mirror of
https://github.com/storytold/pdfcraft.git
synced 2026-11-10 13:01:29 +00:00
M2: a JBIG2 mask with a large symbol dictionary draws, and one a decoder limit refuses takes its picture with it (#6722) (#6784)
This commit is contained in:
Piohrun authored and 
GitHub committed
1 parent
d9ec80243b
commit
e2464e1440
18 files changed
+791
-36
No files matched your search
@@ -434,7 +434,10 @@ pub(crate) fn render(args: &[String]) -> Result<(), CliError> {
|
||||
for warning in &p.warnings {
|
||||
match warning {
|
||||
pdfcraft_render::RenderWarning::ContentTruncated => {
|
||||
let _ = writeln!(std::io::stderr().lock(), "warning: page {page}: content past the page's safety budget was skipped");
|
||||
let _ = writeln!(
|
||||
std::io::stderr().lock(),
|
||||
"warning: page {page}: content past the page's safety budget, or a picture whose JBIG2 mask is past a decoder limit, was skipped"
|
||||
);
|
||||
}
|
||||
pdfcraft_render::RenderWarning::ColourFallback => {
|
||||
let _ =
|
||||
|
||||
@@ -207,8 +207,9 @@ mutually exclusive with `hide_text_block`.
|
||||
|
||||
When the renderer reports a warning for the page, `page_render` and `render_preview` return a
|
||||
JSON part after the PNG, `{ "page": 1, "warnings": [...] }`, with the sentences
|
||||
`pdfcraft-cli render` prints: "content past the page's safety budget was skipped" and "a colour
|
||||
that could not be computed was painted in a fallback colour". A page without warnings returns
|
||||
`pdfcraft-cli render` prints, such as "content past the page's safety budget, or a picture whose
|
||||
JBIG2 mask is past a decoder limit, was skipped" and "a colour that could not be computed was
|
||||
painted in a fallback colour". A page without warnings returns
|
||||
the PNG alone.
|
||||
|
||||
|
||||
|
||||
@@ -412,7 +412,9 @@ pub(crate) fn rendered_content(out: &pdfcraft_render::RenderedPage, page: usize)
|
||||
fn render_warning_text(warning: pdfcraft_render::RenderWarning) -> &'static str {
|
||||
use pdfcraft_render::RenderWarning;
|
||||
match warning {
|
||||
RenderWarning::ContentTruncated => "content past the page's safety budget was skipped",
|
||||
RenderWarning::ContentTruncated => {
|
||||
"content past the page's safety budget, or a picture whose JBIG2 mask is past a decoder limit, was skipped"
|
||||
}
|
||||
RenderWarning::ColourFallback => "a colour that could not be computed was painted in a fallback colour",
|
||||
RenderWarning::MalformedIndexedImage => "an image with a malformed Indexed colour table may be drawn wrongly or not at all",
|
||||
RenderWarning::Type3WidthsMissing => "a Type 3 font has no /Widths; its glyphs were spaced by the widths their glyph procedures give",
|
||||
|
||||
@@ -212,7 +212,7 @@ pub fn tools() -> Vec<ToolDef> {
|
||||
)),
|
||||
t("doc_set_info", "Set document metadata", "Set a document information entry such as Title, Author, Subject or Keywords, or a custom property under any other name (no spaces, delimiters, / or #; at most 127 bytes; doc_info lists them under custom); an empty value removes it. When the file has XMP metadata, the matching XMP property (dc:title, dc:creator, dc:description, pdf:Keywords, xmp:CreatorTool, pdf:Producer) is changed too, so viewers that read XMP first show the new value, and a custom property is kept there as pdfx:<name> when its name can be an XML name (in a PDF/A file only one already there is changed). Undoable.")
|
||||
.with(schema(json!({ "doc": doc(), "key": { "type": "string" }, "value": { "type": "string" } }), &["doc", "key", "value"])),
|
||||
t("page_render", "Render a page", "Render one page to a PNG image (default 96 dpi, at most 600). When the picture is incomplete or approximate (content cut at the page's safety budget, a colour painted in a fallback colour), a JSON part follows the image: { page, warnings: [sentence, ...] }.")
|
||||
t("page_render", "Render a page", "Render one page to a PNG image (default 96 dpi, at most 600). When the picture is incomplete or approximate (content cut at the page's safety budget, a picture left out because its JBIG2 mask is past a decoder limit, a colour painted in a fallback colour), a JSON part follows the image: { page, warnings: [sentence, ...] }.")
|
||||
.ro()
|
||||
.with(schema(json!({ "doc": doc(), "page": { "type": "integer", "minimum": 1 }, "dpi": { "type": "number", "minimum": 1, "maximum": 600 },
|
||||
"hide_text_block": { "type": "integer", "minimum": 1, "description": "Render an inline editor background without this paragraph (number from text_paragraphs, resolved as text_edit does: refused once an edit merged that paragraph into a neighbour). Does not modify the document." },
|
||||
|
||||
@@ -123,6 +123,45 @@ fn page_render_reports_a_recovered_malformed_indexed_image() {
|
||||
let _ = std::fs::remove_dir_all(dir);
|
||||
}
|
||||
|
||||
/// A picture whose JBIG2 soft mask is past one of the decoder's limits isn't drawn (#6722), and
|
||||
/// `page_render` says why the page is incomplete, in the words `pdfcraft-cli render` prints.
|
||||
#[test]
|
||||
fn page_render_says_a_picture_was_left_out_for_its_jbig2_mask() {
|
||||
let dir = std::env::temp_dir().join(format!("pdfcraft-render-warnings-jbig2-mask-{}", std::process::id()));
|
||||
let _ = std::fs::remove_dir_all(&dir);
|
||||
std::fs::create_dir_all(&dir).unwrap();
|
||||
// One JBIG2 segment (ISO 14492 §7.4.8): the information of a page 65,536 columns wide, a
|
||||
// column past the decoder's bound on a side, as the mask's dictionary says too.
|
||||
let mut mask = vec![0, 0, 0, 0, 48, 0, 1, 0, 0, 0, 19];
|
||||
mask.extend_from_slice(&65536u32.to_be_bytes());
|
||||
mask.extend_from_slice(&2u32.to_be_bytes());
|
||||
mask.extend_from_slice(&[0; 11]); // resolution, flags, striping
|
||||
let content = "q 200 0 0 200 0 0 cm /Im Do Q";
|
||||
let mut 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 << /XObject << /Im 5 0 R >> >> /Contents 4 0 R >> endobj\n\
|
||||
4 0 obj << /Length {} >> stream\n{content}\nendstream endobj\n\
|
||||
5 0 obj << /Type /XObject /Subtype /Image /Width 1 /Height 1 /BitsPerComponent 8 /ColorSpace /DeviceGray /SMask 6 0 R /Length 1 >> stream\n\0\nendstream endobj\n\
|
||||
6 0 obj << /Type /XObject /Subtype /Image /Width 65536 /Height 2 /BitsPerComponent 1 /ColorSpace /DeviceGray /Filter /JBIG2Decode /Length {} >> stream\n",
|
||||
content.len(),
|
||||
mask.len()
|
||||
)
|
||||
.into_bytes();
|
||||
pdf.extend_from_slice(&mask);
|
||||
pdf.extend_from_slice(b"\nendstream endobj\ntrailer << /Root 1 0 R >>\n%%EOF");
|
||||
std::fs::write(dir.join("mask.pdf"), pdf).unwrap();
|
||||
let mut a = Automation::new().with_root(&dir).unwrap();
|
||||
let doc = open(&mut a, "mask.pdf");
|
||||
let out = a.call("page_render", &json!({ "doc": doc, "page": 1, "dpi": 72 })).unwrap();
|
||||
let Some(Content::Json(report)) = out.get(1) else { panic!("expected the warnings as JSON: {out:?}") };
|
||||
assert_eq!(
|
||||
report["warnings"],
|
||||
json!(["content past the page's safety budget, or a picture whose JBIG2 mask is past a decoder limit, was skipped"])
|
||||
);
|
||||
let _ = std::fs::remove_dir_all(dir);
|
||||
}
|
||||
|
||||
/// Over MCP the warnings are a text block after the image and the call's `structuredContent`.
|
||||
#[cfg(feature = "mcp")]
|
||||
#[test]
|
||||
|
||||
@@ -269,7 +269,9 @@ pub struct RenderedPage {
|
||||
/// A non-fatal condition reported while interpreting a page.
|
||||
#[derive(Clone, Copy, Debug, PartialEq, Eq)]
|
||||
pub enum RenderWarning {
|
||||
/// Content was skipped after the per-page decoded-content budget was exhausted.
|
||||
/// Content was left out at one of the renderer's limits: content past the page's
|
||||
/// decoded-content budget or its JBIG2 allowance, or a picture whose JBIG2 mask is past a
|
||||
/// decoder limit.
|
||||
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.
|
||||
|
||||
@@ -4234,7 +4234,7 @@ fn inline_images_with_ei_in_their_data_parse_in_linear_time() {
|
||||
/// From the nightly `cargo xtask fuzz`: a JBIG2 image whose stream declares a page and a
|
||||
/// generic region of 65535 × 65535 pixels (each side within JBIG2's limit) behind a small
|
||||
/// /Width and /Height: decoding its 4.3 billion pixels one by one took minutes. Vendored
|
||||
/// hayro-jbig2 patch: at most 2^28 pixels per bitmap, and 2^26 per symbol dictionary.
|
||||
/// hayro-jbig2 patch: at most 2^28 pixels per bitmap, and as many per symbol dictionary.
|
||||
#[test]
|
||||
fn jbig2_regions_of_billions_of_pixels_are_refused() {
|
||||
// Embedded JBIG2 segments (ISO 14492 §7.2): page information, then an immediate generic
|
||||
@@ -4302,9 +4302,14 @@ fn jbig2_segment(out: &mut Vec<u8>, number: u32, kind: u8, refs: &[u8], data: &[
|
||||
/// The page information of a 16 × 2 JBIG2 page whose default pixel is black, so that the image, if
|
||||
/// it decodes, draws black whatever its other segments hold.
|
||||
fn black_jbig2_page() -> Vec<u8> {
|
||||
black_jbig2_page_of(16, 2)
|
||||
}
|
||||
|
||||
/// [`black_jbig2_page`], `width` × `height`.
|
||||
fn black_jbig2_page_of(width: u32, height: u32) -> Vec<u8> {
|
||||
let mut page = Vec::new();
|
||||
page.extend_from_slice(&16u32.to_be_bytes());
|
||||
page.extend_from_slice(&2u32.to_be_bytes());
|
||||
page.extend_from_slice(&width.to_be_bytes());
|
||||
page.extend_from_slice(&height.to_be_bytes());
|
||||
page.extend_from_slice(&[0; 8]); // resolution
|
||||
page.extend_from_slice(&[4, 0, 0]); // flags (default pixel black), striping
|
||||
let mut stream = Vec::new();
|
||||
@@ -4495,6 +4500,289 @@ fn a_picture_whose_jbig2_mask_is_past_the_pages_allowance_is_not_drawn() {
|
||||
assert_eq!(other, (true, false), "and a page with nothing left says nothing of a mask that isn't JBIG2");
|
||||
}
|
||||
|
||||
/// A symbol dictionary may hold as many pixels as the largest page bitmap. It was held to a
|
||||
/// quarter of that, and the soft mask of a scanned drawing, one dictionary of 7,559 symbols, passed
|
||||
/// it: refused, the mask left its picture drawn whole, which covered the page in noise (#6722).
|
||||
#[test]
|
||||
fn a_symbol_dictionary_holds_as_many_pixels_as_a_page() {
|
||||
let stream = |heights: &[u32]| {
|
||||
let mut stream = black_jbig2_page();
|
||||
jbig2_segment(&mut stream, 1, 0, &[], &wide_jbig2_dictionary(65535, heights));
|
||||
stream
|
||||
};
|
||||
assert!(jbig2_image_draws(&stream(&[1100])), "72,088,500 pixels, past 2^26");
|
||||
assert!(jbig2_image_draws(&stream(&[2047, 2048])), "268,365,825 pixels, within 2^28");
|
||||
assert!(!jbig2_image_draws(&stream(&[2048, 2049])), "268,496,895 pixels, past 2^28");
|
||||
}
|
||||
|
||||
/// A JBIG2 mask one of the decoder's limits refuses takes its picture with it, as one left out for
|
||||
/// the page's allowance does: the file isn't to blame, and a scan's colour layer drawn without its
|
||||
/// mask covers the page in noise (#6722). A mask the file damaged leaves its picture whole, as
|
||||
/// upstream draws it. A size the file damaged can read as past a limit, and is taken for one.
|
||||
#[test]
|
||||
fn a_picture_whose_jbig2_mask_a_decoder_limit_refuses_is_not_drawn() {
|
||||
let draws = |entry: &str, (width, height): (u32, u32), mask: &[u8]| {
|
||||
let content = b"q 20 0 0 20 5 5 cm /Im1 Do Q";
|
||||
let mut pdf = b"%PDF-1.7\n1 0 obj << /Type /Catalog /Pages 2 0 R >> endobj\n2 0 obj << /Type /Pages /Kids [3 0 R] /Count 1 >> endobj\n3 0 obj << /Type /Page /Parent 2 0 R /MediaBox [0 0 40 40] /Contents 4 0 R /Resources << /XObject << /Im1 5 0 R >> >> >> endobj\n".to_vec();
|
||||
pdf.extend_from_slice(format!("4 0 obj << /Length {} >> stream\n", content.len()).as_bytes());
|
||||
pdf.extend_from_slice(content);
|
||||
pdf.extend_from_slice(b"\nendstream endobj\n");
|
||||
pdf.extend_from_slice(
|
||||
format!("5 0 obj << /Type /XObject /Subtype /Image /Width 1 /Height 1 /BitsPerComponent 8 /ColorSpace /DeviceGray {entry} 6 0 R /Length 1 >> stream\n\0\nendstream endobj\n").as_bytes(),
|
||||
);
|
||||
let kind = if entry == "/Mask" { "/ImageMask true" } else { "/ColorSpace /DeviceGray" };
|
||||
pdf.extend_from_slice(
|
||||
format!(
|
||||
"6 0 obj << /Type /XObject /Subtype /Image /Width {width} /Height {height} /BitsPerComponent 1 {kind} /Filter /JBIG2Decode /Length {} >> stream\n",
|
||||
mask.len()
|
||||
)
|
||||
.as_bytes(),
|
||||
);
|
||||
pdf.extend_from_slice(mask);
|
||||
pdf.extend_from_slice(b"\nendstream endobj\ntrailer << /Root 1 0 R >>\n%%EOF\n");
|
||||
let page = PageRenderer::new(Arc::new(pdf), RenderConfig::default()).render(RenderRequest {
|
||||
page: 0,
|
||||
kind: RequestKind::Pixels,
|
||||
tile: None,
|
||||
scale: 1.0,
|
||||
tag: 0,
|
||||
..Default::default()
|
||||
});
|
||||
assert!(page.error.is_none(), "{:?}", page.error);
|
||||
let shown = match &page.rgba[((25 * 40 + 15) * 4)..][..4] {
|
||||
[0, 0, 0, 255] => true,
|
||||
[255, 255, 255, 255] => false,
|
||||
other => panic!("neither the picture nor the page: {other:?}"),
|
||||
};
|
||||
(shown, page.warnings.contains(&RenderWarning::ContentTruncated))
|
||||
};
|
||||
let out = (false, true);
|
||||
// A page a column wider than the decoder's bound on a side, as the mask's dictionary says too.
|
||||
let wide = black_jbig2_page_of(65536, 2);
|
||||
assert_eq!(draws("/SMask", (65536, 2), &wide), out, "a soft mask past the decoder's bound on a side");
|
||||
assert_eq!(draws("/Mask", (65536, 2), &wide), out, "a stencil mask past it");
|
||||
// A page of 65,535 rows and columns, past the pixels the renderer decodes, as the dictionary
|
||||
// says too.
|
||||
let large = black_jbig2_page_of(65535, 65535);
|
||||
assert_eq!(draws("/SMask", (65535, 65535), &large), out, "a soft mask past the renderer's bound on pixels");
|
||||
assert_eq!(draws("/Mask", (65535, 65535), &large), out, "a stencil mask past it");
|
||||
// A dictionary of more symbol pixels than a page holds.
|
||||
let mut dictionary = black_jbig2_page();
|
||||
jbig2_segment(&mut dictionary, 1, 0, &[], &wide_jbig2_dictionary(65535, &[2048, 2049]));
|
||||
assert_eq!(draws("/SMask", (16, 2), &dictionary), out, "a soft mask whose dictionary is past its bound");
|
||||
// Cut short in its dictionary: the file's damage, not a limit.
|
||||
let mut damaged = black_jbig2_page();
|
||||
jbig2_segment(&mut damaged, 1, 0, &[], &wide_jbig2_dictionary(100, &[100])[..12]);
|
||||
assert_eq!(draws("/SMask", (16, 2), &damaged), (true, false), "a damaged mask is no mask");
|
||||
// Control: the stream's page is far larger than the dictionary says. That is damage, which
|
||||
// reads as past the decoder's bound on pixels, and is taken for it: it can't be told from a
|
||||
// hostile size, and leaving the picture out is the safe side.
|
||||
let disagreeing = black_jbig2_page_of(65535, 65535);
|
||||
assert_eq!(draws("/SMask", (16, 2), &disagreeing), out, "a size damaged past a limit is taken for one");
|
||||
|
||||
// A stencil mask a limit refused is drawn on its own: it takes nothing else out, and is a
|
||||
// failed image, not content left out (`a_jbig2_image_drawn_on_its_own_that_a_limit_refuses_is_a_failed_image`).
|
||||
// Nor does it leave anything behind for the next picture: one whose mask is never decoded (it
|
||||
// has no /Width) is drawn whole, as upstream draws it.
|
||||
let content = b"q 4 0 0 4 30 30 cm /St Do Q q 20 0 0 20 5 5 cm /Im1 Do Q";
|
||||
let mut pdf = b"%PDF-1.7\n1 0 obj << /Type /Catalog /Pages 2 0 R >> endobj\n2 0 obj << /Type /Pages /Kids [3 0 R] /Count 1 >> endobj\n3 0 obj << /Type /Page /Parent 2 0 R /MediaBox [0 0 40 40] /Contents 4 0 R /Resources << /XObject << /Im1 5 0 R /St 7 0 R >> >> >> endobj\n".to_vec();
|
||||
pdf.extend_from_slice(format!("4 0 obj << /Length {} >> stream\n", content.len()).as_bytes());
|
||||
pdf.extend_from_slice(content);
|
||||
pdf.extend_from_slice(b"\nendstream endobj\n5 0 obj << /Type /XObject /Subtype /Image /Width 1 /Height 1 /BitsPerComponent 8 /ColorSpace /DeviceGray /SMask 6 0 R /Length 1 >> stream\n\0\nendstream endobj\n");
|
||||
let mask = black_jbig2_page();
|
||||
pdf.extend_from_slice(format!("6 0 obj << /Type /XObject /Subtype /Image /Height 2 /BitsPerComponent 1 /ColorSpace /DeviceGray /Filter /JBIG2Decode /Length {} >> stream\n", mask.len()).as_bytes());
|
||||
pdf.extend_from_slice(&mask);
|
||||
pdf.extend_from_slice(format!("\nendstream endobj\n7 0 obj << /Type /XObject /Subtype /Image /Width 65536 /Height 2 /ImageMask true /Filter /JBIG2Decode /Length {} >> stream\n", wide.len()).as_bytes());
|
||||
pdf.extend_from_slice(&wide);
|
||||
pdf.extend_from_slice(b"\nendstream endobj\ntrailer << /Root 1 0 R >>\n%%EOF\n");
|
||||
let page = PageRenderer::new(Arc::new(pdf), RenderConfig::default()).render(RenderRequest {
|
||||
page: 0,
|
||||
kind: RequestKind::Pixels,
|
||||
tile: None,
|
||||
scale: 1.0,
|
||||
tag: 0,
|
||||
..Default::default()
|
||||
});
|
||||
assert!(page.error.is_none(), "{:?}", page.error);
|
||||
assert_eq!(&page.rgba[((25 * 40 + 15) * 4)..][..4], [0, 0, 0, 255], "the picture after the stencil is drawn whole");
|
||||
assert!(page.warnings.is_empty(), "the stencil left nothing out: {:?}", page.warnings);
|
||||
}
|
||||
|
||||
/// A JBIG2 image drawn on its own that a limit refuses, a stencil mask included, takes nothing else
|
||||
/// out, so it is a failed image, as it was before #6722: only a picture's mask refused by a limit
|
||||
/// is reported as content left out, with the picture it takes along (patch 73). Refused by the
|
||||
/// decoder's bound on a side or by the renderer's bound on pixels, each image's `/Width` and
|
||||
/// `/Height` those of its JBIG2 page.
|
||||
#[test]
|
||||
fn a_jbig2_image_drawn_on_its_own_that_a_limit_refuses_is_a_failed_image() {
|
||||
use hayro::hayro_interpret::font::Glyph;
|
||||
use hayro::hayro_interpret::hayro_syntax::Pdf;
|
||||
use hayro::hayro_interpret::{
|
||||
BlendMode, ClipPath, Context, Device, GlyphDrawMode, Image, InterpreterCache, InterpreterSettings, Paint, PathDrawMode, SoftMask,
|
||||
TransformExt, interpret_page,
|
||||
};
|
||||
use kurbo::{Affine, BezPath, Rect};
|
||||
|
||||
/// Asks each image for its pixels, which decodes it, and draws nothing.
|
||||
struct Pixels;
|
||||
impl<'a> Device<'a> for Pixels {
|
||||
fn set_soft_mask(&mut self, _: Option<SoftMask<'a>>) {}
|
||||
fn set_blend_mode(&mut self, _: BlendMode) {}
|
||||
fn draw_path(&mut self, _: &BezPath, _: Affine, _: &Paint<'a>, _: &PathDrawMode) {}
|
||||
fn push_clip_path(&mut self, _: &ClipPath) {}
|
||||
fn push_transparency_group(&mut self, _: f32, _: Option<SoftMask<'a>>, _: BlendMode) {}
|
||||
fn draw_glyph(&mut self, _: &Glyph<'a>, _: Affine, _: Affine, _: &Paint<'a>, _: &GlyphDrawMode) {}
|
||||
fn draw_image(&mut self, image: Image<'a, '_>, _: Affine) {
|
||||
match image {
|
||||
Image::Raster(r) => r.with_rgba(|_, _| {}, Some((20, 20))),
|
||||
Image::Stencil(s) => s.with_stencil(|_, _| {}, Some((20, 20))),
|
||||
}
|
||||
}
|
||||
fn pop_clip_path(&mut self) {}
|
||||
fn pop_transparency_group(&mut self) {}
|
||||
}
|
||||
|
||||
// The warnings drawing one image reports.
|
||||
let warnings = |kind: &str, (width, height): (u32, u32)| {
|
||||
let stream = black_jbig2_page_of(width, height);
|
||||
let content = "q 20 0 0 20 5 5 cm /Im Do Q";
|
||||
let mut pdf = format!(
|
||||
"%PDF-1.7\n1 0 obj << /Type /Catalog /Pages 2 0 R >> endobj\n2 0 obj << /Type /Pages /Kids [3 0 R] /Count 1 >> endobj\n3 0 obj << /Type /Page /Parent 2 0 R /MediaBox [0 0 40 40] /Contents 4 0 R /Resources << /XObject << /Im 5 0 R >> >> >> endobj\n4 0 obj << /Length {} >> stream\n{content}\nendstream endobj\n5 0 obj << /Type /XObject /Subtype /Image /Width {width} /Height {height} {kind} /Filter /JBIG2Decode /Length {} >> stream\n",
|
||||
content.len(),
|
||||
stream.len()
|
||||
)
|
||||
.into_bytes();
|
||||
pdf.extend_from_slice(&stream);
|
||||
pdf.extend_from_slice(b"\nendstream endobj\ntrailer << /Root 1 0 R >>\n%%EOF\n");
|
||||
let pdf = Pdf::new(Arc::new(pdf)).expect("parses");
|
||||
let page = &pdf.pages()[0];
|
||||
let cache = InterpreterCache::new();
|
||||
let reported = Arc::new(Mutex::new(Vec::new()));
|
||||
let settings = InterpreterSettings {
|
||||
warning_sink: {
|
||||
let reported = reported.clone();
|
||||
Arc::new(move |warning| reported.lock().unwrap().push(format!("{warning:?}")))
|
||||
},
|
||||
..InterpreterSettings::default()
|
||||
};
|
||||
let mut ctx = Context::new(page.initial_transform(true).to_kurbo(), Rect::new(0.0, 0.0, 40.0, 40.0), &cache, page.xref(), settings);
|
||||
interpret_page(page, &mut ctx, &mut Pixels);
|
||||
reported.lock().unwrap().clone()
|
||||
};
|
||||
let stencil = "/ImageMask true";
|
||||
let raster = "/BitsPerComponent 1 /ColorSpace /DeviceGray";
|
||||
let failed = ["ImageDecodeFailure"];
|
||||
assert_eq!(warnings(stencil, (65536, 2)), failed, "a stencil mask past the decoder's bound on a side");
|
||||
assert_eq!(warnings(stencil, (65535, 65535)), failed, "a stencil mask past the renderer's bound on pixels");
|
||||
assert_eq!(warnings(raster, (65536, 2)), failed, "an image past the decoder's bound on a side");
|
||||
assert_eq!(warnings(raster, (65535, 65535)), failed, "an image past the renderer's bound on pixels");
|
||||
}
|
||||
|
||||
/// What refused one image says nothing of the next: after a picture one of the decoder's limits
|
||||
/// refused, a stencil mask and a soft mask whose filters fail before JBIG2 is reached (LZW data that
|
||||
/// doesn't decode) are bad, not refused by a limit, on that page and on the next. The decoder's
|
||||
/// note of the refusal was read before a decode had set it, and outlived its page: the stencil
|
||||
/// said content was left out, and the picture under the soft mask wasn't drawn.
|
||||
#[test]
|
||||
fn a_limit_refusal_says_nothing_of_the_next_image() {
|
||||
let refused = black_jbig2_page_of(65536, 2);
|
||||
let bad = [0xff; 64];
|
||||
let page = |number: u8, content: u8| {
|
||||
format!("{number} 0 obj << /Type /Page /Parent 2 0 R /MediaBox [0 0 40 40] /Contents {content} 0 R /Resources << /XObject << /Big 7 0 R /St 8 0 R /Im 9 0 R >> >> >> endobj\n").into_bytes()
|
||||
};
|
||||
let content = |number: u8, text: &str| format!("{number} 0 obj << /Length {} >> stream\n{text}\nendstream endobj\n", text.len()).into_bytes();
|
||||
let object = |number: u8, dict: &str, data: &[u8]| {
|
||||
let mut object = format!("{number} 0 obj << {dict} /Length {} >> stream\n", data.len()).into_bytes();
|
||||
object.extend_from_slice(data);
|
||||
object.extend_from_slice(b"\nendstream endobj\n");
|
||||
object
|
||||
};
|
||||
let mut pdf =
|
||||
b"%PDF-1.7\n1 0 obj << /Type /Catalog /Pages 2 0 R >> endobj\n2 0 obj << /Type /Pages /Kids [3 0 R 4 0 R] /Count 2 >> endobj\n".to_vec();
|
||||
pdf.extend(page(3, 5));
|
||||
pdf.extend(page(4, 6));
|
||||
pdf.extend(content(5, "q 10 0 0 10 30 30 cm /Big Do Q q 10 0 0 10 30 0 cm 0 g /St Do Q q 20 0 0 20 5 5 cm /Im Do Q"));
|
||||
pdf.extend(content(6, "q 10 0 0 10 30 0 cm 0 g /St Do Q q 20 0 0 20 5 5 cm /Im Do Q"));
|
||||
pdf.extend(object(
|
||||
7,
|
||||
"/Type /XObject /Subtype /Image /Width 65536 /Height 2 /BitsPerComponent 1 /ColorSpace /DeviceGray /Filter /JBIG2Decode",
|
||||
&refused,
|
||||
));
|
||||
pdf.extend(object(8, "/Type /XObject /Subtype /Image /Width 16 /Height 2 /ImageMask true /Filter [/LZWDecode /JBIG2Decode]", &bad));
|
||||
pdf.extend(object(9, "/Type /XObject /Subtype /Image /Width 1 /Height 1 /BitsPerComponent 8 /ColorSpace /DeviceGray /SMask 10 0 R", &[0]));
|
||||
pdf.extend(object(
|
||||
10,
|
||||
"/Type /XObject /Subtype /Image /Width 16 /Height 2 /BitsPerComponent 1 /ColorSpace /DeviceGray /Filter [/LZWDecode /JBIG2Decode]",
|
||||
&bad,
|
||||
));
|
||||
pdf.extend_from_slice(b"trailer << /Root 1 0 R >>\n%%EOF\n");
|
||||
// Both pages from one renderer, on one thread.
|
||||
let mut renderer = PageRenderer::new(Arc::new(pdf), RenderConfig::default());
|
||||
let [first, second] =
|
||||
[0, 1].map(|page| renderer.render(RenderRequest { page, kind: RequestKind::Pixels, tile: None, scale: 1.0, tag: 0, ..Default::default() }));
|
||||
let drawn = |page: &RenderedPage| {
|
||||
assert!(page.error.is_none(), "{:?}", page.error);
|
||||
(page.rgba[((25 * 40 + 15) * 4)..][..4] == [0, 0, 0, 255], page.warnings.contains(&RenderWarning::ContentTruncated))
|
||||
};
|
||||
// The next page first: on the page of the refusal, the stale note shows whether or not it
|
||||
// outlives the page.
|
||||
assert_eq!(drawn(&second), (true, false), "on the next page, the picture is drawn and nothing was left out");
|
||||
assert_eq!(drawn(&first), (true, false), "on its page, the picture is drawn and nothing was left out");
|
||||
}
|
||||
|
||||
/// A JPX picture is decoded again for each size a page draws it at, while a soft mask far larger
|
||||
/// than where it is drawn is averaged down once and kept for the sizes it serves (patch 82). A
|
||||
/// JBIG2 mask a decoder limit refused is kept refused, so the picture drawn at another size is left
|
||||
/// out again, not drawn whole because the mask wasn't decoded that time. The scans of #6722 are
|
||||
/// JPX under such a mask.
|
||||
#[test]
|
||||
fn a_jpx_picture_whose_jbig2_mask_a_limit_refuses_stays_out_at_every_size() {
|
||||
// A page a column wider than the decoder's bound on a side, as the mask's dictionary says too.
|
||||
let wide = black_jbig2_page_of(65536, 2);
|
||||
// A 64 × 64 grey JPX codestream, every sample 128 (as `jpx_midpoint_pdf`'s, larger): larger
|
||||
// than where it is drawn, it is decoded for each size it is drawn at.
|
||||
let mut codestream = vec![0xff, 0x4f, 0xff, 0x51, 0, 41, 0, 0]; // SOC, SIZ, Rsiz.
|
||||
for value in [64_u32, 64, 0, 0, 64, 64, 0, 0] {
|
||||
codestream.extend_from_slice(&value.to_be_bytes());
|
||||
}
|
||||
codestream.extend_from_slice(&[0, 1, 7, 1, 1]); // One component, eight bits.
|
||||
// COD: one decomposition level, so it decodes at half its size for a small target; QCD: no
|
||||
// quantization, the four subbands' exponents.
|
||||
codestream.extend_from_slice(&[0xff, 0x52, 0, 12, 0, 0, 0, 1, 0, 1, 4, 4, 0, 1]);
|
||||
codestream.extend_from_slice(&[0xff, 0x5c, 0, 7, 0x40, 0x40, 0x48, 0x48, 0x50]);
|
||||
codestream.extend_from_slice(&[0xff, 0x90, 0, 10, 0, 0, 0, 0, 0, 16, 0, 1, 0xff, 0x93, 0, 0]); // SOT, SOD, two empty packets.
|
||||
codestream.extend_from_slice(&[0xff, 0xd9]); // EOC.
|
||||
// At 10, 20 and 10 units square: the second draw is a new size for the picture.
|
||||
let content = b"q 10 0 0 10 2 2 cm /Im1 Do Q q 20 0 0 20 16 16 cm /Im1 Do Q q 10 0 0 10 2 28 cm /Im1 Do Q";
|
||||
let mut pdf = b"%PDF-1.7\n1 0 obj << /Type /Catalog /Pages 2 0 R >> endobj\n2 0 obj << /Type /Pages /Kids [3 0 R] /Count 1 >> endobj\n3 0 obj << /Type /Page /Parent 2 0 R /MediaBox [0 0 40 40] /Contents 4 0 R /Resources << /XObject << /Im1 5 0 R >> >> >> endobj\n".to_vec();
|
||||
pdf.extend_from_slice(format!("4 0 obj << /Length {} >> stream\n", content.len()).as_bytes());
|
||||
pdf.extend_from_slice(content);
|
||||
pdf.extend_from_slice(
|
||||
format!("\nendstream endobj\n5 0 obj << /Type /XObject /Subtype /Image /Width 64 /Height 64 /BitsPerComponent 8 /ColorSpace /DeviceGray /SMask 6 0 R /Filter /JPXDecode /Length {} >> stream\n", codestream.len())
|
||||
.as_bytes(),
|
||||
);
|
||||
pdf.extend_from_slice(&codestream);
|
||||
pdf.extend_from_slice(
|
||||
format!("\nendstream endobj\n6 0 obj << /Type /XObject /Subtype /Image /Width 65536 /Height 2 /BitsPerComponent 1 /ColorSpace /DeviceGray /Filter /JBIG2Decode /Length {} >> stream\n", wide.len())
|
||||
.as_bytes(),
|
||||
);
|
||||
pdf.extend_from_slice(&wide);
|
||||
pdf.extend_from_slice(b"\nendstream endobj\ntrailer << /Root 1 0 R >>\n%%EOF\n");
|
||||
let page = PageRenderer::new(Arc::new(pdf), RenderConfig::default()).render(RenderRequest {
|
||||
page: 0,
|
||||
kind: RequestKind::Pixels,
|
||||
tile: None,
|
||||
scale: 1.0,
|
||||
tag: 0,
|
||||
..Default::default()
|
||||
});
|
||||
assert!(page.error.is_none(), "{:?}", page.error);
|
||||
// The middle of each draw, in rows from the top.
|
||||
let shown = [(33, 7), (14, 26), (7, 7)].map(|(row, column)| page.rgba[(row * 40 + column) * 4..][..4] != [255, 255, 255, 255]);
|
||||
assert_eq!(shown, [false; 3], "drawn at 10, 20 and 10");
|
||||
assert!(page.warnings.contains(&RenderWarning::ContentTruncated));
|
||||
}
|
||||
|
||||
/// A page's allowance ends with it, so what decodes on its thread afterwards has no page to run out
|
||||
/// on, and a `Context` used again starts afresh.
|
||||
#[test]
|
||||
@@ -4747,6 +5035,40 @@ fn narrow_jbig2_dictionary(symbols: u32, height: u32) -> Vec<u8> {
|
||||
dictionary
|
||||
}
|
||||
|
||||
/// A Huffman-coded symbol dictionary of one white symbol of `width` columns in each height class
|
||||
/// of `heights` (rising), none exported: wide symbols hold many pixels in few retained words.
|
||||
fn wide_jbig2_dictionary(width: u32, heights: &[u32]) -> Vec<u8> {
|
||||
let mut bits = Bits::default();
|
||||
let mut previous = 0;
|
||||
for &height in heights {
|
||||
match height - previous {
|
||||
// Height class delta (table B.4): 1, or the upper line.
|
||||
1 => bits.put(0, 1),
|
||||
delta => {
|
||||
bits.put(0b11111, 5);
|
||||
bits.put(delta - 76, 32);
|
||||
}
|
||||
}
|
||||
previous = height;
|
||||
bits.put(0b111110, 6); // width delta, the upper line of table B.2
|
||||
bits.put(width - 75, 32);
|
||||
bits.put(0b111111, 6); // end of the class (B.2)
|
||||
let rows = height.div_ceil(8) + 1; // an MMR-coded white bitmap: one bit a row
|
||||
bits.table_b1(rows); // BMSIZE (B.1)
|
||||
bits.align();
|
||||
for _ in 0..rows {
|
||||
bits.put(0xFF, 8);
|
||||
}
|
||||
}
|
||||
let symbols = u32::try_from(heights.len()).unwrap();
|
||||
bits.table_b1(symbols); // the first export run, not exported, is all of them
|
||||
let mut dictionary = vec![0x00, 0x01]; // Huffman, tables B.4, B.2, B.1, B.1
|
||||
dictionary.extend_from_slice(&0u32.to_be_bytes()); // exported
|
||||
dictionary.extend_from_slice(&symbols.to_be_bytes()); // new
|
||||
dictionary.extend_from_slice(&bits.bytes);
|
||||
dictionary
|
||||
}
|
||||
|
||||
/// An intermediate generic region, white, every row typical: it decodes in a few bytes however
|
||||
/// large it is.
|
||||
fn jbig2_white_region(width: u32, height: u32) -> Vec<u8> {
|
||||
|
||||
@@ -237,3 +237,114 @@ fn a_picture_left_out_for_the_pages_allowance_draws_on_the_next_page() {
|
||||
assert!(black(&second, 10) && black(&second, 30), "A, and B left out of the first page, draw on the second");
|
||||
assert!(second.1.is_empty(), "{:?}", second.1);
|
||||
}
|
||||
|
||||
/// A JBIG2 mask its decoding work refuses: four typical-row regions of 16,384 × 16,384 take more
|
||||
/// than a stream may.
|
||||
fn jbig2_mask_past_its_work() -> Vec<u8> {
|
||||
use super::{black_jbig2_page, jbig2_segment, jbig2_white_region};
|
||||
let mut mask = black_jbig2_page();
|
||||
for number in 1..=4 {
|
||||
jbig2_segment(&mut mask, number, 38, &[], &jbig2_white_region(16384, 16384)); // immediate generic region
|
||||
}
|
||||
mask
|
||||
}
|
||||
|
||||
/// What drawing 64 × 64 pictures under JBIG2 soft masks did, with the page's JBIG2 allowance
|
||||
/// `work`: `/P` under `mask` (`/Width` × `/Height` `size`) and `/W` under
|
||||
/// [`jbig2_mask_past_its_work`], each of `draws` a name and a size (units square). The decodes the
|
||||
/// cache ran, how many times content was said to be left out, and what the device was handed.
|
||||
fn draw_under_jbig2_masks(mask: &[u8], size: (u32, u32), draws: &[(&str, u32)], work: u64) -> (usize, usize, Draws) {
|
||||
let pixels = vec![0; 64 * 64 * 3];
|
||||
let picture = |mask: u8| {
|
||||
format!(
|
||||
"<< /Type /XObject /Subtype /Image /Width 64 /Height 64 /ColorSpace /DeviceRGB /BitsPerComponent 8 /SMask {mask} 0 R /Length {} >>",
|
||||
pixels.len()
|
||||
)
|
||||
};
|
||||
let soft_mask = |(width, height): (u32, u32), data: &[u8]| {
|
||||
format!(
|
||||
"<< /Type /XObject /Subtype /Image /Width {width} /Height {height} /ColorSpace /DeviceGray /BitsPerComponent 1 /Filter /JBIG2Decode /Length {} >>",
|
||||
data.len()
|
||||
)
|
||||
};
|
||||
let past_its_work = jbig2_mask_past_its_work();
|
||||
let content = draws.iter().map(|(name, s)| format!("q {s} 0 0 {s} 10 10 cm /{name} Do Q")).collect::<Vec<_>>().join(" ");
|
||||
let bytes = image_cache_pdf(
|
||||
&content,
|
||||
"<< /XObject << /P 5 0 R /W 7 0 R >> >>",
|
||||
&[(&picture(6), &pixels), (&soft_mask(size, mask), mask), (&picture(8), &pixels), (&soft_mask((16, 2), &past_its_work), &past_its_work)],
|
||||
);
|
||||
let parsed = Pdf::new(Arc::new(bytes)).expect("parses");
|
||||
let page = &parsed.pages()[0];
|
||||
let cache = InterpreterCache::new();
|
||||
let truncated = Arc::new(AtomicUsize::new(0));
|
||||
let others = Arc::new(Mutex::new(Vec::new()));
|
||||
let settings = InterpreterSettings {
|
||||
warning_sink: {
|
||||
let (truncated, others) = (truncated.clone(), others.clone());
|
||||
Arc::new(move |warning| match warning {
|
||||
InterpreterWarning::ContentTruncated => {
|
||||
truncated.fetch_add(1, Ordering::Relaxed);
|
||||
}
|
||||
other => others.lock().unwrap().push(format!("{other:?}")),
|
||||
})
|
||||
},
|
||||
jbig2_work: work,
|
||||
..InterpreterSettings::default()
|
||||
};
|
||||
let initial = page.initial_transform(true).to_kurbo();
|
||||
let mut ctx = Context::new(initial, Rect::new(0.0, 0.0, 130.0, 70.0), &cache, page.xref(), settings);
|
||||
let mut device = Draws::default();
|
||||
interpret_page(page, &mut ctx, &mut device);
|
||||
assert!(others.lock().unwrap().is_empty(), "reported {:?}", others.lock().unwrap());
|
||||
(cache.decoded_image_decodes(), truncated.load(Ordering::Relaxed), device)
|
||||
}
|
||||
|
||||
/// A picture whose JBIG2 soft mask a decoder limit refuses isn't drawn (patch 73), and the limit
|
||||
/// is the stream's own: decoding it again refuses it again. So the refusal is kept with the picture
|
||||
/// that went with it (patch 91), and a page drawing it a hundred times decodes them once, as for
|
||||
/// one draw. Kept as content left out, every draw still says so. The refusal wasn't kept, and the
|
||||
/// picture, of any size, was decoded again at every draw: 2.45 s for a hundred draws of a 4,096 ×
|
||||
/// 4,096 JPX picture, against 0.23 s under a mask the file damaged. A mask larger than its picture
|
||||
/// is averaged down for each size it is drawn at, from one kept at an intermediate size (patch 82),
|
||||
/// so a second size finds the refusal kept there and keeps it for that size too, also after
|
||||
/// another picture's mask was refused for its work, which isn't kept.
|
||||
#[test]
|
||||
fn a_picture_whose_jbig2_mask_a_limit_refuses_is_decoded_once_however_often_it_is_drawn() {
|
||||
use super::{black_jbig2_page, black_jbig2_page_of, jbig2_segment, wide_jbig2_dictionary};
|
||||
let mut dictionary = black_jbig2_page();
|
||||
jbig2_segment(&mut dictionary, 1, 0, &[], &wide_jbig2_dictionary(65535, &[2048, 2049]));
|
||||
let masks = [
|
||||
("past the decoder's bound on a side", black_jbig2_page_of(65536, 2), (65536, 2)),
|
||||
("past the renderer's bound on pixels", black_jbig2_page_of(65535, 65535), (65535, 65535)),
|
||||
("whose dictionary is past its bound", dictionary, (16, 2)),
|
||||
];
|
||||
let work = InterpreterSettings::default().jbig2_work;
|
||||
for (what, mask, size) in masks {
|
||||
let (once, _, _) = draw_under_jbig2_masks(&mask, size, &[("P", 20)], work);
|
||||
let (decodes, truncated, draws) = draw_under_jbig2_masks(&mask, size, &[("P", 20); 100], work);
|
||||
assert_eq!(draws.rasters, 0, "a mask {what} leaves the picture out");
|
||||
assert_eq!(decodes, once, "a mask {what}: a hundred draws decode as one does");
|
||||
assert_eq!(truncated, 100, "a mask {what}: every draw says content was left out");
|
||||
// With no page allowance to run out of, so that the mask past its work is refused by its
|
||||
// own limit and the page's allowance doesn't stop what is kept.
|
||||
let each = [("P", 20), ("W", 20), ("P", 40)];
|
||||
let (once_each, _, _) = draw_under_jbig2_masks(&mask, size, &each, u64::MAX);
|
||||
let (decodes, _, draws) = draw_under_jbig2_masks(&mask, size, &[&each[..], &[("P", 40); 2]].concat(), u64::MAX);
|
||||
assert_eq!(draws.rasters, 0, "a mask {what} leaves the picture out at either size");
|
||||
assert_eq!(decodes, once_each, "a mask {what}: drawn again at its second size, decoded as once at each");
|
||||
}
|
||||
}
|
||||
|
||||
/// A JBIG2 mask refused for the work its decoding takes isn't kept: that work may be what its page
|
||||
/// had left, which another page has afresh. So the picture under it is decoded at every draw, here
|
||||
/// with no page allowance to run out of, where the stream's own limit is what refuses it.
|
||||
#[test]
|
||||
fn a_picture_whose_jbig2_mask_is_refused_for_its_work_is_decoded_at_every_draw() {
|
||||
let mask = super::black_jbig2_page();
|
||||
let (once, _, _) = draw_under_jbig2_masks(&mask, (16, 2), &[("W", 20)], u64::MAX);
|
||||
let (decodes, truncated, draws) = draw_under_jbig2_masks(&mask, (16, 2), &[("W", 20); 3], u64::MAX);
|
||||
assert_eq!(draws.rasters, 0, "the picture is left out");
|
||||
assert_eq!(decodes, 3 * once, "decoded at every draw");
|
||||
assert_eq!(truncated, 3, "every draw says content was left out");
|
||||
}
|
||||
Vendored
+3
-3
@@ -39,11 +39,11 @@ 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 (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
|
||||
| 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 as many symbol pixels per symbol dictionary as the largest page bitmap holds, 2^28 (a fuzzed dictionary decoded for minutes; each symbol now pays for its pixels out of the stream's decoding work and is held in the retained bitmaps, and at the earlier 2^26 the soft mask of a scanned drawing, one dictionary of 7,559 symbols, was refused: #6722), and a refusal by one of the decoder's limits is told apart from damaged data (`DecodeError::is_limit`, `OverflowError::BitmapLimit`); (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 Line 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` |
|
||||
| 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::vendor_provenance_egui_wgpu_surface_fit_identity`, 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::vendor_provenance_egui_wgpu_catch_errors_identity`, 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; (2) `StripStorage::room_for_path{,_within}`: whether one more path's coverage (at most the whole surface, counted twice) still fits below 2^31 values, the most a strip's packed alpha index reaches (`Strip::new` asserts it), or below a smaller limit; (4) `flatten::stroke`: when kurbo 0.13.1's stroker returns an outline containing NaN, which `fill` would drop whole, the path is stroked again from a copy (`robust_for_stroking`, one element out per element in) in which each curve whose control points lie within the stroke tolerance of its chord is a line (the #4907 fix, a nearly straight cubic given a NaN join, kurbo issues #617 and #519; its row here was lost in a merge and is restored with this entry) and each cubic whose second control point is its end point, as `y` builds (ISO 32000-2 §8.5.2.1 Table 58), has that control point moved the tolerance towards its first (`open_zero_end_handle`; the curve moves by at most 4/9 of the tolerance): kurbo's cusp search on such a curve's offset can stop on the end point, where the derivative is zero, and normalising it gives NaN, so at 16, 32 and 63 pt a two-curve `y` path drew nothing and a file in the PDFBox tracker lost its 32 pt "XX" outline. Only an exact zero triggers it (none of 192,000 random strokes with a handle 1e-9 long, nor of 256,000 `v` strokes, came back with NaN; 1,073 of 192,000 random `y`/`v` strokes at 1–64 pt did before and none after). A finite outline takes the old path unchanged | (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; (2) `strip_generator::pdfcraft_tests::strips_have_room_until_a_surface_short_of_the_limit`; (4) `flatten::tests::a_tiny_degenerate_cubic_does_not_drop_the_stroke` and the render crate's `stroke_degenerate_cubic` fail without the near-line replacement, `flatten::tests::a_wide_stroke_of_a_curve_with_a_zero_end_tangent_is_drawn` (widths 1–64, every join and cap, `y` and the mirrored `v`) and the render crate's `stroke_zero_end_tangent` fail without the moved control point; `a_finite_outline_is_stroked_as_before` and `a_path_with_nan_is_still_dropped` pass either way |
|
||||
|
||||
Vendored
+31
-5
@@ -93,7 +93,10 @@ impl Cache {
|
||||
/// and gets nothing, as the decode did. A failure counts [`FAILED_DECODE_BYTES`] towards the
|
||||
/// budget, so failures can't grow the map without bound either. A failure that may come from
|
||||
/// what the page had left (its JBIG2 allowance, `ContentTruncated`) isn't kept: another page,
|
||||
/// or the same page drawn again, starts with a fresh allowance.
|
||||
/// or the same page drawn again, starts with a fresh allowance. One that left out a JBIG2 mask
|
||||
/// for a limit its stream reaches by itself is kept, with the image it takes along (patch 73,
|
||||
/// [`note_stream_limited`]): decoding them again would only refuse them again, and an image of
|
||||
/// any size under such a mask was decoded again at every draw.
|
||||
#[derive(Clone)]
|
||||
pub(crate) struct DecodedImageCache {
|
||||
inner: Arc<Mutex<DecodedImageCacheInner>>,
|
||||
@@ -142,6 +145,26 @@ pub(crate) struct DecodedImageKey {
|
||||
/// entry take in the map.
|
||||
const FAILED_DECODE_BYTES: usize = 128;
|
||||
|
||||
/// PdfCraft patch (91): with the warnings of a failure kept, that it left out a JBIG2 mask for a
|
||||
/// limit its stream reaches by itself ([`note_stream_limited`]); no warning's flag.
|
||||
const STREAM_LIMITED: u8 = 128;
|
||||
|
||||
std::thread_local! {
|
||||
static LEFT_OUT_BY_STREAM_LIMIT: std::cell::Cell<bool> = const { std::cell::Cell::new(false) };
|
||||
}
|
||||
|
||||
/// PdfCraft patch (73): note, wherever a decode reports `ContentTruncated` for an image or a kept
|
||||
/// failure replays it, whether that left out a JBIG2 mask for a limit its stream reaches by itself
|
||||
/// (`hayro_syntax::jbig2_limited_by_stream`): its failure, and the failure of the image it takes
|
||||
/// along, is then the stream's to keep, since decoding it again refuses it again.
|
||||
pub(crate) fn note_stream_limited(limited: bool) {
|
||||
LEFT_OUT_BY_STREAM_LIMIT.with(|left_out| left_out.set(limited));
|
||||
}
|
||||
|
||||
fn stream_limited() -> bool {
|
||||
LEFT_OUT_BY_STREAM_LIMIT.with(std::cell::Cell::get)
|
||||
}
|
||||
|
||||
/// PdfCraft patch (91): what a [`DecodedImageCache`] keeps for a key.
|
||||
enum DecodedEntry {
|
||||
/// The decoded image.
|
||||
@@ -244,6 +267,7 @@ impl DecodedImageCache {
|
||||
match hit {
|
||||
Some(Ok(hit)) => return Some(hit),
|
||||
Some(Err(bits)) => {
|
||||
note_stream_limited(bits & STREAM_LIMITED != 0);
|
||||
warnings_in(bits).for_each(|warning| sink(warning));
|
||||
return None;
|
||||
}
|
||||
@@ -278,12 +302,12 @@ impl DecodedImageCache {
|
||||
Some(DecodedEntry::Failed(_)) if val.is_none() => return None,
|
||||
_ => {}
|
||||
}
|
||||
let truncated = reported & warning_bit(InterpreterWarning::ContentTruncated) != 0;
|
||||
let size = match &val {
|
||||
Some(v) => size_of(v),
|
||||
// A failure the page's JBIG2 allowance may have caused isn't the image's to keep.
|
||||
None if reported & warning_bit(InterpreterWarning::ContentTruncated) != 0
|
||||
|| hayro_syntax::page_jbig2_work_spent() =>
|
||||
{
|
||||
// A failure the page's JBIG2 allowance may have caused isn't the image's to keep, nor
|
||||
// one a JBIG2 decode's work did, which may be the page's too.
|
||||
None if hayro_syntax::page_jbig2_work_spent() || (truncated && !stream_limited()) => {
|
||||
return None;
|
||||
}
|
||||
None => FAILED_DECODE_BYTES,
|
||||
@@ -297,6 +321,8 @@ impl DecodedImageCache {
|
||||
}
|
||||
let entry = match &val {
|
||||
Some(val) => DecodedEntry::Decoded(Box::new(val.clone())),
|
||||
// Here only when a limit of its stream refused the mask that left it out (above).
|
||||
None if truncated => DecodedEntry::Failed(reported | STREAM_LIMITED),
|
||||
None => DecodedEntry::Failed(reported),
|
||||
};
|
||||
// An entry replaced (a failure another thread kept) isn't given back: the budget
|
||||
|
||||
+2
@@ -168,6 +168,8 @@ pub enum InterpreterWarning {
|
||||
/// An image failed to decode.
|
||||
ImageDecodeFailure,
|
||||
/// PdfCraft patch (18): a page content stream was skipped after exhausting its safety budget.
|
||||
/// Patch (73): or an image was left out for the page's JBIG2 allowance, or because its JBIG2
|
||||
/// mask is past the allowance or one of the decoder's limits.
|
||||
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
|
||||
|
||||
+55
-6
@@ -24,6 +24,8 @@ use smallvec::{SmallVec, smallvec};
|
||||
use std::borrow::Cow;
|
||||
use std::iter;
|
||||
use std::ops::Deref;
|
||||
use std::sync::Arc;
|
||||
use std::sync::atomic::{AtomicBool, Ordering};
|
||||
|
||||
pub(crate) enum XObject<'a> {
|
||||
FormXObject(FormXObject<'a>),
|
||||
@@ -495,6 +497,12 @@ pub(crate) struct ImageXObject<'a> {
|
||||
interpolate: bool,
|
||||
is_mask: bool,
|
||||
is_stencil_mask: bool,
|
||||
/// PdfCraft patch (73): whether this is a picture's soft mask or `/Mask`, not an image drawn
|
||||
/// on its own, by `Do` or inline, a stencil mask included. Only a picture's mask refused by a
|
||||
/// limit takes something out with it, and is reported so. A picture's mask is cached only
|
||||
/// averaged down (`shrunk_to`), which an image drawn on its own never is, so the two never
|
||||
/// share an entry and its warnings.
|
||||
masks_picture: bool,
|
||||
stream: Stream<'a>,
|
||||
transfer_function: Option<ActiveTransferFunction>,
|
||||
warning_sink: WarningSinkFn,
|
||||
@@ -523,6 +531,7 @@ impl<'a> ImageXObject<'a> {
|
||||
.get::<bool>(IM)
|
||||
.or_else(|| dict.get::<bool>(IMAGE_MASK))
|
||||
.unwrap_or(false);
|
||||
let masks_picture = is_mask;
|
||||
is_mask |= is_stencil_mask;
|
||||
|
||||
let mut default_space = None;
|
||||
@@ -607,6 +616,7 @@ impl<'a> ImageXObject<'a> {
|
||||
stream: stream.clone(),
|
||||
is_mask,
|
||||
is_stencil_mask,
|
||||
masks_picture,
|
||||
default_space,
|
||||
})
|
||||
}
|
||||
@@ -939,7 +949,16 @@ fn decode_context<'a>(
|
||||
// PdfCraft patch: images and masks over `MAX_IMAGE_PIXELS` are not decoded at all (the
|
||||
// renderer skips them anyway): a fuzzed `/W 4294967295` stencil mask allocated gigabytes here.
|
||||
if !image_size_ok(obj.width, obj.height) {
|
||||
(obj.warning_sink)(InterpreterWarning::ImageDecodeFailure);
|
||||
// PdfCraft patch (73): a picture's JBIG2 mask of a size this bound refuses is one a limit
|
||||
// refused, as when the decoder refuses it (below), and its size is the stream's own.
|
||||
// `ImageXObject::new` refuses a size of 0, so this is past the bound.
|
||||
let limited = obj.masks_picture && uses_jbig2(&obj.stream);
|
||||
crate::cache::note_stream_limited(limited);
|
||||
(obj.warning_sink)(if limited {
|
||||
InterpreterWarning::ContentTruncated
|
||||
} else {
|
||||
InterpreterWarning::ImageDecodeFailure
|
||||
});
|
||||
return None;
|
||||
}
|
||||
let dict = obj.stream.dict();
|
||||
@@ -958,13 +977,26 @@ fn decode_context<'a>(
|
||||
height: obj.height,
|
||||
};
|
||||
|
||||
// PdfCraft patch (73): what refused an image decoded before this one says nothing about it,
|
||||
// whether or not its filters reach JBIG2.
|
||||
hayro_syntax::clear_jbig2_limited();
|
||||
let decoded = obj
|
||||
.stream
|
||||
.decoded_image(&decode_params)
|
||||
.map_err(|_| {
|
||||
// PdfCraft patch (73): left out for the page's allowance, it is content the page's
|
||||
// budget skipped, which is reported, and no failure of this image.
|
||||
(obj.warning_sink)(if hayro_syntax::page_jbig2_work_spent() && uses_jbig2(&obj.stream) {
|
||||
// budget skipped, which is reported, and no failure of this image. So is a picture's
|
||||
// mask one of the decoder's limits refused, which takes the picture with it
|
||||
// (`decode_raster`).
|
||||
// Reported so, the decoded-image cache (patch 91) keeps the failure only when the
|
||||
// limit is one the stream reaches by itself, whatever the page had left.
|
||||
let limited = obj.masks_picture && hayro_syntax::jbig2_limited();
|
||||
let left_out =
|
||||
(hayro_syntax::page_jbig2_work_spent() || limited) && uses_jbig2(&obj.stream);
|
||||
crate::cache::note_stream_limited(
|
||||
left_out && obj.masks_picture && hayro_syntax::jbig2_limited_by_stream(),
|
||||
);
|
||||
(obj.warning_sink)(if left_out {
|
||||
InterpreterWarning::ContentTruncated
|
||||
} else {
|
||||
InterpreterWarning::ImageDecodeFailure
|
||||
@@ -1197,6 +1229,20 @@ fn decode_raster(
|
||||
|
||||
let mut image = image_data?;
|
||||
|
||||
// PdfCraft patch (73): whether the mask, decoded below or kept failed by the decoded-image
|
||||
// cache, was left out for the page's allowance or a decoder's limit: only those report
|
||||
// `ContentTruncated` there (`decode_context`).
|
||||
let left_out = Arc::new(AtomicBool::new(false));
|
||||
let sink: WarningSinkFn = {
|
||||
let (left_out, sink) = (left_out.clone(), obj.warning_sink.clone());
|
||||
Arc::new(move |warning| {
|
||||
if matches!(warning, InterpreterWarning::ContentTruncated) {
|
||||
left_out.store(true, Ordering::Relaxed);
|
||||
}
|
||||
sink(warning);
|
||||
})
|
||||
};
|
||||
let obj = &obj.reporting_to(&sink);
|
||||
let alpha = if let Some((alpha, matte_rgb)) =
|
||||
resolve_matte(obj, &ctx.color_space, target_dimension)
|
||||
&& alpha.width == ctx.width
|
||||
@@ -1223,11 +1269,14 @@ fn decode_raster(
|
||||
};
|
||||
|
||||
// PdfCraft patch (73): a bad mask leaves the image as it is, but one left out for the page's
|
||||
// allowance takes the image with it. Both are reported, and only here is the file not to blame
|
||||
// for what the mask would have hidden being shown.
|
||||
// allowance, or refused by one of the decoder's limits, takes the image with it. Both are
|
||||
// reported, and only there is the file not to blame for what the mask would have hidden being
|
||||
// shown: a scan's colour layer drawn without its JBIG2 mask covers the page in noise (#6722).
|
||||
// A size or count the file damaged can read as past a limit, and is taken for one: it can't
|
||||
// be told from a hostile one, and leaving the image out is the safe side.
|
||||
let dict = obj.stream.dict();
|
||||
let mask = dict.get::<Stream<'_>>(SMASK).or_else(|| dict.get::<Stream<'_>>(MASK));
|
||||
if alpha.is_none() && hayro_syntax::page_jbig2_work_spent() && mask.is_some_and(|m| uses_jbig2(&m)) {
|
||||
if alpha.is_none() && left_out.load(Ordering::Relaxed) && mask.is_some_and(|m| uses_jbig2(&m)) {
|
||||
return None;
|
||||
}
|
||||
|
||||
|
||||
Vendored
+36
-4
@@ -70,10 +70,10 @@ pub(crate) const BITMAP_WORDS: usize = size_of::<Bitmap>() / size_of::<Word>();
|
||||
/// output from the page header in between, and a 743-byte PDF's Indexed image asked for 137 GB.
|
||||
pub(crate) fn check_page_size(width: u32, height: u32) -> Result<()> {
|
||||
if width > MAX_DIMENSION || height > MAX_DIMENSION {
|
||||
return Err(OverflowError::BitmapDimension.into());
|
||||
return Err(OverflowError::BitmapLimit.into());
|
||||
}
|
||||
if u64::from(width) * u64::from(height) > MAX_PIXELS {
|
||||
return Err(OverflowError::BitmapDimension.into());
|
||||
return Err(OverflowError::BitmapLimit.into());
|
||||
}
|
||||
Ok(())
|
||||
}
|
||||
@@ -129,11 +129,11 @@ impl Bitmap {
|
||||
default_pixel: bool,
|
||||
) -> Result<Self> {
|
||||
if width > MAX_DIMENSION || height > MAX_DIMENSION {
|
||||
bail!(OverflowError::BitmapDimension);
|
||||
bail!(OverflowError::BitmapLimit);
|
||||
}
|
||||
// PdfCraft patch: see `MAX_PIXELS`.
|
||||
if u64::from(width) * u64::from(height) > MAX_PIXELS {
|
||||
bail!(OverflowError::BitmapDimension);
|
||||
bail!(OverflowError::BitmapLimit);
|
||||
}
|
||||
|
||||
let stride = width.div_ceil(WORD_BITS);
|
||||
@@ -357,3 +357,35 @@ impl Bitmap {
|
||||
Ok(area)
|
||||
}
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod pdfcraft_limit_tests {
|
||||
use super::*;
|
||||
use crate::error::DecodeError;
|
||||
|
||||
/// PdfCraft patch: a bitmap past the bound on a side or on pixels is refused by a limit.
|
||||
#[test]
|
||||
fn a_bitmap_past_its_bounds_is_refused_by_a_limit() {
|
||||
let limit = Err(DecodeError::Overflow(OverflowError::BitmapLimit));
|
||||
assert_eq!(
|
||||
Bitmap::new(MAX_DIMENSION + 1, 1).map(|_| ()),
|
||||
limit,
|
||||
"a side"
|
||||
);
|
||||
assert_eq!(
|
||||
Bitmap::new(1, MAX_DIMENSION + 1).map(|_| ()),
|
||||
limit,
|
||||
"the other"
|
||||
);
|
||||
// 2^28 + 2^14 pixels, each side within its bound.
|
||||
assert_eq!(
|
||||
Bitmap::new(1 << 14, (1 << 14) + 1).map(|_| ()),
|
||||
limit,
|
||||
"the pixels"
|
||||
);
|
||||
assert!(
|
||||
Bitmap::new(1 << 14, 1 << 14).is_ok(),
|
||||
"2^28 pixels are within it"
|
||||
);
|
||||
}
|
||||
}
|
||||
+9
-5
@@ -24,10 +24,14 @@ use crate::reader::Reader;
|
||||
|
||||
const MAX_SYMBOLS: u32 = u16::MAX as u32;
|
||||
|
||||
/// PdfCraft patch: the most symbol pixels one dictionary may decode (2^26). Symbols are
|
||||
/// decoded pixel by pixel, and up to 65535 of them of up to 65535 × 65535 each kept a fuzzed
|
||||
/// file decoding for minutes; real dictionaries hold about a million pixels.
|
||||
const MAX_DICTIONARY_PIXELS: u64 = 1 << 26;
|
||||
/// PdfCraft patch: the most symbol pixels one dictionary may decode, as many as the largest page
|
||||
/// bitmap holds (2^28, `bitmap::MAX_PIXELS`). Symbols are decoded pixel by pixel, and up to 65535
|
||||
/// of them of up to 65535 × 65535 each kept a fuzzed file decoding for minutes; each symbol now
|
||||
/// pays for its pixels out of the stream's decoding work (`bitmap::MAX_WORK`), which bounds the
|
||||
/// time, and holds them in the retained bitmaps (`room`), which bounds the memory. The bound was
|
||||
/// 2^26, a quarter of this, which a real scan passes: the soft mask of a 14,642 × 8,879 drawing
|
||||
/// with one dictionary of 7,559 symbols (#6722) needed more, and was refused.
|
||||
const MAX_DICTIONARY_PIXELS: u64 = crate::bitmap::MAX_PIXELS;
|
||||
|
||||
/// PdfCraft patch: decoding steps that decode nothing, allowed beyond what a valid dictionary can
|
||||
/// need. A height class without a symbol and an export run of length 0 don't move their loops
|
||||
@@ -135,7 +139,7 @@ pub(crate) fn decode(
|
||||
.pixels
|
||||
.saturating_add(u64::from(symbol_width) * u64::from(ctx.height_class_height));
|
||||
if ctx.pixels > MAX_DICTIONARY_PIXELS {
|
||||
bail!(OverflowError::BitmapDimension);
|
||||
bail!(OverflowError::BitmapLimit);
|
||||
}
|
||||
// PdfCraft patch: see `bitmap::INTEGER_WORK`. Its width, and a stream can hold thousands
|
||||
// of dictionaries of symbols of no pixels. An aggregated one reads its count, a symbol
|
||||
|
||||
Vendored
+58
@@ -141,6 +141,10 @@ pub enum OverflowError {
|
||||
SegmentCount,
|
||||
/// PdfCraft patch: a stream asks for more decoding work than it may.
|
||||
DecodingWork,
|
||||
/// PdfCraft patch: a bitmap, gray-scale image or symbol dictionary is larger than the decoder
|
||||
/// holds (see `bitmap::MAX_PIXELS`): one of its limits, where `BitmapDimension` is arithmetic
|
||||
/// that overflows.
|
||||
BitmapLimit,
|
||||
}
|
||||
|
||||
impl fmt::Display for DecodeError {
|
||||
@@ -171,6 +175,7 @@ impl fmt::Display for OverflowError {
|
||||
Self::RetainedBitmaps => write!(f, "the segments retain too many bitmaps"),
|
||||
Self::SegmentCount => write!(f, "too many segments or references in a stream"),
|
||||
Self::DecodingWork => write!(f, "a stream asks for too much decoding work"),
|
||||
Self::BitmapLimit => write!(f, "a bitmap is larger than the decoder holds"),
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -312,6 +317,59 @@ impl From<OverflowError> for DecodeError {
|
||||
}
|
||||
}
|
||||
|
||||
impl DecodeError {
|
||||
/// PdfCraft patch: whether one of the decoder's limits refused the stream (on a bitmap's size,
|
||||
/// a dictionary's symbols, a region's instances, the bitmaps retained, the segments or the
|
||||
/// decoding work) rather than its data failing to decode. A file within the format can reach
|
||||
/// these, so a caller can tell a refusal of its own from a damaged file. A size or count the
|
||||
/// file damaged can read as past one of them, and is a limit here too: it can't be told from a
|
||||
/// hostile one.
|
||||
pub fn is_limit(&self) -> bool {
|
||||
matches!(
|
||||
self,
|
||||
Self::Overflow(
|
||||
OverflowError::BitmapLimit
|
||||
| OverflowError::GridDimension
|
||||
| OverflowError::SymbolCount
|
||||
| OverflowError::RetainedBitmaps
|
||||
| OverflowError::SegmentCount
|
||||
| OverflowError::DecodingWork
|
||||
) | Self::Symbol(SymbolError::TooManyInstances)
|
||||
)
|
||||
}
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod pdfcraft_limit_tests {
|
||||
use super::*;
|
||||
|
||||
/// PdfCraft patch: the decoder's own limits are limits, and arithmetic that overflows,
|
||||
/// damage, is not.
|
||||
#[test]
|
||||
fn the_decoders_limits_are_limits_and_overflowing_arithmetic_is_not() {
|
||||
let limits = [
|
||||
DecodeError::Overflow(OverflowError::BitmapLimit),
|
||||
DecodeError::Overflow(OverflowError::GridDimension),
|
||||
DecodeError::Overflow(OverflowError::SymbolCount),
|
||||
DecodeError::Overflow(OverflowError::RetainedBitmaps),
|
||||
DecodeError::Overflow(OverflowError::SegmentCount),
|
||||
DecodeError::Overflow(OverflowError::DecodingWork),
|
||||
DecodeError::Symbol(SymbolError::TooManyInstances),
|
||||
];
|
||||
for limit in limits {
|
||||
assert!(limit.is_limit(), "{limit:?} is a limit");
|
||||
}
|
||||
let damage = [
|
||||
DecodeError::Overflow(OverflowError::BitmapDimension),
|
||||
DecodeError::Overflow(OverflowError::PlacementCoordinate),
|
||||
DecodeError::Symbol(SymbolError::TooManySymbols),
|
||||
];
|
||||
for damage in damage {
|
||||
assert!(!damage.is_limit(), "{damage:?} is damage");
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/// Result type for JBIG2 decoding operations.
|
||||
pub type Result<T> = core::result::Result<T, DecodeError>;
|
||||
|
||||
|
||||
Vendored
+33
-2
@@ -81,11 +81,11 @@ fn decode_arithmetic(
|
||||
let height = params.height;
|
||||
|
||||
if width > MAX_DIMENSION || height > MAX_DIMENSION {
|
||||
bail!(OverflowError::BitmapDimension);
|
||||
bail!(OverflowError::BitmapLimit);
|
||||
}
|
||||
// PdfCraft patch: the product is bounded too (see `bitmap::MAX_GRID_CELLS`).
|
||||
if u64::from(width) * u64::from(height) > crate::bitmap::MAX_GRID_CELLS {
|
||||
bail!(OverflowError::BitmapDimension);
|
||||
bail!(OverflowError::BitmapLimit);
|
||||
}
|
||||
|
||||
// `GSBPP` - The number of bits per gray-scale value.
|
||||
@@ -289,3 +289,34 @@ fn extract_bits<S: Simd>(
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod pdfcraft_limit_tests {
|
||||
use super::*;
|
||||
use crate::error::DecodeError;
|
||||
|
||||
/// PdfCraft patch: a gray-scale image past the bound on a side or on cells is refused by a
|
||||
/// limit, before anything is decoded. A halftone region refuses such a grid first, so this is
|
||||
/// reached only by calling it.
|
||||
#[test]
|
||||
fn a_gray_scale_image_past_its_bounds_is_refused_by_a_limit() {
|
||||
let decode = |width, height| {
|
||||
let params = GrayScaleParams {
|
||||
use_mmr: false,
|
||||
bits_per_pixel: 1,
|
||||
width,
|
||||
height,
|
||||
template: Template::Template0,
|
||||
skip_mask: None,
|
||||
};
|
||||
decode_gray_scale_image(&[], ¶ms, &mut ScratchBuffers::default()).map(|_| ())
|
||||
};
|
||||
let limit = Err(DecodeError::Overflow(OverflowError::BitmapLimit));
|
||||
assert_eq!(decode(MAX_DIMENSION + 1, 1), limit, "a side");
|
||||
assert_eq!(
|
||||
decode(1 << 13, (1 << 12) + 1),
|
||||
limit,
|
||||
"the cells, each side within its bound"
|
||||
);
|
||||
}
|
||||
}
|
||||
+71
-1
@@ -19,12 +19,79 @@ pub const MAX_PAGE_JBIG2_WORK: u64 = 1 << 30;
|
||||
std::thread_local! {
|
||||
// Unbounded until a page says otherwise: what isn't drawing a page has no page to run out on.
|
||||
static PAGE_WORK_LEFT: core::cell::Cell<u64> = const { core::cell::Cell::new(u64::MAX) };
|
||||
// PdfCraft patch (31): what refused the image decoded last on this thread, if one of the
|
||||
// decoder's limits did: `STREAM_LIMIT` or `WORK_LIMIT`, 0 otherwise.
|
||||
static LIMITED: core::cell::Cell<u8> = const { core::cell::Cell::new(0) };
|
||||
}
|
||||
|
||||
/// PdfCraft patch (31): a limit the stream reaches by itself, whatever ran before it (a bitmap's
|
||||
/// size, a dictionary's symbols, the bitmaps retained and the like), so decoding it again is
|
||||
/// refused again.
|
||||
#[cfg(feature = "std")]
|
||||
const STREAM_LIMIT: u8 = 1;
|
||||
/// PdfCraft patch (31): the decoding work, which may be what the page or run had left.
|
||||
#[cfg(feature = "std")]
|
||||
const WORK_LIMIT: u8 = 2;
|
||||
|
||||
/// PdfCraft patch (31): whether the JBIG2 image decoded last on this thread was refused by one of
|
||||
/// the decoder's limits rather than failing on its data. A soft mask a limit refused hides what
|
||||
/// its image would show without it: hayro-interpret leaves such an image out, where a mask the
|
||||
/// file damaged leaves its image whole (#6722). A size or count the file damaged can read as past
|
||||
/// a limit, and is taken for one: it can't be told from a hostile one, and leaving the image out
|
||||
/// is the safe side.
|
||||
#[cfg(feature = "std")]
|
||||
pub fn jbig2_limited() -> bool {
|
||||
LIMITED.with(core::cell::Cell::get) != 0
|
||||
}
|
||||
|
||||
#[cfg(not(feature = "std"))]
|
||||
pub fn jbig2_limited() -> bool {
|
||||
false
|
||||
}
|
||||
|
||||
/// PdfCraft patch (31): whether the refusal [`jbig2_limited`] reports came from a limit the stream
|
||||
/// reaches by itself, not from the decoding work, so the same stream is refused again whenever it
|
||||
/// is decoded.
|
||||
#[cfg(feature = "std")]
|
||||
pub fn jbig2_limited_by_stream() -> bool {
|
||||
LIMITED.with(core::cell::Cell::get) == STREAM_LIMIT
|
||||
}
|
||||
|
||||
#[cfg(not(feature = "std"))]
|
||||
pub fn jbig2_limited_by_stream() -> bool {
|
||||
false
|
||||
}
|
||||
|
||||
/// PdfCraft patch (31): forget what refused the image decoded last, before decoding another
|
||||
/// through filters that may fail before JBIG2 is reached.
|
||||
#[cfg(feature = "std")]
|
||||
pub fn clear_jbig2_limited() {
|
||||
LIMITED.with(|limited| limited.set(0));
|
||||
}
|
||||
|
||||
#[cfg(not(feature = "std"))]
|
||||
pub fn clear_jbig2_limited() {}
|
||||
|
||||
#[cfg(feature = "std")]
|
||||
fn note_limited(error: Option<&hayro_jbig2::DecodeError>) {
|
||||
let refused = match error {
|
||||
Some(hayro_jbig2::DecodeError::Overflow(hayro_jbig2::OverflowError::DecodingWork)) => {
|
||||
WORK_LIMIT
|
||||
}
|
||||
Some(e) if e.is_limit() => STREAM_LIMIT,
|
||||
_ => 0,
|
||||
};
|
||||
LIMITED.with(|limited| limited.set(refused));
|
||||
}
|
||||
|
||||
#[cfg(not(feature = "std"))]
|
||||
fn note_limited(_: Option<&hayro_jbig2::DecodeError>) {}
|
||||
|
||||
/// PdfCraft patch (31): what the JBIG2 images decoded next on this thread may take, for a new page.
|
||||
#[cfg(feature = "std")]
|
||||
pub fn set_page_jbig2_work(work: u64) {
|
||||
PAGE_WORK_LEFT.with(|left| left.set(work));
|
||||
clear_jbig2_limited();
|
||||
}
|
||||
|
||||
/// Pays for reading `bytes` of a stream and its globals out of what the page has left, or `None`.
|
||||
@@ -50,6 +117,7 @@ fn decode_for_page<D: hayro_jbig2::Decoder>(image: &hayro_jbig2::Image<'_>, deco
|
||||
let mut left = PAGE_WORK_LEFT.with(core::cell::Cell::get);
|
||||
let decoded = image.decode_within(decoder, &mut left);
|
||||
PAGE_WORK_LEFT.with(|cell| cell.set(left));
|
||||
note_limited(decoded.as_ref().err());
|
||||
decoded.ok()
|
||||
}
|
||||
|
||||
@@ -93,7 +161,9 @@ pub(crate) fn decode(
|
||||
|
||||
charge_page_reading(data.len().saturating_add(globals.as_deref().map_or(0, <[u8]>::len)))?;
|
||||
|
||||
let image = hayro_jbig2::Image::new_embedded(data, globals.as_deref()).ok()?;
|
||||
let image = hayro_jbig2::Image::new_embedded(data, globals.as_deref())
|
||||
.inspect_err(|e| note_limited(Some(e)))
|
||||
.ok()?;
|
||||
|
||||
// Whenever possible (if we don't have an indexed color space), we convert
|
||||
// the data as 8-bit instead of 1-bit, so that it can be easier converted
|
||||
|
||||
+4
-1
@@ -9,7 +9,10 @@ mod dct;
|
||||
#[cfg(feature = "images")]
|
||||
mod jbig2;
|
||||
#[cfg(feature = "images")]
|
||||
pub use jbig2::{MAX_PAGE_JBIG2_WORK, page_jbig2_work_spent};
|
||||
pub use jbig2::{
|
||||
MAX_PAGE_JBIG2_WORK, clear_jbig2_limited, jbig2_limited, jbig2_limited_by_stream,
|
||||
page_jbig2_work_spent,
|
||||
};
|
||||
#[cfg(all(feature = "images", feature = "std"))]
|
||||
pub use jbig2::set_page_jbig2_work;
|
||||
#[cfg(feature = "images")]
|
||||
|
||||
Reference in new issue
Block a user