From b85d5199938aec0ceff7012688ff82e1852db482 Mon Sep 17 00:00:00 2001 From: MMexicann Date: Tue, 13 Oct 2026 14:16:44 +0000 Subject: [PATCH 01/44] M6: preserve whitespace in XML and XFDF attributes Encode tabs and line feeds as character references so XML normalization cannot change field names, comment identities or metadata. Add failing-before-fix saved-PDF round-trip regressions. Co-Authored-By: Codex --- ROADMAP.md | 3 ++ crates/xfdf/README.md | 3 ++ crates/xfdf/src/lib.rs | 3 ++ crates/xfdf/src/tests.rs | 102 +++++++++++++++++++++++++++++++++++++++ docs/roadmap.md | 4 +- 5 files changed, 114 insertions(+), 1 deletion(-) diff --git a/ROADMAP.md b/ROADMAP.md index a035c9bf35..1dd67e82e2 100644 --- a/ROADMAP.md +++ b/ROADMAP.md @@ -2,6 +2,7 @@ **Stage: alpha** · next: beta, ~26% (ready for real work 49% → 75%) and ~400–700 h away +> **Last reviewed:** 2026-10-13 · **Last updated:** 2026-10-13 · **Change:** minor (M6: preserve XML/XFDF attribute whitespace; estimates unchanged) · **Target:** Adobe Acrobat Pro (Acrobat DC, continuous track 26.002.21931, macOS) > **Last reviewed:** 2026-10-12 · **Last updated:** 2026-10-12 · **Change:** minor (M13: CLI check visits each directory once through aliases and cycles; estimates unchanged) · **Target:** Adobe Acrobat Pro (Acrobat DC, continuous track 26.002.21931, macOS) > **Last reviewed:** 2026-10-12 · **Last updated:** 2026-10-12 · **Change:** minor (M4: Extract and Split preserve shared Type 3 glyph resources; estimates unchanged) · **Target:** Adobe Acrobat Pro (Acrobat DC, continuous track 26.002.21931, macOS) > **Last reviewed:** 2026-10-12 · **Last updated:** 2026-10-12 · **Change:** minor (M2: packed TIFF-predictor RGB rows retain their byte boundaries; estimates unchanged) · **Target:** Adobe Acrobat Pro (Acrobat DC, continuous track 26.002.21931, macOS) @@ -148,6 +149,7 @@ Ranked; detail and the full milestone table in [docs/roadmap.md](docs/roadmap.md ## Progress log +- **2026-10-13 (M6, data exchange fidelity):** XML and XFDF exports preserve tabs and line breaks in field names and comment metadata using character references. Saved-PDF regressions cover distinct names that XML would normalize to the same attribute value, restored field values and replacement of the original comment identities. Estimates unchanged. - **2026-10-12 (M13, CLI robustness scans):** `pdfcraft-cli check` visits a directory once even when input roots overlap or directory symlinks lead back into the tree. PDFs reached through file symlinks remain accepted. Three real CLI regressions cover overlapping roots, a directory cycle and directory/file aliases. Estimates unchanged. - **2026-10-12 (M4, Type 3 extraction fidelity):** Extract and Split preserve shared image/resource dictionaries reached through Type 3 glyphs, including nested forms, patterns and soft masks. A bounded object-graph walk protects unknown glyph content; unreadable pages/forms retain their glyph resources, and shared explicit fonts are visited once. Separate page dictionaries still prune unused images. Synthetic save/reopen regressions and an opt-in Poppler pixel oracle cover resource ownership, nested forms, cycles, limits and repeated fonts. Estimates unchanged. - **2026-10-12 (M2, TIFF predictor rows):** Packed RGB images using TIFF horizontal differencing keep every row when samples do not fill the last byte. The renderer aligns each decoded row before moving to the next. Synthetic decoding tests cover 1/2/4-bit samples, horizontal differencing and an 8-bit control; a red/green page-render regression verifies visible output. Estimates unchanged. @@ -424,6 +426,7 @@ Newest first: the date, what moved, and the new overall estimate. | Date | Change | Summary | |---|---|---| +| 2026-10-13 | minor | M6: XML/XFDF attribute whitespace survives form and comment export/import; estimates unchanged | | 2026-10-12 | minor | M3/#1364 candidate: absolute local GoToR links require desktop consent or headless allow_absolute; existing relative navigation and validation retained. Estimates unchanged. | | 2026-10-12 | minor | M8: redaction retires inherited `/Resources` so a parent `/Pages` can't keep a removed XObject reachable; only redacted pages that inherit are pinned (one shared reference), unredacted pages are untouched; estimates unchanged | | 2026-10-12 | minor | M7/#1200 candidate: bounded local GoToR opening, root-confined automation, and action-preserving appearance edits; named destinations and window behavior remain partial; estimates unchanged. | diff --git a/crates/xfdf/README.md b/crates/xfdf/README.md index fd2852584b..cf21100aa3 100644 --- a/crates/xfdf/README.md +++ b/crates/xfdf/README.md @@ -18,6 +18,9 @@ let report = import(&mut doc, &bytes)?; // XFDF, FDF, XML, CSV o - **Form data**: Acrobat's XML (`xfdf:original` keeps names that aren't XML names), CSV and tab-delimited text (a row of names, a row of values). +XML and XFDF exports preserve tabs and line breaks in field names and comment metadata with +character references, so XML attribute normalization cannot change their identities. + Import replaces comments with the same `/NM` (and drops the replaced comment's pop-up), draws appearances PdfCraft can draw, and sets values through the form's own checks (formats, validation, recalculation); read-only fields take imported values, as in Acrobat. XML is read diff --git a/crates/xfdf/src/lib.rs b/crates/xfdf/src/lib.rs index d9287101ba..c7bc2999d2 100644 --- a/crates/xfdf/src/lib.rs +++ b/crates/xfdf/src/lib.rs @@ -197,6 +197,9 @@ fn esc(s: &str) -> String { '<' => o.push_str("<"), '>' => o.push_str(">"), '"' => o.push_str("""), + // XML 1.0 §3.3.3 normalizes literal attribute whitespace, but not references. + '\t' => o.push_str(" "), + '\n' => o.push_str(" "), '\r' => o.push_str(" "), c if (c as u32) < 0x20 && c != '\n' && c != '\t' => {} c => o.push(c), diff --git a/crates/xfdf/src/tests.rs b/crates/xfdf/src/tests.rs index be747d77e1..9ec1299e0d 100644 --- a/crates/xfdf/src/tests.rs +++ b/crates/xfdf/src/tests.rs @@ -142,6 +142,108 @@ fn values(doc: &Document) -> Vec<(String, Vec)> { fields(doc).into_iter().map(|f| (f.name, f.value)).collect() } +#[test] +fn xml_exports_preserve_whitespace_in_field_names() { + let names = ["Line\nName", "Line\tName", "Line\rName", "Line\r\nName", "\t Leading\nTrailing \t", "Line Name"]; + let value = "value\twith\nlines\r\nand & \"quotes\""; + let mut src = one_field(); + pdfcraft_forms::delete_field(&mut src, "Name").unwrap(); + for (index, name) in names.iter().enumerate() { + let placeholder = format!("field{index}"); + add_field(&mut src, 0, [50.0, 700.0, 250.0, 720.0], &NewField::Text { multiline: true }, Some(&placeholder)).unwrap(); + // Existing PDFs can have leading/trailing whitespace even though add_field trims it. + let field = fields(&src).into_iter().find(|f| f.name == placeholder).unwrap(); + src.update_dict(field.obj, |d| d.set(b"T".to_vec(), PdfString::text(name))).unwrap(); + set_value(&mut src, name, &FieldValue::Text(format!("{index}: {value}"))).unwrap(); + } + let source_bytes = write_full(&src, &SaveOptions::default()).unwrap(); + let src = Document::open(Arc::new(source_bytes.clone())).unwrap(); + for format in [Format::Xml, Format::Xfdf] { + let exported = if format == Format::Xfdf { export_xfdf(&src, false, true, "form.pdf") } else { export_data(&src, format) }; + let xml = roxmltree::Document::parse(&exported).unwrap(); + let exported_names: Vec<_> = if format == Format::Xfdf { + xml.descendants().filter(|n| n.has_tag_name("field")).map(|n| n.attribute("name").unwrap()).collect() + } else { + xml.root_element() + .children() + .filter(|n| n.is_element()) + .map(|n| n.attribute(("http://ns.adobe.com/xfdf-transition/", "original")).unwrap()) + .collect() + }; + assert_eq!(exported_names, names, "{format:?}: {exported}"); + let mut dst = Document::open(Arc::new(source_bytes.clone())).unwrap(); + for name in names { + set_value(&mut dst, name, &FieldValue::Text("replace me".into())).unwrap(); + } + let report = import(&mut dst, exported.as_bytes()).unwrap(); + assert_eq!(report.fields, names.len(), "{format:?}: {report:?}"); + assert!(report.rejected.is_empty(), "{report:?}"); + let saved = write_full(&dst, &SaveOptions::default()).unwrap(); + let reopened = Document::open(Arc::new(saved)).unwrap(); + assert_eq!(values(&reopened), values(&src), "{format:?}"); + } + assert_eq!(write_full(&src, &SaveOptions::default()).unwrap(), source_bytes, "export must not change the source PDF"); +} + +#[test] +fn xfdf_exports_preserve_whitespace_in_comment_attributes() { + let mut src = one_field(); + let shape = Shape::Note { at: [100.0, 500.0], icon: pdfcraft_annot::NoteIcon::Comment }; + let names = ["note\tline\nidentity", "note line identity"]; + let author = "Ada\tLovelace\nReview"; + let subject = "Subject\twith\nlines\r\nand & quotes\""; + for name in names { + add_annotation( + &mut src, + &NewAnnotation { page: 0, style: Style::default_for(&shape), shape: shape.clone(), contents: name.into(), author: author.into() }, + &Meta { id: name.into(), date: None }, + ) + .unwrap(); + } + let annotation_refs = |doc: &Document| { + let page = pdfcraft_model::pages(doc)[0].obj; + doc.get(page) + .as_dict() + .unwrap() + .get(b"Annots") + .map(|a| doc.resolve(a)) + .unwrap() + .as_array() + .unwrap() + .iter() + .filter_map(Object::as_ref) + .filter(|r| doc.get(*r).as_dict().unwrap().name(b"Subtype") == Some(b"Text")) + .collect::>() + }; + for annotation in annotation_refs(&src) { + src.update_dict(annotation, |d| d.set(b"Subj".to_vec(), PdfString::text(subject))).unwrap(); + } + let source_bytes = write_full(&src, &SaveOptions::default()).unwrap(); + let mut dst = Document::open(Arc::new(source_bytes)).unwrap(); + let file = "form\twith\nlines.pdf"; + let xfdf = export_xfdf(&dst, true, false, file); + let xml = roxmltree::Document::parse(&xfdf).unwrap(); + let notes: Vec<_> = xml.descendants().filter(|n| n.has_tag_name("text")).collect(); + assert_eq!(notes.iter().map(|n| n.attribute("name").unwrap()).collect::>(), names); + for note in notes { + assert_eq!(note.attribute("title"), Some(author)); + assert_eq!(note.attribute("subject"), Some(subject)); + } + assert_eq!(xml.descendants().find(|n| n.has_tag_name("f")).unwrap().attribute("href"), Some(file)); + let before = annotation_refs(&dst); + let report = import(&mut dst, xfdf.as_bytes()).unwrap(); + assert_eq!(report.comments, names.len()); + assert_eq!(annotation_refs(&dst), before, "reimport must replace the original comments"); + let saved = write_full(&dst, &SaveOptions::default()).unwrap(); + let reopened = Document::open(Arc::new(saved)).unwrap(); + for (annotation, name) in annotation_refs(&reopened).iter().zip(names) { + let dict = reopened.get(*annotation); + assert_eq!(text_of(&reopened, dict.as_dict().unwrap(), b"NM").as_deref(), Some(name)); + assert_eq!(text_of(&reopened, dict.as_dict().unwrap(), b"T").as_deref(), Some(author)); + assert_eq!(text_of(&reopened, dict.as_dict().unwrap(), b"Subj").as_deref(), Some(subject)); + } +} + #[test] fn xfdf_round_trips_comments_and_values() { let src = filled(); diff --git a/docs/roadmap.md b/docs/roadmap.md index 04103fb632..417b95aa90 100644 --- a/docs/roadmap.md +++ b/docs/roadmap.md @@ -1,5 +1,6 @@ # PdfCraft roadmap: milestones and what's next +> **Last reviewed:** 2026-10-13 · **Last updated:** 2026-10-13 · **Change:** minor (M6: preserve XML/XFDF attribute whitespace; estimates unchanged) · **Target:** Adobe Acrobat Pro (Acrobat DC, continuous track 26.002.21931, macOS) > **Last reviewed:** 2026-10-12 · **Last updated:** 2026-10-12 · **Change:** minor (M13: CLI check visits each directory once through aliases and cycles; estimates unchanged) · **Target:** Adobe Acrobat Pro (Acrobat DC, continuous track 26.002.21931, macOS) > **Last reviewed:** 2026-10-12 · **Last updated:** 2026-10-12 · **Change:** minor (M4: Extract and Split preserve shared Type 3 glyph resources; estimates unchanged) · **Target:** Adobe Acrobat Pro (Acrobat DC, continuous track 26.002.21931, macOS) > **Last reviewed:** 2026-10-12 · **Last updated:** 2026-10-12 · **Change:** minor (M2: packed TIFF-predictor RGB rows retain their byte boundaries; estimates unchanged) · **Target:** Adobe Acrobat Pro (Acrobat DC, continuous track 26.002.21931, macOS) @@ -99,7 +100,7 @@ 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: 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: 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); 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 | -| 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.
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 | +| 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. XML/XFDF exports preserve tabs and line breaks in names and comment metadata.
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 | | 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. 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). 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). Missing: editing existing text and images in place (the longest pole), watermark print/screen visibility and repeat | @@ -161,6 +162,7 @@ M2 (renderer), M7 (content editing), M10 (OCR and Office), M11 (Preflight and st | Date | Change | Summary | |---|---|---| +| 2026-10-13 | minor | M6: XML/XFDF attribute whitespace survives form and comment export/import; estimates unchanged | | 2026-10-12 | minor | M13: CLI check directory identity, with overlap and symlink regressions; estimates unchanged | | 2026-10-12 | minor | M4: shared Type 3 glyph resources survive extraction, with save/reopen and independent raster regressions; estimates unchanged | | 2026-10-12 | minor | M2: packed TIFF-predictor RGB row boundaries, with decoding and page-render regressions; estimates unchanged | From 893cb7430eee01c924d367a2ec61a7ae22a4af7a Mon Sep 17 00:00:00 2001 From: Mex <44814932+MMexicann@users.noreply.github.com> Date: Wed, 14 Oct 2026 21:58:05 +0200 Subject: [PATCH 02/44] M1: preserve output-limit errors in raw Flate fallback --- ROADMAP.md | 4 ++++ crates/cos/src/object.rs | 13 +++++++++++++ crates/filters/README.md | 2 +- crates/filters/src/flate.rs | 7 ++++++- crates/filters/src/lib.rs | 20 ++++++++++++++++++++ docs/gaps.md | 5 +++++ docs/roadmap.md | 4 +++- parity/acrobat-features.toml | 4 ++-- 8 files changed, 54 insertions(+), 5 deletions(-) diff --git a/ROADMAP.md b/ROADMAP.md index b4ab4ea8a6..8f8a2056a5 100644 --- a/ROADMAP.md +++ b/ROADMAP.md @@ -2,6 +2,7 @@ **Stage: alpha** · next: beta, ~26% (ready for real work 49% → 75%) and ~400–700 h away +> **Last reviewed:** 2026-10-14 · **Last updated:** 2026-10-14 · **Change:** minor (M1: raw-deflate fallback preserves decoding-limit errors; estimates unchanged) · **Target:** Adobe Acrobat Pro (Acrobat DC, continuous track 26.002.21931, macOS) > **Last reviewed:** 2026-10-13 · **Last updated:** 2026-10-13 · **Change:** minor (M3 candidate: native opens retain chosen tools through password retries and defer startup intake while preparation is pending; estimates unchanged) · **Target:** Adobe Acrobat Pro (Acrobat DC, continuous track 26.002.21931, macOS) > **Last reviewed:** 2026-10-12 · **Last updated:** 2026-10-12 · **Change:** minor (M13: CLI check visits each directory once through aliases and cycles; estimates unchanged) · **Target:** Adobe Acrobat Pro (Acrobat DC, continuous track 26.002.21931, macOS) > **Last reviewed:** 2026-10-12 · **Last updated:** 2026-10-12 · **Change:** minor (M4: Extract and Split preserve shared Type 3 glyph resources; estimates unchanged) · **Target:** Adobe Acrobat Pro (Acrobat DC, continuous track 26.002.21931, macOS) @@ -149,6 +150,8 @@ Ranked; detail and the full milestone table in [docs/roadmap.md](docs/roadmap.md ## Progress log +- **2026-10-14 (M1, Flate fallback):** Raw deflate whose first bytes resemble a zlib header no longer loses a decoding-limit error during fallback. Strict and tolerant filter regressions and a COS stream regression cover refusal at the caller limit and successful decoding within it. No parity status or estimate changes. + - **2026-10-13 (M3, native-opening candidate):** Chosen tools survive preparation, conversion and password retries; startup intake waits for pending preparation. Regression tests cover completion, cancellation and document identity. Estimates unchanged. - **2026-10-12 (M10, Windows printing without PowerShell, #1107):** craft-print now prints on Windows in-process: printers from EnumPrinters/GetDefaultPrinter, jobs drawn as vectors by Windows.Data.Pdf into the XPS print API with a driver-validated PrintTicket (exact paper, orientation, no scaling), so printing works where App Control for Business or AppLocker run PowerShell in Constrained Language Mode. Portrait and landscape sheets still print as one job (turned with /Rotate); a sheet size the driver lacks is refused rather than shrunk. Pins craft-libs f03ec27 (craft-libs#28); deny.toml allows the storytold/winprint.rs fork and adds a webpki-root-certs licence exception and a RUSTSEC-2024-0370 ignore for winprint's build-dependencies. An earlier craft-print revision was checked in Windows Sandbox under enforced WDAC: printers listed, CLI and desktop jobs spooled, and no powershell.exe in the 4688 audit. The final pinned revision passed craft-libs Windows CI, including a real paused-queue job; that Sandbox run has not been repeated. Estimates unchanged. - **2026-10-12 (M13, CLI robustness scans):** `pdfcraft-cli check` visits a directory once even when input roots overlap or directory symlinks lead back into the tree. PDFs reached through file symlinks remain accepted. Three real CLI regressions cover overlapping roots, a directory cycle and directory/file aliases. Estimates unchanged. @@ -427,6 +430,7 @@ Newest first: the date, what moved, and the new overall estimate. | Date | Change | Summary | |---|---|---| +| 2026-10-14 | minor | M1: raw-deflate fallback preserves decoding-limit errors in strict and tolerant decoding; synthetic filter and COS stream regressions. Estimates unchanged. | | 2026-10-12 | minor | M3/#1364 candidate: absolute local GoToR links require desktop consent or headless allow_absolute; existing relative navigation and validation retained. Estimates unchanged. | | 2026-10-12 | minor | M8: redaction retires inherited `/Resources` so a parent `/Pages` can't keep a removed XObject reachable; only redacted pages that inherit are pinned (one shared reference), unredacted pages are untouched; estimates unchanged | | 2026-10-12 | minor | M7/#1200 candidate: bounded local GoToR opening, root-confined automation, and action-preserving appearance edits; named destinations and window behavior remain partial; estimates unchanged. | diff --git a/crates/cos/src/object.rs b/crates/cos/src/object.rs index dc7648d4f9..438b8d5f35 100644 --- a/crates/cos/src/object.rs +++ b/crates/cos/src/object.rs @@ -482,6 +482,19 @@ mod tests { assert_eq!(stream.decoded_strict().unwrap(), b"abc"); } + #[test] + fn raw_flate_fallback_streams_preserve_the_caller_limit() { + // Raw deflate with a stored byte and a final empty block. 78 01 also + // passes the zlib header check, so decoding must retry the whole input. + let mut dict = Dict::new(); + dict.set(b"Filter".to_vec(), Object::name("FlateDecode")); + let stream = Stream::from_raw(dict, vec![0x78, 0x01, 0x00, 0xfe, 0xff, b'A', 0x01, 0x00, 0x00, 0xff, 0xff]); + let result = stream.decoded_within(0); + assert!(matches!(&result, Err(CosError::Filter(detail)) if detail.contains("exceeds the limit of 0 bytes")), "{result:?}"); + assert_eq!(stream.decoded_within(1).unwrap(), b"A"); + assert_eq!(stream.decoded_strict().unwrap(), b"A"); + } + #[test] fn first_filter_decodes_only_the_outer_wrapper() { let data = "0 0 m 100 100 l S\n".repeat(64).into_bytes(); diff --git a/crates/filters/README.md b/crates/filters/README.md index de7f8d2230..df64e4b7c0 100644 --- a/crates/filters/README.md +++ b/crates/filters/README.md @@ -24,7 +24,7 @@ encode_flate(data) -> Vec // zlib, level 6 - `chain` is applied first to last, as in a `/Filter` array. - Image codecs (DCT, JPX, JBIG2, CCITT), `Crypt` and unknown filters anywhere in a chain give `Unsupported`: callers keep such data encoded. Decryption belongs to `crypt`. -- `max_output` bounds every intermediate buffer (including the pre-predictor buffer) and gives `LimitExceeded(max_output)`. +- `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_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/flate.rs b/crates/filters/src/flate.rs index 5aa6443f69..dac0851e07 100644 --- a/crates/filters/src/flate.rs +++ b/crates/filters/src/flate.rs @@ -26,7 +26,12 @@ pub(crate) fn decode(data: &[u8], max: usize) -> Step { Some((_, flg)) if flg & 0x20 != 0 => Err(Failure::corrupt(NAME, "zlib preset dictionary is not allowed in PDF", Vec::new())), Some(_) => match inflate_raw(&data[2..], max) { // 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 { .. }) => inflate_raw(data, max).map_err(|_| f), + 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), + retry => retry, + }, r => r, }, None => inflate_raw(data, max), diff --git a/crates/filters/src/lib.rs b/crates/filters/src/lib.rs index ffaf08ca11..9a0124d859 100644 --- a/crates/filters/src/lib.rs +++ b/crates/filters/src/lib.rs @@ -295,6 +295,26 @@ mod tests { assert_eq!(decode(&chain, &hex, 100).unwrap().len(), 100); } + #[test] + fn raw_flate_fallback_preserves_output_limits() { + // RFC 1951 stored blocks: the first is nonfinal with LEN=257 and + // NLEN=!257, followed by a final empty block. Its ignored alignment + // bits make the first two bytes also look like a valid zlib header. + let data = vec![b'A'; 257]; + let mut raw = vec![0x78, 0x01, 0x01, 0xfe, 0xfe]; + raw.extend_from_slice(&data); + raw.extend_from_slice(&[0x01, 0x00, 0x00, 0xff, 0xff]); + let chain = [(Filter::Flate, Params::default())]; + for max in [0, 1, 128, 256] { + assert!(matches!(decode(&chain, &raw, max), Err(FilterError::LimitExceeded(m)) if m == max)); + assert!(matches!(decode_tolerant(&chain, &raw, max), Err(FilterError::LimitExceeded(m)) if m == max)); + } + for max in [257, 258] { + assert_eq!(decode(&chain, &raw, max).unwrap(), data); + assert_eq!(decode_tolerant(&chain, &raw, max).unwrap(), (data.clone(), false)); + } + } + #[test] fn tolerant_flate_returns_partial() { let data: Vec = (0..20_000u32).map(|i| (i % 97) as u8 ^ (i / 300) as u8).collect(); diff --git a/docs/gaps.md b/docs/gaps.md index 4c235c1745..457a868fcb 100644 --- a/docs/gaps.md +++ b/docs/gaps.md @@ -1,5 +1,6 @@ # Where PdfCraft falls short of Acrobat Pro +> **Last reviewed:** 2026-10-14 · **Last updated:** 2026-10-14 · **Change:** minor (M1: raw-deflate fallback preserves decoding-limit errors; estimates unchanged) · **Target:** Adobe Acrobat Pro (Acrobat DC, continuous track 26.002.21931, macOS) > **Last reviewed:** 2026-10-12 · **Last updated:** 2026-10-12 · **Change:** minor (gap 6: #1398 stamps read upright on rotated pages; estimates unchanged) · **Target:** Adobe Acrobat Pro (Acrobat DC, continuous track 26.002.21931, macOS) > **Last reviewed:** 2026-10-12 · **Last updated:** 2026-10-12 · **Change:** minor (gap 6: #1317, #1327, #1302, #1315 and #1340; estimates unchanged) · **Target:** Adobe Acrobat Pro (Acrobat DC, continuous track 26.002.21931, macOS) > **Last reviewed:** 2026-10-10 · **Last updated:** 2026-10-12 · **Change:** minor (#1316: replacing a line keeps a neighbouring line whose glyph box overlaps; gap 3 remains) · **Target:** Adobe Acrobat Pro (Acrobat DC, continuous track 26.002.21931, macOS) @@ -136,6 +137,9 @@ update the numbers. resize unchanged (#1327), keeps arrow defaults off plain lines (#1302), stops a custom text match on the separator instead of the next glyph (#1315), and states the vertical-text redaction refusal without claiming an overlap (#1340). The rest of the backlog is untriaged. +- **Fix verified (2026-10-14):** raw-deflate fallback returns a decoding-limit error instead of + accepting an empty partial stream when a misleading zlib header triggers a retry. Synthetic + filter and COS stream regressions cover refusal at the limit and decoding within it. - **Impact:** every one is a user who lost trust. Crash reports outrank feature work (`AGENTS.md` §4). - **Estimate:** 45–80 h (≈ 0.2–0.4 h per issue). **Doc:** this file. @@ -324,6 +328,7 @@ update the numbers. | Date | Change | Summary | |---|---|---| +| 2026-10-14 | minor | M1: raw-deflate fallback preserves decoding-limit errors in strict and tolerant decoding; synthetic filter and COS stream regressions. Estimates unchanged. | | 2026-10-12 | minor | Gap 6: rubber stamps, explicit image rectangles and PDF-page stamps read upright on rotated pages (#1398). Estimates unchanged. | | 2026-10-12 | minor | #1316: replacing a line or paragraph keeps a neighbouring line whose glyph box overlaps. Gap 3 remains. Estimates unchanged. | | 2026-10-12 | minor | Exclusive image crops resize with their pixels across nested states, intervening operators and content streams; shared clips remain fixed. Synthetic engine/tool regressions and private image save/reopen checks; estimates unchanged. | diff --git a/docs/roadmap.md b/docs/roadmap.md index fabb5e603d..8da76e0d24 100644 --- a/docs/roadmap.md +++ b/docs/roadmap.md @@ -1,5 +1,6 @@ # PdfCraft roadmap: milestones and what's next +> **Last reviewed:** 2026-10-14 · **Last updated:** 2026-10-14 · **Change:** minor (M1: raw-deflate fallback preserves decoding-limit errors; estimates unchanged) · **Target:** Adobe Acrobat Pro (Acrobat DC, continuous track 26.002.21931, macOS) > **Last reviewed:** 2026-10-13 · **Last updated:** 2026-10-13 · **Change:** minor (M3 candidate: native opens retain chosen tools through password retries and defer startup intake while preparation is pending; estimates unchanged) · **Target:** Adobe Acrobat Pro (Acrobat DC, continuous track 26.002.21931, macOS) > **Last reviewed:** 2026-10-12 · **Last updated:** 2026-10-12 · **Change:** minor (M13: CLI check visits each directory once through aliases and cycles; estimates unchanged) · **Target:** Adobe Acrobat Pro (Acrobat DC, continuous track 26.002.21931, macOS) > **Last reviewed:** 2026-10-12 · **Last updated:** 2026-10-12 · **Change:** minor (M4: Extract and Split preserve shared Type 3 glyph resources; estimates unchanged) · **Target:** Adobe Acrobat Pro (Acrobat DC, continuous track 26.002.21931, macOS) @@ -88,7 +89,7 @@ total matches the parity estimate. | M | Milestone | Plan size (h) | Done | Remaining (h, 2026-10-10) | Notes | |---|---|---|---|---|---| | M0 | Skeleton: workspace, xtask gates, CI | 15–30 | 98% | 1–2 | GitHub workflow, `deny.toml` (licence audit of every dependency), parity checklist (826 features, `xtask parity`) done. Missing: remaining crate stubs, testkit/oracle crates | -| M1 | COS: filters, crypt, parser, xref, writer | 120–200 | 80% | 20–40 | Done:
- filters and crypt: every standard-security revision R2–R6 (RC4, AES-128/256), SASLprep, permissions, creating encryption;
- cos: parse and repair (including invalid xref object-number ranges), decoded-stream limits including unfiltered data, decrypt on load, re-encrypt on save, incremental and full writing.
Corpus: open/edit/save passes on 958 files, and all 7 password-protected files open.
Full saves now pack objects into compressed object streams. An unchanged incremental save of a classic table writes a zero-length cross-reference subsection instead of a section with no subsections (#1339). Fuzzing runs nightly (`xtask fuzz`). Missing: ≥ 250 tests, own image codecs | +| M1 | COS: filters, crypt, parser, xref, writer | 120–200 | 80% | 20–40 | Done:
- filters and crypt: every standard-security revision R2–R6 (RC4, AES-128/256), SASLprep, permissions, creating encryption;
- cos: parse and repair (including invalid xref object-number ranges), decoded-stream limits including unfiltered data, decrypt on load, re-encrypt on save, incremental and full writing.
Corpus: open/edit/save passes on 958 files, and all 7 password-protected files open.
Full saves now pack objects into compressed object streams. An unchanged incremental save of a classic table writes a zero-length cross-reference subsection instead of a section with no subsections (#1339). Fuzzing runs nightly (`xtask fuzz`). Raw-deflate fallback preserves decoding-limit errors, including through tolerant COS stream decoding. Missing: ≥ 250 tests, own image codecs | | M2 | Model, render, text | 200–350 | 15% | 130–230 | hayro bootstrap renderer (vendored patches); inspector predictor scratch is bounded by available input, and JPX sample rescaling handles 1–32 bits safely. Text extraction reaches word-F1 0.98 against pdftotext. Short same-line redraws split before placement rather than interleaving. Missing: model crate, fonts, DisplayList, renderer independent of hayro. Inspector page-label traversal and output are resource-bounded, with physical-number fallback warnings. Packed TIFF-predictor RGB rows retain later rows in decoding and rendering. | | M2 | Model, render, text | 200–350 | 15% | 130–230 | hayro bootstrap renderer (vendored patches); inspector predictor scratch is bounded by available input, and JPX sample rescaling handles 1–32 bits safely. Text extraction reaches word-F1 0.98 against pdftotext. Short same-line redraws split before placement rather than interleaving. Missing: model crate, fonts, DisplayList, renderer independent of hayro. Inspector page-label traversal and output are resource-bounded, with physical-number fallback warnings | | 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). #1364 candidate: absolute local GoToR links ask before target access; headless callers explicitly opt in. Native-opening candidate: chosen tools survive preparation and password retries; startup intake waits for pending preparation. | @@ -162,6 +163,7 @@ M2 (renderer), M7 (content editing), M10 (OCR and Office), M11 (Preflight and st | Date | Change | Summary | |---|---|---| +| 2026-10-14 | minor | M1: raw-deflate fallback preserves decoding-limit errors in strict and tolerant decoding; synthetic filter and COS stream regressions. Estimates unchanged. | | 2026-10-12 | minor | M13: CLI check directory identity, with overlap and symlink regressions; estimates unchanged | | 2026-10-12 | minor | M4: shared Type 3 glyph resources survive extraction, with save/reopen and independent raster regressions; estimates unchanged | | 2026-10-12 | minor | M2: packed TIFF-predictor RGB row boundaries, with decoding and page-render regressions; estimates unchanged | diff --git a/parity/acrobat-features.toml b/parity/acrobat-features.toml index 359a71e9a6..37b98326d6 100644 --- a/parity/acrobat-features.toml +++ b/parity/acrobat-features.toml @@ -106,8 +106,8 @@ milestone = "M1" status = "shipped" commands = [] tools = [] -evidence = ["crates/filters/src/lib.rs::chain_three_filters_with_predictor", "crates/filters/src/lzw.rs::spec_example", "crates/filters/src/predictor.rs::png_hand_vectors"] -notes = "" +evidence = ["crates/filters/src/lib.rs::chain_three_filters_with_predictor", "crates/filters/src/lzw.rs::spec_example", "crates/filters/src/predictor.rs::png_hand_vectors", "crates/filters/src/lib.rs::raw_flate_fallback_preserves_output_limits", "crates/cos/src/object.rs::raw_flate_fallback_streams_preserve_the_caller_limit"] +notes = "Raw-deflate fallback preserves output limits in strict and tolerant decoding, including misleading zlib headers. Image codecs remain outside this general-purpose filter implementation." [[feature]] id = "core.image-filters" From 14c3d951e7a942dbcc3003fb68c4635d66825250 Mon Sep 17 00:00:00 2001 From: Mex <44814932+MMexicann@users.noreply.github.com> Date: Thu, 15 Oct 2026 23:04:14 +0200 Subject: [PATCH 03/44] M6: preserve complete plain XML form values --- ROADMAP.md | 4 +++- crates/xfdf/README.md | 3 +++ crates/xfdf/src/lib.rs | 3 ++- crates/xfdf/src/tests.rs | 31 +++++++++++++++++++++++++++++++ docs/roadmap.md | 5 +++-- parity/acrobat-features.toml | 4 ++-- 6 files changed, 44 insertions(+), 6 deletions(-) diff --git a/ROADMAP.md b/ROADMAP.md index 66b9677569..1f0c6656fc 100644 --- a/ROADMAP.md +++ b/ROADMAP.md @@ -2,7 +2,7 @@ **Stage: alpha** · next: beta, ~25% (ready for real work 50% → 75%) and ~400–700 h away -> **Last reviewed:** 2026-10-15 · **Last updated:** 2026-10-15 · **Change:** minor (M2/gap 12: the Annex D.2 alias codes read as the ink they draw in both tables; the text oracle scores reading order; estimates unchanged) · **Target:** Adobe Acrobat Pro (Acrobat DC, continuous track 26.002.21931, macOS) +> **Last reviewed:** 2026-10-15 · **Last updated:** 2026-10-15 · **Change:** minor (M6: AcroForm XML text; estimates unchanged) > **Last reviewed:** 2026-10-13 · **Last updated:** 2026-10-14 · **Change:** minor (M14: the Italian catalog has every entry the other catalogs had and the code looks up; estimates unchanged) · **Target:** Adobe Acrobat Pro (Acrobat DC, continuous track 26.002.21931, macOS) > **Last reviewed:** 2026-10-14 · **Last updated:** 2026-10-14 · **Change:** minor (M3 #2080 candidate: explicit search jumps join per-tab history; rail and control-channel Back/Forward; estimates unchanged) > **Last reviewed:** 2026-10-13 · **Last updated:** 2026-10-13 · **Change:** minor (M4 #1910: Organize Pages opens on the current page; estimates unchanged) · **Target:** Adobe Acrobat Pro (Acrobat DC, continuous track 26.002.21931, macOS) @@ -157,6 +157,7 @@ Ranked; detail and the full milestone table in [docs/roadmap.md](docs/roadmap.md | 8 | 1.0 polish: performance, right-to-left, missing languages, keyboard-only (M14) | 55–95 | ## Progress log +- **2026-10-15 (M6, AcroForm XML text):** Plain AcroForm XML imports retain all direct text around comments and processing instructions, including CDATA and character references. Synthetic regressions verify exact values and unknown catalog data after incremental and full save/reopen. Nested-element and XFA interpretation are unchanged. Estimates unchanged. - **2026-10-15 (M2, gap 12):** `cargo xtask text-oracle` scores reading order as well as word F1: the longest common subsequence of the two word sequences over the longer one. F1 is a bag of words and cannot see order at all -- measuring #2431, a change that moves text and nothing else, it called 26 of the 29 files whose output changed identical, where the order score separated 18 improvements from 6 regressions. Reports, does not gate; a disagreement with Poppler, not a verdict. Estimates unchanged. - **2026-10-15 (M2, #2305 follow-up):** WinAnsiEncoding 0xA0 and 0xAD and MacRomanEncoding 0xCA extract as the ordinary space and hyphen Annex D.2 names them, in the vendored hayro tables (patch 30) as well as `crates/fonts`, so search, copy and redaction see characters that were hidden behind U+00A0 and U+00AD. Across the pdf.js corpus the soft hyphens we extract fall 117 to 13 and the non-breaking spaces 30 to 26; the rest come from `/ToUnicode`. An explicit `/Differences` name keeps its glyph list value, as pdftotext does. Estimates unchanged. - **2026-10-13 (community, M3, #1569 review):** Pixel-only Wayland wheel, wheel-tilt and continuous input use standalone moved events, so Ctrl zoom does not remain latched after the modifier is released (#991); vendored winit patch (13), with a policy test. Estimates unchanged. @@ -493,6 +494,7 @@ Newest first: the date, what moved, and the new overall estimate. | Date | Change | Summary | |---|---|---| +| 2026-10-15 | minor | M6: Plain AcroForm XML imports retain all direct text around comments and processing instructions, including CDATA and character references. Estimates unchanged. | | 2026-10-12 | minor | M6: valid AcroForm XML element names with original PDF field names preserved; saved-PDF collision and Unicode regressions. Estimates unchanged. | | 2026-10-12 | minor | M6: preserve carriage returns in exported CSV field names and values; saved-PDF round-trip coverage. Estimates unchanged. | | 2026-10-13 | minor | M4: Insert-from-file preserves source bookmarks; integration tests retained with current main. Estimates unchanged. | diff --git a/crates/xfdf/README.md b/crates/xfdf/README.md index 2b179e2007..fdc9aa401c 100644 --- a/crates/xfdf/README.md +++ b/crates/xfdf/README.md @@ -18,6 +18,9 @@ let report = import(&mut doc, &bytes)?; // XFDF, FDF, XML, CSV o - **Form data**: Acrobat's XML (`xfdf:original` keeps names that aren't XML names), CSV and tab-delimited text (a row of names, a row of values). +Plain AcroForm XML imports retain all direct text around comments and processing instructions, +including CDATA and character references. Nested-element and XFA interpretation are unchanged. + Import replaces comments with the same `/NM` (and drops the replaced comment's pop-up), draws appearances PdfCraft can draw, and sets values through the form's own checks (formats, validation, recalculation); read-only fields take imported values, as in Acrobat. XML is read diff --git a/crates/xfdf/src/lib.rs b/crates/xfdf/src/lib.rs index 50326c4e71..6706b11eed 100644 --- a/crates/xfdf/src/lib.rs +++ b/crates/xfdf/src/lib.rs @@ -1114,7 +1114,8 @@ fn import_table(doc: &mut Document, text: &str) -> Result { .map(|c| { let name = c.attributes().find(|a| a.name() == "original").map(|a| a.value().to_string()).unwrap_or_else(|| c.tag_name().name().to_string()); - (name, vec![c.text().unwrap_or("").to_string()]) + // Comments and processing instructions do not end a field's character data. + (name, vec![c.children().filter(|node| node.is_text()).filter_map(|node| node.text()).collect()]) }) .collect() } else if t.lines().next().is_some_and(|l| l.contains('\t')) { diff --git a/crates/xfdf/src/tests.rs b/crates/xfdf/src/tests.rs index d244df1adf..f5cc52cec7 100644 --- a/crates/xfdf/src/tests.rs +++ b/crates/xfdf/src/tests.rs @@ -1011,3 +1011,34 @@ fn xfdf_import_keeps_text_around_xml_comments_and_instructions() { assert_eq!(values(&reopened)[0].1, want, "{xml_text}"); } } + +#[test] +fn xml_form_import_preserves_text_around_comments_and_instructions() { + for (body, expected) in [ + ("leftright", "leftright"), + ("leftmiddleright", "leftmiddleright"), + ("]]>&right", "&right"), + (" left right ", " left right "), + ("", ""), + ] { + let mut original = one_field(); + let root = original.root().unwrap(); + original.update_dict(root, |dict| dict.set(b"PCUnknown".to_vec(), PdfString::text("retained"))).unwrap(); + set_value(&mut original, "Name", &FieldValue::Text("replace me".into())).unwrap(); + let source = write_full(&original, &SaveOptions::default()).unwrap(); + let mut doc = Document::open(Arc::new(source.clone())).unwrap(); + let xml = format!("{body}"); + let report = import(&mut doc, xml.as_bytes()).unwrap(); + assert_eq!(report.fields, 1); + assert!(report.rejected.is_empty()); + for saved in [write_full(&doc, &SaveOptions::default()).unwrap(), write_incremental(&doc, &SaveOptions::default()).unwrap()] { + let reopened = Document::open(Arc::new(saved)).unwrap(); + let name = fields(&reopened).into_iter().find(|f| f.name == "Name").unwrap(); + let want = if expected.is_empty() { Vec::new() } else { vec![expected.to_string()] }; + assert_eq!(name.value, want, "XML body: {body}"); + let root = reopened.get(reopened.root().unwrap()); + assert_eq!(root.as_dict().unwrap().get(b"PCUnknown").unwrap().as_string().unwrap().to_text(), "retained"); + } + assert_eq!(fields(&original).into_iter().find(|f| f.name == "Name").unwrap().value, vec!["replace me"]); + } +} diff --git a/docs/roadmap.md b/docs/roadmap.md index 3148823ea5..a54011b3dc 100644 --- a/docs/roadmap.md +++ b/docs/roadmap.md @@ -1,6 +1,6 @@ # PdfCraft roadmap: milestones and what's next -> **Last reviewed:** 2026-10-13 · **Last updated:** 2026-10-14 · **Change:** minor (M14: the Italian catalog has every entry the other catalogs had and the code looks up, 2,528 entries; estimates unchanged) · **Target:** Adobe Acrobat Pro (Acrobat DC, continuous track 26.002.21931, macOS) +> **Last reviewed:** 2026-10-15 · **Last updated:** 2026-10-15 · **Change:** minor (M6: AcroForm XML text; estimates unchanged) > **Last reviewed:** 2026-10-12 · **Last updated:** 2026-10-13 · **Change:** minor (M2/M6: spot-colour images convert once per pixel value; widget placement and the Fields panel scale with the field count; estimates unchanged) · **Target:** Adobe Acrobat Pro (Acrobat DC, continuous track 26.002.21931, macOS) > **Last reviewed:** 2026-10-14 · **Last updated:** 2026-10-14 · **Change:** minor (M3 candidate: coordinate control clicks on slow frames and coalesced text selection; estimates unchanged) · **Target:** Adobe Acrobat Pro (Acrobat DC, continuous track 26.002.21931, macOS) > **Last reviewed:** 2026-10-14 · **Last updated:** 2026-10-14 · **Change:** minor (M3 #2080 candidate: explicit search jumps join per-tab history; rail and control-channel Back/Forward; estimates unchanged) @@ -116,7 +116,7 @@ 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: 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); 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 | -| 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: 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. 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. | | 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. 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). 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). Missing: editing existing text and images in place (the longest pole), watermark print/screen visibility and repeat | @@ -179,6 +179,7 @@ M2 (renderer), M7 (content editing), M10 (OCR and Office), M11 (Preflight and st | Date | Change | Summary | |---|---|---| +| 2026-10-15 | minor | M6: Plain AcroForm XML imports retain all direct text around comments and processing instructions, including CDATA and character references. Estimates unchanged. | | 2026-10-12 | minor | M6: valid AcroForm XML element names with original PDF field names preserved; saved-PDF collision and Unicode regressions. Estimates unchanged. | | 2026-10-12 | minor | M6: preserve carriage returns in exported CSV field names and values; saved-PDF round-trip coverage. Estimates unchanged. | | 2026-10-12 | minor | M7 local candidate: text drafts grow and save their width; single visual rows grow across style boundaries; both text tools retype added items and Add Text edits source text. Added-item textless previews are read-only and covered by UI/tool regressions. Estimates unchanged. | diff --git a/parity/acrobat-features.toml b/parity/acrobat-features.toml index 533013b547..3961251b4e 100644 --- a/parity/acrobat-features.toml +++ b/parity/acrobat-features.toml @@ -4704,8 +4704,8 @@ milestone = "M6" status = "shipped" commands = ["form.export_data", "form.import_data"] tools = ["doc_export_data", "doc_import_data"] -evidence = ["crates/xfdf/src/tests.rs::form_data_as_xml_csv_and_text", "crates/automation/tests/automation.rs::comments_and_form_data_travel_as_xfdf_fdf_and_text"] -notes = "Acrobat's XML (xfdf:original), CSV, tab-delimited" +evidence = ["crates/xfdf/src/tests.rs::form_data_as_xml_csv_and_text", "crates/automation/tests/automation.rs::comments_and_form_data_travel_as_xfdf_fdf_and_text", "crates/xfdf/src/tests.rs::xml_form_import_preserves_text_around_comments_and_instructions"] +notes = "Acrobat's XML (xfdf:original), CSV, tab-delimited; Plain AcroForm XML imports retain all direct text around comments and processing instructions, including CDATA and character references. Nested-element and XFA interpretation remain outside this flat exchange format." [[feature]] id = "form.merge-to-spreadsheet" From cee48385b76631270f68ea1e928060cc378bf405 Mon Sep 17 00:00:00 2001 From: skylar taylor-barrick Date: Sat, 17 Oct 2026 12:57:57 -0600 Subject: [PATCH 04/44] deny: acknowledge the new zbus unmaintained advisories RUSTSEC-2026-0370/0371/0372 were published today for zvariant, zbus_names and zvariant_derive. All three are unmaintained notices rather than vulnerabilities, and none has a fixed release to move to. They reach the tree as the D-Bus stack behind accesskit_unix -> atspi (Linux accessibility) and as a dev-dependency of pdfcraft-platform, so nothing ships in the other targets' binaries. This is why main went red today; no dependency version changed. --- deny.toml | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/deny.toml b/deny.toml index 2362d56822..ed9c26c206 100644 --- a/deny.toml +++ b/deny.toml @@ -48,6 +48,13 @@ ignore = [ # winprint's fmt-derive (craft-print's Windows spooler), so it runs at compile time on Windows # and is not in the binary. { id = "RUSTSEC-2024-0370", reason = "compile-time proc macro of winprint's fmt-derive (craft-print Windows printing, #1107)" }, + # zvariant, zbus_names and zvariant_derive are unmaintained (no vulnerability, and no fixed + # release to move to). They reach the tree as the D-Bus stack behind `accesskit_unix` -> + # `atspi`, which is Linux accessibility only, and as a dev-dependency of pdfcraft-platform. + # Revisit when the accesskit/zbus chain moves to a maintained successor. + { id = "RUSTSEC-2026-0370", reason = "zvariant unmaintained; Linux a11y stack via accesskit_unix" }, + { id = "RUSTSEC-2026-0371", reason = "zbus_names unmaintained; Linux a11y stack via accesskit_unix" }, + { id = "RUSTSEC-2026-0372", reason = "zvariant_derive unmaintained; Linux a11y stack via accesskit_unix" }, ] # egui's default UI fonts (Ubuntu-Light, Hack, emoji-icon-font): font licences on the AGENTS.md From 392406eb4ad488bddacb9eae12ad73b987e13a30 Mon Sep 17 00:00:00 2001 From: skylar taylor-barrick Date: Sat, 17 Oct 2026 21:50:58 +0200 Subject: [PATCH 05/44] fix(content): read a comment at the end of a content stream as the renderer does (#3081) Pieces::join separated a page's content streams with a newline, which ended a comment left open at the end of one stream. hayro, MuPDF and Poppler join them with a space, so the comment runs on into the next stream and hides its first line. Edit text, object_list, the redaction audit, redaction and the Office/HTML export therefore saw text and boxes that nothing draws, and redacting unrelated text on the page made the hidden content visible: the rewritten stream dropped the comment. - Pieces::join uses a space, so every reader of the joined streams agrees with rendering. - The parser records, per piece, whether a top-level comment runs into it and out of it (boundaries only, not every comment). A redaction rewrite of a piece ends an incoming comment before its first operator and leaves an outgoing one open, so hidden content stays hidden. - Reading for export parses the streams joined, instead of one by one. - The redaction tag check compares the joined streams the same way. - Pieces::piece_of uses a binary search. --- crates/audit/src/tests.rs | 19 +++++++ crates/content/src/lib.rs | 72 +++++++++++++++++++++++-- crates/content/src/tests.rs | 105 ++++++++++++++++++++++++++++++++++++ crates/edit/src/text.rs | 14 ++++- crates/redact/src/interp.rs | 16 +++++- crates/redact/src/lib.rs | 3 +- crates/redact/src/tests.rs | 39 ++++++++++++++ 7 files changed, 258 insertions(+), 10 deletions(-) diff --git a/crates/audit/src/tests.rs b/crates/audit/src/tests.rs index ed36a8d5ee..64ea05bde8 100644 --- a/crates/audit/src/tests.rs +++ b/crates/audit/src/tests.rs @@ -500,3 +500,22 @@ fn forms_nested_past_depth_limit_fail_closed() { let result = audit_redactions(&open(nested_forms(33))); assert!(matches!(result, Err(crate::AuditError::TooDeep)), "{result:?}"); } + +#[test] +fn comment_across_streams_neither_invents_text_nor_a_cover() { + let doc = open(two_streams(b"BT /F1 24 Tf 72 700 Td (Visible text) Tj ET % note", b"0 g 70 690 200 40 re f")); + assert!(audit_redactions(&doc).unwrap().is_empty(), "commented cover must not be reported"); + let doc = open(two_streams(b"BT /F1 24 Tf 72 700 Td (Before comment) Tj ET % note", b"BT /F1 24 Tf 72 650 Td (After comment) Tj ET")); + let text: String = pdfcraft_edit::text_lines(&doc, 0).unwrap().into_iter().map(|line| line.text).collect(); + assert!(!text.contains("After comment"), "editor exposed phantom text: {text}"); +} + +#[test] +fn reading_blocks_respect_stream_comments_and_split_operands() { + let doc = open(two_streams(b"BT /F1 24 Tf 72 700 Td (Before comment) Tj ET % note", b"BT /F1 24 Tf 72 650 Td (After comment) Tj ET")); + let text: String = pdfcraft_edit::reading_blocks(&doc, 0).unwrap().into_iter().map(|block| block.editor_text).collect(); + assert_eq!(text, "Before comment"); + let doc = open(two_streams(b"BT /F1 24 Tf 72 700 Td (Split operand)", b"Tj ET")); + let text: String = pdfcraft_edit::reading_blocks(&doc, 0).unwrap().into_iter().map(|block| block.editor_text).collect(); + assert_eq!(text, "Split operand"); +} diff --git a/crates/content/src/lib.rs b/crates/content/src/lib.rs index 32334e047b..c7c8bca9ee 100644 --- a/crates/content/src/lib.rs +++ b/crates/content/src/lib.rs @@ -60,6 +60,10 @@ pub struct Parsed { pub ops: Vec, /// Bytes that could not be read as operands or operators. pub skipped: usize, + /// For [`Pieces::parse`]: per piece, whether a comment runs into it from the piece before + /// and whether one runs out of it into the next. Only boundaries are recorded, so the size + /// depends on the number of pieces, not of comments. + comment_edges: Vec<(bool, bool)>, } fn is_ws(b: u8) -> bool { @@ -72,12 +76,25 @@ fn is_delim(b: u8) -> bool { /// Parse a (decoded) content stream. pub fn parse(data: &[u8]) -> Parsed { - let mut out = Parsed::default(); + parse_pieces(data, &[]) +} + +/// Parse `data`, recording which of the piece boundaries `ends` (as in [`Pieces`]) a comment +/// crosses. +fn parse_pieces(data: &[u8], ends: &[usize]) -> Parsed { + let mut out = Parsed { comment_edges: vec![(false, false); ends.len()], ..Parsed::default() }; + let mut boundary = 0; let mut lx = Lexer::new(data, 0); let mut operands: Vec = Vec::new(); let mut start: Option = None; loop { + let trivia = lx.pos; lx.skip_ws(); + // Only the whitespace the lexer skips here holds top-level comments: a `%` inside a + // string, a name, an array or dictionary operand or inline image data is not one. + if boundary < ends.len() { + comment_edges(data, trivia..lx.pos, ends, &mut boundary, &mut out.comment_edges); + } let Some(&b) = data.get(lx.pos) else { break }; let at = lx.pos; let operand_start = matches!(b, b'/' | b'(' | b'<' | b'[' | b'+' | b'-' | b'.') || b.is_ascii_digit(); @@ -148,6 +165,39 @@ pub fn parse(data: &[u8]) -> Parsed { out } +/// Record the piece boundaries crossed by the comments in `trivia` (skipped whitespace and +/// comments). `boundary` is the first boundary not yet passed; boundaries only move forward. +fn comment_edges(data: &[u8], trivia: std::ops::Range, ends: &[usize], boundary: &mut usize, edges: &mut [(bool, bool)]) { + let mut at = trivia.start; + while at < trivia.end { + if data.get(at) != Some(&b'%') { + at += 1; + continue; + } + let comment = at; + while at < trivia.end && !matches!(data.get(at), Some(b'\r' | b'\n')) { + at += 1; + } + // The separator of piece `boundary` is the last byte before its end. + while let Some(&end) = ends.get(*boundary) { + let separator = end.saturating_sub(1); + if separator >= at { + break; + } + if separator >= comment { + if let Some(edge) = edges.get_mut(*boundary) { + edge.1 = true; + } + // Includes a comment whose end of line is the next piece's first byte. + if let Some(edge) = edges.get_mut(boundary.saturating_add(1)) { + edge.0 = true; + } + } + *boundary += 1; + } + } +} + /// Read an inline image starting after `BI`: (parameters, data, position after `EI`). `Err` holds /// the position after the `EI` (or the end of the stream) of an image whose parameters can't be read. fn inline_image(data: &[u8], pos: usize) -> Result<(Dict, Vec, usize), usize> { @@ -305,7 +355,9 @@ pub fn serialize_ops(ops: &[Op]) -> Vec { /// A page's content streams joined into the one stream they are. Writers may split it between /// any two tokens (ISO 32000-2 §7.8.2), so an operator's operands can end one piece and its /// keyword start the next: parse the pieces joined ([`Pieces::parse`]) and map positions back -/// with [`Pieces::piece_of`]. A newline separates the pieces so tokens never run together. +/// with [`Pieces::piece_of`]. A space separates the pieces, as renderers join them (hayro, +/// MuPDF and Poppler alike): tokens never run together, and a comment at the end of a piece +/// runs on into the next one, up to its first end of line. #[derive(Clone, Debug, Default, PartialEq)] pub struct Pieces { data: Vec, @@ -319,7 +371,7 @@ impl Pieces { let mut ends = Vec::with_capacity(pieces.len()); for p in pieces { data.extend_from_slice(p.as_ref()); - data.push(b'\n'); + data.push(b' '); ends.push(data.len()); } Pieces { data, ends } @@ -341,12 +393,22 @@ impl Pieces { /// Parse the pieces as one stream. pub fn parse(&self) -> Parsed { - parse(&self.data) + parse_pieces(&self.data, &self.ends) + } + + /// Per piece, from `parsed` (this piece set's [`Pieces::parse`]): whether a comment runs + /// into it from the piece before, and whether one runs out of it into the next. A writer + /// that rewrites a piece without its comments must keep both: end the incoming comment + /// before its first operator, and leave a comment open at its end. + pub fn comment_edges(&self, parsed: &Parsed) -> Vec<(bool, bool)> { + let mut edges = parsed.comment_edges.clone(); + edges.resize(self.len(), (false, false)); + edges } /// The piece holding joined position `at` (the last piece for positions past the end). pub fn piece_of(&self, at: usize) -> usize { - self.ends.iter().position(|&e| at < e).unwrap_or(self.ends.len().saturating_sub(1)) + self.ends.partition_point(|&e| e <= at).min(self.ends.len().saturating_sub(1)) } /// The pieces an operator spans: (the one its first token is in, the one its keyword is in). diff --git a/crates/content/src/tests.rs b/crates/content/src/tests.rs index 18e0b8cbcc..1119bdaf90 100644 --- a/crates/content/src/tests.rs +++ b/crates/content/src/tests.rs @@ -283,3 +283,108 @@ fn pieces_parse_as_one_stream_and_splice_back() { assert_eq!(out.len(), 3); assert!(Pieces::join::<&[u8]>(&[]).splice([(0..1, b"x".to_vec())]).is_empty()); } + +#[test] +fn stream_boundary_comment_matches_space_concatenation() { + for eol in [b"\n".as_slice(), b"\r", b"\r\n"] { + let mut tail = b"(HIDDEN) Tj".to_vec(); + tail.extend(eol); + tail.extend(b"(LIVE) Tj"); + let pieces = Pieces::join(&[b"BT % comment".as_slice(), b"(ALSO HIDDEN) Tj", &tail, b"ET"]); + let parsed = pieces.parse(); + let shown: Vec<_> = parsed.ops.iter().filter(|op| op.is("Tj")).collect(); + assert_eq!(shown.len(), 1); + assert_eq!(shown[0].operands[0].as_string().unwrap().bytes, b"LIVE"); + } +} + +#[test] +fn comment_edges_terminate_at_next_piece_byte_zero() { + for eol in [b"\n".as_slice(), b"\r", b"\r\n"] { + let mut next = eol.to_vec(); + next.extend_from_slice(b"q Q"); + let pieces = Pieces::join(&[b"% outgoing".as_slice(), next.as_slice()]); + let parsed = pieces.parse(); + assert_eq!(pieces.comment_edges(&parsed), vec![(false, true), (true, false)], "EOL {eol:?}"); + assert_eq!(parsed.ops.iter().map(|op| op.op.as_slice()).collect::>(), vec![b"q".as_slice(), b"Q"]); + } +} + +#[test] +fn comment_edges_span_empty_pieces_and_end_of_content() { + let pieces = Pieces::join(&[b"q % outgoing".as_slice(), b"", b"", b"ignored\nQ"]); + let parsed = pieces.parse(); + assert_eq!(pieces.comment_edges(&parsed), vec![(false, true), (true, true), (true, true), (true, false)]); + assert_eq!(parsed.ops.iter().map(|op| op.op.as_slice()).collect::>(), vec![b"q".as_slice(), b"Q"]); + + let pieces = Pieces::join(&[b"% outgoing".as_slice(), b"", b"still ignored"]); + let parsed = pieces.parse(); + assert_eq!(pieces.comment_edges(&parsed), vec![(false, true), (true, true), (true, true)]); + assert!(parsed.ops.is_empty()); + + let pieces = Pieces::join::<&[u8]>(&[]); + assert!(pieces.comment_edges(&pieces.parse()).is_empty()); +} + +#[test] +fn comment_edges_ignore_percent_inside_operands_and_image_data() { + for first in [ + b"(literal % not a comment) Tj".as_slice(), + b"/Percent#25Name MP", + b"[(literal % not a comment)] TJ", + b"/P << /ActualText (literal % not a comment) >> BDC EMC", + b"BI /W 1 /H 1 /BPC 8 /CS /G ID % EI", + ] { + let pieces = Pieces::join(&[first, b"q Q"]); + let parsed = pieces.parse(); + assert_eq!(pieces.comment_edges(&parsed), vec![(false, false), (false, false)], "{first:?}"); + assert_eq!(parsed.ops.last().unwrap().op, b"Q"); + assert_eq!(parsed.skipped, 0); + } +} + +#[test] +fn compound_operand_comment_split_is_owned_by_spanning_operator() { + for parts in [[b"[(A) % ignored".as_slice(), b"still ignored\n(B)] TJ"], [b"/P << /MCID 0 % ignored".as_slice(), b"still ignored\n>> BDC"]] { + let pieces = Pieces::join(&parts); + let parsed = pieces.parse(); + // The object lexer consumes this nested comment. Its containing operator spans + // both pieces, which forces both to be rewritten together by the redactor. + assert_eq!(pieces.comment_edges(&parsed), vec![(false, false), (false, false)]); + assert_eq!(parsed.ops.len(), 1); + assert_eq!(pieces.pieces_of(&parsed.ops[0]), (0, 1)); + assert_eq!(parsed.skipped, 0); + } +} + +#[test] +fn comment_edges_do_not_confuse_local_comments_with_boundary_comments() { + let pieces = Pieces::join(&[b"% local\nq % crossing".as_slice(), b"ignored\n% local again\nQ\n% final local\n", b"q Q"]); + let parsed = pieces.parse(); + assert_eq!(pieces.comment_edges(&parsed), vec![(false, true), (true, false), (false, false)]); + assert_eq!(parsed.ops.iter().map(|op| op.op.as_slice()).collect::>(), vec![b"q".as_slice(), b"Q", b"q", b"Q"]); +} + +#[test] +fn comment_edge_storage_depends_on_piece_count_not_comment_count() { + let mut first = b"%\n".repeat(16_384); + first.extend_from_slice(b"q % crossing"); + let pieces = Pieces::join(&[first.as_slice(), b"ignored\nQ"]); + let parsed = pieces.parse(); + assert_eq!(pieces.comment_edges(&parsed), vec![(false, true), (true, false)]); + assert_eq!(parsed.ops.len(), 2); + // Also exercise public parsing without piece-boundary metadata. + assert_eq!(parse(&first).ops.len(), 1); +} + +#[test] +fn piece_lookup_preserves_exact_boundary_and_empty_piece_mapping() { + // Joined layout: qQ; separator belongs to prior piece. + let pieces = Pieces::join(&[b"q".as_slice(), b"", b"Q"]); + for (at, expected) in [(0, 0), (1, 0), (2, 1), (3, 2), (4, 2), (5, 2), (usize::MAX, 2)] { + assert_eq!(pieces.piece_of(at), expected, "position {at}"); + } + let empty = Pieces::join::<&[u8]>(&[]); + assert_eq!(empty.piece_of(0), 0); + assert_eq!(empty.piece_of(usize::MAX), 0); +} diff --git a/crates/edit/src/text.rs b/crates/edit/src/text.rs index 9c83cf9a39..93d1b54fcc 100644 --- a/crates/edit/src/text.rs +++ b/crates/edit/src/text.rs @@ -1276,8 +1276,18 @@ fn reading_lines(doc: &Document, page: usize) -> Result, EditError let streams = content_streams(doc, &p.dict); let mut w = Walk { doc, lines: Vec::new(), next_stream: streams.len(), path: Vec::new(), visits: 0 }; let mut carry = Carry::new(); - for (si, (_, data)) in streams.into_iter().enumerate() { - walk(&mut w, &parse(&data).ops, &res, &mut carry, si); + // Read the page's streams as the one stream they are, as rendering and editing do: a + // comment or an operator's operands can run on from one stream into the next. Each operator + // still counts as its first stream's, which keeps lines from different streams apart. + let pieces = Pieces::join(&streams.into_iter().map(|(_, data)| data).collect::>()); + let mut grouped: Vec> = (0..pieces.len()).map(|_| Vec::new()).collect(); + for op in pieces.parse().ops { + if let Some(group) = grouped.get_mut(pieces.pieces_of(&op).0) { + group.push(op); + } + } + for (si, ops) in grouped.iter().enumerate() { + walk(&mut w, ops, &res, &mut carry, si); } let mut lines = w.lines; // A visual-order Indic font draws pre-base vowel signs before their consonant. diff --git a/crates/redact/src/interp.rs b/crates/redact/src/interp.rs index c76e119953..50802eff39 100644 --- a/crates/redact/src/interp.rs +++ b/crates/redact/src/interp.rs @@ -380,6 +380,9 @@ pub(crate) fn process(doc: &mut Document, scope: &mut Scope<'_>, streams: &[Vec< // next. Parse them joined, then give each operator back to the piece its keyword is in. let joined = Pieces::join(streams); let mut parsed = joined.parse(); + // A rewritten piece loses its comments, so keep where they began and ended: a comment that + // ran on into the next piece still hides that piece's first line. + let comment_edges = joined.comment_edges(&parsed); if !scope.hidden_layers.is_empty() { let props = res_dict(doc, resources, b"Properties"); let (kept, removed) = strip_hidden_layers(doc, scope, parsed.ops, &props); @@ -405,7 +408,7 @@ pub(crate) fn process(doc: &mut Document, scope: &mut Scope<'_>, streams: &[Vec< } } - for (piece, mut changed) in pieces.into_iter().zip(rewrite) { + for ((piece, mut changed), (comment_in, comment_out)) in pieces.into_iter().zip(rewrite).zip(comment_edges) { let mut ops: Vec = Vec::with_capacity(piece.len()); for op in piece { let o = op.op.as_slice(); @@ -622,7 +625,16 @@ pub(crate) fn process(doc: &mut Document, scope: &mut Scope<'_>, streams: &[Vec< if !path.is_empty() { ops.append(&mut path); } - out.streams.push(changed.then(|| serialize_ops(&ops))); + out.streams.push(changed.then(|| { + // The piece before still ends inside a comment: end it before the first operator. + let mut bytes = if comment_in { b"\n".to_vec() } else { Vec::new() }; + bytes.extend(serialize_ops(&ops)); + // The piece ended inside a comment that hid the start of the next one: keep it open. + if comment_out { + bytes.push(b'%'); + } + bytes + })); } out } diff --git a/crates/redact/src/lib.rs b/crates/redact/src/lib.rs index 61231bd982..21af3691c7 100644 --- a/crates/redact/src/lib.rs +++ b/crates/redact/src/lib.rs @@ -400,7 +400,8 @@ pub fn apply(doc: &mut Document, pages: Option<&[usize]>) -> Result