mirror of
https://github.com/storytold/pdfcraft.git
synced 2026-10-31 23:59:07 +00:00
fix(render): draw comma-below letters in non-embedded standard fonts (refs #1666)
The stand-ins for the standard fonts (PDFium's Foxit fonts) have neither the comma-below letters nor a commaaccent glyph, and the composite-letter patch left comma accents out. A non-embedded font naming /scommaaccent therefore drew nothing, which is the blank "si" left in Romanian XFA forms, and /tcommaaccent drew a cedilla through the glyph list's alias to U+0163. Romanian s/S/t/T and Latvian k/K/l/L/n/N/r/R/G with a comma below are now built from the letter and the font's comma, scaled to three quarters and set just under the baseline, moved back along the slant in italics. The uni021A and uni021B names of T and t with a comma below, which the glyph list does not name, resolve by code point. Lowercase g with its turned comma above is still not built. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
Tiago KielandClaude Opus 5.5 committed
1 parent
ec0a965074
commit
88735a7003
3 files changed
+123
-6
No files matched your search
@@ -5755,6 +5755,74 @@ trailer << /Root 1 0 R >>
|
||||
}
|
||||
}
|
||||
|
||||
/// Comma-below letters in non-embedded standard fonts (vendored hayro-interpret patch to
|
||||
/// `StandardKind`). The stand-ins have neither these letters nor a `commaaccent` to build
|
||||
/// them from, so Romanian ș Ș (a form laid out from its XFA template names `/scommaaccent`)
|
||||
/// and Latvian ķ ļ ņ ŗ Ģ drew nothing, and ț Ț drew a cedilla. Each is now its letter with a
|
||||
/// comma under it, apart from the letter and inside the descender.
|
||||
#[test]
|
||||
fn comma_below_letters_in_standard_fonts_draw_a_comma_under_the_letter() {
|
||||
let pairs = [
|
||||
("s", "scommaaccent"),
|
||||
("S", "Scommaaccent"),
|
||||
("t", "tcommaaccent"),
|
||||
("T", "Tcommaaccent"),
|
||||
("k", "kcommaaccent"),
|
||||
("K", "Kcommaaccent"),
|
||||
("l", "lcommaaccent"),
|
||||
("L", "Lcommaaccent"),
|
||||
("n", "ncommaaccent"),
|
||||
("N", "Ncommaaccent"),
|
||||
("r", "rcommaaccent"),
|
||||
("R", "Rcommaaccent"),
|
||||
("G", "Gcommaaccent"),
|
||||
];
|
||||
let letters: Vec<&str> = pairs.iter().flat_map(|(base, accented)| [*base, *accented]).collect();
|
||||
let (size, baseline) = (40u32, 60u32);
|
||||
for font in ["Helvetica", "Times-Roman", "Courier", "Helvetica-BoldOblique"] {
|
||||
let mut content = String::new();
|
||||
for i in 0..letters.len() {
|
||||
content.push_str(&format!("BT /F1 {size} Tf {} {} Td <{:02X}> Tj ET\n", 10 + 40 * i, 80 - baseline, 1 + i));
|
||||
}
|
||||
let differences = letters.iter().map(|n| format!("/{n}")).collect::<Vec<_>>().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 {} 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 /Type1 /BaseFont /{font}
|
||||
/Encoding << /Type /Encoding /BaseEncoding /WinAnsiEncoding /Differences [1 {differences}] >> >> endobj
|
||||
trailer << /Root 1 0 R >>
|
||||
%%EOF",
|
||||
20 + 40 * letters.len(),
|
||||
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(), "{font}: {:?}", p.error);
|
||||
// The rows (y down) of the i-th letter that have dark pixels.
|
||||
let ink_rows = |i: u32| -> Vec<u32> {
|
||||
(0..p.height)
|
||||
.filter(|y| ((8 + 40 * i)..(48 + 40 * i).min(p.width)).any(|x| p.rgba[((y * p.width + x) * 4) as usize] < 128))
|
||||
.collect()
|
||||
};
|
||||
for (pair, (_, name)) in pairs.iter().enumerate() {
|
||||
let (base, accented) = (ink_rows(2 * pair as u32), ink_rows(2 * pair as u32 + 1));
|
||||
let (Some(&base_bottom), Some(&bottom)) = (base.last(), accented.last()) else {
|
||||
panic!("{font} {name}: draws nothing ({} rows of its base letter)", base.len());
|
||||
};
|
||||
assert!(bottom > base_bottom + 2, "{font} {name}: a mark hangs below the letter ({bottom} vs {base_bottom})");
|
||||
assert!(
|
||||
(base_bottom + 1..bottom).any(|y| !accented.contains(&y)),
|
||||
"{font} {name}: the mark is apart from the letter, a comma and not a cedilla"
|
||||
);
|
||||
assert!(bottom < baseline + size * 3 / 10, "{font} {name}: the comma stays within the descender ({bottom})");
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// Contributor-original classic-xref vector fixtures; no embedded or external assets.
|
||||
fn raw_crop_unit_pdf(unit: f64, rotation: i32, crop: [f64; 4], marker: Option<[f64; 4]>) -> Vec<u8> {
|
||||
let bounds = crop.map(|n| n.to_string()).join(" ");
|
||||
|
||||
Vendored
+1
-1
@@ -11,7 +11,7 @@ In `hayro-interpret`, Type 3 glyph bounding boxes are transformed to device spac
|
||||
|
||||
| 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) 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<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 with its background painted inside it as the initial backdrop, so a Multiply highlight blends with a dark reading-colours background instead of staying an opaque block (identity on white pages); (20) a tilingLine 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 with its background painted inside it as the initial backdrop, so a Multiply highlight blends with a dark reading-colours background instead of staying an opaque block (identity on white pages); (20) a tiling pattern whose step is too large for a cell pixmap, Line truncated
|
||||
|
||||
+54
-5
@@ -445,7 +445,8 @@ impl StandardKind {
|
||||
/// 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.
|
||||
/// moved along the slant; an ogonek hangs from the letter's right edge; a comma below is
|
||||
/// the font's comma, smaller, under the baseline.
|
||||
fn composite_outline(&self, glyph: GlyphId) -> Option<BezPath> {
|
||||
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)?)?;
|
||||
@@ -455,13 +456,27 @@ impl StandardKind {
|
||||
.map(|g| self.base_font_blob.outline_glyph(g))
|
||||
};
|
||||
let mut path = outline(base)?;
|
||||
let accent = outline(accent)?;
|
||||
let mut accent = outline(accent)?;
|
||||
if path.elements().is_empty() || accent.elements().is_empty() {
|
||||
return Some(path);
|
||||
}
|
||||
if place == Place::CommaBelow {
|
||||
accent = Affine::scale(COMMA_BELOW_SCALE) * accent;
|
||||
}
|
||||
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::CommaBelow => {
|
||||
// Its top a little below the baseline (or the letter's overshoot below it), and
|
||||
// in an italic font moved back along the slant by as much as it is lowered.
|
||||
let dy = b.y0.min(0.0) - COMMA_BELOW_GAP * a.height() - a.y1;
|
||||
let slant = if self.base_font.is_italic() {
|
||||
dy * ITALIC_ACCENT_SLANT
|
||||
} else {
|
||||
0.0
|
||||
};
|
||||
(b.center().x - a.center().x + slant, dy)
|
||||
}
|
||||
Place::Ogonek => (b.x1 - a.x1, 0.0),
|
||||
Place::Above => {
|
||||
let x_top = outline("x")
|
||||
@@ -582,12 +597,21 @@ const COMPOSITE_GLYPH_BASE: u32 = 0x0100_0000;
|
||||
/// an italic stand-in (tan 15°; the standard italics lean 12° to 16°).
|
||||
const ITALIC_ACCENT_SLANT: f64 = 0.27;
|
||||
|
||||
/// PdfCraft patch: the size of a comma accent against the font's comma. A full-size comma
|
||||
/// moved under the baseline reaches past the descenders and into the line below.
|
||||
const COMMA_BELOW_SCALE: f64 = 0.75;
|
||||
|
||||
/// PdfCraft patch: the gap between the baseline and a comma accent, as a share of its height.
|
||||
const COMMA_BELOW_GAP: f64 = 0.15;
|
||||
|
||||
/// Where an accent goes on its base letter.
|
||||
#[derive(Clone, Copy, Debug, PartialEq, Eq)]
|
||||
enum Place {
|
||||
Above,
|
||||
Below,
|
||||
Ogonek,
|
||||
/// The font's comma, smaller, under the letter (the stand-ins have no `commaaccent`).
|
||||
CommaBelow,
|
||||
}
|
||||
|
||||
/// PdfCraft patch: the stand-ins for the standard fonts (PDFium's Foxit fonts) carry only the
|
||||
@@ -596,7 +620,11 @@ enum Place {
|
||||
/// 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.
|
||||
/// The comma-below letters of Romanian (ș ț) and Latvian (ķ ļ ņ ŗ Ģ) are the base letter and the
|
||||
/// font's comma, since the stand-ins have no `commaaccent` either; without them a form laid out
|
||||
/// from its XFA template drew Romanian ș as a blank and ț with a cedilla. Letters whose accent
|
||||
/// isn't a plain one (ď ľ ť, whose caron is an apostrophe beside the letter, and ģ, whose comma
|
||||
/// is turned and above it) aren't here.
|
||||
const ACCENTED_LETTERS: &[(&str, &str, &str, Place)] = &[
|
||||
("Amacron", "A", "macron", Place::Above),
|
||||
("amacron", "a", "macron", Place::Above),
|
||||
@@ -628,6 +656,7 @@ const ACCENTED_LETTERS: &[(&str, &str, &str, Place)] = &[
|
||||
("Gbreve", "G", "breve", Place::Above),
|
||||
("gbreve", "g", "breve", Place::Above),
|
||||
("Gdotaccent", "G", "dotaccent", Place::Above),
|
||||
("Gcommaaccent", "G", "comma", Place::CommaBelow),
|
||||
("gdotaccent", "g", "dotaccent", Place::Above),
|
||||
("Hcircumflex", "H", "circumflex", Place::Above),
|
||||
("hcircumflex", "h", "circumflex", Place::Above),
|
||||
@@ -641,10 +670,16 @@ const ACCENTED_LETTERS: &[(&str, &str, &str, Place)] = &[
|
||||
("iogonek", "i", "ogonek", Place::Ogonek),
|
||||
("Idotaccent", "I", "dotaccent", Place::Above),
|
||||
("Jcircumflex", "J", "circumflex", Place::Above),
|
||||
("Kcommaaccent", "K", "comma", Place::CommaBelow),
|
||||
("kcommaaccent", "k", "comma", Place::CommaBelow),
|
||||
("Lacute", "L", "acute", Place::Above),
|
||||
("lacute", "l", "acute", Place::Above),
|
||||
("Lcommaaccent", "L", "comma", Place::CommaBelow),
|
||||
("lcommaaccent", "l", "comma", Place::CommaBelow),
|
||||
("Nacute", "N", "acute", Place::Above),
|
||||
("nacute", "n", "acute", Place::Above),
|
||||
("Ncommaaccent", "N", "comma", Place::CommaBelow),
|
||||
("ncommaaccent", "n", "comma", Place::CommaBelow),
|
||||
("Ncaron", "N", "caron", Place::Above),
|
||||
("ncaron", "n", "caron", Place::Above),
|
||||
("Omacron", "O", "macron", Place::Above),
|
||||
@@ -655,6 +690,8 @@ const ACCENTED_LETTERS: &[(&str, &str, &str, Place)] = &[
|
||||
("ohungarumlaut", "o", "hungarumlaut", Place::Above),
|
||||
("Racute", "R", "acute", Place::Above),
|
||||
("racute", "r", "acute", Place::Above),
|
||||
("Rcommaaccent", "R", "comma", Place::CommaBelow),
|
||||
("rcommaaccent", "r", "comma", Place::CommaBelow),
|
||||
("Rcaron", "R", "caron", Place::Above),
|
||||
("rcaron", "r", "caron", Place::Above),
|
||||
("Sacute", "S", "acute", Place::Above),
|
||||
@@ -663,8 +700,12 @@ const ACCENTED_LETTERS: &[(&str, &str, &str, Place)] = &[
|
||||
("scircumflex", "s", "circumflex", Place::Above),
|
||||
("Scedilla", "S", "cedilla", Place::Below),
|
||||
("scedilla", "s", "cedilla", Place::Below),
|
||||
("Scommaaccent", "S", "comma", Place::CommaBelow),
|
||||
("scommaaccent", "s", "comma", Place::CommaBelow),
|
||||
("Tcedilla", "T", "cedilla", Place::Below),
|
||||
("tcedilla", "t", "cedilla", Place::Below),
|
||||
("Tcommaaccent", "T", "comma", Place::CommaBelow),
|
||||
("tcommaaccent", "t", "comma", Place::CommaBelow),
|
||||
("Tcaron", "T", "caron", Place::Above),
|
||||
("Utilde", "U", "tilde", Place::Above),
|
||||
("utilde", "u", "tilde", Place::Above),
|
||||
@@ -689,7 +730,8 @@ const ACCENTED_LETTERS: &[(&str, &str, &str, Place)] = &[
|
||||
];
|
||||
|
||||
/// PdfCraft patch: the base letter, accent and placement of an accented letter in
|
||||
/// [`ACCENTED_LETTERS`], by glyph name (`uni011E` and `u011E` forms too).
|
||||
/// [`ACCENTED_LETTERS`], by glyph name (`uni011E` and `u011E` forms too). Ș ș Ț ț by code point:
|
||||
/// the glyph list names only the first two, and gives the names of the second two to Ţ ţ.
|
||||
fn accented_parts(name: &str) -> Option<(&'static str, &'static str, Place)> {
|
||||
let name = normalized_glyph_name(name);
|
||||
let by_name = |n: &str| {
|
||||
@@ -698,5 +740,12 @@ fn accented_parts(name: &str) -> Option<(&'static str, &'static str, Place)> {
|
||||
.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)?)?))
|
||||
by_name(name).or_else(|| {
|
||||
let c = glyph_name_to_unicode(name)?;
|
||||
match c {
|
||||
'\u{021A}' => by_name("Tcommaaccent"),
|
||||
'\u{021B}' => by_name("tcommaaccent"),
|
||||
_ => by_name(glyph_names::get_reverse(c)?),
|
||||
}
|
||||
})
|
||||
}
|
||||
Reference in new issue
Block a user