mirror of
https://github.com/storytold/pdfcraft.git
synced 2026-11-06 18:52:36 +00:00
M2: keep an interpolated soft mask smooth on a shrunk image's grid
A soft mask no larger than its area-shrunk image is sampled onto the image's grid, and it was always sampled nearest-neighbour: a mask that asks for /Interpolate became a hard step where main drew a ramp (jpeskov's 64 x 64 image at 32 x 32 under a 2 x 2 mask). An interpolated mask is now blended bilinearly onto the grid, centres aligned; one without /Interpolate is still sampled nearest, which keeps the colour-fringe fix. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
kronbiiandClaude Opus 5.5 committed
1 parent
ff227b770c
commit
5ed2f4ba4f
3 files changed
+93
-12
No files matched your search
@@ -6734,6 +6734,35 @@ fn a_smaller_soft_mask_does_not_bleed_transparent_colour_when_minified() {
|
||||
assert!(r >= 254 && g.abs_diff(128) <= 1 && b == g, "half-covered red over white, got ({r}, {g}, {b})");
|
||||
}
|
||||
|
||||
/// A smaller soft mask that asks for `/Interpolate` stays smooth when it is sampled onto the grid
|
||||
/// of an area-shrunk image. Here a 64 × 64 black image is drawn at 32 × 32 under a 2 × 2 mask,
|
||||
/// opaque on the left and clear on the right: the mask is enlarged while the image shrinks, and
|
||||
/// sampled nearest-neighbour onto the image's grid the edge became a hard black and white step.
|
||||
#[test]
|
||||
fn an_interpolated_smaller_soft_mask_stays_smooth_when_its_image_is_minified() {
|
||||
let content = "q 32 0 0 32 0 0 cm /Im0 Do Q";
|
||||
let (image, mask) = ("00".repeat(64 * 64), "FF00FF00");
|
||||
let pdf = format!(
|
||||
"%PDF-1.4\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 32 32] /Contents 4 0 R /Resources << /XObject << /Im0 5 0 R >> >> >> endobj\n\
|
||||
4 0 obj << /Length {} >> stream\n{content}\nendstream endobj\n\
|
||||
5 0 obj << /Type /XObject /Subtype /Image /Width 64 /Height 64 /ColorSpace /DeviceGray /BitsPerComponent 8 /SMask 6 0 R /Filter /ASCIIHexDecode /Length {} >> stream\n{image}>\nendstream endobj\n\
|
||||
6 0 obj << /Type /XObject /Subtype /Image /Width 2 /Height 2 /ColorSpace /DeviceGray /BitsPerComponent 8 /Interpolate true /Filter /ASCIIHexDecode /Length {} >> stream\n{mask}>\nendstream endobj\n\
|
||||
trailer << /Root 1 0 R >>\n%%EOF\n",
|
||||
content.len(),
|
||||
image.len() + 1,
|
||||
mask.len() + 1
|
||||
);
|
||||
let mut renderer = PageRenderer::new(Arc::new(pdf.into_bytes()), RenderConfig::default());
|
||||
let page = renderer.render(RenderRequest { page: 0, kind: RequestKind::Pixels, scale: 1.0, ..Default::default() });
|
||||
assert!(page.error.is_none(), "{:?}", page.error);
|
||||
assert_eq!((page.width, page.height), (32, 32));
|
||||
let row: Vec<u8> = page.rgba.as_chunks::<4>().0.iter().skip(16 * 32).take(32).map(|[r, ..]| *r).collect();
|
||||
let ramp = row.iter().filter(|v| (1..255).contains(*v)).count();
|
||||
assert!(ramp >= 8 && row.is_sorted() && row.first() == Some(&0) && row.last() == Some(&255), "a smooth black to white edge, got {row:?}");
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn non_interpolated_alpha_images_keep_their_colours_and_mask_when_minified() {
|
||||
let palette: [[u8; 3]; 8] = [[0, 0, 0], [255, 255, 255], [255, 0, 0], [0, 255, 0], [0, 0, 255], [255, 255, 0], [255, 0, 255], [0, 255, 255]];
|
||||
|
||||
Vendored
+1
-1
@@ -40,7 +40,7 @@ Other resource categories retain their existing parent-chain lookup.
|
||||
| Crate | Version | Licence | Patches | Test |
|
||||
|---|---|---|---|---|
|
||||
| hayro-interpret | 0.7.0 | Apache-2.0 OR MIT | (1) select `/AP /N` appearance states via `/AS` (checkboxes, radios, stateful icons) and honour the NoView flag; (2) Type3 Unicode fallback to `/Encoding` glyph names, then printable ASCII; (3) `Type3Glyph::advance_width`; (4) `InterpreterSettings::ocg_overrides` for viewer layer toggles; (5) soft masks whose group lacks `/CS` were dropped (Chrome gradient text); (6) paint nesting cap `MAX_PAINT_NESTING` for tiling patterns and Type 3 glyphs (self-referencing content overflowed the stack); (7) CID width ranges in `/W` and `/W2` clamped to `MAX_CID` (a `0 4294967295 w` range hung); (8) `InterpreterSettings::hide_comments` skips markup annotations but keeps widgets and links (View ▸ Hide all comments); (9) `image_size_ok`: images and masks over 2^28 pixels are not decoded (a fuzzed `/W 4294967295` stencil mask allocated 4 GiB); (10) `MAX_NESTED_PAINTS`: nested paints (forms, Type 3 glyphs and tiling patterns inside one another) share a per-page budget of 50,000 (a glyph showing eight glyphs of its own font, sixteen deep, hung); (11) depends on skrifa 0.47 instead of 0.42 (upstream read-fonts fixed a Type 1 tokenizer that recursed through runs of numbers: a fuzzed font hung or overflowed the stack), with the one API change (`Charset::glyph_id` returns `Option`); (12) annotation appearances whose `/BBox` or `/Matrix` collapses to a line or a point are skipped (mapping them onto `/Rect` divided by zero and handed the device infinite or NaN matrices); (13) a Highlight annotation without a usable normal appearance is drawn from its `/QuadPoints`, `/C` and `/CA` with Multiply blending, as pdfcraft-annot draws highlights (it was not drawn at all); (14) simple-font `/Widths` (`read_widths`): entries only for codes 0–255 (one entry per code below `/FirstChar` was allocated: `4294967295` asked for 34 GB), an entry that isn't a number leaves its code missing instead of ending the array, and a `/LastChar` below `/FirstChar` gives no widths instead of discarding the font for a standard one; (15) the appearance box is mapped onto `/Rect` corner to corner: the translation now accounts for the scale (an appearance whose box didn't start at the origin and differed in size from `/Rect` was drawn shifted); (16) a clip set by `W`/`W*` takes effect after whichever path-painting operator ends the path (`S`, `f`, `B`, … as well as `n`; ISO 32000-2 §8.5.4): it was applied only on `n`, so `re W* S` clipped nothing and the clip stayed pending for a later, unrelated `n`; (17) `InterpreterSettings::cancelled`: once set, interpretation stops before the next content operator (a render pool sets it for every worker when dropped, after an edit or on closing, and for one worker when the watchdog gives up on its render, so renders whose answers nobody can receive stop instead of running to the end); (18) `MAX_PAGE_CONTENT`: the content a page holds at once (its contents, and the forms, tiling patterns and Type 3 glyph procedures being painted) stays within 512 MiB (`decode_content`; once it runs out, `InterpreterWarning::ContentTruncated` is reported (once per page by pdfcraft-render) so a truncated page is not a clean render; each level gives its bytes back when it finishes): forms nest fifty deep and each level kept its content while the next ran, so a form painting itself around a stream inflating to 256 MiB would have held over 12 GB; and Type 0 sampled functions take at most `MAX_SAMPLE_ENTRIES` (2^21) table points and `MAX_SAMPLE_VALUES` (2^23) samples, read no further than `/Size` asks (256 MiB of 1-bit samples asked for over 8 GB); (19) mesh shadings (types 4–7) are sampled only inside the area being drawn (`ShadingPattern::encode_within`, which the vendored hayro renderer calls with that area plus a pixel), within 8 visits per pixel of it plus 4 per triangle (`TriangleSampler`), and patches are triangulated one at a time: points far off the page were sampled over their whole bounding box, up to 65536 × 65536 entries (a fuzzed 147-byte patch stream; a synthetic page passed 6 GB in six seconds), ten thousand overlapping triangles ran for minutes, and every patch became 722 triangles before any limit; meshes hold at most `MAX_MESH_PATCHES` (2^16) patches and `MAX_MESH_TRIANGLES` (2^20) triangles, a lattice needs two to 2^19 vertices per row (`/VerticesPerRow 0` pushed empty rows for ever; one huge row read the whole stream), and a page samples at most `MAX_PAGE_MESH_TRIANGLES` (2^25) mesh triangles in all (a mesh painted a thousand times was triangulated a thousand times); each cut logs a warning; (20) PDF function construction is limited to 64 levels and 10,000 total nodes with cycle detection; calculator parsing and evaluation share procedure depth/work budgets, integer division/bitshift/rotation/index are panic-free, and fixed-size stack errors propagate; (21) a Type 0 font drawn with a substitute that isn't CID-keyed (it isn't embedded, or its program doesn't load) draws `.nLine truncated
|
||||
| hayro | 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 | 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 | (1) `raster::tests::jbig2_regions_of_billions_of_pixels_are_refused`, `raster::tests::jbig2_halftone_grids_past_their_bound_are_refused`; (2) the nightly `cargo xtask fuzz` finding, which now finishes in about a second; (3) `raster::tests::jbig2_symbol_dictionaries_that_never_advance_terminate`; (4) `segment::tests::test_referred_to_count_is_capped` (`cargo test --manifest-path vendor/hayro-jbig2/Cargo.toml`); (5) `raster::tests::jbig2_regions_held_past_a_pages_bound_are_refused`, `jbig2_symbols_without_pixels_count_towards_a_pages_bound`, `jbig2_retained_contexts_count_towards_a_pages_bound`, `jbig2_huffman_tables_count_towards_a_pages_bound`, `jbig2_new_symbols_count_towards_a_pages_bound`, `jbig2_new_symbols_are_held_to_what_a_page_has_left`, `jbig2_pattern_dictionaries_count_towards_a_pages_bound`, and in the crate (`cargo test --manifest-path vendor/hayro-jbig2/Cargo.toml`) `decode::symbol::tests::exported_symbols_are_counted_before_they_are_copied`, `tests::the_room_left_shrinks_as_segments_are_stored`; (6) `raster::tests::jbig2_segments_referring_to_too_many_symbols_are_refused`; (7) `raster::tests::jbig2_pattern_dictionaries_too_large_to_shift_still_draw`, `jbig2_shifted_patterns_never_refuse_an_image`; (8) `raster::tests::jbig2_huffman_tables_of_too_many_lines_are_refused`, `jbig2_streams_of_too_many_segments_are_reLine 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
|
||||
|
||||
Vendored
+63
-11
@@ -193,27 +193,67 @@ fn image_buffer(len: usize) -> Option<Vec<u8>> {
|
||||
Some(out)
|
||||
}
|
||||
|
||||
/// PdfCraft patch: `mask` sampled onto the grid of a `width` × `height` image, each image sample
|
||||
/// taking the mask sample under its centre. `None` for an empty side or a buffer over the limits.
|
||||
/// PdfCraft patch: `mask` sampled onto the grid of a `width` × `height` image (no side smaller
|
||||
/// than the mask's). Each image sample takes the mask sample under its centre or, for a mask that
|
||||
/// asks for `/Interpolate`, the bilinear blend of the four around it, so the mask's edges stay as
|
||||
/// smooth as when it was enlarged on its own. `None` for an empty side, an image side smaller than
|
||||
/// the mask's, or a buffer over the limits.
|
||||
fn mask_on_image_grid(mask: &LumaData, width: u32, height: u32) -> Option<Vec<u8>> {
|
||||
if width == 0 || height == 0 || mask.width == 0 || mask.height == 0 {
|
||||
return None;
|
||||
}
|
||||
let mut out = image_buffer(source_byte_len(width, height, 1, MAX_IMAGE_PIXELS)?)?;
|
||||
let mut columns = Vec::new();
|
||||
columns.try_reserve_exact(width as usize).ok()?;
|
||||
columns.extend((0..width).map(|x| nearest_source_index(mask.width, width, x)));
|
||||
let columns = grid_axis(mask.width, width, mask.interpolate)?;
|
||||
let rows = grid_axis(mask.height, height, mask.interpolate)?;
|
||||
let mask_width = mask.width as usize;
|
||||
for y in 0..height {
|
||||
let start = nearest_source_index(mask.height, height, y).checked_mul(mask_width)?;
|
||||
let row = mask.data.get(start..start.checked_add(mask_width)?)?;
|
||||
for &x in &columns {
|
||||
out.push(*row.get(x)?);
|
||||
let row = |y: usize| {
|
||||
let start = y.checked_mul(mask_width)?;
|
||||
mask.data.get(start..start.checked_add(mask_width)?)
|
||||
};
|
||||
let one = u64::from(GRID_ONE);
|
||||
for &(y0, y1, fy) in &rows {
|
||||
let (top, bottom, fy) = (row(y0)?, row(y1)?, u64::from(fy));
|
||||
for &(x0, x1, fx) in &columns {
|
||||
let fx = u64::from(fx);
|
||||
let blend = |r: &[u8]| Some(u64::from(*r.get(x0)?) * (one - fx) + u64::from(*r.get(x1)?) * fx);
|
||||
// At most 255 × GRID_ONE², so the sum fits in a u64 and the result in a u8.
|
||||
let v = (blend(top)? * (one - fy) + blend(bottom)? * fy + one * one / 2) / (one * one);
|
||||
out.push(v.min(255) as u8);
|
||||
}
|
||||
}
|
||||
Some(out)
|
||||
}
|
||||
|
||||
/// PdfCraft patch: fixed-point unit of [`grid_axis`]'s blend weights.
|
||||
const GRID_ONE: u32 = 1 << 16;
|
||||
|
||||
/// PdfCraft patch: for each of `dst` samples (`dst >= src`) taken from `src` along one axis, the
|
||||
/// two source samples it lies between and the weight of the second, in [`GRID_ONE`] units.
|
||||
/// Centres line up: target `t` lies at `(t + ½)·src/dst − ½` source samples, held to the ends.
|
||||
/// Without `smooth` both are the nearest sample, so the weight does not matter.
|
||||
fn grid_axis(src: u32, dst: u32, smooth: bool) -> Option<Vec<(usize, usize, u32)>> {
|
||||
if src == 0 || dst < src {
|
||||
return None;
|
||||
}
|
||||
let mut out = Vec::new();
|
||||
out.try_reserve_exact(dst as usize).ok()?;
|
||||
let last = u64::from(src - 1) << 16;
|
||||
for t in 0..dst {
|
||||
if !smooth {
|
||||
let s = nearest_source_index(src, dst, t);
|
||||
out.push((s, s, 0));
|
||||
continue;
|
||||
}
|
||||
// In u128, as `(2t + 1)·src·2^16` can pass 2^64 for a long side; the quotient is at
|
||||
// most `src·2^16`, so it fits back in a u64.
|
||||
let centre = ((2 * u128::from(t) + 1) * u128::from(src) << 16) / (2 * u128::from(dst));
|
||||
let at = u64::try_from(centre).ok()?.saturating_sub(u64::from(GRID_ONE / 2)).min(last);
|
||||
let s = (at >> 16) as usize;
|
||||
out.push((s, (s + 1).min(src as usize - 1), (at & 0xFFFF) as u32));
|
||||
}
|
||||
Some(out)
|
||||
}
|
||||
|
||||
/// PdfCraft patch (#624): the source index that PicScale's nearest-neighbour plan copies for
|
||||
/// destination `index` of `dst` samples taken from `src`. It is the same fixed-point centre
|
||||
/// sampling as `ResampleNearestPlan`, so these are the samples a nearest resize would copy.
|
||||
@@ -2908,7 +2948,18 @@ mod area_shrink_tests {
|
||||
assert_eq!(mask_on_image_grid(&mask(&[10, 20], 2, 1), 4, 2), Some(vec![10, 10, 20, 20, 10, 10, 20, 20]));
|
||||
// Centres of 7 samples over 3: 0.5/7·3 = 0.21 → 0, 1.5/7·3 = 0.64 → 0, 2.5/7·3 = 1.07 → 1, …
|
||||
assert_eq!(mask_on_image_grid(&mask(&[1, 2, 3], 3, 1), 7, 1), Some(vec![1, 1, 2, 2, 2, 3, 3]));
|
||||
assert_eq!(mask_on_image_grid(&mask(&[1, 2, 3, 4], 1, 4), 1, 2), Some(vec![2, 4]));
|
||||
}
|
||||
|
||||
/// A mask that asks for `/Interpolate` is blended between the samples around each centre,
|
||||
/// and held at its ends: the centres of 4 samples over 2 lie at -¼, ¼, ¾ and 1¼.
|
||||
#[test]
|
||||
fn an_interpolated_mask_is_blended_onto_the_image_grid() {
|
||||
let smooth = |data: &[u8], width, height| LumaData { interpolate: true, ..mask(data, width, height) };
|
||||
assert_eq!(mask_on_image_grid(&smooth(&[0, 255], 2, 1), 4, 2), Some(vec![0, 64, 191, 255, 0, 64, 191, 255]));
|
||||
// Centres of 7 samples over 3 lie 3/7 apart, from -2/7 to 2 2/7: a ramp, flat at the ends.
|
||||
assert_eq!(mask_on_image_grid(&smooth(&[0, 70, 140], 3, 1), 7, 1), Some(vec![0, 10, 40, 70, 100, 130, 140]));
|
||||
assert_eq!(mask_on_image_grid(&smooth(&[0, 255], 1, 2), 1, 4), Some(vec![0, 64, 191, 255]));
|
||||
assert_eq!(mask_on_image_grid(&smooth(&[7, 9], 2, 1), 2, 1), Some(vec![7, 9]), "same size is unchanged");
|
||||
}
|
||||
|
||||
#[test]
|
||||
@@ -2916,6 +2967,7 @@ mod area_shrink_tests {
|
||||
assert_eq!(mask_on_image_grid(&mask(&[], 0, 1), 4, 1), None, "an empty mask");
|
||||
assert_eq!(mask_on_image_grid(&mask(&[1, 2], 2, 1), 0, 1), None, "an empty image");
|
||||
assert_eq!(mask_on_image_grid(&mask(&[1], 2, 1), 4, 1), None, "mask data shorter than its size");
|
||||
assert_eq!(mask_on_image_grid(&mask(&[1, 2, 3, 4], 1, 4), 1, 2), None, "a mask larger than the image");
|
||||
}
|
||||
|
||||
/// Every target sample's weights add up to exactly one, and together the targets take every
|
||||
|
||||
Reference in new issue
Block a user