PdfCraft: An open-source PDF reader and editor written by scratch in pure Rust
fix: bound soft-wrap metadata and preserve unknown backdrop content
FredAppsee71348bc862
diff --git a/crates/edit/src/backdrop.rs b/crates/edit/src/backdrop.rsindex 156501d95..a7973d887 100644--- a/crates/edit/src/backdrop.rs+++ b/crates/edit/src/backdrop.rs@@ -379,7 +379,7 @@ fn scan(doc: &Document, p: &pdfcraft_model::Page, swap: Option<(ObjRef, &[u8])>)}let bytes = match swap {Some((with, b)) if with == *r => b.to_vec(),- _ => s.decoded().unwrap_or_default(),+ _ => s.decoded().ok()?,};starts.push(total);total = total.saturating_add(bytes.len()).saturating_add(1);diff --git a/crates/edit/src/backdrop_tests.rs b/crates/edit/src/backdrop_tests.rsindex 6ca100adc..98578da57 100644--- a/crates/edit/src/backdrop_tests.rs+++ b/crates/edit/src/backdrop_tests.rs@@ -556,3 +556,16 @@ fn graphics_state_set_back_before_the_fill_still_finds_the_backdrop() {assert_eq!(page_backdrop(&doc, 0).unwrap(), Some(Backdrop::Fill), "{state}");}}++#[test]+fn an_undecodable_stream_before_a_white_fill_keeps_the_backdrop_unknown() {+ let objs = vec![+ "<< /Type /Catalog /Pages 2 0 R >>".to_string(),+ "<< /Type /Pages /Kids [3 0 R] /Count 1 /MediaBox [0 0 300 200] >>".into(),+ "<< /Type /Page /Parent 2 0 R /Contents [4 0 R 5 0 R] >>".into(),+ stream("/Filter /FlateDecode", "not a deflate stream"),+ stream("", &format!("1 g 0 0 300 200 re f {TEXT}")),+ ];+ let doc = build(&objs);+ assert_eq!(page_backdrop(&doc, 0).unwrap(), None, "unknown earlier paint must not be treated as an empty stream");+}diff --git a/crates/edit/src/tests.rs b/crates/edit/src/tests.rsindex 5187a2aec..3650ffd0b 100644--- a/crates/edit/src/tests.rs+++ b/crates/edit/src/tests.rs@@ -8552,3 +8552,28 @@ fn wrapped_rows_keep_alignment_separate_from_hard_break_markers() {let content = String::from_utf8_lossy(&page_content_bytes(&doc, 0)).into_owned();assert!(content.contains("/PCSoft") && content.contains("/PCHard"), "both break kinds survive: {content}");}++#[test]+fn hostile_soft_wrap_counts_fail_before_reflow_allocates() {+ for marker in [+ "/PCSoft << /N 9223372036854775807 >> BDC EMC",+ "/PCSoft << /N 16777217 >> BDC EMC",+ "/PCSoft << /N 8388608 >> BDC EMC /PCSoft << /N 8388609 >> BDC EMC",+ ] {+ let doc = text_page(&format!("BT /F1 12 Tf 20 700 Td (First) Tj {marker} 0 -14 Td (Second) Tj ET"));+ let error = text::text_lines(&doc, 0).unwrap_err();+ assert!(error.to_string().contains("too large"), "{marker}: {error}");+ }+}++#[test]+fn ordinary_soft_wrap_counts_keep_their_spaces() {+ for gap in [0, 1, 2, 8] {+ let doc = text_page(&format!("BT /F1 12 Tf 20 700 Td (First) Tj /PCSoft << /N {gap} >> BDC EMC 0 -14 Td (Second) Tj ET"));+ let lines = text::text_lines(&doc, 0).unwrap();+ assert_eq!(lines.len(), 2);+ let blocks = text::text_blocks(&doc, 0).unwrap();+ assert_eq!(blocks.len(), 1);+ assert_eq!(blocks[0].reflow_text, format!("First{}Second", " ".repeat(gap)));+ }+}diff --git a/crates/edit/src/text/interp.rs b/crates/edit/src/text/interp.rsindex 73ca1b142..af9a51f0d 100644--- a/crates/edit/src/text/interp.rs+++ b/crates/edit/src/text/interp.rs@@ -807,6 +807,13 @@ pub(super) fn interpret(.and_then(Object::as_int).and_then(|n| usize::try_from(n).ok()).unwrap_or(1);+ // The marker is untrusted and later expands into spaces during reflow.+ // Charge it to the same page-wide budget as glyph text, so many individually+ // small markers cannot multiply the allocation past the limit either.+ carry.text_left = carry+ .text_left+ .checked_sub(soft_gap)+ .ok_or_else(|| EditError::Invalid("the page's text is too large to read".into()))?;} else if op.name(0) == Some(b"PCHard") {hard_break = true;soft_break = false;diff --git a/crates/filters/README.md b/crates/filters/README.mdindex e52a6cb33..0c34857c4 100644--- a/crates/filters/README.md+++ b/crates/filters/README.md@@ -5,7 +5,6 @@ PDF stream filters: the decoders and encoders behind `/Filter` and `/DecodeParms- **Layer:** L0, standalone. No dependency on any other PdfCraft crate. `cos` depends on it (architecture §3 rule 3).- **Licence:** MIT OR Apache-2.0. Clean-room: written from ISO 32000-2 §7.4, RFC 1950/1951 (through `flate2` with the pure-Rust `miniz_oxide` backend), TIFF 6.0 §14 (predictor 2) and RFC 2083 §6 (PNG filters). CCITT Group 4 encoding (ITU-T T.6) is the `fax` crate's (MIT, already in the tree through `tiff`), checked here by round trips through an independent decoder; CCITT decoding (T.4 and T.6) is the `hayro-ccitt` crate's (MIT OR Apache-2.0, already in the tree through hayro), bounded here. JBIG2 generic region encoding is written from the public ISO/IEC 14492 Final Committee Draft (WG1 N1359, 1999); Annex H.2 checks the arithmetic coder byte for byte.-Lossless symbol coding is also implemented: exact-copy dictionaries/text regions, bounded by the encoder; no approximate or lossy symbol substitution.- `#![forbid(unsafe_code)]`. Builds for `wasm32-unknown-unknown`.## API@@ -29,7 +28,6 @@ pub struct CcittParams { k, columns, rows, end_of_line, encoded_byte_align, end_decode_ccitt(data, ¶ms, max_rows) -> Result<Vec<u8>, FilterError> // CCITT fax as CCITTFaxDecode gives it; columns <= MAX_CCITT_COLUMNSencode_jbig2_generic(data, columns, rows) -> Result<Vec<u8>, FilterError> // 1-bit rows as lossless JBIG2 for JBIG2Decode; columns <= MAX_JBIG2_COLUMNSencode_jbig2(data, columns, rows) -> Result<Vec<u8>, FilterError> // 1-bit rows as lossless JBIG2 for JBIG2Decode, symbol coded when that is smaller; columns <= MAX_JBIG2_COLUMNS-encode_jbig2_generic(data, columns, rows) -> Result<Vec<u8>, FilterError> // the same as one generic region```- `chain` is applied first to last, as in a `/Filter` array.@@ -49,7 +47,6 @@ encode_jbig2_generic(data, columns, rows) -> Result<Vec<u8>, FilterError> // t| ASCII85Decode | `<~` prefix, `z`, white space, `~>` (or bare `~`, or none) EOD, final partial group; `z` inside a group, a 1-char final group, overflow or bad characters → Corrupt | `z` for zero groups, newline every 75 characters, `~>` || RunLengthDecode | 0–127 literal, 129–255 repeat, 128 EOD (optional); truncated run → Corrupt | runs of ≥2 repeat, literals up to 128, 128 || CCITTFaxDecode | not in a chain (`Unsupported`); `decode_ccitt` decodes Group 3 and Group 4 on its own, as rows of 1-bit samples each on a new byte, black 0 unless `black_is_1`, at most `max_rows` rows (fewer with `/Rows`), the rows before any damage, up to 1,048,576 samples a row; Group 3 rows on bytes are read by their end-of-line codes when the data starts with one and on bytes otherwise, whatever `end_of_line` says, so data with codes but none before the first row (not as T.4 sends them) is read on bytes, as the renderer draws it, and at `k` 0 may come out as other rows (`pdfcraft_cos::Document::decoded_image` calls it for a fax image, after the filters before it) | `encode_g4`: Group 4 (`/K -1`) with an end-of-block mark, 0 bits coded black so `/BlackIs1 false` decodes the same bits; rows packed MSB first, each on a new byte, padding bits and trailing bytes ignored; up to 32,767 samples a row (the encoder counts positions in 16 bits); no rows or columns, or too wide → Unsupported, too few bytes → Corrupt |-| JBIG2Decode | not here (`Unsupported`; the renderer and image export decode it with `hayro-jbig2`) | `encode_jbig2_generic`: the embedded organisation (D.3) with a page information segment and an immediate lossless generic region (7.4.6), no `/JBIG2Globals`; template 0 with its nominal AT pixels and typical prediction (6.2.5), coded with the MQ arithmetic coder (Annex E, Table E.1) and ended by its 0xFF 0xAC marker. A 0 sample is coded as a JBIG2 1 (black), since `JBIG2Decode` gives black as 0, so the stream decodes to the same bits; rows packed MSB first, each on a new byte, padding bits and trailing bytes ignored; up to 1,048,576 samples a row; no rows or columns, or too wide → Unsupported, too few bytes → Corrupt || JBIG2Decode | not here (`Unsupported`; the renderer and image export decode it with `hayro-jbig2`) | `encode_jbig2_generic`: the embedded organisation (D.3) with a page information segment and an immediate lossless generic region (7.4.6), no `/JBIG2Globals`; template 0 with its nominal AT pixels and typical prediction (6.2.5), coded with the MQ arithmetic coder (Annex E, Table E.1) and ended by its 0xFF 0xAC marker. A 0 sample is coded as a JBIG2 1 (black), since `JBIG2Decode` gives black as 0, so the stream decodes to the same bits; rows packed MSB first, each on a new byte, padding bits and trailing bytes ignored; up to 1,048,576 samples a row; no rows or columns, or too wide → Unsupported, too few bytes → Corrupt. `encode_jbig2`: the smaller of that and symbol coding (`jbig2/symbols.rs`): each distinct mark (8-connected black pixels, at most 256 a side) stored once in a symbol dictionary (7.4.2; arithmetic coded, each bitmap a template 0 generic region without typical prediction, the bitmaps sharing their contexts) and placed by immediate lossless text regions referring to it (7.4.3; bottom-left reference corner, strips of 1, 2, 4 or 8 rows, whichever is smallest), each of at most 10,000 instances over a band of rows, as the decoder PdfCraft renders with (`hayro-jbig2`) takes no more in one region, with larger marks, and in a second plan marks that occur once, in a generic region over their box. Only exact copies share a symbol (no refinement), so the stream decodes to the same bits; fewer than two symbols, more than 2^20 black runs, 65,536 distinct marks or 16 MiB of their pixels, or more than 2^24 rows, and the generic coding is used; a plan of more than 32,767 symbols (that decoder refuses more) isn't made |## Tests@@ -65,6 +62,7 @@ encode_jbig2_generic(data, columns, rows) -> Result<Vec<u8>, FilterError> // t## Status-M1.1/M1.2 for the general-purpose filters are done. Not yet here: the image codecs (DCT via zune-jpeg, JPX via hayro-jpeg2000, JBIG2, DCT encode), CCITT Group 3 encoding and Flate encode levels other than 6.+M1.1/M1.2 for the general-purpose filters are done. Not yet here: the image decoders (DCT via zune-jpeg, JPX via hayro-jpeg2000, JBIG2), DCT encoding, CCITT Group 3 encoding and Flate encode levels other than 6.+Lossless symbol coding is also implemented: exact-copy dictionaries/text regions, bounded by the encoder; no approximate or lossy symbol substitution.diff --git a/crates/optimize/README.md b/crates/optimize/README.mdindex 388345be7..9f96b1721 100644--- a/crates/optimize/README.md+++ b/crates/optimize/README.md@@ -80,13 +80,13 @@ let report = optimize_with_progress(&mut doc, &settings, &mut |stage| keep_going- Apart from the downsampling it is lossless: the samples keep their meaning, so the colourspace, decode array and `/Mask` stay, but for packed RGB, which becomes grey with one decodepair. Group 4 wins on scans, whose ragged edges defeat Flate; on clean computer-drawn 1-bit- art Flate can be smaller. Not yet: JBIG2, inline images, an image's own `/SMask` or `/Mask`+ art Flate can be smaller. Not yet: inline images, an image's own `/SMask` or `/Mask`image (only images drawn on a page are visited), and Group 4 for rows wider than 32,767samples.-Lossless JBIG2 is also available as Monochrome Images compression, with a bounded generic-region encoder and no symbol substitution. Export reads its embedded images and bounded shared globals.--The JBIG2 choice now uses a bounded exact-copy symbol dictionary when smaller than the generic-region result; lossy symbol substitution is not used.+ - Lossless JBIG2 uses bounded generic-region encoding or exact-copy symbol dictionaries when+ smaller. No lossy symbol substitution is used. Export reads embedded images and bounded+ shared globals.- **Discard objects:** thumbnails, alternate images, document tags, print settings.- **Clean up:** Flate for streams with no filter; for streams with an outer ASCII85 or ASCIIHexlayer, that layer is removed when the result is smaller (the inner filters keep their encodeddiff --git a/crates/ui-egui/src/canvas.rs b/crates/ui-egui/src/canvas.rsindex 3bbc91ef2..8b280ba75 100644--- a/crates/ui-egui/src/canvas.rs+++ b/crates/ui-egui/src/canvas.rs@@ -2019,6 +2019,11 @@ fn draw_pages(// its owner; in the gap between pages it has none).if ptr.pressed().is_some() {view.router.cancel();+ // The page widget is not focusable. Explicitly return keyboard ownership from Pages+ // when the user presses the document, without stealing focus through a modal.+ if let Some(id) = view.pages_focus_id {+ ui.memory_mut(|m| m.surrender_focus(id));+ }}let pointer = ptr.pos;// A press on a page makes it the current one (as in Acrobat), so a page command withdiff --git a/crates/ui-egui/src/canvas/page_pointer/tests.rs b/crates/ui-egui/src/canvas/page_pointer/tests.rsindex 124e37020..2cbde2b99 100644--- a/crates/ui-egui/src/canvas/page_pointer/tests.rs+++ b/crates/ui-egui/src/canvas/page_pointer/tests.rs@@ -410,12 +410,7 @@ fn page_modules_take_presses_from_the_router_without_repeating_hit_tests() {("tools/comments/input.rs", "select_input"),] {let source = std::fs::read_to_string(src.join(file)).expect("page input module");- let body = source- .lines()- .skip_while(|line| declares(line) != Some(function))- .take_while(|line| *line != "}")- .collect::<Vec<_>>()- .join("\n");+ let body = source.lines().skip_while(|line| declares(line) != Some(function)).take_while(|line| *line != "}").collect::<Vec<_>>().join("\n");// Forms reuse their hit test for hover text and to require release over the captured// widget. Neither chooses the press owner. Pin both calls to the current pointer `p`,// not the press origin, and reject an additional call or a changed argument.diff --git a/crates/ui-egui/tests/it/view.rs b/crates/ui-egui/tests/it/view.rsindex b9a01f408..aef5ddae7 100644--- a/crates/ui-egui/tests/it/view.rs+++ b/crates/ui-egui/tests/it/view.rs@@ -2310,3 +2310,22 @@ fn the_pages_panel_tools_are_off_without_page_editing_permission() {assert!(h.query_by_label("Delete the selected pages").is_none(), "its menu doesn't open");assert_eq!(h.state().session.get(id).unwrap().info.pages.len(), 3);}++#[test]+fn a_document_press_releases_pages_keyboard_focus_without_escape() {+ let mut h = harness(&[("panel", "pages")]);+ h.get_by_label("Page 2").click();+ h.run_steps(3);+ let focused = h.ctx.memory(|m| m.focused());+ assert!(focused.is_some(), "the thumbnail owns keyboard input");+ let pos = rect(&h, 1).unwrap().center();+ h.event(egui::Event::PointerMoved(pos));+ for pressed in [true, false] {+ h.event(egui::Event::PointerButton { pos, button: egui::PointerButton::Primary, pressed, modifiers: Modifiers::NONE });+ h.run_steps(1);+ }+ h.run_steps(2);+ assert_ne!(h.ctx.memory(|m| m.focused()), focused, "pressing the document relinquishes Pages focus without Escape");+ sidebar_key(&mut h, Key::A, Modifiers::COMMAND);+ assert!(h.state().views[0].selected.is_empty(), "Ctrl+A now belongs to the viewer, not page thumbnails");+}diff --git a/docs/pdf-spec-parity.md b/docs/pdf-spec-parity.mdindex e34a93127..b62ecbc17 100644--- a/docs/pdf-spec-parity.md+++ b/docs/pdf-spec-parity.md@@ -1,10 +1,8 @@# PDF specification and standards parity-> **Last reviewed:** 2026-10-10 · **Last updated:** 2026-10-26 · **Change:** minor (§7.4: redaction decodes CCITT fax images, Group 3 on bytes aside; earlier, §7.4: CCITT decoding in `pdfcraft-filters`) · **Target:** Adobe Acrobat Pro (Acrobat DC, continuous track 26.002.21931, macOS)--Lossless JBIG2 encoding and image export are included alongside CCITT decoding and monochrome downsampling; combined validation is pending.+> Integration update 2026-10-30: lossless JBIG2 generic and exact-copy symbol coding are included; no lossy substitution. Combined tests passed at bdf5620; the subsequent review fixes require fresh CI.-JBIG2 exact-copy symbol dictionaries and text regions are included; lossy substitution is not supported.+> **Last reviewed:** 2026-10-10 · **Last updated:** 2026-10-26 · **Change:** minor (§7.4: redaction decodes CCITT fax images, Group 3 on bytes aside; earlier, §7.4: CCITT decoding in `pdfcraft-filters`) · **Target:** Adobe Acrobat Pro (Acrobat DC, continuous track 26.002.21931, macOS)How much of ISO 32000-2 (PDF 2.0) and the PDF subset standards PdfCraft implements, set againstwhat Acrobat Pro implements. This is PdfCraft's equivalent of a "geometry" or "codec" checklist:@@ -25,11 +23,7 @@ are borrowed; PDF 2.0 additions and most subset standards are missing. **150–2|---|---|---|---|---|| §7.2–7.5 | Syntax, objects, file structure, xref tables and streams, object streams, hybrid files, incremental updates | full | **own**, tolerant, repairs damaged files | `crates/cos`; corpus 958 files; fuzzed nightly || §7.4 | Stream filters: Flate, LZW, ASCII85, ASCIIHex, RunLength, predictors | full | **own** | `crates/filters` |-| §7.4 | Image filters: DCT, JPX, JBIG2, CCITTFax | full | **borrowed** (decode); CCITT Group 4 encoding | `core.image-filters` partial; own codecs M1.1/M1.2; CCITT decoding in `pdfcraft-filters` (`decode_ccitt`, through `hayro-ccitt`) for export, redaction and the Optimizer, which encodes Group 4 (`optimize.mono-compression`); no JBIG2 encoding |--Lossless JBIG2 encoding and image export are included alongside CCITT decoding and monochrome downsampling; combined validation is pending.--JBIG2 exact-copy symbol dictionaries and text regions are included; lossy substitution is not supported.+| §7.4 | Image filters: DCT, JPX, JBIG2, CCITTFax | full | **borrowed** (decode); CCITT Group 4 and lossless JBIG2 encoding | `core.image-filters` partial; own codecs M1.1/M1.2; CCITT decoding in `pdfcraft-filters` (`decode_ccitt`, through `hayro-ccitt`) for export, redaction and the Optimizer, which encodes Group 4 (`optimize.mono-compression`); lossless JBIG2 generic-region or exact-copy symbol encoding and image export; no lossy substitution || §7.5.8 | Linearization | R W | R only | `core.linearization` planned || §7.6.4 | Standard security handler R2–R6 (RC4 40/128, AES-128, AES-256), crypt filters, `/EncryptMetadata`, SASLprep | full | **own**, read and write | `crates/crypt`; written files open in Acrobat DC since #836 (#774: Acrobat needs the catalog outside object streams) || §7.6.5 | Public-key security handler | full | none | `core.open-public-key`, `protect.certificate-encryption` planned |@@ -140,10 +134,6 @@ JBIG2 exact-copy symbol dictionaries and text regions are included; lossy substi|---|---|---|| 2026-10-26 | minor | §7.4: redaction clears pixels in CCITT fax images through the CCITT decoder, instead of removing them whole (Group 4 and Group 3 off bytes; Group 3 on bytes is still removed whole, as the bootstrap renderer may draw it as other rows than the decoder reads) || 2026-10-26 | minor | §7.4: CCITT decoding (`hayro-ccitt`) in `pdfcraft-filters`, for export and the Optimizer |--Lossless JBIG2 encoding and image export are included alongside CCITT decoding and monochrome downsampling; combined validation is pending.--JBIG2 exact-copy symbol dictionaries and text regions are included; lossy substitution is not supported.| 2026-10-26 | minor | §7.4: CCITT Group 4 encoding (`fax`) in the Optimizer || 2026-10-14 | minor | §12.4.4: `/Trans` and `/Dur` read into `DocInfo::transitions` and reported by `doc_info` || 2026-10-11 | minor | §7.6.4: encrypted files we write open in Acrobat (#774, fixed by #836) |diff --git a/docs/target-app-parity.md b/docs/target-app-parity.mdindex cd018f048..46767848c 100644--- a/docs/target-app-parity.md+++ b/docs/target-app-parity.md@@ -1,10 +1,8 @@# PdfCraft parity with Adobe Acrobat Pro-> **Last reviewed:** 2026-10-25 · **Last updated:** 2026-10-26 · **Change:** minor (K Optimize and standards no longer lists monochrome downsampling as missing; scores and estimates unchanged)--Lossless JBIG2 encoding and image export are included alongside CCITT decoding and monochrome downsampling; combined validation is pending.+> Integration update 2026-10-30: lossless JBIG2 generic and exact-copy symbol coding are included; no lossy substitution. Combined tests passed at bdf5620; the subsequent review fixes require fresh CI.-JBIG2 exact-copy symbol dictionaries and text regions are included; lossy substitution is not supported.+> **Last reviewed:** 2026-10-25 · **Last updated:** 2026-10-26 · **Change:** minor (K Optimize and standards no longer lists monochrome downsampling as missing; scores and estimates unchanged)> **Last reviewed:** 2026-10-25 · **Last updated:** 2026-10-26 · **Change:** minor (`optimize.mono-compression` partial (CCITT Group 4): K Optimize and standards 15 shipped and 11 partial of 58, 35.3%; breadth 57.0% unweighted (423 + 75 of 808), mainstream 63.3% (292 + 45 of 497); estimates unchanged)> **Last reviewed:** 2026-10-25 · **Last updated:** 2026-10-25 · **Change:** minor (localization current state: Arabic logical catalog, explicit RTL direction and mirrored stock chrome; native/browser RTL workflows unqualified. Native release Hans face via LXGW WenKai Lite. Scores and estimates unchanged)@@ -214,11 +212,7 @@ full parity in that area.| H Digital signatures | 45 | 23 | 10 | 62.2% | 45% | 40–70 | PAdES B-B signing and validation (PKCS #12, macOS Keychain, Windows store with PIN prompts), certification, encrypted documents, certificate usage checks; B-T, LTV, OCSP/CRL with caller-supplied evidence. Missing: PKCS #11 and smart cards outside Windows, timestamp-server preferences, online revocation fetching, FieldMDP and field locking, OS trust store, EU Trusted Lists, compare signed version || I Scan and OCR | 26 | 5 | 2 | 23.1% | 15% | 40–75 | Searchable image (ocrs, Latin script without accents) on pages, ranges and many files. Missing: every other language (#744 Dutch; accents, CJK, Cyrillic, Arabic), editable-text output, deskew, rotation, despeckle, camera images beyond straightening (found or placed corners): orientation, clean-up, MRC compression, scanners || J Create and export | 34 | 12 | 3 | 39.7% | 25% | 55–100 | Create from images, multipage TIFF, text, clipboard, blank, many files at once; export PNG/JPEG/TIFF, text, RTF; Word and HTML partial. Missing: Office/HTML/web/PostScript to PDF, Excel and PowerPoint export, Word layout fidelity (#773), SVG/XML/EPS/PS/JPEG 2000 export, accessible text |-| K Optimize and standards | 58 | 15 | 11 | 35.3% | 20% | 65–115 | Reduce File Size and the Optimizer (images, discards, clean-up, space audit); PDF/A-2b/3b verify and convert (partial). Missing: Preflight (profiles, fixups, reports), PDF/A-1/4 and a/u levels, PDF/X, PDF/UA, PDF/E, PDF/VT, transparency flattening, font unembedding, monochrome JBIG2 |--Lossless JBIG2 encoding and image export are included alongside CCITT decoding and monochrome downsampling; combined validation is pending.--JBIG2 exact-copy symbol dictionaries and text regions are included; lossy substitution is not supported.+| K Optimize and standards | 58 | 15 | 11 | 35.3% | 20% | 65–115 | Reduce File Size and the Optimizer (images, CCITT and lossless JBIG2 monochrome compression, discards, clean-up, space audit); PDF/A-2b/3b verify and convert (partial). Missing: Preflight (profiles, fixups, reports), PDF/A-1/4 and a/u levels, PDF/X, PDF/UA, PDF/E, PDF/VT, transparency flattening, font unembedding, lossy/refinement JBIG2 || L Print | 39 | 15 | 1 | 39.7% | 35% | 30–55 | Acrobat's sizing, n-up, booklet, poster, comments & forms, preview, print-ready PDF, CUPS on macOS/Linux, the Windows spooler (#756) and the browser's print dialog on the web. Missing: print as image, PostScript, all print-production tools (output preview, separations, ink manager, printer marks, colour conversion) || M Accessibility | 61 | 38 | 1 | 63.1% | 30% | 40–70 | Accessibility Checker (all 32 rules, report, fixes), alternate text, title and language. Missing: autotag, Tags/Order/Content panels, Reading Order tool, artifact marking, table editor, Read Out Loud, full keyboard operation of the app, screen-reader audit || N Automation, preferences, misc | 75 | 20 | 5 | 30.0% | 35% | 25–45 | CLI, MCP, UI control channel, 141 automation tools, Action Wizard (run, create), compare (text, visual, report, side by side, Text/Visual filter). Missing: most Preferences pages, Acrobat's finer compare filters, Action Wizard management, custom commands, AI providers, rich media/3D, hosted web app |@@ -305,10 +299,6 @@ licensed OCR or AI model.| Date | Change | Summary ||---|---|---|| 2026-10-26 | minor | K Optimize and standards no longer lists monochrome downsampling as missing (black-and-white images above 450 ppi are averaged down to 300). Scores and estimates unchanged. |--Lossless JBIG2 encoding and image export are included alongside CCITT decoding and monochrome downsampling; combined validation is pending.--JBIG2 exact-copy symbol dictionaries and text regions are included; lossy substitution is not supported.| 2026-10-26 | minor | `optimize.mono-compression` became partial (CCITT Group 4), counted on the table's own measurement: K Optimize and standards 15 shipped and 11 partial of 58 (35.3%), no longer listing CCITT as missing; breadth 57.0% unweighted (423 + 75 of 808), mainstream 63.3% (292 + 45 of 497). Estimates unchanged. || 2026-10-25 | minor | Localization current state: Arabic catalogs stay logical, Arabic/Kurdish labels take an explicit RTL direction, and stock chrome mirrors; native/browser RTL input, IME and complex workflows remain unqualified. Native Simplified Chinese uses LXGW WenKai Lite; the web build has no Hans face. Scores and estimates unchanged. || 2026-10-20 | minor | M12 #3673: the Character encoding rule accepts Identity-H/V fonts with Adobe CJK collections, or a predefined non-Identity CMap, while rejecting unknown names and foreign registries. Synthetic checker and read-only automation regressions passed after failing before the fix; per-glyph mapping validation and embedded-font extraction remain separate. Breadth, readiness and hours unchanged. |