Merge remote-tracking branch 'origin/main' into pr-5373

# Conflicts: # ROADMAP.md # docs/gaps.md
Tests: harnesses that render through wgpu take turns (#5354 )
2026-11-04 17:30:18 -06:00 · 2026-11-03 09:02:40 -05:00 · 2026-11-03 09:01:59 -05:00 · 2026-11-03 15:00:45 +01:00 · 2026-11-03 08:55:09 -05:00 · 2026-11-03 04:58:01 +00:00
402 changed files with 18531 additions and 62952 deletions
@@ -6,6 +6,7 @@ on:
  pull_request:
    paths:
      - 'Cargo*'
+      - 'craft-i18n.rev'
      - 'apps/wordcraft/**'
      - 'apps/wordcraft-web/**'
      - 'crates/ui-egui/**'
@@ -14,6 +15,7 @@ on:
    branches: [main]
    paths:
      - 'Cargo*'
+      - 'craft-i18n.rev'
      - 'apps/wordcraft/**'
      - 'apps/wordcraft-web/**'
      - 'crates/ui-egui/**'
@@ -41,6 +43,26 @@ jobs:
      CARGO_INCREMENTAL: '0'
    steps:
      - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
+        with:
+          persist-credentials: false
+
+      # The interface catalogs and craft-proof's Language data come from craft-i18n at the commit in
+      # craft-i18n.rev, so these tests build with the same data as the gate (ci.yml).
+      - name: Check out craft-i18n
+        uses: storytold/craft-common-actions/actions/checkout-craft-i18n@main
+
+      # The catalogs include CJK interface languages, so the UI tests need the suite's fonts, as in
+      # the gate (same commit as ci.yml and release.yml).
+      - name: Check out craft-fonts
+        uses: storytold/craft-common-actions/actions/checkout-craft-fonts@main
+        with:
+          ref: b076417b5880bd4154bd22f00695b1d28c6bea83
+
+      - name: Build with craft-fonts
+        shell: bash
+        run: |
+          echo "CRAFT_FONTS_DIR=$GITHUB_WORKSPACE/craft-fonts" >> "$GITHUB_ENV"
+          echo "CRAFT_FONTS_REQUIRED=1" >> "$GITHUB_ENV"

      - name: Install Linux build and software-rendering dependencies
        if: runner.os == 'Linux'
@@ -11,7 +11,7 @@ on:
        default: ""

 permissions:
-  contents: write
+  contents: read

 concurrency:
  group: release-${{ github.ref }}
@@ -19,6 +19,10 @@ concurrency:

 jobs:
  release:
+    # Only this job publishes the GitHub release, so only it gets write access.
+    permissions:
+      contents: write
+      packages: write
    # Intentionally tracked at @main (not SHA-pinned) so org-wide CI improvements, security fixes, and build optimizations propagate without PR churn across all craftapp repos.
    uses: storytold/craft-common-actions/.github/workflows/release.yml@main
    with:
@@ -26,8 +26,8 @@ permissions:

 jobs:
  windows-arm64:
-    # Immutable supporting workflow revision until the new install contract lands upstream.
-    uses: storytold/craft-common-actions/.github/workflows/windows-arm64.yml@8bb4e5ab95443171104ad88113fe1ef9b0e5ce3f
+    # Intentionally tracked at @main (not SHA-pinned) so org-wide CI improvements, security fixes, and build optimizations propagate without PR churn across all craftapp repos.
+    uses: storytold/craft-common-actions/.github/workflows/windows-arm64.yml@main
    with:
      app-name: wordcraft
      app-dir: WordCraft
@@ -1,13 +1,13 @@
 # WordCraft — instructions for agents

-WordCraft is a clean-room, open-source, Rust-native word processor targeting Microsoft Word parity — and going further on speed, openness and agent control. It runs natively on macOS, Windows, Linux and BSD, and on the web via WASM. Siblings with the same conventions: `../photocraft` (Photoshop), `../vectorcraft` (Illustrator), `../filmcraft` (Premiere), `../lightcraft` (Lightroom), `../pdfcraft` (Acrobat), `../effectcraft` (After Effects), `../designcraft` (InDesign). Shared rules and learnings: [`storytold/craftrules`](https://github.com/storytold/craftrules) (`../../craftrules`) — read its `AGENTS.md`.
+WordCraft is a clean-room, open-source, Rust-native word processor targeting Microsoft Word parity — and going further on speed, openness and agent control. It runs natively on macOS, Windows, Linux and BSD, and on the web via WASM. Siblings with the same conventions: `../photocraft` (Photoshop), `../vectorcraft` (Illustrator), `../filmcraft` (Premiere), `../lightcraft` (Lightroom), `../pdfcraft` (Acrobat), `../effectcraft` (After Effects), `../designcraft` (InDesign).

 ## Start every session here
 1. Read `plan/STATUS.md` (current milestone, next task), then the task in `plan/execution-plan.md` and the relevant `plan/architecture.md` section. `plan/` is gitignored (local only); if it's missing, start from `ROADMAP.md`, `docs/gaps.md` and `docs/roadmap.md` (Current focus).
 2. Follow the autonomous operation protocol (`plan/execution-plan.md` §5). Don't stop to ask unless a decision is genuinely the owner's (licensing, publishing, pushing to new remotes, secrets).

 ## Never crash
-People trust WordCraft with their writing; a crash loses their work. **This outranks feature work**: never ship a feature through a panic path, and fix a crash before building on top of it. Standard: [`craftrules/standards/never-crash.md`](https://github.com/storytold/craftrules/blob/main/standards/never-crash.md).
+People trust WordCraft with their writing; a crash loses their work. **This outranks feature work**: never ship a feature through a panic path, and fix a crash before building on top of it.
 - **No panics in non-test code:** no `unwrap()`, `expect()`, `panic!`, `unreachable!`, `todo!`, `unimplemented!`; no `unsafe` (`unsafe_code = "forbid"`).
 - **Errors are `Result<T, E>`** through the crate's error type and `?`. An unfinished feature returns an error or is disabled; it never panics.
 - **Input-derived numbers are hostile** (files, commands, MCP/control params): `get()` instead of `[i]`, slice strings only at char boundaries, checked/saturating arithmetic, clamp sizes, cap allocations, bound recursion.
@@ -20,7 +20,7 @@ People trust WordCraft with their writing; a crash loses their work. **This outr
 - Never copy, trace, screenshot-crop or recreate icons, images, templates, themes, clip art, fonts, cursors, sounds or any other asset from Microsoft Word/Office or any Microsoft, Adobe, Avid or Autodesk product. Not even "temporarily".
 - Every asset must be **original** (drawn in code — prefer this: `crates/ui-egui/src/icons.rs`), **public domain / CC0**, **OSI open source**, or **Creative Commons that allows redistribution**, or licensed open source by a contributor who made it.
 - **Every asset file has a row in [`ATTRIBUTION.md`](ATTRIBUTION.md)** (author, source, licence). `cargo xtask assets` (part of `cargo xtask ci`) fails otherwise. Add the row in the same commit as the file.
- Fonts: new font files go to [`storytold/craft-fonts`](https://github.com/storytold/craft-fonts), never this repo; it's an optional build input (`CRAFT_FONTS_DIR`). Documents asking for proprietary fonts (Calibri, Aptos, Cambria…) are rendered with installed system fonts or metric-compatible open substitutes (`crates/fonts/src/word.rs`) — never bundle proprietary fonts.
+- Fonts: new font files go to [`storytold/craft-fonts`](https://github.com/storytold/craft-fonts), never this repo; it's an optional build input (`CRAFT_FONTS_DIR`). Spelling word lists and hyphenation patterns live in [`storytold/craft-i18n`](https://github.com/storytold/craft-i18n) `language-data/`, never this repo; they are embedded from `CRAFT_I18N_DIR` (pinned by `craft-i18n.rev`, which CI checks out). Without it the app builds, but English spelling falls back to an installed Hunspell English or the built-in Moby word list (with no American/British variant table) and pattern hyphenation is off (Bulgarian, Turkish and Russian still hyphenate by rule), so proofing tests need it. Documents asking for proprietary fonts (Calibri, Aptos, Cambria…) are rendered with installed system fonts or metric-compatible open substitutes (`crates/fonts/src/word.rs`) — never bundle proprietary fonts.
 - Templates, sample documents and themes are our own text and colours (`crates/engine/src/sample.rs`, `cmd/design.rs`). Demo images are public domain, with sources recorded.

 ## Clean room
@@ -34,11 +34,12 @@ People trust WordCraft with their writing; a crash loses their work. **This outr
 | L0 | `geom` | units, rects, measurement parsing |
 | L1 | `doc`, `fonts` | document model + edit primitives; font DB, shaping, Word font substitution |
 | L2 | `layout`, `docx`, `formats` | line breaking, pagination, tables, headers/footers, hit testing; OOXML I/O; TXT/MD/HTML/RTF/ODT |
-| L3 | `render`, `pdf`, `proof` | vello_cpu rasteriser; krilla PDF; proofing |
+| L3 | `render`, `pdf` | vello_cpu rasteriser; krilla PDF |
 | L4 | `engine` | Session, undo, **command registry**, Word feature catalog, samples, I/O dispatch |
 | L5 | `mcp` | MCP server (headless or bridged to the app) |
 | L6 | `ui-egui` | Word-style egui front end (swappable) |
 | apps | `apps/wordcraft`, `apps/wordcraft-cli`, `apps/wordcraft-web` | binaries |
+| external | `craft-proof` (craft-libs, used as `wordcraft-proof`, sits at L1) | proofing: spelling, grammar, hyphenation; its word lists and patterns are craft-i18n's `language-data/` (`CRAFT_I18N_DIR`) |

 - **Everything is a command.** User-visible behaviour = a `CommandSpec` in `crates/engine/src/cmd/*.rs` (id, label, ribbon location, shortcut, params doc, `enabled`, `run`) + tests. UI-only commands (`ui.*`) live in `crates/ui-egui/src/lib.rs`. The ribbon, shortcuts, command search, CLI, control channel and MCP all dispatch by id. Programmatic calls never open dialogs.
 - **Parity is measured:** `crates/engine/src/catalog.rs` lists Word's ribbon/menu features with command ids. `cargo xtask parity` writes `docs/parity-checklist.md`; a test enforces a floor that only rises. Implement missing ids to raise it.
@@ -63,22 +64,24 @@ Typing, Enter, Backspace, Tab, lists, AutoCorrect and AutoFormat follow Word's o
 - Parallel agents: separate `CARGO_TARGET_DIR` per agent; edit only the crates you own; delete your target dir when done (disk).

 ## Roadmap
-Progress docs follow [`craftrules/standards/progress-docs.md`](https://github.com/storytold/craftrules/blob/main/standards/progress-docs.md): `ROADMAP.md` (stage, headline numbers, progress log), `docs/target-app-parity.md` (the assessment), `docs/gaps.md` (ranked work list), `docs/roadmap.md` (milestones, Current focus), `docs/architecture.md`, and the parity checklists `docs/file-format-parity.md`, `docs/layout-parity.md`, `docs/typing-parity.md`, `docs/ui-parity.md`, `docs/hardware-parity.md`, `docs/localization-parity.md`. When work lands, update the gap, the parity doc and the progress log, and bump each touched doc's status line and revision history.
+Progress docs: `ROADMAP.md` (stage, headline numbers, progress log), `docs/target-app-parity.md` (the assessment), `docs/gaps.md` (ranked work list), `docs/roadmap.md` (milestones, Current focus), `docs/architecture.md`, and the parity checklists `docs/file-format-parity.md`, `docs/layout-parity.md`, `docs/typing-parity.md`, `docs/ui-parity.md`, `docs/hardware-parity.md`, `docs/localization-parity.md`. When work lands, update the gap, the parity doc and the progress log, and bump each touched doc's status line and revision history.

 ## Contributor credits (About window)

 - About ▸ Contributors/Models are compiled into the binary from `contributors/contributors.json`
-  (commit stats; generated, never hand-edit) and `contributors/people.toml` (names people chose for
+  (commit stats; never hand-edit) and `contributors/people.toml` (names people chose for
  themselves). See `docs/contributors.md`.
 - **Agents working for a contributor:** when you prepare a PR, check whether your human's GitHub
  username has a `[people.<username>]` entry in `contributors/people.toml`. If not, ask them once
  whether they want to be credited by more than their username: a real name, a display name, and/or
  their public GitHub profile name (`sync_github_name = true`). If yes, add **only their own** entry
-  (copy the template at the top of the file, or run
-  `python3 ../../craftrules/scripts/contributors.py --add-me . --real-name "…" --sync-github-name`)
+  (copy the template at the top of the file)
  and include it in their PR, committed as them. If no, change nothing: they are credited as
  `@username` anyway.
 - Never add, edit, guess or copy anyone else's entry or name (not from git config, commit authors or
  GitHub profiles). Never hand-edit `contributors.json`.
- Maintainers refresh the stats with `python3 ../../craftrules/scripts/contributors.py .` (it also
-  re-verifies who wrote each `people.toml` entry; `--check` only verifies).
+
+## CI workflows
+- Workflows in `.github/workflows/` call the shared workflows in [`storytold/craft-common-actions`](https://github.com/storytold/craft-common-actions) at `@main`, with their inputs and secrets. No other jobs: if no shared workflow does what's needed, it doesn't go here.
+- Don't add or change CI in a feature or fix PR. If the existing workflows can't build or test a change, link an existing craft-common-actions issue or PR, or open a new issue, or a PR only for a small fix that is safe for every app and does not increase CI time.
+- Some workflow files here still run their own jobs. Don't add to them. Moving a job into craft-common-actions is its own task, never part of another PR, and the job stays here until a shared workflow runs it.
@@ -10,15 +10,6 @@ Generated-in-code art is original and has no file to list: the UI icon set (`cra
 |---|---|---|---|---|
 | `egui` dependency: `epaint_default_fonts/fonts/egui-icons.ttf` | John Slegers (emoji-icon-font) | https://github.com/storytold/egui/blob/173cc7375d35dc5fbc5b5d0994fdf787f547c5d1/crates/epaint_default_fonts/fonts/egui-icons.txt; original https://github.com/jslegers/emoji-icon-font | MIT (full copyright and permission text in NOTICE) | Small egui special-icon subset; embedded by default_fonts, retained in FontDefinitions::default() |
 | `egui` dependency: `epaint_default_fonts/fonts/emoji-icon-font.ttf` | John Slegers | https://github.com/storytold/egui/blob/173cc7375d35dc5fbc5b5d0994fdf787f547c5d1/crates/epaint_default_fonts/fonts/emoji-icon-font-mit-license.txt; original https://github.com/jslegers/emoji-icon-font | MIT (full copyright and permission text in NOTICE) | Parent monochrome icon/emoji face embedded by monochrome_emoji_fonts; separate from the egui-icons subset |
-| `assets/hyphenation/en-us.pat` | DesignCraft contributors (generated) | trained from the Moby list by DesignCraft's patgen | Public Domain (CC0-1.0) | Our own Liang hyphenation patterns (no TeX patterns) |
-| `assets/hyphenation/en-us.dic` | Grady Ward (Moby Hyphenator II word list); converted by DesignCraft contributors | https://www.gutenberg.org/ebooks/3204 (file `mhyph.txt`, SHA-256 `eeb30474c86b8af3469035ec1a0913e35905325ca885290db9dfed9881e230ac`), via DesignCraft | Public Domain | ~165k words with break points; drives spelling and hyphenation |
-| `assets/spelling/en-extra.txt` | WordCraft contributors | original word list written for this repository (common modern words the Moby list lacks); no other dictionary copied | MIT OR Apache-2.0 | ~240 lowercase English base forms supplementing spelling (#520), including British spellings (#40) |
-| `assets/spelling/en-variants.txt` | WordCraft contributors | original list written for this repository from general knowledge of English spelling; no other dictionary or variant list copied | MIT OR Apache-2.0 | ~280 American/British spelling pairs (-or/-our, -er/-re, -ize/-ise, -yze/-yse, -ense/-ence, doubled l, ae/oe…) with a policy per English: en-US, en-CA and the British-spelling Englishes (#1281, #1045) |
-| `assets/spelling/ru-extra.txt` | WordCraft contributors | original word list written for this repository (common modern Russian words older Hunspell dictionaries lack, with their declension classes); no other dictionary copied | MIT OR Apache-2.0 | ~200 Russian base forms supplementing spelling; their forms are generated by `crates/proof/src/ru/extra.rs` |
-| `assets/hyphenation/pl.pat` | Hanna Kołodziejska, Bogusław Jackowski, Marek Ryćko (Polish TeX hyphenation patterns, 1987–1995); hyph-utf8 package | https://github.com/hyphenation/tex-hyphen (`hyph-utf8/tex/generic/hyph-utf8/patterns/tex/hyph-pl.tex`, SHA-256 `83ddbbd21bc06a44bc4f4a4c49c38782e809cff5f026b764c044daa29e818843`), bundled unmodified | MIT (the file is offered under MIT or Knuth's public-domain terms; WordCraft uses MIT, whose notice is in the file's header) | 4,053 Liang patterns and 20 exception words; Polish hyphenation |
-| `assets/hyphenation/pt.pat` | Pedro J. de Rezende, J. Joao Dias Almeida, Leonardo Araujo, Aline Benevides (Portuguese TeX hyphenation patterns, 1987–2024); hyph-utf8 package | https://github.com/hyphenation/tex-hyphen (`hyph-utf8/tex/generic/hyph-utf8/patterns/tex/hyph-pt.tex`, SHA-256 `c110a39e501db372d1d755e1c64464321a2efa7d8e9617f66001000389b941f2`), bundled unmodified | BSD 3-clause (the file's licence header names it and carries the notice) | 426 Liang patterns and 2 exception words; Portuguese hyphenation |
-| `assets/hyphenation/it.pat` | Claudio Beccari (Italian TeX hyphenation patterns, 2008–2014); hyph-utf8 package | https://github.com/hyphenation/tex-hyphen (`hyph-utf8/tex/generic/hyph-utf8/patterns/tex/hyph-it.tex`, SHA-256 `6ce56ed6ed2ca7c0688838e366e6595e0429f984f4fc6e96ec045cebb1e76a47`), bundled unmodified | MIT (the file is offered under LPPL 1.3+ or MIT; WordCraft uses MIT, whose notice is in the file's header) | 355 Liang patterns, no exception words; Italian hyphenation |
-| `assets/hyphenation/de.pat` | Deutschsprachige Trennmustermannschaft: Stephan Hennig, Werner Lemberg, Günter Milde, Sander van Geloven, Georg Pfeiffer, Gisbert W. Selke, Tobias Wendorf, Keno Wehr (German TeX hyphenation patterns, reformed spelling, 2013–2024); hyph-utf8 package | https://github.com/hyphenation/tex-hyphen (`hyph-utf8/tex/generic/hyph-utf8/patterns/tex/hyph-de-1996.tex`, SHA-256 `374ad1ce3263f8a2791ec070ef9b516c532dae64456f3fb656e617e8ae53a9d3`), bundled unmodified | MIT (the notice is in the file's header) | 36,709 Liang patterns, no exception words; German hyphenation (de-DE, de-AT, de-CH) |
 | `assets/app-icon/wordcraft-1024.png` | WordCraft contributors | original artwork drawn in SVG (`assets/app-icon/wordcraft.svg`), rendered by `packaging/icons.sh` | MIT OR Apache-2.0 | Placeholder app icon until the WordCraft mascot drawing lands |
 | `packaging/macos/dmg/background.svg` | @XusBadia | original work for this repository, derived from the WordCraft app icon (`assets/app-icon/wordcraft.svg`, referenced via `<image>`, not copied); text is outlined Inter / JetBrains Mono glyph paths | MIT OR Apache-2.0, like the code ([`LICENSE-MIT`](LICENSE-MIT), [`LICENSE-APACHE`](LICENSE-APACHE)) | WordCraft macOS DMG window background (2026-10-08); used for the Finder window of the macOS DMG, rendered to `background.tiff` by `packaging/macos/dmg/generate.py` |
 | `packaging/macos/dmg/background.tiff` | @XusBadia | Rendered from `packaging/macos/dmg/background.svg` by `packaging/macos/dmg/generate.py` | MIT OR Apache-2.0, like the code ([`LICENSE-MIT`](LICENSE-MIT), [`LICENSE-APACHE`](LICENSE-APACHE)) | 1x + 2x HiDPI TIFF for the macOS DMG window; includes the app icon (see its row) and LittleCMS's built-in sRGB profile ("No copyright, use freely") |
@@ -59,14 +50,15 @@ Generated-in-code art is original and has no file to list: the UI icon set (`cra
 | `docs/images/dark.png` | WordCraft contributors | screenshot of WordCraft itself (sample document written for WordCraft, rendered by `ui_shot`) | MIT OR Apache-2.0 | Original; no Microsoft UI or assets |
 | `docs/images/backstage.png` | WordCraft contributors | screenshot of WordCraft itself (sample document written for WordCraft, rendered by `ui_shot`) | MIT OR Apache-2.0 | Original; no Microsoft UI or assets |
 | `docs/images/layout.png` | WordCraft contributors | screenshot of WordCraft itself (sample document written for WordCraft, rendered by `ui_shot`) | MIT OR Apache-2.0 | Original; no Microsoft UI or assets |
-| `docs/brand/LICENSE-brand.txt` | ArtCraft Team | craftrules `assets/brand/` | ArtCraft trademark, `docs/brand/LICENSE-brand.txt` | Not open source; usable unmodified only |
-| `docs/brand/artcraft-logo-white.png` | ArtCraft Team | craftrules `assets/brand/` | ArtCraft trademark, `docs/brand/LICENSE-brand.txt` | Not open source; usable unmodified only |
-| `docs/brand/artcraft-logo-white.svg` | ArtCraft Team | craftrules `assets/brand/` | ArtCraft trademark, `docs/brand/LICENSE-brand.txt` | Not open source; usable unmodified only |
-| `docs/brand/artcraft-logo.png` | ArtCraft Team | craftrules `assets/brand/` | ArtCraft trademark, `docs/brand/LICENSE-brand.txt` | Not open source; usable unmodified only |
-| `docs/brand/artcraft-logo.svg` | ArtCraft Team | craftrules `assets/brand/` | ArtCraft trademark, `docs/brand/LICENSE-brand.txt` | Not open source; usable unmodified only |
-| `docs/brand/artcraft-mark-black.png` | ArtCraft Team | craftrules `assets/brand/` | ArtCraft trademark, `docs/brand/LICENSE-brand.txt` | Not open source; usable unmodified only |
-| `docs/brand/artcraft-mark-black.svg` | ArtCraft Team | craftrules `assets/brand/` | ArtCraft trademark, `docs/brand/LICENSE-brand.txt` | Not open source; usable unmodified only |
-| `docs/brand/artcraft-mark.png` | ArtCraft Team | craftrules `assets/brand/` | ArtCraft trademark, `docs/brand/LICENSE-brand.txt` | Not open source; usable unmodified only |
-| `docs/brand/artcraft-mark.svg` | ArtCraft Team | craftrules `assets/brand/` | ArtCraft trademark, `docs/brand/LICENSE-brand.txt` | Not open source; usable unmodified only |
+| `docs/brand/LICENSE-brand.txt` | ArtCraft Team | ArtCraft brand kit (project owner) | ArtCraft trademark, `docs/brand/LICENSE-brand.txt` | Not open source; usable unmodified only |
+| `docs/brand/artcraft-logo-white.png` | ArtCraft Team | ArtCraft brand kit (project owner) | ArtCraft trademark, `docs/brand/LICENSE-brand.txt` | Not open source; usable unmodified only |
+| `docs/brand/artcraft-logo-white.svg` | ArtCraft Team | ArtCraft brand kit (project owner) | ArtCraft trademark, `docs/brand/LICENSE-brand.txt` | Not open source; usable unmodified only |
+| `docs/brand/artcraft-logo.png` | ArtCraft Team | ArtCraft brand kit (project owner) | ArtCraft trademark, `docs/brand/LICENSE-brand.txt` | Not open source; usable unmodified only |
+| `docs/brand/artcraft-logo.svg` | ArtCraft Team | ArtCraft brand kit (project owner) | ArtCraft trademark, `docs/brand/LICENSE-brand.txt` | Not open source; usable unmodified only |
+| `docs/brand/artcraft-mark-black.png` | ArtCraft Team | ArtCraft brand kit (project owner) | ArtCraft trademark, `docs/brand/LICENSE-brand.txt` | Not open source; usable unmodified only |
+| `docs/brand/artcraft-mark-black.svg` | ArtCraft Team | ArtCraft brand kit (project owner) | ArtCraft trademark, `docs/brand/LICENSE-brand.txt` | Not open source; usable unmodified only |
+| `docs/brand/artcraft-mark.png` | ArtCraft Team | ArtCraft brand kit (project owner) | ArtCraft trademark, `docs/brand/LICENSE-brand.txt` | Not open source; usable unmodified only |
+| `docs/brand/artcraft-mark.svg` | ArtCraft Team | ArtCraft brand kit (project owner) | ArtCraft trademark, `docs/brand/LICENSE-brand.txt` | Not open source; usable unmodified only |
 | craft-fonts (optional build input, not files in this repo): BIZ UDPGothic, BIZ UDMincho, Shippori Mincho, Noto Sans CJK SC, Noto Sans Arabic | see https://github.com/storytold/craft-fonts/blob/main/ATTRIBUTION.md | embedded only when built with `CRAFT_FONTS_DIR` (all official releases) | OFL-1.1 | Japanese and Chinese UI, Japanese document fallback |
 | craft-i18n (optional build input, not files in this repo): the interface translations | see https://github.com/storytold/craft-i18n/blob/main/ATTRIBUTION.md, which credits every translator of WordCraft's former in-repo catalogs (`crates/ui-egui/src/i18n/*.tsv`, migrated at `wordcraft@806a945`) | embedded only when built with `CRAFT_I18N_DIR`, at the commit in `craft-i18n.rev` (all official releases) | MIT OR Apache-2.0 | Interface languages other than English; clean-room translations from the English interface labels |
+| craft-i18n Language data (optional build input, not files in this repo): the spelling word lists and hyphenation patterns (`language-data/`: the Moby Hyphenator II list and our patterns for English, `en-extra.txt`, `en-variants.txt`, `ru-extra.txt`, and the hyph-utf8 German, Polish, Portuguese and Italian patterns) | see the Language data section of https://github.com/storytold/craft-i18n/blob/main/ATTRIBUTION.md (authors, upstream sources with SHA-256, licences); moved there from `assets/hyphenation/` and `assets/spelling/` byte for byte | embedded by craft-proof (storytold/craft-libs) only when built with `CRAFT_I18N_DIR`, at the commit in `craft-i18n.rev` (all official releases) | Public Domain / CC0-1.0, MIT, BSD-3-Clause, MIT OR Apache-2.0 (per file; see NOTICE) | Spelling and hyphenation; without it English spelling falls back to an installed Hunspell English or craft-proof's built-in Moby list, and pattern hyphenation is off |
@@ -1,13 +1,13 @@
 # WordCraft — instructions for agents

-WordCraft is a clean-room, open-source, Rust-native word processor targeting Microsoft Word parity — and going further on speed, openness and agent control. It runs natively on macOS, Windows, Linux and BSD, and on the web via WASM. Siblings with the same conventions: `../photocraft` (Photoshop), `../vectorcraft` (Illustrator), `../filmcraft` (Premiere), `../lightcraft` (Lightroom), `../pdfcraft` (Acrobat), `../effectcraft` (After Effects), `../designcraft` (InDesign). Shared rules and learnings: [`storytold/craftrules`](https://github.com/storytold/craftrules) (`../../craftrules`) — read its `AGENTS.md`.
+WordCraft is a clean-room, open-source, Rust-native word processor targeting Microsoft Word parity — and going further on speed, openness and agent control. It runs natively on macOS, Windows, Linux and BSD, and on the web via WASM. Siblings with the same conventions: `../photocraft` (Photoshop), `../vectorcraft` (Illustrator), `../filmcraft` (Premiere), `../lightcraft` (Lightroom), `../pdfcraft` (Acrobat), `../effectcraft` (After Effects), `../designcraft` (InDesign).

 ## Start every session here
 1. Read `plan/STATUS.md` (current milestone, next task), then the task in `plan/execution-plan.md` and the relevant `plan/architecture.md` section. `plan/` is gitignored (local only); if it's missing, start from `ROADMAP.md`, `docs/gaps.md` and `docs/roadmap.md` (Current focus).
 2. Follow the autonomous operation protocol (`plan/execution-plan.md` §5). Don't stop to ask unless a decision is genuinely the owner's (licensing, publishing, pushing to new remotes, secrets).

 ## Never crash
-People trust WordCraft with their writing; a crash loses their work. **This outranks feature work**: never ship a feature through a panic path, and fix a crash before building on top of it. Standard: [`craftrules/standards/never-crash.md`](https://github.com/storytold/craftrules/blob/main/standards/never-crash.md).
+People trust WordCraft with their writing; a crash loses their work. **This outranks feature work**: never ship a feature through a panic path, and fix a crash before building on top of it.
 - **No panics in non-test code:** no `unwrap()`, `expect()`, `panic!`, `unreachable!`, `todo!`, `unimplemented!`; no `unsafe` (`unsafe_code = "forbid"`).
 - **Errors are `Result<T, E>`** through the crate's error type and `?`. An unfinished feature returns an error or is disabled; it never panics.
 - **Input-derived numbers are hostile** (files, commands, MCP/control params): `get()` instead of `[i]`, slice strings only at char boundaries, checked/saturating arithmetic, clamp sizes, cap allocations, bound recursion.
@@ -20,7 +20,7 @@ People trust WordCraft with their writing; a crash loses their work. **This outr
 - Never copy, trace, screenshot-crop or recreate icons, images, templates, themes, clip art, fonts, cursors, sounds or any other asset from Microsoft Word/Office or any Microsoft, Adobe, Avid or Autodesk product. Not even "temporarily".
 - Every asset must be **original** (drawn in code — prefer this: `crates/ui-egui/src/icons.rs`), **public domain / CC0**, **OSI open source**, or **Creative Commons that allows redistribution**, or licensed open source by a contributor who made it.
 - **Every asset file has a row in [`ATTRIBUTION.md`](ATTRIBUTION.md)** (author, source, licence). `cargo xtask assets` (part of `cargo xtask ci`) fails otherwise. Add the row in the same commit as the file.
- Fonts: new font files go to [`storytold/craft-fonts`](https://github.com/storytold/craft-fonts), never this repo; it's an optional build input (`CRAFT_FONTS_DIR`). Documents asking for proprietary fonts (Calibri, Aptos, Cambria…) are rendered with installed system fonts or metric-compatible open substitutes (`crates/fonts/src/word.rs`) — never bundle proprietary fonts.
+- Fonts: new font files go to [`storytold/craft-fonts`](https://github.com/storytold/craft-fonts), never this repo; it's an optional build input (`CRAFT_FONTS_DIR`). Spelling word lists and hyphenation patterns live in [`storytold/craft-i18n`](https://github.com/storytold/craft-i18n) `language-data/`, never this repo; they are embedded from `CRAFT_I18N_DIR` (pinned by `craft-i18n.rev`, which CI checks out). Without it the app builds, but English spelling falls back to an installed Hunspell English or the built-in Moby word list (with no American/British variant table) and pattern hyphenation is off (Bulgarian, Turkish and Russian still hyphenate by rule), so proofing tests need it. Documents asking for proprietary fonts (Calibri, Aptos, Cambria…) are rendered with installed system fonts or metric-compatible open substitutes (`crates/fonts/src/word.rs`) — never bundle proprietary fonts.
 - Templates, sample documents and themes are our own text and colours (`crates/engine/src/sample.rs`, `cmd/design.rs`). Demo images are public domain, with sources recorded.

 ## Clean room
@@ -34,11 +34,12 @@ People trust WordCraft with their writing; a crash loses their work. **This outr
 | L0 | `geom` | units, rects, measurement parsing |
 | L1 | `doc`, `fonts` | document model + edit primitives; font DB, shaping, Word font substitution |
 | L2 | `layout`, `docx`, `formats` | line breaking, pagination, tables, headers/footers, hit testing; OOXML I/O; TXT/MD/HTML/RTF/ODT |
-| L3 | `render`, `pdf`, `proof` | vello_cpu rasteriser; krilla PDF; proofing |
+| L3 | `render`, `pdf` | vello_cpu rasteriser; krilla PDF |
 | L4 | `engine` | Session, undo, **command registry**, Word feature catalog, samples, I/O dispatch |
 | L5 | `mcp` | MCP server (headless or bridged to the app) |
 | L6 | `ui-egui` | Word-style egui front end (swappable) |
 | apps | `apps/wordcraft`, `apps/wordcraft-cli`, `apps/wordcraft-web` | binaries |
+| external | `craft-proof` (craft-libs, used as `wordcraft-proof`, sits at L1) | proofing: spelling, grammar, hyphenation; its word lists and patterns are craft-i18n's `language-data/` (`CRAFT_I18N_DIR`) |

 - **Everything is a command.** User-visible behaviour = a `CommandSpec` in `crates/engine/src/cmd/*.rs` (id, label, ribbon location, shortcut, params doc, `enabled`, `run`) + tests. UI-only commands (`ui.*`) live in `crates/ui-egui/src/lib.rs`. The ribbon, shortcuts, command search, CLI, control channel and MCP all dispatch by id. Programmatic calls never open dialogs.
 - **Parity is measured:** `crates/engine/src/catalog.rs` lists Word's ribbon/menu features with command ids. `cargo xtask parity` writes `docs/parity-checklist.md`; a test enforces a floor that only rises. Implement missing ids to raise it.
@@ -62,4 +63,9 @@ Typing, Enter, Backspace, Tab, lists, AutoCorrect and AutoFormat follow Word's o
 - Parallel agents: separate `CARGO_TARGET_DIR` per agent; edit only the crates you own; delete your target dir when done (disk).

 ## Roadmap
-Progress docs follow [`craftrules/standards/progress-docs.md`](https://github.com/storytold/craftrules/blob/main/standards/progress-docs.md): `ROADMAP.md` (stage, headline numbers, progress log), `docs/target-app-parity.md` (the assessment), `docs/gaps.md` (ranked work list), `docs/roadmap.md` (milestones, Current focus), `docs/architecture.md`, and the parity checklists `docs/file-format-parity.md`, `docs/layout-parity.md`, `docs/typing-parity.md`, `docs/ui-parity.md`, `docs/hardware-parity.md`, `docs/localization-parity.md`. When work lands, update the gap, the parity doc and the progress log, and bump each touched doc's status line and revision history.
+Progress docs: `ROADMAP.md` (stage, headline numbers, progress log), `docs/target-app-parity.md` (the assessment), `docs/gaps.md` (ranked work list), `docs/roadmap.md` (milestones, Current focus), `docs/architecture.md`, and the parity checklists `docs/file-format-parity.md`, `docs/layout-parity.md`, `docs/typing-parity.md`, `docs/ui-parity.md`, `docs/hardware-parity.md`, `docs/localization-parity.md`. When work lands, update the gap, the parity doc and the progress log, and bump each touched doc's status line and revision history.
+
+## CI workflows
+- Workflows in `.github/workflows/` call the shared workflows in [`storytold/craft-common-actions`](https://github.com/storytold/craft-common-actions) at `@main`, with their inputs and secrets. No other jobs: if no shared workflow does what's needed, it doesn't go here.
+- Don't add or change CI in a feature or fix PR. If the existing workflows can't build or test a change, link an existing craft-common-actions issue or PR, or open a new issue, or a PR only for a small fix that is safe for every app and does not increase CI time.
+- Some workflow files here still run their own jobs. Don't add to them. Moving a job into craft-common-actions is its own task, never part of another PR, and the job stays here until a shared workflow runs it.
@@ -809,9 +809,9 @@ dependencies = [

 [[package]]
 name = "clipboard-win"
-version = "5.4.1"
+version = "5.4.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "bde03770d3df201d4fb868f2c9c59e66a3e4e2bd06692a0fe701e7103c7e84d4"
+checksum = "052af7878466feccda12ba7a6a67d019d712f296809559b47c12c8cc196d3a9a"
 dependencies = [
 "error-code",
 ]
@@ -1011,6 +1011,45 @@ dependencies = [
 "libc",
 ]

+[[package]]
+name = "craft-atomic"
+version = "0.1.0"
+source = "git+https://github.com/storytold/craft-libs?rev=762a06a4c6b48b522b7d4de84a87917ef90265e6#762a06a4c6b48b522b7d4de84a87917ef90265e6"
+dependencies = [
+ "rustix 1.1.5",
+]
+
+[[package]]
+name = "craft-font-catalog"
+version = "0.1.0"
+source = "git+https://github.com/storytold/craft-libs?rev=762a06a4c6b48b522b7d4de84a87917ef90265e6#762a06a4c6b48b522b7d4de84a87917ef90265e6"
+dependencies = [
+ "fontique",
+ "skrifa 0.47.0",
+ "thiserror 2.0.21",
+ "windows-registry",
+]
+
+[[package]]
+name = "craft-font-store"
+version = "0.1.0"
+source = "git+https://github.com/storytold/craft-libs?rev=762a06a4c6b48b522b7d4de84a87917ef90265e6#762a06a4c6b48b522b7d4de84a87917ef90265e6"
+dependencies = [
+ "craft-atomic",
+ "craft-font-catalog",
+ "flate2",
+ "log",
+ "ruzstd",
+ "serde",
+ "serde_json",
+ "sha2 0.10.9",
+ "skrifa 0.47.0",
+ "tar",
+ "thiserror 2.0.21",
+ "toml",
+ "ureq",
+]
+
 [[package]]
 name = "craft-fonts-build"
 version = "0.1.0"
@@ -1061,6 +1100,17 @@ dependencies = [
 "winsafe",
 ]

+[[package]]
+name = "craft-proof"
+version = "0.1.0"
+source = "git+https://github.com/storytold/craft-libs?rev=47c9f62530db72bc5c3831c86653b47b20c640be#47c9f62530db72bc5c3831c86653b47b20c640be"
+dependencies = [
+ "log",
+ "miniz_oxide 0.9.1",
+ "toml",
+ "unicode-normalization",
+]
+
 [[package]]
 name = "craft-ui"
 version = "0.1.0"
@@ -1084,13 +1134,14 @@ dependencies = [
 [[package]]
 name = "craft-update"
 version = "0.1.0"
-source = "git+https://github.com/storytold/craft-libs?rev=92d392cff132eaf53e13afff77f38b5c11b73aa0#92d392cff132eaf53e13afff77f38b5c11b73aa0"
+source = "git+https://github.com/storytold/craft-libs?rev=c5a1cbfb5f9049f9270955caffb5bee5997aebf7#c5a1cbfb5f9049f9270955caffb5bee5997aebf7"
 dependencies = [
 "chrono",
 "dunce",
 "egui",
 "flate2",
 "getrandom 0.3.4",
+ "image",
 "log",
 "plist",
 "semver",
@@ -1207,9 +1258,9 @@ dependencies = [

 [[package]]
 name = "ctutils"
-version = "0.4.3"
+version = "0.4.7"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "03bb0e1cc970d482d121d9a1744999169b69a07470b3d644a7894e53fcaf4574"
+checksum = "a2376ffd6f96d8a9db59875b4b6b0237d6900b5baf64279714e05493ce64828a"
 dependencies = [
 "cmov",
 ]
@@ -1800,6 +1851,28 @@ dependencies = [
 "bytemuck",
 ]

+[[package]]
+name = "fontique"
+version = "0.11.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6688bc1294fe7117d788937b6c53480169b29c566954af490830d4c09da9516a"
+dependencies = [
+ "hashbrown 0.17.1",
+ "linebender_resource_handle",
+ "memmap2",
+ "objc2 0.6.5",
+ "objc2-core-foundation",
+ "objc2-core-text",
+ "objc2-foundation 0.3.2",
+ "parlance",
+ "read-fonts 0.41.0",
+ "roxmltree",
+ "smallvec",
+ "windows",
+ "windows-core",
+ "yeslogic-fontconfig-sys",
+]
+
 [[package]]
 name = "foreign-types"
 version = "0.5.0"
@@ -3333,6 +3406,16 @@ dependencies = [
 "objc2-foundation 0.2.2",
 ]

+[[package]]
+name = "objc2-core-text"
+version = "0.3.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0cde0dfb48d25d2b4862161a4d5fcc0e3c24367869ad306b0c9ec0073bfed92d"
+dependencies = [
+ "bitflags 2.13.2",
+ "objc2-core-foundation",
+]
+
 [[package]]
 name = "objc2-encode"
 version = "4.1.0"
@@ -3604,6 +3687,12 @@ dependencies = [
 "windows-link",
 ]

+[[package]]
+name = "parlance"
+version = "0.1.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "73072a9470554c8e794778acece2312661218aaabb635600957d952cf01c716e"
+
 [[package]]
 name = "pdf-writer"
 version = "0.15.0"
@@ -4515,6 +4604,12 @@ dependencies = [
 "wait-timeout",
 ]

+[[package]]
+name = "ruzstd"
+version = "0.9.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "69e4ce4a039f42bf25920b95667e4d789e98749ab11bbb8d2c2936f788421bb5"
+
 [[package]]
 name = "ryu"
 version = "1.0.23"
@@ -5722,6 +5817,7 @@ dependencies = [
 "rustls-platform-verifier",
 "ureq-proto",
 "utf8-zero",
+ "webpki-roots",
 ]

 [[package]]
@@ -6105,6 +6201,15 @@ dependencies = [
 "rustls-pki-types",
 ]

+[[package]]
+name = "webpki-roots"
+version = "1.0.11"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f5f280bbb2b287bc8e7de7e3852945a0ff50d1bbcb5ed42b6c7a568c546df171"
+dependencies = [
+ "rustls-pki-types",
+]
+
 [[package]]
 name = "weezl"
 version = "0.1.12"
@@ -6647,12 +6752,13 @@ dependencies = [

 [[package]]
 name = "wordcraft"
-version = "0.12.0"
+version = "0.15.0"
 dependencies = [
 "arboard",
 "chrono",
 "clipboard-win",
 "craft-print",
+ "craft-proof",
 "craft-update",
 "dispatch2",
 "eframe",
@@ -6675,14 +6781,13 @@ dependencies = [
 "wordcraft-doc",
 "wordcraft-engine",
 "wordcraft-fonts",
- "wordcraft-proof",
 "wordcraft-ui-egui",
 "zbus",
 ]

 [[package]]
 name = "wordcraft-cli"
-version = "0.12.0"
+version = "0.15.0"
 dependencies = [
 "serde_json",
 "sys-locale",
@@ -6695,11 +6800,11 @@ dependencies = [

 [[package]]
 name = "wordcraft-control-key"
-version = "0.12.0"
+version = "0.15.0"

 [[package]]
 name = "wordcraft-doc"
-version = "0.12.0"
+version = "0.15.0"
 dependencies = [
 "base64 0.23.1",
 "log",
@@ -6713,7 +6818,7 @@ dependencies = [

 [[package]]
 name = "wordcraft-docbin"
-version = "0.12.0"
+version = "0.15.0"
 dependencies = [
 "cfb",
 "chrono",
@@ -6730,7 +6835,7 @@ dependencies = [

 [[package]]
 name = "wordcraft-docx"
-version = "0.12.0"
+version = "0.15.0"
 dependencies = [
 "aes",
 "base64 0.23.1",
@@ -6754,10 +6859,13 @@ dependencies = [

 [[package]]
 name = "wordcraft-engine"
-version = "0.12.0"
+version = "0.15.0"
 dependencies = [
 "cfb",
 "chrono",
+ "craft-font-catalog",
+ "craft-font-store",
+ "craft-proof",
 "encoding_rs",
 "getrandom 0.3.4",
 "image",
@@ -6777,7 +6885,6 @@ dependencies = [
 "wordcraft-geom",
 "wordcraft-layout",
 "wordcraft-pdf",
- "wordcraft-proof",
 "wordcraft-render",
 "zeroize",
 "zip 3.0.0",
@@ -6785,7 +6892,7 @@ dependencies = [

 [[package]]
 name = "wordcraft-fonts"
-version = "0.12.0"
+version = "0.15.0"
 dependencies = [
 "brotli-decompressor",
 "harfrust 0.13.3",
@@ -6799,7 +6906,7 @@ dependencies = [

 [[package]]
 name = "wordcraft-formats"
-version = "0.12.0"
+version = "0.15.0"
 dependencies = [
 "cfb",
 "chardetng",
@@ -6812,12 +6919,13 @@ dependencies = [
 "quick-xml 0.41.0",
 "wordcraft-doc",
 "wordcraft-geom",
+ "wordcraft-metafile",
 "zip 3.0.0",
 ]

 [[package]]
 name = "wordcraft-geom"
-version = "0.12.0"
+version = "0.15.0"
 dependencies = [
 "image",
 "serde",
@@ -6825,8 +6933,9 @@ dependencies = [

 [[package]]
 name = "wordcraft-layout"
-version = "0.12.0"
+version = "0.15.0"
 dependencies = [
+ "craft-proof",
 "image",
 "js-sys",
 "kurbo",
@@ -6840,12 +6949,11 @@ dependencies = [
 "wordcraft-fonts",
 "wordcraft-geom",
 "wordcraft-metafile",
- "wordcraft-proof",
 ]

 [[package]]
 name = "wordcraft-mcp"
-version = "0.12.0"
+version = "0.15.0"
 dependencies = [
 "log",
 "serde_json",
@@ -6857,7 +6965,7 @@ dependencies = [

 [[package]]
 name = "wordcraft-metafile"
-version = "0.12.0"
+version = "0.15.0"
 dependencies = [
 "kurbo",
 "thiserror 2.0.21",
@@ -6865,7 +6973,7 @@ dependencies = [

 [[package]]
 name = "wordcraft-pdf"
-version = "0.12.0"
+version = "0.15.0"
 dependencies = [
 "chrono",
 "craft-pdf",
@@ -6884,19 +6992,9 @@ dependencies = [
 "wordcraft-metafile",
 ]

-[[package]]
-name = "wordcraft-proof"
-version = "0.12.0"
-dependencies = [
- "log",
- "miniz_oxide 0.9.1",
- "proptest",
- "unicode-normalization",
-]
-
 [[package]]
 name = "wordcraft-render"
-version = "0.12.0"
+version = "0.15.0"
 dependencies = [
 "image",
 "log",
@@ -6910,7 +7008,7 @@ dependencies = [

 [[package]]
 name = "wordcraft-ui-egui"
-version = "0.12.0"
+version = "0.15.0"
 dependencies = [
 "cfb",
 "chrono",
@@ -6941,7 +7039,7 @@ dependencies = [

 [[package]]
 name = "wordcraft-web"
-version = "0.12.0"
+version = "0.15.0"
 dependencies = [
 "eframe",
 "egui",
@@ -6960,7 +7058,7 @@ dependencies = [

 [[package]]
 name = "wordcraft-zotero"
-version = "0.12.0"
+version = "0.15.0"
 dependencies = [
 "log",
 "proptest",
@@ -7123,11 +7221,22 @@ checksum = "9440ea3e5aeabb0ac63af70daf835274065238cdd0cec83418f417eae38bacee"

 [[package]]
 name = "xtask"
-version = "0.12.0"
+version = "0.15.0"
 dependencies = [
 "serde_json",
 ]

+[[package]]
+name = "yeslogic-fontconfig-sys"
+version = "6.0.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1d8b8abf912b9a29ff112e1671c97c33636903d13a69712037190e6805af4f76"
+dependencies = [
+ "dlib",
+ "once_cell",
+ "pkg-config",
+]
+
 [[package]]
 name = "yoke"
 version = "0.8.4"
@@ -4,7 +4,7 @@ members = ["crates/*", "apps/*", "xtask"]
 default-members = ["crates/*", "apps/wordcraft", "apps/wordcraft-cli", "xtask"]

 [workspace.package]
-version = "0.12.0"
+version = "0.15.0"
 edition = "2024"
 license = "MIT OR Apache-2.0"
 rust-version = "1.95"
@@ -21,7 +21,15 @@ wordcraft-docbin = { path = "crates/docbin" }
 wordcraft-formats = { path = "crates/formats" }
 wordcraft-render = { path = "crates/render" }
 wordcraft-pdf = { path = "crates/pdf" }
-wordcraft-proof = { path = "crates/proof" }
+# Proofing is craft-libs' craft-proof (it was crates/proof); its Language data is craft-i18n's
+# language-data/, embedded from CRAFT_I18N_DIR (craft-i18n.rev). The package keeps the
+# `wordcraft-proof` name here so `wordcraft_proof::` paths are unchanged.
+# craft-proof is storytold/craft-libs main at the merge of #497 (flag-based compounding), which
+# also has #496 (review follow-ups, en-AU) and the merged #482–#490/#495 stack; the font store's
+# `language-pack` kind is #486 (CP4.1).
+wordcraft-proof = { package = "craft-proof", git = "https://github.com/storytold/craft-libs", rev = "47c9f62530db72bc5c3831c86653b47b20c640be", version = "=0.1.0" }
+craft-font-store = { git = "https://github.com/storytold/craft-libs", rev = "762a06a4c6b48b522b7d4de84a87917ef90265e6", version = "=0.1.0" }
+craft-font-catalog = { git = "https://github.com/storytold/craft-libs", rev = "762a06a4c6b48b522b7d4de84a87917ef90265e6", version = "=0.1.0" }
 wordcraft-engine = { path = "crates/engine" }
 wordcraft-mcp = { path = "crates/mcp" }
 wordcraft-zotero = { path = "crates/zotero" }
@@ -59,7 +67,8 @@ brotli-decompressor = "5"
 vello_cpu = "0.2"
 image = { version = "0.25", default-features = false, features = ["png", "jpeg", "webp", "gif", "bmp", "tiff"] }
 craft-pdf = { git = "https://github.com/storytold/craft-libs", rev = "92d392cff132eaf53e13afff77f38b5c11b73aa0", version = "=0.1.0", default-features = false, features = ["write"] }
-craft-update = { git = "https://github.com/storytold/craft-libs", version = "=0.1.0", rev = "92d392cff132eaf53e13afff77f38b5c11b73aa0", features = ["egui"] }
+# craft-update: app-specific pretend versions apply to startup and manual checks.
+craft-update = { git = "https://github.com/storytold/craft-libs", version = "=0.1.0", rev = "c5a1cbfb5f9049f9270955caffb5bee5997aebf7", features = ["egui"] }
 quick-xml = "0.41"
 zip = { version = "3", default-features = false, features = ["deflate"] }
 # zlib streams (compressed metafile pictures in `.doc` drawings); already in the lock as a dependency of other crates.
@@ -20,13 +20,77 @@ list (author, source, license) is in ATTRIBUTION.md.
  https://github.com/storytold/craft-fonts/blob/main/ATTRIBUTION.md (BIZ UDPGothic, BIZ UDMincho,
  Shippori Mincho), under the SIL Open Font License 1.1. Their licence texts ship with the
  packages as OFL-<family>.txt. Builds without CRAFT_FONTS_DIR do not include them.
- English word list (assets/hyphenation/en-us.dic) — derived from the Moby Hyphenator II list by
+- Language data (craft-i18n): the word lists, dictionaries and hyphenation patterns below are embedded at build
+  time from https://github.com/storytold/craft-i18n (language-data/, CRAFT_I18N_DIR at the commit
+  in craft-i18n.rev; all official releases) by craft-proof (storytold/craft-libs). Builds without
+  CRAFT_I18N_DIR do not include them.
+- English word list (craft-i18n language-data/en-us/en-us.dic) — derived from the Moby Hyphenator II list by
  Grady Ward, public domain (Project Gutenberg eBook #3204). The hyphenation patterns
-  (assets/hyphenation/en-us.pat) were trained from it and are released as CC0-1.0.
- Polish hyphenation patterns (assets/hyphenation/pl.pat) — hyph-pl.tex from the hyph-utf8
+  (craft-i18n language-data/en-us/hyphenation.pat) were trained from it and are released as CC0-1.0.
+- English spelling dictionaries (craft-i18n language-data/en-us, en-gb and en-ca: spelling.aff and
+  spelling.dic) — the SCOWL rel-2026.02.25 Hunspell dictionaries en_US, en_GB-ise and en_CA from
+  https://wordlist.aspell.net, bundled unmodified. Their upstream notice (embedded too, for the
+  About window) is language-data/en-us/LICENCE-SCOWL.txt in craft-i18n. The word lists:
+
+    Copyright 2000-2026 by Kevin Atkinson
+
+    Permission to use, copy, modify, distribute, and sell any part of SCOWLv2, or
+    word lists created from it, is hereby granted without fee, provided that the
+    above copyright notice appears in all copies and that both the above
+    copyright notice and this notice appear in supporting documentation.  Kevin
+    Atkinson makes no representations about the suitability of this database for
+    any purpose.  It is provided "as is" without express or implied warranty.
+
+  The Australian data:
+
+    Copyright 2016 by Benjamin Titze
+
+    Permission to use, copy, modify, distribute and sell this array, the
+    associated software, and its documentation for any purpose is hereby
+    granted without fee, provided that the above copyright notice appears
+    in all copies and that both that copyright notice and this permission
+    notice appear in supporting documentation. Benjamin Titze makes no
+    representations about the suitability of this array for any
+    purpose. It is provided "as is" without express or implied warranty.
+
+  The affix files, a modified version of Geoff Kuenning's Ispell english.aff:
+
+    Copyright 1993, Geoff Kuenning, Granada Hills, CA
+    All rights reserved.
+
+    Redistribution and use in source and binary forms, with or without
+    modification, are permitted provided that the following conditions
+    are met:
+
+    1. Redistributions of source code must retain the above copyright
+       notice, this list of conditions and the following disclaimer.
+    2. Redistributions in binary form must reproduce the above copyright
+       notice, this list of conditions and the following disclaimer in the
+       documentation and/or other materials provided with the distribution.
+    3. All modifications to the source code must be clearly marked as
+       such.  Binary redistributions based on modified source code
+       must be clearly marked as modified versions in the documentation
+       and/or other materials provided with the distribution.
+    (clause 4 removed with permission from Geoff Kuenning)
+    5. The name of Geoff Kuenning may not be used to endorse or promote
+       products derived from this software without specific prior
+       written permission.
+
+    THIS SOFTWARE IS PROVIDED BY GEOFF KUENNING AND CONTRIBUTORS ``AS IS'' AND
+    ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+    IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+    ARE DISCLAIMED.  IN NO EVENT SHALL GEOFF KUENNING OR CONTRIBUTORS BE LIABLE
+    FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+    DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+    OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+    HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+    LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+    OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+    SUCH DAMAGE.
+- Polish hyphenation patterns (craft-i18n language-data/pl/hyphenation.pat) — hyph-pl.tex from the hyph-utf8
  package, Copyright (C) 1987-1995 Hanna Kołodziejska, Bogusław Jackowski, Marek Ryćko, bundled
  unmodified and used under the MIT License; the copyright and permission notice is in the file.
- Portuguese hyphenation patterns (assets/hyphenation/pt.pat) — hyph-pt.tex from the hyph-utf8
+- Portuguese hyphenation patterns (craft-i18n language-data/pt/hyphenation.pat) — hyph-pt.tex from the hyph-utf8
  package, bundled unmodified and used under the BSD 3-Clause License:

    Copyright (C) 1987, 1994, 1996, 2015 Pedro J. de Rezende, 1996, 2015 J. Joao Dias Almeida,
@@ -52,7 +116,7 @@ list (author, source, license) is in ATTRIBUTION.md.
    ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
    NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED
    OF THE POSSIBILITY OF SUCH DAMAGE.
- German hyphenation patterns (assets/hyphenation/de.pat) — hyph-de-1996.tex (reformed spelling)
+- German hyphenation patterns (craft-i18n language-data/de/hyphenation.pat) — hyph-de-1996.tex (reformed spelling)
  from the hyph-utf8 package, bundled unmodified and used under the MIT License; the copyright
  and permission notice is in the file:

@@ -74,7 +138,7 @@ list (author, source, license) is in ATTRIBUTION.md.
    FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
    OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
    DEALINGS IN THE SOFTWARE.
- Italian hyphenation patterns (assets/hyphenation/it.pat) — hyph-it.tex from the hyph-utf8
+- Italian hyphenation patterns (craft-i18n language-data/it/hyphenation.pat) — hyph-it.tex from the hyph-utf8
  package, Copyright (C) 2008-2011 Claudio Beccari, bundled unmodified and used under the MIT
  License (offered under LPPL 1.3+ or MIT); the copyright and permission notice is in the file:

@@ -124,7 +124,7 @@ Every screenshot below is WordCraft itself, rendered offscreen by its own UI tes
 | **References** | Table of contents, footnotes and endnotes, citations and bibliography (APA, MLA, Chicago, IEEE), captions, table of figures, cross-references, index, table of authorities |
 | **Review** | Spelling and grammar with suggestions (English and Polish, by each run's language), thesaurus, word count, comments in margin balloons or a pane, track changes, accept/reject, compare documents, restrict editing, accessibility checker, document inspector |
 | **Mailings** | Mail merge from CSV, merge fields, address block, greeting line, rules, preview, finish to a document; envelopes and labels |
-| **View** | Print layout, web layout, draft, read mode, focus, zoom, one/multiple pages, page width, Navigation pane, rulers, gridlines, dark mode; interface in English, 简体中文, 繁體中文, 日本語, Português (Brasil), Español, Українська, Српски / Srpski, Eesti, Türkçe, Русский, Italiano, Deutsch, Polski, Čeština, Magyar, Français, Български, Tiếng Việt, 한국어, Svenska, Hrvatski or Slovenščina (follows the system language by default) |
+| **View** | Print layout, web layout, draft, read mode, focus, zoom, one/multiple pages, page width, Navigation pane, rulers, gridlines, dark mode; interface in English, 简体中文, 繁體中文, 日本語, Português (Brasil), Español, Українська, Српски / Srpski, Eesti, Türkçe, Русский, Italiano, Deutsch, Polski, Čeština, Magyar, Français, Български, Tiếng Việt, 한국어, Svenska, Hrvatski, Nederlands, Dansk, Română, العربية (mirrored) or Slovenščina (follows the system language by default) |
 | **Files** | .docx read/write, legacy 97-2003 .doc import, PDF export, .odt, .rtf, .html, .md, .tex, .txt import/export, page images |

 The honest picture, area by area, is in [ROADMAP.md](ROADMAP.md), the
@@ -140,6 +140,19 @@ cargo run --release -p wordcraft -- --sample        # the desktop app with the s
 cargo run --release -p wordcraft -- report.docx     # open a document
 ```

+The interface translations and the spelling and hyphenation data come from
+[craft-i18n](https://github.com/storytold/craft-i18n), an optional build input. To build with them,
+check it out at the commit in `craft-i18n.rev` and point `CRAFT_I18N_DIR` at it (an absolute
+path); without it WordCraft builds with an English interface, English spelling falls back to an
+installed Hunspell English or craft-proof's built-in word list, and only Bulgarian, Turkish and
+Russian hyphenate (by rule):
+
+```sh
+git clone https://github.com/storytold/craft-i18n ../craft-i18n
+git -C ../craft-i18n checkout "$(cat craft-i18n.rev)"
+CRAFT_I18N_DIR="$PWD/../craft-i18n" cargo run --release -p wordcraft -- --sample
+```
+
 Command line:

 ```sh
@@ -194,7 +207,7 @@ covers every target starting with it (`wordcraft*=debug`). The logger is
 | Layer | Crate | Job |
 |---|---|---|
 | L0 | `wordcraft-geom` | units and measurements |
-| L1 | `wordcraft-doc`, `wordcraft-fonts`, `wordcraft-proof` | document model and editing; fonts and shaping; spelling, grammar, hyphenation |
+| L1 | `wordcraft-doc`, `wordcraft-fonts`, `wordcraft-proof` ([`craft-proof`](https://github.com/storytold/craft-libs/tree/main/crates/proof) from craft-libs) | document model and editing; fonts and shaping; spelling, grammar, hyphenation (data: craft-i18n `language-data/`, `CRAFT_I18N_DIR`) |
 | L2 | `wordcraft-layout`, `wordcraft-docx`, `wordcraft-formats` | line breaking, pagination, tables, notes, hit testing; OOXML; ODT/RTF/HTML/Markdown/TXT |
 | L3 | `wordcraft-render`, `wordcraft-pdf` | rasteriser (vello_cpu); PDF ([craft-pdf](docs/shared-pdf.md), Krilla) |
 | L4 | `wordcraft-engine` | session, undo, 422 commands, document feature catalog |
@@ -345,7 +358,15 @@ stand on its own.
 | <img src="https://raw.githubusercontent.com/storytold/pdfcraft/main/assets/app-icon/hicolor/64x64/apps/ai.storyteller.pdfcraft.png" alt="" width="32" height="32"> | **PdfCraft** | Reading, organizing and protecting PDFs | [GitHub](https://github.com/storytold/pdfcraft) | [Website](https://getartcraft.com/apps/pdfcraft) |
 | <img src="https://raw.githubusercontent.com/storytold/effectcraft/main/assets/app-icon/hicolor/64x64/apps/ai.storyteller.effectcraft.png" alt="" width="32" height="32"> | **EffectCraft** | Motion graphics and visual effects | [GitHub](https://github.com/storytold/effectcraft) | [Website](https://getartcraft.com/apps/effectcraft) |
 | <img src="https://raw.githubusercontent.com/storytold/designcraft/main/assets/app-icon/hicolor/64x64/apps/ai.storyteller.designcraft.png" alt="" width="32" height="32"> | **DesignCraft** | Page layout and publishing | [GitHub](https://github.com/storytold/designcraft) | [Website](https://getartcraft.com/apps/designcraft) |
-| <img src="https://raw.githubusercontent.com/storytold/wordcraft/main/assets/app-icon/hicolor/64x64/apps/ai.storyteller.wordcraft.png" alt="" width="32" height="32"> | **WordCraft** | **Writing and document design · you are here** | [GitHub](https://github.com/storytold/wordcraft) | [Website](https://getartcraft.com/apps/wordcraft) |
+| <img src="https://raw.githubusercontent.com/storytold/figcraft/main/assets/app-icon/hicolor/64x64/apps/ai.storyteller.figcraft.png" alt="" width="32" height="32"> | **FigCraft** | Interface design and prototyping | [GitHub](https://github.com/storytold/figcraft) | [Website](https://getartcraft.com/apps/figcraft) |
+| <img src="https://raw.githubusercontent.com/storytold/wordcraft/main/assets/app-icon/hicolor/64x64/apps/ai.storyteller.wordcraft.png" alt="" width="32" height="32"> | **WordCraft** | Word processing and documents | [GitHub](https://github.com/storytold/wordcraft) | [Website](https://getartcraft.com/apps/wordcraft) |
+| <img src="https://raw.githubusercontent.com/storytold/soundcraft/main/assets/app-icon/hicolor/64x64/apps/ai.storyteller.soundcraft.png" alt="" width="32" height="32"> | **SoundCraft** | Audio recording and editing | [GitHub](https://github.com/storytold/soundcraft) | [Website](https://getartcraft.com/apps/soundcraft) |
+| <img src="https://raw.githubusercontent.com/storytold/deckcraft/main/assets/app-icon/hicolor/64x64/apps/ai.storyteller.deckcraft.png" alt="" width="32" height="32"> | **DeckCraft** | Presentations and slide decks | [GitHub](https://github.com/storytold/deckcraft) | [Website](https://getartcraft.com/apps/deckcraft) |
+| <img src="https://raw.githubusercontent.com/storytold/cadcraft/main/assets/app-icon/hicolor/64x64/apps/ai.storyteller.cadcraft.png" alt="" width="32" height="32"> | **CADCraft** | Computer-aided design | [GitHub](https://github.com/storytold/cadcraft) | [Website](https://getartcraft.com/apps/cadcraft) |
+| <img src="https://raw.githubusercontent.com/storytold/gridcraft/main/assets/app-icon/hicolor/64x64/apps/ai.storyteller.gridcraft.png" alt="" width="32" height="32"> | **GridCraft** | Spreadsheets and data | [GitHub](https://github.com/storytold/gridcraft) | [Website](https://getartcraft.com/apps/gridcraft) |
+| <img src="https://raw.githubusercontent.com/storytold/texturecraft/main/assets/app-icon/hicolor/64x64/apps/ai.storyteller.texturecraft.png" alt="" width="32" height="32"> | **TextureCraft** | 3D texture painting | [GitHub](https://github.com/storytold/texturecraft) | [Website](https://getartcraft.com/apps/texturecraft) |
+| <img src="https://raw.githubusercontent.com/storytold/craft-anything/main/assets/app-icon/hicolor/64x64/apps/ai.storyteller.craft-anything.png" alt="" width="32" height="32"> | **Craft Anything** | See how any software works, then build your own | [GitHub](https://github.com/storytold/craft-anything) | [Website](https://getartcraft.com/apps/craft-anything) |
+| <img src="https://raw.githubusercontent.com/tangency-labs/solidcraft/main/assets/icons/app/linux/exports/hicolor/64x64/apps/io.tangencylabs.solidcraft.png" alt="" width="32" height="32"> | **SolidCraft** | Parametric 3D CAD by Tangency Labs (community app) | [GitHub](https://github.com/tangency-labs/solidcraft) | |

 And [**ArtCraft**](https://getartcraft.com/) itself, our AI image and video studio for artists who want real control.

@@ -0,0 +1,26 @@
+# Security policy
+
+## Reporting a vulnerability
+
+Please report security problems privately through GitHub:
+**[Report a vulnerability](https://github.com/storytold/wordcraft/security/advisories/new)**
+(Security tab › Advisories › Report a vulnerability).
+
+Don't open a public issue or pull request for a vulnerability until a fix is released.
+
+Useful to include:
+- the WordCraft version or commit, and the platform (macOS, Windows, Linux, BSD, web);
+- what an attacker can do, and what they need (a crafted document, MCP or control-channel access, a local account…);
+- steps or a sample file that reproduce it.
+
+We'll acknowledge the report, keep you updated while we work on a fix, and credit you in the advisory unless you'd rather not be named.
+
+## Supported versions
+
+Fixes go into `main` and ship in the next release. Older releases don't get backported fixes.
+
+## Scope
+
+In scope: anything that lets a document, file, command, MCP or control-channel request, or network response read or write files it shouldn't, run code, leak data, or crash WordCraft and lose the user's work.
+
+Crashes from hostile input count, because WordCraft treats every panic as a bug (see [Never crash](AGENTS.md)).
@@ -758,6 +758,12 @@ fn parity_markdown(p: &Value) -> String {

 fn main() -> ExitCode {
    let args: Vec<OsString> = std::env::args_os().skip(1).collect();
+    // Language packs installed in the suite's font store are used; `proof.installPack` installs
+    // only while the person has turned downloading on in the app.
+    wordcraft_engine::packs::use_font_store(false);
+    if let Some(source) = wordcraft_engine::packs::index_override() {
+        eprintln!("wordcraft-cli: Language packs come from a test source: {source}");
+    }
    match run(&args) {
        Ok(()) | Err(Failure::StdoutClosed) => ExitCode::SUCCESS,
        Err(Failure::Error(e)) => {
@@ -49,9 +49,9 @@ impl PrefsSync {
    pub fn changed(&mut self, app: &WordApp) -> Option<String> {
        let mut prefs = app.prefs();
        if let Some((host, own)) = &self.host_author
-            && prefs.author == *host
+            && prefs.author.as_deref() == Some(host.as_str())
        {
-            prefs.author = own.clone();
+            prefs.author = Some(own.clone());
        }
        let json = match serde_json::to_string(&prefs) {
            Ok(j) => j,
@@ -9,7 +9,8 @@ use wordcraft_engine::Session;
 use wordcraft_ui_egui::async_saves::{AsyncSaves, SaveOutcome};
 use wordcraft_ui_egui::{Inbox, Services, WordApp};

-const DOC_EXTS: &[&str] = &["docx", "docm", "dotx", "dotm", "doc", "dot", "odt", "rtf", "txt", "md", "html", "htm", "tex", "json", "xml"];
+const DOC_EXTS: &[&str] =
+    &["docx", "docm", "dotx", "dotm", "doc", "dot", "odt", "rtf", "txt", "md", "html", "htm", "mht", "mhtml", "tex", "json", "xml"];
 const IMAGE_EXTS: &[&str] = &["png", "jpg", "jpeg", "gif", "webp", "bmp", "wmf", "emf"];
 const RECIPIENT_EXTS: &[&str] = wordcraft_engine::cmd::mailings::RECIPIENT_EXTENSIONS;
 mod font_store;
@@ -47,10 +47,9 @@ pub fn poll(inbox: &Inbox, app: &mut WordApp, ctx: &egui::Context) {
                        // Leave Backstage, as opening from the Open dialog does.
                        Ok(_) => app.ui.backstage = false,
                        Err(e) => {
-                            log::warn!("{p}: {e}");
-                            let e = e.to_string();
-                            let msg = wordcraft_ui_egui::tl!("Couldn't open {path}: {error}");
-                            app.status(wordcraft_ui_egui::i18n::fmt(msg, &[("path", p), ("error", &e)]));
+                            app.report_open_failure(p, &e);
+                            // Backstage hides the status bar, so leave it to show the error.
+                            app.ui.backstage = false;
                        }
                    }
                }
@@ -329,6 +329,26 @@ fn text_args() -> (Vec<String>, Vec<std::path::PathBuf>) {
    (args, files)
 }

+/// The arguments without the ones macOS adds when it launches an app (#1103): `-psn_0_12345`, and
+/// the `-NS…` / `-Apple…` options (`-AppleLanguages (en)`, `-NSDocumentRevisionsDebugMode YES`) with
+/// the value after each. They are not files, and opening them as files fails.
+fn without_launch_args(args: Vec<String>) -> Vec<String> {
+    let mut kept = Vec::with_capacity(args.len());
+    let mut args = args.into_iter().peekable();
+    while let Some(a) = args.next() {
+        if a.starts_with("-psn_") {
+            continue;
+        }
+        if a.starts_with("-NS") || a.starts_with("-Apple") {
+            // Its value, unless the next argument is another flag.
+            args.next_if(|v| !v.starts_with('-'));
+            continue;
+        }
+        kept.push(a);
+    }
+    kept
+}
+
 /// Open a file whose name isn't valid Unicode (#1440). `file.open` takes its path as text, so it
 /// gets the file's bytes under the lossy name, and the document then keeps the real path to save to.
 /// The bytes are read as `file.open` reads a path: only a regular file, and at most 2 GB.
@@ -340,7 +360,9 @@ fn open_non_unicode(app: &mut WordApp, path: &std::path::Path) {
        // Not when it waits for a password: that open names the document itself.
        Ok(r) if r.get("pending").is_none() => app.session.path = Some(path.into()),
        Ok(_) => {}
-        Err(e) => log::warn!("{name}: {e}"),
+        Err(e) => {
+            app.report_open_failure(&name, &e);
+        }
    }
 }

@@ -350,7 +372,7 @@ fn open_non_unicode(app: &mut WordApp, path: &std::path::Path) {
 fn main() -> eframe::Result {
    // Windows: the update helper is a copy of this program started with `--finish-update`.
    #[cfg(windows)]
-    if let Some(result) = craft_update::self_update::finish(&craft_update::suite::WORDCRAFT, &std::env::args_os().skip(1).collect::<Vec<_>>()) {
+    if let Some(result) = craft_update::self_update::finish(&wordcraft_ui_egui::UPDATE_APP, &std::env::args_os().skip(1).collect::<Vec<_>>()) {
        std::process::exit(i32::from(result.is_err()));
    }
    // First, so the panic hook and every start-up warning are recorded (`logging`).
@@ -360,6 +382,8 @@ fn main() -> eframe::Result {
    let mut files = Vec::new();
    let mut sample = false;
    let (args, other_files) = text_args();
+    // Only macOS (Finder / LaunchServices) adds these; elsewhere `-NS…` could be a real file name.
+    let args = if cfg!(target_os = "macos") { without_launch_args(args) } else { args };
    let mut bad_control: Option<Option<String>> = None;
    let mut args = args.into_iter().peekable();
    while let Some(a) = args.next() {
@@ -466,11 +490,13 @@ fn main() -> eframe::Result {
            app.set_startup_update_check(true);
            load_prefs(&mut app);
            load_user_dictionary(&mut app);
+            // Language packs from the suite's font store; an Install click is the person's own.
+            wordcraft_engine::packs::use_font_store(true);
            // A region chosen in File › Options replaces the system's for the first blank
            // document too (#838).
            if !sample && app.session.prefs.region.is_some() {
                let doc = app.session.blank_document();
-                app.session.set_document(doc);
+                app.replace_startup_document(doc);
            }
            app.watch_desktop_theme(&cc.egui_ctx);
            if prefs_enabled()
@@ -504,7 +530,7 @@ fn main() -> eframe::Result {
            }
            for f in files {
                if let Err(e) = app.run("file.open", serde_json::json!({"path": f})) {
-                    log::warn!("{f}: {e}");
+                    app.report_open_failure(&f, &e);
                }
            }
            for f in other_files {
@@ -590,6 +616,33 @@ mod tests {
    }
 }

+#[cfg(test)]
+mod launch_arg_tests {
+    use super::without_launch_args;
+
+    fn strip(args: &[&str]) -> Vec<String> {
+        without_launch_args(args.iter().map(|a| a.to_string()).collect())
+    }
+
+    #[test]
+    fn macos_launch_arguments_are_not_files() {
+        assert_eq!(strip(&["-psn_0_12345", "a.docx"]), ["a.docx"]);
+        assert_eq!(strip(&["-AppleLanguages", "(en)", "a.docx"]), ["a.docx"]);
+        assert_eq!(strip(&["a.docx", "-NSDocumentRevisionsDebugMode", "YES", "b.docx"]), ["a.docx", "b.docx"]);
+        // A flag with no value after it, or followed by another flag, takes nothing with it.
+        assert_eq!(strip(&["a.docx", "-AppleLocale"]), ["a.docx"]);
+        assert_eq!(strip(&["-NSFoo", "--sample", "a.docx"]), ["--sample", "a.docx"]);
+    }
+
+    #[test]
+    fn real_arguments_are_kept() {
+        assert_eq!(strip(&["--control", "7981", "--sample", "-h"]), ["--control", "7981", "--sample", "-h"]);
+        // Files whose names merely start like a launch argument keep their place when they are paths.
+        assert_eq!(strip(&["./-psn_x.docx", "Apple.docx", "-", "-nsfoo"]), ["./-psn_x.docx", "Apple.docx", "-", "-nsfoo"]);
+        assert!(strip(&[]).is_empty());
+    }
+}
+
 #[cfg(test)]
 mod prefs_tests {
    use super::write_prefs;
@@ -1,431 +0,0 @@
-% title: Hyphenation patterns for Italian
-% copyright: Copyright (C) 2008-2011 Claudio Beccari
-% notice: This file is part of the hyph-utf8 package.
-%     See http://www.hyphenation.org/tex for more information.
-% language:
-%     name: Italian
-%     tag: it
-% version: 4.9 2014/04/22
-% authors:
-%   -
-%     name: Claudio Beccari
-%     contact: claudio.beccari (at) gmail.com
-% licence:
-%     - This file is available under any of the following licences:
-%     -
-%         name: LPPL
-%         version: 1.3
-%         or_later: true
-%         url: http://www.latex-project.org/lppl.txt
-%         status: maintained
-%         maintainer: Claudio Beccari, e-mail claudio dot beccari at gmail dot com
-%     -
-%         name: MIT
-%         url: https://opensource.org/licenses/MIT
-%         text: >
-%             Permission is hereby granted, free of charge, to any person
-%             obtaining a copy of this software and associated documentation
-%             files (the "Software"), to deal in the Software without
-%             restriction, including without limitation the rights to use,
-%             copy, modify, merge, publish, distribute, sublicense, and/or sell
-%             copies of the Software, and to permit persons to whom the
-%             Software is furnished to do so, subject to the following
-%             conditions:
-%
-%             The above copyright notice and this permission notice shall be
-%             included in all copies or substantial portions of the Software.
-%
-%             THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
-%             EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES
-%             OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
-%             NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT
-%             HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
-%             WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
-%             FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
-%             OTHER DEALINGS IN THE SOFTWARE.
-% hyphenmins:
-%     typesetting:
-%         left: 2
-%         right: 2
-% changes:
-%     - 2014-04-22 - Add few patterns involving `h'
-%     - 2011-08-16 - Change the licence from GNU LGPL into LPPL v1.3.
-%     - 2010-05-24 - Fix for Italian patterns for proper hyphenation of -ich and Ljubljana.
-%     - 2008-06-09 - Import of original ithyph.tex into hyph-utf8 package.
-%     - 2008-03-08 - (last change in ithyph.tex)
-% texlive:
-%     encoding: ascii
-%     babelname: italian
-%     legacy_patterns: ithyph.tex
-%     message: Italian hyphenation patterns
-%     description: |-
-%         Hyphenation patterns for Italian in ASCII encoding.
-%         Compliant with the Recommendation UNI 6461 on hyphenation
-%         issued by the Italian Standards Institution
-%         (Ente Nazionale di Unificazione UNI).
-% ==========================================
-%
-% These hyphenation patterns for the Italian language are supposed to comply
-% with the Recommendation UNI 6461 on hyphenation issued by the Italian
-% Standards Institution (Ente Nazionale di Unificazione UNI).  No guarantee
-% or declaration of fitness to any particular purpose is given and any
-% liability is disclaimed.
-%
-\patterns{
-.a3p2n               % After the Garzanti dictionary: a-pnea, a-pnoi-co,...
-.anti1
-.anti3m2n
-.bio1
-.ca4p3s
-.circu2m1
-.contro1
-.di2s3cine
-.e2x1eu
-.fran2k3
-.free3
-.li3p2sa
-.narco1
-.opto1
-.orto3p2
-.para1
-.ph2l
-.ph2r
-.poli3p2
-.pre1
-.p2s
-.re1i2scr
-.sha2re3
-.tran2s3c
-.tran2s3d
-.tran2s3l
-.tran2s3n
-.tran2s3p
-.tran2s3r
-.tran2s3t
-.su2b3lu
-.su2b3r
-.wa2g3n
-.wel2t1
-2'2
-a1ia
-a1ie
-a1io
-a1iu
-a1uo
-a1ya
-2at.
-e1iu
-e2w
-o1ia
-o1ie
-o1io
-o1iu
-1b
-2bb
-2bc
-2bd
-2bf
-2bm
-2bn
-2bp
-2bs
-2bt
-2bv
-b2l
-b2r
-2b.
-2b'
-1c
-2cb
-2cc
-2cd
-2cf
-2ck
-2cm
-2cn
-2cq
-2cs
-2ct
-2cz
-2chh
-c2h
-2ch.
-2ch'.
-2ch''.
-2chb
-ch2r
-2chn
-c2l
-c2r
-2c.
-2c'
-.c2
-1d
-2db
-2dd
-2dg
-2dl
-2dm
-2dn
-2dp
-d2r
-2ds
-2dt
-2dv
-2dw
-2d.
-2d'
-.d2
-1f
-2fb
-2fg
-2ff
-2fn
-f2l
-f2r
-2fs
-2ft
-2f.
-2f'
-1g
-2gb
-2gd
-2gf
-2gg
-g2h
-g2l
-2gm
-g2n
-2gp
-g2r
-2gs
-2gt
-2gv
-2gw
-2gz
-2gh2t
-2g.
-2g'
-.h2
-1h
-2hb
-2hd
-2hh
-hi3p2n
-h2l
-2hm
-2hn
-2hr
-2hv
-2h.
-2h'
-.j2
-1j
-2j.
-2j'
-.k2
-1k
-2kg
-2kf
-k2h
-2kk
-k2l
-2km
-k2r
-2ks
-2kt
-2k.
-2k'
-1l
-2lb
-2lc
-2ld
-2l3f2
-2lg
-l2h
-l2j
-2lk
-2ll
-2lm
-2ln
-2lp
-2lq
-2lr
-2ls
-2lt
-2lv
-2lw
-2lz
-2l.
-2l'.
-2l''
-1m
-2mb
-2mc
-2mf
-2ml
-2mm
-2mn
-2mp
-2mq
-2mr
-2ms
-2mt
-2mv
-2mw
-2m.
-2m'
-1n
-2nb
-2nc
-2nd
-2nf
-2ng
-2nk
-2nl
-2nm
-2nn
-2np
-2nq
-2nr
-2ns
-n2s3fer
-2nt
-2nv
-2nz
-n2g3n
-2nheit
-2n.
-2n'
-1p
-2pd
-p2h
-p2l
-2pn
-3p2ne
-2pp
-p2r
-2ps
-3p2sic
-2pt
-2pz
-2p.
-2p'
-1q
-2qq
-2q.
-2q'
-1r
-2rb
-2rc
-2rd
-2rf
-r2h
-2rg
-2rk
-2rl
-2rm
-2rn
-2rp
-2rq
-2rr
-2rs
-2rt
-r2t2s3
-2rv
-2rx
-2rw
-2rz
-2r.
-2r'
-1s2
-2shm
-2sh.
-2sh'
-2s3s
-s4s3m
-2s3p2n
-2stb
-2stc
-2std
-2stf
-2stg
-2stm
-2stn
-2stp
-2sts
-2stt
-2stv
-2sz
-4s.
-4s'.
-4s''
-.t2
-1t
-2tb
-2tc
-2td
-2tf
-2tg
-t2h
-2th.
-t2l
-2tm
-2tn
-2tp
-t2r
-t2s
-3t2sch
-2tt
-t2t3s
-2tv
-2tw
-t2z
-2tzk
-tz2s
-2t.
-2t'.
-2t''
-1v
-2vc
-v2l
-v2r
-2vv
-2v.
-2v'.
-2v''
-1w
-w2h
-wa2r
-2w1y
-2w.
-2w'
-1x
-2xb
-2xc
-2xf
-2xh
-2xm
-2xp
-2xt
-2xw
-2x.
-2x'
-y1ou
-y1i
-1z
-2zb
-2zd
-2zl
-2zn
-2zp
-2zt
-2zs
-2zv
-2zz
-2z.
-2z'.
-2z''
-.z2
-}                          % Pattern end
-
@@ -1,503 +0,0 @@
-% title: Hyphenation patterns for Portuguese
-% copyright: Copyright (C) 1987, 1994, 1996, 2015 Pedro J. de Rezende, 1996, 2015 J. Joao Dias Almeida, 2024 Leonardo Araujo and Aline Benevides
-% notice: This file is part of the hyph-utf8 package.
-%     See http://www.hyphenation.org/tex for more information.
-% language:
-%     name: Portuguese
-%     tag: pt
-% version: 1.4 2024-07-13
-% authors:
-%   -
-%     name: Pedro J. de Rezende
-%     contact: rezende (at) ic.unicamp.br
-%   -
-%     name: J. Joao Dias Almeida
-%     contact: jj (at) di.uminho.pt
-%   -
-%     name: Leonardo Araujo
-%     contact: leolca (at) gmail.com
-%   -
-%     name: Aline Benevides
-%     contact: benevides.aline12 (at) gmail.com
-% licence:
-%     name: BSD 3-clause licence
-%     url: https://opensource.org/licenses/BSD-3-Clause
-%     text: >
-%         Redistribution and use in source and binary forms, with or without
-%         modification, are permitted provided that the following conditions
-%         are met:
-%         * Redistributions of source code must retain the above copyright
-%           notice, this list of conditions and the following disclaimer.
-%         * Redistributions in binary form must reproduce the above copyright
-%           notice, this list of conditions and the following disclaimer in the
-%           documentation and/or other materials provided with the
-%           distribution.
-%         * Neither the name of the University of Campinas, of the University
-%           of Minho nor the names of its contributors may be used to endorse
-%           or promote products derived from this software without specific
-%           prior written permission.
-% 
-%         THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
-%         "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
-%         LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
-%         A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL PEDRO J. DE
-%         REZENDE OR J.JOAO DIAS ALMEIDA BE LIABLE FOR ANY DIRECT, INDIRECT,
-%         INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
-%         BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS
-%         OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED
-%         AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
-%         LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY
-%         WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
-%         POSSIBILITY OF SUCH DAMAGE.
-% hyphenmins:
-%     typesetting:
-%         left: 2
-%         right: 3
-% changes:
-%     - Version 1.4 Release date: 13/07/2024 Leonardo Araujo and Aline Benevides
-%     - Version 1.3 Release date: 12/08/2015 Pedro J. de Rezende and J. Joao Dias Almeida
-%     - Version 1.2 Release date: 07/21/1996 Pedro J. de Rezende and J. Joao Dias Almeida
-%     - Version 1.1 Release date: 04/12/1994 Pedro J. de Rezende
-%     - Version 1.0 Release date: 02/13/1987 Pedro J. de Rezende
-% texlive:
-%     synonyms:
-%         - portuges
-%     encoding: ec
-%     babelname: portuguese
-%     legacy_patterns: pthyph.tex
-%     message: Portuguese hyphenation patterns
-%     description: Hyphenation patterns for Portuguese in T1/EC and UTF-8 encodings.
-%
-\patterns{
-1b2l
-1b2r
-1ba
-1be
-1bi
-1bo
-1bu
-1bá
-1bâ
-1bã
-1bé
-1bí
-1bó
-1bú
-1bê
-1bõ
-1c2h
-1c2l
-1c2r
-1ca
-1ce
-1ci
-1co
-1cu
-1cá
-1câ
-1cã
-1cé
-1cí
-1có
-1cú
-1cê
-1cõ
-1ça
-1çe
-1çi
-1ço
-1çu
-1çá
-1çâ
-1çã
-1çé
-1çí
-1çó
-1çú
-1çê
-1çõ
-1d2l
-1d2r
-1da
-1de
-1di
-1do
-1du
-1dá
-1dâ
-1dã
-1dé
-1dí
-1dó
-1dú
-1dê
-1dõ
-1f2l
-1f2r
-1fa
-1fe
-1fi
-1fo
-1fu
-1fá
-1fâ
-1fã
-1fé
-1fí
-1fó
-1fú
-1fê
-1fõ
-1g2l
-1g2r
-1ga
-1ge
-1gi
-1go
-1gu
-1gu4a
-1gu4e
-1gu4i
-1gu4o
-1gá
-1gâ
-1gã
-1gé
-1gí
-1gó
-1gú
-1gê
-1gõ
-1ja
-1je
-1ji
-1jo
-1ju
-1já
-1jâ
-1jã
-1jé
-1jí
-1jó
-1jú
-1jê
-1jõ
-1k2l
-1k2r
-1ka
-1ke
-1ki
-1ko
-1ku
-1ká
-1kâ
-1kã
-1ké
-1kí
-1kó
-1kú
-1kê
-1kõ
-1l2h
-1la
-1le
-1li
-1lo
-1lu
-1lá
-1lâ
-1lã
-1lé
-1lí
-1ló
-1lú
-1lê
-1lõ
-1ma
-1me
-1mi
-1mo
-1mu
-1má
-1mâ
-1mã
-1mé
-1mí
-1mó
-1mú
-1mê
-1mõ
-1n2h
-1na
-1ne
-1ni
-1no
-1nu
-1ná
-1nâ
-1nã
-1né
-1ní
-1nó
-1nú
-1nê
-1nõ
-1p2l
-1p2r
-1pa
-1pe
-1pi
-1po
-1pu
-1pá
-1pâ
-1pã
-1pé
-1pí
-1pó
-1pú
-1pê
-1põ
-1qu4a
-1qu4e
-1qu4i
-1qu4o
-1ra
-1re
-1ri
-1ro
-1ru
-1rá
-1râ
-1rã
-1ré
-1rí
-1ró
-1rú
-1rê
-1rõ
-1sa
-1se
-1si
-1so
-1su
-1sá
-1sâ
-1sã
-1sé
-1sí
-1só
-1sú
-1sê
-1sõ
-1t2l
-1t2r
-1ta
-1te
-1ti
-1to
-1tu
-1tá
-1tâ
-1tã
-1té
-1tí
-1tó
-1tú
-1tê
-1tõ
-1v2l
-1v2r
-1va
-1ve
-1vi
-1vo
-1vu
-1vá
-1vâ
-1vã
-1vé
-1ví
-1vó
-1vú
-1vê
-1võ
-1w2l
-1w2r
-1xa
-1xe
-1xi
-1xo
-1xu
-1xá
-1xâ
-1xã
-1xé
-1xí
-1xó
-1xú
-1xê
-1xõ
-1za
-1ze
-1zi
-1zo
-1zu
-1zá
-1zâ
-1zã
-1zé
-1zí
-1zó
-1zú
-1zê
-1zõ
-a3a
-a3e
-a3o
-c3c
-e3a
-e3e
-e3o
-i3a
-i3e
-i3i
-i3o
-i3â
-i3ê
-i3ô
-o3a
-o3e
-o3o
-r3r
-s3s
-u3a
-u3e
-u3o
-u3u
-.p2si
-.p2sí
-.g2no
-.g2nó
-.g2nô
-t2c
-1p2neu
-.t2m
-.p2t
-su2b3r
-su2b3l
-.su3b4li
-a1ir.
-u1ir.
-1qu
-1vô
-1lô
-1cô
-1gô
-1bô
-1tô
-1rô
-1pô
-a1é
-a1í
-a1ó
-a1ú
-e1á
-e1â
-e1ã
-e1é
-e1ê
-e1í
-e1ó
-é1o
-e1ú
-i1á
-i1ã
-í1a
-i1é
-i1í
-i1ó
-í1o
-i1u
-i1ú
-o1á
-o1é
-o1í
-o1ó
-u1á
-u1ã
-u1â
-u1í
-ú1o
-1qu2á
-1qu2â
-1qu2í
-1gu2í
-a1ind
-a1i1nh
-e1imp
-e1inc
-e1inf
-e1ing
-e1ins
-e1int
-e1inv
-u1iz.
-a1iz.
-4a.
-4e.
-4o.
-1gu2á
-1gu2ã
-1qu2ã
-.m2n
-c2za
-.s2
-1p2seu1d
-1dô
-1fô
-1mô
-1nô
-1sô
-1zô
-tu1i
-tu2it
-tu2id
-bu1i
-nu1i
-o1in
-u1in
-su1i
-í1e
-ju1i
-fu1i
-du1i
-do1im
-au1i
-u1i1ç
-u1ê
-1gu2ê
-1qu2ê
-1çô
-u1é
-1gu2é
-1qu2é
-1xô
-a1â
-a1ã
-a1ô
-e1ô
-.ne4o
-o1ã
-o1ê
-o1im
-o2i1na
-pro1i1b
-co2ima
-.t2
-1-
-}
-\hyphenation{% Do NOT make any alterations to this list! --- PdR
-hard-ware
-soft-ware
-}
@@ -1,241 +0,0 @@
-# English spelling supplement: common words the public-domain Moby list (1990s) lacks.
-# Written by WordCraft contributors (MIT OR Apache-2.0); see ATTRIBUTION.md.
-# One lowercase base form per line, sorted. Plurals, -ed, -ing, -er, -ly… come from the
-# inflection rules in crates/proof/src/lib.rs, so list "desktop", not "desktops".
-airbag
-airfare
-artcraft
-autocomplete
-autocorrect
-autofill
-autoformat
-autosave
-backend
-bitcoin
-bitmap
-blockchain
-blog
-blogger
-bluetooth
-captcha
-caregiver
-carpool
-cellphone
-chatbot
-chatroom
-checkbox
-checklist
-childcare
-clamour
-clickable
-colourful
-colourisation
-colourise
-colourless
-configurable
-copyedit
-coronavirus
-covid
-crowdfunding
-crowdsource
-crypto
-cryptocurrency
-customizable
-customization
-cyber
-cybersecurity
-cyberspace
-database
-dataset
-daycare
-desktop
-download
-downloadable
-downsize
-dropdown
-earbud
-ebook
-ecommerce
-email
-emoji
-emoticon
-endeavour
-esports
-facebook
-favicon
-fintech
-firewall
-flowchart
-foodie
-freeware
-frontend
-fundraiser
-gameplay
-gamification
-geeky
-geolocation
-gigabit
-gigabyte
-github
-glamour
-globalization
-google
-groupthink
-hackathon
-hardcode
-hashtag
-healthcare
-homepage
-homeschool
-honour
-honourable
-honourably
-hotspot
-hyperlink
-hypertext
-inbox
-incentivize
-infographic
-instagram
-internet
-interoperability
-intranet
-ipad
-iphone
-javascript
-kickstart
-kilobyte
-laptop
-lifestyle
-linkedin
-linux
-livestream
-lockdown
-login
-logout
-lowercase
-makeover
-malware
-manoeuvrable
-megabyte
-megapixel
-meme
-metadata
-microchip
-microsoft
-middleware
-mindset
-multicultural
-multiplayer
-multitask
-nerdy
-netbook
-netflix
-newsfeed
-offboard
-offline
-onboard
-online
-onscreen
-outsource
-paediatric
-paralegal
-passcode
-petabyte
-phishing
-photobomb
-playdate
-playlist
-plugin
-podcast
-popup
-prequel
-printout
-prioritise
-prioritization
-prioritize
-privatise
-ransomware
-recyclable
-rigour
-ringtone
-roadmap
-rollout
-runtime
-scalability
-screencast
-screensaver
-screenshot
-scrollbar
-selfie
-signup
-sitemap
-skillset
-smartphone
-smartwatch
-smiley
-snowboard
-spellcheck
-spellchecker
-spreadsheet
-spyware
-stakeholder
-standup
-startup
-subfolder
-sunscreen
-superfood
-superuser
-synthesise
-tagline
-takeout
-techie
-telecommute
-teleconference
-telehealth
-telemedicine
-terabyte
-textbox
-timeline
-timestamp
-toolbar
-toolkit
-touchpad
-touchscreen
-trackball
-trackpad
-travelogue
-upcycle
-upload
-uppercase
-upsell
-upskill
-usability
-username
-videoconference
-videogame
-vlog
-vlogger
-voicemail
-walkthrough
-webcam
-webcast
-webinar
-weblog
-webmaster
-webpage
-website
-whatsapp
-whiteboard
-wifi
-wiki
-wikipedia
-wireframe
-wordcraft
-workaround
-workflow
-workforce
-workplace
-workspace
-workstation
-youtube
@@ -1,305 +0,0 @@
-# English spelling variants: American and British forms of the same word, for the English
-# dialects (#1281, #1045). Written by WordCraft contributors from general knowledge of English
-# spelling (MIT OR Apache-2.0); no other word list copied. See ATTRIBUTION.md.
-#
-# Each line: POLICY AMERICAN BRITISH
-# POLICY is three letters, for American English (en-US), Canadian English (en-CA) and the
-# British-spelling Englishes (en-GB, en-AU, en-NZ, en-IE, en-ZA, en-IN…), in that order:
-#   u  only the American form is right there (the British one is flagged, American suggested)
-#   b  only the British form is right there
-#   *  both are right
-# Inflections (colours, centred, organising, organisation…) come from the rules in
-# crates/proof/src/en_variants.rs for -or/-our, -er/-re and -ize/-ise style pairs; other pairs
-# get only a plural, so list their other forms on lines of their own. When in doubt a form is
-# accepted: a false alarm is worse than a missed variant.
-
-# -or / -our
-ubb arbor arbour
-ubb ardor ardour
-ubb armor armour
-ubb armory armoury
-ubb behavior behaviour
-ubb behavioral behavioural
-ubb candor candour
-ubb clamor clamour
-ubb color colour
-ubb demeanor demeanour
-ubb discolor discolour
-ubb dishonor dishonour
-ubb endeavor endeavour
-ubb favor favour
-ubb favorite favourite
-ubb favoritism favouritism
-ubb fervor fervour
-ubb flavor flavour
-ubb harbor harbour
-ubb honor honour
-ubb humor humour
-ubb labor labour
-ubb misbehavior misbehaviour
-ubb neighbor neighbour
-ubb neighborhood neighbourhood
-ubb neighborly neighbourly
-ubb odor odour
-ubb parlor parlour
-ubb rancor rancour
-ubb rigor rigour
-ubb rumor rumour
-ubb savior saviour
-ubb savor savour
-ubb savory savoury
-ubb splendor splendour
-ubb succor succour
-ubb tumor tumour
-ubb unfavorable unfavourable
-ubb valor valour
-ubb vapor vapour
-ubb vigor vigour
-
-# -er / -re
-ubb caliber calibre
-ubb center centre
-ubb centimeter centimetre
-ubb epicenter epicentre
-ubb fiber fibre
-ubb kilometer kilometre
-ubb liter litre
-ubb luster lustre
-ubb maneuver manoeuvre
-ubb meager meagre
-ubb millimeter millimetre
-ubb miter mitre
-ubb ocher ochre
-ubb saber sabre
-ubb sepulcher sepulchre
-ubb somber sombre
-ubb specter spectre
-*bb theater theatre
-# A meter is also a measuring device in British English.
-u** meter metre
-
-# -ize / -ise (British English accepts both: Oxford spelling uses -ize)
-uu* agonize agonise
-uu* apologize apologise
-uu* authorize authorise
-uu* capitalize capitalise
-uu* categorize categorise
-uu* centralize centralise
-uu* characterize characterise
-uu* civilize civilise
-uu* colonize colonise
-uu* commercialize commercialise
-uu* computerize computerise
-uu* criticize criticise
-uu* crystallize crystallise
-uu* customize customise
-uu* decentralize decentralise
-uu* demonize demonise
-uu* deodorize deodorise
-uu* destabilize destabilise
-uu* digitize digitise
-uu* dramatize dramatise
-uu* economize economise
-uu* emphasize emphasise
-uu* energize energise
-uu* equalize equalise
-uu* familiarize familiarise
-uu* fantasize fantasise
-uu* fertilize fertilise
-uu* finalize finalise
-uu* formalize formalise
-uu* fossilize fossilise
-uu* galvanize galvanise
-uu* generalize generalise
-uu* globalize globalise
-uu* harmonize harmonise
-uu* hospitalize hospitalise
-uu* humanize humanise
-uu* hypnotize hypnotise
-uu* hypothesize hypothesise
-uu* idealize idealise
-uu* idolize idolise
-uu* immobilize immobilise
-uu* immortalize immortalise
-uu* immunize immunise
-uu* industrialize industrialise
-uu* initialize initialise
-uu* italicize italicise
-uu* itemize itemise
-uu* jeopardize jeopardise
-uu* legalize legalise
-uu* legitimize legitimise
-uu* liberalize liberalise
-uu* localize localise
-uu* magnetize magnetise
-uu* marginalize marginalise
-uu* maximize maximise
-uu* mechanize mechanise
-uu* memorize memorise
-uu* mesmerize mesmerise
-uu* minimize minimise
-uu* mobilize mobilise
-uu* modernize modernise
-uu* monopolize monopolise
-uu* moralize moralise
-uu* nationalize nationalise
-uu* naturalize naturalise
-uu* neutralize neutralise
-uu* normalize normalise
-uu* optimize optimise
-uu* organize organise
-uu* ostracize ostracise
-uu* oxidize oxidise
-uu* pasteurize pasteurise
-uu* patronize patronise
-uu* penalize penalise
-uu* personalize personalise
-uu* plagiarize plagiarise
-uu* polarize polarise
-uu* popularize popularise
-uu* pressurize pressurise
-uu* prioritize prioritise
-uu* privatize privatise
-uu* publicize publicise
-uu* pulverize pulverise
-uu* randomize randomise
-uu* rationalize rationalise
-uu* realize realise
-uu* recognize recognise
-uu* reorganize reorganise
-uu* revolutionize revolutionise
-uu* satirize satirise
-uu* scrutinize scrutinise
-uu* sensitize sensitise
-uu* socialize socialise
-uu* specialize specialise
-uu* stabilize stabilise
-uu* standardize standardise
-uu* sterilize sterilise
-uu* stigmatize stigmatise
-uu* subsidize subsidise
-uu* summarize summarise
-uu* symbolize symbolise
-uu* sympathize sympathise
-uu* synchronize synchronise
-uu* synthesize synthesise
-uu* systematize systematise
-uu* tantalize tantalise
-uu* terrorize terrorise
-uu* theorize theorise
-uu* trivialize trivialise
-uu* urbanize urbanise
-uu* utilize utilise
-uu* vandalize vandalise
-uu* verbalize verbalise
-uu* victimize victimise
-uu* visualize visualise
-uu* vocalize vocalise
-uu* westernize westernise
-
-# -yze / -yse
-u*b analyze analyse
-u*b catalyze catalyse
-u*b dialyze dialyse
-u*b electrolyze electrolyse
-u*b hydrolyze hydrolyse
-u*b paralyze paralyse
-u*b psychoanalyze psychoanalyse
-
-# -ense / -ence
-ubb defense defence
-ubb offense offence
-ubb pretense pretence
-ubb defenseless defenceless
-# In British English "license" and "practise" are the verbs, so only American English flags.
-u** license licence
-u** practice practise
-
-# Doubled l (American English accepts both)
-*bb canceled cancelled
-*bb canceling cancelling
-*bb channeled channelled
-*bb channeling channelling
-*bb counseled counselled
-*bb counseling counselling
-*bb counselor counsellor
-*bb counselors counsellors
-*bb dueling duelling
-*bb equaled equalled
-*bb equaling equalling
-*bb fueled fuelled
-*bb fueling fuelling
-*bb jeweler jeweller
-*bb jewelers jewellers
-*bb jewelry jewellery
-*bb labeled labelled
-*bb labeling labelling
-*bb leveled levelled
-*bb leveling levelling
-*bb marveled marvelled
-*bb marveling marvelling
-*bb marvelous marvellous
-*bb modeled modelled
-*bb modeling modelling
-*bb quarreled quarrelled
-*bb quarreling quarrelling
-*bb signaled signalled
-*bb signaling signalling
-*bb totaled totalled
-*bb totaling totalling
-*bb traveled travelled
-*bb traveler traveller
-*bb travelers travellers
-*bb traveling travelling
-*bb tunneled tunnelled
-*bb tunneling tunnelling
-*bb woolen woollen
-
-# -og / -ogue
-*bb catalog catalogue
-*bb cataloged catalogued
-*bb cataloging cataloguing
-
-# ae / oe
-u*b anemia anaemia
-u*b anemic anaemic
-u*b anesthesia anaesthesia
-u*b anesthetic anaesthetic
-**b archeology archaeology
-**b archeologist archaeologist
-u*b diarrhea diarrhoea
-u*b edema oedema
-u*b esophagus oesophagus
-u*b estrogen oestrogen
-u*b gynecologist gynaecologist
-u*b gynecology gynaecology
-u*b hematology haematology
-u*b hemoglobin haemoglobin
-u*b hemorrhage haemorrhage
-u*b leukemia leukaemia
-u*b orthopedic orthopaedic
-u*b pediatric paediatric
-u*b pediatrician paediatrician
-u*b pediatrics paediatrics
-
-# Other words
-u*b aluminum aluminium
-u*b cozy cosy
-ubb mold mould
-ubb molded moulded
-ubb molding moulding
-ubb moldy mouldy
-ubb molt moult
-ubb pajamas pyjamas
-ubb plow plough
-ubb plowed ploughed
-ubb plowing ploughing
-u** program programme
-u*b skeptic sceptic
-u*b skeptical sceptical
-u*b skepticism scepticism
-ubb smolder smoulder
-ubb smoldering smouldering
-# "Tire" and "curb" are also verbs everywhere, so only American English flags.
-uu* tire tyre
-uu* curb kerb
@@ -1,214 +0,0 @@
-# Russian spelling supplement: common words older Russian Hunspell dictionaries lack.
-# Written by WordCraft contributors (MIT OR Apache-2.0); see ATTRIBUTION.md.
-# One word per line: the base form, a TAB, then its declension, from which
-# crates/proof/src/ru/extra.rs makes every form:
-#   m     masculine noun ending in a consonant (маркетплейс, -а, -у, -ом, -е, -ы/-и, -ов/-ей…)
-#   f     feminine noun in -а (инфографика, -и, -е, -у, -ой…; genitive plural without ending)
-#   fia   feminine noun in -ия (интеграция, -ии, -ию, -ией, -ий…)
-#   fs    feminine noun in -ь (соцсеть, -и, -ью, -ей, -ям…)
-#   nie   neuter noun in -ие (согласие, -ия, -ию, -ием, -ий…)
-#   no    neuter noun in -о (юрлицо, -а, -у, -ом, -е; genitive plural without ending)
-#   adj   adjective or participle in -ый, -ий, -ой (бонусный, газоиспользующий)
-#   ovat  verb in -овать with its conjugation and participles (колеровать, администрировать)
-#   =     the forms themselves, space-separated (verbs, nouns with a fleeting vowel)
-# A word alone on its line doesn't decline (онлайн, медиа). Capitalized words are names and match
-# only when written with a capital.
-
-# Commerce, marketing and the web
-маркетплейс	m
-селлер	m
-фулфилмент	m
-ритейл	m
-ритейлер	m
-дистрибьютор	m
-дропшиппинг	m
-мерчандайзер	m
-эквайринг	m
-промокод	m
-кешбэк	m
-кэшбэк	m
-лендинг	m
-лид	m
-тренд	m
-бренд	m
-брендбук	m
-ребрендинг	m
-таргетинг	m
-геотаргетинг	m
-ретаргетинг	m
-таргетолог	m
-маркетолог	m
-копирайтер	m
-рерайтер	m
-контент	m
-блогер	m
-инфлюенсер	m
-хештег	m
-хэштег	m
-репост	m
-лайк	m
-подкаст	m
-стриминг	m
-вебинар	m
-чат	m
-бот	m
-чат-бот	m
-стартап	m
-франчайзинг	m
-аутсорсинг	m
-аутстаффинг	m
-коворкинг	m
-дедлайн	m
-фидбэк	m
-фидбек	m
-кейс	m
-скриншот	m
-скринкаст	m
-баннер	m
-виджет	m
-дашборд	m
-сервис	m
-сайт	m
-скан	m
-токен	m
-аккаунт	m
-логин	m
-пароль	m
-смартфон	m
-гаджет	m
-планшет	m
-ноутбук	m
-апгрейд	m
-апдейт	m
-бэкап	m
-бэкенд	m
-фронтенд	m
-датасет	m
-промпт	m
-интерфейс	m
-хостинг	m
-домен	m
-сниппет	m
-трафик	m
-юзер	m
-стикер	m
-чекбокс	m
-инпут	m
-плейсхолдер	m
-тултип	m
-гипсокартон	m
-пеноплекс	m
-праймер	m
-колер	m
-колорант	m
-Яндекс	m
-Битрикс	m
-Вебвизор	m
-Дзен	m
-инфографика	f
-аналитика	f
-оплата	f
-предоплата	f
-постоплата	f
-доплата	f
-переплата	f
-недоплата	f
-маркировка	= маркировка маркировки маркировке маркировку маркировкой маркировкою маркировок маркировкам маркировками маркировках
-отгрузка	= отгрузка отгрузки отгрузке отгрузку отгрузкой отгрузкою отгрузок отгрузкам отгрузками отгрузках
-колеровка	= колеровка колеровки колеровке колеровку колеровкой колеровкою колеровок колеровкам колеровками колеровках
-рассылка	= рассылка рассылки рассылке рассылку рассылкой рассылкою рассылок рассылкам рассылками рассылках
-выгрузка	= выгрузка выгрузки выгрузке выгрузку выгрузкой выгрузкою выгрузок выгрузкам выгрузками выгрузках
-интеграция	fia
-пагинация	fia
-госрегистрация	fia
-геолокация	fia
-монетизация	fia
-кастомизация	fia
-персонализация	fia
-сегментация	fia
-верификация	fia
-валидация	fia
-авторизация	fia
-аутентификация	fia
-оптимизация	fia
-визуализация	fia
-соцсеть	fs
-согласие	nie
-домовладение	nie
-рождение	nie
-паллетирование	nie
-неисполнение	nie
-непредоставление	nie
-бонусный	adj
-маркетинговый	adj
-мотивационный	adj
-гипоаллергенный	adj
-тиксотропный	adj
-сополимерный	adj
-покупочный	adj
-таргетированный	adj
-брендированный	adj
-кастомный	adj
-онлайновый	adj
-офлайновый	adj
-колеруемый	adj
-колерованный	adj
-заколерованный	adj
-газоиспользующий	adj
-колеровать	ovat
-заколеровать	ovat
-администрировать	ovat
-модерировать	ovat
-отмодерировать	ovat
-таргетировать	ovat
-монетизировать	ovat
-брендировать	ovat
-кастомизировать	ovat
-детектировать	ovat
-верифицировать	ovat
-валидировать	ovat
-генерировать	ovat
-сгенерировать	ovat
-мониторить	= мониторить мониторю мониторишь мониторит мониторим мониторите мониторят мониторил мониторила мониторили мониторя мониторинг
-гуглить	= гуглить гуглю гуглишь гуглит гуглим гуглите гуглят гуглил гуглила гуглили
-скачивать	= скачивать скачиваю скачиваешь скачивает скачиваем скачиваете скачивают скачивал скачивала скачивали скачивается скачиваются
-оценивание	nie
-медучреждение	nie
-юрлицо	no
-учётка	= учётка учётки учётке учётку учёткой учёток учёткам учётками учётках учетка учетки учетке учетку учеткой учеток учеткам учетками учетках
-перелинковка	= перелинковка перелинковки перелинковке перелинковку перелинковкой перелинковок
-поклейка	= поклейка поклейки поклейке поклейку поклейкой поклеек
-детекция	fia
-досудебный	adj
-категорийный	adj
-оркестратор	m
-оффер	m
-трекер	m
-бриф	m
-гайд	m
-монтажёр	m
-тенант	m
-мерчант	m
-амбассадор	m
-Роскомнадзор	m
-Директ	m
-Маркет	m
-вовлечённость	fs
-вовлеченность	fs
-укрывистость	fs
-# Words that don't decline
-онлайн
-офлайн
-оффлайн
-медиа
-демо
-франчайзи
-киноа
-смс
-пн
-вт
-ср
-чт
-пт
-сб
-вс
@@ -1,13 +1,10 @@
-# Contributor names for the About window (craftrules standards/contributors.md).
+# Contributor names for the About window.
 #
 # Everyone who contributes is credited by GitHub username automatically. Anything more is up to
 # you: add YOUR OWN entry below, in your own PR (commit it yourself). Never add someone else; a
 # maintainer may add a person only when that person asked, recording where in consent_source.
 #
-# Easiest: python3 ../../craftrules/scripts/contributors.py --add-me . \
-#            [--real-name "Ada Lovelace"] [--display-name "Ada"] [--sync-github-name]
-#
-# Or copy this block, replacing your-github-username (every field is optional):
+# Copy this block, replacing your-github-username (every field is optional):
 #
 #   [people.your-github-username]
 #   real_name = "Your Name"        # shown when the viewer picks "Real name"
@@ -181,3 +178,12 @@ sync_github_name = true

 [people.pakiat]
 display_name = "OtorO"
+
+[people.TobyWu666]
+display_name = "tobywu"
+
+[people.Bra1nZ]
+sync_github_name = true
+
+[people.dylanmtaylor]
+sync_github_name = true
@@ -1 +1 @@
-9205108cfdced5177706264038848b68b2422d2b
+059cbf95c2a3eb95d637ca8584faca1129d17f48
@@ -9,7 +9,8 @@ description = "WordCraft document model: stories, paragraphs, runs, tables, sect
 workspace = true

 [features]
-# Test inputs other crates' tests share (`cfb_guard::repeating_difat_sample`); turned on only as a
+# Test inputs other crates' tests share (`cfb_guard::repeating_difat_sample`,
+# `zip_guard::zip64_entry_count_sample`); turned on only as a
 # dev-dependency, so never built into the app.
 test-support = []

@@ -115,12 +115,22 @@ pub fn next_cluster(text: &str, off: usize) -> usize {
    }
 }

-/// Scripts whose Backspace removes one character at a time (a vowel sign, a medial, a stacked
-/// consonant) rather than the whole cluster, as on Windows and macOS: the Brahmic scripts of
-/// South and South-East Asia.
+/// Characters Backspace removes individually rather than with their whole cluster: Arabic
+/// combining marks and characters of the Brahmic scripts of South and South-East Asia.
 pub fn backspaces_by_char(c: char) -> bool {
    matches!(u32::from(c),
-        0x0900..=0x0DFF // Devanagari … Sinhala
+        0x0610..=0x061A // Arabic nonspacing marks (Unicode 17.0)
+        | 0x064B..=0x065F
+        | 0x0670
+        | 0x06D6..=0x06DC
+        | 0x06DF..=0x06E4
+        | 0x06E7..=0x06E8
+        | 0x06EA..=0x06ED
+        | 0x0897..=0x089F
+        | 0x08CA..=0x08E1
+        | 0x08E3..=0x08FF
+        | 0x10EFA..=0x10EFF
+        | 0x0900..=0x0DFF // Devanagari … Sinhala
        | 0x0E00..=0x0EFF // Thai, Lao
        | 0x0F00..=0x0FFF // Tibetan
        | 0x1000..=0x109F // Myanmar
@@ -250,8 +260,10 @@ mod tests {
    }

    #[test]
-    fn backspace_by_character_in_brahmic_scripts_only() {
+    fn backspace_by_character_in_brahmic_scripts_and_arabic_marks() {
        assert!(backspaces_by_char('ေ') && backspaces_by_char('ि') && backspaces_by_char('្'));
+        assert!(backspaces_by_char('\u{064E}') && backspaces_by_char('\u{06E7}') && backspaces_by_char('\u{10EFF}'));
        assert!(!backspaces_by_char('\u{301}') && !backspaces_by_char('a') && !backspaces_by_char('語'));
+        assert!(!backspaces_by_char('ب') && !backspaces_by_char('\u{06E5}') && !backspaces_by_char('\u{08E2}'));
    }
 }
@@ -48,6 +48,131 @@ impl LineCap {
    }
 }

+/// An arrowhead's width across its line or length along it (ST_LineEndWidth and
+/// ST_LineEndLength, ECMA-376 §20.1.10.39–40): 2, 3 or 5 times the line's width, as Word draws it.
+#[derive(Clone, Copy, Debug, Default, PartialEq, Eq, Serialize, Deserialize)]
+#[serde(rename_all = "camelCase")]
+pub enum ArrowSize {
+    Small,
+    #[default]
+    Medium,
+    Large,
+}
+
+impl ArrowSize {
+    /// Read a DrawingML size (`sm`, `med`, `lg`); absent or unknown values are medium.
+    pub fn from_ooxml(value: &str) -> Self {
+        match value {
+            "sm" => Self::Small,
+            "lg" => Self::Large,
+            _ => Self::Medium,
+        }
+    }
+
+    /// The DrawingML spelling.
+    pub fn ooxml(self) -> &'static str {
+        match self {
+            Self::Small => "sm",
+            Self::Medium => "med",
+            Self::Large => "lg",
+        }
+    }
+
+    /// Read a VML width (`narrow`, `medium`, `wide`) or length (`short`, `medium`, `long`).
+    pub fn from_vml(value: &str) -> Self {
+        match value {
+            "narrow" | "short" => Self::Small,
+            "wide" | "long" => Self::Large,
+            _ => Self::Medium,
+        }
+    }
+
+    /// How many [`arrow_unit`]s the arrowhead measures.
+    pub fn factor(self) -> f32 {
+        match self {
+            Self::Small => 2.0,
+            Self::Medium => 3.0,
+            Self::Large => 5.0,
+        }
+    }
+}
+
+/// The kind of an arrowhead (ST_LineEndType, ECMA-376 §20.1.10.33), kept for saving; every kind
+/// is drawn as a triangle.
+#[derive(Clone, Copy, Debug, Default, PartialEq, Eq, Serialize, Deserialize)]
+#[serde(rename_all = "camelCase")]
+pub enum ArrowKind {
+    #[default]
+    Triangle,
+    Stealth,
+    Diamond,
+    Oval,
+    Arrow,
+}
+
+impl ArrowKind {
+    /// Read a DrawingML end type other than `none`; unknown values are triangles.
+    pub fn from_ooxml(value: &str) -> Self {
+        match value {
+            "stealth" => Self::Stealth,
+            "diamond" => Self::Diamond,
+            "oval" => Self::Oval,
+            "arrow" => Self::Arrow,
+            _ => Self::Triangle,
+        }
+    }
+
+    /// The DrawingML spelling.
+    pub fn ooxml(self) -> &'static str {
+        match self {
+            Self::Triangle => "triangle",
+            Self::Stealth => "stealth",
+            Self::Diamond => "diamond",
+            Self::Oval => "oval",
+            Self::Arrow => "arrow",
+        }
+    }
+
+    /// Read a VML arrow (`block`, `classic`, `diamond`, `oval`, `open`) other than `none`.
+    pub fn from_vml(value: &str) -> Self {
+        match value {
+            "classic" => Self::Stealth,
+            "diamond" => Self::Diamond,
+            "oval" => Self::Oval,
+            "open" => Self::Arrow,
+            _ => Self::Triangle,
+        }
+    }
+}
+
+/// An arrowhead's kind and size (`a:headEnd` / `a:tailEnd`). The default is a medium triangle.
+#[derive(Clone, Copy, Debug, Default, PartialEq, Eq, Serialize, Deserialize)]
+#[serde(default, rename_all = "camelCase")]
+pub struct ArrowStyle {
+    pub kind: ArrowKind,
+    pub width: ArrowSize,
+    pub length: ArrowSize,
+}
+
+impl ArrowStyle {
+    pub fn is_default(&self) -> bool {
+        *self == Self::default()
+    }
+
+    /// The arrowhead's length along its line and width across it, for a line `line_width` wide.
+    pub fn dims(self, line_width: f32) -> (f32, f32) {
+        let unit = arrow_unit(line_width);
+        (self.length.factor() * unit, self.width.factor() * unit)
+    }
+}
+
+/// What an arrowhead's size is a multiple of: the line's width, but at least 2 points (Word draws
+/// a thinner line's arrowheads as for a 2-point line).
+pub fn arrow_unit(line_width: f32) -> f32 {
+    let w = if line_width.is_finite() { line_width.clamp(0.25, 200.0) } else { 0.75 };
+    w.max(2.0)
+}
+
 /// The rest of a shape's properties. Empty (the default) for most shapes.
 #[derive(Clone, Debug, PartialEq, Default, Serialize, Deserialize)]
 #[serde(default, rename_all = "camelCase")]
@@ -69,6 +194,11 @@ pub struct ShapeExtra {
    pub arrow_start: bool,
    #[serde(skip_serializing_if = "is_false")]
    pub arrow_end: bool,
+    /// The kind and size of the start and end arrowheads, when there are any.
+    #[serde(skip_serializing_if = "ArrowStyle::is_default")]
+    pub start_style: ArrowStyle,
+    #[serde(skip_serializing_if = "ArrowStyle::is_default")]
+    pub end_style: ArrowStyle,
    /// A rounded rectangle's corner radius (`roundRect`'s `adj`, ECMA-376 §20.1.10.56): in
    /// 100000ths of the shorter side, at most [`MAX_CORNER`]; `None` draws [`DEFAULT_CORNER`].
    #[serde(skip_serializing_if = "Option::is_none")]
@@ -83,6 +213,39 @@ pub struct ShapeExtra {
    /// main colour (the shape's `stroke`).
    #[serde(skip_serializing_if = "Option::is_none")]
    pub outline_fill: Option<crate::fill::Fill>,
+    /// A horizontal rule (VML `o:hr`: a web page's `<hr>` pasted into Word): it takes its whole
+    /// line, and is drawn across [`HorizontalRule::pct`] of it or at the shape's own width.
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub hr: Option<HorizontalRule>,
+}
+
+/// How a horizontal rule sits on its line (VML `o:hrpct`, `o:hralign`), as Word draws one:
+/// across `pct` percent of the line's width (the paragraph's, inside its indents), or at the
+/// shape's own width when `pct` is 0; `align` places it when it is narrower than the line.
+#[derive(Clone, Copy, Debug, PartialEq, Default, Serialize, Deserialize)]
+#[serde(default, rename_all = "camelCase")]
+pub struct HorizontalRule {
+    pub pct: f32,
+    pub align: crate::props::Align,
+    /// Word's standard look (`o:hrstd`), kept for saving.
+    pub standard: bool,
+}
+
+impl HorizontalRule {
+    /// The rule's width on a line `line` wide, for a shape `own` wide.
+    pub fn width(&self, line: f32, own: f32) -> f32 {
+        let line = line.max(0.0);
+        if self.pct.is_finite() && self.pct > 0.0 { line * (self.pct.min(100.0) / 100.0) } else { own.clamp(0.0, line) }
+    }
+
+    /// Where a rule `w` wide starts on a line from `x`, `line` wide.
+    pub fn left(&self, x: f32, line: f32, w: f32) -> f32 {
+        match self.align {
+            crate::props::Align::Center => x + (line - w) / 2.0,
+            crate::props::Align::Right => x + line - w,
+            _ => x,
+        }
+    }
 }

 fn is_zero(v: &u32) -> bool {
@@ -14,7 +14,7 @@
 //! outside what's deleted (so deleting across a control's edge empties it rather than breaking
 //! it); writers call [`Document::balance_controls`] so a saved file always has whole controls.

-use std::collections::{BTreeMap, BTreeSet};
+use std::collections::{BTreeMap, BTreeSet, HashMap};

 use serde::{Deserialize, Serialize};

@@ -422,24 +422,37 @@ fn scan(story: StoryRef, bl: &Blocks, prefix: &mut Vec<u32>, depth: usize, out:
 }

 /// Positions of the markers without a partner in a block list and the cells inside it.
-fn orphans(bl: &Blocks, prefix: &mut Vec<u32>, depth: usize, out: &mut Vec<(Path, usize)>, tables: &mut Vec<(Path, usize, bool)>) {
+pub(crate) fn orphans(bl: &Blocks, prefix: &mut Vec<u32>, depth: usize, out: &mut Vec<(Path, usize)>, tables: &mut Vec<(Path, usize, bool)>) {
    if depth > MAX_DEPTH {
        return;
    }
    let events = control_events(bl);
    let (_, lone) = pair_events(&events);
-    for k in lone {
-        let Some(e) = events.get(k) else { continue };
-        let mut path = prefix.clone();
-        path.push(u32::try_from(e.block()).unwrap_or(u32::MAX));
-        match (e, e.off()) {
-            (_, Some(off)) => out.push((Path(path), off)),
-            (ControlEvent::Open { .. }, None) => {
-                // Which of the table's opens: count those before it on the same table.
-                let nth = events.iter().take(k).filter(|x| matches!(x, ControlEvent::Open { block, off: None, .. } if *block == e.block())).count();
-                tables.push((Path(path), nth, true));
+    if !lone.is_empty() {
+        let mut table_counts: HashMap<usize, usize> = HashMap::new();
+        let mut open_nth = Vec::with_capacity(events.len());
+        for e in &events {
+            if let ControlEvent::Open { block, off: None, .. } = e {
+                let count = table_counts.entry(*block).or_insert(0);
+                open_nth.push(*count);
+                *count += 1;
+            } else {
+                open_nth.push(0);
+            }
+        }
+        for k in lone {
+            let Some(e) = events.get(k) else { continue };
+            let mut path = prefix.clone();
+            path.push(u32::try_from(e.block()).unwrap_or(u32::MAX));
+            match (e, e.off()) {
+                (_, Some(off)) => out.push((Path(path), off)),
+                (ControlEvent::Open { .. }, None) => {
+                    // Which of the table's opens: index among table opens on the same table.
+                    let nth = open_nth.get(k).copied().unwrap_or(0);
+                    tables.push((Path(path), nth, true));
+                }
+                (ControlEvent::Close { .. }, None) => tables.push((Path(path), 0, false)),
            }
-            (ControlEvent::Close { .. }, None) => tables.push((Path(path), 0, false)),
        }
    }
    for (i, b) in bl.iter().enumerate() {
@@ -443,8 +443,7 @@ impl Document {
        Ok(id)
    }

-    /// Count words like Word's status bar (whitespace-separated tokens containing a letter or digit,
-    /// including generated numbered-list labels).
+    /// Count words like Word's status bar ([`crate::count_words`], plus generated numbered-list labels).
    pub fn word_count(&self) -> usize {
        self.story_word_count(StoryRef::Body)
    }
@@ -795,7 +794,9 @@ impl Document {
                p.kind = "lpwstr".into();
                p.value = value.to_string();
            }
-            None => self.custom_props.push(CustomProp { name: name.to_string(), kind: "lpwstr".into(), value: value.to_string() }),
+            None => {
+                self.custom_props.push(CustomProp { name: name.to_string(), kind: "lpwstr".into(), value: value.to_string(), ..Default::default() })
+            }
        }
    }

@@ -205,11 +205,15 @@ struct BoxBudget {
    costs: BTreeMap<u32, usize>,
    /// Boxes left without a story because the paste's budget couldn't hold theirs.
    skipped: usize,
+    /// A box the fragment has no story for may show this document's story of that id (a
+    /// fragment copied from this document without its parts). Off for another document's
+    /// fragment, whose ids mean nothing here.
+    local: bool,
 }

 impl BoxBudget {
    fn new() -> BoxBudget {
-        BoxBudget { stories: MAX_PASTED_BOXES, bytes: MAX_PASTED_BOX_BYTES, active: Vec::new(), costs: BTreeMap::new(), skipped: 0 }
+        BoxBudget { stories: MAX_PASTED_BOXES, bytes: MAX_PASTED_BOX_BYTES, active: Vec::new(), costs: BTreeMap::new(), skipped: 0, local: true }
    }
 }

@@ -385,6 +389,167 @@ fn restyle_block(b: &mut Block, from: &str, to: &Option<String>, depth: usize) -
    }
 }

+/// What [`Document::adopt_with`] renumbers in another document's content: media keys, lists,
+/// note and comment stories, comment ids, text boxes (one it doesn't bring is dropped), revisions
+/// (after ours, at `rev`; an id past the `revs` it brings is dropped) and styles (those kept under new ids; unstyled paragraphs take
+/// `default_style` when it's given).
+struct Relink<'a> {
+    media: &'a BTreeMap<String, String>,
+    nums: &'a BTreeMap<u32, u32>,
+    notes: &'a BTreeMap<u32, u32>,
+    comments: &'a BTreeMap<u32, u32>,
+    boxes: &'a BTreeMap<u32, Part>,
+    /// Added to permission range ids: ours come first.
+    perms: u32,
+    rev: u32,
+    revs: u32,
+    styles: &'a BTreeMap<String, String>,
+    default_style: Option<&'a str>,
+}
+
+impl Relink<'_> {
+    fn block(&self, b: &mut Block) {
+        // Its own stack, like `each_para_mut`: tables however deeply nested are relinked (#1339).
+        let mut todo = vec![b];
+        while let Some(b) = todo.pop() {
+            match b {
+                Block::Para(p) => self.para(p),
+                Block::Table(t) => {
+                    self.style(&mut t.props.style);
+                    self.shift_change(&mut t.props.fmt_change);
+                    if let Some(c) = t.props.fmt_change.as_mut() {
+                        self.style(&mut c.old.style);
+                    }
+                    for row in t.rows.iter_mut() {
+                        self.shift_change(&mut row.props.fmt_change);
+                        for cell in row.cells.iter_mut() {
+                            self.shift_change(&mut cell.props.fmt_change);
+                            todo.extend(cell.blocks.iter_mut().map(Arc::make_mut));
+                        }
+                    }
+                }
+            }
+        }
+    }
+
+    fn style(&self, id: &mut Option<String>) {
+        if let Some(new) = id.as_ref().and_then(|i| self.styles.get(i)) {
+            *id = Some(new.clone());
+        }
+    }
+
+    /// A paragraph's style: unstyled ones take `default_style` when it's given.
+    fn para_style(&self, id: &mut Option<String>) {
+        match (&*id, self.default_style) {
+            (None, Some(d)) => *id = Some(d.to_string()),
+            _ => self.style(id),
+        }
+    }
+
+    fn num(&self, n: &mut Option<crate::props::NumRef>) {
+        if let Some(n) = n.as_mut()
+            && n.num != 0
+        {
+            n.num = self.nums.get(&n.num).copied().unwrap_or(0);
+        }
+    }
+
+    /// Our id for the other document's revision `r`, if it has one.
+    fn rev_id(&self, r: u32) -> Option<u32> {
+        if r < self.revs { self.rev.checked_add(r) } else { None }
+    }
+
+    fn shift_change<T>(&self, c: &mut Option<Box<crate::props::PropChange<T>>>) {
+        match (c.as_ref().and_then(|c| self.rev_id(c.rev)), c.as_mut()) {
+            (Some(v), Some(x)) => x.rev = v,
+            _ => *c = None,
+        }
+    }
+
+    fn para(&self, p: &mut Paragraph) {
+        self.num(&mut p.props.numbering);
+        self.para_style(&mut p.props.style);
+        for r in &mut p.runs {
+            self.style(&mut r.props.style);
+        }
+        self.style(&mut p.mark.style);
+        for c in p.runs.iter_mut().map(|r| &mut r.props).chain([&mut p.mark]) {
+            c.ins = c.ins.and_then(|r| self.rev_id(r));
+            c.del = c.del.and_then(|r| self.rev_id(r));
+            self.shift_change(&mut c.fmt_change);
+            // A tracked change's old formatting names styles and lists as the live one does.
+            if let Some(f) = c.fmt_change.as_mut() {
+                self.style(&mut f.old.style);
+            }
+        }
+        self.shift_change(&mut p.props.fmt_change);
+        if let Some(f) = p.props.fmt_change.as_mut() {
+            self.para_style(&mut f.old.style);
+            self.num(&mut f.old.numbering);
+        }
+        if let Some(s) = p.section.as_deref_mut() {
+            self.shift_change(&mut s.fmt_change);
+        }
+        match (p.props.num_change.as_ref().and_then(|c| self.rev_id(c.rev)), p.props.num_change.as_mut()) {
+            (Some(v), Some(c)) => c.rev = v,
+            _ => p.props.num_change = None,
+        }
+        for o in &mut p.objects {
+            self.object(o, 0);
+        }
+        p.touch();
+    }
+
+    fn object(&self, o: &mut InlineObject, depth: usize) {
+        // An id that names nothing here becomes one that names nothing at all.
+        let map = |m: &BTreeMap<u32, u32>, id: &mut u32| *id = m.get(id).copied().unwrap_or(u32::MAX);
+        match o {
+            InlineObject::Image { media, .. } => {
+                if let Some(k) = self.media.get(media.as_str()) {
+                    *media = k.clone();
+                }
+            }
+            InlineObject::Graphic { graphic, .. } => {
+                let mapped = |m: &str| self.media.get(m).filter(|k| k.as_str() != m);
+                if graphic.items.iter().any(|i| matches!(i, crate::graphic::GraphicItem::Image { media, .. } if mapped(media).is_some())) {
+                    for i in &mut Arc::make_mut(graphic).items {
+                        if let crate::graphic::GraphicItem::Image { media, .. } = i
+                            && let Some(k) = self.media.get(media.as_str())
+                        {
+                            *media = k.clone();
+                        }
+                    }
+                }
+            }
+            InlineObject::Group { children, .. } if depth < MAX_BOX_DEPTH => children.iter_mut().for_each(|c| self.object(&mut c.obj, depth + 1)),
+            InlineObject::NoteRef { id, .. } => map(self.notes, id),
+            InlineObject::CommentStart { id } | InlineObject::CommentEnd { id } => map(self.comments, id),
+            InlineObject::PermStart { id, .. } | InlineObject::PermEnd { id } => *id = id.saturating_add(self.perms),
+            _ => {}
+        }
+        for story in o.text_box_slots() {
+            if story.is_some_and(|id| !self.boxes.contains_key(&id)) {
+                *story = None;
+            }
+        }
+    }
+}
+
+/// One past the highest permission range id in `blocks`.
+fn perm_end<'a>(blocks: impl Iterator<Item = &'a Arc<Block>>) -> u32 {
+    let mut end = 0u32;
+    for b in blocks {
+        each_para(b, 0, &mut |p| {
+            for o in &p.objects {
+                if let InlineObject::PermStart { id, .. } | InlineObject::PermEnd { id } = o {
+                    end = end.max(id.saturating_add(1));
+                }
+            }
+        });
+    }
+    end
+}
+
 /// Text box story ids of a paragraph's shapes.
 fn box_ids(p: &Paragraph) -> impl Iterator<Item = u32> + '_ {
    p.objects.iter().flat_map(InlineObject::text_boxes)
@@ -434,10 +599,16 @@ impl Document {
                    at.extend(offs.get(k).copied());
                }
            }
+            // Reference offsets and run boundaries are ordered; do not restart at the first
+            // reference for every run, including runs after the last reference.
+            let mut at = at.into_iter().peekable();
            let mut start = 0usize;
            for r in &mut p.runs {
                let end = start.saturating_add(r.len);
-                if at.iter().any(|&o| o >= start && o < end) {
+                while at.peek().is_some_and(|&o| o < start) {
+                    at.next();
+                }
+                if at.peek().is_some_and(|&o| o < end) {
                    swap(&mut r.props.style);
                }
                start = end;
@@ -792,6 +963,63 @@ impl Document {
        Fragment { blocks, parts }
    }

+    /// A copy of the block at `path` (a whole table, say) as a fragment, with its text boxes.
+    pub fn copy_block(&self, story: crate::StoryRef, path: &Path) -> Option<Fragment> {
+        Some(self.fragment_of(vec![self.block(story, path)?.clone()]))
+    }
+
+    /// A copy of rows `rows` of the table at `tp`, with the cells of each that reach into grid
+    /// columns `cols` (see [`crate::Table::slice`]), as a fragment holding that table.
+    pub fn copy_table_cells(&self, story: crate::StoryRef, tp: &Path, rows: (usize, usize), cols: (usize, usize)) -> Option<Fragment> {
+        let t = self.table(story, tp)?.slice(rows, cols);
+        if t.rows.is_empty() {
+            return None;
+        }
+        Some(self.fragment_of(vec![Block::Table(t)]))
+    }
+
+    /// `blocks` as a fragment: half content controls dropped, text boxes copied along.
+    fn fragment_of(&self, mut blocks: Vec<Block>) -> Fragment {
+        crate::control::balance_blocks(&mut blocks);
+        let parts = self.text_box_parts(&blocks);
+        Fragment { blocks, parts }
+    }
+
+    /// The table whose whole text `a..b` covers when the range runs across its cells: from the
+    /// start of its first paragraph to the end of its last. Of the tables holding both ends, the
+    /// outermost one covered whole (a table nested in a cell when the range covers just it).
+    /// `None` for a range inside one cell, or one that doesn't cover a whole table.
+    pub fn whole_table(&self, a: &Pos, b: &Pos) -> Option<Path> {
+        let (a, b) = order(a, b);
+        if a.story != b.story || a.off != 0 || a.path.parent() == b.path.parent() {
+            return None;
+        }
+        let mut paths: Option<Vec<Path>> = None;
+        // Table block paths are the prefixes of a cell paragraph's path one block deep, then
+        // every three steps (block, row, cell) deeper.
+        let mut n = 1usize;
+        while n.saturating_add(3) <= a.path.0.len() {
+            let pre = a.path.0.get(..n)?;
+            if !b.path.0.starts_with(pre) {
+                return None;
+            }
+            let tp = Path(pre.to_vec());
+            if self.table(a.story, &tp).is_some() {
+                let paths = paths.get_or_insert_with(|| self.para_paths(a.story));
+                let mut inside = paths.iter().filter(|p| p.0.starts_with(pre));
+                if let Some(first) = inside.next() {
+                    let last = inside.next_back().unwrap_or(first);
+                    let end = self.para(a.story, last).map_or(0, Paragraph::len);
+                    if *first == a.path && *last == b.path && b.off >= end {
+                        return Some(tp);
+                    }
+                }
+            }
+            n = n.saturating_add(3);
+        }
+        None
+    }
+
    /// The whole body as a fragment (with its text boxes), to insert into another document.
    pub fn body_fragment(&self) -> Fragment {
        let blocks: Vec<Block> = self.body.iter().map(|b| (**b).clone()).collect();
@@ -799,6 +1027,186 @@ impl Document {
        Fragment { blocks, parts }
    }

+    /// Another document's body as a fragment of this one, to insert: the media, lists, styles,
+    /// notes, comments and tracked changes it refers to come along (lists, notes, comments and
+    /// revisions renumbered so they can't collide with ours; a style we already have by id stays
+    /// ours), and its text boxes ride in [`Fragment::parts`].
+    pub fn adopt(&mut self, src: Document) -> Fragment {
+        self.adopt_with(src, false)
+    }
+
+    /// [`Self::adopt`]; with `keep_styles` its content keeps its own formatting (Word's
+    /// `w:matchSrc`): a style whose id we already have comes along under a new id, and its
+    /// document defaults go into its base styles, which its unstyled paragraphs then use.
+    pub fn adopt_with(&mut self, src: Document, keep_styles: bool) -> Fragment {
+        self.adopt_in(src, keep_styles, &mut 0)
+    }
+
+    /// [`Self::adopt_with`], its permission range ids from at least `perms` on (and past ours);
+    /// `perms` moves past them.
+    fn adopt_in(&mut self, mut src: Document, keep_styles: bool, perms: &mut u32) -> Fragment {
+        let mut renamed = BTreeMap::new();
+        let mut default_style = None;
+        if keep_styles {
+            if src.styles.get("Normal").is_none() {
+                src.styles.upsert(crate::styles::Style { id: "Normal".into(), name: "Normal".into(), ..Default::default() });
+            }
+            // Ids given out here are taken too: two styles never get the same new one.
+            let mut given = std::collections::HashSet::new();
+            let room = src.styles.styles.len().saturating_mul(2).saturating_add(self.styles.styles.len()).saturating_add(1);
+            for st in &src.styles.styles {
+                if self.styles.get(&st.id).is_some() {
+                    let fresh = (1..=room)
+                        .map(|n| format!("{}{n}", st.id))
+                        .find(|id| self.styles.get(id).is_none() && src.styles.get(id).is_none() && !given.contains(id));
+                    if let Some(fresh) = fresh {
+                        given.insert(fresh.clone());
+                        renamed.insert(st.id.clone(), fresh);
+                    }
+                }
+            }
+            default_style = Some(renamed.get("Normal").cloned().unwrap_or_else(|| "Normal".into()));
+        }
+        let restyle = |id: &mut Option<String>| {
+            if let Some(new) = id.as_ref().and_then(|i| renamed.get(i)) {
+                *id = Some(new.clone());
+            }
+        };
+        let mut media = BTreeMap::new();
+        for (key, data) in &src.media {
+            let ext = key.rsplit_once('.').map(|(_, e)| e).unwrap_or("png");
+            media.insert(key.clone(), self.add_media(data.to_vec(), ext));
+        }
+        let next_abs = self.numbering.abstracts.iter().map(|a| a.id.saturating_add(1)).max().unwrap_or(0);
+        let mut abs_map = BTreeMap::new();
+        for (i, a) in src.numbering.abstracts.iter().enumerate() {
+            let id = next_abs.saturating_add(i as u32);
+            abs_map.insert(a.id, id);
+            let mut a = crate::numbering::AbstractNum { id, ..a.clone() };
+            a.levels.iter_mut().for_each(|l| restyle(&mut l.style));
+            self.numbering.abstracts.push(a);
+        }
+        let next_num = self.numbering.nums.iter().map(|n| n.id.saturating_add(1)).max().unwrap_or(1).max(1);
+        let mut nums = BTreeMap::new();
+        for (i, n) in src.numbering.nums.iter().enumerate() {
+            let id = next_num.saturating_add(i as u32);
+            nums.insert(n.id, id);
+            let abstract_id = abs_map.get(&n.abstract_id).copied().unwrap_or(n.abstract_id);
+            let mut n = crate::numbering::Num { id, abstract_id, ..n.clone() };
+            n.level_overrides.iter_mut().for_each(|(_, l)| restyle(&mut l.style));
+            self.numbering.nums.push(n);
+        }
+        let renumber = |n: &mut Option<crate::props::NumRef>| {
+            if let Some(n) = n.as_mut()
+                && n.num != 0
+            {
+                n.num = nums.get(&n.num).copied().unwrap_or(0);
+            }
+        };
+        // What a style in the other document doesn't set comes from its defaults there, and
+        // Word's own (no space, single lines) where those don't say.
+        let mut para_defaults = src.styles.default_para.clone();
+        para_defaults.space_before.get_or_insert(0.0);
+        para_defaults.space_after.get_or_insert(0.0);
+        para_defaults.line_spacing.get_or_insert(crate::props::LineSpacing::Multiple(1.0));
+        for st in &src.styles.styles {
+            let mut st = st.clone();
+            // Our defaults stay ours.
+            st.default = false;
+            if keep_styles {
+                if let Some(new) = renamed.get(&st.id) {
+                    st.name = format!("{} ({new})", st.name);
+                    st.id = new.clone();
+                }
+                restyle(&mut st.based_on);
+                restyle(&mut st.next);
+                restyle(&mut st.linked);
+                // A character style's runs get the defaults through their paragraph's style.
+                if st.based_on.is_none() && st.kind != crate::styles::StyleKind::Character {
+                    let mut chr = src.styles.default_chr.clone();
+                    chr.overlay(&st.chr);
+                    st.chr = chr;
+                    let mut para = para_defaults.clone();
+                    para.overlay(&st.para);
+                    st.para = para;
+                }
+            }
+            if self.styles.get(&st.id).is_none() {
+                renumber(&mut st.para.numbering);
+                self.styles.upsert(st);
+            }
+        }
+        let rev = u32::try_from(self.revisions.len()).unwrap_or(u32::MAX);
+        self.revisions.extend(src.revisions.iter().cloned());
+        // Notes and comments get stories (and comments ids) of their own here; their text is
+        // relinked below, once every new id is known.
+        let mut notes = BTreeMap::new();
+        for (id, part) in src.parts.iter().filter(|(_, p)| matches!(p.kind, PartKind::Footnote | PartKind::Endnote)) {
+            notes.insert(*id, self.add_part(part.kind, Vec::new()));
+        }
+        let mut comments = BTreeMap::new();
+        let mut next_comment = self.comments.keys().next_back().map_or(0, |k| k.saturating_add(1));
+        for (id, c) in &src.comments {
+            if src.parts.get(&c.part).is_some_and(|p| p.kind == PartKind::Comment) {
+                notes.insert(c.part, self.add_part(PartKind::Comment, Vec::new()));
+                comments.insert(*id, next_comment);
+                next_comment = next_comment.saturating_add(1);
+            }
+        }
+        let boxes: BTreeMap<u32, Part> = src.parts.iter().filter(|(_, p)| p.kind == PartKind::TextBox).map(|(k, p)| (*k, p.clone())).collect();
+        // Its permission ranges are numbered after ours, so no end of theirs closes one of ours.
+        let first_perm = perm_end(self.body.iter().chain(self.parts.values().flat_map(|p| p.blocks.iter()))).max(*perms);
+        *perms = first_perm.saturating_add(perm_end(src.body.iter().chain(src.parts.values().flat_map(|p| p.blocks.iter()))));
+        let link = Relink {
+            media: &media,
+            nums: &nums,
+            notes: &notes,
+            comments: &comments,
+            boxes: &boxes,
+            perms: first_perm,
+            rev,
+            revs: u32::try_from(src.revisions.len()).unwrap_or(u32::MAX),
+            styles: &renamed,
+            default_style: default_style.as_deref(),
+        };
+        let mut parts = boxes.clone();
+        for part in parts.values_mut() {
+            part.blocks.iter_mut().for_each(|b| link.block(Arc::make_mut(b)));
+        }
+        // A note's or comment's text boxes get stories here now; the body's go with the fragment.
+        let mut budget = BoxBudget::new();
+        for (old, new) in &notes {
+            let Some(part) = src.parts.get(old) else { continue };
+            let mut blocks: Vec<Block> = part.blocks.iter().map(|b| (**b).clone()).collect();
+            blocks.iter_mut().for_each(|b| link.block(b));
+            self.adopt_text_boxes(&mut blocks, &parts, 0, &mut budget);
+            if let Some(p) = self.parts.get_mut(new) {
+                p.blocks = blocks.into_iter().map(Arc::new).collect();
+            }
+        }
+        for (id, c) in &src.comments {
+            if let (Some(new), Some(part)) = (comments.get(id), notes.get(&c.part)) {
+                let parent = c.parent.and_then(|p| comments.get(&p).copied());
+                // Its durable id is unique in its own document only: the writer gives the copy one.
+                self.comments.insert(*new, crate::Comment { parent, part: *part, durable_id: None, ..c.clone() });
+            }
+        }
+        let mut blocks: Vec<Block> = src.body.iter().map(|b| (**b).clone()).collect();
+        blocks.iter_mut().for_each(|b| link.block(b));
+        Fragment { blocks, parts }
+    }
+
+    /// [`Self::adopt_with`] as blocks to place in a story directly (a reader building one): its
+    /// text boxes already have stories of their own here. `perms` is the first permission range
+    /// id the reader hasn't given out (ranges it holds aren't in this document yet); it moves past
+    /// the adopted ones.
+    pub fn adopt_blocks(&mut self, src: Document, keep_styles: bool, perms: &mut u32) -> Vec<Block> {
+        let Fragment { mut blocks, parts } = self.adopt_in(src, keep_styles, perms);
+        let mut budget = BoxBudget::new();
+        self.adopt_text_boxes(&mut blocks, &parts, 0, &mut budget);
+        blocks
+    }
+
    /// Copies of the text box stories shapes in `blocks` show, nested boxes included.
    fn text_box_parts(&self, blocks: &[Block]) -> BTreeMap<u32, Part> {
        let mut out = BTreeMap::new();
@@ -846,6 +1254,13 @@ impl Document {
            }
            return out;
        }
+        // Across the cells of a whole table: the table itself, not its cells' paragraphs (#1744).
+        if let Some(tp) = self.whole_table(&a, &b)
+            && let Some(blk) = self.block(a.story, &tp)
+        {
+            out.push(blk.clone());
+            return out;
+        }
        for p in self.paths_between(&a, &b) {
            if let Some(para) = self.para(a.story, &p) {
                let mut q = para.clone();
@@ -901,7 +1316,7 @@ impl Document {
            budget.skipped = budget.skipped.saturating_add(1);
            return None;
        }
-        let src = parts.get(&old).or_else(|| self.parts.get(&old).filter(|p| p.kind == PartKind::TextBox))?;
+        let src = parts.get(&old).or_else(|| self.parts.get(&old).filter(|p| budget.local && p.kind == PartKind::TextBox))?;
        // Charge what the copy really allocates before making any of it: the block slots, and the
        // blocks holding text boxes (deep-copied below). The rest are shared `Arc`s, however many
        // boxes show them, so they cost nothing more. Worked out once per paste.
@@ -942,6 +1357,22 @@ impl Document {
        Some(id)
    }

+    /// The blocks of `frag`, a fragment of another document, with every text box given a new
+    /// story of its own here copied from the fragment's parts (as a paste does), to place them
+    /// in this document; a box the fragment has no story for keeps none.
+    pub fn adopt_fragment(&mut self, frag: &Fragment) -> Vec<Block> {
+        let mut blocks = frag.blocks.clone();
+        let mut budget = BoxBudget { local: false, ..BoxBudget::new() };
+        self.adopt_text_boxes(&mut blocks, &frag.parts, 0, &mut budget);
+        if budget.skipped > 0 {
+            log::warn!(
+                "{} text boxes are left empty; their stories are past what one copy brings ({MAX_PASTED_BOXES} stories, {MAX_PASTED_BOX_BYTES} bytes)",
+                budget.skipped
+            );
+        }
+        blocks
+    }
+
    /// Insert a fragment at `pos`; returns the position after the pasted content.
    pub fn insert_fragment(&mut self, pos: &Pos, frag: &Fragment) -> Result<Pos> {
        // Tables that would nest deeper than the limit here become their paragraphs (#1596).
@@ -664,3 +664,230 @@ fn a_table_nested_deeper_than_the_paragraph_walk_is_never_removed_whole() {
    d.delete_range(&Pos { story: StoryRef::Body, path: first, off: 0 }, &Pos::body(2, 0)).unwrap();
    assert!(d.body.get(1).is_some_and(|b| b.as_table().is_some()), "a table with paragraphs the walk never saw was removed");
 }
+#[test]
+fn adopting_a_document_renumbers_what_it_refers_to() {
+    use crate::para::NoteKind;
+    use crate::{Comment, Revision, RevisionKind};
+    // Ours already has a footnote, a comment, a list and a revision with the ids the other's use.
+    let mut ours = doc(&["ours"]);
+    let our_note = ours.add_part(PartKind::Footnote, vec![para_block(Paragraph::with_text("our note", CharProps::default()))]);
+    ours.comments.insert(0, Comment { part: our_note, ..Comment::default() });
+    let our_list = ours.numbering.add_list(crate::numbering::ListKind::Bullet);
+    ours.revisions.push(Revision { kind: RevisionKind::Insert, ..Revision::default() });
+
+    let mut theirs = doc(&["theirs"]);
+    let note = theirs.add_part(PartKind::Footnote, vec![para_block(Paragraph::with_text("their note", CharProps::default()))]);
+    let said = theirs.add_part(PartKind::Comment, vec![para_block(Paragraph::with_text("their comment", CharProps::default()))]);
+    theirs.comments.insert(0, Comment { author: "Them".into(), part: said, durable_id: Some("0A0B0C0D".into()), ..Comment::default() });
+    let list = theirs.numbering.add_list(crate::numbering::ListKind::Bullet);
+    assert_eq!(list, our_list);
+    theirs.revisions.push(Revision { kind: RevisionKind::Delete, ..Revision::default() });
+    let mut style = crate::styles::Style { id: "TheirList".into(), name: "Their List".into(), ..Default::default() };
+    style.para.numbering = Some(crate::props::NumRef { num: list, level: 0 });
+    theirs.styles.upsert(style);
+    let p = theirs.para_mut(StoryRef::Body, &Path::top(0)).unwrap();
+    p.props.numbering = Some(crate::props::NumRef { num: list, level: 0 });
+    p.runs[0].props.del = Some(0);
+    // An insertion naming a revision it doesn't have.
+    p.runs[0].props.ins = Some(7);
+    let props = p.props_of_char(0).clone();
+    p.insert_object(0, InlineObject::NoteRef { kind: NoteKind::Footnote, id: note, custom: String::new() }, &props).unwrap();
+    p.insert_object(0, InlineObject::CommentStart { id: 0 }, &props).unwrap();
+
+    let frag = ours.adopt(theirs);
+    let Some(Block::Para(p)) = frag.blocks.first() else { panic!() };
+    let new_list = p.props.numbering.unwrap().num;
+    assert_ne!(new_list, our_list);
+    assert!(ours.numbering.num(new_list).is_some());
+    assert_eq!(ours.styles.get("TheirList").and_then(|s| s.para.numbering).map(|n| n.num), Some(new_list));
+    // Their deletion is their revision, after ours.
+    let del = p.runs.iter().find_map(|r| r.props.del).unwrap();
+    assert_eq!(ours.revisions.get(del as usize).map(|r| r.kind), Some(RevisionKind::Delete));
+    assert!(p.runs.iter().all(|r| r.props.ins.is_none()));
+    // Their note and comment come along under ids of their own.
+    let (note_id, comment_id) = p.objects.iter().fold((None, None), |(n, c), o| match o {
+        InlineObject::NoteRef { id, .. } => (Some(*id), c),
+        InlineObject::CommentStart { id } => (n, Some(*id)),
+        _ => (n, c),
+    });
+    let text = |id: u32| {
+        ours.parts
+            .get(&id)
+            .map(|p| p.blocks.iter().map(|b| if let Block::Para(p) = &**b { p.text.clone() } else { String::new() }).collect::<String>())
+    };
+    assert_eq!(text(note_id.unwrap()).as_deref(), Some("their note"));
+    let comment = ours.comments.get(&comment_id.unwrap()).unwrap();
+    assert_eq!((comment.author.as_str(), text(comment.part).as_deref()), ("Them", Some("their comment")));
+    // Its durable id is the other document's: the writer gives the copy one of its own.
+    assert_eq!(comment.durable_id, None);
+    assert_eq!(text(our_note).as_deref(), Some("our note"));
+}
+
+#[test]
+fn a_kept_character_style_leaves_what_it_doesnt_set_to_the_paragraph_style() {
+    use crate::styles::{Style, StyleKind, StyleSheet};
+    let mut ours = doc(&["ours"]);
+    let mut theirs = doc(&["theirs"]);
+    theirs.styles = StyleSheet::empty();
+    theirs.styles.default_chr = CharProps { size: Some(9.0), ..Default::default() };
+    let big = CharProps { size: Some(20.0), ..Default::default() };
+    theirs.styles.upsert(Style { id: "Big".into(), name: "Big".into(), chr: big, ..Default::default() });
+    theirs.styles.upsert(Style { id: "Link".into(), name: "Link".into(), kind: StyleKind::Character, ..Default::default() });
+    let p = theirs.para_mut(StoryRef::Body, &Path::top(0)).unwrap();
+    p.props.style = Some("Big".into());
+    p.runs[0].props.style = Some("Link".into());
+
+    let frag = ours.adopt_with(theirs, true);
+    let Some(Block::Para(p)) = frag.blocks.first() else { panic!() };
+    assert_eq!(ours.styles.resolve_char(p.props.style.as_deref(), &p.runs[0].props).size, 20.0);
+}
+
+#[test]
+fn kept_styles_renamed_on_adoption_are_renamed_in_list_levels_too() {
+    use crate::styles::Style;
+    let mut ours = doc(&["ours"]);
+    ours.styles.upsert(Style { id: "Heading1".into(), name: "heading 1".into(), ..Default::default() });
+    let mut theirs = doc(&["theirs"]);
+    theirs.styles.upsert(Style { id: "Heading1".into(), name: "heading 1".into(), ..Default::default() });
+    let list = theirs.numbering.add_list(crate::numbering::ListKind::Numbered);
+    let abs = theirs.numbering.nums.iter().find(|n| n.id == list).map(|n| n.abstract_id).unwrap();
+    let a = theirs.numbering.abstracts.iter_mut().find(|a| a.id == abs).unwrap();
+    a.levels[0].style = Some("Heading1".into());
+    let level = a.levels[0].clone();
+    theirs.numbering.nums.iter_mut().find(|n| n.id == list).unwrap().level_overrides.push((1, level));
+
+    let before = ours.numbering.abstracts.len();
+    ours.adopt_with(theirs, true);
+    let copied = &ours.numbering.abstracts[before..];
+    let styles: Vec<_> = copied
+        .iter()
+        .flat_map(|a| a.levels.iter())
+        .chain(ours.numbering.nums.iter().flat_map(|n| n.level_overrides.iter().map(|(_, l)| l)))
+        .filter_map(|l| l.style.clone())
+        .collect();
+    assert_eq!(styles.len(), 2, "{styles:?}");
+    for st in &styles {
+        assert_ne!(st, "Heading1");
+        assert!(ours.styles.get(st).is_some(), "{st}");
+    }
+}
+
+#[test]
+fn an_adopted_section_breaks_tracked_change_names_its_revision() {
+    use crate::{Revision, RevisionKind, SectionProps};
+    let mut ours = doc(&["ours"]);
+    ours.revisions.push(Revision { kind: RevisionKind::Insert, ..Revision::default() });
+    let mut theirs = doc(&["theirs"]);
+    theirs.revisions.push(Revision { kind: RevisionKind::Format, ..Revision::default() });
+    let p = theirs.para_mut(StoryRef::Body, &Path::top(0)).unwrap();
+    p.section = Some(Box::new(SectionProps { fmt_change: crate::props::PropChange::boxed(0, SectionProps::default()), ..SectionProps::default() }));
+
+    let frag = ours.adopt(theirs);
+    let Some(Block::Para(p)) = frag.blocks.first() else { panic!() };
+    let rev = p.section.as_ref().and_then(|s| s.fmt_change.as_ref()).map(|c| c.rev);
+    assert_eq!(rev.and_then(|r| ours.revisions.get(r as usize)).map(|r| r.kind), Some(RevisionKind::Format));
+}
+
+#[test]
+fn an_adopted_tracked_format_change_keeps_its_old_styles_and_list() {
+    use crate::props::{NumRef, ParaProps, PropChange};
+    use crate::{Revision, RevisionKind};
+    for keep in [false, true] {
+        let mut ours = doc(&["ours"]);
+        let our_list = ours.numbering.add_list(crate::numbering::ListKind::Bullet);
+        let mut theirs = doc(&["theirs"]);
+        theirs.revisions.push(Revision { kind: RevisionKind::Format, ..Revision::default() });
+        let list = theirs.numbering.add_list(crate::numbering::ListKind::Bullet);
+        assert_eq!(list, our_list);
+        let p = theirs.para_mut(StoryRef::Body, &Path::top(0)).unwrap();
+        // Live and old props name the same styles (ours has them too) and their list.
+        p.props.style = Some("Quote".into());
+        p.props.numbering = Some(NumRef { num: list, level: 0 });
+        let old = ParaProps { style: Some("Quote".into()), numbering: Some(NumRef { num: list, level: 0 }), ..ParaProps::default() };
+        p.props.fmt_change = PropChange::boxed(0, old);
+        p.runs[0].props.style = Some("Strong".into());
+        p.runs[0].props.fmt_change = PropChange::boxed(0, CharProps { style: Some("Strong".into()), ..CharProps::default() });
+
+        let frag = ours.adopt_with(theirs, keep);
+        let Some(Block::Para(p)) = frag.blocks.first() else { panic!() };
+        let old = &p.props.fmt_change.as_ref().unwrap().old;
+        assert_eq!((&old.style, old.numbering), (&p.props.style, p.props.numbering), "keep_styles {keep}");
+        assert_ne!(old.numbering.map(|n| n.num), Some(our_list));
+        let run = &p.runs[0].props;
+        assert_eq!(run.fmt_change.as_ref().unwrap().old.style, run.style, "keep_styles {keep}");
+    }
+}
+
+#[test]
+fn adopted_styles_never_become_our_defaults() {
+    use crate::styles::{Style, StyleKind};
+    for keep in [false, true] {
+        let mut ours = doc(&["ours"]);
+        let mut theirs = doc(&["theirs"]);
+        // A localized default character style, and one whose id we have too.
+        theirs.styles.upsert(Style { id: "Absatz".into(), kind: StyleKind::Character, default: true, ..Default::default() });
+        theirs.styles.upsert(Style { id: "Strong".into(), kind: StyleKind::Character, default: true, ..Default::default() });
+        ours.adopt_with(theirs, keep);
+        assert!(ours.styles.styles.iter().all(|s| !s.default), "keep_styles {keep}");
+    }
+}
+
+#[test]
+fn adopted_permission_ranges_keep_ids_of_their_own() {
+    let perm = |id, editor: &str| InlineObject::PermStart { id, group: String::new(), editor: editor.into() };
+    let mut ours = doc(&["ours"]);
+    ours.insert_object(&Pos::body(0, 4), InlineObject::PermEnd { id: 0 }, &CharProps::default()).unwrap();
+    ours.insert_object(&Pos::body(0, 0), perm(0, "us"), &CharProps::default()).unwrap();
+    // Theirs: a closed range and one left open, numbered from 0 like ours.
+    let mut theirs = doc(&["theirs"]);
+    theirs.insert_object(&Pos::body(0, 6), perm(1, "them"), &CharProps::default()).unwrap();
+    theirs.insert_object(&Pos::body(0, 6), InlineObject::PermEnd { id: 0 }, &CharProps::default()).unwrap();
+    theirs.insert_object(&Pos::body(0, 0), perm(0, "them"), &CharProps::default()).unwrap();
+
+    let frag = ours.adopt(theirs);
+    let Some(Block::Para(p)) = frag.blocks.first() else { panic!() };
+    let ids: Vec<u32> = p
+        .objects
+        .iter()
+        .filter_map(|o| match o {
+            InlineObject::PermStart { id, .. } | InlineObject::PermEnd { id } => Some(*id),
+            _ => None,
+        })
+        .collect();
+    assert_eq!(ids.len(), 3);
+    assert!(!ids.contains(&0), "{ids:?}");
+    assert_eq!(ids[0], ids[1], "a range's start and end still pair: {ids:?}");
+    assert_ne!(ids[1], ids[2]);
+}
+
+#[test]
+fn an_adopted_notes_text_box_gets_a_story_of_its_own() {
+    use crate::para::NoteKind;
+    // Ours has a text box under the id their note's text box has.
+    let mut ours = doc(&["ours"]);
+    ours.add_part(PartKind::Footnote, Vec::new());
+    let our_box = text_box(&mut ours, &Pos::body(0, 0), "our box");
+    let mut theirs = doc(&["theirs"]);
+    let note = theirs.add_part(PartKind::Footnote, vec![para_block(Paragraph::with_text("note", CharProps::default()))]);
+    let their_box = theirs.add_part(PartKind::TextBox, vec![para_block(Paragraph::with_text("their box", CharProps::default()))]);
+    assert_eq!(their_box, our_box);
+    theirs
+        .insert_object(&Pos { story: StoryRef::Part(note), path: Path::top(0), off: 0 }, box_shape(Some(their_box)), &CharProps::default())
+        .unwrap();
+    theirs
+        .insert_object(&Pos::body(0, 0), InlineObject::NoteRef { kind: NoteKind::Footnote, id: note, custom: String::new() }, &CharProps::default())
+        .unwrap();
+
+    let blocks = ours.adopt(theirs).blocks;
+    let Some(Block::Para(p)) = blocks.first() else { panic!() };
+    let new_note = p.objects.iter().find_map(|o| if let InlineObject::NoteRef { id, .. } = o { Some(*id) } else { None }).unwrap();
+    let story = ours.parts[&new_note]
+        .blocks
+        .iter()
+        .find_map(|b| if let Block::Para(p) = &**b { p.objects.iter().find_map(|o| o.text_boxes().first().copied()) } else { None })
+        .unwrap();
+    assert_ne!(story, our_box);
+    let part = &ours.parts[&story];
+    assert_eq!(part.kind, PartKind::TextBox);
+    assert!(matches!(part.blocks.first().map(|b| &**b), Some(Block::Para(p)) if p.text == "their box"));
+}
@@ -48,6 +48,7 @@ pub mod symbol_fonts;
 pub mod table;
 pub mod wordart;
 pub mod wrap;
+pub mod zip_guard;

 use std::collections::BTreeMap;
 use std::sync::Arc;
@@ -338,6 +338,23 @@ impl Counters {
                *f = LevelFlags { started: false, first: Some(*start) };
            }
        }
+        // A level above that hasn't counted yet counts its first number here, as in Word: after
+        // 1.1 and 1.2 with no level-1 item before them, the next level-1 item is 2, whether or not
+        // the deeper level's text shows it.
+        for (k, (v, f)) in st.iter_mut().zip(fl.iter_mut()).enumerate().take(lv) {
+            if f.started {
+                continue;
+            }
+            let start = match self.seen.entry((num, k as u8)) {
+                std::collections::hash_map::Entry::Vacant(e) => {
+                    e.insert(true);
+                    n.start_overrides.iter().find(|(l, _)| *l as usize == k).map(|(_, s)| *s)
+                }
+                std::collections::hash_map::Entry::Occupied(_) => None,
+            };
+            *v = start.or(f.first).unwrap_or_else(|| level_def(k).map_or(1, |l| l.start));
+            *f = LevelFlags { started: true, first: None };
+        }
        if let (Some(v), Some(f)) = (st.get_mut(lv), fl.get_mut(lv)) {
            *v = if f.started { v.saturating_add(1) } else { f.first.unwrap_or(def.start) };
            *f = LevelFlags { started: true, first: None };
@@ -426,8 +443,9 @@ mod tests {
        assert_eq!(c.next_label(&n, id, 2).unwrap().0, "1.02");
        assert_eq!(c.next_label(&n, id, 1).unwrap().0, "");
        assert_eq!(c.next_label(&n, id, 2).unwrap().0, "2.01");
-        // Levels it doesn't define still come from the abstract list.
-        assert_eq!(c.next_label(&n, id, 0).unwrap().0, "1.");
+        // Levels it doesn't define still come from the abstract list; level 0 took its first number
+        // with the first level-1 item, so this is its second.
+        assert_eq!(c.next_label(&n, id, 0).unwrap().0, "2.");
        assert_eq!(n.level(id, 2).map(|l| l.format), Some(NumFormat::DecimalZero));
    }

@@ -476,6 +494,40 @@ mod tests {
        assert_eq!(l(2), "(1)", "level 1 restarts level 3");
    }

+    #[test]
+    fn a_deeper_item_first_counts_the_levels_above_it() {
+        // Measured in Word: a level above that hasn't counted yet takes its first number at the
+        // first deeper item, whether or not that item's text shows it.
+        let labels_with = |starts: [u32; 3], texts: [&str; 3], overrides: &[(u8, u32)], seq: &[u8]| {
+            let mut n = Numbering::default();
+            let id = n.add_list(ListKind::Legal);
+            if let Some(a) = n.abstracts.first_mut() {
+                for (l, (s, t)) in a.levels.iter_mut().zip(starts.into_iter().zip(texts)) {
+                    l.start = s;
+                    l.text = t.into();
+                }
+            }
+            if let Some(num) = n.nums.iter_mut().find(|x| x.id == id) {
+                num.start_overrides = overrides.to_vec();
+            }
+            let mut c = Counters::default();
+            seq.iter().map(|lv| c.next_label(&n, id, *lv).unwrap().0).collect::<Vec<_>>()
+        };
+        let labels = |starts: [u32; 3], texts: [&str; 3], seq: &[u8]| labels_with(starts, texts, &[], seq);
+        let std = ["%1.", "%1.%2.", "%1.%2.%3."];
+        assert_eq!(labels([1, 1, 1], std, &[1, 1, 0, 0]), ["1.1.", "1.2.", "2.", "3."]);
+        assert_eq!(labels([10, 1, 1], std, &[1, 1, 1, 1, 0, 0]), ["10.1.", "10.2.", "10.3.", "10.4.", "11.", "12."]);
+        assert_eq!(labels([1, 1, 1], ["%1.", "(%2)", "%1.%2.%3."], &[1, 1, 0, 0]), ["(1)", "(2)", "2.", "3."]);
+        assert_eq!(labels([1, 1, 1], std, &[2, 1, 0, 1]), ["1.1.1.", "1.2.", "2.", "2.1."]);
+        assert_eq!(labels([1, 1, 1], ["%1.", "%1.%2.", "(%3)"], &[2, 1, 0]), ["(1)", "1.2.", "2."]);
+        assert_eq!(labels([1, 1, 1], std, &[0, 2, 1, 0]), ["1.", "1.1.1.", "1.2.", "2."]);
+        // The num's own start for the level above counts in its place, as the level's start does.
+        assert_eq!(labels_with([1, 1, 1], std, &[(0, 10)], &[1, 1, 0]), ["10.1.", "10.2.", "11."]);
+        assert_eq!(labels_with([1, 1, 1], std, &[(0, 5)], &[1, 0, 1]), ["5.1.", "6.", "6.1."]);
+        // A level-1 item after the first deeper ones restarts level 2 below it, as usual.
+        assert_eq!(labels([1, 1, 1], std, &[1, 1, 0, 1, 1, 0, 2]), ["1.1.", "1.2.", "2.", "2.1.", "2.2.", "3.", "3.1.1."]);
+    }
+
    #[test]
    fn a_level_starting_at_zero_counts_up() {
        let mut n = Numbering::default();
@@ -501,9 +501,8 @@ impl Paragraph {
    pub fn next_boundary(&self, off: usize) -> usize {
        crate::cluster::next_cluster(&self.text, self.clamp(off))
    }
-    /// Where Backspace at `off` deletes from: the previous character in the Brahmic scripts
-    /// (Myanmar, Khmer, Devanagari, Thai…), where it removes one vowel sign or stacked consonant
-    /// at a time, otherwise the previous caret stop.
+    /// Where Backspace at `off` deletes from: one Arabic combining mark or one character in the
+    /// Brahmic scripts (Myanmar, Khmer, Devanagari, Thai…), otherwise the previous caret stop.
    pub fn backspace_from(&self, off: usize) -> usize {
        let off = self.clamp(off);
        match self.text.get(..off).and_then(|t| t.char_indices().next_back()) {
@@ -273,6 +273,12 @@ pub struct CharProps {
    pub small_caps: Option<bool>,
    #[serde(skip_serializing_if = "Option::is_none")]
    pub hidden: Option<bool>,
+    /// Hidden in Web Layout (`w:webHidden`); distinct from `w:vanish` (`hidden`).
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub web_hidden: Option<bool>,
+    /// Snap characters to the document grid (`w:snapToGrid`). Unset inherits; Word's default is on.
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub snap_to_grid: Option<bool>,
    /// Character spacing (expanded/condensed), points.
    #[serde(skip_serializing_if = "Option::is_none")]
    pub spacing: Option<f32>,
@@ -448,6 +454,7 @@ impl CharProps {
    /// overlaid on `base`.
    pub fn minus(mut self, base: &CharProps) -> CharProps {
        self.minus_text_style(base);
+        self.minus_run_visibility(base);
        self.minus_script_style(base);
        self.minus_document_marks(base);
        self
@@ -458,6 +465,10 @@ impl CharProps {
            shading, border, vert_align, caps, small_caps, hidden, spacing, scale, position, kern, outline, shadow, emboss, engrave, lang, no_proof, rtl);
    }

+    fn minus_run_visibility(&mut self, base: &CharProps) {
+        drop_same_fields!(self, base; web_hidden, snap_to_grid);
+    }
+
    fn minus_script_style(&mut self, base: &CharProps) {
        drop_same_fields!(self, base; cs, font_cs, font_ea, size_cs, bold_cs, italic_cs, lang_bidi, lang_ea, east_asian_layout);
    }
@@ -472,6 +483,7 @@ impl CharProps {
    /// format both scripts must set both values explicitly.
    pub fn overlay(&mut self, patch: &CharProps) {
        self.overlay_text_style(patch);
+        self.overlay_run_visibility(patch);
        self.overlay_script_style(patch);
        self.overlay_document_marks(patch);
        if let Some(p) = &patch.text_effects {
@@ -484,6 +496,10 @@ impl CharProps {
            shading, border, vert_align, caps, small_caps, hidden, spacing, scale, position, kern, outline, shadow, emboss, engrave, lang, no_proof, rtl);
    }

+    fn overlay_run_visibility(&mut self, patch: &CharProps) {
+        overlay_fields!(self, patch; web_hidden, snap_to_grid);
+    }
+
    fn overlay_script_style(&mut self, patch: &CharProps) {
        overlay_fields!(self, patch; cs, font_cs, font_ea, size_cs, bold_cs, italic_cs, lang_bidi, lang_ea, east_asian_layout);
    }
@@ -270,7 +270,12 @@ impl ResolvedPara {
            drop_cap_margin: p.drop_cap_margin.unwrap_or(false),
            drop_cap_distance: p.drop_cap_distance.filter(|d| d.is_finite()).unwrap_or(0.0).clamp(0.0, MAX_DROP_CAP_DISTANCE),
            drop_cap_font: p.drop_cap_font.clone().filter(|f| !f.trim().is_empty()),
-            frame: p.frame.clone().filter(|_| p.drop_cap.unwrap_or(0) == 0),
+            // Explicit zero dimensions cancel a frame; omitted dimensions still fit its text.
+            frame: p.frame.clone().filter(|f| p.drop_cap.unwrap_or(0) == 0 && (f.w != Some(0.0) || f.h != Some(0.0))).map(|mut f| {
+                f.w = f.w.filter(|v| *v != 0.0);
+                f.h = f.h.filter(|v| *v != 0.0);
+                f
+            }),
            suppress_hyphens: p.suppress_hyphens.unwrap_or(false),
            suppress_line_numbers: p.suppress_line_numbers.unwrap_or(false),
            kinsoku: p.kinsoku.unwrap_or(true),
@@ -295,8 +300,12 @@ impl StyleSheet {
        self.para_style_props_over(style, self.default_para.clone(), self.default_chr.clone())
    }

-    /// The paragraph style chain of `style` applied over `pp` / `cp`.
+    /// The paragraph style chain of `style` applied over `pp` / `cp`. A style the document doesn't
+    /// define is the default paragraph style, Normal, as in Word: a footer naming a `Footer` style
+    /// that `styles.xml` leaves out is formatted as Normal, not with the document defaults alone
+    /// (#5077).
    fn para_style_props_over(&self, style: &str, mut pp: ParaProps, mut cp: CharProps) -> (ParaProps, CharProps) {
+        let style = if self.get(style).is_some() { style } else { "Normal" };
        for s in self.chain(style) {
            if s.kind == StyleKind::Paragraph {
                let mut sp = s.para.clone();
@@ -395,6 +404,31 @@ mod tests {
        assert_eq!(s.resolve_char(None, &direct).font, "Wingdings");
    }

+    /// #5077: a paragraph naming a style the document doesn't define is formatted as Normal,
+    /// paragraph and run alike, not with the document defaults alone.
+    #[test]
+    fn an_undefined_paragraph_style_is_normal() {
+        let mut s = StyleSheet::builtin();
+        s.default_para.space_after = Some(10.0);
+        if let Some(n) = s.get_mut("Normal") {
+            n.para.space_after = Some(2.0);
+            n.chr.size = Some(13.0);
+        }
+        let undefined = ParaProps { style: Some("NoSuchStyle".into()), ..Default::default() };
+        let normal = s.resolve_para(&ParaProps::default());
+        let p = s.resolve_para(&undefined);
+        assert_eq!(p.space_after, 2.0);
+        assert_eq!(p.space_after, normal.space_after);
+        assert_eq!(p.line_spacing, normal.line_spacing);
+        assert_eq!(s.resolve_char(Some("NoSuchStyle"), &CharProps::default()).size, 13.0);
+        // The paragraph keeps the style it names; direct formatting still wins.
+        assert_eq!(p.style, "NoSuchStyle");
+        let direct = ParaProps { space_after: Some(7.0), ..undefined };
+        assert_eq!(s.resolve_para(&direct).space_after, 7.0);
+        // A defined style is unchanged.
+        assert_eq!(s.resolve_para(&ParaProps { style: Some("Heading1".into()), ..Default::default() }).space_after, 4.0);
+    }
+
    #[test]
    fn heading_resolves() {
        let s = StyleSheet::builtin();
@@ -10,6 +10,10 @@ pub struct Source {
    pub kind: String,
    /// "Last, First; Last, First"
    pub author: String,
+    /// A corporate author ("World Health Organization"): written as it is, never split into
+    /// names, and in place of `author` when set (Create Source › Corporate Author, `b:Corporate`,
+    /// #4848).
+    pub corporate: String,
    pub title: String,
    pub year: String,
    pub publisher: String,
@@ -39,6 +43,9 @@ pub struct CustomProp {
    /// the property's XML content kept verbatim (vectors, blobs).
    pub kind: String,
    pub value: String,
+    /// Bookmark associated with this property (`linkTarget`), retained without evaluating it.
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub link_target: Option<String>,
 }

 /// Document properties (File › Info).
@@ -77,6 +77,80 @@ pub const MAX_COLS: usize = 63;
 pub const MAX_TABLE_DEPTH: usize = 24;

 impl Table {
+    /// Grid columns `lo..hi` that [`Table::slice`] copies for `rows`/`cols` (widened over merged cells),
+    /// and whether any cell touches them (Cut clears the same cells it copies).
+    pub fn slice_bounds(&self, rows: (usize, usize), cols: (usize, usize)) -> (usize, usize, bool) {
+        let ((r0, r1), (g0, g1)) = (rows, cols);
+        let kept = || self.rows.iter().take(r1.saturating_add(1)).skip(r0);
+        // Grid columns `lo..hi` the cells touching them cover: a cell merged across that is partly
+        // in them widens them, for every row, so the copy isn't ragged. Each round only widens
+        // (at most once per grid column), so a bound of the grid's width plus one round is enough.
+        let (mut lo, mut hi) = (g0, g1.saturating_add(1));
+        let mut any = false;
+        for _ in 0..=MAX_COLS.saturating_add(1) {
+            let (mut nlo, mut nhi, mut found) = (lo, hi, false);
+            for row in kept() {
+                let mut g = 0usize;
+                for cell in &row.cells {
+                    let end = g.saturating_add(cell.span());
+                    if g < hi && end > lo {
+                        (nlo, nhi, found) = (nlo.min(g), nhi.max(end), true);
+                    }
+                    g = end;
+                }
+            }
+            any = found;
+            if (nlo, nhi) == (lo, hi) {
+                break;
+            }
+            (lo, hi) = (nlo, nhi);
+        }
+        (lo, hi, any)
+    }
+
+    /// A copy of rows `rows` of this table holding, of each row, the cells that reach into grid
+    /// columns `cols` (both inclusive): what Copy takes from selected rows or cells. Content
+    /// controls around rows and the table aren't copied (they'd lose their other end); a cell
+    /// that continues a vertical merge from a row left out starts the merge instead.
+    pub fn slice(&self, rows: (usize, usize), cols: (usize, usize)) -> Table {
+        let (r0, r1) = rows;
+        let kept = || self.rows.iter().take(r1.saturating_add(1)).skip(r0);
+        let (lo, hi, any) = self.slice_bounds(rows, cols);
+        let mut out_rows = Vec::new();
+        for row in kept() {
+            let mut g = 0usize;
+            let mut cells = Vec::new();
+            for cell in &row.cells {
+                let end = g.saturating_add(cell.span());
+                if any && g < hi && end > lo {
+                    cells.push(cell.clone());
+                }
+                g = end;
+            }
+            if !cells.is_empty() {
+                out_rows.push(Row { props: row.props.clone(), cells, controls: ControlWrap::default() });
+            }
+        }
+        if let Some(first) = out_rows.first_mut() {
+            for c in &mut first.cells {
+                if c.props.vmerge == VMerge::Continue {
+                    c.props.vmerge = VMerge::Restart;
+                }
+            }
+        }
+        let whole = lo == 0 && hi >= self.grid.len();
+        let grid = if whole { self.grid.clone() } else { self.grid.get(lo..hi.min(self.grid.len())).map(<[f32]>::to_vec).unwrap_or_default() };
+        let mut props = self.props.clone();
+        if !whole {
+            // Part of the columns: as wide as they are, not the whole table's width.
+            if props.width.is_some() || props.width_pct.is_some() {
+                props.width = Some(grid.iter().sum());
+            }
+            props.width_pct = None;
+        }
+        Table { props, grid, rows: out_rows, controls: ControlWrap::default() }
+    }
+
    /// A `rows × cols` table spanning `width` points, "Table Grid" style.
    pub fn new(rows: usize, cols: usize, width: f32) -> Table {
        let rows = rows.clamp(1, MAX_ROWS);
@@ -566,6 +640,69 @@ impl Table {
 mod tests {
    use super::*;

+    /// A 3×3 table, 100 pt columns: (0,0)–(0,1) merged across, (1,2)–(2,2) merged down.
+    fn merged() -> Table {
+        let mut t = Table::new(3, 3, 300.0);
+        t.merge(0, 0, 0, 1);
+        t.merge(1, 2, 2, 2);
+        assert_eq!(t.rows[0].cells.iter().map(Cell::span).collect::<Vec<_>>(), [2, 1]);
+        assert_eq!((t.rows[1].cells[2].props.vmerge, t.rows[2].cells[2].props.vmerge), (VMerge::Restart, VMerge::Continue));
+        t
+    }
+
+    fn spans(t: &Table) -> Vec<Vec<usize>> {
+        t.rows.iter().map(|r| r.cells.iter().map(Cell::span).collect()).collect()
+    }
+
+    /// #1744 review: a cell merged across that is partly selected takes its whole width, and the
+    /// other rows widen with it, so the copy isn't ragged.
+    #[test]
+    fn slice_widens_to_a_merged_cell_in_every_row() {
+        let t = merged().slice((0, 1), (1, 2));
+        assert_eq!(t.grid, [100.0, 100.0, 100.0]);
+        assert_eq!(spans(&t), [vec![2, 1], vec![1, 1, 1]]);
+        // Rows without the merged cell: just the selected columns.
+        let t = merged().slice((1, 2), (1, 2));
+        assert_eq!(t.grid, [100.0, 100.0]);
+        assert_eq!(spans(&t), [vec![1, 1], vec![1, 1]]);
+    }
+
+    /// #1744 review: a cell continuing a vertical merge from a row left out starts it instead.
+    #[test]
+    fn slice_starts_a_vertical_merge_whose_first_row_is_left_out() {
+        let t = merged().slice((2, 2), (0, 2));
+        assert_eq!(t.rows.len(), 1);
+        assert_eq!(t.rows[0].cells[2].props.vmerge, VMerge::Restart);
+        // Both rows kept: the merge is kept as it is.
+        let t = merged().slice((1, 2), (2, 2));
+        assert_eq!((t.rows[0].cells[0].props.vmerge, t.rows[1].cells[0].props.vmerge), (VMerge::Restart, VMerge::Continue));
+    }
+
+    /// #1744 review: part of the columns is as wide as they are; content controls around rows
+    /// and the table aren't copied.
+    #[test]
+    fn slice_width_and_controls() {
+        let mut t = Table::new(3, 3, 300.0);
+        (t.props.width, t.props.width_pct) = (Some(300.0), Some(50.0));
+        let wrap = ControlWrap { open: vec![crate::control::ContentControl::default()], close: 1 };
+        t.controls = wrap.clone();
+        t.rows[1].controls = wrap;
+        let part = t.slice((0, 2), (2, 2));
+        assert_eq!((part.grid.len(), part.props.width, part.props.width_pct), (1, Some(100.0), None));
+        let whole = t.slice((0, 2), (0, 2));
+        assert_eq!((whole.props.width, whole.props.width_pct), (Some(300.0), Some(50.0)), "all columns keep the table's width");
+        let row = t.slice((1, 1), (0, 2));
+        assert!(row.controls.is_empty() && row.rows[0].controls.is_empty());
+        // A table sized only by a percentage keeps a width for the part.
+        let mut pct = Table::new(3, 3, 300.0);
+        (pct.props.width, pct.props.width_pct) = (None, Some(50.0));
+        let part = pct.slice((0, 2), (2, 2));
+        assert_eq!((part.props.width, part.props.width_pct), (Some(100.0), None));
+        // Nothing in range: no rows.
+        assert!(t.slice((5, 6), (0, 2)).rows.is_empty());
+        assert!(t.slice((0, 2), (9, 9)).rows.is_empty());
+    }
+
    #[test]
    fn grid_before_shifts_the_row() {
        let mut t = Table::new(2, 3, 300.0);
@@ -1,5 +1,7 @@
 use super::*;

+mod note_conversion;
+
 #[test]
 fn new_document_is_valid() {
    let d = Document::new();
@@ -16,6 +18,20 @@ fn word_count() {
    assert_eq!(count_words(" -- "), 0);
 }

+/// #4547: each Han ideograph and kana counts as a word; punctuation and Hangul spacing don't change.
+#[test]
+fn word_count_counts_each_chinese_and_japanese_character() {
+    // #4547: unspaced Chinese counted as one word per run.
+    assert_eq!(count_words("我们今天去公园。"), 7);
+    assert_eq!(count_words("WordCraft是一个文字处理器，很好用！"), 1 + 11);
+    assert_eq!(count_words("ひらがなとカタカナ"), 9);
+    assert_eq!(count_words("ｶﾀｶﾅ"), 4);
+    assert_eq!(count_words("ｶﾞｷﾞ"), 2, "voiced sound marks belong to their kana");
+    assert_eq!(count_words("。、・「」"), 0);
+    // Korean is spaced: Hangul counts by tokens.
+    assert_eq!(count_words("안녕하세요 세계"), 2);
+}
+
 #[test]
 fn word_count_includes_numbered_list_labels_but_not_bullets() {
    let mut d = Document::new();
@@ -61,6 +77,23 @@ fn word_count_includes_numbered_labels_with_nothing_suffix() {
    assert_eq!(d.word_count(), 5);
 }

+/// #4547: a generated CJK list label such as 第十二章 still counts as one word.
+#[test]
+fn word_count_keeps_a_cjk_list_label_one_word() {
+    let mut d = Document::new();
+    let num_id = d.numbering.add_list(ListKind::Numbered);
+    let aid = d.numbering.num(num_id).expect("list num exists").abstract_id;
+    let a = d.numbering.abstracts.iter_mut().find(|a| a.id == aid).expect("abstract num exists");
+    a.levels[0].format = section::NumFormat::ChineseCounting;
+    a.levels[0].text = "第%1章".into();
+    a.levels[0].start = 12;
+    let mut p = Paragraph::with_text("总结", CharProps::default());
+    p.props.numbering = Some(props::NumRef { num: num_id, level: 0 });
+    d.body = vec![Arc::new(Block::Para(p))];
+    // The label 第十二章 stays one word (#4547 changed only document text); 总结 is two.
+    assert_eq!(d.word_count(), 1 + 2);
+}
+
 #[test]
 fn sections_and_section_mut() {
    let mut d = Document::from_text("a\nb\nc");
@@ -415,6 +448,25 @@ fn box_para(story: u32, id: u32) -> Blocks {
    vec![para_block(p)]
 }

+#[test]
+fn adopting_relinks_lists_in_deeply_nested_tables() {
+    // As #1339: a list paragraph 20 tables down takes the list it is brought in with.
+    let mut ours = Document::from_text("ours");
+    let our_list = ours.numbering.add_list(numbering::ListKind::Bullet);
+    let mut theirs = Document::from_text("theirs");
+    let list = theirs.numbering.add_list(numbering::ListKind::Bullet);
+    assert_eq!(list, our_list);
+    let mut p = Paragraph::with_text("item", CharProps::default());
+    p.props.numbering = Some(props::NumRef { num: list, level: 0 });
+    theirs.body = nested_tables(20, vec![para_block(p)]);
+    let mut nums = Vec::new();
+    for b in &ours.adopt(theirs).blocks {
+        edit::each_para(b, 0, &mut |p| nums.extend(p.props.numbering.map(|n| n.num)));
+    }
+    assert_eq!(nums.len(), 1);
+    assert_ne!(nums[0], our_list);
+}
+
 #[test]
 fn text_boxes_shown_from_deeply_nested_tables_are_kept() {
    // #1339: the paragraph walk stopped 16 tables down, so a box shown only from deeper was taken
@@ -651,3 +703,66 @@ fn control_markers_kept_are_sorted() {
        assert!(kept.windows(2).all(|p| p[0] < p[1]), "sorted, no repeats: {kept:?}");
    }
 }
+
+#[test]
+fn lone_table_open_markers_linear_time() {
+    let mut d = Document::new();
+    let mut t = Table::new(1, 1, 100.0);
+    const COUNT: usize = 2_000;
+    t.controls.open = (0..COUNT).map(|i| ContentControl { tag: format!("ctrl_{i}"), ..Default::default() }).collect();
+    d.body.insert(0, Arc::new(Block::Table(t)));
+
+    let mut paras = Vec::new();
+    let mut tables = Vec::new();
+    let timer = std::time::Instant::now();
+    crate::control::orphans(&d.body, &mut Vec::new(), 0, &mut paras, &mut tables);
+
+    assert_eq!(paras.len(), 0);
+    assert_eq!(tables.len(), COUNT);
+    for (i, (path, nth, is_open)) in tables.iter().enumerate() {
+        assert_eq!(*path, Path::top(0));
+        assert_eq!(*nth, i);
+        assert!(*is_open);
+    }
+
+    assert!(d.has_unbalanced_controls());
+    let removed = d.balance_controls();
+    assert_eq!(removed, COUNT);
+    assert!(!d.has_unbalanced_controls());
+    assert!(timer.elapsed().as_secs_f32() < 10.0, "{:?}", timer.elapsed());
+    let Block::Table(tbl) = &*d.body[0] else { panic!("expected table") };
+    assert!(tbl.controls.open.is_empty());
+}
+
+#[test]
+fn lone_table_open_markers_mixed_tables_and_paired() {
+    let mut d = Document::new();
+    let mut t0 = Table::new(1, 1, 100.0);
+    t0.controls.open = (0..3).map(|i| ContentControl { tag: format!("t0_{i}"), ..Default::default() }).collect();
+    t0.controls.close = 1;
+
+    let mut t1 = Table::new(1, 1, 100.0);
+    t1.controls.open = (0..2).map(|i| ContentControl { tag: format!("t1_{i}"), ..Default::default() }).collect();
+
+    d.body = vec![Arc::new(Block::Table(t0)), Arc::new(Block::Table(t1))];
+
+    let mut paras = Vec::new();
+    let mut tables = Vec::new();
+    crate::control::orphans(&d.body, &mut Vec::new(), 0, &mut paras, &mut tables);
+
+    assert_eq!(paras.len(), 0);
+    assert_eq!(tables, vec![(Path::top(0), 0, true), (Path::top(0), 1, true), (Path::top(1), 0, true), (Path::top(1), 1, true),]);
+
+    let removed = d.balance_controls();
+    assert_eq!(removed, 4);
+    assert!(!d.has_unbalanced_controls());
+
+    let Block::Table(res0) = &*d.body[0] else { panic!("expected table") };
+    assert_eq!(res0.controls.open.len(), 1);
+    assert_eq!(res0.controls.open[0].tag, "t0_2");
+    assert_eq!(res0.controls.close, 1);
+
+    let Block::Table(res1) = &*d.body[1] else { panic!("expected table") };
+    assert!(res1.controls.open.is_empty());
+    assert_eq!(res1.controls.close, 0);
+}
@@ -0,0 +1,145 @@
+use super::*;
+use crate::para::{InlineObject, NoteKind, OBJ};
+
+fn reference(id: u32, kind: NoteKind) -> InlineObject {
+    InlineObject::NoteRef { kind, id, custom: "*".into() }
+}
+
+fn styled(len: usize, style: &str) -> Run {
+    Run { len, props: CharProps { style: Some(style.into()), italic: Some(true), ..Default::default() } }
+}
+
+#[test]
+fn conversion_preserves_reference_run_boundaries_and_unmatched_storage() {
+    for (foot, end, expected) in [
+        (true, false, ["FootnoteReference", "EndnoteReference", "FootnoteReference", "EndnoteReference", "EndnoteReference", "FootnoteReference"]),
+        (false, true, ["FootnoteReference", "FootnoteReference", "FootnoteReference", "EndnoteReference", "FootnoteReference", "FootnoteReference"]),
+        (true, true, ["FootnoteReference", "EndnoteReference", "FootnoteReference", "EndnoteReference", "FootnoteReference", "FootnoteReference"]),
+    ] {
+        let mut d = Document::new();
+        let note = |style: &str| {
+            let mut p = Paragraph::with_text("Original note 漢", CharProps::default());
+            p.props.style = Some(style.into());
+            p.mark.style = Some(style.into());
+            vec![para_block(p)]
+        };
+        let f = d.add_part(PartKind::Footnote, note("FootnoteText"));
+        let e = d.add_part(PartKind::Endnote, note("EndnoteText"));
+        let p = Paragraph {
+            text: format!("é{OBJ}{OBJ}漢{OBJ}{OBJ}"),
+            objects: vec![
+                reference(f, NoteKind::Footnote),
+                InlineObject::BookmarkStart { name: "kept".into() },
+                reference(e, NoteKind::Endnote),
+                reference(999, NoteKind::Footnote),
+                reference(f, NoteKind::Footnote),
+            ],
+            runs: vec![
+                styled(2, "FootnoteReference"),
+                styled(3, "FootnoteReference"),
+                styled(3, "FootnoteReference"),
+                styled(3, "EndnoteReference"),
+                styled(3, "EndnoteReference"),
+                styled(3, "FootnoteReference"),
+            ],
+            ..Paragraph::new()
+        };
+        let mut table = Table::new(1, 1, 200.0);
+        table.rows[0].cells[0].blocks = vec![para_block(p.clone())];
+        d.body = vec![para_block(p.clone()), Arc::new(Block::Table(table))];
+        let h = d.add_part(PartKind::Header, vec![para_block(p.clone())]);
+        let t = d.add_part(PartKind::TextBox, vec![para_block(p.clone())]);
+        let before = d.clone();
+        assert_eq!(d.convert_notes(foot, end), usize::from(foot) + usize::from(end));
+        for (story, path) in [
+            (StoryRef::Body, Path::top(0)),
+            (StoryRef::Body, Path(vec![1, 0, 0, 0])),
+            (StoryRef::Part(h), Path::top(0)),
+            (StoryRef::Part(t), Path::top(0)),
+        ] {
+            let got = d.para(story, &path).unwrap();
+            assert_eq!(got.text, p.text);
+            assert_eq!(got.runs.iter().map(|r| r.props.style.as_deref().unwrap()).collect::<Vec<_>>(), expected);
+            assert!(got.runs.iter().all(|r| r.props.italic == Some(true)));
+            assert_eq!(got.objects[1], p.objects[1]);
+            assert_eq!(got.objects[3], p.objects[3], "a missing note stays unchanged");
+            assert_eq!(got.objects[0], reference(f, if foot { NoteKind::Endnote } else { NoteKind::Footnote }));
+            assert_eq!(got.objects[2], reference(e, if end { NoteKind::Footnote } else { NoteKind::Endnote }));
+            assert_eq!(got.objects[4], got.objects[0], "surplus object storage retains the existing conversion");
+        }
+        for (id, flipped, from, to) in [(f, foot, "FootnoteText", "EndnoteText"), (e, end, "EndnoteText", "FootnoteText")] {
+            let got = d.para(StoryRef::Part(id), &Path::top(0)).unwrap();
+            assert_eq!(got.text, before.plain_text(StoryRef::Part(id)));
+            assert_eq!(got.props.style.as_deref(), Some(if flipped { to } else { from }));
+            assert_eq!(got.mark.style, got.props.style);
+        }
+        let mut missing = Paragraph {
+            text: format!("{OBJ}{OBJ}"),
+            objects: vec![reference(f, if foot { NoteKind::Endnote } else { NoteKind::Footnote })],
+            runs: vec![styled(0, "FootnoteReference"), styled(3, "FootnoteReference"), styled(3, "FootnoteReference")],
+            ..Paragraph::new()
+        };
+        missing.runs.push(styled(usize::MAX, "FootnoteReference"));
+        d.body = vec![para_block(missing)];
+        d.convert_notes(true, true);
+        let got = d.para(StoryRef::Body, &Path::top(0)).unwrap();
+        assert_eq!(
+            got.runs.iter().map(|r| r.props.style.as_deref().unwrap()).collect::<Vec<_>>(),
+            ["FootnoteReference", "EndnoteReference", "FootnoteReference", "FootnoteReference"]
+        );
+    }
+}
+
+fn dense(n: usize) -> Document {
+    let mut d = Document::new();
+    let id = d.add_part(PartKind::Footnote, vec![para_block(Paragraph::with_text("Shared original note", CharProps::default()))]);
+    d.body = vec![para_block(Paragraph {
+        text: format!("{}{}", OBJ.to_string().repeat(n), "x".repeat(n)),
+        objects: (0..n).map(|_| reference(id, NoteKind::Footnote)).collect(),
+        runs: (0..n).map(|_| styled(OBJ.len_utf8(), "FootnoteReference")).chain((0..n).map(|_| styled(1, "FootnoteReference"))).collect(),
+        ..Paragraph::new()
+    })];
+    d
+}
+
+// Thread CPU excludes scheduler delays. Missing or nonadvancing counters provide no timing
+// evidence; the semantic assertions still run on those platforms.
+fn cpu_cost(f: impl FnOnce()) -> Option<f64> {
+    let ran = || std::fs::read_to_string("/proc/thread-self/schedstat").ok()?.split_whitespace().next()?.parse::<u64>().ok();
+    let before = ran();
+    f();
+    match (before, ran()) {
+        (Some(a), Some(b)) if b > a => Some((b - a) as f64 * 1e-9),
+        _ => None,
+    }
+}
+
+#[test]
+fn conversion_work_scales_with_reference_and_formatting_runs() {
+    let (small, big) = (dense(2_000), dense(16_000));
+    let convert = |input: &Document| {
+        let mut d = input.clone();
+        assert_eq!(d.convert_notes(true, false), 1);
+        let p = d.para(StoryRef::Body, &Path::top(0)).unwrap();
+        let n = p.objects.len();
+        assert!(p.runs[..n].iter().all(|r| r.props.style.as_deref() == Some("EndnoteReference")));
+        assert!(p.runs[n..].iter().all(|r| r.props.style.as_deref() == Some("FootnoteReference")));
+        std::hint::black_box(d);
+    };
+    convert(&small);
+    convert(&big);
+    let (mut t1, mut t8) = (f64::INFINITY, f64::INFINITY);
+    for _ in 0..3 {
+        let a = cpu_cost(|| (0..8).for_each(|_| convert(&small)));
+        let b = cpu_cost(|| convert(&big));
+        if let (Some(a), Some(b)) = (a, b) {
+            t1 = t1.min(a / 8.0);
+            t8 = t8.min(b);
+        }
+    }
+    if t1.is_finite() && t8.is_finite() {
+        let ratio = t8 / t1;
+        eprintln!("note conversion CPU: small={t1:.6}s big={t8:.6}s ratio={ratio:.2}");
+        assert!(ratio < 24.0, "8x the references and runs cost {ratio:.2}x CPU");
+    }
+}
@@ -3,9 +3,36 @@ use super::parts::PartKind;
 use super::position::Path;
 use super::{InlineObject, Numbering, numbering, para, section, styles};

-/// Words in `s` (tokens separated by whitespace that contain at least one alphanumeric char).
+/// Words in `s`, as Word counts them: tokens separated by whitespace that contain at least one
+/// alphanumeric char, plus each Han ideograph and kana as a word of its own (Chinese and Japanese
+/// are written without spaces, #4547; Korean is spaced, so Hangul counts by tokens).
 pub fn count_words(s: &str) -> usize {
-    s.split(|c: char| c.is_whitespace() || c == para::OBJ).filter(|w| w.chars().any(char::is_alphanumeric)).count()
+    // The half-width voiced sound marks belong to the kana before them, not a word of their own.
+    let word_char = |c: char| c.is_alphanumeric() && !matches!(c, '\u{FF9E}' | '\u{FF9F}');
+    let tokens = s.split(|c: char| c.is_whitespace() || c == para::OBJ || is_cjk_word(c)).filter(|w| w.chars().any(word_char)).count();
+    tokens.saturating_add(s.chars().filter(|c| is_cjk_word(*c)).count())
+}
+
+/// Words in a generated list label: whitespace-separated tokens holding a letter or digit, so a
+/// CJK label such as 第十二章 stays one word (how Word counts those is unverified).
+fn count_label_words(s: &str) -> usize {
+    s.split(char::is_whitespace).filter(|w| w.chars().any(char::is_alphanumeric)).count()
+}
+
+/// A Han ideograph or kana letter (not CJK punctuation), which Word counts as one word.
+fn is_cjk_word(c: char) -> bool {
+    matches!(c,
+        '\u{3005}'..='\u{3007}' // 々 〆 〇
+        | '\u{3031}'..='\u{3035}' | '\u{303B}' // vertical kana repeat marks, 〻
+        | '\u{3040}'..='\u{30FF}' // hiragana, katakana
+        | '\u{31F0}'..='\u{31FF}' // katakana phonetic extensions
+        | '\u{3400}'..='\u{4DBF}' // extension A
+        | '\u{4E00}'..='\u{9FFF}' // unified ideographs
+        | '\u{F900}'..='\u{FAFF}' // compatibility ideographs
+        | '\u{FF66}'..='\u{FF9D}' // half-width katakana
+        | '\u{1B000}'..='\u{1B16F}' // kana supplement and extended
+        | '\u{20000}'..='\u{3FFFF}' // extensions B and later
+    ) && c.is_alphanumeric()
 }

 /// How deep in nested tables [`Document::para_paths`] goes: cells below this are skipped.
@@ -146,7 +173,7 @@ pub(crate) fn story_word_count_of(
                    && let Some((label, def)) = counters.next_label(numbering, n.num, n.level)
                    && !matches!(def.format, section::NumFormat::Bullet | section::NumFormat::None)
                {
-                    total = total.saturating_add(count_words(&label));
+                    total = total.saturating_add(count_label_words(&label));
                }
                total = total.saturating_add(count_words(&p.plain_text()));
            }
@@ -0,0 +1,191 @@
+//! A bytes-only check of a ZIP package's declared entry count before the `zip` crate opens it
+//! (#3660). Every reader of `.docx`, `.odt` and spreadsheet packages calls [`check`] first.
+//!
+//! `zip::ZipArchive::new` reserves room for, and parses, as many central directory headers as the
+//! end record declares before its caller can look at `len()`. A ZIP64 end record can declare
+//! millions of entries for a file of a few hundred megabytes (only 46 bytes each have to fit), and
+//! each parsed entry costs several times that in memory. Here the end records are found the way
+//! `zip` finds them (APPNOTE.TXT §4.3.14 to §4.3.16), and a package declaring more than the
+//! reader's limit is refused before `zip` parses anything. Anything else that is wrong is left for
+//! `zip` to report.
+
+const EOCD: &[u8; 4] = b"PK\x05\x06";
+const EOCD64_LOCATOR: &[u8; 4] = b"PK\x06\x07";
+const EOCD64: &[u8; 4] = b"PK\x06\x06";
+const CENTRAL_HEADER: &[u8; 4] = b"PK\x01\x02";
+
+/// End records looked at, at most. A package has one; a few more can turn up inside stored data.
+const MAX_END_RECORDS: usize = 16;
+
+/// Refuse `bytes` when the end record `zip` would use declares more than `max_entries` entries.
+///
+/// `zip` searches the file backwards for an end of central directory record. A ZIP64 one points
+/// through its locator at the ZIP64 end record, which `zip` looks for from the locator's offset
+/// on: every such record there is checked, and as `zip` may fall back to an earlier end record
+/// when one doesn't parse, the search goes on. A plain one is used when it declares no entries, or
+/// a central directory header lies between its directory offset and itself: it is the last one
+/// looked at.
+pub fn check(bytes: &[u8], max_entries: u64) -> Result<(), String> {
+    let u16_at = |at: usize| bytes.get(at..at.checked_add(2)?).map(|b| u16::from_le_bytes([b[0], b[1]]));
+    let u32_at = |at: usize| bytes.get(at..at.checked_add(4)?).map(|b| u32::from_le_bytes([b[0], b[1], b[2], b[3]]));
+    let u64_at = |at: usize| bytes.get(at..at.checked_add(8)?).and_then(|b| <[u8; 8]>::try_from(b).ok()).map(u64::from_le_bytes);
+    let refuse = |n: u64| -> Result<(), String> {
+        if n > max_entries { Err(format!("the package declares {n} entries, more than {max_entries}")) } else { Ok(()) }
+    };
+    let mut end = bytes.len();
+    let mut seen = 0;
+    while let Some(at) = bytes.get(..end).and_then(|b| b.windows(4).rposition(|w| w == EOCD)) {
+        end = at;
+        seen += 1;
+        if seen > MAX_END_RECORDS {
+            return Err(format!("more than {MAX_END_RECORDS} end of central directory records"));
+        }
+        // `zip` skips a record whose comment runs past the end of the file.
+        let Some(comment) = u16_at(at + 20) else { continue };
+        if at + 22 + usize::from(comment) > bytes.len() {
+            continue;
+        }
+        let (Some(on_disk), Some(total), Some(cd_offset)) = (u16_at(at + 8), u16_at(at + 10), u32_at(at + 16)) else { continue };
+        let zip64 = total == u16::MAX || cd_offset == u32::MAX;
+        if zip64
+            && let Some(locator) = at.checked_sub(20)
+            && bytes.get(locator..locator + 4) == Some(EOCD64_LOCATOR.as_slice())
+        {
+            let (Some(eocd64), Some(disks)) = (u64_at(locator + 8), u32_at(locator + 16)) else { continue };
+            let Some(from) = usize::try_from(eocd64).ok().filter(|&f| f < locator) else { continue };
+            if disks > 1 {
+                continue;
+            }
+            let records = bytes.get(from..locator).unwrap_or_default().windows(4).enumerate().filter(|(_, w)| *w == EOCD64);
+            for (i, _) in records {
+                let p = from + i;
+                refuse(u64_at(p + 24).unwrap_or(0).max(u64_at(p + 32).unwrap_or(0)))?;
+            }
+            continue;
+        }
+        if total == 0 {
+            return Ok(());
+        }
+        let cd = cd_offset as usize;
+        if cd < at && bytes.get(cd..at).is_some_and(|b| b.windows(4).any(|w| w == CENTRAL_HEADER)) {
+            return refuse(u64::from(on_disk.max(total)));
+        }
+    }
+    Ok(())
+}
+
+/// A package of one empty stored file, `a`, whose central directory lists it `entries` times (at
+/// most as many as fit in 64 MiB) under a ZIP64 end record that declares them all: `zip` 3.0.0
+/// parses and keeps every one of them before its caller can count them. Regression input for the
+/// readers' tests: built only for tests, this crate's and (through the `test-support` feature,
+/// which they turn on as a dev-dependency) the readers', never into the app.
+#[cfg(any(test, feature = "test-support"))]
+pub fn zip64_entry_count_sample(entries: u64) -> Vec<u8> {
+    // Local file header (APPNOTE.TXT §4.3.7): version 10, stored, no data, name "a".
+    let mut f = b"PK\x03\x04".to_vec();
+    f.extend_from_slice(&[10, 0, 0, 0, 0, 0, 0, 0, 0x21, 0]); // version, flags, method, time, date
+    f.extend_from_slice(&[0; 12]); // crc, sizes
+    f.extend_from_slice(&[1, 0, 0, 0]); // name and extra lengths
+    f.push(b'a');
+    let cd_at = f.len() as u64;
+    // Its central header (§4.3.12), 47 bytes.
+    let mut header = CENTRAL_HEADER.to_vec();
+    header.extend_from_slice(&[10, 0, 10, 0, 0, 0, 0, 0, 0, 0, 0x21, 0]); // versions, flags, method, time, date
+    header.extend_from_slice(&[0; 12]); // crc, sizes
+    header.extend_from_slice(&[1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]); // name, extra, comment, disk, attributes
+    header.extend_from_slice(&[0; 4]); // local header offset
+    header.push(b'a');
+    let count = entries.min((64 << 20) / header.len() as u64);
+    for _ in 0..count {
+        f.extend_from_slice(&header);
+    }
+    let cd_len = f.len() as u64 - cd_at;
+    let eocd64_at = f.len() as u64;
+    // ZIP64 end of central directory record (§4.3.14), 56 bytes.
+    f.extend_from_slice(EOCD64);
+    f.extend_from_slice(&44u64.to_le_bytes()); // size of the rest of the record
+    f.extend_from_slice(&[45, 0, 45, 0]); // versions
+    f.extend_from_slice(&[0; 8]); // this disk, disk with the central directory
+    f.extend_from_slice(&entries.to_le_bytes()); // entries on this disk
+    f.extend_from_slice(&entries.to_le_bytes()); // entries
+    f.extend_from_slice(&cd_len.to_le_bytes());
+    f.extend_from_slice(&cd_at.to_le_bytes());
+    // Its locator (§4.3.15), 20 bytes.
+    f.extend_from_slice(EOCD64_LOCATOR);
+    f.extend_from_slice(&0u32.to_le_bytes());
+    f.extend_from_slice(&eocd64_at.to_le_bytes());
+    f.extend_from_slice(&1u32.to_le_bytes());
+    // End of central directory record (§4.3.16), 22 bytes, each count and offset "see ZIP64".
+    f.extend_from_slice(EOCD);
+    f.extend_from_slice(&[0; 4]);
+    f.extend_from_slice(&[0xFF; 12]);
+    f.extend_from_slice(&[0; 2]);
+    f
+}
+
+#[cfg(test)]
+mod tests {
+    use super::{CENTRAL_HEADER, EOCD, check, zip64_entry_count_sample};
+
+    /// A plain package's tail: one central header at 0, then an end record declaring `entries`.
+    fn plain(entries: u16, comment: &[u8]) -> Vec<u8> {
+        let mut f = CENTRAL_HEADER.to_vec();
+        f.resize(46, 0);
+        f.extend_from_slice(EOCD);
+        f.extend_from_slice(&[0, 0, 0, 0]);
+        f.extend_from_slice(&entries.to_le_bytes());
+        f.extend_from_slice(&entries.to_le_bytes());
+        f.extend_from_slice(&46u32.to_le_bytes());
+        f.extend_from_slice(&0u32.to_le_bytes());
+        f.extend_from_slice(&(comment.len() as u16).to_le_bytes());
+        f.extend_from_slice(comment);
+        f
+    }
+
+    #[test]
+    fn a_zip64_end_record_declaring_too_many_entries_is_refused() {
+        // #3660: `zip` would reserve and parse them all before the reader's cap.
+        let sample = zip64_entry_count_sample(20_001);
+        assert!(check(&sample, 20_000).is_err_and(|e| e.contains("20001 entries")));
+        assert!(check(&zip64_entry_count_sample(5), 20_000).is_ok());
+        // Junk before the package (a self-extracting stub) doesn't hide it.
+        let mut prefixed = vec![0x55u8; 4096];
+        prefixed.extend_from_slice(&sample);
+        assert!(check(&prefixed, 20_000).is_err());
+    }
+
+    #[test]
+    fn a_plain_end_record_is_checked_as_zip_reads_it() {
+        assert!(check(&plain(3, b""), 20_000).is_ok());
+        assert!(check(&plain(30_000, b"a comment"), 20_000).is_err_and(|e| e.contains("30000 entries")));
+        // A record whose comment runs past the end is not the one `zip` uses.
+        let mut cut = plain(30_000, b"");
+        cut.truncate(cut.len() - 2);
+        cut.extend_from_slice(&500u16.to_le_bytes());
+        assert!(check(&cut, 20_000).is_ok());
+        assert!(check(b"not a package", 20_000).is_ok());
+        assert!(check(b"", 20_000).is_ok());
+    }
+
+    #[test]
+    fn a_fake_end_record_after_the_real_one_does_not_hide_it() {
+        // `zip` skips a last record with no central header before it and uses the one before.
+        let mut f = zip64_entry_count_sample(1_000_000);
+        f.extend_from_slice(EOCD);
+        f.extend_from_slice(&[0, 0, 0, 0]);
+        f.extend_from_slice(&7u16.to_le_bytes());
+        f.extend_from_slice(&7u16.to_le_bytes());
+        f.extend_from_slice(&0u32.to_le_bytes());
+        f.extend_from_slice(&((f.len() - 12) as u32).to_le_bytes());
+        f.extend_from_slice(&0u16.to_le_bytes());
+        assert!(check(&f, 20_000).is_err());
+    }
+
+    #[test]
+    fn many_end_records_are_refused() {
+        // Each declares one entry and has no central header before it, so `zip` would try them all.
+        let record = [0, 0, 0, 0, 1, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0];
+        let f: Vec<u8> = (0..20).flat_map(|_| EOCD.iter().copied().chain(record)).collect();
+        assert!(check(&f, 20_000).is_err_and(|e| e.contains("end of central directory records")));
+    }
+}
@@ -20,7 +20,9 @@ const C_ICO: u16 = 0x2A42; // palette colour
 const C_CR: u16 = 0x6870; // explicit COLORREF
 const C_HPS: u16 = 0x4A43; // half-points
 const C_HPS_POS: u16 = 0x4845; // super/subscript by half-points
-const C_FTC0: u16 = 0x4A4F; // font index
+const C_FTC0: u16 = 0x4A4F; // font index (ASCII)
+const C_FTC1: u16 = 0x4A50; // East Asian font index (sprmCRgFtc1)
+const C_FTC_BI: u16 = 0x4A5E; // complex-script font index (sprmCFtcBi)
 const C_HIGHLIGHT: u16 = 0x2A0C;
 const C_ISTD: u16 = 0x4A30; // character style

@@ -254,6 +256,16 @@ pub(crate) fn apply_char(p: &mut CharProps, prl: &Prl, base: &CharProps, fonts:
                p.font = Some(name.clone());
            }
        }
+        C_FTC1 => {
+            if let Some(name) = u16_of(prl).and_then(|i| fonts.get(i as usize)) {
+                p.font_ea = Some(name.clone());
+            }
+        }
+        C_FTC_BI => {
+            if let Some(name) = u16_of(prl).and_then(|i| fonts.get(i as usize)) {
+                p.font_cs = Some(name.clone());
+            }
+        }
        C_HIGHLIGHT => {
            if let Some(h) = HL.get(prl.operand.first().copied().unwrap_or(0) as usize) {
                p.highlight = Some(*h);
@@ -417,10 +429,15 @@ pub(crate) fn apply_para(p: &mut ParaProps, prl: &Prl) {

 /// Build the model stylesheet: resolve each raw style's chain (base → this) and the ids we
 /// reference from paragraphs.
-pub(crate) fn stylesheet(raw: &[crate::stsh::RawStyle], fonts: &[String]) -> StyleSheet {
+pub(crate) fn stylesheet(raw: &[crate::stsh::RawStyle], fonts: &[String], standard: crate::stsh::StandardFonts) -> StyleSheet {
    let mut sheet = StyleSheet::empty();
-    // Word's base character properties: font index 0 of the table, 10 pt ([MS-DOC] sprmCHps).
-    sheet.default_chr.font = fonts.first().cloned();
+    // Word's base character properties: the stylesheet's standard fonts (Aptos in a Word 365
+    // file, whose font table still starts with Times New Roman, #5066), else font index 0 of the
+    // table; 10 pt ([MS-DOC] sprmCHps).
+    let font = |i: Option<u16>| i.and_then(|i| fonts.get(usize::from(i))).cloned();
+    sheet.default_chr.font = font(standard.ascii).or_else(|| fonts.first().cloned());
+    sheet.default_chr.font_ea = font(standard.east_asian);
+    sheet.default_chr.font_cs = font(standard.bidi);
    if sheet.default_chr.size.is_none() {
        sheet.default_chr.size = Some(10.0);
    }
@@ -233,6 +233,7 @@ pub fn read_with_password(bytes: &[u8], password: Option<&str>) -> Result<Docume
        Some((f, l)) => stsh::parse(&table, f, l)?,
        None => Vec::new(),
    };
+    let standard_fonts = fib.pair(fib::pair::STSHF).map(|(f, l)| stsh::standard_fonts(&table, f, l)).unwrap_or_default();
    let chpx_bins = match fib.pair(fib::pair::PLCF_BTE_CHPX) {
        Some((f, l)) => Bins::parse(&table, f, l)?,
        None => Bins::parse(&[], 0, 0)?,
@@ -247,7 +248,7 @@ pub fn read_with_password(bytes: &[u8], password: Option<&str>) -> Result<Docume
        doc.core = core;
    }
    doc.body.clear();
-    doc.styles = fmt::stylesheet(&raw_styles, &fonts);
+    doc.styles = fmt::stylesheet(&raw_styles, &fonts, standard_fonts);
    doc.numbering = list::parse(&table, &fib, &fonts);
    let sheet: StyleSheet = doc.styles.clone();
    let sects = sections::parse(&word, &table, &fib);
@@ -363,6 +364,11 @@ pub fn read_with_password(bytes: &[u8], password: Option<&str>) -> Result<Docume
    // Sections: each section's properties attach to the paragraph that ends it (its story of
    // header/footer parts included); the section reaching the end of the text is the final one.
    let mut paras = walk(&ctx, 0, fib.ccp.text, &mut pics);
+    // The first paragraph ending at each CP, found once rather than by a scan per section.
+    let mut ending: std::collections::HashMap<u32, usize> = std::collections::HashMap::new();
+    for (i, p) in paras.iter().enumerate() {
+        ending.entry(p.end_cp).or_insert(i);
+    }
    let last = sects.last().map(|s| s.props.clone());
    for (si, sec) in sects.iter().enumerate() {
        let mut props = sec.props.clone();
@@ -373,11 +379,8 @@ pub fn read_with_password(bytes: &[u8], password: Option<&str>) -> Result<Docume
        if is_final {
            continue; // handled below through `last`
        }
-        for p in paras.iter_mut() {
-            if p.end_cp == sec.end_cp {
-                p.para.section = Some(Box::new(props));
-                break;
-            }
+        if let Some(p) = ending.get(&sec.end_cp).and_then(|&i| paras.get_mut(i)) {
+            p.para.section = Some(Box::new(props));
        }
    }
    if let Some(mut l) = last {
@@ -20,6 +20,41 @@ pub(crate) struct RawStyle {
    pub(crate) chpx: Vec<u8>,
 }

+/// The stylesheet's standard fonts, the ones text takes when neither its style nor its own
+/// formatting names a font: font-table indexes of the ASCII, East Asian and other
+/// (non-East-Asian, non-ASCII) fonts (`Stshif.rgftcStandardChpStsh`, [MS-DOC] §2.9.273) and the
+/// complex-script font (`Stshi.ftcBi`, §2.9.272). `None` where the header is too short for one.
+#[derive(Clone, Copy, Debug, Default, PartialEq, Eq)]
+pub(crate) struct StandardFonts {
+    pub(crate) ascii: Option<u16>,
+    pub(crate) east_asian: Option<u16>,
+    pub(crate) other: Option<u16>,
+    pub(crate) bidi: Option<u16>,
+}
+
+/// `StshiLsd.cbLSD`: the size of a latent style's `LSD` ([MS-DOC] `StshiLsd`).
+const LSD_SIZE: u16 = 4;
+
+/// The [`StandardFonts`] in the header (`Stshi`) of the `STSH` at `table[fc..fc+lcb]`: Word 365
+/// writes Aptos there while the font table's first entry is still Times New Roman (#5066).
+pub(crate) fn standard_fonts(table: &[u8], fc: u32, lcb: u32) -> StandardFonts {
+    let Some(stsh) = (fc as usize).checked_add(lcb as usize).and_then(|end| table.get(fc as usize..end)) else { return StandardFonts::default() };
+    let cb_stshi = stsh.get(0..2).map_or(0, |b| u16::from_le_bytes([b[0], b[1]]) as usize);
+    let stshi = stsh.get(2..).map_or(&[][..], |s| s.get(..cb_stshi.min(s.len())).unwrap_or(&[]));
+    // Stshif: cstd, cbSTDBaseInFile, flags, stiMaxWhenSaved, istdMaxFixedWhenSaved,
+    // nVerBuiltInNamesWhenSaved (2 bytes each), then rgftcStandardChpStsh (3 × 2); ftcBi follows.
+    let at = |o: usize| stshi.get(o..o + 2).map(|b| u16::from_le_bytes([b[0], b[1]]));
+    // ftcBi is optional, and the latent style data (`StshiLsd`, whose `cbLSD` MUST be 4) follows
+    // it: a 4 right after it says it is there, a 4 in its place with more data after says it was
+    // left out. A header that ends right after the field (as Word 97's) has it, a 4 included.
+    let bidi = match (at(18), at(20)) {
+        (b, Some(LSD_SIZE) | None) => b,
+        (Some(LSD_SIZE), Some(_)) => None,
+        (b, _) => b,
+    };
+    StandardFonts { ascii: at(12), east_asian: at(14), other: at(16), bidi }
+}
+
 /// Parse the `STSH` at `table[fc..fc+lcb]`.
 pub(crate) fn parse(table: &[u8], fc: u32, lcb: u32) -> Result<Vec<RawStyle>, DocbinError> {
    let fc = fc as usize;
@@ -421,7 +421,17 @@ fn std_bytes_next(stk: u8, istd_base: u16, istd_next: u16, name: &str, papx: &[u

 /// An STSH with the given styles.
 fn stsh_bytes(styles: &[Vec<u8>]) -> Vec<u8> {
-    let stshi = [(styles.len() as u16).to_le_bytes(), 10u16.to_le_bytes()].concat(); // cstd, cbSTDBaseInFile
+    stsh_bytes_with(styles, None)
+}
+
+/// An STSH with the given styles; with `standard`, a full Stshif and ftcBi giving the standard
+/// fonts' indexes (ASCII, East Asian, other, complex script), as Word writes them.
+fn stsh_bytes_with(styles: &[Vec<u8>], standard: Option<[u16; 4]>) -> Vec<u8> {
+    let mut stshi = [(styles.len() as u16).to_le_bytes(), 10u16.to_le_bytes()].concat(); // cstd, cbSTDBaseInFile
+    if let Some(fonts) = standard {
+        stshi.extend_from_slice(&[0u8; 8]); // flags, stiMaxWhenSaved, istdMaxFixedWhenSaved, nVerBuiltInNamesWhenSaved
+        stshi.extend(fonts.iter().flat_map(|f| f.to_le_bytes()));
+    }
    let mut v = (stshi.len() as u16).to_le_bytes().to_vec();
    v.extend_from_slice(&stshi);
    for s in styles {
@@ -532,6 +542,8 @@ struct RichExtra {
    prm: u16,
    alt_fonts: Vec<Option<&'static str>>,
    style_next: Vec<u16>,
+    /// The stylesheet's standard fonts (ASCII, East Asian, other, complex script).
+    standard_fonts: Option<[u16; 4]>,
 }

 fn rich_doc(spec: &RichSpec) -> Vec<u8> {
@@ -571,7 +583,7 @@ fn rich_doc_with(spec: &RichSpec, extra: &RichExtra) -> Vec<u8> {
        .enumerate()
        .map(|(i, s)| std_bytes_next(s.0, s.1, extra.style_next.get(i).copied().unwrap_or(0x0FFF), s.2, &s.3, &s.4))
        .collect();
-    let stsh = stsh_bytes(&styles);
+    let stsh = stsh_bytes_with(&styles, extra.standard_fonts);
    let fonts: Vec<(&str, Option<&str>)> = spec.fonts.iter().enumerate().map(|(i, n)| (*n, extra.alt_fonts.get(i).copied().flatten())).collect();
    let ffn = ffn_bytes_alt(&fonts);
    let clx_at = 0x40;
@@ -654,6 +666,67 @@ fn font_and_size_from_style_and_direct() {
    assert!(p.runs.first().is_some_and(|r| r.props.font.as_deref() == Some("Arial")), "run font: {:?}", p.runs);
 }

+/// #5066: the default font is the stylesheet's standard font (Aptos in a Word 365 file), not
+/// the font table's first entry (still Times New Roman there); the East Asian and complex-script
+/// standard fonts are the defaults for those scripts, and runs name theirs with sprmCRgFtc1 and
+/// sprmCFtcBi.
+#[test]
+fn the_default_font_is_the_stylesheets_standard_font() {
+    let spec = |runs: Vec<(u32, Vec<u8>)>| RichSpec {
+        text: "Hello\r",
+        styles: vec![(1, 0x0FFF, "Normal", Vec::new(), grpprl(&[(0x4A43, &24u16.to_le_bytes())]))],
+        fonts: vec!["Times New Roman", "Symbol", "Arial", "Aptos", "MS Mincho", "Arial Unicode"],
+        chpx_runs: runs,
+        papx_entries: vec![(0, 0, Vec::new())],
+    };
+    let with = |standard: Option<[u16; 4]>, runs| {
+        read(&rich_doc_with(&spec(runs), &RichExtra { standard_fonts: standard, ..Default::default() })).expect("opens")
+    };
+    let doc = with(Some([3, 4, 3, 2]), vec![(0, Vec::new())]);
+    let d = &doc.styles.default_chr;
+    assert_eq!((d.font.as_deref(), d.font_ea.as_deref(), d.font_cs.as_deref()), (Some("Aptos"), Some("MS Mincho"), Some("Arial")));
+    let p = para0(&doc);
+    let resolved = doc.styles.resolve_char(p.props.style.as_deref(), &p.runs[0].props);
+    assert_eq!(resolved.font, "Aptos", "Normal names no font, so the text takes the standard one");
+    // A run's own East Asian and complex-script fonts.
+    let doc = with(Some([3, 4, 3, 2]), vec![(0, grpprl(&[(0x4A50, &5u16.to_le_bytes()), (0x4A5E, &3u16.to_le_bytes())]))]);
+    let run = &para0(&doc).runs[0].props;
+    assert_eq!((run.font_ea.as_deref(), run.font_cs.as_deref()), (Some("Arial Unicode"), Some("Aptos")));
+    // Indexes past the font table, or a header too short to hold them, keep entry 0.
+    for standard in [Some([99, 99, 99, 99]), None] {
+        let doc = with(standard, vec![(0, Vec::new())]);
+        let d = &doc.styles.default_chr;
+        assert_eq!((d.font.as_deref(), d.font_ea.as_deref(), d.font_cs.as_deref()), (Some("Times New Roman"), None, None), "{standard:?}");
+    }
+}
+
+/// #5066: `ftcBi` is optional in the stylesheet header, and the latent style data (`cbLSD`, 4,
+/// then the LSDs) follows it: a header that leaves it out doesn't make `cbLSD` the complex-script
+/// font.
+#[test]
+fn the_complex_script_standard_font_is_read_only_when_present() {
+    let header = |tail: &[u16]| -> Vec<u8> {
+        // cstd, cbSTDBaseInFile, flags, stiMaxWhenSaved, istdMaxFixedWhenSaved,
+        // nVerBuiltInNamesWhenSaved; ASCII, East Asian, other.
+        let words = [&[0u16, 10, 0, 1, 0, 0, 3, 4, 3][..], tail].concat();
+        let stshi: Vec<u8> = words.iter().flat_map(|w| w.to_le_bytes()).collect();
+        [(stshi.len() as u16).to_le_bytes().to_vec(), stshi].concat()
+    };
+    let bidi = |tail: &[u16]| {
+        let b = header(tail);
+        crate::stsh::standard_fonts(&b, 0, b.len() as u32).bidi
+    };
+    assert_eq!(bidi(&[2]), Some(2), "a header that ends with it (Word 97)");
+    assert_eq!(bidi(&[4]), Some(4), "font 4, at the end of the header");
+    assert_eq!(bidi(&[2, 4, 0, 0]), Some(2), "followed by the latent style data");
+    assert_eq!(bidi(&[4, 4, 0, 0]), Some(4), "font 4, followed by the latent style data");
+    assert_eq!(bidi(&[4, 0, 0]), None, "left out: cbLSD is in its place");
+    assert_eq!(bidi(&[]), None, "a header too short for it");
+    let b = header(&[4, 0, 0]);
+    let fonts = crate::stsh::standard_fonts(&b, 0, b.len() as u32);
+    assert_eq!((fonts.ascii, fonts.east_asian, fonts.other), (Some(3), Some(4), Some(3)), "the other fonts are read all the same");
+}
+
 #[test]
 fn paragraph_props_and_heading_style() {
    let spec = RichSpec {
@@ -945,6 +1018,32 @@ fn two_sections_box_the_first() {
    assert!(!doc.last_section.title_page);
 }

+#[test]
+fn sections_ending_off_a_paragraph_mark_attach_nowhere() {
+    // Hostile section ends that miss every paragraph mark are skipped; the one that ends a
+    // paragraph still boxes it. Paragraphs are found by their end, not scanned per section.
+    let mut sections: Vec<(u32, Vec<u8>)> = (1..6).map(|cp| (cp, Vec::new())).collect();
+    sections.push((6, grpprl(&[(0x300A, &[0x01])])));
+    sections.push((12, Vec::new()));
+    let spec = StructSpec {
+        text: "first\rsecond\r",
+        header_stories: vec![],
+        sections,
+        chpx_runs: vec![(0, Vec::new())],
+        papx_entries: vec![(0, 0, Vec::new()), (6, 0, Vec::new())],
+        plf_lst: Vec::new(),
+        plf_lfo: Vec::new(),
+        note_stories: vec![],
+        endnote_stories: vec![],
+        extra_pairs: Vec::new(),
+        data_stream: Vec::new(),
+    };
+    let doc = read(&struct_doc(&spec)).expect("opens");
+    let paras: Vec<_> = doc.body.iter().filter_map(|b| b.as_para()).collect();
+    assert!(paras.first().and_then(|p| p.section.as_ref()).expect("first paragraph boxed").title_page);
+    assert_eq!(paras.iter().filter(|p| p.section.is_some()).count(), 1, "the missing ends attach nowhere");
+}
+
 #[test]
 fn header_story_becomes_part() {
    let spec = StructSpec {
@@ -90,13 +90,16 @@ pub(crate) fn parse(root: &El, seen: &mut Seen, room: usize) -> Sources {
        let tag = child_text(src_el, "Tag");
        let raw_kind = child_text(src_el, "SourceType");
        let kind = crate::write::from_source_type(&raw_kind);
-        let (author, editor) = match src_el.els().find(|e| e.local() == "Author") {
+        let (author, corporate, editor) = match src_el.els().find(|e| e.local() == "Author") {
            Some(a) => {
-                let auth = a.els().find(|e| e.local() == "Author").map(parse_persons).filter(|s| !s.is_empty()).unwrap_or_else(|| parse_persons(a));
+                let role = a.els().find(|e| e.local() == "Author");
+                let auth = role.map(parse_persons).filter(|s| !s.is_empty()).unwrap_or_else(|| parse_persons(a));
+                // Word's Corporate Author: one name, kept whole (`b:Corporate`, #4848).
+                let corporate = role.map(|r| child_text(r, "Corporate").trim().to_string()).unwrap_or_default();
                let ed = a.els().find(|e| e.local() == "Editor").map(parse_persons).unwrap_or_default();
-                (auth, ed)
+                (auth, corporate, ed)
            }
-            None => (String::new(), String::new()),
+            None => (String::new(), String::new(), String::new()),
        };
        let editor = if editor.is_empty() { src_el.els().find(|e| e.local() == "Editor").map(parse_persons).unwrap_or_default() } else { editor };
        let title = child_text(src_el, "Title");
@@ -132,11 +135,12 @@ pub(crate) fn parse(root: &El, seen: &mut Seen, room: usize) -> Sources {
        };

        // Keep sources with some content, once each (by tag, or title and author untagged).
-        if tag.is_empty() && title.is_empty() && author.is_empty() && editor.is_empty() {
+        if tag.is_empty() && title.is_empty() && author.is_empty() && corporate.is_empty() && editor.is_empty() {
            continue;
        }
        let fresh = if tag.is_empty() {
-            seen.untagged.insert((title.clone(), if author.is_empty() { editor.clone() } else { author.clone() }))
+            let who = [&author, &corporate, &editor].into_iter().find(|w| !w.is_empty()).cloned().unwrap_or_default();
+            seen.untagged.insert((title.clone(), who))
        } else {
            seen.tags.insert(tag.clone())
        };
@@ -147,6 +151,7 @@ pub(crate) fn parse(root: &El, seen: &mut Seen, room: usize) -> Sources {
            tag,
            kind,
            author,
+            corporate,
            title,
            year,
            city,
@@ -265,6 +270,25 @@ mod tests {
        assert!(read_sources(br#"<o:Sources xmlns:o="urn:example:other"><o:Source/></o:Sources>"#).is_err(), "an unrelated namespace");
    }

+    /// #4848: a corporate author (Word's Corporate Author box, `b:Corporate`) is read whole, and
+    /// an untagged source with only a corporate author is still kept, once.
+    #[test]
+    fn a_corporate_author_is_read_whole() {
+        let xml = br#"<b:Sources xmlns:b="http://schemas.openxmlformats.org/officeDocument/2006/bibliography">
+  <b:Source><b:Tag>Wor20</b:Tag><b:SourceType>Report</b:SourceType>
+    <b:Author><b:Author><b:Corporate> World Health Organization </b:Corporate></b:Author></b:Author>
+    <b:Title>World report on hearing</b:Title><b:Year>2020</b:Year></b:Source>
+  <b:Source><b:SourceType>Book</b:SourceType>
+    <b:Author><b:Author><b:Corporate>Harbor Guild, Inc.</b:Corporate></b:Author></b:Author></b:Source>
+  <b:Source><b:SourceType>Book</b:SourceType>
+    <b:Author><b:Author><b:Corporate>Harbor Guild, Inc.</b:Corporate></b:Author></b:Author></b:Source>
+</b:Sources>"#;
+        let f = read_sources(xml).unwrap();
+        assert_eq!(f.sources.len(), 2, "{:?}", f.sources);
+        assert_eq!((f.sources[0].corporate.as_str(), f.sources[0].author.as_str()), ("World Health Organization", ""));
+        assert_eq!(f.sources[1].corporate, "Harbor Guild, Inc.", "a comma doesn't split a corporate name");
+    }
+
    /// Word's own 2004/10 bibliography namespace (`Sources.xml` written by scripts and older
    /// builds, the VBA `Source.XML` format) reads as well as OOXML's.
    #[test]
@@ -193,6 +193,25 @@ fn hostile_encryption_info_errors_without_panicking() {
    assert!(decrypt(&fake, Some("pw")).is_err());
 }

+/// The key a real-world Standard-encrypted package derives: Apache POI's test file
+/// `protected_passtika.xlsx` (Apache-2.0 test data), password "tika", written by Excel
+/// itself. The value was computed from [MS-OFFCRYPTO] §2.3.4.7 independently of this code —
+/// the file decrypts to a valid package under it and nothing else opens that file — so real
+/// Word 2007 documents stay pinned, not just spec-derived ones.
+#[test]
+fn standard_key_matches_a_real_world_package() {
+    let salt: [u8; 16] = [0x19, 0xd0, 0xc7, 0xf3, 0x95, 0x28, 0x78, 0x43, 0x6a, 0x49, 0x49, 0xd7, 0xf0, 0xa2, 0xcf, 0x1e];
+    const KEY: &str = "8d4d00143a5f2e4918af7e6e7410d46c";
+    let hex = |b: &[u8]| b.iter().map(|x| format!("{x:02x}")).collect::<String>();
+    assert_eq!(hex(&standard_key(&salt, "tika", 16)), KEY);
+    // A different password or salt gives a different key; the key is exactly the length
+    // asked for, for each AES width.
+    assert_ne!(hex(&standard_key(&salt, "tika2", 16)), KEY);
+    assert_ne!(hex(&standard_key(&[0; 16], "tika", 16)), KEY);
+    assert_eq!(standard_key(&salt, "tika", 24).len(), 24);
+    assert_eq!(standard_key(&salt, "tika", 32).len(), 32);
+}
+
 /// Standard encryption's key derivation (§2.3.4.7) for the password "Password1234_" and the
 /// salt 00 01 … 0F. The expected keys were computed outside WordCraft (Python's hashlib)
 /// following the specification's steps, so the encryptor and decryptor can't share a mistake.
@@ -25,11 +25,11 @@ pub fn read(root: &El) -> Vec<CustomProp> {
        let Some(v) = p.els().next() else { continue };
        let kind = v.local();
        let prop = if SIMPLE.contains(&kind) {
-            CustomProp { name: name.to_string(), kind: kind.to_string(), value: v.text() }
+            CustomProp { name: name.to_string(), kind: kind.to_string(), value: v.text(), link_target: p.attr("linkTarget").map(str::to_string) }
        } else {
            let mut xml = String::new();
            el_xml(v, &mut xml, 0);
-            CustomProp { name: name.to_string(), kind: "raw".into(), value: xml }
+            CustomProp { name: name.to_string(), kind: "raw".into(), value: xml, link_target: p.attr("linkTarget").map(str::to_string) }
        };
        out.push(prop);
    }
@@ -51,7 +51,12 @@ pub fn write(props: &[CustomProp]) -> Vec<u8> {
        if p.kind == "raw" && !raw_is_wellformed(&p.value) {
            continue;
        }
-        w.open("property", &[("fmtid", FMTID), ("pid", &pid.to_string()), ("name", &p.name)]);
+        let pid = pid.to_string();
+        let mut attrs = vec![("fmtid", FMTID), ("pid", &pid), ("name", &p.name)];
+        if let Some(target) = &p.link_target {
+            attrs.push(("linkTarget", target));
+        }
+        w.open("property", &attrs);
        if p.kind == "raw" {
            w.raw(&p.value);
        } else {
@@ -76,7 +76,7 @@ pub fn sniff_xml(bytes: &[u8]) -> XmlKind {

 /// Read a Flat OPC file.
 pub fn read(bytes: &[u8]) -> Result<Document, DocxError> {
-    crate::read::read_opened(&unpack(bytes)?)
+    crate::read::read_opened(&unpack(bytes)?, None)
 }

 /// The data element of the part being read.
@@ -32,7 +32,7 @@ pub use crypt::{
 };
 pub use flat::{XmlKind, sniff_xml, write as write_flat};
 pub use fonts::{EmbeddedFont, embedded_fonts};
-pub use read::read;
+pub use read::{AltChunk, ChunkImporter, ReadOptions, read};
 pub use smart_art::smart_art_items;
 pub use wordml2003_write::write as write_wordml2003;
 pub use write::{write, write_as};
@@ -56,11 +56,19 @@ pub fn read_xml(bytes: &[u8]) -> Result<wordcraft_doc::Document, DocxError> {

 /// The title (`dc:title`) in a package's core properties part (`docProps/core.xml`, ECMA-376
 /// Part 2 §11), trimmed; `None` when the part can't be read or has no title. Only the package's
-/// directory and at most `max_part` bytes of that part are read: for listing templates by name
-/// without reading the whole package.
-pub fn package_title<R: std::io::Read + std::io::Seek>(package: R, max_part: u64) -> Option<String> {
+/// directory and at most `max_part` bytes of that part are inflated: for listing templates by
+/// name without unpacking the whole package. A package over 64 MiB, or one declaring more entries
+/// than `MAX_ENTRIES` (20,000), has none (#3660).
+pub fn package_title<R: std::io::Read>(package: R, max_part: u64) -> Option<String> {
    use std::io::Read;
-    let mut zip = zip::ZipArchive::new(package).ok()?;
+    const MAX_PACKAGE: u64 = 64 << 20;
+    let mut bytes = Vec::new();
+    package.take(MAX_PACKAGE + 1).read_to_end(&mut bytes).ok()?;
+    if bytes.len() as u64 > MAX_PACKAGE {
+        return None;
+    }
+    wordcraft_doc::zip_guard::check(&bytes, package::MAX_ENTRIES as u64).ok()?;
+    let mut zip = zip::ZipArchive::new(std::io::Cursor::new(bytes)).ok()?;
    let part = zip.by_name("docProps/core.xml").ok()?;
    let mut xml = Vec::new();
    part.take(max_part).read_to_end(&mut xml).ok()?;
@@ -84,11 +92,18 @@ pub(crate) const CANVAS_SPIN_EXT: &str = "urn:wordcraft:canvas-xfrm";
 /// `password` first. An encrypted package without a password gives
 /// [`DocxError::PasswordRequired`]; a wrong one, [`DocxError::WrongPassword`].
 pub fn read_with_password(bytes: &[u8], password: Option<&str>) -> Result<wordcraft_doc::Document, DocxError> {
+    read_with(bytes, &ReadOptions { password, ..Default::default() })
+}
+
+/// Read a package with options: the password of an encrypted one ([`read_with_password`]) and
+/// an importer for `w:altChunk` content in formats other than WordprocessingML (see
+/// [`ChunkImporter`]).
+pub fn read_with(bytes: &[u8], opts: &ReadOptions) -> Result<wordcraft_doc::Document, DocxError> {
    if is_encrypted(bytes) {
-        let package = zeroize::Zeroizing::new(decrypt(bytes, password)?);
-        return read::read_package(&package);
+        let package = zeroize::Zeroizing::new(decrypt(bytes, opts.password)?);
+        return read::read_package(&package, opts.chunks);
    }
-    read(bytes)
+    read::read_package(bytes, opts.chunks)
 }

 /// Which kind of WordprocessingML package to write. The main part's content type differs per
@@ -47,6 +47,7 @@ pub mod rt {
    pub const DIAGRAM_COLORS: &str = "http://schemas.openxmlformats.org/officeDocument/2006/relationships/diagramColors";
    pub const CUSTOM_XML: &str = "http://schemas.openxmlformats.org/officeDocument/2006/relationships/customXml";
    pub const GLOSSARY: &str = "http://schemas.openxmlformats.org/officeDocument/2006/relationships/glossaryDocument";
+    pub const AF_CHUNK: &str = "http://schemas.openxmlformats.org/officeDocument/2006/relationships/aFChunk";
 }

 /// Content type of a glossary document part (ECMA-376 Part 1 §11.3.8).
@@ -212,6 +213,8 @@ impl Package {
    }

    pub fn open_limited(bytes: &[u8], max_part: u64, max_total: u64) -> Result<Package, DocxError> {
+        // Before `zip` parses every entry the end record declares (#3660).
+        wordcraft_doc::zip_guard::check(bytes, MAX_ENTRIES as u64).map_err(DocxError::Limit)?;
        let mut zip = zip::ZipArchive::new(Cursor::new(bytes)).map_err(|e| DocxError::Zip(e.to_string()))?;
        if zip.len() > MAX_ENTRIES {
            return Err(DocxError::Limit(format!("{} zip entries", zip.len())));
@@ -252,6 +255,11 @@ impl Package {
        Ok(Package::new(files))
    }

+    /// The bytes of all its parts.
+    pub fn size(&self) -> u64 {
+        self.files.values().map(|f| f.len() as u64).sum()
+    }
+
    /// A package from parts already in memory (a Flat OPC file, a converted document), by part
    /// name without the leading `/`.
    pub fn from_parts(files: BTreeMap<String, Vec<u8>>) -> Package {
@@ -524,6 +532,21 @@ mod tests {
        assert!(folded.iter().all(|w| w.contains("2 zip entries")), "{folded:?}");
    }

+    #[test]
+    fn a_package_declaring_too_many_entries_is_refused_before_zip_reads_them() {
+        // #3660: a ZIP64 end record declaring more than MAX_ENTRIES.
+        let bomb = wordcraft_doc::zip_guard::zip64_entry_count_sample(MAX_ENTRIES as u64 + 1);
+        assert!(matches!(Package::open(&bomb), Err(DocxError::Limit(e)) if e.contains("declares")));
+        assert_eq!(crate::package_title(std::io::Cursor::new(bomb), 1 << 20), None);
+        // A real package still opens, and its title still reads.
+        let z = zip_of(&[(
+            "docProps/core.xml",
+            br#"<cp:coreProperties xmlns:cp="http://schemas.openxmlformats.org/package/2006/metadata/core-properties" xmlns:dc="http://purl.org/dc/elements/1.1/"><dc:title>Plan</dc:title></cp:coreProperties>"#.to_vec(),
+        )]);
+        assert!(Package::open(&z).is_ok());
+        assert_eq!(crate::package_title(std::io::Cursor::new(z), 1 << 20).as_deref(), Some("Plan"));
+    }
+
    #[test]
    fn decompression_bomb_is_rejected() {
        let z = zip_of(&[("word/document.xml", vec![b' '; 2_000_000])]);
@@ -587,7 +610,7 @@ mod tests {
            ("word/media/pic.png", b"\x89PNG picture bytes".to_vec()),
        ]);
        let pkg = Package::open(&z).unwrap();
-        let doc = crate::read::read_opened(&pkg).unwrap();
+        let doc = crate::read::read_opened(&pkg, None).unwrap();
        let held = doc.media.values().next().expect("the picture is read");
        assert!(Arc::ptr_eq(held, pkg.get_shared("word/media/pic.png").unwrap()), "the same bytes, not a copy");
        assert_eq!(pkg.get("/WORD/media/PIC.png"), Some(&b"\x89PNG picture bytes"[..]), "lookups are unchanged");
@@ -1,6 +1,7 @@
 //! DOCX → [`Document`].

 pub(crate) mod chart;
+mod chunk;
 pub(crate) mod diagram;
 mod drawing_color;
 mod embed;
@@ -13,7 +14,7 @@ mod shape_style;
 mod story;
 mod wordart;

-use std::collections::{BTreeMap, HashMap, HashSet};
+use std::collections::{HashMap, HashSet};
 use std::sync::Arc;

 use wordcraft_doc::control::{ControlEvent, ControlKind, control_events, pair_events};
@@ -46,6 +47,9 @@ pub(crate) use meta::PROTECTION_HASH_ATTRS;
 pub(crate) use styles::LOWER_NAMES;
 use toc::{is_toc, toc_control_to_toc, toc_field_to_heading, unstyle_toc_links};

+use chunk::ChunkState;
+pub use chunk::{AltChunk, ChunkImporter, ReadOptions};
+
 /// Most fonts read from a font table, and the longest name (hostile files).
 const MAX_TABLE_FONTS: usize = 2000;
 const MAX_FONT_NAME: usize = 256;
@@ -87,12 +91,12 @@ pub(crate) struct Reader<'p> {
    pub bookmarks: HashMap<String, String>,
    /// Restrict Editing exception ranges (`w:permStart`): the file's id → ours.
    pub perms: HashMap<String, u32>,
+    /// The next permission range id to give out (chunks' ranges take theirs from it too).
+    pub next_perm: u32,
    /// Chart and diagram parts by path, parsed once.
    graphic_parts: HashMap<String, Option<Arc<El>>>,
    /// Charts and diagrams by (kind, part path, width bits, height bits), built once.
    graphics: HashMap<(GraphicKind, String, u32, u32), Arc<Graphic>>,
-    /// Graphic work left before charts and diagrams are left empty (see [`MAX_GRAPHIC_WORK`]).
-    graphic_budget: usize,
    /// Drawing ids connectors are glued to (`a:stCxn`, `a:endCxn`), and whether any shape's id
    /// was kept while reading (those not glued to are dropped at the end).
    pub glued: HashSet<u32>,
@@ -103,6 +107,8 @@ pub(crate) struct Reader<'p> {
    content_types: Option<ContentTypes>,
    /// Parts kept for charts, diagrams and OLE objects (see `embed`).
    embedded: EmbeddedManifest,
+    /// What alternative format chunks may still bring in, and how (see [`chunk`]).
+    chunks: ChunkState<'p>,
    /// Linked text boxes as read: (`wps:txbx/@id` or `wps:linkedTxbx/@id`, `seq` (0 for the box
    /// holding the text), text box part). See [`link_text_boxes`].
    pub txbx_links: Vec<(u32, u32, u32)>,
@@ -125,17 +131,24 @@ pub fn read(bytes: &[u8]) -> Result<Document, DocxError> {
    if crate::is_encrypted(bytes) {
        return crate::read_with_password(bytes, None);
    }
-    read_package(bytes)
+    read_package(bytes, None)
 }

-/// [`read`] for bytes known not to be an encrypted package.
-pub(crate) fn read_package(bytes: &[u8]) -> Result<Document, DocxError> {
-    read_opened(&Package::open(bytes)?)
+/// [`read`] for bytes known not to be an encrypted package; `chunks` imports alternative format
+/// chunks in formats other than WordprocessingML.
+pub(crate) fn read_package(bytes: &[u8], chunks: Option<ChunkImporter>) -> Result<Document, DocxError> {
+    read_opened(&Package::open(bytes)?, chunks)
 }

 /// Read a package whose parts are already unpacked (from a zip, a Flat OPC file or a converted
 /// Word 2003 XML document).
-pub(crate) fn read_opened(pkg: &Package) -> Result<Document, DocxError> {
+pub(crate) fn read_opened(pkg: &Package, chunks: Option<ChunkImporter>) -> Result<Document, DocxError> {
+    read_opened_in(pkg, ChunkState::new(chunks)).map(|(doc, ..)| doc)
+}
+
+/// [`read_opened`] with what chunks may still bring in; also gives the chunks, chunk bytes and
+/// graphic work left of that.
+fn read_opened_in(pkg: &Package, chunks: ChunkState) -> Result<(Document, usize, u64, usize), DocxError> {
    let root_rels = pkg.rels("");
    let main = root_rels.by_type(rt::OFFICE_DOC).filter(|r| !r.external).map(|r| r.target.clone()).unwrap_or_else(|| "word/document.xml".to_string());
    let Some(root) = pkg.xml_strict(&main)? else {
@@ -164,9 +177,9 @@ pub(crate) fn read_opened(pkg: &Package) -> Result<Document, DocxError> {
        comments_ended: HashSet::new(),
        bookmarks: HashMap::new(),
        perms: HashMap::new(),
+        next_perm: 0,
        graphic_parts: HashMap::new(),
        graphics: HashMap::new(),
-        graphic_budget: MAX_GRAPHIC_WORK,
        glued: HashSet::new(),
        shape_ids: false,
        main: main.clone(),
@@ -175,6 +188,7 @@ pub(crate) fn read_opened(pkg: &Package) -> Result<Document, DocxError> {
        txbx_links: Vec::new(),
        theme_fills: Default::default(),
        group_fill: None,
+        chunks,
    };
    r.pc.major_font = r.doc.settings.major_font.clone();
    r.pc.minor_font = r.doc.settings.minor_font.clone();
@@ -210,18 +224,20 @@ pub(crate) fn read_opened(pkg: &Package) -> Result<Document, DocxError> {
    if let Some(p) = part(rt::SETTINGS) {
        lenient("settings", r.read_settings(&p));
    }
-    if let Some(p) = part(rt::FOOTNOTES) {
-        lenient("footnotes", r.read_notes(&p, true));
-    }
-    if let Some(p) = part(rt::ENDNOTES) {
-        lenient("endnotes", r.read_notes(&p, false));
-    }
+    // Comments before notes: a comment range inside a footnote or endnote resolves its id against
+    // the comments already read, and was dropped when the notes came first.
    if let Some(p) = part(rt::COMMENTS) {
        let ex = part(rt::COMMENTS_EX);
        let ids = part(rt::COMMENTS_IDS);
        let cex = part(rt::COMMENTS_EXTENSIBLE);
        lenient("comments", r.read_comments(&p, ex.as_deref(), ids.as_deref(), cex.as_deref()));
    }
+    if let Some(p) = part(rt::FOOTNOTES) {
+        lenient("footnotes", r.read_notes(&p, true));
+    }
+    if let Some(p) = part(rt::ENDNOTES) {
+        lenient("endnotes", r.read_notes(&p, false));
+    }
    // Bibliography sources live in a custom XML data store (`b:Sources`), related from the
    // package root or the main part; Word's own files sometimes leave the relationship out, so
    // the conventional `customXml/itemN.xml` names are tried too. Each part is read at most once.
@@ -265,7 +281,7 @@ pub(crate) fn read_opened(pkg: &Package) -> Result<Document, DocxError> {
    if let Some(body) = root.child("w:body") {
        let mut sc = StoryCtx::default();
        let mut blocks = Blocks::new();
-        r.read_blocks(&mut sc, body, &rels, &mut blocks, 0);
+        r.read_blocks(&mut sc, body, &rels, &mut blocks, r.chunks.depth);
        r.flush_pending(&mut sc, &mut blocks);
        r.doc.body = blocks;
        unstyle_toc_links(&mut r.doc);
@@ -319,9 +335,10 @@ pub(crate) fn read_opened(pkg: &Package) -> Result<Document, DocxError> {
    if r.shape_ids {
        keep_glued_ids(&mut r.doc, &r.glued);
    }
+    let (left, bytes, graphic) = (r.chunks.left, r.chunks.bytes, r.chunks.graphic);
    let mut doc = r.doc;
    doc.ensure_nonempty();
-    Ok(doc)
+    Ok((doc, left, bytes, graphic))
 }

 /// Most move ranges open at once, and most move names tracked, per file.
@@ -0,0 +1,187 @@
+//! `w:altChunk` (ECMA-376 §17.17.2.1): content kept in another format (HTML, MHT, RTF, plain
+//! text, another WordprocessingML document) that Word brings into the document where the chunk
+//! stands when it opens the file. A nested WordprocessingML package is read here; other formats
+//! go to the caller's [`ChunkImporter`] (the format crates sit beside this one), and without one
+//! the chunk is left out.
+
+use std::sync::Arc;
+
+use wordcraft_doc::{Block, Blocks, Document};
+
+use super::story::StoryCtx;
+use super::{Reader, part_of};
+use crate::package::{ContentTypes, MAX_PART, MAX_TOTAL, Package, Rels, rt};
+use crate::xml::El;
+
+/// Most chunks brought in from one file (nested documents' chunks included).
+pub(crate) const MAX_CHUNKS: usize = 256;
+/// Deepest a WordprocessingML chunk may nest in another.
+pub(crate) const MAX_CHUNK_NESTING: u8 = 4;
+
+/// An alternative format chunk's content, as a [`ChunkImporter`] gets it.
+pub struct AltChunk<'a> {
+    /// The part's content type (`application/xhtml+xml`, `message/rfc822`, `application/rtf`,
+    /// `text/plain`…), empty when the package doesn't give one.
+    pub content_type: &'a str,
+    /// The part's name (`word/afchunk.mht`): its extension tells the format when the content type
+    /// doesn't.
+    pub part: &'a str,
+    pub bytes: &'a [u8],
+}
+
+/// Turns a chunk the docx reader can't read itself into a document whose body takes the chunk's
+/// place; `None` leaves the chunk out.
+pub type ChunkImporter<'a> = &'a dyn Fn(&AltChunk) -> Option<Document>;
+
+/// How [`crate::read_with`] reads a package.
+#[derive(Clone, Copy, Default)]
+pub struct ReadOptions<'a> {
+    /// The password of an encrypted package.
+    pub password: Option<&'a str>,
+    /// Imports `w:altChunk` content in formats other than WordprocessingML.
+    pub chunks: Option<ChunkImporter<'a>>,
+}
+
+impl Reader<'_> {
+    /// Bring the chunk `e` names into `out` where it stands (`depth`: of the XML around it).
+    pub(crate) fn read_alt_chunk(&mut self, sc: &mut StoryCtx, e: &El, rels: &Rels, out: &mut Blocks, depth: usize) {
+        let Some(part) = e.attr("r:id").and_then(|id| part_of(rels, id, rt::AF_CHUNK)) else { return };
+        let pkg = self.pkg;
+        let Some(bytes) = pkg.get(&part) else {
+            log::warn!("docx: alternative format chunk {part} is missing");
+            return;
+        };
+        // Every chunk's bytes count against one budget for the whole file, however often the same
+        // part is named and however deep chunks nest.
+        if self.chunks.left == 0 || bytes.len() as u64 > self.chunks.bytes {
+            log::warn!("docx: more than {MAX_CHUNKS} alternative format chunks or {MAX_TOTAL} bytes of them; the rest are left out");
+            return;
+        }
+        self.chunks.left -= 1;
+        self.chunks.bytes -= bytes.len() as u64;
+        let ct = self.content_types.get_or_insert_with(|| ContentTypes::read(pkg)).of(&part).unwrap_or("").to_string();
+        let chunk = AltChunk { content_type: &ct, part: &part, bytes };
+        // A WordprocessingML chunk is a package; one that isn't Word's fails to read (logged).
+        let is_docx = bytes.starts_with(b"PK\x03\x04");
+        let doc = if is_docx { self.read_nested(bytes, depth) } else { self.chunks.import.and_then(|f| f(&chunk)) };
+        let Some(mut doc) = doc else {
+            log::warn!("docx: alternative format chunk {part} ({ct}) is in a format WordCraft can't bring in");
+            return;
+        };
+        // The chunk flows in the section it stands in; its own section breaks don't come along.
+        for b in &mut doc.body {
+            if let Block::Para(p) = &**b
+                && p.section.is_some()
+                && let Block::Para(p) = Arc::make_mut(b)
+            {
+                p.section = None;
+            }
+        }
+        // `w:matchSrc`: a Word document's content keeps its own styles (other formats' formatting
+        // is their own already).
+        let keep = is_docx && e.child("w:altChunkPr").and_then(|p| p.child("w:matchSrc")).is_some_and(crate::units::on_off);
+        let mut blocks = self.doc.adopt_blocks(doc, keep, &mut self.next_perm);
+        // Bookmarks and comment marks read before the chunk stay before it.
+        self.flush_pending_before(sc, out, &mut blocks);
+        out.extend(blocks.into_iter().map(Arc::new));
+    }
+
+    /// A WordprocessingML chunk: its document, read with the same importer and what is left of
+    /// the budgets, its XML depth counting on from `depth`.
+    fn read_nested(&mut self, bytes: &[u8], depth: usize) -> Option<Document> {
+        if self.chunks.nesting >= MAX_CHUNK_NESTING {
+            log::warn!("docx: alternative format chunks nest deeper than {MAX_CHUNK_NESTING}; the inner ones are left out");
+            return None;
+        }
+        let pkg =
+            Package::open_limited(bytes, MAX_PART, self.chunks.bytes).map_err(|e| log::warn!("docx: unreadable nested document chunk: {e}")).ok()?;
+        self.chunks.bytes = self.chunks.bytes.saturating_sub(pkg.size());
+        let state = ChunkState { nesting: self.chunks.nesting + 1, depth: depth + 1, ..self.chunks };
+        let (doc, left, bytes, graphic) =
+            super::read_opened_in(&pkg, state).map_err(|e| log::warn!("docx: unreadable nested document chunk: {e}")).ok()?;
+        self.chunks.left = left;
+        self.chunks.bytes = bytes;
+        self.chunks.graphic = graphic;
+        Some(doc)
+    }
+}
+
+/// What a reader may still bring in from chunks.
+#[derive(Clone, Copy)]
+pub(crate) struct ChunkState<'a> {
+    /// Chunks left in the file's budget ([`MAX_CHUNKS`]).
+    pub left: usize,
+    /// Chunk bytes (nested packages unpacked) left in the file's budget.
+    pub bytes: u64,
+    /// Graphic work left in the file's budget ([`super::MAX_GRAPHIC_WORK`]): nested documents'
+    /// charts and diagrams count against it too.
+    pub graphic: usize,
+    /// How deep in nested WordprocessingML chunks this reader is.
+    pub nesting: u8,
+    /// The XML depth its stories start at (a nested document's: that of the chunk naming it).
+    pub depth: usize,
+    pub import: Option<ChunkImporter<'a>>,
+}
+
+impl<'a> ChunkState<'a> {
+    pub fn new(import: Option<ChunkImporter<'a>>) -> Self {
+        ChunkState { left: MAX_CHUNKS, bytes: MAX_TOTAL, graphic: super::MAX_GRAPHIC_WORK, nesting: 0, depth: 0, import }
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use std::io::Write;
+
+    use wordcraft_doc::{Block, Document, InlineObject};
+
+    use super::ChunkState;
+    use crate::package::Package;
+
+    /// A package whose body is `body`, with the document relationship `rel` (id, type, target) to
+    /// the part `(name, bytes)`.
+    fn package(body: &str, (id, ty, target): (&str, &str, &str), (name, bytes): (&str, &[u8])) -> Vec<u8> {
+        let ns = r#"xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main" xmlns:r="http://schemas.openxmlformats.org/officeDocument/2006/relationships" xmlns:wp="http://schemas.openxmlformats.org/drawingml/2006/wordprocessingDrawing" xmlns:a="http://schemas.openxmlformats.org/drawingml/2006/main""#;
+        let rels =
+            |inner: &str| format!(r#"<Relationships xmlns="http://schemas.openxmlformats.org/package/2006/relationships">{inner}</Relationships>"#);
+        let rel = |id: &str, ty: &str, target: &str| {
+            format!(r#"<Relationship Id="{id}" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/{ty}" Target="{target}"/>"#)
+        };
+        let files: [(&str, Vec<u8>); 4] = [
+            ("_rels/.rels", rels(&rel("rId1", "officeDocument", "word/document.xml")).into_bytes()),
+            ("word/document.xml", format!(r#"<w:document {ns}><w:body>{body}</w:body></w:document>"#).into_bytes()),
+            ("word/_rels/document.xml.rels", rels(&rel(id, ty, target)).into_bytes()),
+            (name, bytes.to_vec()),
+        ];
+        let mut zw = zip::ZipWriter::new(std::io::Cursor::new(Vec::new()));
+        for (name, bytes) in files {
+            zw.start_file(name, zip::write::SimpleFileOptions::default()).unwrap();
+            zw.write_all(&bytes).unwrap();
+        }
+        zw.finish().unwrap().into_inner()
+    }
+
+    /// Whether the body's first paragraph's chart is drawn.
+    fn drawn(d: &Document) -> bool {
+        let Some(Block::Para(p)) = d.body.first().map(|b| &**b) else { panic!("no paragraph") };
+        p.objects.iter().any(|o| matches!(o, InlineObject::Graphic { graphic, .. } if !graphic.items.is_empty()))
+    }
+
+    #[test]
+    fn a_nested_documents_charts_count_against_the_files_graphic_budget() {
+        let chart = r#"<c:chartSpace xmlns:c="http://schemas.openxmlformats.org/drawingml/2006/chart"><c:chart><c:plotArea><c:barChart><c:ser><c:val><c:numLit><c:ptCount val="2"/><c:pt idx="0"><c:v>1</c:v></c:pt><c:pt idx="1"><c:v>2</c:v></c:pt></c:numLit></c:val></c:ser></c:barChart></c:plotArea></c:chart></c:chartSpace>"#;
+        let drawing = r#"<w:p><w:r><w:drawing><wp:inline><wp:extent cx="2743200" cy="1828800"/><wp:docPr id="5" name="G"/><a:graphic><a:graphicData uri="http://schemas.openxmlformats.org/drawingml/2006/chart"><c:chart xmlns:c="http://schemas.openxmlformats.org/drawingml/2006/chart" r:id="rIdChart"/></a:graphicData></a:graphic></wp:inline></w:drawing></w:r></w:p>"#;
+        let inner = package(drawing, ("rIdChart", "chart", "charts/chart1.xml"), ("word/charts/chart1.xml", chart.as_bytes()));
+        let outer = package(r#"<w:altChunk r:id="rIdC"/>"#, ("rIdC", "aFChunk", "afchunk.docx"), ("word/afchunk.docx", &inner));
+        let pkg = Package::open(&outer).unwrap();
+        let read = |graphic| {
+            let (d, .., left) = super::super::read_opened_in(&pkg, ChunkState { graphic, ..ChunkState::new(None) }).unwrap();
+            (drawn(&d), left)
+        };
+        let (shown, left) = read(super::super::MAX_GRAPHIC_WORK);
+        assert!(shown);
+        assert!(left < super::super::MAX_GRAPHIC_WORK, "the nested chart's work is the file's");
+        // With the file's budget spent, the nested document doesn't get one of its own.
+        assert_eq!(read(0), (false, 0));
+    }
+}
@@ -1,6 +1,6 @@
 use super::{
-    Arc, BTreeMap, Blocks, Comment, DocxError, El, HashMap, HashSet, MAX_PARTS, MAX_SOURCES, MAX_TEMPLATE_PATH, NoteKind, NumFormat, Paragraph,
-    PartKind, Reader, Rels, Seen, StoryCtx, Zoom, ZoomFit, int, math, on_off, para_block, props, tw, u32_of,
+    Arc, Blocks, Comment, DocxError, El, HashMap, MAX_PARTS, MAX_SOURCES, MAX_TEMPLATE_PATH, NoteKind, NumFormat, Paragraph, PartKind, Reader, Rels,
+    Seen, StoryCtx, Zoom, ZoomFit, int, math, on_off, para_block, props, tw, u32_of,
 };

 impl Reader<'_> {
@@ -120,7 +120,7 @@ impl Reader<'_> {
            let mut sc = StoryCtx::default();
            let mut blocks = Blocks::new();
            self.current_note = Some((kind, id));
-            self.read_blocks(&mut sc, n, &rels, &mut blocks, 0);
+            self.read_blocks(&mut sc, n, &rels, &mut blocks, self.chunks.depth);
            self.flush_pending(&mut sc, &mut blocks);
            self.current_note = None;
            if let Some(p) = self.doc.parts.get_mut(&id)
@@ -152,7 +152,7 @@ impl Reader<'_> {
        let mut sc = StoryCtx::default();
        let mut blocks = Blocks::new();
        self.in_note_sep = true;
-        self.read_blocks(&mut sc, n, rels, &mut blocks, 0);
+        self.read_blocks(&mut sc, n, rels, &mut blocks, self.chunks.depth);
        self.flush_pending(&mut sc, &mut blocks);
        self.in_note_sep = false;
        if blocks.is_empty() {
@@ -188,11 +188,7 @@ impl Reader<'_> {
        let rels = self.pkg.rels(path);
        let mut by_para: HashMap<String, u32> = HashMap::new();
        let mut next_id = 0u32;
-        let mut entries: BTreeMap<u32, Comment> = BTreeMap::new();
-        // Ids given before this part, looked up rather than scanned for every generated id: a
-        // scan per comment made many non-numeric ids quadratic (#3692). Ids given here are in
-        // `entries`.
-        let given: HashSet<u32> = self.comment_map.values().copied().collect();
+        // Straight into the document, beside the comments chunks in notes brought in.
        for c in root.children("w:comment") {
            if self.doc.parts.len() >= MAX_PARTS {
                break;
@@ -202,23 +198,26 @@ impl Reader<'_> {
                continue;
            }
            let id = match file_id.parse::<u32>() {
-                Ok(v) if !entries.contains_key(&v) => v,
+                Ok(v) if !self.doc.comments.contains_key(&v) => v,
                _ => {
-                    while entries.contains_key(&next_id) || given.contains(&next_id) {
+                    // Every id handed out so far is a key of `doc.comments` (inserted below).
+                    while self.doc.comments.contains_key(&next_id) {
                        next_id += 1;
                    }
                    next_id
                }
            };
+            // Taken before its text is read: a chunk there brings comments of its own.
+            self.doc.comments.insert(id, Comment::default());
            let mut sc = StoryCtx::default();
            let mut blocks = Blocks::new();
-            self.read_blocks(&mut sc, c, &rels, &mut blocks, 0);
+            self.read_blocks(&mut sc, c, &rels, &mut blocks, self.chunks.depth);
            self.flush_pending(&mut sc, &mut blocks);
            let part = self.doc.add_part(PartKind::Comment, blocks);
            if let Some(pid) = c.children("w:p").last().and_then(|p| p.attr("w14:paraId")) {
                by_para.insert(pid.to_string(), id);
            }
-            entries.insert(
+            self.doc.comments.insert(
                id,
                Comment {
                    author: c.attr("w:author").unwrap_or("").to_string(),
@@ -239,7 +238,7 @@ impl Reader<'_> {
                let Some(cid) = e.attr("w15:paraId").and_then(|p| by_para.get(p)).copied() else { continue };
                let parent = e.attr("w15:paraIdParent").and_then(|p| by_para.get(p)).copied().filter(|p| *p != cid);
                let done = e.attr("w15:done").is_some_and(|v| v == "1" || v == "true");
-                if let Some(c) = entries.get_mut(&cid) {
+                if let Some(c) = self.doc.comments.get_mut(&cid) {
                    c.parent = parent;
                    c.resolved = done;
                }
@@ -258,7 +257,7 @@ impl Reader<'_> {
            for e in x.els().filter(|e| e.local() == "commentId") {
                let Some(cid) = local(e, "paraId").and_then(|p| by_para.get(&p).copied()) else { continue };
                let Some(durable) = local(e, "durableId").filter(|d| crate::write::durable_id_ok(d)) else { continue };
-                if let Some(c) = entries.get_mut(&cid) {
+                if let Some(c) = self.doc.comments.get_mut(&cid) {
                    c.durable_id = Some(durable.to_ascii_uppercase());
                    by_durable.insert(durable.to_ascii_uppercase(), cid);
                }
@@ -270,12 +269,11 @@ impl Reader<'_> {
            for e in x.els().filter(|e| e.local() == "commentExtensible") {
                let Some(cid) = local(e, "durableId").and_then(|d| by_durable.get(&d.to_ascii_uppercase()).copied()) else { continue };
                let date = local(e, "dateUtc").filter(|d| d.len() <= 40 && d.chars().all(|c| c.is_ascii_alphanumeric() || ":-.+".contains(c)));
-                if let (Some(c), Some(date)) = (entries.get_mut(&cid), date) {
+                if let (Some(c), Some(date)) = (self.doc.comments.get_mut(&cid), date) {
                    c.date_utc = Some(date);
                }
            }
        }
-        self.doc.comments = entries;
        Ok(())
    }

@@ -144,7 +144,7 @@ impl Reader<'_> {
        sc.in_hf = true;
        let mut blocks = Blocks::new();
        self.hf_depth += 1;
-        self.read_blocks(&mut sc, &root, &rels, &mut blocks, 0);
+        self.read_blocks(&mut sc, &root, &rels, &mut blocks, self.chunks.depth);
        self.hf_depth = self.hf_depth.saturating_sub(1);
        self.flush_pending(&mut sc, &mut blocks);
        if let Some(p) = self.doc.parts.get_mut(&id)
@@ -23,8 +23,8 @@ fn text_frame(k: &El) -> wordcraft_doc::props::TextFrame {
    let word = |name: &str, allowed: &[&str], default: &str| k.attr(name).filter(|v| allowed.contains(v)).unwrap_or(default).to_string();
    let align = |name: &str, allowed: &[&str]| k.attr(name).filter(|v| allowed.contains(v)).map(str::to_string);
    wordcraft_doc::props::TextFrame {
-        w: len("w:w").filter(|v| *v > 0.0),
-        h: len("w:h").map(f32::abs).filter(|v| *v > 0.0),
+        w: len("w:w").filter(|v| *v >= 0.0),
+        h: len("w:h").map(f32::abs),
        h_exact: k.attr("w:hRule") == Some("exact"),
        x: len("w:x").unwrap_or(0.0),
        y: len("w:y").unwrap_or(0.0),
@@ -258,6 +258,8 @@ impl PropCtx {
                "w:imprint" => c.engrave = Some(on_off(k)),
                "w:noProof" => c.no_proof = Some(on_off(k)),
                "w:vanish" => c.hidden = Some(on_off(k)),
+                "w:webHidden" => c.web_hidden = Some(on_off(k)),
+                "w:snapToGrid" => c.snap_to_grid = Some(on_off(k)),
                "w:rtl" => c.rtl = Some(on_off(k)),
                "w:color" => {
                    c.color = match (self.theme_color(k, "w:themeColor", "w:themeTint", "w:themeShade"), k.attr("w:val")) {
@@ -166,9 +166,9 @@ fn children_of_choice(ac: &El) -> Option<&El> {
    ac.children("mc:Choice").find(|c| ok(c)).or_else(|| ac.child("mc:Fallback")).or_else(|| ac.child("mc:Choice"))
 }

-/// Gather `name` children (rows, cells), looking through `w:sdt`/`w:customXml` wrappers; each
-/// with the content controls that open before it and how many close after it. `pending` holds
-/// controls opened but not yet given to an element.
+/// Gather `name` children (rows, cells), looking through content controls, custom XML and the
+/// selected alternate-content branch; each with the content controls that open before it and how
+/// many close after it. `pending` holds controls opened but not yet given to an element.
 fn collect<'a>(e: &'a El, name: &str, out: &mut Vec<(&'a El, ControlWrap)>, pending: &mut Vec<ContentControl>, depth: usize) {
    if depth > 8 {
        return;
@@ -194,6 +194,10 @@ fn collect<'a>(e: &'a El, name: &str, out: &mut Vec<(&'a El, ControlWrap)>, pend
            }
        } else if k.name == "w:customXml" {
            collect(k, name, out, pending, depth + 1);
+        } else if k.name == "mc:AlternateContent"
+            && let Some(branch) = children_of_choice(k)
+        {
+            collect(branch, name, out, pending, depth + 1);
        }
    }
 }
@@ -51,6 +51,7 @@ impl Reader<'_> {
                    }
                }
                "w:sdt" => self.read_block_sdt(sc, e, rels, out, depth),
+                "w:altChunk" => self.read_alt_chunk(sc, e, rels, out, depth),
                "w:customXml" | "w:smartTag" | "w:ins" | "w:moveTo" => self.read_blocks(sc, e, rels, out, depth + 1),
                // Math is allowed straight in a story (EG_BlockLevelElts takes EG_RunLevelElements,
                // which takes EG_MathContent): it gets a paragraph of its own (#1273).
@@ -135,6 +136,21 @@ impl Reader<'_> {
        sc.pending.clear();
    }

+    /// Markers read before content placed whole (a chunk's `next`) stay before it: at the end of
+    /// the paragraph before, or after a table or with none, at the start of the content's first
+    /// paragraph, as a paragraph read there would take them (with a table first, the next
+    /// paragraph read takes them).
+    pub fn flush_pending_before(&mut self, sc: &mut StoryCtx, out: &mut Blocks, next: &mut [Block]) {
+        if out.last().is_some_and(|b| matches!(**b, Block::Para(_))) {
+            return self.flush_pending(sc, out);
+        }
+        if let Some(Block::Para(p)) = next.first_mut() {
+            for o in sc.pending.drain(..).rev() {
+                let _ = p.insert_object(0, o, &CharProps::default());
+            }
+        }
+    }
+
    pub(super) fn marker(&mut self, e: &El) -> Option<InlineObject> {
        let id = e.attr("w:id").map(str::trim).unwrap_or("").to_string();
        match e.name.as_str() {
@@ -161,8 +177,15 @@ impl Reader<'_> {
                if self.perms.len() >= 100_000 {
                    return None;
                }
-                let n = self.perms.len() as u32;
-                let id = *self.perms.entry(id).or_insert(n);
+                let id = match self.perms.get(&id) {
+                    Some(n) => *n,
+                    None => {
+                        let n = self.next_perm;
+                        self.next_perm = n.saturating_add(1);
+                        self.perms.insert(id, n);
+                        n
+                    }
+                };
                let text = |a: &str| e.attr(a).filter(|v| v.len() <= 256).unwrap_or("").to_string();
                let (group, editor) = (text("w:edGrp"), text("w:ed"));
                if group.is_empty() && editor.is_empty() {
@@ -218,8 +218,8 @@ impl Reader<'_> {
        if let Some(g) = self.graphics.get(&key) {
            return g.clone();
        }
-        let items = if self.graphic_budget == 0 { Vec::new() } else { self.graphic_items(kind, &key.1, w, h) };
-        self.graphic_budget = self.graphic_budget.saturating_sub(graphic_work(&items));
+        let items = if self.chunks.graphic == 0 { Vec::new() } else { self.graphic_items(kind, &key.1, w, h) };
+        self.chunks.graphic = self.chunks.graphic.saturating_sub(graphic_work(&items));
        // A chart or SmartArt that is exactly what WordCraft writes for its model can be edited
        // (and is written from the model); any other stays as it was read.
        let chart = match kind {
@@ -499,10 +499,26 @@ impl Reader<'_> {
                .and_then(|g| preset_adj(g, "adj"))
                .and_then(|v| u32::try_from(v.clamp(0, i64::from(wordcraft_doc::connector::MAX_CORNER))).ok());
        }
-        // Arrowheads: any end type but `none` (ECMA-376 §20.1.10.33) is drawn as a triangle.
-        let arrow = |tag: &str| ln.and_then(|l| l.child(tag)).and_then(|e| e.attr("type")).is_some_and(|t| t != "none");
-        extra.arrow_start = arrow("a:headEnd");
-        extra.arrow_end = arrow("a:tailEnd");
+        // Arrowheads: any end type but `none` (ECMA-376 §20.1.10.33) is drawn as a triangle of its
+        // width and length.
+        let arrow = |tag: &str| {
+            let e = ln.and_then(|l| l.child(tag))?;
+            let kind = e.attr("type").filter(|t| *t != "none")?;
+            let size = |name: &str| wordcraft_doc::connector::ArrowSize::from_ooxml(e.attr(name).unwrap_or("med"));
+            Some(wordcraft_doc::connector::ArrowStyle {
+                kind: wordcraft_doc::connector::ArrowKind::from_ooxml(kind),
+                width: size("w"),
+                length: size("len"),
+            })
+        };
+        if let Some(style) = arrow("a:headEnd") {
+            extra.arrow_start = true;
+            extra.start_style = style;
+        }
+        if let Some(style) = arrow("a:tailEnd") {
+            extra.arrow_end = true;
+            extra.end_style = style;
+        }
        // A connector's glued ends (ECMA-376 §20.1.2.2.36, §20.1.2.2.13).
        if let Some(cn) = wsp.child("wps:cNvCnPr") {
            let end = |tag: &str| {
@@ -540,7 +556,7 @@ impl Reader<'_> {
        let mut blocks = Blocks::new();
        // Shapes in the text aren't members of a group the box may be in.
        let group = self.group_fill.take();
-        self.read_blocks(&mut inner, content, rels, &mut blocks, 0);
+        self.read_blocks(&mut inner, content, rels, &mut blocks, self.chunks.depth);
        self.group_fill = group;
        self.flush_pending(&mut inner, &mut blocks);
        self.doc.add_part(PartKind::TextBox, blocks)
@@ -295,11 +295,41 @@ impl Reader<'_> {
        }
        let kind = kind?;
        let mut extra = ShapeExtra { cap, ..Default::default() };
+        // A horizontal rule (`o:hr`, a pasted `<hr>`): across `o:hrpct` tenths of a percent of its
+        // line, or its own width (`o:hrpct="0"`); a width of 0 with no percentage is the whole
+        // line. `o:hralign` places a shorter one (Word, measured: 50 % centred, left, right).
+        // Only a rule in the text, shown: a positioned or hidden one stays a plain shape, which
+        // keeps its placement and visibility when saved.
+        if attr("o:hr").is_some_and(|v| matches!(v.trim(), "t" | "true" | "1")) && float.wrap == Wrap::Inline && !float.hidden {
+            let tenths = attr("o:hrpct").and_then(|v| v.trim().parse::<f32>().ok()).filter(|p| p.is_finite() && *p > 0.0);
+            let pct = tenths.map_or(if w > 0.0 { 0.0 } else { 100.0 }, |t| (t / 10.0).min(100.0));
+            let align = match attr("o:hralign").map(|a| a.trim().to_ascii_lowercase()).as_deref() {
+                Some("center") => wordcraft_doc::props::Align::Center,
+                Some("right") => wordcraft_doc::props::Align::Right,
+                _ => wordcraft_doc::props::Align::Left,
+            };
+            let standard = attr("o:hrstd").is_some_and(|v| matches!(v.trim(), "t" | "true" | "1"));
+            extra.hr = Some(wordcraft_doc::connector::HorizontalRule { pct, align, standard });
+        }
        if kind == ShapeKind::Line {
-            // Arrowheads (`v:stroke` startarrow / endarrow): any but `none` is drawn.
-            let arrow = |name: &str| shape.child("v:stroke").and_then(|s| s.attr(name)).is_some_and(|v| v != "none");
-            extra.arrow_start = arrow("startarrow");
-            extra.arrow_end = arrow("endarrow");
+            // Arrowheads (`v:stroke` startarrow / endarrow, with their width and length): any but
+            // `none` is drawn.
+            use wordcraft_doc::connector::{ArrowKind, ArrowSize, ArrowStyle};
+            let stroke = shape.child("v:stroke");
+            let arrow = |end: &str| {
+                let s = stroke?;
+                let kind = s.attr(&format!("{end}arrow")).filter(|v| *v != "none")?;
+                let size = |what: &str| ArrowSize::from_vml(s.attr(&format!("{end}arrow{what}")).unwrap_or("medium"));
+                Some(ArrowStyle { kind: ArrowKind::from_vml(kind), width: size("width"), length: size("length") })
+            };
+            if let Some(style) = arrow("start") {
+                extra.arrow_start = true;
+                extra.start_style = style;
+            }
+            if let Some(style) = arrow("end") {
+                extra.arrow_end = true;
+                extra.end_style = style;
+            }
        }
        if shape.local() == "line" {
            // A line runs `from` → `to` (points, offsets from where its style places it). A preset
@@ -42,6 +42,13 @@ pub(crate) fn ui_style_name(n: &str) -> String {
    n.to_string()
 }

+/// The outline level (0 for Heading 1) of Word's built-in style named `heading 1` … `heading 9`.
+fn builtin_heading_level(name: &str) -> Option<u8> {
+    let name = name.trim();
+    let digit = name.get(..8).filter(|p| p.eq_ignore_ascii_case("heading ")).and(name.get(8..))?;
+    digit.parse::<u8>().ok().filter(|d| digit.len() == 1 && (1..=9).contains(d)).map(|d| d - 1)
+}
+
 impl Reader<'_> {
    pub(super) fn read_styles(&mut self, path: &str) -> Result<(), DocxError> {
        /// Largest `w:latentStyles` kept (Word's has ~380 exceptions, ~40 KB).
@@ -115,7 +122,7 @@ impl Reader<'_> {
                priority: s.child_val("w:uiPriority").and_then(u32_of),
                quick: flag(s, "w:qFormat").unwrap_or(false),
                hidden: flag(s, "w:semiHidden").unwrap_or(false) || flag(s, "w:hidden").unwrap_or(false),
-                builtin: !s.attr("w:customStyle").is_some_and(|v| v == "1" || v == "true"),
+                builtin: !s.attr("w:customStyle").is_some_and(|v| matches!(v.trim(), "1" | "true" | "on")),
                locked: flag(s, "w:locked").unwrap_or(false),
                // Only where the writer couldn't tell from the id (it flags the English ids).
                default: s.attr("w:default").is_some_and(|v| v == "1" || v == "true")
@@ -131,6 +138,16 @@ impl Reader<'_> {
            if let Some(p) = s.child("w:pPr") {
                st.para = self.pc.ppr(p).0;
            }
+            // Word gives its built-in heading styles their outline level whether or not the file
+            // writes `w:outlineLvl` (some producers leave it out): "heading 2" is level 2 in the
+            // Navigation pane and the table of contents, whatever its id (#4696).
+            if kind == StyleKind::Paragraph
+                && st.builtin
+                && st.para.outline_level.is_none()
+                && let Some(level) = s.child_val("w:name").and_then(builtin_heading_level)
+            {
+                st.para.outline_level = Some(level);
+            }
            if let Some(rp) = s.child("w:rPr") {
                st.chr = self.pc.rpr(rp);
            }
@@ -33,7 +33,7 @@ const MAX_STORIES: usize = 50_000;

 /// Read a Word 2003 XML Document.
 pub fn read(bytes: &[u8]) -> Result<Document, DocxError> {
-    crate::read::read_opened(&convert(bytes)?)
+    crate::read::read_opened(&convert(bytes)?, None)
 }

 /// Parts the converted package gets relationships for.
@@ -121,10 +121,16 @@ pub(super) fn bibliography_xml(doc: &Document) -> Vec<u8> {
        w.open("b:Source", &[]);
        w.leaf("b:Tag", &[], &src.tag);
        w.leaf("b:SourceType", &[], to_source_type(&src.kind));
-        // Author & Editor
-        if !src.author.is_empty() || !src.editor.is_empty() {
+        // Author & Editor. A role holds a name list or a corporate name, not both (ECMA-376
+        // `CT_NameOrCorporateType`), so a corporate author takes the author's place (#4848).
+        let corporate = src.corporate.trim();
+        if !src.author.is_empty() || !corporate.is_empty() || !src.editor.is_empty() {
            w.open("b:Author", &[]);
-            if !src.author.is_empty() {
+            if !corporate.is_empty() {
+                w.open("b:Author", &[]);
+                w.leaf("b:Corporate", &[], corporate);
+                w.close("b:Author");
+            } else if !src.author.is_empty() {
                w.open("b:Author", &[]);
                write_name_list(&mut w, &src.author);
                w.close("b:Author");
@@ -429,13 +429,15 @@ fn write_comments(
                ("xmlns:mc", "http://schemas.openxmlformats.org/markup-compatibility/2006"),
            ],
        );
-        let pid_of = |cid: u32| comment_paras.iter().find(|(c, _)| *c == cid).map(|(_, p)| p.clone());
+        // Assigned in BTreeMap comment-ID order above, including gaps for missing parts.
+        let pid_of =
+            |cid: u32| comment_paras.binary_search_by_key(&cid, |(c, _)| *c).ok().and_then(|i| comment_paras.get(i)).map(|(_, p)| p.as_str());
        for (cid, c) in &doc.comments {
            let Some(pid) = pid_of(*cid) else { continue };
            let done = if c.resolved { "1" } else { "0" };
            match c.parent.and_then(pid_of) {
-                Some(parent) => w.empty("w15:commentEx", &[("w15:paraId", &pid), ("w15:paraIdParent", &parent), ("w15:done", done)]),
-                None => w.empty("w15:commentEx", &[("w15:paraId", &pid), ("w15:done", done)]),
+                Some(parent) => w.empty("w15:commentEx", &[("w15:paraId", pid), ("w15:paraIdParent", parent), ("w15:done", done)]),
+                None => w.empty("w15:commentEx", &[("w15:paraId", pid), ("w15:done", done)]),
            }
        }
        w.close("w15:commentsEx");
@@ -53,7 +53,9 @@ pub fn rpr_inner(w: &mut W, c: &CharProps) {
    toggle(w, "w:emboss", c.emboss);
    toggle(w, "w:imprint", c.engrave);
    toggle(w, "w:noProof", c.no_proof);
+    toggle(w, "w:snapToGrid", c.snap_to_grid);
    toggle(w, "w:vanish", c.hidden);
+    toggle(w, "w:webHidden", c.web_hidden);
    match c.color {
        Some(TextColor::Auto) => w.val("w:color", "auto"),
        Some(TextColor::Rgb(rgb)) => w.val("w:color", &rgb.hex()),
@@ -172,6 +172,8 @@ pub(super) fn write_comment_ids(
    if comment_paras.is_empty() {
        return;
    }
+    // Keep the existing exact-string reservation rule, including comments without a written part.
+    let reserved: std::collections::HashSet<&str> = doc.comments.values().filter_map(|c| c.durable_id.as_deref()).collect();
    let mut used: std::collections::HashSet<String> = std::collections::HashSet::new();
    let mut next = 0x1000_0000u32;
    let mut rows: Vec<(String, String, Option<String>)> = Vec::new();
@@ -183,7 +185,7 @@ pub(super) fn write_comment_ids(
            None => loop {
                next = next.saturating_add(1);
                let d = format!("{next:08X}");
-                if !used.contains(&d) && !doc.comments.values().any(|o| o.durable_id.as_deref() == Some(d.as_str())) {
+                if !used.contains(&d) && !reserved.contains(d.as_str()) {
                    break d;
                }
            },
@@ -382,11 +382,10 @@ fn line_dash(w: &mut W, dash: &wordcraft_doc::line_dash::LineDash) {
 /// A shape's `a:effectLst` (ECMA-376 Part 1 §20.1.8.26), children in schema order.
 /// A line's arrowheads (`a:headEnd`, `a:tailEnd`, ECMA-376 §20.1.8.38 / §20.1.8.57).
 fn arrow_ends(w: &mut W, extra: &wordcraft_doc::connector::ShapeExtra) {
-    if extra.arrow_start {
-        w.empty("a:headEnd", &[("type", "triangle")]);
-    }
-    if extra.arrow_end {
-        w.empty("a:tailEnd", &[("type", "triangle")]);
+    for (on, tag, style) in [(extra.arrow_start, "a:headEnd", extra.start_style), (extra.arrow_end, "a:tailEnd", extra.end_style)] {
+        if on {
+            w.empty(tag, &[("type", style.kind.ooxml()), ("w", style.width.ooxml()), ("len", style.length.ooxml())]);
+        }
    }
 }

@@ -115,6 +115,9 @@ impl Writer<'_> {
            // ink keep their original source and related parts.
            InlineObject::Graphic { .. } => self.write_graphic(w, o, props, rels, depth),
            InlineObject::Image { .. } => self.write_image(w, o, props, rels, depth),
+            InlineObject::Shape { extra, float, .. } if extra.hr.is_some() && float.wrap == Wrap::Inline && !float.hidden => {
+                self.write_hr(w, o, props)
+            }
            InlineObject::Shape { .. } => self.write_shape(w, o, props, rels, depth),
            InlineObject::Group { .. } => self.write_group(w, o, props, rels, depth),
            InlineObject::Ruby { base, ruby, align, size, raise, base_size, lang, props: ruby_props } => {
@@ -277,6 +280,74 @@ impl Writer<'_> {
        self.rev_close(w, props);
    }

+    /// A horizontal rule goes back as the VML rule it was read from: DrawingML has none, and a
+    /// fixed-size shape would lose its line-wide width.
+    fn write_hr(&mut self, w: &mut W, o: &InlineObject, props: &CharProps) {
+        let InlineObject::Shape { w: sw, h: sh, fill, stroke, stroke_width, extra, float, .. } = o else { return };
+        let Some(hr) = extra.hr else { return };
+        let align = match hr.align {
+            wordcraft_doc::props::Align::Center => "center",
+            wordcraft_doc::props::Align::Right => "right",
+            _ => "left",
+        };
+        let width = if hr.pct > 0.0 { "0".to_string() } else { format!("{:.2}pt", sw.max(0.0)) };
+        let mut style = format!("width:{width};height:{:.2}pt", sh.max(0.0));
+        let spin = float.spin();
+        if spin.deg != 0.0 {
+            style.push_str(&format!(";rotation:{}", spin.deg));
+        }
+        match (spin.flip_h, spin.flip_v) {
+            (true, true) => style.push_str(";flip:x y"),
+            (true, false) => style.push_str(";flip:x"),
+            (false, true) => style.push_str(";flip:y"),
+            (false, false) => {}
+        }
+        let pct = format!("{}", (hr.pct * 10.0).round().max(0.0) as u32);
+        let fill_hex = fill.as_ref().map(|f| format!("#{}", f.main_color().hex()));
+        let stroke_hex = stroke.map(|c| format!("#{}", c.hex()));
+        let weight = format!("{stroke_width:.2}pt");
+        let mut attrs: Vec<(&str, &str)> = vec![
+            ("xmlns:v", "urn:schemas-microsoft-com:vml"),
+            ("xmlns:o", "urn:schemas-microsoft-com:office:office"),
+            ("style", &style),
+            ("o:hrpct", &pct),
+            ("o:hralign", align),
+            ("o:hr", "t"),
+        ];
+        if hr.standard {
+            attrs.push(("o:hrstd", "t"));
+        }
+        if let Some(f) = &fill_hex {
+            attrs.push(("fillcolor", f));
+        } else {
+            attrs.push(("filled", "f"));
+        }
+        match &stroke_hex {
+            Some(s) => {
+                attrs.push(("strokecolor", s));
+                attrs.push(("strokeweight", &weight));
+            }
+            None => attrs.push(("stroked", "f")),
+        }
+        self.rev_open(w, props);
+        w.open("w:r", &[]);
+        self.rpr(w, props);
+        w.open("w:pict", &[]);
+        // A see-through fill keeps its opacity, which `fillcolor` can't say.
+        match fill.as_ref() {
+            Some(wordcraft_doc::fill::Fill::Solid { transparency, .. }) if *transparency > 0.0 => {
+                let opacity = format!("{:.4}", (1.0 - transparency / 100.0).clamp(0.0, 1.0));
+                w.open("v:rect", &attrs);
+                w.empty("v:fill", &[("opacity", &opacity)]);
+                w.close("v:rect");
+            }
+            _ => w.empty("v:rect", &attrs),
+        }
+        w.close("w:pict");
+        w.close("w:r");
+        self.rev_close(w, props);
+    }
+
    fn write_shape(&mut self, w: &mut W, o: &InlineObject, props: &CharProps, rels: &mut PartRels, depth: usize) {
        let InlineObject::Shape { kind, w: sw, h: sh, float, effects, freeform, extra, .. } = o else { return };
        self.rev_open(w, props);
@@ -0,0 +1,365 @@
+//! Alternative format chunks (`w:altChunk`, ECMA-376 §17.17.2.1): content in another format that
+//! is brought in where the chunk stands. All markup here is synthetic.
+
+use std::io::Write;
+
+use wordcraft_doc::{Block, Document, InlineObject, StoryRef};
+use wordcraft_docx::{AltChunk, ReadOptions, read, read_with};
+
+const NS: &str = r#"xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main" xmlns:r="http://schemas.openxmlformats.org/officeDocument/2006/relationships""#;
+const ROOT_RELS: &str = r#"<Relationships xmlns="http://schemas.openxmlformats.org/package/2006/relationships"><Relationship Id="rId1" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/officeDocument" Target="word/document.xml"/></Relationships>"#;
+const DOCX_MAIN: &str = "application/vnd.openxmlformats-officedocument.wordprocessingml.document.main+xml";
+
+fn p(text: &str) -> String {
+    format!(r#"<w:p><w:r><w:t xml:space="preserve">{text}</w:t></w:r></w:p>"#)
+}
+
+/// A package whose body is `body`, with the chunk `afchunk.{ext}` (content type `ct`) as `rIdC`.
+fn package(body: &str, chunk: Option<(&str, &str, &[u8])>) -> Vec<u8> {
+    package_styled(body, chunk, None)
+}
+
+/// [`package`] with a styles part holding `styles`.
+fn package_styled(body: &str, chunk: Option<(&str, &str, &[u8])>, styles: Option<&str>) -> Vec<u8> {
+    let doc = format!(r#"<w:document {NS}><w:body>{body}<w:sectPr/></w:body></w:document>"#);
+    let mut files: Vec<(String, Vec<u8>)> = vec![("_rels/.rels".into(), ROOT_RELS.into()), ("word/document.xml".into(), doc.into_bytes())];
+    let mut types = String::from(
+        r#"<Types xmlns="http://schemas.openxmlformats.org/package/2006/content-types"><Default Extension="rels" ContentType="application/vnd.openxmlformats-package.relationships+xml"/><Default Extension="xml" ContentType="application/xml"/>"#,
+    );
+    let mut rels = String::new();
+    if let Some((ext, ct, bytes)) = chunk {
+        types.push_str(&format!(r#"<Default Extension="{ext}" ContentType="{ct}"/>"#));
+        rels.push_str(&format!(r#"<Relationship Id="rIdC" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/aFChunk" Target="/word/afchunk.{ext}"/>"#));
+        files.push((format!("word/afchunk.{ext}"), bytes.to_vec()));
+    }
+    if let Some(styles) = styles {
+        rels.push_str(
+            r#"<Relationship Id="rIdS" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/styles" Target="styles.xml"/>"#,
+        );
+        files.push(("word/styles.xml".into(), format!(r#"<w:styles {NS}>{styles}</w:styles>"#).into_bytes()));
+    }
+    if !rels.is_empty() {
+        files.push((
+            "word/_rels/document.xml.rels".into(),
+            format!(r#"<Relationships xmlns="http://schemas.openxmlformats.org/package/2006/relationships">{rels}</Relationships>"#).into_bytes(),
+        ));
+    }
+    types.push_str(r#"<Override PartName="/word/document.xml" ContentType="application/vnd.openxmlformats-officedocument.wordprocessingml.document.main+xml"/></Types>"#);
+    files.push(("[Content_Types].xml".into(), types.into_bytes()));
+    let mut zw = zip::ZipWriter::new(std::io::Cursor::new(Vec::new()));
+    for (name, bytes) in files {
+        zw.start_file(name, zip::write::SimpleFileOptions::default()).unwrap();
+        zw.write_all(&bytes).unwrap();
+    }
+    zw.finish().unwrap().into_inner()
+}
+
+const CHUNK: &str = r#"<w:altChunk r:id="rIdC"/>"#;
+
+fn body_lines(d: &Document) -> Vec<String> {
+    d.plain_text(StoryRef::Body).split('\n').map(str::to_string).collect()
+}
+
+#[test]
+fn a_chunk_comes_in_through_the_importer_where_it_stands() {
+    let html = b"<p>Chunk one</p><p>Chunk two</p>";
+    let bytes = package(&format!("{}{CHUNK}{}", p("Before"), p("After")), Some(("htm", "application/xhtml+xml", html)));
+    let seen = std::cell::RefCell::new(Vec::new());
+    let import = |c: &AltChunk| {
+        seen.borrow_mut().push((c.content_type.to_string(), c.part.to_string(), c.bytes.to_vec()));
+        Some(Document::from_text("Chunk one\nChunk two"))
+    };
+    let d = read_with(&bytes, &ReadOptions { chunks: Some(&import), ..Default::default() }).unwrap();
+    assert_eq!(body_lines(&d), ["Before", "Chunk one", "Chunk two", "After"]);
+    assert_eq!(*seen.borrow(), [("application/xhtml+xml".to_string(), "word/afchunk.htm".to_string(), html.to_vec())]);
+    // Without an importer the chunk is left out.
+    assert_eq!(body_lines(&read(&bytes).unwrap()), ["Before", "After"]);
+}
+
+#[test]
+fn a_bookmark_opened_before_a_chunk_at_the_start_of_the_body_is_kept() {
+    let body = format!(r#"<w:bookmarkStart w:id="0" w:name="Here"/>{CHUNK}<w:bookmarkEnd w:id="0"/>{}"#, p("After"));
+    let bytes = package(&body, Some(("htm", "application/xhtml+xml", b"<p>Chunk</p>")));
+    let import = |_: &AltChunk| Some(Document::from_text("Chunk"));
+    let d = read_with(&bytes, &ReadOptions { chunks: Some(&import), ..Default::default() }).unwrap();
+    assert_eq!(body_lines(&d), ["Chunk", "After"]);
+    let marks = d.bookmarks();
+    assert_eq!(marks.len(), 1);
+    assert_eq!((marks[0].0.as_str(), marks[0].1.path.last(), marks[0].1.off), ("Here", 0, 0));
+}
+
+#[test]
+fn a_bookmark_opened_between_a_table_and_a_chunk_starts_the_chunk() {
+    let table = format!("<w:tbl><w:tr><w:tc>{}</w:tc></w:tr></w:tbl>", p("Cell"));
+    let body = format!(r#"{table}<w:bookmarkStart w:id="0" w:name="Here"/>{CHUNK}<w:bookmarkEnd w:id="0"/>{}"#, p("After"));
+    let bytes = package(&body, Some(("htm", "application/xhtml+xml", b"<p>Chunk</p>")));
+    let import = |_: &AltChunk| Some(Document::from_text("Chunk"));
+    let d = read_with(&bytes, &ReadOptions { chunks: Some(&import), ..Default::default() }).unwrap();
+    let marks = d.bookmarks();
+    assert_eq!(marks.len(), 1);
+    assert_eq!((marks[0].1.path.clone(), marks[0].1.off), (wordcraft_doc::Path::top(1), 0), "not in the table's cell");
+}
+
+#[test]
+fn permission_ranges_of_chunks_and_their_host_stay_apart() {
+    let inner = package(r#"<w:p><w:permStart w:id="0" w:ed="them"/><w:r><w:t>Inner</w:t></w:r><w:permEnd w:id="0"/></w:p>"#, None);
+    // The host's range 0 is open across two chunks whose own ranges are 0 too.
+    let body = format!(
+        r#"<w:p><w:permStart w:id="0" w:edGrp="everyone"/><w:r><w:t>Host</w:t></w:r></w:p>{CHUNK}{CHUNK}<w:p><w:r><w:t>After</w:t></w:r><w:permEnd w:id="0"/></w:p>"#
+    );
+    let d = read(&package(&body, Some(("docx", DOCX_MAIN, &inner)))).unwrap();
+    assert_eq!(body_lines(&d), ["Host", "Inner", "Inner", "After"]);
+    let check = |d: &Document| {
+        let ranges = d.perm_ranges();
+        let mut ids: Vec<u32> = ranges.iter().map(|r| r.id).collect();
+        ids.sort_unstable();
+        ids.dedup();
+        assert_eq!(ids.len(), 3, "{ranges:?}");
+        let host = ranges.iter().find(|r| r.group == "everyone").unwrap();
+        assert_eq!((host.start.path.last(), host.end.path.last()), (0, 3));
+        assert!(ranges.iter().filter(|r| r.editor == "them").all(|r| r.start.path == r.end.path));
+    };
+    check(&d);
+    check(&read(&wordcraft_docx::write(&d).unwrap()).unwrap());
+}
+
+/// A package whose body is `body`, with story parts (relationship type, part name, XML) and the
+/// Word document `chunk` as `rIdC` from the main part and from each story part.
+fn package_with_stories(body: &str, stories: &[(&str, &str, String)], chunk: Option<&[u8]>) -> Vec<u8> {
+    let rel = |id: &str, ty: &str, target: &str| {
+        format!(r#"<Relationship Id="{id}" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/{ty}" Target="{target}"/>"#)
+    };
+    let rels =
+        |inner: String| format!(r#"<Relationships xmlns="http://schemas.openxmlformats.org/package/2006/relationships">{inner}</Relationships>"#);
+    let chunk_rel = if chunk.is_some() { rel("rIdC", "aFChunk", "/word/afchunk.docx") } else { String::new() };
+    let doc = format!(r#"<w:document {NS}><w:body>{body}<w:sectPr/></w:body></w:document>"#);
+    let mut main_rels = chunk_rel.clone();
+    let mut files: Vec<(String, Vec<u8>)> = vec![("_rels/.rels".into(), ROOT_RELS.into()), ("word/document.xml".into(), doc.into_bytes())];
+    for (i, (ty, name, xml)) in stories.iter().enumerate() {
+        main_rels.push_str(&rel(&format!("rIdS{i}"), ty, name));
+        files.push((format!("word/{name}"), xml.clone().into_bytes()));
+        files.push((format!("word/_rels/{name}.rels"), rels(chunk_rel.clone()).into_bytes()));
+    }
+    files.push(("word/_rels/document.xml.rels".into(), rels(main_rels).into_bytes()));
+    if let Some(c) = chunk {
+        files.push(("word/afchunk.docx".into(), c.to_vec()));
+    }
+    let mut zw = zip::ZipWriter::new(std::io::Cursor::new(Vec::new()));
+    for (name, bytes) in files {
+        zw.start_file(name, zip::write::SimpleFileOptions::default()).unwrap();
+        zw.write_all(&bytes).unwrap();
+    }
+    zw.finish().unwrap().into_inner()
+}
+
+/// A paragraph `text` that comment `id` (in the file) is anchored around.
+fn commented(id: u32, text: &str) -> String {
+    format!(
+        r#"<w:p><w:commentRangeStart w:id="{id}"/><w:r><w:t>{text}</w:t></w:r><w:commentRangeEnd w:id="{id}"/><w:r><w:commentReference w:id="{id}"/></w:r></w:p>"#
+    )
+}
+
+/// A comments part: (file id, author, content).
+fn comments_part(list: &[(u32, &str, String)]) -> (&'static str, &'static str, String) {
+    let body: String = list.iter().map(|(id, who, content)| format!(r#"<w:comment w:id="{id}" w:author="{who}">{content}</w:comment>"#)).collect();
+    ("comments", "comments.xml", format!("<w:comments {NS}>{body}</w:comments>"))
+}
+
+/// The authors of the comments anchored in the stories whose text contains `text`, and whether
+/// every comment has text of its own and a distinct id.
+fn anchored(d: &Document, text: &str) -> Vec<String> {
+    let mut stories: Vec<&[std::sync::Arc<Block>]> = vec![&d.body];
+    stories.extend(d.parts.values().map(|p| p.blocks.as_slice()));
+    let mut out = Vec::new();
+    for blocks in stories {
+        for b in blocks {
+            let Block::Para(p) = &**b else { continue };
+            if !p.text.contains(text) {
+                continue;
+            }
+            for o in &p.objects {
+                if let InlineObject::CommentStart { id } = o {
+                    out.push(d.comments.get(id).map_or("?".to_string(), |c| c.author.clone()));
+                }
+            }
+        }
+    }
+    out
+}
+
+/// A Word document with one comment by "Them" around "Inner".
+fn commented_chunk() -> Vec<u8> {
+    package_with_stories(&commented(0, "Inner"), &[comments_part(&[(0, "Them", p("Theirs"))])], None)
+}
+
+#[test]
+fn a_chunk_in_a_footnote_keeps_its_comments_beside_the_documents() {
+    let notes = format!(r#"<w:footnotes {NS}><w:footnote w:id="1"><w:altChunk r:id="rIdC"/></w:footnote></w:footnotes>"#);
+    let body = format!(r#"{}<w:p><w:r><w:footnoteReference w:id="1"/></w:r></w:p>"#, commented(0, "Host"));
+    let stories = [("footnotes", "footnotes.xml", notes), comments_part(&[(0, "Us", p("Ours"))])];
+    let d = read(&package_with_stories(&body, &stories, Some(&commented_chunk()))).unwrap();
+    assert_eq!(d.comments.len(), 2, "{:?}", d.comments);
+    assert_eq!(anchored(&d, "Host"), ["Us"]);
+    assert_eq!(anchored(&d, "Inner"), ["Them"]);
+}
+
+#[test]
+fn a_chunk_in_a_comment_keeps_its_comments_beside_the_documents() {
+    let inside = format!(r#"{}<w:altChunk r:id="rIdC"/>"#, p("Ours"));
+    let body = format!("{}{}", commented(0, "Host"), commented(1, "Second"));
+    let stories = [comments_part(&[(0, "Us", inside), (1, "Us too", p("Ours too"))])];
+    let d = read(&package_with_stories(&body, &stories, Some(&commented_chunk()))).unwrap();
+    assert_eq!(d.comments.len(), 3, "{:?}", d.comments);
+    assert_eq!(anchored(&d, "Host"), ["Us"]);
+    assert_eq!(anchored(&d, "Second"), ["Us too"]);
+    assert_eq!(anchored(&d, "Inner"), ["Them"]);
+}
+
+#[test]
+fn a_wordprocessing_chunk_is_read_without_an_importer_and_flows_in_its_section() {
+    let inner = package(&format!("{}{}", p("Inner one"), p("Inner two")), None);
+    let bytes = package(&format!("{}{CHUNK}{}", p("Before"), p("After")), Some(("docx", DOCX_MAIN, &inner)));
+    let d = read(&bytes).unwrap();
+    assert_eq!(body_lines(&d), ["Before", "Inner one", "Inner two", "After"]);
+    // The inner document's own section doesn't come along.
+    assert_eq!(d.sections().len(), 1);
+}
+
+/// Styles a matchSrc chunk brings under new ids get distinct ones: with `A` and `A1` ours and
+/// `A` to `A10` the chunk's, its `A` and `A1` both renamed don't land on one id (the second then
+/// lost, its paragraphs taking the first's formatting), and keep their formatting through a save.
+#[test]
+fn match_src_gives_each_renamed_style_its_own_id() {
+    let style = |id: &str, half_points: u32| {
+        format!(r#"<w:style w:type="paragraph" w:styleId="{id}"><w:name w:val="{id}"/><w:rPr><w:sz w:val="{half_points}"/></w:rPr></w:style>"#)
+    };
+    let ours: String = ["A", "A1"].iter().map(|id| style(id, 22)).collect();
+    let mut theirs = style("A", 20) + &style("A1", 28);
+    for n in 2..=10 {
+        theirs += &style(&format!("A{n}"), 16);
+    }
+    let para = |id: &str, text: &str| format!(r#"<w:p><w:pPr><w:pStyle w:val="{id}"/></w:pPr><w:r><w:t>{text}</w:t></w:r></w:p>"#);
+    let inner = package_styled(&(para("A", "ten") + &para("A1", "fourteen")), None, Some(&theirs));
+    let body = format!(r#"{}<w:altChunk r:id="rIdC"><w:altChunkPr><w:matchSrc/></w:altChunkPr></w:altChunk>"#, p("Ours"));
+    let d = read(&package_styled(&body, Some(("docx", DOCX_MAIN, &inner)), Some(&ours))).unwrap();
+    let check = |d: &Document| {
+        let look = |text: &str| {
+            d.body
+                .iter()
+                .find_map(|b| match &**b {
+                    Block::Para(p) if p.text == text => {
+                        Some((p.props.style.clone(), d.styles.resolve_char(p.props.style.as_deref(), p.props_of_char(0)).size))
+                    }
+                    _ => None,
+                })
+                .unwrap()
+        };
+        let ((ten, ten_size), (fourteen, fourteen_size)) = (look("ten"), look("fourteen"));
+        assert_ne!(ten, fourteen);
+        assert_eq!((ten_size, fourteen_size), (10.0, 14.0));
+    };
+    check(&d);
+    check(&read(&wordcraft_docx::write(&d).unwrap()).unwrap());
+}
+
+#[test]
+fn match_src_keeps_a_word_chunks_own_formatting() {
+    // Both define Normal and Subtitle differently, and the chunk's defaults differ from ours.
+    let ours = r#"<w:docDefaults><w:rPrDefault><w:rPr><w:sz w:val="22"/></w:rPr></w:rPrDefault><w:pPrDefault><w:pPr><w:spacing w:after="200"/></w:pPr></w:pPrDefault></w:docDefaults><w:style w:type="paragraph" w:default="1" w:styleId="Normal"><w:name w:val="Normal"/><w:pPr><w:spacing w:after="248" w:line="248" w:lineRule="exact"/></w:pPr></w:style><w:style w:type="paragraph" w:styleId="Subtitle"><w:name w:val="Subtitle"/><w:rPr><w:i/></w:rPr></w:style>"#;
+    let theirs = r#"<w:docDefaults><w:rPrDefault><w:rPr><w:sz w:val="24"/></w:rPr></w:rPrDefault></w:docDefaults><w:style w:type="paragraph" w:default="1" w:styleId="Normal"><w:name w:val="Normal"/></w:style><w:style w:type="paragraph" w:styleId="Subtitle"><w:name w:val="Subtitle"/><w:basedOn w:val="Normal"/></w:style>"#;
+    let inner = package_styled(
+        &format!(r#"{}<w:p><w:pPr><w:pStyle w:val="Subtitle"/></w:pPr><w:r><w:t>Sub</w:t></w:r></w:p>"#, p("Plain")),
+        None,
+        Some(theirs),
+    );
+    for match_src in [true, false] {
+        let pr = if match_src { "<w:altChunkPr><w:matchSrc/></w:altChunkPr>" } else { "" };
+        let body = format!(r#"{}<w:altChunk r:id="rIdC">{pr}</w:altChunk>"#, p("Ours"));
+        let d = read(&package_styled(&body, Some(("docx", DOCX_MAIN, &inner)), Some(ours))).unwrap();
+        let look = |i: usize| match &*d.body[i] {
+            Block::Para(p) => {
+                let para = d.styles.resolve_para(&p.props);
+                let chr = d.styles.resolve_char(p.props.style.as_deref(), p.props_of_char(0));
+                (para.space_after, chr.size, chr.italic)
+            }
+            b => panic!("{b:?}"),
+        };
+        // Ours stays ours either way.
+        assert_eq!(look(0), (12.4, 11.0, false));
+        if match_src {
+            // The chunk's own Normal (its 12 pt, Word's no space after) and its Subtitle (not italic).
+            assert_eq!(look(1), (0.0, 12.0, false));
+            assert_eq!(look(2), (0.0, 12.0, false));
+        } else {
+            // Without it the chunk takes our styles (our Subtitle stands on our defaults).
+            assert_eq!(look(1), (12.4, 11.0, false));
+            assert_eq!(look(2), (10.0, 11.0, true));
+        }
+    }
+}
+
+#[test]
+fn nested_wordprocessing_chunks_stop_at_a_depth() {
+    let mut bytes = package(&p("Deepest"), None);
+    for level in 0..8 {
+        bytes = package(&format!("{}{CHUNK}", p(&format!("Level {level}"))), Some(("docx", DOCX_MAIN, &bytes)));
+    }
+    let lines = body_lines(&read(&bytes).unwrap());
+    assert_eq!(lines.first().map(String::as_str), Some("Level 7"));
+    assert!(!lines.iter().any(|l| l == "Deepest"), "{lines:?}");
+    assert!(lines.len() >= 4, "{lines:?}");
+}
+
+#[test]
+fn a_chunks_pictures_come_with_it() {
+    let bytes = package(&format!("{}{CHUNK}", p("Before")), Some(("htm", "text/html", b"<p>x</p>")));
+    let import = |_: &AltChunk| {
+        let mut d = Document::new();
+        let key = d.add_media(vec![1, 2, 3], "png");
+        let mut para = wordcraft_doc::Paragraph::new();
+        let image = InlineObject::Image { media: key, w: 10.0, h: 10.0, alt: String::new(), float: Default::default(), crop: [0.0; 4], ole: None };
+        para.insert_object(0, image, &Default::default()).unwrap();
+        d.body = vec![std::sync::Arc::new(Block::Para(para))];
+        Some(d)
+    };
+    let d = read_with(&bytes, &ReadOptions { chunks: Some(&import), ..Default::default() }).unwrap();
+    let keys: Vec<String> = d
+        .body
+        .iter()
+        .filter_map(|b| match &**b {
+            Block::Para(p) => p.objects.iter().find_map(|o| match o {
+                InlineObject::Image { media, .. } => Some(media.clone()),
+                _ => None,
+            }),
+            _ => None,
+        })
+        .collect();
+    assert_eq!(keys.len(), 1);
+    assert_eq!(d.media.get(&keys[0]).map(|m| m.as_slice()), Some(&[1u8, 2, 3][..]));
+}
+
+#[test]
+fn a_file_brings_in_a_bounded_number_of_chunks() {
+    let bytes = package(&CHUNK.repeat(300), Some(("htm", "text/html", b"<p>x</p>")));
+    let calls = std::cell::Cell::new(0);
+    let import = |_: &AltChunk| {
+        calls.set(calls.get() + 1);
+        Some(Document::from_text("x"))
+    };
+    let d = read_with(&bytes, &ReadOptions { chunks: Some(&import), ..Default::default() }).unwrap();
+    assert_eq!(calls.get(), 256);
+    assert_eq!(body_lines(&d).len(), 256);
+}
+
+#[test]
+fn hostile_chunks_never_panic() {
+    for (ext, ct, bytes) in [("docx", DOCX_MAIN, &b"PK\x03\x04 not a zip"[..]), ("htm", "text/html", b""), ("bin", "", b"\x00\xff")] {
+        let bytes = package(&format!("{CHUNK}{CHUNK}{}", p("x")), Some((ext, ct, bytes)));
+        let import = |_: &AltChunk| None;
+        let d = read_with(&bytes, &ReadOptions { chunks: Some(&import), ..Default::default() }).unwrap();
+        assert_eq!(body_lines(&d), ["x"]);
+    }
+    // A chunk naming a missing part or another relationship type is left out.
+    let bytes = package(&format!(r#"<w:altChunk r:id="nope"/><w:altChunk/>{}"#, p("y")), None);
+    assert_eq!(body_lines(&read(&bytes).unwrap()), ["y"]);
+}
@@ -155,6 +155,38 @@ fn zotero_fields_and_prefs_round_trip() {
    assert_eq!(read(&write(&d2).unwrap()).unwrap().custom_props, d.custom_props);
 }

+#[test]
+fn custom_property_bookmark_links_survive_saves_and_value_edits() {
+    let props = r#"<c:Properties xmlns:c="http://schemas.openxmlformats.org/officeDocument/2006/custom-properties" xmlns:v="http://schemas.openxmlformats.org/officeDocument/2006/docPropsVTypes">
+<c:property fmtid="{D5CDD505-2E9C-101B-9397-08002B2CF9AE}" pid="2" name="Linked" linkTarget="OriginalBookmark"><v:lpwstr>Original value</v:lpwstr></c:property>
+<c:property fmtid="{D5CDD505-2E9C-101B-9397-08002B2CF9AE}" pid="3" name="Raw" linkTarget="RawBookmark"><v:vector size="1" baseType="lpwstr"><v:lpwstr>Ω</v:lpwstr></v:vector></c:property>
+<c:property fmtid="{D5CDD505-2E9C-101B-9397-08002B2CF9AE}" pid="4" name="Unlinked"><v:i4>17</v:i4></c:property>
+</c:Properties>"#;
+    let doc = format!(
+        r#"<w:document {W_NS}><w:body><w:p><w:bookmarkStart w:id="1" w:name="OriginalBookmark"/>{}<w:bookmarkEnd w:id="1"/></w:p><w:p><w:bookmarkStart w:id="2" w:name="RawBookmark"/>{}<w:bookmarkEnd w:id="2"/></w:p></w:body></w:document>"#,
+        t("Original value"),
+        t("Ω")
+    );
+    let bytes = zip(&[("_rels/.rels", ROOT_RELS.as_bytes()), ("word/document.xml", doc.as_bytes()), ("docProps/custom.xml", props.as_bytes())]);
+    let mut d = read(&bytes).unwrap();
+    for value in ["Original value", "Edited value"] {
+        d.set_custom_prop("linked", value);
+        let before = d.custom_props.clone();
+        for _ in 0..2 {
+            let out = write(&d).unwrap();
+            let mut z = zip::ZipArchive::new(std::io::Cursor::new(&out)).unwrap();
+            let mut xml = String::new();
+            std::io::Read::read_to_string(&mut z.by_name("docProps/custom.xml").unwrap(), &mut xml).unwrap();
+            assert!(xml.contains(r#"linkTarget="OriginalBookmark""#), "{xml}");
+            assert!(xml.contains(r#"linkTarget="RawBookmark""#), "{xml}");
+            assert_eq!(xml.matches("linkTarget=").count(), 2, "unlinked properties stay unlinked");
+            d = read(&out).unwrap();
+            assert_eq!(d.custom_props, before);
+            assert_eq!(d.custom_prop("Linked"), Some(value));
+        }
+    }
+}
+
 #[test]
 fn unterminated_and_resultless_addin_fields() {
    // A field left open at the end of the document, and one with no result at all.
@@ -0,0 +1,55 @@
+//! Saving large comment threads must not search all comments for each emitted ID.
+
+use wordcraft_doc::{Comment, Document, Paragraph, Part, PartKind, para_block};
+
+fn comments(n: u32, imported: bool) -> Document {
+    let mut d = Document::from_text("Original comment save fixture.");
+    for i in 0..n {
+        // Sparse IDs and replies to a later comment also exercise paragraph-ID lookup order.
+        let id = i * 3 + 7;
+        d.parts.insert(id, Part { kind: PartKind::Comment, blocks: vec![para_block(Paragraph::new())], ..Default::default() });
+        d.comments.insert(
+            id,
+            Comment { part: id, parent: (i + 1 < n).then_some(id + 3), durable_id: imported.then(|| format!("{:08X}", i + 1)), ..Default::default() },
+        );
+    }
+    d
+}
+
+fn cpu_cost(mut f: impl FnMut()) -> f64 {
+    let ran = || std::fs::read_to_string("/proc/thread-self/schedstat").ok()?.split_whitespace().next()?.parse::<u64>().ok();
+    let (wall, before) = (std::time::Instant::now(), ran());
+    f();
+    match (before, ran()) {
+        (Some(a), Some(b)) if b > a => (b - a) as f64 * 1e-9,
+        _ => wall.elapsed().as_secs_f64(),
+    }
+}
+
+#[test]
+fn many_comments_save_without_quadratic_id_searches() {
+    for imported in [true, false] {
+        let small = comments(4_000, imported);
+        let big = comments(32_000, imported);
+        let save = |d: &Document| drop(std::hint::black_box(wordcraft_docx::write(d).unwrap()));
+        save(&small);
+        save(&big);
+        let mut ratios = Vec::new();
+        // Alternating inputs and thread CPU time leave scheduler delays out on Linux. Elsewhere
+        // use elapsed time; retry ratios far from linear before declaring a regression.
+        for _ in 0..3 {
+            let (mut s, mut b) = (f64::INFINITY, f64::INFINITY);
+            for _ in 0..3 {
+                s = s.min(cpu_cost(|| (0..8).for_each(|_| save(&small))) / 8.0);
+                b = b.min(cpu_cost(|| save(&big)));
+            }
+            let ratio = b / s.max(1e-9);
+            eprintln!("comments imported={imported}: {s:.4}s -> {b:.4}s, ratio {ratio:.2}");
+            if ratio < 24.0 {
+                break;
+            }
+            ratios.push(ratio);
+        }
+        assert!(ratios.len() < 3, "8x comments took {ratios:?}x CPU: repeated ID searches");
+    }
+}
@@ -48,6 +48,76 @@ fn read_body(body: &str) -> Document {
    wordcraft_docx::read(&docx(body, &[], &[])).unwrap()
 }

+/// Markup compatibility replaces an AlternateContent wrapper with one selected branch,
+/// including where a table expects rows or cells (ECMA-376 Part 3).
+#[test]
+fn table_alternate_content_keeps_selected_rows_and_cells() {
+    let cell = |text: &str| format!("<w:tc><w:p><w:r><w:t>{text}</w:t></w:r></w:p></w:tc>");
+    let row = |text: &str| format!("<w:tr>{}</w:tr>", cell(text));
+    let table =
+        |rows: &str, columns: usize| format!(r#"<w:tbl><w:tblGrid>{}</w:tblGrid>{rows}</w:tbl>"#, r#"<w:gridCol w:w="2400"/>"#.repeat(columns));
+    let alternate = |chosen: &str, fallback: &str, requires: &str| {
+        format!(
+            r#"<mc:AlternateContent><mc:Choice Requires="{requires}">{chosen}</mc:Choice><mc:Fallback>{fallback}</mc:Fallback></mc:AlternateContent>"#
+        )
+    };
+    for (requires, use_choice) in [("wps", true), ("alias", true), ("unknown", false), ("wps unknown", false)] {
+        for cells in [false, true] {
+            let choice = if cells { cell("Chosen cell") } else { row("Chosen row") };
+            let fallback = if cells { cell("Fallback cell") } else { row("Fallback row") };
+            let selected = if use_choice { &choice } else { &fallback };
+            let middle = alternate(&choice, &fallback, requires);
+            let (actual, expected) = if cells {
+                (
+                    format!("<w:tr>{}{middle}{}</w:tr>", cell("Before"), cell("After")),
+                    format!("<w:tr>{}{selected}{}</w:tr>", cell("Before"), cell("After")),
+                )
+            } else {
+                (format!("{}{middle}{}", row("Before"), row("After")), format!("{}{selected}{}", row("Before"), row("After")))
+            };
+            let columns = if cells { 3 } else { 1 };
+            let expected = read_body(&table(&expected, columns));
+            let wrapped = format!(
+                r#"<w:customXml xmlns:alias="http://schemas.microsoft.com/office/word/2010/wordprocessingShape" xmlns:unknown="urn:original:unsupported">{}</w:customXml>"#,
+                table(&actual, columns)
+            );
+            let mut actual = read_body(&wrapped);
+            for round in 0..=2 {
+                assert_eq!(actual.body, expected.body, "requires={requires}, cells={cells}, round={round}");
+                if round < 2 {
+                    actual = wordcraft_docx::read(&wordcraft_docx::write(&actual).unwrap()).unwrap();
+                }
+            }
+        }
+    }
+}
+
+#[test]
+fn table_alternate_content_keeps_nested_row_and_cell_controls() {
+    let wrap =
+        |tag: &str, content: &str| format!(r#"<w:sdt><w:sdtPr><w:tag w:val="{tag}"/></w:sdtPr><w:sdtContent>{content}</w:sdtContent></w:sdt>"#);
+    let alternate =
+        |content: &str| format!(r#"<mc:AlternateContent><mc:Choice Requires="wps">{content}</mc:Choice><mc:Fallback/></mc:AlternateContent>"#);
+    let cell = "<w:tc><w:p><w:r><w:t>Controlled cell</w:t></w:r></w:p></w:tc>";
+    let oracle_cell = wrap("cell", cell);
+    let actual_cell = alternate(&wrap("cell", &alternate(cell)));
+    let oracle_row = wrap("row", &format!("<w:tr>{oracle_cell}</w:tr>"));
+    let actual_row = wrap("row", &alternate(&format!("<w:tr>{actual_cell}</w:tr>")));
+    let expected = read_body(&format!("<w:tbl>{oracle_row}</w:tbl>"));
+    let mut actual = read_body(&format!("<w:tbl>{}</w:tbl>", alternate(&actual_row)));
+    for round in 0..=2 {
+        assert_eq!(actual.body, expected.body, "round={round}");
+        let table = actual.body.iter().find_map(|b| b.as_table()).unwrap();
+        assert_eq!(table.rows[0].controls.open[0].tag, "row");
+        assert_eq!(table.rows[0].controls.close, 1);
+        assert_eq!(table.rows[0].cells[0].controls.open[0].tag, "cell");
+        assert_eq!(table.rows[0].cells[0].controls.close, 1);
+        if round < 2 {
+            actual = wordcraft_docx::read(&wordcraft_docx::write(&actual).unwrap()).unwrap();
+        }
+    }
+}
+
 #[test]
 fn repeated_style_ids_use_last() {
    let styles = format!(
@@ -114,6 +184,68 @@ fn paragraph_default_presence_survives_repeated_saves() {
    }
 }

+#[test]
+fn zero_frame_keeps_normal_flow() {
+    const ROUND_TRIPS: usize = 2;
+    let zero = r#"<w:framePr w:w="0" w:h="0" w:xAlign="left" w:y="0" w:hRule="exact" w:vAnchor="margin"/>"#;
+    let sized = r#"<w:framePr w:w="2400" w:h="1200" w:x="1440" w:y="2880" w:hAnchor="page" w:vAnchor="page" w:hRule="exact"/>"#;
+    for frame in [zero, sized] {
+        let styles = format!(
+            r#"<w:styles {W_NS}><w:docDefaults><w:pPrDefault><w:pPr>{frame}<w:spacing w:after="160"/></w:pPr></w:pPrDefault></w:docDefaults>
+            <w:style w:type="paragraph" w:styleId="Framed"><w:name w:val="Framed"/><w:pPr>{sized}</w:pPr></w:style></w:styles>"#
+        );
+        let header = format!(r#"<w:hdr {W_NS}><w:p><w:r><w:t>Header alpha</w:t></w:r></w:p><w:p><w:r><w:t>Header beta</w:t></w:r></w:p></w:hdr>"#);
+        let footer = format!(r#"<w:ftr {W_NS}><w:p><w:r><w:t>Footer delta</w:t></w:r></w:p></w:ftr>"#);
+        let body = format!(
+            r#"<w:p><w:r><w:t>Body one</w:t></w:r></w:p>
+            <w:p><w:pPr>{sized}</w:pPr><w:r><w:t>Direct frame</w:t></w:r></w:p>
+            <w:p><w:pPr><w:pStyle w:val="Framed"/></w:pPr><w:r><w:t>Styled frame</w:t></w:r></w:p>
+            <w:p><w:pPr><w:pStyle w:val="Framed"/>{zero}</w:pPr><w:r><w:t>Frame reset</w:t></w:r></w:p>
+            <w:sectPr><w:headerReference w:type="default" r:id="header"/><w:footerReference w:type="default" r:id="footer"/></w:sectPr>"#
+        );
+        let mut document = wordcraft_docx::read(&docx(
+            &body,
+            &[("styles", "styles", "styles.xml"), ("header", "header", "header1.xml"), ("footer", "footer", "footer1.xml")],
+            &[("word/styles.xml", &styles), ("word/header1.xml", &header), ("word/footer1.xml", &footer)],
+        ))
+        .unwrap();
+        for pass in 0..=ROUND_TRIPS {
+            let body = paras(&document);
+            let resolved = document.styles.resolve_para(&body[0].props);
+            assert!(resolved.frame.is_none(), "document defaults never create a frame");
+            assert!(document.styles.default_para.frame.is_none());
+            let reset = body[3].props.frame.as_ref().unwrap();
+            assert_eq!((reset.w, reset.h), (Some(0.0), Some(0.0)), "the direct reset survives saving");
+            assert_eq!(resolved.space_after, 8.0);
+            assert!(document.styles.resolve_para(&body[1].props).frame.is_some());
+            assert!(document.styles.resolve_para(&body[2].props).frame.is_some());
+            assert!(document.styles.resolve_para(&body[3].props).frame.is_none());
+            for id in [document.last_section.headers.default, document.last_section.footers.default] {
+                for block in &document.parts.get(&id.unwrap()).unwrap().blocks {
+                    let paragraph = block.as_para().unwrap();
+                    assert!(document.styles.resolve_para(&paragraph.props).frame.is_none(), "defaults do not frame headers or footers");
+                }
+            }
+            if pass == ROUND_TRIPS {
+                break;
+            }
+            document = wordcraft_docx::read(&wordcraft_docx::write(&document).unwrap()).unwrap();
+        }
+    }
+}
+
+#[test]
+fn frame_zero_side_is_automatic() {
+    for (attrs, width, height) in
+        [(r#"w:w="0" w:h="1200""#, None, Some(60.0)), (r#"w:w="2400" w:h="0" w:hRule="exact""#, Some(120.0), None), ("", None, None)]
+    {
+        let document = read_body(&format!(r#"<w:p><w:pPr><w:framePr {attrs}/></w:pPr><w:r><w:t>Original automatic frame</w:t></w:r></w:p>"#));
+        let paragraph = paras(&document)[0];
+        let frame = document.styles.resolve_para(&paragraph.props).frame.unwrap();
+        assert_eq!((frame.w, frame.h), (width, height));
+    }
+}
+
 #[test]
 fn omitted_paragraph_defaults_can_be_edited() {
    let styles =
@@ -2413,6 +2545,52 @@ fn vml_lines_and_rectangles() {
    ));
 }

+/// An arrowhead's kind, width and length (DrawingML `a:headEnd`/`a:tailEnd` `type`/`w`/`len`, VML
+/// `startarrow`/`startarrowwidth`/`startarrowlength`) are read and saved: they set the size Word
+/// draws it at. An end without `w`/`len` is medium.
+#[test]
+fn arrowheads_keep_their_kind_and_size() {
+    use wordcraft_doc::connector::{ArrowKind, ArrowSize, ArrowStyle};
+    let style = |kind, width, length| ArrowStyle { kind, width, length };
+    let body = [
+        anchored_wsp(
+            "Line",
+            1270000,
+            0,
+            r#"<a:prstGeom prst="line"><a:avLst/></a:prstGeom><a:ln w="12700"><a:solidFill><a:srgbClr val="000000"/></a:solidFill><a:headEnd type="stealth" w="sm" len="lg"/><a:tailEnd type="diamond" w="lg" len="sm"/></a:ln>"#,
+            "",
+            "<wps:cNvCnPr/>",
+        ),
+        anchored_wsp("Plain", 1270000, 0, r#"<a:prstGeom prst="line"><a:avLst/></a:prstGeom><a:ln><a:solidFill><a:srgbClr val="000000"/></a:solidFill><a:tailEnd type="triangle"/></a:ln>"#, "", "<wps:cNvCnPr/>"),
+        r#"<w:r><w:pict><v:line style="position:absolute" from="10pt,20pt" to="40pt,20pt"><v:stroke startarrow="classic" startarrowwidth="narrow" startarrowlength="long" endarrow="oval" endarrowwidth="wide" endarrowlength="short"/></v:line></w:pict></w:r>"#.to_string(),
+    ]
+    .concat();
+    let ends = |d: &Document| -> Vec<(bool, ArrowStyle, bool, ArrowStyle)> {
+        paras(d)[0]
+            .objects
+            .iter()
+            .map(|o| match o {
+                InlineObject::Shape { extra, .. } => (extra.arrow_start, extra.start_style, extra.arrow_end, extra.end_style),
+                o => panic!("{o:?}"),
+            })
+            .collect()
+    };
+    let expected = vec![
+        (true, style(ArrowKind::Stealth, ArrowSize::Small, ArrowSize::Large), true, style(ArrowKind::Diamond, ArrowSize::Large, ArrowSize::Small)),
+        (false, ArrowStyle::default(), true, ArrowStyle::default()),
+        (true, style(ArrowKind::Stealth, ArrowSize::Small, ArrowSize::Large), true, style(ArrowKind::Oval, ArrowSize::Large, ArrowSize::Small)),
+    ];
+    let d = read_body(&format!("<w:p>{body}</w:p>"));
+    assert_eq!(ends(&d), expected);
+    let bytes = wordcraft_docx::write(&d).unwrap();
+    let mut xml = String::new();
+    let mut zip = zip::ZipArchive::new(std::io::Cursor::new(bytes.as_slice())).unwrap();
+    std::io::Read::read_to_string(&mut zip.by_name("word/document.xml").unwrap(), &mut xml).unwrap();
+    assert!(xml.contains(r#"<a:headEnd type="stealth" w="sm" len="lg"/>"#), "{xml}");
+    assert!(xml.contains(r#"<a:tailEnd type="diamond" w="lg" len="sm"/>"#), "{xml}");
+    assert_eq!(ends(&wordcraft_docx::read(&bytes).unwrap()), expected);
+}
+
 /// The right arrow's shapetype as Word writes it (ECMA-376 Part 4 `v:shapetype`, `o:spt` 13).
 const VML_RIGHT_ARROW_TYPE: &str = r#"<v:shapetype id="_x0000_t13" coordsize="21600,21600" o:spt="13" adj="16200,5400" path="m@0,l@0@1,0@1,0@2@0@2@0,21600,21600,10800xe"><v:stroke joinstyle="miter"/><v:formulas><v:f eqn="val #0"/><v:f eqn="val #1"/></v:formulas><v:path o:connecttype="custom"/></v:shapetype>"#;

@@ -3914,6 +4092,30 @@ fn equation_in_alternate_content_is_read() {
    assert!(!p.plain_text().contains("[picture]"));
 }

+/// A fill's `a:alpha` is its opacity: a translucent white wash over a picture stayed opaque and
+/// hid the picture.
+#[test]
+fn a_shape_fill_keeps_its_transparency() {
+    let fill =
+        r#"<a:prstGeom prst="rect"><a:avLst/></a:prstGeom><a:solidFill><a:srgbClr val="FFFFFF"><a:alpha val="30980"/></a:srgbClr></a:solidFill>"#;
+    let d = read_body(&format!("<w:p>{}</w:p>", anchored_wsp("Wash", 1270000, 635000, fill, "", "<wps:cNvSpPr/>")));
+    let transparency = |d: &Document| match &paras(d)[0].objects[0] {
+        InlineObject::Shape { fill: Some(wordcraft_doc::fill::Fill::Solid { color, transparency }), .. } => (Some(*color), *transparency),
+        o => panic!("{o:?}"),
+    };
+    const FILL_ALPHA: u32 = 30_980;
+    const ALPHA_SCALE: f32 = 100_000.0;
+    // Canonical Fill stores the percentage computed from opacity, including f32 rounding.
+    let expected = 100.0 - (FILL_ALPHA as f32 / ALPHA_SCALE) * 100.0;
+    assert_eq!(transparency(&d), (Some(Rgb(255, 255, 255)), expected));
+    let bytes = wordcraft_docx::write(&d).unwrap();
+    let parts = unzip(&bytes);
+    let xml = String::from_utf8_lossy(parts.get("word/document.xml").unwrap());
+    assert!(xml.contains(&format!("<a:alpha val=\"{FILL_ALPHA}\"/>")), "{xml}");
+    let again = wordcraft_docx::read(&bytes).unwrap();
+    assert_eq!(transparency(&again), (Some(Rgb(255, 255, 255)), expected));
+}
+
 /// #1500: gradient fills and transparency on shapes (the cases in the issue), from the shape's
 /// own properties, the theme's fill styles (`a:fillRef` 3 and 1003, as Word's cover pages use),
 /// a group's fill (`a:grpFill`), an outline gradient and VML's `v:fill`. Each is read as the
@@ -4110,3 +4312,62 @@ fn vml_textbox_style_anchor_and_fit() {
    assert_eq!(tb.body.anchor, wordcraft_doc::props::VAlign::Center);
    assert!(tb.body.auto_fit);
 }
+
+/// A VML horizontal rule (`o:hr`, a web page's `<hr>` pasted into Word) is read as one: the whole
+/// line when it has no width and no `o:hrpct`, a share of it (`o:hrpct`, tenths of a percent), or
+/// its own width (`o:hrpct="0"`), placed by `o:hralign`. It saves back as the same VML rule.
+#[test]
+fn vml_horizontal_rules_are_read_and_kept() {
+    use wordcraft_doc::connector::HorizontalRule;
+    use wordcraft_doc::props::Align;
+    let hr = |attrs: &str, style: &str| format!(r#"<w:p><w:r><w:pict><v:rect style="{style}" {attrs}/></w:pict></w:r></w:p>"#);
+    let body = [
+        hr(r#"o:hralign="center" o:hrstd="t" o:hr="t""#, "width:0;height:1.5pt"),
+        hr(r#"o:hrpct="500" o:hralign="right" o:hr="t""#, "width:0;height:1.5pt"),
+        hr(r#"o:hrpct="0" o:hralign="center" o:hr="t""#, "width:100pt;height:3pt"),
+        hr("", "width:100pt;height:3pt"),
+    ]
+    .concat();
+    let rules = |d: &Document| -> Vec<(Option<HorizontalRule>, f32)> {
+        paras(d)
+            .iter()
+            .filter_map(|p| p.objects.iter().find_map(|o| if let InlineObject::Shape { extra, w, .. } = o { Some((extra.hr, *w)) } else { None }))
+            .collect()
+    };
+    let d = read_body(&body);
+    let got = rules(&d);
+    assert_eq!(
+        got,
+        [
+            (Some(HorizontalRule { pct: 100.0, align: Align::Center, standard: true }), 0.0),
+            (Some(HorizontalRule { pct: 50.0, align: Align::Right, standard: false }), 0.0),
+            (Some(HorizontalRule { pct: 0.0, align: Align::Center, standard: false }), 100.0),
+            (None, 100.0),
+        ]
+    );
+    let again = wordcraft_docx::read(&wordcraft_docx::write(&d).unwrap()).unwrap();
+    assert_eq!(rules(&again)[..3], got[..3]);
+    // A rule's rotation and flips are kept.
+    let spin = |d: &Document| paras(d)[0].objects.iter().find_map(|o| o.frame()).map(|(_, _, f)| f.spin());
+    let d = read_body(&hr(r#"o:hrpct="500" o:hr="t""#, "width:0;height:1.5pt;rotation:45;flip:x y"));
+    assert_eq!(spin(&d), Some(wordcraft_geom::Spin::new(45.0, true, true)));
+    let again = wordcraft_docx::read(&wordcraft_docx::write(&d).unwrap()).unwrap();
+    assert_eq!(spin(&again), spin(&d));
+    // A see-through rule stays see-through.
+    let fill = |d: &Document| paras(d)[0].objects.iter().find_map(|o| if let InlineObject::Shape { fill, .. } = o { fill.clone() } else { None });
+    let d = read_body(
+        r##"<w:p><w:r><w:pict><v:rect style="width:0;height:1.5pt" o:hr="t" fillcolor="#ff0000"><v:fill opacity="0.25"/></v:rect></w:pict></w:r></w:p>"##,
+    );
+    let Some(wordcraft_doc::fill::Fill::Solid { transparency, .. }) = fill(&d) else { panic!("{:?}", fill(&d)) };
+    assert!((transparency - 75.0).abs() < 0.01, "{transparency}");
+    let again = wordcraft_docx::read(&wordcraft_docx::write(&d).unwrap()).unwrap();
+    assert_eq!(fill(&again), fill(&d));
+    // A positioned or hidden rule stays a plain shape, keeping its placement and visibility.
+    let body = [
+        hr(r#"o:hralign="center" o:hr="t""#, "position:absolute;margin-left:10pt;margin-top:20pt;width:100pt;height:2pt"),
+        hr(r#"o:hralign="center" o:hr="t""#, "visibility:hidden;width:0;height:2pt"),
+    ]
+    .concat();
+    let d = read_body(&body);
+    assert_eq!(rules(&d).iter().map(|r| r.0).collect::<Vec<_>>(), [None, None]);
+}
@@ -0,0 +1,57 @@
+//! #4696: Word's built-in heading styles have their outline level even when the file's
+//! `styles.xml` doesn't write `w:outlineLvl` (some producers leave it out). Word for Windows,
+//! opening such a file, reports `OutlineLevel` 1 and 2 for "heading 1" and "heading 2" (whatever
+//! their style ids) and body text for a custom style.
+use std::io::Write;
+use wordcraft_doc::Paragraph;
+
+const W: &str = "http://schemas.openxmlformats.org/wordprocessingml/2006/main";
+
+fn package(styles: &str, body: &str) -> Vec<u8> {
+    let root = r#"<?xml version="1.0" encoding="UTF-8"?><Relationships xmlns="http://schemas.openxmlformats.org/package/2006/relationships"><Relationship Id="rId1" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/officeDocument" Target="word/document.xml"/></Relationships>"#;
+    let rels = r#"<?xml version="1.0" encoding="UTF-8"?><Relationships xmlns="http://schemas.openxmlformats.org/package/2006/relationships"><Relationship Id="rId1" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/styles" Target="styles.xml"/></Relationships>"#;
+    let doc = format!(r#"<?xml version="1.0" encoding="UTF-8" standalone="yes"?><w:document xmlns:w="{W}"><w:body>{body}</w:body></w:document>"#);
+    let styles = format!(r#"<?xml version="1.0" encoding="UTF-8" standalone="yes"?><w:styles xmlns:w="{W}">{styles}</w:styles>"#);
+    let mut zw = zip::ZipWriter::new(std::io::Cursor::new(Vec::new()));
+    for (name, body) in
+        [("_rels/.rels", root), ("word/document.xml", doc.as_str()), ("word/_rels/document.xml.rels", rels), ("word/styles.xml", styles.as_str())]
+    {
+        zw.start_file(name, zip::write::SimpleFileOptions::default()).unwrap();
+        zw.write_all(body.as_bytes()).unwrap();
+    }
+    zw.finish().unwrap().into_inner()
+}
+
+fn para(style: &str, text: &str) -> String {
+    format!(r#"<w:p><w:pPr><w:pStyle w:val="{style}"/></w:pPr><w:r><w:t>{text}</w:t></w:r></w:p>"#)
+}
+
+fn levels(d: &wordcraft_doc::Document) -> Vec<Option<u8>> {
+    d.body.iter().filter_map(|b| b.as_para()).map(|p: &Paragraph| d.styles.resolve_para(&p.props).outline_level).collect()
+}
+
+#[test]
+fn built_in_heading_styles_have_their_outline_level_without_outline_lvl() {
+    let styles = r#"<w:style w:type="paragraph" w:default="1" w:styleId="Normal"><w:name w:val="Normal"/></w:style>
+        <w:style w:type="paragraph" w:styleId="Heading1"><w:name w:val="heading 1"/><w:basedOn w:val="Normal"/></w:style>
+        <w:style w:type="paragraph" w:styleId="Titolo2"><w:name w:val="heading 2"/><w:basedOn w:val="Normal"/></w:style>
+        <w:style w:type="paragraph" w:styleId="Heading9"><w:name w:val="Heading 9"/></w:style>
+        <w:style w:type="paragraph" w:styleId="Below"><w:name w:val="Below heading 2"/><w:basedOn w:val="Titolo2"/></w:style>
+        <w:style w:type="paragraph" w:customStyle="1" w:styleId="MyHead"><w:name w:val="My heading 3"/><w:basedOn w:val="Normal"/></w:style>
+        <w:style w:type="paragraph" w:styleId="Heading10"><w:name w:val="heading 10"/></w:style>
+        <w:style w:type="paragraph" w:customStyle="on" w:styleId="Fake4"><w:name w:val="heading 4"/></w:style>
+        <w:style w:type="paragraph" w:styleId="Heading3"><w:name w:val="heading 3"/><w:pPr><w:outlineLvl w:val="5"/></w:pPr></w:style>"#;
+    let body = ["Heading1", "Titolo2", "Heading9", "Below", "MyHead", "Heading10", "Fake4", "Heading3", "Normal"]
+        .iter()
+        .map(|s| para(s, "x"))
+        .collect::<String>();
+    let d = wordcraft_docx::read(&package(styles, &body)).unwrap();
+    // Heading 1, 2 and 9 by name; a style based on a heading inherits its level; a custom style,
+    // "heading 10", a custom style named "heading 4" (`w:customStyle="on"`) and Normal have none; a
+    // level the file gives is kept.
+    let want = vec![Some(0), Some(1), Some(8), Some(1), None, None, None, Some(5), None];
+    assert_eq!(levels(&d), want);
+    // The level survives a save and reopen.
+    let again = wordcraft_docx::read(&wordcraft_docx::write(&d).unwrap()).unwrap();
+    assert_eq!(levels(&again), want);
+}
@@ -1,8 +1,10 @@
+mod alt_chunks;
 mod bidi;
 mod bidi_runs;
 mod cell_margin_inheritance;
 mod char_units;
 mod citations;
+mod comment_save_cost;
 mod complex_script_inheritance;
 mod content_control_save_cost;
 mod content_controls;
@@ -13,14 +15,17 @@ mod east_asian_lang;
 mod east_asian_layout;
 mod fixtures;
 mod glossary;
+mod heading_levels;
 mod legacy_forms;
 mod ligatures;
 mod malformed;
+mod note_comments;
 mod passthrough;
 mod positional_tabs;
 mod privacy;
 mod roundtrip;
 mod row_property_exceptions;
+mod run_props;
 mod section_form_protection;
 mod section_page_number_type;
 mod section_text_direction;
@@ -28,6 +33,7 @@ mod section_valign;
 mod settings_merge;
 mod text_boxes;
 mod toc_ranges;
+mod undefined_style;
 mod vml_shapes;
 mod word_xml;
 mod wordml2003_write;
@@ -0,0 +1,68 @@
+//! Comments anchored inside footnotes and endnotes keep their ranges on read. All markup here is
+//! synthetic, written from ECMA-376 §17.13.4 and §17.11.
+
+use wordcraft_doc::para::{NoteKind, OBJ};
+use wordcraft_doc::{Document, InlineObject};
+
+use crate::fixtures::zip;
+
+const W_NS: &str = r#"xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main" xmlns:r="http://schemas.openxmlformats.org/officeDocument/2006/relationships""#;
+const ROOT_RELS: &str = r#"<Relationships xmlns="http://schemas.openxmlformats.org/package/2006/relationships"><Relationship Id="rId1" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/officeDocument" Target="word/document.xml"/></Relationships>"#;
+const DOC_RELS: &str = r#"<Relationships xmlns="http://schemas.openxmlformats.org/package/2006/relationships"><Relationship Id="rId1" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/footnotes" Target="footnotes.xml"/><Relationship Id="rId2" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/endnotes" Target="endnotes.xml"/><Relationship Id="rId3" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/comments" Target="comments.xml"/></Relationships>"#;
+
+fn note(tag: &str, mark: &str, comment: u32, text: &str) -> String {
+    format!(
+        r#"<w:{tag} w:id="1"><w:p><w:r><w:{mark}/></w:r><w:commentRangeStart w:id="{comment}"/><w:r><w:t xml:space="preserve"> {text}</w:t></w:r><w:commentRangeEnd w:id="{comment}"/><w:r><w:commentReference w:id="{comment}"/></w:r></w:p></w:{tag}>"#
+    )
+}
+
+fn read_doc() -> Document {
+    let doc = format!(
+        r#"<w:document {W_NS}><w:body><w:p><w:r><w:t>Body</w:t></w:r><w:r><w:footnoteReference w:id="1"/></w:r><w:r><w:endnoteReference w:id="1"/></w:r></w:p></w:body></w:document>"#
+    );
+    let footnotes = format!(r#"<w:footnotes {W_NS}>{}</w:footnotes>"#, note("footnote", "footnoteRef", 7, "Foot."));
+    let endnotes = format!(r#"<w:endnotes {W_NS}>{}</w:endnotes>"#, note("endnote", "endnoteRef", 8, "End."));
+    let comments = format!(
+        r#"<w:comments {W_NS}><w:comment w:id="7" w:author="Ann" w:initials="A"><w:p><w:r><w:t>On the footnote</w:t></w:r></w:p></w:comment><w:comment w:id="8" w:author="Bob" w:initials="B"><w:p><w:r><w:t>On the endnote</w:t></w:r></w:p></w:comment></w:comments>"#
+    );
+    let bytes = zip(&[
+        ("_rels/.rels", ROOT_RELS.as_bytes()),
+        ("word/document.xml", doc.as_bytes()),
+        ("word/_rels/document.xml.rels", DOC_RELS.as_bytes()),
+        ("word/footnotes.xml", footnotes.as_bytes()),
+        ("word/endnotes.xml", endnotes.as_bytes()),
+        ("word/comments.xml", comments.as_bytes()),
+    ]);
+    wordcraft_docx::read(&bytes).unwrap()
+}
+
+/// comments.xml has to be read before the notes: a note's `w:commentRangeStart` resolves its id
+/// against the comments already read, and was dropped when the notes came first.
+#[test]
+fn comment_ranges_inside_notes_are_kept() {
+    let d = read_doc();
+    let body = d.body[0].as_para().unwrap();
+    let refs: Vec<(NoteKind, u32)> = body
+        .objects
+        .iter()
+        .filter_map(|o| match o {
+            InlineObject::NoteRef { kind, id, .. } => Some((*kind, *id)),
+            _ => None,
+        })
+        .collect();
+    assert_eq!(refs.len(), 2, "{:?}", body.objects);
+    for ((kind, id), (author, text)) in refs.into_iter().zip([("Ann", " Foot."), ("Bob", " End.")]) {
+        let p = d.parts.get(&id).unwrap().blocks[0].as_para().unwrap();
+        let comment = match &p.objects[..] {
+            [InlineObject::NoteRef { kind: k, id: n, .. }, InlineObject::CommentStart { id: c }, InlineObject::CommentEnd { id: e }]
+                if *k == kind && *n == id && c == e =>
+            {
+                *c
+            }
+            o => panic!("{kind:?} {id}: {o:?}"),
+        };
+        assert_eq!(d.comments.get(&comment).unwrap().author, author);
+        assert_eq!(p.text.chars().filter(|c| *c == OBJ).count(), 3);
+        assert_eq!(p.plain_text(), text);
+    }
+}
@@ -443,3 +443,51 @@ fn embedded_fonts_load_and_save_when_the_package_spells_the_font_table_in_capita
    assert_eq!(fonts.len(), 1, "the font survives a save: {:?}", files.keys());
    assert_eq!(fonts[0].data, font_bytes);
 }
+
+#[test]
+fn comment_ids_keep_sparse_threads_reservations_and_missing_parts() {
+    use wordcraft_doc::{Comment, Document, Paragraph, Part, PartKind, para_block};
+    let mut doc = Document::from_text("Original thread fixture.");
+    // New IDs must skip the exact durable ID reserved by a later comment, even one whose
+    // missing part keeps it out of commentsIds.xml. Duplicate imported IDs are reassigned.
+    let rows = [
+        (3, None, Some(90), false, true),
+        (11, Some("5a1b2c3d"), Some(90), true, true),
+        (25, Some("5A1B2C3D"), Some(999), false, true),
+        (90, Some("10000001"), None, true, true),
+        (999, Some("10000002"), None, false, false),
+        (u32::MAX, Some("not-hex"), Some(3), false, true),
+    ];
+    for (id, durable, parent, resolved, has_part) in rows {
+        let part = id;
+        if has_part {
+            doc.parts.insert(
+                part,
+                Part {
+                    kind: PartKind::Comment,
+                    blocks: vec![para_block(Paragraph::with_text(&format!("Comment {id} β"), Default::default()))],
+                    ..Default::default()
+                },
+            );
+        }
+        doc.comments.insert(id, Comment { part, parent, resolved, durable_id: durable.map(str::to_string), ..Default::default() });
+    }
+    let files = save(&doc);
+    let (ids, _) = written_ids(&files);
+    assert_eq!(ids.iter().map(|(_, id)| id.as_str()).collect::<Vec<_>>(), ["10000003", "5A1B2C3D", "10000004", "10000001", "10000005"]);
+    let ex = text(&files, "word/commentsExtended.xml");
+    assert_eq!(ex.matches("<w15:commentEx ").count(), 5);
+    assert!(ex.contains(r#"w15:paraId="10000001" w15:paraIdParent="10000004" w15:done="0""#));
+    assert!(ex.contains(r#"w15:paraId="10000002" w15:paraIdParent="10000004" w15:done="1""#));
+    assert!(ex.contains(r#"w15:paraId="10000003" w15:done="0""#), "a missing parent part has no paragraph ID");
+    assert!(ex.contains(r#"w15:paraId="10000006" w15:paraIdParent="10000001" w15:done="0""#));
+    let back = wordcraft_docx::read(&wordcraft_docx::write(&doc).unwrap()).unwrap();
+    // Reader IDs need not match the sparse input IDs. Check the thread by authored text.
+    let comment = |text: &str| back.comments.iter().find(|(_, c)| back.plain_text(wordcraft_doc::StoryRef::Part(c.part)).trim() == text).unwrap();
+    let (root, _) = comment("Comment 90 β");
+    assert_eq!(comment("Comment 3 β").1.parent, Some(*root));
+    assert_eq!(comment("Comment 11 β").1.parent, Some(*root));
+    assert!(comment("Comment 11 β").1.resolved);
+    let (first, _) = comment("Comment 3 β");
+    assert_eq!(comment(&format!("Comment {} β", u32::MAX)).1.parent, Some(*first));
+}
@@ -89,6 +89,8 @@ fn every_char_prop_round_trips() {
        caps: Some(true),
        small_caps: Some(false),
        hidden: Some(true),
+        web_hidden: Some(true),
+        snap_to_grid: Some(false),
        spacing: Some(1.5),
        scale: Some(150.0),
        position: Some(3.0),
@@ -2267,6 +2269,39 @@ fn bibliography_sources_round_trip() {
    assert_bibliography_sources_round_trip(&bytes);
 }

+/// #4848: a corporate author saves as Word's `b:Corporate`, in place of a name list (a role holds
+/// one or the other), and reads back whole.
+#[test]
+fn a_corporate_author_round_trips() {
+    let mut d = Document::new();
+    d.sources.push(Source {
+        tag: "Wor20".into(),
+        kind: "report".into(),
+        corporate: "World Health Organization".into(),
+        title: "World report on hearing".into(),
+        year: "2020".into(),
+        editor: "Chadha, Shelly".into(),
+        ..Default::default()
+    });
+    d.sources.push(Source {
+        tag: "Both".into(),
+        author: "Rivera, Alex".into(),
+        corporate: "Harbor Guild, Inc.".into(),
+        title: "Shared Spaces".into(),
+        ..Default::default()
+    });
+    let bytes = wordcraft_docx::write(&d).expect("write");
+    let mut zip = zip::ZipArchive::new(std::io::Cursor::new(&bytes[..])).unwrap();
+    let mut item_xml = String::new();
+    std::io::Read::read_to_string(&mut zip.by_name("customXml/item1.xml").unwrap(), &mut item_xml).unwrap();
+    assert!(item_xml.contains("<b:Author><b:Author><b:Corporate>World Health Organization</b:Corporate></b:Author><b:Editor>"), "{item_xml}");
+    assert!(item_xml.contains("<b:Corporate>Harbor Guild, Inc.</b:Corporate>"), "{item_xml}");
+    assert!(!item_xml.contains("<b:Last>Rivera</b:Last>"), "the corporate author takes the person authors' place: {item_xml}");
+    let back = wordcraft_docx::read(&bytes).expect("read");
+    let got: Vec<(&str, &str, &str)> = back.sources.iter().map(|s| (s.corporate.as_str(), s.author.as_str(), s.editor.as_str())).collect();
+    assert_eq!(got, [("World Health Organization", "", "Chadha, Shelly"), ("Harbor Guild, Inc.", "", "")]);
+}
+
 fn assert_bibliography_parts(bytes: &[u8]) {
    let mut zip = zip::ZipArchive::new(std::io::Cursor::new(bytes)).unwrap();
    assert!(zip.by_name("customXml/item1.xml").is_ok());
@@ -0,0 +1,74 @@
+//! Run and style properties that must survive repeated DOCX saves.
+
+use std::io::{Read, Write};
+
+fn docx(body: &str, styles: &str) -> Vec<u8> {
+    let root = r#"<Relationships xmlns="http://schemas.openxmlformats.org/package/2006/relationships"><Relationship Id="rId1" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/officeDocument" Target="word/document.xml"/></Relationships>"#;
+    let rels = r#"<Relationships xmlns="http://schemas.openxmlformats.org/package/2006/relationships"><Relationship Id="rId1" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/styles" Target="styles.xml"/></Relationships>"#;
+    let document = format!(
+        r#"<w:document xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main"><w:body>{body}<w:sectPr/></w:body></w:document>"#
+    );
+    let styles = format!(r#"<w:styles xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main">{styles}</w:styles>"#);
+    let mut zip = zip::ZipWriter::new(std::io::Cursor::new(Vec::new()));
+    for (name, xml) in [
+        ("_rels/.rels", root.to_string()),
+        ("word/document.xml", document),
+        ("word/_rels/document.xml.rels", rels.to_string()),
+        ("word/styles.xml", styles),
+    ] {
+        zip.start_file(name, zip::write::SimpleFileOptions::default()).unwrap();
+        zip.write_all(xml.as_bytes()).unwrap();
+    }
+    zip.finish().unwrap().into_inner()
+}
+
+fn part(bytes: &[u8], name: &str) -> String {
+    let mut zip = zip::ZipArchive::new(std::io::Cursor::new(bytes)).unwrap();
+    let mut xml = String::new();
+    zip.by_name(name).unwrap().read_to_string(&mut xml).unwrap();
+    xml
+}
+
+#[test]
+fn run_and_style_snap_to_grid_and_web_hidden_survive_two_saves() {
+    let styles = r#"
+        <w:style w:type="character" w:styleId="On"><w:rPr><w:snapToGrid/><w:webHidden/></w:rPr></w:style>
+        <w:style w:type="character" w:styleId="Off"><w:rPr><w:snapToGrid w:val="0"/><w:webHidden w:val="0"/></w:rPr></w:style>
+    "#;
+    let body = r#"
+        <w:p>
+          <w:r><w:rPr><w:rStyle w:val="On"/></w:rPr><w:t>inherit</w:t></w:r>
+          <w:r><w:rPr><w:snapToGrid/><w:webHidden/></w:rPr><w:t>direct true</w:t></w:r>
+          <w:r><w:rPr><w:rStyle w:val="On"/><w:snapToGrid w:val="0"/><w:webHidden w:val="0"/></w:rPr><w:t>override</w:t></w:r>
+          <w:r><w:rPr><w:rStyle w:val="Off"/><w:vanish/></w:rPr><w:t>visible in print</w:t></w:r>
+          <w:r><w:t>absent</w:t></w:r>
+        </w:p>
+    "#;
+    let mut doc = wordcraft_docx::read(&docx(body, styles)).unwrap();
+    let p = doc.body.iter().find_map(|b| b.as_para()).unwrap();
+    assert_eq!(p.runs[0].props.snap_to_grid, None);
+    assert_eq!(p.runs[0].props.web_hidden, None);
+    assert_eq!(p.runs[1].props.snap_to_grid, Some(true));
+    assert_eq!(p.runs[1].props.web_hidden, Some(true));
+    assert_eq!(p.runs[2].props.snap_to_grid, Some(false));
+    assert_eq!(p.runs[2].props.web_hidden, Some(false));
+    assert_eq!(p.runs[3].props.hidden, Some(true));
+    assert_eq!(p.runs[3].props.web_hidden, None);
+    assert_eq!(p.runs[4].props.snap_to_grid, None);
+    assert_eq!(p.runs[4].props.web_hidden, None);
+    assert!(!doc.styles.resolve_char(None, &p.runs[0].props).hidden, "w:webHidden does not hide Print Layout text");
+    assert!(doc.styles.resolve_char(None, &p.runs[3].props).hidden, "w:vanish still controls hidden text");
+    for pass in 0..2 {
+        let out = wordcraft_docx::write(&doc).unwrap();
+        let style_xml = part(&out, "word/styles.xml");
+        assert!(style_xml.contains(r#"<w:snapToGrid/><w:webHidden/>"#), "pass {pass}: {style_xml}");
+        assert!(style_xml.contains(r#"<w:snapToGrid w:val="0"/><w:webHidden w:val="0"/>"#), "pass {pass}: {style_xml}");
+        let document_xml = part(&out, "word/document.xml");
+        assert!(document_xml.contains(r#"<w:snapToGrid w:val="0"/>"#), "pass {pass}: {document_xml}");
+        assert!(document_xml.contains(r#"<w:webHidden w:val="0"/>"#), "pass {pass}: {document_xml}");
+        assert!(document_xml.contains("<w:snapToGrid/><w:webHidden/>"), "pass {pass}: {document_xml}");
+        assert!(document_xml.contains("<w:vanish/>"), "pass {pass}: {document_xml}");
+        assert!(document_xml.contains("visible in print"));
+        doc = wordcraft_docx::read(&out).unwrap();
+    }
+}
@@ -0,0 +1,71 @@
+//! A paragraph whose `w:pStyle` names a style `styles.xml` doesn't define is formatted as Normal,
+//! as in Word, not with the document defaults alone (#5077). Pandoc writes footers as
+//! `<w:pStyle w:val="Footer"/>` without defining Footer.
+use std::io::Write;
+use wordcraft_doc::props::LineSpacing;
+use wordcraft_doc::{Block, Document, PartKind};
+
+const W: &str = "http://schemas.openxmlformats.org/wordprocessingml/2006/main";
+const R: &str = "http://schemas.openxmlformats.org/officeDocument/2006/relationships";
+
+fn package(normal_id: &str) -> Vec<u8> {
+    let root = r#"<?xml version="1.0" encoding="UTF-8"?><Relationships xmlns="http://schemas.openxmlformats.org/package/2006/relationships"><Relationship Id="rId1" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/officeDocument" Target="word/document.xml"/></Relationships>"#;
+    let doc = format!(
+        r#"<?xml version="1.0" encoding="UTF-8" standalone="yes"?><w:document xmlns:w="{W}" xmlns:r="{R}"><w:body><w:p><w:pPr><w:pStyle w:val="Footer"/></w:pPr><w:r><w:t>body</w:t></w:r></w:p><w:p><w:r><w:t>normal</w:t></w:r></w:p><w:sectPr><w:footerReference w:type="default" r:id="rId2"/></w:sectPr></w:body></w:document>"#
+    );
+    let footer = format!(
+        r#"<?xml version="1.0" encoding="UTF-8" standalone="yes"?><w:ftr xmlns:w="{W}"><w:p><w:pPr><w:pStyle w:val="Footer"/><w:jc w:val="center"/></w:pPr><w:r><w:t>1</w:t></w:r></w:p></w:ftr>"#
+    );
+    let styles = format!(
+        r#"<?xml version="1.0" encoding="UTF-8" standalone="yes"?><w:styles xmlns:w="{W}"><w:docDefaults><w:rPrDefault><w:rPr><w:sz w:val="24"/></w:rPr></w:rPrDefault><w:pPrDefault><w:pPr><w:spacing w:after="200"/></w:pPr></w:pPrDefault></w:docDefaults><w:style w:type="paragraph" w:default="1" w:styleId="{normal_id}"><w:name w:val="Normal"/><w:pPr><w:spacing w:before="20" w:after="40" w:line="259" w:lineRule="auto"/></w:pPr><w:rPr><w:sz w:val="26"/></w:rPr></w:style></w:styles>"#
+    );
+    let rels = r#"<?xml version="1.0" encoding="UTF-8"?><Relationships xmlns="http://schemas.openxmlformats.org/package/2006/relationships"><Relationship Id="rId1" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/styles" Target="styles.xml"/><Relationship Id="rId2" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/footer" Target="footer1.xml"/></Relationships>"#;
+    let mut zw = zip::ZipWriter::new(std::io::Cursor::new(Vec::new()));
+    for (name, body) in [
+        ("_rels/.rels", root),
+        ("word/document.xml", doc.as_str()),
+        ("word/_rels/document.xml.rels", rels),
+        ("word/styles.xml", styles.as_str()),
+        ("word/footer1.xml", footer.as_str()),
+    ] {
+        zw.start_file(name, zip::write::SimpleFileOptions::default()).unwrap();
+        zw.write_all(body.as_bytes()).unwrap();
+    }
+    zw.finish().unwrap().into_inner()
+}
+
+fn footer_para(d: &Document) -> &wordcraft_doc::Paragraph {
+    let part = d.parts.values().find(|p| p.kind == PartKind::Footer).expect("a footer");
+    match part.blocks.first().map(|b| &**b) {
+        Some(Block::Para(p)) => p,
+        _ => panic!("the footer starts with a paragraph"),
+    }
+}
+
+#[test]
+fn a_paragraph_naming_an_undefined_style_is_formatted_as_normal() {
+    // Also when the file's default paragraph style has another id (read as Normal).
+    for normal_id in ["Normal", "a"] {
+        let d = wordcraft_docx::read(&package(normal_id)).unwrap();
+        let Some(Block::Para(body)) = d.body.first().map(|b| &**b) else { panic!("a body paragraph") };
+        let Some(Block::Para(normal)) = d.body.get(1).map(|b| &**b) else { panic!("a second body paragraph") };
+        let normal_rp = d.styles.resolve_para(&normal.props);
+        assert_eq!((normal_rp.space_before, normal_rp.space_after), (1.0, 2.0), "{normal_id}");
+        for p in [body, footer_para(&d)] {
+            // The paragraph keeps the style it names, for the round trip.
+            assert_eq!(p.props.style.as_deref(), Some("Footer"));
+            let rp = d.styles.resolve_para(&p.props);
+            assert_eq!((rp.space_before, rp.space_after), (1.0, 2.0), "{normal_id}: Normal's spacing, not the defaults' 10 pt after");
+            assert_eq!(rp.line_spacing, LineSpacing::Multiple(259.0 / 240.0), "{normal_id}");
+            assert_eq!(d.styles.resolve_char(Some("Footer"), &Default::default()).size, 13.0, "{normal_id}");
+        }
+    }
+}
+
+#[test]
+fn an_undefined_style_is_written_back_as_it_was_named() {
+    let d = wordcraft_docx::read(&package("Normal")).unwrap();
+    let again = wordcraft_docx::read(&wordcraft_docx::write(&d).unwrap()).unwrap();
+    assert_eq!(footer_para(&again).props.style.as_deref(), Some("Footer"));
+    assert_eq!(again.styles.resolve_para(&footer_para(&again).props).space_after, 2.0);
+}
@@ -41,6 +41,9 @@ js-sys = "0.3"

 [target.'cfg(not(target_arch = "wasm32"))'.dependencies]
 getrandom = { workspace = true }
+# Language packs (CP4.3): downloaded, verified and unpacked by the suite's font store.
+craft-font-store = { workspace = true }
+craft-font-catalog = { workspace = true }

 [target.'cfg(unix)'.dependencies]
 # O_NONBLOCK, so a path swapped for a named pipe can't block `open` (#3666).
@@ -28,6 +28,7 @@ pub mod moves;
 pub mod objects;
 pub mod options;
 pub mod outline;
+pub mod packs;
 pub mod page;
 pub mod para;
 pub mod paste;
@@ -84,6 +85,7 @@ pub fn registry() -> Registry {
    v.extend(review::specs());
    v.extend(file::specs());
    v.extend(options::specs());
+    v.extend(packs::specs());
    v.extend(design::specs());
    v.extend(references::specs());
    v.extend(fields::specs());
@@ -2,6 +2,7 @@

 use serde_json::Value;
 use wordcraft_doc::{Pos, StoryRef};
+use wordcraft_layout::ViewMode;

 use super::{parse_pos, sel_result};
 use crate::{CmdError, CmdResult, CommandSpec, Selection, Session, p};
@@ -254,10 +255,24 @@ fn line(s: &mut Session, v: &Value, home: bool) -> CmdResult {
    sel_result(s)
 }

+/// Page Up (`dir < 0`) / Page Down: the same place on the page before or after, or in the views
+/// that are one long page, the line a printed page's text above or below.
 fn page(s: &mut Session, v: &Value, dir: i32) -> CmdResult {
    let ext = extend(v);
    let l = s.layout();
    let from = s.sel.focus.clone();
+    // Web Layout, Draft and Outline lay the document out as one long page (#5290).
+    if !s.view.read_mode && matches!(s.view.mode, ViewMode::Web | ViewMode::Draft | ViewMode::Outline) {
+        // A selection can end in text a collapsed outline heading hides: page from where it shows.
+        let at = if l.caret_on(&from, s.page_hint).is_none() { super::outline::shown_pos(s, &from, false) } else { None };
+        let at = at.unwrap_or_else(|| from.clone());
+        let Some(c) = l.caret_on(&at, s.page_hint) else { return sel_result(s) };
+        let page_h = l.pages.get(c.page).map_or(0.0, |p| p.h);
+        let y = (c.top + 1.0 + dir as f32 * page_step(s, &at)).min(page_h).max(0.0);
+        let to = l.line_toward(&at, s.page_hint, c.x, y, dir).unwrap_or(from);
+        apply(s, to, ext);
+        return sel_result(s);
+    }
    let Some(c) = l.caret_on(&from, s.page_hint) else { return sel_result(s) };
    let np = if dir < 0 { c.page.saturating_sub(1) } else { (c.page + 1).min(l.pages.len().saturating_sub(1)) };
    let to = l.hit(np, c.x, c.top + 1.0, from.story).unwrap_or(from);
@@ -266,6 +281,16 @@ fn page(s: &mut Session, v: &Value, dir: i32) -> CmdResult {
    sel_result(s)
 }

+/// How far Page Up/Down move in the continuous views: the height of the text area of the
+/// section `at` is in (the first section when `at` isn't in the body), at least an inch.
+fn page_step(s: &Session, at: &Pos) -> f32 {
+    let block = if at.story == StoryRef::Body { at.path.0.first().map_or(0, |&i| i as usize) } else { 0 };
+    let sections = s.doc.sections();
+    let sect = sections.iter().find(|(end, _)| *end >= block).or(sections.last()).map(|(_, p)| *p);
+    let body = sect.map_or(0.0, |p| p.page_h - p.margin_top.abs() - p.margin_bottom.abs());
+    if body.is_finite() { body.max(72.0) } else { 72.0 }
+}
+
 fn set(s: &mut Session, v: &Value) -> CmdResult {
    let ext = extend(v);
    let to = if let Some(pv) = v.get("pos") {
@@ -273,8 +298,9 @@ fn set(s: &mut Session, v: &Value) -> CmdResult {
    } else if let (Some(pg), Some(x), Some(y)) = (p::u64(v, "page"), p::f32(v, "x"), p::f32(v, "y")) {
        let story = super::story_param(s, v);
        let l = s.layout();
-        s.page_hint = pg as usize;
-        l.hit(pg as usize, x, y, story).ok_or_else(|| CmdError::Params("no text on that page".into()))?
+        let page = usize::try_from(pg).unwrap_or(usize::MAX);
+        s.page_hint = page;
+        l.hit(page, x, y, story).ok_or_else(|| CmdError::Params("no text on that page".into()))?
    } else {
        return Err(CmdError::Params("`pos` or `page`/`x`/`y` required".into()));
    };
@@ -1,5 +1,5 @@
 use super::generated::page_of;
-use super::{CharProps, CmdError, CmdResult, InlineObject, Paragraph, Pos, Selection, Session, StoryRef, Value, delete_selection, json, p};
+use super::{CharProps, CmdError, CmdResult, Document, InlineObject, Paragraph, Pos, Selection, Session, StoryRef, Value, delete_selection, json, p};

 pub(super) fn cross_ref(s: &mut Session, v: &Value) -> CmdResult {
    let to = p::str(v, "to").unwrap_or("heading");
@@ -77,13 +77,19 @@ pub(super) fn caption_label(p: &Paragraph, text: &str) -> Option<String> {
    (!label.is_empty() && label.chars().count() <= 40).then_some(label)
 }

+/// Whether `p` is a caption: its style is Caption or one based on it, as a caption restyled with a
+/// style of its own (a `Table Caption` based on Caption) still is (#4411).
+pub(super) fn is_caption(doc: &Document, p: &Paragraph) -> bool {
+    p.props.style.as_deref().is_some_and(|id| id == "Caption" || doc.styles.chain(id).iter().any(|s| s.id == "Caption"))
+}
+
 /// The caption paragraphs of the body: (text, position, label).
 fn captions(s: &Session) -> Vec<(String, Pos, Option<String>)> {
    s.doc
        .para_paths(StoryRef::Body)
        .into_iter()
        .filter_map(|path| {
-            let p = s.doc.para(StoryRef::Body, &path).filter(|p| p.props.style.as_deref() == Some("Caption"))?;
+            let p = s.doc.para(StoryRef::Body, &path).filter(|p| is_caption(&s.doc, p))?;
            let text = p.plain_text();
            let label = caption_label(p, &text);
            Some((text, Pos { story: StoryRef::Body, path, off: 0 }, label))
@@ -125,7 +131,7 @@ pub fn ref_targets(s: &Session, to: &str) -> Vec<(String, Pos)> {
            };
            for path in s.doc.para_paths(StoryRef::Body) {
                if let Some(p) = s.doc.para(StoryRef::Body, &path)
-                    && p.props.style.as_deref() == Some("Caption")
+                    && is_caption(&s.doc, p)
                    && p.plain_text().starts_with(label)
                {
                    targets.push((p.plain_text(), Pos { story: StoryRef::Body, path: path.clone(), off: 0 }));
@@ -1,10 +1,10 @@
-use super::cross_refs::caption_label;
+use super::cross_refs::{caption_label, is_caption};
 use super::render::entry;
 use super::sources::bib_order;
 use super::styles::style;
 use super::{
-    Block, CharProps, CmdError, CmdResult, FieldCode, InlineObject, Paragraph, Path, Pos, Session, SortKey, StoryRef, TabAlign, TabLeader, TabStop,
-    Value, delete_selection, heading_letter, p, sel_result, sort_key,
+    Block, CharProps, CmdError, CmdResult, Document, FieldCode, InlineObject, Paragraph, Path, Pos, Session, SortKey, StoryRef, TabAlign, TabLeader,
+    TabStop, Value, delete_selection, heading_letter, p, sel_result, sort_key,
 };

 /// The TOC field for `references.tableOfFigures` (ECMA-376 §17.16.5.68): `\c "<label>"` lists the
@@ -86,8 +86,8 @@ fn figures_label(instr: &str) -> Option<String> {

 /// Whether `p` is a caption numbered by SEQ identifier `ident` (any case, as Word matches it). A
 /// caption typed by hand, without a SEQ field, goes by its label.
-fn captioned_as(p: &Paragraph, ident: &str) -> bool {
-    if p.props.style.as_deref() != Some("Caption") {
+fn captioned_as(doc: &Document, p: &Paragraph, ident: &str) -> bool {
+    if !is_caption(doc, p) {
        return false;
    }
    let seq = p.objects.iter().find_map(|o| match o {
@@ -256,7 +256,7 @@ fn entries_for(s: &mut Session, kind: &str) -> Vec<(String, bool)> {
    for path in s.doc.para_paths(StoryRef::Body) {
        let Some(p) = s.doc.para(StoryRef::Body, &path) else { continue };
        if let Some(ident) = &figures {
-            if captioned_as(p, ident) {
+            if captioned_as(&s.doc, p, ident) {
                let text = if bare { caption_body(p, &ident.replace('_', " ")) } else { p.plain_text() };
                marks.push((text, Pos { story: StoryRef::Body, path: path.clone(), off: 0 }));
            }
@@ -280,7 +280,7 @@ fn entries_for(s: &mut Session, kind: &str) -> Vec<(String, bool)> {
        for path in s.doc.para_paths(StoryRef::Body) {
            let Some(p) = s.doc.para(StoryRef::Body, &path) else { continue };
            if let Some(ident) = &figures {
-                if captioned_as(p, ident) {
+                if captioned_as(&s.doc, p, ident) {
                    v.push(Pos { story: StoryRef::Body, path: path.clone(), off: 0 });
                }
                continue;
@@ -1,6 +1,12 @@
 use super::Source;
 use super::styles::{Cite, Name, Names, style};

+/// A source's corporate author, when it has one: written as it is in place of the person names
+/// (Word's Corporate Author, #4848).
+pub(super) fn corporate(src: &Source) -> Option<&str> {
+    Some(src.corporate.trim()).filter(|c| !c.is_empty())
+}
+
 pub(super) fn authors(a: &str) -> Vec<(String, String)> {
    a.split(';')
        .map(str::trim)
@@ -110,12 +116,13 @@ pub fn cite(src: &Source, style_name: &str, n: usize, pages: &str) -> String {
    let st = style(style_name);
    let au = authors(&src.author);
    let lasts: Vec<&str> = au.iter().map(|a| a.0.as_str()).collect();
-    let who = match lasts.as_slice() {
-        [] => src.title.clone(),
-        [one] => one.to_string(),
-        [first, ..] if lasts.len() >= st.et_al_from.max(2) => format!("{first} et al."),
-        [a, b] => format!("{a} {} {b}", st.and),
-        [init @ .., z] => format!("{} {} {z}", init.join(", "), st.and),
+    let who = match (corporate(src), lasts.as_slice()) {
+        (Some(c), _) => c.to_string(),
+        (None, []) => src.title.clone(),
+        (None, [one]) => one.to_string(),
+        (None, [first, ..]) if lasts.len() >= st.et_al_from.max(2) => format!("{first} et al."),
+        (None, [a, b]) => format!("{a} {} {b}", st.and),
+        (None, [init @ .., z]) => format!("{} {} {z}", init.join(", "), st.and),
    };
    match st.cite {
        Cite::AuthorPage if pages.is_empty() => format!("({who})"),
@@ -148,7 +155,7 @@ pub fn entry(src: &Source, style_name: &str, n: usize) -> String {
    let field = |key: &str| -> String {
        match key {
            "n" => n.to_string(),
-            "names" => name_list(&au, &st.names),
+            "names" => corporate(src).map_or_else(|| name_list(&au, &st.names), str::to_string),
            "year" if src.year.is_empty() => "n.d.".into(),
            "year" => src.year.clone(),
            "title" => src.title.clone(),
@@ -1,5 +1,5 @@
 use super::generated::update_generated;
-use super::render::{authors, cite};
+use super::render::{authors, cite, corporate};
 use super::styles::{CiteStyle, Order, style};
 use super::{CmdError, CmdResult, Document, InlineObject, Selection, Session, Source, StoryRef, Value, delete_selection, json, p, sort_key};

@@ -14,18 +14,19 @@ fn auto_tag(doc: &Document, src: &Source) -> String {
    (1u32..).map(|n| format!("{base}{n}")).find(|t| !taken(t)).unwrap_or(base)
 }

-/// The author of a source for matching untagged entries: the editor when there is no author.
+/// The author of a source for matching untagged entries: the corporate author (which takes the
+/// author's place when a source is saved), else the author, else the editor.
 #[cfg(not(target_arch = "wasm32"))]
 fn by_author(x: &Source) -> &str {
-    if x.author.is_empty() { x.editor.as_str() } else { x.author.as_str() }
+    [x.corporate.trim(), x.author.as_str(), x.editor.as_str()].into_iter().find(|w| !w.is_empty()).unwrap_or_default()
 }

 /// The stem of a new source's tag, before `1`, `2`… are added while it is taken: the first three
-/// alphanumerics of the first author's name (nothing of the author's, `Src`) and the last two
-/// digits of the year.
+/// alphanumerics of the first author's name or the corporate author (nothing of the author's,
+/// `Src`) and the last two digits of the year.
 fn auto_tag_base(src: &Source) -> String {
-    let name: String =
-        authors(&src.author).first().map(|x| x.0.clone()).unwrap_or_default().chars().filter(|c| c.is_alphanumeric()).take(3).collect();
+    let first = corporate(src).map(str::to_string).or_else(|| authors(&src.author).first().map(|x| x.0.clone())).unwrap_or_default();
+    let name: String = first.chars().filter(|c| c.is_alphanumeric()).take(3).collect();
    let name = if name.is_empty() { "Src".to_string() } else { name };
    let digits: Vec<char> = src.year.chars().filter(char::is_ascii_digit).collect();
    let year: String = digits.get(digits.len().saturating_sub(2)..).unwrap_or_default().iter().collect();
@@ -184,8 +185,13 @@ fn cited_tags(doc: &Document) -> Vec<String> {
    out
 }

+/// A source's place in an author-sorted bibliography: the corporate author, else the first
+/// author's surname, else the title.
 fn author_key(src: &Source) -> String {
-    authors(&src.author).first().map(|a| a.0.to_lowercase()).unwrap_or_else(|| src.title.to_lowercase())
+    corporate(src)
+        .map(str::to_lowercase)
+        .or_else(|| authors(&src.author).first().map(|a| a.0.to_lowercase()))
+        .unwrap_or_else(|| src.title.to_lowercase())
 }

 /// Indices into `doc.sources` in bibliography order: the cited sources (every source while
@@ -103,8 +103,10 @@ pub static STYLES: [CiteStyle; 12] = [
        et_al_from: 3,
        order: Order::Author,
        names: names(Name::LastInitials, Name::LastInitials, ", ", ", & ", ", & "),
-        book: "⟦{names} ⟧({year}). {title}.⟦ {publisher}.⟧⟦ {url}⟧",
-        article: "⟦{names} ⟧({year}). {title}. {journal}⟦, {volume}⟧⟦, {pages}⟧.⟦ {url}⟧",
+        // The names end with a full stop: an initial's, or one added after a group author or a
+        // name without initials ("World Health Organization. (2021).", #4848).
+        book: "⟦{names}. ⟧({year}). {title}.⟦ {publisher}.⟧⟦ {url}⟧",
+        article: "⟦{names}. ⟧({year}). {title}. {journal}⟦, {volume}⟧⟦, {pages}⟧.⟦ {url}⟧",
        bib_title: "References",
    },
    CiteStyle {
@@ -18,6 +18,49 @@ fn citations_and_bibliography() {
    assert!(s.doc.plain_text(StoryRef::Body).contains("[1]"));
 }

+/// #4848: a corporate author is cited and listed as written, in every style: never turned into
+/// a surname and initials ("Organization, W. H."), never left out for the title. Its tag and its
+/// place in an author-sorted list come from the name too.
+#[test]
+fn a_corporate_author_is_cited_and_listed_as_written() {
+    let mut s = Session::new(wordcraft_doc::Document::new());
+    s.run("text.insert", &json!({"text": "Hearing loss is common "})).unwrap();
+    let who = "World Health Organization";
+    s.run("references.citation", &json!({"source": {"kind": "report", "corporate": who, "title": "World report on hearing", "year": "2021", "publisher": "WHO Press", "city": "Geneva"}}))
+        .unwrap();
+    s.run("text.insert", &json!({"text": " and rising "})).unwrap();
+    s.run("references.citation", &json!({"source": {"author": "Adams, Kim", "title": "Quiet Rooms", "year": "2019"}})).unwrap();
+    s.run("text.newParagraph", &json!({})).unwrap();
+    s.run("references.bibliography", &json!({})).unwrap();
+    assert_eq!(s.doc.sources[0].tag, "Wor21", "the tag starts with the corporate name");
+    let t = s.doc.plain_text(StoryRef::Body);
+    assert!(t.contains(&format!("({who}, 2021)")), "{t}");
+    assert!(t.contains(&format!("{who}. (2021). World report on hearing. WHO Press.")), "{t}");
+    // Sorted by the corporate name: Adams before World.
+    let adams = t.find("Adams, K. (2019)").unwrap_or(usize::MAX);
+    let world = t.find(&format!("{who}. (2021)")).unwrap_or(0);
+    assert!(adams < world, "{t}");
+    for style in [
+        "MLA",
+        "Chicago",
+        "GB/T 7714",
+        "GOST (name sort)",
+        "GOST (title sort)",
+        "ISO 690 (author-date)",
+        "ISO 690 (numerical)",
+        "Harvard (Anglia)",
+        "Turabian",
+        "IEEE",
+        "SIST02",
+    ] {
+        s.run("references.citationStyle", &json!({"style": style})).unwrap();
+        let t = s.doc.plain_text(StoryRef::Body);
+        let entry = t.lines().find(|l| l.contains("World report on hearing")).unwrap_or_default();
+        assert!(entry.contains(who), "{style}: {entry}");
+        assert!(!entry.contains("Organization, W") && !entry.contains("ORGANIZATION, W"), "{style}: {entry}");
+    }
+}
+
 /// Updating fields in a document without generated lists leaves its styles alone: a new
 /// style would make the next layout start over from nothing.
 #[test]
@@ -162,6 +205,49 @@ fn caption_labels_do_not_need_a_digit() {
    assert!(s.doc.plain_text(StoryRef::Body).ends_with("See Photo Plate I"), "{}", s.doc.plain_text(StoryRef::Body));
 }

+/// #4411: captions restyled with a style based on Caption, directly (`Caption Table`) or through
+/// another (`Caption Table Wide`), are still captions after a DOCX save and reopen: every `tableX`
+/// caption is a cross-reference target and in the table of figures, and a Table caption is a
+/// Table target. Captions in a style not based on Caption are not, nor are their labels.
+#[test]
+fn captions_in_a_style_based_on_caption() {
+    let mut s = Session::new(wordcraft_doc::Document::from_text("T1\nT2\nT3\nT4\nT5\nNote\nGrid\nStone\nSee "));
+    let caption = |s: &mut Session, text: &str, label: &str, title: &str| {
+        s.run("select.text", &json!({"text": text})).unwrap();
+        s.run("references.caption", &json!({"label": label, "text": title})).unwrap();
+    };
+    for k in 1..=5 {
+        caption(&mut s, &format!("T{k}"), "tableX", &format!("Row {k}"));
+    }
+    caption(&mut s, "Note", "tableX", "Aside");
+    caption(&mut s, "Grid", "Table", "Grid");
+    caption(&mut s, "Stone", "Plate", "Stone");
+    s.run("styles.create", &json!({"name": "Caption Table", "basedOn": "Caption", "fromSelection": false})).unwrap();
+    s.run("styles.create", &json!({"name": "Caption Table Wide", "basedOn": "Caption Table", "fromSelection": false})).unwrap();
+    s.run("styles.create", &json!({"name": "Aside", "fromSelection": false})).unwrap();
+    let style = |s: &Session, name: &str| s.doc.styles.find(name).map(|st| st.id.clone());
+    let (table, wide, aside) = (style(&s, "Caption Table"), style(&s, "Caption Table Wide"), style(&s, "Aside"));
+    for path in s.doc.para_paths(StoryRef::Body) {
+        let p = s.doc.para_mut(StoryRef::Body, &path).unwrap();
+        let text = p.plain_text();
+        p.props.style = match text.get(..8).unwrap_or_default() {
+            "tableX 1" | "tableX 2" => table.clone(),
+            "tableX 3" | "Table 1:" => wide.clone(),
+            "tableX 6" | "Plate 1:" => aside.clone(),
+            _ => continue,
+        };
+    }
+    let bytes = wordcraft_docx::write(&s.doc).expect("docx write");
+    let mut s = Session::new(wordcraft_docx::read(&bytes).expect("docx read"));
+    let want: Vec<String> = (1..=5).map(|k| format!("tableX {k}: Row {k}")).collect();
+    assert_eq!(s.run("insert.crossReference", &json!({"to": "label:tableX"})).unwrap(), json!(want));
+    assert_eq!(s.run("insert.crossReference", &json!({"to": "table"})).unwrap(), json!(["Table 1: Grid"]));
+    assert_eq!(caption_labels(&s), ["tableX", "Table"]);
+    s.run("caret.docEnd", &json!({})).unwrap();
+    s.run("references.tableOfFigures", &json!({"label": "tableX", "pageNumbers": false})).unwrap();
+    assert_eq!(list_entries(&s).into_iter().map(|(t, _)| t).collect::<Vec<_>>(), want);
+}
+
 /// The entries of every generated list, in order, with their last tab stop's leader.
 fn list_entries(s: &Session) -> Vec<(String, Option<TabLeader>)> {
    s.doc
@@ -180,6 +180,8 @@ pub(crate) fn dispatch(s: &mut Session, id: &str, mutates: bool, run: fn(&mut Se
        // Whole cells: table commands take the rectangle between the corners, and Tab moves on
        // from it without clearing it, as in Word.
        _ if cells && (id.starts_with("table.") || matches!(id, "text.tab" | "text.backTab")) => run(s, v),
+        // Copy and Cut of whole cells take a table of them (#1744).
+        "edit.copy" | "edit.cut" if cells => run(s, v),
        "edit.copy" => copy(s, &segs),
        "edit.cut" => {
            let r = copy(s, &segs)?;
@@ -48,10 +48,10 @@ fn scan(s: &Session) -> (HashMap<u32, Pos>, Vec<Pos>, Vec<Pos>) {
    let (mut ids, mut conns, mut groups) = (HashMap::new(), Vec::new(), Vec::new());
    for path in s.doc.para_paths(StoryRef::Body) {
        let Some(para) = s.doc.para(StoryRef::Body, &path) else { continue };
-        for off in para.object_offsets() {
+        for (off, obj) in para.objects_with_offsets() {
            let pos = Pos { story: StoryRef::Body, path: path.clone(), off };
-            match para.object_at(off) {
-                Some(InlineObject::Shape { kind, extra, float, .. }) => {
+            match obj {
+                InlineObject::Shape { kind, extra, float, .. } => {
                    if extra.id != 0 {
                        ids.entry(extra.id).or_insert(pos.clone());
                    }
@@ -59,7 +59,7 @@ fn scan(s: &Session) -> (HashMap<u32, Pos>, Vec<Pos>, Vec<Pos>) {
                        conns.push(pos);
                    }
                }
-                Some(InlineObject::Group { children, .. })
+                InlineObject::Group { children, .. }
                    if children.iter().any(|c| matches!(&c.obj, InlineObject::Shape { kind, extra, .. } if kind.is_connector() && (extra.start.is_some() || extra.end.is_some()))) =>
                {
                    groups.push(pos)
@@ -91,10 +91,11 @@ pub fn reroute(s: &mut Session) -> bool {
        s.touch();
    }
    let layout = s.layout();
+    let objects = layout.object_index();
    let site = |e: Option<ConnEnd>, page: usize| -> Option<(f32, f32)> {
        let e = e?;
        let target = ids.get(&e.id)?;
-        let hit = layout.object(target, page)?;
+        let hit = objects.object(target, page)?;
        let kind = match s.doc.para_at(target)?.object_at(target.off)? {
            InlineObject::Shape { kind, .. } => *kind,
            _ => return None,
@@ -103,7 +104,7 @@ pub fn reroute(s: &mut Session) -> bool {
    };
    let mut plans = Vec::new();
    for pos in conns {
-        let Some(hit) = layout.object(&pos, s.page_hint) else { continue };
+        let Some(hit) = objects.object(&pos, s.page_hint) else { continue };
        let Some(InlineObject::Shape { extra, float, .. }) = s.doc.para_at(&pos).and_then(|p| p.object_at(pos.off)) else { continue };
        let r = hit.rect;
        let (s0, e0) = ends(r.x, r.y, r.w, r.h, float.flip_h, float.flip_v);
@@ -313,6 +314,49 @@ mod tests {
        }
    }

+    /// Drawing commands must not search every page again for each glued connector.
+    #[test]
+    fn rerouting_many_pages_does_not_rescan_all_objects_per_connector() {
+        use wordcraft_doc::{Document, Paragraph, para_block};
+        let mut doc = Document::new();
+        doc.body = (0..8000u32)
+            .map(|i| {
+                let mut p = Paragraph::default();
+                p.props.page_break_before = Some(i > 0);
+                let id = i * 2 + 1;
+                for (kind, x, extra) in [
+                    (ShapeKind::Rectangle, 100.0, ShapeExtra { id, ..Default::default() }),
+                    (ShapeKind::Ellipse, 300.0, ShapeExtra { id: id + 1, ..Default::default() }),
+                    (
+                        ShapeKind::ElbowConnector,
+                        0.0,
+                        ShapeExtra { start: Some(ConnEnd { id, site: 3 }), end: Some(ConnEnd { id: id + 1, site: 2 }), ..Default::default() },
+                    ),
+                ] {
+                    let float = Float { wrap: Wrap::InFrontOfText, h_rel: Anchor::Page, v_rel: Anchor::Page, x, y: 200.0, ..Default::default() };
+                    p.insert_object(p.len(), shape(kind, extra, float), &Default::default()).unwrap();
+                }
+                para_block(p)
+            })
+            .collect();
+        let mut s = Session::new(doc);
+        s.view.proofing = false;
+        s.page_hint = 0;
+        assert_eq!(s.layout().pages.len(), 8000);
+        let started = std::time::Instant::now();
+        assert!(reroute(&mut s));
+        let elapsed = started.elapsed();
+        eprintln!("8000-page reroute: {elapsed:?}");
+        assert!(elapsed < std::time::Duration::from_secs(5), "reroute took {elapsed:?}");
+        for path in s.doc.para_paths(StoryRef::Body) {
+            let para = s.doc.para(StoryRef::Body, &path).unwrap();
+            let InlineObject::Shape { w, h, float, .. } = para.object_at(6).unwrap() else { panic!("connector") };
+            assert_eq!((*w, *h, float.x, float.y), (160.0, 0.0, 140.0, 210.0));
+        }
+        s.touch();
+        assert!(!reroute(&mut s), "rerouting must settle after refreshing the layout");
+    }
+
    /// The per-case shape/geometry of one scaled-group reroute case.
    struct ScaledGroupSpec {
        w: f32,
@@ -2,7 +2,7 @@

 use serde_json::{Value, json};
 use wordcraft_doc::edit::Fragment;
-use wordcraft_doc::{Pos, StoryRef};
+use wordcraft_doc::{Path, Pos, StoryRef};

 use super::{delete_selection, find_pattern, pos_json, sel_result};
 use crate::{CmdError, CmdResult, CommandSpec, Selection, Session, p};
@@ -27,10 +27,16 @@ fn undo_to(s: &mut Session, v: &Value) -> CmdResult {
    Ok(r)
 }

-fn has_sel(s: &Session) -> Option<&'static str> {
+/// Something the Spike can collect: text (it doesn't take empty cells).
+fn has_text_sel(s: &Session) -> Option<&'static str> {
    if s.sel.is_collapsed() { Some("nothing is selected") } else { None }
 }

+/// Something to cut: text, or whole table cells (an empty cell's selection has no length, #1744).
+fn has_sel(s: &Session) -> Option<&'static str> {
+    if s.sel.is_collapsed() && s.cell_range().is_none() { Some("nothing is selected") } else { None }
+}
+
 pub fn specs() -> Vec<CommandSpec> {
    vec![
        CommandSpec::new("edit.undo", "Undo", "Quick Access Toolbar", |s, _| {
@@ -63,7 +69,7 @@ pub fn specs() -> Vec<CommandSpec> {
        CommandSpec::new("edit.copy", "Copy", "Home › Clipboard", copy).key("Mod+C / Mod+Insert").pure(),
        // Word's Spike (Ctrl+F3, Ctrl+Shift+F3; ⌘ on the Mac): the AutoText entry "Spike", so Quick
        // Parts and AutoText insert it without emptying it, as in Word.
-        CommandSpec::new("edit.spike", "Spike", "Editing", spike).key("Mod+F3").when(has_sel),
+        CommandSpec::new("edit.spike", "Spike", "Editing", spike).key("Mod+F3").when(has_text_sel),
        CommandSpec::new("edit.insertSpike", "Insert Spike", "Editing", insert_spike).key("Mod+Shift+F3").when(|s| {
            if s.math.is_some() {
                Some("leave the equation first")
@@ -167,11 +173,25 @@ pub fn specs() -> Vec<CommandSpec> {
 }

 fn copy(s: &mut Session, _: &Value) -> CmdResult {
+    let whole = super::table::selected_table(s);
+    copy_with(s, whole.as_ref())
+}
+
+/// Copy, `whole` being the table the selection covers whole, if it does.
+fn copy_with(s: &mut Session, whole: Option<&Path>) -> CmdResult {
    let (a, b) = s.sel.ordered();
-    if a == b {
-        return Ok(json!({"text": ""}));
-    }
-    let f = s.doc.copy_range(&a, &b);
+    // Whole table cells selected copy as a table, even empty ones (their selection has no
+    // length): the whole table, or a table of just the selected rows or cells (#1744).
+    let table = match (whole, s.cell_range()) {
+        (Some(tp), _) => s.doc.copy_block(a.story, tp),
+        (None, Some(r)) => s.doc.copy_table_cells(r.story, &r.table, r.rows, r.cols),
+        (None, None) => None,
+    };
+    let f = match table {
+        Some(f) => f,
+        None if a == b => return Ok(json!({"text": ""})),
+        None => s.doc.copy_range(&a, &b),
+    };
    s.clipboard_text = f.clipboard_text();
    s.clip_history.push(&f, &s.clipboard_text);
    s.clipboard = Some(f);
@@ -200,8 +220,26 @@ pub(crate) fn copy_result(s: &mut Session) -> Value {
    r
 }

-fn cut(s: &mut Session, v: &Value) -> CmdResult {
-    let r = copy(s, v)?;
+fn cut(s: &mut Session, _: &Value) -> CmdResult {
+    let whole = super::table::selected_table(s);
+    let r = copy_with(s, whole.as_ref())?;
+    // A whole table selected: Cut removes the table, as Delete Table does (#1744). With Track
+    // Changes on, the cut below marks its text deleted (a tracked cut may become a move).
+    if !s.doc.settings.track_changes
+        && let Some(tp) = &whole
+    {
+        super::table::delete_table_at(s, tp)?;
+        super::controls::restore_placeholder(s)?;
+        return Ok(r);
+    }
+    // Whole rows or some cells: their text goes, the rows and cells stay, as in Word.
+    if whole.is_none()
+        && let Some(range) = s.cell_range().cloned()
+    {
+        super::table::clear_range_cells(s, &range)?;
+        super::controls::restore_placeholder(s)?;
+        return Ok(r);
+    }
    // A tracked cut of a paragraph or sentence may become a move when pasted.
    if !super::moves::cut_tracked(s)? {
        delete_selection(s)?;
@@ -738,7 +776,7 @@ fn goto(s: &mut Session, v: &Value) -> CmdResult {
    });
    if let Some(pg) = rel.or_else(|| p::u64(v, "page")) {
        let l = s.layout();
-        let idx = (pg.max(1) as usize - 1).min(l.pages.len().saturating_sub(1));
+        let idx = crate::p::page_index(pg).min(l.pages.len().saturating_sub(1));
        let target = l.pages.get(idx).and_then(|page| {
            page.items.iter().find_map(|it| match it {
                wordcraft_layout::Placed::Lines { story, path, para, l0, .. } if *story == StoryRef::Body => {
@@ -147,7 +147,7 @@ pub fn specs() -> Vec<CommandSpec> {
            .params(r#"{"id"?: n (an open document, see view.switchWindows; default the active one), "force"?: bool (discard unsaved changes; without it a document with unsaved changes is an error and stays open)} → {"closed": id, "active": id, "documents": [{"id", "title", "path", "dirty", "active"}]}; closing the last document leaves a new blank one"#)
            .pure(),
        CommandSpec::new("file.properties", "Properties", "File › Info", properties)
-            .params(r#"{"title"?, "subject"?, "author"?, "keywords"?, "comments"?, "category"?, "custom"?: {name: string | null (removes)}}"#),
+            .params(r#"{"title"?, "subject"?, "author"?, "keywords"?, "comments"?, "category"?, "custom"?: {name: string | {"value": string, "linkTarget"?: string | null} | null (removes)}}; text values and bookmark targets are at most 1 MiB; a string keeps an existing target, an object replaces it (omitted/null target unlinks)"#),
        CommandSpec::new("file.info", "Info", "File", info).pure(),
        CommandSpec::new("file.setAuthor", "User Name", "File › Options › General", set_author)
            .params(r#"{"name": string (author of new tracked changes and comments)}"#)
@@ -428,7 +428,7 @@ fn export_png(s: &mut Session, v: &Value) -> CmdResult {
        s.push_ui_request(json!({"open": "exportPng"}));
        return Ok(json!({"exported": false}));
    };
-    let page = p::u64(v, "page").unwrap_or(1).max(1) as usize - 1;
+    let page = crate::p::page_index(p::u64(v, "page").unwrap_or(1));
    let scale = p::f32(v, "scale").unwrap_or(2.0).clamp(0.1, 8.0);
    let l = s.export_layout_with(export_options(s, v).markup);
    let pg = l.pages.get(page).ok_or_else(|| CmdError::Params(format!("no page {}", page + 1)))?;
@@ -445,6 +445,15 @@ fn export_png(s: &mut Session, v: &Value) -> CmdResult {
    Ok(json!({"path": path, "width": img.width, "height": img.height, "bytes": png.len()}))
 }

+/// Text and its bookmark association cross the dialog/command boundary together on rename.
+#[derive(serde::Deserialize)]
+#[serde(rename_all = "camelCase", deny_unknown_fields)]
+struct LinkedCustomText<'a> {
+    value: &'a str,
+    #[serde(borrow)]
+    link_target: Option<&'a str>,
+}
+
 fn properties(s: &mut Session, v: &Value) -> CmdResult {
    let c = &mut s.doc.core;
    let set = |dst: &mut String, k: &str| {
@@ -460,7 +469,7 @@ fn properties(s: &mut Session, v: &Value) -> CmdResult {
    set(&mut c.category, "category");
    if let Some(custom) = v.get("custom") {
        let Some(m) = custom.as_object() else {
-            return Err(CmdError::Params("`custom` must be an object of name → string or null".into()));
+            return Err(CmdError::Params("`custom` must be an object of name → text, linked text value, or null".into()));
        };
        // Removals first: a case-only rename sends the old spelling as null and the new one
        // with its value, and `set_custom_prop` matches names case-insensitively, so setting
@@ -471,17 +480,32 @@ fn properties(s: &mut Session, v: &Value) -> CmdResult {
            }
        }
        for (name, val) in m {
-            match val {
-                // Removals took the name as stored above: a file opened from an older Word may
-                // hold one longer than today's limit, and it must still be deletable (#2982).
-                Value::Null => {}
-                Value::String(x) if x.len() <= MAX_CUSTOM_VALUE => {
-                    if name.trim().is_empty() || name.chars().count() > MAX_CUSTOM_NAME {
-                        return Err(CmdError::Params(format!("custom property names are 1–{MAX_CUSTOM_NAME} characters")));
-                    }
-                    s.doc.set_custom_prop(name, x);
+            let bad_value =
+                || CmdError::Params(format!("custom property `{name}` must be text (≤ {MAX_CUSTOM_VALUE} bytes), a linked text value, or null"));
+            let (value, target) = match val {
+                // Removal also accepts names longer than today's limit (#2982).
+                Value::Null => continue,
+                Value::String(value) => (value.as_str(), None),
+                Value::Object(_) => {
+                    let linked: LinkedCustomText<'_> = serde::Deserialize::deserialize(val).map_err(|_| bad_value())?;
+                    (linked.value, Some(linked.link_target))
                }
-                _ => return Err(CmdError::Params(format!("custom property `{name}` must be a string (≤ {MAX_CUSTOM_VALUE} bytes) or null"))),
+                _ => return Err(bad_value()),
+            };
+            if value.len() > MAX_CUSTOM_VALUE {
+                return Err(bad_value());
+            }
+            if name.trim().is_empty() || name.chars().count() > MAX_CUSTOM_NAME {
+                return Err(CmdError::Params(format!("custom property names are 1–{MAX_CUSTOM_NAME} characters")));
+            }
+            if target.flatten().is_some_and(|t| t.len() > MAX_CUSTOM_VALUE) {
+                return Err(CmdError::Params(format!("custom property bookmark targets are at most {MAX_CUSTOM_VALUE} bytes")));
+            }
+            s.doc.set_custom_prop(name, value);
+            if let Some(target) = target
+                && let Some(prop) = s.doc.custom_props.iter_mut().find(|p| p.name.eq_ignore_ascii_case(name))
+            {
+                prop.link_target = target.map(str::to_string);
            }
        }
    }
@@ -495,7 +519,7 @@ fn properties(s: &mut Session, v: &Value) -> CmdResult {
 /// Longest custom property name (Word's limit). The Custom Properties dialog validates with it
 /// too (#2982).
 pub const MAX_CUSTOM_NAME: usize = 255;
-/// Largest custom property value we accept from a command. The Custom Properties dialog
+/// Largest custom property value or bookmark target we accept from a command. The Custom Properties dialog
 /// validates with it too (#2982).
 pub const MAX_CUSTOM_VALUE: usize = 1024 * 1024;

@@ -197,6 +197,17 @@ fn column_rows(s: &Session) -> Option<Vec<(Pos, Pos)>> {

 /// Apply a change to the selection (or the pending caret formatting).
 pub fn apply(s: &mut Session, f: &dyn Fn(&mut CharProps)) -> CmdResult {
+    apply_to(s, target, f)
+}
+
+/// The selection only, not the word at a caret: what highlighting formats (#4086).
+fn selection(s: &Session) -> Option<(Pos, Pos)> {
+    let (a, b) = s.sel.ordered();
+    (a != b).then_some((a, b))
+}
+
+/// [`apply`], with `target` choosing what a non-column selection formats.
+fn apply_to(s: &mut Session, target: fn(&Session) -> Option<(Pos, Pos)>, f: &dyn Fn(&mut CharProps)) -> CmdResult {
    // A column selection formats each row's piece.
    if let Some(rows) = column_rows(s) {
        for (a, b) in rows {
@@ -211,6 +222,12 @@ pub fn apply(s: &mut Session, f: &dyn Fn(&mut CharProps)) -> CmdResult {
    match selected_text_box(s).or_else(|| target(s)) {
        Some((a, b)) => {
            s.doc.format_range(&a, &b, f)?;
+            // The word at a caret took the change: so does formatting waiting for typing (#4086).
+            if s.sel.is_collapsed()
+                && let Some(pend) = s.pending.as_mut()
+            {
+                f(pend);
+            }
        }
        None => {
            let mut pend = s.typing_props();
@@ -354,26 +371,59 @@ fn current_size(s: &Session) -> f32 {
 }

 fn step_size(s: &mut Session, dir: i32) -> CmdResult {
-    let cur = current_size(s);
-    let next = if dir > 0 {
-        SIZES.iter().copied().find(|x| *x > cur + 0.01).unwrap_or(((cur / 10.0).floor() + 1.0) * 10.0)
-    } else {
-        SIZES.iter().rev().copied().find(|x| *x < cur - 0.01).unwrap_or(1.0)
-    };
-    let next = next.clamp(1.0, 1638.0);
-    // Each run steps from its own size when the selection mixes sizes.
-    apply(s, &|c| {
-        c.size = Some(next);
-        c.size_cs = Some(next);
+    resize(s, &|cur| {
+        if dir > 0 {
+            SIZES.iter().copied().find(|x| *x > cur + 0.01).unwrap_or(((cur / 10.0).floor() + 1.0) * 10.0)
+        } else {
+            SIZES.iter().rev().copied().find(|x| *x < cur - 0.01).unwrap_or(1.0)
+        }
    })
 }

 fn nudge_size(s: &mut Session, d: f32) -> CmdResult {
-    let next = (current_size(s) + d).clamp(1.0, 1638.0);
-    apply(s, &|c| {
-        c.size = Some(next);
-        c.size_cs = Some(next);
-    })
+    resize(s, &|cur| cur + d)
+}
+
+/// Relative commands transform each run's effective size, including inherited sizes. Keep
+/// `apply`'s targets and the existing explicit override of both normal and complex-script size.
+fn resize(s: &mut Session, next: &dyn Fn(f32) -> f32) -> CmdResult {
+    let set = |c: &mut CharProps, size: f32| {
+        let size = next(size).clamp(1.0, 1638.0);
+        c.size = Some(size);
+        c.size_cs = Some(size);
+    };
+    let ranges = column_rows(s).or_else(|| selected_text_box(s).or_else(|| target(s)).map(|range| vec![range]));
+    let Some(ranges) = ranges else {
+        // Pending typing props and an empty paragraph's mark get the same single change.
+        let size = current_size(s);
+        return apply(s, &|c| set(c, size));
+    };
+    // Resolve against one immutable snapshot while formatting splits and normalizes runs.
+    let styles = s.doc.styles.clone();
+    for (a, b) in ranges {
+        for path in s.doc.paths_between(&a, &b) {
+            let p = s.doc.para_mut(a.story, &path)?;
+            let style = p.props.style.clone();
+            let from = if path == a.path { a.off } else { 0 };
+            let to = if path == b.path { b.off } else { p.len() };
+            let format = |c: &mut CharProps| set(c, styles.resolve_char(style.as_deref(), c).size);
+            // Avoid format_range here: its path walk would repeat a paragraph-prefix scan.
+            p.format(from, to, &format)?;
+            // Keep format_range's paragraph-mark rule, including filtering linked marks.
+            if to == p.len() && (from == 0 || path != a.path) {
+                let style = p.mark.style.clone();
+                format(&mut p.mark);
+                if p.mark.link.take().is_some() {
+                    p.mark.style = style.filter(|s| s != "Hyperlink");
+                }
+            }
+        }
+        // An empty selected cell has only its paragraph mark, which needs a new layout too.
+        if a == b {
+            s.doc.para_mut(a.story, &a.path)?.touch();
+        }
+    }
+    sel_result(s)
 }

 fn color(s: &mut Session, v: &Value) -> CmdResult {
@@ -410,7 +460,7 @@ fn target_has_highlight(s: &Session, h: Highlight) -> bool {
            return true;
        }
    }
-    if let Some((a, b)) = selected_text_box(s).or_else(|| target(s)) {
+    if let Some((a, b)) = selected_text_box(s).or_else(|| selection(s)) {
        for path in s.doc.paths_between(&a, &b) {
            let Some(p) = s.doc.para(a.story, &path) else { continue };
            let from = if path == a.path { a.off } else { 0 };
@@ -422,7 +472,12 @@ fn target_has_highlight(s: &Session, h: Highlight) -> bool {
            }
        }
    }
-    // No runs: retain the caret/pending and empty text-box paragraph-mark rules.
+    // No runs: retain the caret/pending and empty text-box paragraph-mark rules. A caret checks
+    // what is typed next, not the word it's in (#4086).
+    if selected_text_box(s).or_else(|| selection(s)).is_none() {
+        let style = s.doc.para_at(&s.sel.focus).and_then(|p| p.props.style.as_deref());
+        return seen || matches(style, &s.typing_props());
+    }
    seen || resolved(s).iter().all(|r| r.highlight == h.rgb())
 }

@@ -472,7 +527,8 @@ fn highlight(s: &mut Session, v: &Value) -> CmdResult {
    };
    let remove = color.is_none() && target_has_highlight(s, h);
    let value = if remove { Highlight::None } else { h };
-    let result = apply(s, &|x| x.highlight = Some(value))?;
+    // A caret highlights what is typed next, not the word it's in, as in Word (#4086).
+    let result = apply_to(s, selection, &|x| x.highlight = Some(value))?;
    s.last_highlight = h;
    Ok(result)
 }
@@ -134,7 +134,8 @@ pub fn specs() -> Vec<CommandSpec> {
        CommandSpec::new("insert.textFromFile", "Text from File", "Insert › Text › Object", |s, v| {
            let path = p::req_str(v, "path")?;
            let doc = crate::io::open_path(std::path::Path::new(path)).map_err(CmdError::Failed)?;
-            let mut frag = doc.body_fragment();
+            // The file's pictures, lists and styles come along (its own keys and ids mean nothing here).
+            let mut frag = s.doc.adopt(doc);
            super::paste::unlink_sections(&mut frag.blocks);
            let at = delete_selection(s)?;
            let end = s.doc.insert_fragment(&at, &frag)?;
@@ -222,7 +222,7 @@ pub fn specs() -> Vec<CommandSpec> {
            r#"{"delivery": string, "return"?: string, "size"?: "Envelope #10|#9|Monarch|DL|C4|C5|C6|B5", "width"?: pt, "height"?: pt, "add"?: bool (add to this document instead of a new one)}"#,
        ),
        CommandSpec::new("mailings.labels", "Labels", "Mailings › Create", labels).params(
-            r#"{"text"?: string, "product"?: "letter-3x10|letter-2x10|letter-2x7|letter-2x5|letter-4x20|a4-3x7|a4-2x7|a4-3x8|a4-2x4", "rows"?: n, "cols"?: n, "fromRecipients"?: bool, "single"?: {"row": n, "col": n}}"#,
+            r#"{"text"?: string, "product"?: "letter-3x10|letter-2x10|letter-2x7|letter-2x5|letter-4x20|a4-3x7|a4-2x7|a4-3x8|a4-2x4", "rows"?: n, "cols"?: n, "fromRecipients"?: bool (one label per selected recipient, continuing across sheets), "single"?: {"row": n, "col": n}}"#,
        ),
    ]
 }
--- a/Show More
+++ b/Show More