mirror of
https://github.com/storytold/pdfcraft.git
synced 2026-10-31 07:39:08 +00:00
M2: a DeviceN colour with twelve inks paints, and a colour that can't be evaluated no longer blanks the page (#4260)
ISO 32000-2 §8.6.6.5: "DeviceN colour spaces (PDF 1.3) may contain an arbitrary number of colour components", and scn takes one operand per component. The content parser (vendored hayro-syntax) held ten operands per instruction; pushing the eleventh failed, and the failure ended the whole content stream. A twelve-ink background fill therefore drew nothing, and nothing after it was drawn either: a blank page, no error. hayro-syntax patch (26): an instruction keeps up to 256 operands (enough for the largest DeviceN space the interpreter reads, 255 inks, plus a pattern name). Past that the oldest are dropped, in order, rather than the stream ending: operators already read the operands nearest to them, so this is how stray operands are treated below the cap too. hayro-interpret patch (55): a Separation or DeviceN tint transform that can't be read no longer makes the colour space unreadable (its paints were drawn in DeviceGray from the first tint, white for a full tint); it keeps the space, and like a transform that fails when evaluated it paints that colour in the alternate space's initial colour. Those fallbacks, and a cs/CS colour space that can't be read, were silent: they are reported once per content stream as InterpreterWarning::ColorFallback, which pdfcraft-render records as RenderWarning::ColourFallback and pdfcraft-cli render prints. Tests, each seen failing with its fix reverted: the report's twelve-ink page paints black and draws what follows; a four-ink control; 300 stray operands before rg still draw; a calculator tint transform that pops too much, and an unknown function type, fall back with one warning and the rest of the page drawn; hayro-syntax keeps all twelve scn operands and, past the cap, the latest 256 in order (fails without the reorder). Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_0175FWj4xFhMhSH3UpMU8DSC
This commit is contained in:
mtlcl410andClaude Opus 5.5 committed
1 parent
a047c6ba09
commit
0142a96ca3
9 files changed
+322
-37
No files matched your search
@@ -688,6 +688,10 @@ fn render(args: &[String]) -> Result<(), CliError> {
|
||||
pdfcraft_render::RenderWarning::ContentTruncated => {
|
||||
let _ = writeln!(std::io::stderr().lock(), "warning: page {page}: content past the page's safety budget was skipped");
|
||||
}
|
||||
pdfcraft_render::RenderWarning::ColourFallback => {
|
||||
let _ =
|
||||
writeln!(std::io::stderr().lock(), "warning: page {page}: a colour that could not be computed was painted in a fallback colour");
|
||||
}
|
||||
}
|
||||
}
|
||||
Ok(())
|
||||
|
||||
@@ -220,6 +220,9 @@ pub struct RenderedPage {
|
||||
pub enum RenderWarning {
|
||||
/// Content was skipped after the per-page decoded-content budget was exhausted.
|
||||
ContentTruncated,
|
||||
/// A colour could not be computed (a colour space that cannot be read, or a Separation or
|
||||
/// DeviceN tint transform that cannot be evaluated) and was painted in a fallback colour.
|
||||
ColourFallback,
|
||||
}
|
||||
|
||||
/// Counters for work performed by a renderer or render pool.
|
||||
@@ -402,12 +405,15 @@ fn warning_settings(settings: &InterpreterSettings, warnings: Arc<Mutex<Vec<Rend
|
||||
InterpreterSettings {
|
||||
warning_sink: Arc::new(move |warning| {
|
||||
// Nested forms, Type 3 glyphs and patterns are interpreted again and each reports the
|
||||
// exhausted budget: once per page is enough.
|
||||
if matches!(warning, InterpreterWarning::ContentTruncated) {
|
||||
let mut warnings = lock(&target);
|
||||
if !warnings.contains(&RenderWarning::ContentTruncated) {
|
||||
warnings.push(RenderWarning::ContentTruncated);
|
||||
}
|
||||
// exhausted budget, or the colours that fell back: once per page is enough.
|
||||
let warning = match warning {
|
||||
InterpreterWarning::ContentTruncated => RenderWarning::ContentTruncated,
|
||||
InterpreterWarning::ColorFallback => RenderWarning::ColourFallback,
|
||||
InterpreterWarning::UnsupportedFont | InterpreterWarning::ImageDecodeFailure => return,
|
||||
};
|
||||
let mut warnings = lock(&target);
|
||||
if !warnings.contains(&warning) {
|
||||
warnings.push(warning);
|
||||
}
|
||||
}),
|
||||
..settings.clone()
|
||||
@@ -8163,6 +8169,10 @@ trailer << /Root 1 0 R >>
|
||||
// #1201: /DefaultGray, /DefaultRGB and /DefaultCMYK (vendored hayro-interpret patch 38).
|
||||
mod default_colour_spaces;
|
||||
|
||||
// #4260: DeviceN colours with many inks, and tint transforms that cannot be evaluated
|
||||
// (vendored hayro-syntax patch 26, hayro-interpret patch 55).
|
||||
mod devicen_inks;
|
||||
|
||||
/// #3109 / #3116: clipping-only text (`7 Tr`) installs a clip for subsequent painting
|
||||
/// but draws no pixels itself.
|
||||
#[test]
|
||||
|
||||
@@ -0,0 +1,123 @@
|
||||
//! #4260: a DeviceN colour with more inks than the content parser held operands for, and a
|
||||
//! colour whose tint transform cannot be evaluated (ISO 32000-2 §8.6.6.5).
|
||||
//!
|
||||
//! The content parser kept at most ten operands per operator (vendored hayro-syntax patch 26):
|
||||
//! the eleventh operand of a twelve-ink `scn` ended the whole content stream, so the page came
|
||||
//! out blank with no error. A tint transform that cannot be evaluated painted the alternate
|
||||
//! space's initial colour without a word (vendored hayro-interpret patch 55): it now says so.
|
||||
|
||||
use super::{RenderWarning, rgb_at};
|
||||
use crate::{PageRenderer, RenderConfig, RenderRequest, RenderedPage, RequestKind};
|
||||
use std::sync::Arc;
|
||||
|
||||
/// The page is 200 × 200 pt, drawn at 72 dpi.
|
||||
const SIDE: usize = 200;
|
||||
|
||||
const GREEN: [u8; 3] = [0, 255, 0];
|
||||
const RED: [u8; 3] = [255, 0, 0];
|
||||
const BLUE: [u8; 3] = [0, 0, 255];
|
||||
const BLACK: [u8; 3] = [0, 0, 0];
|
||||
|
||||
/// The twelve inks of the report's print dieline.
|
||||
const TWELVE_INKS: &str =
|
||||
"[/Cyan /Magenta /Yellow /Black /PANTONE156C /PANTONE2227C /PANTONE1565C /PANTONE2975C /PANTONE7463C /Varnish /Dieline /SGKBlack]";
|
||||
|
||||
/// The report's tint transform: all inks at 1.0 give CMYK 1 1 1 1.
|
||||
const TINT: &str = "<< /FunctionType 2 /Domain [0 1] /N 1 /C0 [0 0 0 0] /C1 [1 1 1 1] >>";
|
||||
|
||||
/// Render the one page `content` draws with the colour space `CS1` defined as `cs1`.
|
||||
fn render(content: &str, cs1: &str) -> RenderedPage {
|
||||
render_with(content, cs1, "")
|
||||
}
|
||||
|
||||
/// [`render`], with `objects` (whole indirect objects from 5 0 obj on) added to the file.
|
||||
fn render_with(content: &str, cs1: &str, objects: &str) -> RenderedPage {
|
||||
let pdf = format!(
|
||||
"%PDF-1.7\n1 0 obj << /Type /Catalog /Pages 2 0 R >> endobj\n\
|
||||
2 0 obj << /Type /Pages /Kids [3 0 R] /Count 1 >> endobj\n\
|
||||
3 0 obj << /Type /Page /Parent 2 0 R /MediaBox [0 0 200 200] /Resources << /ColorSpace << /CS1 {cs1} >> >> /Contents 4 0 R >> endobj\n\
|
||||
4 0 obj << /Length {} >> stream\n{content}\nendstream endobj\n\
|
||||
{objects}trailer << /Root 1 0 R >>\n%%EOF",
|
||||
content.len()
|
||||
);
|
||||
let mut renderer = PageRenderer::new(Arc::new(pdf.into_bytes()), RenderConfig::default());
|
||||
let page = renderer.render(RenderRequest { page: 0, kind: RequestKind::Pixels, tile: None, scale: 1.0, tag: 0, preview: false });
|
||||
assert!(page.error.is_none(), "{:?}", page.error);
|
||||
assert_eq!((page.width, page.height), (SIDE as u32, SIDE as u32));
|
||||
page
|
||||
}
|
||||
|
||||
/// The colour at (`x`, `y`) in page points from the bottom left.
|
||||
fn at(page: &RenderedPage, x: usize, y: usize) -> [u8; 3] {
|
||||
rgb_at(&page.rgba, SIDE, x, SIDE - 1 - y)
|
||||
}
|
||||
|
||||
/// CMYK 1 1 1 1 through the renderer's CMYK profile: very dark, whatever the exact profile.
|
||||
fn is_rich_black(rgb: [u8; 3]) -> bool {
|
||||
rgb.iter().all(|c| *c < 48)
|
||||
}
|
||||
|
||||
/// The report's page: twelve inks, all at 1.0, fill the page black. A green square drawn
|
||||
/// afterwards shows the rest of the content is still read.
|
||||
#[test]
|
||||
fn a_twelve_ink_devicen_colour_paints() {
|
||||
let content = "/CS1 cs 1 1 1 1 1 1 1 1 1 1 1 1 scn 0 0 200 200 re f 0 1 0 rg 0 0 20 20 re f";
|
||||
let page = render(content, &format!("[/DeviceN {TWELVE_INKS} /DeviceCMYK {TINT}]"));
|
||||
assert!(is_rich_black(at(&page, 100, 100)), "the twelve-ink fill paints: {:?}", at(&page, 100, 100));
|
||||
assert_eq!(at(&page, 10, 10), GREEN, "what follows the twelve-ink colour is drawn");
|
||||
assert!(page.warnings.is_empty(), "{:?}", page.warnings);
|
||||
}
|
||||
|
||||
/// The control from the report: the same colour with four inks always painted.
|
||||
#[test]
|
||||
fn a_four_ink_devicen_colour_paints() {
|
||||
let content = "/CS1 cs 1 1 1 1 scn 0 0 200 200 re f 0 1 0 rg 0 0 20 20 re f";
|
||||
let page = render(content, &format!("[/DeviceN [/Cyan /Magenta /Yellow /Black] /DeviceCMYK {TINT}]"));
|
||||
assert!(is_rich_black(at(&page, 100, 100)), "the four-ink fill paints: {:?}", at(&page, 100, 100));
|
||||
assert_eq!(at(&page, 10, 10), GREEN);
|
||||
assert!(page.warnings.is_empty(), "{:?}", page.warnings);
|
||||
}
|
||||
|
||||
/// An operator with more operands than the parser keeps still reads the ones nearest to it,
|
||||
/// as one with a few stray operands does, and the content after it is drawn.
|
||||
#[test]
|
||||
fn an_operator_with_hundreds_of_operands_does_not_end_the_content() {
|
||||
let strays = "0 ".repeat(300);
|
||||
let content = format!("1 0 0 rg 0 0 200 200 re f {strays}0 1 0 rg 0 0 20 20 re f");
|
||||
let page = render(&content, "/DeviceRGB");
|
||||
assert_eq!(at(&page, 100, 100), RED, "the content before the stray operands is drawn");
|
||||
assert_eq!(at(&page, 10, 10), GREEN, "the operator after them reads its own three operands");
|
||||
}
|
||||
|
||||
/// A tint transform that fails when it runs (a calculator function that pops more than it is
|
||||
/// given) paints that one colour in the alternate space's initial colour (black in DeviceRGB)
|
||||
/// and records a warning; the paints before and after it are drawn as usual.
|
||||
#[test]
|
||||
fn a_tint_transform_that_cannot_be_evaluated_draws_the_rest_of_the_page_and_warns() {
|
||||
let program = "{ pop pop pop }";
|
||||
let function = format!(
|
||||
"5 0 obj << /FunctionType 4 /Domain [0 1 0 1] /Range [0 1 0 1 0 1] /Length {} >> stream\n{program}\nendstream endobj\n",
|
||||
program.len()
|
||||
);
|
||||
let content = "1 0 0 rg 0 0 100 200 re f /CS1 cs 0.5 0.5 scn 100 0 100 200 re f 0 0 1 rg 0 0 50 50 re f";
|
||||
let page = render_with(content, "[/DeviceN [/Spot1 /Spot2] /DeviceRGB 5 0 R]", &function);
|
||||
assert_eq!(at(&page, 75, 150), RED, "the paint before the colour is drawn");
|
||||
assert_eq!(at(&page, 150, 150), BLACK, "the colour falls back to the alternate space's initial colour");
|
||||
assert_eq!(at(&page, 25, 25), BLUE, "the paint after the colour is drawn");
|
||||
assert!(page.warnings.contains(&RenderWarning::ColourFallback), "{:?}", page.warnings);
|
||||
}
|
||||
|
||||
/// A tint transform that cannot even be read (an unknown function type) keeps the colour space,
|
||||
/// so its paints fall back the same way, with the same warning, instead of being drawn in
|
||||
/// DeviceGray from the first tint (white here).
|
||||
#[test]
|
||||
fn a_tint_transform_that_cannot_be_read_falls_back_and_warns() {
|
||||
let cs1 = format!("[/DeviceN {TWELVE_INKS} /DeviceCMYK << /FunctionType 7 /Domain [0 1] >>]");
|
||||
let content = "/CS1 cs 1 1 1 1 1 1 1 1 1 1 1 1 scn 0 0 200 200 re f 0 1 0 rg 0 0 20 20 re f";
|
||||
let page = render(content, &cs1);
|
||||
assert!(is_rich_black(at(&page, 100, 100)), "the colour falls back to CMYK black: {:?}", at(&page, 100, 100));
|
||||
assert_eq!(at(&page, 10, 10), GREEN, "what follows is drawn");
|
||||
assert!(page.warnings.contains(&RenderWarning::ColourFallback), "{:?}", page.warnings);
|
||||
// Reported once per page, however many paints fell back.
|
||||
assert_eq!(page.warnings.iter().filter(|w| **w == RenderWarning::ColourFallback).count(), 1);
|
||||
}
|
||||
Vendored
+2
-2
@@ -17,11 +17,11 @@ 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` |
|
||||
| hayro-syntax | 0.7.2 | Apache-2.0 OR MIT | (1) Page-tree cycle guard in `resolve_pages` (visited set + depth cap): a `/Kids` loop among compressed objects overflowed the stack and aborted the process; (2) `ccitt_size_ok`: CCITT images wider than 2^20 columns or over 2^28 pixels are not decoded (a fuzzed `/Columns 4294967295` allocated 4 GiB); (3) Flate/LZW predictor row widths are saturating `usize`, a zero width is refused and a row longer than the data is not allocated (a fuzzed `/Columns 9223372036854775807` wrapped to a 2^61-byte allocation and aborted); (4) the inline-image end-of-data check (`EI`) doesn't nest inside its own look-ahead and examines at most 256 candidates and steps (50 images with "EI" in their data ran for over ten minutes); an EI followed by a delimiter (EI%..., EI[...) ends the image like one followed by white space; only a regular character after EI skips the candidate; (5) a stream whose `/Length` is wrong is recovered only when `stream` is the next token — scanning ahead to a later object's `stream` made an indirect appearance-state dictionary (Quartz checkboxes: `/AP /N` → `<< /Yes … /Off … >>`) render as a non-form, so the widget was skipped; (6) JPX rescaling uses an exact integer sample range for 1–32-bit components (32 shifted past u32, and floating-point maxima at 25–31 bits wrapped to zero), and refuses zero-sized rows; (7) `decode_limit`: Flate (through flate2 and the fallback inflater), LZW, RunLength and ASCII85 never write past `MAX_DECODED_STREAM` (256 MiB), or, for the last filter of an image of known size, past twice its pixel bytes (a predictor tag byte per byte), at most 1 GiB; `Stream::decoded_within` for budgeted callers; a page's `/Contents` array shares one `MAX_DECODED_STREAM` (a 2 MB page whose content stream or 8 × 8 image inflated to 2 GB took the renderer past 3 GB in under a second; naming the stream twenty times in `/Contents`, 5 GB); (8) high-precision numbers (jsPDF MediaBox coordinates with over 19 digits) parse without overflowing the u64 mantissa: fractional digits past it are dropped, integer digits past it scale the value (a real, kept finite); (9) large dictionary indexes are built on first use and shared across repeated reads within each PDF (#307); the validated-byte cache is bounded, reader contexts remain separate, repairs and inline/content dictionaries bypass sharing, and small dictionaries stay eager; (10) decoded object-stream slots publish once under contention, cold loading rejects recursive dependencies, and xref repair serializes without holding recursive read guards; this permits one parser per native render pool with private worker caches; (11) `sync.rs`: a poisoned lock is recovered instead of unwrapped (a worker panic no longer cascades into every reader of the same PDF), and xref repair takes a blocking write lock instead of asserting a non-blocking one; (12) `SegmentList` (`util.rs`) returns `None` for an out-of-range index instead of panicking; (13) a page's `/UserUnit` scales `render_dimensions` and `initial_transform`, so the page and everything on it are sized in points, as Acrobat shows them; it is read as Acrobat reads it (the page's own entry, not inherited; a number from 1 up, at most 75,000; anything else counts as 1), and a page without it keeps exactly the transform it had; (14) revision 2–4 passwords are tried as given and then in PDFDocEncoding (`legacy_passwords` in `crypto/mod.rs`, which resolves the upstream `TODO: Convert to PDFDocEncoding`): passwords arrive as UTF-8 text, so a password with characters outside ASCII (`Çok güzel`, `ılık€`) written in PDFDocEncoding, as ISO 32000-2 §7.6.4.3.2 asks and qpdf and Acrobat write it, was always wrong; (15) page content is read a piece at a time (`page::ContentReader`, `Page::content_reader`): plain streams and Flate streams without a predictor are decoded as they are read, with a budget of 64 times their compressed size and never less than `MAX_DECODED_STREAM` (a stream that expands past it is cut and reported); other streams are decoded whole, as before, and share `MAX_DECODED_STREAM`. The content tokenizer reads a window at a time (`UntypedIter::new_window`, `TypedIter::needs_more`, `TypedIter::committed`): an instruction that runs past the window is not decided until more data follows, which `Reader` records by flagging reads and `at_end` past the end of the data, including through the clones the parser makes. The Flate decoder keeps its own 32 KiB history, so it pauses at any output size. `ContentReader::new` reuses raw/decrypted stream bytes for budget accounting and piece creation, and `decoded_raw_within` applies the existing Whole-stream filters and limits to those bytes without decrypting twice; (16) revision 5–6 (AES-256) passwords are tried in their SASLprep form (RFC 4013, then UTF-8, at most 127 bytes, as ISO 32000-2 §7.6.4.3.3 Algorithm 2.A asks and pdfcraft-crypt writes them) and then, if that differs, as given (`aes256_passwLine truncated
|
||||
| hayro-syntax | 0.7.2 | Apache-2.0 OR MIT | (1) Page-tree cycle guard in `resolve_pages` (visited set + depth cap): a `/Kids` loop among compressed objects overflowed the stack and aborted the process; (2) `ccitt_size_ok`: CCITT images wider than 2^20 columns or over 2^28 pixels are not decoded (a fuzzed `/Columns 4294967295` allocated 4 GiB); (3) Flate/LZW predictor row widths are saturating `usize`, a zero width is refused and a row longer than the data is not allocated (a fuzzed `/Columns 9223372036854775807` wrapped to a 2^61-byte allocation and aborted); (4) the inline-image end-of-data check (`EI`) doesn't nest inside its own look-ahead and examines at most 256 candidates and steps (50 images with "EI" in their data ran for over ten minutes); an EI followed by a delimiter (EI%..., EI[...) ends the image like one followed by white space; only a regular character after EI skips the candidate; (5) a stream whose `/Length` is wrong is recovered only when `stream` is the next token — scanning ahead to a later object's `stream` made an indirect appearance-state dictionary (Quartz checkboxes: `/AP /N` → `<< /Yes … /Off … >>`) render as a non-form, so the widget was skipped; (6) JPX rescaling uses an exact integer sample range for 1–32-bit components (32 shifted past u32, and floating-point maxima at 25–31 bits wrapped to zero), and refuses zero-sized rows; (7) `decode_limit`: Flate (through flate2 and the fallback inflater), LZW, RunLength and ASCII85 never write past `MAX_DECODED_STREAM` (256 MiB), or, for the last filter of an image of known size, past twice its pixel bytes (a predictor tag byte per byte), at most 1 GiB; `Stream::decoded_within` for budgeted callers; a page's `/Contents` array shares one `MAX_DECODED_STREAM` (a 2 MB page whose content stream or 8 × 8 image inflated to 2 GB took the renderer past 3 GB in under a second; naming the stream twenty times in `/Contents`, 5 GB); (8) high-precision numbers (jsPDF MediaBox coordinates with over 19 digits) parse without overflowing the u64 mantissa: fractional digits past it are dropped, integer digits past it scale the value (a real, kept finite); (9) large dictionary indexes are built on first use and shared across repeated reads within each PDF (#307); the validated-byte cache is bounded, reader contexts remain separate, repairs and inline/content dictionaries bypass sharing, and small dictionaries stay eager; (10) decoded object-stream slots publish once under contention, cold loading rejects recursive dependencies, and xref repair serializes without holding recursive read guards; this permits one parser per native render pool with private worker caches; (11) `sync.rs`: a poisoned lock is recovered instead of unwrapped (a worker panic no longer cascades into every reader of the same PDF), and xref repair takes a blocking write lock instead of asserting a non-blocking one; (12) `SegmentList` (`util.rs`) returns `None` for an out-of-range index instead of panicking; (13) a page's `/UserUnit` scales `render_dimensions` and `initial_transform`, so the page and everything on it are sized in points, as Acrobat shows them; it is read as Acrobat reads it (the page's own entry, not inherited; a number from 1 up, at most 75,000; anything else counts as 1), and a page without it keeps exactly the transform it had; (14) revision 2–4 passwords are tried as given and then in PDFDocEncoding (`legacy_passwords` in `crypto/mod.rs`, which resolves the upstream `TODO: Convert to PDFDocEncoding`): passwords arrive as UTF-8 text, so a password with characters outside ASCII (`Çok güzel`, `ılık€`) written in PDFDocEncoding, as ISO 32000-2 §7.6.4.3.2 asks and qpdf and Acrobat write it, was always wrong; (15) page content is read a piece at a time (`page::ContentReader`, `Page::content_reader`): plain streams and Flate streams without a predictor are decoded as they are read, with a budget of 64 times their compressed size and never less than `MAX_DECODED_STREAM` (a stream that expands past it is cut and reported); other streams are decoded whole, as before, and share `MAX_DECODED_STREAM`. The content tokenizer reads a window at a time (`UntypedIter::new_window`, `TypedIter::needs_more`, `TypedIter::committed`): an instruction that runs past the window is not decided until more data follows, which `Reader` records by flagging reads and `at_end` past the end of the data, including through the clones the parser makes. The Flate decoder keeps its own 32 KiB history, so it pauses at any output size. `ContentReader::new` reuses raw/decrypted stream bytes for budget accounting and piece creation, and `decoded_raw_within` applies the existing Whole-stream filters and limits to those bytes without decrypting twice; (16) revision 5–6 (AES-256) passwords are tried in their SASLprep form (RFC 4013, then UTF-8, at most 127 bytes, as ISO 32000-2 §7.6.4.3.3 Algorithm 2.A asks and pdfcraft-crypt writes them) and then, if that differs, as given (`aes256_passwLine truncated
|
||||
| winit | 0.30.13 | Apache-2.0 | (1) on Windows 11 (build 22000 and later), `WM_DPICHANGED` applies the rect Windows suggests. It used to nudge the window onto the monitor `MonitorFromWindow` names, which during a drag is still the monitor being left; the nudge sent another `WM_DPICHANGED`, so a window dragged to a monitor with another scale factor grew and stayed on the wrong monitor at the wrong scale (#324). Backport of winit master 488c036a ([winit#4341](https://github.com/rust-windowing/winit/pull/4341)), which no 0.30 release has; Windows 10 keeps the old adjustment, as on winit master. (2) on Wayland, a seat's text input is destroyed when the seat goes away, not whenever it loses a capability: losing any capability (a touch screen or tablet unplugged, a remote-desktop session ending) destroyed it, and only an added capability recreated it, so IME stopped working until restart. Port of [winit#4747](https://github.com/rust-windowing/winit/pull/4747); (3) on Windows, an IME composition reports its cursor from `GCS_CURSORPOS` only when `WM_IME_COMPOSITION` says it is set, and at the end of the composition otherwise: the Microsoft Korean IME never sets it, so the cursor read as 0 (egui then drew no caret while composing; it now draws it after the syllable). Port of [winit#4746](https://github.com/rust-windowing/winit/pull/4746); (4) on Windows, a hidden window is not maximized until it is shown, and a hidden window shown while maximized gets one `ShowWindow(SW_MAXIMIZE)`: `SW_MAXIMIZE` shows a hidden window, so PdfCraft, which eframe keeps hidden until its first frame is drawn, appeared unpainted (white) when it restored a maximized window, and could lose its focus. Port of [winit#4587](https://github.com/rust-windowing/winit/pull/4587) (the later, focus-safe form of [winit#4575](https://github.com/rust-windowing/winit/pull/4575)); (5) on X11, when allowing or disallowing IME replaces the focused window's input context (egui does it each time a text field gains or loses focus), the new context is focused: no focus event follows, so it stayed unfocused until the window lost and regained focus. Port of [winit#4727](https://github.com/rust-windowing/winit/pull/4727); (6) on macOS, `insertText` commits through IME when a composition was started (`pending_commit`, set by `setMarkedText`) rather than when marked text is left: input methods that end a composition with `unmarkText` before `insertText` lost the text, and Apple Korean dropped the key typed after a syllable (`한` then `5` or `;`); other `insertText` calls stay `KeyboardInput`; a commit outside a key press (a candidate clicked with the mouse, dictation) clears the marked text and leaves no key to swallow, as in [winit#4748](https://github.com/rust-windowing/winit/pull/4748) (without it the next key, such as Backspace, was lost). `validAttributesForMarkedText` lists the underline and marked-clause attributes, without which some input methods don't compose. Port of [winit#4650](https://github.com/rust-windowing/winit/pull/4650), the 0.30 backport of [winit#4651](https://github.com/rust-windowing/winit/pull/4651) (merged on winit master), with the underline attribute spelled as AppKit's `NSUnderlineStyleAttributeName` (`NSUnderline`); (7) on macOS, disallowing IME with a composition in progress (focus leaving a text field) tells the input method to discard its marked text (`discardMarkedText`): it kept composing it once IME was allowed again, so the abandoned syllable came back (`하`, then `가` typed in the next field, became `학`, then `하` + `가`; Japanese `か` then `さ` became `傘`). Port of [winit#4745](https://github.com/rust-windowing/winit/pull/4745); (8) on macOS, text inserted outside a key press without a composition (the emoji picker) is reported as `Ime::Commit`; it was dropped. Port of the emoji-picker part of [winit#4749](https://github.com/rust-windowing/winit/pull/4749) (0.30 backport of [winit#4748](https://github.com/rust-windowing/winit/pull/4748)); its `selectedRange` change for dictation is left out because it switches on press-and-hold for every held key (an accent menu instead of key repeat, and the chosen accent added after the repeated letters); (9) on macOS, a key whose text was committed through IME isn't also sent as `KeyboardInput` unless AppKit forwards it as a command (Enter): Apple Korean answers Space with no syllable in progress with `setMarkedText(" ")`, `insertText(" ")`, `setMarkedText("")`, and the last call reset winit's state, so the space arrived twice. Same goal as [winit#4478](https://github.com/rust-windowing/winit/pull/4478), whose changes don't reach this call order (macOS 14); to be proposed upstream there; (10) on macOS, when the first key in a fresh app reaches Apple Korean's `insertText` as a raw compatibility jamo instead of starting a composition, that key is interpreted once more, synchronously, before it is sent as `KeyboardInput` (g k s typed ㅎㅏㄴ instead of 한); only an unmodified, Line truncated
|
||||
| egui-wgpu | 0.36.2 | MIT OR Apache-2.0 | (1) `winit::surface_fit`: a window's surface is configured within the device's `max_texture_dimension_2d`, both sides shrunk by one factor that egui then draws at (`pixels_per_point × render_scale`), so the whole window is drawn into the surface (on DX12 it is stretched over the window and lines up with the pointer; wgpu's GL backend copies it unscaled into a corner); the longer side becomes exactly the limit; the depth and MSAA textures follow, and a recreated surface starts again from the window's own size. egui-wgpu configured the window's size as is, and `Surface::configure` panics beyond the limit: a window restored at another monitor's scale (opening an Outlook attachment on a mixed-DPI laptop asked an 8192-pixel device for 8600 × 3423, #577) or stretched across monitors closed PdfCraft, before its window appeared when it happened at start-up ([emilk/egui#8361](https://github.com/emilk/egui/issues/8361)). The published crate leaves out egui's licence files; `LICENSE-APACHE` and `LICENSE-MIT` are from the 0.36.2 tag; (2) `winit::catch_errors`: a new window's surface is configured inside wgpu error scopes (validation, out of memory, internal), and a failure is returned as `WgpuError::ConfigureSurface` (for the root window at start-up eframe returns it as `Error::Wgpu`, which PdfCraft retries with OpenGL); nothing is kept for the window. wgpu's default handler panicked instead, and eframe configures the root surface before the app is created, so a driver that can't configure one closed PdfCraft at launch (a 2015 Intel GPU through wgpu's GL backend timed out waiting for the GPU to go idle, `GpuWaitTimeout`, #519). Unchanged, so still a panic: an error in a later reconfigure (resize, a lost surface), a device lost during the first configure (wgpu reports it only to a callback), and a window shown at zero size (first configured on resize) | (1) `pdfcraft` `tests::a_window_larger_than_the_gpu_limit_gets_a_surface_within_it`, `tests::surface_fit_never_empties_or_overflows_a_surface`, and `tests::egui_wgpu_carries_the_surface_size_fit`, which keeps the patch in the build and in the paths that size a surface; (2) `pdfcraft` `tests::a_gpu_error_while_a_window_is_set_up_is_returned_not_a_panic` (a real device: an error inside `catch_errors` is returned, not a panic) and `tests::egui_wgpu_returns_a_surface_it_cannot_configure_as_an_error`, which keeps it around `add_surface`'s configure |
|
||||
| vello_common | 0.0.8 | Apache-2.0 OR MIT | (1) `clip::intersect` (the clip step every clipped path passes through) starts its row walk at the first row both paths have strips in, not the earlier of the two first rows. The walk visited every row from the top of the clip for each path (on the A1 sample's full-page canvas, about half its strip rows per stroke), and rows where one path has no strips produce no output, so the strips are unchanged (vello_common 0.1 starts at the later row too). Its cost grew with the page, and a full-page render of the A1 sample was about 30% faster; the output is byte-identical | (1) `clip::tests::intersect_walks_only_rows_both_paths_have_strips` counts the rows the walk visits (`cargo test --manifest-path vendor/vello_common/Cargo.toml`) and fails without the patch; the render crate's pixel tests run through the patched crate |
|
||||
|
||||
Vendored
+54
-10
@@ -28,6 +28,22 @@ pub type ColorComponents = SmallVec<[f32; 4]>;
|
||||
std::thread_local! {
|
||||
// PdfCraft patch (34): see `tint_transform_runs`.
|
||||
static TINT_TRANSFORM_RUNS: core::cell::Cell<u64> = const { core::cell::Cell::new(0) };
|
||||
// PdfCraft patch (55): see `note_color_fallback`.
|
||||
static COLOR_FALLBACK: core::cell::Cell<bool> = const { core::cell::Cell::new(false) };
|
||||
}
|
||||
|
||||
/// PdfCraft patch (55): record that a colour could not be computed and was painted in a
|
||||
/// fallback colour, reported as `InterpreterWarning::ColorFallback` when the content stream
|
||||
/// being interpreted ends. Per thread, like the page's other budgets: one page is interpreted
|
||||
/// on one thread.
|
||||
pub(crate) fn note_color_fallback() {
|
||||
COLOR_FALLBACK.with(|fell_back| fell_back.set(true));
|
||||
}
|
||||
|
||||
/// PdfCraft patch (55): whether a colour fell back since the last call (or since the page
|
||||
/// started), clearing it, so each fallback is reported once.
|
||||
pub(crate) fn take_color_fallback() -> bool {
|
||||
COLOR_FALLBACK.with(|fell_back| fell_back.replace(false))
|
||||
}
|
||||
|
||||
/// PdfCraft patch (34): how many colours this thread has run through a Separation or DeviceN
|
||||
@@ -1030,10 +1046,30 @@ impl ToRgb for Indexed {
|
||||
#[derive(Debug, Clone)]
|
||||
pub(crate) struct Separation {
|
||||
alternate_space: ColorSpace,
|
||||
tint_transform: Function,
|
||||
/// PdfCraft patch (55): `None` when the tint transform cannot be read (see
|
||||
/// `eval_tint_transform`).
|
||||
tint_transform: Option<Function>,
|
||||
is_none_separation: bool,
|
||||
}
|
||||
|
||||
/// PdfCraft patch (55): `tint_transform` run on the tints of one colour, or, when it cannot be
|
||||
/// read or evaluated, the initial colour of `alternate_space` (black in every device space), with
|
||||
/// the fallback recorded. hayro already fell back this way when evaluation failed, silently; a
|
||||
/// transform it could not read made the whole colour space unreadable, and the space's
|
||||
/// paints were drawn in DeviceGray from their first tint instead (white for a full tint).
|
||||
fn eval_tint_transform(
|
||||
tint_transform: Option<&Function>,
|
||||
alternate_space: &ColorSpace,
|
||||
tints: &[f32],
|
||||
) -> ColorComponents {
|
||||
tint_transform
|
||||
.and_then(|f| f.eval(tints.to_smallvec()))
|
||||
.unwrap_or_else(|| {
|
||||
note_color_fallback();
|
||||
alternate_space.initial_color()
|
||||
})
|
||||
}
|
||||
|
||||
impl Separation {
|
||||
fn new(array: &Array<'_>, cache: &Cache) -> Option<Self> {
|
||||
let mut iter = array.flex_iter();
|
||||
@@ -1041,7 +1077,9 @@ impl Separation {
|
||||
let _ = iter.next::<Name<'_>>()?;
|
||||
let name = iter.next::<Name<'_>>()?;
|
||||
let alternate_space = ColorSpace::new(iter.next::<Object<'_>>()?, cache)?;
|
||||
let tint_transform = Function::new(&iter.next::<Object<'_>>()?)?;
|
||||
// PdfCraft patch (55): an unreadable tint transform keeps the space (see
|
||||
// `eval_tint_transform`).
|
||||
let tint_transform = iter.next::<Object<'_>>().and_then(|f| Function::new(&f));
|
||||
// Either I did something wrong, or no other viewers properly handles
|
||||
// `All`, so let's just ignore it as well.
|
||||
let is_none_separation = name.as_str() == "None";
|
||||
@@ -1057,12 +1095,15 @@ impl Separation {
|
||||
impl ToRgb for Separation {
|
||||
fn convert_f32(&self, input: &[f32], output: &mut [u8], _: bool) -> Option<()> {
|
||||
count_tint_transform_runs(input.len());
|
||||
// PdfCraft patch (55): see `eval_tint_transform`.
|
||||
let evaluated = input
|
||||
.iter()
|
||||
.flat_map(|n| {
|
||||
self.tint_transform
|
||||
.eval(smallvec![*n])
|
||||
.unwrap_or(self.alternate_space.initial_color())
|
||||
eval_tint_transform(
|
||||
self.tint_transform.as_ref(),
|
||||
&self.alternate_space,
|
||||
&[*n],
|
||||
)
|
||||
})
|
||||
.collect::<Vec<_>>();
|
||||
self.alternate_space.convert_f32(&evaluated, output, false)
|
||||
@@ -1077,7 +1118,9 @@ impl ToRgb for Separation {
|
||||
pub(crate) struct DeviceN {
|
||||
alternate_space: ColorSpace,
|
||||
num_components: u8,
|
||||
tint_transform: Function,
|
||||
/// PdfCraft patch (55): `None` when the tint transform cannot be read (see
|
||||
/// `eval_tint_transform`).
|
||||
tint_transform: Option<Function>,
|
||||
is_none: bool,
|
||||
}
|
||||
|
||||
@@ -1094,7 +1137,9 @@ impl DeviceN {
|
||||
let num_components = u8::try_from(names.len()).ok()?;
|
||||
let all_none = names.iter().all(|n| n.as_str() == "None");
|
||||
let alternate_space = ColorSpace::new(iter.next::<Object<'_>>()?, cache)?;
|
||||
let tint_transform = Function::new(&iter.next::<Object<'_>>()?)?;
|
||||
// PdfCraft patch (55): an unreadable tint transform keeps the space (see
|
||||
// `eval_tint_transform`).
|
||||
let tint_transform = iter.next::<Object<'_>>().and_then(|f| Function::new(&f));
|
||||
|
||||
if num_components == 0 {
|
||||
return None;
|
||||
@@ -1113,12 +1158,11 @@ impl ToRgb for DeviceN {
|
||||
fn convert_f32(&self, input: &[f32], output: &mut [u8], _: bool) -> Option<()> {
|
||||
let colours = input.len().checked_div(usize::from(self.num_components));
|
||||
count_tint_transform_runs(colours.unwrap_or(0));
|
||||
// PdfCraft patch (55): see `eval_tint_transform`.
|
||||
let evaluated = input
|
||||
.chunks_exact(self.num_components as usize)
|
||||
.flat_map(|n| {
|
||||
self.tint_transform
|
||||
.eval(n.to_smallvec())
|
||||
.unwrap_or(self.alternate_space.initial_color())
|
||||
eval_tint_transform(self.tint_transform.as_ref(), &self.alternate_space, n)
|
||||
})
|
||||
.collect::<Vec<_>>();
|
||||
self.alternate_space.convert_f32(&evaluated, output, false)
|
||||
|
||||
+2
@@ -209,6 +209,8 @@ impl<'a> Context<'a> {
|
||||
NESTED_PAINTS.with(|n| n.set(0));
|
||||
CONTENT_LEFT.with(|c| c.set(MAX_PAGE_CONTENT));
|
||||
CONTENT_TRUNCATED.with(|truncated| truncated.set(false));
|
||||
// PdfCraft patch (55): a fallback left over from another page is not this page's.
|
||||
crate::color::take_color_fallback();
|
||||
crate::encode::reset_mesh_budget();
|
||||
|
||||
Self::new_with(initial_transform, bbox, cache, xref, settings, state, 0)
|
||||
|
||||
+24
-2
@@ -157,6 +157,10 @@ pub enum InterpreterWarning {
|
||||
ImageDecodeFailure,
|
||||
/// PdfCraft patch (18): a page content stream was skipped after exhausting its safety budget.
|
||||
ContentTruncated,
|
||||
/// PdfCraft patch (55): a colour could not be computed (a colour space that cannot be
|
||||
/// read, or a Separation or DeviceN tint transform that cannot be evaluated) and was painted
|
||||
/// in a fallback colour. Reported at most once per content stream.
|
||||
ColorFallback,
|
||||
}
|
||||
|
||||
/// interpret the contents of the page and render them into the device.
|
||||
@@ -562,8 +566,13 @@ fn interpret_window<'a>(
|
||||
}
|
||||
TypedInstruction::ColorSpaceStroke(c) => {
|
||||
// PdfCraft patch (38): see `named_color_space`.
|
||||
// PdfCraft patch (55): a space that cannot be read is drawn in DeviceGray, as
|
||||
// before, and the fallback is reported.
|
||||
let cs = named_color_space(c.0, resources, &defaults, context)
|
||||
.unwrap_or(ColorSpace::device_gray());
|
||||
.unwrap_or_else(|| {
|
||||
crate::color::note_color_fallback();
|
||||
ColorSpace::device_gray()
|
||||
});
|
||||
|
||||
if !cs.is_pattern() {
|
||||
context.get_mut().graphics_state.stroke_pattern = None;
|
||||
@@ -573,8 +582,13 @@ fn interpret_window<'a>(
|
||||
}
|
||||
TypedInstruction::ColorSpaceNonStroke(c) => {
|
||||
// PdfCraft patch (38): see `named_color_space`.
|
||||
// PdfCraft patch (55): a space that cannot be read is drawn in DeviceGray, as
|
||||
// before, and the fallback is reported.
|
||||
let cs = named_color_space(c.0, resources, &defaults, context)
|
||||
.unwrap_or(ColorSpace::device_gray());
|
||||
.unwrap_or_else(|| {
|
||||
crate::color::note_color_fallback();
|
||||
ColorSpace::device_gray()
|
||||
});
|
||||
|
||||
if !cs.is_pattern() {
|
||||
context.get_mut().graphics_state.non_stroke_pattern = None;
|
||||
@@ -932,6 +946,10 @@ pub fn interpret<'a>(
|
||||
if crate::context::content_was_truncated() {
|
||||
(context.settings.warning_sink)(InterpreterWarning::ContentTruncated);
|
||||
}
|
||||
// PdfCraft patch (55): and that a colour was painted in a fallback colour.
|
||||
if crate::color::take_color_fallback() {
|
||||
(context.settings.warning_sink)(InterpreterWarning::ColorFallback);
|
||||
}
|
||||
}
|
||||
|
||||
/// PdfCraft patch: the bytes of a window of page content. A window grows only while an instruction
|
||||
@@ -990,4 +1008,8 @@ fn interpret_content<'a>(
|
||||
if cut || content.truncated() || crate::context::content_was_truncated() {
|
||||
(context.settings.warning_sink)(InterpreterWarning::ContentTruncated);
|
||||
}
|
||||
// PdfCraft patch (55): and that a colour was painted in a fallback colour.
|
||||
if crate::color::take_color_fallback() {
|
||||
(context.settings.warning_sink)(InterpreterWarning::ColorFallback);
|
||||
}
|
||||
}
|
||||
+56
-17
@@ -37,12 +37,11 @@ use crate::content::ops::TypedInstruction;
|
||||
use crate::object;
|
||||
use crate::object::dict::{Dict, InlineImageDict};
|
||||
use crate::object::name::{Name, skip_name_like};
|
||||
use crate::object::{Array, Null, Number, Object, Stream};
|
||||
use crate::object::{Array, Number, Object, Stream};
|
||||
use crate::reader::Reader;
|
||||
use crate::reader::{Readable, ReaderContext, ReaderExt, Skippable};
|
||||
use crate::trivia::{Comment, is_regular_character, is_white_space_character};
|
||||
use crate::util::find_needle;
|
||||
use core::array;
|
||||
use core::fmt::{Debug, Formatter};
|
||||
use core::ops::Deref;
|
||||
use core::marker::PhantomData;
|
||||
@@ -51,8 +50,18 @@ use smallvec::SmallVec;
|
||||
// 6 operands are used for example for ctm or cubic curves,
|
||||
// but anything above should be pretty rare (only for example for
|
||||
// DeviceN color spaces, or invalid PDF files). So we settle on 10.
|
||||
// PdfCraft patch (26): this is now only how many operands are held inline; see `MAX_OPERANDS`.
|
||||
const OPERANDS_THRESHOLD: usize = 10;
|
||||
|
||||
/// PdfCraft patch (26): the most operands one instruction keeps. The stack held ten, and the
|
||||
/// eleventh operand of an instruction ended the whole content stream, so a DeviceN colour of
|
||||
/// eleven or more inks (ISO 32000-2 §8.6.6.5 allows "an arbitrary number of colour
|
||||
/// components") blanked the rest of the page (#4260). An `SCN`/`scn` for the largest DeviceN
|
||||
/// space the interpreter reads (255 inks) takes 255 numbers and a pattern name. Past this, the
|
||||
/// oldest operands are dropped: operators read the operands nearest to them (see `shift` in the
|
||||
/// operator macros), so this is how stray operands below an instruction are already treated.
|
||||
const MAX_OPERANDS: usize = 256;
|
||||
|
||||
impl Debug for Operator<'_> {
|
||||
fn fmt(&self, f: &mut Formatter<'_>) -> core::fmt::Result {
|
||||
write!(f, "{}", self.0.as_str())
|
||||
@@ -436,6 +445,8 @@ impl<'a> UntypedIter<'a> {
|
||||
|
||||
self.operator = Some(operator);
|
||||
self.committed = self.reader.offset();
|
||||
// PdfCraft patch (26): operands in reading order, if some were dropped.
|
||||
self.stack.settle();
|
||||
return Some(Instruction {
|
||||
operands: &self.stack,
|
||||
operator: self.operator.as_ref().unwrap(),
|
||||
@@ -594,8 +605,13 @@ impl<'b, 'a> Instruction<'b, 'a> {
|
||||
pub struct Stack<'a> {
|
||||
// TODO: Explore using an object pool to avoid repeatedly
|
||||
// allocating/deallocating objects.
|
||||
data: [Object<'a>; OPERANDS_THRESHOLD],
|
||||
len: usize,
|
||||
// PdfCraft patch (26): up to `MAX_OPERANDS` operands, the first `OPERANDS_THRESHOLD` inline.
|
||||
data: SmallVec<[Object<'a>; OPERANDS_THRESHOLD]>,
|
||||
/// PdfCraft patch (26): once `data` is full, the slot of its oldest operand, which the next
|
||||
/// operand replaces. Always 0 while the stack is not full, and after `settle`.
|
||||
oldest: usize,
|
||||
/// PdfCraft patch (26): whether operands were dropped since the stack was last settled.
|
||||
dropped: bool,
|
||||
}
|
||||
|
||||
impl<'a> Default for Stack<'a> {
|
||||
@@ -608,31 +624,53 @@ impl<'a> Stack<'a> {
|
||||
/// Create a new, empty stack.
|
||||
pub fn new() -> Self {
|
||||
Self {
|
||||
data: array::from_fn(|_| Object::Null(Null)),
|
||||
len: 0,
|
||||
data: SmallVec::new(),
|
||||
oldest: 0,
|
||||
dropped: false,
|
||||
}
|
||||
}
|
||||
|
||||
/// PdfCraft patch (26): push an operand, dropping the oldest once `MAX_OPERANDS` are held
|
||||
/// (see `MAX_OPERANDS`). Never fails: it used to, and the failure ended the content stream.
|
||||
fn push(&mut self, operand: Object<'a>) -> Option<()> {
|
||||
if self.len >= OPERANDS_THRESHOLD {
|
||||
return None;
|
||||
if self.data.len() < MAX_OPERANDS {
|
||||
self.data.push(operand);
|
||||
return Some(());
|
||||
}
|
||||
|
||||
self.data[self.len] = operand;
|
||||
self.len += 1;
|
||||
self.dropped = true;
|
||||
if let Some(slot) = self.data.get_mut(self.oldest) {
|
||||
*slot = operand;
|
||||
}
|
||||
self.oldest = (self.oldest + 1) % MAX_OPERANDS;
|
||||
Some(())
|
||||
}
|
||||
|
||||
/// PdfCraft patch (26): put the operands back in the order they were read, oldest first,
|
||||
/// after `push` dropped some. Called before the instruction is handed out.
|
||||
fn settle(&mut self) {
|
||||
if self.dropped {
|
||||
warn!("more than {MAX_OPERANDS} operands before an operator; the oldest were dropped");
|
||||
// Cannot panic: operands are dropped only once `data` holds `MAX_OPERANDS`, and
|
||||
// `oldest` stays below that.
|
||||
self.data.rotate_left(self.oldest);
|
||||
self.oldest = 0;
|
||||
self.dropped = false;
|
||||
}
|
||||
}
|
||||
|
||||
fn clear(&mut self) {
|
||||
self.len = 0;
|
||||
self.data.clear();
|
||||
self.oldest = 0;
|
||||
self.dropped = false;
|
||||
}
|
||||
|
||||
fn len(&self) -> usize {
|
||||
self.len
|
||||
self.data.len()
|
||||
}
|
||||
|
||||
fn as_slice(&self) -> &[Object<'a>] {
|
||||
&self.data[..self.len]
|
||||
&self.data
|
||||
}
|
||||
|
||||
fn get<'b, T>(&'b self, index: usize) -> Option<T>
|
||||
@@ -665,11 +703,12 @@ impl Debug for Stack<'_> {
|
||||
|
||||
impl Clone for Stack<'_> {
|
||||
fn clone(&self) -> Self {
|
||||
let mut stack = Self::new();
|
||||
for item in self.as_slice() {
|
||||
stack.push(item.clone()).unwrap();
|
||||
// PdfCraft patch (26): a plain copy (pushing each operand again could no longer fail).
|
||||
Self {
|
||||
data: self.data.clone(),
|
||||
oldest: self.oldest,
|
||||
dropped: self.dropped,
|
||||
}
|
||||
stack
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
+41
@@ -152,6 +152,47 @@ f
|
||||
assert!(iter.next().is_none());
|
||||
}
|
||||
|
||||
/// PdfCraft patch (26): a twelve-ink DeviceN colour's `scn` keeps all twelve operands, and
|
||||
/// the instructions after it are still read (#4260). The eleventh operand ended the stream.
|
||||
#[test]
|
||||
fn scn_with_twelve_components_keeps_them_all() {
|
||||
let input = b"1 2 3 4 5 6 7 8 9 10 11 12 scn 0 0 10 10 re f";
|
||||
let mut iter = TypedIter::new(input);
|
||||
|
||||
match iter.next() {
|
||||
Some(TypedInstruction::NonStrokeColorNamed(NonStrokeColorNamed(nums, None))) => {
|
||||
let expected = (1..=12).map(Number::from_i32).collect::<Vec<_>>();
|
||||
assert_eq!(nums.as_slice(), expected.as_slice());
|
||||
}
|
||||
other => panic!("unexpected instruction: {other:?}"),
|
||||
}
|
||||
assert!(matches!(iter.next(), Some(TypedInstruction::RectPath(_))));
|
||||
assert!(matches!(iter.next(), Some(TypedInstruction::FillPathNonZero(_))));
|
||||
assert!(iter.next().is_none());
|
||||
}
|
||||
|
||||
/// PdfCraft patch (26): past the operand cap the oldest operands are dropped, in order, and
|
||||
/// the operator reads the ones nearest to it.
|
||||
#[test]
|
||||
fn operands_past_the_cap_keep_the_latest_in_order() {
|
||||
let mut input = String::new();
|
||||
for i in 0..600 {
|
||||
input.push_str(&format!("{i} "));
|
||||
}
|
||||
input.push_str("scn 0 1 0 rg");
|
||||
let mut iter = TypedIter::new(input.as_bytes());
|
||||
|
||||
match iter.next() {
|
||||
Some(TypedInstruction::NonStrokeColorNamed(NonStrokeColorNamed(nums, None))) => {
|
||||
let expected = (344..600).map(Number::from_i32).collect::<Vec<_>>();
|
||||
assert_eq!(nums.as_slice(), expected.as_slice());
|
||||
}
|
||||
other => panic!("unexpected instruction: {other:?}"),
|
||||
}
|
||||
assert!(matches!(iter.next(), Some(TypedInstruction::NonStrokeColorDeviceRgb(_))));
|
||||
assert!(iter.next().is_none());
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn scn() {
|
||||
let input = b"
|
||||
|
||||
Reference in new issue
Block a user