fix(text): read a TrueType font without an encoding as WinAnsi (#1477)

* fix(text): read a TrueType font without an encoding as WinAnsi (fixes #1468)

* fix(text): describe the WinAnsi reading by pdftotext's output

---------

Co-authored-by: Brandon Thomas <[email protected]>

crates/render/src/text.rs

@@ -2534,4 +2534,43 @@ mod tests {
         let all = t.glyphs_in([0.0, 0.0, 60.0, 40.0]);
         assert_eq!(t.column_text(&all), "日本\n語文");
     }
+
+    /// An embedded TrueType font with no `/Encoding`, flagged `flags`, its `/ToUnicode` (if
+    /// any) mapping only printable ASCII, as OCR engines write the text layer of a scan.
+    fn ocr_layer_text(flags: i64, ascii_to_unicode: bool) -> String {
+        use lopdf::{Document, Object, Stream, dictionary};
+        let mut doc = Document::with_version("1.7");
+        let program = doc.add_object(Stream::new(dictionary! {}, include_bytes!("../../../assets/fonts/Inter-Regular.ttf").to_vec()));
+        let descriptor =
+            doc.add_object(dictionary! { "Type" => "FontDescriptor", "FontName" => "Inter-Regular", "Flags" => flags, "FontFile2" => program });
+        let mut font = dictionary! { "Type" => "Font", "Subtype" => "TrueType", "BaseFont" => "Inter-Regular", "FontDescriptor" => descriptor };
+        if ascii_to_unicode {
+            let cmap = b"/CIDInit /ProcSet findresource begin 12 dict begin begincmap /CMapName /Ascii def /CMapType 2 def 1 begincodespacerange <00> <FF> endcodespacerange 1 beginbfrange <20> <7E> <0020> endbfrange endcmap CMapName currentdict /CMap defineresource pop end end";
+            font.set("ToUnicode", doc.add_object(Stream::new(dictionary! {}, cmap.to_vec())));
+        }
+        let font = doc.add_object(font);
+        // WinAnsi bytes: "Rückfragen für Überhitzungsschutz: können, weiß, Café".
+        let mut ops = b"BT /F1 14 Tf 1 0 0 1 20 200 Tm (".to_vec();
+        ops.extend_from_slice(b"R\xfcckfragen f\xfcr \xdcberhitzungsschutz: k\xf6nnen, wei\xdf, Caf\xe9");
+        ops.extend_from_slice(b") Tj ET");
+        let content = doc.add_object(Stream::new(dictionary! {}, ops));
+        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(400), Object::Integer(400)], "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();
+        extract_page(&pdf, 0, &InterpreterSettings::default()).unwrap().plain_text()
+    }
+
+    #[test]
+    fn truetype_without_an_encoding_reads_its_codes_as_win_ansi() {
+        // Café: 0xE9 is /Oslash in StandardEncoding, so reading the codes as Standard first and
+        // WinAnsi only for the gaps would still give "CafØ".
+        let expected = "Rückfragen für Überhitzungsschutz: können, weiß, Café";
+        assert_eq!(ocr_layer_text(4, false), expected, "symbolic, no /ToUnicode");
+        assert_eq!(ocr_layer_text(32, true), expected, "nonsymbolic, /ToUnicode for ASCII only");
+    }
 }

vendor/README.md

@@ -7,6 +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 `.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-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
 

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

@@ -1,5 +1,5 @@
 use crate::font::blob::{CffFontBlob, OpenTypeFontBlob};
-use crate::font::generated::{glyph_names, mac_os_roman, mac_roman, standard};
+use crate::font::generated::{glyph_names, mac_os_roman, mac_roman, standard, win_ansi};
 use crate::font::standard_font::StandardKind;
 use crate::font::{
     Encoding, FallbackFontQuery, FontFlags, glyph_name_to_unicode, read_to_unicode,
@@ -191,7 +191,7 @@ impl TrueTypeFont {
 
         match &self.kind {
             Kind::Embedded(e) => e
-                .code_to_name(code as u8)
+                .code_to_unicode_name(code as u8)
                 .and_then(glyph_name_to_unicode)
                 .map(BfString::Char),
             Kind::Standard(s) => s.char_code_to_unicode(code as u8).map(BfString::Char),
@@ -277,6 +277,19 @@ impl EmbeddedKind {
             .or_else(|| standard::get(code))
     }
 
+    /// PdfCraft patch: the glyph name text extraction reads a code as. Without a base encoding
+    /// a TrueType font's codes are read as WinAnsi, matching pdftotext's output, not as
+    /// Standard: OCR engines write the text layer of a scan with WinAnsi codes and no
+    /// `/Encoding`, and Standard has no name for ü, ö or ß and gives é (0xE9) as Ø. Glyph
+    /// selection (`code_to_name`) is unchanged.
+    fn code_to_unicode_name(&self, code: u8) -> Option<&str> {
+        self.differences
+            .get(&code)
+            .map(|s| s.as_str())
+            .or_else(|| self.encoding.map_code(code))
+            .or_else(|| win_ansi::get(code))
+    }
+
     fn outline_glyph(&self, glyph: GlyphId) -> BezPath {
         self.base_font.outline_glyph(glyph)
     }