diff --git a/crates/render/src/raster.rs b/crates/render/src/raster.rs index cf2fec87e..0e64ac241 100644 --- a/crates/render/src/raster.rs +++ b/crates/render/src/raster.rs @@ -4972,6 +4972,66 @@ trailer << /Root 1 0 R >> assert!(px.rgba[((50 * px.width + 25) * 4) as usize] < 64, "the glyph is drawn"); } + /// Accented letters in non-embedded fonts (vendored hayro-interpret patch to + /// `StandardKind`): the stand-ins for the standard fonts hold only the glyphs of the + /// Standard, WinAnsi and Mac Roman encodings, so a letter a font names beyond those in its + /// /Differences drew nothing. iText 2 writes Turkish this way (`/Gbreve`, `/Idotaccent`, + /// `/Scedilla`, `/gbreve`, `/scedilla` over Ð, Ý, Þ, ð, þ), and a Turkish letter had blanks + /// for Ğ, İ, Ş, ğ and ş. Each is now its base letter with the accent above or below it. + #[test] + fn accented_letters_the_standard_stand_ins_lack_are_built_from_their_parts() { + let letters = ["G", "Gbreve", "S", "Scedilla", "I", "Idotaccent", "g", "gbreve", "s", "scedilla"]; + let mut content = String::new(); + for (i, _) in letters.iter().enumerate() { + content.push_str(&format!("BT /F1 40 Tf {} 20 Td <{:02X}> Tj ET\n", 10 + 40 * i, 65 + i)); + } + let differences = letters.iter().map(|n| format!("/{n}")).collect::>().join(" "); + let pdf = format!( + "%PDF-1.4 +1 0 obj << /Type /Catalog /Pages 2 0 R >> endobj +2 0 obj << /Type /Pages /Kids [3 0 R] /Count 1 >> endobj +3 0 obj << /Type /Page /Parent 2 0 R /MediaBox [0 0 420 80] /Contents 4 0 R /Resources << /Font << /F1 5 0 R >> >> >> endobj +4 0 obj << /Length {} >> stream +{content}endstream endobj +5 0 obj << /Type /Font /Subtype /TrueType /BaseFont /TimesNewRomanPSMT /FirstChar 65 /LastChar 74 + /Widths [722 722 556 556 333 333 500 500 389 389] /FontDescriptor 6 0 R + /Encoding << /Type /Encoding /Differences [65 {differences}] >> >> endobj +6 0 obj << /Type /FontDescriptor /FontName /TimesNewRomanPSMT /Flags 32 /FontBBox [-568 -306 2045 1039] + /ItalicAngle 0 /Ascent 693 /Descent -215 /CapHeight 662 /StemV 80 >> endobj +trailer << /Root 1 0 R >> +%%EOF", + content.len() + ); + let mut r = PageRenderer::new(Arc::new(pdf.into_bytes()), RenderConfig::default()); + let p = r.render(RenderRequest { page: 0, kind: RequestKind::Pixels, tile: None, scale: 1.0, tag: 0, ..Default::default() }); + assert!(p.error.is_none(), "{:?}", p.error); + // The dark pixels of the i-th letter: how many, and its top and bottom rows (y down). + let ink = |i: u32| { + let (mut count, mut top, mut bottom) = (0, u32::MAX, 0); + for y in 0..p.height { + for x in (8 + 40 * i)..(46 + 40 * i).min(p.width) { + if p.rgba[((y * p.width + x) * 4) as usize] < 128 { + count += 1; + top = top.min(y); + bottom = bottom.max(y); + } + } + } + (count, top, bottom) + }; + for (pair, above) in [(0, true), (1, false), (2, true), (3, true), (4, false)] { + let (base, accented) = (ink(2 * pair), ink(2 * pair + 1)); + let name = letters[2 * pair as usize + 1]; + assert!(base.0 > 0, "{name}: the base letter draws"); + assert!(accented.0 > base.0, "{name} draws its letter and accent: {accented:?} vs {base:?}"); + if above { + assert!(accented.1 + 2 < base.1, "{name}: the accent sits above the letter: {accented:?} vs {base:?}"); + } else { + assert!(accented.2 > base.2 + 2, "{name}: the accent hangs below the letter: {accented:?} vs {base:?}"); + } + } + } + /// A page's `/UserUnit` (the size of its unit in points) scales the page and everything on /// it, after the crop box and before `/Rotate`, as Acrobat shows such pages: with /// `/UserUnit 2`, scale 1 renders pixel for pixel what scale 2 renders without it. As in diff --git a/vendor/README.md b/vendor/README.md index 7e8964c48..94109f443 100644 --- a/vendor/README.md +++ b/vendor/README.md @@ -7,7 +7,7 @@ the fix. Vendoring copyleft code is never allowed (plan/adr/0001). | 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 `.notdef` for a CID of an Adobe character collection (Japan1, GB1, CNS1, Korea1) that it can't find by Unicode: hayro took the CID for a glyph index of the substitute, which numbers its glyphs its own way, so the character was drawn as an unrelated one (𠮷 as "Ｑ" in BIZ UDPGothic); (22) a Type 0 font drawn with a substitute finds a character given with a variation selector (`/ToUnicode`, or Adobe-Japan1-UCS2, which maps the JIS X 0208 forms of the kanji JIS X 0213:2004 redrew that way: CID 1247 is 噂 U+E0100) through the substitute's variation sequences, else as the character alone: such a CID found no glyph and was drawn as an unrelated one; (23) backport of hayro 0.8's `gradient` module: `EncodedShadingPattern::as_svg_gradient` turns an axial or radial shading into stops of an sRGB gradient (within 0.01 per channel, a stop at every stitching-function bound via `Function::stitching_bounds`) when a native gradient draws it exactly (extended past the box drawn in; a radial one with no background colour); (24) `DecodedImageCache`: decoded image pixels shared across renders through the interpreter cache within a 64 MiB budget (an image-heavy page decoded its thousands of images again per tile and per scale), keyed by every decode input (`DecodedImageKey`: the stream's place and dictionary bytes, its object, mask/stencil/raster output, interpolation, decode target size, preview or final); images under a transfer function and inline images are not cached, an image over the budget is never kept, and a poisoned lock decodes uncached; (25) `Device::actual_text` hands the device a marked content sequence's `/ActualText` (inline or named in `/Properties`), so text extraction keeps the Thai, Indic and Arabic clusters Chrome marks this way (their shaped tone marks and vowels have no Unicode of their own) | (1) `raster::tests::widget_appearance_states`; (2, 3) `xtask text-oracle` on corpus/pdfjs issue918; (4) `raster::tests::layer_override_hides_content`; (5) `raster::tests::soft_mask_without_group_colour_space_is_applied`; (6) `raster::tests::self_referencing_tiling_pattern_terminates`, `raster::tests::self_referencing_type3_glyph_terminates`; (7) `raster::tests::huge_cid_width_ranges_terminate`; (8) `raster::tests::hiding_comments_keeps_fields`; (9) `raster::tests::absurd_mask_and_fax_sizes_are_refused_before_decoding`; (10) `raster::tests::type3_glyphs_that_fan_out_into_themselves_finish`; (11) `raster::tests::type1_font_programs_with_long_runs_of_numbers_load_quickly`; (12) `raster::tests::degenerate_annotation_appearances_are_skipped`; (13) `raster::tests::highlights_without_an_appearance_are_drawn`; (14) `raster::tests::malformed_simple_font_widths_keep_later_widths_and_the_font`, `raster::tests::huge_simple_font_first_char_terminates`; (15) `raster::tests::annotation_appearance_box_maps_onto_rect`; (16) `raster::tests::clipping_path_applies_after_any_painting_operator`; (17) `raster::tests::dropping_the_pool_cancels_its_renders`, `raster::tests::the_watchdog_stops_the_render_it_gives_up_on`; (18) `raster::tests::page_contents_and_nested_forms_share_one_budget`, `raster::tests::content_painted_again_and_again_keeps_drawing`, `raster::tests::sampled_functions_with_billions_of_samples_are_refused`; (19) `raster::tests::mesh_shadings_far_off_the_page_render`, `raster::tests::many_overlapping_mesh_triangles_finish`, `raster::tests::mesh_shadings_with_many_patches_or_no_rows_finish`; (20) `raster::tests::function_limits_calculator_arithmetic_and_depth`, `raster::tests::function_limits_public_construction_work_and_depth`, `raster::tests::function_limits_stitching_cycles_are_refused_and_shared_children_work`, `raster::tests::function_limits_invalid_calculator_keeps_the_page_renderable`; (21) `raster::tests::cids_a_substitute_lacks_are_not_drawn_as_other_glyphs` |; (22) `raster::tests::variation_sequences_draw_their_kanji_in_a_substitute`; (23) `raster::tests::axial_and_radial_shadings_draw_as_native_gradients`; (24) `raster::tests::tiles_match_full_render`, `raster::tests::skipping_paths_off_the_canvas_changes_no_pixel` (both decode through the cache), `raster::tests::decoded_images_with_identical_dictionaries_keep_their_own_pixels`, `raster::tests::decoded_images_under_a_transfer_function_are_not_shared`; (25) `text::tests::actual_text_replaces_the_glyphs_it_marks_in_every_writing_direction`, `text::tests::actual_text_follows_the_pdf_rules_for_marked_content` +| 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 `.notdef` for a CID of an Adobe character collection (Japan1, GB1, CNS1, Korea1) that it can't find by Unicode: hayro took the CID for a glyph index of the substitute, which numbers its glyphs its own way, so the character was drawn as an unrelated one (𠮷 as "Ｑ" in BIZ UDPGothic); (22) a Type 0 font drawn with a substitute finds a character given with a variation selector (`/ToUnicode`, or Adobe-Japan1-UCS2, which maps the JIS X 0208 forms of the kanji JIS X 0213:2004 redrew that way: CID 1247 is 噂 U+E0100) through the substitute's variation sequences, else as the character alone: such a CID found no glyph and was drawn as an unrelated one; (23) backport of hayro 0.8's `gradient` module: `EncodedShadingPattern::as_svg_gradient` turns an axial or radial shading into stops of an sRGB gradient (within 0.01 per channel, a stop at every stitching-function bound via `Function::stitching_bounds`) when a native gradient draws it exactly (extended past the box drawn in; a radial one with no background colour); (24) `DecodedImageCache`: decoded image pixels shared across renders through the interpreter cache within a 64 MiB budget (an image-heavy page decoded its thousands of images again per tile and per scale), keyed by every decode input (`DecodedImageKey`: the stream's place and dictionary bytes, its object, mask/stencil/raster output, interpolation, decode target size, preview or final); images under a transfer function and inline images are not cached, an image over the budget is never kept, and a poisoned lock decodes uncached; (25) `Device::actual_text` hands the device a marked content sequence's `/ActualText` (inline or named in `/Properties`), so text extraction keeps the Thai, Indic and Arabic clusters Chrome marks this way (their shaped tone marks and vowels have no Unicode of their own); (26) non-embedded simple fonts drawn with a standard-font stand-in build the Latin Extended-A letters the stand-in lacks (`/Gbreve`, `/Idotaccent`, `/Scedilla`, `/aogonek`, `/ccaron`…) from the base letter and accent it has (`StandardKind::composite_glyph`, `ACCENTED_LETTERS`): PDFium's Foxit stand-ins hold only the Standard/WinAnsi/Mac Roman glyphs, so iText letters with Times New Roman unembedded showed blanks for Ğ, İ, Ş, ğ and ş | (1) `raster::tests::widget_appearance_states`; (2, 3) `xtask text-oracle` on corpus/pdfjs issue918; (4) `raster::tests::layer_override_hides_content`; (5) `raster::tests::soft_mask_without_group_colour_space_is_applied`; (6) `raster::tests::self_referencing_tiling_pattern_terminates`, `raster::tests::self_referencing_type3_glyph_terminates`; (7) `raster::tests::huge_cid_width_ranges_terminate`; (8) `raster::tests::hiding_comments_keeps_fields`; (9) `raster::tests::absurd_mask_and_fax_sizes_are_refused_before_decoding`; (10) `raster::tests::type3_glyphs_that_fan_out_into_themselves_finish`; (11) `raster::tests::type1_font_programs_with_long_runs_of_numbers_load_quickly`; (12) `raster::tests::degenerate_annotation_appearances_are_skipped`; (13) `raster::tests::highlights_without_an_appearance_are_drawn`; (14) `raster::tests::malformed_simple_font_widths_keep_later_widths_and_the_font`, `raster::tests::huge_simple_font_first_char_terminates`; (15) `raster::tests::annotation_appearance_box_maps_onto_rect`; (16) `raster::tests::clipping_path_applies_after_any_painting_operator`; (17) `raster::tests::dropping_the_pool_cancels_its_renders`, `raster::tests::the_watchdog_stops_the_render_it_gives_up_on`; (18) `raster::tests::page_contents_and_nested_forms_share_one_budget`, `raster::tests::content_painted_again_and_again_keeps_drawing`, `raster::tests::sampled_functions_with_billions_of_samples_are_refused`; (19) `raster::tests::mesh_shadings_far_off_the_page_render`, `raster::tests::many_overlapping_mesh_triangles_finish`, `raster::tests::mesh_shadings_with_many_patches_or_no_rows_finish`; (20) `raster::tests::function_limits_calculator_arithmetic_and_depth`, `raster::tests::function_limits_public_construction_work_and_depth`, `raster::tests::function_limits_stitching_cycles_are_refused_and_shared_children_work`, `raster::tests::function_limits_invalid_calculator_keeps_the_page_renderable`; (21) `raster::tests::cids_a_substitute_lacks_are_not_drawn_as_other_glyphs`; (26) `raster::tests::accented_letters_the_standard_stand_ins_lack_are_built_from_their_parts` |; (22) `raster::tests::variation_sequences_draw_their_kanji_in_a_substitute`; (23) `raster::tests::axial_and_radial_shadings_draw_as_native_gradients`; (24) `raster::tests::tiles_match_full_render`, `raster::tests::skipping_paths_off_the_canvas_changes_no_pixel` (both decode through the cache), `raster::tests::decoded_images_with_identical_dictionaries_keep_their_own_pixels`, `raster::tests::decoded_images_under_a_transfer_function_are_not_shared`; (25) `text::tests::actual_text_replaces_the_glyphs_it_marks_in_every_writing_direction`, `text::tests::actual_text_follows_the_pdf_rules_for_marked_content` | 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 `.notdef` for a CID of an Adobe character collection (Japan1, GB1, CNS1, Korea1) that it can't find by Unicode: hayro took the CID for a glyph index of the substitute, which numbers its glyphs its own way, so the character was drawn as an unrelated one (𠮷 as "Ｑ" in BIZ UDPGothic); (22) a Type 0 font drawn with a substitute finds a character given with a variation selector (`/ToUnicode`, or Adobe-Japan1-UCS2, which maps the JIS X 0208 forms of the kanji JIS X 0213:2004 redrew that way: CID 1247 is 噂 U+E0100) through the substitute's variation sequences, else as the character alone: such a CID found no glyph and was drawn as an unrelated one; (23) backport of hayro 0.8's `gradient` module: `EncodedShadingPattern::as_svg_gradient` turns an axial or radial shading into stops of an sRGB gradient (within 0.01 per channel, a stop at every stitching-function bound via `Function::stitching_bounds`) when a native gradient draws it exactly (extended past the box drawn in; a radial one with no background colour); (24) `DecodedImageCache`: decoded image pixels shared across renders through the interpreter cache within a 64 MiB budget (an image-heavy page decoded its thousands of images again per tile and per scale), keyed by every decode input (`DecodedImageKey`: the stream's place and dictionary bytes, its object, mask/stencil/raster output, interpolation, decode target size, preview or final); images under a transfer function and inline images are not cached, an image over the budget is never kept, and a poisoned lock decodes uncached; (25) Lab colour spaces honour their own `/WhitePoint`: L\*a\*b\* goes to XYZ relative to that white, is Bradford-adapted to D65 and converted to sRGB (ISO 32000-2 §8.6.5.4) instead of through `LAB.icc` as if every white were D50 (a D65 blue came out 45 levels too red; the profile is removed); components normalised to [0, 1] (`manual_scale`, an `/Indexed` palette over Lab) map onto L\* 0..100 and the a\*/b\* `/Range` | (1) `raster::tests::widget_appearance_states`; (2, 3) `xtask text-oracle` on corpus/pdfjs issue918; (4) `raster::tests::layer_override_hides_content`; (5) `raster::tests::soft_mask_without_group_colour_space_is_applied`; (6) `raster::tests::self_referencing_tiling_pattern_terminates`, `raster::tests::self_referencing_type3_glyph_terminates`; (7) `raster::tests::huge_cid_width_ranges_terminate`; (8) `raster::tests::hiding_comments_keeps_fields`; (9) `raster::tests::absurd_mask_and_fax_sizes_are_refused_before_decoding`; (10) `raster::tests::type3_glyphs_that_fan_out_into_themselves_finish`; (11) `raster::tests::type1_font_programs_with_long_runs_of_numbers_load_quickly`; (12) `raster::tests::degenerate_annotation_appearances_are_skipped`; (13) `raster::tests::highlights_without_an_appearance_are_drawn`; (14) `raster::tests::malformed_simple_font_widths_keep_later_widths_and_the_font`, `raster::tests::huge_simple_font_first_char_terminates`; (15) `raster::tests::annotation_appearance_box_maps_onto_rect`; (16) `raster::tests::clipping_path_applies_after_any_painting_operator`; (17) `raster::tests::dropping_the_pool_cancels_its_renders`, `raster::tests::the_watchdog_stops_the_render_it_gives_up_on`; (18) `raster::tests::page_contents_and_nested_forms_share_one_budget`, `raster::tests::content_painted_again_and_again_keeps_drawing`, `raster::tests::sampled_functions_with_billions_of_samples_are_refused`; (19) `raster::tests::mesh_shadings_far_off_the_page_render`, `raster::tests::many_overlapping_mesh_triangles_finish`, `raster::tests::mesh_shadings_with_many_patches_or_no_rows_finish`; (20) `raster::tests::function_limits_calculator_arithmetic_and_depth`, `raster::tests::function_limits_public_construction_work_and_depth`, `raster::tests::function_limits_stitching_cycles_are_refused_and_shared_children_work`, `raster::tests::function_limits_invalid_calculator_keeps_the_page_renderable`; (21) `raster::tests::cids_a_substitute_lacks_are_not_drawn_as_other_glyphs` |; (22) `raster::tests::variation_sequences_draw_their_kanji_in_a_substitute`; (23) `raster::tests::axial_and_radial_shadings_draw_as_native_gradients`; (24) `raster::tests::tiles_match_full_render`, `raster::tests::skipping_paths_off_the_canvas_changes_no_pixel` (both decode through the cache), `raster::tests::decoded_images_with_identical_dictionaries_keep_their_own_pixels`, `raster::tests::decoded_images_under_a_transfer_function_are_not_shared`; (25) `raster::tests::lab_honours_the_space_white_point`, `raster::tests::indexed_palettes_over_lab_keep_their_colours` | 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) backport of hayro 0.8: shadings that `as_svg_gradient` can represent are painted as a `vello_cpu` linear or two-point radial gradient instead of a texture sampled pixel by pixel through the shading function (InDesign fades are luminosity soft masks of one full-page axial `sh`: 40 on a report page took 15 s at 144 dpi, now under 1 s); without upstream's half-pixel shift, which suits vello_cpu 0.3 but moves 0.0.8's gradients off pixel centres; (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` 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) | (1) `raster::tests::tiles_match_full_render`; (2) `raster::tests::absurd_image_dimensions_are_skipped`; (3) `raster::tests::tiling_cells_stay_small_whatever_the_step`; (4) `raster::tests::absurd_predictor_columns_and_line_widths_render`; (5) `raster::tests::dash_patterns_that_cut_a_stroke_into_billions_of_pieces_render`; (6) `raster::tests::invalid_dash_patterns_terminate_and_are_drawn_solid`; (7) `raster::tests::pixels_are_a_plain_renders_bytes_in_a_buffer_a_gui_can_take_over`; (8) `raster::tests::image_resampling_rejects_anisotropic_target_growth`, `raster::tests::image_resampling_bounds_intermediate_before_planning`, `raster::tests::image_resampling_rejects_invalid_sources_and_scales`, `raster::tests::image_resampling_keeps_valid_sizes_and_exact_limits`, `raster::tests::resampling_fallback_preserves_original_geometry_and_pixels`, `raster::tests::image_resampling_wide_sources_shrink_before_backend_side_limits`, `raster::tests::image_resampling_wide_transparent_sources_still_shrink`, `raster::tests::image_resampling_padded_backend_dimensions_stay_checked`, `raster::tests::image_resampling_mismatched_alpha_mask_keeps_pixels_and_placement`; (9) `raster::tests::skipping_paths_off_the_canvas_changes_no_pixel`; (10) `raster::tests::axial_and_radial_shadings_draw_as_native_gradients`; (11) `raster::tests::skipping_paths_off_the_canvas_changes_no_pixel`; (12) `raster::tests::preview_renders_skip_tiny_images_but_finals_draw_everything`; (13) `color_replacement_tests::{black_maps_to_text_colour, white_maps_to_background, midgrey_interpolates, alpha_copied_verbatim, only_black_threshold, line_art_false_skips_paths_but_not_text}`, `color_replacement_render_tests::{color_replacement_maps_text_and_line_art, color_replacement_maps_stencil_mask_ink}`; (14) `raster::tests::interpolated_minified_image_edges_snap_to_whole_pixels` (`cargo test -p hayro`) | diff --git a/vendor/hayro-interpret/src/font/standard_font.rs b/vendor/hayro-interpret/src/font/standard_font.rs index c198e542a..c73c75dd2 100644 --- a/vendor/hayro-interpret/src/font/standard_font.rs +++ b/vendor/hayro-interpret/src/font/standard_font.rs @@ -9,7 +9,7 @@ use crate::font::{ use hayro_syntax::object::Dict; use hayro_syntax::object::Name; use hayro_syntax::object::dict::keys::{BASE_FONT, FONT_DESC, FONT_WEIGHT, ITALIC_ANGLE}; -use kurbo::BezPath; +use kurbo::{Affine, BezPath, Shape}; use skrifa::GlyphId; use skrifa::raw::TableProvider; use std::cell::RefCell; @@ -413,13 +413,18 @@ impl StandardKind { let result = self .code_to_ps_name(code) .and_then(|c| { - self.base_font_blob.name_to_glyph(c).or_else(|| { - // If the font doesn't have a POST table, try to map via unicode instead. - glyph_names::get(c).and_then(|c| { - self.base_font_blob - .unicode_to_glyph(c.chars().nth(0).unwrap() as u32) + self.base_font_blob + .name_to_glyph(c) + .or_else(|| { + // If the font doesn't have a POST table, try to map via unicode instead. + glyph_names::get(c).and_then(|c| { + self.base_font_blob + .unicode_to_glyph(c.chars().nth(0).unwrap() as u32) + }) }) - }) + // PdfCraft patch: an accented letter the stand-in lacks is built from its + // parts (see `ACCENTED_LETTERS`). + .or_else(|| self.composite_glyph(code, c)) }) .unwrap_or(GlyphId::NOTDEF); self.glyph_to_code.borrow_mut().insert(result, code); @@ -427,14 +432,79 @@ impl StandardKind { result } + /// PdfCraft patch: the glyph id standing for the letter `name` built from its base letter and + /// accent, when the stand-in has both. Ids from [`COMPOSITE_GLYPH_BASE`] up are one per + /// character code, so the outline is found again from the code alone. + fn composite_glyph(&self, code: u8, name: &str) -> Option { + let (base, accent, _) = accented_parts(name)?; + self.base_font_blob.name_to_glyph(base)?; + self.base_font_blob.name_to_glyph(accent)?; + Some(GlyphId::new(COMPOSITE_GLYPH_BASE + u32::from(code))) + } + + /// PdfCraft patch: the outline of a glyph from [`Self::composite_glyph`] — the base letter, + /// then the accent centred on it. An accent above a letter taller than `x` is raised by the + /// difference (the stand-in's accents sit on lowercase letters) and, in an italic font, + /// moved along the slant; an ogonek hangs from the letter's right edge. + fn composite_outline(&self, glyph: GlyphId) -> Option { + let code = u8::try_from(glyph.to_u32().checked_sub(COMPOSITE_GLYPH_BASE)?).ok()?; + let (base, accent, place) = accented_parts(self.code_to_ps_name(code)?)?; + let outline = |name: &str| { + self.base_font_blob + .name_to_glyph(name) + .map(|g| self.base_font_blob.outline_glyph(g)) + }; + let mut path = outline(base)?; + let accent = outline(accent)?; + if path.elements().is_empty() || accent.elements().is_empty() { + return Some(path); + } + let (b, a) = (path.bounding_box(), accent.bounding_box()); + let (dx, dy) = match place { + Place::Below => (b.center().x - a.center().x, 0.0), + Place::Ogonek => (b.x1 - a.x1, 0.0), + Place::Above => { + let x_top = outline("x") + .filter(|x| !x.elements().is_empty()) + .map_or(b.y1, |x| x.bounding_box().y1); + // Overshoot of round lowercase letters (o, g, s) over x is not a taller letter. + let raise = if b.y1 > x_top * 1.1 { + b.y1 - x_top + } else { + 0.0 + }; + let slant = if self.base_font.is_italic() { + raise * ITALIC_ACCENT_SLANT + } else { + 0.0 + }; + (b.center().x - a.center().x + slant, raise) + } + }; + if !(dx.is_finite() && dy.is_finite()) { + return Some(path); + } + path.extend(Affine::translate((dx, dy)) * accent); + Some(path) + } + pub(crate) fn outline_glyph(&self, glyph: GlyphId) -> BezPath { - let path = self.base_font_blob.outline_glyph(glyph); + let composite = self.composite_outline(glyph); + let is_composite = composite.is_some(); + let path = composite.unwrap_or_else(|| self.base_font_blob.outline_glyph(glyph)); // If the font is not embedded, we might need to stretch it so that // it matches the metrics of the actual underlying font blob. + // PdfCraft patch: a composite id isn't a glyph of the blob, so its width comes from the + // standard metrics of its name. + let blob_width = if is_composite { + None + } else { + self.base_font_blob.advance_width(glyph) + }; if let Some(code) = self.glyph_to_code.borrow().get(&glyph).copied() - && let Some(actual_width) = self.base_font_blob.advance_width(glyph).or_else(|| { + && let Some(actual_width) = blob_width.or_else(|| { self.code_to_ps_name(code) .and_then(|name| self.base_font.get_width(name)) }) @@ -495,3 +565,130 @@ impl StandardKind { self.base_font.is_monospace() } } + +/// PdfCraft patch: the first glyph id of the letters [`StandardKind`] builds from parts, far +/// above the glyph count of any font (one id per character code from here). +const COMPOSITE_GLYPH_BASE: u32 = 0x0100_0000; + +/// PdfCraft patch: how far an accent raised over a capital moves right per unit of height in +/// an italic stand-in (tan 15°; the standard italics lean 12° to 16°). +const ITALIC_ACCENT_SLANT: f64 = 0.27; + +/// Where an accent goes on its base letter. +#[derive(Clone, Copy, Debug, PartialEq, Eq)] +enum Place { + Above, + Below, + Ogonek, +} + +/// PdfCraft patch: the stand-ins for the standard fonts (PDFium's Foxit fonts) carry only the +/// glyphs of the Standard, WinAnsi and Mac Roman encodings, so a font that isn't embedded and +/// names other Latin letters in its /Differences (`/Gbreve`, `/Idotaccent`, `/Scedilla`…, as +/// iText 2 writes Turkish text with Times New Roman left unembedded) drew nothing for them. Each of +/// these Latin Extended-A letters is a base letter the stand-ins have plus one of their accents, +/// as Type 1 `seac` composites and the composites of the standard-14 AFM files are built. +/// Letters whose accent isn't a plain one (ď ľ ť and the comma accents) aren't here. +const ACCENTED_LETTERS: &[(&str, &str, &str, Place)] = &[ + ("Amacron", "A", "macron", Place::Above), + ("amacron", "a", "macron", Place::Above), + ("Abreve", "A", "breve", Place::Above), + ("abreve", "a", "breve", Place::Above), + ("Aogonek", "A", "ogonek", Place::Ogonek), + ("aogonek", "a", "ogonek", Place::Ogonek), + ("Cacute", "C", "acute", Place::Above), + ("cacute", "c", "acute", Place::Above), + ("Ccircumflex", "C", "circumflex", Place::Above), + ("ccircumflex", "c", "circumflex", Place::Above), + ("Cdotaccent", "C", "dotaccent", Place::Above), + ("cdotaccent", "c", "dotaccent", Place::Above), + ("Ccaron", "C", "caron", Place::Above), + ("ccaron", "c", "caron", Place::Above), + ("Dcaron", "D", "caron", Place::Above), + ("Emacron", "E", "macron", Place::Above), + ("emacron", "e", "macron", Place::Above), + ("Ebreve", "E", "breve", Place::Above), + ("ebreve", "e", "breve", Place::Above), + ("Edotaccent", "E", "dotaccent", Place::Above), + ("edotaccent", "e", "dotaccent", Place::Above), + ("Eogonek", "E", "ogonek", Place::Ogonek), + ("eogonek", "e", "ogonek", Place::Ogonek), + ("Ecaron", "E", "caron", Place::Above), + ("ecaron", "e", "caron", Place::Above), + ("Gcircumflex", "G", "circumflex", Place::Above), + ("gcircumflex", "g", "circumflex", Place::Above), + ("Gbreve", "G", "breve", Place::Above), + ("gbreve", "g", "breve", Place::Above), + ("Gdotaccent", "G", "dotaccent", Place::Above), + ("gdotaccent", "g", "dotaccent", Place::Above), + ("Hcircumflex", "H", "circumflex", Place::Above), + ("hcircumflex", "h", "circumflex", Place::Above), + ("Itilde", "I", "tilde", Place::Above), + ("itilde", "dotlessi", "tilde", Place::Above), + ("Imacron", "I", "macron", Place::Above), + ("imacron", "dotlessi", "macron", Place::Above), + ("Ibreve", "I", "breve", Place::Above), + ("ibreve", "dotlessi", "breve", Place::Above), + ("Iogonek", "I", "ogonek", Place::Ogonek), + ("iogonek", "i", "ogonek", Place::Ogonek), + ("Idotaccent", "I", "dotaccent", Place::Above), + ("Jcircumflex", "J", "circumflex", Place::Above), + ("Lacute", "L", "acute", Place::Above), + ("lacute", "l", "acute", Place::Above), + ("Nacute", "N", "acute", Place::Above), + ("nacute", "n", "acute", Place::Above), + ("Ncaron", "N", "caron", Place::Above), + ("ncaron", "n", "caron", Place::Above), + ("Omacron", "O", "macron", Place::Above), + ("omacron", "o", "macron", Place::Above), + ("Obreve", "O", "breve", Place::Above), + ("obreve", "o", "breve", Place::Above), + ("Ohungarumlaut", "O", "hungarumlaut", Place::Above), + ("ohungarumlaut", "o", "hungarumlaut", Place::Above), + ("Racute", "R", "acute", Place::Above), + ("racute", "r", "acute", Place::Above), + ("Rcaron", "R", "caron", Place::Above), + ("rcaron", "r", "caron", Place::Above), + ("Sacute", "S", "acute", Place::Above), + ("sacute", "s", "acute", Place::Above), + ("Scircumflex", "S", "circumflex", Place::Above), + ("scircumflex", "s", "circumflex", Place::Above), + ("Scedilla", "S", "cedilla", Place::Below), + ("scedilla", "s", "cedilla", Place::Below), + ("Tcedilla", "T", "cedilla", Place::Below), + ("tcedilla", "t", "cedilla", Place::Below), + ("Tcaron", "T", "caron", Place::Above), + ("Utilde", "U", "tilde", Place::Above), + ("utilde", "u", "tilde", Place::Above), + ("Umacron", "U", "macron", Place::Above), + ("umacron", "u", "macron", Place::Above), + ("Ubreve", "U", "breve", Place::Above), + ("ubreve", "u", "breve", Place::Above), + ("Uring", "U", "ring", Place::Above), + ("uring", "u", "ring", Place::Above), + ("Uhungarumlaut", "U", "hungarumlaut", Place::Above), + ("uhungarumlaut", "u", "hungarumlaut", Place::Above), + ("Uogonek", "U", "ogonek", Place::Ogonek), + ("uogonek", "u", "ogonek", Place::Ogonek), + ("Wcircumflex", "W", "circumflex", Place::Above), + ("wcircumflex", "w", "circumflex", Place::Above), + ("Ycircumflex", "Y", "circumflex", Place::Above), + ("ycircumflex", "y", "circumflex", Place::Above), + ("Zacute", "Z", "acute", Place::Above), + ("zacute", "z", "acute", Place::Above), + ("Zdotaccent", "Z", "dotaccent", Place::Above), + ("zdotaccent", "z", "dotaccent", Place::Above), +]; + +/// PdfCraft patch: the base letter, accent and placement of an accented letter in +/// [`ACCENTED_LETTERS`], by glyph name (`uni011E` and `u011E` forms too). +fn accented_parts(name: &str) -> Option<(&'static str, &'static str, Place)> { + let name = normalized_glyph_name(name); + let by_name = |n: &str| { + ACCENTED_LETTERS + .iter() + .find(|(letter, ..)| *letter == n) + .map(|&(_, base, accent, place)| (base, accent, place)) + }; + by_name(name).or_else(|| by_name(glyph_names::get_reverse(glyph_name_to_unicode(name)?)?)) +}