diff --git a/.github/workflows/house-rules.yml b/.github/workflows/house-rules.yml new file mode 100644 index 0000000000..de64ad3ee4 --- /dev/null +++ b/.github/workflows/house-rules.yml @@ -0,0 +1,28 @@ +name: House rules + +on: + push: + branches: [main] + paths: + - AGENTS.md + - CLAUDE.md + - .github/workflows/house-rules.yml + pull_request: + paths: + - AGENTS.md + - CLAUDE.md + - .github/workflows/house-rules.yml + workflow_dispatch: + +permissions: + contents: read + +concurrency: + group: house-rules-${{ github.ref }} + cancel-in-progress: true + +jobs: + house-rules: + uses: storytold/craft-common-actions/.github/workflows/house-rules.yml@main + with: + rust: true diff --git a/.github/workflows/release.yml b/.github/workflows/release.yml index d8549142f7..4b44d79b68 100644 --- a/.github/workflows/release.yml +++ b/.github/workflows/release.yml @@ -19,7 +19,14 @@ concurrency: cancel-in-progress: false jobs: + # Regenerates contributors/contributors.json for the release commit; every build bundles it. + credits: + permissions: + contents: read + pull-requests: read + uses: storytold/craft-common-actions/.github/workflows/refresh-contributors.yml@main release: + needs: credits # Intentionally tracked at @main (not SHA-pinned) so org-wide CI improvements, security fixes, and build optimizations propagate without PR churn across all craftapp repos. uses: storytold/craft-common-actions/.github/workflows/release.yml@main with: @@ -27,6 +34,7 @@ jobs: app-title: PdfCraft craft-fonts-ref: b076417b5880bd4154bd22f00695b1d28c6bea83 version: ${{ inputs.version }} + contributors-artifact: ${{ needs.credits.outputs.artifact-name }} secrets: APPLE_CERTIFICATE: ${{ secrets.APPLE_CERTIFICATE }} APPLE_CERTIFICATE_PASSWORD: ${{ secrets.APPLE_CERTIFICATE_PASSWORD }} @@ -42,3 +50,4 @@ 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 }} diff --git a/AGENTS.md b/AGENTS.md index 3ab900aa95..b68d8c8921 100644 --- a/AGENTS.md +++ b/AGENTS.md @@ -1,6 +1,59 @@ + +## House rules + +These apply in every Craft repository. A later rule may be stricter, not weaker. The source is `standards/house-rules-core.md` in `storytold/craft-contrib`. Propose changes there, not in a copy. + +1. **A person is accountable.** Whoever runs an agent answers for what it opens and for its review comments. +2. **Check, then claim.** Before writing code, read the issue comments, search pull requests for `#N` and the keywords, and check recent commits on `main`. Comment on the issue first. Release a claim you will not finish. +3. **Verify, don't guess.** Open a definition before using it. Confirm the cause in the code, even when someone names a location. +4. **Keep fixes narrow and tested.** Fix what the issue describes, where the bug is. Add a test that fails without the fix. +5. **Review the diff before opening a pull request.** Identifiers exist as used, the test fails without the fix, nothing unrelated changed, and the description is true. +6. **Look for a better pull request.** If another fixes the same thing, close yours when it is better or equal, and say why. +7. **Report only what ran.** Say what you tested and what you could not run. Without a local build or test, say so and rely on CI before marking ready. +8. **`main` changes through a pull request.** Do not push to it. Branch protection enforces this. There is no exception. +9. **Stop and ask only about** licensing outside the allowlist, publishing, releases, a new remote, secrets, spending money, destructive git, and anything else hard to undo. Otherwise keep working. `plan/` is a gitignored notebook, not rules. Without it, do not ask for it and do not stop. +10. **Keep secrets and personal details out** of the repository, logs and requests. +11. **CI stays shared.** Workflows call `storytold/craft-common-actions`. Do not change CI in a feature or fix pull request. If CI cannot cover a change, open an issue there. +12. **Guards say why.** A check that looks removable says what it prevents. Read that before changing it. +13. **Instructions must be readable by everyone.** No notes about one machine, and no links to files a reader cannot open. `craftrules` is retired. Do not link to it. +14. **Keep pull requests moving.** Concurrent pull requests are fine; unanswered actionable feedback is not. Respond in 7 days, a reminder at 14, closure eligible at 30, from when an actionable request waits on the author. Suggestions and unconfirmed bot findings do not start the clock. A fix, explanation or agreed plan resets it; unrelated activity does not. Waiting on a reviewer or maintainer pauses it and does not count against the author. A maintainer decides closure; it is never automatic. Reuse search results, do not poll, and stop at a rate limit. +15. **No agent attribution.** A pull request does not say an agent wrote it. A repository rule may not require that. + + +## Rust Craft repositories + +These apply to native Craft apps and to shared Rust libraries. Select them by repository type. A repository that merely contains some Rust does not take this block. Rules later in a repository's file may be stricter, but not weaker. The source is `standards/house-rules-rust.md` in [storytold/craft-contrib](https://github.com/storytold/craft-contrib). + +1. **Never crash.** Non-test code does not panic and has no `unsafe`, except where the repository file names an exception. Return errors, treat input as hostile, and bound recursion and allocations. New production crate roots copy the `deny` attribute from an existing crate: `clippy::unwrap_used`, `clippy::expect_used`, `clippy::panic`, `clippy::unimplemented`, `clippy::todo`, `clippy::unreachable`. Every crash fix comes with a test that panicked before the fix. +2. **Clean room.** Learn from observed behaviour and public specifications. Do not copy another product's code, assets, strings or artwork. Check a dependency's licence before adding it. +3. **Assets and fonts.** Every asset is original or suitably licensed, and is recorded in `ATTRIBUTION.md` in the same change. Font files live in [storytold/craft-fonts](https://github.com/storytold/craft-fonts), not in the app repository. +4. **Rust only for native Craft apps.** No handwritten JavaScript or TypeScript, and no Tauri, Electron or webview shell, in those apps. Shared tooling follows its documented technical scope and maintainer-approved exceptions. Craft PR Review's existing Tauri and TypeScript UI is one such exception. It does not relax this rule for native apps. Preserve any existing web build. +5. **Time goes through `chrono`.** Do not hand-roll calendar conversion. For dates beyond what `chrono` can represent, follow [standards/time.md](https://github.com/storytold/craft-contrib/blob/main/standards/time.md). +6. **Contributor credits.** Add or edit only your own person's entry in `contributors/people.toml`, and only after asking them. Never guess a name or hand-edit `contributors.json`. + +## Licence allowlist + +Dependencies and assets use SPDX identifiers. An expression is allowed when every identifier is in this list. A repository may name a shorter list. It may not add an identifier here by editing its own copy of these rules. + +- `ISC` +- `MIT` +- `BSD-2-Clause` +- `BSD-3-Clause` +- `Apache-2.0` +- `OFL-1.1` +- `Ubuntu-font-1.0` +- `Bitstream-Vera` +- `CC0-1.0` +- `CC-BY-4.0` +- `CC-BY-SA-4.0` +- `LicenseRef-Public-Domain` + +`LicenseRef-Storyteller-Trademark` is not in this list. It covers Storyteller brand marks only, where a repository already says so. + + # AGENTS.md — rules for every agent and contributor -These rules bind every AI agent and every human contributor working in this repository. They come before any task, instruction or deadline. `CLAUDE.md` holds the day-to-day working instructions. If the two ever disagree, **this file wins.** +These rules bind every AI agent and every human contributor working in this repository. They come before any task, instruction or deadline. Day-to-day working instructions are in this file; `CLAUDE.md` imports it. --- @@ -85,7 +138,7 @@ If you find an asset that breaks these rules, stop and remove it from the reposi --- -## 2. Clean-room rules (summary; details in `CLAUDE.md` and `plan/adr/0001`) +## 2. Clean-room rules (summary; `plan/adr/0001` is an optional local note) - Never read, disassemble or copy anything inside the Acrobat bundle. Only names and listings are allowed, and **never** open `Contents/Resources/JavaScripts/`. - Behaviour comes only from public specifications (ISO 32000-2, the Arlington model), public documentation and black-box observation. @@ -106,7 +159,7 @@ If you find an asset that breaks these rules, stop and remove it from the reposi PdfCraft opens files from strangers, and people trust it with their work. A malformed PDF, a bad tool argument, a corrupt settings file or a full disk must produce an error the user (or agent) can act on, never a crash and never lost work. **This outranks feature work:** don't ship a feature by adding a panic path, and fix a crash before building on top of it. The rules below are the ones that bind this repository. -- **Fail with `Result`.** Non-test code returns errors through the crate's error type and `?`. Where readers are lenient by design, fall back gracefully and record the repair (see Fidelity in `CLAUDE.md`). +- **Fail with `Result`.** Non-test code returns errors through the crate's error type and `?`. Where readers are lenient by design, fall back gracefully and record the repair (see Fidelity below). - **No panicking shortcuts.** No `unwrap()`, `expect()`, `panic!`, `unreachable!`, `todo!` or `unimplemented!` outside tests, unless the call is provably infallible (e.g. writing to a `Vec`), with a comment saying why. `assert!` only for internal invariants that input cannot reach. - **No `unsafe`.** The workspace sets `unsafe_code = "forbid"`. If a platform API needs it, use a maintained safe wrapper crate; a real exception needs the owner's sign-off. - **Treat every input-derived number as hostile.** Use `get()` instead of `[i]` or `[a..b]`. Slice strings only at char boundaries. Use checked/saturating arithmetic for lengths, offsets and counts. Guard against division by zero and NaN/inf casts, and never cast a negative value to `usize`. Cap allocations sized by the file. @@ -115,10 +168,18 @@ PdfCraft opens files from strangers, and people trust it with their work. A malf - **Prove it.** Every crash fix comes with a small synthetic regression test that panicked before the fix. Turn fuzzer findings (`cargo xtask fuzz`) into such tests before fixing them. - **Enforced by clippy.** Root `clippy.toml` lets tests use `unwrap`/`expect`/`panic!`. A crate that is clean carries `#![deny(clippy::unwrap_used, clippy::expect_used, clippy::panic, clippy::unimplemented, clippy::todo, clippy::unreachable)]`; new crates start with it. -## 5. Everything else +## 5. Page interaction, fidelity and gates - -Follow `CLAUDE.md`. It covers quality gates, layering, commit rules and how to run and look at the app. +- **Layering.** Nothing below L7 depends on egui/winit/eframe/rfd. `cos`, `filters`, `crypt` and `arlington` stay standalone. +- **Page input.** Page modules read `PagePointer` (`crates/ui-egui/src/page_pointer.rs`), never egui's raw pointer state. `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`, `crates/ui-egui/src/canvas/page_cursor.rs`) and never set it themselves. `page_pointer::tests::page_modules_claim_the_cursor_and_never_set_it` enforces it. +- **Page presses.** A page module decides what is under a point in one hit test (`Hit` in `crates/ui-egui/src/canvas/page_router.rs`) and acts on a press only through that router. Modules never read the router; they are told. `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. +- **Fonts** are the optional build input `CRAFT_FONTS_DIR`. Code using `pdfcraft_fonts::CRAFT_FONTS` must work when it is empty. +- **Quality gates** before every commit: `cargo fmt --check`, clippy with `-D warnings`, the tests, `cargo xtask layers`, `cargo xtask assets`, and the wasm check. New workspace crates include `workspace = true` under `[lints]`. Scope `cargo clippy -p --all-targets -- -D warnings` and `cargo test -p ` to the crates you touched; the workspace sweep is CI's job. +- **Review at four zooms** as you go: the clause, the function, the module, and the project (layering, wasm, undo, save fidelity, a matching automation tool, an honest `parity/` entry). Prove a test fails before the fix by reverting the fix once. +- `plan/` is an optional gitignored notebook. Do not ask for it and do not stop when it is absent. Public status is [`ROADMAP.md`](ROADMAP.md), [`docs/gaps.md`](docs/gaps.md) and [`docs/roadmap.md`](docs/roadmap.md). "Shipped" in `parity/` means exists and tested, not parity with Acrobat. +- `cargo run -p pdfcraft -- ` opens the app. `pdfcraft-cli run` drives the engine headlessly. `cargo xtask fuzz` findings stay in `fuzz-out/` and become synthetic tests. For UI work, look at a screenshot from `--control` or the `shot` example. ## Contributor credits (About window) diff --git a/ATTRIBUTION.md b/ATTRIBUTION.md index c70d84e624..a8de85e07a 100644 --- a/ATTRIBUTION.md +++ b/ATTRIBUTION.md @@ -4,10 +4,11 @@ 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 (256) +## In this repository (258) | Asset | Title | Author | Licence | Source | Used for | |---|---|---|---|---|---| +| `docs/images/pdfcraft-ocr-verify.png` | PdfCraft screenshot: OCR Verify screen | PdfCraft contributors (generated by `cargo xtask screenshots`) | MIT OR Apache-2.0 | this repository | README: OCR review. Shows only PdfCraft UI, its Lucide icons and a synthetic scanned page built from the embedded fonts, with a real recognition (the OCR models) loaded into the Verify screen | | `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 | @@ -44,7 +45,7 @@ Every asset PdfCraft includes, bundles or uses to build its published material, | `assets/icons/chevron-up.svg` | Lucide icon "chevron-up" | Lucide Contributors (portions Cole Bemis, Feather) | ISC AND MIT | https://github.com/lucide-icons/lucide (npm lucide-static 1.49.0, icons/chevron-up.svg) | UI icon, embedded via crates/ui-egui/src/icon_data.rs | | `assets/icons/chevrons-left.svg` | Lucide icon "chevrons-left" | Lucide Contributors (portions Cole Bemis, Feather) | ISC AND MIT | https://github.com/lucide-icons/lucide (npm lucide-static 1.49.0, icons/chevrons-left.svg) | UI icon, embedded via crates/ui-egui/src/icon_data.rs | | `assets/icons/chevrons-right.svg` | Lucide icon "chevrons-right" | Lucide Contributors (portions Cole Bemis, Feather) | ISC AND MIT | https://github.com/lucide-icons/lucide (npm lucide-static 1.49.0, icons/chevrons-right.svg) | UI icon, embedded via crates/ui-egui/src/icon_data.rs | -| `assets/icons/circle-check.svg` | Lucide icon "circle-check" | Lucide Contributors (portions Cole Bemis, Feather) | ISC AND MIT | https://github.com/lucide-icons/lucide (npm lucide-static 1.49.0, icons/circle-check.svg) | UI icon, embedded via crates/ui-egui/src/icon_data.rs | +| `assets/icons/circle-check.svg` | Lucide icon "circle-check" | Lucide Contributors (portions Cole Bemis, Feather) | ISC AND MIT | https://github.com/lucide-icons/lucide (npm lucide-static 1.49.0, icons/circle-check.svg) | UI icon, embedded via crates/ui-egui/src/icon_data.rs; drawn as PDF path data by crates/sign/src/status_layers.rs into displayed signature status layers | | `assets/icons/circle-dashed.svg` | Lucide icon "circle-dashed" | Lucide Contributors (portions Cole Bemis, Feather) | ISC AND MIT | https://github.com/lucide-icons/lucide (npm lucide-static 1.49.0, icons/circle-dashed.svg) | UI icon, embedded via crates/ui-egui/src/icon_data.rs | | `assets/icons/circle-dot.svg` | Lucide icon "circle-dot" | Lucide Contributors (portions Cole Bemis, Feather) | ISC AND MIT | https://github.com/lucide-icons/lucide (npm lucide-static 1.49.0, icons/circle-dot.svg) | UI icon, embedded via crates/ui-egui/src/icon_data.rs | | `assets/icons/circle-help.svg` | Lucide icon "circle-help" | Lucide Contributors (portions Cole Bemis, Feather) | ISC AND MIT | https://github.com/lucide-icons/lucide (npm lucide-static 1.49.0, icons/circle-help.svg) | UI icon, embedded via crates/ui-egui/src/icon_data.rs | @@ -173,7 +174,7 @@ Every asset PdfCraft includes, bundles or uses to build its published material, | `assets/icons/text-select.svg` | Lucide icon "text-select" | Lucide Contributors (portions Cole Bemis, Feather) | ISC AND MIT | https://github.com/lucide-icons/lucide (npm lucide-static 1.49.0, icons/text-select.svg) | UI icon, embedded via crates/ui-egui/src/icon_data.rs | | `assets/icons/trash-2.svg` | Lucide icon "trash-2" | Lucide Contributors (portions Cole Bemis, Feather) | ISC AND MIT | https://github.com/lucide-icons/lucide (npm lucide-static 1.49.0, icons/trash-2.svg) | UI icon, embedded via crates/ui-egui/src/icon_data.rs | | `assets/icons/trash.svg` | Lucide icon "trash" | Lucide Contributors (portions Cole Bemis, Feather) | ISC AND MIT | https://github.com/lucide-icons/lucide (npm lucide-static 1.49.0, icons/trash.svg) | UI icon, embedded via crates/ui-egui/src/icon_data.rs | -| `assets/icons/triangle-alert.svg` | Lucide icon "triangle-alert" | Lucide Contributors (portions Cole Bemis, Feather) | ISC AND MIT | https://github.com/lucide-icons/lucide (npm lucide-static 1.49.0, icons/triangle-alert.svg) | UI icon, embedded via crates/ui-egui/src/icon_data.rs | +| `assets/icons/triangle-alert.svg` | Lucide icon "triangle-alert" | Lucide Contributors (portions Cole Bemis, Feather) | ISC AND MIT | https://github.com/lucide-icons/lucide (npm lucide-static 1.49.0, icons/triangle-alert.svg) | UI icon, embedded via crates/ui-egui/src/icon_data.rs; drawn as PDF path data by crates/sign/src/status_layers.rs into displayed signature status layers | | `assets/icons/type.svg` | Lucide icon "type" | Lucide Contributors (portions Cole Bemis, Feather) | ISC AND MIT | https://github.com/lucide-icons/lucide (npm lucide-static 1.49.0, icons/type.svg) | UI icon, embedded via crates/ui-egui/src/icon_data.rs | | `assets/icons/underline.svg` | Lucide icon "underline" | Lucide Contributors (portions Cole Bemis, Feather) | ISC AND MIT | https://github.com/lucide-icons/lucide (npm lucide-static 1.49.0, icons/underline.svg) | UI icon, embedded via crates/ui-egui/src/icon_data.rs | | `assets/icons/undo-2.svg` | Lucide icon "undo-2" | Lucide Contributors (portions Cole Bemis, Feather) | ISC AND MIT | https://github.com/lucide-icons/lucide (npm lucide-static 1.49.0, icons/undo-2.svg) | UI icon, embedded via crates/ui-egui/src/icon_data.rs | @@ -183,7 +184,7 @@ Every asset PdfCraft includes, bundles or uses to build its published material, | `assets/icons/x.svg` | Lucide icon "x" | Lucide Contributors (portions Cole Bemis, Feather) | ISC AND MIT | https://github.com/lucide-icons/lucide (npm lucide-static 1.49.0, icons/x.svg) | UI icon, embedded via crates/ui-egui/src/icon_data.rs | | `assets/icons/zoom-in.svg` | Lucide icon "zoom-in" | Lucide Contributors (portions Cole Bemis, Feather) | ISC AND MIT | https://github.com/lucide-icons/lucide (npm lucide-static 1.49.0, icons/zoom-in.svg) | UI icon, embedded via crates/ui-egui/src/icon_data.rs | | `assets/icons/zoom-out.svg` | Lucide icon "zoom-out" | Lucide Contributors (portions Cole Bemis, Feather) | ISC AND MIT | https://github.com/lucide-icons/lucide (npm lucide-static 1.49.0, icons/zoom-out.svg) | UI icon, embedded via crates/ui-egui/src/icon_data.rs | -| `assets/fonts/Inter-Regular.ttf` | Inter Regular | The Inter Project Authors (Rasmus Andersson) | OFL-1.1 | https://github.com/rsms/inter | UI font, embedded in the app; demo PDF labels; slanted fallback glyphs in Fill & Sign typed signatures for characters Dancing Script lacks (Cyrillic, Greek), drawn as filled paths | +| `assets/fonts/Inter-Regular.ttf` | Inter Regular | The Inter Project Authors (Rasmus Andersson) | OFL-1.1 | https://github.com/rsms/inter | UI font, embedded in the app; demo PDF labels; slanted fallback glyphs in Fill & Sign typed signatures for characters Dancing Script lacks (Cyrillic, Greek), drawn as filled paths; embedded into displayed signature status captions beyond WinAnsi by crates/sign/src/status_layers.rs | | `assets/fonts/Inter-Medium.ttf` | Inter Medium | The Inter Project Authors (Rasmus Andersson) | OFL-1.1 | https://github.com/rsms/inter | UI font, embedded in the app; demo PDF labels | | `assets/fonts/Inter-SemiBold.ttf` | Inter SemiBold | The Inter Project Authors (Rasmus Andersson) | OFL-1.1 | https://github.com/rsms/inter | UI font, embedded in the app; demo PDF labels | | `assets/fonts/JetBrainsMono-Regular.ttf` | JetBrains Mono Regular | The JetBrains Mono Project Authors | OFL-1.1 | https://github.com/JetBrains/JetBrainsMono | UI monospace font; demo PDF code | @@ -248,7 +249,7 @@ Every asset PdfCraft includes, bundles or uses to build its published material, | `assets/icons/thumbs-up.svg` | Lucide icon "thumbs-up" | Lucide Contributors (portions Cole Bemis, Feather) | ISC AND MIT | https://github.com/lucide-icons/lucide (npm lucide-static 1.49.0, icons/thumbs-up.svg) | UI icon, embedded via crates/ui-egui/src/icon_data.rs | | `assets/icons/thumbs-down.svg` | Lucide icon "thumbs-down" | Lucide Contributors (portions Cole Bemis, Feather) | ISC AND MIT | https://github.com/lucide-icons/lucide (npm lucide-static 1.49.0, icons/thumbs-down.svg) | UI icon, embedded via crates/ui-egui/src/icon_data.rs | | `assets/icons/message-square-plus.svg` | Lucide icon "message-square-plus" | Lucide Contributors (portions Cole Bemis, Feather) | ISC AND MIT | https://github.com/lucide-icons/lucide (npm lucide-static 1.49.0, icons/message-square-plus.svg) | UI icon, embedded via crates/ui-egui/src/icon_data.rs | -| `assets/icons/circle-x.svg` | Lucide icon "circle-x" | Lucide Contributors (portions Cole Bemis, Feather) | ISC AND MIT | https://github.com/lucide-icons/lucide (npm lucide-static 1.49.0, icons/circle-x.svg) | UI icon, embedded via crates/ui-egui/src/icon_data.rs | +| `assets/icons/circle-x.svg` | Lucide icon "circle-x" | Lucide Contributors (portions Cole Bemis, Feather) | ISC AND MIT | https://github.com/lucide-icons/lucide (npm lucide-static 1.49.0, icons/circle-x.svg) | UI icon, embedded via crates/ui-egui/src/icon_data.rs; drawn as PDF path data by crates/sign/src/status_layers.rs into displayed signature status layers | | `crates/ui-egui/tests/data/form.pdf` | One-page AcroForm test fixture (text, check box, radio group, combo box) | PdfCraft contributors | MIT OR Apache-2.0 | Contributor-original: hand-written PDF objects, no third-party content | Form-filling UI tests (crates/ui-egui/tests/it/forms.rs, commands.rs) | | `assets/icons/pentagon.svg` | Lucide icon "pentagon" | Lucide Contributors (portions Cole Bemis, Feather) | ISC AND MIT | https://github.com/lucide-icons/lucide (npm lucide-static 1.49.0, icons/pentagon.svg) | UI icon, embedded via crates/ui-egui/src/icon_data.rs | | `assets/icons/message-square-quote.svg` | Lucide icon "message-square-quote" | Lucide Contributors (portions Cole Bemis, Feather) | ISC AND MIT | https://github.com/lucide-icons/lucide (npm lucide-static 1.49.0, icons/message-square-quote.svg) | UI icon, embedded via crates/ui-egui/src/icon_data.rs | @@ -263,6 +264,7 @@ Every asset PdfCraft includes, bundles or uses to build its published material, | `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/a-large-small.svg` | Lucide icon "a-large-small" | Lucide Contributors (portions Cole Bemis, Feather) | ISC AND MIT | https://github.com/lucide-icons/lucide (npm lucide-static 1.49.0, icons/a-large-small.svg) | UI icon, embedded via crates/ui-egui/src/widgets/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 | ## Compiled in through dependencies (6) @@ -312,4 +314,4 @@ Not in this repository and never downloaded by it: compiled in only when the bui | Input | Option | Title | Author | Licence | Source | Attribution | Used for | |---|---|---|---|---|---|---|---| | `craft-i18n` | `CRAFT_I18N_DIR` | Interface translations: the craft-i18n catalogs (locales//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 | +| `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); status captions of named-layer signatures in Arabic, Japanese, Thai and Devanagari, drawn as filled outlines into the display copy by crates/sign/src/status_layers.rs; 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 | diff --git a/ATTRIBUTION.toml b/ATTRIBUTION.toml index 9638749929..608bb601a5 100644 --- a/ATTRIBUTION.toml +++ b/ATTRIBUTION.toml @@ -10,6 +10,17 @@ # 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 = "docs/images/pdfcraft-ocr-verify.png" +title = "PdfCraft screenshot: OCR Verify screen" +author = "PdfCraft contributors (generated by `cargo xtask screenshots`)" +source = "this repository" +licence = "MIT OR Apache-2.0" +licence_file = "LICENSE-MIT" +kind = "image" +usage = "README: OCR review. Shows only PdfCraft UI, its Lucide icons and a synthetic scanned page built from the embedded fonts, with a real recognition (the OCR models) loaded into the Verify screen" +sha256 = "ea7485b151e27ad3fd2a2dac079436ab11745d42032201a029bb20f819c6af8f" + [[asset]] path = "assets/icons/accessibility.svg" title = "Lucide icon \"accessibility\"" @@ -414,7 +425,7 @@ source = "https://github.com/lucide-icons/lucide (npm lucide-static 1.49.0, icon licence = "ISC AND MIT" licence_file = "assets/icons/LICENSE-lucide.txt" kind = "icon" -usage = "UI icon, embedded via crates/ui-egui/src/icon_data.rs" +usage = "UI icon, embedded via crates/ui-egui/src/icon_data.rs; drawn as PDF path data by crates/sign/src/status_layers.rs into displayed signature status layers" sha256 = "201e790f3a05c65b2c4b0f952c9b9e1f35cd1c5b21698b3f4be131883fe90bc8" [[asset]] @@ -1833,7 +1844,7 @@ source = "https://github.com/lucide-icons/lucide (npm lucide-static 1.49.0, icon licence = "ISC AND MIT" licence_file = "assets/icons/LICENSE-lucide.txt" kind = "icon" -usage = "UI icon, embedded via crates/ui-egui/src/icon_data.rs" +usage = "UI icon, embedded via crates/ui-egui/src/icon_data.rs; drawn as PDF path data by crates/sign/src/status_layers.rs into displayed signature status layers" sha256 = "55aa37e0b73e7f8cd906952dbdeb96283c6595ca64aba240a17f3455cb989114" [[asset]] @@ -1943,7 +1954,7 @@ source = "https://github.com/rsms/inter" licence = "OFL-1.1" licence_file = "assets/fonts/OFL-Inter.txt" kind = "font" -usage = "UI font, embedded in the app; demo PDF labels; slanted fallback glyphs in Fill & Sign typed signatures for characters Dancing Script lacks (Cyrillic, Greek), drawn as filled paths" +usage = "UI font, embedded in the app; demo PDF labels; slanted fallback glyphs in Fill & Sign typed signatures for characters Dancing Script lacks (Cyrillic, Greek), drawn as filled paths; embedded into displayed signature status captions beyond WinAnsi by crates/sign/src/status_layers.rs" sha256 = "40d692fce188e4471e2b3cba937be967878f631ad3ebbbdcd587687c7ebe0c82" [[asset]] @@ -2993,7 +3004,7 @@ source = "https://github.com/lucide-icons/lucide (npm lucide-static 1.49.0, icon licence = "ISC AND MIT" licence_file = "assets/icons/LICENSE-lucide.txt" kind = "icon" -usage = "UI icon, embedded via crates/ui-egui/src/icon_data.rs" +usage = "UI icon, embedded via crates/ui-egui/src/icon_data.rs; drawn as PDF path data by crates/sign/src/status_layers.rs into displayed signature status layers" sha256 = "ef1fec17d88794ba6c34c5cf63bdadbd234b3d4dffbcc3d55468b47e3f398472" [[asset]] @@ -3131,7 +3142,7 @@ source = "https://github.com/storytold/craft-fonts (pinned by commit in .github/ licence = "OFL-1.1" attribution = "https://github.com/storytold/craft-fonts/blob/main/ATTRIBUTION.md" kind = "font" -usage = "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" +usage = "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); status captions of named-layer signatures in Arabic, Japanese, Thai and Devanagari, drawn as filled outlines into the display copy by crates/sign/src/status_layers.rs; 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" [[asset]] path = "crates/sign/tests/data/x509-rsa-sha1.pdf" @@ -3200,6 +3211,17 @@ kind = "icon" usage = "UI icon, embedded via crates/ui-egui/src/icon_data.rs" sha256 = "d344d9f9222f6c1b698c0c82a753a2212d9bd7785f06c00cd6e4910fe2fee8f8" +[[asset]] +path = "assets/icons/a-large-small.svg" +title = "Lucide icon \"a-large-small\"" +author = "Lucide Contributors (portions Cole Bemis, Feather)" +source = "https://github.com/lucide-icons/lucide (npm lucide-static 1.49.0, icons/a-large-small.svg)" +licence = "ISC AND MIT" +licence_file = "assets/icons/LICENSE-lucide.txt" +kind = "icon" +usage = "UI icon, embedded via crates/ui-egui/src/widgets/icon_data.rs" +sha256 = "d4985fc71174d108e322c3b25cb6abe2837a115fe3f239a1918645db436743ec" + [[asset]] path = "assets/icons/move-horizontal.svg" title = "Lucide icon \"move-horizontal\"" diff --git a/CLAUDE.md b/CLAUDE.md index 5c7034b7a4..43c994c2d3 100644 --- a/CLAUDE.md +++ b/CLAUDE.md @@ -1,65 +1 @@ -# PdfCraft — instructions for agents - -PdfCraft is a clean-room, open-source, Rust-native PDF application targeting Adobe Acrobat Pro parity. It runs natively on macOS, Windows, Linux and FreeBSD, and on the web via WASM. It is the sibling of `../photocraft` (a Photoshop-class editor) and follows the same conventions. - -## Start every session here -1. Read `plan/STATUS.md`: the current milestone, the next unchecked task and any blockers. `ROADMAP.md` is the one-page summary (stage, numbers, progress log) and `docs/roadmap.md` the milestone table; at the end of every session update the milestone row and add a line to the ROADMAP.md progress log. - - Read `docs/gaps.md` (the ranked gaps: Acrobat interop, the open-issue backlog, the renderer and a fidelity harness, editing existing content, Pro workflows, 1.0 polish) and `docs/target-app-parity.md` (the numbers and how they are measured) before choosing work. Prefer the gaps over new P2/P3 features, and keep both documents true when things change (`docs/` progress docs carry a status line and a revision history). - - "Shipped" in `parity/` means "exists and tested", not "as good as Acrobat". Don't mark a feature shipped on a generic test, and say in its notes what is still missing. -2. Read that task in `plan/execution-plan.md` §3, the relevant section of `plan/architecture.md`, and the README of the crate you're touching. -3. Follow the **autonomous operation protocol** in `plan/execution-plan.md` §7 (orient → plan → implement + test → verify → record → commit). Don't stop to ask unless §7 lists the decision as the user's. - -`plan/` is gitignored (local-only, like PhotoCraft). The machine-readable parity checklist lives in `parity/` (committed). - -## Non-negotiables -- **Assets: read `AGENTS.md` §1 before adding or showing any icon, image, font or document.** No assets from Adobe products, ever. Only openly licensed or contributor-original assets are allowed, each with an entry in `ATTRIBUTION.toml`. `cargo xtask assets` enforces this. `AGENTS.md` overrides this file. -- **Fonts live in [storytold/craft-fonts](https://github.com/storytold/craft-fonts).** Never commit font files here (`AGENTS.md` §1.4). It is the optional build input `CRAFT_FONTS_DIR`: `git clone https://github.com/storytold/craft-fonts ../craft-fonts && CRAFT_FONTS_DIR=../craft-fonts cargo test --workspace` embeds the Japanese fonts (UI fallback, Japanese text in edited PDFs) and runs their tests, which otherwise skip. Code using `pdfcraft_fonts::CRAFT_FONTS` must work when it is empty. -- **Clean-room.** - - Never read, disassemble or copy anything inside the Acrobat bundle (names and listings only). **Never open `Contents/Resources/JavaScripts/`.** - - Behaviour comes from public docs, specs (ISO 32000-2, the Arlington model) and black-box observation (`plan/acrobat/`). - - Never copy GPL/AGPL code. MuPDF, Ghostscript, Poppler, veraPDF and DSS run only as external oracle processes. - - See `plan/README.md` §Clean-room and `plan/adr/0001`. -- **Privacy.** When observing Acrobat, use synthetic fixtures only. Never capture the Home view, recent files or account info. Capture by window id (`plan/acrobat/tools/`). Never commit Acrobat outputs, corpus files or personal data. -- **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 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. - - No indexing or slicing with input-derived positions (use `get`, and slice strings only at char boundaries). - - Use checked or saturating arithmetic on input-derived numbers, and guard against division by zero and NaN/inf casts. - - Cap allocations sized by input, and bound recursion with depth limits or seen-sets. - - Handle lock poisoning. - - No `unsafe` (`unsafe_code = "forbid"`). - - Every crash fix gets a synthetic regression test. See `AGENTS.md` §4. -- **Rust only** in the product and build (`xtask`). No handwritten JS/TS. -- **Time goes through `chrono`** (workspace dependency). Never hand-roll UTC/calendar conversion (days-to-date algorithms, leap-year math); a crate owns only its output format string. The one exception is range extension: past the years chrono can represent, shift the date by whole 400-year Gregorian cycles (146,097 days, after which the calendar repeats), let chrono compute the month and day, and add the cycles back to the year (splitting seconds into hours, minutes and seconds is plain arithmetic). -- **Review every update as you make it, at four zooms.** Not an end-of-task pass — a per-update habit, so a defect never gets built on. **Clause:** checked arithmetic, `get()` not `[i]`, char-boundary slicing, the right error through `?`, `<` against `<=`, the 1-based/0-based seam, capped allocations. **Function:** is it total — name an input that panics; walk empty, zero, max, malformed, cyclic; is the return type honest. **File/module:** two sources of truth, dead or duplicated code, is the public surface still smallest and the doc comment still true. **Project:** layering, wasm, undo/redo, save fidelity, encryption and permissions, a matching `automation` tool or registry entry, and whether a `parity/` status or note just became untrue. Scale the zoom to the change, and fix what a level turns up before widening. - - Tests mirror the zooms: property → unit → crate integration → end-to-end. - - **Prove a test fails before the fix by actually reverting the fix.** A test nobody has seen fail is not evidence. This has caught two worthless tests in this repo: one confinement test passed with path resolution switched off entirely, because the tools failed on a nonexistent document id before reaching the path. - - **Rebasing is a review step, not a mechanical one.** Read every hunk you resolve, and the auto-merged hunks in the files you touched too — `main` moves fast enough that a file can change by hundreds of lines under a branch. -- **External PRs are held to safety, security and completeness before style.** Provenance first (no Adobe-derived asset, no committed font, no copied GPL/AGPL code, behaviour from the spec and not from reading another implementation), then no new panic path or `unsafe`, then `--root` confinement on every path including ones reached by nested dispatch, opt-in-only MCP and control channel, no new outbound network, then a headless `automation` tool, tests at the right zoom and an honest `parity/` entry. Provenance is the part a contributor cannot be expected to know, and the only part that cannot be undone after merge. -- **Quality gates** before every commit: `cargo fmt --check`, clippy with `-D warnings`, the tests, `cargo xtask layers`, `cargo xtask assets`, and the wasm check once `xtask ci` exists (M0). - - New workspace crates must include `[lints] workspace = true` in `Cargo.toml` to inherit `[workspace.lints]`. Production crate roots must declare the required crate-level lint attributes before modules or other crate items; crate-level `//!` documentation may precede them. - - **Scope builds and tests to the crates you touched** — `cargo clippy -p -j 2 --all-targets` and `cargo test -p -j 2`, under a `timeout`. A full `--workspace` build has locked up a development machine's CPU; it is CI's job and CI runs it on every PR. Run the workspace sweep locally only when you have a reason to and the machine is free. -- **Check for existing work before starting a fix or feature.** Search the issues and PRs, open and closed, with `gh issue list -R storytold/pdfcraft --state all --search ""` and the same with `gh pr list` (try a few phrasings), and check whether a merged fix is already on `main` (`git merge-base --is-ancestor origin/main`). If one is, the report is likely from an older build: say so rather than fixing it again. If an open PR covers it, review or build on that PR instead of opening a competing one. If an issue exists, reference it in the PR (`Fixes #123`). -- **Commits and PRs:** `main` is the only integration branch and is **never pushed to directly**. Branch from an up-to-date `main` as `/` (`feat/`, `fix/`, `docs/`, `chore/`, `refactor/`), one task id per commit (e.g. `M1.4: xref stream reader`), commit only green states, and open a PR into `main` using `.github/pull_request_template.md`. Merge only when CI is green. - - **`main` moves fast enough that PRs rot.** It took 396 commits in the three days to 2026-10-12, and most open PRs are conflicting at any given time. Rebase your own branch the same day `main` moves under it, and ask the author to rebase theirs — never rewrite a contributor's branch. Conflict risk tracks how *contested* the files are, not how large the change is: tooling, tests and docs are nearly free, while `crates/fonts`, `ui-egui` and the i18n catalogues are where several people collide at once. - -## Running and looking at the app -- `cargo run -p pdfcraft -- ` opens the desktop app. -- `cargo run -p pdfcraft-cli -- run --script steps.json --root DIR` drives the engine headlessly through the automation tools (`pdfcraft-cli tools` lists them). Use it, together with `page_render`, to check engine changes. `pdfcraft-cli mcp` is the opt-in MCP server (AGENTS.md §3). -- `cargo xtask fuzz --time 300` mutation-fuzzes open/render/edit/save in child processes. Findings land in `fuzz-out/findings/` (git-ignored; never commit corpus-derived files). Turn every real finding into a small synthetic regression test before fixing it. -- `cargo xtask parity [--partial]` reports Acrobat-parity progress from `parity/acrobat-features.toml`. Update the entry when a feature ships. -- `cargo xtask demo-pdf` builds `dist/demo/pdfcraft-showcase.pdf` (needs Chrome) for visual checks. -- For UI work, **look at the result**. Either launch `pdfcraft --control FILE doc.pdf` and use `pdfcraft-cli ui --control FILE screenshot --out x.png` (plus `inspect`, `click`, `key`, `type`, `command`, `set`), or take a headless shot with `cargo run -p pdfcraft-ui-egui --example shot`. Compare against `plan/acrobat/02-ui-ux.md`. Control-channel tests use kittest (`crates/ui-egui/tests/control.rs`). -- Parallel agents: use a separate `CARGO_TARGET_DIR` per agent and separate git worktrees. - -## Current bootstrap debt (tracked in STATUS.md) -- `pdfcraft-render` renders through the `hayro` crate directly and inspects documents through `lopdf`. Both get replaced by `cos` / `model` / the DisplayList device (M1–M2, ADR-0004). - -## CI workflows -- Workflows in `.github/workflows/` call the shared workflows in [`storytold/craft-common-actions`](https://github.com/storytold/craft-common-actions) at `@main`, with their inputs and secrets. No other jobs: if no shared workflow does what's needed, it doesn't go here. -- Don't add or change CI in a feature or fix PR. If the existing workflows can't build or test a change, link an existing craft-common-actions issue or PR, or open a new issue, or a PR only for a small fix that is safe for every app and does not increase CI time. -- Some workflow files here still run their own jobs. Don't add to them. Moving a job into craft-common-actions is its own task, never part of another PR, and the job stays here until a shared workflow runs it. +@AGENTS.md diff --git a/Cargo.lock b/Cargo.lock index 573b215b7c..4526947945 100644 --- a/Cargo.lock +++ b/Cargo.lock @@ -143,6 +143,15 @@ dependencies = [ "zerocopy", ] +[[package]] +name = "aho-corasick" +version = "1.1.5" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "c982642fa9e8606056828ee9a8505737230110bb1099153c79efe865c59d12ba" +dependencies = [ + "memchr", +] + [[package]] name = "aligned-vec" version = "0.6.4" @@ -1303,6 +1312,26 @@ dependencies = [ "zip", ] +[[package]] +name = "craft-web-api" +version = "0.1.0" +source = "git+https://github.com/storytold/craft-libs?rev=fd5e2feff6ea25bed371a99cc732b3968d621505#fd5e2feff6ea25bed371a99cc732b3968d621505" +dependencies = [ + "js-sys", + "serde_json", + "wasm-bindgen", + "wasm-bindgen-futures", +] + +[[package]] +name = "craft-web-host" +version = "0.1.0" +source = "git+https://github.com/storytold/craft-libs?rev=fd5e2feff6ea25bed371a99cc732b3968d621505#fd5e2feff6ea25bed371a99cc732b3968d621505" +dependencies = [ + "wasm-bindgen", + "web-sys", +] + [[package]] name = "craft-winprint-gdi" version = "0.1.0" @@ -4236,7 +4265,6 @@ version = "0.18.1" dependencies = [ "pdfcraft-content", "pdfcraft-cos", - "pdfcraft-filters", "pdfcraft-fonts", "pdfcraft-model", "thiserror 2.0.21", @@ -4324,6 +4352,7 @@ version = "0.18.1" dependencies = [ "chrono", "hayro-syntax", + "js-sys", "pdfcraft-crypt", "pdfcraft-filters", "pdfcraft-oracle", @@ -4331,6 +4360,7 @@ dependencies = [ "proptest", "serde_json", "thiserror 2.0.21", + "wasm-bindgen", ] [[package]] @@ -4507,6 +4537,7 @@ version = "0.18.1" dependencies = [ "ocrs", "pdfcraft-fonts", + "png 0.18.1", "rten", "tempfile", "thiserror 2.0.21", @@ -4598,6 +4629,7 @@ dependencies = [ name = "pdfcraft-redact" version = "0.18.1" dependencies = [ + "aho-corasick", "pdfcraft-annot", "pdfcraft-content", "pdfcraft-cos", @@ -4606,8 +4638,11 @@ dependencies = [ "pdfcraft-fonts", "pdfcraft-forms", "pdfcraft-model", + "pdfcraft-render", "pdfcraft-testkit", "pdfcraft-xfa", + "regex", + "sha2 0.11.1", "thiserror 2.0.21", ] @@ -4652,9 +4687,11 @@ dependencies = [ "p521", "pbkdf2", "pdfcraft-annot", + "pdfcraft-content", "pdfcraft-cos", "pdfcraft-fonts", "pdfcraft-model", + "pdfcraft-testkit", "rc2", "ripemd", "rsa", @@ -4702,6 +4739,7 @@ dependencies = [ "pdfcraft-engine", "pdfcraft-fonts", "pdfcraft-model", + "pdfcraft-ocr", "pdfcraft-platform", "pdfcraft-render", "pdfcraft-xfa", @@ -4729,10 +4767,13 @@ dependencies = [ name = "pdfcraft-web" version = "0.18.1" dependencies = [ + "craft-web-api", + "craft-web-host", "eframe", "egui", "js-sys", "pdfcraft-ui-egui", + "serde_json", "wasm-bindgen-futures", "web-sys", ] @@ -5481,6 +5522,29 @@ dependencies = [ "bitflags 2.13.2", ] +[[package]] +name = "regex" +version = "1.13.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "f020237b6c8eed93db2e2cb53c00c60a8e1bc73da7d073199a1180401450218d" +dependencies = [ + "aho-corasick", + "memchr", + "regex-automata", + "regex-syntax", +] + +[[package]] +name = "regex-automata" +version = "0.4.18" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "ad8553b9b26413251cbf30e620595c7a41b3887f03da04579c0e6b0d6a06b4b2" +dependencies = [ + "aho-corasick", + "memchr", + "regex-syntax", +] + [[package]] name = "regex-syntax" version = "0.8.11" diff --git a/Cargo.toml b/Cargo.toml index bf6a4e3146..407e40040f 100644 --- a/Cargo.toml +++ b/Cargo.toml @@ -70,7 +70,11 @@ pdfcraft-prc-render = { path = "crates/prc-render", version = "0.18.1" } hayro = "0.7.1" hayro-syntax = "0.7.2" lopdf = "0.45" -flate2 = { version = "1.1", default-features = false, features = ["rust_backend"] } +# zlib-rs: miniz_oxide took about 1.7 µs for every fixed-Huffman block, empty or not +# (`pdfcraft_filters::FLATE_READ_WORK`). Other dependencies still build flate2's default +# miniz_oxide backend; flate2 prefers zlib-rs when both are built, as the Windows build already did +# through craft-update. `flate::tests::a_copy_from_before_the_start_is_damage` shows which runs. +flate2 = { version = "1.1", default-features = false, features = ["zlib-rs"] } weezl = "0.2" # CCITT Group 4 encoding (pdfcraft-filters); already in the tree through tiff. fax = "0.2.7" @@ -80,6 +84,9 @@ hayro-jbig2 = "0.3" # foundation thiserror = "2" +# Linear-time matching (no backtracking) for caller-supplied redaction patterns. `perf-dfa` gives +# the lazy-DFA cache that `RegexBuilder::dfa_size_limit` bounds (the limit is inert without it). +regex = { version = "1", default-features = false, features = ["std", "unicode", "perf-dfa"] } serde = { version = "1", features = ["derive", "rc"] } serde_json = "1" log = "0.4" diff --git a/README.md b/README.md index 3c1b67936a..f488d160cc 100644 --- a/README.md +++ b/README.md @@ -94,7 +94,7 @@ Real-world typography: world scripts, vertical Japanese, colour emoji, gradients ### Fearless -Every save appends your changes and leaves the original bytes untouched. Writes are atomic, undo runs deep, and nothing is lost if you close by mistake. +Ordinary saves append your changes and leave the original bytes untouched. Edits to damaged objects whose xref and header generations disagree use a full rewrite, keeping both accepted references connected to the same repaired object. Writes are atomic, undo runs deep, and nothing is lost if you close by mistake. @@ -253,6 +253,18 @@ Documents restricted by their author show a clear notice, and PdfCraft honours t +## Scan pages, then read the words back before trusting them + +**Scan & OCR ▸ Recognize text** turns a scan into searchable text — the current page, a range, or a folder of files written as searchable copies — with optional cleanup before reading (auto-rotate, deskew, denoise, binarize; word boxes map back to the original scan) and a second engine: an installed Tesseract joins the built-in one, merged per your strategy. A searchable result applies as one undoable step; the **Editable text** output opens the **OCR Verify screen** instead, where each word carries the engine's confidence as a colour, suspects are one keypress away, and corrections, a user dictionary and Re-OCR of a region or a page happen before Accept writes the new document. **Scan & OCR ▸ Correct recognized text** reviews any recognition there before it is applied. + +

+ The OCR Verify screen: a scanned note with each recognized word boxed in its confidence colour, the info strip reporting a 95% average confidence and one low-confidence word, and the confidence legend with its thresholds below +
+ The OCR Verify screen: words coloured by confidence — the legend spells the thresholds out — reviewed and corrected before anything is applied. +

+ +--- + ## Every tool, one keystroke away Press ⌘K to search every tool and command, or browse the **All tools** catalogue. Tools that are still in development are marked with the milestone that will ship them. diff --git a/ROADMAP.md b/ROADMAP.md index 00dd8fdee0..3d075c415d 100644 --- a/ROADMAP.md +++ b/ROADMAP.md @@ -3,6 +3,8 @@ > **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:** 2026-10-31 | **Last updated:** 2026-10-31 | **Change:** minor (M3/M4, #5330: Crop pages is directly available in the document quick toolbar; 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) @@ -21,10 +23,17 @@ > **Last reviewed:** 2026-10-23 · **Last updated:** 2026-10-23 · **Change:** minor (M2, PR #4172: extend on-screen CJK fallback to Combine thumbnails and figure previews; recognise FangSong and subset-prefixed Founder names; estimates unchanged) > **Last reviewed:** 2026-10-15 · **Last updated:** 2026-10-15 · **Change:** minor (typed small Edit font sizes and Fill & Sign text/date colour, #2444/#2496; estimates unchanged) +> **Last reviewed:** 2026-10-20 · **Last updated:** 2026-10-20 · **Change:** patch (M1, #1143: repaired aliases survive preflight, snapshots and normalized saves; retained materialized revisions report generation disagreements; estimates unchanged) + +> **Last reviewed:** 2026-10-18 · **Last updated:** 2026-10-18 · **Change:** minor (M1, #1143: explicit live xref/header generation repair policy and bounded diagnostics; estimates unchanged) + +> **Last reviewed:** 2026-10-15 · **Last updated:** 2026-10-15 · **Change:** minor (M1: refresh object-generation reference identity against current upstream; estimates unchanged) **Stage: alpha** · next: beta, ~25% (ready for real work 50% → 75%) and ~400–700 h away -> **Last reviewed:** 2026-10-29 | **Last updated:** 2026-10-29 | **Change:** minor (M7 #2517: a narrowed then widened paragraph keeps the typed spaces the wrap consumed, after save and reopen; estimates unchanged) +> **Last reviewed:** 2026-10-29 | **Last updated:** 2026-10-29 | **Change:** minor (M2: scans keep their strokes at screen size and are smoothed when zoomed; M7 #2517: a narrowed then widened paragraph keeps the typed spaces the wrap consumed, after save and reopen; estimates unchanged) +> **Last reviewed:** 2026-10-28 | **Last updated:** 2026-10-28 | **Change:** minor (M10, #4119 partial: Enhance scanned file cleans scanned pages in place: background removal, edge shadow removal, despeckle; estimates unchanged) > **Last reviewed:** 2026-10-27 | **Last updated:** 2026-10-27 | **Change:** minor (M10: OCR model downloads use verified ONNX pairs with legacy discovery fallback; estimates unchanged) +> **Last reviewed:** 2026-10-25 | **Last updated:** 2026-10-25 | **Change:** minor (web: same-document host mode on the canvas, `data-host="page"`; estimates unchanged) > **Last reviewed:** 2026-10-25 | **Last updated:** 2026-10-25 | **Change:** minor (M14 localization current state: Arabic logical catalog, explicit RTL label direction and mirrored stock chrome; native/browser RTL workflows unqualified. Native release Hans face via LXGW WenKai Lite; estimates unchanged) > **Last reviewed:** 2026-10-23 · **Last updated:** 2026-10-23 · **Change:** minor (M7, #2636 partial: pasting added text boxes and images in the engine and through `content_copy`; estimates unchanged) > **Last reviewed:** 2026-10-23 · **Last updated:** 2026-10-23 · **Change:** minor (M11: image optimization accounts for page-local UserUnit; estimates unchanged) @@ -222,7 +231,9 @@ Ranked; detail and the full milestone table in [docs/roadmap.md](docs/roadmap.md | 8 | 1.0 polish: performance, right-to-left, missing languages, keyboard-only (M14) | 55–95 | ## Progress log +- **2026-10-13 (M8, redact by regex):** `redact_mark` takes `regex` (caller expression, linear-time engine, length/size/nesting caps, empty-matching refused) with optional `validate` (luhn, mod97, iban). Headless only; issue #1886. +- **2026-10-28 (M10, #4119 partial):** Scan & OCR ▸ Enhance scanned file cleans scanned pages in place: background removal (level 0–100, as the camera clean-up), edge shadow removal (book gutters, copier borders) and despeckle. Each scan image is decoded, cleaned and written back into its own object at the same size and colour space (JPEG stays JPEG, others lossless, 1-bit stays 1-bit), so the OCR text layer, comments and links stay; one undo step, shared images once, unsupported images (CMYK, indexed, JPEG 2000, JBIG2, CCITT, broken data) reported. `page_enhance_scan` drives it headlessly. Not yet an option of Recognize text. Estimates unchanged. - **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. @@ -235,6 +246,8 @@ Ranked; detail and the full milestone table in [docs/roadmap.md](docs/roadmap.md - **2026-11-02 (M10, #5743):** macOS print jobs name their title and owner (`com.apple.print.JobInfo.PMJobName`, `PMJobOwner`), as the system print dialog does, because a Kyocera filter crashes on a job without them. Checked by a test and through `doc_print` against a stand-in `lp`; not yet on a physical printer. +- **2026-11-02 (M14, #5737, #5460):** Preferences can turn off the update check at start. It stays on by default, and Help ▸ Check for updates still asks. + - **2026-11-01 (M7, #5657):** Header/footer, watermark and background additions and replacements stage the complete call before committing. Synthetic later-page failures preserve exact incremental bytes, object count, dirty state and allocation cursor; success controls retain other marks and shared/inherited resources. Estimates unchanged. - **2026-11-01 (M14, #5572):** Preferences ▸ Documents and view sets how many recent files to keep, from 0 to 50 with 12 by default. At 0 Home has no Recent section and File ▸ Open Recent is disabled. The list is cut when Preferences closes, so the number can pass through 0 on its way to another. @@ -246,6 +259,7 @@ Ranked; detail and the full milestone table in [docs/roadmap.md](docs/roadmap.md - 2026-11-01: PR #2155 review follow-up preserves editor crops through group moves and keeps arranged artwork outside added-item streams; unsafe nested-tag extraction is refused. Image handles and flips follow page orientation, added images accept general transforms, and clipboard/text/Home/font-discovery edge cases have focused regressions. Candidate only; estimates unchanged. - 2026-11-01: PR #2155 maintainer edits remove redundant image/text helpers and add regressions for crop ownership, arrange scope/state fidelity, clipboard precedence, crop-drag bounds, and font scanning. Transform and Unicode-script tools complete the headless paths. +- **2026-10-31 (M3/M4, #5330):** The document quick toolbar offers Crop pages directly through the existing page.crop command, with the command’s assembly-permission check and an active-tool highlight. The existing crop, undo and headless page_set_box paths are unchanged. No toolbar customization or new shortcut. Estimates unchanged. - **2026-10-18 (M3, #1354, local candidate):** Integrated --two-paged with current main, retaining upstream modal/picker ownership and single-tab reuse. Native launch/opening/password regressions, negative checks against the old wrapper, visual inspection, formatting, strict scoped Clippy, layers, assets, parity and scoped WASM compilation pass. Three existing socket tests are unavailable in this workspace; one existing network test remains ignored. No push or GitHub merge; estimates unchanged. - **2026-10-31 (M2, PR #4172 review):** Added same-machine pixel oracles for GBK Song, Hei, Kai and FangSong, including all four subset-prefixed Founder aliases. Reference PDFs use explicit Unicode mappings and independently selected installed faces; font data and rasters remain in memory. All eight cases ran; wrong-glyph and wrong-family production mutations each failed the new assertion and were restored. Validation: 422 renderer unit tests, renderer all-target Clippy with -D warnings, formatting, layers/assets/parity and renderer WASM checks passed; existing optional-patch/WASM warnings and parity notes remain. Estimates unchanged. @@ -261,8 +275,10 @@ Ranked; detail and the full milestone table in [docs/roadmap.md](docs/roadmap.md - **2026-10-26 (M2, PR #4172):** Reconciled current main, preserving its Japanese serif/weight selection and both branches' progress records. Installed CJK viewer and preview fallback remains display-only; estimates unchanged. - **2026-10-29 (M7, #2517):** Widening a paragraph rejoins a wrap with the number of spaces that wrap consumed, including a typed run and none for a Chinese or Japanese word split. The count survives an incremental save and a full rewrite, and a width-only `text_edit` uses it. Estimates unchanged. +- **2026-10-29 (M2):** Scanned pages look like the paper again. An image that doesn't ask for /Interpolate was shrunk by nearest-neighbour (since #635), which kept one sample in N per axis, so the text of a 300 dpi scan at 100% lost most of its strokes; it is now area-averaged to whole device pixels (on a 13-page 300 dpi scan every sample at 96–192 dpi is within 1 of the exact area average; it was up to 255 off). Enlarged, an image of page-scan size is smoothed bilinearly, so a zoomed scan has no staircases; icons, QR codes and pixel art keep hard pixels. Estimates unchanged. - **2026-10-26 (M11, JBIG2 symbols):** Lossless JBIG2 now stores each distinct mark of a black-and-white image once, as a symbol, and places its exact copies, when that is smaller than the generic region: on six pages of rendered 300 dpi text 28% of the generic region's size and 17% of Group 4's, and the same bits back through two independent decoders (hayro-jbig2 and Poppler). Scans, whose letters are seldom identical, gain little until refinement coding; a dictionary shared between pages (`/JBIG2Globals`) is next. Estimates unchanged. - **2026-10-25 (M5, comment replies):** One reply can be deleted from the Comments panel without its thread. On the selected card each reply has its own "…" menu (Edit, Copy text, Delete); Delete takes that reply with its pop-up and the replies to it, as `comment_delete` already did headlessly, and the comment and its other replies stay. The card stays selected, and the panel's editor stays open, on what they were on though the delete moved it in `/Annots`. Undo and Redo close the editor, since either can move what it was open on. A locked reply can't be deleted. Estimates unchanged. +- **2026-10-25 (web, same-document host mode):** A page that loads the PdfCraft web module into its own document (no iframe) can opt into the host bridge with `data-host="page"` on the app's canvas — the exact value `page`; any other value keeps the normal app with downloads, unless a same-origin framed `?host=parent` selects the parent bridge (unframed or cross-origin, `?host=parent` also keeps the normal app). It is the `?host=parent` bridge with the transport swapped: the same five messages travel as non-bubbling `CustomEvent`s on the canvas (`detail` holds the parent messages' fields without `type`; the host answers with a `pdfcraft:open` event), so saves reach the host instead of downloading and dirty and start-up-failure reporting are unchanged. Unit tests cover the opt-in rule; no parity or estimate changes. - **2026-10-24 (M10, #4158 partial):** Word, HTML, RTF and PowerPoint export keep a block that continues another on its line (an italic case name, a link, a superscript) as a run in its own style inside that paragraph, with the source's word space, instead of a paragraph of its own. Style changes that wrap onto the next line still split paragraphs (the reading blocks keep style boundaries). Estimates unchanged. - **2026-10-24 (M3, window move on Wayland, #3970 follow-up):** After a move or resize by PdfCraft's own title bar or edges, the button release given back to egui goes before the pointer leaving the window, so hover no longer sticks at the old place until the pointer moves. Found by CodeRabbit in review of #3970; a unit test covers it. Estimates unchanged. - **2026-10-24 (M14, #4253):** The annotation quick bar remembers Keep tool selected across restarts, including unpinning. Old and malformed settings keep safe defaults; the opt-in UI control channel reads and changes the same preference. Estimates unchanged. @@ -291,6 +307,11 @@ Ranked; detail and the full milestone table in [docs/roadmap.md](docs/roadmap.md Estimates unchanged. - **2026-10-21 (M3, window resize and move on Wayland):** With PdfCraft's own title bar on GNOME/Wayland, a second resize by a window edge, or a second move by the empty tab strip, works straight after the first; it waited for a click inside the window, because the compositor keeps the button's release from egui. A unit test covers the release given back; checked by hand in a test build. Estimates unchanged. - **2026-10-24 (M5, move preview):** A comment being moved is drawn where it goes while it is dragged (a rectangle or oval showed only its blue frame): the comment is rendered alone once as the drag starts and laid over the page, which shows it where it was until the move is applied. Engine `Document::comment_layer`; synthetic engine and UI regressions. Estimates unchanged. +- **2026-10-24 (M5, border shape):** Text boxes and Fill & Sign's typed text take an oval or a circle for their border (Comment Properties ▸ Border shape, Fill & Sign's toolbar): the text box keeps its place and the shape goes around it, the text centred, a circle snug around the text (its box no wider than the text needs); stored as /RD and /PCBorderShape and drawn in the appearance. comment_add / comment_edit / fill_sign_add `border_shape`. One new label in every catalog. Synthetic annot, UI and automation regressions. Estimates unchanged. +- **2026-10-24 (M5, Escape in Fill & Sign):** Escape leaves a Fill & Sign tool as it leaves a comment tool: the first press closes the open type box, the next goes back to Select, so the Text tool no longer opens a box at every click with no way out by the keyboard. A synthetic UI regression covers the Text and Checkmark tools. Estimates unchanged. +- **2026-10-23 (M5, ortho):** Shift while drawing holds a line or arrow level or plumb, whichever is nearer (a CAD drawing's ortho mode), and each new side of connected lines, a polygon or a cloud from the corner before; dragging an end or corner with Shift is held the same way (it turned to 45° steps). `measure::snap::ortho`; `comment_add ortho`. Estimates unchanged. +- **2026-10-24 (M3, arrow keys on a wide page):** → / ← scroll a page wider than the window (a plan zoomed in) sideways a line at a time and turn the page at its edge, as ↓ / ↑ do in single-page view; ⌘→ / ⌘← turn it at once, and a page that fits across turns as before (#185). A synthetic viewer regression covers both. Estimates unchanged. +- **2026-10-24 (M5, part opacity):** Comment Properties sets a text box's text, border and fill, and a shape's line and fill, each at an opacity of its own (a see-through fill with an opaque line on a plan); stored as /CA, /ca (PDF 2.0) and /PCTextOpacity and drawn with separate graphics states, so other viewers show it. Make Properties Default and the settings carry it; comment_add / comment_edit `fill_opacity`, `text_opacity`. Four new labels in every catalog. Synthetic annot, UI and automation regressions. Estimates unchanged. - **2026-10-22 (M4, #3916 partial):** Document edits and Undo/Redo cancel an Organize page drag. Pointer-release regressions check exact page order and save/reopen. - **2026-10-22 (M10, #3752 paper):** CUPS jobs ask for the chosen paper in every size. The 13 sizes the Print dialog sent no paper for (A6, A0–A2, ARCH, ANSI C–E) use PWG 5101.1 names, checked against a synthetic PPD with `cupsfilter`, and `doc_print` to a printer sends the paper too. The macOS tray half (Auto Select instead of the PPD's default tray) is a craft-print change that needs a pin bump here. Estimates unchanged. @@ -298,6 +319,7 @@ Ranked; detail and the full milestone table in [docs/roadmap.md](docs/roadmap.md - **2026-10-22 (M14, macOS association recovery candidate):** Successful desktop open/save/sign can queue recovery of an existing per-file binding to the running PDFCraft bundle through NSWorkspace. Metadata-only watcher changes retain undo and avoid false overwrite prompts; real same-length/same-mtime edits remain protected. Rebased on 0.12.0 and reuses #3042's shared atomic metadata preservation; the bounded recovery parser does not narrow save limits. Prior native Preview TEST-signature and Finder workflows passed on macOS 27.0.1; other versions remain unqualified. Estimates unchanged. - **2026-10-13 (M7, free image rotation):** A selected page image has a rotate knob (Shift: 15 degree steps) and `image_edit` a `rotate_by` action; the angle is written as one undoable `cm`. Snapping to page edges while moving is in #1740; resize snapping is not done. Estimates unchanged. +- **2026-10-20 (M9 #79 review, M2, M8):** text extraction reads a marked-content /ActualText that marks no glyph where it paints (paths and images, cut to what is visible, along the direction they are drawn), so words drawn as outlines can be found, copied and exported; OCR and scan field detection still count such a page as having no text of its own. Redaction strips /ActualText, /Alt, /E and /T from inline marked content around paint it clips, as it already did around paint it removed, so a partly redacted outlined word leaves no name in the file. Named-layer recognition also needs the layer form to draw n1 and n3. Estimates unchanged. - **2026-10-20 (M4, initial view):** Window and interface options read indirect boolean ViewerPreferences values. Synthetic regressions cover true/false, direct/indirect preference dictionaries and save/reopen; malformed entries retain false defaults. Estimates unchanged. - **2026-10-20 (M3, #3535):** Escape with a menu open closes the menu and keeps the text selection; the next Escape clears it, as before. One keypress used to do both. A synthetic UI regression checks it. Estimates unchanged. - **2026-10-16 (M3, close prompt keyboard):** The "Save changes?" prompt opens with Save chosen (Enter saves, as before) and the arrow keys and Tab / Shift+Tab move the choice to Cancel or Don't save, shown with a focus ring; Enter or Space press the chosen button and Escape still cancels. Before, Enter always saved whatever was Tab-focused. Estimates unchanged. @@ -312,6 +334,7 @@ Ranked; detail and the full milestone table in [docs/roadmap.md](docs/roadmap.md - **2026-10-20 (M11, #3507):** Image merging keeps trailing comments, split operands and graphics state across content streams. Synthetic tool tests check saved text, rendered regions and exact image rows. - **2026-10-17 (M8, gap 6, #2662):** A filled cover over a long line counts when it hides half of any one word, not only 40% of the line's words or box, so a black box over one number in a long line — or an unapplied redaction mark over it — no longer audits clean while the number is still extractable; a sliver under half of every word it touches and under 40% of the line is still not flagged +- **2026-10-13 (M10, OCR review, batch and two engines):** Scan & OCR gains a review step, a second engine and Unicode output. Recognition can clean the raster first (opt-in auto-rotate, deskew, denoise, binarize; word boxes map back to the scan) and read with the built-in ocrs engine, an installed tesseract program run as a fenced external process (a validated location that fails closed instead of falling back to the PATH, allow-listed languages, a private temp directory, timeout and output caps), or both: Automatic asks tesseract when the ocrs reading is weak or of unknown confidence, and a ROVER merge keeps the more confident word (an unscored ocrs word yields only to a tesseract word of 70 or more). The OCR Verify screen (Scan & OCR ▸ Correct recognized text) reviews a recognition before it is applied: confidence-coloured word boxes, corrections, a per-language user dictionary (a plain-text file in the preferences folder, so a word added from any document stays on disk after it closes), Re-OCR of a page or a region, Accept/Reject per page or whole. Pages accepted one by one each apply once; a region re-read moves the review marks of the words it keeps, and a whole-page re-read clears that page's marks (undoable in the panel). Output is searchable (an invisible layer, one undo step) or a NEW editable document of visible text. Words beyond WinAnsi are drawn in Type3 faces from craft-fonts with a ToUnicode map in the editable output (characters no bundled face has appear as '?'); the searchable layer writes them as Type3 fonts with empty character programs and a ToUnicode map, so extraction reads them back with no fonts and no substitutions; redaction removes that layer like any other text (tests in pdfcraft-redact; the end-to-end engine test needs the craft-fonts build input and is skipped without it). Batch runs skip pages that already have text unless forced, and skip whole files that have text only with the opt-in skip-files flag (off by default; Force OCR overrides both); they refuse two inputs of the same file name and existing outputs before reading anything, and report low-confidence pages at the settings' threshold. Headless: ocr_recognize (engine, strategy, preprocessing, region; the editable output goes to an `out` that must not exist yet, and `out` is refused for a searchable run), ocr_words, ocr_review_apply, ocr_dictionary, ocr_status and ocr_recognize_files. All 21 interface catalogs carry the new strings; the Lithuanian ones were added without native review. Reading with every cleaning step off passes the render through untouched, as on main (the 300 dpi normalization runs only when a cleaning step is on: enlarging a 72 dpi render 4x on its own made the models read "due: €250" as "ue: ?250"). Still missing: the deep scan clean-up options (descreen, background and edge-shadow removal), scan images in the editable output, matching the scanned typeface, and recognition quality beyond the tested English set. - **2026-10-13 (M10, #1757):** Office export keeps each dotted-leader contents entry in one paragraph, with its page number, instead of inferring table cells from its separate text objects. - **2026-10-22 (M6, calculation scripts):** The Calculate tab and a rename read simplified field notation only from a comment, where Acrobat writes it: a string that spells `BVCALC … EVCALC` is no longer taken for the notation, or rewritten by a rename. A `/` after the condition of `if`, `while`, `for` or `with` starts a regular expression, so a rename no longer rewrites a name inside one, and a quote inside one no longer hides the `getField` calls after it. Both found in review of #3550. A `//` comment ends at `\r`, U+2028 or U+2029 as well as `\n`, so in a script with `\r` line endings the code after one is no longer hidden from a rename, or taken for the notation. Estimates unchanged. - **2026-10-20 (M6, calculation order page):** Prepare a form ▸ Calculation order, a page of its own, lists the calculated fields in the order they calculate with their formulas and values, moved with Up/Down arrows (as Acrobat's Set Field Calculation Order), Alt+↑/↓ or by dragging. A card says what is wrong with the order and holds Fix order; a loop has a card of its own that opens one of its formulas. On the page, each calculated field shows its step, and arrows show what the field in focus reads and what reads it. Estimates unchanged. @@ -322,6 +345,7 @@ Ranked; detail and the full milestone table in [docs/roadmap.md](docs/roadmap.md - **2026-10-20 (M12, #3673):** Character encoding accepts Identity-H/V fonts with Adobe CJK collections and recognizes predefined non-Identity CMaps independently. Unknown CMaps and foreign registries remain refused; synthetic checker and read-only automation regressions passed after failing before the fix. Per-glyph mapping validation and embedded-font extraction remain separate. Estimates unchanged. - **2026-10-19 (M6, renames keep formulas):** Renaming a field renames it in every calculation that reads it, in the same undo step: `AFSimple_Calculate` field lists, simplified field notation (the comment and the JavaScript after it) and `getField` calls naming it in one string literal; the rest of each script is kept as written. A sum used to drop the renamed field, notation read it as 0 and a script kept a stale value. Field Properties says how many formulas changed and `form_set_props` lists them as `formulas_updated`. Names built at run time and other events' scripts are not rewritten. Estimates unchanged. - **2026-10-19 (M6, text field table):** Prepare a form ▸ Text field table drags out an area and adds rows and columns of named text fields as one undoable edit, laid out on the page as displayed, with a live preview, per-column name patterns and widths, and refusal before anything is added when a cell would be too small or a name taken; `form_add_field_table` does the same headlessly. `form.multiple-copies` is partial: copying an existing field into a grid is still missing. Estimates unchanged. +- **2026-10-17 (research):** Added a [PDF workflow research reference](docs/research/pdf-workflows/README.md): dated public-source locators, 20 workflow research domains, a pinned feature mapping and interaction evidence. Reference documentation; no feature statuses, milestone priorities or estimates changed. - **2026-10-16 (M7, #2516):** A paragraph number from `text_paragraphs` keeps naming the paragraph it listed after edits regroup the page: `text_edit`, `text_edit_layout` and `page_render`'s `hide_text_block` find it again by its text and box, and refuse one that was merged into a neighbour (the edited paragraph included) instead of rewriting the paragraph that took its number (`stale_paragraphs` lists the numbers gone). The inline editor's switch-paragraph click holds the same key. No stable identity across save and reopen yet (#2508). - **2026-10-19 (M7, #3591):** A background added to a page that already has one is painted over the old one instead of going under it and staying hidden. Behind the content, backgrounds come first, in the order added, and then behind-content watermarks, so a watermark added after a background no longer disappears. Synthetic regressions in `crates/edit` check the order. Estimates unchanged. @@ -333,9 +357,15 @@ Ranked; detail and the full milestone table in [docs/roadmap.md](docs/roadmap.md - **2026-10-20 (M3, #3541/#3620):** Comment hover follows the individual marked lines instead of the enclosing multiline rectangle, and overlapping comments follow paint order. Synthetic UI regressions cover all four text-markup kinds, page/view rotations, neighboring highlights, legacy rectangle fallback and unchanged PDF bytes. Estimates unchanged. - **2026-10-20 (M10, #3532 partial):** Vector printing retains existing widget artwork when its appearance lacks Subtype. A print-owned copy adds Form dispatch metadata. The source stream and all explicit subtypes stay unchanged. Synthetic source/output raster checks cover resources, selected/shared appearances, placement, flags and content modes. Appearance regeneration and physical printer validation remain outside this fix. Estimates unchanged. +- **2026-10-20 (M5, several comments):** Comment Properties opened on one of several selected comments, the context menu's Colour and the quick bar's colour change all of them as one undo step, each where the property applies (a font size to text boxes, a fill to shapes, a width to lines and shapes); one that stays locked keeps its look. Copied Fill & Sign ticks, crosses, dots and lines hang on the pointer as themselves rather than as empty boxes, and copied text boxes show their text (`FillMark::strokes` is shared by the appearance and the outline). Estimates unchanged. +- **2026-10-19 (M5, comments between documents):** Comments copy and paste, within and between documents: ⌘C with comments selected copies them as XFDF (each with its replies) to the app's and the system clipboard, ⌘V / Edit ▸ Paste comments / the page menu pastes them onto the current page as new comments under names of their own (`Edit::PasteComments`, `pdfcraft_xfdf::import_comments` with a target page and fresh names, so nothing is replaced and pasting twice gives two sets; `export_xfdf_comments` writes a selection with its replies). Several comments select at once (⌘-click, ⇧-click, on the page and in the panel); Delete removes them as one step and a drag moves them together. Connected lines, polygons and clouds finish from the right-click menu's Complete (Undo last point, Cancel drawing beside it), as other editors do. Tools `comments_copy` / `comments_paste`. Estimates unchanged. - **2026-10-20 (M5, arrow keys move comments):** With a comment selected, the arrow keys move it a screen pixel and ⌘/Ctrl or Shift and an arrow ten, instead of scrolling the view or turning the page; up is up on screen at any zoom and rotation, and each press is one undo step. Text markup and locked comments stay put. Estimates unchanged. +- **2026-10-20 (M8, #3647):** Apply prunes fully removed tiling patterns, then checks retained pattern resources for text, images and unreadable content before reporting success. Shared patterns, Form-owned and inherited patterns, and cells kept by another page cause an atomic refusal when safe removal cannot be shown. Synthetic saved-file and automation regressions cover refusal, preserved marks and undo, and vector-only controls. Estimates unchanged. + +- **2026-10-20 (M1, PR #1143 review):** Repair-aware dictionary/preflight edits and snapshot restoration preserve both accepted generations of a damaged live slot. Such edits use the existing full-save fallback; classic and packed rewrites coalesce aliases so page-tree parent links retain one object identity. Explicit generation replacement remains single-generation. Materialized xref diagnostics inspect retained primary and hybrid rows before folding, retaining the 256-object cap plus summary and discarding abandoned-index notes. Synthetic red/green controls cover preflight, undo restoration, equal values, explicit narrowing, encryption packing and four save variants. Estimates unchanged. + - **2026-10-19 (M14, #3373):** The main menu and its long submenus scroll in short windows, keeping their commands reachable. Estimates unchanged. - **2026-10-19 (M3, #3387):** Save-prompt shortcuts yield to later consent and utility dialogs; a synthetic UI regression checks that an edited document stays open. Estimates unchanged. @@ -380,6 +410,8 @@ Ranked; detail and the full milestone table in [docs/roadmap.md](docs/roadmap.md - **2026-10-16 (M10, #1201 partial):** Lossless image export applies each component's Decode pair. Indexed values round and clip before palette lookup. Color-key masks keep raw samples. The existing 16-bit precision limit remains. JPEG and mask Decode, ICC transforms, and calibrated colors remain outside this fix. Estimates unchanged. - **2026-10-16 (M3, #2739):** Wrapped revision buttons stay above Binding in Document Properties. A synthetic regression checks control bounds and opens a saved revision at two viewport widths. Estimates unchanged. - **2026-10-19 (M7, tracked text):** Editable paragraphs and object labels distinguish repeated glyph tracking from word gaps in TJ arrays and separately positioned glyphs. Synthetic regressions cover character spacing, horizontal scaling, rotated baselines, larger word gaps, and rows of one-glyph words or cells (inferred tracking is capped at half an em, so `a b c` and digit or Y/N columns keep their spaces). Estimates unchanged. +- **2026-10-16 (M9, #79):** a signature appearance that follows the named-layer convention (its /N draws one Form that holds and draws n1 and n3) shows the signature's real state: n1, n3 and n4 are redrawn in the display copy with the panel's icons and a caption in the interface language (Helvetica; else shaped in embedded Inter, or in a craft-fonts face for Arabic, Japanese and Telugu; else English, as Chinese always is). Exports, both print modes and the CLI's render show the redrawn state; saves never do. Every signature keeps its badge, since a document can clip or cover its own layers. Estimates unchanged. +- **2026-10-16 (M9):** the page validation overlay moves to the widget's bottom-right corner as it lies on the page (so it turns with the page and the view) and takes a quarter of the widget's shorter side, at most 48 screen points, so it annotates the signer's artwork from a corner instead of covering the middle of it; a field too small for a legible mark keeps its outline, a rectangle the screen cannot place is not drawn at all, and the whole widget answers the pointer. Estimates unchanged. - **2026-10-16 (M5, #2669, item 5):** The Comments panel groups replies by name and counts all page roots once per frame. Estimates unchanged. - **2026-10-16 (M7, #2140):** Header & footer (and Bates numbering, which uses the same dialog) can shrink the page content so the header and footer don't cover it: the original content is scaled evenly into the band they leave free, centred across, also on rotated pages; Remove and Update take the scaling away, and margins that leave no room are refused. Dialog checkbox with a preview of the band, `shrink` on `doc_header_footer`, all catalogs. Annotations and added text and images are not moved yet. Estimates unchanged. - **2026-10-20 (M14, Spanish catalog gaps):** `es.tsv` gains the 143 `(context, English)` keys the other catalogs carried and it was missing, so Spanish covers the whole bundled key union like Lithuanian and Vietnamese: calendar months and weekdays, the `certificate` context, X.509 key usages, signature-revision and digital-ID lines, password validation, eight plural messages, the combine-from-folder strings, the rendering and stale-file notices and the shortcut-spelled tooltips. Counts in `localization-parity.md` re-measured against the current union (`vi` restated against it for the same reason). Status stays `partial`: no translated help, and OS details stay outside the catalog. Estimates unchanged. @@ -399,6 +431,8 @@ Ranked; detail and the full milestone table in [docs/roadmap.md](docs/roadmap.md - **2026-10-15 (community, M6, #2608):** In Prepare a form the selected field moves with the arrow keys: a point per press, ten with Shift, as the object nudge and dragging it do. Each press is one undo step ("Change field properties"), and the keys no longer turn the page while a field is selected. Estimates unchanged. - **2026-10-15 (M3, closable community card):** The ArtCraft community card on Home has a close button that hides it for the rest of the run; it returns on the next launch, and its links stay in the top bar's Discord button and the Help menu. A UI regression covers closing and the fresh-launch default. Estimates unchanged. - **2026-10-13 (community, M3, #1569 review):** Pixel-only Wayland wheel, wheel-tilt and continuous input use standalone moved events, so Ctrl zoom does not remain latched after the modifier is released (#991); vendored winit patch (13), with a policy test. Estimates unchanged. +- **2026-10-18 (M1, PR #1143 repair policy):** A live in-file reference resolves when its generation matches the xref row or a same-number header at that indexed offset. Neither-match and free slots remain null, including when old object bytes remain. Opening records bounded xref/header disagreements without parsing object bodies or expanding compact xref rows. Synthetic controls cover read order, clones, overlays, dictionary edits, full classic/packed saves and an independent reader of incremental output. **Correction to the 2026-10-15 note below:** its async-opening-test sentence was not evidenced by this COS change; no fresh async-opening or GUI validation is claimed. The full-reference stream-length recursion key is defensive hardening, not an independently isolated regression fix. Estimates unchanged. +- **2026-10-15 (M1, PR #1143 refresh):** COS reference lookups and full saves distinguish complete object references, so stale generations cannot expose replacement content. Snapshot restoration also keeps edits to objects with nonzero generations before incremental saves. Synthetic regressions cover caches, overlays, snapshots, stream lengths and classic/packed saves. Current upstream async-opening test corrections are included. Estimates unchanged. - **2026-10-15 (M14, #2383 candidate):** Device-limit requests now clamp unsupported maxima and minimum alignments before enabling the adapter's full 2D texture extent. This addresses the reported V3D request of 16 shader variables on an adapter supporting 15. Synthetic regressions fail before the clamp and pass afterward, along with the existing HiDPI case and Windows GPU-required application tests. Raspberry Pi startup remains unverified; milestone and overall estimates are unchanged. - **2026-10-12 (M6):** XFDF field import and data-file extraction join all text nodes in a value, preserving text after XML comments and processing instructions. Synthetic regressions cover Unicode, CDATA, empty values and PDF save/reopen. Estimates unchanged. - **2026-10-12 (M7, picture right-click menu):** The Edit text & images menu of a picture gains Cut Image, Redact Image (a redaction mark over the picture, applied from Redact a PDF), Create Link… and Recognize Text… (for that page), in all 21 catalogs. The menu was drawn only while the pointer was over the picture, so its items outside the picture (most of a logo's menu, and Delete below a page) could not be clicked; an open menu now stays drawn. Still missing from Acrobat's menu: Arrange (bring to front, send backward), Remove crop, Draw freehand and Edit image using… (opening an external editor). @@ -766,6 +800,7 @@ Newest first: the date, what moved, and the new overall estimate. | 2026-11-01 | patch | M7 #5657: header/footer, watermark and background operations commit all selected pages together; later-page errors preserve marks, content, shared/inherited resources and pending edits; estimates unchanged. | | 2026-10-28 | patch | M2, PR #4172: integrate main 5af10276 and retain both roadmap histories; viewer-only CJK and print/output font policies and estimates unchanged. | | 2026-10-27 | minor | M10: OCR stages SHA-256-verified ONNX models after the upstream RTEN URL brownout; discovery prefers a complete ONNX pair per directory, falls back to a complete RTEN pair, and never mixes formats or directories; language/web limits and estimates unchanged. | +| 2026-10-20 | minor | M9 #79 review, M2, M8: /ActualText that marks no glyph extracts where it paints, as far as it is visible; redaction strips /ActualText around paint it clips; named-layer recognition needs the layer form to draw n1 and n3. Estimates unchanged. | | 2026-10-23 | minor | M8, #3205 follow-up: phone-pattern redaction includes the +39 country code on labelled Italian geographic numbers with a slash; dates, protocol identifiers and whole-run guards remain. Estimates unchanged. | | 2026-10-23 | minor | M11: image downsampling measures physical resolution after page-local UserUnit scaling, including shared nested forms; synthetic measurement and optimization regressions. Estimates unchanged. | | 2026-10-23 | minor | M10: Word table cells use the grid columns they span, including cells after a merged cell; synthetic export regression and CLI reproduction. Estimates unchanged. | @@ -777,8 +812,11 @@ Newest first: the date, what moved, and the new overall estimate. | 2026-10-20 | minor | M6, #3502: form detection preserves comments across content streams; estimates unchanged. | | 2026-10-20 | minor | M10, #3532 partial: vector printing retains existing appearances with absent Subtype; estimates unchanged. | | 2026-10-20 | minor | M11 #3507: image merging preserves comments and state across content streams. Estimates unchanged. | +| 2026-10-18 | minor | M1, #1143: a live reference may match the xref generation or a same-number header at its indexed offset; neither-match and free slots remain null. Bounded repair diagnostics and synthetic cache, free-slot, edit and classic/packed save regressions; estimates unchanged. | | 2026-10-18 | minor | M5, PR #1971: nested source `/Page` and `/Pages` dictionaries export as null without traversing page content or the page tree. Synthetic saved/reopened three-page regression retains unrelated metadata and aliases. FDF import semantics, copied-graph limits and estimates unchanged. | | 2026-10-15 | minor | M5: budget retained FDF entries before cloning; discovery keeps lazy array owners and annotation positions, with alias/cache-eviction stress fixtures. Limits cover the copied graph; source parsing/page discovery retain existing COS/parser limits, with no total source-memory bound. FDF import semantics and estimates unchanged. | +| 2026-10-16 | minor | M9 #79: named-layer signature appearances show the signature's real state in the display copy, exports and both print modes, never in saves; captions follow the interface language. Estimates unchanged. | +| 2026-10-16 | minor | M9: the page validation overlay moves to the widget's bottom-right corner as it lies on the page and stops growing past 48 screen points, so it annotates the signer's artwork from a corner instead of covering the middle of it; a field under 32 screen points keeps its outline. Estimates unchanged. | | 2026-10-15 | minor | M7: the Edit text caret is as tall as the row it is on in a region with several sizes; estimates unchanged. | | 2026-10-18 | minor | M4, PR #1919 review: repeated page indices apply each rotation to the latest page-local value, preserving indirect/inherited angles. Synthetic adjacent/interleaved duplicates retain siblings and page contents through incremental and full saves. Estimates unchanged. | | 2026-10-18 | minor | M3, #3149: page replacement cancels render demand collected for the previous geometry; all viewer raster upload paths reject empty or oversized textures before cache eviction. Synthetic regressions reproduce the reported 1880×2350 upload at a 2048 limit, retain cached images and unsaved edits, and resume bounded backdrops and tiles. Estimates unchanged. | @@ -787,6 +825,7 @@ Newest first: the date, what moved, and the new overall estimate. | 2026-10-14 | minor | M1: raw-deflate fallback preserves decoding-limit errors in strict and tolerant decoding; synthetic filter and COS stream regressions. Estimates unchanged. | | 2026-10-16 | minor | M14: Czech catalog completed (2,674 entries) and "tag" terminology unified. Estimates unchanged. | | 2026-10-13 | minor | M9: separate page validation overlays preserve signature artwork, and snapshot tabs reuse instead of multiplying; baked captions remain unchanged (#79 open); estimates unchanged | +| 2026-10-15 | minor | M1: refresh object-generation reference identity, retaining current upstream progress and regression tests. Estimates unchanged. | | 2026-10-16 | minor | M10 #1201 partial: lossless image export applies component Decode pairs and Indexed mapping. Estimates unchanged. | | 2026-10-15 | minor | M6: CSV export and spreadsheet merging quote tabs, and import distinguishes quoted tabs from TSV delimiters without changing field identities. Estimates unchanged. | | 2026-10-13 | minor | M4: rotation queries and edits resolve indirect page-tree values; inherited, negative and large rotations verified through both saves. Estimates unchanged. | diff --git a/apps/pdfcraft-cli/src/commands.rs b/apps/pdfcraft-cli/src/commands.rs index 9d0b2057f0..3118c901b4 100644 --- a/apps/pdfcraft-cli/src/commands.rs +++ b/apps/pdfcraft-cli/src/commands.rs @@ -366,8 +366,9 @@ pub(crate) fn render(args: &[String]) -> Result<(), CliError> { Some("pam") => None, _ => return Err(format!("render: --out {out}: use a .png, .jpg, .tif or .pam name").into()), }; - // The app renders a display copy that draws comments missing their /AP streams; the CLI - // must agree with it (and with independent viewers), while keeping the file it reads intact. + // The app renders a display copy that draws comments missing their /AP streams and the state + // of named-layer signatures (here with no trusted certificates); the CLI must agree with it + // (and with independent viewers), while keeping the file it reads intact. let bytes = read(path)?; let password = flag(args, "--password"); // The renderer takes only the user password of R2–R4 files; `Session::open` and the display diff --git a/apps/pdfcraft-cli/tests/it/batch_exit.rs b/apps/pdfcraft-cli/tests/it/batch_exit.rs new file mode 100644 index 0000000000..6dfb9f61e9 --- /dev/null +++ b/apps/pdfcraft-cli/tests/it/batch_exit.rs @@ -0,0 +1,111 @@ +//! The exit codes the CLI has today: `ExitCode::SUCCESS` (0) or `ExitCode::FAILURE` (1). +//! +//! Pinned here so that the exit-code contract is a visible, reviewed change when it comes: a +//! failed file, an outside-root path and a usage error all exit 1 today. + +use serde_json::Value; +use std::path::{Path, PathBuf}; +use std::process::{Command, Output}; + +const BIN: &str = env!("CARGO_BIN_EXE_pdfcraft-cli"); + +/// A fresh folder for one test, so the tests can run in parallel and leave nothing behind. +fn workdir(name: &str) -> PathBuf { + let dir = std::env::temp_dir().join(format!("pdfcraft-cli-exit-{}-{name}", std::process::id())); + let _ = std::fs::remove_dir_all(&dir); + std::fs::create_dir_all(&dir).unwrap(); + dir +} + +/// `batch` with `args`, run from the working directory `dir`. +fn batch(dir: &Path, args: &[&str]) -> Output { + Command::new(BIN).current_dir(dir).arg("batch").args(args).output().unwrap() +} + +/// `run --script --report` from the working directory `dir`: one JSON document for the run. +fn run_report(dir: &Path, script: &Path) -> Output { + Command::new(BIN).current_dir(dir).args(["run", "--script"]).arg(script).arg("--report").output().unwrap() +} + +/// The one JSON document a command prints on stdout. +fn reported(output: &Output) -> Value { + serde_json::from_slice(&output.stdout).unwrap() +} + +#[test] +fn batch_exits_0_when_every_file_succeeds() { + let dir = workdir("batch-ok"); + std::fs::write(dir.join("page.txt"), "Exit code page").unwrap(); + let output = batch(&dir, &["page.txt", "--steps", "convert", "--out-dir", "out"]); + assert_eq!(output.status.code(), Some(0), "{}", String::from_utf8_lossy(&output.stderr)); + let report = reported(&output); + assert_eq!(report["completed"], 1, "{report}"); + assert_eq!(report["failed"], 0, "{report}"); + assert!(dir.join("out/page.pdf").exists(), "the converted page is written"); + std::fs::remove_dir_all(&dir).unwrap(); +} + +#[test] +fn batch_exits_1_when_one_file_fails() { + let dir = workdir("batch-fail"); + std::fs::write(dir.join("bad.pdf"), "broken").unwrap(); + let output = batch(&dir, &["bad.pdf", "--steps", "convert", "--out-dir", "out"]); + assert_eq!(output.status.code(), Some(1), "{}", String::from_utf8_lossy(&output.stderr)); + let report = reported(&output); + assert_eq!(report["failed"], 1, "{report}"); + std::fs::remove_dir_all(&dir).unwrap(); +} + +#[test] +fn batch_usage_error_exits_1_and_creates_nothing() { + let dir = workdir("batch-usage"); + std::fs::write(dir.join("page.txt"), "Exit code page").unwrap(); + // Baseline: a usage error exits 1 today. A later change to the exit-code contract will + // update this assertion on purpose. + let output = batch(&dir, &["page.txt", "--out-dir", "out"]); + assert_eq!(output.status.code(), Some(1), "{}", String::from_utf8_lossy(&output.stderr)); + assert!(output.stdout.is_empty(), "a usage error prints to stderr, not a report on stdout"); + assert!(!output.stderr.is_empty(), "a usage error says what is wrong"); + assert!(!dir.join("out").exists(), "a refused batch creates no output"); + std::fs::remove_dir_all(&dir).unwrap(); +} + +#[test] +fn batch_outside_root_exits_1_and_creates_nothing() { + let dir = workdir("batch-outside-root"); + let output = Command::new(BIN) + .current_dir(&dir) + .args(["batch", "../outside.pdf", "--steps", "convert", "--out-dir", "out", "--root"]) + .arg(&dir) + .output() + .unwrap(); + assert_eq!(output.status.code(), Some(1), "{}", String::from_utf8_lossy(&output.stderr)); + let stderr = String::from_utf8_lossy(&output.stderr); + assert!(stderr.contains("is outside the allowed directory"), "the input is refused by the root: {stderr}"); + assert!(output.stdout.is_empty(), "a refused batch prints no report"); + assert!(!dir.join("out").exists(), "a refused batch creates no output"); + std::fs::remove_dir_all(&dir).unwrap(); +} + +#[test] +fn run_script_report_exits_0_when_ok_and_1_when_a_step_fails() { + let dir = workdir("run-report"); + let script = dir.join("steps.json"); + let blank = serde_json::json!({ "tool": "doc_create", "args": { "from": "blank", "width": 100, "height": 100 } }); + let steps = serde_json::json!([blank.clone(), { "tool": "no_such_tool", "args": {} }]); + std::fs::write(&script, steps.to_string()).unwrap(); + + let failing = run_report(&dir, &script); + assert_eq!(failing.status.code(), Some(1), "{}", String::from_utf8_lossy(&failing.stderr)); + let report = reported(&failing); + assert_eq!(report["ok"], false, "{report}"); + assert_eq!(report["steps"][1]["status"], "error", "{report}"); + + std::fs::write(&script, serde_json::json!([blank]).to_string()).unwrap(); + let good = run_report(&dir, &script); + assert_eq!(good.status.code(), Some(0), "{}", String::from_utf8_lossy(&good.stderr)); + let report = reported(&good); + assert_eq!(report["ok"], true, "{report}"); + assert_eq!(report["steps"][0]["status"], "ok", "{report}"); + std::fs::remove_dir_all(&dir).unwrap(); +} diff --git a/apps/pdfcraft-cli/tests/it/main.rs b/apps/pdfcraft-cli/tests/it/main.rs index f0b87c97a7..30a6e25882 100644 --- a/apps/pdfcraft-cli/tests/it/main.rs +++ b/apps/pdfcraft-cli/tests/it/main.rs @@ -3,6 +3,7 @@ mod audit; mod automation_roots; mod batch; +mod batch_exit; mod check; mod edit; mod extract; diff --git a/apps/pdfcraft-web/Cargo.toml b/apps/pdfcraft-web/Cargo.toml index ad8243d594..ad5b62229c 100644 --- a/apps/pdfcraft-web/Cargo.toml +++ b/apps/pdfcraft-web/Cargo.toml @@ -11,10 +11,15 @@ workspace = true [dependencies] pdfcraft-ui-egui = { workspace = true } +# The host messages (storytold/craft-libs): one contract and one bridge for the web builds. +# The page command API (storytold/craft-libs#413): window.pdfcraft over the UI control channel. +craft-web-api = { git = "https://github.com/storytold/craft-libs", rev = "fd5e2feff6ea25bed371a99cc732b3968d621505", version = "0.1.0" } +craft-web-host = { git = "https://github.com/storytold/craft-libs", rev = "fd5e2feff6ea25bed371a99cc732b3968d621505", version = "0.1.0" } eframe = { workspace = true, features = ["default_fonts", "glow", "persistence", "accesskit"] } egui = { workspace = true, features = ["default_fonts", "monochrome_emoji_fonts"] } +serde_json = { workspace = true } [target.'cfg(target_arch = "wasm32")'.dependencies] wasm-bindgen-futures = "0.4" -web-sys = { version = "0.3", features = ["Window", "Document", "Element", "HtmlCanvasElement", "HtmlElement", "Location", "Url", "UrlSearchParams", "Response", "Event", "MessageEvent", "EventTarget"] } +web-sys = { version = "0.3", features = ["Window", "Document", "Element", "HtmlCanvasElement", "HtmlElement", "Location", "Url", "UrlSearchParams", "Response", "Event", "MessageEvent", "EventTarget", "CustomEvent", "CustomEventInit"] } js-sys = "0.3" diff --git a/apps/pdfcraft-web/src/api.rs b/apps/pdfcraft-web/src/api.rs new file mode 100644 index 0000000000..3f1d265377 --- /dev/null +++ b/apps/pdfcraft-web/src/api.rs @@ -0,0 +1,127 @@ +//! `window.pdfcraft`: the page command API (`craft-web-api`, storytold/craft-libs#413) over the app's +//! UI control channel (`pdfcraft_ui_egui::control`), opt-in with `?control`. +//! +//! The crate owns the JavaScript side (`request`, `execute`, `commands`, `docInspect`, `uiInspect`, +//! `screenshot`, as promises with a timeout). This module is PdfCraft's part: a [`Request`] that +//! sends each call through the app's [`ControlClient`] and waits for the reply, and the table that +//! names PdfCraft's methods: its control channel drives the UI, so `commands` is `ui.commands`, +//! `execute` runs a registry command with `ui.command`, `docInspect` is `ui.state` and `uiInspect` +//! is `ui.inspect`. +//! +//! The channel keeps the accessibility tree of every frame, so it is off unless the page asks for it +//! (`?control`), as FigCraft's is. PdfCraft's control requests cannot be withdrawn, so a call the page +//! gave up on may still run (or be rejected) when the app reaches it, as it does for a desktop client that timed out. + +use serde_json::{Value, json}; + +/// The reply of a control request as the protocol's `{ok, result}` / `{ok: false, error}` object. +fn reply_object(reply: Result) -> Value { + match reply { + Ok(result) => json!({"ok": true, "result": result}), + Err(error) => json!({"ok": false, "error": error}), + } +} + +/// The params of `ui.command`. `execute(command, params)` sends `{command, params}`; `ui.command` +/// takes `{id}` (and `params` for `ui.panel`). A request that already names an `id` is the page's own +/// `request("ui.command", {id})` and goes through unchanged. +fn command_params(params: Value) -> Value { + match params.get("command").and_then(Value::as_str) { + Some(command) if params.get("id").is_none() => json!({"id": command, "params": params.get("params").cloned().unwrap_or(Value::Null)}), + _ => params, + } +} + +#[cfg(target_arch = "wasm32")] +pub use web::install; + +#[cfg(target_arch = "wasm32")] +mod web { + use std::rc::Rc; + use std::sync::mpsc::{Receiver, TryRecvError}; + + use craft_web_api::methods::Methods; + use craft_web_api::page::{PageApi, Request}; + use pdfcraft_ui_egui::control::{ControlClient, Reply}; + use serde_json::{Value, json}; + use wasm_bindgen_futures::JsFuture; + + use super::{command_params, reply_object}; + + /// The app id in `window.`. + const APP: &str = "pdfcraft"; + + /// How often a waiting call looks for the app's reply, in milliseconds (about a frame). + const POLL_MS: i32 = 16; + + /// PdfCraft's control methods behind each function. + fn methods() -> Methods { + Methods { + commands: Some("ui.commands"), + execute: Some("ui.command"), + doc_inspect: Some("ui.state"), + ui_inspect: Some("ui.inspect"), + screenshot: Some("ui.screenshot"), + } + } + + /// Put `window.pdfcraft` on the page, sending its calls through `client`. An existing + /// `window.pdfcraft` keeps the functions it already has. + pub fn install(client: ControlClient) { + let request: Request = Rc::new(move |method, params| { + let params = if method == "ui.command" { command_params(params) } else { params }; + Box::pin(wait(client.send(&method, params))) + }); + if let Err(e) = Rc::new(PageApi::new(APP, methods(), request)).install() { + eframe::web_sys::console::warn_1(&format!("PdfCraft: couldn't install window.{APP}: {e:?}").into()); + } + } + + /// The app's reply, polled about once a frame. + async fn wait(reply: Receiver) -> Value { + loop { + match reply.try_recv() { + Ok(reply) => return reply_object(reply), + Err(TryRecvError::Empty) => sleep(POLL_MS).await, + Err(TryRecvError::Disconnected) => return json!({"ok": false, "error": "the app dropped the request"}), + } + } + } + + async fn sleep(ms: i32) { + let promise = js_sys::Promise::new(&mut |resolve, _| { + if let Some(window) = web_sys::window() { + let _ = window.set_timeout_with_callback_and_timeout_and_arguments_0(&resolve, ms); + } + }); + let _ = JsFuture::from(promise).await; + } +} + +#[cfg(test)] +mod tests { + use serde_json::json; + + use super::*; + + #[test] + fn execute_becomes_a_ui_command_by_id() { + assert_eq!(command_params(json!({"command": "file.word_count", "params": {"a": 1}})), json!({"id": "file.word_count", "params": {"a": 1}})); + assert_eq!(command_params(json!({"command": "file.save", "params": {}})), json!({"id": "file.save", "params": {}})); + } + + #[test] + fn a_request_that_names_an_id_goes_through_unchanged() { + let own = json!({"id": "file.save"}); + assert_eq!(command_params(own.clone()), own); + let both = json!({"id": "ui.panel", "command": "x", "params": {"reset": true}}); + assert_eq!(command_params(both.clone()), both, "an id wins over a command"); + assert_eq!(command_params(json!({})), json!({})); + } + + #[test] + fn replies_become_the_protocols_objects() { + assert_eq!(reply_object(Ok(json!({"n": 1}))), json!({"ok": true, "result": {"n": 1}})); + assert_eq!(reply_object(Err("boom".to_string())), json!({"ok": false, "error": "boom"})); + } +} diff --git a/apps/pdfcraft-web/src/main.rs b/apps/pdfcraft-web/src/main.rs index 73d14f4a6c..d23dd15a57 100644 --- a/apps/pdfcraft-web/src/main.rs +++ b/apps/pdfcraft-web/src/main.rs @@ -3,20 +3,16 @@ #![deny(clippy::unwrap_used, clippy::expect_used, clippy::panic, clippy::unimplemented, clippy::todo, clippy::unreachable)] +#[cfg(any(target_arch = "wasm32", test))] +mod api; + #[cfg(target_arch = "wasm32")] fn main() { - use eframe::wasm_bindgen::JsCast; use pdfcraft_ui_egui::PdfCraftApp; let options = eframe::WebOptions { renderer: eframe::Renderer::Glow, ..Default::default() }; wasm_bindgen_futures::spawn_local(async move { - let Some(canvas) = web_sys::window() - .and_then(|w| w.document()) - .and_then(|d| d.get_element_by_id("pdfcraft")) - .and_then(|e| e.dyn_into::().ok()) - else { - return; - }; + let Some(canvas) = app_canvas() else { return }; let started = eframe::WebRunner::new() .start( canvas, @@ -54,11 +50,11 @@ fn main() { // eframe never raises a close request on a browser reload or tab close, so `guard_quit` never // prompts; ask the browser to confirm instead while a document has unsaved work (#812). warn_before_unload(app.unsaved_flag.clone()); - // `?host=parent`: a same-origin page embedding PdfCraft in an iframe (such - // as the Nextcloud app) passes files in and takes saves back (`host` below). - if query_param("host").as_deref() == Some("parent") - && let Some(bridge) = host::Bridge::new() - { + // Host modes (`host` below, over `craft-web-host`): `?host=parent`, a + // same-origin page embedding PdfCraft in an iframe (such as the Nextcloud + // app), or `data-host="page"` on the canvas, a host that runs the module in + // its own document. + if let Some(bridge) = app_canvas().as_ref().and_then(host::Bridge::connect) { // `?author=`: the host's name for the user signs their comments, // unless they chose a name in PdfCraft (the web default is "Guest"). if let Some(author) = query_param("author").map(|a| a.trim().to_string()).filter(|a| !a.is_empty()) @@ -75,15 +71,18 @@ fn main() { &"PdfCraft: ?host=parent needs a framing page on the same origin; saves download instead".into(), ); } + // `?control`: `window.pdfcraft`, the page's command API (`api`). Opt-in: the control + // channel keeps the accessibility tree of every frame. + if query_param("control").is_some() { + api::install(app.attach_control(&cc.egui_ctx)); + } Ok(Box::new(app)) }), ) .await; if let Err(e) = started { eframe::web_sys::console::error_1(&e); - if query_param("host").as_deref() == Some("parent") - && let Some(bridge) = host::Bridge::new() - { + if let Some(bridge) = app_canvas().as_ref().and_then(host::Bridge::connect) { bridge.post_failed(&e.as_string().unwrap_or_else(|| format!("{e:?}"))); } } @@ -123,136 +122,116 @@ async fn fetch_bytes(url: &str) -> Result, String> { Ok(js_sys::Uint8Array::new(&buf).to_vec()) } -/// The `postMessage` bridge to a same-origin parent page. Messages are plain objects with a -/// `type`: +/// The app's canvas: the one element `index.html` and every embedding page must provide, with +/// the id the app looks up. +#[cfg(target_arch = "wasm32")] +fn app_canvas() -> Option { + use eframe::wasm_bindgen::JsCast; + web_sys::window()?.document()?.get_element_by_id("pdfcraft").and_then(|e| e.dyn_into::().ok()) +} + +/// Host modes: how the page embedding PdfCraft passes files in and takes saves back. The messages +/// and the two transports are `craft-web-host`'s (storytold/craft-libs), the same contract as the +/// other Craft apps' bridges, with the `pdfcraft:` prefix. This module is PdfCraft's part of it. /// -/// - `pdfcraft:ready` (to the parent): the app is listening; send files now. -/// - `pdfcraft:open` (from the parent): `{ name, bytes }`, where `bytes` is an `ArrayBuffer` or -/// `Uint8Array` holding a PDF. It opens in a tab, like a `?file=` URL. -/// - `pdfcraft:save` (to the parent): `{ name, saveAs, bytes }` when the user saves; `bytes` is -/// a transferred `ArrayBuffer`. The parent stores the file (and reports its own errors). -/// - `pdfcraft:dirty` (to the parent): `{ dirty }` whenever unsaved work appears or goes away. -/// - `pdfcraft:failed` (to the parent): `{ error }` when the app couldn't start. -/// -/// Only the parent window on the app's own origin is heard or answered. With a parent on -/// another origin there is no bridge: the app runs as if unframed and saves download. +/// - `?host=parent` is the `postMessage` bridge for a same-origin page that embeds PdfCraft in an +/// iframe (such as the Nextcloud app). With a parent on another origin there is no bridge: the +/// app runs as if unframed and saves download (#2167). `data-host="page"` on the app's canvas +/// is for a host that loads the module into its own document, with no iframe: the same messages +/// travel as DOM `CustomEvent`s on that canvas. `?host=parent` wins when both are present. +/// - `pdfcraft:ready` once the app is listening; send files now. PdfCraft reads bytes, so it +/// says `file: false` and a host sends `bytes`. +/// - `pdfcraft:open` (from the host): `{ name, bytes }` holding a PDF. It opens in a tab, like a +/// `?file=` URL; a file over [`host::MAX_OPEN_BYTES`] is refused before it is copied. +/// - `pdfcraft:save` (to the host): `{ name, saveAs, bytes }` when the user saves. The host stores +/// the file (and reports its own errors). +/// - `pdfcraft:dirty` whenever unsaved work appears or goes away, `pdfcraft:failed` when the app +/// couldn't start. #[cfg(target_arch = "wasm32")] mod host { - use eframe::wasm_bindgen::{JsCast, JsValue, closure::Closure}; + use std::rc::Rc; + + use craft_web_host::web::{FileData, Host, Message}; + + /// The app id in the host messages (`pdfcraft:ready`). + const APP: &str = "pdfcraft"; + + /// The name a file gets when the host sent none (the crate says `document` for a blank name). + const DEFAULT_NAME: &str = "document.pdf"; + + /// The largest file the host may hand over to open, checked before it is copied (the app's own readers have their own limits). + const MAX_OPEN_BYTES: u64 = 512 << 20; #[derive(Clone)] pub struct Bridge { - window: web_sys::Window, - parent: web_sys::Window, - origin: String, + host: Rc, } impl Bridge { - /// `None` when the page isn't framed (there is no parent to talk to), or when the parent - /// is on another origin: messages only go to this origin, so the browser would drop - /// every save without an error while the document showed as saved (#2167). - pub fn new() -> Option { - let window = web_sys::window()?; - let parent = window.parent().ok().flatten()?; - if js_sys::Object::is(&parent, &window) { - return None; - } - let origin = window.location().origin().ok()?; - // Reading another origin's location throws, which is `None` too. - if parent.location().origin().ok()? != origin { - return None; - } - Some(Self { window, parent, origin }) - } - - fn post(&self, message: &js_sys::Object, transfer: Option<&JsValue>) -> Result<(), String> { - let sent = match transfer { - Some(t) => self.parent.post_message_with_transfer(message, &self.origin, &js_sys::Array::of1(t)), - None => self.parent.post_message(message, &self.origin), - }; - sent.map_err(|e| e.as_string().unwrap_or_else(|| format!("{e:?}"))) + /// The bridge for this page, or `None` when PdfCraft isn't hosted: no `?host=parent` and + /// no `data-host="page"` on the canvas, an unframed `?host=parent` page, or a parent on + /// another origin (messages only go to this origin, so the browser would drop every save + /// without an error while the document showed as saved, #2167). + pub fn connect(canvas: &web_sys::HtmlCanvasElement) -> Option { + Some(Self { host: Rc::new(Host::connect(APP, canvas)?) }) } pub fn post_ready(&self) { - if let Some(m) = message(&[("type", "pdfcraft:ready".into()), ("version", env!("CARGO_PKG_VERSION").into())]) { - let _ = self.post(&m, None); - } + let _ = self.host.post_ready(env!("CARGO_PKG_VERSION"), false); } - /// The app couldn't start (no WebGL, for example): let the parent say so. + /// The app couldn't start (no WebGL, for example): let the host say so. pub fn post_failed(&self, error: &str) { - if let Some(m) = message(&[("type", "pdfcraft:failed".into()), ("error", error.into())]) { - let _ = self.post(&m, None); - } + let _ = self.host.post_failed(error, None); } - /// Hear `pdfcraft:open` from the parent and queue the file like a `?file=` download. + /// Hear `pdfcraft:open` and queue the file like a `?file=` download. pub fn listen(&self, inbox: pdfcraft_ui_egui::Inbox, ctx: egui::Context) { - let parent = self.parent.clone(); - let origin = self.origin.clone(); - let on_message = Closure::::new(move |event: web_sys::MessageEvent| { - if event.origin() != origin || !event.source().is_some_and(|s| js_sys::Object::is(&s, &parent)) { - return; + self.host.listen(move |message| { + if let Message::Open { name, data } = message { + queue_open(&name, &data, &inbox, &ctx); } - let data = event.data(); - if string(&data, "type").as_deref() != Some("pdfcraft:open") { - return; - } - let name = string(&data, "name").filter(|n| !n.trim().is_empty()).unwrap_or_else(|| "document.pdf".to_string()); - let Ok(bytes) = js_sys::Reflect::get(&data, &JsValue::from_str("bytes")) else { return }; - let bytes = if let Some(array) = bytes.dyn_ref::() { - array.to_vec() - } else if bytes.is_instance_of::() { - js_sys::Uint8Array::new(&bytes).to_vec() - } else { - return; - }; - if let Ok(mut q) = inbox.lock() { - q.push((name, bytes)); - } - ctx.request_repaint(); }); - if self.window.add_event_listener_with_callback("message", on_message.as_ref().unchecked_ref()).is_ok() { - // The listener lives as long as the page. - on_message.forget(); - } } pub fn save_fn(&self) -> pdfcraft_ui_egui::HostSaveFn { - let bridge = self.clone(); - Box::new(move |name: &str, bytes: &[u8], save_as: bool| { - let buffer = js_sys::Uint8Array::from(bytes).buffer(); - let m = - message(&[("type", "pdfcraft:save".into()), ("name", name.into()), ("saveAs", save_as.into()), ("bytes", buffer.clone().into())]) - .ok_or_else(|| "couldn't build the message".to_string())?; - bridge.post(&m, Some(&buffer)) - }) + let host = self.host.clone(); + Box::new(move |name: &str, bytes: &[u8], save_as: bool| host.post_save(name, bytes, None, save_as)) } pub fn dirty_fn(&self) -> pdfcraft_ui_egui::HostDirtyFn { - let bridge = self.clone(); + let host = self.host.clone(); + // A host starts out clean: the first report is a change only when it is dirty. let mut last = false; Box::new(move |dirty: bool| { if dirty != last { last = dirty; - if let Some(m) = message(&[("type", "pdfcraft:dirty".into()), ("dirty", dirty.into())]) { - let _ = bridge.post(&m, None); - } + host.post_dirty(dirty); } }) } } - fn message(fields: &[(&str, JsValue)]) -> Option { - let m = js_sys::Object::new(); - for (key, value) in fields { - js_sys::Reflect::set(&m, &JsValue::from_str(key), value).ok()?; + /// The `pdfcraft:open` payload, `{ name, bytes }` where `bytes` holds a PDF: queue it like a + /// `?file=` download and wake the app. The crate has cleaned the name (and cut it to 255 + /// characters); a blank one comes as `document` and becomes `document.pdf`. + fn queue_open(name: &str, data: &FileData, inbox: &pdfcraft_ui_egui::Inbox, ctx: &egui::Context) { + let name = if name == "document" { DEFAULT_NAME } else { name }.to_string(); + let FileData::Bytes(view) = data else { + eframe::web_sys::console::warn_1(&format!("PdfCraft: host file {name} came as a File; PdfCraft reads bytes only; not opened").into()); + return; + }; + // A file from the host is untrusted input: refuse an oversized one before copying it into the app's memory. + if data.size() > MAX_OPEN_BYTES as f64 { + eframe::web_sys::console::warn_1( + &format!("PdfCraft: host file is {} bytes, over the {} MiB host open limit; not opened", data.size(), MAX_OPEN_BYTES >> 20).into(), + ); + return; } - Some(m) - } - - fn string(data: &JsValue, key: &str) -> Option { - js_sys::Reflect::get(data, &JsValue::from_str(key)).ok()?.as_string() + if let Ok(mut q) = inbox.lock() { + q.push((name, view.to_vec())); + } + ctx.request_repaint(); } } diff --git a/apps/pdfcraft/src/main.rs b/apps/pdfcraft/src/main.rs index 5bc5c5c372..4de423db7f 100644 --- a/apps/pdfcraft/src/main.rs +++ b/apps/pdfcraft/src/main.rs @@ -333,7 +333,7 @@ fn native_options(integrated: bool, app_frame: bool, renderer: eframe::Renderer) let mut viewport = egui::ViewportBuilder::default() .with_title("PdfCraft") .with_inner_size([1440.0, 920.0]) - .with_min_inner_size([820.0, 520.0]) + .with_min_inner_size(pdfcraft_ui_egui::MIN_WINDOW_SIZE) .with_drag_and_drop(true) // Wayland app id: matches packaging/linux/ai.storyteller.pdfcraft.desktop. .with_app_id(APP_ID); @@ -439,6 +439,8 @@ fn app_creator<'a>( if let Some(dir) = pdfcraft_ui_egui::RecoveryStore::default_dir() { app.enable_recovery(pdfcraft_ui_egui::RecoveryStore::new(dir)); } + // The OCR Verify screen stores its per-language dictionary beside recovery data. + app.ocr_verify.dictionary_dir = pdfcraft_ui_egui::default_dictionary_dir(); if let Some(state) = &cc.wgpu_render_state { let adapter = state.adapter.get_info(); let max_texture_dimension_2d = state.device.limits().max_texture_dimension_2d; diff --git a/assets/icons/a-large-small.svg b/assets/icons/a-large-small.svg new file mode 100644 index 0000000000..7716db3cf2 --- /dev/null +++ b/assets/icons/a-large-small.svg @@ -0,0 +1,18 @@ + + + + + + + diff --git a/contributors/people.toml b/contributors/people.toml index fecfb68c90..a22c884ccb 100644 --- a/contributors/people.toml +++ b/contributors/people.toml @@ -183,3 +183,11 @@ sync_github_name = true [people.Combiler01] sync_github_name = true + +[people.helenkwok] +real_name = "Helen Kwok" + +[people.vangel76] +real_name = "Valentin Klein" +display_name = "vangel76" +sync_github_name = false diff --git a/crates/a11y/Cargo.toml b/crates/a11y/Cargo.toml index 42a86bbad2..adef6053a1 100644 --- a/crates/a11y/Cargo.toml +++ b/crates/a11y/Cargo.toml @@ -14,6 +14,5 @@ workspace = true pdfcraft-cos = { workspace = true } pdfcraft-model = { workspace = true } pdfcraft-content = { workspace = true } -pdfcraft-filters = { workspace = true } pdfcraft-fonts = { workspace = true } thiserror.workspace = true diff --git a/crates/a11y/src/alt.rs b/crates/a11y/src/alt.rs index fde1048e47..55c0857878 100644 --- a/crates/a11y/src/alt.rs +++ b/crates/a11y/src/alt.rs @@ -25,6 +25,8 @@ pub enum AltError { NotAFigure(u32), #[error("the page has more content than can be edited")] TooLarge, + #[error("the figure's content may be in a damaged or unreadable content stream, or after the damage, so nothing was changed")] + Damaged, #[error("{0}")] Cos(#[from] pdfcraft_cos::CosError), } @@ -52,6 +54,8 @@ pub enum ArtifactError { ParentTree(String), #[error("the page has more content than can be edited")] TooLarge, + #[error("the tag's marked content may be in a damaged or unreadable content stream, or after the damage, so nothing was changed")] + Damaged, #[error(transparent)] Cos(#[from] pdfcraft_cos::CosError), } @@ -372,7 +376,19 @@ fn content_entries(doc: &Document, page: &Dict) -> Vec { } } -type DecodedStream = (Object, Option<(Stream, Vec)>); +/// How much of a content stream decoded. +#[derive(Clone, Copy, Debug, PartialEq)] +enum Read { + Whole, + /// Damaged partway: the data is what decoded before the damage. What follows it is unknown, + /// the syntax the later streams start in too. + Damaged, + /// Not at all (a filter this reader lacks, say): the data is empty. + Unread, +} + +/// A `/Contents` entry and, for a stream, the stream, its decoded data and how much of it decoded. +type DecodedStream = (Object, Option<(Stream, Vec, Read)>); /// Decode the page's content streams within the page decode budget. `None` when a stream is /// rejected because the budget is exhausted. @@ -383,14 +399,14 @@ fn decode_page_streams(doc: &Document, page: &Dict) -> Option for entry in entries { let decoded = match &*doc.resolve(&entry) { Object::Stream(s) => { - let data = match budget.decode(s) { - Ok(data) => data, + let (data, read) = match budget.decode_with_damage(doc, s, usize::MAX) { + Ok((data, damaged)) => (data, if damaged { Read::Damaged } else { Read::Whole }), // 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(), + Err(_) => (Vec::new(), Read::Unread), }; - Some((s.clone(), data)) + Some((s.clone(), data, read)) } _ => None, }; @@ -403,6 +419,18 @@ fn marked_id(doc: &Document, props: &Dict, op: &pdfcraft_content::Op, ids: &Hash (op.op == b"BDC").then(|| bdc_mcid(doc, props, op)).flatten().filter(|n| ids.contains(n)) } +/// What [`artifact_marked_content`] did. +#[derive(Debug, PartialEq)] +enum Marked { + /// The streams holding the content were rewritten. + Done, + /// None of the content is on the page, or with `require_all` not all of it: nothing changed. + NotFound, + /// Some of it is, or may be, in a stream damaged partway or one that doesn't decode, neither of + /// which can be rewritten without losing what wasn't read, or after the damage: nothing changed. + Damaged, +} + /// 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. @@ -412,25 +440,45 @@ fn artifact_marked_content( streams: Vec, ids: &HashSet, require_all: bool, -) -> Result { +) -> Result { 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(); + // The pieces are the streams, in order. + let decoded: Vec<&[u8]> = streams.iter().filter_map(|(_, s)| s.as_ref().map(|(_, bytes, _)| bytes.as_slice())).collect(); + let read: Vec = streams.iter().filter_map(|(_, s)| s.as_ref().map(|(_, _, read)| *read)).collect(); + let damage = read.iter().position(|r| *r == Read::Damaged); 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) { + // What follows the damage is unknown: a string or comment the damage left open runs + // on into the next stream, so what reads as an operator after it may not be one. An + // operator whose operands start before a stream not read whole and whose keyword comes + // after it takes them from around what wasn't read: that stream may end them itself. + let (first, last) = pieces.pieces_of(&op); + if damage.is_some_and(|d| last > d) || read.get(first..last).is_some_and(|r| r.iter().any(|r| *r != Read::Whole)) { + return Ok(Marked::Damaged); + } found.insert(id); edits.push((op.span, b"/Artifact BMC".to_vec())); } } - if if require_all { found != *ids } else { found.is_empty() } { - return Ok(false); + // Content not found may be past the damage, or in a stream that doesn't decode: whether it + // is on the page isn't known. + if found != *ids && read.iter().any(|r| *r != Read::Whole) { + return Ok(Marked::Damaged); } - let mut spliced = pieces.splice(edits).into_iter(); + if if require_all { found != *ids } else { found.is_empty() } { + return Ok(Marked::NotFound); + } + let spliced = pieces.splice(edits); + if read.iter().zip(&decoded).zip(&spliced).any(|((read, old), new)| *read != Read::Whole && *old != new.as_slice()) { + return Ok(Marked::Damaged); + } + let mut spliced = spliced.into_iter(); let mut next = Vec::with_capacity(streams.len()); for (entry, stream) in streams { - let Some((stream, old)) = stream else { + let Some((stream, old, _)) = stream else { next.push(entry); continue; }; @@ -456,7 +504,7 @@ fn artifact_marked_content( _ => Object::Array(next), }; doc.update_dict(page.obj, |p| p.set(b"Contents".to_vec(), contents))?; - Ok(true) + Ok(Marked::Done) } /// Decorative figure: its marked content on the page becomes an artifact, and the element @@ -468,11 +516,15 @@ pub fn mark_decorative(doc: &mut Document, obj: ObjRef) -> Result<(), AltError> 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()) { let streams = decode_page_streams(doc, &page.dict).ok_or(AltError::TooLarge)?; - // The parent tree no longer points those ids at the figure. - 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)?; + match artifact_marked_content(doc, page, streams, &ids, false)? { + // The parent tree no longer points those ids at the figure. + Marked::Done => { + if let Some(key) = page.dict.get(b"StructParents").and_then(|o| doc.resolve(o).as_int()) { + clear_parent_tree(doc, key, obj)?; + } + } + Marked::NotFound => {} + Marked::Damaged => return Err(AltError::Damaged), } } // Out of its parent's kids. @@ -513,10 +565,12 @@ pub fn mark_tag_artifact(doc: &mut Document, obj: ObjRef) -> Result<(), Artifact 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); + match artifact_marked_content(doc, page, streams, &ids, true)? { + Marked::Done => {} + Marked::NotFound => return Err(ArtifactError::ContentNotFound), + Marked::Damaged => return Err(ArtifactError::Damaged), } - if let Some(key) = page.dict.get(b"StructParents").and_then(Object::as_int) { + if let Some(key) = page.dict.get(b"StructParents").and_then(|o| doc.resolve(o).as_int()) { clear_parent_tree(doc, key, obj).map_err(|e| ArtifactError::ParentTree(e.to_string()))?; } doc.update_dict(parent, |p| p.set(b"K".to_vec(), replacement))?; diff --git a/crates/a11y/src/autotag.rs b/crates/a11y/src/autotag.rs index 9b65f6972b..5c0dc2bd19 100644 --- a/crates/a11y/src/autotag.rs +++ b/crates/a11y/src/autotag.rs @@ -4,7 +4,7 @@ //! which can then be retagged with the existing tag-property tool after human review. use pdfcraft_content::{Op, parse, serialize_ops}; -use pdfcraft_cos::{Dict, Document, ObjRef, Object, Stream}; +use pdfcraft_cos::{DecodeBudget, Dict, Document, ObjRef, Object, Stream}; const MAX_PAGES: usize = 1_000; const MAX_PAGE_BYTES: usize = 16 * 1024 * 1024; @@ -57,18 +57,24 @@ fn content_bytes(doc: &Document, page: &pdfcraft_model::Page, index: usize) -> R let Object::Stream(stream) = &*value else { return Err(unsupported(index, "contents include a non-stream object")) }; let remaining = MAX_PAGE_BYTES.saturating_sub(all.len().saturating_add(1)); if remaining == 0 { - return Err(unsupported(index, "decoded content exceeds 16 MiB")); + return Err(unsupported(index, "decoding the content takes more than 16 MiB")); } - let chain = stream.filters(); - let decoded = if chain.is_empty() { - if stream.raw.len() > remaining { - return Err(unsupported(index, "decoded content exceeds 16 MiB")); + // Strictly, and with `/DecodeParms` given by reference: the content is written back from it. + let mut budget = DecodeBudget::new(remaining, 0); + let decoded = budget.decode_strict(doc, stream).map_err(|e| { + // The allowance counts what every filter stage decodes, as a page's does. + if budget.remaining() == 0 { + unsupported(index, "decoding the content takes more than 16 MiB") + } else { + // The decoder's own reason: `CosError::Filter`'s text would say again that the data + // couldn't be decoded. + let why = match e { + pdfcraft_cos::CosError::Filter(why) => why, + other => other.to_string(), + }; + unsupported(index, format!("content cannot be decoded strictly: {why}")) } - stream.raw.to_vec() - } else { - pdfcraft_filters::decode(&chain, &stream.raw, remaining) - .map_err(|e| unsupported(index, format!("content cannot be decoded strictly: {e}")))? - }; + })?; all.extend_from_slice(&decoded); all.push(b' '); } diff --git a/crates/a11y/src/tests.rs b/crates/a11y/src/tests.rs index 3024319ec3..d8566eddf1 100644 --- a/crates/a11y/src/tests.rs +++ b/crates/a11y/src/tests.rs @@ -79,6 +79,68 @@ fn autotag_text_writes_marked_content_and_parent_tree_across_pages() { assert_eq!(status(&check(&reopened, &Options::default()), Rule::TaggedContent), Status::Passed); } +/// Page content behind a predictor whose `/DecodeParms` are given by reference is read through +/// them: autotagging writes the text back as it was, marked, not with the predictor's tag bytes in +/// it (a `\0` every eight bytes, which split `24` into `2 4`). +#[test] +fn autotag_text_reads_content_with_parameters_given_by_reference() { + use pdfcraft_cos::{Dict, ObjRef}; + let mut content = b"BT /F1 24 Tf 72 700 Td (Hello World) Tj ET".to_vec(); + content.resize(content.len().div_ceil(8) * 8, b' '); + // PNG rows of eight bytes, each tagged 0 (no prediction). + let rows: Vec = content.chunks(8).flat_map(|row| std::iter::once(0).chain(row.iter().copied())).collect(); + let mut doc = pdf( + &[ + "<< /Type /Catalog /Pages 2 0 R >>".into(), + "<< /Type /Pages /Kids [3 0 R] /Count 1 >>".into(), + "<< /Type /Page /Parent 2 0 R /MediaBox [0 0 600 800] /Contents 4 0 R /Resources << /Font << /F1 5 0 R >> >> >>".into(), + stream(""), + FONT.into(), + ], + "", + ); + let parms: Dict = [(b"Predictor".to_vec(), Object::Int(12)), (b"Columns".to_vec(), Object::Int(8))].into_iter().collect(); + let parms = doc.add(Object::Dict(parms)); + let mut predicted = pdfcraft_cos::Stream::flate(Dict::new(), &rows); + predicted.dict.set(b"DecodeParms".to_vec(), Object::Ref(parms)); + doc.set(ObjRef::new(4, 0), predicted); + assert_eq!(autotag_text(&mut doc).unwrap(), AutoTagResult { pages: 1, paragraphs: 1 }); + let page = &pdfcraft_model::pages(&doc)[0]; + let written = doc.resolve(page.dict.get(b"Contents").unwrap()); + let Object::Stream(written) = &*written else { panic!("page content") }; + let text = String::from_utf8_lossy(&written.decoded_strict().unwrap()).into_owned(); + assert!(text.contains("/F1 24 Tf") && text.contains("(Hello World) Tj"), "{text}"); +} + +/// Autotagging refuses a page whose content it can't read whole, and says why: content past +/// 16 MiB, or content that doesn't decode strictly, with the decoder's reason right after. +#[test] +fn autotag_text_says_why_it_cannot_read_a_page() { + use pdfcraft_cos::{Dict, ObjRef, Stream}; + let reason = |content: Stream| { + let mut doc = pdf( + &[ + "<< /Type /Catalog /Pages 2 0 R >>".into(), + "<< /Type /Pages /Kids [3 0 R] /Count 1 >>".into(), + "<< /Type /Page /Parent 2 0 R /MediaBox [0 0 600 800] /Contents 4 0 R /Resources << /Font << /F1 5 0 R >> >> >>".into(), + stream(""), + FONT.into(), + ], + "", + ); + doc.set(ObjRef::new(4, 0), content); + match autotag_text(&mut doc) { + Err(AutoTagError::Unsupported { reason, .. }) => reason, + other => panic!("{other:?}"), + } + }; + assert_eq!(reason(Stream::from_raw(Dict::new(), vec![b' '; 17 << 20])), "decoding the content takes more than 16 MiB"); + let mut corrupt = Stream::from_raw(Dict::new(), b"not zlib data".to_vec()); + corrupt.dict.set(b"Filter".to_vec(), Object::name("FlateDecode")); + let why = reason(corrupt); + assert!(why.starts_with("content cannot be decoded strictly: FlateDecode: "), "{why}"); +} + #[test] fn autotag_text_refuses_paint_and_does_not_modify_the_document() { let mut doc = pdf( @@ -1087,6 +1149,185 @@ fn mark_tag_artifact_validates_parent_and_all_mcids_before_mutating_document() { assert_eq!(*absent.get(ObjRef::new(9, 0)), before_pt); } +/// zlib data that reads as `readable` and is then damaged, with more of the stream after the +/// damage: a stored block, then a block of the reserved type (RFC 1951 §3.2.3), then `rest`. +fn damaged_flate(readable: &[u8], rest: &[u8]) -> pdfcraft_cos::Stream { + let len = u16::try_from(readable.len()).unwrap(); + let mut raw = vec![0x78, 0x01, 0x00]; + raw.extend_from_slice(&len.to_le_bytes()); + raw.extend_from_slice(&(!len).to_le_bytes()); + raw.extend_from_slice(readable); + raw.push(0x07); + raw.extend_from_slice(rest); + let mut dict = pdfcraft_cos::Dict::new(); + dict.set(b"Filter".to_vec(), pdfcraft_cos::Object::name("FlateDecode")); + pdfcraft_cos::Stream::from_raw(dict, raw) +} + +/// A tag's content in a stream damaged partway stays tagged: rewriting the stream from what +/// decoded would lose what follows the damage. Nothing changes, the structure tree and the stream +/// included. Content in a whole stream before a damaged one is marked, and the damaged one kept +/// as stored. +#[test] +fn a_tags_content_in_a_stream_damaged_partway_is_not_rewritten() { + use pdfcraft_cos::{ObjRef, Object}; + let content = b"/Figure << /MCID 0 >> BDC q 40 0 0 20 10 150 cm /Im Do Q EMC /Photo << /MCID 1 >> BDC 100 100 50 30 re f EMC\n"; + let damaged = damaged_flate(content, b"0 0 1 rg 0 0 10 10 re f"); + let mut doc = figures_doc(); + doc.set(ObjRef::new(4, 0), damaged.clone()); + let contents = |doc: &Document| doc.get(ObjRef::new(3, 0)).as_dict().unwrap().get(b"Contents").cloned(); + let state = |doc: &Document| (contents(doc), doc.get(ObjRef::new(9, 0)), doc.get(ObjRef::new(6, 0)), doc.get(ObjRef::new(4, 0))); + let before = state(&doc); + assert_eq!(figures(&doc).len(), 2, "read up to the damage"); + assert_eq!(mark_tag_artifact(&mut doc, ObjRef::new(7, 0)), Err(ArtifactError::Damaged)); + assert_eq!(mark_decorative(&mut doc, ObjRef::new(7, 0)), Err(AltError::Damaged)); + assert_eq!(state(&doc), before); + + let mut doc = figures_doc(); + let other = doc.add(damaged_flate(b"0 g\n", b"0 0 1 rg 0 0 10 10 re f")); + doc.update_dict(ObjRef::new(3, 0), |p| p.set(b"Contents".to_vec(), Object::Array(vec![Object::Ref(ObjRef::new(4, 0)), Object::Ref(other)]))) + .unwrap(); + mark_tag_artifact(&mut doc, ObjRef::new(7, 0)).unwrap(); + let Some(Object::Array(list)) = contents(&doc) else { panic!("contents {:?}", contents(&doc)) }; + assert_ne!(list.first(), Some(&Object::Ref(ObjRef::new(4, 0))), "the tag's stream is rewritten"); + assert_eq!(list.get(1), Some(&Object::Ref(other)), "kept as stored"); +} + +/// What follows the damage is unknown, the syntax the next stream starts in too, so a tag's +/// content in a stream after a damaged one stays tagged. Here a comment the damage leaves open +/// runs on into the next stream, up to its first end of line, and a string starting there reads +/// as operators, among them what looks like the figure's content: rewritten, it would change the +/// string. Nothing changes, the structure tree included. +#[test] +fn a_tags_content_after_a_damaged_stream_is_not_rewritten() { + use pdfcraft_cos::{Dict, ObjRef, Object, Stream}; + let in_a_string = b"(a note\n/Figure << /MCID 0 >> BDC 0 g EMC\n) pop /Photo << /MCID 1 >> BDC 100 100 50 30 re f EMC"; + for (damaged, after) in [(b"0 g\n".as_slice(), None), (b"0 g % a comment".as_slice(), Some(in_a_string.as_slice()))] { + let mut doc = figures_doc(); + if let Some(after) = after { + doc.set(ObjRef::new(4, 0), Stream::from_raw(Dict::new(), after.to_vec())); + } + let first = doc.add(damaged_flate(damaged, b"\n0 0 1 rg 0 0 10 10 re f")); + doc.update_dict(ObjRef::new(3, 0), |p| p.set(b"Contents".to_vec(), Object::Array(vec![Object::Ref(first), Object::Ref(ObjRef::new(4, 0))]))) + .unwrap(); + let state = |doc: &Document| { + (doc.get(ObjRef::new(3, 0)).as_dict().unwrap().get(b"Contents").cloned(), doc.get(ObjRef::new(9, 0)), doc.get(ObjRef::new(6, 0))) + }; + let before = state(&doc); + assert_eq!(mark_tag_artifact(&mut doc, ObjRef::new(7, 0)), Err(ArtifactError::Damaged), "{damaged:?}"); + assert_eq!(mark_decorative(&mut doc, ObjRef::new(7, 0)), Err(AltError::Damaged), "{damaged:?}"); + assert_eq!(state(&doc), before, "{damaged:?}"); + } +} + +/// A page may split its content between an operator's operands and its keyword. When the operands +/// of the figure's `BDC` end the stream before one damaged from its start or one that doesn't +/// decode, the `BDC` the page reads is in what wasn't read: joined without it, those operands and +/// the next tag's read as one `BDC`, which reaches into the stream after it. Neither marking +/// changes anything, the structure tree included. +#[test] +fn a_tags_operands_before_a_stream_not_read_whole_are_not_rewritten() { + use pdfcraft_cos::{Dict, ObjRef, Object, Stream}; + let rest = b" BDC q 40 0 0 20 10 150 cm /Im Do Q EMC"; + for damaged in [true, false] { + let mut doc = figures_doc(); + doc.set(ObjRef::new(4, 0), Stream::from_raw(Dict::new(), b"/Figure << /MCID 0 >>".to_vec())); + let hidden = if damaged { + damaged_flate(b"", rest) + } else { + let filter = doc.add(Object::name("FlateDecode")); + let mut s = Stream::flate(Dict::new(), rest); + s.dict.set(b"Filter".to_vec(), Object::Ref(filter)); + s + }; + let hidden = doc.add(hidden); + let after = doc.add(Object::Stream(Stream::from_raw(Dict::new(), b"/Photo << /MCID 1 >> BDC 100 100 50 30 re f EMC".to_vec()))); + let listed = Object::Array(vec![Object::Ref(ObjRef::new(4, 0)), Object::Ref(hidden), Object::Ref(after)]); + doc.update_dict(ObjRef::new(3, 0), |p| p.set(b"Contents".to_vec(), listed)).unwrap(); + let state = |doc: &Document| { + (doc.get(ObjRef::new(3, 0)).as_dict().unwrap().get(b"Contents").cloned(), doc.get(ObjRef::new(9, 0)), doc.get(ObjRef::new(6, 0))) + }; + let before = state(&doc); + assert_eq!(mark_tag_artifact(&mut doc, ObjRef::new(7, 0)), Err(ArtifactError::Damaged), "damaged: {damaged}"); + assert_eq!(mark_decorative(&mut doc, ObjRef::new(7, 0)), Err(AltError::Damaged), "damaged: {damaged}"); + assert_eq!(state(&doc), before, "damaged: {damaged}"); + } +} + +/// A tag's content not found on the page may be in a stream that doesn't decode: it isn't known +/// to be off the page, so neither marking changes anything, the structure tree included. +#[test] +fn a_tags_content_not_found_beside_a_stream_that_does_not_decode_is_not_taken_for_absent() { + use pdfcraft_cos::{Dict, ObjRef, Object, Stream}; + let mut doc = figures_doc(); + doc.update_dict(ObjRef::new(7, 0), |d| d.set(b"K".to_vec(), Object::Int(2))).unwrap(); + let mut dict = Dict::new(); + dict.set(b"Filter".to_vec(), Object::name("NoSuchFilter")); + let other = doc.add(Object::Stream(Stream::from_raw(dict, b"/Figure << /MCID 2 >> BDC 0 g EMC".to_vec()))); + doc.update_dict(ObjRef::new(3, 0), |p| p.set(b"Contents".to_vec(), Object::Array(vec![Object::Ref(other), Object::Ref(ObjRef::new(4, 0))]))) + .unwrap(); + let state = |doc: &Document| { + (doc.get(ObjRef::new(3, 0)).as_dict().unwrap().get(b"Contents").cloned(), doc.get(ObjRef::new(9, 0)), doc.get(ObjRef::new(6, 0))) + }; + let before = state(&doc); + assert_eq!(mark_decorative(&mut doc, ObjRef::new(7, 0)), Err(AltError::Damaged)); + assert_eq!(mark_tag_artifact(&mut doc, ObjRef::new(7, 0)), Err(ArtifactError::Damaged)); + assert_eq!(state(&doc), before); +} + +/// A tag's content not found before the damage in a damaged stream may be past it: it isn't known +/// to be off the page, so neither marking changes anything. +#[test] +fn a_tags_content_past_the_damage_is_not_taken_for_absent() { + use pdfcraft_cos::ObjRef; + let damaged = + damaged_flate(b"/Photo << /MCID 1 >> BDC 100 100 50 30 re f EMC\n", b"/Figure << /MCID 0 >> BDC q 40 0 0 20 10 150 cm /Im Do Q EMC"); + let mut doc = figures_doc(); + doc.set(ObjRef::new(4, 0), damaged); + let contents = |doc: &Document| doc.get(ObjRef::new(3, 0)).as_dict().unwrap().get(b"Contents").cloned(); + let before = (contents(&doc), doc.get(ObjRef::new(9, 0)), doc.get(ObjRef::new(6, 0))); + assert_eq!(mark_decorative(&mut doc, ObjRef::new(7, 0)), Err(AltError::Damaged)); + assert_eq!(mark_tag_artifact(&mut doc, ObjRef::new(7, 0)), Err(ArtifactError::Damaged)); + assert_eq!((contents(&doc), doc.get(ObjRef::new(9, 0)), doc.get(ObjRef::new(6, 0))), before); +} + +/// A page's `/StructParents` given by reference is read through it: the parent tree no longer +/// points the marked content at the tag. +#[test] +fn struct_parents_given_by_reference_are_read() { + use pdfcraft_cos::{ObjRef, Object}; + let by_reference = || { + let mut doc = figures_doc(); + let key = doc.add(Object::Int(0)); + doc.update_dict(ObjRef::new(3, 0), |p| p.set(b"StructParents".to_vec(), Object::Ref(key))).unwrap(); + doc + }; + let nums = |doc: &Document| doc.get(ObjRef::new(9, 0)).as_dict().and_then(|d| d.get(b"Nums").cloned()); + let mut doc = by_reference(); + mark_decorative(&mut doc, ObjRef::new(7, 0)).unwrap(); + assert_eq!(nums(&doc), Some(Object::Array(vec![Object::Int(0), Object::Array(vec![Object::Null, Object::Ref(ObjRef::new(8, 0))])]))); + let mut doc = by_reference(); + mark_tag_artifact(&mut doc, ObjRef::new(8, 0)).unwrap(); + assert_eq!(nums(&doc), Some(Object::Array(vec![Object::Int(0), Object::Array(vec![Object::Ref(ObjRef::new(7, 0)), Object::Null])]))); +} + +/// A content stream that doesn't decode at all is kept as stored, and a tag in the page's other +/// streams is still marked: only running past the decode budget refuses. +#[test] +fn a_tag_beside_a_stream_that_does_not_decode_is_marked() { + use pdfcraft_cos::{Dict, ObjRef, Object, Stream}; + let mut doc = figures_doc(); + let mut dict = Dict::new(); + dict.set(b"Filter".to_vec(), Object::name("NoSuchFilter")); + let other = doc.add(Object::Stream(Stream::from_raw(dict, b"0 g".to_vec()))); + doc.update_dict(ObjRef::new(3, 0), |p| p.set(b"Contents".to_vec(), Object::Array(vec![Object::Ref(other), Object::Ref(ObjRef::new(4, 0))]))) + .unwrap(); + mark_tag_artifact(&mut doc, ObjRef::new(7, 0)).unwrap(); + let contents = doc.get(ObjRef::new(3, 0)).as_dict().unwrap().get(b"Contents").cloned(); + let Some(Object::Array(list)) = contents else { panic!("contents {contents:?}") }; + assert_eq!(list.first(), Some(&Object::Ref(other)), "kept as stored"); +} + fn ref_(n: u32) -> Option { Some(pdfcraft_cos::ObjRef::new(n, 0)) } diff --git a/crates/annot/src/appearance.rs b/crates/annot/src/appearance.rs index 89c0f70f48..7148e9fc2e 100644 --- a/crates/annot/src/appearance.rs +++ b/crates/annot/src/appearance.rs @@ -232,6 +232,31 @@ fn rg_stroke(c: Rgb) -> String { format!("{} {} {} RG\n", n(c[0]), n(c[1]), n(c[2])) } +/// A FreeText's border colour where it has its own: the stroking colour in `/DA` (`RG`, or `G` +/// for grey). `None`: the border takes the text colour. +pub fn da_border(d: &Dict) -> Option { + let da = d.get(b"DA").and_then(|o| o.as_string()).map(|s| String::from_utf8_lossy(&s.bytes).into_owned())?; + let toks: Vec<&str> = da.split_whitespace().collect(); + let num = |i: usize| toks.get(i).and_then(|t| t.parse::().ok()).filter(|x| x.is_finite()); + let mut col = None; + for (i, t) in toks.iter().enumerate() { + match *t { + "RG" if i >= 3 => { + if let (Some(r), Some(g), Some(b)) = (num(i - 3), num(i - 2), num(i - 1)) { + col = Some([r, g, b].map(|x| x.clamp(0.0, 1.0))); + } + } + "G" if i >= 1 => { + if let Some(g) = num(i - 1) { + col = Some([g.clamp(0.0, 1.0); 3]); + } + } + _ => {} + } + } + col +} + /// `/DA` of a text box: (text colour, font size). Defaults to black 12 pt. pub fn parse_da(d: &Dict) -> (Rgb, f64) { let da = d.get(b"DA").and_then(|o| o.as_string()).map(|s| String::from_utf8_lossy(&s.bytes).into_owned()).unwrap_or_default(); @@ -262,19 +287,47 @@ pub fn parse_da(d: &Dict) -> (Rgb, f64) { (col.map(|x| x.clamp(0.0, 1.0)), size.min(400.0)) } -fn ext_gstate(opacity: f64, multiply: bool) -> Option { - if opacity >= 1.0 && !multiply { +/// How opaque a comment's parts are drawn, 0–1: its line or border (`/CA`); its fill or +/// background (`/ca`, which PDF 2.0 gives the non-stroking operations; without it, as the line); +/// and a text box's text (`/PCTextOpacity`, PdfCraft's own; without it, as the fill, since text +/// is filled too). A comment with only `/CA` is drawn at that opacity throughout, as before. +#[derive(Clone, Copy, Debug, PartialEq)] +pub struct PartOpacity { + pub line: f64, + pub fill: f64, + pub text: f64, +} + +/// The parts' opacities of the comment `d` (see [`PartOpacity`]). +pub fn part_opacity(d: &Dict) -> PartOpacity { + let get = |key: &[u8]| d.get(key).and_then(|o| o.as_f64()).filter(|x| x.is_finite()).map(|x| x.clamp(0.0, 1.0)); + let line = get(b"CA").unwrap_or(1.0); + let fill = get(b"ca").unwrap_or(line); + let text = get(b"PCTextOpacity").unwrap_or(fill); + PartOpacity { line, fill, text } +} + +/// `/GS0`: the line's opacity for strokes and the fill's for everything filled; `/GS1`, where the +/// text's differs from the fill's: the text's for its glyphs. +fn ext_gstate(parts: PartOpacity, multiply: bool) -> Option { + if parts.line >= 1.0 && parts.fill >= 1.0 && parts.text >= 1.0 && !multiply { return None; } - let mut gs = Dict::new(); - gs.set(b"Type".to_vec(), Object::name("ExtGState")); - if multiply { - gs.set(b"BM".to_vec(), Object::name("Multiply")); - } - gs.set(b"CA".to_vec(), Object::Real(opacity)); - gs.set(b"ca".to_vec(), Object::Real(opacity)); + let gs = |stroke: f64, fill: f64| { + let mut gs = Dict::new(); + gs.set(b"Type".to_vec(), Object::name("ExtGState")); + if multiply { + gs.set(b"BM".to_vec(), Object::name("Multiply")); + } + gs.set(b"CA".to_vec(), Object::Real(stroke)); + gs.set(b"ca".to_vec(), Object::Real(fill)); + Object::Dict(gs) + }; let mut res = Dict::new(); - res.set(b"GS0".to_vec(), Object::Dict(gs)); + res.set(b"GS0".to_vec(), gs(parts.line, parts.fill)); + if parts.text != parts.fill { + res.set(b"GS1".to_vec(), gs(parts.line, parts.text)); + } Some(res) } @@ -313,10 +366,18 @@ fn stamp_turn(d: &Dict) -> i64 { /// The page `/Rotate` a text box's or Fill & Sign text's lines are turned back by /// (`/PCTextRotate`, written when it is added to a turned page). -fn text_turn(d: &Dict) -> i64 { +pub(crate) fn text_turn(d: &Dict) -> i64 { d.get(b"PCTextRotate").and_then(Object::as_int).unwrap_or(0).rem_euclid(360) / 90 * 90 } +/// A FreeText's `/RD`: how far its text box lies inside `/Rect` from the left, bottom, right and +/// top. A distance a hair below 0 (rounding) reads as 0; `None` when one is negative or they can't +/// be read. +pub(crate) fn inset(d: &Dict) -> Option<[f64; 4]> { + let rd: [f64; 4] = nums(d, b"RD")?.try_into().ok()?; + rd.iter().all(|x| x.is_finite() && *x > -0.001).then(|| rd.map(|x| x.max(0.0))) +} + /// The first text [`build`] would draw in the standard fonts (Helvetica, WinAnsiEncoding) that /// they can't, which would come out as `?`: what it is (for the message) and the character. The /// text of a text box, callout or Fill & Sign text, a line's caption, a measurement's label, a @@ -391,7 +452,9 @@ struct AppearanceContext<'a> { subtype: &'a [u8], rect: [f64; 4], cloudy: bool, + /// The line's opacity (`parts.line`). opacity: f64, + parts: PartOpacity, stroke: Option, width: f64, } @@ -408,7 +471,7 @@ impl AppearanceDrawing { fn new(context: &AppearanceContext<'_>) -> Self { let mut drawing = Self::default(); if let Some(gs) = ext_gstate( - context.opacity, + context.parts, context.subtype == b"Highlight" || (context.subtype == b"Ink" && context.dict.name(b"IT") == Some(b"FreehandHighlight")), ) { drawing.resources.set(b"ExtGState".to_vec(), Object::Dict(gs)); @@ -455,7 +518,8 @@ fn appearance_context(d: &Dict) -> Option> { subtype, rect, cloudy, - opacity: d.get(b"CA").and_then(|o| o.as_f64()).unwrap_or(1.0).clamp(0.0, 1.0), + opacity: part_opacity(d).line, + parts: part_opacity(d), stroke: color(d, b"C")?, width: border_width(d), }) @@ -845,46 +909,25 @@ fn draw_stamp(context: &AppearanceContext<'_>, mut drawing: AppearanceDrawing) - let [x0, y0, x1, y1] = draw; let (w, h) = (x1 - x0, y1 - y0); let lw = w.min(h) * 0.12; + // The strokes come from `FillMark::strokes`, which a copy's outline draws too. + let path = |mark: crate::FillMark| { + let ops: Vec = mark + .strokes(draw) + .iter() + .flat_map(|s| s.iter().enumerate().map(|(i, p)| format!("{} {} {}", n(p[0]), n(p[1]), if i == 0 { "m" } else { "l" }))) + .collect(); + format!("{} S\n", ops.join(" ")) + }; match name { - b"PCCheck" => c.push_str(&format!( - "{}{} w 1 J 1 j\n{} {} m {} {} l {} {} l S\n", - rg_stroke(col), - n(lw), - n(x0 + w * 0.15), - n(y0 + h * 0.5), - n(x0 + w * 0.4), - n(y0 + h * 0.2), - n(x0 + w * 0.88), - n(y0 + h * 0.85) - )), - b"PCCross" => c.push_str(&format!( - "{}{} w 1 J\n{} {} m {} {} l {} {} m {} {} l S\n", - rg_stroke(col), - n(lw), - n(x0 + w * 0.18), - n(y0 + h * 0.18), - n(x1 - w * 0.18), - n(y1 - h * 0.18), - n(x0 + w * 0.18), - n(y1 - h * 0.18), - n(x1 - w * 0.18), - n(y0 + h * 0.18) - )), + b"PCCheck" => c.push_str(&format!("{}{} w 1 J 1 j\n{}", rg_stroke(col), n(lw), path(crate::FillMark::Check))), + b"PCCross" => c.push_str(&format!("{}{} w 1 J\n{}", rg_stroke(col), n(lw), path(crate::FillMark::Cross))), b"PCDot" => { let r = w.min(h) * 0.3; c.push_str(&rg(col)); c.push_str(&ellipse(x0 + w / 2.0 - r, y0 + h / 2.0 - r, x0 + w / 2.0 + r, y0 + h / 2.0 + r)); c.push_str("f\n"); } - b"PCLine" => c.push_str(&format!( - "{}{} w 1 J\n{} {} m {} {} l S\n", - rg_stroke(col), - n(h.clamp(0.5, 2.0)), - n(x0), - n(y0 + h / 2.0), - n(x1), - n(y0 + h / 2.0) - )), + b"PCLine" => c.push_str(&format!("{}{} w 1 J\n{}", rg_stroke(col), n(h.clamp(0.5, 2.0)), path(crate::FillMark::Line))), other => { // Only stamps PdfCraft made: others keep their own artwork. if !matches!(d.get(b"PCStamp"), Some(Object::Bool(true))) { @@ -902,14 +945,59 @@ fn draw_stamp(context: &AppearanceContext<'_>, mut drawing: AppearanceDrawing) - Some(form(rect, c.as_bytes(), res)) } +/// The oval or circle (`shape`) around a text box whose whole box is `full`: its background +/// and border go into `c`; returns the text box inside it. +#[allow(clippy::too_many_arguments)] +fn shaped_border( + d: &Dict, + shape: crate::BorderShape, + full: [f64; 4], + turn: i64, + bw: f64, + bg: Option, + line_color: Rgb, + c: &mut String, +) -> Option<[f64; 4]> { + // Laid out as displayed: a quarter turn swaps the sides' differences. + let rect = match inset(d) { + Some(rd) => { + let (dx, dy) = if matches!(turn, 90 | 270) { (rd[1], rd[0]) } else { (rd[0], rd[1]) }; + [full[0] + dx, full[1] + dy, full[2] - dx, full[3] - dy] + } + None => shape.inside(full, bw, full), + }; + if rect[2] - rect[0] < 1.0 || rect[3] - rect[1] < 1.0 { + return None; + } + let h = bw / 2.0; + let [x0, y0, x1, y1] = [full[0] + h, full[1] + h, full[2] - h, full[3] - h]; + let path = match shape { + crate::BorderShape::Circle => { + let (cx, cy, r) = ((x0 + x1) / 2.0, (y0 + y1) / 2.0, (x1 - x0).min(y1 - y0) / 2.0); + ellipse(cx - r, cy - r, cx + r, cy + r) + } + _ => ellipse(x0, y0, x1, y1), + }; + if let Some(bg) = bg { + c.push_str(&format!("{}{path}f\n", rg(bg))); + } + if bw > 0.0 { + c.push_str(&format!("{}{} w\n{}{path}S\n[] 0 d\n", rg_stroke(line_color), n(bw), dash(d))); + } + Some(rect) +} + fn draw_free_text(context: &AppearanceContext<'_>, mut drawing: AppearanceDrawing) -> Option { let d = context.dict; + let parts = context.parts; let rect = context.rect; let stroke = context.stroke; let mut c = std::mem::take(&mut drawing.content); let mut res = std::mem::take(&mut drawing.resources); let _tail = std::mem::take(&mut drawing.tail); let (text_color, size) = parse_da(d); + // The box's border and a callout's leader line: their own colour, else the text's. + let line_color = da_border(d).unwrap_or(text_color); let bg = stroke; let bw = if d.contains(b"BS") || d.contains(b"Border") { border_width(d) } else { 0.0 }; // A callout: the leader line (arrowhead at its first point), and the text box inside @@ -948,7 +1036,7 @@ fn draw_free_text(context: &AppearanceContext<'_>, mut drawing: AppearanceDrawin if pts.len() < 2 || pts.iter().any(|p| !p.0.is_finite() || !p.1.is_finite()) { return None; } - c.push_str(&format!("{}{}{} w 1 J 1 j\n", rg_stroke(text_color), rg(bg.unwrap_or([1.0; 3])), n(lw))); + c.push_str(&format!("{}{}{} w 1 J 1 j\n", rg_stroke(line_color), rg(bg.unwrap_or([1.0; 3])), n(lw))); for (i, p) in pts.iter().enumerate() { c.push_str(&format!("{} {} {}\n", n(p.0), n(p.1), if i == 0 { "m" } else { "l" })); } @@ -957,26 +1045,40 @@ fn draw_free_text(context: &AppearanceContext<'_>, mut drawing: AppearanceDrawin return None; } } - if let Some(bg) = bg { - c.push_str(&format!("{}{} {} {} {} re f\n", rg(bg), n(rect[0]), n(rect[1]), n(rect[2] - rect[0]), n(rect[3] - rect[1]))); - } - if bw > 0.0 { - let h = bw / 2.0; - c.push_str(&format!( - "{}{} w\n{}{} {} {} {} re S\n[] 0 d\n", - rg_stroke(text_color), - n(bw), - dash(d), - n(rect[0] + h), - n(rect[1] + h), - n(rect[2] - rect[0] - bw), - n(rect[3] - rect[1] - bw) - )); + // An oval or a circle (`/PCBorderShape`) around the text box, which is `/Rect` inset by + // `/RD` and keeps its place: background and border take the shape, the text is laid out + // in the text box as in a rectangle. + let shape = crate::BorderShape::of(d); + if shape != crate::BorderShape::Rectangle { + rect = shaped_border(d, shape, full, turn, bw, bg, line_color, &mut c)?; + } else { + if let Some(bg) = bg { + c.push_str(&format!("{}{} {} {} {} re f\n", rg(bg), n(rect[0]), n(rect[1]), n(rect[2] - rect[0]), n(rect[3] - rect[1]))); + } + if bw > 0.0 { + let h = bw / 2.0; + c.push_str(&format!( + "{}{} w\n{}{} {} {} {} re S\n[] 0 d\n", + rg_stroke(line_color), + n(bw), + dash(d), + n(rect[0] + h), + n(rect[1] + h), + n(rect[2] - rect[0] - bw), + n(rect[3] - rect[1] - bw) + )); + } } let text = d.get(b"Contents").and_then(|o| o.as_string()).map(PdfString::to_text).unwrap_or_default(); let pad = 2.0 + bw; let width = (rect[2] - rect[0] - 2.0 * pad).max(1.0); - let q = d.int(b"Q").unwrap_or(0); + // In an oval or a circle the lines are centred in the text box, up and down too. + let round = shape != crate::BorderShape::Rectangle; + let q = if round { 1 } else { d.int(b"Q").unwrap_or(0) }; + // The text at its own opacity, where it has one. + if parts.text != parts.fill { + c.push_str("/GS1 gs\n"); + } c.push_str(&format!( "{} {} {} {} re W n\nBT\n/Helv {} Tf\n{}", n(rect[0]), @@ -987,8 +1089,12 @@ fn draw_free_text(context: &AppearanceContext<'_>, mut drawing: AppearanceDrawin rg(text_color) )); let mut out = c.into_bytes(); + let lines = wrap(&text, size, width); let mut y = rect[3] - pad - size * 0.9; - for line in wrap(&text, size, width) { + if round { + y -= ((rect[3] - rect[1] - 2.0 * pad - lines.len() as f64 * size * 1.2) / 2.0).max(0.0); + } + for line in lines { if y < rect[1] - size { break; } diff --git a/crates/annot/src/appearance/symbols.rs b/crates/annot/src/appearance/symbols.rs index 3b33662524..3178f78e94 100644 --- a/crates/annot/src/appearance/symbols.rs +++ b/crates/annot/src/appearance/symbols.rs @@ -1,4 +1,4 @@ -use super::{Dict, Object, PdfString, Rgb, Stream, color, ext_gstate, form, literal, n, nums, rg, rg_stroke, text_width, win_ansi}; +use super::{Dict, Object, PartOpacity, PdfString, Rgb, Stream, color, ext_gstate, form, literal, n, nums, rg, rg_stroke, text_width, win_ansi}; /// The label and colour of a standard rubber stamp name (ISO 32000-2 Table 184), for a stamp /// another program wrote without an appearance. Names are matched byte for byte, as PDF names @@ -51,7 +51,7 @@ pub(crate) fn display_stamp(d: &Dict) -> Option { // A malformed `/C` falls back to the stamp's own colour rather than hiding the stamp. let stroke = color(d, b"C").flatten(); let mut res = Dict::new(); - if let Some(gs) = ext_gstate(opacity, false) { + if let Some(gs) = ext_gstate(PartOpacity { line: opacity, fill: opacity, text: opacity }, false) { res.set(b"ExtGState".to_vec(), Object::Dict(gs)); } // A stamp whose intent (`/IT`, PDF 2.0) is an image or a snapshot has no `/Name` to default. diff --git a/crates/annot/src/create.rs b/crates/annot/src/create.rs index 1904745e95..6376655ce9 100644 --- a/crates/annot/src/create.rs +++ b/crates/annot/src/create.rs @@ -1,6 +1,6 @@ use super::draw::draw_appearance; use super::lookup::{annot_dict, annot_ref, annots, fill_sign_shape, page_ref, set_annots}; -use super::modify::{n, rich_text}; +use super::modify::{free_text_da, n, rich_text, set_part_keys, shape_text_box}; use super::types::{ FLAG_NO_ROTATE, FLAG_NO_ZOOM, FLAG_PRINT, LineEnding, Markup, Meta, NOTE_SIZE, NewAnnotation, OverlayLook, Rgb, Shape, StampGroup, Style, }; @@ -214,8 +214,13 @@ pub fn add_annotation(doc: &mut Document, new: &NewAnnotation, meta: &Meta) -> R let rect = rect_for(&new.shape, style)?; let mut d = base_dict(new.shape.subtype(), rect, page, &new.contents, &new.author, meta); d.set(b"Subj".to_vec(), PdfString::text(subject(&new.shape))); - let opacity = style.opacity.clamp(0.0, 1.0); - set_non_opaque_style(&mut d, opacity); + if style.fill_opacity.into_iter().chain(style.text_opacity).any(|o| !o.is_finite()) { + return Err(AnnotError::Invalid("invalid opacity".into())); + } + let line = style.opacity.clamp(0.0, 1.0); + let fill = style.fill_opacity.map_or(line, |o| o.clamp(0.0, 1.0)); + let text = style.text_opacity.map_or(fill, |o| o.clamp(0.0, 1.0)); + set_part_keys(&mut d, appearance::PartOpacity { line, fill, text }); let border = |d: &mut Dict| { let mut bs = Dict::new(); bs.set(b"W".to_vec(), Object::Real(style.width.max(0.0))); @@ -380,20 +385,22 @@ pub fn add_annotation(doc: &mut Document, new: &NewAnnotation, meta: &Meta) -> R d.set(b"IT".to_vec(), Object::name("FreeTextTypeWriter")); } let size = if font_size.is_finite() && *font_size > 0.0 { font_size.clamp(1.0, 400.0) } else { 12.0 }; - let [r, g, b] = style.color.map(|x| x.clamp(0.0, 1.0)); - d.set(b"DA".to_vec(), PdfString::literal(format!("{} {} {} rg /Helv {} Tf", n(r), n(g), n(b), n(size)).into_bytes())); + d.set(b"DA".to_vec(), free_text_da(style.color, style.border_color, size)); d.set(b"Q".to_vec(), Object::Int(0)); if let Some(f) = style.fill { d.set(b"C".to_vec(), rgb(f)); } border(&mut d); rich_text(&mut d); - // The text is laid out for the page as displayed, like a stamp's label. if !matches!(new.shape, Shape::Callout { .. }) { + // The text is laid out for the page as displayed, like a stamp's label. let turn = pdfcraft_model::pages(doc).get(new.page).map_or(0, |p| p.rotation(doc)); if matches!(turn, 90 | 180 | 270) { d.set(b"PCTextRotate".to_vec(), Object::Int(turn)); } + // An oval or a circle goes around the text box, its text wrapped as displayed: + // after `/PCTextRotate`, which swaps the box's sides on a quarter-turned page. + shape_text_box(&mut d, rect, style.border_shape, style.width); } } _ => {} @@ -421,7 +428,7 @@ pub fn add_annotation(doc: &mut Document, new: &NewAnnotation, meta: &Meta) -> R } fn validate_style(style: &Style) -> Result<(), AnnotError> { - if !finite(&style.color) || !style.opacity.is_finite() || !style.width.is_finite() { + if !finite(&style.color) || style.border_color.is_some_and(|c| !finite(&c)) || !style.opacity.is_finite() || !style.width.is_finite() { return Err(AnnotError::Invalid("invalid style".into())); } Ok(()) @@ -443,12 +450,6 @@ fn set_redaction_properties(dict: &mut Dict, style: &Style, quads: &[[f64; 8]], } } -fn set_non_opaque_style(dict: &mut Dict, opacity: f64) { - if opacity < 1.0 { - dict.set(b"CA".to_vec(), Object::Real(opacity)); - } -} - fn add_popup(doc: &mut Document, parent: ObjRef, rect: Option<[f64; 4]>, annots: &mut Vec) -> Result<(), AnnotError> { let Some(rect) = rect else { return Ok(()) }; let mut popup = Dict::new(); diff --git a/crates/annot/src/info.rs b/crates/annot/src/info.rs index 1a54dbc077..ba181d7504 100644 --- a/crates/annot/src/info.rs +++ b/crates/annot/src/info.rs @@ -2,7 +2,7 @@ use super::create::finite; use super::draw::set_appearance; use super::lookup::{annot_dict, annot_ref, annotation_flags, annots, drawn_upright, is_fill_sign, page_ref, page_refs}; use super::modify::{fillable, touch, unlocked}; -use super::types::{FLAG_LOCKED, LineEnding, Meta, NoteIcon, Rgb}; +use super::types::{BorderShape, FLAG_LOCKED, LineEnding, Meta, NoteIcon, Rgb}; use super::{AnnotError, Dict, Document, ObjRef, Object, PdfString, appearance}; // ── reading ───────────────────────────────────────────────────────────────────────────────── @@ -217,6 +217,15 @@ pub struct Props { pub fill: Option, /// Text boxes, typewriter text and callouts: the `/DA` font size in points. pub font_size: Option, + /// Text boxes, typewriter text and callouts: the border's own colour (`None`: the text's). + pub border_color: Option, + /// Text boxes and typewriter text: the border's shape (callouts have none to choose). + pub border_shape: Option, + /// How opaque the fill is drawn, for a comment with a fill control (`opacity` is then its + /// line's or border's). + pub fill_opacity: Option, + /// How opaque a text box's, typewriter text's or callout's text is drawn. + pub text_opacity: Option, } /// The current properties of the comment at `(page, index)`. @@ -239,7 +248,7 @@ pub fn props(doc: &Document, page: usize, index: usize) -> Option { author: text_value(doc, d, b"T").unwrap_or_default(), subject: text_value(doc, d, b"Subj").unwrap_or_default(), color, - opacity: d.get(b"CA").and_then(|o| o.as_f64()).unwrap_or(1.0), + opacity: appearance::part_opacity(d).line, width, icon: (subtype == "Text").then(|| d.name(b"Name").and_then(|n| NoteIcon::from_name(&String::from_utf8_lossy(n))).unwrap_or(NoteIcon::Note)), modified: text_value(doc, d, b"M"), @@ -248,6 +257,10 @@ pub fn props(doc: &Document, page: usize, index: usize) -> Option { fillable: fillable(&subtype), fill: fill_of(d), font_size: (subtype == "FreeText").then(|| appearance::parse_da(d).1), + border_color: (subtype == "FreeText").then(|| appearance::da_border(d)).flatten(), + border_shape: (subtype == "FreeText" && !d.contains(b"CL")).then(|| BorderShape::of(d)), + fill_opacity: fillable(&subtype).then(|| appearance::part_opacity(d).fill), + text_opacity: (subtype == "FreeText").then(|| appearance::part_opacity(d).text), subtype, endings: line_endings_of(d), }) diff --git a/crates/annot/src/lib.rs b/crates/annot/src/lib.rs index 4f24d04b08..52c0aad74f 100644 --- a/crates/annot/src/lib.rs +++ b/crates/annot/src/lib.rs @@ -41,13 +41,14 @@ pub use lookup::{ 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, + add_reply, add_text_replacement, deletable, delete_annotation, erase_ink, fillable, goes_with, lift_annotation, move_annotation, + set_border_color, set_border_shape, set_contents, set_fill, set_font_size, set_locked, set_marked, set_part_opacity, 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, + AttachIcon, BorderShape, FillMark, LineEnding, Markup, Meta, NOTE_SIZE, NewAnnotation, NoteIcon, OverlayFont, OverlayLook, ReviewState, Rgb, + Shape, StampGroup, StampKind, Style, StyleChange, TextReplacement, rect_quad, }; pub mod appearance; diff --git a/crates/annot/src/modify.rs b/crates/annot/src/modify.rs index a615b8e013..c7d87be090 100644 --- a/crates/annot/src/modify.rs +++ b/crates/annot/src/modify.rs @@ -5,8 +5,8 @@ use super::draw::{draw_appearance, redraw_or_restore, set_appearance}; use super::info::{line_endings_of, text_value}; use super::lookup::{annot_dict, annot_ref, annotation_flags, annots, page_ref, set_annots}; use super::types::{ - FLAG_HIDDEN, FLAG_LOCKED, FLAG_NO_ROTATE, FLAG_NO_ZOOM, FLAG_PRINT, LineEnding, Markup, Meta, NewAnnotation, ReviewState, Rgb, Shape, Style, - StyleChange, TextReplacement, + BorderShape, FLAG_HIDDEN, FLAG_LOCKED, FLAG_NO_ROTATE, FLAG_NO_ZOOM, FLAG_PRINT, LineEnding, Markup, Meta, NewAnnotation, ReviewState, Rgb, + Shape, Style, StyleChange, TextReplacement, }; use super::{AnnotError, Dict, Document, HashMap, HashSet, ObjRef, Object, PdfString, appearance}; @@ -159,10 +159,13 @@ pub fn with_replies_and_popups(doc: &Document, list: &[Object], doomed: impl Int } /// Change a comment's text. Text boxes are redrawn to show it, and their rectangle follows the -/// new text: the wrap width and top edge stay, the height fits the wrapped lines. +/// new text: the wrap width and top edge stay, the height fits the wrapped lines. A circle snug +/// around its text stays snug around the new text, centred where it was. pub fn set_contents(doc: &mut Document, page: usize, index: usize, text: &str, meta: &Meta) -> Result<(), AnnotError> { let (_, r) = annot_ref(doc, page, index)?; - let free_text = annot_dict(doc, r).name(b"Subtype") == Some(b"FreeText"); + let d = annot_dict(doc, r); + let free_text = d.name(b"Subtype") == Some(b"FreeText"); + let snug = free_text && is_snug(&d); doc.update_dict(r, |d| { d.set(b"Contents".to_vec(), PdfString::text(text)); // The rich-text version follows the new plain text (text boxes), or would contradict it. @@ -177,8 +180,16 @@ pub fn set_contents(doc: &mut Document, page: usize, index: usize, text: &str, m // The box grows and shrinks with the text instead of clipping it. A locked box keeps its // text editable (as in Acrobat), so the re-fit ignores the lock. New text is drawn even // where the standard fonts can't draw some of it (marked and reported, see - // `draw_appearance`). - match fitted_box(doc, r, text) { + // `draw_appearance`). A circle snug around its text stays snug around the new text; one + // made larger by hand keeps its size, only growing for more lines. + let fit = if snug { + snug_refit(doc, r) + } else { + let d = annot_dict(doc, r); + let circle = text_box_of(&d).filter(|_| BorderShape::of(&d) == BorderShape::Circle); + fitted_box(doc, r, text).map(|fit| circle.map_or(fit, |old| [fit[0], fit[1].min(old[1]), fit[2], fit[3]])) + }; + match fit { Some(rect) => apply_text_box(doc, r, rect, meta, true)?, None => draw_appearance(doc, r)?, } @@ -197,11 +208,12 @@ fn fitted_box(doc: &Document, r: ObjRef, text: &str) -> Option<[f64; 4]> { let rect = nums(b"Rect").filter(|v| v.len() == 4 && v.iter().all(|x| x.is_finite()))?; let rect = [rect[0], rect[1], rect[2], rect[3]]; // A callout re-fits its text box (`/Rect` inset by `/RD`); the leader line keeps its place. + // So does a text box inside an oval or a circle. let tb = if d.contains(b"CL") { let rd = nums(b"RD").filter(|v| v.len() == 4 && v.iter().all(|x| *x >= 0.0))?; [rect[0] + rd[0], rect[1] + rd[1], rect[2] - rd[2], rect[3] - rd[3]] } else { - rect + text_box_of(&d).unwrap_or(rect) }; let (x0, top) = (tb[0].min(tb[2]), tb[1].max(tb[3])); let w = tb[2] - tb[0]; @@ -388,9 +400,134 @@ pub fn set_rect(doc: &mut Document, page: usize, index: usize, rect: [f64; 4], m if !matches!(subtype.as_str(), "Square" | "Circle" | "FreeText") { return Err(AnnotError::Invalid(format!("{subtype} comments can't be resized"))); } + // An oval's or a circle's frame is resized: its text box follows inside. + let shape = if subtype == "FreeText" { BorderShape::of(&d) } else { BorderShape::Rectangle }; + let rect = match (shape, text_box_of(&d)) { + (BorderShape::Rectangle, _) | (_, None) => rect, + // A circle's text box keeps its proportions and reaches the circle with its longer sides; + // the circle then goes around it again, never closer than its text allows. + (BorderShape::Circle, Some(was)) => { + let (o, w) = (normalize(rect), normalize(was)); + let (cx, cy, r) = ((o[0] + o[2]) / 2.0, (o[1] + o[3]) / 2.0, (o[2] - o[0]).min(o[3] - o[1]) / 2.0); + let (wx, wy) = ((w[2] - w[0]) / 2.0, (w[3] - w[1]) / 2.0); + let k = r / wx.max(wy).max(1e-6); + let (ix, iy) = ((wx * k).max(0.5), (wy * k).max(0.5)); + [cx - ix, cy - iy, cx + ix, cy + iy] + } + (shape, Some(was)) => shape.inside(rect, border_width_of(&d), was), + }; apply_text_box(doc, r, rect, meta, false) } +/// A FreeText's text box: `/Rect` inset by `/RD` for a callout or a text box inside an oval or a +/// circle, else `/Rect`. `None` when they can't be read. +pub(crate) fn text_box_of(d: &Dict) -> Option<[f64; 4]> { + let nums = |key: &[u8]| -> Option> { d.get(key)?.as_array()?.iter().map(|o| o.as_f64()).collect() }; + let rect = normalize(four(&nums(b"Rect")?)?); + if !d.contains(b"CL") && BorderShape::of(d) == BorderShape::Rectangle { + return Some(rect); + } + let rd = appearance::inset(d)?; + let tb = [rect[0] + rd[0], rect[1] + rd[1], rect[2] - rd[2], rect[3] - rd[3]]; + (tb[2] - tb[0] >= 1.0 && tb[3] - tb[1] >= 1.0).then_some(tb) +} + +/// Give text box or typewriter text `d`, whose text box is `tb`, the border `shape` (`width` +/// wide): `/Rect` around it, `/RD` and `/PCBorderShape`, or for a rectangle `/Rect` the text +/// box itself again. +pub(crate) fn shape_text_box(d: &mut Dict, tb: [f64; 4], shape: BorderShape, width: f64) { + // A circle goes around the text as the box lays it out. + let text = (shape == BorderShape::Circle).then(|| text_extent(d, displayed_sides(d, tb).0 - 2.0 * (2.0 + width.max(0.0)))); + let outer = shape.around(tb, width, text); + d.set(b"Rect".to_vec(), num_array(&outer)); + if shape == BorderShape::Rectangle { + d.remove(b"PCBorderShape"); + d.remove(b"RD"); + } else { + d.set(b"PCBorderShape".to_vec(), Object::name(shape.name())); + // A circle touching the text box's sides would put them a rounding error outside it. + let tb = normalize(tb); + let rd = [tb[0] - outer[0], tb[1] - outer[1], outer[2] - tb[2], outer[3] - tb[3]].map(|x| x.max(0.0)); + d.set(b"RD".to_vec(), num_array(&rd)); + } +} + +/// The width of the widest line and the height of the lines of FreeText `d`'s text, as its +/// appearance lays the text out `wrap` wide. +fn text_extent(d: &Dict, wrap: f64) -> [f64; 2] { + let text = d.get(b"Contents").and_then(|o| o.as_string()).map(PdfString::to_text).unwrap_or_default(); + let (_, size) = appearance::parse_da(d); + let lines = appearance::wrap(&text, size, wrap.max(1.0)); + let widest = lines.iter().map(|l| appearance::text_width(l, size)).fold(0.0, f64::max); + [widest, lines.len().max(1) as f64 * size * 1.2] +} + +/// The width and height of FreeText `d`'s text box `tb` as displayed: swapped on a page turned by +/// a quarter, where its text is laid out upright. +fn displayed_sides(d: &Dict, tb: [f64; 4]) -> (f64, f64) { + let tb = normalize(tb); + let (w, h) = (tb[2] - tb[0], tb[3] - tb[1]); + if matches!(appearance::text_turn(d), 90 | 270) { (h, w) } else { (w, h) } +} + +/// FreeText `d`'s text box `tb`, with a border `width` wide, made as large as its text wrapped +/// `wrap` wide needs (its widest line and its lines, inside the padding a box sized to its text +/// has) and centred where it was: a circle goes around this, not around a box wider than its text. +fn snug_text_box(d: &Dict, tb: [f64; 4], width: f64, wrap: f64) -> [f64; 4] { + let tb = normalize(tb); + let pad = 2.0 + width.max(0.0); + let [w, h] = text_extent(d, wrap); + let (hx, hy) = (w / 2.0 + pad + 2.0, h / 2.0 + pad + 1.0); + let (hx, hy) = if matches!(appearance::text_turn(d), 90 | 270) { (hy, hx) } else { (hx, hy) }; + let (cx, cy) = ((tb[0] + tb[2]) / 2.0, (tb[1] + tb[3]) / 2.0); + [cx - hx, cy - hy, cx + hx, cy + hy] +} + +/// Whether FreeText `d` is a circle whose text box is snug around its text ([`snug_text_box`]): +/// it then follows its text as that changes, where one made larger by hand keeps its size. +fn is_snug(d: &Dict) -> bool { + let Some(tb) = text_box_of(d).filter(|_| BorderShape::of(d) == BorderShape::Circle) else { return false }; + let width = border_width_of(d); + let s = snug_text_box(d, tb, width, displayed_sides(d, tb).0 - 2.0 * (2.0 + width)); + let tb = normalize(tb); + ((s[2] - s[0]) - (tb[2] - tb[0])).abs() < 0.5 && ((s[3] - s[1]) - (tb[3] - tb[1])).abs() < 0.5 +} + +/// The text box of a circle snug around its text for the text and size it has now: its lines up to +/// 300 pt wide, centred where it was. +fn snug_refit(doc: &Document, r: ObjRef) -> Option<[f64; 4]> { + let d = annot_dict(doc, r); + let width = border_width_of(&d); + Some(snug_text_box(&d, text_box_of(&d)?, width, 300.0 - 2.0 * (2.0 + width))) +} + +/// Give a text box or typewriter text an oval, a circle or a rectangle for its border, and redraw +/// it. Its text box keeps its place; the oval or circle goes around it. For a circle the text box +/// first shrinks to its text, its lines wrapped as they are. +pub fn set_border_shape(doc: &mut Document, page: usize, index: usize, shape: BorderShape, meta: &Meta) -> Result<(), AnnotError> { + let (_, r) = annot_ref(doc, page, index)?; + unlocked(doc, r)?; + let d = annot_dict(doc, r); + if d.name(b"Subtype") != Some(b"FreeText") || d.contains(b"CL") { + return Err(AnnotError::Invalid("only text boxes and typewriter text have a border shape".into())); + } + let tb = text_box_of(&d).ok_or_else(|| AnnotError::Invalid("the text box can't be read".into()))?; + let tb = match shape { + BorderShape::Circle => { + let width = border_width_of(&d); + snug_text_box(&d, tb, width, displayed_sides(&d, tb).0 - 2.0 * (2.0 + width)) + } + _ => tb, + }; + refuse_foreign_text(doc, &d)?; + let before = d; + doc.update_dict(r, |d| { + shape_text_box(d, tb, shape, border_width_of(d)); + touch(d, meta); + })?; + redraw_or_restore(doc, r, before) +} + /// At most this many points reshape a comment (a drawn polygon has a handful). const MAX_POINTS: usize = 100_000; @@ -503,6 +640,8 @@ fn apply_text_box(doc: &mut Document, r: ObjRef, rect: [f64; 4], meta: &Meta, ne } None => (rect, None), }; + let (shape, width) = (BorderShape::of(&d), border_width_of(&d)); + let free_text = d.name(b"Subtype") == Some(b"FreeText"); doc.update_dict(r, |d| { d.set(b"Rect".to_vec(), num_array(&outer)); match &cl { @@ -510,6 +649,8 @@ fn apply_text_box(doc: &mut Document, r: ObjRef, rect: [f64; 4], meta: &Meta, ne d.set(b"CL".to_vec(), num_array(l)); d.set(b"RD".to_vec(), num_array(&[rect[0] - outer[0], rect[1] - outer[1], outer[2] - rect[2], outer[3] - rect[3]])); } + // An oval or a circle goes around the text box again. + None if free_text => shape_text_box(d, rect, shape, width), None => { d.remove(b"RD"); } @@ -528,6 +669,8 @@ fn apply_text_box(doc: &mut Document, r: ObjRef, rect: [f64; 4], meta: &Meta, ne } } +/// The border width as the appearance draws it: `/BS /W`, else the third number of `/Border` +/// (another app's), else 1. fn border_width_of(d: &Dict) -> f64 { appearance::border_width(d) } @@ -558,7 +701,8 @@ fn ink_rect_for_width(d: &Dict, old_w: f64, w: f64) -> Option<[f64; 4]> { Some([inner[0] - base[0] - new_half, inner[1] - base[1] - new_half, inner[2] + base[2] + new_half, inner[3] + base[3] + new_half]) } -/// Change a comment's colour, opacity, line width and/or line endings, and redraw it. +/// Change a comment's colour, opacity (of the whole comment), line width and/or line endings, and +/// redraw it. pub fn set_style(doc: &mut Document, page: usize, index: usize, change: StyleChange, meta: &Meta) -> Result<(), AnnotError> { let StyleChange { color, opacity, width, endings } = change; let (_, r) = annot_ref(doc, page, index)?; @@ -581,25 +725,34 @@ pub fn set_style(doc: &mut Document, page: usize, index: usize, change: StyleCha } refuse_foreign_text(doc, &d)?; let free_text = subtype == "FreeText"; + // Typewriter text has no box of its own: a border goes around its text, so the box grows + // (or shrinks) by the change on every side and the text keeps its place and its lines. + // So does a text box inside an oval or a circle, which goes around it again. + let shape = if free_text { BorderShape::of(&d) } else { BorderShape::Rectangle }; + let typewriter = free_text && (d.name(b"IT") == Some(b"FreeTextTypeWriter") || shape != BorderShape::Rectangle) && !d.contains(b"CL"); + let regrow = width.filter(|_| typewriter).and_then(|w| { + let by = w.max(0.0) - if d.contains(b"BS") || d.contains(b"Border") { border_width_of(&d) } else { 0.0 }; + let rect = grow(text_box_of(&d)?, by); + (by != 0.0 && finite(&rect) && rect[2] - rect[0] >= 1.0 && rect[3] - rect[1] >= 1.0).then_some((rect, w.max(0.0))) + }); let before = d; doc.update_dict(r, |d| { + if let Some((rect, w)) = regrow { + shape_text_box(d, rect, shape, w); + } if let Some(c) = color { if free_text { let (_, size) = appearance::parse_da(d); - let [r, g, b] = c.map(|x| x.clamp(0.0, 1.0)); - d.set(b"DA".to_vec(), PdfString::literal(format!("{} {} {} rg /Helv {} Tf", n(r), n(g), n(b), n(size)).into_bytes())); + d.set(b"DA".to_vec(), free_text_da(c, appearance::da_border(d), size)); rich_text(d); } else { d.set(b"C".to_vec(), rgb(c)); } } + // The whole comment: its fill and text drop opacities of their own. if let Some(o) = opacity { let o = o.clamp(0.0, 1.0); - if o < 1.0 { - d.set(b"CA".to_vec(), Object::Real(o)); - } else { - d.remove(b"CA"); - } + set_part_keys(d, appearance::PartOpacity { line: o, fill: o, text: o }); } if let Some(w) = width { let old_w = border_width_of(d); @@ -629,6 +782,37 @@ pub fn set_style(doc: &mut Document, page: usize, index: usize, change: StyleCha redraw_or_restore(doc, r, before) } +/// A FreeText's `/DA`: the text colour, the border's own colour when it has one (the stroking +/// colour, `RG`), Helvetica at `size`. +pub(crate) fn free_text_da(text: Rgb, border: Option, size: f64) -> PdfString { + let [r, g, b] = text.map(|x| x.clamp(0.0, 1.0)); + let stroke = border.map(|c| c.map(|x| x.clamp(0.0, 1.0))).map(|[r, g, b]| format!("{} {} {} RG ", n(r), n(g), n(b))).unwrap_or_default(); + PdfString::literal(format!("{} {} {} rg {stroke}/Helv {} Tf", n(r), n(g), n(b), n(size)).into_bytes()) +} + +/// Give a text box, typewriter text or callout a border colour of its own (`None`: the text's +/// again), and redraw it. +pub fn set_border_color(doc: &mut Document, page: usize, index: usize, color: Option, meta: &Meta) -> Result<(), AnnotError> { + let (_, r) = annot_ref(doc, page, index)?; + unlocked(doc, r)?; + let d = annot_dict(doc, r); + if d.name(b"Subtype") != Some(b"FreeText") { + return Err(AnnotError::Invalid("only text boxes, typewriter text and callouts have a border colour".into())); + } + if color.is_some_and(|c| !finite(&c)) { + return Err(AnnotError::Invalid("invalid colour".into())); + } + refuse_foreign_text(doc, &d)?; + let before = d; + doc.update_dict(r, |d| { + let (text, size) = appearance::parse_da(d); + d.set(b"DA".to_vec(), free_text_da(text, color, size)); + rich_text(d); + touch(d, meta); + })?; + redraw_or_restore(doc, r, before) +} + /// Change the font size of a text box, typewriter text or callout (`/DA` keeps its colour; the /// rich-text strings follow) and redraw it. The box grows to hold the wrapped text at the new /// size and never shrinks, so a box the user drew large stays large. Sizes are 1 to 400 pt. @@ -643,26 +827,27 @@ pub fn set_font_size(doc: &mut Document, page: usize, index: usize, size: f64, m return Err(AnnotError::Invalid("font size must be 1\u{2013}400 pt".into())); } refuse_foreign_text(doc, &d)?; + let snug = is_snug(&d); let before = d; doc.update_dict(r, |d| { let (col, _) = appearance::parse_da(d); - d.set(b"DA".to_vec(), PdfString::literal(format!("{} {} {} rg /Helv {} Tf", n(col[0]), n(col[1]), n(col[2]), n(size)).into_bytes())); + d.set(b"DA".to_vec(), free_text_da(col, appearance::da_border(d), size)); rich_text(d); touch(d, meta); })?; let text = text_value(doc, &annot_dict(doc, r), b"Contents").unwrap_or_default(); - let result = match fitted_box(doc, r, &text) { - Some(fit) => { + let result = match (snug, if snug { snug_refit(doc, r) } else { fitted_box(doc, r, &text) }) { + // A circle snug around its text stays snug around it at the new size. + (true, Some(fit)) => apply_text_box(doc, r, fit, meta, false), + (false, Some(fit)) => { let cur = annot_dict(doc, r); - let nums: Vec = - cur.get(b"Rect").and_then(|o| o.as_array()).map(|a| a.iter().filter_map(|x| x.as_f64()).collect()).unwrap_or_default(); // Keep the top and sides; only the bottom edge moves, and only downwards. - match four(&nums).map(normalize) { + match text_box_of(&cur) { Some(old) if !cur.contains(b"CL") => apply_text_box(doc, r, [fit[0], fit[1].min(old[1]), fit[2], fit[3]], meta, false), _ => apply_text_box(doc, r, fit, meta, false), } } - None => redraw_or_restore(doc, r, before.clone()), + (_, None) => redraw_or_restore(doc, r, before.clone()), }; if result.is_err() { doc.set(r, Object::Dict(before)); @@ -707,6 +892,63 @@ pub fn set_fill(doc: &mut Document, page: usize, index: usize, fill: Option redraw_or_restore(doc, r, before) } +/// Draw a rectangle's, oval's, polygon's or text box's fill, or a text box's text, at an +/// opacity of its own (0–1), its line or border keeping the comment's (`/CA`), and redraw it. +/// `None` leaves that part as it is drawn now. The fill goes in `/ca` (PDF 2.0's opacity for +/// what is filled), the text in `/PCTextOpacity`, each only where it differs from the one it +/// would otherwise follow. +pub fn set_part_opacity(doc: &mut Document, page: usize, index: usize, fill: Option, text: Option, meta: &Meta) -> Result<(), AnnotError> { + let (_, r) = annot_ref(doc, page, index)?; + unlocked(doc, r)?; + let d = annot_dict(doc, r); + let subtype = String::from_utf8_lossy(d.name(b"Subtype").unwrap_or_default()).into_owned(); + if fill.is_some() && !fillable(&subtype) { + return Err(AnnotError::Invalid("only rectangles, ovals, polygons and text boxes have a fill of their own".into())); + } + if text.is_some() && subtype != "FreeText" { + return Err(AnnotError::Invalid("only text boxes, typewriter text and callouts have text of their own".into())); + } + if fill.into_iter().chain(text).any(|o| !o.is_finite()) { + return Err(AnnotError::Invalid("invalid opacity".into())); + } + // Check before changing anything: a stale appearance would contradict the new opacity. + if appearance::build(&d).is_none() { + return Err(AnnotError::Unsupported(subtype)); + } + refuse_foreign_text(doc, &d)?; + let before = d; + doc.update_dict(r, |d| { + let mut parts = appearance::part_opacity(d); + if let Some(f) = fill { + parts.fill = f.clamp(0.0, 1.0); + } + if let Some(t) = text { + parts.text = t.clamp(0.0, 1.0); + } + set_part_keys(d, parts); + touch(d, meta); + })?; + redraw_or_restore(doc, r, before) +} + +/// Write a comment's parts' opacities (see [`appearance::PartOpacity`]): the line's as `/CA`, the +/// fill's as `/ca` and the text's as `/PCTextOpacity`, each only where it differs from the one +/// it would otherwise follow (the fill the line, the text the fill), so a comment drawn at one +/// opacity keeps just `/CA`. +pub(crate) fn set_part_keys(d: &mut Dict, parts: appearance::PartOpacity) { + let appearance::PartOpacity { line, fill, text } = parts; + let mut put = |key: &[u8], value: f64, unless: f64| { + if value == unless { + d.remove(key); + } else { + d.set(key.to_vec(), Object::Real(value)); + } + }; + put(b"CA", line, 1.0); + put(b"ca", fill, line); + put(b"PCTextOpacity", text, fill); +} + /// Grow a line or polyline's rectangle so a non-`None` ending is not clipped. Idempotent. fn ensure_ending_room(d: &mut Dict) { let subtype = d.name(b"Subtype").unwrap_or_default(); diff --git a/crates/annot/src/tests.rs b/crates/annot/src/tests.rs index 2ff781a3a5..ff7f8925f0 100644 --- a/crates/annot/src/tests.rs +++ b/crates/annot/src/tests.rs @@ -2,6 +2,7 @@ use std::sync::Arc; use pdfcraft_cos::{Document, ObjRef, Object, SaveOptions, write_incremental}; +use super::modify::text_box_of; use super::*; /// Two pages. Page 1 has an inline Square annotation in a direct /Annots array; page 2 has an @@ -40,7 +41,7 @@ fn new(page: usize, shape: Shape) -> NewAnnotation { NewAnnotation { page, shape, - style: Style { color: [0.0, 0.4, 1.0], opacity: 1.0, width: 2.0, fill: None }, + style: Style { color: [0.0, 0.4, 1.0], opacity: 1.0, width: 2.0, fill: None, ..Style::default() }, contents: "hello".into(), author: "Ada".into(), } @@ -356,6 +357,296 @@ fn restyle_and_resize_redraw_the_appearance() { assert!(matches!(set_rect(&mut doc, 0, l, [0.0, 0.0, 5.0, 5.0], &meta("")), Err(AnnotError::Invalid(_)))); } +/// Typed text or a text box takes an oval or a circle for its border: the text box keeps its +/// place and the shape goes around it (`/Rect` grows, `/RD` holds the text box, `/PCBorderShape` +/// the shape); back to a rectangle, it is the text box it was. A resized frame takes its text box +/// along, a thicker border leaves it where it is. +#[test] +fn text_boxes_take_an_oval_or_a_circle_around_their_text() { + let close = |a: &[f64], b: &[f64]| a.len() == b.len() && a.iter().zip(b).all(|(x, y)| (x - y).abs() < 0.01); + let nums = |d: &Dict, k: &[u8]| -> Vec { + d.get(k).and_then(|o| o.as_array()).map(|a| a.iter().filter_map(|x| x.as_f64()).collect()).unwrap_or_default() + }; + // Where the text starts: its first line's text matrix. + let text_at = |doc: &Document, d: &Dict| ap_content(doc, d).lines().find(|l| l.ends_with(" Tm") || l.contains(" Tm ")).map(str::to_owned); + let mut doc = fixture(); + let mut tw = new(0, Shape::Typewriter { rect: [100.0, 100.0, 200.0, 120.0], font_size: 10.0 }); + tw.style.width = 1.0; + let t = add_annotation(&mut doc, &tw, &meta("t")).unwrap(); + // In an oval or a circle the text is centred in its text box (left-aligned in a box): one + // line of "hello" at 10 pt in the 100 × 20 text box centred on (150, 110), 3 pt from its top. + let centred = format!("1 0 0 1 {} {} Tm (hello) Tj", n(150.0 - appearance::text_width("hello", 10.0) / 2.0), n(107.0)); + assert!(text_at(&doc, &list(&doc, 0)[t]).is_some_and(|l| l.starts_with("1 0 0 1 103 ")), "a box: left-aligned"); + set_border_shape(&mut doc, 0, t, BorderShape::Oval, &meta("")).unwrap(); + let doc2 = reopen(&doc); + let d = &list(&doc2, 0)[t]; + // Around the 100 × 20 text box, centred: √2 its size, two points more for the 1 pt border. + let (ax, ay) = (50.0 * std::f64::consts::SQRT_2 + 2.0, 10.0 * std::f64::consts::SQRT_2 + 2.0); + assert!(close(&rect(d), &[150.0 - ax, 110.0 - ay, 150.0 + ax, 110.0 + ay]), "{:?}", rect(d)); + assert!(close(&nums(d, b"RD"), &[ax - 50.0, ay - 10.0, ax - 50.0, ay - 10.0]), "{:?}", nums(d, b"RD")); + assert_eq!(d.name(b"PCBorderShape"), Some(&b"Oval"[..])); + let ap = ap_content(&doc2, d); + assert!(ap.contains(" c\n") && ap.contains("S\n") && !ap.contains("re S"), "an oval, not a box: {ap}"); + assert_eq!(text_at(&doc2, d).as_deref(), Some(centred.as_str()), "the text keeps its place"); + assert_eq!(props(&doc2, 0, t).unwrap().border_shape, Some(BorderShape::Oval)); + // A circle around the text: the text box shrinks to "hello" with its padding, centred where it + // was, and the circle touches its sides (the text a point clear of the border inside). + set_border_shape(&mut doc, 0, t, BorderShape::Circle, &meta("")).unwrap(); + let d = &list(&doc, 0)[t]; + let hw = appearance::text_width("hello", 10.0) / 2.0; + let r = (hw + 5.0).max(hw.hypot(6.0) + 2.0); + assert!(close(&rect(d), &[150.0 - r, 110.0 - r, 150.0 + r, 110.0 + r]), "{:?}", rect(d)); + assert!(close(&nums(d, b"RD"), &[r - hw - 5.0, r - 10.0, r - hw - 5.0, r - 10.0]), "{:?}", nums(d, b"RD")); + assert_eq!(text_at(&doc, d).as_deref(), Some(centred.as_str())); + // A thicker border: the typed text's box grows by the change on every side, so its text keeps + // its place inside the thicker line (as with a rectangle), and the circle goes around that. + set_style(&mut doc, 0, t, StyleChange::new(None, None, Some(3.0), None), &meta("")).unwrap(); + let d = &list(&doc, 0)[t]; + assert_eq!(text_at(&doc, d).as_deref(), Some(centred.as_str())); + let r3 = (hw + 7.0).max(hw.hypot(6.0) + 4.0); + assert!(close(&rect(d), &[150.0 - r3, 110.0 - r3, 150.0 + r3, 110.0 + r3]), "{:?}", rect(d)); + // Its frame resized: the text box follows inside, keeping its proportions, its longer sides + // reaching the circle. + set_rect(&mut doc, 0, t, [150.0 - 2.0 * r3, 110.0 - 2.0 * r3, 150.0 + 2.0 * r3, 110.0 + 2.0 * r3], &meta("")).unwrap(); + let d = &list(&doc, 0)[t]; + let rd = nums(d, b"RD"); + let tb = [rect(d)[0] + rd[0], rect(d)[1] + rd[1], rect(d)[2] - rd[2], rect(d)[3] - rd[3]]; + assert!(((tb[2] - tb[0]) / (tb[3] - tb[1]) - (hw + 7.0) / 12.0).abs() < 0.01, "the text box keeps its proportions: {tb:?}"); + assert!(close(&rect(d), &[150.0 - 2.0 * r3, 110.0 - 2.0 * r3, 150.0 + 2.0 * r3, 110.0 + 2.0 * r3]), "{:?}", rect(d)); + // A rectangle again: the text box it has, nothing around it. + set_border_shape(&mut doc, 0, t, BorderShape::Rectangle, &meta("")).unwrap(); + let d = &list(&doc, 0)[t]; + assert!(close(&rect(d), &tb), "{:?} vs {tb:?}", rect(d)); + assert!(!d.contains(b"RD") && !d.contains(b"PCBorderShape")); + assert!(ap_content(&doc, d).contains("re S")); + + // A filled text box made with an oval: the background takes the shape too. + let mut tb = new(0, Shape::TextBox { rect: [300.0, 500.0, 400.0, 540.0], font_size: 12.0 }); + (tb.style.fill, tb.style.width, tb.style.border_shape) = (Some([1.0, 1.0, 0.6]), 1.0, BorderShape::Oval); + let b = add_annotation(&mut doc, &tb, &meta("b")).unwrap(); + let d = &list(&doc, 0)[b]; + assert_eq!(d.name(b"PCBorderShape"), Some(&b"Oval"[..])); + let ap = ap_content(&doc, d); + assert!(ap.contains("1 1 0.6 rg") && ap.contains(" c\nh\nf\n") && !ap.contains(" re f"), "{ap}"); + // A callout's border stays a rectangle. + let c = add_annotation( + &mut doc, + &new( + 0, + Shape::Callout { + rect: [300.0, 300.0, 400.0, 340.0], + knee: [280.0, 320.0], + point: [250.0, 280.0], + ending: LineEnding::OpenArrow, + font_size: 10.0, + }, + ), + &meta("c"), + ) + .unwrap(); + assert!(matches!(set_border_shape(&mut doc, 0, c, BorderShape::Oval, &meta("")), Err(AnnotError::Invalid(_)))); + assert_eq!(props(&doc, 0, c).unwrap().border_shape, None); + assert_eq!(BorderShape::parse("CIRCLE"), Some(BorderShape::Circle)); +} + +/// A circle goes snug around short text, as a number on a drawing is circled: the text box is no +/// wider than its text needs and the circle touches its sides, where one through the box's corners +/// stood well clear. It follows the text and its size as they change; one made larger by hand +/// keeps its size. +#[test] +fn a_circle_goes_snug_around_its_text_and_follows_it() { + let close = |a: (f64, f64), b: (f64, f64)| (a.0 - b.0).abs() < 0.01 && (a.1 - b.1).abs() < 0.01; + let mut doc = fixture(); + // "3" at 10 pt with a 1 pt border, in the box Fill & Sign sizes to it: the digit with 2 pt of + // padding and 4 pt to spare across, a line and 6 pt down, the border around that. + let w3 = appearance::text_width("3", 10.0); + let mut typed = new(0, Shape::Typewriter { rect: [100.0, 680.0, 110.0 + w3, 700.0], font_size: 10.0 }); + (typed.contents, typed.style.width, typed.style.border_shape) = ("3".into(), 1.0, BorderShape::Circle); + let t = add_annotation(&mut doc, &typed, &meta("t")).unwrap(); + let frame = |doc: &Document| { + let r = rect(&list(doc, 0)[t]); + ((r[2] - r[0], r[3] - r[1]), ((r[0] + r[2]) / 2.0, (r[1] + r[3]) / 2.0)) + }; + let centre = (105.0 + w3 / 2.0, 690.0); + // As tall as the box, 20 pt across: through the corners it was 29. + assert!(close(frame(&doc).0, (20.0, 20.0)) && close(frame(&doc).1, centre), "{:?}", frame(&doc)); + // The text box Fill & Sign gives a box to type into, 40 pt wide: a circle goes snug around its + // text there too. + let mut wide = typed.clone(); + wide.shape = Shape::Typewriter { rect: [300.0, 680.0, 342.0, 700.0], font_size: 10.0 }; + wide.style.border_shape = BorderShape::Rectangle; + let b = add_annotation(&mut doc, &wide, &meta("b")).unwrap(); + set_border_shape(&mut doc, 0, b, BorderShape::Circle, &meta("")).unwrap(); + let r = rect(&list(&doc, 0)[b]); + assert!(close((r[2] - r[0], r[3] - r[1]), (20.0, 20.0)), "{r:?}"); + // More text: the circle grows with it, about the same centre; less, and it shrinks back. + set_contents(&mut doc, 0, t, "123", &meta("")).unwrap(); + let w = appearance::text_width("123", 10.0) / 2.0; + let d = 2.0 * (w + 5.0).max(10.0).max(w.hypot(6.0) + 2.0); + assert!(close(frame(&doc).0, (d, d)) && close(frame(&doc).1, centre), "{:?}", frame(&doc)); + set_contents(&mut doc, 0, t, "3", &meta("")).unwrap(); + assert!(close(frame(&doc).0, (20.0, 20.0)) && close(frame(&doc).1, centre), "{:?}", frame(&doc)); + // A larger font: a larger circle, still snug. + set_font_size(&mut doc, 0, t, 20.0, &meta("")).unwrap(); + let w = appearance::text_width("3", 20.0) / 2.0; + let d = 2.0 * (w + 5.0).max(16.0).max(w.hypot(12.0) + 2.0); + assert!(close(frame(&doc).0, (d, d)) && close(frame(&doc).1, centre), "{:?}", frame(&doc)); + set_font_size(&mut doc, 0, t, 10.0, &meta("")).unwrap(); + assert!(close(frame(&doc).0, (20.0, 20.0)), "{:?}", frame(&doc)); + // Made larger by hand, it keeps its size as its text changes. + set_rect(&mut doc, 0, t, [centre.0 - 20.0, centre.1 - 20.0, centre.0 + 20.0, centre.1 + 20.0], &meta("")).unwrap(); + assert!(close(frame(&doc).0, (40.0, 40.0)), "{:?}", frame(&doc)); + set_contents(&mut doc, 0, t, "4", &meta("")).unwrap(); + assert!(close(frame(&doc).0, (40.0, 40.0)) && close(frame(&doc).1, centre), "{:?}", frame(&doc)); +} + +/// A circle around a line wider than it is tall touches its text box's sides: `/RD` is 0 there, +/// not a rounding error below it, and a hair below 0 still reads. (A text box that couldn't be +/// read stopped following its text, and its text wrapped in a narrower one.) The circle keeps its +/// centre as its text changes. +#[test] +fn a_circle_touching_its_text_box_keeps_following_its_text() { + let mut doc = fixture(); + // Sized to its text: 2 pt of padding and half a point to spare across, a line down. + let (w, h) = (appearance::text_width("Testtext", 12.0) + 4.5, 12.0 * 1.11 + 4.0); + let mut b = new(0, Shape::TextBox { rect: [210.79, 700.0 - h, 210.79 + w, 700.0], font_size: 12.0 }); + (b.contents, b.style.width) = ("Testtext".into(), 0.0); + let t = add_annotation(&mut doc, &b, &meta("t")).unwrap(); + // Circle, then a 1 pt border, which the circle grows by. + set_border_shape(&mut doc, 0, t, BorderShape::Circle, &meta("")).unwrap(); + set_style(&mut doc, 0, t, StyleChange::new(None, None, Some(1.0), None), &meta("")).unwrap(); + let lines = |doc: &Document| ap_content(doc, &list(doc, 0)[t]).matches(" Tj").count(); + let frame = |doc: &Document| { + let r = rect(&list(doc, 0)[t]); + ((r[2] - r[0], r[3] - r[1]), ((r[0] + r[2]) / 2.0, (r[1] + r[3]) / 2.0)) + }; + let rd = |doc: &Document| -> Vec { list(doc, 0)[t].get(b"RD").unwrap().as_array().unwrap().iter().map(|o| o.as_f64().unwrap()).collect() }; + assert!(rd(&doc).iter().all(|x| *x >= 0.0) && rd(&doc)[0] < 0.01, "touching the sides: {:?}", rd(&doc)); + assert_eq!(lines(&doc), 1, "Testtext on one line"); + let (wide, centre) = frame(&doc); + set_contents(&mut doc, 0, t, "KRS", &meta("")).unwrap(); + let (small, at) = frame(&doc); + assert!(small.0 < wide.0 - 10.0 && (small.0 - small.1).abs() < 0.01, "a smaller circle: {small:?} from {wide:?}"); + assert!((at.0 - centre.0).abs() < 0.01 && (at.1 - centre.1).abs() < 0.01, "about its centre: {at:?} {centre:?}"); + assert_eq!(lines(&doc), 1); + // A hair below 0, as rounding left it: still read, so the circle follows its text again. + let (_, r) = annot_ref(&mut doc, 0, t).unwrap(); + let mut was = rd(&doc); + was[0] = -2.8e-14; + doc.update_dict(r, |d| d.set(b"RD".to_vec(), num_array(&was))).unwrap(); + assert!(text_box_of(&list(&doc, 0)[t]).is_some()); + set_contents(&mut doc, 0, t, "Testtext", &meta("")).unwrap(); + assert!((frame(&doc).0.0 - wide.0).abs() < 0.01 && lines(&doc) == 1, "{:?}", frame(&doc)); + assert!(rd(&doc).iter().all(|x| *x >= 0.0), "{:?}", rd(&doc)); +} + +/// On a page turned a quarter, typed text is laid out as the page is shown (`/PCTextRotate`), and a +/// circle made with it goes around the text as shown: as large as around the same text on an +/// upright page. (Made before the turn was set, its text wrapped at the box's displayed height and +/// the circle went around several lines.) +#[test] +fn a_circle_made_on_a_turned_page_is_sized_as_on_an_upright_one() { + let w = appearance::text_width("12345", 10.0); + let typed = |rect: [f64; 4]| { + let mut t = new(0, Shape::Typewriter { rect, font_size: 10.0 }); + (t.contents, t.style.width, t.style.border_shape) = ("12345".into(), 1.0, BorderShape::Circle); + t + }; + let size = |doc: &Document, i: usize| { + let r = rect(&list(doc, 0)[i]); + (r[2] - r[0], r[3] - r[1]) + }; + let mut upright = fixture(); + let u = add_annotation(&mut upright, &typed([100.0, 680.0, 110.0 + w, 700.0]), &meta("u")).unwrap(); + for turn in [90, 270] { + let mut doc = fixture(); + let page = page_refs(&doc).unwrap()[0]; + doc.update_dict(page, |d| d.set(b"Rotate".to_vec(), Object::Int(turn))).unwrap(); + // The same box as shown: its sides swapped in user space. + let t = add_annotation(&mut doc, &typed([100.0, 680.0, 120.0, 690.0 + w]), &meta("t")).unwrap(); + assert_eq!(list(&doc, 0)[t].get(b"PCTextRotate").and_then(Object::as_int), Some(turn)); + let (turned, straight) = (size(&doc, t), size(&upright, u)); + assert!((turned.0 - straight.0).abs() < 0.01 && (turned.1 - straight.1).abs() < 0.01, "{turn}°: {turned:?}, upright {straight:?}"); + } +} + +/// A rectangle's fill, and a text box's border, background and text, each drawn at an opacity of +/// its own: the line's in `/CA`, the fill's in `/ca` (PDF 2.0), the text's in `/PCTextOpacity`, and +/// in the appearance `/GS0` (strokes at the line's, fills at the fill's) and `/GS1` for the text. +#[test] +fn parts_are_drawn_at_opacities_of_their_own() { + let num = |d: &Dict, k: &[u8]| d.get(k).and_then(|o| o.as_f64()); + let gstate = |doc: &Document, d: &Dict, name: &[u8]| -> Option<(f64, f64)> { + let n = d.get(b"AP").map(|a| doc.resolve(a)).and_then(|a| a.as_dict().and_then(|a| a.reference(b"N")))?; + let obj = doc.get(n); + let Object::Stream(s) = &*obj else { return None }; + let res = s.dict.get(b"Resources").map(|r| doc.resolve(r))?; + let gs = res.as_dict()?.get(b"ExtGState").map(|g| doc.resolve(g))?; + let gs = gs.as_dict()?.get(name).map(|g| doc.resolve(g))?; + let gs = gs.as_dict()?; + Some((gs.get(b"CA")?.as_f64()?, gs.get(b"ca")?.as_f64()?)) + }; + let mut doc = fixture(); + let r = add_annotation(&mut doc, &new(0, Shape::Rectangle { rect: [10.0, 10.0, 110.0, 60.0] }), &meta("r")).unwrap(); + set_fill(&mut doc, 0, r, Some([1.0, 1.0, 0.0]), &meta("")).unwrap(); + set_part_opacity(&mut doc, 0, r, Some(0.3), None, &meta("")).unwrap(); + let doc2 = reopen(&doc); + let d = &list(&doc2, 0)[r]; + assert_eq!((num(d, b"CA"), num(d, b"ca")), (None, Some(0.3)), "an opaque line, a fill of its own"); + assert_eq!(gstate(&doc2, d, b"GS0"), Some((1.0, 0.3))); + let ap = ap_content(&doc2, d); + assert!(ap.starts_with("/GS0 gs") && ap.contains("\nB\n"), "filled and stroked in one go: {ap}"); + let p = props(&doc2, 0, r).unwrap(); + assert_eq!((p.opacity, p.fill_opacity, p.text_opacity), (1.0, Some(0.3), None)); + // The whole comment's opacity (StyleAnnotation, the quick bar): the fill goes along again. + set_style(&mut doc, 0, r, StyleChange::new(None, Some(0.6), None, None), &meta("")).unwrap(); + let d = &list(&doc, 0)[r]; + assert_eq!((num(d, b"CA"), num(d, b"ca")), (Some(0.6), None)); + assert_eq!(props(&doc, 0, r).unwrap().fill_opacity, Some(0.6)); + + // A text box with its border opaque, its background at 20 % and its text opaque, as made. + let mut tb = new(0, Shape::TextBox { rect: [200.0, 600.0, 400.0, 650.0], font_size: 12.0 }); + tb.style.fill = Some([1.0, 1.0, 0.6]); + tb.style.width = 1.0; + (tb.style.fill_opacity, tb.style.text_opacity) = (Some(0.2), Some(1.0)); + let t = add_annotation(&mut doc, &tb, &meta("t")).unwrap(); + let doc2 = reopen(&doc); + let d = &list(&doc2, 0)[t]; + assert_eq!((num(d, b"CA"), num(d, b"ca"), num(d, b"PCTextOpacity")), (None, Some(0.2), Some(1.0))); + assert_eq!((gstate(&doc2, d, b"GS0"), gstate(&doc2, d, b"GS1")), (Some((1.0, 0.2)), Some((1.0, 1.0)))); + let ap = ap_content(&doc2, d); + let (gs1, text) = (ap.find("/GS1 gs\n").expect("the text's own state, an operator of its own"), ap.find("BT").expect("text")); + assert!(ap.find(" re f").is_some_and(|fill| fill < gs1) && gs1 < text, "background at 20 %, then the text at its own: {ap}"); + // A new fill opacity leaves the text as it is drawn. + set_part_opacity(&mut doc, 0, t, Some(0.5), None, &meta("")).unwrap(); + let d = &list(&doc, 0)[t]; + assert_eq!((num(d, b"ca"), num(d, b"PCTextOpacity")), (Some(0.5), Some(1.0))); + let p = props(&doc, 0, t).unwrap(); + assert_eq!((p.opacity, p.fill_opacity, p.text_opacity), (1.0, Some(0.5), Some(1.0))); + // All at one opacity again: only /CA stays. + set_part_opacity(&mut doc, 0, t, Some(1.0), Some(1.0), &meta("")).unwrap(); + let d = &list(&doc, 0)[t]; + assert_eq!((num(d, b"CA"), num(d, b"ca"), num(d, b"PCTextOpacity")), (None, None, None)); + + // Only the parts a comment has, and finite values; nothing changes when refused. + let l = add_annotation( + &mut doc, + &new(0, Shape::Line { from: [0.0, 0.0], to: [10.0, 10.0], start: LineEnding::None, end: LineEnding::None }), + &meta("l"), + ) + .unwrap(); + assert!(matches!(set_part_opacity(&mut doc, 0, l, Some(0.5), None, &meta("")), Err(AnnotError::Invalid(_))), "a line has no fill"); + assert!(matches!(set_part_opacity(&mut doc, 0, r, None, Some(0.5), &meta("")), Err(AnnotError::Invalid(_))), "a rectangle has no text"); + let before = list(&doc, 0)[r].clone(); + assert!(matches!(set_part_opacity(&mut doc, 0, r, Some(f64::NAN), None, &meta("")), Err(AnnotError::Invalid(_)))); + assert_eq!(list(&doc, 0)[r], before); + // Another app's comment with /CA alone is drawn at it throughout, as before. + assert_eq!( + appearance::part_opacity(&Dict::from_iter([(b"CA".to_vec(), Object::Real(0.4))])), + appearance::PartOpacity { line: 0.4, fill: 0.4, text: 0.4 } + ); +} + #[test] fn shapes_can_be_filled_and_unfilled() { let mut doc = fixture(); @@ -591,6 +882,85 @@ fn fill_and_sign_items_are_drawn() { assert!(set_style(&mut doc, 1, 0, StyleChange::new(Some([0.0; 3]), None, None, None), &meta("")).is_err()); } +/// A border chosen for typewriter text goes around it in the text's colour. Changing it grows or +/// shrinks the box on every side, so the text stays where it was typed; a text box keeps its box. +#[test] +fn a_typewriter_border_goes_around_its_text_which_stays_put() { + let mut doc = fixture(); + let shape = Shape::Typewriter { rect: [100.0, 700.0, 200.0, 716.0], font_size: 11.0 }; + let style = Style { width: 1.0, ..Style::default_for(&shape) }; + let t = add_annotation(&mut doc, &NewAnnotation { page: 1, shape, style, contents: "Ada".into(), author: "Ada".into() }, &meta("x")).unwrap(); + // The text starts 2 pt inside the border: 100 + 1 + 2 across, 716 - 1 - 2 - 0.9 em down. + let at = "1 0 0 1 103 703.1 Tm"; + let d = &list(&doc, 1)[t]; + let ap = ap_content(&doc, d); + assert!(ap.contains("1 w\n") && ap.contains(" re S"), "a 1 pt border: {ap}"); + assert!(ap.contains(at), "{ap}"); + for (width, expected) in [(2.0, [99.0, 699.0, 201.0, 717.0]), (0.0, [101.0, 701.0, 199.0, 715.0])] { + set_style(&mut doc, 1, t, StyleChange::new(None, None, Some(width), None), &meta("")).unwrap(); + let d = &list(&doc, 1)[t]; + assert_eq!(rect(d), expected, "{width} pt border"); + let ap = ap_content(&doc, d); + assert!(ap.contains(at), "{width} pt: the text keeps its place: {ap}"); + assert_eq!(ap.contains(" re S"), width > 0.0, "{width} pt: {ap}"); + } + let shape = Shape::TextBox { rect: [100.0, 600.0, 200.0, 650.0], font_size: 11.0 }; + let b = add_annotation(&mut doc, &new(1, shape), &meta("b")).unwrap(); + set_style(&mut doc, 1, b, StyleChange::new(None, None, Some(3.0), None), &meta("")).unwrap(); + assert_eq!(rect(&list(&doc, 1)[b]), [100.0, 600.0, 200.0, 650.0], "a text box keeps the box it was drawn with"); + // Another app's typed text with its width in /Border (no /BS): 4 pt, so 2 pt shrinks the box + // by 2 on every side, as it is drawn. + let shape = Shape::Typewriter { rect: [100.0, 500.0, 200.0, 530.0], font_size: 11.0 }; + let o = add_annotation( + &mut doc, + &NewAnnotation { page: 1, style: Style::default_for(&shape), shape: shape.clone(), contents: "Bo".into(), author: "Ada".into() }, + &meta("o"), + ) + .unwrap(); + let (_, r) = annot_ref(&mut doc, 1, o).unwrap(); + doc.update_dict(r, |d| { + d.remove(b"BS"); + d.set(b"Border".to_vec(), num_array(&[0.0, 0.0, 4.0])); + }) + .unwrap(); + set_style(&mut doc, 1, o, StyleChange::new(None, None, Some(2.0), None), &meta("")).unwrap(); + assert_eq!(rect(&list(&doc, 1)[o]), [102.0, 502.0, 198.0, 528.0], "the imported 4 pt border is read from /Border"); + // A border colour that isn't a colour is refused before anything is written. + let mut bad = NewAnnotation { page: 1, style: Style::default_for(&shape), shape, contents: "x".into(), author: "Ada".into() }; + bad.style.border_color = Some([f64::NAN, 0.0, 0.0]); + let before = list(&doc, 1).len(); + assert!(matches!(add_annotation(&mut doc, &bad, &meta("n")), Err(AnnotError::Invalid(_)))); + assert_eq!(list(&doc, 1).len(), before); +} + +/// Text keeps its colour and the border gets its own: the stroking colour in `/DA`, which a new +/// text colour or font size keeps, and which `None` gives back to the text's. +#[test] +fn a_text_border_can_have_its_own_colour() { + let mut doc = fixture(); + let shape = Shape::Typewriter { rect: [100.0, 700.0, 200.0, 716.0], font_size: 11.0 }; + let style = Style { color: [0.0, 0.5, 0.0], width: 1.0, border_color: Some([1.0, 0.0, 0.0]), ..Style::default_for(&shape) }; + let t = add_annotation(&mut doc, &NewAnnotation { page: 1, shape, style, contents: "Ada".into(), author: "Ada".into() }, &meta("x")).unwrap(); + let da = |doc: &Document| text(&list(doc, 1)[t], b"DA"); + assert_eq!(da(&doc), "0 0.5 0 rg 1 0 0 RG /Helv 11 Tf"); + let ap = ap_content(&doc, &list(&doc, 1)[t]); + assert!(ap.contains("1 0 0 RG\n1 w"), "the border in red: {ap}"); + assert!(ap.contains("0 0.5 0 rg"), "the text in green: {ap}"); + assert_eq!(props(&doc, 1, t).unwrap().border_color, Some([1.0, 0.0, 0.0])); + set_style(&mut doc, 1, t, StyleChange::new(Some([0.0, 0.0, 1.0]), None, None, None), &meta("")).unwrap(); + assert_eq!(da(&doc), "0 0 1 rg 1 0 0 RG /Helv 11 Tf", "a new text colour keeps the border's"); + set_font_size(&mut doc, 1, t, 14.0, &meta("")).unwrap(); + assert_eq!(da(&doc), "0 0 1 rg 1 0 0 RG /Helv 14 Tf", "so does a new size"); + set_border_color(&mut doc, 1, t, Some([0.5, 0.5, 0.5]), &meta("")).unwrap(); + assert!(ap_content(&doc, &list(&doc, 1)[t]).contains("0.5 0.5 0.5 RG\n1 w")); + set_border_color(&mut doc, 1, t, None, &meta("")).unwrap(); + assert_eq!(da(&doc), "0 0 1 rg /Helv 14 Tf"); + assert!(ap_content(&doc, &list(&doc, 1)[t]).contains("0 0 1 RG\n1 w"), "the text's colour again"); + assert_eq!(props(&doc, 1, t).unwrap().border_color, None); + let m = add_annotation(&mut doc, &new(0, Shape::Rectangle { rect: [10.0, 10.0, 50.0, 50.0] }), &meta("m")).unwrap(); + assert!(set_border_color(&mut doc, 0, m, Some([1.0, 0.0, 0.0]), &meta("")).is_err(), "a rectangle's colour is its border"); +} + #[test] fn author_subject_and_note_icon_change() { let mut doc = fixture(); @@ -873,8 +1243,8 @@ fn cloud_ys(path: &str) -> Vec { fn replace_text_groups_a_strikeout_and_a_caret() { let mut doc = fixture(); let quads = [[100.0, 720.0, 200.0, 720.0, 100.0, 706.0, 200.0, 706.0]]; - let red = Style { color: [0.89, 0.13, 0.13], opacity: 1.0, width: 1.0, fill: None }; - let blue = Style { color: [0.0, 0.47, 0.84], opacity: 1.0, width: 1.0, fill: None }; + let red = Style { color: [0.89, 0.13, 0.13], opacity: 1.0, width: 1.0, fill: None, ..Style::default() }; + let blue = Style { color: [0.0, 0.47, 0.84], opacity: 1.0, width: 1.0, fill: None, ..Style::default() }; let i = add_text_replacement( &mut doc, TextReplacement { diff --git a/crates/annot/src/types.rs b/crates/annot/src/types.rs index 522995b9f9..f6bcc68a7e 100644 --- a/crates/annot/src/types.rs +++ b/crates/annot/src/types.rs @@ -1,5 +1,5 @@ use super::create::normalize; -use super::{ObjRef, appearance}; +use super::{Dict, ObjRef, appearance}; pub type Rgb = [f64; 3]; @@ -124,6 +124,28 @@ impl FillMark { let (w, h) = if matches!(rotation.rem_euclid(360), 90 | 270) { (h, w) } else { (w, h) }; [at[0] - w / 2.0, at[1] - h / 2.0, at[0] + w / 2.0, at[1] + h / 2.0] } + + /// The mark whose `/Name` this is. + pub fn from_name(n: &[u8]) -> Option { + [FillMark::Check, FillMark::Cross, FillMark::Dot, FillMark::Line].into_iter().find(|m| m.name().as_bytes() == n) + } + + /// The pen strokes the mark is drawn with in `rect` (user space): what its appearance strokes, + /// and what a copy of it shows while it is being placed. The dot is a filled circle (radius + /// 0.3 × the shorter side, centred) and has none. + pub fn strokes(self, rect: [f64; 4]) -> Vec> { + let [x0, y0, x1, y1] = rect; + let (w, h) = (x1 - x0, y1 - y0); + match self { + FillMark::Check => vec![vec![[x0 + w * 0.15, y0 + h * 0.5], [x0 + w * 0.4, y0 + h * 0.2], [x0 + w * 0.88, y0 + h * 0.85]]], + FillMark::Cross => vec![ + vec![[x0 + w * 0.18, y0 + h * 0.18], [x1 - w * 0.18, y1 - h * 0.18]], + vec![[x0 + w * 0.18, y1 - h * 0.18], [x1 - w * 0.18, y0 + h * 0.18]], + ], + FillMark::Dot => Vec::new(), + FillMark::Line => vec![vec![[x0, y0 + h / 2.0], [x1, y0 + h / 2.0]]], + } + } } /// The stamps of Acrobat's stamp palette (drawn in PdfCraft's own style). @@ -566,6 +588,16 @@ pub struct Style { pub width: f64, /// Interior fill for rectangles and ovals (`/IC`), background for text boxes. pub fill: Option, + /// A text box's, typewriter text's or callout's border colour where it differs from the + /// text's (`None`: the text colour), the stroking colour in its `/DA`. + pub border_color: Option, + /// A text box's or typewriter text's border shape (a callout's is always a rectangle). + pub border_shape: BorderShape, + /// The fill's own opacity, 0–1 (`/ca`), where it differs from `opacity` (which is then the + /// line's or border's); `None`: as `opacity`. + pub fill_opacity: Option, + /// A text box's text's own opacity, 0–1 (`/PCTextOpacity`); `None`: as the fill's. + pub text_opacity: Option, } /// The style properties changed by one annotation edit. `None` leaves a property unchanged. @@ -597,7 +629,102 @@ pub struct TextReplacement<'a> { impl Default for Style { fn default() -> Self { - Self { color: [1.0, 0.82, 0.0], opacity: 1.0, width: 1.0, fill: None } + Self { + color: [1.0, 0.82, 0.0], + opacity: 1.0, + width: 1.0, + fill: None, + fill_opacity: None, + text_opacity: None, + border_color: None, + border_shape: BorderShape::Rectangle, + } + } +} + +/// The shape of a text box's or typewriter text's border (PdfCraft's `/PCBorderShape`, absent for +/// a rectangle). An oval or a circle goes around the text box, which keeps its place: `/Rect` +/// grows to hold it, centred on the text box, and `/RD` says where the text box is inside +/// (§12.5.6.6), as for a callout. Other apps that redraw the comment draw a rectangle. +#[derive(Clone, Copy, Debug, Default, PartialEq, Eq)] +pub enum BorderShape { + #[default] + Rectangle, + Oval, + Circle, +} + +impl BorderShape { + pub const ALL: [BorderShape; 3] = [BorderShape::Rectangle, BorderShape::Oval, BorderShape::Circle]; + + pub fn name(self) -> &'static str { + match self { + BorderShape::Rectangle => "Rectangle", + BorderShape::Oval => "Oval", + BorderShape::Circle => "Circle", + } + } + + /// `rectangle`, `oval` or `circle`, in any case. + pub fn parse(s: &str) -> Option { + Self::ALL.into_iter().find(|b| b.name().eq_ignore_ascii_case(s)) + } + + /// The border shape of FreeText `d`: always a rectangle for a callout. + pub fn of(d: &Dict) -> Self { + if d.contains(b"CL") { + return BorderShape::Rectangle; + } + match d.name(b"PCBorderShape") { + Some(b"Oval") => BorderShape::Oval, + Some(b"Circle") => BorderShape::Circle, + _ => BorderShape::Rectangle, + } + } + + /// The rectangle this shape, with a border `width` wide, takes around text box `tb`, centred on + /// it: an oval through the text box's corners (`√2` its size), a point clear of the border; a + /// circle around the text's lines (`text`: the widest line's width and the lines' height, when + /// known), a point clear of the border and touching the text box's longer sides at least + /// (its corners, padding only, may lie outside), else through the box's corners; the text box + /// itself for a rectangle. + pub fn around(self, tb: [f64; 4], width: f64, text: Option<[f64; 2]>) -> [f64; 4] { + let tb = normalize(tb); + let (cx, cy, hx, hy) = ((tb[0] + tb[2]) / 2.0, (tb[1] + tb[3]) / 2.0, (tb[2] - tb[0]) / 2.0, (tb[3] - tb[1]) / 2.0); + let gap = width.max(0.0) + 1.0; + let (ax, ay) = match self { + BorderShape::Rectangle => return tb, + BorderShape::Oval => (hx * std::f64::consts::SQRT_2 + gap, hy * std::f64::consts::SQRT_2 + gap), + BorderShape::Circle => { + let r = match text { + Some([w, h]) => ((w / 2.0).hypot(h / 2.0) + gap).max(hx).max(hy), + None => hx.hypot(hy) + gap, + }; + (r, r) + } + }; + [cx - ax, cy - ay, cx + ax, cy + ay] + } + + /// The text box inside `outer` for this shape when none is recorded: the inverse of + /// [`Self::around`] for an oval, a box through a circle's corners for a circle, keeping the + /// proportions of `was` (the one it had). + pub(crate) fn inside(self, outer: [f64; 4], width: f64, was: [f64; 4]) -> [f64; 4] { + let o = normalize(outer); + let (cx, cy, hx, hy) = ((o[0] + o[2]) / 2.0, (o[1] + o[3]) / 2.0, (o[2] - o[0]) / 2.0, (o[3] - o[1]) / 2.0); + let gap = width.max(0.0) + 1.0; + let (ix, iy) = match self { + BorderShape::Rectangle => return o, + BorderShape::Oval => ((hx - gap) / std::f64::consts::SQRT_2, (hy - gap) / std::f64::consts::SQRT_2), + BorderShape::Circle => { + let w = normalize(was); + let (wx, wy) = ((w[2] - w[0]) / 2.0, (w[3] - w[1]) / 2.0); + let k = (hx.min(hy) - gap) / wx.hypot(wy).max(1e-6); + (wx * k, wy * k) + } + }; + let (ix, iy) = (ix.max(0.5), iy.max(0.5)); + [cx - ix, cy - iy, cx + ix, cy + iy] } } @@ -615,7 +742,7 @@ impl Style { } Shape::Callout { .. } => ([0.0, 0.0, 0.0], 1.0), Shape::Caret { .. } | Shape::Attachment { .. } => ([0.0, 0.47, 0.84], 1.0), - Shape::FreehandHighlight { .. } => return Self { color: [1.0, 0.94, 0.0], opacity: 0.35, width: 14.0, fill: None }, + Shape::FreehandHighlight { .. } => return Self { color: [1.0, 0.94, 0.0], opacity: 0.35, width: 14.0, ..Self::default() }, Shape::Ink { .. } => ([0.0, 0.4, 0.87], 2.0), Shape::TextBox { .. } | Shape::Typewriter { .. } => ([0.0, 0.0, 0.0], 0.0), Shape::Mark { .. } => ([0.0, 0.0, 0.0], 1.5), @@ -624,9 +751,9 @@ impl Style { Shape::CustomStamp { .. } => ([0.0, 0.0, 0.0], 0.0), Shape::TypedSignature { .. } => ([0.0, 0.0, 0.0], 0.0), // Red outline while marked; a black box once applied. - Shape::Redact { .. } => return Self { color: [0.89, 0.13, 0.13], opacity: 1.0, width: 1.0, fill: Some([0.0, 0.0, 0.0]) }, + Shape::Redact { .. } => return Self { color: [0.89, 0.13, 0.13], fill: Some([0.0, 0.0, 0.0]), ..Self::default() }, }; - Self { color, opacity: 1.0, width, fill: None } + Self { color, width, ..Self::default() } } } diff --git a/crates/audit/src/cover.rs b/crates/audit/src/cover.rs index bb5adf7ff8..9f771f7040 100644 --- a/crates/audit/src/cover.rs +++ b/crates/audit/src/cover.rs @@ -283,7 +283,7 @@ impl<'a> Walker<'a> { 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 data = self.budget.decode_strict(self.doc, stream)?; // 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); @@ -326,7 +326,7 @@ pub fn filled_rects(doc: &Document, page: &Dict) -> Result, Audi let mut streams = Vec::with_capacity(contents.len()); for c in &contents { if let Object::Stream(s) = &*doc.resolve(c) { - streams.push(budget.decode_strict(s)?); + streams.push(budget.decode_strict(doc, s)?); } } let pieces = Pieces::join(&streams); diff --git a/crates/automation/README.md b/crates/automation/README.md index d218fbcda6..2fbbff8ccb 100644 --- a/crates/automation/README.md +++ b/crates/automation/README.md @@ -26,6 +26,11 @@ its undo/redo history. `page_add_text`, `content_update` and `text_edit` take per-line `aligns`. An `"inherit"` entry follows the box-level `align`; legacy `null` entries remain accepted with the same meaning. +`page_add_text` and `content_update` take one of `color` (`#RRGGBB` or a name, painted in +DeviceRGB), `gray` (0 black to 1 white, DeviceGray `g`) and `cmyk` (`[c, m, y, k]`, each 0 to 1, +DeviceCMYK `k`), so text added to a print file can be 100 K black. `content_list` reports `gray` or +`cmyk` for such text. + `Content` is `Json(Value)` or `Png { data, width, height }`. Errors are `UnknownTool`, `InvalidArgs` (the call didn't match the schema) or `Failed` (a readable message for the agent). ## Conventions @@ -281,3 +286,26 @@ navigation-history tool; use the opt-in UI control channel to navigate the displ (`#RRGGBB`, default black) for `text` and `date`. The colour is saved in the FreeText appearance and survives reopening. Other mark/signature types reject `color`; their appearance controls are separate. + +## Reviewing OCR headlessly + +`ocr_words {doc, retain_review: true}` reads words without editing the document and returns +`review`, plus pages and word boxes/confidences. Page and word positions are 1-based. +`region` can restrict recognition to one named page, using displayed-page points. Without +`retain_review`, word inspection remains stateless. + +Apply reviewed text with `ocr_review_apply {doc, review, corrections: [{page: 1, word: 1, +text: "Corrected"}]}`. Omitted words keep their text; empty text removes a word. Geometry +comes from the retained recognition, never caller input. The captured document guard rejects +stale/foreign results. Successful application consumes the handle and is one undoable step. +Use `output_mode: "editable", out: "reviewed.pdf"` to write a separate editable document, +or `discard: true` to release the result without applying it. Failed validation preserves the +review for correction or discard. A new retained recognition replaces that document's prior +handle; closing the document releases it. At most eight documents may retain reviews, with +65,536-word/4-MiB input bounds and a 65,536-page cap. + +`ocr_dictionary {path: "ocr-dictionary-en.txt", add: ["Quartz"], remove: ["old"]}` atomically +updates the same one-word-per-UTF-8-line format OCR Verify uses. Omit add/remove to read it. +The explicit path honors `--root`, including symlink confinement; choose the appropriate +per-language file used by the UI. Entries are case-insensitive and duplicate-free. Invalid +or oversized inputs fail before writing (65,536 words, 4 MiB, at most 1,024 bytes per word). diff --git a/crates/automation/src/a11y/ocr.rs b/crates/automation/src/a11y/ocr.rs index 82e521ddd5..2846aa44a6 100644 --- a/crates/automation/src/a11y/ocr.rs +++ b/crates/automation/src/a11y/ocr.rs @@ -1,98 +1,534 @@ use super::{Args, Automation, Result, ToolError, Value, child, failed, json, write_atomic}; impl Automation { - /// Recognition settings from the arguments: `dpi` (clamped to 72–600), `language` (refused - /// unless the models read it) and `skip_text_pages`, each left at its default when absent. + /// The settings every OCR tool shares: dpi, language, the engine/strategy choice, the four + /// preprocessing flags, the skip flags and the output mode — each named exactly as its tool + /// schema says. An unknown engine, strategy or mode is an honest error, never a silent + /// fallback: a tool run must not quietly do something other than what it was asked. pub(crate) fn ocr_settings(&self, a: &Args) -> Result { + use pdfcraft_engine::ocr::{EngineChoice, MergeStrategy, OutputMode}; let mut settings = pdfcraft_engine::ocr::OcrSettings::default(); if let Some(d) = a.opt_num("dpi")? { settings.dpi = d.clamp(72.0, 600.0) as f32; } if let Some(l) = a.opt_str("language")? { if !pdfcraft_engine::ocr::LANGUAGES.iter().any(|x| x.0 == l) { - return Err(ToolError::InvalidArgs(format!("unsupported language {l:?}"))); + return Err(ToolError::InvalidArgs(format!( + "unsupported language {l:?} (supported: {})", + pdfcraft_engine::ocr::LANGUAGES.iter().map(|(c, _)| *c).collect::>().join(", ") + ))); } settings.language = l.into(); } - if let Some(s) = a.opt_bool("skip_text_pages")? { - settings.skip_text_pages = s; + if let Some(e) = a.opt_str("engine")? { + settings.engine = match e.trim().to_ascii_lowercase().as_str() { + "ocrs" => EngineChoice::Ocrs, + "tesseract" => EngineChoice::Tesseract, + "auto" | "automatic" | "ensemble" => EngineChoice::Auto, + other => return Err(ToolError::InvalidArgs(format!("unsupported engine {other:?} (ocrs, tesseract or auto)"))), + }; + } + settings.strategy = match a.opt_str("strategy")? { + Some(s) => match s.trim().to_ascii_lowercase().as_str() { + "primary" | "primary-only" | "primary_only" => MergeStrategy::PrimaryOnly, + "confidence" | "confidence-weighted" | "confidence_weighted" => MergeStrategy::ConfidenceWeighted, + "rover" | "rover-vote" | "rover_vote" | "vote" => MergeStrategy::RoverVote, + other => return Err(ToolError::InvalidArgs(format!("unsupported strategy {other:?} (primary, confidence or rover)"))), + }, + // Unset: the engine choice decides (auto brings in the second engine when the + // first reading is weak; a named engine reads alone). + None => settings.engine.default_strategy(), + }; + if let Some(m) = a.opt_str("output_mode")? { + settings.output_mode = match m.trim().to_ascii_lowercase().as_str() { + "searchable" | "searchable-image" | "searchable_image" => OutputMode::Searchable, + "editable" | "editable-text" | "editable_text" => OutputMode::EditableText, + other => return Err(ToolError::InvalidArgs(format!("unsupported output mode {other:?} (searchable or editable)"))), + }; + } + for (key, flag) in [ + ("auto_rotate", &mut settings.auto_rotate), + ("deskew", &mut settings.deskew), + ("denoise", &mut settings.denoise), + ("binarize", &mut settings.binarize), + ] { + if let Some(on) = a.opt_bool(key)? { + *flag = on; + } + } + for (key, flag) in [ + ("skip_text_pages", &mut settings.skip_text_pages), + ("skip_text_files", &mut settings.skip_text_files), + ("force_ocr", &mut settings.force_ocr), + ] { + if let Some(on) = a.opt_bool(key)? { + *flag = on; + } } Ok(settings) } - /// Recognizes text in each of `paths` and writes the result under the same file name in - /// `folder`, reporting per file its output, word count and skipped pages, or its error. A - /// path outside the root refuses the whole call before any work starts. + /// The optional `region` argument ([x0, y0, x1, y1] in points from the top-left of the + /// displayed page) as the job's pixel crop, at the resolution that page is really read at. + /// A region reads exactly one page. + fn ocr_region( + &self, + a: &Args, + id: pdfcraft_engine::DocId, + page: usize, + settings: &pdfcraft_engine::ocr::OcrSettings, + ) -> Result> { + const BAD: &str = "region must be [x0, y0, x1, y1] in points"; + let Some(v) = a.get("region") else { return Ok(None) }; + let arr = v.as_array().ok_or_else(|| ToolError::InvalidArgs(BAD.into()))?; + if arr.len() != 4 { + return Err(ToolError::InvalidArgs(BAD.into())); + } + let mut pts = [0.0f64; 4]; + for (i, x) in arr.iter().enumerate() { + pts[i] = x.as_f64().filter(|f| f.is_finite()).ok_or_else(|| ToolError::InvalidArgs(BAD.into()))?; + } + let scale = f64::from( + self.session.ocr_job(id, &[page], settings.clone()).ok_or_else(|| failed("the document could not be read"))?.render_scale(page), + ); + let px: Vec = pts.iter().map(|p| scale * p).map(|p| if p.is_finite() { p } else { 0.0 }).map(|p| p as f32).collect(); + Ok(Some([px[0], px[1], px[2], px[3]])) + } + + /// The per-page result entries the OCR tools return: recognised text or why the page was + /// passed over. The text itself is only echoed when the document allows copying; the + /// counts and metadata always are. + fn ocr_pages_json(found: &[pdfcraft_engine::ocr::OcrPage], include_text: bool) -> Vec { + found + .iter() + .map(|p| match &p.skipped { + Some(why) => json!({ "page": p.page + 1, "skipped": why }), + None => { + let mut page = json!({ "page": p.page + 1, "words": p.words.len(), "already_on_page": p.already_on_page }); + // The editable output's substitution warnings (characters no font could + // show) are part of the result: reported per page, never dropped. + if !p.notes.is_empty() { + page["notes"] = json!(p.notes); + } + if include_text { + page["text"] = json!(p.text()); + } + page + } + }) + .collect() + } + pub(crate) fn ocr_recognize_files(&mut self, a: &Args) -> Result { let settings = self.ocr_settings(a)?; let folder = self.resolve(a.str("folder")?, true)?; - // A path that leaves the root refuses the whole call before any work starts, like the - // other tools (the write check passes missing files, which stay per-file errors below). + // A path that leaves the read root refuses the whole call before any work starts; + // a file that is merely missing stays a per-file error below. let paths = a.strs("paths")?; for p in &paths { self.resolve_for(p, crate::file_access::Access::Read, true)?; } - // Two inputs that would write the same output file overwrite each other while both report - // success, so the whole batch is refused here: before the folder is created, anything is - // read, or the OCR engines load. + // Two inputs of one file name (from different folders) would write the same output: + // the second would replace the first while both report success. The whole batch is + // refused up front — before the folder is created, anything is read or the engines + // load — naming the file, the way the default filesystem compares names. let targets: Vec = paths.iter().map(|p| child(&folder, &input_file_name(p))).collect(); let shared = shared_file_names(&targets); if !shared.is_empty() { return Err(ToolError::InvalidArgs(format!( - "more than one input would write to the same output file, so each would replace the one before it. Colliding file names: {}. Give each input a different file name, or run them in separate batches with different folders.", + "several paths share a file name, so their outputs in folder would overwrite each other (rename or run them separately): {}", shared.join(", ") ))); } std::fs::create_dir_all(&folder).map_err(|e| failed(e.to_string()))?; - let ocr = pdfcraft_engine::ocr::engine().map_err(failed)?; + let names: Vec = paths.iter().map(|p| input_file_name(p)).collect(); + // Collision pre-flight: a searchable copy never silently overwrites. Every target is + // checked before the first page is read; a collision aborts the whole batch with the + // names in the error. + let mut collisions = std::collections::BTreeSet::new(); + for name in names { + if child(&folder, &name).exists() { + collisions.insert(name); + } + } + if !collisions.is_empty() { + let mut list: Vec = collisions.iter().take(5).cloned().collect(); + if collisions.len() > list.len() { + list.push(format!("and {} more", collisions.len() - list.len())); + } + return Err(failed(format!( + "the output folder already holds {} (delete or move them, or choose another folder): {}", + if collisions.len() == 1 { "a file of that name" } else { "files of those names" }, + list.join(", ") + ))); + } + // The engines are built (and named if they cannot be) before the first file is read. + let recognizers = pdfcraft_engine::ocr::recognizers(&settings).map_err(failed)?; let mut out = Vec::new(); + let (mut ok, mut skipped_files, mut words) = (0usize, 0usize, 0usize); for p in paths { let name = input_file_name(p); let result = self.resolve(p, false).map_err(|e| e.to_string()).and_then(|src| crate::read_input_bytes(&src).map_err(|e| e.to_string())).and_then( - |bytes| pdfcraft_engine::ocr::recognize_file(&name, std::sync::Arc::new(bytes), None, settings.clone(), &ocr, |_, _| true), + |bytes| { + pdfcraft_engine::ocr::recognize_file(&name, std::sync::Arc::new(bytes), None, settings.clone(), &recognizers, |_, _| true) + }, ); - out.push(match result { + match result { Ok(r) => { + let skipped_pages: Vec = r.pages.iter().filter(|p| p.skipped.is_some()).map(|p| p.page + 1).collect(); + if r.skipped() { + // A file passed over by the skip-files option is its own bucket: its + // original is left alone and nothing is written. + skipped_files += 1; + out.push(json!({ "path": p, "skipped": r.file_skipped, "skipped_pages": skipped_pages })); + continue; + } let target = child(&folder, &name); write_atomic(&target, &r.bytes)?; - let skipped: Vec = r.pages.iter().filter(|p| p.skipped.is_some()).map(|p| p.page + 1).collect(); - json!({ "path": p, "output": target.to_string_lossy(), "words": r.words(), "skipped_pages": skipped }) + ok += 1; + words += r.words(); + let mut entry = json!({ "path": p, "output": target.to_string_lossy(), "words": r.words(), "skipped_pages": skipped_pages }); + // The batch's low-confidence note: at or under the settings' threshold (60 + // by default), on 1-based sorted pages. + let threshold = settings.low_confidence_threshold; + if let Some((count, pages)) = pdfcraft_engine::ocr::low_confidence_pages(&r.pages, threshold) { + entry["low_confidence"] = json!({ "count": count, "pages": pages, "threshold": threshold }); + } + out.push(entry); } - Err(e) => json!({ "path": p, "error": e }), - }); + Err(e) => out.push(json!({ "path": p, "error": e })), + } } - Ok(json!({ "files": out })) + Ok(json!({ "files": out, "recognized": ok, "words": words, "skipped_files": skipped_files })) } - /// Recognizes text on the open document's `pages` (every page when absent) and adds it, - /// reporting the total word count and, per page, why it was skipped or what it found. pub(crate) fn ocr_recognize(&mut self, a: &Args) -> Result { - let settings = self.ocr_settings(a)?; + use pdfcraft_engine::ocr::OutputMode; + let mut settings = self.ocr_settings(a)?; let pages = if a.opt_ints("pages")?.is_some() { self.pages(a, "pages")? } else { Vec::new() }; - let doc = self.doc(a)?; // Recognizing needs only permission to change the document; the words it found are // returned only when copying is allowed too. - let (id, copy) = (doc.id, doc.allows_copying()); - let found = self.session.recognize_text(id, &pages, settings).map_err(failed)?; + let (id, copy) = { + let doc = self.doc(a)?; + (doc.id, doc.allows_copying()) + }; + // The optional region reads exactly one page. + if a.get("region").is_some() { + if pages.len() != 1 { + return Err(ToolError::InvalidArgs("region reads one page: name it in pages".into())); + } + settings.region = self.ocr_region(a, id, pages[0], &settings)?; + } + // The editable output's destination is checked before anything runs: a NEW file, never + // the open source and never an existing file replaced silently. + let out = match settings.output_mode { + OutputMode::Searchable => { + // `out` belongs to the editable output; a searchable run writes into the open + // document, so an `out` here would be silently ignored (and never checked + // against the root). + if a.get("out").is_some() { + return Err(ToolError::InvalidArgs("out is only used with output_mode editable; remove it, or choose editable".into())); + } + None + } + OutputMode::EditableText => { + // The editable output writes the recognized text out of the document: a + // document that forbids copying refuses here, before anything runs. + self.doc_to_copy(a)?; + // A write: the file does not exist yet, and write_atomic makes its folder. + let out = self.resolve(a.str("out")?, true)?; + if let Some(source) = self.session.get(id).and_then(|d| d.path.clone()) + && let (Ok(a), Ok(b)) = (std::fs::canonicalize(&out), std::fs::canonicalize(&source)) + && a == b + { + return Err(failed("out is the source document; the editable output is a new file, so choose another path")); + } + if out.exists() { + return Err(failed(format!( + "out already exists ({}); the editable output is a new file, so choose a path that does not exist yet", + out.to_string_lossy() + ))); + } + Some(out) + } + }; + // Honest up front: the engines are built (and named if they cannot be) before anything + // is read or written. + let recognizers = pdfcraft_engine::ocr::recognizers(&settings).map_err(failed)?; + match out { + None => { + let found = self.session.recognize_text(id, &pages, settings).map_err(failed)?; + let words = found.iter().map(|p| p.words.len()).sum::(); + Ok(json!({ "words": words, "pages": Self::ocr_pages_json(&found, copy) })) + } + Some(out) => { + let job = self.session.ocr_job(id, &pages, settings).ok_or_else(|| failed("the document could not be read"))?; + let found = job.run(&recognizers, |_, _| true); + let bytes = self.session.editable_ocr_bytes(id, &found).map_err(failed)?; + // recognition can take minutes: a file created meanwhile is refused, not replaced + if let Some(folder) = out.parent() { + std::fs::create_dir_all(folder).map_err(failed)?; + } + crate::bates::publish_new(&out, &bytes)?; + Ok(json!({ + "out": out.to_string_lossy(), + "words": found.iter().map(|p| p.words.len()).sum::(), + "pages": Self::ocr_pages_json(&found, copy), + })) + } + } + } + + /// The words of a recognition, for reviewing without the GUI: text, box (points from the + /// top-left of the displayed page), confidence, band, and which words are suspects. + /// Changes nothing; needs the engines (ocr_status). + pub(crate) fn ocr_words(&mut self, a: &Args) -> Result { + let mut settings = self.ocr_settings(a)?; + let pages = if a.opt_ints("pages")?.is_some() { self.pages(a, "pages")? } else { Vec::new() }; + // The word list is the document's text, word by word: refused when the document + // forbids copying it out. + let id = self.doc_to_copy(a)?.id; + if a.get("region").is_some() { + if pages.len() != 1 { + return Err(ToolError::InvalidArgs("region reads one page: name it in pages".into())); + } + settings.region = self.ocr_region(a, id, pages[0], &settings)?; + } + let retain = a.opt_bool("retain_review")?.unwrap_or(false); + if retain && !self.ocr_reviews.contains_key(&id) && self.ocr_reviews.len() >= 8 { + return Err(failed("at most 8 OCR reviews may be retained; discard one first")); + } + let recognizers = pdfcraft_engine::ocr::recognizers(&settings).map_err(failed)?; + let job = self.session.ocr_job(id, &pages, settings.clone()).ok_or_else(|| failed("the document could not be read"))?; + let infos: std::collections::HashMap = + self.session.get(id).map(|d| d.info.pages.clone()).unwrap_or_default().into_iter().enumerate().collect(); + let guard = job.guard.clone(); + let found = job.run(&recognizers, |_, _| true); + if found.len() > 65536 { + return Err(failed("at most 65536 OCR review pages are allowed")); + } + pdfcraft_engine::ocr::validate_ocr_words(found.iter().flat_map(|p| &p.words)).map_err(failed)?; + let band_name = |band: pdfcraft_engine::ocr::ConfidenceBand| match band { + pdfcraft_engine::ocr::ConfidenceBand::High => "high", + pdfcraft_engine::ocr::ConfidenceBand::Medium => "medium", + pdfcraft_engine::ocr::ConfidenceBand::Low => "low", + }; + let mut suspects = 0usize; let list: Vec = found .iter() - .map(|p| match &p.skipped { - Some(why) => json!({ "page": p.page + 1, "skipped": why }), - None if copy => json!({ "page": p.page + 1, "words": p.words.len(), "already_on_page": p.already_on_page, "text": p.text() }), - None => json!({ "page": p.page + 1, "words": p.words.len(), "already_on_page": p.already_on_page }), + .map(|p| { + let info = infos.get(&p.page); + let words: Vec = p + .words + .iter() + .map(|w| { + let suspect = pdfcraft_engine::ocr::is_suspect(w.confidence); + if suspect { + suspects += 1; + } + // The word's corners in view space, as the box [x, y, w, h] in points + // from the top-left of the displayed page. + let view = |pt: [f64; 2]| info.map(|i| i.user_to_view(pt[0] as f32, pt[1] as f32)); + let corners = [ + view(w.origin), + view([w.origin[0] + w.across[0], w.origin[1] + w.across[1]]), + view([w.origin[0] + w.up[0], w.origin[1] + w.up[1]]), + view([w.origin[0] + w.across[0] + w.up[0], w.origin[1] + w.across[1] + w.up[1]]), + ]; + let xs: Vec = corners.iter().flatten().map(|v| v[0]).collect(); + let ys: Vec = corners.iter().flatten().map(|v| v[1]).collect(); + let (min_x, min_y) = (xs.iter().cloned().fold(f32::INFINITY, f32::min), ys.iter().cloned().fold(f32::INFINITY, f32::min)); + let (w_pt, h_pt) = ( + xs.iter().cloned().fold(f32::NEG_INFINITY, f32::max) - min_x, + ys.iter().cloned().fold(f32::NEG_INFINITY, f32::max) - min_y, + ); + json!({ + "text": w.text, + "box": [min_x, min_y, w_pt, h_pt], + "confidence": w.confidence.map(|c| (c * 10.0).round() / 10.0), + "band": w.confidence.map(|c| band_name(pdfcraft_engine::ocr::band_for(c))), + "suspect": suspect, + "source": w.source, + }) + }) + .collect(); + let mut page = + json!({ "page": p.page + 1, "already_on_page": p.already_on_page, "words": words, "mean_confidence": p.mean_confidence().map(|c| (c * 10.0).round() / 10.0) }); + if let Some(why) = &p.skipped { + page["skipped"] = json!(why); + } + page }) .collect(); - Ok(json!({ "words": found.iter().map(|p| p.words.len()).sum::(), "pages": list })) + let mut out = json!({ "words": found.iter().map(|p| p.words.len()).sum::(), "suspects": suspects, "pages": list }); + if retain { + self.next_ocr_review = + self.next_ocr_review.checked_add(1).filter(|n| *n <= i64::MAX as u64).ok_or_else(|| failed("OCR review handles exhausted"))?; + out["review"] = json!(self.next_ocr_review); + self.ocr_reviews.insert(id, crate::OcrReview { handle: self.next_ocr_review, guard, pages: found }); + } + Ok(out) + } + + /// Apply only caller corrections to retained original boxes, through the stored guard. + pub(crate) fn ocr_review_apply(&mut self, a: &Args) -> Result { + let id = self.doc(a)?.id; + let handle = a.int("review")?; + let review = self + .ocr_reviews + .get(&id) + .filter(|r| i64::try_from(r.handle).ok() == Some(handle)) + .ok_or_else(|| failed("unknown OCR review for this document; call ocr_words with retain_review"))?; + if a.opt_bool("discard")?.unwrap_or(false) { + if a.get("corrections").is_some() { + return Err(ToolError::InvalidArgs("discard cannot include corrections".into())); + } + self.ocr_reviews.remove(&id); + return Ok(json!({ "discarded": handle })); + } + if let Some(why) = self.session.stale_reason(&review.guard) { + return Err(failed(why)); + } + let corrections = a.get("corrections").map(|v| v.as_array().ok_or_else(|| Args::wrong("corrections", "an array"))).transpose()?; + if corrections.is_some_and(|c| c.len() > 65536) { + return Err(failed("at most 65536 OCR corrections are allowed")); + } + // Prevalidate and cap every replacement before cloning the retained result. + let mut edits = Vec::new(); + let mut bytes = 0usize; + let mut seen = std::collections::BTreeSet::new(); + let page_indices: std::collections::BTreeMap<_, _> = review.pages.iter().enumerate().map(|(i, p)| (p.page, i)).collect(); + for item in corrections.into_iter().flatten() { + if !item.is_object() || item.as_object().is_some_and(|o| o.keys().any(|k| !matches!(k.as_str(), "page" | "word" | "text"))) { + return Err(ToolError::InvalidArgs("corrections accept only page, word and text".into())); + } + let c = Args(item); + let page = + usize::try_from(c.int("page")?).ok().and_then(|p| p.checked_sub(1)).ok_or_else(|| Args::wrong("page", "a 1-based position"))?; + let word = + usize::try_from(c.int("word")?).ok().and_then(|w| w.checked_sub(1)).ok_or_else(|| Args::wrong("word", "a 1-based position"))?; + let text = c.str("text")?; + bytes = bytes.checked_add(text.len()).filter(|n| *n <= 4 * 1024 * 1024).ok_or_else(|| failed("OCR corrections exceed 4 MiB"))?; + if !seen.insert((page, word)) { + return Err(failed("duplicate OCR word correction")); + } + let pi = page_indices.get(&page).copied().ok_or_else(|| failed("page is not in this OCR review"))?; + if review.pages.get(pi).and_then(|p| p.words.get(word)).is_none() { + return Err(failed("word is not in this OCR review")); + } + edits.push((pi, word, text.to_owned())); + } + let mut pages = review.pages.clone(); + for (pi, wi, text) in edits { + if let Some(w) = pages.get_mut(pi).and_then(|p| p.words.get_mut(wi)) { + w.text = text; + } + } + pdfcraft_engine::ocr::validate_ocr_words(pages.iter().flat_map(|p| &p.words)).map_err(failed)?; + for page in &mut pages { + page.words.retain(|w| !w.text.trim().is_empty()); + } + if pages.iter().all(|p| p.words.is_empty()) { + return Err(failed("the OCR review has no words to apply")); + } + let out = match a.opt_str("output_mode")?.unwrap_or("searchable") { + "searchable" => { + if a.get("out").is_some() { + return Err(ToolError::InvalidArgs("out is only for editable output".into())); + } + let count = self.session.apply_ocr_checked(id, &pages, &review.guard).map_err(failed)?; + json!({ "applied": count, "review": handle }) + } + "editable" => { + // The editable output writes the review's words out of the document: a + // document that forbids copying refuses here (the review is kept). + self.doc_to_copy(a)?; + let target = self.resolve(a.str("out")?, true)?; + if self + .session + .get(id) + .and_then(|d| d.path.as_deref()) + .and_then(|p| std::fs::canonicalize(p).ok()) + .as_ref() + .is_some_and(|source| std::fs::canonicalize(&target).as_ref().ok() == Some(source)) + { + return Err(failed("out is the source document; choose a new file")); + } + // A NEW file: an existing one is never replaced silently (the review is kept). + if target.exists() { + return Err(failed(format!("out already exists ({}); choose a path that does not exist yet", target.to_string_lossy()))); + } + let bytes = self.session.editable_ocr_bytes(id, &pages).map_err(failed)?; + write_atomic(&target, &bytes)?; + json!({ "out": target.to_string_lossy(), "review": handle, "words": pages.iter().map(|p| p.words.len()).sum::() }) + } + _ => return Err(ToolError::InvalidArgs("output_mode must be searchable or editable".into())), + }; + self.ocr_reviews.remove(&id); + Ok(out) + } + + /// Read/update the same per-language dictionary file used by OCR Verify. + pub(crate) fn ocr_dictionary(&mut self, a: &Args) -> Result { + use pdfcraft_engine::ocr::dictionary; + use std::io::Read as _; + for key in ["add", "remove"] { + if let Some(value) = a.get(key) { + let values = value.as_array().ok_or_else(|| Args::wrong(key, "an array of strings"))?; + if values.len() > 65536 { + return Err(failed("at most 65536 dictionary words are allowed")); + } + } + } + let add = if a.get("add").is_some() { a.strs("add")? } else { Vec::new() }; + let remove = if a.get("remove").is_some() { a.strs("remove")? } else { Vec::new() }; + let writing = a.get("add").is_some() || a.get("remove").is_some(); + // Updating sorts, lower-cases and rewrites the file, so this tool names dictionary files only: + // pointed at `.env` or a README it would corrupt it. + let file = std::path::Path::new(a.str("path")?).file_name().and_then(|n| n.to_str()).unwrap_or(""); + let plain = file.chars().all(|c| c.is_ascii_alphanumeric() || matches!(c, '-' | '_' | '.')); + if file.len() > 64 || !plain || !file.starts_with("ocr-dictionary") || !file.ends_with(".txt") { + return Err(failed("path must name a dictionary file: ocr-dictionary-.txt (letters, digits, '-', '_' and '.' only)")); + } + let path = self.resolve(a.str("path")?, writing)?; + let mut input = String::new(); + match std::fs::File::open(&path) { + Ok(file) => { + file.take((dictionary::MAX_BYTES + 1) as u64).read_to_string(&mut input).map_err(|e| failed(format!("OCR dictionary: {e}")))?; + } + Err(e) if e.kind() == std::io::ErrorKind::NotFound && writing => {} + Err(e) => return Err(failed(format!("OCR dictionary: {e}"))), + } + let text = dictionary::update(&input, &add, &remove).map_err(failed)?; + if writing { + write_atomic(&path, text.as_bytes())?; + } + let words = dictionary::words(&text).map_err(failed)?; + Ok(json!({ "path": path.to_string_lossy(), "count": words.len(), "words": words })) } - /// Whether text recognition's models are installed, the directories searched for them (in - /// order), and the languages it reads, each as a code and a name. pub(crate) fn ocr_status(&self) -> Result { use pdfcraft_engine::ocr; let dirs: Vec = ocr::Models::search_dirs().iter().map(|d| d.to_string_lossy().into_owned()).collect(); let langs: Vec = ocr::LANGUAGES.iter().map(|(c, n)| json!({ "code": c, "name": n })).collect(); - Ok(json!({ "available": ocr::available(), "search_dirs": dirs, "languages": langs })) + let engines: Vec = ocr::engines_status() + .iter() + .map(|e| { + let mut v = json!({ "id": e.id, "available": e.available }); + if let Some(p) = &e.program { + v["path"] = json!(p); + } + if let Some(vv) = &e.version { + v["version"] = json!(vv); + } + if let Some(why) = &e.why_not { + v["unavailable"] = json!(why); + } + v + }) + .collect(); + Ok(json!({ "available": ocr::available(), "search_dirs": dirs, "languages": langs, "engines": engines })) } } diff --git a/crates/automation/src/batch.rs b/crates/automation/src/batch.rs index decb18d2b7..f650e565b7 100644 --- a/crates/automation/src/batch.rs +++ b/crates/automation/src/batch.rs @@ -84,8 +84,8 @@ impl<'a> Recipe<'a> { match *step { "convert" => bytes = session.convert_to_pdf(name, &bytes)?.1, "ocr" => { - let engine = ocr::engine().map_err(failed)?; - let result = ocr::recognize_file(name, bytes, None, self.ocr.clone(), &engine, |_, _| true).map_err(failed)?; + let recognizers = ocr::recognizers(&self.ocr).map_err(failed)?; + let result = ocr::recognize_file(name, bytes, None, self.ocr.clone(), &recognizers, |_, _| true).map_err(failed)?; log.push( json!({"step":"ocr","words":result.words(),"skipped_pages":result.pages.iter().filter(|p| p.skipped.is_some()).count()}), ); @@ -185,6 +185,7 @@ impl Automation { let recipe = Recipe::parse(self, args)?; let recursive = args.opt_bool("recursive")?.unwrap_or(false); let stop = args.opt_bool("stop_on_error")?.unwrap_or(false); + let dry_run = args.opt_bool("dry_run")?.unwrap_or(false); let paths = args.strs("paths")?; if paths.is_empty() || paths.len() > 1000 { return Err(Args::wrong("paths", "1 to 1000 files or folders")); @@ -211,11 +212,41 @@ impl Automation { let mut files = discovery.skipped; let (mut completed, mut failed_count) = (0, 0); let mut stopped = false; + let mut planned_outputs: HashSet = HashSet::new(); for (path, relative) in discovery.files { if stopped || !recipe.accepts(&path) { files.push(json!({"path":path.to_string_lossy(),"status":"skipped","reason":if stopped {"stopped after error"} else {"unsupported input extension"}})); continue; } + if dry_run { + let planned: Result = (|| { + let target = out.join(&relative).with_extension("pdf"); + let target = self.resolve(target.to_str().ok_or_else(|| failed("output path is not UTF-8"))?, true)?; + if !target.starts_with(&out) { + return Err(failed("output path leaves out_dir")); + } + let dir = target.parent().ok_or_else(|| failed("output has no parent"))?; + let stem = target.file_stem().ok_or_else(|| failed("output has no stem"))?.to_string_lossy().into_owned(); + for n in 1..=10_000 { + let candidate = if n == 1 { target.clone() } else { dir.join(format!("{stem} ({n}).pdf")) }; + if candidate.symlink_metadata().is_ok() || planned_outputs.contains(&candidate) { + continue; + } + planned_outputs.insert(candidate.clone()); + return Ok(candidate); + } + Err(failed("all 10000 output names are occupied")) + })(); + match planned { + Ok(target) => files.push(json!({"path":path.to_string_lossy(),"status":"planned","output":target.to_string_lossy().replace('\\', "/"),"steps":recipe.steps})), + Err(e) => { + failed_count += 1; + files.push(json!({"path":path.to_string_lossy(),"status":"error","error":e.to_string()})); + stopped = stop; + } + } + continue; + } // Recheck confinement and links before reading a discovered file. let result: Result<_> = std::panic::catch_unwind(std::panic::AssertUnwindSafe(|| { let current = self.resolve(path.to_str().ok_or_else(|| failed("input path is not UTF-8"))?, false)?; @@ -244,8 +275,8 @@ impl Automation { } } } - let skipped = files.len().saturating_sub(completed + failed_count); - Ok(json!({"completed":completed,"failed":failed_count,"skipped":skipped,"stopped":stopped,"files":files})) + let skipped = files.iter().filter(|file| file["status"] == "skipped").count(); + Ok(json!({"dry_run":dry_run,"completed":completed,"failed":failed_count,"skipped":skipped,"stopped":stopped,"files":files})) } } @@ -279,4 +310,20 @@ mod tests { discovery.visited = 0; assert!(discovery.walk(Path::new("absent"), Path::new(""), Path::new("output"), true, MAX_DEPTH + 1).unwrap_err().to_string().contains("64")); } + + #[test] + fn doc_batch_dry_run_lists_outputs_without_writing() { + let dir = tempfile::tempdir().unwrap(); + std::fs::create_dir(dir.path().join("input")).unwrap(); + let pdf = Session::new().create_from_text("Doc", "Hello").unwrap(); + std::fs::write(dir.path().join("input/a.pdf"), &*pdf).unwrap(); + let auto = Automation::new().with_root(dir.path()).unwrap(); + let report = auto.doc_batch(&Args(&json!({"paths":["input"],"steps":["optimize"],"out_dir":"out","dry_run":true}))).unwrap(); + assert_eq!(report["dry_run"], true, "{report}"); + assert_eq!(report["completed"], 0, "{report}"); + assert_eq!(report["failed"], 0, "{report}"); + assert_eq!(report["files"][0]["status"], "planned", "{report}"); + assert!(report["files"][0]["output"].as_str().unwrap().ends_with("out/a.pdf"), "{report}"); + assert!(!dir.path().join("out").exists()); + } } diff --git a/crates/automation/src/bates.rs b/crates/automation/src/bates.rs index 3cd1d7849e..5267716e85 100644 --- a/crates/automation/src/bates.rs +++ b/crates/automation/src/bates.rs @@ -199,7 +199,7 @@ impl Automation { } /// Publish a PDF atomically while refusing a target created by another process after preflight. -fn publish_new(path: &Path, bytes: &[u8]) -> Result<()> { +pub(super) 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)?; diff --git a/crates/automation/src/comments.rs b/crates/automation/src/comments.rs index 135d0868ee..78f4cefbe0 100644 --- a/crates/automation/src/comments.rs +++ b/crates/automation/src/comments.rs @@ -5,7 +5,9 @@ use std::collections::HashMap; -use pdfcraft_engine::{Edit, LineEnding, Markup, NewAnnotation, NoteIcon, ReviewState, Rgb, Shape, StampGroup, StampKind, Style, SummarySort}; +use pdfcraft_engine::{ + BorderShape, Edit, LineEnding, Markup, NewAnnotation, NoteIcon, ReviewState, Rgb, Shape, StampGroup, StampKind, Style, SummarySort, +}; use pdfcraft_render::{Annotation, PageInfo}; use serde_json::{Value, json}; @@ -190,6 +192,25 @@ impl Automation { "rect": crate::view_rect(&doc.info, c.page, c.shown_rect(doc.info.pages.get(c.page).map_or(0, |p| p.rotation))), "color": c.color.map(hex), }); + // A text box's or typed text's oval or circle (a rectangle is not reported). + if c.subtype == "FreeText" + && let Some(shape) = doc.comment_props(c.page, c.index).and_then(|p| p.border_shape).filter(|s| *s != BorderShape::Rectangle) + { + v["border_shape"] = json!(shape.name().to_ascii_lowercase()); + } + // How opaque it is drawn: as a whole, or its fill and text each at their own. + // Not for replies, which are drawn with the comment they answer. + if !c.is_reply() + && let Some(p) = doc.comment_props(c.page, c.index) + { + v["opacity"] = json!(p.opacity); + if let Some(f) = p.fill_opacity { + v["fill_opacity"] = json!(f); + } + if let Some(t) = p.text_opacity { + v["text_opacity"] = json!(t); + } + } // A line's ends, or the corners of connected lines, a polygon or a cloud, as // comment_edit's `points` takes them. // Unchanged on a page the viewer could not read, as `rect` is. @@ -253,6 +274,12 @@ impl Automation { if endings.is_some() && !matches!(kind, "line" | "arrow" | "polyline" | "callout") { return Err(ToolError::InvalidArgs("endings apply to a line, arrow, polyline or callout".into())); } + // Shift while drawing: each end or corner held level or plumb with the one before. + let ortho = a.opt_bool("ortho")?.unwrap_or(false); + if ortho && !matches!(kind, "line" | "arrow" | "polygon" | "cloud" | "polyline") { + return Err(ToolError::InvalidArgs("ortho applies to a line, arrow, polygon, cloud or polyline".into())); + } + let held = |last: [f64; 2], p: [f64; 2]| if ortho { pdfcraft_engine::measure::snap::ortho(last, p) } else { p }; let markup = match kind { "highlight" => Some(Markup::Highlight), "underline" => Some(Markup::Underline), @@ -325,7 +352,8 @@ impl Automation { Shape::TextBox { rect: rect_to_user(&info, a.need::<4>("rect", "a text box")?), font_size } } "line" | "arrow" => { - let (f, t) = (a.need::<2>("from", "a line")?, a.need::<2>("to", "a line")?); + let f = a.need::<2>("from", "a line")?; + let t = held(f, a.need::<2>("to", "a line")?); let [start, end] = ending_pair(kind, endings.as_deref())?; Shape::Line { from: to_user(&info, f[0], f[1]), to: to_user(&info, t[0], t[1]), start, end } } @@ -352,10 +380,15 @@ impl Automation { "polygon" | "cloud" | "polyline" => { let wrong = || ToolError::InvalidArgs(format!("{kind} needs `points`: an array of [x, y] points")); let pts = a.get("points").and_then(|p| p.as_array()).ok_or_else(wrong)?; + let mut last = None; let vertices = pts .iter() .map(|p| match p.as_array().map(|p| p.iter().map(|v| v.as_f64()).collect::>()).as_deref() { - Some([Some(x), Some(y)]) => Ok(to_user(&info, *x, *y)), + Some([Some(x), Some(y)]) => { + let p = last.map_or([*x, *y], |l| held(l, [*x, *y])); + last = Some(p); + Ok(to_user(&info, p[0], p[1])) + } _ => Err(wrong()), }) .collect::>>()?; @@ -425,9 +458,28 @@ impl Automation { if let Some(o) = a.opt_num("opacity")? { style.opacity = o.clamp(0.0, 1.0); } + // The fill's and a text box's text's own opacities (the line keeps `opacity`). + let (fill_opacity, text_opacity) = (a.opt_num("fill_opacity")?, a.opt_num("text_opacity")?); + let texts = matches!(shape, Shape::TextBox { .. } | Shape::Typewriter { .. } | Shape::Callout { .. }); + if fill_opacity.is_some() && !(texts || matches!(shape, Shape::Rectangle { .. } | Shape::Oval { .. } | Shape::Polygon { .. })) { + return Err(ToolError::InvalidArgs( + "fill_opacity applies to a rectangle, oval, polygon, cloud, text box, typewriter text or callout".into(), + )); + } + if text_opacity.is_some() && !texts { + return Err(ToolError::InvalidArgs("text_opacity applies to a text box, typewriter text or callout".into())); + } + style.fill_opacity = fill_opacity.map(|o| o.clamp(0.0, 1.0)); + style.text_opacity = text_opacity.map(|o| o.clamp(0.0, 1.0)); if let Some(w) = a.opt_num("width")? { style.width = w.max(0.0); } + if let Some(b) = border_shape(a)? { + if !matches!(shape, Shape::TextBox { .. } | Shape::Typewriter { .. }) { + return Err(ToolError::InvalidArgs("border_shape is for a text box or typewriter text".into())); + } + style.border_shape = b; + } let contents = a.opt_str("contents")?.unwrap_or_default().to_string(); let author = a.opt_str("author")?.unwrap_or(DEFAULT_AUTHOR).to_string(); // Replace Text: the struck-out text and a grouped caret holding `contents`. @@ -488,6 +540,7 @@ impl Automation { } pub(crate) fn fill_sign_add(&mut self, a: &Args) -> Result { + let border_shape = border_shape(a)?; use pdfcraft_engine::FillMark; let page = self.page(a)?; let info = self.doc(a)?.info.pages[page].clone(); @@ -515,6 +568,25 @@ impl Automation { if !(4.0..=300.0).contains(&size) { return Err(ToolError::InvalidArgs("font_size must be 4–300 pt".into())); } + let requested_border = a.opt_num("border")?; + if requested_border.is_some() && !matches!(kind, "text" | "date") { + return Err(ToolError::InvalidArgs("border is only for type text or date".into())); + } + let border = requested_border.unwrap_or(0.0); + if !(0.0..=12.0).contains(&border) { + return Err(ToolError::InvalidArgs("border must be 0–12 pt".into())); + } + let border_color = a.opt_str("border_color")?.map(parse_color).transpose()?; + if border_color.is_some() && border <= 0.0 { + return Err(ToolError::InvalidArgs("border_color needs a border".into())); + } + if border_shape.is_some() && !matches!(kind, "text" | "date") { + return Err(ToolError::InvalidArgs("border_shape is only for type text or date".into())); + } + // Without a border an oval or a circle would grow the box around nothing drawn. + if border_shape.is_some_and(|s| s != BorderShape::Rectangle) && border <= 0.0 { + return Err(ToolError::InvalidArgs("border_shape needs a border".into())); + } if let Some(path) = a.opt_str("path")? { if !matches!(kind, "signature" | "initials") || a.opt_str("text")?.is_some() { return Err(ToolError::InvalidArgs("path is only for an image signature or initials; pass either path or text".into())); @@ -538,13 +610,16 @@ impl Automation { let edit = image.edit(page, &info, at, kind == "initials", &author).ok_or_else(|| ToolError::InvalidArgs("at must be finite".into()))?; return self.apply(a, edit); } + // A circle goes around the text, so its box is no wider than the text needs. + let min_width = if border_shape == Some(BorderShape::Circle) { 0.0 } else { 20.0 }; let text_at = |t: &str| { 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 w = (longest + 8.0).clamp(min_width, 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 } + let [x0, y0, x1, y1] = pdfcraft_engine::text_box_at(i64::from(info.rotation), at, w, h).unwrap_or([at[0], at[1] - h, at[0] + w, at[1]]); + // A border goes around the box, so the text sits where it would without one. + Shape::Typewriter { rect: [x0 - border, y0 - border, x1 + border, y1 + border], font_size: size } }; let (shape, contents) = match kind { "text" => { @@ -590,6 +665,11 @@ impl Automation { if let Some(color) = requested_color { style.color = color; } + if matches!(shape, Shape::Typewriter { .. }) { + style.width = border; + style.border_color = border_color; + style.border_shape = border_shape.unwrap_or_default(); + } self.apply(a, Edit::AddAnnotation(NewAnnotation { page, shape, style, contents, author })) } @@ -656,6 +736,21 @@ impl Automation { let fill = if f.eq_ignore_ascii_case("none") { None } else { Some(parse_color(f)?) }; edits.push(Edit::FillAnnotation { page, index, fill }); } + if let Some(c) = a.opt_str("border_color")? { + let color = if c.eq_ignore_ascii_case("text") { None } else { Some(parse_color(c)?) }; + edits.push(Edit::BorderColorAnnotation { page, index, color }); + } + if let Some(shape) = border_shape(a)? { + edits.push(Edit::BorderShapeAnnotation { page, index, shape }); + } + // After `opacity`, which sets the whole comment's. + let (fill_opacity, text_opacity) = (a.opt_num("fill_opacity")?, a.opt_num("text_opacity")?); + if fill_opacity.into_iter().chain(text_opacity).any(|o| !(0.0..=1.0).contains(&o)) { + return Err(ToolError::InvalidArgs("fill_opacity and text_opacity are 0–1".into())); + } + if fill_opacity.is_some() || text_opacity.is_some() { + edits.push(Edit::PartOpacity { page, index, fill: fill_opacity, text: text_opacity }); + } if let Some(size) = a.opt_num("font_size")? { if !(1.0..=400.0).contains(&size) { return Err(ToolError::InvalidArgs("font_size must be 1–400 pt".into())); @@ -689,7 +784,7 @@ impl Automation { } if edits.is_empty() { return Err(ToolError::InvalidArgs( - "nothing to change: pass contents, color, opacity, width, fill, font_size, rect, move or points".into(), + "nothing to change: pass contents, color, opacity, fill_opacity, text_opacity, width, fill, border_color, border_shape, font_size, rect, move or points".into(), )); } let edit = if edits.len() == 1 { edits.remove(0) } else { Edit::Batch { label: "Edit comment".into(), edits } }; @@ -700,6 +795,49 @@ impl Automation { let (page, index) = self.comment_target(a)?; self.apply(a, Edit::DeleteAnnotation { page, index }) } + + /// The XFDF of the listed comments and their replies (`comments`: 1-based [page, index] pairs). + pub(crate) fn comments_copy(&self, a: &Args) -> Result { + let id = self.doc(a)?.id; + let all = self.comments(a)?; + let shape = || ToolError::InvalidArgs("comments: [[page, index], …] (1-based, as comment_list reports)".into()); + let list = a.get("comments").and_then(Value::as_array).ok_or_else(shape)?; + let mut which = Vec::with_capacity(list.len()); + for item in list { + let pair = item.as_array().filter(|p| p.len() == 2).and_then(|p| Some((p.first()?.as_u64()?, p.get(1)?.as_u64()?))); + let Some((page, index)) = pair.filter(|(p, i)| *p >= 1 && *i >= 1) else { return Err(shape()) }; + let (page, index) = (usize::try_from(page - 1).map_err(|_| shape())?, usize::try_from(index - 1).map_err(|_| shape())?); + if !all.iter().any(|c| c.page == page && c.index == index) { + return Err(failed(format!("there is no comment {} on page {} (see comment_list)", index + 1, page + 1))); + } + which.push((page, index)); + } + let xfdf = self.session.export_comments(id, &which).map_err(failed)?; + Ok(json!({ "xfdf": xfdf, "comments": which.len() })) + } + + /// Add the comments of `xfdf` (from `comments_copy`) to `page` as new comments. + pub(crate) fn comments_paste(&mut self, a: &Args) -> Result { + let page = self.page(a)?; + let xfdf = a.str("xfdf")?.to_owned(); + if !pdfcraft_engine::is_xfdf_comments(&xfdf) { + return Err(ToolError::InvalidArgs("xfdf: the text comments_copy returned (XFDF with )".into())); + } + let offset = match a.nums::<2>("at")? { + Some([x, y]) => { + let info = self.doc(a)?.info.pages.get(page).cloned().ok_or_else(|| failed(format!("no page {}", page + 1)))?; + let [cx, cy] = to_user(&info, x, y); + let b = + pdfcraft_engine::comments_bounds(&xfdf).ok_or_else(|| ToolError::InvalidArgs("xfdf: no comment with a rect to place".into()))?; + Some([cx - (b[0] + b[2]) / 2.0, cy - (b[1] + b[3]) / 2.0]) + } + None => None, + }; + let before = self.comments(a)?.len(); + let mut out = self.apply(a, Edit::PasteComments { xfdf, page, offset })?; + out["comments"] = json!(self.comments(a)?.len().saturating_sub(before)); + Ok(out) + } } impl Automation { @@ -744,6 +882,13 @@ impl Automation { } } +/// `border_shape`: `rectangle`, `oval` or `circle`. +fn border_shape(a: &Args) -> Result> { + a.opt_str("border_shape")? + .map(|s| BorderShape::parse(s).ok_or_else(|| ToolError::InvalidArgs(format!("unknown border_shape {s:?}: rectangle, oval or circle")))) + .transpose() +} + #[cfg(test)] mod tests { use super::*; diff --git a/crates/automation/src/content.rs b/crates/automation/src/content.rs index 6b25c31f61..1f26dcc26a 100644 --- a/crates/automation/src/content.rs +++ b/crates/automation/src/content.rs @@ -2,7 +2,7 @@ //! move/resize/retype/restyle it, delete it. Geometry is in points from the top-left of the //! displayed page (y down), like every other tool. -use pdfcraft_engine::{ADDED_CHAR_SPACING_LIMIT, AddedContent, AddedText, Edit, FontFamily, TextAlign}; +use pdfcraft_engine::{ADDED_CHAR_SPACING_LIMIT, AddedContent, AddedText, Edit, FontFamily, TextAlign, TextInk}; use serde_json::{Value, json}; use crate::comments::parse_color; @@ -30,6 +30,27 @@ fn rect_arg(a: &Args, key: &str) -> Result> { .transpose() } +const INK_ARGS: &str = "give one of color (#RRGGBB or a name), gray (0 black to 1 white) and cmyk ([c, m, y, k], each 0 to 1)"; + +/// `gray` or `cmyk`: the text painted in DeviceGray or DeviceCMYK rather than RGB. At most one of +/// them and `color`. +fn ink_arg(a: &Args) -> Result> { + if ["color", "gray", "cmyk"].iter().filter(|k| a.get(k).is_some()).count() > 1 { + return Err(bad(INK_ARGS)); + } + let unit = |v: Option, key: &str| v.filter(|v| (0.0..=1.0).contains(v)).ok_or_else(|| bad(format!("{key} takes numbers from 0 to 1"))); + if let Some(g) = a.get("gray") { + return Ok(Some(TextInk::Gray(unit(g.as_f64(), "gray")?))); + } + let Some(c) = a.get("cmyk") else { return Ok(None) }; + let parts = c.as_array().filter(|p| p.len() == 4).ok_or_else(|| bad("cmyk must be [c, m, y, k]"))?; + let mut cmyk = [0.0; 4]; + for (out, v) in cmyk.iter_mut().zip(parts) { + *out = unit(v.as_f64(), "cmyk")?; + } + Ok(Some(TextInk::Cmyk(cmyk))) +} + /// Apply the style arguments to `t`. fn style(a: &Args, t: &mut AddedText) -> Result<()> { if let Some(s) = a.opt_num("size")? { @@ -49,8 +70,12 @@ fn style(a: &Args, t: &mut AddedText) -> Result<()> { if let Some(i) = a.opt_bool("italic")? { t.italic = i; } - if let Some(c) = a.opt_str("color")? { - t.color = parse_color(c)?; + if let Some(ink) = ink_arg(a)? { + t.set_ink(Some(ink)); + } else if let Some(c) = a.opt_str("color")? { + // An RGB colour paints in RGB, even one that is the ink's look. + t.set_ink(None); + t.set_color(parse_color(c)?); } if let Some(al) = a.opt_str("align")? { t.align = parse_align(al)?; @@ -124,6 +149,12 @@ impl Automation { v["bold"] = json!(t.bold); v["italic"] = json!(t.italic); v["char_spacing"] = json!(t.char_spacing); + // Text painted in a print colour space says so; RGB text has neither. + match t.painted_ink() { + Some(TextInk::Gray(g)) => v["gray"] = json!(g), + Some(TextInk::Cmyk(c)) => v["cmyk"] = json!(c), + None => {} + } } AddedContent::Image(_) => v["type"] = json!("image"), } @@ -205,8 +236,8 @@ impl Automation { if a.get("text").is_some() { return Err(bad("images have no text")); } - if ["font", "size", "bold", "italic", "color", "align", "aligns", "char_spacing"].iter().any(|k| a.get(k).is_some()) { - return Err(bad("font, size, bold, italic, color, align, aligns and char_spacing apply to text")); + if ["font", "size", "bold", "italic", "color", "gray", "cmyk", "align", "aligns", "char_spacing"].iter().any(|k| a.get(k).is_some()) { + return Err(bad("font, size, bold, italic, color, gray, cmyk, align, aligns and char_spacing apply to text")); } if let Some(deg) = a.opt_int("rotate")? { if deg.rem_euclid(90) != 0 { diff --git a/crates/automation/src/dispatch.rs b/crates/automation/src/dispatch.rs index 988461eac0..69c56747c8 100644 --- a/crates/automation/src/dispatch.rs +++ b/crates/automation/src/dispatch.rs @@ -137,6 +137,7 @@ impl Automation { out["detected"] = json!(given.is_none()); out } + "page_enhance_scan" => self.page_enhance_scan(&a)?, "page_delete" => { let pages = self.pages(&a, "pages")?; self.apply(&a, Edit::DeletePages { pages })? @@ -466,6 +467,7 @@ impl Automation { "bring_forward" => ImageEdit::Arrange(pdfcraft_engine::ArrangeOrder::BringForward), "send_backward" => ImageEdit::Arrange(pdfcraft_engine::ArrangeOrder::SendBackward), "remove_crop" => ImageEdit::RemoveCrop, + "ungroup" => ImageEdit::Ungroup, "replace" => { let path = self.resolve(a.str("path")?, false)?; let bytes = read_input(&path)?; @@ -811,6 +813,9 @@ impl Automation { "form_set_actions" => self.form_set_actions(&a)?, "ocr_status" => self.ocr_status()?, "ocr_recognize_files" => self.ocr_recognize_files(&a)?, + "ocr_words" => self.ocr_words(&a)?, + "ocr_review_apply" => self.ocr_review_apply(&a)?, + "ocr_dictionary" => self.ocr_dictionary(&a)?, "accessibility_report" => self.a11y_report(&a)?, "accessibility_review_record" => self.a11y_review_record(&a)?, "accessibility_review_save" => self.a11y_review_save(&a)?, @@ -866,6 +871,8 @@ impl Automation { "comments_summarize" => self.comments_summarize(&a)?, "comment_edit" => self.comment_edit(&a)?, "comment_delete" => self.comment_delete(&a)?, + "comments_copy" => self.comments_copy(&a)?, + "comments_paste" => self.comments_paste(&a)?, other => return Err(ToolError::UnknownTool(other.into())), }; Ok(vec![Content::Json(out)]) @@ -919,3 +926,35 @@ impl Automation { Ok(out) } } + +impl Automation { + /// `page_enhance_scan`: Enhance ▸ Scanned document on the chosen pages (all by default). + fn page_enhance_scan(&mut self, a: &Args) -> Result { + let pages = match a.opt_ints("pages")? { + Some(_) => self.pages(a, "pages")?, + None => Vec::new(), + }; + let level = match a.opt_int("level")? { + None => pdfcraft_engine::scan_clean::ScanCleanSettings::default().level, + Some(l @ 0..=100) => l as u8, + Some(l) => return Err(ToolError::InvalidArgs(format!("level must be between 0 and 100, not {l}"))), + }; + let mut settings = pdfcraft_engine::scan_clean::ScanCleanSettings::at(level); + if let Some(on) = a.opt_bool("edge_shadows")? { + settings.edge_shadows = on; + } + if let Some(on) = a.opt_bool("despeckle")? { + settings.despeckle = on; + } + let id = self.doc(a)?.id; + let report = self.session.enhance_scanned_pages(id, &pages, settings).map_err(failed)?; + let numbered = |p: &[usize]| p.iter().map(|p| p + 1).collect::>(); + let skipped: Vec = report.skipped.iter().map(|k| json!({ "pages": numbered(&k.pages), "name": k.name, "reason": k.reason })).collect(); + let mut out = summary(self.doc(a)?); + out["pages_cleaned"] = json!(numbered(&report.pages)); + out["images"] = json!(report.images); + out["not_scanned"] = json!(numbered(&report.not_scanned)); + out["skipped"] = json!(skipped); + Ok(out) + } +} diff --git a/crates/automation/src/documents.rs b/crates/automation/src/documents.rs index 979b041a73..e4d0d722a0 100644 --- a/crates/automation/src/documents.rs +++ b/crates/automation/src/documents.rs @@ -6,6 +6,10 @@ use super::{Arc, Automation, BlockKey, DocId, Document, Edit, Path, PathBuf, Tex /// How far a watermark may be moved from the page centre, in points (a page is at most 14,400). const WATERMARK_MAX_OFFSET: f64 = 20_000.0; +/// `doc_optimize` with `target_bytes`: (max target ppi, max JPEG quality) per extra attempt, mildest first. +/// The quality applies only to images the caller left on JPEG; zip and retain keep their encoding. +const TARGET_LADDER: [(f64, u8); 5] = [(110.0, 45), (96.0, 35), (72.0, 28), (54.0, 20), (36.0, 12)]; + /// Bookmarks in one page of the bookmark list, by default and at most. const BOOKMARK_PAGE: usize = 100; @@ -120,6 +124,7 @@ impl Automation { self.texts.remove(&id); self.listed.retain(|(d, _), _| *d != id); self.evicted.remove(&id); + self.ocr_reviews.remove(&id); Ok(json!({ "closed": id.0 })) } @@ -379,7 +384,45 @@ impl Automation { }) .collect::>()?, }; - let (bytes, r) = self.session.optimized_bytes(id, &settings, &discard).map_err(failed)?; + let target = match a.opt_int("target_bytes")? { + None => None, + Some(t) if t >= 1 => Some(usize::try_from(t).map_err(|_| ToolError::InvalidArgs(format!("target_bytes {t} is too large")))?), + Some(t) => return Err(ToolError::InvalidArgs(format!("target_bytes must be at least 1, not {t}"))), + }; + let (mut bytes, mut r) = self.session.optimized_bytes(id, &settings, &discard).map_err(failed)?; + let mut attempts = 1; + let mut step_used = 0; + // Settings already optimized with; a rung that changes nothing is not run again. + let mut tried = vec![settings.clone()]; + if let Some(t) = target { + // Stronger image settings, one rung per attempt, until the copy fits. Every attempt + // starts from the open document, so a failed one changes nothing; the number of + // attempts is fixed. The smallest copy is kept if none fits. + for (k, &(ppi, quality)) in TARGET_LADDER.iter().enumerate() { + if bytes.len() <= t { + break; + } + let mut s = settings.clone(); + for img in [&mut s.color, &mut s.gray] { + img.downsample = true; + img.target_ppi = img.target_ppi.min(ppi); + img.above_ppi = img.above_ppi.min(ppi * 1.5).max(img.target_ppi); + // Only a caller who chose JPEG gets a lower quality; zip and retain stay as asked. + if let Compression::Jpeg(q) = img.compression { + img.compression = Compression::Jpeg(q.min(quality)); + } + } + if tried.contains(&s) { + continue; + } + let (b2, r2) = self.session.optimized_bytes(id, &s, &discard).map_err(failed)?; + tried.push(s); + attempts += 1; + if b2.len() < bytes.len() { + (bytes, r, step_used) = (b2, r2, k + 1); + } + } + } write_atomic(&path, &bytes)?; fn valid_version(v: &[u8]) -> Option<&str> { if matches!(v, [b'1'..=b'9', b'.', b'0'..=b'9']) { std::str::from_utf8(v).ok() } else { None } @@ -399,7 +442,19 @@ impl Automation { // entry). Both are "d.d", so text order is version order. let pdf_version = catalog_version.as_deref().into_iter().chain(header_version).max(); let o = &r.optimize; - Ok(json!({ + let mut extra = json!({}); + if let Some(t) = target { + let (ppi, quality) = step_used.checked_sub(1).and_then(|k| TARGET_LADDER.get(k)).copied().unzip(); + let lossy = matches!(settings.color.compression, Compression::Jpeg(_)) || matches!(settings.gray.compression, Compression::Jpeg(_)); + let quality = quality.filter(|_| lossy); + extra = json!({ + "target_bytes": t, + "target_reached": bytes.len() <= t, + "attempts": attempts, + "target_settings": { "step": step_used, "max_ppi": ppi, "max_jpeg_quality": quality }, + }); + } + let mut out = json!({ "path": path.to_string_lossy(), "pdf_version": pdf_version, "object_streams": settings.effective_object_streams(), @@ -424,7 +479,11 @@ impl Automation { "unused_xobjects": o.unused_xobjects, "merged_objects": r.merged, "discarded": r.discarded.iter().map(|(h, n)| json!({ "category": h.id(), "count": n })).collect::>(), - })) + }); + if let (Some(o), Some(e)) = (out.as_object_mut(), extra.as_object()) { + o.extend(e.iter().map(|(k, v)| (k.clone(), v.clone()))); + } + Ok(out) } /// A watermark or background picture: `file` (an image or a PDF) and `file_page` (1-based). diff --git a/crates/automation/src/json.rs b/crates/automation/src/json.rs index 9e93d4c347..c950e72f05 100644 --- a/crates/automation/src/json.rs +++ b/crates/automation/src/json.rs @@ -375,6 +375,9 @@ pub(crate) fn info(d: &Document) -> Value { })).collect::>(), "warnings": i.warnings, "repairs": d.repair_log(), + // Objects that could not be read (each reads as null): nothing was repaired, what they held is + // lost. Last, so it includes what reading the fields above failed on. + "unreadable_objects": d.unreadable_objects(), }) } diff --git a/crates/automation/src/lib.rs b/crates/automation/src/lib.rs index 520d836b01..7e4443d244 100644 --- a/crates/automation/src/lib.rs +++ b/crates/automation/src/lib.rs @@ -76,6 +76,12 @@ pub(crate) use paths::{read_input, read_input_bytes}; #[cfg(test)] use paths::{write_atomic_synced, write_atomic_with}; +struct OcrReview { + handle: u64, + guard: pdfcraft_engine::ocr::OcrGuard, + pages: Vec, +} + /// A headless PdfCraft session driven by tool calls. pub struct Automation { session: Session, @@ -92,6 +98,9 @@ pub struct Automation { /// Documents that lost a listing to the cap. A page of one with no listing is refused rather /// than read as "a number is a position", which the page may no longer match. evicted: HashSet, + /// Review sessions held for `ocr_words` (a guard and the pages read), by document. + ocr_reviews: HashMap, + next_ocr_review: u64, } impl Default for Automation { @@ -110,6 +119,8 @@ impl Automation { texts: TextCache::default(), listed: HashMap::new(), evicted: HashSet::new(), + ocr_reviews: HashMap::new(), + next_ocr_review: 0, } } diff --git a/crates/automation/src/pages.rs b/crates/automation/src/pages.rs index 8c793be153..6db58ab475 100644 --- a/crates/automation/src/pages.rs +++ b/crates/automation/src/pages.rs @@ -20,6 +20,10 @@ pub(crate) const FIND_MAX_WARNINGS: usize = 100; pub(crate) const FIND_MAX_WARNING_BYTES: usize = 1024; +/// HTML that one `text_extract` with `format: "html"` returns across all its pages; a page past +/// it gets none. `html_truncated` covers this and any page whose own copy hit its caps. +const MAX_EXTRACT_HTML_BYTES: usize = 32 << 20; + impl Automation { // ---- pages and text ---------------------------------------------------------------------- @@ -201,6 +205,16 @@ impl Automation { } pub(crate) fn text_extract(&mut self, a: &Args) -> Result { + self.text_extract_within(a, MAX_EXTRACT_HTML_BYTES) + } + + /// [`Self::text_extract`] with at most `html_budget` bytes of HTML across all pages. + pub(crate) fn text_extract_within(&mut self, a: &Args, html_budget: usize) -> Result { + let html = match a.opt_str("format")?.unwrap_or("text") { + "text" => false, + "html" => true, + other => return Err(ToolError::InvalidArgs(format!("format must be \"text\" or \"html\", not {other:?}"))), + }; let doc = self.doc_to_copy(a)?; let id = doc.id; let pages = match a.opt_ints("pages")? { @@ -214,8 +228,42 @@ impl Automation { Some(r) => t.column_text(&t.glyphs_in(r)), None => t.plain_text(), }; - let out: Vec = pages.iter().zip(texts).map(|(p, t)| json!({ "page": p + 1, "text": text(&t) })).collect(); - Ok(json!({ "pages": out })) + let doc = self.doc(a)?; + let mut out = Vec::with_capacity(pages.len()); + // `spent`: the budget ran out, so later pages get no HTML. `cut`: some page's HTML is + // missing part of its text, by the budget or by the copy's own caps. + let (mut html_left, mut spent, mut cut) = (html_budget, false, false); + for (&p, t) in pages.iter().zip(texts) { + let mut page = json!({ "page": p + 1, "text": text(&t) }); + if html { + // Copy with formatting: the same glyphs as an HTML fragment, within one budget for + // the whole call; a page past it gets none and the call says so. + let mut copy = pdfcraft_engine::RichCopy::default(); + if !spent { + let glyphs: Vec = match rect { + Some(r) => t.glyphs_in(r), + None => (0..t.glyphs.len()).collect(), + }; + copy = doc.rich_copy(p, &t, &glyphs).map_err(failed)?; + match html_left.checked_sub(copy.html.len()) { + Some(left) => html_left = left, + None => { + spent = true; + copy = pdfcraft_engine::RichCopy::default(); + } + } + } + cut |= spent || copy.truncated; + page["html"] = json!(copy.html); + page["styles_incomplete"] = json!(copy.styles_incomplete || spent); + } + out.push(page); + } + let mut result = json!({ "pages": out }); + if html { + result["html_truncated"] = json!(cut); + } + Ok(result) } /// Matches in document order, extracting page text in growing batches and stopping as soon as diff --git a/crates/automation/src/redact.rs b/crates/automation/src/redact.rs index a146f3f8ff..6ec66ce680 100644 --- a/crates/automation/src/redact.rs +++ b/crates/automation/src/redact.rs @@ -2,8 +2,8 @@ //! (removing what they cover for good) or clear them. use pdfcraft_engine::{ - Edit, Hidden, NewAnnotation, REDACT_MAX_WORDS, REDACTION_CODE_SETS, RedactPattern, RedactionCodeSet, Shape, Style, find_pattern, rect_quad, - redact_word_list, + Edit, Hidden, NewAnnotation, REDACT_MAX_WORDS, REDACT_VALIDATORS, REDACTION_CODE_SETS, RedactPattern, RedactRegex, RedactValidator, + RedactionCodeSet, Shape, Style, find_pattern, rect_quad, redact_word_list, }; use serde_json::{Value, json}; @@ -59,16 +59,20 @@ impl Automation { a.get("find").is_some(), a.get("words").is_some(), a.get("pattern").is_some(), + a.get("regex").is_some(), a.opt_bool("whole_pages")?.unwrap_or(false), ]; if chosen.iter().filter(|c| **c).count() != 1 { - return Err(ToolError::InvalidArgs("pass exactly one of rect (with page), find, words, pattern or whole_pages: true".into())); + return Err(ToolError::InvalidArgs("pass exactly one of rect (with page), find, words, pattern, regex or whole_pages: true".into())); } let case_sensitive = a.opt_bool("case_sensitive")?.unwrap_or(false); let whole_words = a.opt_bool("whole_words")?.unwrap_or(false); if (case_sensitive || whole_words) && a.get("find").is_none() && a.get("words").is_none() { return Err(ToolError::InvalidArgs("case_sensitive and whole_words apply only to find or words".into())); } + if a.get("validate").is_some() && a.get("regex").is_none() { + return Err(ToolError::InvalidArgs("validate applies only to regex".into())); + } // Per searched word or phrase: how many marks it made. let mut matched_words: Vec<(String, usize)> = Vec::new(); if a.get("rect").is_some() { @@ -89,6 +93,19 @@ impl Automation { Some(p) => Some(RedactPattern::from_id(p).ok_or_else(|| ToolError::InvalidArgs(format!("unknown pattern {p:?}")))?), None => None, }; + let user_re = match a.opt_str("regex")? { + Some(src) => { + let validator = match a.opt_str("validate")? { + Some(v) => Some(RedactValidator::from_id(v).ok_or_else(|| { + let ids: Vec<_> = REDACT_VALIDATORS.iter().map(|v| v.id()).collect(); + ToolError::InvalidArgs(format!("unknown validate {v:?}; allowed: {}", ids.join(", "))) + })?), + None => None, + }; + Some(RedactRegex::new(src, validator).map_err(|e| ToolError::InvalidArgs(e.to_string()))?) + } + None => None, + }; let needles: Vec = match (a.opt_str("find")?, a.get("words")) { (Some(f), _) => vec![f.to_owned()], (None, Some(_)) => { @@ -108,9 +125,27 @@ impl Automation { let texts = self.page_texts(id, &pages)?; let info = self.doc(a)?.info.clone(); for (&p, text) in pages.iter().zip(&texts) { - let hits: Vec<(Option, _)> = match pattern { - Some(pat) => text.find_with(|chars| find_pattern(pat, chars)).into_iter().map(|h| (None, h)).collect(), - None => needles + let hits: Vec<(Option, _)> = match (&user_re, pattern) { + (Some(re), _) => { + // A page with too many matches fails the call: marking only the first ones + // would leave the rest readable after redact_apply. + let too_many = std::cell::Cell::new(false); + let found = text.find_with(|chars| { + re.find(chars).unwrap_or_else(|_| { + too_many.set(true); + Vec::new() + }) + }); + if too_many.get() { + return Err(ToolError::InvalidArgs(format!( + "regex has more than 10000 matches on page {}; nothing was marked. Narrow the expression so that every match can be marked", + p + 1 + ))); + } + found.into_iter().map(|h| (None, h)).collect() + } + (None, Some(pat)) => text.find_with(|chars| find_pattern(pat, chars)).into_iter().map(|h| (None, h)).collect(), + (None, None) => needles .iter() .enumerate() .flat_map(|(i, w)| text.find_opts(w, case_sensitive, whole_words).into_iter().map(move |h| (Some(i), h))) diff --git a/crates/automation/src/signing.rs b/crates/automation/src/signing.rs index 743a36ff56..df0fd643fb 100644 --- a/crates/automation/src/signing.rs +++ b/crates/automation/src/signing.rs @@ -119,6 +119,7 @@ impl Automation { "page": s.page.map(|p| p + 1), "rect": rect, "visible": s.visible, + "verdict_shown": s.verdict_shown, "revision": s.revision, "sub_filter": s.sub_filter, "algorithm": s.algorithm, diff --git a/crates/automation/src/tests.rs b/crates/automation/src/tests.rs index fd4efa79da..ad0aa039dc 100644 --- a/crates/automation/src/tests.rs +++ b/crates/automation/src/tests.rs @@ -550,3 +550,35 @@ fn tool_file_reads_refuse_inputs_exceeding_512_mib() { } let _ = std::fs::remove_dir_all(&dir); } + +#[test] +fn text_extract_html_has_one_budget_across_pages() { + let mut a = Automation::new(); + let id = search_document(&mut a, 3); + let args = json!({ "doc": id.0, "format": "html" }); + let full = a.text_extract(&Args(&args)).unwrap(); + assert_eq!(full["html_truncated"], false); + let sizes: Vec = full["pages"].as_array().unwrap().iter().map(|p| p["html"].as_str().unwrap().len()).collect(); + assert!(sizes.iter().all(|n| *n > 0), "{full}"); + // Room for two pages: the third gets no HTML, and the call says so. + let capped = a.text_extract_within(&Args(&args), sizes[0] + sizes[1] + sizes[2] - 1).unwrap(); + let pages = capped["pages"].as_array().unwrap(); + assert_eq!(capped["html_truncated"], true); + assert_eq!(pages[1]["html"], full["pages"][1]["html"]); + assert_eq!(pages[2]["html"], ""); + assert_eq!(pages[2]["styles_incomplete"], true); + assert_eq!(pages[2]["text"], "Page 3", "the plain text is not capped by the HTML budget"); + // Plain text alone says nothing about HTML. + assert!(a.text_extract(&Args(&json!({ "doc": id.0 }))).unwrap().get("html_truncated").is_none()); + // A smaller page after the one that overflowed still gets none: "Page 1" fits what "Page 10" + // did not. + let id = search_document(&mut a, 10); + let args = json!({ "doc": id.0, "pages": [10, 1], "format": "html" }); + let full = a.text_extract(&Args(&args)).unwrap(); + let (ten, one) = (full["pages"][0]["html"].as_str().unwrap().len(), full["pages"][1]["html"].as_str().unwrap().len()); + assert!(one < ten, "{full}"); + let capped = a.text_extract_within(&Args(&args), ten - 1).unwrap(); + assert_eq!(capped["pages"][0]["html"], ""); + assert_eq!(capped["pages"][1]["html"], "", "no HTML after the budget ran out: {capped}"); + assert_eq!(capped["pages"][1]["styles_incomplete"], true); +} diff --git a/crates/automation/src/tools.rs b/crates/automation/src/tools.rs index f6afb7966a..995f6c9dad 100644 --- a/crates/automation/src/tools.rs +++ b/crates/automation/src/tools.rs @@ -5,6 +5,8 @@ use serde_json::{Value, json}; +use pdfcraft_engine::REDACT_PATTERNS; + use crate::ToolError; #[derive(Clone, Debug)] @@ -30,6 +32,12 @@ fn pages(what: &str) -> Value { json!({ "type": "array", "items": { "type": "integer", "minimum": 1 }, "minItems": 1, "description": format!("1-based page numbers {what}.") }) } +/// The Search & Redact pattern ids, from the engine's registry, so the advertised schema cannot +/// drift from the patterns the runtime accepts. +fn pattern_enum() -> Value { + json!({ "type": "string", "enum": REDACT_PATTERNS.iter().map(|p| p.id()).collect::>() }) +} + fn path(what: &str) -> Value { json!({ "type": "array", "items": { "type": "integer", "minimum": 1 }, "description": format!("{what}: 1-based positions from the top level, e.g. [2, 1] = the first child of the second bookmark.") }) } @@ -77,6 +85,12 @@ fn schema(props: Value, required: &[&str]) -> Value { json!({ "type": "object", "properties": props, "required": required, "additionalProperties": false }) } +/// The language codes the engines read, as the `language` enum — from the engine's own table, +/// so the schema and the validator can never disagree. +fn language_enum() -> Value { + Value::Array(pdfcraft_engine::ocr::LANGUAGES.iter().map(|(code, _)| json!(code)).collect()) +} + struct T { name: &'static str, title: &'static str, @@ -134,7 +148,7 @@ pub fn tools() -> Vec { "paths": {"type":"array","items":{"type":"string"},"minItems":1,"maxItems":1000}, "out_dir": {"type":"string"}, "steps": {"type":"array","items":{"type":"string","enum":["convert","ocr","optimize"]},"minItems":1,"maxItems":3,"uniqueItems":true}, - "recursive": {"type":"boolean"}, "stop_on_error": {"type":"boolean"}, + "recursive": {"type":"boolean"}, "stop_on_error": {"type":"boolean"}, "dry_run": {"type":"boolean"}, "ppi": {"type":"number","minimum":9,"maximum":1600}, "quality": {"type":"integer","minimum":1,"maximum":100}, "dpi": {"type":"number","minimum":72,"maximum":600}, @@ -150,7 +164,7 @@ pub fn tools() -> Vec { .cmd("file.open") .with(schema(json!({ "path": { "type": "string" }, "password": { "type": "string", "description": "User or owner password for encrypted files." } }), &["path"])), t("doc_list", "List open documents", "List the open documents with their ids, page counts and unsaved state.").ro().with(schema(json!({}), &[])), - t("doc_info", "Inspect a document", "Metadata, page sizes and labels, bookmarks, annotations, form fields, links, layers, page transitions and display times, the destination it opens at, attachments, fonts, security and repair notes.") + t("doc_info", "Inspect a document", "Metadata, page sizes and labels, bookmarks, annotations, form fields, links, layers, page transitions and display times, the destination it opens at, attachments, fonts, security, repair notes and the objects that could not be read.") .ro() .cmd("file.properties") .with(schema(json!({ "doc": doc() }), &["doc"])), @@ -202,13 +216,14 @@ pub fn tools() -> Vec { .with(schema(json!({ "doc": doc(), "pages": pages("to count (default: all)"), "exclude_tables": { "type": "boolean" }, "exclude_code": { "type": "boolean" }, "exclude_images": { "type": "boolean" } }), &["doc"])), - t("text_extract", "Extract text", "Extract the text of some or all pages, in reading order. With rect, only the text inside that rectangle on each page, as Column select takes it: one row per visual line, side-by-side pieces (table cells) separated by a tab.") + t("text_extract", "Extract text", "Extract the text of some or all pages, in reading order. With rect, only the text inside that rectangle on each page, as Column select takes it: one row per visual line, side-by-side pieces (table cells) separated by a tab. With format \"html\", each page also carries html, the same text as Copy with formatting puts on the clipboard (paragraphs, bold, italic, size, colour and font family), and styles_incomplete when some styles had to be left out. With rect, the html is that text in line order, not split into the column's rows and cells. The HTML of one call is capped at 32 MiB in total; pages past the cap carry empty html with styles_incomplete. html_truncated is set when that cap is reached or when a page's own copy was cut at its span or size cap.") .ro() .cmd("edit.column_select") .with(schema( json!({ "doc": doc(), "pages": pages("to extract (default: all)"), - "rect": { "type": "array", "items": { "type": "number" }, "minItems": 4, "maxItems": 4, "description": "Column select: [x0, y0, x1, y1] in points from the top-left of the displayed page; a glyph counts when its centre is inside." } + "rect": { "type": "array", "items": { "type": "number" }, "minItems": 4, "maxItems": 4, "description": "Column select: [x0, y0, x1, y1] in points from the top-left of the displayed page; a glyph counts when its centre is inside." }, + "format": { "type": "string", "enum": ["text", "html"], "description": "text (default) or html: also return each page's text as formatted HTML." } }), &["doc"], )), @@ -240,6 +255,18 @@ pub fn tools() -> Vec { }), &["doc", "page"], )), + t("page_enhance_scan", "Enhance scanned file", "Clean up scanned pages in place (Scan & OCR ▸ Enhance ▸ Scanned document). A page is a scan when its pictures cover at least half of it; the pictures covering at least a tenth of it are cleaned and written back into the same image objects at the same size and colour space (a JPEG stays a JPEG at quality 90, other grey/RGB images are stored losslessly, a 1-bit image stays 1-bit), so the page's invisible OCR text, comments, links and other content stay as they were, and an image drawn on several pages is cleaned once. level (0–100, default 50) is background removal: the paper's illumination is evened out so a grey, yellowed or unevenly lit background turns white, then the contrast is raised so faint strokes darken; colour ink stays colour. edge_shadows (default: on unless level is 0) lightens shadows along the scan's edges (book gutters, a copier's dark border). despeckle (default: from level 60) turns isolated dark specks white; it is the only change a 1-bit scan takes. Returns pages_cleaned (1-based), images (rewritten), not_scanned (pages that are no scan) and skipped ([{pages, name, reason}]: CMYK, indexed, JPEG 2000, JBIG2 or CCITT images, a scan drawn inside grouped Form artwork, broken data, or nothing to change). One undoable step; none when nothing changed.") + .cmd("ocr.enhance") + .with(schema( + json!({ + "doc": doc(), + "pages": pages("to clean up (default: all)"), + "level": { "type": "integer", "minimum": 0, "maximum": 100 }, + "edge_shadows": { "type": "boolean" }, + "despeckle": { "type": "boolean" }, + }), + &["doc"], + )), t("page_delete", "Delete pages", "Delete pages. Undoable until saved.") .destructive() .cmd("page.delete") @@ -593,7 +620,7 @@ pub fn tools() -> Vec { t( "redact_mark", "Mark for redaction", - "Mark content for redaction (nothing is removed until redact_apply). One of: rect [x0, y0, x1, y1] (points from the top-left of the displayed page) with page; find (text, every match); words (a list of words or phrases, every match of each; the result's matched_words says how many marks each made); pattern (phone, email, credit-card, ssn, date: every match, Acrobat's Search & Redact patterns); whole_pages: true. find and words accept case_sensitive and whole_words (both default false). Select one page with page or multiple with pages (default all); do not pass both. rect requires page. overlay: text shown on the box once applied, or code_set (foia: U.S. FOIA (b)(1)(A)…(b)(9); privacy-act: U.S. Privacy Act (d)(5), (j)(1)…(k)(7)) with codes, shown as \"(b)(6), (b)(7)(C)\"; fill: box colour (default black). Undoable.", + "Mark content for redaction (nothing is removed until redact_apply). One of: rect [x0, y0, x1, y1] (points from the top-left of the displayed page) with page; find (text, every match); words (a list of words or phrases, every match of each; the result's matched_words says how many marks each made); pattern (phone, email, credit-card, ssn, date, iban: every match, Acrobat's Search & Redact patterns); regex (your own regular expression, every match, on the page text with words and lines separated by one space; Rust regex syntax: linear-time, no look-around or back-references, case-sensitive unless (?i), at most 1024 bytes, more than 10000 matches on one page fail the call, matches of the empty string are refused) with optional validate (luhn, mod97, iban: keep a match only if its checksum holds); whole_pages: true. find and words accept case_sensitive and whole_words (both default false). Select one page with page or multiple with pages (default all); do not pass both. rect requires page. overlay: text shown on the box once applied, or code_set (foia: U.S. FOIA (b)(1)(A)…(b)(9); privacy-act: U.S. Privacy Act (d)(5), (j)(1)…(k)(7)) with codes, shown as \"(b)(6), (b)(7)(C)\"; fill: box colour (default black). Undoable.", ) .with(schema( json!({ @@ -604,7 +631,9 @@ pub fn tools() -> Vec { "words": { "type": "array", "items": { "type": "string", "minLength": 1 }, "minItems": 1, "maxItems": 1000 }, "case_sensitive": { "type": "boolean", "description": "Match letter case for find or words (default false)." }, "whole_words": { "type": "boolean", "description": "Match whole words for find or words (default false)." }, - "pattern": { "type": "string", "enum": ["phone", "email", "credit-card", "ssn", "date"] }, + "pattern": pattern_enum(), + "regex": { "type": "string", "minLength": 1, "maxLength": 1024, "description": "Regular expression (Rust regex syntax), at most 1024 bytes (maxLength counts characters, the limit is bytes); every match is marked." }, + "validate": { "type": "string", "enum": ["luhn", "mod97", "iban"], "description": "With regex: keep a match only if its checksum is valid (spaces and hyphens ignored)." }, "whole_pages": { "type": "boolean" }, "pages": pages("to search or mark (default: all); mutually exclusive with page, and not valid with rect"), "overlay": { "type": "string" }, @@ -692,13 +721,13 @@ pub fn tools() -> Vec { }), &["doc"], )), - t("content_list", "List added content", "Text and images added with page_add_text/page_add_image (or Edit a PDF ▸ Add content), per page with a 1-based index, rect (points from the top-left of the page), and text style.") + t("content_list", "List added content", "Text and images added with page_add_text/page_add_image (or Edit a PDF ▸ Add content), per page with a 1-based index, rect (points from the top-left of the page), and text style; text painted in gray or CMYK also has gray (its level) or cmyk ([c, m, y, k]).") .ro() .with(schema(json!({ "doc": doc() }), &["doc"])), t( "page_add_text", "Add text to a page", - "Add text as page content (not a comment). Place it with at [x, y] (top-left, points from the top-left of the displayed page) and width (wrap width, default 200), or rect. Newlines start new lines; long lines wrap. Style: font helvetica/times/courier, size, bold, italic, color (#RRGGBB or a name), align left/center/right, char_spacing (points after each character). Text must be Western European (WinAnsi) characters, or Arabic, Hebrew or Thai when the build has their craft-fonts faces (drawn right to left where the text is); others are refused. It stays editable with content_update. Undoable.", + "Add text as page content (not a comment). Place it with at [x, y] (top-left, points from the top-left of the displayed page) and width (wrap width, default 200), or rect. Newlines start new lines; long lines wrap. Style: font helvetica/times/courier, size, bold, italic, color (#RRGGBB or a name, painted in RGB) or, for print, gray (0 black to 1 white, painted in DeviceGray) or cmyk ([c, m, y, k], each 0 to 1, painted in DeviceCMYK; [0, 0, 0, 1] is 100 K black), one of the three, align left/center/right, char_spacing (points after each character). Text must be Western European (WinAnsi) characters, or Arabic, Hebrew or Thai when the build has their craft-fonts faces (drawn right to left where the text is); others are refused. It stays editable with content_update. Undoable.", ) .cmd("edit.text") .with(schema( @@ -709,6 +738,8 @@ pub fn tools() -> Vec { "rect": { "type": "array", "items": { "type": "number" }, "minItems": 4, "maxItems": 4 }, "font": { "type": "string", "enum": ["helvetica", "times", "courier"] }, "size": { "type": "number", "minimum": 1, "maximum": 500 }, "bold": { "type": "boolean" }, "italic": { "type": "boolean" }, "color": { "type": "string" }, + "gray": { "type": "number", "minimum": 0, "maximum": 1, "description": "DeviceGray level, 0 black to 1 white (instead of color)." }, + "cmyk": { "type": "array", "items": { "type": "number", "minimum": 0, "maximum": 1 }, "minItems": 4, "maxItems": 4, "description": "DeviceCMYK [c, m, y, k], each 0 to 1 (instead of color); [0, 0, 0, 1] is 100 K black." }, "align": { "type": "string", "enum": ["left", "center", "right", "justify"] }, "aligns": { "type": "array", "maxItems": 4096, "items": { "type": "string", "enum": ["left", "center", "right", "justify", "inherit"] }, "description": "Each paragraph's (line's) own alignment, by index; inherit (or legacy null) follows align." }, "char_spacing": { "type": "number", "minimum": -500, "maximum": 500, "description": "Points after each character." }, @@ -725,13 +756,15 @@ pub fn tools() -> Vec { json!({ "doc": doc(), "page": { "type": "integer", "minimum": 1 }, "path": { "type": "string" }, "rect": { "type": "array", "items": { "type": "number" }, "minItems": 4, "maxItems": 4 } }), &["doc", "page", "path"], )), - t("content_update", "Edit added content", "Move/resize (rect), retype (text) or restyle (font, size, bold, italic, color, align, char_spacing in points) an added item (page, index from content_list). Images: rotate (degrees, multiple of 90, counter-clockwise), flip_h / flip_v (toggle), crop [left, bottom, right, top] as fractions trimmed, image (a file that replaces the picture). Undoable.") + t("content_update", "Edit added content", "Move/resize (rect), retype (text) or restyle (font, size, bold, italic, color or gray or cmyk as page_add_text takes them, align, char_spacing in points) an added item (page, index from content_list). Images: rotate (degrees, multiple of 90, counter-clockwise), flip_h / flip_v (toggle), crop [left, bottom, right, top] as fractions trimmed, image (a file that replaces the picture). Undoable.") .with(schema( json!({ "doc": doc(), "page": { "type": "integer", "minimum": 1 }, "index": { "type": "integer", "minimum": 1 }, "rect": { "type": "array", "items": { "type": "number" }, "minItems": 4, "maxItems": 4 }, "text": { "type": "string" }, "font": { "type": "string", "enum": ["helvetica", "times", "courier"] }, "size": { "type": "number", "minimum": 1, "maximum": 500 }, "bold": { "type": "boolean" }, "italic": { "type": "boolean" }, "color": { "type": "string" }, + "gray": { "type": "number", "minimum": 0, "maximum": 1, "description": "DeviceGray level, 0 black to 1 white (instead of color)." }, + "cmyk": { "type": "array", "items": { "type": "number", "minimum": 0, "maximum": 1 }, "minItems": 4, "maxItems": 4, "description": "DeviceCMYK [c, m, y, k], each 0 to 1 (instead of color); [0, 0, 0, 1] is 100 K black." }, "align": { "type": "string", "enum": ["left", "center", "right", "justify"] }, "aligns": { "type": "array", "maxItems": 4096, "items": { "type": "string", "enum": ["left", "center", "right", "justify", "inherit"] }, "description": "Each paragraph's (line's) own alignment, by index; inherit (or legacy null) follows align." }, "char_spacing": { "type": "number", "minimum": -500, "maximum": 500, "description": "Points after each character." }, @@ -846,9 +879,13 @@ pub fn tools() -> Vec { "icon": { "type": "string", "description": "note: Comment, Note, Help, Insert, Key, NewParagraph, Paragraph (the standard names), Check, Circle, Cross, CrossHairs, Star, RightArrow, UpArrow; attachment: PushPin, Paperclip, Graph, Tag." }, "color": color(), "fill": color(), - "opacity": { "type": "number", "minimum": 0, "maximum": 1 }, + "opacity": { "type": "number", "minimum": 0, "maximum": 1, "description": "The whole comment's opacity (its line or border's, where its fill or text has its own)." }, + "fill_opacity": { "type": "number", "minimum": 0, "maximum": 1, "description": "The fill's own opacity: rectangle, oval, polygon, cloud, text box, typewriter text or callout." }, + "text_opacity": { "type": "number", "minimum": 0, "maximum": 1, "description": "The text's own opacity: text box, typewriter text or callout." }, "width": { "type": "number", "minimum": 0, "description": "Line width in points." }, + "border_shape": { "type": "string", "enum": ["rectangle", "oval", "circle"], "description": "A text box's or typewriter text's border shape: an oval or a circle goes around the text box." }, "endings": { "type": "array", "items": { "type": "string", "enum": ["None", "Square", "Circle", "Diamond", "OpenArrow", "ClosedArrow", "Butt", "ROpenArrow", "RClosedArrow", "Slash"] }, "minItems": 1, "maxItems": 2, "description": "Line endings. Two names (start, end) for a line, arrow or polyline; one name for a callout." }, + "ortho": { "type": "boolean", "description": "line/arrow/polygon/cloud/polyline: hold each end or corner level or plumb with the one before, whichever is nearer (Shift while drawing)." }, "font_size": { "type": "number", "exclusiveMinimum": 0 }, }), &["doc", "page", "type"], @@ -861,7 +898,7 @@ pub fn tools() -> Vec { comment_ref(json!({ "status": { "type": "string", "enum": ["none", "accepted", "rejected", "cancelled", "completed"] }, "author": { "type": "string" } })), &["doc", "status"], )), - t("sign_list", "List and validate signatures", "Every signature field with its validation: status (valid, unknown = intact but the signer isn't trusted, invalid, unsigned), signer and certificate, date, reason, location, certification level, page and rect, the revision it covers and changes made after signing (none, allowed, disallowed), with Acrobat-style explanations.") + t("sign_list", "List and validate signatures", "Every signature field with its validation: status (valid, unknown = intact but the signer isn't trusted, invalid, unsigned), signer and certificate, date, reason, location, certification level, page and rect, whether PdfCraft draws that state into the signature's own appearance as displayed (verdict_shown; never written to the file), the revision it covers and changes made after signing (none, allowed, disallowed), with Acrobat-style explanations.") .ro() .with(schema(json!({ "doc": doc() }), &["doc"])), t("sign_id_create", "Create a digital ID", "Create a self-signed digital ID and save it as a password-protected .p12 file (Acrobat: Configure a new digital ID ▸ Create a new digital ID ▸ Save to file). Default key: 2048-bit RSA, valid 5 years.").with(schema( @@ -979,13 +1016,17 @@ pub fn tools() -> Vec { json!({ "doc": doc(), "sort": { "type": "string", "enum": ["page", "author", "date", "type"] }, "out": save_out, "open": open }), &["doc"], )), - t("comment_edit", "Edit a comment", "Change a comment's text, colour, opacity, line width, font size (text box/typewriter/callout), fill (rectangle/oval/polygon/text box/callout; \"none\" removes it), rectangle (rectangle/oval/text box/stamp), position (`move` [dx, dy] in points) or shape (`points`: a line's two ends, or the corners of connected lines, a polygon or a cloud). Stamps keep their original appearance when resized. One undo step.").with(schema( + t("comment_edit", "Edit a comment", "Change a comment's text, colour, opacity (the whole comment's, or its fill's and text's own), line width, font size (text box/typewriter/callout), fill (rectangle/oval/polygon/text box/callout; \"none\" removes it), border colour (`border_color`, text box/typewriter/callout; \"text\" gives it the text's colour again), rectangle (rectangle/oval/text box/stamp), position (`move` [dx, dy] in points) or shape (`points`: a line's two ends, or the corners of connected lines, a polygon or a cloud). Stamps keep their original appearance when resized. One undo step.").with(schema( comment_ref(json!({ "contents": { "type": "string" }, "color": color(), - "opacity": { "type": "number", "minimum": 0, "maximum": 1 }, + "opacity": { "type": "number", "minimum": 0, "maximum": 1, "description": "The whole comment's opacity: its fill and text drop opacities of their own." }, + "fill_opacity": { "type": "number", "minimum": 0, "maximum": 1, "description": "The fill's own opacity (rectangle, oval, polygon, cloud, text box, typewriter text, callout); the line or border keeps the comment's." }, + "text_opacity": { "type": "number", "minimum": 0, "maximum": 1, "description": "The text's own opacity (text box, typewriter text, callout)." }, "width": { "type": "number", "minimum": 0 }, "fill": { "type": "string", "description": "Interior colour of a rectangle, oval, polygon, text box or callout: #RRGGBB, a colour name, or \"none\" for no fill." }, + "border_color": { "type": "string", "description": "A text box's, typewriter text's or callout's border colour: #RRGGBB, a colour name, or \"text\" for the text's colour." }, + "border_shape": { "type": "string", "enum": ["rectangle", "oval", "circle"], "description": "A text box's or typewriter text's border shape: an oval or a circle goes around the text, which keeps its place." }, "font_size": { "type": "number", "minimum": 1, "maximum": 400, "description": "Font size in points of a text box, typewriter text or callout; the box grows to hold the text." }, "rect": { "type": "array", "items": { "type": "number" }, "minItems": 4, "maxItems": 4 }, "move": point(), @@ -996,6 +1037,25 @@ pub fn tools() -> Vec { t("comment_image_preview", "Preview image signature layers", "Return a PNG of the page without the selected image signature/initials (layer=background, default), or its embedded image with alpha (layer=image). Includes the displayed rectangle, document rotation, image_rotation (how far clockwise the image is shown turned) and annotation opacity. Cache these layers for live placement/resizing; commit once with comment_edit. Does not change the document or undo history.") .ro().with(schema(comment_ref(json!({ "layer": { "type": "string", "enum": ["background", "image"], "default": "background" }, "dpi": { "type": "number", "minimum": 1, "maximum": 600, "default": 96 } })), &["doc"])), t("comment_delete", "Delete a comment", "Delete a comment with its pop-up and replies, or one reply (its id, or page and index, from comment_list) with its pop-up and the replies to it; the comment and its other replies stay. Undoable.").destructive().with(schema(comment_ref(json!({})), &["doc"])), + t( + "comments_copy", + "Copy comments", + "The XFDF of these comments, each with its replies: what Copy puts on the clipboard. Paste it into this or another document with comments_paste. `comments`: [[page, index], …], 1-based as comment_list reports them.", + ) + .ro() + .with(schema( + json!({ + "doc": doc(), + "comments": { "type": "array", "items": { "type": "array", "items": { "type": "integer", "minimum": 1 }, "minItems": 2, "maxItems": 2 }, "minItems": 1 } + }), + &["doc", "comments"], + )), + t( + "comments_paste", + "Paste comments", + "Add the comments of an XFDF text (from comments_copy) to `page` as new comments: copies under names of their own, so nothing in the document is replaced and pasting twice gives two sets; replies keep their copied parent. `at` [x, y] (points, origin at the top-left of the displayed page, y down, as comment_add takes them) puts the centre of the copies' bounding box there; without it they keep their positions. Undoable.", + ) + .with(schema(json!({ "doc": doc(), "page": { "type": "integer", "minimum": 1 }, "xfdf": { "type": "string" }, "at": point() }), &["doc", "page", "xfdf"])), t( "doc_protect", "Protect with passwords", @@ -1232,7 +1292,7 @@ pub fn tools() -> Vec { "property": { "type": "string", "enum": ["type", "title", "actual_text", "alternate_text", "language", "summary", "scope"] }, "value": { "type": "string" }, }), &["doc", "object", "generation", "property"])), - t("accessibility_mark_tag_artifact", "Mark tag content as artifact", "Mark a reachable leaf structure tag's direct marked content as an artifact and remove the tag from the reading structure. Use object and generation from accessibility_tags. Tags with child structure elements, no direct marked content, or content not found on its page are rejected. Undoable.") + t("accessibility_mark_tag_artifact", "Mark tag content as artifact", "Mark a reachable leaf structure tag's direct marked content as an artifact and remove the tag from the reading structure. Use object and generation from accessibility_tags. Tags with child structure elements, no direct marked content, content not found on its page, or content that a damaged or undecodable content stream may hide or change are rejected. Undoable.") .with(schema(json!({ "doc": doc(), "object": { "type": "integer", "minimum": 1 }, "generation": { "type": "integer", "minimum": 0, "maximum": 65535 }, @@ -1267,7 +1327,7 @@ pub fn tools() -> Vec { 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. 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.") + 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 inferred tables, bordered only along the grid lines the page draws, 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" }, "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.") @@ -1326,31 +1386,79 @@ pub fn tools() -> Vec { )), t("js_enabled", "JavaScript on or off", "Preferences ▸ JavaScript ▸ Enable Acrobat JavaScript: set it with `enabled`, or read it. With JavaScript off, field scripts other than Acrobat's AF calls don't run.") .with(schema(json!({ "enabled": { "type": "boolean" } }), &[])), - t("ocr_recognize", "Recognize text (OCR)", "Scan & OCR ▸ Recognize text: render pages, read the words in them and add them as invisible text over the page image, so scanned pages become searchable and selectable (a searchable image; the image is not changed). Pages that already have text are skipped unless skip_text_pages is false; then pictures on those pages are read too, and recognised words that the page's own text already has (an earlier OCR layer included) are left out and counted as already_on_page. Returns each page's recognised text (left out when the document's security doesn't allow copying), word count or why it was skipped. Needs the OCR models (ocr_status). Undoable as one step.") + t("ocr_recognize", "Recognize text (OCR)", "Scan & OCR ▸ Recognize text: render pages, read the words in them and add them as invisible text over the page image, so scanned pages become searchable and selectable (a searchable image; the image is not changed). Pages that already have text are skipped unless skip_text_pages or force_ocr say otherwise; words overlapping existing text are omitted and counted as already_on_page. With output_mode \"editable\" nothing is applied: a NEW document of visible text at the recognised boxes is written to out (which must not be the source; empty pages stay blank). engine and strategy choose the readers (an engine that cannot run is an error named up front); the four preprocessing flags clean the raster first. region reads just that part of one page ([x0, y0, x1, y1] in points from the top-left of the displayed page). Returns each page's recognised text, word count or why it was skipped. Needs the engines (ocr_status). Searchable output is undoable as one step.") .cmd("ocr.recognize") .with(schema( json!({ "doc": doc(), "pages": pages("to recognise (default: all)"), "dpi": { "type": "number", "minimum": 72, "maximum": 600, "description": "Resolution pages are read at (default 300; a scanned page is read at most at its own resolution)." }, - "language": { "type": "string", "enum": ["en"], "description": "Document language (default en)." }, - "skip_text_pages": { "type": "boolean", "description": "Leave pages that already contain text alone (default true). false also reads pictures on such pages, without adding their text again." }, + "language": { "type": "string", "enum": language_enum(), "description": "Document language (default en)." }, + "engine": { "type": "string", "enum": ["auto", "ocrs", "tesseract"], "description": "Which engine reads the pages (default ocrs). auto: ocrs first and tesseract as the second engine, combined by strategy (only the engines that can run take part)." }, + "strategy": { "type": "string", "enum": ["primary", "confidence", "rover"], "description": "How two engines' readings combine: primary = the first engine alone; confidence = the second engine joins when the first reading's mean confidence is under 70 or unknown; rover = both always read, merged. Default: confidence with engine auto, primary otherwise." }, + "output_mode": { "type": "string", "enum": ["searchable", "editable"], "description": "searchable (default): invisible text over the pages of the open document. editable: a NEW _ocr-style file of visible text written to out; the source is not touched." }, + "out": { "type": "string", "description": "Where the editable output is written (required with output_mode editable; a new file: never the source path, never an existing file)." }, + "region": { "type": "array", "items": { "type": "number" }, "minItems": 4, "maxItems": 4, "description": "[x0, y0, x1, y1] in points from the top-left of the displayed page: read only that part. Needs exactly one page." }, + "skip_text_pages": { "type": "boolean", "description": "Leave pages that already contain text alone (default true)." }, + "skip_text_files": { "type": "boolean", "description": "Batch: leave whole files that already contain text alone (they come back skipped, not read)." }, + "force_ocr": { "type": "boolean", "description": "Read pages and files even when the skip options would leave them alone (default false)." }, + "auto_rotate": { "type": "boolean", "description": "Turn pages scanned sideways or upside down upright before reading (default false)." }, + "deskew": { "type": "boolean", "description": "Straighten skewed text lines before reading (default false)." }, + "denoise": { "type": "boolean", "description": "A 3×3 median filter against scan speckle (default false)." }, + "binarize": { "type": "boolean", "description": "Sauvola binarization: ink to black, paper to white (default false)." }, }), &["doc"], )), - t("ocr_recognize_files", "Recognize text in multiple files", "Scan & OCR ▸ Recognize text ▸ In multiple files: read every page of each PDF in paths and write the searchable result into folder under the same name (pages that already have text are left alone unless skip_text_pages is false, as in ocr_recognize). Two inputs that would write the same output file are refused before anything is read or written. Returns, per file, the output path, word count and skipped pages, or the error.") + t("ocr_words", "Words of a recognition (for review)", "The words a recognition finds, for inspection without the GUI: per page, each word's text, its box ([x, y, w, h] in points from the top-left of the displayed page), its confidence and band (high >= 90, medium 70–89, low < 70), which engine read it, and whether it is a suspect (low band). suspects counts the words a reviewer should look at first. Changes nothing on the document. retain_review returns a session-local handle for ocr_review_apply (one per document, at most eight; a new retained recognition replaces the old one). Needs the engines (ocr_status).") + .ro() + .with(schema( + json!({ + "doc": doc(), + "retain_review": { "type": "boolean" }, + "region": { "type": "array", "items": { "type": "number" }, "minItems": 4, "maxItems": 4 }, + "pages": pages("to read (default: all)"), + "dpi": { "type": "number", "minimum": 72, "maximum": 600 }, + "language": { "type": "string", "enum": language_enum() }, + "engine": { "type": "string", "enum": ["auto", "ocrs", "tesseract"] }, + "strategy": { "type": "string", "enum": ["primary", "confidence", "rover"] }, + "auto_rotate": { "type": "boolean" }, + "deskew": { "type": "boolean" }, + "denoise": { "type": "boolean" }, + "binarize": { "type": "boolean" }, + "skip_text_pages": { "type": "boolean", "description": "Leave pages that already contain text alone (default true)." }, + "force_ocr": { "type": "boolean", "description": "Read pages even when the skip options would leave them alone (default false)." }, + }), + &["doc"], + )), + t("ocr_review_apply", "Apply or discard reviewed OCR words", "Accept corrected recognition from ocr_words retain_review. Corrections use 1-based page/word positions and text only; empty text removes a word, omitted words keep their original text and boxes. The stored document guard refuses stale, foreign or consumed reviews. Searchable output is one undoable step; editable requires out and writes a new document (out must not exist yet; the review is kept when it does). discard releases the review without applying it. Input is capped at 65536 words and 4 MiB, never truncated.") + .cmd("ocr.correct") + .with(schema(json!({ "doc": doc(), "review": { "type": "integer", "minimum": 1 }, "discard": { "type": "boolean" }, "output_mode": { "type": "string", "enum": ["searchable", "editable"] }, "out": { "type": "string" }, + "corrections": { "type": "array", "maxItems": 65536, "items": { "type": "object", "additionalProperties": false, "properties": { "page": { "type": "integer", "minimum": 1 }, "word": { "type": "integer", "minimum": 1 }, "text": { "type": "string" } }, "required": ["page", "word", "text"] } } }), &["doc", "review"])), + t("ocr_dictionary", "Read or update an OCR review dictionary", "Read or add/remove words in an OCR Verify dictionary file (one case-insensitive word per UTF-8 line). Choose its per-language ocr-dictionary-.txt path. Paths honor root; updates are atomic. Refuses invalid words, over 65536 entries or over 4 MiB. No document changes.") + .destructive() + .cmd("ocr.correct") + .with(schema(json!({ "path": { "type": "string" }, "add": { "type": "array", "maxItems": 65536, "items": { "type": "string" } }, "remove": { "type": "array", "maxItems": 65536, "items": { "type": "string" } } }), &["path"])), + t("ocr_recognize_files", "Recognize text in multiple files", "Scan & OCR ▸ Recognize text ▸ In multiple files: read every page of each PDF in paths and write the searchable result into folder under the same name. skip_text_files leaves whole files that already contain text alone (they are their own skipped bucket, nothing is written); skip_text_pages leaves single text pages alone; force_ocr reads regardless of both. Every output name is checked before the first page is read: two paths sharing a file name (from different folders) are refused, and a file of that name already in folder aborts the batch, with the names in the error. Each written file carries a low_confidence note when words at or under 60 confidence sit on it (1-based sorted pages). Returns, per file, the output path, word count, skipped pages or the error, plus recognized/words/skipped_files totals. Needs the engines (ocr_status).") .cmd("ocr.recognize_batch") .with(schema( json!({ "paths": { "type": "array", "items": { "type": "string" }, "minItems": 1 }, "folder": { "type": "string" }, "dpi": { "type": "number", "minimum": 72, "maximum": 600 }, - "language": { "type": "string", "enum": ["en"] }, - "skip_text_pages": { "type": "boolean", "description": "Leave pages that already contain text alone (default true); see ocr_recognize." }, + "language": { "type": "string", "enum": language_enum() }, + "engine": { "type": "string", "enum": ["auto", "ocrs", "tesseract"] }, + "strategy": { "type": "string", "enum": ["primary", "confidence", "rover"] }, + "skip_text_pages": { "type": "boolean", "description": "Leave pages that already contain text alone (default true)." }, + "skip_text_files": { "type": "boolean", "description": "Leave whole files that already contain text alone (default false)." }, + "force_ocr": { "type": "boolean", "description": "Read even where the skip options would leave things alone (default false)." }, + "auto_rotate": { "type": "boolean" }, + "deskew": { "type": "boolean" }, + "denoise": { "type": "boolean" }, + "binarize": { "type": "boolean" }, }), &["paths", "folder"], )), - t("ocr_status", "OCR status", "Whether text recognition is available (its models are installed: release packages include them; a source build fetches them with `cargo xtask models`; PDFCRAFT_MODELS overrides), where it looks for them, and the languages it reads.") + t("ocr_status", "OCR status", "Whether text recognition is available, where it looks for models (release packages include them; a source build fetches them with `cargo xtask models`; PDFCRAFT_MODELS overrides), its languages, and the engines: ocrs (built in, models) and tesseract (an installed program, with its path).") .ro() .cmd("ocr.recognize") .with(schema(json!({}), &[])), @@ -1371,7 +1479,7 @@ pub fn tools() -> Vec { t( "fill_sign_add", "Fill & Sign: type text or place a mark", - "Fill in a form that has no fields, as Acrobat's Fill & Sign does: type text (`text`, default 10 pt; `font_size` 4–300 pt; optional `color` as #RRGGBB for text/date, default black), place a check, cross, dot or line, today's date (in Preferences ▸ Date format, see fill_sign_date_format, or `format`; `font_size` also applies), or a signature or initials (either `text` drawn in a script font, or `path` to a local PNG/JPEG image up to 4 MiB and 32 megapixels, scaled down to 4 megapixels, preserving transparency; with `scan: true`, `path` is instead a photo of a signature on paper, within the same limits: the signature is found, and the paper, shadows and table around it are removed, with `sensitivity` 0–100, default 50, picking up fainter ink when higher). `at` [x, y] is in points from the top-left of the page: text's top-left, mark's centre, signature's left edge centred vertically. Image signatures fit within 150 pt wide and 32 pt tall (24 pt for initials). Creates movable, undoable annotations. Typed text the standard fonts can't draw is saved and drawn as `?` (`warnings` in the result says so); a typed signature neither the script font nor its fallback can draw is refused (pass `path` instead).", + "Fill in a form that has no fields, as Acrobat's Fill & Sign does: type text (`text`, default 10 pt; `font_size` 4–300 pt; optional `color` as #RRGGBB for text/date, default black; `border` 0–12 pt around it, default none, in its colour or `border_color`), place a check, cross, dot or line, today's date (in Preferences ▸ Date format, see fill_sign_date_format, or `format`; `font_size` also applies), or a signature or initials (either `text` drawn in a script font, or `path` to a local PNG/JPEG image up to 4 MiB and 32 megapixels, scaled down to 4 megapixels, preserving transparency; with `scan: true`, `path` is instead a photo of a signature on paper, within the same limits: the signature is found, and the paper, shadows and table around it are removed, with `sensitivity` 0–100, default 50, picking up fainter ink when higher). `at` [x, y] is in points from the top-left of the page: text's top-left, mark's centre, signature's left edge centred vertically. Image signatures fit within 150 pt wide and 32 pt tall (24 pt for initials). Creates movable, undoable annotations. Typed text the standard fonts can't draw is saved and drawn as `?` (`warnings` in the result says so); a typed signature neither the script font nor its fallback can draw is refused (pass `path` instead).", ) .cmd("sign.fill.text") .with(schema( @@ -1383,6 +1491,9 @@ pub fn tools() -> Vec { "text": { "type": "string", "minLength": 1 }, "font_size": { "type": "number", "minimum": 4, "maximum": 300, "description": "For type text or date (default 10 pt)." }, "color": color(), + "border": { "type": "number", "minimum": 0, "maximum": 12, "description": "For type text or date: a border around it in points, in the text's colour (default 0, none)." }, + "border_color": { "type": "string", "description": "With border: its own colour, #RRGGBB or a colour name." }, + "border_shape": { "type": "string", "enum": ["rectangle", "oval", "circle"], "description": "With border, for type text or date: the border's shape (default rectangle); an oval or a circle goes around the text." }, "path": { "type": "string", "description": "PNG or JPEG for signature/initials; pass either path or text." }, "scan": { "type": "boolean", "description": "With path: scan a photo of a signature on paper (default false)." }, "sensitivity": { "type": "integer", "minimum": 0, "maximum": 100, "description": "With scan: how faint ink may be, 0–100 (default 50)." }, @@ -1451,14 +1562,14 @@ pub fn tools() -> Vec { .ro() .cmd("edit.edit_text") .with(schema(json!({ "doc": doc(), "page": { "type": "integer", "minimum": 1 } }), &["doc", "page"])), - t("image_edit", "Edit an image", "Change one of a page's images (number from page_images): action move (rect: new full placement box in top-left-origin points, based on page_images.rect), crop (rect: the part to keep, top-left-origin points; the pixels stay in place and page_images.visible_rect shows the result; a later move carries the crop along), remove_crop (remove a crop created by PdfCraft while preserving clipping paths from the original document), rotate (quarters clockwise, default 1), rotate_by (degrees: any angle clockwise about the visible centre; the box in page_images then becomes the turned image's bounding box), transform (matrix: 6 numbers [a, b, c, d, e, f] in top-left-origin points, applied after the current placement so a point (x, y) of the image moves to (a·x + c·y + e, b·x + d·y + f); finite, with a·d − b·c not 0; the box in page_images becomes the transformed image's bounding box), flip_horizontal (reflect left/right on the displayed page), flip_vertical (reflect top/bottom on the displayed page; both flip actions follow the page rotation), replace (path: an image file, drawn in the same place), delete, or arrange: bring_to_front, send_to_back, bring_forward, send_backward (reorder stacking order among content on the page; errors when the image is already at the requested limit; arranging an added image converts it into an ordinary page image). Undoable. The selected image crop transforms with its pixels, isolating shared path scopes while retaining neighboring painting. Text-outline clips return a clear error. Rotation/flip use the visible centre. Form artwork supports move/resize/rotate/flip/delete as a group; replace and image_save only support raster images.") + t("image_edit", "Edit an image", "Change one of a page's images (number from page_images): action move (rect: new full placement box in top-left-origin points, based on page_images.rect), crop (rect: the part to keep, top-left-origin points; the pixels stay in place and page_images.visible_rect shows the result; a later move carries the crop along), remove_crop (remove a crop created by PdfCraft while preserving clipping paths from the original document), rotate (quarters clockwise, default 1), rotate_by (degrees: any angle clockwise about the visible centre; the box in page_images then becomes the turned image's bounding box), transform (matrix: 6 numbers [a, b, c, d, e, f] in top-left-origin points, applied after the current placement so a point (x, y) of the image moves to (a·x + c·y + e, b·x + d·y + f); finite, with a·d − b·c not 0; the box in page_images becomes the transformed image's bounding box), flip_horizontal (reflect left/right on the displayed page), flip_vertical (reflect top/bottom on the displayed page; both flip actions follow the page rotation), replace (path: an image file, drawn in the same place), delete, ungroup (Form artwork only: its content is drawn in place, so its text becomes editable with text_paragraphs/text_edit and its pictures separate; refused for knockout groups and for transparency groups that blend inside, are drawn translucent or blend in a colour space other than the page's, which would composite differently, and for forms whose /DefaultGray, /DefaultRGB or /DefaultCMYK the page doesn't share, which would stop remapping their colours), or arrange: bring_to_front, send_to_back, bring_forward, send_backward (reorder stacking order among content on the page; errors when the image is already at the requested limit; arranging an added image converts it into an ordinary page image). Undoable. The selected image crop transforms with its pixels, isolating shared path scopes while retaining neighboring painting. Text-outline clips return a clear error. Rotation/flip use the visible centre. Form artwork supports move/resize/rotate/flip/delete as a group; replace and image_save only support raster images.") .cmd("edit.edit_text") .with(schema( json!({ "doc": doc(), "page": { "type": "integer", "minimum": 1 }, "image": { "type": "integer", "minimum": 1 }, - "action": { "type": "string", "enum": ["move", "crop", "rotate", "rotate_by", "transform", "flip_horizontal", "flip_vertical", "replace", "delete", "bring_to_front", "send_to_back", "bring_forward", "send_backward", "remove_crop"] }, + "action": { "type": "string", "enum": ["move", "crop", "rotate", "rotate_by", "transform", "flip_horizontal", "flip_vertical", "replace", "delete", "bring_to_front", "send_to_back", "bring_forward", "send_backward", "remove_crop", "ungroup"] }, "rect": { "type": "array", "items": { "type": "number" }, "minItems": 4, "maxItems": 4 }, "quarters": { "type": "integer" }, "degrees": { "type": "number" }, @@ -1524,7 +1635,7 @@ pub fn tools() -> Vec { .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, 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.") + 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. target_bytes (optional): if the copy is larger, retry with up to 5 progressively stronger image settings (downsample to at most 110, 96, 72, 54, 36 ppi, applied to colour and grey images; images set to JPEG also get JPEG quality at most 45, 35, 28, 20, 12, while zip and retain images keep their encoding and only get the lower ppi) and stop at the first copy that fits; reports target_reached, attempts and target_settings, and writes the smallest copy with target_reached false when none fits. Without it nothing changes. The open document is unchanged.") .cmd("optimize.advanced") .with(schema( json!({ @@ -1536,6 +1647,7 @@ pub fn tools() -> Vec { "color": { "type": "object" }, "gray": { "type": "object" }, "mono": { "type": "object" }, + "target_bytes": { "type": "integer", "minimum": 1 }, "discard_thumbnails": { "type": "boolean" }, "discard_alternate_images": { "type": "boolean" }, "discard_tags": { "type": "boolean" }, diff --git a/crates/automation/tests/it/action_failures.rs b/crates/automation/tests/it/action_failures.rs new file mode 100644 index 0000000000..b487103a21 --- /dev/null +++ b/crates/automation/tests/it/action_failures.rs @@ -0,0 +1,66 @@ +//! A step that fails fails its file: the file is reported with an error and nothing is written +//! for it. A step that finds nothing to do is still not a failure. + +use std::sync::Arc; + +use pdfcraft_automation::{Automation, Content}; +use pdfcraft_engine::Session; +use pdfcraft_engine::actions::{Action, Step, run_on}; +use serde_json::json; + +fn pdf() -> Vec { + Session::new().create_from_text("Original", "Original text").unwrap().as_ref().clone() +} + +fn one_step(step: Step) -> Action { + Action { name: "Custom".into(), description: String::new(), steps: vec![step], builtin: false } +} + +/// The standard fonts can't draw the character, so the watermark step fails and no file is produced. +#[test] +fn failing_watermark_step_fails_the_file_and_publishes_nothing() { + let r = run_on(&one_step(Step::AddWatermark("中".into())), "one.pdf", Arc::new(pdf()), |_, _| {}); + assert!(r.is_err(), "a failed step must fail its file: {r:?}"); +} + +/// A comment step on a document with no comments has nothing to do, which is not a failure. +#[test] +fn nothing_to_do_step_still_succeeds() { + let r = run_on(&one_step(Step::FlattenComments), "one.pdf", Arc::new(pdf()), |_, _| {}); + assert!(r.is_ok(), "a step with nothing to do is not a failure: {r:?}"); +} + +/// Through the tool: the failing file gets an error entry and no output, and the folder stays empty. +#[test] +fn action_run_marks_the_failing_file_as_error_without_output() { + let dir = tempfile::tempdir().unwrap(); + let input = dir.path().join("in"); + std::fs::create_dir_all(&input).unwrap(); + let in_file = input.join("one.pdf"); + std::fs::write(&in_file, pdf()).unwrap(); + let out = dir.path().join("out"); + let mut auto = Automation::new().with_root(dir.path()).unwrap(); + let reply = auto.call( + "action_run", + &json!({ + "paths": [in_file.to_string_lossy()], + "folder": out.to_string_lossy(), + "steps": [{ "step": "add_watermark", "arg": "中" }], + }), + ); + let report = match reply.unwrap().remove(0) { + Content::Json(value) => value, + other => panic!("expected a report: {other:?}"), + }; + let entry = &report["files"][0]; + assert!(entry["error"].is_string(), "{report}"); + assert!(entry.get("output").is_none(), "{report}"); + assert_eq!(std::fs::read_dir(&out).unwrap().count(), 0, "nothing is published for a failed file"); +} + +/// A removal step with nothing to remove keeps its existing note and succeeds. +#[test] +fn removal_step_with_nothing_to_remove_still_succeeds() { + let r = run_on(&one_step(Step::RemoveHiddenInformation), "one.pdf", Arc::new(pdf()), |_, _| {}); + assert!(r.is_ok(), "nothing to remove is not a failure: {r:?}"); +} diff --git a/crates/automation/tests/it/automation.rs b/crates/automation/tests/it/automation.rs index 05f380dff1..98055ba1b3 100644 --- a/crates/automation/tests/it/automation.rs +++ b/crates/automation/tests/it/automation.rs @@ -843,10 +843,11 @@ fn arabic_ligature_actual_text_is_one_editable_word_through_save_reopen() { } /// Each of these writes to its required `path` and replaces an existing file there, so the MCP -/// annotations must not tell clients the call is read-only or harmless (#130). +/// annotations must not tell clients the call is read-only or harmless (#130). The OCR +/// dictionary's updates rewrite the file in place (lower-cased and sorted), so it counts too. #[test] fn file_writing_tools_are_not_read_only() { - for name in ["doc_export_data", "accessibility_report", "image_save"] { + for name in ["doc_export_data", "accessibility_report", "image_save", "ocr_dictionary"] { let t = tools().into_iter().find(|t| t.name == name).unwrap(); assert!(!t.read_only, "{name} writes a file but advertises read-only"); assert!(t.destructive, "{name} overwrites its path but advertises non-destructive"); @@ -1715,6 +1716,25 @@ fn mcp_default_lists_every_tool_and_has_no_meta_tools() { assert_eq!(rpc(&mut s, 3, "tools/call", json!({ "name": "tool_search" }))["error"]["code"], -32602); } +#[cfg(feature = "mcp")] +#[test] +/// `tools/list` advertises exactly the Search & Redact patterns the registry supports, in `pattern` +/// and by name in the description, so a schema-obeying client can select every one of them. +fn the_advertised_redact_mark_schema_offers_every_pattern() { + use pdfcraft_engine::REDACT_PATTERNS; + let registry: Vec<&str> = REDACT_PATTERNS.iter().map(|p| p.id()).collect(); + let mut s = McpServer::new(Automation::new()); + let list = rpc(&mut s, 1, "tools/list", json!({})); + let mark = list["result"]["tools"].as_array().unwrap().iter().find(|t| t["name"] == "redact_mark").expect("redact_mark is listed"); + let advertised: Vec<&str> = + mark["inputSchema"]["properties"]["pattern"]["enum"].as_array().unwrap().iter().map(|v| v.as_str().unwrap()).collect(); + assert_eq!(advertised, registry, "the advertised pattern enum must be the registry's ids"); + let description = mark["description"].as_str().unwrap(); + for id in ®istry { + assert!(description.contains(id), "the description must name {id}: {description}"); + } +} + #[cfg(feature = "mcp")] #[test] fn mcp_compact_lists_the_core_tools_and_two_meta_tools() { @@ -2135,6 +2155,104 @@ fn numbering_pages_through_tools() { assert!(matches!(a.call("page_number", &json!({ "doc": doc, "from": 1, "to": 1, "style": "klingon" })), Err(ToolError::InvalidArgs(_)))); } +/// Typed text and text boxes take an oval or a circle for their border through the tools; +/// comment_list reports it (a rectangle is not reported). Only typed text, dates and text boxes +/// have one, and only the three shapes. +#[test] +fn text_borders_take_an_oval_or_a_circle_through_the_tools() { + let dir = workdir("border-shape"); + let mut a = auto(&dir); + let doc = ok(&mut a, "doc_open", json!({ "path": "a.pdf" }))["doc"].as_u64().unwrap(); + ok( + &mut a, + "fill_sign_add", + json!({ "doc": doc, "page": 1, "type": "text", "at": [20, 40], "text": "12", "border": 1, "border_shape": "circle" }), + ); + ok( + &mut a, + "comment_add", + json!({ "doc": doc, "page": 1, "type": "textbox", "rect": [10, 200, 190, 240], "contents": "Hello", "width": 1, "border_shape": "Oval" }), + ); + let list = |a: &mut Automation| ok(a, "comment_list", json!({ "doc": doc, "page": 1 }))["comments"].as_array().unwrap().clone(); + let shapes: Vec = list(&mut a).iter().map(|c| c["border_shape"].clone()).collect(); + assert_eq!(shapes, [json!("circle"), json!("oval")]); + let typed = list(&mut a)[0].clone(); + // Snug around "12": the box no wider than the text needs, the circle as wide as that box. + let r: Vec = typed["rect"].as_array().unwrap().iter().map(|v| v.as_f64().unwrap()).collect(); + let w = pdfcraft_engine::annot_text::text_width("12", 10.0) + 10.0; + assert!((r[2] - r[0] - w).abs() < 0.05 && (r[3] - r[1] - w).abs() < 0.05, "{r:?}"); + ok(&mut a, "comment_edit", json!({ "doc": doc, "page": typed["page"], "index": typed["index"], "border_shape": "oval" })); + assert_eq!(list(&mut a)[0]["border_shape"], "oval"); + ok(&mut a, "comment_edit", json!({ "doc": doc, "page": typed["page"], "index": typed["index"], "border_shape": "rectangle" })); + assert!(list(&mut a)[0].get("border_shape").is_none(), "a rectangle is not reported"); + for (tool, args) in [ + ("fill_sign_add", json!({ "doc": doc, "page": 1, "type": "check", "at": [60, 60], "border_shape": "oval" })), + ("fill_sign_add", json!({ "doc": doc, "page": 1, "type": "text", "text": "7", "at": [60, 60], "border_shape": "circle" })), + ("comment_add", json!({ "doc": doc, "page": 1, "type": "rectangle", "rect": [80, 10, 120, 40], "border_shape": "oval" })), + ("comment_edit", json!({ "doc": doc, "page": typed["page"], "index": typed["index"], "border_shape": "star" })), + ] { + assert!(matches!(a.call(tool, &args), Err(ToolError::InvalidArgs(_))), "{args}"); + } + let callout = ok( + &mut a, + "comment_add", + json!({ "doc": doc, "page": 1, "type": "callout", "rect": [110, 100, 190, 140], "to": [40, 60], "contents": "Look" }), + ); + assert!(matches!( + a.call("comment_edit", &json!({ "doc": doc, "page": 1, "index": callout["comment"]["index"], "border_shape": "oval" })), + Err(ToolError::Failed(_)) + )); +} + +/// A rectangle's fill and a text box's text each take an opacity of their own through the tools +/// (the line or border keeps the comment's `opacity`); `opacity` sets the whole comment's again. +#[test] +fn comment_parts_take_opacities_of_their_own_through_the_tools() { + let dir = workdir("part-opacity"); + let mut a = auto(&dir); + let doc = ok(&mut a, "doc_open", json!({ "path": "a.pdf" }))["doc"].as_u64().unwrap(); + ok( + &mut a, + "comment_add", + json!({ "doc": doc, "page": 1, "type": "rectangle", "rect": [10, 10, 60, 40], "fill": "yellow", "fill_opacity": 0.25 }), + ); + ok( + &mut a, + "comment_add", + json!({ "doc": doc, "page": 1, "type": "textbox", "rect": [10, 200, 190, 240], "contents": "Hello", "fill": "#FFFF99", "width": 1, "fill_opacity": 0.2, "text_opacity": 1 }), + ); + let find = |a: &mut Automation, kind: &str| { + let list = ok(a, "comment_list", json!({ "doc": doc, "page": 1 })); + list["comments"].as_array().unwrap().iter().find(|c| c["type"] == kind).unwrap().clone() + }; + let rect = find(&mut a, "Square"); + assert_eq!((rect["opacity"].as_f64(), rect["fill_opacity"].as_f64(), rect.get("text_opacity")), (Some(1.0), Some(0.25), None)); + let tb = find(&mut a, "FreeText"); + assert_eq!((tb["opacity"].as_f64(), tb["fill_opacity"].as_f64(), tb["text_opacity"].as_f64()), (Some(1.0), Some(0.2), Some(1.0))); + // The fill changes, the text stays; an undo step. + ok(&mut a, "comment_edit", json!({ "doc": doc, "page": tb["page"], "index": tb["index"], "fill_opacity": 0.5 })); + let tb = find(&mut a, "FreeText"); + assert_eq!((tb["fill_opacity"].as_f64(), tb["text_opacity"].as_f64()), (Some(0.5), Some(1.0))); + assert_eq!(ok(&mut a, "edit_undo", json!({ "doc": doc }))["undone"], "Change comment properties"); + ok(&mut a, "edit_redo", json!({ "doc": doc })); + // The whole comment's opacity: everything at it again. + ok(&mut a, "comment_edit", json!({ "doc": doc, "page": rect["page"], "index": rect["index"], "opacity": 0.6 })); + let rect = find(&mut a, "Square"); + assert_eq!((rect["opacity"].as_f64(), rect["fill_opacity"].as_f64()), (Some(0.6), Some(0.6))); + // Only the parts a comment has, at 0–1. + for (tool, args) in [ + ("comment_add", json!({ "doc": doc, "page": 1, "type": "line", "from": [0, 0], "to": [50, 50], "fill_opacity": 0.5 })), + ("comment_add", json!({ "doc": doc, "page": 1, "type": "rectangle", "rect": [80, 10, 120, 40], "text_opacity": 0.5 })), + ("comment_edit", json!({ "doc": doc, "page": rect["page"], "index": rect["index"], "fill_opacity": 2 })), + ] { + assert!(matches!(a.call(tool, &args), Err(ToolError::InvalidArgs(_))), "{args}"); + } + assert!(matches!( + a.call("comment_edit", &json!({ "doc": doc, "page": rect["page"], "index": rect["index"], "text_opacity": 0.5 })), + Err(ToolError::Failed(_)) + )); +} + #[test] fn comments_through_tools() { let dir = workdir("comments"); @@ -2420,6 +2538,7 @@ fn protecting_through_tools() { // Copying wasn't allowed either (#568): no text or images come out, though search works. for (tool, args) in [ ("text_extract", json!({ "doc": re })), + ("text_extract", json!({ "doc": re, "format": "html" })), ("text_word_count", json!({ "doc": re })), ("text_paragraphs", json!({ "doc": re, "page": 1 })), ("doc_export_text", json!({ "doc": re, "path": "out.txt" })), @@ -2463,6 +2582,16 @@ fn copy_restricted_text_stays_in_the_document() { } let restyled = ok(&mut a, "text_edit", json!({ "doc": re, "page": 1, "paragraph": 1, "size": 30 })); assert!(!restyled.to_string().contains("Page"), "{restyled}"); + // A path that would carry the page's words OUT of the document — the editable output, or + // the review word list — is refused on a copy-restricted document (no engines needed). + match a.call("ocr_recognize", &json!({ "doc": re, "output_mode": "editable", "out": "copy.pdf" })) { + Err(ToolError::Failed(m)) => assert!(m.contains("don't allow copying"), "{m}"), + other => panic!("the editable output is refused: {other:?}"), + } + match a.call("ocr_words", &json!({ "doc": re })) { + Err(ToolError::Failed(m)) => assert!(m.contains("don't allow copying"), "{m}"), + other => panic!("ocr_words is refused: {other:?}"), + } if ok(&mut a, "ocr_status", json!({}))["available"] != true { eprintln!("skipped the OCR part: OCR models not installed"); return; @@ -3741,6 +3870,62 @@ fn enhance_camera_image_through_tools() { )); } +#[test] +fn enhance_scanned_file_cleans_the_scan_in_place_through_tools() { + let dir = workdir("enhance-scan"); + // A 300 × 400 grey scan: dull paper, a dark gutter at the left, text bars and a speck. + let img = image::GrayImage::from_fn(300, 400, |x, y| { + let light = 0.55 + 0.45 * (x as f32 / 60.0).min(1.0); + let ink = if ((60..360).contains(&y) && (y - 60) % 40 < 6 && (60..240).contains(&x)) || (x, y) == (150, 25) { 0.12 } else { 0.78 }; + image::Luma([(ink * light * 255.0) as u8]) + }); + img.save(dir.join("scan.jpg")).unwrap(); + let mut a = auto(&dir); + let scan = ok(&mut a, "doc_create", json!({ "from": "images", "paths": ["scan.jpg"] }))["doc"].as_u64().unwrap(); + ok(&mut a, "image_save", json!({ "doc": scan, "page": 1, "image": 1, "path": "before.jpg" })); + + let r = ok(&mut a, "page_enhance_scan", json!({ "doc": scan, "level": 100 })); + assert_eq!(r["undo"], "Enhance scanned file"); + assert_eq!((r["pages_cleaned"].clone(), r["images"].clone(), r["not_scanned"].clone()), (json!([1]), json!(1), json!([]))); + assert_eq!(r["skipped"], json!([])); + // In place: still one picture of the same size, still a JPEG, now with white paper. + let images = ok(&mut a, "page_images", json!({ "doc": scan, "page": 1 })); + assert_eq!((images["count"].clone(), images["images"][0]["pixels"].clone()), (json!(1), json!([300, 400]))); + let saved = ok(&mut a, "image_save", json!({ "doc": scan, "page": 1, "image": 1, "path": "after" })); + assert_eq!(saved["format"], "jpg"); + let (before, after) = (image::open(dir.join("before.jpg")).unwrap().to_luma8(), image::open(dir.join("after.jpg")).unwrap().to_luma8()); + for (x, y) in [(150, 40), (3, 40), (3, 380), (150, 25)] { + assert!( + before.get_pixel(x, y)[0] < 200 && after.get_pixel(x, y)[0] >= 230, + "({x}, {y}): {:?} → {:?}", + before.get_pixel(x, y), + after.get_pixel(x, y) + ); + } + assert!(after.get_pixel(150, 62)[0] <= 60, "a stroke stays dark"); + // Undo puts the scan back as it was. + ok(&mut a, "edit_undo", json!({ "doc": scan })); + ok(&mut a, "image_save", json!({ "doc": scan, "page": 1, "image": 1, "path": "undone.jpg" })); + assert_eq!(std::fs::read(dir.join("undone.jpg")).unwrap(), std::fs::read(dir.join("before.jpg")).unwrap()); + + // Switches: despeckle alone leaves everything but the speck. + let r = ok(&mut a, "page_enhance_scan", json!({ "doc": scan, "pages": [1], "level": 0, "despeckle": true, "edge_shadows": false })); + assert_eq!(r["images"], 1); + // A document of text pages has no scans: nothing changes, and it says so. + let text = ok(&mut a, "doc_open", json!({ "path": "a.pdf" }))["doc"].as_u64().unwrap(); + let r = ok(&mut a, "page_enhance_scan", json!({ "doc": text })); + assert_eq!((r["images"].clone(), r["not_scanned"].clone(), r["undo"].clone()), (json!(0), json!([1, 2, 3]), Value::Null)); + // Bad arguments are refused before anything changes. + for bad in [ + json!({ "doc": scan, "level": 101 }), + json!({ "doc": scan, "pages": [9] }), + json!({ "doc": scan, "despeckle": "yes" }), + json!({ "doc": scan, "pages": [] }), + ] { + assert!(matches!(a.call("page_enhance_scan", &bad), Err(ToolError::InvalidArgs(_))), "{bad}"); + } +} + #[test] fn enhance_camera_image_finds_the_edges_by_itself() { let dir = workdir("enhance-camera-auto"); @@ -3969,6 +4154,48 @@ fn fill_sign_text_and_date_colours_are_saved_and_validated() { } } +#[test] +fn fill_sign_text_border_is_saved_and_validated() { + let dir = workdir("fill-sign-text-border"); + let mut a = auto(&dir); + let doc = ok(&mut a, "doc_open", json!({ "path": "a.pdf" }))["doc"].as_u64().unwrap(); + ok(&mut a, "fill_sign_add", json!({ "doc": doc, "page": 1, "type": "text", "at": [20, 40], "text": "Plain" })); + ok(&mut a, "fill_sign_add", json!({ "doc": doc, "page": 1, "type": "text", "at": [20, 80], "text": "Plain", "border": 1.5 })); + let comments = ok(&mut a, "comment_list", json!({ "doc": doc })); + let width = |k: usize| { + let rect = comments["comments"][k]["rect"].as_array().unwrap(); + rect[2].as_f64().unwrap() - rect[0].as_f64().unwrap() + }; + assert!((width(1) - width(0) - 3.0).abs() < 1e-6, "1.5 pt on each side: {comments}"); + ok(&mut a, "doc_save", json!({ "doc": doc, "path": "framed.pdf" })); + let saved = std::fs::read(dir.join("framed.pdf")).unwrap(); + let pdf = pdfcraft_cos::Document::open(std::sync::Arc::new(saved)).unwrap(); + let page = pdfcraft_model::pages(&pdf).remove(0); + let annotations = pdf.resolve(page.dict.get(b"Annots").unwrap()); + let annotation = pdf.resolve(annotations.as_array().unwrap().get(1).unwrap()); + let bs = annotation.as_dict().unwrap().get(b"BS").unwrap().as_dict().unwrap().get(b"W").unwrap().as_f64().unwrap(); + assert_eq!(bs, 1.5, "saved annotation has the requested border"); + // Its own colour, then the text's again through comment_edit. + ok( + &mut a, + "fill_sign_add", + json!({ "doc": doc, "page": 1, "type": "text", "at": [20, 160], "text": "Red", "border": 1, "border_color": "#ff0000" }), + ); + let list = ok(&mut a, "comment_list", json!({ "doc": doc, "page": 1 })); + let red = list["comments"].as_array().unwrap().iter().find(|c| c["contents"] == "Red").unwrap()["index"].clone(); + ok(&mut a, "comment_edit", json!({ "doc": doc, "page": 1, "index": red, "border_color": "text" })); + assert!( + a.call("fill_sign_add", &json!({ "doc": doc, "page": 1, "type": "text", "at": [20, 200], "text": "No", "border_color": "red" })).is_err(), + "no border" + ); + for (kind, border) in [("text", -1.0), ("text", 13.0), ("check", 1.0)] { + assert!(matches!( + a.call("fill_sign_add", &json!({ "doc": doc, "page": 1, "type": kind, "at": [20, 120], "text": "No", "border": border })), + Err(ToolError::InvalidArgs(_)) + )); + } +} + #[test] fn image_signatures_through_tools_preserve_transparency_and_survive_save() { let dir = workdir("image-signatures"); @@ -4591,6 +4818,34 @@ fn redacting_through_tools() { assert!(matches!(a.call("redact_mark", &json!({ "doc": doc })), Err(ToolError::InvalidArgs(_)))); } +#[test] +fn redacting_with_a_caller_regex_through_tools() { + let dir = workdir("redact-regex"); + std::fs::write( + dir.join("ids.txt"), + "Ref 1 85 05 78 006 084 36 end\nRef 2 91 12 34 567 890 12 end\nCard 4539 1488 0343 6467 and 4539 1488 0343 6468", + ) + .unwrap(); + let mut a = auto(&dir); + let doc = ok(&mut a, "doc_create", json!({ "from": "text", "path": "ids.txt" }))["doc"].as_u64().unwrap(); + let bad = |a: &mut Automation, args: Value| matches!(a.call("redact_mark", &args), Err(ToolError::InvalidArgs(_))); + assert!(bad(&mut a, json!({ "doc": doc, "regex": "(unclosed" }))); + assert!(bad(&mut a, json!({ "doc": doc, "regex": "a*" }))); + assert!(bad(&mut a, json!({ "doc": doc, "regex": "x".repeat(2000) }))); + assert!(bad(&mut a, json!({ "doc": doc, "regex": "x", "pattern": "ssn" }))); + assert!(bad(&mut a, json!({ "doc": doc, "regex": "x", "validate": "crc" }))); + assert!(bad(&mut a, json!({ "doc": doc, "find": "x", "validate": "luhn" }))); + assert!(matches!(a.call("redact_mark", &json!({ "doc": doc, "regex": "Z{3}" })), Err(ToolError::Failed(_)))); + let r = ok(&mut a, "redact_mark", json!({ "doc": doc, "regex": r"\d \d\d \d\d \d\d \d{3} \d{3} \d\d" })); + assert_eq!(r["marked"].as_u64(), Some(2)); + let r = ok(&mut a, "redact_mark", json!({ "doc": doc, "regex": r"\d{4}( \d{4}){3}", "validate": "luhn" })); + assert_eq!(r["marked"].as_u64(), Some(1), "only the number with a valid checksum"); + ok(&mut a, "redact_apply", json!({ "doc": doc })); + let text = page_text(&mut a, doc)[0].clone(); + assert!(!text.contains("85 05") && !text.contains("91 12") && !text.contains("6467"), "{text}"); + assert!(text.contains("6468"), "{text}"); +} + #[test] /// Mark, apply and save remove the complete international number while retaining labels and controls. fn redacting_italian_international_slash_numbers_through_tools() { @@ -4613,6 +4868,35 @@ fn redacting_italian_international_slash_numbers_through_tools() { std::fs::remove_dir_all(dir).unwrap(); } +#[test] +/// A client obeying the advertised schema can select iban, and the mark made through the tool +/// covers the spaced number and nothing else. +fn redacting_an_iban_through_tools() { + let table = tools(); + let advertised: Vec<&str> = table.iter().find(|t| t.name == "redact_mark").unwrap().input_schema["properties"]["pattern"]["enum"] + .as_array() + .unwrap() + .iter() + .map(|v| v.as_str().unwrap()) + .collect(); + assert!(advertised.contains(&"iban"), "the advertised redact_mark schema must offer iban: {advertised:?}"); + let dir = workdir("redact-iban"); + std::fs::write(dir.join("invoice.txt"), "Pay DE89 3704 0044 0532 0130 00 today\nAccount 12345678 is ours\nTotal due").unwrap(); + let mut a = auto(&dir); + let doc = ok(&mut a, "doc_create", json!({ "from": "text", "path": "invoice.txt" }))["doc"].as_u64().unwrap(); + let marked = ok(&mut a, "redact_mark", json!({ "doc": doc, "pattern": "iban" })); + assert_eq!(marked["marked"], 1, "the spaced German sample IBAN needs one mark"); + assert!(page_text(&mut a, doc)[0].contains("DE89 3704 0044 0532 0130 00"), "marks alone remove nothing"); + assert_eq!(ok(&mut a, "redact_apply", json!({ "doc": doc }))["applied"], 1); + ok(&mut a, "doc_save", json!({ "doc": doc, "path": "redacted.pdf" })); + let reopened = ok(&mut a, "doc_open", json!({ "path": "redacted.pdf" }))["doc"].as_u64().unwrap(); + let text = &page_text(&mut a, reopened)[0]; + assert!(!text.contains("DE89") && !text.contains("0532"), "{text}"); + assert!(text.lines().any(|line| line.trim() == "Pay"), "only the label before the number remains: {text}"); + assert!(text.contains("Account 12345678") && text.contains("Total due"), "text without an IBAN remains: {text}"); + std::fs::remove_dir_all(dir).unwrap(); +} + /// One page with the text "Secret 1234" and a Redact annotation that has neither a usable /// QuadPoints array nor a Rect, so there is no area to redact. fn redact_pdf_with_unreadable_mark() -> Vec { @@ -4959,6 +5243,83 @@ fn adding_content_through_tools() { assert!(matches!(a.call("content_delete", &json!({ "doc": doc, "page": 1, "index": 5 })), Err(ToolError::Failed(_)))); } +/// #6440: `page_add_text` paints text in CMYK or gray for a print file, so its black is 100 K +/// (`0 0 0 1 k`) rather than DeviceRGB; `content_update` restyles it either way. +#[test] +fn added_text_takes_a_cmyk_or_gray_ink_through_tools() { + let dir = workdir("content-ink"); + let mut a = auto(&dir); + let doc = ok(&mut a, "doc_open", json!({ "path": "a.pdf" }))["doc"].as_u64().unwrap(); + ok(&mut a, "page_add_text", json!({ "doc": doc, "page": 1, "text": "PROOF", "at": [20, 20], "cmyk": [0, 0, 0, 1] })); + ok(&mut a, "page_add_text", json!({ "doc": doc, "page": 1, "text": "Note", "at": [20, 80], "gray": 0.5 })); + let items = ok(&mut a, "content_list", json!({ "doc": doc }))["items"].clone(); + assert_eq!((&items[0]["cmyk"], &items[1]["gray"]), (&json!([0.0, 0.0, 0.0, 1.0]), &json!(0.5))); + // The item streams of the saved file. + let saved_items = |a: &mut Automation, name: &str| -> Vec { + ok(a, "doc_save", json!({ "doc": doc, "path": name })); + let saved = pdfcraft_cos::Document::open(std::sync::Arc::new(std::fs::read(dir.join(name)).unwrap())).unwrap(); + let page = &pdfcraft_model::pages(&saved)[0]; + let list = saved.resolve(page.dict.get(b"Contents").unwrap()).as_array().cloned().unwrap(); + list.iter() + .filter_map(|c| match &*saved.resolve(c) { + pdfcraft_cos::Object::Stream(s) if s.dict.name(b"PCMark") == Some(&b"Added"[..]) => { + Some(String::from_utf8_lossy(&s.decoded().unwrap()).into_owned()) + } + _ => None, + }) + .collect() + }; + let streams = saved_items(&mut a, "ink.pdf"); + assert!(streams[0].contains("0 0 0 1 k") && !streams[0].contains("rg"), "{}", streams[0]); + assert!(streams[1].contains("0.5 g") && !streams[1].contains("rg"), "{}", streams[1]); + // Restyled: to RGB with color, and back to CMYK. + ok(&mut a, "content_update", json!({ "doc": doc, "page": 1, "index": 2, "color": "#000000" })); + ok(&mut a, "content_update", json!({ "doc": doc, "page": 1, "index": 1, "cmyk": [1, 0, 0, 0] })); + let items = ok(&mut a, "content_list", json!({ "doc": doc }))["items"].clone(); + assert_eq!((&items[0]["cmyk"], items[1].get("gray")), (&json!([1.0, 0.0, 0.0, 0.0]), None)); + let streams = saved_items(&mut a, "restyled.pdf"); + assert!(streams[0].contains("1 0 0 0 k") && streams[1].contains("0 0 0 rg"), "{streams:?}"); + // One colour at a time, four numbers from 0 to 1. + for bad in [ + json!({ "color": "red", "cmyk": [0, 0, 0, 1] }), + json!({ "gray": 0.5, "cmyk": [0, 0, 0, 1] }), + json!({ "gray": 1.5 }), + json!({ "cmyk": [0, 0, 1] }), + json!({ "cmyk": [0, 0, 0, 1, 0] }), + json!({ "cmyk": [0, "x", 0, 1] }), + json!({ "cmyk": [0, 0, 0, -0.1] }), + ] { + let mut args = json!({ "doc": doc, "page": 1, "text": "x", "at": [20, 200] }); + args.as_object_mut().unwrap().extend(bad.as_object().unwrap().clone()); + assert!(matches!(a.call("page_add_text", &args), Err(ToolError::InvalidArgs(_))), "{bad}"); + } + assert_eq!(ok(&mut a, "content_list", json!({ "doc": doc }))["count"], 2, "nothing refused was added"); + // content_update refuses them too, an image takes no ink, and a refused update changes nothing. + let mut png = Vec::new(); + { + let mut enc = png::Encoder::new(&mut png, 40, 20); + enc.set_color(png::ColorType::Rgb); + let mut w = enc.write_header().unwrap(); + w.write_image_data(&[200u8; 2400]).unwrap(); + } + std::fs::write(dir.join("logo.png"), png).unwrap(); + ok(&mut a, "page_add_image", json!({ "doc": doc, "page": 1, "path": "logo.png", "rect": [100, 200, 180, 240] })); + let before = ok(&mut a, "content_list", json!({ "doc": doc }))["items"].clone(); + for (index, bad) in [ + (1, json!({ "gray": 0.5, "cmyk": [0, 0, 0, 1] })), + (2, json!({ "color": "red", "gray": 0.5 })), + (1, json!({ "size": 30, "cmyk": [0, 0, 0, 2] })), + (2, json!({ "bold": true, "gray": -1 })), + (3, json!({ "gray": 0.5 })), + (3, json!({ "cmyk": [0, 0, 0, 1] })), + ] { + let mut args = json!({ "doc": doc, "page": 1, "index": index }); + args.as_object_mut().unwrap().extend(bad.as_object().unwrap().clone()); + assert!(matches!(a.call("content_update", &args), Err(ToolError::InvalidArgs(_))), "{bad}"); + } + assert_eq!(ok(&mut a, "content_list", json!({ "doc": doc }))["items"], before, "a refused update changed nothing"); +} + /// Edit ▸ Copy and Paste headlessly (#2636): an added text box or image, as it is, onto its own /// page beside it, onto a point, and into another document. #[test] @@ -6437,6 +6798,44 @@ fn drawing_comments_through_tools() { assert!(matches!(png[0], Content::Png { .. })); } +/// comment_add `ortho`, Shift's hold while drawing: a line's end is held level or plumb with its +/// start, and each corner of connected lines or a polygon with the corner before. +#[test] +fn lines_and_corners_are_held_level_or_plumb_through_the_tool() { + let dir = workdir("ortho"); + let mut a = auto(&dir); + let doc = ok(&mut a, "doc_open", json!({ "path": "a.pdf" }))["doc"].as_u64().unwrap(); + for args in [ + json!({ "type": "line", "from": [20, 40], "to": [120, 52], "ortho": true }), + json!({ "type": "arrow", "from": [180, 40], "to": [170, 140], "ortho": true }), + json!({ "type": "polyline", "points": [[20, 200], [90, 210], [95, 260], [130, 250]], "ortho": true }), + json!({ "type": "line", "from": [20, 280], "to": [120, 290] }), + ] { + let mut args = args; + args.as_object_mut().unwrap().extend([("doc".to_string(), json!(doc)), ("page".to_string(), json!(1))]); + ok(&mut a, "comment_add", args); + } + let list = ok(&mut a, "comment_list", json!({ "doc": doc, "page": 1 })); + // In the order added: the list isn't sorted by index. + let mut listed = list["comments"].as_array().unwrap().clone(); + listed.sort_by_key(|c| c["index"].as_u64()); + let points: Vec> = + listed.iter().map(|c| c["points"].as_array().unwrap().iter().map(|p| [p[0].as_f64().unwrap(), p[1].as_f64().unwrap()]).collect()).collect(); + let want: [&[[f64; 2]]; 4] = [ + &[[20.0, 40.0], [120.0, 40.0]], + &[[180.0, 40.0], [180.0, 140.0]], + &[[20.0, 200.0], [90.0, 200.0], [90.0, 260.0], [130.0, 260.0]], + &[[20.0, 280.0], [120.0, 290.0]], + ]; + assert_eq!(points.len(), want.len(), "{points:?}"); + for (got, want) in points.iter().zip(want) { + assert_eq!(got.len(), want.len(), "{got:?}"); + assert!(got.iter().zip(want).all(|(g, w)| (g[0] - w[0]).abs() < 0.01 && (g[1] - w[1]).abs() < 0.01), "{got:?} for {want:?}"); + } + let refused = a.call("comment_add", &json!({ "doc": doc, "page": 1, "type": "rectangle", "rect": [10, 10, 50, 50], "ortho": true })); + assert!(matches!(refused, Err(ToolError::InvalidArgs(_))), "ortho is for lines and corners: {refused:?}"); +} + #[test] fn signing_with_an_image_typed_or_drawn_graphic_through_tools() { let dir = workdir("signing-graphic"); @@ -6528,6 +6927,43 @@ fn a_dynamic_xfa_forms_signature_box_is_signed_under_its_som_path() { let _ = std::fs::remove_dir_all(&dir); } +#[test] +fn named_layer_verdicts_are_reported_and_rendered_through_tools() { + use pdfcraft_cos::{Dict, Document, Lexer, ObjRef, Object, SaveOptions, Stream}; + let dir = workdir("named-layer-verdict"); + let mut cos = Document::open(std::sync::Arc::new(fixture(1))).unwrap(); + let dict = |text: &str| Lexer::new(text.as_bytes(), 0).object().unwrap().as_dict().unwrap().clone(); + let form = |resources: Dict, ops: &str| { + let mut d = dict("<< /Type /XObject /Subtype /Form /BBox [0 0 100 100] >>"); + d.set(b"Resources".to_vec(), resources); + Stream::from_raw(d, ops.as_bytes().to_vec()) + }; + let blank = cos.add(form(Dict::new(), "")); + let layers = dict(&format!("<< /XObject << /n1 {blank} /n3 {blank} >> >>")); + let layer_form = cos.add(form(layers, "/n1 Do /n3 Do")); + let normal = cos.add(form(dict(&format!("<< /XObject << /FRM {layer_form} >> >>")), "/FRM Do")); + // Deliberately malformed CMS: an invalid signature still gets the redrawn invalid state. + let value = cos.add(dict("<< /Type /Sig /SubFilter /ETSI.CAdES.detached /ByteRange [0 0 0 0] /Contents <00> >>")); + let widget = cos + .add(dict(&format!("<< /FT /Sig /T (Signature1) /Subtype /Widget /F 4 /Rect [50 50 150 150] /P 4 0 R /V {value} /AP << /N {normal} >> >>"))); + cos.update_dict(ObjRef::new(4, 0), |p| p.set(b"Annots".to_vec(), vec![Object::Ref(widget)])).unwrap(); + cos.update_dict(cos.root().unwrap(), |root| root.set(b"AcroForm".to_vec(), dict(&format!("<< /Fields [{widget}] >>")))).unwrap(); + let original = pdfcraft_cos::write_full(&cos, &SaveOptions::default()).unwrap(); + std::fs::write(dir.join("named.pdf"), &original).unwrap(); + let mut a = auto(&dir); + let doc = ok(&mut a, "doc_open", json!({"path": "named.pdf"}))["doc"].as_u64().unwrap(); + let list = ok(&mut a, "sign_list", json!({"doc": doc})); + assert_eq!(list["signatures"][0]["status"], "invalid"); + assert_eq!(list["signatures"][0]["verdict_shown"], true); + let rendered = a.call("page_render", &json!({"doc": doc, "page": 1, "dpi": 72})).unwrap(); + let Content::Png { data, .. } = &rendered[0] else { panic!("expected a PNG") }; + let pixels = image::load_from_memory_with_format(data, image::ImageFormat::Png).unwrap().to_rgba8(); + let red = pixels.pixels().filter(|p| p.0.iter().zip([0xD7, 0x37, 0x3F]).all(|(a, b)| a.abs_diff(b) < 30)).count(); + assert!(red > 100, "the invalid state is drawn: {red} red pixels"); + ok(&mut a, "doc_save", json!({"doc": doc, "path": "saved.pdf", "full": false})); + assert_eq!(std::fs::read(dir.join("saved.pdf")).unwrap(), original, "the drawn state never enters saves"); +} + #[test] fn digital_ids_signing_and_validation_through_tools() { let dir = workdir("signing"); @@ -6586,6 +7022,8 @@ fn sign_document_and_verify_trust(a: &mut Automation, dir: &Path) -> u64 { assert_eq!(t["trusted"].as_array().unwrap().len(), 1); let list = ok(a, "sign_list", json!({ "doc": doc })); assert_eq!((list["all_valid"].as_bool(), list["signatures"][0]["status"].as_str()), (Some(true), Some("valid"))); + // PdfCraft's own appearance has no status layers to draw into: only the page badge shows it. + assert_eq!(list["signatures"][0]["verdict_shown"], false); ok(a, "comment_add", json!({ "doc": doc, "page": 1, "type": "note", "at": [20, 20], "contents": "ok" })); let s = &ok(a, "sign_list", json!({ "doc": doc }))["signatures"][0]; assert_eq!((s["status"].as_str(), s["modification"].as_str()), (Some("valid"), Some("allowed"))); @@ -7194,6 +7632,63 @@ fn a_page_printed_in_strips_gets_small_through_tools() { assert!(matches!(a.call("doc_optimize", &json!({ "doc": doc, "path": "x.pdf", "preset": "tiny" })), Err(ToolError::InvalidArgs(_)))); } +#[test] +fn optimizing_to_a_target_size() { + // Dropped at the end of the test, also when an assertion fails. + let tmp = tempfile::TempDir::new().unwrap(); + let dir = tmp.path().to_path_buf(); + let (w, h) = (2400u32, 1600u32); + let px: Vec = (0..w * h) + .flat_map(|i| { + let (x, y) = (i % w, i / w); + [(x * 255 / w) as u8 ^ ((x * y) & 15) as u8, (y * 255 / h) as u8, ((x + y) & 255) as u8] + }) + .collect(); + let mut jpeg = Vec::new(); + let mut enc = image::codecs::jpeg::JpegEncoder::new_with_quality(&mut jpeg, 95); + enc.set_pixel_density(image::codecs::jpeg::PixelDensity::dpi(600)); + enc.encode(&px, w, h, image::ExtendedColorType::Rgb8).unwrap(); + std::fs::write(dir.join("photo.jpg"), &jpeg).unwrap(); + let mut a = auto(&dir); + let doc = ok(&mut a, "doc_create", json!({ "from": "images", "paths": ["photo.jpg"] }))["doc"].as_u64().unwrap(); + // Without a target nothing changes: no target fields. + let base = ok(&mut a, "doc_optimize", json!({ "doc": doc, "path": "base.pdf" })); + assert!(base.get("target_reached").is_none(), "{base}"); + let base_len = base["bytes_after"].as_u64().unwrap(); + // A target below the default result is met by a stronger step. + let r = ok(&mut a, "doc_optimize", json!({ "doc": doc, "path": "fit.pdf", "target_bytes": base_len - 1 })); + assert_eq!(r["target_reached"], true, "{r}"); + assert!(r["bytes_after"].as_u64().unwrap() < base_len, "{r}"); + assert!(r["target_settings"]["step"].as_u64().unwrap() >= 1, "{r}"); + assert_eq!(std::fs::metadata(dir.join("fit.pdf")).unwrap().len(), r["bytes_after"].as_u64().unwrap()); + // A target already met by the first attempt tries nothing more. + let r = ok(&mut a, "doc_optimize", json!({ "doc": doc, "path": "easy.pdf", "target_bytes": base_len })); + assert_eq!((r["target_reached"].as_bool(), r["attempts"].as_u64()), (Some(true), Some(1)), "{r}"); + // An impossible target: bounded attempts, smallest copy written, said plainly. + let r = ok(&mut a, "doc_optimize", json!({ "doc": doc, "path": "tiny.pdf", "target_bytes": 1 })); + assert_eq!((r["target_reached"].as_bool(), r["attempts"].as_u64()), (Some(false), Some(6)), "{r}"); + assert!(r["bytes_after"].as_u64().unwrap() < base_len, "{r}"); + assert!(std::fs::metadata(dir.join("tiny.pdf")).is_ok()); + // The open document is untouched by the failed attempts, and bad targets are refused. + let again = ok(&mut a, "doc_optimize", json!({ "doc": doc, "path": "again.pdf" })); + assert_eq!(again["bytes_after"].as_u64().unwrap(), base_len); + assert!(matches!(a.call("doc_optimize", &json!({ "doc": doc, "path": "x.pdf", "target_bytes": 0 })), Err(ToolError::InvalidArgs(_)))); + // A caller who asked for lossless images keeps them: retries only tighten the ppi, no JPEG quality. + let lossless = json!({ "compression": "zip" }); + let r = ok(&mut a, "doc_optimize", json!({ "doc": doc, "path": "zip.pdf", "color": lossless, "gray": lossless, "target_bytes": 1 })); + assert_eq!(r["attempts"].as_u64(), Some(6), "{r}"); + assert!(r["target_settings"]["max_ppi"].is_number() && r["target_settings"]["max_jpeg_quality"].is_null(), "{r}"); + // A JPEG caller gets the quality step. + let r = ok(&mut a, "doc_optimize", json!({ "doc": doc, "path": "jpg.pdf", "target_bytes": 1 })); + assert!(r["target_settings"]["max_jpeg_quality"].is_number(), "{r}"); + // Settings already at the ladder's floor leave every rung equal to the first run: no retries. + let floor = json!({ "ppi": 9, "above_ppi": 9, "compression": "jpeg", "quality": 1 }); + let r = ok(&mut a, "doc_optimize", json!({ "doc": doc, "path": "floor.pdf", "color": floor, "gray": floor, "target_bytes": 1 })); + assert_eq!((r["target_reached"].as_bool(), r["attempts"].as_u64()), (Some(false), Some(1)), "{r}"); + // Confinement still applies. + assert!(a.call("doc_optimize", &json!({ "doc": doc, "path": "../out.pdf", "target_bytes": 1000 })).is_err()); +} + #[test] fn initial_view_through_tools() { let dir = workdir("initial-view"); @@ -7220,6 +7715,8 @@ fn ocr_tools_make_a_scan_searchable() { let mut a = auto(&dir); let status = ok(&mut a, "ocr_status", json!({})); assert_eq!(status["languages"][0]["code"], "en"); + assert_eq!(status["engines"][0]["id"], "ocrs", "{status}"); + assert!(status["engines"][1]["id"] == "tesseract" && status["engines"][1]["available"].is_boolean(), "{status}"); if status["available"] != true { eprintln!("skipped: OCR models not installed"); return; @@ -7234,6 +7731,64 @@ fn ocr_tools_make_a_scan_searchable() { let again = ok(&mut a, "ocr_recognize", json!({ "doc": scan, "pages": [1] })); assert!(again["pages"][0]["skipped"].is_string(), "{again}"); assert!(matches!(a.call("ocr_recognize", &json!({ "doc": scan, "language": "xx" })), Err(ToolError::InvalidArgs(_)))); + // An engine that cannot run is named up front, before anything is read. + if status["engines"][1]["available"] != true { + let why = a.call("ocr_recognize", &json!({ "doc": scan, "engine": "tesseract", "skip_text_pages": false })).unwrap_err(); + assert!(matches!(why, ToolError::Failed(_)), "{why}"); + assert!(why.to_string().contains("tesseract"), "{why}"); + } + // ocr_words: the recognition's words with confidence, band and suspects, changing nothing. + // ocrs reports no confidences, so `auto` + a confidence merge is asked for when the second + // engine is there to supply them; without it confidence and band are honestly null. + ok(&mut a, "doc_close", json!({ "doc": scan, "discard_changes": true })); + let scan = ok(&mut a, "doc_create", json!({ "from": "images", "paths": [png.to_string_lossy()] }))["doc"].as_u64().unwrap(); + let mut args = json!({ "doc": scan }); + if status["engines"][1]["available"] == true { + args["engine"] = json!("auto"); + args["strategy"] = json!("confidence"); + } + let words = ok(&mut a, "ocr_words", args); + assert!(words["words"].as_u64().unwrap() >= 4, "{words}"); + let first = &words["pages"][0]["words"][0]; + assert!(first["text"].is_string() && first["box"].as_array().is_some_and(|b| b.len() == 4), "{words}"); + if status["engines"][1]["available"] == true { + let with_confidence = words["pages"][0]["words"] + .as_array() + .expect("words") + .iter() + .filter(|w| w["confidence"].is_number() && w["band"].as_str().is_some()) + .count(); + assert!(with_confidence >= 4, "the second engine's confidences arrive: {words}"); + } else { + assert!(first["confidence"].is_null() && first["band"].is_null() && first["suspect"] == false, "{words}"); + } + assert!(a.call("edit_undo", &json!({ "doc": scan })).is_err(), "ocr_words changes nothing, so there is no undo"); +} + +/// An editable-text recognition writes a NEW file of visible text, never the source. +#[test] +fn ocr_recognize_editable_output_writes_visible_text() { + let dir = workdir("ocr-editable"); + let mut a = auto(&dir); + if ok(&mut a, "ocr_status", json!({}))["available"] != true { + eprintln!("skipped: OCR models not installed"); + return; + } + let text = ok(&mut a, "doc_create", json!({ "from": "text", "text": "Editable output words" }))["doc"].as_u64().unwrap(); + ok(&mut a, "doc_export_images", json!({ "doc": text, "folder": "scan", "dpi": 150, "pages": [1] })); + let png = std::fs::read_dir(dir.join("scan")).unwrap().next().unwrap().unwrap().path(); + let scan = ok(&mut a, "doc_create", json!({ "from": "images", "paths": [png.to_string_lossy()] }))["doc"].as_u64().unwrap(); + ok(&mut a, "doc_save", json!({ "doc": scan, "path": "src/scan.pdf" })); + // The output never lands on the source. + let why = a.call("ocr_recognize", &json!({ "doc": scan, "pages": [1], "output_mode": "editable", "out": "src/scan.pdf" })).unwrap_err(); + assert!(why.to_string().contains("source"), "{why}"); + let r = ok(&mut a, "ocr_recognize", json!({ "doc": scan, "pages": [1], "output_mode": "editable", "out": "out/ocr.pdf" })); + assert!(r["words"].as_u64().unwrap() >= 3, "{r}"); + let ocr = ok(&mut a, "doc_open", json!({ "path": "out/ocr.pdf" }))["doc"].as_u64().unwrap(); + // The text is visible (the engine may misread a letter at this dpi — look for a word that + // survives). + let found = ok(&mut a, "text_find", json!({ "doc": ocr, "query": "output" })); + assert!(found["count"].as_u64() >= Some(1), "the new file's text is visible: {found}"); } /// #1028: `skip_text_pages: false` reads a picture on a page that has its own text, and the @@ -7276,6 +7831,46 @@ fn ocr_recognize_files_refuses_paths_outside_the_root() { assert!(!dir.join("out").exists(), "nothing was started"); } +/// Two inputs of one file name from different folders would write the same output in the +/// batch folder: the batch is refused up front, with or without the OCR engines, naming the +/// file, and nothing is written. +#[test] +fn ocr_recognize_files_refuses_inputs_that_share_a_file_name() { + let dir = workdir("ocr-files-same-name"); + let mut a = auto(&dir); + let doc = ok(&mut a, "doc_open", json!({ "path": "a.pdf" }))["doc"].as_u64().unwrap(); + ok(&mut a, "doc_save", json!({ "doc": doc, "path": "one/scan.pdf" })); + ok(&mut a, "doc_save", json!({ "doc": doc, "path": "two/scan.pdf" })); + let r = a.call("ocr_recognize_files", &json!({ "paths": ["one/scan.pdf", "two/scan.pdf"], "folder": "out" })); + assert!(matches!(&r, Err(ToolError::InvalidArgs(m)) if m.contains("scan.pdf") && m.contains("overwrite")), "{r:?}"); + assert!(std::fs::read_dir(dir.join("out")).map_or(true, |mut d| d.next().is_none()), "nothing was written"); +} + +/// `out` belongs to the editable output. A searchable run (the default) writes into the open +/// document, so an `out` is refused rather than silently ignored, with or without the engines. +#[test] +fn ocr_recognize_refuses_an_out_that_nothing_would_use() { + let dir = workdir("ocr-out-ignored"); + let mut a = auto(&dir); + let doc = ok(&mut a, "doc_open", json!({ "path": "a.pdf" }))["doc"].as_u64().unwrap(); + let r = a.call("ocr_recognize", &json!({ "doc": doc, "out": "../outside.pdf" })); + assert!(matches!(&r, Err(ToolError::InvalidArgs(m)) if m.contains("editable")), "{r:?}"); + assert!(!dir.join("../outside.pdf").exists()); +} + +/// The editable output is a NEW file: an existing `out` is refused before anything runs (with +/// or without the engines), and the file is left as it was. +#[test] +fn ocr_recognize_editable_output_never_replaces_an_existing_file() { + let dir = workdir("ocr-editable-exists"); + let mut a = auto(&dir); + let doc = ok(&mut a, "doc_open", json!({ "path": "a.pdf" }))["doc"].as_u64().unwrap(); + std::fs::write(dir.join("taken.pdf"), b"keep me").unwrap(); + let r = a.call("ocr_recognize", &json!({ "doc": doc, "output_mode": "editable", "out": "taken.pdf" })); + assert!(matches!(&r, Err(e) if e.to_string().contains("already exists")), "{r:?}"); + assert_eq!(std::fs::read(dir.join("taken.pdf")).unwrap(), b"keep me"); +} + #[test] fn ocr_recognize_files_writes_searchable_copies() { let dir = workdir("ocr-files"); @@ -7289,9 +7884,22 @@ fn ocr_recognize_files_writes_searchable_copies() { let png = std::fs::read_dir(dir.join("scan")).unwrap().next().unwrap().unwrap().path(); let scan = ok(&mut a, "doc_create", json!({ "from": "images", "paths": [png.to_string_lossy()] }))["doc"].as_u64().unwrap(); ok(&mut a, "doc_save", json!({ "doc": scan, "path": "in/scan.pdf" })); + // A file that already has text: the skip-files option passes it over as its own bucket. + let typed = ok(&mut a, "doc_create", json!({ "from": "text", "text": "Already typed" }))["doc"].as_u64().unwrap(); + ok(&mut a, "doc_save", json!({ "doc": typed, "path": "in/typed.pdf" })); + // Collision pre-flight: the existing out/scan.pdf (written below) stops a rerun. let r = ok(&mut a, "ocr_recognize_files", json!({ "paths": ["in/scan.pdf", "missing.pdf"], "folder": "out" })); assert!(r["files"][0]["words"].as_u64().unwrap() >= 3, "{r}"); assert!(r["files"][1]["error"].is_string(), "{r}"); + let why = a.call("ocr_recognize_files", &json!({ "paths": ["in/scan.pdf"], "folder": "out" })).unwrap_err(); + assert!(matches!(why, ToolError::Failed(_)), "{why}"); + assert!(why.to_string().contains("scan.pdf"), "{why}"); + // The skip-files bucket and the low-confidence note. + let r = ok(&mut a, "ocr_recognize_files", json!({ "paths": ["in/typed.pdf", "in/scan.pdf"], "folder": "out2", "skip_text_files": true })); + assert_eq!(r["skipped_files"].as_u64(), Some(1), "{r}"); + assert!(r["files"][0]["skipped"].is_string(), "{r}"); + assert_eq!(r["recognized"].as_u64(), Some(1), "{r}"); + assert!(r["files"][1]["output"].is_string(), "{r}"); let out = ok(&mut a, "doc_open", json!({ "path": "out/scan.pdf" }))["doc"].as_u64().unwrap(); let found = ok(&mut a, "text_find", json!({ "doc": out, "query": "recognition" })); assert!(found.to_string().contains("\"page\""), "{found}"); @@ -7301,18 +7909,6 @@ fn ocr_recognize_files_writes_searchable_copies() { /// the second output replaces the first while both results report success. The batch is refused /// up front, naming the file, before the folder is created, anything is read or the OCR engines /// load, so the outcome is the same with or without the models installed. -#[test] -fn ocr_recognize_files_refuses_inputs_that_share_a_file_name() { - let dir = workdir("ocr-files-same-name"); - let mut a = auto(&dir); - let doc = ok(&mut a, "doc_open", json!({ "path": "a.pdf" }))["doc"].as_u64().unwrap(); - ok(&mut a, "doc_save", json!({ "doc": doc, "path": "one/scan.pdf" })); - ok(&mut a, "doc_save", json!({ "doc": doc, "path": "two/scan.pdf" })); - let r = a.call("ocr_recognize_files", &json!({ "paths": ["one/scan.pdf", "two/scan.pdf"], "folder": "out" })); - assert!(matches!(&r, Err(ToolError::InvalidArgs(m)) if m.contains("scan.pdf")), "{r:?}"); - assert!(!dir.join("out").exists(), "nothing was started: the output folder was not created"); -} - /// File names are compared without regard to case on Windows and macOS (`scan.pdf` and `Scan.PDF` /// are one file there), and exactly elsewhere, where they are two files and the batch is not /// refused. @@ -7815,6 +8411,52 @@ BT /F1 11 Tf 20 20 Td (Total due: 150.00) Tj ET"; assert!(rendered.iter().any(|c| matches!(c, Content::Png { .. }))); } +/// #5149: a two-column, two-row table drawn with ruled lines reaches Word as a table with its +/// rules, not as four paragraphs one under another. +#[test] +fn exporting_a_ruled_two_by_two_table_to_word_keeps_the_table() { + let dir = workdir("ruled-table-word"); + let content = "0.5 w 20 270 m 300 270 l S 20 245 m 300 245 l S 20 220 m 300 220 l S \ +20 220 m 20 270 l S 160 220 m 160 270 l S 300 220 m 300 270 l S \ +BT /F1 11 Tf 25 253 Td (Name) Tj 140 0 Td (Value) Tj -140 -25 Td (Alpha) Tj 140 0 Td (One) Tj ET \ +BT /F1 11 Tf 20 150 Td (A paragraph after the table.) Tj ET"; + let stream = format!("<< /Length {} >>\nstream\n{content}\nendstream", content.len()); + let objs = [ + "<< /Type /Catalog /Pages 2 0 R >>", + "<< /Type /Pages /Kids [3 0 R] /Count 1 >>", + "<< /Type /Page /Parent 2 0 R /MediaBox [0 0 320 300] /Contents 4 0 R /Resources << /Font << /F1 5 0 R >> >> >>", + stream.as_str(), + "<< /Type /Font /Subtype /Type1 /BaseFont /Helvetica >>", + ]; + std::fs::write(dir.join("table.pdf"), pdf_of(&objs)).unwrap(); + let mut a = auto(&dir); + let doc = ok(&mut a, "doc_open", json!({ "path": "table.pdf" }))["doc"].as_u64().unwrap(); + ok(&mut a, "doc_export_office", json!({ "doc": doc, "path": "table.docx" })); + let zip = std::fs::read(dir.join("table.docx")).unwrap(); + let mut at = 0; + let mut xml = String::new(); + while zip[at..].starts_with(b"PK\x03\x04") { + let size = u32::from_le_bytes(zip[at + 18..at + 22].try_into().unwrap()) as usize; + let len = u16::from_le_bytes(zip[at + 26..at + 28].try_into().unwrap()) as usize; + let data = at + 30 + len; + if &zip[at + 30..data] == b"word/document.xml" { + std::io::Read::read_to_string(&mut flate2::read::DeflateDecoder::new(&zip[data..data + size]), &mut xml).unwrap(); + break; + } + at = data + size; + } + assert_eq!(xml.matches("").count(), 1, "the ruled grid is a table: {xml}"); + let table = xml.split_once("").and_then(|(_, t)| t.split_once("")).map(|(t, _)| t).unwrap(); + assert_eq!(table.matches("").count(), 2, "{table}"); + for word in ["Name", "Value", "Alpha", "One"] { + assert_eq!(table.matches(&format!(">{word}")).count(), 1, "{word} is a cell: {xml}"); + assert_eq!(xml.matches(&format!(">{word}")).count(), 1, "{word} is written once"); + } + assert!(table.contains("w:val=\"single\""), "the drawn rules become borders: {table}"); + assert!(!table.contains("A paragraph after the table.")); + assert_eq!(xml.matches(">A paragraph after the table.").count(), 1); +} + /// #4158: a word set in italic inside a sentence ("Before *Chevron* after.") reaches Word as an /// italic run of the sentence's paragraph, not as a paragraph of its own between two halves. #[test] @@ -8917,27 +9559,15 @@ fn a_deleted_image_is_not_kept_by_reduce_or_optimize() { /// page is turned with /Rotate 90. fn table_pdf() -> Vec { let body = "BT /F1 12 Tf 20 250 Td (Name) Tj 130 0 Td (Qty) Tj -130 -20 Td (Apple) Tj 130 0 Td (12) Tj -130 -20 Td (Pear) Tj 130 0 Td (7) Tj ET"; - let objs = [ - "<< /Type /Catalog /Pages 2 0 R >>".to_string(), - "<< /Type /Pages /Kids [4 0 R 5 0 R] /Count 2 /MediaBox [0 0 300 300] >>".to_string(), - "<< /Type /Font /Subtype /Type1 /BaseFont /Helvetica >>".to_string(), - "<< /Type /Page /Parent 2 0 R /Contents 6 0 R /Resources << /Font << /F1 3 0 R >> >> >>".to_string(), - "<< /Type /Page /Parent 2 0 R /Rotate 90 /Contents 6 0 R /Resources << /Font << /F1 3 0 R >> >> >>".to_string(), - format!("<< /Length {} >>\nstream\n{body}\nendstream", body.len()), - ]; - 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 + let stream = format!("<< /Length {} >>\nstream\n{body}\nendstream", body.len()); + pdf_of(&[ + "<< /Type /Catalog /Pages 2 0 R >>", + "<< /Type /Pages /Kids [4 0 R 5 0 R] /Count 2 /MediaBox [0 0 300 300] >>", + "<< /Type /Font /Subtype /Type1 /BaseFont /Helvetica >>", + "<< /Type /Page /Parent 2 0 R /Contents 6 0 R /Resources << /Font << /F1 3 0 R >> >> >>", + "<< /Type /Page /Parent 2 0 R /Rotate 90 /Contents 6 0 R /Resources << /Font << /F1 3 0 R >> >> >>", + &stream, + ]) } /// Issue #740: `text_extract` with `rect` takes what Column select takes, in the displayed-page @@ -8978,6 +9608,56 @@ fn text_extract_with_a_rect_takes_one_column() { } } +/// Copy with formatting, headless: `format: "html"` adds each page's text as the HTML fragment +/// Copy puts on the clipboard, for the whole page or only what `rect` takes. +#[test] +fn text_extract_as_html_keeps_the_formatting() { + let dir = workdir("rich-copy"); + std::fs::write(dir.join("table.pdf"), table_pdf()).unwrap(); + let mut a = auto(&dir); + let doc = ok(&mut a, "doc_open", json!({ "path": "table.pdf" }))["doc"].as_u64().unwrap(); + let page = &ok(&mut a, "text_extract", json!({ "doc": doc, "pages": [1], "format": "html" }))["pages"][0]; + let html = page["html"].as_str().unwrap(); + assert!(html.starts_with("

Name"), "{html}"); + assert!(html.contains("Pear") && html.contains("Qty"), "{html}"); + assert_eq!(page["text"], "Name\nApple\nPear\nQty\n12\n7", "the plain text is unchanged"); + assert_eq!(page["styles_incomplete"], false); + // Plain text by default: no html key. + assert!(ok(&mut a, "text_extract", json!({ "doc": doc, "pages": [1] }))["pages"][0].get("html").is_none()); + // Only what the rect takes; nothing inside gives empty HTML. + let column = ok(&mut a, "text_extract", json!({ "doc": doc, "pages": [1], "rect": [120, 0, 300, 300], "format": "html" })); + let html = column["pages"][0]["html"].as_str().unwrap(); + assert!(html.contains("Qty") && !html.contains("Name"), "{html}"); + let none = ok(&mut a, "text_extract", json!({ "doc": doc, "pages": [1], "rect": [0, 0, 5, 5], "format": "html" })); + assert_eq!(none["pages"][0]["html"], ""); + // An unknown format is refused. + for bad in [json!("rtf"), json!(1)] { + let e = a.call("text_extract", &json!({ "doc": doc, "format": bad })).unwrap_err(); + assert!(matches!(e, ToolError::InvalidArgs(_)), "{bad}: {e}"); + } + // Bold, italic, colour and size come through end to end. + let body = "BT /F1 18 Tf 20 250 Td (Big) Tj ET BT /F2 12 Tf 20 200 Td (Strong) Tj ET \ + BT /F3 12 Tf 20 150 Td (Slanted) Tj ET BT 0 0 1 rg /F1 12 Tf 20 100 Td (Blue) Tj ET"; + let stream = format!("<< /Length {} >>\nstream\n{body}\nendstream", body.len()); + let styled = pdf_of(&[ + "<< /Type /Catalog /Pages 2 0 R >>", + "<< /Type /Pages /Kids [3 0 R] /Count 1 /MediaBox [0 0 300 300] >>", + "<< /Type /Page /Parent 2 0 R /Contents 4 0 R /Resources << /Font << /F1 5 0 R /F2 6 0 R /F3 7 0 R >> >> >>", + &stream, + "<< /Type /Font /Subtype /Type1 /BaseFont /Helvetica >>", + "<< /Type /Font /Subtype /Type1 /BaseFont /Helvetica-Bold >>", + "<< /Type /Font /Subtype /Type1 /BaseFont /Helvetica-Oblique >>", + ]); + std::fs::write(dir.join("styled.pdf"), styled).unwrap(); + let doc = ok(&mut a, "doc_open", json!({ "path": "styled.pdf" }))["doc"].as_u64().unwrap(); + let page = &ok(&mut a, "text_extract", json!({ "doc": doc, "format": "html" }))["pages"][0]; + let html = page["html"].as_str().unwrap(); + assert!(html.contains("font-size:18pt\">Big"), "{html}"); + assert!(html.contains("Strong"), "{html}"); + assert!(html.contains("Slanted"), "{html}"); + assert!(html.contains("color:#0000FF\">Blue"), "{html}"); +} + #[test] fn mixed_visual_region_edit_preview_save_reopen_and_undo_through_tools() { use pdfcraft_cos::{Dict, Document, Object, Stream, write_incremental}; @@ -10488,6 +11168,310 @@ fn simple_rule_scan_drawn(content: &[u8]) -> Vec { write_full(&doc, &SaveOptions::default()).unwrap() } +/// #3005: a table and a small signature drawn inside one transparency-group Form XObject (how +/// HTML-to-PDF converters write a block with a translucent picture). Edit a PDF sees one piece +/// of artwork and no text; `image_edit ungroup` draws it in place with the same pixels, its +/// text becomes paragraphs that `text_edit` changes, and undo brings the form back. +fn table_in_a_form_pdf() -> Vec { + let table = b"BT /F1 12 Tf 1 0 0 1 20 120 Tm (Revenue) Tj 1 0 0 1 120 120 Tm (153,300.00) Tj 1 0 0 1 20 100 Tm (Costs) Tj 1 0 0 1 120 100 Tm (382,110.00) Tj ET 0.6 G 0.5 w 15 115 m 220 115 l S"; + // Two pictures with soft masks overlapping each other, the second also over the table's + // last cell: a translucent wash, and a picture whose corner pixels are see-through. + let inner = [&table[..], b" q 40 0 0 20 30 40 cm /Sig Do Q q 60 0 0 40 50 30 cm /Wash Do Q q 100 0 0 30 110 90 cm /Sig Do Q"].concat(); + let rgb: Vec = std::iter::repeat_n([20u8, 60, 220], 16).flatten().collect(); + let alpha: Vec = (0..16).map(|i| if i % 3 == 0 { 255 } else { 0 }).collect(); + let page = b"q /Fm1 Do Q"; + let stream = |dict: &str, data: &[u8]| [format!("{dict} /Length {} >>\nstream\n", data.len()).as_bytes(), data, b"\nendstream"].concat(); + let objs: Vec> = vec![ + b"<< /Type /Catalog /Pages 2 0 R >>".to_vec(), + b"<< /Type /Pages /Kids [3 0 R] /Count 1 >>".to_vec(), + b"<< /Type /Page /Parent 2 0 R /MediaBox [0 0 240 160] /Contents 4 0 R /Resources << /XObject << /Fm1 5 0 R >> >> >>".to_vec(), + stream("<<", page), + stream( + "<< /Type /XObject /Subtype /Form /BBox [0 0 240 160] /Group << /S /Transparency /CS /DeviceRGB >> /Resources << /Font << /F1 6 0 R >> /XObject << /Sig 7 0 R /Wash 9 0 R >> >>", + &inner, + ), + b"<< /Type /Font /Subtype /Type1 /BaseFont /Helvetica /Encoding /WinAnsiEncoding >>".to_vec(), + stream("<< /Type /XObject /Subtype /Image /Width 4 /Height 4 /ColorSpace /DeviceRGB /BitsPerComponent 8 /SMask 8 0 R", &rgb), + stream("<< /Type /XObject /Subtype /Image /Width 4 /Height 4 /ColorSpace /DeviceGray /BitsPerComponent 8", &alpha), + stream( + "<< /Type /XObject /Subtype /Image /Width 2 /Height 2 /ColorSpace /DeviceRGB /BitsPerComponent 8 /SMask 10 0 R", + &[230, 40, 40].repeat(4), + ), + stream("<< /Type /XObject /Subtype /Image /Width 2 /Height 2 /ColorSpace /DeviceGray /BitsPerComponent 8", &[128, 96, 160, 64]), + ]; + 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()); + out +} + +#[test] +fn ungrouping_a_table_drawn_in_a_form_makes_its_text_editable() { + let dir = workdir("ungroup"); + std::fs::write(dir.join("table.pdf"), table_in_a_form_pdf()).unwrap(); + let mut a = auto(&dir); + let doc = ok(&mut a, "doc_open", json!({ "path": "table.pdf" }))["doc"].as_u64().unwrap(); + let paragraphs = |a: &mut Automation| ok(a, "text_paragraphs", json!({ "doc": doc, "page": 1 }))["paragraphs"].as_array().unwrap().len(); + let objects = |a: &mut Automation| ok(a, "object_list", json!({ "doc": doc, "page": 1 }))["objects"].as_array().unwrap().len(); + assert_eq!((paragraphs(&mut a), objects(&mut a)), (0, 1), "one piece of artwork, no text"); + let (w, h, before) = a.render_pixels(doc, 1, 2.0).unwrap(); + + ok(&mut a, "image_edit", json!({ "doc": doc, "page": 1, "image": 1, "action": "ungroup" })); + let (w2, h2, after) = a.render_pixels(doc, 1, 2.0).unwrap(); + assert_eq!((w, h), (w2, h2)); + let differing = before.as_ref().as_chunks::<4>().0.iter().zip(after.as_ref().as_chunks::<4>().0).filter(|(p, q)| p != q).count(); + assert_eq!(differing, 0, "ungrouping draws the same pixels"); + assert!(paragraphs(&mut a) >= 4, "the table's text is page text now"); + let images = ok(&mut a, "page_images", json!({ "doc": doc, "page": 1 })); + let kinds: Vec<_> = images["images"].as_array().unwrap().iter().map(|i| i["kind"].clone()).collect(); + assert_eq!(kinds, vec![json!("image"); 3], "the pictures are separate pictures now: {images}"); + + let list = ok(&mut a, "text_paragraphs", json!({ "doc": doc, "page": 1 })); + let target = + list["paragraphs"].as_array().unwrap().iter().find(|p| p["text"].as_str().is_some_and(|t| t.contains("382,110.00"))).unwrap()["paragraph"] + .clone(); + ok(&mut a, "text_edit", json!({ "doc": doc, "page": 1, "paragraph": target, "text": "400,000.00" })); + let text = ok(&mut a, "text_extract", json!({ "doc": doc, "pages": [1] })); + let s = text.to_string(); + assert!(s.contains("400,000.00") && !s.contains("382,110.00"), "{s}"); + + ok(&mut a, "edit_undo", json!({ "doc": doc })); + ok(&mut a, "edit_undo", json!({ "doc": doc })); + assert_eq!((paragraphs(&mut a), objects(&mut a)), (0, 1), "undo brings the form back"); +} + +/// One 300 × 300 page that draws form `Fm1` with `page_do`; the form (with `matrix`) fills with +/// pattern `/P1` (`pattern`) in `content`, and a red outline on the page marks where it lands. +fn pattern_in_a_form_pdf(page_do: &str, matrix: &str, content: &str, pattern: &str) -> Vec { + let objs = [ + "<< /Type /Catalog /Pages 2 0 R >>".to_string(), + "<< /Type /Pages /Kids [3 0 R] /Count 1 >>".to_string(), + "<< /Type /Page /Parent 2 0 R /MediaBox [0 0 300 300] /Contents 4 0 R /Resources << /XObject << /Fm1 5 0 R >> >> >>".to_string(), + stream_object("<<", &format!("{page_do} 1 0 0 RG 1 w 60 60 180 180 re S")), + stream_object(&format!("<< /Type /XObject /Subtype /Form /BBox [0 0 300 300] {matrix} /Resources << /Pattern << /P1 6 0 R >> >>"), content), + pattern.to_string(), + ]; + 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 +} + +/// #3067 review: a pattern's matrix maps pattern space to the default space of the stream that +/// uses it (ISO 32000-2 §8.7.2), so a pattern filled inside a form moved by its `/Matrix` or by a +/// `cm` before the `Do` must stay where it was when the form is drawn inline. Each case draws +/// differently in Acrobat when the placement is lost (tiles out of phase or half size, the +/// shading outside its box); ungrouped, every one paints the same pixels. +#[test] +fn ungrouping_keeps_patterns_where_the_forms_placement_put_them() { + let tiling = stream_object( + "<< /Type /Pattern /PatternType 1 /PaintType 1 /TilingType 1 /BBox [0 0 20 20] /XStep 20 /YStep 20 /Resources << >>", + "0 0 0 rg 0 0 10 10 re f 10 10 10 10 re f", + ); + let shading = "<< /Type /Pattern /PatternType 2 /Shading << /ShadingType 2 /ColorSpace /DeviceRGB /Coords [0 0 100 0] /Function << /FunctionType 2 /Domain [0 1] /C0 [1 0 0] /C1 [0 0 1] /N 1 >> /Extend [false false] >> >>"; + let cases = [ + ("no placement", "q /Fm1 Do Q", "", "/Pattern cs /P1 scn 60 60 180 180 re f", tiling.as_str()), + ("form Matrix, half a tile", "q /Fm1 Do Q", "/Matrix [1 0 0 1 10 0]", "/Pattern cs /P1 scn 50 60 180 180 re f", tiling.as_str()), + ("cm doubling the form", "q 2 0 0 2 0 0 cm /Fm1 Do Q", "", "/Pattern cs /P1 scn 30 30 90 90 re f", tiling.as_str()), + ("shading moved by the form Matrix", "q /Fm1 Do Q", "/Matrix [1 0 0 1 100 100]", "/Pattern cs /P1 scn 0 0 100 100 re f", shading), + ]; + for (what, page_do, matrix, content, pattern) in cases { + let dir = workdir("ungroup_patterns"); + std::fs::write(dir.join("p.pdf"), pattern_in_a_form_pdf(page_do, matrix, content, pattern)).unwrap(); + let mut a = auto(&dir); + let doc = ok(&mut a, "doc_open", json!({ "path": "p.pdf" }))["doc"].as_u64().unwrap(); + let (w, h, before) = a.render_pixels(doc, 1, 1.0).unwrap(); + ok(&mut a, "image_edit", json!({ "doc": doc, "page": 1, "image": 1, "action": "ungroup" })); + ok(&mut a, "doc_save", json!({ "doc": doc, "path": "out.pdf" })); + let saved = ok(&mut a, "doc_open", json!({ "path": "out.pdf" }))["doc"].as_u64().unwrap(); + let (w2, h2, after) = a.render_pixels(saved, 1, 1.0).unwrap(); + assert_eq!((w, h), (w2, h2), "{what}"); + let differing = before.as_ref().as_chunks::<4>().0.iter().zip(after.as_ref().as_chunks::<4>().0).filter(|(p, q)| p != q).count(); + assert_eq!(differing, 0, "{what}: ungrouping draws the same pixels, saved and reopened"); + } +} + +/// An indirect stream object: `dict` (without its closing `>>`) and `data`. +fn stream_object(dict: &str, data: &str) -> String { + format!("{dict} /Length {} >>\nstream\n{data}\nendstream", data.len()) +} + +/// Reviewing headlessly: corrections keep the boxes, a stale or foreign review is refused, and +/// applying consumes the handle (the pages already accepted were applied once). +#[test] +fn ocr_review_corrections_keep_boxes_are_guarded_and_apply_once() { + fn render(a: &mut Automation, doc: u64) -> Vec { + let mut result = a.call("page_render", &json!({ "doc": doc, "page": 1, "dpi": 72 })).unwrap(); + match result.remove(0) { + Content::Png { data, .. } => data, + other => panic!("expected a rendered page, got {other:?}"), + } + } + let dir = workdir("ocr-review"); + let mut a = auto(&dir); + if ok(&mut a, "ocr_status", json!({}))["available"] != true { + eprintln!("skipped: OCR models not installed"); + return; + } + let text = ok(&mut a, "doc_create", json!({ "from": "text", "text": "Review these original words" }))["doc"].as_u64().unwrap(); + ok(&mut a, "doc_export_images", json!({ "doc": text, "folder": "scan", "dpi": 150, "pages": [1] })); + let png = std::fs::read_dir(dir.join("scan")).unwrap().next().unwrap().unwrap().path(); + let scan = ok(&mut a, "doc_create", json!({ "from": "images", "paths": [png.to_string_lossy()] }))["doc"].as_u64().unwrap(); + let before = render(&mut a, scan); + let found = ok(&mut a, "ocr_words", json!({ "doc": scan, "retain_review": true })); + assert!(found["words"].as_u64().unwrap() >= 3, "{found}"); + let review = found["review"].as_u64().unwrap(); + assert!(page_text(&mut a, scan).iter().all(String::is_empty)); + for args in [ + json!({ "doc": text, "review": review }), + json!({ "doc": scan, "review": review, "corrections": [{"page":1,"word":999999,"text":"bad"}] }), + json!({ "doc": scan, "review": review, "corrections": [{"page":1,"word":1,"text":"bad","origin":[0,0]}] }), + json!({ "doc": scan, "review": review, "corrections": [{"page":1,"word":1,"text":"a".repeat(4*1024*1024+1)}] }), + json!({ "doc": scan, "review": review, "corrections": [{"page":1,"word":1,"text":"a"},{"page":1,"word":1,"text":"b"}] }), + ] { + assert!(a.call("ocr_review_apply", &args).is_err()); + assert!(page_text(&mut a, scan).iter().all(String::is_empty)); + } + let result = ok( + &mut a, + "ocr_review_apply", + json!({ "doc": scan, "review": review, "corrections": [{"page":1,"word":1,"text":"日本語"},{"page":1,"word":2,"text":""}] }), + ); + assert!(result["applied"].as_u64().unwrap() >= 2); + let extracted = page_text(&mut a, scan).join("\n"); + assert!(extracted.contains("日本語"), "{extracted}"); + assert_eq!(render(&mut a, scan), before, "corrected text remains invisible at its original geometry"); + assert!(a.call("ocr_review_apply", &json!({ "doc": scan, "review": review })).is_err(), "consumed reviews cannot be replayed"); + ok(&mut a, "edit_undo", json!({ "doc": scan })); + assert!(page_text(&mut a, scan).iter().all(String::is_empty)); + assert!(a.call("edit_undo", &json!({ "doc": scan })).is_err(), "review acceptance is one undo step"); + + let found = ok(&mut a, "ocr_words", json!({ "doc": scan, "retain_review": true })); + let stale = found["review"].as_u64().unwrap(); + ok(&mut a, "page_rotate", json!({ "doc": scan, "pages": [1], "degrees": 90 })); + let error = a.call("ocr_review_apply", &json!({ "doc": scan, "review": stale })).unwrap_err().to_string(); + assert!(error.contains("changed since recognition"), "{error}"); + assert!(page_text(&mut a, scan).iter().all(String::is_empty)); + ok(&mut a, "ocr_review_apply", json!({ "doc": scan, "review": stale, "discard": true })); + assert!(a.call("ocr_review_apply", &json!({ "doc": scan, "review": stale })).is_err()); + ok(&mut a, "edit_undo", json!({ "doc": scan })); + + let first = ok(&mut a, "ocr_words", json!({ "doc": scan, "retain_review": true }))["review"].as_u64().unwrap(); + let second = ok(&mut a, "ocr_words", json!({ "doc": scan, "retain_review": true }))["review"].as_u64().unwrap(); + assert_ne!(first, second); + assert!(a.call("ocr_review_apply", &json!({ "doc": scan, "review": first })).is_err()); + ok( + &mut a, + "ocr_review_apply", + json!({ "doc": scan, "review": second, "output_mode": "editable", "out": "reviewed.pdf", "corrections": [{"page":1,"word":1,"text":"Corrected"}] }), + ); + assert!(page_text(&mut a, scan).iter().all(String::is_empty)); + let output = ok(&mut a, "doc_open", json!({ "path": "reviewed.pdf" }))["doc"].as_u64().unwrap(); + assert!(page_text(&mut a, output).join("\n").contains("Corrected")); + // The editable output is a new file: an existing one is refused and the review is kept. + let third = ok(&mut a, "ocr_words", json!({ "doc": scan, "retain_review": true }))["review"].as_u64().unwrap(); + let again = a.call("ocr_review_apply", &json!({ "doc": scan, "review": third, "output_mode": "editable", "out": "reviewed.pdf" })); + assert!(matches!(&again, Err(e) if e.to_string().contains("already exists")), "{again:?}"); + ok(&mut a, "ocr_review_apply", json!({ "doc": scan, "review": third, "discard": true })); +} + +#[test] +fn ocr_dictionary_updates_are_atomic_bounded_and_confined() { + let dir = workdir("ocr-dictionary"); + let mut a = auto(&dir); + let path = "ocr-dictionary-en.txt"; + let out = ok(&mut a, "ocr_dictionary", json!({ "path": path, "add": ["Quartz", "quartz", "日本語"] })); + assert_eq!(out["count"], 2); + assert_eq!(pdfcraft_engine::ocr::dictionary::words(&std::fs::read_to_string(dir.join(path)).unwrap()).unwrap().len(), 2); + let before = std::fs::read(dir.join(path)).unwrap(); + for args in [ + json!({ "path": path, "add": ["a\nb"] }), + json!({ "path": path, "add": ["x".repeat(1025)] }), + json!({ "path": path, "add": ["İ".repeat(512)] }), + json!({ "path": path, "add": vec!["x"; 65537] }), + json!({ "path": "../outside-ocr-dictionary.txt", "add": ["x"] }), + ] { + assert!(a.call("ocr_dictionary", &args).is_err()); + } + assert_eq!(std::fs::read(dir.join(path)).unwrap(), before); + assert_eq!(ok(&mut a, "ocr_dictionary", json!({ "path": path, "remove": ["QUARTZ"] }))["words"], json!(["日本語"])); + assert_eq!(ok(&mut a, "ocr_dictionary", json!({ "path": path }))["count"], 1); + std::fs::write(dir.join("ocr-dictionary-large.txt"), vec![b'a'; 4 * 1024 * 1024 + 1]).unwrap(); + let too_big = a.call("ocr_dictionary", &json!({ "path": "ocr-dictionary-large.txt", "add": ["x"] })).unwrap_err().to_string(); + assert!(!too_big.contains("must name a dictionary file"), "refused for its size, not its name: {too_big}"); + assert_eq!(std::fs::metadata(dir.join("ocr-dictionary-large.txt")).unwrap().len(), 4 * 1024 * 1024 + 1); +} + +/// The tool rewrites what it is pointed at (lower-cased, sorted), so it only takes dictionary file +/// names: another small text file under the root is neither read nor changed. +#[test] +fn ocr_dictionary_refuses_files_that_are_not_dictionaries() { + let dir = workdir("ocr-dictionary-names"); + let mut a = auto(&dir); + let env = b"TOKEN=Zebra +APPLE=1 +"; + for name in [".env", "notes.txt", "ocr-dictionary-en.md", "ocr-dictionary-e n.txt", "sub/readme.txt"] { + if let Some(parent) = std::path::Path::new(name).parent() { + std::fs::create_dir_all(dir.join(parent)).unwrap(); + } + std::fs::write(dir.join(name), env).unwrap(); + for args in [json!({ "path": name }), json!({ "path": name, "add": [] }), json!({ "path": name, "add": ["x"] })] { + let err = a.call("ocr_dictionary", &args).unwrap_err().to_string(); + assert!(err.contains("must name a dictionary file"), "{name} {args}: {err}"); + } + assert_eq!(std::fs::read(dir.join(name)).unwrap(), env, "{name} is untouched"); + } +} + +#[test] +fn ocr_retained_reviews_have_eight_document_cap_and_close_releases_slot() { + let dir = workdir("ocr-review-cap"); + let mut a = auto(&dir); + if ok(&mut a, "ocr_status", json!({}))["available"] != true { + eprintln!("skipped: OCR models not installed"); + return; + } + let mut docs = Vec::new(); + let mut handles = Vec::new(); + for _ in 0..9 { + let doc = ok(&mut a, "doc_create", json!({"from":"text", "text":"Already recognized text"}))["doc"].as_u64().unwrap(); + docs.push(doc); + } + for doc in docs.iter().take(8) { + handles.push(ok(&mut a, "ocr_words", json!({"doc":doc,"retain_review":true}))["review"].as_u64().unwrap()); + } + let error = a.call("ocr_words", &json!({"doc":docs[8],"retain_review":true})).unwrap_err().to_string(); + assert!(error.contains("at most 8"), "{error}"); + let replacement = ok(&mut a, "ocr_words", json!({"doc":docs[0],"retain_review":true}))["review"].as_u64().unwrap(); + assert_ne!(replacement, handles[0]); + assert!(a.call("ocr_review_apply", &json!({"doc":docs[0],"review":handles[0],"discard":true})).is_err()); + ok(&mut a, "doc_close", json!({"doc":docs[0],"discard_changes":true})); + assert!(a.call("ocr_review_apply", &json!({"doc":docs[0],"review":replacement})).is_err()); + let final_handle = ok(&mut a, "ocr_words", json!({"doc":docs[8],"retain_review":true}))["review"].as_u64().unwrap(); + ok(&mut a, "ocr_review_apply", json!({"doc":docs[8],"review":final_handle,"discard":true})); +} + #[test] fn editor_crop_group_move_and_arrange_survive_added_item_deletion_through_tools() { let dir = workdir("editor-crop-group-arrange"); @@ -10832,3 +11816,49 @@ fn a_bad_bookmark_tree_is_refused_whole_and_names_the_node() { assert!(!out.exists()); assert_eq!(ok(&mut a, "bookmark_list", json!({ "doc": doc }))["bookmarks"], json!([])); } + +/// Copy and paste comments between documents through the tools: the copies carry their replies, +/// land on the asked-for page under their own names (a second paste gives a second set), and a +/// plain text is refused. +#[test] +fn comments_copy_and_paste_between_documents_through_tools() { + let dir = workdir("comments-clipboard"); + let mut a = auto(&dir); + let src = ok(&mut a, "doc_open", json!({ "path": "a.pdf" }))["doc"].as_u64().unwrap(); + ok(&mut a, "comment_add", json!({ "doc": src, "page": 2, "type": "note", "at": [30, 30], "contents": "Please review", "author": "Ada" })); + ok(&mut a, "comment_add", json!({ "doc": src, "page": 2, "type": "rectangle", "rect": [20, 20, 80, 60], "contents": "Box" })); + ok(&mut a, "comment_reply", json!({ "doc": src, "page": 2, "index": 1, "text": "Done", "author": "Bob" })); + // Positions as comment_list reports them (a note's pop-up takes a position of its own). + let listed = ok(&mut a, "comment_list", json!({ "doc": src, "page": 2 })); + let pairs: Vec = listed["comments"].as_array().unwrap().iter().map(|c| json!([c["page"], c["index"]])).collect(); + assert_eq!(pairs.len(), 2, "{listed}"); + let copied = ok(&mut a, "comments_copy", json!({ "doc": src, "comments": pairs })); + assert_eq!(copied["comments"], 2); + let xfdf = copied["xfdf"].as_str().unwrap().to_owned(); + assert!(xfdf.contains("inreplyto=") && xfdf.contains("> = + placed["comments"].as_array().unwrap().iter().map(|c| c["rect"].as_array().unwrap().iter().map(|v| v.as_f64().unwrap()).collect()).collect(); + let (x0, y0, x1, y1) = + rects.iter().fold((f64::MAX, f64::MAX, f64::MIN, f64::MIN), |(a, b, c, d), r| (a.min(r[0]), b.min(r[1]), c.max(r[2]), d.max(r[3]))); + assert!(((x0 + x1) / 2.0 - 100.0).abs() < 1.0 && ((y0 + y1) / 2.0 - 150.0).abs() < 1.0, "centred at [100, 150]: {rects:?}"); + assert!(matches!(a.call("comments_paste", &json!({ "doc": dst, "page": 1, "xfdf": "hello" })), Err(ToolError::InvalidArgs(_)))); + assert!(a.call("comments_copy", &json!({ "doc": src, "comments": [[9, 9]] })).is_err(), "no such comment"); + assert!(matches!(a.call("comments_copy", &json!({ "doc": src, "comments": [[2]] })), Err(ToolError::InvalidArgs(_)))); + assert_eq!(ok(&mut a, "comment_list", json!({ "doc": src }))["comments"].as_array().unwrap().len(), 2, "the source is untouched"); +} diff --git a/crates/automation/tests/it/batch.rs b/crates/automation/tests/it/batch.rs index af5e0c1272..8b7650fd3f 100644 --- a/crates/automation/tests/it/batch.rs +++ b/crates/automation/tests/it/batch.rs @@ -238,3 +238,61 @@ fn mcp_batch_errors_keep_the_structured_per_file_report() { assert_eq!(report["result"]["isError"], true, "{report}"); assert_eq!(report["result"]["structuredContent"]["failed"], 1); } + +#[test] +fn dry_run_planned_files_are_not_counted_as_skipped() { + let dir = tempfile::tempdir().unwrap(); + std::fs::create_dir_all(dir.path().join("input/sub")).unwrap(); + std::fs::create_dir_all(dir.path().join("out")).unwrap(); + let original = pdf(); + std::fs::write(dir.path().join("input/a.pdf"), &original).unwrap(); + std::fs::write(dir.path().join("input/sub/a.pdf"), &original).unwrap(); + std::fs::write(dir.path().join("out/a.pdf"), b"precious").unwrap(); + let mut auto = Automation::new().with_root(dir.path()).unwrap(); + let report = result(&mut auto, json!({"paths":["input","input/sub"],"steps":["optimize"],"out_dir":"out","dry_run":true})); + assert_eq!(report["dry_run"], true, "{report}"); + assert_eq!(report["completed"], 0, "{report}"); + assert_eq!(report["failed"], 0, "{report}"); + assert_eq!(report["skipped"], 0, "planned files are not skipped: {report}"); + let files = report["files"].as_array().unwrap(); + assert_eq!(files.len(), 2, "{report}"); + assert!(files.iter().all(|file| file["status"] == "planned"), "{report}"); + assert!(files.iter().all(|file| file["steps"] == json!(["optimize"])), "planned files list the ordered steps: {report}"); + assert!(files[0]["output"].as_str().unwrap().ends_with("out/a (2).pdf"), "existing output gets the publish collision name: {report}"); + assert!(files[1]["output"].as_str().unwrap().ends_with("out/a (3).pdf"), "later planned files reserve their names: {report}"); + assert_eq!(std::fs::read(dir.path().join("out/a.pdf")).unwrap(), b"precious"); + assert!(!dir.path().join("out/a (2).pdf").exists(), "dry run writes nothing: {report}"); + #[cfg(unix)] + { + // An output subfolder that resolves outside out_dir is a per-file error: + // it counts as failed, honors stop_on_error, and later files are skipped. + for outside_root in [false, true] { + let dir = tempfile::tempdir().unwrap(); + let outside = tempfile::tempdir().unwrap(); + std::fs::create_dir_all(dir.path().join("input/sub")).unwrap(); + std::fs::create_dir_all(dir.path().join("out")).unwrap(); + std::fs::write(dir.path().join("input/a.pdf"), pdf()).unwrap(); + std::fs::write(dir.path().join("input/sub/page.pdf"), pdf()).unwrap(); + std::fs::write(dir.path().join("input/z.pdf"), pdf()).unwrap(); + let target = if outside_root { outside.path().to_path_buf() } else { dir.path().join("outside") }; + if !outside_root { + std::fs::create_dir(&target).unwrap(); + } + std::os::unix::fs::symlink(&target, dir.path().join("out/sub")).unwrap(); + let mut auto = Automation::new().with_root(dir.path()).unwrap(); + let report = result( + &mut auto, + json!({"paths":["input"],"steps":["optimize"],"out_dir":"out","recursive":true,"dry_run":true,"stop_on_error":true}), + ); + assert_eq!(report["failed"], 1, "preview target failure is per-file: {report}"); + assert_eq!(report["stopped"], true, "{report}"); + assert_eq!(report["skipped"], 1, "only the unprocessed file is skipped: {report}"); + let files = report["files"].as_array().unwrap(); + assert_eq!(files.len(), 3, "{report}"); + assert_eq!(files[0]["status"], "planned", "{report}"); + assert_eq!(files[1]["status"], "error", "{report}"); + assert_eq!(files[2]["status"], "skipped", "stop_on_error leaves later files unplanned: {report}"); + assert!(!dir.path().join("out/a.pdf").exists(), "dry run writes nothing: {report}"); + } + } +} diff --git a/crates/automation/tests/it/batch_failures.rs b/crates/automation/tests/it/batch_failures.rs new file mode 100644 index 0000000000..f993d85eab --- /dev/null +++ b/crates/automation/tests/it/batch_failures.rs @@ -0,0 +1,89 @@ +//! A batch run that fails a file publishes only the completed outputs, and a +//! publish the file system refuses publishes nothing. + +use pdfcraft_automation::{Automation, Content}; +use pdfcraft_engine::Session; +use serde_json::{Value, json}; + +fn result(auto: &mut Automation, args: Value) -> Value { + match auto.call("doc_batch", &args).unwrap().remove(0) { + Content::Json(value) => value, + _ => panic!("expected a report"), + } +} + +fn pdf() -> Vec { + Session::new().create_from_text("Original", "Original text").unwrap().as_ref().clone() +} + +/// Sets a folder's permission bits. +#[cfg(unix)] +fn set_mode(path: &std::path::Path, mode: u32) { + use std::os::unix::fs::PermissionsExt; + std::fs::set_permissions(path, std::fs::Permissions::from_mode(mode)).unwrap(); +} + +/// Puts back the write permission the temporary folder needs before it is removed. +#[cfg(unix)] +struct RestoreMode(std::path::PathBuf); + +#[cfg(unix)] +impl Drop for RestoreMode { + fn drop(&mut self) { + use std::os::unix::fs::PermissionsExt; + let _ = std::fs::set_permissions(&self.0, std::fs::Permissions::from_mode(0o755)); + } +} + +#[test] +fn failed_inputs_publish_only_completed_outputs() { + let dir = tempfile::tempdir().unwrap(); + std::fs::create_dir(dir.path().join("input")).unwrap(); + std::fs::write(dir.path().join("input/good.pdf"), pdf()).unwrap(); + std::fs::write(dir.path().join("input/bad.pdf"), "not a pdf").unwrap(); + let mut auto = Automation::new().with_root(dir.path()).unwrap(); + let report = result(&mut auto, json!({"paths":["input"],"steps":["optimize"],"out_dir":"out","recursive":false})); + assert_eq!(report["completed"], 1, "{report}"); + assert_eq!(report["failed"], 1, "{report}"); + let files = report["files"].as_array().unwrap(); + assert_eq!(files.len(), 2, "{report}"); + let bad = files.iter().find(|file| file["path"].as_str().is_some_and(|path| path.ends_with("bad.pdf"))).unwrap(); + assert_eq!(bad["status"], "error", "{report}"); + assert!(bad["output"].is_null(), "a failed file reports no output: {report}"); + let names: Vec = + std::fs::read_dir(dir.path().join("out")).unwrap().map(|entry| entry.unwrap().file_name().to_string_lossy().into_owned()).collect(); + // Publish stages its bytes under a dot-prefixed name in the output folder, so + // no entry carrying that prefix may survive the run. + for name in &names { + assert!(!name.starts_with('.'), "temporary name left behind: {name} ({names:?})"); + } + assert_eq!(names, vec!["good.pdf".to_string()], "only the completed output is published"); +} + +#[cfg(unix)] +#[test] +fn read_only_output_folder_publishes_nothing() { + let dir = tempfile::tempdir().unwrap(); + std::fs::create_dir(dir.path().join("input")).unwrap(); + std::fs::write(dir.path().join("input/good.pdf"), pdf()).unwrap(); + let out = dir.path().join("out"); + std::fs::create_dir(&out).unwrap(); + set_mode(&out, 0o555); + let _restore = RestoreMode(out.clone()); + // A root process ignores the mode bits, and then the assertions below would + // pass without testing the refusal. Fail loudly instead of skipping. + assert!(std::fs::write(out.join("probe"), b"").is_err(), "run as a non-root user: the read-only output folder accepted a new file"); + let mut auto = Automation::new().with_root(dir.path()).unwrap(); + let report = result(&mut auto, json!({"paths":["input"],"steps":["optimize"],"out_dir":"out","recursive":false})); + assert_eq!(report["completed"], 0, "{report}"); + assert_eq!(report["failed"], 1, "{report}"); + let files = report["files"].as_array().unwrap(); + assert_eq!(files.len(), 1, "{report}"); + // Publish cannot create its staging file in a folder it may not write, so + // the entry carries the system's error and no output. + assert_eq!(files[0]["status"], "error", "{report}"); + assert!(files[0]["output"].is_null(), "a refused publish reports no output: {report}"); + let error = files[0]["error"].as_str().unwrap(); + assert!(!error.is_empty(), "{report}"); + assert_eq!(std::fs::read_dir(&out).unwrap().count(), 0, "the refused publish writes nothing into the read-only folder: {report}"); +} diff --git a/crates/automation/tests/it/batch_secrets.rs b/crates/automation/tests/it/batch_secrets.rs new file mode 100644 index 0000000000..08223f0955 --- /dev/null +++ b/crates/automation/tests/it/batch_secrets.rs @@ -0,0 +1,84 @@ +//! Tool results and errors from the folder tools carry no known test password. +//! +//! The passwords are set on the document and passed to the tool, and must never come back out: a +//! result that echoes one has leaked it into logs, transcripts and MCP callers. + +use pdfcraft_automation::{Automation, Content}; +use pdfcraft_engine::{Changes, Edit, Protection, Session}; +use serde_json::{Value, json}; + +/// The known test passwords; neither may appear in a result or an error. +const OPEN_PASSWORD: &str = "PLANT-OPEN-5f2c9a"; +const OWNER_PASSWORD: &str = "PLANT-OWNER-71de0b"; + +/// A one-page PDF locked with the known test passwords. +/// +/// The open password is the only way in. The batch bates tool rewrites page content, and +/// `Changes::None` forbids that, so this fixture permits every change except extracting pages; +/// the restrictions stay real, since the open password never lifts them. +fn protected_pdf() -> Vec { + let mut session = Session::new(); + let bytes = session.create_from_text("Batch secrets", "Planted password test").unwrap(); + let id = session.open("locked.pdf", None, bytes, None).unwrap(); + session + .apply( + id, + Edit::Protect(Protection { + open_password: Some(OPEN_PASSWORD.into()), + permissions_password: Some(OWNER_PASSWORD.into()), + changes: Changes::AnyExceptExtract, + ..Default::default() + }), + ) + .unwrap(); + session.save_bytes(id).unwrap().as_ref().clone() +} + +fn json_result(a: &mut Automation, tool: &str, args: Value) -> Value { + match a.call(tool, &args) { + Ok(mut content) => match content.remove(0) { + Content::Json(value) => value, + other => panic!("{tool}: expected JSON, got {other:?}"), + }, + Err(error) => panic!("{tool} {args}: {error}"), + } +} + +#[test] +fn results_and_errors_hold_no_planted_password_for_bates_or_batch() { + let dir = tempfile::tempdir().unwrap(); + std::fs::write(dir.path().join("locked.pdf"), protected_pdf()).unwrap(); + let mut a = Automation::new().with_root(dir.path()).unwrap(); + + // The right open password: numbering succeeds and reports the numbers only. + let numbered = + json_result(&mut a, "doc_bates_multi", json!({"files":[{"input":"locked.pdf","output":"locked-numbered.pdf","password":OPEN_PASSWORD}]})); + assert_eq!(numbered["completed"], 1, "{numbered}"); + assert_eq!(numbered["files"][0]["status"], "ok", "{numbered}"); + // The report carries the per-file entry the Bates tool builds, so a field added to that entry + // lands in the text checked below. + assert_eq!(numbered["files"][0]["first"], 1, "{numbered}"); + assert!(numbered["files"][0]["output"].as_str().is_some_and(|path| path.ends_with("locked-numbered.pdf")), "{numbered}"); + assert!(dir.path().join("locked-numbered.pdf").exists(), "the numbered copy is written"); + + // The wrong open password: the tool refuses the file with an error. + let refused = match a + .call("doc_bates_multi", &json!({"files":[{"input":"locked.pdf","output":"locked-refused.pdf","password":"not-the-open-password"}]})) + { + Err(error) => error.to_string(), + Ok(value) => panic!("a wrong open password must be refused: {value:?}"), + }; + + // The folder job refuses the encrypted file without a password, in its per-file report. + let batch = json_result(&mut a, "doc_batch", json!({"paths":["locked.pdf"],"steps":["optimize"],"out_dir":"out"})); + assert_eq!(batch["failed"], 1, "{batch}"); + assert_eq!(batch["files"][0]["status"], "error", "{batch}"); + assert!(batch["files"][0]["error"].as_str().is_some_and(|text| !text.is_empty()), "{batch}"); + assert!(!dir.path().join("out/locked.pdf").exists(), "a refused file publishes nothing"); + + for report in [serde_json::to_string(&numbered).unwrap(), refused, serde_json::to_string(&batch).unwrap()] { + for secret in [OPEN_PASSWORD, OWNER_PASSWORD] { + assert!(!report.contains(secret), "a result or error echoed a planted password: {report}"); + } + } +} diff --git a/crates/automation/tests/it/main.rs b/crates/automation/tests/it/main.rs index 3122fe5825..92e54c99a6 100644 --- a/crates/automation/tests/it/main.rs +++ b/crates/automation/tests/it/main.rs @@ -1,10 +1,13 @@ //! The crate's integration tests, linked into one test binary. +mod action_failures; mod attachment_key; mod automation; mod automation_roots; mod backdrop; mod batch; +mod batch_failures; +mod batch_secrets; mod button_caption; mod form_bulk; mod hostile_args; @@ -14,3 +17,4 @@ mod optimize_content_boundaries; mod redact_after_stray_q_form; mod redact_text_after_q; mod render_warnings; +mod unreadable_objects; diff --git a/crates/automation/tests/it/unreadable_objects.rs b/crates/automation/tests/it/unreadable_objects.rs new file mode 100644 index 0000000000..f19a19078a --- /dev/null +++ b/crates/automation/tests/it/unreadable_objects.rs @@ -0,0 +1,64 @@ +//! `doc_info` lists the objects of a file that could not be read: each reads as null, so the file +//! opens, but what it held is lost and nothing was repaired. + +use pdfcraft_automation::{Automation, Content}; +use serde_json::{Value, json}; + +/// A one-page PDF whose document information dictionary (object 4) is `info`. +fn with_info(info: &str) -> Vec { + let bodies = [ + "<< /Type /Catalog /Pages 2 0 R >>", + "<< /Type /Pages /Kids [3 0 R] /Count 1 >>", + "<< /Type /Page /Parent 2 0 R /MediaBox [0 0 200 200] >>", + info, + ]; + let mut out = b"%PDF-1.7\n".to_vec(); + let mut offsets = Vec::new(); + for (i, body) in bodies.iter().enumerate() { + offsets.push(out.len()); + out.extend_from_slice(format!("{} 0 obj\n{body}\nendobj\n", i + 1).as_bytes()); + } + let xref = out.len(); + out.extend_from_slice(format!("xref\n0 {}\n0000000000 65535 f \n", bodies.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 /Info 4 0 R >>\nstartxref\n{xref}\n%%EOF\n", bodies.len() + 1).as_bytes()); + out +} + +fn info_of(a: &mut Automation, path: &str) -> Value { + let doc = match a.call("doc_open", &json!({ "path": path })).unwrap().remove(0) { + Content::Json(v) => v["doc"].as_u64().unwrap(), + other => panic!("expected JSON: {other:?}"), + }; + match a.call("doc_info", &json!({ "doc": doc })).unwrap().remove(0) { + Content::Json(v) => v, + other => panic!("expected JSON: {other:?}"), + } +} + +/// An unparseable `/Info` is listed with its number and why, the rest of the file reads, and +/// nothing is reported as repaired. +#[test] +fn doc_info_lists_an_object_that_could_not_be_read() { + let dir = std::env::temp_dir().join(format!("pdfcraft-unreadable-objects-{}", std::process::id())); + let _ = std::fs::remove_dir_all(&dir); + std::fs::create_dir_all(&dir).unwrap(); + std::fs::write(dir.join("broken.pdf"), with_info("<< /Title (Report) /Author ) >>")).unwrap(); + std::fs::write(dir.join("sound.pdf"), with_info("<< /Title (Report) >>")).unwrap(); + let mut a = Automation::new().with_root(&dir).unwrap(); + + let info = info_of(&mut a, "broken.pdf"); + let lines = info["unreadable_objects"].as_array().unwrap(); + assert_eq!(lines.len(), 1, "{info}"); + let line = lines[0].as_str().unwrap(); + assert!(line.starts_with("object 4 0 could not be read: syntax error"), "{line}"); + assert_eq!(info["repairs"], json!([]), "nothing was repaired"); + assert_eq!(info["pages"].as_array().unwrap().len(), 1, "the rest of the file reads"); + + let info = info_of(&mut a, "sound.pdf"); + assert_eq!(info["unreadable_objects"], json!([]), "{info}"); + assert_eq!(info["title"], "Report"); + let _ = std::fs::remove_dir_all(dir); +} diff --git a/crates/automation/tests/pattern_redaction.rs b/crates/automation/tests/pattern_redaction.rs new file mode 100644 index 0000000000..667779cef6 --- /dev/null +++ b/crates/automation/tests/pattern_redaction.rs @@ -0,0 +1,146 @@ +//! Rectangle redaction must not report a pattern-cell secret safely removed (#3647). + +use std::sync::Arc; + +use pdfcraft_automation::{Automation, Content}; +use pdfcraft_cos::{Dict, Document, Object, Stream}; +use pdfcraft_engine::DocId; +use serde_json::{Value, json}; + +fn tool(automation: &mut Automation, name: &str, args: Value) -> Value { + match automation.call(name, &args).unwrap().remove(0) { + Content::Json(value) => value, + other => panic!("expected JSON: {other:?}"), + } +} + +/// `retained`: paint with the pattern once more, away from the mark (x 290..340 lies right of it). +/// A path the mark hits is removed whole (F-008) and a pattern nothing surviving paints with is +/// pruned, so only a pattern that some surviving paint still uses reaches the guard. +fn fixture(cell: &[u8], partial: bool, compressed: bool, retained: bool) -> Vec { + let mut pattern = Dict::from_iter([ + (b"Type".to_vec(), Object::name("Pattern")), + (b"PatternType".to_vec(), Object::Int(1)), + (b"PaintType".to_vec(), Object::Int(1)), + (b"TilingType".to_vec(), Object::Int(1)), + (b"BBox".to_vec(), Object::Array(vec![0.into(), 0.into(), 500.into(), 300.into()])), + (b"XStep".to_vec(), Object::Int(500)), + (b"YStep".to_vec(), Object::Int(300)), + ]); + pattern.set( + b"Resources".to_vec(), + Object::Dict(Dict::from_iter([( + b"Font".to_vec(), + Object::Dict(Dict::from_iter([(b"F1".to_vec(), Object::Ref(pdfcraft_cos::ObjRef::new(4, 0)))])), + )])), + ); + let width = if partial { 400 } else { 170 }; + let survivor = if retained { " 290 115 50 30 re f" } else { "" }; + let content = format!("BT /F1 20 Tf 40 250 Td (PUBLIC) Tj ET /Pattern cs /P0 scn 35 110 {width} 35 re f{survivor}"); + let mut page_stream = Vec::new(); + pdfcraft_cos::serialize(&Object::Stream(Stream::from_raw(Dict::new(), content.into_bytes())), &mut page_stream); + let mut pattern_stream = Vec::new(); + let stream = if compressed { Stream::flate(pattern, cell) } else { Stream::from_raw(pattern, cell.to_vec()) }; + pdfcraft_cos::serialize(&Object::Stream(stream), &mut pattern_stream); + let objects = [ + b"<< /Type /Catalog /Pages 2 0 R >>".to_vec(), + b"<< /Type /Pages /Kids [3 0 R] /Count 1 >>".to_vec(), + b"<< /Type /Page /Parent 2 0 R /MediaBox [0 0 500 300] /Contents 5 0 R /Resources << /Font << /F1 4 0 R >> /Pattern << /P0 6 0 R >> >> >>" + .to_vec(), + b"<< /Type /Font /Subtype /Type1 /BaseFont /Helvetica /Encoding /WinAnsiEncoding >>".to_vec(), + page_stream, + pattern_stream, + ]; + let mut bytes = b"%PDF-1.7\n".to_vec(); + let mut offsets = Vec::new(); + for (index, object) in objects.iter().enumerate() { + offsets.push(bytes.len()); + bytes.extend(format!("{} 0 obj\n", index + 1).as_bytes()); + bytes.extend(object); + bytes.extend(b"\nendobj\n"); + } + let xref = bytes.len(); + bytes.extend(format!("xref\n0 {}\n0000000000 65535 f \n", objects.len() + 1).as_bytes()); + for offset in offsets { + bytes.extend(format!("{offset:010} 00000 n \n").as_bytes()); + } + bytes.extend(format!("trailer\n<< /Size {} /Root 1 0 R >>\nstartxref\n{xref}\n%%EOF\n", objects.len() + 1).as_bytes()); + bytes +} + +fn saved_has_secret(bytes: Vec) -> bool { + let document = Document::open(Arc::new(bytes)).unwrap(); + document.object_numbers().into_iter().any(|num| { + let object = document.try_get(num).unwrap(); + matches!(&*object, Object::Stream(stream) if stream.decoded().unwrap().windows(10).any(|part| part == b"CELLSECRET")) + }) +} + +#[test] +fn pattern_redaction_tools_remove_or_refuse_without_leaking_or_changing_undo() { + let dir = tempfile::tempdir().unwrap(); + for (partial, retained) in [(false, false), (true, false), (true, true)] { + for compressed in [false, true] { + let cell = b"BT /F1 20 Tf 40 120 Td (CELLSECRET) Tj ET BT /F1 20 Tf 300 120 Td (SAFE) Tj ET"; + let bytes = fixture(cell, partial, compressed, retained); + assert!(saved_has_secret(bytes.clone())); + std::fs::write(dir.path().join("input.pdf"), bytes).unwrap(); + let mut automation = Automation::new().with_root(dir.path()).unwrap().with_clock(|| 1_700_000_000); + let id = tool(&mut automation, "doc_open", json!({"path": "input.pdf"}))["doc"].as_u64().unwrap(); + tool(&mut automation, "redact_mark", json!({"doc": id, "page": 1, "rect": [30, 150, 215, 195]})); + let before = automation.session().get(DocId(id)).unwrap().bytes.clone(); + let pixels = automation.render_pixels(id, 1, 1.0).unwrap(); + match automation.call("redact_apply", &json!({"doc": id})) { + Ok(_) => { + assert!(!retained, "a text-bearing cell still in use must not be reported safe (partial: {partial})"); + tool(&mut automation, "doc_save", json!({"doc": id, "path": "redacted.pdf"})); + assert!( + !saved_has_secret(std::fs::read(dir.path().join("redacted.pdf")).unwrap()), + "successful apply/save left the pattern-cell text recoverable" + ); + } + Err(error) => { + assert!(retained, "a pattern nothing surviving paints with should apply (partial: {partial}): {error}"); + assert!(error.to_string().contains("tiling pattern"), "{error}"); + assert!(!error.to_string().contains("CELLSECRET")); + let document = automation.session().get(DocId(id)).unwrap(); + assert_eq!(document.bytes, before); + assert_eq!(document.redaction_marks(), 1); + assert_eq!(document.can_undo(), Some("Add redaction mark")); + assert_eq!(automation.render_pixels(id, 1, 1.0).unwrap(), pixels); + tool(&mut automation, "edit_undo", json!({"doc": id})); + assert_eq!(automation.session().get(DocId(id)).unwrap().redaction_marks(), 0); + } + } + } + } +} + +#[test] +fn pattern_redaction_vector_control_saves_reopens_and_preserves_outside_pixels() { + let dir = tempfile::tempdir().unwrap(); + // The guard's control: the cell is plain vectors and a paint outside the mark still uses it, + // so it is inspected and kept, not refused, and what that paint draws is unchanged. + let bytes = fixture(b"0.2 0.4 0.6 rg 40 120 15 15 re f 300 120 30 20 re f", true, true, true); + std::fs::write(dir.path().join("vectors.pdf"), bytes).unwrap(); + let mut automation = Automation::new().with_root(dir.path()).unwrap().with_clock(|| 1_700_000_000); + let id = tool(&mut automation, "doc_open", json!({"path": "vectors.pdf"}))["doc"].as_u64().unwrap(); + let (width, height, original) = automation.render_pixels(id, 1, 1.0).unwrap(); + tool(&mut automation, "redact_mark", json!({"doc": id, "page": 1, "rect": [30, 150, 215, 195]})); + let applied = tool(&mut automation, "redact_apply", json!({"doc": id})); + assert_eq!(applied["applied"], 1); + let save = tool(&mut automation, "doc_save", json!({"doc": id, "path": "vectors-redacted.pdf"})); + assert_eq!(save["incremental"], false); + let reopened = tool(&mut automation, "doc_open", json!({"path": "vectors-redacted.pdf"}))["doc"].as_u64().unwrap(); + let (new_width, new_height, actual) = automation.render_pixels(reopened, 1, 1.0).unwrap(); + assert_eq!((new_width, new_height), (width, height)); + for (index, (before, after)) in original.as_chunks::<4>().0.iter().zip(actual.as_chunks::<4>().0).enumerate() { + let (x, y) = (index % width as usize, index / width as usize); + if x >= 280 { + assert_eq!(before, after, "unmarked pattern pixels changed at {x},{y}"); + } + if (35..205).contains(&x) && (155..190).contains(&y) { + assert_eq!(after, &[0, 0, 0, 255], "marked interior must be black"); + } + } +} diff --git a/crates/compare/src/lib.rs b/crates/compare/src/lib.rs index 91245cbc21..26a50eaf71 100644 --- a/crates/compare/src/lib.rs +++ b/crates/compare/src/lib.rs @@ -41,6 +41,8 @@ pub struct Side { /// The page the change is on (for a pure insertion or deletion, where the other side's /// words would have been). pub page: usize, + /// The page its last word is on: words changed across a page break are one change. + pub last_page: usize, pub rects: Vec<[f64; 4]>, /// For an empty side (the other side's words were inserted or deleted): the box of the /// word next to where they would be. @@ -245,6 +247,7 @@ fn side(words: &[&Word], neighbour: Option<&Word>) -> Side { Side { text: words.iter().map(|w| w.text.as_str()).collect::>().join(" "), page: words.first().or(neighbour.as_ref()).map_or(0, |w| w.page), + last_page: words.last().or(neighbour.as_ref()).map_or(0, |w| w.page), rects: rects(words), near: if words.is_empty() { neighbour.map(|w| w.rect) } else { None }, } @@ -349,6 +352,17 @@ mod tests { assert_eq!(c.count(Kind::Inserted), 2); } + #[test] + fn a_change_across_a_page_break_knows_both_pages() { + let mut old = words("alpha beta", 0); + old.extend(words("gamma delta", 1)); + let mut new = words("alpha one", 0); + new.extend(words("two delta", 1)); + let c = compare(&old, &new); + assert_eq!(c.changes.len(), 1); + assert_eq!((c.changes[0].new.page, c.changes[0].new.last_page), (0, 1)); + } + #[test] fn deletions_across_pages_keep_their_pages() { let mut old = words("alpha beta gamma", 0); diff --git a/crates/cos/Cargo.toml b/crates/cos/Cargo.toml index a2fb3f4c4e..0bf2e894d2 100644 --- a/crates/cos/Cargo.toml +++ b/crates/cos/Cargo.toml @@ -15,6 +15,13 @@ thiserror = { workspace = true } # PDF date strings (`pdf_date`) go through chrono (no hand-rolled calendar code). chrono = { workspace = true } +# On the web, a rewrite's fresh file identifier takes its entropy from the browser +# (`crypto.getRandomValues`). Both crates are already in the dependency tree of the web shell +# (`js-sys` 0.3 / `wasm-bindgen` 0.2); native builds compile neither. +[target.'cfg(target_arch = "wasm32")'.dependencies] +js-sys = "0.3" +wasm-bindgen = "0.2" + [dev-dependencies] pdfcraft-oracle = { workspace = true } pdfcraft-testkit = { workspace = true } diff --git a/crates/cos/README.md b/crates/cos/README.md index 7b576f293f..9f5fb56725 100644 --- a/crates/cos/README.md +++ b/crates/cos/README.md @@ -53,7 +53,20 @@ another. Edits never touch the original bytes. - **Every cross-reference form:** classic tables with their quirky subsections, cross-reference streams, hybrid-reference files (`/XRefStm`), and object streams. - **Repair.** A file whose xref is wrong or missing is reconstructed by scanning for `obj` - headers. Repairs are *recorded*, never silent, so the UI can say the file was damaged. + headers. Repairs are *recorded*, never silent, so the UI can say the file was damaged. A live + in-file reference may match either its xref generation or a same-number object header at + that indexed offset; a missing, free, or neither-matching slot still resolves to null. + Header probes inspect at most 128 bytes at the indexed and header-relative offsets, without + parsing object bodies. On open, disagreements in retained xref revisions are recorded once + per object, up to 256 objects plus an omitted-details summary. This diagnostic scan does + not expand compact xref ranges; the winning xref entry remains authoritative for free + slots. Compressed objects require generation zero. Explicit `set` overlays accept only the + supplied generation; `set_existing` and `update_dict` retain both accepted generations of a + damaged live slot, including through snapshots, and require full rewrite. + `accepted_generations(num)` lists the generations a slot accepts, so code comparing two + revisions can tell whether a reference still reaches the same slot. Headers beyond + this bounded probe are not additionally recovered. Materialized primary and hybrid rows are + diagnosed before folding, so a newer row does not hide a retained disagreement. - **Tolerant, never fatal.** The lexer works on a byte slice and a position; it allocates nothing for skipped data, bounds-checks every index, and caps nesting depth. Malformed input yields `CosError`, never a panic — this crate is the first thing a hostile file meets. Exhausted xref entries are skipped with a repair log; exhausted /Size hints allocate unused numbers without overflowing or replacing existing objects. @@ -66,14 +79,25 @@ another. Edits never touch the original bytes. ## Writing -`write_incremental` appends only the edited objects, a cross-reference section **in the same -style as the file's last one**, and a trailer with `/Prev`. The original bytes are never modified, -which is what keeps a signature over an earlier revision valid. +`write_incremental` ordinarily appends only the edited objects, a cross-reference section **in +the same style as the file's last one**, and a trailer with `/Prev`, preserving the original +bytes and signatures over earlier revisions. It delegates to `write_full` when reconstruction, +encryption changes or `full_save_required()` demand a rewrite. Repair-aware edits to a live +xref/header generation disagreement use this fallback rather than append a contradictory row. `write_full` writes only what the trailer can reach, renumbered densely — the Save As and garbage-collecting path. By default (`SaveOptions::object_streams`) it packs non-stream objects into compressed object streams with a cross-reference stream (PDF 1.5+); turning that off writes a -classic table any reader accepts. +classic table any reader accepts. Both forms map accepted xref/header aliases to one output +object, retaining shared identity such as page-tree parent links; unrelated generations stay null. + +A full save keeps the file's `/ID` as it is, unless the document asked for a new identifier with +`Document::require_full_save_with_new_id` (redaction and sanitizing do). Then both strings are +regenerated, and `SaveOptions::id_entropy` can supply entropy for reproducible output (tests pin +output this way). Without it the identifier mixes in fresh entropy from the host — the browser's +`crypto.getRandomValues` on the web, the operating system's random hash seed on the desktop — so a +fresh copy of the program cannot reproduce it. An encrypted file keeps the first string, because its +key is derived from it. Dictionaries keep their key order and streams keep their *encoded* bytes, so rewritten objects stay recognisable in a diff and byte-stable when re-serialized. diff --git a/crates/cos/src/budget.rs b/crates/cos/src/budget.rs index 65b750e7b3..1a99885944 100644 --- a/crates/cos/src/budget.rs +++ b/crates/cos/src/budget.rs @@ -11,7 +11,9 @@ use crate::{CosError, Document, ObjRef, Object, Stream}; /// 16 ns, so this is 2 to 5 minutes, and about as long again for what an operation does with the /// pixels. A page scanned at 300 dpi takes about 17 million, 8.4 for its pixels and that again to /// decode them, so this alone reads about 1,000 of them. A byte into or out of a filter is a step -/// too, and takes less: 3 ns at most, or up to 19 ns through a predictor on samples of a bit. +/// too, and takes less: 3 ns at most, or up to 19 ns through a predictor on samples of a bit. A +/// byte Flate reads is [`pdfcraft_filters::FLATE_READ_WORK`] steps besides, since inflating blocks +/// that make nothing takes up to 21 ns a byte: about 7 ns a step. const IMAGE_WORK: u64 = 1 << 34; /// The steps each byte of the file adds to [`IMAGE_WORK`], so that a long scan is read whole: such a /// page pays for itself with about 2 KB of the file, about the smallest a page of text is stored @@ -38,9 +40,9 @@ const JPEG_WORK: u64 = 2; /// and images can share one, so reading it again for each has to count. const JPEG_READ_WORK: u64 = 4; -/// A stream decode within a byte bound, with the bytes its filter stages decoded: the data or -/// the error, each with that count. -type Decoder = fn(&Stream, usize) -> Result<(Vec, usize), (FilterError, usize)>; +/// A stream decode within a byte bound, with the bytes its filter stages decoded: the data and +/// whether it stopped at damage, or the error, each with that count. +type Decoder = fn(&Stream, usize) -> Result<(Vec, bool, usize), (FilterError, usize)>; /// What one operation over a document's images may still spend decoding them: exporting them, /// optimizing them, and storing LZW streams with Flate as it does, clearing them for redaction. @@ -263,45 +265,57 @@ impl DecodeBudget { } /// `stream` decoded like [`Stream::decoded`], charged to the allowance. Fails, without - /// decoding, once the allowance is spent. + /// decoding, once the allowance is spent. A stream damaged partway gives what decoded before + /// the damage, so code that writes the stream back reads it with + /// [`DecodeBudget::decode_with_damage`] instead. pub fn decode(&mut self, stream: &Stream) -> Result, CosError> { - self.charge(stream, usize::MAX, Stream::decoded_within_counted) + self.charge(stream, usize::MAX, Stream::decoded_within_counted).map(|(data, _)| data) } /// Like [`DecodeBudget::decode`], for a stream with a tighter bound of its own: decoding /// past `max` bytes is an error that charges `max`, the work it took to find out. pub fn decode_within(&mut self, stream: &Stream, max: usize) -> Result, CosError> { - self.charge(stream, max, Stream::decoded_within_counted) + self.charge(stream, max, Stream::decoded_within_counted).map(|(data, _)| data) + } + + /// [`DecodeBudget::decode_within`] (`usize::MAX` for no bound of its own), with the stream's + /// `/DecodeParms` given by reference read in `doc`, also saying whether the stream is damaged: + /// `true` when a filter stopped at corrupt data, so the bytes are only what decoded before it. + /// A stream written back from them loses everything after the damage, which other readers may + /// still read. + pub fn decode_with_damage(&mut self, doc: &Document, stream: &Stream, max: usize) -> Result<(Vec, bool), CosError> { + self.charge(&doc.decoding_view(stream), max, Stream::decoded_within_counted) } /// `stream` decoded like [`Stream::decoded_strict`] (any corruption is an error), charged to - /// the allowance. - pub fn decode_strict(&mut self, stream: &Stream) -> Result, CosError> { - self.charge(stream, usize::MAX, Stream::decoded_strict_within_counted) + /// the allowance, with its `/DecodeParms` given by reference read in `doc`. + pub fn decode_strict(&mut self, doc: &Document, stream: &Stream) -> Result, CosError> { + let strict: Decoder = |s, max| s.decoded_strict_within_counted(max).map(|(data, spent)| (data, false, spent)); + self.charge(&doc.decoding_view(stream), usize::MAX, strict).map(|(data, _)| data) } /// Decodes `stream` within `max` and the allowance, charging what every filter stage /// decoded: a stage's output counts even when a later stage shrinks it, and a corrupt stream /// pays for the bytes decoded before the error, so referencing a stream again and again /// spends the allowance by the work each decode does. - fn charge(&mut self, stream: &Stream, max: usize, decode: Decoder) -> Result, CosError> { + fn charge(&mut self, stream: &Stream, max: usize, decode: Decoder) -> Result<(Vec, bool), CosError> { if self.bytes == 0 && !stream.raw.is_empty() { return Err(CosError::Filter(FilterError::LimitExceeded(self.limit).to_string())); } if max < self.bytes { let result = decode(stream, max); let spent = match &result { - Ok((_, spent)) => *spent, + Ok((_, _, spent)) => *spent, Err((FilterError::LimitExceeded(_), _)) => max, Err((_, spent)) => *spent, }; self.bytes = self.bytes.saturating_sub(spent); - return result.map(|(data, _)| data).map_err(|(e, _)| CosError::Filter(e.to_string())); + return result.map(|(data, damaged, _)| (data, damaged)).map_err(|(e, _)| CosError::Filter(e.to_string())); } match decode(stream, self.bytes) { - Ok((data, spent)) => { + Ok((data, damaged, spent)) => { self.bytes = self.bytes.saturating_sub(spent); - Ok(data) + Ok((data, damaged)) } Err((FilterError::LimitExceeded(_), _)) => { self.bytes = 0; @@ -332,17 +346,24 @@ impl DecodeBudget { self.seen.insert(r) } - /// Each stream `contents` names, decoded against the allowance, in order. `contents` is a - /// page's `/Contents`: one stream, or an array whose non-stream entries are left out. - /// A stream that fails to decode, or arrives after the allowance is spent, is an `Err` in its - /// place, so the caller chooses between skipping it and giving up. + /// Each stream `contents` names, decoded against the allowance, in order, its `/DecodeParms` + /// given by reference read in `doc`. `contents` is a page's `/Contents`: one stream, or an + /// array whose non-stream entries are left out. A stream that fails to decode, or arrives + /// after the allowance is spent, is an `Err` in its place, so the caller chooses between + /// skipping it and giving up. pub fn decode_contents(&mut self, doc: &Document, contents: &Object) -> Vec, CosError>> { + self.decode_contents_with_damage(doc, contents).into_iter().map(|read| read.map(|(data, _)| data)).collect() + } + + /// [`DecodeBudget::decode_contents`], each stream also saying whether it is damaged partway + /// ([`DecodeBudget::decode_with_damage`], which reads `/DecodeParms` given by reference). + pub fn decode_contents_with_damage(&mut self, doc: &Document, contents: &Object) -> Vec, bool), CosError>> { match &*doc.resolve(contents) { - Object::Stream(s) => vec![self.decode(s)], + Object::Stream(s) => vec![self.decode_with_damage(doc, s, usize::MAX)], Object::Array(list) => list .iter() .filter_map(|entry| match &*doc.resolve(entry) { - Object::Stream(s) => Some(self.decode(s)), + Object::Stream(s) => Some(self.decode_with_damage(doc, s, usize::MAX)), _ => None, }) .collect(), @@ -367,6 +388,11 @@ mod image_tests { Stream::from_raw(dict, pdfcraft_filters::encode_jbig2_generic(&[0xFF; 4], 16, 2).unwrap()) } + /// What a Flate stage pays to read `n` bytes, besides what it makes. + fn read(n: usize) -> u64 { + pdfcraft_filters::FLATE_READ_WORK * n as u64 + } + /// Each image spends what it took from one allowance, and those past it are refused and /// counted, whatever their filters. What can't be decoded here costs nothing, and fails /// without being one of these. @@ -413,7 +439,7 @@ mod image_tests { let mut dict = Dict::new(); dict.set(b"Filter".to_vec(), Object::Array(vec![Object::name("FlateDecode"), Object::name("FlateDecode")])); let bomb = Stream::from_raw(dict, pdfcraft_filters::encode_flate(&inner)); - let cost = (bomb.raw.len() + inner.len() + samples.len()) as u64; + let cost = (bomb.raw.len() + inner.len() + samples.len()) as u64 + read(bomb.raw.len()) + read(inner.len()); let mut budget = ImageBudget::with_work(2 * cost + 1); for left in [cost + 1, 1] { assert_eq!(budget.decode(&doc, &bomb, 1 << 20).unwrap(), samples); @@ -442,17 +468,17 @@ mod image_tests { let image = behind(pdfcraft_filters::encode_flate(&alone.raw)); let mut budget = ImageBudget::with_work(u64::MAX); assert_eq!(budget.decode(&doc, &image, 1 << 20).unwrap(), samples); - assert_eq!(u64::MAX - budget.work_left(), decoding + (image.raw.len() + alone.raw.len()) as u64); + assert_eq!(u64::MAX - budget.work_left(), decoding + (image.raw.len() + alone.raw.len()) as u64 + read(image.raw.len())); // Past this image's limit: an error, with what finding out took paid and the rest left. let bomb = behind(pdfcraft_filters::encode_flate(&vec![0; 1 << 16])); let mut budget = ImageBudget::with_work(u64::MAX); assert!(budget.decode(&doc, &bomb, 1000).is_err()); - assert_eq!(u64::MAX - budget.work_left(), bomb.raw.len() as u64 + 1000); + assert_eq!(u64::MAX - budget.work_left(), bomb.raw.len() as u64 + read(bomb.raw.len()) + 1000); assert_eq!(budget.refused(), 0, "that image's limit isn't the run's"); // A small allowance is a limit too: it stops there, and the image is refused. - let mut budget = ImageBudget::with_work(bomb.raw.len() as u64 + 10); + let mut budget = ImageBudget::with_work(bomb.raw.len() as u64 + read(bomb.raw.len()) + 10); assert!(budget.decode(&doc, &bomb, 1 << 20).is_err()); assert_eq!((budget.work_left(), budget.refused()), (0, 1)); } @@ -492,7 +518,7 @@ mod image_tests { let doc = Document::open(std::sync::Arc::new(file)).unwrap(); let image = doc.get(doc.root().unwrap()).as_dict().unwrap().reference(b"Image").unwrap(); let s = stream(&doc, image); - let filters = (raw.len() + skipped.len()) as u64; + let filters = (raw.len() + skipped.len()) as u64 + read(raw.len()); assert_eq!(spent(&doc, &s), first, "the first read undoes them"); assert_eq!(spent(&doc, &s), first - filters, "kept"); @@ -507,7 +533,7 @@ mod image_tests { let image = jbig2(Some(Object::Dict(parms))); let mut budget = ImageBudget::with_work(u64::MAX); assert!(budget.decode(&doc, &image, 1 << 20).unwrap_err().to_string().contains("globals")); - assert_eq!(u64::MAX - budget.work_left(), (over.len() + crate::MAX_JBIG2_GLOBALS) as u64); + assert_eq!(u64::MAX - budget.work_left(), (over.len() + crate::MAX_JBIG2_GLOBALS) as u64 + read(over.len())); assert_eq!(budget.refused(), 0); } @@ -528,7 +554,7 @@ mod image_tests { dict.set(b"DecodeParms".to_vec(), Object::Array(vec![Object::Null, Object::Dict(parms)])); let image = Stream::from_raw(dict, pdfcraft_filters::encode_flate(&coded)); let pixels = u64::from(w) * u64::from(h); - let cost = (image.raw.len() + coded.len() + 4 * coded.len() + 512 * h as usize) as u64 + pixels; + let cost = (image.raw.len() + coded.len() + 4 * coded.len() + 512 * h as usize) as u64 + read(image.raw.len()) + pixels; let mut budget = ImageBudget::with_work(cost); assert_eq!(budget.decode(&doc, &image, 1 << 20).unwrap().len(), 512 * h as usize); assert_eq!(budget.work_left(), 0, "exactly that"); @@ -553,7 +579,7 @@ mod image_tests { }; let rows = vec![0xFFu8; 512 * 1024]; let flate = blank(Some("FlateDecode"), pdfcraft_filters::encode_flate(&rows)); - let cost = (flate.raw.len() + rows.len()) as u64 + 4096 * 1024; + let cost = (flate.raw.len() + rows.len()) as u64 + read(flate.raw.len()) + 4096 * 1024; let mut budget = ImageBudget::with_work(cost); assert_eq!(budget.decode(&doc, &flate, 1 << 24).unwrap(), rows); assert_eq!((budget.work_left(), budget.refused()), (0, 0), "exactly that"); @@ -590,6 +616,36 @@ mod image_tests { assert_eq!((budget.work_left(), budget.refused()), (0, 1)); } + /// What Flate reads is priced for blocks that make nothing, and an image an encoder made pays + /// little for it: a scan-like picture stored in under half its size costs no more than half + /// again its bytes, samples and pixels. Redaction decodes a picture once for each page that draws it, so + /// a letterhead on hundreds of pages has to fit about as often as it did unpriced (here, at + /// most half again the cost). + #[test] + fn an_image_an_encoder_made_pays_little_for_its_reading() { + let doc = Document::new_empty(); + let mut seed = 0x2545_F491_4F6C_DD1Du64; + let samples: Vec = (0..256 * 256usize) + .map(|i| { + seed ^= seed << 13; + seed ^= seed >> 7; + seed ^= seed << 17; + ((i % 256) as u8 / 16) ^ (seed as u8 & 3) + }) + .collect(); + let mut dict = Dict::new(); + dict.set(b"Width".to_vec(), Object::Int(256)); + dict.set(b"Height".to_vec(), Object::Int(256)); + let image = Stream::flate(dict, &samples); + assert!(image.raw.len() * 2 < samples.len(), "stored smaller: {}", image.raw.len()); + let unpriced = (image.raw.len() + samples.len()) as u64 + 256 * 256; + let mut budget = ImageBudget::with_work(u64::MAX); + budget.decode(&doc, &image, 1 << 20).unwrap(); + let paid = u64::MAX - budget.work_left(); + assert_eq!(paid, unpriced + read(image.raw.len())); + assert!(2 * paid <= 3 * unpriced, "{paid} steps against {unpriced}"); + } + /// An image pays for the pixels its data holds, not those its size declares: one claiming /// 131072 by 131072 pixels with a few bytes of Flate costs what those bytes give, and the /// images after it are decoded as they would be without it. @@ -609,8 +665,8 @@ mod image_tests { budget.decode(&doc, s, 1 << 24).unwrap(); u64::MAX - budget.work_left() }; - assert_eq!(cost(&claims), (claims.raw.len() + 16 + 16 * 8) as u64, "its bytes, and a pixel a bit of them"); - assert_eq!(cost(&image), (image.raw.len() + 64 * 64) as u64 + 64 * 64, "its bytes, and its pixels"); + assert_eq!(cost(&claims), (claims.raw.len() + 16 + 16 * 8) as u64 + read(claims.raw.len()), "its bytes, and a pixel a bit of them"); + assert_eq!(cost(&image), (image.raw.len() + 64 * 64) as u64 + read(image.raw.len()) + 64 * 64, "its bytes, and its pixels"); for decode in [ImageBudget::decode, ImageBudget::decode_filters] { let mut budget = ImageBudget::with_work(cost(&claims) + cost(&image)); assert_eq!(decode(&mut budget, &doc, &claims, 1 << 24).unwrap(), [0; 16]); @@ -627,7 +683,7 @@ mod image_tests { let samples = vec![7u8; 1000]; let raw = pdfcraft_filters::encode_flate(&samples); let chain = [(Filter::Flate, Params::default())]; - let cost = (raw.len() + samples.len()) as u64; + let cost = (raw.len() + samples.len()) as u64 + read(raw.len()); let mut budget = ImageBudget::with_work(cost + 10); assert_eq!(budget.decode_chain(&chain, &raw, 1 << 20).unwrap(), samples); assert_eq!(budget.work_left(), 10); @@ -664,7 +720,7 @@ mod image_tests { assert_eq!(budget.decode_filters(&doc, &image, 1 << 20).unwrap(), rows); let cost = u64::MAX - budget.work_left(); // The tag byte of each of its 100 rows counts, which the predictor takes off. - assert_eq!(cost, (image.raw.len() + rows.len() + 100) as u64); + assert_eq!(cost, (image.raw.len() + rows.len() + 100) as u64 + read(image.raw.len())); let mut budget = ImageBudget::with_work(cost - 1); assert!(budget.decode_filters(&doc, &image, 1 << 20).is_err()); assert_eq!((budget.work_left(), budget.refused()), (0, 1)); @@ -769,7 +825,7 @@ mod tests { assert_eq!(budget.remaining(), 0); let mut budget = DecodeBudget::new((1 << 20) - 1, 1); let Object::Stream(stream) = &*doc.get(bomb) else { panic!("not a stream") }; - assert!(budget.decode_strict(stream).is_err()); + assert!(budget.decode_strict(&doc, stream).is_err()); assert_eq!(budget.remaining(), 0); let mut budget = DecodeBudget::new(10 << 20, 1); @@ -793,14 +849,111 @@ mod tests { let corrupt = Stream::from_raw(whole.dict.clone(), whole.raw.get(..cut).unwrap_or_default().to_vec()); let partial = corrupt.decoded().map(|d| d.len()).unwrap_or(0); assert!(partial > 0, "a cut flate stream decodes in part"); + let doc = Document::new_empty(); let mut budget = DecodeBudget::new(10 << 20, 1); - assert!(budget.decode_strict(&corrupt).is_err()); + assert!(budget.decode_strict(&doc, &corrupt).is_err()); assert_eq!(budget.remaining(), (10 << 20) - partial); let mut budget = DecodeBudget::new(10 << 20, 1); assert!(budget.decode_within(&corrupt, 1 << 30).is_ok()); assert_eq!(budget.remaining(), (10 << 20) - partial); } + /// A stream damaged partway decodes to what came before the damage, and says so, so that code + /// writing it back can leave it as it is. What every reader takes is no damage: a missing + /// checksum, no filter at all. + #[test] + fn a_stream_damaged_partway_says_so() { + let doc = Document::new_empty(); + let read = |budget: &mut DecodeBudget, s: &Stream, max| budget.decode_with_damage(&doc, s, max).map(|(d, damaged)| (d.len(), damaged)).ok(); + let whole = Stream::flate(Dict::new(), &vec![b' '; 1 << 20]); + let cut = Stream::from_raw(whole.dict.clone(), whole.raw.get(..whole.raw.len() / 2).unwrap_or_default().to_vec()); + let partial = cut.decoded().map(|d| d.len()).unwrap_or(0); + assert!(partial > 0, "a cut flate stream decodes in part"); + let mut budget = DecodeBudget::new(10 << 20, 1); + assert_eq!(read(&mut budget, &cut, usize::MAX), Some((partial, true))); + assert_eq!(budget.remaining(), (10 << 20) - partial); + // Within a bound of its own, under what is left. + assert_eq!(read(&mut budget, &cut, 4 << 20), Some((partial, true))); + assert_eq!(budget.decode(&cut).map(|d| d.len()).ok(), Some(partial)); + + let mut budget = DecodeBudget::new(10 << 20, 1); + assert_eq!(read(&mut budget, &whole, usize::MAX), Some((1 << 20, false))); + assert_eq!(read(&mut budget, &whole, 4 << 20), Some((1 << 20, false))); + let unchecked = Stream::from_raw(whole.dict.clone(), whole.raw.get(..whole.raw.len() - 4).unwrap_or_default().to_vec()); + assert_eq!(read(&mut budget, &unchecked, usize::MAX), Some((1 << 20, false))); + assert_eq!(read(&mut budget, &Stream::from_raw(Dict::new(), b"0 0 m".to_vec()), usize::MAX), Some((5, false))); + // A later stage's damage is the stream's. + let mut dict = Dict::new(); + dict.set(b"Filter".to_vec(), Object::Array(vec![Object::name("FlateDecode"), Object::name("ASCIIHexDecode")])); + let hex = Stream::from_raw(dict, Stream::flate(Dict::new(), b"4142zz4344>").raw.to_vec()); + assert_eq!(budget.decode_with_damage(&doc, &hex, usize::MAX).ok(), Some((b"AB".to_vec(), true))); + // So is an earlier stage's, though the stage after it reads all it was given: a stored + // block of whole hex, then a block of the reserved type (RFC 1951 §3.2.3). + let readable = b"4142>"; + let len = u16::try_from(readable.len()).unwrap_or_default(); + let mut raw = vec![0x78, 0x01, 0x00]; + raw.extend_from_slice(&len.to_le_bytes()); + raw.extend_from_slice(&(!len).to_le_bytes()); + raw.extend_from_slice(readable); + raw.push(0x07); + let flate_damaged = Stream::from_raw(hex.dict.clone(), raw); + assert_eq!(budget.decode_with_damage(&doc, &flate_damaged, usize::MAX).ok(), Some((b"AB".to_vec(), true))); + } + + /// `/DecodeParms` given by reference, or a parameter given by reference in them, is read: a + /// predicted stream decodes as with them direct. Of the stream, decoding copies no more than + /// its filters and their parameters. + #[test] + fn parameters_given_by_reference_are_read() { + let content = b"q 10 0 0 10 0 0 cm /Im Do Q"; + // PNG Up, one column: each byte a row of its own, tagged 2. + let mut rows = Vec::new(); + let mut above = 0u8; + for &b in content { + rows.extend([2, b.wrapping_sub(above)]); + above = b; + } + let raw = Stream::flate(Dict::new(), &rows).raw; + let mut doc = Document::new_empty(); + let direct: Dict = [(b"Predictor".to_vec(), Object::Int(12))].into_iter().collect(); + let by_reference = Object::Ref(doc.add(Object::Dict(direct.clone()))); + let predictor = doc.add(Object::Int(12)); + let inner = Object::Dict([(b"Predictor".to_vec(), Object::Ref(predictor))].into_iter().collect()); + for parms in [Object::Dict(direct), by_reference, inner] { + let mut dict = Dict::new(); + dict.set(b"Filter".to_vec(), Object::name("FlateDecode")); + dict.set(b"DecodeParms".to_vec(), parms.clone()); + dict.set(b"Other".to_vec(), Object::Array(vec![Object::Int(0); 1000])); + let s = Stream::from_raw(dict, raw.to_vec()); + assert_eq!(DecodeBudget::page().decode_with_damage(&doc, &s, usize::MAX).ok(), Some((content.to_vec(), false)), "{parms:?}"); + assert_eq!(DecodeBudget::page().decode_strict(&doc, &s).ok(), Some(content.to_vec()), "{parms:?}"); + let r = doc.add(Object::Stream(s.clone())); + let read = DecodeBudget::page().decode_contents_with_damage(&doc, &Object::Array(vec![Object::Ref(r)])); + assert_eq!(read, [Ok((content.to_vec(), false))], "{parms:?}"); + assert_eq!(DecodeBudget::page().decode_contents(&doc, &Object::Ref(r)), [Ok(content.to_vec())], "{parms:?}"); + let view = doc.decoding_view(&s); + assert!(matches!(view, std::borrow::Cow::Borrowed(_)) || view.dict.len() == 2, "{:?}", view.dict); + } + } + + /// A page's content streams each say whether they are damaged, in their places. + #[test] + fn a_pages_streams_each_say_whether_they_are_damaged() { + let mut doc = Document::new_empty(); + let whole = doc.add(Object::Stream(Stream::flate(Dict::new(), b"0 0 m 1 1 l S"))); + let Object::Stream(s) = &*doc.get(whole) else { panic!("not a stream") }; + let cut = Stream::from_raw(s.dict.clone(), s.raw.get(..s.raw.len() - 6).unwrap_or_default().to_vec()); + let cut = doc.add(Object::Stream(cut)); + let contents = Object::Array(vec![Object::Ref(whole), Object::Null, Object::Ref(cut)]); + let mut budget = DecodeBudget::page(); + let read: Vec<_> = budget.decode_contents_with_damage(&doc, &contents).into_iter().map(|r| r.map(|(_, damaged)| damaged).ok()).collect(); + assert_eq!(read, [Some(false), Some(true)]); + let one: Vec<_> = + budget.decode_contents_with_damage(&doc, &Object::Ref(cut)).into_iter().map(|r| r.map(|(_, damaged)| damaged).ok()).collect(); + assert_eq!(one, [Some(true)]); + assert_eq!(budget.decode_contents(&doc, &contents).iter().filter(|r| r.is_ok()).count(), 2, "read up to the damage"); + } + /// A stream that fails its reading as zlib, and then as raw deflate after decoding all of it, /// gives nothing back, and each reference still pays for what it decoded. #[test] @@ -832,7 +985,7 @@ mod tests { assert_eq!(budget.remaining(), (10 << 20) - charged); assert!(budget.decode_within(&chained, 2 << 20).is_ok()); assert_eq!(budget.remaining(), (10 << 20) - 2 * charged); - assert!(budget.decode_strict(&chained).is_ok()); + assert!(budget.decode_strict(&Document::new_empty(), &chained).is_ok()); assert_eq!(budget.remaining(), (10 << 20) - 3 * charged); } } diff --git a/crates/cos/src/document.rs b/crates/cos/src/document.rs index e52aba2ce3..e322f22a15 100644 --- a/crates/cos/src/document.rs +++ b/crates/cos/src/document.rs @@ -24,11 +24,11 @@ pub(crate) use objects::Held; pub(crate) use reader::find; #[cfg(test)] use reader::rfind; -pub(crate) use state::ObjectReader; -use state::{ObjStm, Slot}; +use state::{ObjStm, Slot, Unreadable}; +pub(crate) use state::{ObjectReader, held_bytes}; pub use state::{ReadState, SourceIdentity}; #[cfg(test)] -use state::{SECTION_READS, held_bytes, objstm_member}; +use state::{SECTION_READS, objstm_member}; use xref::XrefIndex; pub use xref::{Revision, XrefEntry}; @@ -48,8 +48,14 @@ pub struct Document { /// `fill_xref_gaps`. located: Arc>, repair_log: Arc>, + /// What loading each file object gave, a failure as well: a damaged object is otherwise + /// loaded again on every read, and a member of an object stream that can't be decoded + /// decodes the stream again (`Document::load`). cache: Arc>, objstms: Arc>>>, + /// See [`Self::unreadable_objects`]. Shared by clones, like the caches: it describes the + /// source, and is reset wherever they are. + unreadable: Arc>, /// 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`). jbig2_globals: Arc>>>>, @@ -71,6 +77,9 @@ pub struct Document { encryption_changed: bool, /// Set by edits that must not leave earlier revisions in the file (redaction). full_save: bool, + /// The next full save also gives the file a new identifier (`/ID`), see + /// [`Document::require_full_save_with_new_id`]. + new_id: bool, /// The handler and `/Encrypt` object number that saves use, when encryption changed. out_security: Option>, out_encrypt_num: Option, diff --git a/crates/cos/src/document/objects.rs b/crates/cos/src/document/objects.rs index 62ef1e74cc..91b8656a3f 100644 --- a/crates/cos/src/document/objects.rs +++ b/crates/cos/src/document/objects.rs @@ -1,6 +1,10 @@ +use std::collections::HashSet; + use super::reader::find; -use super::state::{LENGTHS, LoadGuard, ObjStm, ObjectReader, ReadState, Slot, SourceIdentity, held_bytes, objstm_member}; -use super::xref::{Revision, XrefEntry}; +use super::state::{ + LENGTHS, LoadGuard, ObjStm, ObjectReader, ReadState, Slot, SourceIdentity, loaded_bytes, note_overlay_read, objstm_member, overlay_reads, +}; +use super::xref::{Revision, XrefEntry, XrefIndex}; use super::{ Arc, CosError, Cow, Dict, Document, Lexer, MAX_DECODED, MAX_JBIG2_GLOBALS, ObjRef, Object, Stream, is_whitespace, parse_indirect_shared, }; @@ -86,6 +90,39 @@ impl Document { &self.repair_log } + /// Objects of the file that could not be read, lowest number first, as lines such as + /// "object 11 0 could not be read: syntax error at byte 512: ...". [`Self::get`] reads each + /// as null (ISO 32000-2 §7.3.10), so a document with one opens, but what it held is lost: + /// unlike [`Self::repair_log`], nothing was repaired. Lists the objects read so far, by this + /// document, its clones or a scan of it, that have not since been edited; past 100, a last + /// line says there were more. Opening again, authenticating or rebuilding the index starts + /// the list afresh, as it does the object cache. + pub fn unreadable_objects(&self) -> Vec { + let Ok(unreadable) = self.unreadable.lock() else { return Vec::new() }; + unreadable.lines(|num| self.overlay.contains_key(&num)) + } + + /// Record `num` as unreadable. `reason` is built only for an object not yet listed, so a file + /// whose broken object is asked for again and again pays for it once. + fn note_unreadable(&self, num: u32, reason: impl FnOnce() -> String) { + // A poisoned lock only means the object goes unlisted; the read itself still fails. + let Ok(mut unreadable) = self.unreadable.lock() else { return }; + let hidden = |n: u32| self.overlay.contains_key(&n); + if unreadable.wants(num, hidden) { + unreadable.note(num, self.generation(num), &reason(), hidden); + } + } + + /// Why an object listed at `offset` could not be read: what parsing it there, without resolving + /// an indirect `/Length`, found. A best account, not the only one: the reader also tried + /// elsewhere. + fn why_unreadable(&self, offset: usize) -> String { + match parse_indirect_shared(&self.data, offset, &|_| None, &self.endstreams) { + Err(e) => e.to_string(), + Ok(_) => "no readable copy was found at its cross-reference offset or elsewhere in the file".into(), + } + } + /// Add a line to [`Self::repair_log`]: a leniency applied while reading that the user should /// know about (fidelity: never silent). pub fn note_repair(&mut self, line: String) { @@ -129,8 +166,8 @@ impl Document { pub fn xref_entry_is_exact(&self, num: u32) -> bool { match self.xref_entry(num) { None | Some(XrefEntry::Free { .. }) => true, - Some(XrefEntry::InFile { offset, .. }) => { - let at = |off: usize| matches!(parse_indirect_shared(&self.data, off, &|_| None, &self.endstreams), Ok((id, _)) if id.num == num); + Some(XrefEntry::InFile { offset, generation }) => { + let at = |off: usize| matches!(parse_indirect_shared(&self.data, off, &|_| None, &self.endstreams), Ok((id, _)) if id == ObjRef::new(num, generation)); // Offsets may count from a header that does not start the file. usize::try_from(offset).is_ok_and(|off| at(off) || (self.header_offset != 0 && at(off.saturating_add(self.header_offset)))) } @@ -151,9 +188,117 @@ impl Document { // ── object access ─────────────────────────────────────────────────────────────────────── - /// Fetch an object by reference. Missing objects are `Null` (ISO 32000-2 §7.3.10). + /// Fetch an object by reference. Undefined references are `Null` (ISO 32000-2 §7.3.10). + /// A live file slot also accepts its actual header generation when a damaged xref row + /// disagrees; the disagreement is recorded in [`Self::repair_log`]. Free slots never do. pub fn get(&self, r: ObjRef) -> Arc { - self.try_get(r.num).unwrap_or_else(|_| Arc::new(Object::Null)) + self.try_get_reference(r).unwrap_or_else(|_| Arc::new(Object::Null)) + } + + pub(super) fn reference_matches(&self, r: ObjRef) -> bool { + match self.overlay.get(&r.num) { + Some(Slot::Set(generation, _)) => r.generation == *generation, + Some(Slot::RepairedSet(generation, alias, _)) => r.generation == *generation || r.generation == *alias, + Some(Slot::Freed(_)) => false, + None => match self.entries.lookup(r.num, &self.data) { + Some(XrefEntry::InFile { offset, generation }) => { + r.generation == generation || self.indexed_header_reference(r.num, offset) == Some(r) + } + Some(XrefEntry::InStream { .. }) => r.generation == 0, + None | Some(XrefEntry::Free { .. }) => false, + }, + } + } + + /// The generations a reference to `num` may carry and still resolve (see [`Self::get`]), + /// sorted: none for a free or unknown slot, else the slot's generation, and for a damaged + /// file slot (or a repair-aware edit of one) also the generation its object header carries. + /// Code comparing revisions (signature validation) uses it to tell whether the references + /// that reached an object in one revision still reach the same slot in another. + pub fn accepted_generations(&self, num: u32) -> Vec { + // Mirrors `reference_matches`, which stays allocation-free for every lookup. + let mut generations = match self.overlay.get(&num) { + Some(Slot::Set(generation, _)) => vec![*generation], + Some(Slot::RepairedSet(generation, alias, _)) => vec![*generation, *alias], + Some(Slot::Freed(_)) => Vec::new(), + None => match self.entries.lookup(num, &self.data) { + Some(XrefEntry::InFile { offset, generation }) => { + std::iter::once(generation).chain(self.indexed_header_reference(num, offset).map(|h| h.generation)).collect() + } + Some(XrefEntry::InStream { .. }) => vec![0], + None | Some(XrefEntry::Free { .. }) => Vec::new(), + }, + }; + generations.sort_unstable(); + generations.dedup(); + generations + } + + pub(super) fn try_get_reference(&self, r: ObjRef) -> Result, CosError> { + if !self.reference_matches(r) { + return Ok(Arc::new(Object::Null)); + } + self.try_get(r.num) + } + + /// A repair probe, not a whole-file search: only the indexed header (or the same offset + /// relative to a shifted PDF header) can establish this additional generation. A small + /// window bounds hostile whitespace/tokens; ordinary xref-matching reads are unchanged. + pub(super) fn indexed_header_reference(&self, num: u32, offset: u64) -> Option { + let at = |off: usize| { + let bytes = self.data.get(off..off.saturating_add(128).min(self.data.len()))?; + let mut lexer = Lexer::new(bytes, 0); + lexer.skip_ws(); + let number = std::str::from_utf8(lexer.token()).ok()?.parse::().ok()?; + lexer.skip_ws(); + let generation = std::str::from_utf8(lexer.token()).ok()?.parse::().ok()?; + (number == num && lexer.eat_keyword(b"obj")).then_some(ObjRef::new(number, generation)) + }; + let off = usize::try_from(offset).ok()?; + at(off).or_else(|| if self.header_offset == 0 { None } else { off.checked_add(self.header_offset).and_then(at) }) + } + + /// Add at most one bounded diagnostic per object. False stops diagnostic probing only; + /// parsers must still read the remaining xref rows needed to build their index. + pub(super) fn inspect_xref_generation_repair(&self, num: u32, entry: XrefEntry, recorded: &mut HashSet, log: &mut Vec) -> bool { + let XrefEntry::InFile { offset, generation } = entry else { return true }; + if recorded.contains(&num) { + return true; + } + let Some(header) = self.indexed_header_reference(num, offset) else { return true }; + if header.generation == generation { + return true; + } + if recorded.len() == 256 { + log.push("additional xref/header generation disagreements omitted after 256 objects".into()); + return false; + } + recorded.insert(num); + log.push(format!("object {num}: xref generation {generation} disagrees with object header generation {}", header.generation)); + true + } + + /// Diagnose once at open without expanding compact ranges or decoding an xref twice. + /// Materialized readers retain bounded notes while they read accepted sections, before + /// newer rows hide older ones. Discarded parse attempts/rebuilt indexes carry no notes. + pub(super) fn note_xref_generation_repairs(&self, log: &mut Vec) { + match &*self.entries { + XrefIndex::Materialized(_, notes) => log.extend(notes.iter().cloned()), + XrefIndex::Compact { revisions, .. } => { + let mut recorded = HashSet::new(); + for revision in revisions { + for section in std::iter::once(&revision.primary).chain(revision.hybrid.iter()) { + for num in section.numbers() { + if let Some(entry) = section.lookup(num, &self.data) + && !self.inspect_xref_generation_repair(num, entry, &mut recorded, log) + { + return; + } + } + } + } + } + } } /// Follow a reference if `o` is one; otherwise return `o` itself. An object can be nothing but @@ -178,7 +323,29 @@ impl Document { /// ([`pdfcraft_filters::MAX_CHAIN`]). Only small values are copied, so a file can't have a /// large object copied once for each key and filter. pub fn with_direct_parms<'s>(&self, s: &'s Stream) -> Cow<'s, Stream> { - let Some(p) = s.dict.get(b"DecodeParms") else { return Cow::Borrowed(s) }; + let Some(made) = self.direct_parms(s) else { return Cow::Borrowed(s) }; + let mut s = s.clone(); + s.dict.set(b"DecodeParms".to_vec(), made); + Cow::Owned(s) + } + + /// [`Document::with_direct_parms`] for decoding alone: where that copies `s`, this makes a + /// stream of `s`'s data, shared, and a dictionary of its `/Filter` and the parameters made + /// direct, all its filters read. A stream named again and again, as a page's `/Contents` may + /// list one, isn't copied whole each time. + pub(crate) fn decoding_view<'s>(&self, s: &'s Stream) -> Cow<'s, Stream> { + let Some(made) = self.direct_parms(s) else { return Cow::Borrowed(s) }; + let mut dict = Dict::new(); + if let Some(f) = s.dict.get(b"Filter") { + dict.set(b"Filter".to_vec(), f.clone()); + } + dict.set(b"DecodeParms".to_vec(), made); + Cow::Owned(Stream { dict, raw: s.raw.clone() }) + } + + /// The `/DecodeParms` [`Document::with_direct_parms`] gives `s`, or `None` when it keeps `s`. + fn direct_parms(&self, s: &Stream) -> Option { + let p = s.dict.get(b"DecodeParms")?; let crypt = |f: &Object| matches!(f.as_name(), Some(b"Crypt")); let filters: Vec = match s.dict.get(b"Filter") { Some(Object::Array(a)) => a.iter().map(crypt).collect(), @@ -186,7 +353,7 @@ impl Document { None => Vec::new(), }; if filters.iter().filter(|c| !**c).count() > pdfcraft_filters::MAX_CHAIN { - return Cow::Borrowed(s); + return None; } let mut changed = matches!(p, Object::Ref(_)); // Its numbers and flags kept, resolved; anything else is no filter's parameters (null). @@ -213,12 +380,7 @@ impl Document { } _ => one(p, &mut changed), }; - if !changed { - return Cow::Borrowed(s); - } - let mut s = s.clone(); - s.dict.set(b"DecodeParms".to_vec(), made); - Cow::Owned(s) + changed.then_some(made) } /// `o`, or the object it refers to, without copying either. @@ -387,27 +549,38 @@ impl Document { } pub fn try_get(&self, num: u32) -> Result, CosError> { - match self.overlay.get(&num) { - Some(Slot::Set(_, o)) => return Ok(o.clone()), - Some(Slot::Freed(_)) => return Ok(Arc::new(Object::Null)), - None => {} + if let Some(slot) = self.overlay.get(&num) { + note_overlay_read(); + return Ok(match slot { + Slot::Set(_, o) | Slot::RepairedSet(_, _, o) => o.clone(), + Slot::Freed(_) => Arc::new(Object::Null), + }); } - if let Some(o) = self.cache.lock().map_err(|_| CosError::Poisoned)?.get(&num) { - return Ok(o.clone()); + if let Some(loaded) = self.cache.lock().map_err(|_| CosError::Poisoned)?.get(&num) { + return loaded.clone(); } // Loading can re-enter (indirect stream `/Length`, object streams); damaged files make // 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. - 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) + let edits_read = overlay_reads(); + let loaded = self.load(num, 0).map(Arc::new); + if let Err(e) = &loaded + && !matches!(e, CosError::Poisoned) + { + self.note_unreadable(num, || e.to_string()); + } + // A failure is kept like an object, or every read of a damaged object loads it again. A + // poisoned lock says nothing about the object. Clones share the cache, so a load that read + // this document's edits (an edited object stream or `/Length`) is not kept. + if overlay_reads() == edits_read && !matches!(loaded, Err(CosError::Poisoned)) { + // 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, loaded.clone(), loaded_bytes(&loaded, &self.data)); + self.evict_editor_cache_if_over_budget(num)?; + } + loaded } /// Bounds for the editing cache: roomier than the scan reader's (128 objects / 8 MB) @@ -519,11 +692,20 @@ impl Document { None | Some(XrefEntry::Free { .. }) => Ok(Object::Null), Some(XrefEntry::InFile { offset, .. }) => { let resolve = |r: ObjRef| { - if let Some(known) = LENGTHS.with(|m| m.borrow().get(&r.num).copied()) { + if self.overlay.contains_key(&r.num) { + note_overlay_read(); + } + // A length resolved through this document's edits counts as an edit read + // on every reuse. + if let Some((known, edits)) = LENGTHS.with(|m| m.borrow().get(&r).copied()) { + if edits { + note_overlay_read(); + } return known; } - let length = self.try_get(r.num).ok().and_then(|o| o.as_int()); - LENGTHS.with(|m| m.borrow_mut().insert(r.num, length)); + let edits_read = overlay_reads(); + let length = self.try_get_reference(r).ok().and_then(|o| o.as_int()); + LENGTHS.with(|m| m.borrow_mut().insert(r, (length, overlay_reads() != edits_read))); length }; let off = offset as usize; @@ -536,7 +718,10 @@ impl Document { .or_else(|| if self.header_offset == 0 { None } else { at(off.saturating_add(self.header_offset)) }) .or_else(|| self.located.get(&num).and_then(|(o, _)| usize::try_from(*o).ok()).and_then(at)) .or_else(|| self.scan_for(num).map(|(id, o)| self.decrypted(id, o))) - .ok_or(CosError::MissingObject(num)) + .ok_or_else(|| { + self.note_unreadable(num, || self.why_unreadable(off)); + CosError::MissingObject(num) + }) } Some(XrefEntry::InStream { stream, index }) => { let stm = self.objstm(stream)?; @@ -549,7 +734,9 @@ impl Document { } pub(super) fn objstm(&self, num: u32) -> Result, CosError> { - if let Some(s) = self.objstms.lock().map_err(|_| CosError::Poisoned)?.get(&num) { + // An edited or freed stream is this document's alone: clones share the parsed streams. + let edited = self.overlay.contains_key(&num); + if !edited && let Some(s) = self.objstms.lock().map_err(|_| CosError::Poisoned)?.get(&num) { return Ok(s.clone()); } // A file entry that cannot place the stream (one that says it is itself compressed @@ -557,6 +744,7 @@ impl Document { // header, as a plain object with a wrong offset is. An edited or freed stream, in the // overlay or in a saved revision's table, is what that says it is: the file's copy // must not come back. + let edits_read = overlay_reads(); let loaded = match self.try_get(num) { Ok(o) if matches!(*o, Object::Stream(_)) => o, _ if self.overlay.contains_key(&num) || matches!(self.xref_entry(num), Some(XrefEntry::Free { .. })) => { @@ -564,6 +752,8 @@ impl Document { } _ => Arc::new(self.scan_for(num).map(|(id, o)| self.decrypted(id, o)).ok_or(CosError::MissingObject(num))?), }; + // A stream whose load read this document's edits (its `/Length`) is as much its own as an edited one. + let own = edited || overlay_reads() != edits_read; 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(); @@ -571,6 +761,8 @@ impl Document { // 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)); + #[cfg(test)] + super::tests::OBJSTM_DECODES.with(|decodes| decodes.set(decodes.get() + 1)); let data = readable.decoded_within(self.stream_limit)?; let mut lx = Lexer::new(&data, 0); let mut index = Vec::with_capacity(n); @@ -579,6 +771,9 @@ impl Document { index.push(objstm_member(onum, off, first, data.len())); } let stm = Arc::new(ObjStm { index, data: Arc::new(data) }); + if own { + return Ok(stm); + } // Same bound as the object cache: decoded object streams can be megabytes each. // Insert first so the retained `num` is actually in the map. self.objstms.lock().map_err(|_| CosError::Poisoned)?.insert(num, stm.clone()); @@ -635,11 +830,44 @@ impl Document { pub fn set(&mut self, r: ObjRef, obj: impl Into) { let obj = self.adopt(obj.into()); self.overlay.insert(r.num, Slot::Set(r.generation, Arc::new(obj))); + self.forget_member_failures(r.num); if r.num >= self.next_num { self.next_num = r.num.saturating_add(1); } } + /// Replace an accepted existing reference without losing a damaged source slot's aliases. + /// Unlike [`Self::set`], this preserves both xref/header generations when they disagree. + /// Such an edit forces a full rewrite so the output has consistent references, rather than + /// appending a new contradictory xref row. Missing, free and stale references are errors. + pub fn set_existing(&mut self, r: ObjRef, obj: impl Into) -> Result<(), CosError> { + if !self.reference_matches(r) { + return Err(CosError::MissingObject(r.num)); + } + let alias = self.alternate_generation(r); + if let Some(alias) = alias { + let obj = self.adopt(obj.into()); + self.overlay.insert(r.num, Slot::RepairedSet(r.generation, alias, Arc::new(obj))); + } else { + self.set(r, obj); + } + Ok(()) + } + + /// Other accepted generation for a known-live reference to a damaged slot. + pub(super) fn alternate_generation(&self, r: ObjRef) -> Option { + match self.overlay.get(&r.num) { + Some(Slot::RepairedSet(generation, alias, _)) => Some(if r.generation == *generation { *alias } else { *generation }), + Some(_) => None, + None => match self.entries.lookup(r.num, &self.data) { + Some(XrefEntry::InFile { offset, generation }) => self.indexed_header_reference(r.num, offset).and_then(|header| { + (header.generation != generation).then_some(if r.generation == generation { header.generation } else { generation }) + }), + _ => None, + }, + } + } + /// Add a new indirect object and return its reference. pub fn add(&mut self, obj: impl Into) -> ObjRef { let r = ObjRef::new(self.allocate_num(), 0); @@ -662,6 +890,16 @@ impl Document { /// Delete an object (its number becomes free with the next generation). pub fn free(&mut self, r: ObjRef) { self.overlay.insert(r.num, Slot::Freed(r.generation.saturating_add(1))); + self.forget_member_failures(r.num); + } + + /// Forget cached failures of the members `stream` held in the file: they were failures of + /// the file's copy, and an edit of `stream` may read. Clones share the cache, so theirs are + /// searched again too, which costs time only. A poisoned lock leaves the cache as it is. + fn forget_member_failures(&self, stream: u32) { + if let Ok(mut cache) = self.cache.lock() { + cache.forget_failures(|n| matches!(self.entries.lookup(*n, &self.data), Some(XrefEntry::InStream { stream: s, .. }) if s == stream)); + } } /// Free what was added since the file was read and nothing refers to any more: the objects @@ -699,7 +937,8 @@ impl Document { let generation = current.generation(num); let same = saved_nums.binary_search(&num).is_ok() && self.generation(num) == generation - && saved_reader.try_get(ObjRef::new(num, 0))? == current_reader.try_get(ObjRef::new(num, 0))?; + && self.alternate_generation(ObjRef::new(num, generation)) == current.alternate_generation(ObjRef::new(num, generation)) + && saved_reader.try_get(ObjRef::new(num, generation))? == current_reader.try_get(ObjRef::new(num, generation))?; if !same { changed.push(num); } @@ -728,8 +967,14 @@ impl Document { let mut current_reader = current.object_reader(); for num in changed { let generation = current.generation(num); - let object = current_reader.try_get(ObjRef::new(num, 0))?; - self.set(ObjRef::new(num, generation), (*object).clone()); + let object = current_reader.try_get(ObjRef::new(num, generation))?; + if let Some(alias) = current.alternate_generation(ObjRef::new(num, generation)) { + let object = self.adopt((*object).clone()); + self.overlay.insert(num, Slot::RepairedSet(generation, alias, Arc::new(object))); + self.next_num = self.next_num.max(num.saturating_add(1)); + } else { + self.set(ObjRef::new(num, generation), (*object).clone()); + } } *self.trailer_mut() = current.trailer().clone(); Ok(()) @@ -740,14 +985,13 @@ impl Document { let mut obj = (*self.get(r)).clone(); let d = obj.as_dict_mut().ok_or(CosError::NotADictionary(r))?; f(d); - self.set(r, obj); - Ok(()) + self.set_existing(r, obj) } /// Current generation of an object number. pub fn generation(&self, num: u32) -> u16 { match self.overlay.get(&num) { - Some(Slot::Set(g, _)) => *g, + Some(Slot::Set(g, _) | Slot::RepairedSet(g, _, _)) => *g, Some(Slot::Freed(g)) => *g, None => match self.entries.lookup(num, &self.data) { Some(XrefEntry::InFile { generation, .. }) => generation, @@ -759,7 +1003,7 @@ impl Document { pub(crate) fn overlay_entries(&self) -> impl Iterator>)> + '_ { self.overlay.iter().map(|(n, s)| match s { - Slot::Set(g, o) => (*n, *g, Some(o.clone())), + Slot::Set(g, o) | Slot::RepairedSet(g, _, o) => (*n, *g, Some(o.clone())), Slot::Freed(g) => (*n, *g, None), }) } @@ -782,7 +1026,7 @@ impl Document { if source.peek().is_some_and(|n| *n == num) { source.next(); } - if matches!(slot, Slot::Set(..)) { + if matches!(slot, Slot::Set(..) | Slot::RepairedSet(..)) { numbers.push(num); } } @@ -800,7 +1044,7 @@ impl Document { pub(super) fn root_is_catalog(&self) -> bool { let Some(r) = self.root() else { return false }; - matches!(self.try_get(r.num).as_deref(), Ok(Object::Dict(d)) if d.name(b"Type") == Some(b"Catalog") || d.contains(b"Pages")) + matches!(self.try_get_reference(r).as_deref(), Ok(Object::Dict(d)) if d.name(b"Type") == Some(b"Catalog") || d.contains(b"Pages")) } } diff --git a/crates/cos/src/document/open.rs b/crates/cos/src/document/open.rs index 70bbcc313e..b628cea89c 100644 --- a/crates/cos/src/document/open.rs +++ b/crates/cos/src/document/open.rs @@ -1,5 +1,5 @@ use super::reader::find; -use super::state::Credentials; +use super::state::{Credentials, Slot}; use super::xref::XrefIndex; use super::{Arc, BTreeMap, CosError, Dict, Document, HashSet, ObjRef, Object}; @@ -23,6 +23,7 @@ impl Document { repair_log: Arc::new(Vec::new()), cache: Arc::default(), objstms: Arc::default(), + unreadable: Arc::default(), jbig2_globals: Arc::default(), stream_limit: crate::object::MAX_DECODED, overlay: BTreeMap::new(), @@ -35,6 +36,7 @@ impl Document { unfound: Arc::default(), encryption_changed: false, full_save: false, + new_id: false, out_security: None, out_encrypt_num: None, }; @@ -109,6 +111,7 @@ impl Document { repair_log: Arc::new(Vec::new()), cache: Arc::default(), objstms: Arc::default(), + unreadable: Arc::default(), jbig2_globals: Arc::default(), stream_limit: stream_limit.min(crate::object::MAX_DECODED), overlay: BTreeMap::new(), @@ -121,6 +124,7 @@ impl Document { unfound: Arc::default(), encryption_changed: false, full_save: false, + new_id: false, out_security: None, out_encrypt_num: None, }; @@ -156,6 +160,9 @@ impl Document { } doc.reconstruct(&mut log)?; } + // Header generations are plaintext, including in encrypted files. Inspect only the + // bounded headers, not object bodies, and retain the compact xref representation. + doc.note_xref_generation_repairs(&mut log); doc.repair_log = Arc::new(log); // Reconstruction may have found a different trailer: (re)authenticate against it. if (!ok || !authenticated) @@ -211,6 +218,7 @@ impl Document { // Objects read while locating the catalog were read before decryption was possible. self.cache = Arc::default(); self.objstms = Arc::default(); + self.unreadable = Arc::default(); Ok(()) } @@ -287,9 +295,23 @@ impl Document { self.full_save = true; } + /// Like [`Document::require_full_save`], and the rewritten file also gets a new file identifier + /// (`/ID`), so that a redacted or sanitized copy never claims to be its source (ISO 32000-2 + /// §14.4). An encrypted file keeps the first string of its identifier, which its key depends on. + pub fn require_full_save_with_new_id(&mut self) { + self.full_save = true; + self.new_id = true; + } + /// The next save must rewrite the whole file (see [`Document::require_full_save`]). + /// Repair-aware edits retaining two accepted generations cannot use one incremental slot. pub fn full_save_required(&self) -> bool { - self.full_save + self.full_save || self.overlay.values().any(|slot| matches!(slot, Slot::RepairedSet(..))) + } + + /// The next full save gives the file a new identifier (see [`Document::require_full_save_with_new_id`]). + pub fn new_id_required(&self) -> bool { + self.new_id } /// Security was set or removed since the document was opened (the next save applies it). diff --git a/crates/cos/src/document/reader.rs b/crates/cos/src/document/reader.rs index d21bf9403f..18f5ce848a 100644 --- a/crates/cos/src/document/reader.rs +++ b/crates/cos/src/document/reader.rs @@ -1,5 +1,6 @@ #[cfg(test)] use super::state::SECTION_READS; +use super::state::Unreadable; use super::xref::{ MAX_COMPACT_XREF_BYTES, MAX_COMPACT_XREF_ROWS, Revision, XrefEntry, XrefIndex, XrefRange, XrefRevisionSection, XrefSection, XrefSectionData, }; @@ -17,8 +18,8 @@ impl Document { return Ok((index, trailer, revisions, Vec::new())); } } - let (entries, trailer, revisions, oddities) = self.read_xref_chain_materialized(log)?; - Ok((XrefIndex::Materialized(Arc::new(entries)), trailer, revisions, oddities)) + let (entries, trailer, revisions, oddities, generation_repairs) = self.read_xref_chain_materialized(log)?; + Ok((XrefIndex::Materialized(Arc::new(entries), Arc::new(generation_repairs)), trailer, revisions, oddities)) } fn read_compact_xref_chain(&self, log: &mut Vec) -> Result)>, CosError> { @@ -323,7 +324,7 @@ impl Document { pub(super) fn read_xref_chain_materialized( &self, log: &mut Vec, - ) -> Result<(BTreeMap, Dict, Vec, Vec<(u64, u32)>), CosError> { + ) -> Result<(BTreeMap, Dict, Vec, Vec<(u64, u32)>, Vec), CosError> { let data = &self.data; let tail_start = data.len().saturating_sub(4096); let sx = rfind(data, b"startxref", tail_start).ok_or(CosError::Syntax { offset: data.len(), detail: "no startxref".into() })?; @@ -343,6 +344,9 @@ impl Document { // At most MAX_XREF_OBJECTS entries are kept in all; a stream past that is read again. let mut hybrids: HashMap>> = HashMap::new(); let (mut hybrid_rows, mut noted) = (0usize, HashSet::new()); + let mut generation_repairs = Vec::new(); + let mut recorded = HashSet::new(); + let mut diagnose = true; let mut next = Some(first); while let Some(off) = next.take() { if !visited.insert(off) || visited.len() > 10_000 { @@ -371,6 +375,12 @@ impl Document { } }; revisions.push(Revision { xref_offset: off, is_stream, header_relative }); + for (&num, &entry) in § { + if !diagnose { + break; + } + diagnose = self.inspect_xref_generation_repair(num, entry, &mut recorded, &mut generation_repairs); + } // Hybrid files (§7.5.8.4): the /XRefStm entries supplement the table and replace the // free entries it gives objects only a cross-reference stream can locate. let hybrid = sect_trailer.int(b"XRefStm").filter(|x| *x >= 0); @@ -390,6 +400,12 @@ impl Document { let mut stm = BTreeMap::new(); let read = match self.read_section(x as usize, &mut stm, &mut odd, log) { Ok(_) => { + for (&num, &entry) in &stm { + if !diagnose { + break; + } + diagnose = self.inspect_xref_generation_repair(num, entry, &mut recorded, &mut generation_repairs); + } for (&num, &e) in &stm { match sect.get(&num) { None | Some(XrefEntry::Free { .. }) => { @@ -427,7 +443,7 @@ impl Document { for k in [&b"Prev"[..], b"XRefStm", b"Type", b"W", b"Index", b"Filter", b"DecodeParms", b"Length"] { trailer.remove(k); } - Ok((entries, trailer, revisions, oddities)) + Ok((entries, trailer, revisions, oddities, generation_repairs)) } /// Read one section at `off`, adding entries not already known (newer sections win). `odd` @@ -606,7 +622,7 @@ impl Document { } if found > 0 { log.push(format!("the cross-reference data leaves out {found} objects the file contains; located them by their object headers")); - self.entries = Arc::new(XrefIndex::Materialized(Arc::new(filled))); + self.entries = Arc::new(XrefIndex::Materialized(Arc::new(filled), Arc::default())); } self.located = Arc::new(located); } @@ -619,10 +635,20 @@ impl Document { // Offsets of objects that may be cross-reference streams: their dictionaries are the // trailers of files that have no `trailer` keyword (§7.5.8). let mut xref_streams = Vec::new(); - for (num, offset, generation, body) in object_headers(&data) { + let headers = object_headers(&data); + // Where `/XRef` occurs in the file, found in one pass. + let mut xref_marks = Vec::new(); + let mut mark_from = 0; + while let Some(p) = find(&data, b"/XRef", mark_from, data.len()) { + xref_marks.push(p); + mark_from = p + 1; + } + for &(num, offset, generation, body) in &headers { entries.insert(num, XrefEntry::InFile { offset, generation }); objstms.push(num); - if find(&data, b"/XRef", body, body.saturating_add(1024)).is_some() + // `/XRef` within the 1024 bytes after the header (the first one that is there). + let first = xref_marks.partition_point(|&p| p < body); + if xref_marks.get(first).is_some_and(|&p| p + 5 <= body.saturating_add(1024).min(data.len())) && let Ok(at) = usize::try_from(offset) { xref_streams.push(at); @@ -631,8 +657,9 @@ impl Document { if entries.is_empty() { return Err(CosError::Syntax { offset: 0, detail: "no objects found".into() }); } - self.entries = Arc::new(XrefIndex::Materialized(Arc::new(entries.clone()))); + self.entries = Arc::new(XrefIndex::Materialized(Arc::new(entries.clone()), Arc::default())); self.cache.lock().map_err(|_| CosError::Poisoned)?.clear(); + *self.unreadable.lock().map_err(|_| CosError::Poisoned)? = Unreadable::default(); // Objects inside object streams. for num in objstms { if let Ok(o) = self.try_get(num) @@ -648,7 +675,9 @@ impl Document { } } let object_count = entries.len(); - self.entries = Arc::new(XrefIndex::Materialized(Arc::new(entries))); + self.entries = Arc::new(XrefIndex::Materialized(Arc::new(entries), Arc::default())); + // Failures from the scan stand: the members added change no scanned entry, and a + // `/Length` found only now cannot make a stream unreadable. self.cache.lock().map_err(|_| CosError::Poisoned)?.clear(); // Trailer: the last `trailer` dictionary or cross-reference stream dictionary with a // usable /Root (last in the file, whichever kind), else the catalog itself. One whose @@ -658,7 +687,7 @@ impl Document { // A file whose only trailers are cross-reference streams (and whose `startxref` is gone // or points nowhere) keeps its /Info, /ID and /Encrypt this way. let rank = |at: usize, d: &Dict| { - let root = self.try_get(d.reference(b"Root")?.num).ok()?; + let root = self.try_get_reference(d.reference(b"Root")?).ok()?; let Object::Dict(c) = &*root else { return None }; Some((c.name(b"Type") == Some(b"Catalog") || c.contains(b"Pages"), at)) }; @@ -808,7 +837,33 @@ pub(crate) fn find(hay: &[u8], needle: &[u8], from: usize, to: usize) -> Option< if from >= to || needle.is_empty() || to - from < needle.len() { return None; } - hay[from..to].windows(needle.len()).position(|w| w == needle).map(|p| p + from) + let hay = &hay[from..to]; + // Look for the needle's rarest byte first, a plain byte scan, and compare the rest only there. + const COMMON: &[u8] = b" etaoinsrhldcumfpgwybvkxjqz"; + let (k, rare) = + needle.iter().copied().enumerate().max_by_key(|&(_, b)| COMMON.iter().position(|&c| c == b).unwrap_or(COMMON.len())).unwrap_or((0, 0)); + let mut i = k; + while let Some(p) = hay.get(i..).and_then(|rest| position_of(rest, rare)) { + let start = i + p - k; + if hay.get(start..start + needle.len()) == Some(needle) { + return Some(start + from); + } + i += p + 1; + } + None +} + +/// The first position of `byte` in `hay`. Whole 32-byte blocks are tested without branching, which +/// the compiler turns into vector compares; only a block that holds the byte is searched. +fn position_of(hay: &[u8], byte: u8) -> Option { + const BLOCK: usize = 32; + let (blocks, rest) = hay.as_chunks::(); + for (i, block) in blocks.iter().enumerate() { + if block.iter().fold(false, |any, &b| any | (b == byte)) { + return block.iter().position(|&b| b == byte).map(|p| i * BLOCK + p); + } + } + rest.iter().position(|&b| b == byte).map(|p| blocks.len() * BLOCK + p) } pub(super) fn rfind(hay: &[u8], needle: &[u8], from: usize) -> Option { diff --git a/crates/cos/src/document/state.rs b/crates/cos/src/document/state.rs index 96dde01c0f..af71f95359 100644 --- a/crates/cos/src/document/state.rs +++ b/crates/cos/src/document/state.rs @@ -6,8 +6,20 @@ thread_local! { static LOADING: std::cell::RefCell> = const { std::cell::RefCell::new(Vec::new()) }; /// Indirect `/Length` values resolved during the current outermost load: a damaged file /// retries a parse several ways, and each retry would resolve the same lengths again - /// (exponential in the chain of streams whose lengths point at further streams). - pub(super) static LENGTHS: std::cell::RefCell>> = std::cell::RefCell::new(HashMap::new()); + /// (exponential in the chain of streams whose lengths point at further streams). Each is + /// kept with whether resolving it read unsaved edits. + pub(super) static LENGTHS: std::cell::RefCell, bool)>> = std::cell::RefCell::new(HashMap::new()); + /// Unsaved edits read on this thread (`Document::try_get`, and a `/Length` in `Document::load`). + static OVERLAY_READS: std::cell::Cell = const { std::cell::Cell::new(0) }; +} + +/// Unsaved edits read so far on this thread: a load during which this changes depended on one. +pub(super) fn overlay_reads() -> u64 { + OVERLAY_READS.with(std::cell::Cell::get) +} + +pub(super) fn note_overlay_read() { + OVERLAY_READS.with(|c| c.set(c.get().wrapping_add(1))); } /// Marks an object as being loaded on this thread. Loading can re-enter (indirect stream @@ -30,6 +42,14 @@ impl LoadGuard { } } +/// What loading a file object gave, kept in the document's cache either way. +pub(super) type Loaded = Result, CosError>; + +/// The bytes a load result holds of its own ([`held_bytes`]); a failure holds none. +pub(super) fn loaded_bytes(loaded: &Loaded, data: &Arc>) -> usize { + loaded.as_ref().map_or(0, |o| held_bytes(o, data, 0)) +} + impl Drop for LoadGuard { fn drop(&mut self) { let outermost = LOADING.with(|l| { @@ -61,10 +81,67 @@ pub(super) fn objstm_member(num: i64, offset: i64, first: Option, len: us (start < len).then_some((num, start)) } +/// Objects the reader could not read, each with the reason (see `Document::unreadable_objects`). +/// Bounded: a document records past [`Unreadable::MAX`] of the objects it shows only the fact that +/// there were more. Entries a clone has edited are hidden from it and do not count, so the whole +/// list holds at most `MAX` plus the objects edited in clones. +#[derive(Debug, Default)] +pub(super) struct Unreadable { + pub(super) objects: BTreeMap, + pub(super) more: bool, +} + +impl Unreadable { + pub(super) const MAX: usize = 100; + /// Characters of a reason kept: a parser's message can quote the bytes it stopped at. + const REASON: usize = 160; + + /// Whether `num` is to be recorded: not listed yet and there is room among the entries the + /// asking document still shows (`hidden` are the ones it has edited, as in [`Self::lines`]), + /// so a clone's edits never use up its own allowance. A full list notes that there were more, + /// so a caller asks this before building the reason. + pub(super) fn wants(&mut self, num: u32, hidden: impl Fn(u32) -> bool) -> bool { + if self.objects.contains_key(&num) { + return false; + } + if self.objects.keys().filter(|n| !hidden(**n)).count() >= Self::MAX { + self.more = true; + return false; + } + true + } + + /// Record `num` once; the first reason given is kept. + pub(super) fn note(&mut self, num: u32, generation: u16, reason: &str, hidden: impl Fn(u32) -> bool) { + if self.wants(num, hidden) { + self.objects.insert(num, (generation, reason.chars().take(Self::REASON).collect())); + } + } + + /// One line per recorded object not `hidden`, then one saying there were more, if there were. + pub(super) fn lines(&self, hidden: impl Fn(u32) -> bool) -> Vec { + // Clones share the list and each hides its own edits, so the list may hold more than + // `MAX` entries in all; each document still shows at most `MAX`. + let mut shown = self.objects.iter().filter(|(num, _)| !hidden(**num)); + let mut lines: Vec = shown + .by_ref() + .take(Self::MAX) + .map(|(num, (generation, reason))| format!("object {num} {generation} could not be read: {reason}")) + .collect(); + if self.more || shown.next().is_some() { + lines.push(format!("more objects could not be read; only the first {} are listed", Self::MAX)); + } + lines + } +} + /// Where an overlay slot came from. #[derive(Clone, Debug, PartialEq)] pub(super) enum Slot { Set(u16, Arc), + /// Both generations accepted from a damaged live source slot survive a repair-aware edit. + /// A full rewrite is required: a new xref slot cannot encode two generations. + RepairedSet(u16, u16, Arc), Freed(u16), } @@ -103,6 +180,7 @@ impl ReadState { a == b && match (x, y) { (Slot::Set(g, o), Slot::Set(h, p)) => g == h && Arc::ptr_eq(o, p), + (Slot::RepairedSet(g, a, o), Slot::RepairedSet(h, b, p)) => g == h && a == b && Arc::ptr_eq(o, p), (Slot::Freed(g), Slot::Freed(h)) => g == h, _ => false, } @@ -133,7 +211,7 @@ impl ObjectReader { } pub(crate) fn try_get(&mut self, reference: ObjRef) -> Result, CosError> { - let object = self.document.try_get(reference.num); + let object = self.document.try_get_reference(reference); // A missed eviction here only costs a re-parse, so never fail the read on a poisoned // lock. The editing-cache evictors propagate instead; they guard user edits. if let Ok(mut streams) = self.document.objstms.lock() { @@ -178,7 +256,7 @@ thread_local! { pub(super) static SECTION_READS: std::cell::Cell = const { std::cell::Cell::new(0) }; } -/// Parsed objects by number, each with what it holds ([`held_bytes`]) measured once, when it goes +/// What loading each object gave (a failure as well), 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 @@ -187,12 +265,12 @@ thread_local! { /// (#5873). #[derive(Default)] pub(crate) struct ObjectCache { - entries: HashMap, usize)>, + entries: HashMap, owned: usize, } impl ObjectCache { - pub(crate) fn get(&self, num: &u32) -> Option<&Arc> { + pub(crate) fn get(&self, num: &u32) -> Option<&Loaded> { self.entries.get(num).map(|(object, _)| object) } @@ -201,8 +279,8 @@ impl ObjectCache { 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, owned: usize) { + /// Keep what loading `num` gave, which holds `owned` bytes ([`loaded_bytes`]). + pub(crate) fn insert(&mut self, num: u32, object: Loaded, owned: usize) { if let Some((_, before)) = self.entries.insert(num, (object, owned)) { self.owned = self.owned.saturating_sub(before); } @@ -228,6 +306,11 @@ impl ObjectCache { self.owned = 0; } + /// Drop the cached failures `stale` picks. A failure holds no bytes, so the total stands. + pub(crate) fn forget_failures(&mut self, mut stale: impl FnMut(&u32) -> bool) { + self.entries.retain(|num, (loaded, _)| loaded.is_ok() || !stale(num)); + } + 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)); @@ -235,7 +318,7 @@ impl ObjectCache { #[cfg(test)] pub(crate) fn values(&self) -> impl Iterator> { - self.entries.values().map(|(object, _)| object) + self.entries.values().filter_map(|(object, _)| object.as_ref().ok()) } } @@ -252,7 +335,7 @@ const OWNED_BYTES_DEPTH: usize = 256; /// 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>, depth: usize) -> usize { +pub(crate) fn held_bytes(object: &Object, data: &Arc>, depth: usize) -> usize { if depth > OWNED_BYTES_DEPTH { return usize::MAX; } diff --git a/crates/cos/src/document/tests.rs b/crates/cos/src/document/tests.rs index f12437baaf..f69ffae042 100644 --- a/crates/cos/src/document/tests.rs +++ b/crates/cos/src/document/tests.rs @@ -3,6 +3,8 @@ 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 = const { std::cell::Cell::new(0) }; + /// How many times `Document::objstm` decoded an object stream on this thread. + pub(super) static OBJSTM_DECODES: std::cell::Cell = 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 @@ -599,7 +601,7 @@ pub(crate) fn build(bodies: &[&str], trailer: &str) -> Vec { fn assert_compact_matches_materialized(doc: &Document) { assert!(matches!(doc.entries.as_ref(), XrefIndex::Compact { .. }), "valid xrefs should not retain a per-entry map"); - let (entries, _, revisions, _) = doc.read_xref_chain_materialized(&mut Vec::new()).unwrap(); + let (entries, _, revisions, _, _) = doc.read_xref_chain_materialized(&mut Vec::new()).unwrap(); assert_eq!(revisions.as_slice(), doc.revisions()); let max = entries.keys().next_back().copied().unwrap_or(0); assert_eq!(doc.entries.max_num(), max); @@ -687,7 +689,7 @@ fn malformed_size_uses_the_materialized_compatibility_path() { let at = bytes.windows(marker.len()).position(|window| window == marker).unwrap(); bytes[at..at + marker.len()].copy_from_slice(b"/Size 2"); let doc = Document::open(Arc::new(bytes)).unwrap(); - assert!(matches!(doc.entries.as_ref(), XrefIndex::Materialized(_))); + assert!(matches!(doc.entries.as_ref(), XrefIndex::Materialized(..))); assert_eq!(doc.next_num, 4); assert_eq!(doc.object_numbers(), vec![1, 2, 3]); } @@ -730,6 +732,163 @@ fn an_entry_that_misses_its_object_is_found_by_searching_but_is_not_exact() { assert!(doc.xref_entry_is_exact(1) && doc.xref_entry_is_exact(2)); } +/// An object that can't be read at its entry or anywhere else is searched for in the whole file +/// once: every later read, in a clone too, gives the same error without searching again. An +/// edit of that number still answers for it. +#[test] +fn an_unreadable_object_is_searched_for_once() { + let bodies = ["<< /Type /Catalog /Pages 2 0 R >>", "<< /Type /Pages /Kids [] /Count 0 >>", "<< /Odd Key(x) >>"]; + let doc = Document::open(Arc::new(build(&bodies, "/Root 1 0 R /Info 3 0 R"))).unwrap(); + FILE_SCANS.with(|scans| scans.set(0)); + let first = doc.try_get(3); + assert!(first.is_err(), "{first:?}"); + for _ in 0..10 { + assert_eq!(doc.try_get(3), first); + assert_eq!(*doc.get(ObjRef::new(3, 0)), Object::Null); + } + let mut edited = doc.clone(); + assert_eq!(edited.try_get(3), first); + assert_eq!(FILE_SCANS.with(std::cell::Cell::get), 1, "searches for an object that isn't there"); + let report = doc.unreadable_objects(); + assert_eq!(report.len(), 1, "cached failures must stay listed exactly once: {report:?}"); + assert_eq!(edited.unreadable_objects(), report, "clones retain the cached failure diagnostic"); + edited.set(ObjRef::new(3, 0), Object::Int(7)); + assert_eq!(edited.try_get(3).as_deref(), Ok(&Object::Int(7))); + assert_eq!(doc.try_get(3), first, "the edit is the clone's alone"); + edited.free(ObjRef::new(3, 0)); + assert_eq!(edited.try_get(3).as_deref(), Ok(&Object::Null)); +} + +/// A member of an object stream that can't be decoded (here, one that decodes past the document's +/// stream limit) is decoded once: every later read, in a clone too, gives the same error without +/// decoding the stream again. The stream itself loads, so no search of the file is involved. +#[test] +fn a_member_of_an_undecodable_object_stream_is_decoded_once() { + let file = object_stream_file("3 0 ", &format!("<< /Hidden ({}) >>", "x".repeat(4096)), 0); + let doc = Document::open_with_stream_limit(Arc::new(file), None, 1024).unwrap(); + OBJSTM_DECODES.with(|decodes| decodes.set(0)); + let first = doc.try_get(3); + assert!(matches!(first, Err(CosError::Filter(_))), "{first:?}"); + for _ in 0..10 { + assert_eq!(doc.try_get(3), first); + } + assert_eq!(doc.clone().try_get(3), first); + assert_eq!(OBJSTM_DECODES.with(std::cell::Cell::get), 1, "decodes an object stream that can't be decoded"); +} + +/// Clones share the cache, and an edit is one clone's alone: a member of an object stream that +/// one clone freed or replaced still reads, in the others, from the file's stream. +#[test] +fn an_edited_object_stream_leaves_other_clones_members_alone() { + let file = Arc::new(object_stream_file("3 0 ", "<< /Hidden (yes) >>", 0)); + let doc = Document::open(file.clone()).unwrap(); + let mut freed = doc.clone(); + freed.free(ObjRef::new(4, 0)); + assert_eq!(freed.try_get(3), Err(CosError::MissingObject(4))); + assert_eq!(text_of(&doc, 3, b"Hidden").as_deref(), Some("yes"), "the free reached another clone"); + let doc = Document::open(file).unwrap(); + let mut replaced = doc.clone(); + let mut dict = Dict::new(); + dict.set(b"Type".to_vec(), Object::name("ObjStm")); + dict.set(b"N".to_vec(), Object::Int(1)); + dict.set(b"First".to_vec(), Object::Int(4)); + replaced.set(ObjRef::new(4, 0), crate::Stream::from_raw(dict, b"3 0 << /Hidden (no) >>".to_vec())); + assert_eq!(text_of(&replaced, 3, b"Hidden").as_deref(), Some("no")); + assert_eq!(text_of(&doc, 3, b"Hidden").as_deref(), Some("yes"), "the replacement reached another clone"); +} + +/// A member that failed to load from the file's object stream is kept as a failure, but replacing +/// or freeing that stream forgets it: the member then reads from the edit. +#[test] +fn an_edited_object_stream_forgets_its_members_failures() { + let file = Arc::new(object_stream_file("3 0 ", ") broken", 0)); + let mut doc = Document::open(file.clone()).unwrap(); + assert!(doc.try_get(3).is_err(), "the file's member does not parse"); + let mut dict = Dict::new(); + dict.set(b"Type".to_vec(), Object::name("ObjStm")); + dict.set(b"N".to_vec(), Object::Int(1)); + dict.set(b"First".to_vec(), Object::Int(4)); + doc.set(ObjRef::new(4, 0), crate::Stream::from_raw(dict, b"3 0 << /Hidden (fixed) >>".to_vec())); + assert_eq!(text_of(&doc, 3, b"Hidden").as_deref(), Some("fixed"), "the cached failure outlived the edit"); + assert!(doc.try_get(3).is_ok()); + let mut doc = Document::open(file).unwrap(); + assert!(matches!(doc.try_get(3), Err(CosError::Syntax { .. })), "the file's member does not parse"); + doc.free(ObjRef::new(4, 0)); + assert_eq!(doc.try_get(3), Err(CosError::MissingObject(4)), "the freed stream's member"); +} + +/// An object stream framed by one clone's edit of its indirect `/Length` is that clone's alone: +/// the others still read its members within the file's length. +#[test] +fn an_edited_object_stream_length_leaves_other_clones_members_alone() { + let file = Arc::new(object_stream_file_with("3 0 ", "<< /Hidden (cut endstream here) >>", 0, true)); + let doc = Document::open(file).unwrap(); + let mut edited = doc.clone(); + // Ends the stream at the `endstream` inside the member's string. + let cut = "3 0 << /Hidden (cut".len(); + edited.set(ObjRef::new(6, 0), Object::Int(cut as i64)); + assert_ne!(text_of(&edited, 3, b"Hidden").as_deref(), Some("cut endstream here"), "the edited length was not used"); + assert_eq!(text_of(&doc, 3, b"Hidden").as_deref(), Some("cut endstream here"), "the edited length reached another clone"); +} + +/// A `/Length` read through one clone's edits and reused within the same load still keeps that +/// load to the clone. Here the file's offsets are header-relative behind junk, so object 10's +/// offset first lands on object 12, whose length (object 8, in the edited object stream 9) is +/// read; object 10's own length then loads object stream 4, framed by object 8 too. +#[test] +fn a_reused_edited_length_leaves_other_clones_members_alone() { + let mut out = b"%PDF-1.5\n".to_vec(); + let mut offs = [0usize; 13]; + let mut obj = |out: &mut Vec, 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"); + }; + let stream = |dict: &str, data: &str| format!("<< {dict} >>\nstream\n{data}\nendstream").into_bytes(); + 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 inner = "11 0 3 2 5 << /Hidden (cut endstream here) >>"; + obj(&mut out, 4, &stream("/Type /ObjStm /N 2 /First 9 /Length 8 0 R", inner)); + let lengths = format!("8 0 {}", inner.len()); + obj(&mut out, 9, &stream(&format!("/Type /ObjStm /N 1 /First 4 /Length {}", lengths.len()), &lengths)); + obj(&mut out, 12, &stream("/Length 8 0 R", &"x".repeat(40))); + obj(&mut out, 10, &stream("/Length 11 0 R", "PDATA")); + // A cross-reference stream: a hybrid file's /XRefStm is not looked for behind junk. + let compressed = [(3, 4, 1), (8, 9, 0), (11, 4, 0)]; + let mut data = Vec::new(); + for (n, off) in offs.iter().enumerate() { + let row = match compressed.iter().find(|c| c.0 == n) { + Some(&(_, stream, index)) => [2, 0, stream, index], + None if *off == 0 => [0, 0, 0, 0], + None => { + let [.., hi, lo] = u32::try_from(*off).unwrap().to_be_bytes(); + [1, hi, lo, 0] + } + }; + data.extend_from_slice(&row); + } + let table = out.len(); + let dict = format!("<< /Type /XRef /Size 14 /W [1 2 1] /Index [0 13] /Root 1 0 R /Length {} >>", data.len()); + out.extend_from_slice(format!("13 0 obj\n{dict}\nstream\n").as_bytes()); + out.extend_from_slice(&data); + out.extend_from_slice(format!("\nendstream\nendobj\nstartxref\n{table}\n%%EOF\n").as_bytes()); + let mut file = vec![b'J'; offs[10] - offs[12] - 1]; + file.push(b'\n'); + file.extend_from_slice(&out); + let doc = Document::open(Arc::new(file)).unwrap(); + let mut edited = doc.clone(); + let cut = "11 0 3 2 5 << /Hidden (cut".len(); + let mut dict = Dict::new(); + dict.set(b"Type".to_vec(), Object::name("ObjStm")); + dict.set(b"N".to_vec(), Object::Int(1)); + dict.set(b"First".to_vec(), Object::Int(4)); + edited.set(ObjRef::new(9, 0), crate::Stream::from_raw(dict, format!("8 0 {cut}").into_bytes())); + assert!(matches!(&*edited.get(ObjRef::new(10, 0)), Object::Stream(s) if &s.raw[..] == b"PDATA")); + assert_ne!(text_of(&edited, 3, b"Hidden").as_deref(), Some("cut endstream here"), "the edited length was not used"); + assert_eq!(text_of(&doc, 3, b"Hidden").as_deref(), Some("cut endstream here"), "the edited length reached another clone"); +} + /// A classic table with `/Size` rows and object 0's free entry first, its subsection numbered /// `1 n` instead of `0 n` (#2676): every row is one number off. fn misnumbered_table(start: u32) -> Vec { @@ -1181,15 +1340,18 @@ fn reads_classic_revision_and_edits_are_copy_on_write() { fn object_numbers_merge_source_and_overlay_in_order() { let mut doc = Document::new_empty(); doc.overlay.clear(); - doc.entries = Arc::new(XrefIndex::Materialized(Arc::new(BTreeMap::from([ - (0, XrefEntry::Free { next_generation: 65535 }), - (2, XrefEntry::InFile { offset: 10, generation: 7 }), - (4, XrefEntry::Free { next_generation: 9 }), - (6, XrefEntry::InStream { stream: 80, index: 1 }), - (8, XrefEntry::InFile { offset: 20, generation: 5 }), - (10, XrefEntry::InFile { offset: 30, generation: 3 }), - (u32::MAX, XrefEntry::InFile { offset: 40, generation: 1 }), - ])))); + doc.entries = Arc::new(XrefIndex::Materialized( + Arc::new(BTreeMap::from([ + (0, XrefEntry::Free { next_generation: 65535 }), + (2, XrefEntry::InFile { offset: 10, generation: 7 }), + (4, XrefEntry::Free { next_generation: 9 }), + (6, XrefEntry::InStream { stream: 80, index: 1 }), + (8, XrefEntry::InFile { offset: 20, generation: 5 }), + (10, XrefEntry::InFile { offset: 30, generation: 3 }), + (u32::MAX, XrefEntry::InFile { offset: 40, generation: 1 }), + ])), + Arc::default(), + )); doc.set(ObjRef::new(1, 2), Object::Int(1)); // before the first live source slot doc.set(ObjRef::new(2, 8), Object::Int(2)); // override, without duplication doc.set(ObjRef::new(4, 9), Object::Int(4)); // reuse a source free slot @@ -1252,7 +1414,7 @@ fn temporary_reader_keeps_file_views_and_evicts_data_of_its_own() { // 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])); let size = held_bytes(&owned, &reader.document.data, 0); - reader.document.cache.lock().unwrap().insert(3, Arc::new(owned), size); + reader.document.cache.lock().unwrap().insert(3, Ok(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"); } @@ -1465,8 +1627,14 @@ fn hybrid_reference_files_read_the_xref_stream_too() { /// stream puts it at position `member` of object stream 4, which holds `header` (the number /// and offset pairs) and then `members`. fn object_stream_file(header: &str, members: &str, member: u8) -> Vec { + object_stream_file_with(header, members, member, false) +} + +/// [`object_stream_file`], with the stream's `/Length` in object 6 when `indirect_length`. +fn object_stream_file_with(header: &str, members: &str, member: u8, indirect_length: bool) -> Vec { let mut out = b"%PDF-1.5\n".to_vec(); - let mut offs = [0usize; 6]; + let size = if indirect_length { 7 } else { 6 }; + let mut offs = vec![0usize; size]; let mut obj = |out: &mut Vec, n: usize, body: &[u8]| { offs[n] = out.len(); out.extend_from_slice(format!("{n} 0 obj\n").as_bytes()); @@ -1477,7 +1645,8 @@ fn object_stream_file(header: &str, members: &str, member: u8) -> Vec { obj(&mut out, 2, b"<< /Type /Pages /Kids [] /Count 0 /Extra 3 0 R >>"); let count = header.split_whitespace().count() / 2; let inner = format!("{header}{members}"); - let mut stm = format!("<< /Type /ObjStm /N {count} /First {} /Length {} >>\nstream\n", header.len(), inner.len()).into_bytes(); + let length = if indirect_length { "6 0 R".to_string() } else { inner.len().to_string() }; + let mut stm = format!("<< /Type /ObjStm /N {count} /First {} /Length {length} >>\nstream\n", header.len()).into_bytes(); stm.extend_from_slice(inner.as_bytes()); stm.extend_from_slice(b"\nendstream"); obj(&mut out, 4, &stm); @@ -1486,13 +1655,16 @@ fn object_stream_file(header: &str, members: &str, member: u8) -> Vec { xs.extend_from_slice(&data); xs.extend_from_slice(b"\nendstream"); obj(&mut out, 5, &xs); + if indirect_length { + obj(&mut out, 6, inner.len().to_string().as_bytes()); + } let table = out.len(); - out.extend_from_slice(b"xref\n0 6\n0000000000 65535 f \n"); + out.extend_from_slice(format!("xref\n0 {size}\n0000000000 65535 f \n").as_bytes()); 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 6 /Root 1 0 R /XRefStm {} >>\nstartxref\n{table}\n%%EOF\n", offs[5]).as_bytes()); + out.extend_from_slice(format!("trailer << /Size {size} /Root 1 0 R /XRefStm {} >>\nstartxref\n{table}\n%%EOF\n", offs[5]).as_bytes()); out } @@ -1846,6 +2018,105 @@ 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"); } +/// A file whose object 3 (its `/Info`) can't be parsed: the rest reads. +fn with_unreadable_info() -> Vec { + build( + &["<< /Type /Catalog /Pages 2 0 R >>", "<< /Type /Pages /Kids [] /Count 0 >>", "<< /Title (Report) /Author ) >>"], + "/Root 1 0 R /Info 3 0 R", + ) +} + +/// An object that can't be parsed reads as null and is listed once, by number and generation, +/// with why. Clones and scans share the list, an edit takes the object off it (in that document +/// only), and a sound file lists nothing. +#[test] +fn unreadable_objects_are_listed_with_the_reason() { + let doc = Document::open(Arc::new(with_unreadable_info())).unwrap(); + assert!(doc.unreadable_objects().is_empty(), "nothing has read object 3 yet"); + assert_eq!(*doc.get(ObjRef::new(3, 0)), Object::Null); + assert!(doc.try_get(3).is_err()); + let lines = doc.unreadable_objects(); + assert_eq!(lines.len(), 1, "read twice, listed once: {lines:?}"); + assert!(lines[0].starts_with("object 3 0 could not be read: syntax error"), "{lines:?}"); + let scanned = doc.clone(); + assert_eq!(scanned.scan_objects_checked().filter(|(_, o)| o.is_err()).count(), 1); + assert_eq!(doc.unreadable_objects(), lines, "the scan found the same object"); + let unread = Document::open(Arc::new(with_unreadable_info())).unwrap(); + let scanned = unread.clone(); + assert_eq!(scanned.scan_objects_checked().filter(|(_, o)| o.is_err()).count(), 1); + assert_eq!(unread.unreadable_objects(), lines, "a clone's scan reaches the original"); + let mut edited = doc.clone(); + edited.set(ObjRef::new(3, 0), Object::Dict(Dict::new())); + assert!(edited.unreadable_objects().is_empty(), "the edit replaced it"); + assert_eq!(doc.unreadable_objects(), lines); + let sound = + build(&["<< /Type /Catalog /Pages 2 0 R >>", "<< /Type /Pages /Kids [] /Count 0 >>", "<< /Title (Report) >>"], "/Root 1 0 R /Info 3 0 R"); + let sound = Document::open(Arc::new(sound)).unwrap(); + assert_eq!(sound.scan_objects_checked().filter(|(_, o)| o.is_err()).count(), 0); + assert!(sound.unreadable_objects().is_empty()); +} + +/// A file rebuilt from its object headers still lists an object the scan could not read. +#[test] +fn a_rebuilt_file_lists_the_objects_its_scan_could_not_read() { + let text = "%PDF-1.7\n1 0 obj\n<< /Type /Catalog /Pages 2 0 R >>\nendobj\n2 0 obj\n<< /Type /Pages /Kids [] /Count 0 >>\nendobj\n3 0 obj\n<< /A ) >>\nendobj\n%%EOF\n"; + let doc = Document::open(Arc::new(text.as_bytes().to_vec())).unwrap(); + assert!(doc.repair_log().iter().any(|l| l.starts_with("rebuilt cross-reference index")), "{:?}", doc.repair_log()); + let lines = doc.unreadable_objects(); + assert_eq!(lines.len(), 1, "{lines:?}"); + assert!(lines[0].starts_with("object 3 0 could not be read: syntax error"), "{lines:?}"); +} + +/// The list keeps at most 100 objects and then says there were more; an object whose +/// cross-reference offset holds no object is listed with that as its reason. +#[test] +fn the_unreadable_object_list_is_bounded() { + let mut bodies = vec!["<< /Type /Catalog /Pages 2 0 R >>", "<< /Type /Pages /Kids [] /Count 0 >>"]; + bodies.extend(std::iter::repeat_n("<< /A ) >>", 120)); + let doc = Document::open(Arc::new(build(&bodies, "/Root 1 0 R"))).unwrap(); + assert_eq!(doc.scan_objects_checked().filter(|(_, o)| o.is_err()).count(), 120); + let lines = doc.unreadable_objects(); + assert_eq!(lines.len(), 101, "{:?}", lines.last()); + assert!(lines[0].starts_with("object 3 0 could not be read"), "{}", lines[0]); + assert_eq!(lines[100], "more objects could not be read; only the first 100 are listed"); + + let base = build(&["<< /Type /Catalog /Pages 2 0 R >>", "<< /Type /Pages /Kids [] /Count 0 >>", "(three)"], "/Root 1 0 R"); + let text = String::from_utf8_lossy(&base).into_owned(); + let gone = text.replacen("3 0 obj\n(three)", "9 0 obj\n(three)", 1); + let doc = Document::open(Arc::new(gone.into_bytes())).unwrap(); + assert!(doc.try_get(3).is_err()); + assert_eq!( + doc.unreadable_objects(), + ["object 3 0 could not be read: no readable copy was found at its cross-reference offset or elsewhere in the file"] + ); +} + +/// The unreadable list is shared by clones, and each hides what it has edited. A clone that edited +/// every listed object still lists its own failures: hidden entries don't use up its allowance. +#[test] +fn objects_a_clone_edited_do_not_use_up_its_unreadable_allowance() { + let mut bodies = vec!["<< /Type /Catalog /Pages 2 0 R >>", "<< /Type /Pages /Kids [] /Count 0 >>"]; + bodies.extend(std::iter::repeat_n("<< /A ) >>", 110)); + let doc = Document::open(Arc::new(build(&bodies, "/Root 1 0 R"))).unwrap(); + for num in 3..103 { + assert!(doc.try_get(num).is_err()); + } + assert_eq!(doc.unreadable_objects().len(), 100); + let mut edited = doc.clone(); + for num in 3..103 { + edited.set(ObjRef::new(num, 0), Object::Null); + } + for num in 103..113 { + assert!(edited.try_get(num).is_err()); + } + let lines = edited.unreadable_objects(); + assert_eq!(lines.len(), 10, "{lines:?}"); + assert!(lines[0].starts_with("object 103 0 could not be read"), "{}", lines[0]); + let original = doc.unreadable_objects(); + assert_eq!(original.len(), 101, "the original still shows at most 100, then says there were more"); + assert_eq!(original[100], "more objects could not be read; only the first 100 are listed"); +} + #[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 @@ -1881,10 +2152,10 @@ fn the_object_cache_keeps_its_total_as_objects_come_and_go() { 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); + cache.insert(1, Ok(one.clone()), a); + cache.insert(2, Ok(two), b); assert_eq!(cache.owned(), a + b); - cache.insert(2, one, a); + cache.insert(2, Ok(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)); @@ -1918,3 +2189,29 @@ fn the_editor_cache_charges_a_dictionary_for_the_values_it_holds() { 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"); } + +#[test] +fn find_agrees_with_a_plain_window_search() { + let naive = |hay: &[u8], needle: &[u8], from: usize, to: usize| { + if from >= to || needle.is_empty() || to - from < needle.len() { + return None; + } + hay[from..to].windows(needle.len()).position(|w| w == needle).map(|p| p + from) + }; + let mut seed = 0x9E37_79B9_7F4A_7C15u64; + let mut next = move || { + seed ^= seed << 13; + seed ^= seed >> 7; + seed ^= seed << 17; + seed + }; + let alphabet = b"/XRef t\n<>0"; + for _ in 0..20_000 { + let hay: Vec = (0..next() % 200).map(|_| alphabet[(next() % alphabet.len() as u64) as usize]).collect(); + let needles: [&[u8]; 5] = [b"/XRef", b"trailer", b"R", b"ff", b"<<"]; + let needle = needles[(next() % 5) as usize]; + let from = (next() % (hay.len() as u64 + 1)) as usize; + let to = from + (next() % (hay.len() as u64 + 1 - from as u64)) as usize; + assert_eq!(find(&hay, needle, from, to), naive(&hay, needle, from, to), "{hay:?} {needle:?} {from} {to}"); + } +} diff --git a/crates/cos/src/document/xref.rs b/crates/cos/src/document/xref.rs index 02390ff7da..771df28b80 100644 --- a/crates/cos/src/document/xref.rs +++ b/crates/cos/src/document/xref.rs @@ -41,7 +41,7 @@ pub(super) struct XrefRevisionSection { #[derive(Clone, Debug)] pub(super) enum XrefIndex { Compact { revisions: Vec, max_num: u32, has_entries: bool }, - Materialized(Arc>), + Materialized(Arc>, Arc>), } pub(super) const MAX_COMPACT_XREF_ROWS: usize = 2_000_000; @@ -149,8 +149,8 @@ impl XrefSection { } } - pub(super) fn extend_numbers(&self, numbers: &mut Vec) { - for range in &self.ranges { + pub(super) fn numbers(&self) -> impl Iterator + '_ { + self.ranges.iter().flat_map(|range| { let available = match &self.data { XrefSectionData::Table => range.count as usize, XrefSectionData::Stream { bytes, widths } => { @@ -158,14 +158,12 @@ impl XrefSection { bytes.len().saturating_sub(range.offset).checked_div(row_width).unwrap_or(0) } }; - for i in 0..available.min(range.count as usize) { - if let Ok(i) = u32::try_from(i) - && let Some(num) = range.start.checked_add(i) - { - numbers.push(num); - } - } - } + (0..available.min(range.count as usize)).filter_map(move |i| u32::try_from(i).ok().and_then(|i| range.start.checked_add(i))) + }) + } + + pub(super) fn extend_numbers(&self, numbers: &mut Vec) { + numbers.extend(self.numbers()); } } @@ -189,20 +187,20 @@ impl XrefRevisionSection { impl XrefIndex { pub(super) fn empty() -> Self { - Self::Materialized(Arc::new(BTreeMap::new())) + Self::Materialized(Arc::new(BTreeMap::new()), Arc::default()) } pub(super) fn lookup(&self, num: u32, file: &[u8]) -> Option { match self { Self::Compact { revisions, .. } => revisions.iter().find_map(|revision| revision.lookup(num, file)), - Self::Materialized(entries) => entries.get(&num).copied(), + Self::Materialized(entries, _) => entries.get(&num).copied(), } } pub(super) fn is_empty(&self) -> bool { match self { Self::Compact { has_entries, .. } => !has_entries, - Self::Materialized(entries) => entries.is_empty(), + Self::Materialized(entries, _) => entries.is_empty(), } } @@ -211,14 +209,14 @@ impl XrefIndex { pub(super) fn remove_exhausted(&mut self) -> bool { match self { Self::Compact { .. } => false, - Self::Materialized(entries) => Arc::make_mut(entries).remove(&u32::MAX).is_some(), + Self::Materialized(entries, _) => Arc::make_mut(entries).remove(&u32::MAX).is_some(), } } /// Every entry, newest section first, as the materialized reader keeps them. pub(super) fn to_map(&self, file: &[u8]) -> BTreeMap { match self { - Self::Materialized(entries) => entries.as_ref().clone(), + Self::Materialized(entries, _) => entries.as_ref().clone(), Self::Compact { revisions, .. } => { let mut numbers = Vec::new(); for revision in revisions { @@ -232,13 +230,13 @@ impl XrefIndex { pub(super) fn max_num(&self) -> u32 { match self { Self::Compact { max_num, .. } => *max_num, - Self::Materialized(entries) => entries.keys().next_back().copied().unwrap_or(0), + Self::Materialized(entries, _) => entries.keys().next_back().copied().unwrap_or(0), } } pub(super) fn object_numbers(&self, file: &[u8]) -> Vec { match self { - Self::Materialized(entries) => { + Self::Materialized(entries, _) => { entries.iter().filter_map(|(&num, entry)| (!matches!(entry, XrefEntry::Free { .. })).then_some(num)).collect() } Self::Compact { revisions, .. } => { diff --git a/crates/cos/src/lib.rs b/crates/cos/src/lib.rs index 8e051e4578..32a6f6d8b3 100644 --- a/crates/cos/src/lib.rs +++ b/crates/cos/src/lib.rs @@ -30,7 +30,7 @@ pub use parser::{Lexer, is_whitespace, parse_indirect}; pub use pdfcraft_crypt::{ Algorithm, Auth, Method as CryptMethod, NewEncryption, Permissions, SecurityHandler, effective_password, pdfdoc_byte, pdfdoc_char, }; -pub use writer::{SaveOptions, pdf_date, serialize, write_full, write_incremental}; +pub use writer::{SaveOptions, pdf_date, reachable_objects, serialize, write_full, write_incremental}; #[derive(Debug, thiserror::Error, Clone, PartialEq)] pub enum CosError { diff --git a/crates/cos/src/object.rs b/crates/cos/src/object.rs index 5d437faa82..68e8b1383e 100644 --- a/crates/cos/src/object.rs +++ b/crates/cos/src/object.rs @@ -297,13 +297,18 @@ impl Stream { /// [`Stream::decoded_within`] for a caller charging an allowance: the filter error is kept /// typed, so a caller can tell a spent limit from corrupt data, `max` bounds all filter - /// stages together, and the result gives the bytes they decoded (the work done, on success - /// and on failure). - pub(crate) fn decoded_within_counted(&self, max: usize) -> Result<(Vec, usize), (pdfcraft_filters::FilterError, usize)> { + /// stages together, and the result gives whether the data stopped at damage (it is then what + /// decoded before it) and the bytes the stages decoded (the work done, on success and on + /// failure). + pub(crate) fn decoded_within_counted(&self, max: usize) -> Result<(Vec, bool, usize), (pdfcraft_filters::FilterError, usize)> { + let mut damaged = false; let decode = |chain: &[(Filter, Params)], data: &[u8], max| { - pdfcraft_filters::decode_tolerant_counted(chain, data, max).map(|(v, _, spent)| (v, spent)) + pdfcraft_filters::decode_tolerant_counted(chain, data, max).map(|(v, partial, spent)| { + damaged = partial; + (v, spent) + }) }; - self.decode_chain(max, decode) + self.decode_chain(max, decode).map(|(v, spent)| (v, damaged, spent)) } /// [`Stream::decoded_within`] spending from `work`, what an operation may still do across a @@ -337,8 +342,14 @@ impl Stream { /// Decoded data, bounded by [`MAX_DECODED`]; any corruption is an error. pub fn decoded_strict(&self) -> Result, CosError> { + self.decoded_strict_within(MAX_DECODED) + } + + /// Like [`Stream::decoded_strict`], bounded by `max` (and [`MAX_DECODED`]): for data that + /// will be copied elsewhere, where a damaged stream must not pass for a shorter one. + pub fn decoded_strict_within(&self, max: usize) -> Result, CosError> { let decode = |chain: &[(Filter, Params)], data: &[u8], max| pdfcraft_filters::decode(chain, data, max).map(|v| (v, 0)).map_err(|e| (e, 0)); - self.decode_chain(MAX_DECODED, decode).map(|(v, _)| v).map_err(|(e, _)| CosError::Filter(e.to_string())) + self.decode_chain(max, decode).map(|(v, _)| v).map_err(|(e, _)| CosError::Filter(e.to_string())) } /// [`Stream::decoded_strict`] bounded by `max` and counted like diff --git a/crates/cos/src/writer.rs b/crates/cos/src/writer.rs index dcfcb97997..75d49dbd76 100644 --- a/crates/cos/src/writer.rs +++ b/crates/cos/src/writer.rs @@ -15,7 +15,7 @@ use std::io::Write; use std::sync::Arc; use crate::CosError; -use crate::document::{Document, ObjectReader, XrefEntry}; +use crate::document::{Document, ObjectReader, XrefEntry, held_bytes}; use crate::object::{Dict, ObjRef, Object, PdfString, Stream}; /// Serialize one object. Deterministic: same object → same bytes. @@ -23,9 +23,7 @@ pub fn serialize(o: &Object, out: &mut Vec) { match o { Object::Null => out.extend_from_slice(b"null"), Object::Bool(b) => out.extend_from_slice(if *b { b"true" } else { b"false" }), - Object::Int(i) => { - let _ = write!(out, "{i}"); - } + Object::Int(i) => write_int(*i, out), Object::Real(r) => write_real(*r, out), Object::String(s) => write_string(s, out), Object::Name(n) => write_name(n, out), @@ -42,11 +40,46 @@ pub fn serialize(o: &Object, out: &mut Vec) { Object::Dict(d) => write_dict(d, out), Object::Stream(s) => write_stream(s, out), Object::Ref(r) => { - let _ = write!(out, "{} {} R", r.num, r.generation); + write_digits(u64::from(r.num), out); + out.push(b' '); + write_digits(u64::from(r.generation), out); + out.extend_from_slice(b" R"); } } } +/// Upper-case hexadecimal digits. +const HEX: &[u8; 16] = b"0123456789ABCDEF"; + +/// The decimal digits of `v`, the same bytes `write!(out, "{v}")` gives, without the formatter. +fn write_digits(mut v: u64, out: &mut Vec) { + // `u64::MAX` has 20 digits, so `at` never goes below 0. + let mut buf = [0u8; 20]; + let mut at = buf.len(); + loop { + at -= 1; + buf[at] = b'0' + (v % 10) as u8; + v /= 10; + if v == 0 { + break; + } + } + out.extend_from_slice(&buf[at..]); +} + +/// A signed integer in decimal, as `write!(out, "{i}")` writes it. +fn write_int(i: i64, out: &mut Vec) { + if i < 0 { + out.push(b'-'); + } + write_digits(i.unsigned_abs(), out); +} + +/// `b` as two upper-case hexadecimal digits. +fn hex_pair(b: u8) -> [u8; 2] { + [HEX[usize::from(b >> 4)], HEX[usize::from(b & 15)]] +} + fn write_real(r: f64, out: &mut Vec) { if !r.is_finite() { out.push(b'0'); @@ -55,7 +88,7 @@ fn write_real(r: f64, out: &mut Vec) { // A whole number is written as an integer only within the integer range Annex C gives // (±2³¹−1), so `4e9` or `1e30` stays a real token for readers with 32-bit integers. if r.fract() == 0.0 && r.abs() <= f64::from(i32::MAX) { - let _ = write!(out, "{}", r as i32); + write_int(i64::from(r as i32), out); return; } // Plain decimal notation (§7.3.3 has no exponents). Rust's `Display` for f64 prints the @@ -76,7 +109,8 @@ fn write_name(n: &[u8], out: &mut Vec) { if regular { out.push(b); } else { - let _ = write!(out, "#{b:02X}"); + out.push(b'#'); + out.extend_from_slice(&hex_pair(b)); } } } @@ -84,9 +118,10 @@ fn write_name(n: &[u8], out: &mut Vec) { fn write_string(s: &PdfString, out: &mut Vec) { let binary = s.bytes.iter().filter(|b| !(b' '..=b'~').contains(*b) && !matches!(b, b'\n' | b'\r' | b'\t')).count(); if s.hex || binary * 4 > s.bytes.len().max(1) { + out.reserve(s.bytes.len().saturating_mul(2).saturating_add(2)); out.push(b'<'); - for b in &s.bytes { - let _ = write!(out, "{b:02X}"); + for &b in &s.bytes { + out.extend_from_slice(&hex_pair(b)); } out.push(b'>'); return; @@ -105,7 +140,7 @@ fn write_string(s: &PdfString, out: &mut Vec) { 0x0C => out.extend_from_slice(b"\\f"), b' '..=b'~' => out.push(b), _ => { - let _ = write!(out, "\\{b:03o}"); + out.extend_from_slice(&[b'\\', b'0' + (b >> 6), b'0' + ((b >> 3) & 7), b'0' + (b & 7)]); } } } @@ -167,11 +202,17 @@ pub struct SaveOptions { /// before adding it, with [`Document::free_unlinked_additions`]. Full saves always leave /// these out. pub drop_unlinked: bool, + /// Entropy for the file identifier of a rewrite that asks for a new one (see + /// [`Document::require_full_save_with_new_id`]). Given, the identifier depends only on this and + /// on the written bytes, so the same save gives the same file; tests use it to pin output. + /// Without it, fresh entropy from the host (the operating system on native targets, the + /// browser on WebAssembly) is mixed in. + pub id_entropy: Option<[u8; 16]>, } impl Default for SaveOptions { fn default() -> Self { - Self { mod_date: None, id_seed: 0x5052_494E_5443_5241, object_streams: true, drop_unlinked: false } + Self { mod_date: None, id_seed: 0x5052_494E_5443_5241, object_streams: true, drop_unlinked: false, id_entropy: None } } } @@ -267,20 +308,24 @@ pub fn write_incremental(doc: &Document, opts: &SaveOptions) -> Result, Ok(file) } -/// Write only reachable objects, renumbered from 1, with a table or cross-reference stream. -pub fn write_full(doc: &Document, opts: &SaveOptions) -> Result, CosError> { - if doc.stream_limited() { - return Err(CosError::ReadOnlyLimit); - } - // A full traversal must not fill the editor's shared caches (which undo snapshots also - // own). Parsed objects and decoded object streams are temporary working data here. - let mut reader = doc.object_reader(); - stamp_mod_date(&mut reader.document, opts); - let trailer_in = reader.document.trailer().clone(); +/// The objects [`write_full`] writes: everything reachable from the trailer's /Root, /Info and +/// /Encrypt and from its unknown entries, breadth-first, with the new number each gets +/// (aliases of one slot included) and, in visit order, whether it is a stream and the parsed +/// object where the budget allowed keeping it. +type SaveOrder = (HashMap, Vec<(ObjRef, bool)>, Vec>>); + +/// Number the objects reachable from the trailer. `retain` keeps parsed objects for the write +/// pass, up to the budget. A caller that needs only the numbers passes `false`, so the traversal +/// holds no parsed objects beyond the current one. +fn full_save_order(reader: &mut ObjectReader, trailer_in: &Dict, retain: bool) -> Result { // Breadth-first walk from the trailer, assigning new numbers in visit order. let mut map: HashMap = HashMap::new(); // Record the type while traversing so classifying packed objects needs no second parse. let mut order: Vec<(ObjRef, bool)> = Vec::new(); + // The parsed object of each entry in `order`, kept for the write pass while the budget + // allows it. Past the budget the write pass reads the object again. + let mut kept: Vec>> = Vec::new(); + let mut kept_budget = KeptObjects::default(); let mut queue: VecDeque = VecDeque::new(); let visit_refs = |o: &Object, queue: &mut VecDeque| collect_refs(o, &mut |r| queue.push_back(r)); for key in [&b"Root"[..], b"Info", b"Encrypt"] { @@ -307,10 +352,44 @@ pub fn write_full(doc: &Document, opts: &SaveOptions) -> Result, CosErro if matches!(*o, Object::Null) { continue; // dangling reference: written as null by renumbering below } - map.insert(r, output_number(order.len())?); - order.push((r, matches!(*o, Object::Stream(_)))); + // Accepted xref/header aliases denote one slot, including page-tree cycles. + // Check for null first: an unrelated or freed generation must remain dangling. + let canonical = ObjRef::new(r.num, reader.document.generation(r.num)); + if let Some(&num) = map.get(&canonical) { + map.insert(r, num); + continue; + } + let num = output_number(order.len())?; + map.insert(r, num); + map.insert(canonical, num); + order.push((canonical, matches!(*o, Object::Stream(_)))); visit_refs(&o, &mut queue); + kept.push((retain && kept_budget.admit(&o, reader.document.bytes())).then_some(o)); } + Ok((map, order, kept)) +} + +/// The object numbers a full save of `doc` would write: exactly the objects [`write_full`] +/// reaches from the trailer, object streams included. For a check that something removed from a +/// document cannot reach the saved file through a reference nobody looked for. +pub fn reachable_objects(doc: &Document) -> Result, CosError> { + let mut reader = doc.object_reader(); + let trailer_in = reader.document.trailer().clone(); + let (_, order, _) = full_save_order(&mut reader, &trailer_in, false)?; + Ok(order.into_iter().map(|(r, _)| r.num).collect()) +} + +/// Write only reachable objects, renumbered from 1, with a table or cross-reference stream. +pub fn write_full(doc: &Document, opts: &SaveOptions) -> Result, CosError> { + if doc.stream_limited() { + return Err(CosError::ReadOnlyLimit); + } + // A full traversal must not fill the editor's shared caches (which undo snapshots also + // own). Parsed objects and decoded object streams are temporary working data here. + let mut reader = doc.object_reader(); + stamp_mod_date(&mut reader.document, opts); + let trailer_in = reader.document.trailer().clone(); + let (map, order, mut kept) = full_save_order(&mut reader, &trailer_in, true)?; let version = reader.document.version().chars().take(3).collect::(); let version = if opts.object_streams && version.as_str() < "1.5" { "1.5".to_string() } else { version }; let mut out = Vec::new(); @@ -319,13 +398,15 @@ pub fn write_full(doc: &Document, opts: &SaveOptions) -> Result, CosErro out.extend_from_slice(&[b'%', 0xE2, 0xE3, 0xCF, 0xD3, b'\n']); // 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 = std::collections::HashSet::new(); + let mut encryption_objects: std::collections::HashSet = std::collections::HashSet::new(); let mut pending: Vec = 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) { + if let Some(&num) = map.get(&r) + && encryption_objects.insert(num) + { collect_refs(&reader.get(r), &mut |x| pending.push(x)); } } @@ -333,18 +414,19 @@ pub fn write_full(doc: &Document, opts: &SaveOptions) -> Result, CosErro // damaged and could not be repaired", before it even asks for the password), while other // readers accept it. qpdf keeps the catalog out of object streams too. Verified with // Acrobat DC on macOS (#774). - let root_outside = if reader.document.output_security().0.is_some() { trailer_in.reference(b"Root") } else { None }; + let root_outside = + if reader.document.output_security().0.is_some() { trailer_in.reference(b"Root").and_then(|r| map.get(&r)).copied() } else { None }; let mut rows: BTreeMap = BTreeMap::new(); // Keep only references, not renamed copies of the entire object graph. Standalone // objects still precede object streams, preserving the established output order. - let mut packed: Vec<(u32, ObjRef)> = Vec::new(); + let mut packed: Vec<(u32, ObjRef, Option>)> = Vec::new(); for (i, (r, is_stream)) in order.iter().enumerate() { let num = output_number(i)?; - let in_stream = opts.object_streams && !is_stream && !encryption_objects.contains(r) && root_outside != Some(*r); + let in_stream = opts.object_streams && !is_stream && !encryption_objects.contains(&num) && root_outside != Some(num); if in_stream { - packed.push((num, *r)); + packed.push((num, *r, kept[i].take())); } else { - let o = reread(&mut reader, *r, *is_stream)?; + let o = written_object(&mut reader, *r, *is_stream, kept[i].take())?; 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, &o, &mut out); @@ -354,9 +436,9 @@ pub fn write_full(doc: &Document, opts: &SaveOptions) -> Result, CosErro // individually: the whole stream is (§7.5.7, §7.6.2). let mut next = output_number(order.len())?; let mut batch = ObjectStreamBatch::default(); - for (num, reference) in packed { + for (num, reference, parsed) in packed { let mut encoded = Vec::new(); - serialize(&renumber(&*reread(&mut reader, reference, false)?, &map), &mut encoded); + serialize(&renumber(&*written_object(&mut reader, reference, false, parsed)?, &map), &mut encoded); if batch.count > 0 && batch.body.len().saturating_add(encoded.len()).saturating_add(1) > OBJSTM_BYTES { batch.flush(&reader.document, &mut next, &mut rows, &mut out)?; } @@ -371,26 +453,7 @@ pub fn write_full(doc: &Document, opts: &SaveOptions) -> Result, CosErro } } batch.flush(&reader.document, &mut next, &mut rows, &mut out)?; - let mut trailer = Dict::new(); - for key in [&b"Root"[..], b"Info", b"Encrypt"] { - if let Some(r) = trailer_in.reference(key).and_then(|r| map.get(&r)) { - trailer.set(key.to_vec(), Object::Ref(ObjRef::new(*r, 0))); - } - } - 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(), direct_id(&reader.document, id)); - } - for (key, value) in trailer_in.iter() { - if !trailer_key_rewritten(key) { - trailer.set(key.clone(), renumber(value, &map)); - } - } - if reader.document.output_security().0.is_none() { - ensure_id(&mut trailer, opts, reader.document.bytes()); - } + let mut trailer = full_save_trailer(&reader.document, &trailer_in, &map, opts, &out); if opts.object_streams { write_xref_stream(&mut out, 0, &mut trailer, rows, next); } else { @@ -409,6 +472,66 @@ pub fn write_full(doc: &Document, opts: &SaveOptions) -> Result, CosErro Ok(out) } +/// What `write_full` keeps of the objects it parsed while numbering them, measured with +/// [`held_bytes`] (the parsed tree and any data that is not a view into the file). Beyond the +/// budget objects are read again when written, which bounds the memory of a save of a huge +/// document. +#[derive(Default)] +struct KeptObjects { + bytes: usize, +} + +impl KeptObjects { + const BYTES: usize = 64 * 1024 * 1024; + + /// Whether `object` still fits the budget; if so it is counted against it. + fn admit(&mut self, object: &Object, data: &Arc>) -> bool { + let bytes = self.bytes.saturating_add(held_bytes(object, data, 0)); + if bytes > Self::BYTES { + return false; + } + self.bytes = bytes; + true + } +} + +/// The object to write for `r`: the one parsed while numbering when it was kept, else `r` read +/// again. +fn written_object(reader: &mut ObjectReader, r: ObjRef, is_stream: bool, kept: Option>) -> Result, CosError> { + match kept { + Some(o) => Ok(o), + None => reread(reader, r, is_stream), + } +} + +/// Assemble the full rewrite's trailer and apply its identifier policy. +fn full_save_trailer(doc: &Document, trailer_in: &Dict, map: &HashMap, opts: &SaveOptions, out: &[u8]) -> Dict { + let mut trailer = Dict::new(); + for key in [&b"Root"[..], b"Info", b"Encrypt"] { + if let Some(r) = trailer_in.reference(key).and_then(|r| map.get(&r)) { + trailer.set(key.to_vec(), Object::Ref(ObjRef::new(*r, 0))); + } + } + 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(), direct_id(doc, id)); + } + for (key, value) in trailer_in.iter() { + if !trailer_key_rewritten(key) { + trailer.set(key.clone(), renumber(value, map)); + } + } + if doc.output_security().0.is_none() { + ensure_id(&mut trailer, opts, doc.bytes()); + } + if doc.new_id_required() { + regenerate_id(&mut trailer, opts, out, doc.output_security().0.is_some()); + } + trailer +} + /// Object `r` read again for writing. The traversal read it once and only kept its number, so /// a second read that fails, finds nothing or finds a different kind of object must fail the /// save rather than write `null` in its place. @@ -657,6 +780,136 @@ fn ensure_id(trailer: &mut Dict, opts: &SaveOptions, content: &[u8]) { trailer.set(b"ID".to_vec(), Object::Array(vec![s.clone(), s])); } +/// Give a rewritten file a new identifier (§14.4), so that a redacted or sanitized copy does not +/// claim to be its source. An encrypted file keeps the first string, which its key is derived from, +/// and gets a new second one. When there is no such string (no `/ID`, one entry, or a first entry +/// that is not a string) the reader takes the empty string as the key input (`Document::first_id`), +/// so the empty string is written first and the key stays valid. +fn regenerate_id(trailer: &mut Dict, opts: &SaveOptions, written: &[u8], encrypted: bool) { + let fresh = Object::String(PdfString { bytes: new_id_bytes(opts, written), hex: true }); + let pair = if encrypted { + let first = match trailer.get(b"ID") { + Some(Object::Array(a)) => match a.first() { + Some(Object::String(s)) => Object::String(s.clone()), + _ => Object::String(PdfString { bytes: Vec::new(), hex: true }), + }, + _ => Object::String(PdfString { bytes: Vec::new(), hex: true }), + }; + vec![first, fresh] + } else { + vec![fresh.clone(), fresh] + }; + trailer.set(b"ID".to_vec(), Object::Array(pair)); +} + +/// FNV-1a over 64 bits, with its published offset basis and prime. The identifier is built from it +/// rather than from `std`'s `DefaultHasher`, whose algorithm the standard library does not specify. +const FNV_OFFSET: u64 = 0xcbf2_9ce4_8422_2325; +const FNV_PRIME: u64 = 0x0000_0100_0000_01b3; + +fn fnv1a(state: u64, bytes: &[u8]) -> u64 { + bytes.iter().fold(state, |h, b| (h ^ u64::from(*b)).wrapping_mul(FNV_PRIME)) +} + +/// Sixteen bytes for a file identifier, one 8-byte half per lane. The bytes are a pure function of +/// `SaveOptions::id_entropy`, `id_seed` and the written file: the hash is FNV-1a (above) and every +/// integer is written as a fixed-width big-endian value, so the same input gives the same identifier +/// on every platform and toolchain. Without entropy only the salt changes (see `id_salt`). FNV is +/// not collision-resistant against chosen content; the identifier only has to be unique, not secret. +/// Every written byte is hashed, once, in a single traversal of the output. +fn new_id_bytes(opts: &SaveOptions, written: &[u8]) -> Vec { + let salt = id_salt(opts); + let length = u64::try_from(written.len()).unwrap_or(u64::MAX); + let mut halves = [0u8, 1].map(|lane| { + let mut h = fnv1a(FNV_OFFSET, &salt.to_be_bytes()); + h = fnv1a(h, &[lane]); + h = fnv1a(h, &opts.id_seed.to_be_bytes()); + fnv1a(h, &length.to_be_bytes()) + }); + for chunk in written.chunks(4096) { + for h in &mut halves { + *h = fnv1a(*h, chunk); + } + } + halves.iter().flat_map(|h| h.to_be_bytes()).collect() +} + +/// The salt of an identifier. With caller entropy it is a fixed hash of that entropy (deterministic, +/// for tests and callers who pin output). Without it the salt is fresh: on WebAssembly from the +/// browser ([`browser_salt`], so two fresh web apps that write the same bytes cannot share an +/// identifier), and elsewhere from the standard library's random hash keys — seeded by the operating +/// system, so separate processes differ — mixed with a process-wide counter, which separates +/// successive calls in one process. +fn id_salt(opts: &SaveOptions) -> u64 { + use std::hash::BuildHasher; + use std::sync::atomic::{AtomicU64, Ordering}; + static COUNTER: AtomicU64 = AtomicU64::new(0); + match &opts.id_entropy { + Some(entropy) => fnv1a(FNV_OFFSET, entropy), + None => { + #[cfg(target_arch = "wasm32")] + if let Some(salt) = browser_salt() { + return salt; + } + std::collections::hash_map::RandomState::new().hash_one(COUNTER.fetch_add(1, Ordering::Relaxed)) + } + } +} + +/// One byte from one `Math.random` draw: the draw (in [0, 1)) scaled to [0, 256), integer part +/// taken. The quotient is in [0, 256), so a saturating cast never wraps; a NaN or infinite draw +/// (which a conforming engine never returns) folds in as 0. No input can panic here. +#[cfg(any(target_arch = "wasm32", test))] +fn draw_byte(random: f64) -> u8 { + (random * 256.0).floor().rem_euclid(256.0) as u8 +} + +/// The `Math.random` fallback's mixing: one salt byte per draw (see [`draw_byte`]), folded through +/// FNV-1a exactly like the Web Crypto bytes, so all sixteen bytes of the fold carry entropy from +/// the draws. Pure and platform-independent, so the native test target can exercise it; on wasm +/// each draw comes from `Math.random`. +#[cfg(any(target_arch = "wasm32", test))] +fn salt_from_draws(draws: &[f64; 16]) -> u64 { + let mut bytes = [0u8; 16]; + for (byte, draw) in bytes.iter_mut().zip(draws) { + *byte = draw_byte(*draw); + } + fnv1a(FNV_OFFSET, &bytes) +} + +/// Fresh salt entropy from the browser, on WebAssembly. `crypto.getRandomValues` (Web Crypto, the +/// browser's secure generator, available in windows and workers alike) gives sixteen bytes, folded +/// into one salt. When that API is missing or refuses the call, `Math.random` is mixed instead +/// ([`salt_from_draws`]: sixteen draws, so the salt's full width carries entropy) — browsers seed +/// it afresh for every document, so a fresh instance still cannot reproduce another's salt. Only +/// where neither is reachable does the caller fall back to its `RandomState` salt, whose keys are +/// fixed at compile time on `wasm32-unknown-unknown` — the state before browser entropy was wired +/// in. +#[cfg(target_arch = "wasm32")] +fn browser_salt() -> Option { + use wasm_bindgen::JsCast; + let crypto = js_sys::Reflect::get(&js_sys::global(), &wasm_bindgen::JsValue::from_str("crypto")) + .ok() + .filter(|crypto| !crypto.is_undefined() && !crypto.is_null()); + if let Some(crypto) = crypto { + let fill = js_sys::Reflect::get(&crypto, &wasm_bindgen::JsValue::from_str("getRandomValues")) + .ok() + .and_then(|fill| fill.dyn_into::().ok()); + if let Some(fill) = fill { + let bytes = js_sys::Uint8Array::new_with_length(16); + if fill.call1(&crypto, &bytes).is_ok() { + return Some(fnv1a(FNV_OFFSET, &bytes.to_vec())); + } + } + } + // Web Crypto is missing or refused the call: degrade to `Math.random` rather than giving up. + let mut draws = [0.0; 16]; + for draw in &mut draws { + *draw = js_sys::Math::random(); + } + Some(salt_from_draws(&draws)) +} + /// A PDF date string for "now" given seconds since the Unix epoch (UTC). pub fn pdf_date(unix_secs: i64) -> String { let (days, secs) = (unix_secs.div_euclid(86_400), unix_secs.rem_euclid(86_400)); @@ -699,6 +952,56 @@ mod tests { use proptest::prelude::*; + #[test] + fn the_same_entropy_and_bytes_give_the_same_identifier_on_every_platform() { + // Computed from the formula outside this crate: fixed-width big-endian fields and FNV-1a. + let opts = super::SaveOptions { id_entropy: Some([0x42; 16]), id_seed: 7, ..super::SaveOptions::default() }; + let want = [0x96, 0xf8, 0xcb, 0x7d, 0x5b, 0xb0, 0x09, 0xc8, 0x92, 0xc9, 0xb7, 0x51, 0xdf, 0xe6, 0xab, 0xd1]; + assert_eq!(super::new_id_bytes(&opts, b"%PDF-1.7\n"), want); + } + + #[test] + fn fnv1a_is_the_published_64_bit_algorithm() { + // Published FNV-1a (64 bit) test vectors, so the identifier can be reproduced outside this crate. + assert_eq!(super::fnv1a(super::FNV_OFFSET, b""), 0xcbf2_9ce4_8422_2325); + assert_eq!(super::fnv1a(super::FNV_OFFSET, b"a"), 0xaf63_dc4c_8601_ec8c); + assert_eq!(super::fnv1a(super::FNV_OFFSET, b"foobar"), 0x8594_4171_f739_67e8); + } + + #[test] + fn math_random_draws_fill_the_whole_salt_width() { + // Draw i = (i + 1/2)/256 scales to the integer i, so the fold's byte i proves draw i landed + // there: all sixteen bytes carry their own draw's entropy (the fallback once shifted four + // draws into one word, leaving the other four bytes of the fold constant). + let draws: [f64; 16] = std::array::from_fn(|i| (i as f64 + 0.5) / 256.0); + let bytes: Vec = (0..16).collect(); + assert_eq!(super::salt_from_draws(&draws), super::fnv1a(super::FNV_OFFSET, &bytes)); + } + + #[test] + fn every_math_random_draw_reaches_the_salt() { + let base = [0.5; 16]; + let baseline = super::salt_from_draws(&base); + for i in 0..16 { + let mut draws = base; + draws[i] = 0.75; + assert_ne!(super::salt_from_draws(&draws), baseline, "draw {i} did not reach the salt"); + } + } + + #[test] + fn a_math_random_draw_outside_its_range_still_mixes_without_panicking() { + // A conforming `Math.random` stays in [0, 1), but the mixing must not panic outside it. + assert_eq!(super::draw_byte(0.0), 0); + assert_eq!(super::draw_byte(0.5), 128); + assert_eq!(super::draw_byte(255.5 / 256.0), 255); + assert_eq!(super::draw_byte(-0.5 / 256.0), 255); + assert_eq!(super::draw_byte(-1.0), 0); + assert_eq!(super::draw_byte(2.0), 0); + assert_eq!(super::draw_byte(f64::NAN), 0); + assert_eq!(super::draw_byte(f64::INFINITY), 0); + } + use super::*; use crate::Lexer; @@ -708,6 +1011,38 @@ mod tests { Lexer::new(&out, 0).object().expect("parses") } + #[test] + fn kept_objects_stop_at_their_byte_budget() { + let data = Arc::new(Vec::new()); + let string = Object::String(PdfString::literal(vec![b'x'; 1000])); + let array = Object::Array(vec![Object::Int(1), Object::Null]); + let mut kept = KeptObjects::default(); + assert!(kept.admit(&string, &data) && kept.admit(&array, &data)); + assert_eq!(kept.bytes, held_bytes(&string, &data, 0) + held_bytes(&array, &data, 0)); + let mut full = KeptObjects { bytes: KeptObjects::BYTES - held_bytes(&string, &data, 0) + 1 }; + let before = full.bytes; + assert!(!full.admit(&string, &data), "one byte over the budget"); + assert_eq!(full.bytes, before, "a refused object is not counted"); + let mut deep = Object::Null; + for _ in 0..300 { + deep = Object::Array(vec![deep]); + } + assert!(!KeptObjects::default().admit(&deep, &data), "nesting past the limit is never kept"); + } + + #[test] + fn kept_objects_count_names_and_dictionary_keys() { + let data = Arc::new(Vec::new()); + let name = Object::Name(vec![b'n'; KeptObjects::BYTES + 1]); + let mut kept = KeptObjects::default(); + assert!(!kept.admit(&name, &data), "a name over the byte budget is not kept"); + assert_eq!(kept.bytes, 0); + let mut dict = Dict::new(); + dict.set(vec![b'k'; KeptObjects::BYTES + 1], Object::Null); + assert!(!kept.admit(&Object::Dict(dict), &data), "nor a dictionary key"); + assert_eq!(kept.bytes, 0); + } + #[test] fn a_second_read_that_differs_fails_the_save_instead_of_writing_null() { let mut doc = Document::new_empty(); diff --git a/crates/cos/tests/file_identifier.rs b/crates/cos/tests/file_identifier.rs new file mode 100644 index 0000000000..313d56257b --- /dev/null +++ b/crates/cos/tests/file_identifier.rs @@ -0,0 +1,276 @@ +//! The file identifier (`/ID`, ISO 32000-2 §14.4) of a full save. An ordinary save keeps the +//! identifier the file has and writes the same bytes twice. A rewrite the document asked for (after +//! redaction or sanitizing) gives the file a new pair. An encrypted file keeps its first string, +//! because its file key is derived from it. + +use std::sync::Arc; + +use pdfcraft_cos::{Algorithm, Document, NewEncryption, Object, PdfString, SaveOptions, write_full, write_incremental}; +use pdfcraft_testkit::Pdf; + +const ID_HEX: &str = "/ID [<00112233445566778899AABBCCDDEEFF> <00112233445566778899AABBCCDDEEFF>]"; +const ID_BYTES: [u8; 16] = [0x00, 0x11, 0x22, 0x33, 0x44, 0x55, 0x66, 0x77, 0x88, 0x99, 0xAA, 0xBB, 0xCC, 0xDD, 0xEE, 0xFF]; + +/// One page whose content holds a secret, with `entry` added to the trailer (for example an `/ID`). +fn source_with(entry: Option<&str>) -> Vec { + let pdf = Pdf::new() + .obj("<< /Type /Catalog /Pages 2 0 R >>") + .obj("<< /Type /Pages /Kids [3 0 R] /Count 1 /MediaBox [0 0 200 200] >>") + .obj("<< /Type /Page /Parent 2 0 R /Contents 4 0 R /Resources << /Font << /F1 5 0 R >> >> >>") + .stream("", "BT /F1 12 Tf 20 100 Td (TOPSECRET) Tj ET") + .obj("<< /Type /Font /Subtype /Type1 /BaseFont /Helvetica >>"); + match entry { + Some(entry) => pdf.trailer_entry(entry).build(), + None => pdf.build(), + } +} + +/// [`source_with`] with the standard identifier, or none. +fn source(with_id: bool) -> Vec { + source_with(with_id.then_some(ID_HEX)) +} + +/// A one-page file whose 70,000-byte content stream ends in `last`. Two of these built with +/// different last bytes have the same length and differ only past the first 64 KiB. +fn large_source(last: u8) -> Vec { + let mut content = vec![b' '; 70_000]; + content.push(last); + Pdf::new() + .obj("<< /Type /Catalog /Pages 2 0 R >>") + .obj("<< /Type /Pages /Kids [3 0 R] /Count 1 /MediaBox [0 0 200 200] >>") + .obj("<< /Type /Page /Parent 2 0 R /Contents 4 0 R /Resources << /Font << /F1 5 0 R >> >> >>") + .stream("", content) + .obj("<< /Type /Font /Subtype /Type1 /BaseFont /Helvetica >>") + .build() +} + +fn reopen(bytes: Vec) -> Document { + Document::open(Arc::new(bytes)).unwrap() +} + +/// The strings of the trailer's `/ID` (empty when there is none). +fn id_strings(doc: &Document) -> Vec> { + match doc.trailer().get(b"ID") { + Some(Object::Array(a)) => a.iter().map(|s| s.as_string().map(|s| s.bytes.clone()).unwrap_or_default()).collect(), + _ => Vec::new(), + } +} + +#[test] +fn an_ordinary_save_keeps_the_identifier_and_writes_the_same_bytes() { + let doc = reopen(source(true)); + let opts = SaveOptions::default(); + let saved = write_full(&doc, &opts).unwrap(); + assert_eq!(saved, write_full(&doc, &opts).unwrap(), "unchanged inputs produce identical bytes"); + assert_eq!(id_strings(&reopen(saved)), vec![ID_BYTES.to_vec(), ID_BYTES.to_vec()]); + let appended = reopen(write_incremental(&doc, &opts).unwrap()); + assert_eq!(id_strings(&appended), vec![ID_BYTES.to_vec(), ID_BYTES.to_vec()]); +} + +#[test] +fn an_ordinary_save_of_a_file_without_an_identifier_creates_the_same_one_every_time() { + let doc = reopen(source(false)); + let opts = SaveOptions::default(); + let saved = write_full(&doc, &opts).unwrap(); + assert_eq!(saved, write_full(&doc, &opts).unwrap(), "unchanged inputs produce identical bytes"); + let ids = id_strings(&reopen(saved)); + assert_eq!(ids.len(), 2); + assert!(ids.iter().all(|s| s.len() == 16), "{ids:?}"); +} + +#[test] +fn a_rewrite_the_document_asked_for_gets_a_new_identifier() { + let mut doc = reopen(source(true)); + doc.require_full_save_with_new_id(); + assert!(doc.full_save_required() && doc.new_id_required()); + let opts = SaveOptions::default(); + for saved in [write_incremental(&doc, &opts).unwrap(), write_full(&doc, &opts).unwrap()] { + let ids = id_strings(&reopen(saved)); + assert_eq!(ids.len(), 2); + for id in &ids { + assert_eq!(id.len(), 16); + assert_ne!(id.as_slice(), ID_BYTES.as_slice(), "the copy must not claim the source's identifier"); + } + } + // Every save is a new identity, not the same one again. + let first = id_strings(&reopen(write_full(&doc, &opts).unwrap())); + let second = id_strings(&reopen(write_full(&doc, &opts).unwrap())); + assert_ne!(first, second); +} + +#[test] +fn a_rewrite_without_an_identifier_still_gets_one() { + let mut doc = reopen(source(false)); + doc.require_full_save_with_new_id(); + let ids = id_strings(&reopen(write_full(&doc, &SaveOptions::default()).unwrap())); + assert_eq!(ids.len(), 2); + assert!(ids.iter().all(|s| s.len() == 16), "{ids:?}"); +} + +#[test] +fn caller_entropy_makes_the_new_identifier_reproducible() { + let mut doc = reopen(source(true)); + doc.require_full_save_with_new_id(); + let with = |entropy: u8| SaveOptions { id_entropy: Some([entropy; 16]), ..SaveOptions::default() }; + let first = write_full(&doc, &with(1)).unwrap(); + assert_eq!(first, write_full(&doc, &with(1)).unwrap(), "the same entropy gives the same bytes"); + let other = write_full(&doc, &with(2)).unwrap(); + assert_ne!(id_strings(&reopen(first)), id_strings(&reopen(other)), "different entropy gives a different identifier"); +} + +#[test] +fn an_encrypted_rewrite_keeps_the_first_identifier_string_its_key_depends_on() { + for algorithm in [Algorithm::Rc4_128, Algorithm::Aes128, Algorithm::Aes256] { + let mut doc = reopen(source(true)); + doc.set_encryption(&NewEncryption { + algorithm, + user_password: "user", + owner_password: "owner", + permissions: -1, + encrypt_metadata: true, + seed: [5; 32], + }) + .unwrap(); + let protected = write_full(&doc, &SaveOptions::default()).unwrap(); + let before = Document::open_with_password(Arc::new(protected), Some("user")).unwrap(); + + let mut doc = before.clone(); + doc.require_full_save_with_new_id(); + let out = write_incremental(&doc, &SaveOptions::default()).unwrap(); + // The output opens with the same password only if its first identifier string is unchanged. + let back = Document::open_with_password(Arc::new(out), Some("user")).unwrap(); + let (old, new) = (id_strings(&before), id_strings(&back)); + assert_eq!(new.len(), 2, "{algorithm:?}"); + assert_eq!(new.first(), old.first(), "{algorithm:?}: the key depends on the first string"); + assert_ne!(new.get(1), old.get(1), "{algorithm:?}: the second string is new"); + } +} + +/// The `/ID` shapes whose key the reader takes as the empty string: none at all, one entry, and a +/// first entry that is not a string. +fn unusable_ids() -> Vec<(&'static str, Option)> { + let empty = Object::String(PdfString::literal(Vec::new())); + vec![ + ("absent", None), + ("one entry", Some(Object::Array(vec![empty.clone()]))), + ("first entry not a string", Some(Object::Array(vec![Object::Int(7), empty]))), + ] +} + +/// An encrypted file whose key is derived from the empty string, with its trailer `/ID` replaced by `id`. +fn protected_with_id(algorithm: Algorithm, id: Option) -> Vec { + let mut doc = reopen(source_with(Some("/ID [<> <>]"))); + doc.set_encryption(&NewEncryption { + algorithm, + user_password: "user", + owner_password: "owner", + permissions: -1, + encrypt_metadata: true, + seed: [5; 32], + }) + .unwrap(); + match id { + Some(id) => doc.trailer_mut().set(b"ID".to_vec(), id), + None => { + doc.trailer_mut().remove(b"ID"); + } + } + write_full(&doc, &SaveOptions::default()).unwrap() +} + +#[test] +fn an_encrypted_rewrite_without_a_usable_identifier_still_gets_a_new_one() { + // The key is derived from the first string of /ID, and a missing /ID, a one-entry /ID and a + // first entry that is not a string all count as the empty string. The rewrite keeps that + // (empty) first string, so the file still opens with its password, and writes a new second one. + for algorithm in [Algorithm::Rc4_128, Algorithm::Aes128, Algorithm::Aes256] { + for (shape, id) in unusable_ids() { + let before = Document::open_with_password(Arc::new(protected_with_id(algorithm, id)), Some("user")).unwrap(); + let mut doc = before.clone(); + doc.require_full_save_with_new_id(); + let out = write_incremental(&doc, &SaveOptions::default()).unwrap(); + let back = Document::open_with_password(Arc::new(out), Some("user")).unwrap(); + let ids = id_strings(&back); + let previous = id_strings(&before); + assert_eq!(ids.len(), 2, "{algorithm:?}, {shape}: the rewrite writes a pair"); + assert!(ids.first().is_some_and(|s| s.is_empty()), "{algorithm:?}, {shape}: the first string is the one the key uses"); + assert_eq!(ids.get(1).map(Vec::len), Some(16), "{algorithm:?}, {shape}"); + assert_ne!(ids.get(1), previous.get(1), "{algorithm:?}, {shape}: the second string is new"); + } + } +} + +/// The standard fixture rewritten for a new identifier, with `id_entropy` of 0x42. +fn fixed_entropy_rewrite() -> Vec { + let mut doc = reopen(source(true)); + doc.require_full_save_with_new_id(); + write_full(&doc, &SaveOptions { id_entropy: Some([0x42; 16]), ..SaveOptions::default() }).unwrap() +} + +#[test] +fn a_fixed_entropy_gives_the_same_identifier_every_time() { + // The formula itself is pinned on fixed bytes in the writer's tests. The written file is not the + // same on every platform, so no identifier of a rewrite can be pinned here. + let first = id_strings(&reopen(fixed_entropy_rewrite())); + assert_eq!(first.len(), 2); + assert!(first.iter().all(|s| s.len() == 16), "{first:?}"); + assert_eq!(first, id_strings(&reopen(fixed_entropy_rewrite()))); +} + +#[test] +fn the_identifier_depends_on_the_whole_rewritten_file() { + // Same caller entropy and same length; the two rewrites differ only in one byte of a stream + // that lies past the first 64 KiB of the output. Their identifiers must still differ. + let opts = SaveOptions { id_entropy: Some([9; 16]), ..SaveOptions::default() }; + let rewrite = |last: u8| { + let mut doc = reopen(large_source(last)); + doc.require_full_save_with_new_id(); + write_full(&doc, &opts).unwrap() + }; + let (a, b) = (rewrite(b'A'), rewrite(b'B')); + assert_eq!(a.len(), b.len(), "the two rewrites have the same length"); + let first_difference = a.iter().zip(&b).position(|(x, y)| x != y).unwrap_or(usize::MAX); + assert!(first_difference > 64 * 1024, "the rewrites first differ at byte {first_difference}, inside the first 64 KiB"); + assert_ne!(id_strings(&reopen(a)), id_strings(&reopen(b)), "content past 64 KiB must change the identifier"); +} + +/// Where [`stand_in_for_a_fresh_process`] writes its rewrite. +const ID_PROBE: &str = "PDFCRAFT_TEST_ID_PROBE"; + +/// The child half of [`separate_fresh_processes_get_different_identifiers`]: it runs alone, in its +/// own process, and writes a default-path rewrite of the standard fixture to the file the parent +/// named. Without the variable it is a plain no-op. +#[test] +fn stand_in_for_a_fresh_process() { + let Some(path) = std::env::var_os(ID_PROBE) else { return }; + let mut doc = reopen(source(true)); + doc.require_full_save_with_new_id(); + std::fs::write(path, write_full(&doc, &SaveOptions::default()).unwrap()).unwrap(); +} + +#[test] +fn separate_fresh_processes_get_different_identifiers() { + // The default identifier is meant to differ between fresh instances of the whole save pipeline, + // not only between two calls in one process (which the counter already separates). On the native + // test target a fresh instance is a fresh process, whose hash keys the operating system seeds; + // the fix under test runs on WebAssembly, where no browser test harness exists — there the + // browser's `crypto.getRandomValues` stands in for this seeding, and this test cannot see it. + let exe = std::env::current_exe().unwrap(); + let probe = |name: &str| { + let path = std::env::temp_dir().join(format!("pdfcraft-id-probe-{}-{name}.pdf", std::process::id())); + let out = std::process::Command::new(&exe) + .args(["--exact", "stand_in_for_a_fresh_process", "--nocapture", "--"]) + .env(ID_PROBE, &path) + .output() + .expect("run this test's own binary as a child"); + assert!(out.status.success(), "{name}: the child failed: {}", String::from_utf8_lossy(&out.stderr)); + let saved = std::fs::read(&path).unwrap_or_else(|e| panic!("{name}: the child wrote its file: {e}")); + let ids = id_strings(&reopen(saved)); + assert_eq!(ids.len(), 2, "{name}"); + assert!(ids.iter().all(|s| s.len() == 16), "{name}: {ids:?}"); + let _ = std::fs::remove_file(&path); + ids + }; + let (first, second) = (probe("a"), probe("b")); + assert_ne!(first, second, "two fresh processes must not share an identifier"); +} diff --git a/crates/cos/tests/it/generations.rs b/crates/cos/tests/it/generations.rs new file mode 100644 index 0000000000..bbe2ff0b33 --- /dev/null +++ b/crates/cos/tests/it/generations.rs @@ -0,0 +1,510 @@ +//! An indirect reference identifies an object number AND its generation (ISO 32000-2 §7.3.10). + +use std::sync::Arc; + +use hayro_syntax::object::{Dict as HayroDict, ObjectIdentifier}; +use pdfcraft_cos::{Document, ObjRef, Object, SaveOptions, XrefEntry, write_full, write_incremental}; + +/// Object 3 was reused: only 3 1 R refers to the current value, never 3 0 R. +fn reused_object() -> Arc> { + object_file(&[ + (1, 0, "<< /Type /Catalog /Pages 2 0 R /Stale 3 0 R /Current 3 1 R >>"), + (2, 0, "<< /Type /Pages /Kids [] /Count 0 >>"), + (3, 1, "42"), + ]) +} + +fn object_file(objects: &[(u32, u16, &str)]) -> Arc> { + object_file_with_entry(objects, None) +} + +fn object_file_with_entry(objects: &[(u32, u16, &str)], changed: Option<(u32, u16, bool)>) -> Arc> { + let mut bytes = b"%PDF-1.7\n".to_vec(); + let mut offsets = Vec::new(); + for (num, generation, value) in objects { + offsets.push((*num, bytes.len(), *generation)); + bytes.extend_from_slice(format!("{num} {generation} obj\n{value}\nendobj\n").as_bytes()); + } + let xref = bytes.len(); + let size = objects.len() + 1; + bytes.extend_from_slice(format!("xref\n0 {size}\n0000000000 65535 f \n").as_bytes()); + for (num, offset, generation) in offsets { + let (generation, free) = changed.filter(|(n, _, _)| *n == num).map_or((generation, false), |(_, g, free)| (g, free)); + let (offset, kind) = if free { (0, 'f') } else { (offset, 'n') }; + bytes.extend_from_slice(format!("{offset:010} {generation:05} {kind} \n").as_bytes()); + } + bytes.extend_from_slice(format!("trailer\n<< /Size {size} /Root 1 0 R >>\nstartxref\n{xref}\n%%EOF\n").as_bytes()); + Arc::new(bytes) +} + +fn contradictory_entry(free: bool) -> Arc> { + object_file_with_entry( + &[(1, 0, "<< /Type /Catalog /Pages 2 0 R /Stale 3 0 R /Current 3 1 R >>"), (2, 0, "<< /Type /Pages /Kids [] /Count 0 >>"), (3, 1, "42")], + Some((3, if free { 2 } else { 0 }, free)), + ) +} + +#[test] +fn contradictory_xref_generation_recovers_the_matching_header_and_records_repair() { + for warm in [false, true] { + let doc = Document::open(contradictory_entry(false)).unwrap(); + if warm { + assert_eq!(*doc.try_get(3).unwrap(), Object::Int(42)); + } + assert_eq!(*doc.get(ObjRef::new(3, 1)), Object::Int(42)); + assert_eq!(*doc.resolve(&Object::Ref(ObjRef::new(3, 1))), Object::Int(42)); + // Preserve the existing xref-matching behavior, but never accept an unrelated generation. + assert_eq!(*doc.get(ObjRef::new(3, 0)), Object::Int(42)); + assert_eq!(*doc.get(ObjRef::new(3, 2)), Object::Null); + assert!(!doc.xref_entry_is_exact(3), "a contradictory generation is not an exact xref entry"); + assert!( + doc.repair_log() + .iter() + .any(|line| { line.contains("object 3") && line.contains("xref generation 0") && line.contains("header generation 1") }), + "{:?}", + doc.repair_log() + ); + let repairs = doc.repair_log().to_vec(); + for _ in 0..3 { + assert_eq!(*doc.get(ObjRef::new(3, 1)), Object::Int(42)); + } + assert_eq!(doc.repair_log(), repairs); + + let mut edited = doc.clone(); + edited.free(ObjRef::new(3, 1)); + for generation in [0, 1, 2] { + assert_eq!(*edited.get(ObjRef::new(3, generation)), Object::Null); + } + edited.set(ObjRef::new(3, 2), Object::Int(99)); + assert_eq!(*edited.get(ObjRef::new(3, 1)), Object::Null); + assert_eq!(*edited.get(ObjRef::new(3, 2)), Object::Int(99)); + assert_eq!(*doc.get(ObjRef::new(3, 1)), Object::Int(42)); + } +} + +/// A damaged row may name generation zero while the retained object and catalog use one. +fn contradictory_dictionary() -> Arc> { + object_file_with_entry( + &[(1, 0, "<< /Type /Catalog /Pages 2 0 R /Current 3 1 R >>"), (2, 0, "<< /Type /Pages /Kids [] /Count 0 >>"), (3, 1, "<< /Value 42 >>")], + Some((3, 0, false)), + ) +} + +fn assert_repaired_dictionary(bytes: Vec, value: i32) { + let bytes = Arc::new(bytes); + let oracle = hayro_syntax::Pdf::new(bytes.clone()).unwrap(); + let catalog = oracle.xref().get::>(ObjectIdentifier::new(1, 0)).unwrap(); + assert_eq!(catalog.get::>(b"Current").unwrap().get::(b"Value"), Some(value)); + let back = Document::open(bytes).unwrap(); + let catalog = back.get(back.root().unwrap()); + let current = back.resolve(catalog.as_dict().unwrap().get(b"Current").unwrap()); + assert_eq!(current.as_dict().unwrap().int(b"Value"), Some(i64::from(value))); +} + +#[test] +fn repaired_header_references_survive_full_saves_and_dictionary_edits() { + let original = contradictory_dictionary(); + let doc = Document::open(original.clone()).unwrap(); + for object_streams in [false, true] { + assert_repaired_dictionary(write_full(&doc, &SaveOptions { object_streams, ..SaveOptions::default() }).unwrap(), 42); + } + let mut edited = doc.clone(); + edited.update_dict(ObjRef::new(3, 1), |dict| dict.set(b"Value".to_vec(), Object::Int(77))).unwrap(); + assert_eq!(edited.generation(3), 1); + let incremental = write_incremental(&edited, &SaveOptions::default()).unwrap(); + assert!(edited.full_save_required(), "repair-aware dictionary edits normalize on full rewrite"); + assert_repaired_dictionary(incremental, 77); + for object_streams in [false, true] { + assert_repaired_dictionary(write_full(&edited, &SaveOptions { object_streams, ..SaveOptions::default() }).unwrap(), 77); + } + let mut restored = doc.clone(); + restored.overlay_changes_from(&edited).unwrap(); + assert_repaired_dictionary(write_incremental(&restored, &SaveOptions::default()).unwrap(), 77); +} + +#[test] +fn free_xref_slots_never_revive_retained_object_headers() { + for warm in [false, true] { + let doc = Document::open(contradictory_entry(true)).unwrap(); + assert!(matches!(doc.xref_entry(3), Some(XrefEntry::Free { next_generation: 2 }))); + if warm { + assert_eq!(*doc.try_get(3).unwrap(), Object::Null); + } + for generation in [0, 1, 2] { + assert_eq!(*doc.get(ObjRef::new(3, generation)), Object::Null); + } + assert_eq!(*doc.resolve(&Object::Ref(ObjRef::new(3, 1))), Object::Null); + assert!(doc.repair_log().is_empty(), "{:?}", doc.repair_log()); + } + // Control: the retained bytes really are a readable object when its slot is live. + let live = Document::open(contradictory_entry(false)).unwrap(); + assert_eq!(*live.try_get(3).unwrap(), Object::Int(42)); +} + +#[test] +fn incremental_generation_identity_is_visible_to_an_independent_reader() { + let original = reused_object(); + let mut doc = Document::open(original.clone()).unwrap(); + doc.set(ObjRef::new(3, 1), Object::Int(77)); + let bytes = write_incremental(&doc, &SaveOptions::default()).unwrap(); + assert!(bytes.starts_with(&original)); + let oracle = hayro_syntax::Pdf::new(Arc::new(bytes)).unwrap(); + let catalog = oracle.xref().get::>(ObjectIdentifier::new(1, 0)).unwrap(); + assert_eq!(catalog.get::(b"Current"), Some(77)); + assert_eq!(catalog.get::(b"Stale"), None); +} + +#[test] +fn generation_repair_diagnostics_are_bounded_without_disabling_recovery() { + let mut objects = vec![(1, 0, "<< /Type /Catalog /Pages 2 0 R >>"), (2, 0, "<< /Type /Pages /Kids [] /Count 0 >>")]; + objects.extend((3..303).map(|num| (num, 1, "42"))); + let bytes = object_file(&objects); + let bytes = String::from_utf8(bytes.as_ref().clone()).unwrap().replace("00001 n \n", "00000 n \n"); + for materialized in [false, true] { + let bytes = if materialized { bytes.replace("/Size 303", "/Size 302") } else { bytes.clone() }; + let doc = Document::open(Arc::new(bytes.into_bytes())).unwrap(); + assert_eq!(doc.repair_log().len(), 257); + assert!(doc.repair_log().last().unwrap().contains("omitted after 256 objects")); + assert_eq!(*doc.get(ObjRef::new(3, 1)), Object::Int(42)); + assert_eq!(*doc.get(ObjRef::new(302, 1)), Object::Int(42)); + assert_eq!(*doc.get(ObjRef::new(302, 2)), Object::Null); + assert_eq!(doc.repair_log().len(), 257); + } +} + +#[test] +fn references_require_the_current_generation_even_with_a_warm_cache() { + let bytes = reused_object(); + let oracle = hayro_syntax::Pdf::new(bytes.clone()).unwrap(); + assert_eq!(oracle.xref().get::(ObjectIdentifier::new(3, 0)), None); + assert_eq!(oracle.xref().get::(ObjectIdentifier::new(3, 1)), Some(42)); + + let doc = Document::open(bytes).unwrap(); + assert!(doc.repair_log().is_empty()); + assert_eq!(*doc.get(ObjRef::new(3, 0)), Object::Null); + assert_eq!(*doc.try_get(3).unwrap(), Object::Int(42)); + assert_eq!(*doc.get(ObjRef::new(3, 1)), Object::Int(42)); + assert_eq!(*doc.get(ObjRef::new(3, 0)), Object::Null); + assert_eq!(*doc.resolve(&Object::Ref(ObjRef::new(3, 0))), Object::Null); + assert_eq!(*doc.get(ObjRef::new(3, 2)), Object::Null); +} + +#[test] +fn overlay_generation_changes_do_not_retarget_old_references_or_clones() { + let mut doc = Document::open(reused_object()).unwrap(); + let snapshot = doc.clone(); + let old = ObjRef::new(3, 1); + let new = ObjRef::new(3, 2); + doc.free(old); + assert_eq!(*doc.get(old), Object::Null); + doc.set(new, Object::Int(99)); + assert_eq!(*doc.get(old), Object::Null); + assert_eq!(*doc.get(new), Object::Int(99)); + assert_eq!(*snapshot.get(old), Object::Int(42)); + assert_eq!(*snapshot.get(new), Object::Null); + + let saved = write_incremental(&doc, &SaveOptions::default()).unwrap(); + let back = Document::open(Arc::new(saved)).unwrap(); + assert!(back.repair_log().is_empty()); + assert_eq!(*back.get(old), Object::Null); + assert_eq!(*back.get(new), Object::Int(99)); +} + +#[test] +fn restoring_snapshot_preserves_changes_to_nonzero_generation_objects() { + for generation in [1, 2] { + let mut saved = Document::open(reused_object()).unwrap(); + let mut current = saved.clone(); + let reference = ObjRef::new(3, generation); + current.set(reference, Object::Int(99)); + current.update_dict(current.root().unwrap(), |catalog| catalog.set(b"Current".to_vec(), Object::Ref(reference))).unwrap(); + + saved.overlay_changes_from(¤t).unwrap(); + assert_eq!(*saved.get(reference), Object::Int(99), "generation {generation}"); + let back = Document::open(Arc::new(write_incremental(&saved, &SaveOptions::default()).unwrap())).unwrap(); + assert!(back.repair_log().is_empty()); + assert_eq!(*back.get(reference), Object::Int(99), "generation {generation}"); + let catalog = back.get(back.root().unwrap()); + assert_eq!(*back.resolve(catalog.as_dict().unwrap().get(b"Current").unwrap()), Object::Int(99)); + } +} + +#[test] +fn full_save_does_not_turn_stale_references_into_live_ones() { + let doc = Document::open(reused_object()).unwrap(); + for object_streams in [false, true] { + let saved = write_full(&doc, &SaveOptions { object_streams, ..SaveOptions::default() }).unwrap(); + let saved = Arc::new(saved); + let oracle = hayro_syntax::Pdf::new(saved.clone()).unwrap(); + let catalog = oracle.xref().get::>(ObjectIdentifier::new(1, 0)).unwrap(); + assert_eq!(catalog.get::(b"Current"), Some(42)); + assert_eq!(catalog.get::(b"Stale"), None); + let back = Document::open(saved).unwrap(); + assert!(back.repair_log().is_empty()); + let catalog = back.get(back.root().unwrap()); + let catalog = catalog.as_dict().unwrap(); + assert_eq!(catalog.get(b"Stale"), Some(&Object::Null)); + assert_eq!(*back.resolve(catalog.get(b"Current").unwrap()), Object::Int(42)); + } +} + +#[test] +fn compressed_objects_only_accept_generation_zero() { + let doc = Document::open(reused_object()).unwrap(); + let saved = write_full(&doc, &SaveOptions::default()).unwrap(); + let back = Document::open(Arc::new(saved)).unwrap(); + let catalog = back.get(back.root().unwrap()); + let current = catalog.as_dict().unwrap().reference(b"Current").unwrap(); + assert_eq!(current.generation, 0); + assert!(matches!(back.xref_entry(current.num), Some(XrefEntry::InStream { .. }))); + assert_eq!(*back.get(current), Object::Int(42)); + assert_eq!(*back.get(ObjRef::new(current.num, 1)), Object::Null); +} + +#[test] +fn indirect_stream_lengths_require_the_referenced_generation() { + for generation in [0, 1] { + // The embedded endstream is data when /Length resolves, but the existing missing- + // length recovery stops there when the reference is stale. + let stream = format!("<< /Length 4 {generation} R >>\nstream\nA\nendstream\nB\nendstream"); + let doc = Document::open(object_file(&[ + (1, 0, "<< /Type /Catalog /Pages 2 0 R >>"), + (2, 0, "<< /Type /Pages /Kids [] /Count 0 >>"), + (3, 0, &stream), + (4, 1, "13"), + ])) + .unwrap(); + let object = doc.get(ObjRef::new(3, 0)); + let Object::Stream(stream) = &*object else { panic!("expected stream") }; + assert_eq!(&stream.raw[..], if generation == 1 { b"A\nendstream\nB".as_slice() } else { b"A".as_slice() }); + } +} + +/// A newer valid row must not hide damage in a retained older revision. +fn shadowed_generation_disagreement(materialized: bool, shifted: bool) -> Arc> { + let original = contradictory_dictionary(); + let text = std::str::from_utf8(&original).unwrap(); + let previous: usize = text.rsplit("startxref\n").next().unwrap().lines().next().unwrap().parse().unwrap(); + let mut bytes = (*original).clone(); + let offset = bytes.len(); + bytes.extend_from_slice(b"3 1 obj\n<< /Value 77 >>\nendobj\n"); + let xref = bytes.len(); + let size = if materialized { 3 } else { 4 }; + bytes.extend_from_slice( + format!("xref\n3 1\n{offset:010} 00001 n \ntrailer\n<< /Size {size} /Root 1 0 R /Prev {previous} >>\nstartxref\n{xref}\n%%EOF\n").as_bytes(), + ); + if shifted { + bytes.splice(..0, b"junk before the header\n".iter().copied()); + } + Arc::new(bytes) +} + +#[test] +fn retained_generation_disagreements_are_reported_in_materialized_mode_too() { + for materialized in [false, true] { + for shifted in [false, true] { + let doc = Document::open(shadowed_generation_disagreement(materialized, shifted)).unwrap(); + assert_eq!(doc.revisions().len(), 2, "the xref chain is retained"); + assert!(!doc.reconstructed()); + assert_eq!(doc.get(ObjRef::new(3, 1)).as_dict().unwrap().int(b"Value"), Some(77)); + assert!( + doc.repair_log().iter().any(|line| line.contains("object 3: xref generation 0 disagrees with object header generation 1")), + "materialized={materialized}, shifted={shifted}: {:?}", + doc.repair_log() + ); + } + } +} + +#[test] +fn repair_aware_edits_keep_both_aliases_and_full_save_normalizes_them() { + let mut doc = Document::open(contradictory_entry(false)).unwrap(); + let snapshot = doc.clone(); + doc.set_existing(ObjRef::new(3, 0), Object::Int(77)).unwrap(); + for generation in [0, 1] { + assert_eq!(*doc.get(ObjRef::new(3, generation)), Object::Int(77)); + assert_eq!(*snapshot.get(ObjRef::new(3, generation)), Object::Int(42)); + } + let state = doc.read_state(); + assert!(doc.set_existing(ObjRef::new(3, 2), Object::Int(99)).is_err()); + assert!(state.matches(&doc)); + assert_eq!(*doc.get(ObjRef::new(3, 2)), Object::Null); + let mut restored = snapshot.clone(); + restored.overlay_changes_from(&doc).unwrap(); + for changed in [&doc, &restored] { + assert!(changed.full_save_required()); + for bytes in [ + write_incremental(changed, &SaveOptions::default()).unwrap(), + write_full(changed, &SaveOptions { object_streams: false, ..SaveOptions::default() }).unwrap(), + ] { + let bytes = Arc::new(bytes); + let oracle = hayro_syntax::Pdf::new(bytes.clone()).unwrap(); + let catalog = oracle.xref().get::>(ObjectIdentifier::new(1, 0)).unwrap(); + assert_eq!(catalog.get::(b"Current"), Some(77)); + assert_eq!(catalog.get::(b"Stale"), Some(77), "both source aliases stay live"); + let back = Document::open(bytes).unwrap(); + assert!(back.repair_log().is_empty(), "normalized output has no generation repairs"); + } + } + // Explicit replacement keeps its narrower, caller-supplied generation contract. + doc.set(ObjRef::new(3, 2), Object::Int(99)); + assert_eq!(*doc.get(ObjRef::new(3, 0)), Object::Null); + assert_eq!(*doc.get(ObjRef::new(3, 1)), Object::Null); + assert_eq!(*doc.get(ObjRef::new(3, 2)), Object::Int(99)); +} + +#[test] +fn hybrid_generation_diagnostics_observe_rows_before_the_table_hides_them() { + let mut bytes = b"%PDF-1.7\n".to_vec(); + let mut offsets = Vec::new(); + for (num, generation, body) in [(1, 0, "<< /Type /Catalog /Pages 2 0 R >>"), (2, 0, "<< /Type /Pages /Kids [] /Count 0 >>"), (3, 1, "42")] { + offsets.push(bytes.len()); + bytes.extend_from_slice(format!("{num} {generation} obj\n{body}\nendobj\n").as_bytes()); + } + let hybrid = bytes.len(); + offsets.push(hybrid); + bytes.extend_from_slice(b"4 0 obj\n<< /Type /XRef /Size 5 /W [1 4 2] /Index [3 1] /Length 7 >>\nstream\n"); + bytes.push(1); + bytes.extend_from_slice(&(offsets[2] as u32).to_be_bytes()); + bytes.extend_from_slice(&0u16.to_be_bytes()); + bytes.extend_from_slice(b"\nendstream\nendobj\n"); + let xref = bytes.len(); + bytes.extend_from_slice(b"xref\n0 5\n0000000000 65535 f \n"); + for (i, offset) in offsets.into_iter().enumerate() { + let generation = u16::from(i == 2); + bytes.extend_from_slice(format!("{offset:010} {generation:05} n \n").as_bytes()); + } + bytes.extend_from_slice(format!("trailer\n<< /Size 5 /Root 1 0 R /XRefStm {hybrid} >>\nstartxref\n{xref}\n%%EOF\n").as_bytes()); + let doc = Document::open(Arc::new(bytes)).unwrap(); + assert!(!doc.reconstructed()); + assert!(doc.xref_oddities().iter().any(|(_, num)| *num == 3), "the conflicting hybrid row is set aside"); + assert_eq!(*doc.get(ObjRef::new(3, 1)), Object::Int(42)); + assert_eq!(*doc.get(ObjRef::new(3, 0)), Object::Null, "the table still determines accepted references"); + assert!(doc.repair_log().iter().any(|line| line.contains("object 3: xref generation 0 disagrees with object header generation 1"))); +} + +#[test] +fn discarded_xref_repair_notes_do_not_survive_object_header_reconstruction() { + let bytes = + String::from_utf8((*contradictory_dictionary()).clone()).unwrap().replace("/Root 1 0 R", "/Root 99 0 R").replace("/Size 4", "/Size 3"); + let doc = Document::open(Arc::new(bytes.into_bytes())).unwrap(); + assert!(doc.reconstructed()); + assert!(doc.repair_log().iter().all(|line| !line.contains("xref generation")), "{:?}", doc.repair_log()); +} + +#[test] +fn restoring_equal_values_still_restores_the_accepted_generation_aliases() { + for edited in [false, true] { + for value in [42, 77] { + let mut current = Document::open(contradictory_entry(false)).unwrap(); + if edited { + current.set_existing(ObjRef::new(3, 0), Object::Int(42)).unwrap(); + } + let mut saved = Document::open(object_file(&[ + (1, 0, "<< /Type /Catalog /Pages 2 0 R /Stale 3 0 R /Current 3 1 R >>"), + (2, 0, "<< /Type /Pages /Kids [] /Count 0 >>"), + (3, 0, &value.to_string()), + ])) + .unwrap(); + assert_eq!(*saved.get(ObjRef::new(3, 1)), Object::Null); + saved.overlay_changes_from(¤t).unwrap(); + for generation in [0, 1] { + assert_eq!(*saved.get(ObjRef::new(3, generation)), Object::Int(42), "edited={edited}, value={value}"); + } + assert!(saved.full_save_required()); + } + } +} + +#[test] +fn repaired_page_tree_aliases_keep_one_identity_in_full_saves() { + let source = object_file_with_entry( + &[ + (1, 0, "<< /Type /Catalog /Pages 2 1 R /Stale 2 2 R >>"), + (2, 1, "<< /Type /Pages /Kids [3 0 R] /Count 1 >>"), + (3, 0, "<< /Type /Page /Parent 2 0 R /MediaBox [0 0 10 10] >>"), + ], + Some((2, 0, false)), + ); + for edited in [false, true] { + let mut doc = Document::open(source.clone()).unwrap(); + if edited { + doc.update_dict(ObjRef::new(2, 0), |dict| dict.set(b"Edited".to_vec(), Object::Bool(true))).unwrap(); + } + let mut restored = Document::open(source.clone()).unwrap(); + restored.overlay_changes_from(&doc).unwrap(); + for current in [&doc, &restored] { + for object_streams in [false, true] { + let opts = SaveOptions { object_streams, ..SaveOptions::default() }; + let mut saves = vec![write_full(current, &opts).unwrap()]; + if edited { + saves.push(write_incremental(current, &opts).unwrap()); + } + for bytes in saves { + let back = Document::open(Arc::new(bytes)).unwrap(); + let catalog = back.get(back.root().unwrap()); + let catalog = catalog.as_dict().unwrap(); + let pages_ref = catalog.reference(b"Pages").unwrap(); + let pages = back.get(pages_ref); + let child_ref = pages.as_dict().unwrap().get(b"Kids").unwrap().as_array().unwrap()[0].as_ref().unwrap(); + let child = back.get(child_ref); + assert_eq!(child.as_dict().unwrap().reference(b"Parent"), Some(pages_ref), "edited={edited}, packed={object_streams}"); + assert!(matches!(catalog.get(b"Stale"), Some(Object::Null)), "unrelated generations stay null"); + assert!(back.repair_log().is_empty()); + } + } + } + } +} + +#[test] +fn restoring_explicit_sets_removes_old_generation_aliases() { + for value in [42, 77] { + let mut current = Document::open(contradictory_entry(false)).unwrap(); + current.set(ObjRef::new(3, 0), Object::Int(42)); + for repaired_overlay in [false, true] { + let mut saved = Document::open(contradictory_entry(false)).unwrap(); + if repaired_overlay { + saved.set_existing(ObjRef::new(3, 0), Object::Int(value)).unwrap(); + } + saved.overlay_changes_from(¤t).unwrap(); + assert_eq!(*saved.get(ObjRef::new(3, 0)), Object::Int(42)); + assert_eq!(*saved.get(ObjRef::new(3, 1)), Object::Null, "value={value}, overlay={repaired_overlay}"); + } + } +} + +/// `accepted_generations` lists exactly the generations `get` resolves, for every kind of slot: +/// a clean file slot, a damaged one (row and header disagree), a repair-aware edit, a plain +/// edit, a freed slot, a free row, an object stream member and an unknown number. +#[test] +fn accepted_generations_are_the_generations_get_resolves() { + let agrees = |doc: &Document, num: u32, expected: &[u16]| { + assert_eq!(doc.accepted_generations(num), expected, "object {num}"); + for generation in 0..8 { + let live = !matches!(*doc.get(ObjRef::new(num, generation)), Object::Null); + assert_eq!(live, expected.contains(&generation), "object {num} generation {generation}"); + } + }; + let doc = Document::open(contradictory_entry(false)).unwrap(); + agrees(&doc, 1, &[0]); + agrees(&doc, 3, &[0, 1]); + agrees(&doc, 9, &[]); + let mut repaired = doc.clone(); + repaired.set_existing(ObjRef::new(3, 0), Object::Int(77)).unwrap(); + agrees(&repaired, 3, &[0, 1]); + let mut narrowed = doc.clone(); + narrowed.set(ObjRef::new(3, 2), Object::Int(99)); + agrees(&narrowed, 3, &[2]); + let mut freed = doc.clone(); + freed.free(ObjRef::new(3, 0)); + agrees(&freed, 3, &[]); + agrees(&Document::open(contradictory_entry(true)).unwrap(), 3, &[]); + let mut doc = + Document::open(object_file(&[(1, 0, "<< /Type /Catalog /Pages 2 0 R >>"), (2, 0, "<< /Type /Pages /Kids [] /Count 0 >>")])).unwrap(); + let member = doc.add(Object::Dict(Default::default())); + doc.update_dict(ObjRef::new(1, 0), |c| c.set(b"Extra".to_vec(), Object::Ref(member))).unwrap(); + let packed = Document::open(Arc::new(write_full(&doc, &SaveOptions { object_streams: true, ..SaveOptions::default() }).unwrap())).unwrap(); + assert!(matches!(packed.xref_entry(member.num), Some(XrefEntry::InStream { .. })), "the member is in an object stream"); + agrees(&packed, member.num, &[0]); +} diff --git a/crates/cos/tests/it/main.rs b/crates/cos/tests/it/main.rs index 52cf05d6c2..f8e75ba804 100644 --- a/crates/cos/tests/it/main.rs +++ b/crates/cos/tests/it/main.rs @@ -3,6 +3,8 @@ mod bounded_writer; mod corpus; mod encryption; +mod generations; mod proptests; +mod serialize_format; mod shared_streams; mod writer; diff --git a/crates/cos/tests/it/serialize_format.rs b/crates/cos/tests/it/serialize_format.rs new file mode 100644 index 0000000000..8cfba2baf1 --- /dev/null +++ b/crates/cos/tests/it/serialize_format.rs @@ -0,0 +1,116 @@ +//! `serialize` writes integers, references, hexadecimal strings, octal escapes and `#xx` name +//! escapes with its own digit loops. They must give the bytes the standard formatter gives. + +use pdfcraft_cos::{ObjRef, Object, PdfString, serialize}; +use proptest::prelude::*; + +fn bytes_of(o: &Object) -> Vec { + let mut v = Vec::new(); + serialize(o, &mut v); + v +} + +#[test] +fn integer_extremes_and_digit_boundaries() { + let mut cases = vec![0i64, 1, -1, 9, 10, 99, 100, i64::MAX, i64::MIN, i64::MIN + 1, i64::from(i32::MAX), i64::from(i32::MIN)]; + let mut p = 1i64; + while let Some(next) = p.checked_mul(10) { + cases.extend([next - 1, next, next + 1, -next]); + p = next; + } + for i in cases { + assert_eq!(bytes_of(&Object::Int(i)), i.to_string().into_bytes(), "{i}"); + } +} + +#[test] +fn reference_extremes() { + for (n, g) in [(0, 0), (1, 0), (u32::MAX, u16::MAX), (10, 65535), (4_000_000_000, 7)] { + assert_eq!(bytes_of(&Object::Ref(ObjRef::new(n, g))), format!("{n} {g} R").into_bytes()); + } +} + +#[test] +fn every_byte_value_in_hex_strings_octal_escapes_and_names() { + let all: Vec = (0..=255).collect(); + let hex: String = all.iter().map(|b| format!("{b:02X}")).collect(); + assert_eq!(bytes_of(&Object::String(PdfString { bytes: all.clone(), hex: true })), format!("<{hex}>").into_bytes()); + // A literal string with a few control bytes escapes them in octal. + let lit = bytes_of(&Object::String(PdfString { bytes: b"abcdefghijkl\x01\x7f\xffz".to_vec(), hex: false })); + assert_eq!(lit, b"(abcdefghijkl\\001\\177\\377z)"); + let name = bytes_of(&Object::Name(all.clone())); + let mut want = b"/".to_vec(); + for &b in &all { + let regular = (b'!'..=b'~').contains(&b) && !matches!(b, b'(' | b')' | b'<' | b'>' | b'[' | b']' | b'{' | b'}' | b'/' | b'%' | b'#'); + if regular { + want.push(b); + } else { + want.extend_from_slice(format!("#{b:02X}").as_bytes()); + } + } + assert_eq!(name, want); +} + +#[test] +fn whole_real_at_i32_min_stays_a_real_token() { + // -2^31 is outside the Annex C integer range (±2^31-1), so it keeps its trailing point. + assert_eq!(bytes_of(&Object::Real(f64::from(i32::MIN))), b"-2147483648."); +} + +proptest! { + #[test] + fn integers_match_the_formatter(i in any::()) { + prop_assert_eq!(bytes_of(&Object::Int(i)), format!("{i}").into_bytes()); + } + + #[test] + fn whole_reals_match_the_formatter(i in -i32::MAX..=i32::MAX) { + prop_assert_eq!(bytes_of(&Object::Real(f64::from(i))), format!("{i}").into_bytes()); + } + + #[test] + fn references_match_the_formatter(n in any::(), g in any::()) { + prop_assert_eq!(bytes_of(&Object::Ref(ObjRef::new(n, g))), format!("{n} {g} R").into_bytes()); + } + + #[test] + fn hex_strings_match_the_formatter(bytes in proptest::collection::vec(any::(), 0..300)) { + let mut want = String::from("<"); + for b in &bytes { + want.push_str(&format!("{b:02X}")); + } + want.push('>'); + prop_assert_eq!(bytes_of(&Object::String(PdfString { bytes, hex: true })), want.into_bytes()); + } + + #[test] + fn binary_literal_strings_match_the_formatter(bytes in proptest::collection::vec(any::(), 0..300)) { + // Mostly-binary input is written as hex; mostly-text input with escapes is a literal. + let got = bytes_of(&Object::String(PdfString { bytes: bytes.clone(), hex: false })); + let binary = bytes.iter().filter(|b| !(b' '..=b'~').contains(*b) && !matches!(b, b'\n' | b'\r' | b'\t')).count(); + let mut want = Vec::new(); + if binary * 4 > bytes.len().max(1) { + want.push(b'<'); + for b in &bytes { + want.extend_from_slice(format!("{b:02X}").as_bytes()); + } + want.push(b'>'); + } else { + want.push(b'('); + for &b in &bytes { + match b { + b'(' | b')' | b'\\' => want.extend_from_slice(&[b'\\', b]), + b'\n' => want.extend_from_slice(b"\\n"), + b'\r' => want.extend_from_slice(b"\\r"), + b'\t' => want.extend_from_slice(b"\\t"), + 0x08 => want.extend_from_slice(b"\\b"), + 0x0C => want.extend_from_slice(b"\\f"), + b' '..=b'~' => want.push(b), + _ => want.extend_from_slice(format!("\\{b:03o}").as_bytes()), + } + } + want.push(b')'); + } + prop_assert_eq!(got, want); + } +} diff --git a/crates/cos/tests/it/writer.rs b/crates/cos/tests/it/writer.rs index eb03523189..2716b9242e 100644 --- a/crates/cos/tests/it/writer.rs +++ b/crates/cos/tests/it/writer.rs @@ -358,11 +358,32 @@ fn objects_referenced_by_the_encrypt_dictionary_stay_outside_object_streams() { let cf = doc.get(enc_ref).as_dict().unwrap().get(b"CF").cloned().unwrap(); let cf_ref = doc.add(cf); doc.update_dict(enc_ref, |d| d.set(b"CF".to_vec(), Object::Ref(cf_ref))).unwrap(); - let packed = write_full(&doc, &SaveOptions::default()).unwrap(); - let back = Document::open(Arc::new(packed.clone())).expect("reopens"); - assert!(back.repair_log().is_empty(), "{:?}", back.repair_log()); - assert_eq!(title(&back), b"Caf\xe9 (draft)"); - assert_eq!(hayro_pages(&packed), 4); + // Visit this alias from Root before the encryption walk reaches /CF's other alias. + doc.update_dict(doc.root().unwrap(), |d| d.set(b"CFProbe".to_vec(), Object::Ref(cf_ref))).unwrap(); + let classic = write_full(&doc, &SaveOptions { object_streams: false, ..SaveOptions::default() }).unwrap(); + let saved = Document::open(Arc::new(classic.clone())).unwrap(); + let cf_num = saved.get(saved.root().unwrap()).as_dict().unwrap().reference(b"CFProbe").unwrap().num; + for damaged in [false, true] { + let mut bytes = classic.clone(); + if damaged { + // Equal-length edits preserve the xref offsets and its generation-zero row. + for (from, to) in [(format!("\n{cf_num} 0 obj"), format!("\n{cf_num} 1 obj")), (format!("/CF {cf_num} 0 R"), format!("/CF {cf_num} 1 R"))] + { + let start = bytes.windows(from.len()).position(|w| w == from.as_bytes()).unwrap(); + bytes[start..start + from.len()].copy_from_slice(to.as_bytes()); + } + } + let doc = Document::open(Arc::new(bytes)).unwrap(); + let packed = write_full(&doc, &SaveOptions::default()).unwrap(); + let back = Document::open(Arc::new(packed.clone())).expect("reopens"); + assert!(back.repair_log().is_empty(), "{:?}", back.repair_log()); + assert_eq!(title(&back), b"Caf\xe9 (draft)"); + assert_eq!(hayro_pages(&packed), 4); + let probe = back.get(back.root().unwrap()).as_dict().unwrap().reference(b"CFProbe").unwrap(); + let encrypt = back.get(back.trailer().reference(b"Encrypt").unwrap()); + assert_eq!(encrypt.as_dict().unwrap().reference(b"CF"), Some(probe)); + assert!(matches!(back.xref_entry(probe.num), Some(pdfcraft_cos::XrefEntry::InFile { .. })), "crypt filters must stay outside object streams"); + } } #[test] diff --git a/crates/create/src/extract.rs b/crates/create/src/extract.rs index d5103071e6..863ad2da0a 100644 --- a/crates/create/src/extract.rs +++ b/crates/create/src/extract.rs @@ -183,12 +183,17 @@ fn image(doc: &Document, s: &Stream, budget: &mut ImageBudget) -> Result<(&'stat .unwrap_or(false); // In a PDF a CMYK JPEG's samples are ink amounts unless /Decode inverts them, while image // viewers read a CMYK JPEG file as inverted (Adobe's convention): as is, it would show as - // a negative. - let as_is_negative = jpeg && !inverted && matches!(space(doc, s.dict.get(b"ColorSpace")), Ok(Space::Cmyk)); + // a negative. The space is read once: an indexed one's lookup table is paid for each time. + let read = (jpeg && !inverted).then(|| space(doc, s.dict.get(b"ColorSpace"), budget)); + let as_is_negative = matches!(read, Some(Ok(Space::Cmyk))); if jpeg && alpha.is_none() && key.is_none() && !as_is_negative { return as_is(); } - let mut space = if mask { Space::Gray } else { space(doc, s.dict.get(b"ColorSpace"))? }; + let mut space = match read { + _ if mask => Space::Gray, + Some(read) => read?, + None => space(doc, s.dict.get(b"ColorSpace"), budget)?, + }; let (samples, bpc) = if jpeg { if !budget.pay_jpeg((w as u64).saturating_mul(h as u64).saturating_mul(space.components() as u64), &s.raw) { return Err(FilterError::Spent.to_string()); @@ -436,7 +441,10 @@ impl Space { /// A lookup table holds at most 256 entries of 4 bytes; decoding stops well past that. const MAX_LOOKUP: usize = 64 << 10; -fn space(doc: &Document, cs: Option<&Object>) -> Result { +/// The colour space `cs` names; an indexed one's lookup table is read within `budget`, as the +/// image's samples are, since each image reads it again and its filters can do work that makes +/// nothing. +fn space(doc: &Document, cs: Option<&Object>, budget: &mut ImageBudget) -> Result { let Some(cs) = cs else { return Err("the image has no colour space".into()) }; let cs = doc.resolve(cs); let unsupported = |n: &[u8]| Err(format!("{} images can't be exported yet", String::from_utf8_lossy(n))); @@ -470,7 +478,7 @@ fn space(doc: &Document, cs: Option<&Object>) -> Result { if nested { return Err("nested indexed colour spaces aren't valid".into()); } - let base = space(doc, a.get(1))?; + let base = space(doc, a.get(1), budget)?; let hival = match a.get(2).map(|value| doc.resolve(value)).as_deref() { Some(Object::Int(value)) if (0..=255).contains(value) => *value as u8, _ => return Err("an indexed colour space with an invalid hival".into()), @@ -478,10 +486,14 @@ fn space(doc: &Document, cs: Option<&Object>) -> Result { let table = match a.get(3).map(|t| doc.resolve(t)).as_deref() { Some(Object::String(s)) => s.bytes.clone(), // Through its parameters given by reference too, as the image's samples. - Some(Object::Stream(t)) => doc - .with_direct_parms(t) - .decoded_within(MAX_LOOKUP) - .map_err(|_| "an indexed colour space with an oversized or damaged lookup table".to_string())?, + Some(Object::Stream(t)) => { + let refused = budget.refused(); + match budget.decode_filters(doc, t, MAX_LOOKUP) { + Ok(table) => table, + Err(_) if budget.refused() > refused => return Err(FilterError::Spent.to_string()), + Err(_) => return Err("an indexed colour space with an oversized or damaged lookup table".into()), + } + } _ => return Err("an indexed colour space without a lookup table".into()), }; Ok(Space::Indexed(Box::new(base), hival, table)) diff --git a/crates/create/src/lib.rs b/crates/create/src/lib.rs index 6346e85120..149bd99d97 100644 --- a/crates/create/src/lib.rs +++ b/crates/create/src/lib.rs @@ -92,6 +92,26 @@ pub fn blank(width: f64, height: f64, pages: usize) -> Result)]) -> Result { + if pages.is_empty() || pages.len() > 10_000 { + return Err(CreateError::Invalid("invalid page count".into())); + } + if pages.iter().any(|(w, h, _, _)| !(w.is_finite() && h.is_finite() && (3.0..=MAX_SIDE).contains(w) && (3.0..=MAX_SIDE).contains(h))) { + return Err(CreateError::Invalid("invalid page size".into())); + } + let mut doc = Document::new_empty(); + let mut tree = Pages::of(&doc)?; + for (w, h, resources, content) in pages { + let content = if content.is_empty() { None } else { Some(content.clone()) }; + tree.add(&mut doc, *w, *h, resources.clone(), content); + } + tree.finish(&mut doc)?; + Ok(doc) +} + // ── images ────────────────────────────────────────────────────────────────────────────────── /// An image ready to embed: its XObject dictionary, encoded data, optional soft mask, the ICC @@ -496,6 +516,129 @@ fn decoded(name: &str, bytes: &[u8], format: image::ImageFormat) -> Result Option { + b.get(at..at + 2).map(|x| u16::from_le_bytes([x[0], x[1]])) +} + +/// How a PCX image holds its pixels: bits per plane and planes. +#[derive(Clone, Copy, PartialEq)] +enum PcxLayout { + /// One byte per pixel per colour: each scanline has a red, a green and a blue row. + Rgb, + /// One byte per pixel, an index into the palette after the image (grey without one). + Indexed, + /// One bit per pixel in each of 1 to 4 planes, an index into the header's palette. + Bits(usize), +} + +impl PcxLayout { + fn of(bits: u8, planes: usize) -> Option { + match (bits, planes) { + (8, 3) => Some(PcxLayout::Rgb), + (8, 1) => Some(PcxLayout::Indexed), + (1, 1..=4) => Some(PcxLayout::Bits(planes)), + _ => None, + } + } +} + +/// The palette of a PCX image, and where its run-length coded scanlines end. An 8-bit image ends +/// with a 0x0C byte and 256 colours; a one-plane bit image is black and white whatever its header +/// holds; other bit images use the 16 colours at byte 16. +fn pcx_palette(bytes: &[u8], layout: PcxLayout) -> (Vec, usize) { + match layout { + PcxLayout::Rgb => (Vec::new(), bytes.len()), + PcxLayout::Indexed => match bytes.len().checked_sub(769).filter(|at| *at >= 128 && bytes.get(*at) == Some(&0x0C)) { + Some(at) => (bytes.get(at + 1..).unwrap_or_default().to_vec(), at), + None => ((0..=255u8).flat_map(|v| [v, v, v]).collect(), bytes.len()), + }, + PcxLayout::Bits(1) => (vec![0, 0, 0, 255, 255, 255], bytes.len()), + PcxLayout::Bits(_) => (bytes.get(16..64).unwrap_or_default().to_vec(), bytes.len()), + } +} + +/// The `rows` scanlines of `line` bytes each, decoded. A run may cross from one plane's row into the +/// next, but not out of its scanline. +fn pcx_scanlines(mut body: &[u8], rows: usize, line: usize) -> Option> { + let mut out = Vec::new(); + out.try_reserve_exact(rows.checked_mul(line)?).ok()?; + for row in 1..=rows { + let end = row * line; + while out.len() < end { + let (&c, rest) = body.split_first()?; + body = rest; + if c < 0xC0 { + out.push(c); + continue; + } + let (&value, rest) = body.split_first()?; + body = rest; + let count = usize::from(c & 0x3F); + if count > end - out.len() { + return None; + } + out.resize(out.len() + count, value); + } + } + Some(out) +} + +/// The RGB samples of the `w` pixels of scanline `row` (planes `stride` bytes apart). +fn pcx_row(out: &mut Vec, row: &[u8], w: usize, stride: usize, layout: PcxLayout, palette: &[u8]) { + let at = |i: usize| row.get(i).copied().unwrap_or(0); + for x in 0..w { + let index = match layout { + PcxLayout::Rgb => { + out.extend([at(x), at(stride + x), at(2 * stride + x)]); + continue; + } + PcxLayout::Indexed => usize::from(at(x)), + PcxLayout::Bits(planes) => (0..planes).fold(0, |index, k| index | (usize::from(at(k * stride + x / 8) >> (7 - x % 8) & 1) << k)), + }; + out.extend((0..3).map(|c| palette.get(index * 3 + c).copied().unwrap_or(0))); + } +} + +/// A PCX image: a 128-byte header (size at 4-11, resolution at 12 and 14, plane count at 65, bytes +/// per plane row at 66), then run-length coded scanlines, each holding one row of every plane. +fn pcx(name: &str, bytes: &[u8]) -> Result { + let bad = |m: &str| CreateError::Image(name.into(), m.into()); + let header = bytes.get(..128).ok_or_else(|| bad("a damaged PCX header"))?; + let word = |at: usize| le16(header, at).unwrap_or(0); + let byte = |at: usize| header.get(at).copied().unwrap_or(0); + let (bits, planes, stride) = (byte(3), usize::from(byte(65)), usize::from(word(66))); + let (Some(w), Some(h)) = (word(8).checked_sub(word(4)), word(10).checked_sub(word(6))) else { + return Err(bad("a damaged PCX header")); + }; + let (w, h) = (usize::from(w) + 1, usize::from(h) + 1); + if planes == 0 || stride == 0 { + return Err(bad("a damaged PCX header")); + } + let layout = PcxLayout::of(bits, planes).ok_or_else(|| bad("this PCX plane layout is not supported"))?; + if stride < (w * usize::from(bits)).div_ceil(8) { + return Err(bad("a damaged PCX header")); + } + let line = planes * stride; + if line.saturating_mul(h) > MAX_DECODED_BYTES || w.saturating_mul(h).saturating_mul(3) > MAX_DECODED_BYTES { + return Err(bad("unusual PCX image size")); + } + let (palette, end) = pcx_palette(bytes, layout); + let body = bytes.get(128..end).unwrap_or_default(); + let scanlines = pcx_scanlines(body, h, line).ok_or_else(|| bad("a damaged PCX body"))?; + let mut data = Vec::new(); + data.try_reserve_exact(w * h * 3).map_err(|_| bad("not enough memory for this image"))?; + for row in scanlines.chunks_exact(line) { + pcx_row(&mut data, row, w, stride, layout, &palette); + } + let dpi = (f64::from(word(12)), f64::from(word(14))); + let dpi = if dpi.0 > 0.0 && dpi.1 > 0.0 { dpi } else { (72.0, 72.0) }; + let mut d = Dict::new(); + d.set(b"ColorSpace".to_vec(), Object::name("DeviceRGB")); + d.set(b"BitsPerComponent".to_vec(), Object::Int(8)); + let px = (u32::try_from(w).unwrap_or(0), u32::try_from(h).unwrap_or(0)); + Ok(Embedded { dict: d, data, filtered: false, smask: None, icc: None, px, dpi }) +} + /// Largest GIF logical screen, in pixels (4096×4096). const MAX_GIF_PIXELS: u64 = 1 << 24; @@ -603,7 +746,13 @@ pub enum SourceKind { } /// File extensions Create converts to PDF (images and plain text). -pub const CONVERTIBLE: [&str; 12] = ["png", "jpg", "jpeg", "tif", "tiff", "gif", "bmp", "jp2", "j2k", "jpx", "txt", "text"]; +pub const CONVERTIBLE: [&str; 13] = ["png", "jpg", "jpeg", "tif", "tiff", "gif", "bmp", "jp2", "j2k", "jpx", "pcx", "txt", "text"]; + +/// A PCX file: its manufacturer byte, a version (1 was never used), run-length coding and 1 or 8 +/// bits per plane. `pcx` says when the rest of the header isn't one it can read. +fn is_pcx(bytes: &[u8]) -> bool { + bytes.first() == Some(&0x0A) && matches!(bytes.get(1), Some(0 | 2..=5)) && bytes.get(2) == Some(&1) && matches!(bytes.get(3), Some(1 | 8)) +} /// A classic TIFF or a BigTIFF (version 43), in either byte order. fn is_tiff(bytes: &[u8]) -> bool { @@ -620,6 +769,7 @@ fn is_image(bytes: &[u8]) -> bool { || bytes.starts_with(b"\x89PNG\r\n\x1a\n") || is_tiff(bytes) || is_gif(bytes) + || is_pcx(bytes) // JPEG 2000: a JP2 file or a raw codestream. || bytes.starts_with(JP2_SIGNATURE) || bytes.starts_with(&[0xFF, 0x4F, 0xFF, 0x51]) @@ -655,6 +805,8 @@ fn embed(name: &str, bytes: &[u8], wanted: usize) -> Result, Creat Ok(vec![decoded(name, &pdfcraft_xfa::image::bmp_with_pixel_offset(bytes), image::ImageFormat::Bmp)?]) } else if is_gif(bytes) { Ok(vec![decoded(name, bytes, image::ImageFormat::Gif)?]) + } else if is_pcx(bytes) { + Ok(vec![pcx(name, bytes)?]) } else if bytes.starts_with(JP2_SIGNATURE) || bytes.starts_with(&[0xFF, 0x4F, 0xFF, 0x51]) { Ok(vec![jpx(name, bytes)?]) } else { diff --git a/crates/create/src/tests.rs b/crates/create/src/tests.rs index 9e620c19c3..88a6e05ac9 100644 --- a/crates/create/src/tests.rs +++ b/crates/create/src/tests.rs @@ -485,6 +485,82 @@ fn bigtiff_images_become_pages() { assert_eq!(media(&pages(&doc)[0]), [0.0, 0.0, 2.0, 1.0], "4×2 px at 144 dpi"); } +/// A PCX header for a `w` by `h` image at 72 dpi. +fn pcx_header(version: u8, bits: u8, planes: u8, stride: u16, w: u16, h: u16) -> Vec { + let mut pcx = vec![0u8; 128]; + pcx[..4].copy_from_slice(&[0x0A, version, 1, bits]); + pcx[8..10].copy_from_slice(&(w - 1).to_le_bytes()); + pcx[10..12].copy_from_slice(&(h - 1).to_le_bytes()); + pcx[12..14].copy_from_slice(&72u16.to_le_bytes()); + pcx[14..16].copy_from_slice(&72u16.to_le_bytes()); + pcx[65] = planes; + pcx[66..68].copy_from_slice(&stride.to_le_bytes()); + pcx +} + +/// A 24-bit PCX: each scanline holds a red, a green and a blue row. +#[test] +fn pcx_images_become_pages() { + let mut pcx = pcx_header(5, 8, 3, 2, 2, 2); + pcx.extend_from_slice(&[10, 11, 20, 21, 30, 31]); + pcx.extend_from_slice(&[40, 41, 50, 51, 60, 61]); + let embedded = super::pcx("a.pcx", &pcx).unwrap(); + assert_eq!(embedded.data, [10, 20, 30, 11, 21, 31, 40, 50, 60, 41, 51, 61]); + let doc = reopen(&from_images(&[("a.pcx".into(), pcx)]).unwrap()); + assert_eq!(pages(&doc).len(), 1); + assert_eq!(media(&pages(&doc)[0]), [0.0, 0.0, 2.0, 2.0]); + assert_eq!(image_of(&doc, 0).name(b"ColorSpace"), Some(&b"DeviceRGB"[..])); +} + +#[test] +fn a_pcx_run_may_cross_planes_but_not_scanlines() { + // 0xC4 repeats 7 four times: the red row and half of the green one + let mut pcx = pcx_header(5, 8, 3, 2, 2, 1); + pcx.extend_from_slice(&[0xC4, 7, 8, 9]); + assert_eq!(super::pcx("a.pcx", &pcx).unwrap().data[..], [7, 7, 8, 7, 7, 9]); + let mut pcx = pcx_header(5, 8, 3, 2, 2, 2); + pcx.extend_from_slice(&[0xC8, 7, 1, 2, 3, 4]); + assert!(super::pcx("a.pcx", &pcx).is_err(), "eight bytes in a six-byte scanline"); +} + +#[test] +fn an_8_bit_pcx_uses_its_palette_and_is_grey_without_one() { + let mut pcx = pcx_header(5, 8, 1, 2, 2, 1); + pcx.extend_from_slice(&[1, 2]); + assert_eq!(super::pcx("a.pcx", &pcx).unwrap().data[..], [1, 1, 1, 2, 2, 2], "no palette: grey"); + pcx.push(0x0C); + let mut palette = vec![0u8; 768]; + palette[3..9].copy_from_slice(&[9, 8, 7, 6, 5, 4]); + pcx.extend_from_slice(&palette); + assert_eq!(super::pcx("a.pcx", &pcx).unwrap().data[..], [9, 8, 7, 6, 5, 4]); +} + +#[test] +fn bit_plane_pcx_images_read_their_palette() { + // version 2, one plane: black and white + let mut pcx = pcx_header(2, 1, 1, 2, 2, 1); + pcx.extend_from_slice(&[0b1000_0000, 0]); + assert!(from_images(&[("a.pcx".into(), pcx.clone())]).is_ok(), "an old version is still a PCX"); + assert_eq!(super::pcx("a.pcx", &pcx).unwrap().data[..], [255, 255, 255, 0, 0, 0]); + // two planes: colour 3 is at byte 16 + 9 + let mut pcx = pcx_header(5, 1, 2, 1, 1, 1); + pcx[25..28].copy_from_slice(&[1, 2, 3]); + pcx.extend_from_slice(&[0x80, 0x80]); + assert_eq!(super::pcx("a.pcx", &pcx).unwrap().data[..], [1, 2, 3]); +} + +#[test] +fn damaged_pcx_headers_and_bodies_are_refused() { + let no_planes = pcx_header(5, 8, 0, 2, 2, 1); + let no_stride = pcx_header(5, 8, 3, 0, 2, 1); + let short_stride = pcx_header(5, 8, 3, 1, 2, 1); + let short_body = pcx_header(5, 8, 3, 2, 2, 1); + for bytes in [no_planes, no_stride, short_stride, short_body] { + assert!(super::pcx("a.pcx", &bytes).is_err()); + } + assert!(super::pcx("a.pcx", &[0x0A, 5, 1, 8]).is_err(), "no header"); +} + /// A synthetic ICC profile: a 128-byte header (size, device class, colour space, `acsp`) and /// some payload. Only the header is read. fn icc_profile(space: &[u8; 4]) -> Vec { @@ -2333,6 +2409,98 @@ fn flate_images_past_the_exports_allowance_are_left_out_with_the_reason() { assert_eq!(budget.refused(), 1); } +/// An indexed image's lookup table, given as a stream, is read within the export's allowance as +/// the image's samples are: each image reads it again, and its filters can do work that makes +/// nothing (Flate over empty blocks). Past the allowance the image is left out with the reason. +#[test] +fn a_lookup_table_is_read_within_the_exports_allowance() { + use pdfcraft_cos::{Dict, Document, ImageBudget, Object, PdfString, Stream}; + let table = [255, 0, 0, 0, 0, 255]; + let lookup = Stream::flate(Dict::new(), &table); + let exported = |as_stream: bool, work: u64| { + let mut doc = Document::new_empty(); + let table = if as_stream { Object::Ref(doc.add(Object::Stream(lookup.clone()))) } else { Object::String(PdfString::literal(table.to_vec())) }; + let mut dict = Dict::new(); + dict.set(b"Subtype".to_vec(), Object::name("Image")); + dict.set(b"Width".to_vec(), Object::Int(2)); + dict.set(b"Height".to_vec(), Object::Int(1)); + dict.set(b"BitsPerComponent".to_vec(), Object::Int(8)); + dict.set(b"ColorSpace".to_vec(), Object::Array(vec![Object::name("Indexed"), Object::name("DeviceRGB"), Object::Int(1), table])); + let image = doc.add(Object::Stream(Stream::flate(dict, &[0, 1]))); + let mut budget = ImageBudget::with_work(work); + let file = crate::extract::image_file_within(&doc, image, &mut budget); + (file, work - budget.work_left(), budget.refused()) + }; + let (direct, image_alone, _) = exported(false, u64::MAX); + let (streamed, both, _) = exported(true, u64::MAX); + assert_eq!(streamed.unwrap(), direct.unwrap(), "the same picture"); + let read = (lookup.raw.len() + table.len()) as u64 + pdfcraft_filters::FLATE_READ_WORK * lookup.raw.len() as u64; + assert_eq!(both, image_alone + read, "the table is paid for as it is read"); + let (refused, _, count) = exported(true, image_alone); + assert!(refused.unwrap_err().contains("more image decoding than")); + assert_eq!(count, 1); +} + +/// A JPEG's colour space is read once for an export, its lookup table paid for once: whether it is +/// CMYK (a negative as is) and what its samples are both come from that reading. An indexed JPEG +/// isn't valid, and is written as it is, but its soft mask makes it go on past the first. With the +/// mask, a table the allowance can't pay for leaves the image out, with the reason. +#[test] +fn a_jpegs_lookup_table_is_paid_for_once() { + use pdfcraft_cos::{Dict, Document, ImageBudget, Object, PdfString, Stream}; + let table = [255, 0, 0, 0, 0, 255]; + let lookup = Stream::flate(Dict::new(), &table); + let mut jpeg = Vec::new(); + image::GrayImage::from_pixel(2, 1, image::Luma([1])).write_to(&mut std::io::Cursor::new(&mut jpeg), image::ImageFormat::Jpeg).unwrap(); + // `given`: None leaves the colour space out, Some(true) gives the table as a stream. + let exported = |given: Option, work: u64| { + let mut doc = Document::new_empty(); + let table = given.map(|as_stream| { + if as_stream { Object::Ref(doc.add(Object::Stream(lookup.clone()))) } else { Object::String(PdfString::literal(table.to_vec())) } + }); + let mut mask = Dict::new(); + for (k, v) in + [("Subtype", Object::name("Image")), ("Width", Object::Int(2)), ("Height", Object::Int(1)), ("BitsPerComponent", Object::Int(8))] + { + mask.set(k.as_bytes().to_vec(), v); + } + mask.set(b"ColorSpace".to_vec(), Object::name("DeviceGray")); + let mask = doc.add(Object::Stream(Stream::flate(mask, &[255, 128]))); + let mut dict = Dict::new(); + for (k, v) in + [("Subtype", Object::name("Image")), ("Width", Object::Int(2)), ("Height", Object::Int(1)), ("BitsPerComponent", Object::Int(8))] + { + dict.set(k.as_bytes().to_vec(), v); + } + if let Some(table) = table { + dict.set(b"ColorSpace".to_vec(), Object::Array(vec![Object::name("Indexed"), Object::name("DeviceRGB"), Object::Int(1), table])); + } + dict.set(b"Filter".to_vec(), Object::name("DCTDecode")); + dict.set(b"SMask".to_vec(), Object::Ref(mask)); + let image = doc.add(Object::Stream(Stream::from_raw(dict, jpeg.clone()))); + let mut budget = ImageBudget::with_work(work); + let file = crate::extract::image_file_within(&doc, image, &mut budget); + (file, work - budget.work_left(), budget.refused()) + }; + let (direct, direct_cost, _) = exported(Some(false), u64::MAX); + let (streamed, streamed_cost, _) = exported(Some(true), u64::MAX); + assert_eq!(direct, Ok(("jpg", jpeg.clone())), "written as it is"); + assert_eq!(streamed, direct); + let read = (lookup.raw.len() + table.len()) as u64 + pdfcraft_filters::FLATE_READ_WORK * lookup.raw.len() as u64; + assert_eq!(streamed_cost, direct_cost + read, "one reading of the table"); + + // Without a colour space nothing is read after the soft mask, so this is what the mask costs. + let (none, mask, _) = exported(None, u64::MAX); + assert_eq!(none.unwrap_err(), "the image has no colour space"); + // Read first, the table would be refused a step short of the mask too, and the mask after it. + assert!(read >= mask, "the table costs at least what the mask does"); + assert_eq!(exported(Some(true), mask - 1).2, 1, "the mask is read first, and refused alone"); + let (refused, _, count) = exported(Some(true), mask + read - 1); + let refused = refused.unwrap_err(); + assert!(refused.contains("more image decoding than"), "{refused}"); + assert_eq!(count, 1, "refused at the table, and nothing after it asks to be paid for"); +} + /// A JPEG is written as it is, at no cost, unless something means decoding it, here a mask: that /// pays for its samples, and past the allowance the image goes, with the reason, as it would come out without /// its transparency otherwise. diff --git a/crates/crypt/src/lib.rs b/crates/crypt/src/lib.rs index ff92d9af66..e697bc8553 100644 --- a/crates/crypt/src/lib.rs +++ b/crates/crypt/src/lib.rs @@ -82,17 +82,24 @@ pub enum Auth { User, } -/// Permission bits from `/P` (§7.6.4.2, Table 22). Owners have every permission. +/// Permission flags from `/P`, read the way the handler's revision reads them (ISO 32000-1:2008, +/// Table 22). Owners have every permission. #[derive(Clone, Copy, Debug, PartialEq, Eq)] pub struct Permissions { pub bits: i32, pub owner: bool, + /// The `/R` value of the handler that read `bits`. + pub revision: i64, } impl Permissions { fn bit(&self, n: u32) -> bool { self.owner || (self.bits >> (n - 1)) & 1 == 1 } + /// Revision 3 and later read the full flag list of Table 22; revision 2 has its own. + fn is_revision_3_or_later(&self) -> bool { + self.revision >= 3 + } pub fn print(&self) -> bool { self.bit(3) } @@ -107,17 +114,22 @@ impl Permissions { self.bit(6) } pub fn fill_forms(&self) -> bool { - self.bit(9) || self.bit(6) + if self.is_revision_3_or_later() { self.bit(9) || self.bit(6) } else { self.bit(6) } } + /// Revision 2 covers accessibility with the copy flag (bit 5); revision 3 and later with bit 10. pub fn extract_for_accessibility(&self) -> bool { - self.bit(10) + if self.is_revision_3_or_later() { self.bit(10) } else { self.bit(5) } } - /// Insert, rotate or delete pages; create bookmarks and thumbnails. + /// Insert, rotate or delete pages; create bookmarks and thumbnails. Revision 3 and later grant + /// it by bit 11 alone. Table 22 defines bit 11 for those revisions only, so at revision 2 the + /// modify flag (bit 4) covers it. pub fn assemble(&self) -> bool { - self.bit(11) || self.bit(4) + if self.is_revision_3_or_later() { self.bit(11) } else { self.bit(4) } } + /// Revision 3 and later need bit 3 as well as bit 12. Table 22 defines bit 12 for those + /// revisions only: at revision 2 the print flag (bit 3) is all there is. pub fn print_high_quality(&self) -> bool { - self.bit(12) + if self.is_revision_3_or_later() { self.print() && self.bit(12) } else { self.print() } } } @@ -250,7 +262,7 @@ impl SecurityHandler { /// edited `/P` grants nothing extra. Without a readable `/Perms`, `/P` applies as before. pub fn permissions(&self) -> Permissions { let bits = self.perms_p().map_or(self.dict.p, |p| self.dict.p & p); - Permissions { bits, owner: self.auth == Auth::Owner } + Permissions { bits, owner: self.auth == Auth::Owner, revision: self.dict.r } } /// `/P` as `/Perms` holds it: AES-256 ECB of one block (= CBC with a zero IV), marked `adb`. diff --git a/crates/crypt/src/tests.rs b/crates/crypt/src/tests.rs index 6064176d78..09a88ed129 100644 --- a/crates/crypt/src/tests.rs +++ b/crates/crypt/src/tests.rs @@ -240,11 +240,11 @@ fn unsupported_handlers_are_reported() { #[test] fn permission_bits_follow_table_22() { - let p = Permissions { bits: -3904, owner: false }; // 0xFFFFF0C0: only reserved bits set + let p = Permissions { bits: -3904, owner: false, revision: 3 }; // 0xFFFFF0C0: only reserved bits set assert!(!p.print() && !p.modify() && !p.copy() && !p.annotate() && !p.assemble()); - let p = Permissions { bits: -1, owner: false }; + let p = Permissions { bits: -1, owner: false, revision: 3 }; assert!(p.print() && p.modify() && p.copy() && p.annotate() && p.assemble() && p.fill_forms()); - let p = Permissions { bits: 0, owner: true }; + let p = Permissions { bits: 0, owner: true, revision: 3 }; assert!(p.modify(), "owners ignore /P"); } diff --git a/crates/crypt/tests/it/main.rs b/crates/crypt/tests/it/main.rs index 8b39bf1956..e7742bbd75 100644 --- a/crates/crypt/tests/it/main.rs +++ b/crates/crypt/tests/it/main.rs @@ -1,4 +1,5 @@ //! The crate's integration tests, linked into one test binary. +mod permissions_revision; mod proptests; mod qpdf_literals; diff --git a/crates/crypt/tests/it/permissions_revision.rs b/crates/crypt/tests/it/permissions_revision.rs new file mode 100644 index 0000000000..bad709cd51 --- /dev/null +++ b/crates/crypt/tests/it/permissions_revision.rs @@ -0,0 +1,126 @@ +//! The permission accessors of `pdfcraft_crypt::Permissions`, checked against the flag table of +//! ISO 32000-1:2008 (Table 22). Expected values come from that table only. +//! +//! Bit n has the mask `1 << (n - 1)`. Readers use bits 3 to 6 and 9 to 12 and ignore the rest. + +use pdfcraft_crypt::{Algorithm, Auth, NewEncryption, Permissions, SecurityHandler, create}; + +const ID: &[u8] = b"0123456789abcdef"; +const T: bool = true; +const F: bool = false; + +/// The eight accessors in this order: print, high-quality print, modify, copy, accessibility, +/// annotate, fill forms, assemble. +fn cells(p: &Permissions) -> [bool; 8] { + [p.print(), p.print_high_quality(), p.modify(), p.copy(), p.extract_for_accessibility(), p.annotate(), p.fill_forms(), p.assemble()] +} + +/// Creates a file with `flags` at revision `revision`, opens it with the user password, and +/// returns the user's permissions. +fn user_view(alg: Algorithm, revision: i64, flags: i32) -> Permissions { + let made = create( + &NewEncryption { algorithm: alg, user_password: "user", owner_password: "owner", permissions: flags, encrypt_metadata: true, seed: [42; 32] }, + ID, + ) + .expect("the handler is created"); + assert_eq!(made.dict().r, revision, "the algorithm writes revision {revision}"); + let opened = SecurityHandler::open(made.dict().clone(), ID, Some("user")).expect("the user password opens the file"); + assert_eq!(opened.auth(), Auth::User, "the user password gives user access"); + opened.permissions() +} + +/// Revision 3 and later: each row is a flag word and the expected eight cells. +const REVISION_3_ROWS: &[(&str, i32, [bool; 8])] = &[ + ("every meaningful flag set, ignored flags clear", -196, [T, T, T, T, T, T, T, T]), + ("every flag set, ignored flags set too", -1, [T, T, T, T, T, T, T, T]), + ("reserved flags only", -4096, [F, F, F, F, F, F, F, F]), + ("ignored flags set, meaningful flags clear", -3901, [F, F, F, F, F, F, F, F]), + ("modify flag clear", -9, [T, T, F, T, T, T, T, T]), + ("copy flag clear", -17, [T, T, T, F, T, T, T, T]), + ("annotate flag clear", -33, [T, T, T, T, T, F, T, T]), + ("annotate and fill-existing flags clear", -289, [T, T, T, T, T, F, F, T]), + ("annotate flag set, fill-existing flag clear", -257, [T, T, T, T, T, T, T, T]), + ("accessibility flag clear", -513, [T, T, T, T, F, T, T, T]), + ("high-quality flag clear, print flag set", -2049, [T, F, T, T, T, T, T, T]), + ("bits 3 to 12 set, reserved bits clear", 4092, [T, T, T, T, T, T, T, T]), + ("positive flag word, bit 32 clear", 2_147_483_647, [T, T, T, T, T, T, T, T]), + ("revision 2 example read at revision 3", -44, [T, T, F, T, T, F, T, T]), +]; + +#[test] +fn revision_three_rows_hold_through_a_created_and_reopened_file() { + for (name, bits, want) in REVISION_3_ROWS { + assert_eq!(cells(&user_view(Algorithm::Rc4_128, 3, *bits)), *want, "{name}: flag word {bits:#010x}"); + } +} + +#[test] +fn owner_access_gives_every_flag() { + let made = create( + &NewEncryption { + algorithm: Algorithm::Rc4_128, + user_password: "user", + owner_password: "owner", + permissions: 0, + encrypt_metadata: true, + seed: [42; 32], + }, + ID, + ) + .expect("the handler is created"); + assert_eq!(made.auth(), Auth::Owner, "the owner password gives owner access"); + assert_eq!(cells(&made.permissions()), [T; 8]); +} + +#[test] +fn revision_two_print_modify_copy_and_annotate_follow_the_table() { + for (bits, want) in [(-4, [T, T, T, T]), (-44, [T, F, T, F]), (-17, [T, T, F, T])] { + let p = user_view(Algorithm::Rc4_40, 2, bits); + assert_eq!([p.print(), p.modify(), p.copy(), p.annotate()], want, "revision 2, flag word {bits}"); + } +} + +#[test] +fn revision_two_with_every_flag_set_grants_accessibility_and_form_filling() { + let p = user_view(Algorithm::Rc4_40, 2, -4); + assert!(p.extract_for_accessibility(), "bit 5 is set, and at revision 2 it covers accessibility"); + assert!(p.fill_forms(), "bit 6 is set"); +} + +#[test] +fn revision_three_assembly_needs_its_own_flag() { + let p = user_view(Algorithm::Rc4_128, 3, -1025); + assert!(p.modify(), "bit 4 is set"); + assert!(!p.assemble(), "assembly needs bit 11; bit 4 alone does not grant it"); +} + +#[test] +fn revision_three_high_quality_print_needs_the_print_flag() { + let p = user_view(Algorithm::Rc4_128, 3, -5); + assert!(!p.print(), "bit 3 is clear"); + assert!(!p.print_high_quality(), "high-quality print needs bit 3 and bit 12"); +} + +#[test] +fn revision_two_accessibility_follows_the_copy_flag() { + let p = user_view(Algorithm::Rc4_40, 2, -17); + assert!(!p.copy(), "bit 5 is clear"); + assert!(!p.extract_for_accessibility(), "at revision 2 accessibility is bit 5"); +} + +#[test] +fn revision_two_form_filling_ignores_bit_nine() { + let p = user_view(Algorithm::Rc4_40, 2, -44); + assert!(!p.annotate(), "bit 6 is clear"); + assert!(!p.fill_forms(), "at revision 2 form filling is bit 6 alone"); +} + +#[test] +fn revision_two_ignores_the_flags_only_later_revisions_define() { + // Bit 4 is clear and bit 11 set: bit 11 means nothing at revision 2, so assembly stays refused. + let p = user_view(Algorithm::Rc4_40, 2, -44); + assert!(!p.assemble(), "at revision 2 assembly is bit 4 alone"); + // Bit 3 is set and bit 12 clear: printing at revision 2 has one quality. + let p = user_view(Algorithm::Rc4_40, 2, -2049); + assert!(p.print_high_quality(), "at revision 2 high-quality print is bit 3 alone"); +} diff --git a/crates/edit/src/added.rs b/crates/edit/src/added.rs index a603a37060..0fc2aa7359 100644 --- a/crates/edit/src/added.rs +++ b/crates/edit/src/added.rs @@ -31,7 +31,7 @@ use layout::Piece; pub(crate) use layout::WRAP_CALLS; pub use layout::{PASTE_STEP, first_undrawable, lines, paste_place, paste_rect, text_rect, text_width}; pub use store::{add_content, delete_content, isolate_content, list_added, scan_markers, update_content}; -pub use types::{Added, AddedImage, AddedText, Align, CHAR_SPACING_LIMIT, Family, MarkerScan}; +pub use types::{Added, AddedImage, AddedText, Align, CHAR_SPACING_LIMIT, Family, Ink, MarkerScan}; #[derive(Clone, Debug, PartialEq)] pub enum Content { diff --git a/crates/edit/src/added/draw.rs b/crates/edit/src/added/draw.rs index 9404f939b1..f3f9b55859 100644 --- a/crates/edit/src/added/draw.rs +++ b/crates/edit/src/added/draw.rs @@ -1,7 +1,7 @@ use super::layout::{ Piece, arabic_error, hebrew_error, is_arabic, is_hebrew, is_thai, latin_width, norm, shaped_layout, text_rect, thai_error, wrapped, }; -use super::types::{AddedText, Align, Family}; +use super::types::{AddedText, Align, Family, Ink}; use super::{ Content, Dict, Document, EditError, GlyphError, GlyphOutline, HashMap, HashSet, ObjRef, Object, PdfString, ShapedCluster, ShapedScript, Stream, align_code, literal, matrix_number, n, shaped_glyph, win_ansi, @@ -105,8 +105,7 @@ pub(super) fn draw_laid_shaped( fonts.set(name.clone().into_bytes(), Object::Ref(font)); names.push(name); } - let [cr, cg, cb] = t.color.map(|v| v.clamp(0.0, 1.0)); - out.extend(format!("BT {} {} {} rg\n", n(cr), n(cg), n(cb)).bytes()); + out.extend(format!("BT {}\n", t.fill_op()).bytes()); if t.char_spacing != 0.0 { out.extend(format!("{} Tc\n", n(t.char_spacing)).bytes()); } @@ -293,8 +292,7 @@ pub(super) fn draw(doc: &mut Document, c: &Content, view: [f64; 6], taken: &Dict } res.set(b"Font".to_vec(), Object::Dict(fonts)); let r = text_rect(t); - let [cr, cg, cb] = t.color.map(|v| v.clamp(0.0, 1.0)); - out.extend(format!("BT /{name} {} Tf {} {} {} rg\n", n(t.size), n(cr), n(cg), n(cb)).bytes()); + out.extend(format!("BT /{name} {} Tf {}\n", n(t.size), t.fill_op()).bytes()); if t.char_spacing != 0.0 { out.extend(format!("{} Tc\n", n(t.char_spacing)).bytes()); } @@ -355,6 +353,12 @@ pub(super) fn params(c: &Content) -> Dict { d.set(b"Font".to_vec(), Object::name(t.family.base_font(t.bold, t.italic))); d.set(b"Size".to_vec(), Object::Real(t.size)); d.set(b"Color".to_vec(), arr(&t.color)); + // The ink beside its RGB look, which a reader that knows no ink keeps showing. + match t.painted_ink() { + Some(Ink::Gray(g)) => d.set(b"Gray".to_vec(), Object::Real(g)), + Some(Ink::Cmyk(c)) => d.set(b"CMYK".to_vec(), arr(&c)), + None => {} + } d.set(b"Align".to_vec(), Object::Int(align_code(t.align))); // Each paragraph's own alignment, or null where it follows /Align. let aligns = crate::paragraph_align::tidy(t.aligns.clone(), t.align); diff --git a/crates/edit/src/added/store.rs b/crates/edit/src/added/store.rs index 7dae55596f..3555910f04 100644 --- a/crates/edit/src/added/store.rs +++ b/crates/edit/src/added/store.rs @@ -1,8 +1,33 @@ use super::draw::{draw, params}; use super::layout::{first_undrawable, is_thai, nums, shaped_arabic, thai_error}; -use super::types::{Added, AddedImage, AddedText, CHAR_SPACING_LIMIT, Family, MarkerScan, TAG}; +use super::types::{Added, AddedImage, AddedText, CHAR_SPACING_LIMIT, Family, Ink, MarkerScan, TAG}; use super::{Content, Dict, Document, EditError, GlyphError, MarkKind, ObjRef, Object, Stream, align_from, check, contents, page_list, place_tagged}; +/// A text item's gray or CMYK ink. Items written before inks, and an ink out of range or not +/// made only of numbers (a `/Gray` name, a `/CMYK` entry that isn't a number), have none: the +/// text paints in its RGB `/Color`. +fn ink(doc: &Document, d: &Dict) -> Option { + let ink = if let Some(g) = d.get(b"Gray") { + Ink::Gray(read_value(doc, g, Object::as_f64)?) + } else { + // Four entries or none: a longer array is never copied or read through. + read_value(doc, d.get(b"CMYK")?, |cmyk| { + let [c, m, y, k] = cmyk.as_array()?.as_slice() else { return None }; + Some(Ink::Cmyk([c.as_f64()?, m.as_f64()?, y.as_f64()?, k.as_f64()?])) + })? + }; + Some(ink).filter(|i| i.valid()) +} + +/// `f` of `o`, a reference followed. A direct value is read where it is, never copied, so a +/// large one a file puts there costs nothing to look at. +fn read_value(doc: &Document, o: &Object, f: impl FnOnce(&Object) -> T) -> T { + match o { + Object::Ref(_) => f(&doc.resolve(o)), + direct => f(direct), + } +} + fn parse(doc: &Document, d: &Dict) -> Option { let r = nums(doc, d.get(b"Rect")); let rect: [f64; 4] = r.try_into().ok()?; @@ -21,7 +46,7 @@ fn parse(doc: &Document, d: &Dict) -> Option { .map(|a| a.iter().take(crate::paragraph_align::count(&text)).map(|v| v.as_int().map(|c| align_from(Some(c)))).collect()) }) .unwrap_or_default(); - Some(Content::Text(AddedText { + let mut t = AddedText { rect, text, family, @@ -29,11 +54,19 @@ fn parse(doc: &Document, d: &Dict) -> Option { italic, size: d.get(b"Size").and_then(Object::as_f64).unwrap_or(12.0), color: if c.len() == 3 { [c[0], c[1], c[2]] } else { [0.0; 3] }, + ink: ink(doc, d), align, aligns: crate::paragraph_align::tidy(aligns, align), // Items written before character spacing have none. char_spacing: d.get(b"CharSpacing").and_then(Object::as_f64).filter(|v| v.is_finite()).unwrap_or(0.0), - })) + }; + // An ink whose look isn't the stored colour (a file edited by hand) is none. + t.drop_stale_ink(); + // One that stands is the ink as painted, finer digits dropped, and its look. + if let Some(i) = t.ink { + t.set_ink(Some(i)); + } + Some(Content::Text(t)) } b"Image" => { let crop = nums(doc, d.get(b"Crop")); @@ -138,6 +171,9 @@ fn validate(c: &Content) -> Result<(), EditError> { "the character spacing must be between -{CHAR_SPACING_LIMIT} and {CHAR_SPACING_LIMIT} points" ))); } + if t.ink.is_some_and(|i| !i.valid()) { + return Err(EditError::Invalid("a gray level and each CMYK value must be from 0 to 1".into())); + } if (r[2] - r[0]).abs() < 1.0 { return Err(EditError::Invalid("the text box is too narrow".into())); } diff --git a/crates/edit/src/added/types.rs b/crates/edit/src/added/types.rs index 0caaaa863b..24101b2eea 100644 --- a/crates/edit/src/added/types.rs +++ b/crates/edit/src/added/types.rs @@ -1,5 +1,5 @@ use super::layout::norm; -use super::{Content, MarkKind, ObjRef, Std14}; +use super::{Content, MarkKind, ObjRef, Std14, n}; pub(super) const TAG: &str = "Added"; @@ -90,6 +90,60 @@ pub enum Align { Justify, } +/// A device colour added text is painted in instead of RGB, for print files: a text's black in +/// CMYK stays 100 K rather than a DeviceRGB black the printer separates into rich black. +#[derive(Clone, Copy, Debug, PartialEq)] +pub enum Ink { + /// A DeviceGray level, from 0 (black) to 1 (white): painted with `g`. + Gray(f64), + /// DeviceCMYK `[c, m, y, k]`, each from 0 to 1 (`[0, 0, 0, 1]` is 100 K): painted with `k`. + Cmyk([f64; 4]), +} + +impl Ink { + /// Whether every component is a number from 0 to 1. + pub fn valid(self) -> bool { + self.components().iter().all(|v| v.is_finite() && (0.0..=1.0).contains(v)) + } + + /// The ink as its operator paints it: each component to the thousandth that `g` and `k` are + /// written with (as RGB's `rg`), so the item, what it reads back as and the page agree. + pub fn painted(self) -> Ink { + let round = |v: f64| (v * 1000.0).round() / 1000.0; + match self { + Ink::Gray(g) => Ink::Gray(round(g)), + Ink::Cmyk(c) => Ink::Cmyk(c.map(round)), + } + } + + fn components(&self) -> &[f64] { + match self { + Ink::Gray(g) => std::slice::from_ref(g), + Ink::Cmyk(c) => c, + } + } + + /// How the ink looks on screen: gray is the same level in each of red, green and blue + /// (ISO 32000-2 §10.4.2.2), CMYK takes each colour plus black from 1 (§10.4.2.5). + pub fn rgb(self) -> [f64; 3] { + match self { + Ink::Gray(g) => [g.clamp(0.0, 1.0); 3], + Ink::Cmyk([c, m, y, k]) => [c, m, y].map(|v| 1.0 - (v + k).clamp(0.0, 1.0)), + } + } + + /// The operator that makes this ink the fill colour, without a line end. + pub(super) fn fill_op(self) -> String { + match self { + Ink::Gray(g) => format!("{} g", n(g.clamp(0.0, 1.0))), + Ink::Cmyk(c) => { + let [c, m, y, k] = c.map(|v| v.clamp(0.0, 1.0)); + format!("{} {} {} {} k", n(c), n(m), n(y), n(k)) + } + } + } +} + #[derive(Clone, Debug, PartialEq)] pub struct AddedText { /// The text box in display space; its width wraps the text and its top is the first line's @@ -100,7 +154,14 @@ pub struct AddedText { pub bold: bool, pub italic: bool, pub size: f64, + /// The RGB colour: what the text is painted in, unless it has an [`AddedText::ink`] this is + /// the look of. pub color: [f64; 3], + /// A gray or CMYK ink the text is painted in, with `color` its look ([`Ink::rgb`]). Set it + /// with [`AddedText::set_ink`] and the colour with [`AddedText::set_color`], which drops an + /// ink the colour no longer shows; one left behind by setting `color` directly paints nothing + /// ([`AddedText::painted_ink`]) until [`AddedText::drop_stale_ink`] forgets it. + pub ink: Option, pub align: Align, /// Extra space after every character, in points: the PDF's character spacing (`Tc`). pub char_spacing: f64, @@ -114,6 +175,44 @@ impl AddedText { pub fn paragraph_align(&self, i: usize) -> Align { crate::paragraph_align::align_of(&self.aligns, i, self.align) } + + /// Paint the text in `ink` (its look becomes [`AddedText::color`]), or in RGB with `None`. An + /// ink in range is kept as painted ([`Ink::painted`]); one out of range stays as given, for + /// saving to refuse. + pub fn set_ink(&mut self, ink: Option) { + let ink = ink.map(|i| if i.valid() { i.painted() } else { i }); + if let Some(i) = ink { + self.color = i.rgb(); + } + self.ink = ink; + } + + /// Paint the text in RGB `rgb`. Its ink stays only when `rgb` is the ink's own look; once + /// gone it stays gone, so picking that look again later paints in RGB. + pub fn set_color(&mut self, rgb: [f64; 3]) { + self.color = rgb; + self.drop_stale_ink(); + } + + /// Forget an ink `color` no longer shows, so two styles that paint the same compare equal. + pub fn drop_stale_ink(&mut self) { + self.ink = self.painted_ink(); + } + + /// The ink the text is painted in, or `None` for RGB: the one it has while `color` is still + /// its look. + pub fn painted_ink(&self) -> Option { + // Within rounding: a look read back from a file, or from a colour picker, is the same. + self.ink.filter(|i| i.rgb().iter().zip(self.color).all(|(a, b)| (a - b).abs() < 1e-6)) + } + + /// The operator that sets the text's fill colour, without a line end. + pub(super) fn fill_op(&self) -> String { + match self.painted_ink() { + Some(ink) => ink.fill_op(), + None => crate::marks::rgb(self.color), + } + } } impl Default for AddedText { @@ -126,6 +225,7 @@ impl Default for AddedText { italic: false, size: 12.0, color: [0.0; 3], + ink: None, align: Align::Left, aligns: Vec::new(), char_spacing: 0.0, diff --git a/crates/edit/src/backdrop.rs b/crates/edit/src/backdrop.rs index 43e16b40ec..f6788bb51c 100644 --- a/crates/edit/src/backdrop.rs +++ b/crates/edit/src/backdrop.rs @@ -208,7 +208,7 @@ pub(crate) fn restore(doc: &mut Document, page: &pdfcraft_model::Page) -> Result let same = |w: &ObjRef| match &*doc.get(*w) { Object::Stream(s) => { [TAG, &b"PCMark"[..], b"Subtype"].iter().all(|k| s.dict.get(k).is_none()) - && DecodeBudget::new(SCAN_BYTES, 0).decode_strict(s).ok().as_deref() == Some(bytes.as_slice()) + && DecodeBudget::new(SCAN_BYTES, 0).decode_strict(doc, s).ok().as_deref() == Some(bytes.as_slice()) } _ => false, }; @@ -248,7 +248,7 @@ fn restored_copy(doc: &Document, page: &pdfcraft_model::Page, copy: ObjRef) -> O return None; } let hash = note.get(b"Before")?.as_string()?; - let bytes = DecodeBudget::new(SCAN_BYTES, 0).decode_strict(s).ok()?; + let bytes = DecodeBudget::new(SCAN_BYTES, 0).decode_strict(doc, s).ok()?; let parsed = pdfcraft_content::parse(head(&bytes)); // The `n` standing in for the fill, after exactly the operators that came before it. let fill = parsed.ops.get(index)?; @@ -384,11 +384,11 @@ fn scan(doc: &Document, p: &pdfcraft_model::Page, swap: Option<(ObjRef, &[u8])>) if b.len() > SCAN_BYTES.saturating_sub(total) { return None; } - budget.decode_strict(&Stream::from_raw(Dict::new(), b.to_vec())).ok()? + budget.decode_strict(doc, &Stream::from_raw(Dict::new(), b.to_vec())).ok()? } // Tolerant decoding can return an empty or partial stream after corruption. // That cannot prove which paint preceded the candidate backdrop. - _ => budget.decode_strict(s).ok()?, + _ => budget.decode_strict(doc, s).ok()?, }; if bytes.len() > SCAN_BYTES.saturating_sub(total).saturating_sub(1) { return None; diff --git a/crates/edit/src/background.rs b/crates/edit/src/background.rs index 376cb5a165..27073ddc09 100644 --- a/crates/edit/src/background.rs +++ b/crates/edit/src/background.rs @@ -1,7 +1,7 @@ //! A page's background colour: the colour the page is painted with before anything else, as //! Edit a PDF ▸ Background and many producers do it, for exports that keep a page colour (#2992). -use pdfcraft_content::{Matrix, Op, Pieces}; +use pdfcraft_content::{Matrix, Op}; use pdfcraft_cos::{Dict, Document}; use crate::{EditError, Rgb}; @@ -51,7 +51,7 @@ pub fn page_background(doc: &Document, page: usize) -> Result, EditE let resources = p.dict.get(b"Resources").map(|r| doc.resolve(r)).and_then(|r| r.as_dict().cloned()).unwrap_or_default(); let gstates = resources.get(b"ExtGState").map(|g| doc.resolve(g)).and_then(|g| g.as_dict().cloned()).unwrap_or_default(); let streams = crate::text::content_streams(doc, &p.dict)?; - let pieces = Pieces::join(&streams.iter().map(|(_, d)| d.as_slice()).collect::>()); + let pieces = crate::text::joined(&streams); let ops = pieces.parse().ops; let mut st = State { ctm: Matrix::IDENTITY, space: Space::Gray, fill: Some([0.0; 3]), alpha: 1.0, plain: true, clip: Some(Vec::new()) }; diff --git a/crates/edit/src/images.rs b/crates/edit/src/images.rs index 72656fa1bb..e1b9e3626e 100644 --- a/crates/edit/src/images.rs +++ b/crates/edit/src/images.rs @@ -1,15 +1,15 @@ //! Edit a PDF ▸ edit existing images and grouped artwork (Image/Form XObjects painted by `Do` //! in its own content streams), and changing one: move/resize/rotate/flip (the `Do` is wrapped in //! `q … cm … Q` with the extra transform), replace (it draws another XObject in the same place), -//! or delete. Only the stream that draws it is rewritten, as a new object. +//! delete, or ungroup grouped artwork (its content drawn in place, see `ungroup`). Only the stream that draws it is rewritten, as a new object. use kurbo::{BezPath, Point, Shape}; -use pdfcraft_content::{Matrix, Op, Pieces, parse, serialize_ops}; +use pdfcraft_content::{Matrix, Op, parse, serialize_ops}; use pdfcraft_cos::{Dict, Document, ObjRef, Object}; use std::sync::Arc; use crate::EditError; -use crate::text::content_streams; +use crate::text::{ContentStream, content_streams, joined}; /// The identity of a soft mask (`/SMask`) in the PDF graphics state. #[derive(Clone, Debug)] @@ -47,7 +47,7 @@ pub struct PageImage { pub width: u32, pub height: u32, /// The content stream its `Do` (its first token) is in, and the `Do`'s index among the - /// operators of the page's streams joined ([`Pieces`]). + /// operators of the page's streams joined ([`pdfcraft_content::Pieces`]). pub stream: usize, op: usize, /// CTM before `Do`, excluding a Form's own Matrix. @@ -103,11 +103,6 @@ fn too_many_images() -> EditError { EditError::Invalid(format!("the page draws more than {MAX_PAGE_IMAGES} images")) } -/// The page's streams joined into the one stream they are: an operator may span two of them. -fn joined(streams: &[(Object, Vec)]) -> Pieces { - Pieces::join(&streams.iter().map(|(_, data)| data.as_slice()).collect::>()) -} - fn page_of(doc: &Document, page: usize) -> Result { pdfcraft_model::pages(doc).into_iter().nth(page).ok_or(EditError::NoSuchPage(page)) } @@ -470,6 +465,9 @@ pub enum ImageChange { Arrange(ArrangeOrder), /// Remove any private crop on the image. RemoveCrop, + /// Grouped Form artwork only: draw the form's content in place of its `Do`, so its text and + /// pictures become the page's own and can be edited one by one (#2964). + Ungroup, } /// The user-space transform that maps box `from` onto box `to` (move and resize). @@ -532,12 +530,17 @@ fn exclusive_clip(ops: &[Op], op: usize) -> Option<(usize, Matrix)> { /// The `q cm … Q` whose only content after its `cm` is `start..=end` (a `Do`, or a balanced /// `q … Q` scope), with the index and value of that `cm`. Another transform of the same /// placement is folded into it, so repeated moves and resizes don't nest one more `q` each. -fn enclosing_transform(ops: &[Op], start: usize, end: usize) -> Option<(usize, Matrix)> { +/// None when its `Q` is at or past `hidden` ([`crate::text::first_op_after_damage`]): a stream +/// between that wasn't read may draw in that `cm` too. +fn enclosing_transform(ops: &[Op], start: usize, end: usize, hidden: usize) -> Option<(usize, Matrix)> { let at = start.checked_sub(1)?; let cm = ops.get(at)?; if !ops.get(at.checked_sub(1)?)?.is("q") || !ops.get(end.checked_add(1)?)?.is("Q") || !cm.is("cm") || cm.operands.len() != 6 { return None; } + if end.checked_add(1)? >= hidden { + return None; + } let m = Matrix(cm.nums::<6>()?); m.0.iter().all(|v| v.is_finite()).then_some((at, m)) } @@ -1057,7 +1060,9 @@ fn determine_arrange_spans( has_other_paint: bool, marked_unit: bool, ) -> Result<(std::ops::Range, usize, usize, usize), EditError> { - let scope = image_scopes(ops, target, "arranged") + // Nothing is hidden for Arrange: it takes out the scope it finds, so a scope that closes past a + // stream not read whole changes a stream past it, which `rewritten_contents` refuses. + let scope = image_scopes(ops, target, "arranged", ops.len()) .ok() .and_then(|s| s.isolated) .filter(|&(start, end, _)| start >= target_unit.start && end < target_unit.end); @@ -1191,13 +1196,7 @@ fn build_relocated_unit_ops( } /// Change the stacking order of `img`, drawn on page `p` by its content streams `all`. -fn arrange_image( - doc: &mut Document, - p: &pdfcraft_model::Page, - all: &[(Object, Vec)], - img: &PageImage, - order: ArrangeOrder, -) -> Result<(), EditError> { +fn arrange_image(doc: &mut Document, p: &pdfcraft_model::Page, all: &[ContentStream], img: &PageImage, order: ArrangeOrder) -> Result<(), EditError> { let pieces = joined(all); let ops = pieces.parse().ops; let target = img.op; @@ -1264,7 +1263,7 @@ fn arrange_image( ops.get(dest_unit.start).map(|op| pieces.piece_of(op.span.start)) }; let owned_destination = destination_piece - .filter(|piece| all.get(*piece).is_some_and(|(obj, _)| doc.resolve(obj).as_dict().is_some_and(|d| d.get(b"PCAdded").is_some()))); + .filter(|piece| all.get(*piece).is_some_and(|s| doc.resolve(&s.entry).as_dict().is_some_and(|d| d.get(b"PCAdded").is_some()))); if let Some(piece) = owned_destination { let whole_unit = ops.iter().enumerate().all(|(index, op)| { let (first, last) = pieces.pieces_of(op); @@ -1439,13 +1438,14 @@ fn arrange_image( }; if let Some(piece) = owned_destination { + let insertion = piece.saturating_add(usize::from(insert_after)); + crate::text::drawn_before_damage(all, insertion)?; let changed = pieces.splice([(target_span, removal_replacement)]); - let contents = crate::text::rewritten_contents(doc, all, changed); + let contents = crate::text::rewritten_contents(doc, all, changed)?; let mut list = match contents { Object::Array(list) => list, one => vec![one], }; - let insertion = piece.saturating_add(usize::from(insert_after)); if insertion > list.len() { return Err(EditError::Invalid("the destination content stream is missing".into())); } @@ -1467,7 +1467,7 @@ fn arrange_image( } let changed = pieces.splice(edits); - let contents = crate::text::rewritten_contents(doc, all, changed); + let contents = crate::text::rewritten_contents(doc, all, changed)?; doc.update_dict(p.obj, |d| d.set(b"Contents".to_vec(), contents))?; Ok(()) } @@ -1501,8 +1501,10 @@ impl ImageScopes { } } -/// [`ImageScopes`] of the `Do` at `target`. An image inside a text object cannot be `done`. -fn image_scopes(ops: &[Op], target: usize, done: &str) -> Result { +/// [`ImageScopes`] of the `Do` at `target`. An image inside a text object cannot be `done`. A scope +/// still open at op `hidden` ([`crate::text::first_op_after_damage`]) holds a stream that wasn't +/// read, which may paint there: it counts as painting something else. +fn image_scopes(ops: &[Op], target: usize, done: &str, hidden: usize) -> Result { struct Scope { start: usize, matrix: Matrix, @@ -1521,6 +1523,11 @@ fn image_scopes(ops: &[Op], target: usize, done: &str) -> Result