daniel543x/pdfcraft
1
0 Fork 0
mirror of https://github.com/storytold/pdfcraft.git synced 2026-11-09 12:32:52 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix(redact): Q inside a text object restores the text matrices; revert the render change

Browse Source 
Review on #4831 pointed out the PDF Association's erratum to ISO 32000-2
(pdf-association/pdf-issues #368): inside a text object, q/Q also save and
restore Tm and Tlm (§9.4.1, referenced from §8.4.2). Acrobat 26.2 agrees on
a synthetic PDF 2.0 page. The renderer on main already did this, so the
previous commit's hayro-interpret patch (67) was wrong: it is reverted here,
with its vendor/README row and the render tests.

The real disagreement was in the redactor's own interpreter, which kept Tm
and Tlm across Q. Find took its boxes from the renderer's text, the redactor
measured the glyphs elsewhere, and redact_apply refused on residue. Its
state stack now holds (Gs, Tm, Tlm) and Q restores all three.

Test: it::redact_text_after_q, end to end on %PDF-2.0 fixtures, three cases
(font change inside q/Q; q 100 0 Td Q; the same followed by T*). With the
redactor change reverted, each case fails on its own at redact_apply. With
only Tm restored, the T* case fails.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01SqmHYx8FiWM5PcsoiErgp9
This commit is contained in:
KenM76andClaude Opus 5.5 committed 2026-10-26 19:51:58 -04:00
1 parent 086339b7d7
commit 0457aa88f9
6 files changed
+43 -172
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

crates/automation/tests/it/redact_text_after_q.rs
+34 -23
View File
@@ -1,14 +1,23 @@
//! Search-and-redact of text that follows a `q`/`Q` inside a text object. Find's boxes come from
//! the renderer's text and redaction measures the content itself, so the two must agree on where
//! the text after `Q` is (vendored hayro-interpret patch 67); when they disagreed, `redact_apply`
//! refused to change anything.
//! Search-and-redact of text that follows a `q`/`Q` inside a text object. `Q` restores the text
//! matrices there (ISO 32000-2 §9.4.1 as corrected by the PDF Association's errata, issue 368), so
//! "SECRET" is drawn from the pen position before `q`, over the "B". Find's boxes come from the
//! renderer's text, which places it there; redaction measures the content itself, and while it
//! carried the pen across `Q` the two disagreed and `redact_apply` refused to change anything.
use pdfcraft_automation::{Automation, Content};
use serde_json::{Value, json};
const CONTENT: &str = "BT /F1 12 Tf 72 700 Td (AAAA) Tj q /F2 24 Tf (B) Tj Q (SECRET) Tj ET";
/// The content, the text that stays after SECRET is redacted, and the text that goes with it.
const CASES: [(&str, &str, &str); 3] = [
// A larger font inside `q`/`Q`: the font and the pen are both restored, so SECRET lies over
// the B and the B goes with it.
("BT /F1 12 Tf 72 700 Td (AAAA) Tj q /F2 24 Tf (B) Tj Q (SECRET) Tj ET", "AAAA", "B"),
// A move inside `q`/`Q` is undone.
("BT /F1 12 Tf 72 700 Td (AA) Tj q 100 0 Td Q (SECRET) Tj ET", "AA", "SECRET"),
// The text line matrix is restored too: `T*` starts the next line from the line before `q`.
("BT /F1 12 Tf 14 TL 72 700 Td (AA) Tj q 100 0 Td Q T* (SECRET) Tj ET", "AA", "SECRET"),
];
fn pdf() -> Vec<u8> {
fn pdf(content: &str) -> Vec<u8> {
let objects = [
"<< /Type /Catalog /Pages 2 0 R >>".to_owned(),
"<< /Type /Pages /Kids [3 0 R] /Count 1 >>".to_owned(),
@@ -16,9 +25,9 @@ fn pdf() -> Vec<u8> {
/F1 << /Type /Font /Subtype /Type1 /BaseFont /Helvetica >> \
/F2 << /Type /Font /Subtype /Type1 /BaseFont /Courier >> >> >> >>"
.to_owned(),
format!("<< /Length {} >>\nstream\n{CONTENT}\nendstream", CONTENT.len()),
format!("<< /Length {} >>\nstream\n{content}\nendstream", content.len()),
];
let mut out = b"%PDF-1.7\n".to_vec();
let mut out = b"%PDF-2.0\n".to_vec();
let mut offsets = Vec::new();
for (i, object) in objects.iter().enumerate() {
offsets.push(out.len());
@@ -49,18 +58,20 @@ fn text(a: &mut Automation, doc: &Value) -> String {
#[test]
fn find_and_redact_removes_text_after_a_q_q_inside_its_text_object() {
let dir = std::env::temp_dir().join(format!("pdfcraft-redact-after-q-{}", std::process::id()));
let _ = std::fs::remove_dir_all(&dir);
std::fs::create_dir_all(&dir).unwrap();
std::fs::write(dir.join("in.pdf"), pdf()).unwrap();
let mut a = Automation::new().with_root(&dir).unwrap();
let doc = ok(&mut a, "doc_open", json!({ "path": "in.pdf" }))["doc"].clone();
assert_eq!(ok(&mut a, "redact_mark", json!({ "doc": doc, "find": "SECRET" }))["marked"], 1);
ok(&mut a, "redact_apply", json!({ "doc": doc }));
ok(&mut a, "doc_save", json!({ "doc": doc, "path": "out.pdf", "full": true }));
let saved = ok(&mut a, "doc_open", json!({ "path": "out.pdf" }))["doc"].clone();
let after = text(&mut a, &saved);
assert!(!after.contains("SECRET"), "{after:?}");
assert!(after.contains("AAAAB"), "the text before the mark stays: {after:?}");
let _ = std::fs::remove_dir_all(&dir);
for (case, (content, kept, gone)) in CASES.iter().enumerate() {
let dir = std::env::temp_dir().join(format!("pdfcraft-redact-after-q-{}-{case}", std::process::id()));
let _ = std::fs::remove_dir_all(&dir);
std::fs::create_dir_all(&dir).unwrap();
std::fs::write(dir.join("in.pdf"), pdf(content)).unwrap();
let mut a = Automation::new().with_root(&dir).unwrap();
let doc = ok(&mut a, "doc_open", json!({ "path": "in.pdf" }))["doc"].clone();
assert_eq!(ok(&mut a, "redact_mark", json!({ "doc": doc, "find": "SECRET" }))["marked"], 1, "{content}");
ok(&mut a, "redact_apply", json!({ "doc": doc }));
ok(&mut a, "doc_save", json!({ "doc": doc, "path": "out.pdf", "full": true }));
let saved = ok(&mut a, "doc_open", json!({ "path": "out.pdf" }))["doc"].clone();
let after = text(&mut a, &saved);
assert!(!after.contains("SECRET") && !after.contains(gone), "{content}: {after:?}");
assert!(after.contains(kept), "{content}: the text before the mark stays: {after:?}");
let _ = std::fs::remove_dir_all(&dir);
}
}
crates/redact/src/interp.rs
+7 -4
View File
@@ -801,7 +801,10 @@ pub(crate) fn process(doc: &mut Document, scope: &mut Scope<'_>, streams: &[Vec<
fn process_from(doc: &mut Document, scope: &mut Scope<'_>, streams: &[Vec<u8>], resources: &Dict, mut gs: Gs) -> Output {
let mut out = Output::default();
let fallback = Rc::new(Metrics::fallback());
let mut stack: Vec<Gs> = Vec::new();
// With each saved state, the text and text line matrices: inside a text object `q`/`Q`
// save and restore them too (ISO 32000-2 §9.4.1 as corrected by the PDF Association's
// errata, issue 368), as the renderer does.
let mut stack: Vec<(Gs, Matrix, Matrix)> = Vec::new();
let (mut tm, mut tlm) = (Matrix::IDENTITY, Matrix::IDENTITY);
let fonts_res = res_dict(doc, resources, b"Font");
let ext_gstates = res_dict(doc, resources, b"ExtGState");
@@ -901,10 +904,10 @@ fn process_from(doc: &mut Document, scope: &mut Scope<'_>, streams: &[Vec<u8>],
clip = false;
}
match o {
b"q" => stack.push(gs.clone()),
b"q" => stack.push((gs.clone(), tm, tlm)),
b"Q" => {
if let Some(g) = stack.pop() {
gs = g;
if let Some((g, m, lm)) = stack.pop() {
(gs, tm, tlm) = (g, m, lm);
}
}
b"cm" => {
crates/render/tests/it/main.rs
-1
View File
@@ -8,6 +8,5 @@ mod named_form_properties;
mod search;
mod separation_all;
mod substitute_widths;
mod text_matrix_q;
mod tiling_cell_placement;
mod type3_text_clip;
crates/render/tests/it/text_matrix_q.rs
-129
View File
@@ -1,129 +0,0 @@
//! Contributor-original synthetic pages: `q`/`Q` inside a text object. The text matrices are not
//! part of the graphics state (ISO 32000-2 §8.4.1 Table 51, §9.4.1), so a `Q` restores the font
//! but not the pen (vendored hayro-interpret patch 67). Each case is paired with a page that
//! changes the font back by hand instead, which must come out the same.
use pdfcraft_render::{PageRenderer, PageText, RenderConfig, RenderRequest, RequestKind};
use std::sync::Arc;
/// `q`/`Q` around a larger font: the text after `Q` continues from the end of the "B".
const SAVED: &str = "BT /F1 12 Tf 72 300 Td (AAAA) Tj q /F2 24 Tf (B) Tj Q (SECRET) Tj ET";
/// The same text with the font set back by `Tf`.
const BY_HAND: &str = "BT /F1 12 Tf 72 300 Td (AAAA) Tj /F2 24 Tf (B) Tj /F1 12 Tf (SECRET) Tj ET";
/// A move inside `q`/`Q` moves the pen for good: `Td` is not undone by `Q`.
const MOVED_IN_SAVE: &str = "BT /F1 12 Tf 72 300 Td (AA) Tj q 100 0 Td Q (SECRET) Tj ET";
const MOVED: &str = "BT /F1 12 Tf 72 300 Td (AA) Tj 100 0 Td (SECRET) Tj ET";
/// A form that moves its own pen and ends with an unbalanced `Q`, shown inside a text object
/// (`Do` is not allowed there, but readers draw it).
const FORM_INSIDE: &str = "BT /F1 12 Tf 72 300 Td (AA) Tj /X Do (SECRET) Tj ET";
const FORM_BODY: &[u8] = b"BT /F1 12 Tf 200 0 Td ET Q";
const NO_FORM: &str = "BT /F1 12 Tf 72 300 Td (AA) Tj (SECRET) Tj ET";
/// One page per entry of `contents`, 400 × 400, with Helvetica as /F1, Courier as /F2 and the
/// form /X.
fn pdf(contents: &[&str]) -> Arc<Vec<u8>> {
let n = contents.len();
let kids: String = (0..n).map(|i| format!("{} 0 R ", 5 + 2 * i)).collect();
let mut objects: Vec<Vec<u8>> = vec![
b"<< /Type /Catalog /Pages 2 0 R >>".to_vec(),
format!("<< /Type /Pages /Kids [{kids}] /Count {n} >>").into_bytes(),
b"<< /Font << /F1 << /Type /Font /Subtype /Type1 /BaseFont /Helvetica >> /F2 << /Type /Font /Subtype /Type1 /BaseFont /Courier >> >> /XObject << /X 4 0 R >> >>".to_vec(),
stream(b"/Type /XObject /Subtype /Form /BBox [0 0 400 400] /Resources 3 0 R", FORM_BODY),
];
for (i, content) in contents.iter().enumerate() {
objects.push(format!("<< /Type /Page /Parent 2 0 R /MediaBox [0 0 400 400] /Resources 3 0 R /Contents {} 0 R >>", 6 + 2 * i).into_bytes());
objects.push(stream(b"", content.as_bytes()));
}
let mut out = b"%PDF-1.7\n".to_vec();
let mut offsets = Vec::new();
for (i, object) in objects.iter().enumerate() {
offsets.push(out.len());
out.extend_from_slice(format!("{} 0 obj\n", i + 1).as_bytes());
out.extend_from_slice(object);
out.extend_from_slice(b"\nendobj\n");
}
let xref = out.len();
out.extend_from_slice(format!("xref\n0 {}\n0000000000 65535 f \n", objects.len() + 1).as_bytes());
for offset in offsets {
out.extend_from_slice(format!("{offset:010} 00000 n \n").as_bytes());
}
out.extend_from_slice(format!("trailer << /Size {} /Root 1 0 R >>\nstartxref\n{xref}\n%%EOF\n", objects.len() + 1).as_bytes());
Arc::new(out)
}
fn stream(dict: &[u8], body: &[u8]) -> Vec<u8> {
let mut s = b"<< ".to_vec();
s.extend_from_slice(dict);
s.extend_from_slice(format!(" /Length {} >>\nstream\n", body.len()).as_bytes());
s.extend_from_slice(body);
s.extend_from_slice(b"\nendstream");
s
}
fn request(page: usize, kind: RequestKind) -> RenderRequest {
RenderRequest { page, kind, tile: None, scale: 1.0, tag: 0, preview: false }
}
fn texts(contents: &[&str]) -> Vec<Arc<PageText>> {
let mut renderer = PageRenderer::new(pdf(contents), RenderConfig::default());
(0..contents.len())
.map(|page| {
let out = renderer.render(request(page, RequestKind::Text));
assert!(out.error.is_none(), "page {} text error: {:?}", page + 1, out.error);
out.text.expect("page text")
})
.collect()
}
/// The boxes of the glyphs of `word`'s one match on the page.
fn boxes(text: &PageText, word: &str) -> Vec<[f32; 4]> {
let hits = text.find(word);
assert_eq!(hits.len(), 1, "one {word} in {:?}", text.plain_text());
hits[0].clone().map(|i| text.glyphs[i].rect).collect()
}
fn assert_same_boxes(a: &[[f32; 4]], b: &[[f32; 4]]) {
assert_eq!(a.len(), b.len());
for (x, y) in a.iter().zip(b) {
assert!(x.iter().zip(y).all(|(p, q)| (p - q).abs() < 0.01), "{x:?} != {y:?}");
}
}
#[test]
fn text_after_q_q_continues_where_the_text_inside_left_off() {
let pages = texts(&[SAVED, BY_HAND]);
let secret = boxes(&pages[0], "SECRET");
assert_same_boxes(&secret, &boxes(&pages[1], "SECRET"));
let b = boxes(&pages[0], "B");
assert!(secret[0][0] >= b[0][2] - 0.01, "SECRET starts at {} inside the B ending at {}", secret[0][0], b[0][2]);
}
#[test]
fn q_q_still_restores_the_font() {
let pages = texts(&[SAVED, BY_HAND]);
let height = |r: [f32; 4]| r[3] - r[1];
let secret = boxes(&pages[0], "SECRET");
let b = boxes(&pages[0], "B");
assert!(height(secret[0]) < height(b[0]) * 0.75, "SECRET is drawn at the 12 pt font, not the B's 24 pt");
}
#[test]
fn a_move_inside_q_q_is_kept() {
let pages = texts(&[MOVED_IN_SAVE, MOVED]);
assert_same_boxes(&boxes(&pages[0], "SECRET"), &boxes(&pages[1], "SECRET"));
}
#[test]
fn a_forms_unbalanced_q_does_not_move_the_page_text() {
let pages = texts(&[FORM_INSIDE, NO_FORM]);
assert_same_boxes(&boxes(&pages[0], "SECRET"), &boxes(&pages[1], "SECRET"));
}
#[test]
fn q_q_inside_a_text_object_draws_like_the_font_set_back_by_hand() {
let mut renderer = PageRenderer::new(pdf(&[SAVED, BY_HAND]), RenderConfig::default());
let saved = renderer.render(request(0, RequestKind::Pixels));
let by_hand = renderer.render(request(1, RequestKind::Pixels));
assert!(saved.error.is_none() && by_hand.error.is_none());
assert_eq!((saved.width, saved.height), (by_hand.width, by_hand.height));
assert!(saved.rgba == by_hand.rgba, "the two pages draw differently");
}
vendor/README.md
Vendored
+1 -1
View File
@@ -39,7 +39,7 @@ 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 `.nLine truncated
| 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 `.nLine truncated
| 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<ColorReplacement>` 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, axis-aligned image is snapped to whole device pixels: shrunk once to its rounded device rectangle and drawn 1:1 at 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); (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 thLine truncated
| hayro-jbig2 | 0.3.0 | Apache-2.0 OR MIT | (1) at most 2^28 pixels per bitmap, page bitmap, halftone grid and grayscale image (each side could be 65535: 4.3 billion pixels decoded one by one); (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) | (1) `raster::tests::jbig2_regions_of_billions_of_pixels_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`) |
| 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` |
vendor/hayro-interpret/src/interpret/mod.rs
Vendored
+1 -14
View File
@@ -637,20 +637,7 @@ fn interpret_window<'a>(
TypedInstruction::ClipEvenOdd(_) => {
*(context.clip_mut()) = Some(FillRule::EvenOdd);
}
TypedInstruction::RestoreState(_) => {
// PdfCraft patch (67): the text and text line matrices are not part of the
// graphics state (ISO 32000-2 §8.4.1 Table 51, §9.4.1), so a `Q` inside a text
// object keeps the pen where the text before it left it. Outside one, the next
// `BT` resets both. Forms and annotations run between a save and restore of their
// own, and Type 3 glyphs, patterns and soft masks in a context of their own, so a
// stream's pen does not reach its caller unless the stream pops past its own
// saves, which already hands the caller a wrong state.
let text = &context.get().text_state;
let pen = (text.text_matrix, text.text_line_matrix);
context.restore_state(device);
let text = &mut context.get_mut().text_state;
(text.text_matrix, text.text_line_matrix) = pen;
}
TypedInstruction::RestoreState(_) => context.restore_state(device),
TypedInstruction::FlatnessTolerance(_) => {
// Ignore for now.
}