diff --git a/crates/cos/src/document.rs b/crates/cos/src/document.rs index 6d39d53db..ebfeb2b49 100644 --- a/crates/cos/src/document.rs +++ b/crates/cos/src/document.rs @@ -1504,7 +1504,7 @@ impl Document { } } sections.push(XrefRevisionSection { primary, hybrid }); - next = sect_trailer.int(b"Prev").filter(|p| *p >= 0).map(|p| p as u64); + next = prev_offset(data, §_trailer, off, |num| sections.iter().find_map(|s| s.lookup(num, data)), log); if trailer.is_none() { trailer = Some(sect_trailer); } @@ -1792,7 +1792,7 @@ impl Document { for (num, e) in sect { entries.entry(num).or_insert(e); } - next = sect_trailer.int(b"Prev").filter(|p| *p >= 0).map(|p| p as u64); + next = prev_offset(data, §_trailer, off, |num| entries.get(&num).copied(), log); if trailer.is_none() { trailer = Some(sect_trailer); } @@ -2098,6 +2098,49 @@ fn object_headers(data: &[u8]) -> Vec<(u32, u64, u16)> { headers } +/// The offset of the section before the one whose trailer this is (`/Prev`), if any. Some writers +/// give it as a reference, `N 0 R`. When the sections read so far (`lookup`) place that object +/// and it holds an offset (iText's `indirectPrev.pdf`), that is the offset; otherwise, as the +/// tiff2pdf files in JHOVE's PDF-HUL-157 cases need, the sections before are at N. Either way the +/// reference is noted. Any other value that is not an offset is noted and ends the chain. +fn prev_offset(data: &[u8], trailer: &Dict, off: u64, lookup: impl Fn(u32) -> Option, log: &mut Vec) -> Option { + match trailer.get(b"Prev") { + Some(Object::Int(p)) if *p >= 0 => Some(*p as u64), + Some(Object::Ref(r)) => { + let held = match lookup(r.num) { + Some(XrefEntry::InFile { offset, generation }) if generation == r.generation => { + usize::try_from(offset).ok().and_then(|at| parse_indirect(data, at, &|_| None).ok()).and_then(|(at, value)| match value { + Object::Int(p) if at == *r && p >= 0 => Some(p as u64), + _ => None, + }) + } + _ => None, + }; + match held { + Some(p) => { + log.push(format!( + "the trailer at {off} gives /Prev as the reference {} {} R; reading the offset {p} it holds", + r.num, r.generation + )); + Some(p) + } + None => { + log.push(format!( + "the trailer at {off} gives /Prev as the reference {} {} R; reading it as offset {}", + r.num, r.generation, r.num + )); + Some(u64::from(r.num)) + } + } + } + Some(_) => { + log.push(format!("the trailer at {off} has a /Prev that is not an offset; the sections before it are unreachable")); + None + } + None => None, + } +} + pub(crate) fn find(hay: &[u8], needle: &[u8], from: usize, to: usize) -> Option { let to = to.min(hay.len()); if from >= to || needle.is_empty() || to - from < needle.len() { @@ -3208,6 +3251,76 @@ endobj } } + /// A trailer whose /Prev is written as the reference `N 0 R` (tiff2pdf did this; the files + /// are JHOVE's PDF-HUL-157 cases, #2366) used to end the cross-reference chain silently, so + /// every object of the earlier sections read as null: a four-page file showed one page, and + /// a full save wrote the three missing kids as null. The offset is read from the reference. + #[test] + fn a_prev_written_as_a_reference_still_reaches_the_earlier_sections() { + let base = build( + &["<< /Type /Catalog /Pages 2 0 R >>", "<< /Type /Pages /Kids [3 0 R] /Count 1 >>", "<< /Type /Page /Parent 2 0 R >>"], + "/Root 1 0 R", + ); + let prev = String::from_utf8_lossy(&base).rfind("xref\n0 4").unwrap(); + let update = |prev_entry: &str| { + let mut bytes = base.clone(); + let at = bytes.len(); + bytes.extend_from_slice(b"4 0 obj\n<< /Title (Update) >>\nendobj\n"); + let xref = bytes.len(); + bytes.extend_from_slice( + format!( + "xref\n4 1\n{at:010} 00000 n \ntrailer\n<< /Size 5 /Root 1 0 R /Info 4 0 R /Prev {prev_entry} >>\nstartxref\n{xref}\n%%EOF\n" + ) + .as_bytes(), + ); + Document::open(Arc::new(bytes)).unwrap() + }; + let good = update(&prev.to_string()); + let bad = update(&format!("{prev} 0 R")); + assert!(good.repair_log().is_empty(), "{:?}", good.repair_log()); + assert_eq!(bad.revisions().len(), 2, "{:?}", bad.repair_log()); + assert_eq!(bad.repair_log().len(), 1, "a note about the /Prev: {:?}", bad.repair_log()); + assert_eq!(bad.xref_entry(3), good.xref_entry(3), "the page of the first section is reached"); + assert_eq!(bad.get(ObjRef::new(3, 0)).as_dict().and_then(|d| d.name(b"Type")), Some(&b"Page"[..])); + assert_eq!( + bad.get(ObjRef::new(4, 0)).as_dict().and_then(|d| d.get(b"Title").and_then(|t| t.as_string().map(|s| s.to_text()))), + Some("Update".into()) + ); + } + + /// iText's `indirectPrev.pdf` in miniature: the update's trailer gives `/Prev 4 0 R`, and + /// object 4, listed in that update, holds the offset of the first section. Read as offset 4 + /// (inside the header), the chain broke and the file was rebuilt without its revisions. + #[test] + fn a_prev_reference_to_an_object_holding_the_offset_reads_that_offset() { + let mut bytes = build( + &["<< /Type /Catalog /Pages 2 0 R >>", "<< /Type /Pages /Kids [3 0 R] /Count 1 >>", "<< /Type /Page /Parent 2 0 R >>"], + "/Root 1 0 R", + ); + let prev = String::from_utf8_lossy(&bytes).rfind("xref\n0 4").unwrap(); + let mut at = Vec::new(); + for (num, body) in + [(2, "<< /Type /Pages /Kids [3 0 R 5 0 R] /Count 2 >>".to_string()), (4, prev.to_string()), (5, "<< /Type /Page /Parent 2 0 R >>".into())] + { + at.push(bytes.len()); + bytes.extend_from_slice(format!("{num} 0 obj\n{body}\nendobj\n").as_bytes()); + } + let xref = bytes.len(); + bytes.extend_from_slice( + format!( + "xref\n2 1\n{:010} 00000 n \n4 2\n{:010} 00000 n \n{:010} 00000 n \ntrailer\n<< /Size 6 /Root 1 0 R /Prev 4 0 R >>\nstartxref\n{xref}\n%%EOF\n", + at[0], at[1], at[2] + ) + .as_bytes(), + ); + let doc = Document::open(Arc::new(bytes)).unwrap(); + assert_eq!(doc.revisions().len(), 2, "{:?}", doc.repair_log()); + assert_eq!(doc.repair_log().len(), 1, "a note about the /Prev, and no rebuild: {:?}", doc.repair_log()); + assert!(doc.repair_log()[0].contains(&format!("the offset {prev}")), "{:?}", doc.repair_log()); + assert_eq!(doc.get(ObjRef::new(3, 0)).as_dict().and_then(|d| d.name(b"Type")), Some(&b"Page"[..])); + assert_compact_matches_materialized(&doc); + } + #[test] fn damaged_xref_is_reconstructed() { let mut bytes = build(&["<< /Type /Catalog /Pages 2 0 R >>", "<< /Type /Pages /Kids [] /Count 0 >>"], "/Root 1 0 R"); diff --git a/vendor/README.md b/vendor/README.md index 45c7e4421..ab4b367ae 100644 --- a/vendor/README.md +++ b/vendor/README.md @@ -17,7 +17,7 @@ In `hayro-interpret`, Type 3 glyph bounding boxes are transformed to device spac | hayro | 0.7.1 | Apache-2.0 OR MIT | (1) `RenderSettings::{x_offset, y_offset}` to render one tile of a large page; (2) images over `MAX_IMAGE_PIXELS` (2^28) are skipped (a fuzzed `/W 4294967295` hung in resampling); (3) `tiling_cell_scale` keeps a tiling pattern's cell pixmap within 3000 px a side whatever its `/XStep`/`/YStep` (a fuzzed step far beyond `/BBox` allocated 2 GB); (4) stroke widths clamped to 4 × (canvas width + height) device pixels (a fuzzed `/LW 9223372036854775807` allocated 10 GB in stroke expansion); (5) `usable_dash_pattern`: a stroke whose dash pattern could cut it into more than `MAX_DASHES_PER_STROKE` (250,000) pieces, counting kurbo's restart of the pattern at every subpath and `ClosePath`, is drawn solid (a fuzzed `/D [[11] 0]` on a line from x = 92234775807 allocated over 5 GB, `[0.000001] 0 d` on a 20 pt line over 10 GB); (6) a dash pattern with a negative or non-finite entry, or a period that isn't positive, is drawn solid (`[-1 -1] 0 d` looped for ever in kurbo); (7) `render_size` and `render_into`: render into a buffer the caller allocates (PdfCraft renders into pixel-aligned memory that the GUI takes over as texture data); `render` is `render_into` on a new pixmap; (8) checked image source/target/RGBA, alpha-premultiplication scratch and intermediate sizes before resampling, finite transforms and exact source/mask buffers; sources wider than u16 may shrink before backend limits, with a 2^20 source-axis cap and conservative 128 MiB filter-planning estimate; an over-limit or failed resize keeps the original image resolution and geometry when the source fits the backend, otherwise skips it, with a logged warning; staging, resampling output/scratch, RGBA conversion and padding buffers use fallible reserves; (9) `may_paint_canvas`: a fill or stroke whose control-point box, grown by how far its paint reaches past the path (half the stroke width times the larger of the miter limit and √2) plus 0.5 user units and 2 pixels, misses the canvas is not drawn, so a tile no longer strokes and fills every path of its page (item 5 of #623); `set_skip_offscreen_paths` turns this off for the regression test; (10) `/Interpolate` governs the pre-resize too (#624): a minified image that does not request interpolation is pre-resized with nearest-neighbour, planned without the Catmull-Rom filter limits (`image_resampling_size` takes the flag); a Type 3 glyph image is sampled bicubically only when interpolated; a minified image with a matching soft mask is nearest-sampled straight into premultiplied RGBA; (11) `may_paint_rect`: an image whose stream-size box, mapped to the device, misses the canvas is skipped before decoding (decoded data can only shrink against that box), so a tile of an image-heavy page no longer decodes, resamples and rasterizes every image on it; (12) preview renders (`InterpreterSettings::preview`: backdrops, thumbnails, grid cells, signature-drag backgrounds) skip images under `PREVIEW_MIN_IMAGE_AREA` device pixels, while final renders always draw them; (13) reading colours (#897): `RenderSettings::color_replacement` takes a `ColorReplacement` (text colour, background, `only_black`, `line_art`) that remaps solid text and line-art paint while rendering, glyph outlines counting as text and stencil-mask ink as line art; images, image alpha masks, soft masks and pattern cells keep their colours; `render_pdf` gains a `color_replacement: Option` argument (pass `None` for true colours); the upstream-only `[dev-dependencies.log]` entry is removed from `Cargo.toml` (log is a normal dependency since the logging patch), so `cargo test -p hayro` runs this crate's unit tests; (14) a shrunk, interpolated, axis-aligned image is snapped to whole device pixels: shrunk once to its rounded device rectangle and drawn 1:1 at the rounded corner, instead of a ceil-sized raster resampled again at a fractional scale and offset (`snap_minified_image`; scans looked soft next to Acrobat); (15) a soft mask of another size than its image is filtered when shrunk, whatever its `/Interpolate` (#1649): such a mask carries the shape on its own (Word saves text as a tiny black image with a glyph-bitmap mask), and nearest-neighbour dropped every stroke thinner than the shrink factor; (16) under a soft mask or a blend mode, axial and radial shadings are sampled instead of drawn as native gradients (#2128): vello_cpu 0.0.8 copies an opaque gradient over fully covered tiles without the mask or blend mode, so PowerPoint's faded gradient fills came out solid; (17) the renderer keeps annotation paints out of the reading-colours mapping between `begin_annotations` and `end_annotations` (#1548); (18) the page renders as one transparency group with its background painted inside it as the initial backdrop, so a Multiply highlight blends with a dark reading-colours background instead of staying an opaque block (identity on white pages); (20) a tiling pattern whose step is too large for a cell pixmap, where what is painted (a fill, or a stroke with its width) can only show the first cell (PowerPoint's `/XStep 2147480100` for a picture fill drawn once), has its `/BBox` drawn at full scale with a transparent border and padded instead of tiled (`shows_one_cell`; a cell whose scale isn't finite and positive, from a `/BBox` too thin to divide by, keeps the old path: `usable_cell_scale`); shrinking the cell to fit the 3000 px limit of (3) left the picture under a pixel, so network diagrams lost their pictures (#3349) | (1) `raster::tests::tiles_match_full_render`; (2) `raster::tests::absurd_image_dimensions_are_skipped`; (3) `raster::tests::tiling_cells_stay_small_whatever_the_step`; (4) `raster::tests::absurd_predictor_columns_and_line_widths_render`; (5) `raster::tests::dash_patterns_that_cut_a_stroke_into_billions_of_pieces_render`; (6) `raster::tests::invalid_dash_patterns_terminate_and_are_drawn_solid`; (7) `raster::tests::pixels_are_a_plain_renders_bytes_in_a_buffer_a_gui_can_take_over`; (8) `raster::tests::image_resampling_rejects_anisotropic_target_growth`, `raster::tests::image_resampling_bounds_intermediate_before_planning`, `raster::tests::image_resampling_rejects_invalid_sources_and_scales`, `raster::tests::image_resampling_keeps_valid_sizes_and_exact_limits`, `raster::tests::resampling_fallback_preserves_original_geometry_and_pixels`, `raster::tests::image_resampling_wide_sources_shrink_before_backend_side_limits`, `raster::tests::image_resampling_wide_transparent_sources_still_shrink`, `raster::tests::image_resampling_padded_backend_dimensions_stay_checked`, `raster::tests::image_resampling_mismatched_alpha_mask_keeps_pixels_and_placement`; (9) `raster::tests::skipping_paths_off_the_canvas_changes_no_pixel`; (10) `raster::tests::non_interpolated_images_are_not_smoothed_when_minified`, `raster::tests::non_interpolated_gray_images_are_not_smoothed_when_minified`, `raster::tests::non_integer_minification_samples_the_same_columns`, `raster::tests::non_integer_minification_samples_colour_and_mask_from_the_same_columns`, `raster::tests::non_interpolated_alpha_images_keep_their_colours_and_mask_when_minified`, `raster::tests::non_interpolated_type3_glyph_images_are_not_smoothed_when_minified`, `raster::tests::image_resampling_nearest_accepts_wide_sources_the_filter_refuses`, `raster::tests::wide_non_interpolated_sources_draw_after_shrinking`; (11) `raster::tests::skipping_paths_off_the_canvas_changes_no_pixel`; (12) `raster::tests::preview_renders_skip_tiny_images_but_finals_draw_everything`; (13) `color_replacement_tests::{black_maps_to_text_colour, white_maps_to_background, midgrey_interpolates, alpha_copied_verbatim, only_black_threshold, line_art_false_skips_paths_but_not_text}`, `color_replacement_render_tests::{color_replacement_maps_text_and_line_art, color_replacement_maps_stencil_mask_ink}`; (14) `raster::tests::interpolated_minified_image_edges_snap_to_whole_pixels` (`cargo test -p hayro`); (15) `raster::tests::shrunk_soft_mask_larger_than_its_image_keeps_thin_strokes`; (16) `raster::tests::soft_mask_applies_to_a_shading_pattern_fill`; (17), (18) `raster::tests::reading_colors_keep_highlight_annotations_readable`; (20) `raster::tests::a_tiling_pattern_drawn_once_shows_its_cell`, `raster::tests::a_large_step_still_tiles_where_the_next_cell_shows`, `raster::tests::a_tiling_cell_too_thin_to_scale_keeps_the_old_path` | | hayro-jbig2 | 0.3.0 | Apache-2.0 OR MIT | (1) at most 2^28 pixels per bitmap, page bitmap, halftone grid and grayscale image (each side could be 65535: 4.3 billion pixels decoded one by one); (2) at most 2^26 symbol pixels per symbol dictionary (a fuzzed dictionary decoded for minutes); (3) a symbol dictionary's height classes are capped at one per new symbol and its export runs at `2 × symbols + 1`, each plus `EXTRA_EMPTY_STEPS` (1024): an empty height class or a zero-length export run doesn't advance, and past the end of its data the arithmetic decoder can decode them for ever (one changed byte hung the renderer) | (1) `raster::tests::jbig2_regions_of_billions_of_pixels_are_refused`; (2) the nightly `cargo xtask fuzz` finding, which now finishes in about a second; (3) `raster::tests::jbig2_symbol_dictionaries_that_never_advance_terminate` | | 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) | (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` | -| 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); (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 and RunLength 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_passwords` in `crypto/mod.rs`, which resolves the upstream `TODO: Do the above.`; `stringprep`, already in the tree through pdfcraft-crypt, is an optional dependency enabled by `std`, and without `std` passwords are used as given): the renderer used the password as typed, so one that SASLprep changes (a decomposed `café`, a no-break space, the fullwidth `ａｂ` a Japanese IME types in full-width mode) was wrong, although pdfcraft-cos accepted it: protecting a document with such an open password was rolled back ("the password is incorrect"), and a file with such a password did not open with it.; (17) CCITT `/Rows 0` means the height is not predetermined (ISO 32000-2 Table 11), not zero rows: scanned Group 4 pages written that way rendered blank; (18) The streaming Flate decoder (`lzw_flate::flate::fallback`) copies a back-reference in runs of up to its distance (`extend_from_within`), not byte by byte. The copy reads only bytes already in the output, and a copy whose source does not exist still writes nothing, so the bytes are those a byte-by-byte copy writes. Inflating the A1 sample's content stream (278.6 MB) takes about 14% less time (0.66 s to 0.56 s); the output is identical; (19) CCITT `/Rows` below the image's `/Height` decodes to the height: a plotter driver wrote `/Rows` equal to `/Columns`, so only the first rows were decoded and the rest drawn black (#3308) (20) `stream` followed by spaces or tabs and then the line break (`stream \r\n`, as Microsoft Reporting Services writes it) starts the data after the line break; the content stream was taken to start at the space and the page rendered blank.; (21) a JP2 colour specification naming an enumerated colour space the decoder refuses (CIEJab in a veraPDF fixture, YCbCr, PhotoYCC, YPbPr, bilevel…) no longer fails the image: it is decoded again from a copy whose `colr` names the space the decoder assumes without one, greyscale, sRGB or CMYK by component count, as MuPDF and Poppler draw it (`without_refused_enumerated_colour`; the page drew blank, #3306); (22) an object stream's index of `objnum offset` pairs is parsed once per stream and kept beside its decoded data (`ObjectStreamIndexes`, `XRef::with_object_stream_indexes`), and an offset past `usize` is malformed instead of wrapping: `XRef::get_with` parsed the whole index again for every object it fetched from the stream, so reading all of a stream of N objects took N² steps (a Firefox page whose 65,542 objects share one stream took 37 s to draw and 40 s to extract its text); (23) the inline-image end-of-data look-ahead no longer rejects a candidate `EI` because a byte above 0x7F lies between it and the next one: when the candidate is the end, those bytes are the content stream that follows the image, and its strings carry such bytes (WinAnsi `(Grüße) Tj`, the two-byte codes of any Type 0 font), so the operator check that follows decides alone, bounded as in (4) (a scanned page whose OCR text held an accented word and a later capital "EI" — EINGANG, BEI, KLEIN — drew and extracted nothing after the image: 40 of 275 pages across five real documents) | (1) `cos/tests/writer.rs::page_tree_loops_in_object_streams_do_not_crash_readers`; (2) `raster::tests::absurd_mask_and_fax_sizes_are_refused_before_decoding`; (3) `raster::tests::absurd_predictor_columns_and_line_widths_render`; (4) `raster::tests::inline_images_with_ei_in_their_data_parse_in_linear_time`; (5) `raster::tests::indirect_appearance_state_dict_is_not_another_stream`; (6) `raster::tests::jpx_stream_bit_depth_boundaries_do_not_panic`, `raster::tests::jpx_32_bit_image_does_not_prevent_other_page_content_from_rendering`, `raster::tests::jpx_gray_rgb_and_alpha_keep_eight_bit_samples`, `raster::tests::jpx_streams_reject_out_of_range_bit_depths`; (7) `raster::tests::decompression_bombs_stop_at_the_stream_limit`, `raster::tests::page_contents_and_nested_forms_share_one_budget`; (8) `inspect::tests::jspdf_high_precision_mediabox_does_not_overflow_dimensions`, `object::number::tests::high_precision_float_does_not_overflow_mantissa` (hayro-syntax); (9) `object::dict::lazy_index_tests`, `raster::tests::large_resource_indexes_preserve_pixels_and_text`; (10) `data::tests`, `xref::tests::concurrent_cold_object_stream_reads_all_succeed`, `raster::tests::shared_parser_is_lazy_and_initializes_once_under_contention`; (11) `data::tests::panicking_initializer_wakes_waiters_and_prevents_retries`, `xref::tests::concurrent_cold_object_stream_reads_all_succeed`; (12) `util::tests::segment_list_rejects_out_of_range_indices`; (13) `raster::tests::user_unit_scales_the_page_and_everything_on_it`; (14) `crypto::pdfcraft_password_tests`, `pdfcraft-engine` `tests::legacy_passwords_with_turkish_characters_open`; (15) `content::tests::windows_keep_every_instruction_at_every_split`, `content::tests::windows_keep_every_instruction_in_pieces_of_any_size`, `content::tests::windows_match_the_slice_on_random_content`, `content::tests::windows_drop_blanks_and_keep_a_comment_that_may_go_on`, `page::content_reader_tests::content_past_the_cap_is_read_to_the_end`, `page::content_reader_tests::a_stream_that_expands_past_the_budget_is_cut_there`, `page::content_reader_tests::a_small_expansion_under_the_cap_is_not_cut`, `raster::tests::page_content_past_the_old_cap_renders`, `raster::tests::content_reader_returns_the_same_bytes_in_any_pieces`, `raster::tests::content_bombs_stop_at_the_budget_and_say_so`, `page::content_reader_tests::plain_and_whole_pieces_keep_their_bytes`, `page::content_reader_tests::repeated_content_reference_counts_compressed_bytes_once`, `page::content_reader_tests::whole_cap_still_counts_later_unique_streams`; (16) `crypto::pdfcraft_password_tests::aes256_passwords_are_tried_in_their_saslprep_form_then_as_given`, `crypto::pdfcraft_password_tests::aes256_passwords_open_as_typed_and_in_their_saslprep_form`, `pdfcraft-engine` `tests::aes256_open_passwords_that_saslprep_changes_protect_and_reopen_as_typed`, `tests::aes256_files_whose_passwords_saslprep_changes_open_as_typed`; (17) `raster::tests::group4_fax_with_rows_zero_decodes_to_the_image_height`; (18) `filter::lzw_flate::tests::back_reference_longer_than_its_distance_repeats_its_source`, `back_reference_cut_by_the_limit_resumes_in_the_next_call` and `back_reference_reads_bytes_written_by_an_earlier_call`; each fails when the copy returns the wrong remaining count; (19) `raster::tests::group4_fax_with_rows_below_its_height_decodes_to_the_image_height`; (20) `raster::tests::space_before_the_line_break_after_stream_still_renders`; (21) `raster::tests::a_jp2_image_in_a_refused_enumerated_colour_space_is_drawn`, `filter::jpx::tests::refused_enumerated_colour_spaces_become_the_component_counts_default`, `filter::jpx::tests::what_the_decoder_handles_or_cant_be_read_is_left_alone` (`cargo test --manifest-path vendor/hayro-syntax/Cargo.toml`); (22) `raster::tests::objects_in_one_large_object_stream_are_read_in_linear_time`; (23) `text::tests::text_after_an_inline_image_survives_a_non_ascii_byte_before_a_later_ei`, `content::tests::an_inline_image_ends_at_its_own_ei_when_later_text_holds_a_non_ascii_byte` (hayro-syntax) +| 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); (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 and RunLength 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_passwords` in `crypto/mod.rs`, which resolves the upstream `TODO: Do the above.`; `stringprep`, already in the tree through pdfcraft-crypt, is an optional dependency enabled by `std`, and without `std` passwords are used as given): the renderer used the password as typed, so one that SASLprep changes (a decomposed `café`, a no-break space, the fullwidth `ａｂ` a Japanese IME types in full-width mode) was wrong, although pdfcraft-cos accepted it: protecting a document with such an open password was rolled back ("the password is incorrect"), and a file with such a password did not open with it.; (17) CCITT `/Rows 0` means the height is not predetermined (ISO 32000-2 Table 11), not zero rows: scanned Group 4 pages written that way rendered blank; (18) The streaming Flate decoder (`lzw_flate::flate::fallback`) copies a back-reference in runs of up to its distance (`extend_from_within`), not byte by byte. The copy reads only bytes already in the output, and a copy whose source does not exist still writes nothing, so the bytes are those a byte-by-byte copy writes. Inflating the A1 sample's content stream (278.6 MB) takes about 14% less time (0.66 s to 0.56 s); the output is identical; (19) CCITT `/Rows` below the image's `/Height` decodes to the height: a plotter driver wrote `/Rows` equal to `/Columns`, so only the first rows were decoded and the rest drawn black (#3308) (20) `stream` followed by spaces or tabs and then the line break (`stream \r\n`, as Microsoft Reporting Services writes it) starts the data after the line break; the content stream was taken to start at the space and the page rendered blank.; (21) a JP2 colour specification naming an enumerated colour space the decoder refuses (CIEJab in a veraPDF fixture, YCbCr, PhotoYCC, YPbPr, bilevel…) no longer fails the image: it is decoded again from a copy whose `colr` names the space the decoder assumes without one, greyscale, sRGB or CMYK by component count, as MuPDF and Poppler draw it (`without_refused_enumerated_colour`; the page drew blank, #3306); (22) an object stream's index of `objnum offset` pairs is parsed once per stream and kept beside its decoded data (`ObjectStreamIndexes`, `XRef::with_object_stream_indexes`), and an offset past `usize` is malformed instead of wrapping: `XRef::get_with` parsed the whole index again for every object it fetched from the stream, so reading all of a stream of N objects took N² steps (a Firefox page whose 65,542 objects share one stream took 37 s to draw and 40 s to extract its text); (23) the inline-image end-of-data look-ahead no longer rejects a candidate `EI` because a byte above 0x7F lies between it and the next one: when the candidate is the end, those bytes are the content stream that follows the image, and its strings carry such bytes (WinAnsi `(Grüße) Tj`, the two-byte codes of any Type 0 font), so the operator check that follows decides alone, bounded as in (4) (a scanned page whose OCR text held an accented word and a later capital "EI" — EINGANG, BEI, KLEIN — drew and extracted nothing after the image: 40 of 275 pages across five real documents); (24) `xref::prev_offset`: a trailer `/Prev` written as a reference `N G R` is read as the offset that object holds when the section's own entries place it (iText's `indirectPrev.pdf`; each section's entries are read before its `Prev` is followed), and otherwise as offset N (tiff2pdf; JHOVE's PDF-HUL-157 files, #2366), as `pdfcraft-cos` and other readers take it, so the earlier sections' pages are seen instead of one | (1) `cos/tests/writer.rs::page_tree_loops_in_object_streams_do_not_crash_readers`; (2) `raster::tests::absurd_mask_and_fax_sizes_are_refused_before_decoding`; (3) `raster::tests::absurd_predictor_columns_and_line_widths_render`; (4) `raster::tests::inline_images_with_ei_in_their_data_parse_in_linear_time`; (5) `raster::tests::indirect_appearance_state_dict_is_not_another_stream`; (6) `raster::tests::jpx_stream_bit_depth_boundaries_do_not_panic`, `raster::tests::jpx_32_bit_image_does_not_prevent_other_page_content_from_rendering`, `raster::tests::jpx_gray_rgb_and_alpha_keep_eight_bit_samples`, `raster::tests::jpx_streams_reject_out_of_range_bit_depths`; (7) `raster::tests::decompression_bombs_stop_at_the_stream_limit`, `raster::tests::page_contents_and_nested_forms_share_one_budget`; (8) `inspect::tests::jspdf_high_precision_mediabox_does_not_overflow_dimensions`, `object::number::tests::high_precision_float_does_not_overflow_mantissa` (hayro-syntax); (9) `object::dict::lazy_index_tests`, `raster::tests::large_resource_indexes_preserve_pixels_and_text`; (10) `data::tests`, `xref::tests::concurrent_cold_object_stream_reads_all_succeed`, `raster::tests::shared_parser_is_lazy_and_initializes_once_under_contention`; (11) `data::tests::panicking_initializer_wakes_waiters_and_prevents_retries`, `xref::tests::concurrent_cold_object_stream_reads_all_succeed`; (12) `util::tests::segment_list_rejects_out_of_range_indices`; (13) `raster::tests::user_unit_scales_the_page_and_everything_on_it`; (14) `crypto::pdfcraft_password_tests`, `pdfcraft-engine` `tests::legacy_passwords_with_turkish_characters_open`; (15) `content::tests::windows_keep_every_instruction_at_every_split`, `content::tests::windows_keep_every_instruction_in_pieces_of_any_size`, `content::tests::windows_match_the_slice_on_random_content`, `content::tests::windows_drop_blanks_and_keep_a_comment_that_may_go_on`, `page::content_reader_tests::content_past_the_cap_is_read_to_the_end`, `page::content_reader_tests::a_stream_that_expands_past_the_budget_is_cut_there`, `page::content_reader_tests::a_small_expansion_under_the_cap_is_not_cut`, `raster::tests::page_content_past_the_old_cap_renders`, `raster::tests::content_reader_returns_the_same_bytes_in_any_pieces`, `raster::tests::content_bombs_stop_at_the_budget_and_say_so`, `page::content_reader_tests::plain_and_whole_pieces_keep_their_bytes`, `page::content_reader_tests::repeated_content_reference_counts_compressed_bytes_once`, `page::content_reader_tests::whole_cap_still_counts_later_unique_streams`; (16) `crypto::pdfcraft_password_tests::aes256_passwords_are_tried_in_their_saslprep_form_then_as_given`, `crypto::pdfcraft_password_tests::aes256_passwords_open_as_typed_and_in_their_saslprep_form`, `pdfcraft-engine` `tests::aes256_open_passwords_that_saslprep_changes_protect_and_reopen_as_typed`, `tests::aes256_files_whose_passwords_saslprep_changes_open_as_typed`; (17) `raster::tests::group4_fax_with_rows_zero_decodes_to_the_image_height`; (18) `filter::lzw_flate::tests::back_reference_longer_than_its_distance_repeats_its_source`, `back_reference_cut_by_the_limit_resumes_in_the_next_call` and `back_reference_reads_bytes_written_by_an_earlier_call`; each fails when the copy returns the wrong remaining count; (19) `raster::tests::group4_fax_with_rows_below_its_height_decodes_to_the_image_height`; (20) `raster::tests::space_before_the_line_break_after_stream_still_renders`; (21) `raster::tests::a_jp2_image_in_a_refused_enumerated_colour_space_is_drawn`, `filter::jpx::tests::refused_enumerated_colour_spaces_become_the_component_counts_default`, `filter::jpx::tests::what_the_decoder_handles_or_cant_be_read_is_left_alone` (`cargo test --manifest-path vendor/hayro-syntax/Cargo.toml`); (22) `raster::tests::objects_in_one_large_object_stream_are_read_in_linear_time`; (23) `text::tests::text_after_an_inline_image_survives_a_non_ascii_byte_before_a_later_ei`, `content::tests::an_inline_image_ends_at_its_own_ei_when_later_text_holds_a_non_ascii_byte` (hayro-syntax); (24) `xref::tests::prev_as_reference_reaches_the_earlier_section`, `xref::tests::prev_as_reference_to_an_object_holding_the_offset_reads_that_offset`, `pdfcraft-cos` `document::tests::a_prev_written_as_a_reference_still_reaches_the_earlier_sections`, `document::tests::a_prev_reference_to_an_object_holding_the_offset_reads_that_offset` | 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); (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_passwords` in `crypto/mod.rs`, which resolves the upstream `TODO: Do the above.`; `stringprep`, already in the tree through pdfcraft-crypt, is an optional dependency enabled by `std`, and without `std` passwords are used as given): the renderer used the password as typed, so one that SASLprep changes (a decomposed `café`, a no-break space, the fullwidth `ａｂ` a Japanese IME types in full-width mode) was wrong, although pdfcraft-cos accepted it: protecting a document with such an open password was rolled back ("the password is incorrect"), and a file with such a password did not open with it. | (1) `cos/tests/writer.rs::page_tree_loops_in_object_streams_do_not_crash_readers`; (2) `raster::tests::absurd_mask_and_fax_sizes_are_refused_before_decoding`; (3) `raster::tests::absurd_predictor_columns_and_line_widths_render`; (4) `raster::tests::inline_images_with_ei_in_their_data_parse_in_linear_time`; (5) `raster::tests::indirect_appearance_state_dict_is_not_another_stream`; (6) `raster::tests::jpx_stream_bit_depth_boundaries_do_not_panic`, `raster::tests::jpx_32_bit_image_does_not_prevent_other_page_content_from_rendering`, `raster::tests::jpx_gray_rgb_and_alpha_keep_eight_bit_samples`, `raster::tests::jpx_streams_reject_out_of_range_bit_depths`; (7) `raster::tests::decompression_bombs_stop_at_the_stream_limit`, `raster::tests::page_contents_and_nested_forms_share_one_budget`; (8) `inspect::tests::jspdf_high_precision_mediabox_does_not_overflow_dimensions`, `object::number::tests::high_precision_float_does_not_overflow_mantissa` (hayro-syntax); (9) `object::dict::lazy_index_tests`, `raster::tests::large_resource_indexes_preserve_pixels_and_text`; (10) `data::tests`, `xref::tests::concurrent_cold_object_stream_reads_all_succeed`, `raster::tests::shared_parser_is_lazy_and_initializes_once_under_contention`; (11) `data::tests::panicking_initializer_wakes_waiters_and_prevents_retries`, `xref::tests::concurrent_cold_object_stream_reads_all_succeed`; (12) `util::tests::segment_list_rejects_out_of_range_indices`; (13) `raster::tests::user_unit_scales_the_page_and_everything_on_it`; (14) `crypto::pdfcraft_password_tests`, `pdfcraft-engine` `tests::legacy_passwords_with_turkish_characters_open`; (15) `content::tests::windows_keep_every_instruction_at_every_split`, `content::tests::windows_keep_every_instruction_in_pieces_of_any_size`, `content::tests::windows_match_the_slice_on_random_content`, `content::tests::windows_drop_blanks_and_keep_a_comment_that_may_go_on`, `page::content_reader_tests::content_past_the_cap_is_read_to_the_end`, `page::content_reader_tests::a_stream_that_expands_past_the_budget_is_cut_there`, `page::content_reader_tests::a_small_expansion_under_the_cap_is_not_cut`, `raster::tests::page_content_past_the_old_cap_renders`, `raster::tests::content_reader_returns_the_same_bytes_in_any_pieces`, `raster::tests::content_bombs_stop_at_the_budget_and_say_so`, `page::content_reader_tests::plain_and_whole_pieces_keep_their_bytes`, `page::content_reader_tests::repeated_content_reference_counts_compressed_bytes_once`, `page::content_reader_tests::whole_cap_still_counts_later_unique_streams`; (16) `crypto::pdfcraft_password_tests::aes256_passwords_are_tried_in_their_saslprep_form_then_as_given`, `crypto::pdfcraft_password_tests::aes256_passwords_open_as_typed_and_in_their_saslprep_form`, `pdfcraft-engine` `tests::aes256_open_passwords_that_saslprep_changes_protect_and_reopen_as_typed`, `tests::aes256_files_whose_passwords_saslprep_changes_open_as_typed` | 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 | (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` | | 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); (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 and RunLength 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 | (1) `cos/tests/writer.rs::page_tree_loops_in_object_streams_do_not_crash_readers`; (2) `raster::tests::absurd_mask_and_fax_sizes_are_refused_before_decoding`; (3) `raster::tests::absurd_predictor_columns_and_line_widths_render`; (4) `raster::tests::inline_images_with_ei_in_their_data_parse_in_linear_time`; (5) `raster::tests::indirect_appearance_state_dict_is_not_another_stream`; (6) `raster::tests::jpx_stream_bit_depth_boundaries_do_not_panic`, `raster::tests::jpx_32_bit_image_does_not_prevent_other_page_content_from_rendering`, `raster::tests::jpx_gray_rgb_and_alpha_keep_eight_bit_samples`, `raster::tests::jpx_streams_reject_out_of_range_bit_depths`; (7) `raster::tests::decompression_bombs_stop_at_the_stream_limit`, `raster::tests::page_contents_and_nested_forms_share_one_budget`; (8) `inspect::tests::jspdf_high_precision_mediabox_does_not_overflow_dimensions`, `object::number::tests::high_precision_float_does_not_overflow_mantissa` (hayro-syntax); (9) `object::dict::lazy_index_tests`, `raster::tests::large_resource_indexes_preserve_pixels_and_text`; (10) `data::tests`, `xref::tests::concurrent_cold_object_stream_reads_all_succeed`, `raster::tests::shared_parser_is_lazy_and_initializes_once_under_contention`; (11) `data::tests::panicking_initializer_wakes_waiters_and_prevents_retries`, `xref::tests::concurrent_cold_object_stream_reads_all_succeed`; (12) `util::tests::segment_list_rejects_out_of_range_indices`; (13) `raster::tests::user_unit_scales_the_page_and_everything_on_it` | diff --git a/vendor/hayro-syntax/src/xref.rs b/vendor/hayro-syntax/src/xref.rs index 673d516d2..2d9df169b 100644 --- a/vendor/hayro-syntax/src/xref.rs +++ b/vendor/hayro-syntax/src/xref.rs @@ -807,6 +807,34 @@ fn populate_xref_impl<'a>(data: &'a [u8], pos: usize, xref_map: &mut XrefMap) -> populate_xref_impl_inner(data, pos, xref_map, &mut visited) } +/// The offset of the previous xref section (`Prev`). +// PdfCraft patch: (#2366) some writers give `Prev` as a reference `N G R`. When this section's +// own entries (`own`) place that object and it holds an offset (iText's `indirectPrev.pdf`), that +// is the offset; otherwise its object number is (tiff2pdf, in JHOVE's PDF-HUL-157 files), as +// `pdfcraft-cos` and other readers take it. +fn prev_offset(data: &[u8], trailer: &Dict<'_>, own: &XrefMap) -> Option { + if let Some(prev) = trailer.get::(PREV) { + return usize::try_from(prev).ok(); + } + + let r = trailer.get_ref(PREV)?; + let id = ObjectIdentifier::new(r.obj_number, r.gen_number); + let held = match own.get(&id) { + Some(EntryType::Normal(at)) => { + let mut reader = Reader::new(data); + reader.jump(*at); + reader + .read_with_context::>(&ReaderContext::dummy()) + .filter(|o| o.id() == &id) + .map(|o| o.get()) + .filter(|p| *p >= 0) + } + _ => None, + }; + + usize::try_from(held.unwrap_or(r.obj_number)).ok() +} + /// Maximum number of allowed xref `Prev` pointers before we abort. const MAX_XREF_CHAIN_DEPTH: usize = 256; @@ -882,17 +910,8 @@ fn populate_from_xref_table<'a>( reader.skip_white_spaces(); let mut max_obj = 0; - - if let Some(prev) = trailer.get::(PREV) { - // First insert the entries from any previous xref tables. - populate_xref_impl_inner(data, prev as usize, insert_map, visited)?; - } - - // In hybrid files, entries in `XRefStm` should have higher priority, therefore we insert them - // after looking at `PREV`. - if let Some(xref_stm) = trailer.get::(XREF_STM) { - populate_xref_impl_inner(data, xref_stm as usize, insert_map, visited)?; - } + // PdfCraft patch: (#2366) this section's entries are read first, for `prev_offset`. + let mut own = XrefMap::default(); while let Some(header) = reader.read_without_context::() { reader.skip_white_spaces(); @@ -908,7 +927,7 @@ fn populate_from_xref_table<'a>( // Specification says we should ignore any object number > SIZE, but probably // not important? if entry.used { - insert_map.insert( + own.insert( ObjectIdentifier::new(obj_number as i32, entry.gen_number), EntryType::Normal(entry.offset), ); @@ -916,6 +935,19 @@ fn populate_from_xref_table<'a>( } } + if let Some(prev) = prev_offset(data, &trailer, &own) { + // First insert the entries from any previous xref tables. + populate_xref_impl_inner(data, prev, insert_map, visited)?; + } + + // In hybrid files, entries in `XRefStm` should have higher priority, therefore we insert them + // after looking at `PREV`. + if let Some(xref_stm) = trailer.get::(XREF_STM) { + populate_xref_impl_inner(data, xref_stm as usize, insert_map, visited)?; + } + + insert_map.extend(own); + Some(trailer.data()) } @@ -929,11 +961,6 @@ fn populate_from_xref_stream<'a>( .read_with_context::>>(&ReaderContext::dummy())? .get(); - if let Some(prev) = stream.dict().get::(PREV) { - // First insert the entries from any previous xref tables. - let _ = populate_xref_impl_inner(data, prev as usize, insert_map, visited)?; - } - let size = stream.dict().get::(SIZE)?; let [f1_len, f2_len, f3_len] = stream.dict().get::<[u8; 3]>(W)?; @@ -950,6 +977,8 @@ fn populate_from_xref_stream<'a>( } let xref_data = stream.decoded().ok()?; + // PdfCraft patch: (#2366) this section's entries are read first, for `prev_offset`. + let mut own = XrefMap::default(); let mut xref_reader = Reader::new(xref_data.as_ref()); if let Some(arr) = stream.dict().get::>(INDEX) { @@ -963,21 +992,20 @@ fn populate_from_xref_stream<'a>( f1_len, f2_len, f3_len, - insert_map, + &mut own, )?; } } else { - xref_stream_subsection( - &mut xref_reader, - 0, - size, - f1_len, - f2_len, - f3_len, - insert_map, - )?; + xref_stream_subsection(&mut xref_reader, 0, size, f1_len, f2_len, f3_len, &mut own)?; } + if let Some(prev) = prev_offset(data, stream.dict(), &own) { + // First insert the entries from any previous xref tables. + let _ = populate_xref_impl_inner(data, prev, insert_map, visited)?; + } + + insert_map.extend(own); + Some(stream.dict().data()) } @@ -1434,6 +1462,78 @@ mod tests { let _result = populate_xref_impl(pdf.as_ref(), xref_pos, &mut xref_map); } + #[test] + fn prev_as_reference_reaches_the_earlier_section() { + let mut pdf = b"%PDF-1.0\n1 0 obj\n<< /Type /Catalog /Pages 2 0 R >>\nendobj\n".to_vec(); + let first_xref_pos = pdf.len(); + pdf.extend_from_slice( + format!( + "xref\n\ + 0 2\n\ + 0000000000 65535 f \n\ + 0000000009 00000 n \n\ + trailer\n<< /Size 2 /Root 1 0 R >>\n\ + startxref\n{first_xref_pos}\n%%EOF\n" + ) + .as_bytes(), + ); + let second_xref_pos = pdf.len(); + pdf.extend_from_slice( + format!( + "xref\n\ + 0 1\n\ + 0000000000 65535 f \n\ + trailer\n<< /Size 2 /Root 1 0 R /Prev {first_xref_pos} 0 R >>\n\ + startxref\n{second_xref_pos}\n%%EOF" + ) + .as_bytes(), + ); + + let mut xref_map = FxHashMap::default(); + let xref_pos = find_last_xref_pos(pdf.as_ref()).unwrap(); + assert_eq!(xref_pos, second_xref_pos); + populate_xref_impl(pdf.as_ref(), xref_pos, &mut xref_map).unwrap(); + assert!(xref_map.contains_key(&ObjectIdentifier::new(1, 0))); + } + + #[test] + fn prev_as_reference_to_an_object_holding_the_offset_reads_that_offset() { + let mut pdf = b"%PDF-1.0\n1 0 obj\n<< /Type /Catalog /Pages 2 0 R >>\nendobj\n".to_vec(); + let first_xref_pos = pdf.len(); + pdf.extend_from_slice( + format!( + "xref\n\ + 0 2\n\ + 0000000000 65535 f \n\ + 0000000009 00000 n \n\ + trailer\n<< /Size 2 /Root 1 0 R >>\n\ + startxref\n{first_xref_pos}\n%%EOF\n" + ) + .as_bytes(), + ); + // Object 3 holds the offset; read as offset 3, `Prev` would point inside the header. + let held_pos = pdf.len(); + pdf.extend_from_slice(format!("3 0 obj\n{first_xref_pos}\nendobj\n").as_bytes()); + let second_xref_pos = pdf.len(); + pdf.extend_from_slice( + format!( + "xref\n\ + 3 1\n\ + {held_pos:010} 00000 n \n\ + trailer\n<< /Size 4 /Root 1 0 R /Prev 3 0 R >>\n\ + startxref\n{second_xref_pos}\n%%EOF" + ) + .as_bytes(), + ); + + let mut xref_map = FxHashMap::default(); + let xref_pos = find_last_xref_pos(pdf.as_ref()).unwrap(); + assert_eq!(xref_pos, second_xref_pos); + populate_xref_impl(pdf.as_ref(), xref_pos, &mut xref_map).unwrap(); + assert!(xref_map.contains_key(&ObjectIdentifier::new(1, 0))); + assert!(xref_map.contains_key(&ObjectIdentifier::new(3, 0))); + } + #[test] fn find_last_xref_uses_last_startxref() { let pdf = b"%PDF-1.0\nstartxref\n5\n%%EOF\nstartxref\n42\n%%EOF";