mirror of
https://github.com/storytold/pdfcraft.git
synced 2026-11-10 13:01:29 +00:00
M3: a symbolic TrueType font in the Macintosh glyph order reads its codes as Mac OS Roman (hayro-interpret patch 101)
An embedded symbolic TrueType font with no /Encoding, no /ToUnicode and no glyph names (post 3.0) read its codes as WinAnsi in text extraction. A code now reads as Mac OS Roman when two things agree: the font's Macintosh Roman (1, 0) cmap subtable selects the glyph the code draws (ISO 32000-2 9.6.5.4), and that glyph sits where the standard Macintosh glyph order puts the code's Mac OS Roman character. pdf.js's issue2017r.pdf now extracts its accented line as PDFium does. Windows subsets in the same order whose codes are WinAnsi keep their reading, as do fonts that name their glyphs, fonts without a (1, 0) subtable and fonts whose (1, 0) subtable selects other glyphs. pdfcraft-fonts reads the same codes the same way for the editor. Glyph selection is unchanged. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Pq7HyCHD1R3rywQBPCHXZA
This commit is contained in:
mtlcl410andClaude Opus 5.5 committed
1 parent
784ce9212b
commit
210c2a65a4
6 files changed
+486
-1
No files matched your search
@@ -1269,6 +1269,9 @@ fn unicode_map(doc: &Document, font: &Dict, composite: bool) -> Unicode {
|
||||
out.encoding.insert(code as u32, c.to_string());
|
||||
}
|
||||
}
|
||||
if base_name.is_none() && !symbolic_builtin {
|
||||
out.encoding.extend(symbolic_mac_roman_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())
|
||||
{
|
||||
@@ -1329,6 +1332,74 @@ fn identity_to_unicode() -> Vec<u8> {
|
||||
cmap.into_bytes()
|
||||
}
|
||||
|
||||
/// What each code of an embedded TrueType font that isn't flagged non-symbolic, names no base
|
||||
/// encoding and doesn't name its glyphs shows when two things say the code is Mac OS Roman: its
|
||||
/// Macintosh Roman (1, 0) `cmap` subtable selects the glyph the code draws (ISO 32000-2 §9.6.5.4:
|
||||
/// single bytes "look up the associated glyph descriptions" there, and a (3, 0) subtable maps "the
|
||||
/// single-byte codes in the (1, 0) subtable" prepended with 0xF0), and the glyph sits where the
|
||||
/// standard Macintosh glyph order (the 258 names of a version 1.0 `post` table) puts that Mac OS
|
||||
/// Roman character. So code 0x88 drawn with glyph 106, `agrave`, is `à`, where Standard has
|
||||
/// nothing and WinAnsi `ˆ`, while a Windows subset in the same order whose codes are WinAnsi (0x92
|
||||
/// drawn with glyph 183, `quoteright`) keeps its reading. The glyph drawn is found the way the
|
||||
/// renderer finds it: the Windows (3, 0) and (3, 1) subtables first, with the code and the code at
|
||||
/// 0xF000, 0xF100 and 0xF200, then the Macintosh and Unicode-platform ones. The renderer's text
|
||||
/// layer reads the same codes the same way (vendored hayro-interpret patch (101)).
|
||||
fn symbolic_mac_roman_texts(doc: &Document, font: &Dict) -> Vec<(u32, String)> {
|
||||
use skrifa::GlyphId;
|
||||
use skrifa::raw::{TableProvider as _, tables::cmap::PlatformId, tables::post::DEFAULT_GLYPH_NAMES, types::Tag};
|
||||
let Some(descriptor) = dict(doc, font.get(b"FontDescriptor")) else { return Vec::new() };
|
||||
// Flag bit 6, Nonsymbolic (ISO 32000-2 Table 121).
|
||||
if descriptor_flags(doc, &descriptor) & 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(MAX_SFNT) else { return Vec::new() };
|
||||
let Ok(face) = skrifa::FontRef::from_index(&bytes, 0) else { return Vec::new() };
|
||||
// A CFF program in `/FontFile2` selects its glyphs by name, not through the `cmap`. A `post`
|
||||
// table of version 1.0 or 2.0 (also with its 16-bit halves swapped, as the renderer reads it)
|
||||
// names the glyphs, and a font that names them needn't keep the order: a Wingdings subset
|
||||
// draws code 0x83 with glyph 101, `Eacute` in the order, which it names `threesans`.
|
||||
let named = face
|
||||
.table_data(Tag::new(b"post"))
|
||||
.is_some_and(|data| matches!(data.as_bytes().get(..4), Some([0, 1, 0, 0] | [0, 2, 0, 0] | [0, 0, 0, 1] | [0, 0, 0, 2])));
|
||||
if face.cff().is_ok() || named {
|
||||
return Vec::new();
|
||||
}
|
||||
let Ok(cmap) = face.cmap() else { return Vec::new() };
|
||||
let records = cmap.encoding_records();
|
||||
let lookup = |code: u32, windows: bool| {
|
||||
records.iter().find_map(|record| {
|
||||
let offsets: &[u32] = match (record.platform_id(), record.encoding_id()) {
|
||||
(PlatformId::Windows, 0 | 1) if windows => &[0, 0xF000, 0xF100, 0xF200],
|
||||
(PlatformId::Macintosh | PlatformId::Unicode, 0) if !windows => &[0],
|
||||
_ => return None,
|
||||
};
|
||||
let subtable = record.subtable(cmap.offset_data()).ok()?;
|
||||
offsets.iter().find_map(|o| subtable.map_codepoint(code + o).filter(|g| *g != GlyphId::NOTDEF))
|
||||
})
|
||||
};
|
||||
(0..=255u32)
|
||||
.filter_map(|code| {
|
||||
let drawn = lookup(code, true).or_else(|| lookup(code, false))?;
|
||||
let mac = records.iter().find_map(|record| {
|
||||
(record.platform_id() == PlatformId::Macintosh && record.encoding_id() == 0)
|
||||
.then(|| record.subtable(cmap.offset_data()).ok()?.map_codepoint(code))
|
||||
.flatten()
|
||||
})?;
|
||||
if mac != drawn {
|
||||
return None;
|
||||
}
|
||||
let c = char::from_u32(*crate::encodings::MAC_ROMAN.get(usize::try_from(code).ok()?)?).filter(|c| *c != '\0')?;
|
||||
let standard = *DEFAULT_GLYPH_NAMES.get(usize::try_from(drawn.to_u32()).ok()?)?;
|
||||
// Mac OS Roman 0xCA reads as a space, for the reason WinAnsi 0xA0 does (`MAC_ROMAN`).
|
||||
let at_its_place = glyph_unicode(standard) == Some(c) || (code == 0xCA && standard == "nonbreakingspace");
|
||||
at_its_place.then(|| (code, c.to_string()))
|
||||
})
|
||||
.collect()
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests;
|
||||
|
||||
|
||||
@@ -795,3 +795,106 @@ fn low_codes_resolve_to_the_covering_range() {
|
||||
assert_eq!(covered, [5, 6, 7, 100, 101]);
|
||||
assert_eq!((u.covering(0xFFFF).is_some(), u.covering(0x1_0001).is_some(), u.covering(0x1_0002).is_none()), (true, true, true));
|
||||
}
|
||||
|
||||
/// [`cmap_only_sfnt_named`] without a `post` table.
|
||||
fn cmap_only_sfnt(mac: Option<&[(u8, u8)]>, windows: &[(u16, u16)]) -> Vec<u8> {
|
||||
cmap_only_sfnt_named(mac, windows, false)
|
||||
}
|
||||
|
||||
/// An sfnt holding a `cmap` table with these subtables: (1, 0) format 0 mapping codes to glyphs,
|
||||
/// and (3, 0) format 4 mapping each code point to its glyph, one segment each; and, if `named`, a
|
||||
/// version 2.0 `post` table.
|
||||
fn cmap_only_sfnt_named(mac: Option<&[(u8, u8)]>, windows: &[(u16, u16)], named: bool) -> Vec<u8> {
|
||||
let be16 = |out: &mut Vec<u8>, n: u16| out.extend_from_slice(&n.to_be_bytes());
|
||||
let mut subtables: Vec<((u16, u16), Vec<u8>)> = Vec::new();
|
||||
if let Some(map) = mac {
|
||||
let mut t = Vec::new();
|
||||
for n in [0u16, 262, 0] {
|
||||
be16(&mut t, n);
|
||||
}
|
||||
let mut ids = [0u8; 256];
|
||||
for &(code, glyph) in map {
|
||||
ids[usize::from(code)] = glyph;
|
||||
}
|
||||
t.extend(ids);
|
||||
subtables.push(((1, 0), t));
|
||||
}
|
||||
let segments: Vec<(u16, u16)> = windows.iter().copied().chain([(0xFFFF, 0)]).collect();
|
||||
let count = segments.len() as u16;
|
||||
let mut t = Vec::new();
|
||||
for n in [4u16, 16 + 8 * count, 0, 2 * count, 2, 0, 0] {
|
||||
be16(&mut t, n);
|
||||
}
|
||||
segments.iter().for_each(|&(c, _)| be16(&mut t, c));
|
||||
be16(&mut t, 0);
|
||||
segments.iter().for_each(|&(c, _)| be16(&mut t, c));
|
||||
segments.iter().for_each(|&(c, g)| be16(&mut t, if c == 0xFFFF { 1 } else { g.wrapping_sub(c) }));
|
||||
segments.iter().for_each(|_| be16(&mut t, 0));
|
||||
subtables.push(((3, 0), t));
|
||||
|
||||
let mut cmap = Vec::new();
|
||||
be16(&mut cmap, 0);
|
||||
be16(&mut cmap, subtables.len() as u16);
|
||||
let mut offset = 4 + 8 * subtables.len() as u32;
|
||||
for ((platform, encoding), bytes) in &subtables {
|
||||
be16(&mut cmap, *platform);
|
||||
be16(&mut cmap, *encoding);
|
||||
cmap.extend_from_slice(&offset.to_be_bytes());
|
||||
offset += bytes.len() as u32;
|
||||
}
|
||||
subtables.iter().for_each(|(_, bytes)| cmap.extend(bytes));
|
||||
let mut tables = vec![(*b"cmap", cmap)];
|
||||
if named {
|
||||
// Version 2.0 with no glyphs to name.
|
||||
let mut post = vec![0, 2, 0, 0];
|
||||
post.resize(34, 0);
|
||||
tables.push((*b"post", post));
|
||||
}
|
||||
let mut out = vec![0, 1, 0, 0];
|
||||
out.extend_from_slice(&(tables.len() as u16).to_be_bytes());
|
||||
out.extend([0; 6]);
|
||||
let mut offset = 12 + 16 * tables.len() as u32;
|
||||
for (tag, table) in &tables {
|
||||
out.extend(tag);
|
||||
out.extend_from_slice(&0u32.to_be_bytes());
|
||||
out.extend_from_slice(&offset.to_be_bytes());
|
||||
out.extend_from_slice(&(table.len() as u32).to_be_bytes());
|
||||
offset += table.len() as u32;
|
||||
}
|
||||
tables.into_iter().for_each(|(_, table)| out.extend(table));
|
||||
out
|
||||
}
|
||||
|
||||
/// A symbolic TrueType font with no `/Encoding` reads a code as Mac OS Roman when its (1, 0) `cmap`
|
||||
/// subtable selects the glyph the code draws and the glyph sits where the standard Macintosh glyph
|
||||
/// order puts that character, as the renderer's text layer reads it (vendored hayro-interpret
|
||||
/// patch (101), ISO 32000-2 §9.6.5.4). Otherwise the codes read as before (Standard): WinAnsi codes
|
||||
/// in that order (0x92 drawn with `quoteright`), no (1, 0) subtable, one selecting other glyphs
|
||||
/// than the (3, 0) one, a font flagged non-symbolic, or one that names its glyphs.
|
||||
#[test]
|
||||
fn a_symbolic_truetype_font_in_the_macintosh_order_reads_its_codes_as_mac_roman() {
|
||||
let read = |program: Vec<u8>, flags: i64, codes: [u32; 2]| {
|
||||
let mut doc = Document::new_empty();
|
||||
let program = doc.add(Object::Stream(Stream::flate(Dict::new(), &program)));
|
||||
let mut descriptor = Dict::new();
|
||||
descriptor.set(b"Flags".to_vec(), Object::Int(flags));
|
||||
descriptor.set(b"FontFile2".to_vec(), Object::Ref(program));
|
||||
let f = font(&mut doc, vec![("Subtype", Object::name("TrueType")), ("FontDescriptor", Object::Dict(descriptor))]);
|
||||
let u = unicode_map(&doc, &f, false);
|
||||
codes.map(|c| u.text(c).unwrap_or_default().into_owned())
|
||||
};
|
||||
// `agrave` and `eacute` are glyphs 106 and 112 of the standard Macintosh order, `endash` and
|
||||
// `quoteright` 178 and 183.
|
||||
let mac_order = cmap_only_sfnt(Some(&[(0x88, 106), (0x8E, 112)]), &[(0xF088, 106), (0xF08E, 112)]);
|
||||
assert_eq!(read(mac_order.clone(), 4, [0x88, 0x8E]), ["à", "é"]);
|
||||
assert_eq!(read(mac_order, 32, [0x88, 0x8E]), ["", ""], "flagged non-symbolic");
|
||||
let winansi = cmap_only_sfnt(Some(&[(0x92, 183), (0x96, 178)]), &[(0xF092, 183), (0xF096, 178)]);
|
||||
assert_eq!(read(winansi, 4, [0x92, 0x96]), ["", ""], "WinAnsi codes in the Macintosh order");
|
||||
let windows_only = cmap_only_sfnt(None, &[(0xF088, 106), (0xF08E, 112)]);
|
||||
assert_eq!(read(windows_only, 4, [0x88, 0x8E]), ["", ""], "no (1, 0) subtable");
|
||||
let disagreeing = cmap_only_sfnt(Some(&[(0x88, 112), (0x8E, 106)]), &[(0xF088, 106), (0xF08E, 112)]);
|
||||
assert_eq!(read(disagreeing, 4, [0x88, 0x8E]), ["", ""], "a (1, 0) subtable selecting other glyphs");
|
||||
// A `post` table of version 2.0 names the glyphs; what it calls them doesn't matter here.
|
||||
let named = cmap_only_sfnt_named(Some(&[(0x88, 106), (0x8E, 112)]), &[(0xF088, 106), (0xF08E, 112)], true);
|
||||
assert_eq!(read(named, 4, [0x88, 0x8E]), ["", ""], "a font that names its glyphs");
|
||||
}
|
||||
@@ -8199,6 +8199,10 @@ mod icc_profile_cache;
|
||||
// A symbolic TrueType font draws through its (3, 0) cmap subtable first (#4156).
|
||||
mod symbolic_truetype_cmap;
|
||||
|
||||
// A symbolic TrueType font in the standard Macintosh glyph order reads its codes as Mac OS Roman
|
||||
// (vendored hayro-interpret patch 101).
|
||||
mod symbolic_truetype_mac_roman_text;
|
||||
|
||||
/// Render `pdf`'s first page at 72 dpi with no time limit beyond the test's own.
|
||||
fn render_first_page(pdf: Vec<u8>) -> RenderedPage {
|
||||
let mut r = PageRenderer::new(Arc::new(pdf), RenderConfig::default());
|
||||
|
||||
@@ -0,0 +1,246 @@
|
||||
//! A symbolic TrueType font with no `/Encoding`, no `/ToUnicode` and no glyph names reads a code
|
||||
//! as Mac OS Roman when its (1, 0) `cmap` subtable selects the glyph the code draws and that glyph
|
||||
//! sits where the standard Macintosh glyph order puts the code's Mac OS Roman character (vendored
|
||||
//! hayro-interpret patch 101; ISO 32000-2 §9.6.5.4: single bytes "look up the associated glyph
|
||||
//! descriptions" in the (1, 0) subtable, and a (3, 0) subtable maps "the single-byte codes in the
|
||||
//! (1, 0) subtable" prepended with 0xF0). pdf.js's issue2017r.pdf has such a font; its text read as
|
||||
//! WinAnsi, `ˆ` for `à`.
|
||||
//!
|
||||
//! The fonts are built here, in memory: [`GLYPHS`] glyphs, those the tests show filled squares, no
|
||||
//! `post` table, and the `cmap` subtables each test asks for. No font file is involved.
|
||||
|
||||
use super::*;
|
||||
|
||||
/// Glyphs in each font: past the standard Macintosh order's `quoteright` (183).
|
||||
const GLYPHS: u16 = 200;
|
||||
|
||||
/// The standard Macintosh order's glyphs for `agrave`, `eacute`, `endash` and `quoteright`.
|
||||
const AGRAVE: u8 = 106;
|
||||
const EACUTE: u8 = 112;
|
||||
const ENDASH: u8 = 178;
|
||||
const QUOTERIGHT: u8 = 183;
|
||||
|
||||
fn be16(out: &mut Vec<u8>, n: u16) {
|
||||
out.extend_from_slice(&n.to_be_bytes());
|
||||
}
|
||||
|
||||
fn be32(out: &mut Vec<u8>, n: u32) {
|
||||
out.extend_from_slice(&n.to_be_bytes());
|
||||
}
|
||||
|
||||
/// A (1, 0) format 0 subtable mapping each code to its glyph.
|
||||
fn mac_subtable(map: &[(u8, u8)]) -> Vec<u8> {
|
||||
let mut out = Vec::new();
|
||||
for n in [0u16, 262, 0] {
|
||||
be16(&mut out, n); // format, length, language
|
||||
}
|
||||
let mut ids = [0u8; 256];
|
||||
for &(code, glyph) in map {
|
||||
ids[usize::from(code)] = glyph;
|
||||
}
|
||||
out.extend(ids);
|
||||
out
|
||||
}
|
||||
|
||||
/// A (3, 0) format 4 subtable mapping each code at 0xF000 to its glyph, one segment each.
|
||||
fn windows_subtable(map: &[(u8, u8)]) -> Vec<u8> {
|
||||
let segments: Vec<(u16, u16)> = map.iter().map(|&(code, glyph)| (0xF000 | u16::from(code), u16::from(glyph))).chain([(0xFFFF, 0)]).collect();
|
||||
let count = segments.len() as u16;
|
||||
let mut out = Vec::new();
|
||||
for n in [4u16, 16 + 8 * count, 0, 2 * count, 2, 0, 0] {
|
||||
be16(&mut out, n); // format, length, language, segCountX2, searchRange, entrySelector, rangeShift
|
||||
}
|
||||
for &(code, _) in &segments {
|
||||
be16(&mut out, code); // endCode
|
||||
}
|
||||
be16(&mut out, 0); // reservedPad
|
||||
for &(code, _) in &segments {
|
||||
be16(&mut out, code); // startCode
|
||||
}
|
||||
for &(code, glyph) in &segments {
|
||||
be16(&mut out, if code == 0xFFFF { 1 } else { glyph.wrapping_sub(code) }); // idDelta
|
||||
}
|
||||
for _ in &segments {
|
||||
be16(&mut out, 0); // idRangeOffset
|
||||
}
|
||||
out
|
||||
}
|
||||
|
||||
/// A TrueType font of [`GLYPHS`] glyphs, the `inked` ones squares, whose (3, 0) subtable maps
|
||||
/// `windows` and whose (1, 0) subtable, if any, maps `mac`. A `named` font has a version 2.0 `post`
|
||||
/// table naming its `inked` glyphs `bullet0`, `bullet1` and so on.
|
||||
fn font(inked: &[u8], mac: Option<&[(u8, u8)]>, windows: &[(u8, u8)], named: bool) -> Vec<u8> {
|
||||
// One contour, the square 0..1000 on both axes.
|
||||
let mut square = Vec::new();
|
||||
for n in [1u16, 0, 0, 1000, 1000] {
|
||||
be16(&mut square, n);
|
||||
}
|
||||
be16(&mut square, 3); // the contour's last point
|
||||
be16(&mut square, 0); // no instructions
|
||||
square.extend([1u8; 4]); // four on-curve points, two-byte coordinates
|
||||
for dx in [0i16, 1000, 0, -1000] {
|
||||
square.extend_from_slice(&dx.to_be_bytes());
|
||||
}
|
||||
for dy in [0i16, 0, 1000, 0] {
|
||||
square.extend_from_slice(&dy.to_be_bytes());
|
||||
}
|
||||
let mut glyf = Vec::new();
|
||||
let mut loca = Vec::new();
|
||||
for glyph in 0..GLYPHS {
|
||||
be16(&mut loca, (glyf.len() / 2) as u16);
|
||||
if inked.iter().any(|g| u16::from(*g) == glyph) {
|
||||
glyf.extend_from_slice(&square);
|
||||
}
|
||||
}
|
||||
be16(&mut loca, (glyf.len() / 2) as u16);
|
||||
|
||||
let mut head = vec![0; 54];
|
||||
head[0..4].copy_from_slice(&[0, 1, 0, 0]);
|
||||
head[12..16].copy_from_slice(&0x5f0f_3cf5u32.to_be_bytes());
|
||||
head[18..20].copy_from_slice(&1000u16.to_be_bytes());
|
||||
head[40..42].copy_from_slice(&1000i16.to_be_bytes());
|
||||
head[42..44].copy_from_slice(&1000i16.to_be_bytes());
|
||||
let mut hhea = vec![0; 36];
|
||||
hhea[0..4].copy_from_slice(&[0, 1, 0, 0]);
|
||||
hhea[4..6].copy_from_slice(&1000i16.to_be_bytes());
|
||||
hhea[34..36].copy_from_slice(&GLYPHS.to_be_bytes());
|
||||
let mut hmtx = Vec::new();
|
||||
for _ in 0..GLYPHS {
|
||||
be16(&mut hmtx, 1000);
|
||||
be16(&mut hmtx, 0);
|
||||
}
|
||||
let mut maxp = vec![0, 1, 0, 0];
|
||||
be16(&mut maxp, GLYPHS);
|
||||
maxp.resize(32, 0);
|
||||
|
||||
let subtables: Vec<((u16, u16), Vec<u8>)> =
|
||||
mac.map(|m| ((1, 0), mac_subtable(m))).into_iter().chain([((3, 0), windows_subtable(windows))]).collect();
|
||||
let mut cmap = Vec::new();
|
||||
be16(&mut cmap, 0);
|
||||
be16(&mut cmap, subtables.len() as u16);
|
||||
let mut offset = 4 + 8 * subtables.len() as u32;
|
||||
for ((platform, encoding), bytes) in &subtables {
|
||||
be16(&mut cmap, *platform);
|
||||
be16(&mut cmap, *encoding);
|
||||
be32(&mut cmap, offset);
|
||||
offset += bytes.len() as u32;
|
||||
}
|
||||
for (_, bytes) in &subtables {
|
||||
cmap.extend(bytes);
|
||||
}
|
||||
|
||||
let mut tables =
|
||||
vec![(*b"cmap", cmap), (*b"glyf", glyf), (*b"head", head), (*b"hhea", hhea), (*b"hmtx", hmtx), (*b"loca", loca), (*b"maxp", maxp)];
|
||||
if named {
|
||||
let mut post = vec![0, 2, 0, 0];
|
||||
post.resize(32, 0);
|
||||
be16(&mut post, GLYPHS);
|
||||
for glyph in 0..GLYPHS {
|
||||
// Index 258 and on are the table's own names, in order.
|
||||
let own = inked.iter().position(|g| u16::from(*g) == glyph);
|
||||
be16(&mut post, own.map_or(0, |i| 258 + i as u16));
|
||||
}
|
||||
for i in 0..inked.len() {
|
||||
let name = format!("bullet{i}");
|
||||
post.push(name.len() as u8);
|
||||
post.extend(name.bytes());
|
||||
}
|
||||
tables.push((*b"post", post));
|
||||
}
|
||||
let mut out = vec![0, 1, 0, 0];
|
||||
be16(&mut out, tables.len() as u16);
|
||||
for n in [64u16, 2, 48] {
|
||||
be16(&mut out, n);
|
||||
}
|
||||
let mut payload = Vec::new();
|
||||
let mut offset = 12 + 16 * tables.len();
|
||||
for (tag, bytes) in tables {
|
||||
out.extend(tag);
|
||||
let mut padded = bytes.clone();
|
||||
padded.resize(bytes.len().div_ceil(4) * 4, 0);
|
||||
let sum = padded.as_chunks::<4>().0.iter().fold(0u32, |s, b| s.wrapping_add(u32::from_be_bytes(*b)));
|
||||
be32(&mut out, sum);
|
||||
be32(&mut out, offset as u32);
|
||||
be32(&mut out, bytes.len() as u32);
|
||||
offset += padded.len();
|
||||
payload.extend(padded);
|
||||
}
|
||||
out.extend(payload);
|
||||
out
|
||||
}
|
||||
|
||||
/// The text extracted from a page that shows `codes` in `font`, marked symbolic and with no
|
||||
/// `/Encoding` and no `/ToUnicode`.
|
||||
fn extracted(font: &[u8], codes: &[u8]) -> String {
|
||||
let hex: String = codes.iter().map(|c| format!("{c:02X}")).collect();
|
||||
let content = format!("BT /F1 30 Tf 5 5 Td <{hex}> Tj ET").into_bytes();
|
||||
let widths = vec!["1000"; 256].join(" ");
|
||||
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 80 40] /Resources << /Font << /F1 5 0 R >> >> /Contents 4 0 R >>".to_vec(),
|
||||
[format!("<< /Length {} >>\nstream\n", content.len()).into_bytes(), content.clone(), b"\nendstream".to_vec()].concat(),
|
||||
format!("<< /Type /Font /Subtype /TrueType /BaseFont /AAAAAA+Sym /FirstChar 0 /LastChar 255 /Widths [{widths}] /FontDescriptor 6 0 R >>").into_bytes(),
|
||||
b"<< /Type /FontDescriptor /FontName /AAAAAA+Sym /Flags 4 /FontBBox [0 0 1000 1000] /ItalicAngle 0 /Ascent 1000 /Descent 0 /CapHeight 1000 /StemV 80 /FontFile2 7 0 R >>".to_vec(),
|
||||
[format!("<< /Length {} >>\nstream\n", font.len()).into_bytes(), font.to_vec(), b"\nendstream".to_vec()].concat(),
|
||||
];
|
||||
let mut pdf = b"%PDF-1.7\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\n<< /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 out = r.render(RenderRequest { page: 0, kind: RequestKind::Text, tile: None, scale: 1.0, tag: 0, ..Default::default() });
|
||||
assert!(out.error.is_none(), "{:?}", out.error);
|
||||
out.text.map(|t| t.plain_text()).unwrap_or_default()
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn a_symbolic_truetype_font_in_the_macintosh_order_reads_its_codes_as_mac_roman() {
|
||||
// As issue2017r.pdf's font: code c and 0xF000 + c select the glyph the standard Macintosh
|
||||
// order gives Mac OS Roman c.
|
||||
let map = [(0x88, AGRAVE), (0x8E, EACUTE)];
|
||||
let font = font(&[AGRAVE, EACUTE], Some(&map), &map, false);
|
||||
assert_eq!(extracted(&font, &[0x88, 0x8E]), "àé", "Mac OS Roman 0x88 is à and 0x8E é");
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn winansi_codes_of_a_font_in_the_macintosh_order_read_as_before() {
|
||||
// A Windows subset in the same order: code 0x92 draws `quoteright`, WinAnsi 0x92, where Mac OS
|
||||
// Roman 0x92 is `iacute`.
|
||||
let map = [(0x92, QUOTERIGHT), (0x96, ENDASH)];
|
||||
let font = font(&[ENDASH, QUOTERIGHT], Some(&map), &map, false);
|
||||
assert_eq!(extracted(&font, &[0x92, 0x96]), "\u{2019}\u{2013}", "WinAnsi, not Mac OS Roman's íñ");
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn a_symbolic_truetype_font_without_a_1_0_subtable_reads_as_before() {
|
||||
let font = font(&[AGRAVE, EACUTE], None, &[(0x88, AGRAVE), (0x8E, EACUTE)], false);
|
||||
assert_eq!(extracted(&font, &[0x88, 0x8E]), "ˆŽ", "with no (1, 0) subtable the codes read as WinAnsi");
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn a_1_0_subtable_selecting_other_glyphs_than_the_drawn_ones_is_not_read() {
|
||||
// The (3, 0) subtable is used first (#4156); a (1, 0) one that disagrees doesn't say what the
|
||||
// drawn glyphs are.
|
||||
let font = font(&[AGRAVE, EACUTE], Some(&[(0x88, EACUTE), (0x8E, AGRAVE)]), &[(0x88, AGRAVE), (0x8E, EACUTE)], false);
|
||||
assert_eq!(extracted(&font, &[0x88, 0x8E]), "ˆŽ", "the codes read as WinAnsi, as before");
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn a_font_that_names_its_glyphs_is_not_read_by_their_order() {
|
||||
// A Wingdings subset draws code 0x83 with glyph 101, `Eacute` in the order, and names it
|
||||
// `threesans`: a font with glyph names needn't keep the order.
|
||||
let map = [(0x88, AGRAVE), (0x8E, EACUTE)];
|
||||
let font = font(&[AGRAVE, EACUTE], Some(&map), &map, true);
|
||||
assert_eq!(extracted(&font, &[0x88, 0x8E]), "ˆŽ", "the codes read as WinAnsi, as before");
|
||||
}
|
||||
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 (since (21), only inside Type 3 glyphs), 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 image that is interpolated (or, since (21), area-averaged) and whose axes lie along the device's (upright, mirrored or a quarter turn, as on a page under `/Rotate`) is snapped to whole device pixels: shrunk once to its rounded device rectangle (halves round up, so a tile snaps an edge where the whole page does) and drawn 1:1 from 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, and until #5530 a turned one still did, up to 200 grey levels off the same page drawn upright). An image counts as axis-aligned when the terms the snap drops move its far edges by at most a hundredth of a device pixel (`SNAP_SKEW`), not by a tolerance on the coefficients, which let a slight skew of a very wide image through; and the snapped 1:1 transform is used only when the shrink produced the snapped size, so a failed resize keeps the full transform instead of drawing the source raster at its source size; (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 stroLine truncated
|
||||
| hayro-jbig2 | 0.3.0 | Apache-2.0 OR MIT | (1) at most 2^28 pixels per bitmap and page bitmap, and 2^25 cells per halftone grid and grayscale image (each side could be 65535: 4.3 billion pixels decoded one by one, and a 4-byte value per cell); (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); (5) what a page's segments hold for later ones (intermediate regions, pattern and symbol dictionaries with their headers and retained contexts, and Huffman tables) is at most 64 MiB, two square bitmaps of 16,384 a side (`MAX_RETAINED_WORDS`), and a dictionary's new and exported symbols are counted against it as they are made: each was bounded on its own, but a few dozen bytes an intermediate region held 33 MB each, and 8 MiB symbols exported again and again killed the process, so a few kilobytes could exhaust memory; (6) a segment may refer to at most 2^20 symbols, checked before any are collected: references may repeat, and 65,535 of them to one dictionary, in a 78 KB stream, asked for 17 GB; (7) a pattern dictionary keeps at most 16 MiB of shifted copies, which only speed up drawing, and none that wouldn't fit what the page has left (`MAX_SHIFTED_WORDS`); (8) a custom Huffman table has at most 2^16 lines, and a stream with its globals at most 2^20 segments and 2^22 references, checked as they are read: both grew before anything counted them, and PDFs of a kilobyte or so reached 5 GB and more behind nested Flate; (9) a page past the bounds of (1) is refused when the stream is opened: a caller sizes its output from the header before the page bitmap is made, and an Indexed image in a 743-byte PDF asked for 137 GB, which aborts; (10) a stream may ask for at most 2^30 units of decoding work, four of the largest pages, about 6 s to 17 s (`MAX_WORK`): decoding a bitmap costs a pixel each and 4 a row, copying one a word each and 1 a row, and each integer an item reads costs 38, what one takes at worst, so one with no pixels pays too, before it is decoded: each bitmap was bounded, but nothing bounded how many there were, and a 795-byte PDF took 265 s; (11) `Image::decode_within` spends from what a run of images may still do, starting with its page's pixels, and `charge_reading` charges reading a stream and its globals before anything is parsed, so an operation over a document can bound what `MAX_WORK` bounds for one image, and images that fail or decode nothing add up too: a file of thousands of images made to reach that limit took as many times as long; (12) adding to a location, a reference offset, a symbol's corner or a Huffman range line near the end of an `i32`, and negating a decoded integer of 2^31, overflowed: a panic wherever overflow is checked. The refinement context, a text region's corners, the integer decoder and the Huffman table wrap, as a release build did, and `Bitmap::combine` saturates, which comes to the same, as a location that overflows is past the end of any page. What is drawn doesn't change; (13) a bitmap filled with a default pixel of 1 (a page, or an intermediate text or halftone region) had 1s past its width in the last word of each row, and a refinement, which reads its reference a word at a time, read them as pixels where the standard has 0 (6.3.5.2): refining such a reference not a multiple of 32 wide decoded to other pixels than were coded, release builds too. `Bitmap::clear_padding` clears those bits when a bitmap is filled with 1s, as cutting symbols and patterns from a collective bitmap already did. Ghostscript reads the test's page and text streams as they decode now; (14) a region's location is unsigned (5.4.4), so one past `i32::MAX` is off the page, where the decoder took it for a signed one: a region there was drawn back onto the page from the left or the top (at 0xFFFFFFFC, four pixels left of it), and a refinement there, of the page or of a region at the same place (7.4.7.5), was refused as an overflow, and the page with it. `Bitmap::combine_region` keeps such a location past the page. A refinement of another region refines it where it is, as Table 35 has it (GRREFERENCEDX and GRREFERENCEDY 0), whatever the two locations say; a refinement of the page, see (16); (15) a refinement whose reference is offset right of it (GRREFERENCEDX above 0, which a refined text instance has from a wider bitmap, TaLine truncated
|
||||
| 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` |
|
||||
|
||||
+61
@@ -18,6 +18,7 @@ use kurbo::BezPath;
|
||||
use skrifa::attribute::Style;
|
||||
use skrifa::raw::TableProvider;
|
||||
use skrifa::raw::tables::cmap::PlatformId;
|
||||
use skrifa::raw::tables::post::DEFAULT_GLYPH_NAMES;
|
||||
use skrifa::{GlyphId, MetadataProvider};
|
||||
use std::cell::RefCell;
|
||||
use std::collections::HashMap;
|
||||
@@ -291,6 +292,8 @@ impl EmbeddedKind {
|
||||
// `Encoding::text_alias`.
|
||||
.or_else(|| self.encoding.text_alias(code))
|
||||
.or_else(|| self.encoding.map_code(code))
|
||||
// PdfCraft patch (101): see `EmbeddedKind::mac_roman_name`.
|
||||
.or_else(|| self.mac_roman_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))
|
||||
@@ -400,6 +403,64 @@ impl EmbeddedKind {
|
||||
glyph
|
||||
}
|
||||
|
||||
/// PdfCraft patch (101): the Mac OS Roman glyph name a code of a symbolic font without an
|
||||
/// encoding or glyph names reads as, when two things say the code is Mac OS Roman:
|
||||
///
|
||||
/// - its Macintosh Roman (1, 0) `cmap` subtable selects the glyph the code draws. ISO
|
||||
/// 32000-2 §9.6.5.4 has single bytes "look up the associated glyph descriptions" there, and
|
||||
/// has a (3, 0) subtable map "the single-byte codes in the (1, 0) subtable" prepended with
|
||||
/// 0xF0;
|
||||
/// - the glyph sits where the standard Macintosh glyph order (the 258 names of a version 1.0
|
||||
/// `post` table) puts that character. Fonts distilled from Macintosh originals keep that
|
||||
/// order and drop the names (`post` version 3.0): pdf.js's issue2017r.pdf draws code 0x88
|
||||
/// with glyph 106, `agrave`, Mac OS Roman 0x88.
|
||||
///
|
||||
/// The second test is needed: Windows subsets in the same order carry a (1, 0) subtable too,
|
||||
/// but their codes are WinAnsi (code 0x92 draws glyph 183, `quoteright`, not Mac OS Roman's
|
||||
/// `iacute`), and reading every such code as Mac OS Roman turned "USDA’s" into "USDAís".
|
||||
/// A font that names its glyphs in its `post` table needn't keep the order (a Wingdings subset
|
||||
/// draws code 0x83 with glyph 101, `Eacute` in the order, which it names `threesans`).
|
||||
/// `None` when the font is non-symbolic, names an encoding, is a CFF program, names its glyphs,
|
||||
/// or either test fails (SAS's AMT fonts carry a wrong (1, 0) table, #4156): the code then
|
||||
/// reads as before. Glyph selection is unchanged.
|
||||
fn mac_roman_name(&self, code: u8) -> Option<&'static str> {
|
||||
if self.is_non_symbolic()
|
||||
|| !matches!(self.encoding, Encoding::BuiltIn)
|
||||
|| self.cff_blob.is_some()
|
||||
|| !self.glyph_names.is_empty()
|
||||
{
|
||||
return None;
|
||||
}
|
||||
let glyph = self.map_code(code);
|
||||
if glyph == GlyphId::NOTDEF {
|
||||
return None;
|
||||
}
|
||||
let cmap = self.base_font.font_ref().cmap().ok()?;
|
||||
let mac = cmap.encoding_records().iter().find_map(|record| {
|
||||
if record.platform_id() == PlatformId::Macintosh && record.encoding_id() == 0 {
|
||||
record
|
||||
.subtable(cmap.offset_data())
|
||||
.ok()?
|
||||
.map_codepoint(code)
|
||||
} else {
|
||||
None
|
||||
}
|
||||
})?;
|
||||
if mac != glyph {
|
||||
return None;
|
||||
}
|
||||
let standard = match *DEFAULT_GLYPH_NAMES.get(usize::try_from(glyph.to_u32()).ok()?)? {
|
||||
// The order's name for Mac OS Roman 0xCA; the tables here call it `nbspace`.
|
||||
"nonbreakingspace" => "nbspace",
|
||||
name => name,
|
||||
};
|
||||
let name = mac_os_roman::get(code).or_else(|| mac_roman::get(code))?;
|
||||
if name != standard {
|
||||
return None;
|
||||
}
|
||||
Encoding::MacRoman.text_alias(code).or(Some(name))
|
||||
}
|
||||
|
||||
fn glyph_width(&self, code: u8) -> f32 {
|
||||
match self.widths.get(code as usize).copied() {
|
||||
Some(Width::Value(w)) => w,
|
||||
|
||||
Reference in new issue
Block a user