mirror of
https://github.com/storytold/pdfcraft.git
synced 2026-11-11 00:41:21 +00:00
Merge remote-tracking branch 'upstream/main' into pr-fix/print-area
# Conflicts: # crates/ui-egui/src/i18n/ar.tsv # crates/ui-egui/src/i18n/bg.tsv # crates/ui-egui/src/i18n/ca.tsv # crates/ui-egui/src/i18n/cs.tsv # crates/ui-egui/src/i18n/de.tsv # crates/ui-egui/src/i18n/el.tsv # crates/ui-egui/src/i18n/es.tsv # crates/ui-egui/src/i18n/fi.tsv # crates/ui-egui/src/i18n/fr.tsv # crates/ui-egui/src/i18n/hi.tsv # crates/ui-egui/src/i18n/hu.tsv # crates/ui-egui/src/i18n/id.tsv # crates/ui-egui/src/i18n/it.tsv # crates/ui-egui/src/i18n/ja.tsv # crates/ui-egui/src/i18n/kk.tsv # crates/ui-egui/src/i18n/ko.tsv # crates/ui-egui/src/i18n/lt.tsv # crates/ui-egui/src/i18n/pl.tsv # crates/ui-egui/src/i18n/pt-br.tsv # crates/ui-egui/src/i18n/ro.tsv # crates/ui-egui/src/i18n/ru.tsv # crates/ui-egui/src/i18n/sl.tsv # crates/ui-egui/src/i18n/sq.tsv # crates/ui-egui/src/i18n/te.tsv # crates/ui-egui/src/i18n/tr.tsv # crates/ui-egui/src/i18n/uk.tsv # crates/ui-egui/src/i18n/vi.tsv # crates/ui-egui/src/i18n/zh-hans.tsv # crates/ui-egui/src/i18n/zh-hant.tsv
This commit is contained in:
Osvaldo Duran Melendez committed
commit
36149fcd82
218 files changed
+11284
-96258
No files matched your search
@@ -3,6 +3,9 @@
|
||||
# signatures) and assets whose SHA-256 ATTRIBUTION.toml records (cargo xtask assets).
|
||||
* -text
|
||||
|
||||
# The craft-i18n pin: CI and the build read it as one SHA, so it stays LF everywhere (readers trim it too).
|
||||
craft-i18n.rev text eol=lf
|
||||
|
||||
# Not text at all: no textual diffs or merges either.
|
||||
*.pdf binary
|
||||
*.p12 binary
|
||||
|
||||
@@ -52,14 +52,14 @@ Anything else is forbidden, including assets whose licence you cannot prove from
|
||||
- path or URL, title, author;
|
||||
- source (URL, with version or commit);
|
||||
- SPDX licence, and the licence file in the repo;
|
||||
- SHA-256, except for translation catalogs (see below);
|
||||
- SHA-256;
|
||||
- how it is used.
|
||||
- **Translation catalogs** (`crates/ui-egui/src/i18n/*.tsv`, `kind = "translation"`) are project files under the project licence. Their entries carry no `sha256`: git history records every change and who made it. Every other kind (fonts, images, data) is hashed.
|
||||
- **Translations** live in craft-i18n (`locales/<code>/common.tsv` and `pdfcraft.tsv`), embedded at build time from the checkout pinned in `craft-i18n.rev`; PdfCraft keeps no catalogs. `ATTRIBUTION.toml` records them as one `[[build_input]]` (`kind = "translation"`); craft-i18n's own `ATTRIBUTION.md` credits the translators. Every `[[asset]]` (fonts, images, data) is hashed.
|
||||
- **`ATTRIBUTION.md`** is generated from it (`cargo xtask assets --write`). Never edit it by hand.
|
||||
- **`NOTICE`** keeps the licence notices that the licences require.
|
||||
- **`cargo xtask assets`** runs in `cargo xtask ci`. It fails if:
|
||||
- an asset file in the repository has no entry;
|
||||
- an entry's hash is missing or does not match (translation catalogs carry none);
|
||||
- an entry's hash is missing or does not match;
|
||||
- a licence is not on the allowlist;
|
||||
- a licence file is missing;
|
||||
- an image, icon or font names Adobe as author or source, except a font licensed under OFL-1.1 alone.
|
||||
|
||||
+4
-37
@@ -2,40 +2,12 @@
|
||||
|
||||
<!-- Generated from ATTRIBUTION.toml by `cargo xtask assets --write`. Do not edit by hand. -->
|
||||
|
||||
Every asset PdfCraft includes, bundles or uses to build its published material, with its author, source and licence. The policy is in [AGENTS.md](AGENTS.md) §1. The machine-readable list, with the SHA-256 of every asset but the translation catalogs, is [ATTRIBUTION.toml](ATTRIBUTION.toml). Licence texts are kept beside the assets and summarised in [NOTICE](NOTICE).
|
||||
Every asset PdfCraft includes, bundles or uses to build its published material, with its author, source and licence. The policy is in [AGENTS.md](AGENTS.md) §1. The machine-readable list, with the SHA-256 of every asset, is [ATTRIBUTION.toml](ATTRIBUTION.toml). Licence texts are kept beside the assets and summarised in [NOTICE](NOTICE).
|
||||
|
||||
## In this repository (289)
|
||||
## In this repository (255)
|
||||
|
||||
| Asset | Title | Author | Licence | Source | Used for |
|
||||
|---|---|---|---|---|---|
|
||||
| `crates/ui-egui/src/i18n/el.tsv` | Greek interface translation catalog | Camthalion77 and contributors | MIT OR Apache-2.0 | Contributor-original: clean-room translations of PdfCraft English UI labels; 2026-10-18 page-gap labels are contributor-original AI-assisted translations from English, not separately native-reviewed; 2026-10-22 secured-document notice labels are contributor-original AI-assisted translations from English, not separately native-reviewed; the 2026-10-22 reply-count label is an AI-assisted translation from English, not separately native-reviewed | Greek UI strings, compiled in by crates/ui-egui/src/i18n.rs |
|
||||
| `crates/ui-egui/src/i18n/zh-hans.tsv` | Simplified Chinese interface translation catalog | PdfCraft contributors | MIT OR Apache-2.0 | Contributor-original: clean-room translations of PdfCraft's English UI labels, no proprietary localisation resources; 2026-10-18 page-gap labels are contributor-original AI-assisted translations from English, not separately native-reviewed; 2026-10-22 secured-document notice labels are contributor-original AI-assisted translations from English, not separately native-reviewed; the 2026-10-22 reply-count label is an AI-assisted translation from English, not separately native-reviewed | Simplified Chinese UI strings, compiled in by crates/ui-egui/src/i18n.rs |
|
||||
| `crates/ui-egui/src/i18n/zh-hant.tsv` | Traditional Chinese (Taiwan) interface translation catalog | PdfCraft contributors | MIT OR Apache-2.0 | Contributor-original: clean-room translations of PdfCraft's English UI labels, no proprietary localisation resources; 2026-10-18 page-gap labels are contributor-original AI-assisted translations from English, not separately native-reviewed; 2026-10-22 secured-document notice labels are contributor-original AI-assisted translations from English, not separately native-reviewed; the 2026-10-22 reply-count label is an AI-assisted translation from English, not separately native-reviewed | Traditional Chinese UI strings, compiled in by crates/ui-egui/src/i18n.rs |
|
||||
| `crates/ui-egui/src/i18n/cs.tsv` | Czech interface translation catalog | PdfCraft contributors | MIT OR Apache-2.0 | Contributor-original: clean-room translations of PdfCraft's English UI labels, no proprietary localisation resources; 2026-10-18 page-gap labels are contributor-original AI-assisted translations from English, not separately native-reviewed; 2026-10-22 signature-check and standard-identification wordings are contributor-original AI-assisted translations from English, not separately native-reviewed; 2026-10-22 secured-document notice labels are contributor-original AI-assisted translations from English, not separately native-reviewed; the 2026-10-22 reply-count label is an AI-assisted translation from English, not separately native-reviewed | Czech UI strings, compiled in by crates/ui-egui/src/i18n.rs |
|
||||
| `crates/ui-egui/src/i18n/pt-br.tsv` | Brazilian Portuguese interface translation catalog | André Cardoso (andrecards), PdfCraft contributors | MIT OR Apache-2.0 | Clean-room translations of PdfCraft's English UI labels, no proprietary localisation resources: the ~1,826-entry gist posted in issue #288 (https://gist.github.com/andrecards/ac388c25fba17312ce83207f8b7b467e), completed and reviewed by PdfCraft contributors; 2026-10-18 page-gap labels are contributor-original AI-assisted translations from English, not separately native-reviewed; 2026-10-22 text-field-table limit messages are contributor-original AI-assisted translations from English, not separately native-reviewed; 2026-10-22 secured-document notice labels are contributor-original AI-assisted translations from English, not separately native-reviewed; the 2026-10-22 reply-count label is an AI-assisted translation from English, not separately native-reviewed | Brazilian Portuguese UI strings, compiled in by crates/ui-egui/src/i18n.rs |
|
||||
| `crates/ui-egui/src/i18n/es.tsv` | Spanish interface translation catalog | PdfCraft contributors | MIT OR Apache-2.0 | Contributor-original: clean-room translations of PdfCraft's English UI labels, no proprietary localisation resources; the 2026-10-20 coverage additions are AI-assisted and not separately native-reviewed; 2026-10-18 page-gap labels are contributor-original AI-assisted translations from English, not separately native-reviewed; 2026-10-22 signature-check wordings are contributor-original AI-assisted translations from English, not separately native-reviewed; 2026-10-22 secured-document notice labels are contributor-original AI-assisted translations from English, not separately native-reviewed; the 2026-10-22 reply-count label is an AI-assisted translation from English, not separately native-reviewed | Spanish UI strings, compiled in by crates/ui-egui/src/i18n.rs |
|
||||
| `crates/ui-egui/src/i18n/fr.tsv` | French interface translation catalog | PdfCraft contributors | MIT OR Apache-2.0 | Contributor-original: clean-room translations of PdfCraft's English UI labels, no proprietary localisation resources; 2026-10-18 page-gap labels are contributor-original AI-assisted translations from English, not separately native-reviewed; 2026-10-22 secured-document notice labels are contributor-original AI-assisted translations from English, not separately native-reviewed; the 2026-10-22 reply-count label is an AI-assisted translation from English, not separately native-reviewed | French UI strings, compiled in by crates/ui-egui/src/i18n.rs |
|
||||
| `crates/ui-egui/src/i18n/de.tsv` | German interface translation catalog | PdfCraft contributors | MIT OR Apache-2.0 | Contributor-original: clean-room translations of PdfCraft's English UI labels, no proprietary localisation resources; 2026-10-18 page-gap labels are contributor-original AI-assisted translations from English, not separately native-reviewed; 2026-10-22 secured-document notice labels are contributor-original AI-assisted translations from English, not separately native-reviewed; the 2026-10-22 reply-count label is an AI-assisted translation from English, not separately native-reviewed | German UI strings, compiled in by crates/ui-egui/src/i18n.rs |
|
||||
| `crates/ui-egui/src/i18n/lo.tsv` | Lao interface translation catalog | @bounkirdni-2025 | MIT OR Apache-2.0 | Contributor-original: clean-room translations of PdfCraft English UI labels, no proprietary localisation resources; 2026-10-22 page-gap labels are contributor-original AI-assisted translations from English, not separately native-reviewed; 2026-10-22 secured-document notice labels are contributor-original AI-assisted translations from English, not separately native-reviewed; the 2026-10-22 reply-count label is an AI-assisted translation from English, not separately native-reviewed | Lao UI strings, compiled in by crates/ui-egui/src/i18n.rs |
|
||||
| `crates/ui-egui/src/i18n/te.tsv` | Telugu interface translation catalog | PdfCraft contributors | MIT OR Apache-2.0 | Contributor-original: clean-room translations of PdfCraft's English UI labels, no proprietary localisation resources; 2026-10-18 page-gap labels are contributor-original AI-assisted translations from English, not separately native-reviewed; 2026-10-22 secured-document notice labels are contributor-original AI-assisted translations from English, not separately native-reviewed; the 2026-10-22 reply-count label is an AI-assisted translation from English, not separately native-reviewed | Telugu UI strings, compiled in by crates/ui-egui/src/i18n.rs |
|
||||
| `crates/ui-egui/src/i18n/it.tsv` | Italian interface translation catalog | PdfCraft contributors | MIT OR Apache-2.0 | Contributor-original: clean-room translations of PdfCraft's English UI labels, no proprietary localisation resources; 2026-10-18 page-gap labels are contributor-original AI-assisted translations from English, not separately native-reviewed; 2026-10-22 secured-document notice labels are contributor-original AI-assisted translations from English, not separately native-reviewed; the 2026-10-22 reply-count label is an AI-assisted translation from English, not separately native-reviewed | Italian UI strings, compiled in by crates/ui-egui/src/i18n.rs |
|
||||
| `crates/ui-egui/src/i18n/pl.tsv` | Polish interface translation catalog | PdfCraft contributors | MIT OR Apache-2.0 | Contributor-original: clean-room translations of PdfCraft's English UI labels, no proprietary localisation resources; 2026-10-18 page-gap labels are contributor-original AI-assisted translations from English, not separately native-reviewed; 2026-10-22 signature-check wordings are contributor-original AI-assisted translations from English, not separately native-reviewed; 2026-10-22 secured-document notice labels are contributor-original AI-assisted translations from English, not separately native-reviewed; the 2026-10-22 reply-count label is an AI-assisted translation from English, not separately native-reviewed | Polish UI strings, compiled in by crates/ui-egui/src/i18n.rs |
|
||||
| `crates/ui-egui/src/i18n/ru.tsv` | Russian interface translation catalog | PdfCraft contributors | MIT OR Apache-2.0 | Contributor-original: clean-room translations of PdfCraft's English UI labels, no proprietary localisation resources; 2026-10-18 page-gap labels are contributor-original AI-assisted translations from English, not separately native-reviewed; 2026-10-22 secured-document notice labels are contributor-original AI-assisted translations from English, not separately native-reviewed; the 2026-10-22 reply-count label is an AI-assisted translation from English, not separately native-reviewed | Russian UI strings, compiled in by crates/ui-egui/src/i18n.rs |
|
||||
| `crates/ui-egui/src/i18n/hu.tsv` | Hungarian interface translation catalog | PdfCraft contributors | MIT OR Apache-2.0 | Contributor-original: clean-room translations of PdfCraft's English UI labels, no proprietary localisation resources; 2026-10-18 page-gap labels are contributor-original AI-assisted translations from English, not separately native-reviewed; 2026-10-22 secured-document notice labels are contributor-original AI-assisted translations from English, not separately native-reviewed; the 2026-10-22 reply-count label is an AI-assisted translation from English, not separately native-reviewed | Hungarian UI strings, compiled in by crates/ui-egui/src/i18n.rs |
|
||||
| `crates/ui-egui/src/i18n/bg.tsv` | Bulgarian interface translation catalog | PdfCraft contributors | MIT OR Apache-2.0 | Contributor-original: clean-room translations of PdfCraft's English UI labels, no proprietary localisation resources; 2026-10-18 page-gap labels are contributor-original AI-assisted translations from English, not separately native-reviewed; 2026-10-22 secured-document notice labels are contributor-original AI-assisted translations from English, not separately native-reviewed; the 2026-10-22 reply-count label is an AI-assisted translation from English, not separately native-reviewed | Bulgarian UI strings, compiled in by crates/ui-egui/src/i18n.rs |
|
||||
| `crates/ui-egui/src/i18n/kk.tsv` | Kazakh interface translation catalog | PdfCraft contributors | MIT OR Apache-2.0 | Contributor-original: clean-room translations of the English UI labels into Kazakh, no proprietary localisation resources; 2026-10-18 page-gap labels are contributor-original AI-assisted translations from English, not separately native-reviewed; 2026-10-22 secured-document notice labels are contributor-original AI-assisted translations from English, not separately native-reviewed; the 2026-10-22 reply-count label is an AI-assisted translation from English, not separately native-reviewed | Kazakh UI strings, compiled in by crates/ui-egui/src/i18n.rs |
|
||||
| `crates/ui-egui/src/i18n/ja.tsv` | Japanese interface translation catalog | PdfCraft contributors | MIT OR Apache-2.0 | Contributor-original: clean-room translations of PdfCraft's English UI labels, no proprietary localisation resources; 2026-10-18 page-gap labels are contributor-original AI-assisted translations from English, not separately native-reviewed; 2026-10-22 secured-document notice labels are contributor-original AI-assisted translations from English, not separately native-reviewed; the 2026-10-22 reply-count label is an AI-assisted translation from English, not separately native-reviewed | Japanese UI strings, compiled in by crates/ui-egui/src/i18n.rs |
|
||||
| `crates/ui-egui/src/i18n/uk.tsv` | Ukrainian interface translation catalog | PdfCraft contributors | MIT OR Apache-2.0 | Contributor-original: clean-room translations of PdfCraft's English UI labels, no proprietary localisation resources; 2026-10-18 page-gap labels are contributor-original AI-assisted translations from English, not separately native-reviewed; 2026-10-22 secured-document notice labels are contributor-original AI-assisted translations from English, not separately native-reviewed; the 2026-10-22 reply-count label is an AI-assisted translation from English, not separately native-reviewed | Ukrainian UI strings, compiled in by crates/ui-egui/src/i18n.rs |
|
||||
| `crates/ui-egui/src/i18n/ar.tsv` | Arabic interface translation catalog | PdfCraft contributors | MIT OR Apache-2.0 | Contributor-original: clean-room translations of PdfCraft's English UI labels, no proprietary localisation resources; 2026-10-18 page-gap labels are contributor-original AI-assisted translations from English, not separately native-reviewed; 2026-10-22 secured-document notice labels are contributor-original AI-assisted translations from English, not separately native-reviewed; the 2026-10-22 reply-count label is an AI-assisted translation from English, not separately native-reviewed | Arabic UI strings, compiled in by crates/ui-egui/src/i18n.rs |
|
||||
| `crates/ui-egui/src/i18n/ckb.tsv` | Central Kurdish (Sorani) interface translation catalog | PdfCraft contributors | MIT OR Apache-2.0 | Contributor-original: clean-room translations of PdfCraft's English UI labels, no proprietary localisation resources; 2026-10-22 page-gap labels are contributor-original AI-assisted translations from English, not separately native-reviewed; 2026-10-22 secured-document notice labels are contributor-original AI-assisted translations from English, not separately native-reviewed; the 2026-10-22 reply-count label is an AI-assisted translation from English, not separately native-reviewed | Central Kurdish UI strings, compiled in by crates/ui-egui/src/i18n.rs |
|
||||
| `crates/ui-egui/src/i18n/fa.tsv` | Persian (Farsi) interface translation catalog | PdfCraft contributors | MIT OR Apache-2.0 | Contributor-original: clean-room translations of PdfCraft's English UI labels, no proprietary localisation resources; 2026-10-25 initial catalog covering the current 2,776-entry key union, AI-assisted translations from English, not separately native-reviewed | Persian UI strings, compiled in by crates/ui-egui/src/i18n.rs |
|
||||
| `crates/ui-egui/src/i18n/tr.tsv` | Turkish interface translation catalog | PdfCraft contributors | MIT OR Apache-2.0 | Contributor-original: clean-room translations of PdfCraft's English UI labels, no proprietary localisation resources; 2026-10-18 page-gap labels are contributor-original AI-assisted translations from English, not separately native-reviewed; 2026-10-22 secured-document notice labels are contributor-original AI-assisted translations from English, not separately native-reviewed; the 2026-10-22 reply-count label is an AI-assisted translation from English, not separately native-reviewed | Turkish UI strings, compiled in by crates/ui-egui/src/i18n.rs |
|
||||
| `crates/ui-egui/src/i18n/lt.tsv` | Lithuanian interface translation catalog | PdfCraft contributors | MIT OR Apache-2.0 | Contributor-original: clean-room translations of PdfCraft's English UI labels and user-facing messages; original catalog reviewed by a native Lithuanian-speaking contributor; 2026-10-15 coverage additions are AI-assisted and not separately native-reviewed; 2026-10-18 page-gap labels are contributor-original AI-assisted translations from English, not separately native-reviewed; 2026-10-22 secured-document notice labels are contributor-original AI-assisted translations from English, not separately native-reviewed; the 2026-10-22 reply-count label is an AI-assisted translation from English, not separately native-reviewed | Lithuanian UI strings, compiled in by crates/ui-egui/src/i18n.rs |
|
||||
| `crates/ui-egui/src/i18n/hi.tsv` | Hindi interface translation catalog | PdfCraft contributors | MIT OR Apache-2.0 | Contributor-original: clean-room translations of PdfCraft's English UI labels, no proprietary localisation resources; 2026-10-22 page-gap labels are contributor-original AI-assisted translations from English, not separately native-reviewed; 2026-10-22 text-field-table labels are contributor-original AI-assisted translations from English, not separately native-reviewed; 2026-10-22 secured-document notice labels are contributor-original AI-assisted translations from English, not separately native-reviewed; the 2026-10-22 reply-count label is an AI-assisted translation from English, not separately native-reviewed | Hindi UI strings, compiled in by crates/ui-egui/src/i18n.rs |
|
||||
| `crates/ui-egui/src/i18n/id.tsv` | Indonesian interface translation catalog | PdfCraft contributors | MIT OR Apache-2.0 | Contributor-original: clean-room translations of PdfCraft's English UI labels, no proprietary localisation resources; 2026-10-22 page-gap labels are contributor-original AI-assisted translations from English, not separately native-reviewed; 2026-10-22 text-field-table labels are contributor-original AI-assisted translations from English, not separately native-reviewed; 2026-10-22 secured-document notice labels are contributor-original AI-assisted translations from English, not separately native-reviewed; the 2026-10-22 reply-count label is an AI-assisted translation from English, not separately native-reviewed | Indonesian UI strings, compiled in by crates/ui-egui/src/i18n.rs |
|
||||
| `crates/ui-egui/src/i18n/ko.tsv` | Korean interface translation catalog | PdfCraft contributors | MIT OR Apache-2.0 | Contributor-original: clean-room translations of PdfCraft's English UI labels, no proprietary localisation resources; 2026-10-22 page-gap labels are contributor-original AI-assisted translations from English, not separately native-reviewed; 2026-10-22 text-field-table labels are contributor-original AI-assisted translations from English, not separately native-reviewed; 2026-10-22 secured-document notice labels are contributor-original AI-assisted translations from English, not separately native-reviewed; the 2026-10-22 reply-count label is an AI-assisted translation from English, not separately native-reviewed | Korean UI strings, compiled in by crates/ui-egui/src/i18n.rs |
|
||||
| `crates/ui-egui/src/i18n/ro.tsv` | Romanian interface translation catalog | PdfCraft contributors | MIT OR Apache-2.0 | Contributor-original: clean-room translations of PdfCraft's English UI labels and user-facing messages; AI-assisted and not yet reviewed line by line by a native Romanian speaker; 2026-10-22 page-gap labels are contributor-original AI-assisted translations from English, not separately native-reviewed; 2026-10-22 text-field-table labels are contributor-original AI-assisted translations from English, not separately native-reviewed; 2026-10-22 secured-document notice labels are contributor-original AI-assisted translations from English, not separately native-reviewed; the 2026-10-22 reply-count label is an AI-assisted translation from English, not separately native-reviewed | Romanian UI strings, compiled in by crates/ui-egui/src/i18n.rs |
|
||||
| `crates/ui-egui/src/i18n/fi.tsv` | Finnish interface translation catalog | PdfCraft contributors | MIT OR Apache-2.0 | Contributor-original: AI-assisted (Claude Code) clean-room translations of PdfCraft's English UI labels and user-facing messages; not yet proofread by a native Finnish speaker; 2026-10-22 page-gap labels are contributor-original AI-assisted translations from English, not separately native-reviewed; 2026-10-22 text-field-table labels are contributor-original AI-assisted translations from English, not separately native-reviewed; 2026-10-22 secured-document notice labels are contributor-original AI-assisted translations from English, not separately native-reviewed; 2026-10-22 calculation-order, text-format, print, thumbnail, layer, comment-reshape and signature labels (previously English placeholders) are contributor-original AI-assisted translations from English, not separately native-reviewed; the 2026-10-22 reply-count label is an AI-assisted translation from English, not separately native-reviewed | Finnish UI strings, compiled in by crates/ui-egui/src/i18n.rs |
|
||||
| `assets/icons/accessibility.svg` | Lucide icon "accessibility" | Lucide Contributors (portions Cole Bemis, Feather) | ISC AND MIT | https://github.com/lucide-icons/lucide (npm lucide-static 1.49.0, icons/accessibility.svg) | UI icon, embedded via crates/ui-egui/src/icon_data.rs |
|
||||
| `assets/icons/align-left.svg` | Lucide icon "align-left" | Lucide Contributors (portions Cole Bemis, Feather) | ISC AND MIT | https://github.com/lucide-icons/lucide (npm lucide-static 1.49.0, icons/align-left.svg) | UI icon, embedded via crates/ui-egui/src/icon_data.rs |
|
||||
| `assets/icons/align-center.svg` | Lucide icon "align-center" | Lucide Contributors (portions Cole Bemis, Feather) | ISC AND MIT | https://github.com/lucide-icons/lucide (npm lucide-static 1.49.0, icons/align-center.svg) | UI icon, embedded via crates/ui-egui/src/icon_data.rs |
|
||||
@@ -286,17 +258,11 @@ Every asset PdfCraft includes, bundles or uses to build its published material,
|
||||
| `packaging/macos/dmg/background.tiff` | PdfCraft macOS DMG window background (rendered) | @XusBadia | MIT OR Apache-2.0 | Rendered from packaging/macos/dmg/background.svg by packaging/macos/dmg/generate.py | 1x + 2x HiDPI 16-colour palette TIFF copied into the macOS DMG by packaging/macos/package.sh; includes the app icon and the free LittleCMS built-in sRGB profile |
|
||||
| `crates/sign/tests/data/x509-rsa-sha1.pdf` | One-page PDF with a legacy adbe.x509.rsa_sha1 signature by the RSA test key | PdfCraft contributors | MIT OR Apache-2.0 | Contributor-original: hand-written PDF objects; signature made with `openssl dgst -sha1 -sign` over its byte ranges (see crates/sign/tests/data/README.md) | Signature validation tests (crates/sign/tests/it/pdf.rs): the legacy adbe.x509.rsa_sha1 format |
|
||||
| `assets/icons/monitor.svg` | Lucide icon "monitor" | Lucide Contributors (portions Cole Bemis, Feather) | ISC AND MIT | https://github.com/lucide-icons/lucide (npm lucide-static 1.49.0, icons/monitor.svg) | UI icon, embedded via crates/ui-egui/src/icon_data.rs |
|
||||
| `crates/ui-egui/src/i18n/vi.tsv` | Vietnamese interface translation catalog | PdfCraft contributors | MIT OR Apache-2.0 | Contributor-original: clean-room translations of PdfCraft's English UI labels; PhotoCraft and VectorCraft Vietnamese catalogs used only as translation memory when English source and semantic context matched; original catalog reviewed by a native Vietnamese-speaking contributor; 2026-10-15 coverage additions are AI-assisted and not separately native-reviewed; 2026-10-18 page-gap labels are contributor-original AI-assisted translations from English, not separately native-reviewed; 2026-10-22 signature-check wordings are contributor-original AI-assisted translations from English, not separately native-reviewed; 2026-10-22 secured-document notice labels are contributor-original AI-assisted translations from English, not separately native-reviewed; the 2026-10-22 reply-count label is an AI-assisted translation from English, not separately native-reviewed | Vietnamese UI strings, compiled in by crates/ui-egui/src/i18n.rs |
|
||||
| `crates/ui-egui/src/i18n/sl.tsv` | Slovene interface translation catalog | PdfCraft contributors | MIT OR Apache-2.0 | Contributor-original: clean-room translations of PdfCraft's English UI labels, no proprietary localisation resources; 2026-10-18 page-gap labels are contributor-original AI-assisted translations from English, not separately native-reviewed; 2026-10-22 secured-document notice labels are contributor-original AI-assisted translations from English, not separately native-reviewed; the 2026-10-22 reply-count label is an AI-assisted translation from English, not separately native-reviewed | Slovene UI strings, compiled in by crates/ui-egui/src/i18n.rs |
|
||||
| `vendor/vello_common/assets/probe.png` | vello_common probe reference image (rendered from probe.rgba) | Linebender vello contributors | MIT OR Apache-2.0 | vello_common 0.0.8 (crates.io), vendored in vendor/vello_common; regenerated by its vello_sparse_tests regenerate_probe_reference binary | Reference picture of the vendored vello_common probe module, for people only; the build reads probe.rgba, not this file |
|
||||
| `crates/ui-egui/src/i18n/nb.tsv` | Norwegian Bokmål interface translation catalog | PdfCraft contributors | MIT OR Apache-2.0 | Contributor-original: clean-room translations of PdfCraft's English UI labels, no proprietary localisation resources; 2026-10-22 page-gap labels are contributor-original AI-assisted translations from English, not separately native-reviewed; 2026-10-22 secured-document notice labels are contributor-original AI-assisted translations from English, not separately native-reviewed; the 2026-10-22 reply-count label is an AI-assisted translation from English, not separately native-reviewed | Norwegian Bokmål UI strings, compiled in by crates/ui-egui/src/i18n.rs |
|
||||
| `assets/icons/superscript.svg` | Lucide icon "superscript" | Lucide Contributors (portions Cole Bemis, Feather) | ISC AND MIT | https://github.com/lucide-icons/lucide (npm lucide-static 1.49.0, icons/superscript.svg) | UI icon, embedded via crates/ui-egui/src/icon_data.rs |
|
||||
| `assets/icons/subscript.svg` | Lucide icon "subscript" | Lucide Contributors (portions Cole Bemis, Feather) | ISC AND MIT | https://github.com/lucide-icons/lucide (npm lucide-static 1.49.0, icons/subscript.svg) | UI icon, embedded via crates/ui-egui/src/icon_data.rs |
|
||||
| `assets/icons/pilcrow.svg` | Lucide icon "pilcrow" | Lucide Contributors (portions Cole Bemis, Feather) | ISC AND MIT | https://github.com/lucide-icons/lucide (npm lucide-static 1.49.0, icons/pilcrow.svg) | UI icon, embedded via crates/ui-egui/src/icon_data.rs |
|
||||
| `assets/icons/move-horizontal.svg` | Lucide icon "move-horizontal" | Lucide Contributors (portions Cole Bemis, Feather) | ISC AND MIT | https://github.com/lucide-icons/lucide (npm lucide-static 1.49.0, icons/move-horizontal.svg) | UI icon, embedded via crates/ui-egui/src/icon_data.rs |
|
||||
| `crates/ui-egui/src/i18n/sq.tsv` | Albanian interface translation catalog | PdfCraft contributors | MIT OR Apache-2.0 | Contributor-original: clean-room translations of PdfCraft's English UI labels, no proprietary localisation resources; 2026-10-22 page-gap labels are contributor-original AI-assisted translations from English, not separately native-reviewed; 2026-10-22 signature-appearance labels are contributor-original AI-assisted translations from English, not separately native-reviewed; 2026-10-22 text-field-table labels are contributor-original AI-assisted translations from English, not separately native-reviewed; 2026-10-22 secured-document notice labels are contributor-original AI-assisted translations from English, not separately native-reviewed; the 2026-10-22 reply-count label is an AI-assisted translation from English, not separately native-reviewed | Albanian UI strings, compiled in by crates/ui-egui/src/i18n.rs |
|
||||
| `crates/ui-egui/src/i18n/th.tsv` | Thai interface translation catalog | PdfCraft contributors | MIT OR Apache-2.0 | Contributor-original: clean-room translations of PdfCraft's English UI labels, no proprietary localisation resources; 2026-10-22 page-gap labels are contributor-original AI-assisted translations from English, not separately native-reviewed; 2026-10-22 secured-document notice labels are contributor-original AI-assisted translations from English, not separately native-reviewed; the 2026-10-22 reply-count label is an AI-assisted translation from English, not separately native-reviewed | Thai UI strings, compiled in by crates/ui-egui/src/i18n.rs |
|
||||
| `crates/ui-egui/src/i18n/ca.tsv` | Catalan interface translation catalog | PdfCraft contributors | MIT OR Apache-2.0 | Contributor-original: clean-room translations of PdfCraft's English UI labels, written from their meaning; no proprietary localisation resources; 2026-10-22 page-gap labels are contributor-original AI-assisted translations from English, not separately native-reviewed; 2026-10-22 text-field-table labels are contributor-original AI-assisted translations from English, not separately native-reviewed; 2026-10-22 secured-document notice labels are contributor-original AI-assisted translations from English, not separately native-reviewed; the 2026-10-22 reply-count label is an AI-assisted translation from English, not separately native-reviewed | Catalan UI strings, compiled in by crates/ui-egui/src/i18n.rs |
|
||||
|
||||
## Compiled in through dependencies (6)
|
||||
|
||||
@@ -338,10 +304,11 @@ Fonts are fetched by `cargo xtask demo-pdf` into `target/demo-fonts/`, OCR model
|
||||
| `text-detection.onnx` | Ocrs text detection model | Robert Knight (ocrs-models; trained on HierText, CC-BY-SA-4.0) | CC-BY-SA-4.0 | https://github.com/robertknight/ocrs/blob/0c826441362a701c55560fefc17bf356b6d1037e/ocrs/examples/download-models.sh (author-published ONNX models; model card: https://huggingface.co/robertknight/ocrs/blob/df0edd170279ab971b53e094c627255a87e1a503/README.md, cc-by-sa-4.0) | Scan & OCR: finds words on page images (cargo xtask models) |
|
||||
| `text-recognition.onnx` | Ocrs text recognition model | Robert Knight (ocrs-models; trained on HierText, CC-BY-SA-4.0) | CC-BY-SA-4.0 | https://github.com/robertknight/ocrs/blob/0c826441362a701c55560fefc17bf356b6d1037e/ocrs/examples/download-models.sh (author-published ONNX models; model card: https://huggingface.co/robertknight/ocrs/blob/df0edd170279ab971b53e094c627255a87e1a503/README.md, cc-by-sa-4.0) | Scan & OCR: reads the words it finds (cargo xtask models) |
|
||||
|
||||
## Optional build inputs (1)
|
||||
## Optional build inputs (2)
|
||||
|
||||
Not in this repository and never downloaded by it: compiled in only when the build sets the option (official releases do). Each input attributes its own files.
|
||||
|
||||
| Input | Option | Title | Author | Licence | Source | Attribution | Used for |
|
||||
|---|---|---|---|---|---|---|---|
|
||||
| `craft-i18n` | `CRAFT_I18N_DIR` | Interface translations: the craft-i18n catalogs (locales/<code>/common.tsv and pdfcraft.tsv) of the 34 languages PdfCraft offers besides English | The craft-i18n translators, including every translator of PdfCraft's former in-repo catalogs (crates/ui-egui/src/i18n/*.tsv, migrated at pdfcraft@ecdd1e6) | MIT OR Apache-2.0 | https://github.com/storytold/craft-i18n (pinned by commit in craft-i18n.rev, which CI, releases and the flatpak manifests read) | https://github.com/storytold/craft-i18n/blob/main/ATTRIBUTION.md | Interface text in languages other than English, embedded by crates/ui-egui/build.rs and looked up through craft-libs' craft-i18n crate; a build without CRAFT_I18N_DIR is English only. Clean-room translations from PdfCraft's English interface labels |
|
||||
| `craft-fonts` | `CRAFT_FONTS_DIR` | Japanese fonts: BIZ UDPGothic (Regular, Bold), Shippori Mincho, BIZ UDMincho; native Simplified Chinese font: LXGW WenKai Lite; Arabic font: Noto Sans Arabic | The BIZ UDGothic and BIZ UDMincho Project Authors (Morisawa Inc.), The Shippori Mincho Project Authors (FONTDASU), LXGW and the original Klee Project Authors / Fontworks (LXGW WenKai Lite), The Noto Project Authors (Noto Sans Arabic) | OFL-1.1 | https://github.com/storytold/craft-fonts (pinned by commit in .github/workflows/release.yml and .github/workflows/ci.yml); LXGW WenKai Lite from https://github.com/lxgw/LxgwWenKai-Lite/releases/tag/v1.530 (commit b712c83d98acf977bacfb7fb010207802808bda9) | https://github.com/storytold/craft-fonts/blob/main/ATTRIBUTION.md | Japanese fallback in the interface (BIZ UDPGothic first) and Japanese glyphs in edited PDF text (Shippori Mincho); Simplified Chinese interface fallback on native builds only (LXGW WenKai Lite Regular, font SHA-256 f799a538a3355877e597a0ae04050e897932c9ae7689eb9227c2953c5dd549ea, OFL SHA-256 0333a85fe077b6849f8e417acc44e8bd879442ceb681e271acf93e2d57fd4e2e, read from fonts/simplified-chinese-manifest.txt and never embedded on wasm); Arabic interface text, file names and document titles (Noto Sans Arabic); the web build embeds BIZ UDPGothic Regular and the pinned small Arabic, Hebrew, Thai and Devanagari faces; the selected craft-fonts revision contains no Telugu face. Other non-Japanese CJK faces retain the general 4 MiB cap; the reviewed native-only LXGW fallback has a separate 16 MiB cap. Open-source OFL releases are permitted under current AGENTS.md §1.1 |
|
||||
+12
-341
@@ -1,296 +1,15 @@
|
||||
[[asset]]
|
||||
path = "crates/ui-egui/src/i18n/el.tsv"
|
||||
title = "Greek interface translation catalog"
|
||||
author = "Camthalion77 and contributors"
|
||||
source = "Contributor-original: clean-room translations of PdfCraft English UI labels; 2026-10-18 page-gap labels are contributor-original AI-assisted translations from English, not separately native-reviewed; 2026-10-22 secured-document notice labels are contributor-original AI-assisted translations from English, not separately native-reviewed; the 2026-10-22 reply-count label is an AI-assisted translation from English, not separately native-reviewed"
|
||||
licence = "MIT OR Apache-2.0"
|
||||
licence_file = "LICENSE-MIT"
|
||||
kind = "translation"
|
||||
usage = "Greek UI strings, compiled in by crates/ui-egui/src/i18n.rs"
|
||||
|
||||
# ATTRIBUTION.toml: one entry per asset (AGENTS.md §1). The source of truth for provenance and licences.
|
||||
# ATTRIBUTION.md is generated from this file: `cargo xtask assets --write`. Checked by `cargo xtask assets` (part of `xtask ci`).
|
||||
#
|
||||
# [[asset]] a file in this repository (committed or vendored); `sha256` must match the file.
|
||||
# Translation catalogs (kind = "translation", crates/ui-egui/src/i18n/*.tsv) are project files
|
||||
# under the project licence and carry no `sha256`: git history records their provenance.
|
||||
# [[bundled]] a file compiled into PdfCraft by a Cargo dependency (its crate version must match Cargo.lock).
|
||||
# [[fetched]] downloaded at build time by xtask (never committed), pinned by `sha256`.
|
||||
# [[build_input]] an optional build input outside this repository (e.g. craft-fonts via CRAFT_FONTS_DIR);
|
||||
# [[build_input]] an optional build input outside this repository (craft-fonts via CRAFT_FONTS_DIR, craft-i18n via CRAFT_I18N_DIR);
|
||||
# never committed or downloaded here, its own repository attributes each file.
|
||||
#
|
||||
# licence: SPDX expression from the allowlist in AGENTS.md §1.2. adobe_data = true marks the closed list of
|
||||
# Adobe-authored non-visual technical data allowed by AGENTS.md §1.1.
|
||||
|
||||
[[asset]]
|
||||
path = "crates/ui-egui/src/i18n/zh-hans.tsv"
|
||||
title = "Simplified Chinese interface translation catalog"
|
||||
author = "PdfCraft contributors"
|
||||
source = "Contributor-original: clean-room translations of PdfCraft's English UI labels, no proprietary localisation resources; 2026-10-18 page-gap labels are contributor-original AI-assisted translations from English, not separately native-reviewed; 2026-10-22 secured-document notice labels are contributor-original AI-assisted translations from English, not separately native-reviewed; the 2026-10-22 reply-count label is an AI-assisted translation from English, not separately native-reviewed"
|
||||
licence = "MIT OR Apache-2.0"
|
||||
licence_file = "LICENSE-MIT"
|
||||
kind = "translation"
|
||||
usage = "Simplified Chinese UI strings, compiled in by crates/ui-egui/src/i18n.rs"
|
||||
|
||||
[[asset]]
|
||||
path = "crates/ui-egui/src/i18n/zh-hant.tsv"
|
||||
title = "Traditional Chinese (Taiwan) interface translation catalog"
|
||||
author = "PdfCraft contributors"
|
||||
source = "Contributor-original: clean-room translations of PdfCraft's English UI labels, no proprietary localisation resources; 2026-10-18 page-gap labels are contributor-original AI-assisted translations from English, not separately native-reviewed; 2026-10-22 secured-document notice labels are contributor-original AI-assisted translations from English, not separately native-reviewed; the 2026-10-22 reply-count label is an AI-assisted translation from English, not separately native-reviewed"
|
||||
licence = "MIT OR Apache-2.0"
|
||||
licence_file = "LICENSE-MIT"
|
||||
kind = "translation"
|
||||
usage = "Traditional Chinese UI strings, compiled in by crates/ui-egui/src/i18n.rs"
|
||||
|
||||
[[asset]]
|
||||
path = "crates/ui-egui/src/i18n/cs.tsv"
|
||||
title = "Czech interface translation catalog"
|
||||
author = "PdfCraft contributors"
|
||||
source = "Contributor-original: clean-room translations of PdfCraft's English UI labels, no proprietary localisation resources; 2026-10-18 page-gap labels are contributor-original AI-assisted translations from English, not separately native-reviewed; 2026-10-22 signature-check and standard-identification wordings are contributor-original AI-assisted translations from English, not separately native-reviewed; 2026-10-22 secured-document notice labels are contributor-original AI-assisted translations from English, not separately native-reviewed; the 2026-10-22 reply-count label is an AI-assisted translation from English, not separately native-reviewed"
|
||||
licence = "MIT OR Apache-2.0"
|
||||
licence_file = "LICENSE-MIT"
|
||||
kind = "translation"
|
||||
usage = "Czech UI strings, compiled in by crates/ui-egui/src/i18n.rs"
|
||||
|
||||
[[asset]]
|
||||
path = "crates/ui-egui/src/i18n/pt-br.tsv"
|
||||
title = "Brazilian Portuguese interface translation catalog"
|
||||
author = "André Cardoso (andrecards), PdfCraft contributors"
|
||||
source = "Clean-room translations of PdfCraft's English UI labels, no proprietary localisation resources: the ~1,826-entry gist posted in issue #288 (https://gist.github.com/andrecards/ac388c25fba17312ce83207f8b7b467e), completed and reviewed by PdfCraft contributors; 2026-10-18 page-gap labels are contributor-original AI-assisted translations from English, not separately native-reviewed; 2026-10-22 text-field-table limit messages are contributor-original AI-assisted translations from English, not separately native-reviewed; 2026-10-22 secured-document notice labels are contributor-original AI-assisted translations from English, not separately native-reviewed; the 2026-10-22 reply-count label is an AI-assisted translation from English, not separately native-reviewed"
|
||||
licence = "MIT OR Apache-2.0"
|
||||
licence_file = "LICENSE-MIT"
|
||||
kind = "translation"
|
||||
usage = "Brazilian Portuguese UI strings, compiled in by crates/ui-egui/src/i18n.rs"
|
||||
|
||||
[[asset]]
|
||||
path = "crates/ui-egui/src/i18n/es.tsv"
|
||||
title = "Spanish interface translation catalog"
|
||||
author = "PdfCraft contributors"
|
||||
source = "Contributor-original: clean-room translations of PdfCraft's English UI labels, no proprietary localisation resources; the 2026-10-20 coverage additions are AI-assisted and not separately native-reviewed; 2026-10-18 page-gap labels are contributor-original AI-assisted translations from English, not separately native-reviewed; 2026-10-22 signature-check wordings are contributor-original AI-assisted translations from English, not separately native-reviewed; 2026-10-22 secured-document notice labels are contributor-original AI-assisted translations from English, not separately native-reviewed; the 2026-10-22 reply-count label is an AI-assisted translation from English, not separately native-reviewed"
|
||||
licence = "MIT OR Apache-2.0"
|
||||
licence_file = "LICENSE-MIT"
|
||||
kind = "translation"
|
||||
usage = "Spanish UI strings, compiled in by crates/ui-egui/src/i18n.rs"
|
||||
|
||||
[[asset]]
|
||||
path = "crates/ui-egui/src/i18n/fr.tsv"
|
||||
title = "French interface translation catalog"
|
||||
author = "PdfCraft contributors"
|
||||
source = "Contributor-original: clean-room translations of PdfCraft's English UI labels, no proprietary localisation resources; 2026-10-18 page-gap labels are contributor-original AI-assisted translations from English, not separately native-reviewed; 2026-10-22 secured-document notice labels are contributor-original AI-assisted translations from English, not separately native-reviewed; the 2026-10-22 reply-count label is an AI-assisted translation from English, not separately native-reviewed"
|
||||
licence = "MIT OR Apache-2.0"
|
||||
licence_file = "LICENSE-MIT"
|
||||
kind = "translation"
|
||||
usage = "French UI strings, compiled in by crates/ui-egui/src/i18n.rs"
|
||||
|
||||
[[asset]]
|
||||
path = "crates/ui-egui/src/i18n/de.tsv"
|
||||
title = "German interface translation catalog"
|
||||
author = "PdfCraft contributors"
|
||||
source = "Contributor-original: clean-room translations of PdfCraft's English UI labels, no proprietary localisation resources; 2026-10-18 page-gap labels are contributor-original AI-assisted translations from English, not separately native-reviewed; 2026-10-22 secured-document notice labels are contributor-original AI-assisted translations from English, not separately native-reviewed; the 2026-10-22 reply-count label is an AI-assisted translation from English, not separately native-reviewed"
|
||||
licence = "MIT OR Apache-2.0"
|
||||
licence_file = "LICENSE-MIT"
|
||||
kind = "translation"
|
||||
usage = "German UI strings, compiled in by crates/ui-egui/src/i18n.rs"
|
||||
|
||||
[[asset]]
|
||||
path = "crates/ui-egui/src/i18n/lo.tsv"
|
||||
title = "Lao interface translation catalog"
|
||||
author = "@bounkirdni-2025"
|
||||
source = "Contributor-original: clean-room translations of PdfCraft English UI labels, no proprietary localisation resources; 2026-10-22 page-gap labels are contributor-original AI-assisted translations from English, not separately native-reviewed; 2026-10-22 secured-document notice labels are contributor-original AI-assisted translations from English, not separately native-reviewed; the 2026-10-22 reply-count label is an AI-assisted translation from English, not separately native-reviewed"
|
||||
licence = "MIT OR Apache-2.0"
|
||||
licence_file = "LICENSE-MIT"
|
||||
kind = "translation"
|
||||
usage = "Lao UI strings, compiled in by crates/ui-egui/src/i18n.rs"
|
||||
|
||||
[[asset]]
|
||||
path = "crates/ui-egui/src/i18n/te.tsv"
|
||||
title = "Telugu interface translation catalog"
|
||||
author = "PdfCraft contributors"
|
||||
source = "Contributor-original: clean-room translations of PdfCraft's English UI labels, no proprietary localisation resources; 2026-10-18 page-gap labels are contributor-original AI-assisted translations from English, not separately native-reviewed; 2026-10-22 secured-document notice labels are contributor-original AI-assisted translations from English, not separately native-reviewed; the 2026-10-22 reply-count label is an AI-assisted translation from English, not separately native-reviewed"
|
||||
licence = "MIT OR Apache-2.0"
|
||||
licence_file = "LICENSE-MIT"
|
||||
kind = "translation"
|
||||
usage = "Telugu UI strings, compiled in by crates/ui-egui/src/i18n.rs"
|
||||
|
||||
[[asset]]
|
||||
path = "crates/ui-egui/src/i18n/it.tsv"
|
||||
title = "Italian interface translation catalog"
|
||||
author = "PdfCraft contributors"
|
||||
source = "Contributor-original: clean-room translations of PdfCraft's English UI labels, no proprietary localisation resources; 2026-10-18 page-gap labels are contributor-original AI-assisted translations from English, not separately native-reviewed; 2026-10-22 secured-document notice labels are contributor-original AI-assisted translations from English, not separately native-reviewed; the 2026-10-22 reply-count label is an AI-assisted translation from English, not separately native-reviewed"
|
||||
licence = "MIT OR Apache-2.0"
|
||||
licence_file = "LICENSE-MIT"
|
||||
kind = "translation"
|
||||
usage = "Italian UI strings, compiled in by crates/ui-egui/src/i18n.rs"
|
||||
|
||||
[[asset]]
|
||||
path = "crates/ui-egui/src/i18n/pl.tsv"
|
||||
title = "Polish interface translation catalog"
|
||||
author = "PdfCraft contributors"
|
||||
source = "Contributor-original: clean-room translations of PdfCraft's English UI labels, no proprietary localisation resources; 2026-10-18 page-gap labels are contributor-original AI-assisted translations from English, not separately native-reviewed; 2026-10-22 signature-check wordings are contributor-original AI-assisted translations from English, not separately native-reviewed; 2026-10-22 secured-document notice labels are contributor-original AI-assisted translations from English, not separately native-reviewed; the 2026-10-22 reply-count label is an AI-assisted translation from English, not separately native-reviewed"
|
||||
licence = "MIT OR Apache-2.0"
|
||||
licence_file = "LICENSE-MIT"
|
||||
kind = "translation"
|
||||
usage = "Polish UI strings, compiled in by crates/ui-egui/src/i18n.rs"
|
||||
|
||||
[[asset]]
|
||||
path = "crates/ui-egui/src/i18n/ru.tsv"
|
||||
title = "Russian interface translation catalog"
|
||||
author = "PdfCraft contributors"
|
||||
source = "Contributor-original: clean-room translations of PdfCraft's English UI labels, no proprietary localisation resources; 2026-10-18 page-gap labels are contributor-original AI-assisted translations from English, not separately native-reviewed; 2026-10-22 secured-document notice labels are contributor-original AI-assisted translations from English, not separately native-reviewed; the 2026-10-22 reply-count label is an AI-assisted translation from English, not separately native-reviewed"
|
||||
licence = "MIT OR Apache-2.0"
|
||||
licence_file = "LICENSE-MIT"
|
||||
kind = "translation"
|
||||
usage = "Russian UI strings, compiled in by crates/ui-egui/src/i18n.rs"
|
||||
|
||||
[[asset]]
|
||||
path = "crates/ui-egui/src/i18n/hu.tsv"
|
||||
title = "Hungarian interface translation catalog"
|
||||
author = "PdfCraft contributors"
|
||||
source = "Contributor-original: clean-room translations of PdfCraft's English UI labels, no proprietary localisation resources; 2026-10-18 page-gap labels are contributor-original AI-assisted translations from English, not separately native-reviewed; 2026-10-22 secured-document notice labels are contributor-original AI-assisted translations from English, not separately native-reviewed; the 2026-10-22 reply-count label is an AI-assisted translation from English, not separately native-reviewed"
|
||||
licence = "MIT OR Apache-2.0"
|
||||
licence_file = "LICENSE-MIT"
|
||||
kind = "translation"
|
||||
usage = "Hungarian UI strings, compiled in by crates/ui-egui/src/i18n.rs"
|
||||
|
||||
[[asset]]
|
||||
path = "crates/ui-egui/src/i18n/bg.tsv"
|
||||
title = "Bulgarian interface translation catalog"
|
||||
author = "PdfCraft contributors"
|
||||
source = "Contributor-original: clean-room translations of PdfCraft's English UI labels, no proprietary localisation resources; 2026-10-18 page-gap labels are contributor-original AI-assisted translations from English, not separately native-reviewed; 2026-10-22 secured-document notice labels are contributor-original AI-assisted translations from English, not separately native-reviewed; the 2026-10-22 reply-count label is an AI-assisted translation from English, not separately native-reviewed"
|
||||
licence = "MIT OR Apache-2.0"
|
||||
licence_file = "LICENSE-MIT"
|
||||
kind = "translation"
|
||||
usage = "Bulgarian UI strings, compiled in by crates/ui-egui/src/i18n.rs"
|
||||
|
||||
[[asset]]
|
||||
path = "crates/ui-egui/src/i18n/kk.tsv"
|
||||
title = "Kazakh interface translation catalog"
|
||||
author = "PdfCraft contributors"
|
||||
source = "Contributor-original: clean-room translations of the English UI labels into Kazakh, no proprietary localisation resources; 2026-10-18 page-gap labels are contributor-original AI-assisted translations from English, not separately native-reviewed; 2026-10-22 secured-document notice labels are contributor-original AI-assisted translations from English, not separately native-reviewed; the 2026-10-22 reply-count label is an AI-assisted translation from English, not separately native-reviewed"
|
||||
licence = "MIT OR Apache-2.0"
|
||||
licence_file = "LICENSE-MIT"
|
||||
kind = "translation"
|
||||
usage = "Kazakh UI strings, compiled in by crates/ui-egui/src/i18n.rs"
|
||||
|
||||
[[asset]]
|
||||
path = "crates/ui-egui/src/i18n/ja.tsv"
|
||||
title = "Japanese interface translation catalog"
|
||||
author = "PdfCraft contributors"
|
||||
source = "Contributor-original: clean-room translations of PdfCraft's English UI labels, no proprietary localisation resources; 2026-10-18 page-gap labels are contributor-original AI-assisted translations from English, not separately native-reviewed; 2026-10-22 secured-document notice labels are contributor-original AI-assisted translations from English, not separately native-reviewed; the 2026-10-22 reply-count label is an AI-assisted translation from English, not separately native-reviewed"
|
||||
licence = "MIT OR Apache-2.0"
|
||||
licence_file = "LICENSE-MIT"
|
||||
kind = "translation"
|
||||
usage = "Japanese UI strings, compiled in by crates/ui-egui/src/i18n.rs"
|
||||
|
||||
[[asset]]
|
||||
path = "crates/ui-egui/src/i18n/uk.tsv"
|
||||
title = "Ukrainian interface translation catalog"
|
||||
author = "PdfCraft contributors"
|
||||
source = "Contributor-original: clean-room translations of PdfCraft's English UI labels, no proprietary localisation resources; 2026-10-18 page-gap labels are contributor-original AI-assisted translations from English, not separately native-reviewed; 2026-10-22 secured-document notice labels are contributor-original AI-assisted translations from English, not separately native-reviewed; the 2026-10-22 reply-count label is an AI-assisted translation from English, not separately native-reviewed"
|
||||
licence = "MIT OR Apache-2.0"
|
||||
licence_file = "LICENSE-MIT"
|
||||
kind = "translation"
|
||||
usage = "Ukrainian UI strings, compiled in by crates/ui-egui/src/i18n.rs"
|
||||
|
||||
[[asset]]
|
||||
path = "crates/ui-egui/src/i18n/ar.tsv"
|
||||
title = "Arabic interface translation catalog"
|
||||
author = "PdfCraft contributors"
|
||||
source = "Contributor-original: clean-room translations of PdfCraft's English UI labels, no proprietary localisation resources; 2026-10-18 page-gap labels are contributor-original AI-assisted translations from English, not separately native-reviewed; 2026-10-22 secured-document notice labels are contributor-original AI-assisted translations from English, not separately native-reviewed; the 2026-10-22 reply-count label is an AI-assisted translation from English, not separately native-reviewed"
|
||||
licence = "MIT OR Apache-2.0"
|
||||
licence_file = "LICENSE-MIT"
|
||||
kind = "translation"
|
||||
usage = "Arabic UI strings, compiled in by crates/ui-egui/src/i18n.rs"
|
||||
|
||||
[[asset]]
|
||||
path = "crates/ui-egui/src/i18n/ckb.tsv"
|
||||
title = "Central Kurdish (Sorani) interface translation catalog"
|
||||
author = "PdfCraft contributors"
|
||||
source = "Contributor-original: clean-room translations of PdfCraft's English UI labels, no proprietary localisation resources; 2026-10-22 page-gap labels are contributor-original AI-assisted translations from English, not separately native-reviewed; 2026-10-22 secured-document notice labels are contributor-original AI-assisted translations from English, not separately native-reviewed; the 2026-10-22 reply-count label is an AI-assisted translation from English, not separately native-reviewed"
|
||||
licence = "MIT OR Apache-2.0"
|
||||
licence_file = "LICENSE-MIT"
|
||||
kind = "translation"
|
||||
usage = "Central Kurdish UI strings, compiled in by crates/ui-egui/src/i18n.rs"
|
||||
|
||||
[[asset]]
|
||||
path = "crates/ui-egui/src/i18n/fa.tsv"
|
||||
title = "Persian (Farsi) interface translation catalog"
|
||||
author = "PdfCraft contributors"
|
||||
source = "Contributor-original: clean-room translations of PdfCraft's English UI labels, no proprietary localisation resources; 2026-10-25 initial catalog covering the current 2,776-entry key union, AI-assisted translations from English, not separately native-reviewed"
|
||||
licence = "MIT OR Apache-2.0"
|
||||
licence_file = "LICENSE-MIT"
|
||||
kind = "translation"
|
||||
usage = "Persian UI strings, compiled in by crates/ui-egui/src/i18n.rs"
|
||||
|
||||
[[asset]]
|
||||
path = "crates/ui-egui/src/i18n/tr.tsv"
|
||||
title = "Turkish interface translation catalog"
|
||||
author = "PdfCraft contributors"
|
||||
source = "Contributor-original: clean-room translations of PdfCraft's English UI labels, no proprietary localisation resources; 2026-10-18 page-gap labels are contributor-original AI-assisted translations from English, not separately native-reviewed; 2026-10-22 secured-document notice labels are contributor-original AI-assisted translations from English, not separately native-reviewed; the 2026-10-22 reply-count label is an AI-assisted translation from English, not separately native-reviewed"
|
||||
licence = "MIT OR Apache-2.0"
|
||||
licence_file = "LICENSE-MIT"
|
||||
kind = "translation"
|
||||
usage = "Turkish UI strings, compiled in by crates/ui-egui/src/i18n.rs"
|
||||
|
||||
[[asset]]
|
||||
path = "crates/ui-egui/src/i18n/lt.tsv"
|
||||
title = "Lithuanian interface translation catalog"
|
||||
author = "PdfCraft contributors"
|
||||
source = "Contributor-original: clean-room translations of PdfCraft's English UI labels and user-facing messages; original catalog reviewed by a native Lithuanian-speaking contributor; 2026-10-15 coverage additions are AI-assisted and not separately native-reviewed; 2026-10-18 page-gap labels are contributor-original AI-assisted translations from English, not separately native-reviewed; 2026-10-22 secured-document notice labels are contributor-original AI-assisted translations from English, not separately native-reviewed; the 2026-10-22 reply-count label is an AI-assisted translation from English, not separately native-reviewed"
|
||||
licence = "MIT OR Apache-2.0"
|
||||
licence_file = "LICENSE-MIT"
|
||||
kind = "translation"
|
||||
usage = "Lithuanian UI strings, compiled in by crates/ui-egui/src/i18n.rs"
|
||||
|
||||
[[asset]]
|
||||
path = "crates/ui-egui/src/i18n/hi.tsv"
|
||||
title = "Hindi interface translation catalog"
|
||||
author = "PdfCraft contributors"
|
||||
source = "Contributor-original: clean-room translations of PdfCraft's English UI labels, no proprietary localisation resources; 2026-10-22 page-gap labels are contributor-original AI-assisted translations from English, not separately native-reviewed; 2026-10-22 text-field-table labels are contributor-original AI-assisted translations from English, not separately native-reviewed; 2026-10-22 secured-document notice labels are contributor-original AI-assisted translations from English, not separately native-reviewed; the 2026-10-22 reply-count label is an AI-assisted translation from English, not separately native-reviewed"
|
||||
licence = "MIT OR Apache-2.0"
|
||||
licence_file = "LICENSE-MIT"
|
||||
kind = "translation"
|
||||
usage = "Hindi UI strings, compiled in by crates/ui-egui/src/i18n.rs"
|
||||
[[asset]]
|
||||
path = "crates/ui-egui/src/i18n/id.tsv"
|
||||
title = "Indonesian interface translation catalog"
|
||||
author = "PdfCraft contributors"
|
||||
source = "Contributor-original: clean-room translations of PdfCraft's English UI labels, no proprietary localisation resources; 2026-10-22 page-gap labels are contributor-original AI-assisted translations from English, not separately native-reviewed; 2026-10-22 text-field-table labels are contributor-original AI-assisted translations from English, not separately native-reviewed; 2026-10-22 secured-document notice labels are contributor-original AI-assisted translations from English, not separately native-reviewed; the 2026-10-22 reply-count label is an AI-assisted translation from English, not separately native-reviewed"
|
||||
licence = "MIT OR Apache-2.0"
|
||||
licence_file = "LICENSE-MIT"
|
||||
kind = "translation"
|
||||
usage = "Indonesian UI strings, compiled in by crates/ui-egui/src/i18n.rs"
|
||||
[[asset]]
|
||||
path = "crates/ui-egui/src/i18n/ko.tsv"
|
||||
title = "Korean interface translation catalog"
|
||||
author = "PdfCraft contributors"
|
||||
source = "Contributor-original: clean-room translations of PdfCraft's English UI labels, no proprietary localisation resources; 2026-10-22 page-gap labels are contributor-original AI-assisted translations from English, not separately native-reviewed; 2026-10-22 text-field-table labels are contributor-original AI-assisted translations from English, not separately native-reviewed; 2026-10-22 secured-document notice labels are contributor-original AI-assisted translations from English, not separately native-reviewed; the 2026-10-22 reply-count label is an AI-assisted translation from English, not separately native-reviewed"
|
||||
licence = "MIT OR Apache-2.0"
|
||||
licence_file = "LICENSE-MIT"
|
||||
kind = "translation"
|
||||
usage = "Korean UI strings, compiled in by crates/ui-egui/src/i18n.rs"
|
||||
|
||||
[[asset]]
|
||||
path = "crates/ui-egui/src/i18n/ro.tsv"
|
||||
title = "Romanian interface translation catalog"
|
||||
author = "PdfCraft contributors"
|
||||
source = "Contributor-original: clean-room translations of PdfCraft's English UI labels and user-facing messages; AI-assisted and not yet reviewed line by line by a native Romanian speaker; 2026-10-22 page-gap labels are contributor-original AI-assisted translations from English, not separately native-reviewed; 2026-10-22 text-field-table labels are contributor-original AI-assisted translations from English, not separately native-reviewed; 2026-10-22 secured-document notice labels are contributor-original AI-assisted translations from English, not separately native-reviewed; the 2026-10-22 reply-count label is an AI-assisted translation from English, not separately native-reviewed"
|
||||
licence = "MIT OR Apache-2.0"
|
||||
licence_file = "LICENSE-MIT"
|
||||
kind = "translation"
|
||||
usage = "Romanian UI strings, compiled in by crates/ui-egui/src/i18n.rs"
|
||||
|
||||
|
||||
[[asset]]
|
||||
path = "crates/ui-egui/src/i18n/fi.tsv"
|
||||
title = "Finnish interface translation catalog"
|
||||
author = "PdfCraft contributors"
|
||||
source = "Contributor-original: AI-assisted (Claude Code) clean-room translations of PdfCraft's English UI labels and user-facing messages; not yet proofread by a native Finnish speaker; 2026-10-22 page-gap labels are contributor-original AI-assisted translations from English, not separately native-reviewed; 2026-10-22 text-field-table labels are contributor-original AI-assisted translations from English, not separately native-reviewed; 2026-10-22 secured-document notice labels are contributor-original AI-assisted translations from English, not separately native-reviewed; 2026-10-22 calculation-order, text-format, print, thumbnail, layer, comment-reshape and signature labels (previously English placeholders) are contributor-original AI-assisted translations from English, not separately native-reviewed; the 2026-10-22 reply-count label is an AI-assisted translation from English, not separately native-reviewed"
|
||||
licence = "MIT OR Apache-2.0"
|
||||
licence_file = "LICENSE-MIT"
|
||||
kind = "translation"
|
||||
usage = "Finnish UI strings, compiled in by crates/ui-egui/src/i18n.rs"
|
||||
|
||||
[[asset]]
|
||||
path = "assets/icons/accessibility.svg"
|
||||
title = "Lucide icon \"accessibility\""
|
||||
@@ -3381,6 +3100,17 @@ kind = "model"
|
||||
usage = "Scan & OCR: reads the words it finds (cargo xtask models)"
|
||||
sha256 = "86c145c2edb96c8caed5b1ebb8f44d706408922211451c309c625157dd6061c5"
|
||||
|
||||
[[build_input]]
|
||||
name = "craft-i18n"
|
||||
option = "CRAFT_I18N_DIR"
|
||||
title = "Interface translations: the craft-i18n catalogs (locales/<code>/common.tsv and pdfcraft.tsv) of the 34 languages PdfCraft offers besides English"
|
||||
author = "The craft-i18n translators, including every translator of PdfCraft's former in-repo catalogs (crates/ui-egui/src/i18n/*.tsv, migrated at pdfcraft@ecdd1e6)"
|
||||
source = "https://github.com/storytold/craft-i18n (pinned by commit in craft-i18n.rev, which CI, releases and the flatpak manifests read)"
|
||||
licence = "MIT OR Apache-2.0"
|
||||
attribution = "https://github.com/storytold/craft-i18n/blob/main/ATTRIBUTION.md"
|
||||
kind = "translation"
|
||||
usage = "Interface text in languages other than English, embedded by crates/ui-egui/build.rs and looked up through craft-libs' craft-i18n crate; a build without CRAFT_I18N_DIR is English only. Clean-room translations from PdfCraft's English interface labels"
|
||||
|
||||
[[build_input]]
|
||||
name = "craft-fonts"
|
||||
option = "CRAFT_FONTS_DIR"
|
||||
@@ -3414,26 +3144,6 @@ kind = "icon"
|
||||
usage = "UI icon, embedded via crates/ui-egui/src/icon_data.rs"
|
||||
sha256 = "d1a443233345724859de8e4fb48968ba91e885e12ddbd710701548bd91b39428"
|
||||
|
||||
[[asset]]
|
||||
path = "crates/ui-egui/src/i18n/vi.tsv"
|
||||
title = "Vietnamese interface translation catalog"
|
||||
author = "PdfCraft contributors"
|
||||
source = "Contributor-original: clean-room translations of PdfCraft's English UI labels; PhotoCraft and VectorCraft Vietnamese catalogs used only as translation memory when English source and semantic context matched; original catalog reviewed by a native Vietnamese-speaking contributor; 2026-10-15 coverage additions are AI-assisted and not separately native-reviewed; 2026-10-18 page-gap labels are contributor-original AI-assisted translations from English, not separately native-reviewed; 2026-10-22 signature-check wordings are contributor-original AI-assisted translations from English, not separately native-reviewed; 2026-10-22 secured-document notice labels are contributor-original AI-assisted translations from English, not separately native-reviewed; the 2026-10-22 reply-count label is an AI-assisted translation from English, not separately native-reviewed"
|
||||
licence = "MIT OR Apache-2.0"
|
||||
licence_file = "LICENSE-MIT"
|
||||
kind = "translation"
|
||||
usage = "Vietnamese UI strings, compiled in by crates/ui-egui/src/i18n.rs"
|
||||
|
||||
[[asset]]
|
||||
path = "crates/ui-egui/src/i18n/sl.tsv"
|
||||
title = "Slovene interface translation catalog"
|
||||
author = "PdfCraft contributors"
|
||||
source = "Contributor-original: clean-room translations of PdfCraft's English UI labels, no proprietary localisation resources; 2026-10-18 page-gap labels are contributor-original AI-assisted translations from English, not separately native-reviewed; 2026-10-22 secured-document notice labels are contributor-original AI-assisted translations from English, not separately native-reviewed; the 2026-10-22 reply-count label is an AI-assisted translation from English, not separately native-reviewed"
|
||||
licence = "MIT OR Apache-2.0"
|
||||
licence_file = "LICENSE-MIT"
|
||||
kind = "translation"
|
||||
usage = "Slovene UI strings, compiled in by crates/ui-egui/src/i18n.rs"
|
||||
|
||||
[[asset]]
|
||||
|
||||
path = "vendor/vello_common/assets/probe.png"
|
||||
@@ -3446,16 +3156,6 @@ kind = "image"
|
||||
usage = "Reference picture of the vendored vello_common probe module, for people only; the build reads probe.rgba, not this file"
|
||||
sha256 = "78c59a0cfd2c829909d77006f94e34dac1ae5d1f90e7f10f72e84de541fef697"
|
||||
|
||||
[[asset]]
|
||||
path = "crates/ui-egui/src/i18n/nb.tsv"
|
||||
title = "Norwegian Bokmål interface translation catalog"
|
||||
author = "PdfCraft contributors"
|
||||
source = "Contributor-original: clean-room translations of PdfCraft's English UI labels, no proprietary localisation resources; 2026-10-22 page-gap labels are contributor-original AI-assisted translations from English, not separately native-reviewed; 2026-10-22 secured-document notice labels are contributor-original AI-assisted translations from English, not separately native-reviewed; the 2026-10-22 reply-count label is an AI-assisted translation from English, not separately native-reviewed"
|
||||
licence = "MIT OR Apache-2.0"
|
||||
licence_file = "LICENSE-MIT"
|
||||
kind = "translation"
|
||||
usage = "Norwegian Bokmål UI strings, compiled in by crates/ui-egui/src/i18n.rs"
|
||||
|
||||
[[asset]]
|
||||
path = "assets/icons/superscript.svg"
|
||||
title = "Lucide icon \"superscript\""
|
||||
@@ -3500,32 +3200,3 @@ kind = "icon"
|
||||
usage = "UI icon, embedded via crates/ui-egui/src/icon_data.rs"
|
||||
sha256 = "864ab2f19254e6ac7240bc6a98323197332e8f714d4d3f94831f41309e5ef2f7"
|
||||
|
||||
[[asset]]
|
||||
path = "crates/ui-egui/src/i18n/sq.tsv"
|
||||
title = "Albanian interface translation catalog"
|
||||
author = "PdfCraft contributors"
|
||||
source = "Contributor-original: clean-room translations of PdfCraft's English UI labels, no proprietary localisation resources; 2026-10-22 page-gap labels are contributor-original AI-assisted translations from English, not separately native-reviewed; 2026-10-22 signature-appearance labels are contributor-original AI-assisted translations from English, not separately native-reviewed; 2026-10-22 text-field-table labels are contributor-original AI-assisted translations from English, not separately native-reviewed; 2026-10-22 secured-document notice labels are contributor-original AI-assisted translations from English, not separately native-reviewed; the 2026-10-22 reply-count label is an AI-assisted translation from English, not separately native-reviewed"
|
||||
licence = "MIT OR Apache-2.0"
|
||||
licence_file = "LICENSE-MIT"
|
||||
kind = "translation"
|
||||
usage = "Albanian UI strings, compiled in by crates/ui-egui/src/i18n.rs"
|
||||
|
||||
[[asset]]
|
||||
path = "crates/ui-egui/src/i18n/th.tsv"
|
||||
title = "Thai interface translation catalog"
|
||||
author = "PdfCraft contributors"
|
||||
source = "Contributor-original: clean-room translations of PdfCraft's English UI labels, no proprietary localisation resources; 2026-10-22 page-gap labels are contributor-original AI-assisted translations from English, not separately native-reviewed; 2026-10-22 secured-document notice labels are contributor-original AI-assisted translations from English, not separately native-reviewed; the 2026-10-22 reply-count label is an AI-assisted translation from English, not separately native-reviewed"
|
||||
licence = "MIT OR Apache-2.0"
|
||||
licence_file = "LICENSE-MIT"
|
||||
kind = "translation"
|
||||
usage = "Thai UI strings, compiled in by crates/ui-egui/src/i18n.rs"
|
||||
|
||||
[[asset]]
|
||||
path = "crates/ui-egui/src/i18n/ca.tsv"
|
||||
title = "Catalan interface translation catalog"
|
||||
author = "PdfCraft contributors"
|
||||
source = "Contributor-original: clean-room translations of PdfCraft's English UI labels, written from their meaning; no proprietary localisation resources; 2026-10-22 page-gap labels are contributor-original AI-assisted translations from English, not separately native-reviewed; 2026-10-22 text-field-table labels are contributor-original AI-assisted translations from English, not separately native-reviewed; 2026-10-22 secured-document notice labels are contributor-original AI-assisted translations from English, not separately native-reviewed; the 2026-10-22 reply-count label is an AI-assisted translation from English, not separately native-reviewed"
|
||||
licence = "MIT OR Apache-2.0"
|
||||
licence_file = "LICENSE-MIT"
|
||||
kind = "translation"
|
||||
usage = "Catalan UI strings, compiled in by crates/ui-egui/src/i18n.rs"
|
||||
Generated
+37
-36
@@ -4208,7 +4208,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "pdfcraft"
|
||||
version = "0.17.0"
|
||||
version = "0.18.1"
|
||||
dependencies = [
|
||||
"chrono",
|
||||
"craft-update",
|
||||
@@ -4232,7 +4232,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "pdfcraft-a11y"
|
||||
version = "0.17.0"
|
||||
version = "0.18.1"
|
||||
dependencies = [
|
||||
"pdfcraft-content",
|
||||
"pdfcraft-cos",
|
||||
@@ -4244,7 +4244,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "pdfcraft-annot"
|
||||
version = "0.17.0"
|
||||
version = "0.18.1"
|
||||
dependencies = [
|
||||
"hayro-syntax",
|
||||
"pdfcraft-cos",
|
||||
@@ -4255,7 +4255,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "pdfcraft-audit"
|
||||
version = "0.17.0"
|
||||
version = "0.18.1"
|
||||
dependencies = [
|
||||
"pdfcraft-content",
|
||||
"pdfcraft-cos",
|
||||
@@ -4266,7 +4266,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "pdfcraft-automation"
|
||||
version = "0.17.0"
|
||||
version = "0.18.1"
|
||||
dependencies = [
|
||||
"base64 0.23.1",
|
||||
"flate2",
|
||||
@@ -4288,7 +4288,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "pdfcraft-cli"
|
||||
version = "0.17.0"
|
||||
version = "0.18.1"
|
||||
dependencies = [
|
||||
"base64 0.23.1",
|
||||
"pdfcraft-audit",
|
||||
@@ -4306,11 +4306,11 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "pdfcraft-compare"
|
||||
version = "0.17.0"
|
||||
version = "0.18.1"
|
||||
|
||||
[[package]]
|
||||
name = "pdfcraft-content"
|
||||
version = "0.17.0"
|
||||
version = "0.18.1"
|
||||
dependencies = [
|
||||
"hayro-syntax",
|
||||
"pdfcraft-cos",
|
||||
@@ -4318,7 +4318,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "pdfcraft-cos"
|
||||
version = "0.17.0"
|
||||
version = "0.18.1"
|
||||
dependencies = [
|
||||
"chrono",
|
||||
"hayro-syntax",
|
||||
@@ -4333,7 +4333,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "pdfcraft-create"
|
||||
version = "0.17.0"
|
||||
version = "0.18.1"
|
||||
dependencies = [
|
||||
"encoding_rs",
|
||||
"hayro-ccitt",
|
||||
@@ -4352,7 +4352,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "pdfcraft-crypt"
|
||||
version = "0.17.0"
|
||||
version = "0.18.1"
|
||||
dependencies = [
|
||||
"aes",
|
||||
"md-5",
|
||||
@@ -4364,7 +4364,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "pdfcraft-edit"
|
||||
version = "0.17.0"
|
||||
version = "0.18.1"
|
||||
dependencies = [
|
||||
"hayro-syntax",
|
||||
"kurbo 0.13.1",
|
||||
@@ -4382,7 +4382,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "pdfcraft-engine"
|
||||
version = "0.17.0"
|
||||
version = "0.18.1"
|
||||
dependencies = [
|
||||
"chrono",
|
||||
"craft-docpath",
|
||||
@@ -4426,14 +4426,14 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "pdfcraft-export"
|
||||
version = "0.17.0"
|
||||
version = "0.18.1"
|
||||
dependencies = [
|
||||
"flate2",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "pdfcraft-filters"
|
||||
version = "0.17.0"
|
||||
version = "0.18.1"
|
||||
dependencies = [
|
||||
"fax",
|
||||
"flate2",
|
||||
@@ -4446,7 +4446,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "pdfcraft-fonts"
|
||||
version = "0.17.0"
|
||||
version = "0.18.1"
|
||||
dependencies = [
|
||||
"harfrust",
|
||||
"pdfcraft-cos",
|
||||
@@ -4456,7 +4456,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "pdfcraft-forms"
|
||||
version = "0.17.0"
|
||||
version = "0.18.1"
|
||||
dependencies = [
|
||||
"hayro-syntax",
|
||||
"pdfcraft-content",
|
||||
@@ -4469,11 +4469,11 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "pdfcraft-geom"
|
||||
version = "0.17.0"
|
||||
version = "0.18.1"
|
||||
|
||||
[[package]]
|
||||
name = "pdfcraft-js"
|
||||
version = "0.17.0"
|
||||
version = "0.18.1"
|
||||
dependencies = [
|
||||
"boa_engine",
|
||||
"chrono",
|
||||
@@ -4481,7 +4481,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "pdfcraft-measure"
|
||||
version = "0.17.0"
|
||||
version = "0.18.1"
|
||||
dependencies = [
|
||||
"pdfcraft-annot",
|
||||
"pdfcraft-content",
|
||||
@@ -4494,14 +4494,14 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "pdfcraft-model"
|
||||
version = "0.17.0"
|
||||
version = "0.18.1"
|
||||
dependencies = [
|
||||
"pdfcraft-cos",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "pdfcraft-ocr"
|
||||
version = "0.17.0"
|
||||
version = "0.18.1"
|
||||
dependencies = [
|
||||
"ocrs",
|
||||
"pdfcraft-fonts",
|
||||
@@ -4512,7 +4512,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "pdfcraft-optimize"
|
||||
version = "0.17.0"
|
||||
version = "0.18.1"
|
||||
dependencies = [
|
||||
"image",
|
||||
"pdfcraft-annot",
|
||||
@@ -4528,11 +4528,11 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "pdfcraft-oracle"
|
||||
version = "0.17.0"
|
||||
version = "0.18.1"
|
||||
|
||||
[[package]]
|
||||
name = "pdfcraft-organize"
|
||||
version = "0.17.0"
|
||||
version = "0.18.1"
|
||||
dependencies = [
|
||||
"hayro-syntax",
|
||||
"pdfcraft-content",
|
||||
@@ -4543,7 +4543,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "pdfcraft-platform"
|
||||
version = "0.17.0"
|
||||
version = "0.18.1"
|
||||
dependencies = [
|
||||
"async-channel",
|
||||
"futures-lite",
|
||||
@@ -4553,7 +4553,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "pdfcraft-preflight"
|
||||
version = "0.17.0"
|
||||
version = "0.18.1"
|
||||
dependencies = [
|
||||
"flate2",
|
||||
"pdfcraft-content",
|
||||
@@ -4564,7 +4564,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "pdfcraft-print"
|
||||
version = "0.17.0"
|
||||
version = "0.18.1"
|
||||
dependencies = [
|
||||
"craft-print",
|
||||
"pdfcraft-content",
|
||||
@@ -4576,7 +4576,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "pdfcraft-redact"
|
||||
version = "0.17.0"
|
||||
version = "0.18.1"
|
||||
dependencies = [
|
||||
"pdfcraft-annot",
|
||||
"pdfcraft-content",
|
||||
@@ -4593,7 +4593,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "pdfcraft-render"
|
||||
version = "0.17.0"
|
||||
version = "0.18.1"
|
||||
dependencies = [
|
||||
"bytemuck",
|
||||
"flate2",
|
||||
@@ -4612,7 +4612,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "pdfcraft-sign"
|
||||
version = "0.17.0"
|
||||
version = "0.18.1"
|
||||
dependencies = [
|
||||
"aes",
|
||||
"aws-lc-rs",
|
||||
@@ -4648,17 +4648,18 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "pdfcraft-testkit"
|
||||
version = "0.17.0"
|
||||
version = "0.18.1"
|
||||
|
||||
[[package]]
|
||||
name = "pdfcraft-ui-egui"
|
||||
version = "0.17.0"
|
||||
version = "0.18.1"
|
||||
dependencies = [
|
||||
"arboard",
|
||||
"base64 0.23.1",
|
||||
"block2 0.6.2",
|
||||
"bytemuck",
|
||||
"chrono",
|
||||
"craft-i18n",
|
||||
"craft-keymap",
|
||||
"craft-menu",
|
||||
"craft-quit",
|
||||
@@ -4706,7 +4707,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "pdfcraft-web"
|
||||
version = "0.17.0"
|
||||
version = "0.18.1"
|
||||
dependencies = [
|
||||
"eframe",
|
||||
"egui",
|
||||
@@ -4718,7 +4719,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "pdfcraft-xfa"
|
||||
version = "0.17.0"
|
||||
version = "0.18.1"
|
||||
dependencies = [
|
||||
"base64 0.23.1",
|
||||
"image",
|
||||
@@ -4732,7 +4733,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "pdfcraft-xfdf"
|
||||
version = "0.17.0"
|
||||
version = "0.18.1"
|
||||
dependencies = [
|
||||
"pdfcraft-annot",
|
||||
"pdfcraft-cos",
|
||||
|
||||
+38
-34
@@ -5,7 +5,7 @@ exclude = ["vendor"]
|
||||
default-members = ["crates/*", "apps/pdfcraft", "apps/pdfcraft-cli", "xtask"]
|
||||
|
||||
[workspace.package]
|
||||
version = "0.17.0"
|
||||
version = "0.18.1"
|
||||
edition = "2024"
|
||||
license = "MIT OR Apache-2.0"
|
||||
rust-version = "1.95"
|
||||
@@ -19,6 +19,10 @@ craft-quit = { git = "https://github.com/storytold/craft-libs", version = "0.1.0
|
||||
# One menu definition for the native macOS menu bar and the in-window bar elsewhere.
|
||||
craft-menu = { git = "https://github.com/storytold/craft-libs", version = "0.1.0", rev = "787a7a0f972fd1d7a7618fdbeca3a5267a0407ff" }
|
||||
craft-keymap = { git = "https://github.com/storytold/craft-libs", version = "0.1.0", rev = "787a7a0f972fd1d7a7618fdbeca3a5267a0407ff", default-features = false }
|
||||
# Interface translations: lookup, fallback, CLDR plurals and language names over the craft-i18n
|
||||
# catalogs that `crates/ui-egui/build.rs` embeds from `CRAFT_I18N_DIR` (storytold/craft-i18n, at
|
||||
# the commit in `craft-i18n.rev`). Already in the tree through craft-ui.
|
||||
craft-i18n = { git = "https://github.com/storytold/craft-libs", version = "0.1.0", rev = "787a7a0f972fd1d7a7618fdbeca3a5267a0407ff" }
|
||||
# Shared system spooler; document composition remains in pdfcraft-print.
|
||||
craft-print = { git = "https://github.com/storytold/craft-libs", version = "0.1.0", rev = "787a7a0f972fd1d7a7618fdbeca3a5267a0407ff" }
|
||||
# Whether a path stored in a document may be opened (GoToR link targets).
|
||||
@@ -26,39 +30,39 @@ craft-docpath = { version = "0.1.0", git = "https://github.com/storytold/craft-l
|
||||
# craft-update: app-specific pretend versions apply to startup and manual checks.
|
||||
craft-update = { git = "https://github.com/storytold/craft-libs", version = "=0.1.0", rev = "787a7a0f972fd1d7a7618fdbeca3a5267a0407ff", features = ["egui"] }
|
||||
# internal
|
||||
pdfcraft-geom = { path = "crates/geom", version = "0.17.0" }
|
||||
pdfcraft-filters = { path = "crates/filters", version = "0.17.0" }
|
||||
pdfcraft-cos = { path = "crates/cos", version = "0.17.0" }
|
||||
pdfcraft-crypt = { path = "crates/crypt", version = "0.17.0" }
|
||||
pdfcraft-organize = { path = "crates/organize", version = "0.17.0" }
|
||||
pdfcraft-measure = { path = "crates/measure", version = "0.17.0" }
|
||||
pdfcraft-annot = { path = "crates/annot", version = "0.17.0" }
|
||||
pdfcraft-audit = { path = "crates/audit", version = "0.17.0" }
|
||||
pdfcraft-fonts = { path = "crates/fonts", version = "0.17.0" }
|
||||
pdfcraft-model = { path = "crates/model", version = "0.17.0" }
|
||||
pdfcraft-content = { path = "crates/content", version = "0.17.0" }
|
||||
pdfcraft-redact = { path = "crates/redact", version = "0.17.0" }
|
||||
pdfcraft-print = { path = "crates/print", version = "0.17.0" }
|
||||
pdfcraft-xfdf = { path = "crates/xfdf", version = "0.17.0" }
|
||||
pdfcraft-sign = { path = "crates/sign", version = "0.17.0" }
|
||||
pdfcraft-optimize = { path = "crates/optimize", version = "0.17.0" }
|
||||
pdfcraft-a11y = { path = "crates/a11y", version = "0.17.0" }
|
||||
pdfcraft-oracle = { path = "crates/oracle", version = "0.17.0" }
|
||||
pdfcraft-testkit = { path = "crates/testkit", version = "0.17.0" }
|
||||
pdfcraft-ocr = { path = "crates/ocr", version = "0.17.0" }
|
||||
pdfcraft-js = { path = "crates/js", version = "0.17.0" }
|
||||
pdfcraft-compare = { path = "crates/compare", version = "0.17.0" }
|
||||
pdfcraft-preflight = { path = "crates/preflight", version = "0.17.0" }
|
||||
pdfcraft-export = { path = "crates/export", version = "0.17.0" }
|
||||
pdfcraft-edit = { path = "crates/edit", version = "0.17.0" }
|
||||
pdfcraft-create = { path = "crates/create", version = "0.17.0" }
|
||||
pdfcraft-forms = { path = "crates/forms", version = "0.17.0" }
|
||||
pdfcraft-xfa = { path = "crates/xfa", version = "0.17.0" }
|
||||
pdfcraft-render = { path = "crates/render", version = "0.17.0" }
|
||||
pdfcraft-engine = { path = "crates/engine", version = "0.17.0" }
|
||||
pdfcraft-platform = { path = "crates/platform", version = "0.17.0" }
|
||||
pdfcraft-ui-egui = { path = "crates/ui-egui", version = "0.17.0" }
|
||||
pdfcraft-automation = { path = "crates/automation", version = "0.17.0", default-features = false }
|
||||
pdfcraft-geom = { path = "crates/geom", version = "0.18.1" }
|
||||
pdfcraft-filters = { path = "crates/filters", version = "0.18.1" }
|
||||
pdfcraft-cos = { path = "crates/cos", version = "0.18.1" }
|
||||
pdfcraft-crypt = { path = "crates/crypt", version = "0.18.1" }
|
||||
pdfcraft-organize = { path = "crates/organize", version = "0.18.1" }
|
||||
pdfcraft-measure = { path = "crates/measure", version = "0.18.1" }
|
||||
pdfcraft-annot = { path = "crates/annot", version = "0.18.1" }
|
||||
pdfcraft-audit = { path = "crates/audit", version = "0.18.1" }
|
||||
pdfcraft-fonts = { path = "crates/fonts", version = "0.18.1" }
|
||||
pdfcraft-model = { path = "crates/model", version = "0.18.1" }
|
||||
pdfcraft-content = { path = "crates/content", version = "0.18.1" }
|
||||
pdfcraft-redact = { path = "crates/redact", version = "0.18.1" }
|
||||
pdfcraft-print = { path = "crates/print", version = "0.18.1" }
|
||||
pdfcraft-xfdf = { path = "crates/xfdf", version = "0.18.1" }
|
||||
pdfcraft-sign = { path = "crates/sign", version = "0.18.1" }
|
||||
pdfcraft-optimize = { path = "crates/optimize", version = "0.18.1" }
|
||||
pdfcraft-a11y = { path = "crates/a11y", version = "0.18.1" }
|
||||
pdfcraft-oracle = { path = "crates/oracle", version = "0.18.1" }
|
||||
pdfcraft-testkit = { path = "crates/testkit", version = "0.18.1" }
|
||||
pdfcraft-ocr = { path = "crates/ocr", version = "0.18.1" }
|
||||
pdfcraft-js = { path = "crates/js", version = "0.18.1" }
|
||||
pdfcraft-compare = { path = "crates/compare", version = "0.18.1" }
|
||||
pdfcraft-preflight = { path = "crates/preflight", version = "0.18.1" }
|
||||
pdfcraft-export = { path = "crates/export", version = "0.18.1" }
|
||||
pdfcraft-edit = { path = "crates/edit", version = "0.18.1" }
|
||||
pdfcraft-create = { path = "crates/create", version = "0.18.1" }
|
||||
pdfcraft-forms = { path = "crates/forms", version = "0.18.1" }
|
||||
pdfcraft-xfa = { path = "crates/xfa", version = "0.18.1" }
|
||||
pdfcraft-render = { path = "crates/render", version = "0.18.1" }
|
||||
pdfcraft-engine = { path = "crates/engine", version = "0.18.1" }
|
||||
pdfcraft-platform = { path = "crates/platform", version = "0.18.1" }
|
||||
pdfcraft-ui-egui = { path = "crates/ui-egui", version = "0.18.1" }
|
||||
pdfcraft-automation = { path = "crates/automation", version = "0.18.1", default-features = false }
|
||||
|
||||
# pdf
|
||||
hayro = "0.7.1"
|
||||
|
||||
+17
@@ -1,5 +1,9 @@
|
||||
# PdfCraft roadmap
|
||||
|
||||
> **Last reviewed:** 2026-11-03 | **Last updated:** 2026-11-03 | **Change:** patch (M5 #5850 review: indirect typewriter intent and composer edits preserve outer whitespace; movement regression commits by outside click; estimates unchanged)
|
||||
|
||||
> **Last reviewed:** 2026-11-03 | **Last updated:** 2026-11-03 | **Change:** patch (M5 #5850: Enter adds Fill & Sign line breaks; outside clicks commit, Escape cancels, and saved multiline appearances retain their text and height; estimates unchanged)
|
||||
|
||||
> **Last reviewed:** 2026-11-01 | **Last updated:** 2026-11-01 | **Change:** patch (M7, PR #2155 further review: inherited drawing/text state, affine image gestures, paste/selection ownership, no-op scripts and menu permissions; estimates unchanged)
|
||||
|
||||
> **Last reviewed:** 2026-11-01 | **Last updated:** 2026-11-01 | **Change:** patch (M7, PR #2155 latest comments: explicit image-paste events, mixed-size field refresh, and documented mixed-script normalization with Undo; estimates unchanged)
|
||||
@@ -219,6 +223,16 @@ Ranked; detail and the full milestone table in [docs/roadmap.md](docs/roadmap.md
|
||||
|
||||
## Progress log
|
||||
|
||||
- **2026-11-03 (M5, #5850 review):** Resolve indirect IT when recognizing typewriter contents and Fill & Sign marks. Comment listing and property lookup retain their existing direct-Subtype behavior. A real double-click Edit composer preserves the typewriter’s text as written; ordinary comment edits keep trimming. Regressions cover direct Subtype with indirect intent, save/reopen, raw posted contents and same-index comments on different pages. The existing live-movement test now commits its setup with an outside click rather than Enter. Estimates unchanged.
|
||||
|
||||
- **2026-11-03 (M5, #5850):** Fill & Sign Enter inserts a line break in a growing editor; clicking outside commits and Escape cancels. Nonempty text keeps leading, internal and trailing line breaks. The headless fill_sign_add path sizes its typewriter box for the same wrapped lines so saved appearances show every row. Production-order keyboard and engine save/reopen/render regressions exercise the UI and headless callers. Estimates unchanged.
|
||||
|
||||
- **2026-11-03 (M7, #5835):** In image crop mode, a right-click on the image, its crop box or its handles keeps the crop and opens no menu, so the menu no longer switches as the pointer moves. A right-click elsewhere clears the selection and opens the page menu. UI tests cover all four page rotations, overlapping images, a 45° image, and a check that the Done/Cancel/Remove Crop pills at a page edge still keep the crop.
|
||||
|
||||
- **2026-11-02 (M10, #5743):** macOS print jobs name their title and owner (`com.apple.print.JobInfo.PMJobName`, `PMJobOwner`), as the system print dialog does, because a Kyocera filter crashes on a job without them. Checked by a test and through `doc_print` against a stand-in `lp`; not yet on a physical printer.
|
||||
|
||||
- **2026-11-01 (M7, #5657):** Header/footer, watermark and background additions and replacements stage the complete call before committing. Synthetic later-page failures preserve exact incremental bytes, object count, dirty state and allocation cursor; success controls retain other marks and shared/inherited resources. Estimates unchanged.
|
||||
|
||||
- **2026-11-01 (M14, #5572):** Preferences ▸ Documents and view sets how many recent files to keep, from 0 to 50 with 12 by default. At 0 Home has no Recent section and File ▸ Open Recent is disabled. The list is cut when Preferences closes, so the number can pass through 0 on its way to another.
|
||||
|
||||
- **2026-11-01 (M5/M14, customizable hotbar, freehand highlight, and moveable navigation rail):** Added Freehand-Highlight (`/Subtype /Ink`, `/IT /FreehandHighlight`, Multiply blending, 100 pt max line width) inside the standard Highlight flyout and headless `comment_add`; added a customizable floating or side-docked hotbar with a full-side chrome strip mode, settings gear icon anchored at the bar end, and 24–64 px sizing; and added Left/Right docking for the navigation rail (`rail_side`). Focused unit and integration tests pass across `annot`, `automation`, and `ui-egui`. Estimates unchanged.
|
||||
@@ -744,6 +758,9 @@ Newest first: the date, what moved, and the new overall estimate.
|
||||
|
||||
| Date | Change | Summary |
|
||||
|---|---|---|
|
||||
| 2026-11-03 | patch | M5 #5850 review: indirect typewriter intent and composer edits preserve outer whitespace; movement regression commits by outside click; estimates unchanged. |
|
||||
| 2026-11-03 | patch | M5 #5850: Enter adds Fill & Sign line breaks; outside clicks commit, Escape cancels, and saved multiline appearances retain their text and height; estimates unchanged. |
|
||||
| 2026-11-01 | patch | M7 #5657: header/footer, watermark and background operations commit all selected pages together; later-page errors preserve marks, content, shared/inherited resources and pending edits; estimates unchanged. |
|
||||
| 2026-10-28 | patch | M2, PR #4172: integrate main 5af10276 and retain both roadmap histories; viewer-only CJK and print/output font policies and estimates unchanged. |
|
||||
| 2026-10-27 | minor | M10: OCR stages SHA-256-verified ONNX models after the upstream RTEN URL brownout; discovery prefers a complete ONNX pair per directory, falls back to a complete RTEN pair, and never mixes formats or directories; language/web limits and estimates unchanged. |
|
||||
| 2026-10-23 | minor | M8, #3205 follow-up: phone-pattern redaction includes the +39 country code on labelled Italian geographic numbers with a slash; dates, protocol identifiers and whole-run guards remain. Estimates unchanged. |
|
||||
|
||||
@@ -663,6 +663,29 @@ fn the_desktop_entry_names_the_window_class() {
|
||||
assert_eq!(class, Some(super::APP_ID));
|
||||
}
|
||||
|
||||
/// Both flatpak manifests build with the craft-i18n commit `craft-i18n.rev` pins: CI and
|
||||
/// releases read the file, and the manifests have to name the commit themselves. The pin may
|
||||
/// have a trailing newline or CRLF (a Windows checkout), so it is trimmed, as every reader does.
|
||||
#[test]
|
||||
fn the_flatpak_manifests_pin_the_craft_i18n_rev() {
|
||||
let root = std::path::Path::new(env!("CARGO_MANIFEST_DIR")).join("../..");
|
||||
let rev = std::fs::read_to_string(root.join("craft-i18n.rev")).unwrap();
|
||||
let rev = rev.trim();
|
||||
assert!(rev.len() == 40 && rev.bytes().all(|b| b.is_ascii_hexdigit()), "craft-i18n.rev holds one full SHA: {rev:?}");
|
||||
for manifest in ["ai.storyteller.pdfcraft.yml", "ai.storyteller.pdfcraft.bundle.yml"] {
|
||||
let text = std::fs::read_to_string(root.join("packaging/linux/flatpak").join(manifest)).unwrap();
|
||||
let source =
|
||||
text.split("url: https://github.com/storytold/craft-i18n").nth(1).unwrap_or_else(|| panic!("{manifest}: a craft-i18n git source"));
|
||||
let source = source.split("- type:").next().unwrap_or(source);
|
||||
let commit = source
|
||||
.lines()
|
||||
.find_map(|l| l.trim().strip_prefix("commit:"))
|
||||
.unwrap_or_else(|| panic!("{manifest}: the craft-i18n source pins a commit"));
|
||||
assert_eq!(commit.trim().trim_matches(['\'', '"']), rev, "{manifest}");
|
||||
assert!(text.contains("CRAFT_I18N_DIR: /run/build/pdfcraft/craft-i18n"), "{manifest}: the build names the catalogs");
|
||||
}
|
||||
}
|
||||
|
||||
// Regression test for #246: `eprintln!` panics when standard error is a broken pipe (a GUI
|
||||
// launch on Windows), and a panic inside the panic hook aborts the process. The start-up
|
||||
// path and the hook must write to standard error without it.
|
||||
|
||||
@@ -180,3 +180,6 @@ sync_github_name = true
|
||||
|
||||
[people.dylanmtaylor]
|
||||
sync_github_name = true
|
||||
|
||||
[people.Combiler01]
|
||||
sync_github_name = true
|
||||
@@ -0,0 +1 @@
|
||||
575cfdef63227b14daf173b8cc87928bfdfa325e
|
||||
+78
-92
@@ -125,9 +125,9 @@ pub(crate) fn elements(doc: &Document) -> Vec<Element> {
|
||||
}
|
||||
|
||||
/// The marked-content ids an element owns directly.
|
||||
fn mcids(d: &Dict) -> Vec<i64> {
|
||||
fn mcids(doc: &Document, d: &Dict) -> Vec<i64> {
|
||||
let mut out = Vec::new();
|
||||
let mut push = |o: &Object| match o {
|
||||
let mut push = |o: &Object| match &*doc.resolve(o) {
|
||||
Object::Int(n) => out.push(*n),
|
||||
Object::Dict(m) if m.name(b"Type") == Some(b"MCR") => {
|
||||
if let Some(n) = m.get(b"MCID").and_then(Object::as_int) {
|
||||
@@ -323,7 +323,7 @@ pub fn figures(doc: &Document) -> Vec<Figure> {
|
||||
let mut wanted: HashMap<usize, HashSet<i64>> = HashMap::new();
|
||||
for (e, page) in &figures {
|
||||
if let Some(p) = page {
|
||||
wanted.entry(*p).or_default().extend(mcids(&e.dict));
|
||||
wanted.entry(*p).or_default().extend(mcids(doc, &e.dict));
|
||||
}
|
||||
}
|
||||
let bounds: HashMap<usize, HashMap<i64, [f64; 4]>> =
|
||||
@@ -333,7 +333,7 @@ pub fn figures(doc: &Document) -> Vec<Figure> {
|
||||
.map(|(e, page)| {
|
||||
let alt = e.dict.get(b"Alt").map(|o| doc.resolve(o)).and_then(|o| o.as_string().map(|s| s.to_text()));
|
||||
let on_page = page.and_then(|p| bounds.get(&p));
|
||||
let bbox = on_page.and_then(|b| mcids(&e.dict).iter().filter_map(|id| b.get(id)).fold(None, |acc, b| Some(union(acc, *b))));
|
||||
let bbox = on_page.and_then(|b| mcids(doc, &e.dict).iter().filter_map(|id| b.get(id)).fold(None, |acc, b| Some(union(acc, *b))));
|
||||
Figure { obj: e.object, page, alt, bbox }
|
||||
})
|
||||
.collect()
|
||||
@@ -363,52 +363,73 @@ pub fn set_alt(doc: &mut Document, obj: ObjRef, alt: Option<&str>) -> Result<(),
|
||||
}
|
||||
|
||||
/// The page's content entries: one stream, or the elements of a contents array.
|
||||
fn content_entries(doc: &Document, page: &Dict) -> Option<Vec<Object>> {
|
||||
let c = page.get(b"Contents")?;
|
||||
Some(match &*doc.resolve(c) {
|
||||
fn content_entries(doc: &Document, page: &Dict) -> Vec<Object> {
|
||||
let Some(c) = page.get(b"Contents") else { return Vec::new() };
|
||||
match &*doc.resolve(c) {
|
||||
Object::Array(a) => a.clone(),
|
||||
Object::Stream(_) => vec![c.clone()],
|
||||
_ => return None,
|
||||
})
|
||||
_ => Vec::new(),
|
||||
}
|
||||
}
|
||||
|
||||
fn marked(doc: &Document, props: &Dict, op: &pdfcraft_content::Op, ids: &HashSet<i64>) -> bool {
|
||||
op.op == b"BDC" && bdc_mcid(doc, props, op).is_some_and(|n| ids.contains(&n))
|
||||
}
|
||||
type DecodedStream = (Object, Option<(Stream, Vec<u8>)>);
|
||||
|
||||
/// Turn the figure's marked-content blocks into artifacts, rewriting only the streams that
|
||||
/// contain them. Other content streams, and unknown entries on a rewritten stream, stay.
|
||||
fn artifact_marked_content(doc: &mut Document, page: &pdfcraft_model::Page, ids: &HashSet<i64>) -> Result<bool, AltError> {
|
||||
let Some(entries) = content_entries(doc, &page.dict) else { return Ok(false) };
|
||||
let props = page_properties(doc, &page.dict);
|
||||
let mut streams: Vec<Option<(Stream, Vec<u8>)>> = Vec::with_capacity(entries.len());
|
||||
/// Decode the page's content streams within the page decode budget. `None` when a stream is
|
||||
/// rejected because the budget is exhausted.
|
||||
fn decode_page_streams(doc: &Document, page: &Dict) -> Option<Vec<DecodedStream>> {
|
||||
let entries = content_entries(doc, page);
|
||||
let mut streams = Vec::with_capacity(entries.len());
|
||||
let mut budget = DecodeBudget::page();
|
||||
for entry in &entries {
|
||||
match &*doc.resolve(entry) {
|
||||
for entry in entries {
|
||||
let decoded = match &*doc.resolve(&entry) {
|
||||
Object::Stream(s) => {
|
||||
let data = match budget.decode(s) {
|
||||
Ok(data) => data,
|
||||
// Content past the budget may hold more of the figure: editing the rest
|
||||
// would leave that part marked as a figure the tree no longer has.
|
||||
Err(_) if budget.exhausted() => return Err(AltError::TooLarge),
|
||||
// Content past the budget may hold more of the tag: editing the rest
|
||||
// would leave that part marked as a tag the tree no longer has.
|
||||
Err(_) if budget.exhausted() => return None,
|
||||
Err(_) => Vec::new(),
|
||||
};
|
||||
streams.push(Some((s.clone(), data)));
|
||||
Some((s.clone(), data))
|
||||
}
|
||||
_ => streams.push(None),
|
||||
_ => None,
|
||||
};
|
||||
streams.push((entry, decoded));
|
||||
}
|
||||
Some(streams)
|
||||
}
|
||||
|
||||
fn marked_id(doc: &Document, props: &Dict, op: &pdfcraft_content::Op, ids: &HashSet<i64>) -> Option<i64> {
|
||||
(op.op == b"BDC").then(|| bdc_mcid(doc, props, op)).flatten().filter(|n| ids.contains(n))
|
||||
}
|
||||
|
||||
/// Turn the tag's marked-content blocks into artifacts, rewriting only the streams that
|
||||
/// contain them. Other content streams, and unknown entries on a rewritten stream, stay.
|
||||
/// With `require_all`, every id in `ids` must appear on the page before any stream is rewritten.
|
||||
fn artifact_marked_content(
|
||||
doc: &mut Document,
|
||||
page: &pdfcraft_model::Page,
|
||||
streams: Vec<DecodedStream>,
|
||||
ids: &HashSet<i64>,
|
||||
require_all: bool,
|
||||
) -> Result<bool, pdfcraft_cos::CosError> {
|
||||
let props = page_properties(doc, &page.dict);
|
||||
let decoded: Vec<&[u8]> = streams.iter().filter_map(|(_, s)| s.as_ref().map(|(_, bytes)| bytes.as_slice())).collect();
|
||||
let pieces = pdfcraft_content::Pieces::join(&decoded);
|
||||
let mut found = HashSet::new();
|
||||
let mut edits = Vec::new();
|
||||
for op in pieces.parse().ops {
|
||||
if let Some(id) = marked_id(doc, &props, &op, ids) {
|
||||
found.insert(id);
|
||||
edits.push((op.span, b"/Artifact BMC".to_vec()));
|
||||
}
|
||||
}
|
||||
let decoded: Vec<&[u8]> = streams.iter().flatten().map(|(_, bytes)| bytes.as_slice()).collect();
|
||||
let pieces = pdfcraft_content::Pieces::join(&decoded);
|
||||
let edits: Vec<_> =
|
||||
pieces.parse().ops.into_iter().filter(|op| marked(doc, &props, op, ids)).map(|op| (op.span, b"/Artifact BMC".to_vec())).collect();
|
||||
if edits.is_empty() {
|
||||
if if require_all { found != *ids } else { found.is_empty() } {
|
||||
return Ok(false);
|
||||
}
|
||||
let mut spliced = pieces.splice(edits).into_iter();
|
||||
let mut next = Vec::with_capacity(entries.len());
|
||||
let mut changed = false;
|
||||
for (entry, stream) in entries.into_iter().zip(streams) {
|
||||
let mut next = Vec::with_capacity(streams.len());
|
||||
for (entry, stream) in streams {
|
||||
let Some((stream, old)) = stream else {
|
||||
next.push(entry);
|
||||
continue;
|
||||
@@ -421,7 +442,6 @@ fn artifact_marked_content(doc: &mut Document, page: &pdfcraft_model::Page, ids:
|
||||
next.push(entry);
|
||||
continue;
|
||||
}
|
||||
changed = true;
|
||||
let mut dict = stream.dict;
|
||||
dict.remove(b"Length");
|
||||
dict.remove(b"Filter");
|
||||
@@ -431,28 +451,27 @@ fn artifact_marked_content(doc: &mut Document, page: &pdfcraft_model::Page, ids:
|
||||
// appear elsewhere in this array or on another page, where it must stay unchanged.
|
||||
next.push(Object::Ref(doc.add(stream)));
|
||||
}
|
||||
if changed {
|
||||
let contents = match next.as_slice() {
|
||||
[one] => one.clone(),
|
||||
_ => Object::Array(next),
|
||||
};
|
||||
doc.update_dict(page.obj, |p| p.set(b"Contents".to_vec(), contents))?;
|
||||
}
|
||||
Ok(changed)
|
||||
let contents = match next.as_slice() {
|
||||
[one] => one.clone(),
|
||||
_ => Object::Array(next),
|
||||
};
|
||||
doc.update_dict(page.obj, |p| p.set(b"Contents".to_vec(), contents))?;
|
||||
Ok(true)
|
||||
}
|
||||
|
||||
/// Decorative figure: its marked content on the page becomes an artifact, and the element
|
||||
/// leaves the structure tree (and the parent tree).
|
||||
pub fn mark_decorative(doc: &mut Document, obj: ObjRef) -> Result<(), AltError> {
|
||||
let d = check_figure(doc, obj)?;
|
||||
let ids: HashSet<i64> = mcids(&d).into_iter().collect();
|
||||
let ids: HashSet<i64> = mcids(doc, &d).into_iter().collect();
|
||||
let pages = pdfcraft_model::pages(doc);
|
||||
let pg = d.get(b"Pg").and_then(Object::as_ref).or_else(|| elements(doc).into_iter().find(|e| e.object == obj).and_then(|e| e.page));
|
||||
if let Some(page) = pg.and_then(|p| pages.iter().find(|x| x.obj == p)).filter(|_| !ids.is_empty())
|
||||
&& artifact_marked_content(doc, page, &ids)?
|
||||
{
|
||||
if let Some(page) = pg.and_then(|p| pages.iter().find(|x| x.obj == p)).filter(|_| !ids.is_empty()) {
|
||||
let streams = decode_page_streams(doc, &page.dict).ok_or(AltError::TooLarge)?;
|
||||
// The parent tree no longer points those ids at the figure.
|
||||
if let Some(key) = page.dict.get(b"StructParents").and_then(Object::as_int) {
|
||||
if artifact_marked_content(doc, page, streams, &ids, false)?
|
||||
&& let Some(key) = page.dict.get(b"StructParents").and_then(Object::as_int)
|
||||
{
|
||||
clear_parent_tree(doc, key, obj)?;
|
||||
}
|
||||
}
|
||||
@@ -484,54 +503,23 @@ pub fn mark_tag_artifact(doc: &mut Document, obj: ObjRef) -> Result<(), Artifact
|
||||
if has_child_structure(doc, &element.dict) {
|
||||
return Err(ArtifactError::HasChildren);
|
||||
}
|
||||
let ids: HashSet<i64> = mcids(&element.dict).into_iter().collect();
|
||||
let ids: HashSet<i64> = mcids(doc, &element.dict).into_iter().collect();
|
||||
if ids.is_empty() {
|
||||
return Err(ArtifactError::NoMarkedContent);
|
||||
}
|
||||
let pages = pdfcraft_model::pages(doc);
|
||||
let page_ref = element.page.ok_or(ArtifactError::NoPage)?;
|
||||
let page = pages.iter().find(|page| page.obj == page_ref).ok_or(ArtifactError::NoPage)?;
|
||||
let mut content = Vec::new();
|
||||
if let Some(c) = page.dict.get(b"Contents") {
|
||||
let mut budget = DecodeBudget::page();
|
||||
for data in budget.decode_contents(doc, c) {
|
||||
match data {
|
||||
Ok(data) => {
|
||||
content.extend_from_slice(&data);
|
||||
content.push(b' ');
|
||||
}
|
||||
// The page's /Contents is replaced with what was decoded: content past the
|
||||
// budget would be dropped from the page.
|
||||
Err(_) if budget.exhausted() => return Err(ArtifactError::TooLarge),
|
||||
Err(_) => {}
|
||||
}
|
||||
}
|
||||
}
|
||||
let mut ops = pdfcraft_content::parse(&content).ops;
|
||||
let mut found = HashSet::new();
|
||||
for op in &mut ops {
|
||||
let id = (op.op == b"BDC")
|
||||
.then(|| match op.operands.get(1) {
|
||||
Some(Object::Dict(mark)) => mark.get(b"MCID").and_then(Object::as_int),
|
||||
_ => None,
|
||||
})
|
||||
.flatten()
|
||||
.filter(|id| ids.contains(id));
|
||||
if let Some(id) = id {
|
||||
*op = pdfcraft_content::Op::new("BMC", vec![Object::name("Artifact")]);
|
||||
found.insert(id);
|
||||
}
|
||||
}
|
||||
if found != ids {
|
||||
let parent = element.dict.get(b"P").and_then(Object::as_ref).ok_or(ArtifactError::NoParent)?;
|
||||
let replacement = replacement_kids(doc, parent, obj)?;
|
||||
let streams = decode_page_streams(doc, &page.dict).ok_or(ArtifactError::TooLarge)?;
|
||||
if !artifact_marked_content(doc, page, streams, &ids, true)? {
|
||||
return Err(ArtifactError::ContentNotFound);
|
||||
}
|
||||
let stream = doc.add(Object::Stream(Stream::flate(Dict::new(), &pdfcraft_content::serialize_ops(&ops))));
|
||||
doc.update_dict(page.obj, |p| p.set(b"Contents".to_vec(), Object::Ref(stream)))?;
|
||||
if let Some(key) = page.dict.get(b"StructParents").and_then(Object::as_int) {
|
||||
clear_parent_tree(doc, key, obj).map_err(|e| ArtifactError::ParentTree(e.to_string()))?;
|
||||
}
|
||||
let parent = element.dict.get(b"P").and_then(Object::as_ref).ok_or(ArtifactError::NoParent)?;
|
||||
remove_from_parent(doc, parent, obj)?;
|
||||
doc.update_dict(parent, |p| p.set(b"K".to_vec(), replacement))?;
|
||||
// Keep the retired object valid if another object holds an out-of-tree reference to it.
|
||||
doc.update_dict(obj, |d| {
|
||||
d.remove(b"P");
|
||||
@@ -551,20 +539,18 @@ fn has_child_structure(doc: &Document, tag: &Dict) -> bool {
|
||||
tag.get(b"K").is_some_and(|items| child(doc, items))
|
||||
}
|
||||
|
||||
fn remove_from_parent(doc: &mut Document, parent: ObjRef, obj: ObjRef) -> Result<(), ArtifactError> {
|
||||
fn replacement_kids(doc: &Document, parent: ObjRef, obj: ObjRef) -> Result<Object, ArtifactError> {
|
||||
let kids = doc.get(parent).as_dict().and_then(|p| p.get(b"K").cloned()).ok_or(ArtifactError::NoParent)?;
|
||||
let replacement = match kids {
|
||||
match kids {
|
||||
Object::Array(items) => {
|
||||
if items.iter().filter(|item| item.as_ref() == Some(obj)).count() != 1 {
|
||||
return Err(ArtifactError::AmbiguousParent);
|
||||
}
|
||||
Object::Array(items.into_iter().filter(|item| item.as_ref() != Some(obj)).collect())
|
||||
Ok(Object::Array(items.into_iter().filter(|item| item.as_ref() != Some(obj)).collect()))
|
||||
}
|
||||
Object::Ref(r) if r == obj => Object::Array(Vec::new()),
|
||||
_ => return Err(ArtifactError::NoParent),
|
||||
};
|
||||
doc.update_dict(parent, |p| p.set(b"K".to_vec(), replacement))?;
|
||||
Ok(())
|
||||
Object::Ref(r) if r == obj => Ok(Object::Array(Vec::new())),
|
||||
_ => Err(ArtifactError::NoParent),
|
||||
}
|
||||
}
|
||||
|
||||
/// Replace `obj` by null in the page's parent-tree array (`key`), in a flat /Nums tree.
|
||||
|
||||
@@ -1017,6 +1017,76 @@ fn named_property_lists_are_found_and_marked_decorative_like_inline_ones() {
|
||||
assert!(props.contains(b"P0") && props.contains(b"P1") && props.contains(b"Other"), "resources are left as they were");
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn mark_tag_artifact_finds_named_property_lists_and_indirect_mcrs() {
|
||||
use pdfcraft_cos::{Dict, ObjRef, Object};
|
||||
let mut doc = named_figures_doc();
|
||||
let mcr = doc.add(Object::Dict([(b"Type".to_vec(), Object::name("MCR")), (b"MCID".to_vec(), Object::Int(0))].into_iter().collect::<Dict>()));
|
||||
doc.update_dict(ObjRef::new(7, 0), |d| d.set(b"K".to_vec(), Object::Ref(mcr))).unwrap();
|
||||
assert_eq!(figures(&doc)[0].bbox, Some([10.0, 150.0, 50.0, 170.0]), "indirect MCR is resolved for figure bounds");
|
||||
|
||||
for (tag, gone) in [(ObjRef::new(7, 0), "/P0"), (ObjRef::new(8, 0), "/P1")] {
|
||||
mark_tag_artifact(&mut doc, tag).unwrap();
|
||||
let pages = pdfcraft_model::pages(&doc);
|
||||
let c = doc.resolve(pages[0].dict.get(b"Contents").unwrap());
|
||||
let Object::Stream(c) = &*c else { panic!("one content stream") };
|
||||
let text = String::from_utf8(c.decoded().unwrap()).unwrap();
|
||||
assert!(text.contains("/Artifact BMC") && !text.contains(gone), "{text}");
|
||||
}
|
||||
assert_eq!(tags(&doc).into_iter().map(|t| t.object.num).collect::<Vec<_>>(), [6]);
|
||||
let nums = doc.get(ObjRef::new(9, 0)).as_dict().and_then(|d| d.get(b"Nums").cloned());
|
||||
assert_eq!(nums, Some(Object::Array(vec![Object::Int(0), Object::Array(vec![Object::Null, Object::Null])])));
|
||||
let r = check(&doc, &Options { rules: [Rule::FiguresAltText, Rule::TaggedContent].into(), pages: None });
|
||||
assert_eq!(failed(&r), Vec::<Rule>::new(), "{:?}", r.results);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn mark_tag_artifact_validates_parent_and_all_mcids_before_mutating_document() {
|
||||
use pdfcraft_cos::{ObjRef, Object};
|
||||
|
||||
// Missing /P on the tag must fail before touching /Contents or /ParentTree.
|
||||
let mut no_parent = figures_doc();
|
||||
let before_contents = no_parent.get(ObjRef::new(3, 0)).as_dict().unwrap().get(b"Contents").cloned();
|
||||
let before_pt = no_parent.get(ObjRef::new(9, 0)).as_ref().clone();
|
||||
no_parent
|
||||
.update_dict(ObjRef::new(7, 0), |d| {
|
||||
d.remove(b"P");
|
||||
})
|
||||
.unwrap();
|
||||
assert_eq!(mark_tag_artifact(&mut no_parent, ObjRef::new(7, 0)), Err(ArtifactError::NoParent));
|
||||
assert_eq!(no_parent.get(ObjRef::new(3, 0)).as_dict().unwrap().get(b"Contents").cloned(), before_contents);
|
||||
assert_eq!(*no_parent.get(ObjRef::new(9, 0)), before_pt);
|
||||
|
||||
// Duplicate entry in parent's /K must fail with AmbiguousParent before touching /Contents or /ParentTree.
|
||||
let mut dup_parent = figures_doc();
|
||||
dup_parent
|
||||
.update_dict(ObjRef::new(6, 0), |d| {
|
||||
d.set(b"K".to_vec(), Object::Array(vec![Object::Ref(ObjRef::new(7, 0)), Object::Ref(ObjRef::new(8, 0)), Object::Ref(ObjRef::new(7, 0))]));
|
||||
})
|
||||
.unwrap();
|
||||
assert_eq!(mark_tag_artifact(&mut dup_parent, ObjRef::new(7, 0)), Err(ArtifactError::AmbiguousParent));
|
||||
assert_eq!(dup_parent.get(ObjRef::new(3, 0)).as_dict().unwrap().get(b"Contents").cloned(), before_contents);
|
||||
assert_eq!(*dup_parent.get(ObjRef::new(9, 0)), before_pt);
|
||||
|
||||
// Partial MCID match (MCID 0 present, MCID 99 absent) must fail with ContentNotFound in
|
||||
// mark_tag_artifact without mutating /Contents, while mark_decorative still converts MCID 0.
|
||||
let mut partial = figures_doc();
|
||||
partial.update_dict(ObjRef::new(7, 0), |d| d.set(b"K".to_vec(), Object::Array(vec![Object::Int(0), Object::Int(99)]))).unwrap();
|
||||
assert_eq!(mark_tag_artifact(&mut partial, ObjRef::new(7, 0)), Err(ArtifactError::ContentNotFound));
|
||||
assert_eq!(partial.get(ObjRef::new(3, 0)).as_dict().unwrap().get(b"Contents").cloned(), before_contents);
|
||||
assert_eq!(*partial.get(ObjRef::new(9, 0)), before_pt);
|
||||
mark_decorative(&mut partial, ObjRef::new(7, 0)).unwrap();
|
||||
assert_ne!(partial.get(ObjRef::new(3, 0)).as_dict().unwrap().get(b"Contents").cloned(), before_contents);
|
||||
assert_ne!(*partial.get(ObjRef::new(9, 0)), before_pt);
|
||||
|
||||
// When none of a figure's MCIDs appear on the page, mark_decorative leaves /Contents and /ParentTree untouched.
|
||||
let mut absent = figures_doc();
|
||||
absent.update_dict(ObjRef::new(7, 0), |d| d.set(b"K".to_vec(), Object::Int(99))).unwrap();
|
||||
mark_decorative(&mut absent, ObjRef::new(7, 0)).unwrap();
|
||||
assert_eq!(absent.get(ObjRef::new(3, 0)).as_dict().unwrap().get(b"Contents").cloned(), before_contents);
|
||||
assert_eq!(*absent.get(ObjRef::new(9, 0)), before_pt);
|
||||
}
|
||||
|
||||
fn ref_(n: u32) -> Option<pdfcraft_cos::ObjRef> {
|
||||
Some(pdfcraft_cos::ObjRef::new(n, 0))
|
||||
}
|
||||
|
||||
@@ -99,14 +99,20 @@ fn shown_strings(ops: &[Op]) -> Vec<String> {
|
||||
|
||||
#[test]
|
||||
fn mark_decorative_leaves_the_other_stream_untouched() {
|
||||
let mut doc = tagged_figure_two_streams("0 0 1 rg 300 600 100 50 re f", "BT /F1 12 Tf 72 500 Td (After) Tj ET");
|
||||
let before = doc.get(ObjRef::new(11, 0)).clone();
|
||||
mark_decorative(&mut doc, ObjRef::new(8, 0)).expect("mark decorative succeeds");
|
||||
assert!(figures(&doc).is_empty());
|
||||
assert_eq!(*doc.get(ObjRef::new(11, 0)), *before, "the second stream holds no figure and keeps its object");
|
||||
let page = doc.get(ObjRef::new(3, 0));
|
||||
let contents = page.as_dict().unwrap().get(b"Contents").unwrap().as_array().unwrap();
|
||||
assert_eq!(contents[1].as_ref(), Some(ObjRef::new(11, 0)), "the untouched stream must not be replaced by a re-encoded copy");
|
||||
for use_artifact in [false, true] {
|
||||
let mut doc = tagged_figure_two_streams("0 0 1 rg 300 600 100 50 re f", "BT /F1 12 Tf 72 500 Td (After) Tj ET");
|
||||
let before = doc.get(ObjRef::new(11, 0)).clone();
|
||||
if use_artifact {
|
||||
mark_tag_artifact(&mut doc, ObjRef::new(8, 0)).expect("mark tag artifact succeeds");
|
||||
} else {
|
||||
mark_decorative(&mut doc, ObjRef::new(8, 0)).expect("mark decorative succeeds");
|
||||
}
|
||||
assert!(figures(&doc).is_empty());
|
||||
assert_eq!(*doc.get(ObjRef::new(11, 0)), *before, "the second stream holds no figure and keeps its object");
|
||||
let page = doc.get(ObjRef::new(3, 0));
|
||||
let contents = page.as_dict().unwrap().get(b"Contents").unwrap().as_array().unwrap();
|
||||
assert_eq!(contents[1].as_ref(), Some(ObjRef::new(11, 0)), "the untouched stream must not be replaced by a re-encoded copy");
|
||||
}
|
||||
}
|
||||
|
||||
/// A and B supply different operands to R's BDC. Reusing R must not let the first
|
||||
|
||||
@@ -47,8 +47,12 @@ pub(crate) fn text_value(doc: &Document, d: &Dict, key: &[u8]) -> Option<String>
|
||||
Object::Name(n) => String::from_utf8_lossy(n).into_owned(),
|
||||
_ => return None,
|
||||
};
|
||||
let s = s.trim_matches('\0').trim().to_string();
|
||||
(!s.is_empty()).then_some(s)
|
||||
let s = s.trim_matches('\0');
|
||||
// Typewriter outer whitespace belongs to the text (keep in step with render's inspector).
|
||||
let name_is = |key: &[u8], expected: &[u8]| d.get(key).is_some_and(|o| doc.resolve(o).as_name() == Some(expected));
|
||||
let keep_breaks = key == b"Contents" && name_is(b"Subtype", b"FreeText") && name_is(b"IT", b"FreeTextTypeWriter");
|
||||
let s = if keep_breaks { s } else { s.trim() };
|
||||
(!s.trim().is_empty()).then(|| s.to_owned())
|
||||
}
|
||||
|
||||
/// Whether an annotation subtype is a comment. Links, form widgets, pop-ups and the non-markup
|
||||
|
||||
@@ -137,11 +137,11 @@ pub fn is_fill_sign(doc: &Document, d: &Dict) -> bool {
|
||||
if matches!(d.get(b"PCFillSign").map(|o| doc.resolve(o)).as_deref(), Some(Object::Bool(true))) {
|
||||
return true;
|
||||
}
|
||||
let subtype = d.name(b"Subtype").unwrap_or_default();
|
||||
if subtype == b"FreeText" && d.name(b"IT") == Some(b"FreeTextTypeWriter") {
|
||||
let name_is = |key: &[u8], expected: &[u8]| d.get(key).is_some_and(|o| doc.resolve(o).as_name() == Some(expected));
|
||||
if name_is(b"Subtype", b"FreeText") && name_is(b"IT", b"FreeTextTypeWriter") {
|
||||
return true;
|
||||
}
|
||||
if subtype == b"Stamp" {
|
||||
if name_is(b"Subtype", b"Stamp") {
|
||||
if matches!(d.name(b"Name"), Some(b"PCCheck" | b"PCCross" | b"PCDot" | b"PCLine" | b"PCTypedSignature")) {
|
||||
return true;
|
||||
}
|
||||
@@ -151,7 +151,7 @@ pub fn is_fill_sign(doc: &Document, d: &Dict) -> bool {
|
||||
return true;
|
||||
}
|
||||
}
|
||||
subtype == b"Ink" && text_value(doc, d, b"Subj").as_deref() == Some("Signature")
|
||||
name_is(b"Subtype", b"Ink") && text_value(doc, d, b"Subj").as_deref() == Some("Signature")
|
||||
}
|
||||
|
||||
pub(crate) fn annotation_flags(doc: &Document, d: &Dict) -> i64 {
|
||||
|
||||
@@ -2250,3 +2250,27 @@ fn freehand_highlight_is_compatible_ink_with_marker_blending() {
|
||||
assert!((a - b).abs() < 1e-4, "expected [10, 90, 130, 110], got {rect_from_border:?}");
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn indirect_typewriter_names_keep_outer_whitespace_in_summaries() {
|
||||
let mut doc = fixture();
|
||||
let intent = Object::Ref(doc.add(Object::name("FreeTextTypeWriter")));
|
||||
let page = page_refs(&doc).unwrap()[0];
|
||||
let mut entries = annots(&doc, page);
|
||||
let Object::Dict(annotation) = &mut entries[0] else { panic!("fixture annotation is inline") };
|
||||
annotation.set(b"Subtype".to_vec(), Object::name("FreeText"));
|
||||
annotation.set(b"IT".to_vec(), intent);
|
||||
let contents = " \nAda\n\nLovelace\n\n ";
|
||||
annotation.set(b"Contents".to_vec(), PdfString::text(contents));
|
||||
set_annots(&mut doc, page, entries).unwrap();
|
||||
let check = |doc: &Document| {
|
||||
let list = summaries(doc);
|
||||
let summary = list.iter().find(|a| a.page == 0 && a.index == 0).expect("direct Subtype is listed");
|
||||
assert_eq!(summary.contents.as_deref(), Some(contents), "indirect typewriter intent preserves outer whitespace");
|
||||
assert_eq!(summary.subtype, "FreeText");
|
||||
assert_eq!(summary.intent.as_deref(), Some("FreeTextTypeWriter"));
|
||||
assert!(summary.fill_sign, "indirect intent still identifies a Fill & Sign mark");
|
||||
};
|
||||
check(&doc);
|
||||
check(&reopen(&doc));
|
||||
}
|
||||
+19
-18
@@ -15,7 +15,7 @@
|
||||
//! the joined stream)`; rectangles inside a form XObject carry the `Do` operator's position.
|
||||
//! Positions compare lexicographically in paint order.
|
||||
|
||||
use pdfcraft_content::{Matrix, Op, Pieces, parse};
|
||||
use pdfcraft_content::{Matrix, Op, Pieces, ops};
|
||||
use pdfcraft_cos::{DecodeBudget, Dict, Document, Object};
|
||||
|
||||
use crate::AuditError;
|
||||
@@ -123,12 +123,13 @@ impl<'a> Walker<'a> {
|
||||
Ok(())
|
||||
}
|
||||
|
||||
/// Walk one operator slice with the given graphics state. `at_do` is the `Do` position to
|
||||
/// Walk one stream's operators, read one at a time (a stream of millions of short operators
|
||||
/// is never held whole), with the given graphics state. `at_do` is the `Do` position to
|
||||
/// stamp on rectangles found inside a form XObject, or `None` at page level (where each
|
||||
/// fill operator's own position is used).
|
||||
fn walk_ops(
|
||||
&mut self,
|
||||
ops: &[Op],
|
||||
ops: impl Iterator<Item = Op>,
|
||||
gs: &mut Gs,
|
||||
stack: &mut Vec<Gs>,
|
||||
resources: &Dict,
|
||||
@@ -136,8 +137,9 @@ impl<'a> Walker<'a> {
|
||||
at_do: Option<(usize, usize)>,
|
||||
) -> Result<(), AuditError> {
|
||||
let mut path = Path::Empty;
|
||||
for (i, op) in ops.iter().enumerate() {
|
||||
for (i, op) in ops.enumerate() {
|
||||
self.bump()?;
|
||||
let op = &op;
|
||||
// Paint position of this operator: its own `(piece, joined index)` at page level,
|
||||
// the enclosing `Do`'s position inside a form XObject.
|
||||
let pos = match at_do {
|
||||
@@ -257,8 +259,9 @@ impl<'a> Walker<'a> {
|
||||
/// changes inside never leak out; every rectangle found is stamped with the `Do`
|
||||
/// position `pos`.
|
||||
fn walk_xobject(&mut self, name: &[u8], gs: &Gs, resources: &Dict, depth: usize, pos: (usize, usize)) -> Result<(), AuditError> {
|
||||
let xobjects = resources.get(b"XObject").map(|o| self.doc.resolve(o)).and_then(|o| o.as_dict().cloned()).unwrap_or_default();
|
||||
let Some(entry) = xobjects.get(name) else { return Ok(()) };
|
||||
// Borrowed, not copied: a `Do` must not cost the size of the whole XObject table.
|
||||
let xobjects = resources.get(b"XObject").map(|o| self.doc.resolve(o));
|
||||
let Some(entry) = xobjects.as_deref().and_then(Object::as_dict).and_then(|d| d.get(name)) else { return Ok(()) };
|
||||
let resolved = self.doc.resolve(entry);
|
||||
let Object::Stream(stream) = &*resolved else { return Ok(()) };
|
||||
let dict = &stream.dict;
|
||||
@@ -274,18 +277,18 @@ impl<'a> Walker<'a> {
|
||||
(v.len() == 6 && v.iter().all(|x| x.is_finite())).then(|| Matrix([v[0], v[1], v[2], v[3], v[4], v[5]]))
|
||||
})
|
||||
.unwrap_or(Matrix::IDENTITY);
|
||||
let sub_resources = dict.get(b"Resources").map(|o| self.doc.resolve(o)).and_then(|o| o.as_dict().cloned()).unwrap_or_default();
|
||||
let (sub_resources, empty) = (dict.get(b"Resources").map(|o| self.doc.resolve(o)), Dict::new());
|
||||
let sub_resources = sub_resources.as_deref().and_then(Object::as_dict).unwrap_or(&empty);
|
||||
if !self.budget.enter_form() {
|
||||
return Err(AuditError::TooManyForms);
|
||||
}
|
||||
// A form stream that cannot be decoded fails the audit: it might hide a cover.
|
||||
let data = self.budget.decode_strict(stream)?;
|
||||
let ops = parse(&data).ops;
|
||||
// The XObject matrix maps form space into the user space active at `Do`.
|
||||
let mut sub_gs = gs.clone();
|
||||
sub_gs.ctm = matrix.then(&gs.ctm);
|
||||
let mut sub_stack = Vec::new();
|
||||
self.walk_ops(&ops, &mut sub_gs, &mut sub_stack, &sub_resources, depth + 1, Some(pos))
|
||||
self.walk_ops(ops(&data), &mut sub_gs, &mut sub_stack, sub_resources, depth + 1, Some(pos))
|
||||
}
|
||||
}
|
||||
|
||||
@@ -298,13 +301,10 @@ fn user_point(gs: &Gs, op: &Op) -> Option<[f64; 2]> {
|
||||
|
||||
/// The non-stroking alpha (`/ca`) of a named ExtGState, defaulting to opaque.
|
||||
fn ext_alpha(doc: &Document, resources: &Dict, name: &[u8]) -> f64 {
|
||||
let alpha = resources
|
||||
.get(b"ExtGState")
|
||||
.map(|o| doc.resolve(o))
|
||||
.and_then(|o| o.as_dict().cloned())
|
||||
.and_then(|d| d.get(name).map(|o| doc.resolve(o)))
|
||||
.and_then(|o| o.as_dict().cloned())
|
||||
.and_then(|d| d.get(b"ca").map(|o| doc.resolve(o)).and_then(|o| o.as_f64()));
|
||||
// Borrowed, not copied: a `gs` must not cost the size of the whole ExtGState table.
|
||||
let states = resources.get(b"ExtGState").map(|o| doc.resolve(o));
|
||||
let state = states.as_deref().and_then(Object::as_dict).and_then(|d| d.get(name)).map(|o| doc.resolve(o));
|
||||
let alpha = state.as_deref().and_then(Object::as_dict).and_then(|d| d.get(b"ca").map(|o| doc.resolve(o)).and_then(|o| o.as_f64()));
|
||||
alpha.filter(|a| a.is_finite()).map(|a| a.clamp(0.0, 1.0)).unwrap_or(1.0)
|
||||
}
|
||||
|
||||
@@ -330,10 +330,11 @@ pub fn filled_rects(doc: &Document, page: &Dict) -> Result<Vec<FilledRect>, Audi
|
||||
}
|
||||
}
|
||||
let pieces = Pieces::join(&streams);
|
||||
let parsed = pieces.parse();
|
||||
let mut w = Walker { doc, pieces: &pieces, out: Vec::new(), ops_seen: 0, budget };
|
||||
let mut gs = Gs::default();
|
||||
let mut stack = Vec::new();
|
||||
w.walk_ops(&parsed.ops, &mut gs, &mut stack, &resources, 0, None)?;
|
||||
// Read one operator at a time: the joined stream can hold millions of them within the
|
||||
// decode budget, and the walk only ever needs the current one.
|
||||
w.walk_ops(ops(pieces.data()), &mut gs, &mut stack, &resources, 0, None)?;
|
||||
Ok(w.out)
|
||||
}
|
||||
+38
-19
@@ -99,6 +99,9 @@ const COVER_FRACTION: f64 = 0.4;
|
||||
const WORD_FRACTION: f64 = 0.5;
|
||||
/// WCAG contrast ratio below which the text is unreadable against the cover.
|
||||
const COVER_CONTRAST: f64 = 3.0;
|
||||
/// Bytes of a hidden line's text read (copied or trimmed) that cost one comparison: a byte scan
|
||||
/// is far cheaper than a box comparison, but a long padded line under many covers adds up.
|
||||
const TEXT_BYTES_PER_COMPARISON: usize = 16;
|
||||
|
||||
/// Audit every page for faux redactions and unapplied redaction marks. Fails closed: any
|
||||
/// content that cannot be decoded, or that needs more work or report than the audit's bounds, is
|
||||
@@ -157,15 +160,24 @@ impl Budget {
|
||||
cover: &[f64; 4],
|
||||
hides: impl Fn(&TextLine) -> bool,
|
||||
) -> Result<Option<String>, AuditError> {
|
||||
self.comparisons = self.comparisons.saturating_add(self.page_cost);
|
||||
if self.comparisons > self.limits.comparisons {
|
||||
return Err(AuditError::TooManyComparisons);
|
||||
}
|
||||
self.spend(self.page_cost)?;
|
||||
if !copying {
|
||||
return Ok(lines.iter().any(|line| hides(line) && !line.text.trim().is_empty()).then(String::new));
|
||||
let mut hidden = false;
|
||||
for line in lines.iter().filter(|l| hides(l)) {
|
||||
// Trimming walks the line's text (padding and all): it costs its bytes.
|
||||
self.spend(line.text.len() / TEXT_BYTES_PER_COMPARISON)?;
|
||||
if !line.text.trim().is_empty() {
|
||||
hidden = true;
|
||||
break;
|
||||
}
|
||||
}
|
||||
return Ok(hidden.then(String::new));
|
||||
}
|
||||
let mut covered = String::new();
|
||||
for line in lines.iter().filter(|l| hides(l)) {
|
||||
// Copying and trimming the line walks its text once per cover: a long padded
|
||||
// line under many covers would otherwise be read far more than its runs suggest.
|
||||
self.spend(line.text.len() / TEXT_BYTES_PER_COMPARISON)?;
|
||||
if !covered.is_empty() {
|
||||
covered.push(' ');
|
||||
}
|
||||
@@ -174,11 +186,21 @@ impl Budget {
|
||||
Ok((!covered.trim().is_empty()).then_some(covered))
|
||||
}
|
||||
|
||||
/// `n` units of work done against the comparison bound.
|
||||
fn spend(&mut self, n: usize) -> Result<(), AuditError> {
|
||||
self.comparisons = self.comparisons.saturating_add(n);
|
||||
if self.comparisons > self.limits.comparisons {
|
||||
return Err(AuditError::TooManyComparisons);
|
||||
}
|
||||
Ok(())
|
||||
}
|
||||
|
||||
/// The text a finding reports for `covered`: none when copying is withheld. Charges what it
|
||||
/// reports against the output bound.
|
||||
/// reports, and the finding's own record, against the output bound: a finding with no text
|
||||
/// (copying withheld, or a shared annotation list on many pages) still takes memory.
|
||||
fn report_text(&mut self, covered: String, copying: bool) -> Result<String, AuditError> {
|
||||
let reported = if copying { covered } else { String::new() };
|
||||
self.covered_text = self.covered_text.saturating_add(reported.len());
|
||||
self.covered_text = self.covered_text.saturating_add(reported.len()).saturating_add(std::mem::size_of::<AuditFinding>());
|
||||
if self.covered_text > self.limits.covered_text {
|
||||
return Err(AuditError::TooMuchOutput);
|
||||
}
|
||||
@@ -321,17 +343,14 @@ enum AnnotationCover {
|
||||
fn annots(doc: &Document, page: &Dict) -> Result<Vec<AnnotationCover>, AuditError> {
|
||||
let Some(a) = page.get(b"Annots") else { return Ok(Vec::new()) };
|
||||
let resolved = doc.resolve(a);
|
||||
let items: Vec<pdfcraft_cos::Object> = match &*resolved {
|
||||
pdfcraft_cos::Object::Array(items) => items.clone(),
|
||||
// A missing /Annots means no marks; a malformed one fails the audit.
|
||||
_ => return Err(AuditError::BadAnnots),
|
||||
};
|
||||
// A missing /Annots means no marks; a malformed one fails the audit.
|
||||
let Some(items) = resolved.as_array() else { return Err(AuditError::BadAnnots) };
|
||||
let mut out = Vec::new();
|
||||
for a in &items {
|
||||
let dict = match &*doc.resolve(a) {
|
||||
pdfcraft_cos::Object::Dict(d) => d.clone(),
|
||||
_ => continue,
|
||||
};
|
||||
for a in items {
|
||||
// Borrowed from the resolved object: one large dictionary listed many times is not
|
||||
// copied once per listing.
|
||||
let resolved = doc.resolve(a);
|
||||
let Some(dict) = resolved.as_dict() else { continue };
|
||||
let v: Vec<f64> = match dict.get(b"Rect") {
|
||||
None => continue,
|
||||
Some(r) => doc.resolve(r).as_array().map(|arr| arr.iter().filter_map(|o| doc.resolve(o).as_f64()).collect()).unwrap_or_default(),
|
||||
@@ -340,7 +359,7 @@ fn annots(doc: &Document, page: &Dict) -> Result<Vec<AnnotationCover>, AuditErro
|
||||
continue;
|
||||
}
|
||||
let rect = [v[0].min(v[2]), v[1].min(v[3]), v[0].max(v[2]), v[1].max(v[3])];
|
||||
match subtype(doc, &dict)?.as_deref() {
|
||||
match subtype(doc, dict)?.as_deref() {
|
||||
Some(b"Redact") => out.push(AnnotationCover::Redact(rect)),
|
||||
Some(b"Square") => {
|
||||
let flags = dict.get(b"F").and_then(|f| doc.resolve(f).as_int()).unwrap_or(0);
|
||||
@@ -349,7 +368,7 @@ fn annots(doc: &Document, page: &Dict) -> Result<Vec<AnnotationCover>, AuditErro
|
||||
}
|
||||
let alpha = dict.get(b"CA").map(|o| doc.resolve(o)).and_then(|o| o.as_f64()).unwrap_or(1.0);
|
||||
if alpha >= 1.0
|
||||
&& let Some(rgb) = annotation_color(doc, &dict, b"IC")
|
||||
&& let Some(rgb) = annotation_color(doc, dict, b"IC")
|
||||
{
|
||||
out.push(AnnotationCover::Square { rect, rgb });
|
||||
}
|
||||
|
||||
@@ -720,9 +720,11 @@ fn runs_without_words_count_against_the_comparison_bound() {
|
||||
let doc = open(one_page(&content, ""));
|
||||
let lines = pdfcraft_edit::glyph_text_lines(&doc, &pdfcraft_model::pages(&doc)[0]).expect("text");
|
||||
assert_eq!(lines.iter().map(|l| (l.ink.len(), l.runs().count())).collect::<Vec<_>>(), [(1, 51)]);
|
||||
let limits = crate::Limits { comparisons: 50, covered_text: usize::MAX };
|
||||
// Plus the hidden line's text, read once to copy it.
|
||||
let text = lines[0].text.len() / crate::TEXT_BYTES_PER_COMPARISON;
|
||||
let limits = crate::Limits { comparisons: 50 + text, covered_text: usize::MAX };
|
||||
assert!(matches!(crate::audit(&doc, limits), Err(crate::AuditError::TooManyComparisons)));
|
||||
let limits = crate::Limits { comparisons: 51, covered_text: usize::MAX };
|
||||
let limits = crate::Limits { comparisons: 51 + text, covered_text: usize::MAX };
|
||||
assert_eq!(crate::audit(&doc, limits).expect("within the budget").len(), 1);
|
||||
}
|
||||
|
||||
@@ -746,14 +748,18 @@ fn copy_restricted_documents_withhold_covered_text() {
|
||||
let findings = audit_redactions(&user).expect("audit must run");
|
||||
assert_eq!(findings.len(), 1, "the cover is still reported: {findings:?}");
|
||||
assert_eq!(findings[0].covered_text, "");
|
||||
// The output bound counts the text reported, so withheld text costs nothing.
|
||||
let nothing = crate::Limits { comparisons: usize::MAX, covered_text: 0 };
|
||||
// The output bound counts the text reported and the finding's record, so withheld text
|
||||
// costs only the record.
|
||||
let record = std::mem::size_of::<AuditFinding>();
|
||||
let nothing = crate::Limits { comparisons: usize::MAX, covered_text: record };
|
||||
assert_eq!(crate::audit(&user, nothing).expect("withheld text is not output").len(), 1);
|
||||
let none = crate::Limits { covered_text: record - 1, ..nothing };
|
||||
assert!(matches!(crate::audit(&user, none), Err(crate::AuditError::TooMuchOutput)));
|
||||
let owner = Document::open_with_password(bytes, Some("owner")).expect("open");
|
||||
let findings = audit_redactions(&owner).expect("audit must run");
|
||||
assert_eq!(findings.len(), 1, "{findings:?}");
|
||||
assert_eq!(findings[0].covered_text, "SECRET DATA 123");
|
||||
let exact = crate::Limits { comparisons: usize::MAX, covered_text: "SECRET DATA 123".len() };
|
||||
let exact = crate::Limits { comparisons: usize::MAX, covered_text: "SECRET DATA 123".len() + record };
|
||||
assert!(crate::audit(&owner, exact).is_ok());
|
||||
let short = crate::Limits { covered_text: exact.covered_text - 1, ..exact };
|
||||
assert!(matches!(crate::audit(&owner, short), Err(crate::AuditError::TooMuchOutput)));
|
||||
@@ -820,3 +826,52 @@ fn form_entries_past_the_page_allowance_fail_the_audit() {
|
||||
let page: Dict = [(b"Contents".to_vec(), Object::Ref(draws)), (b"Resources".to_vec(), Object::Dict(resources))].into_iter().collect();
|
||||
assert!(matches!(crate::cover::filled_rects(&doc, &page), Err(crate::AuditError::TooManyForms)));
|
||||
}
|
||||
|
||||
/// Copying a covered line's text walks all of it, padding included, so a long padded line under
|
||||
/// many covers costs its bytes once per cover, not one run per cover (CodeRabbit).
|
||||
#[test]
|
||||
fn covered_text_bytes_count_against_the_comparison_bound() {
|
||||
// One run: 20 KiB of spaces around a word, which trims to the word alone.
|
||||
let mut content = b"BT /F1 24 Tf 100 700 Td (".to_vec();
|
||||
content.extend_from_slice(&[b' '; 10_000]);
|
||||
content.extend_from_slice(b"SECRET");
|
||||
content.extend_from_slice(&[b' '; 10_000]);
|
||||
content.extend_from_slice(b") Tj ET\n0 g\n");
|
||||
for _ in 0..10 {
|
||||
content.extend_from_slice(b"-1 688 1000000 32 re f\n");
|
||||
}
|
||||
let doc = open(one_page(&content, ""));
|
||||
let lines = pdfcraft_edit::glyph_text_lines(&doc, &pdfcraft_model::pages(&doc)[0]).expect("text");
|
||||
assert_eq!(lines.len(), 1);
|
||||
let bytes = lines[0].text.len();
|
||||
assert!(bytes > 20_000, "{bytes} bytes of text");
|
||||
// Each cover: one comparison for the line, plus its bytes when it is hidden.
|
||||
let exact = crate::Limits { comparisons: 10 * (1 + bytes / crate::TEXT_BYTES_PER_COMPARISON), covered_text: usize::MAX };
|
||||
let findings = crate::audit(&doc, exact).expect("within the budget");
|
||||
assert_eq!(findings.len(), 10, "{findings:?}");
|
||||
assert!(findings.iter().all(|f| f.covered_text == "SECRET"), "{findings:?}");
|
||||
let short = crate::Limits { comparisons: exact.comparisons - 1, ..exact };
|
||||
assert!(matches!(crate::audit(&doc, short), Err(crate::AuditError::TooManyComparisons)));
|
||||
}
|
||||
|
||||
/// One annotation list shared by many pages makes a finding on each: every finding's record
|
||||
/// counts against the output bound, text or no text (CodeRabbit).
|
||||
#[test]
|
||||
fn every_finding_record_counts_against_the_output_bound() {
|
||||
let content = b"BT /F1 24 Tf 100 700 Td (SECRET) Tj ET\n";
|
||||
let mut b = Builder::new();
|
||||
b.add("<< /Type /Catalog /Pages 2 0 R >>");
|
||||
b.add("<< /Type /Pages /Kids [3 0 R 7 0 R 8 0 R] /Count 3 >>");
|
||||
b.add("<< /Type /Page /Parent 2 0 R /MediaBox [0 0 612 792] /Contents 4 0 R /Resources << /Font << /F1 5 0 R >> >> /Annots 6 0 R >>");
|
||||
b.add_stream(content);
|
||||
b.add(FONT);
|
||||
b.add("[<< /Type /Annot /Subtype /Redact /Rect [95 685 200 725] >>]");
|
||||
b.add("<< /Type /Page /Parent 2 0 R /MediaBox [0 0 612 792] /Contents 4 0 R /Resources << /Font << /F1 5 0 R >> >> /Annots 6 0 R >>");
|
||||
b.add("<< /Type /Page /Parent 2 0 R /MediaBox [0 0 612 792] /Contents 4 0 R /Resources << /Font << /F1 5 0 R >> >> /Annots 6 0 R >>");
|
||||
let doc = open(b.build());
|
||||
let one = "SECRET".len() + std::mem::size_of::<AuditFinding>();
|
||||
let exact = crate::Limits { comparisons: usize::MAX, covered_text: 3 * one };
|
||||
assert_eq!(crate::audit(&doc, exact).expect("within the budget").len(), 3);
|
||||
let short = crate::Limits { covered_text: 3 * one - 1, ..exact };
|
||||
assert!(matches!(crate::audit(&doc, short), Err(crate::AuditError::TooMuchOutput)));
|
||||
}
|
||||
@@ -5,6 +5,8 @@ Agent control for PdfCraft: a headless tool table over the engine, and an opt-in
|
||||
- **Layer:** L7 (architecture §13), but headless. It depends on `engine`, `render` and `organize`, never on a UI toolkit.
|
||||
- **Status:** over a hundred tools; `pdfcraft-cli tools` lists the current set with their schemas (the count isn't repeated here, so it can't go stale). They cover inspection, rendering, text, page edits and organizing, page labels, bookmarks, comments and their review, form filling and authoring (fields, properties, scripts, data exchange, detection), redaction and sanitizing, password protection and signatures, calibrated 2D measurements and CSV export, adding text, images, links and stamps, optimizing, OCR, printing, export, metadata, undo/redo, save, combine, extract and split. Comment tools take geometry in the same top-left-origin points as everything else, and `comment_add` can mark text by searching for it (`find`). The MCP server also serves the open documents as resources, page images included. The running app's UI is driven separately, through the `ui.*` control channel in `pdfcraft-ui-egui`.
|
||||
|
||||
`fill_sign_add` text accepts line breaks, including blank lines. Its typewriter box grows to hold all wrapped rows, and saving/reopening preserves the contents and appearance.
|
||||
|
||||
## API
|
||||
|
||||
```rust
|
||||
|
||||
@@ -6,6 +6,13 @@ impl Automation {
|
||||
let ext = path.extension().map(|e| e.to_string_lossy().into_owned()).unwrap_or_default();
|
||||
let format = pdfcraft_engine::compare::OfficeFormat::from_extension(&ext)
|
||||
.ok_or_else(|| ToolError::InvalidArgs(format!("unsupported extension {ext:?} (docx, pptx, html, rtf or md)")))?;
|
||||
let html_mode = a.opt_str("html_mode")?.unwrap_or("rich");
|
||||
let format = match (format, html_mode) {
|
||||
(pdfcraft_engine::compare::OfficeFormat::Html, "rich") => pdfcraft_engine::compare::OfficeFormat::Html,
|
||||
(pdfcraft_engine::compare::OfficeFormat::Html, "simple") => pdfcraft_engine::compare::OfficeFormat::HtmlSimple,
|
||||
(_, "rich") => format,
|
||||
(_, _) => return Err(ToolError::InvalidArgs("html_mode is only available for HTML exports (rich or simple)".into())),
|
||||
};
|
||||
let export = self.doc_to_copy(a)?.export_office_checked(format);
|
||||
write_atomic(&path, &export.bytes)?;
|
||||
// Text left out to keep a hostile page bounded is said, not silent (#3120).
|
||||
@@ -15,7 +22,7 @@ impl Automation {
|
||||
if !export.truncated_pages.is_empty() {
|
||||
use pdfcraft_engine::compare::{MAX_FORM_DEPTH, MAX_FORM_VISITS};
|
||||
out["warnings"] = json!([format!(
|
||||
"forms nested more than {MAX_FORM_DEPTH} deep, or past the first {MAX_FORM_VISITS} forms of a page (forms the page draws itself count too), were left out on the pages in truncated_pages: their text and images are missing from the export, although the viewer may still show them"
|
||||
"pictures past what one export may hold or decode, or forms nested more than {MAX_FORM_DEPTH} deep, or past the first {MAX_FORM_VISITS} forms of a page (forms the page draws itself count too), were left out on the pages in truncated_pages: their text and images are missing from the export, although the viewer may still show them"
|
||||
)]);
|
||||
}
|
||||
Ok(out)
|
||||
|
||||
@@ -0,0 +1,214 @@
|
||||
use std::io::Write;
|
||||
|
||||
use pdfcraft_engine::{Edit, HeaderFooter};
|
||||
use serde_json::{Value, json};
|
||||
|
||||
use super::error::{Result, ToolError, failed};
|
||||
use super::json::Args;
|
||||
use super::paths::read_input;
|
||||
use super::{Arc, Automation, Path, PathBuf};
|
||||
|
||||
struct FilePlan {
|
||||
input: String,
|
||||
source: PathBuf,
|
||||
password: Option<String>,
|
||||
output: PathBuf,
|
||||
pages: usize,
|
||||
first: u64,
|
||||
last: u64,
|
||||
}
|
||||
|
||||
impl Automation {
|
||||
pub(crate) fn doc_bates_multi(&mut self, args: &Args) -> Result<Value> {
|
||||
let files = args.0.get("files").and_then(Value::as_array).ok_or_else(|| ToolError::InvalidArgs("files must be an array".into()))?;
|
||||
if files.is_empty() || files.len() > 1000 {
|
||||
return Err(ToolError::InvalidArgs("files must contain 1 to 1000 entries".into()));
|
||||
}
|
||||
let start = match args.0.get("start_number") {
|
||||
None | Some(Value::Null) => 1,
|
||||
Some(value) => value
|
||||
.as_u64()
|
||||
.filter(|n| *n >= 1)
|
||||
.ok_or_else(|| ToolError::InvalidArgs("start_number must be a whole number of at least 1".into()))?,
|
||||
};
|
||||
let digits = args.opt_int("digits")?.unwrap_or(6);
|
||||
let digits =
|
||||
u8::try_from(digits).ok().filter(|d| (1..=12).contains(d)).ok_or_else(|| ToolError::InvalidArgs("digits must be from 1 to 12".into()))?;
|
||||
let prefix = args.opt_str("prefix")?.unwrap_or("");
|
||||
let suffix = args.opt_str("suffix")?.unwrap_or("");
|
||||
// `#` separates the token's fields and `>>` ends it: either would cut the token short.
|
||||
if prefix.len() > 128 || suffix.len() > 128 || [prefix, suffix].iter().any(|s| s.contains('#') || s.contains(">>")) {
|
||||
return Err(ToolError::InvalidArgs("prefix and suffix must be at most 128 bytes and cannot contain # or >>".into()));
|
||||
}
|
||||
let dry_run = args.opt_bool("dry_run")?.unwrap_or(false);
|
||||
|
||||
// Resolve and reserve the complete path list before opening or writing anything.
|
||||
let mut sources = Vec::with_capacity(files.len());
|
||||
let mut targets = Vec::with_capacity(files.len());
|
||||
let mut passwords = Vec::with_capacity(files.len());
|
||||
for entry in files {
|
||||
let input = entry
|
||||
.get("input")
|
||||
.and_then(Value::as_str)
|
||||
.filter(|s| !s.is_empty())
|
||||
.ok_or_else(|| ToolError::InvalidArgs("each file needs a non-empty input path".into()))?;
|
||||
let output = entry
|
||||
.get("output")
|
||||
.and_then(Value::as_str)
|
||||
.filter(|s| !s.is_empty())
|
||||
.ok_or_else(|| ToolError::InvalidArgs("each file needs a non-empty output path".into()))?;
|
||||
let source = self.resolve(input, false)?;
|
||||
let target = self.resolve(output, true)?;
|
||||
if target.exists() {
|
||||
return Err(failed(format!("output already exists; refusing to replace it: {output}")));
|
||||
}
|
||||
let parent = target.parent().ok_or_else(|| failed(format!("output has no parent directory: {output}")))?;
|
||||
if !parent.is_dir() {
|
||||
return Err(failed(format!("output directory does not exist: {}", parent.display())));
|
||||
}
|
||||
sources.push((input.to_string(), source));
|
||||
targets.push((output.to_string(), target));
|
||||
passwords.push(entry.get("password").and_then(Value::as_str).map(str::to_owned));
|
||||
}
|
||||
let input_paths: std::collections::HashSet<_> = sources.iter().map(|(_, path)| path.clone()).collect();
|
||||
let mut output_paths = std::collections::HashSet::new();
|
||||
for (name, path) in &targets {
|
||||
if input_paths.contains(path) {
|
||||
return Err(failed(format!("output {name} names an input file; choose a separate output path")));
|
||||
}
|
||||
if !output_paths.insert(path.clone()) {
|
||||
return Err(failed(format!("two files use the same output path: {name}")));
|
||||
}
|
||||
}
|
||||
|
||||
let mut plans = Vec::with_capacity(files.len());
|
||||
let mut next = start;
|
||||
let mut input_bytes = 0u64;
|
||||
for (index, ((input_name, input_path), (_, output_path))) in sources.iter().zip(&targets).enumerate() {
|
||||
let size = std::fs::metadata(input_path).map_err(failed)?.len();
|
||||
input_bytes = input_bytes
|
||||
.checked_add(size)
|
||||
.filter(|total| *total <= 512 * 1024 * 1024)
|
||||
.ok_or_else(|| failed("combined Bates input exceeds the 512 MiB safety limit"))?;
|
||||
let bytes = read_input(input_path)?;
|
||||
input_bytes = input_bytes
|
||||
.saturating_sub(size)
|
||||
.checked_add(u64::try_from(bytes.len()).unwrap_or(u64::MAX))
|
||||
.filter(|total| *total <= 512 * 1024 * 1024)
|
||||
.ok_or_else(|| failed("combined Bates input exceeds the 512 MiB safety limit"))?;
|
||||
let display_name = input_path.file_name().map(|n| n.to_string_lossy().into_owned()).unwrap_or_default();
|
||||
let password = passwords.get(index).and_then(Option::as_deref);
|
||||
let id = self.session.open(display_name, Some(input_path.to_string_lossy().into_owned()), Arc::new(bytes), password).map_err(failed)?;
|
||||
let pages =
|
||||
self.session.get(id).map(|doc| doc.info.pages.len()).ok_or_else(|| failed("opened document disappeared during Bates preflight"))?;
|
||||
self.session.close(id);
|
||||
if pages == 0 {
|
||||
return Err(failed(format!("{input_name} has no pages to number")));
|
||||
}
|
||||
let count = u64::try_from(pages).map_err(|_| failed(format!("page count is too large for {input_name}")))?;
|
||||
let last = next.checked_add(count.saturating_sub(1)).ok_or_else(|| failed(format!("Bates number range overflows for {input_name}")))?;
|
||||
plans.push(FilePlan {
|
||||
input: input_name.clone(),
|
||||
source: input_path.clone(),
|
||||
password: passwords.get(index).cloned().flatten(),
|
||||
output: output_path.clone(),
|
||||
pages,
|
||||
first: next,
|
||||
last,
|
||||
});
|
||||
if index + 1 < sources.len() {
|
||||
next = last.checked_add(1).ok_or_else(|| failed(format!("Bates sequence overflows after {input_name}")))?;
|
||||
}
|
||||
}
|
||||
|
||||
let intervals: Vec<Value> = plans
|
||||
.iter()
|
||||
.zip(&targets)
|
||||
.map(|(p, (name, _))| json!({"input":p.input,"output":name,"pages":p.pages,"first":p.first,"last":p.last}))
|
||||
.collect();
|
||||
if dry_run {
|
||||
return Ok(json!({"dry_run":true,"files":intervals}));
|
||||
}
|
||||
|
||||
let mut staged = Vec::with_capacity(plans.len());
|
||||
let mut results = Vec::with_capacity(plans.len());
|
||||
let mut output_bytes = 0u64;
|
||||
for plan in &plans {
|
||||
let source_bytes = match read_input(&plan.source) {
|
||||
Ok(bytes) => bytes,
|
||||
Err(error) => {
|
||||
results.push(json!({"input":plan.input,"output":plan.output,"status":"error","pages":plan.pages,"first":plan.first,"last":plan.last,"error":error.to_string()}));
|
||||
continue;
|
||||
}
|
||||
};
|
||||
let name = plan.source.file_name().map(|n| n.to_string_lossy().into_owned()).unwrap_or_default();
|
||||
let id = match self.session.open(name, Some(plan.source.to_string_lossy().into_owned()), Arc::new(source_bytes), plan.password.as_deref())
|
||||
{
|
||||
Ok(id) => id,
|
||||
Err(error) => {
|
||||
results.push(json!({"input":plan.input,"output":plan.output,"status":"error","pages":plan.pages,"first":plan.first,"last":plan.last,"error":error.to_string()}));
|
||||
continue;
|
||||
}
|
||||
};
|
||||
if self.session.get(id).is_none_or(|doc| doc.info.pages.len() != plan.pages) {
|
||||
self.session.close(id);
|
||||
results.push(json!({"input":plan.input,"output":plan.output,"status":"error","pages":plan.pages,"first":plan.first,"last":plan.last,"error":"input changed after preflight; page count differs"}));
|
||||
continue;
|
||||
}
|
||||
let template = format!("<<Bates Number#{digits}#{}#{prefix}#{suffix}>>", plan.first);
|
||||
let mut settings = HeaderFooter::default();
|
||||
settings.text[4] = template;
|
||||
let pages: Vec<usize> = (0..plan.pages).collect();
|
||||
let applied = self.session.apply(id, Edit::AddHeaderFooter { pages, settings, replace: false });
|
||||
let result = applied.and_then(|()| self.session.save_full_bytes(id));
|
||||
match result {
|
||||
Ok(bytes) => {
|
||||
let total = output_bytes.saturating_add(u64::try_from(bytes.len()).unwrap_or(u64::MAX));
|
||||
if total > 512 * 1024 * 1024 {
|
||||
results.push(json!({"input":plan.input,"output":plan.output,"status":"error","pages":plan.pages,"first":plan.first,"last":plan.last,"error":"combined Bates output exceeds the 512 MiB safety limit"}));
|
||||
} else {
|
||||
output_bytes = total;
|
||||
staged.push((plan.output.clone(), bytes));
|
||||
}
|
||||
}
|
||||
Err(error) => results.push(json!({"input":plan.input,"output":plan.output,"status":"error","pages":plan.pages,"first":plan.first,"last":plan.last,"error":error.to_string()})),
|
||||
}
|
||||
self.session.close(id);
|
||||
}
|
||||
for (path, bytes) in staged {
|
||||
match publish_new(&path, &bytes) {
|
||||
Ok(()) => {
|
||||
let plan = plans.iter().find(|p| p.output == path);
|
||||
if let Some(plan) = plan {
|
||||
results.push(json!({"input":plan.input,"output":path,"status":"ok","first":plan.first,"last":plan.last,"pages":plan.pages}));
|
||||
}
|
||||
}
|
||||
Err(error) => {
|
||||
let plan = plans.iter().find(|p| p.output == path);
|
||||
if let Some(plan) = plan {
|
||||
results.push(json!({"input":plan.input,"output":path,"status":"error","pages":plan.pages,"first":plan.first,"last":plan.last,"error":error.to_string()}));
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
results.sort_by_key(|result| plans.iter().position(|plan| result["output"] == json!(plan.output)).unwrap_or(usize::MAX));
|
||||
let completed = results.iter().filter(|r| r["status"] == "ok").count();
|
||||
let failed_count = results.len().saturating_sub(completed);
|
||||
Ok(json!({"dry_run":false,"completed":completed,"failed":failed_count,"files":results}))
|
||||
}
|
||||
}
|
||||
|
||||
/// Publish a PDF atomically while refusing a target created by another process after preflight.
|
||||
fn publish_new(path: &Path, bytes: &[u8]) -> Result<()> {
|
||||
let parent = path.parent().ok_or_else(|| failed("output has no parent directory"))?;
|
||||
let mut temp = tempfile::NamedTempFile::new_in(parent).map_err(failed)?;
|
||||
temp.write_all(bytes).map_err(failed)?;
|
||||
temp.as_file().sync_all().map_err(failed)?;
|
||||
temp.persist_noclobber(path).map(|_| ()).map_err(|error| {
|
||||
if error.error.kind() == std::io::ErrorKind::AlreadyExists {
|
||||
failed(format!("output appeared after preflight; refusing to replace it: {}", path.display()))
|
||||
} else {
|
||||
failed(error.error)
|
||||
}
|
||||
})
|
||||
}
|
||||
@@ -539,8 +539,10 @@ impl Automation {
|
||||
return self.apply(a, edit);
|
||||
}
|
||||
let text_at = |t: &str| {
|
||||
let w = (pdfcraft_engine::annot_text::text_width(t, size) + 8.0).clamp(20.0, 600.0);
|
||||
let h = size * 1.2 + 6.0;
|
||||
let longest = t.lines().map(|line| pdfcraft_engine::annot_text::text_width(line, size)).fold(0.0, f64::max);
|
||||
let w = (longest + 8.0).clamp(20.0, 600.0);
|
||||
let rows = pdfcraft_engine::annot_text::wrap(t, size, w - 4.0).len().max(1);
|
||||
let h = rows as f64 * size * 1.2 + 6.0;
|
||||
let rect = pdfcraft_engine::text_box_at(i64::from(info.rotation), at, w, h).unwrap_or([at[0], at[1] - h, at[0] + w, at[1]]);
|
||||
Shape::Typewriter { rect, font_size: size }
|
||||
};
|
||||
|
||||
@@ -53,6 +53,7 @@ impl Automation {
|
||||
tools::check_args(def, args)?;
|
||||
let a = Args(args);
|
||||
let out = match name {
|
||||
"doc_bates_multi" => self.doc_bates_multi(&a)?,
|
||||
"doc_open" => self.doc_open(&a)?,
|
||||
"doc_batch" => self.doc_batch(&a)?,
|
||||
"doc_list" => json!({ "documents": self.session.docs().iter().map(summary).collect::<Vec<_>>() }),
|
||||
@@ -323,13 +324,13 @@ impl Automation {
|
||||
let id = self.doc(&a)?.id;
|
||||
let before = self.doc(&a)?.bytes.len();
|
||||
let path = self.resolve(a.str("path")?, true)?;
|
||||
let (bytes, merged) = self.session.reduced_bytes(id).map_err(failed)?;
|
||||
let (bytes, merged, images_refused) = self.session.reduced_bytes(id).map_err(failed)?;
|
||||
// As in the app, a copy that isn't smaller is not written (#490).
|
||||
let written = bytes.len() < before;
|
||||
if written {
|
||||
write_atomic(&path, &bytes)?;
|
||||
}
|
||||
json!({ "path": path.to_string_lossy(), "written": written, "bytes_before": before, "bytes_after": bytes.len(), "merged_objects": merged })
|
||||
json!({ "path": path.to_string_lossy(), "written": written, "bytes_before": before, "bytes_after": bytes.len(), "merged_objects": merged, "images_refused": images_refused })
|
||||
}
|
||||
"doc_optimize" => self.doc_optimize(&a)?,
|
||||
"doc_initial_view" => self.doc_initial_view(&a)?,
|
||||
|
||||
@@ -410,6 +410,7 @@ impl Automation {
|
||||
"images": o.images,
|
||||
"images_resampled": o.images_resampled,
|
||||
"images_recompressed": o.images_recompressed,
|
||||
"images_refused": o.images_refused,
|
||||
"image_bytes_before": o.image_bytes_before,
|
||||
"image_bytes_after": o.image_bytes_after,
|
||||
"thumbnails": o.thumbnails,
|
||||
|
||||
@@ -16,6 +16,7 @@
|
||||
|
||||
mod a11y;
|
||||
mod batch;
|
||||
mod bates;
|
||||
mod comments;
|
||||
mod content;
|
||||
mod conventions;
|
||||
|
||||
@@ -201,8 +201,8 @@ impl Automation {
|
||||
}
|
||||
|
||||
pub(crate) fn doc_remove_hidden(&mut self, a: &Args) -> Result<Value> {
|
||||
let edit = match a.get("categories") {
|
||||
None => Edit::Sanitize,
|
||||
let which = match a.get("categories") {
|
||||
None => None,
|
||||
Some(_) => {
|
||||
let which = a
|
||||
.strs("categories")?
|
||||
@@ -212,10 +212,24 @@ impl Automation {
|
||||
if which.is_empty() {
|
||||
return Err(ToolError::InvalidArgs("categories is empty".into()));
|
||||
}
|
||||
Some(which)
|
||||
}
|
||||
};
|
||||
// One scan, for this check and for what was removed. The removal refuses when it counts
|
||||
// every listed category as 0 (an AcroForm with no fields counts 1), with an error about
|
||||
// redaction marks; this reads the same scan, so it refuses exactly then. A document that
|
||||
// can't be edited has no scan: `apply` says why.
|
||||
let info = self.doc(a)?.hidden_info();
|
||||
let edit = match which {
|
||||
None => Edit::Sanitize,
|
||||
Some(which) => {
|
||||
if !info.is_empty() && which.iter().all(|h| info.iter().find(|c| c.0 == *h).is_none_or(|c| c.1 == 0)) {
|
||||
return Err(failed("nothing to remove: the listed categories hold nothing (see doc_hidden_info)"));
|
||||
}
|
||||
Edit::RemoveHidden { which }
|
||||
}
|
||||
};
|
||||
let before: usize = self.doc(a)?.hidden_info().iter().map(|c| c.1).sum();
|
||||
let before: usize = info.iter().map(|c| c.1).sum();
|
||||
let mut out = self.apply(a, edit)?;
|
||||
let after: usize = self.doc(a)?.hidden_info().iter().map(|c| c.1).sum();
|
||||
out["removed"] = json!(before.saturating_sub(after));
|
||||
|
||||
@@ -121,6 +121,14 @@ pub fn tools() -> Vec<ToolDef> {
|
||||
let save_out = json!({ "type": "string", "description": "File to write. Omit to open the result as a new unsaved document instead." });
|
||||
let open = json!({ "type": "boolean", "description": "Also open the result as a new document (default: only when out is omitted)." });
|
||||
vec![
|
||||
t("doc_bates_multi", "Add Bates numbering across files", "Apply one consecutive Bates sequence to an ordered list of PDFs. Each file entry has input and output paths and an optional open or permissions password. The operation first validates every input/output and computes inclusive numeric intervals; dry_run returns that allocation without writing. Existing output files are never replaced. On application, files that cannot be edited or saved are reported individually and later files continue.")
|
||||
.destructive()
|
||||
.with(schema(json!({
|
||||
"files": {"type":"array","minItems":1,"maxItems":1000,"description":"PDFs in Bates sequence order.","items":{"type":"object","properties":{"input":{"type":"string","minLength":1,"description":"Input PDF path."},"output":{"type":"string","minLength":1,"description":"New output PDF path; must not exist."},"password":{"type":"string","description":"Open or permissions password, if needed."}},"required":["input","output"],"additionalProperties":false}},
|
||||
"start_number": {"type":"integer","minimum":1,"description":"First number in the sequence (default 1)."}, "digits": {"type":"integer","minimum":1,"maximum":12,"description":"Zero-padded number width (default 6)."},
|
||||
"prefix": {"type":"string","maxLength":128,"description":"Text before the number: at most 128 UTF-8 bytes, without # or >>."}, "suffix": {"type":"string","maxLength":128,"description":"Text after the number: at most 128 UTF-8 bytes, without # or >>."},
|
||||
"dry_run": {"type":"boolean","description":"Return each file's inclusive number interval without writing (default false)."}
|
||||
}), &["files"])),
|
||||
t("doc_batch", "Process files and folders", "Run convert, ocr and/or optimize over files and folders, one file at a time. recursive defaults to false. Preserve paths relative to each selected folder inside out_dir; duplicate inputs run once. Skip unsupported files, links and the output subtree. Existing outputs receive numbered names and are never replaced. Continue after per-file errors unless stop_on_error is true. Return completed/failed/skipped counts and per-file results. Discovery is bounded to 10000 entries and 64 folder levels. Convert must be first; each step can appear once. OCR uses installed models. Optimize uses Reduce File Size settings, optionally overriding target ppi (threshold 1.5 times ppi; black-and-white images go to the larger of ppi and 300) and JPEG quality; a larger candidate keeps the original bytes. Sources and open documents are unchanged.")
|
||||
.with(schema(json!({
|
||||
"paths": {"type":"array","items":{"type":"string"},"minItems":1,"maxItems":1000},
|
||||
@@ -562,7 +570,7 @@ pub fn tools() -> Vec<ToolDef> {
|
||||
t(
|
||||
"doc_remove_hidden",
|
||||
"Remove hidden information / Sanitize",
|
||||
"Remove the listed categories (see doc_hidden_info), or every category when none are listed (Sanitize Document). Form fields are flattened so their values stay visible. The next save rewrites the whole file. Undoable until saved.",
|
||||
"Remove the listed categories (see doc_hidden_info), or every category when none are listed (Sanitize Document). Fails when the listed categories hold nothing. Form fields are flattened so their values stay visible. The next save rewrites the whole file. Undoable until saved.",
|
||||
)
|
||||
.destructive()
|
||||
.with(schema(
|
||||
@@ -1195,9 +1203,9 @@ pub fn tools() -> Vec<ToolDef> {
|
||||
json!({ "doc": doc(), "field": { "type": "string" }, "event": { "type": "string", "enum": ["keystroke", "format", "validate", "calculate", "mouse_up"] }, "script": { "type": "string" } }),
|
||||
&["doc", "field", "event"],
|
||||
)),
|
||||
t("doc_export_office", "Export to Word, PowerPoint, HTML, RTF or Markdown", "Export a PDF ▸ Word (.docx), PowerPoint (.pptx, one slide per page), HTML (.html, one file with images inline), RTF (.rtf) or Markdown (.md or .markdown: pipe tables, images left out), chosen by path's extension: text, headings, bold and italic. Word uses borderless inferred tables and positioned editable shapes on pages with artwork, rotated or large text; each source page retains its size. Font matching and vector graphics remain limited. Export reads forms 50 deep and up to 50 000 a page, counting forms the page draws itself. Pages that go past either limit are listed in truncated_pages, with a warning; the text and images of the forms left out are missing.")
|
||||
t("doc_export_office", "Export to Word, PowerPoint, HTML, RTF or Markdown", "Export a PDF ▸ Word (.docx), PowerPoint (.pptx, one slide per page), HTML (.html, one file with images inline), RTF (.rtf) or Markdown (.md or .markdown: pipe tables, images left out), chosen by path's extension: text, headings, bold and italic. HTML uses rich styling by default; set html_mode to simple for CSS-free headings, paragraphs, emphasis and tables. Simple HTML keeps text and inline images but omits colour and layout styling. Word uses borderless inferred tables and positioned editable shapes on pages with artwork, rotated or large text; each source page retains its size. Font matching and vector graphics remain limited. Export reads forms 50 deep and up to 50 000 a page, counting forms the page draws itself. Pages that go past either limit, or that have pictures past what one export may hold or decode, are listed in truncated_pages, with a warning; what was left out is missing.")
|
||||
.cmd("export.docx")
|
||||
.with(schema(json!({ "doc": doc(), "path": { "type": "string" } }), &["doc", "path"])),
|
||||
.with(schema(json!({ "doc": doc(), "path": { "type": "string" }, "html_mode": { "type": "string", "enum": ["rich", "simple"], "default": "rich" } }), &["doc", "path"])),
|
||||
t("pdfa_verify", "Verify PDF/A", "Standards ▸ Verify PDF/A compliance: the PDF/A-2b or 3b rules the document breaks (ISO 19005 clause, message, page, whether Save as PDF/A can fix it), plus what it declares.")
|
||||
.ro()
|
||||
.cmd("standards.pdfa")
|
||||
@@ -1282,7 +1290,7 @@ pub fn tools() -> Vec<ToolDef> {
|
||||
.ro()
|
||||
.cmd("ocr.recognize")
|
||||
.with(schema(json!({}), &[])),
|
||||
t("doc_export_all_images", "Export all images", "Write the images that pages use into a folder (`<name>_Page_<n>_Image_<k>.jpg|png`, n zero-padded to the page count's digits), each once: JPEG images unchanged, others as PNG with their soft mask as alpha. min_size skips images with fewer pixels on their shorter side. Images that can't be decoded yet (JPEG 2000, separations) are listed under skipped. Includes unsaved edits.")
|
||||
t("doc_export_all_images", "Export all images", "Write the images that pages use into a folder (`<name>_Page_<n>_Image_<k>.jpg|png`, n zero-padded to the page count's digits), each once: JPEG images unchanged, others as PNG with their soft mask as alpha. min_size skips images with fewer pixels on their shorter side. Images that can't be decoded yet (JPEG 2000, separations), or past what one export may decode or hold, are listed under skipped, with the reason. Includes unsaved edits.")
|
||||
.cmd("export.all_images")
|
||||
.with(schema(
|
||||
json!({
|
||||
@@ -1341,7 +1349,7 @@ pub fn tools() -> Vec<ToolDef> {
|
||||
}),
|
||||
&["from"],
|
||||
)),
|
||||
t("doc_reduce", "Reduce file size", "Write a smaller copy of the document to `path` with Acrobat's Reduce File Size choices: colour and grey images above 225 ppi downsampled to 150 ppi and JPEG-compressed (medium quality), black-and-white images averaged down to 300 ppi above 450 ppi and each stored as CCITT Group 4 (or 1-bit Flate, once resampled or packed from more bits) whenever that is smaller, thumbnails dropped, identical fonts and images merged, unused objects dropped, compressed object streams. If the copy wouldn't be smaller, nothing is written and `written` is false. The open document is unchanged.")
|
||||
t("doc_reduce", "Reduce file size", "Write a smaller copy of the document to `path` with Acrobat's Reduce File Size choices: colour and grey images above 225 ppi downsampled to 150 ppi and JPEG-compressed (medium quality), black-and-white images averaged down to 300 ppi above 450 ppi and each stored as CCITT Group 4 (or 1-bit Flate, once resampled or packed from more bits) whenever that is smaller, thumbnails dropped, identical fonts and images merged, unused objects dropped, compressed object streams. If the copy wouldn't be smaller, nothing is written and `written` is false. Images past what one run may decode stay as they are, counted in images_refused; streams it only stores with Flate past that stay LZW, uncounted. The open document is unchanged.")
|
||||
.cmd("optimize.reduce")
|
||||
.with(schema(json!({ "doc": doc(), "path": { "type": "string" } }), &["doc", "path"])),
|
||||
t("doc_initial_view", "Initial view", "Read or change how the document opens (Document Properties ▸ Initial View) and its reading options: navigation (page, bookmarks, pages, attachments, layers), layout (default, single, continuous, two_up, two_up_continuous, two_up_cover, two_up_continuous_cover), magnification (default, actual, fit_page, fit_width, fit_height, fit_visible, or a percentage), page, window options (fit_window, center_window, full_screen, display_title), interface options (hide_menubar, hide_toolbar, hide_window_ui), language and binding (left, right). Only the given ones change; returns the result. Undoable.").with(schema(
|
||||
@@ -1452,7 +1460,7 @@ pub fn tools() -> Vec<ToolDef> {
|
||||
.with(schema(json!({ "doc": doc() }), &["doc"])),
|
||||
t("doc_open_revision", "Open a revision", "Open saved revision `revision` (1 = the oldest) of a document as a new, unsaved document, to see the file as it was then.")
|
||||
.with(schema(json!({ "doc": doc(), "revision": { "type": "integer", "minimum": 1 } }), &["doc", "revision"])),
|
||||
t("doc_optimize", "Optimize PDF", "Write an optimized copy to `path` (Acrobat's PDF Optimizer). preset: standard (default; Reduce File Size's choices) or mobile (images to 96 ppi above 144, JPEG high quality); the options below change it. compatibility: retain (default; keeps the document's version, or 1.5 when object streams are written), 1.4, 1.5, 1.6, 1.7 or 2.0. merge_fragments (default true) first puts a page picture drawn as many stacked image strips (as some PDF printers write it) back together into one image, so it can be resampled (merged_images, fragments_merged). color / gray: { downsample, ppi, above_ppi, compression: jpeg|zip|retain, quality 1–100 } (defaults: downsample to 150 ppi above 225, JPEG 60). mono: { downsample, ppi, above_ppi, compression: ccitt_g4|jbig2|retain } for black-and-white images and image masks (default: averaged down to 300 ppi above 450 ppi, counted in images_resampled; stored losslessly as CCITT Group 4 or JBIG2 (or 1-bit Flate, once resampled or packed from more bits) when that is smaller, Group 3 fax images, JBIG2 images, black-and-white RGB and indexed images using only palette entries 0 and 1 among them, counted in images_recompressed; retain resamples only, a CCITT image staying CCITT, a JBIG2 image JBIG2 and any other becoming Flate). Images are measured where pages draw them and replaced only when smaller. discard_*: thumbnails (default true), alternate_images (true), tags, print_settings; flate_unencoded (true); object_streams (default true; always off for 1.4); lzw_to_flate (true) decodes LZW streams and stores them with Flate instead, leaving any it cannot decode unchanged (lzw_streams counts the streams converted); remove_invalid_links and remove_unreferenced_dests (true); images and forms the pages list but never draw are always dropped (unused_xobjects). discard: Remove Hidden Information categories (metadata, attachments, comments, form-fields, hidden-text, hidden-layers, bookmarks, links-actions-scripts, private-data). Signed documents are refused. The open document is unchanged.")
|
||||
t("doc_optimize", "Optimize PDF", "Write an optimized copy to `path` (Acrobat's PDF Optimizer). preset: standard (default; Reduce File Size's choices) or mobile (images to 96 ppi above 144, JPEG high quality); the options below change it. compatibility: retain (default; keeps the document's version, or 1.5 when object streams are written), 1.4, 1.5, 1.6, 1.7 or 2.0. merge_fragments (default true) first puts a page picture drawn as many stacked image strips (as some PDF printers write it) back together into one image, so it can be resampled (merged_images, fragments_merged). color / gray: { downsample, ppi, above_ppi, compression: jpeg|zip|retain, quality 1–100 } (defaults: downsample to 150 ppi above 225, JPEG 60). mono: { downsample, ppi, above_ppi, compression: ccitt_g4|jbig2|retain } for black-and-white images and image masks (default: averaged down to 300 ppi above 450 ppi, counted in images_resampled; stored losslessly as CCITT Group 4 or JBIG2 (or 1-bit Flate, once resampled or packed from more bits) when that is smaller, Group 3 fax images, JBIG2 images, black-and-white RGB and indexed images using only palette entries 0 and 1 among them, counted in images_recompressed; retain resamples only, a CCITT image staying CCITT, a JBIG2 image JBIG2 and any other becoming Flate). Images past what one run may decode stay as they are, counted in images_refused; streams it only stores with Flate past that stay LZW, uncounted. Images are measured where pages draw them and replaced only when smaller. discard_*: thumbnails (default true), alternate_images (true), tags, print_settings; flate_unencoded (true); object_streams (default true; always off for 1.4); lzw_to_flate (true) decodes LZW streams and stores them with Flate instead, leaving any it cannot decode unchanged (lzw_streams counts the streams converted); remove_invalid_links and remove_unreferenced_dests (true); images and forms the pages list but never draw are always dropped (unused_xobjects). discard: Remove Hidden Information categories (metadata, attachments, comments, form-fields, hidden-text, hidden-layers, bookmarks, links-actions-scripts, private-data). Signed documents are refused. The open document is unchanged.")
|
||||
.cmd("optimize.advanced")
|
||||
.with(schema(
|
||||
json!({
|
||||
|
||||
@@ -2832,6 +2832,74 @@ fn headers_watermarks_and_backgrounds_through_tools() {
|
||||
assert!(matches!(refused, Err(ToolError::InvalidArgs(e)) if e.contains("Courier")));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn bates_numbers_continue_across_files_and_report_preflight_and_permission_failures() {
|
||||
let dir = workdir("bates-multi");
|
||||
let files = json!([
|
||||
{"input":"b.pdf","output":"b-numbered.pdf"},
|
||||
{"input":"a.pdf","output":"a-numbered.pdf"}
|
||||
]);
|
||||
let mut a = auto(&dir);
|
||||
let allocation = ok(&mut a, "doc_bates_multi", json!({"files":files,"start_number":50,"dry_run":true}));
|
||||
assert_eq!(allocation["files"][0]["first"], 50);
|
||||
assert_eq!(allocation["files"][0]["last"], 51);
|
||||
assert_eq!(allocation["files"][1]["first"], 52);
|
||||
assert_eq!(allocation["files"][1]["last"], 54);
|
||||
assert!(!dir.join("a-numbered.pdf").exists());
|
||||
|
||||
let applied = ok(&mut a, "doc_bates_multi", json!({"files":files,"start_number":17,"prefix":"CASE-"}));
|
||||
assert_eq!(applied["completed"], 2);
|
||||
let mut out = auto(&dir);
|
||||
let first = ok(&mut out, "doc_open", json!({"path":"a-numbered.pdf"}))["doc"].as_u64().unwrap();
|
||||
let second = ok(&mut out, "doc_open", json!({"path":"b-numbered.pdf"}))["doc"].as_u64().unwrap();
|
||||
assert!(page_text(&mut out, second)[0].contains("CASE-000017"));
|
||||
assert!(page_text(&mut out, first)[0].contains("CASE-000019"));
|
||||
|
||||
let overflow = err(&mut a, "doc_bates_multi", json!({"files":[{"input":"b.pdf","output":"overflow.pdf"}],"start_number":u64::MAX}));
|
||||
assert!(overflow.to_string().contains("overflows"));
|
||||
assert!(!dir.join("overflow.pdf").exists());
|
||||
// A range may end at u64::MAX itself.
|
||||
let at_max = ok(&mut a, "doc_bates_multi", json!({"files":[{"input":"b.pdf","output":"max.pdf"}],"start_number":u64::MAX - 1,"dry_run":true}));
|
||||
assert_eq!(at_max["files"][0]["last"], u64::MAX);
|
||||
for bad in
|
||||
[json!({"start_number":-3}), json!({"start_number":2.5}), json!({"start_number":"7"}), json!({"prefix":"CASE>>"}), json!({"suffix":"A>>B"})]
|
||||
{
|
||||
let mut args = json!({"files":[{"input":"b.pdf","output":"bad.pdf"}],"dry_run":true});
|
||||
args.as_object_mut().unwrap().extend(bad.as_object().unwrap().clone());
|
||||
assert!(a.call("doc_bates_multi", &args).is_err(), "{bad}");
|
||||
}
|
||||
|
||||
use pdfcraft_engine::{Changes, Edit, Protection, Session};
|
||||
let mut session = Session::new();
|
||||
let id = session.open("locked.pdf", None, std::sync::Arc::new(fixture(1)), None).unwrap();
|
||||
session
|
||||
.apply(
|
||||
id,
|
||||
Edit::Protect(Protection {
|
||||
open_password: Some("open".into()),
|
||||
permissions_password: Some("owner".into()),
|
||||
changes: Changes::None,
|
||||
..Default::default()
|
||||
}),
|
||||
)
|
||||
.unwrap();
|
||||
std::fs::write(dir.join("locked.pdf"), session.save_bytes(id).unwrap().as_ref()).unwrap();
|
||||
let result = ok(
|
||||
&mut a,
|
||||
"doc_bates_multi",
|
||||
json!({"files":[
|
||||
{"input":"b.pdf","output":"partial-numbered.pdf"},
|
||||
{"input":"locked.pdf","output":"locked-numbered.pdf","password":"open"}
|
||||
]}),
|
||||
);
|
||||
assert_eq!(result["completed"], 1);
|
||||
assert_eq!(result["failed"], 1);
|
||||
assert_eq!(result["files"][1]["first"], 3);
|
||||
assert!(result["files"][1]["error"].as_str().unwrap().contains("owner password"), "{result}");
|
||||
assert!(dir.join("partial-numbered.pdf").exists());
|
||||
assert!(!dir.join("locked-numbered.pdf").exists());
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn a_shrinking_header_and_footer_moves_the_page_content_out_of_their_way_through_tools() {
|
||||
let dir = workdir("hf-shrink");
|
||||
@@ -4670,12 +4738,23 @@ fn removing_hidden_information_through_tools() {
|
||||
assert_eq!(r["undo"], "Remove hidden information");
|
||||
assert_eq!(ok(&mut a, "comment_list", json!({ "doc": doc }))["count"], 0);
|
||||
assert!(count(&ok(&mut a, "doc_hidden_info", json!({ "doc": doc })), "metadata") >= 1, "only comments went");
|
||||
// With none left, removing them again says so, and Optimize discarding them still runs.
|
||||
let again = a.call("doc_remove_hidden", &json!({ "doc": doc, "categories": ["comments"] }));
|
||||
assert!(matches!(&again, Err(ToolError::Failed(m)) if m.starts_with("nothing to remove")), "{again:?}");
|
||||
let optimized = ok(&mut a, "doc_optimize", json!({ "doc": doc, "path": "optimized.pdf", "discard": ["comments", "bookmarks"] }));
|
||||
assert_eq!(optimized["discarded"], json!([]), "{optimized}");
|
||||
let r = ok(&mut a, "doc_remove_hidden", json!({ "doc": doc }));
|
||||
assert_eq!(r["undo"], "Sanitize document");
|
||||
ok(&mut a, "doc_save", json!({ "doc": doc, "path": "clean.pdf" }));
|
||||
let bytes = std::fs::read(dir.join("clean.pdf")).unwrap();
|
||||
assert!(!bytes.windows(11).any(|w| w == b"Secret plan"), "the old revision is gone");
|
||||
assert!(matches!(a.call("doc_remove_hidden", &json!({ "doc": doc, "categories": ["nonsense"] })), Err(ToolError::InvalidArgs(_))));
|
||||
// A document that can't be edited has no scan: the refusal says why, not that nothing is there.
|
||||
let junk = [vec![b'x'; 5000], std::fs::read(dir.join("a.pdf")).unwrap()].concat();
|
||||
std::fs::write(dir.join("junk.pdf"), junk).unwrap();
|
||||
let read_only = ok(&mut a, "doc_open", json!({ "path": "junk.pdf" }))["doc"].as_u64().unwrap();
|
||||
let refused = a.call("doc_remove_hidden", &json!({ "doc": read_only, "categories": ["comments"] }));
|
||||
assert!(matches!(&refused, Err(ToolError::Failed(m)) if m.contains("can't be edited")), "{refused:?}");
|
||||
}
|
||||
|
||||
/// A one-page PDF whose text "TOP SECRET" sits under an opaque black rectangle.
|
||||
@@ -6651,10 +6730,12 @@ fn optimizing_through_tools() {
|
||||
let reduced = ok(&mut a, "doc_reduce", json!({ "doc": doc, "path": "reduced.pdf" }));
|
||||
assert!(reduced["bytes_after"].as_u64().unwrap() < reduced["bytes_before"].as_u64().unwrap());
|
||||
assert_eq!(reduced["written"], true);
|
||||
assert_eq!(reduced["images_refused"], 0);
|
||||
assert_eq!(std::fs::metadata(dir.join("reduced.pdf")).unwrap().len(), reduced["bytes_after"].as_u64().unwrap());
|
||||
|
||||
// Target PDF 1.4 (disables object streams) and PDF 2.0 (with object_streams toggled off).
|
||||
let v14 = ok(&mut a, "doc_optimize", json!({ "doc": doc, "path": "v14.pdf", "compatibility": "1.4" }));
|
||||
assert_eq!(v14["images_refused"], 0);
|
||||
assert_eq!((v14["pdf_version"].as_str(), v14["object_streams"].as_bool()), (Some("1.4"), Some(false)), "{v14}");
|
||||
let v14_bytes = std::fs::read(dir.join("v14.pdf")).unwrap();
|
||||
assert!(v14_bytes.starts_with(b"%PDF-1.4\n") && !v14_bytes.windows(7).any(|w| w == b"/ObjStm"));
|
||||
@@ -7602,6 +7683,17 @@ fn exporting_to_word_html_and_rtf() {
|
||||
}
|
||||
let html = std::fs::read_to_string(dir.join("a.html")).unwrap();
|
||||
assert!(html.contains("Page 1") && html.contains("Page 3") && html.matches("<hr>").count() == 2, "{html}");
|
||||
ok(&mut a, "doc_export_office", json!({ "doc": doc, "path": "simple.html", "html_mode": "simple" }));
|
||||
let simple_html = std::fs::read_to_string(dir.join("simple.html")).unwrap();
|
||||
assert!(
|
||||
simple_html.contains("Page 1")
|
||||
&& !simple_html.contains("<style")
|
||||
&& !simple_html.contains("style=")
|
||||
&& !simple_html.contains("<span")
|
||||
&& !simple_html.contains("<div")
|
||||
);
|
||||
assert!(a.call("doc_export_office", &json!({ "doc": doc, "path": "bad.html", "html_mode": "compact" })).is_err());
|
||||
assert!(a.call("doc_export_office", &json!({ "doc": doc, "path": "bad.docx", "html_mode": "simple" })).is_err());
|
||||
assert!(std::fs::read(dir.join("a.docx")).unwrap().starts_with(b"PK"));
|
||||
assert!(std::fs::read(dir.join("a.pptx")).unwrap().starts_with(b"PK"));
|
||||
assert!(std::fs::read_to_string(dir.join("a.rtf")).unwrap().contains("Page 2"));
|
||||
@@ -10552,3 +10644,32 @@ fn mixed_script_tools_normalize_but_undo_restores_the_exact_mixture() {
|
||||
assert_eq!(page_text(&mut a, reopened)[0], plain);
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn multiline_fill_sign_engine_round_trip_preserves_lines_and_appearance() {
|
||||
let dir = workdir("fill-sign-multiline");
|
||||
let mut a = auto(&dir);
|
||||
let doc = ok(&mut a, "doc_open", json!({"path":"a.pdf"}))["doc"].as_u64().unwrap();
|
||||
let text = "\nAda\n\nLovelace\n";
|
||||
ok(&mut a, "fill_sign_add", json!({"doc":doc,"page":1,"type":"text","at":[20,20],"text":text}));
|
||||
let id = pdfcraft_engine::DocId(doc);
|
||||
let annot = &a.session().get(id).unwrap().info.annotations[0];
|
||||
assert_eq!(annot.contents.as_deref(), Some(text), "typewriter contents keep outer line breaks");
|
||||
assert!(annot.rect[3] - annot.rect[1] >= 66.0, "five text lines need their full height, including blank lines: {:?}", annot.rect);
|
||||
let pixels = a.render_pixels(doc, 1, 1.0).unwrap();
|
||||
// The fixture's page text is at y=150; only the typewriter draws at y=65..80.
|
||||
assert!(
|
||||
(65..80).any(|y| (20..80).any(|x| {
|
||||
let i = (y * pixels.0 as usize + x) * 4;
|
||||
pixels.2[i..i + 3].iter().all(|v| *v < 100)
|
||||
})),
|
||||
"the lower nonempty line appears inside its box"
|
||||
);
|
||||
let rendered = a.call("page_render", &json!({"doc":doc,"page":1,"dpi":72})).unwrap();
|
||||
ok(&mut a, "doc_save", json!({"doc":doc,"path":"multiline.pdf"}));
|
||||
let mut re = auto(&dir);
|
||||
let reopened = ok(&mut re, "doc_open", json!({"path":"multiline.pdf"}))["doc"].as_u64().unwrap();
|
||||
assert_eq!(re.session().get(pdfcraft_engine::DocId(reopened)).unwrap().info.annotations[0].contents.as_deref(), Some(text));
|
||||
assert_eq!(rendered, re.call("page_render", &json!({"doc":reopened,"page":1,"dpi":72})).unwrap(), "saved appearances are identical");
|
||||
std::fs::remove_dir_all(dir).unwrap();
|
||||
}
|
||||
@@ -730,11 +730,14 @@ impl Matrix {
|
||||
pub fn invert(&self) -> Option<Matrix> {
|
||||
let [a, b, c, d, e, f] = self.0;
|
||||
let det = a * d - b * c;
|
||||
if det.abs() < 1e-12 || !det.is_finite() {
|
||||
if det == 0.0 || !det.is_finite() || det.abs() <= 1e-12 * ((a * d).abs() + (b * c).abs()) {
|
||||
return None;
|
||||
}
|
||||
let (ia, ib, ic, id) = (d / det, -b / det, -c / det, a / det);
|
||||
Some(Matrix([ia, ib, ic, id, -(e * ia + f * ic), -(e * ib + f * id)]))
|
||||
let inverse = [ia, ib, ic, id, -(e * ia + f * ic), -(e * ib + f * id)];
|
||||
// A determinant that underflows toward zero can still pass the relative check above,
|
||||
// and dividing by it overflows: such a matrix has no usable inverse.
|
||||
inverse.iter().all(|v| v.is_finite()).then_some(Matrix(inverse))
|
||||
}
|
||||
|
||||
/// The bounding box of a rectangle `[x0 y0 x1 y1]` after this transform.
|
||||
|
||||
@@ -552,3 +552,17 @@ fn inline_images_end_where_the_renderer_ends_them() {
|
||||
assert_eq!((parsed.skipped, parsed.ambiguous_images), (0, 0), "{}", String::from_utf8_lossy(data));
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn invert_accepts_small_scale_and_rejects_singular() {
|
||||
let m = Matrix([1e-7, 0., 0., 1e-7, 0., 0.]);
|
||||
let inv = m.invert().expect("a uniform 1e-7 scale is invertible");
|
||||
let id = m.then(&inv).0;
|
||||
for (got, want) in id.iter().zip(Matrix::IDENTITY.0) {
|
||||
assert!((got - want).abs() < 1e-9, "{id:?}");
|
||||
}
|
||||
assert!(Matrix([1., 2., 2., 4., 0., 0.]).invert().is_none());
|
||||
assert!(Matrix([f64::NAN, 0., 0., 1., 0., 0.]).invert().is_none());
|
||||
// A subnormal scale passes the relative check but its inverse overflows (CodeRabbit on #5703).
|
||||
assert!(Matrix([1e-310, 0., 0., 1., 0., 0.]).invert().is_none());
|
||||
}
|
||||
@@ -93,5 +93,8 @@ recognisable in a diff and byte-stable when re-serialized.
|
||||
- Image codecs. `pdfcraft-filters` carries the non-image filters and CCITT fax and JBIG2 decoding
|
||||
(`Document::decoded_image`, a JBIG2 image's `/JBIG2Globals` within `MAX_JBIG2_GLOBALS`, 32 MiB,
|
||||
their filters undone once a document for the images that share them, up to 64 MiB kept, while
|
||||
their segments are decoded for every image);
|
||||
their segments are decoded for every image, and `ImageBudget` for an operation over many images,
|
||||
which share one allowance of decoding, filters, decoders and pixels alike, and are refused past
|
||||
it: `IMAGE_WORK`, 2^34 steps, or 2 to 5 minutes of JBIG2 and about 1,000 pages scanned at
|
||||
300 dpi, plus `IMAGE_WORK_PER_BYTE`, 2^13 steps for each byte of the file);
|
||||
DCT and JPX are still decoded through the bootstrap renderer (`core.image-filters`, M2.6).
|
||||
@@ -6,16 +6,218 @@ use pdfcraft_filters::FilterError;
|
||||
|
||||
use crate::{CosError, Document, ObjRef, Object, Stream};
|
||||
|
||||
/// The steps of decoding an operation over a document's images may take whatever the file's size.
|
||||
/// A step of JBIG2 decoding ([`hayro_jbig2::Image::decode_within`]) is about a pixel, and takes 6 to
|
||||
/// 16 ns, so this is 2 to 5 minutes, and about as long again for what an operation does with the
|
||||
/// pixels. A page scanned at 300 dpi takes about 17 million, 8.4 for its pixels and that again to
|
||||
/// decode them, so this alone reads about 1,000 of them. A byte into or out of a filter is a step
|
||||
/// too, and takes less: 3 ns at most, or up to 19 ns through a predictor on samples of a bit.
|
||||
const IMAGE_WORK: u64 = 1 << 34;
|
||||
/// The steps each byte of the file adds to [`IMAGE_WORK`], so that a long scan is read whole: such a
|
||||
/// page pays for itself with about 2 KB of the file, about the smallest a page of text is stored
|
||||
/// in, and a stream of any filter this reads can be decoded about 8 times at Flate's best, 1,032 to
|
||||
/// one. So what a hostile file can ask for grows with its length, by about 14 minutes for 10 MB.
|
||||
const IMAGE_WORK_PER_BYTE: u64 = 1 << 13;
|
||||
|
||||
/// Decoded bytes one page's content walk may produce in all: its `/Contents` streams and every
|
||||
/// form XObject it enters, each occurrence counted again.
|
||||
pub const MAX_PAGE_DECODED: usize = 256 << 20;
|
||||
/// Form XObjects one page's content walk may enter, each entry counted again.
|
||||
pub const MAX_PAGE_FORMS: usize = 50_000;
|
||||
|
||||
/// The steps a sample of a JPEG costs: a few bytes can hold a page of one grey, and decoding,
|
||||
/// resampling and storing it took about 20 to 45 ns a sample.
|
||||
const JPEG_WORK: u64 = 2;
|
||||
/// The steps a byte of a JPEG costs to read: its tables took 24 ns a byte before a size was known,
|
||||
/// and images can share one, so reading it again for each has to count.
|
||||
const JPEG_READ_WORK: u64 = 4;
|
||||
|
||||
/// A stream decode within a byte bound, with the bytes its filter stages decoded: the data or
|
||||
/// the error, each with that count.
|
||||
type Decoder = fn(&Stream, usize) -> Result<(Vec<u8>, usize), (FilterError, usize)>;
|
||||
|
||||
/// What one operation over a document's images may still spend decoding them: exporting them,
|
||||
/// optimizing them, and storing LZW streams with Flate as it does, clearing them for redaction.
|
||||
///
|
||||
/// An image has its own limit, which doesn't bound a file of thousands of images made to reach it:
|
||||
/// a few hundred bytes of JBIG2 can ask for seconds of decoding, 4 KB of Flate inside Flate for a
|
||||
/// gigabyte, and an image that shares `/JBIG2Globals` decodes them again. So images share this
|
||||
/// allowance, whatever they do with what they decode and whether or not it works, and past it they
|
||||
/// aren't decoded. A caller then treats them as it does an image it can't read, and
|
||||
/// [`ImageBudget::refused`] says how many there were.
|
||||
///
|
||||
/// An image also pays for its pixels once decoded, as what reads it goes through them one by one
|
||||
/// however few bytes coded them: blank rows of fax or Flate take almost none. It pays for no more
|
||||
/// than its data holds, a bit a pixel at least, so an image declaring a size its data doesn't fill
|
||||
/// costs what a smaller one would, not the run's allowance. A JPEG pays for its samples when
|
||||
/// it is decoded ([`ImageBudget::pay_jpeg`]), and is otherwise not charged, as JPEG 2000 isn't:
|
||||
/// their decoders don't run here.
|
||||
#[derive(Debug)]
|
||||
pub struct ImageBudget {
|
||||
work: u64,
|
||||
refused: usize,
|
||||
}
|
||||
|
||||
impl ImageBudget {
|
||||
/// The allowance for an operation on `doc`, which a longer file makes larger. The streams made
|
||||
/// or changed since it was opened count as the file's bytes do, so a document built in memory
|
||||
/// (combined, created, or given pages of scans) gets what it would once saved and opened again.
|
||||
pub fn new(doc: &Document) -> Self {
|
||||
let length = |n: usize| u64::try_from(n).unwrap_or(u64::MAX);
|
||||
let edited = doc
|
||||
.scan_objects_subset(doc.modified_objects())
|
||||
.filter_map(|(_, object)| match &*object.ok()? {
|
||||
Object::Stream(s) => Some(length(s.raw.len())),
|
||||
_ => None,
|
||||
})
|
||||
.fold(0u64, u64::saturating_add);
|
||||
let bytes = length(doc.bytes().len()).saturating_add(edited);
|
||||
Self::with_work(IMAGE_WORK.saturating_add(bytes.saturating_mul(IMAGE_WORK_PER_BYTE)))
|
||||
}
|
||||
|
||||
/// An allowance of `work` steps of decoding.
|
||||
pub fn with_work(work: u64) -> Self {
|
||||
Self { work, refused: 0 }
|
||||
}
|
||||
|
||||
/// The samples of image `s`, decoded and charged to the allowance: the one way to decode an
|
||||
/// image outside the renderer, so that an operation over many images can't decode them without
|
||||
/// one.
|
||||
///
|
||||
/// They go through its filters ([`Stream::decoded`]), or, for a CCITT fax or JBIG2 image (its
|
||||
/// last filter), through the filters before it and then [`pdfcraft_filters::decode_ccitt_within`]
|
||||
/// with its [`Document::fax_params`], or [`pdfcraft_filters::decode_jbig2_within`] with its
|
||||
/// `/JBIG2Globals`, as `CCITTFaxDecode` and `JBIG2Decode` give them (ISO 32000-2 §7.4.6,
|
||||
/// §7.4.7). Parameters given by reference count, for every filter
|
||||
/// ([`Document::with_direct_parms`]). A fax image's `/Columns` has to be its `/Width`, and a
|
||||
/// JBIG2 image's page its `/Width` × `/Height`: PdfCraft's renderer draws the whole page into
|
||||
/// the image. Up to its `/Height` rows are decoded, whatever a fax image's `/Rows` says; damaged
|
||||
/// fax data gives fewer, so a caller checks it has the rows it needs. Damaged JBIG2 data, and
|
||||
/// globals that can't be read (within [`MAX_JBIG2_GLOBALS`](crate::MAX_JBIG2_GLOBALS)), are an
|
||||
/// error.
|
||||
///
|
||||
/// No stage, the filters before a fax or JBIG2 decoder included, may produce more than `max`
|
||||
/// bytes, nor more than [`MAX_DECODED`](crate::MAX_DECODED). A JBIG2 image's `/JBIG2Globals`
|
||||
/// are another stream, shared between images, and are decoded within `MAX_JBIG2_GLOBALS`
|
||||
/// whatever `max` is. Each filter as it runs, the globals when they have to be read, and the fax
|
||||
/// or JBIG2 decoder spend from the allowance, and the image then pays for its pixels; with
|
||||
/// nothing left an image is refused before anything is read, its globals included.
|
||||
///
|
||||
/// ```
|
||||
/// # let doc = pdfcraft_cos::Document::new_empty();
|
||||
/// # let s = pdfcraft_cos::Stream::from_raw(pdfcraft_cos::Dict::new(), Vec::new());
|
||||
/// let samples = pdfcraft_cos::ImageBudget::new(&doc).decode(&doc, &s, 1 << 20);
|
||||
/// assert_eq!(samples.unwrap(), b"");
|
||||
/// ```
|
||||
///
|
||||
/// `Document` has no way of its own to decode an image:
|
||||
///
|
||||
/// ```compile_fail
|
||||
/// # let doc = pdfcraft_cos::Document::new_empty();
|
||||
/// # let s = pdfcraft_cos::Stream::from_raw(pdfcraft_cos::Dict::new(), Vec::new());
|
||||
/// let _ = doc.decoded_image(&s);
|
||||
/// ```
|
||||
///
|
||||
/// ```compile_fail
|
||||
/// # let doc = pdfcraft_cos::Document::new_empty();
|
||||
/// # let s = pdfcraft_cos::Stream::from_raw(pdfcraft_cos::Dict::new(), Vec::new());
|
||||
/// let _ = doc.decoded_image_within(&s, 1 << 20);
|
||||
/// ```
|
||||
pub fn decode(&mut self, doc: &Document, s: &Stream, max: usize) -> Result<Vec<u8>, CosError> {
|
||||
let decoded = doc.decoded_image_spending(s, max, &mut self.work);
|
||||
self.count_refused(s, &decoded);
|
||||
self.pay_size(s, decoded?)
|
||||
}
|
||||
|
||||
/// Image `s` through its filters alone, charged to the allowance: [`Stream::decoded_within`]
|
||||
/// with its `/DecodeParms` given by reference read too ([`Document::with_direct_parms`]), for an
|
||||
/// image that has no fax or JBIG2 decoder to go through.
|
||||
pub fn decode_filters(&mut self, doc: &Document, s: &Stream, max: usize) -> Result<Vec<u8>, CosError> {
|
||||
let decoded = doc.with_direct_parms(s).decoded_spending(max, &mut self.work);
|
||||
self.count_refused(s, &decoded);
|
||||
let decoded = decoded?;
|
||||
if s.filters().iter().all(|(f, _)| f.is_decodable()) { self.pay_size(s, decoded) } else { Ok(decoded) }
|
||||
}
|
||||
|
||||
/// `data` through `chain`, any corruption being an error ([`pdfcraft_filters::decode_within`]),
|
||||
/// for a stream a run rewrites rather than an image it reads, charged to the allowance.
|
||||
pub fn decode_chain(
|
||||
&mut self,
|
||||
chain: &[(pdfcraft_filters::Filter, pdfcraft_filters::Params)],
|
||||
data: &[u8],
|
||||
max: usize,
|
||||
) -> Result<Vec<u8>, FilterError> {
|
||||
pdfcraft_filters::decode_within(chain, data, max, &mut self.work)
|
||||
}
|
||||
|
||||
/// Pays `steps` of other work on decoded data, or spends all there is and says so.
|
||||
pub fn spend(&mut self, steps: u64) -> bool {
|
||||
let left = self.work.checked_sub(steps);
|
||||
self.work = left.unwrap_or(0);
|
||||
left.is_some()
|
||||
}
|
||||
|
||||
/// Pays for `pixels` a decode goes on to work through, or spends all there is, and the image
|
||||
/// is refused.
|
||||
pub fn pay_pixels(&mut self, pixels: u64) -> bool {
|
||||
let paid = self.spend(pixels);
|
||||
self.refused += usize::from(!paid);
|
||||
paid
|
||||
}
|
||||
|
||||
/// Pays for reading JPEG `data` and decoding its `samples`, as [`ImageBudget::pay_pixels`] does.
|
||||
/// A caller pays before its tables are parsed, which can be most of the file.
|
||||
pub fn pay_jpeg(&mut self, samples: u64, data: &[u8]) -> bool {
|
||||
let reading = (data.len() as u64).saturating_mul(JPEG_READ_WORK);
|
||||
self.pay_pixels(samples.saturating_mul(JPEG_WORK).saturating_add(reading))
|
||||
}
|
||||
|
||||
/// Pays for the pixels of image `s` that its `decoded` data holds, those of its `/Width` and
|
||||
/// `/Height` but no more than a bit of the data each, unless it is JBIG2, whose decoder pays for
|
||||
/// its page, or isn't decoded here. What can't be paid for refuses the image.
|
||||
fn pay_size(&mut self, s: &Stream, decoded: Vec<u8>) -> Result<Vec<u8>, CosError> {
|
||||
if !charged(s) || matches!(s.filters().last(), Some((pdfcraft_filters::Filter::Jbig2, _))) {
|
||||
return Ok(decoded);
|
||||
}
|
||||
let side = |key: &[u8]| s.dict.int(key).and_then(|v| u64::try_from(v).ok()).unwrap_or(0);
|
||||
let held = u64::try_from(decoded.len()).unwrap_or(u64::MAX).saturating_mul(8);
|
||||
if self.pay_pixels(side(b"Width").saturating_mul(side(b"Height")).min(held)) {
|
||||
Ok(decoded)
|
||||
} else {
|
||||
Err(CosError::Filter(FilterError::Spent.to_string()))
|
||||
}
|
||||
}
|
||||
|
||||
/// An image that failed with nothing left was refused, unless it has a filter that costs
|
||||
/// nothing here, which fails whatever is left.
|
||||
fn count_refused(&mut self, s: &Stream, decoded: &Result<Vec<u8>, CosError>) {
|
||||
if decoded.is_err() && self.work == 0 && charged(s) {
|
||||
self.refused += 1;
|
||||
}
|
||||
}
|
||||
|
||||
/// The decodes refused for lack of allowance: an image read twice over is counted twice.
|
||||
pub fn refused(&self) -> usize {
|
||||
self.refused
|
||||
}
|
||||
|
||||
/// The steps of decoding still allowed.
|
||||
pub fn work_left(&self) -> u64 {
|
||||
self.work
|
||||
}
|
||||
}
|
||||
|
||||
/// Whether `s` can be decoded here and so charged: general filters, a fax or JBIG2 decoder last at
|
||||
/// most. Those decoders anywhere else can't run.
|
||||
fn charged(s: &Stream) -> bool {
|
||||
use pdfcraft_filters::Filter;
|
||||
s.readable_filters().is_ok_and(|chain| {
|
||||
chain.split_last().is_none_or(|((last, _), before)| {
|
||||
(last.is_decodable() || matches!(last, Filter::Jbig2 | Filter::CcittFax)) && before.iter().all(|(f, _)| f.is_decodable())
|
||||
})
|
||||
})
|
||||
}
|
||||
|
||||
/// What one operation may still decode and enter across all the streams it reads.
|
||||
///
|
||||
/// [`MAX_DECODED`](crate::MAX_DECODED) bounds one decode. It does not bound a page whose
|
||||
@@ -143,6 +345,401 @@ impl DecodeBudget {
|
||||
}
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod image_tests {
|
||||
use super::*;
|
||||
use crate::Dict;
|
||||
|
||||
fn jbig2(parms: Option<Object>) -> Stream {
|
||||
let mut dict = Dict::new();
|
||||
dict.set(b"Width".to_vec(), Object::Int(16));
|
||||
dict.set(b"Height".to_vec(), Object::Int(2));
|
||||
dict.set(b"Filter".to_vec(), Object::name("JBIG2Decode"));
|
||||
if let Some(parms) = parms {
|
||||
dict.set(b"DecodeParms".to_vec(), parms);
|
||||
}
|
||||
Stream::from_raw(dict, pdfcraft_filters::encode_jbig2_generic(&[0xFF; 4], 16, 2).unwrap())
|
||||
}
|
||||
|
||||
/// Each image spends what it took from one allowance, and those past it are refused and
|
||||
/// counted, whatever their filters. What can't be decoded here costs nothing, and fails
|
||||
/// without being one of these.
|
||||
#[test]
|
||||
fn the_images_of_an_operation_share_its_allowance() {
|
||||
let doc = Document::new_empty();
|
||||
let image = jbig2(None);
|
||||
let mut budget = ImageBudget::with_work(u64::MAX);
|
||||
let samples = budget.decode(&doc, &image, 1 << 20).unwrap();
|
||||
let cost = u64::MAX - budget.work_left();
|
||||
assert!(cost > 0);
|
||||
let mut budget = ImageBudget::with_work(3 * cost);
|
||||
for left in [2, 1, 0] {
|
||||
assert_eq!(budget.decode(&doc, &image, 1 << 20).unwrap(), samples);
|
||||
assert_eq!(budget.work_left(), left * cost);
|
||||
}
|
||||
assert_eq!(budget.refused(), 0, "the allowance held exactly three");
|
||||
for refused in [1, 2] {
|
||||
assert!(budget.decode(&doc, &image, 1 << 20).is_err());
|
||||
assert_eq!(budget.refused(), refused);
|
||||
}
|
||||
assert!(budget.decode(&doc, &Stream::flate(Dict::new(), b"samples"), 1 << 20).is_err());
|
||||
assert!(budget.decode(&doc, &Stream::from_raw(Dict::new(), b"samples".to_vec()), 1 << 20).is_err());
|
||||
assert_eq!(budget.refused(), 4, "other images share it");
|
||||
for name in ["NoSuchFilter", "DCTDecode", "JPXDecode"] {
|
||||
let mut dict = Dict::new();
|
||||
dict.set(b"Filter".to_vec(), Object::name(name));
|
||||
assert!(budget.decode(&doc, &Stream::from_raw(dict, b"data".to_vec()), 1 << 20).is_err());
|
||||
assert_eq!(budget.refused(), 4, "{name} isn't one of these");
|
||||
}
|
||||
let mut dict = Dict::new();
|
||||
dict.set(b"Filter".to_vec(), Object::Int(5));
|
||||
assert!(budget.decode(&doc, &Stream::from_raw(dict, b"data".to_vec()), 1 << 20).is_err());
|
||||
assert_eq!(budget.refused(), 4, "a /Filter that can't be read isn't either");
|
||||
}
|
||||
|
||||
/// What a file of images each inflating a megabyte asks for: 4 KB of Flate inside Flate can ask
|
||||
/// for a gigabyte, and these aren't JBIG2, so without the allowance nothing would stop them.
|
||||
#[test]
|
||||
fn filter_bombs_stop_at_the_allowance() {
|
||||
let doc = Document::new_empty();
|
||||
let samples = vec![0; 1 << 20];
|
||||
let inner = pdfcraft_filters::encode_flate(&samples);
|
||||
let mut dict = Dict::new();
|
||||
dict.set(b"Filter".to_vec(), Object::Array(vec![Object::name("FlateDecode"), Object::name("FlateDecode")]));
|
||||
let bomb = Stream::from_raw(dict, pdfcraft_filters::encode_flate(&inner));
|
||||
let cost = (bomb.raw.len() + inner.len() + samples.len()) as u64;
|
||||
let mut budget = ImageBudget::with_work(2 * cost + 1);
|
||||
for left in [cost + 1, 1] {
|
||||
assert_eq!(budget.decode(&doc, &bomb, 1 << 20).unwrap(), samples);
|
||||
assert_eq!(budget.work_left(), left);
|
||||
}
|
||||
assert!(budget.decode(&doc, &bomb, 1 << 20).is_err());
|
||||
assert_eq!((budget.work_left(), budget.refused()), (0, 1), "the first it can't pay for ends it");
|
||||
}
|
||||
|
||||
/// Filters in front of a JBIG2 decoder pay as they run, on top of what the decoder takes, and
|
||||
/// one that fails has still paid: nothing about the JBIG2 data is known by then, and each image
|
||||
/// of a file can do this.
|
||||
#[test]
|
||||
fn filters_in_front_of_jbig2_pay_whether_or_not_they_work() {
|
||||
let doc = Document::new_empty();
|
||||
let alone = jbig2(None);
|
||||
let mut budget = ImageBudget::with_work(u64::MAX);
|
||||
let samples = budget.decode(&doc, &alone, 1 << 20).unwrap();
|
||||
let decoding = u64::MAX - budget.work_left();
|
||||
let behind = |raw: Vec<u8>| {
|
||||
let mut dict = alone.dict.clone();
|
||||
dict.set(b"Filter".to_vec(), Object::Array(vec![Object::name("FlateDecode"), Object::name("JBIG2Decode")]));
|
||||
Stream::from_raw(dict, raw)
|
||||
};
|
||||
|
||||
let image = behind(pdfcraft_filters::encode_flate(&alone.raw));
|
||||
let mut budget = ImageBudget::with_work(u64::MAX);
|
||||
assert_eq!(budget.decode(&doc, &image, 1 << 20).unwrap(), samples);
|
||||
assert_eq!(u64::MAX - budget.work_left(), decoding + (image.raw.len() + alone.raw.len()) as u64);
|
||||
|
||||
// Past this image's limit: an error, with what finding out took paid and the rest left.
|
||||
let bomb = behind(pdfcraft_filters::encode_flate(&vec![0; 1 << 16]));
|
||||
let mut budget = ImageBudget::with_work(u64::MAX);
|
||||
assert!(budget.decode(&doc, &bomb, 1000).is_err());
|
||||
assert_eq!(u64::MAX - budget.work_left(), bomb.raw.len() as u64 + 1000);
|
||||
assert_eq!(budget.refused(), 0, "that image's limit isn't the run's");
|
||||
|
||||
// A small allowance is a limit too: it stops there, and the image is refused.
|
||||
let mut budget = ImageBudget::with_work(bomb.raw.len() as u64 + 10);
|
||||
assert!(budget.decode(&doc, &bomb, 1 << 20).is_err());
|
||||
assert_eq!((budget.work_left(), budget.refused()), (0, 1));
|
||||
}
|
||||
|
||||
/// Globals that are read again for every image pay every time, and fail having paid. Kept
|
||||
/// ones have no filters left to undo, so they pay for being read and nothing more.
|
||||
#[test]
|
||||
fn globals_pay_for_their_filters_each_time_they_are_decoded() {
|
||||
let skipped = [0, 0, 0, 0, 0x3E, 0, 0, 0, 0, 0, 4, 0, 0, 0, 1];
|
||||
let raw = pdfcraft_filters::encode_flate(&skipped);
|
||||
let stream = |doc: &Document, r: ObjRef| match &*doc.get(r) {
|
||||
Object::Stream(s) => s.clone(),
|
||||
_ => panic!("not a stream"),
|
||||
};
|
||||
let spent = |doc: &Document, s: &Stream| {
|
||||
let mut budget = ImageBudget::with_work(u64::MAX);
|
||||
budget.decode(doc, s, 1 << 20).unwrap();
|
||||
u64::MAX - budget.work_left()
|
||||
};
|
||||
let mut doc = Document::new_empty();
|
||||
let mut dict = Dict::new();
|
||||
dict.set(b"Filter".to_vec(), Object::name("FlateDecode"));
|
||||
let globals = doc.add(Object::Stream(Stream::from_raw(dict, raw.clone())));
|
||||
let mut parms = Dict::new();
|
||||
parms.set(b"JBIG2Globals".to_vec(), Object::Ref(globals));
|
||||
let image = doc.add(Object::Stream(jbig2(Some(Object::Dict(parms)))));
|
||||
let root = doc.root().unwrap();
|
||||
doc.update_dict(root, |c| c.set(b"Image".to_vec(), Object::Ref(image))).unwrap();
|
||||
|
||||
// Added in memory, so not kept: the filters are undone for each read.
|
||||
let s = stream(&doc, image);
|
||||
let first = spent(&doc, &s);
|
||||
assert_eq!(spent(&doc, &s), first, "not kept, so paid for again");
|
||||
|
||||
// Read from a file, so kept: the second read has no filters to undo.
|
||||
let file = crate::write_full(&doc, &crate::SaveOptions::default()).unwrap();
|
||||
let doc = Document::open(std::sync::Arc::new(file)).unwrap();
|
||||
let image = doc.get(doc.root().unwrap()).as_dict().unwrap().reference(b"Image").unwrap();
|
||||
let s = stream(&doc, image);
|
||||
let filters = (raw.len() + skipped.len()) as u64;
|
||||
assert_eq!(spent(&doc, &s), first, "the first read undoes them");
|
||||
assert_eq!(spent(&doc, &s), first - filters, "kept");
|
||||
|
||||
// Globals that fail pay too, with the image not refused: these go past their own limit.
|
||||
let over = pdfcraft_filters::encode_flate(&vec![0; crate::MAX_JBIG2_GLOBALS + 1]);
|
||||
let mut doc = Document::new_empty();
|
||||
let mut dict = Dict::new();
|
||||
dict.set(b"Filter".to_vec(), Object::name("FlateDecode"));
|
||||
let globals = doc.add(Object::Stream(Stream::from_raw(dict, over.clone())));
|
||||
let mut parms = Dict::new();
|
||||
parms.set(b"JBIG2Globals".to_vec(), Object::Ref(globals));
|
||||
let image = jbig2(Some(Object::Dict(parms)));
|
||||
let mut budget = ImageBudget::with_work(u64::MAX);
|
||||
assert!(budget.decode(&doc, &image, 1 << 20).unwrap_err().to_string().contains("globals"));
|
||||
assert_eq!(u64::MAX - budget.work_left(), (over.len() + crate::MAX_JBIG2_GLOBALS) as u64);
|
||||
assert_eq!(budget.refused(), 0);
|
||||
}
|
||||
|
||||
/// A fax image pays for what comes before its decoder and for the rows it asks for, and past
|
||||
/// the allowance it is refused like any other.
|
||||
#[test]
|
||||
fn fax_images_share_the_allowance() {
|
||||
let doc = Document::new_empty();
|
||||
let (w, h) = (4096u32, 64u32);
|
||||
let coded = pdfcraft_filters::encode_g4(&vec![0xFF; 512 * h as usize], w, h).unwrap();
|
||||
let mut parms = Dict::new();
|
||||
parms.set(b"K".to_vec(), Object::Int(-1));
|
||||
parms.set(b"Columns".to_vec(), Object::Int(i64::from(w)));
|
||||
let mut dict = Dict::new();
|
||||
dict.set(b"Width".to_vec(), Object::Int(i64::from(w)));
|
||||
dict.set(b"Height".to_vec(), Object::Int(i64::from(h)));
|
||||
dict.set(b"Filter".to_vec(), Object::Array(vec![Object::name("FlateDecode"), Object::name("CCITTFaxDecode")]));
|
||||
dict.set(b"DecodeParms".to_vec(), Object::Array(vec![Object::Null, Object::Dict(parms)]));
|
||||
let image = Stream::from_raw(dict, pdfcraft_filters::encode_flate(&coded));
|
||||
let pixels = u64::from(w) * u64::from(h);
|
||||
let cost = (image.raw.len() + coded.len() + 4 * coded.len() + 512 * h as usize) as u64 + pixels;
|
||||
let mut budget = ImageBudget::with_work(cost);
|
||||
assert_eq!(budget.decode(&doc, &image, 1 << 20).unwrap().len(), 512 * h as usize);
|
||||
assert_eq!(budget.work_left(), 0, "exactly that");
|
||||
assert!(budget.decode(&doc, &image, 1 << 20).is_err());
|
||||
assert_eq!(budget.refused(), 1);
|
||||
}
|
||||
|
||||
/// An image pays for its pixels however few bytes hold them, or a blank page of fax or Flate
|
||||
/// would cost a run a second for a few bytes' worth of allowance; a JBIG2 image doesn't pay
|
||||
/// twice, and one this doesn't decode pays nothing. Past what is left it isn't read.
|
||||
#[test]
|
||||
fn an_image_pays_for_its_pixels() {
|
||||
let doc = Document::new_empty();
|
||||
let blank = |filter: Option<&str>, data: Vec<u8>| {
|
||||
let mut dict = Dict::new();
|
||||
dict.set(b"Width".to_vec(), Object::Int(4096));
|
||||
dict.set(b"Height".to_vec(), Object::Int(1024));
|
||||
if let Some(filter) = filter {
|
||||
dict.set(b"Filter".to_vec(), Object::name(filter));
|
||||
}
|
||||
Stream::from_raw(dict, data)
|
||||
};
|
||||
let rows = vec![0xFFu8; 512 * 1024];
|
||||
let flate = blank(Some("FlateDecode"), pdfcraft_filters::encode_flate(&rows));
|
||||
let cost = (flate.raw.len() + rows.len()) as u64 + 4096 * 1024;
|
||||
let mut budget = ImageBudget::with_work(cost);
|
||||
assert_eq!(budget.decode(&doc, &flate, 1 << 24).unwrap(), rows);
|
||||
assert_eq!((budget.work_left(), budget.refused()), (0, 0), "exactly that");
|
||||
// Its filters alone pay the same.
|
||||
let mut budget = ImageBudget::with_work(cost);
|
||||
assert_eq!(budget.decode_filters(&doc, &flate, 1 << 24).unwrap(), rows);
|
||||
assert_eq!(budget.work_left(), 0);
|
||||
// Short of its pixels it is refused, having paid for its filters.
|
||||
let mut budget = ImageBudget::with_work(4096 * 1024 - 1);
|
||||
assert!(budget.decode(&doc, &flate, 1 << 24).unwrap_err().to_string().contains("more image decoding than"));
|
||||
assert_eq!((budget.work_left(), budget.refused()), (0, 1));
|
||||
let mut budget = ImageBudget::with_work(4096 * 1024 - 1);
|
||||
assert!(budget.decode_filters(&doc, &flate, 1 << 24).is_err());
|
||||
assert_eq!((budget.work_left(), budget.refused()), (0, 1));
|
||||
// What isn't decoded here pays for nothing, and fails as it would.
|
||||
let mut budget = ImageBudget::with_work(10);
|
||||
assert!(budget.decode(&doc, &blank(Some("DCTDecode"), b"data".to_vec()), 1 << 24).is_err());
|
||||
assert_eq!((budget.work_left(), budget.refused()), (10, 0));
|
||||
// Unfiltered data pays too, and a size that isn't one is no size.
|
||||
let mut budget = ImageBudget::with_work(u64::MAX);
|
||||
budget.decode(&doc, &blank(None, rows.clone()), 1 << 24).unwrap();
|
||||
assert_eq!(u64::MAX - budget.work_left(), rows.len() as u64 + 4096 * 1024);
|
||||
let mut odd = Dict::new();
|
||||
odd.set(b"Width".to_vec(), Object::Int(-4));
|
||||
odd.set(b"Height".to_vec(), Object::Int(9));
|
||||
let mut budget = ImageBudget::with_work(u64::MAX);
|
||||
budget.decode(&doc, &Stream::from_raw(odd, vec![1, 2]), 1 << 24).unwrap();
|
||||
assert_eq!(u64::MAX - budget.work_left(), 2);
|
||||
// A JPEG pays twice over for each sample, and four times for each byte it is read from.
|
||||
let mut budget = ImageBudget::with_work(30);
|
||||
assert!(budget.pay_jpeg(9, b"ab"));
|
||||
assert_eq!((budget.work_left(), budget.refused()), (4, 0));
|
||||
assert!(!budget.pay_jpeg(0, b"ab"));
|
||||
assert_eq!((budget.work_left(), budget.refused()), (0, 1));
|
||||
}
|
||||
|
||||
/// An image pays for the pixels its data holds, not those its size declares: one claiming
|
||||
/// 131072 by 131072 pixels with a few bytes of Flate costs what those bytes give, and the
|
||||
/// images after it are decoded as they would be without it.
|
||||
#[test]
|
||||
fn an_image_pays_for_no_more_pixels_than_its_data_holds() {
|
||||
let doc = Document::new_empty();
|
||||
let sized = |side: i64, data: &[u8]| {
|
||||
let mut dict = Dict::new();
|
||||
dict.set(b"Width".to_vec(), Object::Int(side));
|
||||
dict.set(b"Height".to_vec(), Object::Int(side));
|
||||
Stream::flate(dict, data)
|
||||
};
|
||||
let claims = sized(131_072, &[0; 16]);
|
||||
let image = sized(64, &[7; 64 * 64]);
|
||||
let cost = |s: &Stream| {
|
||||
let mut budget = ImageBudget::with_work(u64::MAX);
|
||||
budget.decode(&doc, s, 1 << 24).unwrap();
|
||||
u64::MAX - budget.work_left()
|
||||
};
|
||||
assert_eq!(cost(&claims), (claims.raw.len() + 16 + 16 * 8) as u64, "its bytes, and a pixel a bit of them");
|
||||
assert_eq!(cost(&image), (image.raw.len() + 64 * 64) as u64 + 64 * 64, "its bytes, and its pixels");
|
||||
for decode in [ImageBudget::decode, ImageBudget::decode_filters] {
|
||||
let mut budget = ImageBudget::with_work(cost(&claims) + cost(&image));
|
||||
assert_eq!(decode(&mut budget, &doc, &claims, 1 << 24).unwrap(), [0; 16]);
|
||||
assert_eq!(decode(&mut budget, &doc, &image, 1 << 24).unwrap(), [7; 64 * 64], "the image after it is decoded");
|
||||
assert_eq!((budget.work_left(), budget.refused()), (0, 0));
|
||||
}
|
||||
}
|
||||
|
||||
/// A stream a run rewrites is read strictly and charged, and what the caller does with it after
|
||||
/// comes out of the same allowance: what can't be paid for spends all of it.
|
||||
#[test]
|
||||
fn a_rewritten_stream_shares_the_allowance() {
|
||||
use pdfcraft_filters::{Filter, FilterError, Params};
|
||||
let samples = vec![7u8; 1000];
|
||||
let raw = pdfcraft_filters::encode_flate(&samples);
|
||||
let chain = [(Filter::Flate, Params::default())];
|
||||
let cost = (raw.len() + samples.len()) as u64;
|
||||
let mut budget = ImageBudget::with_work(cost + 10);
|
||||
assert_eq!(budget.decode_chain(&chain, &raw, 1 << 20).unwrap(), samples);
|
||||
assert_eq!(budget.work_left(), 10);
|
||||
assert!(budget.spend(4));
|
||||
assert_eq!(budget.work_left(), 6);
|
||||
assert!(budget.spend(6), "exactly what is left");
|
||||
assert_eq!(budget.work_left(), 0);
|
||||
assert!(budget.spend(0));
|
||||
let mut budget = ImageBudget::with_work(5);
|
||||
assert!(!budget.spend(6));
|
||||
assert_eq!(budget.work_left(), 0, "spends all of it");
|
||||
assert!(matches!(budget.decode_chain(&chain, &raw, 1 << 20), Err(FilterError::Spent)));
|
||||
let cut = raw.get(..raw.len() / 2).unwrap();
|
||||
assert!(matches!(ImageBudget::with_work(u64::MAX).decode_chain(&chain, cut, 1 << 20), Err(FilterError::Corrupt { .. })), "strictly");
|
||||
}
|
||||
|
||||
/// An image read through its filters alone reads parameters given by reference, is charged, and
|
||||
/// is refused like the others. It isn't given to a decoder.
|
||||
#[test]
|
||||
fn filters_alone_are_charged_too() {
|
||||
let mut doc = Document::new_empty();
|
||||
let p = pdfcraft_filters::Params { predictor: 12, columns: 4, ..pdfcraft_filters::Params::default() };
|
||||
let rows = vec![7u8; 400];
|
||||
let mut parms = Dict::new();
|
||||
parms.set(b"Predictor".to_vec(), Object::Int(12));
|
||||
parms.set(b"Columns".to_vec(), Object::Int(4));
|
||||
let parms = doc.add(Object::Dict(parms));
|
||||
let mut dict = Dict::new();
|
||||
dict.set(b"Filter".to_vec(), Object::name("FlateDecode"));
|
||||
dict.set(b"DecodeParms".to_vec(), Object::Ref(parms));
|
||||
let raw = pdfcraft_filters::encode(&pdfcraft_filters::Filter::Flate, &p, &rows).unwrap();
|
||||
let image = Stream::from_raw(dict, raw);
|
||||
let mut budget = ImageBudget::with_work(u64::MAX);
|
||||
assert_eq!(budget.decode_filters(&doc, &image, 1 << 20).unwrap(), rows);
|
||||
let cost = u64::MAX - budget.work_left();
|
||||
// The tag byte of each of its 100 rows counts, which the predictor takes off.
|
||||
assert_eq!(cost, (image.raw.len() + rows.len() + 100) as u64);
|
||||
let mut budget = ImageBudget::with_work(cost - 1);
|
||||
assert!(budget.decode_filters(&doc, &image, 1 << 20).is_err());
|
||||
assert_eq!((budget.work_left(), budget.refused()), (0, 1));
|
||||
let mut budget = ImageBudget::with_work(u64::MAX);
|
||||
assert!(budget.decode_filters(&doc, &jbig2(None), 1 << 20).is_err());
|
||||
assert_eq!(budget.work_left(), u64::MAX, "no decoder here, so nothing was read");
|
||||
// Nor for a fax image, nor for a decoder that isn't last, however large they say they are.
|
||||
for chain in [vec!["CCITTFaxDecode"], vec!["CCITTFaxDecode", "FlateDecode"], vec!["JBIG2Decode", "FlateDecode"]] {
|
||||
let mut dict = Dict::new();
|
||||
dict.set(b"Width".to_vec(), Object::Int(1000));
|
||||
dict.set(b"Height".to_vec(), Object::Int(1000));
|
||||
dict.set(b"Filter".to_vec(), Object::Array(chain.iter().map(|f| Object::name(f)).collect()));
|
||||
let image = Stream::from_raw(dict, b"data".to_vec());
|
||||
let mut budget = ImageBudget::with_work(u64::MAX);
|
||||
assert!(budget.decode_filters(&doc, &image, 1 << 20).is_err());
|
||||
assert_eq!(budget.work_left(), u64::MAX, "{chain:?}");
|
||||
}
|
||||
// Through `decode` a decoder that isn't last pays nothing either; one that is does.
|
||||
let mut dict = Dict::new();
|
||||
dict.set(b"Width".to_vec(), Object::Int(1000));
|
||||
dict.set(b"Height".to_vec(), Object::Int(1000));
|
||||
dict.set(b"Filter".to_vec(), Object::Array(vec![Object::name("JBIG2Decode"), Object::name("FlateDecode")]));
|
||||
let mut budget = ImageBudget::with_work(u64::MAX);
|
||||
assert!(budget.decode(&doc, &Stream::from_raw(dict, b"data".to_vec()), 1 << 20).is_err());
|
||||
assert_eq!(budget.work_left(), u64::MAX);
|
||||
}
|
||||
|
||||
/// The images of a file share its globals, so an image refused doesn't read them: this one's
|
||||
/// can't be read, which is how to tell.
|
||||
#[test]
|
||||
fn an_image_past_the_allowance_does_not_read_its_globals() {
|
||||
let mut doc = Document::new_empty();
|
||||
let mut unreadable = Dict::new();
|
||||
unreadable.set(b"Filter".to_vec(), Object::name("NoSuchFilter"));
|
||||
let globals = doc.add(Object::Stream(Stream::from_raw(unreadable, b"data".to_vec())));
|
||||
let mut parms = Dict::new();
|
||||
parms.set(b"JBIG2Globals".to_vec(), Object::Ref(globals));
|
||||
let image = jbig2(Some(Object::Dict(parms)));
|
||||
let read = ImageBudget::with_work(u64::MAX).decode(&doc, &image, 1 << 20).unwrap_err().to_string();
|
||||
assert!(read.contains("globals"), "{read}");
|
||||
let refused = ImageBudget::with_work(0).decode(&doc, &image, 1 << 20).unwrap_err().to_string();
|
||||
assert!(refused.contains("more image decoding than"), "{refused}");
|
||||
}
|
||||
|
||||
/// A longer file gets more, by its length, and an empty one the fixed part.
|
||||
#[test]
|
||||
fn a_longer_file_allows_more_decoding() {
|
||||
assert_eq!(ImageBudget::new(&Document::new_empty()).work_left(), IMAGE_WORK);
|
||||
let pdf = b"%PDF-1.7\n1 0 obj << /Type /Catalog >> endobj\ntrailer << /Root 1 0 R >>\n%%EOF".to_vec();
|
||||
let len = pdf.len() as u64;
|
||||
let doc = Document::open(std::sync::Arc::new(pdf)).unwrap();
|
||||
assert_eq!(ImageBudget::new(&doc).work_left(), IMAGE_WORK + len * IMAGE_WORK_PER_BYTE);
|
||||
}
|
||||
|
||||
/// A document made in memory, as Combine, Create and inserted scans make one, gets for the
|
||||
/// streams it was given what it would get for them once saved: what isn't a stream adds nothing.
|
||||
#[test]
|
||||
fn streams_made_in_memory_allow_more_decoding_too() {
|
||||
let mut doc = Document::new_empty();
|
||||
doc.add(Object::Stream(Stream::from_raw(Dict::new(), vec![0; 3000])));
|
||||
doc.add(Object::Dict(Dict::new()));
|
||||
doc.add(Object::Stream(Stream::flate(Dict::new(), &[1; 100])));
|
||||
let flate = pdfcraft_filters::encode_flate(&[1; 100]).len() as u64;
|
||||
assert_eq!(ImageBudget::new(&doc).work_left(), IMAGE_WORK + (3000 + flate) * IMAGE_WORK_PER_BYTE);
|
||||
// A stream of an opened file changed in memory counts with the file.
|
||||
let pdf = b"%PDF-1.7\n1 0 obj << /Type /Catalog >> endobj\ntrailer << /Root 1 0 R >>\n%%EOF".to_vec();
|
||||
let len = pdf.len() as u64;
|
||||
let mut doc = Document::open(std::sync::Arc::new(pdf)).unwrap();
|
||||
doc.add(Object::Stream(Stream::from_raw(Dict::new(), vec![0; 500])));
|
||||
assert_eq!(ImageBudget::new(&doc).work_left(), IMAGE_WORK + (len + 500) * IMAGE_WORK_PER_BYTE);
|
||||
}
|
||||
|
||||
// What the constants' comments promise, for a page scanned at 300 dpi: about 1,000 of them
|
||||
// whatever the file's size, and a page paying for itself with 2 KB of the file.
|
||||
const PAGE: u64 = 17_000_000;
|
||||
const _: () = assert!(IMAGE_WORK >= 1_000 * PAGE);
|
||||
const _: () = assert!(IMAGE_WORK_PER_BYTE * 2_100 >= PAGE);
|
||||
// And that a stream can be decoded about 8 times at Flate's best, 1,032 to one, and the byte in.
|
||||
const _: () = assert!(IMAGE_WORK_PER_BYTE >= 7 * 1_033);
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::*;
|
||||
@@ -198,6 +795,21 @@ mod tests {
|
||||
assert_eq!(budget.remaining(), (10 << 20) - partial);
|
||||
}
|
||||
|
||||
/// A stream that fails its reading as zlib, and then as raw deflate after decoding all of it,
|
||||
/// gives nothing back, and each reference still pays for what it decoded.
|
||||
#[test]
|
||||
fn a_decode_that_gives_nothing_back_still_pays() {
|
||||
let mut data = vec![0x78, 0x01, 0x06, 0xFE, 0xF9];
|
||||
data.extend(vec![0u8; 0x0601]);
|
||||
data.push(0x07);
|
||||
let mut dict = Dict::new();
|
||||
dict.set(b"Filter".to_vec(), Object::name("FlateDecode"));
|
||||
let stream = Stream::from_raw(dict, data);
|
||||
let mut budget = DecodeBudget::new(10 * 0x0601, 1);
|
||||
assert!(budget.decode(&stream).unwrap().is_empty());
|
||||
assert_eq!(budget.remaining(), 9 * 0x0601);
|
||||
}
|
||||
|
||||
/// A chain whose later stage shrinks the data pays for every stage's output: a Flate stage
|
||||
/// that inflates to hex text, which ASCIIHex then halves, charges both.
|
||||
#[test]
|
||||
|
||||
@@ -27,7 +27,7 @@ pub(crate) use state::ObjectReader;
|
||||
use state::{ObjStm, Slot};
|
||||
pub use state::{ReadState, SourceIdentity};
|
||||
#[cfg(test)]
|
||||
use state::{SECTION_READS, objstm_member, owned_bytes};
|
||||
use state::{SECTION_READS, held_bytes, objstm_member};
|
||||
use xref::XrefIndex;
|
||||
pub use xref::{Revision, XrefEntry};
|
||||
|
||||
@@ -47,7 +47,7 @@ pub struct Document {
|
||||
/// `fill_xref_gaps`.
|
||||
located: Arc<BTreeMap<u32, (u64, u16)>>,
|
||||
repair_log: Arc<Vec<String>>,
|
||||
cache: Arc<Mutex<HashMap<u32, Arc<Object>>>>,
|
||||
cache: Arc<Mutex<state::ObjectCache>>,
|
||||
objstms: Arc<Mutex<HashMap<u32, Arc<ObjStm>>>>,
|
||||
/// What `/JBIG2Globals` streams of the file decode to, by object number: the images of a scan
|
||||
/// share them, and each would otherwise decode them again (see `Document::jbig2_globals`).
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
use super::reader::find;
|
||||
use super::state::{LENGTHS, LoadGuard, ObjStm, ObjectReader, ReadState, Slot, SourceIdentity, objstm_member, owned_bytes};
|
||||
use super::state::{LENGTHS, LoadGuard, ObjStm, ObjectReader, ReadState, Slot, SourceIdentity, held_bytes, objstm_member};
|
||||
use super::xref::{Revision, XrefEntry};
|
||||
use super::{
|
||||
Arc, CosError, Cow, Dict, Document, Lexer, MAX_DECODED, MAX_JBIG2_GLOBALS, ObjRef, Object, Stream, is_whitespace, parse_indirect_shared,
|
||||
@@ -274,34 +274,32 @@ impl Document {
|
||||
.unwrap_or_default()
|
||||
}
|
||||
|
||||
/// The samples of image `s`, decoded: through its filters ([`Stream::decoded`]), or, for a
|
||||
/// CCITT fax or JBIG2 image (its last filter), through the filters before it and then
|
||||
/// [`pdfcraft_filters::decode_ccitt`] with its [`Document::fax_params`], or
|
||||
/// [`pdfcraft_filters::decode_jbig2`] with its `/JBIG2Globals`, as `CCITTFaxDecode` and
|
||||
/// `JBIG2Decode` give them (ISO 32000-2 §7.4.6, §7.4.7). Parameters given by reference count,
|
||||
/// for every filter ([`Document::with_direct_parms`]). A fax image's `/Columns` has to be its
|
||||
/// `/Width`, and a JBIG2 image's page its `/Width` × `/Height`: PdfCraft's renderer draws the
|
||||
/// whole page into the image. Up to its `/Height` rows are decoded, whatever a fax image's `/Rows` says,
|
||||
/// within [`MAX_DECODED`] bytes; damaged fax data gives fewer, so a caller checks it has the
|
||||
/// rows it needs. Damaged JBIG2 data, and globals that can't be read (within
|
||||
/// [`MAX_JBIG2_GLOBALS`]), are an error.
|
||||
pub fn decoded_image(&self, s: &Stream) -> Result<Vec<u8>, CosError> {
|
||||
/// [`Document::decoded_image_spending`] with no limit on the work, for tests of what an image
|
||||
/// decodes to: everything else decodes images through an [`ImageBudget`](crate::ImageBudget).
|
||||
#[cfg(test)]
|
||||
pub(crate) fn decoded_image(&self, s: &Stream) -> Result<Vec<u8>, CosError> {
|
||||
self.decoded_image_within(s, MAX_DECODED)
|
||||
}
|
||||
|
||||
/// [`Document::decoded_image`] for an image whose decoding has a tighter bound than
|
||||
/// [`MAX_DECODED`]: no stage, the filters before a fax or JBIG2 decoder included, may produce
|
||||
/// more than `max` bytes. A JBIG2 image's `/JBIG2Globals` are another stream, shared between
|
||||
/// images, and are decoded within [`MAX_JBIG2_GLOBALS`] whatever `max` is.
|
||||
pub fn decoded_image_within(&self, s: &Stream, max: usize) -> Result<Vec<u8>, CosError> {
|
||||
/// [`Document::decoded_image`] within `max` bytes.
|
||||
#[cfg(test)]
|
||||
pub(crate) fn decoded_image_within(&self, s: &Stream, max: usize) -> Result<Vec<u8>, CosError> {
|
||||
let mut unbounded = u64::MAX;
|
||||
self.decoded_image_spending(s, max, &mut unbounded)
|
||||
}
|
||||
|
||||
/// The samples of image `s`, decoded within `max` bytes ([`MAX_DECODED`] at most), spending from
|
||||
/// `work`: see [`ImageBudget::decode`](crate::ImageBudget::decode), the way in from outside this
|
||||
/// crate, which says what this decodes and how.
|
||||
pub(crate) fn decoded_image_spending(&self, s: &Stream, max: usize, work: &mut u64) -> Result<Vec<u8>, CosError> {
|
||||
let max = max.min(MAX_DECODED);
|
||||
let s = &*self.with_direct_parms(s);
|
||||
let filter = |e: pdfcraft_filters::FilterError| CosError::Filter(e.to_string());
|
||||
let chain = s.readable_filters().map_err(filter)?;
|
||||
// The filters before the image codec, such as ASCII85Decode, are undone first.
|
||||
let undo = |before: &[(pdfcraft_filters::Filter, pdfcraft_filters::Params)]| match before {
|
||||
let undo = |before: &[(pdfcraft_filters::Filter, pdfcraft_filters::Params)], work: &mut u64| match before {
|
||||
[] => Ok(Cow::Borrowed(&s.raw[..])),
|
||||
_ => pdfcraft_filters::decode_tolerant(before, &s.raw, max).map(|(data, _)| Cow::Owned(data)).map_err(filter),
|
||||
_ => pdfcraft_filters::decode_tolerant_within(before, &s.raw, max, work).map(Cow::Owned).map_err(filter),
|
||||
};
|
||||
// `/Width` and `/Height` are read as given directly, as every caller reads them first: one
|
||||
// given by reference has the image refused there, before it gets here.
|
||||
@@ -310,10 +308,12 @@ impl Document {
|
||||
let (Some(columns), Some(height)) = (s.dict.int(b"Width").and_then(|w| u32::try_from(w).ok()), height) else {
|
||||
return Err(CosError::Filter("a JBIG2 image's /Width or /Height isn't a size".into()));
|
||||
};
|
||||
let globals = self.jbig2_globals(s)?;
|
||||
return pdfcraft_filters::decode_jbig2(&undo(before)?, globals.as_deref().map(Vec::as_slice), columns, height, max).map_err(filter);
|
||||
// Nothing to read for what can't be decoded: the images of a file share its globals.
|
||||
let globals = if *work == 0 { None } else { self.jbig2_globals(s, work)? };
|
||||
let data = if *work == 0 { Cow::Borrowed(&[][..]) } else { undo(before, work)? };
|
||||
return pdfcraft_filters::decode_jbig2_within(&data, globals.as_deref().map(Vec::as_slice), columns, height, max, work).map_err(filter);
|
||||
}
|
||||
let Some(p) = self.fax_params(s) else { return s.decoded_within(max) };
|
||||
let Some(p) = self.fax_params(s) else { return s.decoded_spending(max, work) };
|
||||
// As many rows as the image has: a /Rows below /Height would cut the picture short, and
|
||||
// rows past /Height aren't drawn.
|
||||
let p = pdfcraft_filters::CcittParams { rows: 0, ..p };
|
||||
@@ -322,8 +322,8 @@ impl Document {
|
||||
}
|
||||
let stride = usize::try_from(p.columns).unwrap_or(usize::MAX).div_ceil(8).max(1);
|
||||
let rows = u32::try_from(max / stride).unwrap_or(u32::MAX).min(height.unwrap_or(0));
|
||||
let data = undo(chain.split_last().map_or(&[][..], |(_, before)| before))?;
|
||||
pdfcraft_filters::decode_ccitt(&data, &p, rows).map_err(filter)
|
||||
let data = undo(chain.split_last().map_or(&[][..], |(_, before)| before), work)?;
|
||||
pdfcraft_filters::decode_ccitt_within(&data, &p, rows, work).map_err(filter)
|
||||
}
|
||||
|
||||
/// The `/JBIG2Globals` stream a JBIG2 image `s` names by reference in its last filter's
|
||||
@@ -348,8 +348,9 @@ impl Document {
|
||||
/// it was read (the same in every clone) and with its `/DecodeParms` direct (by reference they
|
||||
/// are another object, which can change while this one doesn't), has its filters undone once a
|
||||
/// document and is kept, up to [`JBIG2_GLOBALS_HELD`] in all; others are read each time. That
|
||||
/// saves the filters only: the segments it holds are decoded again for every image.
|
||||
fn jbig2_globals(&self, s: &Stream) -> Result<Option<Arc<Vec<u8>>>, CosError> {
|
||||
/// saves the filters only: the segments it holds are decoded again for every image. Undoing
|
||||
/// the filters spends from `work`, so globals read for every image pay every time.
|
||||
fn jbig2_globals(&self, s: &Stream, work: &mut u64) -> Result<Option<Arc<Vec<u8>>>, CosError> {
|
||||
let Some(entry) = self.last_filter_parms(s).get(b"JBIG2Globals").cloned() else { return Ok(None) };
|
||||
let held = match entry {
|
||||
Object::Ref(r) if !self.overlay.contains_key(&r.num) => Some(r.num),
|
||||
@@ -361,7 +362,7 @@ impl Document {
|
||||
let Object::Stream(g) = &*self.resolve(&entry) else { return Ok(None) };
|
||||
let readable = self.with_direct_parms(g);
|
||||
let held = held.filter(|_| matches!(readable, Cow::Borrowed(_)));
|
||||
let mut data = readable.decoded_within(MAX_JBIG2_GLOBALS).map_err(|e| {
|
||||
let mut data = readable.decoded_spending(MAX_JBIG2_GLOBALS, work).map_err(|e| {
|
||||
let detail = match e {
|
||||
CosError::Filter(detail) => detail,
|
||||
e => e.to_string(),
|
||||
@@ -398,8 +399,9 @@ impl Document {
|
||||
let obj = Arc::new(obj);
|
||||
// The editing cache is bounded like the scan reader's: re-parsing a file-backed view
|
||||
// is cheap, and returned objects outlive eviction.
|
||||
self.cache.lock().map_err(|_| CosError::Poisoned)?.insert(num, obj.clone());
|
||||
self.evict_editor_cache_if_over_budget(num, &obj)?;
|
||||
let owned = held_bytes(&obj, &self.data, 0);
|
||||
self.cache.lock().map_err(|_| CosError::Poisoned)?.insert(num, obj.clone(), owned);
|
||||
self.evict_editor_cache_if_over_budget(num)?;
|
||||
Ok(obj)
|
||||
}
|
||||
|
||||
@@ -408,10 +410,10 @@ impl Document {
|
||||
/// document cannot pin its whole object graph. Only owned (decrypted/copied) bytes
|
||||
/// count; file-backed views re-parse for free.
|
||||
///
|
||||
/// Worst case per document: input bytes + up to `EDITOR_CACHE_OBJECTS` ×
|
||||
/// `EDITOR_LARGE_OBJECT` (1024 × 256 KB = 256 MB) of small objects between full
|
||||
/// accounting passes + `EDITOR_OBJSTM_BYTES` (32 MB) + unsaved `overlay` edits.
|
||||
/// The count cap always holds; byte accounting between passes is approximate.
|
||||
/// Worst case per document: input bytes + `EDITOR_CACHE_BYTES` (32 MB) of owned object
|
||||
/// data + `EDITOR_OBJSTM_BYTES` (32 MB) + unsaved `overlay` edits. Each object is measured
|
||||
/// once, as it is cached ([`ObjectCache`](super::state::ObjectCache)), so both caps hold
|
||||
/// after every insertion.
|
||||
/// Clones share these caches, so one clone's eviction drops another's hot set;
|
||||
/// that only costs re-parsing, never correctness. Eviction keeps just the newcomer:
|
||||
/// file-backed views re-parse cheaply and editor working sets stay far below 1024.
|
||||
@@ -424,37 +426,13 @@ impl Document {
|
||||
|
||||
const EDITOR_OBJSTM_BYTES: usize = 32 * 1024 * 1024;
|
||||
|
||||
/// Newcomers above this force a full accounting pass even below the count cap:
|
||||
/// `EDITOR_CACHE_BYTES / 128`, so 128 large newcomers always trigger a pass before the
|
||||
/// byte budget can double.
|
||||
const EDITOR_LARGE_OBJECT: usize = 256 * 1024;
|
||||
|
||||
fn evict_editor_cache_if_over_budget(&self, fresh_num: u32, fresh: &Object) -> Result<(), CosError> {
|
||||
// Fast path: the full fold is O(cache) per insert, so skip it for a small newcomer
|
||||
// below the count cap. `len` is copied out first; nothing here holds the lock.
|
||||
let len = self.cache.lock().map_err(|_| CosError::Poisoned)?.len();
|
||||
if len <= Self::EDITOR_CACHE_OBJECTS && owned_bytes(fresh, &self.data, 0) <= Self::EDITOR_LARGE_OBJECT {
|
||||
return Ok(());
|
||||
}
|
||||
// Walk a snapshot off-lock; re-lock only to evict.
|
||||
let live: Vec<(u32, Arc<Object>)> = self.cache.lock().map_err(|_| CosError::Poisoned)?.iter().map(|(n, o)| (*n, o.clone())).collect();
|
||||
let data = &self.data;
|
||||
let owned: usize = live.iter().fold(0usize, |n, (_, o)| n.saturating_add(owned_bytes(o, data, 0)));
|
||||
if live.len() <= Self::EDITOR_CACHE_OBJECTS && owned <= Self::EDITOR_CACHE_BYTES {
|
||||
return Ok(());
|
||||
}
|
||||
// Re-check under the final lock: another thread may have inserted or evicted since
|
||||
// the snapshot. Keep its newcomers, and skip the eviction if back within budget.
|
||||
let snapshot: std::collections::HashSet<u32> = live.into_iter().map(|(n, _)| n).collect();
|
||||
fn evict_editor_cache_if_over_budget(&self, fresh_num: u32) -> Result<(), CosError> {
|
||||
let mut cache = self.cache.lock().map_err(|_| CosError::Poisoned)?;
|
||||
if cache.len() <= Self::EDITOR_CACHE_OBJECTS {
|
||||
let data = &self.data;
|
||||
let owned: usize = cache.values().fold(0usize, |n, o| n.saturating_add(owned_bytes(o, data, 0)));
|
||||
if owned <= Self::EDITOR_CACHE_BYTES {
|
||||
return Ok(());
|
||||
}
|
||||
if cache.len() <= Self::EDITOR_CACHE_OBJECTS && cache.owned() <= Self::EDITOR_CACHE_BYTES {
|
||||
return Ok(());
|
||||
}
|
||||
cache.retain(|n, _| *n == fresh_num || !snapshot.contains(n));
|
||||
// Eviction keeps just the newcomer: file-backed views re-parse cheaply.
|
||||
cache.retain(|n| *n == fresh_num);
|
||||
Ok(())
|
||||
}
|
||||
|
||||
|
||||
@@ -163,11 +163,10 @@ impl ObjectReader {
|
||||
// input bytes, which the document keeps anyway, so they don't count; decrypted
|
||||
// streams and strings do. Checked after failed loads too: resolving a /Length may
|
||||
// have cached large objects.
|
||||
if let Ok(mut cache) = self.document.cache.lock() {
|
||||
let data = &self.document.data;
|
||||
if cache.len() >= Self::OBJECTS || cache.values().fold(0usize, |n, o| n.saturating_add(owned_bytes(o, data, 0))) > Self::STREAM_BYTES {
|
||||
cache.clear();
|
||||
}
|
||||
if let Ok(mut cache) = self.document.cache.lock()
|
||||
&& (cache.len() >= Self::OBJECTS || cache.owned() > Self::STREAM_BYTES)
|
||||
{
|
||||
cache.clear();
|
||||
}
|
||||
object
|
||||
}
|
||||
@@ -179,26 +178,96 @@ thread_local! {
|
||||
pub(super) static SECTION_READS: std::cell::Cell<usize> = const { std::cell::Cell::new(0) };
|
||||
}
|
||||
|
||||
/// Nesting [`owned_bytes`] walks: past the parser's own nesting limit, so every parsed object
|
||||
/// Parsed objects by number, each with what it holds ([`held_bytes`]) measured once, when it goes
|
||||
/// in, and their sum kept beside them.
|
||||
///
|
||||
/// Both caches are bounded by those bytes. Summing them on every read walked every cached object
|
||||
/// whole each time: a file whose page dictionaries carry kilobytes of private data (InDesign's
|
||||
/// `/PieceInfo`) took seconds to open, almost all of it re-measuring objects already measured
|
||||
/// (#5873).
|
||||
#[derive(Default)]
|
||||
pub(crate) struct ObjectCache {
|
||||
entries: HashMap<u32, (Arc<Object>, usize)>,
|
||||
owned: usize,
|
||||
}
|
||||
|
||||
impl ObjectCache {
|
||||
pub(crate) fn get(&self, num: &u32) -> Option<&Arc<Object>> {
|
||||
self.entries.get(num).map(|(object, _)| object)
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
pub(crate) fn contains_key(&self, num: &u32) -> bool {
|
||||
self.entries.contains_key(num)
|
||||
}
|
||||
|
||||
/// Keep `object` as `num`, which holds `owned` bytes (what [`held_bytes`] says of it).
|
||||
pub(crate) fn insert(&mut self, num: u32, object: Arc<Object>, owned: usize) {
|
||||
if let Some((_, before)) = self.entries.insert(num, (object, owned)) {
|
||||
self.owned = self.owned.saturating_sub(before);
|
||||
}
|
||||
self.owned = self.owned.saturating_add(owned);
|
||||
}
|
||||
|
||||
pub(crate) fn len(&self) -> usize {
|
||||
self.entries.len()
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
pub(crate) fn is_empty(&self) -> bool {
|
||||
self.entries.is_empty()
|
||||
}
|
||||
|
||||
/// The bytes the cached objects hold between them.
|
||||
pub(crate) fn owned(&self) -> usize {
|
||||
self.owned
|
||||
}
|
||||
|
||||
pub(crate) fn clear(&mut self) {
|
||||
self.entries.clear();
|
||||
self.owned = 0;
|
||||
}
|
||||
|
||||
pub(crate) fn retain(&mut self, mut keep: impl FnMut(&u32) -> bool) {
|
||||
self.entries.retain(|num, _| keep(num));
|
||||
self.owned = self.entries.values().fold(0usize, |n, (_, owned)| n.saturating_add(*owned));
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
pub(crate) fn values(&self) -> impl Iterator<Item = &Arc<Object>> {
|
||||
self.entries.values().map(|(object, _)| object)
|
||||
}
|
||||
}
|
||||
|
||||
/// Nesting [`held_bytes`] walks: past the parser's own nesting limit, so every parsed object
|
||||
/// is measured in full.
|
||||
const OWNED_BYTES_DEPTH: usize = 256;
|
||||
|
||||
/// Bytes `object` holds of its own: string and stream data that is not a view into `data`
|
||||
/// (the input file). An object nested deeper than [`OWNED_BYTES_DEPTH`] cannot be measured
|
||||
/// and counts as too large to keep.
|
||||
pub(super) fn owned_bytes(object: &Object, data: &Arc<Vec<u8>>, depth: usize) -> usize {
|
||||
/// What keeping `object` parsed costs: string and stream data that is not a view into `data`
|
||||
/// (the input file), and the parsed tree around it -- an [`Object`] per value and a key per
|
||||
/// dictionary entry. An object nested deeper than [`OWNED_BYTES_DEPTH`] cannot be measured and
|
||||
/// counts as too large to keep.
|
||||
///
|
||||
/// The tree counts. Measured by its strings and streams alone, a page dictionary carrying
|
||||
/// InDesign's `/PieceInfo` -- thousands of small numeric arrays, parsed into tens of thousands of
|
||||
/// values -- weighed nothing, so the caches kept a thousand of them: a 35 MB file held 1.5 GB
|
||||
/// (#5873).
|
||||
pub(super) fn held_bytes(object: &Object, data: &Arc<Vec<u8>>, depth: usize) -> usize {
|
||||
if depth > OWNED_BYTES_DEPTH {
|
||||
return usize::MAX;
|
||||
}
|
||||
let node = std::mem::size_of::<Object>();
|
||||
// A key, its slot beside the value, and room in the index a large dictionary keeps.
|
||||
let entry = |key: &[u8]| key.len().saturating_add(std::mem::size_of::<(crate::Name, Object)>()).saturating_add(16);
|
||||
let dict =
|
||||
|d: &crate::Dict, start: usize| d.iter().fold(start, |n, (k, v)| n.saturating_add(entry(k)).saturating_add(held_bytes(v, data, depth + 1)));
|
||||
match object {
|
||||
Object::String(s) => s.bytes.len(),
|
||||
Object::Stream(s) => {
|
||||
let own = if s.raw.shares(data) { 0 } else { s.raw.len() };
|
||||
s.dict.iter().fold(own, |n, (_, v)| n.saturating_add(owned_bytes(v, data, depth + 1)))
|
||||
}
|
||||
Object::Array(a) => a.iter().fold(0usize, |n, v| n.saturating_add(owned_bytes(v, data, depth + 1))),
|
||||
Object::Dict(d) => d.iter().fold(0usize, |n, (_, v)| n.saturating_add(owned_bytes(v, data, depth + 1))),
|
||||
_ => 0,
|
||||
Object::String(s) => node.saturating_add(s.bytes.len()),
|
||||
Object::Name(n) => node.saturating_add(n.len()),
|
||||
Object::Stream(s) => dict(&s.dict, node.saturating_add(if s.raw.shares(data) { 0 } else { s.raw.len() })),
|
||||
Object::Array(a) => a.iter().fold(node, |n, v| n.saturating_add(held_bytes(v, data, depth + 1))),
|
||||
Object::Dict(d) => dict(d, node),
|
||||
_ => node,
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
@@ -1109,7 +1109,8 @@ fn temporary_reader_keeps_file_views_and_evicts_data_of_its_own() {
|
||||
// Data of its own (decrypted streams, strings) counts: past the budget the cache is
|
||||
// cleared after the next read, including a failed one.
|
||||
let owned = Object::Stream(crate::Stream::from_raw(Dict::new(), vec![b'y'; ObjectReader::STREAM_BYTES + 1]));
|
||||
reader.document.cache.lock().unwrap().insert(3, Arc::new(owned));
|
||||
let size = held_bytes(&owned, &reader.document.data, 0);
|
||||
reader.document.cache.lock().unwrap().insert(3, Arc::new(owned), size);
|
||||
assert_eq!(*reader.get(ObjRef::new(99, 0)), Object::Null);
|
||||
assert!(reader.document.cache.lock().unwrap().is_empty(), "owned data over budget is evicted");
|
||||
}
|
||||
@@ -1192,13 +1193,14 @@ fn editor_cache_counts_deeply_nested_strings() {
|
||||
source.update_dict(source.root().unwrap(), |d| d.set(b"Extension".to_vec(), Object::Array(objects))).unwrap();
|
||||
let bytes = Arc::new(crate::write_full(&source, &crate::SaveOptions::default()).unwrap());
|
||||
let doc = Document::open(bytes).unwrap();
|
||||
assert_eq!(owned_bytes(&nested, &doc.data, 0), 1 << 20);
|
||||
let held = held_bytes(&nested, &doc.data, 0);
|
||||
assert!((1 << 20..(1 << 20) + 4096).contains(&held), "the string and a little tree: {held}");
|
||||
let root = doc.get(doc.root().unwrap());
|
||||
for reference in root.as_dict().unwrap().get(b"Extension").unwrap().as_array().unwrap() {
|
||||
let Object::Ref(reference) = reference else { panic!("indirect object") };
|
||||
drop(doc.get(*reference));
|
||||
let cache = doc.cache.lock().unwrap();
|
||||
let owned = cache.values().fold(0usize, |n, o| n.saturating_add(owned_bytes(o, &doc.data, 0)));
|
||||
let owned = cache.values().fold(0usize, |n, o| n.saturating_add(held_bytes(o, &doc.data, 0)));
|
||||
let strings = cache.values().filter(|o| o.as_array().is_some()).count();
|
||||
assert!(strings << 20 <= Document::EDITOR_CACHE_BYTES + (1 << 20), "{strings} MiB strings cached, {owned} bytes counted");
|
||||
}
|
||||
@@ -1240,8 +1242,8 @@ fn editor_cache_stays_bounded() {
|
||||
|
||||
#[test]
|
||||
fn editor_cache_byte_bound_fires() {
|
||||
// 40 × 1 MB strings: far below the count cap, above the 32 MB byte budget. Each
|
||||
// newcomer exceeds EDITOR_LARGE_OBJECT, so every insert takes a full accounting pass.
|
||||
// 40 × 1 MB strings: far below the count cap, above the 32 MB byte budget, which is
|
||||
// checked after every insertion.
|
||||
let mut source = Document::new_empty();
|
||||
let objects: Vec<_> = (0..40)
|
||||
.map(|i| {
|
||||
@@ -1701,3 +1703,50 @@ fn a_stream_whose_length_is_itself_and_never_ends_loads_quickly() {
|
||||
});
|
||||
rx.recv_timeout(std::time::Duration::from_secs(20)).expect("loading must not retry exponentially");
|
||||
}
|
||||
|
||||
/// The cache keeps the sum of what its objects hold as they come and go, so neither reader has
|
||||
/// to measure the cache again on every read (#5873).
|
||||
#[test]
|
||||
fn the_object_cache_keeps_its_total_as_objects_come_and_go() {
|
||||
let data = Arc::new(Vec::new());
|
||||
let one = Arc::new(Object::String(crate::PdfString::literal(vec![b'x'; 100])));
|
||||
let two = Arc::new(Object::Array(vec![Object::Int(1); 10]));
|
||||
let (a, b) = (held_bytes(&one, &data, 0), held_bytes(&two, &data, 0));
|
||||
let mut cache = super::state::ObjectCache::default();
|
||||
cache.insert(1, one.clone(), a);
|
||||
cache.insert(2, two, b);
|
||||
assert_eq!(cache.owned(), a + b);
|
||||
cache.insert(2, one, a);
|
||||
assert_eq!(cache.owned(), a + a, "a replaced object no longer counts");
|
||||
cache.retain(|n| *n == 1);
|
||||
assert_eq!((cache.len(), cache.owned()), (1, a));
|
||||
cache.clear();
|
||||
assert_eq!((cache.len(), cache.owned()), (0, 0));
|
||||
}
|
||||
|
||||
/// A dictionary of numbers owns no string or stream bytes, but parsed it is tens of thousands
|
||||
/// of values: InDesign's per-page `/PieceInfo`. Counting only strings and streams, the editing
|
||||
/// cache kept a thousand such pages and a 35 MB book held 1.5 GB (#5873). What the parsed tree
|
||||
/// holds counts now, so the byte budget bounds them.
|
||||
#[test]
|
||||
fn the_editor_cache_charges_a_dictionary_for_the_values_it_holds() {
|
||||
let entries: String = (0..2000).map(|i| format!("/{i}[{i} 141 3 116.22 -375.993 1.0]")).collect();
|
||||
let dict = format!("<< /PieceInfo << /InDesign << /Map << {entries} >> >> >> >>");
|
||||
let count = 300;
|
||||
let refs: String = (0..count).map(|i| format!("{} 0 R ", i + 2)).collect();
|
||||
let mut bodies = vec![format!("<< /Type /Catalog /Extension [{refs}] >>")];
|
||||
bodies.extend((0..count).map(|_| dict.clone()));
|
||||
let bodies: Vec<&str> = bodies.iter().map(String::as_str).collect();
|
||||
let doc = Document::open(Arc::new(build(&bodies, "/Root 1 0 R"))).unwrap();
|
||||
let one = doc.get(crate::ObjRef::new(2, 0));
|
||||
let held = held_bytes(&one, &doc.data, 0);
|
||||
assert!(held > 2000 * std::mem::size_of::<Object>(), "the parsed tree counts: {held} bytes");
|
||||
for i in 0..count {
|
||||
drop(doc.get(crate::ObjRef::new(i as u32 + 2, 0)));
|
||||
}
|
||||
let cache = doc.cache.lock().unwrap();
|
||||
assert!(cache.owned() <= Document::EDITOR_CACHE_BYTES, "{} bytes held", cache.owned());
|
||||
assert!(cache.len() < count, "the byte budget evicted some, below the count cap: {} kept", cache.len());
|
||||
let sum = cache.values().fold(0usize, |n, o| n.saturating_add(held_bytes(o, &doc.data, 0)));
|
||||
assert_eq!(cache.owned(), sum, "the kept total is the cache's own");
|
||||
}
|
||||
@@ -22,7 +22,7 @@ mod parser;
|
||||
mod security;
|
||||
mod writer;
|
||||
|
||||
pub use budget::{DecodeBudget, MAX_PAGE_DECODED, MAX_PAGE_FORMS};
|
||||
pub use budget::{DecodeBudget, ImageBudget, MAX_PAGE_DECODED, MAX_PAGE_FORMS};
|
||||
pub use bytes::Bytes;
|
||||
pub use document::{Document, ReadState, Revision, SourceIdentity, XrefEntry};
|
||||
pub use object::{Dict, MAX_DECODED, MAX_JBIG2_GLOBALS, Name, ObjRef, Object, PdfString, Stream};
|
||||
|
||||
@@ -306,6 +306,14 @@ impl Stream {
|
||||
self.decode_chain(max, decode)
|
||||
}
|
||||
|
||||
/// [`Stream::decoded_within`] spending from `work`, what an operation may still do across a
|
||||
/// document's images ([`pdfcraft_filters::decode_tolerant_within`]).
|
||||
pub(crate) fn decoded_spending(&self, max: usize, work: &mut u64) -> Result<Vec<u8>, CosError> {
|
||||
let filter = |e: pdfcraft_filters::FilterError| CosError::Filter(e.to_string());
|
||||
let chain = self.readable_filters().map_err(filter)?;
|
||||
pdfcraft_filters::decode_tolerant_within(&chain, &self.raw, max.min(MAX_DECODED), work).map_err(filter)
|
||||
}
|
||||
|
||||
/// The stream decoded through its filters by `decode`, or copied when it has none, within
|
||||
/// `max` and [`MAX_DECODED`].
|
||||
fn decode_chain(
|
||||
|
||||
@@ -341,7 +341,11 @@ impl<'a> Lexer<'a> {
|
||||
let s = std::str::from_utf8(tok).map_err(|_| self.err("bad number"))?;
|
||||
if s.contains('.') {
|
||||
// Tolerate forms like "--5", "5-" or "1.2.3" by parsing the longest valid prefix.
|
||||
let cleaned: String = s.trim_start_matches('+').replacen("--", "-", 1);
|
||||
// Only a doubled sign needs a cleaned copy: a page of InDesign `/PieceInfo` is
|
||||
// thousands of plain reals, and building a copy and a substring search for each
|
||||
// was a large part of reading one (#5873).
|
||||
let t = s.trim_start_matches('+');
|
||||
let cleaned = if t.as_bytes().windows(2).any(|w| w == b"--") { std::borrow::Cow::Owned(t.replacen("--", "-", 1)) } else { t.into() };
|
||||
let v = cleaned.get(..real_prefix_len(cleaned.as_bytes())).and_then(|p| parse_counted::<f64>(p).ok());
|
||||
return Ok(Object::Real(v.unwrap_or(0.0)));
|
||||
}
|
||||
@@ -707,4 +711,13 @@ mod tests {
|
||||
let mut lx = Lexer::new(two.as_bytes(), 0);
|
||||
assert!(lx.object().is_ok() && lx.object().is_ok());
|
||||
}
|
||||
|
||||
/// A plain real is read without a cleaned copy of its token; the forms that need one read
|
||||
/// as they did (#5873).
|
||||
#[test]
|
||||
fn reals_read_the_same_with_and_without_a_doubled_sign() {
|
||||
for (token, want) in [("1.5", 1.5), ("-375.993", -375.993), ("+2.25", 2.25), ("--5.5", -5.5), ("1.2.3", 1.2), ("-.5", -0.5), ("0.0", 0.0)] {
|
||||
assert_eq!(Lexer::new(token.as_bytes(), 0).object().unwrap(), Object::Real(want), "{token}");
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -27,12 +27,14 @@ Layer L4. Create a PDF (Acrobat's Create a PDF tool), execution plan M10.2:
|
||||
Every function returns a `pdfcraft_cos::Document`; the caller writes it.
|
||||
|
||||
Image export and Save Image As apply each lossless image's Decode pair before converting its color components.
|
||||
JBIG2 images and masks are decoded through `pdfcraft_cos::Document::decoded_image` (`pdfcraft_filters::decode_jbig2`), behind
|
||||
JBIG2 images and masks are decoded through `pdfcraft_cos::ImageBudget` (`pdfcraft_filters::decode_jbig2_within`), behind
|
||||
other filters too, with the `/JBIG2Globals` of their own `/DecodeParms` entry, as `JBIG2Decode` gives them: black as 0. An image
|
||||
whose JBIG2 page isn't its size (PdfCraft's renderer draws the whole page into the image; the page is refused before it is decoded),
|
||||
or whose globals can't be read or decode to more than 32 MiB (they are decoded before the page's size is known, so they have a
|
||||
limit of their own), is skipped; such a mask is left out and the image exported opaque, as JPX and CCITT
|
||||
masks are.
|
||||
limit of their own), is skipped, and such a mask is left out and the image exported opaque, as JPX and CCITT masks are.
|
||||
Past what one export may decode, which its images share, filters, decoders and pixels alike (`ImageBudget`; a JPEG when it has to be
|
||||
decoded, as a mask, to apply one, or to undo a CMYK file's inversion, and not when it is written as it is), an image is skipped, and so is one whose mask is past it, which would otherwise come out showing what the mask hides. An export also stops at 2 GiB of files held, or twice the document if that
|
||||
is more, since they stay in memory until it ends.
|
||||
Indexed Decode values select palette entries after rounding and clipping. Color-key masks compare the original samples.
|
||||
Missing, null or malformed Decode arrays keep the default mapping.
|
||||
Soft-mask Decode intervals map samples to opacity before the mask is resized, including reversed ranges and indirect entries.
|
||||
|
||||
@@ -6,7 +6,8 @@
|
||||
|
||||
use std::collections::HashSet;
|
||||
|
||||
use pdfcraft_cos::{Dict, Document, ObjRef, Object, Stream};
|
||||
use pdfcraft_cos::{Dict, Document, ImageBudget, MAX_DECODED, ObjRef, Object, Stream};
|
||||
use pdfcraft_filters::FilterError;
|
||||
|
||||
/// One image, ready to write.
|
||||
#[derive(Clone, Debug, PartialEq)]
|
||||
@@ -31,12 +32,29 @@ pub struct ImageExport {
|
||||
/// Images larger than this many pixels are skipped (memory).
|
||||
const MAX_PIXELS: u64 = 100_000_000;
|
||||
|
||||
/// What one export may hold of the files it makes: they are all in memory until it ends, and a file
|
||||
/// of a few KB can make gigabytes of PNG. Images past it are left out, with the reason.
|
||||
const MAX_EXPORT_BYTES: usize = 2 << 30;
|
||||
|
||||
/// What an export of a file of `file_bytes` may hold: twice the file if that is more than
|
||||
/// [`MAX_EXPORT_BYTES`], so that a file of large images is exported whole.
|
||||
pub(crate) fn export_bytes(file_bytes: usize) -> usize {
|
||||
MAX_EXPORT_BYTES.max(file_bytes.saturating_mul(2))
|
||||
}
|
||||
|
||||
/// The images of `pages` (0-based; each image once, on the first page using it), skipping
|
||||
/// those with fewer than `min_side` pixels on their shorter side.
|
||||
pub fn extract_images(doc: &Document, pages: &[usize], min_side: u32) -> ImageExport {
|
||||
extract_images_within(doc, pages, min_side, &mut ImageBudget::new(doc), export_bytes(doc.bytes().len()))
|
||||
}
|
||||
|
||||
/// [`extract_images`] within `budget`, and holding `max_bytes` of files. An image past either is
|
||||
/// left out, with the reason.
|
||||
pub(crate) fn extract_images_within(doc: &Document, pages: &[usize], min_side: u32, budget: &mut ImageBudget, max_bytes: usize) -> ImageExport {
|
||||
let all = pdfcraft_model::pages(doc);
|
||||
let mut out = ImageExport::default();
|
||||
let mut seen = HashSet::new();
|
||||
let mut held = 0usize;
|
||||
for &p in pages {
|
||||
let Some(page) = all.get(p) else { continue };
|
||||
let mut refs = Vec::new();
|
||||
@@ -53,8 +71,15 @@ pub fn extract_images(doc: &Document, pages: &[usize], min_side: u32) -> ImageEx
|
||||
if w <= 0 || h <= 0 || (w.min(h) as u64) < min_side as u64 {
|
||||
continue;
|
||||
}
|
||||
match image(doc, s) {
|
||||
Ok((extension, data)) => out.images.push(ExtractedImage { page: p, object: r, width: w as u32, height: h as u32, extension, data }),
|
||||
if held >= max_bytes {
|
||||
out.skipped.push((p, r, "more images than one export can hold".into()));
|
||||
continue;
|
||||
}
|
||||
match image(doc, s, budget) {
|
||||
Ok((extension, data)) => {
|
||||
held = held.saturating_add(data.len());
|
||||
out.images.push(ExtractedImage { page: p, object: r, width: w as u32, height: h as u32, extension, data });
|
||||
}
|
||||
Err(why) => out.skipped.push((p, r, why)),
|
||||
}
|
||||
}
|
||||
@@ -64,8 +89,13 @@ pub fn extract_images(doc: &Document, pages: &[usize], min_side: u32) -> ImageEx
|
||||
|
||||
/// One image XObject as a file: JPEG as is, else PNG ("Save image as").
|
||||
pub fn image_file(doc: &Document, image: ObjRef) -> Result<(&'static str, Vec<u8>), String> {
|
||||
image_file_within(doc, image, &mut ImageBudget::new(doc))
|
||||
}
|
||||
|
||||
/// [`image_file`] within `budget`, for a caller making a file of many images.
|
||||
pub fn image_file_within(doc: &Document, image: ObjRef, budget: &mut ImageBudget) -> Result<(&'static str, Vec<u8>), String> {
|
||||
match &*doc.get(image) {
|
||||
Object::Stream(s) if s.dict.name(b"Subtype") == Some(b"Image") => self::image(doc, s),
|
||||
Object::Stream(s) if s.dict.name(b"Subtype") == Some(b"Image") => self::image(doc, s, budget),
|
||||
_ => Err("not an image".into()),
|
||||
}
|
||||
}
|
||||
@@ -100,20 +130,20 @@ fn filters(s: &Stream) -> Vec<Vec<u8>> {
|
||||
}
|
||||
}
|
||||
|
||||
/// The samples of image `s`, decoded ([`Document::decoded_image`]): through its filters, with a
|
||||
/// The samples of image `s`, decoded ([`ImageBudget::decode`]): through its filters, with a
|
||||
/// `/DecodeParms` dictionary given by reference, or as an array's entry, or with numbers inside by
|
||||
/// reference, read too (a predictor given so would otherwise be lost); a CCITT fax or JBIG2 image
|
||||
/// through its decoder too, behind other filters as well, a JBIG2 image with its `/JBIG2Globals`.
|
||||
/// A JBIG2 page has to be the image's size, which the caller checked against the export's limit,
|
||||
/// before the page is decoded.
|
||||
fn decoded(doc: &Document, s: &Stream) -> Result<Vec<u8>, String> {
|
||||
doc.decoded_image(s).map_err(|e| e.to_string())
|
||||
fn decoded(doc: &Document, s: &Stream, budget: &mut ImageBudget) -> Result<Vec<u8>, String> {
|
||||
budget.decode(doc, s, MAX_DECODED).map_err(|e| e.to_string())
|
||||
}
|
||||
|
||||
/// The file for one image: its JPEG data as is, or a PNG. An image with transparency (a soft
|
||||
/// mask, a stencil `/Mask` or a colour-key `/Mask`) is always a PNG with that transparency as
|
||||
/// alpha, JPEG images included, so cut-out images keep their transparent background.
|
||||
fn image(doc: &Document, s: &Stream) -> Result<(&'static str, Vec<u8>), String> {
|
||||
fn image(doc: &Document, s: &Stream, budget: &mut ImageBudget) -> Result<(&'static str, Vec<u8>), String> {
|
||||
let f = filters(s);
|
||||
let jpeg = matches!(f.last().map(Vec::as_slice), Some(b"DCTDecode" | b"DCT")) && f.len() == 1;
|
||||
match f.last().map(Vec::as_slice) {
|
||||
@@ -132,7 +162,12 @@ fn image(doc: &Document, s: &Stream) -> Result<(&'static str, Vec<u8>), String>
|
||||
};
|
||||
let mask = s.dict.get(b"ImageMask").is_some_and(|m| matches!(&*doc.resolve(m), Object::Bool(true)));
|
||||
// A stencil mask (`ImageMask true`) has no /SMask or /Mask of its own (8.9.6.2).
|
||||
let mut alpha = if mask { None } else { soft_mask(doc, s, w, h).or_else(|| stencil_mask(doc, s, w, h)) };
|
||||
let refused = budget.refused();
|
||||
let mut alpha = if mask { None } else { soft_mask(doc, s, w, h, budget).or_else(|| stencil_mask(doc, s, w, h, budget)) };
|
||||
// Without its mask the image would come out opaque, showing what the mask hides.
|
||||
if budget.refused() > refused {
|
||||
return Err(FilterError::Spent.to_string());
|
||||
}
|
||||
let key = if mask { None } else { colour_key(doc, s) };
|
||||
// Keep the existing JPEG and stencil-mask Decode handling separate from lossless colour images.
|
||||
let endpoint = |value: Option<&Object>| value.map(|v| doc.resolve(v)).and_then(|v| v.as_f64()).filter(|v| v.is_finite());
|
||||
@@ -155,13 +190,16 @@ fn image(doc: &Document, s: &Stream) -> Result<(&'static str, Vec<u8>), String>
|
||||
}
|
||||
let mut space = if mask { Space::Gray } else { space(doc, s.dict.get(b"ColorSpace"))? };
|
||||
let (samples, bpc) = if jpeg {
|
||||
if !budget.pay_jpeg((w as u64).saturating_mul(h as u64).saturating_mul(space.components() as u64), &s.raw) {
|
||||
return Err(FilterError::Spent.to_string());
|
||||
}
|
||||
// Grey, RGB or CMYK samples (YCCK is converted); a JPEG that doesn't decode, or an
|
||||
// indexed one (not valid), is written as is, without its transparency.
|
||||
let Some((samples, decoded)) = jpeg_samples(&s.raw, &space, w, h) else { return as_is() };
|
||||
space = decoded;
|
||||
(samples, 8)
|
||||
} else {
|
||||
let data = decoded(doc, s)?;
|
||||
let data = decoded(doc, s, budget)?;
|
||||
let bpc = if mask { 1 } else { s.dict.int(b"BitsPerComponent").unwrap_or(8) };
|
||||
let bpc = match bpc {
|
||||
1 => 1,
|
||||
@@ -252,6 +290,32 @@ fn size(w: i64, h: i64) -> Option<(usize, usize)> {
|
||||
(w > 0 && h > 0 && pixels <= MAX_PIXELS).then_some((w, h))
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
thread_local! {
|
||||
/// JPEGs decoded whole, for the tests that keep one from being decoded for nothing.
|
||||
pub(crate) static JPEGS_DECODED: std::cell::Cell<usize> = const { std::cell::Cell::new(0) };
|
||||
}
|
||||
|
||||
/// The size a JPEG's header gives, which is what decoding it goes by, whatever its dictionary
|
||||
/// says: an image of one pixel can hold a header of 500 megapixels.
|
||||
fn jpeg_size(data: &[u8]) -> Option<(usize, usize)> {
|
||||
use zune_jpeg::zune_core::{bytestream::ZCursor, options::DecoderOptions};
|
||||
let options = DecoderOptions::default().set_strict_mode(false).set_max_width(usize::from(u16::MAX)).set_max_height(usize::from(u16::MAX));
|
||||
let mut dec = zune_jpeg::JpegDecoder::new_with_options(ZCursor::new(data), options);
|
||||
dec.decode_headers().ok()?;
|
||||
dec.dimensions()
|
||||
}
|
||||
|
||||
/// JPEG `data`, decoded, if its header says it is `w` × `h`.
|
||||
fn jpeg_of_size(data: &[u8], w: usize, h: usize) -> Option<image::DynamicImage> {
|
||||
if jpeg_size(data)? != (w, h) {
|
||||
return None;
|
||||
}
|
||||
#[cfg(test)]
|
||||
JPEGS_DECODED.with(|n| n.set(n.get() + 1));
|
||||
image::load_from_memory_with_format(data, image::ImageFormat::Jpeg).ok()
|
||||
}
|
||||
|
||||
/// A JPEG's samples (8 bits): grey for a grey image, CMYK as stored for a CMYK one, else RGB,
|
||||
/// with the space they are in.
|
||||
fn jpeg_samples(data: &[u8], space: &Space, w: usize, h: usize) -> Option<(Vec<u8>, Space)> {
|
||||
@@ -260,10 +324,7 @@ fn jpeg_samples(data: &[u8], space: &Space, w: usize, h: usize) -> Option<(Vec<u
|
||||
Space::Cmyk => return cmyk_jpeg_samples(data, w, h).map(|px| (px, Space::Cmyk)),
|
||||
_ => {}
|
||||
}
|
||||
let img = image::load_from_memory_with_format(data, image::ImageFormat::Jpeg).ok()?;
|
||||
if img.width() as usize != w || img.height() as usize != h {
|
||||
return None;
|
||||
}
|
||||
let img = jpeg_of_size(data, w, h)?;
|
||||
Some(match space {
|
||||
Space::Gray => (img.into_luma8().into_raw(), Space::Gray),
|
||||
_ => (img.into_rgb8().into_raw(), Space::Rgb),
|
||||
@@ -464,32 +525,35 @@ fn cmyk(c: u8, m: u8, y: u8, k: u8) -> [u8; 3] {
|
||||
}
|
||||
|
||||
/// The soft mask (`/SMask`) as 8-bit alpha, scaled to the image's size when it has another.
|
||||
fn soft_mask(doc: &Document, s: &Stream, w: usize, h: usize) -> Option<Vec<u8>> {
|
||||
fn soft_mask(doc: &Document, s: &Stream, w: usize, h: usize, budget: &mut ImageBudget) -> Option<Vec<u8>> {
|
||||
let r = s.dict.get(b"SMask")?.as_ref()?;
|
||||
let obj = doc.get(r);
|
||||
let Object::Stream(m) = &*obj else { return None };
|
||||
gray_plane(doc, m, w, h)
|
||||
gray_plane(doc, m, w, h, budget)
|
||||
}
|
||||
|
||||
/// A stencil `/Mask` (an image mask stream, 8.9.6.3) as 8-bit alpha: its 1 samples (0 with
|
||||
/// `/Decode [1 0]`) hide the image.
|
||||
fn stencil_mask(doc: &Document, s: &Stream, w: usize, h: usize) -> Option<Vec<u8>> {
|
||||
fn stencil_mask(doc: &Document, s: &Stream, w: usize, h: usize, budget: &mut ImageBudget) -> Option<Vec<u8>> {
|
||||
let r = s.dict.get(b"Mask")?.as_ref()?;
|
||||
let obj = doc.get(r);
|
||||
let Object::Stream(m) = &*obj else { return None };
|
||||
Some(gray_plane(doc, m, w, h)?.into_iter().map(|v| 255 - v).collect())
|
||||
Some(gray_plane(doc, m, w, h, budget)?.into_iter().map(|v| 255 - v).collect())
|
||||
}
|
||||
|
||||
/// A one-component mask image as 8-bit values (its `/Decode` interval applied), scaled to
|
||||
/// `w` × `h`. `None` when it can't be decoded (JPEG 2000 masks).
|
||||
fn gray_plane(doc: &Document, m: &Stream, w: usize, h: usize) -> Option<Vec<u8>> {
|
||||
fn gray_plane(doc: &Document, m: &Stream, w: usize, h: usize, budget: &mut ImageBudget) -> Option<Vec<u8>> {
|
||||
let (mw, mh) = size(m.dict.int(b"Width")?, m.dict.int(b"Height")?)?;
|
||||
let stencil = m.dict.get(b"ImageMask").is_some_and(|v| matches!(&*doc.resolve(v), Object::Bool(true)));
|
||||
let f = filters(m);
|
||||
let mut px = match f.last().map(Vec::as_slice) {
|
||||
Some(b"DCTDecode" | b"DCT") if f.len() == 1 => {
|
||||
let img = image::load_from_memory_with_format(&m.raw, image::ImageFormat::Jpeg).ok()?.into_luma8();
|
||||
(img.width() as usize == mw && img.height() as usize == mh).then(|| img.into_raw())?
|
||||
// Past the allowance the image goes too: `image` sees this one refused.
|
||||
if !budget.pay_jpeg((mw as u64).saturating_mul(mh as u64), &m.raw) {
|
||||
return None;
|
||||
}
|
||||
jpeg_of_size(&m.raw, mw, mh)?.into_luma8().into_raw()
|
||||
}
|
||||
Some(b"DCTDecode" | b"DCT" | b"JPXDecode") => return None,
|
||||
_ => {
|
||||
@@ -503,7 +567,7 @@ fn gray_plane(doc: &Document, m: &Stream, w: usize, h: usize) -> Option<Vec<u8>>
|
||||
_ => return None,
|
||||
};
|
||||
let max = (1u32 << bpc.min(8)) - 1;
|
||||
unpack(&decoded(doc, m).ok()?, mw, mh, 1, bpc)?.into_iter().map(|v| (v as u32 * 255 / max) as u8).collect()
|
||||
unpack(&decoded(doc, m, budget).ok()?, mw, mh, 1, bpc)?.into_iter().map(|v| (v as u32 * 255 / max) as u8).collect()
|
||||
}
|
||||
};
|
||||
if let Some([lo, hi]) = decode(doc, m, 1).and_then(|pairs| pairs.first().copied()) {
|
||||
|
||||
+51
-26
@@ -6,7 +6,7 @@ use pdfcraft_cos::{Dict, Document, ObjRef, Object, PdfString, Stream, serialize}
|
||||
|
||||
mod extract;
|
||||
mod upright_image;
|
||||
pub use extract::{ExtractedImage, ImageExport, extract_images, image_file};
|
||||
pub use extract::{ExtractedImage, ImageExport, extract_images, image_file, image_file_within};
|
||||
use pdfcraft_fonts::{literal, win_ansi, wrap};
|
||||
|
||||
#[derive(Debug, thiserror::Error, PartialEq)]
|
||||
@@ -23,29 +23,48 @@ pub const LETTER: (f64, f64) = (612.0, 792.0);
|
||||
/// The largest page side PDF allows (ISO 32000-2 Annex C: 14 400 units).
|
||||
const MAX_SIDE: f64 = 14_400.0;
|
||||
|
||||
fn add_page(doc: &mut Document, w: f64, h: f64, resources: Dict, content: Option<Vec<u8>>) -> Result<ObjRef, CreateError> {
|
||||
// `Document::new_empty` always has a page tree.
|
||||
let pages = doc
|
||||
.root()
|
||||
.and_then(|r| doc.get(r).as_dict().and_then(|d| d.reference(b"Pages")))
|
||||
.ok_or_else(|| CreateError::Invalid("the new document has no page tree".into()))?;
|
||||
let mut page = Dict::new();
|
||||
page.set(b"Type".to_vec(), Object::name("Page"));
|
||||
page.set(b"Parent".to_vec(), Object::Ref(pages));
|
||||
page.set(b"MediaBox".to_vec(), Object::Array(vec![0.into(), 0.into(), Object::Real(w), Object::Real(h)]));
|
||||
page.set(b"Resources".to_vec(), Object::Dict(resources));
|
||||
if let Some(c) = content {
|
||||
let s = doc.add(Object::Stream(Stream::flate(Dict::new(), &c)));
|
||||
page.set(b"Contents".to_vec(), Object::Ref(s));
|
||||
/// The page tree of a document being made, with the pages added to it so far: its `/Kids` are
|
||||
/// written once, by [`Pages::finish`]. Adding each page to the tree in the document would copy every
|
||||
/// page before it, which a text of a million form feeds makes quadratic.
|
||||
struct Pages {
|
||||
tree: ObjRef,
|
||||
kids: Vec<Object>,
|
||||
}
|
||||
|
||||
impl Pages {
|
||||
/// The page tree of `doc`, with the pages it has.
|
||||
fn of(doc: &Document) -> Result<Self, CreateError> {
|
||||
// `Document::new_empty` always has a page tree.
|
||||
let tree = doc
|
||||
.root()
|
||||
.and_then(|r| doc.get(r).as_dict().and_then(|d| d.reference(b"Pages")))
|
||||
.ok_or_else(|| CreateError::Invalid("the new document has no page tree".into()))?;
|
||||
let kids = doc.get(tree).as_dict().and_then(|d| d.get(b"Kids")).and_then(|k| k.as_array().cloned()).unwrap_or_default();
|
||||
Ok(Self { tree, kids })
|
||||
}
|
||||
|
||||
fn add(&mut self, doc: &mut Document, w: f64, h: f64, resources: Dict, content: Option<Vec<u8>>) {
|
||||
let mut page = Dict::new();
|
||||
page.set(b"Type".to_vec(), Object::name("Page"));
|
||||
page.set(b"Parent".to_vec(), Object::Ref(self.tree));
|
||||
page.set(b"MediaBox".to_vec(), Object::Array(vec![0.into(), 0.into(), Object::Real(w), Object::Real(h)]));
|
||||
page.set(b"Resources".to_vec(), Object::Dict(resources));
|
||||
if let Some(c) = content {
|
||||
let s = doc.add(Object::Stream(Stream::flate(Dict::new(), &c)));
|
||||
page.set(b"Contents".to_vec(), Object::Ref(s));
|
||||
}
|
||||
self.kids.push(Object::Ref(doc.add(page)));
|
||||
}
|
||||
|
||||
/// Writes the pages added into the tree.
|
||||
fn finish(self, doc: &mut Document) -> Result<(), CreateError> {
|
||||
let count = i64::try_from(self.kids.len()).map_err(|_| CreateError::Invalid("too many pages".into()))?;
|
||||
doc.update_dict(self.tree, |d| {
|
||||
d.set(b"Count".to_vec(), Object::Int(count));
|
||||
d.set(b"Kids".to_vec(), Object::Array(self.kids));
|
||||
})
|
||||
.map_err(|e| CreateError::Invalid(e.to_string()))
|
||||
}
|
||||
let r = doc.add(page);
|
||||
let _ = doc.update_dict(pages, |d| {
|
||||
let mut kids = d.get(b"Kids").and_then(|k| k.as_array().cloned()).unwrap_or_default();
|
||||
kids.push(Object::Ref(r));
|
||||
d.set(b"Count".to_vec(), Object::Int(kids.len() as i64));
|
||||
d.set(b"Kids".to_vec(), Object::Array(kids));
|
||||
});
|
||||
Ok(r)
|
||||
}
|
||||
|
||||
fn set_title(doc: &mut Document, title: &str) {
|
||||
@@ -65,9 +84,11 @@ pub fn blank(width: f64, height: f64, pages: usize) -> Result<Document, CreateEr
|
||||
return Err(CreateError::Invalid("invalid page size or count".into()));
|
||||
}
|
||||
let mut doc = Document::new_empty();
|
||||
let mut tree = Pages::of(&doc)?;
|
||||
for _ in 0..pages {
|
||||
add_page(&mut doc, width, height, Dict::new(), None)?;
|
||||
tree.add(&mut doc, width, height, Dict::new(), None);
|
||||
}
|
||||
tree.finish(&mut doc)?;
|
||||
Ok(doc)
|
||||
}
|
||||
|
||||
@@ -675,6 +696,7 @@ pub fn from_images_with_resolution(images: &[(String, Vec<u8>)], resolution: Ima
|
||||
return Err(CreateError::Invalid("no images".into()));
|
||||
}
|
||||
let mut doc = Document::new_empty();
|
||||
let mut tree = Pages::of(&doc)?;
|
||||
let mut profiles = Vec::new();
|
||||
for img in images.iter().map(|(name, bytes)| embed(name, bytes, usize::MAX)).collect::<Result<Vec<_>, _>>()?.into_iter().flatten() {
|
||||
let dpi = match resolution {
|
||||
@@ -692,8 +714,9 @@ pub fn from_images_with_resolution(images: &[(String, Vec<u8>)], resolution: Ima
|
||||
let mut res = Dict::new();
|
||||
res.set(b"XObject".to_vec(), Object::Dict(xobj));
|
||||
let content = format!("q {w:.3} 0 0 {h:.3} 0 0 cm /Im0 Do Q\n").into_bytes();
|
||||
add_page(&mut doc, w, h, res, Some(content))?;
|
||||
tree.add(&mut doc, w, h, res, Some(content));
|
||||
}
|
||||
tree.finish(&mut doc)?;
|
||||
if let Some((name, _)) = images.first() {
|
||||
set_title(&mut doc, name.rsplit_once('.').map_or(name.as_str(), |(s, _)| s));
|
||||
}
|
||||
@@ -787,6 +810,7 @@ fn set_text(title: &str, text: &str, page: (f64, f64), font_size: f64) -> Result
|
||||
font.set(b"BaseFont".to_vec(), Object::name("Helvetica"));
|
||||
font.set(b"Encoding".to_vec(), Object::name("WinAnsiEncoding"));
|
||||
let fr = doc.add(font);
|
||||
let mut tree = Pages::of(&doc)?;
|
||||
let mut page_lines: Vec<Vec<String>> = vec![Vec::new()];
|
||||
for l in lines.iter().take(lines.len().saturating_sub(1)) {
|
||||
if l == "\u{c}" || page_lines.last().is_some_and(|p| p.len() >= per_page) {
|
||||
@@ -810,8 +834,9 @@ fn set_text(title: &str, text: &str, page: (f64, f64), font_size: f64) -> Result
|
||||
fonts.set(b"F1".to_vec(), Object::Ref(fr));
|
||||
let mut res = Dict::new();
|
||||
res.set(b"Font".to_vec(), Object::Dict(fonts));
|
||||
add_page(&mut doc, w, h, res, Some(c))?;
|
||||
tree.add(&mut doc, w, h, res, Some(c));
|
||||
}
|
||||
tree.finish(&mut doc)?;
|
||||
set_title(&mut doc, title);
|
||||
Ok(doc)
|
||||
}
|
||||
|
||||
@@ -124,6 +124,27 @@ fn text_is_wrapped_and_paginated() {
|
||||
assert!(content(p.last().unwrap()).contains("(After a form feed) Tj"), "a form feed starts a page");
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn text_of_many_form_feeds_makes_its_pages_in_linear_time() {
|
||||
// Each form feed starts a page: adding each to the page tree copied all the pages before it,
|
||||
// which made forty thousand of them take over a minute in a debug build, against about two
|
||||
// seconds when the tree is written once.
|
||||
let text = "x\u{c}".repeat(40_000);
|
||||
let start = std::time::Instant::now();
|
||||
let doc = from_text("many", &text, LETTER, 11.0).unwrap();
|
||||
let took = start.elapsed();
|
||||
let tree = doc.get(doc.get(doc.root().unwrap()).as_dict().unwrap().reference(b"Pages").unwrap());
|
||||
let tree = tree.as_dict().unwrap();
|
||||
assert_eq!(tree.get(b"Kids").and_then(|k| k.as_array()).map(|a| a.len()), Some(40_001));
|
||||
assert_eq!(tree.int(b"Count"), Some(40_001));
|
||||
assert!(took < std::time::Duration::from_secs(30), "{took:?}");
|
||||
// Blank documents and pages made from images keep their pages, in order.
|
||||
let doc = reopen(&blank(200.0, 300.0, 3).unwrap());
|
||||
assert_eq!(pages(&doc).len(), 3);
|
||||
let doc = reopen(&from_images(&[("a.png".into(), png_bytes(false)), ("b.png".into(), png_bytes(true))]).unwrap());
|
||||
assert_eq!(pages(&doc).len(), 2);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn text_keeps_leading_spaces_and_tabs() {
|
||||
let doc = reopen(&from_text("t", " indented\n\ttabbed\nplain", LETTER, 11.0).unwrap());
|
||||
@@ -2234,6 +2255,260 @@ fn jbig2_globals_are_decoded_within_a_limit_of_their_own() {
|
||||
}
|
||||
}
|
||||
|
||||
/// One allowance for all the images of an export: an image past it is left out, saying so.
|
||||
#[test]
|
||||
fn jbig2_images_past_the_exports_allowance_are_left_out_with_the_reason() {
|
||||
use pdfcraft_cos::{Dict, Document, ImageBudget, Object, Stream};
|
||||
let mut dict = Dict::new();
|
||||
dict.set(b"Subtype".to_vec(), Object::name("Image"));
|
||||
dict.set(b"Width".to_vec(), Object::Int(16));
|
||||
dict.set(b"Height".to_vec(), Object::Int(2));
|
||||
dict.set(b"BitsPerComponent".to_vec(), Object::Int(1));
|
||||
dict.set(b"ColorSpace".to_vec(), Object::name("DeviceGray"));
|
||||
dict.set(b"Filter".to_vec(), Object::name("JBIG2Decode"));
|
||||
let image = Stream::from_raw(dict, pdfcraft_filters::encode_jbig2_generic(&[0xFF; 4], 16, 2).unwrap());
|
||||
let mut cost = ImageBudget::with_work(u64::MAX);
|
||||
cost.decode(&Document::new_empty(), &image, 1 << 20).unwrap();
|
||||
let cost = u64::MAX - cost.work_left();
|
||||
|
||||
let pdf = b"%PDF-1.7\n1 0 obj << /Type /Catalog /Pages 2 0 R >> endobj\n2 0 obj << /Type /Pages /Kids [3 0 R] /Count 1 >> endobj\n3 0 obj << /Type /Page /Parent 2 0 R /MediaBox [0 0 100 100] >> endobj\ntrailer << /Root 1 0 R >>\n%%EOF".to_vec();
|
||||
let mut doc = Document::open(std::sync::Arc::new(pdf)).unwrap();
|
||||
let (a, b) = (doc.add(Object::Stream(image.clone())), doc.add(Object::Stream(image)));
|
||||
let mut xobjects = Dict::new();
|
||||
xobjects.set(b"A".to_vec(), Object::Ref(a));
|
||||
xobjects.set(b"B".to_vec(), Object::Ref(b));
|
||||
let mut resources = Dict::new();
|
||||
resources.set(b"XObject".to_vec(), Object::Dict(xobjects));
|
||||
let page = pdfcraft_model::pages(&doc).swap_remove(0).obj;
|
||||
doc.update_dict(page, |p| p.set(b"Resources".to_vec(), Object::Dict(resources))).unwrap();
|
||||
|
||||
let export = crate::extract::extract_images_within(&doc, &[0], 1, &mut ImageBudget::with_work(cost), usize::MAX);
|
||||
assert_eq!(export.images.len(), 1);
|
||||
assert_eq!(export.skipped.len(), 1);
|
||||
assert!(export.skipped[0].2.contains("more image decoding than"), "{:?}", export.skipped);
|
||||
// What an export holds is bounded too: the files are all in memory until it ends.
|
||||
let export = crate::extract::extract_images_within(&doc, &[0], 1, &mut ImageBudget::with_work(u64::MAX), 1);
|
||||
assert_eq!(export.images.len(), 1, "the first goes past it");
|
||||
assert_eq!(export.skipped.len(), 1);
|
||||
assert!(export.skipped[0].2.contains("than one export can hold"), "{:?}", export.skipped);
|
||||
// A file of many images shares one allowance too, image by image.
|
||||
let mut budget = ImageBudget::with_work(cost);
|
||||
assert!(crate::extract::image_file_within(&doc, a, &mut budget).is_ok());
|
||||
assert!(crate::extract::image_file_within(&doc, b, &mut budget).is_err());
|
||||
}
|
||||
|
||||
/// An image that isn't JBIG2 shares the allowance too: a file of filter bombs would hold an export
|
||||
/// as long as one of JBIG2. What isn't decoded here, a JPEG, is still exported.
|
||||
#[test]
|
||||
fn flate_images_past_the_exports_allowance_are_left_out_with_the_reason() {
|
||||
use pdfcraft_cos::{Dict, Document, ImageBudget, Object, Stream};
|
||||
let image = |filter: &str, raw: Vec<u8>| {
|
||||
let mut dict = Dict::new();
|
||||
dict.set(b"Subtype".to_vec(), Object::name("Image"));
|
||||
dict.set(b"Width".to_vec(), Object::Int(2));
|
||||
dict.set(b"Height".to_vec(), Object::Int(2));
|
||||
dict.set(b"BitsPerComponent".to_vec(), Object::Int(8));
|
||||
dict.set(b"ColorSpace".to_vec(), Object::name("DeviceGray"));
|
||||
dict.set(b"Filter".to_vec(), Object::name(filter));
|
||||
Stream::from_raw(dict, raw)
|
||||
};
|
||||
let flate = image("FlateDecode", pdfcraft_filters::encode_flate(&[0x80; 4]));
|
||||
let mut cost = ImageBudget::with_work(u64::MAX);
|
||||
cost.decode(&Document::new_empty(), &flate, 1 << 20).unwrap();
|
||||
let cost = u64::MAX - cost.work_left();
|
||||
|
||||
let mut doc = Document::new_empty();
|
||||
let (a, b) = (doc.add(Object::Stream(flate.clone())), doc.add(Object::Stream(flate)));
|
||||
let mut budget = ImageBudget::with_work(cost);
|
||||
assert!(crate::extract::image_file_within(&doc, a, &mut budget).is_ok());
|
||||
let refused = crate::extract::image_file_within(&doc, b, &mut budget).unwrap_err();
|
||||
assert!(refused.contains("more image decoding than"), "{refused}");
|
||||
assert_eq!(budget.refused(), 1);
|
||||
|
||||
let jpeg = image::RgbImage::from_pixel(2, 2, image::Rgb([9, 9, 9]));
|
||||
let mut bytes = Vec::new();
|
||||
jpeg.write_to(&mut std::io::Cursor::new(&mut bytes), image::ImageFormat::Jpeg).unwrap();
|
||||
let jpeg = doc.add(Object::Stream(image("DCTDecode", bytes)));
|
||||
assert!(crate::extract::image_file_within(&doc, jpeg, &mut budget).is_ok(), "nothing charged");
|
||||
assert_eq!(budget.refused(), 1);
|
||||
}
|
||||
|
||||
/// A JPEG is written as it is, at no cost, unless something means decoding it, here a mask: that
|
||||
/// pays for its samples, and past the allowance the image goes, with the reason, as it would come out without
|
||||
/// its transparency otherwise.
|
||||
#[test]
|
||||
fn a_jpeg_that_has_to_be_decoded_shares_the_allowance() {
|
||||
use pdfcraft_cos::{Dict, Document, ImageBudget, Object, Stream};
|
||||
let mut jpeg = Vec::new();
|
||||
image::RgbImage::from_pixel(4, 4, image::Rgb([9, 9, 9])).write_to(&mut std::io::Cursor::new(&mut jpeg), image::ImageFormat::Jpeg).unwrap();
|
||||
let image_dict = |extra: Option<(&[u8], Object)>| {
|
||||
let mut d = Dict::new();
|
||||
d.set(b"Subtype".to_vec(), Object::name("Image"));
|
||||
d.set(b"Width".to_vec(), Object::Int(4));
|
||||
d.set(b"Height".to_vec(), Object::Int(4));
|
||||
d.set(b"BitsPerComponent".to_vec(), Object::Int(8));
|
||||
d.set(b"ColorSpace".to_vec(), Object::name("DeviceRGB"));
|
||||
d.set(b"Filter".to_vec(), Object::name("DCTDecode"));
|
||||
if let Some((key, value)) = extra {
|
||||
d.set(key.to_vec(), value);
|
||||
}
|
||||
d
|
||||
};
|
||||
let mut doc = Document::new_empty();
|
||||
let mut mask = Dict::new();
|
||||
mask.set(b"Subtype".to_vec(), Object::name("Image"));
|
||||
mask.set(b"Width".to_vec(), Object::Int(4));
|
||||
mask.set(b"Height".to_vec(), Object::Int(4));
|
||||
mask.set(b"BitsPerComponent".to_vec(), Object::Int(8));
|
||||
mask.set(b"ColorSpace".to_vec(), Object::name("DeviceGray"));
|
||||
let mask = doc.add(Object::Stream(Stream::from_raw(mask, vec![0x80; 16])));
|
||||
let doc_jpeg_len = jpeg.len();
|
||||
let masked = doc.add(Object::Stream(Stream::from_raw(image_dict(Some((b"SMask", Object::Ref(mask)))), jpeg.clone())));
|
||||
let plain = doc.add(Object::Stream(Stream::from_raw(image_dict(None), jpeg)));
|
||||
|
||||
let mut budget = ImageBudget::with_work(0);
|
||||
assert!(crate::extract::image_file_within(&doc, plain, &mut budget).is_ok(), "written as it is");
|
||||
assert_eq!(budget.refused(), 0);
|
||||
let mut budget = ImageBudget::with_work(u64::MAX);
|
||||
assert!(crate::extract::image_file_within(&doc, masked, &mut budget).is_ok());
|
||||
let cost = u64::MAX - budget.work_left();
|
||||
let read = 4 * doc_jpeg_len as u64;
|
||||
assert_eq!(cost, 16 + 16 + 2 * 4 * 4 * 3 + read, "the mask's bytes and pixels, the JPEG's samples twice and its reading");
|
||||
let mut budget = ImageBudget::with_work(cost - 1);
|
||||
let refused = crate::extract::image_file_within(&doc, masked, &mut budget).unwrap_err();
|
||||
assert!(refused.contains("more image decoding than"), "{refused}");
|
||||
assert_eq!(budget.refused(), 1);
|
||||
}
|
||||
|
||||
/// A JPEG that is itself a mask pays for its samples, each time an image reads it: images can
|
||||
/// share one, and only the images are ever seen once.
|
||||
#[test]
|
||||
fn a_jpeg_mask_pays_for_its_samples() {
|
||||
use pdfcraft_cos::{Dict, Document, ImageBudget, Object, Stream};
|
||||
let mut jpeg = Vec::new();
|
||||
image::GrayImage::from_pixel(4, 4, image::Luma([90])).write_to(&mut std::io::Cursor::new(&mut jpeg), image::ImageFormat::Jpeg).unwrap();
|
||||
let mut mask = Dict::new();
|
||||
mask.set(b"Subtype".to_vec(), Object::name("Image"));
|
||||
mask.set(b"Width".to_vec(), Object::Int(4));
|
||||
mask.set(b"Height".to_vec(), Object::Int(4));
|
||||
mask.set(b"BitsPerComponent".to_vec(), Object::Int(8));
|
||||
mask.set(b"ColorSpace".to_vec(), Object::name("DeviceGray"));
|
||||
mask.set(b"Filter".to_vec(), Object::name("DCTDecode"));
|
||||
let mut doc = Document::new_empty();
|
||||
let read = 4 * jpeg.len() as u64;
|
||||
let mask = doc.add(Object::Stream(Stream::from_raw(mask, jpeg)));
|
||||
let mut image = Dict::new();
|
||||
image.set(b"Subtype".to_vec(), Object::name("Image"));
|
||||
image.set(b"Width".to_vec(), Object::Int(1));
|
||||
image.set(b"Height".to_vec(), Object::Int(1));
|
||||
image.set(b"BitsPerComponent".to_vec(), Object::Int(8));
|
||||
image.set(b"ColorSpace".to_vec(), Object::name("DeviceGray"));
|
||||
image.set(b"SMask".to_vec(), Object::Ref(mask));
|
||||
let image = doc.add(Object::Stream(Stream::from_raw(image, vec![0x80])));
|
||||
let mut budget = ImageBudget::with_work(u64::MAX);
|
||||
assert!(crate::extract::image_file_within(&doc, image, &mut budget).is_ok());
|
||||
assert_eq!(u64::MAX - budget.work_left(), 2 * 4 * 4 + read + 2, "its samples twice, its reading, and the image's byte and pixel");
|
||||
// Just short of what the mask costs: it isn't decoded, and takes the image with it.
|
||||
let mut budget = ImageBudget::with_work(2 * 4 * 4 + read - 1);
|
||||
let refused = crate::extract::image_file_within(&doc, image, &mut budget).unwrap_err();
|
||||
assert!(refused.contains("more image decoding than"), "{refused}");
|
||||
assert_eq!((budget.work_left(), budget.refused()), (0, 1));
|
||||
}
|
||||
|
||||
/// What decoding a JPEG takes goes by its header, so that is what has to agree with the
|
||||
/// dictionary before it is decoded: one image of a pixel can hold a page of 500 megapixels. The
|
||||
/// file comes out as it is either way, so what shows is whether it was decoded.
|
||||
#[test]
|
||||
fn a_jpeg_larger_than_its_dictionary_says_isnt_decoded() {
|
||||
use pdfcraft_cos::{Dict, Document, ImageBudget, Object, Stream};
|
||||
let mut jpeg = Vec::new();
|
||||
image::RgbImage::from_pixel(4, 4, image::Rgb([9, 9, 9])).write_to(&mut std::io::Cursor::new(&mut jpeg), image::ImageFormat::Jpeg).unwrap();
|
||||
// A colour key means decoding it, to find the pixels it hides.
|
||||
let keyed = |side: i64| {
|
||||
let mut d = Dict::new();
|
||||
d.set(b"Subtype".to_vec(), Object::name("Image"));
|
||||
d.set(b"Width".to_vec(), Object::Int(side));
|
||||
d.set(b"Height".to_vec(), Object::Int(side));
|
||||
d.set(b"BitsPerComponent".to_vec(), Object::Int(8));
|
||||
d.set(b"ColorSpace".to_vec(), Object::name("DeviceRGB"));
|
||||
d.set(b"Filter".to_vec(), Object::name("DCTDecode"));
|
||||
d.set(b"Mask".to_vec(), Object::Array(vec![Object::Int(0); 6]));
|
||||
Stream::from_raw(d, jpeg.clone())
|
||||
};
|
||||
let decodes = |doc: &Document, image: pdfcraft_cos::ObjRef| {
|
||||
crate::extract::JPEGS_DECODED.with(|n| n.set(0));
|
||||
assert!(crate::extract::image_file_within(doc, image, &mut ImageBudget::with_work(u64::MAX)).is_ok());
|
||||
crate::extract::JPEGS_DECODED.with(std::cell::Cell::get)
|
||||
};
|
||||
let mut doc = Document::new_empty();
|
||||
let (honest, lying) = (doc.add(Object::Stream(keyed(4))), doc.add(Object::Stream(keyed(1))));
|
||||
assert_eq!(decodes(&doc, honest), 1);
|
||||
assert_eq!(decodes(&doc, lying), 0);
|
||||
// The same as a mask: read as none, without being decoded.
|
||||
let mut mask = keyed(1);
|
||||
mask.dict.remove(b"Mask");
|
||||
let mask = doc.add(Object::Stream(mask));
|
||||
let mut image = Dict::new();
|
||||
image.set(b"Subtype".to_vec(), Object::name("Image"));
|
||||
image.set(b"Width".to_vec(), Object::Int(1));
|
||||
image.set(b"Height".to_vec(), Object::Int(1));
|
||||
image.set(b"BitsPerComponent".to_vec(), Object::Int(8));
|
||||
image.set(b"ColorSpace".to_vec(), Object::name("DeviceGray"));
|
||||
image.set(b"SMask".to_vec(), Object::Ref(mask));
|
||||
let image = doc.add(Object::Stream(Stream::from_raw(image, vec![0x80])));
|
||||
assert_eq!(decodes(&doc, image), 0);
|
||||
// Reading the header to find that out is paid for: a mask can be mostly tables, shared by
|
||||
// every image of a file, and with nothing left it isn't read.
|
||||
let mut budget = ImageBudget::with_work(u64::MAX);
|
||||
assert!(crate::extract::image_file_within(&doc, image, &mut budget).is_ok());
|
||||
assert_eq!(u64::MAX - budget.work_left(), 2 + 4 * jpeg.len() as u64 + 2, "its one declared sample twice, its bytes, the image's byte and pixel");
|
||||
let mut budget = ImageBudget::with_work(0);
|
||||
assert!(crate::extract::image_file_within(&doc, image, &mut budget).is_err());
|
||||
assert_eq!(budget.refused(), 1, "the image goes, with its mask unread");
|
||||
}
|
||||
|
||||
/// A mask past the allowance can't be left out as an unreadable one is, or the image comes out
|
||||
/// opaque, showing what the mask hides: the image goes, with the reason.
|
||||
#[test]
|
||||
fn an_image_whose_jbig2_mask_is_past_the_allowance_is_left_out() {
|
||||
use pdfcraft_cos::{Dict, Document, ImageBudget, Object, Stream};
|
||||
let mut mask = Dict::new();
|
||||
mask.set(b"Subtype".to_vec(), Object::name("Image"));
|
||||
mask.set(b"Width".to_vec(), Object::Int(16));
|
||||
mask.set(b"Height".to_vec(), Object::Int(2));
|
||||
mask.set(b"BitsPerComponent".to_vec(), Object::Int(1));
|
||||
mask.set(b"ColorSpace".to_vec(), Object::name("DeviceGray"));
|
||||
mask.set(b"Filter".to_vec(), Object::name("JBIG2Decode"));
|
||||
let mut doc = Document::new_empty();
|
||||
let mask = doc.add(Object::Stream(Stream::from_raw(mask, pdfcraft_filters::encode_jbig2_generic(&[0xFF; 4], 16, 2).unwrap())));
|
||||
// A JPEG, read for nothing until its mask is, so only the mask can be what stops it.
|
||||
let mut jpeg = Vec::new();
|
||||
image::RgbImage::from_pixel(1, 1, image::Rgb([9, 9, 9])).write_to(&mut std::io::Cursor::new(&mut jpeg), image::ImageFormat::Jpeg).unwrap();
|
||||
let mut image = Dict::new();
|
||||
image.set(b"Subtype".to_vec(), Object::name("Image"));
|
||||
image.set(b"Width".to_vec(), Object::Int(1));
|
||||
image.set(b"Height".to_vec(), Object::Int(1));
|
||||
image.set(b"BitsPerComponent".to_vec(), Object::Int(8));
|
||||
image.set(b"ColorSpace".to_vec(), Object::name("DeviceRGB"));
|
||||
image.set(b"Filter".to_vec(), Object::name("DCTDecode"));
|
||||
image.set(b"SMask".to_vec(), Object::Ref(mask));
|
||||
let image = doc.add(Object::Stream(Stream::from_raw(image, jpeg)));
|
||||
assert!(crate::extract::image_file_within(&doc, image, &mut ImageBudget::with_work(u64::MAX)).is_ok());
|
||||
let refused = crate::extract::image_file_within(&doc, image, &mut ImageBudget::with_work(0)).unwrap_err();
|
||||
assert!(refused.contains("more image decoding than"), "{refused}");
|
||||
}
|
||||
|
||||
/// A large honest file keeps its images: what an export may hold grows with the file past the fixed
|
||||
/// part, and a file too long to double doesn't wrap round to nothing.
|
||||
#[test]
|
||||
fn an_export_may_hold_twice_a_large_file() {
|
||||
let fixed = crate::extract::export_bytes(0);
|
||||
assert_eq!(fixed, 2 << 30);
|
||||
assert_eq!(crate::extract::export_bytes(fixed / 2), fixed);
|
||||
assert_eq!(crate::extract::export_bytes(fixed / 2 + 1), fixed + 2);
|
||||
assert_eq!(crate::extract::export_bytes(usize::MAX), usize::MAX);
|
||||
}
|
||||
|
||||
/// `/Decode` says which way round a stencil mask is, and its numbers can be given by reference. Read
|
||||
/// as absent, they gave the wrong answer, so the file came out a negative of what the page draws.
|
||||
#[test]
|
||||
|
||||
@@ -7,9 +7,25 @@ use super::place::{
|
||||
};
|
||||
use super::{Document, EditError, Object, added, backdrop, helvetica_width};
|
||||
|
||||
/// Commit one complete mark operation only after every selected page succeeds. The snapshot
|
||||
/// shares original bytes, cross-references, caches and unchanged objects; only the overlay table
|
||||
/// and document metadata are copied. Dropping a failed stage also drops removed marks, changed
|
||||
/// page/resources/backdrop dictionaries and new objects, including the allocation cursor.
|
||||
fn apply_mark_transaction(doc: &mut Document, apply: impl FnOnce(&mut Document) -> Result<(), EditError>) -> Result<(), EditError> {
|
||||
let mut staged = doc.clone();
|
||||
apply(&mut staged)?;
|
||||
*doc = staged;
|
||||
Ok(())
|
||||
}
|
||||
|
||||
/// Add a header and footer to `pages` (0-based). With `replace`, existing headers and footers on
|
||||
/// those pages are removed first (Acrobat's Replace Existing).
|
||||
/// those pages are removed first (Acrobat's Replace Existing). The whole call is atomic:
|
||||
/// on error, the document (including earlier selected pages) is unchanged.
|
||||
pub fn add_header_footer(doc: &mut Document, pages: &[usize], hf: &HeaderFooter, replace: bool, cx: &Context) -> Result<(), EditError> {
|
||||
apply_mark_transaction(doc, |staged| add_header_footer_in_place(staged, pages, hf, replace, cx))
|
||||
}
|
||||
|
||||
fn add_header_footer_in_place(doc: &mut Document, pages: &[usize], hf: &HeaderFooter, replace: bool, cx: &Context) -> Result<(), EditError> {
|
||||
let all = page_list(doc);
|
||||
check(pages, all.len())?;
|
||||
if hf.text.iter().all(|t| t.trim().is_empty()) {
|
||||
@@ -121,8 +137,13 @@ pub fn add_header_footer(doc: &mut Document, pages: &[usize], hf: &HeaderFooter,
|
||||
Ok(())
|
||||
}
|
||||
|
||||
/// Add a text watermark to `pages`.
|
||||
/// Add a text or picture watermark to `pages`. All selected pages, including mark replacement,
|
||||
/// form one transaction; on error, the document is unchanged.
|
||||
pub fn add_watermark(doc: &mut Document, pages: &[usize], wm: &Watermark, replace: bool) -> Result<(), EditError> {
|
||||
apply_mark_transaction(doc, |staged| add_watermark_in_place(staged, pages, wm, replace))
|
||||
}
|
||||
|
||||
fn add_watermark_in_place(doc: &mut Document, pages: &[usize], wm: &Watermark, replace: bool) -> Result<(), EditError> {
|
||||
let all = page_list(doc);
|
||||
check(pages, all.len())?;
|
||||
let text = wm.text.trim();
|
||||
@@ -201,8 +222,13 @@ pub fn add_watermark(doc: &mut Document, pages: &[usize], wm: &Watermark, replac
|
||||
|
||||
/// Add a solid-colour background behind the content of `pages`. With `bg.replace_backdrop`, a
|
||||
/// white backdrop a page paints itself is replaced first, so the background shows (see
|
||||
/// [`backdrop`]); a picture backdrop (a scan) still hides it.
|
||||
/// [`backdrop`]); a picture backdrop (a scan) still hides it. All selected pages, including
|
||||
/// replacement and backdrop edits, form one transaction; on error, the document is unchanged.
|
||||
pub fn add_background(doc: &mut Document, pages: &[usize], bg: &Background, replace: bool) -> Result<(), EditError> {
|
||||
apply_mark_transaction(doc, |staged| add_background_in_place(staged, pages, bg, replace))
|
||||
}
|
||||
|
||||
fn add_background_in_place(doc: &mut Document, pages: &[usize], bg: &Background, replace: bool) -> Result<(), EditError> {
|
||||
let all = page_list(doc);
|
||||
check(pages, all.len())?;
|
||||
if replace {
|
||||
|
||||
@@ -98,8 +98,13 @@ pub fn page_background(doc: &Document, page: usize) -> Result<Option<Rgb>, EditE
|
||||
}
|
||||
b"sc" | b"scn" => st.fill = colour(st.space, op),
|
||||
b"gs" => {
|
||||
if let Some(g) = op.name(0).and_then(|n| gstates.get(n)).map(|g| doc.resolve(g)).and_then(|g| g.as_dict().cloned()) {
|
||||
apply_gstate(doc, &g, &mut st);
|
||||
let mut held = None;
|
||||
let gstate = match op.name(0).and_then(|n| gstates.get(n)) {
|
||||
Some(g) => crate::text::dict_in_place(doc, g, &mut held),
|
||||
None => None,
|
||||
};
|
||||
if let Some(g) = gstate {
|
||||
apply_gstate(doc, g, &mut st);
|
||||
}
|
||||
}
|
||||
b"re" => match op.nums::<4>() {
|
||||
|
||||
+17
-13
@@ -379,34 +379,34 @@ pub fn reading_images(doc: &Document, page: usize) -> Result<Vec<PageImage>, Edi
|
||||
forms: &mut Forms,
|
||||
out: &mut Vec<PageImage>,
|
||||
) -> Result<(), EditError> {
|
||||
let xo = resources.get(b"XObject").map(|x| doc.resolve(x)).and_then(|x| x.as_dict().cloned()).unwrap_or_default();
|
||||
let mut held = None;
|
||||
let xo = crate::text::resource_dict(doc, resources, b"XObject", &mut held);
|
||||
for (i, op) in ops.iter().enumerate() {
|
||||
st.apply(op)?;
|
||||
let ctm = st.placement.matrix;
|
||||
if op.is("Do") {
|
||||
let Some(name) = op.name(0) else { continue };
|
||||
let drawn = xo.and_then(|xo| xo.get(name));
|
||||
if let Some(form) = crate::text::form_call(doc, resources, name, ctm, &forms.path, &mut forms.budget) {
|
||||
if let Some(r) = form.obj {
|
||||
forms.path.push(r);
|
||||
}
|
||||
let bounds =
|
||||
xo.get(name).map(|o| doc.resolve(o)).and_then(|o| o.as_dict().and_then(|d| d.get(b"BBox")).map(|b| doc.resolve(b))).and_then(
|
||||
|b| {
|
||||
let a = b.as_array()?;
|
||||
let [x0, y0, x1, y1] = a.as_slice() else { return None };
|
||||
Some(form.ctm.bbox([x0.as_f64()?, y0.as_f64()?, x1.as_f64()?, y1.as_f64()?]))
|
||||
},
|
||||
);
|
||||
drawn.map(|o| doc.resolve(o)).and_then(|o| o.as_dict().and_then(|d| d.get(b"BBox")).map(|b| doc.resolve(b))).and_then(|b| {
|
||||
let a = b.as_array()?;
|
||||
let [x0, y0, x1, y1] = a.as_slice() else { return None };
|
||||
Some(form.ctm.bbox([x0.as_f64()?, y0.as_f64()?, x1.as_f64()?, y1.as_f64()?]))
|
||||
});
|
||||
let clip = bounds.map_or(st.placement.clip, |b| intersection(st.placement.clip, b).unwrap_or([0.0; 4]));
|
||||
let mut inner = ImageState::new(form.ctm, clip, st.placement.clips.clone());
|
||||
let piece = stream(op);
|
||||
walk(doc, &parse(&form.data).ops, &form.resources, &mut inner, &|_| piece, forms, out)?;
|
||||
walk(doc, &parse(&form.data).ops, form.resources(resources), &mut inner, &|_| piece, forms, out)?;
|
||||
if form.obj.is_some() {
|
||||
forms.path.pop();
|
||||
}
|
||||
continue;
|
||||
}
|
||||
let Some(r) = xo.get(name).and_then(Object::as_ref) else { continue };
|
||||
let Some(r) = drawn.and_then(Object::as_ref) else { continue };
|
||||
let obj = doc.get(r);
|
||||
let Object::Stream(s) = &*obj else { continue };
|
||||
if s.dict.name(b"Subtype") != Some(b"Image") {
|
||||
@@ -584,6 +584,10 @@ fn sequence_end(ops: &[Op], i: usize, end: usize, opens: &[&str], close: &str) -
|
||||
end
|
||||
}
|
||||
|
||||
/// The stacking units of `ops[scan_start..scan_end]` that Arrange moves past one another, in
|
||||
/// paint order: a `q … Q`, `BT … ET` or marked-content sequence up to its matching close (or the
|
||||
/// end of the scan), a single `Do`, `sh` or inline image, or a run of other operators that ends
|
||||
/// at a path-painting operator or before the next unit. Units that paint nothing are left out.
|
||||
pub(crate) fn content_units(ops: &[Op], scan_start: usize, scan_end: usize) -> Vec<std::ops::Range<usize>> {
|
||||
let mut units = Vec::new();
|
||||
let mut i = scan_start;
|
||||
@@ -598,9 +602,9 @@ pub(crate) fn content_units(ops: &[Op], scan_start: usize, scan_end: usize) -> V
|
||||
sequence_end(ops, i, scan_end, &["q"], "Q")
|
||||
} else if op.is("BT") {
|
||||
sequence_end(ops, i, scan_end, &[], "ET")
|
||||
} else if op.is("BI") {
|
||||
sequence_end(ops, i, scan_end, &[], "EI")
|
||||
} else if op.is("Do") || op.is("sh") {
|
||||
} else if op.is("BI") || op.is("Do") || op.is("sh") {
|
||||
// The parser emits a whole inline image (`BI` … `ID` … `EI`) as one `BI` op, so it is a
|
||||
// unit of its own (#3146).
|
||||
i.saturating_add(1)
|
||||
} else {
|
||||
let mut j = i;
|
||||
|
||||
@@ -1,6 +1,11 @@
|
||||
//! pdfcraft-edit — page content editing (L4). Today: page marks, Acrobat's Header & footer,
|
||||
//! Watermark, Background and Bates numbering (execution plan M7.6).
|
||||
//!
|
||||
//! **Atomic page-mark operations.** Adding or replacing headers/footers, watermarks and backgrounds
|
||||
//! stages the whole call on a document snapshot and commits only after every selected page succeeds.
|
||||
//! An error preserves existing marks, content, resources, pending edits and allocated objects. The
|
||||
//! snapshot shares original PDF bytes and unchanged objects; it copies the overlay table and metadata.
|
||||
//!
|
||||
//! **How marks are stored.** Each mark is one content stream appended to (or, for content behind
|
||||
//! the page, inserted after the backgrounds at the start of) the page's `/Contents`, drawn in
|
||||
//! display space (after `/Rotate`) and wrapped in a marked-content artifact (§14.8.2.2) so
|
||||
|
||||
@@ -0,0 +1,211 @@
|
||||
//! The public mark APIs either commit the complete operation or leave the document untouched.
|
||||
use super::{cx, fixture, reopen, streams};
|
||||
use crate::place::MARK_PLACEMENT_FAILURE;
|
||||
use crate::*;
|
||||
use pdfcraft_cos::{ObjRef, SaveOptions, write_incremental};
|
||||
|
||||
const SELECTED: &[usize] = &[0, 1, 2];
|
||||
|
||||
struct PlacementFailure;
|
||||
|
||||
impl PlacementFailure {
|
||||
fn after_two_pages(kind: MarkKind) -> Self {
|
||||
MARK_PLACEMENT_FAILURE.with(|failure| {
|
||||
assert!(failure.get().is_none());
|
||||
failure.set(Some((kind, 2, 0)));
|
||||
});
|
||||
Self
|
||||
}
|
||||
|
||||
fn completed(&self) -> usize {
|
||||
MARK_PLACEMENT_FAILURE.with(|failure| failure.get().unwrap().2)
|
||||
}
|
||||
}
|
||||
|
||||
impl Drop for PlacementFailure {
|
||||
fn drop(&mut self) {
|
||||
MARK_PLACEMENT_FAILURE.with(|failure| failure.set(None));
|
||||
}
|
||||
}
|
||||
|
||||
/// Four pages share an original stream and resources, both inherited and directly referenced.
|
||||
/// All have all three existing marks, including a picture background with a replaced white fill.
|
||||
fn marked_document() -> (Document, MarkSource) {
|
||||
let mut doc = fixture();
|
||||
let parent = ObjRef::new(2, 0);
|
||||
let extra = doc.add(Object::Dict(Dict::from_iter([
|
||||
(b"Type".to_vec(), Object::name("Page")),
|
||||
(b"Parent".to_vec(), Object::Ref(parent)),
|
||||
(b"Contents".to_vec(), Object::Ref(ObjRef::new(7, 0))),
|
||||
])));
|
||||
doc.update_dict(parent, |d| {
|
||||
d.set(b"Kids".to_vec(), Object::Array([3, 4, 5].map(|n| Object::Ref(ObjRef::new(n, 0))).into_iter().chain([Object::Ref(extra)]).collect()));
|
||||
d.set(b"Count".to_vec(), Object::Int(4));
|
||||
})
|
||||
.unwrap();
|
||||
doc.set(ObjRef::new(7, 0), Object::Stream(Stream::from_raw(Dict::new(), b"1 g 0 0 600 800 re f 0 g BT /F1 9 Tf (Original page) Tj ET".to_vec())));
|
||||
let picture = |doc: &mut Document, gray| {
|
||||
let image = doc.add(Object::Stream(Stream::from_raw(
|
||||
Dict::from_iter([
|
||||
(b"Type".to_vec(), Object::name("XObject")),
|
||||
(b"Subtype".to_vec(), Object::name("Image")),
|
||||
(b"Width".to_vec(), Object::Int(1)),
|
||||
(b"Height".to_vec(), Object::Int(1)),
|
||||
(b"ColorSpace".to_vec(), Object::name("DeviceGray")),
|
||||
(b"BitsPerComponent".to_vec(), Object::Int(8)),
|
||||
]),
|
||||
vec![gray],
|
||||
)));
|
||||
MarkSource { xobject: image, size: (1.0, 1.0), image: true }
|
||||
};
|
||||
let old_picture = picture(&mut doc, 170);
|
||||
let replacement_picture = picture(&mut doc, 80);
|
||||
let all = [0, 1, 2, 3];
|
||||
let hf = HeaderFooter {
|
||||
text: ["Old header".into(), String::new(), String::new(), String::new(), String::new(), String::new()],
|
||||
font: added::Family::Times,
|
||||
..Default::default()
|
||||
};
|
||||
add_header_footer(&mut doc, &all, &hf, false, &cx()).unwrap();
|
||||
add_watermark(&mut doc, &all, &Watermark { text: "Old watermark".into(), opacity: 0.45, ..Default::default() }, false).unwrap();
|
||||
add_background(&mut doc, &all, &Background { source: Some(old_picture), opacity: 0.6, replace_backdrop: true, ..Default::default() }, false)
|
||||
.unwrap();
|
||||
let pages = page_list(&doc);
|
||||
let shared = ObjRef::new(6, 0);
|
||||
let resources = (*doc.resolve(pages[0].dict.get(b"Resources").unwrap())).clone();
|
||||
doc.set(shared, resources);
|
||||
for (i, page) in pages.iter().enumerate() {
|
||||
doc.update_dict(page.obj, |d| {
|
||||
if i % 2 == 0 {
|
||||
d.set(b"Resources".to_vec(), Object::Ref(shared));
|
||||
} else {
|
||||
d.remove(b"Resources");
|
||||
}
|
||||
})
|
||||
.unwrap();
|
||||
}
|
||||
let doc = reopen(&doc);
|
||||
assert!(!doc.is_modified());
|
||||
let pages = page_list(&doc);
|
||||
assert_eq!(pages.len(), 4);
|
||||
assert!(doc.get(pages[1].obj).as_dict().unwrap().get(b"Resources").is_none(), "a selected page inherits its resources");
|
||||
assert_eq!(pages[0].dict.get(b"Resources").and_then(Object::as_ref), Some(shared));
|
||||
assert_eq!(pages[2].dict.get(b"Resources").and_then(Object::as_ref), Some(shared));
|
||||
for i in 0..4 {
|
||||
for kind in [MarkKind::HeaderFooter, MarkKind::Watermark, MarkKind::Background] {
|
||||
assert_eq!(mark_streams(&doc, i, kind).len(), 1, "page {i} has existing {kind:?}");
|
||||
}
|
||||
}
|
||||
(doc, replacement_picture)
|
||||
}
|
||||
|
||||
fn mark_streams(doc: &Document, page: usize, kind: MarkKind) -> Vec<String> {
|
||||
streams(doc, page).into_iter().filter(|s| s.contains(&format!("/PCMark /{}", kind.tag()))).collect()
|
||||
}
|
||||
|
||||
fn apply_replacement(doc: &mut Document, kind: MarkKind, source: MarkSource, replace: bool) -> Result<(), EditError> {
|
||||
match kind {
|
||||
MarkKind::HeaderFooter => add_header_footer(
|
||||
doc,
|
||||
SELECTED,
|
||||
&HeaderFooter {
|
||||
text: ["New header".into(), String::new(), String::new(), String::new(), String::new(), String::new()],
|
||||
font: added::Family::Courier,
|
||||
shrink: true,
|
||||
..Default::default()
|
||||
},
|
||||
replace,
|
||||
&cx(),
|
||||
),
|
||||
MarkKind::Watermark => add_watermark(doc, SELECTED, &Watermark { source: Some(source), opacity: 0.25, ..Default::default() }, replace),
|
||||
MarkKind::Background => {
|
||||
add_background(doc, SELECTED, &Background { color: [0.1, 0.3, 0.7], replace_backdrop: true, ..Default::default() }, replace)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
fn unchanged_after_later_page_failure(kind: MarkKind) {
|
||||
// Replacement and addition share the same operation boundary; exercise replacement first.
|
||||
for (replace, pending_edit) in [(true, false), (true, true), (false, false), (false, true)] {
|
||||
let (mut doc, source) = marked_document();
|
||||
if pending_edit {
|
||||
let pending = doc.add(Object::String(pdfcraft_cos::PdfString::literal(b"unsaved caller edit".to_vec())));
|
||||
doc.update_dict(page_list(&doc)[0].obj, |d| d.set(b"CallerEdit".to_vec(), Object::Ref(pending))).unwrap();
|
||||
}
|
||||
let modified = doc.is_modified();
|
||||
let before = write_incremental(&doc, &SaveOptions::default()).unwrap();
|
||||
let objects = doc.object_numbers().len();
|
||||
let mut allocation_probe = doc.clone();
|
||||
let next_object = allocation_probe.add(Object::Null);
|
||||
let failure = PlacementFailure::after_two_pages(kind);
|
||||
let result = apply_replacement(&mut doc, kind, source, replace);
|
||||
assert_eq!(result, Err(EditError::Invalid("injected mark placement failure".into())));
|
||||
assert_eq!(failure.completed(), 2, "the error followed two real page placements");
|
||||
assert_eq!(doc.object_numbers().len(), objects, "{kind:?}, replace={replace}: no allocated objects remain");
|
||||
assert_eq!(doc.is_modified(), modified, "{kind:?}, replace={replace}: the dirty state is preserved");
|
||||
assert!(write_incremental(&doc, &SaveOptions::default()).unwrap() == before, "{kind:?}, replace={replace}: every byte stays unchanged");
|
||||
assert_eq!(doc.add(Object::Null), next_object, "the allocation cursor is unchanged too");
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn header_footer_changes_are_atomic_after_a_later_page_failure() {
|
||||
unchanged_after_later_page_failure(MarkKind::HeaderFooter);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn watermark_changes_are_atomic_after_a_later_page_failure() {
|
||||
unchanged_after_later_page_failure(MarkKind::Watermark);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn background_changes_are_atomic_after_a_later_page_failure() {
|
||||
unchanged_after_later_page_failure(MarkKind::Background);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn replacements_commit_all_selected_pages_and_preserve_other_marks_and_shared_resources() {
|
||||
for kind in [MarkKind::HeaderFooter, MarkKind::Watermark, MarkKind::Background] {
|
||||
let (mut doc, source) = marked_document();
|
||||
let before = doc.clone();
|
||||
let expected = match kind {
|
||||
MarkKind::HeaderFooter => "(New header)".to_string(),
|
||||
MarkKind::Watermark => format!("/PCPic{} Do", source.xobject.num),
|
||||
MarkKind::Background => "0.1 0.3 0.7 rg".to_string(),
|
||||
};
|
||||
apply_replacement(&mut doc, kind, source, true).unwrap();
|
||||
let doc = reopen(&doc);
|
||||
assert_eq!(streams(&doc, 3), streams(&before, 3), "the unselected page keeps its content");
|
||||
let unselected = page_list(&before)[3].obj;
|
||||
assert_eq!(doc.get(unselected), before.get(unselected), "the unselected page keeps its resources and entries");
|
||||
for reference in [ObjRef::new(6, 0), ObjRef::new(7, 0)] {
|
||||
assert_eq!(
|
||||
format!("{:?}", doc.get(reference)),
|
||||
format!("{:?}", before.get(reference)),
|
||||
"shared resources and original content stay unchanged"
|
||||
);
|
||||
}
|
||||
for page in SELECTED {
|
||||
let marks = mark_streams(&doc, *page, kind);
|
||||
assert_eq!(marks.len(), 1, "one replacement on selected page {page}");
|
||||
assert!(marks[0].contains(&expected), "the new mark is present: {}", marks[0]);
|
||||
let old_page = &page_list(&before)[*page];
|
||||
let new_page = &page_list(&doc)[*page];
|
||||
let old_resources = before.resolve(old_page.dict.get(b"Resources").unwrap());
|
||||
let new_resources = doc.resolve(new_page.dict.get(b"Resources").unwrap());
|
||||
for category in [&b"Font"[..], &b"ExtGState"[..], &b"XObject"[..]] {
|
||||
let old = before.resolve(old_resources.as_dict().unwrap().get(category).unwrap());
|
||||
let new = doc.resolve(new_resources.as_dict().unwrap().get(category).unwrap());
|
||||
for (name, value) in old.as_dict().unwrap().iter() {
|
||||
assert_eq!(new.as_dict().unwrap().get(name), Some(value), "old resources remain usable on page {page}");
|
||||
assert_eq!(doc.resolve(value), before.resolve(value), "referenced resource contents are unchanged on page {page}");
|
||||
}
|
||||
}
|
||||
for other in [MarkKind::HeaderFooter, MarkKind::Watermark, MarkKind::Background] {
|
||||
if other != kind {
|
||||
assert_eq!(mark_streams(&doc, *page, other), mark_streams(&before, *page, other), "unrelated {other:?} on page {page}");
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -286,7 +286,12 @@ pub fn expand(template: &str, page_number: u32, count: usize, bates: u64, cx: &C
|
||||
let digits = parts.get(1).and_then(|d| d.parse::<usize>().ok()).unwrap_or(6).clamp(1, 15);
|
||||
format!("{}{:0digits$}{}", parts.get(3).unwrap_or(&""), bates, parts.get(4).unwrap_or(&""))
|
||||
}
|
||||
_ => format!("<<{token}>>"),
|
||||
_ => {
|
||||
// Not a token: emit one `<` and retry, so a later token is still found.
|
||||
out.push('<');
|
||||
rest = &rest[start + 1..];
|
||||
continue;
|
||||
}
|
||||
};
|
||||
out.push_str(&value);
|
||||
rest = &after[end + 2..];
|
||||
@@ -302,3 +307,16 @@ pub(crate) fn bates_start(template: &str) -> Option<u64> {
|
||||
let t = &t[..t.find(">>")?];
|
||||
t.split('#').nth(2).and_then(|s| s.parse().ok()).or(Some(1))
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod expand_tests {
|
||||
use super::*;
|
||||
|
||||
#[test]
|
||||
fn expand_token_after_extra_angle_brackets() {
|
||||
let cx = Context::default();
|
||||
assert_eq!(expand("<<<1>>>", 3, 9, 1, &cx), "<3>");
|
||||
assert_eq!(expand("<< <<1>>", 3, 9, 1, &cx), "<< 3");
|
||||
assert_eq!(expand("<<x>> <<1>>", 3, 9, 1, &cx), "<<x>> 3");
|
||||
}
|
||||
}
|
||||
@@ -294,7 +294,32 @@ pub(crate) fn isolation(doc: &Document, list: &[Object]) -> Isolation {
|
||||
/// Put a mark's content on a page: behind (with the behind-marks at the start) or on top
|
||||
/// (appended, after wrapping the original content in q/Q).
|
||||
pub(crate) fn place(doc: &mut Document, page: &pdfcraft_model::Page, kind: MarkKind, content: Vec<u8>, behind: bool) -> Result<(), EditError> {
|
||||
place_tagged(doc, page, kind.tag(), content, behind).map(drop)
|
||||
place_tagged(doc, page, kind.tag(), content, behind)?;
|
||||
#[cfg(test)]
|
||||
fail_after_mark_placement(kind)?;
|
||||
Ok(())
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
thread_local! {
|
||||
/// Force an error after N completed placements of one kind, on this test thread only.
|
||||
pub(crate) static MARK_PLACEMENT_FAILURE: std::cell::Cell<Option<(MarkKind, usize, usize)>> = const { std::cell::Cell::new(None) };
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
fn fail_after_mark_placement(kind: MarkKind) -> Result<(), EditError> {
|
||||
MARK_PLACEMENT_FAILURE.with(|failure| {
|
||||
if let Some((target, after, completed)) = failure.get()
|
||||
&& target == kind
|
||||
{
|
||||
let completed = completed.saturating_add(1);
|
||||
failure.set(Some((target, after, completed)));
|
||||
if completed == after {
|
||||
return Err(EditError::Invalid("injected mark placement failure".into()));
|
||||
}
|
||||
}
|
||||
Ok(())
|
||||
})
|
||||
}
|
||||
|
||||
/// Put content on a page, tagged `tag` (see [`place`]). On top, whatever graphics state the
|
||||
|
||||
@@ -4,6 +4,9 @@ use pdfcraft_cos::{Document, SaveOptions, write_full, write_incremental};
|
||||
|
||||
use super::*;
|
||||
|
||||
#[path = "mark_transaction_tests.rs"]
|
||||
mod mark_transactions;
|
||||
|
||||
/// Three pages: an upright page with content that leaves the graphics state changed (an
|
||||
/// unbalanced `cm`), a page rotated 90° and one with inherited, shared resources.
|
||||
fn fixture() -> Document {
|
||||
@@ -5572,6 +5575,41 @@ fn reading_follows_form_xobjects() {
|
||||
assert!(own[0].is_form && own[0].object == Some(pdfcraft_cos::ObjRef::new(6, 0)), "{own:?}");
|
||||
}
|
||||
|
||||
/// A page's `/XObject` and a form's `/Resources` are read wherever they are stored, and a form with
|
||||
/// none of its own, or with something else there, uses the ones it was drawn with (PDF 1.1 files).
|
||||
/// Each of these pages shows one line of text and one picture through one form.
|
||||
#[test]
|
||||
fn reading_follows_forms_however_their_resources_are_stored() {
|
||||
let body = "BT /F1 12 Tf 72 700 Td (In the form) Tj ET q 20 0 0 10 5 5 cm /Im Do Q";
|
||||
let (font, direct) = ("/Font << /F1 5 0 R >>", "/XObject << /Fm 6 0 R /Im 7 0 R >>");
|
||||
for (page, form) in [
|
||||
(format!("<< {font} {direct} >>"), ""),
|
||||
(format!("<< {font} /XObject 9 0 R >>"), ""),
|
||||
(format!("<< /Font 10 0 R {direct} >>"), ""),
|
||||
(format!("<< {font} {direct} >>"), "/Resources 99 0 R"),
|
||||
(format!("<< {font} {direct} >>"), "/Resources 12"),
|
||||
("<< /XObject << /Fm 6 0 R >> >>".to_string(), "/Resources 8 0 R"),
|
||||
("<< /XObject 9 0 R >>".to_string(), "/Resources << /Font << /F1 5 0 R >> /XObject 9 0 R >>"),
|
||||
] {
|
||||
let doc = build(&[
|
||||
"<< /Type /Catalog /Pages 2 0 R >>",
|
||||
"<< /Type /Pages /Kids [3 0 R] /Count 1 >>",
|
||||
&format!("<< /Type /Page /Parent 2 0 R /MediaBox [0 0 600 800] /Resources {page} /Contents 4 0 R >>"),
|
||||
&stream("", "/Fm Do"),
|
||||
"<< /Type /Font /Subtype /Type1 /BaseFont /Courier >>",
|
||||
&stream(&format!("/Type /XObject /Subtype /Form /BBox [0 0 600 800] {form}"), body),
|
||||
&stream("/Type /XObject /Subtype /Image /Width 1 /Height 1 /ColorSpace /DeviceGray /BitsPerComponent 8", "A"),
|
||||
"<< /Font << /F1 5 0 R >> /XObject 9 0 R >>",
|
||||
"<< /Fm 6 0 R /Im 7 0 R >>",
|
||||
"<< /F1 5 0 R >>",
|
||||
]);
|
||||
let blocks = text::reading_blocks(&doc, 0).unwrap();
|
||||
let texts: Vec<(&str, &str)> = blocks.iter().map(|b| (b.text.as_str(), b.base_font.as_str())).collect();
|
||||
assert_eq!(texts, [("In the form", "Courier")], "{page} {form}");
|
||||
assert_eq!(images::reading_images(&doc, 0).unwrap().len(), 1, "{page} {form}");
|
||||
}
|
||||
}
|
||||
|
||||
/// A chain of forms, each drawing the next twenty times, twelve deep: within the depth cap but
|
||||
/// 20^11 visits without a budget. Reading stops at the page's visit budget instead of hanging.
|
||||
#[test]
|
||||
@@ -9775,6 +9813,133 @@ fn content_units_does_not_swallow_subsequent_units_on_standalone_gs() {
|
||||
assert_eq!(units.len(), 2);
|
||||
}
|
||||
|
||||
/// A 1 × 1 grey inline image whose one sample is `data`.
|
||||
fn inline_image(data: char) -> String {
|
||||
format!("BI /W 1 /H 1 /CS /G /BPC 8 ID {data} EI")
|
||||
}
|
||||
|
||||
/// What page 0 paints, in order: `BI x` for an inline image with sample `x`, `Do x,y` for an
|
||||
/// XObject placed by a `cm` translating to x,y, and `Tj` for text. A `cm` lasts until its `Q`, so an
|
||||
/// XObject moved out of its `q`/`Q` wrapper shows as a bare `Do `.
|
||||
fn painted(doc: &Document) -> Vec<String> {
|
||||
let mut at = vec![String::new()];
|
||||
pdfcraft_content::parse(&page_content_bytes(doc, 0))
|
||||
.ops
|
||||
.iter()
|
||||
.filter_map(|op| match op.op.as_slice() {
|
||||
b"q" => {
|
||||
at.push(at.last().unwrap().clone());
|
||||
None
|
||||
}
|
||||
b"Q" => {
|
||||
at.pop();
|
||||
None
|
||||
}
|
||||
b"cm" => {
|
||||
let m = op.nums::<6>().unwrap();
|
||||
*at.last_mut().unwrap() = format!("{},{}", m[4], m[5]);
|
||||
None
|
||||
}
|
||||
b"Do" => Some(format!("Do {}", at.last().unwrap())),
|
||||
b"BI" => Some(format!("BI {}", String::from_utf8_lossy(&op.inline.as_ref().unwrap().1))),
|
||||
b"Tj" => Some("Tj".into()),
|
||||
_ => None,
|
||||
})
|
||||
.collect()
|
||||
}
|
||||
|
||||
/// The index in [`images::page_images`] of the image whose box starts at `x`,`y`.
|
||||
fn image_at(doc: &Document, x: f64, y: f64) -> usize {
|
||||
images::page_images(doc, 0).unwrap().iter().position(|i| (i.rect[0] - x).abs() < 1e-6 && (i.rect[1] - y).abs() < 1e-6).unwrap()
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn content_units_keep_each_top_level_inline_image_to_itself() {
|
||||
// The parser emits a whole inline image as one `BI` op; its unit must not run on to the end
|
||||
// (#3146). Inline images at the start, side by side and at the end are one unit each.
|
||||
let content = format!(
|
||||
"{} q 200 0 0 100 100 100 cm /Im0 Do Q {} {} q 10 0 0 10 300 300 cm /Im0 Do Q {}",
|
||||
inline_image('a'),
|
||||
inline_image('b'),
|
||||
inline_image('c'),
|
||||
inline_image('d')
|
||||
);
|
||||
let ops = pdfcraft_content::parse(content.as_bytes()).ops;
|
||||
let units = images::content_units(&ops, 0, ops.len());
|
||||
assert_eq!(units, [0..1, 1..5, 5..6, 6..7, 7..11, 11..12]);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn content_units_keep_a_nested_inline_image_inside_its_enclosing_unit() {
|
||||
// A `BI` inside `q`/`Q` or a marked-content sequence stays part of that sequence's unit.
|
||||
let content = format!("q {} Q /Span << /MCID 0 >> BDC {} EMC {}", inline_image('a'), inline_image('b'), inline_image('c'));
|
||||
let ops = pdfcraft_content::parse(content.as_bytes()).ops;
|
||||
let units = images::content_units(&ops, 0, ops.len());
|
||||
assert_eq!(units, [0..3, 3..6, 6..7]);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn send_backward_after_a_top_level_inline_image_moves_one_step() {
|
||||
// Before #3146 the inline image's unit swallowed everything after it, so SendBackward on a later
|
||||
// image acted like SendToBack: it must step behind the text only.
|
||||
let content = format!(
|
||||
"{} q 100 0 0 100 100 100 cm /Im0 Do Q BT /F1 12 Tf 72 700 Td (Middle Text) Tj ET q 150 0 0 150 200 200 cm /Im0 Do Q",
|
||||
inline_image('x')
|
||||
);
|
||||
let mut doc = image_page_with(&content);
|
||||
let front = image_at(&doc, 200.0, 200.0);
|
||||
arrange(&mut doc, 0, front, images::ArrangeOrder::SendBackward).unwrap();
|
||||
let doc = reopen(&doc);
|
||||
assert_eq!(painted(&doc), ["BI x", "Do 100,100", "Do 200,200", "Tj"]);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn arrange_steps_an_image_past_one_inline_image_at_a_time() {
|
||||
// Before #3146 BringForward on B, inside the first inline image's unit, put it in front of
|
||||
// everything. One step forward is past the next inline image only, and one step back again
|
||||
// is behind that inline image only.
|
||||
let content = format!(
|
||||
"q 100 0 0 100 100 100 cm /Im0 Do Q {} q 150 0 0 150 200 200 cm /Im0 Do Q {} BT /F1 12 Tf 72 700 Td (Text) Tj ET q 50 0 0 50 300 300 cm /Im0 Do Q",
|
||||
inline_image('a'),
|
||||
inline_image('b')
|
||||
);
|
||||
let mut doc = image_page_with(&content);
|
||||
let b = image_at(&doc, 200.0, 200.0);
|
||||
arrange(&mut doc, 0, b, images::ArrangeOrder::BringForward).unwrap();
|
||||
let mut doc = reopen(&doc);
|
||||
assert_eq!(painted(&doc), ["Do 100,100", "BI a", "BI b", "Do 200,200", "Tj", "Do 300,300"]);
|
||||
let b = image_at(&doc, 200.0, 200.0);
|
||||
arrange(&mut doc, 0, b, images::ArrangeOrder::SendBackward).unwrap();
|
||||
let doc = reopen(&doc);
|
||||
assert_eq!(painted(&doc), ["Do 100,100", "BI a", "Do 200,200", "BI b", "Tj", "Do 300,300"]);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn arrange_around_inline_images_at_the_ends_of_the_stream() {
|
||||
// Before #3146 BringToFront on the last image after an inline image "succeeded" without moving
|
||||
// it. It is already in front, so it is refused and nothing changes.
|
||||
let content =
|
||||
format!("{} q 100 0 0 100 100 100 cm /Im0 Do Q BT /F1 12 Tf 72 700 Td (Text) Tj ET q 150 0 0 150 200 200 cm /Im0 Do Q", inline_image('a'));
|
||||
let mut doc = image_page_with(&content);
|
||||
let before = page_content_bytes(&doc, 0);
|
||||
let front = image_at(&doc, 200.0, 200.0);
|
||||
assert!(arrange(&mut doc, 0, front, images::ArrangeOrder::BringToFront).is_err());
|
||||
assert!(arrange(&mut doc, 0, front, images::ArrangeOrder::BringForward).is_err());
|
||||
assert_eq!(page_content_bytes(&doc, 0), before);
|
||||
// Send to back goes behind the inline image that starts the stream.
|
||||
arrange(&mut doc, 0, front, images::ArrangeOrder::SendToBack).unwrap();
|
||||
let doc = reopen(&doc);
|
||||
assert_eq!(painted(&doc), ["Do 200,200", "BI a", "Do 100,100", "Tj"]);
|
||||
|
||||
// Bring to front goes past the inline image that ends the stream.
|
||||
let content = format!("q 100 0 0 100 100 100 cm /Im0 Do Q BT /F1 12 Tf 72 700 Td (Text) Tj ET {}", inline_image('z'));
|
||||
let mut doc = image_page_with(&content);
|
||||
let back = image_at(&doc, 100.0, 100.0);
|
||||
arrange(&mut doc, 0, back, images::ArrangeOrder::BringToFront).unwrap();
|
||||
let doc = reopen(&doc);
|
||||
assert_eq!(painted(&doc), ["Tj", "BI z", "Do 100,100"]);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn different_inline_soft_masks_have_distinct_identities() {
|
||||
let doc = Document::new_empty();
|
||||
|
||||
@@ -54,7 +54,7 @@ use fallback::{
|
||||
use fallback::{add_type3_font, is_type3_fallback};
|
||||
use interp::{Origin, Paint, union};
|
||||
use lines::page_dict;
|
||||
pub(crate) use lines::{FormBudget, content_streams, content_streams_within, form_call, rewritten_contents, splice};
|
||||
pub(crate) use lines::{FormBudget, content_streams, content_streams_within, dict_in_place, form_call, resource_dict, rewritten_contents, splice};
|
||||
pub use lines::{MAX_FORM_DEPTH, MAX_FORM_VISITS, glyph_text_lines, text_lines};
|
||||
pub use rewrite::{LineEdit, replace_line, rewrite_block};
|
||||
use rewrite::{coincident_ops, rewrite_block_from};
|
||||
|
||||
@@ -773,8 +773,9 @@ pub(super) fn interpret(
|
||||
// `Some(properties)`: read `/ActualText`, looking named property lists up in `properties`.
|
||||
logical_text: Option<&Dict>,
|
||||
) -> Result<Vec<Shown>, EditError> {
|
||||
let fonts_res = resources.get(b"Font").map(|f| doc.resolve(f)).and_then(|f| f.as_dict().cloned()).unwrap_or_default();
|
||||
let states = resources.get(b"ExtGState").map(|g| doc.resolve(g)).and_then(|g| g.as_dict().cloned()).unwrap_or_default();
|
||||
let (mut held_fonts, mut held_states, none) = (None, None, Dict::new());
|
||||
let fonts_res = super::resource_dict(doc, resources, b"Font", &mut held_fonts).unwrap_or(&none);
|
||||
let states = super::resource_dict(doc, resources, b"ExtGState", &mut held_states).unwrap_or(&none);
|
||||
let mut out: Vec<Shown> = Vec::new();
|
||||
let mut ts = carry.ts.clone();
|
||||
let mut at_bt = (0usize, ts.clone());
|
||||
@@ -881,8 +882,12 @@ pub(super) fn interpret(
|
||||
if let Some(name) = op.name(0) {
|
||||
select_gs(&mut ts.ext_gstate, name);
|
||||
}
|
||||
let params = op.name(0).and_then(|name| states.get(name)).map(|p| doc.resolve(p));
|
||||
if let Some(params) = params.as_deref().and_then(Object::as_dict) {
|
||||
let mut held = None;
|
||||
let params = match op.name(0).and_then(|name| states.get(name)) {
|
||||
Some(p) => super::dict_in_place(doc, p, &mut held),
|
||||
None => None,
|
||||
};
|
||||
if let Some(params) = params {
|
||||
ts.gs.apply(doc, params);
|
||||
// `/LW` sets the line width as `w` does (ISO 32000-2 §8.4.5).
|
||||
let lw = params.get(b"LW").and_then(|w| doc.resolve(w).as_f64()).filter(|w| w.is_finite());
|
||||
|
||||
@@ -1,3 +1,5 @@
|
||||
use std::sync::Arc;
|
||||
|
||||
use super::fallback::{same_font, same_paint};
|
||||
use super::interp::{Carry, Origin, Pen, Shown, TextState, Ts, direction, interpret, to_frame, union};
|
||||
use super::{DecodeBudget, Dict, Document, EditError, HashMap, Matrix, Object, Op, Pieces, Stream, TextLine, parse, serialize_ops};
|
||||
@@ -452,10 +454,41 @@ impl FormBudget {
|
||||
pub(crate) struct FormCall {
|
||||
pub(crate) obj: Option<pdfcraft_cos::ObjRef>,
|
||||
pub(crate) data: Vec<u8>,
|
||||
pub(crate) resources: Dict,
|
||||
/// The form, and its `/Resources` when they are an object of their own, which is what
|
||||
/// [`FormCall::resources`] reads.
|
||||
form: Arc<Object>,
|
||||
own: Option<Arc<Object>>,
|
||||
pub(crate) ctm: Matrix,
|
||||
}
|
||||
|
||||
impl FormCall {
|
||||
/// The resources its content is read with: its own, or if it has none, `drawn_with`, the ones
|
||||
/// it was drawn with (PDF 1.1 files). Read in place, as a page can draw a form thousands of times:
|
||||
/// a copy for each took time in the square of them.
|
||||
pub(crate) fn resources<'a>(&'a self, drawn_with: &'a Dict) -> &'a Dict {
|
||||
let direct = || match &*self.form {
|
||||
Object::Stream(s) => s.dict.get(b"Resources").and_then(Object::as_dict),
|
||||
_ => None,
|
||||
};
|
||||
self.own.as_deref().and_then(Object::as_dict).or_else(direct).unwrap_or(drawn_with)
|
||||
}
|
||||
}
|
||||
|
||||
/// `o` as a dictionary, read in place for the same reason as [`FormCall::resources`]. `held` keeps it
|
||||
/// when it is an object of its own. Nothing else is one, and [`Document::resolve`] would copy it.
|
||||
pub(crate) fn dict_in_place<'a>(doc: &Document, o: &'a Object, held: &'a mut Option<Arc<Object>>) -> Option<&'a Dict> {
|
||||
match o {
|
||||
Object::Dict(dict) => Some(dict),
|
||||
Object::Ref(_) => held.insert(doc.resolve(o)).as_dict(),
|
||||
_ => None,
|
||||
}
|
||||
}
|
||||
|
||||
/// The dictionary at `key` of `resources`, `/XObject` or `/Font`, say, as each form reads these.
|
||||
pub(crate) fn resource_dict<'a>(doc: &Document, resources: &'a Dict, key: &[u8], held: &'a mut Option<Arc<Object>>) -> Option<&'a Dict> {
|
||||
dict_in_place(doc, resources.get(key)?, held)
|
||||
}
|
||||
|
||||
/// The form XObject `name` in `resources`, drawn with `ctm`. `None` for images, missing names
|
||||
/// and forms already being read (`path`), and for forms nested too deep or past the page's
|
||||
/// budget, which `budget` records as truncated; each form entered counts one visit.
|
||||
@@ -472,13 +505,15 @@ pub(crate) fn form_call(
|
||||
if limited && budget.truncated {
|
||||
return None;
|
||||
}
|
||||
let xobjects = resources.get(b"XObject").map(|x| doc.resolve(x)).and_then(|x| x.as_dict().cloned())?;
|
||||
let o = xobjects.get(name)?;
|
||||
let obj = o.as_ref();
|
||||
let mut held = None;
|
||||
let o = resource_dict(doc, resources, b"XObject", &mut held)?.get(name)?;
|
||||
// Only a reference can name a stream, so nothing else needs reading, or copying.
|
||||
let obj = Some(o.as_ref()?);
|
||||
if obj.is_some_and(|r| path.contains(&r)) {
|
||||
return None;
|
||||
}
|
||||
let Object::Stream(s) = &*doc.resolve(o) else { return None };
|
||||
let form = doc.resolve(o);
|
||||
let Object::Stream(s) = &*form else { return None };
|
||||
if s.dict.name(b"Subtype") != Some(b"Form") {
|
||||
return None;
|
||||
}
|
||||
@@ -492,8 +527,7 @@ pub(crate) fn form_call(
|
||||
let v: Vec<f64> = a.iter().filter_map(|x| doc.resolve(x).as_f64()).collect();
|
||||
<[f64; 6]>::try_from(v).ok().filter(|v| v.iter().all(|x| x.is_finite()))
|
||||
});
|
||||
// A form without its own resources uses the ones it was drawn with (PDF 1.1 files).
|
||||
let own = s.dict.get(b"Resources").map(|r| doc.resolve(r)).and_then(|r| r.as_dict().cloned());
|
||||
let own = s.dict.get(b"Resources").filter(|r| matches!(r, Object::Ref(_))).map(|r| doc.resolve(r));
|
||||
let data = match budget.decode.decode(s) {
|
||||
Ok(data) => data,
|
||||
Err(_) if budget.decode.remaining() == 0 => {
|
||||
@@ -503,7 +537,7 @@ pub(crate) fn form_call(
|
||||
Err(_) => Vec::new(),
|
||||
};
|
||||
budget.visits = budget.visits.saturating_add(1);
|
||||
Some(FormCall { obj, data, resources: own.unwrap_or_else(|| resources.clone()), ctm: m.map_or(ctm, |m| Matrix(m).then(&ctm)) })
|
||||
Some(FormCall { obj, data, form, own, ctm: m.map_or(ctm, |m| Matrix(m).then(&ctm)) })
|
||||
}
|
||||
|
||||
/// The lines a page shows as it reads, including text drawn by form XObjects (which
|
||||
@@ -522,8 +556,9 @@ pub(super) fn reading_lines(doc: &Document, page: usize) -> Result<(Vec<TextLine
|
||||
fn walk(w: &mut Walk, ops: &[Op], resources: &Dict, carry: &mut Carry, stream: &dyn Fn(usize) -> usize) -> Result<(), EditError> {
|
||||
let mut cache = HashMap::new();
|
||||
let mut invoked = Vec::new();
|
||||
let properties = resources.get(b"Properties").and_then(|o| w.doc.dict(o)).unwrap_or_default();
|
||||
let shown = interpret(w.doc, ops, resources, &mut cache, carry, Some(&mut invoked), Some(&properties))?;
|
||||
let (mut held, none) = (None, Dict::new());
|
||||
let properties = resource_dict(w.doc, resources, b"Properties", &mut held).unwrap_or(&none);
|
||||
let shown = interpret(w.doc, ops, resources, &mut cache, carry, Some(&mut invoked), Some(properties))?;
|
||||
let mut last = None;
|
||||
let mut last_stream = None;
|
||||
let mut forms = invoked.into_iter().peekable();
|
||||
@@ -556,7 +591,7 @@ pub(super) fn reading_lines(doc: &Document, page: usize) -> Result<(Vec<TextLine
|
||||
if let Some(r) = form.obj {
|
||||
w.path.push(r);
|
||||
}
|
||||
walk(w, &ops, &form.resources, &mut carry, &|_| stream)?;
|
||||
walk(w, &ops, form.resources(resources), &mut carry, &|_| stream)?;
|
||||
*text_left = carry.text_left;
|
||||
if form.obj.is_some() {
|
||||
w.path.pop();
|
||||
|
||||
@@ -146,6 +146,11 @@ pub struct FileResult {
|
||||
pub log: Vec<String>,
|
||||
}
|
||||
|
||||
/// What an action's log says of the images a Reduce File Size step left, if there are any.
|
||||
fn images_refused_note(images: usize) -> Option<String> {
|
||||
(images > 0).then(|| format!("Reduce file size: {images} image(s) stayed as they were, past what one run may decode"))
|
||||
}
|
||||
|
||||
fn apply_step(s: &mut Session, id: DocId, step: &Step, log: &mut Vec<String>) -> Result<Option<DocId>, EditError> {
|
||||
let pages = s.get(id).map_or(0, |d| d.info.pages.len());
|
||||
let all: Vec<usize> = (0..pages).collect();
|
||||
@@ -156,9 +161,10 @@ fn apply_step(s: &mut Session, id: DocId, step: &Step, log: &mut Vec<String>) ->
|
||||
return Ok(None);
|
||||
}
|
||||
Step::ReduceFileSize => {
|
||||
let (bytes, _) = s.optimized_bytes(id, &crate::optimize::Settings::default(), &[])?;
|
||||
let (bytes, report) = s.optimized_bytes(id, &crate::optimize::Settings::default(), &[])?;
|
||||
let before = s.get(id).map_or(0, |d| d.bytes.len());
|
||||
log.push(format!("Reduce file size: {} → {} bytes", before, bytes.len()));
|
||||
log.extend(images_refused_note(report.optimize.images_refused));
|
||||
let name = s.get(id).map(|d| d.name.clone()).unwrap_or_default();
|
||||
s.close(id);
|
||||
let new = s.open(name, None, bytes, None).map_err(|e| EditError::Reopen(e.to_string()))?;
|
||||
@@ -222,3 +228,16 @@ pub fn run_on(action: &Action, name: &str, bytes: Arc<Vec<u8>>, mut progress: im
|
||||
let bytes = if d.is_signed() { s.save_bytes(id) } else { s.save_full_bytes(id) }.map_err(|e| e.to_string())?;
|
||||
Ok(FileResult { name: name.to_string(), bytes, log })
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::images_refused_note;
|
||||
|
||||
/// A log line only for images that stayed, saying how many.
|
||||
#[test]
|
||||
fn the_log_says_when_images_stayed_as_they_were() {
|
||||
assert_eq!(images_refused_note(0), None);
|
||||
assert!(images_refused_note(1).is_some_and(|note| note.contains("1 image(s)")));
|
||||
assert!(images_refused_note(3).is_some_and(|note| note.contains("3 image(s)")));
|
||||
}
|
||||
}
|
||||
@@ -140,6 +140,8 @@ pub enum OfficeFormat {
|
||||
Docx,
|
||||
Pptx,
|
||||
Html,
|
||||
/// CSS-free HTML that preserves text and inline images but drops colours and layout styling.
|
||||
HtmlSimple,
|
||||
Rtf,
|
||||
Markdown,
|
||||
}
|
||||
@@ -150,6 +152,7 @@ impl OfficeFormat {
|
||||
OfficeFormat::Docx => "docx",
|
||||
OfficeFormat::Pptx => "pptx",
|
||||
OfficeFormat::Html => "html",
|
||||
OfficeFormat::HtmlSimple => "html",
|
||||
OfficeFormat::Rtf => "rtf",
|
||||
OfficeFormat::Markdown => "md",
|
||||
}
|
||||
@@ -173,14 +176,15 @@ pub struct OfficeExport {
|
||||
/// The exported file.
|
||||
pub bytes: Vec<u8>,
|
||||
/// Pages (0-based) that draw forms nested deeper than [`MAX_FORM_DEPTH`] or more of them
|
||||
/// than [`MAX_FORM_VISITS`], or pictures past [`MAX_EXPORT_IMAGE_BYTES`]: export stops
|
||||
/// reading there to stay bounded on hostile files, so the text and images of those forms, or
|
||||
/// than [`MAX_FORM_VISITS`], or pictures past [`MAX_EXPORT_IMAGE_BYTES`] or past what one export
|
||||
/// may decode: export stops reading there to stay bounded on hostile files, so the text and images of those forms, or
|
||||
/// those pictures, are missing from `bytes`.
|
||||
pub truncated_pages: Vec<usize>,
|
||||
}
|
||||
|
||||
/// An image object prepared for Office export: its file extension and encoded bytes, or why it is
|
||||
/// left out (`Err(true)`: past [`MAX_EXPORT_IMAGE_BYTES`]; `Err(false)`: it can't be encoded).
|
||||
/// left out (`Err(true)`: past [`MAX_EXPORT_IMAGE_BYTES`], or what the export may decode;
|
||||
/// `Err(false)`: it can't be encoded).
|
||||
type PreparedImage = Result<(&'static str, Arc<[u8]>), bool>;
|
||||
|
||||
impl crate::Document {
|
||||
@@ -194,6 +198,18 @@ impl crate::Document {
|
||||
/// pictures went past `image_budget` bytes ([`OfficeExport::truncated_pages`]). Without
|
||||
/// `images` no picture is prepared.
|
||||
pub(crate) fn export_pages_checked(&self, images: bool, image_budget: usize) -> (Vec<pdfcraft_export::Page>, Vec<usize>) {
|
||||
let Some(editor) = self.editor.as_ref() else { return (Vec::new(), Vec::new()) };
|
||||
self.export_pages_within(images, image_budget, &mut pdfcraft_cos::ImageBudget::new(&editor.cos))
|
||||
}
|
||||
|
||||
/// [`Self::export_pages_checked`], its pictures decoded within `image_work`, which is shared
|
||||
/// by the whole export: a picture past it is left out like one past `image_budget`.
|
||||
pub(crate) fn export_pages_within(
|
||||
&self,
|
||||
images: bool,
|
||||
image_budget: usize,
|
||||
image_work: &mut pdfcraft_cos::ImageBudget,
|
||||
) -> (Vec<pdfcraft_export::Page>, Vec<usize>) {
|
||||
let Some(cos) = self.editor.as_ref().map(|e| &e.cos) else { return (Vec::new(), Vec::new()) };
|
||||
let mut truncated = Vec::new();
|
||||
// Each image object is encoded once and shared by every place that draws it.
|
||||
@@ -244,7 +260,9 @@ impl crate::Document {
|
||||
.filter_map(|im| {
|
||||
let object = im.object?;
|
||||
let prepared = encoded.entry(object).or_insert_with(|| {
|
||||
let (ext, bytes) = pdfcraft_create::image_file(cos, object).map_err(|_| false)?;
|
||||
let refused = image_work.refused();
|
||||
let (ext, bytes) =
|
||||
pdfcraft_create::image_file_within(cos, object, &mut *image_work).map_err(|_| image_work.refused() > refused)?;
|
||||
image_bytes = image_bytes.checked_sub(bytes.len()).ok_or(true)?;
|
||||
Ok((if ext == "jpg" { "jpg" } else { "png" }, Arc::from(bytes)))
|
||||
});
|
||||
@@ -286,6 +304,7 @@ impl crate::Document {
|
||||
OfficeFormat::Docx => pdfcraft_export::docx(&pages, &title),
|
||||
OfficeFormat::Pptx => pdfcraft_export::pptx(&pages, &title),
|
||||
OfficeFormat::Html => pdfcraft_export::html(&pages, &title).into_bytes(),
|
||||
OfficeFormat::HtmlSimple => pdfcraft_export::html_simple(&pages, &title).into_bytes(),
|
||||
OfficeFormat::Rtf => pdfcraft_export::rtf(&pages).into_bytes(),
|
||||
OfficeFormat::Markdown => pdfcraft_export::markdown(&pages).into_bytes(),
|
||||
};
|
||||
|
||||
@@ -92,7 +92,24 @@ impl OptimizeJob {
|
||||
pdfcraft_xfa::clear_password_values(&mut cos).map_err(|e| EditError::Write(e.to_string()))?;
|
||||
let mut step = |stage| if progress(stage) { Ok(()) } else { Err(EditError::Cancelled) };
|
||||
step(OptimizeStage::Discarding)?;
|
||||
let discarded = if discard.is_empty() { Vec::new() } else { pdfcraft_redact::sanitize::remove_hidden(&mut cos, &discard)? };
|
||||
let discarded = if discard.is_empty() {
|
||||
Vec::new()
|
||||
} else {
|
||||
// Every ticked category, as `remove_hidden` decides between them: with form fields
|
||||
// ticked, discarding hidden text also takes the hidden text the flattened appearances
|
||||
// bring onto the page, which no scan before flattening counts. It refuses when its scan
|
||||
// counts every one as 0, which would end the whole optimization, and may have changed
|
||||
// the copy by then (an empty outline root goes with bookmarks), so the copy from before
|
||||
// is kept instead: nothing is discarded.
|
||||
let before = cos.clone();
|
||||
match pdfcraft_redact::sanitize::remove_hidden(&mut cos, &discard) {
|
||||
Err(pdfcraft_redact::RedactError::NothingToApply) => {
|
||||
cos = before;
|
||||
Vec::new()
|
||||
}
|
||||
r => r?,
|
||||
}
|
||||
};
|
||||
let report = optimize::optimize_with_progress(&mut cos, &settings, &mut |s| {
|
||||
step(match s {
|
||||
optimize::Stage::Fragments => OptimizeStage::Fragments,
|
||||
|
||||
@@ -71,12 +71,12 @@ impl Session {
|
||||
/// Reduce File Size: Acrobat's defaults (colour and grey images above 225 ppi to 150 ppi,
|
||||
/// JPEG medium quality; black-and-white averaged down to 300 ppi above 450 ppi, and stored as
|
||||
/// CCITT Group 4 whenever smaller; thumbnails dropped), identical resources merged, unused
|
||||
/// objects dropped, objects packed into compressed object streams. Returns the bytes and how
|
||||
/// many objects were merged. The open document is not changed (Acrobat saves the reduced copy
|
||||
/// as a new file).
|
||||
pub fn reduced_bytes(&self, id: DocId) -> Result<(Arc<Vec<u8>>, usize), EditError> {
|
||||
/// objects dropped, objects packed into compressed object streams. Returns the bytes, how
|
||||
/// many objects were merged and how many images stayed as they were, past what one run may
|
||||
/// decode. The open document is not changed (Acrobat saves the reduced copy as a new file).
|
||||
pub fn reduced_bytes(&self, id: DocId) -> Result<(Arc<Vec<u8>>, usize, usize), EditError> {
|
||||
let (bytes, report) = self.optimized_bytes(id, &optimize::Settings::default(), &[])?;
|
||||
Ok((bytes, report.merged))
|
||||
Ok((bytes, report.merged, report.optimize.images_refused))
|
||||
}
|
||||
|
||||
/// Optimize PDF ▸ Advanced optimization: `settings` for images and objects, plus Remove
|
||||
|
||||
@@ -55,7 +55,10 @@ impl Document {
|
||||
if w <= 0 || h <= 0 || w > i64::from(MAX_SIDE) || h > i64::from(MAX_SIDE) || w.saturating_mul(h) > MAX_PIXELS as i64 {
|
||||
return Err(SignatureImageError::PlacedSize.to_string());
|
||||
}
|
||||
let (_, bytes) = pdfcraft_create::image_file(&editor.cos, picture)?;
|
||||
// Decoded within an allowance sized for the small picture a signature is, not the
|
||||
// document's: a stream that inflates past it is refused before it is held whole.
|
||||
let (_, bytes) =
|
||||
pdfcraft_create::image_file_within(&editor.cos, picture, &mut pdfcraft_cos::ImageBudget::with_work(SIGNATURE_IMAGE_WORK))?;
|
||||
let image = SignatureImage::from_bytes(&bytes).map_err(|e| e.to_string())?;
|
||||
let opacity =
|
||||
pdfcraft_annot::props(&editor.cos, page, index).map(|p| p.opacity).filter(|v| v.is_finite()).unwrap_or(1.0).clamp(0.0, 1.0) as f32;
|
||||
@@ -90,6 +93,9 @@ pub fn upright_box(rotation: i64, at: [f64; 2], width: f64, height: f64) -> Opti
|
||||
/// Saved signatures live in settings, so both source and normalized PNG are bounded.
|
||||
pub const MAX_SIGNATURE_IMAGE_BYTES: usize = 4 << 20;
|
||||
const MAX_PIXELS: u64 = 4 << 20;
|
||||
/// Steps of decoding the signature's picture may take: every stage of its filters, for a
|
||||
/// picture of at most [`MAX_PIXELS`] samples, fits in it many times over.
|
||||
const SIGNATURE_IMAGE_WORK: u64 = 1 << 28;
|
||||
const MAX_SIDE: u32 = 4096;
|
||||
/// Larger sources (scans, phone photos) are decoded within these bounds, then scaled down.
|
||||
const MAX_SOURCE_SIDE: u32 = 8192;
|
||||
|
||||
+159
-2
@@ -3603,13 +3603,73 @@ fn create_and_reduce() {
|
||||
)
|
||||
.unwrap();
|
||||
let full = s2.save_full_bytes(id2).unwrap();
|
||||
let (reduced, _) = s2.reduced_bytes(id2).unwrap();
|
||||
let (reduced, ..) = s2.reduced_bytes(id2).unwrap();
|
||||
assert!(reduced.len() <= full.len(), "{} > {}", reduced.len(), full.len());
|
||||
let mut s3 = Session::new();
|
||||
let r = s3.open("r.pdf", None, reduced, None).unwrap();
|
||||
assert_eq!(page_texts(&s3, r), ["Page 1", "Page 1"]);
|
||||
}
|
||||
|
||||
/// Discarding a category that holds nothing discards nothing; it used to end the whole
|
||||
/// optimization with an error about redaction marks.
|
||||
#[test]
|
||||
fn optimize_discarding_an_empty_category_still_runs() {
|
||||
let (s, id) = session_with(2);
|
||||
let (bytes, report) = s.optimized_bytes(id, &optimize::Settings::default(), &[crate::Hidden::Bookmarks, crate::Hidden::Comments]).unwrap();
|
||||
assert!(bytes.starts_with(b"%PDF-"));
|
||||
assert!(report.discarded.is_empty(), "{:?}", report.discarded);
|
||||
// An outline root with no entries is no bookmarks: it stays, as Remove Hidden Information,
|
||||
// which refuses then, leaves it.
|
||||
let outline = pdfcraft_testkit::Pdf::new()
|
||||
.obj("<< /Type /Catalog /Pages 2 0 R /Outlines 4 0 R /PageMode /UseOutlines >>")
|
||||
.obj("<< /Type /Pages /Kids [3 0 R] /Count 1 /MediaBox [0 0 612 792] >>")
|
||||
.obj("<< /Type /Page /Parent 2 0 R >>")
|
||||
.obj("<< /Type /Outlines /Count 0 >>")
|
||||
.build();
|
||||
let mut s = Session::new();
|
||||
let id = s.open("outline.pdf", None, Arc::new(outline), None).unwrap();
|
||||
let (bytes, report) = s.optimized_bytes(id, &optimize::Settings::default(), &[crate::Hidden::Bookmarks]).unwrap();
|
||||
assert!(report.discarded.is_empty(), "{:?}", report.discarded);
|
||||
let saved = pdfcraft_cos::Document::open(bytes).unwrap();
|
||||
let catalog = saved.get(saved.root().unwrap()).as_dict().cloned().unwrap();
|
||||
assert!(catalog.contains(b"Outlines") && catalog.contains(b"PageMode"), "{catalog:?}");
|
||||
// Beside an empty tick, one that holds something is discarded, and only that one.
|
||||
let noted = pdfcraft_testkit::Pdf::new()
|
||||
.obj("<< /Type /Catalog /Pages 2 0 R >>")
|
||||
.obj("<< /Type /Pages /Kids [3 0 R] /Count 1 /MediaBox [0 0 612 792] >>")
|
||||
.obj("<< /Type /Page /Parent 2 0 R /Annots [4 0 R] >>")
|
||||
.obj("<< /Type /Annot /Subtype /Text /Rect [20 20 40 40] /Contents (internal note) >>")
|
||||
.build();
|
||||
let mut s = Session::new();
|
||||
let id = s.open("noted.pdf", None, Arc::new(noted), None).unwrap();
|
||||
let (_, report) = s.optimized_bytes(id, &optimize::Settings::default(), &[crate::Hidden::Bookmarks, crate::Hidden::Comments]).unwrap();
|
||||
assert_eq!(report.discarded, vec![(crate::Hidden::Comments, 1)]);
|
||||
// A field whose appearance draws text invisibly: flattening it brings that text onto the page,
|
||||
// which no scan before counts as hidden, and discarding hidden text takes it too.
|
||||
let form = pdfcraft_testkit::Pdf::new()
|
||||
.obj("<< /Type /Catalog /Pages 2 0 R /AcroForm << /Fields [4 0 R] /DA (/F1 0 Tf 0 g) >> >>")
|
||||
.obj("<< /Type /Pages /Kids [3 0 R] /Count 1 /MediaBox [0 0 612 792] >>")
|
||||
.obj("<< /Type /Page /Parent 2 0 R /Annots [4 0 R] /Resources << /Font << /F1 6 0 R >> >> /Contents 7 0 R >>")
|
||||
.obj("<< /Type /Annot /Subtype /Widget /FT /Tx /T (name) /V (shown) /Rect [100 100 300 130] /P 3 0 R /F 4 /AP << /N 5 0 R >> >>")
|
||||
.stream(
|
||||
"/Type /XObject /Subtype /Form /BBox [0 0 200 30] /Resources << /Font << /F1 6 0 R >> >>",
|
||||
"/Tx BMC BT /F1 12 Tf 2 10 Td (shown) Tj ET BT /F1 12 Tf 3 Tr 2 20 Td (HIDDENSECRET) Tj ET EMC",
|
||||
)
|
||||
.obj("<< /Type /Font /Subtype /Type1 /BaseFont /Helvetica >>")
|
||||
.stream("", "BT /F1 12 Tf 72 700 Td (Page text) Tj ET")
|
||||
.build();
|
||||
let mut s = Session::new();
|
||||
let id = s.open("form.pdf", None, Arc::new(form), None).unwrap();
|
||||
let (bytes, _) = s.optimized_bytes(id, &optimize::Settings::default(), &[crate::Hidden::FormFields, crate::Hidden::HiddenText]).unwrap();
|
||||
let saved = pdfcraft_cos::Document::open(bytes).unwrap();
|
||||
for (r, object) in saved.scan_objects() {
|
||||
if let pdfcraft_cos::Object::Stream(st) = &*object {
|
||||
let data = st.decoded().unwrap_or_default();
|
||||
assert!(!data.windows(12).any(|w| w == b"HIDDENSECRET"), "the hidden text stays in {r:?}");
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn an_optimize_job_reports_its_stages_and_can_be_cancelled() {
|
||||
use crate::optimizer::OptimizeStage;
|
||||
@@ -8244,10 +8304,35 @@ fn copy_image_reads_the_globals_of_a_jbig2_picture() {
|
||||
let (w, h, rgba) = d.page_image_rgba(0, 0).unwrap();
|
||||
assert_eq!((w, h), (16, 2));
|
||||
assert!(rgba.chunks(4).all(|p| p == [0, 0, 0, 255]), "the page's default pixel, from the globals");
|
||||
// An Office export shares one allowance across its pictures. One past it is left out, and the
|
||||
// export says the page is missing something, as for a picture past its bytes.
|
||||
let (pages, truncated) = d.export_pages_within(true, 1 << 20, &mut pdfcraft_cos::ImageBudget::with_work(u64::MAX));
|
||||
assert_eq!((pages[0].images.len(), truncated.len()), (1, 0));
|
||||
let (pages, truncated) = d.export_pages_within(true, 1 << 20, &mut pdfcraft_cos::ImageBudget::with_work(0));
|
||||
assert!(pages[0].images.is_empty());
|
||||
assert_eq!(truncated, [0]);
|
||||
}
|
||||
|
||||
/// An Office export leaves out a picture it can't encode, as it did. That isn't a page cut short:
|
||||
/// only a picture past what the export may do is reported as one.
|
||||
#[test]
|
||||
fn an_office_export_doesnt_call_an_unreadable_picture_truncated() {
|
||||
let pdf = b"%PDF-1.7\n1 0 obj << /Type /Catalog /Pages 2 0 R >> endobj\n\
|
||||
2 0 obj << /Type /Pages /Kids [3 0 R] /Count 1 /MediaBox [0 0 200 300] >> endobj\n\
|
||||
3 0 obj << /Type /Page /Parent 2 0 R /Contents 4 0 R /Resources << /XObject << /Im1 5 0 R >> >> >> endobj\n\
|
||||
4 0 obj << /Length 31 >> stream\nq 160 0 0 20 20 100 cm /Im1 Do Q\nendstream endobj\n\
|
||||
5 0 obj << /Type /XObject /Subtype /Image /Width 2 /Height 2 /ColorSpace /DeviceGray /BitsPerComponent 8 /Filter /JPXDecode /Length 4 >> stream\nnone\nendstream endobj\n\
|
||||
trailer << /Root 1 0 R >>\n%%EOF"
|
||||
.to_vec();
|
||||
let mut s = Session::new();
|
||||
let id = s.open("picture.pdf", None, Arc::new(pdf), None).unwrap();
|
||||
let (pages, truncated) = s.get(id).unwrap().export_pages_within(true, 1 << 20, &mut pdfcraft_cos::ImageBudget::with_work(u64::MAX));
|
||||
assert!(pages[0].images.is_empty());
|
||||
assert_eq!(truncated, Vec::<usize>::new());
|
||||
}
|
||||
|
||||
/// Copy Image takes a JBIG2 picture as its pixels and as a PNG file, behind another filter
|
||||
/// (ASCIIHexDecode) too: Export's decoding, through `Document::decoded_image`.
|
||||
/// (ASCIIHexDecode) too: Export's decoding, through `ImageBudget::decode`.
|
||||
#[test]
|
||||
fn copy_image_copies_a_jbig2_picture_behind_another_filter() {
|
||||
// 16 × 2: the left half of the top row black, the rest white.
|
||||
@@ -9215,6 +9300,61 @@ fn a_fields_own_script_may_not_save_as_or_show_a_panel() {
|
||||
assert_eq!(o.requests, [js::Request::SaveAs]);
|
||||
}
|
||||
|
||||
/// A page of `count` pictures of one flat grey, `side` pixels square, each an object of its own.
|
||||
fn page_of_pictures(count: usize, side: usize) -> Vec<u8> {
|
||||
let data = pdfcraft_filters::encode_flate(&vec![0x80; side * side]);
|
||||
let names: String = (0..count).map(|i| format!("/Im{i} {} 0 R ", 5 + i)).collect();
|
||||
let content: String = (0..count).map(|i| format!("q 10 0 0 10 0 0 cm /Im{i} Do Q\n")).collect();
|
||||
let mut pdf = format!(
|
||||
"%PDF-1.7\n1 0 obj << /Type /Catalog /Pages 2 0 R >> endobj\n\
|
||||
2 0 obj << /Type /Pages /Kids [3 0 R] /Count 1 /MediaBox [0 0 200 300] >> endobj\n\
|
||||
3 0 obj << /Type /Page /Parent 2 0 R /Contents 4 0 R /Resources << /XObject << {names}>> >> >> endobj\n\
|
||||
4 0 obj << /Length {} >> stream\n{content}\nendstream endobj\n",
|
||||
content.len()
|
||||
)
|
||||
.into_bytes();
|
||||
for i in 0..count {
|
||||
let dict = format!(
|
||||
"{} 0 obj << /Type /XObject /Subtype /Image /Width {side} /Height {side} /ColorSpace /DeviceGray /BitsPerComponent 8 /Filter /FlateDecode /Length {} >> stream\n",
|
||||
5 + i,
|
||||
data.len()
|
||||
);
|
||||
pdf.extend_from_slice(dict.as_bytes());
|
||||
pdf.extend_from_slice(&data);
|
||||
pdf.extend_from_slice(b"\nendstream endobj\n");
|
||||
}
|
||||
pdf.extend_from_slice(b"trailer << /Root 1 0 R >>\n%%EOF");
|
||||
pdf
|
||||
}
|
||||
|
||||
/// The allowance is the export's, not each picture's: a page of many small pictures stops where it
|
||||
/// runs out, the rest are left out and counted, and the page is listed, which is what the export's
|
||||
/// warning goes by. A few large pictures are well within it, and all come through.
|
||||
#[test]
|
||||
fn a_page_of_many_pictures_stops_at_the_exports_allowance() {
|
||||
let export = |pdf: Vec<u8>, work: &mut pdfcraft_cos::ImageBudget| {
|
||||
let mut s = Session::new();
|
||||
let id = s.open("pictures.pdf", None, Arc::new(pdf), None).unwrap();
|
||||
s.get(id).unwrap().export_pages_within(true, 1 << 30, work)
|
||||
};
|
||||
let mut one = pdfcraft_cos::ImageBudget::with_work(u64::MAX);
|
||||
export(page_of_pictures(1, 2), &mut one);
|
||||
let cost = u64::MAX - one.work_left();
|
||||
assert!(cost > 0);
|
||||
|
||||
let mut work = pdfcraft_cos::ImageBudget::with_work(100 * cost);
|
||||
let (pages, truncated) = export(page_of_pictures(10_000, 2), &mut work);
|
||||
assert_eq!(pages[0].images.len(), 100);
|
||||
assert_eq!(truncated, vec![0]);
|
||||
assert_eq!(work.refused(), 9_900);
|
||||
|
||||
let mut s = Session::new();
|
||||
let id = s.open("large.pdf", None, Arc::new(page_of_pictures(3, 1_000)), None).unwrap();
|
||||
let (pages, truncated) = s.get(id).unwrap().export_pages_checked(true, 1 << 30);
|
||||
assert_eq!(pages[0].images.len(), 3);
|
||||
assert_eq!(truncated, Vec::<usize>::new());
|
||||
}
|
||||
|
||||
/// A page whose forms go past the reading limit and whose picture goes past the image budget is
|
||||
/// listed once among the truncated pages.
|
||||
#[test]
|
||||
@@ -10111,3 +10251,20 @@ fn image_transform_engine_refuses_singular_matrices_without_mutation() {
|
||||
assert_eq!(s.get(id).unwrap().bytes, before);
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn fill_sign_multiline_text_survives_engine_save_reopen_and_render() {
|
||||
let (mut session, id) = rotated_blank(0);
|
||||
let text = "\nAda\n\nLovelace\n";
|
||||
let shape = Shape::Typewriter { rect: text_box_at(0, [20.0, 250.0], 120.0, 66.0).unwrap(), font_size: 10.0 };
|
||||
let style = Style::default_for(&shape);
|
||||
session.apply(id, Edit::AddAnnotation(NewAnnotation { page: 0, shape, style, contents: text.into(), author: "Test".into() })).unwrap();
|
||||
assert_eq!(session.get(id).unwrap().info.annotations[0].contents.as_deref(), Some(text), "engine keeps outer typewriter line breaks");
|
||||
let before = render_page(&session, id);
|
||||
assert!(before.rgba.as_chunks::<4>().0.iter().any(|p| p[..3] == [0, 0, 0]), "the appearance contains ink");
|
||||
let bytes = session.save_bytes(id).unwrap();
|
||||
let mut reopened = Session::new();
|
||||
let again = reopened.open("multiline.pdf", None, bytes, None).unwrap();
|
||||
assert_eq!(reopened.get(again).unwrap().info.annotations[0].contents.as_deref(), Some(text), "reopening preserves all blank lines");
|
||||
assert_eq!(before.rgba, render_page(&reopened, again).rgba, "the saved appearance is identical");
|
||||
}
|
||||
@@ -38,11 +38,23 @@ pub(crate) fn base64(data: &[u8]) -> String {
|
||||
/// One HTML file: headings and paragraphs, tables as real `<table>` elements, images inline, a
|
||||
/// rule between pages.
|
||||
pub fn html(pages: &[Page], title: &str) -> String {
|
||||
html_with_mode(pages, title, false)
|
||||
}
|
||||
|
||||
/// A simple HTML export with no CSS; page layout and colours are omitted.
|
||||
pub fn html_simple(pages: &[Page], title: &str) -> String {
|
||||
html_with_mode(pages, title, true)
|
||||
}
|
||||
|
||||
fn html_with_mode(pages: &[Page], title: &str, simple: bool) -> String {
|
||||
let mut s = format!(
|
||||
"<!DOCTYPE html>\n<html>\n<head>\n<meta charset=\"utf-8\">\n<title>{}</title>\n<style>body{{max-width:46em;margin:2em auto;font-family:sans-serif;line-height:1.45}}\
|
||||
img{{max-width:100%}}hr{{border:0;border-top:1px solid #ccc;margin:2em 0}}\
|
||||
table{{border-collapse:collapse;margin:1em 0}}td,th{{border:1px solid #999;padding:2px 6px;vertical-align:top}}</style>\n</head>\n<body>\n",
|
||||
esc(title)
|
||||
"<!DOCTYPE html>\n<html>\n<head>\n<meta charset=\"utf-8\">\n<title>{}</title>\n{}\n</head>\n<body>\n",
|
||||
esc(title),
|
||||
if simple {
|
||||
""
|
||||
} else {
|
||||
"<style>body{max-width:46em;margin:2em auto;font-family:sans-serif;line-height:1.45}img{max-width:100%}hr{border:0;border-top:1px solid #ccc;margin:2em 0}table{border-collapse:collapse;margin:1em 0}td,th{border:1px solid #999;padding:2px 6px;vertical-align:top}</style>"
|
||||
}
|
||||
);
|
||||
for it in items(pages) {
|
||||
match it {
|
||||
@@ -59,13 +71,13 @@ table{{border-collapse:collapse;margin:1em 0}}td,th{{border:1px solid #999;paddi
|
||||
}
|
||||
// The paragraph has its first run's colour; a run in another colour says so.
|
||||
let colour = rgb8(r.block.color);
|
||||
if colour != rgb8(first.color) {
|
||||
if !simple && colour != rgb8(first.color) {
|
||||
let [red, green, blue] = colour;
|
||||
run = format!("<span style=\"color:#{red:02X}{green:02X}{blue:02X}\">{run}</span>");
|
||||
}
|
||||
t.push_str(&run);
|
||||
}
|
||||
let style = hex(first.color).map_or(String::new(), |h| format!(" style=\"color:#{h}\""));
|
||||
let style = if simple { String::new() } else { hex(first.color).map_or(String::new(), |h| format!(" style=\"color:#{h}\"")) };
|
||||
match lvl {
|
||||
0 => s.push_str(&format!("<p{style}>{t}</p>\n")),
|
||||
l => s.push_str(&format!("<h{l}{style}>{t}</h{l}>\n")),
|
||||
@@ -84,7 +96,7 @@ table{{border-collapse:collapse;margin:1em 0}}td,th{{border:1px solid #999;paddi
|
||||
body = format!("<strong>{body}</strong>");
|
||||
}
|
||||
let span = if c.span > 1 { format!(" colspan=\"{}\"", c.span) } else { String::new() };
|
||||
let style = hex(c.color).map_or(String::new(), |h| format!(" style=\"color:#{h}\""));
|
||||
let style = if simple { String::new() } else { hex(c.color).map_or(String::new(), |h| format!(" style=\"color:#{h}\"")) };
|
||||
s.push_str(&format!("<td{span}{style}>{body}</td>"));
|
||||
}
|
||||
s.push_str("</tr>\n");
|
||||
|
||||
@@ -27,9 +27,9 @@ pub(crate) use as_docx::hex;
|
||||
#[cfg(test)]
|
||||
use as_docx::{MAX_MEDIA, docx_table};
|
||||
pub(crate) use as_html::esc;
|
||||
pub use as_html::html;
|
||||
#[cfg(test)]
|
||||
use as_html::{allowed, base64};
|
||||
pub use as_html::{html, html_simple};
|
||||
pub use as_markdown::markdown;
|
||||
#[cfg(test)]
|
||||
use as_markdown::{emphasis, paragraph};
|
||||
|
||||
@@ -85,6 +85,24 @@ fn html_has_headings_paragraphs_and_images_in_order() {
|
||||
assert_eq!(base64(b"Ma"), "TWE=");
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn simple_html_has_no_css_or_layout_elements() {
|
||||
let mut p = page();
|
||||
let mut unicode = block("naïve 日本語.", 72.0, 300.0, 300.0, 311.0);
|
||||
unicode.bold = true;
|
||||
unicode.italic = true;
|
||||
p.blocks.push(unicode);
|
||||
let source = html_simple(&[p, table_page()], "Simple export");
|
||||
for banned in ["<style", "style=", "<div", "<span"] {
|
||||
assert!(!source.contains(banned), "{banned} in {source}");
|
||||
}
|
||||
for wanted in ["<h1", "<p>", "<strong>", "<em>", "<table", "naïve 日本語."] {
|
||||
assert!(source.contains(wanted), "no {wanted} in {source}");
|
||||
}
|
||||
// The rich export of the same pages keeps its stylesheet: only simple mode drops it.
|
||||
assert!(html(&[page()], "Rich").contains("<style"));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn docx_is_a_word_package() {
|
||||
let d = docx(&[page()], "Report");
|
||||
|
||||
@@ -15,12 +15,14 @@ Filter::from_name(b"FlateDecode" | b"Fl" | ...) -> Filter // full names and in
|
||||
Filter::name(&self) -> &str; Filter::is_image_codec(&self) -> bool
|
||||
|
||||
pub struct Params { predictor, colors, bits_per_component, columns, early_change } // i64s; Default = 1, 1, 8, 1, 1
|
||||
pub enum FilterError { Corrupt { filter, detail }, LimitExceeded(usize), Unsupported(String) }
|
||||
pub enum FilterError { Corrupt { filter, detail }, LimitExceeded(usize), Unsupported(String), Spent }
|
||||
|
||||
decode(chain, data, max_output) -> Result<Vec<u8>, FilterError>
|
||||
decode_counted(chain, data, max_output) -> Result<(Vec<u8>, usize /*decoded*/), (FilterError, usize /*decoded*/)>
|
||||
decode_tolerant(chain, data, max_output) -> Result<(Vec<u8>, bool /*partial*/), FilterError>
|
||||
decode_tolerant_counted(chain, data, max_output) -> Result<(Vec<u8>, bool /*partial*/, usize /*decoded*/), (FilterError, usize /*decoded*/)>
|
||||
decode_tolerant_within(chain, data, max_output, work: &mut u64) -> Result<Vec<u8>, FilterError>
|
||||
decode_within(chain, data, max_output, work: &mut u64) -> Result<Vec<u8>, FilterError>
|
||||
encode(filter, params, data) -> Result<Vec<u8>, FilterError>
|
||||
encode_flate(data) -> Vec<u8> // zlib, level 6
|
||||
encode_g4(data, columns, rows) -> Result<Vec<u8>, FilterError> // 1-bit rows as CCITT Group 4; columns <= MAX_G4_COLUMNS
|
||||
@@ -35,6 +37,7 @@ encode_jbig2(data, columns, rows) -> Result<Vec<u8>, FilterError> // 1-bit row
|
||||
- Image codecs (DCT, JPX, JBIG2, CCITT), `Crypt` and unknown filters anywhere in a chain give `Unsupported`: callers keep such data encoded. So does a chain longer than `MAX_CHAIN` (8) filters, before any stage runs. Decryption belongs to `crypt`.
|
||||
- `max_output` bounds every intermediate buffer (including the pre-predictor buffer) and gives `LimitExceeded(max_output)`. This also holds when Flate retries raw deflate after a misleading zlib header, in both strict and tolerant decoding.
|
||||
- `decode_counted` and `decode_tolerant_counted` are for a caller charging a budget (`pdfcraft_cos::DecodeBudget`). `max_output` bounds all stages together (each stage gets what the earlier ones left), and they give the bytes every stage that ran decoded, on success and on failure. A stage's output counts as its decoder produced it, before a predictor or a later stage shrinks it, and a failed decode pays for what it decoded first.
|
||||
- `decode_tolerant_within` is for a run of images (`pdfcraft_cos::ImageBudget`), as `decode_within` (its strict form), `decode_jbig2_within` and `decode_ccitt_within` are, all spending from one `work`, in the JBIG2 decoder's steps. `max_output` bounds each stage, as in `decode_tolerant`, and no stage decodes past what `work` has left. It pays a step a byte of `data` first and a step a byte each stage decodes, so a chain that fails has paid for what it did: 0.2 to 3 ns a byte in or out, up to 19 ns through a predictor on samples of a bit, against the 6 to 16 ns of a JBIG2 step. What `work` can't pay for spends all of it, and gives `Spent`; with nothing left nothing is read. A chain that can't be decoded at all costs nothing and gives its usual error.
|
||||
- `decode_tolerant` turns `Corrupt` into "what was decoded so far" plus `partial = true`, then runs the rest of the chain on it (predictors are applied to partial output too). `LimitExceeded` and `Unsupported` are still errors.
|
||||
|
||||
## Behaviour
|
||||
|
||||
+73
-18
@@ -50,7 +50,7 @@ pub fn encode_g4(data: &[u8], columns: u32, rows: u32) -> Result<Vec<u8>, Filter
|
||||
}
|
||||
}
|
||||
|
||||
/// The widest row [`decode_ccitt`] decodes: its row buffer stays within 128 KiB.
|
||||
/// The widest row [`decode_ccitt_within`] decodes: its row buffer stays within 128 KiB.
|
||||
pub const MAX_CCITT_COLUMNS: u32 = 1 << 20;
|
||||
|
||||
/// A `CCITTFaxDecode` stream's `/DecodeParms` (ISO 32000-2 Table 11). [`Default`] gives the
|
||||
@@ -74,22 +74,8 @@ impl Default for CcittParams {
|
||||
}
|
||||
}
|
||||
|
||||
/// CCITT fax `data` decoded as `CCITTFaxDecode` gives it: rows of `columns` 1-bit samples, most
|
||||
/// significant bit first, each starting on a new byte, with black as 0 (as 1 with `black_is_1`).
|
||||
///
|
||||
/// At most `max_rows` rows are decoded (fewer when `rows` says so), so the output is bounded by
|
||||
/// the caller. Damaged data gives the rows decoded before the damage, as viewers show them: a
|
||||
/// caller that needs a number of rows checks it got them.
|
||||
///
|
||||
/// Group 3 rows on bytes (`k` from 0, `encoded_byte_align`) are read by their end-of-line codes,
|
||||
/// whether the fill starts each code on a byte or ends it on one, when `data` starts with one (T.4
|
||||
/// sends one before the first row when it sends them at all), and on bytes otherwise, whatever
|
||||
/// `end_of_line` says. Group 4 is read as its parameters say. Data with codes but none before the
|
||||
/// first row is read on bytes, as PdfCraft's renderer draws it; with `k` 0 and the fill ending each
|
||||
/// code on a byte, that may be other rows than were coded.
|
||||
///
|
||||
/// Errors: `columns` that aren't from 1 to [`MAX_CCITT_COLUMNS`] ([`FilterError::Unsupported`]).
|
||||
pub fn decode_ccitt(data: &[u8], p: &CcittParams, max_rows: u32) -> Result<Vec<u8>, FilterError> {
|
||||
/// What [`decode_ccitt_within`] decodes once it is paid for.
|
||||
fn decode_ccitt(data: &[u8], p: &CcittParams, max_rows: u32) -> Result<Vec<u8>, FilterError> {
|
||||
let columns = u32::try_from(p.columns)
|
||||
.ok()
|
||||
.filter(|c| (1..=MAX_CCITT_COLUMNS).contains(c))
|
||||
@@ -123,6 +109,39 @@ pub fn decode_ccitt(data: &[u8], p: &CcittParams, max_rows: u32) -> Result<Vec<u
|
||||
Ok(out.out)
|
||||
}
|
||||
|
||||
/// The steps of reading a byte of fax code ([`decode_ccitt_within`]): noise takes 114 ns a byte of
|
||||
/// rows and about two bytes of code to a byte of rows, so that and a step a byte of rows is about
|
||||
/// what a step of JBIG2 decoding takes.
|
||||
const CODE_WORK: u64 = 4;
|
||||
|
||||
/// CCITT fax `data` decoded as `CCITTFaxDecode` gives it: rows of `columns` 1-bit samples, most
|
||||
/// significant bit first, each starting on a new byte, with black as 0 (as 1 with `black_is_1`).
|
||||
///
|
||||
/// At most `max_rows` rows are decoded (fewer when `rows` says so), so the output is bounded by
|
||||
/// the caller. Damaged data gives the rows decoded before the damage, as viewers show them: a
|
||||
/// caller that needs a number of rows checks it got them.
|
||||
///
|
||||
/// Group 3 rows on bytes (`k` from 0, `encoded_byte_align`) are read by their end-of-line codes,
|
||||
/// whether the fill starts each code on a byte or ends it on one, when `data` starts with one (T.4
|
||||
/// sends one before the first row when it sends them at all), and on bytes otherwise, whatever
|
||||
/// `end_of_line` says. Group 4 is read as its parameters say. Data with codes but none before the
|
||||
/// first row is read on bytes, as PdfCraft's renderer draws it; with `k` 0 and the fill ending each
|
||||
/// code on a byte, that may be other rows than were coded.
|
||||
///
|
||||
/// Errors: `columns` that aren't from 1 to [`MAX_CCITT_COLUMNS`] ([`FilterError::Unsupported`]).
|
||||
///
|
||||
/// Decoding spends from `work`, what decoding may still cost across a run of images, and there is
|
||||
/// no way in without it: a
|
||||
/// byte of rows a step, whether or not the data holds them, and [`CODE_WORK`] a byte of `data`.
|
||||
/// A blank row takes a bit of code, so the rows are what a few bytes can ask for. It is all paid
|
||||
/// before anything is decoded, and what `work` can't pay for spends all of it.
|
||||
pub fn decode_ccitt_within(data: &[u8], p: &CcittParams, max_rows: u32, work: &mut u64) -> Result<Vec<u8>, FilterError> {
|
||||
let rows = u32::try_from(p.rows).ok().filter(|r| *r > 0).map_or(max_rows, |r| r.min(max_rows));
|
||||
let stride = u64::try_from(p.columns).unwrap_or(0).div_ceil(8);
|
||||
crate::pay(work, stride.saturating_mul(u64::from(rows)).saturating_add((data.len() as u64).saturating_mul(CODE_WORK)))?;
|
||||
decode_ccitt(data, p, max_rows)
|
||||
}
|
||||
|
||||
/// Whether CCITT fax `data` starts with an end-of-line code: a 1 after 11 zeros or more, fill
|
||||
/// included. T.4 sends one before the first row when it sends them at all, and no other code starts
|
||||
/// with more than eight zeros.
|
||||
@@ -133,7 +152,7 @@ fn starts_with_end_of_line(data: &[u8]) -> bool {
|
||||
|
||||
/// Rows of 1-bit samples filled from a decoder's pixels: `columns` a row, each row on a new byte, at
|
||||
/// most `rows` rows. Pixels past a row's end and rows past the last are dropped. The JBIG2 decoder
|
||||
/// ([`crate::decode_jbig2`]) fills them too.
|
||||
/// ([`crate::decode_jbig2_within`]) fills them too.
|
||||
pub(crate) struct Rows {
|
||||
pub(crate) out: Vec<u8>,
|
||||
row: Vec<u8>,
|
||||
@@ -189,6 +208,42 @@ impl hayro_ccitt::Decoder for Rows {
|
||||
mod tests {
|
||||
use super::*;
|
||||
|
||||
/// A run pays for the rows an image asks for and the code it reads, before any of it is
|
||||
/// decoded: rows the data doesn't hold are paid for too, as a few bytes can ask for any number.
|
||||
#[test]
|
||||
fn a_run_of_images_pays_for_the_rows_it_asks_for() {
|
||||
let (w, h) = (4096u32, 64u32);
|
||||
let stride = (w as usize).div_ceil(8);
|
||||
let data = encode_g4(&vec![0xFF; stride * h as usize], w, h).unwrap();
|
||||
let p = CcittParams { k: -1, columns: i64::from(w), ..CcittParams::default() };
|
||||
let whole = decode_ccitt(&data, &p, h).unwrap();
|
||||
let cost = (whole.len() + 4 * data.len()) as u64;
|
||||
let mut work = cost;
|
||||
assert_eq!(decode_ccitt_within(&data, &p, h, &mut work).unwrap(), whole, "exactly enough");
|
||||
assert_eq!(work, 0);
|
||||
let mut work = cost + 7;
|
||||
decode_ccitt_within(&data, &p, h, &mut work).unwrap();
|
||||
assert_eq!(work, 7, "only what it took");
|
||||
let mut work = cost - 1;
|
||||
let refused = decode_ccitt_within(&data, &p, h, &mut work).unwrap_err();
|
||||
assert!(matches!(refused, FilterError::Spent), "a step short: {refused}");
|
||||
assert_eq!(work, 0, "spends all that was left");
|
||||
// Nothing left: not read at all, so bad columns aren't reported as bad columns.
|
||||
let bad = CcittParams { columns: 0, ..p };
|
||||
assert!(decode_ccitt_within(&data, &bad, h, &mut 0).is_err_and(|e| matches!(e, FilterError::Spent)));
|
||||
// No code at all, for the same rows.
|
||||
let mut work = u64::MAX;
|
||||
decode_ccitt_within(&[], &p, h, &mut work).unwrap();
|
||||
assert_eq!(u64::MAX - work, whole.len() as u64);
|
||||
// `/Rows` below what is asked for, and no rows.
|
||||
let mut work = u64::MAX;
|
||||
decode_ccitt_within(&data, &CcittParams { rows: 3, ..p }, h, &mut work).unwrap();
|
||||
assert_eq!(u64::MAX - work, (3 * stride + 4 * data.len()) as u64);
|
||||
let mut work = u64::MAX;
|
||||
decode_ccitt_within(&data, &p, 0, &mut work).unwrap();
|
||||
assert_eq!(u64::MAX - work, 4 * data.len() as u64);
|
||||
}
|
||||
|
||||
/// The rows decoded by an independent decoder (`hayro-ccitt`), as 1 for white and 0 for black.
|
||||
pub(crate) fn decode(data: &[u8], columns: u32, rows: u32) -> Vec<Vec<bool>> {
|
||||
struct Rows(Vec<Vec<bool>>, Vec<bool>, usize);
|
||||
|
||||
@@ -28,8 +28,9 @@ pub(crate) fn decode(data: &[u8], max: usize) -> Step {
|
||||
// A header that only looked valid: retry the whole input as raw deflate.
|
||||
Err(f) if f.partial.is_empty() && matches!(f.error, crate::FilterError::Corrupt { .. }) => match inflate_raw(data, max) {
|
||||
// Keep the original corruption diagnostic only if the retry is corrupt
|
||||
// too. A limit error must remain fatal even for tolerant decoding.
|
||||
Err(retry) if matches!(retry.error, crate::FilterError::Corrupt { .. }) => Err(f),
|
||||
// too. A limit error must remain fatal even for tolerant decoding. What the
|
||||
// retry decoded isn't kept, but a caller charging for work has to hear of it.
|
||||
Err(retry) if matches!(retry.error, crate::FilterError::Corrupt { .. }) => Err(Failure { discarded: retry.partial.len(), ..f }),
|
||||
retry => retry,
|
||||
},
|
||||
r => r,
|
||||
|
||||
@@ -7,7 +7,7 @@
|
||||
mod decode;
|
||||
mod symbols;
|
||||
|
||||
pub use decode::{MAX_JBIG2_PIXELS, decode_jbig2};
|
||||
pub use decode::{MAX_JBIG2_PIXELS, decode_jbig2_within};
|
||||
|
||||
use crate::FilterError;
|
||||
use crate::mq::{Context, MqEncoder};
|
||||
|
||||
@@ -3,7 +3,7 @@
|
||||
use crate::FilterError;
|
||||
use crate::ccitt::Rows;
|
||||
|
||||
/// The largest JBIG2 page [`decode_jbig2`] decodes, in pixels. The decoder decodes a page whole,
|
||||
/// The largest JBIG2 page [`decode_jbig2_within`] decodes, in pixels. The decoder decodes a page whole,
|
||||
/// and takes pages of up to about this many (20,000 × 10,000 decodes).
|
||||
pub const MAX_JBIG2_PIXELS: u64 = 1 << 28;
|
||||
|
||||
@@ -22,10 +22,23 @@ pub const MAX_JBIG2_PIXELS: u64 = 1 << 28;
|
||||
/// ([`FilterError::Corrupt`]); a page past `max` ([`FilterError::LimitExceeded`]) or
|
||||
/// [`MAX_JBIG2_PIXELS`] ([`FilterError::Unsupported`], or `Corrupt` from the decoder, which has the
|
||||
/// same cap and can refuse the page first).
|
||||
pub fn decode_jbig2(data: &[u8], globals: Option<&[u8]>, columns: u32, rows: u32, max: usize) -> Result<Vec<u8>, FilterError> {
|
||||
///
|
||||
/// Decoding spends from `work`: what decoding may still cost across a run of images, in the
|
||||
/// decoder's count of steps. There is no way in without it, so a run of images can't decode them
|
||||
/// without sharing an allowance. Reading `data` and `globals` is charged first
|
||||
/// ([`hayro_jbig2::charge_reading`]), so an image that turns out not to decode has paid for that,
|
||||
/// then what decoding takes ([`hayro_jbig2::Image::decode_within`]). An image takes at most what
|
||||
/// one decode may on top of its reading and its page, whatever `work` allows, and one that `work`
|
||||
/// can't pay for spends all of it. With nothing left an image isn't read at all, so the images after
|
||||
/// that one cost nothing but this check, however large their globals.
|
||||
pub fn decode_jbig2_within(data: &[u8], globals: Option<&[u8]>, columns: u32, rows: u32, max: usize, work: &mut u64) -> Result<Vec<u8>, FilterError> {
|
||||
if rows == 0 {
|
||||
return Ok(Vec::new());
|
||||
}
|
||||
if *work == 0 {
|
||||
return Err(FilterError::Spent);
|
||||
}
|
||||
hayro_jbig2::charge_reading(work, data.len().saturating_add(globals.map_or(0, <[u8]>::len))).map_err(|_| FilterError::Spent)?;
|
||||
let corrupt = |detail: String| FilterError::Corrupt { filter: "JBIG2Decode", detail };
|
||||
let image = hayro_jbig2::Image::new_embedded(data, globals).map_err(|e| corrupt(e.to_string()))?;
|
||||
let (width, height) = (image.width(), image.height());
|
||||
@@ -41,7 +54,8 @@ pub fn decode_jbig2(data: &[u8], globals: Option<&[u8]>, columns: u32, rows: u32
|
||||
return Err(FilterError::LimitExceeded(max));
|
||||
}
|
||||
let mut out = Rows::new(width, height, false);
|
||||
image.decode(&mut out).map_err(|e| corrupt(e.to_string()))?;
|
||||
// Stopped by what was left, it isn't a damaged image, whatever the decoder calls it.
|
||||
image.decode_within(&mut out, work).map_err(|e| if *work == 0 { FilterError::Spent } else { corrupt(e.to_string()) })?;
|
||||
Ok(out.out)
|
||||
}
|
||||
|
||||
@@ -63,6 +77,12 @@ mod tests {
|
||||
use super::*;
|
||||
use crate::{encode_jbig2, encode_jbig2_generic};
|
||||
|
||||
/// [`decode_jbig2_within`] with no limit on the work.
|
||||
fn decode_jbig2(data: &[u8], globals: Option<&[u8]>, columns: u32, rows: u32, max: usize) -> Result<Vec<u8>, FilterError> {
|
||||
let mut unbounded = u64::MAX;
|
||||
decode_jbig2_within(data, globals, columns, rows, max, &mut unbounded)
|
||||
}
|
||||
|
||||
/// `rows` rows of `columns` samples of noise, the bits that pad each row to a byte 0.
|
||||
fn noise(columns: u32, rows: u32) -> Vec<u8> {
|
||||
let stride = (columns as usize).div_ceil(8);
|
||||
@@ -123,6 +143,45 @@ mod tests {
|
||||
assert_eq!(decode_jbig2(&symbols, None, w, h, usize::MAX).unwrap(), marks);
|
||||
}
|
||||
|
||||
/// What a page costs is the same however much a run has left. Given exactly that it decodes,
|
||||
/// and less stops it: spending all that's left, and what comes after isn't read. A page that
|
||||
/// fails still spends what it took.
|
||||
#[test]
|
||||
fn a_run_of_images_spends_its_allowance_down_to_the_step() {
|
||||
let (w, h) = (203u32, 41u32);
|
||||
let data = encode_jbig2_generic(&noise(w, h), w, h).unwrap();
|
||||
let whole = decode_jbig2(&data, None, w, h, usize::MAX).unwrap();
|
||||
let mut work = u64::MAX;
|
||||
assert_eq!(decode_jbig2_within(&data, None, w, h, usize::MAX, &mut work).unwrap(), whole);
|
||||
let cost = u64::MAX - work;
|
||||
assert!(cost >= u64::from(w) * u64::from(h), "a pixel at a time: {cost}");
|
||||
let mut work = cost;
|
||||
assert_eq!(decode_jbig2_within(&data, None, w, h, usize::MAX, &mut work).unwrap(), whole, "exactly enough");
|
||||
assert_eq!(work, 0);
|
||||
let mut work = cost + 7;
|
||||
decode_jbig2_within(&data, None, w, h, usize::MAX, &mut work).unwrap();
|
||||
assert_eq!(work, 7, "only what it took");
|
||||
let mut work = cost - 1;
|
||||
assert!(matches!(decode_jbig2_within(&data, None, w, h, usize::MAX, &mut work), Err(FilterError::Spent)), "a step short");
|
||||
assert_eq!(work, 0, "spends all that was left");
|
||||
// Nothing left: not read at all, so this garbage isn't reported as garbage.
|
||||
assert!(matches!(decode_jbig2_within(b"garbage", None, w, h, usize::MAX, &mut work), Err(FilterError::Spent)));
|
||||
// Too little even for its page.
|
||||
let mut work = 3;
|
||||
assert!(decode_jbig2_within(&data, None, w, h, usize::MAX, &mut work).is_err());
|
||||
assert_eq!(work, 0);
|
||||
// A region that can't be read after the one that can: the page fails having spent the
|
||||
// first, and the segment it fails on, and that isn't being out of allowance.
|
||||
let bad_region = [0, 0, 0, 9, 38, 0, 1, 0, 0, 0, 1, 0xFF];
|
||||
let mut work = u64::MAX;
|
||||
assert!(decode_jbig2_within(&[&data[..], &bad_region].concat(), None, w, h, usize::MAX, &mut work).is_err());
|
||||
assert_eq!(u64::MAX - work, cost + 1 + 4 * bad_region.len() as u64, "the first region, a segment more, and reading it");
|
||||
// Not a stream at all: it pays for being read, and globals count with it.
|
||||
let mut work = u64::MAX;
|
||||
assert!(matches!(decode_jbig2_within(b"garbage", Some(b"globals"), w, h, usize::MAX, &mut work), Err(FilterError::Corrupt { .. })));
|
||||
assert_eq!(u64::MAX - work, 4 * 14);
|
||||
}
|
||||
|
||||
/// The page has to be the image's size, and is bounded before it is decoded, being decoded
|
||||
/// whole: within `max` as rows of one bit, and within [`MAX_JBIG2_PIXELS`]. Globals are given
|
||||
/// to the decoder: ones it skips decode, ones that aren't JBIG2 are an error, as is damaged
|
||||
|
||||
+272
-26
@@ -7,9 +7,27 @@
|
||||
//! Image codecs (`DCTDecode`, `JPXDecode`, `JBIG2Decode`, `CCITTFaxDecode`),
|
||||
//! `Crypt` and unknown filters are reported as [`FilterError::Unsupported`] so
|
||||
//! callers keep such data encoded. CCITT fax and JBIG2 images decode on their own
|
||||
//! ([`decode_ccitt`], [`decode_jbig2`]), as `pdfcraft_cos::Document::decoded_image`
|
||||
//! does after the filters before them. 1-bit samples can be encoded as CCITT Group 4
|
||||
//! ([`encode_g4`]) or lossless JBIG2 ([`encode_jbig2`]).
|
||||
//! ([`decode_ccitt_within`], [`decode_jbig2_within`]), each spending from an allowance its caller
|
||||
//! shares across a run of images, as `pdfcraft_cos::ImageBudget::decode` does after the filters
|
||||
//! before them. Neither decodes without one:
|
||||
//!
|
||||
//! ```compile_fail
|
||||
//! let _ = pdfcraft_filters::decode_jbig2(&[], None, 1, 1, 1 << 20);
|
||||
//! ```
|
||||
//!
|
||||
//! ```compile_fail
|
||||
//! let _ = pdfcraft_filters::decode_ccitt(&[], &pdfcraft_filters::CcittParams::default(), 1);
|
||||
//! ```
|
||||
//!
|
||||
//! ```
|
||||
//! let mut work = 1 << 20;
|
||||
//! assert!(pdfcraft_filters::decode_jbig2_within(&[], None, 1, 1, 1 << 20, &mut work).is_err());
|
||||
//! let p = pdfcraft_filters::CcittParams { columns: 8, ..Default::default() };
|
||||
//! assert!(pdfcraft_filters::decode_ccitt_within(&[], &p, 1, &mut work).is_ok());
|
||||
//! ```
|
||||
//!
|
||||
//! 1-bit samples can be encoded as CCITT Group 4 ([`encode_g4`]) or lossless JBIG2
|
||||
//! ([`encode_jbig2`]).
|
||||
//!
|
||||
//! Every decoder is bounded by a caller-supplied `max_output` (decompression-bomb
|
||||
//! defence) and never panics on malformed input.
|
||||
@@ -28,8 +46,8 @@ mod runlength;
|
||||
|
||||
use std::borrow::Cow;
|
||||
|
||||
pub use ccitt::{CcittParams, MAX_CCITT_COLUMNS, MAX_G4_COLUMNS, decode_ccitt, encode_g4};
|
||||
pub use jbig2::{MAX_JBIG2_COLUMNS, MAX_JBIG2_PIXELS, decode_jbig2, encode_jbig2, encode_jbig2_generic};
|
||||
pub use ccitt::{CcittParams, MAX_CCITT_COLUMNS, MAX_G4_COLUMNS, decode_ccitt_within, encode_g4};
|
||||
pub use jbig2::{MAX_JBIG2_COLUMNS, MAX_JBIG2_PIXELS, decode_jbig2_within, encode_jbig2, encode_jbig2_generic};
|
||||
|
||||
/// A PDF stream filter, identified by its `/Filter` name.
|
||||
#[derive(Clone, Debug, PartialEq, Eq, Hash)]
|
||||
@@ -91,7 +109,8 @@ impl Filter {
|
||||
matches!(self, Filter::Dct | Filter::Jpx | Filter::Jbig2 | Filter::CcittFax)
|
||||
}
|
||||
|
||||
fn is_decodable(&self) -> bool {
|
||||
/// True for the general-purpose filters, which a chain can hold ([`decode`]).
|
||||
pub fn is_decodable(&self) -> bool {
|
||||
matches!(self, Filter::Flate | Filter::Lzw | Filter::AsciiHex | Filter::Ascii85 | Filter::RunLength)
|
||||
}
|
||||
}
|
||||
@@ -123,33 +142,53 @@ pub enum FilterError {
|
||||
LimitExceeded(usize),
|
||||
#[error("unsupported filter: {0}")]
|
||||
Unsupported(String),
|
||||
/// A run of images has nothing left to spend ([`decode_tolerant_within`]).
|
||||
#[error("more image decoding than one operation may do")]
|
||||
Spent,
|
||||
}
|
||||
|
||||
/// A decoder failure carrying whatever was decoded before the error.
|
||||
pub(crate) struct Failure {
|
||||
pub(crate) error: FilterError,
|
||||
pub(crate) partial: Vec<u8>,
|
||||
/// Bytes decoded on the way that `partial` doesn't hold: they took as long.
|
||||
pub(crate) discarded: usize,
|
||||
}
|
||||
|
||||
impl Failure {
|
||||
pub(crate) fn corrupt(filter: &'static str, detail: impl Into<String>, partial: Vec<u8>) -> Self {
|
||||
Failure { error: FilterError::Corrupt { filter, detail: detail.into() }, partial }
|
||||
Failure { error: FilterError::Corrupt { filter, detail: detail.into() }, partial, discarded: 0 }
|
||||
}
|
||||
|
||||
pub(crate) fn limit(max: usize) -> Self {
|
||||
Failure { error: FilterError::LimitExceeded(max), partial: Vec::new() }
|
||||
Failure { error: FilterError::LimitExceeded(max), partial: Vec::new(), discarded: 0 }
|
||||
}
|
||||
}
|
||||
|
||||
pub(crate) type Step = Result<Vec<u8>, Failure>;
|
||||
|
||||
/// Takes `steps` from `work`, what a run of images may still cost. What it can't pay for spends
|
||||
/// all of it.
|
||||
pub(crate) fn pay(work: &mut u64, steps: u64) -> Result<(), FilterError> {
|
||||
match work.checked_sub(steps) {
|
||||
Some(left) => {
|
||||
*work = left;
|
||||
Ok(())
|
||||
}
|
||||
None => {
|
||||
*work = 0;
|
||||
Err(FilterError::Spent)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/// Decodes `data` through `chain` (first element applied first).
|
||||
///
|
||||
/// Image codecs, `Crypt` and unknown filters anywhere in the chain give
|
||||
/// [`FilterError::Unsupported`] (callers keep such data encoded), as does a chain longer than
|
||||
/// [`MAX_CHAIN`]. `max_output` bounds every intermediate buffer.
|
||||
pub fn decode(chain: &[(Filter, Params)], data: &[u8], max_output: usize) -> Result<Vec<u8>, FilterError> {
|
||||
run(chain, data, max_output, true, false).map(|(v, _, _)| v).map_err(|(e, _)| e)
|
||||
run(chain, data, max_output, None, true).map(|(v, _, _)| v).map_err(|(e, _)| e)
|
||||
}
|
||||
|
||||
/// Like [`decode`] for a caller charging an allowance: `max_output` bounds the bytes all stages
|
||||
@@ -157,47 +196,98 @@ pub fn decode(chain: &[(Filter, Params)], data: &[u8], max_output: usize) -> Res
|
||||
/// bytes, on success and on failure. A stage's output counts even when a later stage or its
|
||||
/// predictor shrinks it.
|
||||
pub fn decode_counted(chain: &[(Filter, Params)], data: &[u8], max_output: usize) -> Result<(Vec<u8>, usize), (FilterError, usize)> {
|
||||
run(chain, data, max_output, true, true).map(|(v, _, spent)| (v, spent))
|
||||
run(chain, data, max_output, Some(max_output), true).map(|(v, _, spent)| (v, spent))
|
||||
}
|
||||
|
||||
/// Like [`decode`], but on corrupt data returns what was decoded before the error and
|
||||
/// reports `partial = true` (the behaviour viewers expect). The remaining filters of the
|
||||
/// chain still run on the partial data. Limit and unsupported errors are still errors.
|
||||
pub fn decode_tolerant(chain: &[(Filter, Params)], data: &[u8], max_output: usize) -> Result<(Vec<u8>, bool), FilterError> {
|
||||
run(chain, data, max_output, false, false).map(|(v, partial, _)| (v, partial)).map_err(|(e, _)| e)
|
||||
run(chain, data, max_output, None, false).map(|(v, partial, _)| (v, partial)).map_err(|(e, _)| e)
|
||||
}
|
||||
|
||||
/// [`decode_tolerant`] bounded and counted as [`decode_counted`] is.
|
||||
pub fn decode_tolerant_counted(chain: &[(Filter, Params)], data: &[u8], max_output: usize) -> Result<(Vec<u8>, bool, usize), (FilterError, usize)> {
|
||||
run(chain, data, max_output, false, true)
|
||||
run(chain, data, max_output, Some(max_output), false)
|
||||
}
|
||||
|
||||
/// [`decode_tolerant`], spending from `work`, what decoding may still cost across a run of images:
|
||||
/// a step for each byte of `data`, paid before anything is decoded, and one for each byte a stage
|
||||
/// decodes, so a chain that fails, or a stage that goes past `max_output`, has paid for what it did.
|
||||
/// No stage decodes past what is left: a chain that `work` can't pay for spends all of it and stops
|
||||
/// there, so with nothing left nothing is read. A chain that can't be decoded at all costs nothing,
|
||||
/// whatever is left, so what an image's filters are is known from the error.
|
||||
///
|
||||
/// Unlike [`decode_tolerant`], no filters at all gives `data` itself, within `max_output`.
|
||||
pub fn decode_tolerant_within(chain: &[(Filter, Params)], data: &[u8], max_output: usize, work: &mut u64) -> Result<Vec<u8>, FilterError> {
|
||||
spending(chain, data, max_output, work, false)
|
||||
}
|
||||
|
||||
/// [`decode`], spending from `work` as [`decode_tolerant_within`] does: corrupt data is an error,
|
||||
/// having paid for what was decoded before it.
|
||||
pub fn decode_within(chain: &[(Filter, Params)], data: &[u8], max_output: usize, work: &mut u64) -> Result<Vec<u8>, FilterError> {
|
||||
spending(chain, data, max_output, work, true)
|
||||
}
|
||||
|
||||
fn spending(chain: &[(Filter, Params)], data: &[u8], max_output: usize, work: &mut u64, strict: bool) -> Result<Vec<u8>, FilterError> {
|
||||
decodable(chain)?;
|
||||
pay(work, data.len() as u64)?;
|
||||
if chain.is_empty() {
|
||||
return if data.len() > max_output { Err(FilterError::LimitExceeded(max_output)) } else { Ok(data.to_vec()) };
|
||||
}
|
||||
let left = usize::try_from(*work).unwrap_or(usize::MAX);
|
||||
match run(chain, data, max_output, Some(left), strict) {
|
||||
Ok((out, _, decoded)) => pay(work, decoded as u64).map(|()| out),
|
||||
// The stage stopped at the lower of the two, which took as much to find out.
|
||||
Err((FilterError::LimitExceeded(_), decoded)) if left.saturating_sub(decoded) > max_output => {
|
||||
pay(work, (decoded as u64).saturating_add(max_output as u64))?;
|
||||
Err(FilterError::LimitExceeded(max_output))
|
||||
}
|
||||
Err((FilterError::LimitExceeded(_), _)) => {
|
||||
*work = 0;
|
||||
Err(FilterError::Spent)
|
||||
}
|
||||
Err((e, decoded)) => pay(work, decoded as u64).and(Err(e)),
|
||||
}
|
||||
}
|
||||
|
||||
/// Longest filter chain decoded. Real streams use one to three filters; every stage may produce
|
||||
/// up to the output limit, so the chain length multiplies the work.
|
||||
pub const MAX_CHAIN: usize = 8;
|
||||
|
||||
/// The decoded data, whether it is partial and the bytes all stages decoded, or the error and
|
||||
/// the bytes decoded before it. `max` bounds each stage, or with `cumulative` all of them
|
||||
/// together.
|
||||
fn run(chain: &[(Filter, Params)], data: &[u8], max: usize, strict: bool, cumulative: bool) -> Result<(Vec<u8>, bool, usize), (FilterError, usize)> {
|
||||
/// Whether a chain is one [`run`] takes, and if not, the error.
|
||||
fn decodable(chain: &[(Filter, Params)]) -> Result<(), FilterError> {
|
||||
if chain.len() > MAX_CHAIN {
|
||||
return Err((FilterError::Unsupported(format!("a chain of {} filters", chain.len())), 0));
|
||||
return Err(FilterError::Unsupported(format!("a chain of {} filters", chain.len())));
|
||||
}
|
||||
if let Some((f, _)) = chain.iter().find(|(f, _)| !f.is_decodable()) {
|
||||
return Err((FilterError::Unsupported(f.name().to_owned()), 0));
|
||||
match chain.iter().find(|(f, _)| !f.is_decodable()) {
|
||||
Some((f, _)) => Err(FilterError::Unsupported(f.name().to_owned())),
|
||||
None => Ok(()),
|
||||
}
|
||||
}
|
||||
|
||||
/// The decoded data, whether it is partial and the bytes all stages decoded, or the error and
|
||||
/// the bytes decoded before it. `max` bounds each stage, and `total` all of them together.
|
||||
fn run(
|
||||
chain: &[(Filter, Params)],
|
||||
data: &[u8],
|
||||
max: usize,
|
||||
total: Option<usize>,
|
||||
strict: bool,
|
||||
) -> Result<(Vec<u8>, bool, usize), (FilterError, usize)> {
|
||||
decodable(chain).map_err(|e| (e, 0))?;
|
||||
let mut cur: Cow<[u8]> = Cow::Borrowed(data);
|
||||
let mut partial = false;
|
||||
let mut spent = 0usize;
|
||||
for (filter, params) in chain {
|
||||
#[cfg(test)]
|
||||
STAGE_BYTES.with(|c| c.set(c.get() + cur.len()));
|
||||
let limit = if cumulative { max.saturating_sub(spent) } else { max };
|
||||
let limit = total.map_or(max, |total| max.min(total.saturating_sub(spent)));
|
||||
let (step, work) = decode_one(filter, params, &cur, limit);
|
||||
spent = spent.saturating_add(work);
|
||||
cur = Cow::Owned(match step {
|
||||
Ok(v) => v,
|
||||
Err(Failure { error: FilterError::Corrupt { .. }, partial: out }) if !strict => {
|
||||
Err(Failure { error: FilterError::Corrupt { .. }, partial: out, .. }) if !strict => {
|
||||
partial = true;
|
||||
out
|
||||
}
|
||||
@@ -216,15 +306,15 @@ fn decode_one(filter: &Filter, params: &Params, data: &[u8], max: usize) -> (Ste
|
||||
Filter::AsciiHex => counted(asciihex::decode(data, max)),
|
||||
Filter::Ascii85 => counted(ascii85::decode(data, max)),
|
||||
Filter::RunLength => counted(runlength::decode(data, max)),
|
||||
other => (Err(Failure { error: FilterError::Unsupported(other.name().to_owned()), partial: Vec::new() }), 0),
|
||||
other => (Err(Failure { error: FilterError::Unsupported(other.name().to_owned()), partial: Vec::new(), discarded: 0 }), 0),
|
||||
}
|
||||
}
|
||||
|
||||
/// A step with the bytes it produced, its output or its partial output.
|
||||
/// A step with the bytes it produced: its output, or its partial output and what it threw away.
|
||||
fn counted(step: Step) -> (Step, usize) {
|
||||
let n = match &step {
|
||||
Ok(v) => v.len(),
|
||||
Err(f) => f.partial.len(),
|
||||
Err(f) => f.partial.len().saturating_add(f.discarded),
|
||||
};
|
||||
(step, n)
|
||||
}
|
||||
@@ -236,12 +326,12 @@ fn with_predictor(step: Step, params: &Params, name: &'static str) -> (Step, usi
|
||||
let (step, n) = counted(step);
|
||||
let step = match step {
|
||||
Ok(v) => predictor::decode(params, v, name),
|
||||
Err(Failure { error, partial }) => {
|
||||
Err(Failure { error, partial, discarded }) => {
|
||||
let partial = match predictor::decode(params, partial, name) {
|
||||
Ok(v) => v,
|
||||
Err(f) => f.partial,
|
||||
};
|
||||
Err(Failure { error, partial })
|
||||
Err(Failure { error, partial, discarded })
|
||||
}
|
||||
};
|
||||
(step, n)
|
||||
@@ -428,6 +518,9 @@ mod tests {
|
||||
assert_eq!(decode(&chain, &data, max).map(|d| d.len()).ok(), Some(1 << 19));
|
||||
assert!(matches!(decode_counted(&chain, &data, max), Err((FilterError::LimitExceeded(m), _)) if m == max));
|
||||
assert_eq!(decode_counted(&chain, &data, 2 << 20).map(|(_, spent)| spent).ok(), Some((1 << 20) + (1 << 19)));
|
||||
let tolerant = decode_tolerant_counted(&chain, &data, 2 << 20).map(|(out, partial, spent)| (out.len(), partial, spent));
|
||||
assert_eq!(tolerant.ok(), Some((1 << 19, false, (1 << 20) + (1 << 19))));
|
||||
assert!(matches!(decode_tolerant_counted(&chain, &data, max), Err((FilterError::LimitExceeded(m), _)) if m == max));
|
||||
}
|
||||
|
||||
/// A PNG predictor drops a tag byte per row, but Flate produced it: the count includes it,
|
||||
@@ -446,4 +539,157 @@ mod tests {
|
||||
assert!(matches!(e, FilterError::Corrupt { .. }), "{e}");
|
||||
assert_eq!(spent, bad.len());
|
||||
}
|
||||
|
||||
fn refused(e: &FilterError) -> bool {
|
||||
matches!(e, FilterError::Spent)
|
||||
}
|
||||
|
||||
/// A chain pays for what it reads and what each stage decodes, down to the byte: Flate inflates
|
||||
/// hex that ASCIIHex halves, so a stage counts when a later one shrinks it.
|
||||
#[test]
|
||||
fn a_chain_spends_down_to_the_byte() {
|
||||
let hex = b"ab".repeat(1 << 10);
|
||||
let data = encode_flate(&hex);
|
||||
let chain = [(Filter::Flate, Params::default()), (Filter::AsciiHex, Params::default())];
|
||||
let whole = decode(&chain, &data, 1 << 20).unwrap();
|
||||
let cost = (data.len() + hex.len() + whole.len()) as u64;
|
||||
let mut work = u64::MAX;
|
||||
assert_eq!(decode_tolerant_within(&chain, &data, 1 << 20, &mut work).unwrap(), whole);
|
||||
assert_eq!(u64::MAX - work, cost);
|
||||
let mut work = cost;
|
||||
assert_eq!(decode_tolerant_within(&chain, &data, 1 << 20, &mut work).unwrap(), whole, "exactly enough");
|
||||
assert_eq!(work, 0);
|
||||
let mut work = cost + 7;
|
||||
decode_tolerant_within(&chain, &data, 1 << 20, &mut work).unwrap();
|
||||
assert_eq!(work, 7, "only what it took");
|
||||
let mut work = cost - 1;
|
||||
assert!(refused(&decode_tolerant_within(&chain, &data, 1 << 20, &mut work).unwrap_err()), "a step short");
|
||||
assert_eq!(work, 0, "spends all that was left");
|
||||
// Each stage has `max_output` to itself, as in a plain decode: together they are past it.
|
||||
let mut work = u64::MAX;
|
||||
assert_eq!(decode_tolerant_within(&chain, &data, hex.len(), &mut work).unwrap(), whole);
|
||||
}
|
||||
|
||||
/// No stage runs past what is left: the first stage of this bomb stops there, so the second
|
||||
/// isn't given anything to read, and with too little to read it nothing runs at all.
|
||||
#[test]
|
||||
fn a_chain_stops_at_what_is_left() {
|
||||
let inner = encode_flate(&vec![0; 1 << 20]);
|
||||
let bomb = encode_flate(&inner);
|
||||
let chain = [(Filter::Flate, Params::default()), (Filter::Flate, Params::default())];
|
||||
let read = |work: u64| {
|
||||
super::STAGE_BYTES.with(|c| c.set(0));
|
||||
let mut work = work;
|
||||
assert!(refused(&decode_tolerant_within(&chain, &bomb, usize::MAX, &mut work).unwrap_err()));
|
||||
assert_eq!(work, 0);
|
||||
super::STAGE_BYTES.with(|c| c.get())
|
||||
};
|
||||
assert_eq!(read((bomb.len() + inner.len()) as u64 + 10), bomb.len() + inner.len(), "the second stage stops");
|
||||
assert_eq!(read(bomb.len() as u64 + 10), bomb.len(), "the first stops, and the second never runs");
|
||||
assert_eq!(read(bomb.len() as u64 - 1), 0, "it can't pay to be read");
|
||||
}
|
||||
|
||||
/// Past `max_output` the chain has failed, and hasn't run out of anything: it pays what it took
|
||||
/// to find out, and what is left stays. Whichever limit a stage stops at is the one reported.
|
||||
#[test]
|
||||
fn a_stage_past_its_limit_pays_for_finding_out() {
|
||||
let data = encode_flate(&vec![0; 1 << 16]);
|
||||
let chain = [(Filter::Flate, Params::default())];
|
||||
let mut work = u64::MAX;
|
||||
assert!(matches!(decode_tolerant_within(&chain, &data, 1000, &mut work), Err(FilterError::LimitExceeded(1000))));
|
||||
assert_eq!(u64::MAX - work, data.len() as u64 + 1000);
|
||||
// The later stage of two, which pays for the first as well.
|
||||
let bomb = encode_flate(&data);
|
||||
let two = [(Filter::Flate, Params::default()), (Filter::Flate, Params::default())];
|
||||
let mut work = u64::MAX;
|
||||
assert!(matches!(decode_tolerant_within(&two, &bomb, data.len(), &mut work), Err(FilterError::LimitExceeded(_))));
|
||||
assert_eq!(u64::MAX - work, (bomb.len() + 2 * data.len()) as u64);
|
||||
// Both limits at once: a run that can't go on is what a caller needs to hear.
|
||||
let mut work = data.len() as u64 + 1000;
|
||||
assert!(refused(&decode_tolerant_within(&chain, &data, 1000, &mut work).unwrap_err()));
|
||||
assert_eq!(work, 0);
|
||||
let mut work = data.len() as u64 + 1001;
|
||||
assert!(matches!(decode_tolerant_within(&chain, &data, 1000, &mut work), Err(FilterError::LimitExceeded(1000))));
|
||||
assert_eq!(work, 1, "the image's limit, with a step to spare");
|
||||
}
|
||||
|
||||
/// What a damaged stream decoded is paid for, however the decode ends.
|
||||
#[test]
|
||||
fn a_chain_that_fails_has_paid_for_what_it_did() {
|
||||
let data: Vec<u8> = (0..20_000u32).map(|i| (i % 97) as u8 ^ (i / 300) as u8).collect();
|
||||
let mut cut = encode_flate(&data);
|
||||
cut.truncate(cut.len() / 2);
|
||||
let chain = [(Filter::Flate, Params::default())];
|
||||
let (partial, _) = decode_tolerant(&chain, &cut, 1 << 20).unwrap();
|
||||
assert!(!partial.is_empty());
|
||||
let mut work = u64::MAX;
|
||||
assert_eq!(decode_tolerant_within(&chain, &cut, 1 << 20, &mut work).unwrap(), partial);
|
||||
assert_eq!(u64::MAX - work, (cut.len() + partial.len()) as u64);
|
||||
// Read strictly it is an error, for the same work.
|
||||
let mut work = u64::MAX;
|
||||
assert!(matches!(decode_within(&chain, &cut, 1 << 20, &mut work), Err(FilterError::Corrupt { .. })));
|
||||
assert_eq!(u64::MAX - work, (cut.len() + partial.len()) as u64);
|
||||
let whole = encode_flate(&data);
|
||||
let mut work = u64::MAX;
|
||||
assert_eq!(decode_within(&chain, &whole, 1 << 20, &mut work).unwrap(), data);
|
||||
assert_eq!(u64::MAX - work, (whole.len() + data.len()) as u64);
|
||||
// A predictor that comes to nothing, after all of this was inflated for it.
|
||||
let p = Params { predictor: 99, ..Params::default() };
|
||||
let data = encode_flate(&vec![0; 1 << 16]);
|
||||
let mut work = u64::MAX;
|
||||
assert!(decode_tolerant_within(&[(Filter::Flate, p)], &data, 1 << 20, &mut work).unwrap().is_empty());
|
||||
assert_eq!(u64::MAX - work, data.len() as u64 + (1 << 16));
|
||||
}
|
||||
|
||||
/// A stream that reads as zlib only until it fails, and as raw deflate until that fails too,
|
||||
/// gives back no data, and has still decoded everything the retry did.
|
||||
#[test]
|
||||
fn a_retry_that_fails_pays_for_what_it_decoded() {
|
||||
// Stored as raw deflate: this many bytes, then a block of a reserved type. As zlib: the
|
||||
// same reserved type at once, so the first reading fails with nothing.
|
||||
let mut data = vec![0x78, 0x01, 0x06, 0xFE, 0xF9];
|
||||
data.extend(vec![0u8; 0x0601]);
|
||||
data.push(0x07);
|
||||
let chain = [(Filter::Flate, Params::default())];
|
||||
let (out, partial) = decode_tolerant(&chain, &data, 1 << 20).unwrap();
|
||||
assert!(out.is_empty() && partial, "what is read stays as it was");
|
||||
let (_, _, spent) = decode_tolerant_counted(&chain, &data, 1 << 20).unwrap();
|
||||
assert_eq!(spent, 0x0601);
|
||||
let (e, spent) = decode_counted(&chain, &data, 1 << 20).unwrap_err();
|
||||
assert!(matches!(e, FilterError::Corrupt { .. }), "{e}");
|
||||
assert_eq!(spent, 0x0601);
|
||||
let mut work = u64::MAX;
|
||||
assert!(decode_tolerant_within(&chain, &data, 1 << 20, &mut work).unwrap().is_empty());
|
||||
assert_eq!(u64::MAX - work, (data.len() + 0x0601) as u64);
|
||||
// Through a predictor, which would otherwise lose the count.
|
||||
let p = Params { predictor: 12, columns: 4, ..Params::default() };
|
||||
let (_, _, spent) = decode_tolerant_counted(&[(Filter::Flate, p)], &data, 1 << 20).unwrap();
|
||||
assert_eq!(spent, 0x0601);
|
||||
}
|
||||
|
||||
/// With nothing left nothing is read. What can't be decoded at all never costs anything, and
|
||||
/// says so whatever is left. Without filters, what is read is the data.
|
||||
#[test]
|
||||
fn what_a_chain_is_shows_whatever_is_left() {
|
||||
let flate = [(Filter::Flate, Params::default())];
|
||||
let mut work = 0;
|
||||
assert!(refused(&decode_tolerant_within(&flate, b"garbage", 1 << 20, &mut work).unwrap_err()));
|
||||
let long = vec![(Filter::Flate, Params::default()); MAX_CHAIN + 1];
|
||||
for chain in [vec![(Filter::Dct, Params::default())], vec![(Filter::Jbig2, Params::default())], long] {
|
||||
for left in [0, 100] {
|
||||
let mut work = left;
|
||||
let e = decode_tolerant_within(&chain, b"data", 1 << 20, &mut work).unwrap_err();
|
||||
assert!(matches!(e, FilterError::Unsupported(_)) && !refused(&e), "{e}");
|
||||
assert_eq!(work, left);
|
||||
}
|
||||
}
|
||||
let mut work = 100;
|
||||
assert_eq!(decode_tolerant_within(&[], b"data", 4, &mut work).unwrap(), b"data");
|
||||
assert_eq!(work, 96);
|
||||
assert!(matches!(decode_tolerant_within(&[], b"data", 3, &mut work), Err(FilterError::LimitExceeded(3))));
|
||||
assert_eq!(work, 92);
|
||||
let mut work = 3;
|
||||
assert!(refused(&decode_tolerant_within(&[], b"data", 4, &mut work).unwrap_err()));
|
||||
assert_eq!(work, 0);
|
||||
}
|
||||
}
|
||||
@@ -227,4 +227,22 @@ mod tests {
|
||||
assert_eq!(parse_num("12abc"), Some(12.0));
|
||||
assert_eq!(parse_num("abc"), None);
|
||||
}
|
||||
|
||||
/// A number prints to at most fifteen significant digits, so the binary noise of a value
|
||||
/// with six digits before the point (279893.88 is 279893.880000000004656… as a double) stays
|
||||
/// hidden, while small values keep their twelve decimals.
|
||||
#[test]
|
||||
fn num_text_prints_at_most_fifteen_significant_digits() {
|
||||
assert_eq!(num_text(279_893.88), "279893.88");
|
||||
assert_eq!(num_text(-279_893.88), "-279893.88");
|
||||
assert_eq!(num_text(279_893.88 + 291_774.12 + 304_171.06 + 317_107.44 + 273_970.85), "1466917.35");
|
||||
assert_eq!(num_text(1_000_000.0 / 3.0), "333333.333333333");
|
||||
assert_eq!(num_text(1.0 / 3.0), "0.333333333333");
|
||||
assert_eq!(num_text(0.3 - 0.1 - 0.2), "0", "noise below twelve decimals is zero");
|
||||
// Past fifteen digits before the point no decimals are left, and the integer keeps its zeros.
|
||||
assert_eq!(num_text(1e15 + 0.5), "1000000000000000");
|
||||
assert_eq!(num_text(1e20), "100000000000000000000");
|
||||
assert_eq!(num_text(-1e20), "-100000000000000000000");
|
||||
assert_eq!(num_text(f64::MAX).len(), 309);
|
||||
}
|
||||
}
|
||||
@@ -21,7 +21,11 @@ pub(super) enum Val {
|
||||
Sink,
|
||||
}
|
||||
|
||||
/// A number as FormCalc prints it: integers without a fraction, otherwise up to 15 digits.
|
||||
/// A number as FormCalc prints it: integers without a fraction, otherwise to at most 12
|
||||
/// decimals and 15 significant digits, without trailing zeros. 15 digits is the most a double
|
||||
/// holds for every value, so a value typed with up to 15 digits prints back as typed
|
||||
/// (`279893.88 * 1` is `279893.88`, not `279893.880000000005`), and the binary noise past
|
||||
/// them never shows. The 12 decimals hide noise left by sums that should be zero.
|
||||
pub(super) fn num_text(n: f64) -> String {
|
||||
if !n.is_finite() {
|
||||
return if n.is_nan() {
|
||||
@@ -35,8 +39,12 @@ pub(super) fn num_text(n: f64) -> String {
|
||||
if n.fract() == 0.0 && n.abs() < 1e15 {
|
||||
return format!("{}", n as i64);
|
||||
}
|
||||
let s = format!("{n:.12}");
|
||||
let s = s.trim_end_matches('0').trim_end_matches('.');
|
||||
// Digits before the point (at most 309 for a finite double); 1 for |n| < 1.
|
||||
let int_digits = format!("{:.0}", n.abs().trunc()).len();
|
||||
let decimals = 15usize.saturating_sub(int_digits).min(12);
|
||||
let s = format!("{n:.decimals$}");
|
||||
// Only a fraction loses its trailing zeros: with no decimals left they belong to the integer.
|
||||
let s = if s.contains('.') { s.trim_end_matches('0').trim_end_matches('.') } else { s.as_str() };
|
||||
if s.is_empty() || s == "-0" { "0".into() } else { s.to_string() }
|
||||
}
|
||||
|
||||
|
||||
@@ -1026,6 +1026,20 @@ mod formcalc {
|
||||
assert_eq!(calc(r#"Format("9.9", -1.5)"#), "-1.5");
|
||||
}
|
||||
|
||||
/// A calculated amount shows the number it is, not the binary noise past a double's 15
|
||||
/// significant digits: 279893.88 is stored as 279893.880000000004656…, which twelve fixed
|
||||
/// decimals printed as `279893.880000000005`. Small values keep their twelve decimals.
|
||||
#[test]
|
||||
fn calculated_numbers_print_at_most_fifteen_significant_digits() {
|
||||
assert_eq!(calc("1 * 279893.88"), "279893.88");
|
||||
assert_eq!(calc("1 * 291774.12"), "291774.12");
|
||||
assert_eq!(calc("279893.88 + 291774.12 + 304171.06 + 317107.44 + 273970.85"), "1466917.35");
|
||||
assert_eq!(calc("1000000 / 3"), "333333.333333333");
|
||||
assert_eq!(calc("1000 / 3"), "333.333333333333");
|
||||
assert_eq!(calc("1 / 3"), "0.333333333333");
|
||||
assert_eq!(calc("0.1 + 0.2"), "0.3");
|
||||
}
|
||||
|
||||
/// Assigning one long value to many fields at once stops at the run's byte budget and is
|
||||
/// charged per copy, and a reset list names each field once.
|
||||
#[test]
|
||||
|
||||
@@ -28,9 +28,10 @@ let report = optimize_with_progress(&mut doc, &settings, &mut |stage| keep_going
|
||||
If a use can't be
|
||||
measured (forms nested deeper, or drawn too many times), no image is resampled. Colour and grayscale images above a
|
||||
threshold are resampled with a bicubic (Catmull-Rom) filter to a target resolution and
|
||||
stored as JPEG (Acrobat's quality steps) or ZIP; soft masks are resampled with their image.
|
||||
stored as JPEG (Acrobat's quality steps) or ZIP; soft masks are resampled with their image. A
|
||||
stencil `/Mask` has its own resolution, so the picture changes under it and it stays as it is.
|
||||
An image is replaced only if the result is smaller. Left alone by these colour and grey
|
||||
settings: CMYK and other colour spaces, image masks, decode arrays, more than 8 bits, JPEG 2000,
|
||||
settings: CMYK and other colour spaces, image masks, colour-key masks, decode arrays, more than 8 bits, JPEG 2000,
|
||||
JBIG2 and CCITT (black-and-white images, CCITT and JBIG2 among them, are below). A JPEG is read with
|
||||
its colour transform (an Adobe marker's, else `/ColorTransform`, ISO 32000-2 §7.4.8), so one
|
||||
stored untransformed keeps its colours; one whose marker and `/ColorTransform` disagree is left
|
||||
@@ -100,13 +101,19 @@ let report = optimize_with_progress(&mut doc, &settings, &mut |stage| keep_going
|
||||
|
||||
- Lossless JBIG2 uses bounded generic-region encoding or exact-copy symbol dictionaries when
|
||||
smaller. No lossy symbol substitution is used. Export, redaction and this step read JBIG2
|
||||
images, with bounded shared globals.
|
||||
images, with bounded shared globals. All of a run's images share one allowance of decoding
|
||||
(`pdfcraft_cos::ImageBudget`), filters, decoders and pixels alike, JPEG samples and merged
|
||||
pictures too: about
|
||||
1,000 scanned pages' worth, plus more for each byte of the file, enough to decode a stream
|
||||
about 8 times at Flate's best. Images past it stay as they are, and `Report::images_refused`
|
||||
counts those the image step read. Streams it only stores with Flate (below) aren't counted.
|
||||
- **Discard objects:** thumbnails, alternate images, document tags, print settings.
|
||||
- **Clean up:** Flate for streams with no filter; for streams with an outer ASCII85 or ASCIIHex
|
||||
layer, that layer is removed when the result is smaller (the inner filters keep their encoded
|
||||
bytes; streams with `/DecodeParms`, images and object streams keep their ASCII layer. LZW-compressed
|
||||
streams, content and images alike, are decoded and stored with Flate instead (Acrobat's "In
|
||||
streams that use LZW encoding, use Flate instead"): a predictor carries over to Flate without
|
||||
streams that use LZW encoding, use Flate instead"), from the run's allowance, past which they
|
||||
stay LZW: a predictor carries over to Flate without
|
||||
`EarlyChange`, filters applied before the LZW one go with it and those after it keep their
|
||||
bytes. A stream whose LZW data doesn't decode cleanly is left as it is. Not yet: inline images.
|
||||
|
||||
|
||||
@@ -18,7 +18,7 @@
|
||||
//! drops them.
|
||||
|
||||
use pdfcraft_content::{Matrix, Op, parse, serialize_ops};
|
||||
use pdfcraft_cos::{DecodeBudget, Dict, Document, ObjRef, Object, Stream};
|
||||
use pdfcraft_cos::{DecodeBudget, Dict, Document, ImageBudget, ObjRef, Object, Stream};
|
||||
|
||||
use crate::images::{components, content_bytes, decodable, page_resources, pixels, resample};
|
||||
use crate::{OptimizeError, Report, Stage};
|
||||
@@ -152,7 +152,7 @@ fn run_end(ops: &[Op], i: usize, count: usize) -> usize {
|
||||
}
|
||||
|
||||
/// The run's pixels as one image, top row first: `(pixels, width, height)`.
|
||||
fn merge(doc: &Document, run: &[Fragment], n: usize) -> Option<(Vec<u8>, u32, u32)> {
|
||||
fn merge(doc: &Document, run: &[Fragment], n: usize, budget: &mut ImageBudget) -> Option<(Vec<u8>, u32, u32)> {
|
||||
let (top, bottom) = (run.first()?.rect[3], run.last()?.rect[1]);
|
||||
let width = run.iter().map(|f| f.width).max()?;
|
||||
// Pixel rows per unit of height: the finest fragment's.
|
||||
@@ -167,7 +167,12 @@ fn merge(doc: &Document, run: &[Fragment], n: usize) -> Option<(Vec<u8>, u32, u3
|
||||
return None;
|
||||
}
|
||||
let row = (width as usize).checked_mul(n)?;
|
||||
let mut out = vec![255u8; row.checked_mul(height as usize)?];
|
||||
// What this builds isn't what its strips cost to read: four small ones can ask for all of it.
|
||||
let bytes = row.checked_mul(height as usize)?;
|
||||
if !budget.pay_pixels(u64::try_from(bytes).ok()?) {
|
||||
return None;
|
||||
}
|
||||
let mut out = vec![255u8; bytes];
|
||||
for f in run {
|
||||
let r0 = (((top - f.rect[3]) * density).round().max(0.0) as u32).min(height);
|
||||
let r1 = (((top - f.rect[1]) * density).round().max(0.0) as u32).min(height);
|
||||
@@ -176,7 +181,7 @@ fn merge(doc: &Document, run: &[Fragment], n: usize) -> Option<(Vec<u8>, u32, u3
|
||||
}
|
||||
let obj = doc.get(f.image);
|
||||
let Object::Stream(s) = &*obj else { return None };
|
||||
let px = pixels(doc, s, n)?;
|
||||
let px = pixels(doc, s, n, budget)?;
|
||||
let px = if (f.width, f.height) == (width, r1 - r0) { px } else { resample(&px, n, f.width, f.height, width, r1 - r0)? };
|
||||
out.get_mut(r0 as usize * row..r1 as usize * row)?.copy_from_slice(px.get(..(r1 - r0) as usize * row)?);
|
||||
}
|
||||
@@ -230,7 +235,13 @@ fn add_xobject(doc: &mut Document, page: ObjRef, name: &[u8], image: ObjRef) ->
|
||||
}
|
||||
|
||||
/// Merge the fragment runs of one page; returns how many fragments were merged.
|
||||
fn merge_page(doc: &mut Document, page: ObjRef, report: &mut Report, progress: &mut dyn FnMut(Stage) -> bool) -> Result<usize, OptimizeError> {
|
||||
fn merge_page(
|
||||
doc: &mut Document,
|
||||
page: ObjRef,
|
||||
report: &mut Report,
|
||||
progress: &mut dyn FnMut(Stage) -> bool,
|
||||
images: &mut ImageBudget,
|
||||
) -> Result<usize, OptimizeError> {
|
||||
let Some(contents) = doc.get(page).as_dict().and_then(|d| d.get(b"Contents").cloned()) else { return Ok(0) };
|
||||
// A page whose content isn't all known is left alone: rewriting it would drop the rest.
|
||||
let Some(data) = content_bytes(doc, &contents, &mut DecodeBudget::page()) else { return Ok(0) };
|
||||
@@ -286,7 +297,7 @@ fn merge_page(doc: &mut Document, page: ObjRef, report: &mut Report, progress: &
|
||||
if !progress(Stage::Fragments) {
|
||||
return Err(OptimizeError::Cancelled);
|
||||
}
|
||||
let Some((px, w, h)) = merge(doc, &run, n) else {
|
||||
let Some((px, w, h)) = merge(doc, &run, n, images) else {
|
||||
out.extend(ops.get(i..j).unwrap_or_default().iter().cloned());
|
||||
i = j;
|
||||
continue;
|
||||
@@ -320,9 +331,15 @@ fn merge_page(doc: &mut Document, page: ObjRef, report: &mut Report, progress: &
|
||||
Ok(merged)
|
||||
}
|
||||
|
||||
pub(crate) fn run(doc: &mut Document, pages: &[ObjRef], report: &mut Report, progress: &mut dyn FnMut(Stage) -> bool) -> Result<(), OptimizeError> {
|
||||
pub(crate) fn run(
|
||||
doc: &mut Document,
|
||||
pages: &[ObjRef],
|
||||
report: &mut Report,
|
||||
progress: &mut dyn FnMut(Stage) -> bool,
|
||||
budget: &mut ImageBudget,
|
||||
) -> Result<(), OptimizeError> {
|
||||
for p in pages {
|
||||
report.fragments_merged += merge_page(doc, *p, report, progress)?;
|
||||
report.fragments_merged += merge_page(doc, *p, report, progress, budget)?;
|
||||
}
|
||||
Ok(())
|
||||
}
|
||||
@@ -343,7 +360,49 @@ mod tests {
|
||||
Fragment { image, rect: [0.0, edge, 1.0, 1.0], width: 1 << 16, height: 1 },
|
||||
Fragment { image, rect: [0.0, 0.0, 1.0, edge], width: 1 << 16, height: 1 },
|
||||
];
|
||||
assert!(merge(&Document::new_empty(), &run, 3).is_none());
|
||||
assert!(merge(&Document::new_empty(), &run, 3, &mut ImageBudget::with_work(u64::MAX)).is_none());
|
||||
}
|
||||
|
||||
/// Merging reads the images the pass after it reads, from the same allowance: with nothing
|
||||
/// left the strips stay as they are, and the budget shows the read it refused.
|
||||
#[test]
|
||||
fn merging_spends_the_runs_allowance() {
|
||||
let mut doc = Document::new_empty();
|
||||
let mut image = Dict::new();
|
||||
for (k, v) in
|
||||
[("Subtype", Object::name("Image")), ("Width", Object::Int(8)), ("Height", Object::Int(1)), ("BitsPerComponent", Object::Int(8))]
|
||||
{
|
||||
image.set(k.as_bytes().to_vec(), v);
|
||||
}
|
||||
image.set(b"ColorSpace".to_vec(), Object::name("DeviceGray"));
|
||||
let (mut xobjects, mut drawn, mut raw) = (Dict::new(), String::new(), 0);
|
||||
for row in 0..8 {
|
||||
let strip = Stream::flate(image.clone(), &[row * 30; 8]);
|
||||
raw += strip.raw.len() as u64;
|
||||
let r = doc.add(Object::Stream(strip));
|
||||
xobjects.set(format!("I{row}").into_bytes(), Object::Ref(r));
|
||||
drawn.push_str(&format!("q 80 0 0 10 0 {} cm /I{row} Do Q\n", 70 - 10 * i32::from(row)));
|
||||
}
|
||||
let content = doc.add(Object::Stream(Stream::flate(Dict::new(), drawn.as_bytes())));
|
||||
let mut resources = Dict::new();
|
||||
resources.set(b"XObject".to_vec(), Object::Dict(xobjects));
|
||||
let mut page = Dict::new();
|
||||
page.set(b"Type".to_vec(), Object::name("Page"));
|
||||
page.set(b"Resources".to_vec(), Object::Dict(resources));
|
||||
page.set(b"Contents".to_vec(), Object::Ref(content));
|
||||
let page = doc.add(Object::Dict(page));
|
||||
let mut budget = ImageBudget::with_work(0);
|
||||
assert_eq!(merge_page(&mut doc.clone(), page, &mut Report::default(), &mut |_| true, &mut budget).unwrap(), 0);
|
||||
assert_eq!(budget.refused(), 1);
|
||||
// Reading each strip, and building the picture of 8 rows of 8 they make.
|
||||
let cost = raw + 8 * (8 + 8) + 8 * 8;
|
||||
let mut budget = ImageBudget::with_work(u64::MAX);
|
||||
assert_eq!(merge_page(&mut doc.clone(), page, &mut Report::default(), &mut |_| true, &mut budget).unwrap(), 8);
|
||||
assert_eq!(u64::MAX - budget.work_left(), cost);
|
||||
// Enough for the strips and not for the picture: nothing is built.
|
||||
let mut budget = ImageBudget::with_work(cost - 1);
|
||||
assert_eq!(merge_page(&mut doc, page, &mut Report::default(), &mut |_| true, &mut budget).unwrap(), 0);
|
||||
assert_eq!(budget.refused(), 1);
|
||||
}
|
||||
|
||||
/// Many images drawn on top of each other are not one picture; looking for runs among them reads
|
||||
@@ -370,7 +429,7 @@ mod tests {
|
||||
page.set(b"Resources".to_vec(), Object::Dict(resources));
|
||||
let page = doc.add(Object::Dict(page));
|
||||
GROUP_READS.with(|c| c.set(0));
|
||||
let merged = merge_page(&mut doc, page, &mut Report::default(), &mut |_| true);
|
||||
let merged = merge_page(&mut doc, page, &mut Report::default(), &mut |_| true, &mut ImageBudget::with_work(u64::MAX));
|
||||
assert_eq!(merged.ok(), Some(0));
|
||||
let reads = GROUP_READS.with(|c| c.get());
|
||||
assert!(reads <= 40 * 4 * groups, "{reads} group reads");
|
||||
|
||||
+329
-22
@@ -4,7 +4,7 @@ use std::collections::{HashMap, HashSet};
|
||||
use std::sync::Arc;
|
||||
|
||||
use pdfcraft_content::{Matrix, Pieces};
|
||||
use pdfcraft_cos::{DecodeBudget, Dict, Document, ObjRef, Object, Stream};
|
||||
use pdfcraft_cos::{DecodeBudget, Dict, Document, ImageBudget, ObjRef, Object, Stream};
|
||||
|
||||
use crate::{Compression, ImageSettings, MonoCompression, MonoSettings, OptimizeError, Report, Settings, Stage};
|
||||
|
||||
@@ -479,7 +479,7 @@ fn count_decoded(_n: u64) {
|
||||
/// every row, and the image would be written back wrong. `None` for a JPEG whose colour transform
|
||||
/// readers may disagree about ([`ycc_encoded`]), and for data that decodes past what the samples
|
||||
/// can need ([`allowance`]).
|
||||
pub(crate) fn pixels(doc: &Document, s: &Stream, n: usize) -> Option<Vec<u8>> {
|
||||
pub(crate) fn pixels(doc: &Document, s: &Stream, n: usize, budget: &mut ImageBudget) -> Option<Vec<u8>> {
|
||||
let (w, h) = (u32::try_from(s.dict.int(b"Width")?).ok()?, u32::try_from(s.dict.int(b"Height")?).ok()?);
|
||||
if w == 0 || h == 0 || u64::from(w) * u64::from(h) > MAX_PIXELS {
|
||||
return None;
|
||||
@@ -490,11 +490,14 @@ pub(crate) fn pixels(doc: &Document, s: &Stream, n: usize) -> Option<Vec<u8>> {
|
||||
// never get here: the colour space check excludes them. The JPEG's own size must be the
|
||||
// dictionary's: `jpeg_samples` refuses another from its header, before any pixels.
|
||||
let ycc = n == 3 && ycc_encoded(doc, s)?;
|
||||
if !budget.pay_jpeg(u64::try_from(bytes).ok()?, &s.raw) {
|
||||
return None;
|
||||
}
|
||||
let v = jpeg_samples(&s.raw, usize::try_from(w).ok()?, usize::try_from(h).ok()?, n, ycc)?;
|
||||
count_decoded(u64::from(w) * u64::from(h));
|
||||
(v.len() == bytes).then_some(v)
|
||||
} else {
|
||||
let v = doc.with_direct_parms(s).decoded_within(allowance(bytes, h)?).ok()?;
|
||||
let v = budget.decode_filters(doc, s, allowance(bytes, h)?).ok()?;
|
||||
Some(v.get(..bytes)?.to_vec())
|
||||
}
|
||||
}
|
||||
@@ -714,12 +717,27 @@ fn image_stream(old: &Dict, px: &[u8], n: usize, w: u32, h: u32, compression: Co
|
||||
}
|
||||
}
|
||||
|
||||
/// Whether a `/Mask` value is a stencil mask: an image that says `/ImageMask true`.
|
||||
fn is_stencil(doc: &Document, mask: &Object) -> bool {
|
||||
matches!(&*doc.resolve(mask), Object::Stream(s) if matches!(s.dict.get(b"ImageMask"), Some(Object::Bool(true))))
|
||||
}
|
||||
|
||||
/// One image: resample and/or recompress per `settings`; `ppi` is its effective resolution.
|
||||
/// Returns the new image and its new soft mask, if the result is smaller.
|
||||
fn process(doc: &Document, s: &Stream, ppi: f64, settings: &ImageSettings, n: usize) -> Option<(Stream, Option<(ObjRef, Stream)>)> {
|
||||
fn process(
|
||||
doc: &Document,
|
||||
s: &Stream,
|
||||
ppi: f64,
|
||||
settings: &ImageSettings,
|
||||
n: usize,
|
||||
budget: &mut ImageBudget,
|
||||
) -> Option<(Stream, Option<(ObjRef, Stream)>)> {
|
||||
let d = &s.dict;
|
||||
// A colour-key mask names sample values, which resampling and JPEG would change. A stencil mask
|
||||
// is an image of its own, with its own resolution (ISO 32000-2 §8.9.6.3): the picture can change
|
||||
// under it and its edges stay as they are.
|
||||
if d.get(b"Decode").is_some_and(|a| !is_identity_decode(doc, a, n))
|
||||
|| d.contains(b"Mask")
|
||||
|| d.get(b"Mask").is_some_and(|m| !is_stencil(doc, m))
|
||||
|| d.name(b"ImageMask").is_some()
|
||||
|| matches!(d.get(b"ImageMask"), Some(Object::Bool(true)))
|
||||
{
|
||||
@@ -748,7 +766,7 @@ fn process(doc: &Document, s: &Stream, ppi: f64, settings: &ImageSettings, n: us
|
||||
} else {
|
||||
(w, h)
|
||||
};
|
||||
let px = pixels(doc, s, n)?;
|
||||
let px = pixels(doc, s, n, budget)?;
|
||||
let px = if (nw, nh) != (w, h) { resample(&px, n, w, h, nw, nh)? } else { px };
|
||||
let new = image_stream(d, &px, n, nw, nh, settings.compression, was_dct)?;
|
||||
// A soft mask must keep the image's dimensions: resample it with the image (lossless).
|
||||
@@ -761,7 +779,7 @@ fn process(doc: &Document, s: &Stream, ppi: f64, settings: &ImageSettings, n: us
|
||||
return None;
|
||||
}
|
||||
let (mw, mh) = (u32::try_from(m.dict.int(b"Width")?).ok()?, u32::try_from(m.dict.int(b"Height")?).ok()?);
|
||||
let mpx = pixels(doc, m, 1)?;
|
||||
let mpx = pixels(doc, m, 1, budget)?;
|
||||
let mpx = resample(&mpx, 1, mw, mh, nw, nh)?;
|
||||
smask = Some((mr, image_stream(&m.dict, &mpx, 1, nw, nh, Compression::Flate, false)?));
|
||||
}
|
||||
@@ -801,7 +819,7 @@ type Pixel = fn(&[u8]) -> Option<bool>;
|
||||
/// with its width and height, and, when they were packed from more bits, its dictionary as a 1-bit
|
||||
/// image. These count:
|
||||
/// - one bit per pixel in one colour component, or an image mask, stored with no filter, with
|
||||
/// general-purpose ones, or with CCITT fax or JBIG2 last ([`Document::decoded_image_within`], no further
|
||||
/// general-purpose ones, or with CCITT fax or JBIG2 last ([`ImageBudget::decode`], no further
|
||||
/// than its rows can need);
|
||||
/// - with `pack`, and with no colour-key `/Mask` (its ranges are in the image's own values):
|
||||
/// - eight-bit grey (one component, not indexed) whose every sample is 0 or 255. A decode array
|
||||
@@ -815,7 +833,7 @@ type Pixel = fn(&[u8]) -> Option<bool>;
|
||||
/// - an indexed image of 2, 4 or 8 bits that uses only palette entries 0 and 1, which stay 0 and
|
||||
/// 1 at one bit, whatever their colours, so the colour space stays. A decode array other than
|
||||
/// the default stops it: in index units it would mean something else at one bit.
|
||||
fn one_bit(doc: &Document, s: &Stream, pack: bool, defaults: bool) -> Option<(Vec<u8>, u32, u32, Option<Dict>)> {
|
||||
fn one_bit(doc: &Document, s: &Stream, pack: bool, defaults: bool, budget: &mut ImageBudget) -> Option<(Vec<u8>, u32, u32, Option<Dict>)> {
|
||||
let d = &s.dict;
|
||||
// Through u32 first, as everywhere here, so the product can't overflow.
|
||||
let (w, h) = (u32::try_from(d.int(b"Width")?).ok()?, u32::try_from(d.int(b"Height")?).ok()?);
|
||||
@@ -836,7 +854,7 @@ fn one_bit(doc: &Document, s: &Stream, pack: bool, defaults: bool) -> Option<(Ve
|
||||
_ => allowance(len, h)?,
|
||||
};
|
||||
count_decoded(u64::from(w) * u64::from(h));
|
||||
let mut data = doc.decoded_image_within(s, max).ok()?;
|
||||
let mut data = budget.decode(doc, s, max).ok()?;
|
||||
if data.len() < len {
|
||||
return None;
|
||||
}
|
||||
@@ -904,7 +922,7 @@ fn one_bit(doc: &Document, s: &Stream, pack: bool, defaults: bool) -> Option<(Ve
|
||||
let row_len = wu.checked_mul(n)?.checked_mul(bpc)?.div_ceil(8);
|
||||
// Through its parameters given by reference too: without a PNG predictor's tag bytes taken
|
||||
// off, rows of 0 and 255 (or palette entries 0 and 1) would still pass below, each shifted.
|
||||
let samples = doc.with_direct_parms(s).decoded_within(allowance(row_len.checked_mul(hu)?, h)?).ok()?;
|
||||
let samples = budget.decode_filters(doc, s, allowance(row_len.checked_mul(hu)?, h)?).ok()?;
|
||||
Some((packed_rows(&samples, row_len, wu, hu, (n, bpc, white))?, w, h, Some(packed)))
|
||||
}
|
||||
|
||||
@@ -1104,7 +1122,7 @@ fn downsample_bits_checked(data: &[u8], w: u32, h: u32, nw: u32, nh: u32, dark_i
|
||||
/// The samples keep their meaning, so the colour space, decode array and `/Mask` stay, but for
|
||||
/// black-and-white RGB, which becomes grey with one decode pair, and an indexed image's default
|
||||
/// decode array, which goes as the default at one bit.
|
||||
fn mono(doc: &Document, s: &Stream, ppi: f64, defaults: bool, settings: &MonoSettings) -> Option<(Stream, bool)> {
|
||||
fn mono(doc: &Document, s: &Stream, ppi: f64, defaults: bool, settings: &MonoSettings, budget: &mut ImageBudget) -> Option<(Stream, bool)> {
|
||||
let d = &s.dict;
|
||||
let downsample = settings.downsample && ppi.is_finite() && ppi > settings.above_ppi && settings.target_ppi > 0.0 && !d.contains(b"SMask");
|
||||
let retain = settings.compression == MonoCompression::Retain;
|
||||
@@ -1118,10 +1136,13 @@ fn mono(doc: &Document, s: &Stream, ppi: f64, defaults: bool, settings: &MonoSet
|
||||
// JBIG2 (whose symbols may be smaller than its own coding) can be smaller stored again alone.
|
||||
let alone_to_g4 = s.filters().len() == 1 && settings.compression == MonoCompression::CcittG4;
|
||||
let only_to_resample = retain || (alone_to_g4 && (jbig2 || fax.is_some_and(|p| p.k < 0)));
|
||||
if only_to_resample && !downsample {
|
||||
// What can't be averaged, whatever it holds, comes to the same `None` below, after a decode that
|
||||
// would spend the run's allowance on it.
|
||||
let too_wide = d.int(b"Width").is_some_and(|w| w > i64::from(pdfcraft_filters::MAX_CCITT_COLUMNS));
|
||||
if only_to_resample && (!downsample || defaults || too_wide || settings.target_ppi >= ppi || (jbig2 && dark_is_one(doc, d).is_none())) {
|
||||
return None;
|
||||
}
|
||||
let (data, w, h, packed) = one_bit(doc, s, !retain, defaults)?;
|
||||
let (data, w, h, packed) = one_bit(doc, s, !retain, defaults, budget)?;
|
||||
let packed_from_more = packed.is_some();
|
||||
let k = settings.target_ppi / ppi;
|
||||
// `downsample_bits` keeps a counter for each column: no more columns than a fax row may have,
|
||||
@@ -1188,12 +1209,15 @@ fn mono(doc: &Document, s: &Stream, ppi: f64, defaults: bool, settings: &MonoSet
|
||||
(best.0 < crate::stored_len(s)?).then_some((best.1, resampled))
|
||||
}
|
||||
|
||||
/// One pass over the document's images, within `budget`. An image past it stays as it is, and is
|
||||
/// counted in the report.
|
||||
pub(crate) fn run(
|
||||
doc: &mut Document,
|
||||
pages: &[ObjRef],
|
||||
settings: &Settings,
|
||||
report: &mut Report,
|
||||
progress: &mut dyn FnMut(Stage) -> bool,
|
||||
budget: &mut ImageBudget,
|
||||
) -> Result<(), OptimizeError> {
|
||||
let (ppi, mut defaults, read) = walk_pages(doc, pages);
|
||||
// Black-and-white RGB becomes grey, which default colour spaces would draw otherwise, and an
|
||||
@@ -1222,10 +1246,11 @@ pub(crate) fn run(
|
||||
let obj = doc.get(r);
|
||||
let Object::Stream(s) = &*obj else { continue };
|
||||
report.images += 1;
|
||||
let refused = budget.refused();
|
||||
// Packed from more bits a sample, it is lossless at one bit, but the grey or colour
|
||||
// settings can make it smaller still (below).
|
||||
let packed_from_more = s.dict.int(b"BitsPerComponent").is_some_and(|b| b > 1);
|
||||
let (packed, mono) = match mono(doc, s, ppi, defaults.contains(&r.num), &settings.mono) {
|
||||
let (packed, mono) = match mono(doc, s, ppi, defaults.contains(&r.num), &settings.mono, budget) {
|
||||
Some(m) if packed_from_more => (Some(m), None),
|
||||
m => (None, m),
|
||||
};
|
||||
@@ -1242,7 +1267,7 @@ pub(crate) fn run(
|
||||
continue;
|
||||
}
|
||||
let n = s.dict.get(b"ColorSpace").and_then(|cs| components(doc, cs));
|
||||
let processed = n.and_then(|n| process(doc, s, ppi, if n == 1 { &settings.gray } else { &settings.color }, n));
|
||||
let processed = n.and_then(|n| process(doc, s, ppi, if n == 1 { &settings.gray } else { &settings.color }, n, budget));
|
||||
// A dithered scan, say, downsampled and JPEG-compressed: the smaller wins, counting a soft
|
||||
// mask resampled with it.
|
||||
let smask_len = |smask: Option<&(ObjRef, Stream)>| match smask {
|
||||
@@ -1268,7 +1293,11 @@ pub(crate) fn run(
|
||||
doc.set(r, Object::Stream(new));
|
||||
continue;
|
||||
}
|
||||
let Some((new, smask)) = processed else { continue };
|
||||
let Some((new, smask)) = processed else {
|
||||
// Read to be packed and again to be resampled, it is still one image, and it stayed.
|
||||
report.images_refused += usize::from(budget.refused() > refused);
|
||||
continue;
|
||||
};
|
||||
let resized = new.dict.int(b"Width") != s.dict.int(b"Width") || new.dict.int(b"Height") != s.dict.int(b"Height");
|
||||
report.image_bytes_before += s.raw.len();
|
||||
report.image_bytes_after += new.raw.len();
|
||||
@@ -1316,13 +1345,16 @@ mod dimension_tests {
|
||||
dict.set(b"Width".to_vec(), Object::Int(width));
|
||||
dict.set(b"Height".to_vec(), Object::Int(height));
|
||||
let stream = Stream::from_raw(dict, vec![0; 4]);
|
||||
assert!(pixels(&Document::new_empty(), &stream, channels).is_none(), "{width} x {height} x {channels}");
|
||||
assert!(
|
||||
pixels(&Document::new_empty(), &stream, channels, &mut ImageBudget::with_work(u64::MAX)).is_none(),
|
||||
"{width} x {height} x {channels}"
|
||||
);
|
||||
}
|
||||
let mut dict = Dict::new();
|
||||
dict.set(b"Width".to_vec(), Object::Int(2));
|
||||
dict.set(b"Height".to_vec(), Object::Int(2));
|
||||
let stream = Stream::from_raw(dict, vec![1, 2, 3, 4, 5]);
|
||||
assert_eq!(pixels(&Document::new_empty(), &stream, 1), Some(vec![1, 2, 3, 4]));
|
||||
assert_eq!(pixels(&Document::new_empty(), &stream, 1, &mut ImageBudget::with_work(u64::MAX)), Some(vec![1, 2, 3, 4]));
|
||||
}
|
||||
|
||||
/// JBIG2 alone, with Group 4 asked for, is decoded only to be resampled. A cost guard: dropped,
|
||||
@@ -1344,7 +1376,7 @@ mod dimension_tests {
|
||||
let settings = MonoSettings { compression: MonoCompression::CcittG4, ..MonoSettings::REDUCE };
|
||||
let decoded = |s: &Stream, settings: &MonoSettings| {
|
||||
DECODED_PIXELS.with(|c| c.set(0));
|
||||
mono(&Document::new_empty(), s, 300.0, false, settings);
|
||||
mono(&Document::new_empty(), s, 300.0, false, settings, &mut ImageBudget::with_work(u64::MAX));
|
||||
DECODED_PIXELS.with(|c| c.get())
|
||||
};
|
||||
let alone = image(Object::name("JBIG2Decode"), coded.clone());
|
||||
@@ -1355,6 +1387,281 @@ mod dimension_tests {
|
||||
assert!(decoded(&alone, &jbig2) > 0, "stored as JBIG2 its symbols may come out smaller");
|
||||
}
|
||||
|
||||
/// A run has one allowance for all its JBIG2 images. Those past it stay as they are, and the
|
||||
/// report says how many: a file of thousands of them can't hold a run for hours.
|
||||
#[test]
|
||||
fn jbig2_images_past_the_runs_allowance_stay_as_they_are() {
|
||||
let coded = pdfcraft_filters::encode_jbig2_generic(&[0xF0; 4], 16, 2).unwrap();
|
||||
let mut dict = Dict::new();
|
||||
dict.set(b"Type".to_vec(), Object::name("XObject"));
|
||||
dict.set(b"Subtype".to_vec(), Object::name("Image"));
|
||||
dict.set(b"Width".to_vec(), Object::Int(16));
|
||||
dict.set(b"Height".to_vec(), Object::Int(2));
|
||||
dict.set(b"BitsPerComponent".to_vec(), Object::Int(1));
|
||||
dict.set(b"ColorSpace".to_vec(), Object::name("DeviceGray"));
|
||||
dict.set(b"Filter".to_vec(), Object::name("JBIG2Decode"));
|
||||
let image = Stream::from_raw(dict, coded);
|
||||
let mut cost = ImageBudget::with_work(u64::MAX);
|
||||
cost.decode(&Document::new_empty(), &image, 1 << 20).unwrap();
|
||||
let cost = u64::MAX - cost.work_left();
|
||||
|
||||
let mut doc = Document::new_empty();
|
||||
let refs = [doc.add(Object::Stream(image.clone())), doc.add(Object::Stream(image.clone())), doc.add(Object::Stream(image.clone()))];
|
||||
let mut xobjects = Dict::new();
|
||||
for (i, r) in refs.iter().enumerate() {
|
||||
xobjects.set(format!("I{i}").into_bytes(), Object::Ref(*r));
|
||||
}
|
||||
let mut resources = Dict::new();
|
||||
resources.set(b"XObject".to_vec(), Object::Dict(xobjects));
|
||||
// Drawn small enough, at 720 ppi, for the settings to resample all three.
|
||||
let content = doc.add(Object::Stream(Stream::flate(Dict::new(), b"q 1.6 0 0 .2 0 0 cm /I0 Do /I1 Do /I2 Do Q")));
|
||||
let mut page = Dict::new();
|
||||
page.set(b"Type".to_vec(), Object::name("Page"));
|
||||
page.set(b"Resources".to_vec(), Object::Dict(resources));
|
||||
page.set(b"Contents".to_vec(), Object::Ref(content));
|
||||
let page = doc.add(Object::Dict(page));
|
||||
|
||||
let settings = Settings { mono: MonoSettings { compression: MonoCompression::CcittG4, ..MonoSettings::REDUCE }, ..Settings::default() };
|
||||
let mut report = Report::default();
|
||||
let mut budget = ImageBudget::with_work(2 * cost);
|
||||
run(&mut doc, &[page], &settings, &mut report, &mut |_| true, &mut budget).unwrap();
|
||||
assert_eq!(report.images_refused, 1);
|
||||
assert_eq!(budget.work_left(), 0, "two decoded and the third refused");
|
||||
assert_eq!(report.images_resampled, 2);
|
||||
let changed = refs.iter().filter(|r| matches!(&*doc.get(**r), Object::Stream(s) if *s != image)).count();
|
||||
assert_eq!(changed, 2, "the third is as it was");
|
||||
}
|
||||
|
||||
/// Images that aren't JBIG2 share the run's allowance too, both on the way to being resampled
|
||||
/// and on the way to being packed to a bit a sample: a file of filter bombs would hold a run
|
||||
/// as long as one of JBIG2, and those past it stay as they are.
|
||||
#[test]
|
||||
fn flate_images_past_the_runs_allowance_stay_as_they_are() {
|
||||
// Noise, resampled, or black and white, packed.
|
||||
let mut seed = 0x2545_F491_4F6C_DD1Du64;
|
||||
let noise: Vec<u8> = (0..256 * 256)
|
||||
.map(|_| {
|
||||
seed ^= seed << 13;
|
||||
seed ^= seed >> 7;
|
||||
seed ^= seed << 17;
|
||||
seed as u8
|
||||
})
|
||||
.collect();
|
||||
let black_and_white: Vec<u8> = noise.iter().map(|v| if v & 1 == 0 { 0 } else { 255 }).collect();
|
||||
for (name, samples, settings) in [
|
||||
("resampled", &noise, Settings::default()),
|
||||
(
|
||||
"packed",
|
||||
&black_and_white,
|
||||
Settings { mono: MonoSettings { compression: MonoCompression::CcittG4, ..MonoSettings::REDUCE }, ..Settings::default() },
|
||||
),
|
||||
] {
|
||||
let page_of = |images: usize| {
|
||||
let mut doc = Document::new_empty();
|
||||
let mut dict = Dict::new();
|
||||
dict.set(b"Subtype".to_vec(), Object::name("Image"));
|
||||
dict.set(b"Width".to_vec(), Object::Int(256));
|
||||
dict.set(b"Height".to_vec(), Object::Int(256));
|
||||
dict.set(b"BitsPerComponent".to_vec(), Object::Int(8));
|
||||
dict.set(b"ColorSpace".to_vec(), Object::name("DeviceGray"));
|
||||
let image = Stream::flate(dict, samples);
|
||||
let refs: Vec<ObjRef> = (0..images).map(|_| doc.add(Object::Stream(image.clone()))).collect();
|
||||
let mut xobjects = Dict::new();
|
||||
let mut drawn = String::from("q 10 0 0 10 0 0 cm ");
|
||||
for (i, r) in refs.iter().enumerate() {
|
||||
xobjects.set(format!("I{i}").into_bytes(), Object::Ref(*r));
|
||||
drawn.push_str(&format!("/I{i} Do "));
|
||||
}
|
||||
drawn.push('Q');
|
||||
let mut resources = Dict::new();
|
||||
resources.set(b"XObject".to_vec(), Object::Dict(xobjects));
|
||||
let content = doc.add(Object::Stream(Stream::flate(Dict::new(), drawn.as_bytes())));
|
||||
let mut page = Dict::new();
|
||||
page.set(b"Type".to_vec(), Object::name("Page"));
|
||||
page.set(b"Resources".to_vec(), Object::Dict(resources));
|
||||
page.set(b"Contents".to_vec(), Object::Ref(content));
|
||||
let page = doc.add(Object::Dict(page));
|
||||
(doc, page, refs, image)
|
||||
};
|
||||
let (mut doc, page, ..) = page_of(1);
|
||||
let mut budget = ImageBudget::with_work(u64::MAX);
|
||||
let mut report = Report::default();
|
||||
run(&mut doc, &[page], &settings, &mut report, &mut |_| true, &mut budget).unwrap();
|
||||
let cost = u64::MAX - budget.work_left();
|
||||
assert!(cost > 0, "{name}");
|
||||
assert_eq!(report.images_refused, 0, "{name}");
|
||||
|
||||
let (mut doc, page, refs, image) = page_of(3);
|
||||
let mut budget = ImageBudget::with_work(2 * cost);
|
||||
let mut report = Report::default();
|
||||
run(&mut doc, &[page], &settings, &mut report, &mut |_| true, &mut budget).unwrap();
|
||||
assert_eq!(report.images_refused, 1, "{name}: {report:?}");
|
||||
assert_eq!(budget.work_left(), 0, "{name}");
|
||||
let changed = refs.iter().filter(|r| matches!(&*doc.get(**r), Object::Stream(s) if *s != image)).count();
|
||||
assert_eq!(changed, 2, "{name}: the third is as it was");
|
||||
}
|
||||
}
|
||||
|
||||
/// An image the allowance ran out on between being packed and being resampled is rewritten,
|
||||
/// as the packed one, so it isn't one that stayed as it was.
|
||||
#[test]
|
||||
fn a_packed_image_isnt_counted_as_refused() {
|
||||
let mut seed = 0x2545_F491_4F6C_DD1Du64;
|
||||
let samples: Vec<u8> = (0..256 * 256)
|
||||
.map(|_| {
|
||||
seed ^= seed << 13;
|
||||
seed ^= seed >> 7;
|
||||
seed ^= seed << 17;
|
||||
if seed & 1 == 0 { 0 } else { 255 }
|
||||
})
|
||||
.collect();
|
||||
let mut doc = Document::new_empty();
|
||||
let mut dict = Dict::new();
|
||||
dict.set(b"Subtype".to_vec(), Object::name("Image"));
|
||||
dict.set(b"Width".to_vec(), Object::Int(256));
|
||||
dict.set(b"Height".to_vec(), Object::Int(256));
|
||||
dict.set(b"BitsPerComponent".to_vec(), Object::Int(8));
|
||||
dict.set(b"ColorSpace".to_vec(), Object::name("DeviceGray"));
|
||||
let image = Stream::flate(dict, &samples);
|
||||
let read = (image.raw.len() + samples.len()) as u64 + 256 * 256;
|
||||
let original = doc.add(Object::Stream(image.clone()));
|
||||
let mut xobjects = Dict::new();
|
||||
xobjects.set(b"I0".to_vec(), Object::Ref(original));
|
||||
let mut resources = Dict::new();
|
||||
resources.set(b"XObject".to_vec(), Object::Dict(xobjects));
|
||||
let content = doc.add(Object::Stream(Stream::flate(Dict::new(), b"q 10 0 0 10 0 0 cm /I0 Do Q")));
|
||||
let mut page = Dict::new();
|
||||
page.set(b"Type".to_vec(), Object::name("Page"));
|
||||
page.set(b"Resources".to_vec(), Object::Dict(resources));
|
||||
page.set(b"Contents".to_vec(), Object::Ref(content));
|
||||
let page = doc.add(Object::Dict(page));
|
||||
let settings = Settings { mono: MonoSettings { compression: MonoCompression::CcittG4, ..MonoSettings::REDUCE }, ..Settings::default() };
|
||||
let mut report = Report::default();
|
||||
let mut budget = ImageBudget::with_work(read);
|
||||
run(&mut doc, &[page], &settings, &mut report, &mut |_| true, &mut budget).unwrap();
|
||||
assert_eq!(budget.refused(), 1, "its second read was refused");
|
||||
assert_eq!(report.images_refused, 0, "{report:?}");
|
||||
assert_eq!(report.images_recompressed + report.images_resampled, 1, "{report:?}");
|
||||
assert!(matches!(&*doc.get(original), Object::Stream(s) if *s != image));
|
||||
}
|
||||
|
||||
/// An image the run has no use for stayed as it was too, but nothing refused it: this one is
|
||||
/// too small to compress and drawn at no more than its size.
|
||||
#[test]
|
||||
fn an_image_left_alone_isnt_counted_as_refused() {
|
||||
let mut doc = Document::new_empty();
|
||||
let mut dict = Dict::new();
|
||||
dict.set(b"Subtype".to_vec(), Object::name("Image"));
|
||||
dict.set(b"Width".to_vec(), Object::Int(8));
|
||||
dict.set(b"Height".to_vec(), Object::Int(8));
|
||||
dict.set(b"BitsPerComponent".to_vec(), Object::Int(8));
|
||||
dict.set(b"ColorSpace".to_vec(), Object::name("DeviceGray"));
|
||||
let image = doc.add(Object::Stream(Stream::flate(dict, &[0x80; 64])));
|
||||
let mut xobjects = Dict::new();
|
||||
xobjects.set(b"I0".to_vec(), Object::Ref(image));
|
||||
let mut resources = Dict::new();
|
||||
resources.set(b"XObject".to_vec(), Object::Dict(xobjects));
|
||||
let content = doc.add(Object::Stream(Stream::flate(Dict::new(), b"q 72 0 0 72 0 0 cm /I0 Do Q")));
|
||||
let mut page = Dict::new();
|
||||
page.set(b"Type".to_vec(), Object::name("Page"));
|
||||
page.set(b"Resources".to_vec(), Object::Dict(resources));
|
||||
page.set(b"Contents".to_vec(), Object::Ref(content));
|
||||
let page = doc.add(Object::Dict(page));
|
||||
let mut report = Report::default();
|
||||
run(&mut doc, &[page], &Settings::default(), &mut report, &mut |_| true, &mut ImageBudget::with_work(u64::MAX)).unwrap();
|
||||
assert_eq!((report.images, report.images_refused), (1, 0), "{report:?}");
|
||||
}
|
||||
|
||||
/// A JPEG pays for its samples before it is decoded, however few bytes it takes: past what is
|
||||
/// left it isn't, and counts as refused.
|
||||
#[test]
|
||||
fn a_jpeg_pays_for_its_samples() {
|
||||
let mut dict = Dict::new();
|
||||
dict.set(b"Width".to_vec(), Object::Int(16));
|
||||
dict.set(b"Height".to_vec(), Object::Int(8));
|
||||
dict.set(b"BitsPerComponent".to_vec(), Object::Int(8));
|
||||
dict.set(b"ColorSpace".to_vec(), Object::name("DeviceRGB"));
|
||||
let jpeg = image_stream(&dict, &[120; 16 * 8 * 3], 3, 16, 8, Compression::Jpeg(60), false).expect("a JPEG");
|
||||
let doc = Document::new_empty();
|
||||
let cost = 2 * 16 * 8 * 3 + 4 * jpeg.raw.len() as u64;
|
||||
let mut budget = ImageBudget::with_work(cost);
|
||||
assert_eq!(pixels(&doc, &jpeg, 3, &mut budget).map(|p| p.len()), Some(16 * 8 * 3));
|
||||
assert_eq!((budget.work_left(), budget.refused()), (0, 0), "exactly that");
|
||||
let mut budget = ImageBudget::with_work(cost - 1);
|
||||
assert!(pixels(&doc, &jpeg, 3, &mut budget).is_none());
|
||||
assert_eq!((budget.work_left(), budget.refused()), (0, 1));
|
||||
}
|
||||
|
||||
/// A soft mask resampled with its image is read from the same allowance as the image.
|
||||
#[test]
|
||||
fn a_soft_mask_resampled_with_its_image_spends_the_allowance() {
|
||||
let mut seed = 0x2545_F491_4F6C_DD1Du64;
|
||||
let noise: Vec<u8> = (0..256 * 256)
|
||||
.map(|_| {
|
||||
seed ^= seed << 13;
|
||||
seed ^= seed >> 7;
|
||||
seed ^= seed << 17;
|
||||
seed as u8
|
||||
})
|
||||
.collect();
|
||||
let image = |space: &str| {
|
||||
let mut dict = Dict::new();
|
||||
dict.set(b"Subtype".to_vec(), Object::name("Image"));
|
||||
dict.set(b"Width".to_vec(), Object::Int(256));
|
||||
dict.set(b"Height".to_vec(), Object::Int(256));
|
||||
dict.set(b"BitsPerComponent".to_vec(), Object::Int(8));
|
||||
dict.set(b"ColorSpace".to_vec(), Object::name(space));
|
||||
Stream::flate(dict, &noise)
|
||||
};
|
||||
let mut doc = Document::new_empty();
|
||||
let mask = image("DeviceGray");
|
||||
let cost = (mask.raw.len() + noise.len()) as u64 + 256 * 256;
|
||||
let masked = doc.add(Object::Stream(mask));
|
||||
let mut with_mask = image("DeviceGray");
|
||||
with_mask.dict.set(b"SMask".to_vec(), Object::Ref(masked));
|
||||
let spent = |s: &Stream| {
|
||||
let mut budget = ImageBudget::with_work(u64::MAX);
|
||||
process(&doc, s, 720.0, &Settings::default().gray, 1, &mut budget).expect("resampled, and smaller");
|
||||
u64::MAX - budget.work_left()
|
||||
};
|
||||
assert_eq!(spent(&with_mask), spent(&image("DeviceGray")) + cost);
|
||||
}
|
||||
|
||||
/// Decoded only to be resampled, what can't be averaged whatever it holds isn't decoded, so it
|
||||
/// takes nothing from the images that can be, and isn't counted as refused past the allowance.
|
||||
#[test]
|
||||
fn a_jbig2_image_that_cant_be_averaged_spends_nothing() {
|
||||
let image = |edit: &dyn Fn(&mut Dict)| {
|
||||
let mut dict = Dict::new();
|
||||
dict.set(b"Subtype".to_vec(), Object::name("Image"));
|
||||
dict.set(b"Width".to_vec(), Object::Int(16));
|
||||
dict.set(b"Height".to_vec(), Object::Int(2));
|
||||
dict.set(b"BitsPerComponent".to_vec(), Object::Int(1));
|
||||
dict.set(b"ColorSpace".to_vec(), Object::name("DeviceGray"));
|
||||
dict.set(b"Filter".to_vec(), Object::name("JBIG2Decode"));
|
||||
edit(&mut dict);
|
||||
Stream::from_raw(dict, pdfcraft_filters::encode_jbig2_generic(&[0xF0; 4], 16, 2).unwrap())
|
||||
};
|
||||
let spent_at = |target_ppi: f64, s: &Stream, defaults: bool| {
|
||||
let settings = MonoSettings { compression: MonoCompression::Retain, above_ppi: 100.0, target_ppi, ..MonoSettings::REDUCE };
|
||||
let mut budget = ImageBudget::with_work(u64::MAX);
|
||||
let _ = mono(&Document::new_empty(), s, 720.0, defaults, &settings, &mut budget);
|
||||
u64::MAX - budget.work_left()
|
||||
};
|
||||
let spent = |s: &Stream, defaults: bool| spent_at(300.0, s, defaults);
|
||||
let plain = image(&|_| {});
|
||||
assert_eq!(spent_at(720.0, &plain, false), 0, "already at the target");
|
||||
assert!(spent_at(719.0, &plain, false) > 0, "just above it");
|
||||
assert!(spent(&plain, false) > 0, "one that can be averaged is decoded");
|
||||
assert_eq!(spent(&plain, true), 0, "drawn where a device colour space is remapped");
|
||||
let width = |w: i64| image(&move |d| d.set(b"Width".to_vec(), Object::Int(w)));
|
||||
let widest = i64::from(pdfcraft_filters::MAX_CCITT_COLUMNS);
|
||||
assert!(spent(&width(widest), false) > 0, "the widest that can be averaged is decoded");
|
||||
assert_eq!(spent(&width(widest + 1), false), 0, "too wide to average");
|
||||
let tinted = image(&|d| d.set(b"ColorSpace".to_vec(), Object::Array(vec![Object::name("CalGray"), Object::Dict(Dict::new())])));
|
||||
assert_eq!(spent(&tinted, false), 0, "no way to tell which sample is dark");
|
||||
}
|
||||
|
||||
/// A JPEG larger than its dictionary says is refused from its header, before its pixels are decoded.
|
||||
#[test]
|
||||
fn a_jpeg_of_another_size_than_its_dictionary_is_not_decoded() {
|
||||
@@ -1367,9 +1674,9 @@ mod dimension_tests {
|
||||
Stream::from_raw(dict, data.clone())
|
||||
};
|
||||
DECODED_PIXELS.with(|c| c.set(0));
|
||||
assert!(pixels(&Document::new_empty(), &stream(10, 10), 1).is_none());
|
||||
assert!(pixels(&Document::new_empty(), &stream(10, 10), 1, &mut ImageBudget::with_work(u64::MAX)).is_none());
|
||||
assert_eq!(DECODED_PIXELS.with(|c| c.get()), 0, "pixels decoded");
|
||||
assert_eq!(pixels(&Document::new_empty(), &stream(1000, 1000), 1).map(|p| p.len()), Some(1000 * 1000));
|
||||
assert_eq!(pixels(&Document::new_empty(), &stream(1000, 1000), 1, &mut ImageBudget::with_work(u64::MAX)).map(|p| p.len()), Some(1000 * 1000));
|
||||
}
|
||||
|
||||
/// Resampling goes through no more than one of the two sizes holds, whatever their proportions:
|
||||
|
||||
+47
-10
@@ -36,7 +36,7 @@ mod unused;
|
||||
|
||||
pub use audit::{SpaceCategory, SpaceUse, audit_space};
|
||||
|
||||
use pdfcraft_cos::{Dict, Document, MAX_PAGE_DECODED, ObjRef, Object, Stream, serialize};
|
||||
use pdfcraft_cos::{Dict, Document, ImageBudget, MAX_PAGE_DECODED, ObjRef, Object, Stream, serialize};
|
||||
use pdfcraft_filters::{Filter, Params};
|
||||
|
||||
pub use images::effective_resolutions;
|
||||
@@ -279,6 +279,8 @@ pub struct Report {
|
||||
pub images: usize,
|
||||
pub images_resampled: usize,
|
||||
pub images_recompressed: usize,
|
||||
/// Images left as they are: decoding them all would take more than one run may spend.
|
||||
pub images_refused: usize,
|
||||
/// Encoded image bytes before and after (images that changed).
|
||||
pub image_bytes_before: usize,
|
||||
pub image_bytes_after: usize,
|
||||
@@ -329,10 +331,12 @@ pub fn optimize_with_progress(doc: &mut Document, settings: &Settings, progress:
|
||||
}
|
||||
let mut report = Report::default();
|
||||
let pages = pdfcraft_annot::page_refs(doc).map_err(|_| OptimizeError::NoPages)?;
|
||||
// Merging fragments, the image pass and the LZW pass read the same images, so they share it.
|
||||
let mut budget = ImageBudget::new(doc);
|
||||
if settings.merge_fragments {
|
||||
fragments::run(doc, &pages, &mut report, progress)?;
|
||||
fragments::run(doc, &pages, &mut report, progress, &mut budget)?;
|
||||
}
|
||||
images::run(doc, &pages, settings, &mut report, progress)?;
|
||||
images::run(doc, &pages, settings, &mut report, progress, &mut budget)?;
|
||||
if !progress(Stage::CleanUp) {
|
||||
return Err(OptimizeError::Cancelled);
|
||||
}
|
||||
@@ -428,7 +432,11 @@ pub fn optimize_with_progress(doc: &mut Document, settings: &Settings, progress:
|
||||
let r = ObjRef { num, generation: doc.generation(num) };
|
||||
let obj = doc.get(r);
|
||||
let Object::Stream(s) = &*obj else { continue };
|
||||
if let Some(replacement) = lzw_to_flate(s, MAX_LZW_DECODED) {
|
||||
// Each can take a second or more, of a pass that has no other way to stop.
|
||||
if s.filters().iter().any(|(f, _)| *f == Filter::Lzw) && !progress(Stage::CleanUp) {
|
||||
return Err(OptimizeError::Cancelled);
|
||||
}
|
||||
if let Some(replacement) = lzw_to_flate(s, MAX_LZW_DECODED, &mut budget) {
|
||||
doc.set(r, Object::Stream(replacement));
|
||||
report.lzw_streams += 1;
|
||||
}
|
||||
@@ -463,14 +471,17 @@ pub fn optimize_with_progress(doc: &mut Document, settings: &Settings, progress:
|
||||
/// Largest decoded LZW stream converted, as for a page's content: the data and its check are
|
||||
/// held together, so a few hundred kilobytes of hostile LZW can't ask for gigabytes.
|
||||
const MAX_LZW_DECODED: usize = MAX_PAGE_DECODED;
|
||||
/// The steps of a run's allowance a decoded byte costs to store with Flate and read back: up to
|
||||
/// 78 ns a byte to encode and 4 to check, at the 6 to 16 ns of a step.
|
||||
const LZW_REWRITE_WORK: u64 = 8;
|
||||
|
||||
/// `s` with its LZW compression replaced by Flate (Acrobat's "In streams that use LZW encoding,
|
||||
/// use Flate instead"). The filters up to the last LZW one are decoded, strictly and with its
|
||||
/// predictor; the result is Flate-encoded under the same predictor, without `EarlyChange`, and
|
||||
/// the filters after it keep their encoded bytes. A stream that doesn't decode cleanly, or
|
||||
/// whose filters or parameters can't be read for certain, or that decodes past `max` bytes, is
|
||||
/// left as it is.
|
||||
fn lzw_to_flate(s: &Stream, max: usize) -> Option<Stream> {
|
||||
/// whose filters or parameters can't be read for certain, or that decodes past `max` bytes or
|
||||
/// what `budget` has left, is left as it is.
|
||||
fn lzw_to_flate(s: &Stream, max: usize, budget: &mut ImageBudget) -> Option<Stream> {
|
||||
// An external file's data isn't in `raw`; cross-reference and object streams are rewritten
|
||||
// on save, so converting them would change nothing in the file.
|
||||
if s.dict.contains(b"F") || matches!(s.dict.name(b"Type"), Some(b"XRef" | b"ObjStm")) {
|
||||
@@ -513,7 +524,10 @@ fn lzw_to_flate(s: &Stream, max: usize) -> Option<Stream> {
|
||||
if !parms.get(..=lzw)?.iter().all(direct) {
|
||||
return None;
|
||||
}
|
||||
let data = pdfcraft_filters::decode(stages, &s.raw, max).ok()?;
|
||||
let data = budget.decode_chain(stages, &s.raw, max).ok()?;
|
||||
if !budget.spend((data.len() as u64).saturating_mul(LZW_REWRITE_WORK)) {
|
||||
return None;
|
||||
}
|
||||
let flate = Params { early_change: 1, ..params.clone() };
|
||||
let raw = pdfcraft_filters::encode(&Filter::Flate, &flate, &data).ok()?;
|
||||
// The predictor's encoder must give back exactly what its decoder read (a short last row,
|
||||
@@ -597,8 +611,31 @@ mod tests {
|
||||
let mut dict = Dict::new();
|
||||
dict.set(b"Filter".to_vec(), Object::name("LZWDecode"));
|
||||
let s = Stream::from_raw(dict, raw);
|
||||
assert!(lzw_to_flate(&s, data.len() - 1).is_none());
|
||||
let converted = lzw_to_flate(&s, data.len()).unwrap();
|
||||
let mut budget = ImageBudget::with_work(u64::MAX);
|
||||
assert!(lzw_to_flate(&s, data.len() - 1, &mut budget).is_none());
|
||||
let converted = lzw_to_flate(&s, data.len(), &mut budget).unwrap();
|
||||
assert_eq!(converted.decoded_strict().unwrap(), data);
|
||||
}
|
||||
|
||||
/// Rewriting a stream spends the run's allowance: reading it, decoding it, and storing and
|
||||
/// checking what it decoded. One the allowance can't pay for stays LZW, and ends the rewriting.
|
||||
#[test]
|
||||
fn lzw_streams_spend_the_runs_allowance() {
|
||||
let data = b"0 0 m 612 792 l S\n".repeat(64);
|
||||
let raw = pdfcraft_filters::encode(&Filter::Lzw, &Params::default(), &data).unwrap();
|
||||
let mut dict = Dict::new();
|
||||
dict.set(b"Filter".to_vec(), Object::name("LZWDecode"));
|
||||
let s = Stream::from_raw(dict, raw);
|
||||
let cost = (s.raw.len() + data.len()) as u64 + data.len() as u64 * LZW_REWRITE_WORK;
|
||||
let mut budget = ImageBudget::with_work(cost + 7);
|
||||
assert!(lzw_to_flate(&s, data.len(), &mut budget).is_some());
|
||||
assert_eq!(budget.work_left(), 7);
|
||||
let mut budget = ImageBudget::with_work(cost);
|
||||
assert!(lzw_to_flate(&s, data.len(), &mut budget).is_some(), "exactly enough");
|
||||
assert_eq!(budget.work_left(), 0);
|
||||
let mut budget = ImageBudget::with_work(cost - 1);
|
||||
assert!(lzw_to_flate(&s, data.len(), &mut budget).is_none(), "a step short");
|
||||
assert_eq!(budget.work_left(), 0, "and the next stream isn't read");
|
||||
assert!(lzw_to_flate(&s, data.len(), &mut budget).is_none());
|
||||
}
|
||||
}
|
||||
@@ -9,6 +9,12 @@ use pdfcraft_optimize::{
|
||||
effective_resolutions, optimize,
|
||||
};
|
||||
|
||||
/// What image `s` decodes to, its fax or JBIG2 data included, with no limit on the work: the
|
||||
/// samples an operation would read through its `ImageBudget`.
|
||||
fn decoded_image(doc: &Document, s: &Stream) -> Result<Vec<u8>, pdfcraft_cos::CosError> {
|
||||
pdfcraft_cos::ImageBudget::with_work(u64::MAX).decode(doc, s, pdfcraft_cos::MAX_DECODED)
|
||||
}
|
||||
|
||||
fn image(doc: &mut Document, w: u32, h: u32, n: usize, jpeg: bool, smask: Option<ObjRef>) -> ObjRef {
|
||||
// A smooth gradient with a little texture (photo-like).
|
||||
let mut px = Vec::with_capacity((w * h) as usize * n);
|
||||
@@ -910,7 +916,7 @@ fn rgb_and_two_colour_indexed_black_and_white_images_become_one_bit() {
|
||||
(Some(1), Some(&b"CCITTFaxDecode"[..]), Some(&cs)),
|
||||
"{i:?}"
|
||||
);
|
||||
assert_eq!(doc.decoded_image(&s).unwrap(), text, "{i:?}");
|
||||
assert_eq!(decoded_image(&doc, &s).unwrap(), text, "{i:?}");
|
||||
let decode = if i == rgb_inverted { Some(Object::Array(vec![1.into(), 0.into()])) } else { None };
|
||||
assert_eq!(s.dict.get(b"Decode").cloned(), decode, "{i:?}");
|
||||
}
|
||||
@@ -1066,7 +1072,7 @@ fn retain_keeps_a_group_3_halftone_as_it_is() {
|
||||
let fax = doc.add(Object::Stream(Stream::from_raw(d, g3.clone())));
|
||||
// 7.68 pt for 64 samples is 600 ppi.
|
||||
page(&mut doc, &[("A", fax)], "q 7.68 0 0 7.68 100 600 cm /A Do Q");
|
||||
assert_eq!(doc.decoded_image(&stream(&doc, fax)).unwrap().len(), 64 * 8, "the fixture decodes");
|
||||
assert_eq!(decoded_image(&doc, &stream(&doc, fax)).unwrap().len(), 64 * 8, "the fixture decodes");
|
||||
let r = optimize(&mut doc, &Settings { mono: RETAIN, ..Settings::default() }).unwrap();
|
||||
assert_eq!((r.images_resampled, r.images_recompressed), (0, 0), "{r:?}");
|
||||
assert_eq!(stream(&doc, fax).raw[..], g3[..]);
|
||||
@@ -1564,7 +1570,7 @@ fn ambiguous_monochrome_text_is_recompressed_without_lossy_reduction() {
|
||||
}
|
||||
assert_eq!(raw(&kept, hex_at_400), raw(&doc, hex_at_400), "and nothing else changes");
|
||||
for i in [flate, fax, hex_fax] {
|
||||
assert_eq!((size(&kept, i), kept.decoded_image(&stream(&kept, i)).unwrap()), ((1200, 480), text.clone()), "{i:?}");
|
||||
assert_eq!((size(&kept, i), decoded_image(&kept, &stream(&kept, i)).unwrap()), ((1200, 480), text.clone()), "{i:?}");
|
||||
}
|
||||
let bits = [eight, rgb, rgb_inverted].map(|i| stream(&kept, i).dict.int(b"BitsPerComponent"));
|
||||
assert_eq!(bits, [Some(8); 3], "Retain leaves eight bits to the grey and colour settings");
|
||||
@@ -1578,7 +1584,7 @@ fn ambiguous_monochrome_text_is_recompressed_without_lossy_reduction() {
|
||||
let s = stream(&doc, i);
|
||||
assert_eq!((size(&doc, i), s.dict.int(b"BitsPerComponent")), ((1200, 480), if i == mask { None } else { Some(1) }));
|
||||
assert!(matches!(s.filters().as_slice(), [(Filter::CcittFax | Filter::Flate, _)]), "{i:?}");
|
||||
assert_eq!(doc.decoded_image(&s).unwrap(), text.clone(), "{i:?}");
|
||||
assert_eq!(decoded_image(&doc, &s).unwrap(), text.clone(), "{i:?}");
|
||||
}
|
||||
assert_eq!(stream(&doc, mask).dict.get(b"Decode"), Some(&decode), "the decode array stays");
|
||||
// Grey now, with grey's decode pair, which makes 1 black: its ties are black too.
|
||||
@@ -1588,12 +1594,12 @@ fn ambiguous_monochrome_text_is_recompressed_without_lossy_reduction() {
|
||||
(size(&doc, rgb_inverted), s.dict.get(b"ColorSpace"), s.dict.get(b"Decode")),
|
||||
((1200, 480), Some(&Object::name("DeviceGray")), Some(&inverting))
|
||||
);
|
||||
assert_eq!(doc.decoded_image(&s).unwrap(), text.iter().map(|b| !b).collect::<Vec<u8>>(), "the same picture, ties black");
|
||||
assert_eq!(decoded_image(&doc, &s).unwrap(), text.iter().map(|b| !b).collect::<Vec<u8>>(), "the same picture, ties black");
|
||||
for i in [at_400, soft, hex_at_400] {
|
||||
assert_eq!((size(&doc, i), stream(&doc, i).dict.name(b"Filter")), ((1200, 480), Some(&b"CCITTFaxDecode"[..])), "{i:?}");
|
||||
}
|
||||
assert!(raw(&doc, hex_at_400).len() < hex_len, "the ASCIIHexDecode is dropped");
|
||||
assert_eq!(doc.decoded_image(&stream(&doc, hex_at_400)).unwrap(), text, "and the picture kept");
|
||||
assert_eq!(decoded_image(&doc, &stream(&doc, hex_at_400)).unwrap(), text, "and the picture kept");
|
||||
assert_eq!([fax_at_400].map(|r| raw(&doc, r)), untouched);
|
||||
let after = render(&doc);
|
||||
assert_eq!(after, before, "conservative retention preserves the rendered page exactly");
|
||||
@@ -1681,7 +1687,7 @@ fn a_fax_image_behind_a_decompression_bomb_is_left_alone() {
|
||||
let r = optimize(&mut doc, &Settings::default()).unwrap();
|
||||
if padding == 0 {
|
||||
assert_eq!(r.images_resampled, 0, "ambiguous local tones are retained: {r:?}");
|
||||
assert_eq!(doc.decoded_image(&stream(&doc, img)).unwrap(), bilevel(w, h, false));
|
||||
assert_eq!(decoded_image(&doc, &stream(&doc, img)).unwrap(), bilevel(w, h, false));
|
||||
} else {
|
||||
assert_eq!((r.images_resampled, r.images_recompressed), (0, 0), "{r:?}");
|
||||
assert_eq!(stream(&doc, img).raw, before);
|
||||
@@ -1776,7 +1782,7 @@ fn monochrome_images_keep_what_they_should() {
|
||||
assert_eq!([alone, deep].map(|r| raw(&doc, r)), before, "a Group 4 halftone alone, and sixteen-bit grey");
|
||||
assert_eq!(filters(&doc, wrapped), 1, "a wrapped Group 4 halftone is stored again alone by default");
|
||||
assert!(matches!(stream(&doc, scan).filters().as_slice(), [(Filter::CcittFax | Filter::Flate, _)]), "the scan: Group 4 or Flate");
|
||||
assert_eq!(doc.decoded_image(&stream(&doc, scan)).unwrap(), ragged, "the scan preserves every sample");
|
||||
assert_eq!(decoded_image(&doc, &stream(&doc, scan)).unwrap(), ragged, "the scan preserves every sample");
|
||||
assert_eq!((stream(&doc, fax).dict.name(b"Filter"), filters(&doc, fax)), (Some(&b"CCITTFaxDecode"[..]), 1), "the busy fax image");
|
||||
|
||||
let (mut doc, [_, wrapped, scan, _, _]) = build();
|
||||
@@ -1785,7 +1791,7 @@ fn monochrome_images_keep_what_they_should() {
|
||||
assert_eq!(raw(&doc, wrapped), before, "Retain: a wrapped Group 4 halftone stays as it is");
|
||||
let s = stream(&doc, scan);
|
||||
assert_eq!((s.dict.int(b"Width"), s.dict.name(b"Filter")), (Some(1200), Some(&b"FlateDecode"[..])), "Retain: {r:?}");
|
||||
assert_eq!(doc.decoded_image(&s).unwrap(), ragged, "Retain preserves every sample");
|
||||
assert_eq!(decoded_image(&doc, &s).unwrap(), ragged, "Retain preserves every sample");
|
||||
}
|
||||
|
||||
/// `rows` coded as CCITT Group 3, one-dimensional (`/K 0`): each row its runs in turn, white first,
|
||||
@@ -1853,7 +1859,12 @@ fn group_3_fax_images_become_group_4() {
|
||||
let g3 = group_3(&runs, k > 0, on_bytes);
|
||||
let (end_of_line, encoded_byte_align) = (k > 0 && on_bytes.is_none(), on_bytes.is_some());
|
||||
let p = pdfcraft_filters::CcittParams { k, columns: w.into(), end_of_line, encoded_byte_align, ..Default::default() };
|
||||
assert_eq!(pdfcraft_filters::decode_ccitt(&g3, &p, h).unwrap(), bits, "/K {k}, on bytes {on_bytes:?}: the Group 3 data is the picture");
|
||||
let mut work = u64::MAX;
|
||||
assert_eq!(
|
||||
pdfcraft_filters::decode_ccitt_within(&g3, &p, h, &mut work).unwrap(),
|
||||
bits,
|
||||
"/K {k}, on bytes {on_bytes:?}: the Group 3 data is the picture"
|
||||
);
|
||||
|
||||
let mut doc = Document::new_empty();
|
||||
let mut d = Dict::new();
|
||||
@@ -1886,7 +1897,7 @@ fn group_3_fax_images_become_group_4() {
|
||||
let s = stream(&doc, fax);
|
||||
assert_eq!(doc.fax_params(&s).map(|p| p.k), Some(-1), "/K {k}, on bytes {on_bytes:?}: Group 4");
|
||||
assert!(s.raw.len() < g3.len(), "{} bytes, from {}", s.raw.len(), g3.len());
|
||||
assert_eq!(doc.decoded_image(&s).unwrap(), bits, "/K {k}, on bytes {on_bytes:?}: the same picture");
|
||||
assert_eq!(decoded_image(&doc, &s).unwrap(), bits, "/K {k}, on bytes {on_bytes:?}: the same picture");
|
||||
assert!(render(&doc) == render(&control), "/K {k}, on bytes {on_bytes:?}: the page looks as the picture does");
|
||||
}
|
||||
}
|
||||
@@ -2102,14 +2113,14 @@ fn jbig2_scans_are_averaged_and_stored_again() {
|
||||
let im = mono_image(&mut doc, w, h, &squares, None, &grey);
|
||||
page(&mut doc, &[("Im", im)], "q 144 0 0 57.6 20 600 cm /Im Do Q");
|
||||
assert_eq!(optimize(&mut doc, &settings).unwrap().images_resampled, 1, "Flate, {compression:?}");
|
||||
let averaged = doc.decoded_image(&stream(&doc, im)).unwrap();
|
||||
let averaged = decoded_image(&doc, &stream(&doc, im)).unwrap();
|
||||
for (filters, globals) in [(&["JBIG2Decode"][..], false), (&["ASCIIHexDecode", "JBIG2Decode"][..], false), (&["JBIG2Decode"][..], true)] {
|
||||
let (mut doc, im) = jbig2_page(&coded, filters, globals, (w, h), at_600);
|
||||
let r = optimize(&mut doc, &settings).unwrap();
|
||||
let s = stream(&doc, im);
|
||||
let what = format!("{filters:?}, globals {globals}, {compression:?}: {r:?}");
|
||||
assert_eq!((r.images_resampled, s.dict.int(b"Width"), s.dict.int(b"Height")), (1, Some(600), Some(240)), "{what}");
|
||||
assert_eq!(doc.decoded_image(&s).unwrap(), averaged, "{what}");
|
||||
assert_eq!(decoded_image(&doc, &s).unwrap(), averaged, "{what}");
|
||||
assert!(!s.dict.contains(b"DecodeParms") || s.dict.name(b"Filter") == Some(&b"CCITTFaxDecode"[..]), "{what}");
|
||||
let filter = s.dict.name(b"Filter").map(<[u8]>::to_vec);
|
||||
// The smallest of what each compression may store; under Retain, JBIG2 again.
|
||||
@@ -2140,13 +2151,13 @@ fn jbig2_scans_are_averaged_and_stored_again() {
|
||||
let s = stream(&doc, im);
|
||||
assert_eq!((r.images_resampled, r.images_recompressed, s.dict.name(b"Filter")), (0, 1, Some(&b"JBIG2Decode"[..])), "{r:?}");
|
||||
assert!(s.raw.len() * 2 < generic.len(), "symbols {} bytes, the generic region {}", s.raw.len(), generic.len());
|
||||
assert_eq!(doc.decoded_image(&s).unwrap(), text);
|
||||
assert_eq!(decoded_image(&doc, &s).unwrap(), text);
|
||||
// Behind ASCIIHex it is stored again alone, being smaller so.
|
||||
let (mut doc, im) = jbig2_page(&generic, &["ASCIIHexDecode", "JBIG2Decode"], false, (tw, th), at_300);
|
||||
optimize(&mut doc, &jbig2_asked).unwrap();
|
||||
let s = stream(&doc, im);
|
||||
assert_eq!((s.filters().len(), s.dict.name(b"Filter")), (1, Some(&b"JBIG2Decode"[..])));
|
||||
assert_eq!(doc.decoded_image(&s).unwrap(), text);
|
||||
assert_eq!(decoded_image(&doc, &s).unwrap(), text);
|
||||
// So it is as Group 4 when that is smaller: here the hex digits are spaced out, as ASCIIHex
|
||||
// allows, so that the stream is many times the code.
|
||||
let (mut doc, im) = jbig2_page(&generic, &["ASCIIHexDecode", "JBIG2Decode"], false, (tw, th), at_300);
|
||||
@@ -2156,7 +2167,7 @@ fn jbig2_scans_are_averaged_and_stored_again() {
|
||||
optimize(&mut doc, &Settings::default()).unwrap();
|
||||
let s = stream(&doc, im);
|
||||
assert_eq!((s.filters().len(), s.dict.name(b"Filter")), (1, Some(&b"CCITTFaxDecode"[..])), "Group 4 alone");
|
||||
assert_eq!(doc.decoded_image(&s).unwrap(), text);
|
||||
assert_eq!(decoded_image(&doc, &s).unwrap(), text);
|
||||
|
||||
// A JBIG2 page taller than the image: the renderer draws the whole page into it, so it isn't
|
||||
// read, and stays as it is.
|
||||
@@ -3399,6 +3410,42 @@ fn lzw_streams_become_flate_and_decode_to_the_same_bytes() {
|
||||
assert!(!stream(&doc, c_late).dict.contains(b"DecodeParms"), "nothing left to say for the content stream");
|
||||
}
|
||||
|
||||
/// A stream can take a second or more to store again, so a cancel lands between any two of them,
|
||||
/// and nothing runs after it.
|
||||
#[test]
|
||||
fn a_cancel_lands_during_the_lzw_pass() {
|
||||
use pdfcraft_optimize::{OptimizeError, Stage, optimize_with_progress};
|
||||
let build = |streams: usize| {
|
||||
let mut doc = Document::new_empty();
|
||||
let mut d = Dict::new();
|
||||
d.set(b"Filter".to_vec(), Object::name("LZWDecode"));
|
||||
for _ in 0..streams {
|
||||
doc.add(Object::Stream(Stream::from_raw(d.clone(), lzw(&lzw_ops(), &Params::default()))));
|
||||
}
|
||||
page(&mut doc, &[], "0 0 1 1 re f");
|
||||
doc
|
||||
};
|
||||
let asked = |streams: usize| {
|
||||
let mut asked = 0;
|
||||
optimize_with_progress(&mut build(streams), &Settings::default(), &mut |s| {
|
||||
asked += usize::from(s == Stage::CleanUp);
|
||||
true
|
||||
})
|
||||
.unwrap();
|
||||
asked
|
||||
};
|
||||
let none = asked(0);
|
||||
assert_eq!(asked(3), none + 3, "once a stream");
|
||||
let mut left = none + 1;
|
||||
let mut doc = build(3);
|
||||
let r = optimize_with_progress(&mut doc, &Settings::default(), &mut |s| {
|
||||
left -= usize::from(s == Stage::CleanUp);
|
||||
left > 0
|
||||
});
|
||||
assert!(matches!(r, Err(OptimizeError::Cancelled)), "{r:?}");
|
||||
assert_eq!(left, 0, "nothing runs after it");
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn a_page_drawn_from_lzw_streams_renders_the_same_after_conversion() {
|
||||
let png = Params { predictor: 12, colors: 3, columns: 64, early_change: 0, ..Params::default() };
|
||||
@@ -3534,7 +3581,7 @@ fn indexed_thin_rules_survive_averaging_for_both_palette_orders_and_decodes() {
|
||||
optimize(&mut gray, &Settings::default()).unwrap();
|
||||
let gray_after = render(&Document::open(Arc::new(write_full(&gray, &SaveOptions::default()).unwrap())).unwrap());
|
||||
let gray_stream = stream(&gray, gray_image);
|
||||
let gray_samples = gray.decoded_image(&gray_stream).unwrap();
|
||||
let gray_samples = decoded_image(&gray, &gray_stream).unwrap();
|
||||
assert_eq!((gray_stream.dict.int(b"Width"), gray_stream.dict.int(b"Height")), (Some(600), Some(240)));
|
||||
assert!(gray_samples.iter().any(|b| *b != 0xFF), "the DeviceGray thin rule survives");
|
||||
for white_first in [false, true] {
|
||||
@@ -3567,7 +3614,7 @@ fn indexed_thin_rules_survive_averaging_for_both_palette_orders_and_decodes() {
|
||||
assert_eq!((s.dict.int(b"Width"), s.dict.int(b"Height")), (Some(600), Some(240)), "white-first={white_first}, inverted={inverted}");
|
||||
// The rows are 600 samples, whole bytes: flipping each byte flips each sample.
|
||||
let expected: Vec<u8> = gray_samples.iter().map(|b| if white_first != inverted { !b } else { *b }).collect();
|
||||
assert_eq!(doc.decoded_image(&s).unwrap(), expected, "white-first={white_first}, inverted={inverted}: the rule is dark");
|
||||
assert_eq!(decoded_image(&doc, &s).unwrap(), expected, "white-first={white_first}, inverted={inverted}: the rule is dark");
|
||||
let saved = Document::open(Arc::new(write_full(&doc, &SaveOptions::default()).unwrap())).unwrap();
|
||||
assert!(render(&saved) == gray_after, "palette white-first={white_first}, inverted={inverted}");
|
||||
}
|
||||
@@ -3628,7 +3675,7 @@ fn an_indexed_palette_is_read_by_the_luma_of_its_colours() {
|
||||
page(&mut doc, &[("Im", image)], "q 144 0 0 57.6 20 600 cm /Im Do Q");
|
||||
optimize(&mut doc, &Settings::default()).unwrap();
|
||||
let s = stream(&doc, image);
|
||||
(s.dict.int(b"Width"), doc.decoded_image(&s).unwrap())
|
||||
(s.dict.int(b"Width"), decoded_image(&doc, &s).unwrap())
|
||||
};
|
||||
let (width, samples) = optimized("Indexed");
|
||||
assert_eq!(width, Some(600));
|
||||
@@ -3736,8 +3783,107 @@ fn mixed_text_and_small_halftone_regions_keep_their_tones_with_wide_white_margin
|
||||
optimize(&mut doc, &Settings::default()).unwrap();
|
||||
let s = stream(&doc, image);
|
||||
assert_eq!((s.dict.int(b"Width"), s.dict.int(b"Height")), (Some(w.into()), Some(h.into())));
|
||||
assert_eq!(doc.decoded_image(&s).unwrap(), data, "screened samples survive, not a solid patch");
|
||||
assert_eq!(decoded_image(&doc, &s).unwrap(), data, "screened samples survive, not a solid patch");
|
||||
let saved = Document::open(Arc::new(write_full(&doc, &SaveOptions::default()).unwrap())).unwrap();
|
||||
assert_eq!(render(&saved), before, "local halftone {side}x{side}");
|
||||
}
|
||||
}
|
||||
|
||||
/// A one-bit stencil of `w` × `h`, solid but for a hole in its middle.
|
||||
fn stencil(doc: &mut Document, w: u32, h: u32) -> ObjRef {
|
||||
let row = (w as usize).div_ceil(8);
|
||||
let mut bits = vec![0u8; row * h as usize];
|
||||
for y in (h as usize / 3)..(2 * h as usize / 3) {
|
||||
for x in (w as usize / 3)..(2 * w as usize / 3) {
|
||||
bits[y * row + x / 8] |= 0x80 >> (x % 8);
|
||||
}
|
||||
}
|
||||
let mut d = Dict::new();
|
||||
d.set(b"Type".to_vec(), Object::name("XObject"));
|
||||
d.set(b"Subtype".to_vec(), Object::name("Image"));
|
||||
d.set(b"ImageMask".to_vec(), Object::Bool(true));
|
||||
d.set(b"Width".to_vec(), Object::Int(i64::from(w)));
|
||||
d.set(b"Height".to_vec(), Object::Int(i64::from(h)));
|
||||
d.set(b"BitsPerComponent".to_vec(), Object::Int(1));
|
||||
doc.add(Object::Stream(Stream::flate(d, &bits)))
|
||||
}
|
||||
|
||||
/// A picture with a stencil mask is made smaller like any other: the mask has a resolution of its
|
||||
/// own, so it stays exactly as it was and the hole it cuts stays where it was.
|
||||
#[test]
|
||||
fn a_picture_with_a_stencil_mask_is_downsampled_under_its_mask() {
|
||||
let mut doc = Document::new_empty();
|
||||
let mask = stencil(&mut doc, 1200, 1200);
|
||||
let img = image(&mut doc, 1200, 1200, 3, true, None);
|
||||
let mut s = stream(&doc, img);
|
||||
s.dict.set(b"Mask".to_vec(), Object::Ref(mask));
|
||||
doc.set(img, Object::Stream(s));
|
||||
let mask_before = stream(&doc, mask);
|
||||
// 1200 pixels over two inches: 600 ppi.
|
||||
page(&mut doc, &[("Im0", img)], "0 0 1 rg 0 0 612 792 re f q 144 0 0 144 100 100 cm /Im0 Do Q");
|
||||
let before = render(&doc);
|
||||
let report = optimize(&mut doc, &Settings::default()).unwrap();
|
||||
assert_eq!(report.images_resampled, 1, "{report:?}");
|
||||
let after = stream(&doc, img);
|
||||
assert_eq!(after.dict.int(b"Width"), Some(300), "150 ppi");
|
||||
assert_eq!(after.dict.reference(b"Mask"), Some(mask), "the mask stays on it");
|
||||
assert_eq!(stream(&doc, mask), mask_before, "and doesn't change");
|
||||
let rendered = render(&doc);
|
||||
assert_eq!(rendered.len(), before.len());
|
||||
let changed = before.iter().zip(&rendered).filter(|(a, b)| a.abs_diff(**b) > 96).count();
|
||||
assert!(changed * 200 < before.len(), "the masked picture looks the same: {changed} of {} samples far off", before.len());
|
||||
// The hole, the middle third of the picture on the 612 by 792 page, still shows what's behind it.
|
||||
// Its first pixel all round is left out: the coarser picture blends into that a little.
|
||||
for y in 597..643 {
|
||||
for x in 149..195 {
|
||||
let i = (y * 612 + x) * 4;
|
||||
assert_eq!(rendered[i..i + 4], before[i..i + 4], "hole pixel ({x}, {y})");
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/// A colour-key mask names sample values: resampling or JPEG would make holes where there were none
|
||||
/// and fill those there were, so the picture stays as it is, however the array is written. A mask
|
||||
/// that can't be read as a stencil is no reason to change the picture either.
|
||||
#[test]
|
||||
fn a_picture_whose_mask_is_not_a_stencil_is_left_alone() {
|
||||
type Mask = fn(&mut Document) -> Object;
|
||||
fn key() -> Object {
|
||||
Object::Array([250, 255, 250, 255, 250, 255].map(Object::Int).to_vec())
|
||||
}
|
||||
fn not_a_stencil(doc: &mut Document, change: fn(&mut Dict)) -> Object {
|
||||
let mask = stencil(doc, 1200, 1200);
|
||||
let mut s = stream(doc, mask);
|
||||
change(&mut s.dict);
|
||||
doc.set(mask, Object::Stream(s));
|
||||
Object::Ref(mask)
|
||||
}
|
||||
let masks: [(&str, Mask); 5] = [
|
||||
("direct array", |_| key()),
|
||||
("array by reference", |doc| Object::Ref(doc.add(key()))),
|
||||
("nothing there", |doc| Object::Ref(doc.add(Object::Null))),
|
||||
("an image that says it isn't a stencil", |doc| {
|
||||
not_a_stencil(doc, |d| {
|
||||
d.set(b"ImageMask".to_vec(), Object::Bool(false));
|
||||
})
|
||||
}),
|
||||
("an image that doesn't say it is one", |doc| {
|
||||
not_a_stencil(doc, |d| {
|
||||
d.remove(b"ImageMask");
|
||||
})
|
||||
}),
|
||||
];
|
||||
for (what, mask) in masks {
|
||||
let mut doc = Document::new_empty();
|
||||
let img = image(&mut doc, 1200, 1200, 3, true, None);
|
||||
let mut s = stream(&doc, img);
|
||||
let mask = mask(&mut doc);
|
||||
s.dict.set(b"Mask".to_vec(), mask);
|
||||
doc.set(img, Object::Stream(s));
|
||||
let before = stream(&doc, img);
|
||||
page(&mut doc, &[("Im0", img)], "q 144 0 0 144 100 100 cm /Im0 Do Q");
|
||||
let report = optimize(&mut doc, &Settings::default()).unwrap();
|
||||
assert_eq!(report.images_resampled + report.images_recompressed, 0, "{what}: {report:?}");
|
||||
assert_eq!(stream(&doc, img), before, "{what}");
|
||||
}
|
||||
}
|
||||
@@ -46,7 +46,9 @@ Headless `doc_print` defaults are unchanged.
|
||||
`spool` delegates discovery, driver options, preferences and submission to
|
||||
[`craft-print`](https://github.com/storytold/craft-libs/tree/main/crates/print).
|
||||
PdfCraft retains page selection, imposition, annotations and print-permission checks.
|
||||
CUPS jobs stream through stdin with `fit-to-page=false`. Windows renders sheets through
|
||||
CUPS jobs stream through stdin with `fit-to-page=false`; on macOS they also carry the job
|
||||
name and owner (`com.apple.print.JobInfo.PMJobName`, `PMJobOwner`) as the system print dialog
|
||||
sends them, which some vendors' filters need (#5743). Windows renders sheets through
|
||||
`Windows.Data.Pdf` and spools them at their physical PDF size with per-page paper and
|
||||
orientation, zero added margins and hardware-edge clipping. Long-edge and short-edge duplex
|
||||
use the corresponding Windows binding edges. Random, exclusively created Windows job files
|
||||
|
||||
@@ -143,14 +143,62 @@ pub(crate) fn printer_options_via_within(
|
||||
options
|
||||
}
|
||||
|
||||
/// The keys the macOS print dialog names a job's title and owner under.
|
||||
#[cfg_attr(not(target_os = "macos"), allow(dead_code))]
|
||||
const JOB_NAME_KEY: &str = "com.apple.print.JobInfo.PMJobName";
|
||||
#[cfg_attr(not(target_os = "macos"), allow(dead_code))]
|
||||
const JOB_OWNER_KEY: &str = "com.apple.print.JobInfo.PMJobOwner";
|
||||
|
||||
/// `text` as a job option's value: `lp_args` passes on only printable ASCII, up to 64 bytes,
|
||||
/// without `/ : = "`, and CUPS would take `'` and `\` as quoting and `{` as the start of a
|
||||
/// collection, so all of these become `_`. Text with nothing left of it, such as a title in
|
||||
/// another script, takes `fallback`: the job must still name something. So does a bare `true` or
|
||||
/// `false`, which CUPS would send as a boolean, not the name a filter reads.
|
||||
#[cfg_attr(not(target_os = "macos"), allow(dead_code))]
|
||||
fn job_option_value(text: &str, fallback: &str) -> String {
|
||||
let kept = |c: char| c.is_ascii_graphic() && !matches!(c, '/' | ':' | '=' | '"' | '\'' | '\\' | '{');
|
||||
let value: String = text.chars().take(64).map(|c| if kept(c) { c } else { '_' }).collect();
|
||||
if !text.chars().any(kept) || value.eq_ignore_ascii_case("true") || value.eq_ignore_ascii_case("false") {
|
||||
return fallback.to_string();
|
||||
}
|
||||
value
|
||||
}
|
||||
|
||||
/// `job` naming its title and `owner` as a job from the macOS print dialog does. `lp` sends
|
||||
/// neither, and a driver's filter can depend on them: Kyocera's crashes without them, so nothing
|
||||
/// prints, while the same file sent with both does (#5743). A value the caller set stands: the
|
||||
/// last of a repeated option wins in CUPS, which compares their names without case.
|
||||
#[cfg_attr(not(target_os = "macos"), allow(dead_code))]
|
||||
pub(crate) fn with_job_info(job: &Job, owner: Option<&str>) -> Job {
|
||||
let mut named = job.clone();
|
||||
for (key, value) in [(JOB_NAME_KEY, job.title.as_str()), (JOB_OWNER_KEY, owner.unwrap_or_default())] {
|
||||
if !job.options.iter().any(|(k, _)| k.eq_ignore_ascii_case(key)) {
|
||||
named.options.push((key.to_string(), job_option_value(value, "PdfCraft")));
|
||||
}
|
||||
}
|
||||
named
|
||||
}
|
||||
|
||||
/// The job as the system spooler takes it.
|
||||
fn spooled(job: &Job) -> Job {
|
||||
#[cfg(target_os = "macos")]
|
||||
{
|
||||
with_job_info(job, std::env::var("USER").ok().as_deref())
|
||||
}
|
||||
#[cfg(not(target_os = "macos"))]
|
||||
{
|
||||
job.clone()
|
||||
}
|
||||
}
|
||||
|
||||
pub fn submit(pdf: &[u8], job: &Job) -> Result<String, crate::PrintError> {
|
||||
craft_print::submit(pdf, job).map_err(|e| crate::PrintError::Spool(e.to_string()))
|
||||
craft_print::submit(pdf, &spooled(job)).map_err(|e| crate::PrintError::Spool(e.to_string()))
|
||||
}
|
||||
|
||||
/// [`submit`], told `(sent, sheets)` as each sheet reaches the spooler (Windows; CUPS takes the
|
||||
/// whole PDF at once and reports nothing).
|
||||
pub fn submit_with_progress(pdf: &[u8], job: &Job, progress: &mut dyn FnMut(usize, usize)) -> Result<String, crate::PrintError> {
|
||||
craft_print::submit_with_progress(pdf, job, progress).map_err(|e| crate::PrintError::Spool(e.to_string()))
|
||||
craft_print::submit_with_progress(pdf, &spooled(job), progress).map_err(|e| crate::PrintError::Spool(e.to_string()))
|
||||
}
|
||||
|
||||
pub fn open_printer_preferences(printer: &str) -> Result<(), crate::PrintError> {
|
||||
|
||||
@@ -305,6 +305,107 @@ fn spooler_arguments_and_printer_list() {
|
||||
assert_eq!(lp_args(&Job::default())[0], "-n", "no -d: the default printer");
|
||||
}
|
||||
|
||||
/// The job name and owner, read from the `lp` arguments, since `lp_args` drops a value it can't
|
||||
/// pass on: the job must reach the spooler named, whatever its title holds (#5743).
|
||||
#[test]
|
||||
fn a_job_names_its_title_and_owner_to_the_spooler() {
|
||||
let args_for = |title: &str, owner: Option<&str>| {
|
||||
let job = Job { title: title.into(), ..Job::default() };
|
||||
lp_args(&spool::with_job_info(&job, owner))
|
||||
};
|
||||
let option = |args: &[String], key: &str| {
|
||||
let prefix = format!("com.apple.print.JobInfo.{key}=");
|
||||
args.iter().find_map(|a| a.strip_prefix(prefix.as_str()).map(str::to_string))
|
||||
};
|
||||
let args = args_for("memo.pdf", Some("sam"));
|
||||
assert_eq!(option(&args, "PMJobName").as_deref(), Some("memo.pdf"), "{args:?}");
|
||||
assert_eq!(option(&args, "PMJobOwner").as_deref(), Some("sam"), "{args:?}");
|
||||
// The title keeps its place as `-t`, in full.
|
||||
assert!(args_for("Q3 report: a/b=\"c\".pdf", None).windows(2).any(|w| w[0] == "-t" && w[1] == "Q3 report: a/b=\"c\".pdf"));
|
||||
|
||||
let named = args_for("Q3 report: a/b=\"c\".pdf", None);
|
||||
assert_eq!(option(&named, "PMJobName").as_deref(), Some("Q3_report__a_b__c_.pdf"), "what lp can't be given becomes _");
|
||||
assert_eq!(option(&named, "PMJobOwner").as_deref(), Some("PdfCraft"), "no owner known: the filter still gets one");
|
||||
|
||||
for nothing_left in ["", " ", "見積書", "/:=\""] {
|
||||
assert_eq!(option(&args_for(nothing_left, Some("")), "PMJobName").as_deref(), Some("PdfCraft"), "{nothing_left:?}");
|
||||
}
|
||||
assert_eq!(option(&args_for("見積書2.pdf", None), "PMJobName").as_deref(), Some("___2.pdf"), "a part of it is kept");
|
||||
let long = option(&args_for(&format!("a{}", "é".repeat(200)), None), "PMJobName").unwrap_or_default();
|
||||
assert_eq!(long.len(), 64, "cut to what lp_args takes, on a multi-byte title too: {long}");
|
||||
|
||||
// What CUPS would quote away or send as another type, as this Mac's libcups does.
|
||||
for (title, name) in [("it's.pdf", "it_s.pdf"), (r"a\b.pdf", "a_b.pdf"), ("{draft}.pdf", "_draft}.pdf"), ("a{b", "a_b")] {
|
||||
assert_eq!(option(&args_for(title, None), "PMJobName").as_deref(), Some(name), "{title:?}");
|
||||
}
|
||||
for boolean in ["true", "TRUE", "false", "False"] {
|
||||
assert_eq!(option(&args_for(boolean, Some(boolean)), "PMJobName").as_deref(), Some("PdfCraft"), "{boolean:?}");
|
||||
assert_eq!(option(&args_for(boolean, Some(boolean)), "PMJobOwner").as_deref(), Some("PdfCraft"), "{boolean:?}");
|
||||
}
|
||||
assert_eq!(option(&args_for("true.pdf", None), "PMJobName").as_deref(), Some("true.pdf"), "only the bare word is a boolean");
|
||||
}
|
||||
|
||||
/// A job's own values stand: CUPS keeps the last of a repeated option, ignoring the case of its
|
||||
/// name, so a default after them would replace what a `doc_print` caller set (#5743).
|
||||
#[test]
|
||||
fn a_job_keeps_the_title_and_owner_it_already_sets() {
|
||||
let values = |job: &Job, key: &str| -> Vec<String> {
|
||||
let found = spool::with_job_info(job, Some("sam")).options;
|
||||
found.into_iter().filter(|(k, _)| k.eq_ignore_ascii_case(key)).map(|(_, v)| v).collect()
|
||||
};
|
||||
let (name, owner) = ("com.apple.print.JobInfo.PMJobName", "com.apple.print.JobInfo.PMJobOwner");
|
||||
let job = Job { title: "memo.pdf".into(), options: vec![(name.to_string(), "Mine".to_string())], ..Job::default() };
|
||||
assert_eq!(values(&job, name), ["Mine"]);
|
||||
assert_eq!(values(&job, owner), ["sam"], "the one it left out still gets its default");
|
||||
|
||||
let job = Job { title: "memo.pdf".into(), options: vec![(owner.to_ascii_uppercase(), "Theirs".to_string())], ..Job::default() };
|
||||
assert_eq!(values(&job, owner), ["Theirs"]);
|
||||
assert_eq!(values(&job, name), ["memo.pdf"]);
|
||||
}
|
||||
|
||||
/// Both ways to submit reach `lp` with the job named. `lp` comes from `PATH`, which only a child
|
||||
/// process can change here, so the test runs itself again with a stand-in that records its
|
||||
/// arguments; no job reaches a real spooler (#5743).
|
||||
#[cfg(target_os = "macos")]
|
||||
#[test]
|
||||
fn a_submitted_job_reaches_lp_named() {
|
||||
const TEST: &str = "tests::a_submitted_job_reaches_lp_named";
|
||||
if let Ok(way) = std::env::var("PDFCRAFT_SUBMIT_TO_STAND_IN") {
|
||||
let job = Job { title: "memo.pdf".into(), ..Job::default() };
|
||||
let sent = match way.as_str() {
|
||||
"submit" => spool::submit(b"%PDF-1.7", &job),
|
||||
_ => spool::submit_with_progress(b"%PDF-1.7", &job, &mut |_, _| {}),
|
||||
};
|
||||
assert!(sent.is_ok(), "{sent:?}");
|
||||
return;
|
||||
}
|
||||
use std::os::unix::fs::PermissionsExt as _;
|
||||
let dir = std::env::temp_dir().join(format!("pdfcraft-lp-stand-in-{}", std::process::id()));
|
||||
std::fs::create_dir_all(&dir).expect("temp dir");
|
||||
let lp = dir.join("lp");
|
||||
let recorded = dir.join("args");
|
||||
let script =
|
||||
format!("#!/bin/sh\nprintf '%s\\n' \"$@\" > '{}'\n/bin/cat > /dev/null\necho 'request id is stand-in-1 (1 file(s))'\n", recorded.display());
|
||||
std::fs::write(&lp, script).expect("stand-in");
|
||||
std::fs::set_permissions(&lp, std::fs::Permissions::from_mode(0o700)).expect("executable");
|
||||
for way in ["submit", "submit_with_progress"] {
|
||||
let _ = std::fs::remove_file(&recorded);
|
||||
let this = std::env::current_exe().expect("this test binary");
|
||||
let child = std::process::Command::new(this)
|
||||
.args(["--exact", TEST, "--nocapture"])
|
||||
.env("PDFCRAFT_SUBMIT_TO_STAND_IN", way)
|
||||
.env("PATH", &dir)
|
||||
.env("USER", "sam")
|
||||
.output()
|
||||
.expect("run the test again");
|
||||
assert!(child.status.success(), "{way}: {}", String::from_utf8_lossy(&child.stdout));
|
||||
let args = std::fs::read_to_string(&recorded).expect("lp was run");
|
||||
assert!(args.lines().any(|a| a == "com.apple.print.JobInfo.PMJobName=memo.pdf"), "{way}: {args}");
|
||||
assert!(args.lines().any(|a| a == "com.apple.print.JobInfo.PMJobOwner=sam"), "{way}: {args}");
|
||||
}
|
||||
let _ = std::fs::remove_dir_all(&dir);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn lpstat_output_is_untranslated() {
|
||||
// A localized lpstat (here Polish) is unreadable to parse_lpstat...
|
||||
|
||||
@@ -37,6 +37,10 @@ clear_marks(&mut doc, None)?; // remove marks without app
|
||||
and a byte per row, plus 4 KiB (ASCIIHex text broken into lines under Flate is a little over
|
||||
twice; for a fax image's code, about a byte per pixel), are removed whole;
|
||||
cleared copies drop `/Alternates` so alternate pixels cannot survive;
|
||||
A run that would decode more of its images than one redaction may (`pdfcraft_cos::ImageBudget`,
|
||||
filters, decoders and pixels alike) is refused
|
||||
and changes nothing: such an image can't be cleared, and removing it whole would take what no mark
|
||||
covers with it.
|
||||
- **vectors**: covered paths are removed; partly covered paths and shadings are clipped so
|
||||
nothing paints inside the areas;
|
||||
- **form XObjects**: rewritten recursively into new objects (pages sharing the original keep it);
|
||||
|
||||
+23
-17
@@ -2,13 +2,13 @@
|
||||
//! whose footprint intersects a region is set to zero (no ink for image masks), and the result is
|
||||
//! written as a new image, Flate, or for a one-bit image of one component Group 4, or JBIG2 when it
|
||||
//! was JBIG2, whichever is smallest; the original object is untouched (other pages may use it).
|
||||
//! CCITT fax and JBIG2 images decode through `Document::decoded_image_within`, but for Group 3 on
|
||||
//! CCITT fax and JBIG2 images decode through `ImageBudget::decode`, but for Group 3 on
|
||||
//! bytes, which PdfCraft's renderer may draw as other rows, and a JBIG2 page of other rows than the
|
||||
//! image's. Images whose codec PdfCraft can't decode (DCT, JPX), and those, return `None`, and the
|
||||
//! caller removes the whole image instead; that is fail-closed.
|
||||
|
||||
use pdfcraft_content::{Matrix, overlaps};
|
||||
use pdfcraft_cos::{Dict, Document, Object, Stream};
|
||||
use pdfcraft_cos::{Dict, Document, ImageBudget, Object, Stream};
|
||||
|
||||
/// Most pixels an image may have to be cleared in place (larger ones are removed).
|
||||
const MAX_PIXELS: u64 = 64 << 20;
|
||||
@@ -39,11 +39,11 @@ fn components(doc: &Document, s: &Stream) -> Option<usize> {
|
||||
/// `Ok(Some(copy))` with the covered pixels cleared, `Ok(None)` when no pixel intersects,
|
||||
/// `Err(())` when the image can't be cleared (the caller removes it).
|
||||
#[allow(clippy::result_unit_err)]
|
||||
pub(crate) fn clear(doc: &Document, s: &Stream, ctm: &Matrix, rects: &[[f64; 4]]) -> Result<Option<Stream>, ()> {
|
||||
decode_and_clear(doc, s, ctm, rects).ok_or(())
|
||||
pub(crate) fn clear(doc: &Document, s: &Stream, ctm: &Matrix, rects: &[[f64; 4]], budget: &mut ImageBudget) -> Result<Option<Stream>, ()> {
|
||||
decode_and_clear(doc, s, ctm, rects, budget).ok_or(())
|
||||
}
|
||||
|
||||
fn decode_and_clear(doc: &Document, s: &Stream, ctm: &Matrix, rects: &[[f64; 4]]) -> Option<Option<Stream>> {
|
||||
fn decode_and_clear(doc: &Document, s: &Stream, ctm: &Matrix, rects: &[[f64; 4]], budget: &mut ImageBudget) -> Option<Option<Stream>> {
|
||||
// Separate masks can retain the original image data.
|
||||
if s.dict.contains(b"SMask") || s.dict.contains(b"Mask") {
|
||||
return None;
|
||||
@@ -54,19 +54,25 @@ fn decode_and_clear(doc: &Document, s: &Stream, ctm: &Matrix, rects: &[[f64; 4]]
|
||||
b"FlateDecode" | b"Fl" | b"LZWDecode" | b"LZW" | b"ASCII85Decode" | b"A85" | b"ASCIIHexDecode" | b"AHx" | b"RunLengthDecode" | b"RL"
|
||||
)
|
||||
};
|
||||
// A CCITT fax or JBIG2 image (its last filter) decodes through `Document::decoded_image_within`,
|
||||
// A CCITT fax or JBIG2 image (its last filter) decodes through `ImageBudget::decode`,
|
||||
// after the filters before it, so a scan stored as Group 4 or JBIG2 is cleared like any other
|
||||
// image.
|
||||
let fax = |f: &Object| f.as_name().is_some_and(|n| matches!(n, b"CCITTFaxDecode" | b"CCF"));
|
||||
let jbig2 = |f: &Object| f.as_name() == Some(b"JBIG2Decode".as_slice());
|
||||
let readable = |f: &Object| f.as_name().is_some_and(supported);
|
||||
// `/Crypt` was undone when the object was loaded (ISO 32000-2 §7.4.10), and decoding leaves it
|
||||
// out wherever it stands.
|
||||
let crypt = |f: &Object| f.as_name() == Some(b"Crypt".as_slice());
|
||||
let (ok, is_fax, is_jbig2) = match s.dict.get(b"Filter") {
|
||||
None => (true, false, false),
|
||||
Some(f @ Object::Name(_)) => (readable(f) || fax(f) || jbig2(f), fax(f), jbig2(f)),
|
||||
Some(Object::Array(a)) => match a.split_last() {
|
||||
Some((last, before)) if fax(last) || jbig2(last) => (before.iter().all(readable), fax(last), jbig2(last)),
|
||||
_ => (a.iter().all(readable), false, false),
|
||||
},
|
||||
Some(f @ Object::Name(_)) => (readable(f) || crypt(f) || fax(f) || jbig2(f), fax(f), jbig2(f)),
|
||||
Some(Object::Array(a)) => {
|
||||
let chain: Vec<&Object> = a.iter().filter(|f| !crypt(f)).collect();
|
||||
match chain.split_last() {
|
||||
Some((last, before)) if fax(last) || jbig2(last) => (before.iter().all(|f| readable(f)), fax(last), jbig2(last)),
|
||||
_ => (chain.iter().all(|f| readable(f)), false, false),
|
||||
}
|
||||
}
|
||||
_ => (false, false, false),
|
||||
};
|
||||
if !ok {
|
||||
@@ -112,7 +118,7 @@ fn decode_and_clear(doc: &Document, s: &Stream, ctm: &Matrix, rects: &[[f64; 4]]
|
||||
// alone would skip such a predictor, and the cleared bytes would then miss the covered pixels),
|
||||
// and refuses a JBIG2 page of another size than the image: the renderer draws the whole page
|
||||
// into the image, so the rows cleared wouldn't be the ones a mark covers on screen.
|
||||
let mut data = doc.decoded_image_within(s, allowance).ok()?;
|
||||
let mut data = budget.decode(doc, s, allowance).ok()?;
|
||||
if data.len() < bytes {
|
||||
return None;
|
||||
}
|
||||
@@ -205,12 +211,12 @@ fn stored_len(s: &Stream) -> usize {
|
||||
|
||||
/// JBIG2 image `s` stored again without its `/JBIG2Globals`: decoded through them, as it is drawn,
|
||||
/// and written as the same samples, Flate, Group 4 or JBIG2 coded alone, whichever is smallest
|
||||
/// (`smallest`), its other entries kept. `None` when it can't
|
||||
/// be decoded for certain (too large, data that doesn't decode, a JBIG2 page of another size than
|
||||
/// the image, or not a one-bit image of one component). Redaction does this to every image that
|
||||
/// (`smallest`), its other entries kept. `None` when it can't be decoded for certain (too large,
|
||||
/// past what is left of `budget`, data that doesn't decode, a JBIG2 page of another size than the
|
||||
/// image, or not a one-bit image of one component). Redaction does this to every image that
|
||||
/// shares a redacted image's globals, since their symbol dictionary holds the shapes of marks drawn
|
||||
/// under the area too.
|
||||
pub(crate) fn without_globals(doc: &Document, s: &Stream) -> Option<Stream> {
|
||||
pub(crate) fn without_globals(doc: &Document, s: &Stream, budget: &mut ImageBudget) -> Option<Stream> {
|
||||
let (w, h) = (s.dict.int(b"Width")?, s.dict.int(b"Height")?);
|
||||
if w <= 0 || h <= 0 || (w as u64) * (h as u64) > MAX_PIXELS {
|
||||
return None;
|
||||
@@ -225,7 +231,7 @@ pub(crate) fn without_globals(doc: &Document, s: &Stream) -> Option<Stream> {
|
||||
// As for `clear`: the filters before the JBIG2 decoder may give up to three bytes for each one
|
||||
// of the raster and a byte a row.
|
||||
let allowance = bytes.checked_add(h)?.checked_mul(3)?.checked_add(4096)?;
|
||||
let mut data = doc.decoded_image_within(s, allowance).ok()?;
|
||||
let mut data = budget.decode(doc, s, allowance).ok()?;
|
||||
if data.len() < bytes {
|
||||
return None;
|
||||
}
|
||||
|
||||
@@ -21,7 +21,7 @@ use std::collections::{HashMap, HashSet};
|
||||
use std::rc::Rc;
|
||||
|
||||
use pdfcraft_content::{Matrix, Op, Pieces, contains, num, overlaps, serialize_ops, string};
|
||||
use pdfcraft_cos::{CosError, DecodeBudget, Dict, Document, MAX_PAGE_FORMS, ObjRef, Object, Stream};
|
||||
use pdfcraft_cos::{CosError, DecodeBudget, Dict, Document, ImageBudget, MAX_PAGE_FORMS, ObjRef, Object, Stream};
|
||||
|
||||
use crate::{RedactError, Report, image, page_streams, tags};
|
||||
use pdfcraft_fonts::pdf::Metrics;
|
||||
@@ -105,6 +105,8 @@ pub(crate) struct Scope<'a> {
|
||||
pub rects: &'a [[f64; 4]],
|
||||
pub mode: Mode,
|
||||
pub report: &'a mut Report,
|
||||
/// What the images it clears may spend, shared by all the pages of a run.
|
||||
pub images: &'a mut ImageBudget,
|
||||
/// Sanitize: remove hidden text (invisible render modes, or wholly outside this page box).
|
||||
pub hidden_text: Option<[f64; 4]>,
|
||||
/// Sanitize: optional content groups that are off; content marked with them is removed.
|
||||
@@ -134,11 +136,12 @@ pub(crate) struct Scope<'a> {
|
||||
impl<'a> Scope<'a> {
|
||||
/// A scope whose form walk spends `budget`, what is left of the page's allowance after its
|
||||
/// content streams were decoded.
|
||||
pub fn new(rects: &'a [[f64; 4]], mode: Mode, report: &'a mut Report, budget: DecodeBudget) -> Self {
|
||||
pub fn new(rects: &'a [[f64; 4]], mode: Mode, report: &'a mut Report, budget: DecodeBudget, images: &'a mut ImageBudget) -> Self {
|
||||
Scope {
|
||||
rects,
|
||||
mode,
|
||||
report,
|
||||
images,
|
||||
hidden_text: None,
|
||||
hidden_layers: HashSet::new(),
|
||||
layers_enabled: false,
|
||||
@@ -750,7 +753,7 @@ fn xobject(
|
||||
out.doomed.push(r);
|
||||
return Some(None);
|
||||
}
|
||||
match image::clear(doc, s, &gs.ctm, scope.rects) {
|
||||
match image::clear(doc, s, &gs.ctm, scope.rects, &mut *scope.images) {
|
||||
Ok(None) => None,
|
||||
Ok(Some(new)) => {
|
||||
let nr = doc.add(Object::Stream(new));
|
||||
@@ -858,6 +861,11 @@ fn xobject(
|
||||
}
|
||||
let mut dict = s.dict.clone();
|
||||
dict.remove(b"Length");
|
||||
if new_data.is_some() {
|
||||
// As for page content streams: the source text of an added item (Edit ▸ Add
|
||||
// content) would keep what the rewrite removed.
|
||||
dict.remove(b"PCAdded");
|
||||
}
|
||||
let mut cleaned_res = res.clone();
|
||||
// Install rewritten nested forms before finding live property names: a new form may
|
||||
// still inherit its caller's resources, and its new Do name must resolve here.
|
||||
|
||||
@@ -70,6 +70,10 @@ pub enum RedactError {
|
||||
/// could not be shown complete.
|
||||
#[error("the document's objects nest too deeply to remove hidden information completely; the operation was refused")]
|
||||
TooDeep,
|
||||
/// Past what one redaction may decode an image can't be cleared, and removing it whole would
|
||||
/// take what no mark covers with it, unreported.
|
||||
#[error("the images under these marks are more than one redaction can decode, so nothing was changed; redact fewer pages at a time")]
|
||||
ImagesPastAllowance,
|
||||
/// A JBIG2 image shares its `/JBIG2Globals` with a redacted one and can't be stored again
|
||||
/// without them, so the shapes they hold, those of marks under the area included, would stay.
|
||||
#[error(
|
||||
@@ -386,6 +390,12 @@ pub fn apply(doc: &mut Document, pages: Option<&[usize]>) -> Result<Report, Reda
|
||||
|
||||
/// [`apply`] without the copy: an error can leave `doc` part redacted.
|
||||
fn apply_to(doc: &mut Document, pages: Option<&[usize]>) -> Result<Report, RedactError> {
|
||||
let images = pdfcraft_cos::ImageBudget::new(doc);
|
||||
apply_within(doc, pages, images)
|
||||
}
|
||||
|
||||
/// [`apply_to`], its images decoded within `images`.
|
||||
fn apply_within(doc: &mut Document, pages: Option<&[usize]>, images: pdfcraft_cos::ImageBudget) -> Result<Report, RedactError> {
|
||||
let (all_marks, unreadable) = marks_checked(doc);
|
||||
// A mark with no readable area is not applied, and applying the others would look complete:
|
||||
// refuse before anything changes. Only the pages being applied count.
|
||||
@@ -428,6 +438,7 @@ fn apply_to(doc: &mut Document, pages: Option<&[usize]>) -> Result<Report, Redac
|
||||
retired_properties: Vec::new(),
|
||||
widget_owner,
|
||||
removed_everywhere: HashSet::new(),
|
||||
images,
|
||||
};
|
||||
for &(pi, page_marks) in &groups {
|
||||
let page = pdfcraft_model::pages(doc).swap_remove(pi);
|
||||
@@ -435,7 +446,10 @@ fn apply_to(doc: &mut Document, pages: Option<&[usize]>) -> Result<Report, Redac
|
||||
redact_page_content(doc, &mut applying, pi, &page, &rects)?;
|
||||
remove_page_annotations(doc, &mut applying, &page, &rects, page_marks)?;
|
||||
}
|
||||
let Applying { mut report, doomed_fields, doomed_xobjects, retired_properties, mut removed_everywhere, .. } = applying;
|
||||
if applying.images.refused() > 0 {
|
||||
return Err(RedactError::ImagesPastAllowance);
|
||||
}
|
||||
let Applying { mut report, doomed_fields, doomed_xobjects, retired_properties, mut removed_everywhere, mut images, .. } = applying;
|
||||
|
||||
// 2b. Replies and pop-ups of a removed annotation can be listed on another page than their
|
||||
// parent: their `/IRT` or `/Parent` would keep the removed comment reachable.
|
||||
@@ -518,7 +532,7 @@ fn apply_to(doc: &mut Document, pages: Option<&[usize]>) -> Result<Report, Redac
|
||||
// A removed image or form must not stay reachable through another resource dictionary (an
|
||||
// inherited or shared /Resources): a full save keeps whatever is still referenced.
|
||||
interp::unlink_doomed(doc, &doomed_xobjects, &retired_properties)?;
|
||||
report.images_restored = restore_shared_jbig2(doc, &doomed_xobjects)?;
|
||||
report.images_restored = restore_shared_jbig2(doc, &doomed_xobjects, &mut images)?;
|
||||
|
||||
// 5. Verify: nothing readable may remain under a region.
|
||||
let mut residue = 0;
|
||||
@@ -532,7 +546,9 @@ fn apply_to(doc: &mut Document, pages: Option<&[usize]>) -> Result<Report, Redac
|
||||
list.iter().zip(data).filter(|(o, _)| !o.as_ref().is_some_and(|r| report.overlays.contains(&r))).map(|(_, d)| d).collect();
|
||||
let resources = page.dict.get(b"Resources").and_then(|r| doc.resolve(r).as_dict().cloned()).unwrap_or_default();
|
||||
let mut scratch = Report::default();
|
||||
let mut scope = Scope::new(&rects, Mode::Verify, &mut scratch, budget);
|
||||
// Verifying doesn't decode images: what clearing left is read as the page draws it.
|
||||
let mut images = pdfcraft_cos::ImageBudget::with_work(0);
|
||||
let mut scope = Scope::new(&rects, Mode::Verify, &mut scratch, budget, &mut images);
|
||||
residue += process(doc, &mut scope, &original, &resources, pdfcraft_content::Matrix::IDENTITY).residue;
|
||||
}
|
||||
if residue > 0 {
|
||||
@@ -554,8 +570,10 @@ const MAX_JBIG2_WALK: usize = 100_000;
|
||||
/// and stored again in place without them, as a cleared copy is, and a full save then leaves them
|
||||
/// out. An image that can't be stored again refuses the redaction (nothing changes, as `apply`
|
||||
/// works on a copy), but for a removed or replaced one, which is either unlinked or still drawn
|
||||
/// whole on another page. Returns how many images that weren't removed or replaced were stored again.
|
||||
fn restore_shared_jbig2(doc: &mut Document, doomed: &[ObjRef]) -> Result<usize, RedactError> {
|
||||
/// whole on another page. They are decoded within what is left of the run's allowance (`images`);
|
||||
/// past it the redaction is refused as one clearing too many images is. Returns how many images
|
||||
/// that weren't removed or replaced were stored again.
|
||||
fn restore_shared_jbig2(doc: &mut Document, doomed: &[ObjRef], images: &mut pdfcraft_cos::ImageBudget) -> Result<usize, RedactError> {
|
||||
let mut globals = HashSet::new();
|
||||
let mut seen = HashSet::new();
|
||||
let mut stack: Vec<ObjRef> = doomed.to_vec();
|
||||
@@ -587,19 +605,24 @@ fn restore_shared_jbig2(doc: &mut Document, doomed: &[ObjRef]) -> Result<usize,
|
||||
.map(|(r, _)| r)
|
||||
.collect();
|
||||
let doomed: HashSet<ObjRef> = doomed.iter().copied().collect();
|
||||
let (mut restored, mut stuck) = (0, 0);
|
||||
let (mut restored, mut stuck, mut past_allowance) = (0, 0, false);
|
||||
for r in sharing {
|
||||
let object = doc.get(r);
|
||||
let Object::Stream(s) = &*object else { continue };
|
||||
match image::without_globals(doc, s) {
|
||||
let refused = images.refused();
|
||||
match image::without_globals(doc, s, images) {
|
||||
Some(new) => {
|
||||
doc.set(r, Object::Stream(new));
|
||||
restored += usize::from(!doomed.contains(&r));
|
||||
}
|
||||
None if doomed.contains(&r) => {}
|
||||
None if images.refused() > refused => past_allowance = true,
|
||||
None => stuck += 1,
|
||||
}
|
||||
}
|
||||
if past_allowance {
|
||||
return Err(RedactError::ImagesPastAllowance);
|
||||
}
|
||||
if stuck > 0 {
|
||||
return Err(RedactError::SharedJbig2Globals(stuck));
|
||||
}
|
||||
@@ -615,6 +638,8 @@ struct Applying {
|
||||
retired_properties: Vec<Object>,
|
||||
widget_owner: Vec<(ObjRef, ObjRef)>,
|
||||
removed_everywhere: HashSet<ObjRef>,
|
||||
/// What clearing images may spend, across the run's pages.
|
||||
images: pdfcraft_cos::ImageBudget,
|
||||
}
|
||||
|
||||
/// Step 1 for one page: rewrites its content so nothing readable stays under a mark, and cleans the tags it no longer shows.
|
||||
@@ -625,13 +650,13 @@ fn redact_page_content(
|
||||
page: &pdfcraft_model::Page,
|
||||
rects: &[[f64; 4]],
|
||||
) -> Result<(), RedactError> {
|
||||
let Applying { report, doomed_xobjects, retired_properties, .. } = applying;
|
||||
let Applying { report, doomed_xobjects, retired_properties, images, .. } = applying;
|
||||
// 1. Content.
|
||||
let mut budget = pdfcraft_cos::DecodeBudget::page();
|
||||
let (list, data) = page_streams_within(doc, &page.dict, pi, &mut budget)?;
|
||||
let resources = page.dict.get(b"Resources").and_then(|r| doc.resolve(r).as_dict().cloned()).unwrap_or_default();
|
||||
let out = {
|
||||
let mut scope = Scope::new(rects, Mode::Apply, report, budget);
|
||||
let mut scope = Scope::new(rects, Mode::Apply, report, budget, images);
|
||||
process(doc, &mut scope, &data, &resources, pdfcraft_content::Matrix::IDENTITY)
|
||||
};
|
||||
// Fail closed: the interpreter lays vertical-writing text out horizontally, so it cannot
|
||||
|
||||
@@ -369,7 +369,8 @@ fn content_pass(doc: &mut Document, text: bool, layers: bool, write: bool) -> Re
|
||||
let resources = page.dict.get(b"Resources").and_then(|r| doc.resolve(r).as_dict().cloned()).unwrap_or_default();
|
||||
let mut report = Report::default();
|
||||
let mode = if write { Mode::Apply } else { Mode::Verify };
|
||||
let mut scope = Scope::new(&[], mode, &mut report, budget);
|
||||
let mut images = pdfcraft_cos::ImageBudget::new(doc);
|
||||
let mut scope = Scope::new(&[], mode, &mut report, budget, &mut images);
|
||||
if text {
|
||||
let c = page.crop(doc);
|
||||
scope.hidden_text = Some([c[0].min(c[2]), c[1].min(c[3]), c[0].max(c[2]), c[1].max(c[3])]);
|
||||
|
||||
@@ -2,7 +2,7 @@
|
||||
//!
|
||||
//! Marked content (MCIDs) that applying redactions changed is found by comparing each MCID's
|
||||
//! operators before and after. Elements owning such content lose their alternate text, actual
|
||||
//! text and expansion (which may spell out the removed words);
|
||||
//! text, title and expansion (which may spell out the removed words), as do their ancestors;
|
||||
//! references to marked content that is now empty are dropped from the element.
|
||||
|
||||
use std::collections::{HashMap, HashSet};
|
||||
@@ -281,7 +281,7 @@ pub(crate) fn clean_within(
|
||||
}
|
||||
doc.update_dict(r, |e| {
|
||||
if sensitive {
|
||||
for key in [&b"Alt"[..], b"ActualText", b"E"] {
|
||||
for key in DESCRIPTIONS {
|
||||
e.remove(key);
|
||||
}
|
||||
}
|
||||
@@ -321,8 +321,10 @@ impl Above {
|
||||
}
|
||||
}
|
||||
|
||||
/// The keys of an element that describe its content.
|
||||
const DESCRIPTIONS: [&[u8]; 3] = [b"Alt", b"ActualText", b"E"];
|
||||
/// The keys of an element that describe its content, and so may repeat what was removed: one
|
||||
/// policy for the element that owned it, the elements above it and elements written in place.
|
||||
/// The title (`/T`) is included, as producers often fill it with the element's text.
|
||||
const DESCRIPTIONS: [&[u8]; 4] = [b"Alt", b"ActualText", b"T", b"E"];
|
||||
|
||||
/// Each element's parents as the walk found them: through `/K`, which `/P` may not agree with.
|
||||
struct Parents(HashMap<ObjRef, Vec<Above>>);
|
||||
@@ -539,7 +541,7 @@ pub(crate) fn drop_object_refs_within(doc: &mut Document, gone: &HashSet<ObjRef>
|
||||
// An element that lost an annotation keeps no text describing it, even with other
|
||||
// kids left: a link's alternate text often repeats the URL, an annotation's its
|
||||
// comment. Elements above it may describe it too.
|
||||
for key in [&b"Alt"[..], b"ActualText", b"T", b"E"] {
|
||||
for key in DESCRIPTIONS {
|
||||
e.remove(key);
|
||||
}
|
||||
})?;
|
||||
|
||||
+112
-7
@@ -52,7 +52,8 @@ fn under(doc: &mut Document, page: usize, rects: &[[f64; 4]]) -> usize {
|
||||
let (_, data) = page_streams_within(doc, &p.dict, page, &mut budget).unwrap();
|
||||
let res = p.dict.get(b"Resources").and_then(|r| doc.resolve(r).as_dict().cloned()).unwrap_or_default();
|
||||
let mut rep = Report::default();
|
||||
let mut scope = Scope::new(rects, Mode::Verify, &mut rep, budget);
|
||||
let mut images = pdfcraft_cos::ImageBudget::with_work(0);
|
||||
let mut scope = Scope::new(rects, Mode::Verify, &mut rep, budget, &mut images);
|
||||
process(doc, &mut scope, &data, &res, pdfcraft_content::Matrix::IDENTITY).residue
|
||||
}
|
||||
|
||||
@@ -519,10 +520,16 @@ fn two_pages_one_resource_dictionary(inherited: bool, again: bool) -> Document {
|
||||
])
|
||||
}
|
||||
|
||||
/// What image `s` decodes to, its fax or JBIG2 data included, with no limit on the work: the
|
||||
/// samples an operation would read through its `ImageBudget`.
|
||||
fn decoded_image(doc: &Document, s: &pdfcraft_cos::Stream) -> Result<Vec<u8>, pdfcraft_cos::CosError> {
|
||||
pdfcraft_cos::ImageBudget::with_work(u64::MAX).decode(doc, s, pdfcraft_cos::MAX_DECODED)
|
||||
}
|
||||
|
||||
/// The samples of the image a page's (possibly inherited) resources name `name`, decoded through
|
||||
/// its image codec too (`Document::decoded_image`).
|
||||
/// its image codec too ([`decoded_image`]).
|
||||
fn named_image(doc: &Document, page: usize, name: &[u8]) -> Option<Vec<u8>> {
|
||||
named_stream(doc, page, name).and_then(|s| doc.decoded_image(&s).ok())
|
||||
named_stream(doc, page, name).and_then(|s| decoded_image(doc, &s).ok())
|
||||
}
|
||||
|
||||
/// The image a page's (possibly inherited) resources name `name`.
|
||||
@@ -707,7 +714,8 @@ fn group_3_on_bytes_is_removed_whole_and_other_fax_images_cleared() {
|
||||
(-1, true, "<< /K -1 /Columns 16 /EncodedByteAlign true >>", vec![0x80, 0x80], vec![], false),
|
||||
] {
|
||||
let p = pdfcraft_filters::CcittParams { k, columns: 16, encoded_byte_align: on_bytes, ..Default::default() };
|
||||
assert_eq!(pdfcraft_filters::decode_ccitt(&data, &p, 2).unwrap(), [0xFF; 4], "{parms}: the picture is white");
|
||||
let mut work = u64::MAX;
|
||||
assert_eq!(pdfcraft_filters::decode_ccitt_within(&data, &p, 2, &mut work).unwrap(), [0xFF; 4], "{parms}: the picture is white");
|
||||
let dict = format!("{image} /DecodeParms {parms}");
|
||||
let mut objs = vec![stream(&dict, data)];
|
||||
objs.extend(extra);
|
||||
@@ -769,7 +777,7 @@ fn no_stream_holds_the_pixels_under_a_mark_on_a_jbig2_scan() {
|
||||
}
|
||||
let holds = |doc: &Document, pixels: &[u8]| {
|
||||
doc.scan_objects().any(|(_, object)| match &*object {
|
||||
Object::Stream(s) => doc.decoded_image(s).is_ok_and(|d| d.windows(pixels.len()).any(|w| w == pixels)),
|
||||
Object::Stream(s) => decoded_image(doc, s).is_ok_and(|d| d.windows(pixels.len()).any(|w| w == pixels)),
|
||||
_ => false,
|
||||
})
|
||||
};
|
||||
@@ -806,6 +814,61 @@ fn jbig2_globals(secret: &[u8]) -> Vec<u8> {
|
||||
g
|
||||
}
|
||||
|
||||
/// An image the run's allowance can't decode can't be cleared. Removed whole, like an image that
|
||||
/// can't be read, it would take what no mark covers with it without a word, so the run stops there,
|
||||
/// and [`apply`] leaves the document as it was.
|
||||
#[test]
|
||||
fn a_jbig2_image_past_the_runs_allowance_stops_the_run() {
|
||||
let mut dict = Dict::new();
|
||||
dict.set(b"Width".to_vec(), Object::Int(16));
|
||||
dict.set(b"Height".to_vec(), Object::Int(2));
|
||||
dict.set(b"BitsPerComponent".to_vec(), Object::Int(1));
|
||||
dict.set(b"ColorSpace".to_vec(), Object::name("DeviceGray"));
|
||||
dict.set(b"Filter".to_vec(), Object::name("JBIG2Decode"));
|
||||
let image = Stream::from_raw(dict, pdfcraft_filters::encode_jbig2_generic(&[0xFF; 4], 16, 2).unwrap());
|
||||
let doc = Document::new_empty();
|
||||
let half = [[0.0, 0.0, 0.5, 1.0]];
|
||||
let clear = |work| crate::image::clear(&doc, &image, &pdfcraft_content::Matrix::IDENTITY, &half, &mut pdfcraft_cos::ImageBudget::with_work(work));
|
||||
assert!(matches!(clear(u64::MAX), Ok(Some(_))), "cleared in a copy");
|
||||
assert!(matches!(clear(0), Err(())), "it can't be cleared");
|
||||
|
||||
let coded = pdfcraft_filters::encode_jbig2_generic(&[0xFF; 4], 16, 2).unwrap();
|
||||
let dict = "/Type /XObject /Subtype /Image /Width 16 /Height 2 /BitsPerComponent 1 /ColorSpace /DeviceGray /Filter /JBIG2Decode";
|
||||
let mut doc = one_page(b"q 160 0 0 20 0 0 cm /Im Do Q", "/XObject << /Im 7 0 R >>", vec![stream(dict, coded)]);
|
||||
mark(&mut doc, 0, &[[0.0, 12.0, 75.0, 18.0]], "");
|
||||
let refused = crate::apply_within(&mut doc, None, pdfcraft_cos::ImageBudget::with_work(0));
|
||||
assert!(matches!(refused, Err(crate::RedactError::ImagesPastAllowance)), "{refused:?}");
|
||||
let mut doc = one_page(
|
||||
b"q 160 0 0 20 0 0 cm /Im Do Q",
|
||||
"/XObject << /Im 7 0 R >>",
|
||||
vec![stream(dict, pdfcraft_filters::encode_jbig2_generic(&[0xFF; 4], 16, 2).unwrap())],
|
||||
);
|
||||
mark(&mut doc, 0, &[[0.0, 12.0, 75.0, 18.0]], "");
|
||||
assert!(crate::apply_within(&mut doc, None, pdfcraft_cos::ImageBudget::with_work(u64::MAX)).is_ok());
|
||||
}
|
||||
|
||||
/// A Flate image past the run's allowance stops the run as a JBIG2 image does: removed whole, it
|
||||
/// would take what no mark covers with it, unreported. A JPEG, which clearing doesn't read, is
|
||||
/// removed whole as it always was, and spends nothing.
|
||||
#[test]
|
||||
fn a_flate_image_past_the_runs_allowance_stops_the_run() {
|
||||
let dict = "/Type /XObject /Subtype /Image /Width 2 /Height 2 /BitsPerComponent 8 /ColorSpace /DeviceGray /Filter /FlateDecode";
|
||||
let page = || one_page(b"q 160 0 0 20 0 0 cm /Im Do Q", "/XObject << /Im 7 0 R >>", vec![stream(dict, pdfcraft_filters::encode_flate(&[9; 4]))]);
|
||||
let mut doc = page();
|
||||
mark(&mut doc, 0, &[[0.0, 12.0, 75.0, 18.0]], "");
|
||||
let refused = crate::apply_within(&mut doc, None, pdfcraft_cos::ImageBudget::with_work(0));
|
||||
assert!(matches!(refused, Err(crate::RedactError::ImagesPastAllowance)), "{refused:?}");
|
||||
let mut doc = page();
|
||||
mark(&mut doc, 0, &[[0.0, 12.0, 75.0, 18.0]], "");
|
||||
assert!(crate::apply_within(&mut doc, None, pdfcraft_cos::ImageBudget::with_work(u64::MAX)).is_ok());
|
||||
|
||||
let dict = "/Type /XObject /Subtype /Image /Width 2 /Height 2 /BitsPerComponent 8 /ColorSpace /DeviceGray /Filter /DCTDecode";
|
||||
let mut doc = one_page(b"q 160 0 0 20 0 0 cm /Im Do Q", "/XObject << /Im 7 0 R >>", vec![stream(dict, b"not read")]);
|
||||
mark(&mut doc, 0, &[[0.0, 12.0, 75.0, 18.0]], "");
|
||||
let report = crate::apply_within(&mut doc, None, pdfcraft_cos::ImageBudget::with_work(0)).unwrap();
|
||||
assert_eq!(report.images_removed, 1);
|
||||
}
|
||||
|
||||
/// A JBIG2 image (a scan the optimizer stored as JBIG2) has its covered pixels cleared in a copy,
|
||||
/// like a fax image, instead of being removed whole: with `/JBIG2Globals`, its `/DecodeParms` by
|
||||
/// reference, behind another filter with its globals at its own place, or as a mask, its decode
|
||||
@@ -830,6 +893,13 @@ fn a_jbig2_image_has_its_covered_pixels_cleared_instead_of_being_removed() {
|
||||
(
|
||||
format!("{image} /ColorSpace /DeviceGray /Filter [/ASCIIHexDecode /JBIG2Decode] /DecodeParms [null << /JBIG2Globals 8 0 R >>]"),
|
||||
hex,
|
||||
vec![globals.clone()],
|
||||
[0x00, 0xFF, 0xFF, 0xFF],
|
||||
),
|
||||
// `/Crypt` was undone on load, and takes a place in the parameters.
|
||||
(
|
||||
format!("{image} /ColorSpace /DeviceGray /Filter [/Crypt /JBIG2Decode] /DecodeParms [null << /JBIG2Globals 8 0 R >>]"),
|
||||
white.clone(),
|
||||
vec![globals],
|
||||
[0x00, 0xFF, 0xFF, 0xFF],
|
||||
),
|
||||
@@ -1199,7 +1269,7 @@ fn globals_a_redacted_jbig2_image_shares_with_another_page_leave_the_file() {
|
||||
let res = doc.resolve(p.dict.get(b"Resources")?).as_dict().cloned()?;
|
||||
let xo = doc.resolve(res.get(b"XObject")?).as_dict().cloned()?;
|
||||
match &*doc.get(xo.get(name)?.as_ref()?) {
|
||||
Object::Stream(s) => doc.decoded_image(s).ok(),
|
||||
Object::Stream(s) => decoded_image(doc, s).ok(),
|
||||
_ => None,
|
||||
}
|
||||
};
|
||||
@@ -1240,6 +1310,15 @@ fn globals_a_redacted_jbig2_image_shares_with_another_page_leave_the_file() {
|
||||
let mut doc = build(&image.replace(&format!("/Height {h}"), &format!("/Height {}", h + 1)));
|
||||
mark(&mut doc, 0, &[[0.25, 113.75, 49.75, 120.0]], "");
|
||||
assert!(matches!(apply(&mut doc, None), Err(RedactError::SharedJbig2Globals(1))));
|
||||
// Storing the second page's image again decodes it, within what is left of the run's
|
||||
// allowance: with nothing left the redaction is refused as one past the allowance, not
|
||||
// reported as an image that can't be read.
|
||||
let mut doc = build(&image);
|
||||
let first_image = [ObjRef::new(7, 0)];
|
||||
let refused = crate::restore_shared_jbig2(&mut doc, &first_image, &mut pdfcraft_cos::ImageBudget::with_work(0));
|
||||
assert!(matches!(refused, Err(RedactError::ImagesPastAllowance)), "{refused:?}");
|
||||
let restored = crate::restore_shared_jbig2(&mut doc, &first_image, &mut pdfcraft_cos::ImageBudget::with_work(u64::MAX));
|
||||
assert_eq!(restored.ok(), Some(1));
|
||||
}
|
||||
|
||||
/// Apply Redactions gives the page its own pruned /Resources, but the dictionary it drew through
|
||||
@@ -2884,7 +2963,7 @@ fn assert_no_secret(doc: &Document, secret: &[u8]) {
|
||||
assert!(!bytes.windows(secret.len()).any(|w| w == secret), "secret remains in object {r:?}");
|
||||
if let Object::Stream(s) = &*object {
|
||||
// Image codecs, a cleared scan coded as Group 4 or JBIG2, decode through the document.
|
||||
let data = s.decoded().or_else(|_| saved.decoded_image(s)).unwrap();
|
||||
let data = s.decoded().or_else(|_| decoded_image(&saved, s)).unwrap();
|
||||
assert!(!data.windows(secret.len()).any(|w| w == secret), "secret remains in stream {r:?}");
|
||||
}
|
||||
}
|
||||
@@ -3792,3 +3871,29 @@ fn a_reply_on_another_page_to_a_removed_popup_goes_too() {
|
||||
assert!(!bytes.windows(gone.len()).any(|w| w == gone), "{} survived", String::from_utf8_lossy(gone));
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn a_rewritten_form_xobject_drops_the_source_text_of_added_content() {
|
||||
// A form drawing invisible text whose dictionary repeats it in /PCAdded.
|
||||
let form = stream(
|
||||
"/Type /XObject /Subtype /Form /BBox [0 0 300 300] /Resources << /Font << /F1 5 0 R >> >> /PCMark /Added /PCAdded << /Kind /Text /Text (LEAK_FORM_SOURCE) >>",
|
||||
b"BT /F1 10 Tf 3 Tr 10 100 Td (HIDDEN) Tj ET BT /F1 10 Tf 10 200 Td (Shown) Tj ET",
|
||||
);
|
||||
let mut doc = one_page(b"/X Do", "/XObject << /X 7 0 R >>", vec![form]);
|
||||
sanitize::remove_hidden(&mut doc, &[sanitize::Hidden::HiddenText]).unwrap();
|
||||
let bytes = write_full(&doc, &SaveOptions { object_streams: false, ..SaveOptions::default() }).unwrap();
|
||||
assert!(!bytes.windows(16).any(|w| w == b"LEAK_FORM_SOURCE"), "the form's added-content source text survived");
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn a_redacted_form_xobject_drops_the_source_text_of_added_content() {
|
||||
let form = stream(
|
||||
"/Type /XObject /Subtype /Form /BBox [0 0 300 300] /Resources << /Font << /F1 5 0 R >> >> /PCMark /Added /PCAdded << /Kind /Text /Text (AB1234CD) >>",
|
||||
b"BT /F1 10 Tf 10 100 Td (AB1234CD) Tj ET",
|
||||
);
|
||||
let mut doc = one_page(b"/X Do", "/XObject << /X 7 0 R >>", vec![form]);
|
||||
mark(&mut doc, 0, &[[20.0, 95.0, 40.0, 110.0]], "");
|
||||
apply(&mut doc, None).unwrap();
|
||||
let bytes = write_full(&doc, &SaveOptions { object_streams: false, ..SaveOptions::default() }).unwrap();
|
||||
assert!(!bytes.windows(4).any(|w| w == b"1234"), "redacted text left in the saved file");
|
||||
}
|
||||
@@ -62,3 +62,61 @@ fn a_link_element_that_keeps_its_text_loses_the_description_of_its_removed_annot
|
||||
let link = doc.get(ObjRef::new(11, 0)).as_dict().cloned().unwrap();
|
||||
assert_eq!(link.get(b"K"), Some(&Object::Array(vec![Object::Int(0)])), "the element keeps its text");
|
||||
}
|
||||
|
||||
/// [`sectioned`], with titles that repeat the secret on the paragraph that owns it, on its section
|
||||
/// and on the document element above both.
|
||||
fn titled() -> Document {
|
||||
let mut doc = sectioned("11 0 R");
|
||||
let title = |t: &str| Object::String(pdfcraft_cos::PdfString::literal(t.as_bytes().to_vec()));
|
||||
for (n, t) in [(8, "LEAK_DOC_TITLE"), (9, "LEAK_OWN_TITLE"), (11, "LEAK_SECT_TITLE"), (10, "Public title")] {
|
||||
doc.update_dict(ObjRef::new(n, 0), |d| d.set(b"T".to_vec(), title(t))).unwrap();
|
||||
}
|
||||
doc
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn titles_repeating_redacted_content_go_from_the_owner_and_its_ancestors() {
|
||||
let mut doc = titled();
|
||||
mark(&mut doc, 0, &[[5.0, 195.0, 60.0, 212.0]], "");
|
||||
apply(&mut doc, None).unwrap();
|
||||
assert!(!full_save_holds(&doc, b"LEAK_"), "a structure title repeating the redacted word survived");
|
||||
let public = doc.get(ObjRef::new(10, 0)).as_dict().cloned().unwrap();
|
||||
assert!(public.contains(b"T"), "an element beside it keeps its own title");
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn titles_repeating_hidden_text_go_from_the_owner_and_its_ancestors() {
|
||||
use crate::sanitize::{Hidden, remove_hidden};
|
||||
let mut doc = titled();
|
||||
let hidden =
|
||||
b"/P <</MCID 0>> BDC BT /F1 10 Tf 3 Tr 10 200 Td (SECRET) Tj ET EMC /P <</MCID 1>> BDC BT /F1 10 Tf 0 Tr 10 100 Td (Public) Tj ET EMC";
|
||||
doc.set(ObjRef::new(4, 0), Object::Stream(Stream::from_raw(Dict::new(), hidden.to_vec())));
|
||||
remove_hidden(&mut doc, &[Hidden::HiddenText]).unwrap();
|
||||
assert!(!full_save_holds(&doc, b"SECRET"), "the hidden text survived");
|
||||
assert!(!full_save_holds(&doc, b"LEAK_"), "a structure title repeating the hidden text survived");
|
||||
let public = doc.get(ObjRef::new(10, 0)).as_dict().cloned().unwrap();
|
||||
assert!(public.contains(b"T"), "an element beside it keeps its own title");
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn an_ancestor_title_describing_a_removed_annotation_goes() {
|
||||
use crate::sanitize::{Hidden, remove_hidden};
|
||||
let mut doc = pdf(vec![
|
||||
b"<< /Type /Catalog /Pages 2 0 R /MarkInfo << /Marked true >> /StructTreeRoot 8 0 R >>".to_vec(),
|
||||
b"<< /Type /Pages /Kids [3 0 R] /Count 1 >>".to_vec(),
|
||||
b"<< /Type /Page /Parent 2 0 R /MediaBox [0 0 300 300] /Contents 4 0 R /Resources << /Font << /F1 5 0 R >> >> /Annots [6 0 R] /StructParents 0 >>"
|
||||
.to_vec(),
|
||||
stream("", b"/Link << /MCID 0 >> BDC BT /F1 10 Tf 10 230 Td (See the site) Tj ET EMC"),
|
||||
FONT.replace("95 0 R", "12 0 R").into_bytes(),
|
||||
b"<< /Type /Annot /Subtype /Link /Rect [10 228 80 240] /StructParent 1 /A << /S /URI /URI (https://example.org/) >> >>".to_vec(),
|
||||
b"null".to_vec(),
|
||||
b"<< /Type /StructTreeRoot /K 9 0 R /ParentTree << /Nums [0 [11 0 R] 1 11 0 R] >> /ParentTreeNextKey 2 >>".to_vec(),
|
||||
b"<< /Type /StructElem /S /Document /P 8 0 R /K 10 0 R >>".to_vec(),
|
||||
// Only a title above the link element repeats the address.
|
||||
b"<< /Type /StructElem /S /P /P 9 0 R /T (LEAK_PARENT_TITLE) /K 11 0 R >>".to_vec(),
|
||||
b"<< /Type /StructElem /S /Link /P 10 0 R /Pg 3 0 R /K [0 << /Type /OBJR /Obj 6 0 R /Pg 3 0 R >>] >>".to_vec(),
|
||||
widths(),
|
||||
]);
|
||||
remove_hidden(&mut doc, &[Hidden::LinksActionsScripts]).unwrap();
|
||||
assert!(!full_save_holds(&doc, b"LEAK_"), "an ancestor's title describing the removed link survived");
|
||||
}
|
||||
@@ -288,11 +288,23 @@ impl<'a> Inspector<'a> {
|
||||
}
|
||||
|
||||
pub(super) fn text(&self, d: &Dictionary, key: &[u8]) -> Option<String> {
|
||||
let s = trimmed_text(self.resolve(d.get(key).ok()?))?;
|
||||
(!s.is_empty()).then_some(s)
|
||||
// Typewriter outer whitespace belongs to the text (keep in step with annot's summaries).
|
||||
let s = if key == b"Contents"
|
||||
&& self.name(d, b"Subtype").as_deref() == Some("FreeText")
|
||||
&& self.name(d, b"IT").as_deref() == Some("FreeTextTypeWriter")
|
||||
{
|
||||
match self.resolve(d.get(key).ok()?) {
|
||||
Object::String(bytes, _) => text_string(bytes).trim_matches('\0').to_owned(),
|
||||
Object::Name(bytes) => String::from_utf8_lossy(bytes).trim_matches('\0').to_owned(),
|
||||
_ => return None,
|
||||
}
|
||||
} else {
|
||||
trimmed_text(self.resolve(d.get(key).ok()?))?
|
||||
};
|
||||
(!s.trim().is_empty()).then_some(s)
|
||||
}
|
||||
|
||||
/// [`Self::text`], converted and spent from `budget` as [`spend`] does, so text that trims
|
||||
/// Whitespace-trimmed metadata, spent from `budget` as [`spend`] does, so text that trims
|
||||
/// short or to nothing still spends its raw length.
|
||||
pub(super) fn budgeted_text(&self, d: &Dictionary, key: &[u8], budget: &mut usize) -> Option<String> {
|
||||
let o = self.resolve(d.get(key).ok()?);
|
||||
|
||||
@@ -1870,3 +1870,45 @@ trailer << /Root 1 0 R >>
|
||||
assert!((p.width - 3874.96).abs() < 0.1, "width expected ~3874.96, got {}", p.width);
|
||||
assert!((p.height - 5493.54).abs() < 0.1, "height expected ~5493.54, got {}", p.height);
|
||||
}
|
||||
|
||||
/// Inspection keeps every object it reads, converted, for as long as it runs, and nothing it
|
||||
/// reports comes from `/PieceInfo`. InDesign writes kilobytes of that private data into every
|
||||
/// page, and a 1,412-page book held over a gigabyte of it (#5873). It is left out of what
|
||||
/// inspection keeps, and what inspection reports is the same as for the page without it.
|
||||
#[test]
|
||||
fn inspection_keeps_no_private_page_data() {
|
||||
use lopdf::dictionary;
|
||||
let make = |private: bool| -> Vec<u8> {
|
||||
let mut doc = Document::with_version("1.7");
|
||||
let pages_id = doc.new_object_id();
|
||||
let mut page = dictionary! {
|
||||
"Type" => "Page",
|
||||
"Parent" => pages_id,
|
||||
"MediaBox" => vec![0.into(), 0.into(), 200.into(), 300.into()],
|
||||
"Rotate" => 90,
|
||||
};
|
||||
if private {
|
||||
let map: Dictionary = (0..50).map(|i| (i.to_string(), Object::Array(vec![Object::Integer(i), Object::Real(116.22)]))).collect();
|
||||
page.set("PieceInfo", dictionary! { "InDesign" => dictionary! { "PageItemUIDToLocationDataMap" => map } });
|
||||
}
|
||||
let page_id = doc.add_object(page);
|
||||
doc.objects.insert(pages_id, dictionary! { "Type" => "Pages", "Kids" => vec![page_id.into()], "Count" => 1 }.into());
|
||||
let catalog = doc.add_object(dictionary! { "Type" => "Catalog", "Pages" => pages_id });
|
||||
doc.trailer.set("Root", catalog);
|
||||
let mut out = Vec::new();
|
||||
doc.save_to(&mut out).unwrap();
|
||||
out
|
||||
};
|
||||
let (with, without) = (make(true), make(false));
|
||||
let lazy = LazyStructure::new(Arc::new(with.clone()), None).unwrap();
|
||||
let page = lazy.get_object((2, 0)).unwrap().as_dict().unwrap();
|
||||
assert!(!page.has(b"PieceInfo"), "the private data is not kept");
|
||||
assert!(page.has(b"MediaBox") && page.has(b"Rotate") && page.has(b"Parent"), "the rest of the page is");
|
||||
|
||||
let report = |bytes: Vec<u8>| {
|
||||
let mut info = inspect(Arc::new(bytes), None).unwrap();
|
||||
info.file_size = 0;
|
||||
format!("{info:?}")
|
||||
};
|
||||
assert_eq!(report(with), report(without), "what inspection reports does not change");
|
||||
}
|
||||
@@ -83,6 +83,10 @@ pub struct RenderConfig {
|
||||
/// viewer and preview rasters: exports, printing and OCR render without it, so nothing drawn with an
|
||||
/// installed font is saved or printed (AGENTS.md §1.2, §1.4).
|
||||
pub system_fonts: bool,
|
||||
/// Steps of JBIG2 decoding a render may take across the page's images, instead of the usual
|
||||
/// `hayro_syntax::MAX_PAGE_JBIG2_WORK`. Those past it aren't drawn, like an image that can't
|
||||
/// be decoded.
|
||||
pub jbig2_work: Option<u64>,
|
||||
}
|
||||
|
||||
impl RenderConfig {
|
||||
@@ -100,7 +104,8 @@ impl RenderConfig {
|
||||
/// Passwords belong to parser construction; request-specific preview overrides are applied
|
||||
/// by `render_page`, which also preserves the caller's warning and cancellation hooks.
|
||||
fn settings(&self) -> InterpreterSettings {
|
||||
let standard = InterpreterSettings::default().font_resolver;
|
||||
let defaults = InterpreterSettings::default();
|
||||
let standard = defaults.font_resolver.clone();
|
||||
let system_fonts = self.system_fonts;
|
||||
InterpreterSettings {
|
||||
ocg_overrides: self.layers.clone(),
|
||||
@@ -108,7 +113,8 @@ impl RenderConfig {
|
||||
font_resolver: Arc::new(move |query| {
|
||||
japanese_fallback(query).or_else(|| system_fonts.then(|| system_fallback(query)).flatten()).or_else(|| standard(query))
|
||||
}),
|
||||
..InterpreterSettings::default()
|
||||
jbig2_work: self.jbig2_work.unwrap_or(defaults.jbig2_work),
|
||||
..defaults
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
@@ -4058,7 +4058,10 @@ fn jbig2_image_draws_with(stream: &[u8], space: &str, entries: &str, objects: &[
|
||||
pdf.extend_from_slice(b"\nendstream endobj\n");
|
||||
pdf.extend_from_slice(objects);
|
||||
pdf.extend_from_slice(b"trailer << /Root 1 0 R >>\n%%EOF\n");
|
||||
let mut r = PageRenderer::new(Arc::new(pdf), RenderConfig::default());
|
||||
// What one image may take, which the page's allowance, tested on its own, would otherwise reach
|
||||
// first: it is the same size, and the page itself comes out of it.
|
||||
let config = RenderConfig { jbig2_work: Some(u64::MAX), ..RenderConfig::default() };
|
||||
let mut r = PageRenderer::new(Arc::new(pdf), config);
|
||||
let page = r.render(RenderRequest { page: 0, kind: RequestKind::Pixels, tile: None, scale: 1.0, tag: 0, ..Default::default() });
|
||||
assert!(page.error.is_none(), "{:?}", page.error);
|
||||
assert_eq!(&page.rgba[((38 * 40 + 1) * 4)..][..4], &[255, 0, 0, 255], "the rest of the page draws");
|
||||
@@ -4070,6 +4073,217 @@ fn jbig2_image_draws_with(stream: &[u8], space: &str, entries: &str, objects: &[
|
||||
}
|
||||
}
|
||||
|
||||
/// The JBIG2 images of a page share one allowance, down to the step, and the next page starts with
|
||||
/// its own. The images differ by an extension segment: one image decoded again isn't decoded twice.
|
||||
#[test]
|
||||
fn the_jbig2_images_of_a_page_share_one_allowance() {
|
||||
let image = |number: u8, id: u8| {
|
||||
let mut stream = black_jbig2_page();
|
||||
jbig2_segment(&mut stream, 1, 62, &[], &[0, 0, 0, 0, id]);
|
||||
let mut object = format!(
|
||||
"{number} 0 obj << /Type /XObject /Subtype /Image /Width 16 /Height 2 /BitsPerComponent 1 /ColorSpace /DeviceGray /Filter /JBIG2Decode /Length {} >> stream\n",
|
||||
stream.len()
|
||||
)
|
||||
.into_bytes();
|
||||
object.extend_from_slice(&stream);
|
||||
object.extend_from_slice(b"\nendstream endobj\n");
|
||||
object
|
||||
};
|
||||
let page = |number: u8, content: u8, xobjects: &str| {
|
||||
format!("{number} 0 obj << /Type /Page /Parent 2 0 R /MediaBox [0 0 40 40] /Contents {content} 0 R /Resources << /XObject << {xobjects} >> >> >> endobj\n").into_bytes()
|
||||
};
|
||||
let content = |number: u8, text: &str| format!("{number} 0 obj << /Length {} >> stream\n{text}\nendstream endobj\n", text.len()).into_bytes();
|
||||
let mut pdf =
|
||||
b"%PDF-1.7\n1 0 obj << /Type /Catalog /Pages 2 0 R >> endobj\n2 0 obj << /Type /Pages /Kids [3 0 R 4 0 R] /Count 2 >> endobj\n".to_vec();
|
||||
pdf.extend(page(3, 5, "/A 7 0 R /B 8 0 R"));
|
||||
pdf.extend(page(4, 6, "/C 9 0 R"));
|
||||
pdf.extend(content(5, "q 20 0 0 40 0 0 cm /A Do Q q 20 0 0 40 20 0 cm /B Do Q"));
|
||||
pdf.extend(content(6, "q 20 0 0 40 0 0 cm /C Do Q"));
|
||||
pdf.extend(image(7, 1));
|
||||
pdf.extend(image(8, 2));
|
||||
pdf.extend(image(9, 3));
|
||||
pdf.extend_from_slice(b"trailer << /Root 1 0 R >>\n%%EOF\n");
|
||||
let pdf = Arc::new(pdf);
|
||||
let black = |page: &RenderedPage, x: usize| match &page.rgba[((20 * 40 + x) * 4)..][..4] {
|
||||
[0, 0, 0, 255] => true,
|
||||
[255, 255, 255, 255] => false,
|
||||
other => panic!("neither an image nor the page: {other:?}"),
|
||||
};
|
||||
let pages = |work: u64| {
|
||||
let mut renderer = PageRenderer::new(pdf.clone(), RenderConfig { jbig2_work: Some(work), ..RenderConfig::default() });
|
||||
[0, 1].map(|page| renderer.render(RenderRequest { page, kind: RequestKind::Pixels, tile: None, scale: 1.0, tag: 0, ..Default::default() }))
|
||||
};
|
||||
let drawn = |work: u64| {
|
||||
let [first, _] = pages(work);
|
||||
assert!(first.error.is_none(), "{:?}", first.error);
|
||||
(black(&first, 10), black(&first, 30))
|
||||
};
|
||||
let one = (1..1_000).find(|work| drawn(*work).0).expect("a small image is cheap");
|
||||
assert_eq!(drawn(one - 1), (false, false), "a step short of the first");
|
||||
assert_eq!(drawn(one), (true, false), "enough for one");
|
||||
assert_eq!(drawn(2 * one - 1), (true, false), "a step short of both");
|
||||
assert_eq!(drawn(2 * one), (true, true), "enough for both");
|
||||
let [first, second] = pages(one);
|
||||
assert!(first.warnings.contains(&RenderWarning::ContentTruncated), "the page says it left something out: {:?}", first.warnings);
|
||||
assert!(pages(2 * one)[0].warnings.is_empty(), "and only then");
|
||||
assert!(black(&second, 10), "the next page has its own allowance, though this one spent all of it");
|
||||
let usual = PageRenderer::new(pdf.clone(), RenderConfig::default()).render(RenderRequest {
|
||||
page: 0,
|
||||
kind: RequestKind::Pixels,
|
||||
tile: None,
|
||||
scale: 1.0,
|
||||
tag: 0,
|
||||
..Default::default()
|
||||
});
|
||||
assert!(black(&usual, 10) && black(&usual, 30), "the usual allowance is far above a page like this");
|
||||
}
|
||||
|
||||
/// Without its mask a picture would show what the mask hides, so a JBIG2 mask past the page's
|
||||
/// allowance takes the picture with it, and the page says so. A mask that can't be read for any
|
||||
/// other reason leaves the picture, as it did.
|
||||
#[test]
|
||||
fn a_picture_whose_jbig2_mask_is_past_the_pages_allowance_is_not_drawn() {
|
||||
let draw = |entry: &str, filter: &str, mask: &[u8], work: u64| {
|
||||
let content = b"q 20 0 0 20 5 5 cm /Im1 Do Q";
|
||||
let mut pdf = b"%PDF-1.7\n1 0 obj << /Type /Catalog /Pages 2 0 R >> endobj\n2 0 obj << /Type /Pages /Kids [3 0 R] /Count 1 >> endobj\n3 0 obj << /Type /Page /Parent 2 0 R /MediaBox [0 0 40 40] /Contents 4 0 R /Resources << /XObject << /Im1 5 0 R >> >> >> endobj\n".to_vec();
|
||||
pdf.extend_from_slice(format!("4 0 obj << /Length {} >> stream\n", content.len()).as_bytes());
|
||||
pdf.extend_from_slice(content);
|
||||
pdf.extend_from_slice(b"\nendstream endobj\n");
|
||||
pdf.extend_from_slice(
|
||||
format!("5 0 obj << /Type /XObject /Subtype /Image /Width 1 /Height 1 /BitsPerComponent 8 /ColorSpace /DeviceGray {entry} 6 0 R /Length 1 >> stream\n\0\nendstream endobj\n").as_bytes(),
|
||||
);
|
||||
let kind = if entry == "/Mask" { "/ImageMask true" } else { "/ColorSpace /DeviceGray" };
|
||||
pdf.extend_from_slice(
|
||||
format!(
|
||||
"6 0 obj << /Type /XObject /Subtype /Image /Width 16 /Height 2 /BitsPerComponent 1 {kind} /Filter {filter} /Length {} >> stream\n",
|
||||
mask.len()
|
||||
)
|
||||
.as_bytes(),
|
||||
);
|
||||
pdf.extend_from_slice(mask);
|
||||
pdf.extend_from_slice(b"\nendstream endobj\ntrailer << /Root 1 0 R >>\n%%EOF\n");
|
||||
let config = RenderConfig { jbig2_work: Some(work), ..RenderConfig::default() };
|
||||
let page = PageRenderer::new(Arc::new(pdf), config).render(RenderRequest {
|
||||
page: 0,
|
||||
kind: RequestKind::Pixels,
|
||||
tile: None,
|
||||
scale: 1.0,
|
||||
tag: 0,
|
||||
..Default::default()
|
||||
});
|
||||
assert!(page.error.is_none(), "{:?}", page.error);
|
||||
let shown = match &page.rgba[((25 * 40 + 15) * 4)..][..4] {
|
||||
[0, 0, 0, 255] => true,
|
||||
[255, 255, 255, 255] => false,
|
||||
other => panic!("neither the picture nor the page: {other:?}"),
|
||||
};
|
||||
(shown, page.warnings.contains(&RenderWarning::ContentTruncated))
|
||||
};
|
||||
let mask = black_jbig2_page();
|
||||
let jbig2 = "/JBIG2Decode";
|
||||
assert_eq!(draw("/SMask", jbig2, &mask, u64::MAX), (false, false), "the mask hides all of it");
|
||||
assert_eq!(draw("/SMask", jbig2, &mask, 0), (false, true), "past the allowance a soft mask hides it too");
|
||||
assert_eq!(draw("/Mask", jbig2, &mask, 0), (false, true), "and so does a stencil mask");
|
||||
assert_eq!(draw("/SMask", jbig2, b"no JBIG2 here", 1 << 20), (true, false), "any other bad mask is no mask");
|
||||
let other = draw("/SMask", "/DCTDecode", b"no JPEG here", 0);
|
||||
assert_eq!(other, (true, false), "and a page with nothing left says nothing of a mask that isn't JBIG2");
|
||||
}
|
||||
|
||||
/// A page's allowance ends with it, so what decodes on its thread afterwards has no page to run out
|
||||
/// on, and a `Context` used again starts afresh.
|
||||
#[test]
|
||||
fn a_pages_jbig2_allowance_ends_with_the_page() {
|
||||
use hayro::hayro_interpret::font::Glyph;
|
||||
use hayro::hayro_interpret::hayro_syntax::Pdf;
|
||||
use hayro::hayro_interpret::{
|
||||
BlendMode, ClipPath, Context, Device, GlyphDrawMode, Image, InterpreterCache, InterpreterSettings, Paint, PathDrawMode, SoftMask,
|
||||
TransformExt, interpret_page,
|
||||
};
|
||||
use hayro_syntax::page_jbig2_work_spent;
|
||||
use kurbo::{Affine, BezPath, Rect};
|
||||
|
||||
/// Notes at each path whether the page has run out.
|
||||
struct Spent(Vec<bool>);
|
||||
impl<'a> Device<'a> for Spent {
|
||||
fn set_soft_mask(&mut self, _: Option<SoftMask<'a>>) {}
|
||||
fn set_blend_mode(&mut self, _: BlendMode) {}
|
||||
fn draw_path(&mut self, _: &BezPath, _: Affine, _: &Paint<'a>, _: &PathDrawMode) {
|
||||
self.0.push(page_jbig2_work_spent());
|
||||
}
|
||||
fn push_clip_path(&mut self, _: &ClipPath) {}
|
||||
fn push_transparency_group(&mut self, _: f32, _: Option<SoftMask<'a>>, _: BlendMode) {}
|
||||
fn draw_glyph(&mut self, _: &Glyph<'a>, _: Affine, _: Affine, _: &Paint<'a>, _: &GlyphDrawMode) {}
|
||||
fn draw_image(&mut self, _: Image<'a, '_>, _: Affine) {}
|
||||
fn pop_clip_path(&mut self) {}
|
||||
fn pop_transparency_group(&mut self) {}
|
||||
}
|
||||
|
||||
let content = "0 0 4 4 re f";
|
||||
let bytes = format!(
|
||||
"%PDF-1.7\n1 0 obj << /Type /Catalog /Pages 2 0 R >> endobj\n2 0 obj << /Type /Pages /Kids [3 0 R] /Count 1 >> endobj\n3 0 obj << /Type /Page /Parent 2 0 R /MediaBox [0 0 40 40] /Contents 4 0 R >> endobj\n4 0 obj << /Length {} >> stream\n{content}\nendstream endobj\ntrailer << /Root 1 0 R >>\n%%EOF\n",
|
||||
content.len()
|
||||
);
|
||||
let pdf = Pdf::new(Arc::new(bytes.into_bytes())).expect("parses");
|
||||
let page = &pdf.pages()[0];
|
||||
let cache = InterpreterCache::new();
|
||||
let settings = InterpreterSettings { jbig2_work: 0, ..InterpreterSettings::default() };
|
||||
let mut ctx = Context::new(page.initial_transform(true).to_kurbo(), Rect::new(0.0, 0.0, 40.0, 40.0), &cache, page.xref(), settings);
|
||||
let mut device = Spent(Vec::new());
|
||||
for _ in 0..2 {
|
||||
interpret_page(page, &mut ctx, &mut device);
|
||||
assert!(!page_jbig2_work_spent(), "no page is being drawn");
|
||||
}
|
||||
assert_eq!(device.0, [true, true], "each time, the page has what its settings give it");
|
||||
}
|
||||
|
||||
/// An image that can't be decoded has still cost its reading, which a page repeats for each time
|
||||
/// it draws one, since such an image isn't kept. So what it reads comes out of the page's allowance,
|
||||
/// and an image after it has less. Allowed exactly what the good one takes, it isn't drawn behind
|
||||
/// the bad one, and is drawn alone.
|
||||
#[test]
|
||||
fn an_image_that_fails_spends_the_pages_allowance_too() {
|
||||
let image = |number: u8, stream: &[u8]| {
|
||||
let mut object = format!(
|
||||
"{number} 0 obj << /Type /XObject /Subtype /Image /Width 16 /Height 2 /BitsPerComponent 1 /ColorSpace /DeviceGray /Filter /JBIG2Decode /Length {} >> stream\n",
|
||||
stream.len()
|
||||
)
|
||||
.into_bytes();
|
||||
object.extend_from_slice(stream);
|
||||
object.extend_from_slice(b"\nendstream endobj\n");
|
||||
object
|
||||
};
|
||||
let pdf = |content: &str| {
|
||||
let mut pdf = format!(
|
||||
"%PDF-1.7\n1 0 obj << /Type /Catalog /Pages 2 0 R >> endobj\n2 0 obj << /Type /Pages /Kids [3 0 R] /Count 1 >> endobj\n\
|
||||
3 0 obj << /Type /Page /Parent 2 0 R /MediaBox [0 0 40 40] /Contents 4 0 R /Resources << /XObject << /Bad 5 0 R /Good 6 0 R >> >> >> endobj\n\
|
||||
4 0 obj << /Length {} >> stream\n{content}\nendstream endobj\n",
|
||||
content.len()
|
||||
)
|
||||
.into_bytes();
|
||||
pdf.extend(image(5, &[0xFF; 64]));
|
||||
pdf.extend(image(6, &black_jbig2_page()));
|
||||
pdf.extend_from_slice(b"trailer << /Root 1 0 R >>\n%%EOF\n");
|
||||
Arc::new(pdf)
|
||||
};
|
||||
let good = "q 40 0 0 40 0 0 cm /Good Do Q";
|
||||
let drawn = |content: &str, work: u64| {
|
||||
let config = RenderConfig { jbig2_work: Some(work), ..RenderConfig::default() };
|
||||
let page = PageRenderer::new(pdf(content), config).render(RenderRequest {
|
||||
page: 0,
|
||||
kind: RequestKind::Pixels,
|
||||
tile: None,
|
||||
scale: 1.0,
|
||||
tag: 0,
|
||||
..Default::default()
|
||||
});
|
||||
assert!(page.error.is_none(), "{:?}", page.error);
|
||||
page.rgba[((20 * 40 + 20) * 4)..][..4] == [0, 0, 0, 255]
|
||||
};
|
||||
let cost = (1..2_000).find(|work| drawn(good, *work)).expect("a small image is cheap");
|
||||
assert!(!drawn(&format!("q 1 0 0 1 0 0 cm /Bad Do Q {good}"), cost), "the bad one spent some of it");
|
||||
assert!(drawn(&format!("q 1 0 0 1 0 0 cm /Bad Do Q {good}"), cost + 4 * 64), "and what it spent is its reading");
|
||||
}
|
||||
|
||||
/// Bits written from the top of each byte, as JBIG2's Huffman-coded data is.
|
||||
#[derive(Default)]
|
||||
struct Bits {
|
||||
@@ -8004,6 +8218,61 @@ fn japanese_substitute_spaces_keep_pdf_widths_and_unicode() {
|
||||
}
|
||||
}
|
||||
|
||||
/// One code, `<0010>`, in a Type 0 font named `base_font` that the PDF doesn't embed, with a
|
||||
/// `/ToUnicode` that maps it to the UTF-16 `unicode`. 0x10 is the hyphen's glyph index in Arial,
|
||||
/// and Identity-H with an identity `/CIDToGIDMap` makes the code that index, as Word writes it.
|
||||
fn soft_hyphen_pdf(base_font: &str, unicode: &str) -> Vec<u8> {
|
||||
let content = "BT /F1 60 Tf 10 20 Td <0010> Tj ET";
|
||||
let cmap = format!(
|
||||
"/CIDInit /ProcSet findresource begin 12 dict begin begincmap
|
||||
/CIDSystemInfo << /Registry (Adobe) /Ordering (UCS) /Supplement 0 >> def
|
||||
/CMapName /Adobe-Identity-UCS def /CMapType 2 def
|
||||
1 begincodespacerange <0000> <FFFF> endcodespacerange
|
||||
1 beginbfchar <0010> <{unicode}> endbfchar
|
||||
endcmap CMapName currentdict /CMap defineresource pop end end"
|
||||
);
|
||||
format!(
|
||||
"%PDF-1.7
|
||||
1 0 obj << /Type /Catalog /Pages 2 0 R >> endobj
|
||||
2 0 obj << /Type /Pages /Kids [3 0 R] /Count 1 >> endobj
|
||||
3 0 obj << /Type /Page /Parent 2 0 R /MediaBox [0 0 60 60] /Contents 4 0 R /Resources << /Font << /F1 5 0 R >> >> >> endobj
|
||||
4 0 obj << /Length {} >> stream
|
||||
{content}
|
||||
endstream endobj
|
||||
5 0 obj << /Type /Font /Subtype /Type0 /BaseFont /{base_font} /Encoding /Identity-H /DescendantFonts [6 0 R] /ToUnicode 8 0 R >> endobj
|
||||
6 0 obj << /Type /Font /Subtype /CIDFontType2 /BaseFont /{base_font} /CIDSystemInfo << /Registry (Adobe) /Ordering (Identity) /Supplement 0 >>
|
||||
/FontDescriptor 7 0 R /CIDToGIDMap /Identity /DW 1000 /W [16 [333]] >> endobj
|
||||
7 0 obj << /Type /FontDescriptor /FontName /{base_font} /Flags 32 /FontBBox [-665 -325 2000 1040] /ItalicAngle 0 /Ascent 728 /Descent -210 /CapHeight 716 /StemV 80 >> endobj
|
||||
8 0 obj << /Length {} >> stream
|
||||
{cmap}
|
||||
endstream endobj
|
||||
trailer << /Root 1 0 R >>
|
||||
%%EOF",
|
||||
content.len(),
|
||||
cmap.len()
|
||||
)
|
||||
.into_bytes()
|
||||
}
|
||||
|
||||
/// #5888: Windows exporters map the hyphen glyph of an Arial they don't embed to U+00AD. The
|
||||
/// standard substitute has no soft hyphen, so code 0x0010 was taken as its glyph 16 and drew
|
||||
/// `Ë` (`!` in bold). It draws the substitute's hyphen now, and the text keeps the soft hyphen.
|
||||
#[test]
|
||||
fn a_soft_hyphen_a_substitute_lacks_draws_its_hyphen() {
|
||||
for base_font in ["ArialMT", "Arial-BoldMT"] {
|
||||
let soft = soft_hyphen_pdf(base_font, "00AD");
|
||||
let out = render_first_page(soft.clone());
|
||||
let expected = render_first_page(soft_hyphen_pdf(base_font, "002D"));
|
||||
assert!(expected.rgba.as_chunks::<4>().0.iter().any(|pixel| pixel[0] < 128), "{base_font}: the hyphen control must draw ink");
|
||||
assert!(out.rgba.as_ref() == expected.rgba.as_ref(), "{base_font}: a soft hyphen draws as the substitute's hyphen");
|
||||
let mut renderer = PageRenderer::new(Arc::new(soft), RenderConfig::default());
|
||||
let text = renderer.render(RenderRequest { page: 0, kind: RequestKind::Text, ..Default::default() });
|
||||
assert!(text.error.is_none(), "{:?}", text.error);
|
||||
let glyphs: String = text.text.unwrap().glyphs.iter().map(|glyph| glyph.text.as_str()).collect();
|
||||
assert_eq!(glyphs, "\u{ad}", "{base_font}: drawing the hyphen must not rewrite Unicode");
|
||||
}
|
||||
}
|
||||
|
||||
/// Half-width katakana are common in Japanese documents set in a non-embedded Mincho font
|
||||
/// such as HeiseiMin-W3. The Mincho substitute must have those glyphs: one that lacks them
|
||||
/// (Shippori Mincho) draws them as .notdef.
|
||||
@@ -8491,6 +8760,99 @@ mod devicen_inks;
|
||||
// patch 27).
|
||||
mod isolated_cmyk_groups;
|
||||
|
||||
/// The generation-0 stand-in a rebuilt table files an object under must not make the object a
|
||||
/// second object: enumeration yielded it once per key, so a document recovered without a readable
|
||||
/// page tree reported the page twice (noted in review of #5580).
|
||||
///
|
||||
/// And a later header for the same object number replaces the stand-in, so `N 0 R` cannot be left
|
||||
/// pointing at a body the exact key no longer names.
|
||||
#[cfg_attr(target_arch = "wasm32", wasm_bindgen_test::wasm_bindgen_test)]
|
||||
#[cfg_attr(not(target_arch = "wasm32"), test)]
|
||||
fn a_rebuilt_tables_generation_0_stand_in_is_not_a_second_object() {
|
||||
// No table, no `startxref`, and no readable page tree: the pages are recovered by looking for
|
||||
// objects that are pages, which is where a doubled object shows up as a doubled page.
|
||||
let pdf = "%PDF-1.4\n\
|
||||
1 0 obj << /Type /Catalog /Pages 2 0 R >> endobj\n\
|
||||
3 99999 obj << /Type /Page /MediaBox [0 0 200 100] /Contents 4 0 R >> endobj\n\
|
||||
4 0 obj << /Length 0 >> stream\n\nendstream endobj\n\
|
||||
trailer << /Root 1 0 R >>\n\
|
||||
%%EOF\n";
|
||||
let mut r = PageRenderer::new(Arc::new(pdf.to_string().into_bytes()), RenderConfig::default());
|
||||
let first = r.render(RenderRequest { page: 0, kind: RequestKind::Pixels, tile: None, scale: 1.0, tag: 0, preview: false });
|
||||
assert!(first.error.is_none(), "the page is recovered: {:?}", first.error);
|
||||
let second = r.render(RenderRequest { page: 1, kind: RequestKind::Pixels, tile: None, scale: 1.0, tag: 0, preview: false });
|
||||
assert!(second.error.is_some(), "and it is one page, not two: page 2 must not exist");
|
||||
|
||||
// Two headers for object 3, the second the one the exact key names: the stand-in follows it.
|
||||
// `(B)` is drawn by the later body, so the page that comes back says which one was read.
|
||||
let twice = "%PDF-1.4\n\
|
||||
1 0 obj << /Type /Catalog /Pages 2 0 R >> endobj\n\
|
||||
2 0 obj << /Type /Pages /Kids [3 0 R] /Count 1 >> endobj\n\
|
||||
3 1 obj << /Type /Page /Parent 2 0 R /MediaBox [0 0 200 100] /Contents 5 0 R >> endobj\n\
|
||||
3 1 obj << /Type /Page /Parent 2 0 R /MediaBox [0 0 300 150] /Contents 5 0 R >> endobj\n\
|
||||
5 0 obj << /Length 0 >> stream\n\nendstream endobj\n\
|
||||
trailer << /Root 1 0 R >>\n\
|
||||
%%EOF\n";
|
||||
let mut r = PageRenderer::new(Arc::new(twice.to_string().into_bytes()), RenderConfig::default());
|
||||
let page = r.render(RenderRequest { page: 0, kind: RequestKind::Pixels, tile: None, scale: 1.0, tag: 0, preview: false });
|
||||
assert!(page.error.is_none(), "the page is found: {:?}", page.error);
|
||||
assert_eq!((page.width, page.height), (300, 150), "`3 0 R` reads the later body, as `3 1` does");
|
||||
}
|
||||
|
||||
/// A file whose cross-reference table has to be rebuilt keeps an object whose header names a
|
||||
/// generation the reference does not.
|
||||
///
|
||||
/// `poppler-85140-0.pdf` is 340 bytes with no table at all, and its one page's header reads
|
||||
/// `3 18446744073709551616 obj` while the page tree points at `3 0 R`. Before #427 the digits
|
||||
/// wrapped, and 2^64 wrapped to exactly 0, so the header read as `3 0 obj` and the file opened by
|
||||
/// accident; once an overflowing integer became a real the object was unreachable and the file
|
||||
/// stopped opening at all, which `cargo xtask check` reports as a regression (#5580).
|
||||
///
|
||||
/// A rebuilt table has no revision history to tell two generations of an object apart -- the scan
|
||||
/// already files objects found in object streams under generation 0 -- so the object number is
|
||||
/// what identifies one. A readable generation that simply is not the one referenced
|
||||
/// (`3 99999 obj`) was lost the same way, and is covered here too.
|
||||
#[cfg_attr(target_arch = "wasm32", wasm_bindgen_test::wasm_bindgen_test)]
|
||||
#[cfg_attr(not(target_arch = "wasm32"), test)]
|
||||
fn a_rebuilt_table_finds_an_object_whose_header_names_another_generation() {
|
||||
for generation in [
|
||||
// The generation the reference names, which always worked.
|
||||
"0",
|
||||
// One that reads as an integer but is not the one referenced.
|
||||
"99999",
|
||||
// And one no generation may be: 2^64, which is what the reported file carries. A
|
||||
// generation number is at most 65,535 (ISO 32000-2 §7.5.4).
|
||||
"18446744073709551616",
|
||||
] {
|
||||
// No table and no `startxref`, so the objects are recovered by scanning the file.
|
||||
let pdf = format!(
|
||||
"%PDF-1.4\n\
|
||||
1 0 obj << /Type /Catalog /Pages 2 0 R >> endobj\n\
|
||||
2 0 obj << /Type /Pages /Kids [3 0 R] /Count 1 >> endobj\n\
|
||||
3 {generation} obj << /Type /Page /Parent 2 0 R /MediaBox [0 0 200 100] >> endobj\n\
|
||||
trailer << /Root 1 0 R >>\n\
|
||||
%%EOF\n"
|
||||
);
|
||||
let mut r = PageRenderer::new(Arc::new(pdf.into_bytes()), RenderConfig::default());
|
||||
let page = r.render(RenderRequest { page: 0, kind: RequestKind::Pixels, tile: None, scale: 1.0, tag: 0, preview: false });
|
||||
assert!(page.error.is_none(), "generation {generation}: the page is found: {:?}", page.error);
|
||||
assert_eq!((page.width, page.height), (200, 100), "generation {generation}: and it is the page's own size");
|
||||
}
|
||||
|
||||
// A stray number before a header (`42 3 0 obj`) is not a header, and must not cost the one
|
||||
// after it: the lenient read leaves the scan where it was when it fails (noted in review).
|
||||
let pdf = "%PDF-1.4\n\
|
||||
1 0 obj << /Type /Catalog /Pages 2 0 R >> endobj\n\
|
||||
2 0 obj << /Type /Pages /Kids [3 0 R] /Count 1 >> endobj\n\
|
||||
42 3 0 obj << /Type /Page /Parent 2 0 R /MediaBox [0 0 200 100] >> endobj\n\
|
||||
trailer << /Root 1 0 R >>\n\
|
||||
%%EOF\n";
|
||||
let mut r = PageRenderer::new(Arc::new(pdf.to_string().into_bytes()), RenderConfig::default());
|
||||
let page = r.render(RenderRequest { page: 0, kind: RequestKind::Pixels, tile: None, scale: 1.0, tag: 0, preview: false });
|
||||
assert!(page.error.is_none(), "the header after a stray number is found: {:?}", page.error);
|
||||
assert_eq!((page.width, page.height), (200, 100));
|
||||
}
|
||||
|
||||
/// #3109 / #3116: clipping-only text (`7 Tr`) installs a clip for subsequent painting
|
||||
/// but draws no pixels itself.
|
||||
#[test]
|
||||
|
||||
@@ -187,9 +187,20 @@ fn convert_dict(dict: &pdfcraft_cos::Dict, depth: usize) -> Result<Dictionary> {
|
||||
if depth > 100 {
|
||||
return Err(Error::RecursionLimit);
|
||||
}
|
||||
dict.iter().map(|(key, value)| Ok((key.clone(), convert(value, depth + 1)?))).collect::<Result<Vec<_>>>().map(|items| items.into_iter().collect())
|
||||
dict.iter()
|
||||
.filter(|(key, _)| key.as_slice() != PRIVATE_DATA)
|
||||
.map(|(key, value)| Ok((key.clone(), convert(value, depth + 1)?)))
|
||||
.collect::<Result<Vec<_>>>()
|
||||
.map(|items| items.into_iter().collect())
|
||||
}
|
||||
|
||||
/// `/PieceInfo`: an application's private data about a page, form or document (ISO 32000-1
|
||||
/// §14.5), left out of what inspection keeps. Nothing here reads it, and every object read is
|
||||
/// kept converted for the inspection's lifetime: InDesign writes kilobytes of it into every page,
|
||||
/// and a 1,412-page book held over a gigabyte of it (#5873). The file and the editing document are
|
||||
/// untouched; this is the read-only view inspection walks.
|
||||
const PRIVATE_DATA: &[u8] = b"PieceInfo";
|
||||
|
||||
fn convert(object: &CosObject, depth: usize) -> Result<Object> {
|
||||
if depth > 100 {
|
||||
return Err(Error::RecursionLimit);
|
||||
|
||||
@@ -14,6 +14,8 @@ craft-ui = { workspace = true }
|
||||
# The menus: native on macOS, an egui bar elsewhere, from one definition (menus.rs).
|
||||
craft-menu = { workspace = true }
|
||||
craft-keymap = { workspace = true }
|
||||
# Interface translations over the embedded craft-i18n catalogs (`build.rs`, `src/i18n.rs`).
|
||||
craft-i18n = { workspace = true }
|
||||
# Quit from the menus asks the window to close, so the unsaved-changes check runs; on macOS a window
|
||||
# close also quits through `terminate:` (the Touch Bar crash, #1136).
|
||||
craft-quit = { workspace = true, features = ["egui"] }
|
||||
|
||||
+84
-1
@@ -1,4 +1,5 @@
|
||||
//! Bake the contributor credits into the binary as static Rust tables. Nothing is read at run time.
|
||||
//! Bake the contributor credits into the binary as static Rust tables, and embed the craft-i18n
|
||||
//! interface catalogs. Nothing is read at run time.
|
||||
//!
|
||||
//! - contributors/contributors.json: commit stats per GitHub username, with a mark for whose people.toml
|
||||
//! entry is verified.
|
||||
@@ -6,6 +7,12 @@
|
||||
//! JSON says the entry was verified (`people_entry`).
|
||||
//!
|
||||
//! A missing or malformed file gives empty tables (or no names) and a warning.
|
||||
//!
|
||||
//! - `CRAFT_I18N_DIR`, a craft-i18n checkout (storytold/craft-i18n, at the SHA in
|
||||
//! `craft-i18n.rev`): `craft_i18n.rs` holds `CRAFT_I18N`, one (locale, shared catalog, PdfCraft
|
||||
//! catalog) entry per locale that has a `pdfcraft.tsv`. Unset, or not a checkout (a warning),
|
||||
//! it is empty and the interface is English only; with `CRAFT_I18N_REQUIRED=1` (CI and releases)
|
||||
//! that is an error instead. Recipe: craft-i18n's `docs/integration.md`.
|
||||
|
||||
use std::fmt::Write as _;
|
||||
|
||||
@@ -23,6 +30,82 @@ fn main() {
|
||||
if let Err(e) = std::fs::write(&out, generate(&json, &people)) {
|
||||
println!("cargo::warning=writing {}: {e}", out.display());
|
||||
}
|
||||
let out = out.with_file_name("craft_i18n.rs");
|
||||
if let Err(e) = std::fs::write(&out, craft_i18n()) {
|
||||
println!("cargo::error=writing {}: {e}", out.display());
|
||||
}
|
||||
}
|
||||
|
||||
/// The catalog this app reads in each locale: `locales/<locale>/pdfcraft.tsv`.
|
||||
const APP_CATALOG: &str = "pdfcraft.tsv";
|
||||
|
||||
/// `CRAFT_I18N` from `CRAFT_I18N_DIR`: the `Embedded` list the craft-i18n crate reads.
|
||||
fn craft_i18n() -> String {
|
||||
println!("cargo::rerun-if-env-changed=CRAFT_I18N_DIR");
|
||||
println!("cargo::rerun-if-env-changed=CRAFT_I18N_REQUIRED");
|
||||
let required = std::env::var("CRAFT_I18N_REQUIRED").is_ok_and(|v| v.trim() == "1");
|
||||
let entries = match std::env::var_os("CRAFT_I18N_DIR").filter(|d| !d.is_empty()) {
|
||||
// Not canonicalized: on Windows that gives `\\?\C:\…`, which `include_str!` can't read.
|
||||
Some(dir) => match locales(&std::path::PathBuf::from(dir).join("locales")) {
|
||||
Ok(entries) => entries,
|
||||
Err(e) => {
|
||||
let level = if required { "error" } else { "warning" };
|
||||
println!("cargo::{level}=CRAFT_I18N_DIR: {e}; the interface is English only");
|
||||
Vec::new()
|
||||
}
|
||||
},
|
||||
None => {
|
||||
if required {
|
||||
println!("cargo::error=CRAFT_I18N_REQUIRED=1 but CRAFT_I18N_DIR is unset: a release must embed the translations");
|
||||
}
|
||||
Vec::new()
|
||||
}
|
||||
};
|
||||
let mut o = String::from("/// (locale, shared catalog, PdfCraft's catalog), one entry per locale; `\"\"` for a missing file.\n");
|
||||
o.push_str("pub static CRAFT_I18N: &craft_i18n::Embedded = &[\n");
|
||||
for (code, shared, app) in entries {
|
||||
// `{:?}` escapes the path (Windows backslashes) as a Rust string literal.
|
||||
let shared = shared.map_or_else(|| "\"\"".to_string(), |p| format!("include_str!({p:?})"));
|
||||
let _ = writeln!(o, " ({code:?}, {shared}, include_str!({app:?})),");
|
||||
}
|
||||
o.push_str("];\n");
|
||||
o
|
||||
}
|
||||
|
||||
/// One embedded locale: its code, its `common.tsv` if it has one, and its PdfCraft catalog.
|
||||
type Locale = (String, Option<std::path::PathBuf>, std::path::PathBuf);
|
||||
|
||||
/// Every locale under `dir` with PdfCraft's catalog, by code. An error when `dir` isn't a
|
||||
/// craft-i18n `locales/` directory.
|
||||
fn locales(dir: &std::path::Path) -> Result<Vec<Locale>, String> {
|
||||
// Build scripts run in the crate's directory and `include_str!` resolves against the
|
||||
// generated file, so a relative path would mean two different places.
|
||||
if !dir.is_absolute() {
|
||||
return Err(format!("{} is not an absolute path", dir.display()));
|
||||
}
|
||||
// Before read_dir, so a checkout that appears later reruns the script.
|
||||
println!("cargo::rerun-if-changed={}", dir.display());
|
||||
let list = std::fs::read_dir(dir).map_err(|e| format!("{} is not a craft-i18n checkout ({e})", dir.display()))?;
|
||||
let mut out = Vec::new();
|
||||
for entry in list.flatten() {
|
||||
let path = entry.path();
|
||||
let Some(code) = path.file_name().and_then(|n| n.to_str()).map(str::to_string) else { continue };
|
||||
let app = path.join(APP_CATALOG);
|
||||
if !app.is_file() {
|
||||
continue;
|
||||
}
|
||||
println!("cargo::rerun-if-changed={}", app.display());
|
||||
let shared = Some(path.join("common.tsv")).filter(|p| p.is_file());
|
||||
if let Some(p) = &shared {
|
||||
println!("cargo::rerun-if-changed={}", p.display());
|
||||
}
|
||||
out.push((code, shared, app));
|
||||
}
|
||||
if out.is_empty() {
|
||||
return Err(format!("{} has no locale with a {APP_CATALOG}", dir.display()));
|
||||
}
|
||||
out.sort();
|
||||
Ok(out)
|
||||
}
|
||||
|
||||
fn read<T>(path: &std::path::Path, fallback: &str, parse: impl Fn(&str) -> Result<T, String>) -> Option<T> {
|
||||
|
||||
@@ -99,6 +99,7 @@ impl PdfCraftApp {
|
||||
#[cfg(target_os = "linux")]
|
||||
desktop_theme_enabled: false,
|
||||
scroll_speed: scroll_speed::ScrollSpeed::default(),
|
||||
invert_middle_drag: false,
|
||||
animation_effects: motion::AnimationEffects::default(),
|
||||
motion: motion::Motion::default(),
|
||||
language: i18n::AUTO.to_string(),
|
||||
@@ -144,6 +145,7 @@ impl PdfCraftApp {
|
||||
#[cfg(all(test, not(target_arch = "wasm32")))]
|
||||
open_prepare_gate: None,
|
||||
pinned: Default::default(),
|
||||
recent_check: Default::default(),
|
||||
pinned_tools: Vec::new(),
|
||||
pin_tool_search: String::new(),
|
||||
toast: None,
|
||||
@@ -453,6 +455,7 @@ impl eframe::App for PdfCraftApp {
|
||||
}
|
||||
self.poll_pending_opens();
|
||||
}
|
||||
self.check_restored_recent();
|
||||
// Chinese wants its own faces before the Japanese ones (one baseline per line).
|
||||
let cjk = theme::CjkPreference::for_language(lang.code());
|
||||
if !self.styled {
|
||||
|
||||
@@ -50,6 +50,9 @@ impl PdfCraftApp {
|
||||
("scroll_speed", _) => {
|
||||
self.scroll_speed = scroll_speed::ScrollSpeed::parse(value).ok_or("scroll_speed must be slow, normal, or fast")?;
|
||||
}
|
||||
("invert_middle_drag", _) => {
|
||||
self.invert_middle_drag = value.parse::<bool>().map_err(|_| "invert_middle_drag must be true or false")?;
|
||||
}
|
||||
("animation_effects", _) => {
|
||||
self.animation_effects = motion::AnimationEffects::parse(value).ok_or("animation_effects must be system, on, or off")?;
|
||||
}
|
||||
|
||||
@@ -332,6 +332,7 @@ impl PdfCraftApp {
|
||||
#[cfg(target_os = "macos")]
|
||||
macos_association::repair(std::path::Path::new(&p));
|
||||
self.recent.retain(|r| r.path != p);
|
||||
self.recent_check.opened(&p);
|
||||
self.recent.insert(0, RecentFile { name: name.to_string(), path: p, pages, size });
|
||||
self.recent.truncate(self.recent_limit);
|
||||
}
|
||||
|
||||
@@ -89,6 +89,7 @@ impl PdfCraftApp {
|
||||
"pinned_folders": self.pinned.folders,
|
||||
"theme": self.theme_preference,
|
||||
"scroll_speed": self.scroll_speed,
|
||||
"invert_middle_drag": self.invert_middle_drag,
|
||||
"animation_effects": self.animation_effects,
|
||||
"default_mode": self.default_mode,
|
||||
"default_layout": canvas::display_token(self.view_defaults.layout, self.view_defaults.continuous),
|
||||
@@ -159,6 +160,9 @@ impl PdfCraftApp {
|
||||
pub fn restore(&mut self, json: &str) {
|
||||
let Ok(v) = serde_json::from_str::<serde_json::Value>(json) else { return };
|
||||
if let Ok(mut bar) = serde_json::from_value::<crate::hotbar::Hotbar>(v["hotbar"].clone()) {
|
||||
if v["hotbar"].get("placed").is_none() {
|
||||
bar.adopt_legacy();
|
||||
}
|
||||
bar.normalize();
|
||||
self.hotbar = bar;
|
||||
}
|
||||
@@ -182,9 +186,9 @@ impl PdfCraftApp {
|
||||
self.organize_zoom = zoom.clamp(*canvas::GRID_ZOOM_RANGE.start(), *canvas::GRID_ZOOM_RANGE.end());
|
||||
}
|
||||
if let Ok(r) = serde_json::from_value::<Vec<RecentFile>>(v["recent"].clone()) {
|
||||
// Only keep entries whose files still exist.
|
||||
#[cfg(not(target_arch = "wasm32"))]
|
||||
let r: Vec<RecentFile> = r.into_iter().filter(|f| std::path::Path::new(&f.path).exists()).collect();
|
||||
// Entries whose files are gone leave once the window is up: asking here could block
|
||||
// startup on a mount that has stopped answering (#5682).
|
||||
self.recent_check.restored(r.iter().map(|f| f.path.clone()).collect());
|
||||
self.recent = r;
|
||||
}
|
||||
// Nonsense keeps the limit it had; settings from before the limit have none.
|
||||
@@ -237,6 +241,9 @@ impl PdfCraftApp {
|
||||
if let Ok(speed) = serde_json::from_value::<scroll_speed::ScrollSpeed>(v["scroll_speed"].clone()) {
|
||||
self.scroll_speed = speed;
|
||||
}
|
||||
if let Some(invert) = v["invert_middle_drag"].as_bool() {
|
||||
self.invert_middle_drag = invert;
|
||||
}
|
||||
if let Ok(effects) = serde_json::from_value::<motion::AnimationEffects>(v["animation_effects"].clone()) {
|
||||
self.animation_effects = effects;
|
||||
}
|
||||
|
||||
Loaded 100 of 218 files, more files were not shown because too many files have changed in this diff.
Show more
Reference in new issue
Block a user