M2: a luminosity soft mask in a DeviceCMYK group converts as ISO 32000-2 10.4.2 says, so 100% K masks fully (#4423)

A luminosity soft mask is drawn into an RGB buffer and its value read
as the luminance of that buffer. A /DeviceCMYK colour reached the
buffer through the CMYK display profile, where 100% K is a dark grey,
so a mask painted 100% K in a DeviceCMYK group let about an eighth of
the masked paint through (mask value 0.125 instead of 0).

ISO 32000-2 11.5.3 converts a device-space group colour to gray "with
no compensation for gamma or other colour calibration", and 10.4.2.3
gives DeviceCMYK to DeviceGray as
gray = 1 - min(1, 0.3 c + 0.59 m + 0.11 y + k).

hayro-interpret patch (63): when the group colour space of a luminosity
soft mask is /DeviceCMYK itself (not an ICC-based or calibrated space),
the mask's context paints /DeviceCMYK fill and stroke colours as that
gray, and a four-component /BC becomes the same gray. A gray reads back
as itself through any luminance weights that sum to one. CMYK on the
page, CMYK in DeviceGray/DeviceRGB mask groups, and CMYK images,
shadings and tiling patterns inside such a mask keep the profile.

Tests: color::device_cmyk_gray_tests (hayro-interpret) and
it::luminosity_group_space (pdfcraft-render); the three DeviceCMYK
render tests fail with the patch reverted.


Claude-Session: https://claude.ai/code/session_0175FWj4xFhMhSH3UpMU8DSC

Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>

crates/render/tests/it/luminosity_group_space.rs

@@ -0,0 +1,132 @@
+//! A luminosity soft mask takes its values from the gray of its group's colour (ISO 32000-2
+//! §11.5.3). In a `/DeviceCMYK` group that gray is `1 - min(1, 0.3 c + 0.59 m + 0.11 y + k)`
+//! (§10.4.2.3), so 100% K masks fully, whatever profile CMYK is displayed through.
+
+use std::sync::Arc;
+
+use pdfcraft_render::{PageRenderer, RenderConfig, RenderRequest, RequestKind};
+
+/// The page's grey backdrop, `0.5 g`, as the renderer writes it.
+const BACKDROP: f64 = 128.0;
+
+fn pdf(objects: &[String]) -> Vec<u8> {
+    let mut out = b"%PDF-1.7\n".to_vec();
+    let mut offsets = Vec::new();
+    for (i, body) in objects.iter().enumerate() {
+        offsets.push(out.len());
+        out.extend_from_slice(format!("{} 0 obj\n{body}\nendobj\n", i + 1).as_bytes());
+    }
+    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\n<< /Size {} /Root 1 0 R >>\nstartxref\n{xref}\n%%EOF\n", objects.len() + 1).as_bytes());
+    out
+}
+
+fn stream(dict: &str, content: &str) -> String {
+    format!("<< {dict} /Length {} >>\nstream\n{content}\nendstream", content.len())
+}
+
+fn render(bytes: Vec<u8>) -> (Vec<u8>, u32) {
+    let mut renderer = PageRenderer::new(Arc::new(bytes), RenderConfig::default());
+    let page = renderer.render(RenderRequest { page: 0, kind: RequestKind::Pixels, tile: None, scale: 1.0, tag: 0, preview: false });
+    assert!(page.error.is_none(), "{:?}", page.error);
+    (page.rgba.to_vec(), page.width)
+}
+
+fn pixel(rgba: &[u8], width: u32, x: u32, y: u32) -> [u8; 3] {
+    let offset = usize::try_from((y * width + x) * 4).unwrap();
+    [rgba[offset], rgba[offset + 1], rgba[offset + 2]]
+}
+
+/// Red filled over the grey backdrop under a luminosity mask whose group, in `space`, paints its
+/// left half with `paint`; its right half is the backdrop `/BC` (`bc`, when given). Returns the
+/// mask values read back from the left and the right half.
+fn mask_values(space: &str, paint: &str, bc: Option<&str>) -> (f64, f64) {
+    let bc = bc.map(|bc| format!("/BC {bc}")).unwrap_or_default();
+    let objects = [
+        "<< /Type /Catalog /Pages 2 0 R >>".to_string(),
+        "<< /Type /Pages /Kids [3 0 R] /Count 1 >>".to_string(),
+        "<< /Type /Page /Parent 2 0 R /MediaBox [0 0 100 100] /Contents 4 0 R /Resources << /ExtGState << /M 5 0 R >> >> >>".to_string(),
+        stream("", "0.5 g 0 0 100 100 re f /M gs 1 0 0 rg 0 0 100 100 re f"),
+        format!("<< /Type /ExtGState /SMask << /Type /Mask /S /Luminosity /G 6 0 R {bc} >> >>"),
+        stream(
+            &format!("/Type /XObject /Subtype /Form /BBox [0 0 100 100] /Group << /S /Transparency /CS {space} >>"),
+            &format!("{paint} 0 0 50 100 re f"),
+        ),
+    ];
+    let (rgba, width) = render(pdf(&objects));
+    let value = |x| {
+        let [r, g, b] = pixel(&rgba, width, x, 50);
+        // Red over grey: red rises from the backdrop to 255 and green and blue fall to 0 as the
+        // mask goes from 0 to 1.
+        let from_red = (f64::from(r) - BACKDROP) / (255.0 - BACKDROP);
+        let from_green = (BACKDROP - f64::from(g)) / BACKDROP;
+        let from_blue = (BACKDROP - f64::from(b)) / BACKDROP;
+        assert!(
+            (from_red - from_green).abs() < 0.03 && (from_green - from_blue).abs() < 0.03,
+            "{space} {paint}: pixel {:?} is not red over the backdrop",
+            [r, g, b]
+        );
+        from_green
+    };
+    (value(25), value(75))
+}
+
+fn assert_mask(space: &str, paint: &str, bc: Option<&str>, left: f64, right: f64) {
+    let (got_left, got_right) = mask_values(space, paint, bc);
+    assert!((got_left - left).abs() < 0.02, "{space} group, `{paint}`: mask {got_left:.3}, expected {left}");
+    assert!((got_right - right).abs() < 0.02, "{space} group, /BC {bc:?}: mask {got_right:.3}, expected {right}");
+}
+
+#[test]
+fn black_ink_in_a_device_cmyk_group_masks_fully_and_no_ink_shows_fully() {
+    assert_mask("/DeviceCMYK", "0 0 0 1 k", None, 0.0, 0.0);
+    assert_mask("/DeviceCMYK", "0 0 0 0 k", None, 1.0, 0.0);
+    assert_mask("/DeviceCMYK", "0 0 0 0.5 k", None, 0.5, 0.0);
+}
+
+#[test]
+fn each_process_ink_in_a_device_cmyk_group_masks_by_its_weight() {
+    assert_mask("/DeviceCMYK", "1 0 0 0 k", None, 0.7, 0.0);
+    assert_mask("/DeviceCMYK", "0 1 0 0 k", None, 0.41, 0.0);
+    assert_mask("/DeviceCMYK", "0 0 1 0 k", None, 0.89, 0.0);
+    assert_mask("/DeviceCMYK", "1 1 1 1 k", None, 0.0, 0.0);
+    // The stroking colour too, and a colour selected with `cs`/`sc`.
+    assert_mask("/DeviceCMYK", "0 0 0 1 K 0 0 0 1 k 50 w 25 0 m 25 100 l S", None, 0.0, 0.0);
+    assert_mask("/DeviceCMYK", "/DeviceCMYK cs 0 0 0 0.5 sc", None, 0.5, 0.0);
+}
+
+#[test]
+fn a_device_cmyk_backdrop_colour_masks_by_its_gray() {
+    assert_mask("/DeviceCMYK", "0 0 0 1 k", Some("[0 0 0 0]"), 0.0, 1.0);
+    assert_mask("/DeviceCMYK", "0 0 0 0 k", Some("[0 0 0 1]"), 1.0, 0.0);
+    assert_mask("/DeviceCMYK", "0 0 0 1 k", Some("[1 0 0 0]"), 0.0, 0.7);
+}
+
+#[test]
+fn gray_and_rgb_groups_mask_as_before() {
+    assert_mask("/DeviceGray", "0 g", None, 0.0, 0.0);
+    assert_mask("/DeviceGray", "1 g", Some("[1]"), 1.0, 1.0);
+    assert_mask("/DeviceGray", "0.5 g", None, 0.5, 0.0);
+    assert_mask("/DeviceRGB", "0 0 0 rg", None, 0.0, 0.0);
+    assert_mask("/DeviceRGB", "1 1 1 rg", Some("[1 1 1]"), 1.0, 1.0);
+    assert_mask("/DeviceRGB", "0.5 0.5 0.5 rg", None, 0.5, 0.0);
+}
+
+#[test]
+fn device_cmyk_on_the_page_keeps_its_display_colour() {
+    // Only a luminosity mask in a DeviceCMYK group reads CMYK as its gray. On the page, CMYK is
+    // displayed through the CMYK profile as before, where 100% K is a dark grey.
+    let objects = [
+        "<< /Type /Catalog /Pages 2 0 R >>".to_string(),
+        "<< /Type /Pages /Kids [3 0 R] /Count 1 >>".to_string(),
+        "<< /Type /Page /Parent 2 0 R /MediaBox [0 0 100 100] /Contents 4 0 R >>".to_string(),
+        stream("", "0 0 0 1 k 0 0 100 100 re f"),
+    ];
+    let (rgba, width) = render(pdf(&objects));
+    let [r, g, b] = pixel(&rgba, width, 50, 50);
+    assert!(r > 10 && g > 10 && b > 10 && r < 80, "100% K on the page: {:?}", [r, g, b]);
+}

crates/render/tests/it/main.rs

@@ -3,6 +3,7 @@
 mod cid_fallback_query;
 mod inline_image_ei;
 mod jbig2_invariants;
+mod luminosity_group_space;
 mod named_form_properties;
 mod search;
 mod separation_all;

parity/acrobat-features.toml

@@ -758,8 +758,8 @@ milestone = "M2"
 status = "partial"
 commands = []
 tools = []
-evidence = ["crates/render/src/raster.rs::soft_mask_without_group_colour_space_is_applied", "crates/render/src/raster.rs::a_multiply_highlight_inside_a_transparency_group_keeps_the_text"]
-notes = "via hayro bootstrap. A transparency group that is neither isolated nor knockout and is entered at full opacity, with no soft mask and Normal blending, is drawn straight onto the page, so a blend mode inside it (the Multiply of a highlight appearance written by other editors) sees the page content (#1968). Missing: a non-isolated group that needs a layer (partial opacity, a soft mask or a blend mode on the group itself) still composites its elements against a blank backdrop, and knockout groups are drawn as ordinary ones"
+evidence = ["crates/render/src/raster.rs::soft_mask_without_group_colour_space_is_applied", "crates/render/src/raster.rs::a_multiply_highlight_inside_a_transparency_group_keeps_the_text", "crates/render/tests/it/luminosity_group_space.rs::black_ink_in_a_device_cmyk_group_masks_fully_and_no_ink_shows_fully"]
+notes = "via hayro bootstrap. A luminosity soft mask whose group is in DeviceCMYK reads its flat CMYK colours and backdrop as their gray, 1 - min(1, 0.3 c + 0.59 m + 0.11 y + k) (ISO 32000-2 §11.5.3), so 100% K masks fully; CMYK images, shadings and tiling patterns inside such a mask still go through the display profile. A transparency group that is neither isolated nor knockout and is entered at full opacity, with no soft mask and Normal blending, is drawn straight onto the page, so a blend mode inside it (the Multiply of a highlight appearance written by other editors) sees the page content (#1968). Missing: a non-isolated group that needs a layer (partial opacity, a soft mask or a blend mode on the group itself) still composites its elements against a blank backdrop, and knockout groups are drawn as ordinary ones"
 
 [[feature]]
 id = "view.render-knockout"

vendor/README.md

@@ -17,7 +17,7 @@ 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

@@ -391,6 +391,13 @@ impl ColorSpace {
         matches!(self.0.as_ref(), ColorSpaceType::DeviceGray)
     }
 
+    // PdfCraft patch (63).
+    /// Whether this is `/DeviceCMYK` itself, not an ICC-based or default colour space that
+    /// stands in for it.
+    pub(crate) fn is_device_cmyk(&self) -> bool {
+        matches!(self.0.as_ref(), ColorSpaceType::DeviceCmyk)
+    }
+
     /// Get the number of components of the color space.
     pub(crate) fn num_components(&self) -> u8 {
         match self.0.as_ref() {
@@ -1342,6 +1349,18 @@ fn f32_to_u8(val: f32) -> u8 {
     (val * 255.0 + 0.5) as u8
 }
 
+// PdfCraft patch (63).
+/// The `/DeviceCMYK` to `/DeviceGray` conversion of ISO 32000-2 §10.4.2.3,
+/// `gray = 1.0 - min(1.0, 0.3 c + 0.59 m + 0.11 y + k)`, which §11.5.3 also gives for the
+/// luminosity of a soft mask whose group is in `/DeviceCMYK`. A missing component counts as
+/// zero, and each component is clamped to `[0, 1]` first (`NaN` and infinities read as zero).
+pub(crate) fn device_cmyk_to_gray(cmyk: &[f32]) -> f32 {
+    let component = |i: usize| clamp_component(cmyk.get(i).copied().unwrap_or(0.0), 0.0, 1.0);
+    let ink = 0.3 * component(0) + 0.59 * component(1) + 0.11 * component(2) + component(3);
+    // Every component is in [0, 1], so `ink` is not negative and the result is in [0, 1].
+    1.0 - ink.min(1.0)
+}
+
 /// Clamp an input-derived colour component to `[lo, hi]` without panicking on
 /// NaN or on a reversed range. Non-finite values map to zero.
 fn clamp_component(value: f32, lo: f32, hi: f32) -> f32 {
@@ -1450,3 +1469,36 @@ pub(crate) trait ToRgb {
         ))
     }
 }
+
+#[cfg(test)]
+mod device_cmyk_gray_tests {
+    use super::device_cmyk_to_gray;
+
+    fn assert_close(cmyk: &[f32], expected: f32) {
+        let got = device_cmyk_to_gray(cmyk);
+        assert!(
+            (got - expected).abs() < 1e-5,
+            "{cmyk:?}: gray {got}, expected {expected}"
+        );
+    }
+
+    #[test]
+    fn each_ink_darkens_by_its_iso_weight() {
+        assert_close(&[0.0, 0.0, 0.0, 0.0], 1.0);
+        assert_close(&[0.0, 0.0, 0.0, 1.0], 0.0);
+        assert_close(&[0.0, 0.0, 0.0, 0.5], 0.5);
+        assert_close(&[1.0, 0.0, 0.0, 0.0], 0.7);
+        assert_close(&[0.0, 1.0, 0.0, 0.0], 0.41);
+        assert_close(&[0.0, 0.0, 1.0, 0.0], 0.89);
+        assert_close(&[0.5, 0.5, 0.5, 0.25], 0.25);
+    }
+
+    #[test]
+    fn ink_past_full_coverage_is_black_and_bad_components_read_as_zero() {
+        assert_close(&[1.0, 1.0, 1.0, 1.0], 0.0);
+        assert_close(&[0.0, 0.0, 0.0, 1.5], 0.0);
+        assert_close(&[2.0, -1.0, f32::NAN, f32::INFINITY], 0.7);
+        assert_close(&[], 1.0);
+        assert_close(&[0.0, 0.0], 1.0);
+    }
+}

vendor/hayro-interpret/src/context.rs

@@ -173,6 +173,11 @@ pub struct Context<'a> {
     /// a limit was reached, the clip count to return to at its `Q`.
     saved_bytes: usize,
     skipped_saves: Vec<usize>,
+    // PdfCraft patch (63).
+    /// This is the content of a luminosity soft mask whose group colour space is `/DeviceCMYK`,
+    /// so a `/DeviceCMYK` fill or stroke colour paints as its gray (ISO 32000-2 §11.5.3,
+    /// §10.4.2.3) rather than through the CMYK profile used for display.
+    pub(crate) luminosity_in_device_cmyk: bool,
 }
 
 /// PdfCraft patch: most graphics states saved at once. Every `q` copies the current state, dash
@@ -251,6 +256,7 @@ impl<'a> Context<'a> {
             nesting_depth,
             saved_bytes: 0,
             skipped_saves: Vec::new(),
+            luminosity_in_device_cmyk: false,
         }
     }
 

vendor/hayro-interpret/src/interpret/path.rs

@@ -1,4 +1,4 @@
-use crate::color::{Color, ColorSpace};
+use crate::color::{Color, ColorSpace, device_cmyk_to_gray};
 use crate::context::{Context, path_as_rect};
 use crate::device::Device;
 use crate::util::{BezPathExt, Float32Ext};
@@ -169,7 +169,13 @@ pub(crate) fn get_paint<'a>(context: &Context<'a>, is_stroke: bool) -> Paint<'a>
             Paint::Color(Color::new(ColorSpace::device_gray(), smallvec![0.0], 0.0))
         }
     } else {
-        let color = Color::new(data.color_space, data.color, data.alpha);
+        // PdfCraft patch (63): see `Context::luminosity_in_device_cmyk`.
+        let color = if context.luminosity_in_device_cmyk && data.color_space.is_device_cmyk() {
+            let gray = device_cmyk_to_gray(&data.color);
+            Color::new(ColorSpace::device_gray(), smallvec![gray], data.alpha)
+        } else {
+            Color::new(data.color_space, data.color, data.alpha)
+        };
 
         if let Some(tf) = &data.transfer_function {
             Paint::Color(Color::from_rgba(tf.apply(&color.to_rgba())))

vendor/hayro-interpret/src/soft_mask.rs

@@ -1,4 +1,4 @@
-use crate::color::{Color, ColorComponents, ColorSpace};
+use crate::color::{Color, ColorComponents, ColorSpace, DeviceFamily, device_cmyk_to_gray};
 use crate::context::{Context, InterpreterCache};
 use crate::device::Device;
 use crate::function::Function;
@@ -59,6 +59,9 @@ struct Repr<'a> {
     transfer_function: Option<TransferFunction>,
     settings: InterpreterSettings,
     background: Color,
+    // PdfCraft patch (63).
+    /// A luminosity mask whose group colour space is `/DeviceCMYK`.
+    luminosity_in_device_cmyk: bool,
     xref: &'a XRef,
     nesting_depth: u32,
 }
@@ -107,10 +110,17 @@ impl<'a> SoftMask<'a> {
         // PdfCraft patch: the group's /CS is optional (ISO 32000-2 §11.6.5.2; Chrome/Skia omit
         // it). Upstream returned None here, silently dropping the whole soft mask. Fall back to
         // DeviceRGB, the blending space our renderer composites in.
-        let cs = group
+        let cs_object = group
             .dict
             .get::<Dict<'_>>(GROUP)
-            .and_then(|g| g.get::<Object<'_>>(CS))
+            .and_then(|g| g.get::<Object<'_>>(CS));
+        // PdfCraft patch (63): the group is composited in `/DeviceCMYK` itself. An ICC-based
+        // or calibrated group space keeps its own conversion.
+        let group_in_device_cmyk = cs_object
+            .as_ref()
+            .and_then(DeviceFamily::of_object)
+            .is_some_and(|family| family == DeviceFamily::Cmyk);
+        let cs = cs_object
             .and_then(|o| ColorSpace::new(o, &context.interpreter_cache.object_cache))
             .unwrap_or_else(ColorSpace::device_rgb);
         let transfer_function = dict
@@ -121,7 +131,19 @@ impl<'a> SoftMask<'a> {
             LUMINOSITY => {
                 let color = dict
                     .get::<ColorComponents>(BC)
-                    .map(|c| Color::new(cs, c, 1.0))
+                    .map(|c| {
+                        // PdfCraft patch (63): a DeviceCMYK backdrop's luminosity is its gray
+                        // (ISO 32000-2 §11.5.3), as for the group's content.
+                        if group_in_device_cmyk && c.len() == 4 {
+                            Color::new(
+                                ColorSpace::device_gray(),
+                                smallvec![device_cmyk_to_gray(&c)],
+                                1.0,
+                            )
+                        } else {
+                            Color::new(cs, c, 1.0)
+                        }
+                    })
                     .unwrap_or(Color::new(ColorSpace::device_gray(), smallvec![0.0], 1.0));
 
                 (MaskType::Luminosity, color)
@@ -157,6 +179,7 @@ impl<'a> SoftMask<'a> {
             settings: context.settings.clone(),
             xref: context.xref,
             background,
+            luminosity_in_device_cmyk: group_in_device_cmyk && mask_type == MaskType::Luminosity,
             parent_resources,
             nesting_depth,
         })))
@@ -174,6 +197,7 @@ impl<'a> SoftMask<'a> {
             state,
             self.0.nesting_depth,
         );
+        ctx.luminosity_in_device_cmyk = self.0.luminosity_in_device_cmyk;
         draw_form_xobject(&self.0.parent_resources, &self.0.group, &mut ctx, device);
     }