M2: JBIG2 arithmetic near the end of an i32 doesn't overflow

A region's location, a refinement's offset, a symbol's corner, a Huffman
range line and a decoded integer of 2^31 could each overflow: a panic
wherever overflow is checked. The last four wrap, as a release build did.
Bitmap::combine saturates, which comes to the same: a side is at most
65,535, so a location that overflows is past the end of any page. What is
drawn doesn't change. Patch (12), after the numbers #5491 and #5569 take.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01AmsdeUCdTaD72jkDw2pJKY

crates/render/src/raster/tests.rs

@@ -3591,6 +3591,86 @@ fn jbig2_symbol_dictionaries_that_never_advance_terminate() {
     }
 }
 
+/// A JBIG2 stream can put a region, a reference or a symbol at the very end of what an `i32` holds,
+/// where adding to it overflowed: a panic wherever overflow is checked, a build's own tests included.
+/// A region or a symbol out there is off the page, so nothing draws. Vendored hayro-jbig2 patch: the arithmetic wraps, as
+/// a release build's did, or in `Bitmap::combine` saturates, which comes to the same. Three of the text
+/// streams are arithmetic-coded: one symbol on a strip of -2^31 + 1, with its bottom left as the corner
+/// placed, one on a strip of -2^31, and one refined by an offset of `i32::MIN`, which reads nothing of
+/// the old symbol and still draws. Two are Huffman-coded, each with its first S at an offset of
+/// 0x7FFFFFFF on a table's 32-bit range line, past what an `i32` holds, and are refused further on.
+#[test]
+fn jbig2_placements_at_the_end_of_an_i32_draw_nothing() {
+    const FAR_CORNER: &str = "0000000030000100000013000000100000000c0000000000000000420000000000010000010000001e000003fffdff02fefefe00000001000000014fdc3ce0205df55c36bfffac00000002062001010000001f000000100000000c000000000000000004000000000001969747cbe88bffac";
+    const STRIP: &str = "0000000030000100000013000000100000000c0000000000000000420000000000010000010000001e000003fffdff02fefefe00000001000000014fdda25e46956d3e0d3fffac00000002062001010000001f000000100000000c000000000000000004001000000001969747cbe5dbffac";
+    const UPPER_LINE: &str = "0000000030000100000013000000100000000c0000000000000000420000000000010000010000001d000003fffdff02fefefe00000001000000014fdaea38c99641e0c8ffac000000020620010100000038000000100000000c00000000000000000400110000000000010100000000000000000000000000000000003f7fffffff0000000000000000";
+    const LOWER_LINE: &str = "0000000030000100000013000000100000000c0000000000000000420000000000010000010000001d000003fffdff02fefefe00000001000000014fdaea38c99641e0c8ffac000000020620010100000038000000100000000c00000000000000000400110000000000010100000000000000000000000000000000003e7fffffff0000000000000000";
+    const OFFSET: &str = "0000000030000100000013000000100000000c0000000000000000420000000000010000010000001e000003fffdff02fefefe00000001000000014fdda9172f614a037ddfffac0000000206200101000000260000000800000006000000000000000004801200000001a9695690b3e5f44a2f105e30d3ffac";
+    let segment = |number: u32, kind: u8, data: &[u8]| {
+        let mut out = number.to_be_bytes().to_vec();
+        out.extend_from_slice(&[kind, 0, 1]);
+        out.extend_from_slice(&u32::try_from(data.len()).unwrap().to_be_bytes());
+        out.extend_from_slice(data);
+        out
+    };
+    let side = 8u32.to_be_bytes();
+    let page = |width: u32| {
+        let mut page = [width.to_be_bytes(), side].concat();
+        page.extend_from_slice(&[0; 8]); // resolution
+        page.extend_from_slice(&[0, 0, 0]); // flags, striping
+        segment(0, 48, &page)
+    };
+    let region = |width: u32, kind: u8, x: u32, y: u32, header: &[u8]| {
+        let mut region = [width.to_be_bytes(), side, x.to_be_bytes(), y.to_be_bytes()].concat();
+        region.push(0); // combination operator
+        region.extend_from_slice(header);
+        region.extend_from_slice(&[0x5a; 64]);
+        [page(width), segment(1, kind, &region)].concat()
+    };
+    let generic = |x, y| region(8, 38, x, y, &[0, 3, 0xff, 0xfd, 0xff, 2, 0xfe, 0xfe, 0xfe]); // template 0, AT pixels
+    // Immediate refinements of the page: template 0 with its usual AT pixels, with others, with typical
+    // prediction, and template 1.
+    let refined = |width, x, y, form: usize| {
+        region(width, 42, x, y, [&[0, 0xff, 0xff, 0xff, 0xff][..], &[0, 0xff, 0xff, 127, 127], &[2, 0xff, 0xff, 0xff, 0xff], &[1]][form])
+    };
+    let hex = |text: &str| (0..text.len() / 2).map(|i| u8::from_str_radix(&text[i * 2..i * 2 + 2], 16).unwrap()).collect::<Vec<u8>>();
+    let ink = |jbig2: Vec<u8>, width: u32, height: u32| {
+        let content = b"q 20 0 0 20 5 5 cm /Im1 Do Q";
+        let mut pdf = b"%PDF-1.7\n1 0 obj << /Type /Catalog /Pages 2 0 R >> endobj\n2 0 obj << /Type /Pages /Kids [3 0 R] /Count 1 >> endobj\n3 0 obj << /Type /Page /Parent 2 0 R /MediaBox [0 0 40 40] /Contents 4 0 R /Resources << /XObject << /Im1 5 0 R >> >> >> endobj\n".to_vec();
+        pdf.extend_from_slice(format!("4 0 obj << /Length {} >> stream\n", content.len()).as_bytes());
+        pdf.extend_from_slice(content);
+        pdf.extend_from_slice(b"\nendstream endobj\n");
+        pdf.extend_from_slice(
+            format!("5 0 obj << /Type /XObject /Subtype /Image /Width {width} /Height {height} /BitsPerComponent 1 /ColorSpace /DeviceGray /Filter /JBIG2Decode /Length {} >> stream\n", jbig2.len())
+                .as_bytes(),
+        );
+        pdf.extend_from_slice(&jbig2);
+        pdf.extend_from_slice(b"\nendstream endobj\ntrailer << /Root 1 0 R >>\n%%EOF\n");
+        let mut r = PageRenderer::new(Arc::new(pdf), RenderConfig::default());
+        let page = r.render(RenderRequest { page: 0, kind: RequestKind::Pixels, tile: None, scale: 1.0, tag: 0, ..Default::default() });
+        assert!(page.error.is_none(), "{:?}", page.error);
+        page.rgba.as_chunks::<4>().0.iter().filter(|p| p[0] < 128).count()
+    };
+    assert!(ink(generic(2, 0), 8, 8) > 0, "a region on the page draws");
+    for form in 0..4 {
+        assert!(ink(refined(8, 0, 0, form), 8, 8) > 0, "a refinement on the page draws: {form}");
+    }
+    let end = 0x7FFF_FFFFu32;
+    for (x, y) in [(end, 0), (0, end), (end - 7, 0), (0, end - 7), (end - 129, 0), (0, end - 129)] {
+        assert_eq!(ink(generic(x, y), 8, 8), 0, "generic at {x:#x}, {y:#x}");
+        for form in 0..4 {
+            assert_eq!(ink(refined(8, x, y, form), 8, 8), 0, "refinement {form} at {x:#x}, {y:#x}");
+        }
+    }
+    // Past a 32-bit word of the row, where the reference is read again.
+    assert_eq!(ink(refined(64, 0, end, 0), 64, 8), 0, "a wide refinement");
+    assert_eq!(ink(hex(FAR_CORNER), 16, 12), 0, "a symbol's far side past the end");
+    assert_eq!(ink(hex(STRIP), 16, 12), 0, "a strip of -2^31");
+    assert!(ink(hex(OFFSET), 16, 12) > 0, "a symbol refined by an offset of i32::MIN");
+    assert_eq!(ink(hex(UPPER_LINE), 16, 12), 0, "an upper range line past an i32");
+    assert_eq!(ink(hex(LOWER_LINE), 16, 12), 0, "a lower range line past an i32");
+}
+
 /// Item 1 of storytold/pdfcraft#623: a page's content used to be cut at `MAX_DECODED_STREAM`,
 /// so everything after the cut was lost (the text and the title block of the A1 sample). Content
 /// that expands by a few times over is read to its end, however large it is.

vendor/README.md

@@ -41,7 +41,7 @@ Other resource categories retain their existing parent-chain lookup.
 |---|---|---|---|---|
 | 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`) |
+| 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); (12) adding to a location, a reference offset, a symbol's corner or a Huffman range line near the end of an `i32`, and negating a decoded integer of 2^31, overflowed: a panic wherever overflow is checked. The refinement context, a text region's corners, the integer decoder and the Huffman table wrap, as a release build did, and `Bitmap::combine` saturates, which comes to the same, as a location that overflows is past the end of any page. What is drawn doesn't change | (1) `raster::tests::jbig2_regions_of_billions_of_pixels_are_refused`; (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`); (12) `raster::tests::jbig2_placements_at_the_end_of_an_i32_draw_nothing` |
 | lopdf | 0.45.0 | MIT | (1) PNG predictor rows longer than the data are refused before their buffers are allocated (a fuzzed `/Columns 4294967295` allocated two 4 GiB rows), and empty frames return without row buffers; (2) predictor row widths use saturating arithmetic or reject overflow; (3) sub-byte TIFF Predictor 2 scratch is bounded by the samples present in the input instead of the declared `/Colors`, aligned with [lopdf#589](https://github.com/J-F-Liu/lopdf/pull/589); (4) the object lookup keeps its cycle history through compressed objects, requires an ordinary in-file container, and caps the chain of indirect lookups at 16 (a chain of new objects, each a `/Length` compressed in a container whose own `/Length` names the next, or a stream whose `/Length` names the next stream, overflowed the stack: a dev build's 2 MiB thread within 800 hops); (5) object-stream members are parsed within their own extent (up to the next distinct offset), an entry whose offset repeats an earlier entry's is skipped (so a repeated object number can resolve to its earlier entry), and offsets are processed in index order; (6) `find_latest_trailer`: a rebuild takes a `/Type /XRef` stream dictionary as the trailer when the file has no `trailer` keyword (the latest in the file wins, as a later `trailer` would), so a concatenated or truncated file keeps its /Info and /ID instead of failing to load; a candidate whose /Root is the catalog beats one whose /Root is another dictionary, and an in-file /Root must match its generation (#2365) | (1) `inspect::tests::png_predictor_rows_longer_than_the_data_are_refused_before_allocating`, `inspect::tests::empty_png_predictor_frames_do_not_allocate_rows`; (2) `inspect::tests::tiff_subbyte_predictor_row_width_overflow_is_refused`; (3) `inspect::tests::tiff_subbyte_predictor_scratch_is_bounded_by_available_samples`, `inspect::tests::tiff_subbyte_predictors_keep_components_rows_and_padding`; (4) `inspect::tests::compressed_object_self_container_does_not_recurse`, `inspect::tests::compressed_object_mutual_containers_do_not_recurse`, `inspect::tests::object_stream_length_cycle_does_not_recurse`, `inspect::tests::compressed_object_container_chain_does_not_recurse`, `inspect::tests::compressed_length_chain_does_not_recurse`, `inspect::tests::plain_stream_length_chain_does_not_recurse`, `inspect::tests::compressed_objects_and_indirect_stream_length_still_load`, `inspect::tests::compressed_length_in_a_container_with_an_indirect_length_still_loads`; (5) `inspect::tests::object_stream_member_extents_bound_owned_strings`, `inspect::tests::object_stream_member_extents_preserve_index_order_and_whitespace`; (6) `inspect::tests::rebuilt_file_keeps_the_info_of_its_cross_reference_stream`, `inspect::tests::rebuilt_file_prefers_a_trailer_whose_root_is_the_catalog` |
 | hayro-syntax | 0.7.2 | Apache-2.0 OR MIT | (1) Page-tree cycle guard in `resolve_pages` (visited set + depth cap): a `/Kids` loop among compressed objects overflowed the stack and aborted the process; (2) `ccitt_size_ok`: CCITT images wider than 2^20 columns or over 2^28 pixels are not decoded (a fuzzed `/Columns 4294967295` allocated 4 GiB); (3) Flate/LZW predictor row widths are saturating `usize`, a zero width is refused and a row longer than the data is not allocated (a fuzzed `/Columns 9223372036854775807` wrapped to a 2^61-byte allocation and aborted); (4) the inline-image end-of-data check (`EI`) doesn't nest inside its own look-ahead and examines at most 256 candidates and steps (50 images with "EI" in their data ran for over ten minutes); an EI followed by a delimiter (EI%..., EI[...) ends the image like one followed by white space; only a regular character after EI skips the candidate; (5) a stream whose `/Length` is wrong is recovered only when `stream` is the next token — scanning ahead to a later object's `stream` made an indirect appearance-state dictionary (Quartz checkboxes: `/AP /N` → `<< /Yes … /Off … >>`) render as a non-form, so the widget was skipped; (6) JPX rescaling uses an exact integer sample range for 1–32-bit components (32 shifted past u32, and floating-point maxima at 25–31 bits wrapped to zero), and refuses zero-sized rows; (7) `decode_limit`: Flate (through flate2 and the fallback inflater), LZW, RunLength and ASCII85 never write past `MAX_DECODED_STREAM` (256 MiB), or, for the last filter of an image of known size, past twice its pixel bytes (a predictor tag byte per byte), at most 1 GiB; `Stream::decoded_within` for budgeted callers; a page's `/Contents` array shares one `MAX_DECODED_STREAM` (a 2 MB page whose content stream or 8 × 8 image inflated to 2 GB took the renderer past 3 GB in under a second; naming the stream twenty times in `/Contents`, 5 GB); (8) high-precision numbers (jsPDF MediaBox coordinates with over 19 digits) parse without overflowing the u64 mantissa: fractional digits past it are dropped, integer digits past it scale the value (a real, kept finite); (9) large dictionary indexes are built on first use and shared across repeated reads within each PDF (#307); the validated-byte cache is bounded, reader contexts remain separate, repairs and inline/content dictionaries bypass sharing, and small dictionaries stay eager; (10) decoded object-stream slots publish once under contention, cold loading rejects recursive dependencies, and xref repair serializes without holding recursive read guards; this permits one parser per native render pool with private worker caches; (11) `sync.rs`: a poisoned lock is recovered instead of unwrapped (a worker panic no longer cascades into every reader of the same PDF), and xref repair takes a blocking write lock instead of asserting a non-blocking one; (12) `SegmentList` (`util.rs`) returns `None` for an out-of-range index instead of panicking; (13) a page's `/UserUnit` scales `render_dimensions` and `initial_transform`, so the page and everything on it are sized in points, as Acrobat shows them; it is read as Acrobat reads it (the page's own entry, not inherited; a number from 1 up, at most 75,000; anything else counts as 1), and a page without it keeps exactly the transform it had; (14) revision 2–4 passwords are tried as given and then in PDFDocEncoding (`legacy_passwords` in `crypto/mod.rs`, which resolves the upstream `TODO: Convert to PDFDocEncoding`): passwords arrive as UTF-8 text, so a password with characters outside ASCII (`Çok güzel`, `ılık€`) written in PDFDocEncoding, as ISO 32000-2 §7.6.4.3.2 asks and qpdf and Acrobat write it, was always wrong; (15) page content is read a piece at a time (`page::ContentReader`, `Page::content_reader`): plain streams and Flate streams without a predictor are decoded as they are read, with a budget of 64 times their compressed size and never less than `MAX_DECODED_STREAM` (a stream that expands past it is cut and reported); other streams are decoded whole, as before, and share `MAX_DECODED_STREAM`. The content tokenizer reads a window at a time (`UntypedIter::new_window`, `TypedIter::needs_more`, `TypedIter::committed`): an instruction that runs past the window is not decided until more data follows, which `Reader` records by flagging reads and `at_end` past the end of the data, including through the clones the parser makes. The Flate decoder keeps its own 32 KiB history, so it pauses at any output size. `ContentReader::new` reuses raw/decrypted stream bytes for budget accounting and piece creation, and `decoded_raw_within` applies the existing Whole-stream filters and limits to those bytes without decrypting twice; (16) revision 5–6 (AES-256) passwords are tried in their SASLprep form (RFC 4013, then UTF-8, at most 127 bytes, as ISO 32000-2 §7.6.4.3.3 Algorithm 2.A asks and pdfcraft-crypt writes them) and then, if that differs, as given (`aes256_passwLine truncated
 | winit | 0.30.13 | Apache-2.0 | (1) on Windows 11 (build 22000 and later), `WM_DPICHANGED` applies the rect Windows suggests. It used to nudge the window onto the monitor `MonitorFromWindow` names, which during a drag is still the monitor being left; the nudge sent another `WM_DPICHANGED`, so a window dragged to a monitor with another scale factor grew and stayed on the wrong monitor at the wrong scale (#324). Backport of winit master 488c036a ([winit#4341](https://github.com/rust-windowing/winit/pull/4341)), which no 0.30 release has; Windows 10 keeps the old adjustment, as on winit master. (2) on Wayland, a seat's text input is destroyed when the seat goes away, not whenever it loses a capability: losing any capability (a touch screen or tablet unplugged, a remote-desktop session ending) destroyed it, and only an added capability recreated it, so IME stopped working until restart. Port of [winit#4747](https://github.com/rust-windowing/winit/pull/4747); (3) on Windows, an IME composition reports its cursor from `GCS_CURSORPOS` only when `WM_IME_COMPOSITION` says it is set, and at the end of the composition otherwise: the Microsoft Korean IME never sets it, so the cursor read as 0 (egui then drew no caret while composing; it now draws it after the syllable). Port of [winit#4746](https://github.com/rust-windowing/winit/pull/4746); (4) on Windows, a hidden window is not maximized until it is shown, and a hidden window shown while maximized gets one `ShowWindow(SW_MAXIMIZE)`: `SW_MAXIMIZE` shows a hidden window, so PdfCraft, which eframe keeps hidden until its first frame is drawn, appeared unpainted (white) when it restored a maximized window, and could lose its focus. Port of [winit#4587](https://github.com/rust-windowing/winit/pull/4587) (the later, focus-safe form of [winit#4575](https://github.com/rust-windowing/winit/pull/4575)); (5) on X11, when allowing or disallowing IME replaces the focused window's input context (egui does it each time a text field gains or loses focus), the new context is focused: no focus event follows, so it stayed unfocused until the window lost and regained focus. Port of [winit#4727](https://github.com/rust-windowing/winit/pull/4727); (6) on macOS, `insertText` commits through IME when a composition was started (`pending_commit`, set by `setMarkedText`) rather than when marked text is left: input methods that end a composition with `unmarkText` before `insertText` lost the text, and Apple Korean dropped the key typed after a syllable (`한` then `5` or `;`); other `insertText` calls stay `KeyboardInput`; a commit outside a key press (a candidate clicked with the mouse, dictation) clears the marked text and leaves no key to swallow, as in [winit#4748](https://github.com/rust-windowing/winit/pull/4748) (without it the next key, such as Backspace, was lost). `validAttributesForMarkedText` lists the underline and marked-clause attributes, without which some input methods don't compose. Port of [winit#4650](https://github.com/rust-windowing/winit/pull/4650), the 0.30 backport of [winit#4651](https://github.com/rust-windowing/winit/pull/4651) (merged on winit master), with the underline attribute spelled as AppKit's `NSUnderlineStyleAttributeName` (`NSUnderline`); (7) on macOS, disallowing IME with a composition in progress (focus leaving a text field) tells the input method to discard its marked text (`discardMarkedText`): it kept composing it once IME was allowed again, so the abandoned syllable came back (`하`, then `가` typed in the next field, became `학`, then `하` + `가`; Japanese `か` then `さ` became `傘`). Port of [winit#4745](https://github.com/rust-windowing/winit/pull/4745); (8) on macOS, text inserted outside a key press without a composition (the emoji picker) is reported as `Ime::Commit`; it was dropped. Port of the emoji-picker part of [winit#4749](https://github.com/rust-windowing/winit/pull/4749) (0.30 backport of [winit#4748](https://github.com/rust-windowing/winit/pull/4748)); its `selectedRange` change for dictation is left out because it switches on press-and-hold for every held key (an accent menu instead of key repeat, and the chosen accent added after the repeated letters); (9) on macOS, a key whose text was committed through IME isn't also sent as `KeyboardInput` unless AppKit forwards it as a command (Enter): Apple Korean answers Space with no syllable in progress with `setMarkedText(" ")`, `insertText(" ")`, `setMarkedText("")`, and the last call reset winit's state, so the space arrived twice. Same goal as [winit#4478](https://github.com/rust-windowing/winit/pull/4478), whose changes don't reach this call order (macOS 14); to be proposed upstream there; (10) on macOS, when the first key in a fresh app reaches Apple Korean's `insertText` as a raw compatibility jamo instead of starting a composition, that key is interpreted once more, synchronously, before it is sent as `KeyboardInput` (g k s typed ㅎㅏㄴ instead of 한); only an unmodified, Line truncated

vendor/hayro-jbig2/src/bitmap.rs

@@ -149,7 +149,8 @@ impl Bitmap {
         // TODO: Figure out how we can optimize this, especially since this is a
         // bottleneck for symbols/patterns.
         let dest_x_start = x.max(0);
-        let dest_x_end = (x + other.width as i32).min(self.width as i32);
+        // Saturating: a location can be anywhere an `i32` reaches, and past the end it is off the page.
+        let dest_x_end = x.saturating_add(other.width as i32).min(self.width as i32);
 
         if dest_x_start >= dest_x_end {
             return;
@@ -160,7 +161,7 @@ impl Bitmap {
         let dest_x_end = dest_x_end as u32;
 
         for src_y in 0..other.height {
-            let dest_y = y + src_y as i32;
+            let dest_y = y.saturating_add(src_y as i32);
             if dest_y < 0 || dest_y >= self.height as i32 {
                 continue;
             }

vendor/hayro-jbig2/src/decode/generic_refinement.rs

@@ -179,10 +179,12 @@ impl<'a> RefinementContextGatherer<'a> {
 
     pub(crate) fn start_row(&mut self, region: &Bitmap, reference: &Bitmap, y: u32) {
         self.reg_y = y;
-        let ref_y = y as i32 - self.reference_dy;
+        // The offsets can be anywhere an `i32` reaches, so coordinates in the reference wrap here and
+        // below. Wrapped, they are off the reference, whose pixels there read as 0.
+        let ref_y = (y as i32).wrapping_sub(self.reference_dy);
         // This will on purpose wrap to a very large `u32` for negative values, such that
         // they resolve to 0 in `ContextGatherer::load_word`.
-        let ref_x0 = (-self.reference_dx) as u32;
+        let ref_x0 = self.reference_dx.wrapping_neg() as u32;
 
         self.reg_cur_x = 0;
         self.reg_m1 = if y >= 1 {
@@ -193,9 +195,9 @@ impl<'a> RefinementContextGatherer<'a> {
         self.reg_cur = 0;
 
         self.ref_cur_x = 0;
-        self.ref_m1 = ContextGatherer::load_word(reference, (ref_y - 1) as u32, 0);
+        self.ref_m1 = ContextGatherer::load_word(reference, ref_y.wrapping_sub(1) as u32, 0);
         self.ref_cur = ContextGatherer::load_word(reference, ref_y as u32, 0);
-        self.ref_p1 = ContextGatherer::load_word(reference, (ref_y + 1) as u32, 0);
+        self.ref_p1 = ContextGatherer::load_word(reference, ref_y.wrapping_add(1) as u32, 0);
 
         self.ctx = match self.template {
             RefinementTemplate::Template1 => {
@@ -257,7 +259,7 @@ impl<'a> RefinementContextGatherer<'a> {
             self.reg_cur = ContextGatherer::load_word(region, self.reg_y, new_start);
         }
 
-        let ref_x_signed = x as i32 - self.reference_dx;
+        let ref_x_signed = (x as i32).wrapping_sub(self.reference_dx);
         if ref_x_signed < 0 {
             self.ref_cur_x = 0;
             self.ref_m1 = 0;
@@ -268,18 +270,20 @@ impl<'a> RefinementContextGatherer<'a> {
 
             if ref_x + 1 >= self.ref_cur_x + WORD_BITS || ref_x < self.ref_cur_x {
                 let new_start = ref_x.saturating_sub(1);
-                let ref_y = self.reg_y as i32 - self.reference_dy;
+                let ref_y = (self.reg_y as i32).wrapping_sub(self.reference_dy);
                 self.ref_cur_x = new_start;
-                self.ref_m1 = ContextGatherer::load_word(reference, (ref_y - 1) as u32, new_start);
+                self.ref_m1 =
+                    ContextGatherer::load_word(reference, ref_y.wrapping_sub(1) as u32, new_start);
                 self.ref_cur = ContextGatherer::load_word(reference, ref_y as u32, new_start);
-                self.ref_p1 = ContextGatherer::load_word(reference, (ref_y + 1) as u32, new_start);
+                self.ref_p1 =
+                    ContextGatherer::load_word(reference, ref_y.wrapping_add(1) as u32, new_start);
             }
         }
     }
 
     #[inline(always)]
     pub(crate) fn tpgr_all_same(&self, x: u32) -> bool {
-        let ref_x = (x as i32 - self.reference_dx) as u32;
+        let ref_x = (x as i32).wrapping_sub(self.reference_dx) as u32;
         let rbx = ref_x.wrapping_sub(self.ref_cur_x);
 
         #[inline(always)]
@@ -310,7 +314,7 @@ impl<'a> RefinementContextGatherer<'a> {
 
     #[inline(always)]
     pub(crate) fn ref_center_pixel(&self, x: u32) -> u8 {
-        let ref_x = (x as i32 - self.reference_dx) as u32;
+        let ref_x = (x as i32).wrapping_sub(self.reference_dx) as u32;
         let rbx = ref_x.wrapping_sub(self.ref_cur_x);
 
         ContextGatherer::get_buf_pixel(self.ref_cur, rbx) as u8
@@ -329,7 +333,7 @@ impl<'a> RefinementContextGatherer<'a> {
     #[inline(always)]
     fn gather_template0_default(&mut self, _region: &Bitmap, _reference: &Bitmap, x: u32) -> u16 {
         let bx = x - self.reg_cur_x;
-        let ref_x = (x as i32 - self.reference_dx) as u32;
+        let ref_x = (x as i32).wrapping_sub(self.reference_dx) as u32;
         let rbx = ref_x.wrapping_sub(self.ref_cur_x);
 
         let new_pixels = (ContextGatherer::get_buf_pixel(self.reg_m1, bx + 1) << 10)
@@ -345,12 +349,12 @@ impl<'a> RefinementContextGatherer<'a> {
     #[inline(always)]
     fn gather_template0_custom(&mut self, region: &Bitmap, reference: &Bitmap, x: u32) -> u16 {
         let bx = x - self.reg_cur_x;
-        let ref_x_i = x as i32 - self.reference_dx;
+        let ref_x_i = (x as i32).wrapping_sub(self.reference_dx);
         let rbx = ref_x_i as u32 - self.ref_cur_x;
 
         let xi = x as i32;
         let yi = self.reg_y as i32;
-        let ref_y = yi - self.reference_dy;
+        let ref_y = yi.wrapping_sub(self.reference_dy);
         let at1 = self.at_pixels[0];
         let at2 = self.at_pixels[1];
 
@@ -360,8 +364,8 @@ impl<'a> RefinementContextGatherer<'a> {
             | (ContextGatherer::get_buf_pixel(self.reg_m1, bx + 1) << 10)
             | (ContextGatherer::get_buf_pixel(self.reg_cur, bx.wrapping_sub(1)) << 9)
             | ((reference.get_pixel(
-                (ref_x_i + at2.x as i32) as u32,
-                (ref_y + at2.y as i32) as u32,
+                ref_x_i.wrapping_add(at2.x as i32) as u32,
+                ref_y.wrapping_add(at2.y as i32) as u32,
             ) as u16)
                 << 8)
             | (ContextGatherer::get_buf_pixel(self.ref_m1, rbx.wrapping_add(1)) << 6)
@@ -375,7 +379,7 @@ impl<'a> RefinementContextGatherer<'a> {
     #[inline(always)]
     fn gather_template1(&mut self, _region: &Bitmap, _reference: &Bitmap, x: u32) -> u16 {
         let bx = x - self.reg_cur_x;
-        let ref_x = (x as i32 - self.reference_dx) as u32;
+        let ref_x = (x as i32).wrapping_sub(self.reference_dx) as u32;
         let rbx = ref_x.wrapping_sub(self.ref_cur_x);
 
         let new_pixels = (ContextGatherer::get_buf_pixel(self.reg_m1, bx + 1) << 7)

vendor/hayro-jbig2/src/decode/text.rs

@@ -173,23 +173,26 @@ pub(crate) fn decode_with(
             }
 
             let symbol_s = current_s;
+            // From the corner a symbol is placed by to its far side. The strip and the offset can
+            // be anywhere an `i32` reaches, and wrapped, the symbol is off the region.
+            let back = |corner: i32, size: i32| corner.wrapping_sub(size).wrapping_add(1);
 
             let (x, y) = if !header.flags.transposed {
                 match header.flags.reference_corner {
                     ReferenceCorner::TopLeft => (symbol_s, symbol_t),
-                    ReferenceCorner::TopRight => (symbol_s - symbol_width + 1, symbol_t),
-                    ReferenceCorner::BottomLeft => (symbol_s, symbol_t - symbol_height + 1),
+                    ReferenceCorner::TopRight => (back(symbol_s, symbol_width), symbol_t),
+                    ReferenceCorner::BottomLeft => (symbol_s, back(symbol_t, symbol_height)),
                     ReferenceCorner::BottomRight => {
-                        (symbol_s - symbol_width + 1, symbol_t - symbol_height + 1)
+                        (back(symbol_s, symbol_width), back(symbol_t, symbol_height))
                     }
                 }
             } else {
                 match header.flags.reference_corner {
                     ReferenceCorner::TopLeft => (symbol_t, symbol_s),
-                    ReferenceCorner::TopRight => (symbol_t - symbol_width + 1, symbol_s),
-                    ReferenceCorner::BottomLeft => (symbol_t, symbol_s - symbol_height + 1),
+                    ReferenceCorner::TopRight => (back(symbol_t, symbol_width), symbol_s),
+                    ReferenceCorner::BottomLeft => (symbol_t, back(symbol_s, symbol_height)),
                     ReferenceCorner::BottomRight => {
-                        (symbol_t - symbol_width + 1, symbol_s - symbol_height + 1)
+                        (back(symbol_t, symbol_width), back(symbol_s, symbol_height))
                     }
                 }
             };

vendor/hayro-jbig2/src/huffman_table.rs

@@ -448,11 +448,11 @@ impl HuffmanNode {
                     // 4) "Otherwise, if table line I is the lower range table line for this
                     //    table, then set: HTVAL = RANGELOW[I] − HTOFFSET"
                     // 5) "Otherwise, set: HTVAL = RANGELOW[I] + HTOFFSET"
-                    // `HTVAL`
+                    // `HTVAL`. Wrapping: a range line's offset can take it past what an `i32` holds.
                     let value = if leaf.is_lower {
-                        leaf.range_low - range_offset
+                        leaf.range_low.wrapping_sub(range_offset)
                     } else {
-                        leaf.range_low + range_offset
+                        leaf.range_low.wrapping_add(range_offset)
                     };
 
                     return Ok(Some(value));

vendor/hayro-jbig2/src/integer_decoder.rs

@@ -70,7 +70,8 @@ impl IntegerDecoder {
         if s == 0 {
             Some(v as i32)
         } else if v > 0 {
-            Some(-(v as i32))
+            // Wrapping: `V` can be 2^31, whose negative is `i32::MIN`, as the cast already reads it.
+            Some((v as i32).wrapping_neg())
         } else {
             None
         }