pauljd/pdfcraft
1
0
Fork 0
mirror of https://github.com/storytold/pdfcraft.git synced 2026-11-09 10:46:38 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge origin/main

Browse Source 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01SqmHYx8FiWM5PcsoiErgp9
This commit is contained in:
KenM76
2026-11-06 06:54:33 -05:00
co-authored by Claude Opus 5.5
parent 980eaf7bce a0811650de
commit cf3ee49fbc
203 changed files with 30709 additions and 1218 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ATTRIBUTION.md
+2 -1
View File
@@ -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 (257)
## 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 |
ATTRIBUTION.toml
+11
View File
@@ -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\""
Cargo.lock
Generated
+26
View File
@@ -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 +1312,15 @@ dependencies = [
"zip",
]
[[package]]
name = "craft-web-host"
version = "0.1.0"
source = "git+https://github.com/storytold/craft-libs?rev=2e2312ddaf21bc3d85cd3395d0955c7d239306f6#2e2312ddaf21bc3d85cd3395d0955c7d239306f6"
dependencies = [
"wasm-bindgen",
"web-sys",
]
[[package]]
name = "craft-winprint-gdi"
version = "0.1.0"
@@ -4324,6 +4342,7 @@ version = "0.18.1"
dependencies = [
"chrono",
"hayro-syntax",
"js-sys",
"pdfcraft-crypt",
"pdfcraft-filters",
"pdfcraft-oracle",
@@ -4331,6 +4350,7 @@ dependencies = [
"proptest",
"serde_json",
"thiserror 2.0.21",
"wasm-bindgen",
]
[[package]]
@@ -4507,6 +4527,7 @@ version = "0.18.1"
dependencies = [
"ocrs",
"pdfcraft-fonts",
"png 0.18.1",
"rten",
"tempfile",
"thiserror 2.0.21",
@@ -4598,6 +4619,7 @@ dependencies = [
name = "pdfcraft-redact"
version = "0.18.1"
dependencies = [
"aho-corasick",
"pdfcraft-annot",
"pdfcraft-content",
"pdfcraft-cos",
@@ -4606,8 +4628,10 @@ dependencies = [
"pdfcraft-fonts",
"pdfcraft-forms",
"pdfcraft-model",
"pdfcraft-render",
"pdfcraft-testkit",
"pdfcraft-xfa",
"sha2 0.11.1",
"thiserror 2.0.21",
]
@@ -4702,6 +4726,7 @@ dependencies = [
"pdfcraft-engine",
"pdfcraft-fonts",
"pdfcraft-model",
"pdfcraft-ocr",
"pdfcraft-platform",
"pdfcraft-render",
"pdfcraft-xfa",
@@ -4729,6 +4754,7 @@ dependencies = [
name = "pdfcraft-web"
version = "0.18.1"
dependencies = [
"craft-web-host",
"eframe",
"egui",
"js-sys",
README.md
+12
View File
@@ -253,6 +253,18 @@ Documents restricted by their author show a clear notice, and PdfCraft honours t
</tr>
</table>
## 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.
<p align="center">
<img src="docs/images/pdfcraft-ocr-verify.png" alt="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" width="100%">
<br>
<sub>The OCR Verify screen: words coloured by confidence — the legend spells the thresholds out — reviewed and corrected before anything is applied.</sub>
</p>
---
## Every tool, one keystroke away
Press <kbd>⌘K</kbd> 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.
ROADMAP.md
+12
View File
@@ -31,6 +31,7 @@
> **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)
@@ -273,6 +274,7 @@ Ranked; detail and the full milestone table in [docs/roadmap.md](docs/roadmap.md
- **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.
@@ -301,7 +303,11 @@ 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.
@@ -323,6 +329,7 @@ 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.
@@ -333,6 +340,7 @@ 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.
@@ -344,9 +352,13 @@ 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.
apps/pdfcraft-cli/tests/it/batch_exit.rs
+111
View File
@@ -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();
}
apps/pdfcraft-cli/tests/it/main.rs
+1
View File
@@ -3,6 +3,7 @@
mod audit;
mod automation_roots;
mod batch;
mod batch_exit;
mod check;
mod edit;
mod extract;
apps/pdfcraft-web/Cargo.toml
+3 -1
View File
@@ -11,10 +11,12 @@ workspace = true
[dependencies]
pdfcraft-ui-egui = { workspace = true }
# The host messages (storytold/craft-libs): one contract and one bridge for the web builds.
craft-web-host = { git = "https://github.com/storytold/craft-libs", rev = "2e2312ddaf21bc3d85cd3395d0955c7d239306f6", version = "0.1.0" }
eframe = { workspace = true, features = ["default_fonts", "glow", "persistence", "accesskit"] }
egui = { workspace = true, features = ["default_fonts", "monochrome_emoji_fonts"] }
[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"
apps/pdfcraft-web/src/main.rs
+81 -110
View File
@@ -5,18 +5,11 @@
#[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::<web_sys::HtmlCanvasElement>().ok())
else {
return;
};
let Some(canvas) = app_canvas() else { return };
let started = eframe::WebRunner::new()
.start(
canvas,
@@ -54,11 +47,11 @@ 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())
@@ -81,9 +74,7 @@ fn main() {
.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 +114,116 @@ async fn fetch_bytes(url: &str) -> Result<Vec<u8>, 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<web_sys::HtmlCanvasElement> {
use eframe::wasm_bindgen::JsCast;
web_sys::window()?.document()?.get_element_by_id("pdfcraft").and_then(|e| e.dyn_into::<web_sys::HtmlCanvasElement>().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<Host>,
}
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<Self> {
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<Self> {
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::<dyn FnMut(web_sys::MessageEvent)>::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::<js_sys::Uint8Array>() {
array.to_vec()
} else if bytes.is_instance_of::<js_sys::ArrayBuffer>() {
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<js_sys::Object> {
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<String> {
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();
}
}
apps/pdfcraft/src/main.rs
+2
View File
@@ -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;
contributors/people.toml
+3
View File
@@ -183,3 +183,6 @@ sync_github_name = true
[people.Combiler01]
sync_github_name = true
[people.helenkwok]
real_name = "Helen Kwok"
crates/annot/src/appearance.rs
+170 -64
View File
@@ -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<Rgb> {
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::<f64>().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<Dict> {
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<Dict> {
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<Rgb>,
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<AppearanceContext<'_>> {
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<String> = 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<Rgb>,
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<Stream> {
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;
}
crates/annot/src/appearance/symbols.rs
+2 -2
View File
@@ -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<Stream> {
// 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.
crates/annot/src/create.rs
+14 -13
View File
@@ -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<Object>) -> Result<(), AnnotError> {
let Some(rect) = rect else { return Ok(()) };
let mut popup = Dict::new();
crates/annot/src/info.rs
+15 -2
View File
@@ -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<Rgb>,
/// Text boxes, typewriter text and callouts: the `/DA` font size in points.
pub font_size: Option<f64>,
/// Text boxes, typewriter text and callouts: the border's own colour (`None`: the text's).
pub border_color: Option<Rgb>,
/// Text boxes and typewriter text: the border's shape (callouts have none to choose).
pub border_shape: Option<BorderShape>,
/// 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<f64>,
/// How opaque a text box's, typewriter text's or callout's text is drawn.
pub text_opacity: Option<f64>,
}
/// The current properties of the comment at `(page, index)`.
@@ -239,7 +248,7 @@ pub fn props(doc: &Document, page: usize, index: usize) -> Option<Props> {
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<Props> {
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),
})
crates/annot/src/lib.rs
+5 -4
View File
@@ -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;
crates/annot/src/modify.rs
+264 -22
View File
@@ -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<Vec<f64>> { 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<Rgb>, 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<Rgb>, 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<f64> =
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<Rgb>
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<f64>, text: Option<f64>, 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();
crates/annot/src/tests.rs
+373 -3
View File
@@ -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<f64> {
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<f64> { 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<f64> {
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 {
crates/annot/src/types.rs
+132 -5
View File
@@ -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<Self> {
[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<Vec<[f64; 2]>> {
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<Rgb>,
/// 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<Rgb>,
/// 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<f64>,
/// A text box's text's own opacity, 0–1 (`/PCTextOpacity`); `None`: as the fill's.
pub text_opacity: Option<f64>,
}
/// 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> {
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() }
}
}
crates/automation/README.md
+23
View File
@@ -281,3 +281,26 @@ 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).
crates/automation/src/a11y/ocr.rs
+472 -36
View File
@@ -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<pdfcraft_engine::ocr::OcrSettings> {
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::<Vec<_>>().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<Option<[f32; 4]>> {
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<f32> = 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<Value> {
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<Value> {
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<std::path::PathBuf> = 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<String> = 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<String> = 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<usize> = 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<usize> = 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<Value> {
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::<usize>();
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::<usize>(),
"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<Value> {
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<usize, pdfcraft_render::PageInfo> =
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<Value> = 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<Value> = 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<f32> = corners.iter().flatten().map(|v| v[0]).collect();
let ys: Vec<f32> = 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::<usize>(), "pages": list }))
let mut out = json!({ "words": found.iter().map(|p| p.words.len()).sum::<usize>(), "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<Value> {
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::<usize>() })
}
_ => 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<Value> {
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-<language>.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<Value> {
use pdfcraft_engine::ocr;
let dirs: Vec<String> = ocr::Models::search_dirs().iter().map(|d| d.to_string_lossy().into_owned()).collect();
let langs: Vec<Value> = 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<Value> = 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 }))
}
}
crates/automation/src/batch.rs
+2 -2
View File
@@ -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()}),
);
crates/automation/src/bates.rs
+1 -1
View File
@@ -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)?;
crates/automation/src/comments.rs
+152 -7
View File
@@ -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::<Vec<_>>()).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::<Result<Vec<_>>>()?;
@@ -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<Value> {
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<Value> {
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<Value> {
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 <annots>)".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<Option<BorderShape>> {
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::*;
crates/automation/src/dispatch.rs
+5
View File
@@ -812,6 +812,9 @@ 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)?,
@@ -867,6 +870,8 @@ 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)])
crates/automation/src/documents.rs
+1
View File
@@ -120,6 +120,7 @@ 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 }))
}
crates/automation/src/lib.rs
+11
View File
@@ -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<pdfcraft_engine::ocr::OcrPage>,
}
/// 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<DocId>,
/// Review sessions held for `ocr_words` (a guard and the pages read), by document.
ocr_reviews: HashMap<DocId, OcrReview>,
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,
}
}
crates/automation/src/tools.rs
+105 -13
View File
@@ -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::<Vec<&str>>() })
}
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,
@@ -606,7 +620,7 @@ pub fn tools() -> Vec<ToolDef> {
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); 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!({
@@ -617,7 +631,7 @@ pub fn tools() -> Vec<ToolDef> {
"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(),
"whole_pages": { "type": "boolean" },
"pages": pages("to search or mark (default: all); mutually exclusive with page, and not valid with rect"),
"overlay": { "type": "string" },
@@ -859,9 +873,13 @@ pub fn tools() -> Vec<ToolDef> {
"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"],
@@ -992,13 +1010,17 @@ pub fn tools() -> Vec<ToolDef> {
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(),
@@ -1009,6 +1031,25 @@ pub fn tools() -> Vec<ToolDef> {
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",
@@ -1339,31 +1380,79 @@ pub fn tools() -> Vec<ToolDef> {
)),
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 <document>_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-<language>.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!({}), &[])),
@@ -1384,7 +1473,7 @@ pub fn tools() -> Vec<ToolDef> {
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(
@@ -1396,6 +1485,9 @@ pub fn tools() -> Vec<ToolDef> {
"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)." },
crates/automation/tests/it/action_failures.rs
+66
View File
@@ -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<u8> {
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:?}");
}
crates/automation/tests/it/automation.rs
+554 -14
View File
@@ -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 &registry {
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<Value> = 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<f64> = 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");
@@ -2464,6 +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;
@@ -4026,6 +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");
@@ -4670,6 +4840,35 @@ 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<u8> {
@@ -6494,6 +6693,44 @@ 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<Vec<[f64; 2]>> =
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");
@@ -7277,6 +7514,8 @@ 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;
@@ -7291,6 +7530,64 @@ 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
@@ -7333,6 +7630,46 @@ 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");
@@ -7346,9 +7683,22 @@ 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}");
@@ -7358,18 +7708,6 @@ 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.
@@ -10583,6 +10921,162 @@ fn simple_rule_scan_drawn(content: &[u8]) -> Vec<u8> {
write_full(&doc, &SaveOptions::default()).unwrap()
}
/// 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<u8> {
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");
@@ -10927,3 +11421,49 @@ 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<Value> = 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("<square"), "{xfdf}");
let dst = ok(&mut a, "doc_open", json!({ "path": "b.pdf" }))["doc"].as_u64().unwrap();
let r = ok(&mut a, "comments_paste", json!({ "doc": dst, "page": 1, "xfdf": xfdf }));
assert_eq!(r["comments"], 3, "two comments and the reply: {r}");
assert_eq!(r["undo"], "Paste comments");
let list = ok(&mut a, "comment_list", json!({ "doc": dst }));
let comments = list["comments"].as_array().unwrap();
assert_eq!(comments.len(), 2, "the reply is in its thread, not a comment of its own: {list}");
assert!(comments.iter().all(|c| c["page"] == 1), "{list}");
assert_eq!(comments.iter().filter(|c| c["contents"] == "Please review").count(), 1);
// The same again: a second set, not a replacement of the first.
ok(&mut a, "comments_paste", json!({ "doc": dst, "page": 1, "xfdf": copied["xfdf"] }));
assert_eq!(ok(&mut a, "comment_list", json!({ "doc": dst }))["comments"].as_array().unwrap().len(), 4);
// Placed: the copies' box is centred at `at` (top-left page coordinates, like comment_add).
let r = ok(&mut a, "comments_paste", json!({ "doc": dst, "page": 2, "xfdf": copied["xfdf"], "at": [100, 150] }));
assert_eq!(r["comments"], 3);
let placed = ok(&mut a, "comment_list", json!({ "doc": dst, "page": 2 }));
let rects: Vec<Vec<f64>> =
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");
}
crates/automation/tests/it/batch_failures.rs
+89
View File
@@ -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<u8> {
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<String> =
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}");
}
crates/automation/tests/it/batch_secrets.rs
+84
View File
@@ -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<u8> {
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}");
}
}
}
crates/automation/tests/it/main.rs
+3
View File
@@ -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;
crates/automation/tests/pattern_redaction.rs
+146
View File
@@ -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<u8> {
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<u8>) -> 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");
}
}
}
crates/compare/src/lib.rs
+14
View File
@@ -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::<Vec<_>>().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);
crates/cos/Cargo.toml
+7
View File
@@ -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 }
crates/cos/README.md
+11 -1
View File
@@ -62,7 +62,9 @@ another. Edits never touch the original bytes.
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. Headers beyond
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
@@ -89,6 +91,14 @@ into compressed object streams with a cross-reference stream (PDF 1.5+); turning
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.
crates/cos/src/document.rs
+3
View File
@@ -71,6 +71,9 @@ 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<Arc<pdfcraft_crypt::SecurityHandler>>,
out_encrypt_num: Option<u32>,
crates/cos/src/document/objects.rs
+24
View File
@@ -175,6 +175,30 @@ impl Document {
}
}
/// 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<u16> {
// 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<Arc<Object>, CosError> {
if !self.reference_matches(r) {
return Ok(Arc::new(Object::Null));
crates/cos/src/document/open.rs
+15
View File
@@ -35,6 +35,7 @@ impl Document {
unfound: Arc::default(),
encryption_changed: false,
full_save: false,
new_id: false,
out_security: None,
out_encrypt_num: None,
};
@@ -121,6 +122,7 @@ impl Document {
unfound: Arc::default(),
encryption_changed: false,
full_save: false,
new_id: false,
out_security: None,
out_encrypt_num: None,
};
@@ -290,12 +292,25 @@ 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.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).
pub fn encryption_changed(&self) -> bool {
self.encryption_changed
crates/cos/src/lib.rs
+1 -1
View File
@@ -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 {
crates/cos/src/writer.rs
+246 -31
View File
@@ -167,11 +167,17 @@ 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 }
}
}
@@ -267,16 +273,12 @@ pub fn write_incremental(doc: &Document, opts: &SaveOptions) -> Result<Vec<u8>,
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<Vec<u8>, 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.
type SaveOrder = (HashMap<ObjRef, u32>, Vec<(ObjRef, bool)>);
fn full_save_order(reader: &mut ObjectReader, trailer_in: &Dict) -> Result<SaveOrder, CosError> {
// Breadth-first walk from the trailer, assigning new numbers in visit order.
let mut map: HashMap<ObjRef, u32> = HashMap::new();
// Record the type while traversing so classifying packed objects needs no second parse.
@@ -320,6 +322,30 @@ pub fn write_full(doc: &Document, opts: &SaveOptions) -> Result<Vec<u8>, CosErro
order.push((canonical, matches!(*o, Object::Stream(_))));
visit_refs(&o, &mut queue);
}
Ok((map, order))
}
/// 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<HashSet<u32>, CosError> {
let mut reader = doc.object_reader();
let trailer_in = reader.document.trailer().clone();
let (_, order) = full_save_order(&mut reader, &trailer_in)?;
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<Vec<u8>, 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) = full_save_order(&mut reader, &trailer_in)?;
let version = reader.document.version().chars().take(3).collect::<String>();
let version = if opts.object_streams && version.as_str() < "1.5" { "1.5".to_string() } else { version };
let mut out = Vec::new();
@@ -383,26 +409,7 @@ pub fn write_full(doc: &Document, opts: &SaveOptions) -> Result<Vec<u8>, 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 {
@@ -421,6 +428,34 @@ pub fn write_full(doc: &Document, opts: &SaveOptions) -> Result<Vec<u8>, CosErro
Ok(out)
}
/// Assemble the full rewrite's trailer and apply its identifier policy.
fn full_save_trailer(doc: &Document, trailer_in: &Dict, map: &HashMap<ObjRef, u32>, 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.
@@ -669,6 +704,136 @@ 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<u8> {
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<u64> {
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::<js_sys::Function>().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));
@@ -711,6 +876,56 @@ 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<u8> = (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;
crates/cos/tests/file_identifier.rs
+276
View File
@@ -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<u8> {
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<u8> {
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<u8> {
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<u8>) -> 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<Vec<u8>> {
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<Object>)> {
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<Object>) -> Vec<u8> {
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<u8> {
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");
}
crates/cos/tests/it/generations.rs
+35
View File
@@ -473,3 +473,38 @@ fn restoring_explicit_sets_removes_old_generation_aliases() {
}
}
}
/// `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]);
}
crates/create/src/lib.rs
+20
View File
@@ -92,6 +92,26 @@ pub fn blank(width: f64, height: f64, pages: usize) -> Result<Document, CreateEr
Ok(doc)
}
/// A document whose pages hold ready-made content: one `(width, height, resources, content)`
/// tuple per page, in page order. Empty content vectors make blank pages. The OCR Verify
/// screen's editable-text output builds its pages this way.
pub fn from_contents(pages: &[(f64, f64, Dict, Vec<u8>)]) -> Result<Document, CreateError> {
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
crates/crypt/src/lib.rs
+19 -7
View File
@@ -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`.
crates/crypt/src/tests.rs
+3 -3
View File
@@ -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");
}
crates/crypt/tests/it/main.rs
+1
View File
@@ -1,4 +1,5 @@
//! The crate's integration tests, linked into one test binary.
mod permissions_revision;
mod proptests;
mod qpdf_literals;
crates/crypt/tests/it/permissions_revision.rs
+126
View File
@@ -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");
}
crates/edit/src/lib.rs
+1 -1
View File
@@ -78,7 +78,7 @@ pub(crate) use place::undrawable;
#[cfg(test)]
use place::{ISOLATION_MAX_DEPTH, OLD_WRAP_CLOSE, WRAP_CLOSE, WRAP_OPEN, is_wrap_close, page_fonts, stream_bytes, stream_tag, tagged, wrapper_role};
use place::{Reach, check, check_on_top, contents, draw_on_top, lift_on_top, page_list, place_tagged, revealed_under_paint};
pub use place::{stamp, undrawable_message};
pub use place::{add_type3_fonts, stamp, stamp_with_fonts, undrawable_message};
#[cfg(test)]
mod marked_isolation_tests;
crates/edit/src/place.rs
+65
View File
@@ -478,14 +478,79 @@ pub(crate) fn place_inside_wrapper(doc: &mut Document, page: &pdfcraft_model::Pa
/// it away); the original content is wrapped in q/Q first. Used for applied redaction boxes.
/// Returns the new content stream.
pub fn stamp(doc: &mut Document, page: usize, tag: &str, content: Vec<u8>) -> Result<ObjRef, EditError> {
stamp_with_fonts(doc, page, tag, &mut pdfcraft_fonts::TextPlan::default(), |_| content)
}
/// Draw the content `make` builds on top of a page, with standard Helvetica as `/PCHelv` and
/// the plan's Type3 fonts added to the page's resources first (so the content can reference
/// them by the names the plan carries). The original content is wrapped in q/Q first; the
/// stream is tagged `tag` (not a mark kind, so Remove never takes it away). This is how the
/// OCR text layers get their Unicode faces (see [`add_type3_fonts`]). Returns the new content
/// stream.
pub fn stamp_with_fonts(
doc: &mut Document,
page: usize,
tag: &str,
plan: &mut pdfcraft_fonts::TextPlan,
make: impl FnOnce(&pdfcraft_fonts::TextPlan) -> Vec<u8>,
) -> Result<ObjRef, EditError> {
let all = page_list(doc);
check(&[page], all.len())?;
check_on_top(doc, &all[page])?;
add_type3_fonts(doc, page, plan)?;
let content = make(plan);
let all = page_list(doc);
add_resources(doc, &all[page], None, Some(&content))?;
let p = page_list(doc).swap_remove(page);
place_tagged(doc, &p, tag, content, false)
}
/// Add the plan's Type3 fonts to a page's (0-based) resources, building each font once and
/// sharing the object with every page that uses it. Fills in each planned font's resource name
/// (`PCOcr`, `PCOcr1`, … — a name free on the page being registered: a font built for an
/// earlier page keeps its name only where that name is free or already that font) and object;
/// the content generators read the names from the plan, so this must run before they are
/// called for each page.
pub fn add_type3_fonts(doc: &mut Document, page: usize, plan: &mut pdfcraft_fonts::TextPlan) -> Result<(), EditError> {
if plan.fonts.is_empty() {
return Ok(());
}
let all = page_list(doc);
check(&[page], all.len())?;
let p = &all[page];
let mut res = p.dict.get(b"Resources").map(|r| doc.resolve(r)).and_then(|r| r.as_dict().cloned()).unwrap_or_default();
let mut fonts = res.get(b"Font").map(|f| doc.resolve(f)).and_then(|f| f.as_dict().cloned()).unwrap_or_default();
for i in 0..plan.fonts.len() {
let object = match plan.fonts[i].object {
Some(r) => {
// Built for an earlier page under a name that was free THERE. On this page the
// name may already be another font (the page's own, or an earlier OCR layer's):
// then this page gets a free name of its own, and the plan carries it for the
// content written next.
let taken = fonts.get(plan.fonts[i].name.as_bytes()).is_some_and(|o| o.as_ref() != Some(r));
if taken {
plan.fonts[i].name = super::text::unique_font_name(&fonts, "PCOcr");
}
r
}
None => {
let glyphs = plan.fonts[i].glyphs.iter().map(|(ch, g)| (*ch, super::text::glyph_path(g), g.width)).collect::<Vec<_>>();
let dict = super::text::type3_font_dict(doc, &glyphs)?;
let r = doc.add(Object::Dict(dict));
plan.fonts[i].name = super::text::unique_font_name(&fonts, "PCOcr");
plan.fonts[i].object = Some(r);
r
}
};
fonts.set(plan.fonts[i].name.as_bytes().to_vec(), Object::Ref(object));
}
res.set(b"Font".to_vec(), Object::Dict(fonts));
// The page gets its own (possibly copied) resources; shared dictionaries stay untouched.
let obj = p.obj;
doc.update_dict(obj, |d| d.set(b"Resources".to_vec(), Object::Dict(res)))?;
Ok(())
}
pub(crate) fn begin(kind: MarkKind, subtype: &str, matrix: [f64; 6]) -> String {
format!(
"q\n/Artifact <</Type /Pagination /Subtype /{subtype} /PCMark /{}>> BDC\n{} {} {} {} {} {} cm\n",
crates/edit/src/tests.rs
+111 -3
View File
@@ -3514,7 +3514,10 @@ fn page_content_bytes(doc: &Document, page: usize) -> Vec<u8> {
}
}
/// A page drawing image XObject /Im0 at 100,100 size 200 × 100 (pixels 4 × 2).
/// A page drawing image XObject /Im0 at 100,100 size 200 × 100 (pixels 4 × 2), on a real optional
/// content layer: the catalog's `/OCProperties` declares object 7 as the only OCG and the page
/// resources' `/Properties` maps `/L0` to it, so `/OC /L0 BDC` marks a valid optional-content
/// member rather than a dangling name.
fn image_page() -> Document {
image_page_with("q 200 0 0 100 100 100 cm /Im0 Do Q BT /F1 12 Tf 72 700 Td (Caption) Tj ET")
}
@@ -3534,12 +3537,13 @@ fn remove_crop(doc: &mut Document, page: usize, index: usize) -> Result<(), Edit
fn image_page_with(content: &str) -> Document {
let objs: Vec<String> = vec![
"<< /Type /Catalog /Pages 2 0 R >>".into(),
"<< /Type /Catalog /Pages 2 0 R /OCProperties << /OCGs [7 0 R] /D << /Order [7 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 >> /XObject << /Im0 6 0 R >> /ExtGState << /GS0 << /Type /ExtGState /ca 0.5 /CA 0.5 >> /GSalpha << /Type /ExtGState /ca 0.6 >> /GSblend << /Type /ExtGState /BM /Multiply >> /GS_translucent << /Type /ExtGState /ca 0.5 >> >> >> >>".into(),
"<< /Type /Page /Parent 2 0 R /MediaBox [0 0 600 800] /Contents 4 0 R /Resources << /Font << /F1 5 0 R >> /XObject << /Im0 6 0 R >> /ExtGState << /GS0 << /Type /ExtGState /ca 0.5 /CA 0.5 >> /GSalpha << /Type /ExtGState /ca 0.6 >> /GSblend << /Type /ExtGState /BM /Multiply >> /GS_translucent << /Type /ExtGState /ca 0.5 >> >> /Properties << /L0 7 0 R >> >> >>".into(),
format!("<< /Length {} >>\nstream\n{content}\nendstream", content.len()),
"<< /Type /Font /Subtype /Type1 /BaseFont /Helvetica >>".into(),
"<< /Type /XObject /Subtype /Image /Width 4 /Height 2 /ColorSpace /DeviceGray /BitsPerComponent 8 /Length 8 >>\nstream\n\u{0}\u{0}\u{0}\u{0}\u{0}\u{0}\u{0}\u{0}\nendstream".into(),
"<< /Type /OCG /Name (Layer 0) >>".into(),
];
let mut out = b"%PDF-1.7\n".to_vec();
let mut offs = Vec::new();
@@ -3753,6 +3757,30 @@ fn repeated_group_moves_of_a_cropped_image_change_one_clip_transform() {
assert_eq!(caption, ["Caption"]);
}
#[test]
fn moving_an_image_inside_marked_content_leaves_every_sequence_intact() {
// `translate_images` changes the image's own `cm`; its `Do` stays where it was, so a moved
// image stays in the sequence that tags it (an image on a layer sits in `/OC … BDC`).
for content in [
"/P <</MCID 0>> BDC q 100 0 0 100 50 50 cm /Im0 Do Q EMC /P <</MCID 1>> BDC BT /F1 12 Tf 72 700 Td (Text) Tj ET EMC",
"/OC /L0 BDC q 100 0 0 100 50 50 cm /Im0 Do Q EMC /P <</MCID 1>> BDC BT /F1 12 Tf 72 700 Td (Text) Tj ET EMC",
] {
let mut doc = image_page_with(content);
let before = images::page_images(&doc, 0).unwrap()[0].rect;
images::translate_images(&mut doc, 0, &[0], [10.0, 0.0]).unwrap();
let after = images::page_images(&doc, 0).unwrap()[0].rect;
assert!(close(after, [before[0] + 10.0, before[1], before[2] + 10.0, before[3]]), "{content}: {after:?}");
let ops = pdfcraft_content::parse(&page_content_bytes(&doc, 0)).ops;
let count = |name: &str| ops.iter().filter(|op| op.is(name)).count();
assert_eq!((count("BDC"), count("EMC")), (2, 2), "{content}: both sequences remain");
let first = ops.iter().position(|op| op.is("BDC")).unwrap();
let end = ops.iter().position(|op| op.is("EMC")).unwrap();
let image = ops.iter().position(|op| op.is("Do")).unwrap();
assert!(first < image && image < end, "{content}: the image is still inside its own sequence");
assert!(!ops[end..].iter().any(|op| op.is("Do")), "{content}: the other sequence gained no image");
}
}
#[test]
fn page_images_move_turn_replace_and_delete() {
let mut doc = image_page();
@@ -10229,6 +10257,86 @@ fn styled_existing_justification_is_refused_instead_of_silently_left_aligning()
assert_eq!(page_content_bytes(&reopen(&doc), 0), before);
}
/// The OCR stamp path registers the plan's Type3 faces (a free `PCOcr…` name per stamp, so a
/// page that is OCR'd twice keeps both layers' fonts), and the stamped codes extract back
/// through the font's ToUnicode CMap.
#[test]
fn stamp_with_fonts_registers_the_planned_type3_faces() {
if without_craft_fonts("stamp_with_fonts_registers_the_planned_type3_faces") {
return;
}
let mut doc = text_page("BT /F2 12 Tf 72 700 Td (ab) Tj ET");
let mut plan = pdfcraft_fonts::TextPlan::for_words(["日本"]);
assert_eq!(plan.missing(), 0);
stamp_with_fonts(&mut doc, 0, "OCR", &mut plan, |p| {
let codes: Vec<u8> = p.encoding(0).iter().map(|&(_, c)| c).collect();
let mut c = format!("BT 3 Tr /PCHelv 1 Tf\n/{} 1 Tf 100 700 Td ", p.fonts[0].name).into_bytes();
c.extend_from_slice(&pdfcraft_fonts::literal(&codes));
c.extend_from_slice(b" Tj ET");
c
})
.unwrap();
assert!(plan.fonts[0].name.starts_with("PCOcr"), "{:?}", plan.fonts[0].name);
// The registered font carries a ToUnicode CMap; the engine's own reader decodes the run.
let reopened = Document::open(Arc::new(write_incremental(&doc, &SaveOptions::default()).unwrap())).unwrap();
let lines = text::text_lines(&reopened, 0).unwrap();
assert!(lines.iter().any(|l| l.text.contains("日本")), "{lines:?}");
// A second stamp on the same page takes the next free name; the first layer's font stands.
let mut second = pdfcraft_fonts::TextPlan::for_words(["語"]);
stamp_with_fonts(&mut doc, 0, "OCR", &mut second, |p| format!("BT 3 Tr /{} 1 Tf 100 600 Td (\u{1}) Tj ET", p.fonts[0].name).into_bytes())
.unwrap();
assert_eq!(second.fonts[0].name, format!("{}1", plan.fonts[0].name));
}
/// A Type3 face built for page 1 is reused on page 2, but page 2 already has a font under the
/// name page 1 gave it: page 2's own font keeps its name, and the shared face is registered on
/// page 2 under a free one that the plan carries for page 2's content. (The plan is written out
/// by hand, so this runs without the craft-fonts build input.)
#[test]
fn a_reused_type3_face_never_replaces_a_later_page_s_font_of_the_same_name() {
let mut doc = build(&[
"<< /Type /Catalog /Pages 2 0 R >>",
"<< /Type /Pages /Kids [3 0 R 4 0 R] /Count 2 >>",
"<< /Type /Page /Parent 2 0 R /MediaBox [0 0 600 800] /Contents 5 0 R >>",
"<< /Type /Page /Parent 2 0 R /MediaBox [0 0 600 800] /Contents 6 0 R /Resources << /Font << /PCOcr 7 0 R >> >> >>",
&stream("", ""),
&stream("", "BT /PCOcr 12 Tf 72 700 Td (own) Tj ET"),
"<< /Type /Font /Subtype /Type1 /BaseFont /Helvetica /Encoding /WinAnsiEncoding >>",
]);
let glyph = pdfcraft_fonts::GlyphOutline { contours: vec![vec![[0.1, 0.0], [0.9, 0.0], [0.5, 0.8]]], width: 1.0, bbox: [0.1, 0.0, 0.9, 0.8] };
let mut plan = pdfcraft_fonts::TextPlan::default();
plan.fonts.push(pdfcraft_fonts::PlannedType3 { family: "Test", glyphs: vec![('日', glyph)], name: String::new(), object: None });
let draw = |p: &pdfcraft_fonts::TextPlan| format!("BT 3 Tr /{} 1 Tf 100 600 Td (\u{1}) Tj ET", p.fonts[0].name).into_bytes();
stamp_with_fonts(&mut doc, 0, "OCR", &mut plan, draw).unwrap();
assert_eq!(plan.fonts[0].name, "PCOcr", "free on page 1");
let face = plan.fonts[0].object.expect("built once");
stamp_with_fonts(&mut doc, 1, "OCR", &mut plan, draw).unwrap();
assert_ne!(plan.fonts[0].name, "PCOcr", "page 2 already has a PCOcr");
let page2 = &pdfcraft_model::pages(&doc)[1];
let res = doc.resolve(page2.dict.get(b"Resources").unwrap());
let fonts = doc.resolve(res.as_dict().unwrap().get(b"Font").unwrap());
let fonts = fonts.as_dict().unwrap();
assert_eq!(fonts.get(b"PCOcr").and_then(|o| o.as_ref()), Some(pdfcraft_cos::ObjRef::new(7, 0)), "page 2's own font keeps its name");
assert_eq!(fonts.get(plan.fonts[0].name.as_bytes()).and_then(|o| o.as_ref()), Some(face), "the shared face, under a free name");
assert_eq!(plan.fonts[0].object, Some(face), "still built once");
}
#[test]
fn planned_type3_charproc_has_valid_metrics_and_encloses_its_ink() {
let glyph = pdfcraft_fonts::GlyphOutline {
contours: vec![vec![[-0.1001, -0.2001], [0.9001, 1.1001]]],
width: 0.8,
bbox: [-0.1001, -0.2001, 0.9001, 1.1001],
};
let parsed = pdfcraft_content::parse(&text::glyph_path(&glyph));
assert_eq!(parsed.skipped, 0);
let metrics = &parsed.ops[0];
assert!(metrics.is("d1"));
assert_eq!(metrics.operands.len(), 6);
assert_eq!((metrics.num(0), metrics.num(1)), (Some(800.0), Some(0.0)));
assert_eq!((metrics.num(2), metrics.num(3), metrics.num(4), metrics.num(5)), (Some(-101.0), Some(-201.0), Some(901.0), Some(1101.0)));
}
#[test]
fn image_arrange_refuses_crossed_scope_boundaries_without_changes() {
for content in ["/P <</MCID 0>> BDC q 10 0 0 10 0 0 cm /Im0 Do EMC Q /Im0 Do", "q /P <</MCID 0>> BDC /Im0 Do Q EMC /Im0 Do"] {
crates/edit/src/text.rs
+1
View File
@@ -52,6 +52,7 @@ use fallback::{
};
#[cfg(test)]
use fallback::{add_type3_font, is_type3_fallback};
pub(crate) use fallback::{glyph_path, type3_font_dict, unique_font_name};
use interp::{Origin, Paint, union};
use lines::page_dict;
pub(crate) use lines::{FormBudget, content_streams, content_streams_within, dict_in_place, form_call, resource_dict, rewritten_contents, splice};
crates/edit/src/text/fallback.rs
+86
View File
@@ -493,6 +493,92 @@ pub(super) fn add_type3_font(doc: &mut Document, fonts_res: &mut Dict, face: &Cr
name
}
/// A glyph's CharProc body at 1000 units per em, with a six-operand `d1` and its actual ink box.
pub(crate) fn glyph_path(glyph: &pdfcraft_fonts::GlyphOutline) -> Vec<u8> {
let scale = 1000.0;
let b = if glyph.contours.is_empty() { [0.0; 4] } else { glyph.bbox };
let mut out = format!(
"{} 0 {} {} {} {} d1\n",
pdf_num(glyph.width * scale),
pdf_num((b[0] * scale).floor()),
pdf_num((b[1] * scale).floor()),
pdf_num((b[2] * scale).ceil()),
pdf_num((b[3] * scale).ceil())
)
.into_bytes();
for contour in &glyph.contours {
let Some(first) = contour.first() else { continue };
out.extend_from_slice(format!("{} {} m\n", pdf_num(first[0] * scale), pdf_num(first[1] * scale)).as_bytes());
for p in contour.iter().skip(1) {
out.extend_from_slice(format!("{} {} l\n", pdf_num(p[0] * scale), pdf_num(p[1] * scale)).as_bytes());
}
out.extend_from_slice(b"h\n");
}
out.extend_from_slice(b"f\n");
out
}
/// A resource name free in `fonts_res`: `base`, then `base1`, `base2`, … (a page that was
/// OCR'd twice keeps both layers' fonts distinct).
pub(crate) fn unique_font_name(fonts_res: &Dict, base: &str) -> String {
let mut name = String::from(base);
let mut suffix = 0usize;
while fonts_res.contains(name.as_bytes()) {
suffix = suffix.saturating_add(1);
name = format!("{base}{suffix}");
}
name
}
/// The Type3 font dictionary for `(character, CharProc body, advance in em)` glyphs, codes from
/// 1: one CharProc per code, `/Differences` glyph names, real `/Widths`, and a `/ToUnicode` CMap
/// so the text extracts back (this is what makes the output Unicode-correct, not just visible).
pub(crate) fn type3_font_dict(doc: &mut Document, glyphs: &[(char, Vec<u8>, f64)]) -> Result<Dict, EditError> {
let mut charprocs = Dict::new();
let mut differences = vec![Object::Int(1)];
let mut widths = Vec::with_capacity(glyphs.len());
let mut cmap = String::from(
"/CIDInit /ProcSet findresource begin\n12 dict begin\nbegincmap\n/CMapType 2 def\n1 begincodespacerange\n<01> <FF>\nendcodespacerange\n",
);
cmap.push_str(&format!("{} beginbfchar\n", glyphs.len()));
let mut codes = Vec::with_capacity(glyphs.len());
for (i, (ch, path, width)) in glyphs.iter().enumerate() {
let code = u8::try_from(i + 1).map_err(|_| EditError::Invalid("too many unique characters for one font".into()))?;
let glyph_name = format!("g{code:02X}");
let mut pd = Dict::new();
pd.set(b"Length".to_vec(), path.len() as i64);
let proc_ref = doc.add(Object::Stream(Stream::from_raw(pd, path.clone())));
charprocs.set(glyph_name.as_bytes().to_vec(), Object::Ref(proc_ref));
differences.push(Object::name(&glyph_name));
widths.push(Object::Real((width * 1000.0).round()));
cmap.push_str(&format!("<{code:02X}> <{}>\n", unicode_hex(*ch)));
codes.push((*ch, code, *width));
}
cmap.push_str("endbfchar\nendcmap\nCMapName currentdict /CMap defineresource pop\nend\nend\n");
let mut cmap_dict = Dict::new();
cmap_dict.set(b"Length".to_vec(), cmap.len() as i64);
let cmap_ref = doc.add(Object::Stream(Stream::from_raw(cmap_dict, cmap.into_bytes())));
let mut encoding = Dict::new();
encoding.set(b"Type".to_vec(), Object::name("Encoding"));
encoding.set(b"Differences".to_vec(), Object::Array(differences));
let mut font = Dict::new();
font.set(b"Type".to_vec(), Object::name("Font"));
font.set(b"Subtype".to_vec(), Object::name("Type3"));
font.set(b"Name".to_vec(), Object::name("PCFallback"));
font.set(b"FontBBox".to_vec(), Object::Array(vec![Object::Int(0), Object::Int(-300), Object::Int(1000), Object::Int(1000)]));
font.set(
b"FontMatrix".to_vec(),
Object::Array(vec![Object::Real(0.001), Object::Int(0), Object::Int(0), Object::Real(0.001), Object::Int(0), Object::Int(0)]),
);
font.set(b"FirstChar".to_vec(), Object::Int(1));
font.set(b"LastChar".to_vec(), Object::Int(codes.len() as i64));
font.set(b"Widths".to_vec(), Object::Array(widths));
font.set(b"Encoding".to_vec(), Object::Dict(encoding));
font.set(b"CharProcs".to_vec(), Object::Dict(charprocs));
font.set(b"ToUnicode".to_vec(), Object::Ref(cmap_ref));
Ok(font)
}
/// The runs that show `text` in the fallback: consecutive characters in one font form one run, so
/// a font is switched only where the text moves to another font. `None` if a character has no code.
pub(super) fn type3_encode(fallback: &Type3Fallback, text: &str) -> Option<Vec<(String, Vec<u8>)>> {
crates/engine/src/actions.rs
+4 -4
View File
@@ -197,14 +197,14 @@ fn apply_step(s: &mut Session, id: DocId, step: &Step, log: &mut Vec<String>) ->
return Ok(None);
}
};
// Steps that find nothing to do (no comments to flatten, …) aren't failures. A removal step
// that didn't remove is: the file would be passed on as cleaned with the data still in it.
// A step that finds nothing to do is not a failure. Any other error fails the file, so nothing is
// published for it: the file would otherwise be passed on without the step it was asked to apply.
let removes = matches!(step, Step::RemoveHiddenInformation | Step::Sanitize);
match s.apply(id, edit) {
Ok(()) => log.push(step.label().to_string()),
Err(EditError::Redact(pdfcraft_redact::RedactError::NothingToApply)) if removes => log.push(format!("{}: nothing to remove", step.label())),
Err(e) if removes => return Err(e),
Err(e) => log.push(format!("{}: {e}", step.label())),
Err(EditError::Redact(pdfcraft_redact::RedactError::NothingToApply)) => log.push(format!("{}: nothing to do", step.label())),
Err(e) => return Err(e),
}
Ok(None)
}
crates/engine/src/catalog.rs
+1 -1
View File
@@ -267,7 +267,7 @@ pub static TOOL_GROUPS: &[ToolGroup] = &[
item("In multiple files", "files", "ocr.recognize_batch", Ready),
item("Enhance scanned file", "sparkles", "ocr.enhance", Ready),
item("Enhance camera image", "camera", "ocr.enhance_camera", Ready),
item("Correct recognized text", "text-select", "ocr.correct", Planned("M10")),
item("Correct recognized text", "text-select", "ocr.correct", Ready),
],
}],
},
crates/engine/src/commands.rs
+5
View File
@@ -220,6 +220,10 @@ pub const COMMANDS: &[CommandSpec] = &[
// Alt-drag for moving windows (several Linux window managers).
// Copy events stay with the frontend so focused text inputs and page clipboard routing keep ownership.
c("edit.copy", "Copy", EDIT, None, Copying, "copy"),
// Comments travel between documents as XFDF (M14): ⌘C with comments selected copies them,
// ⌘V pastes the copies onto the current page; the strip's Copy/Paste in the menus too.
c("comment.copy", "Copy comments", EDIT, None, Document, "copy"),
c("comment.paste", "Paste comments", EDIT, None, Annotate, "clipboard-paste"),
c("edit.column_select", "Column select", EDIT, None, Document, "text-select"),
c("edit.snapshot", "Take a snapshot", EDIT, None, Copying, "camera"),
c("view.full_screen", "Full screen mode", VIEW, Some(Shortcut::cmd("L")), Document, "maximize"),
@@ -357,6 +361,7 @@ pub const COMMANDS: &[CommandSpec] = &[
c("ocr.enhance_camera", "Enhance camera image", None, None, Modification, "camera"),
c("ocr.enhance", "Enhance scanned file…", None, None, Modification, "sparkles"),
c("ocr.recognize_batch", "Recognize text in multiple files…", None, None, Nothing, "files"),
c("ocr.correct", "Correct recognized text…", None, None, Document, "text-select"),
c("a11y.check", "Check for accessibility…", None, None, Document, "accessibility"),
c("a11y.find_untagged", "Find untagged content", None, None, Document, "search"),
c("a11y.autotag", "Automatically tag PDF", None, None, Document, "tag"),
crates/engine/src/compare.rs
+21 -2
View File
@@ -63,6 +63,15 @@ impl Session {
Ok(pdfcraft_compare::compare(&a.words(), &b.words()))
}
/// [`Session::compare`], keeping the changes on `pages` of `new` (0-based; empty: every page).
pub fn compare_pages(&self, old: DocId, new: DocId, pages: &[usize]) -> Result<Comparison, EditError> {
let mut c = self.compare(old, new)?;
if !pages.is_empty() {
c.changes.retain(|ch| pages.iter().any(|page| (ch.new.page..=ch.new.last_page).contains(page)));
}
Ok(c)
}
/// Visual compare: regions where page n of `new` looks different from page n of `old`
/// (rendered at `dpi`), as (page, user-space box in `new`).
pub fn compare_visual(&self, old: DocId, new: DocId, dpi: f32) -> Result<Vec<(usize, [f64; 4])>, EditError> {
@@ -95,7 +104,12 @@ impl Session {
/// The compare report as a new PDF (not opened).
pub fn compare_report(&self, old: DocId, new: DocId) -> Result<Arc<Vec<u8>>, EditError> {
let c = self.compare(old, new)?;
self.compare_report_of(old, new, &[])
}
/// [`Session::compare_report`] of the changes on `pages` ([`Session::compare_pages`]).
pub fn compare_report_of(&self, old: DocId, new: DocId, pages: &[usize]) -> Result<Arc<Vec<u8>>, EditError> {
let c = self.compare_pages(old, new, pages)?;
let name = |id| self.get(id).map(|d| d.name.clone()).unwrap_or_default();
self.create_report("Compare Report", &pdfcraft_compare::report(&c, &name(old), &name(new)))
}
@@ -104,7 +118,12 @@ impl Session {
/// (blue, green) and a note where text was deleted (red), authored "Compare". One undoable
/// step; returns how many comments were added.
pub fn mark_differences(&mut self, old: DocId, new: DocId) -> Result<usize, EditError> {
let c = self.compare(old, new)?;
self.mark_differences_of(old, new, &[])
}
/// [`Session::mark_differences`] of the changes on `pages` ([`Session::compare_pages`]).
pub fn mark_differences_of(&mut self, old: DocId, new: DocId, pages: &[usize]) -> Result<usize, EditError> {
let c = self.compare_pages(old, new, pages)?;
let mut edits = Vec::new();
for ch in &c.changes {
let color = colour(ch.kind);
crates/engine/src/dates.rs
+12
View File
@@ -582,6 +582,18 @@ pub fn date_language(code: &str) -> Option<&'static DateLanguage> {
DATE_LANGUAGES.iter().find(|l| l.code.eq_ignore_ascii_case(code.trim()))
}
/// Form date fields (`AFDate_FormatEx`, `util.printd`, `util.scand`) write month and weekday
/// names in date language `code` from now on, as a localized Acrobat writes its own language's:
/// `dd-mmm-yy` is `18-ott-26` in Italian (#5303). An unknown code is English.
pub fn use_form_date_language(code: &str) {
let l = date_language(code).unwrap_or(&DATE_LANGUAGES[0]);
let names = pdfcraft_forms::af::DateNames { months: l.months, months_short: l.months_short, days: l.days, days_short: l.days_short };
if pdfcraft_forms::af::date_names() != names {
pdfcraft_forms::af::set_date_names(names);
pdfcraft_js::set_date_names(l.months, l.months_short, l.days, l.days_short);
}
}
/// The characters of `text` that Fill & Sign can't write into a PDF yet, each once. Its text is
/// drawn in Helvetica with WinAnsi encoding (Western European letters), so anything else (`ř`,
/// Japanese, Chinese) would become `?` in the file.
crates/engine/src/document.rs
+1 -1
View File
@@ -539,7 +539,7 @@ impl Document {
_ => "Attachments only",
};
let pending = editor.cos.encryption_changed();
let permissions = if pending { pdfcraft_cos::Permissions { bits: h.permissions().bits, owner: false } } else { h.permissions() };
let permissions = if pending { pdfcraft_cos::Permissions { owner: false, ..h.permissions() } } else { h.permissions() };
Some(SecuritySummary { method: method.into(), owner: h.auth() == pdfcraft_cos::Auth::Owner && !pending, permissions, pending })
}
crates/engine/src/edit.rs
+37 -4
View File
@@ -3,10 +3,11 @@
use std::sync::Arc;
use crate::{
AddedContent, AddedText, Background, BoxSpec, EditError, FieldProps, FieldValue, FillMark, HeaderFooter, Hidden, ImageEdit, InitialView, Label,
LineEnding, LinkAction, LinkStyle, MarkFile, MarkKind, Markup, NewAnnotation, NewField, NoteIcon, ObjectTarget, PageBox, Protection, ReviewState,
Rgb, Shape, Standard, Style, TabOrder, TransitionSpec, Watermark, a11y, copy_image, decode_data_file, embed_image, field_table, fit_picture,
image_content_type, is_xfa_data_file, js, mark_source, measure, model_poster, open_source, strip_xfa, unrestricted, xfa, xfa_after_data_change,
AddedContent, AddedText, Background, BorderShape, BoxSpec, EditError, FieldProps, FieldValue, FillMark, HeaderFooter, Hidden, ImageEdit,
InitialView, Label, LineEnding, LinkAction, LinkStyle, MarkFile, MarkKind, Markup, NewAnnotation, NewField, NoteIcon, ObjectTarget, PageBox,
Protection, ReviewState, Rgb, Shape, Standard, Style, TabOrder, TransitionSpec, Watermark, a11y, copy_image, decode_data_file, embed_image,
field_table, fit_picture, image_content_type, is_xfa_data_file, js, mark_source, measure, model_poster, open_source, strip_xfa, unrestricted,
xfa, xfa_after_data_change,
};
mod labels;
@@ -263,12 +264,35 @@ pub enum Edit {
index: usize,
fill: Option<Rgb>,
},
/// 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), the line or border keeping the comment's; `None` leaves that
/// part as it is. `StyleAnnotation`'s opacity sets the whole comment's.
PartOpacity {
page: usize,
index: usize,
fill: Option<f64>,
text: Option<f64>,
},
/// Change the font size (pt) of a text box, typewriter text or callout.
FontSizeAnnotation {
page: usize,
index: usize,
size: f64,
},
/// Give a text box, typewriter text or callout a border colour of its own (`None`: the
/// text's again).
BorderColorAnnotation {
page: usize,
index: usize,
color: Option<Rgb>,
},
/// Give a text box or typewriter text an oval, a circle or a rectangle for its border: the
/// text box keeps its place, the oval or circle goes around it.
BorderShapeAnnotation {
page: usize,
index: usize,
shape: BorderShape,
},
/// Comment properties ▸ General / note icon.
SetAnnotationInfo {
page: usize,
@@ -561,6 +585,15 @@ pub enum Edit {
name: String,
bytes: Arc<Vec<u8>>,
},
/// Paste copied comments (XFDF from [`Session::export_comments`]) onto `page` as new
/// comments: copies under names of their own, so nothing is replaced and pasting twice
/// gives two sets; replies keep their copied parent.
PasteComments {
xfdf: String,
page: usize,
/// Where the copies go: moved by (dx, dy) in user space, or at their own positions.
offset: Option<[f64; 2]>,
},
/// Remove Hidden Information: the chosen categories.
RemoveHidden {
which: Vec<Hidden>,
crates/engine/src/edit/labels.rs
+9 -3
View File
@@ -71,6 +71,7 @@ pub const EDIT_LABELS: &[&str] = &[
"Add stamp",
"Add 3D model",
"Delete comment",
"Paste comments",
"Edit comment",
"Reply",
"Set status None",
@@ -211,6 +212,7 @@ impl Edit {
Edit::AddCustomStamp { .. } => Label::of("Add stamp"),
Edit::AddModel3d { .. } => Label::of("Add 3D model"),
Edit::DeleteAnnotation { .. } => Label::of("Delete comment"),
Edit::PasteComments { .. } => Label::of("Paste comments"),
Edit::SetAnnotationContents { .. } => Label::of("Edit comment"),
Edit::ReplyToAnnotation { .. } => Label::of("Reply"),
// The state's name is part of the wording: a language may need to agree it with the rest.
@@ -230,9 +232,13 @@ impl Edit {
Edit::MoveAnnotation { .. } => Label::of("Move comment"),
Edit::ReshapeAnnotation { .. } => Label::of("Reshape comment"),
Edit::ResizeAnnotation { .. } => Label::of("Resize comment"),
Edit::StyleAnnotation { .. } | Edit::FillAnnotation { .. } | Edit::FontSizeAnnotation { .. } | Edit::SetAnnotationInfo { .. } => {
Label::of("Change comment properties")
}
Edit::StyleAnnotation { .. }
| Edit::FillAnnotation { .. }
| Edit::PartOpacity { .. }
| Edit::FontSizeAnnotation { .. }
| Edit::BorderColorAnnotation { .. }
| Edit::BorderShapeAnnotation { .. }
| Edit::SetAnnotationInfo { .. } => Label::of("Change comment properties"),
Edit::SetFieldValue { name, .. } => Label::with("Fill in {name}", name.as_str()),
Edit::SetFieldImage { name, .. } => Label::with("Set the image of {name}", name.as_str()),
Edit::ResetForm { .. } => Label::of("Clear form"),
crates/engine/src/edit/run.rs
+16 -1
View File
@@ -49,6 +49,7 @@ pub(crate) fn check_permission(edit: &Edit, p: &pdfcraft_cos::Permissions) -> Re
}
Edit::AddMeasurement(_)
| Edit::AddAnnotation(_)
| Edit::PasteComments { .. }
| Edit::AddCustomStamp { .. }
| Edit::AddModel3d { .. }
| Edit::DeleteAnnotation { .. }
@@ -64,7 +65,10 @@ pub(crate) fn check_permission(edit: &Edit, p: &pdfcraft_cos::Permissions) -> Re
| Edit::ResizeAnnotation { .. }
| Edit::StyleAnnotation { .. }
| Edit::FillAnnotation { .. }
| Edit::PartOpacity { .. }
| Edit::FontSizeAnnotation { .. }
| Edit::BorderColorAnnotation { .. }
| Edit::BorderShapeAnnotation { .. }
| Edit::SetAnnotationInfo { .. }
| Edit::SetMeasurementScale { .. } => {
if p.annotate() {
@@ -495,6 +499,14 @@ pub(crate) fn run_edit(doc: &mut pdfcraft_cos::Document, edit: &Edit, cx: &mut E
Edit::AddAnnotation(a) => {
pdfcraft_annot::add_annotation(doc, a, &cx.meta())?;
}
Edit::PasteComments { xfdf, page, offset } => {
// Names from the edit's own id generator: unique to this paste within the document.
let prefix = cx.meta().id;
let report = pdfcraft_xfdf::import_comments(doc, xfdf, Some(*page), Some(&prefix), *offset)?;
if report.comments == 0 {
return Err(EditError::Invalid("the clipboard holds no comments".into()));
}
}
Edit::AddCustomStamp { page, rect, name, file, author } => {
let src = mark_source(doc, file)?;
let (sw, sh) = (src.size.0.max(1.0), src.size.1.max(1.0));
@@ -575,7 +587,10 @@ pub(crate) fn run_edit(doc: &mut pdfcraft_cos::Document, edit: &Edit, cx: &mut E
)?;
}
Edit::FillAnnotation { page, index, fill } => pdfcraft_annot::set_fill(doc, *page, *index, *fill, &cx.meta())?,
Edit::PartOpacity { page, index, fill, text } => pdfcraft_annot::set_part_opacity(doc, *page, *index, *fill, *text, &cx.meta())?,
Edit::FontSizeAnnotation { page, index, size } => pdfcraft_annot::set_font_size(doc, *page, *index, *size, &cx.meta())?,
Edit::BorderColorAnnotation { page, index, color } => pdfcraft_annot::set_border_color(doc, *page, *index, *color, &cx.meta())?,
Edit::BorderShapeAnnotation { page, index, shape } => pdfcraft_annot::set_border_shape(doc, *page, *index, *shape, &cx.meta())?,
Edit::SetAnnotationInfo { page, index, author, subject, icon } => {
pdfcraft_annot::set_info(doc, *page, *index, author.as_deref(), subject.as_deref(), *icon, &cx.meta())?;
}
@@ -703,7 +718,7 @@ pub(crate) fn run_edit(doc: &mut pdfcraft_cos::Document, edit: &Edit, cx: &mut E
Edit::RemoveStandardId { standard } => pdfcraft_organize::remove_standard_id(doc, *standard)?,
Edit::SetDocumentScript { name, script } => pdfcraft_forms::set_document_script(doc, name, script.as_deref())?,
Edit::AddOcrText { page, words } => {
pdfcraft_edit::stamp(doc, *page, "OCR", pdfcraft_ocr::text_layer(words))?;
crate::ocr::layer::add_text(doc, *page, words)?;
}
Edit::EnhanceScan { images } => crate::scan_clean::write_back(doc, images)?,
Edit::EditPageImage { page, index, change } => run_edit_page_image(doc, *page, *index, change)?,
crates/engine/src/history.rs
+4
View File
@@ -53,6 +53,7 @@ pub(crate) fn scope_of(edit: &Edit) -> Scope {
Edit::AddAnnotation(a) if matches!(a.shape, Shape::Attachment { .. }) => Scope::Full,
Edit::AddMeasurement(_)
| Edit::AddAnnotation(_)
| Edit::PasteComments { .. }
| Edit::AddCustomStamp { .. }
| Edit::AddModel3d { .. }
| Edit::DeleteAnnotation { .. }
@@ -68,7 +69,10 @@ pub(crate) fn scope_of(edit: &Edit) -> Scope {
| Edit::ResizeAnnotation { .. }
| Edit::StyleAnnotation { .. }
| Edit::FillAnnotation { .. }
| Edit::PartOpacity { .. }
| Edit::FontSizeAnnotation { .. }
| Edit::BorderColorAnnotation { .. }
| Edit::BorderShapeAnnotation { .. }
| Edit::SetAnnotationInfo { .. } => Scope::Comments,
Edit::AddLink { .. } | Edit::SetLink { .. } | Edit::DeleteLink { .. } | Edit::RemoveLinks { .. } | Edit::AddLinks { .. } => Scope::Links,
Edit::SetFieldValue { .. } | Edit::ResetForm { .. } | Edit::SetFieldImage { .. } | Edit::ApplyScriptChanges { .. } => Scope::Form,
crates/engine/src/js.rs
+25 -6
View File
@@ -199,6 +199,24 @@ impl Scripts for JsRunner {
/// Run field `target`'s script for `event` over the form's fields, keeping what it showed and
/// asked for; a refusal carries its last message.
fn run(&mut self, event: FieldEvent, script: &str, target: &Field, value: &str, fields: &[Field]) -> ScriptResult {
// As in Acrobat, a failing script leaves the value alone (the error goes to the console).
self.run_logged(event, script, target, value, fields, true).unwrap_or_else(|| ScriptResult {
rc: true,
value: value.to_string(),
changes: Vec::new(),
message: None,
})
}
fn rerun_with_english_dates(&mut self, event: FieldEvent, script: &str, target: &Field, value: &str, fields: &[Field]) -> Option<ScriptResult> {
pdfcraft_js::with_english_printd(true, || self.run_logged(event, script, target, value, fields, false))
}
}
impl JsRunner {
/// [`Scripts::run`], keeping what the script showed and asked for only when `log`; `None`
/// when the script failed.
fn run_logged(&mut self, event: FieldEvent, script: &str, target: &Field, value: &str, fields: &[Field], log: bool) -> Option<ScriptResult> {
let states: Vec<_> = fields
.iter()
.map(|f| {
@@ -212,17 +230,18 @@ impl Scripts for JsRunner {
let states = std::sync::Arc::new(states);
let ev = pdfcraft_js::Event::field(event.name(), &target.name, value);
let o = pdfcraft_js::run_shared(script, &ev, &self.doc, std::sync::Arc::clone(&states), &self.doc_scripts, Limits::default());
self.output.absorb(&o);
if o.error.is_some() {
// As in Acrobat, a failing script leaves the value alone (the error goes to the console).
return ScriptResult { rc: true, value: value.to_string(), changes: Vec::new(), message: None };
if log {
self.output.absorb(&o);
}
ScriptResult {
if o.error.is_some() {
return None;
}
Some(ScriptResult {
rc: o.rc,
value: o.value.clone(),
changes: changes(&states, &o.changed),
message: (!o.rc).then(|| o.alerts.last().map(|m| m.text.clone())).flatten(),
}
})
}
}
crates/engine/src/lib.rs
+3 -2
View File
@@ -115,8 +115,8 @@ pub use pdfcraft_fonts::{MAX_SIGNATURE_CHARS, ScriptOutline, script_missing, scr
pub use pdfcraft_annot::appearance as annot_text;
pub use pdfcraft_annot::links::{Highlight as LinkHighlight, LinkAction, LinkItem, LinkStyle};
pub use pdfcraft_annot::{
Activation3d, AppearanceCache, AttachIcon, FillMark, LineEnding, Markup, NOTE_SIZE, NewAnnotation, NoteIcon, OverlayFont, OverlayLook,
Props as CommentProps, ReviewState, Rgb, Shape, StampGroup, StampKind, Style, rect_quad,
Activation3d, AppearanceCache, AttachIcon, BorderShape, FillMark, LineEnding, Markup, NOTE_SIZE, NewAnnotation, NoteIcon, OverlayFont,
OverlayLook, Props as CommentProps, ReviewState, Rgb, Shape, StampGroup, StampKind, Style, rect_quad,
};
pub use pdfcraft_annot::{MAX_MODEL_BYTES as MAX_3D_MODEL_BYTES, ModelFormat as Model3dFormat};
pub use pdfcraft_forms::detect;
@@ -131,6 +131,7 @@ pub use pdfcraft_redact::sanitize::{HIDDEN, Hidden};
pub use pdfcraft_sign as sign;
pub use pdfcraft_sign::{SignOptions, SignatureInfo, Status as SignatureStatus, TrustStore};
pub use pdfcraft_xfdf::Format as DataFormat;
pub use pdfcraft_xfdf::{Outline as CommentOutline, comment_count, comment_outlines, comments_bounds, is_xfdf_comments};
use bookmarks::outline_rows;
pub use bookmarks::{BookmarkPage, BookmarkRow};
crates/engine/src/ocr.rs
+1741 -68
View File
File diff suppressed because it is too large Load Diff
crates/engine/src/ocr/dictionary.rs
+80
View File
@@ -0,0 +1,80 @@
//! The UI dictionary format: one case-insensitive word per UTF-8 line.
use std::collections::BTreeSet;
pub const MAX_BYTES: usize = 4 * 1024 * 1024;
const MAX_WORDS: usize = 65536;
fn word(value: &str) -> Result<String, String> {
let value = value.trim();
if value.is_empty() || value.len() > 1024 || value.chars().any(char::is_control) {
return Err("dictionary words must be nonempty single lines of at most 1024 bytes".into());
}
let normalized = value.to_lowercase();
if normalized.len() > 1024 {
return Err("normalized dictionary words must be at most 1024 bytes".into());
}
Ok(normalized)
}
pub fn words(text: &str) -> Result<BTreeSet<String>, String> {
if text.len() > MAX_BYTES {
return Err("OCR dictionary exceeds 4 MiB".into());
}
let mut words = BTreeSet::new();
for line in text.lines().filter(|line| !line.trim().is_empty()) {
words.insert(word(line)?);
if words.len() > MAX_WORDS {
return Err("OCR dictionary exceeds 65536 words".into());
}
}
Ok(words)
}
/// Normalize, update and bound the complete dictionary before the caller writes it.
pub fn update(text: &str, add: &[&str], remove: &[&str]) -> Result<String, String> {
if add.len() > MAX_WORDS || remove.len() > MAX_WORDS {
return Err("OCR dictionary exceeds 65536 words".into());
}
let mut entries = words(text)?;
for value in remove {
entries.remove(&word(value)?);
}
for value in add {
entries.insert(word(value)?);
if entries.len() > MAX_WORDS {
return Err("OCR dictionary exceeds 65536 words".into());
}
}
let mut out = String::new();
for entry in entries {
if out.len().checked_add(entry.len()).and_then(|n| n.checked_add(1)).is_none_or(|n| n > MAX_BYTES) {
return Err("OCR dictionary exceeds 4 MiB".into());
}
out.push_str(&entry);
out.push('\n');
}
Ok(out)
}
#[cfg(test)]
mod tests {
use super::*;
#[test]
fn dictionary_updates_round_trip_and_refuse_expanding_normalization() {
let text = update("Quartz\n日本語\n", &["QUARTZ", "extra"], &["日本語"]).unwrap();
assert_eq!(text, "extra\nquartz\n");
assert_eq!(words(&text).unwrap(), BTreeSet::from(["extra".into(), "quartz".into()]));
assert!(update("original\n", &[&"İ".repeat(512)], &[]).unwrap_err().contains("normalized"));
assert!(update("original\n", &["two\nlines"], &[]).is_err());
}
#[test]
fn dictionary_limits_cover_existing_and_added_entries() {
let full: String = (0..65536).map(|i| format!("word{i}\n")).collect();
assert_eq!(words(&full).unwrap().len(), 65536);
assert!(update(&full, &["extra"], &[]).is_err());
assert_eq!(update(&full, &["extra"], &["word0"]).unwrap().lines().count(), 65536);
assert!(words(&"a".repeat(MAX_BYTES + 1)).is_err());
}
}
crates/engine/src/ocr/layer.rs
+145
View File
@@ -0,0 +1,145 @@
//! Unicode search text has no visible glyphs. A generated Type 3 font supplies advance widths
//! and a ToUnicode map, with empty character programs; no display font is needed or embedded.
//! Adapted from the searchable-layer implementation in #433 (32e09fbe).
use std::collections::BTreeMap;
use pdfcraft_cos::{Dict, Document, Object, Stream};
use pdfcraft_edit::EditError;
use pdfcraft_ocr::PlacedWord;
/// Refuse oversized text or invalid geometry before cloning words or allocating fonts.
/// These limits apply to the complete input, including all editable export pages.
pub(crate) fn validate_words<'a>(words: impl IntoIterator<Item = &'a PlacedWord>) -> Result<usize, EditError> {
let mut count = 0usize;
let mut length = 0usize;
for w in words {
count += 1;
length = length.checked_add(w.text.len()).ok_or_else(|| EditError::Invalid("OCR text layer is too large".into()))?;
if count > 65536 || length > 4 * 1024 * 1024 {
return Err(EditError::Invalid("OCR text layer is too large".into()));
}
if !w.origin.iter().chain(&w.across).chain(&w.up).all(|v| v.is_finite())
|| !w.across[0].hypot(w.across[1]).is_finite()
|| !w.up[0].hypot(w.up[1]).is_finite()
|| (0..2).any(|i| !(w.origin[i] + 0.2 * w.up[i]).is_finite() || !(w.origin[i] + w.across[i] + 0.2 * w.up[i]).is_finite())
{
return Err(EditError::Invalid("OCR text coordinates must be finite".into()));
}
}
Ok(count)
}
pub(crate) fn add_text(doc: &mut Document, page: usize, words: &[PlacedWord]) -> Result<(), EditError> {
validate_words(words)?;
// Keep the existing Latin layout, including Helvetica's proportional advance widths.
if words.iter().all(|w| {
w.text
.chars()
.all(|c| matches!(c, '\u{20}'..='\u{7e}' | '\u{a0}'..='\u{ff}' | '€' | '‚' | '„' | '…' | '‘' | '’' | '“' | '”' | '•' | '–' | '—' | '™'))
}) {
pdfcraft_edit::stamp(doc, page, "OCR", pdfcraft_ocr::text_layer(words, &pdfcraft_fonts::TextPlan::default()))?;
return Ok(());
}
let p = pdfcraft_model::pages(doc).get(page).cloned().ok_or_else(|| EditError::Invalid("OCR page does not exist".into()))?;
let mut res = p.dict.get(b"Resources").map(|r| doc.resolve(r)).and_then(|r| r.as_dict().cloned()).unwrap_or_default();
let mut fonts = res.get(b"Font").map(|f| doc.resolve(f)).and_then(|f| f.as_dict().cloned()).unwrap_or_default();
let chars: Vec<char> = words.iter().flat_map(|w| w.text.chars()).collect::<std::collections::BTreeSet<_>>().into_iter().collect();
// Match the extractor's em box (-200..800). Baselines below are offset by 0.2 em,
// so search/selection rectangles span the detected image box.
let blank = doc.add(Object::Stream(Stream::from_raw(Dict::new(), b"1000 0 0 -200 1000 800 d1\n".to_vec())));
let mut codes = BTreeMap::new();
let mut names = Vec::new();
for (index, chunk) in chars.chunks(255).enumerate() {
let mut name = format!("PCOcr{index}");
while fonts.contains(name.as_bytes()) {
name.push('x');
}
let mut differences = vec![Object::Int(1)];
let mut procs = Dict::new();
let mut cmap = String::from(
"/CIDInit /ProcSet findresource begin\n12 dict begin\nbegincmap\n/CIDSystemInfo << /Registry (PdfCraft) /Ordering (Unicode) /Supplement 0 >> def\n/CMapName /PdfCraftOCR def\n/CMapType 2 def\n1 begincodespacerange\n<01> <FF>\nendcodespacerange\n",
);
for (batch, part) in chunk.chunks(100).enumerate() {
cmap.push_str(&format!("{} beginbfchar\n", part.len()));
for (i, ch) in part.iter().enumerate() {
let code = (batch * 100 + i + 1) as u8;
let glyph = format!("g{code:02X}");
differences.push(Object::name(&glyph));
procs.set(glyph.into_bytes(), Object::Ref(blank));
let mut units = [0u16; 2];
let hex: String = ch.encode_utf16(&mut units).iter().map(|u| format!("{u:04X}")).collect();
cmap.push_str(&format!("<{code:02X}> <{hex}>\n"));
codes.insert(*ch, (index, code));
}
cmap.push_str("endbfchar\n");
}
cmap.push_str("endcmap\nCMapName currentdict /CMap defineresource pop\nend\nend\n");
let map = doc.add(Object::Stream(Stream::flate(Dict::new(), cmap.as_bytes())));
let mut encoding = Dict::new();
encoding.set(b"Type".to_vec(), Object::name("Encoding"));
encoding.set(b"Differences".to_vec(), Object::Array(differences));
let mut font = Dict::new();
font.set(b"Type".to_vec(), Object::name("Font"));
font.set(b"Subtype".to_vec(), Object::name("Type3"));
font.set(b"FontBBox".to_vec(), Object::Array(vec![0.into(), (-200).into(), 1000.into(), 800.into()]));
font.set(b"FontMatrix".to_vec(), Object::Array(vec![Object::Real(0.001), 0.into(), 0.into(), Object::Real(0.001), 0.into(), 0.into()]));
font.set(b"FirstChar".to_vec(), Object::Int(1));
font.set(b"LastChar".to_vec(), Object::Int(chunk.len() as i64));
font.set(b"Widths".to_vec(), Object::Array(vec![Object::Int(1000); chunk.len()]));
font.set(b"Encoding".to_vec(), Object::Dict(encoding));
font.set(b"CharProcs".to_vec(), Object::Dict(procs));
font.set(b"Resources".to_vec(), Object::Dict(Dict::new()));
font.set(b"ToUnicode".to_vec(), Object::Ref(map));
fonts.set(name.as_bytes().to_vec(), Object::Ref(doc.add(Object::Dict(font))));
names.push(name);
}
res.set(b"Font".to_vec(), Object::Dict(fonts));
doc.update_dict(p.obj, |d| d.set(b"Resources".to_vec(), Object::Dict(res)))?;
// `3 Tr` and the font are graphics state, which `ET` doesn't reset: like
// `pdfcraft_ocr::text_layer` (#3029), the text is drawn inside `q … Q` so the invisible
// rendering mode cannot leak into later content streams on the page.
let mut content = String::from("/OCR BMC\nq\nBT\n3 Tr\n");
for w in words {
let count = w.text.chars().count();
if count == 0 || w.up[0].hypot(w.up[1]) <= 0.0 || w.across[0].hypot(w.across[1]) <= 0.0 {
continue;
}
let mut start = 0;
let mut run = Vec::new();
let mut font_index = None;
let emit = |content: &mut String, font: usize, start: usize, run: &[u8]| {
let n = count as f64;
let at = start as f64 / n;
let hex: String = run.iter().map(|b| format!("{b:02X}")).collect();
content.push_str(&format!(
"/{} 1 Tf\n{} {} {} {} {} {} Tm <{hex}> Tj\n",
names[font],
w.across[0] / n,
w.across[1] / n,
w.up[0],
w.up[1],
w.origin[0] + at * w.across[0] + 0.2 * w.up[0],
w.origin[1] + at * w.across[1] + 0.2 * w.up[1]
));
};
for (i, ch) in w.text.chars().enumerate() {
let Some(&(font, code)) = codes.get(&ch) else { continue };
if let Some(previous) = font_index
&& previous != font
{
emit(&mut content, previous, start, &run);
run.clear();
start = i;
}
font_index = Some(font);
run.push(code);
}
if let Some(font) = font_index {
emit(&mut content, font, start, &run);
}
}
content.push_str("ET\nQ\nEMC\n");
pdfcraft_edit::stamp(doc, page, "OCR", content.into_bytes())?;
Ok(())
}
crates/engine/src/scan_fields.rs
+6 -2
View File
@@ -186,10 +186,14 @@ impl Session {
if !ocr::available() {
return Vec::new();
}
let (Ok(engine), Some(job)) = (ocr::engine(), self.ocr_job(id, &[page], ocr::OcrSettings::default())) else {
let settings = ocr::OcrSettings::default();
let Some(job) = self.ocr_job(id, &[page], settings.clone()) else {
return Vec::new();
};
job.run(&engine, |_, _| true)
let Ok(recognizers) = ocr::recognizers(&settings) else {
return Vec::new();
};
job.run(&recognizers, |_, _| true)
.into_iter()
.flat_map(|p| p.words)
.filter_map(|w| {
crates/engine/src/session/files.rs
+14 -1
View File
@@ -114,6 +114,19 @@ impl Session {
.map_err(EditError::Write)
}
/// XFDF with these comments (0-based page, position in the page's `/Annots`) and their
/// replies: what Copy puts on the clipboard; [`Edit::PasteComments`] takes it back in.
pub fn export_comments(&self, id: DocId, which: &[(usize, usize)]) -> Result<String, EditError> {
let doc = self.get(id).ok_or(EditError::NoDocument)?;
let cos = match doc.editor.as_ref() {
Some(e) => e.cos.clone(),
None => {
pdfcraft_cos::Document::open_with_password(doc.bytes.clone(), doc.password.as_deref()).map_err(|e| EditError::Write(e.to_string()))?
}
};
guard(|| pdfcraft_xfdf::export_xfdf_comments(&cos, which, &doc.name)).map_err(EditError::Write)
}
/// The print-ready PDF for `settings` (sheets laid out for the paper; see `pdfcraft-print`).
pub fn print_pdf(&self, id: DocId, settings: &print::Settings) -> Result<Vec<u8>, EditError> {
let doc = self.get(id).ok_or(EditError::NoDocument)?;
@@ -384,7 +397,7 @@ impl Session {
/// A new file (Combine, Extract, Split, Create) as bytes, checked like a save before anyone
/// writes it (#1698, #2166): it reopens, and shows the pages it was built from.
fn write_new(&self, doc: &pdfcraft_cos::Document) -> Result<Arc<Vec<u8>>, EditError> {
pub(crate) fn write_new(&self, doc: &pdfcraft_cos::Document) -> Result<Arc<Vec<u8>>, EditError> {
let bytes = self.write_unchecked(doc)?;
let expected = pdfcraft_organize::page_count(doc)?;
pdfcraft_cos::Document::open(bytes.clone()).map_err(|e| EditError::Reopen(e.to_string()))?;
crates/engine/src/tests.rs
+52 -9
View File
@@ -623,12 +623,12 @@ fn a_3d_model_needs_the_comments_permission_and_changes_the_comments() {
activation: Activation3d::default(),
name: String::new(),
};
let p = pdfcraft_cos::Permissions { bits: 0, owner: false };
let p = pdfcraft_cos::Permissions { bits: 0, owner: false, revision: 3 };
assert_eq!(check_permission(&edit, &p), Err(EditError::NotPermitted("comments")));
assert_eq!(crate::history::scope_of(&edit), crate::history::Scope::Comments);
}
fn page_texts(s: &Session, id: DocId) -> Vec<String> {
pub(crate) fn page_texts(s: &Session, id: DocId) -> Vec<String> {
let doc = s.get(id).unwrap();
let config = pdfcraft_render::RenderConfig { password: doc.password.as_deref().map(Arc::from), ..Default::default() };
let mut r = pdfcraft_render::PageRenderer::new(doc.bytes.clone(), config);
@@ -2211,7 +2211,7 @@ fn rect_comment(page: usize, rect: [f64; 4]) -> Edit {
Edit::AddAnnotation(NewAnnotation {
page,
shape: Shape::Rectangle { rect },
style: Style { color: [1.0, 0.0, 0.0], opacity: 1.0, width: 2.0, fill: Some([1.0, 0.0, 0.0]) },
style: Style { color: [1.0, 0.0, 0.0], opacity: 1.0, width: 2.0, fill: Some([1.0, 0.0, 0.0]), ..Style::default() },
contents: "Look here".into(),
author: "Reviewer".into(),
})
@@ -5841,6 +5841,10 @@ fn comparing_two_versions_of_a_document() {
let got: Vec<(compare::Kind, &str, &str)> = c.changes.iter().map(|x| (x.kind, x.old.text.as_str(), x.new.text.as_str())).collect();
assert_eq!(got, [(compare::Kind::Replaced, "Monday.", "Tuesday."), (compare::Kind::Replaced, "days.", "days of invoice.")], "{got:?}");
assert!(s.compare(old, old).unwrap().identical());
// limited to pages of the new file: both changes are on the first
assert_eq!(s.compare_pages(old, new, &[]).unwrap().changes.len(), 2);
assert_eq!(s.compare_pages(old, new, &[0]).unwrap().changes.len(), 2);
assert!(s.compare_pages(old, new, &[1]).unwrap().identical());
let report = s.compare_report(old, new).unwrap();
let rid = s.open("report.pdf", None, report, None).unwrap();
@@ -6048,7 +6052,7 @@ fn measurement_edits_are_transactional_and_honour_annotation_permissions() {
assert!(session.get(id).unwrap().measurements().unwrap().measurements.is_empty());
session.redo(id).unwrap();
assert_eq!(session.get(id).unwrap().bytes, before);
let p = pdfcraft_cos::Permissions { bits: 0, owner: false };
let p = pdfcraft_cos::Permissions { bits: 0, owner: false, revision: 3 };
assert_eq!(check_permission(&Edit::AddMeasurement(m), &p), Err(EditError::NotPermitted("comments")));
assert_eq!(
check_permission(
@@ -7322,12 +7326,13 @@ fn datasets_streams(bytes: &Arc<Vec<u8>>) -> usize {
/// and noted.
#[test]
fn hostile_xfa_open_scripts_are_merged_capped_kept_from_printing_and_noted() {
// On open: a calculate setting its own value 50 000 times, an initialize script showing a
// thousand messages and asking to print, open a link and save.
// On open: a calculate setting its own value 20 000 times (50 000 sat right at the 1 s
// unasked-script timeout and abandoned whenever the test machine was loaded), an
// initialize script showing a thousand messages and asking to print, open a link and save.
let tpl = pdfcraft_xfa::fixtures::scripted_template()
.replace(
r#"<calculate><script contentType="application/x-javascript">qty.rawValue * price.rawValue</script></calculate>"#,
r#"<calculate><script contentType="application/x-javascript">for (var i = 0; i &lt; 50000; i++) this.rawValue = i;</script></calculate>"#,
r#"<calculate><script contentType="application/x-javascript">for (var i = 0; i &lt; 20000; i++) this.rawValue = i;</script></calculate>"#,
)
.replace(
r#"if (qty.rawValue === null) qty.rawValue = 2;"#,
@@ -7337,9 +7342,11 @@ fn hostile_xfa_open_scripts_are_merged_capped_kept_from_printing_and_noted() {
let mut s = Session::new().with_clock(|| 1_700_000_000);
let started = std::time::Instant::now();
let id = s.open("hostile.pdf", None, bytes, None).expect("opens");
assert!(started.elapsed() < std::time::Duration::from_secs(5), "{:?}", started.elapsed());
// 30 s and not 5 s: the run is wall-clock timed and a loaded test machine (all suites in
// parallel) can take several seconds for the 20 000 iterations; a real hang still fails.
assert!(started.elapsed() < std::time::Duration::from_secs(30), "{:?}", started.elapsed());
let doc = s.get(id).unwrap();
assert_eq!(doc.form.iter().find(|f| f.name == "total").unwrap().value, vec!["49999".to_string()]);
assert_eq!(doc.form.iter().find(|f| f.name == "total").unwrap().value, vec!["19999".to_string()]);
// One datasets stream for the scripts' revision, not one per value set.
assert!(datasets_streams(&doc.bytes) <= 3, "{} datasets streams", datasets_streams(&doc.bytes));
// What opening changed is noted with the form's other XFA notes.
@@ -10185,6 +10192,42 @@ fn need_appearances_buttons_are_displayed_from_their_captions() {
}
}
/// Copy and paste: the copies of a comment and its reply land on the asked-for page of another
/// document under names of their own (nothing replaced; a second paste gives a second set),
/// undo takes a paste away as one step, and a clipboard without comments is refused.
#[test]
fn pasting_copied_comments_adds_copies_that_undo_as_one_step() {
let (mut s, id) = session_with(2);
s.apply(id, rect_comment(1, [80.0, 80.0, 120.0, 120.0])).unwrap();
s.apply(id, Edit::ReplyToAnnotation { page: 1, index: 0, text: "Done".into(), author: "Ada".into() }).unwrap();
let xfdf = s.export_comments(id, &[(1, 0)]).unwrap();
assert!(xfdf.contains("<square") && xfdf.contains("inreplyto="), "{xfdf}");
let other = s.open("other.pdf", None, Arc::new(fixture(2)), None).expect("opens");
s.apply(other, Edit::PasteComments { xfdf: xfdf.clone(), page: 0, offset: None }).unwrap();
let a = s.get(other).unwrap().info.annotations.clone();
assert_eq!(a.len(), 2, "{a:?}");
assert!(a.iter().all(|x| x.page == 0), "on the asked-for page: {a:?}");
let parent = a.iter().find(|x| x.in_reply_to.is_none()).unwrap();
let reply = a.iter().find(|x| x.in_reply_to.is_some()).unwrap();
assert_eq!(reply.in_reply_to, parent.name, "the reply follows its copied parent");
assert_ne!(parent.name, s.get(id).unwrap().info.annotations[0].name, "a name of its own");
assert_eq!(parent.contents.as_deref(), Some("Look here"));
assert_eq!(s.get(other).unwrap().can_undo(), Some("Paste comments"));
s.apply(other, Edit::PasteComments { xfdf: xfdf.clone(), page: 1, offset: Some([30.0, -10.0]) }).unwrap();
let a = s.get(other).unwrap().info.annotations.clone();
assert_eq!(a.len(), 4, "a second set");
let placed = a.iter().find(|x| x.page == 1 && x.in_reply_to.is_none()).unwrap();
assert!((placed.rect[0] - 110.0).abs() < 0.5 && (placed.rect[1] - 70.0).abs() < 0.5, "moved by the offset: {:?}", placed.rect);
assert_eq!(comment_count(&xfdf), 1);
assert_eq!(comments_bounds(&xfdf).map(|b| b.map(|v| v.round())), Some([80.0, 80.0, 120.0, 120.0]));
s.undo(other).unwrap();
assert_eq!(s.get(other).unwrap().info.annotations.len(), 2);
assert!(s.apply(other, Edit::PasteComments { xfdf: "hello".into(), page: 0, offset: None }).is_err(), "no comments in it");
assert!(s.apply(other, Edit::PasteComments { xfdf, page: 9, offset: None }).is_err(), "no such page");
assert_eq!(s.get(other).unwrap().info.annotations.len(), 2, "a refused paste changes nothing");
assert_eq!(s.get(id).unwrap().info.annotations.len(), 2, "the source is untouched");
}
#[test]
fn repeated_backdrop_artwork_survives_background_undo_redo_and_both_save_modes() {
let white = "1 g";
crates/engine/tests/form_date_language.rs
+453
View File
@@ -0,0 +1,453 @@
//! Form date fields name months in the app's date language (#5303). Its own test binary: the
//! names are process-wide, so other tests must not see them change, and its tests take turns.
use std::sync::{Arc, Mutex, MutexGuard, PoisonError};
use pdfcraft_cos::{Document, Object};
use pdfcraft_engine::dates::use_form_date_language;
use pdfcraft_engine::js::JsRunner;
use pdfcraft_forms::FieldValue;
use pdfcraft_forms::af::{DateTime, Format, format_date, format_value, keystroke, parse_date};
use pdfcraft_js::{DocInfo, Event, Limits, run};
/// Held by each test while it changes the process-wide date names, which start as English (a
/// failed test may have left others).
fn names_lock() -> MutexGuard<'static, ()> {
static LOCK: Mutex<()> = Mutex::new(());
let lock = LOCK.lock().unwrap_or_else(PoisonError::into_inner);
use_form_date_language("en");
lock
}
/// `util.printd(fmt)` of 18 October 2026, then of what `util.scand(fmt, typed)` reads.
fn printd(fmt: &str, typed: &str) -> String {
let doc = DocInfo { file_name: "form.pdf".into(), num_pages: 1, page: 0, info: Vec::new(), xfa: false };
let script = format!("event.value = util.printd('{fmt}', new Date(2026, 9, 18)) + '|' + util.printd('{fmt}', util.scand('{fmt}', '{typed}'));");
let o = run(&script, &Event::field("Format", "date", ""), &doc, &[], &[], Limits::default());
assert_eq!(o.error, None);
o.value
}
#[test]
fn form_dates_follow_the_date_language() {
let _names = names_lock();
let oct18 = DateTime { y: 2026, m: 10, d: 18, hh: 0, mm: 0, ss: 0 };
let dd_mmm_yy = Format::Date("dd-mmm-yy".into());
// English until the app says otherwise.
assert_eq!(format_date(oct18, "dd-mmm-yy dddd ddd mmmm"), "18-Oct-26 Sunday Sun October");
use_form_date_language("it");
// AFDate_FormatEx("dd-mmm-yy"), what the issue's form used.
assert_eq!(format_value(&dd_mmm_yy, "18-10-26"), "18-ott-26");
assert_eq!(format_date(oct18, "dddd d mmmm yyyy, ddd"), "domenica 18 ottobre 2026, dom");
// What it writes reads back, and so does English typing.
assert_eq!(parse_date("18-ott-26", "dd-mmm-yy"), Some(oct18));
assert_eq!(parse_date("18 ottobre 2026", "dd mmmm yyyy"), Some(oct18));
assert_eq!(parse_date("18-Oct-26", "dd-mmm-yy"), Some(oct18));
assert!(keystroke(&dd_mmm_yy, "date", "18-ott-26").is_ok());
// util.printd writes Italian names; util.scand reads them.
assert_eq!(printd("dd-mmm-yy", "18-ott-26"), "18-ott-26|18-ott-26");
assert_eq!(printd("dd-mmm-yy", "18-Oct-26"), "18-ott-26|18-ott-26", "English typing reads too");
assert_eq!(printd("dddd d mmmm yyyy", "domenica 18 ottobre 2026"), "domenica 18 ottobre 2026|domenica 18 ottobre 2026");
// German short names end in a dot; they are written and read whole.
use_form_date_language("de");
assert_eq!(format_value(&dd_mmm_yy, "18-10-26"), "18-Okt.-26");
assert_eq!(parse_date("18-Okt.-26", "dd-mmm-yy"), Some(oct18));
// An unknown language is English again.
use_form_date_language("xx");
assert_eq!(format_value(&dd_mmm_yy, "18-10-26"), "18-Oct-26");
assert_eq!(printd("dd-mmm-yy", "18-Oct-26"), "18-Oct-26|18-Oct-26");
every_date_language_reads_back_what_it_writes();
// Hostile typing never panics and stays quick: long, odd and mixed-script text.
use_form_date_language("th");
let junk = ["", " ", "ม.", "ม.ค.ม.ค.ม.ค.", "\u{0}", "1月1月1月", "tháng tháng", "Ottobre", "🙂ott🙂", "İstanbul ott 26"];
for t in junk.iter().map(|s| s.to_string()).chain(["ม.ค.1".repeat(5000), "9".repeat(100_000)]) {
let started = std::time::Instant::now();
let _ = parse_date(&t, "dd-mmm-yy");
let _ = keystroke(&dd_mmm_yy, "date", &t);
assert!(started.elapsed() < std::time::Duration::from_secs(2), "{} chars took {:?}", t.len(), started.elapsed());
}
use_form_date_language("en");
}
/// An English weekday typed before the month fills the format's weekday, so a month name that
/// the date language shares with a weekday (Italian, Spanish, Romanian and Albanian "mar") is
/// still read as the month: "Tue 17 Mar 2026" read as "Tue 17 Tuesday 2026" (#5303).
#[test]
fn an_english_weekday_before_a_shared_month_name_reads_as_english() {
let _names = names_lock();
let doc = DocInfo { file_name: "form.pdf".into(), num_pages: 1, page: 0, info: Vec::new(), xfa: false };
let mar17 = DateTime { y: 2026, m: 3, d: 17, hh: 0, mm: 0, ss: 0 };
let mut bad = Vec::new();
for language in ["it", "es", "ro", "sq"] {
use_form_date_language(language);
let ddd_d_mmm = "ddd d mmm yyyy";
let typed = [
// What the language writes, then English, then English and localized mixed.
(ddd_d_mmm, format_date(mar17, ddd_d_mmm)),
(ddd_d_mmm, "Tue 17 Mar 2026".into()),
(ddd_d_mmm, "Tuesday 17 Mar 2026".into()),
(ddd_d_mmm, "tue 17 mar 2026".into()),
(ddd_d_mmm, format!("Tue 17 {}", format_date(mar17, "mmm yyyy"))),
(ddd_d_mmm, format!("{} 17 Mar 2026", format_date(mar17, "ddd"))),
("mmm d yyyy ddd", "Mar 17 2026 Tue".into()),
("dddd d mmmm yyyy", "Tuesday 17 March 2026".into()),
];
for (fmt, text) in typed {
if parse_date(&text, fmt) != Some(mar17) {
bad.push(format!("{language} forms {fmt}: {text:?} -> {:?}", parse_date(&text, fmt)));
}
let script = format!("var d = util.scand('{fmt}', {text:?}); event.value = d ? util.printd('yyyy-mm-dd', d) : 'null';");
let o = run(&script, &Event::field("Format", "date", ""), &doc, &[], &[], Limits::default());
if o.value != "2026-03-17" {
bad.push(format!("{language} scand {fmt}: {text:?} -> {:?} {:?}", o.value, o.error));
}
}
}
use_form_date_language("en");
assert!(bad.is_empty(), "{}", bad.join("; "));
}
/// Every date language: what a date field writes reads back as the same date, for each date
/// letter that writes a name, through the form path and through `util.scand`. Called from the
/// one test, which owns the process-wide names.
fn every_date_language_reads_back_what_it_writes() {
let doc = DocInfo { file_name: "form.pdf".into(), num_pages: 1, page: 0, info: Vec::new(), xfa: false };
let mut bad = Vec::new();
for l in pdfcraft_engine::dates::DATE_LANGUAGES.iter() {
use_form_date_language(l.code);
for m in 1..=12u32 {
let dt = DateTime { y: 2026, m, d: 18, hh: 0, mm: 0, ss: 0 };
for fmt in ["dd-mmm-yy", "d mmmm yyyy", "dddd, mmmm d, yyyy", "ddd d mmm yyyy", "mmm d, yyyy ddd", "yyyymmmdd"] {
let text = format_date(dt, fmt);
// A short month ending in a number ("Thg 1") glued to the day is ambiguous
// ("Thg 118": January 18 or November 8): nothing can read it back.
if fmt == "yyyymmmdd" && l.months_short.iter().any(|n| n.ends_with(|c: char| c.is_ascii_digit())) {
continue;
}
if parse_date(&text, fmt).map(|p| (p.y, p.m, p.d)) != Some((2026, m, 18)) {
bad.push(format!("{} forms {fmt}: {text:?}", l.code));
}
let script = format!("var d = util.scand('{fmt}', {text:?}); event.value = d ? util.printd('yyyy-mm-dd', d) : 'null';");
let o = run(&script, &Event::field("Format", "date", ""), &doc, &[], &[], Limits::default());
if o.value != format!("2026-{m:02}-18") {
bad.push(format!("{} scand {fmt}: {text:?} -> {:?} {:?}", l.code, o.value, o.error));
}
}
}
}
use_form_date_language("en");
assert!(bad.is_empty(), "{} failures:\n{}", bad.len(), bad.iter().take(40).cloned().collect::<Vec<_>>().join("\n"));
}
/// A form whose text fields are each `(name, font, format script)`: `/Helv` is Helvetica with
/// WinAnsi, `/Song` a Chinese font with a Unicode CMap, which also holds Cyrillic.
fn form(fields: &[(&str, &str, &str)]) -> Document {
let n = fields.len();
let first = 6;
let refs = |from: usize| (from..from + n).map(|i| format!("{i} 0 R")).collect::<Vec<_>>().join(" ");
let mut objs: Vec<String> = vec![
"<< /Type /Catalog /Pages 2 0 R /AcroForm 4 0 R >>".into(),
"<< /Type /Pages /Kids [3 0 R] /Count 1 /MediaBox [0 0 600 800] >>".into(),
format!("<< /Type /Page /Parent 2 0 R /Annots [{}] >>", refs(first)),
format!("<< /Fields [{}] /DA (/Helv 0 Tf 0 g) /DR << /Font << /Helv 5 0 R /Song {} 0 R >> >> >>", refs(first), first + n),
"<< /Type /Font /Subtype /Type1 /BaseFont /Helvetica /Encoding /WinAnsiEncoding >>".into(),
];
for (i, (name, font, js)) in fields.iter().enumerate() {
let js = js.replace('\\', "\\\\").replace('(', "\\(").replace(')', "\\)");
let y = 700 - 30 * i;
objs.push(format!(
"<< /Type /Annot /Subtype /Widget /FT /Tx /T ({name}) /DA (/{font} 10 Tf 0 g) /Rect [50 {y} 300 {}] /P 3 0 R /AA << /F << /S /JavaScript /JS ({js}) >> >> >>",
y + 20
));
}
objs.push("<< /Type /Font /Subtype /Type0 /BaseFont /STSong-Light /Encoding /UniGB-UCS2-H /DescendantFonts [<< /Type /Font /Subtype /CIDFontType0 /BaseFont /STSong-Light /CIDSystemInfo << /Registry (Adobe) /Ordering (GB1) /Supplement 4 >> >>] >>".into());
let mut out = b"%PDF-1.7
"
.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
{o}
endobj
",
i + 1
)
.as_bytes(),
);
}
let xref = out.len();
out.extend_from_slice(
format!(
"xref
0 {}
0000000000 65535 f
",
objs.len() + 1
)
.as_bytes(),
);
for o in offsets {
out.extend_from_slice(
format!(
"{o:010} 00000 n
"
)
.as_bytes(),
);
}
out.extend_from_slice(
format!(
"trailer
<< /Size {} /Root 1 0 R >>
startxref
{xref}
%%EOF
",
objs.len() + 1
)
.as_bytes(),
);
Document::open(Arc::new(out)).expect("opens")
}
/// The content of field `name`'s normal appearance.
fn appearance(doc: &Document, name: &str) -> Vec<u8> {
let all = pdfcraft_forms::fields(doc);
let f = all.iter().find(|f| f.name == name).expect("field");
let widget = doc.get(f.widgets[0].obj);
let normal = widget.as_dict().and_then(|d| d.get(b"AP")).and_then(|a| doc.resolve(a).as_dict().and_then(|a| a.reference(b"N"))).expect("/AP /N");
match &*doc.get(normal) {
Object::Stream(s) => s.decoded().expect("decodes"),
other => panic!("not a stream: {other:?}"),
}
}
/// What a Unicode-CMap (UCS-2) font is given for `text`.
fn ucs2(text: &str) -> Vec<u8> {
text.encode_utf16().flat_map(u16::to_be_bytes).collect()
}
fn contains(hay: &[u8], needle: &[u8]) -> bool {
hay.windows(needle.len()).any(|w| w == needle)
}
/// Fills `form`'s field `name` with 18 October 2026 through the JavaScript runner.
fn fill(doc: &mut Document, name: &str) {
fill_with(doc, name, "18-10-26");
}
/// Fills `form`'s field `name` with `value` through the JavaScript runner.
fn fill_with(doc: &mut Document, name: &str, value: &str) {
let mut js = JsRunner::new(doc, "form.pdf");
pdfcraft_forms::set_value_with(doc, name, &FieldValue::Text(value.into()), &mut js).expect("fills");
}
/// Month names in the date language that no font of the field can draw are drawn in English,
/// never as `?` ("18-????.-26" in Russian); a font that holds them keeps them (#5303).
#[test]
fn date_names_no_field_font_can_draw_are_drawn_in_english() {
let _names = names_lock();
let date = "AFDate_FormatEx(\"dd-mmm-yy\");";
let fields = [("helv", "Helv", date), ("song", "Song", date)];
for (language, local) in [("ru", "окт."), ("cs", "říj"), ("ja", "10月"), ("el", "Οκτ")] {
use_form_date_language(language);
let mut doc = form(&fields);
fill(&mut doc, "helv");
fill(&mut doc, "song");
let helv = appearance(&doc, "helv");
assert!(contains(&helv, b"(18-Oct-26) Tj"), "{language}: {}", String::from_utf8_lossy(&helv));
assert!(!helv.contains(&b'?'), "{language}: {}", String::from_utf8_lossy(&helv));
assert!(pdfcraft_forms::undrawn_fields(&doc).is_empty(), "{language}");
let song = appearance(&doc, "song");
assert!(contains(&song, &ucs2(&format!("18-{local}-26"))), "{language} keeps its name: {song:?}");
}
// Names Helvetica holds are kept: Italian "ott".
use_form_date_language("it");
let mut doc = form(&fields);
fill(&mut doc, "helv");
assert!(contains(&appearance(&doc, "helv"), b"(18-ott-26) Tj"));
use_form_date_language("en");
}
/// A Format script's `util.printd` is run again with English names for a field whose fonts
/// can't draw the date language's, and kept where they can (#5303).
#[test]
fn format_scripts_print_dates_in_english_where_the_field_cannot_draw_them() {
let _names = names_lock();
let script = "event.value = event.value ? util.printd(\"dd-mmm-yy\", util.scand(\"dd-mm-yy\", event.value)) + \" !\" : \"\";";
let fields = [("helv", "Helv", script), ("song", "Song", script)];
use_form_date_language("ru");
let mut doc = form(&fields);
fill(&mut doc, "helv");
fill(&mut doc, "song");
let helv = appearance(&doc, "helv");
assert!(contains(&helv, b"(18-Oct-26 !) Tj"), "{}", String::from_utf8_lossy(&helv));
assert!(!helv.contains(&b'?'), "{}", String::from_utf8_lossy(&helv));
assert!(pdfcraft_forms::undrawn_fields(&doc).is_empty());
assert!(contains(&appearance(&doc, "song"), &ucs2("18-окт.-26 !")));
// A script whose text has no English either keeps it, reported as undrawn.
let greeting = [("hi", "Helv", "event.value = \"Привет \" + util.printd(\"mmm\", new Date(2026, 9, 18));")];
let mut doc = form(&greeting);
fill(&mut doc, "hi");
assert_eq!(pdfcraft_forms::undrawn_fields(&doc), [("hi".to_string(), 'П')]);
// The English run is the appearance's alone: scripts go on printing the date language.
assert_eq!(printd("dd-mmm-yy", "18-окт.-26"), "18-окт.-26|18-окт.-26");
use_form_date_language("en");
}
/// A Format script's English run is kept when it ran, even where it prints the stored value
/// again: a Helvetica field storing "18-Oct-26", printed again as `dd-mmm-yy`, showed
/// "18-????.-26" in Russian. A script that fails keeps what it showed, reported undrawn (#5303).
#[test]
fn an_english_run_that_prints_the_stored_value_is_drawn() {
let _names = names_lock();
let script = "event.value = util.printd(\"dd-mmm-yy\", util.scand(\"dd-mmm-yy\", event.value));";
use_form_date_language("ru");
let mut doc = form(&[("helv", "Helv", script), ("fails", "Helv", "throw new Error(\"no\");")]);
fill_with(&mut doc, "helv", "18-Oct-26");
let helv = appearance(&doc, "helv");
assert!(contains(&helv, b"(18-Oct-26) Tj"), "{}", String::from_utf8_lossy(&helv));
assert!(!helv.contains(&b'?'), "{}", String::from_utf8_lossy(&helv));
assert!(pdfcraft_forms::undrawn_fields(&doc).is_empty());
fill_with(&mut doc, "fails", "18-окт.-26");
assert_eq!(pdfcraft_forms::undrawn_fields(&doc), [("fails".to_string(), 'о')]);
use_form_date_language("en");
}
/// What `util.scand(fmt, text)` reads, as `yyyy-mm-dd`, or `null`.
fn scanned(fmt: &str, text: &str) -> String {
let doc = DocInfo { file_name: "form.pdf".into(), num_pages: 1, page: 0, info: Vec::new(), xfa: false };
let script = format!("var d = util.scand('{fmt}', {text:?}); event.value = d ? util.printd('yyyy-mm-dd', d) : 'null';");
let o = run(&script, &Event::field("Format", "date", ""), &doc, &[], &[], Limits::default());
assert_eq!(o.error, None);
o.value
}
/// A short weekday typed without its dot ("mar" for French "mar.", Tuesday) is the weekday where
/// the format has one, not the English "Mar" (March) that is the only other name of its length:
/// "mar 6 janv 2026" read as no date in French and Romanian (#5303).
#[test]
fn a_short_weekday_typed_without_its_dot_is_the_weekday() {
let _names = names_lock();
let mut bad = Vec::new();
let cases = [
("fr", "ddd d mmm yyyy", "Mar 6 janv 2026", "2026-01-06"),
("fr", "ddd d mmm yyyy", "mar 17 mars 2026", "2026-03-17"),
("fr", "mmm d yyyy ddd", "janv 6 2026 mar", "2026-01-06"),
("fr", "ddd dd/mm/yyyy", "mar 06/01/2026", "2026-01-06"),
("ro", "ddd d mmm yyyy", "mar 6 ian 2026", "2026-01-06"),
("ro", "ddd dd/mm/yyyy", "mar 06/01/2026", "2026-01-06"),
];
for (language, fmt, text, want) in cases {
use_form_date_language(language);
let got = scanned(fmt, text);
if got != want {
bad.push(format!("{language} scand {fmt}: {text:?} -> {got}"));
}
let read = parse_date(text, fmt).map(|d| format!("{:04}-{:02}-{:02}", d.y, d.m, d.d));
if read.as_deref() != Some(want) {
bad.push(format!("{language} forms {fmt}: {text:?} -> {read:?}"));
}
}
use_form_date_language("en");
assert!(bad.is_empty(), "{}", bad.join("; "));
}
/// A weekday left out of a format with one ("17 mar 2026" for "ddd d mmm yyyy") lets a name the
/// date language shares between a weekday and a month be the month: Italian, Spanish and
/// Albanian "mar" (Tuesday, March) and Albanian "sht" (Saturday, September) were read as the
/// weekday, leaving no month (#5303). Typed weekdays still go first.
#[test]
fn a_shared_name_is_the_month_when_the_weekday_is_left_out() {
let _names = names_lock();
let mut bad = Vec::new();
let cases = [
("it", "ddd d mmm yyyy", "17 Mar 2026", (2026, 3, 17)),
("es", "ddd d mmm yyyy", "17 Mar 2026", (2026, 3, 17)),
("sq", "ddd d mmm yyyy", "17 Mar 2026", (2026, 3, 17)),
("it", "ddd d mmm yyyy", "17 mar 2026", (2026, 3, 17)),
("it", "dddd, mmmm d, yyyy", "mar 17, 2026", (2026, 3, 17)),
("it", "dddd, mmm d, yyyy", "mar 17 2026", (2026, 3, 17)),
("sq", "ddd d mmm yyyy", "5 sht 2026", (2026, 9, 5)),
("it", "ddd d mmm yyyy", "mar 17 Mar 2026", (2026, 3, 17)),
("it", "ddd d mmm yyyy", "mar 17 mar 2026", (2026, 3, 17)),
];
for (language, fmt, text, want) in cases {
use_form_date_language(language);
let read = parse_date(text, fmt).map(|d| (d.y, d.m, d.d));
if read != Some(want) {
bad.push(format!("{language} forms {fmt}: {text:?} -> {read:?}"));
}
if keystroke(&Format::Date(fmt.into()), "date", text).is_err() {
bad.push(format!("{language} keystroke {fmt}: {text:?} refused"));
}
}
use_form_date_language("en");
assert!(bad.is_empty(), "{}", bad.join("; "));
}
/// Turkish names typed in capitals are read: lower-casing letter by letter made "MAYIS" "mayis"
/// (not "mayıs"), "SALI" "sali" and "EKİM" "eki̇m" (an i with a dot above), so no name matched.
/// Dotted, dotless and capital i are one letter when names are read (#5303).
#[test]
fn turkish_names_typed_in_capitals_are_read() {
let _names = names_lock();
use_form_date_language("tr");
let mut bad = Vec::new();
for (fmt, text, want) in [
("d mmmm yyyy", "1 MAYIS 2026", (2026, 5, 1)),
("d mmmm yyyy", "1 EKİM 2026", (2026, 10, 1)),
("d mmmm yyyy", "1 Ekim 2026", (2026, 10, 1)),
("d mmm yyyy", "1 EKİ 2026", (2026, 10, 1)),
("dddd d mmmm yyyy", "SALI 6 OCAK 2026", (2026, 1, 6)),
("dddd d mmmm yyyy", "Salı 6 Ocak 2026", (2026, 1, 6)),
] {
let read = parse_date(text, fmt).map(|d| (d.y, d.m, d.d));
if read != Some(want) {
bad.push(format!("forms {fmt}: {text:?} -> {read:?}"));
}
let (y, m, d) = want;
let got = scanned(fmt, text);
if got != format!("{y:04}-{m:02}-{d:02}") {
bad.push(format!("scand {fmt}: {text:?} -> {got}"));
}
}
// English is read as before, capitals and all.
use_form_date_language("en");
for (fmt, text) in [("d mmmm yyyy", "1 APRIL 2026"), ("dddd d mmmm yyyy", "FRIDAY 1 MAY 2026"), ("d mmm yyyy", "1 MAY 2026")] {
if parse_date(text, fmt).is_none() || scanned(fmt, text) == "null" {
bad.push(format!("en {fmt}: {text:?}"));
}
}
assert!(bad.is_empty(), "{}", bad.join("; "));
}
/// #5464 review: Greek names typed in capitals end in a capital Σ, which is the final ς of the
/// name ("ΙΑΝΟΥΆΡΙΟΣ" for "Ιανουάριος"); they read as they did before names were folded.
#[test]
fn greek_names_typed_in_capitals_are_read() {
let _names = names_lock();
use_form_date_language("el");
let mut bad = Vec::new();
for (fmt, text, want) in [
("d mmmm yyyy", "1 ΙΑΝΟΥΆΡΙΟΣ 2026", (2026, 1, 1)),
("d mmmm yyyy", "1 Ιανουάριος 2026", (2026, 1, 1)),
("d mmmm yyyy", "1 ιανουάριοσ 2026", (2026, 1, 1)),
("mmmm d, yyyy", "ΜΆΙΟΣ 5, 2026", (2026, 5, 5)),
("dddd, mmmm d, yyyy", "FRIDAY, ΙΑΝΟΥΆΡΙΟΣ 2, 2026", (2026, 1, 2)),
] {
let read = parse_date(text, fmt).map(|d| (d.y, d.m, d.d));
if read != Some(want) {
bad.push(format!("forms {fmt}: {text:?} -> {read:?}"));
}
let (y, m, d) = want;
let got = scanned(fmt, text);
if got != format!("{y:04}-{m:02}-{d:02}") {
bad.push(format!("scand {fmt}: {text:?} -> {got}"));
}
}
assert!(bad.is_empty(), "{}", bad.join("; "));
}
crates/engine/tests/it/ocr_edit.rs
+17 -3
View File
@@ -12,7 +12,14 @@ const WORD: [u32; 4] = [40, 40, 100, 60];
/// A 200 × 100 pt "scan" on tinted paper, with OCR text over its word.
fn scanned() -> (Session, pdfcraft_engine::DocId) {
scanned_with(vec![PlacedWord { text: "John".into(), origin: [40.0, 40.0], across: [60.0, 0.0], up: [0.0, 20.0] }])
scanned_with(vec![PlacedWord {
text: "John".into(),
origin: [40.0, 40.0],
across: [60.0, 0.0],
up: [0.0, 20.0],
confidence: None,
source: "ocrs".into(),
}])
}
fn scanned_with(words: Vec<PlacedWord>) -> (Session, pdfcraft_engine::DocId) {
@@ -86,11 +93,18 @@ fn an_explicit_colour_is_kept_for_the_new_text() {
/// descender line when it has descenders, up to the cap height.
fn scanned_word(text: &str, x0: f64, x1: f64, baseline: f64, size: f64) -> PlacedWord {
let low = if text.chars().any(|c| "gjpqy".contains(c)) { 0.21 * size } else { 0.0 };
PlacedWord { text: text.into(), origin: [x0, baseline - low], across: [x1 - x0, 0.0], up: [0.0, 0.718 * size + low] }
PlacedWord {
text: text.into(),
origin: [x0, baseline - low],
across: [x1 - x0, 0.0],
up: [0.0, 0.718 * size + low],
confidence: None,
source: "ocrs".into(),
}
}
fn word(text: &str, x0: f64, x1: f64, baseline: f64) -> PlacedWord {
PlacedWord { text: text.into(), origin: [x0, baseline], across: [x1 - x0, 0.0], up: [0.0, 10.0] }
PlacedWord { text: text.into(), origin: [x0, baseline], across: [x1 - x0, 0.0], up: [0.0, 10.0], confidence: None, source: "ocrs".into() }
}
/// OCR words keep the scan's layout: a phrase is one paragraph, a value in the next table cell and
crates/fonts/README.md
+5
View File
@@ -59,7 +59,12 @@ set). Without that variable `CRAFT_FONTS` is empty and everything below copes:
and shaped Thai Add Text content. Harfrust positions stacked vowel/tone marks and decomposes
Sara Am; cluster ToUnicode entries preserve the original text. The shared Type 3 writer
embeds outlines, so reopening does not depend on installed fonts.
- `craft_glyph(face, ch)` and `face_has(bytes, ch)`: bounded outlines and glyph coverage for any bundled face.
- `SHIPPORI_MINCHO`: Shippori Mincho's bytes, or `None`.
- `TextPlan::for_words`: how the OCR output writes text beyond WinAnsi — per word the first
face (document face first) whose glyphs cover it, planned once per page into Type 3 fonts
(codes, advances, `?` stand-ins) that `pdfcraft-edit` registers and the `pdfcraft-ocr` layers
draw with; characters no face has are counted (`missing`) so the output reports them.
Generated Japanese Type 3 fonts record the fallback face's family and style in an indirect
`FontDescriptor`. `pdf::Metrics::base_font` uses its `FontName` when the Type 3 dictionary has
crates/fonts/src/lib.rs
+14 -1
View File
@@ -14,6 +14,7 @@ pub mod embedding;
mod encodings;
pub mod fallback;
pub mod pdf;
pub mod plan;
mod script;
mod shaping;
pub mod source_shaping;
@@ -24,8 +25,10 @@ pub use craft::{
document_japanese_font_for_style, document_japanese_fonts_for_style, document_latin_fonts, document_thai_font, ui_arabic_fonts, ui_chinese_fonts,
ui_cjk_fonts, ui_devanagari_fonts, ui_hebrew_fonts, ui_japanese_fonts, ui_telugu_fonts, ui_thai_fonts,
};
pub use plan::{MAX_PLAN_GLYPHS, MAX_TYPE3_GLYPHS, PlannedType3, TextPlan};
pub use script::{
GlyphError, GlyphOutline, INTER_REGULAR, MAX_SIGNATURE_CHARS, ScriptOutline, japanese_glyph, japanese_glyph_from, script_missing, script_outline,
GlyphError, GlyphOutline, INTER_REGULAR, MAX_SIGNATURE_CHARS, ScriptOutline, craft_glyph, face_has, japanese_glyph, japanese_glyph_from,
script_missing, script_outline,
};
pub use shaping::{
ShapedCluster, ShapedScript, arabic_glyph, arabic_has, hebrew_has, shape_arabic, shape_hebrew, shape_thai, shaped_glyph, thai_has,
@@ -273,6 +276,16 @@ pub fn set_undrawn_mark(d: &mut pdfcraft_cos::Dict, c: Option<char>) {
}
}
/// The byte used by Unicode text plans, from the shared WinAnsi table (tabs become spaces).
pub fn win_ansi_char(c: char) -> Option<u8> {
if c == '\t' { Some(b' ') } else { win_ansi_byte(c) }
}
/// Whether every character can be represented without substitution in WinAnsi.
pub fn fits_win_ansi(s: &str) -> bool {
s.chars().all(win_ansi_encodable)
}
/// Bytes as a PDF literal string, `(` … `)`, with delimiters escaped.
pub fn literal(bytes: &[u8]) -> Vec<u8> {
let mut out = Vec::with_capacity(bytes.len() + 2);
crates/fonts/src/plan.rs
+338
View File
@@ -0,0 +1,338 @@
//! Planning visible Unicode text output for OCR: which characters the standard WinAnsi
//! fonts show as is, which need a Type3 font drawn from the craft-fonts faces, and which have
//! no glyph anywhere (written as `?` — and counted, never silently dropped).
//!
//! The plan is a pure function of the words ([`TextPlan::for_words`]). The content generators
//! (`pdfcraft_ocr::text_layer` / `visible_text_layer`) read the per-character codes and
//! advances from it, and whoever registers the fonts (`pdfcraft_edit::add_type3_fonts`) fills
//! in each face's resource name and object. The build must work without craft-fonts too: there
//! [`CRAFT_FONTS`] is empty, nothing can be planned, and every non-WinAnsi character is
//! reported as a substitution instead.
use std::collections::HashMap;
use pdfcraft_cos::ObjRef;
use crate::{CraftFont, GlyphOutline, craft_glyph, document_japanese_font, face_has, fits_win_ansi, win_ansi_char};
/// Unique characters per Type3 font: the same bound the text-editing fallback uses, so one
/// hostile word cannot balloon into thousands of glyph streams. A face with more characters
/// simply gets another font.
pub const MAX_TYPE3_GLYPHS: usize = 240;
/// Planned glyphs per plan in total (10 full fonts). A page's recognition cannot realistically
/// exceed it; hostile input beyond it degrades to `?` substitutions, which are counted.
pub const MAX_PLAN_GLYPHS: usize = 2400;
/// One planned Type3 font: the glyphs of one craft-fonts face, one character per code
/// (`code = position + 1`, as in the text-editing fallback). `name` and `object` are filled in
/// when the font is added to a page's resources; until then the content generators fall back to
/// the WinAnsi path for the words that reference it.
pub struct PlannedType3 {
/// The face family the glyphs are drawn from ("Shippori Mincho").
pub family: &'static str,
/// (character, outline with its advance) per code, in code order.
pub glyphs: Vec<(char, GlyphOutline)>,
/// The resource name the content references (`PCOcr`, `PCOcr1`, …); empty until registered.
pub name: String,
/// The built font object, shared by every page that uses the font; set at registration.
pub object: Option<ObjRef>,
}
impl PlannedType3 {
fn new(family: &'static str) -> Self {
PlannedType3 { family, glyphs: Vec::new(), name: String::new(), object: None }
}
fn push(&mut self, ch: char, glyph: GlyphOutline) -> u8 {
self.glyphs.push((ch, glyph));
self.glyphs.len() as u8
}
}
/// How the text layers write a plan's characters: each planned character is a
/// `(font index, code)` pair in its font's encoding; a character no face had a glyph for is
/// either the font's `?` code or absent from the run (both counted in [`TextPlan::missing`]).
#[derive(Default)]
pub struct TextPlan {
/// One planned font per face chunk, in first-use order.
pub fonts: Vec<PlannedType3>,
/// Per input word: `(font, code)` per character; empty for a word the standard WinAnsi
/// fonts write as is (or for which nothing could be planned).
words: Vec<Vec<(usize, u8)>>,
/// character → where its glyph lives, across all fonts (codes are font-local).
index: HashMap<char, (usize, u8)>,
/// Characters with no code in their word's font: they appear as `?` (or, when not even a
/// `?` glyph exists, are left out) and are reported, never silently lost.
missing: usize,
}
impl TextPlan {
/// Plan the output for `words`, in order: characters the WinAnsi fonts can't show get codes
/// in Type3 fonts built from the craft-fonts faces (the document face preferred, then the
/// rest of the build input in manifest order); a word whose face can't show a character
/// substitutes its `?`. Faces are chosen per word, so a word of one script stays one face;
/// characters already planned for an earlier word keep their code. Built without
/// craft-fonts, the plan reports every non-WinAnsi character as a substitution.
pub fn for_words<'a>(words: impl IntoIterator<Item = &'a str>) -> TextPlan {
let faces = document_faces();
let mut coverage = Coverage::default();
let mut plan = TextPlan::default();
for word in words {
if fits_win_ansi(word) {
// The WinAnsi path substitutes '?' behind the caller's back; count it.
plan.missing += word.chars().filter(|&c| win_ansi_char(c).is_none()).count();
plan.words.push(Vec::new());
continue;
}
let Some(face) = choose_face(&faces, word, &mut coverage) else {
// No face for this word's script: the WinAnsi path writes '?' for what it
// can't encode.
plan.missing += word.chars().filter(|&c| win_ansi_char(c).is_none()).count();
plan.words.push(Vec::new());
continue;
};
let mut enc: Vec<(usize, u8)> = Vec::with_capacity(word.len());
let mut run: Option<usize> = None;
for ch in word.chars() {
if let Some(&where_) = plan.index.get(&ch) {
enc.push(where_);
run = Some(where_.0);
continue;
}
if let Ok(glyph) = craft_glyph(face, ch)
&& plan.planned_glyphs() < MAX_PLAN_GLYPHS
&& let Some((fi, code)) = plan.add_glyph(face, ch, glyph)
{
plan.index.insert(ch, (fi, code));
enc.push((fi, code));
run = Some(fi);
continue;
}
// The face has no glyph for the character (or the plan is full): substitute
// the font's '?', in the font the surrounding run is set in.
if let Some((fi, code)) = plan.question_mark(face, run.filter(|&f| plan.fonts[f].family == face.family)) {
enc.push((fi, code));
run = Some(fi);
}
plan.missing += 1;
}
plan.words.push(enc);
}
plan
}
/// The encoding of word `i` (parallel to the slice [`Self::for_words`] planned): a list of
/// `(font, code)` per character, or an empty slice for a word the WinAnsi fonts write.
/// Out-of-range indexes degrade to the empty slice rather than panicking — callers pass the
/// same word list they planned with.
pub fn encoding(&self, word: usize) -> &[(usize, u8)] {
self.words.get(word).map(Vec::as_slice).unwrap_or_default()
}
/// How many characters no font could show (they appear as `?`, or are left out when the
/// word's face has no `?` glyph either).
pub fn missing(&self) -> usize {
self.missing
}
/// The advance of one planned code, in em units (the Type3 glyphs' own widths). `0.0` for
/// anything out of range.
pub fn advance(&self, font: usize, code: u8) -> f64 {
self.fonts.get(font).and_then(|f| f.glyphs.get(usize::from(code).checked_sub(1)?)).map_or(0.0, |(_, g)| g.width)
}
/// The sum of the advances of a word's planned codes, in em units.
pub fn advance_of(&self, encoding: &[(usize, u8)]) -> f64 {
encoding.iter().map(|&(f, c)| self.advance(f, c)).sum()
}
/// Whether every font the encoding references has been registered (has a resource name).
/// Unregistered plans fall back to the WinAnsi path, the same output as before the
/// Unicode mapping existed.
pub fn registered(&self, encoding: &[(usize, u8)]) -> bool {
encoding.iter().all(|&(f, _)| self.fonts.get(f).is_some_and(|font| !font.name.is_empty()))
}
/// Characters with a planned glyph so far.
fn planned_glyphs(&self) -> usize {
self.fonts.iter().map(|f| f.glyphs.len()).sum()
}
/// Add a glyph to the face's current font (a fresh one when that font is full).
fn add_glyph(&mut self, face: &CraftFont, ch: char, glyph: GlyphOutline) -> Option<(usize, u8)> {
let fi = self.font_of_face(face.family)?;
let code = self.fonts[fi].push(ch, glyph);
Some((fi, code))
}
/// The index of the face's open font, or a fresh one. `None` without craft-fonts (the
/// face itself comes from there, so this cannot happen for a planned face).
fn font_of_face(&mut self, family: &'static str) -> Option<usize> {
if let Some(fi) = self.fonts.iter().rposition(|f| f.family == family && f.glyphs.len() < MAX_TYPE3_GLYPHS) {
return Some(fi);
}
if self.fonts.len() >= MAX_PLAN_GLYPHS / MAX_TYPE3_GLYPHS {
return None;
}
self.fonts.push(PlannedType3::new(family));
Some(self.fonts.len() - 1)
}
/// The code of the font's `?` stand-in, adding the glyph when the font lacks it.
/// `prefer` is the run's current font; `None` without craft-fonts.
fn question_mark(&mut self, face: &CraftFont, prefer: Option<usize>) -> Option<(usize, u8)> {
if let Some(fi) = prefer
&& let Some(code) = self.fonts[fi].glyphs.iter().position(|(c, _)| *c == '?')
{
return Some((fi, code as u8 + 1));
}
let fi = self.font_of_face(face.family)?;
if let Some(code) = self.fonts[fi].glyphs.iter().position(|(c, _)| *c == '?') {
return Some((fi, code as u8 + 1));
}
let glyph = craft_glyph(face, '?').ok()?;
let code = self.fonts[fi].push('?', glyph);
Some((fi, code))
}
}
/// The faces that can draw document text, in preference order: the Japanese document face
/// (serif document text) first, then the rest of the build input in manifest order.
fn document_faces() -> Vec<&'static CraftFont> {
let mut out = Vec::new();
if let Some(d) = document_japanese_font() {
out.push(d);
}
for f in crate::CRAFT_FONTS {
if !out.iter().any(|d| std::ptr::eq(*d, f)) {
out.push(f);
}
}
out
}
/// The face for a word: the first (in preference order) whose glyphs cover every character,
/// else the one covering the most characters (ties go to the earlier face). `None` when no
/// face covers any character of the word.
fn choose_face<'f>(faces: &[&'f CraftFont], word: &str, coverage: &mut Coverage) -> Option<&'f CraftFont> {
if let Some(f) = faces.iter().enumerate().find(|(i, f)| word.chars().all(|c| coverage.has(*i, f, c))).map(|(_, f)| *f) {
return Some(f);
}
faces
.iter()
.enumerate()
.map(|(i, f)| (word.chars().filter(|&c| coverage.has(i, f, c)).count(), std::cmp::Reverse(i), *f))
.max_by(|a, b| (a.0, a.1).cmp(&(b.0, b.1)))
.filter(|(covered, _, _)| *covered > 0)
.map(|(_, _, f)| f)
}
/// Which faces have a glyph for which characters, remembered for one plan: a page of words
/// asks the same (face, character) pairs over and over, and each fresh answer parses the font.
#[derive(Default)]
struct Coverage {
known: std::collections::HashMap<(usize, char), bool>,
lookups: usize,
}
impl Coverage {
/// Whether face number `i` (`face`) has `ch`; asks the font once per pair.
fn has(&mut self, i: usize, face: &CraftFont, ch: char) -> bool {
*self.known.entry((i, ch)).or_insert_with(|| {
self.lookups += 1;
face_has(face.bytes, ch)
})
}
}
#[cfg(test)]
mod tests {
use super::*;
/// Face coverage is asked once per (face, character): repeating words cost no new font
/// lookups.
#[test]
fn face_coverage_is_remembered_per_face_and_character() {
let faces = document_faces();
let Some(face) = faces.first() else {
eprintln!("skipping: built without craft-fonts (set CRAFT_FONTS_DIR to run it)");
return;
};
let mut coverage = Coverage::default();
let first = (0..50).map(|_| choose_face(&faces, "日本語", &mut coverage)).last().flatten();
assert!(first.is_some());
assert!(coverage.lookups <= faces.len() * 3, "{} lookups for 3 characters", coverage.lookups);
assert_eq!(coverage.has(0, face, '日'), face_has(face.bytes, '日'));
}
/// A page's vocabulary: German umlauts are WinAnsi, and a character no bundled face has
/// (here an emoji) is counted wherever it appears.
#[test]
fn win_ansi_words_get_no_encoding_and_count_only_real_losses() {
let plan = TextPlan::for_words(["Zürcher", "café", "size"]);
assert!(plan.words.iter().all(Vec::is_empty), "all WinAnsi: no Type3 fonts needed");
assert!(plan.fonts.is_empty());
assert_eq!(plan.missing(), 0);
let none = TextPlan::for_words(["plain text"]);
assert_eq!(none.missing(), 0);
// U+1F600 has no WinAnsi code and no glyph in any bundled face (with craft-fonts the
// JIS faces even cover the snowman): counted, shown as '?'.
let emoji = TextPlan::for_words(["\u{1f600}!"]);
assert_eq!(emoji.missing(), 1);
}
#[test]
fn without_craft_fonts_every_non_win_ansi_character_is_reported() {
if !crate::CRAFT_FONTS.is_empty() {
eprintln!("built with craft-fonts: the planning tests with faces cover this instead");
return;
}
let plan = TextPlan::for_words(["Привет", "日本", "abc"]);
assert!(plan.words.iter().all(Vec::is_empty));
assert!(plan.fonts.is_empty());
assert_eq!(plan.missing(), 8, "six Cyrillic + two CJK characters, each reported");
}
#[test]
fn encodings_are_aligned_and_total_the_advances() {
if crate::CRAFT_FONTS.is_empty() {
eprintln!("skipping: built without craft-fonts (set CRAFT_FONTS_DIR to run it)");
assert!(TextPlan::for_words(["日本"]).fonts.is_empty());
return;
}
let plan = TextPlan::for_words(["日本語", "語"]);
assert_eq!(plan.encoding(0).len(), 3);
assert_eq!(plan.encoding(1).len(), 1);
// 語 planned once keeps its code (and font) in both words.
let (f, c) = plan.encoding(1)[0];
assert_eq!(plan.encoding(0)[2], (f, c), "the repeated character keeps its code");
assert!(plan.advance(f, c) > 0.0);
assert_eq!(plan.advance(f, 0), 0.0, "codes start at 1");
assert_eq!(plan.encoding(7), &[], "out of range degrades to the WinAnsi path");
assert!(plan.advance_of(plan.encoding(0)) > plan.advance_of(plan.encoding(1)));
}
#[test]
fn hostile_input_stays_bounded() {
// Thousands of DISTINCT characters: the covered ones fill fonts up to the caps, the
// rest are reported substitutions.
let word: String = (0..4000u32).filter_map(|i| char::from_u32(0x4e00 + i)).collect();
let plan = TextPlan::for_words([word.as_str()]);
assert!(plan.planned_glyphs() <= MAX_PLAN_GLYPHS);
assert!(plan.fonts.iter().all(|f| f.glyphs.len() <= MAX_TYPE3_GLYPHS));
assert!(plan.missing() > 0, "characters beyond the caps are reported, never silently dropped");
}
#[test]
fn substitution_and_unknown_scripts_come_out_counted() {
if crate::CRAFT_FONTS.is_empty() {
eprintln!("skipping: built without craft-fonts (set CRAFT_FONTS_DIR to run it)");
return;
}
let plan = TextPlan::for_words(["日本\u{1f4a9}語"]);
// The emoji has no glyph in any bundled face; the kana/kanji do.
assert_eq!(plan.missing(), 1);
assert_eq!(plan.encoding(0).len(), 4, "the emoji still has an encoding: the font's ?");
}
}
crates/fonts/src/script.rs
+16 -1
View File
@@ -134,6 +134,17 @@ impl OutlinePen for Flatten {
}
}
/// Whether the face has a glyph for `ch` (a cheap character-map probe, no outline work).
pub fn face_has(bytes: &[u8], ch: char) -> bool {
FontRef::new(bytes).is_ok_and(|font| font.charmap().map(ch).is_some())
}
/// Return one glyph of `face` (a craft-fonts face), bounded so hostile replacement text cannot
/// allocate unbounded outline data.
pub fn craft_glyph(face: &crate::CraftFont, ch: char) -> Result<GlyphOutline, GlyphError> {
glyph_in_face(face.bytes, ch)
}
/// Return one glyph of the Japanese document face ([`crate::document_japanese_font`], Shippori
/// Mincho from craft-fonts), bounded so hostile replacement text cannot allocate unbounded
/// outline data. [`GlyphError::NoFont`] when the build has no Japanese face.
@@ -145,7 +156,11 @@ pub fn japanese_glyph(ch: char) -> Result<GlyphOutline, GlyphError> {
/// The bounded outline and advance from the explicitly selected craft-fonts face.
/// Uses the same complexity and missing-glyph checks as [`japanese_glyph`].
pub fn japanese_glyph_from(face: &crate::CraftFont, ch: char) -> Result<GlyphOutline, GlyphError> {
let Ok(font) = FontRef::new(face.bytes) else { return Err(GlyphError::Missing) };
glyph_in_face(face.bytes, ch)
}
fn glyph_in_face(bytes: &[u8], ch: char) -> Result<GlyphOutline, GlyphError> {
let Ok(font) = FontRef::new(bytes) else { return Err(GlyphError::Missing) };
let loc = LocationRef::default();
let metrics = font.metrics(Size::unscaled(), loc);
let scale = 1.0 / metrics.units_per_em.max(1) as f64;
crates/forms/src/af.rs
+4 -1
View File
@@ -20,7 +20,10 @@ mod script;
#[cfg(test)]
use calc::{Notation, eval_notation, notation_name, notation_tokens, unique};
pub use calc::{calculate, calculation_reads, notation_js, reads_built_names, rename_in_calculation};
pub use format::{DATE_PRESETS, DateTime, TIME_PRESETS, format_date, format_value, js_number, keystroke, make_number, parse_date, validate};
pub use format::{
DATE_PRESETS, DateNames, DateTime, ENGLISH_DATE_NAMES, TIME_PRESETS, date_names, format_date, format_date_in, format_value, format_value_in,
js_number, keystroke, make_number, parse_date, set_date_names, validate,
};
use script::{Arg, call};
pub use script::{NOTATION_NOT_STORABLE, calculate_js, format_js, notation_storable, parse_calculate, parse_format, parse_validate, validate_js};
crates/forms/src/af/format.rs
+191 -11
View File
@@ -89,6 +89,165 @@ const MONTHS: [&str; 12] = ["January", "February", "March", "April", "May", "Jun
const DAYS: [&str; 7] = ["Sunday", "Monday", "Tuesday", "Wednesday", "Thursday", "Friday", "Saturday"];
/// The month and weekday names `mmmm`, `mmm`, `dddd` and `ddd` write (weekdays from Sunday), as
/// a localized Acrobat writes them in its own language (#5303).
#[derive(Clone, Copy, Debug, PartialEq, Eq)]
pub struct DateNames {
pub months: [&'static str; 12],
pub months_short: [&'static str; 12],
pub days: [&'static str; 7],
pub days_short: [&'static str; 7],
}
/// English, the names until the app sets others.
pub const ENGLISH_DATE_NAMES: DateNames = DateNames {
months: MONTHS,
months_short: ["Jan", "Feb", "Mar", "Apr", "May", "Jun", "Jul", "Aug", "Sep", "Oct", "Nov", "Dec"],
days: DAYS,
days_short: ["Sun", "Mon", "Tue", "Wed", "Thu", "Fri", "Sat"],
};
static DATE_NAMES: std::sync::RwLock<DateNames> = std::sync::RwLock::new(ENGLISH_DATE_NAMES);
/// Sets the names date formats write from now on (the app's date language); typed dates are read
/// in them and in English.
pub fn set_date_names(names: DateNames) {
*DATE_NAMES.write().unwrap_or_else(std::sync::PoisonError::into_inner) = names;
}
/// The names date formats write.
pub fn date_names() -> DateNames {
*DATE_NAMES.read().unwrap_or_else(std::sync::PoisonError::into_inner)
}
/// `text` with the month and weekday names of `lists` (in the order months, short months,
/// weekdays, short weekdays) written as their English names, so a parser that reads English
/// reads them. The longest name wins at each place, case ignored, and only a whole name: one
/// that doesn't continue a word, nor end in a digit that a number continues. A name may hold
/// digits ("10月"), spaces ("tháng 10"), dots ("ม.ค.") or combining vowel signs, which a
/// word-by-word reader would split (#5303). Where a weekday and a month share a name (Italian
/// "mar"), the order of the format's name fields (`mmm`, `ddd`) decides. English names are
/// found too, so that one typed ("Tue" before "Mar") fills its field of the format as a
/// localized one does.
fn english_names(text: &str, fmt: &str, lists: [&[&str]; 4]) -> String {
const EN: [&[&str]; 4] = [&MONTHS, &MONTHS, &DAYS, &DAYS];
// No date is this long: hostile text is left as it is rather than scanned name by name.
if text.len() > MAX_DATE_TEXT_BYTES {
return text.to_string();
}
let chars: Vec<char> = text.chars().collect();
let typed_english: [&[&str]; 4] = [&MONTHS, &ENGLISH_DATE_NAMES.months_short, &DAYS, &ENGLISH_DATE_NAMES.days_short];
// Each name as folded chars, whether it is a month, and its English name.
let mut names: Vec<(Vec<String>, bool, &str)> = Vec::new();
for (k, (list, en)) in lists.into_iter().zip(EN).chain(typed_english.into_iter().zip(EN)).enumerate() {
for (name, english) in list.iter().zip(en.iter()) {
// A short name ending in a dot ("mar.") is also read typed without it, as the same
// kind of name, so that where it equals another ("Mar", March) the format decides.
let bare = name.trim_end_matches('.');
for name in std::iter::once(*name).chain((bare.len() < name.len()).then_some(bare)) {
let n: Vec<String> = name.chars().map(fold).collect();
if !n.is_empty() && n.len() <= MAX_NAME_CHARS {
names.push((n, k % 4 < 2, english));
}
}
}
}
names.sort_by_key(|(n, ..)| std::cmp::Reverse(n.len()));
// The format's name fields in order: true for a month, false for a weekday.
let f: Vec<char> = fmt.chars().collect();
let mut expected = Vec::new();
let mut j = 0;
while let Some(&c) = f.get(j) {
let run = f.get(j..).map_or(1, |r| r.iter().take_while(|x| **x == c).count()).max(1);
if run >= 3 && (c == 'm' || c == 'd') {
expected.push(c == 'm');
}
j = j.saturating_add(run);
}
let mut slot = 0;
// A name's first letter may not continue a word; its last may not run on into a letter, nor
// (a digit) into a number.
let letter = |c: Option<&char>| c.is_some_and(|c| c.is_alphabetic());
let mut out = String::with_capacity(text.len());
let mut i = 0;
while let Some(&c) = chars.get(i) {
let fits = |n: &Vec<String>| {
let end = i.saturating_add(n.len());
let first = n.first().and_then(|e| e.chars().next());
let last = n.last().and_then(|e| e.chars().next());
chars.get(i..end).is_some_and(|t| t.iter().map(|c| fold(*c)).eq(n.iter().cloned()))
&& !(first.is_some_and(char::is_alphabetic) && letter(i.checked_sub(1).and_then(|p| chars.get(p))))
&& !match last {
Some(l) if l.is_ascii_digit() => chars.get(end).is_some_and(char::is_ascii_digit),
Some(l) if l.is_alphabetic() => letter(chars.get(end)),
_ => false,
}
};
let longest = names.iter().find(|(n, ..)| fits(n)).map(|(n, ..)| n.len());
let hit = longest.and_then(|len| {
let mut same = names.iter().filter(|(n, ..)| n.len() == len && fits(n));
let want = expected.get(slot).copied();
let all: Vec<_> = same.by_ref().collect();
all.iter().find(|(_, month, _)| Some(*month) == want).or_else(|| all.first()).copied()
});
match hit {
Some((n, month, english)) => {
if expected.get(slot) == Some(month) {
slot += 1;
}
// Apart from what touches it ("10月18"), but no space added at either end.
if out.ends_with(char::is_alphanumeric) {
out.push(' ');
}
out.push_str(english);
i = i.saturating_add(n.len());
if chars.get(i).is_some_and(|c| c.is_alphanumeric()) {
out.push(' ');
}
}
None => {
out.push(c);
i += 1;
}
}
}
out
}
/// `c` as names are compared: lower case, with the capital I and the Turkish dotted and dotless
/// i all "i", and a combining dot above (U+0307) dropped, so that "EKİM", "SALI" and "MAYIS" are
/// Turkish "Ekim", "Salı" and "Mayıs", which lower-casing alone makes "ekim" with a dotted i,
/// "sali" and "mayis" (#5303). The Greek final sigma is a sigma, since a capital Σ, which
/// lower-cases to σ on its own, ends "ΙΑΝΟΥΆΡΙΟΣ" for "Ιανουάριος". One piece for each char, so
/// positions in the text stay aligned.
fn fold(c: char) -> String {
match c {
'I' | 'ı' | 'İ' => "i".to_string(),
'ς' => "σ".to_string(),
_ => c.to_lowercase().filter(|&l| l != '\u{307}').collect(),
}
}
/// `s` [`fold`]ed char by char.
fn folded(s: &str) -> String {
s.chars().map(fold).collect()
}
/// Typed dates longer than this are not searched for names.
const MAX_DATE_TEXT_BYTES: usize = 1024;
/// Names longer than this are not looked for (settings are trusted, but a cap keeps the scan cheap).
const MAX_NAME_CHARS: usize = 32;
/// The month (1 to 12) a typed word names: a start of at least three letters of a month's name,
/// or its whole short name, in `names` or in English.
fn month_named(word: &str, names: &DateNames) -> Option<u32> {
let w = folded(word);
let starts = |list: &[&str; 12]| list.iter().position(|m| w.chars().count() >= 3 && folded(m).starts_with(&w));
let whole = |list: &[&str; 12]| list.iter().position(|m| folded(m).trim_end_matches('.') == w);
starts(&names.months).or_else(|| whole(&names.months_short)).or_else(|| starts(&MONTHS)).map(|i| i as u32 + 1)
}
/// A date and time read from text.
#[derive(Clone, Copy, Debug, PartialEq, Eq)]
pub struct DateTime {
@@ -202,7 +361,20 @@ fn order(fmt: &str) -> Vec<Part> {
/// Parse typed text against a date/time format (AFDate_KeystrokeEx's leniency: any
/// separators, month names, two-digit years). `None` when it isn't a valid date.
pub fn parse_date(text: &str, fmt: &str) -> Option<DateTime> {
let t = text.trim();
let names = date_names();
let lists: [&[&str]; 4] = [&names.months, &names.months_short, &names.days, &names.days_short];
// Weekdays are shown, not typed (see `order`): where the format has one but none was typed, a
// name the language shares between a weekday and a month (Italian "mar") is the month, as
// the names are read again with no weekday expected (#5303).
read_date(&english_names(text, fmt, lists), fmt, &names).or_else(|| {
let no_weekday = fmt.replace("dddd", " ").replace("ddd", " ");
(no_weekday != fmt).then(|| read_date(&english_names(text, &no_weekday, lists), fmt, &names)).flatten()
})
}
/// [`parse_date`] of `english`, typed text whose month and weekday names are English.
fn read_date(english: &str, fmt: &str, names: &DateNames) -> Option<DateTime> {
let t = english.trim();
if t.is_empty() {
return None;
}
@@ -223,10 +395,8 @@ pub fn parse_date(text: &str, fmt: &str) -> Option<DateTime> {
}
if cur.starts_with(|c: char| c.is_ascii_digit()) {
nums.push_back(std::mem::take(cur));
} else if cur.len() >= 3
&& let Some(i) = MONTHS.iter().position(|m| m.to_lowercase().starts_with(&cur.to_lowercase()))
{
*month = Some(i as u32 + 1);
} else if let Some(m) = month_named(cur, names) {
*month = Some(m);
}
cur.clear();
};
@@ -337,6 +507,11 @@ pub fn parse_date(text: &str, fmt: &str) -> Option<DateTime> {
/// Format a date/time with Acrobat's date format letters.
pub fn format_date(dt: DateTime, fmt: &str) -> String {
format_date_in(dt, fmt, &date_names())
}
/// [`format_date`] with month and weekday names from `names`.
pub fn format_date_in(dt: DateTime, fmt: &str, names: &DateNames) -> String {
let chars: Vec<char> = fmt.chars().collect();
let mut out = String::new();
let mut i = 0;
@@ -354,9 +529,9 @@ pub fn format_date(dt: DateTime, fmt: &str) -> String {
('y', _) => {
let _ = write!(out, "{:02}", dt.y.rem_euclid(100));
}
('m', 3..) => match MONTHS.get((dt.m as usize).wrapping_sub(1)) {
Some(name) if n >= 4 => out.push_str(name),
Some(name) => out.push_str(name.get(..3).unwrap_or(name)),
('m', 3..) => match (dt.m as usize).checked_sub(1).and_then(|i| names.months.get(i).zip(names.months_short.get(i))) {
Some((name, _)) if n >= 4 => out.push_str(name),
Some((_, short)) => out.push_str(short),
None => {
let _ = write!(out, "{}", dt.m);
}
@@ -368,8 +543,8 @@ pub fn format_date(dt: DateTime, fmt: &str) -> String {
let _ = write!(out, "{}", dt.m);
}
('d', 3..) => {
let name = DAYS.get(weekday(dt.y, dt.m, dt.d)).copied().unwrap_or_default();
out.push_str(if n >= 4 { name } else { name.get(..3).unwrap_or(name) });
let list = if n >= 4 { &names.days } else { &names.days_short };
out.push_str(list.get(weekday(dt.y, dt.m, dt.d)).copied().unwrap_or_default());
}
('d', 2) => {
let _ = write!(out, "{:02}", dt.d);
@@ -451,6 +626,11 @@ fn apply_mask(mask: &str, text: &str) -> Option<String> {
/// The text shown for a value (the Format event).
pub fn format_value(f: &Format, value: &str) -> String {
format_value_in(f, value, &date_names())
}
/// [`format_value`] with month and weekday names from `names`.
pub fn format_value_in(f: &Format, value: &str, names: &DateNames) -> String {
if value.is_empty() {
return String::new();
}
@@ -479,7 +659,7 @@ pub fn format_value(f: &Format, value: &str) -> String {
),
None => value.to_string(),
},
Format::Date(fmt) | Format::Time(fmt) => parse_date(value, fmt).map_or_else(|| value.to_string(), |dt| format_date(dt, fmt)),
Format::Date(fmt) | Format::Time(fmt) => parse_date(value, fmt).map_or_else(|| value.to_string(), |dt| format_date_in(dt, fmt, names)),
Format::Special(n) => apply_mask(SPECIAL_MASKS[(*n).min(3) as usize], value).unwrap_or_else(|| value.to_string()),
Format::Mask(m) => apply_mask(m, value).unwrap_or_else(|| value.to_string()),
}
crates/forms/src/appearance.rs
+16 -3
View File
@@ -739,8 +739,18 @@ pub fn value_overflow(doc: &Document, f: &Field, w: &Widget) -> Option<Overflow>
field_appearance_fit(doc, f, w, &f.value, true).2
}
/// Whether `text` draws in widget `wd` of `f` with no `?`: in the field's `/DR` font when that
/// holds it, as [`field_appearance_fit`] picks, or else in the Helvetica (WinAnsi) stand-in.
fn draws(doc: &Document, f: &Field, wd: &Dict, text: &str) -> bool {
let da = parse_da(wd.get(b"DA").and_then(|o| doc.resolve(o).as_string().map(|s| s.to_text())).as_deref().unwrap_or(&f.da));
let enc = dr_font(doc, &da.font).map(|(_, enc)| enc).filter(|enc| enc.can_encode(text)).unwrap_or(FontText::WinAnsi);
enc.first_unencodable(text).is_none()
}
/// [`field_appearance_drawn`], and whether the text drawn is cut off by the box.
fn field_appearance_fit(doc: &Document, f: &Field, w: &Widget, values: &[String], format: bool) -> (Stream, Option<char>, Option<Overflow>) {
let wobj = doc.get(w.obj);
let wd = wobj.as_dict().cloned().unwrap_or_default();
// The Format event: what is shown, not what is stored.
let formatted: Vec<String>;
let values = if format
@@ -748,13 +758,16 @@ fn field_appearance_fit(doc: &Document, f: &Field, w: &Widget, values: &[String]
&& values.len() == 1
&& f.actions.format != crate::af::Format::None
{
formatted = vec![crate::af::format_value(&f.actions.format, &values[0])];
let shown = crate::af::format_value(&f.actions.format, &values[0]);
// Month and weekday names in the date language that no font here can draw ("окт." in
// Helvetica) are drawn in English rather than as `?` (#5303).
let english = || crate::af::format_value_in(&f.actions.format, &values[0], &crate::af::ENGLISH_DATE_NAMES);
let dated = matches!(f.actions.format, crate::af::Format::Date(_) | crate::af::Format::Time(_));
formatted = vec![if !dated || draws(doc, f, &wd, &shown) { shown } else { english() }];
&formatted[..]
} else {
values
};
let wobj = doc.get(w.obj);
let wd = wobj.as_dict().cloned().unwrap_or_default();
let (page_w, page_h) = ((w.rect[2] - w.rect[0]).max(1.0), (w.rect[3] - w.rect[1]).max(1.0));
let place = placement(mk_rotation(doc, &wd), page_w, page_h);
let (width, height) = (place.layout_w, place.layout_h);
crates/forms/src/scripting.rs
+22
View File
@@ -60,6 +60,21 @@ pub struct ScriptResult {
pub trait Scripts {
/// Run `script` for `event` on `target`, whose value is `value`; `fields` is the whole form.
fn run(&mut self, event: FieldEvent, script: &str, target: &Field, value: &str, fields: &[Field]) -> ScriptResult;
/// [`Self::run`] again for an appearance, with dates written in English names (`util.printd`)
/// because no font of the field can draw the date language's (#5303); what it logs was
/// already logged by the first run. `None` when it can't: no English dates here, or the
/// script failed. What it returns is what the script made, even when that is the value.
fn rerun_with_english_dates(
&mut self,
_event: FieldEvent,
_script: &str,
_target: &Field,
_value: &str,
_fields: &[Field],
) -> Option<ScriptResult> {
None
}
}
/// No script engine (or JavaScript turned off): scripts change nothing.
@@ -98,6 +113,13 @@ pub(crate) fn formatted(doc: &Document, f: &Field, value: &str, scripts: &mut dy
Some(r.value)
}
/// [`formatted`] with dates in English names, for widgets whose fonts can't draw the date
/// language's; `None` when the field has no Format script or the English run didn't happen.
pub(crate) fn formatted_in_english(doc: &Document, f: &Field, value: &str, scripts: &mut dyn Scripts) -> Option<String> {
let js = f.actions.scripts.format.as_ref()?;
scripts.rerun_with_english_dates(FieldEvent::Format, js, f, value, &fields(doc)).map(|r| r.value)
}
/// Apply script changes to other fields (values written without re-running their scripts;
/// read-only, required and visibility as flags). `except` is the event's own field, whose value
/// the event sets.
crates/forms/src/values.rs
+16 -1
View File
@@ -426,9 +426,24 @@ fn redraw(doc: &mut Document, f: &Field, values: &[String], scripts: &mut dyn Sc
};
let in_place = f.kind == FieldKind::Text && f.has(flags::PASSWORD);
let mut undrawn = false;
// The Format script again with English month and weekday names, once, for widgets whose
// fonts can't draw the date language's (#5303).
let mut english: Option<Option<String>> = None;
for w in &f.widgets {
let (stream, missing) = match &shown {
Some(s) => appearance::field_appearance_drawn(doc, f, w, std::slice::from_ref(s), false),
Some(s) => {
let drawn = appearance::field_appearance_drawn(doc, f, w, std::slice::from_ref(s), false);
// Taken when the English run happened and draws whole, even where it is the
// stored value ("18-Oct-26" printed again from itself).
let again = match (&drawn.1, values) {
(Some(_), [one]) => english.get_or_insert_with(|| scripting::formatted_in_english(doc, f, one, scripts)).as_ref(),
_ => None,
};
match again.map(|e| appearance::field_appearance_drawn(doc, f, w, std::slice::from_ref(e), false)) {
Some(english) if english.1.is_none() => english,
_ => drawn,
}
}
None => appearance::field_appearance_drawn(doc, f, w, values, true),
};
undrawn |= missing.is_some();
crates/js/fuzz/Cargo.toml
+24
View File
@@ -0,0 +1,24 @@
[package]
name = "pdfcraft-js-fuzz"
version = "0.0.0"
publish = false
edition = "2024"
license = "MIT OR Apache-2.0"
[package.metadata]
cargo-fuzz = true
# Detached from the PdfCraft workspace: run with `cargo +nightly fuzz run run_script`
# from crates/js/.
[workspace]
[dependencies]
libfuzzer-sys = "0.4"
pdfcraft-js = { path = ".." }
[[bin]]
name = "run_script"
path = "fuzz_targets/run_script.rs"
test = false
doc = false
bench = false
crates/js/fuzz/fuzz_targets/run_script.rs
+26
View File
@@ -0,0 +1,26 @@
//! Feeds arbitrary bytes, read as a script, to the JavaScript run entry with fixed event and document values.
//!
//! The run's result is discarded: the target only checks that no input panics or hangs past the limits.
#![no_main]
use libfuzzer_sys::fuzz_target;
use pdfcraft_js::{DocInfo, Event, Limits, run};
/// The largest script the target runs (64 KiB); larger inputs are skipped.
const MAX_INPUT: usize = 64 << 10;
fuzz_target!(|data: &[u8]| {
if data.len() > MAX_INPUT {
return;
}
let script = String::from_utf8_lossy(data).into_owned();
let event = Event {
name: "Keystroke".into(),
kind: "Field".into(),
target: Some("field1".into()),
value: "value".into(),
change: String::new(),
will_commit: true,
};
let _outcome = run(&script, &event, &DocInfo::default(), &[], &[], Limits::default());
});
crates/js/src/format.rs
+186 -9
View File
@@ -134,6 +134,177 @@ const MONTHS: [&str; 12] = ["January", "February", "March", "April", "May", "Jun
const DAYS: [&str; 7] = ["Sunday", "Monday", "Tuesday", "Wednesday", "Thursday", "Friday", "Saturday"];
/// Month and weekday names (weekdays from Sunday): full, then short.
type Names = ([&'static str; 12], [&'static str; 12], [&'static str; 7], [&'static str; 7]);
const ENGLISH: Names = (
MONTHS,
["Jan", "Feb", "Mar", "Apr", "May", "Jun", "Jul", "Aug", "Sep", "Oct", "Nov", "Dec"],
DAYS,
["Sun", "Mon", "Tue", "Wed", "Thu", "Fri", "Sat"],
);
static NAMES: std::sync::RwLock<Names> = std::sync::RwLock::new(ENGLISH);
/// Sets the month and weekday names `util.printd` writes for `mmmm`, `mmm`, `dddd` and `ddd`
/// (weekdays from Sunday), as a localized Acrobat writes its own language's (#5303).
/// `util.scand` reads them as well as English.
pub fn set_date_names(months: [&'static str; 12], months_short: [&'static str; 12], days: [&'static str; 7], days_short: [&'static str; 7]) {
*NAMES.write().unwrap_or_else(std::sync::PoisonError::into_inner) = (months, months_short, days, days_short);
}
/// `text` with the month and weekday names of `lists` (in the order months, short months,
/// weekdays, short weekdays) written as their English names, so a parser that reads English
/// reads them. The longest name wins at each place, case ignored, and only a whole name: one
/// that doesn't continue a word, nor end in a digit that a number continues. A name may hold
/// digits ("10月"), spaces ("tháng 10"), dots ("ม.ค.") or combining vowel signs, which a
/// word-by-word reader would split (#5303). Where a weekday and a month share a name (Italian
/// "mar"), the order of the format's name fields (`mmm`, `ddd`) decides. English names are
/// found too, so that one typed ("Tue" before "Mar") fills its field of the format as a
/// localized one does.
fn english_names(text: &str, fmt: &str, lists: [&[&str]; 4]) -> String {
const EN: [&[&str]; 4] = [&MONTHS, &MONTHS, &DAYS, &DAYS];
// No date is this long: hostile text is left as it is rather than scanned name by name.
if text.len() > MAX_DATE_TEXT_BYTES {
return text.to_string();
}
let chars: Vec<char> = text.chars().collect();
let typed_english: [&[&str]; 4] = [&ENGLISH.0, &ENGLISH.1, &ENGLISH.2, &ENGLISH.3];
// Each name as folded chars, whether it is a month, and its English name.
let mut names: Vec<(Vec<String>, bool, &str)> = Vec::new();
for (k, (list, en)) in lists.into_iter().zip(EN).chain(typed_english.into_iter().zip(EN)).enumerate() {
for (name, english) in list.iter().zip(en.iter()) {
// A short name ending in a dot ("mar.") is also read typed without it, as the same
// kind of name, so that where it equals another ("Mar", March) the format decides.
let bare = name.trim_end_matches('.');
for name in std::iter::once(*name).chain((bare.len() < name.len()).then_some(bare)) {
let n: Vec<String> = name.chars().map(fold).collect();
if !n.is_empty() && n.len() <= MAX_NAME_CHARS {
names.push((n, k % 4 < 2, english));
}
}
}
}
names.sort_by_key(|(n, ..)| std::cmp::Reverse(n.len()));
// The format's name fields in order: true for a month, false for a weekday.
let f: Vec<char> = fmt.chars().collect();
let mut expected = Vec::new();
let mut j = 0;
while let Some(&c) = f.get(j) {
let run = f.get(j..).map_or(1, |r| r.iter().take_while(|x| **x == c).count()).max(1);
if run >= 3 && (c == 'm' || c == 'd') {
expected.push(c == 'm');
}
j = j.saturating_add(run);
}
let mut slot = 0;
// A name's first letter may not continue a word; its last may not run on into a letter, nor
// (a digit) into a number.
let letter = |c: Option<&char>| c.is_some_and(|c| c.is_alphabetic());
let mut out = String::with_capacity(text.len());
let mut i = 0;
while let Some(&c) = chars.get(i) {
let fits = |n: &Vec<String>| {
let end = i.saturating_add(n.len());
let first = n.first().and_then(|e| e.chars().next());
let last = n.last().and_then(|e| e.chars().next());
chars.get(i..end).is_some_and(|t| t.iter().map(|c| fold(*c)).eq(n.iter().cloned()))
&& !(first.is_some_and(char::is_alphabetic) && letter(i.checked_sub(1).and_then(|p| chars.get(p))))
&& !match last {
Some(l) if l.is_ascii_digit() => chars.get(end).is_some_and(char::is_ascii_digit),
Some(l) if l.is_alphabetic() => letter(chars.get(end)),
_ => false,
}
};
let longest = names.iter().find(|(n, ..)| fits(n)).map(|(n, ..)| n.len());
let hit = longest.and_then(|len| {
let mut same = names.iter().filter(|(n, ..)| n.len() == len && fits(n));
let want = expected.get(slot).copied();
let all: Vec<_> = same.by_ref().collect();
all.iter().find(|(_, month, _)| Some(*month) == want).or_else(|| all.first()).copied()
});
match hit {
Some((n, month, english)) => {
if expected.get(slot) == Some(month) {
slot += 1;
}
// Apart from what touches it ("10月18"), but no space added at either end.
if out.ends_with(char::is_alphanumeric) {
out.push(' ');
}
out.push_str(english);
i = i.saturating_add(n.len());
if chars.get(i).is_some_and(|c| c.is_alphanumeric()) {
out.push(' ');
}
}
None => {
out.push(c);
i += 1;
}
}
}
out
}
/// `c` as names are compared: lower case, with the capital I and the Turkish dotted and dotless
/// i all "i", and a combining dot above (U+0307) dropped, so that "EKİM", "SALI" and "MAYIS" are
/// Turkish "Ekim", "Salı" and "Mayıs", which lower-casing alone makes "ekim" with a dotted i,
/// "sali" and "mayis" (#5303). The Greek final sigma is a sigma, since a capital Σ, which
/// lower-cases to σ on its own, ends "ΙΑΝΟΥΆΡΙΟΣ" for "Ιανουάριος". One piece for each char, so
/// positions in the text stay aligned.
fn fold(c: char) -> String {
match c {
'I' | 'ı' | 'İ' => "i".to_string(),
'ς' => "σ".to_string(),
_ => c.to_lowercase().filter(|&l| l != '\u{307}').collect(),
}
}
/// `s` [`fold`]ed char by char.
fn folded(s: &str) -> String {
s.chars().map(fold).collect()
}
/// Typed dates longer than this are not searched for names.
const MAX_DATE_TEXT_BYTES: usize = 1024;
/// Names longer than this are not looked for (settings are trusted, but a cap keeps the scan cheap).
const MAX_NAME_CHARS: usize = 32;
fn names() -> Names {
*NAMES.read().unwrap_or_else(std::sync::PoisonError::into_inner)
}
std::thread_local! {
/// Whether `util.printd` on this thread writes English names, whatever the date language.
static PRINTD_ENGLISH: std::cell::Cell<bool> = const { std::cell::Cell::new(false) };
}
/// Runs `run` with `util.printd` writing English month and weekday names when `english` (scripts
/// it starts carry this to their own thread): for an appearance whose fonts can't draw the date
/// language's names, which would come out as `?` (#5303). `util.scand` still reads both.
pub fn with_english_printd<R>(english: bool, run: impl FnOnce() -> R) -> R {
struct Restore(bool);
impl Drop for Restore {
fn drop(&mut self) {
PRINTD_ENGLISH.with(|e| e.set(self.0));
}
}
let _restore = Restore(PRINTD_ENGLISH.with(|e| e.replace(english)));
run()
}
/// Whether [`with_english_printd`] is on for this thread.
pub(crate) fn printd_english() -> bool {
PRINTD_ENGLISH.with(std::cell::Cell::get)
}
/// The names `util.printd` writes.
fn printd_names() -> Names {
if printd_english() { ENGLISH } else { names() }
}
/// `util.printd(cFormat, oDate)`: yyyy yy mmmm mmm mm m dddd ddd dd d HH H hh h MM M ss s tt,
/// and the numeric formats 0 (D:yyyymmddHHMMss), 1 (yyyy.mm.dd HH:MM:ss) and 2 (m/d/yy h:MM:ss tt).
pub(crate) fn printd(_: &JsValue, args: &[JsValue], ctx: &mut Context) -> JsResult<JsValue> {
@@ -161,6 +332,7 @@ pub(crate) fn printd(_: &JsValue, args: &[JsValue], ctx: &mut Context) -> JsResu
let (y, mo, day, wd, h, mi, sec) =
(part("getFullYear")?, part("getMonth")?, part("getDate")?, part("getDay")?, part("getHours")?, part("getMinutes")?, part("getSeconds")?);
let mut out = String::new();
let (months, months_short, days, days_short) = printd_names();
let b = fmt.as_bytes();
let mut i = 0;
while i < b.len() {
@@ -186,13 +358,13 @@ pub(crate) fn printd(_: &JsValue, args: &[JsValue], ctx: &mut Context) -> JsResu
}
}
b'm' => match run {
r if r >= 4 => out.push_str(MONTHS[mo as usize % 12]),
3 => out.push_str(&MONTHS[mo as usize % 12][..3]),
r if r >= 4 => out.push_str(months.get(mo.rem_euclid(12) as usize).copied().unwrap_or_default()),
3 => out.push_str(months_short.get(mo.rem_euclid(12) as usize).copied().unwrap_or_default()),
n => push_num(&mut out, mo + 1, n),
},
b'd' => match run {
r if r >= 4 => out.push_str(DAYS[wd as usize % 7]),
3 => out.push_str(&DAYS[wd as usize % 7][..3]),
r if r >= 4 => out.push_str(days.get(wd.rem_euclid(7) as usize).copied().unwrap_or_default()),
3 => out.push_str(days_short.get(wd.rem_euclid(7) as usize).copied().unwrap_or_default()),
n => push_num(&mut out, day, n),
},
b'H' => push_num(&mut out, h, run),
@@ -435,11 +607,13 @@ fn scan_date(fmt: &str, text: &str, this_year: i32) -> Option<Scanned> {
p += 1;
}
(ScanPart::Field { unit: DateUnit::MonthName, .. }, ScanToken::Letters(l)) => {
v.mo = Some(named(&MONTHS, l)?.saturating_add(1));
let (months, months_short, ..) = names();
v.mo = Some(named(&months, l).or_else(|| named(&months_short, l)).or_else(|| named(&MONTHS, l))?.saturating_add(1));
p += 1;
}
(ScanPart::Field { unit: DateUnit::Weekday, .. }, ScanToken::Letters(l)) => {
named(&DAYS, l)?;
let (.., days, days_short) = names();
named(&days, l).or_else(|| named(&days_short, l)).or_else(|| named(&DAYS, l))?;
p += 1;
}
(ScanPart::Field { unit: DateUnit::AmPm, .. }, ScanToken::Letters(l)) => {
@@ -509,10 +683,11 @@ fn scan_date(fmt: &str, text: &str, this_year: i32) -> Option<Scanned> {
/// The index of the name `word` is, in full or as its first three letters, in any case.
fn named(names: &[&str], word: &str) -> Option<u32> {
let word = word.to_lowercase();
let word = folded(word);
let i = names.iter().position(|n| {
let n = n.to_lowercase();
word == n || n.get(..3) == Some(word.as_str())
let n = folded(n);
// A short name may end in a dot ("Okt."); three letters may be cut from any name.
word == n || word == n.trim_end_matches('.') || n.chars().take(3).collect::<String>() == word
})?;
u32::try_from(i).ok()
}
@@ -524,6 +699,8 @@ pub(crate) fn scand(_: &JsValue, args: &[JsValue], ctx: &mut Context) -> JsResul
return Ok(JsValue::null());
};
let fmt = text(&arg(args, 0), ctx)?;
let (months, months_short, days, days_short) = names();
let typed = english_names(&typed, &fmt, [&months, &months_short, &days, &days_short]);
let date = JsDate::new(ctx);
let this_year = date.get_full_year(ctx)?.to_number(ctx)?;
let this_year = if this_year.is_finite() { this_year as i32 } else { 2000 };
crates/js/src/lib.rs
+1
View File
@@ -44,6 +44,7 @@ mod run;
#[cfg(test)]
pub(crate) use format::PRINTD_SCANNED;
use format::{printd, printf, printx, scand};
pub use format::{set_date_names, with_english_printd};
pub(crate) use globals::menu_item;
use globals::platform;
use host::{arg, as_number, error, function, s, text};
crates/js/src/run.rs
+3 -1
View File
@@ -129,11 +129,13 @@ pub fn run_shared(script: &str, event: &Event, doc: &DocInfo, fields: Arc<Vec<Fi
let (kept, skipped) = (&kept, &skipped);
#[cfg(not(target_arch = "wasm32"))]
{
// The script's thread writes dates as this one asked (`with_english_printd`).
let english = crate::format::printd_english();
std::thread::scope(|scope| {
let spawned = std::thread::Builder::new()
.name("pdfcraft-js".into())
.stack_size(SCRIPT_STACK)
.spawn_scoped(scope, || run_here(script, event, doc, fields, kept, skipped, limits));
.spawn_scoped(scope, || crate::format::with_english_printd(english, || run_here(script, event, doc, fields, kept, skipped, limits)));
match spawned {
Ok(thread) => thread.join().unwrap_or_else(|_| failed("the script stopped with an internal error".into())),
Err(e) => failed(format!("the script engine could not start: {e}")),
crates/measure/src/snap.rs
+6
View File
@@ -189,6 +189,12 @@ pub fn constrain(last: Point, point: Point) -> Point {
let angle = (v[1].atan2(v[0]) / std::f64::consts::FRAC_PI_4).round() * std::f64::consts::FRAC_PI_4;
[last[0] + length * angle.cos(), last[1] + length * angle.sin()]
}
/// Hold a proposed vertex level or plumb with the last vertex, whichever is nearer (a CAD
/// drawing's ortho mode): the vertex slides onto that axis rather than turning onto it.
pub fn ortho(last: Point, point: Point) -> Point {
let v = sub(point, last);
if v[0].abs() >= v[1].abs() { [point[0], last[1]] } else { [last[0], point[1]] }
}
struct Walker<'a> {
doc: &'a Document,
geometry: Geometry,
crates/measure/src/tests.rs
+10
View File
@@ -449,6 +449,16 @@ fn listing_skips_repeated_refs_and_caps_what_it_keeps() {
assert!(!listing.measurements.is_empty());
}
#[test]
fn ortho_holds_a_vertex_level_or_plumb_with_the_last() {
let last = [10.0, 20.0];
assert_eq!(snap::ortho(last, [50.0, 27.0]), [50.0, 20.0], "mostly across: level");
assert_eq!(snap::ortho(last, [-30.0, 13.0]), [-30.0, 20.0], "to the left too");
assert_eq!(snap::ortho(last, [14.0, 80.0]), [10.0, 80.0], "mostly up: plumb");
assert_eq!(snap::ortho(last, [8.0, -40.0]), [10.0, -40.0], "and down");
assert_eq!(snap::ortho(last, [30.0, 40.0]), [30.0, 20.0], "a tie stays level");
assert_eq!(snap::ortho(last, last), last);
}
#[test]
fn a_stream_over_the_byte_budget_uses_it_up_once() {
// 50 references to one Flate stream that inflates past the 16 MiB budget decode once.
let big = pdfcraft_cos::Stream::flate(Dict::new(), &vec![b' '; 17 << 20]);
crates/ocr/Cargo.toml
+4
View File
@@ -16,5 +16,9 @@ ocrs = { version = "0.13.1", default-features = false, features = ["rten"] }
rten = { version = "0.26.0", default-features = false, features = ["onnx_format", "rten_format"] }
thiserror.workspace = true
[target.'cfg(not(target_arch = "wasm32"))'.dependencies]
# The page image is handed to the external tesseract process as a PNG.
png = "0.18"
[dev-dependencies]
tempfile = "3.27"
crates/ocr/README.md
+104
View File
@@ -0,0 +1,104 @@
# pdfcraft-ocr
Layer L4 (may use `fonts` for the text layers' metrics): Scan & OCR — recognising the words in
a page raster and turning them back into page content (execution plan M10).
```rust
// The caller renders a page to pixels and hands them over:
let image = OcrImage::new(w, h, rgba)?; // validated by construction
let lines = recognizer.recognize(&image, &options)?; // Vec<Line>: words in reading order
let placed: Vec<PlacedWord> = …; // PlacedWord::place maps boxes to user space
// The editable output draws real glyphs: plan the words, register the display faces into the
// plan (`pdfcraft_edit::add_type3_fonts`), then generate the layer. An unregistered plan falls
// back to WinAnsi, and characters no registered face has become '?'.
let plan = TextPlan::for_words(placed.iter().map(|w| w.text.as_str()));
add_type3_fonts(&mut doc, page, &mut plan)?; // names the plan's fonts on the page
let layer = visible_text_layer(&placed, &plan); // visible text: the editable output
// The searchable layer needs no display fonts: the engine's own layer (engine::ocr::layer)
// keeps every Unicode character with empty Type3 programs and a ToUnicode map beyond WinAnsi.
```
- **Engines behind one trait.** A [`Recognizer`] reports its `id`, whether it is `available`,
the languages it reads, and reads `Vec<Line>` from an image. Two exist: the pure-Rust
`OcrsRecognizer` (the `ocrs` crate, MIT/Apache-2.0, with its pre-trained models,
CC-BY-SA-4.0, fetched by `cargo xtask models`; found via `$PDFCRAFT_MODELS` or `models/`
beside the executable — see ATTRIBUTION.toml), and — off the web build —
`tesseract::TesseractCli`, which drives an installed `tesseract` binary as an external
process: never linked, bundled or downloaded. Implementations are shared across threads
(`Send + Sync`); nothing spawns on wasm32.
- **The tesseract process is fenced in.** The program comes from a user-configured location or
the PATH, never from document data (the engine validates a configured path as an absolute
path to an existing executable file before it is used). The language code is allow-listed
(`tesseract::language_code`, 12 codes) before anything reaches a process; the page image
goes to a private temp file (a fresh 0700 directory holding a 0600 file on Unix) that is
deleted afterwards; the run has a 120 s timeout, a 64 MiB output cap and a 50 000-word
reading cap (an incomplete reading is rejected rather than applied); every failure comes back through `OcrError` with its cause named. A configured
location that is invalid fails closed (it is never replaced by the PATH search). Availability
is probed with `--list-langs` (its list is read from stdout, or from stderr where older
versions print it); a failed probe is remembered for 30 s, so an install that appears later
is found without a restart. Known limit: at the timeout or the output cap only the direct
child is killed; a wrapper script's own children may outlive it.
- **Confidence drives review.** One classifier (`band_for`) puts a word in the High
(≥ 90), Medium (70–89) or Low (< 70) band — the review overlay's colours, the legend and the
counts; the batch flag rule (`low_confidence`, default threshold 60) is deliberately a
separate threshold. The `ocrs` models report no confidence (its words carry `None`);
a reading whose confidence is unknown is treated as unknown, never as good.
- **Two engines can be merged (ROVER).** Strategies: `PrimaryOnly` (the default), and two
ensembles — `ConfidenceWeighted` (the secondary engine joins when the primary's mean
confidence is under 70 or unknown; an empty primary keeps the fast path) and `RoverVote`
(both engines always run). The merge lets every primary word adopt the best-overlapping
unused secondary word at IoU ≥ 0.5; the higher confidence wins text, box and confidence (a
tie keeps the primary; against a primary word of unknown confidence — ocrs — the secondary
wins only at 70 or more, `UNKNOWN_CONFIDENCE_BAR`), the survivor is named `"ROVER"`, and
unclaimed secondary words are
appended under their engine's name. A merge is capped at 100 M word-pair comparisons (over
it, the primary reading stands alone), and a failing partner degrades to the primary with a
recorded note — a page is never skipped because a partner could not read it.
- **Preprocessing between the raster and recognition**, a pure function in fixed order: DPI
normalization to 300 (only when one of the steps below is on, since they are calibrated for
it; with all of them off the raster is read exactly as rendered, and a scan at or above 300
is left alone), then the opt-in steps —
orientation (90°/180°/270° from projection-profile banding), deskew (± 5°, shear-scored,
below 0.1° is a no-op), denoise (3×3 median) and binarization (Sauvola, window 8, k 0.34).
Every geometric step composes one exact affine `InverseTransform`, and callers map every
word box back to the original raster before placing it. The heuristics are conservative and
panic-free: too small to judge, blank, or no clear winner is a no-op, never a guess.
- **Searchable output preserves Unicode without display fonts.** The engine uses empty
Type3 character programs and `/ToUnicode` maps for non-WinAnsi words, leaving the scan
unchanged. WinAnsi words use `/PCHelv`; the `/OCR` layer is fitted to each word's box.
- **Editable output uses display glyphs.** `visible_text_layer` writes visible text whose
size comes from the box height and whose horizontal scaling uses real font advances.
Beyond WinAnsi, attributed craft-fonts faces supply outline Type3 glyphs with `/ToUnicode`.
Uncovered characters become `?` and are reported in editable output notes; searchable
output retains them. The engine refuses nonfinite geometry or oversized input before
planning fonts: 4 MiB of text and 65,536 words, across all pages for editable export.
Empty geometry is skipped; rotated words carry `across`/`up` vectors and retain direction.
- **Hostile input is rejected, not panicked at.** `OcrImage` holds private, validated state:
non-zero sides, a 10 000-pixel side cap, a 64-megapixel area cap (checked arithmetic — the
counts come from documents, so they are untrusted), and an exact buffer length.
## Where it is wired
The engine's `ocr` module renders pages into `OcrImage`s, runs jobs (`OcrJob::run`) and applies
the words: searchable-image mode draws the invisible layer over the page's own image and leaves
that image untouched; editable mode writes a NEW `<name>_ocr.pdf` of visible text (the scan
image is not carried over, the source is never overwritten). Skip probes keep pages — and
whole files — that already contain text out of the work unless Force OCR overrides them. A
searchable result applies as one undoable step; the Editable text output opens the OCR Verify
screen first, and Scan & OCR ▸ Correct recognized text reviews any recognition there before it
is applied (confidence-coloured boxes, corrections, a per-language user dictionary — a
plain-text file in the preferences folder, so words added from a document persist on disk
outside it until removed — Re-OCR of a region or a page, Accept/Reject), a
multiple-file run writes searchable copies as it goes, and the automation tools `ocr_recognize`,
`ocr_words`, `ocr_status` and `ocr_recognize_files` expose recognition headlessly.
`ocr_words` with `retain_review` returns a bounded session-local handle; `ocr_review_apply`
applies text corrections at the stored original boxes through its stale-document guard,
or discards the result. Empty corrections remove words. Searchable acceptance is one undo
step; editable acceptance writes a separate file. `ocr_dictionary` reads or atomically
updates the UI's per-language dictionary format through an explicitly root-confined path.
Not yet: languages beyond the tested set (the `ocrs` models read only unaccented Latin; the
Tesseract side is bounded by its allow-list and whatever its installed language packs cover),
OCR in the browser (the tesseract module is compiled out for wasm32), the deep scan-cleanup
options (descreen, background removal, edge-shadow removal), and editable glyph coverage
beyond the available attributed faces.
crates/ocr/src/confidence.rs
+106
View File
@@ -0,0 +1,106 @@
//! Confidence: one classifier ([`band_for`]) drives the review overlay, the legend, the counts
//! and the uncertain-word navigation; the batch rule ([`low_confidence`]) is a separate
//! threshold with its own range check. The two rules are deliberately never merged.
/// The three confidence bands (the review overlay's green / yellow / red).
#[derive(Clone, Copy, Debug, PartialEq, Eq, PartialOrd, Ord, Hash)]
pub enum ConfidenceBand {
Low,
Medium,
High,
}
impl ConfidenceBand {
/// The legend line for this band, so the meaning never rests on colour alone.
pub fn legend(self) -> &'static str {
match self {
ConfidenceBand::High => "HIGH (>= 90%)",
ConfidenceBand::Medium => "MEDIUM (70-89%)",
ConfidenceBand::Low => "LOW (< 70%)",
}
}
}
/// The one classifier: `>= 90` is High, `70..=89` Medium, `< 70` Low. Out-of-range values
/// clamp (negative → Low, above 100 → High); NaN is Low.
pub fn band_for(confidence: f32) -> ConfidenceBand {
if confidence >= 90.0 {
ConfidenceBand::High
} else if confidence >= 70.0 {
ConfidenceBand::Medium
} else {
ConfidenceBand::Low
}
}
/// The batch rule, separate from [`band_for`]: a word is flagged when `0 <= conf <= threshold`
/// (default 60). Negative or above-threshold values are not flagged; NaN is not.
pub fn low_confidence(confidence: f32, threshold: f32) -> bool {
(0.0..=threshold).contains(&confidence)
}
/// A word whose confidence lands in the Low band — a suspect for review. A word without a
/// reported confidence has no signal and is never a suspect.
pub fn is_suspect(confidence: Option<f32>) -> bool {
confidence.is_some_and(|c| band_for(c) == ConfidenceBand::Low)
}
#[cfg(test)]
mod tests {
use super::*;
/// The boundary matrix: 89 and 90, 69 and 70 straddle the bands.
#[test]
fn bands_straddle_the_boundaries() {
assert_eq!(band_for(89.0), ConfidenceBand::Medium);
assert_eq!(band_for(90.0), ConfidenceBand::High);
assert_eq!(band_for(69.0), ConfidenceBand::Low);
assert_eq!(band_for(70.0), ConfidenceBand::Medium);
assert_eq!(band_for(0.0), ConfidenceBand::Low);
assert_eq!(band_for(100.0), ConfidenceBand::High);
}
/// Out-of-range values clamp, and NaN lands in the Low band instead of comparing equal to
/// nothing.
#[test]
fn out_of_range_confidences_clamp() {
assert_eq!(band_for(-0.5), ConfidenceBand::Low, "negative → Low");
assert_eq!(band_for(1000.0), ConfidenceBand::High, "above 100 → High");
assert_eq!(band_for(f32::NAN), ConfidenceBand::Low);
assert_eq!(band_for(f32::NEG_INFINITY), ConfidenceBand::Low);
assert_eq!(band_for(f32::INFINITY), ConfidenceBand::High);
}
/// The batch threshold is its own rule: everything in `0..=threshold` flags, including
/// words band_for calls Medium (60 < 70), and negatives never do.
#[test]
fn batch_threshold_is_separate_from_the_bands() {
assert!(low_confidence(60.0, 60.0), "at the threshold it flags");
assert!(low_confidence(0.0, 60.0));
assert!(!low_confidence(60.5, 60.0));
assert!(!low_confidence(-1.0, 60.0), "negative confidences are out of the rule's range");
assert!(!low_confidence(f32::NAN, 60.0));
// The rules disagree on real values: 65 is inside the Low band yet outside the batch
// rule with the default threshold (60), which is why the two must not be merged.
assert!(!low_confidence(65.0, 60.0));
assert_eq!(band_for(65.0), ConfidenceBand::Low);
}
/// Unconfident words are not suspects; Low-band words are.
#[test]
fn suspects_need_a_low_band_confidence() {
assert!(!is_suspect(None));
assert!(!is_suspect(Some(95.0)));
assert!(!is_suspect(Some(70.0)));
assert!(is_suspect(Some(69.9)));
assert!(is_suspect(Some(0.0)));
}
/// The legend names the thresholds, so the overlay never rests on colour alone.
#[test]
fn legend_text_matches_the_classifier() {
assert_eq!(ConfidenceBand::High.legend(), "HIGH (>= 90%)");
assert_eq!(ConfidenceBand::Medium.legend(), "MEDIUM (70-89%)");
assert_eq!(ConfidenceBand::Low.legend(), "LOW (< 70%)");
}
}
crates/ocr/src/lib.rs
+603 -192
View File
@@ -1,35 +1,50 @@
//! pdfcraft-ocr — Scan & OCR ▸ Recognize text (L4).
//!
//! Recognition runs the ocrs engine (MIT/Apache-2.0) with its pre-trained models (CC-BY-SA-4.0,
//! fetched by `cargo xtask models`; see ATTRIBUTION.toml). The caller renders a page to pixels;
//! [`Ocr::recognize`] finds the words in them, and [`text_layer`] turns words placed in user space
//! into page content: invisible text (rendering mode 3) over each word, so the page becomes a
//! The caller renders a page to pixels ([`OcrImage`]) and hands it to a [`Recognizer`]. Two
//! engines exist: the pure-Rust `OcrsRecognizer` (ocrs, MIT/Apache-2.0, with its pre-trained
//! models, CC-BY-SA-4.0, fetched by `cargo xtask models`; see ATTRIBUTION.toml) and — off the
//! web — `tesseract::TesseractCli`, which drives an installed `tesseract` binary as an external
//! process. `merge` combines two engines' readings (ROVER), `preprocess` cleans the raster up
//! between rendering and recognition, and [`text_layer`] turns words placed in user space into
//! page content: invisible text (rendering mode 3) over each word, so the page becomes a
//! searchable image (Acrobat's "Searchable Image (Exact)": the image is left untouched).
//!
//! The models read the Latin alphabet (English and other languages written without accents).
//! Visible editable output uses [`pdfcraft_fonts::TextPlan`] and optional craft-fonts glyph
//! outlines; unsupported visible characters become `?` and are counted. The engine's invisible
//! searchable layer uses empty Type3 programs and ToUnicode maps, preserving Unicode without
//! display fonts. WinAnsi-only invisible text keeps the standard Helvetica layout here.
//!
//! The ocrs models read the Latin alphabet (English and other languages written without
//! accents); Tesseract (the `tesseract` module, off the web build) reads whatever its installed
//! language packs cover.
#![deny(clippy::unwrap_used, clippy::expect_used, clippy::panic, clippy::unimplemented, clippy::todo, clippy::unreachable)]
use std::path::{Path, PathBuf};
pub mod confidence;
pub mod merge;
mod ocrs;
pub mod preprocess;
#[cfg(not(target_arch = "wasm32"))]
pub mod tesseract;
pub use confidence::{ConfidenceBand, band_for, is_suspect, low_confidence};
pub use merge::{MergeStrategy, StrategyOutcome, mean_confidence, recognize_with_strategy, rover_merge};
pub use ocrs::{ALPHABET, DETECTION_MODEL, LANGUAGES, Models, Ocr, OcrsRecognizer, RECOGNITION_MODEL};
pub use pdfcraft_fonts::TextPlan;
pub use pdfcraft_fonts::helvetica_width;
/// The model files, as named in ATTRIBUTION.toml.
pub const DETECTION_MODEL: &str = "text-detection.onnx";
pub const RECOGNITION_MODEL: &str = "text-recognition.onnx";
/// Hard cap on either side of an image any code in this crate will touch, in pixels; larger
/// images are rejected with [`OcrError::ImageTooLarge`] instead of being processed.
pub const MAX_SIDE: u32 = 10_000;
/// The recognition model's alphabet, as it was trained (ocrs-models' `DEFAULT_ALPHABET`): its
/// output classes follow this order. The ocrs crate's own copy has an `E` where the training had
/// `€`, which made a scanned "€250" read as "E250".
pub const ALPHABET: &str = " 0123456789!\"#$%&'()*+,-./:;<=>?@[\\]^_`{|}~€ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz";
/// The languages the models read (ISO 639-1); all use the Latin alphabet without accents.
pub const LANGUAGES: &[(&str, &str)] = &[("en", "English")];
/// Hard cap on an image's TOTAL area, in pixels (64 MP): sides under [`MAX_SIDE`] can still
/// multiply out to a raster no engine should have to read; larger images are rejected with
/// [`OcrError::ImageTooLarge`] instead of being processed.
pub const MAX_PIXELS: u32 = 64_000_000;
#[derive(Debug, thiserror::Error)]
pub enum OcrError {
/// Shown to end users (release packages ship the models; a source build fetches them with
/// `cargo xtask models`). The UI catalogs key this exact text.
#[error("the text recognition models are not installed (reinstall PdfCraft, or set PDFCRAFT_MODELS to the folder that holds them)")]
NoModels,
#[error("loading {0}: {1}")]
@@ -38,52 +53,93 @@ pub enum OcrError {
Recognize(String),
#[error("the image is empty")]
EmptyImage,
#[error("the image is larger than the {MAX_SIDE}-pixel side or {MAX_PIXELS}-pixel limit")]
ImageTooLarge,
#[error("the image buffer holds {got} bytes, expected {want} for {width}x{height} RGBA")]
ImageSize { got: usize, want: usize, width: u32, height: u32 },
#[error("the tesseract program is not available: {0}")]
NoTesseract(String),
#[error("tesseract did not finish within {0} seconds")]
Timeout(u64),
#[error("tesseract produced more than {0} bytes of output")]
OutputTooLarge(u64),
#[error("tesseract failed: {0}")]
Process(String),
}
/// Where the two model files are.
#[derive(Clone, Debug, PartialEq)]
pub struct Models {
pub detection: PathBuf,
pub recognition: PathBuf,
/// An RGBA8 raster, row-major, top-left origin: what the engines read. The fields are private
/// so the invariants (non-zero, capped, exactly `width * height * 4` bytes) hold by
/// construction: an [`OcrImage`] in hand has always been validated, whatever produced it.
#[derive(Clone, Debug, PartialEq, Eq)]
pub struct OcrImage {
width: u32,
height: u32,
rgba: Vec<u8>,
}
impl Models {
/// A complete model pair in `dir`, preferring current ONNX files over legacy RTEN files.
/// An incomplete update never mixes formats or hides an intact legacy pair.
pub fn in_dir(dir: &Path) -> Option<Models> {
[(DETECTION_MODEL, RECOGNITION_MODEL), ("text-detection.rten", "text-recognition.rten")].into_iter().find_map(|(detection, recognition)| {
let m = Models { detection: dir.join(detection), recognition: dir.join(recognition) };
(m.detection.is_file() && m.recognition.is_file()).then_some(m)
})
}
/// Look for the models: `$PDFCRAFT_MODELS`, then where the release packages install them
/// beside the executable ([`Models::dirs_beside_exe`]), then the source tree's `assets/models/`.
pub fn find() -> Option<Models> {
Self::search_dirs().iter().find_map(|d| Self::in_dir(d))
}
/// The directories [`Models::find`] looks in, in order.
pub fn search_dirs() -> Vec<PathBuf> {
let mut dirs = Vec::new();
if let Some(d) = std::env::var_os("PDFCRAFT_MODELS") {
dirs.push(PathBuf::from(d));
impl OcrImage {
/// Validate the sides ([`MAX_SIDE`]) and total area ([`MAX_PIXELS`]) and that `rgba` holds
/// exactly `width * height * 4` bytes (checked arithmetic; the counts come from documents,
/// so they are untrusted).
pub fn new(width: u32, height: u32, rgba: Vec<u8>) -> Result<OcrImage, OcrError> {
if width == 0 || height == 0 {
return Err(OcrError::EmptyImage);
}
if let Some(exe) = std::env::current_exe().ok().and_then(|e| e.parent().map(Path::to_path_buf)) {
dirs.extend(Self::dirs_beside_exe(&exe));
if width > MAX_SIDE || height > MAX_SIDE {
return Err(OcrError::ImageTooLarge);
}
let pixels = (width as usize).checked_mul(height as usize).ok_or(OcrError::ImageTooLarge)?;
if pixels > MAX_PIXELS as usize {
return Err(OcrError::ImageTooLarge);
}
match pixels.checked_mul(4) {
Some(want) if rgba.len() == want => Ok(OcrImage { width, height, rgba }),
Some(want) => Err(OcrError::ImageSize { got: rgba.len(), want, width, height }),
None => Err(OcrError::ImageTooLarge),
}
dirs.push(Path::new(env!("CARGO_MANIFEST_DIR")).join("../../assets/models"));
dirs
}
/// Where the release packages put the models, relative to the directory holding the
/// executable (packaging/*):
/// - `models/` beside it: the Windows MSI and portable zip;
/// - `../Resources/models`: the macOS app bundle (`Contents/MacOS` → `Contents/Resources`);
/// - `../share/pdfcraft/models`: the FHS-style trees (`bin/` → `share/`) of the Linux
/// deb/rpm/tar.gz/AppImage/Flatpak and the FreeBSD tarball, wherever they are installed.
pub fn dirs_beside_exe(exe_dir: &Path) -> Vec<PathBuf> {
vec![exe_dir.join("models"), exe_dir.join("../Resources/models"), exe_dir.join("../share/pdfcraft/models")]
/// The image's width, in pixels.
pub fn width(&self) -> u32 {
self.width
}
/// The image's height, in pixels.
pub fn height(&self) -> u32 {
self.height
}
/// The RGBA bytes, row-major, exactly `width * height * 4` of them.
pub fn rgba(&self) -> &[u8] {
&self.rgba
}
/// The smallest side, in pixels.
pub fn min_side(&self) -> u32 {
self.width.min(self.height)
}
/// One RGBA byte at integer pixel (`x`, `y`), edges clamped; 255 (white) outside. Only
/// whole-pixel positions and channel 0–3 make sense; anything else reads clamped.
pub fn byte(&self, x: f64, y: f64, ch: usize) -> u8 {
let stride = self.width as usize * 4;
if stride == 0 || self.height == 0 || ch > 3 {
return 255;
}
let xi = (x.round().max(0.0) as usize).min(self.width as usize - 1);
let yi = (y.round().max(0.0) as usize).min(self.height as usize - 1);
self.rgba.get(yi * stride + xi * 4 + ch).copied().unwrap_or(255)
}
/// The grayscale value of the pixel at (`x`, `y`), 0 (ink) … 255 (paper), with the borders
/// clamped (edges replicate). `None` only when the image is empty.
pub fn gray(&self, x: i64, y: i64) -> Option<u8> {
let x = x.clamp(0, self.width as i64 - 1);
let y = y.clamp(0, self.height as i64 - 1);
let row = y as usize * self.width as usize * 4;
let o = row + x as usize * 4;
let px = self.rgba.get(o..o + 4)?;
Some(((299 * px[0] as u32 + 587 * px[1] as u32 + 114 * px[2] as u32) / 1000) as u8)
}
}
@@ -92,6 +148,26 @@ impl Models {
pub struct Word {
pub text: String,
pub rect: [f32; 4],
/// How sure the engine is, 0–100, when it reports a confidence at all (`None`: the ocrs
/// engine does not).
pub confidence: Option<f32>,
/// Which engine read this word: the recogniser's [`Recognizer::id`], or `"ROVER"` when two
/// engines were merged and the surviving text is the merged choice.
pub source: String,
}
impl Word {
pub fn new(text: impl Into<String>, rect: [f32; 4], source: &str) -> Word {
Word { text: text.into(), rect, confidence: None, source: source.into() }
}
/// Set the confidence (builder style), clamped to the documented 0–100 scale (a negative
/// value is 0, anything over 100 is 100). NaN means no confidence was reported (`None`),
/// the same unknown the engines that report nothing carry.
pub fn with_confidence(mut self, confidence: f32) -> Word {
self.confidence = if confidence.is_nan() { None } else { Some(confidence.clamp(0.0, 100.0)) };
self
}
}
/// A recognised line of words, in reading order.
@@ -106,63 +182,34 @@ impl Line {
}
}
/// A loaded recogniser. Loading takes a moment; keep one and reuse it.
pub struct Ocr {
engine: ocrs::OcrEngine,
/// What a recogniser needs to know beyond the pixels.
#[derive(Clone, Debug, PartialEq, Eq)]
pub struct RecognizeOptions {
/// Language code from [`LANGUAGES`] (`"en"`, `"de"`, …). Engines map it to their own codes
/// (Tesseract: `tesseract::language_code`, allow-listed before anything reaches a process);
/// unknown codes fall back to the engine's default.
pub language: String,
}
impl Ocr {
pub fn load(models: &Models) -> Result<Ocr, OcrError> {
let load = |p: &Path| rten::Model::load_file(p).map_err(|e| OcrError::Load(p.display().to_string(), e.to_string()));
let params = ocrs::OcrEngineParams {
detection_model: Some(load(&models.detection)?),
recognition_model: Some(load(&models.recognition)?),
alphabet: Some(ALPHABET.into()),
..Default::default()
};
let engine = ocrs::OcrEngine::new(params).map_err(|e| OcrError::Load("ocr engine".into(), e.to_string()))?;
Ok(Ocr { engine })
impl Default for RecognizeOptions {
fn default() -> Self {
RecognizeOptions { language: "en".into() }
}
}
/// Load the models found by [`Models::find`].
pub fn find() -> Result<Ocr, OcrError> {
Self::load(&Models::find().ok_or(OcrError::NoModels)?)
}
/// Recognise the text in an RGBA (or RGB, or grey) image, `width` × `height` pixels.
pub fn recognize(&self, pixels: &[u8], width: u32, height: u32) -> Result<Vec<Line>, OcrError> {
if width == 0 || height == 0 || pixels.is_empty() {
return Err(OcrError::EmptyImage);
}
// ocrs wants 1 or 3 channels.
let rgb: std::borrow::Cow<[u8]> = if pixels.len() == (width * height * 4) as usize {
pixels.as_chunks::<4>().0.iter().flat_map(|p| [p[0], p[1], p[2]]).collect::<Vec<u8>>().into()
} else {
pixels.into()
};
let err = |e: &dyn std::fmt::Display| OcrError::Recognize(e.to_string());
let source = ocrs::ImageSource::from_bytes(&rgb, (width, height)).map_err(|e| err(&e))?;
let input = self.engine.prepare_input(source).map_err(|e| err(&e))?;
let found = self.engine.detect_words(&input).map_err(|e| err(&e))?;
let lines = self.engine.find_text_lines(&input, &found);
let read = self.engine.recognize_text(&input, &lines).map_err(|e| err(&e))?;
use ocrs::TextItem;
Ok(read
.into_iter()
.flatten()
.map(|line| Line {
words: line
.words()
.map(|w| {
let r = w.bounding_rect();
Word { text: w.to_string(), rect: [r.left() as f32, r.top() as f32, r.right() as f32, r.bottom() as f32] }
})
.filter(|w| !w.text.trim().is_empty())
.collect(),
})
.filter(|l| !l.words.is_empty())
.collect())
}
/// One text-recognition engine. Implementations are shared across threads
/// (`Arc<dyn Recognizer>`); `available` and `recognize` may spawn processes only off the web
/// build (see the `tesseract` module).
pub trait Recognizer: Send + Sync {
/// The engine's short name (`"ocrs"`, `"tesseract"`): what [`Word::source`] carries and
/// what settings and tools name it by.
fn id(&self) -> &'static str;
/// Whether this engine can run right now (models installed, binary found).
fn available(&self) -> bool;
/// The languages it reads, as `(code, name)` pairs (`"en"`, `"English"`).
fn languages(&self) -> Vec<(String, String)>;
/// Read the words in `image`, in reading order.
fn recognize(&self, image: &OcrImage, options: &RecognizeOptions) -> Result<Vec<Line>, OcrError>;
}
/// A word placed on a page, in PDF user space: the bottom-left corner of its box, and the
@@ -173,6 +220,10 @@ pub struct PlacedWord {
pub origin: [f64; 2],
pub across: [f64; 2],
pub up: [f64; 2],
/// Confidence 0–100, when the engine reported one.
pub confidence: Option<f32>,
/// Which engine read this word (see [`Word::source`]).
pub source: String,
}
impl PlacedWord {
@@ -183,7 +234,14 @@ impl PlacedWord {
let o = to_user(l, b);
let br = to_user(r, b);
let tl = to_user(l, t);
PlacedWord { text: word.text.clone(), origin: o, across: [br[0] - o[0], br[1] - o[1]], up: [tl[0] - o[0], tl[1] - o[1]] }
PlacedWord {
text: word.text.clone(),
origin: o,
across: [br[0] - o[0], br[1] - o[1]],
up: [tl[0] - o[0], tl[1] - o[1]],
confidence: word.confidence,
source: word.source.clone(),
}
}
}
@@ -214,32 +272,193 @@ fn num(v: f64) -> String {
if s == "-0" { "0".into() } else { s.into() }
}
/// Page content that writes `words` as invisible text in `/PCHelv` (standard Helvetica,
/// WinAnsiEncoding), each word stretched to its box so selection and search highlight the
/// right place. Marked content `/OCR` so it can be told apart from the page's own text.
pub fn text_layer(words: &[PlacedWord]) -> Vec<u8> {
/// One run of a word's planned characters in one Type3 font: the resource name, the codes to
/// show (one byte per character), and the run's start as an offset in em units from the word's
/// origin (the accumulated advances of the runs before it).
struct PlannedRun {
font: String,
codes: Vec<u8>,
start: f64,
}
/// The planned runs of word `i` (the same index [`pdfcraft_fonts::TextPlan::for_words`] planned
/// the words with), or `None` when the word is drawn in Helvetica: every character has a
/// WinAnsi code, or nothing could be planned/registered for it (the pre-Unicode output).
fn planned_runs(plan: &pdfcraft_fonts::TextPlan, word: usize) -> Option<(Vec<PlannedRun>, f64)> {
let enc = plan.encoding(word);
if enc.is_empty() || !plan.registered(enc) {
return None;
}
let mut runs: Vec<PlannedRun> = Vec::new();
let mut total = 0.0;
for &(f, code) in enc {
let font = plan.fonts[f].name.as_str();
match runs.last_mut() {
Some(last) if last.font == font => last.codes.push(code),
_ => runs.push(PlannedRun { font: font.to_string(), codes: vec![code], start: total }),
}
total += plan.advance(f, code);
}
(total.is_finite() && total > 0.0).then_some((runs, total))
}
/// Page content that writes `words` as VISIBLE text at their original boxes: the
/// editable-text output's page content. WinAnsi words are set in `/PCHelv` (standard
/// Helvetica); words with characters beyond WinAnsi are set in the plan's Type3 fonts, one run
/// per font. Each word fills its box — the font size comes from the box height and the
/// horizontal scaling is computed from the real advances of the font that draws the word
/// (Helvetica's approximated, the Type3 faces' exact) and emitted as an explicit `Tz`
/// percentage. Words whose box is empty (or whose text has no measurable width) are skipped; a
/// page that ends up with nothing simply shows nothing.
pub fn visible_text_layer(words: &[PlacedWord], plan: &pdfcraft_fonts::TextPlan) -> Vec<u8> {
visible_text_layer_at(words, plan, 0)
}
/// Visible text for words starting at `word_offset` in a shared document plan.
pub fn visible_text_layer_at(words: &[PlacedWord], plan: &pdfcraft_fonts::TextPlan, word_offset: usize) -> Vec<u8> {
// The rendering mode and the font are graphics state, which `ET` doesn't reset: without
// `q … Q` they would stay set for every later content stream on the page, so text added
// after OCR (a header or footer) drew invisibly (#3029).
let mut out = b"/OCR BMC\nq\nBT\n0 Tr\n/PCHelv 1 Tf\n".to_vec();
// The font and size the text state is set in, so a Tf is written only when they change.
// (The header's size-1 Helvetica covers layers of WinAnsi words only.)
let mut current: Option<(String, f64)> = Some(("PCHelv".to_string(), 1.0));
for (i, w) in words.iter().enumerate() {
let height = w.up[0].hypot(w.up[1]);
let across = w.across[0].hypot(w.across[1]);
let (ux, uy) = (w.across[0] / across, w.across[1] / across);
let (vx, vy) = (w.up[0] / height, w.up[1] / height);
if !across.is_finite()
|| !height.is_finite()
|| across <= 0.0
|| height <= 0.0
|| !ux.is_finite()
|| !vx.is_finite()
|| !w.origin.iter().all(|v| v.is_finite())
{
continue;
}
let size = height / BOX_EM;
let runs = planned_runs(plan, word_offset.saturating_add(i));
// The word's natural advance at this size: Helvetica's approximation, or the exact sum
// of the planned glyphs' widths.
let natural = runs.as_ref().map_or_else(|| helvetica_width(&w.text, size), |(_, total)| total * size);
if natural.is_nan() || natural <= 0.0 {
continue;
}
// Horizontal scaling as a percentage of the natural advance at this size, so the word
// lands exactly on its box (100 = no scaling; a long box on a short word stretches it).
let tz = (across / natural * 100.0).max(1.0);
// The baseline sits above the box's bottom edge by the descender depth.
let o = [w.origin[0] + vx * DESCENT * size, w.origin[1] + vy * DESCENT * size];
out.extend_from_slice(format!("{} Tz ", num(tz)).as_bytes());
match &runs {
None => {
if current.as_ref().is_some_and(|(f, s)| f != "PCHelv" || *s != size) {
out.extend_from_slice(format!("/PCHelv {} Tf ", num(size)).as_bytes());
current = Some(("PCHelv".to_string(), size));
}
out.extend_from_slice(format!("{} {} {} {} {} {} Tm ", num(ux), num(uy), num(vx), num(vy), num(o[0]), num(o[1])).as_bytes());
out.extend(pdfcraft_fonts::literal(&pdfcraft_fonts::win_ansi(&w.text)));
out.extend_from_slice(b" Tj\n");
}
Some((planned, total)) => {
for run in planned {
if current.as_ref().is_some_and(|(f, s)| *f != run.font || *s != size) {
out.extend_from_slice(format!("/{} {} Tf ", run.font, num(size)).as_bytes());
current = Some((run.font.clone(), size));
}
// The run's origin: the word's baseline plus the across vector scaled by
// the advances before this run (the stretch applies to runs alike).
let frac = run.start / total;
out.extend_from_slice(
format!(
"{} {} {} {} {} {} Tm ",
num(ux),
num(uy),
num(vx),
num(vy),
num(o[0] + w.across[0] * frac),
num(o[1] + w.across[1] * frac)
)
.as_bytes(),
);
out.extend(pdfcraft_fonts::literal(&run.codes));
out.extend_from_slice(b" Tj\n");
}
}
}
}
out.extend_from_slice(b"ET\nQ\nEMC\n");
out
}
/// Page content that writes `words` as invisible text (rendering mode 3), each word stretched
/// to its box so selection and search highlight the right place. WinAnsi words are set in
/// `/PCHelv` (standard Helvetica); words with characters beyond WinAnsi are set in the plan's
/// Type3 fonts, one run per font, with the same exact box fit. Marked content `/OCR` so it can
/// be told apart from the page's own text.
pub fn text_layer(words: &[PlacedWord], plan: &pdfcraft_fonts::TextPlan) -> Vec<u8> {
// `3 Tr` and the font are graphics state, which `ET` doesn't reset: without `q … Q` they
// would stay set for every later content stream on the page, so text added after OCR (a
// header or footer) drew invisibly (#3029).
let mut out = b"/OCR BMC\nq\nBT\n3 Tr\n/PCHelv 1 Tf\n".to_vec();
for w in words {
let width = helvetica_width(&w.text, 1.0);
let mut current: Option<(String, f64)> = Some(("PCHelv".to_string(), 1.0));
for (i, w) in words.iter().enumerate() {
let runs = planned_runs(plan, i);
let width = runs.as_ref().map_or_else(|| helvetica_width(&w.text, 1.0), |(_, total)| *total);
let height = w.up[0].hypot(w.up[1]);
if width <= 0.0 || height <= 0.0 {
let across = w.across[0].hypot(w.across[1]);
// Only positive, finite geometry reaches the content stream: a zero-sized box cannot
// be drawn, and a NaN or infinite one would put non-finite numbers on the page. (NaN
// fails every comparison, so the positivity checks already refuse it; the finiteness
// checks keep that property explicit.)
if width <= 0.0 || !(height > 0.0 && height.is_finite()) || !(across > 0.0 && across.is_finite()) || !w.origin.iter().all(|v| v.is_finite()) {
continue;
}
// The em square: the word's own ink (cap height or x-height, descenders or not) spans the
// box, so the text is as tall as the scanned word; its width is stretched to fit the word.
let (top, bottom) = ink_extent(&w.text);
// The em square. Helvetica words: the word's own ink (cap height or x-height,
// descenders or not) spans the box, so the text is as tall as the scanned word. Planned
// (Type3) words: those Helvetica letter heights do not describe the face, so the box spans
// the ascender-descender height. Either way the width is stretched to fit the word.
let (top, bottom) = if runs.is_some() { (BOX_EM - DESCENT, -DESCENT) } else { ink_extent(&w.text) };
let em = [w.up[0] / (top - bottom), w.up[1] / (top - bottom)];
let ax = [w.across[0] / width, w.across[1] / width];
let o = [w.origin[0] - em[0] * bottom, w.origin[1] - em[1] * bottom];
let m = [ax[0], ax[1], em[0], em[1], o[0], o[1]];
let nums: Vec<String> = m.iter().map(|v| num(*v)).collect();
out.extend_from_slice(nums.join(" ").as_bytes());
out.extend_from_slice(b" Tm ");
out.extend(pdfcraft_fonts::literal(&pdfcraft_fonts::win_ansi(&w.text)));
out.extend_from_slice(b" Tj\n");
match &runs {
None => {
let ax = [w.across[0] / width, w.across[1] / width];
if current.as_ref().is_some_and(|(f, s)| f != "PCHelv" || *s != 1.0) {
out.extend_from_slice(b"/PCHelv 1 Tf ");
current = Some(("PCHelv".to_string(), 1.0));
}
let m = [ax[0], ax[1], em[0], em[1], o[0], o[1]];
let nums: Vec<String> = m.iter().map(|v| num(*v)).collect();
out.extend_from_slice(nums.join(" ").as_bytes());
out.extend_from_slice(b" Tm ");
out.extend(pdfcraft_fonts::literal(&pdfcraft_fonts::win_ansi(&w.text)));
out.extend_from_slice(b" Tj\n");
}
Some((planned, total)) => {
for run in planned {
if current.as_ref().is_some_and(|(f, s)| *f != run.font || *s != 1.0) {
out.extend_from_slice(format!("/{} 1 Tf ", run.font).as_bytes());
current = Some((run.font.clone(), 1.0));
}
let m = [
w.across[0] / total,
w.across[1] / total,
em[0],
em[1],
o[0] + w.across[0] * run.start / total,
o[1] + w.across[1] * run.start / total,
];
let nums: Vec<String> = m.iter().map(|v| num(*v)).collect();
out.extend_from_slice(nums.join(" ").as_bytes());
out.extend_from_slice(b" Tm ");
out.extend(pdfcraft_fonts::literal(&run.codes));
out.extend_from_slice(b" Tj\n");
}
}
}
}
out.extend_from_slice(b"ET\nQ\nEMC\n");
out
@@ -253,10 +472,22 @@ mod tests {
fn places_words_through_the_mapping() {
// 2 pixels per point, page 612 × 792, y flipped.
let to_user = |x: f32, y: f32| [x as f64 / 2.0, 792.0 - y as f64 / 2.0];
let w = PlacedWord::place(&Word { text: "Hello".into(), rect: [100.0, 200.0, 300.0, 240.0] }, to_user);
let w = PlacedWord::place(&Word::new("Hello", [100.0, 200.0, 300.0, 240.0], "ocrs"), to_user);
assert_eq!(w.origin, [50.0, 672.0]);
assert_eq!(w.across, [100.0, 0.0]);
assert_eq!(w.up, [0.0, 20.0]);
assert_eq!(w.source, "ocrs");
assert_eq!(w.confidence, None);
}
/// Confidence and source survive placement.
#[test]
fn placed_words_carry_confidence_and_source() {
let to_user = |x: f32, y: f32| [x as f64, y as f64];
let w = Word::new("Hi", [1.0, 2.0, 3.0, 4.0], "tesseract").with_confidence(87.5);
let p = PlacedWord::place(&w, to_user);
assert_eq!(p.confidence, Some(87.5));
assert_eq!(p.source, "tesseract");
}
/// The text layer is Helvetica in WinAnsiEncoding: every character the model can recognise
@@ -267,10 +498,27 @@ mod tests {
assert_eq!(pdfcraft_fonts::first_undrawable(ALPHABET), None);
}
/// `with_confidence` is clamped to the documented 0–100 scale: negatives (and −inf) are 0,
/// anything over 100 (and +inf) is 100, in-scale values pass through, and NaN means no
/// confidence was reported — the same `None` unknown the unreporting engines carry.
#[test]
fn with_confidence_clamps_and_treats_nan_as_unknown() {
let c = |v: f32| Word::new("w", [0.0; 4], "ocrs").with_confidence(v).confidence;
assert_eq!(c(0.0), Some(0.0));
assert_eq!(c(50.0), Some(50.0));
assert_eq!(c(100.0), Some(100.0));
assert_eq!(c(-1.0), Some(0.0), "negatives clamp to 0");
assert_eq!(c(f32::NEG_INFINITY), Some(0.0));
assert_eq!(c(150.0), Some(100.0), "over 100 clamps to 100");
assert_eq!(c(f32::INFINITY), Some(100.0));
assert_eq!(c(f32::NAN), None, "NaN is unknown, not a confidence");
assert_eq!(c(f32::EPSILON), Some(f32::EPSILON), "in-scale values are untouched");
}
#[test]
fn text_layer_is_invisible_text_fitted_to_each_box() {
let w = PlacedWord { text: "Hi".into(), origin: [10.0, 20.0], across: [30.0, 0.0], up: [0.0, 9.3] };
let s = String::from_utf8(text_layer(&[w])).unwrap();
let w = PlacedWord { text: "Hi".into(), origin: [10.0, 20.0], across: [30.0, 0.0], up: [0.0, 9.3], confidence: None, source: "ocrs".into() };
let s = String::from_utf8(text_layer(&[w], &TextPlan::default())).unwrap();
assert!(s.contains("3 Tr") && s.contains("/PCHelv 1 Tf"), "{s}");
let width = helvetica_width("Hi", 1.0);
// "Hi" has no descender: its box spans the cap height, from the baseline up.
@@ -283,8 +531,8 @@ mod tests {
/// after it on the page starts from the graphics state it had before.
#[test]
fn the_layer_restores_the_graphics_state_it_changes() {
let w = PlacedWord { text: "Hi".into(), origin: [10.0, 20.0], across: [30.0, 0.0], up: [0.0, 9.3] };
let s = String::from_utf8(text_layer(&[w])).unwrap();
let w = PlacedWord { text: "Hi".into(), origin: [10.0, 20.0], across: [30.0, 0.0], up: [0.0, 9.3], confidence: None, source: "ocrs".into() };
let s = String::from_utf8(text_layer(&[w], &TextPlan::default())).unwrap();
let mut depth = 0_i32;
for token in s.split_ascii_whitespace() {
match token {
@@ -309,78 +557,200 @@ mod tests {
assert_eq!(ink_extent("Gallus.Ze@camtel.cm"), (CAP_HEIGHT, 0.0));
assert_eq!(ink_extent("Corporation"), (CAP_HEIGHT, -DESCENT));
assert_eq!(ink_extent("--"), (BOX_EM - DESCENT, -DESCENT));
let w = PlacedWord { text: "gap".into(), origin: [0.0, 100.0], across: [20.0, 0.0], up: [0.0, 7.3] };
let s = String::from_utf8(text_layer(&[w])).unwrap();
let w = PlacedWord { text: "gap".into(), origin: [0.0, 100.0], across: [20.0, 0.0], up: [0.0, 7.3], confidence: None, source: "ocrs".into() };
let s = String::from_utf8(text_layer(&[w], &TextPlan::default())).unwrap();
let em = 7.3 / (X_HEIGHT + DESCENT);
assert!(s.contains(&format!(" 0 0 {} 0 {} Tm (gap) Tj", num(em), num(100.0 + em * DESCENT))), "{s}");
}
/// A word whose box is not positive, finite geometry never reaches the content stream:
/// NaN, infinite and zero-sized boxes are dropped, so the layer never carries non-finite
/// numbers.
#[test]
fn text_layer_refuses_non_finite_and_degenerate_boxes() {
let word = |across: [f64; 2], up: [f64; 2], origin: [f64; 2]| PlacedWord {
text: "Hi".into(),
origin,
across,
up,
confidence: Some(90.0),
source: "tesseract".into(),
};
for (why, w) in [
("NaN across", word([f64::NAN, 0.0], [0.0, 9.3], [0.0; 2])),
("NaN up", word([30.0, 0.0], [f64::NAN, 1.0], [0.0; 2])),
("inf up", word([30.0, 0.0], [0.0, f64::INFINITY], [0.0; 2])),
("inf origin", word([30.0, 0.0], [0.0, 9.3], [0.0, f64::INFINITY])),
("zero across", word([0.0, 0.0], [0.0, 9.3], [0.0; 2])),
("NaN origin", word([30.0, 0.0], [0.0, 9.3], [0.0, f64::NAN])),
] {
let s = String::from_utf8(text_layer(&[w], &TextPlan::default())).unwrap();
assert_eq!(s, "/OCR BMC\nq\nBT\n3 Tr\n/PCHelv 1 Tf\nET\nQ\nEMC\n", "{why}: {s}");
assert!(!s.contains("NaN") && !s.contains("inf"), "{why}: {s}");
}
}
/// The editable-text layer draws visible text whose horizontal scaling is an explicit
/// percentage computed from real Helvetica metrics: `Tz` × natural advance = box width.
#[test]
fn visible_text_layer_scales_by_a_percentage_of_real_metrics() {
let w = PlacedWord { text: "Hi".into(), origin: [10.0, 20.0], across: [40.0, 0.0], up: [0.0, 9.3], confidence: None, source: "ocrs".into() };
let s = String::from_utf8(visible_text_layer(&[w], &TextPlan::default())).unwrap();
assert!(s.contains("0 Tr"), "visible, not invisible: {s}");
let size = 9.3 / BOX_EM;
let natural = helvetica_width("Hi", size);
let tz = 40.0 / natural * 100.0;
assert!(s.contains(&format!("{} Tz", num(tz))), "{s}");
assert!(s.contains("(Hi) Tj"), "{s}");
assert!(s.starts_with("/OCR BMC") && s.ends_with("EMC\n"));
}
/// Degenerate boxes and words with no measurable width are skipped, never divide by zero.
#[test]
fn visible_text_layer_skips_degenerate_words() {
let word = |across: [f64; 2], up: [f64; 2], text: &str| PlacedWord {
text: text.into(),
origin: [0.0; 2],
across,
up,
confidence: None,
source: "ocrs".into(),
};
let words = vec![
word([0.0, 0.0], [0.0, 9.0], "flat"),
word([10.0, 0.0], [0.0, 0.0], "short"),
word([f64::NAN, 0.0], [0.0, 9.0], "nan"),
word([10.0, 0.0], [0.0, 9.0], ""),
word([10.0, 0.0], [0.0, 9.0], "Hi"),
];
let s = String::from_utf8(visible_text_layer(&words, &TextPlan::default())).unwrap();
assert_eq!(s.matches("Tj").count(), 1, "only the one drawable word is written: {s}");
}
/// A word whose ORIGIN is not finite never reaches the visible layer either: a NaN or
/// infinite origin would put "NaN"/"inf" into the content stream.
#[test]
fn visible_text_layer_refuses_non_finite_origins() {
let word =
|origin: [f64; 2]| PlacedWord { text: "Hi".into(), origin, across: [10.0, 0.0], up: [0.0, 9.0], confidence: None, source: "ocrs".into() };
for (why, origin) in [("NaN x", [f64::NAN, 100.0]), ("inf y", [10.0, f64::INFINITY]), ("NaN both", [f64::NAN; 2])] {
let s = String::from_utf8(visible_text_layer(&[word(origin)], &TextPlan::default())).unwrap();
assert!(!s.contains("NaN") && !s.contains("inf"), "{why}: {s}");
assert_eq!(s.matches("Tj").count(), 0, "{why}: {s}");
}
}
/// After a Type3 word the text state goes back to Helvetica: the Latin words around a
/// planned word must not inherit its font.
#[test]
fn helvetica_is_restored_after_a_planned_word() {
if pdfcraft_fonts::CRAFT_FONTS.is_empty() {
eprintln!("skipping: built without craft-fonts (set CRAFT_FONTS_DIR to run it)");
return;
}
let word = |text: &str| PlacedWord {
text: text.into(),
origin: [10.0, 20.0],
across: [60.0, 0.0],
up: [0.0, 9.3],
confidence: None,
source: "ocrs".into(),
};
let words = [word("Hi"), word("日本"), word("Ho")];
let mut plan = TextPlan::for_words(["Hi", "日本", "Ho"]);
for (i, font) in plan.fonts.iter_mut().enumerate() {
font.name = format!("PCOcr{i}");
}
let s = String::from_utf8(text_layer(&words, &plan)).unwrap();
assert!(s.contains("/PCOcr0 1 Tf"), "{s}");
// The last Helvetica selection comes after the Type3 run, and the Latin word after it
// is drawn in Helvetica, not left in the planned font.
assert!(s.rfind("/PCOcr0 1 Tf").unwrap_or(0) < s.rfind("/PCHelv 1 Tf").unwrap_or(usize::MAX), "{s}");
// The `Q` closes the `q … Q` scope that keeps `3 Tr` from leaking into later content.
assert!(s.ends_with("Tm (Ho) Tj\nET\nQ\nEMC\n"), "{s}");
// The visible layer restores Helvetica with the word's size.
let v = String::from_utf8(visible_text_layer(&words, &plan)).unwrap();
assert!(v.rfind("/PCOcr0").unwrap_or(0) < v.rfind("/PCHelv").unwrap_or(usize::MAX), "{v}");
assert!(v.contains("(Ho) Tj"), "{v}");
}
/// Words with characters beyond WinAnsi draw in the plan's Type3 font, one run, with the
/// same exact box fit as the Helvetica words (the matrix x-axis spans across / advance).
#[test]
fn planned_words_draw_in_their_font_with_the_same_exact_fit() {
if pdfcraft_fonts::CRAFT_FONTS.is_empty() {
eprintln!("skipping: built without craft-fonts (set CRAFT_FONTS_DIR to run it)");
return;
}
let w =
PlacedWord { text: "日本".into(), origin: [10.0, 20.0], across: [60.0, 0.0], up: [0.0, 9.3], confidence: None, source: "ocrs".into() };
let mut plan = TextPlan::for_words(["日本"]);
// The names the registrar (pdfcraft_edit::add_type3_fonts) fills in — this crate
// cannot reach it, so the test sets them where it reads them.
for (i, font) in plan.fonts.iter_mut().enumerate() {
font.name = format!("PCOcr{i}");
}
let codes: Vec<u8> = plan.encoding(0).iter().map(|&(_, c)| c).collect();
assert_eq!(codes.len(), 2, "{codes:?}");
let total = plan.advance_of(plan.encoding(0));
let s = String::from_utf8(text_layer(std::slice::from_ref(&w), &plan)).unwrap();
assert!(s.contains("/PCOcr0 1 Tf"), "{s}");
assert!(s.contains(&format!("{} 0 0 10 10 22.1 Tm ", num(60.0 / total))), "{s}");
assert!(s.contains(&format!("Tm {} Tj\n", String::from_utf8_lossy(&pdfcraft_fonts::literal(&codes)))), "{s}");
// The visible layer: size from the box height, Tz from the Type3's own advance.
let v = String::from_utf8(visible_text_layer(std::slice::from_ref(&w), &plan)).unwrap();
let size = 9.3 / BOX_EM;
assert!(v.contains(&format!("/PCOcr0 {} Tf ", num(size))), "{v}");
assert!(v.contains(&format!("{} Tz", num(60.0 / (total * size) * 100.0))), "{v}");
}
/// Without planned characters (an empty plan: built without craft-fonts, or before the
/// fonts are registered) the WinAnsi path stands, '?' included.
#[test]
fn unplanned_words_fall_back_to_win_ansi_question_marks() {
let w =
PlacedWord { text: "日本".into(), origin: [10.0, 20.0], across: [60.0, 0.0], up: [0.0, 9.3], confidence: None, source: "ocrs".into() };
let s = String::from_utf8(text_layer(&[w], &TextPlan::default())).unwrap();
assert!(s.contains("(??) Tj"), "{s}");
assert!(!s.contains("PCOcr"), "{s}");
}
/// A character no face has a glyph for becomes the font's '?', still in the run, counted
/// by the plan.
#[test]
fn substitutions_are_written_as_the_font_s_question_mark() {
if pdfcraft_fonts::CRAFT_FONTS.is_empty() {
eprintln!("skipping: built without craft-fonts (set CRAFT_FONTS_DIR to run it)");
return;
}
let w = PlacedWord {
text: "日\u{1f4a9}語".into(),
origin: [0.0, 0.0],
across: [60.0, 0.0],
up: [0.0, 9.3],
confidence: None,
source: "ocrs".into(),
};
let mut plan = TextPlan::for_words(["日\u{1f4a9}語"]);
for (i, font) in plan.fonts.iter_mut().enumerate() {
font.name = format!("PCOcr{i}");
}
assert_eq!(plan.missing(), 1, "the emoji has no glyph anywhere");
assert_eq!(plan.encoding(0).len(), 3, "it still gets an encoding: the font's ?");
let codes: Vec<u8> = plan.encoding(0).iter().map(|&(_, c)| c).collect();
let s = String::from_utf8(text_layer(&[w], &plan)).unwrap();
assert!(s.contains(&format!("Tm {} Tj\n", String::from_utf8_lossy(&pdfcraft_fonts::literal(&codes)))), "{s}");
}
#[test]
fn rotated_pages_keep_the_reading_direction() {
// A page turned 90°: image x runs up the page.
let to_user = |x: f32, y: f32| [y as f64, x as f64];
let w = PlacedWord::place(&Word { text: "Up".into(), rect: [0.0, 0.0, 50.0, 10.0] }, to_user);
let w = PlacedWord::place(&Word::new("Up", [0.0, 0.0, 50.0, 10.0], "ocrs"), to_user);
assert_eq!(w.across, [0.0, 50.0]);
assert_eq!(w.up, [-10.0, 0.0]);
}
/// The current ONNX pair wins when an installation also retains both legacy models.
#[test]
fn model_discovery_prefers_the_complete_onnx_pair() {
let dir = tempfile::tempdir().unwrap();
for file in ["text-detection.onnx", "text-recognition.onnx"] {
std::fs::write(dir.path().join(file), b"model").unwrap();
}
let expected = Some(Models { detection: dir.path().join("text-detection.onnx"), recognition: dir.path().join("text-recognition.onnx") });
assert_eq!(Models::in_dir(dir.path()), expected, "a complete ONNX pair is sufficient");
for file in ["text-detection.rten", "text-recognition.rten"] {
std::fs::write(dir.path().join(file), b"model").unwrap();
}
assert_eq!(Models::in_dir(dir.path()), expected, "the complete ONNX pair takes precedence over legacy models");
}
/// An interrupted ONNX update still permits an intact legacy pair in the same directory.
#[test]
fn model_discovery_falls_back_to_legacy_when_the_onnx_pair_is_incomplete() {
for current in ["text-detection.onnx", "text-recognition.onnx"] {
let dir = tempfile::tempdir().unwrap();
for file in [current, "text-detection.rten", "text-recognition.rten"] {
std::fs::write(dir.path().join(file), b"model").unwrap();
}
assert_eq!(
Models::in_dir(dir.path()),
Some(Models { detection: dir.path().join("text-detection.rten"), recognition: dir.path().join("text-recognition.rten") }),
"{current} alone must not hide a complete legacy pair"
);
}
}
/// Detection and recognition must come from one complete format pair, never a mixed update.
#[test]
fn model_discovery_refuses_mixed_format_pairs() {
for pair in [["text-detection.onnx", "text-recognition.rten"], ["text-detection.rten", "text-recognition.onnx"]] {
let dir = tempfile::tempdir().unwrap();
for file in pair {
std::fs::write(dir.path().join(file), b"model").unwrap();
}
assert_eq!(Models::in_dir(dir.path()), None, "{pair:?} is not a complete model pair");
}
}
/// Existing source builds and PDFCRAFT_MODELS overrides retain their complete RTEN pair.
#[test]
fn model_discovery_keeps_legacy_only_installations() {
let dir = tempfile::tempdir().unwrap();
assert_eq!(Models::in_dir(dir.path()), None);
std::fs::write(dir.path().join("text-detection.rten"), b"model").unwrap();
assert_eq!(Models::in_dir(dir.path()), None, "one legacy model is incomplete");
std::fs::write(dir.path().join("text-recognition.rten"), b"model").unwrap();
assert_eq!(
Models::in_dir(dir.path()),
Some(Models { detection: dir.path().join("text-detection.rten"), recognition: dir.path().join("text-recognition.rten") })
);
}
/// #103: every release package's layout puts the models where the installed app looks.
/// Mirrors packaging/{windows/package.ps1,macos/package.sh,linux/package.sh,freebsd/package.sh}.
#[test]
@@ -443,6 +813,47 @@ mod tests {
assert!(word.rect[0] >= 10.0 && word.rect[0] < 60.0, "{word:?}");
}
/// The recognised words name their engine.
#[test]
fn ocrs_recognizer_names_its_words() {
let Ok(rec) = OcrsRecognizer::find() else {
eprintln!("skipped: OCR models not installed");
return;
};
assert_eq!(rec.id(), "ocrs");
assert!(rec.languages().iter().any(|(c, n)| c == "en" && n == "English"), "{:?}", rec.languages());
let (w, h, px) = test_image::hello();
let image = OcrImage::new(w, h, px).unwrap();
let lines = rec.recognize(&image, &RecognizeOptions::default()).unwrap();
let words: Vec<&Word> = lines.iter().flat_map(|l| &l.words).collect();
assert!(!words.is_empty());
assert!(words.iter().all(|w| w.source == "ocrs"), "{words:?}");
}
/// Hostile images are rejected with errors, never panics: zero sides, sides over the cap,
/// totals over the area cap (even with legal sides), buffers that do not fit, counts that
/// overflow.
#[test]
fn hostile_image_dimensions_are_rejected_not_panicked_at() {
assert!(matches!(OcrImage::new(0, 10, vec![]), Err(OcrError::EmptyImage)));
assert!(matches!(OcrImage::new(10, 0, vec![]), Err(OcrError::EmptyImage)));
assert!(matches!(OcrImage::new(u32::MAX, u32::MAX, vec![]), Err(OcrError::ImageTooLarge)));
assert!(matches!(OcrImage::new(MAX_SIDE + 1, 1, vec![0; 4]), Err(OcrError::ImageTooLarge)));
// 10 000 × 7 000 = 70 MP: legal on both sides, over the 64 MP area cap (no allocation
// is needed to reject it — the buffer is never inspected).
assert!(matches!(OcrImage::new(MAX_SIDE, 7000, vec![]), Err(OcrError::ImageTooLarge)));
// 8 000 × 8 000 = exactly the area cap: accepted shape (the short buffer proves the
// cap check passed), while one more row is refused.
assert!(matches!(OcrImage::new(8000, 8000, vec![0; 16]), Err(OcrError::ImageSize { .. })));
assert!(matches!(OcrImage::new(8000, 8001, vec![0; 16]), Err(OcrError::ImageTooLarge)));
assert!(matches!(OcrImage::new(2, 2, vec![0; 15]), Err(OcrError::ImageSize { .. })));
let ok = OcrImage::new(2, 2, vec![255; 16]).unwrap();
assert_eq!((ok.width(), ok.height()), (2, 2));
assert_eq!(ok.rgba().len(), 16);
assert_eq!(ok.gray(5, 5), Some(255), "clamped reads stay inside");
assert_eq!(ok.gray(-1, -1), Some(255));
}
mod test_image {
/// "HELLO WORLD" drawn with blocky 5×7 letters, 4 pixels per dot, black on white.
pub fn hello() -> (u32, u32, Vec<u8>) {
crates/ocr/src/merge.rs
+583
View File
@@ -0,0 +1,583 @@
//! Combining engines. "ROVER" merges two engines' readings of one page: every primary word
//! adopts the best-overlapping unused secondary word when their boxes agree enough (IoU, below);
//! the higher confidence wins the text, box and confidence (a tie keeps the primary; against a
//! primary of unknown confidence the secondary must reach [`UNKNOWN_CONFIDENCE_BAR`]) and the
//! surviving word is named `"ROVER"`; secondary words nothing claimed are appended, keeping
//! their own engine's name.
use crate::{Line, OcrError, OcrImage, RecognizeOptions, Recognizer, Word};
/// How the chosen engines combine. The default is [`MergeStrategy::PrimaryOnly`] with the
/// default engine (ocrs), which is today's behavior.
#[derive(Clone, Copy, Debug, Default, PartialEq, Eq, Hash)]
pub enum MergeStrategy {
/// Only the primary engine runs.
#[default]
PrimaryOnly,
/// The secondary engine joins only when the primary's reading looks weak: its mean word
/// confidence is under 70, or its confidence is unknown (words were read but none reports
/// a confidence — the ocrs engine). An unknown reading is never counted as 100; an empty
/// primary keeps the fast path (no words, nothing to double-check).
ConfidenceWeighted,
/// Both engines always run and their readings merge (with no secondary engine this
/// degrades to primary only).
RoverVote,
}
/// The mean of the confidences the words report, 0–100; `None` when the reading's confidence
/// is UNKNOWN — words were read but none reports a confidence (the ocrs engine's words).
/// Unknown is never counted as 100: there is no low-confidence signal, but a reading whose
/// confidence nobody knows is not therefore confident, so a confidence-weighted strategy
/// answers it by asking the secondary engine. An empty reading is `Some(100.0)`: no words
/// were read, so there is nothing to double-check and the fast path stands.
pub fn mean_confidence(lines: &[Line]) -> Option<f32> {
let mut total = 0usize;
let mut reported = (0.0f64, 0usize);
for word in lines.iter().flat_map(|l| &l.words) {
total += 1;
if let Some(c) = word.confidence {
reported.0 += c as f64;
reported.1 += 1;
}
}
match (total, reported.1) {
(0, _) => Some(100.0),
(_, 0) => None,
(_, n) => Some((reported.0 / n as f64) as f32),
}
}
/// Intersection over union of two `[left, top, right, bottom]` boxes. An empty intersection is
/// 0; degenerate or NaN boxes give 0 rather than panicking or poisoning the comparison.
pub fn iou(a: &[f32; 4], b: &[f32; 4]) -> f64 {
let l = a[0].max(b[0]);
let t = a[1].max(b[1]);
let r = a[2].min(b[2]);
let btm = a[3].min(b[3]);
if !(r > l && btm > t) {
return 0.0; // disjoint, touching, inverted, or NaN (all comparisons false)
}
let inter = (r - l) as f64 * (btm - t) as f64;
let area = |x: &[f32; 4]| ((x[2] - x[0]).max(0.0) as f64) * ((x[3] - x[1]).max(0.0) as f64);
let union = area(a) + area(b) - inter;
if union <= 0.0 {
return 0.0;
}
inter / union
}
/// The most primary×secondary word comparisons one ROVER merge will attempt. Known limit: a
/// merge over this cap is skipped — the primary reading stands alone, and the skip is noted,
/// never silent — so two enormous readings cannot turn the merge into quadratic work without
/// end. A real page is a few hundred words on each side, orders of magnitude under the cap.
pub const ROVER_MAX_COMPARISONS: usize = 100_000_000;
/// Whether the two readings are too large to merge: their word counts multiply past
/// [`ROVER_MAX_COMPARISONS`]. Shared by [`rover_merge`] (which then keeps the primary) and
/// [`recognize_with_strategy`] (which then notes the skip).
fn over_cap(primary: &[Line], secondary: &[Line]) -> bool {
let primary_words: usize = primary.iter().map(|l| l.words.len()).sum();
let secondary_words: usize = secondary.iter().map(|l| l.words.len()).sum();
primary_words.saturating_mul(secondary_words) > ROVER_MAX_COMPARISONS
}
/// The confidence a secondary word needs to replace a primary word whose confidence is
/// unknown (the ocrs engine reports none). It is the bar under which a reading counts as weak
/// ([`MergeStrategy::ConfidenceWeighted`] asks the second engine below it): a word the second
/// engine itself calls weak does not displace a reading nobody scored.
pub const UNKNOWN_CONFIDENCE_BAR: f32 = 70.0;
/// True when the secondary word's confidence `a` beats the primary's `b`. Both known: the
/// strictly higher one wins (a tie keeps the primary). A known confidence against an unknown
/// primary wins only at or above [`UNKNOWN_CONFIDENCE_BAR`]: an unknown confidence is neither
/// 0 nor 100, so a 5% reading must not replace it, while a confident one may. NaN never wins,
/// and with no confidence on the secondary side the primary stands.
fn higher(a: Option<f32>, b: Option<f32>) -> bool {
match (a, b) {
(Some(a), Some(b)) => a.partial_cmp(&b) == Some(std::cmp::Ordering::Greater),
(Some(a), None) => a >= UNKNOWN_CONFIDENCE_BAR,
_ => false,
}
}
/// Merge the two engines' readings. Primary words keep their order and lines; a word is
/// replaced by its overlapping secondary (IoU >= 0.5) only when that secondary is more
/// confident, and either way the merged word's [`Word::source`] is `"ROVER"`. Secondary words
/// no primary claimed are appended, in their own reading order and lines, under their own
/// engine's name (`secondary_id`). Known limit: over [`ROVER_MAX_COMPARISONS`] comparisons
/// (word counts multiplied) the primary reading is kept as is, unmerged; the strategy runner
/// names that skip in a note.
pub fn rover_merge(primary: Vec<Line>, secondary: Vec<Line>, secondary_id: &str) -> Vec<Line> {
if over_cap(&primary, &secondary) {
return primary; // over the comparison cap: the primary stands alone
}
let mut primary = primary;
// The secondary's words, marked `None` once a primary word claimed them, grouped by their
// own lines so the unclaimed ones can be appended in order.
let mut unused: Vec<Vec<Option<Word>>> = secondary.into_iter().map(|l| l.words.into_iter().map(Some).collect()).collect();
for line in &mut primary {
for word in &mut line.words {
// The best-overlapping unused secondary word, if any beats IoU 0.5.
let mut best: Option<(f64, usize, usize)> = None;
for (li, words) in unused.iter().enumerate() {
for (wi, slot) in words.iter().enumerate() {
let Some(w) = slot else { continue };
let score = iou(&word.rect, &w.rect);
if score >= 0.5 && best.is_none_or(|(b, _, _)| score > b) {
best = Some((score, li, wi));
}
}
}
let Some((_, li, wi)) = best else { continue };
let claimed = unused.get_mut(li).and_then(|l| l.get_mut(wi)).and_then(|slot| slot.take());
let Some(claim) = claimed else { continue };
if higher(claim.confidence, word.confidence) {
*word = Word { source: "ROVER".into(), ..claim };
} else {
// Tie (or the primary wins): keep the primary's text, box and confidence, but
// record that this reading is the engines' agreed one.
word.source = "ROVER".into();
}
}
}
// Append the secondary words nothing claimed, line by line, under their engine's name
// (`secondary_id` backfills words that name no source of their own).
let mut merged = primary;
for line in unused {
let words: Vec<Word> = line
.into_iter()
.flatten()
.map(|mut w| {
if w.source.is_empty() {
w.source = secondary_id.into();
}
w
})
.collect();
if !words.is_empty() {
merged.push(Line { words });
}
}
merged
}
/// What a strategy run produced: the merged (or primary-only) reading, whether the secondary
/// engine's reading is part of it, and the notes recorded along the way.
#[derive(Clone, Debug, PartialEq, Default)]
pub struct StrategyOutcome {
pub lines: Vec<Line>,
/// Whether the secondary engine's reading is part of `lines`: true only when the merge
/// actually happened. A secondary that failed, or whose reading was discarded over the
/// comparison cap, is `false`, with a note in [`StrategyOutcome::notes`] saying why.
pub secondary_ran: bool,
/// Why the page's reading is partial, if it is. The secondary engine is an enhancement,
/// never a gate: when it is configured but fails, the primary reading is kept and the
/// failure is noted here — a page is never skipped because a partner could not read it.
/// Only a primary failure is an [`OcrError`].
pub notes: Vec<String>,
}
/// The note recorded when an ensemble partner fails: the page keeps the primary reading and
/// the cause is named for the report.
fn degraded_note(id: &str, error: &OcrError) -> String {
format!("the {id} engine failed ({error}) — the page keeps the primary reading alone")
}
/// The note recorded when the two readings are too large to merge: the page keeps the primary
/// reading alone and the discarded partner reading is named, never silent.
fn cap_note(id: &str, primary_words: usize, secondary_words: usize) -> String {
format!(
"the readings were too large to merge ({primary_words} × {secondary_words} comparisons, over the cap of {ROVER_MAX_COMPARISONS}) — the page keeps the primary reading alone and the {id} reading is unused"
)
}
/// Run the engines per `strategy` and merge. See [`StrategyOutcome`] for what comes back.
pub fn recognize_with_strategy(
primary: &dyn Recognizer,
secondary: Option<&dyn Recognizer>,
strategy: MergeStrategy,
image: &OcrImage,
options: &RecognizeOptions,
) -> Result<StrategyOutcome, OcrError> {
// The shared shape of the ensemble strategies: the primary has read, the secondary joins
// or fails (a failure degrades to the primary, with a note).
let join = |p: Vec<Line>, sec: &dyn Recognizer| match sec.recognize(image, options) {
// Over the comparison cap the merge is skipped: the secondary's reading was read but
// is not part of the result, so the outcome says so — primary only, honestly not
// merged, with the skip named.
Ok(s) if over_cap(&p, &s) => {
let (primary_words, secondary_words) = (p.iter().map(|l| l.words.len()).sum::<usize>(), s.iter().map(|l| l.words.len()).sum::<usize>());
StrategyOutcome { lines: p, secondary_ran: false, notes: vec![cap_note(sec.id(), primary_words, secondary_words)] }
}
Ok(s) => StrategyOutcome { lines: rover_merge(p, s, sec.id()), secondary_ran: true, notes: Vec::new() },
Err(e) => StrategyOutcome { lines: p, secondary_ran: false, notes: vec![degraded_note(sec.id(), &e)] },
};
match strategy {
MergeStrategy::PrimaryOnly => Ok(StrategyOutcome { lines: primary.recognize(image, options)?, secondary_ran: false, notes: Vec::new() }),
MergeStrategy::RoverVote => match secondary {
None => Ok(StrategyOutcome { lines: primary.recognize(image, options)?, secondary_ran: false, notes: Vec::new() }),
Some(sec) => {
let p = primary.recognize(image, options)?;
Ok(join(p, sec))
}
},
MergeStrategy::ConfidenceWeighted => {
let p = primary.recognize(image, options)?;
match mean_confidence(&p) {
// Confident enough — or an empty reading: the primary stands alone.
Some(mean) if mean >= UNKNOWN_CONFIDENCE_BAR => Ok(StrategyOutcome { lines: p, secondary_ran: false, notes: Vec::new() }),
// A weak mean, or an unknown confidence (words, none reported): the secondary
// runs.
_ => match secondary {
None => Ok(StrategyOutcome { lines: p, secondary_ran: false, notes: Vec::new() }),
Some(sec) => Ok(join(p, sec)),
},
}
}
}
}
#[cfg(test)]
mod tests {
use super::*;
use std::sync::atomic::{AtomicUsize, Ordering};
/// A fake engine: returns canned lines, counts recognize calls, never available.
struct Fake {
id: &'static str,
lines: Vec<Line>,
calls: AtomicUsize,
fail: bool,
}
impl Fake {
fn new(id: &'static str, words: &[(&str, [f32; 4], f32)]) -> Fake {
Fake {
id,
lines: vec![Line { words: words.iter().map(|(t, r, c)| Word::new(*t, *r, id).with_confidence(*c)).collect() }],
calls: AtomicUsize::new(0),
fail: false,
}
}
fn empty(id: &'static str) -> Fake {
Fake { id, lines: Vec::new(), calls: AtomicUsize::new(0), fail: false }
}
/// An engine like ocrs: words, but no confidence reported on any of them.
fn unknown(id: &'static str, n: usize) -> Fake {
Fake {
id,
lines: vec![Line {
words: (0..n).map(|i| Word::new(format!("w{i}"), [i as f32 * 10.0, 0.0, i as f32 * 10.0 + 8.0, 10.0], id)).collect(),
}],
calls: AtomicUsize::new(0),
fail: false,
}
}
}
impl Recognizer for Fake {
fn id(&self) -> &'static str {
self.id
}
fn available(&self) -> bool {
!self.fail
}
fn languages(&self) -> Vec<(String, String)> {
vec![]
}
fn recognize(&self, _image: &OcrImage, _options: &RecognizeOptions) -> Result<Vec<Line>, OcrError> {
self.calls.fetch_add(1, Ordering::SeqCst);
if self.fail {
return Err(OcrError::Recognize("the fake engine failed".into()));
}
Ok(self.lines.clone())
}
}
fn image() -> OcrImage {
OcrImage::new(4, 4, vec![255; 64]).unwrap()
}
fn words(lines: &[Line]) -> Vec<&Word> {
lines.iter().flat_map(|l| &l.words).collect()
}
#[test]
fn iou_of_disjoint_touching_and_nan_boxes_is_zero() {
let a = [0.0, 0.0, 10.0, 10.0];
assert_eq!(iou(&a, &[20.0, 0.0, 30.0, 10.0]), 0.0, "disjoint");
assert_eq!(iou(&a, &[10.0, 0.0, 20.0, 10.0]), 0.0, "touching edges are an empty intersection");
assert_eq!(iou(&a, &[f32::NAN, 0.0, 10.0, 10.0]), 0.0, "NaN boxes score 0, not a panic");
assert_eq!(iou(&a, &a), 1.0, "identical boxes");
assert!((iou(&a, &[5.0, 0.0, 15.0, 10.0]) - 1.0 / 3.0).abs() < 1e-9, "half overlap is IoU 1/3");
}
/// With nothing on the primary side, every secondary word is appended under the secondary
/// engine's own name.
#[test]
fn rover_appends_everything_when_the_primary_is_empty() {
let primary = Vec::new();
let secondary = vec![Line { words: vec![Word::new("sole", [0.0, 0.0, 9.0, 9.0], "tesseract").with_confidence(80.0)] }];
let merged = rover_merge(primary, secondary, "tesseract");
assert_eq!(words(&merged).len(), 1);
assert_eq!(merged[0].words[0].text, "sole");
assert_eq!(merged[0].words[0].source, "tesseract", "unclaimed words keep their own engine");
}
/// Non-overlapping secondary words never displace primary words; they are appended.
#[test]
fn rover_appends_non_overlapping_secondary_words() {
let primary = vec![Line { words: vec![Word::new("kept", [0.0, 0.0, 10.0, 10.0], "ocrs").with_confidence(50.0)] }];
let secondary = vec![Line { words: vec![Word::new("extra", [100.0, 100.0, 120.0, 110.0], "tesseract").with_confidence(99.0)] }];
let merged = rover_merge(primary, secondary, "tesseract");
let w = words(&merged);
assert_eq!(w.len(), 2);
assert_eq!((w[0].text.as_str(), w[0].source.as_str()), ("kept", "ocrs"), "the more confident but disjoint word does not win");
assert_eq!((w[1].text.as_str(), w[1].source.as_str()), ("extra", "tesseract"));
}
/// The higher-confidence word of an overlapping pair wins text, box and confidence, and is
/// named ROVER.
#[test]
fn rover_higher_confidence_wins_and_is_named_rover() {
let primary = vec![Line { words: vec![Word::new("helo", [0.0, 0.0, 10.0, 10.0], "ocrs").with_confidence(60.0)] }];
let secondary = vec![Line { words: vec![Word::new("hello", [1.0, 0.0, 11.0, 10.0], "tesseract").with_confidence(95.0)] }];
let merged = rover_merge(primary, secondary, "tesseract");
let w = words(&merged);
assert_eq!(w.len(), 1, "the secondary word was claimed, not appended");
assert_eq!(w[0].text, "hello");
assert_eq!(w[0].rect, [1.0, 0.0, 11.0, 10.0]);
assert_eq!(w[0].confidence, Some(95.0));
assert_eq!(w[0].source, "ROVER");
}
/// A tie keeps the primary word (still named ROVER, as an agreed reading).
#[test]
fn rover_tie_keeps_the_primary() {
let primary = vec![Line { words: vec![Word::new("primary", [0.0, 0.0, 10.0, 10.0], "ocrs").with_confidence(80.0)] }];
let secondary = vec![Line { words: vec![Word::new("secondary", [0.0, 0.0, 10.0, 10.0], "tesseract").with_confidence(80.0)] }];
let merged = rover_merge(primary, secondary, "tesseract");
let w = words(&merged);
assert_eq!(w.len(), 1);
assert_eq!(w[0].text, "primary");
assert_eq!(w[0].source, "ROVER");
}
/// Boxes under the 0.5 IoU bar never merge, even when the secondary is more confident.
#[test]
fn rover_below_half_iou_does_not_merge() {
let primary = vec![Line { words: vec![Word::new("kept", [0.0, 0.0, 10.0, 10.0], "ocrs").with_confidence(50.0)] }];
// IoU 10·10 / (100 + 169 - 25) = 100/244 ≈ 0.41 < 0.5.
let secondary = vec![Line { words: vec![Word::new("other", [5.0, 0.0, 23.0, 20.0], "tesseract").with_confidence(99.0)] }];
let merged = rover_merge(primary, secondary, "tesseract");
let w = words(&merged);
assert_eq!(w.len(), 2);
assert_eq!(w[0].text, "kept");
assert_eq!(w[0].source, "ocrs");
}
/// Merged words keep their line; the merge never panics on NaN boxes.
#[test]
fn rover_survives_nan_boxes() {
let primary = vec![Line { words: vec![Word::new("nan", [f32::NAN, 0.0, 10.0, 10.0], "ocrs").with_confidence(50.0)] }];
let secondary = vec![Line { words: vec![Word::new("real", [0.0, 0.0, 10.0, 10.0], "tesseract").with_confidence(90.0)] }];
let merged = rover_merge(primary, secondary, "tesseract");
let w = words(&merged);
assert_eq!(w.len(), 2, "a NaN primary box merges with nothing");
assert_eq!(w[0].text, "nan");
assert_eq!(w[1].text, "real");
}
/// Only reported confidences count. An empty reading is Some(100) (nothing to
/// double-check); words without a single confidence are UNKNOWN (`None`), never 100.
#[test]
fn mean_confidence_distinguishes_empty_from_unknown() {
assert_eq!(mean_confidence(&[]), Some(100.0));
assert_eq!(mean_confidence(&[Line { words: vec![Word::new("a", [0.0; 4], "ocrs")] }]), None, "words, no confidences: unknown");
let lines = vec![Line {
words: vec![
Word::new("a", [0.0; 4], "e").with_confidence(40.0),
Word::new("b", [0.0; 4], "e").with_confidence(80.0),
Word::new("c", [0.0; 4], "e"),
],
}];
assert_eq!(mean_confidence(&lines), Some(60.0), "reported confidences are averaged");
}
/// ROVER's preference needs a meaningful comparison: a known confidence beats an unknown
/// one (the ocrs primary yields to a confident tesseract reading), and None vs None keeps
/// the primary.
#[test]
fn rover_known_confidence_beats_unknown_and_none_vs_none_keeps_the_primary() {
let primary = vec![Line { words: vec![Word::new("helo", [0.0, 0.0, 10.0, 10.0], "ocrs")] }];
let secondary = vec![Line { words: vec![Word::new("hello", [0.0, 0.0, 10.0, 10.0], "tesseract").with_confidence(95.0)] }];
let merged = rover_merge(primary, secondary, "tesseract");
assert_eq!(
(merged[0].words[0].text.as_str(), merged[0].words[0].confidence, merged[0].words[0].source.as_str()),
("hello", Some(95.0), "ROVER")
);
let primary = vec![Line { words: vec![Word::new("primary", [0.0, 0.0, 10.0, 10.0], "ocrs")] }];
let secondary = vec![Line { words: vec![Word::new("secondary", [0.0, 0.0, 10.0, 10.0], "tesseract")] }];
let merged = rover_merge(primary, secondary, "tesseract");
assert_eq!(
(merged[0].words[0].text.as_str(), merged[0].words[0].source.as_str()),
("primary", "ROVER"),
"unknown vs unknown is not a comparison: the primary stands"
);
}
/// Over the comparison cap the merge is skipped and the primary reading stands alone (a
/// documented known limit, bounding the merge's quadratic core).
#[test]
fn rover_over_the_comparison_cap_keeps_the_primary() {
// 11 000 × 11 000 = 121 M comparisons > the 100 M cap.
let words = |id: &str| (0..11_000).map(|i| Word::new(format!("w{i}"), [i as f32, 0.0, i as f32 + 5.0, 10.0], id)).collect::<Vec<_>>();
let primary = vec![Line { words: words("ocrs") }];
let secondary = vec![Line { words: words("tesseract") }];
let merged = rover_merge(primary, secondary, "tesseract");
assert_eq!(merged.len(), 1);
assert!(merged[0].words.iter().all(|w| w.source == "ocrs"), "every primary word stands, unmerged");
assert_eq!(merged[0].words.len(), 11_000);
// Under the cap, merging still happens (a small overlap is replaced and named ROVER).
let small_primary = vec![Line { words: vec![Word::new("kept", [0.0, 0.0, 10.0, 10.0], "ocrs").with_confidence(50.0)] }];
let small_secondary = vec![Line { words: vec![Word::new("wins", [0.0, 0.0, 10.0, 10.0], "tesseract").with_confidence(95.0)] }];
let merged = rover_merge(small_primary, small_secondary, "tesseract");
assert_eq!((merged[0].words[0].text.as_str(), merged[0].words[0].source.as_str()), ("wins", "ROVER"));
}
/// Over the comparison cap the merge is skipped honestly at the strategy level: the page
/// keeps the primary reading alone, the skip is named in a note, and `secondary_ran` does
/// not claim the discarded reading is part of the result (though the secondary really did
/// run — its work was spent, its reading unused).
#[test]
fn rover_cap_hit_reports_primary_only_with_a_note_and_an_honest_flag() {
let mut primary = Fake::empty("ocrs");
primary.lines =
vec![Line { words: (0..11_000).map(|i| Word::new(format!("w{i}"), [i as f32, 0.0, i as f32 + 5.0, 10.0], "ocrs")).collect() }];
let mut secondary = Fake::empty("tesseract");
secondary.lines =
vec![Line { words: (0..11_000).map(|i| Word::new(format!("w{i}"), [i as f32, 0.0, i as f32 + 5.0, 10.0], "tesseract")).collect() }];
let outcome = recognize_with_strategy(&primary, Some(&secondary), MergeStrategy::RoverVote, &image(), &RecognizeOptions::default()).unwrap();
assert_eq!(secondary.calls.load(Ordering::SeqCst), 1, "the secondary really ran");
assert_eq!(outcome.lines.len(), 1);
assert_eq!(outcome.lines[0].words.len(), 11_000, "primary only");
assert!(outcome.lines[0].words.iter().all(|w| w.source == "ocrs"), "every primary word stands, unmerged");
assert!(!outcome.secondary_ran, "the secondary's reading is not part of the result");
assert_eq!(outcome.notes.len(), 1, "{:?}", outcome.notes);
assert!(outcome.notes[0].contains("merge"), "{:?}", outcome.notes[0]);
assert!(outcome.notes[0].contains("tesseract"), "{:?}", outcome.notes[0]);
// Under the cap the same strategy merges and reports the secondary honestly.
let primary = Fake::new("ocrs", &[("kept", [0.0, 0.0, 10.0, 10.0], 50.0)]);
let secondary = Fake::new("tesseract", &[("wins", [0.0, 0.0, 10.0, 10.0], 95.0)]);
let outcome = recognize_with_strategy(&primary, Some(&secondary), MergeStrategy::RoverVote, &image(), &RecognizeOptions::default()).unwrap();
assert!(outcome.secondary_ran && outcome.notes.is_empty());
assert_eq!((outcome.lines[0].words[0].text.as_str(), outcome.lines[0].words[0].source.as_str()), ("wins", "ROVER"));
}
#[test]
fn primary_only_never_runs_the_secondary() {
let primary = Fake::new("ocrs", &[("w", [0.0; 4], 90.0)]);
let secondary = Fake::empty("tesseract");
let outcome =
recognize_with_strategy(&primary, Some(&secondary), MergeStrategy::PrimaryOnly, &image(), &RecognizeOptions::default()).unwrap();
assert_eq!(primary.calls.load(Ordering::SeqCst), 1);
assert_eq!(secondary.calls.load(Ordering::SeqCst), 0);
assert!(!outcome.secondary_ran);
assert!(outcome.notes.is_empty());
assert_eq!(words(&outcome.lines).len(), 1);
}
#[test]
fn confidence_weighted_runs_the_secondary_only_on_a_weak_primary() {
let weak = Fake::new("ocrs", &[("w", [0.0; 4], 40.0)]);
let strong = Fake::new("ocrs", &[("w", [0.0; 4], 95.0)]);
let secondary = Fake::empty("tesseract");
let outcome =
recognize_with_strategy(&weak, Some(&secondary), MergeStrategy::ConfidenceWeighted, &image(), &RecognizeOptions::default()).unwrap();
assert!(outcome.secondary_ran, "mean 40 < 70 → the secondary joins");
let outcome =
recognize_with_strategy(&strong, Some(&secondary), MergeStrategy::ConfidenceWeighted, &image(), &RecognizeOptions::default()).unwrap();
assert!(!outcome.secondary_ran, "mean 95 >= 70 → primary alone");
// An empty primary counts as 100: no signal, no secondary run.
let empty = Fake::empty("ocrs");
let outcome =
recognize_with_strategy(&empty, Some(&secondary), MergeStrategy::ConfidenceWeighted, &image(), &RecognizeOptions::default()).unwrap();
assert!(!outcome.secondary_ran);
assert_eq!(secondary.calls.load(Ordering::SeqCst), 1, "only the weak page ran the secondary");
}
/// The ocrs engine reports no confidences: unknown is not 100, so the secondary runs —
/// and its known reading wins the overlapping word (the ensemble's whole point).
#[test]
fn confidence_weighted_runs_the_secondary_on_an_unknown_primary() {
let ocrs_like = Fake::unknown("ocrs", 1);
let secondary = Fake::new("tesseract", &[("hello", [0.0, 0.0, 10.0, 10.0], 95.0)]);
let outcome =
recognize_with_strategy(&ocrs_like, Some(&secondary), MergeStrategy::ConfidenceWeighted, &image(), &RecognizeOptions::default()).unwrap();
assert!(outcome.secondary_ran, "an unknown confidence asks the secondary");
assert_eq!((outcome.lines[0].words[0].text.as_str(), outcome.lines[0].words[0].confidence), ("hello", Some(95.0)));
assert_eq!(outcome.lines[0].words[0].source, "ROVER");
assert_eq!(secondary.calls.load(Ordering::SeqCst), 1);
}
/// Against a primary word of unknown confidence, a secondary word wins only when it is
/// confident (at or above the weak-reading bar): a 5% reading does not replace a word nobody
/// scored, a 70% one does. The merged word is named ROVER either way.
#[test]
fn an_unknown_primary_word_yields_only_to_a_confident_secondary() {
let merge = |conf: f32| {
let secondary = vec![Line { words: vec![Word::new("other", [0.0, 0.0, 10.0, 10.0], "tesseract").with_confidence(conf)] }];
let primary = Fake::unknown("ocrs", 1).lines;
rover_merge(primary, secondary, "tesseract").remove(0).words.remove(0)
};
let weak = merge(5.0);
assert_eq!((weak.text.as_str(), weak.confidence, weak.source.as_str()), ("w0", None, "ROVER"), "a 5% word keeps the primary");
let below = merge(UNKNOWN_CONFIDENCE_BAR - 0.5);
assert_eq!(below.text, "w0");
let at_bar = merge(UNKNOWN_CONFIDENCE_BAR);
assert_eq!((at_bar.text.as_str(), at_bar.confidence), ("other", Some(UNKNOWN_CONFIDENCE_BAR)), "a confident word wins");
let nan = merge(f32::NAN);
assert_eq!(nan.text, "w0", "NaN (unknown after clamping) never wins");
}
#[test]
fn rover_vote_always_runs_both_and_degrades_without_a_secondary() {
let primary = Fake::new("ocrs", &[("w", [0.0; 4], 95.0)]);
let secondary = Fake::empty("tesseract");
let outcome = recognize_with_strategy(&primary, Some(&secondary), MergeStrategy::RoverVote, &image(), &RecognizeOptions::default()).unwrap();
assert!(outcome.secondary_ran);
assert_eq!(secondary.calls.load(Ordering::SeqCst), 1);
// No secondary: primary only.
let outcome = recognize_with_strategy(&primary, None, MergeStrategy::RoverVote, &image(), &RecognizeOptions::default()).unwrap();
assert!(!outcome.secondary_ran);
}
/// A configured secondary that fails degrades to the primary reading, with the failure
/// recorded as a note — never a skipped page, never a silently partial reading without a
/// trace. Both ensemble strategies degrade; a primary failure is still an error.
#[test]
fn a_failing_secondary_degrades_to_the_primary_with_a_note() {
let mut secondary = Fake::empty("tesseract");
secondary.fail = true;
let primary = Fake::new("ocrs", &[("w", [0.0; 4], 95.0)]);
let outcome = recognize_with_strategy(&primary, Some(&secondary), MergeStrategy::RoverVote, &image(), &RecognizeOptions::default()).unwrap();
assert_eq!(words(&outcome.lines).len(), 1, "the primary reading stands");
assert_eq!(outcome.lines[0].words[0].text, "w");
assert!(!outcome.secondary_ran);
assert_eq!(outcome.notes.len(), 1);
assert!(outcome.notes[0].contains("tesseract"), "{:?}", outcome.notes[0]);
// The confidence-weighted strategy degrades the same way on its weak path.
let weak = Fake::new("ocrs", &[("w", [0.0; 4], 40.0)]);
let outcome =
recognize_with_strategy(&weak, Some(&secondary), MergeStrategy::ConfidenceWeighted, &image(), &RecognizeOptions::default()).unwrap();
assert_eq!(words(&outcome.lines).len(), 1);
assert_eq!(outcome.notes.len(), 1, "{:?}", outcome.notes);
// A failing primary is still an error: there is nothing to degrade to.
let mut failing_primary = Fake::new("ocrs", &[("w", [0.0; 4], 95.0)]);
failing_primary.fail = true;
let r = recognize_with_strategy(&failing_primary, Some(&secondary), MergeStrategy::RoverVote, &image(), &RecognizeOptions::default());
assert!(r.is_err());
}
}
crates/ocr/src/ocrs.rs
+251
View File
@@ -0,0 +1,251 @@
//! The pure-Rust engine: the ocrs crate with its pre-trained models, wrapped as a
//! [`Recognizer`] (`OcrsRecognizer`). Reading is offline and local; the models do not report a
//! confidence, so its words have `confidence: None`.
use std::path::{Path, PathBuf};
use super::{Line, MAX_PIXELS, MAX_SIDE, OcrError, OcrImage, RecognizeOptions, Recognizer, Word};
/// The validated byte length of a `width` × `height` RGBA raster, with the same caps
/// [`OcrImage::new`] applies: zero sides are empty, sides over [`MAX_SIDE`] or totals over
/// [`MAX_PIXELS`] are too large. `Ocr::recognize` takes raw dimensions (they come from
/// callers, ultimately from documents, so they are untrusted), and the naive
/// `width * height * 4` overflows `u32` for absurd values — the caps are checked first, in
/// `usize`, so nothing overflows and nothing huge is ever touched.
fn checked_len(width: u32, height: u32) -> Result<usize, OcrError> {
if width == 0 || height == 0 {
return Err(OcrError::EmptyImage);
}
if width > MAX_SIDE || height > MAX_SIDE {
return Err(OcrError::ImageTooLarge);
}
let pixels = (width as usize).checked_mul(height as usize).ok_or(OcrError::ImageTooLarge)?;
if pixels > MAX_PIXELS as usize {
return Err(OcrError::ImageTooLarge);
}
pixels.checked_mul(4).ok_or(OcrError::ImageTooLarge)
}
/// The languages the models read (ISO 639-1); all use the Latin alphabet without accents.
pub const LANGUAGES: &[(&str, &str)] = &[("en", "English")];
/// The model files, as named in ATTRIBUTION.toml.
pub const DETECTION_MODEL: &str = "text-detection.onnx";
pub const RECOGNITION_MODEL: &str = "text-recognition.onnx";
pub const ALPHABET: &str = " 0123456789!\"#$%&'()*+,-./:;<=>?@[\\]^_`{|}~€ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz";
/// Where the two model files are.
#[derive(Clone, Debug, PartialEq)]
pub struct Models {
pub detection: PathBuf,
pub recognition: PathBuf,
}
impl Models {
pub fn dirs_beside_exe(exe_dir: &Path) -> Vec<PathBuf> {
vec![exe_dir.join("models"), exe_dir.join("../Resources/models"), exe_dir.join("../share/pdfcraft/models")]
}
/// The models in `dir`, preferring current ONNX files over legacy RTEN files. An incomplete
/// update never mixes formats or hides an intact legacy pair.
pub fn in_dir(dir: &Path) -> Option<Models> {
[(DETECTION_MODEL, RECOGNITION_MODEL), ("text-detection.rten", "text-recognition.rten")].into_iter().find_map(|(detection, recognition)| {
let m = Models { detection: dir.join(detection), recognition: dir.join(recognition) };
(m.detection.is_file() && m.recognition.is_file()).then_some(m)
})
}
/// Look for the models: `$PDFCRAFT_MODELS`, then `models/` beside the executable (and
/// `Resources/models` in a macOS bundle), then the source tree's `assets/models/`.
pub fn find() -> Option<Models> {
Self::search_dirs().iter().find_map(|d| Self::in_dir(d))
}
/// The directories [`Models::find`] looks in, in order.
pub fn search_dirs() -> Vec<PathBuf> {
let mut dirs = Vec::new();
if let Some(d) = std::env::var_os("PDFCRAFT_MODELS") {
dirs.push(PathBuf::from(d));
}
if let Some(exe) = std::env::current_exe().ok().and_then(|e| e.parent().map(Path::to_path_buf)) {
dirs.extend(Self::dirs_beside_exe(&exe));
}
dirs.push(Path::new(env!("CARGO_MANIFEST_DIR")).join("../../assets/models"));
dirs
}
}
/// A loaded recogniser. Loading takes a moment; keep one and reuse it.
pub struct Ocr {
engine: ocrs::OcrEngine,
}
impl Ocr {
pub fn load(models: &Models) -> Result<Ocr, OcrError> {
let load = |p: &Path| rten::Model::load_file(p).map_err(|e| OcrError::Load(p.display().to_string(), e.to_string()));
let params = ocrs::OcrEngineParams {
detection_model: Some(load(&models.detection)?),
recognition_model: Some(load(&models.recognition)?),
alphabet: Some(ALPHABET.into()),
..Default::default()
};
let engine = ocrs::OcrEngine::new(params).map_err(|e| OcrError::Load("ocr engine".into(), e.to_string()))?;
Ok(Ocr { engine })
}
/// Load the models found by [`Models::find`].
pub fn find() -> Result<Ocr, OcrError> {
Self::load(&Models::find().ok_or(OcrError::NoModels)?)
}
/// Recognise the text in an RGBA (or RGB, or grey) image, `width` × `height` pixels.
pub fn recognize(&self, pixels: &[u8], width: u32, height: u32) -> Result<Vec<Line>, OcrError> {
if pixels.is_empty() {
return Err(OcrError::EmptyImage);
}
let want = checked_len(width, height)?;
// ocrs wants 1 or 3 channels.
let rgb: std::borrow::Cow<[u8]> = if pixels.len() == want {
pixels.as_chunks::<4>().0.iter().flat_map(|p| [p[0], p[1], p[2]]).collect::<Vec<u8>>().into()
} else {
pixels.into()
};
let err = |e: &dyn std::fmt::Display| OcrError::Recognize(e.to_string());
let source = ocrs::ImageSource::from_bytes(&rgb, (width, height)).map_err(|e| err(&e))?;
let input = self.engine.prepare_input(source).map_err(|e| err(&e))?;
let found = self.engine.detect_words(&input).map_err(|e| err(&e))?;
let lines = self.engine.find_text_lines(&input, &found);
let read = self.engine.recognize_text(&input, &lines).map_err(|e| err(&e))?;
use ocrs::TextItem;
Ok(read
.into_iter()
.flatten()
.map(|line| Line {
words: line
.words()
.map(|w| {
let r = w.bounding_rect();
Word::new(w.to_string(), [r.left() as f32, r.top() as f32, r.right() as f32, r.bottom() as f32], "ocrs")
})
.filter(|w| !w.text.trim().is_empty())
.collect(),
})
.filter(|l| !l.words.is_empty())
.collect())
}
}
/// The ocrs engine as a [`Recognizer`] (the default engine).
pub struct OcrsRecognizer {
engine: Ocr,
}
impl OcrsRecognizer {
/// Load the models from `models`.
pub fn load(models: &Models) -> Result<OcrsRecognizer, OcrError> {
Ok(OcrsRecognizer { engine: Ocr::load(models)? })
}
/// Load the models found by [`Models::find`].
pub fn find() -> Result<OcrsRecognizer, OcrError> {
Self::load(&Models::find().ok_or(OcrError::NoModels)?)
}
}
impl Recognizer for OcrsRecognizer {
fn id(&self) -> &'static str {
"ocrs"
}
fn available(&self) -> bool {
Models::find().is_some()
}
fn languages(&self) -> Vec<(String, String)> {
LANGUAGES.iter().map(|(c, n)| ((*c).to_string(), (*n).to_string())).collect()
}
fn recognize(&self, image: &OcrImage, _options: &RecognizeOptions) -> Result<Vec<Line>, OcrError> {
self.engine.recognize(image.rgba(), image.width(), image.height())
}
}
#[cfg(test)]
mod tests {
use super::*;
/// Raw dimensions are untrusted (they come from callers, ultimately from documents): zero
/// sides, sides or pixel totals over the caps, and products that would overflow the naive
/// `width * height * 4` are errors, never panics, before anything is touched.
#[test]
fn raw_dimensions_are_capped_and_checked_not_panicked_at() {
assert!(matches!(checked_len(0, 10), Err(OcrError::EmptyImage)));
assert!(matches!(checked_len(10, 0), Err(OcrError::EmptyImage)));
assert!(matches!(checked_len(MAX_SIDE + 1, 1), Err(OcrError::ImageTooLarge)));
// 65536² would wrap u32 in the old `width * height * 4`; the side cap refuses it first.
assert!(matches!(checked_len(u32::MAX, u32::MAX), Err(OcrError::ImageTooLarge)));
// Legal sides whose product is over the 64 MP area cap.
assert!(matches!(checked_len(MAX_SIDE, 7000), Err(OcrError::ImageTooLarge)));
assert_eq!(checked_len(2, 2).unwrap(), 16);
// Exactly the area cap fits: 8000 × 8000 = 64 MP.
assert_eq!(checked_len(8000, 8000).unwrap(), 8000usize * 8000 * 4);
}
/// The current ONNX pair wins when an installation also retains both legacy models.
#[test]
fn model_discovery_prefers_the_complete_onnx_pair() {
let dir = tempfile::tempdir().unwrap();
for file in ["text-detection.onnx", "text-recognition.onnx"] {
std::fs::write(dir.path().join(file), b"model").unwrap();
}
let expected = Some(Models { detection: dir.path().join("text-detection.onnx"), recognition: dir.path().join("text-recognition.onnx") });
assert_eq!(Models::in_dir(dir.path()), expected, "a complete ONNX pair is sufficient");
for file in ["text-detection.rten", "text-recognition.rten"] {
std::fs::write(dir.path().join(file), b"model").unwrap();
}
assert_eq!(Models::in_dir(dir.path()), expected, "the complete ONNX pair takes precedence over legacy models");
}
/// An interrupted ONNX update still permits an intact legacy pair in the same directory.
#[test]
fn model_discovery_falls_back_to_legacy_when_the_onnx_pair_is_incomplete() {
for current in ["text-detection.onnx", "text-recognition.onnx"] {
let dir = tempfile::tempdir().unwrap();
for file in [current, "text-detection.rten", "text-recognition.rten"] {
std::fs::write(dir.path().join(file), b"model").unwrap();
}
assert_eq!(
Models::in_dir(dir.path()),
Some(Models { detection: dir.path().join("text-detection.rten"), recognition: dir.path().join("text-recognition.rten") }),
"{current} alone must not hide a complete legacy pair"
);
}
}
/// Detection and recognition must come from one complete format pair, never a mixed update.
#[test]
fn model_discovery_refuses_mixed_format_pairs() {
for pair in [["text-detection.onnx", "text-recognition.rten"], ["text-detection.rten", "text-recognition.onnx"]] {
let dir = tempfile::tempdir().unwrap();
for file in pair {
std::fs::write(dir.path().join(file), b"model").unwrap();
}
assert_eq!(Models::in_dir(dir.path()), None, "{pair:?} is not a complete model pair");
}
}
/// Existing source builds and PDFCRAFT_MODELS overrides retain their complete RTEN pair.
#[test]
fn model_discovery_keeps_legacy_only_installations() {
let dir = tempfile::tempdir().unwrap();
assert_eq!(Models::in_dir(dir.path()), None);
std::fs::write(dir.path().join("text-detection.rten"), b"model").unwrap();
assert_eq!(Models::in_dir(dir.path()), None, "one legacy model is incomplete");
std::fs::write(dir.path().join("text-recognition.rten"), b"model").unwrap();
assert_eq!(
Models::in_dir(dir.path()),
Some(Models { detection: dir.path().join("text-detection.rten"), recognition: dir.path().join("text-recognition.rten") })
);
}
}
crates/ocr/src/preprocess.rs
+973
View File
@@ -0,0 +1,973 @@
//! Preprocessing: a pure function between the page raster and recognition, in fixed order —
//! (a) DPI normalization, then the four opt-in steps (b) orientation, (c) deskew, (d) denoise,
//! (e) binarization. Normalization exists for those steps (their windows and thresholds are
//! calibrated for 300 dpi), so it runs only when at least one of them is on: with every step
//! off the raster is handed to the engines exactly as it was rendered. (Enlarging a render
//! on its own changes what the models read: a 72 dpi scan of "due: €250" read as "ue: ?250"
//! after a 4× bilinear enlargement.) Everything is plain Rust on the RGBA raster: no
//! Leptonica, no process, no new dependencies.
//!
//! Every geometric step records its inverse; the result carries one exact
//! [`InverseTransform`] (an affine map, composed in f64), and callers map every word box
//! through it back to the *original* raster coordinates before placing the words.
//!
//! The heuristics are deliberately conservative and panic-free: an image too small to judge,
//! a blank page, or a score without a clear margin is a no-op, never a guess.
use crate::{MAX_PIXELS, MAX_SIDE, OcrError, OcrImage};
/// The four opt-in steps. All off by default: a scan is passed through as rendered.
#[derive(Clone, Copy, Debug, Default, PartialEq, Eq)]
pub struct PreprocessOptions {
/// Detect pages scanned at 90°/180°/270° and turn them upright.
pub auto_rotate: bool,
/// Straighten skewed text lines.
pub deskew: bool,
/// 3×3 median filter (salt-and-pepper noise).
pub denoise: bool,
/// Sauvola binarization (window 8, k 0.34).
pub binarize: bool,
}
impl PreprocessOptions {
/// Whether any step is on (and so the raster is normalized to 300 dpi first).
pub fn any(&self) -> bool {
self.auto_rotate || self.deskew || self.denoise || self.binarize
}
}
/// A preprocessed raster: the image to recognize, the exact way back to the input raster, and
/// the resolution the image now stands for.
#[derive(Debug)]
pub struct Preprocessed {
pub image: OcrImage,
/// Maps pixel coordinates in [`Preprocessed::image`] back to the input raster's.
pub inverse_transform: InverseTransform,
/// The image's resolution in dots per inch: 300 after normalization (only when a step is
/// on), or the source's own
/// when it already rendered at 300 or more.
pub dpi: f32,
}
/// Preprocess `image` (rendered at `source_dpi`) per `options`, in the fixed order. The image
/// is consumed: the common path (every step off, or a no-op) hands the raster back without
/// copying it, and a step that rewrites pixels replaces it.
pub fn preprocess(image: OcrImage, source_dpi: f32, options: &PreprocessOptions) -> Result<Preprocessed, OcrError> {
let mut current = image;
let mut inverse = InverseTransform::identity();
// (a) DPI normalization: for the steps below, a scan under 300 dpi is enlarged by 300/src so
// they see letter-sized strokes. With every step off nothing is resampled. A broken dpi
// (zero, negative, NaN) is left alone.
let mut dpi = if source_dpi.is_finite() && source_dpi >= 1.0 { source_dpi } else { 300.0 };
if options.any() && dpi < 300.0 {
let scale = f64::from(300.0 / dpi);
current = resize_bilinear(&current, scale)?;
inverse = compose(&inverse, &InverseTransform::scale(1.0 / scale));
dpi = 300.0;
}
// (b) Orientation: turn 90/180/270 scans upright (opt-in, skipped for small images).
if options.auto_rotate {
let (w, h) = (current.width, current.height);
let turns = detect_orientation(&current);
if turns != 0 {
current = rotate_quarter_turns(&current, turns);
inverse = compose(&inverse, &inverse_quarter_turns(turns, w, h));
}
}
// (c) Deskew: straighten skewed lines (opt-in; no-op under 64 px, blank, or without a
// clear margin or below 0.1°).
if options.deskew
&& let Some(angle) = estimate_skew(&current)
{
let (straightened, back) = deskew_rotate(&current, angle);
current = straightened;
inverse = compose(&inverse, &back);
}
// (d) Denoise: 3×3 median with edge clamping (opt-in; dimensions never change).
if options.denoise {
current = median3(&current);
}
// (e) Binarize: Sauvola (window 8, k 0.34) via an integral image (opt-in); dark ink stays
// dark and paper stays light.
if options.binarize {
current = sauvola(&current);
}
Ok(Preprocessed { image: current, inverse_transform: inverse, dpi })
}
/// An affine map `(x, y) → (a·x + c·y + e, b·x + d·y + f)`, composed in f64 so mapping a
/// word box back is exact up to float rounding.
#[derive(Clone, Copy, Debug, PartialEq)]
pub struct InverseTransform {
a: f64,
b: f64,
c: f64,
d: f64,
e: f64,
f: f64,
}
impl InverseTransform {
pub fn identity() -> InverseTransform {
InverseTransform { a: 1.0, b: 0.0, c: 0.0, d: 1.0, e: 0.0, f: 0.0 }
}
fn scale(s: f64) -> InverseTransform {
InverseTransform { a: s, b: 0.0, c: 0.0, d: s, e: 0.0, f: 0.0 }
}
/// `compose(outer, inner)` maps `p` to `outer(inner(p))`: the accumulated inverse of the
/// earlier steps is the outer map (their spaces come later in the round trip), so each
/// step calls `compose(&inverse, &this_step_inverse)`. The scale step, for instance,
/// happens first, so its inverse is applied last: `scale⁻¹(rotate⁻¹(p))`.
fn compose_(outer: &InverseTransform, inner: &InverseTransform) -> InverseTransform {
InverseTransform {
a: outer.a * inner.a + outer.c * inner.b,
b: outer.b * inner.a + outer.d * inner.b,
c: outer.a * inner.c + outer.c * inner.d,
d: outer.b * inner.c + outer.d * inner.d,
e: outer.a * inner.e + outer.c * inner.f + outer.e,
f: outer.b * inner.e + outer.d * inner.f + outer.f,
}
}
/// Map a point from the processed image back to the input raster.
pub fn apply(&self, x: f64, y: f64) -> (f64, f64) {
(self.a * x + self.c * y + self.e, self.b * x + self.d * y + self.f)
}
/// Map a word box `[left, top, right, bottom]` back to the input raster: the four corners
/// go through [`Self::apply`] and their bounding box is rounded outward to whole pixels.
/// A box with no finite corners comes back unchanged (garbage in, garbage out — never a
/// panic).
pub fn map_rect(&self, rect: [f32; 4]) -> [f32; 4] {
let corners = [(rect[0], rect[1]), (rect[2], rect[1]), (rect[0], rect[3]), (rect[2], rect[3])];
let mut lo = (f64::INFINITY, f64::INFINITY);
let mut hi = (f64::NEG_INFINITY, f64::NEG_INFINITY);
let mut finite = false;
for (x, y) in corners {
if !(x.is_finite() && y.is_finite()) {
continue;
}
let (mx, my) = self.apply(f64::from(x), f64::from(y));
if mx.is_finite() && my.is_finite() {
finite = true;
lo = (lo.0.min(mx), lo.1.min(my));
hi = (hi.0.max(mx), hi.1.max(my));
}
}
if !finite {
return rect;
}
[lo.0.floor() as f32, lo.1.floor() as f32, hi.0.ceil() as f32, hi.1.ceil() as f32]
}
}
/// The step inverses compose in pipeline order: each new step's inverse is applied *after*
/// the inverses accumulated so far.
fn compose(outer: &InverseTransform, inner: &InverseTransform) -> InverseTransform {
InverseTransform::compose_(outer, inner)
}
/// The size `width` x `height` becomes under `scale`, refused (before any buffer exists) when
/// a side is under one pixel or over [`MAX_SIDE`], or the area is over [`MAX_PIXELS`]: two
/// sides under the side cap can still ask for hundreds of megabytes, which `OcrImage::new`
/// would only refuse after they were allocated.
fn scaled_size(width: u32, height: u32, scale: f64) -> Result<(u32, u32), OcrError> {
let new_w = (f64::from(width) * scale).ceil();
let new_h = (f64::from(height) * scale).ceil();
if !(1.0..=f64::from(MAX_SIDE)).contains(&new_w) || !(1.0..=f64::from(MAX_SIDE)).contains(&new_h) {
return Err(OcrError::ImageTooLarge);
}
let (nw, nh) = (new_w as u32, new_h as u32);
if (nw as usize).checked_mul(nh as usize).is_none_or(|pixels| pixels > MAX_PIXELS as usize) {
return Err(OcrError::ImageTooLarge);
}
Ok((nw, nh))
}
/// Bilinear resize by `scale`, clamped at the edges; the result stays inside [`scaled_size`]'s
/// limits (the side cap and the area cap).
fn resize_bilinear(image: &OcrImage, scale: f64) -> Result<OcrImage, OcrError> {
let (nw, nh) = scaled_size(image.width, image.height, scale)?;
let mut out = vec![255u8; (nw as usize).checked_mul(nh as usize).and_then(|p| p.checked_mul(4)).ok_or(OcrError::ImageTooLarge)?];
for (y, row) in out.chunks_exact_mut(4 * nw as usize).enumerate() {
for (x, px) in row.as_chunks_mut::<4>().0.iter_mut().enumerate() {
// The source position of the destination pixel's centre, and the four
// neighbours bilinear interpolation blends (positions clamp at the edges).
let sx = (x as f64 + 0.5) / scale - 0.5;
let sy = (y as f64 + 0.5) / scale - 0.5;
let (x0, y0) = (sx.floor().max(0.0), sy.floor().max(0.0));
let (fx, fy) = (sx - x0, sy - y0);
for (ch, o) in px.iter_mut().enumerate() {
let blend = |dx: f64, dy: f64| f64::from(image.byte(x0 + dx, y0 + dy, ch));
let v = blend(0.0, 0.0) * (1.0 - fx) * (1.0 - fy)
+ blend(1.0, 0.0) * fx * (1.0 - fy)
+ blend(0.0, 1.0) * (1.0 - fx) * fy
+ blend(1.0, 1.0) * fx * fy;
*o = v.round().clamp(0.0, 255.0) as u8;
}
}
}
OcrImage::new(nw, nh, out)
}
/// Grayscale (Rec.601 luma) of every pixel.
fn grayscale(image: &OcrImage) -> Vec<u8> {
image.rgba.as_chunks::<4>().0.iter().map(|p| ((299 * p[0] as u32 + 587 * p[1] as u32 + 114 * p[2] as u32) / 1000).min(255) as u8).collect()
}
/// How the page must be turned (quarter turns, clockwise) to read upright.
type QuarterTurns = u32;
/// Detect the correction for pages scanned sideways or upside down. Method (documented,
/// panic-free, no OCR): ink is everything darker than the midpoint between the darkest and
/// lightest pixel; for each candidate correction (0/90/180/270 clockwise) the ink's row
/// profile is taken and scored by how sharply it bands (Σ Δ², the projection-profile score:
/// upright text lines band sharply, turned text does not). The best-banding axis wins when it
/// beats the other axis by a factor of 1.3; within the winning axis the line bands'
/// bottom-heaviness (real text carries more ink below each line's middle — baselines and
/// descenders) picks the quarter turn, with a 4%-of-ink margin. Anything less clear is a
/// no-op (`0`), and images under 32 px are never judged.
fn detect_orientation(image: &OcrImage) -> QuarterTurns {
if image.min_side() < 32 {
return 0;
}
let gray = grayscale(image);
let (Some(lo), Some(hi)) = (gray.iter().min(), gray.iter().max()) else { return 0 };
let t = (*lo as u32 + *hi as u32) / 2;
let ink: Vec<bool> = gray.iter().map(|&g| (g as u32) < t).collect();
let (w, h) = (image.width as usize, image.height as usize);
let total: u64 = ink.iter().filter(|i| **i).count() as u64;
if total == 0 {
return 0;
}
// The ink grid rotated by k quarter turns (clockwise), as row profiles.
let mut scores = [0.0f64; 4];
let mut asyms = [0.0f64; 4];
for k in 0u32..4 {
let k = k as usize;
let profile = rotated_row_profile(&ink, w, h, k as u32);
scores[k] = profile.windows(2).map(|p| (p[1] as f64 - p[0] as f64).powi(2)).sum();
asyms[k] = band_bottom_heaviness(&profile);
}
// 0 and 180 share one profile shape (reversed), as do 90 and 270: pick the axis first.
let (vertical_pair, horizontal_pair) = ((scores[0], scores[2]), (scores[1], scores[3]));
let row_axis = vertical_pair.0.max(vertical_pair.1);
let column_axis = horizontal_pair.0.max(horizontal_pair.1);
if row_axis >= column_axis {
if row_axis < column_axis * 1.3 {
return 0; // the axes are too close to call
}
if asyms[0] > 0.15 * total as f64 {
0
} else if asyms[2] > 0.15 * total as f64 {
2
} else {
0 // the bands are not clearly bottom-heavy either way: no-op
}
} else {
if column_axis < row_axis * 1.3 {
return 0;
}
if asyms[1] > 0.15 * total as f64 {
1
} else if asyms[3] > 0.15 * total as f64 {
3
} else {
0
}
}
}
/// The row profile of the ink grid after `k` quarter turns clockwise.
fn rotated_row_profile(ink: &[bool], w: usize, h: usize, k: u32) -> Vec<u64> {
// The rotated image is `w` pixels tall for odd k and `h` for even k; its row index is
// always the new y of the source pixel.
let len = if k.is_multiple_of(2) { h } else { w };
let mut profile = vec![0u64; len];
for (y, row) in ink.chunks_exact(w).enumerate() {
for (x, on) in row.iter().enumerate() {
if !on {
continue;
}
// Where does (x, y) land after k quarter turns clockwise?
let ny = match k {
1 => x,
2 => h - 1 - y,
3 => w - 1 - x,
_ => y,
};
if let Some(p) = profile.get_mut(ny) {
*p += 1;
}
}
}
profile
}
/// Sum over text-line bands of (ink in the band's lower half − ink in its upper half):
/// positive when the bands carry more ink near their bottoms, as real text does.
fn band_bottom_heaviness(profile: &[u64]) -> f64 {
let mut asym = 0.0;
let mut start: Option<usize> = None;
for (i, &p) in profile.iter().chain(std::iter::once(&0)).enumerate() {
match (start, p > 0) {
(None, true) => start = Some(i),
(Some(s), false) => {
let mid = (s + i) / 2;
let lower: u64 = profile.get(s..i).map_or(0, |b| b[mid.saturating_sub(s)..].iter().sum());
let upper: u64 = profile.get(s..i).map_or(0, |b| b[..mid.saturating_sub(s)].iter().sum());
asym += lower as f64 - upper as f64; // signed: a top-heavy band scores below zero
start = None;
}
_ => {}
}
}
asym
}
/// Rotate the raster `k` quarter turns clockwise (an exact pixel permutation).
fn rotate_quarter_turns(image: &OcrImage, k: QuarterTurns) -> OcrImage {
let (w, h) = (image.width as usize, image.height as usize);
let (nw, nh) = if k.is_multiple_of(2) { (image.width, image.height) } else { (image.height, image.width) };
let mut out = vec![255u8; nw as usize * nh as usize * 4];
for (y, row) in image.rgba.chunks_exact(w * 4).enumerate() {
for (x, px) in row.as_chunks::<4>().0.iter().enumerate() {
let (nx, ny) = match k {
1 => (h - 1 - y, x),
2 => (w - 1 - x, h - 1 - y),
3 => (y, w - 1 - x),
_ => (x, y),
};
if let Some(dst) = out.get_mut((ny * nw as usize + nx) * 4..(ny * nw as usize + nx) * 4 + 4) {
dst.copy_from_slice(px);
}
}
}
OcrImage::new(nw, nh, out).unwrap_or_else(|_| image.clone())
}
/// The inverse of a `k`-quarter-turn correction: where each corrected pixel came from.
fn inverse_quarter_turns(k: QuarterTurns, old_w: u32, old_h: u32) -> InverseTransform {
let (w, h) = (f64::from(old_w), f64::from(old_h));
match k {
// Forward (content moves): (x, y) ↦ (h−1−y, x) for one turn clockwise.
1 => InverseTransform { a: 0.0, b: -1.0, c: 1.0, d: 0.0, e: 0.0, f: h - 1.0 },
2 => InverseTransform { a: -1.0, b: 0.0, c: 0.0, d: -1.0, e: w - 1.0, f: h - 1.0 },
3 => InverseTransform { a: 0.0, b: 1.0, c: -1.0, d: 0.0, e: w - 1.0, f: 0.0 },
_ => InverseTransform::identity(),
}
}
/// Estimate the skew of the text lines, in degrees (−5…5, positive: lines run downhill to the
/// right). Method (documented, panic-free): for each candidate angle the ink is sheared into a
/// row profile (`r = y − (x − cx)·tan φ`); the projection-profile score (Σ profile²) peaks
/// where the shear realigns the lines. `None` — leave the page alone — when the image is under
/// 64 px on a side, blank, the winner is under 0.1°, or the winner does not clearly beat
/// leaving the page as is (score < 1.02 × the 0° score).
fn estimate_skew(image: &OcrImage) -> Option<f64> {
if image.min_side() < 64 {
return None;
}
let gray = grayscale(image);
let (Some(lo), Some(hi)) = (gray.iter().min(), gray.iter().max()) else { return None };
let t = (*lo as u32 + *hi as u32) / 2;
let ink: Vec<bool> = gray.iter().map(|&g| (g as u32) < t).collect();
if !ink.iter().any(|i| *i) {
return None; // a blank page has no skew
}
let (w, h) = (image.width, image.height);
let cx = f64::from(w) / 2.0;
let max_shift = (f64::from(w) / 2.0 * 5f64.to_radians().tan()).ceil() as i64 + 2;
let score = |phi_deg: f64| -> f64 {
let slope = phi_deg.to_radians().tan();
let mut profile = vec![0u64; (h as i64 + 2 * max_shift + 1) as usize];
for (y, row) in ink.chunks_exact(w as usize).enumerate() {
for (x, on) in row.iter().enumerate() {
if !on {
continue;
}
let r = y as f64 - (x as f64 - cx) * slope;
let idx = r.round() as i64 + max_shift;
if let Some(p) = profile.get_mut(idx as usize) {
*p += 1;
}
}
}
profile.iter().map(|p| (*p as f64).powi(2)).sum()
};
let mut best = (0.0f64, score(0.0));
let mut phi = -5.0;
while phi <= 5.0 + 1e-9 {
let s = score(phi);
if s > best.1 {
best = (phi, s);
}
phi += 0.25;
}
let (angle, best_score) = best;
if angle.abs() < 0.1 || best_score < 1.02 * score(0.0) {
return None; // straight enough, or no clear winner: no-op
}
Some(angle)
}
/// Rotate the content by `−angle` about the centre (the deskew correction), nearest-neighbour
/// with white fill; also returns the exact dest→src map (the correction's inverse).
fn deskew_rotate(image: &OcrImage, angle_deg: f64) -> (OcrImage, InverseTransform) {
let phi = angle_deg.to_radians();
let (cos, sin) = (phi.cos(), phi.sin());
let (w, h) = (image.width, image.height);
let (cx, cy) = (f64::from(w) / 2.0, f64::from(h) / 2.0);
let back = InverseTransform { a: cos, b: sin, c: -sin, d: cos, e: cx - cos * cx + sin * cy, f: cy - sin * cx - cos * cy };
let mut out = vec![255u8; w as usize * h as usize * 4];
for (y, row) in out.chunks_exact_mut(w as usize * 4).enumerate() {
for (x, px) in row.as_chunks_mut::<4>().0.iter_mut().enumerate() {
let (sx, sy) = back.apply(x as f64, y as f64);
let (xi, yi) = (sx.round() as i64, sy.round() as i64);
if xi < 0 || yi < 0 || xi >= w as i64 || yi >= h as i64 {
continue; // outside the scan: white fill
}
if let Some(src) = image.rgba.get((yi as usize * w as usize + xi as usize) * 4..(yi as usize * w as usize + xi as usize) * 4 + 4) {
px.copy_from_slice(src);
}
}
}
(OcrImage::new(w, h, out).unwrap_or_else(|_| image.clone()), back)
}
/// 3×3 median filter on each colour channel, edges clamped (border pixels replicate);
/// dimensions and alpha are unchanged.
fn median3(image: &OcrImage) -> OcrImage {
let (w, h) = (image.width as usize, image.height as usize);
let mut out = image.rgba.clone();
for (i, dst) in out.as_chunks_mut::<4>().0.iter_mut().enumerate() {
let (x, y) = (i % w, i / w);
let mut rgba = [255u8; 3];
for (ch, v) in rgba.iter_mut().enumerate() {
let mut window = [0u8; 9];
for (n, (dx, dy)) in [(-1i64, -1i64), (0, -1), (1, -1), (-1, 0), (0, 0), (1, 0), (-1, 1), (0, 1), (1, 1)].iter().enumerate() {
let nx = ((x as i64) + dx).clamp(0, w as i64 - 1) as usize;
let ny = ((y as i64) + dy).clamp(0, h as i64 - 1) as usize;
window[n] = image.byte(nx as f64, ny as f64, ch);
}
window.sort_unstable();
*v = window[4];
}
let alpha = dst[3];
dst.copy_from_slice(&[rgba[0], rgba[1], rgba[2], alpha]);
}
OcrImage::new(image.width, image.height, out).unwrap_or_else(|_| image.clone())
}
/// The Sauvola ink mask: local thresholding with the documented window — 8 pixels wide, the
/// 8 pixels from −4 to +3 (the end is exclusive, so `x0..x1` is exactly `x−4..=x+3`), k 0.34 —
/// through an integral image. A pixel is ink when its grey is at or under the local
/// threshold.
fn sauvola_mask(image: &OcrImage) -> Vec<bool> {
let (w, h) = (image.width as usize, image.height as usize);
let gray = grayscale(image);
// Integral sums and square sums, (w+1)×(h+1), so any window sum is four lookups.
let stride = w + 1;
let mut sums = vec![0u64; stride * (h + 1)];
let mut squares = vec![0u64; stride * (h + 1)];
for (y, row) in gray.chunks_exact(w).enumerate() {
let (mut row_sum, mut row_sq) = (0u64, 0u64);
for (x, &g) in row.iter().enumerate() {
row_sum += u64::from(g);
row_sq += u64::from(g) * u64::from(g);
let above = sums.get(y * stride + x + 1).copied().unwrap_or(0);
let above_sq = squares.get(y * stride + x + 1).copied().unwrap_or(0);
if let (Some(s), Some(sq)) = (sums.get_mut((y + 1) * stride + x + 1), squares.get_mut((y + 1) * stride + x + 1)) {
*s = above + row_sum;
*sq = above_sq + row_sq;
}
}
}
let (k, r) = (0.34f64, 128.0f64);
let half = 4usize;
let mut ink = vec![false; w * h];
for (y, row) in ink.chunks_exact_mut(w).enumerate() {
for (x, dst) in row.iter_mut().enumerate() {
let (x0, y0) = (x.saturating_sub(half), y.saturating_sub(half));
// Exclusive end: the window covers −4..=+3, 8 pixels on a side (an end of
// `x + half + 1` would make it 9 and disagree with the documented window).
let (x1, y1) = ((x + half).min(w), (y + half).min(h));
let n = ((x1 - x0) * (y1 - y0)) as f64;
let sum = rect_sum(&sums, stride, x0, y0, x1, y1);
let sq = rect_sum(&squares, stride, x0, y0, x1, y1);
let mean = sum / n;
let var = (sq / n - mean * mean).max(0.0);
let threshold = mean * (1.0 + k * (var.sqrt() / r - 1.0));
*dst = matches!(gray.get(y * w + x), Some(&g) if f64::from(g) <= threshold);
}
}
ink
}
/// Sauvola binarization through [`sauvola_mask`], followed by a one-pixel dilation of the ink:
/// ink goes to black, paper to white, alpha preserved.
fn sauvola(image: &OcrImage) -> OcrImage {
let (w, h) = (image.width as usize, image.height as usize);
// One dilation keeps anti-aliased strokes whole: a thresholded edge pixel that flaked off
// rejoins its stroke (slightly bold beats broken, for reading).
let ink = dilate1(&sauvola_mask(image), w, h);
let mut out = image.rgba.clone();
for (i, px) in out.as_chunks_mut::<4>().0.iter_mut().enumerate() {
let v = if ink.get(i).copied().unwrap_or(false) { 0u8 } else { 255u8 };
if let Some(dst) = px.get_mut(..3) {
dst.copy_from_slice(&[v, v, v]);
}
}
OcrImage::new(image.width, image.height, out).unwrap_or_else(|_| image.clone())
}
/// Grow the ink mask by one pixel (8-neighbourhood, edges clamped by the bounds checks).
fn dilate1(ink: &[bool], w: usize, h: usize) -> Vec<bool> {
let mut out = ink.to_vec();
for y in 0..h {
for x in 0..w {
if !ink.get(y * w + x).copied().unwrap_or(false) {
continue;
}
for dy in [-1isize, 0, 1] {
for dx in [-1isize, 0, 1] {
let (nx, ny) = (x as isize + dx, y as isize + dy);
if nx < 0 || ny < 0 || nx >= w as isize || ny >= h as isize {
continue;
}
if let Some(o) = out.get_mut(ny as usize * w + nx as usize) {
*o = true;
}
}
}
}
}
out
}
fn rect_sum(table: &[u64], stride: usize, x0: usize, y0: usize, x1: usize, y1: usize) -> f64 {
let a = table.get(y1 * stride + x1).copied().unwrap_or(0);
let b = table.get(y0 * stride + x1).copied().unwrap_or(0);
let c = table.get(y1 * stride + x0).copied().unwrap_or(0);
let d = table.get(y0 * stride + x0).copied().unwrap_or(0);
(a + d - b - c) as f64
}
#[cfg(test)]
mod tests {
use super::*;
/// Sides under MAX_SIDE whose area passes MAX_PIXELS (9500 × 9500, 90 MP) are refused
/// when the size is worked out, before the 360 MB buffer is allocated rather than after.
#[test]
fn an_upscale_over_the_area_cap_is_refused_before_allocating() {
assert!(matches!(scaled_size(1000, 1000, 9.5), Err(OcrError::ImageTooLarge)));
assert_eq!(scaled_size(1000, 1000, 2.0).unwrap(), (2000, 2000), "under the caps it still scales");
assert_eq!(scaled_size(8000, 8000, 1.0).unwrap(), (8000, 8000), "exactly 64 MP is allowed");
assert!(matches!(scaled_size(8001, 8000, 1.0), Err(OcrError::ImageTooLarge)), "one row over is not");
assert!(matches!(scaled_size(1000, 1000, 10.5), Err(OcrError::ImageTooLarge)), "a side over MAX_SIDE");
assert!(matches!(scaled_size(1000, 1000, 0.0), Err(OcrError::ImageTooLarge)), "a side under one pixel");
assert!(matches!(scaled_size(1000, 1000, f64::NAN), Err(OcrError::ImageTooLarge)));
let small = OcrImage::new(100, 100, vec![255; 100 * 100 * 4]).unwrap();
assert!(matches!(resize_bilinear(&small, 100.5), Err(OcrError::ImageTooLarge)));
assert_eq!(resize_bilinear(&small, 2.0).unwrap().width, 200);
}
fn white(w: u32, h: u32) -> OcrImage {
OcrImage::new(w, h, vec![255; (w * h * 4) as usize]).unwrap()
}
/// Ink bounding box of a raster (None when blank).
fn ink_bbox(image: &OcrImage) -> Option<[f32; 4]> {
let gray = grayscale(image);
let (Some(lo), Some(hi)) = (gray.iter().min(), gray.iter().max()) else { return None };
let t = (*lo as u32 + *hi as u32) / 2;
let (mut l, mut tp, mut r, mut b) = (u32::MAX, u32::MAX, 0u32, 0u32);
let mut any = false;
for (i, &g) in gray.iter().enumerate() {
if (g as u32) >= t {
continue;
}
any = true;
let (x, y) = ((i as u32) % image.width, (i as u32) / image.width);
l = l.min(x);
r = r.max(x);
tp = tp.min(y);
b = b.max(y);
}
any.then_some([l as f32, tp as f32, r as f32, b as f32])
}
/// A horizontal line of three bottom-heavy block glyphs (L shapes) on white — the fixture
/// for orientation detection (240 × 64 at 300 dpi).
fn l_line() -> OcrImage {
let (w, h) = (240u32, 64u32);
let mut img = white(w, h);
for gx in [20u32, 100, 180] {
fill(&mut img, gx, 12, 12, 40);
fill(&mut img, gx, 40, 36, 12);
}
img
}
fn fill(img: &mut OcrImage, x0: u32, y0: u32, w: u32, h: u32) {
for y in y0..y0 + h {
for x in x0..x0 + w {
let o = ((y * img.width + x) * 4) as usize;
if let Some(p) = img.rgba.get_mut(o..o + 3) {
p.copy_from_slice(&[0, 0, 0]);
}
}
}
}
/// The same fixture pre-rotated by k quarter turns clockwise, built independently of the
/// crate's rotation (so the test cannot pass by a shared bug).
fn rotated(k: u32) -> OcrImage {
let src = l_line();
let (w, h) = (src.width as usize, src.height as usize);
let (nw, nh) = if k.is_multiple_of(2) { (src.width, src.height) } else { (src.height, src.width) };
let mut out = white(nw, nh);
for (y, row) in src.rgba.chunks_exact(w * 4).enumerate() {
for (x, px) in row.as_chunks::<4>().0.iter().enumerate() {
if px[0] != 0 {
continue;
}
let (nx, ny) = match k {
1 => (h - 1 - y, x),
2 => (w - 1 - x, h - 1 - y),
3 => (y, w - 1 - x),
_ => (x, y),
};
fill(&mut out, nx as u32, ny as u32, 1, 1);
}
}
out
}
/// A ruled fixture sheared by `degrees` (lines running downhill to the right for positive
/// angles): four 8-px bars across a 300 × 120 page.
fn sheared(degrees: f64) -> OcrImage {
let (w, h) = (300u32, 120u32);
let mut img = white(w, h);
let slope = degrees.to_radians().tan();
for (base, height) in [(20u32, 8u32), (45, 8), (70, 8), (95, 8)] {
for x in 20..280u32 {
let y = (base as f64 + (x as f64 - 150.0) * slope).round().clamp(0.0, f64::from(h - height - 1)) as u32;
fill(&mut img, x, y, 1, height);
}
}
img
}
/// With the four opt-in flags off and a dpi at or above 300, the raster passes through
/// untouched and the inverse transform is exact.
#[test]
fn flags_off_and_adequate_dpi_is_an_identity_pass_through() {
let src = l_line();
let p = preprocess(src.clone(), 300.0, &PreprocessOptions::default()).unwrap();
assert_eq!(p.image.rgba, src.rgba);
assert_eq!(p.dpi, 300.0);
assert_eq!(p.inverse_transform, InverseTransform::identity());
assert_eq!(p.inverse_transform.map_rect([3.0, 7.0, 41.0, 19.0]), [3.0, 7.0, 41.0, 19.0]);
}
/// With a step on, a scan below 300 dpi is enlarged by 300/src first, and its boxes map
/// back to the original raster.
#[test]
fn low_dpi_scans_are_upscaled_for_the_steps_and_boxes_map_back() {
let src = white(100, 50);
let on = PreprocessOptions { denoise: true, ..Default::default() };
let p = preprocess(src.clone(), 150.0, &on).unwrap();
assert_eq!((p.image.width, p.image.height), (200, 100));
assert_eq!(p.dpi, 300.0);
assert_eq!(p.inverse_transform.map_rect([0.0, 0.0, 200.0, 100.0]), [0.0, 0.0, 100.0, 50.0]);
assert_eq!(p.inverse_transform.apply(2.0, 4.0), (1.0, 2.0));
// 300 and 600 dpi are not resampled; a broken dpi is left alone.
assert_eq!(preprocess(src.clone(), 600.0, &on).unwrap().image.width, 100);
assert_eq!(preprocess(src, f32::NAN, &on).unwrap().image.width, 100);
}
/// With every step off a low-dpi render is read exactly as rendered: not resampled, with
/// the identity as its way back. (Reading a 72 dpi scan through a 4x enlargement changed
/// what the models read: "due: \€250" came back as "ue: ?250".)
#[test]
fn with_every_step_off_a_low_dpi_render_is_not_resampled() {
let src = l_line();
let p = preprocess(src.clone(), 72.0, &PreprocessOptions::default()).unwrap();
assert_eq!(p.image.rgba, src.rgba);
assert_eq!((p.image.width, p.image.height), (src.width, src.height));
assert_eq!(p.dpi, 72.0, "the render's own resolution");
assert_eq!(p.inverse_transform, InverseTransform::identity());
}
/// The upscale refuses to break the side cap.
#[test]
fn upscaling_respects_the_side_cap() {
let src = white(9999, 10);
let r = preprocess(src, 72.0, &PreprocessOptions { denoise: true, ..Default::default() });
assert!(matches!(r, Err(OcrError::ImageTooLarge)), "upscale past the cap: {r:?}");
}
/// An upright page is left alone by the orientation detector.
#[test]
fn upright_pages_are_not_rotated() {
let p = preprocess(l_line(), 300.0, &PreprocessOptions { auto_rotate: true, ..Default::default() }).unwrap();
assert_eq!(p.inverse_transform, InverseTransform::identity());
}
/// Pages scanned at 90/180/270 are detected, turned upright, and their word boxes map back
/// onto the scanned raster's ink.
#[test]
fn quarter_turns_are_detected_corrected_and_mapped_back() {
for k in 1..=3 {
let scanned = rotated(k);
let p = preprocess(scanned.clone(), 300.0, &PreprocessOptions { auto_rotate: true, ..Default::default() }).unwrap();
let corrected = ink_bbox(&p.image).unwrap_or_else(|| panic!("k={k}: the corrected page still has ink"));
// The corrected reading is a horizontal line again: wider than tall.
assert!(corrected[2] - corrected[0] > corrected[3] - corrected[1], "k={k}: {corrected:?}");
// And the box maps back onto the scanned raster's own ink box.
let back = p.inverse_transform.map_rect(corrected);
let original = ink_bbox(&scanned).unwrap();
for i in 0..4 {
assert!((back[i] - original[i]).abs() <= 2.0, "k={k}: {back:?} vs {original:?}");
}
}
}
/// Images under 32 px on a side are never judged; the step is a no-op.
#[test]
fn tiny_images_skip_orientation() {
let src = white(31, 31);
let p = preprocess(src, 300.0, &PreprocessOptions { auto_rotate: true, ..Default::default() }).unwrap();
assert_eq!(p.inverse_transform, InverseTransform::identity());
}
/// Blank pages are inconclusive: every step leaves them alone.
#[test]
fn blank_pages_are_a_noop() {
let src = white(200, 200);
let p = preprocess(src, 300.0, &PreprocessOptions { auto_rotate: true, deskew: true, denoise: true, binarize: true }).unwrap();
assert_eq!(p.inverse_transform, InverseTransform::identity());
}
/// The skew estimator sees a 3° shear (either direction) and leaves a straight page alone.
#[test]
fn skew_is_estimated_and_straight_pages_are_left_alone() {
for degrees in [3.0, -3.0] {
let angle = estimate_skew(&sheared(degrees)).unwrap_or_else(|| panic!("{degrees}° should be found"));
assert!((angle - degrees).abs() <= 0.5, "{degrees}°: got {angle}");
}
assert!(estimate_skew(&sheared(0.0)).is_none(), "a straight page is a no-op");
assert!(estimate_skew(&l_line()).is_none(), "glyph lines without a shear are a no-op");
}
/// Deskew straightens ±3° lines (the vertical span tightens) and the centre maps back to
/// itself.
#[test]
fn deskew_corrects_plus_and_minus_three_degrees() {
for degrees in [3.0, -3.0] {
let src = sheared(degrees);
let before = ink_bbox(&src).unwrap();
let p = preprocess(src.clone(), 300.0, &PreprocessOptions { deskew: true, ..Default::default() }).unwrap();
let after = ink_bbox(&p.image).unwrap();
assert!(after[3] - after[1] < before[3] - before[1], "{degrees}°: {before:?} → {after:?}");
// The exact inverse maps the corrected centre back to the scanned centre.
let (cx, cy) = (f64::from(src.width) / 2.0, f64::from(src.height) / 2.0);
let (bx, by) = p.inverse_transform.apply(cx, cy);
assert!((bx - cx).abs() < 1.0 && (by - cy).abs() < 1.0, "{degrees}°: ({bx}, {by})");
}
}
/// Deskew no-ops on small images (under 64 px) — the detector is never consulted.
#[test]
fn small_images_skip_deskew() {
let src = white(63, 63);
let p = preprocess(src, 300.0, &PreprocessOptions { deskew: true, ..Default::default() }).unwrap();
assert_eq!(p.inverse_transform, InverseTransform::identity());
}
/// The median filter removes isolated specks, keeps solid strokes, and never changes the
/// dimensions.
#[test]
fn denoise_removes_specks_and_keeps_dimensions() {
let mut src = white(32, 32);
fill(&mut src, 15, 15, 1, 1); // salt
fill(&mut src, 4, 4, 5, 5); // a solid stroke
let p = preprocess(src, 300.0, &PreprocessOptions { denoise: true, ..Default::default() }).unwrap();
assert_eq!((p.image.width, p.image.height), (32, 32));
assert_eq!(p.image.byte(15.0, 15.0, 0), 255, "an isolated speck is gone");
assert_eq!(p.image.byte(6.0, 6.0, 0), 0, "the inside of a solid block stays");
assert_eq!(p.inverse_transform, InverseTransform::identity());
}
/// Sauvola keeps the polarity (dark ink stays dark, paper stays light) and the metadata.
/// The fixture is a thin grey stroke: its windows mix ink and paper, so the local
/// threshold separates them (a perfectly flat mid-tone area has no contrast and whitens,
/// which is Sauvola working as designed).
#[test]
fn binarize_keeps_polarity_and_metadata() {
let (w, h) = (64u32, 64u32);
let mut src = white(w, h);
for y in 26..30 {
for x in 8..56 {
let o = ((y * w + x) * 4) as usize;
if let Some(p) = src.rgba.get_mut(o..o + 3) {
p.copy_from_slice(&[70, 70, 70]); // a grey scan's ink, far below paper
}
}
}
let p = preprocess(src, 300.0, &PreprocessOptions { binarize: true, ..Default::default() }).unwrap();
assert_eq!((p.image.width, p.image.height), (w, h));
assert_eq!(p.dpi, 300.0);
assert_eq!(p.image.byte(30.0, 28.0, 0), 0, "ink stays dark");
assert_eq!(p.image.byte(2.0, 2.0, 0), 255, "paper stays light");
for px in p.image.rgba.as_chunks::<4>().0.iter() {
assert!((px[0] == 0 || px[0] == 255) && px[0] == px[1] && px[1] == px[2], "{px:?}");
}
}
/// The inverse transform composes: an upscaled, turned, deskewed page maps corrected
/// points back inside the original raster.
#[test]
fn inverse_transform_maps_points_back_through_every_step() {
let scanned = rotated(1); // a page photographed on its side
let p = preprocess(scanned.clone(), 150.0, &PreprocessOptions { auto_rotate: true, deskew: true, ..Default::default() }).unwrap();
let (w, h) = (f64::from(p.image.width), f64::from(p.image.height));
for (x, y) in [(0.0, 0.0), (w - 1.0, 0.0), (0.0, h - 1.0), (w - 1.0, h - 1.0), (w / 2.0, h / 2.0)] {
let (bx, by) = p.inverse_transform.apply(x, y);
assert!((-2.0..=f64::from(scanned.width) + 2.0).contains(&bx), "x {x} → {bx}");
assert!((-2.0..=f64::from(scanned.height) + 2.0).contains(&by), "y {y} → {by}");
}
// The scale step, alone, is exact.
assert_eq!(InverseTransform::scale(0.5).apply(4.0, 10.0), (2.0, 5.0));
}
/// A realistic letter page (one line of type on white, at 300 dpi) reads as upright: the
/// row axis bands decisively sharper than the column axis, and the near-balanced
/// bottom-heaviness of real mixed-case text is below the 15% flip bar, so the page is left
/// alone rather than risk flipping a good scan upside down.
#[test]
fn realistic_letter_pages_are_left_upright() {
let (w, h) = (1200u32, 1650u32);
let mut img = white(w, h);
let mut x = 120u32;
let base = 300u32;
let mut seed = 7u64;
let mut rnd = || {
seed = seed.wrapping_mul(6364136223846793005).wrapping_add(1442695040888963407);
(seed >> 33) as u32
};
while x < 1000 {
let word = rnd() % 5 + 2;
for _ in 0..word {
let kind = rnd() % 4;
let wl = rnd() % 8 + 3;
match kind {
0 => fill(&mut img, x, base - 20, wl, 20), // x-height
1 => fill(&mut img, x, base - 34, wl, 34), // ascender
2 => fill(&mut img, x, base - 20, wl, 28), // descender
_ => {
fill(&mut img, x, base - 20, 2, 20);
fill(&mut img, x + 3, base - 14, 2, 14); // stems
}
}
x += wl + 2;
}
x += 12; // space
}
assert_eq!(detect_orientation(&img), 0);
let p = preprocess(img, 300.0, &PreprocessOptions { auto_rotate: true, ..Default::default() }).unwrap();
assert_eq!(p.inverse_transform, InverseTransform::identity());
}
/// Hostile inputs are errors or no-ops, never panics: 1×1 rasters, all-black pages, NaN
/// boxes through the inverse map.
#[test]
fn hostile_inputs_never_panic() {
let tiny = white(1, 1);
let all = PreprocessOptions { auto_rotate: true, deskew: true, denoise: true, binarize: true };
let p = preprocess(tiny, 300.0, &all).unwrap();
assert_eq!((p.image.width, p.image.height), (1, 1));
// All-black: no paper, nothing to judge.
let mut black = white(80, 80);
for px in black.rgba.as_chunks_mut::<4>().0 {
px.copy_from_slice(&[0, 0, 0, 255]);
}
let p = preprocess(black, 300.0, &all).unwrap();
assert_eq!(p.inverse_transform, InverseTransform::identity(), "all-black is inconclusive");
// NaN boxes never poison downstream math: the finite corners bound the mapped box,
// and a box with no finite corners comes back unchanged.
let mapped = p.inverse_transform.map_rect([f32::NAN, 0.0, 5.0, 5.0]);
assert!(mapped.iter().all(|v| v.is_finite()), "{mapped:?}");
let unchanged = InverseTransform::identity().map_rect([f32::NAN; 4]);
assert!(unchanged.iter().all(|v| v.is_nan()), "{unchanged:?}");
}
/// The one-pixel dilation is load-bearing, pinned with a fixture that fragments without
/// it: a thin anti-aliased-looking stroke on a grey scan (alternating dark and light
/// pixels) — the raw Sauvola mask drops the light runs (the local window sits on a grey
/// page, so the threshold falls below them), while the binarized image keeps the stroke
/// whole.
#[test]
fn binarize_without_the_dilation_the_stroke_fragments_and_with_it_stays_whole() {
let (w, h) = (64u32, 64u32);
let mut src = white(w, h);
let set = |img: &mut OcrImage, x: u32, y: u32, v: u8| {
let o = ((y * w + x) * 4) as usize;
if let Some(p) = img.rgba.get_mut(o..o + 3) {
p.copy_from_slice(&[v, v, v]);
}
};
for px in src.rgba.as_chunks_mut::<4>().0.iter_mut() {
px[..3].copy_from_slice(&[210, 210, 210]); // a grey scan's paper
}
// The stroke: one pixel tall, alternating dark (reads as ink) and light (an
// anti-aliased shoulder the threshold alone drops) in runs of two.
for x in 8..56u32 {
let v = if (x / 2) % 2 == 0 { 110 } else { 170 };
set(&mut src, x, 32, v);
}
let mask = sauvola_mask(&src);
let at = |x: u32, y: u32| mask[y as usize * w as usize + x as usize];
let dropped: Vec<u32> = (12..52).filter(|&x| !at(x, 32)).collect();
assert!(!dropped.is_empty(), "without the dilation the stroke fragments: these stroke pixels fall under the threshold at {dropped:?}");
let p = preprocess(src, 300.0, &PreprocessOptions { binarize: true, ..Default::default() }).unwrap();
// With the dilation the stroke is whole: every position on it has ink within its
// 8-neighbourhood.
for x in 12..=51u32 {
let ink_near = (-1i32..=1).any(|dy| {
(-1i32..=1).any(|dx| {
let (nx, ny) = (x as i32 + dx, 32 + dy);
p.image.byte(f64::from(nx), f64::from(ny), 0) == 0
})
});
assert!(ink_near, "the stroke is broken at x={x}");
}
}
/// The deskew inverse, checked at OFF-CENTRE points (the centre maps to itself under any
/// rotation, so it cannot catch a wrong sign): a point on a straightened line maps back
/// onto the sheared source line, uphill and downhill.
#[test]
fn deskew_inverse_maps_off_centre_points_back_onto_the_source_line() {
for degrees in [3.0, -3.0] {
let src = sheared(degrees);
let p = preprocess(src, 300.0, &PreprocessOptions { deskew: true, ..Default::default() }).unwrap();
let slope = degrees.to_radians().tan();
// The corrected first line sits at y = 20 (the fixture's base); the same ink was
// at 20 + (x − 150)·slope in the source. Well off centre on purpose. The
// rotation moves x a little too (it mixes in y: at most sin(5°)·40 ≈ 3.5 px
// here), so the line is checked at the mapped x — a wrong sign still misses it
// by ±(x−150)·slope, 6+ px at these offsets.
for x in [30.0f64, 150.0, 270.0] {
let (sx, sy) = p.inverse_transform.apply(x, 20.0);
assert!((sx - x).abs() < 4.0, "{degrees}° x={x}: mapped to ({sx}, {sy})");
let expected = 20.0 + (sx - 150.0) * slope;
assert!((sy - expected).abs() < 2.0, "{degrees}° x={x}: ({sx}, {sy}), the source line is at {expected}");
}
}
}
}
crates/ocr/src/tesseract.rs
+1022
View File
File diff suppressed because it is too large Load Diff
crates/preflight/fuzz/Cargo.toml
+32
View File
@@ -0,0 +1,32 @@
[package]
name = "pdfcraft-preflight-fuzz"
version = "0.0.0"
publish = false
edition = "2024"
license = "MIT OR Apache-2.0"
[package.metadata]
cargo-fuzz = true
# Detached from the PdfCraft workspace: run with `cargo +nightly fuzz run verify`
# from crates/preflight/.
[workspace]
[dependencies]
libfuzzer-sys = "0.4"
pdfcraft-cos = { path = "../../cos" }
pdfcraft-preflight = { path = ".." }
[[bin]]
name = "verify"
path = "fuzz_targets/verify.rs"
test = false
doc = false
bench = false
[[bin]]
name = "convert"
path = "fuzz_targets/convert.rs"
test = false
doc = false
bench = false
crates/preflight/fuzz/fuzz_targets/convert.rs
+21
View File
@@ -0,0 +1,21 @@
//! Feeds arbitrary bytes to `convert` at level A2b; the report it returns is discarded.
#![no_main]
use std::sync::Arc;
use libfuzzer_sys::fuzz_target;
use pdfcraft_cos::Document;
use pdfcraft_preflight::{Level, convert};
/// Largest input the target parses; a longer input is dropped before `Document::open` copies it.
const MAX_INPUT: usize = 16 << 20;
fuzz_target!(|data: &[u8]| {
if data.len() > MAX_INPUT {
return;
}
let Ok(mut doc) = Document::open(Arc::new(data.to_vec())) else {
return;
};
let _ = convert(&mut doc, Level::A2b);
});

Some files were not shown because too many files have changed in this diff Show More