PdfCraft: An open-source PDF reader and editor written by scratch in pure Rust
Merge PR #3227: M11: target PDF version and object streams option in PDF Optimizer
aiongg1d270206bebc
diff --cc crates/optimize/tests/optimize.rsindex 5550709e7,ec068573a..581925150--- a/crates/optimize/tests/optimize.rs+++ b/crates/optimize/tests/optimize.rs@@@ -1091,19 -1025,77 +1093,90 @@@ fn images_are_not_resampled_when_some_uassert_eq!(effective_resolutions(&doc, &refs)[&img], f64::INFINITY);}+/// Each form entry counts against the page's form allowance, even for a form that decodes to+/// nothing and so costs no decoded bytes.+#[test]+fn images_are_not_resampled_when_a_page_enters_more_forms_than_allowed() {+ let mut doc = Document::new_empty();+ let img = image(&mut doc, 1200, 1200, 3, false, None);+ let empty = form(&mut doc, None, "");+ let draws = "/E Do ".repeat(pdfcraft_cos::MAX_PAGE_FORMS + 1);+ page(&mut doc, &[("E", empty), ("Im", img)], &format!("q 72 0 0 72 36 36 cm /Im Do Q {draws}"));+ let refs = pdfcraft_annot::page_refs(&doc).unwrap();+ assert_eq!(effective_resolutions(&doc, &refs)[&img], f64::INFINITY);+}++ #[test]+ fn compatibility_level_sets_version_unpacks_for_1_4_and_checks_encryption() {+ let mut base = Document::new_empty();+ page(&mut base, &[], "BT /F1 12 Tf 72 720 Td (Compatibility test) Tj ET");+ let root = base.root().unwrap();+ base.update_dict(root, |c| c.set(b"Version".to_vec(), Object::name("1.6"))).unwrap();++ for (compat, expected) in [+ (Compatibility::Pdf1_4, "1.4"),+ (Compatibility::Pdf1_5, "1.5"),+ (Compatibility::Pdf1_6, "1.6"),+ (Compatibility::Pdf1_7, "1.7"),+ (Compatibility::Pdf2_0, "2.0"),+ ] {+ let mut doc = base.clone();+ let settings = Settings { compatibility: compat, ..Settings::default() };+ optimize(&mut doc, &settings).unwrap();+ assert_eq!(doc.version(), expected);+ assert!(!doc.get(root).as_dict().unwrap().contains(b"Version"), "overriding catalog /Version is cleared");+ let bytes = write_full(&doc, &SaveOptions { object_streams: settings.effective_object_streams(), ..SaveOptions::default() }).unwrap();+ assert!(bytes.starts_with(format!("%PDF-{expected}\n").as_bytes()), "{expected}");+ let has_objstm = bytes.windows(7).any(|w| w == b"/ObjStm");+ assert_eq!(has_objstm, compat != Compatibility::Pdf1_4, "{compat:?}");+ let info = pdfcraft_render::inspect(Arc::new(bytes), None).unwrap();+ assert_eq!(info.pdf_version, expected);+ }++ // Disabling object_streams on PDF 1.7 writes a classic cross-reference table.+ let mut doc = base.clone();+ let settings = Settings { compatibility: Compatibility::Pdf1_7, object_streams: false, ..Settings::default() };+ optimize(&mut doc, &settings).unwrap();+ let bytes = write_full(&doc, &SaveOptions { object_streams: settings.effective_object_streams(), ..SaveOptions::default() }).unwrap();+ assert!(bytes.starts_with(b"%PDF-1.7\n") && !bytes.windows(7).any(|w| w == b"/ObjStm"));++ // Encryption that requires a newer PDF version than the chosen compatibility is refused.+ let mut aes256 = base.clone();+ aes256+ .set_encryption(&pdfcraft_cos::NewEncryption {+ algorithm: pdfcraft_cos::Algorithm::Aes256,+ user_password: "u",+ owner_password: "o",+ permissions: -1,+ encrypt_metadata: true,+ seed: [1; 32],+ })+ .unwrap();+ assert!(matches!(+ optimize(&mut aes256, &Settings { compatibility: Compatibility::Pdf1_6, ..Settings::default() }),+ Err(OptimizeError::IncompatibleEncryption { required: "1.7", chosen: "1.6" })+ ));+ optimize(&mut aes256, &Settings { compatibility: Compatibility::Pdf2_0, ..Settings::default() }).unwrap();+ assert_eq!(aes256.version(), "2.0");++ let mut aes128 = base;+ aes128+ .set_encryption(&pdfcraft_cos::NewEncryption {+ algorithm: pdfcraft_cos::Algorithm::Aes128,+ user_password: "u",+ owner_password: "o",+ permissions: -1,+ encrypt_metadata: true,+ seed: [1; 32],+ })+ .unwrap();+ assert!(matches!(+ optimize(&mut aes128, &Settings { compatibility: Compatibility::Pdf1_5, ..Settings::default() }),+ Err(OptimizeError::IncompatibleEncryption { required: "1.6", chosen: "1.5" })+ ));+ optimize(&mut aes128, &Settings { compatibility: Compatibility::Pdf1_6, ..Settings::default() }).unwrap();+ }+#[test]fn image_resolution_keeps_comments_across_content_pieces() {for ending in ["", "\n", "\r", "\r\n"] {diff --cc docs/roadmap.mdindex 382459f26,f16781008..bf02bdef1--- a/docs/roadmap.md+++ b/docs/roadmap.md@@@ -1,11 -1,7 +1,12 @@@# PdfCraft roadmap: milestones and what's next-> **Last reviewed:** 2026-10-22 · **Last updated:** 2026-10-22 · **Change:** patch (PR #3227 integration; retain partial target-version compatibility and upstream content-boundary and image-size regression coverage; estimates unchanged)+> **Last reviewed:** 2026-10-23 · **Last updated:** 2026-10-23 · **Change:** minor (M11: image optimization accounts for page-local UserUnit; estimates unchanged)+> **Last reviewed:** 2026-10-22 · **Last updated:** 2026-10-22 · **Change:** minor (M14, #3558: rebase guarded macOS per-file association recovery onto current main; estimates unchanged)+> **Last reviewed:** 2026-10-23 | **Last updated:** 2026-10-23 | **Change:** minor (M10: Word table cells use the widths of their own grid columns; estimates unchanged)+> **Last reviewed:** 2026-10-23 | **Last updated:** 2026-10-23 | **Change:** minor (M10: table spans retain text from covered slots in Office exports; estimates unchanged)+> **Last reviewed:** 2026-10-23 · **Last updated:** 2026-10-23 · **Change:** minor (M10: image export preserves soft-mask Decode opacity ranges; estimates unchanged)++> **Last reviewed:** 2026-10-22 · **Last updated:** 2026-10-22 · **Change:** patch (PR #3227 integration; retain partial target-version compatibility and upstream content-boundary and image-size regression coverage; estimates unchanged)> **Last reviewed:** 2026-10-20 · **Last updated:** 2026-10-20 · **Change:** minor (M12 #3673: Character encoding accepts Identity-H/V with Adobe CJK collections; estimates unchanged)> **Last reviewed:** 2026-10-20 | **Last updated:** 2026-10-20 | **Change:** minor (M10, #3532 partial: vector printing retains existing appearances with absent Subtype; estimates unchanged)@@@ -190,8 -184,8 +191,8 @@@ total matches the parity estimate| M7 | Content editing (text, images, header/footer, watermark) | 250–500 | 20% | 100–180 | Done: header & footer, watermarks, backgrounds, Bates; added text and images that stay editable (move, resize, format, rotate, flip, crop, replace); links (Link tool, Link Properties, create from URLs, remove all). Missing: editing existing text and images in place (the longest pole), image/PDF watermarks || M8 | Security + redaction | 100–180 | 68% | 15–30 | Done: opening protected documents, permissions, Protect Using Password, Remove security; redaction (mark text/areas/pages, Search & Redact with patterns, apply removing glyphs, image pixels, vectors, XObject content, annotations and fields, verification, full rewrite on save); Remove hidden information and Sanitize.<br>Done since: redaction codes (U.S. FOIA and Privacy Act sets as overlay text, in Redaction properties and `redact_mark`). Redaction cleans indirect and form structure references, preserving surviving form tags. Redaction retires inherited resource dictionaries, so a parent `/Pages` can't keep a removed XObject reachable; unredacted pages are left untouched. Image redaction removes alternate images and unsupported masks only on affected images. Changed marked-content spans lose replacement descriptions; untouched spans keep theirs. Hidden-text cleanup retires unused named descriptions across inherited/shared page and form resources (64 focused tests and scoped Rust 1.96 Clippy/wasm checks pass; publication CI pending). The redaction audit counts a filled cover that hides half of any one word of a long line (#2662), applied or not. Missing: certificate security, custom redaction code sets and pattern locales, DCT re-encoding || M9 | Signatures (PAdES, validation) | 160–280 | 60% | 40–70 | Done: new `sign` crate (DER, X.509, CMS, PKCS #12 on RustCrypto; aws-lc-rs for RSA private keys); PAdES B-B signing (visible, invisible, existing fields, certification with DocMDP); validation with trust store and changes-after-signing classification; self-signed digital IDs; Signatures panel, message bar, sign dialogs; agent tools. Checked with pdfsig and OpenSSL.<br>Done since: macOS Keychain and Windows Current User Personal store signing (software-backed CNG keys), certificate viewer, signed documents protected from rewrites, page validation overlays separate from original signature artwork (baked Not Verified captions remain; #79 open), snapshot tabs that reuse instead of multiplying. Missing: timestamps (B-T), LTV (DSS, OCSP, CRL), FieldMDP, smart cards, PKCS #11 |-| M10 | OCR, create, export, print | 200–350 | 33% | 120–215 | Done: create from blank/text/PNG/JPEG/TIFF (multi-page)/GIF/BMP; export PNG/JPEG/TIFF and text; Print (Acrobat's sizing, n-up, booklet, poster, comments & forms, preview, the CUPS and Windows spoolers, print-ready PDF).<br>Done since: embedded/72/custom DPI choices for image imports; export all images; OCR (searchable image for pages, ranges and multiple files); single-sided cut-and-stack imposition with cut marks, through Print and doc_print; architectural/ANSI/large ISO sheet presets, Match page at 100% and PDF-scale preview (#599 follow-up); Create PDF from multiple files (PDFs, images and text, edited as pages in the grid); OCR can also read pictures on pages that have text, without adding that text twice (#1028). Done since: Word invoice export uses borderless inferred tables, floating positioned text/artwork only where text overlaps an image or is rotated, and per-page sizes, covered by synthetic invoice automation regressions (#773); printing on the web through the browser's print dialog, sheets drawn by PdfCraft (gap 4). Lossless image export applies per-component Decode, including Indexed mapping (#1201 partial). Existing 16-bit precision and color-management limits remain. #3532 partial: vector printing retains existing appearances with absent Subtype through a print-owned Form copy; source artwork stays unchanged. #3120: Office export reads form XObjects 50 levels deep, as the renderer does, and up to 50 000 a page; pages past that are listed in `truncated_pages`. Missing: OCR languages beyond Latin, editable-text OCR output, full Office layout fidelity/import. Done since: dotted-leader contents entries stay in separate complete paragraphs (#1757) #2156 candidate: last selected print paper persists across sessions; other print preferences unchanged. |-| M11 | Optimize, preflight, PDF/A/X/UA, print production | 200–350 | 18% | 80–140 | Done: new `optimize` crate: Reduce File Size and the PDF Optimizer (images measured where drawn, bicubic downsampling, JPEG/ZIP recompression only when smaller, discard objects and user data, Flate clean-up, resource merging, object streams). Target-version compatibility is partial: newer content is not detected or converted. Content stream boundaries preserve comments, split operands and graphics state when image fragments merge. Done since: reject invalid image and soft-mask dimensions with checked sizing (#2178). Missing: fonts and transparency panels, space audit, preflight, PDF/A/X/UA PR #3227 integration retains existing scope and estimates against upstream `80b7d215`. |+| M10 | OCR, create, export, print | 200–350 | 33% | 120–215 | Done: create from blank/text/PNG/JPEG/TIFF (multi-page)/GIF/BMP; export PNG/JPEG/TIFF and text; Print (Acrobat's sizing, n-up, booklet, poster, comments & forms, preview, the CUPS and Windows spoolers, print-ready PDF).<br>Done since: embedded/72/custom DPI choices for image imports; export all images; OCR (searchable image for pages, ranges and multiple files); single-sided cut-and-stack imposition with cut marks, through Print and doc_print; architectural/ANSI/large ISO sheet presets, Match page at 100% and PDF-scale preview (#599 follow-up); Create PDF from multiple files (PDFs, images and text, edited as pages in the grid); OCR can also read pictures on pages that have text, without adding that text twice (#1028). Done since: Word invoice export uses borderless inferred tables, floating positioned text/artwork only where text overlaps an image or is rotated, and per-page sizes, covered by synthetic invoice automation regressions (#773); printing on the web through the browser's print dialog, sheets drawn by PdfCraft (gap 4). Lossless image export applies per-component Decode, including Indexed mapping (#1201 partial). Existing 16-bit precision and color-management limits remain. #3532 partial: vector printing retains existing appearances with absent Subtype through a print-owned Form copy; source artwork stays unchanged. #3120: Office export reads form XObjects 50 levels deep, as the renderer does, and up to 50 000 a page; pages past that are listed in `truncated_pages`. Word table cells use the grid columns they span, including cells after a merged cell. Done since: text in a table slot covered by another cell's span remains as paragraph text in Word, HTML, RTF and PowerPoint. Missing: OCR languages beyond Latin, editable-text OCR output, full Office layout fidelity/import. Done since: dotted-leader contents entries stay in separate complete paragraphs (#1757) #2156 candidate: last selected print paper persists across sessions; other print preferences unchanged. Image export applies soft-mask Decode opacity intervals before resizing, including indirect entries and inverted ranges. |- | M11 | Optimize, preflight, PDF/A/X/UA, print production | 200–350 | 18% | 80–140 | Done: new `optimize` crate: Reduce File Size and the PDF Optimizer (images measured where drawn, bicubic downsampling, JPEG/ZIP recompression only when smaller, discard objects and user data, Flate clean-up, resource merging, object streams). Content stream boundaries preserve comments, split operands and graphics state when image fragments merge. Image downsampling includes page-local `/UserUnit` scaling when measuring physical resolution. Done since: reject invalid image and soft-mask dimensions with checked sizing (#2178). Missing: fonts and transparency panels, space audit, preflight, PDF/A/X/UA |++| M11 | Optimize, preflight, PDF/A/X/UA, print production | 200–350 | 18% | 80–140 | Done: new `optimize` crate: Reduce File Size and the PDF Optimizer (images measured where drawn, bicubic downsampling, JPEG/ZIP recompression only when smaller, discard objects and user data, Flate clean-up, resource merging, object streams). Target-version compatibility is partial: newer content is not detected or converted. Content stream boundaries preserve comments, split operands and graphics state when image fragments merge. Image downsampling includes page-local `/UserUnit` scaling when measuring physical resolution. Done since: reject invalid image and soft-mask dimensions with checked sizing (#2178). Missing: fonts and transparency panels, space audit, preflight, PDF/A/X/UA PR #3227 integration retains existing scope and estimates against upstream `80b7d215`. || M12 | Accessibility, compare, measure, search, XFA | 200–380 | 30% | 90–160 | Done: new `a11y` crate with the Accessibility Checker (all 32 rules, report, Fix/Skip/Explain, options dialog and results panel, agent tools). Locatable figure, annotation and form findings highlight their page bounds. Character encoding accepts Identity-H/V with Adobe CJK collections and predefined CJK CMaps independently (#3673); per-glyph validation and embedded-font extraction remain separate.<br>Done since: 2D distance, perimeter and area measurements with persistent viewport calibration, snapping, live information and CSV export; a bounded, text-only auto-tag proposal tool for one page. Marking a figure decorative rewrites only that stream (#1324). An XFA radio item whose value contains a space is written back unchanged (#1319). Done since: #2569: Growable multiline XFA text reflows after edits, with undo/redo, save/reopen and print coverage; oversized fields still become read-only page text. Structured-data synchronization warnings retain accepted whitespace without relayout from stale data. Done since: #2572: Every repeated page-master button resolves its own field to the shared XFA click script, including print buttons. Done since: #2570: Dynamic XFA rich-text fields carry exData/maxLength into AcroForm MaxLen for reported and enforced Unicode character limits, retained after save/reopen. Missing: writing proposed tags and parent tree, field autotag, visual Tags/Order/Content panels, Reading Order tool, compare, geospatial/3D measurement, search index, XFA<br>Reading colours: pending page backgrounds follow the configured colour (#2059). || M13 | Automation (MCP, Action Wizard, CLI) + AI providers | 60–120 | 45% | 25–45 | Done: MCP resources (document info, text, page images); headless tool table (123 tools incl. signing, optimizing, initial view, links, stamps, data exchange, comment review, forms authoring and scripts, redaction, sanitize, print, add content), opt-in MCP server over stdio, CLI `run`/`tools` (closed stdout pipes exit cleanly), UI control channel with drag. Missing: Action Wizard, AI providers<br>Done since: CLI run and MCP reject missing, empty, repeated and option-valued --root arguments before any tool/script execution or MCP initialization. A single-hyphen directory name remains valid; synthetic CLI regressions preserve a would-be overwritten file. `text_find` also caps the per-page match ranges it materializes at the remaining result limit plus one continuation match. CLI robustness scans visit each directory once through overlapping roots and symlink aliases. || M12 | Accessibility, compare, measure, search, XFA | 200–380 | 30% | 90–160 | Done: new `a11y` crate with the Accessibility Checker (all 32 rules, report, Fix/Skip/Explain, options dialog and results panel, agent tools). Locatable figure, annotation and form findings highlight their page bounds. Character encoding accepts Identity-H/V with Adobe CJK collections and predefined CJK CMaps independently (#3673); per-glyph validation and embedded-font extraction remain separate.<br>Done since: 2D distance, perimeter and area measurements with persistent viewport calibration, snapping, live information and CSV export; a bounded text-only auto-tag proposal tool; text-only Apply writes marked content, paragraph tags and a parent tree, then opens the Tags panel for review. Missing: mixed-content and field autotag, heading/list/table/figure classification, Order/Content panels, Reading Order tool, compare, geospatial/3D measurement, search index, XFA<br>Done since: CLI info, text and render use dynamic XFA layout pages, with synthetic count/text/pixel and copy-permission regressions (#1645).<br>Reading colours: pending page backgrounds follow the configured colour (#2059). |diff --cc parity/acrobat-features.tomlindex 63cc83f21,ca8a54bc7..62fc5d84b--- a/parity/acrobat-features.toml+++ b/parity/acrobat-features.toml@@@ -7574,11 -7574,11 +7574,11 @@@ title = "Compress document structure (oarea = "K"tier = "P1"milestone = "M11"- status = "partial"- commands = ["file.save_as"]- tools = ["doc_save"]- evidence = ["crates/cos/tests/it/writer.rs::full_save_packs_objects_into_object_streams"]- notes = "on by default for full saves; no Optimizer option yet"+ status = "shipped"+ commands = ["file.save_as", "optimize.advanced"]+ tools = ["doc_save", "doc_optimize"]-evidence = ["crates/cos/tests/writer.rs::full_save_packs_objects_into_object_streams", "crates/optimize/tests/optimize.rs::compatibility_level_sets_version_unpacks_for_1_4_and_checks_encryption", "crates/automation/tests/automation.rs::optimizing_through_tools", "crates/ui-egui/tests/create.rs::the_pdf_optimizer_dialog_picks_a_preset"]++evidence = ["crates/cos/tests/it/writer.rs::full_save_packs_objects_into_object_streams", "crates/optimize/tests/optimize.rs::compatibility_level_sets_version_unpacks_for_1_4_and_checks_encryption", "crates/automation/tests/it/automation.rs::optimizing_through_tools", "crates/ui-egui/tests/it/create.rs::the_pdf_optimizer_dialog_picks_a_preset"]+ notes = "on by default for full saves and in PDF Optimizer ▸ Clean Up (and doc_optimize object_streams); turning it off or targeting PDF 1.4 unpacks object streams into standalone objects with a classic cross-reference table"[[feature]]id = "optimize.flate-unencoded"