M2: every match on RenderWarning names MalformedIndexedImage, and an Indexed lookup string given by reference is read (ISO 32000-2 8.6.6.3)

- render_warning_text (crates/automation/src/pages.rs, on main since this
  branch was cut) matched RenderWarning exhaustively and did not build
  with the new variant. It now names it, in the CLI's words, so
  page_render and render_preview report the skip. A workspace search
  finds no other match on RenderWarning outside pdfcraft-render.
- An Indexed lookup is a string or a stream (8.6.6.3). Indexed::new and
  is_malformed_indexed tried it as a stream first; a failed stream read
  of a reference consumed the reference, so a string lookup given by
  reference was never found and the image was skipped. The lookup is now
  read once and dispatched by type, in both places.
- hival is judged before the base: an out-of-range hival rules the space
  out even when the base cannot be read (the table size still needs the
  base, so a usable hival keeps today's handling there).

The size check is unchanged: hival is range-checked to 0..=255 before
(hival + 1) * m is formed with checked_add/checked_mul.

Tests (each seen failing with a fault injected): bounds at DeviceCMYK,
DeviceGray and hival 255 (exact and one short); hivals past u32/u64/any
integer, negative and fractional (with unchecked arithmetic and the range
widened the test panics with "attempt to multiply with overflow"); a
lookup string by reference (fails with the old stream-then-string read);
an unreadable base with hival 300; an undecodable lookup stream; and
page_render reporting the skip (without the new arm the crate does not
build, E0004).

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Pq7HyCfwzyRXj4VfQAVVdv

crates/automation/src/pages.rs

@@ -345,6 +345,7 @@ fn render_warning_text(warning: pdfcraft_render::RenderWarning) -> &'static str
     match warning {
         RenderWarning::ContentTruncated => "content past the page's safety budget was skipped",
         RenderWarning::ColourFallback => "a colour that could not be computed was painted in a fallback colour",
+        RenderWarning::MalformedIndexedImage => "an image with a malformed Indexed colour table was not drawn",
     }
 }
 

crates/automation/tests/it/render_warnings.rs

@@ -96,6 +96,33 @@ fn a_clean_page_renders_to_the_png_alone() {
     let _ = std::fs::remove_dir_all(dir);
 }
 
+/// An image whose Indexed lookup table is too short (ISO 32000-2 §8.6.6.3) is skipped, and
+/// `page_render` says so in the words `pdfcraft-cli render` prints.
+#[test]
+fn page_render_reports_a_skipped_malformed_indexed_image() {
+    let dir = std::env::temp_dir().join(format!("pdfcraft-render-warnings-indexed-{}", std::process::id()));
+    let _ = std::fs::remove_dir_all(&dir);
+    std::fs::create_dir_all(&dir).unwrap();
+    let content = "q 200 0 0 200 0 0 cm /Im Do Q";
+    // hival 7 over DeviceRGB needs 24 bytes; the table holds 6.
+    let pdf = format!(
+        "%PDF-1.7\n1 0 obj << /Type /Catalog /Pages 2 0 R >> endobj\n\
+         2 0 obj << /Type /Pages /Kids [3 0 R] /Count 1 >> endobj\n\
+         3 0 obj << /Type /Page /Parent 2 0 R /MediaBox [0 0 200 200] /Resources << /XObject << /Im 5 0 R >> >> /Contents 4 0 R >> endobj\n\
+         4 0 obj << /Length {} >> stream\n{content}\nendstream endobj\n\
+         5 0 obj << /Type /XObject /Subtype /Image /Width 2 /Height 1 /BitsPerComponent 8 /ColorSpace [/Indexed /DeviceRGB 7 <FF0000 00FF00>] /Filter /ASCIIHexDecode /Length 5 >> stream\n0001>\nendstream endobj\n\
+         trailer << /Root 1 0 R >>\n%%EOF",
+        content.len()
+    );
+    std::fs::write(dir.join("indexed.pdf"), pdf).unwrap();
+    let mut a = Automation::new().with_root(&dir).unwrap();
+    let doc = open(&mut a, "indexed.pdf");
+    let out = a.call("page_render", &json!({ "doc": doc, "page": 1, "dpi": 72 })).unwrap();
+    let Some(Content::Json(report)) = out.get(1) else { panic!("expected the warnings as JSON: {out:?}") };
+    assert_eq!(report["warnings"], json!(["an image with a malformed Indexed colour table was not drawn"]));
+    let _ = std::fs::remove_dir_all(dir);
+}
+
 /// Over MCP the warnings are a text block after the image and the call's `structuredContent`.
 #[cfg(feature = "mcp")]
 #[test]

crates/render/tests/it/indexed_lookup.rs

@@ -173,3 +173,59 @@ fn a_page_with_several_malformed_images_reports_the_warning_once_and_draws_the_r
     let at = (195 * page.width as usize + 5) * 4;
     assert_eq!(page.rgba.get(at..at + 3), Some(&[0u8, 0, 255][..]), "content after the skipped images still draws");
 }
+
+#[test]
+fn a_lookup_string_given_by_reference_is_read() {
+    // A lookup is a byte string or a stream (ISO 32000-2 §8.6.6.3), and either may be indirect.
+    // A string by reference used to be missed: trying it as a stream consumed the reference.
+    let full: &[u8] = b"<FF0000 00FF00>";
+    assert_drawn("[/Indexed /DeviceRGB 1 6 0 R]", &[full]);
+    let short: &[u8] = b"<FF0000 00FF>";
+    assert_skipped("[/Indexed /DeviceRGB 1 6 0 R]", &[short]);
+    // Something that is neither a string nor a stream is no table.
+    let number: &[u8] = b"42";
+    assert_skipped("[/Indexed /DeviceRGB 1 6 0 R]", &[number]);
+}
+
+#[test]
+fn the_size_check_holds_at_the_bounds_of_hival_and_the_base() {
+    // Four components (DeviceCMYK): hival 1 needs exactly 8 bytes.
+    let cmyk = |table: &str| format!("[/Indexed /DeviceCMYK 1 <{table}>]");
+    let page = render(pdf(&cmyk("FF000000 00FF0000"), DRAW_IMAGE, &[]));
+    assert!(page.warnings.is_empty(), "exact length: {:?}", page.warnings);
+    assert_ne!(halves(&page), WHITE, "exact length draws");
+    assert_skipped(&cmyk("FF000000 00FF00"), &[]);
+    // One component (DeviceGray): hival 0 needs one byte, and none is not enough.
+    let page = render(pdf("[/Indexed /DeviceGray 0 <00>]", DRAW_IMAGE, &[]));
+    assert!(page.warnings.is_empty(), "{:?}", page.warnings);
+    assert_skipped("[/Indexed /DeviceGray 0 <>]", &[]);
+    // hival 255 over DeviceRGB needs 768 bytes: 767 is one short.
+    assert_skipped(&format!("[/Indexed /DeviceRGB 255 <FF0000 00FF00{}>]", "00".repeat(3 * 254 - 1)), &[]);
+}
+
+#[test]
+fn a_hival_that_would_overflow_a_size_is_ruled_out_without_panicking() {
+    // Values whose (hival + 1) × components would overflow a 32-bit or 64-bit size, or that do
+    // not fit an integer at all, never reach the multiplication: they fail the 0..=255 test.
+    for hival in ["4294967295", "4294967296", "18446744073709551615", "99999999999999999999999", "-2147483649", "256", "255.5"] {
+        assert_skipped(&format!("[/Indexed /DeviceRGB {hival} <FF0000 00FF00>]"), &[]);
+    }
+    // 255.0 written as a real is the integer 255.
+    assert_drawn(&format!("[/Indexed /DeviceRGB 255.0 <FF0000 00FF00{}>]", "00".repeat(3 * 254)), &[]);
+}
+
+#[test]
+fn an_unusable_hival_is_judged_even_when_the_base_cannot_be_read() {
+    // The base is unknown, so the table size cannot be judged, but hival 300 is out of range
+    // whatever the base.
+    assert_skipped("[/Indexed /NoSuchSpace 300 <00>]", &[]);
+    // With a usable hival, an unreadable base keeps its existing handling: no Indexed warning.
+    let page = render(pdf("[/Indexed /NoSuchSpace 1 <00>]", DRAW_IMAGE, &[]));
+    assert!(!page.warnings.contains(&RenderWarning::MalformedIndexedImage), "{:?}", page.warnings);
+}
+
+#[test]
+fn a_lookup_stream_that_cannot_be_decoded_is_no_table() {
+    let broken: &[u8] = b"<< /Length 6 /Filter /FlateDecode >>\nstream\nnot-zl\nendstream";
+    assert_skipped("[/Indexed /DeviceRGB 1 6 0 R]", &[broken]);
+}

vendor/README.md

@@ -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/color.rs

@@ -999,13 +999,10 @@ impl Indexed {
         let hival = iter.next::<u32>()?.min(u8::MAX as u32) as u8;
 
         let values = {
-            let data = iter
-                .next::<Stream<'_>>()
-                .and_then(|s| s.decoded().ok())
-                .or_else(|| {
-                    iter.next::<object::String<'_>>()
-                        .map(|s| Cow::Owned(s.to_vec()))
-                })?;
+            // PdfCraft patch (60): read once and then by type, so a string lookup given by an
+            // indirect reference is found (a failed stream read had already consumed the
+            // reference).
+            let data = iter.next::<Object<'_>>().and_then(indexed_lookup)?;
 
             let num_components = base_color_space.num_components();
 
@@ -1036,8 +1033,10 @@ impl Indexed {
 /// PdfCraft patch (60): whether `object` is an `/Indexed` colour space that ISO 32000-2
 /// §8.6.6.3 rules out: `hival` is not an integer in 0..=255, or the lookup table is missing or
 /// shorter than m × (hival + 1) bytes for a base space of m components. A longer table is fine
-/// (its first bytes are used). An Indexed space whose base cannot be read is not judged here,
-/// so its existing handling is unchanged.
+/// (its first bytes are used). The lookup may be a string or a stream, given in place or by
+/// reference. An Indexed space whose base cannot be read is judged only by its `hival` (the
+/// table's size depends on the base), so with a usable `hival` its existing handling is
+/// unchanged.
 ///
 /// Upstream treated such a space as unreadable, and an image that named it then fell back to
 /// DeviceGray: its indices were drawn as near-black grey levels, even indices whose entries
@@ -1053,19 +1052,21 @@ pub(crate) fn is_malformed_indexed(object: &Object<'_>, cache: &Cache) -> bool {
     if !matches!(family.deref(), INDEXED | I) {
         return false;
     }
-    let Some(base) = iter
-        .next::<Object<'_>>()
-        .and_then(|o| ColorSpace::new(o, cache))
-    else {
-        return false;
-    };
+    let base = iter.next::<Object<'_>>();
     let Some(hival) = iter.next::<object::Number>().and_then(|n| {
         let value = n.as_f64();
-        // A real with a fraction, a negative number or one past 255 is not a usable `hival`.
+        // A real with a fraction, a negative number or one past 255 is not a usable `hival`
+        // (NaN and the infinities fail the range test too).
         (value.fract() == 0.0 && (0.0..=255.0).contains(&value)).then(|| n.as_i64())
     }) else {
+        // Judged before the base: an unusable `hival` rules the space out whatever the base.
         return true;
     };
+    let Some(base) = base.and_then(|o| ColorSpace::new(o, cache)) else {
+        return false;
+    };
+    // `hival` is at most 255 here, so this cannot overflow; it is checked all the same, and a
+    // size that did not fit would rule the space out rather than wrap.
     let Some(needed) = usize::try_from(hival)
         .ok()
         .and_then(|h| h.checked_add(1))
@@ -1074,12 +1075,23 @@ pub(crate) fn is_malformed_indexed(object: &Object<'_>, cache: &Cache) -> bool {
         return true;
     };
     let lookup_len = iter
-        .next::<Stream<'_>>()
-        .and_then(|s| s.decoded().ok().map(|d| d.len()))
-        .or_else(|| iter.next::<object::String<'_>>().map(|s| s.as_bytes().len()));
+        .next::<Object<'_>>()
+        .and_then(indexed_lookup)
+        .map(|d| d.len());
     lookup_len.is_none_or(|len| len < needed)
 }
 
+/// PdfCraft patch (60): an Indexed space's lookup table, a byte string or a stream (ISO 32000-2
+/// §8.6.6.3), with a stream's filters applied. `None` for any other object or a stream that
+/// cannot be decoded.
+fn indexed_lookup(lookup: Object<'_>) -> Option<Cow<'_, [u8]>> {
+    match lookup {
+        Object::Stream(s) => s.decoded().ok(),
+        Object::String(s) => Some(Cow::Owned(s.to_vec())),
+        _ => None,
+    }
+}
+
 impl ToRgb for Indexed {
     fn convert_f32(&self, input: &[f32], output: &mut [u8], _: bool) -> Option<()> {
         let mut indexed = vec![0.0; input.len() * self.base.num_components() as usize];