mirror of
https://github.com/storytold/pdfcraft.git
synced 2026-11-13 06:04:59 +00:00
Merge upstream/main into feat/recent-reveal-5452
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
This commit is contained in:
vangel76
@@ -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
|
||||
|
||||
@@ -42,3 +42,4 @@ jobs:
|
||||
AZURE_SIGNING_ENDPOINT: ${{ secrets.AZURE_SIGNING_ENDPOINT }}
|
||||
AZURE_SIGNING_ACCOUNT: ${{ secrets.AZURE_SIGNING_ACCOUNT }}
|
||||
AZURE_CERT_PROFILE: ${{ secrets.AZURE_CERT_PROFILE }}
|
||||
LINUX_SIGNING_KEY: ${{ secrets.LINUX_SIGNING_KEY }}
|
||||
|
||||
@@ -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.
|
||||
|
||||
+5
-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 (256)
|
||||
|
||||
| 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 |
|
||||
@@ -231,6 +203,7 @@ Every asset PdfCraft includes, bundles or uses to build its published material,
|
||||
| `vendor/hayro-interpret/assets/FoxitSymbol.pfb` | FoxitSymbol (standard-14 substitute font) | Foxit Software Inc. / PDFium Authors | BSD-3-Clause | https://pdfium.googlesource.com/pdfium (via hayro-interpret 0.7.0 assets/) | Renders non-embedded standard-14 fonts (vendored hayro-interpret) |
|
||||
| `vendor/hayro-interpret/assets/CGATS001Compat-v2-micro.icc` | CGATS001Compat v2 micro ICC profile | Clinton Ingram (saucecontrol/Compact-ICC-Profiles) | CC0-1.0 | https://github.com/saucecontrol/Compact-ICC-Profiles | Default CMYK colour conversion (vendored hayro-interpret) |
|
||||
| `crates/fonts/src/std14_metrics.rs` | Standard-14 font advance widths and encodings (as Rust tables) | Adobe (Core14 AFM metrics, PDF specification encodings); tables generated by the PdfCraft contributors | MIT OR Apache-2.0 | ISO 32000-2 Annex D and the Adobe Core14 AFM metrics. Generated by joining the published WinAnsi, Symbol and ZapfDingbats encodings (code to glyph name) with the per-glyph advance widths, then spot-checked against the specification by hand in the tests of crates/fonts/src/std14.rs. Data only: the code that reads these tables lives in std14.rs, so that ordinary edits do not churn this file's hash. | Advance widths for the fourteen standard fonts, which a PDF may name without embedding. Non-visual data, not a typeface: the item AGENTS.md 1.1 permits, held first-party so generated appearance streams and the renderer agree. |
|
||||
| `crates/prc/src/acof/table.rs` | PRC Double prefix-code table (as a Rust table) | Kristof Ralovich (prc-rs); the code table itself is defined by the PRC format (ISO 14739-1, working draft clause 11.17.2) | MIT | Rows taken from prc-rs src/double.rs at commit 287b671bb5b31b05efb5ec1b98f7c359b9e4dd7d (https://github.com/ralovich/prc-rs), mechanically reformatted into (code length, code, entry) tuples; checked to be a complete prefix code by the tests in crates/prc/src/acof.rs. Data only: the code that reads the table lives in acof.rs. The MIT notice is kept in the file header. | Decodes every PRC Double (coordinates, transforms, colours) in 3D annotations' PRC streams. Non-visual data. |
|
||||
| `vendor/hayro-cmap/assets/cmaps.brotli` | Adobe CMap resources (predefined CJK CMaps) | Adobe | BSD-3-Clause | https://github.com/adobe-type-tools/cmap-resources (via hayro-cmap 0.1.0 assets/) | Character-code mapping tables required to read CJK PDFs. Non-visual data, allowed by AGENTS.md §1.1 |
|
||||
| `docs/brand/artcraft-logo-white.png` | ArtCraft brand: artcraft-logo-white | ArtCraft Team | LicenseRef-Storyteller-Trademark | ArtCraft Team brand assets (provided by the project owner, 2026-10-01; identical copies in storytold/photocraft) | ArtCraft branding next to the community links (About dialog, Help menu, home screen) and in docs. ArtCraft Team trademark, not open source; may be used only unmodified within PdfCraft; forks and modified versions must remove it. |
|
||||
| `docs/brand/artcraft-logo-white.svg` | ArtCraft brand: artcraft-logo-white | ArtCraft Team | LicenseRef-Storyteller-Trademark | ArtCraft Team brand assets (provided by the project owner, 2026-10-01; identical copies in storytold/photocraft) | ArtCraft branding next to the community links (About dialog, Help menu, home screen) and in docs. ArtCraft Team trademark, not open source; may be used only unmodified within PdfCraft; forks and modified versions must remove it. |
|
||||
@@ -286,17 +259,11 @@ 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 +305,11 @@ 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 |
|
||||
|
||||
+23
-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\""
|
||||
@@ -2437,6 +2156,17 @@ adobe_data = true
|
||||
usage = "Advance widths for the fourteen standard fonts, which a PDF may name without embedding. Non-visual data, not a typeface: the item AGENTS.md 1.1 permits, held first-party so generated appearance streams and the renderer agree."
|
||||
sha256 = "f225e0b044875b8fa6375b6b5ad935f0d99fcc1ad03ecf9f0baae2cedbfca4d2"
|
||||
|
||||
[[asset]]
|
||||
path = "crates/prc/src/acof/table.rs"
|
||||
title = "PRC Double prefix-code table (as a Rust table)"
|
||||
author = "Kristof Ralovich (prc-rs); the code table itself is defined by the PRC format (ISO 14739-1, working draft clause 11.17.2)"
|
||||
source = "Rows taken from prc-rs src/double.rs at commit 287b671bb5b31b05efb5ec1b98f7c359b9e4dd7d (https://github.com/ralovich/prc-rs), mechanically reformatted into (code length, code, entry) tuples; checked to be a complete prefix code by the tests in crates/prc/src/acof.rs. Data only: the code that reads the table lives in acof.rs. The MIT notice is kept in the file header."
|
||||
licence = "MIT"
|
||||
licence_file = "licenses/prc-rs-LICENSE.txt"
|
||||
kind = "data"
|
||||
usage = "Decodes every PRC Double (coordinates, transforms, colours) in 3D annotations' PRC streams. Non-visual data."
|
||||
sha256 = "8e705c5cde6a3ef778e8aca69759e38845b228b3f7f12949e587b19855d2114c"
|
||||
|
||||
[[bundled]]
|
||||
crate = "epaint_default_fonts"
|
||||
version = "0.37.0"
|
||||
@@ -3381,6 +3111,17 @@ 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 +3155,6 @@ 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 +3167,6 @@ 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 +3211,3 @@ 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"
|
||||
|
||||
@@ -23,7 +23,7 @@ PdfCraft is a clean-room, open-source, Rust-native PDF application targeting Ado
|
||||
- **Layering.** Nothing below L7 depends on egui/winit/eframe/rfd (`plan/architecture.md` §3). `cos`/`filters`/`crypt`/`arlington` stay standalone.
|
||||
- **Page input.** Page modules read `PagePointer` (`crates/ui-egui/src/page_pointer.rs`), never egui's raw pointer state (`hover_pos`, `interact_pos`, `latest_pos`, `press_origin`, button reads); `page_pointer::tests::page_modules_read_the_pointer_only_through_page_pointer` enforces it.
|
||||
- **Page cursor.** Page modules claim the cursor for what is under the pointer (`view.cursor.claim(Layer::…, icon)`, `crates/ui-egui/src/canvas/page_cursor.rs`), never set it (`set_cursor_icon`, `cursor_icon =`, `on_hover_cursor`); `document_area` sets it once, from the claim on the highest layer the active tool reaches. `page_pointer::tests::page_modules_claim_the_cursor_and_never_set_it` enforces it.
|
||||
- **Page presses.** A page module decides what of its own is under a point in one hit test, which returns a `Hit` (owner, layer, cursor, tip; `crates/ui-egui/src/canvas/page_router.rs`) and gives its cursor, its tip and its press. It acts on a press only when the router says the press is its own (`view.router.owner(page)`), never by testing the press point again or by asking another module whether it wants it. Escape cancels any press the pages hold (`cancel_on_escape`), and that press is ignored until the button is up. `page_modules_take_presses_from_the_router_without_repeating_hit_tests` guards the centralized hit calls and captured-owner handlers; runtime routing tests cover gesture behavior.
|
||||
- **Page presses.** A page module decides what of its own is under a point in one hit test, which returns a `Hit` (owner, layer, cursor, tip; `crates/ui-egui/src/canvas/page_router.rs`) and gives its cursor, its tip and its press. It acts on a press only when the press is its own or, for the active tool, nobody's: the page view tells it which (`PagePress`: its own, nobody's, or another page's), and it never tests the press point again or asks another module whether it wants it. Escape cancels any press the pages hold (`cancel_on_escape`), and that press is ignored until the button is up. `page_pointer::tests::page_modules_act_on_a_press_only_through_the_router` enforces it.
|
||||
- **Fidelity.** The PDF object graph is the model. Preserve unknown data. Saves are incremental unless a full rewrite is required. Never silently drop or repair data without recording it.
|
||||
- **Never panic.** Every PDF, script, MCP call, settings file and keystroke is untrusted input, and none of it may crash the app or lose the user's work. This outranks feature work. Return `Result` (the crate's error enum) and propagate with `?`, or fall back leniently and record it. In non-test code:
|
||||
- No `unwrap`/`expect`/`panic!`/`unreachable!`/`todo!` unless it is provably infallible, with a comment saying why.
|
||||
|
||||
Generated
+57
-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",
|
||||
@@ -4277,6 +4277,8 @@ dependencies = [
|
||||
"pdfcraft-model",
|
||||
"pdfcraft-organize",
|
||||
"pdfcraft-platform",
|
||||
"pdfcraft-prc",
|
||||
"pdfcraft-prc-render",
|
||||
"pdfcraft-render",
|
||||
"pdfcraft-xfa",
|
||||
"png 0.18.1",
|
||||
@@ -4288,7 +4290,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "pdfcraft-cli"
|
||||
version = "0.17.0"
|
||||
version = "0.18.1"
|
||||
dependencies = [
|
||||
"base64 0.23.1",
|
||||
"pdfcraft-audit",
|
||||
@@ -4306,11 +4308,11 @@ 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 +4320,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "pdfcraft-cos"
|
||||
version = "0.17.0"
|
||||
version = "0.18.1"
|
||||
dependencies = [
|
||||
"chrono",
|
||||
"hayro-syntax",
|
||||
@@ -4333,7 +4335,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "pdfcraft-create"
|
||||
version = "0.17.0"
|
||||
version = "0.18.1"
|
||||
dependencies = [
|
||||
"encoding_rs",
|
||||
"hayro-ccitt",
|
||||
@@ -4352,7 +4354,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "pdfcraft-crypt"
|
||||
version = "0.17.0"
|
||||
version = "0.18.1"
|
||||
dependencies = [
|
||||
"aes",
|
||||
"md-5",
|
||||
@@ -4364,7 +4366,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "pdfcraft-edit"
|
||||
version = "0.17.0"
|
||||
version = "0.18.1"
|
||||
dependencies = [
|
||||
"hayro-syntax",
|
||||
"kurbo 0.13.1",
|
||||
@@ -4382,7 +4384,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "pdfcraft-engine"
|
||||
version = "0.17.0"
|
||||
version = "0.18.1"
|
||||
dependencies = [
|
||||
"chrono",
|
||||
"craft-docpath",
|
||||
@@ -4426,14 +4428,14 @@ 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 +4448,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "pdfcraft-fonts"
|
||||
version = "0.17.0"
|
||||
version = "0.18.1"
|
||||
dependencies = [
|
||||
"harfrust",
|
||||
"pdfcraft-cos",
|
||||
@@ -4456,7 +4458,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "pdfcraft-forms"
|
||||
version = "0.17.0"
|
||||
version = "0.18.1"
|
||||
dependencies = [
|
||||
"hayro-syntax",
|
||||
"pdfcraft-content",
|
||||
@@ -4469,11 +4471,11 @@ 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 +4483,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "pdfcraft-measure"
|
||||
version = "0.17.0"
|
||||
version = "0.18.1"
|
||||
dependencies = [
|
||||
"pdfcraft-annot",
|
||||
"pdfcraft-content",
|
||||
@@ -4494,14 +4496,14 @@ 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 +4514,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "pdfcraft-optimize"
|
||||
version = "0.17.0"
|
||||
version = "0.18.1"
|
||||
dependencies = [
|
||||
"image",
|
||||
"pdfcraft-annot",
|
||||
@@ -4528,11 +4530,11 @@ 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 +4545,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "pdfcraft-platform"
|
||||
version = "0.17.0"
|
||||
version = "0.18.1"
|
||||
dependencies = [
|
||||
"async-channel",
|
||||
"futures-lite",
|
||||
@@ -4551,9 +4553,27 @@ dependencies = [
|
||||
"zbus",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "pdfcraft-prc"
|
||||
version = "0.18.1"
|
||||
dependencies = [
|
||||
"flate2",
|
||||
"proptest",
|
||||
"thiserror 2.0.21",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "pdfcraft-prc-render"
|
||||
version = "0.18.1"
|
||||
dependencies = [
|
||||
"flate2",
|
||||
"pdfcraft-prc",
|
||||
"thiserror 2.0.21",
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "pdfcraft-preflight"
|
||||
version = "0.17.0"
|
||||
version = "0.18.1"
|
||||
dependencies = [
|
||||
"flate2",
|
||||
"pdfcraft-content",
|
||||
@@ -4564,7 +4584,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "pdfcraft-print"
|
||||
version = "0.17.0"
|
||||
version = "0.18.1"
|
||||
dependencies = [
|
||||
"craft-print",
|
||||
"pdfcraft-content",
|
||||
@@ -4576,7 +4596,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "pdfcraft-redact"
|
||||
version = "0.17.0"
|
||||
version = "0.18.1"
|
||||
dependencies = [
|
||||
"pdfcraft-annot",
|
||||
"pdfcraft-content",
|
||||
@@ -4593,7 +4613,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "pdfcraft-render"
|
||||
version = "0.17.0"
|
||||
version = "0.18.1"
|
||||
dependencies = [
|
||||
"bytemuck",
|
||||
"flate2",
|
||||
@@ -4612,7 +4632,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "pdfcraft-sign"
|
||||
version = "0.17.0"
|
||||
version = "0.18.1"
|
||||
dependencies = [
|
||||
"aes",
|
||||
"aws-lc-rs",
|
||||
@@ -4648,17 +4668,18 @@ 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 +4727,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "pdfcraft-web"
|
||||
version = "0.17.0"
|
||||
version = "0.18.1"
|
||||
dependencies = [
|
||||
"eframe",
|
||||
"egui",
|
||||
@@ -4718,7 +4739,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "pdfcraft-xfa"
|
||||
version = "0.17.0"
|
||||
version = "0.18.1"
|
||||
dependencies = [
|
||||
"base64 0.23.1",
|
||||
"image",
|
||||
@@ -4732,7 +4753,7 @@ dependencies = [
|
||||
|
||||
[[package]]
|
||||
name = "pdfcraft-xfdf"
|
||||
version = "0.17.0"
|
||||
version = "0.18.1"
|
||||
dependencies = [
|
||||
"pdfcraft-annot",
|
||||
"pdfcraft-cos",
|
||||
|
||||
+40
-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 +30,41 @@ 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 }
|
||||
pdfcraft-prc = { path = "crates/prc", version = "0.18.1" }
|
||||
pdfcraft-prc-render = { path = "crates/prc-render", version = "0.18.1" }
|
||||
|
||||
# pdf
|
||||
hayro = "0.7.1"
|
||||
|
||||
@@ -88,6 +88,13 @@ destination = "licenses/egui-emoji-icon-font-mit-license.txt"
|
||||
sha256 = "b9d2c1d909aa149996fd4c91dcb92b2362a04431640c1d200959da94caf8cde1"
|
||||
origin = "https://raw.githubusercontent.com/emilk/egui/0.36.2/crates/epaint_default_fonts/fonts/emoji-icon-font-mit-license.txt"
|
||||
|
||||
[[document]]
|
||||
source = "licenses/prc-rs-LICENSE.txt"
|
||||
licences = ["MIT"]
|
||||
destination = "licenses/prc-rs-LICENSE.txt"
|
||||
sha256 = "ddb846513d92153d8fa16b18ed3e7c86953a582f0d2f49f02b29f1bd569dac58"
|
||||
origin = "https://raw.githubusercontent.com/ralovich/prc-rs/287b671bb5b31b05efb5ec1b98f7c359b9e4dd7d/LICENSE"
|
||||
|
||||
[[document]]
|
||||
source = "vendor/hayro-interpret/LICENSE-APACHE"
|
||||
licences = ["Apache-2.0"]
|
||||
|
||||
+19
-1
@@ -1,6 +1,10 @@
|
||||
# PdfCraft roadmap
|
||||
|
||||
> **Last reviewed:** 2026-11-01 | **Last updated:** 2026-11-01 | **Change:** minor (M3, #5452: native Recent rows gain Reveal in Finder / File Explorer; estimates unchanged); previously 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:** 2026-11-05 | **Last updated:** 2026-11-05 | **Change:** minor (M3, #5452: native Recent rows gain Reveal in Finder / File Explorer; estimates unchanged))
|
||||
|
||||
> **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)
|
||||
|
||||
@@ -220,6 +224,18 @@ Ranked; detail and the full milestone table in [docs/roadmap.md](docs/roadmap.md
|
||||
|
||||
## Progress log
|
||||
|
||||
- **2026-11-03 (M11, shared JBIG2 dictionary):** With Monochrome Images set to JBIG2, Optimize has up to 16 JBIG2 images share one symbol dictionary (`/JBIG2Globals`), the letters found on more than one page stored once, when that is smaller (`pdfcraft_filters::encode_jbig2_shared`). Eight pages of 10 pt text rendered at 300 dpi take 41% less in Helvetica and 42% in Times than coded alone, 10% in Courier; groups of 16 save 45%, of 32 only 47%. Only images redaction can store again without the dictionary share one (image masks and DeviceGray named directly, at most 64 Mi pixels), and redacting one stores the rest of its group so, which the group bounds to 15.
|
||||
|
||||
- **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 (M12, #1297):** `model_add` embeds a U3D or PRC file, recognised by its header, as a 3D annotation with a chosen activation and a poster (an image or PDF page fitted in the box, or a labelled frame); an older file's catalog `/Version` is raised to what the model needs. Views, a rendered poster and a UI command are later steps. Estimates unchanged.
|
||||
|
||||
- **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.
|
||||
|
||||
- **2026-10-31 (M3, #5452):** Native Home Recent rows offer Reveal in Finder / File Explorer from their context menu. They reuse the tab action’s platform dispatch and missing-file notification without opening the PDF or changing Recent. Browser behavior and milestone estimates unchanged.
|
||||
- **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.
|
||||
|
||||
@@ -747,6 +763,8 @@ 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. |
|
||||
|
||||
@@ -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.
|
||||
|
||||
@@ -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
|
||||
|
||||
@@ -278,7 +278,7 @@ fn ext_gstate(opacity: f64, multiply: bool) -> Option<Dict> {
|
||||
Some(res)
|
||||
}
|
||||
|
||||
fn form(bbox: [f64; 4], content: &[u8], resources: Dict) -> Stream {
|
||||
pub(crate) fn form(bbox: [f64; 4], content: &[u8], resources: Dict) -> Stream {
|
||||
let mut d = Dict::new();
|
||||
d.set(b"Type".to_vec(), Object::name("XObject"));
|
||||
d.set(b"Subtype".to_vec(), Object::name("Form"));
|
||||
@@ -288,6 +288,18 @@ fn form(bbox: [f64; 4], content: &[u8], resources: Dict) -> Stream {
|
||||
Stream::flate(d, content)
|
||||
}
|
||||
|
||||
/// The `cm` that draws a picture into `at`: an image (its unit square) or a form XObject whose
|
||||
/// `/Matrix` maps it to `size` points (`None`, or a side that is not positive, draws nothing).
|
||||
pub(crate) fn picture_place(at: [f64; 4], image: bool, size: Option<(f64, f64)>) -> Option<String> {
|
||||
let [x0, y0, x1, y1] = at;
|
||||
let (w, h) = (x1 - x0, y1 - y0);
|
||||
if image {
|
||||
return Some(format!("{} 0 0 {} {} {} cm", n(w), n(h), n(x0), n(y0)));
|
||||
}
|
||||
let (sw, sh) = size.filter(|(sw, sh)| *sw > 0.0 && *sh > 0.0)?;
|
||||
Some(format!("{} 0 0 {} {} {} cm", n(w / sw), n(h / sh), n(x0), n(y0)))
|
||||
}
|
||||
|
||||
/// The page `/Rotate` an image signature's picture is turned back by (`/PCPictureRotate`, written
|
||||
/// when the signature is added to a turned page): 0, 90, 180 or 270.
|
||||
pub(crate) fn picture_turn(d: &Dict) -> i64 {
|
||||
@@ -325,7 +337,7 @@ pub fn undrawable_text(d: &Dict) -> Option<(&'static str, char)> {
|
||||
}
|
||||
|
||||
/// `/Font` resources naming `/Helv`: standard Helvetica with WinAnsiEncoding.
|
||||
fn helvetica_resource() -> Object {
|
||||
pub(crate) fn helvetica_resource() -> Object {
|
||||
let mut font = Dict::new();
|
||||
font.set(b"Type".to_vec(), Object::name("Font"));
|
||||
font.set(b"Subtype".to_vec(), Object::name("Type1"));
|
||||
@@ -786,15 +798,12 @@ fn draw_stamp(context: &AppearanceContext<'_>, mut drawing: AppearanceDrawing) -
|
||||
// the standard counter-rotation as its form `/Matrix`: viewers fit the turned
|
||||
// bounding box to `/Rect` (ISO 32000-2 §12.5.5), so it reads upright as displayed.
|
||||
if let Some(pic) = d.get(b"PCPicture").and_then(Object::as_ref) {
|
||||
let [x0, y0, x1, y1] = rect;
|
||||
let (w, h) = (x1 - x0, y1 - y0);
|
||||
let image = matches!(d.get(b"PCPictureImage"), Some(Object::Bool(true)));
|
||||
let place = if image {
|
||||
format!("{} 0 0 {} {} {} cm", n(w), n(h), n(x0), n(y0))
|
||||
} else {
|
||||
let size = nums(d, b"PCPictureSize").filter(|s| s.len() == 2 && s[0] > 0.0 && s[1] > 0.0)?;
|
||||
format!("{} 0 0 {} {} {} cm", n(w / size[0]), n(h / size[1]), n(x0), n(y0))
|
||||
};
|
||||
let size = nums(d, b"PCPictureSize").and_then(|s| match s.as_slice() {
|
||||
[w, h] if *w > 0.0 && *h > 0.0 => Some((*w, *h)),
|
||||
_ => None,
|
||||
});
|
||||
let place = picture_place(rect, image, size)?;
|
||||
c.push_str(&format!("q {place} /Pic Do Q\n"));
|
||||
let mut xo = Dict::new();
|
||||
xo.set(b"Pic".to_vec(), Object::Ref(pic));
|
||||
|
||||
@@ -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
|
||||
|
||||
@@ -22,7 +22,9 @@ mod create;
|
||||
mod draw;
|
||||
mod info;
|
||||
mod lookup;
|
||||
mod model3d;
|
||||
mod modify;
|
||||
mod threed;
|
||||
mod types;
|
||||
|
||||
#[cfg(test)]
|
||||
@@ -36,11 +38,13 @@ use lookup::{annots, page_ref};
|
||||
pub use lookup::{
|
||||
has_visible_fill_sign, is_fill_sign, isolate_annotation, isolate_annotations, page_refs, picture_rotation, set_annots, signature_image,
|
||||
};
|
||||
pub use model3d::{Model3d, Model3dKind, model_3d, model_3d_annotations};
|
||||
pub(crate) use modify::n;
|
||||
pub use modify::{
|
||||
add_reply, add_text_replacement, deletable, delete_annotation, erase_ink, fillable, goes_with, lift_annotation, move_annotation, set_contents,
|
||||
set_fill, set_font_size, set_locked, set_marked, set_points, set_rect, set_review_state, set_style, with_replies_and_popups,
|
||||
};
|
||||
pub use threed::{Activation as Activation3d, MAX_MODEL_BYTES, ModelFormat, NewModel3d, PosterPicture, add_3d_model, check_model};
|
||||
pub use types::{
|
||||
AttachIcon, FillMark, LineEnding, Markup, Meta, NOTE_SIZE, NewAnnotation, NoteIcon, OverlayFont, OverlayLook, ReviewState, Rgb, Shape,
|
||||
StampGroup, StampKind, Style, StyleChange, TextReplacement, rect_quad,
|
||||
@@ -70,6 +74,12 @@ pub enum AnnotError {
|
||||
/// with a font that has those characters. The message names the character.
|
||||
#[error("{0}")]
|
||||
Undrawable(String),
|
||||
/// A 3D model file that is neither U3D (starts with `U3D` and a zero byte) nor PRC (starts `PRC`).
|
||||
#[error("not a 3D model: the file must be U3D (ECMA-363) or PRC (ISO 14739-1)")]
|
||||
NotAModel,
|
||||
/// A 3D model larger than `MAX_MODEL_BYTES`.
|
||||
#[error("the 3D model is {size} bytes; the largest accepted is {max}")]
|
||||
ModelTooLarge { size: usize, max: usize },
|
||||
#[error("{0}")]
|
||||
Cos(#[from] pdfcraft_cos::CosError),
|
||||
}
|
||||
|
||||
@@ -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 {
|
||||
|
||||
@@ -0,0 +1,77 @@
|
||||
//! Reading the model a 3D annotation shows (ISO 32000-2 §13.6.3 and §13.6.4): its `/3DD` is a
|
||||
//! 3D stream, or a 3D reference dictionary naming the stream another annotation shares.
|
||||
|
||||
use super::lookup::{annots, page_ref};
|
||||
use super::threed::MAX_MODEL_BYTES;
|
||||
use super::{AnnotError, Dict, Document, Object};
|
||||
|
||||
/// The format of a 3D stream, from its `/Subtype`.
|
||||
#[derive(Debug, Clone, Copy, PartialEq, Eq)]
|
||||
pub enum Model3dKind {
|
||||
/// Product Representation Compact (ISO 14739-1).
|
||||
Prc,
|
||||
/// Universal 3D (ECMA-363).
|
||||
U3d,
|
||||
}
|
||||
|
||||
/// A 3D annotation's model: its format and the decoded stream.
|
||||
#[derive(Debug, Clone, PartialEq)]
|
||||
pub struct Model3d {
|
||||
pub kind: Model3dKind,
|
||||
pub data: Vec<u8>,
|
||||
}
|
||||
|
||||
/// The `/Annots` positions of the 3D annotations on 0-based `page`, in order.
|
||||
///
|
||||
/// # Errors
|
||||
/// [`AnnotError::NoPageTree`] or [`AnnotError::NoSuchPage`].
|
||||
pub fn model_3d_annotations(doc: &Document, page: usize) -> Result<Vec<usize>, AnnotError> {
|
||||
let list = annots(doc, page_ref(doc, page)?);
|
||||
Ok(list.iter().enumerate().filter(|(_, a)| doc.dict(a).is_some_and(|d| d.name(b"Subtype") == Some(b"3D"))).map(|(i, _)| i).collect())
|
||||
}
|
||||
|
||||
/// The model of the 3D annotation at `/Annots` position `index` on 0-based `page`, decoded.
|
||||
///
|
||||
/// # Errors
|
||||
/// [`AnnotError::NoSuchAnnotation`] when there is no annotation there; [`AnnotError::Invalid`]
|
||||
/// when it is not a 3D annotation, has no readable 3D stream, names a format other than PRC or
|
||||
/// U3D, or decodes past [`MAX_MODEL_BYTES`].
|
||||
pub fn model_3d(doc: &Document, page: usize, index: usize) -> Result<Model3d, AnnotError> {
|
||||
let list = annots(doc, page_ref(doc, page)?);
|
||||
let entry = list.get(index).ok_or(AnnotError::NoSuchAnnotation { page, index })?;
|
||||
let annot = doc.dict(entry).ok_or(AnnotError::NoSuchAnnotation { page, index })?;
|
||||
let at = || format!("annotation {} on page {}", index.saturating_add(1), page.saturating_add(1));
|
||||
if annot.name(b"Subtype") != Some(b"3D") {
|
||||
return Err(AnnotError::Invalid(format!("{} is not a 3D annotation", at())));
|
||||
}
|
||||
let stream = stream_of(doc, &annot).ok_or_else(|| AnnotError::Invalid(format!("{} has no 3D stream", at())))?;
|
||||
let Object::Stream(s) = stream.as_ref() else {
|
||||
return Err(AnnotError::Invalid(format!("{} has no 3D stream", at())));
|
||||
};
|
||||
let kind = match s.dict.name(b"Subtype") {
|
||||
Some(b"PRC") => Model3dKind::Prc,
|
||||
Some(b"U3D") => Model3dKind::U3d,
|
||||
other => {
|
||||
let name = other.map_or_else(|| "none".to_owned(), |n| String::from_utf8_lossy(n).into_owned());
|
||||
return Err(AnnotError::Invalid(format!("{}'s 3D stream is of an unknown format ({name})", at())));
|
||||
}
|
||||
};
|
||||
let data = doc
|
||||
.with_direct_parms(s)
|
||||
.decoded_within(MAX_MODEL_BYTES)
|
||||
.map_err(|e| AnnotError::Invalid(format!("{}'s 3D stream could not be decoded: {e}", at())))?;
|
||||
Ok(Model3d { kind, data })
|
||||
}
|
||||
|
||||
/// What an annotation's `/3DD` names: the 3D stream itself, or the `/3D` entry of a 3D reference
|
||||
/// dictionary. A reference is followed once; the caller refuses anything that is not a stream.
|
||||
fn stream_of(doc: &Document, annot: &Dict) -> Option<std::sync::Arc<Object>> {
|
||||
let obj = doc.resolve(annot.get(b"3DD")?);
|
||||
match obj.as_ref() {
|
||||
Object::Dict(d) if d.name(b"Type") == Some(b"3DRef") => Some(doc.resolve(d.get(b"3D")?)),
|
||||
_ => Some(obj),
|
||||
}
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests;
|
||||
@@ -0,0 +1,88 @@
|
||||
use std::sync::Arc;
|
||||
|
||||
use super::*;
|
||||
|
||||
/// A one-page document whose page has `annots` as its `/Annots`, plus `extra` objects from 4 on.
|
||||
fn doc(annots: &str, extra: &[Vec<u8>]) -> Document {
|
||||
let mut objs: Vec<Vec<u8>> = vec![
|
||||
b"<< /Type /Catalog /Pages 2 0 R >>".to_vec(),
|
||||
b"<< /Type /Pages /Kids [3 0 R] /Count 1 /MediaBox [0 0 612 792] >>".to_vec(),
|
||||
format!("<< /Type /Page /Parent 2 0 R /Annots {annots} >>").into_bytes(),
|
||||
];
|
||||
objs.extend(extra.iter().cloned());
|
||||
let mut out = b"%PDF-1.7\n".to_vec();
|
||||
let mut offsets = Vec::new();
|
||||
for (i, o) in objs.iter().enumerate() {
|
||||
offsets.push(out.len());
|
||||
out.extend_from_slice(format!("{} 0 obj\n", i + 1).as_bytes());
|
||||
out.extend_from_slice(o);
|
||||
out.extend_from_slice(b"\nendobj\n");
|
||||
}
|
||||
let xref = out.len();
|
||||
out.extend_from_slice(format!("xref\n0 {}\n0000000000 65535 f \n", objs.len() + 1).as_bytes());
|
||||
for o in offsets {
|
||||
out.extend_from_slice(format!("{o:010} 00000 n \n").as_bytes());
|
||||
}
|
||||
out.extend_from_slice(format!("trailer\n<< /Size {} /Root 1 0 R >>\nstartxref\n{xref}\n%%EOF\n", objs.len() + 1).as_bytes());
|
||||
Document::open(Arc::new(out)).expect("opens")
|
||||
}
|
||||
|
||||
fn stream(dict: &str, body: &[u8]) -> Vec<u8> {
|
||||
let mut s = format!("<< {dict} /Length {} >>\nstream\n", body.len()).into_bytes();
|
||||
s.extend_from_slice(body);
|
||||
s.extend_from_slice(b"\nendstream");
|
||||
s
|
||||
}
|
||||
|
||||
fn annot(dd: &str) -> Vec<u8> {
|
||||
format!("<< /Type /Annot /Subtype /3D /Rect [0 0 100 100] /3DD {dd} >>").into_bytes()
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn a_plain_3d_stream_is_read_through_its_filters() {
|
||||
let d = doc("[4 0 R]", &[annot("5 0 R"), stream("/Type /3D /Subtype /PRC /Filter /ASCIIHexDecode", b"505243>")]);
|
||||
assert_eq!(model_3d(&d, 0, 0), Ok(Model3d { kind: Model3dKind::Prc, data: b"PRC".to_vec() }));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn a_3dref_leads_to_the_stream_it_names() {
|
||||
let d = doc("[4 0 R]", &[annot("<< /Type /3DRef /3D 5 0 R >>"), stream("/Type /3D /Subtype /PRC", b"PRC")]);
|
||||
assert_eq!(model_3d(&d, 0, 0).map(|m| m.data), Ok(b"PRC".to_vec()));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn a_u3d_stream_is_read_and_says_so() {
|
||||
let d = doc("[4 0 R]", &[annot("5 0 R"), stream("/Type /3D /Subtype /U3D", b"U3D")]);
|
||||
assert_eq!(model_3d(&d, 0, 0).map(|m| m.kind), Ok(Model3dKind::U3d));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn a_3d_annotation_without_a_stream_is_invalid() {
|
||||
let d = doc("[<< /Type /Annot /Subtype /3D /Rect [0 0 1 1] >>]", &[]);
|
||||
assert!(matches!(model_3d(&d, 0, 0), Err(AnnotError::Invalid(m)) if m.contains("no 3D stream")));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn an_unknown_format_is_invalid() {
|
||||
let d = doc("[4 0 R]", &[annot("5 0 R"), stream("/Type /3D /Subtype /STL", b"x")]);
|
||||
assert!(matches!(model_3d(&d, 0, 0), Err(AnnotError::Invalid(m)) if m.contains("unknown format (STL)")));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn a_3dref_is_followed_once_and_only_to_a_stream() {
|
||||
// A reference naming another reference, or one that names itself, is damage: no stream.
|
||||
let d = doc("[4 0 R]", &[annot("5 0 R"), b"<< /Type /3DRef /3D 6 0 R >>".to_vec(), b"<< /Type /3DRef /3D 5 0 R >>".to_vec()]);
|
||||
assert!(matches!(model_3d(&d, 0, 0), Err(AnnotError::Invalid(m)) if m.contains("no 3D stream")));
|
||||
// The stream is under `/3D`; a `/3DD` inside the reference is not the standard's key.
|
||||
let d = doc("[4 0 R]", &[annot("<< /Type /3DRef /3DD 5 0 R >>"), stream("/Type /3D /Subtype /PRC", b"PRC")]);
|
||||
assert!(matches!(model_3d(&d, 0, 0), Err(AnnotError::Invalid(m)) if m.contains("no 3D stream")));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn another_annotation_is_not_a_3d_one() {
|
||||
let d = doc("[<< /Type /Annot /Subtype /Square /Rect [0 0 1 1] >> 4 0 R]", &[annot("5 0 R"), stream("/Subtype /PRC", b"PRC")]);
|
||||
assert!(matches!(model_3d(&d, 0, 0), Err(AnnotError::Invalid(m)) if m.contains("not a 3D annotation")));
|
||||
assert_eq!(model_3d(&d, 0, 2), Err(AnnotError::NoSuchAnnotation { page: 0, index: 2 }));
|
||||
assert_eq!(model_3d_annotations(&d, 0), Ok(vec![1]));
|
||||
assert_eq!(model_3d_annotations(&d, 1), Err(AnnotError::NoSuchPage(1)));
|
||||
}
|
||||
@@ -2250,3 +2250,162 @@ fn freehand_highlight_is_compatible_ink_with_marker_blending() {
|
||||
assert!((a - b).abs() < 1e-4, "expected [10, 90, 130, 110], got {rect_from_border:?}");
|
||||
}
|
||||
}
|
||||
|
||||
/// A 3D annotation is PDF 1.6 and a PRC model 1.7 (ISO 32000-2 §13.6): an older document's
|
||||
/// catalog says so, and a newer one is left as it is.
|
||||
#[test]
|
||||
fn a_3d_model_raises_an_older_document_to_its_version() {
|
||||
let catalog_version = |doc: &Document| {
|
||||
let root = doc.root().unwrap();
|
||||
doc.get(root).as_dict().unwrap().name(b"Version").map(<[u8]>::to_vec)
|
||||
};
|
||||
let add = |doc: &mut Document, model: &[u8]| {
|
||||
let new = NewModel3d { page: 0, rect: [100.0, 100.0, 300.0, 300.0], model, activation: Activation3d::default(), poster: None, contents: "" };
|
||||
add_3d_model(doc, &new, &meta("m")).unwrap();
|
||||
};
|
||||
let mut doc = fixture();
|
||||
add(&mut doc, b"U3D\0rest");
|
||||
assert_eq!(catalog_version(&reopen(&doc)), None, "a 1.7 file needs nothing for U3D");
|
||||
for (model, version) in [(&b"U3D\0rest"[..], &b"1.6"[..]), (b"PRC rest", b"1.7")] {
|
||||
let mut doc = fixture();
|
||||
doc.set_version("1.4");
|
||||
add(&mut doc, model);
|
||||
assert_eq!(catalog_version(&reopen(&doc)).as_deref(), Some(version));
|
||||
}
|
||||
let mut doc = fixture();
|
||||
doc.set_version("2.0");
|
||||
add(&mut doc, b"PRC rest");
|
||||
assert_eq!(catalog_version(&reopen(&doc)), None, "a 2.0 file takes PRC as it is");
|
||||
}
|
||||
|
||||
/// Before 2.0, PRC is an Adobe extension to PDF 1.7 (§7.12): a PRC model declares it, keeping
|
||||
/// other extensions and a later ADBE level; U3D and a 2.0 file need nothing.
|
||||
#[test]
|
||||
fn a_prc_model_declares_the_adobe_extension_before_pdf_2() {
|
||||
let adbe = |doc: &Document| {
|
||||
let root = doc.root().unwrap();
|
||||
let ext = doc.get(root).as_dict().unwrap().get(b"Extensions").map(|e| doc.resolve(e).as_dict().unwrap().clone());
|
||||
ext.map(|e| {
|
||||
let adbe = e.get(b"ADBE").map(|a| a.as_dict().unwrap().clone());
|
||||
(e.get(b"XYZ").is_some(), adbe.map(|a| (a.name(b"BaseVersion").map(<[u8]>::to_vec), a.get(b"ExtensionLevel").and_then(Object::as_int))))
|
||||
})
|
||||
};
|
||||
let add = |doc: &mut Document, model: &[u8]| {
|
||||
let new = NewModel3d { page: 0, rect: [100.0, 100.0, 300.0, 300.0], model, activation: Activation3d::default(), poster: None, contents: "" };
|
||||
add_3d_model(doc, &new, &meta("m")).unwrap();
|
||||
};
|
||||
let mut doc = fixture();
|
||||
add(&mut doc, b"PRC rest");
|
||||
assert_eq!(adbe(&reopen(&doc)), Some((false, Some((Some(b"1.7".to_vec()), Some(1))))));
|
||||
let mut doc = fixture();
|
||||
add(&mut doc, b"U3D rest");
|
||||
assert_eq!(adbe(&reopen(&doc)), None, "U3D is in ISO 32000-1");
|
||||
let mut doc = fixture();
|
||||
doc.set_version("2.0");
|
||||
add(&mut doc, b"PRC rest");
|
||||
assert_eq!(adbe(&reopen(&doc)), None, "PRC is in ISO 32000-2");
|
||||
|
||||
let mut doc = fixture();
|
||||
let root = doc.root().unwrap();
|
||||
let mut level3 = Dict::new();
|
||||
level3.set(b"BaseVersion".to_vec(), Object::name("1.7"));
|
||||
level3.set(b"ExtensionLevel".to_vec(), Object::Int(3));
|
||||
let mut ext = Dict::new();
|
||||
ext.set(b"ADBE".to_vec(), Object::Dict(level3));
|
||||
ext.set(b"XYZ".to_vec(), Object::Dict(Dict::new()));
|
||||
doc.update_dict(root, |c| c.set(b"Extensions".to_vec(), Object::Dict(ext.clone()))).unwrap();
|
||||
add(&mut doc, b"PRC rest");
|
||||
assert_eq!(adbe(&reopen(&doc)), Some((true, Some((Some(b"1.7".to_vec()), Some(3))))), "a later level is kept");
|
||||
ext.remove(b"ADBE");
|
||||
let mut doc = fixture();
|
||||
doc.update_dict(root, |c| c.set(b"Extensions".to_vec(), Object::Dict(ext))).unwrap();
|
||||
add(&mut doc, b"PRC rest");
|
||||
assert_eq!(adbe(&reopen(&doc)), Some((true, Some((Some(b"1.7".to_vec()), Some(1))))), "other extensions are kept");
|
||||
|
||||
let mut doc = fixture();
|
||||
let mut ext = Dict::new();
|
||||
ext.set(b"ADBE".to_vec(), Object::Array(vec![Object::Dict(Dict::new())]));
|
||||
let ext = doc.add(Object::Dict(ext));
|
||||
doc.update_dict(root, |c| c.set(b"Extensions".to_vec(), Object::Ref(ext))).unwrap();
|
||||
add(&mut doc, b"PRC rest");
|
||||
let doc = reopen(&doc);
|
||||
let ext = doc.resolve(doc.get(doc.root().unwrap()).as_dict().unwrap().get(b"Extensions").unwrap());
|
||||
assert!(ext.as_dict().unwrap().get(b"ADBE").unwrap().as_array().is_some(), "an array of ADBE extensions is left alone");
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn a_picture_is_placed_by_its_box_and_a_form_needs_a_positive_size() {
|
||||
let at = [10.0, 20.0, 110.0, 70.0];
|
||||
assert_eq!(appearance::picture_place(at, true, None).as_deref(), Some("100 0 0 50 10 20 cm"), "an image fills its unit square");
|
||||
assert_eq!(appearance::picture_place(at, false, Some((200.0, 25.0))).as_deref(), Some("0.5 0 0 2 10 20 cm"));
|
||||
for size in [None, Some((0.0, 25.0)), Some((200.0, -1.0))] {
|
||||
assert_eq!(appearance::picture_place(at, false, size), None, "{size:?}");
|
||||
}
|
||||
}
|
||||
|
||||
/// The poster's box must lie in the rectangle, and a form poster needs a size to scale by.
|
||||
#[test]
|
||||
fn a_3d_poster_outside_its_rectangle_or_without_a_size_is_refused() {
|
||||
let picture = |at: [f64; 4], size: (f64, f64)| PosterPicture { xobject: ObjRef { num: 6, generation: 0 }, image: false, size, at };
|
||||
for (poster, why) in [
|
||||
(picture([50.0, 100.0, 250.0, 300.0], (10.0, 10.0)), "starts left of the rectangle"),
|
||||
(picture([100.0, 100.0, 300.0, 301.0], (10.0, 10.0)), "ends above it"),
|
||||
(picture([100.0, 100.0, 300.0, 300.0], (0.0, 10.0)), "has no width"),
|
||||
(picture([100.0 - 2e-7, 150.0, 100.0 - 1e-7, 200.0], (10.0, 10.0)), "lies outside within the rounding slack"),
|
||||
] {
|
||||
let mut doc = fixture();
|
||||
let new = NewModel3d {
|
||||
page: 0,
|
||||
rect: [100.0, 100.0, 300.0, 300.0],
|
||||
model: b"PRC rest",
|
||||
activation: Activation3d::default(),
|
||||
poster: Some(poster),
|
||||
contents: "",
|
||||
};
|
||||
assert!(matches!(add_3d_model(&mut doc, &new, &meta("m")), Err(AnnotError::Invalid(_))), "{why}");
|
||||
assert_eq!(list(&doc, 0).len(), 1, "{why}: nothing added");
|
||||
}
|
||||
}
|
||||
|
||||
/// A poster box fitted to the rectangle in floating point ends an ulp outside it: a 7×3 picture
|
||||
/// centred in [0 100 3.6 110.8] spans -2.2e-16 to 3.6000000000000005. It is taken, inside the
|
||||
/// rectangle.
|
||||
#[test]
|
||||
fn a_3d_poster_fitted_to_its_rectangle_with_rounding_is_taken() {
|
||||
let mut doc = fixture();
|
||||
let at = [-2.220446049250313e-16, 104.62857142857143, 3.6000000000000005, 106.17142857142858];
|
||||
let poster = PosterPicture { xobject: ObjRef { num: 6, generation: 0 }, image: false, size: (7.0, 3.0), at };
|
||||
let new = NewModel3d {
|
||||
page: 0,
|
||||
rect: [0.0, 100.0, 3.6, 110.8],
|
||||
model: b"PRC rest",
|
||||
activation: Activation3d::default(),
|
||||
poster: Some(poster),
|
||||
contents: "",
|
||||
};
|
||||
assert_eq!(add_3d_model(&mut doc, &new, &meta("m")), Ok(1));
|
||||
}
|
||||
|
||||
#[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));
|
||||
}
|
||||
|
||||
@@ -0,0 +1,292 @@
|
||||
//! 3D annotations (ISO 32000-2 §13.6.2): a U3D or PRC model shown in a rectangle on a page,
|
||||
//! with a poster (`/AP /N`) for printing, for readers without 3D, and until it is activated.
|
||||
|
||||
use super::create::{finite, normalize, num_array};
|
||||
use super::lookup::{annots, page_ref, set_annots};
|
||||
use super::types::{FLAG_PRINT, Meta};
|
||||
use super::{AnnotError, Dict, Document, ObjRef, Object, PdfString, Stream, appearance, n};
|
||||
|
||||
/// The largest model accepted, in bytes: well past real U3D/PRC files, and bounded because the
|
||||
/// model is held and compressed in memory.
|
||||
pub const MAX_MODEL_BYTES: usize = 256 << 20;
|
||||
|
||||
/// What the poster says when there is no picture.
|
||||
const PLACEHOLDER_LABEL: &str = "3D model";
|
||||
|
||||
/// A 3D stream's data format (§13.6.3): ECMA-363 U3D or ISO 14739-1 PRC.
|
||||
#[derive(Clone, Copy, Debug, PartialEq, Eq)]
|
||||
pub enum ModelFormat {
|
||||
U3d,
|
||||
Prc,
|
||||
}
|
||||
|
||||
impl ModelFormat {
|
||||
/// The format a model file's first bytes declare: U3D files start `U3D\0` (ECMA-363 file
|
||||
/// header block type), PRC files start `PRC`.
|
||||
///
|
||||
/// # Errors
|
||||
///
|
||||
/// [`AnnotError::NotAModel`] for anything else.
|
||||
pub fn detect(bytes: &[u8]) -> Result<Self, AnnotError> {
|
||||
if bytes.starts_with(b"U3D\0") {
|
||||
Ok(Self::U3d)
|
||||
} else if bytes.starts_with(b"PRC") {
|
||||
Ok(Self::Prc)
|
||||
} else {
|
||||
Err(AnnotError::NotAModel)
|
||||
}
|
||||
}
|
||||
|
||||
/// The 3D stream's `/Subtype`.
|
||||
pub fn subtype(self) -> &'static str {
|
||||
match self {
|
||||
Self::U3d => "U3D",
|
||||
Self::Prc => "PRC",
|
||||
}
|
||||
}
|
||||
|
||||
/// The PDF version a document holding it needs (§13.6): a 3D annotation is 1.6, a PRC stream
|
||||
/// 1.7 under Adobe's extension, declared by [`add_3d_model`] (PDF 2.0 takes PRC as standard).
|
||||
pub fn version(self) -> &'static str {
|
||||
match self {
|
||||
Self::U3d => "1.6",
|
||||
Self::Prc => "1.7",
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/// When a reader turns the poster into the live model (§13.6.2, the activation dictionary's
|
||||
/// `/A`). The standard's default is [`Self::Click`].
|
||||
#[derive(Clone, Copy, Debug, Default, PartialEq, Eq)]
|
||||
pub enum Activation {
|
||||
/// `/XA`: when the user clicks it; it prints as its poster.
|
||||
#[default]
|
||||
Click,
|
||||
/// `/PO`: when the page opens.
|
||||
PageOpen,
|
||||
/// `/PV`: when the page becomes visible.
|
||||
PageVisible,
|
||||
}
|
||||
|
||||
impl Activation {
|
||||
/// Every activation, with the word a tool argument names it by.
|
||||
pub const ALL: [(Self, &'static str); 3] = [(Self::Click, "click"), (Self::PageOpen, "page_open"), (Self::PageVisible, "page_visible")];
|
||||
|
||||
/// The `/A` name.
|
||||
pub fn name(self) -> &'static str {
|
||||
match self {
|
||||
Self::Click => "XA",
|
||||
Self::PageOpen => "PO",
|
||||
Self::PageVisible => "PV",
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/// A picture already in the document (an image XObject, or a form XObject whose `/Matrix` maps it
|
||||
/// to `size` points) drawn into `at`, a box inside the annotation's rectangle.
|
||||
#[derive(Clone, Copy, Debug, PartialEq)]
|
||||
pub struct PosterPicture {
|
||||
pub xobject: ObjRef,
|
||||
pub image: bool,
|
||||
pub size: (f64, f64),
|
||||
pub at: [f64; 4],
|
||||
}
|
||||
|
||||
/// A 3D model to add on `page` (0-based) in `rect` (user space).
|
||||
#[derive(Clone, Debug, PartialEq)]
|
||||
pub struct NewModel3d<'a> {
|
||||
pub page: usize,
|
||||
pub rect: [f64; 4],
|
||||
pub model: &'a [u8],
|
||||
pub activation: Activation,
|
||||
/// The poster's picture; `None` draws a labelled frame.
|
||||
pub poster: Option<PosterPicture>,
|
||||
/// `/Contents`: the annotation's alternate description (§12.5.2).
|
||||
pub contents: &'a str,
|
||||
}
|
||||
|
||||
/// Check a model before anything is added: its size and its format.
|
||||
///
|
||||
/// # Errors
|
||||
///
|
||||
/// [`AnnotError::ModelTooLarge`] past [`MAX_MODEL_BYTES`], else as [`ModelFormat::detect`].
|
||||
pub fn check_model(model: &[u8]) -> Result<ModelFormat, AnnotError> {
|
||||
check_model_size(model, MAX_MODEL_BYTES)?;
|
||||
ModelFormat::detect(model)
|
||||
}
|
||||
|
||||
fn check_model_size(model: &[u8], max: usize) -> Result<(), AnnotError> {
|
||||
if model.len() > max {
|
||||
return Err(AnnotError::ModelTooLarge { size: model.len(), max });
|
||||
}
|
||||
Ok(())
|
||||
}
|
||||
|
||||
/// Add a 3D annotation: the model in a Flate-compressed 3D stream referenced from `/3DD` (so the
|
||||
/// annotation has its own instance, §13.6.2), `/3DA` stating only `/A`, and the poster as `/AP /N`.
|
||||
/// No view (`/3DV`, `/VA`) is written: readers open on the model's own default view. A document
|
||||
/// older than [`ModelFormat::version`] is raised to it. Returns its index in the page's `/Annots`.
|
||||
///
|
||||
/// # Errors
|
||||
///
|
||||
/// As [`check_model`]; [`AnnotError::NoSuchPage`]; [`AnnotError::Invalid`] for a rectangle with no
|
||||
/// area or a poster box outside it.
|
||||
pub fn add_3d_model(doc: &mut Document, new: &NewModel3d<'_>, meta: &Meta) -> Result<usize, AnnotError> {
|
||||
let format = check_model(new.model)?;
|
||||
let page = page_ref(doc, new.page)?;
|
||||
let rect = normalize(new.rect);
|
||||
if !finite(&new.rect) || rect[2] - rect[0] < 1.0 || rect[3] - rect[1] < 1.0 {
|
||||
return Err(AnnotError::Invalid("invalid rectangle for the 3D model (each side at least 1 pt)".into()));
|
||||
}
|
||||
let poster = match &new.poster {
|
||||
Some(p) => picture_poster(rect, p)?,
|
||||
None => placeholder_poster(rect),
|
||||
};
|
||||
let mut stream = Dict::new();
|
||||
stream.set(b"Type".to_vec(), Object::name("3D"));
|
||||
stream.set(b"Subtype".to_vec(), Object::name(format.subtype()));
|
||||
let stream = doc.add(Object::Stream(Stream::flate(stream, new.model)));
|
||||
let poster = doc.add(Object::Stream(poster));
|
||||
let d = annotation_dict(new, rect, page, stream, poster, meta);
|
||||
let r = doc.add(Object::Dict(d));
|
||||
let mut list = annots(doc, page);
|
||||
let index = list.len();
|
||||
list.push(Object::Ref(r));
|
||||
set_annots(doc, page, list)?;
|
||||
at_least_version(doc, format.version())?;
|
||||
if format == ModelFormat::Prc && !at_least(doc, "2.0") {
|
||||
declare_prc_extension(doc)?;
|
||||
}
|
||||
Ok(index)
|
||||
}
|
||||
|
||||
/// Whether the header or the catalog `/Version` says `min` or later (§7.7.2).
|
||||
fn at_least(doc: &Document, min: &str) -> bool {
|
||||
let reached = |v: &[u8]| v.len() >= 3 && v >= min.as_bytes();
|
||||
let catalog = doc.root().and_then(|root| doc.get(root).as_dict().and_then(|c| c.get(b"Version").cloned()));
|
||||
let catalog = catalog.and_then(|v| doc.resolve(&v).as_name().map(<[u8]>::to_vec));
|
||||
reached(doc.version().as_bytes()) || catalog.as_deref().is_some_and(reached)
|
||||
}
|
||||
|
||||
/// PRC came before PDF 2.0 as an Adobe extension to 1.7: such a file declares
|
||||
/// `/Extensions /ADBE` with ExtensionLevel 1 or later (§7.12). Other extensions and an ADBE entry
|
||||
/// that already has a level are kept; one that is not a dictionary (an array of them) is left alone.
|
||||
fn declare_prc_extension(doc: &mut Document) -> Result<(), AnnotError> {
|
||||
let Some(root) = doc.root() else { return Ok(()) };
|
||||
let catalog = doc.get(root);
|
||||
// `None` when present but not a dictionary; an empty one when absent.
|
||||
let dict_or_new = |o: Option<&Object>| match o.map(|o| doc.resolve(o)) {
|
||||
None => Some(Dict::new()),
|
||||
Some(o) => o.as_dict().cloned(),
|
||||
};
|
||||
let Some(mut extensions) = dict_or_new(catalog.as_dict().and_then(|c| c.get(b"Extensions"))) else { return Ok(()) };
|
||||
let Some(mut adbe) = dict_or_new(extensions.get(b"ADBE")) else { return Ok(()) };
|
||||
if adbe.get(b"ExtensionLevel").map(|l| doc.resolve(l)).and_then(|l| l.as_int()).is_some_and(|l| l >= 1) {
|
||||
return Ok(());
|
||||
}
|
||||
adbe.set(b"BaseVersion".to_vec(), Object::name("1.7"));
|
||||
adbe.set(b"ExtensionLevel".to_vec(), Object::Int(1));
|
||||
extensions.set(b"ADBE".to_vec(), Object::Dict(adbe));
|
||||
doc.update_dict(root, |c| c.set(b"Extensions".to_vec(), Object::Dict(extensions)))?;
|
||||
Ok(())
|
||||
}
|
||||
|
||||
/// A document whose header and catalog `/Version` both say less than `min` gets `/Version min` in
|
||||
/// its catalog (§7.7.2: the later of the two applies).
|
||||
fn at_least_version(doc: &mut Document, min: &str) -> Result<(), AnnotError> {
|
||||
let Some(root) = doc.root() else { return Ok(()) };
|
||||
if !at_least(doc, min) {
|
||||
doc.update_dict(root, |c| c.set(b"Version".to_vec(), Object::name(min)))?;
|
||||
}
|
||||
Ok(())
|
||||
}
|
||||
|
||||
fn annotation_dict(new: &NewModel3d<'_>, rect: [f64; 4], page: ObjRef, stream: ObjRef, poster: ObjRef, meta: &Meta) -> Dict {
|
||||
let mut d = Dict::new();
|
||||
d.set(b"Type".to_vec(), Object::name("Annot"));
|
||||
d.set(b"Subtype".to_vec(), Object::name("3D"));
|
||||
d.set(b"Rect".to_vec(), num_array(&rect));
|
||||
d.set(b"P".to_vec(), Object::Ref(page));
|
||||
d.set(b"F".to_vec(), Object::Int(FLAG_PRINT));
|
||||
if !new.contents.is_empty() {
|
||||
d.set(b"Contents".to_vec(), PdfString::text(new.contents));
|
||||
}
|
||||
if !meta.id.is_empty() {
|
||||
d.set(b"NM".to_vec(), PdfString::text(&meta.id));
|
||||
}
|
||||
if let Some(date) = &meta.date {
|
||||
d.set(b"M".to_vec(), PdfString::literal(date.as_bytes().to_vec()));
|
||||
}
|
||||
d.set(b"3DD".to_vec(), Object::Ref(stream));
|
||||
let mut activation = Dict::new();
|
||||
activation.set(b"A".to_vec(), Object::name(new.activation.name()));
|
||||
d.set(b"3DA".to_vec(), Object::Dict(activation));
|
||||
let mut ap = Dict::new();
|
||||
ap.set(b"N".to_vec(), Object::Ref(poster));
|
||||
d.set(b"AP".to_vec(), Object::Dict(ap));
|
||||
d
|
||||
}
|
||||
|
||||
/// The poster drawing `p` into its box, which must lie within `rect`.
|
||||
fn picture_poster(rect: [f64; 4], p: &PosterPicture) -> Result<Stream, AnnotError> {
|
||||
let at = normalize(p.at);
|
||||
// A box fitted to `rect` in floating point can end a few ulps outside it: allow that, then clamp.
|
||||
let slack = rect.iter().fold(1.0_f64, |m, v| m.max(v.abs())) * 1e-9;
|
||||
let near = finite(&p.at) && at[0] >= rect[0] - slack && at[1] >= rect[1] - slack && at[2] <= rect[2] + slack && at[3] <= rect[3] + slack;
|
||||
let at = [at[0].max(rect[0]), at[1].max(rect[1]), at[2].min(rect[2]), at[3].min(rect[3])];
|
||||
if !(near && at[2] > at[0] && at[3] > at[1]) {
|
||||
return Err(AnnotError::Invalid("the poster must fit inside the 3D model's rectangle".into()));
|
||||
}
|
||||
let place = appearance::picture_place(at, p.image, Some(p.size)).ok_or_else(|| AnnotError::Invalid("the poster picture has no size".into()))?;
|
||||
let mut xobjects = Dict::new();
|
||||
xobjects.set(b"Pic".to_vec(), Object::Ref(p.xobject));
|
||||
let mut resources = Dict::new();
|
||||
resources.set(b"XObject".to_vec(), Object::Dict(xobjects));
|
||||
Ok(appearance::form(rect, format!("q {place} /Pic Do Q\n").as_bytes(), resources))
|
||||
}
|
||||
|
||||
/// A light frame with "3D model" centred in it, shrunk to fit (left out when even 2 pt won't).
|
||||
fn placeholder_poster(rect: [f64; 4]) -> Stream {
|
||||
let [x0, y0, x1, y1] = rect;
|
||||
let (w, h) = (x1 - x0, y1 - y0);
|
||||
let mut c =
|
||||
format!("0.94 g {} {} {} {} re f\n0.45 G 1 w {} {} {} {} re S\n", n(x0), n(y0), n(w), n(h), n(x0 + 0.5), n(y0 + 0.5), n(w - 1.0), n(h - 1.0));
|
||||
let mut resources = Dict::new();
|
||||
let unit = appearance::text_width(PLACEHOLDER_LABEL, 1.0);
|
||||
let size = if unit > 0.0 { (w * 0.8 / unit).min(h * 0.4).min(14.0) } else { 0.0 };
|
||||
if size >= 2.0 {
|
||||
let (tx, ty) = (x0 + (w - unit * size) / 2.0, y0 + (h - size * 0.7) / 2.0);
|
||||
c.push_str(&format!("BT 0.3 g /Helv {} Tf {} {} Td ({PLACEHOLDER_LABEL}) Tj ET\n", n(size), n(tx), n(ty)));
|
||||
resources.set(b"Font".to_vec(), appearance::helvetica_resource());
|
||||
}
|
||||
appearance::form(rect, c.as_bytes(), resources)
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::*;
|
||||
|
||||
#[test]
|
||||
fn model_size_is_capped() {
|
||||
assert_eq!(check_model_size(&[0; 8], 8), Ok(()));
|
||||
assert_eq!(check_model_size(&[0; 9], 8), Err(AnnotError::ModelTooLarge { size: 9, max: 8 }));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn the_format_is_read_from_the_header() {
|
||||
assert_eq!(ModelFormat::detect(b"U3D\0rest"), Ok(ModelFormat::U3d));
|
||||
assert_eq!(ModelFormat::detect(b"PRC8800"), Ok(ModelFormat::Prc));
|
||||
for junk in [&b""[..], b"U3D", b"U3DX", b"PR", b"%PDF-1.7", b"prc"] {
|
||||
assert_eq!(ModelFormat::detect(junk), Err(AnnotError::NotAModel), "{junk:?}");
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn the_placeholder_label_shrinks_to_fit_and_is_dropped_when_it_cannot() {
|
||||
let wide = String::from_utf8(placeholder_poster([0.0, 0.0, 300.0, 200.0]).decoded().unwrap().to_vec()).unwrap();
|
||||
assert!(wide.contains("/Helv 14 Tf") && wide.contains("(3D model) Tj"), "{wide}");
|
||||
let tiny = placeholder_poster([0.0, 0.0, 4.0, 4.0]);
|
||||
assert!(!String::from_utf8(tiny.decoded().unwrap().to_vec()).unwrap().contains("Tj"));
|
||||
assert!(tiny.dict.get(b"Resources").and_then(Object::as_dict).is_none_or(|r| r.get(b"Font").is_none()));
|
||||
}
|
||||
}
|
||||
+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)));
|
||||
}
|
||||
|
||||
@@ -14,6 +14,8 @@ pdfcraft-cos = { workspace = true }
|
||||
pdfcraft-render = { workspace = true }
|
||||
pdfcraft-organize = { workspace = true }
|
||||
pdfcraft-platform = { workspace = true }
|
||||
pdfcraft-prc = { workspace = true }
|
||||
pdfcraft-prc-render = { workspace = true }
|
||||
serde_json = { workspace = true }
|
||||
sha2 = "0.11"
|
||||
tempfile = "3.27"
|
||||
|
||||
@@ -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
|
||||
@@ -248,6 +250,15 @@ choices and values over 4096 UTF-8 bytes return an error.
|
||||
|
||||
Example: `form_set_props doc=1 field=agree export_value=Accepted widget=1`.
|
||||
|
||||
## Rendering a 3D model
|
||||
|
||||
`model_render` draws a page's 3D model (a 3D annotation's PRC stream, directly or through a 3D
|
||||
reference) to a PNG, without the viewer. `model` picks the page's Nth 3D model (default 1);
|
||||
`width` and `height` are 1 to 4096 (default 512); `direction` is the view direction from the eye
|
||||
(default `[-1, 1, -1]`, with Z up unless the view looks along Z); `perspective` defaults to true.
|
||||
The model is framed to fill the image and shaded by a headlight on white. U3D models are refused
|
||||
with an error, and the annotation's own views, lighting and render modes are not applied yet.
|
||||
|
||||
## Viewer navigation history
|
||||
|
||||
A running PdfCraft instance launched with `--control FILE` exposes its per-tab history through
|
||||
|
||||
@@ -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).
|
||||
|
||||
@@ -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)
|
||||
}
|
||||
})
|
||||
}
|
||||
@@ -0,0 +1,209 @@
|
||||
//! Bookmark trees in and out of documents: `bookmark_export`, `bookmark_import`, `bookmark_copy`.
|
||||
//!
|
||||
//! The portable form is JSON: `{"bookmarks": [node, …]}`, where a node is `title`, `page`
|
||||
//! (1-based, or `null` for one that goes nowhere), `view` (`{"type", "values"}`: a destination
|
||||
//! type and its values in PDF user space, as the file stores them), `color`, `bold`, `italic`,
|
||||
//! `open` and `children`. What export writes, import takes back unchanged. A file also carries
|
||||
//! `"truncated": true` when the export left out bookmarks nested past the listing limit.
|
||||
use crate::{Args, Automation, Result, ToolError, failed};
|
||||
use pdfcraft_engine::{DocId, Edit, OutlineNode};
|
||||
use serde_json::{Value, json};
|
||||
|
||||
/// Deepest nesting a bookmark tree may have (the listing reaches 33 levels).
|
||||
const MAX_DEPTH: usize = 33;
|
||||
|
||||
/// The keys a node may have: the ones [`node_json`] writes.
|
||||
const NODE_KEYS: [&str; 8] = ["title", "page", "view", "color", "bold", "italic", "open", "children"];
|
||||
|
||||
impl Automation {
|
||||
pub(crate) fn bookmark_export(&self, a: &Args) -> Result<Value> {
|
||||
let id = self.doc(a)?.id;
|
||||
let path = a.opt_path("path")?.unwrap_or_default();
|
||||
let tree = self.outline_of(id, &path)?;
|
||||
let mut out = json!({ "bookmarks": tree.nodes.iter().map(node_json).collect::<Vec<_>>(), "truncated": tree.truncated });
|
||||
if let Some(file) = a.opt_str("out")? {
|
||||
let target = self.resolve(file, true)?;
|
||||
let mut saved = json!({ "bookmarks": out["bookmarks"] });
|
||||
if tree.truncated {
|
||||
saved["truncated"] = json!(true);
|
||||
}
|
||||
let text = serde_json::to_vec_pretty(&saved).map_err(failed)?;
|
||||
crate::write_atomic(&target, &text)?;
|
||||
out["path"] = json!(target);
|
||||
}
|
||||
Ok(out)
|
||||
}
|
||||
|
||||
pub(crate) fn bookmark_import(&mut self, a: &Args) -> Result<Value> {
|
||||
let (nodes, truncated) = match (a.get("bookmarks"), a.opt_str("file")?) {
|
||||
(Some(list), None) => (nodes_of(list)?, false),
|
||||
(None, Some(file)) => {
|
||||
let path = self.resolve(file, false)?;
|
||||
let value: Value = serde_json::from_slice(&crate::read_input(&path)?).map_err(|e| failed(format!("not a bookmark file: {e}")))?;
|
||||
let list = value.get("bookmarks").ok_or_else(|| failed("not a bookmark file: it has no \"bookmarks\" list"))?;
|
||||
(nodes_of(list)?, value.get("truncated") == Some(&Value::Bool(true)))
|
||||
}
|
||||
_ => return Err(ToolError::InvalidArgs("give either bookmarks or file".into())),
|
||||
};
|
||||
let mut out = self.write_tree(a, nodes)?;
|
||||
out["truncated"] = json!(truncated);
|
||||
Ok(out)
|
||||
}
|
||||
|
||||
pub(crate) fn bookmark_copy(&mut self, a: &Args) -> Result<Value> {
|
||||
let from = a.int("from")?;
|
||||
let from = DocId(u64::try_from(from).map_err(|_| ToolError::InvalidArgs("from must be positive".into()))?);
|
||||
let path = a.opt_path("path")?.unwrap_or_default();
|
||||
let tree = self.outline_of(from, &path)?;
|
||||
let mut out = self.write_tree(a, tree.nodes)?;
|
||||
out["truncated"] = json!(tree.truncated);
|
||||
Ok(out)
|
||||
}
|
||||
|
||||
fn outline_of(&self, id: DocId, path: &[usize]) -> Result<pdfcraft_engine::OutlineTree> {
|
||||
match self.session.outline_tree(id, path) {
|
||||
// The engine names the path 0-based; the caller gave it 1-based.
|
||||
Some(tree) => tree.map_err(|e| match e {
|
||||
pdfcraft_organize::OutlineError::NoSuchBookmark(_) => failed(format!("there is no bookmark at {:?}", one_based(path))),
|
||||
e => failed(e),
|
||||
}),
|
||||
None => Err(failed(format!("document {} is not open, or its bookmarks can't be read for editing", id.0))),
|
||||
}
|
||||
}
|
||||
|
||||
/// Write `nodes` into `doc` under `parent` at `position` (or in place of the outline with
|
||||
/// `replace`), and say which of them went nowhere because the document lacks their page.
|
||||
fn write_tree(&mut self, a: &Args, bookmarks: Vec<OutlineNode>) -> Result<Value> {
|
||||
let parent = a.opt_path("parent")?.unwrap_or_default();
|
||||
let index = a.opt_int("position")?.map_or(usize::MAX, |p| usize::try_from(p.max(1) - 1).unwrap_or(usize::MAX));
|
||||
let replace = a.opt_bool("replace")?.unwrap_or(false);
|
||||
let count = self.doc(a)?.info.pages.len();
|
||||
let unmapped = pdfcraft_engine::outline_unmapped(&bookmarks, count);
|
||||
let mut out = self.apply(a, Edit::ImportBookmarks { parent, index, bookmarks, replace })?;
|
||||
out["unmapped"] = json!(unmapped.iter().map(|p| one_based(p)).collect::<Vec<_>>());
|
||||
Ok(out)
|
||||
}
|
||||
}
|
||||
|
||||
fn one_based(path: &[usize]) -> Vec<usize> {
|
||||
path.iter().map(|i| i.saturating_add(1)).collect()
|
||||
}
|
||||
|
||||
/// A node as JSON, leaving out what is at its default (no view, black, regular, no children).
|
||||
fn node_json(n: &OutlineNode) -> Value {
|
||||
let mut v = json!({ "title": n.title, "page": n.page.map(|p| p.saturating_add(1)), "open": n.open });
|
||||
if let Some((kind, values)) = &n.view {
|
||||
v["view"] = json!({ "type": String::from_utf8_lossy(kind), "values": values });
|
||||
}
|
||||
if let Some(c) = n.color {
|
||||
v["color"] = json!(c);
|
||||
}
|
||||
if n.bold {
|
||||
v["bold"] = json!(true);
|
||||
}
|
||||
if n.italic {
|
||||
v["italic"] = json!(true);
|
||||
}
|
||||
if !n.children.is_empty() {
|
||||
v["children"] = json!(n.children.iter().map(node_json).collect::<Vec<_>>());
|
||||
}
|
||||
v
|
||||
}
|
||||
|
||||
fn nodes_of(list: &Value) -> Result<Vec<OutlineNode>> {
|
||||
let mut count = 0;
|
||||
list_of(list, &[], &mut count)
|
||||
}
|
||||
|
||||
/// The nodes of one level; `at` is the 1-based path of their parent, for messages.
|
||||
fn list_of(list: &Value, at: &[usize], count: &mut usize) -> Result<Vec<OutlineNode>> {
|
||||
let items = list.as_array().ok_or_else(|| bad(at, "children must be a list of bookmarks"))?;
|
||||
if at.len() >= MAX_DEPTH && !items.is_empty() {
|
||||
return Err(bad(at, &format!("bookmarks may nest at most {MAX_DEPTH} levels deep")));
|
||||
}
|
||||
*count = count.saturating_add(items.len());
|
||||
if *count > pdfcraft_engine::MAX_IMPORT_BOOKMARKS {
|
||||
return Err(ToolError::InvalidArgs(format!("at most {} bookmarks can be imported at once", pdfcraft_engine::MAX_IMPORT_BOOKMARKS)));
|
||||
}
|
||||
let mut out = Vec::with_capacity(items.len());
|
||||
for (i, item) in items.iter().enumerate() {
|
||||
let mut path = at.to_vec();
|
||||
path.push(i.saturating_add(1));
|
||||
out.push(node_of(item, &path, count)?);
|
||||
}
|
||||
Ok(out)
|
||||
}
|
||||
|
||||
/// One node and, through [`list_of`], its children (recursion bounded by `MAX_DEPTH`).
|
||||
fn node_of(v: &Value, at: &[usize], count: &mut usize) -> Result<OutlineNode> {
|
||||
let o = v.as_object().ok_or_else(|| bad(at, "must be an object"))?;
|
||||
if let Some(k) = o.keys().find(|k| !NODE_KEYS.contains(&k.as_str())) {
|
||||
return Err(bad(at, &format!("unknown key {k:?} (a bookmark has {})", NODE_KEYS.join(", "))));
|
||||
}
|
||||
let field = |k: &str| o.get(k).filter(|x| !x.is_null());
|
||||
// An empty title is kept: files have them, and export writes them as "".
|
||||
let title = field("title").and_then(Value::as_str).ok_or_else(|| bad(at, "needs a title"))?.to_string();
|
||||
let page = match field("page") {
|
||||
None => None,
|
||||
Some(p) => Some(p.as_u64().filter(|p| *p >= 1).and_then(|p| usize::try_from(p - 1).ok()).ok_or_else(|| bad(at, "page must be 1 or more"))?),
|
||||
};
|
||||
let flag = |k: &str| field(k).map_or(Ok(None), |x| x.as_bool().map(Some).ok_or_else(|| bad(at, &format!("{k} must be true or false"))));
|
||||
let color = match field("color") {
|
||||
None => None,
|
||||
Some(c) => {
|
||||
let rgb: Option<Vec<f32>> = c.as_array().and_then(|c| c.iter().map(|x| x.as_f64().map(|x| x as f32)).collect());
|
||||
match rgb.as_deref() {
|
||||
Some(&[r, g, b]) if [r, g, b].iter().all(|c| (0.0..=1.0).contains(c)) => Some([r, g, b]),
|
||||
_ => return Err(bad(at, "color must be [r, g, b], each from 0 to 1")),
|
||||
}
|
||||
}
|
||||
};
|
||||
let children = match field("children") {
|
||||
None => Vec::new(),
|
||||
Some(list) => list_of(list, at, count)?,
|
||||
};
|
||||
Ok(OutlineNode {
|
||||
title,
|
||||
page,
|
||||
view: field("view").map(|x| view_of(x, at)).transpose()?,
|
||||
color,
|
||||
italic: flag("italic")?.unwrap_or(false),
|
||||
bold: flag("bold")?.unwrap_or(false),
|
||||
open: flag("open")?.unwrap_or(true),
|
||||
children,
|
||||
})
|
||||
}
|
||||
|
||||
/// `{"type": "XYZ", "values": [left, top, zoom]}`: a destination type with exactly its values.
|
||||
fn view_of(v: &Value, at: &[usize]) -> Result<(Vec<u8>, Vec<Option<f64>>)> {
|
||||
let kind = v.get("type").and_then(Value::as_str).ok_or_else(|| bad(at, "view needs a type such as XYZ or Fit"))?;
|
||||
let values = match v.get("values").filter(|x| !x.is_null()) {
|
||||
None => Vec::new(),
|
||||
Some(list) => {
|
||||
let list = list.as_array().filter(|l| l.len() <= 4).ok_or_else(|| bad(at, "view values must be a list of at most 4 numbers or nulls"))?;
|
||||
list.iter()
|
||||
.map(|x| match x {
|
||||
Value::Null => Ok(None),
|
||||
x => x.as_f64().map(Some).ok_or_else(|| bad(at, "view values must be numbers or null")),
|
||||
})
|
||||
.collect::<Result<_>>()?
|
||||
}
|
||||
};
|
||||
let arity = pdfcraft_engine::outline_view_arity(kind.as_bytes()).ok_or_else(|| bad(at, VIEW_TYPES))?;
|
||||
if values.len() != arity {
|
||||
return Err(bad(at, &format!("a {kind} view takes {arity} values (numbers, or null to keep the reader's)")));
|
||||
}
|
||||
if kind == "FitR" && values.iter().any(Option::is_none) {
|
||||
return Err(bad(at, "a FitR view needs all four values: left, bottom, right, top"));
|
||||
}
|
||||
Ok((kind.as_bytes().to_vec(), values))
|
||||
}
|
||||
|
||||
const VIEW_TYPES: &str = "view type must be XYZ (3 values: left, top, zoom), Fit, FitB (none), FitH, FitV, FitBH, FitBV (1) or FitR (4)";
|
||||
|
||||
fn bad(at: &[usize], what: &str) -> ToolError {
|
||||
if at.is_empty() {
|
||||
return ToolError::InvalidArgs(format!("bookmarks: {what}"));
|
||||
}
|
||||
ToolError::InvalidArgs(format!("bookmark {at:?}: {what}"))
|
||||
}
|
||||
@@ -75,7 +75,7 @@ fn to_user(p: &PageInfo, x: f64, y: f64) -> [f64; 2] {
|
||||
[ux as f64, uy as f64]
|
||||
}
|
||||
|
||||
fn rect_to_user(p: &PageInfo, r: [f64; 4]) -> [f64; 4] {
|
||||
pub(crate) fn rect_to_user(p: &PageInfo, r: [f64; 4]) -> [f64; 4] {
|
||||
let (a, b) = (to_user(p, r[0], r[1]), to_user(p, r[2], r[3]));
|
||||
[a[0].min(b[0]), a[1].min(b[1]), a[0].max(b[0]), a[1].max(b[1])]
|
||||
}
|
||||
@@ -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<_>>() }),
|
||||
@@ -68,6 +69,7 @@ impl Automation {
|
||||
self.apply(&a, edit)?
|
||||
}
|
||||
"page_render" => return self.page_render(&a),
|
||||
"model_render" => return self.model_render(&a),
|
||||
"comment_image_preview" => return self.comment_image_preview(&a),
|
||||
"text_extract" => self.text_extract(&a)?,
|
||||
"text_word_count" => self.text_word_count(&a)?,
|
||||
@@ -195,6 +197,9 @@ impl Automation {
|
||||
out
|
||||
}
|
||||
"bookmark_list" => self.bookmark_listing(&a)?,
|
||||
"bookmark_export" => self.bookmark_export(&a)?,
|
||||
"bookmark_import" => self.bookmark_import(&a)?,
|
||||
"bookmark_copy" => self.bookmark_copy(&a)?,
|
||||
"bookmark_add" => {
|
||||
let page = self.page(&a)?;
|
||||
let parent = a.opt_path("parent")?.unwrap_or_default();
|
||||
@@ -768,6 +773,7 @@ impl Automation {
|
||||
"comment_list" => self.comment_list(&a)?,
|
||||
"comment_add" => self.comment_add(&a)?,
|
||||
"stamp_custom" => self.stamp_custom(&a)?,
|
||||
"model_add" => self.model_add(&a)?,
|
||||
"comment_reply" => self.comment_reply(&a)?,
|
||||
"comment_set_status" => self.comment_set_status(&a)?,
|
||||
"sign_list" => self.sign_list(&a)?,
|
||||
|
||||
@@ -394,8 +394,18 @@ mod tests {
|
||||
// Helpers that are only called with a resolved path. `doc_batch` (batch.rs) resolves its
|
||||
// inputs and out_dir, walks only inside them (skipping links) and resolves every
|
||||
// discovered file again before `process` reads it or `publish` writes it.
|
||||
const RESOLVED_BY_CALLER: &[&str] =
|
||||
&["write_atomic", "write_atomic_with", "read_input", "read_input_bytes", "read_review_sidecar", "process", "linked", "walk", "publish"];
|
||||
const RESOLVED_BY_CALLER: &[&str] = &[
|
||||
"write_atomic",
|
||||
"write_atomic_with",
|
||||
"read_input",
|
||||
"read_input_bytes",
|
||||
"read_model",
|
||||
"read_review_sidecar",
|
||||
"process",
|
||||
"linked",
|
||||
"walk",
|
||||
"publish",
|
||||
];
|
||||
let mut dirs = vec![Path::new(env!("CARGO_MANIFEST_DIR")).join("src")];
|
||||
let mut files = vec![];
|
||||
while let Some(dir) = dirs.pop() {
|
||||
|
||||
@@ -16,6 +16,7 @@
|
||||
|
||||
mod a11y;
|
||||
mod batch;
|
||||
mod bates;
|
||||
mod comments;
|
||||
mod content;
|
||||
mod conventions;
|
||||
@@ -26,6 +27,8 @@ mod links;
|
||||
#[cfg(feature = "mcp")]
|
||||
pub mod mcp;
|
||||
mod measure;
|
||||
mod model3d;
|
||||
mod model_render;
|
||||
mod printing;
|
||||
mod reading;
|
||||
mod redact;
|
||||
@@ -49,6 +52,7 @@ use file_access::foreign_share;
|
||||
use text_cache::TextCache;
|
||||
|
||||
mod assemble;
|
||||
mod bookmark_io;
|
||||
mod dispatch;
|
||||
mod documents;
|
||||
mod error;
|
||||
|
||||
@@ -557,7 +557,7 @@ fn tool_json(t: &crate::ToolDef) -> Value {
|
||||
"title": t.title,
|
||||
"description": t.description,
|
||||
"inputSchema": t.input_schema,
|
||||
"annotations": { "title": t.title, "readOnlyHint": t.read_only, "destructiveHint": t.destructive, "idempotentHint": t.read_only || matches!(t.name, "doc_save" | "doc_optimize" | "doc_export_data" | "measure_export" | "doc_export_images" | "doc_export_office" | "doc_export_all_images" | "doc_export_text" | "image_save"), "openWorldHint": false },
|
||||
"annotations": { "title": t.title, "readOnlyHint": t.read_only, "destructiveHint": t.destructive, "idempotentHint": t.read_only || matches!(t.name, "doc_save" | "doc_optimize" | "doc_export_data" | "measure_export" | "doc_export_images" | "doc_export_office" | "doc_export_all_images" | "doc_export_text" | "image_save" | "bookmark_export"), "openWorldHint": false },
|
||||
})
|
||||
}
|
||||
|
||||
|
||||
@@ -0,0 +1,114 @@
|
||||
//! 3D model tools (Acrobat: Rich Media ▸ Add 3D, AGENTS.md §3).
|
||||
|
||||
use std::path::Path;
|
||||
|
||||
use pdfcraft_engine::{Activation3d, Edit, MAX_3D_MODEL_BYTES, MarkFile, Model3dFormat};
|
||||
use serde_json::Value;
|
||||
|
||||
use crate::comments::rect_to_user;
|
||||
use crate::{Args, Automation, Result, ToolError, failed};
|
||||
|
||||
/// The largest side of a 3D model's box, in points: the largest page PDF allows (ISO 32000-2 Annex C).
|
||||
const MAX_MODEL_SIDE: f64 = 14_400.0;
|
||||
|
||||
impl Automation {
|
||||
/// A U3D or PRC model in `rect` on `page`, its poster the picture at `poster` (a PDF page or an
|
||||
/// image) fitted inside the box, or a labelled frame.
|
||||
pub(crate) fn model_add(&mut self, a: &Args) -> Result<Value> {
|
||||
let page = self.page(a)?;
|
||||
let info = self.doc(a)?.info.pages.get(page).cloned().ok_or_else(|| ToolError::InvalidArgs(format!("page {} does not exist", page + 1)))?;
|
||||
let r = a.nums::<4>("rect")?.ok_or_else(|| ToolError::InvalidArgs("missing argument rect".into()))?;
|
||||
let (w, h) = ((r[2] - r[0]).abs(), (r[3] - r[1]).abs());
|
||||
if !((1.0..=MAX_MODEL_SIDE).contains(&w) && (1.0..=MAX_MODEL_SIDE).contains(&h)) {
|
||||
return Err(ToolError::InvalidArgs(format!(
|
||||
"rect must be [x0, y0, x1, y1] with each side at least 1 pt and at most {MAX_MODEL_SIDE} pt"
|
||||
)));
|
||||
}
|
||||
let activation = match a.opt_str("activation")? {
|
||||
None => Activation3d::default(),
|
||||
Some(word) => Activation3d::ALL
|
||||
.iter()
|
||||
.find(|(_, w)| *w == word)
|
||||
.map(|(act, _)| *act)
|
||||
.ok_or_else(|| ToolError::InvalidArgs(format!("activation must be one of: {}", Activation3d::ALL.map(|(_, w)| w).join(", "))))?,
|
||||
};
|
||||
let path = self.resolve(a.str("path")?, false)?;
|
||||
let model = read_model(&path, MAX_3D_MODEL_BYTES)?;
|
||||
let file = path.file_name().map(|n| n.to_string_lossy().into_owned()).unwrap_or_default();
|
||||
let name = a.opt_str("name")?.map(str::to_owned).unwrap_or_else(|| file.rsplit_once('.').map_or(file.clone(), |(s, _)| s.to_owned()));
|
||||
let poster = match a.opt_str("poster")? {
|
||||
None => None,
|
||||
Some(p) => {
|
||||
let path = self.resolve(p, false)?;
|
||||
let bytes = crate::read_input(&path)?;
|
||||
let name = path.file_name().map(|n| n.to_string_lossy().into_owned()).unwrap_or_default();
|
||||
let page = usize::try_from(a.opt_int("poster_page")?.unwrap_or(1).max(1)).unwrap_or(1).saturating_sub(1);
|
||||
Some(MarkFile { name, bytes: std::sync::Arc::new(bytes), page })
|
||||
}
|
||||
};
|
||||
let edit = Edit::AddModel3d { page, rect: rect_to_user(&info, r), model: std::sync::Arc::new(model), poster, activation, name };
|
||||
self.apply(a, edit)
|
||||
}
|
||||
}
|
||||
|
||||
/// Read a resolved model file of at most `max` bytes. Its size (from the file system) and its first
|
||||
/// bytes are checked before the rest is read, so a large file that is not a model is never loaded.
|
||||
fn read_model(path: &Path, max: usize) -> Result<Vec<u8>> {
|
||||
use std::io::Read as _;
|
||||
let io = |e: std::io::Error| failed(format!("{}: {e}", path.display()));
|
||||
let too_large = |size: u64| failed(format!("the 3D model is {size} bytes; the largest accepted is {max}"));
|
||||
let cap = u64::try_from(max).unwrap_or(u64::MAX);
|
||||
let mut file = std::fs::File::open(path).map_err(io)?;
|
||||
if let Ok(meta) = file.metadata()
|
||||
&& meta.is_file()
|
||||
&& meta.len() > cap
|
||||
{
|
||||
return Err(too_large(meta.len()));
|
||||
}
|
||||
let mut bytes = Vec::new();
|
||||
(&mut file).take(4).read_to_end(&mut bytes).map_err(io)?;
|
||||
Model3dFormat::detect(&bytes).map_err(failed)?;
|
||||
let rest = cap.saturating_add(1).saturating_sub(bytes.len() as u64);
|
||||
file.take(rest).read_to_end(&mut bytes).map_err(io)?;
|
||||
if bytes.len() > max {
|
||||
return Err(failed(format!("the 3D model is more than {max} bytes, the largest accepted")));
|
||||
}
|
||||
Ok(bytes)
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::*;
|
||||
|
||||
fn file(dir: &Path, name: &str, bytes: &[u8]) -> std::path::PathBuf {
|
||||
let path = dir.join(name);
|
||||
std::fs::write(&path, bytes).unwrap();
|
||||
path
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn a_model_is_read_whole_when_it_fits() {
|
||||
let dir = tempfile::tempdir().unwrap();
|
||||
let mut prc = b"PRC".to_vec();
|
||||
prc.extend_from_slice(&[7; 40]);
|
||||
assert_eq!(read_model(&file(dir.path(), "m.prc", &prc), 64).unwrap(), prc);
|
||||
assert_eq!(read_model(&file(dir.path(), "m.u3d", b"U3D\0x"), 6).unwrap(), b"U3D\0x");
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn a_model_past_the_cap_is_refused_by_its_size_before_it_is_read() {
|
||||
let dir = tempfile::tempdir().unwrap();
|
||||
let path = file(dir.path(), "big.prc", &[b'P', b'R', b'C', 0, 0, 0, 0, 0, 0, 0]);
|
||||
let err = read_model(&path, 4).unwrap_err().to_string();
|
||||
assert!(err.contains("is 10 bytes") && err.contains("largest accepted is 4"), "the file's own size, from the file system: {err}");
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn a_file_that_is_not_a_model_is_refused_by_its_header() {
|
||||
let dir = tempfile::tempdir().unwrap();
|
||||
for junk in [&b"%PDF-1.7 a page"[..], b"PR", b"", b"U3DX and more"] {
|
||||
let err = read_model(&file(dir.path(), "junk.bin", junk), 64).unwrap_err().to_string();
|
||||
assert!(err.contains("not a 3D model"), "{junk:?}: {err}");
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,104 @@
|
||||
//! `model_render`: a page's 3D model (ISO 32000-2 §13.6) drawn to a PNG, without a viewer.
|
||||
|
||||
use pdfcraft_engine::model3d::Model3dKind;
|
||||
use pdfcraft_prc::PrcFile;
|
||||
use pdfcraft_prc_render::{Camera, RenderOptions, assemble, render};
|
||||
|
||||
use super::Automation;
|
||||
use super::dispatch::Content;
|
||||
use super::error::{Result, ToolError, failed};
|
||||
use super::json::Args;
|
||||
use super::pages::encode_png;
|
||||
|
||||
/// Default and largest side of the image, in pixels.
|
||||
pub(crate) const DEFAULT_SIDE: u32 = 512;
|
||||
pub(crate) const MAX_SIDE: u32 = 4096;
|
||||
|
||||
/// The default view: from the front, right and above, as an isometric view looks.
|
||||
const DEFAULT_DIRECTION: [f64; 3] = [-1.0, 1.0, -1.0];
|
||||
|
||||
impl Automation {
|
||||
pub(crate) fn model_render(&mut self, a: &Args) -> Result<Vec<Content>> {
|
||||
let page = self.page(a)?;
|
||||
let width = side(a, "width")?;
|
||||
let height = side(a, "height")?;
|
||||
let direction = direction(a)?;
|
||||
let perspective = a.opt_bool("perspective")?.unwrap_or(true);
|
||||
let doc = self.doc(a)?;
|
||||
let found = doc.model_3d_annotations(page).map_err(failed)?;
|
||||
let index = match a.opt_int("model")? {
|
||||
None => *found.first().ok_or_else(|| failed(format!("page {} has no 3D model", page.saturating_add(1))))?,
|
||||
Some(n) => {
|
||||
let pos = usize::try_from(n).ok().and_then(|n| n.checked_sub(1)).ok_or_else(|| Args::wrong("model", "a positive integer"))?;
|
||||
*found
|
||||
.get(pos)
|
||||
.ok_or_else(|| ToolError::InvalidArgs(format!("page {} has {} 3D models, not {n}", page.saturating_add(1), found.len())))?
|
||||
}
|
||||
};
|
||||
let model = doc.model_3d(page, index).map_err(failed)?;
|
||||
if model.kind == Model3dKind::U3d {
|
||||
return Err(failed("this 3D model is in U3D, which can't be drawn yet; only PRC models can"));
|
||||
}
|
||||
let prc = PrcFile::parse(&model.data).map_err(|e| failed(format!("the 3D model could not be read: {e}")))?;
|
||||
let meshes = assemble(&prc).map_err(failed)?;
|
||||
let aspect = f64::from(width) / f64::from(height);
|
||||
let camera = Camera::fit_meshes(&meshes, direction, up_for(direction), perspective, aspect).map_err(failed)?;
|
||||
let image = render(&meshes, &camera, &RenderOptions { width, height, ..RenderOptions::default() }).map_err(failed)?;
|
||||
let data = encode_png(image.width, image.height, &premultiplied(image.rgba))?;
|
||||
Ok(vec![Content::Png { data, width: image.width, height: image.height }])
|
||||
}
|
||||
}
|
||||
|
||||
fn side(a: &Args, key: &str) -> Result<u32> {
|
||||
match a.opt_int(key)? {
|
||||
None => Ok(DEFAULT_SIDE),
|
||||
Some(n) => u32::try_from(n).ok().filter(|n| (1..=MAX_SIDE).contains(n)).ok_or_else(|| Args::wrong(key, &format!("between 1 and {MAX_SIDE}"))),
|
||||
}
|
||||
}
|
||||
|
||||
/// `direction`: three finite numbers, not all zero, from the eye towards the model.
|
||||
fn direction(a: &Args) -> Result<[f64; 3]> {
|
||||
let Some(v) = a.get("direction") else { return Ok(DEFAULT_DIRECTION) };
|
||||
let wrong = || Args::wrong("direction", "three numbers [x, y, z], not all zero");
|
||||
let items = v.as_array().filter(|x| x.len() == 3).ok_or_else(wrong)?;
|
||||
let mut out = [0.0; 3];
|
||||
for (o, x) in out.iter_mut().zip(items) {
|
||||
*o = x.as_f64().filter(|f| f.is_finite()).ok_or_else(wrong)?;
|
||||
}
|
||||
if out.iter().all(|c| *c == 0.0) {
|
||||
return Err(wrong());
|
||||
}
|
||||
Ok(out)
|
||||
}
|
||||
|
||||
/// Z is up, as CAD models are drawn, unless the view looks along it.
|
||||
fn up_for([x, y, z]: [f64; 3]) -> [f64; 3] {
|
||||
if x.hypot(y) <= z.abs() * 1e-6 { [0.0, 1.0, 0.0] } else { [0.0, 0.0, 1.0] }
|
||||
}
|
||||
|
||||
/// Straight RGBA to the premultiplied RGBA `encode_png` takes.
|
||||
fn premultiplied(mut rgba: Vec<u8>) -> Vec<u8> {
|
||||
for [r, g, b, alpha] in rgba.as_chunks_mut::<4>().0 {
|
||||
let a = u16::from(*alpha);
|
||||
for c in [r, g, b] {
|
||||
*c = u8::try_from((u16::from(*c) * a + 127) / 255).unwrap_or(u8::MAX);
|
||||
}
|
||||
}
|
||||
rgba
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::*;
|
||||
|
||||
#[test]
|
||||
fn premultiplying_scales_colour_by_alpha() {
|
||||
assert_eq!(premultiplied(vec![200, 100, 0, 255, 200, 100, 0, 128, 9, 9, 9, 0]), vec![200, 100, 0, 255, 100, 50, 0, 128, 0, 0, 0, 0]);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn a_view_along_z_keeps_y_up() {
|
||||
assert_eq!(up_for([0.0, 0.0, -1.0]), [0.0, 1.0, 0.0]);
|
||||
assert_eq!(up_for(DEFAULT_DIRECTION), [0.0, 0.0, 1.0]);
|
||||
}
|
||||
}
|
||||
@@ -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},
|
||||
@@ -173,6 +181,13 @@ pub fn tools() -> Vec<ToolDef> {
|
||||
"hide_text_block": { "type": "integer", "minimum": 1, "description": "Render an inline editor background without this paragraph (number from text_paragraphs, resolved as text_edit does: refused once an edit merged that paragraph into a neighbour). Does not modify the document." },
|
||||
"hide_added_text": { "type": "integer", "minimum": 1, "description": "Render a retyping background without this added text item (added index from object_list). Mutually exclusive with hide_text_block. Does not modify the document." }
|
||||
}), &["doc", "page"])),
|
||||
t("model_render", "Render a 3D model", "Draw a page's 3D model (a 3D annotation's PRC stream) to a PNG, framed to fill the image, with headlight shading on a white background. model is its 1-based position among the page's 3D models (default 1). direction is the view direction [x, y, z] from the eye towards the model (default [-1, 1, -1]); Z is up unless the view looks along Z. perspective defaults to true. U3D models can't be drawn yet and give an error. Does not modify the document.")
|
||||
.ro()
|
||||
.with(schema(json!({ "doc": doc(), "page": { "type": "integer", "minimum": 1 }, "model": { "type": "integer", "minimum": 1 },
|
||||
"width": { "type": "integer", "minimum": 1, "maximum": 4096 }, "height": { "type": "integer", "minimum": 1, "maximum": 4096 },
|
||||
"direction": { "type": "array", "items": { "type": "number" }, "minItems": 3, "maxItems": 3 },
|
||||
"perspective": { "type": "boolean" }
|
||||
}), &["doc", "page"])),
|
||||
t("object_list", "List editable objects", "List existing paragraphs, Image/Form artwork and added content once, with source kind/index references, displayed rectangles and document generation. Indexes change when content changes; use generation in object_move to reject stale references.")
|
||||
.ro().with(schema(json!({"doc":doc(),"page":{"type":"integer","minimum":1}}), &["doc","page"])),
|
||||
t("object_move", "Move objects together", "Atomically translate 1–1000 mixed references from object_list by [dx, dy] in displayed points (right/down). Preserves glyph codes, fonts, image data and relative spacing; success is one undo step. Text used as a clipping path and vertical text are refused. A bad/stale reference refuses the entire move.")
|
||||
@@ -315,6 +330,50 @@ pub fn tools() -> Vec<ToolDef> {
|
||||
}),
|
||||
&["doc", "title", "page"],
|
||||
)),
|
||||
t(
|
||||
"bookmark_export",
|
||||
"Export bookmarks",
|
||||
"The bookmark tree, or the subtree at path, as a list of nodes bookmark_import takes back unchanged. A node has title, page (1-based, null when it goes nowhere), open, and when set view ({type, values}: a destination type from ISO 32000-2 §12.3.2.2 Table 149 and its values in PDF user space, as the file stores them), color ([r, g, b], 0-1), bold, italic and children. truncated is true when bookmarks nested deeper than 33 levels were left out. With out, the tree is also written there as a JSON file {\"bookmarks\": [...]}, with \"truncated\": true when that is so; out is overwritten.",
|
||||
)
|
||||
.destructive()
|
||||
.with(schema(
|
||||
json!({ "doc": doc(), "path": path("The bookmark whose subtree to export (omit for the whole outline)"), "out": path_arg() }),
|
||||
&["doc"],
|
||||
)),
|
||||
t(
|
||||
"bookmark_import",
|
||||
"Import bookmarks",
|
||||
"Add a tree of bookmarks, as bookmark_export gives it (bookmarks) or as a JSON file it wrote (file), under a parent bookmark (or at the top level) at a position, or with replace in place of the whole outline. A bookmark whose page this document lacks is kept without a destination and listed in unmapped (1-based paths into the given tree). A view takes exactly its type's values (XYZ 3, FitR 4, FitH/FitV/FitBH/FitBV 1, Fit/FitB none). Give exactly one of bookmarks and file. A title may be empty but not missing; a key a node does not have is refused. Every node is checked before anything is written: at most 100000 bookmarks, nested at most 33 levels counting the parent's. truncated is true when the file says its export left bookmarks out. Undoable.",
|
||||
)
|
||||
.destructive()
|
||||
.with(schema(
|
||||
json!({
|
||||
"doc": doc(),
|
||||
"bookmarks": { "type": "array", "items": { "type": "object" }, "minItems": 1, "description": "Nodes as bookmark_export returns them." },
|
||||
"file": path_arg(),
|
||||
"parent": path("Parent bookmark (omit for the top level)"),
|
||||
"position": { "type": "integer", "minimum": 1, "description": "1-based position among the parent's children (default: last)." },
|
||||
"replace": { "type": "boolean", "description": "Replace the document's bookmarks instead of adding to them (default false; leave parent out)." }
|
||||
}),
|
||||
&["doc"],
|
||||
)),
|
||||
t(
|
||||
"bookmark_copy",
|
||||
"Copy bookmarks from another document",
|
||||
"Copy the bookmarks of document from (or the subtree at path) into doc, by page number: under a parent bookmark (or at the top level) at a position, or with replace in place of doc's outline. A bookmark whose page doc lacks is kept without a destination and listed in unmapped (1-based paths into the copied tree). truncated is true when bookmarks nested deeper than 33 levels were left out of the copy. Undoable.",
|
||||
)
|
||||
.destructive()
|
||||
.with(schema(
|
||||
json!({
|
||||
"doc": doc(),
|
||||
"from": { "type": "integer", "minimum": 1, "description": "Id of the document to copy from." },
|
||||
"path": path("The bookmark whose subtree to copy (omit for the whole outline)"),
|
||||
"parent": path("Parent bookmark in doc (omit for the top level)"),
|
||||
"position": { "type": "integer", "minimum": 1, "description": "1-based position among the parent's children (default: last)." },
|
||||
"replace": { "type": "boolean", "description": "Replace doc's bookmarks instead of adding to them (default false; leave parent out)." }
|
||||
}),
|
||||
&["doc", "from"],
|
||||
)),
|
||||
t("bookmark_rename", "Rename a bookmark", "Change a bookmark's title. Undoable.")
|
||||
.with(schema(json!({ "doc": doc(), "path": path("The bookmark"), "title": { "type": "string", "minLength": 1 } }), &["doc", "path", "title"])),
|
||||
t("bookmark_delete", "Delete a bookmark", "Delete a bookmark and the bookmarks under it. Undoable.")
|
||||
@@ -461,6 +520,20 @@ pub fn tools() -> Vec<ToolDef> {
|
||||
}),
|
||||
&["doc", "page", "path"],
|
||||
)),
|
||||
t("model_add", "Add a 3D model", "Add a 3D model (Acrobat: Rich Media ▸ Add 3D): the U3D or PRC file at path, recognised by its first bytes, as a 3D annotation in rect [x0, y0, x1, y1] (points from the top-left of the displayed page; each side 1–14400 pt; at most 256 MiB). Its poster, what prints and what readers show until the model is activated, is the picture at poster (a PDF page, poster_page default 1, or an image) fitted inside rect keeping its shape and centred; without poster, a frame labelled \"3D model\". activation: click (default), page_open or page_visible. name is its description (default: the file name). No views are added: readers open the model on its own default view. Undoable.")
|
||||
.with(schema(
|
||||
json!({
|
||||
"doc": doc(),
|
||||
"page": { "type": "integer", "minimum": 1 },
|
||||
"path": { "type": "string" },
|
||||
"rect": { "type": "array", "items": { "type": "number" }, "minItems": 4, "maxItems": 4 },
|
||||
"poster": { "type": "string" },
|
||||
"poster_page": { "type": "integer", "minimum": 1 },
|
||||
"activation": { "type": "string", "enum": ["click", "page_open", "page_visible"] },
|
||||
"name": { "type": "string" },
|
||||
}),
|
||||
&["doc", "page", "path", "rect"],
|
||||
)),
|
||||
t("form_set_image", "Set an image field's picture", "Show an image file (PNG, JPEG, TIFF, GIF or BMP) in an image field or button, scaled to fit and centred (what clicking an image field does). On an XFA form the picture is kept in its data too (base64, as Designer saves it) and the form shows it from there. Undoable.")
|
||||
.with(schema(json!({ "doc": doc(), "field": { "type": "string" }, "path": { "type": "string" } }), &["doc", "field", "path"])),
|
||||
t(
|
||||
@@ -562,7 +635,7 @@ 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(
|
||||
@@ -1194,9 +1267,9 @@ 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, 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.")
|
||||
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")
|
||||
@@ -1451,7 +1524,7 @@ 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 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.")
|
||||
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, up to 16 JBIG2 images sharing one symbol dictionary (/JBIG2Globals) where that is smaller still (image masks and DeviceGray images named directly, of at most 64 Mi pixels, which redaction can store again without it), 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.
|
||||
@@ -7604,6 +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"));
|
||||
@@ -10104,6 +10194,31 @@ fn changing_a_lists_options_through_tools_keeps_its_saved_selection_on_the_same_
|
||||
assert_eq!(saved_selection_indices(&dir.join("letters.pdf"), "letters"), Some(vec![0, 1]), "B and C are now items 0 and 1");
|
||||
}
|
||||
|
||||
/// Clearing a field's length limit through `form_set_props` (`"max_length": 0`) leaves it with
|
||||
/// none, even when its parent field has one it would otherwise inherit.
|
||||
#[test]
|
||||
fn clearing_a_kids_length_limit_through_tools_does_not_bring_back_its_parents() {
|
||||
let objs = [
|
||||
"<< /Type /Catalog /Pages 2 0 R /AcroForm 4 0 R >>",
|
||||
"<< /Type /Pages /Kids [3 0 R] /Count 1 /MediaBox [0 0 400 300] >>",
|
||||
"<< /Type /Page /Parent 2 0 R /Annots [6 0 R] >>",
|
||||
"<< /Fields [5 0 R] /DA (/Helv 12 Tf 0 g) /DR << /Font << /Helv 7 0 R >> >> >>",
|
||||
"<< /T (address) /FT /Tx /MaxLen 3 /Kids [6 0 R] >>",
|
||||
"<< /Type /Annot /Subtype /Widget /T (city) /Parent 5 0 R /MaxLen 8 /Rect [10 250 150 268] /P 3 0 R >>",
|
||||
"<< /Type /Font /Subtype /Type1 /BaseFont /Helvetica /Encoding /WinAnsiEncoding >>",
|
||||
];
|
||||
let dir = workdir("kid-max-len");
|
||||
std::fs::write(dir.join("form.pdf"), pdf_of(&objs)).unwrap();
|
||||
let mut a = auto(&dir);
|
||||
let doc = ok(&mut a, "doc_open", json!({ "path": "form.pdf" }))["doc"].as_u64().unwrap();
|
||||
ok(&mut a, "form_set_props", json!({ "doc": doc, "field": "address.city", "max_length": 0 }));
|
||||
ok(&mut a, "form_fill", json!({ "doc": doc, "values": { "address.city": "Absalom" } }));
|
||||
let fields = ok(&mut a, "form_fields", json!({ "doc": doc }));
|
||||
let city = fields["fields"].as_array().unwrap().iter().find(|f| f["name"] == "address.city").unwrap().clone();
|
||||
assert!(city.get("max_length").is_none(), "no limit, not the parent's 3: {city}");
|
||||
assert_eq!(city["value"], "Absalom", "the value is not cut to the parent's 3 characters");
|
||||
}
|
||||
|
||||
/// Clearing a field's default through `form_set_props` (`"default": ""`) leaves it with none,
|
||||
/// even when its parent field has one it would otherwise inherit.
|
||||
#[test]
|
||||
@@ -10523,3 +10638,197 @@ 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();
|
||||
}
|
||||
|
||||
/// Export, then import into another document and copy between open documents: the tree comes
|
||||
/// back unchanged, a page the target lacks is reported, and the import undoes in one step.
|
||||
#[test]
|
||||
fn bookmarks_export_import_and_copy_between_documents() {
|
||||
let dir = workdir("bookmark-io");
|
||||
let mut a = auto(&dir);
|
||||
let src = ok(&mut a, "doc_open", json!({ "path": "a.pdf" }))["doc"].as_u64().unwrap();
|
||||
ok(&mut a, "bookmark_add", json!({ "doc": src, "title": "Intro", "page": 1 }));
|
||||
ok(&mut a, "bookmark_add", json!({ "doc": src, "title": "Detail", "page": 3, "parent": [1] }));
|
||||
ok(&mut a, "bookmark_add", json!({ "doc": src, "title": "End", "page": 2 }));
|
||||
ok(&mut a, "bookmark_set_style", json!({ "doc": src, "path": [1], "color": [1, 0, 0], "bold": true }));
|
||||
let exported = ok(&mut a, "bookmark_export", json!({ "doc": src, "out": "marks.json" }));
|
||||
assert_eq!(exported["truncated"], false);
|
||||
let tree = exported["bookmarks"].clone();
|
||||
assert_eq!((tree[0]["title"].clone(), tree[0]["color"].clone(), tree[0]["bold"].clone()), (json!("Intro"), json!([1.0, 0.0, 0.0]), json!(true)));
|
||||
assert_eq!((tree[0]["children"][0]["title"].clone(), tree[0]["children"][0]["page"].clone()), (json!("Detail"), json!(3)));
|
||||
assert_eq!(tree[0]["view"]["type"], "XYZ");
|
||||
let subtree = ok(&mut a, "bookmark_export", json!({ "doc": src, "path": [1, 1] }))["bookmarks"].clone();
|
||||
assert_eq!(subtree, json!([tree[0]["children"][0]]));
|
||||
|
||||
// b.pdf has two pages: Detail goes to the third, so it arrives without a destination.
|
||||
let dst = ok(&mut a, "doc_open", json!({ "path": "b.pdf" }))["doc"].as_u64().unwrap();
|
||||
let imported = ok(&mut a, "bookmark_import", json!({ "doc": dst, "file": "marks.json" }));
|
||||
assert_eq!(imported["unmapped"], json!([[1, 1]]));
|
||||
let back = ok(&mut a, "bookmark_export", json!({ "doc": dst }))["bookmarks"].clone();
|
||||
assert_eq!(back[0]["children"][0]["page"], json!(null));
|
||||
assert_eq!((back[0]["title"].clone(), back[1].clone()), (tree[0]["title"].clone(), tree[1].clone()));
|
||||
ok(&mut a, "edit_undo", json!({ "doc": dst }));
|
||||
assert_eq!(ok(&mut a, "bookmark_list", json!({ "doc": dst }))["bookmarks"], json!([]));
|
||||
|
||||
// Into a document with every page, the tree is unchanged, wherever it is copied from.
|
||||
let same = ok(&mut a, "doc_open", json!({ "path": "a.pdf" }))["doc"].as_u64().unwrap();
|
||||
ok(&mut a, "bookmark_add", json!({ "doc": same, "title": "Old", "page": 1 }));
|
||||
let copied = ok(&mut a, "bookmark_copy", json!({ "doc": same, "from": src, "replace": true }));
|
||||
assert_eq!(copied["unmapped"], json!([]));
|
||||
assert_eq!(ok(&mut a, "bookmark_export", json!({ "doc": same }))["bookmarks"], tree);
|
||||
ok(&mut a, "bookmark_import", json!({ "doc": same, "bookmarks": subtree, "parent": [2], "position": 1 }));
|
||||
assert_eq!(ok(&mut a, "bookmark_list", json!({ "doc": same }))["bookmarks"][1]["children"][0]["title"], "Detail");
|
||||
}
|
||||
|
||||
/// A one-page document whose outline has an untitled item, a /FitR destination with three of
|
||||
/// its four numbers, and a chain nested `deep` levels below them.
|
||||
fn odd_outline(deep: usize) -> Vec<u8> {
|
||||
let first_deep = 7;
|
||||
let mut objs = vec![
|
||||
"<< /Type /Catalog /Pages 2 0 R /Outlines 4 0 R >>".to_string(),
|
||||
"<< /Type /Pages /Kids [3 0 R] /Count 1 /MediaBox [0 0 200 300] >>".into(),
|
||||
"<< /Type /Page /Parent 2 0 R >>".into(),
|
||||
"<< /Type /Outlines /First 5 0 R /Last 6 0 R >>".into(),
|
||||
"<< /Title () /Parent 4 0 R /Next 6 0 R /Dest [3 0 R /Fit] >>".into(),
|
||||
format!(
|
||||
"<< /Title (Short) /Parent 4 0 R /Prev 5 0 R /Dest [3 0 R /FitR 0 0 10]{} >>",
|
||||
if deep > 0 { format!(" /First {first_deep} 0 R /Last {first_deep} 0 R") } else { String::new() }
|
||||
),
|
||||
];
|
||||
for i in 0..deep {
|
||||
let (me, parent) = (first_deep + i, if i == 0 { 6 } else { first_deep + i - 1 });
|
||||
let child = if i + 1 < deep { format!(" /First {0} 0 R /Last {0} 0 R", me + 1) } else { String::new() };
|
||||
objs.push(format!("<< /Title (Level) /Parent {parent} 0 R /Dest [3 0 R /Fit]{child} >>"));
|
||||
}
|
||||
pdf_of(&objs.iter().map(String::as_str).collect::<Vec<_>>())
|
||||
}
|
||||
|
||||
/// What a real file holds and the JSON form can't say exactly still copies and round-trips: an
|
||||
/// empty title stays empty, a short /FitR keeps its page and drops the view, and bookmarks past
|
||||
/// the listing depth are reported as left out at every step.
|
||||
#[test]
|
||||
fn odd_bookmarks_round_trip_and_a_cut_tree_says_so() {
|
||||
let dir = workdir("bookmark-io-odd");
|
||||
std::fs::write(dir.join("odd.pdf"), odd_outline(0)).unwrap();
|
||||
std::fs::write(dir.join("deep.pdf"), odd_outline(40)).unwrap();
|
||||
let mut a = auto(&dir);
|
||||
let src = ok(&mut a, "doc_open", json!({ "path": "odd.pdf" }))["doc"].as_u64().unwrap();
|
||||
let tree = ok(&mut a, "bookmark_export", json!({ "doc": src, "out": "odd.json" }))["bookmarks"].clone();
|
||||
assert_eq!((tree[0]["title"].clone(), tree[1]["page"].clone(), tree[1].get("view")), (json!(""), json!(1), None));
|
||||
let dst = ok(&mut a, "doc_open", json!({ "path": "b.pdf" }))["doc"].as_u64().unwrap();
|
||||
assert_eq!(ok(&mut a, "bookmark_import", json!({ "doc": dst, "file": "odd.json", "replace": true }))["truncated"], false);
|
||||
// A destination with no view is written as XYZ with nulls: the same page, the reader's view.
|
||||
let back = ok(&mut a, "bookmark_export", json!({ "doc": dst }))["bookmarks"].clone();
|
||||
assert_eq!((back[0].clone(), back[1]["title"].clone(), back[1]["page"].clone()), (tree[0].clone(), json!("Short"), json!(1)));
|
||||
assert_eq!(back[1]["view"], json!({ "type": "XYZ", "values": [null, null, null] }));
|
||||
let copied = ok(&mut a, "bookmark_copy", json!({ "doc": dst, "from": src, "replace": true }));
|
||||
assert_eq!((copied["unmapped"].clone(), copied["truncated"].clone()), (json!([]), json!(false)));
|
||||
match a.call("bookmark_export", &json!({ "doc": src, "path": [3] })) {
|
||||
Err(ToolError::Failed(m)) => assert!(m.contains("no bookmark at [3]"), "{m}"),
|
||||
other => panic!("expected no bookmark, got {other:?}"),
|
||||
}
|
||||
|
||||
let deep = ok(&mut a, "doc_open", json!({ "path": "deep.pdf" }))["doc"].as_u64().unwrap();
|
||||
assert_eq!(ok(&mut a, "bookmark_export", json!({ "doc": deep, "out": "deep.json" }))["truncated"], true);
|
||||
let saved: Value = serde_json::from_slice(&std::fs::read(dir.join("deep.json")).unwrap()).unwrap();
|
||||
assert_eq!(saved["truncated"], true);
|
||||
assert_eq!(ok(&mut a, "bookmark_import", json!({ "doc": dst, "file": "deep.json", "replace": true }))["truncated"], true);
|
||||
assert_eq!(ok(&mut a, "bookmark_copy", json!({ "doc": dst, "from": deep, "replace": true }))["truncated"], true);
|
||||
let export = tools().into_iter().find(|t| t.name == "bookmark_export").unwrap();
|
||||
assert!(export.destructive && !export.read_only, "bookmark_export overwrites out");
|
||||
std::fs::remove_dir_all(dir).unwrap();
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn a_misspelt_bookmark_key_is_refused_not_dropped() {
|
||||
let dir = workdir("bookmark-io-key");
|
||||
let mut a = auto(&dir);
|
||||
let doc = ok(&mut a, "doc_open", json!({ "path": "a.pdf" }))["doc"].as_u64().unwrap();
|
||||
let tree = json!([{ "title": "Parent", "children": [{ "title": "Red", "page": 1, "colour": [1, 0, 0] }] }]);
|
||||
match a.call("bookmark_import", &json!({ "doc": doc, "bookmarks": tree })) {
|
||||
Err(ToolError::InvalidArgs(m)) => assert!(m.contains("[1, 1]") && m.contains("\"colour\""), "{m}"),
|
||||
other => panic!("expected InvalidArgs, got {other:?}"),
|
||||
}
|
||||
assert_eq!(ok(&mut a, "bookmark_list", json!({ "doc": doc }))["bookmarks"], json!([]));
|
||||
std::fs::remove_dir_all(dir).unwrap();
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn a_bad_bookmark_tree_is_refused_whole_and_names_the_node() {
|
||||
let dir = workdir("bookmark-io-bad");
|
||||
let mut a = auto(&dir);
|
||||
let doc = ok(&mut a, "doc_open", json!({ "path": "a.pdf" }))["doc"].as_u64().unwrap();
|
||||
let refused = |a: &mut Automation, bookmarks: Value| match a.call("bookmark_import", &json!({ "doc": doc, "bookmarks": bookmarks })) {
|
||||
Err(ToolError::InvalidArgs(m)) => m,
|
||||
other => panic!("expected InvalidArgs, got {other:?}"),
|
||||
};
|
||||
let fine = json!({ "title": "Fine", "page": 1 });
|
||||
let m = refused(&mut a, json!([fine, { "title": "Parent", "children": [{ "page": 1 }] }]));
|
||||
assert!(m.contains("[2, 1]") && m.contains("title"), "{m}");
|
||||
let m = refused(&mut a, json!([{ "title": 5 }]));
|
||||
assert!(m.contains("[1]") && m.contains("title"), "{m}");
|
||||
let m = refused(&mut a, json!([fine, { "title": "Bad", "page": 0 }]));
|
||||
assert!(m.contains("[2]") && m.contains("page"), "{m}");
|
||||
let m = refused(&mut a, json!([{ "title": "Bad", "color": [2, 0, 0] }]));
|
||||
assert!(m.contains("color"), "{m}");
|
||||
let m = refused(&mut a, json!([{ "title": "Bad", "view": { "type": "XYZ", "values": [1, 2, 3, 4, 5] } }]));
|
||||
assert!(m.contains("view"), "{m}");
|
||||
let mut deep = json!({ "title": "Leaf" });
|
||||
for _ in 0..40 {
|
||||
deep = json!({ "title": "Level", "children": [deep] });
|
||||
}
|
||||
assert!(refused(&mut a, json!([deep])).contains("33 levels"));
|
||||
let m = refused(&mut a, json!([fine, { "title": "Z", "page": 1, "view": { "type": "Zoom" } }]));
|
||||
assert!(m.contains("[2]") && m.contains("XYZ (3 values"), "{m}");
|
||||
let m = refused(&mut a, json!([fine, { "title": "Z", "page": 1, "view": { "type": "FitH", "values": [1, 2] } }]));
|
||||
assert!(m.contains("[2]") && m.contains("FitH view takes 1"), "{m}");
|
||||
let m = refused(&mut a, json!([{ "title": "R", "view": { "type": "FitR", "values": [0, null, 1, 1] } }]));
|
||||
assert!(m.contains("all four"), "{m}");
|
||||
assert!(matches!(a.call("bookmark_import", &json!({ "doc": doc })), Err(ToolError::InvalidArgs(_))));
|
||||
assert!(matches!(a.call("bookmark_import", &json!({ "doc": doc, "bookmarks": [fine], "file": "x.json" })), Err(ToolError::InvalidArgs(_))));
|
||||
// A real bookmark file outside the root is refused for being outside, not for being missing.
|
||||
let outside = dir.with_extension("outside.json");
|
||||
std::fs::write(&outside, br#"{"bookmarks": [{"title": "Outside", "page": 1}]}"#).unwrap();
|
||||
let name = format!("../{}", outside.file_name().unwrap().to_string_lossy());
|
||||
match a.call("bookmark_import", &json!({ "doc": doc, "file": name })) {
|
||||
Err(ToolError::Failed(m)) => assert!(m.contains("outside the allowed directory"), "{m}"),
|
||||
other => panic!("expected the root to refuse it, got {other:?}"),
|
||||
}
|
||||
let _ = std::fs::remove_file(&outside);
|
||||
let out = dir.with_extension("out.json");
|
||||
let name = format!("../{}", out.file_name().unwrap().to_string_lossy());
|
||||
match a.call("bookmark_export", &json!({ "doc": doc, "out": name })) {
|
||||
Err(ToolError::Failed(m)) => assert!(m.contains("outside the allowed directory"), "{m}"),
|
||||
other => panic!("expected the root to refuse it, got {other:?}"),
|
||||
}
|
||||
assert!(!out.exists());
|
||||
assert_eq!(ok(&mut a, "bookmark_list", json!({ "doc": doc }))["bookmarks"], json!([]));
|
||||
}
|
||||
|
||||
@@ -145,6 +145,8 @@ fn tools_that_read_a_path_are_held_to_the_read_root() {
|
||||
ok(&mut server, "doc_open", json!({"path": s(&base.join("in/a.pdf"))}));
|
||||
let (secret, pic, gone) = (s(&base.join("outside/secret.pdf")), s(&base.join("outside/pic.png")), s(&base.join("outside/gone.bin")));
|
||||
let out = s(&base.join("out/result.pdf"));
|
||||
std::fs::write(base.join("in/m.prc"), b"PRC model").unwrap();
|
||||
let model = s(&base.join("in/m.prc"));
|
||||
for (tool, args) in [
|
||||
("page_insert_file", json!({"doc": 1, "path": secret, "at": 1})),
|
||||
("page_replace", json!({"doc": 1, "pages": [1], "path": secret})),
|
||||
@@ -153,6 +155,8 @@ fn tools_that_read_a_path_are_held_to_the_read_root() {
|
||||
("doc_create", json!({"from": "images", "paths": [pic]})),
|
||||
("stamp_custom", json!({"doc": 1, "page": 1, "path": secret, "at": [10, 10]})),
|
||||
("stamp_custom", json!({"doc": 1, "page": 1, "path": secret, "rect": [10, 10, 493, 300]})),
|
||||
("model_add", json!({"doc": 1, "page": 1, "path": secret, "rect": [10, 10, 100, 100]})),
|
||||
("model_add", json!({"doc": 1, "page": 1, "path": model, "rect": [10, 10, 100, 100], "poster": pic})),
|
||||
("page_add_image", json!({"doc": 1, "page": 1, "path": pic})),
|
||||
("image_edit", json!({"doc": 1, "page": 1, "image": 1, "action": "replace", "path": pic})),
|
||||
("comment_add", json!({"doc": 1, "page": 1, "type": "attachment", "at": [10, 10], "path": secret})),
|
||||
|
||||
@@ -8,6 +8,8 @@ mod batch;
|
||||
mod button_caption;
|
||||
mod form_bulk;
|
||||
mod hostile_args;
|
||||
mod model_3d;
|
||||
mod model_render;
|
||||
mod optimize_content_boundaries;
|
||||
mod redact_after_stray_q_form;
|
||||
mod redact_text_after_q;
|
||||
|
||||
@@ -0,0 +1,120 @@
|
||||
//! `model_add` embeds a U3D or PRC model as a 3D annotation (ISO 32000-2 §13.6.2) with a poster,
|
||||
//! end to end: the tool, the saved file, undo, and the refusals.
|
||||
|
||||
use pdfcraft_automation::{Automation, Content, ToolError};
|
||||
use pdfcraft_cos::{Dict, Document, Object, Stream};
|
||||
use serde_json::{Value, json};
|
||||
|
||||
fn tool(a: &mut Automation, name: &str, args: Value) -> Value {
|
||||
match a.call(name, &args).unwrap().remove(0) {
|
||||
Content::Json(value) => value,
|
||||
other => panic!("expected JSON: {other:?}"),
|
||||
}
|
||||
}
|
||||
|
||||
fn png(w: u32, h: u32) -> Vec<u8> {
|
||||
let mut out = Vec::new();
|
||||
let mut encoder = png::Encoder::new(&mut out, w, h);
|
||||
encoder.set_color(png::ColorType::Rgb);
|
||||
encoder.set_depth(png::BitDepth::Eight);
|
||||
encoder.write_header().unwrap().write_image_data(&vec![90; (w * h * 3) as usize]).unwrap();
|
||||
out
|
||||
}
|
||||
|
||||
fn stream(doc: &Document, obj: &Object) -> Stream {
|
||||
match doc.resolve(obj).as_ref() {
|
||||
Object::Stream(s) => s.clone(),
|
||||
other => panic!("expected a stream: {other:?}"),
|
||||
}
|
||||
}
|
||||
|
||||
/// The 3D annotations on the first page of the saved file.
|
||||
fn saved_3d(dir: &std::path::Path) -> (Document, Vec<Dict>) {
|
||||
let doc = Document::open(std::sync::Arc::new(std::fs::read(dir.join("out.pdf")).unwrap())).unwrap();
|
||||
let page = &pdfcraft_model::pages(&doc)[0];
|
||||
let list = page.dict.get(b"Annots").map(|a| doc.resolve(a).as_array().cloned().unwrap()).unwrap_or_default();
|
||||
let found = list.iter().map(|o| doc.resolve(o).as_dict().unwrap().clone()).filter(|d| d.name(b"Subtype") == Some(&b"3D"[..])).collect();
|
||||
(doc, found)
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn model_add_embeds_the_model_with_a_fitted_poster() {
|
||||
let dir = tempfile::tempdir().unwrap();
|
||||
let mut prc = b"PRC".to_vec();
|
||||
prc.extend_from_slice(&[7; 200]);
|
||||
std::fs::write(dir.path().join("bracket.prc"), &prc).unwrap();
|
||||
std::fs::write(dir.path().join("poster.png"), png(80, 40)).unwrap();
|
||||
let mut a = Automation::new().with_root(dir.path()).unwrap();
|
||||
let doc = tool(&mut a, "doc_create", json!({ "from": "blank", "width": 600, "height": 800 }))["doc"].as_u64().unwrap();
|
||||
// A 300 × 300 box from the top-left of the page: user space [100, 400, 400, 700].
|
||||
let call =
|
||||
json!({ "doc": doc, "page": 1, "path": "bracket.prc", "rect": [100, 100, 400, 400], "poster": "poster.png", "activation": "page_open" });
|
||||
tool(&mut a, "model_add", call);
|
||||
tool(&mut a, "doc_save", json!({ "doc": doc, "path": "out.pdf" }));
|
||||
|
||||
let (saved, found) = saved_3d(dir.path());
|
||||
let [annot] = found.as_slice() else { panic!("one 3D annotation: {found:?}") };
|
||||
let rect: Vec<f64> = annot.get(b"Rect").unwrap().as_array().unwrap().iter().filter_map(Object::as_f64).collect();
|
||||
assert_eq!(rect, [100.0, 400.0, 400.0, 700.0]);
|
||||
assert_eq!(annot.get(b"Contents").and_then(Object::as_string).map(|s| s.to_text()).as_deref(), Some("bracket"));
|
||||
let model = stream(&saved, annot.get(b"3DD").unwrap());
|
||||
assert_eq!(model.dict.name(b"Type"), Some(&b"3D"[..]));
|
||||
assert_eq!(model.dict.name(b"Subtype"), Some(&b"PRC"[..]));
|
||||
assert_eq!(model.dict.name(b"Filter"), Some(&b"FlateDecode"[..]));
|
||||
assert_eq!(model.decoded().unwrap().to_vec(), prc, "the model is stored unchanged");
|
||||
let activation = saved.resolve(annot.get(b"3DA").unwrap()).as_dict().unwrap().clone();
|
||||
assert_eq!(activation.name(b"A"), Some(&b"PO"[..]));
|
||||
// The 80 × 40 picture fitted in the 300 × 300 box: 300 × 150, centred top to bottom.
|
||||
let ap = saved.resolve(annot.get(b"AP").unwrap()).as_dict().unwrap().clone();
|
||||
let poster = stream(&saved, ap.get(b"N").unwrap());
|
||||
let content = String::from_utf8(poster.decoded().unwrap().to_vec()).unwrap();
|
||||
assert!(content.contains("300 0 0 150 100 475 cm /Pic Do"), "{content}");
|
||||
|
||||
assert_eq!(tool(&mut a, "edit_undo", json!({ "doc": doc }))["undone"], "Add 3D model");
|
||||
tool(&mut a, "doc_save", json!({ "doc": doc, "path": "out.pdf" }));
|
||||
assert!(saved_3d(dir.path()).1.is_empty(), "undo removes it");
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn model_add_without_a_poster_draws_a_labelled_frame_and_activates_on_click() {
|
||||
let dir = tempfile::tempdir().unwrap();
|
||||
let mut u3d = b"U3D\0".to_vec();
|
||||
u3d.extend_from_slice(&[0; 60]);
|
||||
std::fs::write(dir.path().join("part.u3d"), &u3d).unwrap();
|
||||
let mut a = Automation::new().with_root(dir.path()).unwrap();
|
||||
let doc = tool(&mut a, "doc_create", json!({ "from": "blank", "width": 600, "height": 800 }))["doc"].as_u64().unwrap();
|
||||
tool(&mut a, "model_add", json!({ "doc": doc, "page": 1, "path": "part.u3d", "rect": [50, 50, 250, 200], "name": "Part" }));
|
||||
tool(&mut a, "doc_save", json!({ "doc": doc, "path": "out.pdf" }));
|
||||
|
||||
let (saved, found) = saved_3d(dir.path());
|
||||
let [annot] = found.as_slice() else { panic!("one 3D annotation: {found:?}") };
|
||||
assert_eq!(stream(&saved, annot.get(b"3DD").unwrap()).dict.name(b"Subtype"), Some(&b"U3D"[..]));
|
||||
let activation = saved.resolve(annot.get(b"3DA").unwrap()).as_dict().unwrap().clone();
|
||||
assert_eq!(activation.name(b"A"), Some(&b"XA"[..]), "the standard's default, stated");
|
||||
let ap = saved.resolve(annot.get(b"AP").unwrap()).as_dict().unwrap().clone();
|
||||
let content = String::from_utf8(stream(&saved, ap.get(b"N").unwrap()).decoded().unwrap().to_vec()).unwrap();
|
||||
assert!(content.contains("re S") && content.contains("(3D model) Tj"), "{content}");
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn model_add_refuses_what_is_not_a_model_and_adds_nothing() {
|
||||
let dir = tempfile::tempdir().unwrap();
|
||||
std::fs::write(dir.path().join("notes.txt"), b"PR not a model").unwrap();
|
||||
std::fs::write(dir.path().join("part.prc"), b"PRC....").unwrap();
|
||||
let mut a = Automation::new().with_root(dir.path()).unwrap();
|
||||
let doc = tool(&mut a, "doc_create", json!({ "from": "blank", "width": 600, "height": 800 }))["doc"].as_u64().unwrap();
|
||||
let not_a_model = a.call("model_add", &json!({ "doc": doc, "page": 1, "path": "notes.txt", "rect": [10, 10, 100, 100] }));
|
||||
assert!(matches!(¬_a_model, Err(ToolError::Failed(m)) if m.contains("U3D") && m.contains("PRC")), "{not_a_model:?}");
|
||||
for (args, why) in [
|
||||
(json!({ "rect": [10, 10, 10, 100] }), "zero width"),
|
||||
(json!({ "rect": [0, 0, 20000, 100] }), "wider than a PDF page can be"),
|
||||
(json!({}), "no rect"),
|
||||
(json!({ "rect": [10, 10, 100, 100], "activation": "now" }), "an unknown activation"),
|
||||
] {
|
||||
let mut call = json!({ "doc": doc, "page": 1, "path": "part.prc" });
|
||||
call.as_object_mut().unwrap().extend(args.as_object().unwrap().clone());
|
||||
assert!(matches!(a.call("model_add", &call), Err(ToolError::InvalidArgs(_))), "{why}");
|
||||
}
|
||||
tool(&mut a, "doc_save", json!({ "doc": doc, "path": "out.pdf" }));
|
||||
assert!(saved_3d(dir.path()).1.is_empty());
|
||||
}
|
||||
@@ -0,0 +1,112 @@
|
||||
//! `model_render` draws a page's 3D model headlessly: a synthetic PDF holding a synthetic PRC.
|
||||
|
||||
use std::path::PathBuf;
|
||||
|
||||
use pdfcraft_automation::{Automation, Content};
|
||||
use serde_json::{Value, json};
|
||||
|
||||
/// One triangle at z = 0 facing +z, with corners (-1,-1), (1,-1) and (0,1), as a PRC file of one
|
||||
/// file structure with no product tree, in hexadecimal for the stream's `/ASCIIHexDecode`.
|
||||
const TRIANGLE_PRC_HEX: &str = "505243c91f0000c91f00000100000002000000030000000400000000000000000000000000000000000000010000000500000006000000070000000800000000000000060000006b0000009a000000a3000000ab000000cd000000d5000000dd000000e500000000000000505243c91f0000c91f0000050000000600000007000000080000000000000000000000000000000000000000000000789c63000000010001789c030000000001789c9b71c087758da2422b43084fe3140e038713464cd759381a162800006ed70828789c030000000001789c030000000001789c030000000001";
|
||||
|
||||
/// A one-page PDF whose page holds a 3D annotation over a stream of `/Subtype /{subtype}`.
|
||||
fn pdf(subtype: &str, hex: &str) -> Vec<u8> {
|
||||
let stream = format!("<< /Type /3D /Subtype /{subtype} /Filter /ASCIIHexDecode /Length {} >>\nstream\n{hex}>\nendstream", hex.len() + 1);
|
||||
let objs: Vec<String> = vec![
|
||||
"<< /Type /Catalog /Pages 2 0 R >>".into(),
|
||||
"<< /Type /Pages /Kids [3 0 R] /Count 1 /MediaBox [0 0 200 200] >>".into(),
|
||||
"<< /Type /Page /Parent 2 0 R /Annots [<< /Type /Annot /Subtype /Square /Rect [0 0 10 10] >> 4 0 R] >>".into(),
|
||||
"<< /Type /Annot /Subtype /3D /Rect [20 20 180 180] /3DD 5 0 R >>".into(),
|
||||
stream,
|
||||
];
|
||||
let mut out = b"%PDF-1.7\n".to_vec();
|
||||
let mut offsets = Vec::new();
|
||||
for (i, o) in objs.iter().enumerate() {
|
||||
offsets.push(out.len());
|
||||
out.extend_from_slice(format!("{} 0 obj\n{o}\nendobj\n", i + 1).as_bytes());
|
||||
}
|
||||
let xref = out.len();
|
||||
out.extend_from_slice(format!("xref\n0 {}\n0000000000 65535 f \n", objs.len() + 1).as_bytes());
|
||||
for o in offsets {
|
||||
out.extend_from_slice(format!("{o:010} 00000 n \n").as_bytes());
|
||||
}
|
||||
out.extend_from_slice(format!("trailer\n<< /Size {} /Root 1 0 R >>\nstartxref\n{xref}\n%%EOF\n", objs.len() + 1).as_bytes());
|
||||
out
|
||||
}
|
||||
|
||||
/// A fresh folder with `prc.pdf` and `u3d.pdf` in `in`, `outside.pdf` beside it, and an
|
||||
/// automation rooted at `in`.
|
||||
fn setup(test: &str) -> (PathBuf, Automation) {
|
||||
let dir = std::env::temp_dir().join(format!("pdfcraft-model3d-{test}-{}", std::process::id()));
|
||||
let _ = std::fs::remove_dir_all(&dir);
|
||||
std::fs::create_dir_all(dir.join("in")).unwrap();
|
||||
std::fs::write(dir.join("in/prc.pdf"), pdf("PRC", TRIANGLE_PRC_HEX)).unwrap();
|
||||
std::fs::write(dir.join("in/u3d.pdf"), pdf("U3D", "553344")).unwrap();
|
||||
std::fs::write(dir.join("outside.pdf"), pdf("PRC", TRIANGLE_PRC_HEX)).unwrap();
|
||||
let a = Automation::new().with_root(dir.join("in")).unwrap();
|
||||
(dir, a)
|
||||
}
|
||||
|
||||
fn open(a: &mut Automation, path: &str) -> u64 {
|
||||
match a.call("doc_open", &json!({ "path": path })).unwrap().remove(0) {
|
||||
Content::Json(v) => v["doc"].as_u64().unwrap(),
|
||||
other => panic!("expected JSON: {other:?}"),
|
||||
}
|
||||
}
|
||||
|
||||
/// The RGB of pixel (x, y) of a PNG.
|
||||
fn rgb(data: &[u8], x: usize, y: usize) -> [u8; 3] {
|
||||
let mut reader = png::Decoder::new(std::io::Cursor::new(data)).read_info().unwrap();
|
||||
let mut pixels = vec![0; reader.output_buffer_size().unwrap()];
|
||||
let info = reader.next_frame(&mut pixels).unwrap();
|
||||
let channels = info.line_size / info.width as usize;
|
||||
let at = y * info.line_size + x * channels;
|
||||
[pixels[at], pixels[at + 1], pixels[at + 2]]
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn a_prc_model_is_drawn_over_the_background() {
|
||||
let (_dir, mut a) = setup("prc");
|
||||
let doc = open(&mut a, "prc.pdf");
|
||||
let args = json!({ "doc": doc, "page": 1, "width": 64, "height": 48, "direction": [0, 0, -1], "perspective": false });
|
||||
let out = a.call("model_render", &args).unwrap();
|
||||
let Content::Png { data, width, height } = &out[0] else { panic!("expected a PNG") };
|
||||
assert_eq!((*width, *height), (64, 48));
|
||||
assert_eq!(rgb(data, 0, 0), [255, 255, 255], "the corner is background");
|
||||
assert_eq!(rgb(data, 32, 24), [190, 192, 200], "the centre is the triangle, lit head on");
|
||||
// In perspective the headlight meets the face at a slight angle, so only not-background holds.
|
||||
let out = a.call("model_render", &json!({ "doc": doc, "page": 1, "width": 64, "height": 48, "direction": [0, 0, -1] })).unwrap();
|
||||
let Content::Png { data, .. } = &out[0] else { panic!("expected a PNG") };
|
||||
assert_ne!(rgb(data, 32, 24), [255, 255, 255], "the centre is drawn in perspective too");
|
||||
// The same model named explicitly, and the default isometric view, both draw.
|
||||
assert!(a.call("model_render", &json!({ "doc": doc, "page": 1, "model": 1 })).is_ok());
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn a_u3d_model_or_a_missing_one_is_a_clear_error() {
|
||||
let (_dir, mut a) = setup("u3d");
|
||||
let doc = open(&mut a, "u3d.pdf");
|
||||
let err = a.call("model_render", &json!({ "doc": doc, "page": 1 })).unwrap_err().to_string();
|
||||
assert!(err.contains("U3D"), "{err}");
|
||||
let doc = open(&mut a, "prc.pdf");
|
||||
let err = a.call("model_render", &json!({ "doc": doc, "page": 1, "model": 2 })).unwrap_err().to_string();
|
||||
assert!(err.contains("has 1 3D models, not 2"), "{err}");
|
||||
for bad in [json!({ "direction": [0, 0, 0] }), json!({ "direction": [1, 2] }), json!({ "width": 0 }), json!({ "height": 5000 })] {
|
||||
let mut args = json!({ "doc": doc, "page": 1 });
|
||||
args.as_object_mut().unwrap().extend(bad.as_object().unwrap().clone());
|
||||
assert!(a.call("model_render", &args).is_err(), "{bad}");
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn a_model_outside_the_root_is_never_opened_to_be_drawn() {
|
||||
let (dir, mut a) = setup("root");
|
||||
let outside = dir.join("outside.pdf");
|
||||
for path in [Value::from("../outside.pdf"), Value::from(outside.to_string_lossy().into_owned())] {
|
||||
assert!(a.call("doc_open", &json!({ "path": path })).is_err(), "{path} lies outside the root");
|
||||
}
|
||||
// The tool takes no path of its own: only a document opened inside the root reaches it.
|
||||
assert!(a.call("model_render", &json!({ "doc": 1, "page": 1 })).is_err());
|
||||
let doc = open(&mut a, "prc.pdf");
|
||||
assert!(a.call("model_render", &json!({ "doc": doc, "page": 1 })).is_ok());
|
||||
}
|
||||
@@ -25,6 +25,12 @@ 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 most pixels an image redaction decodes, to clear the ones under a mark or to store again
|
||||
/// without the `/JBIG2Globals` it shares with a redacted image (`pdfcraft_redact`). Optimize has
|
||||
/// JBIG2 images share a dictionary only within it (`pdfcraft_optimize`), so that redaction can
|
||||
/// store each of them again: one it couldn't would refuse the redaction.
|
||||
pub const MAX_REDACTED_IMAGE_PIXELS: u64 = 64 << 20;
|
||||
|
||||
/// 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;
|
||||
|
||||
@@ -19,6 +19,7 @@ mod reader;
|
||||
mod state;
|
||||
mod xref;
|
||||
|
||||
pub(crate) use objects::Held;
|
||||
#[cfg(test)]
|
||||
pub(crate) use reader::find;
|
||||
#[cfg(test)]
|
||||
@@ -27,7 +28,7 @@ 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 +48,7 @@ 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`).
|
||||
@@ -62,6 +63,10 @@ pub struct Document {
|
||||
security: Option<Arc<pdfcraft_crypt::SecurityHandler>>,
|
||||
/// Object number of the `/Encrypt` dictionary (never encrypted itself).
|
||||
encrypt_num: Option<u32>,
|
||||
/// What that dictionary and `/ID` refer to, which the key comes from, and so is as stored.
|
||||
encrypt_members: Arc<HashSet<u32>>,
|
||||
/// Object numbers a scan of the file didn't find: the file doesn't change, so it never will.
|
||||
unfound: Arc<Mutex<HashSet<u32>>>,
|
||||
/// Encryption was added, changed or removed since opening: only a full save can apply it.
|
||||
encryption_changed: bool,
|
||||
/// Set by edits that must not leave earlier revisions in the file (redaction).
|
||||
|
||||
@@ -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,
|
||||
@@ -156,12 +156,16 @@ impl Document {
|
||||
self.try_get(r.num).unwrap_or_else(|_| Arc::new(Object::Null))
|
||||
}
|
||||
|
||||
/// Follow a reference if `o` is one; otherwise return `o` itself.
|
||||
/// Follow a reference if `o` is one; otherwise return `o` itself. An object can be nothing but
|
||||
/// a reference to another, which is followed too, up to [`MAX_REFERENCE_HOPS`] of them.
|
||||
pub fn resolve(&self, o: &Object) -> Arc<Object> {
|
||||
match o {
|
||||
Object::Ref(r) => self.get(*r),
|
||||
other => Arc::new(other.clone()),
|
||||
let Object::Ref(r) = o else { return Arc::new(o.clone()) };
|
||||
let mut held = self.get(*r);
|
||||
for _ in 0..MAX_REFERENCE_HOPS {
|
||||
let Object::Ref(r) = &*held else { break };
|
||||
held = self.get(*r);
|
||||
}
|
||||
held
|
||||
}
|
||||
|
||||
/// `s` with the `/DecodeParms` its filters use made direct, so [`Stream::decoded`] reads them:
|
||||
@@ -218,7 +222,7 @@ impl Document {
|
||||
}
|
||||
|
||||
/// `o`, or the object it refers to, without copying either.
|
||||
fn held<'o>(&self, o: &'o Object) -> Held<'o> {
|
||||
pub(crate) fn held<'o>(&self, o: &'o Object) -> Held<'o> {
|
||||
match o {
|
||||
Object::Ref(_) => Held::Resolved(self.resolve(o)),
|
||||
o => Held::Direct(o),
|
||||
@@ -395,12 +399,14 @@ impl Document {
|
||||
// cycles such as `6 0 obj << /Length 6 0 R >>`. Bound the nesting on every path.
|
||||
let _guard =
|
||||
LoadGuard::enter(num).ok_or_else(|| CosError::Syntax { offset: 0, detail: format!("reference cycle while loading object {num}") })?;
|
||||
let _scope = crate::security::FollowScope::enter();
|
||||
let obj = self.load(num, 0)?;
|
||||
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)
|
||||
}
|
||||
|
||||
@@ -409,10 +415,10 @@ 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.
|
||||
@@ -425,37 +431,13 @@ 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(())
|
||||
}
|
||||
|
||||
@@ -585,7 +567,11 @@ impl Document {
|
||||
let Object::Stream(s) = &*loaded else { return Err(CosError::MissingObject(num)) };
|
||||
let n = s.dict.int(b"N").unwrap_or(0).clamp(0, 1_000_000) as usize;
|
||||
let first = usize::try_from(s.dict.int(b"First").unwrap_or(0).max(0)).ok();
|
||||
let data = s.decoded_within(self.stream_limit)?;
|
||||
// Its parameters can be given by reference, and can sit in another object stream. A scan of
|
||||
// the file's object streams comes here without a read around it.
|
||||
let _scope = crate::security::FollowScope::enter();
|
||||
let readable = crate::security::following(Cow::Borrowed(s), || self.with_direct_parms(s));
|
||||
let data = readable.decoded_within(self.stream_limit)?;
|
||||
let mut lx = Lexer::new(&data, 0);
|
||||
let mut index = Vec::with_capacity(n);
|
||||
for _ in 0..n {
|
||||
@@ -600,8 +586,14 @@ impl Document {
|
||||
Ok(stm)
|
||||
}
|
||||
|
||||
/// Last-resort lookup: scan the file for `num G obj`.
|
||||
/// Last-resort lookup: scan the file for `num G obj`. What isn't there is remembered: each miss
|
||||
/// reads the whole file, and a file can refer to such an object from everywhere.
|
||||
fn scan_for(&self, num: u32) -> Option<(ObjRef, Object)> {
|
||||
if self.unfound.lock().is_ok_and(|unfound| unfound.contains(&num)) {
|
||||
return None;
|
||||
}
|
||||
#[cfg(test)]
|
||||
super::tests::FILE_SCANS.with(|scans| scans.set(scans.get() + 1));
|
||||
let needle = format!("{num} ");
|
||||
let data = &self.data;
|
||||
let mut found = None;
|
||||
@@ -617,6 +609,11 @@ impl Document {
|
||||
found = Some((id, o)); // keep the last (newest) definition
|
||||
}
|
||||
}
|
||||
if found.is_none()
|
||||
&& let Ok(mut unfound) = self.unfound.lock()
|
||||
{
|
||||
unfound.insert(num);
|
||||
}
|
||||
found
|
||||
}
|
||||
|
||||
@@ -682,8 +679,9 @@ impl Document {
|
||||
///
|
||||
/// Used when the working snapshot was restored from an earlier revision and the next
|
||||
/// incremental save must still append to this file (the last saved revision). Objects
|
||||
/// that already match are left untouched. Reads go through private readers so neither
|
||||
/// document's editing cache is filled.
|
||||
/// that already match are left untouched, except members of an object stream of this file
|
||||
/// whose stream number `current` frees or reuses: those are written again on their own.
|
||||
/// Reads go through private readers so neither document's editing cache is filled.
|
||||
pub fn overlay_changes_from(&mut self, current: &Document) -> Result<(), CosError> {
|
||||
let saved_nums = self.object_numbers();
|
||||
let current_nums = current.object_numbers();
|
||||
@@ -707,6 +705,22 @@ impl Document {
|
||||
}
|
||||
}
|
||||
}
|
||||
// An object stream of this file that is freed or replaced takes its members with it, so
|
||||
// a member that is otherwise unchanged is written again on its own.
|
||||
let gone = |n: u32| freed.binary_search(&n).is_ok() || changed.binary_search(&n).is_ok();
|
||||
let orphaned: Vec<u32> = current_nums
|
||||
.iter()
|
||||
.copied()
|
||||
.filter(|&num| changed.binary_search(&num).is_err())
|
||||
.filter(|&num| {
|
||||
let packed_in = match self.xref_entry(num) {
|
||||
Some(XrefEntry::InStream { stream, .. }) => Some(stream),
|
||||
_ => None,
|
||||
};
|
||||
packed_in.is_some_and(gone)
|
||||
})
|
||||
.collect();
|
||||
changed.extend(orphaned);
|
||||
for num in freed {
|
||||
let generation = self.generation(num);
|
||||
self.free(ObjRef::new(num, generation));
|
||||
@@ -809,9 +823,13 @@ const DECODE_PARMS_KEYS: [&[u8]; 13] = [
|
||||
b"ColorTransform",
|
||||
];
|
||||
|
||||
/// How many references in a row [`Document::resolve`] follows: enough for any file, and it ends a
|
||||
/// cycle of them.
|
||||
const MAX_REFERENCE_HOPS: usize = 32;
|
||||
|
||||
/// An object read in place, or the object a reference names as the document holds it: either way
|
||||
/// nothing is copied ([`Document::held`]).
|
||||
enum Held<'o> {
|
||||
pub(crate) enum Held<'o> {
|
||||
Direct(&'o Object),
|
||||
Resolved(Arc<Object>),
|
||||
}
|
||||
|
||||
@@ -1,7 +1,11 @@
|
||||
use super::reader::find;
|
||||
use super::state::Credentials;
|
||||
use super::xref::XrefIndex;
|
||||
use super::{Arc, BTreeMap, CosError, Dict, Document, ObjRef, Object};
|
||||
use super::{Arc, BTreeMap, CosError, Dict, Document, HashSet, ObjRef, Object};
|
||||
|
||||
/// More objects than `/Encrypt` and `/ID` refer to in any file, so that one which refers to the page
|
||||
/// tree, say, doesn't have a whole document read to open it.
|
||||
const MAX_ENCRYPT_MEMBERS: usize = 64;
|
||||
|
||||
impl Document {
|
||||
/// A new document with an empty page tree (for split / extract / combine). It has no
|
||||
@@ -27,6 +31,8 @@ impl Document {
|
||||
version: "1.7".into(),
|
||||
security: None,
|
||||
encrypt_num: None,
|
||||
encrypt_members: Arc::default(),
|
||||
unfound: Arc::default(),
|
||||
encryption_changed: false,
|
||||
full_save: false,
|
||||
out_security: None,
|
||||
@@ -111,6 +117,8 @@ impl Document {
|
||||
version,
|
||||
security: None,
|
||||
encrypt_num: None,
|
||||
encrypt_members: Arc::default(),
|
||||
unfound: Arc::default(),
|
||||
encryption_changed: false,
|
||||
full_save: false,
|
||||
out_security: None,
|
||||
@@ -185,6 +193,8 @@ impl Document {
|
||||
};
|
||||
let params = crate::security::encrypt_dict(self, &dict);
|
||||
let id0 = self.first_id();
|
||||
// Read here, while nothing is decrypted yet.
|
||||
let members = self.encryption_members(enc);
|
||||
let handler = match credentials {
|
||||
Credentials::Password(password) => Arc::new(pdfcraft_crypt::SecurityHandler::open(params, &id0, *password).map_err(|e| match e {
|
||||
pdfcraft_crypt::CryptError::WrongPassword if password.is_none() => CosError::NeedsPassword,
|
||||
@@ -197,6 +207,7 @@ impl Document {
|
||||
};
|
||||
self.security = Some(handler);
|
||||
self.encrypt_num = num;
|
||||
self.encrypt_members = Arc::new(members);
|
||||
// Objects read while locating the catalog were read before decryption was possible.
|
||||
self.cache = Arc::default();
|
||||
self.objstms = Arc::default();
|
||||
@@ -205,10 +216,42 @@ impl Document {
|
||||
|
||||
/// The first file identifier, part of the encryption key (empty when there is none).
|
||||
fn first_id(&self) -> Vec<u8> {
|
||||
match self.trailer.get(b"ID") {
|
||||
Some(Object::Array(a)) => a.first().and_then(|s| s.as_string()).map(|s| s.bytes.clone()).unwrap_or_default(),
|
||||
_ => Vec::new(),
|
||||
let id = self.trailer.get(b"ID").map(|id| self.resolve(id));
|
||||
let first = id.as_deref().and_then(Object::as_array).and_then(|a| a.first()).map(|s| self.resolve(s));
|
||||
first.as_deref().and_then(Object::as_string).map(|s| s.bytes.clone()).unwrap_or_default()
|
||||
}
|
||||
|
||||
/// The objects `/Encrypt`, given as `enc`, and `/ID` refer to, the ones they refer to, and so
|
||||
/// on, up to [`MAX_ENCRYPT_MEMBERS`]. Their strings aren't encrypted (ISO 32000-2 §7.6.2): the
|
||||
/// key is made from them, so they have to read as stored, and stay so. A number with no object
|
||||
/// behind it, and a stream, which those dictionaries never hold, isn't one: an object added
|
||||
/// under that number later, or a page's content a hostile `/Encrypt` names, is encrypted.
|
||||
fn encryption_members(&self, enc: &Object) -> HashSet<u32> {
|
||||
let mut pending = Vec::new();
|
||||
crate::writer::collect_refs(enc, &mut |r| pending.push(r));
|
||||
if let Some(id) = self.trailer.get(b"ID") {
|
||||
crate::writer::collect_refs(id, &mut |r| pending.push(r));
|
||||
}
|
||||
let mut members = HashSet::new();
|
||||
while let Some(r) = pending.pop() {
|
||||
if members.len() >= MAX_ENCRYPT_MEMBERS || members.contains(&r.num) {
|
||||
continue;
|
||||
}
|
||||
let held = self.get(r);
|
||||
if matches!(&*held, Object::Null | Object::Stream(_)) {
|
||||
continue;
|
||||
}
|
||||
members.insert(r.num);
|
||||
crate::writer::collect_refs(&held, &mut |x| pending.push(x));
|
||||
}
|
||||
members
|
||||
}
|
||||
|
||||
/// Whether object `num` is written as it is held, being one of [`Document::encryption_members`],
|
||||
/// unedited, and the save writing the same `/Encrypt`. What was edited or added is encrypted
|
||||
/// whatever its number.
|
||||
pub(crate) fn stored_as_is(&self, num: u32) -> bool {
|
||||
!self.encryption_changed && !self.is_edited(num) && self.encrypt_members.contains(&num)
|
||||
}
|
||||
|
||||
/// Lift the restrictions of a document opened with its user password by entering the
|
||||
@@ -270,8 +313,9 @@ impl Document {
|
||||
/// always a full rewrite. Returns the handler (authenticated as owner).
|
||||
pub fn set_encryption(&mut self, params: &pdfcraft_crypt::NewEncryption) -> Result<(), CosError> {
|
||||
// The file identifier is part of the key; make sure it exists and keep it.
|
||||
let id0 = match self.trailer.get(b"ID") {
|
||||
Some(Object::Array(a)) if a.len() == 2 => a[0].as_string().map(|s| s.bytes.clone()).unwrap_or_default(),
|
||||
let id = self.trailer.get(b"ID").map(|id| self.resolve(id));
|
||||
let id0 = match id.as_deref() {
|
||||
Some(Object::Array(a)) if a.len() == 2 => self.first_id(),
|
||||
_ => {
|
||||
let id = pdfcraft_crypt::file_id(¶ms.seed);
|
||||
let s = Object::String(crate::PdfString { bytes: id.clone(), hex: true });
|
||||
@@ -338,7 +382,9 @@ impl Document {
|
||||
/// Decrypt a freshly parsed indirect object if the document is encrypted.
|
||||
pub(super) fn decrypted(&self, id: ObjRef, o: Object) -> Object {
|
||||
match &self.security {
|
||||
Some(h) if Some(id.num) != self.encrypt_num => crate::security::transform(h, &o, id.num, id.generation, crate::security::Pass::Decrypt),
|
||||
Some(h) if Some(id.num) != self.encrypt_num && !self.encrypt_members.contains(&id.num) => {
|
||||
crate::security::transform(self, h, &o, id.num, id.generation, crate::security::Pass::Decrypt)
|
||||
}
|
||||
_ => o,
|
||||
}
|
||||
}
|
||||
|
||||
@@ -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,
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
@@ -1,5 +1,147 @@
|
||||
use super::*;
|
||||
|
||||
std::thread_local! {
|
||||
/// How many times `Document::scan_for` read the file on this thread.
|
||||
pub(super) static FILE_SCANS: std::cell::Cell<usize> = const { std::cell::Cell::new(0) };
|
||||
}
|
||||
|
||||
/// A scan that doesn't find an object isn't made again: each reads the whole file, and a file can
|
||||
/// refer to such an object from every object it has.
|
||||
#[test]
|
||||
fn what_a_scan_of_the_file_did_not_find_is_remembered() {
|
||||
let body = b"%PDF-1.7\n1 0 obj << /Type /Catalog /Pages 2 0 R >> endobj\n2 0 obj << /Type /Pages /Kids [] /Count 0 >> endobj\n";
|
||||
let mut out = body.to_vec();
|
||||
let xref = out.len();
|
||||
out.extend_from_slice(b"xref\n0 4\n0000000000 65535 f \n");
|
||||
out.extend_from_slice(format!("{:010} 00000 n \n", 9).as_bytes());
|
||||
out.extend_from_slice(format!("{:010} 00000 n \n", body.iter().position(|b| *b == b'\n').unwrap() + 49).as_bytes());
|
||||
out.extend_from_slice(b"0000000001 00000 n \n");
|
||||
out.extend_from_slice(format!("trailer << /Size 4 /Root 1 0 R >>\nstartxref\n{xref}\n%%EOF\n").as_bytes());
|
||||
let doc = Document::open(Arc::new(out)).unwrap();
|
||||
FILE_SCANS.with(|scans| scans.set(0));
|
||||
for _ in 0..5 {
|
||||
assert!(doc.try_get(3).is_err());
|
||||
}
|
||||
assert_eq!(FILE_SCANS.with(std::cell::Cell::get), 1);
|
||||
let clone = doc.clone();
|
||||
assert!(clone.try_get(3).is_err());
|
||||
assert_eq!(FILE_SCANS.with(std::cell::Cell::get), 1, "a clone has the same file");
|
||||
}
|
||||
|
||||
/// An object can be nothing but a reference to another. A chain of them is followed, and one that
|
||||
/// goes round ends in what isn't a dictionary or a name, without hanging.
|
||||
#[test]
|
||||
fn references_to_references_are_followed() {
|
||||
let mut doc = Document::new_empty();
|
||||
let name = doc.add(Object::name("Target"));
|
||||
let one = doc.add(Object::Ref(name));
|
||||
let two = doc.add(Object::Ref(one));
|
||||
assert_eq!(doc.resolve(&Object::Ref(two)).as_name(), Some(b"Target".as_slice()));
|
||||
let a = doc.add(Object::Null);
|
||||
let b = doc.add(Object::Ref(a));
|
||||
doc.set(a, Object::Ref(b));
|
||||
assert_eq!(doc.resolve(&Object::Ref(a)).as_name(), None);
|
||||
}
|
||||
|
||||
/// An object stream's `/DecodeParms` can be given by reference: without them a predictor isn't
|
||||
/// undone, so its members were lost.
|
||||
#[test]
|
||||
fn an_object_stream_with_parameters_by_reference_is_read() {
|
||||
let members = b"3 0 << /Hidden (yes) >>";
|
||||
// PNG Sub, one row.
|
||||
let mut rows = vec![1u8];
|
||||
let mut before = 0u8;
|
||||
for b in members {
|
||||
rows.push(b.wrapping_sub(before));
|
||||
before = *b;
|
||||
}
|
||||
let coded = pdfcraft_filters::encode_flate(&rows);
|
||||
let mut out = b"%PDF-1.5\n".to_vec();
|
||||
let mut offs = [0usize; 7];
|
||||
let mut obj = |out: &mut Vec<u8>, n: usize, body: &[u8]| {
|
||||
offs[n] = out.len();
|
||||
out.extend_from_slice(format!("{n} 0 obj\n").as_bytes());
|
||||
out.extend_from_slice(body);
|
||||
out.extend_from_slice(b"\nendobj\n");
|
||||
};
|
||||
obj(&mut out, 1, b"<< /Type /Catalog /Pages 2 0 R >>");
|
||||
obj(&mut out, 2, b"<< /Type /Pages /Kids [] /Count 0 /Extra 3 0 R >>");
|
||||
let mut stm = format!("<< /Type /ObjStm /N 1 /First 4 /Filter /FlateDecode /DecodeParms 6 0 R /Length {} >>\nstream\n", coded.len()).into_bytes();
|
||||
stm.extend_from_slice(&coded);
|
||||
stm.extend_from_slice(b"\nendstream");
|
||||
obj(&mut out, 4, &stm);
|
||||
let data = [2u8, 0, 4, 0];
|
||||
let mut xs = format!("<< /Type /XRef /Size 7 /W [1 2 1] /Index [3 1] /Length {} >>\nstream\n", data.len()).into_bytes();
|
||||
xs.extend_from_slice(&data);
|
||||
xs.extend_from_slice(b"\nendstream");
|
||||
obj(&mut out, 5, &xs);
|
||||
obj(&mut out, 6, format!("<< /Predictor 11 /Columns {} >>", members.len()).as_bytes());
|
||||
let table = out.len();
|
||||
out.extend_from_slice(b"xref\n0 7\n0000000000 65535 f \n");
|
||||
for (n, off) in offs.iter().enumerate().skip(1) {
|
||||
let line = if n == 3 { "0000000000 65535 f \n".to_string() } else { format!("{off:010} 00000 n \n") };
|
||||
out.extend_from_slice(line.as_bytes());
|
||||
}
|
||||
out.extend_from_slice(format!("trailer << /Size 7 /Root 1 0 R /XRefStm {} >>\nstartxref\n{table}\n%%EOF\n", offs[5]).as_bytes());
|
||||
let doc = Document::open(Arc::new(out)).unwrap();
|
||||
let hidden = doc.get(ObjRef::new(3, 0));
|
||||
assert_eq!(hidden.as_dict().and_then(|d| d.get(b"Hidden")).and_then(Object::as_string).map(|s| s.bytes.clone()), Some(b"yes".to_vec()));
|
||||
}
|
||||
|
||||
/// Each entry of an `/Encrypt` dictionary, and of a crypt filter in it, reads the same by reference.
|
||||
/// Read as absent, `/StmF` or `/CFM` was `/Identity`, so a whole file's streams stayed ciphertext.
|
||||
#[test]
|
||||
fn encrypt_dictionary_entries_read_the_same_by_reference() {
|
||||
let string = |s: &str| Object::String(crate::PdfString::text(s));
|
||||
let mut filter = Dict::new();
|
||||
filter.set(b"CFM".to_vec(), Object::name("AESV2"));
|
||||
filter.set(b"Length".to_vec(), Object::Int(5));
|
||||
let cf = |filter: Dict| {
|
||||
let mut cf = Dict::new();
|
||||
cf.set(b"StdCF".to_vec(), Object::Dict(filter));
|
||||
cf.set(b"Other".to_vec(), Object::Dict(Dict::new()));
|
||||
Object::Dict(cf)
|
||||
};
|
||||
let mut d = Dict::new();
|
||||
let entries = [
|
||||
("Filter", Object::name("Standard")),
|
||||
("V", Object::Int(4)),
|
||||
("R", Object::Int(4)),
|
||||
("Length", Object::Int(128)),
|
||||
("P", Object::Int(-44)),
|
||||
("O", string("owner")),
|
||||
("U", string("user")),
|
||||
("EncryptMetadata", Object::Bool(false)),
|
||||
("CF", cf(filter.clone())),
|
||||
("StmF", Object::name("StdCF")),
|
||||
("StrF", Object::name("Other")),
|
||||
("EFF", Object::name("StdCF")),
|
||||
];
|
||||
for (key, value) in &entries {
|
||||
d.set(key.as_bytes().to_vec(), value.clone());
|
||||
}
|
||||
let mut doc = Document::new_empty();
|
||||
let direct = crate::security::encrypt_dict(&doc, &d);
|
||||
assert_eq!((direct.stm_f.as_slice(), direct.str_f.as_slice(), direct.ef_f.as_slice()), (&b"StdCF"[..], &b"Other"[..], &b"StdCF"[..]));
|
||||
assert_eq!(direct.length_bits, 40, "the filter's own length, in bytes");
|
||||
assert!(!direct.encrypt_metadata);
|
||||
assert_eq!(direct.crypt_filters.iter().filter(|(_, m)| *m == pdfcraft_crypt::Method::Aes128).count(), 1);
|
||||
for (key, value) in &entries {
|
||||
let mut one = d.clone();
|
||||
let r = doc.add(value.clone());
|
||||
one.set(key.as_bytes().to_vec(), Object::Ref(r));
|
||||
assert_eq!(crate::security::encrypt_dict(&doc, &one), direct, "/{key}");
|
||||
}
|
||||
for key in ["CFM", "Length"] {
|
||||
let mut by_reference = filter.clone();
|
||||
let r = doc.add(filter.get(key.as_bytes()).unwrap().clone());
|
||||
by_reference.set(key.as_bytes().to_vec(), Object::Ref(r));
|
||||
let mut one = d.clone();
|
||||
one.set(b"CF".to_vec(), cf(by_reference));
|
||||
assert_eq!(crate::security::encrypt_dict(&doc, &one), direct, "/{key} in the filter");
|
||||
}
|
||||
}
|
||||
|
||||
/// /DecodeParms given by reference, whole, as array entries or as the numbers inside, are read
|
||||
/// once made direct: here a Flate predictor, which the stream alone doesn't see. Only the entries the filters use are
|
||||
/// resolved, and nothing is for a chain longer than a decoder takes.
|
||||
@@ -1109,7 +1251,8 @@ 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 +1335,14 @@ 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 +1384,8 @@ 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 +1845,76 @@ 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");
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn a_restored_revision_keeps_what_the_saved_file_held_in_object_streams() {
|
||||
// The earlier revision: an empty document read back from a file whose catalog and pages
|
||||
// sit in an object stream.
|
||||
let earlier = Document::open(Arc::new(crate::write_full(&Document::new_empty(), &crate::SaveOptions::default()).unwrap())).unwrap();
|
||||
// The saved revision adds an object the catalog links to, so a full save numbers its objects
|
||||
// anew; an undo then returns to the earlier graph.
|
||||
let mut later = earlier.clone();
|
||||
let extra = later.add(Object::Int(7));
|
||||
let root = later.root().unwrap();
|
||||
later.update_dict(root, |c| c.set(b"Extra".to_vec(), Object::Ref(extra))).unwrap();
|
||||
let saved = crate::write_full(&later, &crate::SaveOptions::default()).unwrap();
|
||||
let mut base = Document::open(Arc::new(saved)).unwrap();
|
||||
assert!(
|
||||
base.object_numbers().iter().any(|&n| matches!(base.xref_entry(n), Some(XrefEntry::InStream { .. }))),
|
||||
"the saved file holds objects in a stream"
|
||||
);
|
||||
base.overlay_changes_from(&earlier).unwrap();
|
||||
let file = crate::write_incremental(&base, &crate::SaveOptions::default()).unwrap();
|
||||
let reread = Document::open(Arc::new(file)).unwrap();
|
||||
let catalog = reread.get(reread.root().unwrap()).as_dict().unwrap().clone();
|
||||
assert!(catalog.get(b"Extra").is_none(), "the restored catalog");
|
||||
let pages = reread.resolve(catalog.get(b"Pages").unwrap());
|
||||
assert_eq!(pages.as_dict().and_then(|d| d.name(b"Type")), Some(&b"Pages"[..]), "the pages survive: {pages:?}");
|
||||
}
|
||||
|
||||
/// 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, ImageBudget, MAX_PAGE_DECODED, MAX_PAGE_FORMS};
|
||||
pub use budget::{DecodeBudget, ImageBudget, MAX_PAGE_DECODED, MAX_PAGE_FORMS, MAX_REDACTED_IMAGE_PIXELS};
|
||||
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};
|
||||
|
||||
@@ -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}");
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
+214
-80
@@ -7,10 +7,69 @@
|
||||
//! false. Streams naming a crypt filter (`/Crypt` in `/Filter`) use that filter; embedded files
|
||||
//! use `/EFF`.
|
||||
|
||||
use pdfcraft_crypt::{EncryptDict, Method, SecurityHandler, StreamKind};
|
||||
use std::cell::Cell;
|
||||
|
||||
use pdfcraft_crypt::{EncryptDict, Method, SecurityHandler, StreamKind};
|
||||
use pdfcraft_filters::MAX_CHAIN;
|
||||
|
||||
use crate::document::Held;
|
||||
use crate::{Dict, Document, Object, PdfString, Stream};
|
||||
|
||||
/// How many references one read or write of an object may follow, with all that it loads on the
|
||||
/// way. How an object is treated can be given by reference, and what that loads can do the same: a
|
||||
/// file could make one read a tree of them, each object read again once the cache has let it go.
|
||||
/// An object takes a few of these, and two dozen if every part of it is given by reference; past
|
||||
/// this they read as absent. The parameters of an object stream, read together, count as one.
|
||||
const MAX_FOLLOWED: u32 = 32;
|
||||
|
||||
std::thread_local! {
|
||||
/// How many [`FollowScope`]s this thread is inside.
|
||||
static SCOPES: Cell<u32> = const { Cell::new(0) };
|
||||
/// The references followed in the outermost of them.
|
||||
static FOLLOWED: Cell<u32> = const { Cell::new(0) };
|
||||
/// The references refused in the outermost of them, past [`MAX_FOLLOWED`].
|
||||
static REFUSED: Cell<u32> = const { Cell::new(0) };
|
||||
}
|
||||
|
||||
/// One read or write of an object, with everything it loads on the way: what [`MAX_FOLLOWED`] counts.
|
||||
pub(crate) struct FollowScope;
|
||||
|
||||
impl FollowScope {
|
||||
pub(crate) fn enter() -> Self {
|
||||
if SCOPES.replace(SCOPES.get().saturating_add(1)) == 0 {
|
||||
FOLLOWED.set(0);
|
||||
REFUSED.set(0);
|
||||
}
|
||||
FollowScope
|
||||
}
|
||||
}
|
||||
|
||||
impl Drop for FollowScope {
|
||||
fn drop(&mut self) {
|
||||
SCOPES.set(SCOPES.get().saturating_sub(1));
|
||||
}
|
||||
}
|
||||
|
||||
/// What `f` gives, counted against [`MAX_FOLLOWED`], or `spent` past it. Called inside a
|
||||
/// [`FollowScope`], which is what starts the count again.
|
||||
pub(crate) fn following<T>(spent: T, f: impl FnOnce() -> T) -> T {
|
||||
if FOLLOWED.get() >= MAX_FOLLOWED {
|
||||
REFUSED.set(REFUSED.get().saturating_add(1));
|
||||
return spent;
|
||||
}
|
||||
FOLLOWED.set(FOLLOWED.get() + 1);
|
||||
f()
|
||||
}
|
||||
|
||||
/// `o`, or the object it refers to, for what decides how a stream or dictionary is treated. Past
|
||||
/// [`MAX_FOLLOWED`] a reference reads as absent.
|
||||
fn followed<'o>(doc: &Document, o: &'o Object) -> Held<'o> {
|
||||
match o {
|
||||
Object::Ref(_) => following(Held::Direct(&Object::Null), || doc.held(o)),
|
||||
o => Held::Direct(o),
|
||||
}
|
||||
}
|
||||
|
||||
fn bytes_of(doc: &Document, d: &Dict, key: &[u8]) -> Vec<u8> {
|
||||
d.get(key).map(|v| doc.resolve(v)).and_then(|v| v.as_string().map(|s| s.bytes.clone())).unwrap_or_default()
|
||||
}
|
||||
@@ -18,12 +77,12 @@ fn bytes_of(doc: &Document, d: &Dict, key: &[u8]) -> Vec<u8> {
|
||||
/// Read the handler parameters from an `/Encrypt` dictionary.
|
||||
pub(crate) fn encrypt_dict(doc: &Document, d: &Dict) -> EncryptDict {
|
||||
let int = |k: &[u8], default: i64| d.get(k).map(|v| doc.resolve(v)).and_then(|v| v.as_int()).unwrap_or(default);
|
||||
let name = |k: &[u8]| d.get(k).and_then(|v| v.as_name()).map(|n| n.to_vec()).unwrap_or_else(|| b"Identity".to_vec());
|
||||
let name = |d: &Dict, k: &[u8]| d.get(k).and_then(|v| doc.resolve(v).as_name().map(<[u8]>::to_vec));
|
||||
let mut crypt_filters = Vec::new();
|
||||
if let Some(cf) = d.get(b"CF").map(|c| doc.resolve(c)).and_then(|c| c.as_dict().cloned()) {
|
||||
for (k, v) in cf.iter() {
|
||||
let Some(f) = doc.resolve(v).as_dict().cloned() else { continue };
|
||||
let method = match f.name(b"CFM") {
|
||||
let method = match name(&f, b"CFM").as_deref() {
|
||||
Some(b"V2") => Method::Rc4,
|
||||
Some(b"AESV2") => Method::Aes128,
|
||||
Some(b"AESV3") => Method::Aes256,
|
||||
@@ -40,7 +99,8 @@ pub(crate) fn encrypt_dict(doc: &Document, d: &Dict) -> EncryptDict {
|
||||
.get(b"CF")
|
||||
.map(|c| doc.resolve(c))
|
||||
.and_then(|c| c.as_dict().and_then(|c| c.get(b"StdCF").map(|f| doc.resolve(f))))
|
||||
.and_then(|f| f.as_dict().and_then(|f| f.int(b"Length")))
|
||||
.and_then(|f| f.as_dict().and_then(|f| f.get(b"Length").map(|n| doc.resolve(n))))
|
||||
.and_then(|n| n.as_int())
|
||||
.filter(|n| *n > 0);
|
||||
let length_bits = match (v, cf_len) {
|
||||
(5.., _) => 256,
|
||||
@@ -50,7 +110,7 @@ pub(crate) fn encrypt_dict(doc: &Document, d: &Dict) -> EncryptDict {
|
||||
_ => int(b"Length", 40),
|
||||
};
|
||||
EncryptDict {
|
||||
filter: d.name(b"Filter").map(|n| n.to_vec()).unwrap_or_default(),
|
||||
filter: name(d, b"Filter").unwrap_or_default(),
|
||||
v,
|
||||
r: int(b"R", 0),
|
||||
length_bits,
|
||||
@@ -60,28 +120,46 @@ pub(crate) fn encrypt_dict(doc: &Document, d: &Dict) -> EncryptDict {
|
||||
ue: bytes_of(doc, d, b"UE"),
|
||||
perms: bytes_of(doc, d, b"Perms"),
|
||||
p: int(b"P", -1) as i32,
|
||||
encrypt_metadata: !matches!(d.get(b"EncryptMetadata"), Some(Object::Bool(false))),
|
||||
encrypt_metadata: !matches!(d.get(b"EncryptMetadata").map(|v| doc.resolve(v)).as_deref(), Some(Object::Bool(false))),
|
||||
crypt_filters,
|
||||
stm_f: name(b"StmF"),
|
||||
str_f: name(b"StrF"),
|
||||
ef_f: d.get(b"EFF").and_then(|v| v.as_name()).map(|n| n.to_vec()).unwrap_or_default(),
|
||||
stm_f: name(d, b"StmF").unwrap_or_else(|| b"Identity".to_vec()),
|
||||
str_f: name(d, b"StrF").unwrap_or_else(|| b"Identity".to_vec()),
|
||||
ef_f: name(d, b"EFF").unwrap_or_default(),
|
||||
}
|
||||
}
|
||||
|
||||
/// The crypt filter a stream names in its `/Filter` chain (`/Crypt` + `/DecodeParms /Name`).
|
||||
fn named_crypt_filter(dict: &Dict) -> Option<Vec<u8>> {
|
||||
let names: Vec<&[u8]> = match dict.get(b"Filter") {
|
||||
Some(Object::Name(n)) => vec![n],
|
||||
Some(Object::Array(a)) => a.iter().filter_map(Object::as_name).collect(),
|
||||
/// Whether `f`, an entry of a `/Filter` chain or its only filter, is `/Crypt`.
|
||||
fn is_crypt(doc: &Document, f: &Object) -> bool {
|
||||
followed(doc, f).as_name() == Some(b"Crypt")
|
||||
}
|
||||
|
||||
/// The crypt filter a stream names in its `/Filter` chain (`/Crypt` + `/DecodeParms /Name`), each
|
||||
/// given directly or by reference, in an array or not. A chain longer than any decoder takes names
|
||||
/// none: nothing can read that stream anyway, and every stream of a file can share one long array.
|
||||
/// A `/Name` that reads as absent means `/Identity`, unless a reference on the way to it was refused
|
||||
/// (see [`MAX_FOLLOWED`]): that says nothing about the stream, so it names none, and the document's
|
||||
/// own filter is used.
|
||||
fn named_crypt_filter(doc: &Document, dict: &Dict) -> Option<Vec<u8>> {
|
||||
let refused = REFUSED.get();
|
||||
let filter = followed(doc, dict.get(b"Filter")?);
|
||||
let i = match &*filter {
|
||||
Object::Array(a) if a.len() <= MAX_CHAIN + 1 => a.iter().position(|f| is_crypt(doc, f))?,
|
||||
f if is_crypt(doc, f) => 0,
|
||||
_ => return None,
|
||||
};
|
||||
let i = names.iter().position(|n| *n == b"Crypt")?;
|
||||
let parms = match dict.get(b"DecodeParms") {
|
||||
Some(Object::Dict(d)) if i == 0 => Some(d.clone()),
|
||||
Some(Object::Array(a)) => a.get(i).and_then(|p| p.as_dict().cloned()),
|
||||
let parms = dict.get(b"DecodeParms").map(|p| followed(doc, p));
|
||||
let entry = match parms.as_deref() {
|
||||
Some(Object::Array(a)) => a.get(i).map(|p| followed(doc, p)),
|
||||
Some(p) if i == 0 => Some(Held::Direct(p)),
|
||||
_ => None,
|
||||
};
|
||||
Some(parms.and_then(|p| p.name(b"Name").map(|n| n.to_vec())).unwrap_or_else(|| b"Identity".to_vec()))
|
||||
let name = entry.as_deref().and_then(Object::as_dict).and_then(|p| p.get(b"Name")).map(|n| followed(doc, n));
|
||||
match name.as_deref().and_then(Object::as_name) {
|
||||
Some(name) => Some(name.to_vec()),
|
||||
// /Identity here would read ciphertext as data, and write the stream in the clear.
|
||||
None if REFUSED.get() > refused => None,
|
||||
None => Some(b"Identity".to_vec()),
|
||||
}
|
||||
}
|
||||
|
||||
/// A signature dictionary (field signature, document timestamp or usage-rights signature),
|
||||
@@ -91,42 +169,67 @@ fn named_crypt_filter(dict: &Dict) -> Option<Vec<u8>> {
|
||||
/// `/Contents` alongside an array `/ByteRange` (`/Type` is optional). A signature dictionary
|
||||
/// has no `/Subtype`; a dictionary with one (an annotation, whose `/Contents` is the comment
|
||||
/// text) or with another `/Type` is never exempt, whatever else it carries.
|
||||
fn is_signature_dict(d: &Dict) -> bool {
|
||||
if d.get(b"Subtype").is_some() {
|
||||
/// With `doc` its entries are read through references; a dictionary nested in another object
|
||||
/// has none (see [`transform`]).
|
||||
fn is_signature_dict(doc: Option<&Document>, d: &Dict) -> bool {
|
||||
// All this decides is what happens to such a /Contents.
|
||||
if !matches!(d.get(b"Contents"), Some(Object::String(_))) {
|
||||
return false;
|
||||
}
|
||||
match d.get(b"Type") {
|
||||
Some(_) => matches!(d.name(b"Type"), Some(b"Sig" | b"DocTimeStamp")),
|
||||
None => matches!(d.get(b"Contents"), Some(Object::String(_))) && matches!(d.get(b"ByteRange"), Some(Object::Array(_))),
|
||||
// A null entry, or one that refers to nothing, is an absent one (ISO 32000-2 §7.3.7, §7.3.10).
|
||||
let entry = |key: &[u8]| {
|
||||
let value = d.get(key)?;
|
||||
let held = doc.map_or(Held::Direct(value), |doc| followed(doc, value));
|
||||
(!matches!(*held, Object::Null)).then_some(held)
|
||||
};
|
||||
if entry(b"Subtype").is_some() {
|
||||
return false;
|
||||
}
|
||||
match entry(b"Type") {
|
||||
Some(t) => matches!(t.as_name(), Some(b"Sig" | b"DocTimeStamp")),
|
||||
None => matches!(entry(b"ByteRange").as_deref(), Some(Object::Array(_))),
|
||||
}
|
||||
}
|
||||
|
||||
/// Remove the `/Crypt` entry from a stream's filter chain, with its decode parameters.
|
||||
fn drop_crypt_filter(dict: &mut Dict) {
|
||||
let i = match dict.get(b"Filter") {
|
||||
Some(Object::Array(a)) => a.iter().position(|n| n.as_name() == Some(b"Crypt")),
|
||||
Some(Object::Name(n)) if n.as_slice() == b"Crypt" => Some(0),
|
||||
_ => None,
|
||||
/// Longer than any filter's name. A name can be of any length, and a chain every stream shares can
|
||||
/// hold a long one.
|
||||
const MAX_FILTER_NAME: usize = 127;
|
||||
|
||||
/// The dictionary of `source` without the `/Crypt` entries of its filter chain and their decode
|
||||
/// parameters. The two come out direct when given by reference, which every stream of a file can
|
||||
/// share, so of what was shared only small values are copied: filter names, and the parameters
|
||||
/// decoders read ([`Document::with_direct_parms`]). The chain is short, as [`named_crypt_filter`]
|
||||
/// found a filter in it.
|
||||
fn drop_crypt_filter(doc: &Document, source: &Stream) -> Dict {
|
||||
let entry = |f: &Object| match f {
|
||||
f if is_crypt(doc, f) => Object::name("Crypt"),
|
||||
Object::Name(n) if n.len() <= MAX_FILTER_NAME => f.clone(),
|
||||
Object::Ref(_) => f.clone(),
|
||||
_ => Object::Null,
|
||||
};
|
||||
let Some(i) = i else { return };
|
||||
let mut filters = match dict.get(b"Filter") {
|
||||
Some(Object::Array(a)) => a.clone(),
|
||||
_ => Vec::new(),
|
||||
let filter = source.dict.get(b"Filter").map(|f| followed(doc, f));
|
||||
let chain: Vec<Object> = match filter.as_deref() {
|
||||
Some(Object::Array(a)) => a.iter().map(entry).collect(),
|
||||
Some(f) => vec![entry(f)],
|
||||
None => Vec::new(),
|
||||
};
|
||||
if i < filters.len() {
|
||||
filters.remove(i);
|
||||
}
|
||||
let crypt: Vec<bool> = chain.iter().map(|f| f.as_name() == Some(b"Crypt")).collect();
|
||||
let mut chained = Stream::from_raw(source.dict.clone(), Vec::new());
|
||||
chained.dict.set(b"Filter".to_vec(), Object::Array(chain.clone()));
|
||||
// A lone parameter dictionary belongs to the first filter (as `named_crypt_filter` reads it).
|
||||
match dict.get(b"DecodeParms").cloned() {
|
||||
Some(Object::Array(mut parms)) if i < parms.len() => {
|
||||
parms.remove(i);
|
||||
dict.set(b"DecodeParms".to_vec(), Object::Array(parms));
|
||||
}
|
||||
Some(Object::Dict(_)) if i == 0 => {
|
||||
let parms = match doc.with_direct_parms(&chained).dict.get(b"DecodeParms") {
|
||||
Some(Object::Array(p)) => Some(Object::Array(p.iter().zip(&crypt).filter(|(_, c)| !**c).map(|(p, _)| p.clone()).collect())),
|
||||
Some(Object::Dict(_)) if crypt.first() == Some(&true) => None,
|
||||
_ => source.dict.get(b"DecodeParms").cloned(),
|
||||
};
|
||||
let mut dict = source.dict.clone();
|
||||
match parms {
|
||||
Some(p) => dict.set(b"DecodeParms".to_vec(), p),
|
||||
None => {
|
||||
dict.remove(b"DecodeParms");
|
||||
}
|
||||
_ => {}
|
||||
}
|
||||
let filters: Vec<Object> = chain.into_iter().zip(&crypt).filter(|(_, c)| !**c).map(|(f, _)| f).collect();
|
||||
if filters.is_empty() {
|
||||
dict.remove(b"Filter");
|
||||
if matches!(dict.get(b"DecodeParms"), Some(Object::Array(p)) if p.is_empty()) {
|
||||
@@ -135,6 +238,7 @@ fn drop_crypt_filter(dict: &mut Dict) {
|
||||
} else {
|
||||
dict.set(b"Filter".to_vec(), Object::Array(filters));
|
||||
}
|
||||
dict
|
||||
}
|
||||
|
||||
/// What [`transform`] does to an object.
|
||||
@@ -152,51 +256,81 @@ pub(crate) enum Pass {
|
||||
|
||||
/// Decrypt or encrypt every string and stream in an indirect object, except a signature
|
||||
/// dictionary's `/Contents` (see [`is_signature_dict`]).
|
||||
pub(crate) fn transform(h: &SecurityHandler, o: &Object, num: u32, generation: u16, pass: Pass) -> Object {
|
||||
///
|
||||
/// `o` is as `doc` holds it: what a stream's dictionary gives by reference is read from `doc`, so
|
||||
/// its references have to be the document's, not a save's renumbered ones.
|
||||
pub(crate) fn transform(doc: &Document, h: &SecurityHandler, o: &Object, num: u32, generation: u16, pass: Pass) -> Object {
|
||||
let _scope = FollowScope::enter();
|
||||
let decrypt = pass == Pass::Decrypt;
|
||||
let strings = |s: &PdfString| {
|
||||
let bytes = if decrypt { h.decrypt_string(num, generation, &s.bytes) } else { h.encrypt_string(num, generation, &s.bytes) };
|
||||
PdfString { bytes, hex: s.hex || !decrypt }
|
||||
};
|
||||
walk(o, &strings, h, num, generation, pass)
|
||||
// References are followed here only, for the object itself, never for what is nested in it.
|
||||
// `walk` goes deep, and a load from down there adds that depth again for each object loaded,
|
||||
// which overflowed the stack on a 10 KB file. A stream can't be nested, and a dictionary that
|
||||
// is reads as it says directly.
|
||||
match o {
|
||||
Object::Stream(s) => stream(doc, s, &strings, h, num, generation, pass),
|
||||
Object::Dict(d) if is_signature_dict(Some(doc), d) => signature_dict(d, &strings),
|
||||
o => walk(o, &strings),
|
||||
}
|
||||
}
|
||||
|
||||
fn walk(o: &Object, strings: &dyn Fn(&PdfString) -> PdfString, h: &SecurityHandler, num: u32, generation: u16, pass: Pass) -> Object {
|
||||
let decrypt = pass == Pass::Decrypt;
|
||||
/// `d`, a signature dictionary, with the strings of everything but its `/Contents` transformed.
|
||||
fn signature_dict(d: &Dict, strings: &dyn Fn(&PdfString) -> PdfString) -> Object {
|
||||
Object::Dict(
|
||||
d.iter()
|
||||
.map(|(k, v)| match (k.as_slice(), v) {
|
||||
(b"Contents", Object::String(_)) => (k.clone(), v.clone()),
|
||||
_ => (k.clone(), walk(v, strings)),
|
||||
})
|
||||
.collect(),
|
||||
)
|
||||
}
|
||||
|
||||
fn walk(o: &Object, strings: &dyn Fn(&PdfString) -> PdfString) -> Object {
|
||||
match o {
|
||||
Object::String(s) => Object::String(strings(s)),
|
||||
Object::Array(a) => Object::Array(a.iter().map(|x| walk(x, strings, h, num, generation, pass)).collect()),
|
||||
Object::Dict(d) if is_signature_dict(d) => Object::Dict(
|
||||
d.iter()
|
||||
.map(|(k, v)| match (k.as_slice(), v) {
|
||||
(b"Contents", Object::String(_)) => (k.clone(), v.clone()),
|
||||
_ => (k.clone(), walk(v, strings, h, num, generation, pass)),
|
||||
})
|
||||
.collect(),
|
||||
),
|
||||
Object::Dict(d) => Object::Dict(d.iter().map(|(k, v)| (k.clone(), walk(v, strings, h, num, generation, pass))).collect()),
|
||||
Object::Stream(s) => {
|
||||
let mut dict: Dict = s.dict.iter().map(|(k, v)| (k.clone(), walk(v, strings, h, num, generation, pass))).collect();
|
||||
let ty = s.dict.name(b"Type");
|
||||
// Cross-reference streams are never encrypted (§7.5.8), but only reading may trust the
|
||||
// label: a stream a producer calls /XRef stays plaintext if writing believes it, and the
|
||||
// writer builds its own cross-reference streams outside this transform.
|
||||
if (decrypt && ty == Some(b"XRef")) || (ty == Some(b"Metadata") && !h.encrypts_metadata()) {
|
||||
return Object::Stream(Stream { dict, raw: s.raw.clone() });
|
||||
}
|
||||
let mut named = named_crypt_filter(&s.dict);
|
||||
if pass == Pass::EncryptReplacing && named.as_deref().is_some_and(|n| !h.dict().crypt_filters.iter().any(|(f, _)| f == n)) {
|
||||
drop_crypt_filter(&mut dict);
|
||||
named = None;
|
||||
}
|
||||
let kind = match (&named, ty) {
|
||||
(Some(n), _) => StreamKind::Named(n),
|
||||
(None, Some(b"EmbeddedFile")) => StreamKind::EmbeddedFile,
|
||||
_ => StreamKind::Normal,
|
||||
};
|
||||
let raw = if decrypt { h.decrypt_stream(num, generation, &s.raw, kind) } else { h.encrypt_stream(num, generation, &s.raw, kind) };
|
||||
Object::Stream(Stream { dict, raw: raw.into() })
|
||||
}
|
||||
Object::Array(a) => Object::Array(a.iter().map(|x| walk(x, strings)).collect()),
|
||||
Object::Dict(d) if is_signature_dict(None, d) => signature_dict(d, strings),
|
||||
Object::Dict(d) => Object::Dict(d.iter().map(|(k, v)| (k.clone(), walk(v, strings))).collect()),
|
||||
other => other.clone(),
|
||||
}
|
||||
}
|
||||
|
||||
fn stream(
|
||||
doc: &Document,
|
||||
s: &Stream,
|
||||
strings: &dyn Fn(&PdfString) -> PdfString,
|
||||
h: &SecurityHandler,
|
||||
num: u32,
|
||||
generation: u16,
|
||||
pass: Pass,
|
||||
) -> Object {
|
||||
let decrypt = pass == Pass::Decrypt;
|
||||
let walked = |d: &Dict| -> Dict { d.iter().map(|(k, v)| (k.clone(), walk(v, strings))).collect() };
|
||||
let ty = s.dict.get(b"Type").map(|t| followed(doc, t));
|
||||
let ty = ty.as_deref().and_then(Object::as_name);
|
||||
// Cross-reference streams are never encrypted (§7.5.8), but only reading may trust the
|
||||
// label: a stream a producer calls /XRef stays plaintext if writing believes it, and the
|
||||
// writer builds its own cross-reference streams outside this transform.
|
||||
if (decrypt && ty == Some(b"XRef")) || (ty == Some(b"Metadata") && !h.encrypts_metadata()) {
|
||||
return Object::Stream(Stream { dict: walked(&s.dict), raw: s.raw.clone() });
|
||||
}
|
||||
let mut named = named_crypt_filter(doc, &s.dict);
|
||||
// Before the walk, which then encrypts what is in the dictionary this leaves.
|
||||
let foreign = pass == Pass::EncryptReplacing && named.as_deref().is_some_and(|n| !h.dict().crypt_filters.iter().any(|(f, _)| f == n));
|
||||
let dropped = foreign.then(|| drop_crypt_filter(doc, s));
|
||||
if dropped.is_some() {
|
||||
named = None;
|
||||
}
|
||||
let dict = walked(dropped.as_ref().unwrap_or(&s.dict));
|
||||
let kind = match (&named, ty) {
|
||||
(Some(n), _) => StreamKind::Named(n),
|
||||
(None, Some(b"EmbeddedFile")) => StreamKind::EmbeddedFile,
|
||||
_ => StreamKind::Normal,
|
||||
};
|
||||
let raw = if decrypt { h.decrypt_stream(num, generation, &s.raw, kind) } else { h.encrypt_stream(num, generation, &s.raw, kind) };
|
||||
Object::Stream(Stream { dict, raw: raw.into() })
|
||||
}
|
||||
|
||||
@@ -133,11 +133,12 @@ fn write_stream(s: &Stream, out: &mut Vec<u8>) {
|
||||
|
||||
/// The object as written: encrypted with its (output) number when the document is encrypted,
|
||||
/// except the `/Encrypt` dictionary itself (`source_num` is its number in the source document).
|
||||
/// `o` has the document's numbers in its references ([`crate::security::transform`]).
|
||||
fn prepared<'a>(doc: &Document, source_num: u32, num: u32, generation: u16, o: &'a Object) -> Cow<'a, Object> {
|
||||
match doc.output_security() {
|
||||
(Some(h), encrypt_num) if Some(source_num) != encrypt_num => {
|
||||
(Some(h), encrypt_num) if Some(source_num) != encrypt_num && !doc.stored_as_is(source_num) => {
|
||||
let pass = if doc.encryption_changed() { crate::security::Pass::EncryptReplacing } else { crate::security::Pass::Encrypt };
|
||||
Cow::Owned(crate::security::transform(h, o, num, generation, pass))
|
||||
Cow::Owned(crate::security::transform(doc, h, o, num, generation, pass))
|
||||
}
|
||||
_ => Cow::Borrowed(o),
|
||||
}
|
||||
@@ -287,6 +288,10 @@ pub fn write_full(doc: &Document, opts: &SaveOptions) -> Result<Vec<u8>, CosErro
|
||||
queue.push_back(r);
|
||||
}
|
||||
}
|
||||
// A direct /Encrypt can refer to objects, /CF or /StmF, say.
|
||||
if let Some(encrypt @ Object::Dict(_)) = trailer_in.get(b"Encrypt") {
|
||||
visit_refs(encrypt, &mut queue);
|
||||
}
|
||||
// Unknown trailer entries are document data. Objects they alone reference must be written
|
||||
// too, or a full rewrite would keep the key and drop its value.
|
||||
for (key, value) in trailer_in.iter() {
|
||||
@@ -315,7 +320,10 @@ pub fn write_full(doc: &Document, opts: &SaveOptions) -> Result<Vec<u8>, CosErro
|
||||
// The /Encrypt dictionary and everything it references (e.g. indirect /CF crypt-filter
|
||||
// dictionaries) are needed before anything can be decrypted: never inside object streams.
|
||||
let mut encryption_objects: std::collections::HashSet<ObjRef> = std::collections::HashSet::new();
|
||||
let mut pending: Vec<ObjRef> = trailer_in.reference(b"Encrypt").into_iter().collect();
|
||||
let mut pending: Vec<ObjRef> = Vec::new();
|
||||
if let Some(encrypt) = trailer_in.get(b"Encrypt") {
|
||||
collect_refs(encrypt, &mut |r| pending.push(r));
|
||||
}
|
||||
while let Some(r) = pending.pop() {
|
||||
if encryption_objects.insert(r) {
|
||||
collect_refs(&reader.get(r), &mut |x| pending.push(x));
|
||||
@@ -336,9 +344,10 @@ pub fn write_full(doc: &Document, opts: &SaveOptions) -> Result<Vec<u8>, CosErro
|
||||
if in_stream {
|
||||
packed.push((num, *r));
|
||||
} else {
|
||||
let o = renumber(&*reread(&mut reader, *r, *is_stream)?, &map);
|
||||
let o = reread(&mut reader, *r, *is_stream)?;
|
||||
let o = renumber(&prepared(&reader.document, r.num, num, 0, &o), &map);
|
||||
rows.insert(num, Row::InFile(out.len() as u64, 0));
|
||||
write_indirect(num, 0, &prepared(&reader.document, r.num, num, 0, &o), &mut out);
|
||||
write_indirect(num, 0, &o, &mut out);
|
||||
}
|
||||
}
|
||||
// Object streams take the numbers after the last object. Their contents are not encrypted
|
||||
@@ -368,11 +377,11 @@ pub fn write_full(doc: &Document, opts: &SaveOptions) -> Result<Vec<u8>, CosErro
|
||||
trailer.set(key.to_vec(), Object::Ref(ObjRef::new(*r, 0)));
|
||||
}
|
||||
}
|
||||
if let Some(Object::Dict(d)) = trailer_in.get(b"Encrypt") {
|
||||
trailer.set(b"Encrypt".to_vec(), Object::Dict(d.clone()));
|
||||
if let Some(encrypt @ Object::Dict(_)) = trailer_in.get(b"Encrypt") {
|
||||
trailer.set(b"Encrypt".to_vec(), renumber(encrypt, &map));
|
||||
}
|
||||
if let Some(id) = trailer_in.get(b"ID") {
|
||||
trailer.set(b"ID".to_vec(), id.clone());
|
||||
trailer.set(b"ID".to_vec(), direct_id(&reader.document, id));
|
||||
}
|
||||
for (key, value) in trailer_in.iter() {
|
||||
if !trailer_key_rewritten(key) {
|
||||
@@ -442,6 +451,22 @@ impl ObjectStreamBatch {
|
||||
}
|
||||
}
|
||||
|
||||
/// `/ID` for the trailer, direct, as it has to be with `/Encrypt`: nothing else in the file holds
|
||||
/// what it refers to now. Given by reference it is two entries at most, however many references a
|
||||
/// file gave, so that one large string isn't copied for each. An entry that isn't a string stays in
|
||||
/// its place as an empty one, which is how the key read it.
|
||||
fn direct_id(doc: &Document, id: &Object) -> Object {
|
||||
if matches!(id, Object::Array(a) if !a.iter().any(|s| matches!(s, Object::Ref(_)))) {
|
||||
return id.clone();
|
||||
}
|
||||
let entry = |s: &Object| match &*doc.resolve(s) {
|
||||
s @ Object::String(_) => s.clone(),
|
||||
_ => Object::String(crate::PdfString { bytes: Vec::new(), hex: true }),
|
||||
};
|
||||
let held = doc.resolve(id);
|
||||
Object::Array(held.as_array().into_iter().flatten().take(2).map(entry).collect())
|
||||
}
|
||||
|
||||
/// Trailer keys a full rewrite generates itself. Everything else is copied, with references
|
||||
/// renumbered, so a save does not drop metadata the reader accepted.
|
||||
fn trailer_key_rewritten(key: &[u8]) -> bool {
|
||||
@@ -486,7 +511,7 @@ pub(crate) fn unlinked_additions(doc: &Document) -> HashSet<u32> {
|
||||
pending.into_keys().collect()
|
||||
}
|
||||
|
||||
fn collect_refs(o: &Object, f: &mut impl FnMut(ObjRef)) {
|
||||
pub(crate) fn collect_refs(o: &Object, f: &mut impl FnMut(ObjRef)) {
|
||||
match o {
|
||||
Object::Ref(r) => f(*r),
|
||||
Object::Array(a) => a.iter().for_each(|x| collect_refs(x, f)),
|
||||
@@ -663,6 +688,15 @@ fn civil_from_days(days: i64) -> (i64, u32, u32) {
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
/// `/ID` by reference comes out direct, each entry where it was: the key is made from the first.
|
||||
#[test]
|
||||
fn a_file_identifier_keeps_its_entries_in_their_places() {
|
||||
let doc = Document::new_empty();
|
||||
let string = |bytes: &[u8]| Object::String(crate::PdfString { bytes: bytes.to_vec(), hex: true });
|
||||
let nowhere = Object::Ref(ObjRef::new(9_999, 0));
|
||||
assert_eq!(super::direct_id(&doc, &Object::Array(vec![nowhere, string(b"ab")])), Object::Array(vec![string(b""), string(b"ab")]));
|
||||
}
|
||||
|
||||
use proptest::prelude::*;
|
||||
|
||||
use super::*;
|
||||
|
||||
@@ -494,3 +494,826 @@ fn a_stream_labelled_xref_is_encrypted_when_saved() {
|
||||
let bytes = write_full(&doc, &SaveOptions { object_streams: false, ..SaveOptions::default() }).unwrap();
|
||||
assert!(!bytes.windows(SECRET.len()).any(|w| w == SECRET.as_bytes()), "the labelled stream was written in the clear");
|
||||
}
|
||||
|
||||
/// The content stream's reference.
|
||||
fn contents_of(doc: &Document) -> ObjRef {
|
||||
let catalog = doc.get(doc.root().unwrap()).as_dict().cloned().unwrap();
|
||||
let pages = doc.get(catalog.reference(b"Pages").unwrap()).as_dict().cloned().unwrap();
|
||||
let page = doc.resolve(&pages.get(b"Kids").unwrap().as_array().unwrap()[0]).as_dict().cloned().unwrap();
|
||||
page.reference(b"Contents").unwrap()
|
||||
}
|
||||
|
||||
/// The content stream's data as loaded, whatever its filters say.
|
||||
fn raw_content(doc: &Document) -> String {
|
||||
match &*doc.get(contents_of(doc)) {
|
||||
Object::Stream(s) => String::from_utf8_lossy(&s.raw).trim().to_string(),
|
||||
_ => panic!("no content stream"),
|
||||
}
|
||||
}
|
||||
|
||||
/// Gives the content stream the `/Filter` and `/DecodeParms` of `selector`.
|
||||
fn select(doc: &mut Document, (filter, parms): (Object, Object)) {
|
||||
let contents = contents_of(doc);
|
||||
let Object::Stream(mut s) = doc.get(contents).as_ref().clone() else { panic!("no content stream") };
|
||||
s.dict.set(b"Filter".to_vec(), filter);
|
||||
s.dict.set(b"DecodeParms".to_vec(), parms);
|
||||
doc.set(contents, Object::Stream(s));
|
||||
}
|
||||
|
||||
/// `/Crypt` naming `name`, in the `form`th spelling: all direct, then each part by reference.
|
||||
/// `None` past the last.
|
||||
fn selector(doc: &mut Document, form: usize, name: &str) -> Option<(Object, Object)> {
|
||||
let crypt = Object::name("Crypt");
|
||||
let parms = |n: Object| {
|
||||
let mut d = pdfcraft_cos::Dict::new();
|
||||
d.set(b"Name".to_vec(), n);
|
||||
Object::Dict(d)
|
||||
};
|
||||
let named = parms(Object::name(name));
|
||||
Some(match form {
|
||||
0 => (crypt, named),
|
||||
1 => (crypt, Object::Ref(doc.add(named))),
|
||||
2 => (Object::Array(vec![crypt]), Object::Array(vec![Object::Ref(doc.add(named))])),
|
||||
3 => (Object::Array(vec![crypt]), Object::Ref(doc.add(Object::Array(vec![named])))),
|
||||
4 => (crypt, parms(Object::Ref(doc.add(Object::name(name))))),
|
||||
5 => (Object::Ref(doc.add(crypt)), named),
|
||||
6 => (Object::Ref(doc.add(Object::Array(vec![crypt]))), Object::Array(vec![named])),
|
||||
7 => (Object::Array(vec![Object::Ref(doc.add(crypt))]), Object::Array(vec![named])),
|
||||
// Behind a filter given by reference: places in the two arrays pair up all the same.
|
||||
8 => (Object::Array(vec![Object::Ref(doc.add(Object::name("ASCIIHexDecode"))), crypt]), Object::Array(vec![Object::Null, named])),
|
||||
// The two entries in different forms, which is how a lone filter is usually spelled.
|
||||
9 => (Object::Array(vec![crypt]), named),
|
||||
10 => (crypt, Object::Array(vec![named])),
|
||||
// The filter twice, which names the first's.
|
||||
11 => (Object::Array(vec![crypt.clone(), crypt]), Object::Array(vec![named.clone(), named])),
|
||||
// A reference to a reference.
|
||||
12 => {
|
||||
let name = doc.add(Object::name(name));
|
||||
let hop = doc.add(Object::Ref(name));
|
||||
(crypt, parms(Object::Ref(hop)))
|
||||
}
|
||||
_ => return None,
|
||||
})
|
||||
}
|
||||
|
||||
fn holds(bytes: &[u8], text: &str) -> bool {
|
||||
String::from_utf8_lossy(bytes).contains(text)
|
||||
}
|
||||
|
||||
/// An object `/Encrypt` names is written as stored only while it is as stored. A file whose
|
||||
/// `/Encrypt` names its `/Info` reads that dictionary as stored; once the title is edited, both
|
||||
/// saves encrypt it rather than writing the new title in the clear.
|
||||
#[test]
|
||||
fn an_edited_object_that_encrypt_names_is_encrypted() {
|
||||
let mut doc = Document::open(Arc::new(fixture())).unwrap();
|
||||
doc.set_encryption(&NewEncryption {
|
||||
algorithm: Algorithm::Aes128,
|
||||
user_password: "",
|
||||
owner_password: "owner",
|
||||
permissions: -1,
|
||||
encrypt_metadata: true,
|
||||
seed: [9; 32],
|
||||
})
|
||||
.unwrap();
|
||||
let info = doc.trailer().reference(b"Info").unwrap();
|
||||
let mut dict = doc.get(doc.trailer().reference(b"Encrypt").unwrap()).as_dict().cloned().unwrap();
|
||||
dict.set(b"Junk".to_vec(), Object::Ref(info));
|
||||
doc.trailer_mut().set(b"Encrypt".to_vec(), Object::Dict(dict));
|
||||
let bytes = write_full(&doc, &SaveOptions::default()).unwrap();
|
||||
let mut doc = Document::open(Arc::new(bytes)).unwrap();
|
||||
let info = doc.trailer().reference(b"Info").unwrap();
|
||||
doc.update_dict(info, |d| d.set(b"Title".to_vec(), PdfString::text("Merger plan"))).unwrap();
|
||||
for (save, saved) in [("incremental", write_incremental(&doc, &SaveOptions::default())), ("full", write_full(&doc, &SaveOptions::default()))] {
|
||||
assert!(!holds(&saved.unwrap(), "Merger plan"), "{save}: the edited title was written in the clear");
|
||||
}
|
||||
}
|
||||
|
||||
/// A stream can select its crypt filter by reference at every step: the chain, an entry of it, the
|
||||
/// parameters, an entry of those, the name (ISO 32000-2 §7.3.10, §7.4.10). Read as absent, the
|
||||
/// filter was `/Identity`, so such a stream was saved in the clear and, in a file from elsewhere,
|
||||
/// its ciphertext read as data. A full save renumbers: what it follows has the document's numbers.
|
||||
#[test]
|
||||
fn a_crypt_filter_selected_by_reference_is_used() {
|
||||
for alg in [Algorithm::Aes128, Algorithm::Aes256] {
|
||||
for form in 0.. {
|
||||
let mut doc = Document::open(Arc::new(protect(alg, "", "owner", -1))).unwrap();
|
||||
let Some(selected) = selector(&mut doc, form, "StdCF") else { break };
|
||||
select(&mut doc, selected);
|
||||
let saved = write_incremental(&doc, &SaveOptions::default()).unwrap();
|
||||
assert!(!holds(&saved, "Secret page"), "{alg:?} form {form}: saved encrypted");
|
||||
let back = Document::open(Arc::new(saved)).unwrap();
|
||||
assert_eq!(raw_content(&back), SECRET, "{alg:?} form {form}: read back");
|
||||
let full = write_full(&back, &SaveOptions::default()).unwrap();
|
||||
assert!(!holds(&full, "Secret page"), "{alg:?} form {form}: renumbered, encrypted");
|
||||
assert_eq!(raw_content(&Document::open(Arc::new(full)).unwrap()), SECRET, "{alg:?} form {form}: renumbered");
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/// A reference to a stream that takes `follows` references to read cold, this one included: its
|
||||
/// nine filters are all read, the last leading to the next stream.
|
||||
fn spends(doc: &mut Document, follows: usize) -> Object {
|
||||
let left = follows - 1;
|
||||
let mut filters: Vec<Object> = (0..left.min(8)).map(|i| Object::Ref(doc.add(Object::Int(i as i64)))).collect();
|
||||
if left > 8 {
|
||||
filters.push(spends(doc, left - 8));
|
||||
}
|
||||
let mut dict = pdfcraft_cos::Dict::new();
|
||||
dict.set(b"Filter".to_vec(), Object::Array(filters));
|
||||
Object::Ref(doc.add(Object::Stream(pdfcraft_cos::Stream::from_raw(dict, Vec::new()))))
|
||||
}
|
||||
|
||||
/// Gives the content stream a `/Type` that takes `follows` references to read, ahead of its filter.
|
||||
fn spend_first(doc: &mut Document, follows: usize) {
|
||||
let spent = spends(doc, follows);
|
||||
let contents = contents_of(doc);
|
||||
let Object::Stream(mut s) = doc.get(contents).as_ref().clone() else { panic!("no content stream") };
|
||||
s.dict.set(b"Type".to_vec(), spent);
|
||||
doc.set(contents, Object::Stream(s));
|
||||
}
|
||||
|
||||
/// Past what one read may follow a reference reads as absent, and a crypt filter with no `/Name` is
|
||||
/// `/Identity`. Together those would read this stream's ciphertext as data, so what can't be told
|
||||
/// is the document's own filter, as a `/Filter` that can't be read is.
|
||||
#[test]
|
||||
fn a_crypt_filter_past_what_a_read_may_follow_is_the_documents_own() {
|
||||
let mut doc = Document::open(Arc::new(protect(Algorithm::Aes128, "", "owner", -1))).unwrap();
|
||||
let selected = selector(&mut doc, 1, "StdCF").unwrap();
|
||||
select(&mut doc, selected);
|
||||
spend_first(&mut doc, 40);
|
||||
let saved = write_incremental(&doc, &SaveOptions::default()).unwrap();
|
||||
assert!(!holds(&saved, "Secret page"), "saved encrypted");
|
||||
let back = Document::open(Arc::new(saved)).unwrap();
|
||||
assert_eq!(raw_content(&back), SECRET);
|
||||
let full = write_full(&back, &SaveOptions::default()).unwrap();
|
||||
assert!(!holds(&full, "Secret page"), "renumbered, encrypted");
|
||||
assert_eq!(raw_content(&Document::open(Arc::new(full)).unwrap()), SECRET, "renumbered");
|
||||
}
|
||||
|
||||
/// A read that takes all it may follow has refused nothing: a crypt filter with no `/Name` after it
|
||||
/// is still `/Identity`, and the stream is in the clear.
|
||||
#[test]
|
||||
fn a_crypt_filter_with_no_name_after_all_a_read_may_follow_is_identity() {
|
||||
let mut doc = Document::open(Arc::new(protect(Algorithm::Aes128, "", "owner", -1))).unwrap();
|
||||
select(&mut doc, (Object::name("Crypt"), Object::Dict(pdfcraft_cos::Dict::new())));
|
||||
spend_first(&mut doc, 32);
|
||||
let saved = write_incremental(&doc, &SaveOptions::default()).unwrap();
|
||||
assert!(holds(&saved, "Secret page"), "written as the stream asks");
|
||||
assert_eq!(raw_content(&Document::open(Arc::new(saved)).unwrap()), SECRET);
|
||||
}
|
||||
|
||||
/// `/Identity` selected by reference keeps a stream in the clear in a document that encrypts the
|
||||
/// rest, in every spelling, on both saves.
|
||||
#[test]
|
||||
fn an_identity_crypt_filter_selected_by_reference_leaves_a_stream_alone() {
|
||||
for form in 0.. {
|
||||
let mut doc = Document::open(Arc::new(protect(Algorithm::Aes128, "", "owner", -1))).unwrap();
|
||||
let Some(selected) = selector(&mut doc, form, "Identity") else { break };
|
||||
select(&mut doc, selected);
|
||||
let saved = write_incremental(&doc, &SaveOptions::default()).unwrap();
|
||||
assert!(holds(&saved, "Secret page"), "form {form}: written as the stream asks");
|
||||
let back = Document::open(Arc::new(saved)).unwrap();
|
||||
assert_eq!(raw_content(&back), SECRET, "form {form}");
|
||||
let full = write_full(&back, &SaveOptions::default()).unwrap();
|
||||
assert!(holds(&full, "Secret page"), "form {form}: renumbered");
|
||||
assert_eq!(raw_content(&Document::open(Arc::new(full)).unwrap()), SECRET, "form {form}: renumbered");
|
||||
}
|
||||
}
|
||||
|
||||
/// New protection drops a crypt filter it doesn't define, whichever way the stream selected it. The
|
||||
/// chain comes out direct. Parameters in the stream's own dictionary stay, encrypted with it; of an
|
||||
/// array in an object of its own, which every stream can share, only what decoders read is copied.
|
||||
#[test]
|
||||
fn protecting_drops_a_crypt_filter_selected_by_reference() {
|
||||
let protected = |doc: &mut Document| {
|
||||
doc.set_encryption(&NewEncryption {
|
||||
algorithm: Algorithm::Aes256,
|
||||
user_password: "",
|
||||
owner_password: "owner",
|
||||
permissions: -1,
|
||||
encrypt_metadata: true,
|
||||
seed: [7; 32],
|
||||
})
|
||||
.unwrap();
|
||||
write_full(doc, &SaveOptions::default()).unwrap()
|
||||
};
|
||||
for form in 0.. {
|
||||
let mut doc = Document::open(Arc::new(fixture())).unwrap();
|
||||
let Some(selected) = selector(&mut doc, form, "MyCF") else { break };
|
||||
select(&mut doc, selected);
|
||||
let bytes = protected(&mut doc);
|
||||
assert!(!holds(&bytes, "Secret page"), "form {form}: encrypted");
|
||||
assert!(!holds(&bytes, "MyCF"), "form {form}: no selector left in the stream");
|
||||
let back = Document::open(Arc::new(bytes.clone())).unwrap();
|
||||
assert_eq!(raw_content(&back), SECRET, "form {form}");
|
||||
let contents = back.get(contents_of(&back));
|
||||
let filter = contents.as_dict().unwrap().get(b"Filter");
|
||||
match form {
|
||||
8 => assert!(
|
||||
matches!(filter, Some(Object::Array(a)) if matches!(a.as_slice(), [Object::Ref(_)])),
|
||||
"form 8: the other filter stays: {filter:?}"
|
||||
),
|
||||
_ => assert_eq!(filter, None, "form {form}"),
|
||||
}
|
||||
assert!(hayro_syntax::Pdf::new(bytes).is_ok(), "form {form}");
|
||||
}
|
||||
for shared in [false, true] {
|
||||
let mut doc = Document::open(Arc::new(fixture())).unwrap();
|
||||
let mut named = pdfcraft_cos::Dict::new();
|
||||
named.set(b"Name".to_vec(), Object::name("MyCF"));
|
||||
let mut other = pdfcraft_cos::Dict::new();
|
||||
other.set(b"Note".to_vec(), Object::String(PdfString::text("Private note")));
|
||||
other.set(b"Predictor".to_vec(), Object::Int(1));
|
||||
let parms = Object::Array(vec![Object::Dict(named), Object::Dict(other)]);
|
||||
let parms = if shared { Object::Ref(doc.add(parms)) } else { parms };
|
||||
select(&mut doc, (Object::Array(vec![Object::name("Crypt"), Object::name("ASCIIHexDecode")]), parms));
|
||||
let bytes = protected(&mut doc);
|
||||
assert!(!holds(&bytes, "Private note"), "shared: {shared}");
|
||||
let back = Document::open(Arc::new(bytes)).unwrap();
|
||||
let contents = back.get(contents_of(&back));
|
||||
let kept = contents.as_dict().unwrap().get(b"DecodeParms").unwrap().as_array().unwrap();
|
||||
assert_eq!(kept.len(), 1, "one filter left, one entry");
|
||||
let kept = kept[0].as_dict().unwrap();
|
||||
assert_eq!(kept.get(b"Predictor"), Some(&Object::Int(1)), "shared: {shared}");
|
||||
assert_eq!(kept.get(b"Note").is_some(), !shared, "shared: {shared}");
|
||||
}
|
||||
}
|
||||
|
||||
/// Every stream of a file can share one large object as its `/DecodeParms` or `/Filter`, which
|
||||
/// costs nothing until new protection drops a crypt filter from each. Copied whole, a 1 MB file
|
||||
/// came out at 1 GB.
|
||||
#[test]
|
||||
fn protecting_copies_no_large_object_into_every_stream() {
|
||||
let pad = Object::Array(vec![Object::Int(1); 100_000]);
|
||||
let mut doc = Document::open(Arc::new(fixture())).unwrap();
|
||||
let mut large = pdfcraft_cos::Dict::new();
|
||||
large.set(b"Pad".to_vec(), pad.clone());
|
||||
let parms = doc.add(Object::Array(vec![Object::Null, Object::Dict(large)]));
|
||||
let filter = doc.add(Object::Array(vec![Object::name("Crypt"), Object::Name(vec![b'A'; 100_000]), pad]));
|
||||
let mut streams = Vec::new();
|
||||
for _ in 0..200 {
|
||||
let mut by_parms = pdfcraft_cos::Dict::new();
|
||||
by_parms.set(b"Filter".to_vec(), Object::Array(vec![Object::name("Crypt"), Object::name("ASCIIHexDecode")]));
|
||||
by_parms.set(b"DecodeParms".to_vec(), Object::Ref(parms));
|
||||
streams.push(Object::Ref(doc.add(Object::Stream(pdfcraft_cos::Stream::from_raw(by_parms, b"41>".to_vec())))));
|
||||
let mut by_filter = pdfcraft_cos::Dict::new();
|
||||
by_filter.set(b"Filter".to_vec(), Object::Ref(filter));
|
||||
streams.push(Object::Ref(doc.add(Object::Stream(pdfcraft_cos::Stream::from_raw(by_filter, b"41>".to_vec())))));
|
||||
}
|
||||
doc.update_dict(doc.root().unwrap(), |c| c.set(b"Test".to_vec(), Object::Array(streams))).unwrap();
|
||||
doc.set_encryption(&NewEncryption {
|
||||
algorithm: Algorithm::Aes256,
|
||||
user_password: "",
|
||||
owner_password: "owner",
|
||||
permissions: -1,
|
||||
encrypt_metadata: true,
|
||||
seed: [7; 32],
|
||||
})
|
||||
.unwrap();
|
||||
let bytes = write_full(&doc, &SaveOptions { object_streams: false, ..SaveOptions::default() }).unwrap();
|
||||
assert!(bytes.len() < 1 << 20, "{} bytes", bytes.len());
|
||||
}
|
||||
|
||||
/// A file can name one large string thousands of times in `/ID`, which holds two. An encrypted file
|
||||
/// keeps its `/ID`, so each copy would be in the file a save writes.
|
||||
#[test]
|
||||
fn a_file_identifier_of_many_references_is_two_strings() {
|
||||
let mut doc = Document::open(Arc::new(fixture())).unwrap();
|
||||
doc.set_encryption(&NewEncryption {
|
||||
algorithm: Algorithm::Aes128,
|
||||
user_password: "",
|
||||
owner_password: "owner",
|
||||
permissions: -1,
|
||||
encrypt_metadata: true,
|
||||
seed: [9; 32],
|
||||
})
|
||||
.unwrap();
|
||||
let large = doc.add(Object::String(PdfString { bytes: vec![0xAB; 100_000], hex: true }));
|
||||
doc.trailer_mut().set(b"ID".to_vec(), Object::Array(vec![Object::Ref(large); 500]));
|
||||
let bytes = write_full(&doc, &SaveOptions { object_streams: false, ..SaveOptions::default() }).unwrap();
|
||||
assert!(bytes.len() < 1 << 20, "{} bytes", bytes.len());
|
||||
}
|
||||
|
||||
/// What a file can do with those references: point a stream's selector at the stream itself, or at
|
||||
/// nothing. They read as absent, so a stream with `/Crypt` is `/Identity` (ISO 32000-2 §7.4.10),
|
||||
/// and one that names no filter follows the document's. Loading ends either way.
|
||||
#[test]
|
||||
fn a_crypt_filter_reference_to_itself_or_nothing_reads_as_absent() {
|
||||
let named = |n: Object| {
|
||||
let mut d = pdfcraft_cos::Dict::new();
|
||||
d.set(b"Name".to_vec(), n);
|
||||
Object::Dict(d)
|
||||
};
|
||||
for (what, encrypted) in [
|
||||
("/Filter to itself", true),
|
||||
("/Filter nowhere", true),
|
||||
("/DecodeParms to itself", false),
|
||||
("/DecodeParms nowhere", false),
|
||||
("/Name to itself", false),
|
||||
("/Name nowhere", false),
|
||||
] {
|
||||
let mut doc = Document::open(Arc::new(protect(Algorithm::Aes128, "", "owner", -1))).unwrap();
|
||||
let me = Object::Ref(contents_of(&doc));
|
||||
let nowhere = Object::Ref(ObjRef::new(9_999, 0));
|
||||
let crypt = Object::name("Crypt");
|
||||
select(
|
||||
&mut doc,
|
||||
match what {
|
||||
"/Filter to itself" => (me, Object::Null),
|
||||
"/Filter nowhere" => (nowhere, Object::Null),
|
||||
"/DecodeParms to itself" => (crypt, me),
|
||||
"/DecodeParms nowhere" => (crypt, nowhere),
|
||||
"/Name to itself" => (crypt, named(me)),
|
||||
_ => (crypt, named(nowhere)),
|
||||
},
|
||||
);
|
||||
let saved = write_incremental(&doc, &SaveOptions::default()).unwrap();
|
||||
assert_eq!(!holds(&saved, "Secret page"), encrypted, "{what}");
|
||||
assert_eq!(raw_content(&Document::open(Arc::new(saved)).unwrap()), SECRET, "{what}");
|
||||
}
|
||||
}
|
||||
|
||||
/// A lone parameter dictionary belongs to the first filter, so `/Crypt` behind another filter has
|
||||
/// none of its own and is `/Identity` (ISO 32000-2 §7.4.1), whatever that dictionary says.
|
||||
#[test]
|
||||
fn a_lone_parameter_dictionary_is_the_first_filters() {
|
||||
let mut doc = Document::open(Arc::new(protect(Algorithm::Aes128, "", "owner", -1))).unwrap();
|
||||
let mut parms = pdfcraft_cos::Dict::new();
|
||||
parms.set(b"Name".to_vec(), Object::name("StdCF"));
|
||||
let first = Object::Array(vec![Object::name("Crypt"), Object::name("ASCIIHexDecode")]);
|
||||
let second = Object::Array(vec![Object::name("ASCIIHexDecode"), Object::name("Crypt")]);
|
||||
select(&mut doc, (first, Object::Dict(parms.clone())));
|
||||
assert!(!holds(&write_incremental(&doc, &SaveOptions::default()).unwrap(), "Secret page"), "first: it names StdCF");
|
||||
select(&mut doc, (second, Object::Dict(parms)));
|
||||
assert!(holds(&write_incremental(&doc, &SaveOptions::default()).unwrap(), "Secret page"), "second: it names nothing");
|
||||
}
|
||||
|
||||
/// A lone parameter dictionary is the first filter's, so dropping a `/Crypt` behind that filter
|
||||
/// leaves it, and dropping one in front of it takes it away.
|
||||
#[test]
|
||||
fn protecting_keeps_the_parameters_of_the_filter_before_a_crypt_filter() {
|
||||
let protected = |filters: Vec<Object>| {
|
||||
let mut doc = Document::open(Arc::new(fixture())).unwrap();
|
||||
let mut parms = pdfcraft_cos::Dict::new();
|
||||
parms.set(b"Name".to_vec(), Object::name("MyCF"));
|
||||
select(&mut doc, (Object::Array(filters), Object::Dict(parms)));
|
||||
doc.set_encryption(&NewEncryption {
|
||||
algorithm: Algorithm::Aes256,
|
||||
user_password: "",
|
||||
owner_password: "owner",
|
||||
permissions: -1,
|
||||
encrypt_metadata: true,
|
||||
seed: [7; 32],
|
||||
})
|
||||
.unwrap();
|
||||
let back = Document::open(Arc::new(write_full(&doc, &SaveOptions::default()).unwrap())).unwrap();
|
||||
back.get(contents_of(&back)).as_dict().unwrap().contains(b"DecodeParms")
|
||||
};
|
||||
let (hex, crypt) = (Object::name("ASCIIHexDecode"), Object::name("Crypt"));
|
||||
assert!(protected(vec![hex.clone(), crypt.clone()]), "the first filter's, which stays");
|
||||
assert!(!protected(vec![crypt, hex]), "/Crypt's, which goes");
|
||||
}
|
||||
|
||||
/// Dropping `/Crypt` takes its entry out of `/DecodeParms`, and an array too short to have one is
|
||||
/// left as it is, given directly or by reference.
|
||||
#[test]
|
||||
fn protecting_leaves_a_parameter_array_too_short_for_the_crypt_filter() {
|
||||
for by_reference in [false, true] {
|
||||
let mut doc = Document::open(Arc::new(fixture())).unwrap();
|
||||
let short = Object::Array(vec![Object::Null]);
|
||||
let parms = if by_reference { Object::Ref(doc.add(short)) } else { short };
|
||||
select(&mut doc, (Object::Array(vec![Object::name("ASCIIHexDecode"), Object::name("Crypt")]), parms));
|
||||
doc.set_encryption(&NewEncryption {
|
||||
algorithm: Algorithm::Aes256,
|
||||
user_password: "",
|
||||
owner_password: "owner",
|
||||
permissions: -1,
|
||||
encrypt_metadata: true,
|
||||
seed: [7; 32],
|
||||
})
|
||||
.unwrap();
|
||||
let bytes = write_full(&doc, &SaveOptions::default()).unwrap();
|
||||
assert!(!holds(&bytes, "Secret page"), "by reference: {by_reference}");
|
||||
let back = Document::open(Arc::new(bytes)).unwrap();
|
||||
assert_eq!(raw_content(&back), SECRET, "by reference: {by_reference}");
|
||||
let contents = back.get(contents_of(&back));
|
||||
let filter = contents.as_dict().unwrap().get(b"Filter").unwrap().as_array().unwrap();
|
||||
assert_eq!(filter.len(), 1, "only /Crypt goes");
|
||||
assert_eq!(filter[0].as_name(), Some(b"ASCIIHexDecode".as_slice()), "the other filter stays as it was");
|
||||
}
|
||||
}
|
||||
|
||||
/// A chain of up to [`pdfcraft_filters::MAX_CHAIN`] filters and `/Crypt` is read; a longer one
|
||||
/// names no crypt filter, so its entries aren't followed for every stream sharing it.
|
||||
#[test]
|
||||
fn a_chain_longer_than_any_decoder_takes_names_no_crypt_filter() {
|
||||
let chain = |others: usize| {
|
||||
let mut doc = Document::open(Arc::new(protect(Algorithm::Aes128, "", "owner", -1))).unwrap();
|
||||
let mut filters = vec![Object::name("ASCIIHexDecode"); others];
|
||||
filters.push(Object::name("Crypt"));
|
||||
let array = doc.add(Object::Array(filters));
|
||||
select(&mut doc, (Object::Ref(array), Object::Null));
|
||||
holds(&write_incremental(&doc, &SaveOptions::default()).unwrap(), "Secret page")
|
||||
};
|
||||
assert!(chain(pdfcraft_filters::MAX_CHAIN), "the longest chain read: /Identity, in the clear");
|
||||
assert!(!chain(pdfcraft_filters::MAX_CHAIN + 1), "one more: the document's filter");
|
||||
}
|
||||
|
||||
/// A stream's `/Type` by reference picks its handling like one given directly: metadata left
|
||||
/// readable under `/EncryptMetadata false`, an embedded file under `/EFF`.
|
||||
#[test]
|
||||
fn a_stream_type_given_by_reference_picks_its_crypt_filter() {
|
||||
let mut doc = Document::open(Arc::new(fixture())).unwrap();
|
||||
let catalog = doc.get(doc.root().unwrap()).as_dict().cloned().unwrap();
|
||||
let meta = catalog.reference(b"Metadata").unwrap();
|
||||
let ty = doc.add(Object::name("Metadata"));
|
||||
let Object::Stream(mut s) = doc.get(meta).as_ref().clone() else { panic!("no metadata stream") };
|
||||
s.dict.set(b"Type".to_vec(), Object::Ref(ty));
|
||||
doc.set(meta, Object::Stream(s));
|
||||
doc.set_encryption(&NewEncryption {
|
||||
algorithm: Algorithm::Aes256,
|
||||
user_password: "",
|
||||
owner_password: "o",
|
||||
permissions: -1,
|
||||
encrypt_metadata: false,
|
||||
seed: [5; 32],
|
||||
})
|
||||
.unwrap();
|
||||
let bytes = write_full(&doc, &SaveOptions::default()).unwrap();
|
||||
assert!(holds(&bytes, "<x:xmpmeta>meta</x:xmpmeta>"), "search engines can read XMP");
|
||||
|
||||
let mut doc = Document::open(Arc::new(protect(Algorithm::Aes128, "", "owner", -1))).unwrap();
|
||||
let encrypt = doc.trailer().reference(b"Encrypt").unwrap();
|
||||
doc.update_dict(encrypt, |e| e.set(b"EFF".to_vec(), Object::name("Identity"))).unwrap();
|
||||
let mut doc = Document::open(Arc::new(write_incremental(&doc, &SaveOptions::default()).unwrap())).unwrap();
|
||||
let contents = contents_of(&doc);
|
||||
let ty = doc.add(Object::name("EmbeddedFile"));
|
||||
let Object::Stream(mut s) = doc.get(contents).as_ref().clone() else { panic!("no content stream") };
|
||||
s.dict.set(b"Type".to_vec(), Object::Ref(ty));
|
||||
doc.set(contents, Object::Stream(s));
|
||||
assert!(holds(&write_incremental(&doc, &SaveOptions::default()).unwrap(), "Secret page"), "/EFF /Identity leaves it alone");
|
||||
}
|
||||
|
||||
/// What makes a dictionary a signature's can be given by reference, and what is null or refers to
|
||||
/// nothing is absent: `/Contents` stays as written in each of these.
|
||||
#[test]
|
||||
fn a_signature_dictionary_is_known_in_every_form() {
|
||||
let mut doc = Document::open(Arc::new(fixture())).unwrap();
|
||||
let ty = doc.add(Object::name("Sig"));
|
||||
let range = Object::Array([0, 10, 20, 30].into_iter().map(Object::Int).collect());
|
||||
let by_reference = doc.add(range.clone());
|
||||
let nowhere = Object::Ref(ObjRef::new(9_999, 0));
|
||||
let forms: [(Vec<(&str, Object)>, &str); 5] = [
|
||||
(vec![("Type", Object::Ref(ty))], "DEAD"),
|
||||
(vec![("ByteRange", Object::Ref(by_reference))], "BEEF"),
|
||||
(vec![("Type", Object::Null), ("ByteRange", range.clone())], "CAFE"),
|
||||
(vec![("Type", nowhere.clone()), ("ByteRange", range.clone())], "F00D"),
|
||||
(vec![("Subtype", nowhere), ("ByteRange", range)], "D00D"),
|
||||
];
|
||||
let mut signatures = Vec::new();
|
||||
for (entries, contents) in forms {
|
||||
let mut sig = pdfcraft_cos::Dict::new();
|
||||
for (key, value) in entries {
|
||||
sig.set(key.as_bytes().to_vec(), value);
|
||||
}
|
||||
let bytes = (0..contents.len()).step_by(2).map(|i| u8::from_str_radix(&contents[i..i + 2], 16).unwrap()).collect();
|
||||
sig.set(b"Contents".to_vec(), Object::String(PdfString { bytes, hex: true }));
|
||||
signatures.push(Object::Ref(doc.add(Object::Dict(sig))));
|
||||
}
|
||||
// Nested in another object, it follows nothing, but known directly it is one all the same.
|
||||
let mut nested = pdfcraft_cos::Dict::new();
|
||||
nested.set(b"Type".to_vec(), Object::name("Sig"));
|
||||
nested.set(b"Contents".to_vec(), Object::String(PdfString { bytes: vec![0xAB, 0xBA], hex: true }));
|
||||
let mut field = pdfcraft_cos::Dict::new();
|
||||
field.set(b"V".to_vec(), Object::Dict(nested));
|
||||
signatures.push(Object::Ref(doc.add(Object::Dict(field))));
|
||||
// Neither of what makes one: a string /Contents alone is anybody's, so it's encrypted.
|
||||
let mut other = pdfcraft_cos::Dict::new();
|
||||
other.set(b"Contents".to_vec(), Object::String(PdfString { bytes: vec![0xAB, 0xCD], hex: true }));
|
||||
signatures.push(Object::Ref(doc.add(Object::Dict(other))));
|
||||
doc.update_dict(doc.root().unwrap(), |c| c.set(b"Test".to_vec(), Object::Array(signatures))).unwrap();
|
||||
doc.set_encryption(&NewEncryption {
|
||||
algorithm: Algorithm::Aes256,
|
||||
user_password: "",
|
||||
owner_password: "owner",
|
||||
permissions: -1,
|
||||
encrypt_metadata: true,
|
||||
seed: [3; 32],
|
||||
})
|
||||
.unwrap();
|
||||
let bytes = write_full(&doc, &SaveOptions { object_streams: false, ..SaveOptions::default() }).unwrap();
|
||||
for contents in ["DEAD", "BEEF", "CAFE", "F00D", "D00D", "ABBA"] {
|
||||
assert!(holds(&bytes, &format!("<{contents}>")), "{contents}: written as is");
|
||||
}
|
||||
assert!(!holds(&bytes, "<ABCD>"), "without a /ByteRange it is no signature");
|
||||
}
|
||||
|
||||
/// What a test needs to write an update of a classic file protected with AES-128.
|
||||
struct Classic {
|
||||
bytes: Vec<u8>,
|
||||
root: ObjRef,
|
||||
pages: ObjRef,
|
||||
info: ObjRef,
|
||||
encrypt: ObjRef,
|
||||
id: Vec<u8>,
|
||||
dict: pdfcraft_cos::Dict,
|
||||
}
|
||||
|
||||
fn classic_file() -> Classic {
|
||||
let mut doc = Document::open(Arc::new(fixture())).unwrap();
|
||||
doc.set_encryption(&NewEncryption {
|
||||
algorithm: Algorithm::Aes128,
|
||||
user_password: "",
|
||||
owner_password: "owner",
|
||||
permissions: -1,
|
||||
encrypt_metadata: true,
|
||||
seed: [9; 32],
|
||||
})
|
||||
.unwrap();
|
||||
let bytes = write_full(&doc, &SaveOptions { object_streams: false, ..SaveOptions::default() }).unwrap();
|
||||
let doc = Document::open(Arc::new(bytes.clone())).unwrap();
|
||||
let encrypt = doc.trailer().reference(b"Encrypt").unwrap();
|
||||
let id = doc.trailer().get(b"ID").unwrap().as_array().unwrap()[0].as_string().unwrap().bytes.clone();
|
||||
let dict = doc.get(encrypt).as_dict().cloned().unwrap();
|
||||
let pages = doc.get(doc.root().unwrap()).as_dict().unwrap().reference(b"Pages").unwrap();
|
||||
Classic { root: doc.root().unwrap(), pages, info: doc.trailer().reference(b"Info").unwrap(), bytes, encrypt, id, dict }
|
||||
}
|
||||
|
||||
fn hex(bytes: &[u8]) -> String {
|
||||
bytes.iter().map(|b| format!("{b:02X}")).collect()
|
||||
}
|
||||
|
||||
/// `bytes` with an update appended: `objects`, and a trailer of `trailer` entries, in which `@n`
|
||||
/// stands for the offset of object `n`. An object with nothing in it gets an entry of the
|
||||
/// cross-reference table that points at nothing.
|
||||
fn updated(bytes: &[u8], objects: &[(u32, Vec<u8>)], trailer: &str) -> Vec<u8> {
|
||||
let at = bytes.windows(9).rposition(|w| w == b"startxref").unwrap();
|
||||
let prev: usize = String::from_utf8_lossy(&bytes[at + 9..]).split_whitespace().next().unwrap().parse().unwrap();
|
||||
let mut out = bytes.to_vec();
|
||||
let mut table = String::from("xref\n");
|
||||
let mut trailer = trailer.to_string();
|
||||
for (num, body) in objects {
|
||||
if body.is_empty() {
|
||||
table.push_str(&format!("{num} 1\n0000000010 00000 n \n"));
|
||||
continue;
|
||||
}
|
||||
trailer = trailer.replace(&format!("@{num}"), &out.len().to_string());
|
||||
table.push_str(&format!("{num} 1\n{:010} 00000 n \n", out.len()));
|
||||
out.extend_from_slice(format!("{num} 0 obj\n").as_bytes());
|
||||
out.extend_from_slice(body);
|
||||
out.extend_from_slice(b"\nendobj\n");
|
||||
}
|
||||
let xref = out.len();
|
||||
out.extend_from_slice(table.as_bytes());
|
||||
out.extend_from_slice(format!("trailer\n<< {trailer} /Size 2000 /Prev {prev} >>\nstartxref\n{xref}\n%%EOF\n").as_bytes());
|
||||
out
|
||||
}
|
||||
|
||||
/// The `/Encrypt` dictionary of `file`, with `/O`, `/StmF` and `/StrF` as given.
|
||||
fn encrypt_with(file: &Classic, o: &str, filter: &str) -> Vec<u8> {
|
||||
let string = |key: &[u8]| hex(&file.dict.get(key).unwrap().as_string().unwrap().bytes);
|
||||
format!(
|
||||
"<< /Filter /Standard /V 4 /R 4 /Length 128 /P {} /O {o} /U <{}> /CF << /StdCF << /CFM /AESV2 /Length 16 /AuthEvent /DocOpen >> >> /StmF /{filter} /StrF /{filter} >>",
|
||||
file.dict.int(b"P").unwrap(),
|
||||
string(b"U")
|
||||
)
|
||||
.into_bytes()
|
||||
}
|
||||
|
||||
/// An object stream can have its parameters by reference, and a stream's crypt filter can be
|
||||
/// selected by a member of it: legal together, though each is rare. What reads the stream first
|
||||
/// goes through the object stream, and members must come out of it as they do read directly. They
|
||||
/// didn't, while a read made for a selector wasn't allowed to follow its own: the object stream was
|
||||
/// kept undecoded, its members lost for good, and a full save wrote nulls without saying so.
|
||||
#[test]
|
||||
fn an_object_stream_reached_from_a_selector_keeps_its_members() {
|
||||
let file = classic_file();
|
||||
let parms = "[<< /Name /Identity >> null]";
|
||||
let header = format!("902 0 903 {} ", parms.len() + 1);
|
||||
let members = format!("{header}{parms} << /Keep (yes) >>");
|
||||
let (mut rows, mut before) = (vec![1u8], 0u8);
|
||||
for b in members.bytes() {
|
||||
rows.push(b.wrapping_sub(before));
|
||||
before = b;
|
||||
}
|
||||
let coded = pdfcraft_cos::Stream::flate(pdfcraft_cos::Dict::new(), &rows).raw;
|
||||
let mut object_stream =
|
||||
format!("<< /Type /ObjStm /N 2 /First {} /Filter /FlateDecode /DecodeParms 911 0 R /Length {} >>\nstream\n", header.len(), coded.len())
|
||||
.into_bytes();
|
||||
object_stream.extend_from_slice(&coded);
|
||||
object_stream.extend_from_slice(b"\nendstream");
|
||||
let data = [2u8, 0x03, 0x8E, 0, 2, 0x03, 0x8E, 1];
|
||||
let mut xref = format!("<< /Type /XRef /Size 2000 /W [1 2 1] /Index [902 2] /Length {} >>\nstream\n", data.len()).into_bytes();
|
||||
xref.extend_from_slice(&data);
|
||||
xref.extend_from_slice(b"\nendstream");
|
||||
let string = |key: &[u8]| format!("<{}>", hex(&file.dict.get(key).unwrap().as_string().unwrap().bytes));
|
||||
let objects = [
|
||||
(file.root.num, format!("<< /Type /Catalog /Pages {} 0 R /A 900 0 R /B 903 0 R >>", file.pages.num).into_bytes()),
|
||||
(file.encrypt.num, encrypt_with(&file, &string(b"O"), "Identity")),
|
||||
(900, b"<< /Filter [/Crypt /ASCIIHexDecode] /DecodeParms 902 0 R /Length 1 >>\nstream\n>\nendstream".to_vec()),
|
||||
(910, object_stream),
|
||||
(911, format!("<< /Predictor 11 /Columns {} >>", members.len()).into_bytes()),
|
||||
(912, xref),
|
||||
];
|
||||
let trailer = format!("/Root {} 0 R /Encrypt {} 0 R /ID [<{id}> <{id}>] /XRefStm @912", file.root.num, file.encrypt.num, id = hex(&file.id));
|
||||
let bytes = updated(&file.bytes, &objects, &trailer);
|
||||
let keep =
|
||||
|doc: &Document, r: &Object| doc.resolve(r).as_dict().and_then(|d| d.get(b"Keep")).and_then(Object::as_string).map(|s| s.bytes.clone());
|
||||
let member = Object::Ref(ObjRef::new(903, 0));
|
||||
let doc = Document::open(Arc::new(bytes.clone())).unwrap();
|
||||
assert_eq!(keep(&doc, &member).as_deref(), Some(b"yes".as_slice()), "read first");
|
||||
let doc = Document::open(Arc::new(bytes.clone())).unwrap();
|
||||
let _ = doc.get(ObjRef::new(900, 0));
|
||||
assert_eq!(keep(&doc, &member).as_deref(), Some(b"yes".as_slice()), "read after the stream selecting from it");
|
||||
let saved = write_full(&Document::open(Arc::new(bytes)).unwrap(), &SaveOptions::default()).unwrap();
|
||||
let back = Document::open(Arc::new(saved)).unwrap();
|
||||
let catalog = back.get(back.root().unwrap());
|
||||
assert_eq!(keep(&back, catalog.as_dict().unwrap().get(b"B").unwrap()).as_deref(), Some(b"yes".as_slice()), "after a full save");
|
||||
}
|
||||
|
||||
/// `walk` goes as deep as an object nests, so following a reference from down there adds that depth
|
||||
/// again for each object it loads: this file, under 10 KB, overflowed a 2 MiB stack and took the
|
||||
/// process with it. Only the object itself follows references, and it does so in very little stack.
|
||||
#[test]
|
||||
fn nested_dictionaries_load_nothing_on_a_small_stack() {
|
||||
let file = classic_file();
|
||||
let first = 960u32;
|
||||
let objects: Vec<(u32, Vec<u8>)> = (first..first + 40)
|
||||
.map(|num| {
|
||||
let open = "[".repeat(120);
|
||||
let close = "]".repeat(120);
|
||||
(num, format!("{open}<< /Contents () /Type {} 0 R >>{close}", num + 1).into_bytes())
|
||||
})
|
||||
.collect();
|
||||
let trailer = format!("/Root {} 0 R /Encrypt {} 0 R /ID [<{id}> <{id}>]", file.root.num, file.encrypt.num, id = hex(&file.id));
|
||||
let bytes = updated(&file.bytes, &objects, &trailer);
|
||||
let reading = std::thread::Builder::new().stack_size(1 << 20).spawn(move || {
|
||||
let doc = Document::open(Arc::new(bytes)).unwrap();
|
||||
doc.get(ObjRef::new(first, 0)).as_array().is_some()
|
||||
});
|
||||
assert_eq!(reading.unwrap().join().ok(), Some(true));
|
||||
}
|
||||
|
||||
/// The object itself can follow references, a ladder of them as long as loading may nest, and that
|
||||
/// fits a small stack too.
|
||||
#[test]
|
||||
fn a_ladder_of_signature_checks_fits_a_small_stack() {
|
||||
let file = classic_file();
|
||||
let first = 960u32;
|
||||
let objects: Vec<(u32, Vec<u8>)> =
|
||||
(first..first + 40).map(|num| (num, format!("<< /Contents () /Type {} 0 R >>", num + 1).into_bytes())).collect();
|
||||
let trailer = format!("/Root {} 0 R /Encrypt {} 0 R /ID [<{id}> <{id}>]", file.root.num, file.encrypt.num, id = hex(&file.id));
|
||||
let bytes = updated(&file.bytes, &objects, &trailer);
|
||||
let reading = std::thread::Builder::new().stack_size(1 << 20).spawn(move || {
|
||||
let doc = Document::open(Arc::new(bytes)).unwrap();
|
||||
doc.get(ObjRef::new(first, 0)).as_dict().is_some()
|
||||
});
|
||||
assert_eq!(reading.unwrap().join().ok(), Some(true));
|
||||
}
|
||||
|
||||
/// The strings of `/Encrypt` are never encrypted (ISO 32000-2 §7.6.2), and can be objects of their
|
||||
/// own. Read as ordinary strings they were decrypted, and a full save encrypted them again under
|
||||
/// another number, so the file it wrote no longer opened with its own password.
|
||||
#[test]
|
||||
fn encrypt_strings_given_by_reference_stay_as_stored() {
|
||||
let file = classic_file();
|
||||
let string = |key: &[u8]| hex(&file.dict.get(key).unwrap().as_string().unwrap().bytes);
|
||||
let replaced = format!(
|
||||
"<< /Filter /Standard /V 4 /R 4 /Length 128 /P {} /O 900 0 R /U 901 0 R /CF << /StdCF << /CFM /AESV2 /Length 16 /AuthEvent /DocOpen >> >> /StmF /StdCF /StrF /StdCF >>",
|
||||
file.dict.int(b"P").unwrap()
|
||||
);
|
||||
let objects = [
|
||||
(file.encrypt.num, replaced.into_bytes()),
|
||||
(900, format!("<{}>", string(b"O")).into_bytes()),
|
||||
(901, format!("<{}>", string(b"U")).into_bytes()),
|
||||
];
|
||||
let trailer =
|
||||
format!("/Root {} 0 R /Info {} 0 R /Encrypt {} 0 R /ID [<{id}> <{id}>]", file.root.num, file.info.num, file.encrypt.num, id = hex(&file.id));
|
||||
let source = Document::open(Arc::new(updated(&file.bytes, &objects, &trailer))).unwrap();
|
||||
assert_eq!(content(&source), SECRET, "the file reads");
|
||||
assert_eq!(title(&source).as_deref(), Some("Quarterly numbers"));
|
||||
for object_streams in [false, true] {
|
||||
let saved = write_full(&source, &SaveOptions { object_streams, ..SaveOptions::default() }).unwrap();
|
||||
let back = Document::open(Arc::new(saved)).unwrap();
|
||||
assert_eq!(content(&back), SECRET, "object streams: {object_streams}");
|
||||
assert_eq!(title(&back).as_deref(), Some("Quarterly numbers"), "object streams: {object_streams}");
|
||||
}
|
||||
}
|
||||
|
||||
/// A save keeps what a file is protected with: its `/Encrypt`, which holds the handler and the
|
||||
/// permissions, its `/ID`, and so its file key, under every algorithm and by either kind of save.
|
||||
#[test]
|
||||
fn a_save_keeps_the_handler_the_key_and_the_permissions() {
|
||||
for alg in ALL {
|
||||
let doc = Document::open_with_password(Arc::new(protect(alg, "user", "owner", -1 ^ 0b1_0000)), Some("user")).unwrap();
|
||||
let held = |d: &Document| {
|
||||
let encrypt = d.resolve(d.trailer().get(b"Encrypt").unwrap()).as_dict().unwrap().clone();
|
||||
(encrypt, d.trailer().get(b"ID").cloned(), d.security().unwrap().file_key().to_vec(), format!("{:?}", d.permissions()))
|
||||
};
|
||||
let before = held(&doc);
|
||||
let mut edited = doc.clone();
|
||||
let _ = edited.add(Object::Int(1));
|
||||
for (save, saved) in [
|
||||
("incremental", write_incremental(&edited, &SaveOptions::default()).unwrap()),
|
||||
("full", write_full(&doc, &SaveOptions::default()).unwrap()),
|
||||
] {
|
||||
let back = Document::open_with_password(Arc::new(saved), Some("user")).unwrap();
|
||||
assert!(held(&back) == before, "{alg:?}: a {save} save");
|
||||
assert_eq!(content(&back), SECRET, "{alg:?}: a {save} save");
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/// `/ID` has to be direct in an encrypted file, but one that isn't has its key made from the same
|
||||
/// bytes. A full save writes it direct, and an incremental one leaves it as it was.
|
||||
#[test]
|
||||
fn a_file_identifier_given_by_reference_is_read() {
|
||||
let file = classic_file();
|
||||
let id = hex(&file.id);
|
||||
let reference = |entries: &str, objects: &[(u32, Vec<u8>)]| {
|
||||
let trailer = format!("/Root {} 0 R /Encrypt {} 0 R /ID {entries}", file.root.num, file.encrypt.num);
|
||||
updated(&file.bytes, objects, &trailer)
|
||||
};
|
||||
let whole = reference("900 0 R", &[(900, format!("[<{id}> <{id}>]").into_bytes())]);
|
||||
let entries = reference("[900 0 R 901 0 R]", &[(900, format!("<{id}>").into_bytes()), (901, format!("<{id}>").into_bytes())]);
|
||||
for file in [whole, entries] {
|
||||
let source = Document::open(Arc::new(file)).unwrap();
|
||||
assert_eq!(content(&source), SECRET);
|
||||
let back = Document::open(Arc::new(write_full(&source, &SaveOptions::default()).unwrap())).unwrap();
|
||||
assert_eq!(content(&back), SECRET);
|
||||
assert!(matches!(back.trailer().get(b"ID"), Some(Object::Array(_))), "written direct");
|
||||
let mut edited = source.clone();
|
||||
let _ = edited.add(Object::Int(1));
|
||||
let back = Document::open(Arc::new(write_incremental(&edited, &SaveOptions::default()).unwrap())).unwrap();
|
||||
assert_eq!(content(&back), SECRET, "an incremental save");
|
||||
assert_eq!(back.trailer().get(b"ID"), edited.trailer().get(b"ID"), "and leaves it as it was");
|
||||
}
|
||||
}
|
||||
|
||||
/// A direct `/Encrypt` can refer to objects. A full save dropped those it found only there, and kept
|
||||
/// its references as they were under the old numbers, so nothing in the file read afterwards.
|
||||
#[test]
|
||||
fn a_direct_encrypt_dictionary_keeps_what_it_refers_to() {
|
||||
for object_streams in [false, true] {
|
||||
let mut doc = Document::open(Arc::new(fixture())).unwrap();
|
||||
doc.set_encryption(&NewEncryption {
|
||||
algorithm: Algorithm::Aes128,
|
||||
user_password: "",
|
||||
owner_password: "owner",
|
||||
permissions: -1,
|
||||
encrypt_metadata: true,
|
||||
seed: [9; 32],
|
||||
})
|
||||
.unwrap();
|
||||
let mut dict = doc.get(doc.trailer().reference(b"Encrypt").unwrap()).as_dict().cloned().unwrap();
|
||||
let filter = doc.add(Object::name("StdCF"));
|
||||
let filters = doc.add(dict.get(b"CF").unwrap().clone());
|
||||
dict.set(b"StmF".to_vec(), Object::Ref(filter));
|
||||
dict.set(b"CF".to_vec(), Object::Ref(filters));
|
||||
doc.trailer_mut().set(b"Encrypt".to_vec(), Object::Dict(dict));
|
||||
let options = SaveOptions { object_streams, ..SaveOptions::default() };
|
||||
let saved = write_full(&doc, &options).unwrap();
|
||||
let back = Document::open(Arc::new(saved)).unwrap();
|
||||
assert_eq!(content(&back), SECRET, "object streams: {object_streams}");
|
||||
let again = write_full(&back, &options).unwrap();
|
||||
assert_eq!(content(&Document::open(Arc::new(again)).unwrap()), SECRET, "object streams: {object_streams}, saved again");
|
||||
}
|
||||
}
|
||||
|
||||
/// How a stream is treated can be given by reference, and what that loads can be a stream too. A
|
||||
/// file can make a ladder of those, where each rung reads the rung below, then two trees wider than
|
||||
/// the object cache, which push that rung out of it, then the rung below again. Each rung would
|
||||
/// take twice what the one below does, if one read could follow any number of references.
|
||||
#[test]
|
||||
fn selectors_that_lead_to_selectors_load_at_once() {
|
||||
let mut doc = Document::open(Arc::new(protect(Algorithm::Aes128, "", "owner", -1))).unwrap();
|
||||
let stream_of = |doc: &mut Document, filters: Vec<Object>| {
|
||||
let mut dict = pdfcraft_cos::Dict::new();
|
||||
dict.set(b"Filter".to_vec(), Object::Array(filters));
|
||||
doc.add(Object::Stream(pdfcraft_cos::Stream::from_raw(dict, Vec::new())))
|
||||
};
|
||||
let tree = |doc: &mut Document| {
|
||||
let mut level: Vec<ObjRef> = (0..6_561).map(|i| doc.add(Object::Int(i))).collect();
|
||||
while level.len() > 1 {
|
||||
let chunks: Vec<Vec<Object>> = level.chunks(9).map(|c| c.iter().map(|r| Object::Ref(*r)).collect()).collect();
|
||||
level = chunks.into_iter().map(|c| stream_of(doc, c)).collect();
|
||||
}
|
||||
Object::Ref(level[0])
|
||||
};
|
||||
let (first, second) = (tree(&mut doc), tree(&mut doc));
|
||||
let mut top = doc.add(Object::Int(0));
|
||||
// Twelve rungs of two, and the trees' five levels, stay inside the 32 that loading may nest.
|
||||
for _ in 0..12 {
|
||||
let (a, b) = (stream_of(&mut doc, vec![Object::Ref(top)]), stream_of(&mut doc, vec![Object::Ref(top)]));
|
||||
top = stream_of(&mut doc, vec![Object::Ref(a), first.clone(), second.clone(), Object::Ref(b)]);
|
||||
}
|
||||
let saved = write_incremental(&doc, &SaveOptions::default()).unwrap();
|
||||
let (done, finished) = std::sync::mpsc::channel();
|
||||
std::thread::spawn(move || {
|
||||
let doc = Document::open(Arc::new(saved)).unwrap();
|
||||
let _ = done.send(doc.get(top).as_dict().is_some());
|
||||
});
|
||||
// With the budget it takes milliseconds, and without it longer than anyone would wait, so a
|
||||
// margin this wide can't fail on a busy machine.
|
||||
assert_eq!(finished.recv_timeout(std::time::Duration::from_secs(120)), Ok(true), "loading must not fan out");
|
||||
}
|
||||
|
||||
+50
-25
@@ -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());
|
||||
|
||||
@@ -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;
|
||||
@@ -1687,6 +1691,12 @@ pub(crate) fn selectable_images(
|
||||
.collect())
|
||||
}
|
||||
|
||||
/// Whether an XObject drawn at or after operator `from` of the page's joined operators shows
|
||||
/// inside `rect` (user space).
|
||||
pub(crate) fn painted_over(doc: &Document, page: usize, rect: [f64; 4], from: usize) -> Result<bool, EditError> {
|
||||
Ok(page_images(doc, page)?.iter().any(|i| i.op >= from && i.visible_rect.and_then(|v| intersection(v, rect)).is_some()))
|
||||
}
|
||||
|
||||
fn transform_image(
|
||||
doc: &mut Document,
|
||||
page: &pdfcraft_model::Page,
|
||||
|
||||
@@ -77,7 +77,7 @@ use marks::{matrix_number, n};
|
||||
pub(crate) use place::undrawable;
|
||||
#[cfg(test)]
|
||||
use place::{ISOLATION_MAX_DEPTH, OLD_WRAP_CLOSE, WRAP_CLOSE, WRAP_OPEN, is_wrap_close, page_fonts, stream_bytes, stream_tag, tagged, wrapper_role};
|
||||
use place::{check, check_on_top, contents, page_list, place_tagged};
|
||||
use place::{Reach, check, check_on_top, contents, draw_on_top, lift_on_top, page_list, place_tagged, revealed_under_paint};
|
||||
pub use place::{stamp, undrawable_message};
|
||||
|
||||
#[cfg(test)]
|
||||
|
||||
@@ -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");
|
||||
}
|
||||
}
|
||||
|
||||
@@ -371,6 +371,76 @@ pub(crate) fn place_tagged(doc: &mut Document, page: &pdfcraft_model::Page, tag:
|
||||
Ok(mark_ref)
|
||||
}
|
||||
|
||||
/// Draw `ops`, written for the space whose CTM is `ctm`, on top of everything on `page`, tagged
|
||||
/// `Edited`. A rewritten invisible paragraph goes here when [`revealed_under_paint`]: an OCR
|
||||
/// layer written before the scan image it lies under would keep the revealed text hidden (#3973).
|
||||
pub(crate) fn draw_on_top(doc: &mut Document, page: &pdfcraft_model::Page, ctm: [f64; 6], ops: &[pdfcraft_content::Op]) -> Result<(), EditError> {
|
||||
if ops.is_empty() {
|
||||
return Ok(());
|
||||
}
|
||||
use pdfcraft_content::Op;
|
||||
let mut all = vec![Op::new("q", vec![]), Op::new("cm", ctm.iter().map(|v| pdfcraft_content::num(*v)).collect())];
|
||||
all.extend_from_slice(ops);
|
||||
all.push(Op::new("Q", vec![]));
|
||||
place_tagged(doc, page, "Edited", pdfcraft_content::serialize_ops(&all), false).map(drop)
|
||||
}
|
||||
|
||||
/// Where a rewritten paragraph can be drawn, in user space ([`revealed_under_paint`]).
|
||||
pub(crate) struct Reach {
|
||||
/// The paragraph's old box, where its cover goes.
|
||||
pub rect: [f64; 4],
|
||||
/// The move asked for (`BlockStyle::offset`).
|
||||
pub offset: [f64; 2],
|
||||
/// The widest line the rewrite may draw, how many lines it has, and how far apart they are.
|
||||
pub width: f64,
|
||||
pub rows: usize,
|
||||
pub pitch: f64,
|
||||
pub upright: bool,
|
||||
}
|
||||
|
||||
impl Reach {
|
||||
/// The old box and the moved one, grown to `width` either way (alignment may grow a line left
|
||||
/// or right), down to `rows` lines and up one `pitch` above its top (a larger size on the first line, however many lines the old box had); turned text grows by the lines' diagonal every way.
|
||||
/// Unbounded when a number is not finite.
|
||||
pub(crate) fn bounds(&self) -> [f64; 4] {
|
||||
const UNBOUNDED: [f64; 4] = [f64::NEG_INFINITY, f64::NEG_INFINITY, f64::INFINITY, f64::INFINITY];
|
||||
let ([dx, dy], r) = (self.offset, self.rect);
|
||||
if !r.iter().chain(&self.offset).chain([&self.width, &self.pitch]).all(|v| v.is_finite()) {
|
||||
return UNBOUNDED;
|
||||
}
|
||||
let moved = [r[0] + dx, r[1] + dy, r[2] + dx, r[3] + dy];
|
||||
let rows = f64::from(u32::try_from(self.rows).unwrap_or(u32::MAX));
|
||||
let (width, height) = (self.width.abs(), self.pitch.abs() * rows);
|
||||
let grown = if self.upright {
|
||||
[moved[0].min(moved[2] - width), moved[1].min(moved[3] - height), moved[2].max(moved[0] + width), moved[3] + self.pitch.abs()]
|
||||
} else {
|
||||
let d = width.hypot(height);
|
||||
[moved[0] - d, moved[1] - d, moved[2] + d, moved[3] + d]
|
||||
};
|
||||
let b = [r[0].min(grown[0]), r[1].min(grown[1]), r[2].max(grown[2]), r[3].max(grown[3])];
|
||||
if b.iter().all(|v| v.is_finite()) { b } else { UNBOUNDED }
|
||||
}
|
||||
}
|
||||
|
||||
/// Whether a rewritten paragraph that was `invisible` goes on top of page `page`: something after
|
||||
/// operator `at` of the page's joined `ops` paints over `reach` (user space, [`Reach::bounds`]), as the scan image
|
||||
/// does over an OCR layer written before it (#3973). XObjects count where they are drawn; an inline
|
||||
/// image or a shading after it counts anywhere, and so does any XObject when the page's images
|
||||
/// cannot be listed.
|
||||
pub(crate) fn revealed_under_paint(doc: &Document, page: usize, invisible: bool, reach: [f64; 4], ops: &[pdfcraft_content::Op], at: usize) -> bool {
|
||||
let later = ops.get(at..).unwrap_or_default();
|
||||
if !invisible || later.iter().any(|op| op.is("BI") || op.is("sh")) {
|
||||
return invisible;
|
||||
}
|
||||
later.iter().any(|op| op.is("Do")) && crate::images::painted_over(doc, page, reach, at).unwrap_or(true)
|
||||
}
|
||||
|
||||
/// The operators to draw on top of the page ([`draw_on_top`]): all of `paragraph` when `over`,
|
||||
/// none otherwise. The page was checked to take them ([`check_on_top`]) before the edit began.
|
||||
pub(crate) fn lift_on_top(over: bool, paragraph: &mut Vec<pdfcraft_content::Op>) -> Vec<pdfcraft_content::Op> {
|
||||
if over { std::mem::take(paragraph) } else { Vec::new() }
|
||||
}
|
||||
|
||||
fn too_deep_on_top() -> EditError {
|
||||
EditError::Invalid("the page's marked content is nested too deeply to add anything on top of it".into())
|
||||
}
|
||||
|
||||
@@ -6213,6 +6213,126 @@ fn group_selection_refuses_incomplete_content_and_resource_budget_overruns() {
|
||||
assert!(editable_objects(&doc, 0).is_err(), "an undecodable stream is refused");
|
||||
}
|
||||
|
||||
/// Invisible text moves on top only when something painted after it covers it: an XObject drawn
|
||||
/// over its box (an image, or a form holding one), or any inline image or shading. An image
|
||||
/// clipped away entirely, or drawn elsewhere, does not move it.
|
||||
#[test]
|
||||
fn revealed_text_moves_on_top_only_when_painted_over() {
|
||||
let on_top_of = |doc: Document| {
|
||||
let block = text::text_blocks(&doc, 0).unwrap().remove(0);
|
||||
let ops = pdfcraft_content::parse(&page_content_bytes(&doc, 0)).ops;
|
||||
let at = ops.iter().position(|o| o.is("BT")).unwrap();
|
||||
revealed_under_paint(&doc, 0, block.invisible, block.rect, &ops, at)
|
||||
};
|
||||
let on_top = |content: &str| on_top_of(image_page_with(content));
|
||||
let scan = "q 200 0 0 100 100 100 cm /Im0 Do Q";
|
||||
assert!(on_top(&format!("BT /F1 12 Tf 3 Tr 110 150 Td (Under) Tj ET {scan}")), "the scan covers it");
|
||||
assert!(!on_top(&format!("BT /F1 12 Tf 3 Tr 400 600 Td (Away) Tj ET {scan}")), "an image elsewhere");
|
||||
assert!(!on_top(&format!("{scan} BT /F1 12 Tf 3 Tr 110 150 Td (Over) Tj ET")), "the scan is drawn first");
|
||||
assert!(!on_top(&format!("BT /F1 12 Tf 0 Tr 110 150 Td (Shown) Tj ET {scan}")), "visible text stays where it is");
|
||||
assert!(!on_top("BT /F1 12 Tf 3 Tr 110 150 Td (Path) Tj ET 0 0 600 800 re f"), "a filled path does not move it");
|
||||
assert!(on_top("BT /F1 12 Tf 3 Tr 400 600 Td (Shade) Tj ET /Sh sh"), "a shading after it");
|
||||
assert!(on_top("BT /F1 12 Tf 3 Tr 400 600 Td (Inline) Tj ET BI /W 1 /H 1 /CS /G /BPC 8 ID x EI"), "an inline image after it");
|
||||
let under = "BT /F1 12 Tf 3 Tr 110 150 Td (Under) Tj ET";
|
||||
let elsewhere = "q 50 0 0 50 400 600 cm /Im0 Do Q";
|
||||
assert!(!on_top(&format!("{under} q 0 0 10 10 re W n {scan} Q")), "the scan is clipped away entirely");
|
||||
assert!(on_top(&format!("{under} {elsewhere} {scan}")), "two images, the second over it");
|
||||
assert!(on_top(&format!("{under} {scan} {elsewhere}")), "two images, the first over it");
|
||||
assert!(!on_top(&format!("{under} {elsewhere} {elsewhere}")), "two images, neither over it");
|
||||
let in_form = |content: &str| {
|
||||
let page = "<< /Type /Page /Parent 2 0 R /MediaBox [0 0 600 800] /Contents 4 0 R /Resources << /Font << /F1 5 0 R >> /XObject << /Fm0 7 0 R >> >> >>";
|
||||
let image = stream("/Type /XObject /Subtype /Image /Width 1 /Height 1 /ColorSpace /DeviceGray /BitsPerComponent 8", "A");
|
||||
let form = stream("/Type /XObject /Subtype /Form /BBox [0 0 1 1] /Resources << /XObject << /Im0 6 0 R >> >>", "/Im0 Do");
|
||||
let objs = [
|
||||
"<< /Type /Catalog /Pages 2 0 R >>".to_string(),
|
||||
"<< /Type /Pages /Kids [3 0 R] /Count 1 >>".into(),
|
||||
page.into(),
|
||||
stream("", content),
|
||||
"<< /Type /Font /Subtype /Type1 /BaseFont /Helvetica >>".into(),
|
||||
image,
|
||||
form,
|
||||
];
|
||||
on_top_of(build(&objs.iter().map(String::as_str).collect::<Vec<_>>()))
|
||||
};
|
||||
assert!(in_form(&format!("{under} q 200 0 0 100 100 100 cm /Fm0 Do Q")), "a form holding the scan, over it");
|
||||
assert!(!in_form(&format!("{under} q 50 0 0 50 400 600 cm /Fm0 Do Q")), "a form holding an image elsewhere");
|
||||
}
|
||||
|
||||
/// Revealed OCR text is checked where the rewrite lands, not only where it was: an image drawn
|
||||
/// after it over just the moved or grown text still lifts the text on top, on both rewrite paths.
|
||||
#[test]
|
||||
fn an_ocr_rewrite_goes_on_top_of_paint_over_where_it_lands() {
|
||||
let scan = "q 200 0 0 100 100 100 cm /Im0 Do Q";
|
||||
let moved = text::BlockStyle { offset: Some([-290.0, -450.0]), ..Default::default() };
|
||||
let sized = text::BlockStyle { size: Some(24.0), ..Default::default() };
|
||||
let spaced = text::BlockStyle { line_spacing: Some(3.0), ..Default::default() };
|
||||
let range = text::RangeStyle {
|
||||
range: 0..2,
|
||||
family: None,
|
||||
resource: None,
|
||||
size: Some(120.0),
|
||||
color: None,
|
||||
underline: None,
|
||||
char_spacing: None,
|
||||
scale: None,
|
||||
};
|
||||
let enlarged = text::BlockStyle { ranges: vec![range], ..Default::default() };
|
||||
let above = "q 200 0 0 60 100 200 cm /Im0 Do Q";
|
||||
let cases = [
|
||||
("BT /F1 12 Tf 3 Tr 400 600 Td (Away) Tj ET", "Moved", &moved),
|
||||
("BT /F1 12 Tf 3 Tr 400 600 Td (Away) Tj ET", "Moved\nTwice", &moved),
|
||||
("BT /F1 12 Tf 3 Tr 40 150 Td (Hi) Tj ET", "Hello there, this line now runs well past the scan's left edge", &text::BlockStyle::default()),
|
||||
("BT /F1 12 Tf 3 Tr 40 150 Td (Hi) Tj ET", "Hello there,\nthis line now runs well past the scan's left edge", &text::BlockStyle::default()),
|
||||
("BT /F1 12 Tf 3 Tr 110 230 Td (Above) Tj ET", "One\nTwo\nThree\nFour\nFive\nSix", &text::BlockStyle::default()),
|
||||
];
|
||||
let low = "q 200 0 0 30 100 300 cm /Im0 Do Q";
|
||||
let cases = cases.into_iter().map(|(c, e, s)| (c, e, s, scan)).chain([
|
||||
("BT /F1 12 Tf 3 Tr 110 500 Td (Above) Tj ET", "One\nTwo\nThree\nFour\nFive\nSix", &sized, low),
|
||||
("BT /F1 12 Tf 3 Tr 110 500 Td (Above) Tj ET", "One\nTwo\nThree\nFour\nFive\nSix", &spaced, low),
|
||||
("BT /F1 12 Tf 3 Tr 110 150 Td (Hi there) Tj ET", "Hi there", &enlarged, above),
|
||||
]);
|
||||
for (content, edit, style, scan) in cases {
|
||||
let mut doc = image_page_with(&format!("{content} {scan}"));
|
||||
let before = text::text_blocks(&doc, 0).unwrap().remove(0);
|
||||
let ops = pdfcraft_content::parse(&page_content_bytes(&doc, 0)).ops;
|
||||
let at = ops.iter().position(|o| o.is("BT")).unwrap();
|
||||
assert!(!revealed_under_paint(&doc, 0, true, before.rect, &ops, at), "{edit:?}: the old box alone is clear of the scan");
|
||||
text::rewrite_block(&mut doc, 0, 0, Some(edit), style).unwrap();
|
||||
let ops = pdfcraft_content::parse(&page_content_bytes(&doc, 0)).ops;
|
||||
let scan_at = ops.iter().position(|o| o.is("Do")).unwrap();
|
||||
let shows = ["Tj", "TJ", "'", "\""];
|
||||
assert!(ops.iter().skip(scan_at).any(|o| shows.iter().any(|s| o.is(s))), "{edit:?}: the rewrite is drawn over the scan");
|
||||
}
|
||||
}
|
||||
|
||||
/// [`crate::Reach`] grows the old box to the move, the width either way and the lines below.
|
||||
#[test]
|
||||
fn a_rewrites_reach_covers_its_move_width_and_lines() {
|
||||
let reach = |offset, width, rows, upright| crate::Reach { rect: [10.0, 90.0, 30.0, 100.0], offset, width, rows, pitch: 10.0, upright }.bounds();
|
||||
assert_eq!(reach([0.0, 0.0], 20.0, 1, true), [10.0, 90.0, 30.0, 110.0]);
|
||||
assert_eq!(reach([5.0, -50.0], 20.0, 1, true), [10.0, 40.0, 35.0, 100.0]);
|
||||
assert_eq!(reach([0.0, 0.0], 50.0, 3, true), [-20.0, 70.0, 60.0, 110.0]);
|
||||
assert_eq!(reach([0.0, 0.0], 30.0, 4, false), [-40.0, 40.0, 80.0, 150.0]);
|
||||
assert_eq!(reach([f64::NAN, 0.0], 20.0, 1, true)[0], f64::NEG_INFINITY);
|
||||
let larger = crate::Reach { rect: [10.0, 90.0, 30.0, 100.0], offset: [0.0, 0.0], width: 20.0, rows: 1, pitch: 24.0, upright: true };
|
||||
assert_eq!(larger.bounds(), [10.0, 76.0, 30.0, 124.0], "a larger size grows the line up as well as down");
|
||||
}
|
||||
|
||||
/// Revealed OCR text may have to go on top of the page; a page whose marked content nests too deep
|
||||
/// for that is refused before either rewrite path changes anything.
|
||||
#[test]
|
||||
fn an_ocr_rewrite_refused_on_top_leaves_the_document_as_it_was() {
|
||||
let content = format!("{} BT /F1 20 Tf 3 Tr 42 44 Td (John) Tj ET /Im Do {}", "/X BMC ".repeat(10_001), "EMC ".repeat(10_001));
|
||||
let mut doc = text_page(&content);
|
||||
assert!(text::text_blocks(&doc, 0).unwrap()[0].invisible);
|
||||
let before = write_full(&doc, &SaveOptions::default()).unwrap();
|
||||
for edit in ["Jane", "Jane\nDoe"] {
|
||||
let error = text::rewrite_block(&mut doc, 0, 0, Some(edit), &text::BlockStyle::default()).unwrap_err();
|
||||
assert!(error.to_string().contains("nested too deeply"), "{edit:?}: {error}");
|
||||
assert!(write_full(&doc, &SaveOptions::default()).unwrap() == before, "{edit:?}: a refused rewrite changes nothing");
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn group_move_budget_refusals_keep_the_original_page_selectable() {
|
||||
let text = text_page(&format!("{} BT /F1 12 Tf 40 400 Td (Target) Tj ET", "n ".repeat(99_995)));
|
||||
@@ -9813,6 +9933,133 @@ 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();
|
||||
|
||||
@@ -31,7 +31,8 @@ pub struct TextBlock {
|
||||
/// Byte ranges in `editor_text` and their source line indexes.
|
||||
pub spans: Vec<(std::ops::Range<usize>, usize)>,
|
||||
/// Every line is invisible text (rendering mode 3): an OCR layer over a scanned image, whose
|
||||
/// pixels show the words. A rewrite draws the new text visibly (see [`BlockStyle::cover`]).
|
||||
/// pixels show the words. A rewrite draws the new text visibly, on top of the page when
|
||||
/// the scan is drawn after it (see [`BlockStyle::cover`]).
|
||||
pub invisible: bool,
|
||||
}
|
||||
|
||||
|
||||
@@ -18,13 +18,33 @@ pub(super) struct TextState {
|
||||
/// graphics state the text was painted with that [`TextState::ops`] doesn't restate.
|
||||
pub(super) stroke: Vec<Op>,
|
||||
pub(super) line_width: Option<f64>,
|
||||
ext_gstate: Vec<Vec<u8>>,
|
||||
ext_gstate: Vec<GsSelection>,
|
||||
/// The dash pattern and line cap in force (see [`Ts`]): compared, not restated.
|
||||
pub(super) dash: Dash,
|
||||
pub(super) line_cap: i64,
|
||||
}
|
||||
|
||||
impl TextState {
|
||||
/// The state a page's content starts in (ISO 32000-2 §8.4.1, §9.3.1): what is in force on
|
||||
/// top of the page, after its content wrapped in `q`/`Q`.
|
||||
pub(crate) fn initial() -> Self {
|
||||
TextState {
|
||||
font: None,
|
||||
char_spacing: 0.0,
|
||||
word_spacing: 0.0,
|
||||
scale: 1.0,
|
||||
leading: 0.0,
|
||||
rise: 0.0,
|
||||
fill: Vec::new(),
|
||||
render_mode: 0,
|
||||
stroke: Vec::new(),
|
||||
line_width: None,
|
||||
ext_gstate: Vec::new(),
|
||||
dash: (Vec::new(), 0.0),
|
||||
line_cap: 0,
|
||||
}
|
||||
}
|
||||
|
||||
pub(super) fn of(ts: &Ts) -> Self {
|
||||
TextState {
|
||||
font: ts.font.as_ref().map(|(n, _)| (String::from_utf8_lossy(n).into_owned(), ts.size)),
|
||||
@@ -54,13 +74,17 @@ impl TextState {
|
||||
///
|
||||
/// A `gs` has no inverse, so a selection `current` has and this state doesn't stays in force:
|
||||
/// run these inside a `q`/`Q` that starts from `current`, one per state drawn.
|
||||
pub(crate) fn paint_ops(&self, current: &TextState) -> Vec<Op> {
|
||||
///
|
||||
/// `ctm` is the CTM where they run. A soft mask is placed by the CTM its `gs` ran at
|
||||
/// (ISO 32000-2 §11.6.5.2), so one selected at another CTM is selected there and the CTM
|
||||
/// set back.
|
||||
pub(crate) fn paint_ops(&self, current: &TextState, ctm: [f64; 6]) -> Vec<Op> {
|
||||
let n = pdfcraft_content::num;
|
||||
let mut v = Vec::new();
|
||||
// The selections both share stay in force; the ones after them are selected again in order.
|
||||
let shared = self.ext_gstate.iter().zip(¤t.ext_gstate).take_while(|(a, b)| a == b).count();
|
||||
for name in self.ext_gstate.iter().skip(shared) {
|
||||
v.push(Op::new("gs", vec![Object::Name(name.clone())]));
|
||||
for sel in self.ext_gstate.iter().skip(shared) {
|
||||
sel.push_ops(&mut v, ctm);
|
||||
}
|
||||
// A reselected ExtGState may set `/LW`, so the width (already the effective one) follows it.
|
||||
let reselected = !v.is_empty();
|
||||
@@ -222,7 +246,7 @@ pub(super) struct Ts {
|
||||
/// The line width a `w` or an ExtGState's `/LW` set (`None`: the initial 1.0).
|
||||
pub(super) line_width: Option<f64>,
|
||||
/// The ExtGState resources selected with `gs`, oldest first (see [`select_gs`]).
|
||||
pub(super) ext_gstate: Vec<Vec<u8>>,
|
||||
pub(super) ext_gstate: Vec<GsSelection>,
|
||||
/// The dash pattern a `d` or an ExtGState's `/D` set (initially solid: `[] 0`).
|
||||
pub(super) dash: Dash,
|
||||
/// The line cap a `J` or an ExtGState's `/LC` set (initially 0, butt).
|
||||
@@ -255,12 +279,38 @@ const MAX_GS: usize = 32;
|
||||
/// Record `gs /name` in `list`. A `gs` sets every parameter its dictionary names to an absolute
|
||||
/// value, so a later selection of the same dictionary overrides the earlier one completely: the
|
||||
/// earlier entry goes, which keeps replaying the list equivalent to replaying the stream.
|
||||
fn select_gs(list: &mut Vec<Vec<u8>>, name: &[u8]) {
|
||||
list.retain(|n| n != name);
|
||||
fn select_gs(list: &mut Vec<GsSelection>, name: &[u8], anchor: Option<[f64; 6]>) {
|
||||
list.retain(|s| s.name != name);
|
||||
if list.len() >= MAX_GS {
|
||||
list.remove(0);
|
||||
}
|
||||
list.push(name.to_vec());
|
||||
list.push(GsSelection { name: name.to_vec(), anchor });
|
||||
}
|
||||
|
||||
/// One `gs` selection: the ExtGState's resource name, and the CTM it ran at when the dictionary
|
||||
/// has a soft mask, which that CTM places (ISO 32000-2 §11.6.5.2).
|
||||
#[derive(Clone, Debug, PartialEq)]
|
||||
pub(crate) struct GsSelection {
|
||||
name: Vec<u8>,
|
||||
anchor: Option<[f64; 6]>,
|
||||
}
|
||||
|
||||
impl GsSelection {
|
||||
/// Select this ExtGState from where the CTM is `ctm`: at its anchor, then back to `ctm`. Both
|
||||
/// moves need an invertible matrix; without one it is selected where it runs.
|
||||
fn push_ops(&self, v: &mut Vec<Op>, ctm: [f64; 6]) {
|
||||
let gs = Op::new("gs", vec![Object::Name(self.name.clone())]);
|
||||
let moves = self.anchor.filter(|a| *a != ctm).and_then(|a| {
|
||||
let (anchor, here) = (Matrix(a), Matrix(ctm));
|
||||
Some((anchor.then(&here.invert()?), here.then(&anchor.invert()?)))
|
||||
});
|
||||
let Some((to, back)) = moves else {
|
||||
v.push(gs);
|
||||
return;
|
||||
};
|
||||
let cm = |m: Matrix| Op::new("cm", m.0.iter().map(|x| pdfcraft_content::num(*x)).collect());
|
||||
v.extend([cm(to), gs, cm(back)]);
|
||||
}
|
||||
}
|
||||
|
||||
/// The text-showing operators of one stream with their text, font, box and baseline.
|
||||
@@ -879,14 +929,15 @@ pub(super) fn interpret(
|
||||
b"Ts" => ts.rise = op.num(0).unwrap_or(0.0),
|
||||
b"Tr" => ts.render_mode = op.operands.first().and_then(Object::as_int).unwrap_or(-1),
|
||||
b"gs" => {
|
||||
if let Some(name) = op.name(0) {
|
||||
select_gs(&mut ts.ext_gstate, name);
|
||||
}
|
||||
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(name) = op.name(0) {
|
||||
let masked = params.and_then(|p| p.get(b"SMask")).is_some_and(|m| doc.resolve(m).as_dict().is_some());
|
||||
select_gs(&mut ts.ext_gstate, name, masked.then_some(ts.ctm.0));
|
||||
}
|
||||
if let Some(params) = params {
|
||||
ts.gs.apply(doc, params);
|
||||
// `/LW` sets the line width as `w` does (ISO 32000-2 §8.4.5).
|
||||
|
||||
@@ -702,11 +702,13 @@ fn block_ops(plan: &BlockPlan<'_>, writer: &LineWriter<'_>, wrapped: &[(String,
|
||||
let mut ops = vec![Op::new("q", vec![])];
|
||||
ops.extend(reveal_ops(plan.block, plan.lines, plan.style, plan.emit.ctm)?);
|
||||
// Moved: a translation inside that state.
|
||||
let mut ctm = Matrix(plan.emit.ctm);
|
||||
if let Some((ax, ay)) = plan.movement {
|
||||
ops.push(Op::new("cm", vec![n(1.0), n(0.0), n(0.0), n(1.0), n(ax), n(ay)]));
|
||||
ctm = Matrix([1.0, 0.0, 0.0, 1.0, ax, ay]).then(&ctm);
|
||||
}
|
||||
// Painted as the paragraph was, including what its text object set before the first show.
|
||||
ops.extend(plan.state.paint_ops(plan.after));
|
||||
ops.extend(plan.state.paint_ops(plan.after, ctm.0));
|
||||
ops.push(Op::new("BT", vec![]));
|
||||
let mut state = plan.state.clone();
|
||||
state.word_spacing = 0.0;
|
||||
@@ -816,6 +818,11 @@ pub(crate) fn rewrite_block_from(
|
||||
let first = members.first().copied().ok_or_else(|| EditError::Invalid("the paragraph has no source runs".into()))?;
|
||||
members.iter().try_for_each(|line| line.ensure_editable())?;
|
||||
let p = page_dict(doc, page)?;
|
||||
// Revealed OCR text may go on top of the page (see `revealed_under_paint`): a page that can't
|
||||
// take that is refused here, before either rewrite path changes anything.
|
||||
if b.invisible {
|
||||
crate::check_on_top(doc, &p)?;
|
||||
}
|
||||
let mut res = p.dict.get(b"Resources").map(|r| doc.resolve(r)).and_then(|r| r.as_dict().cloned()).unwrap_or_default();
|
||||
let mut fonts_res = res.get(b"Font").map(|f| doc.resolve(f)).and_then(|f| f.as_dict().cloned()).unwrap_or_default();
|
||||
let dispatch = choose_rewrite_path(doc, &fonts_res, &b, &members, first, text, style)?;
|
||||
@@ -930,9 +937,28 @@ pub(crate) fn rewrite_block_from(
|
||||
char_spacing: o_state.char_spacing,
|
||||
lead,
|
||||
};
|
||||
let plan =
|
||||
BlockPlan { block: &b, lines: &lines, style, emit, after, movement, state: o_state, tm, size, underline: style.underline == Some(true) };
|
||||
let at = if split { start } else { emit.bt_op };
|
||||
// Revealed OCR text that something is painted over goes on top of the page, where it starts
|
||||
// from the initial state.
|
||||
let widest = wrapped.iter().map(|(l, _, _)| advance.of(l)).fold(width, f64::max);
|
||||
let reach = crate::Reach { rect: b.rect, offset: [dx, dy], width: widest, rows: wrapped.len(), pitch: lead * k, upright };
|
||||
let over = crate::revealed_under_paint(doc, page, b.invisible, reach.bounds(), &ops, at);
|
||||
let initial = TextState::initial();
|
||||
let drawn_from = if over { &initial } else { after };
|
||||
let plan = BlockPlan {
|
||||
block: &b,
|
||||
lines: &lines,
|
||||
style,
|
||||
emit,
|
||||
after: drawn_from,
|
||||
movement,
|
||||
state: o_state,
|
||||
tm,
|
||||
size,
|
||||
underline: style.underline == Some(true),
|
||||
};
|
||||
let mut block_ops = block_ops(&plan, &writer, &wrapped, font.show_font.clone())?;
|
||||
let on_top = crate::lift_on_top(over, &mut block_ops);
|
||||
let n = pdfcraft_content::num;
|
||||
block_ops.extend(after.ops().into_iter().filter(|op| !op.is("Tf") || after.font.is_some()));
|
||||
if split {
|
||||
@@ -940,7 +966,6 @@ pub(crate) fn rewrite_block_from(
|
||||
block_ops.push(Op::new("BT", vec![]));
|
||||
block_ops.push(Op::new("Tm", emit.tlm.iter().map(|v| n(*v)).collect()));
|
||||
}
|
||||
let at = if split { start } else { emit.bt_op };
|
||||
let new_data = splice(&pieces, &ops, |i| {
|
||||
let insert = if i == at { std::mem::take(&mut block_ops) } else { Vec::new() };
|
||||
(insert, !dropped.contains(&i))
|
||||
@@ -957,12 +982,14 @@ pub(crate) fn rewrite_block_from(
|
||||
d.set(b"Resources".to_vec(), Object::Dict(res));
|
||||
}
|
||||
})?;
|
||||
crate::draw_on_top(doc, &p, emit.ctm, &on_top)?;
|
||||
Ok(LineEdit { substituted: font.substituted })
|
||||
}
|
||||
|
||||
/// The cover (when [`BlockStyle::cover`] asks for one) and visible rendering that start a
|
||||
/// rewritten invisible paragraph, drawn in the space whose CTM is `ctm`. Nothing for visible text.
|
||||
/// The paragraph's `q`/`Q` restores the rendering mode for the invisible text after it.
|
||||
/// The paragraph's `q`/`Q` restores the rendering mode for the invisible text after it; one
|
||||
/// painted over where it was is drawn on top of the page instead ([`crate::draw_on_top`]).
|
||||
pub(crate) fn reveal_ops(block: &TextBlock, lines: &[TextLine], style: &BlockStyle, ctm: [f64; 6]) -> Result<Vec<Op>, EditError> {
|
||||
if !block.invisible {
|
||||
return Ok(Vec::new());
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
use super::super::interp::TextState;
|
||||
use super::grouping::{across, is_centred, row_rect};
|
||||
use super::{
|
||||
BlockStyle, CraftFont, Dict, Document, EditError, HashMap, LineEdit, MAX_TYPE3_GLYPHS, Matrix, Metrics, Object, Op, PdfString, Pieces,
|
||||
@@ -401,6 +402,16 @@ fn paragraph_geometry(doc: &Document, page: &pdfcraft_model::Page, block: &TextB
|
||||
Ok((dx, dy, style.width.unwrap_or(natural).clamp(1.0, 14_400.0)))
|
||||
}
|
||||
|
||||
/// How far below a row of `size` the next one is written: the source's leading unless a size
|
||||
/// or line spacing is chosen.
|
||||
fn row_step(style: &BlockStyle, size: f64, source_leading: f64) -> f64 {
|
||||
if style.line_spacing.is_none() && style.size.is_none() {
|
||||
source_leading
|
||||
} else {
|
||||
style.line_spacing.unwrap_or(1.5).clamp(0.5, 5.0) * style.size.unwrap_or(size)
|
||||
}
|
||||
}
|
||||
|
||||
type WrappedStyledRows = (StyledRows, RowRanges, Vec<usize>, Vec<bool>, Vec<usize>);
|
||||
|
||||
fn wrap_styled_rows(
|
||||
@@ -976,6 +987,7 @@ pub(crate) fn rewrite_styled_block(
|
||||
let o = &lead.origin;
|
||||
// What is in force where the rewrite is drawn, and what the text after it expects.
|
||||
let after = if split { &o.state } else { &o.bt_state };
|
||||
let at = if split { start } else { o.bt_op };
|
||||
validate_contextual_rows(&rows, &kept)?;
|
||||
let measured: Vec<_> = rows.iter().map(|row| measure(row)).collect::<Result<_, _>>()?;
|
||||
let shaped = prepare_shaped_rows(doc, &fonts, &rows, &kept, advance)?;
|
||||
@@ -989,6 +1001,7 @@ pub(crate) fn rewrite_styled_block(
|
||||
.ok_or_else(|| EditError::Invalid("the paragraph is drawn in a space it cannot be edited in".into()))?;
|
||||
let (tx, ty) = back.apply(dx, dy);
|
||||
block_ops.push(Op::new("cm", vec![n(1.0), n(0.0), n(0.0), n(1.0), n(tx), n(ty)]));
|
||||
let run_ctm = Matrix([1.0, 0.0, 0.0, 1.0, tx, ty]).then(&Matrix(o.ctm)).0;
|
||||
// A new row can land one leading above the next paragraph and look like the same
|
||||
// paragraph. When every row is in this rewrite, a paragraph marker keeps them in one
|
||||
// scope so the neighbour stays out (#2517). A row left in the source stream cannot share
|
||||
@@ -1007,6 +1020,19 @@ pub(crate) fn rewrite_styled_block(
|
||||
})
|
||||
.rfind(|v| *v > 0.0)
|
||||
.unwrap_or(first.size * 1.5);
|
||||
// Revealed OCR text that something is painted over goes on top of the page, where it starts
|
||||
// from the initial state.
|
||||
let largest =
|
||||
block.lines.iter().filter_map(|i| lines.get(*i)).map(|l| l.size).chain(style.ranges.iter().filter_map(|r| r.size)).fold(first.size, f64::max);
|
||||
// At least one line of the largest glyphs, so a larger range reaches up as far as it draws.
|
||||
const LINE_EM: f64 = 1.2;
|
||||
let pitch = source_leading.max(row_step(style, largest, source_leading)).max(largest * LINE_EM);
|
||||
let widest = measured.iter().copied().fold(width, f64::max);
|
||||
// This path lays rows out along user-space baselines, so the paragraph is upright here.
|
||||
let reach = crate::Reach { rect: block.rect, offset: [dx, dy], width: widest, rows: rows.len(), pitch, upright: true };
|
||||
let over = crate::revealed_under_paint(doc, page, block.invisible, reach.bounds(), &ops, at);
|
||||
let initial = TextState::initial();
|
||||
let drawn_from = if over { &initial } else { after };
|
||||
let mut baseline = first.origin.baseline;
|
||||
for (row_index, row) in rows.iter().enumerate() {
|
||||
let anchor = block.rows.get(row_index).and_then(|r| r.first()).and_then(|i| lines.get(*i));
|
||||
@@ -1073,7 +1099,7 @@ pub(crate) fn rewrite_styled_block(
|
||||
// object (`gs`, stroke, line width, `Tr`; #3508/#3509) from the state the rewrite is
|
||||
// drawn in: a `gs` has no inverse, so one run's ExtGState would stay for the next.
|
||||
block_ops.push(Op::new("q", vec![]));
|
||||
block_ops.extend(state.paint_ops(after));
|
||||
block_ops.extend(state.paint_ops(drawn_from, run_ctm));
|
||||
if let Some((_, shaped, _)) = shaped_runs.get(&(row_index, pos)) {
|
||||
let resource = glyph_resources.get(&(row_index, pos)).ok_or_else(|| EditError::Invalid("shaped font is missing".into()))?;
|
||||
let mut properties = Dict::new();
|
||||
@@ -1164,21 +1190,17 @@ pub(crate) fn rewrite_styled_block(
|
||||
x += segment_width;
|
||||
pos = end;
|
||||
}
|
||||
baseline -= if style.line_spacing.is_none() && style.size.is_none() {
|
||||
source_leading
|
||||
} else {
|
||||
style.line_spacing.unwrap_or(1.5).clamp(0.5, 5.0) * style.size.unwrap_or(anchor.size)
|
||||
};
|
||||
baseline -= row_step(style, anchor.size, source_leading);
|
||||
}
|
||||
push_whole_paragraph_marker(&mut block_ops, marked, "EMC");
|
||||
block_ops.push(Op::new("Q", vec![]));
|
||||
let on_top = crate::lift_on_top(over, &mut block_ops);
|
||||
block_ops.extend(after.ops());
|
||||
if split {
|
||||
block_ops.insert(0, Op::new("ET", vec![]));
|
||||
block_ops.push(Op::new("BT", vec![]));
|
||||
block_ops.push(Op::new("Tm", o.tlm.iter().map(|v| n(*v)).collect()));
|
||||
}
|
||||
let at = if split { start } else { o.bt_op };
|
||||
// A kept source row sits outside `block_ops`. Bound the whole paragraph when a marker is
|
||||
// safe. The close is not part of `block_ops`: that vector can end inside a text object
|
||||
// when the rewrite splits one, and a kept row's operators come later in the stream.
|
||||
@@ -1190,5 +1212,6 @@ pub(crate) fn rewrite_styled_block(
|
||||
d.set(b"Contents".to_vec(), contents);
|
||||
d.set(b"Resources".to_vec(), Object::Dict(res));
|
||||
})?;
|
||||
crate::draw_on_top(doc, &p, o.ctm, &on_top)?;
|
||||
Ok(LineEdit { substituted })
|
||||
}
|
||||
|
||||
@@ -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",
|
||||
}
|
||||
@@ -301,6 +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(),
|
||||
};
|
||||
|
||||
@@ -6,7 +6,7 @@ use crate::{
|
||||
AddedContent, AddedText, Background, BoxSpec, EditError, FieldProps, FieldValue, FillMark, HeaderFooter, Hidden, ImageEdit, InitialView, Label,
|
||||
LineEnding, LinkAction, LinkStyle, MarkFile, MarkKind, Markup, NewAnnotation, NewField, NoteIcon, ObjectTarget, PageBox, Protection, ReviewState,
|
||||
Rgb, Shape, Standard, Style, TabOrder, TransitionSpec, Watermark, a11y, copy_image, decode_data_file, embed_image, field_table, fit_picture,
|
||||
image_content_type, is_xfa_data_file, js, mark_source, measure, open_source, strip_xfa, unrestricted, xfa, xfa_after_data_change,
|
||||
image_content_type, is_xfa_data_file, js, mark_source, measure, model_poster, open_source, strip_xfa, unrestricted, xfa, xfa_after_data_change,
|
||||
};
|
||||
|
||||
mod labels;
|
||||
@@ -119,6 +119,15 @@ pub enum Edit {
|
||||
bold: Option<bool>,
|
||||
italic: Option<bool>,
|
||||
},
|
||||
/// Write `bookmarks` as children of `parent` from child `index` on, or with `replace` in
|
||||
/// place of the whole outline (`parent` must then be `[]`). A bookmark whose page this
|
||||
/// document lacks is kept without a destination (see [`pdfcraft_organize::import_outline`]).
|
||||
ImportBookmarks {
|
||||
parent: Vec<usize>,
|
||||
index: usize,
|
||||
bookmarks: Vec<pdfcraft_organize::OutlineNode>,
|
||||
replace: bool,
|
||||
},
|
||||
/// Bookmarks for the tagged headings (H, H1–H6), nested by level under a new first
|
||||
/// "Untitled" bookmark (New Bookmarks from Structure).
|
||||
BookmarksFromStructure,
|
||||
@@ -157,6 +166,17 @@ pub enum Edit {
|
||||
file: MarkFile,
|
||||
author: String,
|
||||
},
|
||||
/// Rich Media ▸ Add 3D: a U3D or PRC `model` as a 3D annotation in `rect` on `page`, named
|
||||
/// `name` (its alternate description). Its poster is the picture in `poster` (a PDF page or an
|
||||
/// image) fitted inside `rect`, keeping its shape and centred, or a labelled frame without one.
|
||||
AddModel3d {
|
||||
page: usize,
|
||||
rect: [f64; 4],
|
||||
model: Arc<Vec<u8>>,
|
||||
poster: Option<MarkFile>,
|
||||
activation: pdfcraft_annot::Activation3d,
|
||||
name: String,
|
||||
},
|
||||
/// Delete the comment at `index` in the page's `/Annots`, with its pop-up and replies.
|
||||
DeleteAnnotation {
|
||||
page: usize,
|
||||
|
||||
@@ -38,6 +38,7 @@ pub const EDIT_LABELS: &[&str] = &[
|
||||
"Set bookmark destination",
|
||||
"Colour",
|
||||
"Style",
|
||||
"Import bookmarks",
|
||||
"New bookmarks from structure",
|
||||
"New bookmarks from text styles",
|
||||
"Number pages",
|
||||
@@ -68,6 +69,7 @@ pub const EDIT_LABELS: &[&str] = &[
|
||||
"Add inserted text",
|
||||
"Add file attachment",
|
||||
"Add stamp",
|
||||
"Add 3D model",
|
||||
"Delete comment",
|
||||
"Edit comment",
|
||||
"Reply",
|
||||
@@ -193,6 +195,7 @@ impl Edit {
|
||||
// The bookmark Style and Colour menus' own names, already said in every language.
|
||||
Edit::SetBookmarkColor { .. } => Label::of("Colour"),
|
||||
Edit::SetBookmarkStyle { .. } => Label::of("Style"),
|
||||
Edit::ImportBookmarks { .. } => Label::of("Import bookmarks"),
|
||||
Edit::BookmarksFromStructure => Label::of("New bookmarks from structure"),
|
||||
Edit::BookmarksFromTextStyles { .. } => Label::of("New bookmarks from text styles"),
|
||||
Edit::NumberPages { .. } => Label::of("Number pages"),
|
||||
@@ -205,6 +208,7 @@ impl Edit {
|
||||
Edit::SetMeasurementScale { .. } => Label::of("Set measurement scale"),
|
||||
Edit::AddAnnotation(a) => Label::of(add_annotation(&a.shape)),
|
||||
Edit::AddCustomStamp { .. } => Label::of("Add stamp"),
|
||||
Edit::AddModel3d { .. } => Label::of("Add 3D model"),
|
||||
Edit::DeleteAnnotation { .. } => Label::of("Delete comment"),
|
||||
Edit::SetAnnotationContents { .. } => Label::of("Edit comment"),
|
||||
Edit::ReplyToAnnotation { .. } => Label::of("Reply"),
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
use super::{
|
||||
AddedContent, Arc, Edit, EditError, FieldValue, ImageEdit, NewAnnotation, Shape, a11y, copy_image, decode_data_file, embed_image, fit_picture,
|
||||
image_content_type, is_xfa_data_file, js, mark_source, measure, open_source, strip_xfa, unrestricted, xfa, xfa_after_data_change,
|
||||
image_content_type, is_xfa_data_file, js, mark_source, measure, model_poster, open_source, strip_xfa, unrestricted, xfa, xfa_after_data_change,
|
||||
};
|
||||
use crate::SourceProblem;
|
||||
use crate::sources::{comment_source, import_pdf_comments};
|
||||
@@ -27,6 +27,7 @@ pub(crate) fn check_permission(edit: &Edit, p: &pdfcraft_cos::Permissions) -> Re
|
||||
| Edit::SetBookmarkPage { .. }
|
||||
| Edit::SetBookmarkColor { .. }
|
||||
| Edit::SetBookmarkStyle { .. }
|
||||
| Edit::ImportBookmarks { .. }
|
||||
| Edit::BookmarksFromStructure
|
||||
| Edit::NumberPages { .. } => {
|
||||
if p.assemble() {
|
||||
@@ -49,6 +50,7 @@ pub(crate) fn check_permission(edit: &Edit, p: &pdfcraft_cos::Permissions) -> Re
|
||||
Edit::AddMeasurement(_)
|
||||
| Edit::AddAnnotation(_)
|
||||
| Edit::AddCustomStamp { .. }
|
||||
| Edit::AddModel3d { .. }
|
||||
| Edit::DeleteAnnotation { .. }
|
||||
| Edit::SetAnnotationContents { .. }
|
||||
| Edit::ReplyToAnnotation { .. }
|
||||
@@ -454,6 +456,9 @@ pub(crate) fn run_edit(doc: &mut pdfcraft_cos::Document, edit: &Edit, cx: &mut E
|
||||
Edit::SetBookmarkPage { path, page } => pdfcraft_organize::set_bookmark_page(doc, path, *page)?,
|
||||
Edit::SetBookmarkColor { path, color } => pdfcraft_organize::set_bookmark_color(doc, path, *color)?,
|
||||
Edit::SetBookmarkStyle { path, bold, italic } => pdfcraft_organize::set_bookmark_style(doc, path, *bold, *italic)?,
|
||||
Edit::ImportBookmarks { parent, index, bookmarks, replace } => {
|
||||
pdfcraft_organize::import_outline(doc, parent, *index, bookmarks, *replace)?;
|
||||
}
|
||||
Edit::BookmarksFromStructure => {
|
||||
let entries: Vec<_> = pdfcraft_a11y::headings(doc)
|
||||
.into_iter()
|
||||
@@ -509,6 +514,16 @@ pub(crate) fn run_edit(doc: &mut pdfcraft_cos::Document, edit: &Edit, cx: &mut E
|
||||
let index = pdfcraft_annot::add_annotation(doc, &new, &cx.meta())?;
|
||||
pdfcraft_annot::orient_image_stamp(doc, *page, index, rotation)?;
|
||||
}
|
||||
Edit::AddModel3d { page, rect, model, poster, activation, name } => {
|
||||
// A file that is not a model is refused before its poster is brought in.
|
||||
pdfcraft_annot::check_model(model)?;
|
||||
let poster = match poster {
|
||||
Some(file) => Some(model_poster(doc, *rect, file)?),
|
||||
None => None,
|
||||
};
|
||||
let new = pdfcraft_annot::NewModel3d { page: *page, rect: *rect, model, activation: *activation, poster, contents: name };
|
||||
pdfcraft_annot::add_3d_model(doc, &new, &cx.meta())?;
|
||||
}
|
||||
Edit::DeleteAnnotation { page, index } => pdfcraft_annot::delete_annotation(doc, *page, *index)?,
|
||||
Edit::SetAnnotationContents { page, index, text } => pdfcraft_annot::set_contents(doc, *page, *index, text, &cx.meta())?,
|
||||
Edit::ReplyToAnnotation { page, index, text, author } => {
|
||||
|
||||
@@ -54,6 +54,7 @@ pub(crate) fn scope_of(edit: &Edit) -> Scope {
|
||||
Edit::AddMeasurement(_)
|
||||
| Edit::AddAnnotation(_)
|
||||
| Edit::AddCustomStamp { .. }
|
||||
| Edit::AddModel3d { .. }
|
||||
| Edit::DeleteAnnotation { .. }
|
||||
| Edit::SetAnnotationContents { .. }
|
||||
| Edit::ReplyToAnnotation { .. }
|
||||
|
||||
@@ -35,6 +35,7 @@ mod history;
|
||||
pub mod js;
|
||||
mod layers;
|
||||
pub mod links;
|
||||
pub mod model3d;
|
||||
pub mod ocr;
|
||||
mod open;
|
||||
pub mod optimizer;
|
||||
@@ -71,7 +72,10 @@ pub use signature_scan::{PhotoRect, ScanError, SignaturePhoto, Turn};
|
||||
pub use stamp_preview::{CommentLayer, StampPreview};
|
||||
pub use text_preview::{TextEditPreview, UnmarkedPages};
|
||||
|
||||
pub use pdfcraft_organize::{BoxSpec, FieldConflicts, PageBox, SplitBy, Transition, TransitionSpec, mime_for_name, split_ranges};
|
||||
pub use pdfcraft_organize::{
|
||||
BoxSpec, FieldConflicts, MAX_IMPORT_BOOKMARKS, OutlineNode, OutlineTree, PageBox, SplitBy, Transition, TransitionSpec, mime_for_name,
|
||||
split_ranges, unmapped as outline_unmapped, view_arity as outline_view_arity,
|
||||
};
|
||||
|
||||
pub use pdfcraft_organize::LabelStyle;
|
||||
pub use pdfcraft_organize::Standard;
|
||||
@@ -108,9 +112,10 @@ pub use pdfcraft_fonts::{MAX_SIGNATURE_CHARS, ScriptOutline, script_missing, scr
|
||||
pub use pdfcraft_annot::appearance as annot_text;
|
||||
pub use pdfcraft_annot::links::{Highlight as LinkHighlight, LinkAction, LinkItem, LinkStyle};
|
||||
pub use pdfcraft_annot::{
|
||||
AppearanceCache, AttachIcon, FillMark, LineEnding, Markup, NOTE_SIZE, NewAnnotation, NoteIcon, OverlayFont, OverlayLook, Props as CommentProps,
|
||||
ReviewState, Rgb, Shape, StampGroup, StampKind, Style, rect_quad,
|
||||
Activation3d, AppearanceCache, AttachIcon, FillMark, LineEnding, Markup, NOTE_SIZE, NewAnnotation, NoteIcon, OverlayFont, OverlayLook,
|
||||
Props as CommentProps, ReviewState, Rgb, Shape, StampGroup, StampKind, Style, rect_quad,
|
||||
};
|
||||
pub use pdfcraft_annot::{MAX_MODEL_BYTES as MAX_3D_MODEL_BYTES, ModelFormat as Model3dFormat};
|
||||
pub use pdfcraft_forms::detect;
|
||||
pub use pdfcraft_optimize as optimize;
|
||||
pub use pdfcraft_preflight as pdfa;
|
||||
@@ -140,7 +145,7 @@ use layers::{apply_layer_state, set_default_layer_state, use_layer_choices};
|
||||
pub use open::{OpenContext, PreparedDocument};
|
||||
pub use page_filter::{PageOrientation, PageParity, filter_pages};
|
||||
pub use pictures::{MarkFile, image_dimensions};
|
||||
use pictures::{embed_image, fit_picture, mark_source};
|
||||
use pictures::{embed_image, fit_picture, mark_source, model_poster};
|
||||
use protection::unrestricted;
|
||||
pub use protection::{Changes, Printing, Protection, SecuritySummary};
|
||||
pub use session::Session;
|
||||
|
||||
@@ -0,0 +1,19 @@
|
||||
//! The 3D models on a page (ISO 32000-2 §13.6), read so a renderer can draw them.
|
||||
|
||||
pub use pdfcraft_annot::{MAX_MODEL_BYTES, Model3d, Model3dKind};
|
||||
|
||||
use crate::Document;
|
||||
|
||||
impl Document {
|
||||
/// The `/Annots` positions of the 3D annotations on 0-based `page`, in order.
|
||||
pub fn model_3d_annotations(&self, page: usize) -> Result<Vec<usize>, String> {
|
||||
let editor = self.editor.as_ref().ok_or("the document can't be read")?;
|
||||
pdfcraft_annot::model_3d_annotations(&editor.cos, page).map_err(|e| e.to_string())
|
||||
}
|
||||
|
||||
/// The decoded model of the 3D annotation at `/Annots` position `index` on 0-based `page`.
|
||||
pub fn model_3d(&self, page: usize, index: usize) -> Result<Model3d, String> {
|
||||
let editor = self.editor.as_ref().ok_or("the document can't be read")?;
|
||||
pdfcraft_annot::model_3d(&editor.cos, page, index).map_err(|e| e.to_string())
|
||||
}
|
||||
}
|
||||
@@ -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,
|
||||
|
||||
@@ -60,6 +60,18 @@ pub(crate) fn mark_source(doc: &mut pdfcraft_cos::Document, f: &MarkFile) -> Res
|
||||
}
|
||||
}
|
||||
|
||||
/// A 3D model's poster: the picture in `file` brought into `doc` and fitted inside `rect`
|
||||
/// (user space), keeping its shape, and centred. It is drawn in user space and not counter-rotated
|
||||
/// (unlike a stamp), so on a page with `/Rotate` it turns with the page, as the model does.
|
||||
pub(crate) fn model_poster(doc: &mut pdfcraft_cos::Document, rect: [f64; 4], file: &MarkFile) -> Result<pdfcraft_annot::PosterPicture, EditError> {
|
||||
let src = mark_source(doc, file)?;
|
||||
let (sw, sh) = src.size;
|
||||
if !(sw.is_finite() && sh.is_finite() && sw > 0.0 && sh > 0.0) {
|
||||
return Err(EditError::Source(format!("{}: the poster has no area", file.name)));
|
||||
}
|
||||
Ok(pdfcraft_annot::PosterPicture { xobject: src.xobject, image: src.image, size: (sw, sh), at: fit_picture(rect, sw, sh) })
|
||||
}
|
||||
|
||||
/// The dimensions of an image from its bytes (JPEG, PNG, TIFF), without decoding the full raster.
|
||||
pub fn image_dimensions(bytes: &[u8]) -> Option<(u32, u32)> {
|
||||
let format = image::guess_format(bytes).ok()?;
|
||||
|
||||
@@ -168,6 +168,14 @@ impl Session {
|
||||
Some(BookmarkPage { rows, next: (end < all.len()).then_some(end), truncated: doc.info.outline_more })
|
||||
}
|
||||
|
||||
/// The bookmark at `path` with everything under it, or the whole outline for `[]`, as a tree
|
||||
/// another document can take ([`crate::Edit::ImportBookmarks`]). `None` when no document has
|
||||
/// `id`, or its structure could not be read for editing.
|
||||
pub fn outline_tree(&self, id: DocId, path: &[usize]) -> Option<Result<pdfcraft_organize::OutlineTree, pdfcraft_organize::OutlineError>> {
|
||||
let editor = self.get(id)?.editor.as_ref()?;
|
||||
Some(pdfcraft_organize::outline_tree(&editor.cos, path))
|
||||
}
|
||||
|
||||
/// Top-level bookmarks as split points: (first page of each part, its bookmark's title).
|
||||
pub fn bookmark_splits(&self, id: DocId) -> Vec<(usize, String)> {
|
||||
let Some(doc) = self.get(id) else { return Vec::new() };
|
||||
|
||||
@@ -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;
|
||||
|
||||
@@ -549,6 +549,85 @@ fn pdf_page_stamps_fit_inside_an_explicit_box() {
|
||||
assert!(content.contains("/Pic Do") && !content.contains("BI"), "{content}");
|
||||
}
|
||||
|
||||
/// #1297: a 3D model on a page keeps the whole box as its rectangle and draws a PDF poster as a
|
||||
/// form XObject fitted inside it, keeping its shape and centred.
|
||||
#[test]
|
||||
fn a_3d_model_gets_a_fitted_vector_poster_and_a_file_that_is_not_one_is_refused() {
|
||||
let mut session = Session::new().with_clock(|| 1_700_000_000);
|
||||
let blank = session.create_blank(595.0, 842.0, 1).unwrap();
|
||||
let id = session.open_new("model.pdf", blank).unwrap();
|
||||
let mut prc = b"PRC".to_vec();
|
||||
prc.extend_from_slice(&[1; 64]);
|
||||
let add = |model: Vec<u8>| Edit::AddModel3d {
|
||||
page: 0,
|
||||
rect: [56.0, 400.0, 539.0, 700.0],
|
||||
model: Arc::new(model),
|
||||
poster: Some(MarkFile { name: "poster.pdf".into(), bytes: Arc::new(half_red_page()), page: 0 }),
|
||||
activation: Activation3d::default(),
|
||||
name: "Bracket".into(),
|
||||
};
|
||||
assert!(session.apply(id, add(b"%PDF-1.7 not a model".to_vec())).is_err());
|
||||
session.apply(id, add(prc)).unwrap();
|
||||
|
||||
let doc = pdfcraft_cos::Document::open(session.save_bytes(id).unwrap()).unwrap();
|
||||
let page = &pdfcraft_model::pages(&doc)[0];
|
||||
let annots = doc.resolve(page.dict.get(b"Annots").unwrap());
|
||||
let [only] = annots.as_array().unwrap().as_slice() else { panic!("the refused model added nothing: {annots:?}") };
|
||||
let annot = doc.get(only.as_ref().unwrap());
|
||||
let annot = annot.as_dict().unwrap();
|
||||
assert_eq!(annot.name(b"Subtype"), Some(&b"3D"[..]));
|
||||
let rect: Vec<f64> = annot.get(b"Rect").unwrap().as_array().unwrap().iter().filter_map(pdfcraft_cos::Object::as_f64).collect();
|
||||
assert_eq!(rect, [56.0, 400.0, 539.0, 700.0], "the whole box, not the fitted picture");
|
||||
assert_eq!(doc.resolve(annot.get(b"3DA").unwrap()).as_dict().unwrap().name(b"A"), Some(&b"XA"[..]));
|
||||
let ap = doc.resolve(annot.get(b"AP").unwrap());
|
||||
let pdfcraft_cos::Object::Stream(normal) = doc.get(ap.as_dict().unwrap().reference(b"N").unwrap()).as_ref().clone() else {
|
||||
panic!("an appearance stream")
|
||||
};
|
||||
let pic = doc.resolve(normal.dict.get(b"Resources").unwrap()).as_dict().unwrap().clone();
|
||||
let pic = doc.resolve(pic.get(b"XObject").unwrap()).as_dict().unwrap().reference(b"Pic").unwrap();
|
||||
let pdfcraft_cos::Object::Stream(picture) = doc.get(pic).as_ref().clone() else { panic!("the picture is a stream") };
|
||||
assert_eq!(picture.dict.name(b"Subtype"), Some(&b"Form"[..]), "the page is kept as a form XObject");
|
||||
// The 80 × 40 page in the 483 × 300 box: 483 × 241.5 from y 429.25.
|
||||
let content = String::from_utf8(normal.decoded().unwrap().to_vec()).unwrap();
|
||||
assert!(content.contains(" 56 429.25 cm /Pic Do"), "{content}");
|
||||
}
|
||||
|
||||
/// A PDF poster whose page has no area is refused rather than drawn as nothing.
|
||||
#[test]
|
||||
fn a_3d_poster_page_without_area_is_refused() {
|
||||
let mut session = Session::new().with_clock(|| 1_700_000_000);
|
||||
let blank = session.create_blank(595.0, 842.0, 1).unwrap();
|
||||
let id = session.open_new("model.pdf", blank).unwrap();
|
||||
let flat = String::from_utf8(half_red_page()).unwrap().replace("[0 0 80 40]", "[0 0 80 0 ]");
|
||||
let add = Edit::AddModel3d {
|
||||
page: 0,
|
||||
rect: [56.0, 400.0, 539.0, 700.0],
|
||||
model: Arc::new(b"PRC rest".to_vec()),
|
||||
poster: Some(MarkFile { name: "flat.pdf".into(), bytes: Arc::new(flat.into_bytes()), page: 0 }),
|
||||
activation: Activation3d::default(),
|
||||
name: "Bracket".into(),
|
||||
};
|
||||
assert!(matches!(session.apply(id, add), Err(EditError::Source(_))));
|
||||
assert!(session.get(id).unwrap().info.annotations.is_empty(), "nothing was added");
|
||||
}
|
||||
|
||||
/// Adding a 3D model is a comment change: refused without the comments permission, and only the
|
||||
/// comments are rebuilt after it.
|
||||
#[test]
|
||||
fn a_3d_model_needs_the_comments_permission_and_changes_the_comments() {
|
||||
let edit = Edit::AddModel3d {
|
||||
page: 0,
|
||||
rect: [0.0, 0.0, 100.0, 100.0],
|
||||
model: Arc::new(b"PRC rest".to_vec()),
|
||||
poster: None,
|
||||
activation: Activation3d::default(),
|
||||
name: String::new(),
|
||||
};
|
||||
let p = pdfcraft_cos::Permissions { bits: 0, owner: false };
|
||||
assert_eq!(check_permission(&edit, &p), Err(EditError::NotPermitted("comments")));
|
||||
assert_eq!(crate::history::scope_of(&edit), crate::history::Scope::Comments);
|
||||
}
|
||||
|
||||
fn page_texts(s: &Session, id: DocId) -> Vec<String> {
|
||||
let doc = s.get(id).unwrap();
|
||||
let config = pdfcraft_render::RenderConfig { password: doc.password.as_deref().map(Arc::from), ..Default::default() };
|
||||
@@ -3610,6 +3689,66 @@ fn create_and_reduce() {
|
||||
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;
|
||||
@@ -10191,3 +10330,153 @@ fn image_transform_engine_refuses_singular_matrices_without_mutation() {
|
||||
assert_eq!(s.get(id).unwrap().bytes, before);
|
||||
}
|
||||
}
|
||||
|
||||
/// Optimize has JBIG2 images share a symbol dictionary only where redaction can store each again
|
||||
/// without it. Of four pages of the same scan, the two in DeviceGray and the image mask share one;
|
||||
/// the one in a DeviceN of one colourant, which redaction doesn't store again, is coded alone.
|
||||
/// Redacting the first page then stores the second and the mask again without the dictionary,
|
||||
/// which leaves the file.
|
||||
#[test]
|
||||
fn redacting_an_optimized_jbig2_page_stores_the_rest_of_its_group_again() {
|
||||
use pdfcraft_cos::{Dict, Document, ObjRef, Object, SaveOptions, Stream, write_full};
|
||||
let (w, h) = (600usize, 480usize);
|
||||
// Lines of 26 letters, each 32 rows of a run from a stem down its left side, of 2 to 24 pixels,
|
||||
// the same to the pixel wherever it is, picked and spaced at random.
|
||||
let mut seed = 0x2545_F491_4F6C_DD1Du64;
|
||||
let mut next = move || {
|
||||
seed ^= seed << 13;
|
||||
seed ^= seed >> 7;
|
||||
seed ^= seed << 17;
|
||||
seed as usize
|
||||
};
|
||||
let letters: Vec<Vec<usize>> = (0..26).map(|_| (0..16).map(|_| 1 + next() % 12).collect()).collect();
|
||||
let stride = w.div_ceil(8);
|
||||
let mut bits = vec![0xFFu8; stride * h];
|
||||
for top in (8..h - 40).step_by(44) {
|
||||
let mut x = 8 + next() % 8;
|
||||
while x + 32 < w {
|
||||
let letter = &letters[next() % 26];
|
||||
for (row, run) in letter.iter().enumerate() {
|
||||
for (px, py) in (x..x + 2 * run).flat_map(|px| [(px, top + 2 * row), (px, top + 2 * row + 1)]) {
|
||||
bits[py * stride + px / 8] &= !(0x80 >> (px % 8));
|
||||
}
|
||||
}
|
||||
x += 2 * letter.iter().max().unwrap_or(&1) + 4 + next() % 5;
|
||||
}
|
||||
}
|
||||
let mut doc = Document::new_empty();
|
||||
let pages = doc.root().and_then(|r| doc.get(r).as_dict().and_then(|d| d.reference(b"Pages"))).unwrap();
|
||||
let device_n = Object::Array(vec![Object::name("DeviceN"), Object::Array(vec![Object::name("Black")]), Object::name("DeviceGray"), {
|
||||
let mut tint = Dict::new();
|
||||
tint.set(b"FunctionType".to_vec(), Object::Int(2));
|
||||
tint.set(b"Domain".to_vec(), Object::Array(vec![Object::Int(0), Object::Int(1)]));
|
||||
tint.set(b"N".to_vec(), Object::Int(1));
|
||||
Object::Dict(tint)
|
||||
}]);
|
||||
let mut images: Vec<ObjRef> = Vec::new();
|
||||
let grey = || ("ColorSpace", Object::name("DeviceGray"));
|
||||
for (k, (key, value)) in [grey(), grey(), ("ColorSpace", device_n), ("ImageMask", Object::Bool(true))].into_iter().enumerate() {
|
||||
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"Width".to_vec(), Object::Int(w as i64));
|
||||
d.set(b"Height".to_vec(), Object::Int(h as i64));
|
||||
d.set(b"BitsPerComponent".to_vec(), Object::Int(1));
|
||||
d.set(key.as_bytes().to_vec(), value);
|
||||
let image = doc.add(Object::Stream(Stream::flate(d, &bits)));
|
||||
images.push(image);
|
||||
let content = doc.add(Object::Stream(Stream::from_raw(Dict::new(), b"q 144 0 0 115.2 36 600 cm /Im Do Q".to_vec())));
|
||||
let mut xobjects = Dict::new();
|
||||
xobjects.set(b"Im".to_vec(), Object::Ref(image));
|
||||
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"Parent".to_vec(), Object::Ref(pages));
|
||||
page.set(b"MediaBox".to_vec(), Object::Array(vec![0.into(), 0.into(), 612.into(), 792.into()]));
|
||||
page.set(b"Resources".to_vec(), Object::Dict(resources));
|
||||
page.set(b"Contents".to_vec(), Object::Ref(content));
|
||||
if k == 0 {
|
||||
let mut mark = Dict::new();
|
||||
mark.set(b"Type".to_vec(), Object::name("Annot"));
|
||||
mark.set(b"Subtype".to_vec(), Object::name("Redact"));
|
||||
mark.set(b"Rect".to_vec(), Object::Array(vec![40.into(), 610.into(), 100.into(), 650.into()]));
|
||||
let mark = doc.add(Object::Dict(mark));
|
||||
page.set(b"Annots".to_vec(), Object::Array(vec![Object::Ref(mark)]));
|
||||
}
|
||||
let page = doc.add(Object::Dict(page));
|
||||
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(page));
|
||||
d.set(b"Count".to_vec(), Object::Int(kids.len() as i64));
|
||||
d.set(b"Kids".to_vec(), Object::Array(kids));
|
||||
})
|
||||
.unwrap();
|
||||
}
|
||||
let mono = pdfcraft_optimize::MonoSettings {
|
||||
compression: pdfcraft_optimize::MonoCompression::Jbig2,
|
||||
downsample: false,
|
||||
..pdfcraft_optimize::MonoSettings::REDUCE
|
||||
};
|
||||
pdfcraft_optimize::optimize(&mut doc, &pdfcraft_optimize::Settings { mono, ..Default::default() }).unwrap();
|
||||
let globals = |doc: &Document, image: ObjRef| match &*doc.get(image) {
|
||||
Object::Stream(s) => s.dict.get(b"DecodeParms").and_then(Object::as_dict).and_then(|d| d.reference(b"JBIG2Globals")),
|
||||
_ => None,
|
||||
};
|
||||
let shared = globals(&doc, images[0]);
|
||||
assert!(shared.is_some() && globals(&doc, images[1]) == shared && globals(&doc, images[3]) == shared, "DeviceGray and the mask share");
|
||||
assert_eq!(globals(&doc, images[2]), None, "the DeviceN page is coded alone");
|
||||
pdfcraft_redact::apply(&mut doc, None).unwrap();
|
||||
let saved = Document::open(Arc::new(write_full(&doc, &SaveOptions::default()).unwrap())).unwrap();
|
||||
let named = saved.scan_objects().filter(|(_, o)| matches!(&**o, Object::Stream(s) if saved.jbig2_globals_ref(s).is_some())).count();
|
||||
assert_eq!(named, 0, "no image names the dictionary, which left with them");
|
||||
}
|
||||
|
||||
#[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");
|
||||
}
|
||||
|
||||
/// A whole tree goes in as one undoable step, and a refused tree changes nothing.
|
||||
#[test]
|
||||
fn imported_bookmarks_undo_in_one_step() {
|
||||
let (mut s, id) = session_with(2);
|
||||
let node = |title: &str, page, children| pdfcraft_organize::OutlineNode {
|
||||
title: title.into(),
|
||||
page,
|
||||
view: None,
|
||||
color: None,
|
||||
italic: false,
|
||||
bold: false,
|
||||
open: true,
|
||||
children,
|
||||
};
|
||||
let bookmarks = vec![node("Intro", Some(0), vec![node("Detail", Some(5), vec![])]), node("End", Some(1), vec![])];
|
||||
s.apply(id, Edit::ImportBookmarks { parent: vec![], index: 0, bookmarks: bookmarks.clone(), replace: false }).unwrap();
|
||||
assert_eq!(outline_titles(&s.get(id).unwrap().info.outline), ["Intro→1[Detail→0]", "End→2"]);
|
||||
assert_eq!(s.get(id).unwrap().can_undo(), Some("Import bookmarks"));
|
||||
assert_eq!(s.outline_tree(id, &[]).unwrap().unwrap().nodes[0].title, "Intro");
|
||||
s.undo(id).unwrap();
|
||||
assert!(s.get(id).unwrap().info.outline.is_empty());
|
||||
s.apply(id, Edit::ImportBookmarks { parent: vec![], index: 0, bookmarks: bookmarks.clone(), replace: false }).unwrap();
|
||||
s.apply(id, Edit::ImportBookmarks { parent: vec![], index: 0, bookmarks: vec![node("New", Some(1), vec![])], replace: true }).unwrap();
|
||||
assert_eq!(outline_titles(&s.get(id).unwrap().info.outline), ["New→2"]);
|
||||
s.undo(id).unwrap();
|
||||
assert_eq!(outline_titles(&s.get(id).unwrap().info.outline), ["Intro→1[Detail→0]", "End→2"]);
|
||||
s.undo(id).unwrap();
|
||||
let err = s.apply(id, Edit::ImportBookmarks { parent: vec![4], index: 0, bookmarks, replace: false }).unwrap_err();
|
||||
assert!(err.to_string().contains("no bookmark"), "{err}");
|
||||
assert!(s.get(id).unwrap().info.outline.is_empty());
|
||||
}
|
||||
|
||||
@@ -207,3 +207,192 @@ fn visible_stretched_text_rewrites_unchanged() {
|
||||
let i = ((y * out.width + x) * 4) as usize;
|
||||
assert_eq!(&out.rgba[i..i + 3], &[255, 255, 255]);
|
||||
}
|
||||
|
||||
/// A scan whose OCR layer is drawn first and the opaque page image over it, as some OCR tools
|
||||
/// write it (#3973): invisible Helvetica `text` on the scanned word, then the image.
|
||||
fn ocr_under_scan(text: &str) -> std::sync::Arc<Vec<u8>> {
|
||||
under_scan(&format!("BT /F1 20 Tf 3 Tr 42 44 Td ({text}) Tj ET"))
|
||||
}
|
||||
|
||||
/// A page whose `text` content is followed by the opaque 200 × 100 scan image.
|
||||
fn under_scan(text: &str) -> std::sync::Arc<Vec<u8>> {
|
||||
under_scan_with(text, |_| pdfcraft_cos::Dict::new())
|
||||
}
|
||||
|
||||
/// As [`under_scan`], with the page's ExtGState resources made by `ext_gstates`.
|
||||
fn under_scan_with(text: &str, ext_gstates: impl FnOnce(&mut pdfcraft_cos::Document) -> pdfcraft_cos::Dict) -> std::sync::Arc<Vec<u8>> {
|
||||
use pdfcraft_cos::{Dict, Document, Object, SaveOptions, Stream};
|
||||
let (w, h) = (200u32, 100u32);
|
||||
let mut rgb = Vec::new();
|
||||
for y in 0..h {
|
||||
for x in 0..w {
|
||||
let ink = (WORD[0]..WORD[2]).contains(&x) && (WORD[1]..WORD[3]).contains(&y);
|
||||
rgb.extend(if ink { INK } else { PAPER });
|
||||
}
|
||||
}
|
||||
let mut d = Document::new_empty();
|
||||
let pages = d.add(Object::Dict(Dict::new()));
|
||||
let content = format!("{text} q 200 0 0 100 0 0 cm /Im Do Q");
|
||||
let contents = d.add(Object::Stream(Stream::flate(Dict::new(), content.as_bytes())));
|
||||
let mut image = Dict::new();
|
||||
image.set(b"Type".to_vec(), Object::name("XObject"));
|
||||
image.set(b"Subtype".to_vec(), Object::name("Image"));
|
||||
image.set(b"Width".to_vec(), Object::Int(i64::from(w)));
|
||||
image.set(b"Height".to_vec(), Object::Int(i64::from(h)));
|
||||
image.set(b"ColorSpace".to_vec(), Object::name("DeviceRGB"));
|
||||
image.set(b"BitsPerComponent".to_vec(), Object::Int(8));
|
||||
let image = d.add(Object::Stream(Stream::flate(image, &rgb)));
|
||||
let mut font = Dict::new();
|
||||
font.set(b"Type".to_vec(), Object::name("Font"));
|
||||
font.set(b"Subtype".to_vec(), Object::name("Type1"));
|
||||
font.set(b"BaseFont".to_vec(), Object::name("Helvetica"));
|
||||
let mut fonts = Dict::new();
|
||||
fonts.set(b"F1".to_vec(), Object::Dict(font));
|
||||
let mut xobjects = Dict::new();
|
||||
xobjects.set(b"Im".to_vec(), Object::Ref(image));
|
||||
let mut res = Dict::new();
|
||||
res.set(b"Font".to_vec(), Object::Dict(fonts));
|
||||
res.set(b"XObject".to_vec(), Object::Dict(xobjects));
|
||||
res.set(b"ExtGState".to_vec(), Object::Dict(ext_gstates(&mut d)));
|
||||
let mut p = Dict::new();
|
||||
p.set(b"Type".to_vec(), Object::name("Page"));
|
||||
p.set(b"Parent".to_vec(), Object::Ref(pages));
|
||||
p.set(b"Contents".to_vec(), Object::Ref(contents));
|
||||
p.set(b"Resources".to_vec(), Object::Dict(res));
|
||||
p.set(b"MediaBox".to_vec(), Object::Array([0, 0, 200, 100].map(Object::Int).to_vec()));
|
||||
let page = d.add(Object::Dict(p));
|
||||
d.update_dict(pages, |p| {
|
||||
p.set(b"Type".to_vec(), Object::name("Pages"));
|
||||
p.set(b"Kids".to_vec(), Object::Array(vec![Object::Ref(page)]));
|
||||
p.set(b"Count".to_vec(), Object::Int(1));
|
||||
})
|
||||
.unwrap();
|
||||
let mut root = Dict::new();
|
||||
root.set(b"Type".to_vec(), Object::name("Catalog"));
|
||||
root.set(b"Pages".to_vec(), Object::Ref(pages));
|
||||
let root = d.add(Object::Dict(root));
|
||||
d.trailer_mut().set(b"Root".to_vec(), Object::Ref(root));
|
||||
std::sync::Arc::new(pdfcraft_cos::write_full(&d, &SaveOptions::default()).unwrap())
|
||||
}
|
||||
|
||||
/// The scanned word's box shows the cover and new ink, not the scan.
|
||||
fn assert_edit_shows(s: &Session, id: pdfcraft_engine::DocId, label: &str) {
|
||||
let px = word_pixels(s, id);
|
||||
let paper = px.iter().filter(|p| near(**p, PAPER)).count();
|
||||
let ink = px.iter().filter(|p| near(**p, INK)).count();
|
||||
assert!(paper * 10 > px.len() * 4, "{label}: the cover is drawn over the scan: {paper} of {} paper", px.len());
|
||||
assert!(ink * 100 > px.len() * 3, "{label}: the new text shows: {ink} of {} ink", px.len());
|
||||
}
|
||||
|
||||
fn texts(s: &Session, id: pdfcraft_engine::DocId) -> Vec<String> {
|
||||
s.get(id).unwrap().text_blocks(0).iter().map(|b| b.text.replace('\n', " ")).collect()
|
||||
}
|
||||
|
||||
fn edit_block(s: &mut Session, id: pdfcraft_engine::DocId, block: usize, text: &str) {
|
||||
s.apply(id, Edit::EditTextBlock { page: 0, block, text: text.into(), style: Default::default() }).unwrap();
|
||||
}
|
||||
|
||||
/// The OCR layer is under the scan image: the rewritten paragraph is drawn on top of the image,
|
||||
/// not in the OCR text's place where the image would hide it (#3973). One line takes the
|
||||
/// single-style rewrite, a typed line break the styled one. Undo restores the hidden layer, and
|
||||
/// the edit survives redo, a save and reopen, and being edited again.
|
||||
#[test]
|
||||
fn an_ocr_layer_under_the_scan_image_shows_its_edit() {
|
||||
for edit in ["Jane", "Jane\nDoe"] {
|
||||
let mut s = Session::new();
|
||||
let id = s.open("ocr-under-scan.pdf", None, ocr_under_scan("John"), None).unwrap();
|
||||
let blocks = s.get(id).unwrap().text_blocks(0);
|
||||
assert_eq!(blocks.len(), 1);
|
||||
assert!(blocks[0].invisible, "the OCR layer is invisible text");
|
||||
assert!(word_pixels(&s, id).iter().all(|p| near(*p, INK)), "the scanned word fills its box");
|
||||
|
||||
edit_block(&mut s, id, 0, edit);
|
||||
assert_eq!(texts(&s, id), [edit.replace('\n', " ")], "{edit:?}");
|
||||
assert_edit_shows(&s, id, edit);
|
||||
|
||||
s.undo(id).unwrap();
|
||||
assert_eq!(texts(&s, id), ["John"], "{edit:?}: undo");
|
||||
assert!(s.get(id).unwrap().text_blocks(0)[0].invisible, "{edit:?}: undo hides the layer again");
|
||||
assert!(word_pixels(&s, id).iter().all(|p| near(*p, INK)), "{edit:?}: undo shows the scan again");
|
||||
s.redo(id).unwrap();
|
||||
assert_edit_shows(&s, id, &format!("{edit:?} redo"));
|
||||
|
||||
let saved = s.save_bytes(id).unwrap();
|
||||
let mut reopened = Session::new();
|
||||
let id = reopened.open("saved.pdf", None, saved, None).unwrap();
|
||||
assert_eq!(texts(&reopened, id), [edit.replace('\n', " ")], "{edit:?}: reopened");
|
||||
assert_edit_shows(&reopened, id, &format!("{edit:?} reopened"));
|
||||
|
||||
edit_block(&mut reopened, id, 0, "Ann");
|
||||
assert_eq!(texts(&reopened, id), ["Ann"], "{edit:?}: edited again");
|
||||
assert_edit_shows(&reopened, id, &format!("{edit:?} edited again"));
|
||||
}
|
||||
}
|
||||
|
||||
/// Visible text earlier in the same text object makes the rewrite split it; the OCR phrase still
|
||||
/// goes on top of the scan, and the visible text stays.
|
||||
#[test]
|
||||
fn an_ocr_phrase_split_from_visible_text_under_the_scan_shows_its_edit() {
|
||||
for edit in ["Jane", "Jane\nDoe"] {
|
||||
let mut s = Session::new();
|
||||
let page = under_scan("BT /F1 20 Tf 10 80 Td (Head) Tj 3 Tr 32 -36 Td (John) Tj ET");
|
||||
let id = s.open("split.pdf", None, page, None).unwrap();
|
||||
let blocks = s.get(id).unwrap().text_blocks(0);
|
||||
let john = blocks.iter().position(|b| b.text == "John").unwrap();
|
||||
assert!(blocks[john].invisible && blocks.iter().any(|b| b.text == "Head" && !b.invisible), "{blocks:?}");
|
||||
edit_block(&mut s, id, john, edit);
|
||||
let mut after = texts(&s, id);
|
||||
after.sort();
|
||||
let mut want = vec!["Head".to_string(), edit.replace('\n', " ")];
|
||||
want.sort();
|
||||
assert_eq!(after, want, "{edit:?}");
|
||||
assert_edit_shows(&s, id, &format!("{edit:?} split"));
|
||||
}
|
||||
}
|
||||
|
||||
/// `/SM`: a luminosity soft mask that is white over 30..110 × 30..70 in the space it is selected
|
||||
/// in, black elsewhere.
|
||||
fn soft_mask_state(d: &mut pdfcraft_cos::Document) -> pdfcraft_cos::Dict {
|
||||
use pdfcraft_cos::{Dict, Object, Stream};
|
||||
let mut group = Dict::new();
|
||||
group.set(b"S".to_vec(), Object::name("Transparency"));
|
||||
group.set(b"CS".to_vec(), Object::name("DeviceRGB"));
|
||||
let mut form = Dict::new();
|
||||
form.set(b"Type".to_vec(), Object::name("XObject"));
|
||||
form.set(b"Subtype".to_vec(), Object::name("Form"));
|
||||
form.set(b"BBox".to_vec(), Object::Array([0, 0, 200, 100].map(Object::Int).to_vec()));
|
||||
form.set(b"Group".to_vec(), Object::Dict(group));
|
||||
let mut mask = Dict::new();
|
||||
mask.set(b"Type".to_vec(), Object::name("Mask"));
|
||||
mask.set(b"S".to_vec(), Object::name("Luminosity"));
|
||||
mask.set(b"G".to_vec(), Object::Ref(d.add(Object::Stream(Stream::flate(form, b"1 g 30 30 80 40 re f")))));
|
||||
let mut state = Dict::new();
|
||||
state.set(b"Type".to_vec(), Object::name("ExtGState"));
|
||||
state.set(b"SMask".to_vec(), Object::Dict(mask));
|
||||
let mut states = Dict::new();
|
||||
states.set(b"SM".to_vec(), Object::Dict(state));
|
||||
states
|
||||
}
|
||||
|
||||
/// The soft mask is selected before a translation, so it is placed by the CTM before it. The
|
||||
/// paragraph lifted over the scan selects it again after its own `cm`: there it must be placed
|
||||
/// as it was, not 100 pt to the right where it would hide the new text, so the edit renders
|
||||
/// exactly as the same edit on the page without the mask. Both rewrite paths.
|
||||
#[test]
|
||||
fn a_soft_mask_selected_before_a_cm_stays_put_when_the_edit_is_lifted() {
|
||||
for edit in ["Jane", "Jane\nDoe"] {
|
||||
let mut plain = Session::new();
|
||||
let page = under_scan("q 1 0 0 1 100 0 cm BT /F1 20 Tf 3 Tr -58 44 Td (John) Tj ET Q");
|
||||
let plain_id = plain.open("plain.pdf", None, page, None).unwrap();
|
||||
edit_block(&mut plain, plain_id, 0, edit);
|
||||
let mut s = Session::new();
|
||||
let page = under_scan_with("q /SM gs 1 0 0 1 100 0 cm BT /F1 20 Tf 3 Tr -58 44 Td (John) Tj ET Q", soft_mask_state);
|
||||
let id = s.open("masked.pdf", None, page, None).unwrap();
|
||||
assert_eq!(texts(&s, id), ["John"]);
|
||||
edit_block(&mut s, id, 0, edit);
|
||||
assert_eq!(texts(&s, id), [edit.replace('\n', " ")], "{edit:?}");
|
||||
assert_edit_shows(&s, id, &format!("{edit:?} masked"));
|
||||
let ink = |s: &Session, id| word_pixels(s, id).iter().filter(|p| near(**p, INK)).count();
|
||||
assert_eq!(ink(&s, id), ink(&plain, plain_id), "{edit:?}: the mask does not hide the new text");
|
||||
}
|
||||
}
|
||||
|
||||
@@ -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");
|
||||
|
||||
@@ -27,10 +27,11 @@ 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
|
||||
pub struct CcittParams { k, columns, rows, end_of_line, encoded_byte_align, end_of_block, black_is_1 } // Table 11; Default = its defaults
|
||||
decode_ccitt(data, ¶ms, max_rows) -> Result<Vec<u8>, FilterError> // CCITT fax as CCITTFaxDecode gives it; columns <= MAX_CCITT_COLUMNS
|
||||
decode_jbig2(data, globals, columns, rows, max) -> Result<Vec<u8>, FilterError> // JBIG2 as JBIG2Decode gives it; a page of columns × rows, within max and MAX_JBIG2_PIXELS
|
||||
encode_jbig2_generic(data, columns, rows) -> Result<Vec<u8>, FilterError> // 1-bit rows as lossless JBIG2 for JBIG2Decode; columns <= MAX_JBIG2_COLUMNS
|
||||
encode_jbig2(data, columns, rows) -> Result<Vec<u8>, FilterError> // 1-bit rows as lossless JBIG2 for JBIG2Decode, symbol coded when that is smaller; columns <= MAX_JBIG2_COLUMNS
|
||||
decode_ccitt_within(data, ¶ms, max_rows, work: &mut u64) -> Result<Vec<u8>, FilterError> // CCITT fax as CCITTFaxDecode gives it; columns <= MAX_CCITT_COLUMNS; its rows paid for from work before they are decoded
|
||||
decode_jbig2_within(data, globals, columns, rows, max, work: &mut u64) -> Result<Vec<u8>, FilterError> // JBIG2 as JBIG2Decode gives it; a page of columns × rows, within max and MAX_JBIG2_PIXELS; reading and decoding it spend from work, in the decoder's steps
|
||||
encode_jbig2_generic(data, columns, rows) -> Result<Vec<u8>, FilterError> // 1-bit rows as lossless JBIG2 for JBIG2Decode; columns and rows <= MAX_JBIG2_COLUMNS (65,535) and MAX_JBIG2_PIXELS (2^28) samples, what the decoder takes
|
||||
encode_jbig2(data, columns, rows) -> Result<Vec<u8>, FilterError> // 1-bit rows as lossless JBIG2 for JBIG2Decode, symbol coded when that is smaller; the same limits
|
||||
encode_jbig2_shared(&[(data, columns, rows)]) -> Result<Option<SharedJbig2>, FilterError> // images symbol coded sharing one dictionary: the /JBIG2Globals data, and each image's stream or None; the same limits
|
||||
```
|
||||
|
||||
- `chain` is applied first to last, as in a `/Filter` array.
|
||||
@@ -50,8 +51,8 @@ encode_jbig2(data, columns, rows) -> Result<Vec<u8>, FilterError> // 1-bit row
|
||||
| ASCIIHexDecode | white space ignored, odd digit padded with 0, `>` EOD (optional), other characters → Corrupt | upper case, newline every 64 digits, `>` |
|
||||
| ASCII85Decode | `<~` prefix, `z`, white space, `~>` (or bare `~`, or none) EOD, final partial group; `z` inside a group, a 1-char final group, overflow or bad characters → Corrupt | `z` for zero groups, newline every 75 characters, `~>` |
|
||||
| RunLengthDecode | 0–127 literal, 129–255 repeat, 128 EOD (optional); truncated run → Corrupt | runs of ≥2 repeat, literals up to 128, 128 |
|
||||
| CCITTFaxDecode | not in a chain (`Unsupported`); `decode_ccitt` decodes Group 3 and Group 4 on its own, as rows of 1-bit samples each on a new byte, black 0 unless `black_is_1`, at most `max_rows` rows (fewer with `/Rows`), the rows before any damage, up to 1,048,576 samples a row; Group 3 rows on bytes are read by their end-of-line codes when the data starts with one and on bytes otherwise, whatever `end_of_line` says, so data with codes but none before the first row (not as T.4 sends them) is read on bytes, as the renderer draws it, and at `k` 0 may come out as other rows (`pdfcraft_cos::Document::decoded_image` calls it for a fax image, after the filters before it) | `encode_g4`: Group 4 (`/K -1`) with an end-of-block mark, 0 bits coded black so `/BlackIs1 false` decodes the same bits; rows packed MSB first, each on a new byte, padding bits and trailing bytes ignored; up to 32,767 samples a row (the encoder counts positions in 16 bits); no rows or columns, or too wide → Unsupported, too few bytes → Corrupt |
|
||||
| JBIG2Decode | not in a chain (`Unsupported`); `decode_jbig2` decodes it on its own with `hayro-jbig2`, given what its `/JBIG2Globals` decode to, as rows of 1-bit samples each on a new byte, black 0; the page has to be `columns` × `rows` (PdfCraft's renderer draws the whole page into the image), within `max` bytes as such rows and 2^28 pixels (`MAX_JBIG2_PIXELS`, about the most the decoder takes), checked before it is decoded; regions inside it are bounded by the decoder alone (a region may claim more pixels than its page); damaged data, or globals that don't decode, are `Corrupt` (`pdfcraft_cos::Document::decoded_image` calls it for a JBIG2 image, after the filters before it) | `encode_jbig2_generic`: the embedded organisation (D.3) with a page information segment and an immediate lossless generic region (7.4.6), no `/JBIG2Globals`; template 0 with its nominal AT pixels and typical prediction (6.2.5), coded with the MQ arithmetic coder (Annex E, Table E.1) and ended by its 0xFF 0xAC marker. A 0 sample is coded as a JBIG2 1 (black), since `JBIG2Decode` gives black as 0, so the stream decodes to the same bits; rows packed MSB first, each on a new byte, padding bits and trailing bytes ignored; up to 1,048,576 samples a row; no rows or columns, or too wide → Unsupported, too few bytes → Corrupt. `encode_jbig2`: the smaller of that and symbol coding (`jbig2/symbols.rs`): each distinct mark (8-connected black pixels, at most 256 a side) stored once in a symbol dictionary (7.4.2; arithmetic coded, each bitmap a template 0 generic region without typical prediction, the bitmaps sharing their contexts) and placed by immediate lossless text regions referring to it (7.4.3; bottom-left reference corner, strips of 1, 2, 4 or 8 rows, whichever is smallest), each of at most 10,000 instances over a band of rows, as the decoder PdfCraft renders with (`hayro-jbig2`) takes no more in one region, with larger marks, and in a second plan marks that occur once, in a generic region over their box. Only exact copies share a symbol (no refinement), so the stream decodes to the same bits; fewer than two symbols, more than 2^20 black runs, 65,536 distinct marks or 16 MiB of their pixels, or more than 2^24 rows, and the generic coding is used; a plan of more than 32,767 symbols (that decoder refuses more) isn't made |
|
||||
| CCITTFaxDecode | not in a chain (`Unsupported`); `decode_ccitt_within` decodes Group 3 and Group 4 on its own, as rows of 1-bit samples each on a new byte, black 0 unless `black_is_1`, at most `max_rows` rows (fewer with `/Rows`), the rows before any damage, up to 1,048,576 samples a row; Group 3 rows on bytes are read by their end-of-line codes when the data starts with one and on bytes otherwise, whatever `end_of_line` says, so data with codes but none before the first row (not as T.4 sends them) is read on bytes, as the renderer draws it, and at `k` 0 may come out as other rows (`pdfcraft_cos::ImageBudget::decode` calls it for a fax image, after the filters before it) | `encode_g4`: Group 4 (`/K -1`) with an end-of-block mark, 0 bits coded black so `/BlackIs1 false` decodes the same bits; rows packed MSB first, each on a new byte, padding bits and trailing bytes ignored; up to 32,767 samples a row (the encoder counts positions in 16 bits); no rows or columns, or too wide → Unsupported, too few bytes → Corrupt |
|
||||
| JBIG2Decode | not in a chain (`Unsupported`); `decode_jbig2_within` decodes it on its own with `hayro-jbig2`, given what its `/JBIG2Globals` decode to, as rows of 1-bit samples each on a new byte, black 0; the page has to be `columns` × `rows` (PdfCraft's renderer draws the whole page into the image), within `max` bytes as such rows and 2^28 pixels (`MAX_JBIG2_PIXELS`, the most the decoder takes), checked before it is decoded; regions inside it are bounded by the decoder alone (a region may claim more pixels than its page); damaged data, or globals that don't decode, are `Corrupt` (`pdfcraft_cos::ImageBudget::decode` calls it for a JBIG2 image, after the filters before it) | `encode_jbig2_generic`: the embedded organisation (D.3) with a page information segment and an immediate lossless generic region (7.4.6), no `/JBIG2Globals`; template 0 with its nominal AT pixels and typical prediction (6.2.5), coded with the MQ arithmetic coder (Annex E, Table E.1) and ended by its 0xFF 0xAC marker. A 0 sample is coded as a JBIG2 1 (black), since `JBIG2Decode` gives black as 0, so the stream decodes to the same bits; rows packed MSB first, each on a new byte, padding bits and trailing bytes ignored; up to 65,535 samples on a side and 2^28 in all, where `hayro-jbig2` stops; no rows or columns, or too large → Unsupported, too few bytes → Corrupt. `encode_jbig2`: the smaller of that and symbol coding (`jbig2/symbols.rs`): each distinct mark (8-connected black pixels, at most 256 a side) stored once in a symbol dictionary (7.4.2; arithmetic coded, each bitmap a template 0 generic region without typical prediction, the bitmaps sharing their contexts) and placed by immediate lossless text regions referring to it (7.4.3; bottom-left reference corner, strips of 1, 2, 4 or 8 rows, whichever is smallest), each of at most 10,000 instances over a band of rows, as the decoder PdfCraft renders with (`hayro-jbig2`) takes no more in one region, with larger marks, and in a second plan marks that occur once, in a generic region over their box. Only exact copies share a symbol (no refinement), so the stream decodes to the same bits; fewer than two symbols, more than 2^20 black runs, 65,536 distinct marks or 16 MiB of their pixels, and the generic coding is used; a plan of more than 32,767 symbols (that decoder refuses more) isn't made. `encode_jbig2_shared`: the marks found in more than one image of a group (at most 16,383, those in the most images first, within the same limits on distinct marks and their pixels as one image's) go once in a symbol dictionary segment associated with no page, number 0, which is the `/JBIG2Globals` data (7.2.6, D.3); each image's stream numbers its segments from 1 (a segment refers only to lower numbers, 7.2.5) and its text regions refer to that dictionary first, then to one of its own for the marks only it repeats, so the shared symbols' IDs come first (Table 31's SBSYMS); the rest is coded as `encode_jbig2`'s symbol coding codes it, the smaller of its two plans. An image that places none of the shared marks gets no stream, to be stored alone; whether the rest save more than the globals take is the caller's to weigh |
|
||||
|
||||
## Tests
|
||||
|
||||
@@ -61,8 +62,8 @@ encode_jbig2(data, columns, rows) -> Result<Vec<u8>, FilterError> // 1-bit row
|
||||
- `ccitt.rs`: `decode_ccitt` gives back the rows `encode_g4` was given (with `/BlackIs1`, `/Rows` and a row limit), refuses bad widths, and bounds its output for any input; byte-aligned Group 3 in each layout, over 32 seeded pictures, decodes to its picture, and a byte short to fewer rows. Group 4 output decoded by `hayro-ccitt` (an independent decoder) matches the input bits: a text-like page, padding bits, the widest row, and property tests over bitmaps of noise and of runs; any input returns rather than panics.
|
||||
- `mq.rs`: the arithmetic coder reproduces Annex H.2's 30 bytes from its 256 decisions.
|
||||
- `jbig2.rs`: output decoded by `hayro-jbig2` (dev-dependency, an independent decoder) matches the input bits: a text-like page (smaller than Group 4), edges, padding, all-white and all-black regions (typical rows), and property tests over bitmaps of noise and of runs; any input returns rather than panics.
|
||||
- `jbig2/decode.rs`: `decode_jbig2` gives back the rows of both codings, padding bits 0; refuses a page of another width or height, past `max` or past `MAX_JBIG2_PIXELS` before decoding it (2^28 pixels take about 34 MB, a bit each), globals that aren't JBIG2 and damaged data, and returns rather than panics on every prefix of a stream.
|
||||
- `jbig2/symbols.rs`: the integer coders against Annex A's example and Table A.1; symbol-coded output decoded by `hayro-jbig2` matches the input bits for every plan and strip size: text whose letters repeat (under half the generic coding's size, the dictionary retained and referred to), large and lone marks left to a generic region, marks on the edges, touching at corners and inside each other's boxes, and property tests over glyphs scattered over each other and the edges with stray pixels (never larger than the generic coding); one shape, a blank page and noise are coded generically; marks joined at a corner, either way, are one mark, and 256 pixels a side is a symbol while 257 wide or tall is left out; black padding bits are ignored; coordinates past 4,435 use Annex A's 32-bit range and PREV stays below 512; past 2^20 runs, 2^24 rows, 65,536 distinct marks or 2^24 symbol pixels the image is coded generically, and at each cap it is still looked at; a plan codes at most 32,767 symbols, which decode, and past that the second plan still codes the repeated ones; more than 10,000 marks are placed by several text regions, numbered in turn, the dictionary retained for each but the last; any input returns rather than panics.
|
||||
- `jbig2/decode.rs`: `decode_jbig2_within` gives back the rows of both codings, padding bits 0; refuses a page of another width or height, past `max` or past `MAX_JBIG2_PIXELS` before decoding it (2^28 pixels take about 34 MB, a bit each), globals that aren't JBIG2 and damaged data, and returns rather than panics on every prefix of a stream.
|
||||
- `jbig2/symbols.rs`: the integer coders against Annex A's example and Table A.1; symbol-coded output decoded by `hayro-jbig2` matches the input bits for every plan and strip size: text whose letters repeat (under half the generic coding's size, the dictionary retained and referred to), large and lone marks left to a generic region, marks on the edges, touching at corners and inside each other's boxes, and property tests over glyphs scattered over each other and the edges with stray pixels (never larger than the generic coding); one shape, a blank page and noise are coded generically; marks joined at a corner, either way, are one mark, and 256 pixels a side is a symbol while 257 wide or tall is left out; black padding bits are ignored; coordinates past 4,435 use Annex A's 32-bit range and PREV stays below 512; past 2^20 runs, 65,536 distinct marks or 2^24 symbol pixels the image is coded generically, and at each cap it is still looked at; a plan codes at most 32,767 symbols, which decode, and past that the second plan still codes the repeated ones; more than 10,000 marks are placed by several text regions, numbered in turn, the dictionary retained for each but the last; pages in one font share one dictionary, segment 0 of no page, retained, which each page's text regions refer to first, taking less together than alone, a page's own repeated marks in a dictionary referred to after it, a page sharing nothing left alone, images with fewer than two marks in common sharing nothing, and past 16,383 shared marks those in the most images kept, with a property test over groups of scattered pages; any input returns rather than panics.
|
||||
- `fuzz/`: a detached cargo-fuzz crate (`cargo +nightly fuzz run decode`, run from `crates/filters/`).
|
||||
|
||||
## Status
|
||||
|
||||
+121
-25
@@ -1,8 +1,9 @@
|
||||
//! JBIG2 encoding (ITU-T T.88 | ISO/IEC 14492), for `JBIG2Decode` (ISO 32000-2 §7.4.7), lossless:
|
||||
//! a generic region, template 0 with its nominal adaptive pixels, typical prediction on, MQ
|
||||
//! arithmetic coding ([`crate::mq`]); or the image's marks as symbols ([`symbols`]). Written from
|
||||
//! the standard's 6.2.5 (coding a generic region), 7.2 (segment headers), 7.4.1, 7.4.6 and 7.4.8
|
||||
//! (the segments) and D.3 (the embedded organisation PDF uses). Decoding is in [`decode`].
|
||||
//! arithmetic coding ([`crate::mq`]); or the image's marks as symbols ([`symbols`]), which a group
|
||||
//! of images may share through `/JBIG2Globals`. Written from the standard's 6.2.5 (coding a generic
|
||||
//! region), 7.2 (segment headers), 7.4.1, 7.4.6 and 7.4.8 (the segments) and D.3 (the embedded
|
||||
//! organisation PDF uses). Decoding is in [`decode`].
|
||||
|
||||
mod decode;
|
||||
mod symbols;
|
||||
@@ -12,9 +13,11 @@ pub use decode::{MAX_JBIG2_PIXELS, decode_jbig2_within};
|
||||
use crate::FilterError;
|
||||
use crate::mq::{Context, MqEncoder};
|
||||
|
||||
/// The widest row [`encode_jbig2_generic`] encodes. JBIG2 allows 32-bit widths; this keeps a
|
||||
/// row's buffers small and its positions in range.
|
||||
pub const MAX_JBIG2_COLUMNS: u32 = 1 << 20;
|
||||
/// The widest row, and the most rows, [`encode_jbig2_generic`] encodes: what `hayro-jbig2`, the
|
||||
/// decoder behind `JBIG2Decode` here, takes on a side. JBIG2 allows 32-bit sizes, but past this
|
||||
/// nothing here could read the stream, and the optimizer, which doesn't read back what it stores,
|
||||
/// replaced such an image with one that draws nothing.
|
||||
pub const MAX_JBIG2_COLUMNS: u32 = 65_535;
|
||||
|
||||
/// Template 0's pixels (Figure 3), as (x, y) offsets from the pixel being coded, each a bit of the
|
||||
/// context in this order: the four on the current row, the five fixed ones on the row above, the
|
||||
@@ -54,9 +57,7 @@ const PAD: usize = 4;
|
||||
/// Errors: as [`encode_jbig2_generic`].
|
||||
pub fn encode_jbig2(data: &[u8], columns: u32, rows: u32) -> Result<Vec<u8>, FilterError> {
|
||||
let generic = encode_jbig2_generic(data, columns, rows)?;
|
||||
// `encode_jbig2_generic` checked that the rows are there.
|
||||
let stride = (columns as usize).div_ceil(8);
|
||||
let samples = usize::try_from(rows).ok().and_then(|r| r.checked_mul(stride)).and_then(|n| data.get(..n));
|
||||
let samples = rows_to_encode(data, columns, rows).ok();
|
||||
Ok(match samples.and_then(|s| symbols::encode(s, columns, rows)) {
|
||||
Some(coded) if coded.len() < generic.len() => coded,
|
||||
_ => generic,
|
||||
@@ -72,18 +73,13 @@ pub fn encode_jbig2(data: &[u8], columns: u32, rows: u32) -> Result<Vec<u8>, Fil
|
||||
/// samples have it. Bytes after the last row are ignored, as are the bits that pad a row to a whole
|
||||
/// byte.
|
||||
///
|
||||
/// Errors: no rows or columns, or rows wider than [`MAX_JBIG2_COLUMNS`]
|
||||
/// ([`FilterError::Unsupported`]); fewer bytes than the rows need ([`FilterError::Corrupt`]).
|
||||
/// Errors: no rows or columns, more of either than [`MAX_JBIG2_COLUMNS`], or more samples than
|
||||
/// [`MAX_JBIG2_PIXELS`], what the decoder takes ([`FilterError::Unsupported`]); fewer bytes than the
|
||||
/// rows need ([`FilterError::Corrupt`]).
|
||||
pub fn encode_jbig2_generic(data: &[u8], columns: u32, rows: u32) -> Result<Vec<u8>, FilterError> {
|
||||
if columns == 0 || rows == 0 || columns > MAX_JBIG2_COLUMNS {
|
||||
return Err(FilterError::Unsupported(format!("JBIG2 encoding of {columns} × {rows} samples")));
|
||||
}
|
||||
let samples = rows_to_encode(data, columns, rows)?;
|
||||
let width = columns as usize;
|
||||
let stride = width.div_ceil(8);
|
||||
let samples = usize::try_from(rows).ok().and_then(|r| r.checked_mul(stride)).and_then(|n| data.get(..n)).ok_or_else(|| FilterError::Corrupt {
|
||||
filter: "JBIG2Decode",
|
||||
detail: format!("{} bytes for {rows} rows of {columns} samples", data.len()),
|
||||
})?;
|
||||
let mut contexts: Vec<Context> = vec![0; 1 << 16];
|
||||
let mut mq = MqEncoder::new();
|
||||
let height = samples.len() / stride;
|
||||
@@ -101,6 +97,48 @@ pub fn encode_jbig2_generic(data: &[u8], columns: u32, rows: u32) -> Result<Vec<
|
||||
Ok(out)
|
||||
}
|
||||
|
||||
/// The samples of `rows` rows of `columns` 1-bit samples in `data`, when the encoders here take
|
||||
/// that size; the errors are [`encode_jbig2_generic`]'s.
|
||||
fn rows_to_encode(data: &[u8], columns: u32, rows: u32) -> Result<&[u8], FilterError> {
|
||||
let too_large = columns > MAX_JBIG2_COLUMNS || rows > MAX_JBIG2_COLUMNS || u64::from(columns) * u64::from(rows) > MAX_JBIG2_PIXELS;
|
||||
if columns == 0 || rows == 0 || too_large {
|
||||
return Err(FilterError::Unsupported(format!("JBIG2 encoding of {columns} × {rows} samples")));
|
||||
}
|
||||
let stride = (columns as usize).div_ceil(8);
|
||||
usize::try_from(rows)
|
||||
.ok()
|
||||
.and_then(|r| r.checked_mul(stride))
|
||||
.and_then(|n| data.get(..n))
|
||||
.ok_or_else(|| FilterError::Corrupt { filter: "JBIG2Decode", detail: format!("{} bytes for {rows} rows of {columns} samples", data.len()) })
|
||||
}
|
||||
|
||||
/// A group of images coded by [`encode_jbig2_shared`]: the data of the `/JBIG2Globals` stream
|
||||
/// they share, and each image's own stream, in the order given, or `None` for one that shares
|
||||
/// nothing with the others.
|
||||
#[derive(Debug)]
|
||||
pub struct SharedJbig2 {
|
||||
pub globals: Vec<u8>,
|
||||
pub images: Vec<Option<Vec<u8>>>,
|
||||
}
|
||||
|
||||
/// Images, each `rows` rows of `columns` 1-bit PDF samples, as lossless JBIG2 sharing one symbol
|
||||
/// dictionary: the marks found in more than one of them are stored once, in a symbol dictionary
|
||||
/// segment not associated with a page, which is the `/JBIG2Globals` stream's data, and each image's
|
||||
/// stream, in the embedded organisation, places them from there, with its other marks coded as
|
||||
/// [`encode_jbig2`]'s symbol coding codes them (see [`symbols`]). With the globals, each decodes to
|
||||
/// its own bits. An image that holds none of those marks, or that symbol coding doesn't take, has
|
||||
/// no stream here; it is stored alone. `None` when the images share fewer than two marks.
|
||||
///
|
||||
/// What each image's stream saves is left for the caller to weigh against what the globals take,
|
||||
/// which the images that use them share.
|
||||
///
|
||||
/// Errors: as [`encode_jbig2_generic`], for the first image it would refuse.
|
||||
pub fn encode_jbig2_shared(images: &[(&[u8], u32, u32)]) -> Result<Option<SharedJbig2>, FilterError> {
|
||||
let images =
|
||||
images.iter().map(|(data, columns, rows)| Ok((rows_to_encode(data, *columns, *rows)?, *columns, *rows))).collect::<Result<Vec<_>, _>>()?;
|
||||
Ok(symbols::encode_shared(&images).map(|(globals, images)| SharedJbig2 { globals, images }))
|
||||
}
|
||||
|
||||
/// A page information segment's data (7.4.8): the page's size, resolution unknown, eventually
|
||||
/// lossless, default pixel 0 (white), OR combination, not striped.
|
||||
fn page_information(columns: u32, rows: u32) -> Vec<u8> {
|
||||
@@ -141,12 +179,18 @@ fn at_pixels(out: &mut Vec<u8>) {
|
||||
}
|
||||
}
|
||||
|
||||
/// A segment (7.2): its header (number, type, the segments it refers to, page 1, data length),
|
||||
/// then its data. `retained`: a later segment refers to this one. `refers_to` holds each
|
||||
/// A segment (7.2) of page 1: its header (number, type, the segments it refers to, the page, data
|
||||
/// length), then its data. `retained`: a later segment refers to this one. `refers_to` holds each
|
||||
/// referred-to segment's number and whether a segment after this one refers to it too (its
|
||||
/// retain bit, 7.2.4). Segment numbers here stay below 256, so each referred-to one takes a byte
|
||||
/// (7.2.5); a segment refers to at most four, so their count and retain bits take one byte too.
|
||||
fn segment(out: &mut Vec<u8>, number: u32, kind: u8, refers_to: &[(u8, bool)], retained: bool, data: &[u8]) {
|
||||
segment_of(out, 1, number, kind, refers_to, retained, data);
|
||||
}
|
||||
|
||||
/// [`segment`], of page `page`: 0 for a segment associated with no page (7.2.6), such as the
|
||||
/// global ones `/JBIG2Globals` holds, which a page's segments may refer to.
|
||||
fn segment_of(out: &mut Vec<u8>, page: u8, number: u32, kind: u8, refers_to: &[(u8, bool)], retained: bool, data: &[u8]) {
|
||||
out.extend_from_slice(&number.to_be_bytes());
|
||||
out.push(kind);
|
||||
// At most four, so the count fits its three bits.
|
||||
@@ -154,8 +198,8 @@ fn segment(out: &mut Vec<u8>, number: u32, kind: u8, refers_to: &[(u8, bool)], r
|
||||
let kept = refers_to.iter().enumerate().fold(0u8, |bits, (k, (_, kept))| bits | u8::from(*kept) << (k + 1));
|
||||
out.push((refers_to.len() as u8) << 5 | kept | u8::from(retained));
|
||||
out.extend(refers_to.iter().map(|(n, _)| *n));
|
||||
out.push(1);
|
||||
// A segment's data never comes near 4 GiB here: a row is at most 1 MiB wide.
|
||||
out.push(page);
|
||||
// A segment's data never comes near 4 GiB here: an image is at most 2^28 samples.
|
||||
out.extend_from_slice(&u32::try_from(data.len()).unwrap_or(u32::MAX).to_be_bytes());
|
||||
out.extend_from_slice(data);
|
||||
}
|
||||
@@ -212,6 +256,11 @@ mod tests {
|
||||
/// The rows an independent decoder (`hayro-jbig2`) reads from `data`, as PDF samples: true
|
||||
/// for white (a JBIG2 0).
|
||||
pub(super) fn decode(data: &[u8]) -> Vec<Vec<bool>> {
|
||||
decode_with(data, None)
|
||||
}
|
||||
|
||||
/// [`decode`], with `/JBIG2Globals`.
|
||||
pub(super) fn decode_with(data: &[u8], globals: Option<&[u8]>) -> Vec<Vec<bool>> {
|
||||
struct Rows(Vec<Vec<bool>>, Vec<bool>, usize);
|
||||
impl hayro_jbig2::Decoder for Rows {
|
||||
fn push_pixel(&mut self, black: bool) {
|
||||
@@ -226,7 +275,7 @@ mod tests {
|
||||
self.0.push(row);
|
||||
}
|
||||
}
|
||||
let image = hayro_jbig2::Image::new_embedded(data, None).unwrap();
|
||||
let image = hayro_jbig2::Image::new_embedded(data, globals).unwrap();
|
||||
let mut rows = Rows(Vec::new(), Vec::new(), image.width() as usize);
|
||||
image.decode(&mut rows).unwrap();
|
||||
rows.0
|
||||
@@ -343,9 +392,56 @@ mod tests {
|
||||
fn what_it_cannot_encode_is_an_error() {
|
||||
assert!(matches!(encode_jbig2_generic(&[0; 8], 0, 1), Err(FilterError::Unsupported(_))));
|
||||
assert!(matches!(encode_jbig2_generic(&[0; 8], 8, 0), Err(FilterError::Unsupported(_))));
|
||||
assert!(matches!(encode_jbig2_generic(&[0; 8], MAX_JBIG2_COLUMNS + 1, 1), Err(FilterError::Unsupported(_))));
|
||||
assert!(matches!(encode_jbig2_generic(&[0; 3], 16, 2), Err(FilterError::Corrupt { .. })), "two rows of 16 need 4 bytes");
|
||||
assert!(matches!(encode_jbig2_generic(&[], 1, u32::MAX), Err(FilterError::Corrupt { .. })));
|
||||
assert!(matches!(encode_jbig2_generic(&[], 1, 2), Err(FilterError::Corrupt { .. })));
|
||||
}
|
||||
|
||||
/// The encoder stops where the decoder does, on each side and in total: past that it would
|
||||
/// write a stream nothing here can read. 16,384 squared is exactly the bound on samples.
|
||||
/// `encode_jbig2_shared` refuses what `encode_jbig2_generic` refuses: an image taller than
|
||||
/// the decoder takes is `Unsupported`, one at the bound isn't refused. (Its one tall mark is
|
||||
/// too large to be a symbol, so nothing is shared: `Ok(None)`.)
|
||||
#[test]
|
||||
fn shared_coding_takes_only_what_the_decoder_takes() {
|
||||
let past = vec![0x7F; MAX_JBIG2_COLUMNS as usize + 1];
|
||||
let tall = (&past[..], 1, MAX_JBIG2_COLUMNS + 1);
|
||||
assert!(matches!(encode_jbig2_shared(&[tall, tall]), Err(FilterError::Unsupported(_))), "too tall");
|
||||
let at = (&past[..MAX_JBIG2_COLUMNS as usize], 1, MAX_JBIG2_COLUMNS);
|
||||
assert!(matches!(encode_jbig2_shared(&[at, at]), Ok(None)), "at the bound");
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn it_encodes_only_what_the_decoder_takes() {
|
||||
let unsupported = |columns, rows| matches!(encode_jbig2_generic(&[], columns, rows), Err(FilterError::Unsupported(_)));
|
||||
assert!(unsupported(MAX_JBIG2_COLUMNS + 1, 1), "too wide");
|
||||
assert!(unsupported(1, MAX_JBIG2_COLUMNS + 1), "too tall");
|
||||
assert!(unsupported(16_385, 16_384), "too many samples, each side within the bound");
|
||||
assert!(unsupported(u32::MAX, u32::MAX), "the product doesn't overflow");
|
||||
// At the bounds what it writes reads back, through the decoder that has to read it.
|
||||
let wide = vec![0x0F; (MAX_JBIG2_COLUMNS as usize).div_ceil(8) * 4];
|
||||
assert_eq!(decode(&encode_jbig2_generic(&wide, MAX_JBIG2_COLUMNS, 4).unwrap()), unpack(&wide, MAX_JBIG2_COLUMNS, 4));
|
||||
let tall = vec![0x7F; MAX_JBIG2_COLUMNS as usize];
|
||||
assert_eq!(decode(&encode_jbig2_generic(&tall, 1, MAX_JBIG2_COLUMNS).unwrap()), unpack(&tall, 1, MAX_JBIG2_COLUMNS));
|
||||
struct Rows(u32, u64);
|
||||
impl hayro_jbig2::Decoder for Rows {
|
||||
fn push_pixel(&mut self, black: bool) {
|
||||
self.1 += u64::from(black);
|
||||
}
|
||||
fn push_pixel_chunk(&mut self, black: bool, chunks: u32) {
|
||||
self.1 += u64::from(black) * u64::from(chunks) * 8;
|
||||
}
|
||||
fn next_line(&mut self) {
|
||||
self.0 += 1;
|
||||
}
|
||||
}
|
||||
// One black pixel, so a page that came back blank wouldn't pass.
|
||||
let mut largest = vec![0xFF; 2_048 * 16_384];
|
||||
largest[0] = 0x7F;
|
||||
let largest = encode_jbig2_generic(&largest, 16_384, 16_384).unwrap();
|
||||
let mut rows = Rows(0, 0);
|
||||
hayro_jbig2::Image::new_embedded(&largest, None).unwrap().decode(&mut rows).unwrap();
|
||||
assert_eq!(rows.0, 16_384);
|
||||
assert_eq!(rows.1, 1);
|
||||
}
|
||||
|
||||
proptest::proptest! {
|
||||
|
||||
@@ -4,7 +4,8 @@ use crate::FilterError;
|
||||
use crate::ccitt::Rows;
|
||||
|
||||
/// 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).
|
||||
/// and takes pages of up to this many (20,000 × 10,000 decodes). It is also the most
|
||||
/// [`encode_jbig2_generic`](crate::encode_jbig2_generic) encodes, so what it stores reads back.
|
||||
pub const MAX_JBIG2_PIXELS: u64 = 1 << 28;
|
||||
|
||||
/// A `JBIG2Decode` stream's `data`, with what its `/JBIG2Globals` stream decodes to, decoded as the
|
||||
@@ -143,6 +144,143 @@ mod tests {
|
||||
assert_eq!(decode_jbig2(&symbols, None, w, h, usize::MAX).unwrap(), marks);
|
||||
}
|
||||
|
||||
/// A region's location is unsigned (ISO/IEC 14492 5.4.4), so one past `i32::MAX` is off the
|
||||
/// page. The decoder took it for a signed one: a region at 0xFFFFFFFC came back onto the page
|
||||
/// four pixels left of it, and a refinement anywhere past `i32::MAX` was refused, and the page
|
||||
/// with it. Each stream is a page of 16 × 12 covered by a generic region, then a region of 8 × 6
|
||||
/// of one kind past `i32::MAX`, coded by the standard's procedures, and decodes to that page
|
||||
/// alone; moved onto the page, the region draws. Vendored hayro-jbig2 patch 14.
|
||||
#[test]
|
||||
fn a_region_located_past_i32_max_is_off_the_page() {
|
||||
const PAGE: &str = "0000000030000100000013000000100000000c00000000000000004200000000000126000100000035000000100000000c0000000000000000040003fffdff02fefefed906aa2cb6ee4ccb4bc975d02669ca7a9c14c20c638f5a5e1bffac";
|
||||
let cases = [
|
||||
// At 0xFFFFFFFC, 1.
|
||||
("generic", "00000002260001000000220000000800000006fffffffc00000001000003fffdff02fefefe17c876ae6f77ffac"),
|
||||
// At 1, 0xFFFFFFFE, with its symbol dictionary.
|
||||
(
|
||||
"text",
|
||||
"000000020000010000001e000003fffdff02fefefe00000001000000014fdda14149cec477ed5fffac00000003062002010000001b000000080000000600000001fffffffe00001000000001a943ffac",
|
||||
),
|
||||
// At 0xFFFFFFFC, 1, with its pattern dictionary.
|
||||
(
|
||||
"halftone",
|
||||
"000000021000010000000a000101000000011fffac00000003162002010000002e0000000800000006fffffffc0000000100000000000800000006000000000000000001000000d09301774485ffac",
|
||||
),
|
||||
// At 0xFFFFFFFC, 1, reading the page there (7.4.7.4): 0s.
|
||||
("refinement of the page", "000000022a00010000001e0000000800000006fffffffc000000010400ffffffff0bd98f188428ffac"),
|
||||
// Of an intermediate region at the same place (7.4.7.5), 1, 0xFFFFFFFE.
|
||||
(
|
||||
"refinement of a region",
|
||||
"0000000224000100000023000000080000000600000001fffffffe000003fffdff02fefefe3d81322da16b7fffac000000032a2002010000001e000000080000000600000001fffffffe0000ffffffffe29946b82229ffac",
|
||||
),
|
||||
// Of an intermediate refinement of an intermediate region, all at 0xFFFFFFFC, 1.
|
||||
(
|
||||
"refinement of a refinement",
|
||||
"00000002240001000000230000000800000006fffffffc00000001000003fffdff02fefefecdfd921ec8c47fffac00000003282002010000001e0000000800000006fffffffc000000010000ffffffff903cdb447a47ffac000000042a2003010000001e0000000800000006fffffffc000000010000ffffffffdcd6078cab86ffac",
|
||||
),
|
||||
];
|
||||
let hex = |text: &str| (0..text.len() / 2).map(|i| u8::from_str_radix(&text[i * 2..i * 2 + 2], 16).unwrap()).collect::<Vec<u8>>();
|
||||
let decode = |segments: &str| decode_jbig2(&[hex(PAGE), hex(segments)].concat(), None, 16, 12, usize::MAX).unwrap();
|
||||
let page = decode("");
|
||||
assert!(page.iter().any(|&byte| byte != 0xFF), "the page has ink");
|
||||
for (kind, segments) in cases {
|
||||
assert_eq!(decode(segments), page, "{kind}");
|
||||
// Moved onto the page, to 4, 1 or 1, 2, the same regions draw: they decode, and are
|
||||
// left out for where they are.
|
||||
let (off, on) = [("fffffffc00000001", "0000000400000001"), ("00000001fffffffe", "0000000100000002")]
|
||||
.into_iter()
|
||||
.find(|(off, _)| segments.contains(off))
|
||||
.unwrap();
|
||||
assert_ne!(decode(&segments.replace(off, on)), page, "{kind} on the page");
|
||||
}
|
||||
|
||||
// A refinement at 2, 0 of an intermediate region at 0x80000000, 0. A refinement of a
|
||||
// region refines it where it is, "GRREFERENCEDX 0, GRREFERENCEDY 0" (Table 35), and the two
|
||||
// should be at one place (7.4.7.5). Where they aren't, it decodes as it does where they are.
|
||||
const ELSEWHERE: &str = "000000022400010000002300000008000000068000000000000000000003fffdff02fefefe1bca3149568cdfffac000000032a2002010000001e000000080000000600000002000000000000ffffffff784a909cc761ffac";
|
||||
let refined = decode(ELSEWHERE);
|
||||
assert_eq!(refined, decode(&ELSEWHERE.replace("8000000000000000", "0000000200000000")), "the region at 2, 0 too");
|
||||
assert_ne!(refined, page, "drawn");
|
||||
}
|
||||
|
||||
/// A refinement of the page refines "the current contents of the page buffer, restricted to the
|
||||
/// area of the page buffer specified by this segment's region segment information field"
|
||||
/// (ISO/IEC 14492 7.4.7.4), at an offset of 0 (Table 35), and reads 0 outside that area
|
||||
/// (6.3.5.2). The decoder read the page around the area too, and refused a refinement wider or
|
||||
/// taller than the page. A refinement of another region refines that region, not the page. And
|
||||
/// a reference 32 or more left of a refinement (GRREFERENCEDX below −31, as a symbol refined
|
||||
/// with an RDX below −31 has, Table 18) is read from where each row starts in it: each row's
|
||||
/// first context read 0 for the reference column it starts at, and from 33 left for the one
|
||||
/// before it too. Each stream is coded by the standard's procedures and decodes to its
|
||||
/// picture, `#` for black. Vendored hayro-jbig2 patch 16.
|
||||
#[test]
|
||||
fn a_refinement_refines_the_page_in_its_area_and_any_reference_where_it_is() {
|
||||
let cases: [(&str, &str, &[&str]); 5] = [
|
||||
(
|
||||
"a 48 × 6 page a generic region has inked, refined at 33: ink on both sides of the area, template 0",
|
||||
"000000003000010000001300000030000000060000000000000000420000000000012600010000004100000030000000060000000000000000040003fffdff02fefefe331433558a5c5056cf412003ec9a38164df39bd4463b9331502c4fb1c267ab77b665aa5962ffac000000022a0001000000210000000c0000000600000021000000000400ffffffff9a6c35bbeee221f687ffac",
|
||||
&[
|
||||
".#..##.######..#.#..#####.##..#........##.##..##",
|
||||
".#..####.####.#...###.##.##.#.#.....#.#.####.###",
|
||||
"##.#......#..#....#..#.###.#..#.#####.###.######",
|
||||
"......#....###.#.##..#.##........#.#.#...#####..",
|
||||
"#.##..###.#.#.##.....#...#.#..#.##.#..#...#...#.",
|
||||
".###...#..#..#..##..#.#..#####.#.##.......###.##",
|
||||
],
|
||||
),
|
||||
(
|
||||
"a 24 × 8 inked page refined at 5, 1, template 1",
|
||||
"000000003000010000001300000018000000080000000000000000420000000000012600010000003500000018000000080000000000000000040003fffdff02fefefeb1e133cb8bcbb8510e81d219bb880dfb40a311dc5c298819efffac000000022a00010000001b0000000a0000000500000005000000010401e55c0078dcd30fffac",
|
||||
&[
|
||||
"#.##.##...##....##.##..#",
|
||||
"#.##.##...#.####..##..#.",
|
||||
"##..##.##...#...###..#.#",
|
||||
".....#.#.##.#...###....#",
|
||||
"..#.#...#.#...#.#...##.#",
|
||||
"....######...#.####....#",
|
||||
"..######..##.#.#..##.#..",
|
||||
"...#..##.####.#..##...#.",
|
||||
],
|
||||
),
|
||||
(
|
||||
"a 16 × 5 inked page refined by a region 4 wider than it, template 0",
|
||||
"000000003000010000001300000010000000050000000000000000420000000000012600010000002600000010000000050000000000000000040003fffdff02fefefe22e5e253a429cbf2c701ffac000000022a000100000023000000140000000500000000000000000400ffffffff3afa516532bbe3d481926fffac",
|
||||
&[".#.#.#.#..#.#.#.", "##.####..###...#", "..####.#..####.#", ".###.#.....#..#.", "#.###..#########"],
|
||||
),
|
||||
(
|
||||
"an intermediate region at 4, 1 on an inked 20 × 8 page, refined there (OR): the region, not the page, template 0",
|
||||
"000000003000010000001300000014000000080000000000000000420000000000012600010000003000000014000000080000000000000000040003fffdff02fefefeb91e434e1726ca89ed06c2bffb0fe5fa7fccc80fffac00000002240001000000230000000a000000050000000400000001000003fffdff02fefefece7a9826ba81bfffac000000032a2002010000001e0000000a0000000500000004000000010000ffffffffd046ee6f6190ffac",
|
||||
&[
|
||||
"#.#.#....#.#...#....",
|
||||
"##..#.#.#.##.....##.",
|
||||
"##.#.#.#.#.###.##...",
|
||||
"###.##.####..###.#.#",
|
||||
"...#.###..###.#.#..#",
|
||||
"#...#######.#...####",
|
||||
"..##.##...#..##..#.#",
|
||||
"#...##...#.##....#..",
|
||||
],
|
||||
),
|
||||
(
|
||||
"a symbol refined in a symbol dictionary from a 40 × 6 one, RDX −33: 33 left, template 1",
|
||||
"0000000030000100000013000000070000000600000000000000004200000000000100000100000036000003fffdff02fefefe00000001000000014f913296209e2187f37bddb8589c8beb7d70109de7124ebe47d04914ef7e655c3c4cffac00000002002001010000001f100203fffdff02fefefe00000001000000014fe451a27bddf49f7ef7e7ffac00000003062002010000001b0000000700000006000000000000000004001000000001a943ffac",
|
||||
&[".####.#", ".##..##", "......#", "...#..#", "#.#.###", "....##."],
|
||||
),
|
||||
];
|
||||
let hex = |text: &str| (0..text.len() / 2).map(|i| u8::from_str_radix(&text[i * 2..i * 2 + 2], 16).unwrap()).collect::<Vec<u8>>();
|
||||
for (form, stream, picture) in cases {
|
||||
let (w, h) = (picture[0].len(), picture.len());
|
||||
// As the filter gives it: black as 0, each row padded to a byte with 0s.
|
||||
let mut rows = vec![0u8; w.div_ceil(8) * h];
|
||||
for (y, row) in picture.iter().enumerate() {
|
||||
for (x, _) in row.bytes().enumerate().filter(|(_, c)| *c == b'.') {
|
||||
rows[y * w.div_ceil(8) + x / 8] |= 0x80 >> (x % 8);
|
||||
}
|
||||
}
|
||||
assert_eq!(decode_jbig2(&hex(stream), None, w as u32, h as u32, usize::MAX).unwrap(), rows, "{form}");
|
||||
}
|
||||
}
|
||||
|
||||
/// 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.
|
||||
@@ -182,6 +320,57 @@ mod tests {
|
||||
assert_eq!(u64::MAX - work, 4 * 14);
|
||||
}
|
||||
|
||||
/// A refinement whose reference is offset right of it (GRREFERENCEDX above 0, as a refined text
|
||||
/// instance has from a wider bitmap, ISO/IEC 14492 Table 12, and a refined symbol from an RDX
|
||||
/// above 0, Table 18) reads the reference from its first column. Left of the reference the
|
||||
/// decoder emptied what it had read of it, and at its first column didn't read it again, so its
|
||||
/// first 32 columns read as 0: such a refinement decoded to other pixels than were coded, or
|
||||
/// failed. Each stream is a refinement coded by the standard's procedures on a page of its own
|
||||
/// size, and decodes to its picture, `#` for black. Vendored hayro-jbig2 patch 15.
|
||||
#[test]
|
||||
fn a_refinement_reads_a_reference_right_of_it_from_its_first_column() {
|
||||
let cases: [(&str, &str, &[&str]); 4] = [
|
||||
(
|
||||
"a text instance of an 8 × 6 symbol refined 6 wider: 3 right, template 0",
|
||||
"00000000300001000000130000000e000000060000000000000000420000000000010000010000001d000003fffdff02fefefe00000001000000014fdd3dba48bdddde35ffac00000002062001010000002c0000000e000000060000000000000000040012ffffffff00000001a96b4a6b78b7fc094fadde1b3e881fffac",
|
||||
&[".#.#.#....#...", "##.###....##.#", ".###...###..#.", "#.......#...#.", "#.####.#...#..", "#.##...###.#.."],
|
||||
),
|
||||
(
|
||||
"refined 2 wider and 2 taller, RDX and RDY 1: 2 right, 2 down, template 1",
|
||||
"00000000300001000000130000000a000000080000000000000000420000000000010000010000001d000003fffdff02fefefe00000001000000014fdd9c52d3ea827a43ffac0000000206200101000000280000000a00000008000000000000000004801200000001a96c00cdac6dd5f6f848ce872411cfffac",
|
||||
&["####.##...", "####..####", "####..##..", "...##...#.", "#......#..", "..#.....#.", "##....####", ".#........"],
|
||||
),
|
||||
(
|
||||
"a symbol refined in a symbol dictionary, RDX 5, RDY −1, template 0 with its AT pixels moved",
|
||||
"00000000300001000000130000000c000000060000000000000000420000000000010000010000001e000003fffdff02fefefe00000001000000014fdda13efc4029efc95fffac000000020020010100000027000203fffdff02fefefefeff010100000001000000014fc98c352dd84a906f120ffb49793fffac00000003062002010000001b0000000c00000006000000000000000004001000000001a943ffac",
|
||||
&["#.#.##.#.###", "..#.#.....##", "##..#...#...", "..##....##..", "##.#.##.####", ".#..#####..#"],
|
||||
),
|
||||
(
|
||||
"a text instance of a 40 × 5 symbol refined 2 wider, RDX 1: 2 right, across a word, template 0",
|
||||
"00000000300001000000130000002a0000000500000000000000004200000000000100000100000031000003fffdff02fefefe00000001000000015240f590d953ae3f4069dede672090d4d61b377906d3f41aafa4f77107ffac00000002062001010000003c0000002a000000050000000000000000040012ffffffff00000001a96c0b9386d4b140486bdc3673dbd031490e468c7f7813d19068ab04a79cbfffac",
|
||||
&[
|
||||
"##.#.#..##.##.#####.#....#.#.#..#..######.",
|
||||
".#.#..###....#..##.#..#.####.#..#.###...##",
|
||||
".#.#......#....#####....#...###...#####...",
|
||||
"#...##.##.......#...###.###...##..##.###.#",
|
||||
"..#..###..###..#...#.......##.#........##.",
|
||||
],
|
||||
),
|
||||
];
|
||||
let hex = |text: &str| (0..text.len() / 2).map(|i| u8::from_str_radix(&text[i * 2..i * 2 + 2], 16).unwrap()).collect::<Vec<u8>>();
|
||||
for (form, stream, picture) in cases {
|
||||
let (w, h) = (picture[0].len(), picture.len());
|
||||
// As the filter gives it: black as 0, each row padded to a byte with 0s.
|
||||
let mut rows = vec![0u8; w.div_ceil(8) * h];
|
||||
for (y, row) in picture.iter().enumerate() {
|
||||
for (x, _) in row.bytes().enumerate().filter(|(_, c)| *c == b'.') {
|
||||
rows[y * w.div_ceil(8) + x / 8] |= 0x80 >> (x % 8);
|
||||
}
|
||||
}
|
||||
assert_eq!(decode_jbig2(&hex(stream), None, w as u32, h as u32, usize::MAX).unwrap(), rows, "{form}");
|
||||
}
|
||||
}
|
||||
|
||||
/// 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
|
||||
@@ -213,4 +402,87 @@ mod tests {
|
||||
let _ = decode_jbig2(&data[..end], None, w, h, usize::MAX);
|
||||
}
|
||||
}
|
||||
|
||||
/// Pixels past a bitmap's edge are 0 (ISO/IEC 14492 6.3.5.2). A page whose default pixel is 1,
|
||||
/// and an intermediate text or halftone region whose default pixel is 1, kept 1s past their
|
||||
/// width in their last word of each row, and a refinement, which reads its reference a word at
|
||||
/// a time, read them as pixels: of rows not a multiple of 32 wide, it decoded to other pixels
|
||||
/// than were coded. Each stream is a refinement coded by the standard's procedures from a
|
||||
/// reference read as 0 past its edge, and decodes to the picture given, `#` for black.
|
||||
/// Vendored hayro-jbig2 patch 13.
|
||||
#[test]
|
||||
fn a_refinement_reads_nothing_past_its_references_width() {
|
||||
// A page of 7 × 6, then of 33 × 6, whose default pixel is 1, refined whole.
|
||||
const PAGE_7: &str = "000000003000010000001300000007000000060000000000000000460000000000012a00010000001e000000070000000600000000000000000400ffffffffe42d7e889ebcffac";
|
||||
const PAGE_33: &str = "000000003000010000001300000021000000060000000000000000460000000000012a000100000034000000210000000600000000000000000400ffffffff314a8d598037eb3f915ab3d526ccae915ad6a6a7b814111b124ae60fffac";
|
||||
// An intermediate text region of 31 × 6 whose default pixel is 1, then one of 7 × 6 on a
|
||||
// page of 40, each refined into the page.
|
||||
const TEXT_31: &str = "00000000300001000000130000001f0000000600000000000000004200000000000100000100000030000003fffdff02fefefe00000001000000014f96dceb76c7f1ff585971969cd9f88e538261a6f713be68d77e8e1fffac00000002042001010000001b0000001f00000006000000000000000000029000000001a943ffac000000032a2002010000002f0000001f0000000600000000000000000400ffffffff9ac311688adbc8f570a2f96aef93d332e3b1f4b27b704bffac";
|
||||
const TEXT_7: &str = "000000003000010000001300000028000000060000000000000000420000000000010000010000001d000003fffdff02fefefe00000001000000014fe1f79f4a95c5b77fffac00000002042001010000001b0000000700000006000000000000000000029000000001a943ffac000000032a2002010000001e000000070000000600000000000000000400ffffffffa71dae12bd7fffac";
|
||||
// An intermediate halftone region of 33 × 6 whose default pixel is 1, refined into the page.
|
||||
const HALFTONE_33: &str = "000000003000010000001300000021000000060000000000000000420000000000011000010000000a000101000000011fffac00000002142001010000004100000021000000060000000000000000009000000021000000060000000000000000010000004ea6618f551d48ff24c2c5c98124d449f2adea6fca76e4297fffac000000032a20020100000032000000210000000600000000000000000400ffffffffe87db809393a3251e565e7a749e6470ab37f7aef186ceaf5167bffac";
|
||||
let cases: [(&str, &str, [&str; 6]); 5] = [
|
||||
("page 7", PAGE_7, ["###.#.#", ".......", "#.####.", "######.", "#.#...#", ".#...##"]),
|
||||
(
|
||||
"page 33",
|
||||
PAGE_33,
|
||||
[
|
||||
".#..##........###..####....#.##.#",
|
||||
".#.###.###.##.##..#..#...#.....##",
|
||||
".....##..#....#.##.######.###..#.",
|
||||
"##...#..##.###..###.##..#.#.#.#.#",
|
||||
".##.#........##.#.#.....###......",
|
||||
"...#.#####.#..#.###......###..###",
|
||||
],
|
||||
),
|
||||
(
|
||||
"text 31",
|
||||
TEXT_31,
|
||||
[
|
||||
"....##....###......#.##.#.#....",
|
||||
".#.....##.......##..###.#...#..",
|
||||
".#.#.#.####...#####.####...#.#.",
|
||||
"......#...#...#.##...##...#..#.",
|
||||
".#..##.###.#.###..####...#...#.",
|
||||
"#...#...#..#.#....#.##.#.....#.",
|
||||
],
|
||||
),
|
||||
(
|
||||
"text 7 on a page of 40",
|
||||
TEXT_7,
|
||||
[
|
||||
"......#.................................",
|
||||
".....##.................................",
|
||||
"##...##.................................",
|
||||
"..#.....................................",
|
||||
"##......................................",
|
||||
"..#.....................................",
|
||||
],
|
||||
),
|
||||
(
|
||||
"halftone 33",
|
||||
HALFTONE_33,
|
||||
[
|
||||
"##...#.###.#.###.....#.####..####",
|
||||
"##.##.#...#.##.##.##.#...#.#.###.",
|
||||
"###..#.#....##.###...#..##.##..##",
|
||||
"##..#...###...##..#.####.###.#...",
|
||||
"####.###.###.#..#..#.#.####...###",
|
||||
"#.#..#........#....#.#.##.##..#.#",
|
||||
],
|
||||
),
|
||||
];
|
||||
let hex = |text: &str| (0..text.len() / 2).map(|i| u8::from_str_radix(&text[i * 2..i * 2 + 2], 16).unwrap()).collect::<Vec<u8>>();
|
||||
for (form, stream, picture) in cases {
|
||||
let w = picture[0].len();
|
||||
// As the filter gives it: black as 0, each row padded to a byte with 0s.
|
||||
let mut rows = vec![0u8; w.div_ceil(8) * picture.len()];
|
||||
for (y, row) in picture.iter().enumerate() {
|
||||
for (x, _) in row.bytes().enumerate().filter(|(_, c)| *c == b'.') {
|
||||
rows[y * w.div_ceil(8) + x / 8] |= 0x80 >> (x % 8);
|
||||
}
|
||||
}
|
||||
assert_eq!(decode_jbig2(&hex(stream), None, w as u32, 6, usize::MAX).unwrap(), rows, "{form}");
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
@@ -11,7 +11,7 @@ use std::collections::HashMap;
|
||||
use std::hash::{DefaultHasher, Hash, Hasher};
|
||||
use std::ops::Range;
|
||||
|
||||
use super::{at_pixels, code_generic, generic_region, page_information, region_information, segment};
|
||||
use super::{at_pixels, code_generic, generic_region, page_information, region_information, segment, segment_of};
|
||||
use crate::mq::{Context, MqEncoder};
|
||||
|
||||
/// The longest side of a mark stored as a symbol. A larger one is left to the generic region.
|
||||
@@ -27,7 +27,9 @@ const MAX_SYMBOLS: usize = 1 << 16;
|
||||
const MAX_SYMBOL_PIXELS: usize = 1 << 24;
|
||||
|
||||
/// The most symbols one plan codes. The decoder PdfCraft renders JBIG2 with (`hayro-jbig2`)
|
||||
/// refuses 32,768 symbols or more, and others may too, so a plan with more isn't made.
|
||||
/// refuses a dictionary whose new and exported symbols pass 65,535 together, and a plan exports
|
||||
/// every symbol it codes, so it refuses 32,768 or more; others may too, so a plan with more isn't
|
||||
/// made.
|
||||
const MAX_CODED_SYMBOLS: usize = (1 << 15) - 1;
|
||||
|
||||
/// The most symbol instances one text region places. The decoder PdfCraft renders JBIG2 with
|
||||
@@ -35,14 +37,14 @@ const MAX_CODED_SYMBOLS: usize = (1 << 15) - 1;
|
||||
/// placed by several regions, each over a band of rows, all referring to the one dictionary.
|
||||
const MAX_REGION_INSTANCES: usize = 10_000;
|
||||
|
||||
// Segment numbers stay at most 256, so a referred-to one takes a byte (7.2.5): the page, the
|
||||
// dictionary, a text region for each MAX_REGION_INSTANCES of at most MAX_RUNS marks, and the
|
||||
// generic region.
|
||||
const _: () = assert!(MAX_RUNS.div_ceil(MAX_REGION_INSTANCES) + 3 <= 256);
|
||||
/// The most symbols a group's shared dictionary holds ([`encode_shared`]): half of what a page may
|
||||
/// place, so each page keeps room for its own.
|
||||
const MAX_SHARED_SYMBOLS: usize = MAX_CODED_SYMBOLS / 2;
|
||||
|
||||
/// The most rows symbol coded. With rows at most 2^20 samples wide, every coordinate and
|
||||
/// difference coded then fits the 32-bit integers Annex A codes.
|
||||
const MAX_ROWS: u32 = 1 << 24;
|
||||
// Segment numbers stay at most 256, so a referred-to one takes a byte (7.2.5): the shared
|
||||
// dictionary, the page, its own dictionary, a text region for each MAX_REGION_INSTANCES of at most
|
||||
// MAX_RUNS marks, and the generic region.
|
||||
const _: () = assert!(MAX_RUNS.div_ceil(MAX_REGION_INSTANCES) + 4 <= 256);
|
||||
|
||||
/// The integer coders' ranges (Table A.1): how many 1 bits pick the range, how many bits give the
|
||||
/// offset into it, and its first value. The last range has no 0 after its prefix.
|
||||
@@ -99,20 +101,111 @@ struct Instance {
|
||||
height: u32,
|
||||
}
|
||||
|
||||
/// A group of images coded by [`encode_shared`]: the globals' data, and each image's stream.
|
||||
type SharedCoding = (Vec<u8>, Vec<Option<Vec<u8>>>);
|
||||
|
||||
/// The symbols of a group's shared dictionary, as one image's [`plan`] places them: the ID each of
|
||||
/// the image's symbols has there, if it is there, and how many symbols that dictionary exports.
|
||||
struct Shared {
|
||||
ids: Vec<Option<u32>>,
|
||||
count: u32,
|
||||
}
|
||||
|
||||
/// `rows` rows of `columns` 1-bit PDF samples (black 0), symbol coded: the smaller of two plans,
|
||||
/// every mark of at most [`MAX_SYMBOL_SIDE`] a side as a symbol, or only those with a copy.
|
||||
/// `None` when neither plan has from two to [`MAX_CODED_SYMBOLS`] symbols, or the image is too
|
||||
/// large or too busy to look at.
|
||||
pub(super) fn encode(samples: &[u8], columns: u32, rows: u32) -> Option<Vec<u8>> {
|
||||
let page = page(samples, columns, rows)?;
|
||||
[1, 2].into_iter().filter_map(|copies| plan(&page, columns, rows, copies, None)).min_by_key(Vec::len)
|
||||
let page = page(samples, columns)?;
|
||||
[1, 2].into_iter().filter_map(|copies| plan(&page, columns, rows, copies, None, None)).min_by_key(Vec::len)
|
||||
}
|
||||
|
||||
/// Images, each as [`encode`] takes one, symbol coded sharing one dictionary: the globals' data, a
|
||||
/// symbol dictionary segment associated with no page (number 0) holding the distinct marks found
|
||||
/// in more than one image, and each image's stream placing them from there, the smaller of
|
||||
/// [`encode`]'s two plans for its other marks. The group's marks are held within the limits one
|
||||
/// image's are ([`MAX_SYMBOLS`], [`MAX_SYMBOL_PIXELS`]): past them, later marks aren't shared. Past
|
||||
/// [`MAX_SHARED_SYMBOLS`] shared marks, those in the most images are kept.
|
||||
///
|
||||
/// An image too large or too busy to look at, or that places none of the shared marks, gets `None`;
|
||||
/// `None` overall when fewer than two marks are shared.
|
||||
pub(super) fn encode_shared(images: &[(&[u8], u32, u32)]) -> Option<SharedCoding> {
|
||||
// The group's distinct marks, each with how many images hold it (as its uses), looked at an
|
||||
// image at a time.
|
||||
let mut table: Vec<Symbol> = Vec::new();
|
||||
let mut by_hash: HashMap<u64, Vec<u32>> = HashMap::new();
|
||||
let mut held = 0usize;
|
||||
for (samples, columns, _) in images {
|
||||
let Some(page) = page(samples, *columns) else { continue };
|
||||
// An image's symbols are distinct, so each counts an image once.
|
||||
for symbol in page.symbols {
|
||||
match find(&table, &by_hash, &symbol) {
|
||||
Some(t) => {
|
||||
if let Some(s) = table.get_mut(t as usize) {
|
||||
s.uses = s.uses.saturating_add(1);
|
||||
}
|
||||
}
|
||||
None => {
|
||||
let Some(more) = held.checked_add(symbol.pixels.len()).filter(|h| *h <= MAX_SYMBOL_PIXELS && table.len() < MAX_SYMBOLS) else {
|
||||
continue;
|
||||
};
|
||||
held = more;
|
||||
let t = u32::try_from(table.len()).ok()?;
|
||||
by_hash.entry(fingerprint(&symbol)).or_default().push(t);
|
||||
table.push(Symbol { uses: 1, ..symbol });
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
let uses = |t: &u32| table.get(*t as usize).map_or(0, |s| s.uses);
|
||||
let mut shared: Vec<u32> = (0..u32::try_from(table.len()).ok()?).filter(|t| uses(t) >= 2).collect();
|
||||
if shared.len() < 2 {
|
||||
return None;
|
||||
}
|
||||
shared.sort_by_key(|t| std::cmp::Reverse(uses(t)));
|
||||
shared.truncate(MAX_SHARED_SYMBOLS);
|
||||
// The dictionary's order, as `plan` keeps it.
|
||||
shared.sort_by_key(|t| table.get(*t as usize).map(|s| (s.height, s.width)));
|
||||
let mut global = vec![None; table.len()];
|
||||
for (k, t) in shared.iter().enumerate() {
|
||||
if let Some(slot) = global.get_mut(*t as usize) {
|
||||
*slot = u32::try_from(k).ok();
|
||||
}
|
||||
}
|
||||
let symbols: Vec<&Symbol> = shared.iter().filter_map(|t| table.get(*t as usize)).collect();
|
||||
let mut globals = Vec::new();
|
||||
segment_of(&mut globals, 0, 0, 0, &[], true, &symbol_dictionary(&symbols)?);
|
||||
let count = u32::try_from(symbols.len()).ok()?;
|
||||
let streams = images
|
||||
.iter()
|
||||
.map(|(samples, columns, rows)| {
|
||||
let page = page(samples, *columns)?;
|
||||
let ids = page.symbols.iter().map(|s| find(&table, &by_hash, s).and_then(|t| global.get(t as usize).copied().flatten())).collect();
|
||||
let shared = Shared { ids, count };
|
||||
[1, 2].into_iter().filter_map(|copies| plan(&page, *columns, *rows, copies, None, Some(&shared))).min_by_key(Vec::len)
|
||||
})
|
||||
.collect();
|
||||
Some((globals, streams))
|
||||
}
|
||||
|
||||
/// What sorts a symbol's bitmap ([`symbols`] and [`encode_shared`] look exact copies up by it).
|
||||
fn fingerprint(s: &Symbol) -> u64 {
|
||||
let mut hasher = DefaultHasher::new();
|
||||
(s.width, s.height, &s.pixels).hash(&mut hasher);
|
||||
hasher.finish()
|
||||
}
|
||||
|
||||
/// The index in `table` of the symbol with `s`'s bitmap, looked up by its [`fingerprint`].
|
||||
fn find(table: &[Symbol], by_hash: &HashMap<u64, Vec<u32>>, s: &Symbol) -> Option<u32> {
|
||||
by_hash
|
||||
.get(&fingerprint(s))?
|
||||
.iter()
|
||||
.copied()
|
||||
.find(|t| table.get(*t as usize).is_some_and(|t| (t.width, t.height) == (s.width, s.height) && t.pixels == s.pixels))
|
||||
}
|
||||
|
||||
/// The image's marks and symbols; `None` past the limits above.
|
||||
fn page(samples: &[u8], columns: u32, rows: u32) -> Option<Page> {
|
||||
if rows > MAX_ROWS {
|
||||
return None;
|
||||
}
|
||||
fn page(samples: &[u8], columns: u32) -> Option<Page> {
|
||||
let width = usize::try_from(columns).ok()?;
|
||||
let stride = width.div_ceil(8);
|
||||
if stride == 0 {
|
||||
@@ -272,23 +365,18 @@ fn symbols(page: &mut Page) -> Option<()> {
|
||||
page.large.push(m);
|
||||
continue;
|
||||
}
|
||||
let pixels = pixels(mark, &page.runs, &page.order);
|
||||
let mut hasher = DefaultHasher::new();
|
||||
(width, height, &pixels).hash(&mut hasher);
|
||||
let same = by_hash.entry(hasher.finish()).or_default();
|
||||
let symbol = Symbol { width, height, pixels: pixels(mark, &page.runs, &page.order), uses: 0 };
|
||||
let symbols = &mut page.symbols;
|
||||
let known =
|
||||
same.iter().copied().find(|s| symbols.get(*s as usize).is_some_and(|s| (s.width, s.height) == (width, height) && s.pixels == pixels));
|
||||
let id = match known {
|
||||
let id = match find(symbols, &by_hash, &symbol) {
|
||||
Some(id) => id,
|
||||
None => {
|
||||
kept = kept.checked_add(pixels.len())?;
|
||||
kept = kept.checked_add(symbol.pixels.len())?;
|
||||
if kept > MAX_SYMBOL_PIXELS || symbols.len() == MAX_SYMBOLS {
|
||||
return None;
|
||||
}
|
||||
let id = u32::try_from(symbols.len()).ok()?;
|
||||
symbols.push(Symbol { width, height, pixels, uses: 0 });
|
||||
same.push(id);
|
||||
by_hash.entry(fingerprint(&symbol)).or_default().push(id);
|
||||
symbols.push(symbol);
|
||||
id
|
||||
}
|
||||
};
|
||||
@@ -305,18 +393,28 @@ fn symbols(page: &mut Page) -> Option<()> {
|
||||
/// the other marks in a generic region. `None` with fewer than two such symbols (their IDs would
|
||||
/// take no bits at all, SBSYMCODELEN 0, a corner of the standard left alone here) or more than
|
||||
/// [`MAX_CODED_SYMBOLS`].
|
||||
fn plan(page: &Page, columns: u32, rows: u32, copies: u32, log_strips: Option<u32>) -> Option<Vec<u8>> {
|
||||
///
|
||||
/// With `shared`, the symbols a group's dictionary holds are placed from there, whatever their uses
|
||||
/// here, and the page's own dictionary holds only the others (none, when it has none), as
|
||||
/// [`encode_shared`] writes them; `None` too for a page that places none of the shared ones.
|
||||
fn plan(page: &Page, columns: u32, rows: u32, copies: u32, log_strips: Option<u32>, shared: Option<&Shared>) -> Option<Vec<u8>> {
|
||||
let symbol = |s: u32| page.symbols.get(s as usize);
|
||||
let global = |s: u32| shared.and_then(|g| g.ids.get(s as usize).copied().flatten());
|
||||
let globals = shared.map_or(0, |g| g.count);
|
||||
// The dictionary's order (6.5.5): height classes from the shortest, each narrowest first.
|
||||
let mut kept: Vec<u32> = (0..page.symbols.len() as u32).filter(|s| symbol(*s).is_some_and(|s| s.uses >= copies)).collect();
|
||||
if kept.len() < 2 || kept.len() > MAX_CODED_SYMBOLS {
|
||||
let mut kept: Vec<u32> =
|
||||
(0..page.symbols.len() as u32).filter(|s| global(*s).is_none() && symbol(*s).is_some_and(|s| s.uses >= copies)).collect();
|
||||
let count = usize::try_from(globals).ok()?.checked_add(kept.len())?;
|
||||
if !(2..=MAX_CODED_SYMBOLS).contains(&count) {
|
||||
return None;
|
||||
}
|
||||
kept.sort_by_key(|s| symbol(*s).map(|s| (s.height, s.width)));
|
||||
let mut id = vec![None; page.symbols.len()];
|
||||
// The shared symbols' IDs come first, as their dictionary is referred to first (Table 31's
|
||||
// SBSYMS).
|
||||
let mut id: Vec<Option<u32>> = (0..page.symbols.len() as u32).map(global).collect();
|
||||
for (k, s) in kept.iter().enumerate() {
|
||||
if let Some(slot) = id.get_mut(*s as usize) {
|
||||
*slot = u32::try_from(k).ok();
|
||||
*slot = u32::try_from(k).ok().and_then(|k| k.checked_add(globals));
|
||||
}
|
||||
}
|
||||
let mut instances = Vec::new();
|
||||
@@ -329,9 +427,12 @@ fn plan(page: &Page, columns: u32, rows: u32, copies: u32, log_strips: Option<u3
|
||||
_ => left.push(*m),
|
||||
}
|
||||
}
|
||||
if shared.is_some() && !instances.iter().any(|i| i.id < globals) {
|
||||
return None;
|
||||
}
|
||||
let kept: Vec<&Symbol> = kept.iter().filter_map(|s| symbol(*s)).collect();
|
||||
let dictionary = symbol_dictionary(&kept)?;
|
||||
let count = u32::try_from(kept.len()).ok()?;
|
||||
let dictionary = if kept.is_empty() { None } else { Some(symbol_dictionary(&kept)?) };
|
||||
let count = u32::try_from(count).ok()?;
|
||||
// Bands of at most MAX_REGION_INSTANCES, from the top.
|
||||
instances.sort_by_key(|i| (i.t, i.s));
|
||||
let mut regions = Vec::new();
|
||||
@@ -344,12 +445,21 @@ fn plan(page: &Page, columns: u32, rows: u32, copies: u32, log_strips: Option<u3
|
||||
});
|
||||
}
|
||||
let mut out = Vec::new();
|
||||
segment(&mut out, 0, 48, &[], false, &page_information(columns, rows));
|
||||
segment(&mut out, 1, 0, &[], true, &dictionary);
|
||||
let mut number = 2;
|
||||
// The shared dictionary is segment 0, in the globals, and a segment refers only to lower
|
||||
// numbers (7.2.5): the page's own follow it.
|
||||
let mut number = u32::from(shared.is_some());
|
||||
segment(&mut out, number, 48, &[], false, &page_information(columns, rows));
|
||||
number += 1;
|
||||
let mut dictionaries: Vec<u8> = shared.map(|_| 0).into_iter().collect();
|
||||
if let Some(dictionary) = &dictionary {
|
||||
segment(&mut out, number, 0, &[], true, dictionary);
|
||||
dictionaries.push(u8::try_from(number).ok()?);
|
||||
number += 1;
|
||||
}
|
||||
for (k, text) in regions.iter().enumerate() {
|
||||
// The dictionary stays retained for the next region, until the last (7.2.4).
|
||||
segment(&mut out, number, 7, &[(1, k + 1 < regions.len())], false, text);
|
||||
// The dictionaries stay retained for the next region, until the last (7.2.4).
|
||||
let refers_to: Vec<(u8, bool)> = dictionaries.iter().map(|n| (*n, k + 1 < regions.len())).collect();
|
||||
segment(&mut out, number, 7, &refers_to, false, text);
|
||||
number += 1;
|
||||
}
|
||||
if !left.is_empty() {
|
||||
@@ -543,8 +653,9 @@ fn encode_id(mq: &mut MqEncoder, contexts: &mut [Context], length: u32, id: u32)
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::*;
|
||||
use crate::jbig2::tests::{decode, samples, unpack};
|
||||
use crate::jbig2::{encode_jbig2, encode_jbig2_generic};
|
||||
use crate::FilterError;
|
||||
use crate::jbig2::tests::{decode, decode_with, samples, unpack};
|
||||
use crate::jbig2::{encode_jbig2, encode_jbig2_generic, encode_jbig2_shared};
|
||||
|
||||
type Bitmap = Vec<Vec<u8>>;
|
||||
|
||||
@@ -665,11 +776,11 @@ mod tests {
|
||||
fn every_plan_round_trips(picture: &Bitmap) -> usize {
|
||||
let (columns, rows) = (picture[0].len() as u32, picture.len() as u32);
|
||||
let data = samples(picture);
|
||||
let page = page(&data, columns, rows).unwrap();
|
||||
let page = page(&data, columns).unwrap();
|
||||
let mut plans = 0;
|
||||
for copies in [1, 2] {
|
||||
for log_strips in 0..4 {
|
||||
if let Some(coded) = plan(&page, columns, rows, copies, Some(log_strips)) {
|
||||
if let Some(coded) = plan(&page, columns, rows, copies, Some(log_strips), None) {
|
||||
assert_eq!(decode(&coded), unpack(&data, columns, rows), "{copies} copies, strips of {}", 1 << log_strips);
|
||||
plans += 1;
|
||||
}
|
||||
@@ -735,10 +846,10 @@ mod tests {
|
||||
row[stride - 1] &= 0xFF << (8 * stride - columns);
|
||||
}
|
||||
let (c, r) = (columns as u32, 120);
|
||||
let page = page(&data, c, r).unwrap();
|
||||
let page = page(&data, c).unwrap();
|
||||
assert!(page.marks.iter().all(|m| m.x1 as usize <= columns), "{columns} columns");
|
||||
for copies in [1, 2] {
|
||||
if let Some(coded) = plan(&page, c, r, copies, None) {
|
||||
if let Some(coded) = plan(&page, c, r, copies, None, None) {
|
||||
assert_eq!(decode(&coded), unpack(&data, c, r), "{columns} columns");
|
||||
}
|
||||
}
|
||||
@@ -771,7 +882,7 @@ mod tests {
|
||||
row[290] = 1;
|
||||
}
|
||||
let data = samples(&picture);
|
||||
let page = page(&data, 300, 300).unwrap();
|
||||
let page = page(&data, 300).unwrap();
|
||||
let boxes: Vec<(u32, u32, u32, u32)> = page.marks.iter().map(|m| (m.x0, m.y0, m.x1 - m.x0, m.y1 - m.y0)).collect();
|
||||
assert_eq!(
|
||||
boxes,
|
||||
@@ -792,18 +903,14 @@ mod tests {
|
||||
assert_eq!(every_plan_round_trips(&picture), 8);
|
||||
}
|
||||
|
||||
/// Past 2^20 black runs or 2^24 rows the image is left to generic coding; at either cap it is
|
||||
/// still looked at.
|
||||
/// Past 2^20 black runs the image is left to generic coding; at the cap it is still looked at.
|
||||
#[test]
|
||||
fn busy_or_tall_images_are_left_to_generic_coding() {
|
||||
fn busy_images_are_left_to_generic_coding() {
|
||||
// 0x55: four black pixels a byte, each its own run, under the same ones on the next row.
|
||||
let columns = 1 << 20;
|
||||
let row = vec![0x55u8; columns / 8];
|
||||
assert!(page(&row.repeat(2), columns as u32, 2).is_some(), "2^20 runs");
|
||||
assert!(page(&row.repeat(3), columns as u32, 3).is_none(), "1.5 × 2^20 runs");
|
||||
let tall = vec![0xFFu8; MAX_ROWS as usize + 1];
|
||||
assert!(page(&tall, 1, MAX_ROWS + 1).is_none());
|
||||
assert!(page(&tall, 1, MAX_ROWS).is_some());
|
||||
assert!(page(&row.repeat(2), columns as u32).is_some(), "2^20 runs");
|
||||
assert!(page(&row.repeat(3), columns as u32).is_none(), "1.5 × 2^20 runs");
|
||||
}
|
||||
|
||||
/// A plan codes at most 32,767 symbols, which an independent decoder reads back; with more,
|
||||
@@ -828,18 +935,18 @@ mod tests {
|
||||
(samples(&picture), columns as u32, rows as u32)
|
||||
};
|
||||
let (data, columns, rows) = codes(MAX_CODED_SYMBOLS, 0);
|
||||
let at_cap = page(&data, columns, rows).unwrap();
|
||||
assert_eq!(decode(&plan(&at_cap, columns, rows, 1, None).unwrap()), unpack(&data, columns, rows));
|
||||
let at_cap = page(&data, columns).unwrap();
|
||||
assert_eq!(decode(&plan(&at_cap, columns, rows, 1, None, None).unwrap()), unpack(&data, columns, rows));
|
||||
// One more distinct mark, each once: neither plan is made.
|
||||
let (data, columns, rows) = codes(MAX_CODED_SYMBOLS + 1, 0);
|
||||
let past = page(&data, columns, rows).unwrap();
|
||||
assert!(plan(&past, columns, rows, 1, None).is_none() && plan(&past, columns, rows, 2, None).is_none());
|
||||
let past = page(&data, columns).unwrap();
|
||||
assert!(plan(&past, columns, rows, 1, None, None).is_none() && plan(&past, columns, rows, 2, None, None).is_none());
|
||||
assert_eq!(encode_jbig2(&data, columns, rows).unwrap(), encode_jbig2_generic(&data, columns, rows).unwrap());
|
||||
// With two of them repeated, the second plan codes those two.
|
||||
let (data, columns, rows) = codes(MAX_CODED_SYMBOLS + 1, 200);
|
||||
let past = page(&data, columns, rows).unwrap();
|
||||
assert!(plan(&past, columns, rows, 1, None).is_none());
|
||||
assert_eq!(decode(&plan(&past, columns, rows, 2, None).unwrap()), unpack(&data, columns, rows));
|
||||
let past = page(&data, columns).unwrap();
|
||||
assert!(plan(&past, columns, rows, 1, None, None).is_none());
|
||||
assert_eq!(decode(&plan(&past, columns, rows, 2, None, None).unwrap()), unpack(&data, columns, rows));
|
||||
// Above a page of text whose letters repeat, that second plan is the one `encode_jbig2`
|
||||
// keeps: the first, of every mark, would code too many symbols.
|
||||
let mut picture: Bitmap = vec![vec![0u8; 256 * 18]; 512];
|
||||
@@ -857,10 +964,10 @@ mod tests {
|
||||
let coded = encode_jbig2(&data, columns, rows).unwrap();
|
||||
assert_eq!(segment_types(&coded)[1], 0, "symbol coded");
|
||||
assert_eq!(decode(&coded), unpack(&data, columns, rows));
|
||||
let (data, columns, rows) = codes(MAX_SYMBOLS, 0);
|
||||
assert_eq!(page(&data, columns, rows).map(|p| p.symbols.len()), Some(MAX_SYMBOLS));
|
||||
let (data, columns, rows) = codes(MAX_SYMBOLS + 1, 0);
|
||||
assert!(page(&data, columns, rows).is_none());
|
||||
let (data, columns, _) = codes(MAX_SYMBOLS, 0);
|
||||
assert_eq!(page(&data, columns).map(|p| p.symbols.len()), Some(MAX_SYMBOLS));
|
||||
let (data, columns, _) = codes(MAX_SYMBOLS + 1, 0);
|
||||
assert!(page(&data, columns).is_none());
|
||||
// `n` black squares of 256 × 256, each with a white pixel in a different place: 2^16
|
||||
// pixels a symbol, so 256 of them are exactly the cap.
|
||||
let squares = |n: usize| {
|
||||
@@ -876,11 +983,11 @@ mod tests {
|
||||
(samples(&picture), columns as u32, rows as u32)
|
||||
};
|
||||
let (data, columns, rows) = squares(256);
|
||||
let at_cap = page(&data, columns, rows).unwrap();
|
||||
let at_cap = page(&data, columns).unwrap();
|
||||
assert_eq!(at_cap.symbols.len(), 256);
|
||||
assert_eq!(decode(&plan(&at_cap, columns, rows, 1, None).unwrap()), unpack(&data, columns, rows));
|
||||
let (data, columns, rows) = squares(257);
|
||||
assert!(page(&data, columns, rows).is_none());
|
||||
assert_eq!(decode(&plan(&at_cap, columns, rows, 1, None, None).unwrap()), unpack(&data, columns, rows));
|
||||
let (data, columns, _) = squares(257);
|
||||
assert!(page(&data, columns).is_none());
|
||||
}
|
||||
|
||||
/// More than 10,000 marks are placed by several text regions, each of at most 10,000 (more
|
||||
@@ -993,7 +1100,199 @@ mod tests {
|
||||
}
|
||||
}
|
||||
|
||||
/// Each segment's page association (7.2.6): the byte after the numbers it refers to.
|
||||
fn associations(data: &[u8]) -> Vec<u8> {
|
||||
let (mut pages, mut at) = (Vec::new(), 0);
|
||||
while at < data.len() {
|
||||
let refers = usize::from(data[at + 5] >> 5);
|
||||
pages.push(data[at + 6 + refers]);
|
||||
let length_at = at + 6 + refers + 1;
|
||||
at = length_at + 4 + u32::from_be_bytes(data[length_at..length_at + 4].try_into().unwrap()) as usize;
|
||||
}
|
||||
pages
|
||||
}
|
||||
|
||||
/// `pictures`, `columns` × `rows` each, coded sharing a dictionary; each image's stream, which
|
||||
/// has to be there, decodes with the globals to its picture.
|
||||
fn shared_round_trip(pictures: &[Bitmap]) -> (Vec<u8>, Vec<Vec<u8>>) {
|
||||
let (columns, rows) = (pictures[0][0].len() as u32, pictures[0].len() as u32);
|
||||
let data: Vec<Vec<u8>> = pictures.iter().map(|p| samples(p)).collect();
|
||||
let images: Vec<(&[u8], u32, u32)> = data.iter().map(|d| (&d[..], columns, rows)).collect();
|
||||
let shared = encode_jbig2_shared(&images).unwrap().unwrap();
|
||||
let (globals, coded) = (shared.globals, shared.images);
|
||||
let coded: Vec<Vec<u8>> = coded.into_iter().map(Option::unwrap).collect();
|
||||
for (d, c) in data.iter().zip(&coded) {
|
||||
assert_eq!(decode_with(c, Some(&globals)), unpack(d, columns, rows));
|
||||
}
|
||||
(globals, coded)
|
||||
}
|
||||
|
||||
/// `font` with a stem 20 pixels tall down each glyph's left side: a font sharing no glyph with
|
||||
/// any [`glyphs`] gives, whose glyphs are at most 18 pixels tall.
|
||||
fn stemmed(font: &[Bitmap]) -> Vec<Bitmap> {
|
||||
font.iter()
|
||||
.map(|g| {
|
||||
(0..g.len().max(20)).map(|y| std::iter::once(1).chain(g.get(y).cloned().unwrap_or_else(|| vec![0; g[0].len()])).collect()).collect()
|
||||
})
|
||||
.collect()
|
||||
}
|
||||
|
||||
/// Mark `k` of a set of distinct ones: a stroke 33 pixels long with a pixel above every other
|
||||
/// column for each 1 bit of `k`, below 2^17.
|
||||
fn comb(k: usize) -> Bitmap {
|
||||
let mut g = vec![vec![0u8; 33]; 2];
|
||||
g[1].fill(1);
|
||||
for bit in 0..17 {
|
||||
g[0][2 * bit] = u8::from(k >> bit & 1 == 1);
|
||||
}
|
||||
g
|
||||
}
|
||||
|
||||
/// The combs `ks`, 120 a row, the rows four pixels apart.
|
||||
fn combs(ks: impl ExactSizeIterator<Item = usize>) -> Bitmap {
|
||||
let mut page = vec![vec![0u8; 120 * 36]; ks.len().div_ceil(120) * 4];
|
||||
for (i, k) in ks.enumerate() {
|
||||
draw(&mut page, &comb(k), (i % 120 * 36) as i64, (i / 120 * 4) as i64);
|
||||
}
|
||||
page
|
||||
}
|
||||
|
||||
/// The symbols a symbol dictionary segment exports (SDNUMEXSYMS, 7.4.2.1.4), in a stream
|
||||
/// that is that segment alone: after its header, flags and adaptive pixels.
|
||||
fn exported(globals: &[u8]) -> usize {
|
||||
u32::from_be_bytes(globals[21..25].try_into().unwrap()) as usize
|
||||
}
|
||||
|
||||
/// Pages in one font share its letters: one symbol dictionary, segment 0, associated with no
|
||||
/// page and retained (7.2.4, 7.2.6), which each page's text region refers to first, its own
|
||||
/// segments numbered after it (7.2.5). Together they take less than they take alone.
|
||||
#[test]
|
||||
fn pages_in_one_font_share_one_dictionary() {
|
||||
let font = glyphs(40, 7);
|
||||
let pictures: Vec<Bitmap> = (0..4).map(|seed| text(1200, 300, &font, 20 + seed)).collect();
|
||||
let (globals, coded) = shared_round_trip(&pictures);
|
||||
assert_eq!(segments(&globals), [(0, 0, true, vec![])]);
|
||||
assert_eq!(associations(&globals), [0]);
|
||||
let (mut shared, mut alone) = (globals.len(), 0);
|
||||
for (picture, c) in pictures.iter().zip(&coded) {
|
||||
let segments = segments(c);
|
||||
assert_eq!(segments.first().map(|s| s.0), Some(1), "the page's own segments follow");
|
||||
assert!(segments.iter().filter(|s| s.1 == 7).all(|s| s.3.first() == Some(&(0, false))), "{segments:?}");
|
||||
assert!(associations(c).iter().all(|page| *page == 1));
|
||||
shared += c.len();
|
||||
alone += encode_jbig2(&samples(picture), 1200, 300).unwrap().len();
|
||||
}
|
||||
assert!(shared < alone, "shared {shared} bytes, alone {alone}");
|
||||
}
|
||||
|
||||
/// Two pages alike place every mark from the shared dictionary and have none of their own; a
|
||||
/// page with letters of its own as well keeps them in its own dictionary, referred to after the
|
||||
/// shared one (its symbols' IDs follow), and the page with nothing shared has no stream.
|
||||
#[test]
|
||||
fn what_a_page_has_alone_stays_its_own() {
|
||||
let (font, other) = (glyphs(30, 7), stemmed(&glyphs(20, 99)));
|
||||
let same = text(900, 240, &font, 3);
|
||||
let mut more = text(900, 240, &font, 4);
|
||||
more.extend(text(900, 120, &other, 5));
|
||||
let (globals, coded) = shared_round_trip(&[same.clone(), same.clone()]);
|
||||
assert!(!globals.is_empty());
|
||||
assert!(coded.iter().all(|c| segment_types(c) == [48, 7]), "{:?}", coded.iter().map(|c| segment_types(c)).collect::<Vec<_>>());
|
||||
let with_more = |p: &Bitmap| p.iter().cloned().chain(std::iter::repeat_n(vec![0u8; 900], 120)).collect::<Bitmap>();
|
||||
let (_, coded) = shared_round_trip(&[with_more(&same), more]);
|
||||
assert_eq!(segment_types(&coded[1])[..3], [48, 0, 7]);
|
||||
assert_eq!(segments(&coded[1])[2].3, [(0, false), (2, false)]);
|
||||
let alone = text(900, 360, &other, 6);
|
||||
let data: Vec<Vec<u8>> = [&same, &same, &alone].iter().map(|p| samples(p)).collect();
|
||||
let images: Vec<(&[u8], u32, u32)> = vec![(&data[0], 900, 240), (&data[1], 900, 240), (&data[2], 900, 360)];
|
||||
let (_, coded) = encode_shared(&images).unwrap();
|
||||
assert!(coded[0].is_some() && coded[1].is_some() && coded[2].is_none());
|
||||
}
|
||||
|
||||
/// Images that share fewer than two marks share nothing; two are enough.
|
||||
#[test]
|
||||
fn images_with_nothing_in_common_share_nothing() {
|
||||
let font = glyphs(30, 7);
|
||||
let (a, b) = (samples(&text(600, 200, &font, 1)), samples(&text(600, 200, &stemmed(&font), 1)));
|
||||
assert!(encode_shared(&[(&a, 600, 200), (&b, 600, 200)]).is_none());
|
||||
assert!(encode_shared(&[(&a, 600, 200)]).is_none(), "one image");
|
||||
assert!(encode_shared(&[]).is_none());
|
||||
// The two commonest letters of the first page, below the last line of the second.
|
||||
let mut two = text(600, 200, &stemmed(&font), 1);
|
||||
draw(&mut two, &font[0], 10, 180);
|
||||
draw(&mut two, &font[1], 100, 180);
|
||||
let two = samples(&two);
|
||||
let (globals, coded) = encode_shared(&[(&a, 600, 200), (&two, 600, 200)]).unwrap();
|
||||
assert_eq!(exported(&globals), 2);
|
||||
assert_eq!(decode_with(coded[1].as_ref().unwrap(), Some(&globals)), unpack(&two, 600, 200));
|
||||
}
|
||||
|
||||
/// The images of a group are checked as `encode_jbig2_generic` checks one, and an image it
|
||||
/// would refuse refuses the group.
|
||||
#[test]
|
||||
fn a_group_with_an_image_the_encoder_refuses_is_refused() {
|
||||
let page = samples(&text(600, 200, &glyphs(30, 7), 1));
|
||||
assert!(matches!(encode_jbig2_shared(&[(&page, 600, 200), (&page[..10], 600, 200)]), Err(FilterError::Corrupt { .. })));
|
||||
assert!(matches!(encode_jbig2_shared(&[(&page, 600, 200), (&page, 0, 200)]), Err(FilterError::Unsupported(_))));
|
||||
assert!(encode_jbig2_shared(&[(&page, 600, 200), (&page, 600, 200)]).unwrap().is_some());
|
||||
}
|
||||
|
||||
/// A group holds its distinct marks within what one image's are held to: past 65,536 a mark
|
||||
/// first seen later isn't held, so isn't shared, while those held count every image they're
|
||||
/// in. Ten marks of the first image are in two images after it, with 464 first seen there.
|
||||
#[test]
|
||||
fn past_the_marks_a_group_holds_later_ones_arent_shared() {
|
||||
let (a, b) = (samples(&combs(0..40_000)), samples(&combs(40_000..65_536)));
|
||||
let late = combs((0..10).chain(65_536..66_000).collect::<Vec<_>>().into_iter());
|
||||
let (rows, late) = (late.len() as u32, samples(&late));
|
||||
let (columns, a_rows, b_rows) = (120 * 36, 40_000u32.div_ceil(120) * 4, 25_536u32.div_ceil(120) * 4);
|
||||
let images = [(&a[..], columns, a_rows), (&b[..], columns, b_rows), (&late[..], columns, rows), (&late[..], columns, rows)];
|
||||
let (globals, coded) = encode_shared(&images).unwrap();
|
||||
assert_eq!(exported(&globals), 10);
|
||||
for c in &coded[2..] {
|
||||
assert_eq!(decode_with(c.as_ref().unwrap(), Some(&globals)), unpack(&late, columns, rows));
|
||||
}
|
||||
}
|
||||
|
||||
/// Past what one dictionary shares, it keeps the marks the most images hold: 20,000 shared,
|
||||
/// the first 10,000 in all three images and the rest in two. The third image then places all
|
||||
/// its marks from it, and the other two code the rest themselves (in a dictionary of their own
|
||||
/// or a generic region, whichever is smaller).
|
||||
#[test]
|
||||
fn past_the_shared_limit_the_most_widely_held_marks_are_shared() {
|
||||
let (both, first) = (combs(0..20_000), combs(0..10_000));
|
||||
let rows = both.len();
|
||||
let first: Bitmap = first.iter().cloned().chain(std::iter::repeat_n(vec![0u8; 120 * 36], rows - first.len())).collect();
|
||||
let (globals, coded) = shared_round_trip(&[both.clone(), both, first]);
|
||||
assert_eq!(exported(&globals), MAX_SHARED_SYMBOLS);
|
||||
assert_eq!(segment_types(&coded[2]), [48, 7]);
|
||||
assert!(segment_types(&coded[0]).iter().any(|t| *t == 0 || *t == 39), "{:?}", segment_types(&coded[0]));
|
||||
}
|
||||
|
||||
proptest::proptest! {
|
||||
/// Glyphs scattered over pages of one font: whatever is shared, every page with a stream
|
||||
/// decodes with the globals to its picture.
|
||||
#[test]
|
||||
fn shared_groups_round_trip(
|
||||
columns in 1usize..200,
|
||||
rows in 1usize..100,
|
||||
shapes in 2usize..8,
|
||||
n in 0usize..60,
|
||||
pages in 2usize..5,
|
||||
seed in proptest::num::u64::ANY,
|
||||
) {
|
||||
let font = glyphs(shapes, seed);
|
||||
let data: Vec<Vec<u8>> = (0..pages).map(|p| samples(&scatter(columns, rows, &font, seed ^ p as u64, n))).collect();
|
||||
let (c, r) = (columns as u32, rows as u32);
|
||||
let images: Vec<(&[u8], u32, u32)> = data.iter().map(|d| (&d[..], c, r)).collect();
|
||||
if let Some((globals, coded)) = encode_shared(&images) {
|
||||
for (d, coded) in data.iter().zip(coded) {
|
||||
if let Some(coded) = coded {
|
||||
proptest::prop_assert_eq!(decode_with(&coded, Some(&globals)), unpack(d, c, r));
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/// Glyphs anywhere, over the edges and each other, with stray pixels: every plan decodes to
|
||||
/// the picture, and `encode_jbig2` is never larger than the generic coding.
|
||||
#[test]
|
||||
@@ -1024,6 +1323,7 @@ mod tests {
|
||||
fn any_input_returns(data in proptest::collection::vec(0u8..=255, 0..600), columns in 0u32..5000, rows in 0u32..80) {
|
||||
let _ = encode_jbig2(&data, columns, rows);
|
||||
let _ = encode(&data, columns, rows);
|
||||
let _ = encode_shared(&[(&data, columns, rows), (&data, columns, rows.saturating_sub(1))]);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
@@ -27,7 +27,8 @@
|
||||
//! ```
|
||||
//!
|
||||
//! 1-bit samples can be encoded as CCITT Group 4 ([`encode_g4`]) or lossless JBIG2
|
||||
//! ([`encode_jbig2`]).
|
||||
//! ([`encode_jbig2`]), a group of images sharing their marks through `/JBIG2Globals`
|
||||
//! ([`encode_jbig2_shared`]).
|
||||
//!
|
||||
//! Every decoder is bounded by a caller-supplied `max_output` (decompression-bomb
|
||||
//! defence) and never panics on malformed input.
|
||||
@@ -47,7 +48,7 @@ mod runlength;
|
||||
use std::borrow::Cow;
|
||||
|
||||
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};
|
||||
pub use jbig2::{MAX_JBIG2_COLUMNS, MAX_JBIG2_PIXELS, SharedJbig2, decode_jbig2_within, encode_jbig2, encode_jbig2_generic, encode_jbig2_shared};
|
||||
|
||||
/// A PDF stream filter, identified by its `/Filter` name.
|
||||
#[derive(Clone, Debug, PartialEq, Eq, Hash)]
|
||||
|
||||
@@ -50,7 +50,10 @@ let cells: Vec<table::Cell> = grid.cells_for(names)?; // "Table1_1", "Table
|
||||
keeps it: `/V` is stored as typed, the appearance draws `?` for those characters, the widget is
|
||||
marked with the first one (`pdfcraft_fonts::UNDRAWN_MARK`, cleared once all of it can be drawn)
|
||||
and the form sets `/NeedAppearances`, so other viewers draw the field from its value with fonts
|
||||
that have them. Not in a document that declares PDF/A, which forbids that flag (`declares_pdfa`).
|
||||
that have them. Not in a document that declares PDF/A, which forbids that flag (`declares_pdfa`:
|
||||
the bytes `pdfaid:part` in XMP metadata each filter stage of which decodes within 8 MiB, the cap
|
||||
preflight's Standards panel reads it with; preflight reads the identifier by its namespace, so a
|
||||
packet that gives that namespace another prefix declares PDF/A there and not here).
|
||||
`undrawn_fields` lists the marked fields; the engine reports each edit that draws one, and
|
||||
flattening refuses to make that `?` permanent.
|
||||
- Displaying a form that leaves its appearances to the viewer (`/NeedAppearances`, or a text or
|
||||
|
||||
@@ -212,13 +212,24 @@ impl FieldAppearanceCache {
|
||||
}
|
||||
}
|
||||
|
||||
/// Whether the document's XMP metadata declares PDF/A conformance (`pdfaid:part`).
|
||||
/// The most each filter stage of the XMP metadata stream may decode for its PDF/A declaration to
|
||||
/// be read, the cap preflight's Standards panel reads it with: past it, metadata declares nothing
|
||||
/// there either.
|
||||
pub(crate) const MAX_XMP_BYTES: usize = 8 << 20;
|
||||
|
||||
/// Whether the document's XMP metadata declares PDF/A conformance (the bytes `pdfaid:part`).
|
||||
/// Metadata a filter stage of which decodes past [`MAX_XMP_BYTES`] doesn't.
|
||||
pub fn declares_pdfa(doc: &Document) -> bool {
|
||||
let Some(root) = doc.root() else { return false };
|
||||
let Some(m) = doc.get(root).as_dict().and_then(|c| c.get(b"Metadata").cloned()) else { return false };
|
||||
let m = doc.resolve(&m);
|
||||
match &*m {
|
||||
Object::Stream(s) => s.decoded().is_ok_and(|b| b.windows(11).any(|w| w == b"pdfaid:part")),
|
||||
// Not a `DecodeBudget`, which counts every stage against one allowance: preflight bounds
|
||||
// each stage, and the two must agree on metadata stored through a chain of filters.
|
||||
// `/DecodeParms` is read only when direct, as preflight and organize read metadata too:
|
||||
// PDF/A asks for it unfiltered, so only a file that breaks that reaches parameters here,
|
||||
// and the readers go to `with_direct_parms` together or they disagree.
|
||||
Object::Stream(s) => s.decoded_within(MAX_XMP_BYTES).is_ok_and(|b| b.windows(11).any(|w| w == b"pdfaid:part")),
|
||||
_ => false,
|
||||
}
|
||||
}
|
||||
|
||||
@@ -234,6 +234,7 @@ pub fn set_props(doc: &mut Document, name: &str, props: &FieldProps) -> Result<S
|
||||
let mut list_picked = None;
|
||||
let (sort_items, old_selection) = items_to_sort(doc, &f, props);
|
||||
let parent_default = ancestor_sets(doc, f.obj, b"DV");
|
||||
let parent_limit = ancestor_sets(doc, f.obj, b"MaxLen");
|
||||
doc.update_dict(f.obj, |d| {
|
||||
d.set(b"Ff".to_vec(), Object::Int(ff as i64));
|
||||
if let Some(t) = &props.tooltip {
|
||||
@@ -246,6 +247,8 @@ pub fn set_props(doc: &mut Document, name: &str, props: &FieldProps) -> Result<S
|
||||
if let Some(m) = props.max_len {
|
||||
match m {
|
||||
Some(m) => d.set(b"MaxLen".to_vec(), Object::Int(m as i64)),
|
||||
// An absent key would inherit the parent's limit; zero is "no limit" (`read.rs`).
|
||||
None if parent_limit => d.set(b"MaxLen".to_vec(), Object::Int(0)),
|
||||
None => {
|
||||
d.remove(b"MaxLen");
|
||||
}
|
||||
@@ -583,10 +586,15 @@ fn apply_late_widget_props(
|
||||
}
|
||||
|
||||
/// Name field `old` `new` in each field's Calculate script that reads it
|
||||
/// ([`crate::af::rename_in_calculation`]).
|
||||
/// ([`crate::af::rename_in_calculation`]). Script streams share one budget, as a reading of the
|
||||
/// form's scripts does, however many fields name the same stream; past it, a script is left as
|
||||
/// it is, like one that won't decode. A Calculate action several fields share by reference is
|
||||
/// read and rewritten once, in place, so they all read the new name.
|
||||
fn rename_in_calculations(doc: &mut Document, all: &[Field], old: &str, new: &str) -> Result<(), FormError> {
|
||||
let aa_of =
|
||||
|doc: &Document, r: ObjRef| doc.get(r).as_dict().and_then(|d| d.get(b"AA").map(|a| doc.resolve(a))).and_then(|a| a.as_dict().cloned());
|
||||
let mut scripts = crate::script_budget();
|
||||
let mut shared = std::collections::HashSet::new();
|
||||
for f in all {
|
||||
// The script is the field's, or its only widget's when the field has none, as
|
||||
// `actions_of` reads it.
|
||||
@@ -595,12 +603,16 @@ fn rename_in_calculations(doc: &mut Document, all: &[Field], old: &str, new: &st
|
||||
_ => None,
|
||||
};
|
||||
let Some((owner, mut aa)) = aa_of(doc, f.obj).map(|aa| (f.obj, aa)).or_else(only_widget) else { continue };
|
||||
let by_ref = aa.get(b"C").and_then(Object::as_ref);
|
||||
if by_ref.is_some_and(|r| !shared.insert(r)) {
|
||||
continue;
|
||||
}
|
||||
let Some(mut action) = aa.get(b"C").and_then(|a| doc.resolve(a).as_dict().cloned()) else { continue };
|
||||
let js = match action.get(b"JS").map(|js| doc.resolve(js)).as_deref() {
|
||||
Some(Object::String(s)) => s.to_text(),
|
||||
// A stream that isn't UTF-8 reads with replacement characters, which must not be
|
||||
// written back in place of what it holds.
|
||||
Some(Object::Stream(s)) => match s.decoded().ok().and_then(|b| String::from_utf8(b).ok()) {
|
||||
Some(Object::Stream(s)) => match scripts.decode(s).ok().and_then(|b| String::from_utf8(b).ok()) {
|
||||
Some(js) => js,
|
||||
None => continue,
|
||||
},
|
||||
@@ -608,6 +620,10 @@ fn rename_in_calculations(doc: &mut Document, all: &[Field], old: &str, new: &st
|
||||
};
|
||||
let Some(js) = crate::af::rename_in_calculation(&js, old, new) else { continue };
|
||||
action.set(b"JS".to_vec(), PdfString::text(&js));
|
||||
if let Some(r) = by_ref {
|
||||
doc.update_dict(r, |d| *d = action)?;
|
||||
continue;
|
||||
}
|
||||
aa.set(b"C".to_vec(), Object::Dict(action));
|
||||
doc.update_dict(owner, |d| d.set(b"AA".to_vec(), Object::Dict(aa)))?;
|
||||
}
|
||||
|
||||
@@ -6,7 +6,7 @@
|
||||
//! the shapes from a page's content, [`raster::shapes`] from a picture of the page (a scan).
|
||||
|
||||
use pdfcraft_content::{Matrix, Pieces};
|
||||
use pdfcraft_cos::{Document, Object};
|
||||
use pdfcraft_cos::{DecodeBudget, Document, Object};
|
||||
|
||||
pub mod raster;
|
||||
|
||||
@@ -49,6 +49,60 @@ pub struct Candidate {
|
||||
/// points along its sides (#2942: a cell drawn with a midpoint on each vertical side).
|
||||
const MAX_RECT_POINTS: usize = 16;
|
||||
|
||||
/// Graphics states saved (`q`) and kept at once while detecting; deeper saves are counted, not kept.
|
||||
const MAX_SAVES: usize = 256;
|
||||
|
||||
/// The graphics states a page saves (`q`) as detection follows its matrix: at most [`MAX_SAVES`]
|
||||
/// kept, deeper ones counted so each `Q` still closes its own. Of those not kept: the matrix when
|
||||
/// the first was made, which closing the last restores; the shallowest a `cm` changed the matrix
|
||||
/// in; and whether a `Q` has closed that one, so the matrix isn't known until the last closes.
|
||||
struct Saves {
|
||||
kept: Vec<Matrix>,
|
||||
lost: usize,
|
||||
lost_base: Matrix,
|
||||
moved_at: usize,
|
||||
unknown: bool,
|
||||
}
|
||||
|
||||
impl Default for Saves {
|
||||
fn default() -> Self {
|
||||
Saves { kept: Vec::new(), lost: 0, lost_base: Matrix::IDENTITY, moved_at: usize::MAX, unknown: false }
|
||||
}
|
||||
}
|
||||
|
||||
impl Saves {
|
||||
fn save(&mut self, ctm: Matrix) {
|
||||
if self.kept.len() < MAX_SAVES && self.lost == 0 {
|
||||
self.kept.push(ctm);
|
||||
} else {
|
||||
if self.lost == 0 {
|
||||
self.lost_base = ctm;
|
||||
}
|
||||
self.lost = self.lost.saturating_add(1);
|
||||
}
|
||||
}
|
||||
|
||||
fn restore(&mut self, ctm: &mut Matrix) {
|
||||
if self.lost == 0 {
|
||||
*ctm = self.kept.pop().unwrap_or(*ctm);
|
||||
return;
|
||||
}
|
||||
self.lost -= 1;
|
||||
if self.lost == 0 {
|
||||
(*ctm, self.moved_at, self.unknown) = (self.lost_base, usize::MAX, false);
|
||||
} else if self.lost < self.moved_at {
|
||||
self.unknown = true;
|
||||
}
|
||||
}
|
||||
|
||||
/// A `cm` changed the matrix at the current depth.
|
||||
fn moved(&mut self) {
|
||||
if self.lost > 0 {
|
||||
self.moved_at = self.moved_at.min(self.lost);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/// The rectangles and horizontal segments a page draws (stroked or filled), in user space.
|
||||
#[derive(Default)]
|
||||
struct DetectionPath {
|
||||
@@ -125,7 +179,15 @@ impl DetectionPath {
|
||||
}
|
||||
}
|
||||
|
||||
/// The shapes page `page`'s content draws, its streams decoded within one page's allowance
|
||||
/// ([`DecodeBudget::page`]), however often `/Contents` lists the same stream.
|
||||
pub fn page_shapes(doc: &Document, page: usize) -> Shapes {
|
||||
shapes_within(doc, page, &mut DecodeBudget::page())
|
||||
}
|
||||
|
||||
/// [`page_shapes`], decoding against `budget`: a stream `/Contents` lists again is charged again,
|
||||
/// and one past what is left reads as empty.
|
||||
pub(crate) fn shapes_within(doc: &Document, page: usize, budget: &mut DecodeBudget) -> Shapes {
|
||||
let mut out = Shapes::default();
|
||||
let Some(p) = pdfcraft_model::pages(doc).into_iter().nth(page) else { return out };
|
||||
let list: Vec<Object> = match p.dict.get(b"Contents").map(|c| doc.resolve(c)) {
|
||||
@@ -139,24 +201,36 @@ pub fn page_shapes(doc: &Document, page: usize) -> Shapes {
|
||||
let mut pieces = Vec::new();
|
||||
for o in list {
|
||||
if let Object::Stream(s) = &*doc.resolve(&o) {
|
||||
pieces.push(s.decoded().unwrap_or_default());
|
||||
pieces.push(budget.decode(s).unwrap_or_default());
|
||||
}
|
||||
}
|
||||
let mut ctm = Matrix::IDENTITY;
|
||||
let mut stack = Vec::new();
|
||||
let mut saves = Saves::default();
|
||||
let mut path_boxes: Vec<[f64; 4]> = Vec::new();
|
||||
let mut subpaths: Vec<DetectionPath> = Vec::new();
|
||||
let mut path = DetectionPath::default();
|
||||
let mut cur: Option<[f64; 2]> = None;
|
||||
for op in Pieces::join(&pieces).parse().ops {
|
||||
let joined = Pieces::join(&pieces);
|
||||
drop(pieces);
|
||||
// An operator at a time: dense content (`n n n …`) parsed whole holds about 80 bytes for each
|
||||
// byte it decoded.
|
||||
for op in pdfcraft_content::ops(joined.data()) {
|
||||
match op.op.as_slice() {
|
||||
b"q" => stack.push(ctm),
|
||||
b"Q" => ctm = stack.pop().unwrap_or(ctm),
|
||||
b"q" => saves.save(ctm),
|
||||
b"Q" => saves.restore(&mut ctm),
|
||||
b"cm" => {
|
||||
if let Some(m) = op.nums::<6>() {
|
||||
ctm = Matrix(m).then(&ctm);
|
||||
saves.moved();
|
||||
}
|
||||
}
|
||||
// Painted where the matrix isn't known: dropped, as `n` drops a path.
|
||||
b"S" | b"s" | b"f" | b"F" | b"f*" | b"B" | b"B*" | b"b" | b"b*" if saves.unknown => {
|
||||
path_boxes.clear();
|
||||
subpaths.clear();
|
||||
path = DetectionPath::default();
|
||||
cur = None;
|
||||
}
|
||||
b"re" => {
|
||||
path.finish(&mut subpaths);
|
||||
if let Some([x, y, w, h]) = op.nums::<4>() {
|
||||
|
||||
@@ -192,11 +192,17 @@ fn actions_of(doc: &Document, d: &Dict, widgets: &[ObjRef], scripts: &mut Decode
|
||||
out
|
||||
}
|
||||
|
||||
fn values_of(doc: &Document, o: Option<&Object>) -> Vec<String> {
|
||||
/// Text streams of field values (`/V`, `/DV`) one reading of the form may decode in all, however
|
||||
/// many fields name the same stream.
|
||||
pub(crate) const MAX_VALUE_BYTES: usize = 64 << 20;
|
||||
|
||||
/// A field's value or default value (`/V`, `/DV`). A text stream is decoded against `budget`, and
|
||||
/// reads as no value once it is spent, as one that won't decode does.
|
||||
fn values_of(doc: &Document, o: Option<&Object>, budget: &mut DecodeBudget) -> Vec<String> {
|
||||
let Some(o) = o else { return Vec::new() };
|
||||
match &*doc.resolve(o) {
|
||||
Object::Array(a) => a.iter().filter_map(|x| text_of(&doc.resolve(x))).collect(),
|
||||
Object::Stream(s) => s.decoded().ok().map(|b| PdfString::literal(b).to_text()).into_iter().collect(),
|
||||
Object::Stream(s) => budget.decode(s).ok().map(|b| PdfString::literal(b).to_text()).into_iter().collect(),
|
||||
other => text_of(other).filter(|s| s != "Off" && !s.is_empty()).into_iter().collect(),
|
||||
}
|
||||
}
|
||||
@@ -345,7 +351,12 @@ pub(crate) fn enumerate(doc: &Document) -> (Vec<Field>, usize) {
|
||||
None => Inherited::default(),
|
||||
};
|
||||
let mut out = Vec::new();
|
||||
let mut seen = Seen { fields: std::collections::HashSet::new(), widgets: std::collections::HashSet::new(), scripts: script_budget() };
|
||||
let mut seen = Seen {
|
||||
fields: std::collections::HashSet::new(),
|
||||
widgets: std::collections::HashSet::new(),
|
||||
scripts: script_budget(),
|
||||
values: DecodeBudget::new(MAX_VALUE_BYTES, 0),
|
||||
};
|
||||
if let Some(af) = &af {
|
||||
for f in af.get(b"Fields").map(|o| doc.resolve(o)).and_then(|o| o.as_array().cloned()).unwrap_or_default() {
|
||||
if let Some(r) = f.as_ref() {
|
||||
@@ -416,13 +427,14 @@ fn unlisted_root(doc: &Document, r: ObjRef, seen: &std::collections::HashSet<Obj
|
||||
}
|
||||
}
|
||||
|
||||
/// What one reading of the form's fields has used: the field and widget dictionaries read, and
|
||||
/// the script budget their actions share.
|
||||
/// What one reading of the form's fields has used: the field and widget dictionaries read, the
|
||||
/// script budget their actions share, and the budget their value streams share.
|
||||
struct Seen {
|
||||
fields: std::collections::HashSet<ObjRef>,
|
||||
/// A widget belongs to the first field that lists it, however often it is listed.
|
||||
widgets: std::collections::HashSet<ObjRef>,
|
||||
scripts: DecodeBudget,
|
||||
values: DecodeBudget,
|
||||
}
|
||||
|
||||
/// Read the field at `r` and the fields under it into `out`, with what they inherit from
|
||||
@@ -549,8 +561,8 @@ fn walk(
|
||||
name: inh.name.clone(),
|
||||
obj: r,
|
||||
kind,
|
||||
value: values_of(doc, inh.v.as_ref()),
|
||||
default: values_of(doc, inh.dv.as_ref()),
|
||||
value: values_of(doc, inh.v.as_ref(), &mut seen.values),
|
||||
default: values_of(doc, inh.dv.as_ref(), &mut seen.values),
|
||||
flags: ff,
|
||||
max_len: inh.max_len,
|
||||
options,
|
||||
|
||||
@@ -3575,6 +3575,149 @@ fn repeated_script_references_share_one_decode_budget() {
|
||||
assert!(calculate > 0 && calculate <= limit, "{calculate} bytes of field scripts");
|
||||
}
|
||||
|
||||
/// An unfiltered stream of `body`, as an object of [`document`].
|
||||
fn raw_stream(body: &str) -> String {
|
||||
format!("<< /Length {} >>\nstream\n{body}\nendstream", body.len())
|
||||
}
|
||||
|
||||
/// 300 fields whose value is one 1 MiB text stream: a reading of the form decodes their values
|
||||
/// within one budget, not 300 MiB.
|
||||
#[test]
|
||||
fn repeated_value_streams_share_one_decode_budget() {
|
||||
let fields_list: String = (0..300).map(|i| format!("{} 0 R ", i + 3)).collect();
|
||||
let mut objs = vec![format!("<< /Type /Catalog /AcroForm << /Fields [{fields_list}] >> >>"), raw_stream(&"x".repeat(1 << 20))];
|
||||
objs.extend((0..300).map(|i| format!("<< /FT /Tx /T (f{i}) /V 2 0 R /DV 2 0 R >>")));
|
||||
let all = fields(&document(&objs));
|
||||
assert_eq!(all.len(), 300);
|
||||
let read: usize = all.iter().flat_map(|f| f.value.iter().chain(&f.default)).map(String::len).sum();
|
||||
assert!(read > 0 && read <= crate::read::MAX_VALUE_BYTES, "{read} bytes of values");
|
||||
assert_eq!(all[0].value, ["x".repeat(1 << 20)], "the first field still reads its value");
|
||||
}
|
||||
|
||||
/// Clear form leaves a field as it is when its default is a stream the value budget didn't reach:
|
||||
/// 70 fields typed in, whose default is one 1 MiB text stream, keep a value, the first ones
|
||||
/// their default and the rest what was typed, none of them emptied.
|
||||
#[test]
|
||||
fn clear_form_keeps_a_field_whose_default_was_not_read() {
|
||||
let n = 70;
|
||||
let fields_list: String = (0..n).map(|i| format!("{} 0 R ", i + 3)).collect();
|
||||
let mut objs = vec![format!("<< /Type /Catalog /AcroForm << /Fields [{fields_list}] >> >>"), raw_stream(&"d".repeat(1 << 20))];
|
||||
objs.extend((0..n).map(|i| format!("<< /FT /Tx /T (f{i}) /V (typed) /DV 2 0 R >>")));
|
||||
let mut doc = document(&objs);
|
||||
reset(&mut doc, None).unwrap();
|
||||
let values: Vec<String> = (0..n)
|
||||
.map(|i| {
|
||||
let field = doc.get(ObjRef::new(i as u32 + 3, 0));
|
||||
field.as_dict().and_then(|d| d.get(b"V")).and_then(|v| v.as_string().map(PdfString::to_text)).unwrap_or_default()
|
||||
})
|
||||
.collect();
|
||||
assert!(values.iter().all(|v| !v.is_empty()), "no field is emptied");
|
||||
assert_eq!(values[0], "d".repeat(1 << 20), "the first field goes back to its default");
|
||||
assert_eq!(values[n - 1], "typed", "the last field, whose default wasn't read, keeps its value");
|
||||
// A value the reading didn't decode, with no default, is cleared: it isn't known to be empty.
|
||||
let mut objs = vec![format!("<< /Type /Catalog /AcroForm << /Fields [{fields_list}] >> >>"), raw_stream(&"v".repeat(1 << 20))];
|
||||
objs.extend((0..n).map(|i| format!("<< /FT /Tx /T (f{i}) /V 2 0 R >>")));
|
||||
let mut doc = document(&objs);
|
||||
reset(&mut doc, None).unwrap();
|
||||
let last = doc.get(ObjRef::new(n as u32 + 2, 0));
|
||||
assert!(last.as_dict().and_then(|d| d.get(b"V")).is_none_or(|v| !matches!(v, Object::Ref(_))), "the last field's unread value is cleared");
|
||||
}
|
||||
|
||||
/// Renaming a field that 300 calculations read through one shared Calculate action, whose script
|
||||
/// is a 256 KiB stream, decodes and rewrites that action once, in place: every calculation reads
|
||||
/// the new name, and nothing is decoded or written 300 times.
|
||||
#[test]
|
||||
fn a_rename_rewrites_a_shared_calculation_once() {
|
||||
let n = 300;
|
||||
let refs = |from: usize| -> String { (from..from + n).map(|i| format!("{i} 0 R ")).collect() };
|
||||
let js = format!("AFSimple_Calculate(\"SUM\", new Array (\"a\"));{}", " ".repeat(256 << 10));
|
||||
let mut objs = vec![
|
||||
"<< /Type /Catalog /Pages 2 0 R /AcroForm 4 0 R >>".into(),
|
||||
"<< /Type /Pages /Kids [3 0 R] /Count 1 /MediaBox [0 0 600 800] >>".into(),
|
||||
format!("<< /Type /Page /Parent 2 0 R /Annots [5 0 R {}] >>", refs(8)),
|
||||
format!("<< /Fields [5 0 R {}] /DA (/Helv 0 Tf 0 g) >>", refs(8)),
|
||||
"<< /Type /Annot /Subtype /Widget /FT /Tx /T (a) /Rect [50 700 250 720] /P 3 0 R >>".into(),
|
||||
"<< /S /JavaScript /JS 7 0 R >>".into(),
|
||||
raw_stream(&js),
|
||||
];
|
||||
objs.extend((0..n).map(|i| format!("<< /Type /Annot /Subtype /Widget /FT /Tx /T (c{i}) /Rect [50 10 250 30] /P 3 0 R /AA << /C 6 0 R >> >>")));
|
||||
let mut doc = document(&objs);
|
||||
set_props(&mut doc, "a", &FieldProps { name: Some("qty".into()), ..FieldProps::default() }).unwrap();
|
||||
let action = ObjRef::new(6, 0);
|
||||
let renamed = (8..8 + n).all(|i| {
|
||||
let field = doc.get(ObjRef::new(i as u32, 0));
|
||||
field.as_dict().and_then(|d| d.get(b"AA")).and_then(|aa| aa.as_dict()?.get(b"C")?.as_ref()) == Some(action)
|
||||
});
|
||||
assert!(renamed, "every calculation still names the one shared action");
|
||||
let js = doc.get(action).as_dict().and_then(|d| d.get(b"JS")?.as_string().map(PdfString::to_text)).unwrap_or_default();
|
||||
assert!(js.contains("\"qty\"") && !js.contains("\"a\""), "the shared action reads the new name");
|
||||
assert!(js.len() <= MAX_SCRIPT_BYTES, "{} bytes written once", js.len());
|
||||
}
|
||||
|
||||
/// A page whose `/Contents` lists one 1 MiB stream ten times is read within the budget given:
|
||||
/// pieces past it read as empty, so their rectangles aren't found.
|
||||
#[test]
|
||||
fn page_shapes_decode_a_repeated_content_stream_within_the_budget() {
|
||||
let piece = format!("%{}\n10 10 20 20 re S\n", "x".repeat(1 << 20));
|
||||
let doc = document(&[
|
||||
"<< /Type /Catalog /Pages 2 0 R >>".into(),
|
||||
"<< /Type /Pages /Kids [3 0 R] /Count 1 /MediaBox [0 0 600 800] >>".into(),
|
||||
format!("<< /Type /Page /Parent 2 0 R /Contents [{}] >>", "4 0 R ".repeat(10)),
|
||||
raw_stream(&piece),
|
||||
]);
|
||||
assert_eq!(crate::detect::page_shapes(&doc, 0).boxes.len(), 10, "one page's allowance reads them all");
|
||||
let mut budget = DecodeBudget::new(4 << 20, 0);
|
||||
let boxes = crate::detect::shapes_within(&doc, 0, &mut budget).boxes.len();
|
||||
assert!((1..=4).contains(&boxes), "{boxes} rectangles read within 4 MiB");
|
||||
assert_eq!(budget.remaining(), 0, "the budget is spent");
|
||||
}
|
||||
|
||||
/// Field detection keeps at most 256 saved graphics states, and each `Q` still restores its own
|
||||
/// `q` past that: a scale set 300 saves deep is gone once they are all restored.
|
||||
#[test]
|
||||
fn page_shapes_restore_saves_past_the_cap() {
|
||||
let content = format!("{} 2 0 0 2 0 0 cm {} 10 10 20 20 re S", "q ".repeat(300), "Q ".repeat(300));
|
||||
let doc = document(&[
|
||||
"<< /Type /Catalog /Pages 2 0 R >>".into(),
|
||||
"<< /Type /Pages /Kids [3 0 R] /Count 1 /MediaBox [0 0 600 800] >>".into(),
|
||||
"<< /Type /Page /Parent 2 0 R /Contents 4 0 R >>".into(),
|
||||
raw_stream(&content),
|
||||
]);
|
||||
assert_eq!(crate::detect::page_shapes(&doc, 0).boxes, [[10.0, 10.0, 30.0, 30.0]]);
|
||||
// A scale set past the cap and closed by its own `Q` leaves a matrix that can't be known until
|
||||
// the last lost save closes: what is drawn in between isn't reported at the scaled place.
|
||||
let content = format!("{} q 2 0 0 2 0 0 cm Q 10 10 20 20 re S {} 40 40 10 10 re S", "q ".repeat(257), "Q ".repeat(257));
|
||||
let doc = document(&[
|
||||
"<< /Type /Catalog /Pages 2 0 R >>".into(),
|
||||
"<< /Type /Pages /Kids [3 0 R] /Count 1 /MediaBox [0 0 600 800] >>".into(),
|
||||
"<< /Type /Page /Parent 2 0 R /Contents 4 0 R >>".into(),
|
||||
raw_stream(&content),
|
||||
]);
|
||||
assert_eq!(crate::detect::page_shapes(&doc, 0).boxes, [[40.0, 40.0, 50.0, 50.0]]);
|
||||
}
|
||||
|
||||
/// The PDF/A declaration is read from metadata each filter stage of which decodes within
|
||||
/// [`crate::appearances::MAX_XMP_BYTES`], as preflight decodes it: a field drawn with characters its
|
||||
/// font lacks decodes no more than that a stage.
|
||||
#[test]
|
||||
fn a_pdfa_declaration_is_read_from_metadata_within_its_cap() {
|
||||
let declared = |xmp: String| declares_pdfa(&document(&["<< /Type /Catalog /Metadata 2 0 R >>".into(), raw_stream(&xmp)]));
|
||||
let pdfa = |padding: usize| format!("<x:xmpmeta><pdfaid:part>2</pdfaid:part>{}</x:xmpmeta>", " ".repeat(padding));
|
||||
assert!(declared(pdfa(1 << 20)));
|
||||
assert!(!declared(pdfa(crate::appearances::MAX_XMP_BYTES)), "metadata past the cap declares nothing");
|
||||
assert!(!declared("<x:xmpmeta><dc:title>pdfaid</dc:title></x:xmpmeta>".into()), "metadata without pdfaid:part declares nothing");
|
||||
// 3.5 MiB stored as hex, then Flate: its stages decode 7 and 3.5 MiB, each within the cap.
|
||||
let xmp = pdfa(7 << 19);
|
||||
let hex: Vec<u8> = xmp.bytes().flat_map(|b| [b"0123456789ABCDEF"[usize::from(b >> 4)], b"0123456789ABCDEF"[usize::from(b & 15)]]).collect();
|
||||
let mut stream = pdfcraft_cos::Stream::flate(pdfcraft_cos::Dict::new(), &hex);
|
||||
stream.dict.set(b"Filter".to_vec(), Object::Array(vec![Object::name("FlateDecode"), Object::name("ASCIIHexDecode")]));
|
||||
let mut doc = Document::new_empty();
|
||||
let metadata = doc.add(Object::Stream(stream));
|
||||
let catalog = doc.add(Object::Dict([(b"Metadata".to_vec(), Object::Ref(metadata))].into_iter().collect()));
|
||||
doc.trailer_mut().set(b"Root".to_vec(), Object::Ref(catalog));
|
||||
assert!(declares_pdfa(&doc), "metadata through a chain of filters declares PDF/A, as preflight decodes it");
|
||||
}
|
||||
|
||||
/// A widget listed many times, by one field's `/Kids` or by a `/Kids` array several fields share,
|
||||
/// is read once: the first field to list it owns it.
|
||||
#[test]
|
||||
@@ -5344,6 +5487,29 @@ fn sorting_keeps_which_of_two_items_with_one_export_value_is_selected() {
|
||||
assert_eq!(selection_indices(&doc, &list), Some(vec![2]));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn clearing_a_kids_length_limit_does_not_bring_back_its_parents() {
|
||||
let mut doc = fixture();
|
||||
let city = field(&fields(&doc), "address.city").clone();
|
||||
let parent = doc.get(city.obj).as_dict().unwrap().reference(b"Parent").unwrap();
|
||||
doc.update_dict(parent, |d| d.set(b"MaxLen".to_vec(), Object::Int(3))).unwrap();
|
||||
set_props(&mut doc, "address.city", &FieldProps { max_len: Some(Some(8)), ..FieldProps::default() }).unwrap();
|
||||
assert_eq!(field(&fields(&doc), "address.city").max_len, Some(8));
|
||||
set_props(&mut doc, "address.city", &FieldProps { max_len: Some(None), ..FieldProps::default() }).unwrap();
|
||||
let mut doc = reopen(&doc);
|
||||
let f = field(&fields(&doc), "address.city").clone();
|
||||
assert_eq!(f.max_len, None, "no limit, not the parent's 3");
|
||||
let own = doc.get(f.obj).as_dict().and_then(|d| d.get(b"MaxLen")).and_then(Object::as_int);
|
||||
assert_eq!(own, Some(0), "the kid holds an explicit unlimited of its own");
|
||||
set_value(&mut doc, "address.city", &FieldValue::Text("Absalom".into())).unwrap();
|
||||
assert_eq!(field(&fields(&reopen(&doc)), "address.city").value, ["Absalom"], "not cut to 3 characters");
|
||||
// Without a parent limit, clearing still removes the key.
|
||||
set_props(&mut doc, "name", &FieldProps { max_len: Some(Some(4)), ..FieldProps::default() }).unwrap();
|
||||
set_props(&mut doc, "name", &FieldProps { max_len: Some(None), ..FieldProps::default() }).unwrap();
|
||||
let name = field(&fields(&doc), "name").clone();
|
||||
assert!(doc.get(name.obj).as_dict().unwrap().get(b"MaxLen").is_none());
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn clearing_a_kids_default_does_not_bring_back_its_parents() {
|
||||
let mut doc = fixture();
|
||||
|
||||
@@ -470,7 +470,9 @@ fn redraw(doc: &mut Document, f: &Field, values: &[String], scripts: &mut dyn Sc
|
||||
/// document that declares PDF/A, which forbids it: there the widget's mark
|
||||
/// (`pdfcraft_fonts::UNDRAWN_MARK`) is all, and the edit's report says the `?` shows everywhere.
|
||||
pub(crate) fn ask_viewers_to_redraw(doc: &mut Document) -> Result<(), FormError> {
|
||||
if declares_pdfa(doc) || need_appearances(doc) {
|
||||
// The form's own flag first: once it is set, the metadata needn't be decoded again for each
|
||||
// field drawn after.
|
||||
if need_appearances(doc) || declares_pdfa(doc) {
|
||||
return Ok(());
|
||||
}
|
||||
let Some(root) = doc.root() else { return Ok(()) };
|
||||
@@ -625,6 +627,22 @@ pub fn clear_password_values(doc: &mut Document) -> Result<usize, FormError> {
|
||||
Ok(targets.len())
|
||||
}
|
||||
|
||||
/// Whether `field`'s `key` (`/V` or `/DV`, its own or inherited) is a stream with data, which
|
||||
/// [`fields`] reads as empty once its value budget is spent.
|
||||
fn unread_stream(doc: &Document, field: ObjRef, key: &[u8]) -> bool {
|
||||
let mut node = Some(field);
|
||||
for _ in 0..64 {
|
||||
let Some(r) = node else { break };
|
||||
let obj = doc.get(r);
|
||||
let Some(d) = obj.as_dict() else { break };
|
||||
if let Some(value) = d.get(key) {
|
||||
return matches!(&*doc.resolve(value), Object::Stream(s) if !s.raw.is_empty());
|
||||
}
|
||||
node = d.reference(b"Parent");
|
||||
}
|
||||
false
|
||||
}
|
||||
|
||||
/// Acrobat's Clear form: every field (or the named ones) back to its default value.
|
||||
pub fn reset(doc: &mut Document, names: Option<&[String]>) -> Result<usize, FormError> {
|
||||
let all = fields(doc);
|
||||
@@ -638,7 +656,11 @@ pub fn reset(doc: &mut Document, names: Option<&[String]>) -> Result<usize, Form
|
||||
}
|
||||
let mut changed = 0;
|
||||
for f in all.iter().filter(|f| names.is_none_or(|n| n.contains(&f.name))) {
|
||||
if f.value == f.default {
|
||||
// A default the reading didn't decode (its budget spent) is unknown, not empty: clearing
|
||||
// the field to nothing would lose the value it should go back to. A value it didn't decode
|
||||
// isn't known to be the default, so it is reset.
|
||||
let unread = |key: &[u8], read: &[String]| read.is_empty() && unread_stream(doc, f.obj, key);
|
||||
if unread(b"DV", &f.default) || (f.value == f.default && !unread(b"V", &f.value)) {
|
||||
continue;
|
||||
}
|
||||
let v = match f.kind {
|
||||
|
||||
@@ -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 +28,12 @@ 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.
|
||||
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,
|
||||
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. Images over 80 million pixels are left
|
||||
alone by the image steps, here and below, whatever their settings (memory); Clean Up may still
|
||||
Flate an unfiltered or LZW one. Left alone by these colour and grey
|
||||
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
|
||||
@@ -86,7 +89,15 @@ let report = optimize_with_progress(&mut doc, &settings, &mut |stage| keep_going
|
||||
alone when JBIG2 is asked for, is stored again as the compression asks when that is smaller (as JBIG2 symbols where
|
||||
its own coding is a generic region, say); a symbol-coded scan, averaged, loses its exact
|
||||
repeats and often comes out larger, and then stays as it is. A JBIG2 image stored again refers to no
|
||||
`/JBIG2Globals`, and one whose page isn't its size (PdfCraft's
|
||||
`/JBIG2Globals` of its own. With JBIG2 asked for, the images stored as JBIG2, up to 16 at a
|
||||
time, then share one symbol dictionary in a new `/JBIG2Globals` stream, holding the marks found
|
||||
in more than one of them: those that come out smaller that way, when together they save more
|
||||
than it takes. Only images that redaction can store again without it share one: image masks
|
||||
and DeviceGray images named directly, of at most 64 Mi pixels (redaction's limit,
|
||||
`pdfcraft_cos::MAX_REDACTED_IMAGE_PIXELS`); others are coded alone.
|
||||
Redacting one of them stores the others of its group again without it, so the group keeps that
|
||||
to 15 images, and each image's decode reads the dictionary of 16 at most. A
|
||||
JBIG2 image whose page isn't its size (PdfCraft's
|
||||
renderer draws the whole page into the image) is left alone. With Retain, a resampled image
|
||||
keeps its kind of compression (CCITT, JBIG2, or Flate) and nothing else changes; an image of
|
||||
more bits is then left to the grey or colour settings. Every change is kept only when it is
|
||||
@@ -95,11 +106,12 @@ let report = optimize_with_progress(&mut doc, &settings, &mut |stage| keep_going
|
||||
space, decode array and `/Mask` stay, but for packed RGB, which becomes grey with one decode
|
||||
pair. Group 4 wins on scans, whose ragged edges defeat Flate; on clean computer-drawn 1-bit
|
||||
art Flate can be smaller. Not yet: inline images, an image's own `/SMask` or `/Mask`
|
||||
image (only images drawn on a page are visited), and Group 4 for rows wider than 32,767
|
||||
samples.
|
||||
image (only images drawn on a page are visited), Group 4 for rows wider than 32,767
|
||||
samples, and JBIG2 past 65,535 samples on a side, where the decoder stops (its 2^28 in all
|
||||
is past the 80 million pixels above).
|
||||
|
||||
- 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
|
||||
smaller, a dictionary shared by up to 16 images when that is smaller still. No lossy symbol substitution is used. Export, redaction and this step read JBIG2
|
||||
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
|
||||
|
||||
@@ -717,6 +717,11 @@ 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(
|
||||
@@ -728,8 +733,11 @@ fn process(
|
||||
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)))
|
||||
{
|
||||
@@ -1109,12 +1117,23 @@ fn downsample_bits_checked(data: &[u8], w: u32, h: u32, nw: u32, nh: u32, dark_i
|
||||
/// to be resampled, and so is JBIG2 alone when Group 4 is asked for; Group 3, Group 4 inside
|
||||
/// another filter, and JBIG2 otherwise are stored again like any other. With `Retain`, a resampled image keeps its kind of compression (CCITT, JBIG2, or
|
||||
/// Flate), and nothing else changes: an image of more bits stays as it is, for the grey or
|
||||
/// colour settings. A JBIG2 image stored again refers to no `/JBIG2Globals`.
|
||||
/// colour settings. A JBIG2 image stored again refers to no `/JBIG2Globals`; with `Jbig2`, [`share`]
|
||||
/// may then have a group of them share one.
|
||||
///
|
||||
/// 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, budget: &mut ImageBudget) -> Option<(Stream, bool)> {
|
||||
///
|
||||
/// Stored as JBIG2 with `Jbig2`, it comes with the 1-bit samples it was coded from, for [`share`]
|
||||
/// to code again with the run's other JBIG2 images.
|
||||
fn mono(
|
||||
doc: &Document,
|
||||
s: &Stream,
|
||||
ppi: f64,
|
||||
defaults: bool,
|
||||
settings: &MonoSettings,
|
||||
budget: &mut ImageBudget,
|
||||
) -> Option<(Stream, bool, Option<Vec<u8>>)> {
|
||||
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;
|
||||
@@ -1198,7 +1217,106 @@ fn mono(doc: &Document, s: &Stream, ppi: f64, defaults: bool, settings: &MonoSet
|
||||
let flate = ((resampled || packed_from_more) && !(retain && (ccitt || jbig2))).then(|| Stream::flate(dict, &data));
|
||||
// Smaller as stored, counting the dictionary: a tiny image can lose by Group 4's parameters.
|
||||
let best = [g4, jbig, flate].into_iter().flatten().filter_map(|c| Some((crate::stored_len(&c)?, c))).min_by_key(|(len, _)| *len)?;
|
||||
(best.0 < crate::stored_len(s)?).then_some((best.1, resampled))
|
||||
let shareable = settings.compression == MonoCompression::Jbig2 && best.1.dict.name(b"Filter") == Some(b"JBIG2Decode");
|
||||
(best.0 < crate::stored_len(s)?).then(|| (best.1, resampled, shareable.then_some(data)))
|
||||
}
|
||||
|
||||
/// The most images that share one symbol dictionary ([`share`]). Redaction stores again every
|
||||
/// image that shares a redacted one's dictionary, and each image's decode reads all of it, so a
|
||||
/// group keeps both to that many; most of what sharing saves comes with the first few images.
|
||||
const SHARED_IMAGES: usize = 16;
|
||||
|
||||
/// The most bytes of 1-bit samples a group holds: a group is coded before it would pass them
|
||||
/// ([`hold_in`]). An image that shares has at most [`SHARED_PIXELS`], and as its rows are whole
|
||||
/// bytes, at most that many bytes, which is this: one always fits a group with nothing in it.
|
||||
const SHARED_BYTES: usize = 64 << 20;
|
||||
|
||||
/// What the globals cost as an object of their own besides their dictionary and data: `N 0 obj`,
|
||||
/// `stream`, `endstream` and `endobj`, a cross-reference entry, and an encrypted file's IV and
|
||||
/// padding. A group is shared only when it saves more than that as well.
|
||||
const NEW_OBJECT: usize = 96;
|
||||
|
||||
/// Adds `image` to `group`, coding the group (`share`, which empties it) first when the image's
|
||||
/// samples would take it past `cap` bytes, and after when it has [`SHARED_IMAGES`].
|
||||
fn hold_in(group: &mut Vec<Held>, image: Held, cap: usize, mut share: impl FnMut(&mut Vec<Held>)) {
|
||||
if group.iter().map(|h| h.bits.len()).fold(image.bits.len(), usize::saturating_add) > cap {
|
||||
share(group);
|
||||
}
|
||||
group.push(image);
|
||||
if group.len() == SHARED_IMAGES {
|
||||
share(group);
|
||||
}
|
||||
}
|
||||
|
||||
/// The most pixels an image sharing a dictionary has: redaction's own limit on the images it
|
||||
/// stores again (see [`shares`]).
|
||||
const SHARED_PIXELS: u64 = pdfcraft_cos::MAX_REDACTED_IMAGE_PIXELS;
|
||||
|
||||
/// Whether an image stored as JBIG2 (its dictionary `d`) may share a dictionary: only one that
|
||||
/// redaction can store again without it, an image mask or a DeviceGray image, named directly, of
|
||||
/// at most [`SHARED_PIXELS`]. Redacting one image of a group stores the others so, as the
|
||||
/// dictionary can hold the shapes of marks under the area, and refuses the redaction for one it
|
||||
/// can't; an image of another colour space, though redaction may take it, is coded alone.
|
||||
fn shares(d: &Dict) -> bool {
|
||||
let side = |key: &[u8]| d.int(key).and_then(|v| u64::try_from(v).ok());
|
||||
let within = side(b"Width").zip(side(b"Height")).is_some_and(|(w, h)| w.saturating_mul(h) <= SHARED_PIXELS);
|
||||
within && (matches!(d.get(b"ImageMask"), Some(Object::Bool(true))) || d.name(b"ColorSpace") == Some(b"DeviceGray"))
|
||||
}
|
||||
|
||||
/// An image the run stored as JBIG2, held to be stored again sharing a dictionary ([`share`]): its
|
||||
/// 1-bit samples, `width` × `height`.
|
||||
struct Held {
|
||||
image: ObjRef,
|
||||
bits: Vec<u8>,
|
||||
width: u32,
|
||||
height: u32,
|
||||
}
|
||||
|
||||
/// Stores the images of `group`, each JBIG2 already, again sharing one symbol dictionary in a
|
||||
/// `/JBIG2Globals` stream ([`pdfcraft_filters::encode_jbig2_shared`]): those that come out smaller
|
||||
/// that way, if together they save more than the globals take. The others stay as they are, and
|
||||
/// so do all of them when that saves nothing. `report` counts the bytes as they end up, the globals
|
||||
/// included.
|
||||
fn share(doc: &mut Document, group: &mut Vec<Held>, report: &mut Report) {
|
||||
let held = std::mem::take(group);
|
||||
if held.len() < 2 {
|
||||
return;
|
||||
}
|
||||
let images: Vec<(&[u8], u32, u32)> = held.iter().map(|h| (&h.bits[..], h.width, h.height)).collect();
|
||||
let Ok(Some(shared)) = pdfcraft_filters::encode_jbig2_shared(&images) else { return };
|
||||
let with_globals = |s: &Stream, coded: Vec<u8>, globals: ObjRef| {
|
||||
let mut dict = s.dict.clone();
|
||||
let mut parms = Dict::new();
|
||||
parms.set(b"JBIG2Globals".to_vec(), Object::Ref(globals));
|
||||
dict.set(b"DecodeParms".to_vec(), Object::Dict(parms));
|
||||
Stream::from_raw(dict, coded)
|
||||
};
|
||||
// Weighed naming the globals with the longest reference there is: the real one is no longer.
|
||||
let longest = ObjRef { num: u32::MAX, generation: u16::MAX };
|
||||
let (mut chosen, mut saved) = (Vec::new(), 0usize);
|
||||
for (h, coded) in held.iter().zip(shared.images) {
|
||||
let Some(coded) = coded else { continue };
|
||||
let object = doc.get(h.image);
|
||||
let Object::Stream(alone) = &*object else { continue };
|
||||
let shorter = crate::stored_len(alone).zip(crate::stored_len(&with_globals(alone, coded.clone(), longest))).filter(|(a, b)| b < a);
|
||||
if let Some((before, after)) = shorter {
|
||||
saved = saved.saturating_add(before - after);
|
||||
chosen.push((h.image, coded));
|
||||
}
|
||||
}
|
||||
let globals = Stream::from_raw(Dict::new(), shared.globals);
|
||||
if chosen.is_empty() || crate::stored_len(&globals).is_none_or(|takes| saved <= takes.saturating_add(NEW_OBJECT)) {
|
||||
return;
|
||||
}
|
||||
report.image_bytes_after = report.image_bytes_after.saturating_add(globals.raw.len());
|
||||
let globals = doc.add(Object::Stream(globals));
|
||||
for (image, coded) in chosen {
|
||||
let object = doc.get(image);
|
||||
let Object::Stream(alone) = &*object else { continue };
|
||||
report.image_bytes_after = report.image_bytes_after.saturating_sub(alone.raw.len()).saturating_add(coded.len());
|
||||
let new = with_globals(alone, coded, globals);
|
||||
doc.set(image, Object::Stream(new));
|
||||
}
|
||||
}
|
||||
|
||||
/// One pass over the document's images, within `budget`. An image past it stays as it is, and is
|
||||
@@ -1231,6 +1349,13 @@ pub(crate) fn run(
|
||||
refs.sort_by_key(|(r, _)| r.num);
|
||||
let total = refs.len();
|
||||
let mut jbig2 = false;
|
||||
let mut group: Vec<Held> = Vec::new();
|
||||
// Holds a JBIG2 image for `share`, which codes the group once it is full.
|
||||
let mut hold = |doc: &mut Document, image: ObjRef, size: (Option<i64>, Option<i64>), bits: Option<Vec<u8>>, report: &mut Report| {
|
||||
let side = |v: Option<i64>| v.and_then(|v| u32::try_from(v).ok());
|
||||
let (Some(bits), Some(width), Some(height)) = (bits, side(size.0), side(size.1)) else { return };
|
||||
hold_in(&mut group, Held { image, bits, width, height }, SHARED_BYTES, |group| share(doc, group, report));
|
||||
};
|
||||
for (done, (r, ppi)) in refs.into_iter().enumerate() {
|
||||
if !progress(Stage::Images { done, total }) {
|
||||
return Err(OptimizeError::Cancelled);
|
||||
@@ -1246,7 +1371,7 @@ pub(crate) fn run(
|
||||
Some(m) if packed_from_more => (Some(m), None),
|
||||
m => (None, m),
|
||||
};
|
||||
if let Some((new, resampled)) = mono {
|
||||
if let Some((new, resampled, bits)) = mono {
|
||||
report.image_bytes_before += s.raw.len();
|
||||
report.image_bytes_after += new.raw.len();
|
||||
if resampled {
|
||||
@@ -1255,7 +1380,10 @@ pub(crate) fn run(
|
||||
report.images_recompressed += 1;
|
||||
}
|
||||
jbig2 |= new.dict.name(b"Filter") == Some(b"JBIG2Decode");
|
||||
let size = (new.dict.int(b"Width"), new.dict.int(b"Height"));
|
||||
let bits = bits.filter(|_| shares(&new.dict));
|
||||
doc.set(r, Object::Stream(new));
|
||||
hold(doc, r, size, bits, report);
|
||||
continue;
|
||||
}
|
||||
let n = s.dict.get(b"ColorSpace").and_then(|cs| components(doc, cs));
|
||||
@@ -1270,10 +1398,10 @@ pub(crate) fn run(
|
||||
}),
|
||||
};
|
||||
let total = |new: &Stream, smask: Option<&(ObjRef, Stream)>| Some(crate::stored_len(new)?.saturating_add(smask_len(smask).unwrap_or(0)));
|
||||
let packed_wins = packed.as_ref().is_some_and(|(p, _)| {
|
||||
let packed_wins = packed.as_ref().is_some_and(|(p, _, _)| {
|
||||
processed.as_ref().is_none_or(|(new, smask)| total(p, None).zip(total(new, smask.as_ref())).is_some_and(|(a, b)| a <= b))
|
||||
});
|
||||
if let Some((new, resampled)) = packed.filter(|_| packed_wins) {
|
||||
if let Some((new, resampled, bits)) = packed.filter(|_| packed_wins) {
|
||||
jbig2 |= new.dict.name(b"Filter") == Some(b"JBIG2Decode");
|
||||
report.image_bytes_before += s.raw.len();
|
||||
report.image_bytes_after += new.raw.len();
|
||||
@@ -1282,7 +1410,10 @@ pub(crate) fn run(
|
||||
} else {
|
||||
report.images_recompressed += 1;
|
||||
}
|
||||
let size = (new.dict.int(b"Width"), new.dict.int(b"Height"));
|
||||
let bits = bits.filter(|_| shares(&new.dict));
|
||||
doc.set(r, Object::Stream(new));
|
||||
hold(doc, r, size, bits, report);
|
||||
continue;
|
||||
}
|
||||
let Some((new, smask)) = processed else {
|
||||
@@ -1303,6 +1434,7 @@ pub(crate) fn run(
|
||||
doc.set(mr, Object::Stream(m));
|
||||
}
|
||||
}
|
||||
share(doc, &mut group, report);
|
||||
if !progress(Stage::Images { done: total, total }) {
|
||||
return Err(OptimizeError::Cancelled);
|
||||
}
|
||||
@@ -1330,6 +1462,58 @@ fn at_least_pdf_1_4(doc: &mut Document) -> Result<(), OptimizeError> {
|
||||
mod dimension_tests {
|
||||
use super::*;
|
||||
|
||||
/// A group is coded before an image's samples would take it past its limit, and once it has
|
||||
/// [`SHARED_IMAGES`]: with room for 10 bytes, images of 4 go two to a group, never three, and
|
||||
/// with room for 8, two of 4 fill one exactly; one of exactly the limit joins a group with
|
||||
/// nothing in it.
|
||||
#[test]
|
||||
fn a_group_is_coded_before_its_samples_would_pass_the_limit() {
|
||||
let held = |bytes: usize| Held { image: ObjRef { num: 1, generation: 0 }, bits: vec![0; bytes], width: 8, height: 8 };
|
||||
let mut coded: Vec<Vec<usize>> = Vec::new();
|
||||
let mut group = Vec::new();
|
||||
let mut code = |g: &mut Vec<Held>| coded.push(std::mem::take(g).iter().map(|h| h.bits.len()).collect());
|
||||
for _ in 0..5 {
|
||||
hold_in(&mut group, held(4), 10, &mut code);
|
||||
}
|
||||
hold_in(&mut group, held(10), 10, &mut code);
|
||||
assert_eq!(coded, [vec![4, 4], vec![4, 4], vec![4]]);
|
||||
assert_eq!(group.iter().map(|h| h.bits.len()).collect::<Vec<_>>(), [10]);
|
||||
// Exactly the limit is within it: with room for 8, two images of 4 stay together.
|
||||
let (mut count, mut group) = (0, Vec::new());
|
||||
let mut code = |g: &mut Vec<Held>| count += std::mem::take(g).len();
|
||||
hold_in(&mut group, held(4), 8, &mut code);
|
||||
hold_in(&mut group, held(4), 8, &mut code);
|
||||
assert_eq!((count, group.len()), (0, 2));
|
||||
let (mut count, mut group) = (0, Vec::new());
|
||||
for _ in 0..SHARED_IMAGES {
|
||||
hold_in(&mut group, held(1), usize::MAX, |g| count += std::mem::take(g).len());
|
||||
}
|
||||
assert_eq!((count, group.len()), (SHARED_IMAGES, 0), "coded on the 16th");
|
||||
}
|
||||
|
||||
/// Only what redaction can store again without the dictionary shares one: an image mask, or
|
||||
/// DeviceGray named directly, of at most 2^26 pixels.
|
||||
#[test]
|
||||
fn only_what_redaction_can_store_again_shares_a_dictionary() {
|
||||
let dict = |entries: Vec<(&str, Object)>| {
|
||||
let mut d = Dict::new();
|
||||
for (k, v) in entries {
|
||||
d.set(k.as_bytes().to_vec(), v);
|
||||
}
|
||||
d
|
||||
};
|
||||
let sized = |w: i64, h: i64, cs: Object| dict(vec![("Width", Object::Int(w)), ("Height", Object::Int(h)), ("ColorSpace", cs)]);
|
||||
assert!(shares(&sized(8192, 8192, Object::name("DeviceGray"))));
|
||||
assert!(!shares(&sized(8192, 8193, Object::name("DeviceGray"))), "a row past 2^26 pixels");
|
||||
assert!(shares(&dict(vec![("Width", Object::Int(8)), ("Height", Object::Int(8)), ("ImageMask", Object::Bool(true))])));
|
||||
let device_n =
|
||||
Object::Array(vec![Object::name("DeviceN"), Object::Array(vec![Object::name("Black")]), Object::name("DeviceGray"), Object::Null]);
|
||||
assert!(!shares(&sized(8, 8, device_n)));
|
||||
assert!(!shares(&sized(8, 8, Object::name("CalGray"))));
|
||||
assert!(!shares(&sized(8, 8, Object::Ref(ObjRef { num: 3, generation: 0 }))), "a colour space by reference");
|
||||
assert!(!shares(&dict(vec![("ColorSpace", Object::name("DeviceGray"))])), "no size");
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn pixel_reader_rejects_hostile_dimensions_before_decoding() {
|
||||
for (width, height, channels) in [(-1, 1, 1), (0, 1, 1), (i64::from(u32::MAX) + 101, 1, 1), (80_000_001, 1, 1), (2, 2, usize::MAX)] {
|
||||
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user