Merge PR #3497: M2: Type 0 fonts with /ToUnicode /Identity-H read their codes as Unicode

contributors/people.toml: kept both new contributor entries.

contributors/people.toml

@@ -156,3 +156,6 @@ sync_github_name = false
 
 [people.MatrixMagician]
 sync_github_name = true
+
+[people.Lcoding15]
+real_name = "Livio Oswald"

crates/fonts/src/pdf.rs

@@ -1143,7 +1143,8 @@ pub fn glyph_unicode(name: &str) -> Option<char> {
     chars.next().filter(|_| chars.len() == 0)
 }
 
-/// Code → Unicode for a font: its ToUnicode CMap, else (simple fonts) its encoding.
+/// Code → Unicode for a font: its ToUnicode CMap (for a composite font, also the name
+/// `/Identity-H` or `/Identity-V`, read as code = Unicode), else (simple fonts) its encoding.
 fn unicode_map(doc: &Document, font: &Dict, composite: bool) -> Unicode {
     let mut out = Unicode::default();
     if !composite {
@@ -1206,14 +1207,44 @@ fn unicode_map(doc: &Document, font: &Dict, composite: bool) -> Unicode {
             }
         }
     }
-    if let Some(Object::Stream(s)) = font.get(b"ToUnicode").map(|t| doc.resolve(t)).as_deref()
-        && let Ok(data) = s.decoded()
-    {
-        parse_to_unicode(&data, &mut out);
+    match font.get(b"ToUnicode").map(|t| doc.resolve(t)).as_deref() {
+        Some(Object::Stream(s)) => {
+            if let Ok(data) = s.decoded() {
+                parse_to_unicode(&data, &mut out);
+            }
+        }
+        // `/ToUnicode /Identity-H` is not a stream, as ISO 32000-2 §9.10.3 requires, but CAD
+        // exporters (WSCAD among them) write it for composite fonts whose two-byte codes are the
+        // UTF-16 code units. Acrobat shows them as code = Unicode, and so does the renderer's
+        // text layer; without it the text could be seen but not edited or found. The same rule
+        // (code = Unicode, no controls or lone surrogates) is in the vendored renderer,
+        // `Type0Font::char_code_to_unicode` in vendor/hayro-interpret/src/font/cid.rs: keep both alike.
+        Some(Object::Name(n)) if composite && matches!(n.as_slice(), b"Identity-H" | b"Identity-V") => {
+            parse_to_unicode(&identity_to_unicode(), &mut out);
+        }
+        _ => {}
     }
     out
 }
 
+/// A ToUnicode CMap mapping each two-byte code to the same UTF-16 code unit, leaving out the
+/// surrogates (which are not characters on their own) and the controls (C0, DEL and C1, as the
+/// renderer's text layer does). No range crosses a last-byte boundary (§9.10.3).
+fn identity_to_unicode() -> Vec<u8> {
+    let mut ranges = vec![(0x20u32, 0x7Eu32), (0xA0, 0xFF)];
+    ranges.extend((0x01u32..=0xFF).filter(|h| !(0xD8..=0xDF).contains(h)).map(|h| (h << 8, (h << 8) | 0xFF)));
+    let mut cmap = String::from("1 begincodespacerange <0000> <FFFF> endcodespacerange\n");
+    // At most 100 entries per section (§9.7.5.2 limits for CMap files).
+    for chunk in ranges.chunks(100) {
+        cmap.push_str(&format!("{} beginbfrange\n", chunk.len()));
+        for (lo, hi) in chunk {
+            cmap.push_str(&format!("<{lo:04X}> <{hi:04X}> <{lo:04X}>\n"));
+        }
+        cmap.push_str("endbfrange\n");
+    }
+    cmap.into_bytes()
+}
+
 #[cfg(test)]
 mod tests {
     use pdfcraft_cos::{Dict, Document, Object, Stream};
@@ -1489,6 +1520,41 @@ mod tests {
         assert_eq!(m.decode(&[0, 1, 0, 7, 0, 2]), "M á");
     }
 
+    /// WSCAD writes `/ToUnicode /Identity-H` (a name, not a CMap stream) on composite fonts whose
+    /// codes are UTF-16 code units: the codes read as the same Unicode, as in Acrobat. Controls
+    /// and lone surrogates map to nothing, and a simple font's name is not a ToUnicode map.
+    #[test]
+    fn identity_to_unicode_names_read_codes_as_unicode() {
+        let doc = Document::new_empty();
+        for name in ["Identity-H", "Identity-V"] {
+            let f = font(
+                &mut Document::new_empty(),
+                vec![
+                    ("Subtype", Object::name("Type0")),
+                    ("BaseFont", Object::name("RobotoMono-Regular")),
+                    ("Encoding", Object::name("Identity-H")),
+                    ("DescendantFonts", Object::Array(vec![Object::Dict(Dict::new())])),
+                    ("ToUnicode", Object::name(name)),
+                ],
+            );
+            let m = Metrics::from_dict(&doc, &f);
+            assert_eq!(m.decode(&[0, b'Z', 0, 0xFC, 0, b'r', 0x20, 0xAC, 0x4E, 0x2D]), "Zür€中", "{name}");
+            assert_eq!(m.text_of(0x0001), None);
+            assert_eq!(m.text_of(0x007F), None, "DEL is a control");
+            assert_eq!(m.text_of(0x0085), None, "a C1 control");
+            assert_eq!(m.text_of(0x00A0).as_deref(), Some("\u{A0}"), "the range resumes after C1");
+            assert_eq!(m.text_of(0x007E).as_deref(), Some("~"));
+            assert_eq!(m.text_of(0xD800), None);
+            assert_eq!(m.text_of(0xFFFD).as_deref(), Some("\u{FFFD}"));
+        }
+        let simple = font(
+            &mut Document::new_empty(),
+            vec![("Subtype", Object::name("TrueType")), ("BaseFont", Object::name("Arial")), ("ToUnicode", Object::name("Identity-H"))],
+        );
+        let m = Metrics::from_dict(&doc, &simple);
+        assert_eq!(m.text_of(0x41).as_deref(), Some("A"), "the encoding still applies");
+    }
+
     /// Chrome's subsets leave the glyphs of `/DW` width out of `/W` (#1443): "s" (CID 0x56) is
     /// still in the font, but nothing is when the font gives no default width to point at.
     #[test]

crates/render/src/text.rs

@@ -1757,6 +1757,37 @@ mod tests {
         }
     }
 
+    /// WSCAD writes `/ToUnicode /Identity-H`, a name rather than a CMap stream, on Type 0 fonts
+    /// whose two-byte codes are UTF-16 code units. The codes read as that Unicode text (as in
+    /// Acrobat), so the page's text can be selected and found; before, it had none. Controls (here a
+    /// DEL and a C1 control at the line ends) are not text.
+    #[test]
+    fn identity_to_unicode_names_give_text() {
+        use lopdf::{Document, Object, Stream, dictionary};
+        for name in ["Identity-H", "Identity-V"] {
+            let mut doc = Document::with_version("1.4");
+            let cid = doc.add_object(dictionary! {
+                "Type" => "Font", "Subtype" => "CIDFontType2", "BaseFont" => "RobotoMono-Regular",
+                "CIDSystemInfo" => dictionary! { "Registry" => Object::string_literal("Adobe"), "Ordering" => Object::string_literal("Identity"), "Supplement" => 0 },
+                "DW" => 600, "CIDToGIDMap" => "Identity"
+            });
+            let font = doc.add_object(dictionary! { "Type" => "Font", "Subtype" => "Type0", "BaseFont" => "RobotoMono-Regular", "Encoding" => "Identity-H", "DescendantFonts" => vec![Object::Reference(cid)], "ToUnicode" => name });
+            let operators = "BT /F1 12 Tf 1 0 0 1 20 250 Tm <004400650063006B0062006C006100740074007F> Tj 1 0 0 1 20 200 Tm <005A00FC0072006900630068002020AC0085> Tj ET";
+            let content = doc.add_object(Stream::new(dictionary! {}, operators.as_bytes().to_vec()));
+            let pages = doc.new_object_id();
+            let page = doc.add_object(dictionary! { "Type" => "Page", "Parent" => pages, "MediaBox" => vec![Object::Integer(0), Object::Integer(0), Object::Integer(300), Object::Integer(300)], "Resources" => dictionary! {"Font" => dictionary! {"F1" => font}}, "Contents" => content });
+            doc.objects.insert(pages, dictionary! {"Type" => "Pages", "Kids" => vec![Object::Reference(page)], "Count" => 1}.into());
+            let catalog = doc.add_object(dictionary! {"Type" => "Catalog", "Pages" => pages});
+            doc.trailer.set("Root", catalog);
+            let mut bytes = Vec::new();
+            doc.save_to(&mut bytes).unwrap();
+            let pdf = Pdf::new(std::sync::Arc::new(bytes)).unwrap();
+            let text = extract_page(&pdf, 0, &InterpreterSettings::default()).unwrap();
+            assert_eq!(text.plain_text(), "Deckblatt\nZürich €", "{name}");
+            assert_eq!(text.find("zürich"), vec![9..15], "{name}: glyphs 9 to 14");
+        }
+    }
+
     /// One page per text matrix, each showing `codes` in Helvetica whose `/ToUnicode` maps the
     /// codes in `unicode` (a `bfchar` body) to several characters.
     fn ligature_pages(unicode: &str, codes: &str, matrices: &[&str]) -> Pdf {

docs/gaps.md

@@ -1,5 +1,6 @@
 # Where PdfCraft falls short of Acrobat Pro
 
+> **Last reviewed:** 2026-10-15 · **Last updated:** 2026-10-19 · **Change:** minor (gap 2: composite fonts with `/ToUnicode /Identity-H` read as Unicode, hayro-interpret patch 44; estimates unchanged) · **Target:** Adobe Acrobat Pro (Acrobat DC, continuous track 26.002.21931, macOS)
 > **Last reviewed:** 2026-10-15 · **Last updated:** 2026-10-15 · **Change:** minor (gap 12: reading order is scored, not just word F1) · **Target:** Adobe Acrobat Pro (Acrobat DC, continuous track 26.002.21931, macOS)
 > **Last reviewed:** 2026-10-14 · **Last updated:** 2026-10-14 · **Change:** minor (M1: raw-deflate fallback preserves decoding-limit errors; estimates unchanged) · **Target:** Adobe Acrobat Pro (Acrobat DC, continuous track 26.002.21931, macOS)
 > **Last reviewed:** 2026-10-12 · **Last updated:** 2026-10-13 · **Change:** minor (gap 14: Vietnamese catalog shipped; Hindi/Indonesian/Korean and Arabic RTL remain) · **Target:** Adobe Acrobat Pro (Acrobat DC, continuous track 26.002.21931, macOS)
@@ -382,6 +383,7 @@ update the numbers.
 
 | Date | Change | Summary |
 |---|---|---|
+| 2026-10-19 | minor | Gap 2: a Type 0 font whose `/ToUnicode` is the name `/Identity-H` or `/Identity-V` (WSCAD) reads its codes as Unicode, so such pages have text to select, find and edit (hayro-interpret patch 44, `view.render-cid-fonts`). Estimates unchanged. |
 | 2026-10-15 | minor | Gap 12: the text oracle scores reading order as well as word F1, which is a bag of words and cannot see order; the first measurement separated 18 improvements from 6 regressions in a change F1 called unchanged on 26 of 29 files. Estimates unchanged. |
 | 2026-10-14 | minor | M1: raw-deflate fallback preserves decoding-limit errors in strict and tolerant decoding; synthetic filter and COS stream regressions. Estimates unchanged. |
 | 2026-10-15 | patch | Gap 24: record localization and installers as partial (unusable Chinese, Telugu and Arabic; unsigned Linux packages) |

parity/acrobat-features.toml

@@ -782,8 +782,8 @@ milestone = "M2"
 status = "partial"
 commands = []
 tools = []
-evidence = ["crates/render/src/raster.rs::huge_cid_width_ranges_terminate", "crates/render/src/raster.rs::non_embedded_japanese_cid_fonts_draw_with_a_craft_fonts_face", "crates/render/src/raster.rs::mincho_substitute_covers_half_width_katakana"]
-notes = "CID-to-Unicode tables are M2.4; a non-embedded Adobe-Japan1 font is drawn in a craft-fonts Japanese face (Mincho or Gothic by name; BIZ UDMincho for Mincho, which covers half-width katakana) when built with craft-fonts; non-embedded GB1, CNS1 and Korea1 fonts still draw nothing (no allowed face)"
+evidence = ["crates/render/src/raster.rs::huge_cid_width_ranges_terminate", "crates/render/src/raster.rs::non_embedded_japanese_cid_fonts_draw_with_a_craft_fonts_face", "crates/render/src/raster.rs::mincho_substitute_covers_half_width_katakana", "crates/render/src/text.rs::identity_to_unicode_names_give_text", "crates/fonts/src/pdf.rs::identity_to_unicode_names_read_codes_as_unicode"]
+notes = "CID-to-Unicode tables are M2.4; a non-embedded Adobe-Japan1 font is drawn in a craft-fonts Japanese face (Mincho or Gothic by name; BIZ UDMincho for Mincho, which covers half-width katakana) when built with craft-fonts; non-embedded GB1, CNS1 and Korea1 fonts still draw nothing (no allowed face); a `/ToUnicode` given as the name `/Identity-H` or `/Identity-V` (WSCAD) reads codes as Unicode for selection, search and editing, without control characters"
 
 [[feature]]
 id = "view.render-image-codecs"

vendor/README.md

@@ -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

vendor/hayro-interpret/src/font/cid.rs

@@ -45,9 +45,16 @@ pub(crate) struct Type0Font {
     /// PdfCraft patch: whether the CIDs belong to an Adobe character collection (Japan1, GB1,
     /// CNS1, Korea1), whose glyph numbering no substitute other than a CID-keyed CFF font shares.
     adobe_collection: bool,
+    /// PdfCraft patch: `/ToUnicode /Identity-H` (a name, not a CMap stream), which CAD exporters
+    /// such as WSCAD write for fonts whose two-byte codes are UTF-16 code units. Acrobat shows
+    /// such text as the code's Unicode value; the identity CMap the name resolves to maps codes
+    /// to CIDs only and gave no text at all.
+    identity_to_unicode: bool,
 }
 
 impl Type0Font {
+    /// Reads a Type 0 font from its dictionary: the descendant CID font, the encoding CMap and
+    /// the code-to-Unicode map (`/ToUnicode`, the `/Identity-H` name, or the UCS2 CMap).
     pub(crate) fn new(
         dict: &Dict<'_>,
         font_resolver: &FontResolverFn,
@@ -117,6 +124,9 @@ impl Type0Font {
         let cache_key = dict.cache_key();
 
         let mut to_unicode = read_to_unicode(dict, cmap_resolver);
+        let identity_to_unicode = dict
+            .get::<Name<'_>>(TO_UNICODE)
+            .is_some_and(|n| matches!(n.as_ref(), b"Identity-H" | b"Identity-V"));
         let mut to_unicode_is_cid_indexed = false;
 
         // If there is no ToUnicode map, try to get the UCS2 CMap.
@@ -162,6 +172,7 @@ impl Type0Font {
             fallback,
             to_unicode_is_cid_indexed,
             adobe_collection,
+            identity_to_unicode,
         })
     }
 
@@ -430,7 +441,16 @@ impl Type0Font {
         }
     }
 
+    /// The text a character code stands for, or `None` when the font gives none (or, for an
+    /// identity `/ToUnicode` name, when the code is a control or a lone surrogate).
     pub(crate) fn char_code_to_unicode(&self, code: u32) -> Option<BfString> {
+        if self.identity_to_unicode {
+            // Controls and lone surrogates are not text. The same rule builds the editing
+            // map, `identity_to_unicode` in crates/fonts/src/pdf.rs: keep both alike.
+            return char::from_u32(code)
+                .filter(|c| !c.is_control())
+                .map(BfString::Char);
+        }
         if let Some(to_unicode) = &self.to_unicode {
             let key = if self.to_unicode_is_cid_indexed {
                 self.code_to_cid(code).unwrap_or(0)