mirror of
https://github.com/storytold/pdfcraft.git
synced 2026-11-13 14:22:25 +00:00
M10: a symbolic TrueType font without an encoding reads its glyph names (#3962)
FrameMaker files distilled with Distiller 3 embed symbolic TrueType subsets with no /Encoding and no /ToUnicode, whose codes are glyph positions in the Macintosh order, 29 below ASCII; the font's own cmap maps them to the right glyphs. Read as WinAnsi (extraction, Word export) or as Standard (the editor), `Solid` came out as `6ROLG`. Both readers now take the post-table name of the glyph a code selects, when that name has a Unicode value, as MuPDF does; the editor's reverse map makes typing set the same glyphs. Fonts flagged Nonsymbolic, fonts with a named base encoding, and fonts the editor already treats as Symbol or ZapfDingbats by name keep their old reading. Vendored hayro-interpret patch (46). Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
mtlcl410andClaude Opus 5.5 committed
1 parent
fa5f9f8c3b
commit
3271fabc5c
5 files changed
+255
-1
No files matched your search
@@ -1227,6 +1227,35 @@ pub fn glyph_unicode(name: &str) -> Option<char> {
|
||||
chars.next().filter(|_| chars.len() == 0)
|
||||
}
|
||||
|
||||
/// What each code of an embedded TrueType font that isn't flagged non-symbolic and names no base
|
||||
/// encoding shows, by the `post` table name of the glyph its `cmap` selects (the way the renderer
|
||||
/// selects it: the code, then at 0xF000, 0xF100 and 0xF200). Such a font's codes need not be
|
||||
/// Standard or WinAnsi: FrameMaker files distilled with Distiller 3 number them in the Macintosh
|
||||
/// glyph order, 29 below ASCII, so `Solid` read as `6ROLG` and typing set the wrong glyphs (#3962).
|
||||
/// Codes without a glyph, or whose glyph has no name with a Unicode value, are left out.
|
||||
fn symbolic_glyph_texts(doc: &Document, font: &Dict) -> Vec<(u32, String)> {
|
||||
use skrifa::{GlyphId, raw::TableProvider as _};
|
||||
let Some(descriptor) = dict(doc, font.get(b"FontDescriptor")) else { return Vec::new() };
|
||||
// Flag bit 6, Nonsymbolic (ISO 32000-2 Table 121).
|
||||
let flags = descriptor.get(b"Flags").and_then(|v| doc.resolve(v).as_f64()).unwrap_or(0.0) as i64;
|
||||
if flags & 32 != 0 {
|
||||
return Vec::new();
|
||||
}
|
||||
let Some(object) = descriptor.get(b"FontFile2") else { return Vec::new() };
|
||||
let object = doc.resolve(object);
|
||||
let Object::Stream(stream) = object.as_ref() else { return Vec::new() };
|
||||
let Ok(bytes) = stream.decoded_within(16 << 20) else { return Vec::new() };
|
||||
let Ok(face) = skrifa::FontRef::from_index(&bytes, 0) else { return Vec::new() };
|
||||
let (Ok(cmap), Ok(post)) = (face.cmap(), face.post()) else { return Vec::new() };
|
||||
(0..=255u32)
|
||||
.filter_map(|code| {
|
||||
let glyph = [0, 0xF000, 0xF100, 0xF200].into_iter().find_map(|o| cmap.map_codepoint(code + o).filter(|g| *g != GlyphId::NOTDEF))?;
|
||||
let glyph = skrifa::raw::types::GlyphId16::new(u16::try_from(glyph.to_u32()).ok()?);
|
||||
Some((code, glyph_text(post.glyph_name(glyph)?)?))
|
||||
})
|
||||
.collect()
|
||||
}
|
||||
|
||||
/// 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 {
|
||||
@@ -1269,6 +1298,11 @@ fn unicode_map(doc: &Document, font: &Dict, composite: bool) -> Unicode {
|
||||
out.encoding.insert(code as u32, c.to_string());
|
||||
}
|
||||
}
|
||||
// A font named as Symbol or ZapfDingbats keeps reporting nothing: its names may be as
|
||||
// un-Latin as its codes (WordPerfect's WPTypographicSymbols calls its apostrophe `equal`).
|
||||
if base_name.is_none() && !symbolic_builtin {
|
||||
out.encoding.extend(symbolic_glyph_texts(doc, font));
|
||||
}
|
||||
if let Some(Object::Dict(d)) = enc.as_deref()
|
||||
&& let Some(diffs) = d.get(b"Differences").map(|x| doc.resolve(x)).and_then(|x| x.as_array().cloned())
|
||||
{
|
||||
|
||||
@@ -190,6 +190,95 @@ fn mac_subset_cmap_uses_pdf_unicode_without_changing_source_program() {
|
||||
assert!(append_editor_cmap(&mut broken, &std::collections::BTreeMap::from([(65, 1)])).is_none());
|
||||
}
|
||||
|
||||
/// #3962: a symbolic TrueType subset with no `/Encoding` whose codes are glyph positions in
|
||||
/// the Macintosh order, 29 below ASCII, mapped by a Mac (1,0) cmap. Its text is what the
|
||||
/// `post` table names the glyphs its codes select, and typing encodes back to those codes.
|
||||
/// A (3,0) symbol cmap at 0xF000 + code is read too: code 0x20, `.notdef` in the Mac table,
|
||||
/// shows `k` there, and code 0xC0 `é`.
|
||||
#[test]
|
||||
fn a_symbolic_truetype_font_without_an_encoding_reads_its_glyph_names() {
|
||||
use skrifa::MetadataProvider as _;
|
||||
const TEXT: &str = "Solid state";
|
||||
let original = include_bytes!("../../../../assets/fonts/Inter-Regular.ttf");
|
||||
let charmap = skrifa::FontRef::new(original).unwrap().charmap();
|
||||
// A format 6 Mac cmap over codes 3..=0x57: each letter at its code minus 29.
|
||||
let (first, last) = (3u16, 0x57u16);
|
||||
let mut glyphs = vec![0u16; usize::from(last - first + 1)];
|
||||
for c in TEXT.chars() {
|
||||
glyphs[usize::from(c as u16 - 29 - first)] = u16::try_from(charmap.map(c).unwrap().to_u32()).unwrap();
|
||||
}
|
||||
let mac_len = 10 + 2 * glyphs.len() as u16;
|
||||
let gid = |c: char| u16::try_from(charmap.map(c).unwrap().to_u32()).unwrap();
|
||||
// Two subtables: the Mac one at 20, the symbol one after it.
|
||||
let mut cmap = vec![0, 0, 0, 2, 0, 1, 0, 0, 0, 0, 0, 20, 0, 3, 0, 0];
|
||||
cmap.extend_from_slice(&(20 + u32::from(mac_len)).to_be_bytes());
|
||||
cmap.extend_from_slice(&[0, 6]);
|
||||
cmap.extend_from_slice(&mac_len.to_be_bytes());
|
||||
cmap.extend_from_slice(&[0, 0]);
|
||||
cmap.extend_from_slice(&first.to_be_bytes());
|
||||
cmap.extend_from_slice(&(glyphs.len() as u16).to_be_bytes());
|
||||
glyphs.iter().for_each(|g| cmap.extend_from_slice(&g.to_be_bytes()));
|
||||
// Format 4: 0xF020 → k, 0xF0C0 → é, then the closing 0xFFFF segment.
|
||||
let segments = [(0xF020u16, gid('k')), (0xF0C0, gid('é')), (0xFFFF, 0)];
|
||||
let words: Vec<u16> = [4, 16 + 8 * 3, 0, 6, 4, 1, 2]
|
||||
.into_iter()
|
||||
.chain(segments.iter().map(|s| s.0))
|
||||
.chain([0])
|
||||
.chain(segments.iter().map(|s| s.0))
|
||||
.chain(segments.iter().map(|&(code, glyph)| if code == 0xFFFF { 1 } else { glyph.wrapping_sub(code) }))
|
||||
.chain([0, 0, 0])
|
||||
.collect();
|
||||
words.iter().for_each(|w| cmap.extend_from_slice(&w.to_be_bytes()));
|
||||
let mut subset = original.to_vec();
|
||||
let count = u16::from_be_bytes(subset[4..6].try_into().unwrap()) as usize;
|
||||
let entry = (0..count).map(|i| 12 + i * 16).find(|i| &subset[*i..*i + 4] == b"cmap").unwrap();
|
||||
let offset = subset.len() as u32;
|
||||
subset[entry + 8..entry + 12].copy_from_slice(&offset.to_be_bytes());
|
||||
subset[entry + 12..entry + 16].copy_from_slice(&(cmap.len() as u32).to_be_bytes());
|
||||
subset.extend_from_slice(&cmap);
|
||||
let codes: Vec<u8> = TEXT.bytes().map(|b| b - 29).collect();
|
||||
let metrics = |flags: i64, encoding: Option<Object>| {
|
||||
let mut doc = Document::new_empty();
|
||||
let program = doc.add(Object::Stream(Stream::flate(Dict::new(), &subset)));
|
||||
let mut descriptor = Dict::new();
|
||||
descriptor.set(b"Flags".to_vec(), Object::Int(flags));
|
||||
descriptor.set(b"FontFile2".to_vec(), Object::Ref(program));
|
||||
let mut entries = vec![("Subtype", Object::name("TrueType")), ("FontDescriptor", Object::Dict(descriptor))];
|
||||
if let Some(encoding) = encoding {
|
||||
entries.push(("Encoding", encoding));
|
||||
}
|
||||
let f = font(&mut doc, entries);
|
||||
Metrics::from_dict(&doc, &f)
|
||||
};
|
||||
let symbolic = metrics(4, None);
|
||||
assert_eq!(symbolic.decode(&codes), TEXT);
|
||||
assert_eq!(symbolic.decode(&[0x20, 0xC0]), "ké");
|
||||
assert_eq!(symbolic.encode("Solid").as_deref(), Some(&codes[..5]), "typing sets the same glyphs");
|
||||
// A named encoding, or the Nonsymbolic flag, says what the codes are: they read through it.
|
||||
assert_eq!(metrics(4, Some(Object::name("WinAnsiEncoding"))).decode(&codes), "6ROLGVWDWH");
|
||||
// `/Differences` still names its codes: 0x36 shows `A` there, not the glyph's `S`.
|
||||
let mut differences = Dict::new();
|
||||
differences.set(b"Differences".to_vec(), Object::Array(vec![Object::Int(0x36), Object::name("A")]));
|
||||
assert_eq!(metrics(4, Some(Object::Dict(differences))).decode(&codes), "Aolid state");
|
||||
assert_eq!(metrics(32, None).decode(&codes), "6ROLGVWDWH");
|
||||
// A font named as a symbol font reports nothing, as before: its glyph names can't be
|
||||
// trusted to be Latin either.
|
||||
let mut doc = Document::new_empty();
|
||||
let program = doc.add(Object::Stream(Stream::flate(Dict::new(), &subset)));
|
||||
let mut descriptor = Dict::new();
|
||||
descriptor.set(b"Flags".to_vec(), Object::Int(4));
|
||||
descriptor.set(b"FontFile2".to_vec(), Object::Ref(program));
|
||||
let f = font(
|
||||
&mut doc,
|
||||
vec![
|
||||
("Subtype", Object::name("TrueType")),
|
||||
("BaseFont", Object::name("KNMDCP+WPTypographicSymbols")),
|
||||
("FontDescriptor", Object::Dict(descriptor)),
|
||||
],
|
||||
);
|
||||
assert_eq!(Metrics::from_dict(&doc, &f).decode(&codes), "");
|
||||
}
|
||||
|
||||
fn metrics_with_flags(flags: Option<Object>) -> Metrics {
|
||||
let mut doc = Document::new_empty();
|
||||
let mut descriptor = Dict::new();
|
||||
|
||||
@@ -1625,6 +1625,106 @@ fn rounded_pixel_budget_invalid_requests_never_reach_allocator() {
|
||||
}
|
||||
}
|
||||
|
||||
/// #3962: FrameMaker files distilled with Distiller 3 embed TrueType subsets that are symbolic,
|
||||
/// with no `/Encoding` and no `/ToUnicode`, whose codes are glyph positions in the Macintosh
|
||||
/// order, 29 below ASCII; the font's own `cmap` maps them to the right glyphs. Read as WinAnsi
|
||||
/// the text came out shifted (`Solid` as `6ROLG`), in the editor and in Word export alike. The
|
||||
/// `post` table names the glyph each code selects, which gives the text (vendored
|
||||
/// hayro-interpret patch 51). A font with an `/Encoding` still reads its codes through it.
|
||||
#[test]
|
||||
fn a_symbolic_truetype_font_without_an_encoding_reads_its_glyph_names() {
|
||||
use skrifa::MetadataProvider;
|
||||
use skrifa::raw::TableProvider;
|
||||
const TEXT: &str = "Solid state";
|
||||
// One more code, 0x3D, selects a glyph whose name has no Unicode value (a stylistic
|
||||
// variant such as `a.ss01`): it still reads as WinAnsi, `=`.
|
||||
const UNNAMED: u16 = 0x3D;
|
||||
// And 0x3E one named `uniXXXX`, which reads as that code point.
|
||||
const UNI: u16 = 0x3E;
|
||||
let font = include_bytes!("../../../../assets/fonts/JetBrainsMono-Regular.ttf");
|
||||
let face = skrifa::FontRef::new(font).expect("the test font parses");
|
||||
let charmap = face.charmap();
|
||||
let post = face.post().expect("the test font has a post table");
|
||||
let glyphs = face.maxp().expect("the test font has a maxp table").num_glyphs();
|
||||
let variant = (1..glyphs)
|
||||
.find(|&g| post.glyph_name(skrifa::raw::types::GlyphId16::new(g)).is_some_and(|n| n.contains('.') && !n.starts_with('.')))
|
||||
.expect("the test font has a variant glyph");
|
||||
let (uni, uni_char) = (1..glyphs)
|
||||
.find_map(|g| {
|
||||
let name = post.glyph_name(skrifa::raw::types::GlyphId16::new(g))?;
|
||||
let c = char::from_u32(u32::from_str_radix(name.strip_prefix("uni")?, 16).ok()?)?;
|
||||
(!c.is_control()).then_some((g, c))
|
||||
})
|
||||
.expect("the test font names a glyph uniXXXX");
|
||||
// Codes 29 below ASCII, mapped by a (3,0) symbol cmap at 0xF000 + code.
|
||||
let mut map: Vec<(u16, u16)> =
|
||||
TEXT.chars().map(|c| (0xF000 + c as u16 - 29, charmap.map(c).expect("the test font has the letter").to_u32() as u16)).collect();
|
||||
map.push((0xF000 + UNNAMED, variant));
|
||||
map.push((0xF000 + UNI, uni));
|
||||
map.sort_unstable();
|
||||
map.dedup();
|
||||
// A format 4 subtable: one segment per code, then the closing 0xFFFF segment.
|
||||
let segments: Vec<(u16, u16)> = map.iter().copied().chain([(0xFFFF, 0)]).collect();
|
||||
let n = segments.len() as u16;
|
||||
let mut sub = Vec::new();
|
||||
let words = |v: &mut Vec<u8>, w: &[u16]| w.iter().for_each(|w| v.extend_from_slice(&w.to_be_bytes()));
|
||||
words(&mut sub, &[4, 16 + 8 * n, 0, 2 * n, 2, 0, 2 * n - 2]);
|
||||
words(&mut sub, &segments.iter().map(|s| s.0).collect::<Vec<_>>());
|
||||
words(&mut sub, &[0]);
|
||||
words(&mut sub, &segments.iter().map(|s| s.0).collect::<Vec<_>>());
|
||||
words(&mut sub, &segments.iter().map(|&(code, gid)| if code == 0xFFFF { 1 } else { gid.wrapping_sub(code) }).collect::<Vec<_>>());
|
||||
words(&mut sub, &vec![0; segments.len()]);
|
||||
let mut cmap = Vec::new();
|
||||
words(&mut cmap, &[0, 1, 3, 0]);
|
||||
cmap.extend_from_slice(&12u32.to_be_bytes());
|
||||
cmap.extend(sub);
|
||||
// The new cmap goes at the end; the table directory's `cmap` entry points at it.
|
||||
let mut program = font.to_vec();
|
||||
while !program.len().is_multiple_of(4) {
|
||||
program.push(0);
|
||||
}
|
||||
let at = program.len();
|
||||
program.extend(&cmap);
|
||||
let tables = usize::from(u16::from_be_bytes([font[4], font[5]]));
|
||||
let entry = (0..tables).map(|i| 12 + 16 * i).find(|&e| &font[e..e + 4] == b"cmap").expect("the test font has a cmap");
|
||||
program[entry + 8..entry + 12].copy_from_slice(&(at as u32).to_be_bytes());
|
||||
program[entry + 12..entry + 16].copy_from_slice(&(cmap.len() as u32).to_be_bytes());
|
||||
|
||||
let text_of = |encoding: &str| -> String {
|
||||
let codes: String = TEXT.chars().map(|c| format!("{:02X}", c as u8 - 29)).collect::<String>() + &format!("{UNNAMED:02X}{UNI:02X}");
|
||||
let content = format!("BT /F1 14 Tf 10 40 Td <{codes}> Tj ET");
|
||||
let objects: Vec<Vec<u8>> = vec![
|
||||
b"<< /Type /Catalog /Pages 2 0 R >>".to_vec(),
|
||||
b"<< /Type /Pages /Kids [3 0 R] /Count 1 >>".to_vec(),
|
||||
b"<< /Type /Page /Parent 2 0 R /MediaBox [0 0 300 80] /Contents 4 0 R /Resources << /Font << /F1 5 0 R >> >> >>".to_vec(),
|
||||
format!("<< /Length {} >>\nstream\n{content}\nendstream", content.len()).into_bytes(),
|
||||
format!("<< /Type /Font /Subtype /TrueType /BaseFont /ABCDEF+JetBrainsMono-Regular /FirstChar 0 /LastChar 255 /Widths [{}] /FontDescriptor 6 0 R {encoding}>>", vec!["600"; 256].join(" ")).into_bytes(),
|
||||
b"<< /Type /FontDescriptor /FontName /ABCDEF+JetBrainsMono-Regular /Flags 4 /FontBBox [-500 -300 1200 1000] /ItalicAngle 0 /Ascent 1020 /Descent -300 /CapHeight 730 /StemV 80 /FontFile2 7 0 R >>".to_vec(),
|
||||
[format!("<< /Length {} >>\nstream\n", program.len()).into_bytes(), program.clone(), b"\nendstream".to_vec()].concat(),
|
||||
];
|
||||
let mut pdf = b"%PDF-1.3\n".to_vec();
|
||||
let mut offsets = Vec::new();
|
||||
for (i, object) in objects.iter().enumerate() {
|
||||
offsets.push(pdf.len());
|
||||
pdf.extend(format!("{} 0 obj\n", i + 1).into_bytes());
|
||||
pdf.extend(object);
|
||||
pdf.extend(b"\nendobj\n");
|
||||
}
|
||||
let xref = pdf.len();
|
||||
pdf.extend(format!("xref\n0 {}\n0000000000 65535 f \n", objects.len() + 1).into_bytes());
|
||||
for offset in offsets {
|
||||
pdf.extend(format!("{offset:010} 00000 n \n").into_bytes());
|
||||
}
|
||||
pdf.extend(format!("trailer << /Size {} /Root 1 0 R >>\nstartxref\n{xref}\n%%EOF\n", objects.len() + 1).into_bytes());
|
||||
let mut r = PageRenderer::new(Arc::new(pdf), RenderConfig::default());
|
||||
let page = r.filtered_text(0, crate::text::TextFilter::default()).expect("the page has text");
|
||||
page.glyphs.iter().map(|g| g.text.as_str()).collect()
|
||||
};
|
||||
assert_eq!(text_of(""), format!("Solid state={uni_char}"));
|
||||
// An encoding says what the codes are, so they read through it.
|
||||
assert_eq!(text_of("/Encoding /WinAnsiEncoding "), "6ROLGVWDWH=>");
|
||||
}
|
||||
|
||||
/// Issue #102: an A4 page (595.28×841.89 pt) rendered 595×841 at 72 dpi, dropping the last
|
||||
/// partial row and column. Like pdftoppm it is now 596×842, the edge pixels partly covered.
|
||||
#[test]
|
||||
|
||||
Vendored
+1
-1
@@ -39,7 +39,7 @@ Other resource categories retain their existing parent-chain lookup.
|
||||
|
||||
| Crate | Version | Licence | Patches | Test |
|
||||
|---|---|---|---|---|
|
||||
| hayro-interpret | 0.7.0 | Apache-2.0 OR MIT | (1) select `/AP /N` appearance states via `/AS` (checkboxes, radios, stateful icons) and honour the NoView flag; (2) Type3 Unicode fallback to `/Encoding` glyph names, then printable ASCII; (3) `Type3Glyph::advance_width`; (4) `InterpreterSettings::ocg_overrides` for viewer layer toggles; (5) soft masks whose group lacks `/CS` were dropped (Chrome gradient text); (6) paint nesting cap `MAX_PAINT_NESTING` for tiling patterns and Type 3 glyphs (self-referencing content overflowed the stack); (7) CID width ranges in `/W` and `/W2` clamped to `MAX_CID` (a `0 4294967295 w` range hung); (8) `InterpreterSettings::hide_comments` skips markup annotations but keeps widgets and links (View ▸ Hide all comments); (9) `image_size_ok`: images and masks over 2^28 pixels are not decoded (a fuzzed `/W 4294967295` stencil mask allocated 4 GiB); (10) `MAX_NESTED_PAINTS`: nested paints (forms, Type 3 glyphs and tiling patterns inside one another) share a per-page budget of 50,000 (a glyph showing eight glyphs of its own font, sixteen deep, hung); (11) depends on skrifa 0.47 instead of 0.42 (upstream read-fonts fixed a Type 1 tokenizer that recursed through runs of numbers: a fuzzed font hung or overflowed the stack), with the one API change (`Charset::glyph_id` returns `Option`); (12) annotation appearances whose `/BBox` or `/Matrix` collapses to a line or a point are skipped (mapping them onto `/Rect` divided by zero and handed the device infinite or NaN matrices); (13) a Highlight annotation without a usable normal appearance is drawn from its `/QuadPoints`, `/C` and `/CA` with Multiply blending, as pdfcraft-annot draws highlights (it was not drawn at all); (14) simple-font `/Widths` (`read_widths`): entries only for codes 0–255 (one entry per code below `/FirstChar` was allocated: `4294967295` asked for 34 GB), an entry that isn't a number leaves its code missing instead of ending the array, and a `/LastChar` below `/FirstChar` gives no widths instead of discarding the font for a standard one; (15) the appearance box is mapped onto `/Rect` corner to corner: the translation now accounts for the scale (an appearance whose box didn't start at the origin and differed in size from `/Rect` was drawn shifted); (16) a clip set by `W`/`W*` takes effect after whichever path-painting operator ends the path (`S`, `f`, `B`, … as well as `n`; ISO 32000-2 §8.5.4): it was applied only on `n`, so `re W* S` clipped nothing and the clip stayed pending for a later, unrelated `n`; (17) `InterpreterSettings::cancelled`: once set, interpretation stops before the next content operator (a render pool sets it for every worker when dropped, after an edit or on closing, and for one worker when the watchdog gives up on its render, so renders whose answers nobody can receive stop instead of running to the end); (18) `MAX_PAGE_CONTENT`: the content a page holds at once (its contents, and the forms, tiling patterns and Type 3 glyph procedures being painted) stays within 512 MiB (`decode_content`; once it runs out, `InterpreterWarning::ContentTruncated` is reported (once per page by pdfcraft-render) so a truncated page is not a clean render; each level gives its bytes back when it finishes): forms nest fifty deep and each level kept its content while the next ran, so a form painting itself around a stream inflating to 256 MiB would have held over 12 GB; and Type 0 sampled functions take at most `MAX_SAMPLE_ENTRIES` (2^21) table points and `MAX_SAMPLE_VALUES` (2^23) samples, read no further than `/Size` asks (256 MiB of 1-bit samples asked for over 8 GB); (19) mesh shadings (types 4–7) are sampled only inside the area being drawn (`ShadingPattern::encode_within`, which the vendored hayro renderer calls with that area plus a pixel), within 8 visits per pixel of it plus 4 per triangle (`TriangleSampler`), and patches are triangulated one at a time: points far off the page were sampled over their whole bounding box, up to 65536 × 65536 entries (a fuzzed 147-byte patch stream; a synthetic page passed 6 GB in six seconds), ten thousand overlapping triangles ran for minutes, and every patch became 722 triangles before any limit; meshes hold at most `MAX_MESH_PATCHES` (2^16) patches and `MAX_MESH_TRIANGLES` (2^20) triangles, a lattice needs two to 2^19 vertices per row (`/VerticesPerRow 0` pushed empty rows for ever; one huge row read the whole stream), and a page samples at most `MAX_PAGE_MESH_TRIANGLES` (2^25) mesh triangles in all (a mesh painted a thousand times was triangulated a thousand times); each cut logs a warning; (20) PDF function construction is limited to 64 levels and 10,000 total nodes with cycle detection; calculator parsing and evaluation share procedure depth/work budgets, integer division/bitshift/rotation/index are panic-free, and fixed-size stack errors propagate; (21) a Type 0 font drawn with a substitute that isn't CID-keyed (it isn't embedded, or its program doesn't load) draws `.nLine truncated
|
||||
| hayro-interpret | 0.7.0 | Apache-2.0 OR MIT | (1) select `/AP /N` appearance states via `/AS` (checkboxes, radios, stateful icons) and honour the NoView flag; (2) Type3 Unicode fallback to `/Encoding` glyph names, then printable ASCII; (3) `Type3Glyph::advance_width`; (4) `InterpreterSettings::ocg_overrides` for viewer layer toggles; (5) soft masks whose group lacks `/CS` were dropped (Chrome gradient text); (6) paint nesting cap `MAX_PAINT_NESTING` for tiling patterns and Type 3 glyphs (self-referencing content overflowed the stack); (7) CID width ranges in `/W` and `/W2` clamped to `MAX_CID` (a `0 4294967295 w` range hung); (8) `InterpreterSettings::hide_comments` skips markup annotations but keeps widgets and links (View ▸ Hide all comments); (9) `image_size_ok`: images and masks over 2^28 pixels are not decoded (a fuzzed `/W 4294967295` stencil mask allocated 4 GiB); (10) `MAX_NESTED_PAINTS`: nested paints (forms, Type 3 glyphs and tiling patterns inside one another) share a per-page budget of 50,000 (a glyph showing eight glyphs of its own font, sixteen deep, hung); (11) depends on skrifa 0.47 instead of 0.42 (upstream read-fonts fixed a Type 1 tokenizer that recursed through runs of numbers: a fuzzed font hung or overflowed the stack), with the one API change (`Charset::glyph_id` returns `Option`); (12) annotation appearances whose `/BBox` or `/Matrix` collapses to a line or a point are skipped (mapping them onto `/Rect` divided by zero and handed the device infinite or NaN matrices); (13) a Highlight annotation without a usable normal appearance is drawn from its `/QuadPoints`, `/C` and `/CA` with Multiply blending, as pdfcraft-annot draws highlights (it was not drawn at all); (14) simple-font `/Widths` (`read_widths`): entries only for codes 0–255 (one entry per code below `/FirstChar` was allocated: `4294967295` asked for 34 GB), an entry that isn't a number leaves its code missing instead of ending the array, and a `/LastChar` below `/FirstChar` gives no widths instead of discarding the font for a standard one; (15) the appearance box is mapped onto `/Rect` corner to corner: the translation now accounts for the scale (an appearance whose box didn't start at the origin and differed in size from `/Rect` was drawn shifted); (16) a clip set by `W`/`W*` takes effect after whichever path-painting operator ends the path (`S`, `f`, `B`, … as well as `n`; ISO 32000-2 §8.5.4): it was applied only on `n`, so `re W* S` clipped nothing and the clip stayed pending for a later, unrelated `n`; (17) `InterpreterSettings::cancelled`: once set, interpretation stops before the next content operator (a render pool sets it for every worker when dropped, after an edit or on closing, and for one worker when the watchdog gives up on its render, so renders whose answers nobody can receive stop instead of running to the end); (18) `MAX_PAGE_CONTENT`: the content a page holds at once (its contents, and the forms, tiling patterns and Type 3 glyph procedures being painted) stays within 512 MiB (`decode_content`; once it runs out, `InterpreterWarning::ContentTruncated` is reported (once per page by pdfcraft-render) so a truncated page is not a clean render; each level gives its bytes back when it finishes): forms nest fifty deep and each level kept its content while the next ran, so a form painting itself around a stream inflating to 256 MiB would have held over 12 GB; and Type 0 sampled functions take at most `MAX_SAMPLE_ENTRIES` (2^21) table points and `MAX_SAMPLE_VALUES` (2^23) samples, read no further than `/Size` asks (256 MiB of 1-bit samples asked for over 8 GB); (19) mesh shadings (types 4–7) are sampled only inside the area being drawn (`ShadingPattern::encode_within`, which the vendored hayro renderer calls with that area plus a pixel), within 8 visits per pixel of it plus 4 per triangle (`TriangleSampler`), and patches are triangulated one at a time: points far off the page were sampled over their whole bounding box, up to 65536 × 65536 entries (a fuzzed 147-byte patch stream; a synthetic page passed 6 GB in six seconds), ten thousand overlapping triangles ran for minutes, and every patch became 722 triangles before any limit; meshes hold at most `MAX_MESH_PATCHES` (2^16) patches and `MAX_MESH_TRIANGLES` (2^20) triangles, a lattice needs two to 2^19 vertices per row (`/VerticesPerRow 0` pushed empty rows for ever; one huge row read the whole stream), and a page samples at most `MAX_PAGE_MESH_TRIANGLES` (2^25) mesh triangles in all (a mesh painted a thousand times was triangulated a thousand times); each cut logs a warning; (20) PDF function construction is limited to 64 levels and 10,000 total nodes with cycle detection; calculator parsing and evaluation share procedure depth/work budgets, integer division/bitshift/rotation/index are panic-free, and fixed-size stack errors propagate; (21) a Type 0 font drawn with a substitute that isn't CID-keyed (it isn't embedded, or its program doesn't load) draws `.nLine truncated
|
||||
| hayro | 0.7.1 | Apache-2.0 OR MIT | (1) `RenderSettings::{x_offset, y_offset}` to render one tile of a large page; (2) images over `MAX_IMAGE_PIXELS` (2^28) are skipped (a fuzzed `/W 4294967295` hung in resampling); (3) `tiling_cell_scale` keeps a tiling pattern's cell pixmap within 3000 px a side whatever its `/XStep`/`/YStep` (a fuzzed step far beyond `/BBox` allocated 2 GB); (4) stroke widths clamped to 4 × (canvas width + height) device pixels (a fuzzed `/LW 9223372036854775807` allocated 10 GB in stroke expansion); (5) `usable_dash_pattern`: a stroke whose dash pattern could cut it into more than `MAX_DASHES_PER_STROKE` (250,000) pieces, counting kurbo's restart of the pattern at every subpath and `ClosePath`, is drawn solid (a fuzzed `/D [[11] 0]` on a line from x = 92234775807 allocated over 5 GB, `[0.000001] 0 d` on a 20 pt line over 10 GB); (6) a dash pattern with a negative or non-finite entry, or a period that isn't positive, is drawn solid (`[-1 -1] 0 d` looped for ever in kurbo); (7) `render_size` and `render_into`: render into a buffer the caller allocates (PdfCraft renders into pixel-aligned memory that the GUI takes over as texture data); `render` is `render_into` on a new pixmap; (8) checked image source/target/RGBA, alpha-premultiplication scratch and intermediate sizes before resampling, finite transforms and exact source/mask buffers; sources wider than u16 may shrink before backend limits, with a 2^20 source-axis cap and conservative 128 MiB filter-planning estimate; an over-limit or failed resize keeps the original image resolution and geometry when the source fits the backend, otherwise skips it, with a logged warning; staging, resampling output/scratch, RGBA conversion and padding buffers use fallible reserves; (9) `may_paint_canvas`: a fill or stroke whose control-point box, grown by how far its paint reaches past the path (half the stroke width times the larger of the miter limit and √2) plus 0.5 user units and 2 pixels, misses the canvas is not drawn, so a tile no longer strokes and fills every path of its page (item 5 of #623); `set_skip_offscreen_paths` turns this off for the regression test; (10) `/Interpolate` governs the pre-resize too (#624): a minified image that does not request interpolation is pre-resized with nearest-neighbour, planned without the Catmull-Rom filter limits (`image_resampling_size` takes the flag); a Type 3 glyph image is sampled bicubically only when interpolated; a minified image with a matching soft mask is nearest-sampled straight into premultiplied RGBA; (11) `may_paint_rect`: an image whose stream-size box, mapped to the device, misses the canvas is skipped before decoding (decoded data can only shrink against that box), so a tile of an image-heavy page no longer decodes, resamples and rasterizes every image on it; (12) preview renders (`InterpreterSettings::preview`: backdrops, thumbnails, grid cells, signature-drag backgrounds) skip images under `PREVIEW_MIN_IMAGE_AREA` device pixels, while final renders always draw them; (13) reading colours (#897): `RenderSettings::color_replacement` takes a `ColorReplacement` (text colour, background, `only_black`, `line_art`) that remaps solid text and line-art paint while rendering, glyph outlines counting as text and stencil-mask ink as line art; images, image alpha masks, soft masks and pattern cells keep their colours; `render_pdf` gains a `color_replacement: Option<ColorReplacement>` argument (pass `None` for true colours); the upstream-only `[dev-dependencies.log]` entry is removed from `Cargo.toml` (log is a normal dependency since the logging patch), so `cargo test -p hayro` runs this crate's unit tests; (14) a shrunk, interpolated, axis-aligned image is snapped to whole device pixels: shrunk once to its rounded device rectangle and drawn 1:1 at the rounded corner, instead of a ceil-sized raster resampled again at a fractional scale and offset (`snap_minified_image`; scans looked soft next to Acrobat); (15) a soft mask of another size than its image is filtered when shrunk, whatever its `/Interpolate` (#1649): such a mask carries the shape on its own (Word saves text as a tiny black image with a glyph-bitmap mask), and nearest-neighbour dropped every stroke thinner than the shrink factor; (16) under a soft mask or a blend mode, axial and radial shadings are sampled instead of drawn as native gradients (#2128): vello_cpu 0.0.8 copies an opaque gradient over fully covered tiles without the mask or blend mode, so PowerPoint's faded gradient fills came out solid; (17) the renderer keeps annotation paints out of the reading-colours mapping between `begin_annotations` and `end_annotations` (#1548); (18) the page renders as one transparency group; under reading colours its background is painted inside it as the initial backdrop, so a Multiply highlight blends with the dark background instead of staying an opaque block, and otherwise the background stays outside, so a blend mode over an empty part of thLine truncated
|
||||
| hayro-jbig2 | 0.3.0 | Apache-2.0 OR MIT | (1) at most 2^28 pixels per bitmap, page bitmap, halftone grid and grayscale image (each side could be 65535: 4.3 billion pixels decoded one by one); (2) at most 2^26 symbol pixels per symbol dictionary (a fuzzed dictionary decoded for minutes); (3) a symbol dictionary's height classes are capped at one per new symbol and its export runs at `2 × symbols + 1`, each plus `EXTRA_EMPTY_STEPS` (1024): an empty height class or a zero-length export run doesn't advance, and past the end of its data the arithmetic decoder can decode them for ever (one changed byte hung the renderer); (4) a segment header's long-form referred-to segment count is capped at `u16::MAX` and a larger count is refused before its retention or referred-to bytes are read: the 29-bit count went straight to `Vec::with_capacity`, a reservation of about 2 GiB whose failure aborts the process (from storytold/craft-libs#176) | (1) `raster::tests::jbig2_regions_of_billions_of_pixels_are_refused`; (2) the nightly `cargo xtask fuzz` finding, which now finishes in about a second; (3) `raster::tests::jbig2_symbol_dictionaries_that_never_advance_terminate`; (4) `segment::tests::test_referred_to_count_is_capped` (`cargo test --manifest-path vendor/hayro-jbig2/Cargo.toml`) |
|
||||
| lopdf | 0.45.0 | MIT | (1) PNG predictor rows longer than the data are refused before their buffers are allocated (a fuzzed `/Columns 4294967295` allocated two 4 GiB rows), and empty frames return without row buffers; (2) predictor row widths use saturating arithmetic or reject overflow; (3) sub-byte TIFF Predictor 2 scratch is bounded by the samples present in the input instead of the declared `/Colors`, aligned with [lopdf#589](https://github.com/J-F-Liu/lopdf/pull/589); (4) the object lookup keeps its cycle history through compressed objects, requires an ordinary in-file container, and caps the chain of indirect lookups at 16 (a chain of new objects, each a `/Length` compressed in a container whose own `/Length` names the next, or a stream whose `/Length` names the next stream, overflowed the stack: a dev build's 2 MiB thread within 800 hops); (5) object-stream members are parsed within their own extent (up to the next distinct offset), an entry whose offset repeats an earlier entry's is skipped (so a repeated object number can resolve to its earlier entry), and offsets are processed in index order; (6) `find_latest_trailer`: a rebuild takes a `/Type /XRef` stream dictionary as the trailer when the file has no `trailer` keyword (the latest in the file wins, as a later `trailer` would), so a concatenated or truncated file keeps its /Info and /ID instead of failing to load; a candidate whose /Root is the catalog beats one whose /Root is another dictionary, and an in-file /Root must match its generation (#2365) | (1) `inspect::tests::png_predictor_rows_longer_than_the_data_are_refused_before_allocating`, `inspect::tests::empty_png_predictor_frames_do_not_allocate_rows`; (2) `inspect::tests::tiff_subbyte_predictor_row_width_overflow_is_refused`; (3) `inspect::tests::tiff_subbyte_predictor_scratch_is_bounded_by_available_samples`, `inspect::tests::tiff_subbyte_predictors_keep_components_rows_and_padding`; (4) `inspect::tests::compressed_object_self_container_does_not_recurse`, `inspect::tests::compressed_object_mutual_containers_do_not_recurse`, `inspect::tests::object_stream_length_cycle_does_not_recurse`, `inspect::tests::compressed_object_container_chain_does_not_recurse`, `inspect::tests::compressed_length_chain_does_not_recurse`, `inspect::tests::plain_stream_length_chain_does_not_recurse`, `inspect::tests::compressed_objects_and_indirect_stream_length_still_load`, `inspect::tests::compressed_length_in_a_container_with_an_indirect_length_still_loads`; (5) `inspect::tests::object_stream_member_extents_bound_owned_strings`, `inspect::tests::object_stream_member_extents_preserve_index_order_and_whitespace`; (6) `inspect::tests::rebuilt_file_keeps_the_info_of_its_cross_reference_stream`, `inspect::tests::rebuilt_file_prefers_a_trailer_whose_root_is_the_catalog` |
|
||||
|
||||
+31
@@ -220,6 +220,9 @@ struct EmbeddedKind {
|
||||
cached_mappings: RefCell<HashMap<u8, GlyphId>>,
|
||||
/// PostScript name from the PDF.
|
||||
postscript_name: Option<String>,
|
||||
/// PdfCraft patch: (see vendor/README.md hayro-interpret (51)) each glyph's `post` table name,
|
||||
/// for the names that give a Unicode value.
|
||||
text_names: HashMap<GlyphId, String>,
|
||||
}
|
||||
|
||||
impl EmbeddedKind {
|
||||
@@ -236,6 +239,11 @@ impl EmbeddedKind {
|
||||
.and_then(|d| OpenTypeFontBlob::new(Arc::new(d.to_vec()), 0))?;
|
||||
|
||||
let glyph_names = base_font.glyph_names();
|
||||
let text_names = glyph_names
|
||||
.iter()
|
||||
.filter(|(name, _)| glyph_names::get(name).is_some() || unicode_from_name(name).is_some())
|
||||
.map(|(name, glyph)| (*glyph, name.clone()))
|
||||
.collect();
|
||||
|
||||
let cff_font_blob = base_font
|
||||
.font_ref()
|
||||
@@ -258,6 +266,7 @@ impl EmbeddedKind {
|
||||
encoding,
|
||||
cached_mappings: RefCell::new(HashMap::new()),
|
||||
postscript_name,
|
||||
text_names,
|
||||
})
|
||||
}
|
||||
|
||||
@@ -291,12 +300,34 @@ impl EmbeddedKind {
|
||||
// `Encoding::text_alias`.
|
||||
.or_else(|| self.encoding.text_alias(code))
|
||||
.or_else(|| self.encoding.map_code(code))
|
||||
.or_else(|| self.symbolic_glyph_name(code))
|
||||
// The last resort reads the code as WinAnsi whatever the font said, so it takes the
|
||||
// same aliasing.
|
||||
.or_else(|| Encoding::WinAnsi.text_alias(code))
|
||||
.or_else(|| win_ansi::get(code))
|
||||
}
|
||||
|
||||
/// PdfCraft patch (51): a symbolic font without an encoding selects its glyphs through its
|
||||
/// own `cmap`, so its codes need not mean anything in WinAnsi. FrameMaker files distilled
|
||||
/// with Distiller 3 number them in the Macintosh glyph order, 29 below ASCII, and read as
|
||||
/// WinAnsi `Solid` came out as `6ROLG` (#3962). The name the `post` table gives the glyph the
|
||||
/// code selects says what it is, as MuPDF reads it. `None` when the font is non-symbolic,
|
||||
/// has an encoding, selects no glyph for the code, or names it with no Unicode value: the
|
||||
/// code is then read as WinAnsi, as before.
|
||||
fn symbolic_glyph_name(&self, code: u8) -> Option<&str> {
|
||||
if self.is_non_symbolic()
|
||||
|| !matches!(self.encoding, Encoding::BuiltIn)
|
||||
|| self.cff_blob.is_some()
|
||||
{
|
||||
return None;
|
||||
}
|
||||
let glyph = self.map_code(code);
|
||||
if glyph == GlyphId::NOTDEF {
|
||||
return None;
|
||||
}
|
||||
self.text_names.get(&glyph).map(String::as_str)
|
||||
}
|
||||
|
||||
fn outline_glyph(&self, glyph: GlyphId) -> BezPath {
|
||||
self.base_font.outline_glyph(glyph)
|
||||
}
|
||||
|
||||
Reference in new issue
Block a user