image = tool == QuickTool::EditText + && view.image_selection.clone().is_some_and(|sel| { + let Some(ref crop) = sel.crop else { return false }; + let pointer_pos = ptr.pos; + let Some(p) = pointer_pos else { return false }; + let Some((_, xf)) = view.screen_xforms.iter().find(|(page_idx, _)| *page_idx == sel.page).cloned() else { return false }; + let images = cached_edit_images(view, doc, sel.page).to_vec(); + let Some(img) = images.get(sel.index) else { return false }; + crop_contains_point(img, crop, &xf, info, sel.page, p) + }); + if is_crop_over_image { + ui.ctx().data_mut(|d| d.insert_temp(crate::edit_text_ui::image_menu_id(), false)); + egui::Popup::close_all(ui.ctx()); + ui.close(); + return; + } // Preparing a form: the selected field's menu. if preparing && let Some((name, wi)) = view.prepare.selected.clone() { // Several fields: Align, Center, Distribute, Set Fields to Same Size. @@ -3334,9 +3383,9 @@ fn pinch_zoom(ui: &egui::Ui, view: &mut DocView, zoom_delta: f32, navigation_rec /// The middle-button auto-scroll's delta, and the edge scroll a drawing in progress asks for: the /// pointer in a band along any edge (or just past it) scrolls the view that way, so a point /// beyond what is shown can be reached without letting go of the tool. -fn auto_scroll_deltas(ui: &egui::Ui, view: &mut DocView, avail: Rect, unobstructed: bool) -> (Vec2, Vec2) { +fn auto_scroll_deltas(ui: &egui::Ui, view: &mut DocView, avail: Rect, unobstructed: bool, invert: bool) -> (Vec2, Vec2) { let auto_delta = if unobstructed { - view.auto_scroll.update(ui, avail, false) + view.auto_scroll.update(ui, avail, false, invert) } else { view.auto_scroll.cancel(); Vec2::ZERO @@ -3513,11 +3562,12 @@ pub fn document_area(app: &mut PdfCraftApp, index: usize, ui: &mut egui::Ui) { let modal = app.modal_open(); let unobstructed = !modal && !app.palette_open; let organize_zoom = app.organize_zoom; + let invert_middle = app.invert_middle_drag; let view = &mut app.views[index]; if view.organize { // One remembered grid size for every document, kept in the settings. view.set_grid_zoom(organize_zoom); - organize_grid(view, doc, unobstructed, app.show_page_edge_shadows, ui, &t); + organize_grid(view, doc, unobstructed, app.show_page_edge_shadows, invert_middle, ui, &t); app.organize_zoom = view.grid_zoom(); return; } @@ -3537,7 +3587,7 @@ pub fn document_area(app: &mut PdfCraftApp, index: usize, ui: &mut egui::Ui) { let present = presentation_click_state(ui, view, navigation_rect, navigation_enabled && app.quick_tool == QuickTool::Select); pinch_zoom(ui, view, zoom_delta, navigation_rect, navigation_enabled); view.viewport_screen = avail; - let (auto_delta, edge_delta) = auto_scroll_deltas(ui, view, avail, unobstructed); + let (auto_delta, edge_delta) = auto_scroll_deltas(ui, view, avail, unobstructed, invert_middle); let content_w = view.content_width(info, avail.width()); let rects = view.layout(info, content_w, ui.ctx().pixels_per_point()); @@ -4055,8 +4105,9 @@ fn apply_frame_requests(app: &mut PdfCraftApp, index: usize, ui: &mut egui::Ui, // Read mode hides the tools (#2646), and full screen is the page and nothing else (#1459); // the quick tools come back with the window. if app.mode != crate::Mode::Read && !app.full_screen { - quick_bar(app, avail, ui); - crate::hotbar::show(app, avail, ui.ctx()); + // The page nearest the left edge, whose margin the bar sits in. + let page_left = app.views[index].screen_rects.iter().map(|(_, r)| r.left()).reduce(f32::min); + quick_bar(app, avail, page_left, ui); } if let Some((source, file, destination)) = remote_open { app.open_remote_link(source, file, destination); diff --git a/crates/ui-egui/src/canvas/autoscroll.rs b/crates/ui-egui/src/canvas/autoscroll.rs index 14751ffc5c..1f4cd62c5d 100644 --- a/crates/ui-egui/src/canvas/autoscroll.rs +++ b/crates/ui-egui/src/canvas/autoscroll.rs @@ -46,15 +46,18 @@ impl AutoScroll { } /// Run before the document's widgets. Starting is restricted to the unobstructed viewport; - /// once started, moving outside that viewport still controls the speed. - pub(crate) fn update(&mut self, ui: &egui::Ui, viewport: egui::Rect, organize: bool) -> Vec2 { - self.update_for_platform(ui, viewport, organize, cfg!(target_os = "linux")) + /// once started, moving outside that viewport still controls the speed. `invert` is + /// Preferences ▸ Invert middle-button drag: the returned delta scrolls the other way. + pub(crate) fn update(&mut self, ui: &egui::Ui, viewport: egui::Rect, organize: bool, invert: bool) -> Vec2 { + self.update_for_platform(ui, viewport, organize, cfg!(target_os = "linux"), invert) } - fn update_for_platform(&mut self, ui: &egui::Ui, viewport: egui::Rect, organize: bool, supported: bool) -> Vec2 { - if !supported { - return self.update_drag(ui, viewport); - } + fn update_for_platform(&mut self, ui: &egui::Ui, viewport: egui::Rect, organize: bool, supported: bool, invert: bool) -> Vec2 { + let delta = if supported { self.update_latched(ui, viewport, organize) } else { self.update_drag(ui, viewport) }; + oriented(delta, invert) + } + + fn update_latched(&mut self, ui: &egui::Ui, viewport: egui::Rect, organize: bool) -> Vec2 { let ctx = ui.ctx(); let (pointer, middle_press, middle_down, middle_released, cancel, cancel_button, dt) = ctx.input(|i| { let cancel_button = [PointerButton::Primary, PointerButton::Secondary, PointerButton::Extra1, PointerButton::Extra2] @@ -237,6 +240,11 @@ pub(crate) fn edge_delta(y: f32, viewport: egui::Rect, dt: f32) -> f32 { -distance.clamp(-MAX_DISPLACEMENT, MAX_DISPLACEMENT) * EDGE_SPEED * dt.clamp(0.0, 0.05) } +/// The middle button's delta, reversed when the user inverted it. +fn oriented(delta: Vec2, invert: bool) -> Vec2 { + if invert { -delta } else { delta } +} + fn scroll_delta(displacement: f32, dt: f32) -> f32 { if !displacement.is_finite() || !dt.is_finite() { return 0.0; @@ -261,10 +269,15 @@ mod tests { /// Run one frame of the non-Linux path; `check` sees the pan delta inside the frame. fn drag_frame(ctx: &Context, scroll: &mut AutoScroll, events: Vec, focused: bool, check: impl Fn(&AutoScroll, Vec2)) { + frame(ctx, scroll, events, focused, (false, false), check); + } + + /// Run one frame; `mode` is (latched auto-scroll supported, inverted). + fn frame(ctx: &Context, scroll: &mut AutoScroll, events: Vec, focused: bool, mode: (bool, bool), check: impl Fn(&AutoScroll, Vec2)) { let mut output = ctx.run_ui( egui::RawInput { screen_rect: Some(egui::Rect::from_min_size(Pos2::ZERO, vec2(400.0, 400.0))), events, focused, ..Default::default() }, |ui| { - let delta = scroll.update_for_platform(ui, ui.max_rect(), false, false); + let delta = scroll.update_for_platform(ui, ui.max_rect(), false, mode.0, mode.1); check(scroll, delta); }, ); @@ -272,6 +285,40 @@ mod tests { output.textures_delta.clear(); } + /// The pan delta after pressing at `p` and moving the pointer by `by`. + fn pan_by(by: Vec2, invert: bool) -> Vec2 { + let (ctx, mut scroll, p) = (Context::default(), AutoScroll::default(), egui::pos2(100.0, 100.0)); + frame(&ctx, &mut scroll, vec![], true, (false, invert), |_, _| {}); + frame(&ctx, &mut scroll, vec![Event::PointerMoved(p), middle(p, true)], true, (false, invert), |_, _| {}); + let moved = std::cell::Cell::new(Vec2::ZERO); + frame(&ctx, &mut scroll, vec![Event::PointerMoved(p + by)], true, (false, invert), |_, d| moved.set(d)); + moved.get() + } + + /// The auto-scroll delta in the frame after latching at `p`, with the pointer `dy` below it. + fn latched_by(dy: f32, invert: bool) -> Vec2 { + let (ctx, mut scroll, p) = (Context::default(), AutoScroll::default(), egui::pos2(100.0, 100.0)); + frame(&ctx, &mut scroll, vec![], true, (true, invert), |_, _| {}); + frame(&ctx, &mut scroll, vec![Event::PointerMoved(p), middle(p, true), middle(p, false)], true, (true, invert), |_, _| {}); + let moved = std::cell::Cell::new(Vec2::ZERO); + frame(&ctx, &mut scroll, vec![Event::PointerMoved(p + vec2(0.0, dy))], true, (true, invert), |s, d| { + assert!(s.active(), "the click latched auto-scroll"); + moved.set(d); + }); + moved.get() + } + + #[test] + fn inverting_the_middle_button_reverses_the_pan_and_the_auto_scroll() { + let by = vec2(-30.0, 40.0); + assert_eq!(pan_by(by, false), by, "by default the page follows the pointer"); + assert_eq!(pan_by(by, true), -by, "inverted, the view moves the way the pointer goes"); + let (normal, inverted) = (latched_by(60.0, false), latched_by(60.0, true)); + assert!(normal.y < 0.0, "by default, below the anchor scrolls down: {normal:?}"); + assert_eq!(inverted, -normal, "inverted, the same distance scrolls the other way"); + assert_eq!(latched_by(10.0, true), Vec2::ZERO, "the dead zone still holds still"); + } + #[test] fn middle_drag_pans_one_to_one_and_owns_the_button_until_release() { let ctx = Context::default(); diff --git a/crates/ui-egui/src/canvas/bars.rs b/crates/ui-egui/src/canvas/bars.rs index 4ad2bf05db..dd3fe8c498 100644 --- a/crates/ui-egui/src/canvas/bars.rs +++ b/crates/ui-egui/src/canvas/bars.rs @@ -1,7 +1,4 @@ -use super::{ - Color32, CornerRadius, DocInfo, DocView, Edit, PdfCraftApp, Pos2, QuickTool, Rect, Sense, SnapshotKind, Stroke, Tokens, comments, icons, theme, - vec2, -}; +use super::{Color32, CornerRadius, DocInfo, DocView, PdfCraftApp, Pos2, Rect, Sense, SnapshotKind, Stroke, Tokens, icons, vec2}; /// Whether `p` lies in the bottom-left quadrant of `area`, where the page size shows (#1855). pub(super) fn in_size_hint_zone(area: Rect, p: Pos2) -> bool { @@ -276,237 +273,57 @@ fn notice_bar(ui: &mut egui::Ui, t: &Tokens, icon: &str, icon_color: Color32, te }); } -/// The floating quick-action bar at the left edge of the document area. -pub(super) fn quick_bar(app: &mut PdfCraftApp, area: Rect, ui: &mut egui::Ui) { - let t = Tokens::get(ui.ctx()); - let mut offset = vec2(0.0, 0.0); - if app.hotbar.full_side { - match app.hotbar.dock.as_deref() { - Some("left") => offset.x += app.hotbar.button_size + 14.0, - Some("top") => offset.y += app.hotbar.button_size + 14.0, - _ => {} +/// The bar's narrowest form: one 32 pt button, 6 pt margins and a 1 pt border each side. +pub(crate) const QUICK_BAR_WIDTH: f32 = 46.0; +pub(crate) const QUICK_BAR_EDGE: f32 = 14.0; + +/// How far from the side panel the quick-action bar stands, given the width of the margin between +/// the panel and the page and the bar's own width: centred in the margin when it holds the bar, +/// else 14 pt in (a page filling the width). With no page on screen the caller passes a margin of 0, +/// which is 14 pt too. +pub(crate) fn quick_bar_offset(margin: f32, width: f32) -> f32 { + // shortcut: centred in at most 100 pt of margin, so a wide margin keeps the bar by the panel. + // `f32::min` returns the other operand for NaN, which would pass the fit check below. + let margin = if margin.is_nan() { 0.0 } else { margin.min(100.0) }; + if margin >= width + 2.0 * 8.0 { (margin - width) / 2.0 } else { QUICK_BAR_EDGE } +} + +/// The unified quick-action bar and hotbar in the margin or docked to an edge. +pub(super) fn quick_bar(app: &mut PdfCraftApp, area: Rect, page_left: Option, ui: &mut egui::Ui) { + crate::hotbar::show(app, area, page_left, ui); +} + +#[cfg(test)] +mod tests { + use super::quick_bar_offset; + + #[test] + fn the_quick_bar_centres_in_the_margin_that_holds_it() { + assert_eq!(quick_bar_offset(72.0, 46.0), 13.0); + assert_eq!(quick_bar_offset(62.0, 46.0), 8.0); + // A wide margin centres in its first 100 pt, not all of it. + assert_eq!(quick_bar_offset(400.0, 46.0), 27.0); + } + + #[test] + fn the_margin_that_just_holds_the_bar_centres_and_a_point_less_does_not() { + // 46 pt of bar and 8 pt to spare each side: 62 pt. + assert_eq!(quick_bar_offset(62.0, 46.0), 8.0); + assert_eq!(quick_bar_offset(61.0, 46.0), 14.0); + assert_eq!(quick_bar_offset(1000.0, 46.0), 27.0); + } + + #[test] + fn a_wider_quick_bar_centres_by_its_own_width_and_needs_a_wider_margin() { + // Fill & Sign's Text tool widens the bar to 70 pt: it centres by that, and 72 pt no longer holds it. + assert_eq!(quick_bar_offset(120.0, 70.0), 15.0); + assert_eq!(quick_bar_offset(72.0, 70.0), 14.0); + } + + #[test] + fn the_quick_bar_keeps_14_pt_in_when_the_margin_cannot_hold_it() { + for margin in [61.9, 30.0, 0.0, -50.0, f32::NEG_INFINITY, f32::NAN] { + assert_eq!(quick_bar_offset(margin, 46.0), 14.0, "{margin}"); } } - let pos = area.left_top() + vec2(14.0, 14.0) + offset; - egui::Area::new(egui::Id::unique("quick-bar")).order(egui::Order::Middle).fixed_pos(pos).show(ui.ctx(), |ui| { - egui::Frame::NONE - .fill(t.card) - .stroke(Stroke::new(1.0, t.border)) - .corner_radius(CornerRadius::same(12)) - .shadow(egui::Shadow { offset: [0, 4], blur: 16, spread: 0, color: Color32::from_black_alpha(if t.dark() { 100 } else { 28 }) }) - .inner_margin(egui::Margin::same(6)) - .show(ui, |ui| { - ui.spacing_mut().item_spacing.y = 2.0; - ui.vertical(|ui| { - if icons::button(ui, "mouse-pointer-2", 32.0, app.quick_tool == QuickTool::Select, tl!("Select (V)")).clicked() { - app.quick_tool = QuickTool::Select; - } - if icons::button(ui, "hand", 32.0, app.quick_tool == QuickTool::Hand, tl!("Hand (H)")).clicked() { - app.quick_tool = QuickTool::Hand; - } - // Comment ▸, Highlight ▸, Draw ▸ (Acrobat's comment toolbar groups). Clicking a - // group selects its last-used tool; clicking it again opens the flyout. - for g in 0..comments::GROUPS.len() { - let current = app.comment_prefs.group_tool[g]; - let active = matches!(app.quick_tool, QuickTool::Comment(t) if t.group() == g); - let resp = icons::button(ui, current.icon(), 32.0, active, tl!(current.label())); - if comments::GROUPS[g].len() == 1 { - if resp.clicked() { - app.execute(current.command()); - } - continue; - } - // A small corner triangle marks the flyout. - let r = resp.rect; - let tri = [r.right_bottom() + vec2(-4.0, -4.0), r.right_bottom() + vec2(-9.0, -4.0), r.right_bottom() + vec2(-4.0, -9.0)]; - ui.painter().add(egui::Shape::convex_polygon(tri.to_vec(), if active { t.accent } else { t.text_faint }, Stroke::NONE)); - let open = (resp.clicked() && active) || resp.secondary_clicked(); - if resp.clicked() && !active { - app.execute(current.command()); - } - egui::Popup::menu(&resp) - .open_memory(open.then_some(egui::SetOpenCommand::Toggle)) - .align(egui::RectAlign::RIGHT_START) - .gap(6.0) - .show(|ui| { - for tool in comments::GROUPS[g] { - let on = app.quick_tool == QuickTool::Comment(*tool); - let (row, click) = ui.allocate_exact_size(vec2(180.0, 28.0), Sense::click()); - let press = theme::Press::track(ui, &click); - press.wash(ui, row, 4, on); - let body = row.translate(press.offset()); - icons::paint(ui, Rect::from_min_size(body.min + vec2(8.0, 6.0), vec2(16.0, 16.0)), tool.icon(), 16.0, t.text); - let reserve = if on { 28.0 } else { 8.0 }; - crate::widgets::paint_left( - ui, - body.left_center() + vec2(34.0, 0.0), - tl!(tool.label()), - theme::regular(13.0), - t.text, - (row.width() - 34.0 - reserve).max(0.0), - ); - if on { - icons::paint( - ui, - Rect::from_min_size(body.right_top() + vec2(-24.0, 7.0), vec2(14.0, 14.0)), - "check", - 14.0, - t.accent, - ); - } - let click = theme::hand(click); - let info = tl!(tool.label()).to_string(); - click.widget_info(|| egui::WidgetInfo::selected(egui::Role::Button, true, on, info.clone())); - if click.clicked() { - app.execute(tool.command()); - ui.close(); - } - } - }); - } - // Edit text & images, while the Edit workspace is open (Acrobat's Edit toolbar) - // or the tool is in use. - if app.mode == crate::Mode::Edit || app.quick_tool == QuickTool::EditText { - let on = app.quick_tool == QuickTool::EditText; - if icons::button(ui, "text-cursor-input", 32.0, on, tl!("Edit text & images")).clicked() { - if on { - app.put_down_edit_text(); - } else { - app.quick_tool = QuickTool::EditText; - } - } - } - // Fill & Sign ▸ (text, marks, date, signature). - let current_fill = match app.quick_tool { - QuickTool::Fill(f) => Some(f), - _ => None, - }; - let shown = current_fill.unwrap_or(crate::fill_sign::FillTool::Text); - let resp = icons::button( - ui, - if current_fill.is_some() { shown.icon() } else { "pen-line" }, - 32.0, - current_fill.is_some(), - tl!("Fill & Sign"), - ); - let r = resp.rect; - let tri = [r.right_bottom() + vec2(-4.0, -4.0), r.right_bottom() + vec2(-9.0, -4.0), r.right_bottom() + vec2(-4.0, -9.0)]; - ui.painter().add(egui::Shape::convex_polygon( - tri.to_vec(), - if current_fill.is_some() { t.accent } else { t.text_faint }, - Stroke::NONE, - )); - if resp.clicked() && current_fill.is_none() { - app.execute(shown.command()); - } - let open = (resp.clicked() && current_fill.is_some()) || resp.secondary_clicked(); - egui::Popup::menu(&resp) - .open_memory(open.then_some(egui::SetOpenCommand::Toggle)) - .align(egui::RectAlign::RIGHT_START) - .gap(6.0) - .show(|ui| { - for tool in crate::fill_sign::FILL_TOOLS { - if matches!(tool, crate::fill_sign::FillTool::Signature | crate::fill_sign::FillTool::Initials) { - continue; - } - let on = current_fill == Some(tool); - let (row, click) = ui.allocate_exact_size(vec2(180.0, 28.0), Sense::click()); - let press = theme::Press::track(ui, &click); - press.wash(ui, row, 4, on); - let body = row.translate(press.offset()); - icons::paint(ui, Rect::from_min_size(body.min + vec2(8.0, 6.0), vec2(16.0, 16.0)), tool.icon(), 16.0, t.text); - let reserve = if on { 28.0 } else { 8.0 }; - crate::widgets::paint_left( - ui, - body.left_center() + vec2(34.0, 0.0), - tl!(tool.label()), - theme::regular(13.0), - t.text, - (row.width() - 34.0 - reserve).max(0.0), - ); - if on { - icons::paint( - ui, - Rect::from_min_size(body.right_top() + vec2(-24.0, 7.0), vec2(14.0, 14.0)), - "check", - 14.0, - t.accent, - ); - } - let click = theme::hand(click); - let info = tl!(tool.label()).to_string(); - click.widget_info(|| egui::WidgetInfo::selected(egui::Role::Button, true, on, info.clone())); - if click.clicked() { - app.execute(tool.command()); - ui.close(); - } - } - ui.separator(); - if let Some(command) = crate::fill_sign::signature_entries(ui, app, &t) { - app.execute(command); - ui.close(); - } - }); - if matches!(current_fill, Some(crate::fill_sign::FillTool::Text | crate::fill_sign::FillTool::Date)) { - ui.label(tl!("Font size:")); - let size = ui.add( - egui::DragValue::new(&mut app.fill_text_size) - .range(crate::fill_sign::MIN_TEXT_SIZE..=crate::fill_sign::MAX_TEXT_SIZE) - .speed(0.25) - .suffix(" pt"), - ); - // #1274: the size also applies to the Fill & Sign text that is selected, - // once per change (a typed value, or the end of a drag), so a drag adds - // one undo step and not one per frame. - if ((size.changed() && !size.dragged()) || size.drag_stopped()) - && let Some((index, id)) = app.active_ids() - && let Some((page, annotation)) = app.views.get(index).and_then(|view| view.comments.selected) - && app.session.get(id).is_some_and(|doc| { - doc.allows_annotation() - && doc - .info - .annotations - .iter() - .any(|a| a.page == page && a.index == annotation && a.fill_sign && a.subtype == "FreeText" && !a.locked) - }) - { - app.apply_edit(Edit::FontSizeAnnotation { page, index: annotation, size: app.fill_text_size }); - } - } - if matches!(current_fill, Some(crate::fill_sign::FillTool::Text | crate::fill_sign::FillTool::Date)) { - ui.menu_button(tl!("Colour"), |ui| { - if let Some(color) = comments::swatch_grid(ui, Some(app.fill_text_color)) { - app.fill_text_color = color; - ui.close(); - } - }); - } - if let QuickTool::Comment(tool) = app.quick_tool { - let (r, _) = ui.allocate_exact_size(vec2(32.0, 9.0), Sense::hover()); - ui.painter().hline(r.x_range().shrink(6.0), r.center().y, Stroke::new(1.0, t.divider)); - if let Some(color) = comments::quick_bar_controls(ui, tool, &mut app.comment_prefs) - && let Some((index, id)) = app.active_ids() - && let Some((page, annotation)) = app.views.get(index).and_then(|view| view.comments.selected) - && app.session.get(id).is_some_and(|doc| { - doc.allows_annotation() - && doc - .info - .annotations - .iter() - .any(|a| a.page == page && a.index == annotation && !a.is_reply() && comments::made_by(a, tool)) - }) - { - app.apply_edit(Edit::StyleAnnotation { - page, - index: annotation, - color: Some(color), - opacity: None, - width: None, - endings: None, - }); - } - } - }); - }); - }); } diff --git a/crates/ui-egui/src/canvas/navigation.rs b/crates/ui-egui/src/canvas/navigation.rs index 731b2c2586..bc98a243fa 100644 --- a/crates/ui-egui/src/canvas/navigation.rs +++ b/crates/ui-egui/src/canvas/navigation.rs @@ -9,6 +9,11 @@ impl DocView { /// zoom are kept). `None` before the first frame has laid pages out, when the bookmark just /// goes to the current page. pub(crate) fn bookmark_position(&self, info: &DocInfo) -> Option<(usize, [Option; 2])> { + // The page grid moves the viewport without refreshing where the pages are on screen, so + // there is no position to read: the bookmark goes to the current page. + if self.organize { + return None; + } if let Some(sel) = self.selection && let Some(text) = self.texts.get(&sel.page) && let Some(p) = info.pages.get(sel.page) @@ -32,11 +37,17 @@ impl DocView { // of pages of different heights, whose shorter page can start below it), else the // nearest one below. let top = self.viewport_screen.top(); - let showing = || self.screen_xforms.iter().filter(|(_, xf)| xf.rect.bottom() > top); - let (page, xf) = showing() - .filter(|(_, xf)| xf.rect.top() <= top) - .min_by_key(|(p, _)| *p) - .or_else(|| showing().min_by(|a, b| a.1.rect.top().total_cmp(&b.1.rect.top()).then(a.0.cmp(&b.0))))?; + // A page showing less than a pixel is rounding, not what the reader is looking at: a jump + // to the next page leaves the previous one's bottom edge within a pixel of the top. Such a + // sliver still counts when nothing else shows (the last page at the very end). + let pick = |slack: f32| { + let showing = || self.screen_xforms.iter().filter(move |(_, xf)| xf.rect.bottom() > top + slack); + showing() + .filter(|(_, xf)| xf.rect.top() <= top) + .min_by_key(|(p, _)| *p) + .or_else(|| showing().min_by(|a, b| a.1.rect.top().total_cmp(&b.1.rect.top()).then(a.0.cmp(&b.0)))) + }; + let (page, xf) = pick(sliver(self.screen_ppp)).or_else(|| pick(0.0))?; let p = info.pages.get(*page)?; // Above the page (in the gap before it) is the page's own top. The window's vertical is // the view's y, or its x when the view is turned a quarter. @@ -268,7 +279,11 @@ impl DocView { let Some(forward) = self.wheel.feed(unit, dy, phase, now, can_turn) else { return false }; let before = self.current; self.step_page(forward); - self.current != before + if self.current == before { + self.wheel.unturn(); + return false; + } + true } /// One wheel event in a non-continuous view whose page is taller than the window, where the @@ -288,6 +303,7 @@ impl DocView { let before = self.current; self.step_page(forward); if self.current == before { + self.wheel.unturn(); return false; } if !forward { @@ -454,3 +470,23 @@ pub fn shortcuts(view: &mut DocView, ctx: &egui::Context, speed: crate::scroll_s /// How far ↓ / ↑ scroll at Normal speed (Scroll speed halves or doubles it). Page Down / Page Up /// keep this much of the previous screen in view. const KEY_SCROLL_LINE: f32 = 40.0; +/// How much of a page must show at the window's top edge to count as the page there, in points: one +/// physical pixel, since page rectangles snap to whole pixels and less is rounding. +fn sliver(pixels_per_point: f32) -> f32 { + if pixels_per_point.is_finite() && pixels_per_point > 0.0 { 1.0 / pixels_per_point } else { 1.0 } +} + +#[cfg(test)] +mod tests { + use super::sliver; + + #[test] + fn a_sliver_is_one_physical_pixel() { + assert_eq!(sliver(1.0), 1.0); + assert_eq!(sliver(2.0), 0.5); + assert_eq!(sliver(0.5), 2.0); + for bad in [0.0, -1.0, f32::NAN, f32::INFINITY] { + assert_eq!(sliver(bad), 1.0, "{bad}"); + } + } +} diff --git a/crates/ui-egui/src/canvas/organize.rs b/crates/ui-egui/src/canvas/organize.rs index 48c7e82d8f..25c99543e4 100644 --- a/crates/ui-egui/src/canvas/organize.rs +++ b/crates/ui-egui/src/canvas/organize.rs @@ -272,6 +272,7 @@ pub(super) fn organize_grid( doc: &pdfcraft_engine::Document, unobstructed: bool, show_page_edge_shadows: bool, + invert_middle: bool, ui: &mut egui::Ui, t: &Tokens, ) { @@ -288,7 +289,7 @@ pub(super) fn organize_grid( let viewport = ui.available_rect_before_wrap(); view.viewport_screen = viewport; let auto_delta = if unobstructed { - view.auto_scroll.update(ui, viewport, true) + view.auto_scroll.update(ui, viewport, true, invert_middle) } else { view.auto_scroll.cancel(); Vec2::ZERO diff --git a/crates/ui-egui/src/canvas/wheel_pager.rs b/crates/ui-egui/src/canvas/wheel_pager.rs index d12c445a8a..c8ce69c57d 100644 --- a/crates/ui-egui/src/canvas/wheel_pager.rs +++ b/crates/ui-egui/src/canvas/wheel_pager.rs @@ -73,6 +73,11 @@ impl WheelPager { self.accum = 0.0; } + /// Reset any turned state when a turn did not happen (e.g. at document boundary). + pub(crate) fn unturn(&mut self) { + self.turned = None; + } + /// Whether the current gesture already turned a page: the rest of it must not pan the page /// just shown away from its top (or bottom). pub(crate) fn gesture_turned(&self) -> bool { @@ -144,6 +149,9 @@ impl WheelPager { }; if notch { if !can_turn { + // A notch is a gesture of its own, so one that only pans ends the gesture a + // previous notch turned; otherwise `gesture_turned` keeps swallowing the wheel (#5713). + self.turned = None; return None; } // Every notch turns a page; a smooth tail of the same gesture won't add another. diff --git a/crates/ui-egui/src/chrome.rs b/crates/ui-egui/src/chrome.rs index 59525aae7b..56125d5709 100644 --- a/crates/ui-egui/src/chrome.rs +++ b/crates/ui-egui/src/chrome.rs @@ -531,6 +531,26 @@ pub fn mode_bar(app: &mut PdfCraftApp, ui: &mut egui::Ui) { }); } +/// The size of the rail's page and zoom fields: wide enough for "6400%", the largest zoom, in the +/// 12 pt font, and inside the 45 pt the rail leaves. +const RAIL_FIELD_SIZE: [f32; 2] = [42.0, 22.0]; +/// Padding inside the rail's page and zoom fields. +const RAIL_FIELD_MARGIN: egui::Vec2 = egui::vec2(1.0, 4.0); + +/// A field the rail can type in: boxed, and the same size whatever it holds, so the page and zoom +/// fields match and fit the rail's width. Sized outright: a text field is at least a control wide. +fn rail_field(ui: &mut egui::Ui, t: &Tokens, edit: egui::TextEdit<'_>) -> egui::Response { + egui::Frame::NONE + .fill(t.field) + .stroke(Stroke::new(1.0, t.border)) + .corner_radius(CornerRadius::same(5)) + .show(ui, |ui| { + ui.spacing_mut().interact_size.x = 0.0; + ui.add_sized(RAIL_FIELD_SIZE, edit) + }) + .inner +} + /// Draw the right tool rail with page navigation, history, zoom, rotation and page-display controls for the /// active view. pub fn right_rail(app: &mut PdfCraftApp, ui: &mut egui::Ui) { @@ -573,7 +593,8 @@ pub fn right_rail(app: &mut PdfCraftApp, ui: &mut egui::Ui) { let mut page_display = None; let rail = Rail::new(egui::Id::unique("rail")) .edge(app.side_panels.rail_edge()) - .frame(egui::Frame::NONE.fill(t.chrome).inner_margin(egui::Margin::symmetric(6, 8)).stroke(Stroke::new(1.0, t.divider))) + .width(49.0) + .frame(egui::Frame::NONE.fill(t.chrome).inner_margin(egui::Margin::symmetric(1, 8)).stroke(Stroke::new(1.0, t.divider))) .show(ui, &items, app.right.as_ref(), |ui| { // Page navigation cluster at the bottom, a panel of its own so that in a short // window the buttons above scroll instead of running into it (#3282). @@ -584,14 +605,6 @@ pub fn right_rail(app: &mut PdfCraftApp, ui: &mut egui::Ui) { if icons::button(ui, if right { "panel-left" } else { "panel-right" }, 32.0, false, dock_tip).clicked() { app.side_panels.rail_side = if right { crate::side_panels::ToolsSide::Left } else { crate::side_panels::ToolsSide::Right }; } - let tip = crate::commands::key_tip(ui.ctx(), tl!("Zoom out ({key})"), crate::commands::ZOOM_OUT); - if icons::button(ui, "zoom-out", 32.0, false, &tip).clicked() { - view.zoom_step(false); - } - let tip = crate::commands::key_tip(ui.ctx(), tl!("Zoom in ({key})"), crate::commands::ZOOM_IN); - if icons::button(ui, "zoom-in", 32.0, false, &tip).clicked() { - view.zoom_step(true); - } // Between rotate and zoom, as in Acrobat. Its command runs once `view` is free. let tip = crate::i18n::fmt(tl!("Page display: {layout}"), &[("layout", tl!(view.layout.label()))]); let resp = icons::button(ui, view.layout.icon(), 32.0, false, &tip); @@ -611,18 +624,31 @@ pub fn right_rail(app: &mut PdfCraftApp, ui: &mut egui::Ui) { view.fit = if view.fit == Fit::Width { Fit::Page } else { Fit::Width }; view.goto = Some((view.current, 0.0)); } + // Out and in side by side right under the zoom field, so they are found with it. + ui.horizontal(|ui| { + ui.spacing_mut().item_spacing.x = 0.0; + // Two buttons across the rail, each leaving a pixel to the rail's edge. + let side = (ui.available_width() / 2.0).floor(); + let tip = crate::commands::key_tip(ui.ctx(), tl!("Zoom out ({key})"), crate::commands::ZOOM_OUT); + if icons::button(ui, "zoom-out", side, false, &tip).clicked() { + view.zoom_step(false); + } + let tip = crate::commands::key_tip(ui.ctx(), tl!("Zoom in ({key})"), crate::commands::ZOOM_IN); + if icons::button(ui, "zoom-in", side, false, &tip).clicked() { + view.zoom_step(true); + } + }); let id = egui::Id::unique("zoom-input"); let draft = id.with("draft"); let mut typed = ui.data(|d| d.get_temp::(draft)).unwrap_or_else(|| format!("{:.0}%", view.zoom * 100.0)); let edit = egui::TextEdit::singleline(&mut typed) .id(id) - .desired_width(40.0) - .align(egui::Align2::CENTER_TOP) - .font(theme::medium(11.0)) - .text_color(t.text_muted) + .align(egui::Align2::CENTER_CENTER) + .font(theme::medium(12.0)) + .text_color(t.text) .frame(egui::Frame::NONE) - .margin(vec2(2.0, 2.0)); - let r = ui.add(edit).on_hover_text(tl!("Zoom — type a percentage and press Enter")); + .margin(RAIL_FIELD_MARGIN); + let r = rail_field(ui, &t, edit).on_hover_text(tl!("Zoom — type a percentage and press Enter")); ui.ctx().accesskit_node_builder(id, |node| node.set_label(tl!("Zoom"))); if r.gained_focus() { let mut state = egui::TextEdit::load_state(ui.ctx(), id).unwrap_or_default(); @@ -682,16 +708,11 @@ pub fn right_rail(app: &mut PdfCraftApp, ui: &mut egui::Ui) { } let edit = egui::TextEdit::singleline(&mut view.page_input) .id(page_input_id) - .desired_width(34.0) - .align(egui::Align2::CENTER_TOP) + .align(egui::Align2::CENTER_CENTER) .font(theme::medium(12.0)) - .margin(vec2(2.0, 4.0)); - let r = egui::Frame::NONE - .fill(t.field) - .stroke(Stroke::new(1.0, t.border)) - .corner_radius(CornerRadius::same(5)) - .show(ui, |ui| ui.add(edit)) - .inner + .frame(egui::Frame::NONE) + .margin(RAIL_FIELD_MARGIN); + let r = rail_field(ui, &t, edit) .on_hover_text(tl!("Current page — type a page number or label (such as iv) and press Enter")) .accessible_name(tl!("Current page")); if r.lost_focus() { diff --git a/crates/ui-egui/src/dialogs.rs b/crates/ui-egui/src/dialogs.rs index 42bed83657..84c36f41aa 100644 --- a/crates/ui-egui/src/dialogs.rs +++ b/crates/ui-egui/src/dialogs.rs @@ -14,11 +14,15 @@ pub(super) mod credits; pub(super) mod marks_ui; pub(super) mod pageboxes; pub(super) mod palette; +pub(super) mod preferences; mod prompts; pub(super) mod protect; pub(super) mod standards_ui; pub(super) mod word_count_ui; +#[cfg(test)] +mod tests; + pub(crate) use prompts::{PromptButton, save_prompt_key}; use prompts::{full_screen_prompt, link_prompt, password, remote_link_prompt, save_prompt, unlock}; @@ -127,6 +131,7 @@ fn dialogs(app: &mut PdfCraftApp, ctx: &egui::Context) { Dialog::Properties(_) => 640.0, Dialog::Print => 820.0, Dialog::FieldProps | Dialog::BulkFieldProps => 600.0, + Dialog::Preferences => 610.0, Dialog::About => 780.0, Dialog::PinTool => 540.0, _ => 520.0, @@ -1356,22 +1361,39 @@ fn dialog_signature(ui: &mut egui::Ui, app: &mut PdfCraftApp, req: &mut Pending) /// `Dialog::Preferences` content. Returns `false` when it has its own buttons and no footer is wanted. fn dialog_preferences(ui: &mut egui::Ui, app: &mut PdfCraftApp, req: &mut Pending) -> bool { + ui.set_width(610.0); let t = Tokens::get(ui.ctx()); + preferences::preferences_header(ui, &t); + ui.add_space(10.0); // The settings outgrow a short window: scroll them rather than run off the screen. // The OK row stays below the scroll, in reach however far the settings are scrolled. - let max = (ui.ctx().content_rect().height() - 120.0 - crate::js_ui::PREFERENCES_BUTTON_ROW).max(crate::js_ui::PREFERENCES_MIN_SCROLL); + let max = (ui.ctx().content_rect().height() - 120.0 - preferences::PREFERENCES_BUTTON_ROW - 40.0).max(preferences::PREFERENCES_MIN_SCROLL); // A scroll area starts from the room the dialog offers it, and a modal offers more // each frame for the first few, so with OK outside the scroll the dialog would grow // over those frames. Asking for the full height as the least it may scroll in // (which only applies when the settings overflow it) opens the dialog at full size. // A scrollbar of its own: the floating one lies over the right edge of the theme // cards and other full-width rows (#3557). + preferences_scroll(ui, max, |ui| preferences::preferences_body(ui, app, &t)); + req.close = preferences::preferences_buttons(ui); + false +} + +fn preferences_scroll(ui: &mut egui::Ui, max: f32, add_contents: impl FnOnce(&mut egui::Ui)) { ui.scope(|ui| { ui.spacing_mut().scroll.floating = false; - egui::ScrollArea::vertical().max_height(max).min_scrolled_height(max).show(ui, |ui| crate::js_ui::preferences_body(ui, app, &t)); + ui.spacing_mut().scroll.bar_inner_margin = 14.0; + ui.spacing_mut().scroll.bar_outer_margin = 2.0; + if ui.style().scroll_animation != egui::style::ScrollAnimation::none() { + ui.style_mut().scroll_animation = egui::style::ScrollAnimation::duration(0.25); + } + egui::ScrollArea::vertical() + .id_salt("preferences-dialog-scroll") + .max_height(max) + .min_scrolled_height(max) + .animated(true) + .show(ui, add_contents); }); - req.close = crate::js_ui::preferences_buttons(ui); - false } /// `Dialog::NumberPages` content. Returns `false` when it has its own buttons and no footer is wanted. diff --git a/crates/ui-egui/src/dialogs/appearance.rs b/crates/ui-egui/src/dialogs/appearance.rs index 48ad0cb31c..2b1b35400f 100644 --- a/crates/ui-egui/src/dialogs/appearance.rs +++ b/crates/ui-egui/src/dialogs/appearance.rs @@ -1,11 +1,10 @@ //! Preferences › Appearance: the appearance mode (follow the system, light or dark) above a light //! and a dark theme card, each with a small picture of PdfCraft in that theme. -use egui::{Rect, RichText, pos2, vec2}; +use egui::{CornerRadius, Rect, RichText, Stroke, pos2, vec2}; use crate::PdfCraftApp; use crate::theme::{self, ThemeKind, ThemePreference, Tokens}; -use crate::widgets; /// The themes each card offers. One of each today; a new theme is one more row here. pub const LIGHT_THEMES: &[(ThemeKind, &str)] = &[(ThemeKind::Light, "Light gray")]; @@ -82,43 +81,70 @@ fn preview(ui: &mut egui::Ui, kind: ThemeKind, width: f32) { } } -/// One theme card: its title, Active when it is what shows now, a preview of the chosen theme -/// and a radio row per theme. Returns true when the card or one of its radio rows was clicked. -fn card(ui: &mut egui::Ui, t: &Tokens, title: &str, active: bool, themes: &[(ThemeKind, &str)]) -> bool { - let inner = egui::Frame::new() - .fill(t.card) - .stroke(egui::Stroke::new(1.0, if active { t.accent } else { t.border })) - .corner_radius(6.0) - .inner_margin(egui::Margin::same(8)) - .show(ui, |ui| { - ui.set_width(ui.available_width()); - ui.horizontal(|ui| { - ui.label(RichText::new(title).font(theme::semibold(12.5)).color(t.text)); - if active { - ui.label(RichText::new(tl!("Active")).color(t.accent_text).small()); - } - }); - ui.add_space(4.0); - let shown = themes.first().map_or(ThemeKind::Light, |(kind, _)| *kind); - preview(ui, shown, ui.available_width()); - ui.add_space(4.0); - let mut clicked = false; - for (kind, label) in themes { - // One theme per card today, so it is always the chosen one. - clicked |= ui.add(widgets::radio(*kind == shown, tl!(label))).clicked(); - } - clicked - }); - // The whole card picks its theme, not just the radio row. - let whole = inner.response.interact(egui::Sense::click()).on_hover_cursor(egui::CursorIcon::PointingHand); - inner.inner || whole.clicked() +/// One theme card: its title, Active when it is what shows now, and a preview of the chosen theme. +/// Returns whether the card was clicked and the control's Response. +fn card(ui: &mut egui::Ui, t: &Tokens, title: &str, active: bool, themes: &[(ThemeKind, &str)], query: &str) -> (bool, egui::Response) { + let mut card_clicked = false; + let frame_stroke = if active { Stroke::new(1.5, t.accent) } else { Stroke::new(1.0, t.border) }; + let scope_res = ui.scope_builder(egui::UiBuilder::new().id_salt(title).sense(egui::Sense::click()), |ui| { + egui::Frame::new().fill(t.card).stroke(frame_stroke).corner_radius(CornerRadius::same(6)).inner_margin(egui::Margin::same(8)).show( + ui, + |ui| { + ui.set_width(ui.available_width()); + ui.horizontal(|ui| { + let font = theme::semibold(12.5); + let ranges = crate::dialogs::preferences::find_match_ranges(title, query); + let galley = if ranges.is_empty() { + crate::bidi::layout_ui(ui, title.to_owned(), font, t.text) + } else { + let (job, _) = crate::dialogs::preferences::create_highlight_job(title, &ranges, font, t.text); + ui.painter().layout_job(job) + }; + let (title_rect, _) = ui.allocate_exact_size(galley.size(), egui::Sense::hover()); + ui.painter().galley(title_rect.min, galley, t.text); + if active { + ui.label(RichText::new(tl!("Active")).color(t.accent_text).small()); + } + }); + ui.add_space(4.0); + let shown = themes.first().map_or(ThemeKind::Light, |(kind, _)| *kind); + preview(ui, shown, ui.available_width()); + }, + ); + }); + + let resp = scope_res.response; + resp.widget_info(|| egui::WidgetInfo::selected(egui::Role::RadioButton, true, active, title)); + + if resp.has_focus() { + ui.painter().rect_stroke(resp.rect, CornerRadius::same(6), Stroke::new(2.0, t.accent_text), egui::StrokeKind::Outside); + } + + let resp = theme::hand(resp); + let key_select = resp.has_focus() && ui.input(|i| i.key_pressed(egui::Key::Space) || i.key_pressed(egui::Key::Enter)); + if resp.clicked() || key_select { + card_clicked = true; + } + (card_clicked, resp) } /// The Appearance section of Preferences. +#[cfg_attr(not(test), expect(dead_code, reason = "called by unit tests"))] pub fn preferences_section(ui: &mut egui::Ui, app: &mut PdfCraftApp, t: &Tokens) { - ui.label(RichText::new(tl_ctx!("theme", "Appearance")).font(theme::semibold(13.0))); + let mut ctx = crate::dialogs::preferences::PrefSearchContext::new("", false); + preferences_section_with_context(ui, app, t, &mut ctx); +} + +/// The Appearance section of Preferences with live search highlighting and scrolling context. +pub(crate) fn preferences_section_with_context( + ui: &mut egui::Ui, + app: &mut PdfCraftApp, + t: &Tokens, + ctx: &mut crate::dialogs::preferences::PrefSearchContext, +) { + ctx.label(ui, tl_ctx!("theme", "Appearance"), theme::semibold(13.0), t.text); ui.horizontal(|ui| { - let label = ui.label(tl!("Appearance mode")); + let label = ctx.label(ui, tl!("Appearance mode"), theme::regular(13.0), t.text); let combo = craft_ui::ComboBox::from_id_salt("appearance-mode").selected_text(tl!(mode_label(app.theme_preference))).show_ui(ui, |ui| { for preference in [ThemePreference::System, ThemePreference::Light, ThemePreference::Dark] { if ui.selectable_label(app.theme_preference == preference, tl!(mode_label(preference))).clicked() { @@ -132,18 +158,29 @@ pub fn preferences_section(ui: &mut egui::Ui, app: &mut PdfCraftApp, t: &Tokens) }); ui.add_space(4.0); let light_active = app.theme == ThemeKind::Light; + let light_title = tl!("Light theme"); + let dark_title = tl!("Dark theme"); + let light_matches = crate::dialogs::preferences::find_match_ranges(light_title, ctx.query).len(); + let dark_matches = crate::dialogs::preferences::find_match_ranges(dark_title, ctx.query).len(); + ctx.total_matches += light_matches + dark_matches; + ui.columns(2, |cols| { let [light, dark] = cols else { return }; - if card(light, t, tl!("Light theme"), light_active, LIGHT_THEMES) { + let (light_clicked, light_resp) = card(light, t, light_title, light_active, LIGHT_THEMES, ctx.query); + if light_clicked { app.execute(mode_command(ThemePreference::Light)); } - if card(dark, t, tl!("Dark theme"), !light_active, DARK_THEMES) { + ctx.scroll_if_first_match(&light_resp, light_matches); + + let (dark_clicked, dark_resp) = card(dark, t, dark_title, !light_active, DARK_THEMES, ctx.query); + if dark_clicked { app.execute(mode_command(ThemePreference::Dark)); } + ctx.scroll_if_first_match(&dark_resp, dark_matches); }); ui.add_space(4.0); // Acrobat's "Highlight existing fields": shared with the toggle in the form bar. - ui.add(crate::widgets::checkbox(&mut app.view_defaults.highlight_fields, tl!("Highlight fields"))); + ctx.checkbox(ui, &mut app.view_defaults.highlight_fields, tl!("Highlight fields"), t); } #[cfg(test)] @@ -175,7 +212,6 @@ mod tests { ); h.run(); assert!(h.query_by_label("Light theme").is_some() && h.query_by_label("Dark theme").is_some()); - assert!(h.query_by_label("Light gray").is_some() && h.query_by_label("Dark gray").is_some()); assert_eq!(h.query_all_by_label("Active").count(), 1); if let Ok(path) = std::env::var("PDFCRAFT_APPEARANCE_SHOT") { h.render().unwrap().save(path).unwrap(); @@ -200,7 +236,7 @@ mod tests { assert_eq!(h.state().theme_preference, ThemePreference::System); } - /// Clicking a theme card, or its radio row, picks that theme, not only the mode combo box. + /// Clicking a theme card picks that theme, not only the mode combo box. #[test] fn clicking_a_theme_card_picks_that_theme() { let mut app = PdfCraftApp::new(); @@ -219,10 +255,9 @@ mod tests { app, ); h.run(); - h.get_by_label("Dark gray").click(); + h.get_by_label("Dark theme").click(); h.run(); assert_eq!((h.state().theme_preference, h.state().theme), (ThemePreference::Dark, ThemeKind::Dark)); - // The card's title is not a widget of its own: the click lands on the card. h.get_by_label("Light theme").click(); h.run(); assert_eq!((h.state().theme_preference, h.state().theme), (ThemePreference::Light, ThemeKind::Light)); diff --git a/crates/ui-egui/src/dialogs/preferences.rs b/crates/ui-egui/src/dialogs/preferences.rs new file mode 100644 index 0000000000..9e3182e416 --- /dev/null +++ b/crates/ui-egui/src/dialogs/preferences.rs @@ -0,0 +1,1031 @@ +//! Preferences dialog: card-based settings interface organized into clean, modular cards +//! with segmented pill controls and real-time search filtering. + +use egui::{Color32, CornerRadius, Margin, Rect, RichText, Sense, Stroke, pos2, vec2}; + +use crate::PdfCraftApp; +use crate::canvas::{Fit, PageLayout}; +use crate::motion::AnimationEffects; +use crate::scroll_speed::ScrollSpeed; +use crate::side_panels::ToolsSide; +use crate::theme::{self, ThemeKind, Tokens}; +use crate::units::Unit; +use crate::widgets::{self, icons}; + +/// The height the Preferences dialog keeps below its scrolling settings for the buttons row. +pub(crate) const PREFERENCES_BUTTON_ROW: f32 = 52.0; + +/// The least height the scrolling settings are given in very small windows. +pub(crate) const PREFERENCES_MIN_SCROLL: f32 = 60.0; + +/// A segmented pill control for mutually exclusive choices. +/// +/// Draws a rounded container with options inside. The active option is highlighted +/// with the accent colour. Emits AccessKit RadioButton widget info with the option's label. +pub fn segmented_pill_choice(ui: &mut egui::Ui, t: &Tokens, current: &mut T, options: &[(T, &str)]) -> bool { + let with_a11y: Vec<(T, &str, &str)> = options.iter().map(|&(v, l)| (v, l, l)).collect(); + segmented_pill_choice_a11y(ui, t, current, &with_a11y) +} + +/// A segmented pill selection bar with separate accessibility labels. +pub fn segmented_pill_choice_a11y(ui: &mut egui::Ui, t: &Tokens, current: &mut T, options: &[(T, &str, &str)]) -> bool { + segmented_pill_choice_a11y_query(ui, t, current, options, "").0 +} + +/// A segmented pill selection bar with separate accessibility labels and optional query highlighting. +/// Returns whether the selection changed and the Response of the first matching option, if any. +pub fn segmented_pill_choice_a11y_query( + ui: &mut egui::Ui, + t: &Tokens, + current: &mut T, + options: &[(T, &str, &str)], + query: &str, +) -> (bool, Option) { + let mut changed = false; + let mut first_match_resp: Option = None; + egui::Frame::new() + .fill(t.field) + .stroke(Stroke::new(1.0, t.border)) + .corner_radius(CornerRadius::same(14)) + .inner_margin(Margin::symmetric(2, 2)) + .show(ui, |ui| { + ui.spacing_mut().item_spacing.x = 2.0; + ui.horizontal(|ui| { + for &(value, label, a11y_label) in options { + let is_active = *current == value; + let font = theme::medium(12.0); + let text_color = if is_active { Color32::WHITE } else { t.text }; + let label_galley = layout_pill_label(ui, label, query, font, text_color); + let w = label_galley.size().x; + let (rect, resp) = ui.allocate_exact_size(vec2(w + 18.0, 24.0), Sense::click()); + resp.widget_info(|| egui::WidgetInfo::selected(egui::Role::RadioButton, true, is_active, a11y_label)); + + if first_match_resp.is_none() && !find_match_ranges(label, query).is_empty() { + first_match_resp = Some(resp.clone()); + } + + if is_active { + ui.painter().rect(rect, CornerRadius::same(12), t.accent, Stroke::NONE, egui::StrokeKind::Inside); + } else { + let press = theme::Press::track(ui, &resp); + let fill = press.fill(Color32::TRANSPARENT, t.hover, t.pressed); + ui.painter().rect(rect, CornerRadius::same(12), fill, Stroke::NONE, egui::StrokeKind::Inside); + } + ui.painter().galley(rect.center() - label_galley.size() / 2.0, label_galley, text_color); + + if resp.has_focus() { + ui.painter().rect_stroke( + rect.expand(1.0), + CornerRadius::same(13), + Stroke::new(2.0, t.accent_text), + egui::StrokeKind::Outside, + ); + } + + let resp = theme::hand(resp); + let key_select = resp.has_focus() && ui.input(|i| i.key_pressed(egui::Key::Space) || i.key_pressed(egui::Key::Enter)); + if (resp.clicked() || key_select) && *current != value { + *current = value; + changed = true; + } + } + }); + }); + (changed, first_match_resp) +} + +/// An independent toggle pill button with optional query highlighting. +/// Returns whether the active state changed and the control's Response. +pub fn toggle_pill_query(ui: &mut egui::Ui, t: &Tokens, active: &mut bool, label: &str, query: &str) -> (bool, egui::Response) { + let mut changed = false; + let is_active = *active; + let font = theme::medium(12.0); + let text_color = if is_active { Color32::WHITE } else { t.text }; + let label_galley = layout_pill_label(ui, label, query, font, text_color); + let w = label_galley.size().x; + let (rect, resp) = ui.allocate_exact_size(vec2(w + 20.0, 26.0), Sense::click()); + resp.widget_info(|| egui::WidgetInfo::selected(egui::Role::CheckBox, true, is_active, label)); + + let (fill, stroke) = if is_active { + (t.accent, Stroke::NONE) + } else { + let press = theme::Press::track(ui, &resp); + (press.fill(t.field, t.hover, t.pressed), Stroke::new(1.0, t.border)) + }; + ui.painter().rect(rect, CornerRadius::same(13), fill, stroke, egui::StrokeKind::Inside); + ui.painter().galley(rect.center() - label_galley.size() / 2.0, label_galley, text_color); + + if resp.has_focus() { + ui.painter().rect_stroke(rect.expand(1.0), CornerRadius::same(14), Stroke::new(2.0, t.accent_text), egui::StrokeKind::Outside); + } + + let resp = theme::hand(resp); + let key_select = resp.has_focus() && ui.input(|i| i.key_pressed(egui::Key::Space) || i.key_pressed(egui::Key::Enter)); + if resp.clicked() || key_select { + *active = !*active; + changed = true; + } + (changed, resp) +} + +fn layout_pill_label(ui: &egui::Ui, label: &str, query: &str, font: egui::FontId, normal_color: Color32) -> std::sync::Arc { + let ranges = find_match_ranges(label, query); + if ranges.is_empty() { + crate::bidi::layout_ui(ui, label.to_owned(), font, normal_color) + } else { + let (job, _) = create_highlight_job(label, &ranges, font, normal_color); + ui.painter().layout_job(job) + } +} + +/// A standard card container for a Preferences section. +/// Groups related settings with clean margins, subtle border and rounded corners. +pub fn preference_card( + ui: &mut egui::Ui, + t: &Tokens, + title: &str, + icon: Option<&str>, + ctx: &mut PrefSearchContext, + content: impl FnOnce(&mut egui::Ui, &mut PrefSearchContext) -> R, +) -> R { + let card_fill = if t.kind == ThemeKind::Light { Color32::from_rgb(0xF7, 0xF8, 0xFA) } else { Color32::from_rgb(0x24, 0x24, 0x28) }; + egui::Frame::new() + .fill(card_fill) + .stroke(Stroke::new(1.0, t.border)) + .corner_radius(CornerRadius::same(8)) + .inner_margin(Margin::symmetric(14, 12)) + .show(ui, |ui| { + ui.set_width(ui.available_width()); + ui.horizontal(|ui| { + ui.spacing_mut().item_spacing.x = 6.0; + if let Some(ic) = icon { + ui.add(icons::image(ic, 16.0, t.accent)); + } + ctx.card_title(ui, title, t); + }); + ui.add_space(8.0); + content(ui, ctx) + }) + .inner +} + +/// Folds a character for case-insensitive search, folding dotted/dotless i variants +/// ('I', 'i', 'İ', 'ı') to 'i', Greek sigmas to 'σ', and otherwise following `char::to_lowercase`. +fn fold_search_char(c: char, mut f: impl FnMut(char)) { + match c { + 'I' | 'i' | '\u{130}' | '\u{131}' => f('i'), + 'Σ' | 'σ' | 'ς' => f('σ'), + _ => { + for lc in c.to_lowercase() { + f(lc); + } + } + } +} + +/// Finds non-overlapping (start_byte, end_byte) slices in `text` matching `query` case-insensitively. +/// All byte indices are guaranteed to align to valid char boundaries. +pub fn find_match_ranges(text: &str, query: &str) -> Vec<(usize, usize)> { + let q = query.trim(); + if q.is_empty() { + return Vec::new(); + } + let mut q_chars = Vec::new(); + for c in q.chars() { + fold_search_char(c, |ch| q_chars.push(ch)); + } + if q_chars.is_empty() { + return Vec::new(); + } + let char_indices: Vec<(usize, char)> = text.char_indices().collect(); + let mut ranges = Vec::new(); + let mut i = 0; + while i < char_indices.len() { + let mut matched = true; + let mut text_char_count = 0; + let mut q_idx = 0; + + while q_idx < q_chars.len() { + if i + text_char_count >= char_indices.len() { + matched = false; + break; + } + let c = char_indices.get(i + text_char_count).map(|(_, ch)| *ch).unwrap_or('\0'); + let mut c_folded = ['\0'; 4]; + let mut len = 0; + fold_search_char(c, |lc| { + if len < c_folded.len() { + c_folded[len] = lc; + len += 1; + } + }); + if len == 0 || q_idx + len > q_chars.len() || q_chars.get(q_idx..q_idx + len) != Some(&c_folded[..len]) { + matched = false; + break; + } + q_idx += len; + text_char_count += 1; + } + + if matched + && q_idx == q_chars.len() + && text_char_count > 0 + && let Some(start_byte) = char_indices.get(i).map(|(pos, _)| *pos) + { + let end_byte = if let Some((pos, _)) = char_indices.get(i + text_char_count) { *pos } else { text.len() }; + ranges.push((start_byte, end_byte)); + i += text_char_count; + continue; + } + i += 1; + } + ranges +} + +/// Builds an `egui::text::LayoutJob` with yellow background for matching spans. +pub fn create_highlight_job( + text: &str, + ranges: &[(usize, usize)], + normal_font: egui::FontId, + normal_color: Color32, +) -> (egui::text::LayoutJob, usize) { + let mut job = egui::text::LayoutJob::default(); + let normal_format = egui::text::TextFormat { font_id: normal_font.clone(), color: normal_color, ..Default::default() }; + let highlight_format = egui::text::TextFormat { + font_id: egui::FontId::new(normal_font.size, egui::FontFamily::Proportional), + color: Color32::BLACK, + background: Color32::from_rgb(255, 220, 60), + ..Default::default() + }; + + let mut cursor = 0; + for &(start, end) in ranges { + if start > cursor + && let Some(sub) = text.get(cursor..start) + { + job.append(sub, 0.0, normal_format.clone()); + } + if let Some(matched) = text.get(start..end) { + job.append(matched, 0.0, highlight_format.clone()); + } + cursor = end; + } + if cursor < text.len() + && let Some(sub) = text.get(cursor..) + { + job.append(sub, 0.0, normal_format); + } + let count = ranges.len(); + (job, count) +} + +/// Creates a `WidgetText` highlighting `query` in `text` and returning match count. +pub fn highlight_widget_text(text: &str, query: &str, normal_font: egui::FontId, normal_color: Color32) -> (egui::WidgetText, usize) { + let ranges = find_match_ranges(text, query); + if ranges.is_empty() { + (egui::WidgetText::from(egui::RichText::new(text).font(normal_font).color(normal_color)), 0) + } else { + let (job, count) = create_highlight_job(text, &ranges, normal_font, normal_color); + (egui::WidgetText::from(job), count) + } +} + +/// Context for browser-style in-situ text scanning, highlighting, and auto-scrolling in Preferences. +pub(crate) struct PrefSearchContext<'a> { + pub query: &'a str, + pub total_matches: usize, + pub first_match_scrolled: bool, + pub should_scroll: bool, +} + +impl<'a> PrefSearchContext<'a> { + pub fn new(query: &'a str, should_scroll: bool) -> Self { + Self { query, total_matches: 0, first_match_scrolled: false, should_scroll } + } + + pub fn scroll_if_first_match(&mut self, resp: &egui::Response, count: usize) { + if count > 0 && self.should_scroll && !self.first_match_scrolled { + resp.scroll_to_me(Some(egui::Align::Center)); + self.first_match_scrolled = true; + } + } + + pub fn checkbox(&mut self, ui: &mut egui::Ui, checked: &mut bool, label: &str, t: &Tokens) -> egui::Response { + let (widget_text, count) = highlight_widget_text(label, self.query, theme::regular(13.0), t.text); + self.total_matches += count; + let resp = ui.add(widgets::checkbox(checked, widget_text)); + self.scroll_if_first_match(&resp, count); + resp + } + + pub fn label(&mut self, ui: &mut egui::Ui, text: &str, font: egui::FontId, color: Color32) -> egui::Response { + let (widget_text, count) = highlight_widget_text(text, self.query, font, color); + self.total_matches += count; + let resp = ui.label(widget_text); + self.scroll_if_first_match(&resp, count); + resp + } + + pub fn label_primary(&mut self, ui: &mut egui::Ui, text: &str, t: &Tokens) -> egui::Response { + self.label(ui, text, theme::regular(13.0), t.text) + } + + pub fn label_secondary(&mut self, ui: &mut egui::Ui, text: &str, t: &Tokens) -> egui::Response { + self.label(ui, text, theme::regular(11.5), t.text_muted) + } + + pub fn card_title(&mut self, ui: &mut egui::Ui, title: &str, t: &Tokens) -> egui::Response { + self.label(ui, title, theme::semibold(13.5), t.text) + } + + pub fn pill_choice(&mut self, ui: &mut egui::Ui, t: &Tokens, current: &mut T, options: &[(T, &str)]) -> bool { + let mut matches = 0; + for &(_, label) in options { + matches += find_match_ranges(label, self.query).len(); + } + self.total_matches += matches; + let with_a11y: Vec<(T, &str, &str)> = options.iter().map(|&(v, l)| (v, l, l)).collect(); + let (changed, match_resp) = segmented_pill_choice_a11y_query(ui, t, current, &with_a11y, self.query); + if let Some(resp) = match_resp { + self.scroll_if_first_match(&resp, matches); + } + changed + } + + pub fn pill_choice_a11y(&mut self, ui: &mut egui::Ui, t: &Tokens, current: &mut T, options: &[(T, &str, &str)]) -> bool { + let mut matches = 0; + for &(_, label, _) in options { + matches += find_match_ranges(label, self.query).len(); + } + self.total_matches += matches; + let (changed, match_resp) = segmented_pill_choice_a11y_query(ui, t, current, options, self.query); + if let Some(resp) = match_resp { + self.scroll_if_first_match(&resp, matches); + } + changed + } + + pub fn toggle_pill(&mut self, ui: &mut egui::Ui, t: &Tokens, active: &mut bool, label: &str) -> bool { + let matches = find_match_ranges(label, self.query).len(); + self.total_matches += matches; + let (changed, resp) = toggle_pill_query(ui, t, active, label, self.query); + self.scroll_if_first_match(&resp, matches); + changed + } +} + +/// Whether the interface can draw a language picker's native name. +fn picker_text_is_drawable(ui: &egui::Ui, text: &str) -> bool { + #[cfg(target_arch = "wasm32")] + { + let _ = (ui, text); + true + } + #[cfg(not(target_arch = "wasm32"))] + { + ui.fonts_mut(|fonts| fonts.has_glyphs(&egui::FontId::proportional(13.0), text)) + } +} + +/// The date picker's displayed name. +pub(crate) fn date_language_picker_name(l: &pdfcraft_engine::dates::DateLanguage, drawable: impl FnOnce(&str) -> bool) -> &'static str { + match crate::i18n::Lang::from_code(l.code) { + Some(language) => language.picker_name(drawable), + None => l.name, + } +} + +/// Interactive search box widget at the top of Preferences. +fn preference_search_box_at(ui: &mut egui::Ui, t: &Tokens, query: &mut String, matches_count: Option, rect: Rect) { + let stroke = Stroke::new(1.0, t.border); + ui.painter().rect(rect, CornerRadius::same(15), t.field, stroke, egui::StrokeKind::Inside); + + // Magnifying glass icon: 14pt icon centered vertically at (rect.min.x + 16, rect.center().y) + let icon_rect = Rect::from_center_size(pos2(rect.min.x + 16.0, rect.center().y), vec2(14.0, 14.0)); + icons::paint(ui, icon_rect, "search", 14.0, t.text_muted); + + let badge_text = if !query.trim().is_empty() { + let count = matches_count.unwrap_or(0); + Some(crate::i18n::trn(crate::i18n::current(), count as u64, "{n} match", "{n} matches")) + } else { + None + }; + + let mut right_cursor = rect.max.x; + let edit_id = ui.auto_id_with("search_input"); + + if !query.is_empty() { + let clear_rect = Rect::from_center_size(pos2(right_cursor - 14.0, rect.center().y), vec2(16.0, 16.0)); + let clear_resp = ui.interact(clear_rect, ui.auto_id_with("clear_search"), Sense::click()); + clear_resp.widget_info(|| egui::WidgetInfo::labeled(egui::Role::Button, true, tl!("Clear search"))); + icons::paint(ui, clear_rect, "x", 12.0, if clear_resp.hovered() { t.text } else { t.text_muted }); + if clear_resp.clicked() { + query.clear(); + let state = egui::text_edit::TextEditState::default(); + state.store(ui.ctx(), edit_id); + } + right_cursor -= 28.0; + } + + if let Some(ref text) = badge_text { + let font = theme::medium(11.0); + let count = matches_count.unwrap_or(0); + let badge_color = if count > 0 { t.accent_text } else { t.text_muted }; + let galley = crate::bidi::layout_ui(ui, text.clone(), font, badge_color); + let bw = galley.size().x; + let badge_pos = pos2(right_cursor - bw - 4.0, rect.center().y - galley.size().y / 2.0); + ui.painter().galley(badge_pos, galley, badge_color); + let badge_rect = Rect::from_min_size(badge_pos, vec2(bw, 16.0)); + let badge_resp = ui.interact(badge_rect, ui.auto_id_with("search_match_count"), Sense::hover()); + badge_resp.widget_info(|| egui::WidgetInfo::labeled(egui::Role::Label, true, text.clone())); + right_cursor -= bw + 8.0; + } + + let edit_rect = Rect::from_min_max(pos2(rect.min.x + 28.0, rect.min.y), pos2(right_cursor.max(rect.min.x + 30.0), rect.max.y)); + let mut child_ui = ui.new_child(egui::UiBuilder::new().max_rect(edit_rect).layout(egui::Layout::left_to_right(egui::Align::Center))); + let edit = child_ui.add( + egui::TextEdit::singleline(query) + .id(edit_id) + .hint_text(tl!("Search settings…")) + .frame(egui::Frame::NONE) + .align(egui::Align2::LEFT_CENTER) + .desired_width(edit_rect.width()), + ); + edit.widget_info(|| egui::WidgetInfo::labeled(egui::Role::TextInput, true, tl!("Search settings…"))); + + if edit.has_focus() && ui.input(|i| i.key_pressed(egui::Key::Escape)) { + query.clear(); + let state = egui::text_edit::TextEditState::default(); + state.store(ui.ctx(), edit_id); + } +} + +/// Top header for Preferences: Title on the left, search box and match count badge on the right. +pub(crate) fn preferences_header(ui: &mut egui::Ui, t: &Tokens) { + let search_id = egui::Id::unique("pdfcraft_preferences_search_query"); + let mut query: String = ui.data(|d| d.get_temp(search_id)).unwrap_or_default(); + let matches_id = egui::Id::unique("pdfcraft_preferences_search_matches"); + let last_matches: usize = ui.data(|d| d.get_temp(matches_id)).unwrap_or(0); + + // Top Header: Title on the left, Search bar on the right. + // Allocate the full available width so the search bar aligns flush with the card boxes below. + let full_w = ui.available_width(); + let header_h = 30.0; + let (header_rect, _) = ui.allocate_exact_size(vec2(full_w, header_h), Sense::hover()); + + // Title on the left, vertically centered in the header row: + let title_rect = Rect::from_min_max(header_rect.min, pos2(header_rect.min.x + 240.0, header_rect.max.y)); + let mut title_ui = ui.new_child(egui::UiBuilder::new().max_rect(title_rect).layout(egui::Layout::left_to_right(egui::Align::Center))); + title_ui.label(RichText::new(tl!("Preferences")).font(theme::semibold(18.0)).color(t.text)); + + // Search bar on the right, right edge flush with the card box boundary: + let search_w = 230.0; + let search_rect = Rect::from_min_max(pos2(header_rect.max.x - search_w, header_rect.min.y), header_rect.max); + let match_count = (!query.trim().is_empty()).then_some(last_matches); + let before = query.clone(); + preference_search_box_at(ui, t, &mut query, match_count, search_rect); + if query != before { + ui.data_mut(|d| d.insert_temp(search_id, query)); + ui.ctx().request_repaint(); + } +} + +/// The body of the Preferences dialog with card layout and browser-style in-situ text scanning. +pub(crate) fn preferences_body(ui: &mut egui::Ui, app: &mut PdfCraftApp, t: &Tokens) { + let search_id = egui::Id::unique("pdfcraft_preferences_search_query"); + let query: String = ui.data(|d| d.get_temp(search_id)).unwrap_or_default(); + let matches_id = egui::Id::unique("pdfcraft_preferences_search_matches"); + let last_matches: usize = ui.data(|d| d.get_temp(matches_id)).unwrap_or(0); + let last_scrolled_id = egui::Id::unique("pdfcraft_pref_last_scrolled_query"); + let last_scrolled_query: String = ui.data(|d| d.get_temp(last_scrolled_id)).unwrap_or_default(); + + let should_scroll = !query.trim().is_empty() && query != last_scrolled_query; + let mut ctx = PrefSearchContext::new(&query, should_scroll); + + // Card 1: General & Interface + let title1 = tl!("General & Interface"); + preference_card(ui, t, title1, Some("settings"), &mut ctx, |ui, ctx| { + card_general(ui, app, t, ctx); + }); + ui.add_space(12.0); + + // Card 2: Appearance & Theme + let title2 = tl_ctx!("theme", "Appearance"); + preference_card(ui, t, title2, Some("sun"), &mut ctx, |ui, ctx| { + card_appearance(ui, app, t, ctx); + }); + ui.add_space(12.0); + + // Card 3: Documents and View + let title3 = tl!("Documents and view"); + preference_card(ui, t, title3, Some("file-text"), &mut ctx, |ui, ctx| { + card_documents_and_view(ui, app, t, ctx); + }); + ui.add_space(12.0); + + // Card 4: Comment + let title4 = tl!("Comment"); + preference_card(ui, t, title4, Some("message-square-text"), &mut ctx, |ui, ctx| { + card_identity(ui, app, t, ctx); + }); + ui.add_space(12.0); + + // Card 5: Fill & Sign + let title5 = tl!("Fill & Sign"); + preference_card(ui, t, title5, Some("pen-tool"), &mut ctx, |ui, ctx| { + card_fill_and_sign(ui, app, t, ctx); + }); + ui.add_space(12.0); + + // Card 6: JavaScript + let title6 = "JavaScript"; + preference_card(ui, t, title6, Some("code-xml"), &mut ctx, |ui, ctx| { + card_javascript(ui, app, t, ctx); + }); + ui.add_space(12.0); + + if ctx.first_match_scrolled { + ui.data_mut(|d| d.insert_temp(last_scrolled_id, query.clone())); + } else if query.trim().is_empty() { + ui.data_mut(|d| d.insert_temp(last_scrolled_id, String::new())); + } + + if ctx.total_matches != last_matches { + ui.data_mut(|d| d.insert_temp(matches_id, ctx.total_matches)); + ui.ctx().request_repaint(); + } +} + +/// Content for Card 1: General & Interface +fn card_general(ui: &mut egui::Ui, app: &mut PdfCraftApp, t: &Tokens, ctx: &mut PrefSearchContext) { + ui.horizontal(|ui| { + let label = ctx.label_primary(ui, tl!("Interface language"), t); + let (selected, picker) = { + let drawable = |text: &str| picker_text_is_drawable(ui, text); + let selected = crate::i18n::Lang::from_code(&app.language) + .map_or_else(|| tl!("Auto").to_owned(), |language| language.picker_name(drawable).to_owned()); + let picker = crate::i18n::Lang::for_picker_by(|language| language.picker_name(drawable)) + .into_iter() + .map(|language| (language, language.picker_name(drawable))) + .collect::>(); + (selected, picker) + }; + let before = app.language.clone(); + craft_ui::ComboBox::from_id_salt("interface-language") + .selected_text(selected) + .width(160.0) + .show_ui(ui, |ui| { + if ui.selectable_value(&mut app.language, crate::i18n::AUTO.to_string(), tl!("Auto")).clicked() { + ui.close(); + } + for (language, name) in &picker { + if ui.selectable_value(&mut app.language, language.code().to_string(), *name).clicked() { + ui.close(); + } + } + }) + .response + .labelled_by(label.id); + if app.language != before { + crate::i18n::set_current(crate::i18n::Lang::from_pref(&app.language)); + } + + ui.add_space(16.0); + use crate::ui_scale; + let label_size = ctx.label_primary(ui, tl!("Interface size"), t); + let native = ui.ctx().native_pixels_per_point().unwrap_or(1.0); + let auto_percent = ui_scale::percent(ui_scale::drawn(None, app.system_text_scale, native)); + let auto = crate::i18n::fmt(tl!("Auto ({percent}%)"), &[("percent", &auto_percent.to_string())]); + let selected = app.ui_scale.map_or_else(|| auto.clone(), |f| format!("{}%", ui_scale::percent(f))); + craft_ui::ComboBox::from_id_salt("interface-size") + .selected_text(selected) + .width(130.0) + .show_ui(ui, |ui| { + if ui.selectable_value(&mut app.ui_scale, None, auto).clicked() { + ui.close(); + } + for p in ui_scale::PRESETS { + let factor = f32::from(p) / 100.0; + if ui.selectable_label(app.ui_scale.is_some_and(|f| ui_scale::percent(f) == u32::from(p)), format!("{p}%")).clicked() { + app.ui_scale = Some(factor); + ui.close(); + } + } + }) + .response + .labelled_by(label_size.id); + }); + ctx.label_secondary(ui, tl!("Auto follows the system's text size. Pages always render at the display's full resolution."), t); + ui.add_space(6.0); + + ui.horizontal(|ui| { + ctx.label_primary(ui, tl!("Tools panel side"), t); + let right = app.side_panels.tools_on_right(); + let mut side = if right { ToolsSide::Right } else { ToolsSide::Left }; + if ctx.pill_choice(ui, t, &mut side, &[(ToolsSide::Left, tl!("Left")), (ToolsSide::Right, tl!("Right"))]) { + app.side_panels.tools_side = side; + } + + ui.add_space(16.0); + ctx.label_primary(ui, tl!("Navigation rail side"), t); + let rail_right = app.side_panels.rail_on_right(); + let mut rside = if rail_right { ToolsSide::Right } else { ToolsSide::Left }; + let left_a11y = format!("{}: {}", tl!("Navigation rail side"), tl!("Left")); + let right_a11y = format!("{}: {}", tl!("Navigation rail side"), tl!("Right")); + if ctx.pill_choice_a11y(ui, t, &mut rside, &[(ToolsSide::Left, tl!("Left"), &left_a11y), (ToolsSide::Right, tl!("Right"), &right_a11y)]) { + app.side_panels.rail_side = rside; + } + }); + ui.add_space(6.0); + + ui.horizontal(|ui| { + ctx.label_primary(ui, tl!("Animation effects"), t); + ctx.pill_choice( + ui, + t, + &mut app.animation_effects, + &[ + (AnimationEffects::System, tl_ctx!("animation effects", AnimationEffects::System.label())), + (AnimationEffects::On, tl_ctx!("animation effects", AnimationEffects::On.label())), + (AnimationEffects::Off, tl_ctx!("animation effects", AnimationEffects::Off.label())), + ], + ); + }); + ui.add_space(6.0); + + #[cfg(not(target_arch = "wasm32"))] + ctx.checkbox(ui, &mut app.reopen_last_session, tl!("Reopen the files that were open when PdfCraft last closed"), t); + #[cfg(not(target_arch = "wasm32"))] + ctx.checkbox(ui, &mut app.restore_last_view, tl!("Restore the last view (page, zoom and page display) when a document is opened again"), t); + #[cfg(not(target_arch = "wasm32"))] + ctx.checkbox(ui, &mut app.reload_changed_files, tl!("Reload documents when their files change on disk"), t); + ctx.checkbox(ui, &mut app.show_secured_notice, tl!("Show a notice when a document is secured"), t); + + #[cfg(not(target_arch = "wasm32"))] + { + ui.horizontal(|ui| { + let label = ctx.label_primary(ui, tl!("Recent files to keep"), t); + ui.add(egui::DragValue::new(&mut app.recent_limit).range(0..=crate::RECENT_FILES_MAX)).labelled_by(label.id); + }); + ctx.label_secondary(ui, tl!("Lowering this forgets the oldest files. At 0 there is no list."), t); + } + + if app.window_controls.is_some() { + ctx.checkbox(ui, &mut app.system_title_bar, tl!("Use system title bar"), t).on_hover_text(tl!( + "Show a basic title bar for the window buttons instead of the tab strip. GNOME doesn't draw title bars for apps, so this one doesn't follow its theme." + )); + } +} + +/// Content for Card 2: Appearance & Theme +fn card_appearance(ui: &mut egui::Ui, app: &mut PdfCraftApp, t: &Tokens, ctx: &mut PrefSearchContext) { + if ctx.checkbox(ui, &mut app.show_page_edge_shadows, tl!("Show Page Edge Shadows"), t).changed() { + ui.ctx().request_repaint(); + } + ui.add_space(4.0); + crate::appearance::preferences_section_with_context(ui, app, t, ctx); + ui.add_space(8.0); + reading_colours_section(ui, app, t, ctx); +} + +/// Content for Card 3: Documents and View +fn card_documents_and_view(ui: &mut egui::Ui, app: &mut PdfCraftApp, t: &Tokens, ctx: &mut PrefSearchContext) { + ui.horizontal(|ui| { + ctx.label_primary(ui, tl!("Default workspace mode"), t); + ctx.pill_choice( + ui, + t, + &mut app.default_mode, + &[ + (crate::Mode::AllTools, tl!("All tools")), + (crate::Mode::Read, tl!("Read")), + (crate::Mode::Edit, tl!("Edit")), + (crate::Mode::Convert, tl!("Convert")), + (crate::Mode::Sign, tl!("E-Sign")), + ], + ); + }); + ctx.label_secondary(ui, tl!("Used when opening PDFs. An explicit launch or control mode takes precedence for the session."), t); + ui.add_space(6.0); + + let defaults = &mut app.view_defaults; + ui.horizontal(|ui| { + ctx.label_primary(ui, tl!("Default page display"), t); + let mut layout_choice = defaults.layout; + if ctx.pill_choice(ui, t, &mut layout_choice, &[(PageLayout::Single, tl!("Single page")), (PageLayout::TwoUp, tl!("Two-page view"))]) { + defaults.layout = layout_choice; + } + let mut continuous = defaults.continuous; + if ctx.toggle_pill(ui, t, &mut continuous, tl!("Continuous scrolling")) { + defaults.continuous = continuous; + } + }); + ctx.checkbox(ui, &mut defaults.show_page_gaps, tl!("Show gaps between pages"), t); + ctx.label_secondary(ui, tl!("Hide gaps to join page edges. Margins inside the PDF remain unchanged."), t); + ui.add_space(6.0); + + ui.horizontal(|ui| { + ctx.label_primary(ui, tl!("Default zoom"), t); + ctx.pill_choice( + ui, + t, + &mut defaults.fit, + &[(Fit::Width, tl!("Fit to width")), (Fit::Page, tl!("Zoom to page level")), (Fit::None, tl!("Custom"))], + ); + let mut percent = defaults.zoom * 100.0; + if ui.add(egui::DragValue::new(&mut percent).range(8.0..=6400.0).max_decimals(0).suffix("%")).changed() { + (defaults.fit, defaults.zoom) = (Fit::None, percent / 100.0); + } + }); + ctx.label_secondary(ui, tl!("Used when a PDF doesn't ask for a layout or zoom. Continuous scrolling never snaps between pages."), t); + ctx.checkbox(ui, &mut app.always_default_view, tl!("Always use my default zoom and page layout"), t); + ui.add_space(6.0); + + ui.horizontal(|ui| { + ctx.label_primary(ui, tl!("Units"), t); + ctx.pill_choice( + ui, + t, + &mut app.units, + &[ + (Unit::Inches, Unit::Inches.label()), + (Unit::Millimetres, Unit::Millimetres.label()), + (Unit::Centimetres, Unit::Centimetres.label()), + (Unit::Points, Unit::Points.label()), + ], + ); + }); + ctx.label_secondary(ui, tl!("For page sizes and margins."), t); + ui.add_space(6.0); + scrolling(ui, app, t, ctx); +} + +/// The scroll speed and the middle button's direction, in Card 3. +fn scrolling(ui: &mut egui::Ui, app: &mut PdfCraftApp, t: &Tokens, ctx: &mut PrefSearchContext) { + ui.horizontal(|ui| { + ctx.label_primary(ui, tl!("Scroll speed (mouse wheel and arrow keys)"), t); + ctx.pill_choice( + ui, + t, + &mut app.scroll_speed, + &[ + (ScrollSpeed::Slow, tl_ctx!("scroll speed", ScrollSpeed::Slow.label())), + (ScrollSpeed::Normal, tl_ctx!("scroll speed", ScrollSpeed::Normal.label())), + (ScrollSpeed::Fast, tl_ctx!("scroll speed", ScrollSpeed::Fast.label())), + ], + ); + }); + ui.add_space(6.0); + ctx.checkbox(ui, &mut app.invert_middle_drag, tl!("Invert middle-button drag"), t); + ctx.label_secondary(ui, tl!("Panning or auto-scrolling with the middle (wheel) button moves the page the other way."), t); +} + +/// Content for Card 4: Identity +fn card_identity(ui: &mut egui::Ui, app: &mut PdfCraftApp, t: &Tokens, ctx: &mut PrefSearchContext) { + ui.horizontal(|ui| { + let label = ctx.label_primary(ui, tl!("Name on new comments"), t); + ui.add(crate::widgets::line(&mut app.comment_prefs.author).desired_width(240.0).char_limit(crate::MAX_AUTHOR_CHARS)).labelled_by(label.id); + }); + ctx.checkbox(ui, &mut app.comment_prefs.hide_empty_highlight_hover, tl!("Hide hover previews for highlights without comment text"), t); +} + +/// Content for Card 5: Fill & Sign +fn card_fill_and_sign(ui: &mut egui::Ui, app: &mut PdfCraftApp, t: &Tokens, ctx: &mut PrefSearchContext) { + ctx.checkbox(ui, &mut app.flatten_fill_sign_on_save, tl!("Flatten Fill & Sign when saving"), t); + ctx.label_secondary(ui, tl!("Text, marks and signatures become part of the page. Other comments stay editable."), t); + ui.add_space(8.0); + date_format(ui, app, t, ctx); +} + +/// Content for Card 6: JavaScript +fn card_javascript(ui: &mut egui::Ui, app: &mut PdfCraftApp, t: &Tokens, ctx: &mut PrefSearchContext) { + let mut on = app.session.javascript(); + if ctx.checkbox(ui, &mut on, tl!("Enable Acrobat JavaScript"), t).changed() { + app.session.set_javascript(on); + } + ctx.label_secondary( + ui, + tl!( + "Scripts run in a sandbox without file or network access. A script that asks to open a web page needs your permission first. With JavaScript off, Acrobat's standard format, validate and calculate functions still work." + ), + t, + ); +} + +/// Preferences dialog buttons: OK on the right. Returns true to close. +pub(crate) fn preferences_buttons(ui: &mut egui::Ui) -> bool { + ui.add_space(10.0); + let mut close = false; + ui.horizontal(|ui| { + ui.with_layout(egui::Layout::right_to_left(egui::Align::Center), |ui| { + if widgets::pill_button(ui, tl!("OK"), true).clicked() { + close = true; + } + }); + }); + close +} + +/// Fill & Sign date pattern and date language picker. +fn date_format(ui: &mut egui::Ui, app: &mut PdfCraftApp, t: &Tokens, ctx: &mut PrefSearchContext) { + use pdfcraft_engine::dates::{DATE_FORMATS, DATE_LANGUAGES, MAX_DATE_FORMAT_CHARS}; + ctx.label(ui, tl!("Date format"), theme::semibold(12.5), t.text); + let sample = |app: &PdfCraftApp, f: &str| format!("{} {f}", app.date_text(Some(f)).unwrap_or_default()); + ui.horizontal(|ui| { + let label = ctx.label_primary(ui, tl!("Fill & Sign dates"), t); + let current = app.session.date_format().to_string(); + let selected = if DATE_FORMATS.contains(¤t.as_str()) { sample(app, ¤t) } else { tl!("Custom").to_string() }; + craft_ui::ComboBox::from_id_salt("date-format") + .selected_text(selected) + .width(240.0) + .show_ui(ui, |ui| { + for f in DATE_FORMATS { + if ui.selectable_label(current == f, sample(app, f)).clicked() && app.session.set_date_format(f).is_ok() { + app.date_format_draft = None; + ui.close(); + } + } + }) + .response + .labelled_by(label.id); + }); + ui.horizontal(|ui| { + let label = ctx.label_primary(ui, tl!("Pattern"), t); + let mut text = app.date_format_draft.clone().unwrap_or_else(|| app.session.date_format().to_string()); + let edit = ui.add(egui::TextEdit::singleline(&mut text).desired_width(160.0).char_limit(MAX_DATE_FORMAT_CHARS)).labelled_by(label.id); + if edit.changed() { + let _ = app.session.set_date_format(&text); + app.date_format_draft = Some(text.clone()); + } + if !edit.has_focus() && pdfcraft_engine::dates::check_date_format(&text).is_ok() { + app.date_format_draft = None; + } + match app.date_text(Some(&text)) { + Ok(today) => { + let today_str = crate::i18n::fmt(tl!("Today: {date}"), &[("date", &today)]); + ctx.label_secondary(ui, &today_str, t); + } + Err(e) => { + ctx.label(ui, &e, theme::regular(13.0), Color32::from_rgb(0xD1, 0x3B, 0x3B)); + } + }; + }); + let bad = app.date_text(None).map(|today| pdfcraft_engine::dates::unwritable(&today)).unwrap_or_default(); + if !bad.is_empty() { + let bad_msg = crate::i18n::fmt( + tl!("{chars} can't be written into the PDF yet: Fill & Sign text is Western European only. Pick a numeric format such as dd.mm.yyyy."), + &[("chars", &bad)], + ); + ctx.label(ui, &bad_msg, theme::regular(13.0), Color32::from_rgb(0xD1, 0x3B, 0x3B)); + } + ui.horizontal(|ui| { + let label = ctx.label_primary(ui, tl!("Language"), t); + let (follow, selected, current, names) = { + let drawable = |text: &str| picker_text_is_drawable(ui, text); + let interface = crate::i18n::current().picker_name(drawable); + let follow = crate::i18n::fmt(tl!("Same as interface ({language})"), &[("language", interface)]); + let current = app.session.date_language().map(str::to_string); + let selected = DATE_LANGUAGES + .iter() + .find(|l| current.as_deref() == Some(l.code)) + .map_or_else(|| follow.clone(), |l| date_language_picker_name(l, drawable).to_string()); + let names = DATE_LANGUAGES.iter().map(|l| (l, date_language_picker_name(l, drawable))).collect::>(); + (follow, selected, current, names) + }; + craft_ui::ComboBox::from_id_salt("date-language") + .selected_text(selected) + .width(240.0) + .show_ui(ui, |ui| { + if ui.selectable_label(current.is_none(), follow).clicked() && app.session.set_date_language(None).is_ok() { + ui.close(); + } + for (l, name) in &names { + if ui.selectable_label(current.as_deref() == Some(l.code), *name).clicked() && app.session.set_date_language(Some(l.code)).is_ok() + { + ui.close(); + } + } + }) + .response + .labelled_by(label.id); + }); + let date_help = crate::i18n::fmt( + tl!( + "yyyy or yy year · m or mm month · mmm or mmmm month name · d or dd day · ddd or dddd weekday. H, h, M, s and t are time letters and can't be used on their own: put {escape} before a letter to show it as is." + ), + &[("escape", "\\")], + ); + ctx.label_secondary(ui, &date_help, t); +} + +/// Reading colours settings: presets, preview and custom replacement options. +fn reading_colours_section(ui: &mut egui::Ui, app: &mut PdfCraftApp, t: &Tokens, ctx: &mut PrefSearchContext) { + ctx.label(ui, tl!("Reading colours"), theme::semibold(13.0), t.text); + let mode = app.reading_colors.mode_name(); + ui.horizontal_wrapped(|ui| { + for (name, label, colors) in [ + ("off", "Off", pdfcraft_render::ReadingColors::default()), + ("black-on-white", "Black on white", pdfcraft_render::ReadingColors::BLACK_ON_WHITE), + ("white-on-black", "White on black", pdfcraft_render::ReadingColors::WHITE_ON_BLACK), + ("yellow-on-black", "Yellow on black", pdfcraft_render::ReadingColors::YELLOW_ON_BLACK), + ("green-on-black", "Green on black", pdfcraft_render::ReadingColors::GREEN_ON_BLACK), + ] { + let params = colors.params.unwrap_or(pdfcraft_render::ReadingParams { + text: [0, 0, 0], + background: [255, 255, 255], + only_black: false, + line_art: true, + }); + ui.vertical(|ui| { + ui.set_width(100.0); + let sample = RichText::new("Aa").size(20.0).color(Color32::from_rgb(params.text[0], params.text[1], params.text[2])); + let button = egui::Button::new(sample) + .fill(Color32::from_rgb(params.background[0], params.background[1], params.background[2])) + .min_size(vec2(90.0, 40.0)) + .stroke(Stroke::new(if mode == name { 2.0 } else { 1.0 }, if mode == name { t.accent } else { t.border })); + let response = ui.add(button); + response.widget_info(|| egui::WidgetInfo::selected(egui::Role::Button, true, mode == name, tl!(label))); + if response.clicked() { + app.set_reading_colors(colors); + } + ctx.label(ui, tl!(label), theme::regular(12.0), t.text); + }); + } + }); + ui.add_space(4.0); + if let Some(params) = app.reading_colors.params { + let text = Color32::from_rgb(params.text[0], params.text[1], params.text[2]); + let background = Color32::from_rgb(params.background[0], params.background[1], params.background[2]); + egui::Frame::new().fill(background).inner_margin(12.0).corner_radius(CornerRadius::same(6)).show(ui, |ui| { + ui.set_min_width((ui.available_width() - 24.0).max(0.0)); + ctx.label(ui, tl!("Reading colours"), theme::semibold(16.0), text); + ctx.label(ui, tl!("Colours are remapped while rendering; the document itself never changes."), theme::regular(13.0), text); + }); + } else { + ctx.label_primary(ui, tl!("Original"), t); + } + egui::CollapsingHeader::new(tl!("Custom")).default_open(mode == "custom").show(ui, |ui| { + let mut colors = if app.reading_colors.params.is_some() { app.reading_colors } else { pdfcraft_render::ReadingColors::BLACK_ON_WHITE }; + let mut changed = false; + if let Some(params) = colors.params.as_mut() { + ui.horizontal(|ui| { + let text = ctx.label_primary(ui, tl!("Text"), t); + changed |= ui.color_edit_button_srgb(&mut params.text).labelled_by(text.id).changed(); + let background = ctx.label_primary(ui, tl!("Page background"), t); + changed |= ui.color_edit_button_srgb(&mut params.background).labelled_by(background.id).changed(); + }); + changed |= ctx.checkbox(ui, &mut params.only_black, tl!("Only change the colour of black text or line art"), t).changed(); + changed |= ctx.checkbox(ui, &mut params.line_art, tl!("Change the colour of line art as well as text"), t).changed(); + } + if changed { + app.set_reading_colors(colors); + } + }); + ctx.label_secondary(ui, tl!("Colours are remapped while rendering; the document itself never changes."), t); +} + +#[cfg(test)] +mod tests { + use super::*; + + #[test] + fn test_find_match_ranges_case_insensitive() { + let text = "Hide hover previews for highlights without comment text"; + let ranges = find_match_ranges(text, "hide hover"); + assert_eq!(ranges, vec![(0, 10)]); + assert_eq!(text.get(ranges[0].0..ranges[0].1), Some("Hide hover")); + + let text2 = "Highlight fields and highlight text"; + let ranges2 = find_match_ranges(text2, "highlight"); + assert_eq!(ranges2.len(), 2); + assert_eq!(text2.get(ranges2[0].0..ranges2[0].1), Some("Highlight")); + assert_eq!(text2.get(ranges2[1].0..ranges2[1].1), Some("highlight")); + + let ranges3 = find_match_ranges(text, "not found"); + assert!(ranges3.is_empty()); + + let ranges4 = find_match_ranges(text, ""); + assert!(ranges4.is_empty()); + } + + #[test] + fn test_find_match_ranges_turkish_i() { + let text = "Doldur ve İmzala"; + let ranges = find_match_ranges(text, "imzala"); + assert_eq!(ranges.len(), 1); + assert_eq!(text.get(ranges[0].0..ranges[0].1), Some("İmzala")); + + let ranges2 = find_match_ranges(text, "İMZALA"); + assert_eq!(ranges2.len(), 1); + assert_eq!(text.get(ranges2[0].0..ranges2[0].1), Some("İmzala")); + + let text2 = "Doldur ve imzala"; + let ranges3 = find_match_ranges(text2, "İmzala"); + assert_eq!(ranges3.len(), 1); + assert_eq!(text2.get(ranges3[0].0..ranges3[0].1), Some("imzala")); + + let ranges4 = find_match_ranges(text, "ımzala"); + assert_eq!(ranges4.len(), 1); + assert_eq!(text.get(ranges4[0].0..ranges4[0].1), Some("İmzala")); + } +} diff --git a/crates/ui-egui/src/dialogs/tests.rs b/crates/ui-egui/src/dialogs/tests.rs new file mode 100644 index 0000000000..03f5c7c5b8 --- /dev/null +++ b/crates/ui-egui/src/dialogs/tests.rs @@ -0,0 +1,35 @@ +use std::cell::Cell; +use std::rc::Rc; + +use egui_kittest::Harness; +use egui_kittest::kittest::Queryable; + +#[test] +fn preferences_scroll_preserves_disabled_animation() { + for animated in [false, true] { + let scroll = Rc::new(Cell::new(false)); + let requested = scroll.clone(); + let mut h = Harness::builder().with_size(egui::vec2(600.0, 400.0)).with_step_dt(1.0 / 60.0).build_ui(move |ui| { + super::preferences_scroll(ui, 200.0, |ui| { + ui.add_space(1000.0); + let target = ui.label("Scroll target"); + if requested.replace(false) { + ui.scroll_to_rect(target.rect, Some(egui::Align::BOTTOM)); + } + ui.add_space(300.0); + }); + }); + h.ctx.all_styles_mut(|style| { + style.scroll_animation = if animated { egui::style::ScrollAnimation::default() } else { egui::style::ScrollAnimation::none() }; + }); + h.run_steps(4); + let before = h.get_by_label("Scroll target").rect().top(); + scroll.set(true); + h.run_steps(4); + let early = h.get_by_label("Scroll target").rect().top(); + h.run_steps(20); + let settled = h.get_by_label("Scroll target").rect().top(); + assert!((before - settled).abs() > 50.0, "the target must scroll: {before} -> {settled}"); + assert_eq!((early - settled).abs() > 1.0, animated, "animated: {animated}, early: {early}, settled: {settled}"); + } +} diff --git a/crates/ui-egui/src/hotbar.rs b/crates/ui-egui/src/hotbar.rs index f6a0c14c7f..c66b7e30b0 100644 --- a/crates/ui-egui/src/hotbar.rs +++ b/crates/ui-egui/src/hotbar.rs @@ -1,9 +1,10 @@ -//! A movable, persistent set of shortcuts to the shared command registry. -use egui::{Rect, Sense, vec2}; +//! A movable, persistent set of shortcuts to the shared command registry and core document tools. +use egui::{Color32, CornerRadius, Rect, Sense, Stroke, vec2}; +use pdfcraft_engine::Edit; use pdfcraft_engine::commands::{COMMANDS, command}; use serde::{Deserialize, Serialize}; -use crate::{PdfCraftApp, icons, theme::Tokens}; +use crate::{PdfCraftApp, QuickTool, comments, icons, theme, theme::Tokens}; /// Persistent state and UI state for the customizable document hotbar. #[derive(Clone, Debug, Serialize, Deserialize)] @@ -16,6 +17,8 @@ pub(crate) struct Hotbar { pub button_size: f32, pub dock: Option, pub full_side: bool, + #[serde(default)] + pub placed: bool, #[serde(skip)] search: String, #[serde(skip)] @@ -23,15 +26,16 @@ pub(crate) struct Hotbar { } impl Default for Hotbar { - /// Create a default empty horizontal floating hotbar. + /// Create a default vertical floating hotbar positioned in the document margin. fn default() -> Self { Self { tools: Vec::new(), - position: [0.5, 0.0], - vertical: false, + position: [0.0, 0.0], + vertical: true, button_size: 32.0, dock: None, full_side: false, + placed: false, search: String::new(), picker_open: false, } @@ -51,6 +55,24 @@ impl Hotbar { for coordinate in &mut self.position { *coordinate = if coordinate.is_finite() { coordinate.clamp(0.0, 1.0) } else { 0.5 }; } + if self.dock.is_some() || self.position != [0.0, 0.0] { + self.placed = true; + } + } + + /// Adopt preferences saved before the hotbar absorbed the quick-action bar (#5890), which have + /// no `placed` key. A bar left at that release's default (floating, horizontal, top centre) + /// moves to the new default in the left margin; any other spot is one the user chose, so it + /// is kept, including the top-left corner. + pub fn adopt_legacy(&mut self) { + if self.dock.is_none() && !self.vertical && self.position == [0.5, 0.0] { + self.position = [0.0, 0.0]; + self.vertical = true; + self.full_side = false; + self.placed = false; + } else { + self.placed = true; + } } /// Parse and validate a comma-separated list of command identifiers for the hotbar. @@ -68,6 +90,7 @@ impl Hotbar { pub fn place(&mut self, side: &str) -> Result<(), String> { if side == "float" { self.dock = None; + self.placed = true; return Ok(()); } let (position, vertical) = match side { @@ -80,12 +103,13 @@ impl Hotbar { self.dock = Some(side.to_owned()); self.position = position; self.vertical = vertical; + self.placed = true; Ok(()) } } /// Render the hotbar settings gear button and open the tool picker when clicked. -fn settings_button(ui: &mut egui::Ui, cell: f32, picker_open: &mut bool) { +fn settings_button(ui: &mut egui::Ui, cell: f32, picker_open: &mut bool) -> bool { let settings = ui .push_id("hotbar-settings", |ui| { icons::button(ui, "settings", cell, false, tl!("Hotbar settings")).on_hover_text(tl!("Hotbar settings / add tools")) @@ -93,6 +117,25 @@ fn settings_button(ui: &mut egui::Ui, cell: f32, picker_open: &mut bool) { .inner; if settings.clicked() { *picker_open = true; + true + } else { + false + } +} + +/// Determine where flyout popup menus should open from a toolbar button based on docking and layout. +fn popup_align_for(dock: Option<&str>, vertical: bool) -> egui::RectAlign { + match dock { + Some("right") => egui::RectAlign::LEFT_START, + Some("bottom") => egui::RectAlign::TOP_START, + Some("top") => egui::RectAlign::BOTTOM_START, + _ => { + if vertical { + egui::RectAlign::RIGHT_START + } else { + egui::RectAlign::BOTTOM_START + } + } } } @@ -103,7 +146,7 @@ fn matches_search(spec: &pdfcraft_engine::commands::CommandSpec, query: &str) -> tl!(spec.label).to_lowercase().contains(&search) || spec.label.to_lowercase().contains(&search) || spec.id.to_lowercase().contains(&search) } -/// Render the configured tool shortcut buttons and their removal context menus. +/// Render the configured custom tool shortcut buttons and their removal context menus. fn tool_buttons(ui: &mut egui::Ui, app: &PdfCraftApp, tools: &[String], cell: f32, run: &mut Option<&'static str>, remove: &mut Option) { for (index, id) in tools.iter().enumerate() { let Some(spec) = command(id) else { continue }; @@ -121,30 +164,279 @@ fn tool_buttons(ui: &mut egui::Ui, app: &PdfCraftApp, tools: &[String], cell: f3 } } -/// Draw the floating or side-docked hotbar and its tool picker window inside `area`. -pub(crate) fn show(app: &mut PdfCraftApp, area: Rect, ctx: &egui::Context) { +/// Render core quick tools: Select, Hand, Comment groups, Edit text, and Fill & Sign. +fn core_tool_buttons(ui: &mut egui::Ui, app: &mut PdfCraftApp, cell: f32, popup_align: egui::RectAlign, t: &Tokens) { + if icons::button(ui, "mouse-pointer-2", cell, app.quick_tool == QuickTool::Select, tl!("Select (V)")).clicked() { + app.quick_tool = QuickTool::Select; + } + if icons::button(ui, "hand", cell, app.quick_tool == QuickTool::Hand, tl!("Hand (H)")).clicked() { + app.quick_tool = QuickTool::Hand; + } + // Comment ▸, Highlight ▸, Draw ▸ (Acrobat's comment toolbar groups). Clicking a + // group selects its last-used tool; clicking it again opens the flyout. + for g in 0..comments::GROUPS.len() { + let current = app.comment_prefs.group_tool[g]; + let active = matches!(app.quick_tool, QuickTool::Comment(t) if t.group() == g); + let resp = icons::button(ui, current.icon(), cell, active, tl!(current.label())); + if comments::GROUPS[g].len() == 1 { + if resp.clicked() { + app.execute(current.command()); + } + continue; + } + // A small corner triangle marks the flyout. + let r = resp.rect; + let tri = [r.right_bottom() + vec2(-4.0, -4.0), r.right_bottom() + vec2(-9.0, -4.0), r.right_bottom() + vec2(-4.0, -9.0)]; + ui.painter().add(egui::Shape::convex_polygon(tri.to_vec(), if active { t.accent } else { t.text_faint }, Stroke::NONE)); + let open = (resp.clicked() && active) || resp.secondary_clicked(); + if resp.clicked() && !active { + app.execute(current.command()); + } + egui::Popup::menu(&resp).open_memory(open.then_some(egui::SetOpenCommand::Toggle)).align(popup_align).gap(6.0).show(|ui| { + for tool in comments::GROUPS[g] { + let on = app.quick_tool == QuickTool::Comment(*tool); + let (row, click) = ui.allocate_exact_size(vec2(180.0, 28.0), Sense::click()); + let press = theme::Press::track(ui, &click); + press.wash(ui, row, 4, on); + let body = row.translate(press.offset()); + icons::paint(ui, Rect::from_min_size(body.min + vec2(8.0, 6.0), vec2(16.0, 16.0)), tool.icon(), 16.0, t.text); + let reserve = if on { 28.0 } else { 8.0 }; + crate::widgets::paint_left( + ui, + body.left_center() + vec2(34.0, 0.0), + tl!(tool.label()), + theme::regular(13.0), + t.text, + (row.width() - 34.0 - reserve).max(0.0), + ); + if on { + icons::paint(ui, Rect::from_min_size(body.right_top() + vec2(-24.0, 7.0), vec2(14.0, 14.0)), "check", 14.0, t.accent); + } + let click = theme::hand(click); + let info = tl!(tool.label()).to_string(); + click.widget_info(|| egui::WidgetInfo::selected(egui::Role::Button, true, on, info.clone())); + if click.clicked() { + app.execute(tool.command()); + ui.close(); + } + } + }); + } + // Edit text & images, while the Edit workspace is open (Acrobat's Edit toolbar) + // or the tool is in use. + if app.mode == crate::Mode::Edit || app.quick_tool == QuickTool::EditText { + let on = app.quick_tool == QuickTool::EditText; + if icons::button(ui, "text-cursor-input", cell, on, tl!("Edit text & images")).clicked() { + if on { + app.put_down_edit_text(); + } else { + app.quick_tool = QuickTool::EditText; + } + } + } + // Fill & Sign ▸ (text, marks, date, signature). + let current_fill = match app.quick_tool { + QuickTool::Fill(f) => Some(f), + _ => None, + }; + let shown = current_fill.unwrap_or(crate::fill_sign::FillTool::Text); + let resp = icons::button(ui, if current_fill.is_some() { shown.icon() } else { "pen-line" }, cell, current_fill.is_some(), tl!("Fill & Sign")); + let r = resp.rect; + let tri = [r.right_bottom() + vec2(-4.0, -4.0), r.right_bottom() + vec2(-9.0, -4.0), r.right_bottom() + vec2(-4.0, -9.0)]; + ui.painter().add(egui::Shape::convex_polygon(tri.to_vec(), if current_fill.is_some() { t.accent } else { t.text_faint }, Stroke::NONE)); + if resp.clicked() && current_fill.is_none() { + app.execute(shown.command()); + } + let open = (resp.clicked() && current_fill.is_some()) || resp.secondary_clicked(); + egui::Popup::menu(&resp).open_memory(open.then_some(egui::SetOpenCommand::Toggle)).align(popup_align).gap(6.0).show(|ui| { + for tool in crate::fill_sign::FILL_TOOLS { + if matches!(tool, crate::fill_sign::FillTool::Signature | crate::fill_sign::FillTool::Initials) { + continue; + } + let on = current_fill == Some(tool); + let (row, click) = ui.allocate_exact_size(vec2(180.0, 28.0), Sense::click()); + let press = theme::Press::track(ui, &click); + press.wash(ui, row, 4, on); + let body = row.translate(press.offset()); + icons::paint(ui, Rect::from_min_size(body.min + vec2(8.0, 6.0), vec2(16.0, 16.0)), tool.icon(), 16.0, t.text); + let reserve = if on { 28.0 } else { 8.0 }; + crate::widgets::paint_left( + ui, + body.left_center() + vec2(34.0, 0.0), + tl!(tool.label()), + theme::regular(13.0), + t.text, + (row.width() - 34.0 - reserve).max(0.0), + ); + if on { + icons::paint(ui, Rect::from_min_size(body.right_top() + vec2(-24.0, 7.0), vec2(14.0, 14.0)), "check", 14.0, t.accent); + } + let click = theme::hand(click); + let info = tl!(tool.label()).to_string(); + click.widget_info(|| egui::WidgetInfo::selected(egui::Role::Button, true, on, info.clone())); + if click.clicked() { + app.execute(tool.command()); + ui.close(); + } + } + ui.separator(); + if let Some(command) = crate::fill_sign::signature_entries(ui, app, t) { + app.execute(command); + ui.close(); + } + }); +} + +/// Extra controls rendered below/beside the buttons when a comment or fill tool is active. +fn active_tool_controls(ui: &mut egui::Ui, app: &mut PdfCraftApp, t: &Tokens, vertical: bool) { + let current_fill = match app.quick_tool { + QuickTool::Fill(f) => Some(f), + _ => None, + }; + if matches!(current_fill, Some(crate::fill_sign::FillTool::Text | crate::fill_sign::FillTool::Date)) { + if vertical { + ui.label(tl!("Font size:")); + } + let size = ui.add( + egui::DragValue::new(&mut app.fill_text_size) + .range(crate::fill_sign::MIN_TEXT_SIZE..=crate::fill_sign::MAX_TEXT_SIZE) + .speed(0.25) + .suffix(" pt"), + ); + if ((size.changed() && !size.dragged()) || size.drag_stopped()) + && let Some((index, id)) = app.active_ids() + && let Some((page, annotation)) = app.views.get(index).and_then(|view| view.comments.selected) + && app.session.get(id).is_some_and(|doc| { + doc.allows_annotation() + && doc + .info + .annotations + .iter() + .any(|a| a.page == page && a.index == annotation && a.fill_sign && a.subtype == "FreeText" && !a.locked) + }) + { + app.apply_edit(Edit::FontSizeAnnotation { page, index: annotation, size: app.fill_text_size }); + } + ui.menu_button(tl!("Colour"), |ui| { + if let Some(color) = comments::swatch_grid(ui, Some(app.fill_text_color)) { + app.fill_text_color = color; + ui.close(); + } + }); + } + if let QuickTool::Comment(tool) = app.quick_tool { + let (r, _) = if vertical { + ui.allocate_exact_size(vec2(crate::canvas::bars::QUICK_BAR_WIDTH, 9.0), Sense::hover()) + } else { + ui.allocate_exact_size(vec2(9.0, crate::canvas::bars::QUICK_BAR_WIDTH), Sense::hover()) + }; + if vertical { + ui.painter().hline(r.x_range().shrink(6.0), r.center().y, Stroke::new(1.0, t.divider)); + } else { + ui.painter().vline(r.center().x, r.y_range().shrink(6.0), Stroke::new(1.0, t.divider)); + } + if let Some(color) = comments::quick_bar_controls(ui, tool, &mut app.comment_prefs) + && let Some((index, id)) = app.active_ids() + && let Some((page, annotation)) = app.views.get(index).and_then(|view| view.comments.selected) + && app.session.get(id).is_some_and(|doc| { + doc.allows_annotation() + && doc + .info + .annotations + .iter() + .any(|a| a.page == page && a.index == annotation && !a.is_reply() && !a.locked && comments::made_by(a, tool)) + }) + { + app.apply_edit(Edit::StyleAnnotation { page, index: annotation, color: Some(color), opacity: None, width: None, endings: None }); + } + } +} + +/// Render a modern iOS-style pill toggle switch. +fn toggle_switch(ui: &mut egui::Ui, on: &mut bool, label: &str, t: &Tokens) -> egui::Response { + let width = 34.0; + let height = 18.0; + let (rect, mut response) = ui.allocate_exact_size(vec2(width, height), Sense::click()); + if response.clicked() { + *on = !*on; + response.mark_changed(); + } + response.widget_info(|| egui::WidgetInfo::selected(egui::Role::Switch, ui.is_enabled(), *on, label)); + + if ui.is_rect_visible(rect) { + let radius = height / 2.0; + let bg_color = if *on { t.accent } else { t.border }; + ui.painter().rect(rect, CornerRadius::same(radius as u8), bg_color, Stroke::NONE, egui::StrokeKind::Inside); + let circle_radius = radius - 2.5; + let circle_x = if *on { rect.max.x - radius } else { rect.min.x + radius }; + ui.painter().circle_filled(egui::pos2(circle_x, rect.center().y), circle_radius, Color32::WHITE); + } + response +} + +/// Render the dock placement choice: [ Float | Left | Right | Top | Bottom ], scrolling sideways +/// when the picker is narrower than the row. +fn segmented_dock_picker(ui: &mut egui::Ui, bar: &mut Hotbar, t: &Tokens) { + let options = [ + (None, tl!("Float")), + (Some("left"), tl!("Left")), + (Some("right"), tl!("Right")), + (Some("top"), tl!("Top")), + (Some("bottom"), tl!("Bottom")), + ]; + let mut side = options.iter().map(|(side, _)| *side).find(|side| *side == bar.dock.as_deref()).flatten(); + let changed = egui::ScrollArea::horizontal() + .id_salt("hotbar-dock") + .auto_shrink([false, true]) + .show(ui, |ui| crate::dialogs::preferences::segmented_pill_choice(ui, t, &mut side, &options)) + .inner; + if changed { + // `place` accepts every side listed above. + let _ = bar.place(side.unwrap_or("float")); + } +} + +/// Draw the unified floating or side-docked toolbar, combining quick actions, core tools, and custom shortcuts. +pub(crate) fn show(app: &mut PdfCraftApp, area: Rect, page_left: Option, ui: &mut egui::Ui) { + let ctx = ui.ctx().clone(); let mut bar = std::mem::take(&mut app.hotbar); - let t = Tokens::get(ctx); - let id = egui::Id::unique("custom-hotbar"); + bar.normalize(); + let t = Tokens::get(&ctx); + let id = egui::Id::unique("quick-bar"); let full_side = bar.full_side && bar.dock.is_some(); let bounds = if full_side { area } else { area.shrink(10.0) }; if let Some(side) = bar.dock.clone() { let _ = bar.place(&side); } let cell = bar.button_size; - let mut size = ctx.data_mut(|data| data.get_temp::(id)).unwrap_or(vec2(90.0, 44.0)); + let popup_align = popup_align_for(bar.dock.as_deref(), bar.vertical); + let mut size = ctx.data_mut(|data| data.get_temp::(id)).unwrap_or(vec2(crate::canvas::bars::QUICK_BAR_WIDTH, 220.0)); if full_side { size = if bar.vertical { vec2(cell + 12.0, bounds.height()) } else { vec2(bounds.width(), cell + 12.0) }; } let travel = (bounds.size() - size).max(vec2(0.0, 0.0)); - let pos = bounds.min + vec2(travel.x * bar.position[0], travel.y * bar.position[1]); + let default_x = crate::canvas::bars::quick_bar_offset(page_left.map_or(0.0, |left| left - area.left()), size.x); + let pos = if full_side { + bounds.min + vec2(travel.x * bar.position[0], travel.y * bar.position[1]) + } else if bar.dock.is_none() && !bar.placed { + area.left_top() + vec2(default_x, crate::canvas::bars::QUICK_BAR_EDGE) + } else { + bounds.min + vec2(travel.x * bar.position[0], travel.y * bar.position[1]) + }; let mut run = None; + let was_picker_open = bar.picker_open; let mut picker_open = bar.picker_open; - let shown = egui::Area::new(id).order(egui::Order::Middle).fixed_pos(pos).constrain_to(bounds).show(ctx, |ui| { + let mut settings_clicked = false; + let shown = egui::Area::new(id).order(egui::Order::Middle).fixed_pos(pos).constrain_to(bounds).show(&ctx, |ui| { let frame = if full_side { egui::Frame::NONE.fill(t.chrome).corner_radius(egui::CornerRadius::ZERO).inner_margin(6) } else { - egui::Frame::new().fill(t.card).stroke(egui::Stroke::new(1.0, t.border)).corner_radius(10).inner_margin(6) + egui::Frame::new() + .fill(t.card) + .stroke(egui::Stroke::new(1.0, t.border)) + .corner_radius(CornerRadius::same(12)) + .shadow(egui::Shadow { offset: [0, 4], blur: 16, spread: 0, color: Color32::from_black_alpha(if t.dark() { 100 } else { 28 }) }) + .inner_margin(6) }; let frame_resp = frame.show(ui, |ui| { if full_side { @@ -160,23 +452,33 @@ pub(crate) fn show(app: &mut PdfCraftApp, area: Rect, ctx: &egui::Context) { if full_side { if bar.vertical { ui.with_layout(egui::Layout::bottom_up(egui::Align::Center), |ui| { - settings_button(ui, cell, &mut picker_open); + settings_clicked |= settings_button(ui, cell, &mut picker_open); ui.add_space(4.0); let remaining = ui.available_height().max(cell); - egui::ScrollArea::vertical().max_width(cell).max_height(remaining).show(ui, |ui| { + egui::ScrollArea::vertical().max_height(remaining).show(ui, |ui| { ui.with_layout(egui::Layout::top_down(egui::Align::Center), |ui| { - tool_buttons(ui, app, &bar.tools, cell, &mut run, &mut remove); + core_tool_buttons(ui, app, cell, popup_align, &t); + active_tool_controls(ui, app, &t, true); + if !bar.tools.is_empty() { + ui.separator(); + tool_buttons(ui, app, &bar.tools, cell, &mut run, &mut remove); + } }); }); }); } else { ui.with_layout(egui::Layout::right_to_left(egui::Align::Center), |ui| { - settings_button(ui, cell, &mut picker_open); + settings_clicked |= settings_button(ui, cell, &mut picker_open); ui.add_space(4.0); let remaining = ui.available_width().max(cell); egui::ScrollArea::horizontal().max_height(cell).max_width(remaining).show(ui, |ui| { ui.with_layout(egui::Layout::left_to_right(egui::Align::Center), |ui| { - tool_buttons(ui, app, &bar.tools, cell, &mut run, &mut remove); + core_tool_buttons(ui, app, cell, popup_align, &t); + active_tool_controls(ui, app, &t, false); + if !bar.tools.is_empty() { + ui.separator(); + tool_buttons(ui, app, &bar.tools, cell, &mut run, &mut remove); + } }); }); }); @@ -198,21 +500,44 @@ pub(crate) fn show(app: &mut PdfCraftApp, area: Rect, ctx: &egui::Context) { grip.widget_info(|| egui::WidgetInfo::labeled(egui::Role::Button, true, drag_label)); if grip.dragged() && bar.dock.is_none() { let delta = grip.drag_delta(); + if !bar.placed { + let cur_x = (pos.x - bounds.min.x).max(0.0); + let cur_y = (pos.y - bounds.min.y).max(0.0); + bar.position[0] = (cur_x / travel.x.max(1.0)).clamp(0.0, 1.0); + bar.position[1] = (cur_y / travel.y.max(1.0)).clamp(0.0, 1.0); + } bar.position[0] = (bar.position[0] + delta.x / travel.x.max(1.0)).clamp(0.0, 1.0); bar.position[1] = (bar.position[1] + delta.y / travel.y.max(1.0)).clamp(0.0, 1.0); + bar.placed = true; } - let scroll_max = if bar.vertical { (bounds.height() - cell - 50.0).max(cell) } else { (bounds.width() - cell - 50.0).max(cell) }; - let scroll = if bar.vertical { - egui::ScrollArea::vertical().max_width(cell).max_height(scroll_max) - } else { - egui::ScrollArea::horizontal().max_height(cell).max_width(scroll_max) - }; - scroll.auto_shrink([true, true]).show(ui, |ui| { - ui.with_layout(layout, |ui| { - tool_buttons(ui, app, &bar.tools, cell, &mut run, &mut remove); + if bar.vertical { + let fixed_overhead = grip_size.y + cell + 24.0; + let max_tools_length = (bounds.height() - fixed_overhead).max(cell); + egui::ScrollArea::vertical().max_height(max_tools_length).show(ui, |ui| { + ui.with_layout(layout, |ui| { + core_tool_buttons(ui, app, cell, popup_align, &t); + active_tool_controls(ui, app, &t, true); + if !bar.tools.is_empty() { + ui.separator(); + tool_buttons(ui, app, &bar.tools, cell, &mut run, &mut remove); + } + }); }); - }); - settings_button(ui, cell, &mut picker_open); + settings_clicked |= settings_button(ui, cell, &mut picker_open); + } else { + core_tool_buttons(ui, app, cell, popup_align, &t); + active_tool_controls(ui, app, &t, false); + if !bar.tools.is_empty() { + ui.separator(); + let scroll_max = (bounds.width() - cell - 50.0).max(cell); + egui::ScrollArea::horizontal().max_height(cell).max_width(scroll_max).show(ui, |ui| { + ui.with_layout(layout, |ui| { + tool_buttons(ui, app, &bar.tools, cell, &mut run, &mut remove); + }); + }); + } + settings_clicked |= settings_button(ui, cell, &mut picker_open); + } }); } if let Some(index) = remove { @@ -241,50 +566,132 @@ pub(crate) fn show(app: &mut PdfCraftApp, area: Rect, ctx: &egui::Context) { }); let picker_id = egui::Id::unique("hotbar-picker"); // A remembered collapsed state can survive disabling the collapse affordance. - let mut expanded = egui::collapsing_header::CollapsingState::load_with_default_open(ctx, picker_id.with("collapsing"), true); + let mut expanded = egui::collapsing_header::CollapsingState::load_with_default_open(&ctx, picker_id.with("collapsing"), true); expanded.set_open(true); - expanded.store(ctx); + expanded.store(&ctx); let screen = ctx.content_rect().shrink(12.0); - let picker_x = if pos.x + cell + 380.0 < screen.right() { pos.x + cell + 20.0 } else { pos.x - 360.0 }; - let picker_pos = egui::pos2( - picker_x.clamp(screen.left(), (screen.right() - 350.0).max(screen.left())), - pos.y.clamp(screen.top(), (screen.bottom() - 640.0).max(screen.top())), - ); - egui::Window::new(tl!("Hotbar tools")) + let margin_x = 14.0; + let card_margin_total = margin_x * 2.0; + let card_width = 280.0f32.min((screen.width() - card_margin_total).max(180.0)); + let outer_width = card_width + card_margin_total; + let bar_rect = shown.response.rect; + let picker_x = + if bar_rect.right() + outer_width + 10.0 < screen.right() { bar_rect.right() + 14.0 } else { bar_rect.left() - outer_width - 14.0 }; + let picker_y = if bar.dock.as_deref() == Some("top") { + (bar_rect.bottom() + 10.0).clamp(screen.top(), (screen.bottom() - 480.0).max(screen.top())) + } else if bar.dock.as_deref() == Some("bottom") { + (bar_rect.top() - 500.0).clamp(screen.top(), (screen.bottom() - 480.0).max(screen.top())) + } else { + bar_rect.top().clamp(screen.top(), (screen.bottom() - 480.0).max(screen.top())) + }; + let picker_pos = egui::pos2(picker_x.clamp(screen.left(), (screen.right() - outer_width).max(screen.left())), picker_y); + let mut close_dialog = false; + let picker_resp = egui::Window::new(tl!("Hotbar tools")) .id(picker_id) .order(egui::Order::Foreground) .open(&mut picker_open) .collapsible(false) .resizable(false) + .title_bar(false) .fixed_pos(picker_pos) - .max_height((screen.height() - 24.0).max(180.0)) - .vscroll(true) - .show(ctx, |ui| { - ui.set_min_width(260.0); - ui.add(egui::Slider::new(&mut bar.button_size, 24.0..=64.0).text(tl!("Toolbar size")).suffix(" px")); - ui.add_enabled(bar.dock.is_none(), crate::widgets::checkbox(&mut bar.vertical, tl!("Vertical layout"))); - if ui.selectable_label(bar.dock.is_none(), tl!("Float (drag anywhere)")).clicked() { - let _ = bar.place("float"); - } - ui.label(tl!("Stick to a side:")); + .frame( + egui::Frame::NONE + .fill(t.card) + .stroke(Stroke::new(1.0, t.border)) + .corner_radius(CornerRadius::same(10)) + .shadow(egui::Shadow { offset: [0, 6], blur: 20, spread: 0, color: Color32::from_black_alpha(if t.dark() { 120 } else { 35 }) }) + .inner_margin(egui::Margin::symmetric(14, 12)), + ) + .show(&ctx, |ui| { + ui.set_width(card_width); + + // Title bar: "Hotbar Tools" on the left, "X" close button on the right ui.horizontal(|ui| { - for (label, side) in [(tl!("Left"), "left"), (tl!("Right"), "right"), (tl!("Top"), "top"), (tl!("Bottom"), "bottom")] { - if ui.selectable_label(bar.dock.as_deref() == Some(side), label).clicked() { - let _ = bar.place(side); + ui.label(egui::RichText::new(tl!("Hotbar tools")).size(14.0).strong().color(t.text)); + ui.with_layout(egui::Layout::right_to_left(egui::Align::Center), |ui| { + if icons::button(ui, "x", 16.0, false, tl!("Close menu")).clicked() { + close_dialog = true; } - } + }); }); + + ui.add_space(10.0); + + // Section 1: Layout & Sizing + ui.label(egui::RichText::new(tl!("Layout & Sizing")).size(13.0).strong().color(t.text)); + ui.add_space(6.0); + + // Toolbar size slider row + ui.horizontal(|ui| { + ui.label(egui::RichText::new(tl!("Toolbar size")).size(12.5).color(t.text)); + let slider_width = (ui.available_width() - 55.0).clamp(50.0, 140.0); + ui.spacing_mut().slider_width = slider_width; + ui.add(egui::Slider::new(&mut bar.button_size, 24.0..=64.0).show_value(false)); + ui.with_layout(egui::Layout::right_to_left(egui::Align::Center), |ui| { + ui.label(egui::RichText::new(format!("{:.0} px", bar.button_size)).size(12.0).color(t.text_muted)); + }); + }); + + ui.add_space(8.0); + + // Vertical layout toggle switch row + ui.horizontal(|ui| { + ui.add_enabled_ui(bar.dock.is_none(), |ui| { + let label = tl!("Vertical layout"); + toggle_switch(ui, &mut bar.vertical, label, &t); + ui.add_space(8.0); + ui.label(egui::RichText::new(label).size(12.5).color(t.text)); + }); + }); + + ui.add_space(10.0); + + // Stick to a side section with segmented control + ui.label(egui::RichText::new(tl!("Stick to a side:")).size(12.5).color(t.text)); + ui.add_space(6.0); + segmented_dock_picker(ui, &mut bar, &t); + + ui.add_space(8.0); + + // Full-side strip checkbox let strip_hint = tl!("Extend the docked toolbar along the entire side. Choose a side above to enable."); ui.add_enabled(bar.dock.is_some(), crate::widgets::checkbox(&mut bar.full_side, tl!("Full-side strip"))) .on_hover_text(strip_hint) .on_disabled_hover_text(strip_hint); - if ui.button(tl!("Close menu")).clicked() { - ui.close(); - } + + ui.add_space(12.0); ui.separator(); - ui.label(tl!("Add tools to hotbar")); - ui.add(egui::TextEdit::singleline(&mut bar.search).hint_text(tl!("Search all tools…"))); - egui::ScrollArea::vertical().max_height(300.0).show(ui, |ui| { + ui.add_space(10.0); + + // Section 2: Add Tools to Hotbar + ui.label(egui::RichText::new(tl!("Add Tools to Hotbar")).size(13.0).strong().color(t.text)); + ui.add_space(8.0); + + // Search bar pill + let search_frame = egui::Frame::NONE + .fill(t.field) + .stroke(Stroke::new(1.0, t.border)) + .corner_radius(CornerRadius::same(8)) + .inner_margin(egui::Margin::symmetric(10, 6)); + search_frame.show(ui, |ui| { + ui.horizontal(|ui| { + ui.spacing_mut().item_spacing.x = 8.0; + ui.add(icons::image("search", 14.0, t.text_faint)); + ui.add( + egui::TextEdit::singleline(&mut bar.search) + .hint_text(tl!("Search all tools…")) + .frame(egui::Frame::NONE) + .desired_width(ui.available_width()), + ); + }); + }); + + ui.add_space(8.0); + + // Scrollable tools list with checkboxes + let max_list_height = (screen.height() - 340.0).clamp(120.0, 220.0); + egui::ScrollArea::vertical().max_height(max_list_height).auto_shrink([false, false]).show(ui, |ui| { + ui.spacing_mut().item_spacing.y = 5.0; for spec in COMMANDS { if !matches_search(spec, &bar.search) { continue; @@ -299,9 +706,23 @@ pub(crate) fn show(app: &mut PdfCraftApp, area: Rect, ctx: &egui::Context) { } } }); - ui.separator(); }); - ctx.data_mut(|data| data.insert_temp(id, shown.response.rect.size())); + let clicked_outside = was_picker_open + && !settings_clicked + && picker_resp.as_ref().is_some_and(|wr| { + wr.response.clicked_elsewhere() + || ctx.input(|i| i.pointer.any_click() && !i.pointer.interact_pos().is_some_and(|p| wr.response.rect.contains(p))) + }); + if clicked_outside || ctx.input(|i| i.key_pressed(egui::Key::Escape)) { + close_dialog = true; + } + if close_dialog { + picker_open = false; + } + ctx.data_mut(|data| { + data.insert_temp(id, shown.response.rect.size()); + data.insert_temp(egui::Id::unique("custom-hotbar"), shown.response.rect.size()); + }); bar.picker_open = picker_open; app.hotbar = bar; if let Some(id) = run { @@ -358,6 +779,24 @@ mod tests { assert_eq!(app.hotbar.position, [0.0, 1.0]); } + #[test] + fn hotbar_restore_moves_legacy_default_into_margin_and_keeps_chosen_spots() { + let mut app = PdfCraftApp::new(); + app.restore(r#"{"hotbar":{"tools":["comment.ink"],"position":[0.5,0.0],"vertical":false,"button_size":40.0,"dock":null}}"#); + assert_eq!(app.hotbar.position, [0.0, 0.0]); + assert!(app.hotbar.vertical); + assert!(!app.hotbar.placed); + assert_eq!(app.hotbar.tools, ["comment.ink"]); + assert_eq!(app.hotbar.button_size, 40.0); + app.restore(r#"{"hotbar":{"position":[0.0,0.0],"vertical":false,"dock":null}}"#); + assert_eq!(app.hotbar.position, [0.0, 0.0]); + assert!(!app.hotbar.vertical); + assert!(app.hotbar.placed, "a legacy bar dragged to the corner stays there"); + app.restore(r#"{"hotbar":{"position":[0.5,0.0],"vertical":false,"dock":null,"placed":true}}"#); + assert_eq!(app.hotbar.position, [0.5, 0.0], "current preferences are not migrated"); + assert!(!app.hotbar.vertical); + } + #[test] fn hotbar_search_matches_translated_and_canonical_labels() { let ink = command("comment.ink").unwrap(); diff --git a/crates/ui-egui/src/i18n/fr.tsv b/crates/ui-egui/src/i18n/fr.tsv index 1c22cf9d81..edfe48de44 100644 --- a/crates/ui-egui/src/i18n/fr.tsv +++ b/crates/ui-egui/src/i18n/fr.tsv @@ -2882,3 +2882,21 @@ certificate Version Version No image on clipboard to paste Aucune image à coller dans le presse-papiers Pinned {tool} to Home {tool} épinglé à l’Accueil Unpinned {tool} from Home {tool} désépinglé de l’Accueil + +# The strings the report listed as missing for fr. + Crop image Recadrer l'image + Mouse wheel scroll speed Vitesse de défilement à la molette + Remove {standard} identification Supprimer l'identification {standard} + The certificate of {} has critical extensions PdfCraft does not recognize, so it is not used to vouch for {}. Le certificat de {} comporte des extensions critiques que PdfCraft ne reconnaît pas ; il n'est donc pas utilisé pour attester {}. + The password must have at least 8 characters. Le mot de passe doit comporter au moins 8 caractères. + The signature's signed attributes have no content type, which CMS requires; it was read anyway. Les attributs signés de la signature n'ont pas de type de contenu, exigé par CMS ; elle a néanmoins été lue. + The signature's signed attributes have no message digest, so the signature does not cover the document. Les attributs signés de la signature n'ont pas de condensat de message ; la signature ne couvre donc pas le document. + The signature's signed attributes name a content type other than data, so it is not a signature of the document. Les attributs signés de la signature indiquent un type de contenu autre que des données ; ce n'est donc pas une signature du document. + The timestamp authority's certificate is not issued for time stamping. Le certificat de l'autorité d'horodatage n'est pas émis pour l'horodatage. + This file changed on disk. Reload it to see the new version; your unsaved changes will be lost. Ce fichier a changé sur le disque. Rechargez-le pour voir la nouvelle version ; vos modifications non enregistrées seront perdues. + This signature uses an RSA key shorter than 2048 bits, which is no longer considered strong enough for signatures. It still validates, but it should not be relied on. Cette signature utilise une clé RSA de moins de 2048 bits, ce qui n'est plus considéré comme suffisamment robuste pour des signatures. Elle se valide toujours, mais il ne faut pas s'y fier. + a table has 1 to {max} columns un tableau a de 1 à {max} colonnes + a table has 1 to {max} rows un tableau a de 1 à {max} lignes + the area, the spacing and the column widths must be numbers, the spacing 0 or more and each width more than 0 l'aire, l'espacement et les largeurs de colonnes doivent être des nombres, l'espacement 0 ou plus et chaque largeur supérieure à 0 + the first row number can be at most {max} le numéro de la première ligne peut être au maximum {max} +theme Appearance Apparence diff --git a/crates/ui-egui/src/i18n/tr.tsv b/crates/ui-egui/src/i18n/tr.tsv index 6921a6c33e..8a0d7bf74b 100644 --- a/crates/ui-egui/src/i18n/tr.tsv +++ b/crates/ui-egui/src/i18n/tr.tsv @@ -4,10 +4,6 @@ # # Clean-room: clean-room translations of PdfCraft's English UI labels, no proprietary localisation resources. -# Untranslated: English text until a translator fills these in. - Lowering this forgets the oldest files. At 0 there is no list. Lowering this forgets the oldest files. At 0 there is no list. - Recent files to keep Recent files to keep - Menu Menü File Dosya Edit Düzen @@ -2613,3 +2609,295 @@ animation effects Off Kapalı No image on clipboard to paste Panoda yapıştırılacak görüntü yok Pinned {tool} to Home {tool} Ana Sayfaya sabitlendi Unpinned {tool} from Home {tool} Ana Sayfadan kaldırıldı + +# Strings the translation gaps report listed on 2026-11-03 (AI-assisted; a native Turkish speaker reviewed the judgement calls: "of", hotbar, navigation rail, certificate terms, weekday heads). + Lowering this forgets the oldest files. At 0 there is no list. Bu değeri düşürmek en eski dosyaları unutturur. 0'da liste olmaz. + Recent files to keep Saklanacak son dosya sayısı + on page {label} {label}. sayfada + 1 line 1 satır + A font isn't embedded Bir yazı tipi gömülü değil + A {} action isn't allowed {} eylemine izin verilmiyor + A {} annotation has additional actions Bir {} açıklamasının ek eylemleri var + A {} annotation has no appearance stream Bir {} açıklamasının görünüm akışı yok + A {} annotation isn't set to print, or is hidden Bir {} açıklaması yazdırılacak şekilde ayarlanmamış ya da gizli + Accessibility Report Erişilebilirlik Raporu + Add tools to hotbar Kısayol çubuğuna araç ekle + Always Her zaman + Automatically Otomatik + CRL Signing CRL İmzalama + Certificate Signing Sertifika İmzalama + Certificate authority Sertifika yetkilisi + Change Author Yazarı Değiştir + Change Keywords Anahtar Kelimeleri Değiştir + Change Subject Konuyu Değiştir + Change Title Başlığı Değiştir + Choose a digital ID. Bir dijital kimlik seçin. + Choose a file… Dosya seç… + Choose a folder… Klasör seç… + Choose… Seç… + Close menu Menüyü kapat + Color Renk + Comment Yorum + Comment and review Yorumla ve incele + Copied to clipboard Panoya kopyalandı + Copy to clipboard Panoya kopyala + Create folder Klasör oluştur + Create links Bağlantı oluştur + Creator Oluşturan + Crop image Resmi kırp + Custom scale Özel ölçek + Cut and stack needs Two-sided: Off. Print single-sided sheets. Kes ve istifle için Çift taraflı: Kapalı olmalı. Tek taraflı sayfalar yazdırın. + Data Encipherment Veri Şifreleme + Decipher Only Yalnızca Şifre Çözme + Detailed Report Ayrıntılı Rapor + DeviceCMYK is used, but the PDF/A output intent isn't a CMYK profile DeviceCMYK kullanılıyor ancak PDF/A çıktı amacı bir CMYK profili değil + DeviceRGB is used, but the PDF/A output intent isn't an RGB profile DeviceRGB kullanılıyor ancak PDF/A çıktı amacı bir RGB profili değil + Digital Signature Dijital İmza + Disabled Devre dışı + Dock navigation rail on Left Gezinme çubuğunu sola yerleştir + Dock navigation rail on Right Gezinme çubuğunu sağa yerleştir + Document properties (⌘D) Belge özellikleri (⌘D) + Drag hotbar Kısayol çubuğunu sürükle + Duplicate Çoğalt + Enabled Etkin + Encipher Only Yalnızca Şifreleme + End entity Son varlık + English İngilizce + Enter a URL Bir URL girin + Enter a name. Bir ad girin. + Enter a page number Bir sayfa numarası girin + Enter the field names Alan adlarını girin + Error Hata + Every line set in the style chosen for a level becomes a bookmark of that level, under a new first bookmark. Bir düzey için seçilen stille yazılmış her satır, yeni bir ilk yer işaretinin altında o düzeyin yer işareti olur. + Extend the docked toolbar along the entire side. Choose a side above to enable. Yerleştirilmiş araç çubuğunu kenar boyunca uzat. Etkinleştirmek için yukarıdan bir kenar seçin. + Field "{}" on page {p} has no description (tooltip) {p}. sayfadaki "{}" alanının açıklaması (araç ipucu) yok + Filename Dosya adı + Flatten Fill & Sign Doldur ve İmzala'yı düzleştir + Float (drag anywhere) Serbest (istediğin yere sürükle) + Folder Klasör + Font (unnamed) on page {p} doesn't map its characters to Unicode {p}. sayfadaki (adsız) yazı tipi karakterlerini Unicode'a eşlemiyor + Font {} on page {p} doesn't map its characters to Unicode {p}. sayfadaki {} yazı tipi karakterlerini Unicode'a eşlemiyor + Form field on page {p} isn't tagged {p}. sayfadaki form alanı etiketli değil + Freehand-Highlight Serbest Vurgulama + Full-side strip Tam kenar şeridi + General & Interface Genel ve Arayüz + Hand El + Help… Yardım… + Hotbar settings Kısayol çubuğu ayarları + Hotbar settings / add tools Kısayol çubuğu ayarları / araç ekle + Hotbar tools Kısayol çubuğu araçları + H{n} follows an H{d}; headings should not skip levels H{n}, bir H{d} ardından geliyor; başlıklar düzey atlamamalı + Import İçe aktar + Information Bilgi + Key Agreement Anahtar Anlaşması + Key Encipherment Anahtar Şifreleme + Level {n} Düzey {n} + Loading… Yükleniyor… + Mouse wheel scroll speed Fare tekerleği kaydırma hızı + Move Taşı + Navigation rail side Gezinme çubuğunun kenarı + Never Hiçbir zaman + New bookmark (⌘B) Yeni yer işareti (⌘B) + New bookmarks from text styles Metin stillerinden yeni yer işaretleri + New bookmarks from text styles… Metin stillerinden yeni yer işaretleri… + Next Sonraki + Next (⌘G) Sonraki (⌘G) + No document language is set Belge dili ayarlanmamış + No page has text: the document appears to be images of pages Hiçbir sayfada metin yok: belge sayfa resimlerinden oluşuyor gibi görünüyor + No results Sonuç yok + Non-Repudiation İnkâr Edilemezlik + On Açık + Open a PDF (⌘O) PDF aç (⌘O) + Open folder Klasörü aç + Organize Düzenle + Page Properties Sayfa Özellikleri + Page properties… Sayfa özellikleri… + Page {n} Sayfa {n} + Page {n} of {total} Sayfa {n} / {total} + Page {p} doesn't tab in structure order {p}. sayfanın sekme sırası yapı sırasını izlemiyor + Page {p}: {n} untagged content item Sayfa {p}: {n} etiketsiz içerik öğesi + Page {p}: {n} untagged content items Sayfa {p}: {n} etiketsiz içerik öğesi + Page {} has additional actions {}. sayfanın ek eylemleri var + Panel layout could not be restored: {error} Panel düzeni geri yüklenemedi: {error} + Panel move was not applied: {error} Panel taşıma uygulanmadı: {error} + PdfCraft can't check this signature yet: {}. PdfCraft bu imzayı henüz denetleyemiyor: {}. + Previous Önceki + Previous (⇧⌘G) Önceki (⇧⌘G) + Print (⌘P) Yazdır (⌘P) + Producer Üretici + Refresh Yenile + Remove from hotbar Kısayol çubuğundan kaldır + Remove {standard} identification {standard} tanımlamasını kaldır + Rendering… İşleniyor… + Report created Rapor oluşturuldu + Reset side panels Yan panelleri sıfırla + Rev. {rev}: Certified by an unknown signer Rev. {rev}: Bilinmeyen bir imzalayan tarafından onaylandı + Rev. {rev}: Certified by {name} Rev. {rev}: {name} tarafından onaylandı + Rev. {rev}: Signed by an unknown signer Rev. {rev}: Bilinmeyen bir imzalayan tarafından imzalandı + Rev. {rev}: Signed by {name} Rev. {rev}: {name} tarafından imzalandı + Rotate view clockwise (⇧⌘+) Görünümü saat yönünde döndür (⇧⌘+) + Rule Name Kural Adı + Save as {level} {level} olarak kaydet + Save changes? Değişiklikler kaydedilsin mi? + Save file Dosyayı kaydet + Search all tools… Tüm araçlarda ara… + Search results Arama sonuçları + Search settings… Ayarlarda ara… + Select Seç + Select all Tümünü seç + Show or hide the Tools panel Araçlar panelini göster veya gizle + Show or hide the side panel Yan paneli göster veya gizle + Signature is invalid İmza geçersiz + Signature is valid İmza geçerli + Signature validity is unknown İmzanın geçerliliği bilinmiyor + Signing time is from the clock on the signer's computer. İmzalama zamanı, imzalayanın bilgisayarındaki saatten alınmıştır. + Stick to a side: Bir kenara yapıştır: + Still rendering — this page is unusually complex… Hâlâ işleniyor — bu sayfa alışılmadık derecede karmaşık… + Success Başarılı + System Sistem + Tab Order Sekme Sırası + Text recognition isn't installed: its models are missing (run `cargo xtask models`, or set PDFCRAFT_MODELS). Metin tanıma kurulu değil: modelleri eksik (`cargo xtask models` çalıştırın ya da PDFCRAFT_MODELS ayarlayın). + The ECDSA signature is not in canonical DER (trailing bytes, padding or a missing sign byte); it was read anyway. ECDSA imzası kurallı DER biçiminde değil (sondaki baytlar, dolgu ya da eksik işaret baytı); yine de okundu. + The ECDSA signature is the raw r and s values instead of a DER sequence; it was read anyway. ECDSA imzası bir DER dizisi yerine ham r ve s değerlerinden oluşuyor; yine de okundu. + The RSA signature value does not have the length of the key's modulus (leading zero bytes dropped or added); it was read anyway. RSA imza değeri, anahtarın modülüyle aynı uzunlukta değil (baştaki sıfır baytlar atılmış ya da eklenmiş); yine de okundu. + The RSA signature's DigestInfo has no NULL parameter (older signers write it so); it was read anyway. RSA imzasının DigestInfo alanında NULL parametresi yok (eski imzalayıcılar böyle yazar); yine de okundu. + The certificate of {} does not allow this many CA certificates below it (path length), so it is not used to vouch for {}. {} sertifikası altında bu kadar çok CA sertifikasına izin vermiyor (yol uzunluğu), bu yüzden {} için güvence olarak kullanılmıyor. + The certificate of {} has critical extensions PdfCraft does not recognize, so it is not used to vouch for {}. {} sertifikasında PdfCraft'ın tanımadığı kritik uzantılar var, bu yüzden {} için güvence olarak kullanılmıyor. + The certificate of {} is not a CA certificate that may issue certificates, so it is not used to vouch for {}. {} sertifikası, sertifika verebilen bir CA sertifikası değil, bu yüzden {} için güvence olarak kullanılmıyor. + The certificate of {} was not valid at the time of signing, so it is not used to vouch for {}. {} sertifikası imzalama sırasında geçerli değildi, bu yüzden {} için güvence olarak kullanılmıyor. + The checker found problems which may prevent the document from being fully accessible. Denetleyici, belgenin tam olarak erişilebilir olmasını engelleyebilecek sorunlar buldu. + The document has been altered or corrupted since the signature was applied. Belge, imza uygulandıktan sonra değiştirilmiş ya da bozulmuş. + The document has been altered or corrupted since the timestamp was applied. Belge, zaman damgası uygulandıktan sonra değiştirilmiş ya da bozulmuş. + The document has been altered since this signature was applied in ways it does not permit ({}). Belge, bu imza uygulandıktan sonra imzanın izin vermediği biçimlerde değiştirilmiş ({}). + The document has been altered since this timestamp was applied in ways it does not permit ({}). Belge, bu zaman damgası uygulandıktan sonra damganın izin vermediği biçimlerde değiştirilmiş ({}). + The document has been modified since this signature was applied, but the changes are permitted ({}). Belge, bu imza uygulandıktan sonra değiştirilmiş ancak değişikliklere izin veriliyor ({}). + The document has been modified since this timestamp was applied, but the changes are permitted ({}). Belge, bu zaman damgası uygulandıktan sonra değiştirilmiş ancak değişikliklere izin veriliyor ({}). + The document has no tags (structure tree) Belgede etiket (yapı ağacı) yok + The document has no title Belgenin başlığı yok + The document isn't marked as tagged (MarkInfo Marked) Belge etiketli olarak işaretlenmemiş (MarkInfo Marked) + The document isn't tagged, so none of its content is Belge etiketli değil, dolayısıyla içeriğinin hiçbir kısmı etiketli değil + The document's embedded revocation information shows that the signer's certificate has not been revoked. Belgeye gömülü iptal bilgileri, imzalayanın sertifikasının iptal edilmediğini gösteriyor. + The embedded timestamp token is valid and its authority is trusted; trusted time is {}. Gömülü zaman damgası belirteci geçerli ve yetkilisine güveniliyor; güvenilir zaman {}. + The font {} isn't embedded {} yazı tipi gömülü değil + The metadata doesn't identify the file as {} Meta veriler dosyayı {} olarak tanımlamıyor + The password is incorrect. Parola yanlış. + The password must have at least 6 characters. Parola en az 6 karakter olmalıdır. + The password must have at least 8 characters. Parola en az 8 karakter olmalıdır. + The passwords do not match. Parolalar eşleşmiyor. + The security settings don't allow screen readers to read the text Güvenlik ayarları ekran okuyucuların metni okumasına izin vermiyor + The signature algorithm and the SignerInfo's digest algorithm name different hashes; the signature was made with the SignerInfo's. İmza algoritması ile SignerInfo'nun özet algoritması farklı karma işlevleri belirtiyor; imza SignerInfo'dakiyle oluşturulmuş. + The signature carries an unverified timestamp ({}): the timestamp authority is not in your list of trusted certificates, so the signing time claimed by the signer is used instead. İmza doğrulanmamış bir zaman damgası taşıyor ({}): zaman damgası yetkilisi güvenilen sertifikalar listenizde değil, bu yüzden onun yerine imzalayanın bildirdiği imzalama zamanı kullanılıyor. + The signature contents are not hexadecimal. İmza içeriği onaltılık değil. + The signature could not be checked ({}). İmza denetlenemedi ({}). + The signature could not be read ({}). İmza okunamadı ({}). + The signature could not be verified ({}). İmza doğrulanamadı ({}). + The signature has no valid byte range. İmzanın geçerli bir bayt aralığı yok. + The signature includes an embedded timestamp. İmza gömülü bir zaman damgası içeriyor. + The signature is BER-encoded (indefinite lengths) rather than DER; it was read leniently. İmza DER yerine BER ile kodlanmış (belirsiz uzunluklar); esnek biçimde okundu. + The signature uses the legacy adbe.x509.rsa_sha1 format. İmza eski adbe.x509.rsa_sha1 biçimini kullanıyor. + The signature value does not match the signer's certificate: the signature is corrupt. İmza değeri imzalayanın sertifikasıyla eşleşmiyor: imza bozuk. + The signature's byte range does not exclude exactly its contents. İmzanın bayt aralığı tam olarak kendi içeriğini dışarıda bırakmıyor. + The signature's byte range does not match the file. İmzanın bayt aralığı dosyayla eşleşmiyor. + The signature's signed attributes have no content type, which CMS requires; it was read anyway. İmzanın imzalı özniteliklerinde CMS'in gerektirdiği içerik türü yok; yine de okundu. + The signature's signed attributes have no message digest, so the signature does not cover the document. İmzanın imzalı özniteliklerinde ileti özeti yok, bu yüzden imza belgeyi kapsamıyor. + The signature's signed attributes name a content type other than data, so it is not a signature of the document. İmzanın imzalı öznitelikleri data dışında bir içerik türü belirtiyor, bu yüzden bu bir belge imzası değil. + The signature's timestamp token could not be verified ({}). İmzanın zaman damgası belirteci doğrulanamadı ({}). + The signature's timestamp token does not cover the signature value. İmzanın zaman damgası belirteci imza değerini kapsamıyor. + The signed content is a constructed (segmented) OCTET STRING, as BER allows; it was read anyway. İmzalanan içerik, BER'in izin verdiği gibi oluşturulmuş (parçalı) bir OCTET STRING; yine de okundu. + The signer's certificate does not allow digital signatures (its key usage has neither digital signature nor non-repudiation). İmzalayanın sertifikası dijital imzaya izin vermiyor (anahtar kullanımında ne dijital imza ne de inkâr edilemezlik var). + The signer's certificate has been revoked ({}). İmzalayanın sertifikası iptal edilmiş ({}). + The signer's certificate has critical extensions PdfCraft does not recognize ({}). İmzalayanın sertifikasında PdfCraft'ın tanımadığı kritik uzantılar var ({}). + The signer's certificate is not in the signature. İmzalayanın sertifikası imzada yok. + The signer's certificate is not issued for signing documents (its extended key usage has no document-signing purpose). İmzalayanın sertifikası belge imzalamak için verilmemiş (genişletilmiş anahtar kullanımında belge imzalama amacı yok). + The signer's certificate was not valid at the time of signing. İmzalayanın sertifikası imzalama sırasında geçerli değildi. + The signer's identity is unknown because it has not been included in your list of trusted certificates and none of its parent certificates are trusted certificates. İmzalayanın kimliği bilinmiyor; çünkü güvenilen sertifikalar listenize eklenmemiş ve üst sertifikalarının hiçbiri güvenilen sertifika değil. + The signer's identity is valid. İmzalayanın kimliği geçerli. + The standard fonts can't draw “{c}” ({code}). Only Western European characters can be added as text for now. Standart yazı tipleri “{c}” ({code}) karakterini çizemiyor. Şimdilik metin olarak yalnızca Batı Avrupa karakterleri eklenebilir. + The timestamp authority's certificate is not issued for time stamping. Zaman damgası yetkilisinin sertifikası zaman damgalama için verilmemiş. + The timestamp authority's certificate was not valid at the time of timestamping. Zaman damgası yetkilisinin sertifikası zaman damgalama sırasında geçerli değildi. + The timestamp contents are not hexadecimal. Zaman damgası içeriği onaltılık değil. + The timestamp has no valid byte range. Zaman damgasının geçerli bir bayt aralığı yok. + The timestamp token could not be read ({}). Zaman damgası belirteci okunamadı ({}). + The timestamp token is valid and its authority is trusted. Zaman damgası belirteci geçerli ve yetkilisine güveniliyor. + The timestamp token is valid, but the timestamp authority is not in your list of trusted certificates. Zaman damgası belirteci geçerli ancak zaman damgası yetkilisi güvenilen sertifikalar listenizde değil. + The timestamp's byte range does not exclude exactly its contents. Zaman damgasının bayt aralığı tam olarak kendi içeriğini dışarıda bırakmıyor. + The timestamp's byte range does not match the file. Zaman damgasının bayt aralığı dosyayla eşleşmiyor. + The window shows the file name, not the title (Initial View > Show) Pencere başlığı değil dosya adını gösteriyor (İlk Görünüm > Göster) + Theme Tema + There is no folder to save the digital ID in. Dijital kimliğin kaydedileceği bir klasör yok. + This document has no text to make bookmarks from. Bu belgede yer işareti oluşturulacak metin yok. + This document has not been modified since this signature was applied. Bu belge, bu imza uygulandığından beri değiştirilmemiş. + This document has not been modified since this timestamp was applied. Bu belge, bu zaman damgası uygulandığından beri değiştirilmemiş. + This file changed on disk. Reload it to see the new version; your unsaved changes will be lost. Bu dosya diskte değişti. Yeni sürümü görmek için yeniden yükleyin; kaydedilmemiş değişiklikleriniz kaybolacak. + This signature uses RIPEMD-160, a legacy 160-bit hash algorithm that is no longer recommended for signatures. It still validates, but it should not be relied on. Bu imza, artık imzalar için önerilmeyen eski bir 160 bitlik karma algoritması olan RIPEMD-160'ı kullanıyor. Hâlâ doğrulanıyor ancak güvenilmemelidir. + This signature uses SHA-1, a weak hash algorithm: collisions in it have been demonstrated. It still validates because many documents signed years ago use it, but it should not be relied on. Bu imza, zayıf bir karma algoritması olan SHA-1'i kullanıyor: bu algoritmada çakışmalar gösterilmiştir. Yıllar önce imzalanmış birçok belge onu kullandığı için hâlâ doğrulanıyor ancak güvenilmemelidir. + This signature uses an RSA key shorter than 2048 bits, which is no longer considered strong enough for signatures. It still validates, but it should not be relied on. Bu imza, artık imzalar için yeterince güçlü sayılmayan, 2048 bitten kısa bir RSA anahtarı kullanıyor. Hâlâ doğrulanıyor ancak güvenilmemelidir. + Toolbar size Araç çubuğu boyutu + Unsigned signature field İmzalanmamış imza alanı + Unsigned signature field: {name} İmzalanmamış imza alanı: {name} + Unspecified Belirtilmemiş + Use Column Order Sütun Sırasını Kullan + Use Document Structure Belge Yapısını Kullan + Use Row Order Satır Sırasını Kullan + Vertical layout Dikey düzen + Warning Uyarı + Window Pencere + Zoom in (⌘+) Yakınlaştır (⌘+) + Zoom in / out (also pinch or ⌘-scroll) Yakınlaştır / uzaklaştır (iki parmakla sıkıştırma ya da ⌘-kaydırma ile de) + Zoom out (⌘−) Uzaklaştır (⌘−) + a table has 1 to {max} columns bir tabloda 1 ile {max} arası sütun olur + a table has 1 to {max} rows bir tabloda 1 ile {max} arası satır olur + alternate text hides an annotation inside it alternatif metin içindeki bir açıklamayı gizliyor + alternate text on an element with no page content sayfa içeriği olmayan bir öğede alternatif metin + bold kalın + comments yorumlar + document security store belge güvenlik deposu + document structure belge yapısı + form fill form doldurma + italic italik + its alternate text is inside another element's and will never be read alternatif metni başka bir öğeninkinin içinde ve hiçbir zaman okunmayacak + links bağlantılar + metadata meta veriler + no alternate text alternatif metin yok + no header cells (TH) başlık hücresi (TH) yok + no summary özet yok + not in a TR bir TR içinde değil + not in a Table, THead, TBody or TFoot bir Table, THead, TBody ya da TFoot içinde değil + not in an L (list) bir L (liste) içinde değil + not in an LI (list item) bir LI (liste öğesi) içinde değil + of / + other changes diğer değişiklikler + page content sayfa içeriği + page {n} is out of range (1–{count}) {n}. sayfa aralığın dışında (1–{count}) + pages added or removed eklenen ya da kaldırılan sayfalar + rows have between {min} and {max} columns satırlarda {min} ile {max} arası sütun var + the area, the spacing and the column widths must be numbers, the spacing 0 or more and each width more than 0 alan, aralık ve sütun genişlikleri sayı olmalı; aralık 0 veya daha büyük, her genişlik 0'dan büyük olmalı + the first heading is an H{n}; headings should not skip levels ilk başlık bir H{n}; başlıklar düzey atlamamalı + the first row number can be at most {max} ilk satır numarası en fazla {max} olabilir + the signed version could not be read imzalı sürüm okunamadı + {font}, {size} pt {font}, {size} pt + {n} lines {n} satır + {n} pages and no bookmarks {n} sayfa ve hiç yer işareti yok + {page} is not a page number or label {page} bir sayfa numarası ya da etiketi değil + {ty} element on page {p}: {what} {p}. sayfadaki {ty} öğesi: {what} + {ty} element: {what} {ty} öğesi: {what} + {who}, certificate issued by an unknown issuer. {who}, sertifikayı bilinmeyen bir yayımcı vermiş. + {who}, certificate issued by {issuer}. {who}, sertifikayı {issuer} vermiş. + {} annotation on page {p} isn't tagged {p}. sayfadaki {} açıklaması etiketli değil + {} annotations aren't allowed {} açıklamalarına izin verilmiyor + … and {n} more … ve {n} tane daha +@plural Delete {n} field|Delete {n} fields {n} alanı sil +@plural {n} byte|{n} bytes {n} bayt +@plural {n} comment|{n} comments {n} yorum +@plural {n} file|{n} files {n} dosya +@plural {n} image optimized|{n} images optimized {n} resim iyileştirildi +@plural {n} item discarded|{n} items discarded {n} öğe atıldı +@plural {n} pixel|{n} pixels {n} piksel +@plural {n} result|{n} results {n} sonuç +calendar weekday Fr Cu +calendar weekday Mo Pt +calendar weekday Sa Ct +calendar weekday Su Pz +calendar weekday Th Pe +calendar weekday Tu Sa +calendar weekday We Ça diff --git a/crates/ui-egui/src/lib.rs b/crates/ui-egui/src/lib.rs index c25dae98e3..643d5e90ff 100644 --- a/crates/ui-egui/src/lib.rs +++ b/crates/ui-egui/src/lib.rs @@ -311,6 +311,9 @@ pub struct PdfCraftApp { desktop_theme_enabled: bool, /// How far a mouse-wheel notch scrolls. pub scroll_speed: scroll_speed::ScrollSpeed, + /// Preferences ▸ Invert middle-button drag: the middle button's pan or auto-scroll moves the + /// view the other way. Off by default. + pub invert_middle_drag: bool, /// Preferences ▸ Animation effects: on, off, or as the system's animation setting says. pub animation_effects: motion::AnimationEffects, /// Whether the system asked for no animations, and how the desktop app asks it. diff --git a/crates/ui-egui/src/panels/edit.rs b/crates/ui-egui/src/panels/edit.rs index 2ba86ee5f5..2c2fb7a09a 100644 --- a/crates/ui-egui/src/panels/edit.rs +++ b/crates/ui-egui/src/panels/edit.rs @@ -55,6 +55,7 @@ pub(super) fn edit_panel(app: &mut PdfCraftApp, ui: &mut egui::Ui, t: &Tokens, g // Format text at the top while text is selected or being added. format_section(app, ui, t); egui::ScrollArea::vertical().auto_shrink([false, false]).show(ui, |ui| { + super::tools::clear_of_scrollbar(ui); widgets::section_title(ui, tl!("Modify page")); ui.horizontal(|ui| { ui.spacing_mut().item_spacing.x = 6.0; @@ -185,6 +186,7 @@ pub(super) fn stamp_palette(app: &mut PdfCraftApp, ui: &mut egui::Ui, t: &Tokens use pdfcraft_engine::{StampGroup, StampKind}; ui.label(egui::RichText::new(tl!("Choose a stamp, then click on the page to place it.")).small().color(t.text_faint)); egui::ScrollArea::vertical().auto_shrink([false, false]).show(ui, |ui| { + super::tools::clear_of_scrollbar(ui); for (group, title) in [ (StampGroup::Dynamic, tl!("Dynamic")), (StampGroup::SignHere, tl!("Sign Here")), diff --git a/crates/ui-egui/src/panels/format_text_ui.rs b/crates/ui-egui/src/panels/format_text_ui.rs index dbb50f73ec..99ffc054e1 100644 --- a/crates/ui-egui/src/panels/format_text_ui.rs +++ b/crates/ui-egui/src/panels/format_text_ui.rs @@ -107,6 +107,23 @@ const LABEL_ICON: f32 = 22.0; /// The button beside a number field that opens its list of common values: just an arrow, so the /// field keeps the room its value needs. const PRESET_LIST: f32 = 22.0; +/// The room a number field keeps for its value ("-5.0 pt"), beside the arrow in its box. +const NUMBER_MIN: f32 = 52.0; +/// The size field's room in the row: English "Mixed", its margins and the 2 pt of its box. The +/// field reserves room for "Mixed" so it doesn't resize while typing, but no more than this. +/// shortcut: a longer translation of "Mixed" scrolls in the field. Upgrade by having the panel +/// report its measured row width to the pane, if that reads badly. +const SIZE_FIELD: f32 = 62.0; +/// The least width the panel's widest rows need, which sets how narrow the Tools pane may be +/// dragged. Size and alignment: the size field and its arrow (in their box), the swatch, the +/// divider, three 30 pt buttons, and the gaps between those six. The spacing rows: two icons and +/// two number fields with their arrows (in a box each), the space between the columns, and four +/// gaps. +pub(crate) const MIN_ROW: f32 = { + let size_row = (SIZE_FIELD + PRESET_LIST + 2.0) + 28.0 + 9.0 + 3.0 * 30.0 + 5.0 * GAP; + let spacing_row = 2.0 * LABEL_ICON + 2.0 * (NUMBER_MIN + PRESET_LIST + 2.0) + 8.0 + 4.0 * GAP; + if size_row > spacing_row { size_row } else { spacing_row } +}; /// What can be typed: horizontal scale in percent, character spacing in points. const SCALE_RANGE: std::ops::RangeInclusive = 10.0..=400.0; const CHAR_SPACING_RANGE: std::ops::RangeInclusive = -5.0..=50.0; @@ -132,105 +149,112 @@ pub(crate) fn panel( // The font, across the panel. ui.spacing_mut().combo_height = 360.0; let width = ui.available_width(); - let font_resp = craft_ui::ComboBox::from_id_salt("format-font") - .selected_text(fonts.shown.as_str()) - .width(width) - .show_ui(ui, |ui| { - if let Some(sources) = fonts.sources { - if ui.selectable_label(false, tl!("Keep source fonts")).clicked() { - out.font = Some(FontChoice::KeepSource); + let font_resp = outlined(ui, |ui| { + craft_ui::ComboBox::from_id_salt("format-font") + .selected_text(fonts.shown.as_str()) + .width(width) + .show_ui(ui, |ui| { + if let Some(sources) = fonts.sources { + if ui.selectable_label(false, tl!("Keep source fonts")).clicked() { + out.font = Some(FontChoice::KeepSource); + } + for (resource, face) in sources.iter().filter(|(r, _)| !r.starts_with("PCApproved")) { + if ui.selectable_label(false, face).clicked() { + out.font = Some(FontChoice::Resource(resource.clone())); + } + } + ui.separator(); } - for (resource, face) in sources.iter().filter(|(r, _)| !r.starts_with("PCApproved")) { - if ui.selectable_label(false, face).clicked() { - out.font = Some(FontChoice::Resource(resource.clone())); + for f in [FontFamily::Helvetica, FontFamily::Times, FontFamily::Courier] { + if ui.selectable_label(fonts.sources.is_none() && look.family == f, f.label()).clicked() { + out.font = Some(FontChoice::Family(f)); } } - ui.separator(); - } - for f in [FontFamily::Helvetica, FontFamily::Times, FontFamily::Courier] { - if ui.selectable_label(fonts.sources.is_none() && look.family == f, f.label()).clicked() { - out.font = Some(FontChoice::Family(f)); - } - } - if fonts.sources.is_some() { - ui.separator(); - if ui.selectable_label(false, tl!("Load font…")).clicked() { - out.font = Some(FontChoice::Load); - } - #[cfg(not(target_arch = "wasm32"))] - ui.menu_button(tl!("Installed fonts…"), |ui| { - ui.set_min_width(260.0); - let reload = ui.button(tl!("Reload")).clicked(); - match crate::files::installed_font_files(ui.ctx(), reload) { - Some(list) if list.is_empty() => { - ui.label(tl!("No openly licensed document fonts found. Load a font file.")); - } - Some(list) => { - let search_id = ui.scope_id().with("installed-font-search"); - let mut query = ui.data(|d| d.get_temp::(search_id)).unwrap_or_default(); - ui.horizontal(|ui| { - let (icon_rect, _) = ui.allocate_exact_size(egui::vec2(16.0, 16.0), egui::Sense::hover()); - crate::icons::paint(ui, icon_rect, "search", 13.0, ui.visuals().text_color().gamma_multiply(0.6)); - let resp = ui - .add(egui::TextEdit::singleline(&mut query).hint_text(tl!("Search…")).desired_width(ui.available_width() - 8.0)); - if resp.changed() { - ui.data_mut(|d| d.insert_temp(search_id, query.clone())); - } - }); - ui.separator(); - - let query_lower = query.trim().to_lowercase(); - let mut families: std::collections::BTreeMap<&str, Vec<&pdfcraft_engine::text_fonts::FontFile>> = - std::collections::BTreeMap::new(); - for font in &list { - if query_lower.is_empty() - || font.family.to_lowercase().contains(&query_lower) - || font.face.to_lowercase().contains(&query_lower) - { - families.entry(&font.family).or_default().push(font); - } - } - - if families.is_empty() { + if fonts.sources.is_some() { + ui.separator(); + if ui.selectable_label(false, tl!("Load font…")).clicked() { + out.font = Some(FontChoice::Load); + } + #[cfg(not(target_arch = "wasm32"))] + ui.menu_button(tl!("Installed fonts…"), |ui| { + ui.set_min_width(260.0); + let reload = ui.button(tl!("Reload")).clicked(); + match crate::files::installed_font_files(ui.ctx(), reload) { + Some(list) if list.is_empty() => { ui.label(tl!("No openly licensed document fonts found. Load a font file.")); - } else { - egui::ScrollArea::vertical().max_height(350.0).show(ui, |ui| { - for (family, faces) in families { - if faces.len() == 1 { - if let Some(&font) = faces.first() { - let label = - if font.face != font.family && !font.face.is_empty() { font.face.as_str() } else { family }; - if ui.button(label).clicked() { - out.font = Some(FontChoice::Installed(font.path.clone())); - ui.close(); - } - } - } else { - ui.menu_button(family, |ui| { - ui.set_min_width(180.0); - for font in faces { + } + Some(list) => { + let search_id = ui.scope_id().with("installed-font-search"); + let mut query = ui.data(|d| d.get_temp::(search_id)).unwrap_or_default(); + ui.horizontal(|ui| { + let (icon_rect, _) = ui.allocate_exact_size(egui::vec2(16.0, 16.0), egui::Sense::hover()); + crate::icons::paint(ui, icon_rect, "search", 13.0, ui.visuals().text_color().gamma_multiply(0.6)); + let resp = ui.add( + egui::TextEdit::singleline(&mut query).hint_text(tl!("Search…")).desired_width(ui.available_width() - 8.0), + ); + if resp.changed() { + ui.data_mut(|d| d.insert_temp(search_id, query.clone())); + } + }); + ui.separator(); + + let query_lower = query.trim().to_lowercase(); + let mut families: std::collections::BTreeMap<&str, Vec<&pdfcraft_engine::text_fonts::FontFile>> = + std::collections::BTreeMap::new(); + for font in &list { + if query_lower.is_empty() + || font.family.to_lowercase().contains(&query_lower) + || font.face.to_lowercase().contains(&query_lower) + { + families.entry(&font.family).or_default().push(font); + } + } + + if families.is_empty() { + ui.label(tl!("No openly licensed document fonts found. Load a font file.")); + } else { + egui::ScrollArea::vertical().max_height(350.0).show(ui, |ui| { + for (family, faces) in families { + if faces.len() == 1 { + if let Some(&font) = faces.first() { let label = - font.face.strip_prefix(family).map(str::trim).filter(|s| !s.is_empty()).unwrap_or(&font.face); + if font.face != font.family && !font.face.is_empty() { font.face.as_str() } else { family }; if ui.button(label).clicked() { out.font = Some(FontChoice::Installed(font.path.clone())); ui.close(); } } - }); + } else { + ui.menu_button(family, |ui| { + ui.set_min_width(180.0); + for font in faces { + let label = font + .face + .strip_prefix(family) + .map(str::trim) + .filter(|s| !s.is_empty()) + .unwrap_or(&font.face); + if ui.button(label).clicked() { + out.font = Some(FontChoice::Installed(font.path.clone())); + ui.close(); + } + } + }); + } } - } - }); + }); + } + } + None => { + ui.label(tl!("Finding document fonts…")); } } - None => { - ui.label(tl!("Finding document fonts…")); - } - } - }); - ui.add_space(4.0); - } - }) - .response; + }); + ui.add_space(4.0); + } + }) + .response + }); font_resp.widget_info(|| egui::WidgetInfo::labeled(egui::Role::ComboBox, ui.is_enabled(), tl!("Font"))); font_resp.on_hover_text(format!("{}\n{}", tl!("Font"), tl!("Thai and Arabic use regular fallback fonts when available."))); ui.add_space(4.0); @@ -318,36 +342,49 @@ pub(crate) fn panel( // Line and paragraph spacing; horizontal scale and character spacing: two columns, each an // icon and its control, `half` wide. - let half = ((ui.available_width() - 2.0 * LABEL_ICON - 8.0 - 3.0 * GAP) / 2.0).max(40.0); + // From the font list's width, not what is left now: a row above that overflows (a long + // translation of "Mixed" in the size field) widens the panel's layout. + let half = ((width - 2.0 * LABEL_ICON - 8.0 - 3.0 * GAP) / 2.0).max(40.0); let editing = extras.is_some(); let mut fallback = Extras::default(); let e = extras.as_deref_mut().unwrap_or(&mut fallback); ui.add_enabled_ui(editing, |ui| { row(ui, |ui| { - labelled_icon(ui, t, "arrow-up-down", tl!("Line spacing")); + let label = labelled_icon(ui, t, "arrow-up-down", tl!("Line spacing")); let own = tl!("Auto").to_string(); let shown = if e.line_spacing == 0.0 { own.clone() } else { number(e.line_spacing) }; - let spacing_resp = craft_ui::ComboBox::from_id_salt("format-line-spacing") - .selected_text(shown) - .width(half) - .show_ui(ui, |ui| { - ui.selectable_value(&mut e.line_spacing, 0.0, own.as_str()); - for v in LINE_SPACINGS { - ui.selectable_value(&mut e.line_spacing, v, number(v)); - } - }) - .response; - spacing_resp.widget_info(|| egui::WidgetInfo::labeled(egui::Role::ComboBox, ui.is_enabled(), tl!("Line spacing"))); + outlined(ui, |ui| { + // The column is `half` wide in every language: a longer "Auto" is cut short (the + // menu and the tooltip have it whole). + ui.set_max_width(half); + let spacing_resp = craft_ui::ComboBox::from_id_salt("format-line-spacing") + .selected_text(centred(ui, &shown)) + .width(half) + .wrap_mode(egui::TextWrapMode::Truncate) + .show_ui(ui, |ui| { + ui.selectable_value(&mut e.line_spacing, 0.0, own.as_str()); + for v in LINE_SPACINGS { + ui.selectable_value(&mut e.line_spacing, v, number(v)); + } + }) + .response + .labelled_by(label.id); + spacing_resp.widget_info(|| egui::WidgetInfo::labeled(egui::Role::ComboBox, ui.is_enabled(), tl!("Line spacing"))); + spacing_resp.on_hover_text(&shown); + }); ui.add_space(8.0); ui.add_enabled_ui(false, |ui| { - labelled_icon(ui, t, "pilcrow", tl!("Paragraph spacing")); + let label = labelled_icon(ui, t, "pilcrow", tl!("Paragraph spacing")); let tip = format!("{} — {}", tl!("Paragraph spacing"), tl!("Planned")); - let _ = craft_ui::ComboBox::from_id_salt("format-paragraph-spacing") - .selected_text("0") - .width(half) - .show_ui(ui, |_| {}) - .response - .on_disabled_hover_text(tip); + let _ = outlined(ui, |ui| { + craft_ui::ComboBox::from_id_salt("format-paragraph-spacing") + .selected_text(centred(ui, "0")) + .width(half) + .show_ui(ui, |_| {}) + .response + .labelled_by(label.id) + .on_disabled_hover_text(tip) + }); }); }); }); @@ -373,6 +410,22 @@ pub(crate) fn panel( out } +/// Runs `add` with the panel's fields outlined and filled, so a list or number field reads as one +/// beside the plain icon buttons around it. +fn outlined(ui: &mut egui::Ui, add: impl FnOnce(&mut egui::Ui) -> R) -> R { + ui.scope(|ui| { + let t = Tokens::get(ui.ctx()); + let w = &mut ui.visuals_mut().widgets; + w.inactive.weak_bg_fill = t.field; + w.inactive.bg_stroke = Stroke::new(1.0, t.border); + w.hovered.bg_stroke = Stroke::new(1.0, t.text_muted); + // A list's text, pad and arrow touch: its gaps would widen it past the column it is given. + ui.spacing_mut().icon_spacing = 0.0; + add(ui) + }) + .inner +} + /// One row of the panel, [`ROW`] high, its controls [`GAP`] apart and centred on it. fn row(ui: &mut egui::Ui, add: impl FnOnce(&mut egui::Ui) -> R) -> R { let size = vec2(ui.available_width(), ROW); @@ -421,16 +474,48 @@ struct Number<'a> { suffix: &'static str, } +/// A combo box's selected text, centred in its button. The button lays out the text and then its +/// arrow, and every growing atom takes an equal share of the room left: a pad as wide as the arrow +/// before the text balances the arrow after it, and the text centres itself in its own share. Text +/// longer than the list is wide (a translated "Auto") is cut short rather than widening it. +fn centred<'a>(ui: &egui::Ui, text: &str) -> egui::Atoms<'a> { + use egui::AtomExt as _; + let pad = egui::Atom::custom(egui::IdSalt::new("combo-pad"), vec2(ui.spacing().icon_width, 0.0)).atom_grow(true); + let text = egui::Atom::from(text.to_string()).atom_grow(true).atom_shrink(true).atom_align(egui::Align2::CENTER_CENTER); + egui::Atoms::new((pad, text)) +} + +/// The arrow that lists a field's common values, centred on the 26-point field beside it. +fn preset_arrow(ui: &mut egui::Ui, label: &str) -> egui::Response { + let (slot, _) = ui.allocate_exact_size(vec2(PRESET_LIST, 26.0), Sense::hover()); + let at = Rect::from_center_size(slot.center(), vec2(PRESET_LIST, PRESET_LIST)); + ui.scope_builder(egui::UiBuilder::new().max_rect(at), |ui| icons::button(ui, "chevron-down", PRESET_LIST, false, label)).inner +} + +/// One box round a value and its arrow, like a list's, so the pair reads as a single control. +fn boxed(ui: &mut egui::Ui, add: impl FnOnce(&mut egui::Ui)) { + let t = Tokens::get(ui.ctx()); + let edge = if ui.is_enabled() { t.border } else { t.border.gamma_multiply(0.5) }; + egui::Frame::new().fill(t.field).stroke(Stroke::new(1.0, edge)).corner_radius(CornerRadius::same(4)).show(ui, |ui| { + let w = &mut ui.visuals_mut().widgets; + for state in [&mut w.inactive, &mut w.hovered, &mut w.active, &mut w.open] { + state.bg_stroke = Stroke::NONE; + } + w.inactive.weak_bg_fill = Color32::TRANSPARENT; + ui.spacing_mut().item_spacing.x = 0.0; + ui.spacing_mut().button_padding.x = 2.0; + add(ui); + }); +} + /// A number field with an arrow beside it that lists common values, in `width` all told: type any /// value in its range, or pick one. Both are named by `label`: the icon before them and its text. fn number_with_presets(ui: &mut egui::Ui, n: Number<'_>, presets: &[f64], width: f32, label: (egui::Id, &str)) { - ui.scope(|ui| { - ui.spacing_mut().item_spacing.x = 2.0; + boxed(ui, |ui| { let field = egui::DragValue::new(&mut *n.value).range(n.range).speed(n.speed).max_decimals(2).suffix(n.suffix); - let height = ui.spacing().interact_size.y; - let drag_resp = ui.add_sized([(width - PRESET_LIST - 2.0).max(30.0), height], field).labelled_by(label.0); + let drag_resp = ui.add_sized([(width - PRESET_LIST - 2.0).max(30.0), 26.0], field).labelled_by(label.0); drag_resp.widget_info(|| egui::WidgetInfo::labeled(egui::Role::SpinButton, ui.is_enabled(), label.1)); - let list = icons::button(ui, "chevron-down", PRESET_LIST, false, label.1); + let list = preset_arrow(ui, label.1); egui::Popup::menu(&list).show(|ui| { for &v in presets { if ui.selectable_label(*n.value == v, number(v)).clicked() { @@ -458,8 +543,9 @@ fn colour_button(ui: &mut egui::Ui, t: &Tokens, color: [f64; 3]) -> egui::Respon /// The bounds match AddedText validation, so the panel also accepts coloured text below 8 pt. fn font_size_input(ui: &mut egui::Ui, size: &mut f64, mixed: bool) -> bool { let mut committed = false; - ui.scope(|ui| { - ui.spacing_mut().item_spacing.x = 2.0; + // The panel's own padding, read before the box tightens it, so "Mixed" keeps its margins. + let margin = egui::Margin::from(ui.spacing().button_padding); + boxed(ui, |ui| { let id = ui.make_persistent_id("font-size-input"); let initial_text = || { if mixed || *size <= 0.0 { tl!("Mixed").to_string() } else { size.to_string() } @@ -472,11 +558,22 @@ fn font_size_input(ui: &mut egui::Ui, size: &mut f64, mixed: bool) -> bool { } // Reserve the localized mixed label, field margins and caret without resizing while typing. let font = egui::TextStyle::Body.resolve(ui.style()); - let margin = egui::Margin::from(ui.spacing().button_padding); let mixed_width = ui.painter().layout_no_wrap(tl!("Mixed").into(), font.clone(), ui.visuals().text_color()).size().x; - let width = (mixed_width + margin.sum().x + 2.0).ceil().max(40.0); - let field = egui::TextEdit::singleline(&mut text).id(id).font(font).margin(margin).desired_width(width); - let response = ui.add_sized([width, ui.spacing().interact_size.y], field).accessible_name(tl!("Font size:")); + // Within the row's allowance, so a long translation ("Valeurs différentes") scrolls in the + // field rather than pushing the row past the pane. + let width = (mixed_width + margin.sum().x + 2.0).ceil().clamp(40.0, SIZE_FIELD - 2.0); + let field = egui::TextEdit::singleline(&mut text) + .id(id) + .font(font) + .margin(margin) + .desired_width(width) + .frame(egui::Frame::NONE) + .align(egui::Align2::CENTER_CENTER); + let mut response = ui.add_sized([width, 26.0], field).accessible_name(tl!("Font size:")); + // A long translation of "Mixed" scrolls in the field: the tooltip has it whole. + if mixed { + response = response.on_hover_text(tl!("Mixed")); + } let cancel = (response.has_focus() || response.lost_focus()) && ui.input(|i| i.key_pressed(egui::Key::Escape)); if cancel { text = initial_text(); @@ -493,7 +590,7 @@ fn font_size_input(ui: &mut egui::Ui, size: &mut f64, mixed: bool) -> bool { } } let before = *size; - let list = icons::button(ui, "chevron-down", PRESET_LIST, false, tl!("Font size")); + let list = preset_arrow(ui, tl!("Font size")); egui::Popup::menu(&list).show(|ui| { for value in SIZES { if ui.selectable_label(*size == value, format!("{value} pt")).clicked() { diff --git a/crates/ui-egui/src/panels/page_selection_ui.rs b/crates/ui-egui/src/panels/page_selection_ui.rs index eb97b16b09..deb811768e 100644 --- a/crates/ui-egui/src/panels/page_selection_ui.rs +++ b/crates/ui-egui/src/panels/page_selection_ui.rs @@ -22,7 +22,9 @@ pub(crate) fn parse(text: &str, count: usize) -> Result, PrintError> let mut pages = BTreeSet::new(); let mut budget = 1_000_000usize; let number = |token: &str| { - let n = token.trim().parse::().map_err(|_| PrintError::NotAPage(token.into()))?; + let t = token.trim(); + let n = + if t.bytes().all(|b| b.is_ascii_digit()) { t.parse::().ok() } else { None }.ok_or_else(|| PrintError::NotAPage(token.into()))?; if n == 0 || n > count { Err(PrintError::OutOfRange(n, count)) } else { Ok(n - 1) } }; for part in text.split([',', ';']).map(str::trim) { @@ -132,6 +134,13 @@ impl PageSelectionInput { mod tests { use super::*; + #[test] + fn plus_sign_is_not_a_page_number() { + for text in ["+3", "+2-4", "2-+4"] { + assert!(matches!(parse(text, 100), Err(PrintError::NotAPage(_))), "{text}"); + } + } + #[test] fn selection_ranges_are_sorted_unique_and_bounded() { let pages = parse("1,12,16-18,89,92,93,97,99", 100).unwrap(); diff --git a/crates/ui-egui/src/panels/side_panels.rs b/crates/ui-egui/src/panels/side_panels.rs index 447aeac9fb..3676d9762b 100644 --- a/crates/ui-egui/src/panels/side_panels.rs +++ b/crates/ui-egui/src/panels/side_panels.rs @@ -17,7 +17,10 @@ use crate::{Mode, PdfCraftApp}; pub const TOOLS_WIDTH: f32 = 272.0; /// Default width of the side panel. pub const SIDE_WIDTH: f32 = 330.0; -const TOOLS_RANGE: RangeInclusive = 240.0..=520.0; +/// The Tools pane's own margins, left and right (14 pt each, and a pt of border), around what a panel lays out. +const TOOLS_GUTTERS: f32 = 30.0; +/// No narrower than Format text's widest row, so nothing in it is cut off. +const TOOLS_RANGE: RangeInclusive = (crate::format_text_ui::MIN_ROW + TOOLS_GUTTERS)..=520.0; const SIDE_RANGE: RangeInclusive = 260.0..=520.0; /// Version of the saved `side_panels` value. const VERSION: u64 = 1; @@ -387,6 +390,31 @@ fn open_panes(app: &PdfCraftApp) -> Vec { open } +/// Width of a pane's resize edge that takes the pointer, right of its border. +const RESIZE_GRIP: f32 = 4.0; + +/// Moves each open pane's resize edge to the right of its border (#5730). +/// +/// The host centres the edge on the border and widens it, so it reaches over whatever ends left +/// of the border. egui puts a vertical scrollbar at the right of its area, so that is the +/// scrollbar of the page beside a right-docked pane, or of the Inspector beside a right-docked +/// Tools pane, and its right half became the edge. Right of a border starts the next area, never +/// with a scrollbar: a right-docked pane's own scrollbar is at its far side, and a left-docked +/// pane keeps a gutter left of its border. +/// +/// The edge is the host's widget registered again with a smaller rect; egui keeps the last rect +/// for the next frame's hit test, and the layer is the one the host used. +fn keep_resize_edges_off_scrollbars(ui: &mut egui::Ui, host: egui::Id, open: &[Pane]) { + for pane in open { + let id = host.with(("pane", *pane)).with("resize"); + // An inert edge (bad geometry) senses no drag: leave it so. + let Some(edge) = ui.ctx().read_response(id).filter(|r| r.sense.senses_drag() && r.rect.is_positive()) else { continue }; + let border = edge.rect.center().x; + let grip = egui::Rect::from_x_y_ranges(border..=border + RESIZE_GRIP, edge.rect.y_range()); + ui.new_child(egui::UiBuilder::new().layer_id(edge.layer_id)).interact(grip, id, egui::Sense::drag()); + } +} + /// Draws the rail and the open panes. Call after the top bars and before the central panel. pub fn show(app: &mut PdfCraftApp, ui: &mut egui::Ui) { if let Some(panel) = app.right { @@ -408,13 +436,16 @@ pub fn show(app: &mut PdfCraftApp, ui: &mut egui::Ui) { let labels = PaneLabels { resize: crate::i18n::t("Resize panels").to_owned(), ..PaneLabels::default() }; let panels = app.side_panels; // Columns: both panes may share the right edge, Tools outermost, as `open` lists them. - let output = PaneHost::new(egui::Id::unique("pdfcraft-side-panels")) + let host = egui::Id::unique("pdfcraft-side-panels"); + let output = PaneHost::new(host) .policy(SidePolicy::Columns) .f6(false) .labels(labels) .frame(egui::Frame::NONE.fill(t.panel)) .body_margin(egui::Margin::ZERO) .show(ui, &open, |pane| Some(state_of(&panels, *pane)), &mut Content { app }); + + keep_resize_edges_off_scrollbars(ui, host, &open); for request in output.requests { match request { PaneRequest::Resize(pane, width) => app.side_panels.set_width(pane, width), @@ -505,11 +536,11 @@ mod tests { json!([]), json!([ ["inspector", {"floating": null, "anchor": "canvas", "placement": {"Split": "Right"}, "size": {"FixedSecond": 380.0}, "stack": null, "sibling": ["canvas"]}], - ["tools", {"floating": null, "anchor": "canvas", "placement": {"Split": "Right"}, "size": {"FixedSecond": 250.0}, "stack": null, "sibling": ["canvas"]}] + ["tools", {"floating": null, "anchor": "canvas", "placement": {"Split": "Right"}, "size": {"FixedSecond": 300.0}, "stack": null, "sibling": ["canvas"]}] ]), ); let restored = restore(&old); - assert_eq!(restored.panels, SidePanels { tools_side: ToolsSide::Right, rail_side: ToolsSide::Right, tools_width: 250.0, side_width: 380.0 }); + assert_eq!(restored.panels, SidePanels { tools_side: ToolsSide::Right, rail_side: ToolsSide::Right, tools_width: 300.0, side_width: 380.0 }); assert_eq!((restored.tools_open, restored.side_closed), (Some(false), true)); } diff --git a/crates/ui-egui/src/panels/tools.rs b/crates/ui-egui/src/panels/tools.rs index 73326fe571..fce62fb2ab 100644 --- a/crates/ui-egui/src/panels/tools.rs +++ b/crates/ui-egui/src/panels/tools.rs @@ -17,7 +17,7 @@ pub fn left_panel(app: &mut PdfCraftApp, ui: &mut egui::Ui) { if app.left == LeftPanel::Tool("organize") && app.active.and_then(|i| app.views.get(i)).is_some_and(|v| !v.organize) { app.left = crate::organize_panel::workspace_panel(app.mode); } - egui::Frame::NONE.fill(t.panel).inner_margin(egui::Margin { left: 14, right: 10, top: 12, bottom: 10 }).stroke(Stroke::new(1.0, t.divider)).show( + egui::Frame::NONE.fill(t.panel).inner_margin(egui::Margin { left: 14, right: 14, top: 12, bottom: 10 }).stroke(Stroke::new(1.0, t.divider)).show( ui, |ui| match app.left { // Organize pages has its own panel whenever the grid shows (with a document open). @@ -58,9 +58,15 @@ pub(crate) fn panel_header(ui: &mut egui::Ui, t: &Tokens, title: &str, lead: Opt (go_back, close) } -/// Width kept free at the right of the tool list for the floating scrollbar. +/// Width kept free at the right of a scrolling list for the floating scrollbar. const SCROLLBAR_GUTTER: f32 = 18.0; +/// The scrollbar floats over the right edge: keeps the rows of the scroll area `ui` is in (and +/// their rounded hover wash) clear of it. +pub(super) fn clear_of_scrollbar(ui: &mut egui::Ui) { + ui.set_max_width((ui.available_width() - SCROLLBAR_GUTTER).max(0.0)); +} + /// The All tools sidebar: Expand (the full view) and Close, then the tool list, the first few /// tools until View more shows them all. fn all_tools(app: &mut PdfCraftApp, ui: &mut egui::Ui, t: &Tokens) { @@ -73,8 +79,7 @@ fn all_tools(app: &mut PdfCraftApp, ui: &mut egui::Ui, t: &Tokens) { app.left_open = false; } egui::ScrollArea::vertical().auto_shrink([false, false]).show(ui, |ui| { - // The scrollbar floats over the right edge: keep the rows (and their rounded hover wash) clear of it. - ui.set_max_width((ui.available_width() - SCROLLBAR_GUTTER).max(0.0)); + clear_of_scrollbar(ui); ui.add_space(2.0); let shown = if app.all_tools_expanded { TOOL_GROUPS.len() } else { COLLAPSED_TOOLS.min(TOOL_GROUPS.len()) }; for g in &TOOL_GROUPS[..shown] { @@ -242,6 +247,7 @@ fn tool_detail(app: &mut PdfCraftApp, ui: &mut egui::Ui, t: &Tokens, g: &'static let marks = if footer { app.active_ids().and_then(|(_, id)| app.session.get(id)).map_or(0, |d| d.redaction_marks()) } else { 0 }; let list_h = if footer { (ui.available_height() - 52.0).max(80.0) } else { ui.available_height() }; egui::ScrollArea::vertical().auto_shrink([false, false]).max_height(list_h).show(ui, |ui| { + clear_of_scrollbar(ui); ui.add_space(2.0); for s in g.sections { widgets::section_title(ui, tl!(s.title)); diff --git a/crates/ui-egui/src/tools/comments/composer.rs b/crates/ui-egui/src/tools/comments/composer.rs index fa2d7f9b1a..8c3dee280c 100644 --- a/crates/ui-egui/src/tools/comments/composer.rs +++ b/crates/ui-egui/src/tools/comments/composer.rs @@ -111,7 +111,10 @@ pub(crate) fn composer(ctx: &egui::Context, view: &mut DocView, info: &DocInfo, return None; } let c = view.comments.composer.take()?; - let text = c.text.trim_end().to_string(); + let typewriter_edit = matches!(c.kind, ComposerKind::Edit(index) if info.annotations.iter().any(|a| + a.page == page && a.index == index && a.subtype == "FreeText" && a.intent.as_deref() == Some("FreeTextTypeWriter") + )); + let text = if typewriter_edit { c.text } else { c.text.trim_end().to_string() }; match c.kind { ComposerKind::Edit(index) => Some(Edit::SetAnnotationContents { page, index, text }), ComposerKind::Note => { diff --git a/crates/ui-egui/src/tools/edit_text_ui.rs b/crates/ui-egui/src/tools/edit_text_ui.rs index 19a165c152..681564c146 100644 --- a/crates/ui-egui/src/tools/edit_text_ui.rs +++ b/crates/ui-egui/src/tools/edit_text_ui.rs @@ -23,7 +23,8 @@ mod layout; pub(crate) use background::TextBackground; pub use image::{CropMode, DragTarget, ImageAction, ImageDrag, ImageHandle, ImageSelection, image_menu_id}; pub(crate) use image::{ - ImageCx, Matrix, body_hit as picture_hit, handle_hit as picture_handle_hit, image_context_menu, image_input, quad_contains, user_to_screen, + ImageCx, Matrix, body_hit as picture_hit, crop_controls_contain, handle_hit as picture_handle_hit, image_context_menu, image_input, + quad_contains, user_to_screen, }; #[cfg(test)] use image::{rotate_knob, turn_degrees, turn_degrees_delta}; diff --git a/crates/ui-egui/src/tools/edit_text_ui/image.rs b/crates/ui-egui/src/tools/edit_text_ui/image.rs index 281f7de80e..600f3d8801 100644 --- a/crates/ui-egui/src/tools/edit_text_ui/image.rs +++ b/crates/ui-egui/src/tools/edit_text_ui/image.rs @@ -246,6 +246,29 @@ fn same_rect(a: [f64; 4], b: [f64; 4]) -> bool { a.into_iter().zip(b).all(|(a, b)| (a - b).abs() < 1e-3) } +fn crop_bounds(image: &pdfcraft_engine::PageImage, xf: &PageXform, info: &DocInfo, page: usize) -> Rect { + let full = xf.user_rect(info, page, image.rect.map(|v| v as f32)); + if full.is_positive() { full } else { xf.user_rect(info, page, image.visible_rect.unwrap_or(image.rect).map(|v| v as f32)) } +} + +/// Whether `p` is on the crop box or one of its handles (#5835). The Done, Cancel and Remove +/// Crop pills are widgets of their own, so they take their clicks before the canvas does. +pub(crate) fn crop_controls_contain( + image: &pdfcraft_engine::PageImage, + mode: &CropMode, + xf: &PageXform, + info: &DocInfo, + page: usize, + p: Pos2, +) -> bool { + let b = crop_bounds(image, xf, info, page); + let k = xf.user_rect(info, page, mode.keep.map(|v| v as f32)).intersect(b); + if !b.is_finite() || !b.is_positive() || !b.size().is_finite() || !k.is_finite() || !k.is_positive() { + return false; + } + k.contains(p) || crop_handles(k).iter().any(|h| h.distance(p) < 10.0) +} + /// Crop mode for the selected image `i` whose visible frame is `b` (screen). Returns `true` /// (the pointer and keys are the crop's while it lasts). #[allow(clippy::cognitive_complexity)] @@ -254,8 +277,7 @@ fn crop_input(cx: &ImageCx<'_>, view: &mut DocView, i: usize, image: &pdfcraft_e let painter = ui.painter(); let Some(mode) = view.image_selection.as_mut().and_then(|s| s.crop.as_mut()) else { return false }; let hover_pos = ptr.pos; - let full_b = xf.user_rect(info, page, image.rect.map(|v| v as f32)); - let b = if full_b.is_positive() { full_b } else { xf.user_rect(info, page, image.visible_rect.unwrap_or(image.rect).map(|v| v as f32)) }; + let b = crop_bounds(image, xf, info, page); let keep_screen = |keep: [f64; 4]| xf.user_rect(info, page, keep.map(|v| v as f32)).intersect(b); let k = keep_screen(mode.keep); if !b.is_finite() || !b.is_positive() || !b.size().is_finite() || !k.is_finite() || !k.is_positive() { diff --git a/crates/ui-egui/src/tools/fill_sign.rs b/crates/ui-egui/src/tools/fill_sign.rs index 045bb64974..597e139c9e 100644 --- a/crates/ui-egui/src/tools/fill_sign.rs +++ b/crates/ui-egui/src/tools/fill_sign.rs @@ -490,7 +490,7 @@ pub(crate) fn page_input(cx: PageToolContext<'_>, input: PageInput<'_>, view: &m FillAction::Edit(Box::new(typed_with_color( tb.page, tb.at, - tb.text.trim(), + &tb.text, tb.size, crate::comments::page_rotation(info, tb.page), author, @@ -555,14 +555,20 @@ pub(crate) fn type_box(ctx: &egui::Context, view: &mut DocView, info: &DocInfo, let Some(t) = view.fill_text.as_mut() else { return }; // The box is white in every theme, so the caret must not follow the theme (pale in dark mode) (#655). ui.visuals_mut().text_cursor.stroke.color = crate::edit_text_ui::caret_color_on(Color32::WHITE); - let width = ((t.text.chars().count().max(8) as f32) * t.size as f32 * 0.6 * zoom).clamp(60.0, 600.0); + let font = egui::FontId::proportional((t.size as f32 * zoom).max(8.0)); + let natural = ui.fonts_mut(|f| f.layout_no_wrap(t.text.clone(), font.clone(), Color32::BLACK).size().x); + let margin = egui::Margin::symmetric(4, 2); + // Include the field padding and a pixel for layout rounding in the measured width. + let width = (natural + margin.sum().x + 1.0).max(8.0 * t.size as f32 * 0.6 * zoom).clamp(60.0, 600.0); // The area's max rect is last frame's size, which caps the edit's width; widen it so the // box grows as text is typed. ui.set_min_width(width); let r = ui .add( - egui::TextEdit::singleline(&mut t.text) - .font(egui::FontId::proportional((t.size as f32 * zoom).max(8.0))) + egui::TextEdit::multiline(&mut t.text) + .margin(margin) + .desired_rows(1) + .font(font) .desired_width(width) .background_color(Color32::from_rgba_unmultiplied(255, 255, 255, 230)) .text_color(crate::comments::color32(t.color)) @@ -587,7 +593,7 @@ pub(crate) fn type_box(ctx: &egui::Context, view: &mut DocView, info: &DocInfo, if commit { let tb = view.fill_text.take()?; if !tb.text.trim().is_empty() { - return Some(typed_with_color(tb.page, tb.at, tb.text.trim(), tb.size, crate::comments::page_rotation(info, tb.page), author, tb.color)); + return Some(typed_with_color(tb.page, tb.at, &tb.text, tb.size, crate::comments::page_rotation(info, tb.page), author, tb.color)); } } None diff --git a/crates/ui-egui/src/workflows/js_ui.rs b/crates/ui-egui/src/workflows/js_ui.rs index 70c3f775e9..c19ffcb66a 100644 --- a/crates/ui-egui/src/workflows/js_ui.rs +++ b/crates/ui-egui/src/workflows/js_ui.rs @@ -316,445 +316,10 @@ pub(crate) fn document_js_body(ui: &mut egui::Ui, app: &mut PdfCraftApp, t: &Tok close } -/// The height the Preferences dialog keeps below its scrolling settings for the OK row: the -/// button, and the space above it. -pub(crate) const PREFERENCES_BUTTON_ROW: f32 = 52.0; - -/// The least height the scrolling settings are given. The dialog around them takes about 80 more, -/// so this still fits the smallest window (520 pt) at the largest interface size (300%, which -/// leaves 173 pt): a taller floor would push OK off the screen again. -pub(crate) const PREFERENCES_MIN_SCROLL: f32 = 60.0; - -/// Whether the interface can draw a language picker's native name. On the web the browser's glyph -/// rasterizer draws scripts no embedded face has, so the native names stay; on native, ask the -/// fonts this build installed (including an installed fallback face, unless system fonts are off). -fn picker_text_is_drawable(ui: &egui::Ui, text: &str) -> bool { - #[cfg(target_arch = "wasm32")] - { - let _ = (ui, text); - true - } - #[cfg(not(target_arch = "wasm32"))] - { - ui.fonts_mut(|fonts| fonts.has_glyphs(&egui::FontId::proportional(13.0), text)) - } -} - -/// The date picker's displayed name. Its languages are the interface languages, so it uses the -/// same drawable-name fallback: a native name whose script this build has no face for would -/// otherwise abort under egui 0.37's `MissingGlyphPolicy::Panic` (for example Hindi without a -/// Devanagari face and installed system fonts turned off). -fn date_language_picker_name(l: &pdfcraft_engine::dates::DateLanguage, drawable: impl FnOnce(&str) -> bool) -> &'static str { - match crate::i18n::Lang::from_code(l.code) { - Some(language) => language.picker_name(drawable), - None => l.name, - } -} - -/// Preferences: interface language and size, appearance, identity and JavaScript. Drawn in a scroll -/// area; [`preferences_buttons`] goes below it, outside the scroll, so OK is always in reach. -pub(crate) fn preferences_body(ui: &mut egui::Ui, app: &mut PdfCraftApp, t: &Tokens) { - ui.label(egui::RichText::new(tl!("Preferences")).font(theme::semibold(18.0))); - ui.label(egui::RichText::new(tl!("Appearance")).font(theme::semibold(13.0))); - if ui.add(widgets::checkbox(&mut app.show_page_edge_shadows, tl!("Show Page Edge Shadows"))).changed() { - ui.ctx().request_repaint(); - } - ui.horizontal(|ui| { - let label = ui.label(tl!("Interface language")); - // A native name is only drawn when these fonts can draw it; otherwise the English name - // keeps the list readable instead of aborting on a missing glyph (for example Hindi - // without a Devanagari face, and installed system fonts turned off). - let (selected, picker) = { - let drawable = |text: &str| picker_text_is_drawable(ui, text); - let selected = crate::i18n::Lang::from_code(&app.language) - .map_or_else(|| tl!("Auto").to_owned(), |language| language.picker_name(drawable).to_owned()); - let picker = crate::i18n::Lang::for_picker_by(|language| language.picker_name(drawable)) - .into_iter() - .map(|language| (language, language.picker_name(drawable))) - .collect::>(); - (selected, picker) - }; - let before = app.language.clone(); - craft_ui::ComboBox::from_id_salt("interface-language") - .selected_text(selected) - .show_ui(ui, |ui| { - if ui.selectable_value(&mut app.language, crate::i18n::AUTO.to_string(), tl!("Auto")).clicked() { - ui.close(); - } - for (language, name) in &picker { - if ui.selectable_value(&mut app.language, language.code().to_string(), *name).clicked() { - ui.close(); - } - } - }) - .response - .labelled_by(label.id); - // Relabel the rest of this dialog in the new language right away, not next frame. - if app.language != before { - crate::i18n::set_current(crate::i18n::Lang::from_pref(&app.language)); - } - }); - ui.horizontal(|ui| { - use crate::ui_scale; - let label = ui.label(tl!("Interface size")); - // Auto shows the size it draws at: the display's scale times the system's text scale. - let native = ui.ctx().native_pixels_per_point().unwrap_or(1.0); - let auto_percent = ui_scale::percent(ui_scale::drawn(None, app.system_text_scale, native)); - let auto = crate::i18n::fmt(tl!("Auto ({percent}%)"), &[("percent", &auto_percent.to_string())]); - let selected = app.ui_scale.map_or_else(|| auto.clone(), |f| format!("{}%", ui_scale::percent(f))); - craft_ui::ComboBox::from_id_salt("interface-size") - .selected_text(selected) - .show_ui(ui, |ui| { - if ui.selectable_value(&mut app.ui_scale, None, auto).clicked() { - ui.close(); - } - for p in ui_scale::PRESETS { - let factor = f32::from(p) / 100.0; - if ui.selectable_label(app.ui_scale.is_some_and(|f| ui_scale::percent(f) == u32::from(p)), format!("{p}%")).clicked() { - app.ui_scale = Some(factor); - ui.close(); - } - } - }) - .response - .labelled_by(label.id); - }); - ui.label( - egui::RichText::new(tl!("Auto follows the system's text size. Pages always render at the display's full resolution.")) - .small() - .color(t.text_muted), - ); - ui.horizontal(|ui| { - ui.label(tl!("Tools panel side")); - let right = app.side_panels.tools_on_right(); - if ui.selectable_label(!right, tl!("Left")).clicked() { - app.side_panels.tools_side = crate::side_panels::ToolsSide::Left; - } - if ui.selectable_label(right, tl!("Right")).clicked() { - app.side_panels.tools_side = crate::side_panels::ToolsSide::Right; - } - }); - ui.horizontal(|ui| { - ui.label(tl!("Navigation rail side")); - let right = app.side_panels.rail_on_right(); - let left_btn = ui.selectable_label(!right, tl!("Left")); - left_btn.widget_info(|| { - egui::WidgetInfo::selected(egui::Role::Button, true, !right, format!("{}: {}", tl!("Navigation rail side"), tl!("Left"))) - }); - if left_btn.clicked() { - app.side_panels.rail_side = crate::side_panels::ToolsSide::Left; - } - let right_btn = ui.selectable_label(right, tl!("Right")); - right_btn.widget_info(|| { - egui::WidgetInfo::selected(egui::Role::Button, true, right, format!("{}: {}", tl!("Navigation rail side"), tl!("Right"))) - }); - if right_btn.clicked() { - app.side_panels.rail_side = crate::side_panels::ToolsSide::Right; - } - }); - ui.add_space(8.0); - crate::appearance::preferences_section(ui, app, t); - ui.add_space(8.0); - reading_colours_section(ui, app, t); - ui.add_space(8.0); - ui.label(egui::RichText::new(tl!("Documents and view")).font(theme::semibold(13.0))); - ui.horizontal(|ui| { - ui.label(tl!("Default workspace mode")); - for (mode, label) in [ - (crate::Mode::AllTools, "All tools"), - (crate::Mode::Read, "Read"), - (crate::Mode::Edit, "Edit"), - (crate::Mode::Convert, "Convert"), - (crate::Mode::Sign, "E-Sign"), - ] { - widgets::radio_value(ui, &mut app.default_mode, mode, tl!(label)); - } - }); - ui.label( - egui::RichText::new(tl!("Used when opening PDFs. An explicit launch or control mode takes precedence for the session.")) - .small() - .color(t.text_muted), - ); - let defaults = &mut app.view_defaults; - ui.horizontal(|ui| { - ui.label(tl!("Default page display")); - for l in crate::canvas::PageLayout::ORDER { - widgets::radio_value(ui, &mut defaults.layout, l, tl!(l.label())); - } - ui.add(widgets::checkbox(&mut defaults.continuous, tl!("Continuous scrolling"))); - }); - ui.add(widgets::checkbox(&mut defaults.show_page_gaps, tl!("Show gaps between pages"))); - ui.label(egui::RichText::new(tl!("Hide gaps to join page edges. Margins inside the PDF remain unchanged.")).small().color(t.text_muted)); - ui.horizontal(|ui| { - use crate::canvas::Fit; - ui.label(tl!("Default zoom")); - widgets::radio_value(ui, &mut defaults.fit, Fit::Width, tl!("Fit to width")); - widgets::radio_value(ui, &mut defaults.fit, Fit::Page, tl!("Zoom to page level")); - widgets::radio_value(ui, &mut defaults.fit, Fit::None, tl!("Custom")); - // Editing the percentage selects Custom. - let mut percent = defaults.zoom * 100.0; - if ui.add(egui::DragValue::new(&mut percent).range(8.0..=6400.0).max_decimals(0).suffix("%")).changed() { - (defaults.fit, defaults.zoom) = (Fit::None, percent / 100.0); - } - }); - ui.label( - egui::RichText::new(tl!("Used when a PDF doesn't ask for a layout or zoom. Continuous scrolling never snaps between pages.")) - .small() - .color(t.text_muted), - ); - ui.add(widgets::checkbox(&mut app.always_default_view, tl!("Always use my default zoom and page layout"))); - ui.horizontal(|ui| { - ui.label(tl!("Units")); - for u in crate::units::Unit::ALL { - widgets::radio_value(ui, &mut app.units, u, u.label()); - } - }); - ui.label(egui::RichText::new(tl!("For page sizes and margins.")).small().color(t.text_muted)); - // The web build has no file paths to list. - #[cfg(not(target_arch = "wasm32"))] - { - ui.horizontal(|ui| { - let label = ui.label(tl!("Recent files to keep")); - ui.add(egui::DragValue::new(&mut app.recent_limit).range(0..=crate::RECENT_FILES_MAX)).labelled_by(label.id); - }); - ui.label(egui::RichText::new(tl!("Lowering this forgets the oldest files. At 0 there is no list.")).small().color(t.text_muted)); - } - // The web build has no file paths to reopen. - #[cfg(not(target_arch = "wasm32"))] - ui.add(widgets::checkbox(&mut app.reopen_last_session, tl!("Reopen the files that were open when PdfCraft last closed"))); - // Acrobat's "Restore last view settings when reopening documents" (#1767). - #[cfg(not(target_arch = "wasm32"))] - ui.add(widgets::checkbox(&mut app.restore_last_view, tl!("Restore the last view (page, zoom and page display) when a document is opened again"))); - // The web build has no files on disk to watch. - #[cfg(not(target_arch = "wasm32"))] - ui.add(widgets::checkbox(&mut app.reload_changed_files, tl!("Reload documents when their files change on disk"))); - // The notice's "Don't show again" turns this off (#4035); the restrictions stay either way. - ui.add(widgets::checkbox(&mut app.show_secured_notice, tl!("Show a notice when a document is secured"))); - ui.horizontal(|ui| { - ui.label(tl!("Scroll speed (mouse wheel and arrow keys)")); - for speed in crate::scroll_speed::ScrollSpeed::ALL { - widgets::radio_value(ui, &mut app.scroll_speed, speed, tl_ctx!("scroll speed", speed.label())); - } - }); - // Whether anything animates, the wheel's scrolling and zooming included; left alone it - // follows the system's animation setting. - ui.horizontal(|ui| { - ui.label(tl!("Animation effects")); - for choice in crate::motion::AnimationEffects::ALL { - widgets::radio_value(ui, &mut app.animation_effects, choice, tl_ctx!("animation effects", choice.label())); - } - }); - // Only where the app draws the title bar (GNOME on Wayland); elsewhere the desktop draws it. - if app.window_controls.is_some() { - ui.add(widgets::checkbox(&mut app.system_title_bar, tl!("Use system title bar"))) - .on_hover_text(tl!("Show a basic title bar for the window buttons instead of the tab strip. GNOME doesn't draw title bars for apps, so this one doesn't follow its theme.")); - } - ui.add_space(8.0); - // Identity: the author of new comments (Acrobat: Preferences ▸ Identity). - ui.label(egui::RichText::new(tl!("Identity")).font(theme::semibold(13.0))); - ui.horizontal(|ui| { - let label = ui.label(tl!("Name on new comments")); - ui.add(crate::widgets::line(&mut app.comment_prefs.author).desired_width(220.0).char_limit(crate::MAX_AUTHOR_CHARS)).labelled_by(label.id); - }); - ui.add(widgets::checkbox(&mut app.comment_prefs.hide_empty_highlight_hover, tl!("Hide hover previews for highlights without comment text"))); - ui.add_space(8.0); - ui.label(egui::RichText::new(tl!("Fill & Sign")).font(theme::semibold(13.0))); - ui.add(widgets::checkbox(&mut app.flatten_fill_sign_on_save, tl!("Flatten Fill & Sign when saving"))); - ui.label( - egui::RichText::new(tl!("Text, marks and signatures become part of the page. Other comments stay editable.")).small().color(t.text_muted), - ); - ui.add_space(8.0); - date_format(ui, app, t); - ui.add_space(8.0); - ui.label(egui::RichText::new("JavaScript").font(theme::semibold(13.0))); - egui::Frame::new().fill(t.hover).corner_radius(egui::CornerRadius::same(6)).inner_margin(egui::Margin::same(10)).show(ui, |ui| { - ui.set_width(ui.available_width()); - let mut on = app.session.javascript(); - if ui.add(widgets::checkbox(&mut on, tl!("Enable Acrobat JavaScript"))).changed() { - app.session.set_javascript(on); - } - ui.label( - egui::RichText::new(tl!("Scripts run in a sandbox without file or network access. A script that asks to open a web page needs your permission first. With JavaScript off, Acrobat's standard format, validate and calculate functions still work.")) - .small() - .color(t.text_muted), - ); - }); -} - -/// The Preferences dialog's OK row. Returns `true` to close. -pub(crate) fn preferences_buttons(ui: &mut egui::Ui) -> bool { - ui.add_space(10.0); - buttons(ui, tl!("OK"), &[]).is_some() -} - -/// Preferences ▸ Date format: a preset, or any pattern typed in, for Fill & Sign dates, and the -/// language of its month and weekday names. A valid pattern applies as it's typed; an invalid -/// one stays in the box with the reason, and the last valid one stays in use. -fn date_format(ui: &mut egui::Ui, app: &mut PdfCraftApp, t: &Tokens) { - use pdfcraft_engine::dates::{DATE_FORMATS, DATE_LANGUAGES, MAX_DATE_FORMAT_CHARS}; - ui.label(egui::RichText::new(tl!("Date format")).font(theme::semibold(13.0))); - let sample = |app: &PdfCraftApp, f: &str| format!("{} {f}", app.date_text(Some(f)).unwrap_or_default()); - ui.horizontal(|ui| { - let label = ui.label(tl!("Fill & Sign dates")); - let current = app.session.date_format().to_string(); - let selected = if DATE_FORMATS.contains(¤t.as_str()) { sample(app, ¤t) } else { tl!("Custom").to_string() }; - craft_ui::ComboBox::from_id_salt("date-format") - .selected_text(selected) - .width(240.0) - .show_ui(ui, |ui| { - for f in DATE_FORMATS { - if ui.selectable_label(current == f, sample(app, f)).clicked() && app.session.set_date_format(f).is_ok() { - app.date_format_draft = None; - ui.close(); - } - } - }) - .response - .labelled_by(label.id); - }); - ui.horizontal(|ui| { - let label = ui.label(tl!("Pattern")); - let mut text = app.date_format_draft.clone().unwrap_or_else(|| app.session.date_format().to_string()); - let edit = ui.add(egui::TextEdit::singleline(&mut text).desired_width(160.0).char_limit(MAX_DATE_FORMAT_CHARS)).labelled_by(label.id); - // The box keeps the text as typed (a trailing space included) while it has focus; the - // setting takes the trimmed pattern whenever it's valid. - if edit.changed() { - let _ = app.session.set_date_format(&text); - app.date_format_draft = Some(text.clone()); - } - if !edit.has_focus() && pdfcraft_engine::dates::check_date_format(&text).is_ok() { - app.date_format_draft = None; - } - match app.date_text(Some(&text)) { - Ok(today) => ui.label(egui::RichText::new(crate::i18n::fmt(tl!("Today: {date}"), &[("date", &today)])).color(t.text_muted)), - // The engine's reason, in English. - Err(e) => ui.label(egui::RichText::new(e).color(egui::Color32::from_rgb(0xD1, 0x3B, 0x3B))), - }; - }); - // Fill & Sign refuses a date it would save as "?"; say so before anyone tries. - let bad = app.date_text(None).map(|today| pdfcraft_engine::dates::unwritable(&today)).unwrap_or_default(); - if !bad.is_empty() { - ui.label( - egui::RichText::new(crate::i18n::fmt( - tl!( - "{chars} can't be written into the PDF yet: Fill & Sign text is Western European only. Pick a numeric format such as dd.mm.yyyy." - ), - &[("chars", &bad)], - )) - .color(egui::Color32::from_rgb(0xD1, 0x3B, 0x3B)), - ); - } - ui.horizontal(|ui| { - let label = ui.label(tl!("Language")); - // Build every label before the combo box mutably borrows `ui`, with the same drawable - // fallback the interface language picker uses. - let (follow, selected, current, names) = { - let drawable = |text: &str| picker_text_is_drawable(ui, text); - let interface = crate::i18n::current().picker_name(drawable); - let follow = crate::i18n::fmt(tl!("Same as interface ({language})"), &[("language", interface)]); - let current = app.session.date_language().map(str::to_string); - let selected = DATE_LANGUAGES - .iter() - .find(|l| current.as_deref() == Some(l.code)) - .map_or_else(|| follow.clone(), |l| date_language_picker_name(l, drawable).to_string()); - let names = DATE_LANGUAGES.iter().map(|l| (l, date_language_picker_name(l, drawable))).collect::>(); - (follow, selected, current, names) - }; - craft_ui::ComboBox::from_id_salt("date-language") - .selected_text(selected) - .width(240.0) - .show_ui(ui, |ui| { - if ui.selectable_label(current.is_none(), follow).clicked() && app.session.set_date_language(None).is_ok() { - ui.close(); - } - for (l, name) in &names { - if ui.selectable_label(current.as_deref() == Some(l.code), *name).clicked() && app.session.set_date_language(Some(l.code)).is_ok() - { - ui.close(); - } - } - }) - .response - .labelled_by(label.id); - }); - ui.label( - egui::RichText::new(crate::i18n::fmt( - tl!("yyyy or yy year · m or mm month · mmm or mmmm month name · d or dd day · ddd or dddd weekday. H, h, M, s and t are time letters and can't be used on their own: put {escape} before a letter to show it as is."), - &[("escape", "\\")], - )) - .small() - .color(t.text_muted), - ); -} - -fn reading_colours_section(ui: &mut egui::Ui, app: &mut PdfCraftApp, t: &Tokens) { - // Reading colours (Acrobat: Replace Document Colors): solid text and line-art paints are - // remapped while rendering, and the page clears to the background colour. The preference - // is app-wide: every open document follows it, and documents open with it. - ui.label(egui::RichText::new(tl!("Reading colours")).font(theme::semibold(13.0))); - let mode = app.reading_colors.mode_name(); - ui.horizontal_wrapped(|ui| { - for (name, label, colors) in [ - ("off", "Off", pdfcraft_render::ReadingColors::default()), - ("black-on-white", "Black on white", pdfcraft_render::ReadingColors::BLACK_ON_WHITE), - ("white-on-black", "White on black", pdfcraft_render::ReadingColors::WHITE_ON_BLACK), - ("yellow-on-black", "Yellow on black", pdfcraft_render::ReadingColors::YELLOW_ON_BLACK), - ("green-on-black", "Green on black", pdfcraft_render::ReadingColors::GREEN_ON_BLACK), - ] { - let params = colors.params.unwrap_or(pdfcraft_render::ReadingParams { - text: [0, 0, 0], - background: [255, 255, 255], - only_black: false, - line_art: true, - }); - ui.vertical(|ui| { - ui.set_width(104.0); - let sample = egui::RichText::new("Aa").size(22.0).color(egui::Color32::from_rgb(params.text[0], params.text[1], params.text[2])); - let button = egui::Button::new(sample) - .fill(egui::Color32::from_rgb(params.background[0], params.background[1], params.background[2])) - .min_size(egui::vec2(94.0, 44.0)) - .stroke(egui::Stroke::new(if mode == name { 2.0 } else { 1.0 }, if mode == name { t.accent } else { t.border })); - let response = ui.add(button); - response.widget_info(|| egui::WidgetInfo::selected(egui::Role::Button, true, mode == name, tl!(label))); - if response.clicked() { - app.set_reading_colors(colors); - } - ui.label(tl!(label)); - }); - } - }); - ui.add_space(8.0); - if let Some(params) = app.reading_colors.params { - let text = egui::Color32::from_rgb(params.text[0], params.text[1], params.text[2]); - let background = egui::Color32::from_rgb(params.background[0], params.background[1], params.background[2]); - egui::Frame::new().fill(background).inner_margin(16.0).show(ui, |ui| { - ui.set_min_width((ui.available_width() - 32.0).max(0.0)); - ui.label(egui::RichText::new(tl!("Reading colours")).size(18.0).color(text)); - ui.label(egui::RichText::new(tl!("Colours are remapped while rendering; the document itself never changes.")).color(text)); - }); - } else { - ui.label(tl!("Original")); - } - egui::CollapsingHeader::new(tl!("Custom")).default_open(mode == "custom").show(ui, |ui| { - let mut colors = if app.reading_colors.params.is_some() { app.reading_colors } else { pdfcraft_render::ReadingColors::BLACK_ON_WHITE }; - let mut changed = false; - if let Some(params) = colors.params.as_mut() { - ui.horizontal(|ui| { - let text = ui.label(tl!("Text")); - changed |= ui.color_edit_button_srgb(&mut params.text).labelled_by(text.id).changed(); - let background = ui.label(tl!("Page background")); - changed |= ui.color_edit_button_srgb(&mut params.background).labelled_by(background.id).changed(); - }); - changed |= ui.add(crate::widgets::checkbox(&mut params.only_black, tl!("Only change the colour of black text or line art"))).changed(); - changed |= ui.add(crate::widgets::checkbox(&mut params.line_art, tl!("Change the colour of line art as well as text"))).changed(); - } - if changed { - app.set_reading_colors(colors); - } - }); - ui.label(egui::RichText::new(tl!("Colours are remapped while rendering; the document itself never changes.")).small().color(t.text_muted)); - ui.add_space(8.0); -} +#[expect(unused_imports, reason = "re-exported for tests and backward compatibility")] +pub(crate) use crate::dialogs::preferences::{ + PREFERENCES_BUTTON_ROW, PREFERENCES_MIN_SCROLL, date_language_picker_name, preferences_body, preferences_buttons, preferences_header, +}; #[cfg(test)] mod tests { diff --git a/crates/ui-egui/tests/it/comments.rs b/crates/ui-egui/tests/it/comments.rs index 6805732422..bd70d802ef 100644 --- a/crates/ui-egui/tests/it/comments.rs +++ b/crates/ui-egui/tests/it/comments.rs @@ -2925,7 +2925,7 @@ fn moved_fill_and_sign_text_is_drawn_where_it_goes_before_release() { click_pt(&mut h, (40.0, 150.0)); h.event(egui::Event::Text("WWWWWW".into())); h.run_steps(1); - h.key_press(egui::Key::Enter); + click(&mut h, pos2(350.0, 850.0)); // Outside the field: Enter now inserts a line break. h.run_steps(3); let a = comments(&h).into_iter().find(|a| a.contents.as_deref() == Some("WWWWWW")).expect("the typed text"); assert!(a.fill_sign && a.subtype == "FreeText", "{a:?}"); @@ -3199,6 +3199,29 @@ fn hotbar_vertical_size_and_docking() { assert_ne!(saved["hotbar"]["position"], moved["hotbar"]["position"]); } +#[test] +fn hotbar_settings_layout_and_side_controls_are_reachable_by_label() { + let mut h = harness(|_| {}); + h.get_by_label("Hotbar settings").click(); + h.run_steps(3); + fn vertical(h: &Harness<'static, PdfCraftApp>) -> serde_json::Value { + serde_json::from_str::(&h.state().persist()).unwrap()["hotbar"]["vertical"].clone() + } + let before = vertical(&h); + h.get_by_role_and_label(Role::Switch, "Vertical layout").click(); + h.run_steps(3); + assert_ne!(vertical(&h), before, "the layout switch toggles by its label"); + h.get_by_role_and_label(Role::RadioButton, "Right").click(); + h.run_steps(3); + let saved: serde_json::Value = serde_json::from_str(&h.state().persist()).unwrap(); + assert_eq!(saved["hotbar"]["dock"], "right"); + assert_eq!(saved["hotbar"]["vertical"], true, "docking at the side lays the bar out vertically"); + h.get_by_role_and_label(Role::RadioButton, "Float").click(); + h.run_steps(3); + let saved: serde_json::Value = serde_json::from_str(&h.state().persist()).unwrap(); + assert!(saved["hotbar"]["dock"].is_null()); +} + #[test] fn hotbar_settings_reopen_even_with_remembered_collapsed_state() { let mut h = harness(|_| {}); @@ -3246,5 +3269,195 @@ fn hotbar_full_side_strip_spans_each_edge_and_returns_to_float() { h.state_mut().set_option("hotbar-side", "float").unwrap(); h.run_steps(5); let size = h.ctx.data_mut(|d| d.get_temp::(egui::Id::unique("custom-hotbar"))).unwrap(); - assert!(size.x < 150.0 && size.y < 150.0, "floating toolbar is compact: {size:?}"); + let (length, thickness) = if size.y > size.x { (size.y, size.x) } else { (size.x, size.y) }; + assert!(thickness <= 64.0 && length < 550.0, "floating toolbar is compact: {size:?}"); +} + +#[test] +fn hotbar_docked_left_does_not_override_quick_tools() { + let mut h = harness(|app| { + app.set_option("hotbar-side", "left").unwrap(); + }); + h.run_steps(5); + // Controls in the docked bar share one layout, so none may overlap (#5890). + let labels = ["Drag hotbar", "Select (V)", "Hand (H)", "Add a sticky note", "Highlight", "Draw", "Fill & Sign", "Hotbar settings"]; + let rects: Vec<_> = labels.iter().map(|&label| h.get_by_label(label).rect()).collect(); + for (i, a) in rects.iter().enumerate() { + for (j, b) in rects.iter().enumerate().skip(i + 1) { + let overlap = a.min.x < b.max.x && b.min.x < a.max.x && a.min.y < b.max.y && b.min.y < a.max.y; + assert!(!overlap, "{} overlaps {}: {a:?} / {b:?}", labels[i], labels[j]); + } + } +} + +#[test] +fn hotbar_docked_in_compact_window_keeps_settings_button_visible() { + for side in ["left", "right"] { + let mut h = Harness::builder().with_size(egui::vec2(800.0, 480.0)).build_eframe(move |_cc| { + let mut app = PdfCraftApp::new(); + app.set_option("language", "en").unwrap(); + app.open_bytes("text.pdf", None, TEXT_FIXTURE.to_vec()).expect("opens"); + app.set_option("left", "closed").unwrap(); + app.set_option("hotbar-side", side).unwrap(); + app.set_option("hotbar-size", "48").unwrap(); + app + }); + h.run_steps(5); + let settings_rect = h.get_by_label("Hotbar settings").rect(); + assert!(settings_rect.max.y <= 480.0, "{side} hotbar settings button must stay within window height: {settings_rect:?}"); + } +} + +#[test] +fn hotbar_settings_menu_closes_on_click_outside() { + let mut h = harness(|app| { + app.open_bytes("text.pdf", None, TEXT_FIXTURE.to_vec()).expect("opens"); + }); + h.get_by_label("Hotbar settings").click(); + h.run_steps(3); + assert!(h.query_by_label("Close menu").is_some()); + + // Clicking outside on the canvas dismisses the settings menu + h.event(egui::Event::PointerButton { + pos: egui::pos2(600.0, 300.0), + button: egui::PointerButton::Primary, + pressed: true, + modifiers: Default::default(), + }); + h.event(egui::Event::PointerButton { + pos: egui::pos2(600.0, 300.0), + button: egui::PointerButton::Primary, + pressed: false, + modifiers: Default::default(), + }); + h.run_steps(3); + assert!(h.query_by_label("Close menu").is_none(), "clicking outside closes the hotbar settings menu"); + + // Reopening and clicking another tool outside dismisses the menu and activates that tool + h.get_by_label("Hotbar settings").click(); + h.run_steps(3); + assert!(h.query_by_label("Close menu").is_some()); + h.get_by_label("Hand (H)").click(); + h.run_steps(3); + assert!(h.query_by_label("Close menu").is_none()); + assert_eq!(h.state().quick_tool, QuickTool::Hand); +} + +#[test] +fn hotbar_picker_in_narrow_viewport_fits_within_screen_width() { + let mut h = Harness::builder().with_size(egui::vec2(270.0, 480.0)).build_eframe(|_cc| { + let mut app = PdfCraftApp::new(); + app.set_option("language", "en").unwrap(); + app.open_bytes("text.pdf", None, TEXT_FIXTURE.to_vec()).expect("opens"); + app + }); + h.get_by_label("Hotbar settings").click(); + h.run_steps(5); + let close_btn = h.get_by_label("Close menu"); + assert!(close_btn.rect().max.x <= 270.0, "Close menu button must stay within viewport width: {:?}", close_btn.rect()); +} + +#[test] +fn hotbar_floating_picker_does_not_overlap_rendered_bar() { + let mut h = Harness::builder().with_size(egui::vec2(1000.0, 600.0)).build_eframe(|_cc| { + let mut app = PdfCraftApp::new(); + app.set_option("language", "en").unwrap(); + app.open_bytes("text.pdf", None, TEXT_FIXTURE.to_vec()).expect("opens"); + app + }); + let settings_btn = h.get_by_label("Hotbar settings"); + let settings_rect = settings_btn.rect(); + settings_btn.click(); + h.run_steps(5); + + let picker_close = h.get_by_label("Close menu"); + let picker_rect = picker_close.rect(); + assert!( + picker_rect.min.x >= settings_rect.max.x || picker_rect.max.x <= settings_rect.min.x, + "picker ({:?}) must not overlap the settings button ({:?}) on the floating bar", + picker_rect, + settings_rect + ); +} + +fn edit_composer_preserves_only_typewriter_whitespace(kind: u8) { + let shots = std::env::var_os("PDFCRAFT_COMPOSER_SHOTS").is_some(); + let _gpu = shots.then(crate::gpu); + use pdfcraft_engine::{Edit, NewAnnotation, NoteIcon, Shape, Style}; + let mut h = harness(move |app| { + app.set_option("layout", "single").unwrap(); + app.set_option("panel", "comments").unwrap(); + app.quick_tool = QuickTool::Select; + // Both pages use index 0, with opposite intents. The lookup must use page AND index. + for page in 0..2 { + let typewriter = if page == 0 { kind != 0 } else { kind == 0 }; + let shape = if typewriter { + Shape::Typewriter { rect: [40.0, 40.0, 180.0, 90.0], font_size: 10.0 } + } else if kind == 2 { + Shape::Note { at: [80.0, 80.0], icon: NoteIcon::Comment } + } else { + Shape::TextBox { rect: [40.0, 40.0, 180.0, 90.0], font_size: 10.0 } + }; + let style = Style::default_for(&shape); + assert!(app.apply_edit(Edit::AddAnnotation(NewAnnotation { page, shape, style, contents: "Original".into(), author: "Tester".into() }))); + } + }); + h.state_mut().views[0].go_to_page(1); + h.run_steps(4); + support::settle(&mut h); + let point = { + let s = h.state(); + let v = &s.views[0]; + let doc = s.session.get(v.id).unwrap(); + let a = doc.info.annotations.iter().find(|a| a.page == 1 && a.index == 0).unwrap(); + let page = v.page_screen_rect(1).expect("the second page is visible"); + let info = &doc.info.pages[1]; + let p = info.user_to_view((a.rect[0] + a.rect[2]) / 2.0, (a.rect[1] + a.rect[3]) / 2.0); + page.min + egui::vec2(p[0], p[1]) * (page.width() / info.width) + }; + support::input::double_click(&mut h, point); + h.run_steps(3); + let c = h.state().views[0].comments.composer.as_ref().expect("double-click opens the edit composer"); + assert_eq!(c.page, 1); + assert_eq!(c.kind, pdfcraft_ui_egui::comments::ComposerKind::Edit(0)); + h.input_mut().events.push(egui::Event::Text(" edited\n\n".into())); + let ctx = h.ctx.clone(); + let mut raw = std::mem::take(h.input_mut()); + h.state_mut().prepare_raw_input(&ctx, &mut raw); + *h.input_mut() = raw; + h.step(); + h.run_steps(2); + assert_eq!(h.state().views[0].comments.composer.as_ref().unwrap().text, "Original edited\n\n"); + if shots { + h.render().unwrap().save(format!("/tmp/5954-composer-{kind}.png")).unwrap(); + } + h.get_all_by_label("Post").last().unwrap().click(); + h.run_steps(3); + assert!(h.state().views[0].comments.composer.is_none()); + let id = h.state().views[0].id; + let bytes = h.state().session.save_bytes(id).unwrap(); + // Check the raw saved string: ordinary-comment reader trimming must not hide a bad post. + let cos = pdfcraft_cos::Document::open(bytes.clone()).unwrap(); + let pages = pdfcraft_model::pages(&cos); + let annots = cos.resolve(pages[1].dict.get(b"Annots").unwrap()); + let annot = cos.resolve(&annots.as_array().unwrap()[0]); + let contents = cos.resolve(annot.as_dict().unwrap().get(b"Contents").unwrap()); + let expected = if kind == 0 { "Original edited\n\n" } else { "Original edited" }; + assert_eq!(contents.as_string().unwrap().to_text(), expected, "only a typewriter edit preserves trailing blank lines"); + let mut reopened = pdfcraft_engine::Session::new(); + let again = reopened.open("edited.pdf", None, bytes, None).unwrap(); + let saved = reopened.get(again).unwrap().info.annotations.iter().find(|a| a.page == 1 && a.index == 0).unwrap(); + assert_eq!(saved.contents.as_deref(), Some(expected)); +} + +#[test] +fn typewriter_edit_composer_keeps_trailing_blank_lines() { + edit_composer_preserves_only_typewriter_whitespace(0); +} + +#[test] +fn other_edit_composers_keep_trimming_trailing_whitespace() { + for kind in [1, 2] { + edit_composer_preserves_only_typewriter_whitespace(kind); + } } diff --git a/crates/ui-egui/tests/it/content.rs b/crates/ui-egui/tests/it/content.rs index ccc3945aaf..572bdf10f9 100644 --- a/crates/ui-egui/tests/it/content.rs +++ b/crates/ui-egui/tests/it/content.rs @@ -724,6 +724,68 @@ fn format_text_rows_line_up_and_fit_the_panel() { } } +/// The Tools pane can't be dragged narrower than Format text needs: at its smallest width no +/// control reaches past the font list, which spans the panel. +#[test] +fn format_text_fits_the_tools_pane_at_its_narrowest() { + use egui::accesskit::Role; + let mut h = harness(); + // At the largest interface size too: it scales points to pixels, and the layout is in points. + h.state_mut().set_option("ui-scale", "300").unwrap(); + h.state_mut().side_panels.tools_width = 0.0; + assert!(h.state_mut().execute("edit.text")); + h.run_steps(3); + let font = h.query_all_by_role(Role::ComboBox).find(|n| n.value().as_deref() == Some("Helvetica")).map(|n| n.rect()).expect("the font list"); + let rects = ["Alignment", "Colour", "Font size", "Character spacing", "Horizontal scale", "Line spacing", "Paragraph spacing"] + .into_iter() + .flat_map(|l| h.query_all_by_label(l).map(move |n| (l, n.rect()))) + .chain(h.query_all_by_role(Role::ComboBox).map(|n| ("list", n.rect()))) + .collect::>(); + for (label, r) in rects { + assert!(r.right() <= font.right() + 0.5, "{label} {r:?} reaches past the font list ({font:?})"); + } + // The font list ends where the pane's own content does: the header's Close button is its right edge. + let close = h.get_by_label("Close panel").rect(); + assert!((font.right() - close.right()).abs() < 1.5, "the font list {font:?} is not at the pane's content edge ({close:?})"); + // The rows below scroll, and the scrollbar floats over their right edge: they stop short of it. + let image = h.get_by_label("Image").rect(); + assert!(image.right() <= font.right() - 17.0, "the Image row {image:?} runs under the scrollbar ({font:?})"); + // The right-hand column ends where the font list does, as the left one starts where it does. + for label in ["Paragraph spacing", "Character spacing"] { + let right = h.query_all_by_label(label).map(|n| n.rect().right()).fold(f32::MIN, f32::max); + assert!((right - font.right()).abs() < 1.5, "{label} ends at {right}, the font list at {}", font.right()); + } +} + +/// The lists and the size row in Format text fit the narrowest Tools pane in every interface +/// language: "Auto" in the line spacing list and "Mixed" in the size field are translated, and in +/// Czech or French they are much longer. The font list spans the pane, so nothing may end past it. +#[test] +fn format_text_lists_fit_the_narrowest_tools_pane_in_every_language() { + use egui::accesskit::Role; + for lang in pdfcraft_ui_egui::i18n::Lang::all() { + let mut h = harness(); + // A script with no face on this machine (Lao without system fonts) can't be drawn at all. + if !h.ctx.fonts_mut(|f| f.has_glyphs(&egui::FontId::proportional(13.0), lang.name())) { + continue; + } + h.state_mut().set_option("language", lang.code()).unwrap(); + h.state_mut().side_panels.tools_width = 0.0; + assert!(h.state_mut().execute("edit.text")); + h.run_steps(3); + let lists: Vec = h.query_all_by_role(Role::ComboBox).map(|n| n.rect()).collect(); + // Found by its value (a font name, never translated), not as the widest list: an overrun + // could make another list the widest. + let font = h.query_all_by_role(Role::ComboBox).find(|n| n.value().as_deref() == Some("Helvetica")).map(|n| n.rect()).expect("the font list"); + for r in &lists { + assert!(r.right() <= font.right() + 0.5, "{}: {r:?} reaches past the font list ({font:?})", lang.code()); + } + // The size row too: its field reserves room for a translated "Mixed". + let align = h.get_by_label(pdfcraft_ui_egui::i18n::t("Alignment")).rect(); + assert!(align.right() <= font.right() + 0.5, "{}: Alignment {align:?} reaches past the font list ({font:?})", lang.code()); + } +} + #[test] fn format_text_panel_sets_alignment_and_lists_planned_controls_disabled() { use egui_kittest::kittest::NodeT; @@ -1428,3 +1490,23 @@ fn typing_in_one_tab_never_reaches_another_tabs_added_text() { h.run_steps(3); assert_eq!(h.state().views[1].content.draft.as_ref().map(|d| d.text.as_str()), Some("Reviewed"), "the other tab's typing stays out"); } + +/// The rail's page and zoom fields are the same size, and each sits wholly inside the rail, so +/// neither box is cut off at the edge (the page box lost its right side once the rail's contents +/// changed width). +#[test] +fn rail_page_and_zoom_fields_match_and_fit_the_rail() { + let mut h = harness(); + h.run_steps(3); + // The rail is 49 pt wide at the window's right edge (1400 pt wide), inside a 1 pt border. + let (rail_left, rail_right) = (1400.0 - 49.0 + 1.0, 1400.0 - 1.0); + let rail = h.get_by_label("Bookmarks").rect(); + let (page, zoom) = (h.get_by_label("Current page").rect(), h.get_by_label("Zoom").rect()); + assert_eq!((page.width(), page.height()), (zoom.width(), zoom.height()), "{page:?} vs {zoom:?}"); + // The size `RAIL_FIELD_SIZE` sets: wide enough for "6400%", the largest zoom. + assert_eq!((page.width(), page.height()), (42.0, 22.0), "{page:?}"); + for r in [page, zoom] { + assert!(r.left() >= rail_left && r.right() <= rail_right, "{r:?} is cut off by the rail ({rail_left}..{rail_right})"); + assert!((r.center().x - rail.center().x).abs() < 1.0, "{r:?} is off the rail's centre ({rail:?})"); + } +} diff --git a/crates/ui-egui/tests/it/control.rs b/crates/ui-egui/tests/it/control.rs index 6a0abd749b..c1465b233d 100644 --- a/crates/ui-egui/tests/it/control.rs +++ b/crates/ui-egui/tests/it/control.rs @@ -916,6 +916,25 @@ fn middle_button_pans_while_held_outside_linux() { assert!(!h.state().session.get(h.state().views[0].id).unwrap().dirty); } +/// With Invert middle-button drag on, a held middle drag moves the view the way the pointer goes. +#[cfg(not(target_os = "linux"))] +#[test] +fn inverted_middle_drag_moves_the_view_the_way_the_pointer_goes() { + let (mut h, c) = harness(); + h.state_mut().set_option("zoom", "400").unwrap(); + ok(&mut h, &c, "ui.set", json!({ "key": "invert_middle_drag", "value": "true" })); + h.run_steps(3); + h.state_mut().views[0].go_to_page(1); + h.run_steps(2); + let p = h.state().views[0].viewport_rect().center(); + let top = h.state().views[0].page_screen_rect(1).unwrap().top(); + ok(&mut h, &c, "ui.drag", json!({ "from": [p.x, p.y], "to": [p.x, p.y - 60.0], "steps": 12, "button": "middle" })); + h.run_steps(2); + let moved = h.state().views[0].page_screen_rect(1).unwrap().top(); + assert!((moved - (top + 60.0)).abs() < 1.0, "dragging up scrolls up, so the page moves down: {top} -> {moved}"); + assert!(!h.state().session.get(h.state().views[0].id).unwrap().dirty); +} + #[test] fn state_and_view_options() { let (mut h, c) = harness(); diff --git a/crates/ui-egui/tests/it/editing.rs b/crates/ui-egui/tests/it/editing.rs index 7b245a5a9e..c4231d0f69 100644 --- a/crates/ui-egui/tests/it/editing.rs +++ b/crates/ui-egui/tests/it/editing.rs @@ -7884,6 +7884,254 @@ fn test_image_context_menu_precedence() { assert!(h.query_all_by_label("Take a snapshot").next().is_none(), "canvas background menu must not trigger"); } +#[test] +fn test_image_context_menu_in_crop_mode_and_when_moved() { + let mut png = Vec::new(); + image::RgbImage::from_pixel(100, 100, image::Rgb([200, 40, 40])).write_to(&mut std::io::Cursor::new(&mut png), image::ImageFormat::Png).unwrap(); + let mut h = Harness::builder().with_size(egui::vec2(1400.0, 900.0)).build_eframe(move |_cc| { + let mut app = PdfCraftApp::new(); + app.set_option("language", "en").unwrap(); + app.open_bytes("picture.png", None, png.clone()).expect("opens"); + app + }); + h.run_steps(4); + let id = h.state().views[0].id; + // Shrink and center the picture on the page so page margins exist around it + let full = h.state().session.get(id).unwrap().page_images(0)[0].rect; + let (qw, qh) = ((full[2] - full[0]) / 4.0, (full[3] - full[1]) / 4.0); + let (mx, my) = ((full[0] + full[2]) / 2.0, (full[1] + full[3]) / 2.0); + h.state_mut().apply_edit(pdfcraft_engine::Edit::EditPageImage { + page: 0, + index: 0, + change: pdfcraft_engine::ImageEdit::Move([mx - qw, my - qh, mx + qw, my + qh]), + }); + h.run_steps(4); + + assert!(h.state_mut().execute("edit.edit_text")); + h.run_steps(2); + let r = h.state().views[0].page_screen_rect(0).expect("on screen"); + let c = r.center(); + + // Select the image + h.hover_at(c); + h.run_steps(1); + h.drag_at(c); + h.run_steps(1); + h.drop_at(c); + h.run_steps(2); + assert!(h.state().views[0].image_selection.is_some(), "selected"); + + // Enter crop mode: + let doc_id = h.state().views[0].id; + let original_rect = h.state().session.get(doc_id).unwrap().page_images(0)[0].rect; + h.state_mut().views[0].image_selection.as_mut().unwrap().crop = Some(pdfcraft_ui_egui::CropMode::new(original_rect)); + h.run_steps(2); + + // Set a smaller crop box that is moved towards top-left + let moved_crop = egui::Rect::from_center_size(c - egui::vec2(5.0, 5.0), egui::vec2(20.0, 20.0)); + set_crop_box(&mut h, moved_crop); + h.run_steps(2); + + // Simulate secondary click on the moved crop box + let click_pos = moved_crop.center(); + h.hover_at(click_pos); + h.run_steps(1); + h.event(egui::Event::PointerButton { pos: click_pos, button: egui::PointerButton::Secondary, pressed: true, modifiers: Default::default() }); + h.event(egui::Event::PointerButton { pos: click_pos, button: egui::PointerButton::Secondary, pressed: false, modifiers: Default::default() }); + h.run_steps(2); + + // In crop mode and when moved, do not open right click window when clicked on the image (#5835) + assert!(h.query_all_by_label("Rotate Clockwise").next().is_none(), "image context menu must not trigger in crop mode"); + assert!(h.query_all_by_label("Flip horizontal").next().is_none(), "image context menu must not trigger in crop mode"); + assert!(h.query_all_by_label("Rotate view clockwise").next().is_none(), "canvas background menu must not trigger in crop mode"); + assert!(h.query_all_by_label("Add bookmark").next().is_none(), "canvas background menu must not trigger in crop mode"); + assert!(h.query_all_by_label("Take a snapshot").next().is_none(), "canvas background menu must not trigger in crop mode"); + assert!(h.state().views[0].image_selection.as_ref().is_some_and(|s| s.crop.is_some()), "crop mode must remain active after right click on image"); + // Action pills remain visible and interactive + assert!(h.query_by_label("Done").is_some()); + assert!(h.query_by_label("Cancel").is_some()); + + // Right clicking outside the image on the page exits crop mode and opens the canvas background menu + let outside_pos = r.left_top() + egui::vec2(10.0, 10.0); + h.hover_at(outside_pos); + h.run_steps(1); + h.event(egui::Event::PointerButton { pos: outside_pos, button: egui::PointerButton::Secondary, pressed: true, modifiers: Default::default() }); + h.event(egui::Event::PointerButton { pos: outside_pos, button: egui::PointerButton::Secondary, pressed: false, modifiers: Default::default() }); + h.run_steps(2); + + assert!(h.state().views[0].image_selection.is_none(), "clicking outside clears image selection"); + assert!(h.query_all_by_label("Rotate view clockwise").next().is_some(), "canvas background menu triggers outside image"); +} + +fn crop_secondary_click(h: &mut Harness<'static, PdfCraftApp>, p: egui::Pos2) { + assert!(h.state().views[0].viewport_rect().contains(p), "test point must be visible: {p:?}"); + h.hover_at(p); + h.run_steps(1); + h.event(egui::Event::PointerButton { pos: p, button: egui::PointerButton::Secondary, pressed: true, modifiers: Default::default() }); + h.run_steps(1); + h.event(egui::Event::PointerButton { pos: p, button: egui::PointerButton::Secondary, pressed: false, modifiers: Default::default() }); + h.run_steps(2); +} + +fn assert_crop_context_preserved(h: &Harness<'static, PdfCraftApp>) { + let selection = h.state().views[0].image_selection.as_ref().expect("crop remains selected"); + assert_eq!(selection.index, 0, "an overlapping image must not steal the crop"); + assert!(selection.crop.is_some(), "crop mode remains active"); + for label in ["Flip horizontal", "Rotate view clockwise", "Take a snapshot"] { + assert!(h.query_all_by_label(label).next().is_none(), "unexpected menu: {label}"); + } + assert!(h.query_by_label("Done").is_some()); + assert!(h.query_by_label("Cancel").is_some()); +} + +#[test] +fn test_image_context_menu_crop_overlapping_image_and_handle() { + for rotation in [0, 90, 180, 270] { + let mut h = Harness::builder().with_size(egui::vec2(1400.0, 1400.0)).build_eframe(move |_cc| { + let mut app = PdfCraftApp::new(); + app.set_option("language", "en").unwrap(); + app.open_bytes("overlap.pdf", None, two_image_fixture()).unwrap(); + app.views[0].rotation = rotation; + app + }); + h.run_steps(4); + let id = h.state().views[0].id; + let rect = h.state().session.get(id).unwrap().page_images(0)[0].rect; + h.state_mut().apply_edit(pdfcraft_engine::Edit::EditPageImage { page: 0, index: 1, change: pdfcraft_engine::ImageEdit::Move(rect) }); + let images = h.state().session.get(id).unwrap().page_images(0); + assert_eq!(images.len(), 2); + assert_eq!(images[0].rect, images[1].rect, "fixture images must overlap"); + assert!(h.state_mut().execute("edit.edit_text")); + h.run_steps(4); + let mut selection = pdfcraft_ui_egui::ImageSelection::at(0, 0); + selection.crop = Some(pdfcraft_ui_egui::CropMode::new(rect)); + h.state_mut().views[0].image_selection = Some(selection); + h.run_steps(2); + let xf = h.state().views[0].page_xform(0).unwrap(); + let doc = h.state().session.get(id).unwrap(); + let image_rect = pdfcraft_ui_egui::canvas::image_screen_rect(&doc.page_images(0)[0], &xf, &doc.info, 0); + crop_secondary_click(&mut h, image_rect.center()); + assert_crop_context_preserved(&h); + // This point is outside both images, but inside the left handle's grip. + crop_secondary_click(&mut h, image_rect.left_center() - egui::vec2(5.0, 0.0)); + assert_crop_context_preserved(&h); + crop_secondary_click(&mut h, image_rect.left_center() - egui::vec2(20.0, 0.0)); + assert!(h.state().views[0].image_selection.is_none()); + assert!(h.query_by_label("Rotate view clockwise").is_some()); + } +} + +#[test] +fn test_image_context_menu_crop_page_edge_pills() { + for rotation in [0, 90, 180, 270] { + let mut h = Harness::builder().with_size(egui::vec2(1400.0, 1400.0)).build_eframe(move |_cc| { + let mut app = PdfCraftApp::new(); + app.set_option("language", "en").unwrap(); + app.open_bytes("edge.pdf", None, two_image_fixture()).unwrap(); + app.views[0].rotation = rotation; + app.views[0].fit = pdfcraft_ui_egui::canvas::Fit::Page; + app + }); + h.run_steps(4); + // A small image at a page corner exercises horizontal clamping and above placement. + let rect = [1.0, 1.0, 21.0, 21.0]; + h.state_mut().apply_edit(pdfcraft_engine::Edit::EditPageImage { page: 0, index: 0, change: pdfcraft_engine::ImageEdit::Move(rect) }); + h.state_mut().apply_edit(pdfcraft_engine::Edit::EditPageImage { + page: 0, + index: 1, + change: pdfcraft_engine::ImageEdit::Move([100.0, 150.0, 120.0, 170.0]), + }); + assert!(h.state_mut().execute("edit.edit_text")); + h.run_steps(4); + let mut selection = pdfcraft_ui_egui::ImageSelection::at(0, 0); + selection.crop = Some(pdfcraft_ui_egui::CropMode::new([2.0, 2.0, 20.0, 20.0])); + h.state_mut().views[0].image_selection = Some(selection); + h.run_steps(2); + for label in ["Done", "Cancel", "Remove Crop"] { + let p = h.get_by_label(label).rect().center(); + crop_secondary_click(&mut h, p); + assert_crop_context_preserved(&h); + } + // Beyond egui's 5-point interaction radius, empty space beside the rightmost pill is canvas. + let beside = h.get_by_label("Done").rect().right_center() + egui::vec2(8.0, 0.0); + let view = &h.state().views[0]; + let doc = h.state().session.get(view.id).unwrap(); + let xf = view.page_xform(0).unwrap(); + assert!( + doc.page_images(0).iter().all(|img| !pdfcraft_ui_egui::canvas::image_screen_rect(img, &xf, &doc.info, 0).contains(beside)), + "background test point must miss both images" + ); + crop_secondary_click(&mut h, beside); + assert!( + h.state().views[0].image_selection.is_none(), + "empty pill-adjacent space, rotation={rotation}, point={beside:?}, viewport={:?}, selection={:?}", + h.state().views[0].viewport_rect(), + h.state().views[0].image_selection + ); + assert!(h.query_by_label("Rotate view clockwise").is_some()); + } +} + +#[test] +fn test_rotated_image_crop_secondary_click_in_outer_bounding_box_clears_selection() { + let mut png = Vec::new(); + image::RgbImage::from_pixel(80, 80, image::Rgb([200, 40, 40])).write_to(&mut std::io::Cursor::new(&mut png), image::ImageFormat::Png).unwrap(); + let mut h = Harness::builder().with_size(egui::vec2(1400.0, 1400.0)).build_eframe(move |_cc| { + let mut app = PdfCraftApp::new(); + app.set_option("language", "en").unwrap(); + app.open_bytes("picture.png", None, png.clone()).expect("opens"); + app + }); + h.run_steps(4); + let id = h.state().views[0].id; + let full = h.state().session.get(id).unwrap().page_images(0)[0].rect; + let (qw, qh) = ((full[2] - full[0]) / 4.0, (full[3] - full[1]) / 4.0); + let (mx, my) = ((full[0] + full[2]) / 2.0, (full[1] + full[3]) / 2.0); + h.state_mut().apply_edit(pdfcraft_engine::Edit::EditPageImage { + page: 0, + index: 0, + change: pdfcraft_engine::ImageEdit::Move([mx - qw, my - qh, mx + qw, my + qh]), + }); + h.run_steps(4); + // Rotate the image by 45° + h.state_mut().apply_edit(pdfcraft_engine::Edit::EditPageImage { page: 0, index: 0, change: pdfcraft_engine::ImageEdit::RotateBy(45.0) }); + h.run_steps(4); + + assert!(h.state_mut().execute("edit.edit_text")); + h.run_steps(2); + let r = h.state().views[0].page_screen_rect(0).expect("on screen"); + let c = r.center(); + + // Select the image and put it into crop mode + h.hover_at(c); + h.run_steps(1); + h.drag_at(c); + h.run_steps(1); + h.drop_at(c); + h.run_steps(2); + assert!(h.state().views[0].image_selection.is_some(), "selected"); + + let doc_id = h.state().views[0].id; + let img = &h.state().session.get(doc_id).unwrap().page_images(0)[0]; + let (cx, cy) = ((full[0] + full[2]) / 2.0, (full[1] + full[3]) / 2.0); + let shrunk_crop = [cx - 5.0, cy - 5.0, cx + 5.0, cy + 5.0]; + h.state_mut().views[0].image_selection.as_mut().unwrap().crop = Some(pdfcraft_ui_egui::CropMode::new(shrunk_crop)); + h.run_steps(2); + + let xf = h.state().views[0].page_xform(0).unwrap(); + let doc_info = &h.state().session.get(doc_id).unwrap().info; + let b = pdfcraft_ui_egui::canvas::image_screen_rect(img, &xf, doc_info, 0); + + // The top-left corner of the axis-aligned bounding box `b` is outside the 45°-rotated diamond quad + let corner = b.left_top() + egui::vec2(2.0, 2.0); + assert!(b.contains(corner), "corner point is inside screen bounding box"); + + // Right-clicking at the corner must clear the crop selection and show the canvas context menu (#5900 review) + crop_secondary_click(&mut h, corner); + assert!(h.state().views[0].image_selection.is_none(), "clicking in outer bounding box of rotated image clears crop selection"); + assert!(h.query_by_label("Rotate view clockwise").is_some()); +} + #[test] fn crop_action_pills_interactive_and_apply_cancel_reset() { let mut png = Vec::new(); diff --git a/crates/ui-egui/tests/it/fill_sign.rs b/crates/ui-egui/tests/it/fill_sign.rs index ce21bd9f74..858e082137 100644 --- a/crates/ui-egui/tests/it/fill_sign.rs +++ b/crates/ui-egui/tests/it/fill_sign.rs @@ -130,7 +130,7 @@ fn text_marks_and_date() { click(&mut h, 50.0, 250.0); h.event(egui::Event::Text("Ada Lovelace".into())); h.run_steps(1); - h.key_press(egui::Key::Enter); + commit_typed_text(&mut h); h.run_steps(4); let v = items(&h); assert_eq!(v.len(), 4, "{v:?}"); @@ -139,9 +139,9 @@ fn text_marks_and_date() { assert!(v.iter().any(|(t, _)| t == "Stamp")); } -/// The open type box, found as the focused text input. +/// The open type box, found by its accessible name for either input role. fn type_box_rect(h: &Harness<'static, PdfCraftApp>) -> egui::Rect { - h.query_all_by_role(egui::accesskit::Role::TextInput).find(|n| n.is_focused()).expect("an open type box").rect() + h.get_by_label("Text to place").rect() } #[test] @@ -149,13 +149,13 @@ fn clicking_elsewhere_with_add_text_keeps_the_typed_text() { let mut h = harness(); h.state_mut().execute("sign.fill.text"); click(&mut h, 50.0, 250.0); - h.event(egui::Event::Text("Ada Lovelace".into())); + h.event(egui::Event::Text("\nAda\nLovelace\n".into())); h.run_steps(1); // Still on Add text: the next click starts a new box, and must keep the first one. click(&mut h, 50.0, 150.0); h.run_steps(2); let v = items(&h); - assert_eq!(v, vec![("FreeText".to_string(), Some("Ada Lovelace".to_string()))]); + assert_eq!(v, vec![("FreeText".to_string(), Some("\nAda\nLovelace\n".to_string()))]); assert!(h.state().views[0].fill_text.as_ref().is_some_and(|t| t.text.is_empty()), "a new, empty box is open"); } @@ -170,7 +170,7 @@ fn fill_text_size_controls_new_text_and_survives_settings_restore() { assert_eq!(h.state().views[0].fill_text.as_ref().map(|t| t.size), Some(24.0)); h.event(egui::Event::Text("Larger text".into())); h.run_steps(1); - h.key_press(egui::Key::Enter); + commit_typed_text(&mut h); h.run_steps(3); let annotation = h.state().session.get(h.state().views[0].id).unwrap().info.annotations.iter().find(|a| a.contents.as_deref() == Some("Larger text")).unwrap(); @@ -192,7 +192,7 @@ fn fill_text_size_resizes_the_selected_text() { click(&mut h, 50.0, 250.0); h.event(egui::Event::Text("Resize me".into())); h.run_steps(1); - h.key_press(egui::Key::Enter); + commit_typed_text(&mut h); h.run_steps(3); let height = |h: &Harness<'static, PdfCraftApp>| { let s = h.state(); @@ -297,7 +297,7 @@ fn fill_text_colour_survives_preview_commit_settings_and_save() { assert_eq!(h.state().views[0].fill_text.as_ref().unwrap().color, color, "the editor uses the selected colour"); h.event(egui::Event::Text("Blue form text".into())); h.run_steps(2); - h.key_press(egui::Key::Enter); + commit_typed_text(&mut h); h.run_steps(3); let id = h.state().views[0].id; let expected = color.map(|v| v as f32); @@ -1812,3 +1812,79 @@ fn mode_tabs_keep_the_hand_over_a_type_box_scrolled_under_them() { h.run_steps(3); assert_eq!(h.state().mode, pdfcraft_ui_egui::Mode::Convert, "the tab takes the click, not the text box"); } + +fn commit_typed_text(h: &mut Harness<'static, PdfCraftApp>) { + let p = pos2(350.0, 850.0); // Blank canvas outside the page and the type box. + h.hover_at(p); + h.drag_at(p); + h.run_steps(1); + h.drop_at(p); + h.run_steps(3); +} + +fn fill_input(h: &mut Harness<'static, PdfCraftApp>, events: impl IntoIterator) { + h.input_mut().events.extend(events); + let ctx = h.ctx.clone(); + let mut raw = std::mem::take(h.input_mut()); + h.state_mut().prepare_raw_input(&ctx, &mut raw); + *h.input_mut() = raw; + h.step(); + h.run_steps(2); +} + +fn fill_key(h: &mut Harness<'static, PdfCraftApp>, key: egui::Key) { + fill_input( + h, + [true, false].map(|pressed| egui::Event::Key { key, physical_key: Some(key), pressed, repeat: false, modifiers: egui::Modifiers::NONE }), + ); +} + +#[test] +fn fill_sign_enter_adds_lines_outside_click_commits_and_escape_cancels() { + let shots = std::env::var_os("PDFCRAFT_FILL_SIGN_SHOTS").is_some(); + let _gpu = shots.then(gpu); + let mut h = harness(); + assert!(h.state_mut().execute("sign.fill.text")); + click(&mut h, 50.0, 300.0); + let initial_height = type_box_rect(&h).height(); + fill_key(&mut h, egui::Key::Enter); + assert_eq!(h.state().views[0].fill_text.as_ref().map(|t| t.text.as_str()), Some("\n"), "Enter inserts a newline and keeps the editor open"); + fill_input(&mut h, [egui::Event::Text("Ada".into())]); + fill_key(&mut h, egui::Key::Enter); + fill_key(&mut h, egui::Key::Enter); + fill_input(&mut h, [egui::Event::Text("Lovelace".into())]); + fill_key(&mut h, egui::Key::Enter); + let text = "\nAda\n\nLovelace\n"; + assert_eq!(h.state().views[0].fill_text.as_ref().unwrap().text, text); + assert!(items(&h).is_empty(), "Enter never places an annotation"); + let galley = h + .output() + .shapes + .iter() + .find_map(|s| match &s.shape { + egui::Shape::Text(t) if t.galley.text() == text => Some(&t.galley), + _ => None, + }) + .unwrap(); + assert_eq!(galley.rows.len(), 5, "short typed lines fit without accidental soft wraps"); + assert!(type_box_rect(&h).height() > initial_height * 3.0, "the editor grows with its lines"); + if shots { + h.render().unwrap().save("/tmp/5850-multiline.png").unwrap(); + } + commit_typed_text(&mut h); + assert!(h.state().views[0].fill_text.is_none()); + assert_eq!(items(&h), [("FreeText".to_owned(), Some(text.to_owned()))]); + let id = h.state().views[0].id; + let saved = h.state().session.save_bytes(id).unwrap(); + let mut session = pdfcraft_engine::Session::new(); + let reopened = session.open("again.pdf", None, saved.clone(), None).unwrap(); + let annot = &session.get(reopened).unwrap().info.annotations[0]; + assert_eq!(annot.contents.as_deref(), Some(text)); + assert!(annot.rect[3] - annot.rect[1] >= 5.0 * 10.0 * 1.2, "the saved box keeps all five lines"); + click(&mut h, 50.0, 180.0); + fill_input(&mut h, [egui::Event::Text("Cancel me".into())]); + fill_key(&mut h, egui::Key::Enter); + fill_key(&mut h, egui::Key::Escape); + assert!(h.state().views[0].fill_text.is_none()); + assert_eq!(h.state().session.save_bytes(id).unwrap(), saved, "Escape cancels without writing"); +} diff --git a/crates/ui-egui/tests/it/preferences_layout.rs b/crates/ui-egui/tests/it/preferences_layout.rs index 1ebe06b7a0..e0a5d4e1cb 100644 --- a/crates/ui-egui/tests/it/preferences_layout.rs +++ b/crates/ui-egui/tests/it/preferences_layout.rs @@ -102,3 +102,152 @@ fn a_very_tall_window_does_not_leave_a_blank_gap_above_ok() { assert!(on_screen(ok, 2600.0) && on_screen(last, 2600.0), "{last:?} {ok:?}"); assert!(ok.min.y - last.max.y < 120.0, "a gap of {} pt between the last setting and OK", ok.min.y - last.max.y); } + +#[test] +fn segmented_pill_controls_switch_modes_and_layouts() { + let mut h = harness(900.0); + // Switch workspace mode via segmented pill + h.get_by_role_and_label(egui::accesskit::Role::RadioButton, "Convert").scroll_to_me(); + h.run_steps(3); + h.get_by_role_and_label(egui::accesskit::Role::RadioButton, "Convert").click(); + h.run_steps(2); + assert_eq!(h.state().default_mode, pdfcraft_ui_egui::Mode::Convert); + + let continuous_before = h.state().view_defaults.continuous; + + // Switch page layout via segmented pill + h.get_by_label("Two-page view").scroll_to_me(); + h.run_steps(3); + h.get_by_label("Two-page view").click(); + h.run_steps(2); + assert_eq!(h.state().view_defaults.layout, pdfcraft_ui_egui::canvas::PageLayout::TwoUp); + assert_eq!(h.state().view_defaults.continuous, continuous_before, "Two-page view retains continuous scrolling"); + + // Switch continuous scrolling pill (can be combined with Two-page view) + h.get_by_label("Continuous scrolling").click(); + h.run_steps(2); + assert_eq!(h.state().view_defaults.continuous, !continuous_before); + assert_eq!(h.state().view_defaults.layout, pdfcraft_ui_egui::canvas::PageLayout::TwoUp, "two-page continuous scrolling is supported"); + + // Switch to single page mode (continuous setting remains independent) + h.get_by_label("Single page").click(); + h.run_steps(2); + assert_eq!(h.state().view_defaults.layout, pdfcraft_ui_egui::canvas::PageLayout::Single); + assert_eq!(h.state().view_defaults.continuous, !continuous_before); + + // Switch tools panel side via segmented pill + h.get_by_label("Left").scroll_to_me(); + h.run_steps(3); + h.get_by_label("Left").click(); + h.run_steps(2); + assert_eq!(h.state().side_panels.tools_side, pdfcraft_ui_egui::side_panels::ToolsSide::Left); + + // Switch measurement units via segmented pill + h.get_by_label("pt").scroll_to_me(); + h.run_steps(3); + h.get_by_label("pt").click(); + h.run_steps(2); + assert_eq!(h.state().units, pdfcraft_ui_egui::units::Unit::Points); +} + +#[test] +fn search_settings_scans_and_highlights_in_situ_without_hiding_cards() { + let mut h = harness(900.0); + // Initially all card titles exist + assert!(h.query_by_label("General & Interface").is_some()); + assert!(h.query_by_label("Comment").is_some()); + assert!(h.query_by_label("JavaScript").is_some()); + + // Type "Hide hover" in search box + h.get_by_role_and_label(egui::accesskit::Role::TextInput, "Search settings…").click(); + h.run_steps(1); + h.get_by_role_and_label(egui::accesskit::Role::TextInput, "Search settings…").type_text("Hide hover"); + h.run_steps(4); + + // In browser-style search, cards are NOT hidden + assert!(h.query_by_label("General & Interface").is_some()); + assert!(h.query_by_label("Comment").is_some()); + assert!(h.query_by_label("JavaScript").is_some()); + + // The setting "Hide hover previews for highlights without comment text" is present and matched + assert!(h.query_by_label("Hide hover previews for highlights without comment text").is_some()); + // Match badge displays 1 match + assert!(h.query_by_label("1 match").is_some()); + + // Clearing search clears match badge + h.get_by_label("Clear search").click(); + h.run_steps(4); + assert!(h.query_by_label("1 match").is_none()); + + // Search for "javascript" + h.get_by_role_and_label(egui::accesskit::Role::TextInput, "Search settings…").click(); + h.run_steps(1); + h.get_by_role_and_label(egui::accesskit::Role::TextInput, "Search settings…").type_text("javascript"); + h.run_steps(4); + + // Cards remain visible and multiple matches are reported + assert!(h.query_by_label("JavaScript").is_some()); + assert!(h.query_by_label("General & Interface").is_some()); + assert!(h.query_by_label_contains("matches").is_some()); + + // Clearing search shows everything again + h.get_by_label("Clear search").click(); + h.run_steps(4); + assert!(h.query_by_label("General & Interface").is_some()); + assert!(h.query_by_label("Comment").is_some()); + assert!(h.query_by_label("JavaScript").is_some()); +} + +#[test] +fn preferences_dialog_scrollbar_spacing_and_controls() { + let h = harness(600.0); + let title = h.get_by(|n| n.role() == egui::accesskit::Role::Label && n.value().as_deref() == Some("Preferences")).rect(); + let search = h.get_by_role_and_label(egui::accesskit::Role::TextInput, "Search settings…").rect(); + let ok = h.get_by_label("OK").rect(); + assert!(on_screen(ok, 600.0)); + // Header title and search box are vertically aligned + assert!((title.center().y - search.center().y).abs() <= 2.0); + // Search box right edge is aligned within the dialog + assert!(search.max.x <= ok.max.x); +} + +#[test] +fn search_scrolls_option_only_and_theme_card_matches_into_visible_viewport() { + let mut h = harness(480.0); + let title = h.get_by(|n| n.role() == egui::accesskit::Role::Label && n.value().as_deref() == Some("Preferences")).rect(); + let ok = h.get_by_label("OK").rect(); + + // "Two-page view" is an option in Card 3 (Documents and view). + // In a 480 pt window, it starts out below the visible scroll viewport. + let opt_before = h.get_by_label("Two-page view").rect(); + assert!(opt_before.min.y >= ok.min.y, "Two-page option starts out below the visible viewport: {opt_before:?} vs OK {ok:?}"); + + // Searching "Two-page" (which only occurs inside that segmented pill option) + // auto-scrolls the matching option into the visible viewport between title and OK. + h.get_by_role_and_label(egui::accesskit::Role::TextInput, "Search settings…").click(); + h.run_steps(1); + h.get_by_role_and_label(egui::accesskit::Role::TextInput, "Search settings…").type_text("Two-page"); + h.run_steps(4); + + let opt_after = h.get_by_label("Two-page view").rect(); + assert!( + opt_after.min.y >= title.max.y && opt_after.max.y <= ok.min.y, + "Two-page option scrolled into visible scroll viewport: {opt_after:?} between title {title:?} and OK {ok:?}" + ); + + // Clear search and test a theme-card-only match + h.get_by_label("Clear search").click(); + h.run_steps(4); + + // Search for "Dark theme" (which occurs only in the dark theme card in Card 2). + h.get_by_role_and_label(egui::accesskit::Role::TextInput, "Search settings…").click(); + h.run_steps(1); + h.get_by_role_and_label(egui::accesskit::Role::TextInput, "Search settings…").type_text("Dark theme"); + h.run_steps(4); + + let dark_card = h.get_by_label("Dark theme").rect(); + assert!( + dark_card.min.y >= title.max.y && dark_card.max.y <= ok.min.y, + "Dark theme card scrolled into visible viewport: {dark_card:?} between title {title:?} and OK {ok:?}" + ); +} diff --git a/crates/ui-egui/tests/it/side_panels.rs b/crates/ui-egui/tests/it/side_panels.rs index 2436d41b61..d61187c143 100644 --- a/crates/ui-egui/tests/it/side_panels.rs +++ b/crates/ui-egui/tests/it/side_panels.rs @@ -15,8 +15,8 @@ trailer << /Root 1 0 R >> const WIDTH: f32 = 1400.0; const NO_BOOKMARKS: &str = "This document has no bookmarks."; -fn harness(setup: impl FnOnce(&mut PdfCraftApp) + 'static) -> Harness<'static, PdfCraftApp> { - let mut h = Harness::builder().with_size(egui::vec2(WIDTH, 900.0)).build_eframe(move |_cc| { +fn harness_sized(size: egui::Vec2, setup: impl FnOnce(&mut PdfCraftApp) + 'static) -> Harness<'static, PdfCraftApp> { + let mut h = Harness::builder().with_size(size).build_eframe(move |_cc| { let mut app = PdfCraftApp::new(); app.set_option("language", "en").unwrap(); app.open_bytes("doc.pdf", None, FIXTURE.to_vec()).unwrap(); @@ -27,6 +27,10 @@ fn harness(setup: impl FnOnce(&mut PdfCraftApp) + 'static) -> Harness<'static, P h } +fn harness(setup: impl FnOnce(&mut PdfCraftApp) + 'static) -> Harness<'static, PdfCraftApp> { + harness_sized(egui::vec2(WIDTH, 900.0), setup) +} + fn rail(h: &Harness<'static, PdfCraftApp>) -> egui::Rect { h.get_by_role_and_label(Role::Button, "Bookmarks").rect() } @@ -83,11 +87,11 @@ fn a_dragged_width_is_remembered_across_restarts() { // The side panel's resize edge: the one right of the page, left of the panel's text. let edge = h .get_all_by_label("Resize panels") - .map(|n| n.rect().center()) + .map(|n| n.rect().left_center()) .filter(|c| c.x < side_left && c.x > WIDTH / 2.0) .min_by(|a, b| (side_left - a.x).total_cmp(&(side_left - b.x))) .expect("the side panel has a resize edge") - // The pane's half of the edge: the page, drawn after the panes, takes the other half. + // 2 pt inside the panel: the edge lies right of the border, clear of the page's scrollbar. + egui::vec2(2.0, 0.0); h.hover_at(edge); h.run_steps(1); @@ -131,3 +135,146 @@ fn f4_toggles_the_side_panel_and_shift_f4_the_tools_panel() { h.run_steps(3); h.get_by_label("Expand all tools"); } + +#[test] +fn scrollbar_and_panel_resize_handle_do_not_collide_on_either_dock_side() { + // 1. Left docking: tools panel on the left (resize handle on the right, scrollbar on the right). + let mut h = harness_sized(egui::vec2(1200.0, 450.0), |app| { + app.all_tools_expanded = true; + }); + h.run_steps(4); + + let splitters: Vec<_> = h.get_all_by_label("Resize panels").collect(); + assert!(!splitters.is_empty(), "Splitter handle should exist"); + let splitter_rect = splitters[0].rect(); + + // Find the scrollbar belonging to the Tools panel (left side of the window). + let sb_node = h.get_all_by_role(Role::ScrollBar).find(|s| s.rect().max.x < 300.0).expect("Tools panel scrollbar should exist"); + let sb_rect = sb_node.rect(); + + // The scrollbar must sit strictly inside the panel, with clear gutter before the splitter. + assert!(sb_rect.max.x < splitter_rect.min.x); + assert!(splitter_rect.min.x - sb_rect.max.x >= 12.0, "Gutter must be at least 12px"); + + // Hovering directly over the scrollbar must NOT trigger panel resize cursor. + for x in [sb_rect.min.x, sb_rect.center().x, sb_rect.max.x - 0.5] { + h.hover_at(egui::pos2(x, sb_rect.center().y)); + h.run_steps(1); + let cursor = h.output().platform_output.cursor_icon; + assert_ne!(cursor, egui::CursorIcon::ResizeHorizontal, "Hovering scrollbar at x={x} should not trigger resize handle"); + } + + // Hovering directly on the splitter handle MUST trigger panel resize cursor. + h.hover_at(splitter_rect.center()); + h.run_steps(1); + assert_eq!(h.output().platform_output.cursor_icon, egui::CursorIcon::ResizeHorizontal); + + // Dragging the scrollbar down scrolls the content up without resizing the panel. + let initial_width = h.state().side_panels.tools_width; + let first_row_before = h.get_by_label("Edit a PDF").rect().top(); + h.hover_at(sb_rect.center()); + h.run_steps(1); + h.drag_at(sb_rect.center()); + h.run_steps(1); + h.hover_at(sb_rect.center() + egui::vec2(0.0, 60.0)); + h.run_steps(1); + h.drop_at(sb_rect.center() + egui::vec2(0.0, 60.0)); + h.run_steps(2); + let first_row_after = h.get_by_label("Edit a PDF").rect().top(); + assert!(first_row_after < first_row_before, "Content should scroll up when dragging scrollbar down"); + assert_eq!(h.state().side_panels.tools_width, initial_width, "Dragging scrollbar must not resize the panel"); + + // Dragging the splitter smoothly resizes the panel. + h.hover_at(splitter_rect.center()); + h.run_steps(1); + h.drag_at(splitter_rect.center()); + h.run_steps(1); + h.hover_at(splitter_rect.center() + egui::vec2(40.0, 0.0)); + h.run_steps(1); + h.drop_at(splitter_rect.center() + egui::vec2(40.0, 0.0)); + h.run_steps(2); + let after_width = h.state().side_panels.tools_width; + assert!(after_width > initial_width); + assert!((after_width - (initial_width + 40.0)).abs() <= 5.0); + + // 2. Right docking: tools panel on the right (resize handle on the left), next to the page's + // scrollbar (#5730). + let mut h_right = harness_sized(egui::vec2(1200.0, 450.0), |app| { + app.set_option("tools-side", "right").unwrap(); + app.all_tools_expanded = true; + }); + h_right.run_steps(4); + + let splitters_right: Vec<_> = h_right.get_all_by_label("Resize panels").collect(); + assert!(!splitters_right.is_empty()); + let right_splitter_rect = splitters_right[0].rect(); + let bars: Vec = h_right.get_all_by_role(Role::ScrollBar).map(|s| s.rect()).filter(|r| r.height() > 0.0).collect(); + // The page's scrollbar ends where the pane begins; the pane's own one is at its far side. + let page_bar = bars + .iter() + .copied() + .filter(|r| r.min.x < right_splitter_rect.center().x) + .max_by(|a, b| a.max.x.total_cmp(&b.max.x)) + .expect("the page has a scrollbar"); + assert!( + (right_splitter_rect.center().x - page_bar.max.x).abs() < 6.0, + "the page's scrollbar is beside the edge: {page_bar:?} {right_splitter_rect:?}" + ); + let tools_bar = bars.iter().copied().find(|r| r.min.x > right_splitter_rect.center().x).expect("Tools panel scrollbar should exist"); + let initial_right_width = h_right.state().side_panels.tools_width; + + // All of either scrollbar is the scrollbar, not the resize edge. + for bar in [page_bar, tools_bar] { + for x in [bar.min.x + 0.5, bar.center().x, bar.max.x - 0.5] { + h_right.hover_at(egui::pos2(x, bar.center().y)); + h_right.run_steps(1); + let cursor = h_right.output().platform_output.cursor_icon; + assert_ne!(cursor, egui::CursorIcon::ResizeHorizontal, "Hovering scrollbar {bar:?} at x={x} should not trigger resize handle"); + } + } + + // Dragging either scrollbar by its right edge scrolls its content and leaves the width alone. + let drag = |h: &mut Harness<'static, PdfCraftApp>, at: egui::Pos2| { + h.hover_at(at); + h.run_steps(1); + h.drag_at(at); + h.run_steps(1); + h.hover_at(at + egui::vec2(0.0, 60.0)); + h.run_steps(1); + h.drop_at(at + egui::vec2(0.0, 60.0)); + h.run_steps(2); + }; + let page_top = |h: &Harness<'static, PdfCraftApp>| h.state().views[0].page_screen_rect(0).expect("page on screen").min.y; + let before = page_top(&h_right); + drag(&mut h_right, egui::pos2(page_bar.max.x - 1.0, page_bar.center().y)); + assert!(page_top(&h_right) < before, "dragging the page's scrollbar scrolls the page"); + assert_eq!(h_right.state().side_panels.tools_width, initial_right_width, "Dragging scrollbar must not resize the panel"); + let before = h_right.get_by_label("Edit a PDF").rect().top(); + drag(&mut h_right, egui::pos2(tools_bar.max.x - 1.0, tools_bar.center().y)); + assert!(h_right.get_by_label("Edit a PDF").rect().top() < before, "Content should scroll up when dragging scrollbar down"); + assert_eq!(h_right.state().side_panels.tools_width, initial_right_width, "Dragging scrollbar must not resize the panel"); + + // Splitter is at the left boundary of the right-docked pane. + h_right.hover_at(right_splitter_rect.center()); + h_right.run_steps(1); + assert_eq!(h_right.output().platform_output.cursor_icon, egui::CursorIcon::ResizeHorizontal); + + // Dragging the splitter on right-docked pane smoothly resizes. + h_right.hover_at(right_splitter_rect.center()); + h_right.run_steps(1); + h_right.drag_at(right_splitter_rect.center()); + h_right.run_steps(1); + // Moving left increases width of right-docked pane + h_right.hover_at(right_splitter_rect.center() - egui::vec2(30.0, 0.0)); + h_right.run_steps(1); + h_right.drop_at(right_splitter_rect.center() - egui::vec2(30.0, 0.0)); + h_right.run_steps(2); + let after_right_width = h_right.state().side_panels.tools_width; + assert!(after_right_width > initial_right_width); + assert!((after_right_width - (initial_right_width + 30.0)).abs() <= 5.0); + + // Inside the right-docked panel (e.g. 15px inside from the splitter), cursor is not resize. + h_right.hover_at(right_splitter_rect.center() + egui::vec2(15.0, 0.0)); + h_right.run_steps(1); + assert_ne!(h_right.output().platform_output.cursor_icon, egui::CursorIcon::ResizeHorizontal); +} diff --git a/crates/ui-egui/tests/it/theme.rs b/crates/ui-egui/tests/it/theme.rs index a02c5c05ca..1f2709cd56 100644 --- a/crates/ui-egui/tests/it/theme.rs +++ b/crates/ui-egui/tests/it/theme.rs @@ -242,11 +242,11 @@ fn preferences_theme_cards_and_use_system_setting_stay_in_sync() { assert_theme(&h, ThemePreference::System, ThemeKind::Dark); assert_eq!(mode_shown(&h), "Use system setting"); - // The OS is dark: the Dark card's radio row picks Dark, and the combo box says so. + // The OS is dark: the Dark card picks Dark, and the combo box says so. // The cards sit below the fold of the Preferences scroll area at this window size. - h.get_by_label("Dark gray").scroll_to_me(); + h.get_by_label("Dark theme").scroll_to_me(); h.run_steps(3); - h.get_by_label("Dark gray").click(); + h.get_by_label("Dark theme").click(); h.run_steps(3); assert_theme(&h, ThemePreference::Dark, ThemeKind::Dark); assert_eq!(mode_shown(&h), "Dark"); diff --git a/crates/ui-egui/tests/it/view.rs b/crates/ui-egui/tests/it/view.rs index 7f444bee0f..0e9443bf51 100644 --- a/crates/ui-egui/tests/it/view.rs +++ b/crates/ui-egui/tests/it/view.rs @@ -520,6 +520,98 @@ fn single_page_swipe_that_reaches_the_edge_does_not_turn_but_a_fresh_one_does() ); } +#[test] +fn single_page_wheel_at_last_page_bottom_edge_can_scroll_back_up() { + let mut h = harness_stepping(1.0 / 60.0, &[("layout", "single"), ("zoom", "200")]); + h.state_mut().views[0].go_to_page(2); // Go to last page of PAGES (3 pages) + h.run_steps(20); + let at = h.state().views[0].viewport_rect().center(); + h.hover_at(at); + h.run_steps(4); + + // Scroll to the bottom edge of page 3 + let mut notches = 0; + let mut last = rect(&h, 2).expect("page 3 on screen").min.y; + let mut at_bottom = false; + while notches < 80 { + h.event(wheel(MouseWheelUnit::Line, -1.0, TouchPhase::Move)); + h.run_steps(12); + notches += 1; + if let Some(r) = rect(&h, 2) { + if (r.min.y - last).abs() < 0.01 { + at_bottom = true; + break; + } + last = r.min.y; + } + } + assert!(at_bottom, "reached bottom edge of last page"); + assert_eq!(h.state().views[0].current, 2, "remains on page 3"); + + // Push the wheel further against the bottom edge (cannot turn because it's the last page) + for _ in 0..5 { + h.event(wheel(MouseWheelUnit::Line, -1.0, TouchPhase::Move)); + h.run_steps(12); + } + let bottom_y = rect(&h, 2).expect("page 3 on screen").min.y; + + // Roll the wheel back up: the page must move away from the bottom edge (#5713) + h.event(wheel(MouseWheelUnit::Line, 1.0, TouchPhase::Move)); + h.run_steps(12); + let after_up_y = rect(&h, 2).expect("page 3 on screen").min.y; + assert!(after_up_y > bottom_y, "scrolling up moves the page away from the bottom edge: {after_up_y} > {bottom_y}"); +} + +/// One notch of a mouse wheel that macOS reports in points (a Logitech mouse sends about 14). +const POINT_NOTCH: f32 = 14.0; + +#[test] +fn single_page_point_notches_pan_the_page_a_notch_turned_to() { + let mut h = harness_stepping(1.0 / 60.0, &[("layout", "single"), ("zoom", "200")]); + let at = h.state().views[0].viewport_rect().center(); + h.hover_at(at); + h.run_steps(20); + for _ in 0..120 { + h.event(wheel(MouseWheelUnit::Point, -POINT_NOTCH, TouchPhase::Move)); + h.run_steps(12); + if h.state().views[0].current == 1 { + break; + } + } + assert_eq!(h.state().views[0].current, 1, "notches pan page 1, then turn to page 2"); + h.run_steps(20); + let top = rect(&h, 1).expect("page 2 on screen").min.y; + for _ in 0..3 { + h.event(wheel(MouseWheelUnit::Point, -POINT_NOTCH, TouchPhase::Move)); + h.run_steps(12); + } + let after = rect(&h, 1).expect("page 2 on screen").min.y; + assert!(after < top, "notches pan page 2 down after the turn (#5713): {after} < {top}"); +} + +#[test] +fn single_page_point_notches_scroll_back_up_from_the_last_page_bottom() { + let mut h = harness_stepping(1.0 / 60.0, &[("layout", "single"), ("zoom", "200")]); + h.state_mut().views[0].go_to_page(2); + h.run_steps(20); + let at = h.state().views[0].viewport_rect().center(); + h.hover_at(at); + h.run_steps(4); + // Past the bottom: the extra notches push against the last page's edge. + for _ in 0..200 { + h.event(wheel(MouseWheelUnit::Point, -POINT_NOTCH, TouchPhase::Move)); + h.run_steps(12); + } + assert_eq!(h.state().views[0].current, 2, "stays on the last page"); + let bottom = rect(&h, 2).expect("page 3 on screen").min.y; + for _ in 0..3 { + h.event(wheel(MouseWheelUnit::Point, POINT_NOTCH, TouchPhase::Move)); + h.run_steps(12); + } + let after = rect(&h, 2).expect("page 3 on screen").min.y; + assert!(after > bottom + 1.0, "notches scroll back up from the last page's bottom (#5713): {after} > {bottom}"); +} + #[test] fn stepping_past_either_end_leaves_the_view_alone() { // Paging on past the first or last page must not jump the page back to its top. @@ -1909,7 +2001,8 @@ fn sidebar_collapse_and_resize_preserves_scroll_position() { let rect_after = v.page_screen_rect(2).expect("page 2 still on screen"); let vp_after = v.viewport_rect(); let rel_y_after = rect_after.min.y - vp_after.min.y; - assert!((rel_y_after - rel_y_before).abs() < 1.0, "page 2 scroll position preserved: before {rel_y_before}, after {rel_y_after}"); + // Page rectangles snap to whole pixels, so a different width can move the page by one. + assert!((rel_y_after - rel_y_before).abs() <= 1.0, "page 2 scroll position preserved: before {rel_y_before}, after {rel_y_after}"); // Reopen bookmarks panel: available width decreases, so fit-width zoom decreases. h.state_mut().set_option("panel", "bookmarks").unwrap(); @@ -1926,7 +2019,10 @@ fn sidebar_collapse_and_resize_preserves_scroll_position() { let rect_reopened = v.page_screen_rect(2).expect("page 2 still on screen"); let vp_reopened = v.viewport_rect(); let rel_y_reopened = rect_reopened.min.y - vp_reopened.min.y; - assert!((rel_y_reopened - rel_y_before).abs() < 1.0, "page 2 scroll position preserved on reopen: before {rel_y_before}, after {rel_y_reopened}"); + assert!( + (rel_y_reopened - rel_y_before).abs() <= 1.0, + "page 2 scroll position preserved on reopen: before {rel_y_before}, after {rel_y_reopened}" + ); } /// Synthetic unequal-height spreads, generated without font or image assets. diff --git a/crates/ui-egui/tests/it/viewer.rs b/crates/ui-egui/tests/it/viewer.rs index 3d824b9ea1..6f7d3d3cc8 100644 --- a/crates/ui-egui/tests/it/viewer.rs +++ b/crates/ui-egui/tests/it/viewer.rs @@ -1838,6 +1838,22 @@ fn the_scroll_speed_preference_scales_mouse_wheel_notches() { assert_eq!(again.scroll_speed, ScrollSpeed::Fast); } +#[test] +fn the_invert_middle_drag_preference_is_off_by_default_and_kept_in_the_settings() { + let mut app = PdfCraftApp::new(); + assert!(!app.invert_middle_drag, "the middle button keeps its direction unless asked"); + app.set_option("invert_middle_drag", "true").unwrap(); + assert!(app.set_option("invert_middle_drag", "yes").unwrap_err().contains("true or false")); + let mut again = PdfCraftApp::new(); + again.restore(&app.persist()); + assert!(again.invert_middle_drag, "turned on, it survives a restart"); + again.set_option("invert_middle_drag", "false").unwrap(); + let mut off = PdfCraftApp::new(); + off.invert_middle_drag = true; + off.restore(&again.persist()); + assert!(!off.invert_middle_drag, "turned off, that is saved too"); +} + /// A 40 × 30 picture (one red corner) and a harness showing a PDF of it. fn picture_harness() -> (image::RgbaImage, Harness<'static, PdfCraftApp>) { picture_harness_sized(egui::vec2(1400.0, 900.0)) diff --git a/docs/architecture.md b/docs/architecture.md index b5beb009b7..77e141d0de 100644 --- a/docs/architecture.md +++ b/docs/architecture.md @@ -72,9 +72,10 @@ The PDF object graph *is* the model (`crates/engine/README.md` §The editing mod - PDF in: any revision chain, xref tables or streams, hybrid files, damaged files (repaired and logged), all standard-security revisions. Image codecs (DCT, JPX) decode through the bootstrap - renderer; CCITT and JBIG2 decode through `pdfcraft-filters` (`decode_ccitt`, `decode_jbig2`, - behind `Document::decoded_image`) for export, redaction and the optimizer, and through the - renderer for display. Export ▸ Images decodes JPEG itself. + renderer; CCITT and JBIG2 decode through `pdfcraft-filters` (`decode_ccitt_within`, + `decode_jbig2_within`, behind `ImageBudget::decode`, the only way to decode an image outside + the renderer, which shares one allowance across an operation's images) for export, redaction + and the optimizer, and through the renderer for display. Export ▸ Images decodes JPEG itself. - PDF out: incremental or full saves, object streams, re-encryption, resource de-duplication when combining. - Other formats: images and text in (`create`); PNG/JPEG/TIFF, text, RTF, Word and HTML out diff --git a/docs/localization-parity.md b/docs/localization-parity.md index fee2ba3e7b..dc0cbab4e5 100644 --- a/docs/localization-parity.md +++ b/docs/localization-parity.md @@ -1,5 +1,6 @@ # Localization parity +> **Last reviewed:** 2026-11-03 · **Last updated:** 2026-11-03 · **Change:** minor (Turkish: 2,867 entries, 0 missing in `cargo xtask i18n-report` on 2026-11-03; AI-assisted) > **Last reviewed:** 2026-10-25 · **Last updated:** 2026-10-25 · **Change:** minor (Persian (`fa`, 2,785 entries) added right-to-left like Arabic and Kurdish; Arabic current state corrected: catalogs stay logical, RTL labels take an explicit direction and stock chrome mirrors; native/browser RTL input, IME and complex workflows remain unqualified. Native release Hans face via LXGW WenKai Lite; release-pinned craft-fonts still has no Telugu face. Current union 2,798 keys. Scores and estimates unchanged) · **Target:** Adobe Acrobat Pro (Acrobat DC, continuous track 26.002.21931, macOS) Per-language status of PdfCraft's interface against Acrobat Pro's. How translations work and how to @@ -72,7 +73,7 @@ help/docs polish (catalog and script work are already done), not missing UI stri | Polish | `pl` | 2,611 entries | partial | yes | | Slovenian | `sl` | 2,536 entries | partial | no | | Greek | `el` | 2,545 entries | partial | no | -| Turkish | `tr` | 2,525 entries | partial | yes | +| Turkish | `tr` | 2,867 entries (0 missing in `cargo xtask i18n-report`, 2026-11-03) | partial; AI-assisted, judgement calls reviewed by a native speaker, full proofreading pending | yes | | Lithuanian | `lt` | 2,798 (100% of current key union) | partial; community native-speaker review ([#1401](https://github.com/storytold/pdfcraft/pull/1401)) | no | | Finnish | `fi` | 2,798 entries (every current key) | partial; AI-assisted, native proofreading pending | yes | | Albanian | `sq` | 2,524 entries | partial; not yet reviewed by a native speaker | no | @@ -93,6 +94,7 @@ Acrobat languages PdfCraft lacks: Danish, Dutch, Swedish, Hebrew. Vietnamese is | 2026-10-25 | minor | Added Persian (`fa`, 2,785 entries, all but 13 of the current 2,798-key union); right-to-left like Arabic and Kurdish, with logical entries reordered by egui 0.37's epaint; AI-assisted, not yet native-reviewed | | 2026-10-21 | minor | Brazilian Portuguese (`pt-br`) now covers all 2,674 distinct keys in the current catalog union; no help or engine/OS error-detail localization; twelve-language mean still rounds to ≈ 68% | | 2026-10-20 | minor | Spanish: the 143 keys the other catalogs had and `es.tsv` was missing; `es` now covers the whole 2,674-key union, like `lt` and `vi`. Restated Lithuanian against the current union (its 2,585 was measured on 2026-10-13) and said plainly in *How this was measured* that the union moves, so counts only compare within a date | +| 2026-11-03 | minor | Turkish: 2,867 entries after translating the 288 keys the translation gaps report listed (AI-assisted); measured with the report, not against the 2,798-key union of 2026-10-25, which predates keys added since | | 2026-10-19 | minor | Removed the 2026-10-13 status line and the 14-language summary that concurrent merges left beside the current ones; the summary keeps the Italian and Norwegian Bokmål measurement dates | | 2026-10-16 | minor | Czech: 2,674 entries after adding the keys the other catalogs had (the engine's sentences, weekday heads, certificate fields, shared buttons) and unifying "tag" as *tag* (not *značka*, which is a redaction mark) | | 2026-10-13 | minor | Vietnamese (`vi`) catalog: 2,591 entries (100% of current key union + `theme`/`Appearance`); twelve-language mean ≈ 68%; native-speaker community review; registered with `plural_none` | diff --git a/docs/roadmap.md b/docs/roadmap.md index 673e9053fe..f376f7cb00 100644 --- a/docs/roadmap.md +++ b/docs/roadmap.md @@ -1,5 +1,11 @@ # PdfCraft roadmap: milestones and what's next +> **Last reviewed:** 2026-11-03 | **Last updated:** 2026-11-03 | **Change:** patch (M5 #5850 review: indirect typewriter intent and composer edits preserve outer whitespace; movement regression commits by outside click; estimates unchanged) + +> **Last reviewed:** 2026-11-03 | **Last updated:** 2026-11-03 | **Change:** patch (M5 #5850: Enter adds Fill & Sign line breaks; outside clicks commit, Escape cancels, and saved multiline appearances retain their text and height; estimates unchanged) + +> **2026-11-03, M7 / #5835 review:** active image crops retain secondary clicks over overlapping images; crop controls share measured layout with hit detection. Rotation, handle and page-edge regressions added; focused tests, scoped Clippy, formatting, layering and asset checks passed locally. Estimates unchanged. + > **Last reviewed:** 2026-11-01 | **Last updated:** 2026-11-01 | **Change:** patch (M7 #5657: header/footer, watermark and background operations commit all selected pages together; later-page errors preserve marks, content, shared/inherited resources and pending edits; estimates unchanged) > **Last reviewed:** 2026-11-01 | **Last updated:** 2026-11-01 | **Change:** patch (M7, PR #2155 further review: inherited drawing/text state, affine image gestures, paste/selection ownership, no-op scripts and menu permissions; estimates unchanged) @@ -217,7 +223,7 @@ total matches the parity estimate. | M4 | Engine, history, save, organize | 100–180 | 95% | 8–15 | Done:
- command registry (menus, shortcuts and palette all use it);
- undo/redo; incremental, atomic and encrypted saves;
- autosave and crash recovery;
- organize, combine, extract, split and insert-from-file, with identical fonts and images stored once;
- CLI `edit/combine/extract/split`.
Done since: Organize opens directly into the page overview, with checkbox selection, an editable page-range selection (#1092), and per-page rotate/delete controls; Combine files in its own tab (sortable, resizable columns; folders; early warnings; unlocking protected files), bookmark editing, page labels (Number pages), CLI `run`, Set Page Boxes, Crop tool, Duplicate pages, Ctrl+A / Cmd+A to select all pages in Organize, Replace pages, bookmarks from tagged headings. Extract and Split preserve shared Type 3 glyph resource graphs, retaining conservative pruning limits. Missing: page transitions, recovery on the web M4: Insert-from-file preserves source bookmarks; integration tests retained with current main. | | M3 | Viewer app (native + web) | 80–150 | 90% | 10–20 | Acrobat-style shell, find, select, panels, tiles, web build, UI control channel for agents (opt-in). Missing: 60 fps test on a 500-page document, snapshot tests of every panel
Done since: fit visible, document title in the window; Linux middle-button scrolling; shared three-state theme preferences in the toolbar, View menu and control channel; numeric Linux portal events and idle wakeups completing #881, with native appearance inheritance retained (#446); late browser startup downloads preserve the current document and Save target (#171). Renderer-creation errors return to the existing OpenGL startup fallback; a real-GPU regression covers errors and device reuse. The underlying x86 DX12 shader compiler failure remains unresolved; see `windows-renderer-startup.md`. With Windows' Animation effects turned off, the wheel scrolls and zooms without easing and egui's animations take no time (`motion.rs`; macOS, Linux and the browser aren't asked yet); Preferences ▸ Animation effects (Use system setting, On, Off) decides it on every platform. | | M4 | Engine, history, save, organize | 100–180 | 95% | 8–15 | Done:
- command registry (menus, shortcuts and palette all use it);
- undo/redo; incremental, atomic and encrypted saves;
- autosave and crash recovery;
- organize, combine, extract, split and insert-from-file, with identical fonts and images stored once;
- CLI `edit/combine/extract/split`.
Done since: Combine files in its own tab (sortable, resizable columns; folders; early warnings; unlocking protected files), bookmark editing, page labels (Number pages), CLI `run`, Set Page Boxes, Crop tool, Duplicate pages, Ctrl+A / Cmd+A to select all pages in Organize, Replace pages, bookmarks from tagged headings. Missing: page transitions, recovery on the web | -| M5 | Comments (all annotation types, XFDF) | 120–200 | 88% | 12–25 | Done: notes, highlight/underline/strikeout/squiggly, text boxes, ink, lines, arrows, rectangles, ovals, stamps (dynamic, Sign Here, Standard Business), with appearance streams; replies, status, checkmarks, locking, move/resize/restyle/delete; properties dialog; panel filter and sort; hide all; summaries (comments only); XFDF/FDF import and export (partial imports preserve existing reply and review-status links); flatten; Fill & Sign with adjustable text/date size; agent tools.
Done since: replies thread by their `/IRT` reference rather than the parent's `/NM`, so files that repeat names per page (PyMuPDF) thread correctly, and the Comments header counts comments without their replies, as Acrobat does, with the reply count under it; the Comments panel groups replies and counts all page roots once per frame (#2669, item 5); each reply in the Comments panel has its own "…" (Edit, Copy text, Delete): Delete takes that reply and the replies to it, the comment and its other replies stay, and the card stays selected; stamps placed on a rotated page read upright (#1398); polygons, connected lines, clouds, callouts, inserted text, colour and checkmark filters; image signature pointer previews, selection handles and live image movement/resizing with proportional corners and independent edge handles; Ctrl+Enter submission for highlight comment text and replies, with Shift+Enter newlines (reconciled with upstream main for PR #1457 on 2026-10-14). Missing: custom stamps, replace-text proposals, summary layouts with the page | +| M5 | Comments (all annotation types, XFDF) | 120–200 | 88% | 12–25 | Done: notes, highlight/underline/strikeout/squiggly, text boxes, ink, lines, arrows, rectangles, ovals, stamps (dynamic, Sign Here, Standard Business), with appearance streams; replies, status, checkmarks, locking, move/resize/restyle/delete; properties dialog; panel filter and sort; hide all; summaries (comments only); XFDF/FDF import and export (partial imports preserve existing reply and review-status links); flatten; Fill & Sign with adjustable text/date size; Enter adds line breaks in a growing typewriter editor, outside clicks commit, Escape cancels, and saved/headless appearances keep multiline text (#5850); indirect typewriter intent resolves before whitespace decisions and Fill & Sign classification, with comment listing/property lookup retaining direct Subtype, and composer edits retain typewriter text as written while other comments retain trimming; agent tools.
Done since: replies thread by their `/IRT` reference rather than the parent's `/NM`, so files that repeat names per page (PyMuPDF) thread correctly, and the Comments header counts comments without their replies, as Acrobat does, with the reply count under it; the Comments panel groups replies and counts all page roots once per frame (#2669, item 5); each reply in the Comments panel has its own "…" (Edit, Copy text, Delete): Delete takes that reply and the replies to it, the comment and its other replies stay, and the card stays selected; stamps placed on a rotated page read upright (#1398); polygons, connected lines, clouds, callouts, inserted text, colour and checkmark filters; image signature pointer previews, selection handles and live image movement/resizing with proportional corners and independent edge handles; Ctrl+Enter submission for highlight comment text and replies, with Shift+Enter newlines (reconciled with upstream main for PR #1457 on 2026-10-14). Missing: custom stamps, replace-text proposals, summary layouts with the page | | M4 | Engine, history, save, organize | 100–180 | 95% | 8–15 | Done:
- command registry (menus, shortcuts and palette all use it);
- undo/redo; incremental, atomic and encrypted saves;
- autosave and crash recovery;
- organize, combine, extract, split and insert-from-file, with identical fonts and images stored once;
- CLI `edit/combine/extract/split`.
Done since: Combine files in its own tab (sortable, resizable columns; folders; early warnings; unlocking protected files), bookmark editing, page labels (Number pages), CLI `run`, Set Page Boxes, Crop tool, Duplicate pages, Ctrl+A / Cmd+A to select all pages in Organize, Replace pages, bookmarks from tagged headings. Missing: page transitions, recovery on the web M4: Insert-from-file preserves source bookmarks; integration tests retained with current main. | | M5 | Comments (all annotation types, XFDF) | 120–200 | 88% | 12–25 | Done: notes, highlight/underline/strikeout/squiggly, text boxes, ink, lines, arrows, rectangles, ovals, stamps (dynamic, Sign Here, Standard Business), with appearance streams; replies, status, checkmarks, locking, move/resize/restyle/delete; properties dialog; panel filter and sort; hide all; summaries (comments only); XFDF/FDF import and export (partial imports preserve existing reply and review-status links); flatten; Fill & Sign with adjustable text/date size; agent tools.
Done since: stamps placed on a rotated page read upright (#1398); polygons, connected lines, clouds, callouts, inserted text, colour and checkmark filters; image signature pointer previews, selection handles and live image movement/resizing with proportional corners and independent edge handles. Missing: custom stamps, replace-text proposals, summary layouts with the page | | M5 | Comments (all annotation types, XFDF) | 120–200 | 88% | 12–25 | Done: notes, highlight/underline/strikeout/squiggly, text boxes, ink, lines, arrows, rectangles, ovals, stamps (dynamic, Sign Here, Standard Business), with appearance streams; replies, status, checkmarks, locking, move/resize/restyle/delete; properties dialog; panel filter and sort; hide all; summaries (comments only); XFDF/FDF import and export (partial imports preserve existing reply and review-status links; nested FDF export uses lazy array owners and annotation positions, with retained entries budgeted before cloning under copied-graph limits and source `/Page` and `/Pages` dictionaries replaced by null at every copy depth); flatten; Fill & Sign with adjustable text/date size; agent tools.
Done since: polygons, connected lines, clouds, callouts, inserted text, colour and checkmark filters; image signature pointer previews, selection handles and live image movement/resizing with proportional corners and independent edge handles. A refused restyle or resize of a text box another program drew leaves that comment unchanged (#1327). Make Current Properties Default on an arrow updates arrows, not plain lines (#1302). Flattening keeps a visible comment it cannot draw (#1317). Missing: custom stamps, replace-text proposals, summary layouts with the page | @@ -225,7 +231,7 @@ total matches the parity estimate. | M6 | Forms + JavaScript | 160–320 | 50% | 40–75 | Done: filling all field types with regenerated appearances; Prepare a form (every field type, multi-select/shared properties, move/resize/delete, Field Properties General/Appearance/Position/Options/Format/Validate/Calculate); Acrobat's AF format/keystroke/validate/calculate functions and simplified field notation run natively in Acrobat's event order; tab order; push-button actions; flatten; agent tools. Form data exchange (FDF, XFDF, XML, CSV, text) done; XFDF values retain text across XML comments and processing instructions. Plain AcroForm XML imports retain all direct text around comments and processing instructions, including CDATA and character references.
Done since: JavaScript engine (boa, sandboxed) running custom keystroke/validate/calculate/format and button scripts, document JavaScripts, console. Missing: Actions tab, wider object model (annotations, layers, dialogs), XFA
Done since: Multi-select choice fields write ascending `/I` option indices while preserving `/V` selection order; synthetic forms/engine regressions cover reverse selection and save/reopen. CSV export preserves carriage returns in names and values. | | M6 | Forms + JavaScript | 160–320 | 50% | 40–75 | Done: filling all field types with regenerated appearances; Prepare a form (every field type, multi-select/shared properties, move/resize/delete, Field Properties General/Appearance/Position/Options/Format/Validate/Calculate); Acrobat's AF format/keystroke/validate/calculate functions and simplified field notation run natively in Acrobat's event order; tab order; push-button actions; flatten; agent tools. Form data exchange (FDF, XFDF, XML, CSV, text) done; XFDF values retain text across XML comments and processing instructions. XML/XFDF exports preserve tabs and line breaks in names and comment metadata. Refreshed against upstream `99941daa` (2026-10-15).
Done since: JavaScript engine (boa, sandboxed) running custom keystroke/validate/calculate/format and button scripts, document JavaScripts, console. Missing: Actions tab, wider object model (annotations, layers, dialogs), XFA
Done since: Multi-select choice fields write ascending `/I` option indices while preserving `/V` selection order; synthetic forms/engine regressions cover reverse selection and save/reopen. CSV export preserves carriage returns in names and values. | | M6 | Forms + JavaScript | 160–320 | 50% | 40–75 | Done: filling all field types with regenerated appearances; Prepare a form (every field type, multi-select/shared properties, move/resize/delete, Field Properties General/Appearance/Position/Options/Format/Validate/Calculate); Acrobat's AF format/keystroke/validate/calculate functions and simplified field notation run natively in Acrobat's event order; tab order; push-button actions; flatten; agent tools. Form data exchange (FDF, XFDF, XML, CSV, text) done; XFDF values retain text across XML comments and processing instructions. XML/XFDF exports preserve tabs and line breaks in names and comment metadata. Plain AcroForm XML imports retain all direct text around comments and processing instructions, including CDATA and character references. CSV export and spreadsheet merging quote tabs, and import distinguishes quoted tabs from TSV delimiters without changing field identities.
Done since: JavaScript engine (boa, sandboxed) running custom keystroke/validate/calculate/format and button scripts, document JavaScripts, console. Missing: Actions tab, wider object model (annotations, layers, dialogs), XFA
Done since: Multi-select choice fields write ascending `/I` option indices while preserving `/V` selection order; synthetic forms/engine regressions cover reverse selection and save/reopen. CSV export preserves carriage returns in names and values. | -| M7 | Content editing (text, images, header/footer, watermark) | 250–500 | 20% | 100–180 | Done: header & footer, watermarks, backgrounds, Bates; added text and images that stay editable (move, resize, format, rotate, flip, crop, replace); links (Link tool, Link Properties, create from URLs, remove all). Done since: Edit text preserves Arabic/Hebrew `/ActualText` typing order, with font-independent regressions; single-glyph RTL ligature spans (including lam-alef) join their surrounding word. Done since (#1116): editable text regions grouped across compatible words and subset fonts, one rich-text editor over a background with the source text removed, embedded sfnt faces reused as editor faces, and visible (clipped) bounds for cropped-image selection and resize. Exclusive crops now resize across nested states and content streams, with shared clips fixed.
Done since: #594 ordinary paragraph drags preserve overlapping source text; UI/engine regressions, native save/reopen, independent-reader checks and full CI passed in the Linux test environment. #1200 candidate: local GoToR links open in desktop tabs and through root-confined automation; appearance-only edits preserve existing actions. Named destinations remain unapplied and `/NewWindow` is a tab hint. Done since: #3187: Added-image automation normalizes extreme signed rotation angles before combining them with the current orientation; integer bounds, history, pixels, save/reopen and MCP have regressions. Done since: #2592: Styled fallback fonts batch up to 240 glyphs per actual face and retain source styles. Budget refusal and distinct same-BaseFont descriptor weights have mutation-checked regressions; coverage and complex mixed runs remain limited. Done since: #5657 page-mark operations are atomic across selected pages, including shared/inherited resources and existing unsaved edits. Missing: editing existing text and images in place (the longest pole), image/PDF watermarks PR #2155 candidate: editor-owned crops preserve original clips through group moves; Arrange preserves added-item stream ownership and refuses unsafe scope/state/tag extraction; image handles and flips follow page orientation; general transforms and Unicode script toggles have headless tools. Clipboard, mixed-size formatting, Home pins and reloadable installed-font discovery have review regressions. Latest follow-up uses explicit image-paste events, refreshes the mixed-size display, and documents script normalization with Undo. Further review covers inherited Form text and mask chronology, scoped transform composition, affine resize/rotation pivots, paste/selection ownership, no-op scripts and page-menu permissions. | +| M7 | Content editing (text, images, header/footer, watermark) | 250–500 | 20% | 100–180 | Done: header & footer, watermarks, backgrounds, Bates; added text and images that stay editable (move, resize, format, rotate, flip, crop, replace); links (Link tool, Link Properties, create from URLs, remove all). Done since: Edit text preserves Arabic/Hebrew `/ActualText` typing order, with font-independent regressions; single-glyph RTL ligature spans (including lam-alef) join their surrounding word. Done since (#1116): editable text regions grouped across compatible words and subset fonts, one rich-text editor over a background with the source text removed, embedded sfnt faces reused as editor faces, and visible (clipped) bounds for cropped-image selection and resize. Exclusive crops now resize across nested states and content streams, with shared clips fixed.
Done since: #594 ordinary paragraph drags preserve overlapping source text; UI/engine regressions, native save/reopen, independent-reader checks and full CI passed in the Linux test environment. #1200 candidate: local GoToR links open in desktop tabs and through root-confined automation; appearance-only edits preserve existing actions. Named destinations remain unapplied and `/NewWindow` is a tab hint. Done since: #3187: Added-image automation normalizes extreme signed rotation angles before combining them with the current orientation; integer bounds, history, pixels, save/reopen and MCP have regressions. Done since: #2592: Styled fallback fonts batch up to 240 glyphs per actual face and retain source styles. Budget refusal and distinct same-BaseFont descriptor weights have mutation-checked regressions; coverage and complex mixed runs remain limited. Done since: #5657 page-mark operations are atomic across selected pages, including shared/inherited resources and existing unsaved edits. Missing: editing existing text and images in place (the longest pole), image/PDF watermarks PR #2155 candidate: editor-owned crops preserve original clips through group moves; Arrange preserves added-item stream ownership and refuses unsafe scope/state/tag extraction; image handles and flips follow page orientation; general transforms and Unicode script toggles have headless tools. Clipboard, mixed-size formatting, Home pins and reloadable installed-font discovery have review regressions. Latest follow-up uses explicit image-paste events, refreshes the mixed-size display, and documents script normalization with Undo. Further review covers inherited Form text and mask chronology, scoped transform composition, affine resize/rotation pivots, paste/selection ownership, no-op scripts and page-menu permissions. Done since: #5835 a right-click on an image in crop mode keeps the crop and opens no menu, also over overlapping and rotated images. | | M7 | Content editing (text, images, header/footer, watermark) | 250–500 | 20% | 100–180 | Done: header & footer, watermarks, backgrounds, Bates; added text and images that stay editable (move, resize, format, rotate, flip, crop, replace); links (Link tool, Link Properties, create from URLs, remove all). Done since: Edit text preserves Arabic/Hebrew `/ActualText` typing order, with font-independent regressions. Done since (#1116): editable text regions grouped across compatible words and subset fonts, one rich-text editor over a background with the source text removed, embedded sfnt faces reused as editor faces, and visible (clipped) bounds for cropped-image selection and resize. Exclusive crops now resize across nested states and content streams, with shared clips fixed.
Done since: #594 ordinary paragraph drags preserve overlapping source text; UI/engine regressions, native save/reopen, independent-reader checks and full CI passed in the Linux test environment. #1200 candidate: local GoToR links open in desktop tabs and through root-confined automation; appearance-only edits preserve existing actions. Named destinations remain unapplied and `/NewWindow` is a tab hint. #1316: replacing a line or paragraph keeps a neighbouring line whose glyph box overlaps when the baselines differ; a second copy on the same baseline is still replaced. Missing: editing existing text and images in place (the longest pole), image/PDF watermarks | | M7 | Content editing (text, images, header/footer, watermark) | 250–500 | 20% | 100–180 | Done: header & footer, watermarks, backgrounds, Bates; added text and images that stay editable (move, resize, format, rotate, flip, crop, replace); links (Link tool, Link Properties, create from URLs, remove all). #3212: Headers, Bates numbers, watermarks and added text stay visible after unfinished marked content, without revealing hidden content. Tracked editable text distinguishes repeated glyph spacing from word gaps, with synthetic paragraph/object regressions. Missing: editing existing text and images in place (the longest pole), watermark print/screen visibility and repeat | | M6 | Forms + JavaScript | 160–320 | 50% | 40–75 | Done: filling all field types with regenerated appearances; Prepare a form (every field type, multi-select/shared properties, move/resize/delete, Field Properties General/Appearance/Position/Options/Format/Validate/Calculate); Acrobat's AF format/keystroke/validate/calculate functions and simplified field notation run natively in Acrobat's event order; tab order; push-button actions; flatten; agent tools. Form data exchange (FDF, XFDF, XML, CSV, text) done; XFDF values retain text across XML comments and processing instructions.
Done since: JavaScript engine (boa, sandboxed) running custom keystroke/validate/calculate/format and button scripts, document JavaScripts, console. Missing: Actions tab, wider object model (annotations, layers, dialogs), XFA
Done since: Existing simple field-font encodings and Differences are respected when generating appearances; an unencodable value uses a separate Helvetica appearance font without changing the source font. Synthetic reopen regressions cover punctuation, subset fallback and multiline text. Exact font metrics/layout and broader Unicode fallback remain incomplete. | @@ -298,6 +304,9 @@ Estimates unchanged. | Date | Change | Summary | |---|---|---| +| 2026-11-03 | patch | M5 #5850 review: indirect typewriter intent and composer edits preserve outer whitespace; movement regression commits by outside click; estimates unchanged. | +| 2026-11-03 | patch | M5 #5850: Enter adds Fill & Sign line breaks; outside clicks commit, Escape cancels, and saved multiline appearances retain their text and height; estimates unchanged. | +| 2026-11-02 | patch | M10 #5743: macOS print jobs carry the job name and owner some vendors' filters need; not yet checked on a physical printer | | 2026-11-01 | patch | M7 #5657: header/footer, watermark and background operations commit all selected pages together; later-page errors preserve marks, content, shared/inherited resources and pending edits; estimates unchanged. | | 2026-10-31 | patch | #1577: reconcile optional page shadows with current viewer/organizer and settings modules; CI validation pending. | | 2026-10-31 | patch | M3 #1354: reconcile the launch override with split app/file modules and the structured open result; preserve headless help/version exits. CI validation pending. | diff --git a/parity/acrobat-features.toml b/parity/acrobat-features.toml index de9cf09232..7c5859a75e 100644 --- a/parity/acrobat-features.toml +++ b/parity/acrobat-features.toml @@ -794,8 +794,8 @@ milestone = "M2" status = "partial" commands = [] tools = [] -evidence = ["crates/render/src/raster/tests.rs::huge_cid_width_ranges_terminate", "crates/render/src/raster/tests.rs::non_embedded_japanese_cid_fonts_draw_with_a_craft_fonts_face", "crates/render/src/raster/tests.rs::mincho_substitute_covers_half_width_katakana", "crates/render/src/raster/tests.rs::non_embedded_chinese_and_korean_cid_fonts_draw_with_an_installed_face", "crates/engine/src/tests.rs::installed_cjk_fonts_draw_in_the_viewer_but_not_in_an_export", "crates/render/src/text/tests.rs::identity_to_unicode_names_give_text", "crates/fonts/src/pdf/tests.rs::identity_to_unicode_names_read_codes_as_unicode"] -notes = "CID-to-Unicode tables are M2.4; a non-embedded Adobe-Japan1 font is drawn in a craft-fonts Japanese face (Mincho or Gothic by name, else by the descendant font descriptor's Serif flag; bold Gothic for a Bold name or a `/FontWeight` of 600 or more; BIZ UDMincho for Mincho, which covers half-width katakana) when built with craft-fonts; the desktop viewer can fall back to an installed CJK face for GB1, CNS1, Korea1 and Japan1, including GBK-EUC-H TrueType CID fonts without ToUnicode. Windows preserves installed SimSun, SimHei, KaiTi and FangSong families, including subset-prefixed Founder aliases. Combine thumbnails and accessibility figure previews use the same on-screen fallback. System faces are display-only, disabled by PDFCRAFT_SYSTEM_FONTS=0, and not used by export, printing, OCR or automation; machines without a candidate and web builds remain unsupported. A `/ToUnicode` given as the name `/Identity-H` or `/Identity-V` (WSCAD) reads codes as Unicode for selection, search and editing, without control characters" +evidence = ["crates/render/src/raster/tests.rs::huge_cid_width_ranges_terminate", "crates/render/src/raster/tests.rs::non_embedded_japanese_cid_fonts_draw_with_a_craft_fonts_face", "crates/render/src/raster/tests.rs::mincho_substitute_covers_half_width_katakana", "crates/render/src/raster/tests.rs::non_embedded_chinese_and_korean_cid_fonts_draw_with_an_installed_face", "crates/engine/src/tests.rs::installed_cjk_fonts_draw_in_the_viewer_but_not_in_an_export", "crates/render/src/text/tests.rs::identity_to_unicode_names_give_text", "crates/fonts/src/pdf/tests.rs::identity_to_unicode_names_read_codes_as_unicode", "crates/render/src/raster/tests.rs::a_soft_hyphen_a_substitute_lacks_draws_its_hyphen"] +notes = "CID-to-Unicode tables are M2.4; a non-embedded Adobe-Japan1 font is drawn in a craft-fonts Japanese face (Mincho or Gothic by name, else by the descendant font descriptor's Serif flag; bold Gothic for a Bold name or a `/FontWeight` of 600 or more; BIZ UDMincho for Mincho, which covers half-width katakana) when built with craft-fonts; the desktop viewer can fall back to an installed CJK face for GB1, CNS1, Korea1 and Japan1, including GBK-EUC-H TrueType CID fonts without ToUnicode. Windows preserves installed SimSun, SimHei, KaiTi and FangSong families, including subset-prefixed Founder aliases. Combine thumbnails and accessibility figure previews use the same on-screen fallback. System faces are display-only, disabled by PDFCRAFT_SYSTEM_FONTS=0, and not used by export, printing, OCR or automation; machines without a candidate and web builds remain unsupported. A `/ToUnicode` given as the name `/Identity-H` or `/Identity-V` (WSCAD) reads codes as Unicode for selection, search and editing, without control characters. A non-embedded Identity font whose `/ToUnicode` gives a soft hyphen (U+00AD, as Windows exporters write Arial's hyphen) draws the standard substitute's hyphen (#5888). Any other character the substitute lacks still falls back to the CID taken as one of the substitute's glyph indexes, an unrelated glyph (#3529, #5726)" [[feature]] id = "view.render-image-codecs" @@ -938,8 +938,8 @@ milestone = "M3" status = "partial" commands = [] tools = [] -evidence = ["crates/ui-egui/tests/it/control.rs::middle_click_autoscroll_latches_has_a_dead_zone_and_scrolls_both_directions", "crates/ui-egui/tests/it/control.rs::organize_pages_supports_autoscroll_without_selecting_or_reordering_pages", "crates/ui-egui/tests/it/control.rs::moving_before_middle_button_release_keeps_scrolling_without_starting_page_tools", "crates/ui-egui/tests/it/control.rs::farther_from_the_click_scrolls_faster_in_the_viewer_and_page_grid", "crates/ui-egui/tests/it/control.rs::autoscroll_uses_the_initial_click_position_when_input_arrives_in_one_frame", "crates/ui-egui/tests/it/control.rs::autoscroll_uses_elapsed_frame_time_and_preserves_fractional_motion_in_both_views", "crates/ui-egui/tests/it/control.rs::middle_button_pans_while_held_outside_linux", "crates/ui-egui/tests/it/comments.rs::a_middle_drag_with_a_drawing_tool_scrolls_instead_of_drawing"] -notes = "Linux-only middle-button vertical autoscroll in the document and Organize Pages; Windows and macOS pan 1:1 while the middle button is held (Grabbing cursor, no latch). On every target the middle button never reaches the page tools, so it scrolls instead of drawing, selecting, cropping or moving. Click to toggle, release keeps scrolling on, and a Chromium-style nonlinear curve increases speed with vertical screen distance from the initial click. A 15-point dead zone pauses immediately. Continuous redraws use elapsed frame time and preserve fractional movement, tested at 30/60/120/144 fps. Cancels on another middle click, Escape, other pointer/wheel input, focus loss, tab changes and dialogs. Driven headlessly through the opt-in UI control channel (ui.click/ui.move/ui.drag). Keyboard-started timed scrolling is not implemented." +evidence = ["crates/ui-egui/tests/it/control.rs::middle_click_autoscroll_latches_has_a_dead_zone_and_scrolls_both_directions", "crates/ui-egui/tests/it/control.rs::organize_pages_supports_autoscroll_without_selecting_or_reordering_pages", "crates/ui-egui/tests/it/control.rs::moving_before_middle_button_release_keeps_scrolling_without_starting_page_tools", "crates/ui-egui/tests/it/control.rs::farther_from_the_click_scrolls_faster_in_the_viewer_and_page_grid", "crates/ui-egui/tests/it/control.rs::autoscroll_uses_the_initial_click_position_when_input_arrives_in_one_frame", "crates/ui-egui/tests/it/control.rs::autoscroll_uses_elapsed_frame_time_and_preserves_fractional_motion_in_both_views", "crates/ui-egui/tests/it/control.rs::middle_button_pans_while_held_outside_linux", "crates/ui-egui/tests/it/comments.rs::a_middle_drag_with_a_drawing_tool_scrolls_instead_of_drawing", "crates/ui-egui/tests/it/control.rs::inverted_middle_drag_moves_the_view_the_way_the_pointer_goes", "crates/ui-egui/tests/it/viewer.rs::the_invert_middle_drag_preference_is_off_by_default_and_kept_in_the_settings"] +notes = "Linux-only middle-button vertical autoscroll in the document and Organize Pages; Windows and macOS pan 1:1 while the middle button is held (Grabbing cursor, no latch). On every target the middle button never reaches the page tools, so it scrolls instead of drawing, selecting, cropping or moving. Click to toggle, release keeps scrolling on, and a Chromium-style nonlinear curve increases speed with vertical screen distance from the initial click. A 15-point dead zone pauses immediately. Continuous redraws use elapsed frame time and preserve fractional movement, tested at 30/60/120/144 fps. Cancels on another middle click, Escape, other pointer/wheel input, focus loss, tab changes and dialogs. Preferences ▸ Invert middle-button drag (off by default, saved; ui.set invert_middle_drag) reverses the direction of both the pan and the auto-scroll (#5790); it changes direction only, not which of the two a platform uses. Driven headlessly through the opt-in UI control channel (ui.click/ui.move/ui.drag). Keyboard-started timed scrolling is not implemented." [[feature]] id = "view.zoom-in-out" @@ -1813,6 +1813,12 @@ evidence = [ "crates/ui-egui/tests/it/comments.rs::hotbar_vertical_size_and_docking", "crates/ui-egui/tests/it/comments.rs::hotbar_settings_reopen_even_with_remembered_collapsed_state", "crates/ui-egui/tests/it/comments.rs::hotbar_full_side_strip_spans_each_edge_and_returns_to_float", + "crates/ui-egui/tests/it/comments.rs::hotbar_docked_left_does_not_override_quick_tools", + "crates/ui-egui/tests/it/comments.rs::hotbar_docked_in_compact_window_keeps_settings_button_visible", + "crates/ui-egui/tests/it/comments.rs::hotbar_settings_menu_closes_on_click_outside", + "crates/ui-egui/tests/it/comments.rs::hotbar_picker_in_narrow_viewport_fits_within_screen_width", + "crates/ui-egui/tests/it/comments.rs::hotbar_floating_picker_does_not_overlap_rendered_bar", + "crates/ui-egui/tests/it/comments.rs::hotbar_settings_layout_and_side_controls_are_reachable_by_label", ] notes = "Pin and unpin tools on the Home page via tool card hover button, All Tools row toggle, or 'Pin a tool' search dialog. Pinned tool order persists across sessions. Customizable document hotbar searches the command registry, adds/removes tools, resizes buttons from 24 to 64 pixels, floats or docks on any side with an optional full-side chrome strip, and persists preferences (UI control: hotbar-tools, hotbar-size, hotbar-side, hotbar-full-side). Missing: hotbar shortcut reordering and full Acrobat customization-dialog parity." @@ -2601,11 +2607,11 @@ title = "Bates numbering across multiple files" area = "C" tier = "P1" milestone = "M7" -status = "planned" +status = "partial" commands = [] -tools = [] -evidence = [] -notes = "" +tools = ["doc_bates_multi"] +evidence = ["crates/automation/tests/it/automation.rs::bates_numbers_continue_across_files_and_report_preflight_and_permission_failures"] +notes = "The headless batch tool allocates inclusive intervals in input order and reports per-file failures; it refuses existing output paths. Missing: a GUI batch dialog (Acrobat sets this up from Header & Footer ▸ Add Bates numbering with a file list), so it is reachable only through `doc_bates_multi`." [[feature]] id = "edit.bates-remove" @@ -5393,8 +5399,8 @@ milestone = "M5" status = "shipped" commands = ["sign.fill.text"] tools = ["fill_sign_add"] -evidence = ["crates/ui-egui/tests/it/fill_sign.rs::text_marks_and_date", "crates/annot/src/tests.rs::fill_and_sign_items_are_drawn", "crates/automation/tests/it/automation.rs::fill_and_sign_through_tools", "crates/engine/src/tests.rs::typed_text_reads_across_as_displayed_on_rotated_pages", "crates/ui-egui/tests/it/fill_sign.rs::fill_text_colour_survives_preview_commit_settings_and_save", "crates/automation/tests/it/automation.rs::fill_sign_text_and_date_colours_are_saved_and_validated"] -notes = "typewriter FreeText, 10 pt Helvetica. Reads across as displayed on pages with /Rotate (sideways-stored scans): the box follows the displayed axes and the appearance is turned back (PdfCraft key /PCTextRotate); other apps that regenerate the appearance from /DA draw it unturned. A later page rotation does not re-turn it. Field detection does not work on scanned (image-only) forms yet; typed fractional font sizes commit once; Fill & Sign text/date colour is remembered and preserved in preview and saved appearances (#2444)" +evidence = ["crates/annot/src/tests.rs::indirect_typewriter_names_keep_outer_whitespace_in_summaries", "crates/ui-egui/tests/it/comments.rs::typewriter_edit_composer_keeps_trailing_blank_lines", "crates/ui-egui/tests/it/comments.rs::other_edit_composers_keep_trimming_trailing_whitespace", "crates/ui-egui/tests/it/comments.rs::moved_fill_and_sign_text_is_drawn_where_it_goes_before_release", "crates/engine/src/tests.rs::fill_sign_multiline_text_survives_engine_save_reopen_and_render", "crates/ui-egui/tests/it/fill_sign.rs::fill_sign_enter_adds_lines_outside_click_commits_and_escape_cancels", "crates/automation/tests/it/automation.rs::multiline_fill_sign_engine_round_trip_preserves_lines_and_appearance", "crates/ui-egui/tests/it/fill_sign.rs::text_marks_and_date", "crates/annot/src/tests.rs::fill_and_sign_items_are_drawn", "crates/automation/tests/it/automation.rs::fill_and_sign_through_tools", "crates/engine/src/tests.rs::typed_text_reads_across_as_displayed_on_rotated_pages", "crates/ui-egui/tests/it/fill_sign.rs::fill_text_colour_survives_preview_commit_settings_and_save", "crates/automation/tests/it/automation.rs::fill_sign_text_and_date_colours_are_saved_and_validated"] +notes = "Indirect IT is resolved when recognizing typewriter contents and Fill & Sign marks; comment listing and properties retain direct Subtype as before; composer edits preserve the typewriter text as written, while other comments retain their existing trimming. Enter inserts a newline; the editor grows with its lines, outside clicks commit and Escape cancels. Nonempty text preserves leading/internal/trailing line breaks, including after save/reopen; fill_sign_add sizes all wrapped rows for the saved appearance (#5850). typewriter FreeText, 10 pt Helvetica. Reads across as displayed on pages with /Rotate (sideways-stored scans): the box follows the displayed axes and the appearance is turned back (PdfCraft key /PCTextRotate); other apps that regenerate the appearance from /DA draw it unturned. A later page rotation does not re-turn it. Field detection does not work on scanned (image-only) forms yet; typed fractional font sizes commit once; Fill & Sign text/date colour is remembered and preserved in preview and saved appearances (#2444)" [[feature]] id = "form.fill-sign-marks" @@ -7214,7 +7220,7 @@ status = "shipped" commands = ["export.all_images"] tools = ["doc_export_all_images"] evidence = ["crates/create/src/tests.rs::ccitt_fax_images_export_as_their_picture", "crates/create/src/tests.rs::group_3_ccitt_masks_and_parameters_by_reference_export_as_their_picture", "crates/create/src/tests.rs::images_export_as_jpeg_unchanged_and_others_as_png", "crates/create/src/tests.rs::indexed_and_one_bit_images_decode", "crates/create/src/tests.rs::jpeg_images_with_a_soft_mask_export_as_png_with_alpha", "crates/create/src/tests.rs::soft_masks_of_another_size_and_stencil_and_colour_key_masks_become_alpha", "crates/create/src/tests.rs::soft_mask_decode_ranges_become_exported_alpha", "crates/create/src/tests.rs::soft_mask_decode_maps_packed_and_jpeg_masks_before_resizing", "crates/automation/tests/it/automation.rs::exporting_all_images_through_tools", "crates/ui-egui/tests/it/export.rs::export_dialogs_write_images_and_text", "crates/create/src/tests.rs::lossless_decode_maps_each_component_before_colour_conversion", "crates/create/src/tests.rs::lossless_indexed_decode_rounds_in_index_units_then_clamps", "crates/create/src/tests.rs::jbig2_images_export_as_their_picture", "crates/create/src/tests.rs::jbig2_globals_are_decoded_within_a_limit_of_their_own", "crates/automation/tests/it/automation.rs::doc_optimize_stores_black_and_white_images_as_jbig2", "crates/create/src/tests.rs::symbol_coded_jbig2_images_export_as_their_picture", "crates/create/src/tests.rs::jbig2_images_behind_another_filter_export_as_their_picture"] -notes = "each image once (page resources and nested forms); JPEG unchanged unless it has transparency, others PNG (gray/RGB/CMYK/ICC/Indexed, 1–16 bpc, stencil masks); transparency as PNG alpha: /SMask (scaled to the image size, /Matte un-blended), stencil /Mask and colour-key /Mask, JPEG images included (#645); JPX masks are left out (image exported opaque); JPX images and separations reported as skipped; minimum size filter. Lossless images apply per-component Decode; Indexed values round and clip before palette lookup. Missing, null or malformed Decode arrays keep the default mapping. Soft-mask Decode intervals preserve opacity before resizing, including indirect arrays and endpoints. Still limited: 16-bit samples use high bytes; general JPEG image Decode, ICC transforms, and calibrated colors remain unsupported. CCITT fax images (Group 3 and 4, with their /DecodeParms, behind other filters too) export as their picture, masks included; byte-aligned Group 3 is read by the end-of-line codes when the data starts with one and on bytes otherwise, and one cut short is reported. Still limited: byte-aligned Group 3 with codes but none before the first row (not as T.4 sends them) is reported, or at /K 0 may export wrong. JBIG2 images (with the /JBIG2Globals of their own /DecodeParms entry, within 32 MiB, behind other filters too) export as their picture, masks included; the JBIG2 page has to be the image's size (the renderer draws the whole page into the image)." +notes = "each image once (page resources and nested forms), up to what one export may decode and hold of files (2 GiB or twice the document), images past that left out with the reason; JPEG unchanged unless it has transparency, others PNG (gray/RGB/CMYK/ICC/Indexed, 1–16 bpc, stencil masks); transparency as PNG alpha: /SMask (scaled to the image size, /Matte un-blended), stencil /Mask and colour-key /Mask, JPEG images included (#645); JPX masks are left out (image exported opaque); JPX images and separations reported as skipped; minimum size filter. Lossless images apply per-component Decode; Indexed values round and clip before palette lookup. Missing, null or malformed Decode arrays keep the default mapping. Soft-mask Decode intervals preserve opacity before resizing, including indirect arrays and endpoints. Still limited: 16-bit samples use high bytes; general JPEG image Decode, ICC transforms, and calibrated colors remain unsupported. CCITT fax images (Group 3 and 4, with their /DecodeParms, behind other filters too) export as their picture, masks included; byte-aligned Group 3 is read by the end-of-line codes when the data starts with one and on bytes otherwise, and one cut short is reported. Still limited: byte-aligned Group 3 with codes but none before the first row (not as T.4 sends them) is reported, or at /K 0 may export wrong. JBIG2 images (with the /JBIG2Globals of their own /DecodeParms entry, within 32 MiB, behind other filters too) export as their picture, masks included; the JBIG2 page has to be the image's size (the renderer draws the whole page into the image)." [[feature]] id = "create.export-html" @@ -7373,8 +7379,8 @@ milestone = "M11" status = "shipped" commands = ["optimize.reduce"] tools = ["doc_reduce"] -evidence = ["crates/ui-egui/tests/it/create.rs::reduce_file_size_writes_a_compact_copy", "crates/ui-egui/tests/it/create.rs::reduce_file_size_saves_nothing_when_the_file_is_already_small", "crates/engine/src/tests.rs::create_and_reduce", "crates/automation/tests/it/automation.rs::creating_and_reducing_through_tools", "crates/automation/tests/it/automation.rs::optimizing_through_tools", "crates/optimize/tests/optimize.rs::an_identity_decode_array_does_not_stop_reduce"] -notes = "images above 225 ppi to 150 ppi JPEG medium (after merging page pictures printed as one-pixel strips into one image), black-and-white images averaged down to 300 ppi above 450 ppi, and stored as CCITT Group 4 whenever that is smaller, thumbnails dropped, resources merged, object streams; scanner images with the default decode array are included; a copy that isn't smaller is not saved (\"already as small as it can be made\"); runs in the background with a progress bar and Cancel" +evidence = ["crates/ui-egui/tests/it/create.rs::reduce_file_size_writes_a_compact_copy", "crates/optimize/tests/optimize.rs::a_picture_with_a_stencil_mask_is_downsampled_under_its_mask", "crates/optimize/tests/optimize.rs::a_picture_whose_mask_is_not_a_stencil_is_left_alone", "crates/ui-egui/tests/it/create.rs::reduce_file_size_saves_nothing_when_the_file_is_already_small", "crates/engine/src/tests.rs::create_and_reduce", "crates/automation/tests/it/automation.rs::creating_and_reducing_through_tools", "crates/automation/tests/it/automation.rs::optimizing_through_tools", "crates/optimize/tests/optimize.rs::an_identity_decode_array_does_not_stop_reduce"] +notes = "images above 225 ppi to 150 ppi JPEG medium (after merging page pictures printed as one-pixel strips into one image), black-and-white images averaged down to 300 ppi above 450 ppi, and stored as CCITT Group 4 whenever that is smaller, thumbnails dropped, resources merged, object streams; scanner images with the default decode array are included; pictures under a stencil mask are included and the mask stays as it is, though samples it hides still count when resampling, so their colour can reach its edge; pictures with a colour-key mask are left alone; a copy that isn't smaller is not saved (\"already as small as it can be made\"); runs in the background with a progress bar and Cancel" [[feature]] id = "optimize.compatibility-level" @@ -7433,8 +7439,8 @@ milestone = "M11" status = "partial" commands = ["optimize.advanced", "optimize.reduce"] tools = ["doc_optimize", "doc_reduce"] -evidence = ["crates/optimize/tests/optimize.rs::eight_bit_black_and_white_images_become_one_bit", "crates/filters/src/ccitt.rs::bitmaps_round_trip", "crates/filters/src/ccitt.rs::a_page_of_text_like_marks_round_trips_and_shrinks", "crates/filters/src/ccitt.rs::what_it_cannot_encode_is_an_error", "crates/optimize/tests/optimize.rs::black_and_white_images_become_ccitt_group_4", "crates/optimize/tests/optimize.rs::group_3_fax_images_become_group_4", "crates/optimize/tests/optimize.rs::rgb_and_two_colour_indexed_black_and_white_images_become_one_bit", "crates/optimize/tests/optimize.rs::black_and_white_rgb_used_beyond_the_page_content_read_stays_rgb", "crates/optimize/tests/optimize.rs::black_and_white_rgb_drawn_only_where_the_optimizer_reads_becomes_grey", "crates/optimize/tests/optimize.rs::black_and_white_rgb_in_resources_its_page_tree_and_a_form_share_becomes_grey", "crates/automation/tests/it/automation.rs::doc_optimize_stores_black_and_white_images_as_ccitt_group_4", "crates/ui-egui/tests/it/create.rs::the_pdf_optimizer_dialog_saves_an_optimized_copy", "crates/filters/src/mq.rs::the_annex_h_test_sequence_encodes_to_its_bytes", "crates/filters/src/jbig2.rs::bitmaps_round_trip", "crates/filters/src/jbig2.rs::a_page_of_text_like_marks_round_trips_and_shrinks", "crates/optimize/tests/optimize.rs::black_and_white_images_become_jbig2", "crates/automation/tests/it/automation.rs::doc_optimize_stores_black_and_white_images_as_jbig2", "crates/filters/src/jbig2/symbols.rs::repeated_marks_are_stored_once", "crates/filters/src/jbig2/symbols.rs::scattered_marks_round_trip", "crates/optimize/tests/optimize.rs::rendered_text_becomes_jbig2_symbols", "crates/optimize/tests/optimize.rs::jbig2_scans_are_averaged_and_stored_again"] -notes = "CCITT Group 4, lossless: PDF Optimizer ▸ Images ▸ Monochrome Images (on by default, so Reduce File Size does it too; doc_optimize mono) stores a 1-bit image of one colour component (grey, indexed, a separation) or an image mask, kept with no filter or general-purpose ones, as Group 4 when that is smaller as stored; the samples decode to the same bits, so colour space, decode array and masks stay. Packed to one bit first, then stored the same way (colour-key masks aside): eight-bit grey of only black and white, eight-bit DeviceRGB of only black and white (as DeviceGray; calibrated RGB, RGB with a profile, RGB drawn or listed where /DefaultGray or /DefaultRGB is in force or referred to from anywhere but the page and form resources read (an annotation's appearance or a pattern drawing it, directly or through resources or a form shared with a page; another image's /Alternates), and RGB whose soft mask has a /Matte aside), and an indexed image of 2, 4 or 8 bits that uses only palette entries 0 and 1 (keeping its palette), unless the grey or colour settings make it smaller still, as they can a dithered scan downsampled to JPEG, its soft mask counted. Group 4 wins on scans; on clean computer-drawn 1-bit art Flate can be smaller, and the image then stays. Group 3 fax images are stored again as Group 4 when that is smaller (damaged Group 3 with end-of-line codes as the decoder recovers it, as it reports no damage there; byte-aligned Group 3 with end-of-line codes but none before the first row, not as T.4 sends them, as PdfCraft draws it, which at /K 0 may be other rows than were coded). CCITT fax images are decoded to be downsampled (optimize.downsample-images), and a resampled image is stored as Group 4 or 1-bit Flate, whichever is smaller. Lossless JBIG2 with bounded exact-copy symbol coding is available too, with image export; lossy JBIG2 remains unsupported. JBIG2 images are read too: averaged like any (under Retain stored as JBIG2 again), and, not resampled, stored again as the compression asks when that is smaller (as JBIG2 symbols where its own coding is a generic region, say); a symbol-coded scan, averaged, loses its exact repeats and is often larger, and then stays as it is; one whose JBIG2 page isn't its size is left alone. Not yet: inline images, soft masks and /Mask images, Group 4 for rows wider than 32,767 samples." +evidence = ["crates/optimize/src/images.rs::flate_images_past_the_runs_allowance_stay_as_they_are", "crates/optimize/tests/optimize.rs::eight_bit_black_and_white_images_become_one_bit", "crates/filters/src/ccitt.rs::bitmaps_round_trip", "crates/filters/src/ccitt.rs::a_page_of_text_like_marks_round_trips_and_shrinks", "crates/filters/src/ccitt.rs::what_it_cannot_encode_is_an_error", "crates/optimize/tests/optimize.rs::black_and_white_images_become_ccitt_group_4", "crates/optimize/tests/optimize.rs::group_3_fax_images_become_group_4", "crates/optimize/tests/optimize.rs::rgb_and_two_colour_indexed_black_and_white_images_become_one_bit", "crates/optimize/tests/optimize.rs::black_and_white_rgb_used_beyond_the_page_content_read_stays_rgb", "crates/optimize/tests/optimize.rs::black_and_white_rgb_drawn_only_where_the_optimizer_reads_becomes_grey", "crates/optimize/tests/optimize.rs::black_and_white_rgb_in_resources_its_page_tree_and_a_form_share_becomes_grey", "crates/automation/tests/it/automation.rs::doc_optimize_stores_black_and_white_images_as_ccitt_group_4", "crates/ui-egui/tests/it/create.rs::the_pdf_optimizer_dialog_saves_an_optimized_copy", "crates/filters/src/mq.rs::the_annex_h_test_sequence_encodes_to_its_bytes", "crates/filters/src/jbig2.rs::bitmaps_round_trip", "crates/filters/src/jbig2.rs::a_page_of_text_like_marks_round_trips_and_shrinks", "crates/optimize/tests/optimize.rs::black_and_white_images_become_jbig2", "crates/automation/tests/it/automation.rs::doc_optimize_stores_black_and_white_images_as_jbig2", "crates/filters/src/jbig2/symbols.rs::repeated_marks_are_stored_once", "crates/filters/src/jbig2/symbols.rs::scattered_marks_round_trip", "crates/optimize/tests/optimize.rs::rendered_text_becomes_jbig2_symbols", "crates/optimize/tests/optimize.rs::jbig2_scans_are_averaged_and_stored_again", "crates/optimize/src/images.rs::jbig2_images_past_the_runs_allowance_stay_as_they_are"] +notes = "All of a run's images share one allowance of decoding, filters, decoders and pixels alike (about 1,000 scanned pages' worth, more for a longer file); those past it stay as they are, those the image pass read being counted in the report, which doc_optimize and doc_reduce return and the panel doesn't show yet. CCITT Group 4, lossless: PDF Optimizer ▸ Images ▸ Monochrome Images (on by default, so Reduce File Size does it too; doc_optimize mono) stores a 1-bit image of one colour component (grey, indexed, a separation) or an image mask, kept with no filter or general-purpose ones, as Group 4 when that is smaller as stored; the samples decode to the same bits, so colour space, decode array and masks stay. Packed to one bit first, then stored the same way (colour-key masks aside): eight-bit grey of only black and white, eight-bit DeviceRGB of only black and white (as DeviceGray; calibrated RGB, RGB with a profile, RGB drawn or listed where /DefaultGray or /DefaultRGB is in force or referred to from anywhere but the page and form resources read (an annotation's appearance or a pattern drawing it, directly or through resources or a form shared with a page; another image's /Alternates), and RGB whose soft mask has a /Matte aside), and an indexed image of 2, 4 or 8 bits that uses only palette entries 0 and 1 (keeping its palette), unless the grey or colour settings make it smaller still, as they can a dithered scan downsampled to JPEG, its soft mask counted. Group 4 wins on scans; on clean computer-drawn 1-bit art Flate can be smaller, and the image then stays. Group 3 fax images are stored again as Group 4 when that is smaller (damaged Group 3 with end-of-line codes as the decoder recovers it, as it reports no damage there; byte-aligned Group 3 with end-of-line codes but none before the first row, not as T.4 sends them, as PdfCraft draws it, which at /K 0 may be other rows than were coded). CCITT fax images are decoded to be downsampled (optimize.downsample-images), and a resampled image is stored as Group 4 or 1-bit Flate, whichever is smaller. Lossless JBIG2 with bounded exact-copy symbol coding is available too, with image export; lossy JBIG2 remains unsupported. JBIG2 images are read too: averaged like any (under Retain stored as JBIG2 again), and, not resampled, stored again as the compression asks when that is smaller (as JBIG2 symbols where its own coding is a generic region, say); a symbol-coded scan, averaged, loses its exact repeats and is often larger, and then stays as it is; one whose JBIG2 page isn't its size is left alone. Not yet: inline images, soft masks and /Mask images, Group 4 for rows wider than 32,767 samples." [[feature]] id = "optimize.only-if-smaller" @@ -8085,8 +8091,8 @@ milestone = "M10" status = "shipped" commands = ["print.dialog"] tools = ["printers", "printer_options", "doc_print"] -evidence = ["crates/print/src/tests.rs::spooler_arguments_and_printer_list", "crates/print/src/tests.rs::driverless_printers_join_the_list_without_a_queue", "crates/print/src/tests.rs::windows_printers_carry_one_default_and_keep_their_names", "crates/print/src/tests.rs::printer_options_come_from_the_ppd", "crates/print/src/tests.rs::printer_option_defaults_and_job_arguments", "crates/ui-egui/tests/it/print.rs::print_dialog_shows_the_printer_driver_options", "crates/ui-egui/tests/it/print.rs::printers_listed_in_the_background_preselect_the_default_unless_one_was_picked", "crates/ui-egui/src/workflows/web_print.rs::resolution_falls_with_the_sheet_count_and_long_jobs_are_refused", "crates/ui-egui/src/workflows/web_print.rs::large_sheets_are_drawn_within_the_pixel_cap_and_bad_sizes_are_refused", "crates/ui-egui/src/workflows/web_print.rs::a_sink_error_or_a_page_that_isnt_there_stops_the_job", "crates/print/src/tests.rs::a_command_that_never_answers_is_stopped_at_the_deadline", "crates/ui-egui/tests/it/print.rs::printer_options_are_read_off_the_gui_thread_and_a_dead_read_offers_nothing"] -notes = "CUPS queues via lpstat -p -d and driverless destinations without a queue via lpstat -e; on Windows shared craft-print lists the queues (EnumPrinters), the default (GetDefaultPrinter) and each driver's two-sided support in this process, and draws jobs as vectors with Windows.Data.Pdf into the XPS print API with a driver-validated PrintTicket (exact paper, orientation, no scaling; portrait and landscape sheets in one job via /Rotate), starting no PowerShell, so printing works under App Control script enforcement (#1107); the printer list and submission run on workers; Save as PDF on every platform. Properties…: on CUPS the driver's own PPD job options (tray, paper type, finishing …, not installable options or what the dialog sets) for this job, sent as lp -o; on Windows the driver's Printing Preferences window (printui), saved as that printer's per-user defaults rather than per job. On the web: \"Browser's print dialog\" (the default there) reaches the system's printers through the browser; PdfCraft draws the sheets itself (300 dpi up to 100 sheets, 200 up to 300, 150 up to 1,000; at most 64 megapixels a sheet and 1 GiB a job) and prints them from a hidden iframe, one per printed page, a landscape sheet among portrait ones turned onto the paper; copies, two-sided and colour are chosen in the browser's dialog; a browser that refuses to print gets the print-ready PDF as a download. Checked in headless Chromium, not yet in Firefox or Safari; pictures, not vectors; sheets of another paper size print at their own size only where the browser honours named @page sizes (Chromium doesn't). Properties… on CUPS reads the driver options off the GUI thread and gives lpoptions ten seconds before the PPD defaults stand (#1818)" +evidence = ["crates/print/src/tests.rs::spooler_arguments_and_printer_list", "crates/print/src/tests.rs::a_job_names_its_title_and_owner_to_the_spooler", "crates/print/src/tests.rs::a_job_keeps_the_title_and_owner_it_already_sets", "crates/print/src/tests.rs::a_submitted_job_reaches_lp_named", "crates/print/src/tests.rs::driverless_printers_join_the_list_without_a_queue", "crates/print/src/tests.rs::windows_printers_carry_one_default_and_keep_their_names", "crates/print/src/tests.rs::printer_options_come_from_the_ppd", "crates/print/src/tests.rs::printer_option_defaults_and_job_arguments", "crates/ui-egui/tests/it/print.rs::print_dialog_shows_the_printer_driver_options", "crates/ui-egui/tests/it/print.rs::printers_listed_in_the_background_preselect_the_default_unless_one_was_picked", "crates/ui-egui/src/workflows/web_print.rs::resolution_falls_with_the_sheet_count_and_long_jobs_are_refused", "crates/ui-egui/src/workflows/web_print.rs::large_sheets_are_drawn_within_the_pixel_cap_and_bad_sizes_are_refused", "crates/ui-egui/src/workflows/web_print.rs::a_sink_error_or_a_page_that_isnt_there_stops_the_job", "crates/print/src/tests.rs::a_command_that_never_answers_is_stopped_at_the_deadline", "crates/ui-egui/tests/it/print.rs::printer_options_are_read_off_the_gui_thread_and_a_dead_read_offers_nothing"] +notes = "CUPS queues via lpstat -p -d and driverless destinations without a queue via lpstat -e; on Windows shared craft-print lists the queues (EnumPrinters), the default (GetDefaultPrinter) and each driver's two-sided support in this process, and draws jobs as vectors with Windows.Data.Pdf into the XPS print API with a driver-validated PrintTicket (exact paper, orientation, no scaling; portrait and landscape sheets in one job via /Rotate), starting no PowerShell, so printing works under App Control script enforcement (#1107); the printer list and submission run on workers; Save as PDF on every platform. Properties…: on CUPS the driver's own PPD job options (tray, paper type, finishing …, not installable options or what the dialog sets) for this job, sent as lp -o; on Windows the driver's Printing Preferences window (printui), saved as that printer's per-user defaults rather than per job. On the web: \"Browser's print dialog\" (the default there) reaches the system's printers through the browser; PdfCraft draws the sheets itself (300 dpi up to 100 sheets, 200 up to 300, 150 up to 1,000; at most 64 megapixels a sheet and 1 GiB a job) and prints them from a hidden iframe, one per printed page, a landscape sheet among portrait ones turned onto the paper; copies, two-sided and colour are chosen in the browser's dialog; a browser that refuses to print gets the print-ready PDF as a download. Checked in headless Chromium, not yet in Firefox or Safari; pictures, not vectors; sheets of another paper size print at their own size only where the browser honours named @page sizes (Chromium doesn't). Properties… on CUPS reads the driver options off the GUI thread and gives lpoptions ten seconds before the PPD defaults stand (#1818); on macOS lp jobs also carry the job name and owner (com.apple.print.JobInfo.PMJobName and PMJobOwner) that the system print dialog sends and some vendors' filters need (#5743). Not yet checked on a physical Kyocera printer." [[feature]] id = "print.copies-collate" diff --git a/vendor/README.md b/vendor/README.md index 3173659698..4fda6483af 100644 --- a/vendor/README.md +++ b/vendor/README.md @@ -39,11 +39,11 @@ Other resource categories retain their existing parent-chain lookup. | Crate | Version | Licence | Patches | Test | |---|---|---|---|---| -| hayro-interpret | 0.7.0 | Apache-2.0 OR MIT | (1) select `/AP /N` appearance states via `/AS` (checkboxes, radios, stateful icons) and honour the NoView flag; (2) Type3 Unicode fallback to `/Encoding` glyph names, then printable ASCII; (3) `Type3Glyph::advance_width`; (4) `InterpreterSettings::ocg_overrides` for viewer layer toggles; (5) soft masks whose group lacks `/CS` were dropped (Chrome gradient text); (6) paint nesting cap `MAX_PAINT_NESTING` for tiling patterns and Type 3 glyphs (self-referencing content overflowed the stack); (7) CID width ranges in `/W` and `/W2` clamped to `MAX_CID` (a `0 4294967295 w` range hung); (8) `InterpreterSettings::hide_comments` skips markup annotations but keeps widgets and links (View ▸ Hide all comments); (9) `image_size_ok`: images and masks over 2^28 pixels are not decoded (a fuzzed `/W 4294967295` stencil mask allocated 4 GiB); (10) `MAX_NESTED_PAINTS`: nested paints (forms, Type 3 glyphs and tiling patterns inside one another) share a per-page budget of 50,000 (a glyph showing eight glyphs of its own font, sixteen deep, hung); (11) depends on skrifa 0.47 instead of 0.42 (upstream read-fonts fixed a Type 1 tokenizer that recursed through runs of numbers: a fuzzed font hung or overflowed the stack), with the one API change (`Charset::glyph_id` returns `Option`); (12) annotation appearances whose `/BBox` or `/Matrix` collapses to a line or a point are skipped (mapping them onto `/Rect` divided by zero and handed the device infinite or NaN matrices); (13) a Highlight annotation without a usable normal appearance is drawn from its `/QuadPoints`, `/C` and `/CA` with Multiply blending, as pdfcraft-annot draws highlights (it was not drawn at all); (14) simple-font `/Widths` (`read_widths`): entries only for codes 0–255 (one entry per code below `/FirstChar` was allocated: `4294967295` asked for 34 GB), an entry that isn't a number leaves its code missing instead of ending the array, and a `/LastChar` below `/FirstChar` gives no widths instead of discarding the font for a standard one; (15) the appearance box is mapped onto `/Rect` corner to corner: the translation now accounts for the scale (an appearance whose box didn't start at the origin and differed in size from `/Rect` was drawn shifted); (16) a clip set by `W`/`W*` takes effect after whichever path-painting operator ends the path (`S`, `f`, `B`, … as well as `n`; ISO 32000-2 §8.5.4): it was applied only on `n`, so `re W* S` clipped nothing and the clip stayed pending for a later, unrelated `n`; (17) `InterpreterSettings::cancelled`: once set, interpretation stops before the next content operator (a render pool sets it for every worker when dropped, after an edit or on closing, and for one worker when the watchdog gives up on its render, so renders whose answers nobody can receive stop instead of running to the end); (18) `MAX_PAGE_CONTENT`: the content a page holds at once (its contents, and the forms, tiling patterns and Type 3 glyph procedures being painted) stays within 512 MiB (`decode_content`; once it runs out, `InterpreterWarning::ContentTruncated` is reported (once per page by pdfcraft-render) so a truncated page is not a clean render; each level gives its bytes back when it finishes): forms nest fifty deep and each level kept its content while the next ran, so a form painting itself around a stream inflating to 256 MiB would have held over 12 GB; and Type 0 sampled functions take at most `MAX_SAMPLE_ENTRIES` (2^21) table points and `MAX_SAMPLE_VALUES` (2^23) samples, read no further than `/Size` asks (256 MiB of 1-bit samples asked for over 8 GB); (19) mesh shadings (types 4–7) are sampled only inside the area being drawn (`ShadingPattern::encode_within`, which the vendored hayro renderer calls with that area plus a pixel), within 8 visits per pixel of it plus 4 per triangle (`TriangleSampler`), and patches are triangulated one at a time: points far off the page were sampled over their whole bounding box, up to 65536 × 65536 entries (a fuzzed 147-byte patch stream; a synthetic page passed 6 GB in six seconds), ten thousand overlapping triangles ran for minutes, and every patch became 722 triangles before any limit; meshes hold at most `MAX_MESH_PATCHES` (2^16) patches and `MAX_MESH_TRIANGLES` (2^20) triangles, a lattice needs two to 2^19 vertices per row (`/VerticesPerRow 0` pushed empty rows for ever; one huge row read the whole stream), and a page samples at most `MAX_PAGE_MESH_TRIANGLES` (2^25) mesh triangles in all (a mesh painted a thousand times was triangulated a thousand times); each cut logs a warning; (20) PDF function construction is limited to 64 levels and 10,000 total nodes with cycle detection; calculator parsing and evaluation share procedure depth/work budgets, integer division/bitshift/rotation/index are panic-free, and fixed-size stack errors propagate; (21) a Type 0 font drawn with a substitute that isn't CID-keyed (it isn't embedded, or its program doesn't load) draws `.notdef` for a CID of an Adobe character collection (Japan1, GB1, CNS1, Korea1) that it can't find by Unicode: hayro took the CID for a glyph index of the substitute, which numbers its glyphs its own way, so the character was drawn as an unrelated one (𠮷 as "Q" in BIZ UDPGothic); (22) a Type 0 font drawn with a substitute finds a character given with a variation selector (`/ToUnicode`, or Adobe-Japan1-UCS2, which maps the JIS X 0208 forms of the kanji JIS X 0213:2004 redrew that way: CID 1247 is 噂 U+E0100) through the substitute's variation sequences, else as the character alone: such a CID found no glyph and was drawn as an unrelated one; (23) backport of hayro 0.8's `gradient` module: `EncodedShadingPattern::as_svg_gradient` turns an axial or radial shading into stops of an sRGB gradient (within 0.01 per channel, a stop at every stitching-function bound via `Function::stitching_bounds`) when a native gradient draws it exactly (extended past the box drawn in; a radial one with no background colour); (24) `DecodedImageCache`: decoded image pixels shared across renders through the interpreter cache within a 64 MiB budget (an image-heavy page decoded its thousands of images again per tile and per scale), keyed by every decode input (`DecodedImageKey`: the stream's place and dictionary bytes, its object, mask/stencil/raster output, interpolation, decode target size, preview or final); images under a transfer function and inline images are not cached, an image over the budget is never kept, and a poisoned lock decodes uncached; (25) `Device::actual_text` hands the device a marked content sequence's `/ActualText` (inline or named in `/Properties`), so text extraction keeps the Thai, Indic and Arabic clusters Chrome marks this way (their shaped tone marks and vowels have no Unicode of their own); (26) non-embedded simple fonts drawn with a standard-font stand-in build the Latin Extended-A letters the stand-in lacks (`/Gbreve`, `/Idotaccent`, `/Scedilla`, `/aogonek`, `/ccaron`…) from the base letter and accent it has (`StandardKind::composite_glyph`, `ACCENTED_LETTERS`): PDFium's Foxit stand-ins hold only the Standard/WinAnsi/Mac Roman glyphs, so iText letters with Times New Roman unembedded showed blanks for Ğ, İ, Ş, ğ and ş; the comma-below letters (`/scommaaccent`, `/Tcommaaccent`, `/kcommaaccent`…, found by character, so `/uni0136` and the glyph list's `/Kcedilla` too) are the letter and the font's comma, smaller and under the baseline, since the stand-ins have no `commaaccent` (Romanian ș drew nothing and ț a cedilla in forms laid out from XFA; ģ, whose comma is turned and above, is not built); (27) an embedded TrueType font without a base encoding reads its codes as WinAnsi for text extraction (`EmbeddedKind::code_to_unicode_name`), matching pdftotext's output, instead of Standard: OCR text layers of scans write WinAnsi codes with no `/Encoding`, and Standard has no ü, ö or ß and reads é as Ø (glyph selection unchanged); (28) an image whose pixels hold at most 16 bits of samples (an 8-bit Separation or DeviceN image, a 1-, 2- or 4-bit gray or indexed one) is converted once per possible pixel value through a lookup table instead of once per pixel (`rgb_via_lookup`): a spot-colour tint transform is often a PostScript calculator program, run for every pixel, so a fillable character sheet's 3304 × 4105 DeviceN background took four seconds and 430 MB to draw a page; each entry is converted on its own (`convert_each`), so a tint transform giving the wrong number of components for a value the image never uses cannot shift the colours of the values it does; (29) `Device::begin_annotations`/`end_annotations` bracket the page's annotations, so a device can tell comment paints from document paints (reading colours recolour the document, never a comment, #1548); (30) the Annex D.2 alias codes read as the ink they draw: WinAnsiEncoding 0xA0 and 0xAD, and MacRomanEncoding 0xCA, carry the glyph names `space` and `hyphen` -- the names those tables also give 0x20 and 0x2D -- not `nbspace` and `sfthyphen`, whose glyph list values U+00A0 and U+00AD are invisible formatting characters. Extraction hid drawn ink behind them, so search and redaction matched neither (`XiaoBiaoSong.pdf` in the pdf.js corpus drew 104 soft hyphens; across the 989 files the soft hyphens we extract fall from 117 to 13 and the non-breaking spaces from 30 to 26, what remains coming from `/ToUnicode` maps, which say so explicitly). The base table only, in the text direction only: a `/Differences` name keeps its glyph list value and glyph lookup is untouched, both as pdftotext does; (31) a Type 0 sampled function keeps its samples in one flat array indexed by strides (`Type0::entry`) instead of a hash map keyed by each grid point: the map was built again, one hashed insert per sample, every time a shading using the function was painted (a 2,097,152-sample ramp painted 30 times took 38 s; `bug1721218` in the pdf.js corpus spent most of a 1.5 s page on it); the interpolation is unchanged, so results are bit for bit the same, a sample missing from a short stream still gives no value, and the maximum sample value is computed without overflowing at 32 bits per sample; (32) the decoded-image cache (24) keys a decode by the size the image is drawn at only when a JPX stream decodes it or its soft mask or mask (`decode_reads_target`): JPX is the only filter that decodes a reduced resolution for a size, so a JPEG or Flate scan was decoded again at every zoom step and kept once per zoom level; one decode now serves every size; `InterpreterCache::decoded_image_decodes` counts the cache's decodes; (33) Coons and tensor-product patches copy their vertices' colours less: each point of a patch's 20 × 20 triangle grid is interpolated once (`generate_patch_triangles`; each cell interpolated its four corners itself, 1,444 interpolations a patch for 400 points), a cell's second triangle takes the vertices its first copied, and the mesh sampler moves a patch's triangles into device space instead of copying each vertex (`TriangleSampler::sample_owned`); the same values, 10–16% faster on mesh-gradient pages; (34) `color::tint_transform_runs`: how many colours the calling thread has run through a Separation or DeviceN tint transform (counted once per batch in `convert_f32`), so a test counts patch (28)'s once-per-sample-value runs instead of timing them (its 10 s deadline failed on a busy FreeBSD VM in CI); (35) `EncodedShadingPattern::extent`: where a mesh shading (types 4–7) can paint at all, the pixels its triangles touched when it was encoded (`None` for the types that paint everywhere, and when the shading has a `/Background`), so the renderer samples a texture there alone and skips a mesh with nothing on the canvas; (36) a mesh shading's pixel whose corner no triangle holds strictly (on an edge two triangles share, or on the mesh's side) takes the triangle that covers its centre, edges included (`Triangle::covers`): testing only the corner left a white seam along every shared edge, and the colour is still taken at the corner; (38) the `/DefaultGray`, `/DefaultRGB` and `/DefaultCMYK` colour spaces of a resource dictionary (ISO 32000-2 §8.6.5.6) replace the device space content selects: with `g`/`G`, `rg`/`RG`, `k`/`K` and `cs`/`CS` (by name, or through a `/ColorSpace` resource that is a device space), and as the `/ColorSpace` of an image XObject, an inline image or a shading painted by `sh` or as a shading pattern (`DefaultColorSpaces`, looked up once per content window in the resources and those they inherit, so a form XObject without a default of its own draws in its page's, as Poppler and MuPDF draw it); a default that is a Lab, Indexed, Pattern or device space, has another number of components or is no colour space is ignored and device colour is drawn as before; device spaces inside other spaces (an Indexed base, a Separation or DeviceN alternate, a Pattern's underlying space), shading dictionaries, masks and transparency group spaces are unchanged, and the decoded-image cache (24) keys a decode by the default it was drawn in. hayro drew device colour as it was, so pages that calibrate it this way (common in PDF/A) came out in the wrong colours; (39) knockout groups (#2971): `Device::set_knockout` right after a `/K true` group is pushed; `Device::knockout_image` for an unmasked image before its group is pushed, when `Device::in_knockout_group`: the device clears its placement rectangle only if it will draw the image (on the canvas, not a preview's tiny image, and it decodes), decoded at its draw size so the draw reuses that decode; and, when `Device::knockout_erase_wanted`, a nested group's content drawn once between `begin_knockout_erase` and `end_knockout_erase` before the group itself, which then always gets a layer of its own; (40) an optional content membership dictionary's visibility expression (`/VE`: `/And`, `/Or`, `/Not`, nested up to 32 deep) decides its visibility ahead of `/OCGs` and `/P` (ISO 32000-2 §8.11.2.2); it was ignored, so content under it stayed visible with its layers hidden; a malformed expression, including one naming an object the document doesn't list in `/OCProperties /OCGs`, falls back to `/OCGs` and `/P` (#2986); (41) a transparency group that is neither isolated nor knockout, entered at full opacity with no soft mask and Normal blending, is drawn straight onto the page instead of into a layer of its own (§11.4.7: its elements composite with the backdrop; the layer made a `/BM /Multiply` highlight appearance an opaque block, #1968); (42) text in a Type 3 font is drawn filled whatever the text rendering mode, except mode 3 (invisible): only that mode has any effect on Type 3 fonts (ISO 32000-1 §9.3.6). Stroking ran the glyph procedure a second time, so `2 Tr` made bitmap fonts look bold, `1 Tr` painted an uncoloured glyph in the stroking colour, and `7 Tr` hid it (`7 Tr` since follows 64); (43) Lab colour spaces honour their own `/WhitePoint`: L\*a\*b\* goes to XYZ relative to that white, is Bradford-adapted to D65 and converted to sRGB (ISO 32000-2 §8.6.5.4) instead of through `LAB.icc` as if every white were D50 (a D65 blue came out 45 levels too red; the profile is removed); components normalised to [0, 1] (`manual_scale`, an `/Indexed` palette over Lab) map onto L\* 0..100 and the a\*/b\* `/Range`; (44) a Type 0 font whose `/ToUnicode` is the name `/Identity-H` or `/Identity-V` (not a CMap stream; WSCAD writes it) reads each code as its Unicode value, as Acrobat shows it (`Type0Font::identity_to_unicode`); the identity CMap the name resolved to maps codes to CIDs only, so such pages had no text to select or find; (46) an image XObject's group applies the fill opacity, so the fill alpha is reset to 1 before a stencil mask takes the fill colour as its paint, and a pattern paint drops the opacity it captured at `scn` (`Pattern::without_opacity`) (it was applied twice: a mask at `ca 0.5` was drawn at a quarter, #2975); (47) `path_as_rect`: a five-element path is a rectangle only when its four points are distinct, each step from one to the next runs along a single axis, and the last returns to the first. The length test admits one MoveTo and four LineTo as well as one MoveTo, three LineTo and a ClosePath, and asking only that every corner of the bounding box was visited says nothing about the order or the steps between, so a five-point polyline whose ends reached the corners was painted as that box -- a fourth side the path does not have -- and a clip of that shape was discarded; the coordinates are compared exactly, since the matrix is applied after this check and a `cm` of 10,000 turns `is_nearly_equal`'s 256th of a unit into tens of device units (#3327); (48) an `/ICCBased` colour space is cached by what its profile is read from (`IccProfileKey`): the stream object it names, looked up without reading the stream, and then the stream's dictionary and its own bytes (decrypted, not decoded), so a byte-for-byte copy of a profile in another object is read once, and a profile stream written directly in its array, which reports the object holding the array as every other stream written there does, is told apart by its bytes. hayro keyed it by the stream dictionary's bytes alone, so two different profiles with the same `/N` and `/Length` shared whichever was read first, and colours in the second were drawn through the first. `InterpreterCache::icc_profile_reads` counts the profiles read; (49) `OpenTypeFontBlob::new` also accepts a `post` table version 1.0, 2.0 or 3.0 written with its 16-bit halves swapped (`00 00 00 03`), as ScanSoft PDF Create! embeds every font; such fonts were refused and their text drawn with a substitute (Hebrew came out garbled or missing, #2946); `glyph_names` reads such a table from a copy with the version written correctly, so a 2.0 table's names serve `/Differences`. Any other unknown version is still refused (pdf.js 9462); (50) `CffFontBlob::glyph_index_by_name` looks a glyph name up in a name to glyph map built on first use (shared between clones) instead of searching the whole charset, with a string lookup per glyph, for every character code of a font; the first glyph with a name still wins; (51) at most 4096 graphics states saved at once, holding at most 64 MiB together (each `q` copies the whole state, dash array and clip list included, so short operators multiplied one large state); a `q` past either limit is counted but not copied, and its `Q` still removes the clips added since (from storytold/craft-libs#239); (52) a `/W2` run whose first CID is past `MAX_CID` stops there, as in `/W` (7), checked before the run's metrics are read: a first CID of 4294967295 inserted one entry and then overflowed, discarding the whole `/W2` table (from storytold/craft-libs#254); (55) a Separation or DeviceN tint transform that cannot be read keeps its colour space, and one that cannot be read or evaluated paints the alternate space's initial colour, as evaluation failures already did; that fallback, and a `cs`/`CS` colour space that cannot be read (drawn in DeviceGray as before), are now reported once per content stream as `InterpreterWarning::ColorFallback` (`RenderWarning::ColourFallback` in `pdfcraft-render`) instead of silently (#4260); (56) an annotation whose Invisible flag (bit 1) is set and whose `/Subtype` is none of the standard types of ISO 32000-2 Table 171 (`is_standard_annotation_type`; no `/Subtype` counts as unknown) is not drawn (Table 167), and a `/Popup` annotation's appearance is never painted on the page (§12.5.6.14: a popup has no appearance stream of its own; the viewer shows it as a window for its parent annotation). Both were drawn from their `/AP`; (57) a simple font drawn with a standard-font stand-in because the document names a font it doesn't embed (`StandardKind` with `fallback`) narrows a glyph to a narrower `/Widths` advance but no longer widens it to a wider one: the advance already places the next glyph (ISO 32000-2 §9.2.4; /Widths in Table 109), and widening drew a non-embedded `Arial,Bold` with 600-unit widths as a heavy fixed-pitch face whose `i` and `l` were solid blocks twice their width; an exact standard-14 font still matches its standard metrics both ways; (58) the fallback request for a Type 0 font that is not embedded (`FallbackFontQuery::with_descriptor`) takes its serif, italic and small-cap flags, `/FontWeight`, `/FontFamily` and `/FontStretch` from the descendant CIDFont's font descriptor (ISO 32000-2 §9.7.4.1, §9.7.6.1; §9.8): it read them from the Type 0 dictionary, which has none, so every such request asked for a regular sans-serif face and no resolver could tell a Song or Mincho font from a Hei or Gothic one, or see `/FontWeight 700`; (59) the NoRotate flag (`/F` bit 5) is honoured: the appearance, fitted to `/Rect`, is turned against the page's `/Rotate` about the rectangle's upper-left corner, which stays where it is, so it reads upright as the page is displayed (ISO 32000-2 §12.5.3). Sticky notes, which are saved NoRotate, were drawn turned with the page (#2583). Form fields and links stay in `/Rect`, where PdfCraft takes their click targets from it; (64) text in a Type 3 font follows ISO 32000-2 §9.3.6 in the clipping modes: under `7 Tr` it is not rendered (reported to the device as clipping text, `GlyphDrawMode::Clip`, so extraction keeps it), and in modes 4 to 7 a Type 3 glyph adds nothing to the clipping path (`clip_glyph`), so text shown only in a Type 3 font leaves no clip at `ET`. Since (42) `7 Tr` painted the glyphs in the fill colour (black by default), so a fill meant to follow showed them wherever it didn't cover them; 4 to 6 still render filled; (66) a Separation colour space whose colourant is the special name `All` paints every colourant at once (ISO 32000-2 §8.6.6.4): on screen and in an RGB print raster its tint t is the gray 1 − t, complemented because the device is additive, whatever its alternate space and tint transform say (hayro drew it through the tint transform, so a `/DeviceCMYK` transform giving cyan drew registration marks light cyan); `/None` still paints nothing, any other name still goes through its alternate, and a DeviceN space naming `All` keeps its alternate, since the clause gives the name that meaning in a Separation space; (63) a luminosity soft mask whose group colour space is `/DeviceCMYK` (by name, not an ICC-based or calibrated space) reads a `/DeviceCMYK` fill or stroke colour drawn in it, and its `/BC`, as their gray `1 - min(1, 0.3 c + 0.59 m + 0.11 y + k)` (ISO 32000-2 §10.4.2.3, §11.5.3: device colour converts to gray with no colour calibration; `Context::luminosity_in_device_cmyk`, `color::device_cmyk_to_gray`): it went through the CMYK display profile, where 100% K is a dark grey, so a 100% K mask let about an eighth of the masked paint through. CMYK images, shadings and tiling patterns inside such a mask, and CMYK on the page, still use the profile; (71) a lookup table in an indirect string reads: it was read as a stream first, which uses up a reference (ISO 32000-2 §8.6.6.3); (72) an uncoloured pattern's underlying space given as a name or a reference is used: it was skipped, so a CMYK cyan drew red (ISO 32000-2 §8.7.3.3); (74) colour spaces nest at most 32 levels, through every way one names another, so a chain of them ends instead of overflowing the stack; an ICC profile's `/Alternate` is read where it's met and isn't kept with the profile, or a page could build a chain past the limit on spaces already read | (1) `raster::tests::widget_appearance_states`; (2, 3) `xtask text-oracle` on corpus/pdfjs issue918; (4) `raster::tests::layer_override_hides_content`; (5) `raster::tests::soft_mask_without_group_colour_space_is_applied`; (6) `raster::tests::self_referencing_tiling_pattern_terminates`, `raster::tests::self_referencing_type3_glyph_terminates`; (7) `raster::tests::huge_cid_width_ranges_terminate`; (8) `raster::tests::hiding_comments_keeps_fields`; (9) `raster::tests::absurd_mask_and_fax_sizes_are_refused_before_decoding`; (10) `raster::tests::type3_glyphs_that_fan_out_into_themselves_finish`; (11) `raster::tests::type1_font_programs_with_long_runs_of_numbers_load_quickly`; (12) `raster::tests::degenerate_annotation_appearances_are_skipped`; (13) `raster::tests::highlights_without_an_appearance_are_drawn`; (14) `raster::tests::malformed_simple_font_widths_keep_later_widths_and_the_font`, `raster::tests::huge_simple_font_first_char_terminates`; (15) `raster::tests::annotation_appearance_box_maps_onto_rect`; (16) `raster::tests::clipping_path_applies_after_any_painting_operator`; (17) `raster::tests::dropping_the_pool_cancels_its_renders`, `raster::tests::the_watchdog_stops_the_render_it_gives_up_on`; (18) `raster::tests::page_contents_and_nested_forms_share_one_budget`, `raster::tests::content_painted_again_and_again_keeps_drawing`, `raster::tests::sampled_functions_with_billions_of_samples_are_refused`; (19) `raster::tests::mesh_shadings_far_off_the_page_render`, `raster::tests::many_overlapping_mesh_triangles_finish`, `raster::tests::mesh_shadings_with_many_patches_or_no_rows_finish`; (20) `raster::tests::function_limits_calculator_arithmetic_and_depth`, `raster::tests::function_limits_public_construction_work_and_depth`, `raster::tests::function_limits_stitching_cycles_are_refused_and_shared_children_work`, `raster::tests::function_limits_invalid_calculator_keeps_the_page_renderable`; (21) `raster::tests::cids_a_substitute_lacks_are_not_drawn_as_other_glyphs`; (22) `raster::tests::variation_sequences_draw_their_kanji_in_a_substitute`; (23) `raster::tests::axial_and_radial_shadings_draw_as_native_gradients`; (24) `raster::tests::tiles_match_full_render`, `raster::tests::skipping_paths_off_the_canvas_changes_no_pixel` (both decode through the cache), `raster::tests::decoded_images_with_identical_dictionaries_keep_their_own_pixels`, `raster::tests::decoded_images_under_a_transfer_function_are_not_shared`; (25) `text::tests::actual_text_replaces_the_glyphs_it_marks_in_every_writing_direction`, `text::tests::actual_text_follows_the_pdf_rules_for_marked_content`; (26) `raster::tests::accented_letters_the_standard_stand_ins_lack_are_built_from_their_parts`, `raster::tests::comma_below_letters_in_standard_fonts_draw_a_comma_under_the_letter`; (27) `text::tests::truetype_without_an_encoding_reads_its_codes_as_win_ansi`; (28) `raster::tests::spot_colour_images_run_their_tint_transform_once_per_sample_value`, `raster::tests::images_converted_through_a_table_keep_every_samples_colour`, `raster::tests::a_malformed_tint_for_an_unused_sample_keeps_the_used_colours`; (29) `raster::tests::reading_colors_keep_highlight_annotations_readable`; (30) `text::tests::the_annex_d2_alias_codes_read_as_an_ordinary_hyphen_and_space`; (31) `raster::tests::shadings_with_large_sampled_functions_paint_quickly`, `raster::tests::sampled_functions_interpolate_their_grid_as_before`; (32) `raster::tests::decoded_images_serve_every_size_they_are_drawn_at`; (33) `raster::tests::patch_meshes_keep_their_corner_colours`; (34) `raster::tests::spot_colour_images_run_their_tint_transform_once_per_sample_value`; (35) `mesh_extent_tests::{a_mesh_paints_its_triangles_alone, a_mesh_keeps_the_graphics_state_alpha, a_mesh_off_the_canvas_paints_nothing}` (`cargo test -p hayro`); (36) `raster::tests::mesh_triangles_sharing_an_edge_leave_no_seam`; (38) `raster::tests::default_colour_spaces::device_rgb_operators_draw_in_default_rgb`, `raster::tests::default_colour_spaces::device_cmyk_operators_draw_in_default_cmyk`, `raster::tests::default_colour_spaces::device_gray_operators_draw_in_default_gray`, `raster::tests::default_colour_spaces::device_images_draw_in_the_default_colour_spaces`, `raster::tests::default_colour_spaces::device_shadings_draw_in_the_default_colour_spaces`, `raster::tests::default_colour_spaces::an_image_drawn_with_and_without_a_default_keeps_both_colours`, `raster::tests::default_colour_spaces::forms_inherit_the_default_colour_spaces_they_do_not_override`, `raster::tests::default_colour_spaces::unusable_defaults_leave_device_colour_alone`; (39) `raster::tests::knockout_groups_replace_what_their_elements_cover`; (40) `raster::tests::visibility_expressions_decide_what_a_membership_dictionary_shows`; (41) `raster::tests::a_multiply_highlight_inside_a_transparency_group_keeps_the_text`; (42) `raster::tests::rendering_modes_but_3_and_7_draw_type3_glyphs_as_filled`; (43) `raster::tests::lab_honours_the_space_white_point`, `raster::tests::indexed_palettes_over_lab_keep_their_colours`; (44) `text::tests::identity_to_unicode_names_give_text`; (46) `raster::tests::stencil_masks_are_drawn_at_the_fill_opacity_once`; (47) `raster::tests::a_five_point_polyline_is_not_painted_as_its_bounding_box`, `raster::tests::a_path_that_visits_every_corner_out_of_order_is_not_a_rectangle`, `raster::tests::a_rectangle_is_still_painted_as_a_rectangle`; (48) `raster::tests::icc_profile_cache::icc_profiles_with_identical_dictionaries_draw_their_own_colours`, `raster::tests::icc_profile_cache::icc_profiles_used_again_are_read_once`; (49) `raster::tests::a_font_whose_post_version_has_swapped_halves_is_still_used`; (50) `font::blob::tests::glyph_names_resolve_to_the_first_glyph_with_that_name`; (51) `context::saved_state_tests::repeated_saves_stay_bounded_and_balanced`; (52) `font::cid::tests::w2_run_past_the_largest_cid_keeps_the_rest_of_the_table` (hayro-interpret); (55) `raster::tests::devicen_inks::a_tint_transform_that_cannot_be_evaluated_draws_the_rest_of_the_page_and_warns`, `raster::tests::devicen_inks::a_tint_transform_that_cannot_be_read_falls_back_and_warns`; (56) `raster::tests::invisible_unknown_annotations_and_popups_paint_nothing`; (57) `substitute_widths::a_substitute_keeps_its_glyph_shapes_at_wider_advances`, `substitute_widths::a_substitute_still_narrows_glyphs_to_narrower_advances` (pdfcraft-render `tests/it`); (58) `cid_fallback_query::a_cid_font_fallback_request_carries_its_descendants_style`, `cid_fallback_query::a_cid_font_without_a_descriptor_asks_for_the_default_style` (pdfcraft-render integration tests); (59) `raster::tests::no_rotate_notes_stay_upright_at_their_corner_on_rotated_pages` (hayro-interpret); (64) `type3_text_clip::{clip_only_type3_text_is_not_rendered_and_leaves_no_clip, invisible_type3_text_is_not_rendered, other_modes_render_type3_glyphs_filled_and_never_clip, only_outline_glyphs_shape_a_clip_shared_with_type3_text, self_nesting_type3_text_in_a_clip_mode_stays_bounded}` (`cargo test -p pdfcraft-render --test it`), `raster::tests::rendering_modes_but_3_and_7_draw_type3_glyphs_as_filled`, `text::tests::clipping_mode_type3_text_is_kept_by_the_ocr_filter`; (66) `separation_all::{separation_all_fills_paint_the_complemented_tint_as_gray, separation_all_strokes_paint_the_complemented_tint_as_gray, separation_all_images_paint_each_sample_as_the_complemented_gray, separation_all_shadings_paint_the_complemented_gray, separation_none_paints_nothing, a_named_separation_still_paints_through_its_alternate, a_device_n_space_naming_all_still_paints_through_its_alternate}` (`cargo test -p pdfcraft-render --test it`); (63) `color::device_cmyk_gray_tests::{each_ink_darkens_by_its_iso_weight, ink_past_full_coverage_is_black_and_bad_components_read_as_zero}` (hayro-interpret), `it::luminosity_group_space::{black_ink_in_a_device_cmyk_group_masks_fully_and_no_ink_shows_fully, each_process_ink_in_a_device_cmyk_group_masks_by_its_weight, a_device_cmyk_backdrop_colour_masks_by_its_gray, gray_and_rgb_groups_mask_as_before, device_cmyk_on_the_page_keeps_its_display_colour}` (pdfcraft-render); (71) `raster::tests::an_indexed_lookup_table_is_read_in_every_legal_form` (pdfcraft-render); (72) `raster::tests::an_uncoloured_pattern_uses_its_underlying_space_in_every_form` (pdfcraft-render); (74) `raster::tests::{a_chain_of_colour_spaces_ends, colour_spaces_are_read_to_the_limit_of_their_nesting, a_chain_built_on_spaces_already_read_ends, a_profile_read_at_the_limit_keeps_its_alternate_for_a_read_nearer_the_top}` (pdfcraft-render) | +| hayro-interpret | 0.7.0 | Apache-2.0 OR MIT | (1) select `/AP /N` appearance states via `/AS` (checkboxes, radios, stateful icons) and honour the NoView flag; (2) Type3 Unicode fallback to `/Encoding` glyph names, then printable ASCII; (3) `Type3Glyph::advance_width`; (4) `InterpreterSettings::ocg_overrides` for viewer layer toggles; (5) soft masks whose group lacks `/CS` were dropped (Chrome gradient text); (6) paint nesting cap `MAX_PAINT_NESTING` for tiling patterns and Type 3 glyphs (self-referencing content overflowed the stack); (7) CID width ranges in `/W` and `/W2` clamped to `MAX_CID` (a `0 4294967295 w` range hung); (8) `InterpreterSettings::hide_comments` skips markup annotations but keeps widgets and links (View ▸ Hide all comments); (9) `image_size_ok`: images and masks over 2^28 pixels are not decoded (a fuzzed `/W 4294967295` stencil mask allocated 4 GiB); (10) `MAX_NESTED_PAINTS`: nested paints (forms, Type 3 glyphs and tiling patterns inside one another) share a per-page budget of 50,000 (a glyph showing eight glyphs of its own font, sixteen deep, hung); (11) depends on skrifa 0.47 instead of 0.42 (upstream read-fonts fixed a Type 1 tokenizer that recursed through runs of numbers: a fuzzed font hung or overflowed the stack), with the one API change (`Charset::glyph_id` returns `Option`); (12) annotation appearances whose `/BBox` or `/Matrix` collapses to a line or a point are skipped (mapping them onto `/Rect` divided by zero and handed the device infinite or NaN matrices); (13) a Highlight annotation without a usable normal appearance is drawn from its `/QuadPoints`, `/C` and `/CA` with Multiply blending, as pdfcraft-annot draws highlights (it was not drawn at all); (14) simple-font `/Widths` (`read_widths`): entries only for codes 0–255 (one entry per code below `/FirstChar` was allocated: `4294967295` asked for 34 GB), an entry that isn't a number leaves its code missing instead of ending the array, and a `/LastChar` below `/FirstChar` gives no widths instead of discarding the font for a standard one; (15) the appearance box is mapped onto `/Rect` corner to corner: the translation now accounts for the scale (an appearance whose box didn't start at the origin and differed in size from `/Rect` was drawn shifted); (16) a clip set by `W`/`W*` takes effect after whichever path-painting operator ends the path (`S`, `f`, `B`, … as well as `n`; ISO 32000-2 §8.5.4): it was applied only on `n`, so `re W* S` clipped nothing and the clip stayed pending for a later, unrelated `n`; (17) `InterpreterSettings::cancelled`: once set, interpretation stops before the next content operator (a render pool sets it for every worker when dropped, after an edit or on closing, and for one worker when the watchdog gives up on its render, so renders whose answers nobody can receive stop instead of running to the end); (18) `MAX_PAGE_CONTENT`: the content a page holds at once (its contents, and the forms, tiling patterns and Type 3 glyph procedures being painted) stays within 512 MiB (`decode_content`; once it runs out, `InterpreterWarning::ContentTruncated` is reported (once per page by pdfcraft-render) so a truncated page is not a clean render; each level gives its bytes back when it finishes): forms nest fifty deep and each level kept its content while the next ran, so a form painting itself around a stream inflating to 256 MiB would have held over 12 GB; and Type 0 sampled functions take at most `MAX_SAMPLE_ENTRIES` (2^21) table points and `MAX_SAMPLE_VALUES` (2^23) samples, read no further than `/Size` asks (256 MiB of 1-bit samples asked for over 8 GB); (19) mesh shadings (types 4–7) are sampled only inside the area being drawn (`ShadingPattern::encode_within`, which the vendored hayro renderer calls with that area plus a pixel), within 8 visits per pixel of it plus 4 per triangle (`TriangleSampler`), and patches are triangulated one at a time: points far off the page were sampled over their whole bounding box, up to 65536 × 65536 entries (a fuzzed 147-byte patch stream; a synthetic page passed 6 GB in six seconds), ten thousand overlapping triangles ran for minutes, and every patch became 722 triangles before any limit; meshes hold at most `MAX_MESH_PATCHES` (2^16) patches and `MAX_MESH_TRIANGLES` (2^20) triangles, a lattice needs two to 2^19 vertices per row (`/VerticesPerRow 0` pushed empty rows for ever; one huge row read the whole stream), and a page samples at most `MAX_PAGE_MESH_TRIANGLES` (2^25) mesh triangles in all (a mesh painted a thousand times was triangulated a thousand times); each cut logs a warning; (20) PDF function construction is limited to 64 levels and 10,000 total nodes with cycle detection; calculator parsing and evaluation share procedure depth/work budgets, integer division/bitshift/rotation/index are panic-free, and fixed-size stack errors propagate; (21) a Type 0 font drawn with a substitute that isn't CID-keyed (it isn't embedded, or its program doesn't load) draws `.notdef` for a CID of an Adobe character collection (Japan1, GB1, CNS1, Korea1) that it can't find by Unicode: hayro took the CID for a glyph index of the substitute, which numbers its glyphs its own way, so the character was drawn as an unrelated one (𠮷 as "Q" in BIZ UDPGothic); (22) a Type 0 font drawn with a substitute finds a character given with a variation selector (`/ToUnicode`, or Adobe-Japan1-UCS2, which maps the JIS X 0208 forms of the kanji JIS X 0213:2004 redrew that way: CID 1247 is 噂 U+E0100) through the substitute's variation sequences, else as the character alone: such a CID found no glyph and was drawn as an unrelated one; (23) backport of hayro 0.8's `gradient` module: `EncodedShadingPattern::as_svg_gradient` turns an axial or radial shading into stops of an sRGB gradient (within 0.01 per channel, a stop at every stitching-function bound via `Function::stitching_bounds`) when a native gradient draws it exactly (extended past the box drawn in; a radial one with no background colour); (24) `DecodedImageCache`: decoded image pixels shared across renders through the interpreter cache within a 64 MiB budget (an image-heavy page decoded its thousands of images again per tile and per scale), keyed by every decode input (`DecodedImageKey`: the stream's place and dictionary bytes, its object, mask/stencil/raster output, interpolation, decode target size, preview or final); images under a transfer function and inline images are not cached, an image over the budget is never kept, and a poisoned lock decodes uncached; (25) `Device::actual_text` hands the device a marked content sequence's `/ActualText` (inline or named in `/Properties`), so text extraction keeps the Thai, Indic and Arabic clusters Chrome marks this way (their shaped tone marks and vowels have no Unicode of their own); (26) non-embedded simple fonts drawn with a standard-font stand-in build the Latin Extended-A letters the stand-in lacks (`/Gbreve`, `/Idotaccent`, `/Scedilla`, `/aogonek`, `/ccaron`…) from the base letter and accent it has (`StandardKind::composite_glyph`, `ACCENTED_LETTERS`): PDFium's Foxit stand-ins hold only the Standard/WinAnsi/Mac Roman glyphs, so iText letters with Times New Roman unembedded showed blanks for Ğ, İ, Ş, ğ and ş; the comma-below letters (`/scommaaccent`, `/Tcommaaccent`, `/kcommaaccent`…, found by character, so `/uni0136` and the glyph list's `/Kcedilla` too) are the letter and the font's comma, smaller and under the baseline, since the stand-ins have no `commaaccent` (Romanian ș drew nothing and ț a cedilla in forms laid out from XFA; ģ, whose comma is turned and above, is not built); (27) an embedded TrueType font without a base encoding reads its codes as WinAnsi for text extraction (`EmbeddedKind::code_to_unicode_name`), matching pdftotext's output, instead of Standard: OCR text layers of scans write WinAnsi codes with no `/Encoding`, and Standard has no ü, ö or ß and reads é as Ø (glyph selection unchanged); (28) an image whose pixels hold at most 16 bits of samples (an 8-bit Separation or DeviceN image, a 1-, 2- or 4-bit gray or indexed one) is converted once per possible pixel value through a lookup table instead of once per pixel (`rgb_via_lookup`): a spot-colour tint transform is often a PostScript calculator program, run for every pixel, so a fillable character sheet's 3304 × 4105 DeviceN background took four seconds and 430 MB to draw a page; each entry is converted on its own (`convert_each`), so a tint transform giving the wrong number of components for a value the image never uses cannot shift the colours of the values it does; (29) `Device::begin_annotations`/`end_annotations` bracket the page's annotations, so a device can tell comment paints from document paints (reading colours recolour the document, never a comment, #1548); (30) the Annex D.2 alias codes read as the ink they draw: WinAnsiEncoding 0xA0 and 0xAD, and MacRomanEncoding 0xCA, carry the glyph names `space` and `hyphen` -- the names those tables also give 0x20 and 0x2D -- not `nbspace` and `sfthyphen`, whose glyph list values U+00A0 and U+00AD are invisible formatting characters. Extraction hid drawn ink behind them, so search and redaction matched neither (`XiaoBiaoSong.pdf` in the pdf.js corpus drew 104 soft hyphens; across the 989 files the soft hyphens we extract fall from 117 to 13 and the non-breaking spaces from 30 to 26, what remains coming from `/ToUnicode` maps, which say so explicitly). The base table only, in the text direction only: a `/Differences` name keeps its glyph list value and glyph lookup is untouched, both as pdftotext does; (31) a Type 0 sampled function keeps its samples in one flat array indexed by strides (`Type0::entry`) instead of a hash map keyed by each grid point: the map was built again, one hashed insert per sample, every time a shading using the function was painted (a 2,097,152-sample ramp painted 30 times took 38 s; `bug1721218` in the pdf.js corpus spent most of a 1.5 s page on it); the interpolation is unchanged, so results are bit for bit the same, a sample missing from a short stream still gives no value, and the maximum sample value is computed without overflowing at 32 bits per sample; (32) the decoded-image cache (24) keys a decode by the size the image is drawn at only when a JPX stream decodes it or its soft mask or mask (`decode_reads_target`): JPX is the only filter that decodes a reduced resolution for a size, so a JPEG or Flate scan was decoded again at every zoom step and kept once per zoom level; one decode now serves every size; `InterpreterCache::decoded_image_decodes` counts the cache's decodes; (33) Coons and tensor-product patches copy their vertices' colours less: each point of a patch's 20 × 20 triangle grid is interpolated once (`generate_patch_triangles`; each cell interpolated its four corners itself, 1,444 interpolations a patch for 400 points), a cell's second triangle takes the vertices its first copied, and the mesh sampler moves a patch's triangles into device space instead of copying each vertex (`TriangleSampler::sample_owned`); the same values, 10–16% faster on mesh-gradient pages; (34) `color::tint_transform_runs`: how many colours the calling thread has run through a Separation or DeviceN tint transform (counted once per batch in `convert_f32`), so a test counts patch (28)'s once-per-sample-value runs instead of timing them (its 10 s deadline failed on a busy FreeBSD VM in CI); (35) `EncodedShadingPattern::extent`: where a mesh shading (types 4–7) can paint at all, the pixels its triangles touched when it was encoded (`None` for the types that paint everywhere, and when the shading has a `/Background`), so the renderer samples a texture there alone and skips a mesh with nothing on the canvas; (36) a mesh shading's pixel whose corner no triangle holds strictly (on an edge two triangles share, or on the mesh's side) takes the triangle that covers its centre, edges included (`Triangle::covers`): testing only the corner left a white seam along every shared edge, and the colour is still taken at the corner; (38) the `/DefaultGray`, `/DefaultRGB` and `/DefaultCMYK` colour spaces of a resource dictionary (ISO 32000-2 §8.6.5.6) replace the device space content selects: with `g`/`G`, `rg`/`RG`, `k`/`K` and `cs`/`CS` (by name, or through a `/ColorSpace` resource that is a device space), and as the `/ColorSpace` of an image XObject, an inline image or a shading painted by `sh` or as a shading pattern (`DefaultColorSpaces`, looked up once per content window in the resources and those they inherit, so a form XObject without a default of its own draws in its page's, as Poppler and MuPDF draw it); a default that is a Lab, Indexed, Pattern or device space, has another number of components or is no colour space is ignored and device colour is drawn as before; device spaces inside other spaces (an Indexed base, a Separation or DeviceN alternate, a Pattern's underlying space), shading dictionaries, masks and transparency group spaces are unchanged, and the decoded-image cache (24) keys a decode by the default it was drawn in. hayro drew device colour as it was, so pages that calibrate it this way (common in PDF/A) came out in the wrong colours; (39) knockout groups (#2971): `Device::set_knockout` right after a `/K true` group is pushed; `Device::knockout_image` for an unmasked image before its group is pushed, when `Device::in_knockout_group`: the device clears its placement rectangle only if it will draw the image (on the canvas, not a preview's tiny image, and it decodes), decoded at its draw size so the draw reuses that decode; and, when `Device::knockout_erase_wanted`, a nested group's content drawn once between `begin_knockout_erase` and `end_knockout_erase` before the group itself, which then always gets a layer of its own; (40) an optional content membership dictionary's visibility expression (`/VE`: `/And`, `/Or`, `/Not`, nested up to 32 deep) decides its visibility ahead of `/OCGs` and `/P` (ISO 32000-2 §8.11.2.2); it was ignored, so content under it stayed visible with its layers hidden; a malformed expression, including one naming an object the document doesn't list in `/OCProperties /OCGs`, falls back to `/OCGs` and `/P` (#2986); (41) a transparency group that is neither isolated nor knockout, entered at full opacity with no soft mask and Normal blending, is drawn straight onto the page instead of into a layer of its own (§11.4.7: its elements composite with the backdrop; the layer made a `/BM /Multiply` highlight appearance an opaque block, #1968); (42) text in a Type 3 font is drawn filled whatever the text rendering mode, except mode 3 (invisible): only that mode has any effect on Type 3 fonts (ISO 32000-1 §9.3.6). Stroking ran the glyph procedure a second time, so `2 Tr` made bitmap fonts look bold, `1 Tr` painted an uncoloured glyph in the stroking colour, and `7 Tr` hid it (`7 Tr` since follows 64); (43) Lab colour spaces honour their own `/WhitePoint`: L\*a\*b\* goes to XYZ relative to that white, is Bradford-adapted to D65 and converted to sRGB (ISO 32000-2 §8.6.5.4) instead of through `LAB.icc` as if every white were D50 (a D65 blue came out 45 levels too red; the profile is removed); components normalised to [0, 1] (`manual_scale`, an `/Indexed` palette over Lab) map onto L\* 0..100 and the a\*/b\* `/Range`; (44) a Type 0 font whose `/ToUnicode` is the name `/Identity-H` or `/Identity-V` (not a CMap stream; WSCAD writes it) reads each code as its Unicode value, as Acrobat shows it (`Type0Font::identity_to_unicode`); the identity CMap the name resolved to maps codes to CIDs only, so such pages had no text to select or find; (46) an image XObject's group applies the fill opacity, so the fill alpha is reset to 1 before a stencil mask takes the fill colour as its paint, and a pattern paint drops the opacity it captured at `scn` (`Pattern::without_opacity`) (it was applied twice: a mask at `ca 0.5` was drawn at a quarter, #2975); (47) `path_as_rect`: a five-element path is a rectangle only when its four points are distinct, each step from one to the next runs along a single axis, and the last returns to the first. The length test admits one MoveTo and four LineTo as well as one MoveTo, three LineTo and a ClosePath, and asking only that every corner of the bounding box was visited says nothing about the order or the steps between, so a five-point polyline whose ends reached the corners was painted as that box -- a fourth side the path does not have -- and a clip of that shape was discarded; the coordinates are compared exactly, since the matrix is applied after this check and a `cm` of 10,000 turns `is_nearly_equal`'s 256th of a unit into tens of device units (#3327); (48) an `/ICCBased` colour space is cached by what its profile is read from (`IccProfileKey`): the stream object it names, looked up without reading the stream, and then the stream's dictionary and its own bytes (decrypted, not decoded), so a byte-for-byte copy of a profile in another object is read once, and a profile stream written directly in its array, which reports the object holding the array as every other stream written there does, is told apart by its bytes. hayro keyed it by the stream dictionary's bytes alone, so two different profiles with the same `/N` and `/Length` shared whichever was read first, and colours in the second were drawn through the first. `InterpreterCache::icc_profile_reads` counts the profiles read; (49) `OpenTypeFontBlob::new` also accepts a `post` table version 1.0, 2.0 or 3.0 written with its 16-bit halves swapped (`00 00 00 03`), as ScanSoft PDF Create! embeds every font; such fonts were refused and their text drawn with a substitute (Hebrew came out garbled or missing, #2946); `glyph_names` reads such a table from a copy with the version written correctly, so a 2.0 table's names serve `/Differences`. Any other unknown version is still refused (pdf.js 9462); (50) `CffFontBlob::glyph_index_by_name` looks a glyph name up in a name to glyph map built on first use (shared between clones) instead of searching the whole charset, with a string lookup per glyph, for every character code of a font; the first glyph with a name still wins; (51) at most 4096 graphics states saved at once, holding at most 64 MiB together (each `q` copies the whole state, dash array and clip list included, so short operators multiplied one large state); a `q` past either limit is counted but not copied, and its `Q` still removes the clips added since (from storytold/craft-libs#239); (52) a `/W2` run whose first CID is past `MAX_CID` stops there, as in `/W` (7), checked before the run's metrics are read: a first CID of 4294967295 inserted one entry and then overflowed, discarding the whole `/W2` table (from storytold/craft-libs#254); (55) a Separation or DeviceN tint transform that cannot be read keeps its colour space, and one that cannot be read or evaluated paints the alternate space's initial colour, as evaluation failures already did; that fallback, and a `cs`/`CS` colour space that cannot be read (drawn in DeviceGray as before), are now reported once per content stream as `InterpreterWarning::ColorFallback` (`RenderWarning::ColourFallback` in `pdfcraft-render`) instead of silently (#4260); (56) an annotation whose Invisible flag (bit 1) is set and whose `/Subtype` is none of the standard types of ISO 32000-2 Table 171 (`is_standard_annotation_type`; no `/Subtype` counts as unknown) is not drawn (Table 167), and a `/Popup` annotation's appearance is never painted on the page (§12.5.6.14: a popup has no appearance stream of its own; the viewer shows it as a window for its parent annotation). Both were drawn from their `/AP`; (57) a simple font drawn with a standard-font stand-in because the document names a font it doesn't embed (`StandardKind` with `fallback`) narrows a glyph to a narrower `/Widths` advance but no longer widens it to a wider one: the advance already places the next glyph (ISO 32000-2 §9.2.4; /Widths in Table 109), and widening drew a non-embedded `Arial,Bold` with 600-unit widths as a heavy fixed-pitch face whose `i` and `l` were solid blocks twice their width; an exact standard-14 font still matches its standard metrics both ways; (58) the fallback request for a Type 0 font that is not embedded (`FallbackFontQuery::with_descriptor`) takes its serif, italic and small-cap flags, `/FontWeight`, `/FontFamily` and `/FontStretch` from the descendant CIDFont's font descriptor (ISO 32000-2 §9.7.4.1, §9.7.6.1; §9.8): it read them from the Type 0 dictionary, which has none, so every such request asked for a regular sans-serif face and no resolver could tell a Song or Mincho font from a Hei or Gothic one, or see `/FontWeight 700`; (59) the NoRotate flag (`/F` bit 5) is honoured: the appearance, fitted to `/Rect`, is turned against the page's `/Rotate` about the rectangle's upper-left corner, which stays where it is, so it reads upright as the page is displayed (ISO 32000-2 §12.5.3). Sticky notes, which are saved NoRotate, were drawn turned with the page (#2583). Form fields and links stay in `/Rect`, where PdfCraft takes their click targets from it; (64) text in a Type 3 font follows ISO 32000-2 §9.3.6 in the clipping modes: under `7 Tr` it is not rendered (reported to the device as clipping text, `GlyphDrawMode::Clip`, so extraction keeps it), and in modes 4 to 7 a Type 3 glyph adds nothing to the clipping path (`clip_glyph`), so text shown only in a Type 3 font leaves no clip at `ET`. Since (42) `7 Tr` painted the glyphs in the fill colour (black by default), so a fill meant to follow showed them wherever it didn't cover them; 4 to 6 still render filled; (66) a Separation colour space whose colourant is the special name `All` paints every colourant at once (ISO 32000-2 §8.6.6.4): on screen and in an RGB print raster its tint t is the gray 1 − t, complemented because the device is additive, whatever its alternate space and tint transform say (hayro drew it through the tint transform, so a `/DeviceCMYK` transform giving cyan drew registration marks light cyan); `/None` still paints nothing, any other name still goes through its alternate, and a DeviceN space naming `All` keeps its alternate, since the clause gives the name that meaning in a Separation space; (63) a luminosity soft mask whose group colour space is `/DeviceCMYK` (by name, not an ICC-based or calibrated space) reads a `/DeviceCMYK` fill or stroke colour drawn in it, and its `/BC`, as their gray `1 - min(1, 0.3 c + 0.59 m + 0.11 y + k)` (ISO 32000-2 §10.4.2.3, §11.5.3: device colour converts to gray with no colour calibration; `Context::luminosity_in_device_cmyk`, `color::device_cmyk_to_gray`): it went through the CMYK display profile, where 100% K is a dark grey, so a 100% K mask let about an eighth of the masked paint through. CMYK images, shadings and tiling patterns inside such a mask, and CMYK on the page, still use the profile; (71) a lookup table in an indirect string reads: it was read as a stream first, which uses up a reference (ISO 32000-2 §8.6.6.3); (72) an uncoloured pattern's underlying space given as a name or a reference is used: it was skipped, so a CMYK cyan drew red (ISO 32000-2 §8.7.3.3); (73) `InterpreterSettings::jbig2_work`, set for each page in `interpret_page` and ended with it, and a JBIG2 image or an image with a JBIG2 mask past it left out with `ContentTruncated`; (74) colour spaces nest at most 32 levels, through every way one names another, so a chain of them ends instead of overflowing the stack; an ICC profile's `/Alternate` is read where it's met and isn't kept with the profile, or a page could build a chain past the limit on spaces already read; (75) a soft hyphen (U+00AD) that a CFF substitute for a CID font has no glyph for draws its hyphen, as Annex D.2 reads WinAnsi 0xAD in (30), instead of the CID taken as a glyph index (#5888) | (1) `raster::tests::widget_appearance_states`; (2, 3) `xtask text-oracle` on corpus/pdfjs issue918; (4) `raster::tests::layer_override_hides_content`; (5) `raster::tests::soft_mask_without_group_colour_space_is_applied`; (6) `raster::tests::self_referencing_tiling_pattern_terminates`, `raster::tests::self_referencing_type3_glyph_terminates`; (7) `raster::tests::huge_cid_width_ranges_terminate`; (8) `raster::tests::hiding_comments_keeps_fields`; (9) `raster::tests::absurd_mask_and_fax_sizes_are_refused_before_decoding`; (10) `raster::tests::type3_glyphs_that_fan_out_into_themselves_finish`; (11) `raster::tests::type1_font_programs_with_long_runs_of_numbers_load_quickly`; (12) `raster::tests::degenerate_annotation_appearances_are_skipped`; (13) `raster::tests::highlights_without_an_appearance_are_drawn`; (14) `raster::tests::malformed_simple_font_widths_keep_later_widths_and_the_font`, `raster::tests::huge_simple_font_first_char_terminates`; (15) `raster::tests::annotation_appearance_box_maps_onto_rect`; (16) `raster::tests::clipping_path_applies_after_any_painting_operator`; (17) `raster::tests::dropping_the_pool_cancels_its_renders`, `raster::tests::the_watchdog_stops_the_render_it_gives_up_on`; (18) `raster::tests::page_contents_and_nested_forms_share_one_budget`, `raster::tests::content_painted_again_and_again_keeps_drawing`, `raster::tests::sampled_functions_with_billions_of_samples_are_refused`; (19) `raster::tests::mesh_shadings_far_off_the_page_render`, `raster::tests::many_overlapping_mesh_triangles_finish`, `raster::tests::mesh_shadings_with_many_patches_or_no_rows_finish`; (20) `raster::tests::function_limits_calculator_arithmetic_and_depth`, `raster::tests::function_limits_public_construction_work_and_depth`, `raster::tests::function_limits_stitching_cycles_are_refused_and_shared_children_work`, `raster::tests::function_limits_invalid_calculator_keeps_the_page_renderable`; (21) `raster::tests::cids_a_substitute_lacks_are_not_drawn_as_other_glyphs`; (22) `raster::tests::variation_sequences_draw_their_kanji_in_a_substitute`; (23) `raster::tests::axial_and_radial_shadings_draw_as_native_gradients`; (24) `raster::tests::tiles_match_full_render`, `raster::tests::skipping_paths_off_the_canvas_changes_no_pixel` (both decode through the cache), `raster::tests::decoded_images_with_identical_dictionaries_keep_their_own_pixels`, `raster::tests::decoded_images_under_a_transfer_function_are_not_shared`; (25) `text::tests::actual_text_replaces_the_glyphs_it_marks_in_every_writing_direction`, `text::tests::actual_text_follows_the_pdf_rules_for_marked_content`; (26) `raster::tests::accented_letters_the_standard_stand_ins_lack_are_built_from_their_parts`, `raster::tests::comma_below_letters_in_standard_fonts_draw_a_comma_under_the_letter`; (27) `text::tests::truetype_without_an_encoding_reads_its_codes_as_win_ansi`; (28) `raster::tests::spot_colour_images_run_their_tint_transform_once_per_sample_value`, `raster::tests::images_converted_through_a_table_keep_every_samples_colour`, `raster::tests::a_malformed_tint_for_an_unused_sample_keeps_the_used_colours`; (29) `raster::tests::reading_colors_keep_highlight_annotations_readable`; (30) `text::tests::the_annex_d2_alias_codes_read_as_an_ordinary_hyphen_and_space`; (31) `raster::tests::shadings_with_large_sampled_functions_paint_quickly`, `raster::tests::sampled_functions_interpolate_their_grid_as_before`; (32) `raster::tests::decoded_images_serve_every_size_they_are_drawn_at`; (33) `raster::tests::patch_meshes_keep_their_corner_colours`; (34) `raster::tests::spot_colour_images_run_their_tint_transform_once_per_sample_value`; (35) `mesh_extent_tests::{a_mesh_paints_its_triangles_alone, a_mesh_keeps_the_graphics_state_alpha, a_mesh_off_the_canvas_paints_nothing}` (`cargo test -p hayro`); (36) `raster::tests::mesh_triangles_sharing_an_edge_leave_no_seam`; (38) `raster::tests::default_colour_spaces::device_rgb_operators_draw_in_default_rgb`, `raster::tests::default_colour_spaces::device_cmyk_operators_draw_in_default_cmyk`, `raster::tests::default_colour_spaces::device_gray_operators_draw_in_default_gray`, `raster::tests::default_colour_spaces::device_images_draw_in_the_default_colour_spaces`, `raster::tests::default_colour_spaces::device_shadings_draw_in_the_default_colour_spaces`, `raster::tests::default_colour_spaces::an_image_drawn_with_and_without_a_default_keeps_both_colours`, `raster::tests::default_colour_spaces::forms_inherit_the_default_colour_spaces_they_do_not_override`, `raster::tests::default_colour_spaces::unusable_defaults_leave_device_colour_alone`; (39) `raster::tests::knockout_groups_replace_what_their_elements_cover`; (40) `raster::tests::visibility_expressions_decide_what_a_membership_dictionary_shows`; (41) `raster::tests::a_multiply_highlight_inside_a_transparency_group_keeps_the_text`; (42) `raster::tests::rendering_modes_but_3_and_7_draw_type3_glyphs_as_filled`; (43) `raster::tests::lab_honours_the_space_white_point`, `raster::tests::indexed_palettes_over_lab_keep_their_colours`; (44) `text::tests::identity_to_unicode_names_give_text`; (46) `raster::tests::stencil_masks_are_drawn_at_the_fill_opacity_once`; (47) `raster::tests::a_five_point_polyline_is_not_painted_as_its_bounding_box`, `raster::tests::a_path_that_visits_every_corner_out_of_order_is_not_a_rectangle`, `raster::tests::a_rectangle_is_still_painted_as_a_rectangle`; (48) `raster::tests::icc_profile_cache::icc_profiles_with_identical_dictionaries_draw_their_own_colours`, `raster::tests::icc_profile_cache::icc_profiles_used_again_are_read_once`; (49) `raster::tests::a_font_whose_post_version_has_swapped_halves_is_still_used`; (50) `font::blob::tests::glyph_names_resolve_to_the_first_glyph_with_that_name`; (51) `context::saved_state_tests::repeated_saves_stay_bounded_and_balanced`; (52) `font::cid::tests::w2_run_past_the_largest_cid_keeps_the_rest_of_the_table` (hayro-interpret); (55) `raster::tests::devicen_inks::a_tint_transform_that_cannot_be_evaluated_draws_the_rest_of_the_page_and_warns`, `raster::tests::devicen_inks::a_tint_transform_that_cannot_be_read_falls_back_and_warns`; (56) `raster::tests::invisible_unknown_annotations_and_popups_paint_nothing`; (57) `substitute_widths::a_substitute_keeps_its_glyph_shapes_at_wider_advances`, `substitute_widths::a_substitute_still_narrows_glyphs_to_narrower_advances` (pdfcraft-render `tests/it`); (58) `cid_fallback_query::a_cid_font_fallback_request_carries_its_descendants_style`, `cid_fallback_query::a_cid_font_without_a_descriptor_asks_for_the_default_style` (pdfcraft-render integration tests); (59) `raster::tests::no_rotate_notes_stay_upright_at_their_corner_on_rotated_pages` (hayro-interpret); (64) `type3_text_clip::{clip_only_type3_text_is_not_rendered_and_leaves_no_clip, invisible_type3_text_is_not_rendered, other_modes_render_type3_glyphs_filled_and_never_clip, only_outline_glyphs_shape_a_clip_shared_with_type3_text, self_nesting_type3_text_in_a_clip_mode_stays_bounded}` (`cargo test -p pdfcraft-render --test it`), `raster::tests::rendering_modes_but_3_and_7_draw_type3_glyphs_as_filled`, `text::tests::clipping_mode_type3_text_is_kept_by_the_ocr_filter`; (66) `separation_all::{separation_all_fills_paint_the_complemented_tint_as_gray, separation_all_strokes_paint_the_complemented_tint_as_gray, separation_all_images_paint_each_sample_as_the_complemented_gray, separation_all_shadings_paint_the_complemented_gray, separation_none_paints_nothing, a_named_separation_still_paints_through_its_alternate, a_device_n_space_naming_all_still_paints_through_its_alternate}` (`cargo test -p pdfcraft-render --test it`); (63) `color::device_cmyk_gray_tests::{each_ink_darkens_by_its_iso_weight, ink_past_full_coverage_is_black_and_bad_components_read_as_zero}` (hayro-interpret), `it::luminosity_group_space::{black_ink_in_a_device_cmyk_group_masks_fully_and_no_ink_shows_fully, each_process_ink_in_a_device_cmyk_group_masks_by_its_weight, a_device_cmyk_backdrop_colour_masks_by_its_gray, gray_and_rgb_groups_mask_as_before, device_cmyk_on_the_page_keeps_its_display_colour}` (pdfcraft-render); (71) `raster::tests::an_indexed_lookup_table_is_read_in_every_legal_form` (pdfcraft-render); (72) `raster::tests::an_uncoloured_pattern_uses_its_underlying_space_in_every_form` (pdfcraft-render); (73) `raster::tests::the_jbig2_images_of_a_page_share_one_allowance`, `a_picture_whose_jbig2_mask_is_past_the_pages_allowance_is_not_drawn` and `a_pages_jbig2_allowance_ends_with_the_page` (pdfcraft-render); (74) `raster::tests::{a_chain_of_colour_spaces_ends, colour_spaces_are_read_to_the_limit_of_their_nesting, a_chain_built_on_spaces_already_read_ends, a_profile_read_at_the_limit_keeps_its_alternate_for_a_read_nearer_the_top}` (pdfcraft-render); (75) `raster::tests::a_soft_hyphen_a_substitute_lacks_draws_its_hyphen` (pdfcraft-render) | | hayro | 0.7.1 | Apache-2.0 OR MIT | (1) `RenderSettings::{x_offset, y_offset}` to render one tile of a large page; (2) images over `MAX_IMAGE_PIXELS` (2^28) are skipped (a fuzzed `/W 4294967295` hung in resampling); (3) `tiling_cell_scale` keeps a tiling pattern's cell pixmap within 3000 px a side whatever its `/XStep`/`/YStep` (a fuzzed step far beyond `/BBox` allocated 2 GB); (4) stroke widths clamped to 4 × (canvas width + height) device pixels (a fuzzed `/LW 9223372036854775807` allocated 10 GB in stroke expansion); (5) `usable_dash_pattern`: a stroke whose dash pattern could cut it into more than `MAX_DASHES_PER_STROKE` (250,000) pieces, counting kurbo's restart of the pattern at every subpath and `ClosePath`, is drawn solid (a fuzzed `/D [[11] 0]` on a line from x = 92234775807 allocated over 5 GB, `[0.000001] 0 d` on a 20 pt line over 10 GB); (6) a dash pattern with a negative or non-finite entry, or a period that isn't positive, is drawn solid (`[-1 -1] 0 d` looped for ever in kurbo); (7) `render_size` and `render_into`: render into a buffer the caller allocates (PdfCraft renders into pixel-aligned memory that the GUI takes over as texture data); `render` is `render_into` on a new pixmap; (8) checked image source/target/RGBA, alpha-premultiplication scratch and intermediate sizes before resampling, finite transforms and exact source/mask buffers; sources wider than u16 may shrink before backend limits, with a 2^20 source-axis cap and conservative 128 MiB filter-planning estimate; an over-limit or failed resize keeps the original image resolution and geometry when the source fits the backend, otherwise skips it, with a logged warning; staging, resampling output/scratch, RGBA conversion and padding buffers use fallible reserves; (9) `may_paint_canvas`: a fill or stroke whose control-point box, grown by how far its paint reaches past the path (half the stroke width times the larger of the miter limit and √2) plus 0.5 user units and 2 pixels, misses the canvas is not drawn, so a tile no longer strokes and fills every path of its page (item 5 of #623); `set_skip_offscreen_paths` turns this off for the regression test; (10) `/Interpolate` governs the pre-resize too (#624): a minified image that does not request interpolation is pre-resized with nearest-neighbour, planned without the Catmull-Rom filter limits (`image_resampling_size` takes the flag); a Type 3 glyph image is sampled bicubically only when interpolated; a minified image with a matching soft mask is nearest-sampled straight into premultiplied RGBA; (11) `may_paint_rect`: an image whose stream-size box, mapped to the device, misses the canvas is skipped before decoding (decoded data can only shrink against that box), so a tile of an image-heavy page no longer decodes, resamples and rasterizes every image on it; (12) preview renders (`InterpreterSettings::preview`: backdrops, thumbnails, grid cells, signature-drag backgrounds) skip images under `PREVIEW_MIN_IMAGE_AREA` device pixels, while final renders always draw them; (13) reading colours (#897): `RenderSettings::color_replacement` takes a `ColorReplacement` (text colour, background, `only_black`, `line_art`) that remaps solid text and line-art paint while rendering, glyph outlines counting as text and stencil-mask ink as line art; images, image alpha masks, soft masks and pattern cells keep their colours; `render_pdf` gains a `color_replacement: Option` argument (pass `None` for true colours); the upstream-only `[dev-dependencies.log]` entry is removed from `Cargo.toml` (log is a normal dependency since the logging patch), so `cargo test -p hayro` runs this crate's unit tests; (14) a shrunk, interpolated image whose axes lie along the device's (upright, mirrored or a quarter turn, as on a page under `/Rotate`) is snapped to whole device pixels: shrunk once to its rounded device rectangle and drawn 1:1 from the rounded corner, instead of a ceil-sized raster resampled again at a fractional scale and offset (`snap_minified_image`; scans looked soft next to Acrobat, and until #5530 a turned one still did, up to 200 grey levels off the same page drawn upright). An image counts as axis-aligned when the terms the snap drops move its far edges by at most a hundredth of a device pixel (`SNAP_SKEW`), not by a tolerance on the coefficients, which let a slight skew of a very wide image through; and the snapped 1:1 transform is used only when the shrink produced the snapped size, so a failed resize keeps the full transform instead of drawing the source raster at its source size; (15) a soft mask of another size than its image is filtered when shrunk, whatever its `/Interpolate` (#1649): such a mask carries the shape on its own (Word saves text as a tiny black image with a glyph-bitmap mask), and nearest-neighbour dropped every stroke thinner than the shrink factor; (16) under a soft mask or a blend mode, axial and radial shadings are sampled instead of drawn as native gradients (#2128): vello_cpu 0.0.8 copies an opaque gradient over fully covered tiles without the mask or blend mode, so PowerPoint's faded gradient fills came out solid; (17) the renderer keeps annotation paints out of the reading-colours mapping between `begin_annotations` and `end_annotations` (#1548); (18) the page renders as one transparency group; under reading colours its background is painted inside it as the initial backdrop, so a Multiply highlight blends with the dark background instead of staying an opaque block, and otherwise the background stays outside, so a blend mode over an empty part of the page keeps its colour instead of blending with the white paper (#2970); (19) `set_paint` samples a mesh shading's texture over its triangles alone (`EncodedShadingPattern::extent`, padded rather than repeated) and skips a mesh with none on the canvas: a BricsCAD plan's 310 one-triangle `sh` each covered the whole tile, 2 s per 1024 px tile at any zoom (the watchdog gave the page up on a busy machine), now about 70 ms; (20) a tiling pattern whose step is too large for a cell pixmap, where what is painted (a fill, or a stroke with its width) can only show the first cell (PowerPoint's `/XStep 2147480100` for a picture fill drawn once), has its `/BBox` drawn at full scale with a transparent border and padded instead of tiled (`shows_one_cell`; a cell whose scale isn't finite and positive, from a `/BBox` too thin to divide by, keeps the old path: `usable_cell_scale`); shrinking the cell to fit the 3000 px limit of (3) left the picture under a pixel, so network diagrams lost their pictures (#3349); (22) knockout groups: while one is innermost, fills, strokes, glyph outlines and shadings are drawn with `Compose::Copy` (weighted by coverage), so each element replaces what earlier elements of the group drew instead of compositing over it; an image or nested group, drawn into a layer of its own, first has what is under its shape cleared (`knockout_image` for an unmasked image's rectangle, only when `draw_image` will draw it, decoded at the size it is drawn; a knockout erase pass that draws a nested group's content with every paint clearing instead of painting, a shading fill's clear clipped to the shading's `/BBox` as its paint is) and then composites over it (#2971); (23) backport of hayro 0.8: shadings that `as_svg_gradient` can represent are painted as a `vello_cpu` linear or two-point radial gradient instead of a texture sampled pixel by pixel through the shading function (InDesign fades are luminosity soft masks of one full-page axial `sh`: 40 on a report page took 15 s at 144 dpi, now under 1 s); without upstream's half-pixel shift, which suits vello_cpu 0.3 but moves 0.0.8's gradients off pixel centres; (25) a tiling cell is drawn at the scale that makes one `/XStep` (`/YStep`) exactly the cell pixmap's whole number of pixels (`tiling_cell_pixels`, at least 1 and at most the cap), so the repeated pixmap puts cells at whole multiples of the step at any device scale; drawing at the unrounded scale repeated the cell up to half a pixel off at every step, and the error grew with distance from the pattern's origin (ISO 32000-2 8.7.3.1) | (1) `raster::tests::tiles_match_full_render`; (2) `raster::tests::absurd_image_dimensions_are_skipped`; (3) `raster::tests::tiling_cells_stay_small_whatever_the_step`; (4) `raster::tests::absurd_predictor_columns_and_line_widths_render`; (5) `raster::tests::dash_patterns_that_cut_a_stroke_into_billions_of_pieces_render`; (6) `raster::tests::invalid_dash_patterns_terminate_and_are_drawn_solid`; (7) `raster::tests::pixels_are_a_plain_renders_bytes_in_a_buffer_a_gui_can_take_over`; (8) `raster::tests::image_resampling_rejects_anisotropic_target_growth`, `raster::tests::image_resampling_bounds_intermediate_before_planning`, `raster::tests::image_resampling_rejects_invalid_sources_and_scales`, `raster::tests::image_resampling_keeps_valid_sizes_and_exact_limits`, `raster::tests::resampling_fallback_preserves_original_geometry_and_pixels`, `raster::tests::image_resampling_wide_sources_shrink_before_backend_side_limits`, `raster::tests::image_resampling_wide_transparent_sources_still_shrink`, `raster::tests::image_resampling_padded_backend_dimensions_stay_checked`, `raster::tests::image_resampling_mismatched_alpha_mask_keeps_pixels_and_placement`; (9) `raster::tests::skipping_paths_off_the_canvas_changes_no_pixel`; (10) `raster::tests::non_interpolated_images_are_not_smoothed_when_minified`, `raster::tests::non_interpolated_gray_images_are_not_smoothed_when_minified`, `raster::tests::non_integer_minification_samples_the_same_columns`, `raster::tests::non_integer_minification_samples_colour_and_mask_from_the_same_columns`, `raster::tests::non_interpolated_alpha_images_keep_their_colours_and_mask_when_minified`, `raster::tests::non_interpolated_type3_glyph_images_are_not_smoothed_when_minified`, `raster::tests::image_resampling_nearest_accepts_wide_sources_the_filter_refuses`, `raster::tests::wide_non_interpolated_sources_draw_after_shrinking`; (11) `raster::tests::skipping_paths_off_the_canvas_changes_no_pixel`; (12) `raster::tests::preview_renders_skip_tiny_images_but_finals_draw_everything`; (13) `color_replacement_tests::{black_maps_to_text_colour, white_maps_to_background, midgrey_interpolates, alpha_copied_verbatim, only_black_threshold, line_art_false_skips_paths_but_not_text}`, `color_replacement_render_tests::{color_replacement_maps_text_and_line_art, color_replacement_maps_stencil_mask_ink}`; (14) `raster::tests::interpolated_minified_image_edges_snap_to_whole_pixels` (`cargo test -p hayro`), `raster::tests::a_turned_or_mirrored_minified_image_snaps_to_whole_pixels`, `rotated_image_snap::a_shrunk_image_on_a_turned_page_is_the_upright_render_turned` (`cargo test -p pdfcraft-render --test it`), `renderer::snap_tests::a_skew_that_moves_a_far_edge_is_not_snapped` (`cargo test -p hayro`); (15) `raster::tests::shrunk_soft_mask_larger_than_its_image_keeps_thin_strokes`; (16) `raster::tests::soft_mask_applies_to_a_shading_pattern_fill`; (17), (18) `raster::tests::reading_colors_keep_highlight_annotations_readable`; (19) `mesh_extent_tests::{a_mesh_paints_its_triangles_alone, a_mesh_keeps_the_graphics_state_alpha, a_mesh_off_the_canvas_paints_nothing}` (`cargo test -p hayro`); (20) `raster::tests::a_tiling_pattern_drawn_once_shows_its_cell`, `raster::tests::a_large_step_still_tiles_where_the_next_cell_shows`, `raster::tests::a_tiling_cell_too_thin_to_scale_keeps_the_old_path`; (22) `raster::tests::knockout_groups_replace_what_their_elements_cover`; (23) `raster::tests::axial_and_radial_shadings_draw_as_native_gradients`; (25) `tiling_cell_placement::{far_cells_of_a_fill_sit_at_whole_steps, far_cells_sit_at_whole_steps_under_a_turned_scaled_matrix, far_cells_of_a_stroke_sit_at_whole_steps, a_cell_pixmap_spans_exactly_one_step}` (`cargo test -p pdfcraft-render --test it`) | -| hayro-jbig2 | 0.3.0 | Apache-2.0 OR MIT | (1) at most 2^28 pixels per bitmap and page bitmap, and 2^25 cells per halftone grid and grayscale image (each side could be 65535: 4.3 billion pixels decoded one by one, and a 4-byte value per cell); (2) at most 2^26 symbol pixels per symbol dictionary (a fuzzed dictionary decoded for minutes); (3) a symbol dictionary's height classes are capped at one per new symbol and its export runs at `2 × symbols + 1`, each plus `EXTRA_EMPTY_STEPS` (1024): an empty height class or a zero-length export run doesn't advance, and past the end of its data the arithmetic decoder can decode them for ever (one changed byte hung the renderer); (4) a segment header's long-form referred-to segment count is capped at `u16::MAX` and a larger count is refused before its retention or referred-to bytes are read: the 29-bit count went straight to `Vec::with_capacity`, a reservation of about 2 GiB whose failure aborts the process (from storytold/craft-libs#176); (5) what a page's segments hold for later ones (intermediate regions, pattern and symbol dictionaries with their headers and retained contexts, and Huffman tables) is at most 64 MiB, two square bitmaps of 16,384 a side (`MAX_RETAINED_WORDS`), and a dictionary's new and exported symbols are counted against it as they are made: each was bounded on its own, but a few dozen bytes an intermediate region held 33 MB each, and 8 MiB symbols exported again and again killed the process, so a few kilobytes could exhaust memory; (6) a segment may refer to at most 2^20 symbols, checked before any are collected: references may repeat, and 65,535 of them to one dictionary, in a 78 KB stream, asked for 17 GB; (7) a pattern dictionary keeps at most 16 MiB of shifted copies, which only speed up drawing, and none that wouldn't fit what the page has left (`MAX_SHIFTED_WORDS`); (8) a custom Huffman table has at most 2^16 lines, and a stream with its globals at most 2^20 segments and 2^22 references, checked as they are read: both grew before anything counted them, and PDFs of a kilobyte or so reached 5 GB and more behind nested Flate; (9) a page past the bounds of (1) is refused when the stream is opened: a caller sizes its output from the header before the page bitmap is made, and an Indexed image in a 743-byte PDF asked for 137 GB, which aborts; (10) a stream may ask for at most 2^30 units of decoding work, four of the largest pages, about 6 s to 17 s (`MAX_WORK`): decoding a bitmap costs a pixel each and 4 a row, copying one a word each and 1 a row, and each integer an item reads costs 38, what one takes at worst, so one with no pixels pays too, before it is decoded: each bitmap was bounded, but nothing bounded how many there were, and a 795-byte PDF took 265 s; (12) adding to a location, a reference offset, a symbol's corner or a Huffman range line near the end of an `i32`, and negating a decoded integer of 2^31, overflowed: a panic wherever overflow is checked. The refinement context, a text region's corners, the integer decoder and the Huffman table wrap, as a release build did, and `Bitmap::combine` saturates, which comes to the same, as a location that overflows is past the end of any page. What is drawn doesn't change | (1) `raster::tests::jbig2_regions_of_billions_of_pixels_are_refused`, `raster::tests::jbig2_halftone_grids_past_their_bound_are_refused`; (2) the nightly `cargo xtask fuzz` finding, which now finishes in about a second; (3) `raster::tests::jbig2_symbol_dictionaries_that_never_advance_terminate`; (4) `segment::tests::test_referred_to_count_is_capped` (`cargo test --manifest-path vendor/hayro-jbig2/Cargo.toml`); (5) `raster::tests::jbig2_regions_held_past_a_pages_bound_are_refused`, `jbig2_symbols_without_pixels_count_towards_a_pages_bound`, `jbig2_retained_contexts_count_towards_a_pages_bound`, `jbig2_huffman_tables_count_towards_a_pages_bound`, `jbig2_new_symbols_count_towards_a_pages_bound`, `jbig2_new_symbols_are_held_to_what_a_page_has_left`, `jbig2_pattern_dictionaries_count_towards_a_pages_bound`, and in the crate (`cargo test --manifest-path vendor/hayro-jbig2/Cargo.toml`) `decode::symbol::tests::exported_symbols_are_counted_before_they_are_copied`, `tests::the_room_left_shrinks_as_segments_are_stored`; (6) `raster::tests::jbig2_segments_referring_to_too_many_symbols_are_refused`; (7) `raster::tests::jbig2_pattern_dictionaries_too_large_to_shift_still_draw`, `jbig2_shifted_patterns_never_refuse_an_image`; (8) `raster::tests::jbig2_huffman_tables_of_too_many_lines_are_refused`, `jbig2_streams_of_too_many_segments_are_refused`, `jbig2_streams_of_too_many_references_are_refused`, and in the crate `tests::the_segments_of_a_stream_and_its_globals_count_together`; (9) `raster::tests::jbig2_pages_past_the_bounds_are_refused_before_anything_is_sized_from_them`, `tests::a_page_past_the_bounds_is_refused_when_opened`; (10) `raster::tests::jbig2_decoding_work_is_counted_item_by_item`; (12) `raster::tests::jbig2_placements_at_the_end_of_an_i32_draw_nothing` | +| hayro-jbig2 | 0.3.0 | Apache-2.0 OR MIT | (1) at most 2^28 pixels per bitmap and page bitmap, and 2^25 cells per halftone grid and grayscale image (each side could be 65535: 4.3 billion pixels decoded one by one, and a 4-byte value per cell); (2) at most 2^26 symbol pixels per symbol dictionary (a fuzzed dictionary decoded for minutes); (3) a symbol dictionary's height classes are capped at one per new symbol and its export runs at `2 × symbols + 1`, each plus `EXTRA_EMPTY_STEPS` (1024): an empty height class or a zero-length export run doesn't advance, and past the end of its data the arithmetic decoder can decode them for ever (one changed byte hung the renderer); (4) a segment header's long-form referred-to segment count is capped at `u16::MAX` and a larger count is refused before its retention or referred-to bytes are read: the 29-bit count went straight to `Vec::with_capacity`, a reservation of about 2 GiB whose failure aborts the process (from storytold/craft-libs#176); (5) what a page's segments hold for later ones (intermediate regions, pattern and symbol dictionaries with their headers and retained contexts, and Huffman tables) is at most 64 MiB, two square bitmaps of 16,384 a side (`MAX_RETAINED_WORDS`), and a dictionary's new and exported symbols are counted against it as they are made: each was bounded on its own, but a few dozen bytes an intermediate region held 33 MB each, and 8 MiB symbols exported again and again killed the process, so a few kilobytes could exhaust memory; (6) a segment may refer to at most 2^20 symbols, checked before any are collected: references may repeat, and 65,535 of them to one dictionary, in a 78 KB stream, asked for 17 GB; (7) a pattern dictionary keeps at most 16 MiB of shifted copies, which only speed up drawing, and none that wouldn't fit what the page has left (`MAX_SHIFTED_WORDS`); (8) a custom Huffman table has at most 2^16 lines, and a stream with its globals at most 2^20 segments and 2^22 references, checked as they are read: both grew before anything counted them, and PDFs of a kilobyte or so reached 5 GB and more behind nested Flate; (9) a page past the bounds of (1) is refused when the stream is opened: a caller sizes its output from the header before the page bitmap is made, and an Indexed image in a 743-byte PDF asked for 137 GB, which aborts; (10) a stream may ask for at most 2^30 units of decoding work, four of the largest pages, about 6 s to 17 s (`MAX_WORK`): decoding a bitmap costs a pixel each and 4 a row, copying one a word each and 1 a row, and each integer an item reads costs 38, what one takes at worst, so one with no pixels pays too, before it is decoded: each bitmap was bounded, but nothing bounded how many there were, and a 795-byte PDF took 265 s; (11) `Image::decode_within` spends from what a run of images may still do, starting with its page's pixels, and `charge_reading` charges reading a stream and its globals before anything is parsed, so an operation over a document can bound what `MAX_WORK` bounds for one image, and images that fail or decode nothing add up too: a file of thousands of images made to reach that limit took as many times as long; (12) adding to a location, a reference offset, a symbol's corner or a Huffman range line near the end of an `i32`, and negating a decoded integer of 2^31, overflowed: a panic wherever overflow is checked. The refinement context, a text region's corners, the integer decoder and the Huffman table wrap, as a release build did, and `Bitmap::combine` saturates, which comes to the same, as a location that overflows is past the end of any page. What is drawn doesn't change | (1) `raster::tests::jbig2_regions_of_billions_of_pixels_are_refused`, `raster::tests::jbig2_halftone_grids_past_their_bound_are_refused`; (2) the nightly `cargo xtask fuzz` finding, which now finishes in about a second; (3) `raster::tests::jbig2_symbol_dictionaries_that_never_advance_terminate`; (4) `segment::tests::test_referred_to_count_is_capped` (`cargo test --manifest-path vendor/hayro-jbig2/Cargo.toml`); (5) `raster::tests::jbig2_regions_held_past_a_pages_bound_are_refused`, `jbig2_symbols_without_pixels_count_towards_a_pages_bound`, `jbig2_retained_contexts_count_towards_a_pages_bound`, `jbig2_huffman_tables_count_towards_a_pages_bound`, `jbig2_new_symbols_count_towards_a_pages_bound`, `jbig2_new_symbols_are_held_to_what_a_page_has_left`, `jbig2_pattern_dictionaries_count_towards_a_pages_bound`, and in the crate (`cargo test --manifest-path vendor/hayro-jbig2/Cargo.toml`) `decode::symbol::tests::exported_symbols_are_counted_before_they_are_copied`, `tests::the_room_left_shrinks_as_segments_are_stored`; (6) `raster::tests::jbig2_segments_referring_to_too_many_symbols_are_refused`; (7) `raster::tests::jbig2_pattern_dictionaries_too_large_to_shift_still_draw`, `jbig2_shifted_patterns_never_refuse_an_image`; (8) `raster::tests::jbig2_huffman_tables_of_too_many_lines_are_refused`, `jbig2_streams_of_too_many_segments_are_refused`, `jbig2_streams_of_too_many_references_are_refused`, and in the crate `tests::the_segments_of_a_stream_and_its_globals_count_together`; (9) `raster::tests::jbig2_pages_past_the_bounds_are_refused_before_anything_is_sized_from_them`, `tests::a_page_past_the_bounds_is_refused_when_opened`; (10) `raster::tests::jbig2_decoding_work_is_counted_item_by_item`; (11) `jbig2::decode::tests::a_run_of_images_spends_its_allowance_down_to_the_step` (pdfcraft-filters); (12) `raster::tests::jbig2_placements_at_the_end_of_an_i32_draw_nothing` | | lopdf | 0.45.0 | MIT | (1) PNG predictor rows longer than the data are refused before their buffers are allocated (a fuzzed `/Columns 4294967295` allocated two 4 GiB rows), and empty frames return without row buffers; (2) predictor row widths use saturating arithmetic or reject overflow; (3) sub-byte TIFF Predictor 2 scratch is bounded by the samples present in the input instead of the declared `/Colors`, aligned with [lopdf#589](https://github.com/J-F-Liu/lopdf/pull/589); (4) the object lookup keeps its cycle history through compressed objects, requires an ordinary in-file container, and caps the chain of indirect lookups at 16 (a chain of new objects, each a `/Length` compressed in a container whose own `/Length` names the next, or a stream whose `/Length` names the next stream, overflowed the stack: a dev build's 2 MiB thread within 800 hops); (5) object-stream members are parsed within their own extent (up to the next distinct offset), an entry whose offset repeats an earlier entry's is skipped (so a repeated object number can resolve to its earlier entry), and offsets are processed in index order; (6) `find_latest_trailer`: a rebuild takes a `/Type /XRef` stream dictionary as the trailer when the file has no `trailer` keyword (the latest in the file wins, as a later `trailer` would), so a concatenated or truncated file keeps its /Info and /ID instead of failing to load; a candidate whose /Root is the catalog beats one whose /Root is another dictionary, and an in-file /Root must match its generation (#2365) | (1) `inspect::tests::png_predictor_rows_longer_than_the_data_are_refused_before_allocating`, `inspect::tests::empty_png_predictor_frames_do_not_allocate_rows`; (2) `inspect::tests::tiff_subbyte_predictor_row_width_overflow_is_refused`; (3) `inspect::tests::tiff_subbyte_predictor_scratch_is_bounded_by_available_samples`, `inspect::tests::tiff_subbyte_predictors_keep_components_rows_and_padding`; (4) `inspect::tests::compressed_object_self_container_does_not_recurse`, `inspect::tests::compressed_object_mutual_containers_do_not_recurse`, `inspect::tests::object_stream_length_cycle_does_not_recurse`, `inspect::tests::compressed_object_container_chain_does_not_recurse`, `inspect::tests::compressed_length_chain_does_not_recurse`, `inspect::tests::plain_stream_length_chain_does_not_recurse`, `inspect::tests::compressed_objects_and_indirect_stream_length_still_load`, `inspect::tests::compressed_length_in_a_container_with_an_indirect_length_still_loads`; (5) `inspect::tests::object_stream_member_extents_bound_owned_strings`, `inspect::tests::object_stream_member_extents_preserve_index_order_and_whitespace`; (6) `inspect::tests::rebuilt_file_keeps_the_info_of_its_cross_reference_stream`, `inspect::tests::rebuilt_file_prefers_a_trailer_whose_root_is_the_catalog` | -| hayro-syntax | 0.7.2 | Apache-2.0 OR MIT | (1) Page-tree cycle guard in `resolve_pages` (visited set + depth cap): a `/Kids` loop among compressed objects overflowed the stack and aborted the process; (2) `ccitt_size_ok`: CCITT images wider than 2^20 columns or over 2^28 pixels are not decoded (a fuzzed `/Columns 4294967295` allocated 4 GiB); (3) Flate/LZW predictor row widths are saturating `usize`, a zero width is refused and a row longer than the data is not allocated (a fuzzed `/Columns 9223372036854775807` wrapped to a 2^61-byte allocation and aborted); (4) the inline-image end-of-data check (`EI`) doesn't nest inside its own look-ahead and examines at most 256 candidates and steps (50 images with "EI" in their data ran for over ten minutes); an EI followed by a delimiter (EI%..., EI[...) ends the image like one followed by white space; only a regular character after EI skips the candidate; (5) a stream whose `/Length` is wrong is recovered only when `stream` is the next token — scanning ahead to a later object's `stream` made an indirect appearance-state dictionary (Quartz checkboxes: `/AP /N` → `<< /Yes … /Off … >>`) render as a non-form, so the widget was skipped; (6) JPX rescaling uses an exact integer sample range for 1–32-bit components (32 shifted past u32, and floating-point maxima at 25–31 bits wrapped to zero), and refuses zero-sized rows; (7) `decode_limit`: Flate (through flate2 and the fallback inflater), LZW, RunLength and ASCII85 never write past `MAX_DECODED_STREAM` (256 MiB), or, for the last filter of an image of known size, past twice its pixel bytes (a predictor tag byte per byte), at most 1 GiB; `Stream::decoded_within` for budgeted callers; a page's `/Contents` array shares one `MAX_DECODED_STREAM` (a 2 MB page whose content stream or 8 × 8 image inflated to 2 GB took the renderer past 3 GB in under a second; naming the stream twenty times in `/Contents`, 5 GB); (8) high-precision numbers (jsPDF MediaBox coordinates with over 19 digits) parse without overflowing the u64 mantissa: fractional digits past it are dropped, integer digits past it scale the value (a real, kept finite); (9) large dictionary indexes are built on first use and shared across repeated reads within each PDF (#307); the validated-byte cache is bounded, reader contexts remain separate, repairs and inline/content dictionaries bypass sharing, and small dictionaries stay eager; (10) decoded object-stream slots publish once under contention, cold loading rejects recursive dependencies, and xref repair serializes without holding recursive read guards; this permits one parser per native render pool with private worker caches; (11) `sync.rs`: a poisoned lock is recovered instead of unwrapped (a worker panic no longer cascades into every reader of the same PDF), and xref repair takes a blocking write lock instead of asserting a non-blocking one; (12) `SegmentList` (`util.rs`) returns `None` for an out-of-range index instead of panicking; (13) a page's `/UserUnit` scales `render_dimensions` and `initial_transform`, so the page and everything on it are sized in points, as Acrobat shows them; it is read as Acrobat reads it (the page's own entry, not inherited; a number from 1 up, at most 75,000; anything else counts as 1), and a page without it keeps exactly the transform it had; (14) revision 2–4 passwords are tried as given and then in PDFDocEncoding (`legacy_passwords` in `crypto/mod.rs`, which resolves the upstream `TODO: Convert to PDFDocEncoding`): passwords arrive as UTF-8 text, so a password with characters outside ASCII (`Çok güzel`, `ılık€`) written in PDFDocEncoding, as ISO 32000-2 §7.6.4.3.2 asks and qpdf and Acrobat write it, was always wrong; (15) page content is read a piece at a time (`page::ContentReader`, `Page::content_reader`): plain streams and Flate streams without a predictor are decoded as they are read, with a budget of 64 times their compressed size and never less than `MAX_DECODED_STREAM` (a stream that expands past it is cut and reported); other streams are decoded whole, as before, and share `MAX_DECODED_STREAM`. The content tokenizer reads a window at a time (`UntypedIter::new_window`, `TypedIter::needs_more`, `TypedIter::committed`): an instruction that runs past the window is not decided until more data follows, which `Reader` records by flagging reads and `at_end` past the end of the data, including through the clones the parser makes. The Flate decoder keeps its own 32 KiB history, so it pauses at any output size. `ContentReader::new` reuses raw/decrypted stream bytes for budget accounting and piece creation, and `decoded_raw_within` applies the existing Whole-stream filters and limits to those bytes without decrypting twice; (16) revision 5–6 (AES-256) passwords are tried in their SASLprep form (RFC 4013, then UTF-8, at most 127 bytes, as ISO 32000-2 §7.6.4.3.3 Algorithm 2.A asks and pdfcraft-crypt writes them) and then, if that differs, as given (`aes256_passwords` in `crypto/mod.rs`, which resolves the upstream `TODO: Do the above.`; `stringprep`, already in the tree through pdfcraft-crypt, is an optional dependency enabled by `std`, and without `std` passwords are used as given): the renderer used the password as typed, so one that SASLprep changes (a decomposed `café`, a no-break space, the fullwidth `ab` a Japanese IME types in full-width mode) was wrong, although pdfcraft-cos accepted it: protecting a document with such an open password was rolled back ("the password is incorrect"), and a file with such a password did not open with it.; (17) CCITT `/Rows 0` means the height is not predetermined (ISO 32000-2 Table 11), not zero rows: scanned Group 4 pages written that way rendered blank; (18) The streaming Flate decoder (`lzw_flate::flate::fallback`) copies a back-reference in runs of up to its distance (`extend_from_within`), not byte by byte. The copy reads only bytes already in the output, and a copy whose source does not exist still writes nothing, so the bytes are those a byte-by-byte copy writes. Inflating the A1 sample's content stream (278.6 MB) takes about 14% less time (0.66 s to 0.56 s); the output is identical; (19) CCITT `/Rows` below the image's `/Height` decodes to the height: a plotter driver wrote `/Rows` equal to `/Columns`, so only the first rows were decoded and the rest drawn black (#3308) (20) `stream` followed by spaces or tabs and then the line break (`stream \r\n`, as Microsoft Reporting Services writes it) starts the data after the line break; the content stream was taken to start at the space and the page rendered blank.; (21) a JP2 colour specification naming an enumerated colour space the decoder refuses (CIEJab in a veraPDF fixture, YCbCr, PhotoYCC, YPbPr, bilevel…) no longer fails the image: it is decoded again from a copy whose `colr` names the space the decoder assumes without one, greyscale, sRGB or CMYK by component count, as MuPDF and Poppler draw it (`without_refused_enumerated_colour`; the page drew blank, #3306); (22) an object stream's index of `objnum offset` pairs is parsed once per stream and kept beside its decoded data (`ObjectStreamIndexes`, `XRef::with_object_stream_indexes`), and an offset past `usize` is malformed instead of wrapping: `XRef::get_with` parsed the whole index again for every object it fetched from the stream, so reading all of a stream of N objects took N² steps (a Firefox page whose 65,542 objects share one stream took 37 s to draw and 40 s to extract its text); (23) the inline-image end-of-data look-ahead no longer rejects a candidate `EI` because a byte above 0x7F lies between it and the next one: when the candidate is the end, those bytes are the content stream that follows the image, and its strings carry such bytes (WinAnsi `(Grüße) Tj`, the two-byte codes of any Type 0 font), so the operator check that follows decides alone, bounded as in (4) (a scanned page whose OCR text held an accented word and a later capital "EI" — EINGANG, BEI, KLEIN — drew and extracted nothing after the image: 40 of 275 pages across five real documents); (24) `xref::prev_offset`: a trailer `/Prev` written as a reference `N G R` is read as the offset that object holds when the section's own entries place it (iText's `indirectPrev.pdf`; each section's entries are read before its `Prev` is followed), and otherwise as offset N (tiff2pdf; JHOVE's PDF-HUL-157 files, #2366), as `pdfcraft-cos` and other readers take it, so the earlier sections' pages are seen instead of one; (25) direct arrays and dictionaries share a reader-local nesting cap of 128, counted while skipping and while parsing a dictionary (its lenient repair reads, rather than skips, an object found where a key belongs, so `<< << …` recursed through that read); deeper objects return `None` instead of overflowing the stack (including unused trailer values, trailer entries, content operands and marked-content properties); a chain of 65 direct stitching functions now stops at this cap, before the 64-function guard; (26) an xref stream subsection must be backed by its decoded data: all-zero `/W` widths (an entry reads no bytes) and a declared count longer than the data are refused before any entry is inserted, where a tiny stream with a large `/Size` or `/Index` count inserted that many entries (from storytold/craft-libs#239); a subsection running past object number `i32::MAX` is refused instead of overflowing or turning negative; (27) an xref stream's type field is read big-endian at its full `/W[0]` width, where only its first byte was read and wider fields shifted every later entry, and `/W[0]` over 8 bytes is refused like `/W[1]` (from storytold/craft-libs#241); (28) a content instruction keeps up to 256 operands (`MAX_OPERANDS`) instead of 10, and past that drops the oldest instead of ending the content stream: the eleventh operand of a twelve-ink DeviceN `scn` (ISO 32000-2 §8.6.6.5 allows any number of components) blanked the rest of the page (#4260); (29) a `/JBIG2Globals` stream that is itself JBIG2 isn't decoded: globals are raw segments, and a chain of 16,000 such streams overflowed the stack, which aborts the process; (32) a group of array items read together (a tuple: an image's `/Decode`, `/W`, `/W2`, and a function's `/Domain`, `/Range`, `/Encode` and `/Decode`) can start with a reference: it was taken for the whole group and lost, which ended the array, so an image with `/Decode [7 0 R 0]` didn't draw and CID widths fell back to `/DW`; (33) an object that holds only a reference stands for what that names, stored on its own or in an object stream, up to 32 references: read as a number it was the reference's own object number, so a `/Decode` or `/W` entry naming such an object took a wrong value, and as anything else it was lost. Past 32, as any cycle goes, it reads as a missing object. An object stream isn't reached that way, as its checks are of the object named; reading its index counts against the 64 nested loads and reads its dictionary alone, as a chain of them, each with a member of the next for its `/N`, `/First` or `/Length`, ran out of stack; and a comment inside a reference counts as white space | (1) `cos/tests/writer.rs::page_tree_loops_in_object_streams_do_not_crash_readers`; (2) `raster::tests::absurd_mask_and_fax_sizes_are_refused_before_decoding`; (3) `raster::tests::absurd_predictor_columns_and_line_widths_render`; (4) `raster::tests::inline_images_with_ei_in_their_data_parse_in_linear_time`, `content::tests::inline_image_ei_may_be_followed_by_a_delimiter`; (5) `raster::tests::indirect_appearance_state_dict_is_not_another_stream`; (6) `raster::tests::jpx_stream_bit_depth_boundaries_do_not_panic`, `raster::tests::jpx_32_bit_image_does_not_prevent_other_page_content_from_rendering`, `raster::tests::jpx_gray_rgb_and_alpha_keep_eight_bit_samples`, `raster::tests::jpx_streams_reject_out_of_range_bit_depths`; (7) `raster::tests::decompression_bombs_stop_at_the_stream_limit`, `raster::tests::page_contents_and_nested_forms_share_one_budget`; (8) `inspect::tests::jspdf_high_precision_mediabox_does_not_overflow_dimensions`, `object::number::tests::high_precision_float_does_not_overflow_mantissa` (hayro-syntax); (9) `object::dict::lazy_index_tests`, `raster::tests::large_resource_indexes_preserve_pixels_and_text`; (10) `data::tests`, `xref::tests::concurrent_cold_object_stream_reads_all_succeed`, `raster::tests::shared_parser_is_lazy_and_initializes_once_under_contention`; (11) `data::tests::panicking_initializer_wakes_waiters_and_prevents_retries`, `xref::tests::concurrent_cold_object_stream_reads_all_succeed`; (12) `util::tests::segment_list_rejects_out_of_range_indices`; (13) `raster::tests::user_unit_scales_the_page_and_everything_on_it`; (14) `crypto::pdfcraft_password_tests`, `pdfcraft-engine` `tests::legacy_passwords_with_turkish_characters_open`; (15) `content::tests::windows_keep_every_instruction_at_every_split`, `content::tests::windows_keep_every_instruction_in_pieces_of_any_size`, `content::tests::windows_match_the_slice_on_random_content`, `content::tests::windows_drop_blanks_and_keep_a_comment_that_may_go_on`, `page::content_reader_tests::content_past_the_cap_is_read_to_the_end`, `page::content_reader_tests::a_stream_that_expands_past_the_budget_is_cut_there`, `page::content_reader_tests::a_small_expansion_under_the_cap_is_not_cut`, `raster::tests::page_content_past_the_old_cap_renders`, `raster::tests::content_reader_returns_the_same_bytes_in_any_pieces`, `raster::tests::content_bombs_stop_at_the_budget_and_say_so`, `page::content_reader_tests::plain_and_whole_pieces_keep_their_bytes`, `page::content_reader_tests::repeated_content_reference_counts_compressed_bytes_once`, `page::content_reader_tests::whole_cap_still_counts_later_unique_streams`; (16) `crypto::pdfcraft_password_tests::aes256_passwords_are_tried_in_their_saslprep_form_then_as_given`, `crypto::pdfcraft_password_tests::aes256_passwords_open_as_typed_and_in_their_saslprep_form`, `pdfcraft-engine` `tests::aes256_open_passwords_that_saslprep_changes_protect_and_reopen_as_typed`, `tests::aes256_files_whose_passwords_saslprep_changes_open_as_typed`; (17) `raster::tests::group4_fax_with_rows_zero_decodes_to_the_image_height`; (18) `filter::lzw_flate::tests::back_reference_longer_than_its_distance_repeats_its_source`, `back_reference_cut_by_the_limit_resumes_in_the_next_call` and `back_reference_reads_bytes_written_by_an_earlier_call`; each fails when the copy returns the wrong remaining count; (19) `raster::tests::group4_fax_with_rows_below_its_height_decodes_to_the_image_height`; (20) `raster::tests::space_before_the_line_break_after_stream_still_renders`; (21) `raster::tests::a_jp2_image_in_a_refused_enumerated_colour_space_is_drawn`, `filter::jpx::tests::refused_enumerated_colour_spaces_become_the_component_counts_default`, `filter::jpx::tests::what_the_decoder_handles_or_cant_be_read_is_left_alone` (`cargo test --manifest-path vendor/hayro-syntax/Cargo.toml`); (22) `raster::tests::objects_in_one_large_object_stream_are_read_in_linear_time`; (23) `text::tests::text_after_an_inline_image_survives_a_non_ascii_byte_before_a_later_ei`, `content::tests::an_inline_image_ends_at_its_own_ei_when_later_text_holds_a_non_ascii_byte` (hayro-syntax); (24) `xref::tests::prev_as_reference_reaches_the_earlier_section`, `xref::tests::prev_as_reference_to_an_object_holding_the_offset_reads_that_offset`, `pdfcraft-cos` `document::tests::a_prev_written_as_a_reference_still_reaches_the_earlier_sections`, `document::tests::a_prev_reference_to_an_object_holding_the_offset_reads_that_offset`; (25) `raster::tests::deeply_nested_direct_objects_do_not_overflow_the_stack`, `raster::tests::dictionaries_nested_without_keys_in_content_do_not_overflow_the_stack`, `raster::tests::dictionaries_nested_without_keys_in_the_trailer_do_not_overflow_the_stack`, `raster::tests::dictionaries_nested_without_keys_as_marked_content_properties_do_not_overflow_the_stack`, `raster::tests::dictionaries_nested_without_keys_are_read_up_to_the_nesting_cap`, `raster::tests::nesting_at_the_cap_fits_a_512_kib_stack` (native only), `raster::tests::function_limits_depth_guard_refuses_a_chain_of_references`; (26) `xref::tests::xref_stream_entries_need_backing_bytes`; (27) `xref::tests::xref_stream_type_field_uses_the_full_w0_width`, `xref::tests::xref_stream_loader_rejects_oversized_w0` (`cargo test --manifest-path vendor/hayro-syntax/Cargo.toml`); (28) `content::ops::tests::scn_with_twelve_components_keeps_them_all`, `content::ops::tests::operands_past_the_cap_keep_the_latest_in_order` (hayro-syntax), `raster::tests::devicen_inks::a_twelve_ink_devicen_colour_paints`, `raster::tests::devicen_inks::a_four_ink_devicen_colour_paints`, `raster::tests::devicen_inks::an_operator_with_hundreds_of_operands_does_not_end_the_content`; (29) `raster::tests::jbig2_globals_that_are_jbig2_themselves_are_not_decoded`, `raster::tests::jbig2_globals_are_read`; (32) `raster::tests::a_decode_array_with_references_in_it_is_read`, `raster::tests::a_functions_arrays_can_start_with_a_reference` (pdfcraft-render), `font::cid::width_tests::a_width_group_can_start_with_a_reference` (hayro-interpret); (33) `raster::tests::a_reference_to_a_reference_is_what_it_names`, `raster::tests::a_decode_array_with_references_in_it_is_read` (pdfcraft-render), `font::cid::width_tests::a_width_group_can_start_with_a_reference` (hayro-interpret), `xref::tests::an_object_stream_isnt_reached_through_a_reference`, `xref::tests::a_chain_of_object_streams_ends_at_the_limit_of_nested_loads`, `xref::tests::a_chain_of_object_streams_takes_no_more_work_for_two_ways_on`, `xref::tests::a_reference_held_in_either_storage_is_followed`, `xref::tests::a_page_a_reference_is_held_to_is_found_once` (hayro-syntax) | +| hayro-syntax | 0.7.2 | Apache-2.0 OR MIT | (1) Page-tree cycle guard in `resolve_pages` (visited set + depth cap): a `/Kids` loop among compressed objects overflowed the stack and aborted the process; (2) `ccitt_size_ok`: CCITT images wider than 2^20 columns or over 2^28 pixels are not decoded (a fuzzed `/Columns 4294967295` allocated 4 GiB); (3) Flate/LZW predictor row widths are saturating `usize`, a zero width is refused and a row longer than the data is not allocated (a fuzzed `/Columns 9223372036854775807` wrapped to a 2^61-byte allocation and aborted); (4) the inline-image end-of-data check (`EI`) doesn't nest inside its own look-ahead and examines at most 256 candidates and steps (50 images with "EI" in their data ran for over ten minutes); an EI followed by a delimiter (EI%..., EI[...) ends the image like one followed by white space; only a regular character after EI skips the candidate; (5) a stream whose `/Length` is wrong is recovered only when `stream` is the next token — scanning ahead to a later object's `stream` made an indirect appearance-state dictionary (Quartz checkboxes: `/AP /N` → `<< /Yes … /Off … >>`) render as a non-form, so the widget was skipped; (6) JPX rescaling uses an exact integer sample range for 1–32-bit components (32 shifted past u32, and floating-point maxima at 25–31 bits wrapped to zero), and refuses zero-sized rows; (7) `decode_limit`: Flate (through flate2 and the fallback inflater), LZW, RunLength and ASCII85 never write past `MAX_DECODED_STREAM` (256 MiB), or, for the last filter of an image of known size, past twice its pixel bytes (a predictor tag byte per byte), at most 1 GiB; `Stream::decoded_within` for budgeted callers; a page's `/Contents` array shares one `MAX_DECODED_STREAM` (a 2 MB page whose content stream or 8 × 8 image inflated to 2 GB took the renderer past 3 GB in under a second; naming the stream twenty times in `/Contents`, 5 GB); (8) high-precision numbers (jsPDF MediaBox coordinates with over 19 digits) parse without overflowing the u64 mantissa: fractional digits past it are dropped, integer digits past it scale the value (a real, kept finite); (9) large dictionary indexes are built on first use and shared across repeated reads within each PDF (#307); the validated-byte cache is bounded, reader contexts remain separate, repairs and inline/content dictionaries bypass sharing, and small dictionaries stay eager; (10) decoded object-stream slots publish once under contention, cold loading rejects recursive dependencies, and xref repair serializes without holding recursive read guards; this permits one parser per native render pool with private worker caches; (11) `sync.rs`: a poisoned lock is recovered instead of unwrapped (a worker panic no longer cascades into every reader of the same PDF), and xref repair takes a blocking write lock instead of asserting a non-blocking one; (12) `SegmentList` (`util.rs`) returns `None` for an out-of-range index instead of panicking; (13) a page's `/UserUnit` scales `render_dimensions` and `initial_transform`, so the page and everything on it are sized in points, as Acrobat shows them; it is read as Acrobat reads it (the page's own entry, not inherited; a number from 1 up, at most 75,000; anything else counts as 1), and a page without it keeps exactly the transform it had; (14) revision 2–4 passwords are tried as given and then in PDFDocEncoding (`legacy_passwords` in `crypto/mod.rs`, which resolves the upstream `TODO: Convert to PDFDocEncoding`): passwords arrive as UTF-8 text, so a password with characters outside ASCII (`Çok güzel`, `ılık€`) written in PDFDocEncoding, as ISO 32000-2 §7.6.4.3.2 asks and qpdf and Acrobat write it, was always wrong; (15) page content is read a piece at a time (`page::ContentReader`, `Page::content_reader`): plain streams and Flate streams without a predictor are decoded as they are read, with a budget of 64 times their compressed size and never less than `MAX_DECODED_STREAM` (a stream that expands past it is cut and reported); other streams are decoded whole, as before, and share `MAX_DECODED_STREAM`. The content tokenizer reads a window at a time (`UntypedIter::new_window`, `TypedIter::needs_more`, `TypedIter::committed`): an instruction that runs past the window is not decided until more data follows, which `Reader` records by flagging reads and `at_end` past the end of the data, including through the clones the parser makes. The Flate decoder keeps its own 32 KiB history, so it pauses at any output size. `ContentReader::new` reuses raw/decrypted stream bytes for budget accounting and piece creation, and `decoded_raw_within` applies the existing Whole-stream filters and limits to those bytes without decrypting twice; (16) revision 5–6 (AES-256) passwords are tried in their SASLprep form (RFC 4013, then UTF-8, at most 127 bytes, as ISO 32000-2 §7.6.4.3.3 Algorithm 2.A asks and pdfcraft-crypt writes them) and then, if that differs, as given (`aes256_passwords` in `crypto/mod.rs`, which resolves the upstream `TODO: Do the above.`; `stringprep`, already in the tree through pdfcraft-crypt, is an optional dependency enabled by `std`, and without `std` passwords are used as given): the renderer used the password as typed, so one that SASLprep changes (a decomposed `café`, a no-break space, the fullwidth `ab` a Japanese IME types in full-width mode) was wrong, although pdfcraft-cos accepted it: protecting a document with such an open password was rolled back ("the password is incorrect"), and a file with such a password did not open with it.; (17) CCITT `/Rows 0` means the height is not predetermined (ISO 32000-2 Table 11), not zero rows: scanned Group 4 pages written that way rendered blank; (18) The streaming Flate decoder (`lzw_flate::flate::fallback`) copies a back-reference in runs of up to its distance (`extend_from_within`), not byte by byte. The copy reads only bytes already in the output, and a copy whose source does not exist still writes nothing, so the bytes are those a byte-by-byte copy writes. Inflating the A1 sample's content stream (278.6 MB) takes about 14% less time (0.66 s to 0.56 s); the output is identical; (19) CCITT `/Rows` below the image's `/Height` decodes to the height: a plotter driver wrote `/Rows` equal to `/Columns`, so only the first rows were decoded and the rest drawn black (#3308) (20) `stream` followed by spaces or tabs and then the line break (`stream \r\n`, as Microsoft Reporting Services writes it) starts the data after the line break; the content stream was taken to start at the space and the page rendered blank.; (21) a JP2 colour specification naming an enumerated colour space the decoder refuses (CIEJab in a veraPDF fixture, YCbCr, PhotoYCC, YPbPr, bilevel…) no longer fails the image: it is decoded again from a copy whose `colr` names the space the decoder assumes without one, greyscale, sRGB or CMYK by component count, as MuPDF and Poppler draw it (`without_refused_enumerated_colour`; the page drew blank, #3306); (22) an object stream's index of `objnum offset` pairs is parsed once per stream and kept beside its decoded data (`ObjectStreamIndexes`, `XRef::with_object_stream_indexes`), and an offset past `usize` is malformed instead of wrapping: `XRef::get_with` parsed the whole index again for every object it fetched from the stream, so reading all of a stream of N objects took N² steps (a Firefox page whose 65,542 objects share one stream took 37 s to draw and 40 s to extract its text); (23) the inline-image end-of-data look-ahead no longer rejects a candidate `EI` because a byte above 0x7F lies between it and the next one: when the candidate is the end, those bytes are the content stream that follows the image, and its strings carry such bytes (WinAnsi `(Grüße) Tj`, the two-byte codes of any Type 0 font), so the operator check that follows decides alone, bounded as in (4) (a scanned page whose OCR text held an accented word and a later capital "EI" — EINGANG, BEI, KLEIN — drew and extracted nothing after the image: 40 of 275 pages across five real documents); (24) `xref::prev_offset`: a trailer `/Prev` written as a reference `N G R` is read as the offset that object holds when the section's own entries place it (iText's `indirectPrev.pdf`; each section's entries are read before its `Prev` is followed), and otherwise as offset N (tiff2pdf; JHOVE's PDF-HUL-157 files, #2366), as `pdfcraft-cos` and other readers take it, so the earlier sections' pages are seen instead of one; (25) direct arrays and dictionaries share a reader-local nesting cap of 128, counted while skipping and while parsing a dictionary (its lenient repair reads, rather than skips, an object found where a key belongs, so `<< << …` recursed through that read); deeper objects return `None` instead of overflowing the stack (including unused trailer values, trailer entries, content operands and marked-content properties); a chain of 65 direct stitching functions now stops at this cap, before the 64-function guard; (26) an xref stream subsection must be backed by its decoded data: all-zero `/W` widths (an entry reads no bytes) and a declared count longer than the data are refused before any entry is inserted, where a tiny stream with a large `/Size` or `/Index` count inserted that many entries (from storytold/craft-libs#239); a subsection running past object number `i32::MAX` is refused instead of overflowing or turning negative; (27) an xref stream's type field is read big-endian at its full `/W[0]` width, where only its first byte was read and wider fields shifted every later entry, and `/W[0]` over 8 bytes is refused like `/W[1]` (from storytold/craft-libs#241); (28) a content instruction keeps up to 256 operands (`MAX_OPERANDS`) instead of 10, and past that drops the oldest instead of ending the content stream: the eleventh operand of a twelve-ink DeviceN `scn` (ISO 32000-2 §8.6.6.5 allows any number of components) blanked the rest of the page (#4260); (29) a `/JBIG2Globals` stream that is itself JBIG2 isn't decoded: globals are raw segments, and a chain of 16,000 such streams overflowed the stack, which aborts the process; (31) `set_page_jbig2_work`: the JBIG2 images decoded on a thread spend one allowance, set per page, 2^30 steps (`MAX_PAGE_JBIG2_WORK`), so a page of many images made to reach their own limit stops at one, and what they cost to read counts, whether they decode or not; unbounded until a page sets it; (32) a group of array items read together (a tuple: an image's `/Decode`, `/W`, `/W2`, and a function's `/Domain`, `/Range`, `/Encode` and `/Decode`) can start with a reference: it was taken for the whole group and lost, which ended the array, so an image with `/Decode [7 0 R 0]` didn't draw and CID widths fell back to `/DW`; (33) an object that holds only a reference stands for what that names, stored on its own or in an object stream, up to 32 references: read as a number it was the reference's own object number, so a `/Decode` or `/W` entry naming such an object took a wrong value, and as anything else it was lost. Past 32, as any cycle goes, it reads as a missing object. An object stream isn't reached that way, as its checks are of the object named; reading its index counts against the 64 nested loads and reads its dictionary alone, as a chain of them, each with a member of the next for its `/N`, `/First` or `/Length`, ran out of stack; and a comment inside a reference counts as white space; (34) a table rebuilt by scanning the file (`fallback_xref_map`) finds an object by its number when its header names another generation, including one no generation may be (`3 18446744073709551616 obj` in `poppler-85140-0.pdf`, #5580): the header is read leniently only in that scan (`read_object_header`), the object is also filed under generation 0 unless a real `N 0 obj` holds that key (a later header for the number moves the stand-in), `XRef::get_with` matches by object number only in a repaired table, and `XRef::objects` yields each location once | (1) `cos/tests/writer.rs::page_tree_loops_in_object_streams_do_not_crash_readers`; (2) `raster::tests::absurd_mask_and_fax_sizes_are_refused_before_decoding`; (3) `raster::tests::absurd_predictor_columns_and_line_widths_render`; (4) `raster::tests::inline_images_with_ei_in_their_data_parse_in_linear_time`, `content::tests::inline_image_ei_may_be_followed_by_a_delimiter`; (5) `raster::tests::indirect_appearance_state_dict_is_not_another_stream`; (6) `raster::tests::jpx_stream_bit_depth_boundaries_do_not_panic`, `raster::tests::jpx_32_bit_image_does_not_prevent_other_page_content_from_rendering`, `raster::tests::jpx_gray_rgb_and_alpha_keep_eight_bit_samples`, `raster::tests::jpx_streams_reject_out_of_range_bit_depths`; (7) `raster::tests::decompression_bombs_stop_at_the_stream_limit`, `raster::tests::page_contents_and_nested_forms_share_one_budget`; (8) `inspect::tests::jspdf_high_precision_mediabox_does_not_overflow_dimensions`, `object::number::tests::high_precision_float_does_not_overflow_mantissa` (hayro-syntax); (9) `object::dict::lazy_index_tests`, `raster::tests::large_resource_indexes_preserve_pixels_and_text`; (10) `data::tests`, `xref::tests::concurrent_cold_object_stream_reads_all_succeed`, `raster::tests::shared_parser_is_lazy_and_initializes_once_under_contention`; (11) `data::tests::panicking_initializer_wakes_waiters_and_prevents_retries`, `xref::tests::concurrent_cold_object_stream_reads_all_succeed`; (12) `util::tests::segment_list_rejects_out_of_range_indices`; (13) `raster::tests::user_unit_scales_the_page_and_everything_on_it`; (14) `crypto::pdfcraft_password_tests`, `pdfcraft-engine` `tests::legacy_passwords_with_turkish_characters_open`; (15) `content::tests::windows_keep_every_instruction_at_every_split`, `content::tests::windows_keep_every_instruction_in_pieces_of_any_size`, `content::tests::windows_match_the_slice_on_random_content`, `content::tests::windows_drop_blanks_and_keep_a_comment_that_may_go_on`, `page::content_reader_tests::content_past_the_cap_is_read_to_the_end`, `page::content_reader_tests::a_stream_that_expands_past_the_budget_is_cut_there`, `page::content_reader_tests::a_small_expansion_under_the_cap_is_not_cut`, `raster::tests::page_content_past_the_old_cap_renders`, `raster::tests::content_reader_returns_the_same_bytes_in_any_pieces`, `raster::tests::content_bombs_stop_at_the_budget_and_say_so`, `page::content_reader_tests::plain_and_whole_pieces_keep_their_bytes`, `page::content_reader_tests::repeated_content_reference_counts_compressed_bytes_once`, `page::content_reader_tests::whole_cap_still_counts_later_unique_streams`; (16) `crypto::pdfcraft_password_tests::aes256_passwords_are_tried_in_their_saslprep_form_then_as_given`, `crypto::pdfcraft_password_tests::aes256_passwords_open_as_typed_and_in_their_saslprep_form`, `pdfcraft-engine` `tests::aes256_open_passwords_that_saslprep_changes_protect_and_reopen_as_typed`, `tests::aes256_files_whose_passwords_saslprep_changes_open_as_typed`; (17) `raster::tests::group4_fax_with_rows_zero_decodes_to_the_image_height`; (18) `filter::lzw_flate::tests::back_reference_longer_than_its_distance_repeats_its_source`, `back_reference_cut_by_the_limit_resumes_in_the_next_call` and `back_reference_reads_bytes_written_by_an_earlier_call`; each fails when the copy returns the wrong remaining count; (19) `raster::tests::group4_fax_with_rows_below_its_height_decodes_to_the_image_height`; (20) `raster::tests::space_before_the_line_break_after_stream_still_renders`; (21) `raster::tests::a_jp2_image_in_a_refused_enumerated_colour_space_is_drawn`, `filter::jpx::tests::refused_enumerated_colour_spaces_become_the_component_counts_default`, `filter::jpx::tests::what_the_decoder_handles_or_cant_be_read_is_left_alone` (`cargo test --manifest-path vendor/hayro-syntax/Cargo.toml`); (22) `raster::tests::objects_in_one_large_object_stream_are_read_in_linear_time`; (23) `text::tests::text_after_an_inline_image_survives_a_non_ascii_byte_before_a_later_ei`, `content::tests::an_inline_image_ends_at_its_own_ei_when_later_text_holds_a_non_ascii_byte` (hayro-syntax); (24) `xref::tests::prev_as_reference_reaches_the_earlier_section`, `xref::tests::prev_as_reference_to_an_object_holding_the_offset_reads_that_offset`, `pdfcraft-cos` `document::tests::a_prev_written_as_a_reference_still_reaches_the_earlier_sections`, `document::tests::a_prev_reference_to_an_object_holding_the_offset_reads_that_offset`; (25) `raster::tests::deeply_nested_direct_objects_do_not_overflow_the_stack`, `raster::tests::dictionaries_nested_without_keys_in_content_do_not_overflow_the_stack`, `raster::tests::dictionaries_nested_without_keys_in_the_trailer_do_not_overflow_the_stack`, `raster::tests::dictionaries_nested_without_keys_as_marked_content_properties_do_not_overflow_the_stack`, `raster::tests::dictionaries_nested_without_keys_are_read_up_to_the_nesting_cap`, `raster::tests::nesting_at_the_cap_fits_a_512_kib_stack` (native only), `raster::tests::function_limits_depth_guard_refuses_a_chain_of_references`; (26) `xref::tests::xref_stream_entries_need_backing_bytes`; (27) `xref::tests::xref_stream_type_field_uses_the_full_w0_width`, `xref::tests::xref_stream_loader_rejects_oversized_w0` (`cargo test --manifest-path vendor/hayro-syntax/Cargo.toml`); (28) `content::ops::tests::scn_with_twelve_components_keeps_them_all`, `content::ops::tests::operands_past_the_cap_keep_the_latest_in_order` (hayro-syntax), `raster::tests::devicen_inks::a_twelve_ink_devicen_colour_paints`, `raster::tests::devicen_inks::a_four_ink_devicen_colour_paints`, `raster::tests::devicen_inks::an_operator_with_hundreds_of_operands_does_not_end_the_content`; (29) `raster::tests::jbig2_globals_that_are_jbig2_themselves_are_not_decoded`, `raster::tests::jbig2_globals_are_read`, `raster::tests::the_jbig2_images_of_a_page_share_one_allowance`, `raster::tests::an_image_that_fails_spends_the_pages_allowance_too`; (32) `raster::tests::a_decode_array_with_references_in_it_is_read`, `raster::tests::a_functions_arrays_can_start_with_a_reference` (pdfcraft-render), `font::cid::width_tests::a_width_group_can_start_with_a_reference` (hayro-interpret); (33) `raster::tests::a_reference_to_a_reference_is_what_it_names`, `raster::tests::a_decode_array_with_references_in_it_is_read` (pdfcraft-render), `font::cid::width_tests::a_width_group_can_start_with_a_reference` (hayro-interpret), `xref::tests::an_object_stream_isnt_reached_through_a_reference`, `xref::tests::a_chain_of_object_streams_ends_at_the_limit_of_nested_loads`, `xref::tests::a_chain_of_object_streams_takes_no_more_work_for_two_ways_on`, `xref::tests::a_reference_held_in_either_storage_is_followed`, `xref::tests::a_page_a_reference_is_held_to_is_found_once` (hayro-syntax); (34) `raster::tests::a_rebuilt_table_finds_an_object_whose_header_names_another_generation`, `raster::tests::a_rebuilt_tables_generation_0_stand_in_is_not_a_second_object` (pdfcraft-render), `xref::tests::an_object_stream_and_its_first_member_are_both_enumerated` (hayro-syntax) | | winit | 0.30.13 | Apache-2.0 | (1) on Windows 11 (build 22000 and later), `WM_DPICHANGED` applies the rect Windows suggests. It used to nudge the window onto the monitor `MonitorFromWindow` names, which during a drag is still the monitor being left; the nudge sent another `WM_DPICHANGED`, so a window dragged to a monitor with another scale factor grew and stayed on the wrong monitor at the wrong scale (#324). Backport of winit master 488c036a ([winit#4341](https://github.com/rust-windowing/winit/pull/4341)), which no 0.30 release has; Windows 10 keeps the old adjustment, as on winit master. (2) on Wayland, a seat's text input is destroyed when the seat goes away, not whenever it loses a capability: losing any capability (a touch screen or tablet unplugged, a remote-desktop session ending) destroyed it, and only an added capability recreated it, so IME stopped working until restart. Port of [winit#4747](https://github.com/rust-windowing/winit/pull/4747); (3) on Windows, an IME composition reports its cursor from `GCS_CURSORPOS` only when `WM_IME_COMPOSITION` says it is set, and at the end of the composition otherwise: the Microsoft Korean IME never sets it, so the cursor read as 0 (egui then drew no caret while composing; it now draws it after the syllable). Port of [winit#4746](https://github.com/rust-windowing/winit/pull/4746); (4) on Windows, a hidden window is not maximized until it is shown, and a hidden window shown while maximized gets one `ShowWindow(SW_MAXIMIZE)`: `SW_MAXIMIZE` shows a hidden window, so PdfCraft, which eframe keeps hidden until its first frame is drawn, appeared unpainted (white) when it restored a maximized window, and could lose its focus. Port of [winit#4587](https://github.com/rust-windowing/winit/pull/4587) (the later, focus-safe form of [winit#4575](https://github.com/rust-windowing/winit/pull/4575)); (5) on X11, when allowing or disallowing IME replaces the focused window's input context (egui does it each time a text field gains or loses focus), the new context is focused: no focus event follows, so it stayed unfocused until the window lost and regained focus. Port of [winit#4727](https://github.com/rust-windowing/winit/pull/4727); (6) on macOS, `insertText` commits through IME when a composition was started (`pending_commit`, set by `setMarkedText`) rather than when marked text is left: input methods that end a composition with `unmarkText` before `insertText` lost the text, and Apple Korean dropped the key typed after a syllable (`한` then `5` or `;`); other `insertText` calls stay `KeyboardInput`; a commit outside a key press (a candidate clicked with the mouse, dictation) clears the marked text and leaves no key to swallow, as in [winit#4748](https://github.com/rust-windowing/winit/pull/4748) (without it the next key, such as Backspace, was lost). `validAttributesForMarkedText` lists the underline and marked-clause attributes, without which some input methods don't compose. Port of [winit#4650](https://github.com/rust-windowing/winit/pull/4650), the 0.30 backport of [winit#4651](https://github.com/rust-windowing/winit/pull/4651) (merged on winit master), with the underline attribute spelled as AppKit's `NSUnderlineStyleAttributeName` (`NSUnderline`); (7) on macOS, disallowing IME with a composition in progress (focus leaving a text field) tells the input method to discard its marked text (`discardMarkedText`): it kept composing it once IME was allowed again, so the abandoned syllable came back (`하`, then `가` typed in the next field, became `학`, then `하` + `가`; Japanese `か` then `さ` became `傘`). Port of [winit#4745](https://github.com/rust-windowing/winit/pull/4745); (8) on macOS, text inserted outside a key press without a composition (the emoji picker) is reported as `Ime::Commit`; it was dropped. Port of the emoji-picker part of [winit#4749](https://github.com/rust-windowing/winit/pull/4749) (0.30 backport of [winit#4748](https://github.com/rust-windowing/winit/pull/4748)); its `selectedRange` change for dictation is left out because it switches on press-and-hold for every held key (an accent menu instead of key repeat, and the chosen accent added after the repeated letters); (9) on macOS, a key whose text was committed through IME isn't also sent as `KeyboardInput` unless AppKit forwards it as a command (Enter): Apple Korean answers Space with no syllable in progress with `setMarkedText(" ")`, `insertText(" ")`, `setMarkedText("")`, and the last call reset winit's state, so the space arrived twice. Same goal as [winit#4478](https://github.com/rust-windowing/winit/pull/4478), whose changes don't reach this call order (macOS 14); to be proposed upstream there; (10) on macOS, when the first key in a fresh app reaches Apple Korean's `insertText` as a raw compatibility jamo instead of starting a composition, that key is interpreted once more, synchronously, before it is sent as `KeyboardInput` (g k s typed ㅎㅏㄴ instead of 한); only an unmodified, non-repeated first key whose one callback inserts that same jamo, with IME enabled and nothing composed, focus and input source unchanged, is retried (`ime_startup.rs`). Port of [winit#4744](https://github.com/rust-windowing/winit/pull/4744), with its policy tests.; (11) on X11 without `Xft.dpi`, the scale factor comes from the X screen's configured DPI (its size in pixels and millimetres) before the output's physical density from RandR: Xorg can deliberately run a dense panel at 96 DPI, and only winit applications then looked zoomed; `Xft.dpi` still wins, `WINIT_X11_SCALE_FACTOR` still overrides, and a screen reporting no size keeps the RandR fallback. PdfCraft patch (#1150, replacing the launcher pin proposed in #908). (12) on macOS, `WinitView` answers `mouseDownCanMoveWindow` with the window's `movable_by_window_background` attribute (NO unless asked): NSView answers YES for a view that isn't opaque, so with the transparent title bar and full-size content view PdfCraft uses, AppKit moved the window for any drag that began in the 28 pt title-bar band before the app saw it, and document tabs (which live in that band) could not be dragged to reorder them. The empty strip still moves the window through `ViewportCommand::StartDrag`. PdfCraft patch. The published crate's asset files (`docs/res/*.svg`, `examples/data/*.png`) are left out, so its `window` example doesn't build; (13) on Wayland, pixel-only wheel, wheel-tilt and continuous-source scroll events report `Moved` rather than starting an unterminated finger gesture, so egui follows modifier release instead of keeping Ctrl zoom latched (#991). Finger gestures and unknown sources retain their existing phase policy | (1) `pdfcraft` `tests::winit_carries_the_windows_11_monitor_scale_fix` keeps the patch in the build; the drag itself needs two monitors with different scale factors on Windows 11; (2) `pdfcraft` `tests/winit_wayland_text_input.rs`; the capability change itself needs a Wayland session and an input method; (3) `pdfcraft` `tests/winit_windows_ime_cursor.rs`; composing itself needs the Microsoft Korean IME; (4) `pdfcraft` `tests/winit_windows_hidden_maximized.rs`; the start-up itself needs Windows and a window that was closed maximized; (5) `pdfcraft` `tests/winit_x11_ime_focus.rs`; switching fields itself needs an X11 session and an input method (IBus, fcitx5); (6) `pdfcraft` `tests/winit_macos_ime_commit.rs`; composing itself needs macOS and an input method; (7) `pdfcraft` `tests/winit_macos_ime_discard.rs`; composing itself needs macOS and an input method; (8) `pdfcraft` `tests/winit_macos_emoji_picker.rs`; the picker itself needs macOS; (9) `pdfcraft` `tests/winit_macos_korean_space.rs`; composing itself needs macOS and Apple Korean; (10) `pdfcraft` `tests/winit_macos_korean_first_key.rs` and `ime_startup.rs`'s own tests (run them with `rustc --test`); typing itself needs macOS and Apple Korean; (11) `pdfcraft` `tests/winit_x11_dpi.rs` keeps the patch in the build, and `util::randr` tests the policy (run them in the vendored crate); the scale itself needs an X11 session; (12) `pdfcraft` `tests/winit_macos_title_bar_drag.rs` keeps the patch in the build; the drag itself needs macOS and a pointer; (13) `pdfcraft` `tests/winit_wayland_scroll.rs` compiles the production phase policy and exercises modifier release through egui; live COSMIC confirmation remains open | | egui-wgpu | 0.36.2 | MIT OR Apache-2.0 | (1) `winit::surface_fit`: a window's surface is configured within the device's `max_texture_dimension_2d`, both sides shrunk by one factor that egui then draws at (`pixels_per_point × render_scale`), so the whole window is drawn into the surface (on DX12 it is stretched over the window and lines up with the pointer; wgpu's GL backend copies it unscaled into a corner); the longer side becomes exactly the limit; the depth and MSAA textures follow, and a recreated surface starts again from the window's own size. egui-wgpu configured the window's size as is, and `Surface::configure` panics beyond the limit: a window restored at another monitor's scale (opening an Outlook attachment on a mixed-DPI laptop asked an 8192-pixel device for 8600 × 3423, #577) or stretched across monitors closed PdfCraft, before its window appeared when it happened at start-up ([emilk/egui#8361](https://github.com/emilk/egui/issues/8361)). The published crate leaves out egui's licence files; `LICENSE-APACHE` and `LICENSE-MIT` are from the 0.36.2 tag; (2) `winit::catch_errors`: a new window's surface is configured inside wgpu error scopes (validation, out of memory, internal), and a failure is returned as `WgpuError::ConfigureSurface` (for the root window at start-up eframe returns it as `Error::Wgpu`, which PdfCraft retries with OpenGL); nothing is kept for the window. wgpu's default handler panicked instead, and eframe configures the root surface before the app is created, so a driver that can't configure one closed PdfCraft at launch (a 2015 Intel GPU through wgpu's GL backend timed out waiting for the GPU to go idle, `GpuWaitTimeout`, #519). Unchanged, so still a panic: an error in a later reconfigure (resize, a lost surface), a device lost during the first configure (wgpu reports it only to a callback), and a window shown at zero size (first configured on resize) | (1) `pdfcraft` `tests::a_window_larger_than_the_gpu_limit_gets_a_surface_within_it`, `tests::surface_fit_never_empties_or_overflows_a_surface`, and `tests::vendor_provenance_egui_wgpu_surface_fit_identity`, which keeps the patch in the build and in the paths that size a surface; (2) `pdfcraft` `tests::a_gpu_error_while_a_window_is_set_up_is_returned_not_a_panic` (a real device: an error inside `catch_errors` is returned, not a panic) and `tests::vendor_provenance_egui_wgpu_catch_errors_identity`, which keeps it around `add_surface`'s configure | | vello_common | 0.0.8 | Apache-2.0 OR MIT | (1) `clip::intersect` (the clip step every clipped path passes through) starts its row walk at the first row both paths have strips in, not the earlier of the two first rows. The walk visited every row from the top of the clip for each path (on the A1 sample's full-page canvas, about half its strip rows per stroke), and rows where one path has no strips produce no output, so the strips are unchanged (vello_common 0.1 starts at the later row too). Its cost grew with the page, and a full-page render of the A1 sample was about 30% faster; the output is byte-identical | (1) `clip::tests::intersect_walks_only_rows_both_paths_have_strips` counts the rows the walk visits (`cargo test --manifest-path vendor/vello_common/Cargo.toml`) and fails without the patch; the render crate's pixel tests run through the patched crate | diff --git a/vendor/hayro-interpret/src/context.rs b/vendor/hayro-interpret/src/context.rs index d41f35ee83..de3907b1ff 100644 --- a/vendor/hayro-interpret/src/context.rs +++ b/vendor/hayro-interpret/src/context.rs @@ -218,6 +218,8 @@ impl<'a> Context<'a> { NESTED_PAINTS.with(|n| n.set(0)); CONTENT_LEFT.with(|c| c.set(MAX_PAGE_CONTENT)); CONTENT_TRUNCATED.with(|truncated| truncated.set(false)); + // PdfCraft patch (73): and fresh JBIG2 decoding, which every image of it shares. + hayro_syntax::set_page_jbig2_work(settings.jbig2_work); // PdfCraft patch (55): a fallback left over from another page is not this page's. crate::color::take_color_fallback(); crate::encode::reset_mesh_budget(); diff --git a/vendor/hayro-interpret/src/font/cid.rs b/vendor/hayro-interpret/src/font/cid.rs index 43b558b050..6c4ea2bc9c 100644 --- a/vendor/hayro-interpret/src/font/cid.rs +++ b/vendor/hayro-interpret/src/font/cid.rs @@ -287,13 +287,14 @@ impl Type0Font { } FontType::Cff(c) => { // Map codepoint to glyph name via AFL, and then look it up. - if let Some(name) = glyph_names::get_reverse(character) - && let Some(gid) = c.glyph_index_by_name(name) - { - Some(gid) - } else { - None - } + let by_name = |character: char| { + glyph_names::get_reverse(character).and_then(|name| c.glyph_index_by_name(name)) + }; + // PdfCraft patch: a soft hyphen the substitute has no glyph for is its hyphen + // (#5888). Windows exporters map the hyphen glyph of a font they don't embed to + // U+00AD, which ISO 32000-2 Annex D.2 calls typographically the same as the + // hyphen; without this the CID, taken as a glyph index, drew an unrelated glyph. + by_name(character).or_else(|| (character == '\u{00ad}').then(|| by_name('-')).flatten()) } FontType::Type1(_) => { // We could in theory map to a glyph via AFL and then look up diff --git a/vendor/hayro-interpret/src/interpret/mod.rs b/vendor/hayro-interpret/src/interpret/mod.rs index 58213439ac..332000e248 100644 --- a/vendor/hayro-interpret/src/interpret/mod.rs +++ b/vendor/hayro-interpret/src/interpret/mod.rs @@ -120,6 +120,10 @@ pub struct InterpreterSettings { /// costs a decode and a resample each for pixels nobody can see. Never set it for a final /// render (tiles, whole pages, print, export). pub preview: bool, + /// PdfCraft patch (73): the steps of JBIG2 decoding a page's images may take between them + /// ([`hayro_syntax::MAX_PAGE_JBIG2_WORK`] by default). Images past it aren't drawn, nor images + /// whose masks are past it, each with [`InterpreterWarning::ContentTruncated`]. + pub jbig2_work: u64, } impl Default for InterpreterSettings { @@ -142,6 +146,7 @@ impl Default for InterpreterSettings { ocg_overrides: Arc::new(Vec::new()), cancelled: None, preview: false, + jbig2_work: hayro_syntax::MAX_PAGE_JBIG2_WORK, } } } @@ -163,12 +168,25 @@ pub enum InterpreterWarning { ColorFallback, } +/// PdfCraft patch (73): ends a page's JBIG2 allowance with the page, so that what decodes on its +/// thread afterwards has no page to run out on. +struct PageJbig2Work; + +impl Drop for PageJbig2Work { + fn drop(&mut self) { + hayro_syntax::set_page_jbig2_work(u64::MAX); + } +} + /// interpret the contents of the page and render them into the device. pub fn interpret_page<'a>( page: &Page<'a>, context: &mut Context<'a>, device: &mut impl Device<'a>, ) { + // PdfCraft patch (73): a context used again is another page. + hayro_syntax::set_page_jbig2_work(context.settings.jbig2_work); + let _allowance = PageJbig2Work; let resources = page.resources(); let mut content = page.content_reader(); // PdfCraft patch: the page's own contents count against its content budget too, where they diff --git a/vendor/hayro-interpret/src/x_object.rs b/vendor/hayro-interpret/src/x_object.rs index cfdd969faf..6fcb34a5d7 100644 --- a/vendor/hayro-interpret/src/x_object.rs +++ b/vendor/hayro-interpret/src/x_object.rs @@ -681,13 +681,23 @@ fn decoded_mask_size(mask: &DecodedMask) -> usize { /// `/Filter` or its inline abbreviation `/F`. Errs towards `true`: a name the decoder would /// ignore still counts, which only keeps the target in the key as before. fn uses_jpx(stream: &Stream<'_>) -> bool { + uses_filter(stream, JPX_DECODE) +} + +/// PdfCraft patch (73): whether `stream` is JBIG2, so that what the page has left, which all of it +/// shares, says something about why this stream failed. +fn uses_jbig2(stream: &Stream<'_>) -> bool { + uses_filter(stream, JBIG2_DECODE) +} + +fn uses_filter(stream: &Stream<'_>, filter: &[u8]) -> bool { let dict = stream.dict(); - let is_jpx = |name: &Name<'_>| name.deref() == JPX_DECODE; + let is_filter = |name: &Name<'_>| name.deref() == filter; [F, FILTER].into_iter().any(|key| { - dict.get::>(key).is_some_and(|name| is_jpx(&name)) + dict.get::>(key).is_some_and(|name| is_filter(&name)) || dict .get::>(key) - .is_some_and(|filters| filters.iter::>().any(|name| is_jpx(&name))) + .is_some_and(|filters| filters.iter::>().any(|name| is_filter(&name))) }) } @@ -755,7 +765,15 @@ fn decode_context<'a>( let decoded = obj .stream .decoded_image(&decode_params) - .map_err(|_| (obj.warning_sink)(InterpreterWarning::ImageDecodeFailure)) + .map_err(|_| { + // PdfCraft patch (73): left out for the page's allowance, it is content the page's + // budget skipped, which is reported, and no failure of this image. + (obj.warning_sink)(if hayro_syntax::page_jbig2_work_spent() && uses_jbig2(&obj.stream) { + InterpreterWarning::ContentTruncated + } else { + InterpreterWarning::ImageDecodeFailure + }); + }) .ok()?; let (mut scale_x, mut scale_y) = (1.0, 1.0); @@ -1008,6 +1026,15 @@ fn decode_raster( .flatten() }; + // PdfCraft patch (73): a bad mask leaves the image as it is, but one left out for the page's + // allowance takes the image with it. Both are reported, and only here is the file not to blame + // for what the mask would have hidden being shown. + let dict = obj.stream.dict(); + let mask = dict.get::>(SMASK).or_else(|| dict.get::>(MASK)); + if alpha.is_none() && hayro_syntax::page_jbig2_work_spent() && mask.is_some_and(|m| uses_jbig2(&m)) { + return None; + } + Some(DecodedRaster { image, alpha }) } diff --git a/vendor/hayro-jbig2/src/lib.rs b/vendor/hayro-jbig2/src/lib.rs index b8ab097b76..2ee0f8f050 100644 --- a/vendor/hayro-jbig2/src/lib.rs +++ b/vendor/hayro-jbig2/src/lib.rs @@ -195,11 +195,37 @@ impl<'a> Image<'a> { /// This is useful in case you want to convert multiple JBIG2 images, /// as it allows `hayro-jbig2` to reuse allocations during decoding. pub fn decode_with(&self, decoder: &mut D, ctx: &mut DecoderContext) -> Result<()> { - decode_segments(&self.segments, self.height_from_stripes, ctx)?; + let mut work_left = bitmap::MAX_WORK; + decode_segments(&self.segments, self.height_from_stripes, ctx, &mut work_left)?; emit_bitmap(&ctx.page_bitmap, decoder); Ok(()) } + + /// PdfCraft patch: [`Image::decode`], spending from `work`, what decoding may still cost + /// across a run of images. An image spends what it took, failing or not, starting with its + /// page's pixels, which whoever asked for them will go through, and its segments, so images + /// that decode nothing add up too. On top of that, it takes at most [`bitmap::MAX_WORK`] + /// whatever `work` says. One that `work` can't pay for spends all of it, so a run ends rather + /// than trying every image it has left. Reading the stream comes before this and is charged + /// by [`charge_reading`]. + pub fn decode_within(&self, decoder: &mut D, work: &mut u64) -> Result<()> { + let start = bitmap::decode_work(self.width, self.height).saturating_add(self.segments.len() as u64); + if charge_work(work, start).is_err() { + *work = 0; + bail!(OverflowError::DecodingWork); + } + let allowed = bitmap::MAX_WORK.min(*work); + let mut left = allowed; + let mut ctx = DecoderContext::default(); + let decoded = decode_segments(&self.segments, self.height_from_stripes, &mut ctx, &mut left); + let refused = decoded == Err(OverflowError::DecodingWork.into()); + *work = if refused && allowed < bitmap::MAX_WORK { 0 } else { *work - (allowed - left) }; + decoded?; + emit_bitmap(&ctx.page_bitmap, &mut *decoder); + + Ok(()) + } } fn emit_bitmap(bitmap: &Bitmap, decoder: &mut D) { @@ -259,13 +285,29 @@ fn emit_bitmap(bitmap: &Bitmap, decoder: &mut D) { } } -/// PdfCraft patch: count `work` more decoding work, refusing past [`bitmap::MAX_WORK`] before what -/// asks for it is decoded. +/// PdfCraft patch: count `work` more decoding work, refusing past what is `left` of +/// [`bitmap::MAX_WORK`] or a run's allowance before what asks for it is decoded. fn charge_work(left: &mut u64, work: u64) -> Result<()> { *left = left.checked_sub(work).ok_or(OverflowError::DecodingWork)?; Ok(()) } +/// PdfCraft patch: the steps of reading a byte of a stream or its globals: parsing and sorting +/// segments, and building their tables, measured at about 3 a byte at the worst. +const READ_WORK: u64 = 4; + +/// PdfCraft patch: charge `work`, what a run of images may still cost, for reading `bytes` of a stream +/// and its globals. This comes before anything is parsed, as it counts whether or not they turn out +/// to decode: an image that fails has still cost its reading, and it is read again for each use. What +/// `work` can't pay for spends all of it. +pub fn charge_reading(work: &mut u64, bytes: usize) -> Result<()> { + if charge_work(work, (bytes as u64).saturating_mul(READ_WORK)).is_err() { + *work = 0; + bail!(OverflowError::DecodingWork); + } + Ok(()) +} + /// PdfCraft patch: the work of a region decoded pixel by pixel. fn region_work(region: &decode::RegionSegmentInfo) -> u64 { bitmap::decode_work(region.width, region.height) @@ -275,6 +317,7 @@ fn decode_segments( segments: &[segment::Segment<'_>], height_from_stripes: Option, decoder_ctx: &mut DecoderContext, + work_left: &mut u64, ) -> Result<()> { // Find and parse page information segment first. if let Some(page_info) = segments @@ -295,7 +338,6 @@ fn decode_segments( let page_bitmap = &mut decoder_ctx.page_bitmap; let page_state = &mut decoder_ctx.page_state; let scratch_buffers = &mut decoder_ctx.scratch_buffers; - let mut work_left = bitmap::MAX_WORK; // Process all segments. for seg in segments { @@ -308,7 +350,7 @@ fn decode_segments( SegmentType::ImmediateGenericRegion | SegmentType::ImmediateLosslessGenericRegion => { let had_unknown_length = seg.header.data_length.is_none(); let header = generic::parse(&mut reader, had_unknown_length)?; - charge_work(&mut work_left, region_work(&header.region_info))?; + charge_work(work_left, region_work(&header.region_info))?; if page_state.can_decode_directly(page_bitmap, &header.region_info, false) { generic::decode_into(&header, page_bitmap, scratch_buffers)?; @@ -326,13 +368,13 @@ fn decode_segments( SegmentType::IntermediateGenericRegion => { // Intermediate segments cannot have unknown length. let header = generic::parse(&mut reader, false)?; - charge_work(&mut work_left, region_work(&header.region_info))?; + charge_work(work_left, region_work(&header.region_info))?; let region = generic::decode(&header, scratch_buffers)?; page_state.store_region(seg.header.segment_number, region.bitmap)?; } SegmentType::PatternDictionary => { let header = pattern::parse(&mut reader)?; - charge_work(&mut work_left, header.work())?; + charge_work(work_left, header.work())?; let dictionary = pattern::decode(&header, scratch_buffers, page_state.retained_room())?; page_state.store_pattern_dictionary(seg.header.segment_number, dictionary)?; } @@ -341,7 +383,7 @@ fn decode_segments( // (6.5.5, step 1) // Collect references to avoid cloning; symbols are only cloned if re-exported. let input_symbols = page_state.referred_symbols(&seg.header.referred_to_segments)?; - charge_work(&mut work_left, input_symbols.len() as u64)?; + charge_work(work_left, input_symbols.len() as u64)?; // Collect Huffman tables from referred table segments. let referred_tables: Vec = seg @@ -368,14 +410,14 @@ fn decode_segments( &page_state.standard_tables, retained_contexts, page_state.retained_room(), - &mut work_left, + work_left, )?; page_state.store_symbol_dictionary(seg.header.segment_number, dictionary)?; } SegmentType::ImmediateTextRegion | SegmentType::ImmediateLosslessTextRegion => { // Collect symbols from referred symbol dictionaries (SBSYMS). let symbols = page_state.referred_symbols(&seg.header.referred_to_segments)?; - charge_work(&mut work_left, symbols.len() as u64)?; + charge_work(work_left, symbols.len() as u64)?; // Collect Huffman tables from referred table segments. // "These user-supplied Huffman decoding tables may be supplied either @@ -389,10 +431,10 @@ fn decode_segments( .collect(); let header = text::parse(&mut reader, symbols.len() as u32)?; - charge_work(&mut work_left, bitmap::copy_work(header.region_info.width, header.region_info.height))?; + charge_work(work_left, bitmap::copy_work(header.region_info.width, header.region_info.height))?; if header.flags.use_huffman { // Its symbol ID table has a line for each symbol. - charge_work(&mut work_left, (symbols.len() as u64).saturating_mul(bitmap::HUFFMAN_LINE_WORK))?; + charge_work(work_left, (symbols.len() as u64).saturating_mul(bitmap::HUFFMAN_LINE_WORK))?; } if page_state.can_decode_directly( @@ -407,7 +449,7 @@ fn decode_segments( &page_state.standard_tables, page_bitmap, scratch_buffers, - &mut work_left, + work_left, )?; } else { let region = text::decode( @@ -416,7 +458,7 @@ fn decode_segments( &referred_tables, &page_state.standard_tables, scratch_buffers, - &mut work_left, + work_left, )?; page_bitmap.combine( ®ion.bitmap, @@ -430,7 +472,7 @@ fn decode_segments( SegmentType::IntermediateTextRegion => { // Collect symbols from referred symbol dictionaries (SBSYMS). let symbols = page_state.referred_symbols(&seg.header.referred_to_segments)?; - charge_work(&mut work_left, symbols.len() as u64)?; + charge_work(work_left, symbols.len() as u64)?; // Collect Huffman tables from referred table segments. let referred_tables: Vec = seg @@ -442,10 +484,10 @@ fn decode_segments( .collect(); let header = text::parse(&mut reader, symbols.len() as u32)?; - charge_work(&mut work_left, bitmap::copy_work(header.region_info.width, header.region_info.height))?; + charge_work(work_left, bitmap::copy_work(header.region_info.width, header.region_info.height))?; if header.flags.use_huffman { // Its symbol ID table has a line for each symbol. - charge_work(&mut work_left, (symbols.len() as u64).saturating_mul(bitmap::HUFFMAN_LINE_WORK))?; + charge_work(work_left, (symbols.len() as u64).saturating_mul(bitmap::HUFFMAN_LINE_WORK))?; } let region = text::decode( &header, @@ -453,7 +495,7 @@ fn decode_segments( &referred_tables, &page_state.standard_tables, scratch_buffers, - &mut work_left, + work_left, )?; page_state.store_region(seg.header.segment_number, region.bitmap)?; } @@ -466,7 +508,7 @@ fn decode_segments( .ok_or(SegmentError::MissingPatternDictionary)?; let header = halftone::parse(&mut reader)?; - charge_work(&mut work_left, halftone::work(&header, pattern_dict))?; + charge_work(work_left, halftone::work(&header, pattern_dict))?; if page_state.can_decode_directly( page_bitmap, @@ -494,7 +536,7 @@ fn decode_segments( .ok_or(SegmentError::MissingPatternDictionary)?; let header = halftone::parse(&mut reader)?; - charge_work(&mut work_left, halftone::work(&header, pattern_dict))?; + charge_work(work_left, halftone::work(&header, pattern_dict))?; let region = halftone::decode(&header, pattern_dict, scratch_buffers)?; page_state.store_region(seg.header.segment_number, region.bitmap)?; } @@ -508,7 +550,7 @@ fn decode_segments( .unwrap_or(page_bitmap); let header = generic_refinement::parse(&mut reader)?; - charge_work(&mut work_left, region_work(&header.region_info))?; + charge_work(work_left, region_work(&header.region_info))?; let region = generic_refinement::decode(&header, reference, scratch_buffers)?; page_state.store_region(seg.header.segment_number, region.bitmap)?; } @@ -526,7 +568,7 @@ fn decode_segments( .and_then(|&num| page_state.get_referred_segment(num)); let header = generic_refinement::parse(&mut reader)?; - charge_work(&mut work_left, region_work(&header.region_info))?; + charge_work(work_left, region_work(&header.region_info))?; if let Some(referred_segment) = referred_segment && page_state.can_decode_directly(page_bitmap, &header.region_info, false) diff --git a/vendor/hayro-syntax/src/filter/jbig2.rs b/vendor/hayro-syntax/src/filter/jbig2.rs index 6f1bfb0768..33a7bc4dd8 100644 --- a/vendor/hayro-syntax/src/filter/jbig2.rs +++ b/vendor/hayro-syntax/src/filter/jbig2.rs @@ -9,6 +9,65 @@ use alloc::vec; use alloc::vec::Vec; use core::iter; +/// PdfCraft patch (31): the steps of decoding a page's JBIG2 images may take between them, as many +/// as one may. Each has its own limit, which doesn't bound a page of many made to reach it. That +/// is about 6 s to 17 s, inside a render's watchdog; an image of the largest size costs a quarter of +/// it to decode and a quarter for its page, and ordinary ones are far below that. +pub const MAX_PAGE_JBIG2_WORK: u64 = 1 << 30; + +#[cfg(feature = "std")] +std::thread_local! { + // Unbounded until a page says otherwise: what isn't drawing a page has no page to run out on. + static PAGE_WORK_LEFT: core::cell::Cell = const { core::cell::Cell::new(u64::MAX) }; +} + +/// PdfCraft patch (31): what the JBIG2 images decoded next on this thread may take, for a new page. +#[cfg(feature = "std")] +pub fn set_page_jbig2_work(work: u64) { + PAGE_WORK_LEFT.with(|left| left.set(work)); +} + +/// Pays for reading `bytes` of a stream and its globals out of what the page has left, or `None`. +/// An image that doesn't decode isn't kept, so a page drawing it again and again reads it again. +#[cfg(feature = "std")] +fn charge_page_reading(bytes: usize) -> Option<()> { + let mut left = PAGE_WORK_LEFT.with(core::cell::Cell::get); + let charged = hayro_jbig2::charge_reading(&mut left, bytes); + PAGE_WORK_LEFT.with(|cell| cell.set(left)); + charged.ok() +} + +#[cfg(not(feature = "std"))] +fn charge_page_reading(_: usize) -> Option<()> { + Some(()) +} + +/// `image` decoded through `decoder`, spending what the page has left, if there is anything. +#[cfg(feature = "std")] +fn decode_for_page(image: &hayro_jbig2::Image<'_>, decoder: &mut D) -> Option<()> { + let mut left = PAGE_WORK_LEFT.with(core::cell::Cell::get); + let decoded = image.decode_within(decoder, &mut left); + PAGE_WORK_LEFT.with(|cell| cell.set(left)); + decoded.ok() +} + +#[cfg(not(feature = "std"))] +fn decode_for_page(image: &hayro_jbig2::Image<'_>, decoder: &mut D) -> Option<()> { + image.decode(decoder).ok() +} + +/// PdfCraft patch (31): whether the page has nothing left for another image, which then isn't read +/// at all. +#[cfg(feature = "std")] +pub fn page_jbig2_work_spent() -> bool { + PAGE_WORK_LEFT.with(core::cell::Cell::get) == 0 +} + +#[cfg(not(feature = "std"))] +pub fn page_jbig2_work_spent() -> bool { + false +} + /// Decode JBIG2 data from a PDF stream. /// /// The `params` dictionary may contain a `JBIG2Globals` entry pointing to @@ -18,6 +77,10 @@ pub(crate) fn decode( params: &Dict<'_>, image_params: &ImageDecodeParams, ) -> Option> { + if page_jbig2_work_spent() { + return None; + } + // PdfCraft patch: globals are raw segments, so JBIG2 inside them means nothing, and decoding // it reads its own globals in turn: a chain of 16,000 such streams overflowed the stack, which // aborts the process. Such a stream reads as globals that can't be decoded. @@ -26,6 +89,8 @@ pub(crate) fn decode( .filter(|g| !g.filters().iter().any(|f| matches!(f, Filter::Jbig2Decode))) .and_then(|g| g.decoded().ok()); + charge_page_reading(data.len().saturating_add(globals.as_deref().map_or(0, <[u8]>::len)))?; + let image = hayro_jbig2::Image::new_embedded(data, globals.as_deref()).ok()?; // Whenever possible (if we don't have an indexed color space), we convert @@ -60,7 +125,7 @@ pub(crate) fn decode( let writer = BitWriter::new(&mut packed, 1)?; let mut decoder = BitWriterDecoder { writer }; - image.decode(&mut decoder).ok()?; + decode_for_page(&image, &mut decoder)?; (packed, 1) } else { @@ -83,7 +148,7 @@ pub(crate) fn decode( } let mut decoder = Luma8Decoder { output: Vec::new() }; - image.decode(&mut decoder).ok()?; + decode_for_page(&image, &mut decoder)?; (decoder.output, 8) }; diff --git a/vendor/hayro-syntax/src/filter/mod.rs b/vendor/hayro-syntax/src/filter/mod.rs index 06bda29487..e81a37df98 100644 --- a/vendor/hayro-syntax/src/filter/mod.rs +++ b/vendor/hayro-syntax/src/filter/mod.rs @@ -9,6 +9,10 @@ mod dct; #[cfg(feature = "images")] mod jbig2; #[cfg(feature = "images")] +pub use jbig2::{MAX_PAGE_JBIG2_WORK, page_jbig2_work_spent}; +#[cfg(all(feature = "images", feature = "std"))] +pub use jbig2::set_page_jbig2_work; +#[cfg(feature = "images")] mod jpx; mod lzw_flate; mod run_length; diff --git a/vendor/hayro-syntax/src/xref.rs b/vendor/hayro-syntax/src/xref.rs index 356bad6b15..d3ab7d324f 100644 --- a/vendor/hayro-syntax/src/xref.rs +++ b/vendor/hayro-syntax/src/xref.rs @@ -4,6 +4,7 @@ use crate::crypto::{DecryptionError, DecryptionTarget, Decryptor, get}; use crate::data::Data; use crate::metadata::Metadata; use crate::object::Name; +use crate::object::Number; use crate::object::ObjectIdentifier; use crate::object::Stream; use crate::object::dict::keys::{ @@ -80,6 +81,65 @@ pub(crate) fn fallback(data: PdfData, password: &[u8]) -> Option { } } +/// PdfCraft patch: an `N G obj` header for the repair scan, taking a generation number that +/// cannot be read as 0. +/// +/// A generation number is at most 65,535 (ISO 32000-2 §7.5.4), so `3 18446744073709551616 obj` is +/// malformed and [`ObjectIdentifier::read`] is right to refuse it everywhere else. This scan runs +/// only when a file's cross-reference table is unusable and its objects are being recovered by +/// reading the file, where refusing the header drops the object and whatever it holds (#5580). +/// Before #427 the digits wrapped, and 2^64 wrapped to exactly 0, which is the only reason such a +/// file used to open. +/// +/// Only here: reading numbers anywhere else is unchanged. +fn read_object_header<'a>(r: &mut Reader<'a>, ctx: &ReaderContext<'a>) -> Option { + let mut strict = r.clone(); + if let Some(obj_id) = strict.read::(ctx) { + *r = strict; + return Some(obj_id); + } + // On a clone as well, so a header that isn't one leaves `r` where it was for the caller. + let mut lenient = r.clone(); + let obj_number = lenient.read_without_context::()?; + lenient.skip_white_spaces_and_comments(); + // Any number at all in the generation position, including one no generation may be. + lenient.skip::(false)?; + lenient.skip_white_spaces_and_comments(); + lenient.forward_tag(b"obj")?; + *r = lenient; + Some(ObjectIdentifier::new(obj_number, 0)) +} + +/// PdfCraft patch: the body of the object at `offset` whose `N G obj` header cannot be read +/// strictly, for a table rebuilt by scanning the file (#5580). The steps are +/// `IndirectObject::read`'s, with [`read_object_header`] in place of the strict identifier. +fn read_repaired_body<'a, T>( + data: &'a [u8], + offset: usize, + id: ObjectIdentifier, + ctx: &ReaderContext<'a>, +) -> Option +where + T: ObjectLike<'a>, +{ + let mut r = Reader::new(data); + r.jump(offset); + // The number is what identifies the object; the generation is what could not be read. + if read_object_header(&mut r, ctx)?.obj_number != id.obj_number { + return None; + } + let mut ctx = ctx.clone(); + if ctx.parent_chain_contains(&id) { + warn!("cycle detected in indirect object: {id:?}"); + + return None; + } + ctx.set_obj_number(id); + ctx.parent_chain_push(id); + r.skip_white_spaces_and_comments(); + r.read_with_context::(&ctx) +} + fn fallback_xref_map<'a>(data: &'a PdfData, password: &[u8]) -> (XrefMap, Option>) { fallback_xref_map_inner(data, ReaderContext::dummy(), true, password) } @@ -91,6 +151,10 @@ fn fallback_xref_map_inner<'a>( password: &[u8], ) -> (XrefMap, Option>) { let mut xref_map = FxHashMap::default(); + // PdfCraft patch: the generation-0 keys below that stand in for a header with another + // generation, so a later header can replace one while a real `N 0 obj` is never displaced + // (noted in review of #5580). + let mut aliases: rustc_hash::FxHashSet = rustc_hash::FxHashSet::default(); let mut trailer_dicts = vec![]; let mut root_ref = None; @@ -105,12 +169,32 @@ fn fallback_xref_map_inner<'a>( // First try to check if we have an object identifier. if r.peek_byte().is_some_and(|b: u8| b.is_ascii_digit()) { - if let Some(obj_id) = r.read::(&dummy_ctx) { + if let Some(obj_id) = read_object_header(&mut r, &dummy_ctx) { let mut cloned = r.clone(); // Check that the object following it is actually valid before inserting it. cloned.skip_white_spaces_and_comments(); if cloned.skip::>(false).is_some() { xref_map.insert(obj_id, EntryType::Normal(cur_pos)); + // PdfCraft patch: also reachable by object number alone, so a reference that + // names a different generation than the header still finds it. A rebuilt + // table has no revision history to tell two generations apart, and a file + // that needs rebuilding references everything as `N 0 R` whatever its headers + // say: `poppler-85140-0.pdf` has one page whose header reads + // `3 18446744073709551616 obj` with a page tree pointing at `3 0 R`, so the + // page was lost and the file did not open at all (#5580). `or_insert`, so a + // real `N 0 obj` is never displaced by this alias. + let by_number = ObjectIdentifier::new(obj_id.obj_number, 0); + if obj_id.gen_number == 0 { + // A real `N 0 obj`: it owns the key from here on, and the last one wins + // as every other entry does. + aliases.remove(&by_number); + } else if !xref_map.contains_key(&by_number) || aliases.contains(&by_number) { + // Stand in for it, and let a later header for the same number replace the + // stand-in -- the exact key moves on, so an alias left behind would send + // `N 0 R` to a body the exact key no longer names (noted in review). + xref_map.insert(by_number, EntryType::Normal(cur_pos)); + aliases.insert(by_number); + } last_obj_num = Some(obj_id); dummy_ctx.set_obj_number(obj_id); } @@ -498,6 +582,14 @@ impl XRef { // Try to yield in the order the objects appeared in the // PDF. elements.sort_by(|e1, e2| e1.1.cmp(&e2.1)); + // PdfCraft patch: one object per location. A rebuilt table can hold two keys for + // one object -- its own generation and the generation-0 stand-in (#5580) -- and + // enumeration yielded the object once for each, so a document recovered by + // `Pages::new_brute_force` reported the page twice (noted in review). Both keys + // stay for lookups; only this walk is deduplicated. The object number is part of + // the key: an object stream at (offset, 0) and its first member, also + // (offset, 0), are two objects. + elements.dedup_by(|a, b| a.1 == b.1 && a.0.obj_number == b.0.obj_number); let mut iter = elements.into_iter(); @@ -653,10 +745,27 @@ impl XRef { } if let Some(object) = r.read_with_context::>(&ctx) { - if object.id() == &id { + // PdfCraft patch: in a table rebuilt by scanning the file, the object number + // is what identifies an object. There is no revision history to tell two + // generations apart, the scan already files objects found in object streams + // under generation 0, and a malformed generation in a header would otherwise + // make the object unreadable through the reference that names it (#5580). A + // table read from the file's own xref keeps the exact match. + if object.id() == &id || (repaired && object.id().obj_number == id.obj_number) { return Some(Fetched::Object(object.get())); } } else { + // PdfCraft patch: the strict read of the header failed. In a table rebuilt by + // scanning the file that can be a generation number no generation may be -- + // `3 18446744073709551616 obj` -- and refusing it loses the object the + // reference names (#5580). The object number still has to be the one asked + // for; only an unreadable generation is tolerated, and only here. + if repaired + && let Some(object) = + read_repaired_body::(repr.data.get().as_ref(), offset, id, &ctx) + { + return Some(Fetched::Object(object)); + } // There is a valid object at the offset, it's just not of the type the caller // expected, which is fine. if r.skip::>>(false).is_some() { @@ -1734,6 +1843,18 @@ mod tests { } } + #[test] + fn an_object_stream_and_its_first_member_are_both_enumerated() { + // Both sit at (stream offset, 0) in `objects`' ordering; one object per location must + // not cost either of them. + let pdf = crate::Pdf::new(object_stream_fixture(false)).unwrap(); + let objects: Vec<_> = pdf.xref().objects().into_iter().collect(); + assert!(objects.iter().any(|o| matches!(o, Object::Stream(_)))); + assert!(objects.iter().any( + |o| matches!(o, Object::Dict(d) if d.get::(b"Marker") == Some(123)) + )); + } + #[test] fn recursive_object_stream_locations_fail_without_recursing() { let pdf = crate::Pdf::new(object_stream_fixture(true)).unwrap();