diff --git a/.github/workflows/packaging-lint.yml b/.github/workflows/packaging-lint.yml index f54b0538b9..ea61d84303 100644 --- a/.github/workflows/packaging-lint.yml +++ b/.github/workflows/packaging-lint.yml @@ -21,3 +21,27 @@ jobs: lint: # 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/packaging-lint.yml@main + + windows-install-policy: + timeout-minutes: 10 + name: Windows installation policy (no app build) + runs-on: windows-latest + steps: + - uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1 + with: + persist-credentials: false + - name: Install the pinned packaging toolchain + shell: pwsh + run: | + $tools = Join-Path $env:RUNNER_TEMP 'craft-install-policy-wix' + dotnet tool install --tool-path $tools wix --version 5.0.2 + if ($LASTEXITCODE -ne 0) { throw 'WiX installation failed.' } + $tools >> $env:GITHUB_PATH + $policy = Get-Content -Raw -LiteralPath packaging/windows/install-policy.json | ConvertFrom-Json + foreach ($extension in @($policy.extensions)) { + & (Join-Path $tools 'wix.exe') extension add -g "WixToolset.$extension.wixext/5.0.2" + if ($LASTEXITCODE -ne 0) { throw "WiX extension $extension installation failed." } + } + - name: Build and check non-executable installer fixtures + shell: pwsh + run: ./packaging/windows/test-install-policy.ps1 -OutputDirectory (Join-Path $env:RUNNER_TEMP 'craft-install-policy-tests') diff --git a/.github/workflows/windows-arm64.yml b/.github/workflows/windows-arm64.yml index d470419d26..838af4524c 100644 --- a/.github/workflows/windows-arm64.yml +++ b/.github/workflows/windows-arm64.yml @@ -27,8 +27,9 @@ permissions: jobs: windows-arm64: - # 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 + uses: storytold/craft-common-actions/.github/workflows/windows-arm64.yml@8bb4e5ab95443171104ad88113fe1ef9b0e5ce3f with: app-name: pdfcraft app-dir: PdfCraft + install-relative-path: Programs/ArtCraft/PdfCraft + install-scope: perUser diff --git a/ATTRIBUTION.md b/ATTRIBUTION.md index fa3efb62a7..23ebcbbe82 100644 --- a/ATTRIBUTION.md +++ b/ATTRIBUTION.md @@ -335,8 +335,8 @@ Fonts are fetched by `cargo xtask demo-pdf` into `target/demo-fonts/`, OCR model | `NotoColorEmoji-Regular.ttf` | Noto Color Emoji | Google Inc. | OFL-1.1 | https://github.com/google/fonts/tree/9710da1eacb3be272583c3224dcb70f9da6eadbb/ofl/notocoloremoji | Showcase PDF (cargo xtask demo-pdf) | | `Inter[opsz,wght].ttf` | Inter (variable) | The Inter Project Authors (Rasmus Andersson) | OFL-1.1 | https://github.com/google/fonts/tree/9710da1eacb3be272583c3224dcb70f9da6eadbb/ofl/inter | Showcase PDF (cargo xtask demo-pdf) | | `Inter-Italic[opsz,wght].ttf` | Inter Italic (variable) | The Inter Project Authors (Rasmus Andersson) | OFL-1.1 | https://github.com/google/fonts/tree/9710da1eacb3be272583c3224dcb70f9da6eadbb/ofl/inter | Showcase PDF (cargo xtask demo-pdf) | -| `text-detection.rten` | Ocrs text detection model | Robert Knight (ocrs-models; trained on HierText, CC-BY-SA-4.0) | CC-BY-SA-4.0 | https://github.com/robertknight/ocrs-models (the models ocrs downloads; model card: https://huggingface.co/robertknight/ocrs, cc-by-sa-4.0) | Scan & OCR: finds words on page images (cargo xtask models) | -| `text-recognition.rten` | Ocrs text recognition model | Robert Knight (ocrs-models; trained on HierText, CC-BY-SA-4.0) | CC-BY-SA-4.0 | https://github.com/robertknight/ocrs-models (the models ocrs downloads; model card: https://huggingface.co/robertknight/ocrs, cc-by-sa-4.0) | Scan & OCR: reads the words it finds (cargo xtask models) | +| `text-detection.onnx` | Ocrs text detection model | Robert Knight (ocrs-models; trained on HierText, CC-BY-SA-4.0) | CC-BY-SA-4.0 | https://github.com/robertknight/ocrs/blob/0c826441362a701c55560fefc17bf356b6d1037e/ocrs/examples/download-models.sh (author-published ONNX models; model card: https://huggingface.co/robertknight/ocrs/blob/df0edd170279ab971b53e094c627255a87e1a503/README.md, cc-by-sa-4.0) | Scan & OCR: finds words on page images (cargo xtask models) | +| `text-recognition.onnx` | Ocrs text recognition model | Robert Knight (ocrs-models; trained on HierText, CC-BY-SA-4.0) | CC-BY-SA-4.0 | https://github.com/robertknight/ocrs/blob/0c826441362a701c55560fefc17bf356b6d1037e/ocrs/examples/download-models.sh (author-published ONNX models; model card: https://huggingface.co/robertknight/ocrs/blob/df0edd170279ab971b53e094c627255a87e1a503/README.md, cc-by-sa-4.0) | Scan & OCR: reads the words it finds (cargo xtask models) | ## Optional build inputs (1) diff --git a/ATTRIBUTION.toml b/ATTRIBUTION.toml index bfaf948862..489247559d 100644 --- a/ATTRIBUTION.toml +++ b/ATTRIBUTION.toml @@ -3356,30 +3356,30 @@ usage = "1x + 2x HiDPI 16-colour palette TIFF copied into the macOS DMG by packa sha256 = "f46881724a6621f3686a612a79dbdce4f7dbe9e2025610e44c9a094341334c2c" [[fetched]] -file = "text-detection.rten" -url = "https://ocrs-models.s3-accelerate.amazonaws.com/text-detection.rten" +file = "text-detection.onnx" +url = "https://ocrs-models.s3-accelerate.amazonaws.com/text-detection.onnx" title = "Ocrs text detection model" author = "Robert Knight (ocrs-models; trained on HierText, CC-BY-SA-4.0)" -source = "https://github.com/robertknight/ocrs-models (the models ocrs downloads; model card: https://huggingface.co/robertknight/ocrs, cc-by-sa-4.0)" +source = "https://github.com/robertknight/ocrs/blob/0c826441362a701c55560fefc17bf356b6d1037e/ocrs/examples/download-models.sh (author-published ONNX models; model card: https://huggingface.co/robertknight/ocrs/blob/df0edd170279ab971b53e094c627255a87e1a503/README.md, cc-by-sa-4.0)" licence = "CC-BY-SA-4.0" licence_url = "https://creativecommons.org/licenses/by-sa/4.0/legalcode.txt" licence_sha256 = "28a9529c7d0bb4dc51f4bf5c116a3d16ef247a052f7591466768ddf563fd1cf5" kind = "model" usage = "Scan & OCR: finds words on page images (cargo xtask models)" -sha256 = "f15cfb56bd02c4bf478a20343986504a1f01e1665c2b3a0ad66340f054b1b5ca" +sha256 = "a917b23dbd9524b465df7e922641b3ff2981623df4ded5a0234004ef2fee7cfe" [[fetched]] -file = "text-recognition.rten" -url = "https://ocrs-models.s3-accelerate.amazonaws.com/text-recognition.rten" +file = "text-recognition.onnx" +url = "https://ocrs-models.s3-accelerate.amazonaws.com/text-recognition.onnx" title = "Ocrs text recognition model" author = "Robert Knight (ocrs-models; trained on HierText, CC-BY-SA-4.0)" -source = "https://github.com/robertknight/ocrs-models (the models ocrs downloads; model card: https://huggingface.co/robertknight/ocrs, cc-by-sa-4.0)" +source = "https://github.com/robertknight/ocrs/blob/0c826441362a701c55560fefc17bf356b6d1037e/ocrs/examples/download-models.sh (author-published ONNX models; model card: https://huggingface.co/robertknight/ocrs/blob/df0edd170279ab971b53e094c627255a87e1a503/README.md, cc-by-sa-4.0)" licence = "CC-BY-SA-4.0" licence_url = "https://creativecommons.org/licenses/by-sa/4.0/legalcode.txt" licence_sha256 = "28a9529c7d0bb4dc51f4bf5c116a3d16ef247a052f7591466768ddf563fd1cf5" kind = "model" usage = "Scan & OCR: reads the words it finds (cargo xtask models)" -sha256 = "e484866d4cce403175bd8d00b128feb08ab42e208de30e42cd9889d8f1735a6e" +sha256 = "86c145c2edb96c8caed5b1ebb8f44d706408922211451c309c625157dd6061c5" [[build_input]] name = "craft-fonts" diff --git a/CLAUDE.md b/CLAUDE.md index f51a96d56e..a37cec4ca6 100644 --- a/CLAUDE.md +++ b/CLAUDE.md @@ -39,6 +39,7 @@ PdfCraft is a clean-room, open-source, Rust-native PDF application targeting Ado - **Rebasing is a review step, not a mechanical one.** Read every hunk you resolve, and the auto-merged hunks in the files you touched too — `main` moves fast enough that a file can change by hundreds of lines under a branch. - **External PRs are held to safety, security and completeness before style.** Provenance first (no Adobe-derived asset, no committed font, no copied GPL/AGPL code, behaviour from the spec and not from reading another implementation), then no new panic path or `unsafe`, then `--root` confinement on every path including ones reached by nested dispatch, opt-in-only MCP and control channel, no new outbound network, then a headless `automation` tool, tests at the right zoom and an honest `parity/` entry. Provenance is the part a contributor cannot be expected to know, and the only part that cannot be undone after merge. - **Quality gates** before every commit: `cargo fmt --check`, clippy with `-D warnings`, the tests, `cargo xtask layers`, `cargo xtask assets`, and the wasm check once `xtask ci` exists (M0). + - New workspace crates must include `[lints] workspace = true` in `Cargo.toml` to inherit `[workspace.lints]`. Production crate roots must declare the required crate-level lint attributes before modules or other crate items; crate-level `//!` documentation may precede them. - **Scope builds and tests to the crates you touched** — `cargo clippy -p -j 2 --all-targets` and `cargo test -p -j 2`, under a `timeout`. A full `--workspace` build has locked up a development machine's CPU; it is CI's job and CI runs it on every PR. Run the workspace sweep locally only when you have a reason to and the machine is free. - **Check for existing work before starting a fix or feature.** Search the issues and PRs, open and closed, with `gh issue list -R storytold/pdfcraft --state all --search ""` and the same with `gh pr list` (try a few phrasings), and check whether a merged fix is already on `main` (`git merge-base --is-ancestor origin/main`). If one is, the report is likely from an older build: say so rather than fixing it again. If an open PR covers it, review or build on that PR instead of opening a competing one. If an issue exists, reference it in the PR (`Fixes #123`). - **Commits and PRs:** `main` is the only integration branch and is **never pushed to directly**. Branch from an up-to-date `main` as `/` (`feat/`, `fix/`, `docs/`, `chore/`, `refactor/`), one task id per commit (e.g. `M1.4: xref stream reader`), commit only green states, and open a PR into `main` using `.github/pull_request_template.md`. Merge only when CI is green. diff --git a/Cargo.lock b/Cargo.lock index 3c713ba5cc..4f8e8ac8cd 100644 --- a/Cargo.lock +++ b/Cargo.lock @@ -1023,6 +1023,15 @@ dependencies = [ "x509-cert", ] +[[package]] +name = "cobs" +version = "0.3.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "0fa961b519f0b462e3a3b4a34b64d119eeaca1d59af726fe450bbba07a9fc0a1" +dependencies = [ + "thiserror 2.0.21", +] + [[package]] name = "codespan-reporting" version = "0.13.1" @@ -1169,12 +1178,40 @@ dependencies = [ [[package]] name = "craft-docpath" version = "0.1.0" -source = "git+https://github.com/storytold/craft-libs?rev=82a24b006eefa036b43c09a67fb9a3fbd17ffe63#82a24b006eefa036b43c09a67fb9a3fbd17ffe63" +source = "git+https://github.com/storytold/craft-libs?rev=e11f9d9aebea5f6b8e74643c1ea1ed172ba5f545#e11f9d9aebea5f6b8e74643c1ea1ed172ba5f545" + +[[package]] +name = "craft-fonts-build" +version = "0.1.0" +source = "git+https://github.com/storytold/craft-libs?rev=e11f9d9aebea5f6b8e74643c1ea1ed172ba5f545#e11f9d9aebea5f6b8e74643c1ea1ed172ba5f545" + +[[package]] +name = "craft-i18n" +version = "0.1.0" +source = "git+https://github.com/storytold/craft-libs?rev=e11f9d9aebea5f6b8e74643c1ea1ed172ba5f545#e11f9d9aebea5f6b8e74643c1ea1ed172ba5f545" +dependencies = [ + "fixed_decimal", + "icu_decimal", + "icu_locale_core", + "icu_locale_fallback", + "icu_normalizer", + "icu_plurals", + "icu_properties", + "icu_provider", + "icu_provider_adapters", + "icu_provider_blob", + "log", + "objc2-foundation 0.3.2", + "sys-locale", + "unicode-bidi", + "windows-registry", + "writeable", +] [[package]] name = "craft-keymap" version = "0.1.0" -source = "git+https://github.com/storytold/craft-libs?rev=edc41f68fa24c46651c3b5117d10f0ead75ec9cb#edc41f68fa24c46651c3b5117d10f0ead75ec9cb" +source = "git+https://github.com/storytold/craft-libs?rev=e11f9d9aebea5f6b8e74643c1ea1ed172ba5f545#e11f9d9aebea5f6b8e74643c1ea1ed172ba5f545" dependencies = [ "egui", "serde", @@ -1184,7 +1221,7 @@ dependencies = [ [[package]] name = "craft-menu" version = "0.1.0" -source = "git+https://github.com/storytold/craft-libs?rev=edc41f68fa24c46651c3b5117d10f0ead75ec9cb#edc41f68fa24c46651c3b5117d10f0ead75ec9cb" +source = "git+https://github.com/storytold/craft-libs?rev=e11f9d9aebea5f6b8e74643c1ea1ed172ba5f545#e11f9d9aebea5f6b8e74643c1ea1ed172ba5f545" dependencies = [ "craft-keymap", "craft-quit", @@ -1197,11 +1234,11 @@ dependencies = [ [[package]] name = "craft-print" version = "0.1.0" -source = "git+https://github.com/storytold/craft-libs?rev=42e30cd5b3f4b114270dd053fccbc33bedc47f68#42e30cd5b3f4b114270dd053fccbc33bedc47f68" +source = "git+https://github.com/storytold/craft-libs?rev=e11f9d9aebea5f6b8e74643c1ea1ed172ba5f545#e11f9d9aebea5f6b8e74643c1ea1ed172ba5f545" dependencies = [ "craft-winprint-gdi", - "miniz_oxide 0.8.9", - "roxmltree", + "miniz_oxide 0.9.1", + "roxmltree 0.21.2", "tempfile", "winprint", "winsafe", @@ -1210,7 +1247,7 @@ dependencies = [ [[package]] name = "craft-quit" version = "0.1.0" -source = "git+https://github.com/storytold/craft-libs?rev=edc41f68fa24c46651c3b5117d10f0ead75ec9cb#edc41f68fa24c46651c3b5117d10f0ead75ec9cb" +source = "git+https://github.com/storytold/craft-libs?rev=e11f9d9aebea5f6b8e74643c1ea1ed172ba5f545#e11f9d9aebea5f6b8e74643c1ea1ed172ba5f545" dependencies = [ "dispatch2", "egui", @@ -1221,20 +1258,28 @@ dependencies = [ [[package]] name = "craft-ui" version = "0.1.0" -source = "git+https://github.com/storytold/craft-libs?rev=edc41f68fa24c46651c3b5117d10f0ead75ec9cb#edc41f68fa24c46651c3b5117d10f0ead75ec9cb" +source = "git+https://github.com/storytold/craft-libs?rev=e11f9d9aebea5f6b8e74643c1ea1ed172ba5f545#e11f9d9aebea5f6b8e74643c1ea1ed172ba5f545" dependencies = [ + "craft-fonts-build", + "craft-i18n", "egui", + "epaint", + "js-sys", "log", "objc2 0.6.5", "objc2-app-kit 0.3.2", "objc2-foundation 0.3.2", "serde", + "skrifa 0.44.0", + "wasm-bindgen", + "wasm-bindgen-futures", + "web-sys", ] [[package]] name = "craft-update" version = "0.1.0" -source = "git+https://github.com/storytold/craft-libs?rev=495e5971bc024aa96e6ed318cb6e7cd3a0103184#495e5971bc024aa96e6ed318cb6e7cd3a0103184" +source = "git+https://github.com/storytold/craft-libs?rev=e11f9d9aebea5f6b8e74643c1ea1ed172ba5f545#e11f9d9aebea5f6b8e74643c1ea1ed172ba5f545" dependencies = [ "chrono", "dunce", @@ -2073,6 +2118,17 @@ version = "0.1.14" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "aedcfb3409746eddb02b9e19ebda1c3394f759a152e48ee875a0844d1b955484" +[[package]] +name = "fixed_decimal" +version = "0.7.3" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "2214fb00f669ee96bee5bb29dfb1ddabe058b2bc426817efc79afa03c9bc55ae" +dependencies = [ + "displaydoc", + "smallvec", + "writeable", +] + [[package]] name = "fixedbitset" version = "0.5.7" @@ -2188,7 +2244,7 @@ version = "0.5.8" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "bbc773e24e02d4ddd8395fd30dc147524273a83e54e0f312d986ea30de5f5646" dependencies = [ - "roxmltree", + "roxmltree 0.20.0", ] [[package]] @@ -2882,6 +2938,23 @@ dependencies = [ "zerovec", ] +[[package]] +name = "icu_decimal" +version = "2.3.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "9eb8f655bba2d0c0459e43a5b0e6cd3cd388109898fb3d85d048165e8b0abd08" +dependencies = [ + "displaydoc", + "fixed_decimal", + "icu_locale_core", + "icu_pattern", + "icu_plurals", + "icu_provider", + "serde", + "writeable", + "zerovec", +] + [[package]] name = "icu_locale_core" version = "2.3.0" @@ -2890,11 +2963,32 @@ checksum = "d56e28588da92eee5c3201a6eff33fabdd49b62269c8938d4ff050ce4d900deb" dependencies = [ "displaydoc", "litemap", + "serde", "tinystr", "writeable", "zerovec", ] +[[package]] +name = "icu_locale_fallback" +version = "2.3.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "251af8e57c9400e3eb58242fe5b8b1152b2a64fdf4cf632f923c38ccee6f2fa9" +dependencies = [ + "icu_locale_core", + "icu_locale_fallback_data", + "icu_provider", + "potential_utf", + "tinystr", + "zerovec", +] + +[[package]] +name = "icu_locale_fallback_data" +version = "2.3.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "decf2a22ec8fa68f1a0c1129a3f8583f8f8bc24e8b9ccbe98ead99f62a4dc3a8" + [[package]] name = "icu_normalizer" version = "2.3.0" @@ -2907,6 +3001,7 @@ dependencies = [ "icu_provider", "smallvec", "utf16_iter", + "utf8_iter", "write16", "zerovec", ] @@ -2917,6 +3012,32 @@ version = "2.3.0" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "1563da1ed3e0b3bf3d74c9b85917ac9c56464d2f57242270c09c9e752f8021a0" +[[package]] +name = "icu_pattern" +version = "0.5.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "2b3db611446bd92c246b03e4aa0bafa71ddb194af431ddbb42b9d70e4bfce1a0" +dependencies = [ + "displaydoc", + "either", + "serde", + "writeable", + "zerovec", +] + +[[package]] +name = "icu_plurals" +version = "2.3.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "e475e6766ef87b1d3c1f97be6363995b0bfaeddbc789671615df598a97ff0593" +dependencies = [ + "displaydoc", + "fixed_decimal", + "icu_provider", + "serde", + "zerovec", +] + [[package]] name = "icu_properties" version = "2.3.0" @@ -2946,6 +3067,9 @@ checksum = "d27bbb9d3abbefac45d55f647c9de1d44aafcd1186eb91879afef17c396c3e73" dependencies = [ "displaydoc", "icu_locale_core", + "postcard", + "serde", + "stable_deref_trait", "writeable", "yoke", "zerofrom", @@ -2953,6 +3077,30 @@ dependencies = [ "zerovec", ] +[[package]] +name = "icu_provider_adapters" +version = "2.3.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "df887bc4f55dbc773c7c45a0c7dfa75be886f7b7812830a71ab7271cc1801820" +dependencies = [ + "icu_locale_fallback", + "icu_provider", +] + +[[package]] +name = "icu_provider_blob" +version = "2.3.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "5916b44fac319d3f58e4d8d805a627df19e27937b582cd99fcde3bb6b7ce1b0e" +dependencies = [ + "icu_provider", + "postcard", + "serde", + "writeable", + "zerotrie", + "zerovec", +] + [[package]] name = "idna" version = "1.1.0" @@ -3251,6 +3399,9 @@ name = "litemap" version = "0.8.3" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "47d9d19d1d6efa0109d2f65ff4c85cddd50bd572e5a00127ab10987290bcefae" +dependencies = [ + "serde_core", +] [[package]] name = "litrs" @@ -4340,6 +4491,7 @@ dependencies = [ "ocrs", "pdfcraft-fonts", "rten", + "tempfile", "thiserror 2.0.21", ] @@ -4391,7 +4543,7 @@ dependencies = [ "pdfcraft-content", "pdfcraft-cos", "pdfcraft-model", - "roxmltree", + "roxmltree 0.20.0", ] [[package]] @@ -4554,7 +4706,7 @@ dependencies = [ "pdfcraft-cos", "pdfcraft-fonts", "png 0.18.1", - "roxmltree", + "roxmltree 0.20.0", "sha2 0.11.1", "thiserror 2.0.21", ] @@ -4567,7 +4719,7 @@ dependencies = [ "pdfcraft-cos", "pdfcraft-forms", "pdfcraft-model", - "roxmltree", + "roxmltree 0.20.0", "thiserror 2.0.21", ] @@ -4888,12 +5040,24 @@ dependencies = [ "portable-atomic", ] +[[package]] +name = "postcard" +version = "1.1.3" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "6764c3b5dd454e283a30e6dfe78e9b31096d9e32036b5d1eaac7a6119ccb9a24" +dependencies = [ + "cobs", + "serde", +] + [[package]] name = "potential_utf" version = "0.1.6" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "d83eb9bc6d8e5cf568e7a1101d60ee05e81ed50ea106026f3d18deeb046d7661" dependencies = [ + "serde_core", + "writeable", "zerovec", ] @@ -5444,6 +5608,15 @@ version = "0.20.0" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "6c20b6793b5c2fa6553b250154b78d6d0db37e72700ae35fad9387a46f487c97" +[[package]] +name = "roxmltree" +version = "0.21.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "9da7f59328b09405b181fee1018925fad50f157afb43c0c0f5c522c256dd5907" +dependencies = [ + "memchr", +] + [[package]] name = "rsa" version = "0.10.0-rc.18" @@ -5473,6 +5646,7 @@ dependencies = [ "rten-base", "rten-gemm", "rten-model-file", + "rten-onnx", "rten-parallel", "rten-shape-inference", "rten-simd", @@ -5522,6 +5696,12 @@ dependencies = [ "rten-base", ] +[[package]] +name = "rten-onnx" +version = "0.26.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "96944374568990b8d1bbc5bae5957585866f9dd8256130460405730948bfd42e" + [[package]] name = "rten-parallel" version = "0.26.0" @@ -6515,7 +6695,10 @@ version = "0.3.2" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "8eab9a99a024a169fe8a903cf9d4a3b3601109bcc13bd9e3c6fff259138626c4" dependencies = [ + "js-sys", "libc", + "wasm-bindgen", + "web-sys", ] [[package]] @@ -6710,6 +6893,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "b1e27c91459209c2986af3dcf603a5a74a4368754ce37414f59acc971167f643" dependencies = [ "displaydoc", + "serde_core", "zerovec", ] @@ -7078,7 +7262,7 @@ dependencies = [ "kurbo 0.11.3", "log", "pico-args", - "roxmltree", + "roxmltree 0.20.0", "simplecss", "siphasher", "strict-num", @@ -8052,6 +8236,9 @@ name = "writeable" version = "0.6.4" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "3ad82d2a33cdc9674dc7465672f271e096168fcdbe0f799d9e6db8c5892679dc" +dependencies = [ + "either", +] [[package]] name = "x11-dl" @@ -8376,8 +8563,11 @@ source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "4ea269c3bd32f0a32c321907a2ae912ba6f4649bb0fc764a15627e99a7095a3f" dependencies = [ "displaydoc", + "litemap", + "serde_core", "yoke", "zerofrom", + "zerovec", ] [[package]] @@ -8386,6 +8576,7 @@ version = "0.11.8" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "bb0464e17806c1d976d5cba29399c7f08e516e279e2ba493f63123b5fca67dd8" dependencies = [ + "serde", "yoke", "zerofrom", "zerovec-derive", diff --git a/Cargo.toml b/Cargo.toml index 8eb38b29af..f86ebaa15f 100644 --- a/Cargo.toml +++ b/Cargo.toml @@ -13,17 +13,17 @@ repository = "https://github.com/storytold/pdfcraft" [workspace.dependencies] # Shared frontend components; engines remain independent of egui. -craft-ui = { git = "https://github.com/storytold/craft-libs", version = "0.1.0", rev = "edc41f68fa24c46651c3b5117d10f0ead75ec9cb", features = ["serde"] } +craft-ui = { git = "https://github.com/storytold/craft-libs", version = "0.1.0", rev = "e11f9d9aebea5f6b8e74643c1ea1ed172ba5f545", features = ["serde"] } # Quit the macOS way (#1136): ⌘Q asks about unsaved changes, and closing quits through `terminate:`. -craft-quit = { git = "https://github.com/storytold/craft-libs", version = "0.1.0", rev = "edc41f68fa24c46651c3b5117d10f0ead75ec9cb" } +craft-quit = { git = "https://github.com/storytold/craft-libs", version = "0.1.0", rev = "e11f9d9aebea5f6b8e74643c1ea1ed172ba5f545" } # One menu definition for the native macOS menu bar and the in-window bar elsewhere. -craft-menu = { git = "https://github.com/storytold/craft-libs", version = "0.1.0", rev = "edc41f68fa24c46651c3b5117d10f0ead75ec9cb" } -craft-keymap = { git = "https://github.com/storytold/craft-libs", version = "0.1.0", rev = "edc41f68fa24c46651c3b5117d10f0ead75ec9cb", default-features = false } +craft-menu = { git = "https://github.com/storytold/craft-libs", version = "0.1.0", rev = "e11f9d9aebea5f6b8e74643c1ea1ed172ba5f545" } +craft-keymap = { git = "https://github.com/storytold/craft-libs", version = "0.1.0", rev = "e11f9d9aebea5f6b8e74643c1ea1ed172ba5f545", default-features = false } # Shared system spooler; document composition remains in pdfcraft-print. -craft-print = { git = "https://github.com/storytold/craft-libs", version = "0.1.0", rev = "42e30cd5b3f4b114270dd053fccbc33bedc47f68" } +craft-print = { git = "https://github.com/storytold/craft-libs", version = "0.1.0", rev = "e11f9d9aebea5f6b8e74643c1ea1ed172ba5f545" } # Whether a path stored in a document may be opened (GoToR link targets). -craft-docpath = { version = "0.1.0", git = "https://github.com/storytold/craft-libs", rev = "82a24b006eefa036b43c09a67fb9a3fbd17ffe63" } -craft-update = { git = "https://github.com/storytold/craft-libs", version = "=0.1.0", rev = "495e5971bc024aa96e6ed318cb6e7cd3a0103184", features = ["egui"] } +craft-docpath = { version = "0.1.0", git = "https://github.com/storytold/craft-libs", rev = "e11f9d9aebea5f6b8e74643c1ea1ed172ba5f545" } +craft-update = { git = "https://github.com/storytold/craft-libs", version = "=0.1.0", rev = "e11f9d9aebea5f6b8e74643c1ea1ed172ba5f545", features = ["egui"] } # internal pdfcraft-geom = { path = "crates/geom", version = "0.14.0" } pdfcraft-filters = { path = "crates/filters", version = "0.14.0" } @@ -91,6 +91,9 @@ web-time = "1.1" unsafe_code = "forbid" [workspace.lints.clippy] +cognitive_complexity = "deny" +too_many_arguments = "deny" +wildcard_imports = "deny" dbg_macro = "warn" todo = "warn" diff --git a/README.md b/README.md index f319ffeadb..1766e26ebb 100644 --- a/README.md +++ b/README.md @@ -459,11 +459,13 @@ The portable zip runs from any folder, a USB stick included. Its `portable.txt` logs and crash recovery in a `PdfCraftData` folder next to `pdfcraft.exe`, so nothing is written to `%APPDATA%`; delete that file to use the normal per-user folders. -The MSI installs for all users and requires administrator privileges. It adds "Edit with PdfCraft" +The MSI installs for your account only by default, without administrator privileges. Choose +"Everyone on this computer" on its first page, or pass `ALLUSERS=1` from an elevated terminal, to install +for all users. It adds "Edit with PdfCraft" to the right-click menu of PDF files and "Create PDF with PdfCraft…" to the right-click menu of images (.png .jpg .jpeg .tif .tiff .gif .bmp .jp2 .j2k .jpx) in File Explorer (on Windows 11, under "Show more options"), without changing which app opens them by default. For unattended deployment -without a desktop shortcut, run from an elevated terminal: +without a desktop shortcut (add `ALLUSERS=1`, from an elevated terminal, for an all-users install): ```powershell msiexec /i "pdfcraft--windows-x64.msi" /qn /norestart INSTALLDESKTOPSHORTCUT=0 @@ -471,7 +473,7 @@ msiexec /i "pdfcraft--windows-x64.msi" /qn /norestart INSTALLDESKTOPSHORTCU | Property | `=0` leaves out | |---|---| -| `INSTALLDESKTOPSHORTCUT` | the all-users desktop shortcut | +| `INSTALLDESKTOPSHORTCUT` | the desktop shortcut | | `INSTALLPDFCONTEXTMENU` | "Edit with PdfCraft" on PDF files | | `INSTALLIMAGECONTEXTMENU` | "Create PDF with PdfCraft…" on images | diff --git a/ROADMAP.md b/ROADMAP.md index 165fccc5e8..f5de8044e1 100644 --- a/ROADMAP.md +++ b/ROADMAP.md @@ -2,6 +2,7 @@ **Stage: alpha** · next: beta, ~25% (ready for real work 50% → 75%) and ~400–700 h away +> **Last reviewed:** 2026-10-27 | **Last updated:** 2026-10-27 | **Change:** minor (M10: OCR model downloads use verified ONNX pairs with legacy discovery fallback; estimates unchanged) > **Last reviewed:** 2026-10-25 | **Last updated:** 2026-10-25 | **Change:** minor (M14 localization current state: Arabic logical catalog, explicit RTL label direction and mirrored stock chrome; native/browser RTL workflows unqualified. Native release Hans face via LXGW WenKai Lite; estimates unchanged) > **Last reviewed:** 2026-10-23 · **Last updated:** 2026-10-23 · **Change:** minor (M7, #2636 partial: pasting added text boxes and images in the engine and through `content_copy`; estimates unchanged) > **Last reviewed:** 2026-10-23 · **Last updated:** 2026-10-23 · **Change:** minor (M11: image optimization accounts for page-local UserUnit; estimates unchanged) @@ -199,6 +200,7 @@ Ranked; detail and the full milestone table in [docs/roadmap.md](docs/roadmap.md ## Progress log +- **2026-10-27 (M10, OCR models):** Model staging downloads and verifies the ONNX pair after the upstream RTEN URL brownout; runtime discovery prefers complete ONNX pairs per directory, retains complete RTEN fallback and preserves directory precedence. - **2026-10-24 (M10, #4158 partial):** Word, HTML, RTF and PowerPoint export keep a block that continues another on its line (an italic case name, a link, a superscript) as a run in its own style inside that paragraph, with the source's word space, instead of a paragraph of its own. Style changes that wrap onto the next line still split paragraphs (the reading blocks keep style boundaries). Estimates unchanged. - **2026-10-24 (M3, window move on Wayland, #3970 follow-up):** After a move or resize by PdfCraft's own title bar or edges, the button release given back to egui goes before the pointer leaving the window, so hover no longer sticks at the old place until the pointer moves. Found by CodeRabbit in review of #3970; a unit test covers it. Estimates unchanged. - **2026-10-24 (M14, #4253):** The annotation quick bar remembers Keep tool selected across restarts, including unpinning. Old and malformed settings keep safe defaults; the opt-in UI control channel reads and changes the same preference. Estimates unchanged. @@ -682,6 +684,7 @@ Newest first: the date, what moved, and the new overall estimate. | Date | Change | Summary | |---|---|---| +| 2026-10-27 | minor | M10: OCR stages SHA-256-verified ONNX models after the upstream RTEN URL brownout; discovery prefers a complete ONNX pair per directory, falls back to a complete RTEN pair, and never mixes formats or directories; language/web limits and estimates unchanged. | | 2026-10-23 | minor | M8, #3205 follow-up: phone-pattern redaction includes the +39 country code on labelled Italian geographic numbers with a slash; dates, protocol identifiers and whole-run guards remain. Estimates unchanged. | | 2026-10-23 | minor | M11: image downsampling measures physical resolution after page-local UserUnit scaling, including shared nested forms; synthetic measurement and optimization regressions. Estimates unchanged. | | 2026-10-23 | minor | M10: Word table cells use the grid columns they span, including cells after a merged cell; synthetic export regression and CLI reproduction. Estimates unchanged. | diff --git a/apps/pdfcraft-cli/src/check.rs b/apps/pdfcraft-cli/src/check.rs index 1821f85826..62993ad6dc 100644 --- a/apps/pdfcraft-cli/src/check.rs +++ b/apps/pdfcraft-cli/src/check.rs @@ -1,6 +1,8 @@ use super::commands::{parse_dpi, read}; use super::options::{AUDIT_OPTIONS, CHECK_ONE_OPTIONS, CHECK_OPTIONS, flag, positional, validate_options}; -use super::*; +use super::{ + Arc, CliError, Command, Duration, Instant, PageRenderer, Path, PathBuf, RenderConfig, RenderRequest, RequestKind, Stdio, inspect, stdout_line, +}; /// Audit a document for faux redactions. Prints the findings as JSON; fails when any are /// found so scripts and CI can gate on it, and when the audit itself cannot run. diff --git a/apps/pdfcraft-cli/src/commands.rs b/apps/pdfcraft-cli/src/commands.rs index 5efec8331c..9d0b2057f0 100644 --- a/apps/pdfcraft-cli/src/commands.rs +++ b/apps/pdfcraft-cli/src/commands.rs @@ -2,7 +2,7 @@ use super::options::{ COMBINE_OPTIONS, EXTRACT_OPTIONS, INFO_OPTIONS, RENDER_OPTIONS, SPLIT_OPTIONS, TEXT_OPTIONS, can_be_path_value, flag, needs_value, positional, validate_options, }; -use super::*; +use super::{Arc, CliError, ImageFormat, PageRenderer, Path, PathBuf, RenderConfig, RenderRequest, RequestKind, Write, inspect, stdout_line}; pub(crate) fn read(path: &str) -> Result>, String> { std::fs::read(path).map(Arc::new).map_err(|e| format!("{path}: {e}")) diff --git a/apps/pdfcraft-cli/src/options.rs b/apps/pdfcraft-cli/src/options.rs index ab1a3db34b..1ddbfabcd5 100644 --- a/apps/pdfcraft-cli/src/options.rs +++ b/apps/pdfcraft-cli/src/options.rs @@ -1,4 +1,4 @@ -use super::*; +use super::CliError; pub(crate) fn flag<'a>(args: &'a [String], name: &str) -> Option<&'a str> { args.iter().position(|a| a == name).and_then(|i| args.get(i + 1)).map(String::as_str) diff --git a/apps/pdfcraft-cli/src/run.rs b/apps/pdfcraft-cli/src/run.rs index 19eed21876..0726087d9d 100644 --- a/apps/pdfcraft-cli/src/run.rs +++ b/apps/pdfcraft-cli/src/run.rs @@ -1,7 +1,9 @@ #[cfg(feature = "mcp")] use super::options::MCP_OPTIONS; use super::options::{RUN_OPTIONS, flag, positional, validate_options}; -use super::*; +#[cfg(feature = "mcp")] +use super::{Arc, Path, Write, automation_args}; +use super::{CliError, stdout_line}; // ---- automation -------------------------------------------------------------------------------- diff --git a/apps/pdfcraft-cli/src/ui.rs b/apps/pdfcraft-cli/src/ui.rs index 9d12233528..dc419171b0 100644 --- a/apps/pdfcraft-cli/src/ui.rs +++ b/apps/pdfcraft-cli/src/ui.rs @@ -1,5 +1,5 @@ use super::options::{UI_OPTIONS, flag, positional, validate_options}; -use super::*; +use super::{CliError, Duration, stdout_line}; // ---- UI control channel client ----------------------------------------------------------------- diff --git a/clippy.toml b/clippy.toml index 7f2fd53057..31e54da30f 100644 --- a/clippy.toml +++ b/clippy.toml @@ -13,3 +13,8 @@ disallowed-methods = [ { path = "egui::Ui::radio_value", reason = "use radio_value from crates/ui-egui/src/widgets.rs, which is outlined and filled" }, { path = "egui::RadioButton::new", reason = "use radio from crates/ui-egui/src/widgets.rs, which is outlined and filled" }, ] +cognitive-complexity-threshold = 30 + +disallowed-types = [ + { path = "egui::ComboBox", reason = "use craft_ui::ComboBox: egui's combo box menu can't grow back while open (egui#5225)" }, +] diff --git a/crates/annot/README.md b/crates/annot/README.md index 8108201835..999baec20a 100644 --- a/crates/annot/README.md +++ b/crates/annot/README.md @@ -30,7 +30,7 @@ let index = add_annotation(&mut doc, &NewAnnotation { page, shape, style, conten add_reply(&mut doc, page, index, "Agreed", "Ada", &meta)?; set_review_state(&mut doc, page, index, ReviewState::Accepted, "Ada", &meta)?; move_annotation(&mut doc, page, index, dx, dy, &meta)?; -set_style(&mut doc, page, index, Some(rgb), Some(0.5), Some(2.0), &meta)?; +set_style(&mut doc, page, index, StyleChange::new(Some(rgb), Some(0.5), Some(2.0), None), &meta)?; delete_annotation(&mut doc, page, index)?; signature_image(&doc, page, index)?; // embedded image XObject of Fill & Sign signature/initials ``` diff --git a/crates/annot/src/appearance.rs b/crates/annot/src/appearance.rs index 508d2bee45..abc746c0dd 100644 --- a/crates/annot/src/appearance.rs +++ b/crates/annot/src/appearance.rs @@ -373,16 +373,60 @@ fn caret_layout(d: &Dict, rect: [f64; 4]) -> ([f64; 4], Option<(f64, f64, f64)>) (caret, Some((caret[2] + gap * scale, caret[1] + size * 0.18, size))) } +#[derive(Clone, Copy)] +struct AppearanceContext<'a> { + dict: &'a Dict, + subtype: &'a [u8], + rect: [f64; 4], + cloudy: bool, + opacity: f64, + stroke: Option, + width: f64, +} + +#[derive(Default)] +struct AppearanceDrawing { + resources: Dict, + content: String, + tail: Vec, +} + +impl AppearanceDrawing { + fn new(context: &AppearanceContext<'_>) -> Self { + let mut drawing = Self::default(); + if let Some(gs) = ext_gstate(context.opacity, context.subtype == b"Highlight") { + drawing.resources.set(b"ExtGState".to_vec(), Object::Dict(gs)); + drawing.content.push_str("/GS0 gs\n"); + } + drawing + } +} + /// Draw the normal appearance of an annotation, or `None` if this subtype/variant isn't supported. /// Text the standard fonts can't draw comes out as `?`: [`undrawable_text`] says which, and /// [`crate::set_appearance`] marks the annotation with it (`pdfcraft_fonts::UNDRAWN_MARK`). pub fn build(d: &Dict) -> Option { + let context = appearance_context(d)?; + let drawing = AppearanceDrawing::new(&context); + match context.subtype { + b"Text" => return draw_icon(&context, "Note", [1.0, 0.82, 0.0], drawing), + b"FileAttachment" => return draw_icon(&context, "PushPin", [0.0, 0.47, 0.84], drawing), + b"Stamp" => return draw_stamp(&context, drawing), + b"FreeText" => return draw_free_text(&context, drawing), + _ => {} + } + let mut drawing = drawing; + draw_body(&context, &mut drawing)?; + finish_appearance(&context, drawing) +} + +fn appearance_context(d: &Dict) -> Option> { // Imported measurement appearances may include leaders, captions and formatting that // this builder cannot reproduce. Preserve them rather than silently losing detail. if d.contains(b"Measure") && !d.contains(b"PCMeasureValue") { return None; } - let subtype = d.name(b"Subtype")?.to_vec(); + let subtype = d.name(b"Subtype")?; let rect = nums(d, b"Rect").filter(|r| r.len() == 4)?; let rect = [rect[0].min(rect[2]), rect[1].min(rect[3]), rect[0].max(rect[2]), rect[1].max(rect[3])]; // Cloudy borders (§12.5.4) are drawn for polygons only. @@ -390,520 +434,576 @@ pub fn build(d: &Dict) -> Option { if cloudy && subtype != b"Polygon" { return None; } - let opacity = d.get(b"CA").and_then(|o| o.as_f64()).unwrap_or(1.0).clamp(0.0, 1.0); - let stroke = color(d, b"C")?; - let w = border_width(d); - let mut res = Dict::new(); - let mut c = String::new(); - // Content after `c` that isn't UTF-8 (WinAnsi text). - let mut tail: Vec = Vec::new(); - let markup = matches!(subtype.as_slice(), b"Highlight" | b"Underline" | b"StrikeOut" | b"Squiggly"); - if let Some(gs) = ext_gstate(opacity, subtype == b"Highlight") { - res.set(b"ExtGState".to_vec(), Object::Dict(gs)); - c.push_str("/GS0 gs\n"); - } - match subtype.as_slice() { - b"Text" => { - let col = stroke.unwrap_or([1.0, 0.82, 0.0]); - let icon = d.name(b"Name").map(|n| String::from_utf8_lossy(n).into_owned()).unwrap_or_else(|| "Note".into()); - c.push_str(¬e_icon(&icon, col)); - return Some(form([0.0, 0.0, NOTE_SIZE, NOTE_SIZE], c.as_bytes(), res)); - } - b"FileAttachment" => { - let col = stroke.unwrap_or([0.0, 0.47, 0.84]); - let icon = d.name(b"Name").map(|n| String::from_utf8_lossy(n).into_owned()).unwrap_or_else(|| "PushPin".into()); - c.push_str(&attach_icon(&icon, col)); - return Some(form([0.0, 0.0, NOTE_SIZE, NOTE_SIZE], c.as_bytes(), res)); - } - _ if markup => { - let q = nums(d, b"QuadPoints").filter(|q| !q.is_empty() && q.len() % 8 == 0)?; - let col = stroke?; - for quad in q.as_chunks::<8>().0.iter() { - let p = |i: usize| (quad[2 * i], quad[2 * i + 1]); - let (p1, p2, p3, p4) = (p(0), p(1), p(2), p(3)); - let h = (p1.0 - p3.0).hypot(p1.1 - p3.1); - // A point a fraction `t` of the way from the bottom edge to the top edge. - let at = |bottom: (f64, f64), top: (f64, f64), t: f64| (bottom.0 + (top.0 - bottom.0) * t, bottom.1 + (top.1 - bottom.1) * t); - match subtype.as_slice() { - b"Highlight" => { - c.push_str(&rg(col)); - c.push_str(&format!( - "{} {} m {} {} l {} {} l {} {} l h f\n", - n(p1.0), - n(p1.1), - n(p2.0), - n(p2.1), - n(p4.0), - n(p4.1), - n(p3.0), - n(p3.1) - )); - } - b"Underline" | b"StrikeOut" => { - let lw = (h * 0.07).clamp(0.5, 3.0); - let t = if subtype == b"Underline" { 0.08 } else { 0.42 }; - let (a, b) = (at(p3, p1, t), at(p4, p2, t)); - c.push_str(&format!("{}{} w\n{} {} m {} {} l S\n", rg_stroke(col), n(lw), n(a.0), n(a.1), n(b.0), n(b.1))); - } - _ => { - // Squiggly: a zigzag along the bottom of the quad. - let lw = (h * 0.05).clamp(0.5, 2.0); - let amp = (h * 0.06).max(0.75); - let len = (p4.0 - p3.0).hypot(p4.1 - p3.1); - let step = (h / 4.0).max(1.5); - let steps = ((len / step).ceil() as usize).clamp(1, 10_000); - c.push_str(&format!("{}{} w 1 j\n", rg_stroke(col), n(lw))); - for i in 0..=steps { - let t = i as f64 / steps as f64; - let base = (p3.0 + (p4.0 - p3.0) * t, p3.1 + (p4.1 - p3.1) * t); - let up = if i % 2 == 0 { amp * 2.0 } else { 0.0 }; - let (ux, uy) = if h > 0.0 { ((p1.0 - p3.0) / h, (p1.1 - p3.1) / h) } else { (0.0, 1.0) }; - let (x, y) = (base.0 + ux * up, base.1 + uy * up); - c.push_str(&format!("{} {} {}\n", n(x), n(y), if i == 0 { "m" } else { "l" })); - } - c.push_str("S\n"); - } - } - } - } - b"Redact" => { - // While marked: the outline of each area (the fill comes when applied). - let q = nums(d, b"QuadPoints").filter(|q| !q.is_empty() && q.len() % 8 == 0)?; - let col = stroke.unwrap_or([0.89, 0.13, 0.13]); - c.push_str(&format!("{}1 w\n", rg_stroke(col))); - for quad in q.as_chunks::<8>().0.iter() { - c.push_str(&format!( - "{} {} m {} {} l {} {} l {} {} l h S\n", - n(quad[0]), - n(quad[1]), - n(quad[2]), - n(quad[3]), - n(quad[6]), - n(quad[7]), - n(quad[4]), - n(quad[5]) - )); - } - } - b"Square" | b"Circle" => { - let fill = interior_color(d, None); - if stroke.is_none() && fill.is_none() { - return Some(form(rect, c.as_bytes(), res)); - } - let inset = w / 2.0; - let [x0, y0, x1, y1] = [rect[0] + inset, rect[1] + inset, rect[2] - inset, rect[3] - inset]; - if let Some(f) = fill { - c.push_str(&rg(f)); - } - if let Some(s) = stroke { - c.push_str(&format!("{}{} w\n{}", rg_stroke(s), n(w), dash(d))); - } - if subtype == b"Square" { - c.push_str(&format!("{} {} {} {} re\n", n(x0), n(y0), n(x1 - x0), n(y1 - y0))); - } else { - c.push_str(&ellipse(x0, y0, x1, y1)); - } - c.push_str(match (fill.is_some(), stroke.is_some() && w > 0.0) { - (true, true) => "B\n", - (true, false) => "f\n", - (false, true) => "S\n", - (false, false) => "n\n", - }); - } - b"Line" => { - let l = nums(d, b"L").filter(|l| l.len() == 4 && l.iter().all(|x| x.is_finite()))?; - let col = stroke?; - let ends: Vec> = match d.get(b"LE") { - None => vec![b"None".to_vec(), b"None".to_vec()], - Some(o) => o.as_array()?.iter().map(|e| e.as_name().map(<[u8]>::to_vec)).collect::>()?, - }; - if ends.len() != 2 || ends.iter().any(|e| !known_ending(e)) { - return None; - } - let fill = interior_color(d, Some(col)).unwrap_or(col); - let layout = line_layout(d, [(l[0], l[1]), (l[2], l[3])], w); - let [p, q] = layout.line; - c.push_str(&format!("{}{}{} w 1 J 1 j\n{}", rg_stroke(col), rg(fill), n(w), dash(d))); - for [s, e] in layout.leaders.iter().chain(&layout.strokes).chain(&layout.tick) { - c.push_str(&format!("{} {} m {} {} l S\n", n(s.0), n(s.1), n(e.0), n(e.1))); - } - c.push_str("[] 0 d\n"); - for (end, (tip, from)) in ends.iter().zip([(p, q), (q, p)]) { - if !line_end(&mut c, end, tip, from, w) { - return None; - } - } - if let Some((text, m)) = layout.caption { - // The caption is black, in the standard font the measurement label uses. - tail.extend( - format!("q 0 g BT /Helv {} Tf {} {} {} {} {} {} Tm ", n(CAPTION_SIZE), n(m[0]), n(m[1]), n(m[2]), n(m[3]), n(m[4]), n(m[5])) - .bytes(), - ); - // WinAnsi bytes go into the stream as-is, not through UTF-8. - tail.extend(literal(&win_ansi(&text))); - tail.extend_from_slice(b" Tj ET Q\n"); - res.set(b"Font".to_vec(), helvetica_resource()); - } - } - b"Polygon" | b"PolyLine" => { - let v = nums(d, b"Vertices").filter(|v| v.len() >= 4 && v.len() % 2 == 0 && v.iter().all(|x| x.is_finite()))?; - let pts: Vec<(f64, f64)> = v.as_chunks::<2>().0.iter().map(|p| (p[0], p[1])).collect(); - let col = stroke; - let closed = subtype == b"Polygon"; - let fill = if closed { interior_color(d, None) } else { None }; - let ends = if subtype == b"PolyLine" { - match d.get(b"LE") { - None => None, - Some(o) => { - let names: Vec> = - o.as_array().filter(|a| a.len() == 2)?.iter().map(|e| e.as_name().map(<[u8]>::to_vec)).collect::>()?; - if names.iter().any(|e| !known_ending(e)) { - return None; - } - Some(names) - } - } - } else { - None - }; - if let Some(f) = fill { - c.push_str(&rg(f)); - } - if let Some(s) = col { - c.push_str(&format!("{}{} w 1 J 1 j\n{}", rg_stroke(s), n(w), dash(d))); - } - if cloudy { - let intensity = d.get(b"BE").and_then(|b| b.as_dict()).and_then(|b| b.get(b"I")).and_then(|i| i.as_f64()).unwrap_or(1.0); - c.push_str(&cloud_path(&pts, cloud_radius(w) * intensity.clamp(0.5, 2.0))); - } else { - for (i, p) in pts.iter().enumerate() { - c.push_str(&format!("{} {} {}\n", n(p.0), n(p.1), if i == 0 { "m" } else { "l" })); - } - if closed { - c.push_str("h\n"); - } - } - c.push_str(match (fill.is_some(), col.is_some() && w > 0.0) { - (true, true) => "B\n", - (true, false) => "f\n", - (false, true) => "S\n", - (false, false) => "n\n", - }); - if let Some(ends) = ends { - let col = col?; - let (Some(start), Some(end)) = (ends.first(), ends.get(1)) else { return None }; - let (Some(&tip0), Some(&from0)) = (pts.first(), pts.get(1)) else { return None }; - let (Some(&tip1), Some(&from1)) = (pts.last(), pts.get(pts.len().saturating_sub(2))) else { return None }; - let fill = interior_color(d, Some(col)).unwrap_or(col); - c.push_str(&format!("[] 0 d\n{}", rg(fill))); - if !line_end(&mut c, start, tip0, from0, w) || !line_end(&mut c, end, tip1, from1, w) { - return None; - } - } - } - b"Caret" => { - // A filled caret: two curved flanks meeting at the top centre. - let col = stroke.unwrap_or([0.0, 0.47, 0.84]); - let (caret, pilcrow) = caret_layout(d, rect); - let [x0, y0, x1, y1] = caret; - let (cx, h) = ((x0 + x1) / 2.0, y1 - y0); - c.push_str(&format!( - "{}{} {} m {} {} {} {} {} {} c {} {} {} {} {} {} c h f\n", - rg(col), - n(x0), - n(y0), - n(cx - (x1 - x0) * 0.1), - n(y0 + h * 0.2), - n(cx), - n(y1 - h * 0.25), - n(cx), - n(y1), - n(cx), - n(y1 - h * 0.25), - n(cx + (x1 - x0) * 0.1), - n(y0 + h * 0.2), - n(x1), - n(y0) - )); - if let Some((x, y, size)) = pilcrow { - // `/Sy /P`: a new paragraph symbol beside the caret (Table 183), in its colour. - // 0xB6 is the pilcrow in WinAnsiEncoding. - let mut out = c.into_bytes(); - out.extend(format!("BT /Helv {} Tf {} {} Td (", n(size), n(x), n(y)).bytes()); - out.push(0xB6); - out.extend_from_slice(b") Tj ET\n"); - res.set(b"Font".to_vec(), helvetica_resource()); - return Some(form(rect, &out, res)); - } - } - b"Ink" => { - let col = stroke?; - let list = d.get(b"InkList")?.as_array()?; - // `/BS` gives an ink stroke its width and dash pattern (Table 182). - c.push_str(&format!("{}{} w 1 J 1 j\n{}", rg_stroke(col), n(w), dash(d))); - for s in list { - let pts: Vec = s.as_array()?.iter().map(|o| o.as_f64()).collect::>()?; - let pts: Vec<(f64, f64)> = pts.as_chunks::<2>().0.iter().map(|p| (p[0], p[1])).collect(); - let Some(first) = pts.first() else { continue }; - c.push_str(&format!("{} {} m\n", n(first.0), n(first.1))); - match pts.as_slice() { - [_] => c.push_str(&format!("{} {} l\n", n(first.0 + 0.01), n(first.1))), - [_, end] => c.push_str(&format!("{} {} l\n", n(end.0), n(end.1))), - _ => c.push_str(&smooth_curve(&pts)), - } - c.push_str("S\n"); - } - } - b"Stamp" => { - // A typed signature: filled outlines normalised to the rectangle. - if let Some(outline) = d.get(b"PCOutline").and_then(|o| o.as_array()) { - let [x0, y0, x1, y1] = rect; - let (w, h) = (x1 - x0, y1 - y0); - c.push_str(&rg(stroke.unwrap_or([0.0; 3]))); - for contour in outline { - let v: Vec = contour.as_array().map(|a| a.iter().filter_map(Object::as_f64).collect()).unwrap_or_default(); - for (i, p) in v.as_chunks::<2>().0.iter().enumerate() { - c.push_str(&format!("{} {} {}\n", n(x0 + p[0] * w), n(y0 + p[1] * h), if i == 0 { "m" } else { "l" })); - } - if v.len() >= 6 { - c.push_str("h\n"); - } - } - c.push_str("f\n"); - return Some(form(rect, c.as_bytes(), res)); - } - // A custom stamp: its picture (an image, or a form mapped to /PCPictureSize) fills - // the rectangle. An image signature added to a turned page (`/PCPictureRotate`) gets - // the standard counter-rotation as its form `/Matrix`: viewers fit the turned - // bounding box to `/Rect` (ISO 32000-2 §12.5.5), so it reads upright as displayed. - if let Some(pic) = d.get(b"PCPicture").and_then(Object::as_ref) { - let [x0, y0, x1, y1] = rect; - let (w, h) = (x1 - x0, y1 - y0); - let image = matches!(d.get(b"PCPictureImage"), Some(Object::Bool(true))); - let place = if image { - format!("{} 0 0 {} {} {} cm", n(w), n(h), n(x0), n(y0)) - } else { - let size = nums(d, b"PCPictureSize").filter(|s| s.len() == 2 && s[0] > 0.0 && s[1] > 0.0)?; - format!("{} 0 0 {} {} {} cm", n(w / size[0]), n(h / size[1]), n(x0), n(y0)) - }; - c.push_str(&format!("q {place} /Pic Do Q\n")); - let mut xo = Dict::new(); - xo.set(b"Pic".to_vec(), Object::Ref(pic)); - res.set(b"XObject".to_vec(), Object::Dict(xo)); - let mut stream = form(rect, c.as_bytes(), res); - let turn = picture_turn(d); - if image && turn != 0 { - // The page's view matrix without its offset: display axes in user space. - let m = pdfcraft_model::view_matrix_for(turn, [0.0; 4]); - let matrix = [m[0], m[1], m[2], m[3], 0.0, 0.0]; - stream.dict.set(b"Matrix".to_vec(), Object::Array(matrix.iter().map(|x| Object::Real(*x)).collect())); - } - return Some(stream); - } - // Only PdfCraft's own Fill & Sign marks are drawn here. - let name = d.name(b"Name")?; - let col = stroke.unwrap_or([0.0; 3]); - // A mark or stamp placed on a turned page is drawn upright in its displayed box, then - // mapped into `/Rect` the way the page maps display space into user space. Viewers - // fit that box to `/Rect`; the page rotation then shows it the right way up. - let turn = stamp_turn(d); - let draw = if turn == 0 { - rect - } else { - let (rw, rh) = (rect[2] - rect[0], rect[3] - rect[1]); - let (dw, dh) = if matches!(turn, 90 | 270) { (rh, rw) } else { (rw, rh) }; - if dw < 1.0 || dh < 1.0 { - return None; - } - [0.0, 0.0, dw, dh] - }; - let turned = |mut stream: Stream| { - if turn != 0 { - let m = pdfcraft_model::view_matrix_for(turn, rect); - stream.dict.set(b"Matrix".to_vec(), Object::Array(m.iter().copied().map(Object::Real).collect())); - } - stream - }; - let [x0, y0, x1, y1] = draw; - let (w, h) = (x1 - x0, y1 - y0); - let lw = w.min(h) * 0.12; - match name { - b"PCCheck" => c.push_str(&format!( - "{}{} w 1 J 1 j\n{} {} m {} {} l {} {} l S\n", - rg_stroke(col), - n(lw), - n(x0 + w * 0.15), - n(y0 + h * 0.5), - n(x0 + w * 0.4), - n(y0 + h * 0.2), - n(x0 + w * 0.88), - n(y0 + h * 0.85) - )), - b"PCCross" => c.push_str(&format!( - "{}{} w 1 J\n{} {} m {} {} l {} {} m {} {} l S\n", - rg_stroke(col), - n(lw), - n(x0 + w * 0.18), - n(y0 + h * 0.18), - n(x1 - w * 0.18), - n(y1 - h * 0.18), - n(x0 + w * 0.18), - n(y1 - h * 0.18), - n(x1 - w * 0.18), - n(y0 + h * 0.18) - )), - b"PCDot" => { - let r = w.min(h) * 0.3; - c.push_str(&rg(col)); - c.push_str(&ellipse(x0 + w / 2.0 - r, y0 + h / 2.0 - r, x0 + w / 2.0 + r, y0 + h / 2.0 + r)); - c.push_str("f\n"); - } - b"PCLine" => c.push_str(&format!( - "{}{} w 1 J\n{} {} m {} {} l S\n", - rg_stroke(col), - n(h.clamp(0.5, 2.0)), - n(x0), - n(y0 + h / 2.0), - n(x1), - n(y0 + h / 2.0) - )), - other => { - // Only stamps PdfCraft made: others keep their own artwork. - if !matches!(d.get(b"PCStamp"), Some(Object::Bool(true))) { - return None; - } - let kind = crate::StampKind::from_name(other)?; - let by = d.get(b"PCByLine").and_then(|o| o.as_string()).map(PdfString::to_text); - let sign_here = kind.group() == crate::StampGroup::SignHere; - return Some(turned(stamp(kind.label(), sign_here, draw, stroke.unwrap_or(kind.color()), by.as_deref(), opacity, res))); - } - } - if turn != 0 { - return Some(turned(form(draw, c.as_bytes(), res))); - } - } - b"FreeText" => { - let (text_color, size) = parse_da(d); - let bg = stroke; - let bw = if d.contains(b"BS") || d.contains(b"Border") { border_width(d) } else { 0.0 }; - // A callout: the leader line (arrowhead at its first point), and the text box inside - // `/Rect` by `/RD`. - // Text added to a turned page is drawn upright in its displayed box, which the form - // `/Matrix` then maps into `/Rect` (as for stamps). Callouts keep user-space axes. - let turn = if d.contains(b"CL") { 0 } else { text_turn(d) }; - let (rect, matrix) = if turn == 0 { - (rect, None) - } else { - let (rw, rh) = (rect[2] - rect[0], rect[3] - rect[1]); - let (dw, dh) = if matches!(turn, 90 | 270) { (rh, rw) } else { (rw, rh) }; - if dw < 1.0 || dh < 1.0 { - return None; - } - ([0.0, 0.0, dw, dh], Some(pdfcraft_model::view_matrix_for(turn, rect))) - }; - let full = rect; - let mut rect = rect; - if d.contains(b"CL") { - let cl = nums(d, b"CL").filter(|l| l.len() == 4 || l.len() == 6)?; - let rd = nums(d, b"RD").filter(|r| r.len() == 4 && r.iter().all(|x| *x >= 0.0))?; - rect = [full[0] + rd[0], full[1] + rd[1], full[2] - rd[2], full[3] - rd[3]]; - if rect[2] - rect[0] < 1.0 || rect[3] - rect[1] < 1.0 { - return None; - } - let end = match d.get(b"LE") { - None => b"None".to_vec(), - Some(o) => o.as_name()?.to_vec(), - }; - if !known_ending(&end) { - return None; - } - let lw = bw.max(0.5); - let pts: Vec<(f64, f64)> = cl.as_chunks::<2>().0.iter().map(|p| (p[0], p[1])).collect(); - if pts.len() < 2 || pts.iter().any(|p| !p.0.is_finite() || !p.1.is_finite()) { - return None; - } - c.push_str(&format!("{}{}{} w 1 J 1 j\n", rg_stroke(text_color), rg(bg.unwrap_or([1.0; 3])), n(lw))); - for (i, p) in pts.iter().enumerate() { - c.push_str(&format!("{} {} {}\n", n(p.0), n(p.1), if i == 0 { "m" } else { "l" })); - } - c.push_str("S\n"); - if !line_end(&mut c, &end, pts[0], pts[1], lw) { - return None; - } - } - if let Some(bg) = bg { - c.push_str(&format!("{}{} {} {} {} re f\n", rg(bg), n(rect[0]), n(rect[1]), n(rect[2] - rect[0]), n(rect[3] - rect[1]))); - } - if bw > 0.0 { - let h = bw / 2.0; - c.push_str(&format!( - "{}{} w\n{}{} {} {} {} re S\n[] 0 d\n", - rg_stroke(text_color), - n(bw), - dash(d), - n(rect[0] + h), - n(rect[1] + h), - n(rect[2] - rect[0] - bw), - n(rect[3] - rect[1] - bw) - )); - } - let text = d.get(b"Contents").and_then(|o| o.as_string()).map(PdfString::to_text).unwrap_or_default(); - let pad = 2.0 + bw; - let width = (rect[2] - rect[0] - 2.0 * pad).max(1.0); - let q = d.int(b"Q").unwrap_or(0); - c.push_str(&format!( - "{} {} {} {} re W n\nBT\n/Helv {} Tf\n{}", - n(rect[0]), - n(rect[1]), - n(rect[2] - rect[0]), - n(rect[3] - rect[1]), - n(size), - rg(text_color) - )); - let mut out = c.into_bytes(); - let mut y = rect[3] - pad - size * 0.9; - for line in wrap(&text, size, width) { - if y < rect[1] - size { - break; - } - let lw = text_width(&line, size); - let x = match q { - 1 => rect[0] + pad + (width - lw) / 2.0, - 2 => rect[2] - pad - lw, - _ => rect[0] + pad, - }; - out.extend(format!("1 0 0 1 {} {} Tm ", n(x), n(y)).bytes()); - out.extend(literal(&win_ansi(&line))); - out.extend_from_slice(b" Tj\n"); - y -= size * 1.2; - } - out.extend_from_slice(b"ET\n"); - res.set(b"Font".to_vec(), helvetica_resource()); - let mut stream = form(full, &out, res); - if let Some(m) = matrix { - stream.dict.set(b"Matrix".to_vec(), Object::Array(m.iter().copied().map(Object::Real).collect())); - } - return Some(stream); - } - _ => return None, + Some(AppearanceContext { + dict: d, + subtype, + rect, + cloudy, + opacity: d.get(b"CA").and_then(|o| o.as_f64()).unwrap_or(1.0).clamp(0.0, 1.0), + stroke: color(d, b"C")?, + width: border_width(d), + }) +} + +fn draw_body(context: &AppearanceContext<'_>, drawing: &mut AppearanceDrawing) -> Option<()> { + match context.subtype { + b"Highlight" | b"Underline" | b"StrikeOut" | b"Squiggly" => draw_markup(context, drawing), + b"Redact" => draw_redaction(context, drawing), + b"Square" | b"Circle" => draw_box(context, drawing), + b"Line" => draw_line(context, drawing), + b"Polygon" | b"PolyLine" => draw_polygon(context, drawing), + b"Caret" => draw_caret(context, drawing), + b"Ink" => draw_ink(context, drawing), + _ => None, } +} + +fn finish_appearance(context: &AppearanceContext<'_>, mut drawing: AppearanceDrawing) -> Option { // PdfCraft measurement captions are kept separate from the comment's free-form text. // A restyle regenerates the path and its value together. - let mut out = c.into_bytes(); - out.extend(tail); - if let Some(value) = d.get(b"PCMeasureValue").and_then(Object::as_string) { + let mut out = drawing.content.into_bytes(); + out.extend(drawing.tail); + if let Some(value) = context.dict.get(b"PCMeasureValue").and_then(Object::as_string) { let value = value.to_text(); - if value.chars().count() <= 256 && matches!(subtype.as_slice(), b"Line" | b"PolyLine" | b"Polygon") { + if value.chars().count() <= 256 && matches!(context.subtype, b"Line" | b"PolyLine" | b"Polygon") { let size = 10.0; - let x = (rect[0] + rect[2] - text_width(&value, size)) * 0.5; - let y = rect[3] - 12.0; - let col = stroke.unwrap_or([0.0, 0.47, 0.84]); + let x = (context.rect[0] + context.rect[2] - text_width(&value, size)) * 0.5; + let y = context.rect[3] - 12.0; + let col = context.stroke.unwrap_or([0.0, 0.47, 0.84]); out.extend(format!("{}BT /Helv {} Tf {} {} Td ", rg(col), n(size), n(x), n(y)).bytes()); // WinAnsi bytes (e.g. 0xB2 for "²") go into the stream as-is, not through UTF-8. out.extend(literal(&win_ansi(&value))); out.extend_from_slice(b" Tj ET\n"); - res.set(b"Font".to_vec(), helvetica_resource()); + drawing.resources.set(b"Font".to_vec(), helvetica_resource()); } } - Some(form(rect, &out, res)) + Some(form(context.rect, &out, drawing.resources)) +} + +fn draw_markup(context: &AppearanceContext<'_>, drawing: &mut AppearanceDrawing) -> Option<()> { + let d = context.dict; + let subtype = context.subtype; + let stroke = context.stroke; + let c = &mut drawing.content; + let q = nums(d, b"QuadPoints").filter(|q| !q.is_empty() && q.len() % 8 == 0)?; + let col = stroke?; + for quad in q.as_chunks::<8>().0.iter() { + let p = |i: usize| (quad[2 * i], quad[2 * i + 1]); + let (p1, p2, p3, p4) = (p(0), p(1), p(2), p(3)); + let h = (p1.0 - p3.0).hypot(p1.1 - p3.1); + // A point a fraction `t` of the way from the bottom edge to the top edge. + let at = |bottom: (f64, f64), top: (f64, f64), t: f64| (bottom.0 + (top.0 - bottom.0) * t, bottom.1 + (top.1 - bottom.1) * t); + match subtype { + b"Highlight" => { + c.push_str(&rg(col)); + c.push_str(&format!("{} {} m {} {} l {} {} l {} {} l h f\n", n(p1.0), n(p1.1), n(p2.0), n(p2.1), n(p4.0), n(p4.1), n(p3.0), n(p3.1))); + } + b"Underline" | b"StrikeOut" => { + let lw = (h * 0.07).clamp(0.5, 3.0); + let t = if subtype == b"Underline" { 0.08 } else { 0.42 }; + let (a, b) = (at(p3, p1, t), at(p4, p2, t)); + c.push_str(&format!("{}{} w\n{} {} m {} {} l S\n", rg_stroke(col), n(lw), n(a.0), n(a.1), n(b.0), n(b.1))); + } + _ => { + // Squiggly: a zigzag along the bottom of the quad. + let lw = (h * 0.05).clamp(0.5, 2.0); + let amp = (h * 0.06).max(0.75); + let len = (p4.0 - p3.0).hypot(p4.1 - p3.1); + let step = (h / 4.0).max(1.5); + let steps = ((len / step).ceil() as usize).clamp(1, 10_000); + c.push_str(&format!("{}{} w 1 j\n", rg_stroke(col), n(lw))); + for i in 0..=steps { + let t = i as f64 / steps as f64; + let base = (p3.0 + (p4.0 - p3.0) * t, p3.1 + (p4.1 - p3.1) * t); + let up = if i % 2 == 0 { amp * 2.0 } else { 0.0 }; + let (ux, uy) = if h > 0.0 { ((p1.0 - p3.0) / h, (p1.1 - p3.1) / h) } else { (0.0, 1.0) }; + let (x, y) = (base.0 + ux * up, base.1 + uy * up); + c.push_str(&format!("{} {} {}\n", n(x), n(y), if i == 0 { "m" } else { "l" })); + } + c.push_str("S\n"); + } + } + } + Some(()) +} + +fn draw_redaction(context: &AppearanceContext<'_>, drawing: &mut AppearanceDrawing) -> Option<()> { + let d = context.dict; + let stroke = context.stroke; + let c = &mut drawing.content; + // While marked: the outline of each area (the fill comes when applied). + let q = nums(d, b"QuadPoints").filter(|q| !q.is_empty() && q.len() % 8 == 0)?; + let col = stroke.unwrap_or([0.89, 0.13, 0.13]); + c.push_str(&format!("{}1 w\n", rg_stroke(col))); + for quad in q.as_chunks::<8>().0.iter() { + c.push_str(&format!( + "{} {} m {} {} l {} {} l {} {} l h S\n", + n(quad[0]), + n(quad[1]), + n(quad[2]), + n(quad[3]), + n(quad[6]), + n(quad[7]), + n(quad[4]), + n(quad[5]) + )); + } + Some(()) +} + +fn draw_box(context: &AppearanceContext<'_>, drawing: &mut AppearanceDrawing) -> Option<()> { + let d = context.dict; + let subtype = context.subtype; + let rect = context.rect; + let stroke = context.stroke; + let w = context.width; + let c = &mut drawing.content; + let fill = interior_color(d, None); + if stroke.is_none() && fill.is_none() { + return Some(()); + } + let inset = w / 2.0; + let [x0, y0, x1, y1] = [rect[0] + inset, rect[1] + inset, rect[2] - inset, rect[3] - inset]; + if let Some(f) = fill { + c.push_str(&rg(f)); + } + if let Some(s) = stroke { + c.push_str(&format!("{}{} w\n{}", rg_stroke(s), n(w), dash(d))); + } + if subtype == b"Square" { + c.push_str(&format!("{} {} {} {} re\n", n(x0), n(y0), n(x1 - x0), n(y1 - y0))); + } else { + c.push_str(&ellipse(x0, y0, x1, y1)); + } + c.push_str(match (fill.is_some(), stroke.is_some() && w > 0.0) { + (true, true) => "B\n", + (true, false) => "f\n", + (false, true) => "S\n", + (false, false) => "n\n", + }); + Some(()) +} + +fn draw_line(context: &AppearanceContext<'_>, drawing: &mut AppearanceDrawing) -> Option<()> { + let d = context.dict; + let stroke = context.stroke; + let w = context.width; + let c = &mut drawing.content; + let res = &mut drawing.resources; + let tail = &mut drawing.tail; + let l = nums(d, b"L").filter(|l| l.len() == 4 && l.iter().all(|x| x.is_finite()))?; + let col = stroke?; + let ends: Vec> = match d.get(b"LE") { + None => vec![b"None".to_vec(), b"None".to_vec()], + Some(o) => o.as_array()?.iter().map(|e| e.as_name().map(<[u8]>::to_vec)).collect::>()?, + }; + if ends.len() != 2 || ends.iter().any(|e| !known_ending(e)) { + return None; + } + let fill = interior_color(d, Some(col)).unwrap_or(col); + let layout = line_layout(d, [(l[0], l[1]), (l[2], l[3])], w); + let [p, q] = layout.line; + c.push_str(&format!("{}{}{} w 1 J 1 j\n{}", rg_stroke(col), rg(fill), n(w), dash(d))); + for [s, e] in layout.leaders.iter().chain(&layout.strokes).chain(&layout.tick) { + c.push_str(&format!("{} {} m {} {} l S\n", n(s.0), n(s.1), n(e.0), n(e.1))); + } + c.push_str("[] 0 d\n"); + for (end, (tip, from)) in ends.iter().zip([(p, q), (q, p)]) { + if !line_end(c, end, tip, from, w) { + return None; + } + } + if let Some((text, m)) = layout.caption { + // The caption is black, in the standard font the measurement label uses. + tail.extend( + format!("q 0 g BT /Helv {} Tf {} {} {} {} {} {} Tm ", n(CAPTION_SIZE), n(m[0]), n(m[1]), n(m[2]), n(m[3]), n(m[4]), n(m[5])).bytes(), + ); + // WinAnsi bytes go into the stream as-is, not through UTF-8. + tail.extend(literal(&win_ansi(&text))); + tail.extend_from_slice(b" Tj ET Q\n"); + res.set(b"Font".to_vec(), helvetica_resource()); + } + Some(()) +} + +fn draw_polygon(context: &AppearanceContext<'_>, drawing: &mut AppearanceDrawing) -> Option<()> { + let d = context.dict; + let subtype = context.subtype; + let stroke = context.stroke; + let w = context.width; + let cloudy = context.cloudy; + let c = &mut drawing.content; + let v = nums(d, b"Vertices").filter(|v| v.len() >= 4 && v.len() % 2 == 0 && v.iter().all(|x| x.is_finite()))?; + let pts: Vec<(f64, f64)> = v.as_chunks::<2>().0.iter().map(|p| (p[0], p[1])).collect(); + let col = stroke; + let closed = subtype == b"Polygon"; + let fill = if closed { interior_color(d, None) } else { None }; + let ends = if subtype == b"PolyLine" { + match d.get(b"LE") { + None => None, + Some(o) => { + let names: Vec> = + o.as_array().filter(|a| a.len() == 2)?.iter().map(|e| e.as_name().map(<[u8]>::to_vec)).collect::>()?; + if names.iter().any(|e| !known_ending(e)) { + return None; + } + Some(names) + } + } + } else { + None + }; + if let Some(f) = fill { + c.push_str(&rg(f)); + } + if let Some(s) = col { + c.push_str(&format!("{}{} w 1 J 1 j\n{}", rg_stroke(s), n(w), dash(d))); + } + if cloudy { + let intensity = d.get(b"BE").and_then(|b| b.as_dict()).and_then(|b| b.get(b"I")).and_then(|i| i.as_f64()).unwrap_or(1.0); + c.push_str(&cloud_path(&pts, cloud_radius(w) * intensity.clamp(0.5, 2.0))); + } else { + for (i, p) in pts.iter().enumerate() { + c.push_str(&format!("{} {} {}\n", n(p.0), n(p.1), if i == 0 { "m" } else { "l" })); + } + if closed { + c.push_str("h\n"); + } + } + c.push_str(match (fill.is_some(), col.is_some() && w > 0.0) { + (true, true) => "B\n", + (true, false) => "f\n", + (false, true) => "S\n", + (false, false) => "n\n", + }); + if let Some(ends) = ends { + let col = col?; + let (Some(start), Some(end)) = (ends.first(), ends.get(1)) else { return None }; + let (Some(&tip0), Some(&from0)) = (pts.first(), pts.get(1)) else { return None }; + let (Some(&tip1), Some(&from1)) = (pts.last(), pts.get(pts.len().saturating_sub(2))) else { return None }; + let fill = interior_color(d, Some(col)).unwrap_or(col); + c.push_str(&format!("[] 0 d\n{}", rg(fill))); + if !line_end(c, start, tip0, from0, w) || !line_end(c, end, tip1, from1, w) { + return None; + } + } + Some(()) +} + +fn draw_caret(context: &AppearanceContext<'_>, drawing: &mut AppearanceDrawing) -> Option<()> { + let d = context.dict; + let rect = context.rect; + let stroke = context.stroke; + let c = &mut drawing.content; + // A filled caret: two curved flanks meeting at the top centre. + let col = stroke.unwrap_or([0.0, 0.47, 0.84]); + let (caret, pilcrow) = caret_layout(d, rect); + let [x0, y0, x1, y1] = caret; + let (cx, h) = ((x0 + x1) / 2.0, y1 - y0); + c.push_str(&format!( + "{}{} {} m {} {} {} {} {} {} c {} {} {} {} {} {} c h f\n", + rg(col), + n(x0), + n(y0), + n(cx - (x1 - x0) * 0.1), + n(y0 + h * 0.2), + n(cx), + n(y1 - h * 0.25), + n(cx), + n(y1), + n(cx), + n(y1 - h * 0.25), + n(cx + (x1 - x0) * 0.1), + n(y0 + h * 0.2), + n(x1), + n(y0) + )); + if let Some((x, y, size)) = pilcrow { + // `/Sy /P`: a new paragraph symbol beside the caret (Table 183), in its colour. + // 0xB6 is the pilcrow in WinAnsiEncoding. + drawing.tail.extend(format!("BT /Helv {} Tf {} {} Td (", n(size), n(x), n(y)).bytes()); + drawing.tail.push(0xB6); + drawing.tail.extend_from_slice(b") Tj ET\n"); + drawing.resources.set(b"Font".to_vec(), helvetica_resource()); + } + Some(()) +} + +fn draw_ink(context: &AppearanceContext<'_>, drawing: &mut AppearanceDrawing) -> Option<()> { + let d = context.dict; + let stroke = context.stroke; + let w = context.width; + let c = &mut drawing.content; + let col = stroke?; + let list = d.get(b"InkList")?.as_array()?; + // `/BS` gives an ink stroke its width and dash pattern (Table 182). + c.push_str(&format!("{}{} w 1 J 1 j\n{}", rg_stroke(col), n(w), dash(d))); + for s in list { + let pts: Vec = s.as_array()?.iter().map(|o| o.as_f64()).collect::>()?; + let pts: Vec<(f64, f64)> = pts.as_chunks::<2>().0.iter().map(|p| (p[0], p[1])).collect(); + let Some(first) = pts.first() else { continue }; + c.push_str(&format!("{} {} m\n", n(first.0), n(first.1))); + match pts.as_slice() { + [_] => c.push_str(&format!("{} {} l\n", n(first.0 + 0.01), n(first.1))), + [_, end] => c.push_str(&format!("{} {} l\n", n(end.0), n(end.1))), + _ => c.push_str(&smooth_curve(&pts)), + } + c.push_str("S\n"); + } + Some(()) +} + +fn draw_stamp(context: &AppearanceContext<'_>, mut drawing: AppearanceDrawing) -> Option { + let d = context.dict; + let rect = context.rect; + let stroke = context.stroke; + let opacity = context.opacity; + let c = &mut drawing.content; + let mut res = std::mem::take(&mut drawing.resources); + // A typed signature: filled outlines normalised to the rectangle. + if let Some(outline) = d.get(b"PCOutline").and_then(|o| o.as_array()) { + let [x0, y0, x1, y1] = rect; + let (w, h) = (x1 - x0, y1 - y0); + c.push_str(&rg(stroke.unwrap_or([0.0; 3]))); + for contour in outline { + let v: Vec = contour.as_array().map(|a| a.iter().filter_map(Object::as_f64).collect()).unwrap_or_default(); + for (i, p) in v.as_chunks::<2>().0.iter().enumerate() { + c.push_str(&format!("{} {} {}\n", n(x0 + p[0] * w), n(y0 + p[1] * h), if i == 0 { "m" } else { "l" })); + } + if v.len() >= 6 { + c.push_str("h\n"); + } + } + c.push_str("f\n"); + return Some(form(rect, c.as_bytes(), res)); + } + // A custom stamp: its picture (an image, or a form mapped to /PCPictureSize) fills + // the rectangle. An image signature added to a turned page (`/PCPictureRotate`) gets + // the standard counter-rotation as its form `/Matrix`: viewers fit the turned + // bounding box to `/Rect` (ISO 32000-2 §12.5.5), so it reads upright as displayed. + if let Some(pic) = d.get(b"PCPicture").and_then(Object::as_ref) { + let [x0, y0, x1, y1] = rect; + let (w, h) = (x1 - x0, y1 - y0); + let image = matches!(d.get(b"PCPictureImage"), Some(Object::Bool(true))); + let place = if image { + format!("{} 0 0 {} {} {} cm", n(w), n(h), n(x0), n(y0)) + } else { + let size = nums(d, b"PCPictureSize").filter(|s| s.len() == 2 && s[0] > 0.0 && s[1] > 0.0)?; + format!("{} 0 0 {} {} {} cm", n(w / size[0]), n(h / size[1]), n(x0), n(y0)) + }; + c.push_str(&format!("q {place} /Pic Do Q\n")); + let mut xo = Dict::new(); + xo.set(b"Pic".to_vec(), Object::Ref(pic)); + res.set(b"XObject".to_vec(), Object::Dict(xo)); + let mut stream = form(rect, c.as_bytes(), res); + let turn = picture_turn(d); + if image && turn != 0 { + // The page's view matrix without its offset: display axes in user space. + let m = pdfcraft_model::view_matrix_for(turn, [0.0; 4]); + let matrix = [m[0], m[1], m[2], m[3], 0.0, 0.0]; + stream.dict.set(b"Matrix".to_vec(), Object::Array(matrix.iter().map(|x| Object::Real(*x)).collect())); + } + return Some(stream); + } + // Only PdfCraft's own Fill & Sign marks are drawn here. + let name = d.name(b"Name")?; + let col = stroke.unwrap_or([0.0; 3]); + // A mark or stamp placed on a turned page is drawn upright in its displayed box, then + // mapped into `/Rect` the way the page maps display space into user space. Viewers + // fit that box to `/Rect`; the page rotation then shows it the right way up. + let turn = stamp_turn(d); + let draw = if turn == 0 { + rect + } else { + let (rw, rh) = (rect[2] - rect[0], rect[3] - rect[1]); + let (dw, dh) = if matches!(turn, 90 | 270) { (rh, rw) } else { (rw, rh) }; + if dw < 1.0 || dh < 1.0 { + return None; + } + [0.0, 0.0, dw, dh] + }; + let turned = |mut stream: Stream| { + if turn != 0 { + let m = pdfcraft_model::view_matrix_for(turn, rect); + stream.dict.set(b"Matrix".to_vec(), Object::Array(m.iter().copied().map(Object::Real).collect())); + } + stream + }; + let [x0, y0, x1, y1] = draw; + let (w, h) = (x1 - x0, y1 - y0); + let lw = w.min(h) * 0.12; + match name { + b"PCCheck" => c.push_str(&format!( + "{}{} w 1 J 1 j\n{} {} m {} {} l {} {} l S\n", + rg_stroke(col), + n(lw), + n(x0 + w * 0.15), + n(y0 + h * 0.5), + n(x0 + w * 0.4), + n(y0 + h * 0.2), + n(x0 + w * 0.88), + n(y0 + h * 0.85) + )), + b"PCCross" => c.push_str(&format!( + "{}{} w 1 J\n{} {} m {} {} l {} {} m {} {} l S\n", + rg_stroke(col), + n(lw), + n(x0 + w * 0.18), + n(y0 + h * 0.18), + n(x1 - w * 0.18), + n(y1 - h * 0.18), + n(x0 + w * 0.18), + n(y1 - h * 0.18), + n(x1 - w * 0.18), + n(y0 + h * 0.18) + )), + b"PCDot" => { + let r = w.min(h) * 0.3; + c.push_str(&rg(col)); + c.push_str(&ellipse(x0 + w / 2.0 - r, y0 + h / 2.0 - r, x0 + w / 2.0 + r, y0 + h / 2.0 + r)); + c.push_str("f\n"); + } + b"PCLine" => c.push_str(&format!( + "{}{} w 1 J\n{} {} m {} {} l S\n", + rg_stroke(col), + n(h.clamp(0.5, 2.0)), + n(x0), + n(y0 + h / 2.0), + n(x1), + n(y0 + h / 2.0) + )), + other => { + // Only stamps PdfCraft made: others keep their own artwork. + if !matches!(d.get(b"PCStamp"), Some(Object::Bool(true))) { + return None; + } + let kind = crate::StampKind::from_name(other)?; + let by = d.get(b"PCByLine").and_then(|o| o.as_string()).map(PdfString::to_text); + let sign_here = kind.group() == crate::StampGroup::SignHere; + return Some(turned(stamp(kind.label(), sign_here, draw, stroke.unwrap_or(kind.color()), by.as_deref(), opacity, res))); + } + } + if turn != 0 { + return Some(turned(form(draw, c.as_bytes(), res))); + } + Some(form(rect, c.as_bytes(), res)) +} + +fn draw_free_text(context: &AppearanceContext<'_>, mut drawing: AppearanceDrawing) -> Option { + let d = context.dict; + let rect = context.rect; + let stroke = context.stroke; + let mut c = std::mem::take(&mut drawing.content); + let mut res = std::mem::take(&mut drawing.resources); + let _tail = std::mem::take(&mut drawing.tail); + let (text_color, size) = parse_da(d); + let bg = stroke; + let bw = if d.contains(b"BS") || d.contains(b"Border") { border_width(d) } else { 0.0 }; + // A callout: the leader line (arrowhead at its first point), and the text box inside + // `/Rect` by `/RD`. + // Text added to a turned page is drawn upright in its displayed box, which the form + // `/Matrix` then maps into `/Rect` (as for stamps). Callouts keep user-space axes. + let turn = if d.contains(b"CL") { 0 } else { text_turn(d) }; + let (rect, matrix) = if turn == 0 { + (rect, None) + } else { + let (rw, rh) = (rect[2] - rect[0], rect[3] - rect[1]); + let (dw, dh) = if matches!(turn, 90 | 270) { (rh, rw) } else { (rw, rh) }; + if dw < 1.0 || dh < 1.0 { + return None; + } + ([0.0, 0.0, dw, dh], Some(pdfcraft_model::view_matrix_for(turn, rect))) + }; + let full = rect; + let mut rect = rect; + if d.contains(b"CL") { + let cl = nums(d, b"CL").filter(|l| l.len() == 4 || l.len() == 6)?; + let rd = nums(d, b"RD").filter(|r| r.len() == 4 && r.iter().all(|x| *x >= 0.0))?; + rect = [full[0] + rd[0], full[1] + rd[1], full[2] - rd[2], full[3] - rd[3]]; + if rect[2] - rect[0] < 1.0 || rect[3] - rect[1] < 1.0 { + return None; + } + let end = match d.get(b"LE") { + None => b"None".to_vec(), + Some(o) => o.as_name()?.to_vec(), + }; + if !known_ending(&end) { + return None; + } + let lw = bw.max(0.5); + let pts: Vec<(f64, f64)> = cl.as_chunks::<2>().0.iter().map(|p| (p[0], p[1])).collect(); + if pts.len() < 2 || pts.iter().any(|p| !p.0.is_finite() || !p.1.is_finite()) { + return None; + } + c.push_str(&format!("{}{}{} w 1 J 1 j\n", rg_stroke(text_color), rg(bg.unwrap_or([1.0; 3])), n(lw))); + for (i, p) in pts.iter().enumerate() { + c.push_str(&format!("{} {} {}\n", n(p.0), n(p.1), if i == 0 { "m" } else { "l" })); + } + c.push_str("S\n"); + if !line_end(&mut c, &end, pts[0], pts[1], lw) { + return None; + } + } + if let Some(bg) = bg { + c.push_str(&format!("{}{} {} {} {} re f\n", rg(bg), n(rect[0]), n(rect[1]), n(rect[2] - rect[0]), n(rect[3] - rect[1]))); + } + if bw > 0.0 { + let h = bw / 2.0; + c.push_str(&format!( + "{}{} w\n{}{} {} {} {} re S\n[] 0 d\n", + rg_stroke(text_color), + n(bw), + dash(d), + n(rect[0] + h), + n(rect[1] + h), + n(rect[2] - rect[0] - bw), + n(rect[3] - rect[1] - bw) + )); + } + let text = d.get(b"Contents").and_then(|o| o.as_string()).map(PdfString::to_text).unwrap_or_default(); + let pad = 2.0 + bw; + let width = (rect[2] - rect[0] - 2.0 * pad).max(1.0); + let q = d.int(b"Q").unwrap_or(0); + c.push_str(&format!( + "{} {} {} {} re W n\nBT\n/Helv {} Tf\n{}", + n(rect[0]), + n(rect[1]), + n(rect[2] - rect[0]), + n(rect[3] - rect[1]), + n(size), + rg(text_color) + )); + let mut out = c.into_bytes(); + let mut y = rect[3] - pad - size * 0.9; + for line in wrap(&text, size, width) { + if y < rect[1] - size { + break; + } + let lw = text_width(&line, size); + let x = match q { + 1 => rect[0] + pad + (width - lw) / 2.0, + 2 => rect[2] - pad - lw, + _ => rect[0] + pad, + }; + out.extend(format!("1 0 0 1 {} {} Tm ", n(x), n(y)).bytes()); + out.extend(literal(&win_ansi(&line))); + out.extend_from_slice(b" Tj\n"); + y -= size * 1.2; + } + out.extend_from_slice(b"ET\n"); + res.set(b"Font".to_vec(), helvetica_resource()); + let mut stream = form(full, &out, res); + if let Some(m) = matrix { + stream.dict.set(b"Matrix".to_vec(), Object::Array(m.iter().copied().map(Object::Real).collect())); + } + Some(stream) +} + +fn draw_icon(context: &AppearanceContext<'_>, name: &str, fallback: Rgb, mut drawing: AppearanceDrawing) -> Option { + let d = context.dict; + let col = context.stroke.unwrap_or(fallback); + let icon = d.name(b"Name").map(|n| String::from_utf8_lossy(n).into_owned()).unwrap_or_else(|| name.into()); + let content = if name == "Note" { note_icon(&icon, col) } else { attach_icon(&icon, col) }; + drawing.content.push_str(&content); + Some(form([0.0, 0.0, NOTE_SIZE, NOTE_SIZE], drawing.content.as_bytes(), drawing.resources)) } diff --git a/crates/annot/src/appearance/symbols.rs b/crates/annot/src/appearance/symbols.rs index d49224cd9f..3b33662524 100644 --- a/crates/annot/src/appearance/symbols.rs +++ b/crates/annot/src/appearance/symbols.rs @@ -1,4 +1,4 @@ -use super::*; +use super::{Dict, Object, PdfString, Rgb, Stream, color, ext_gstate, form, literal, n, nums, rg, rg_stroke, text_width, win_ansi}; /// The label and colour of a standard rubber stamp name (ISO 32000-2 Table 184), for a stamp /// another program wrote without an appearance. Names are matched byte for byte, as PDF names diff --git a/crates/annot/src/create.rs b/crates/annot/src/create.rs index bedd1c6f15..a6db5b940b 100644 --- a/crates/annot/src/create.rs +++ b/crates/annot/src/create.rs @@ -1,8 +1,10 @@ use super::draw::draw_appearance; use super::lookup::{annot_dict, annot_ref, annots, fill_sign_shape, page_ref, set_annots}; use super::modify::{n, rich_text}; -use super::types::{FLAG_NO_ROTATE, FLAG_NO_ZOOM, FLAG_PRINT, LineEnding, Markup, Meta, NOTE_SIZE, NewAnnotation, Rgb, Shape, StampGroup, Style}; -use super::*; +use super::types::{ + FLAG_NO_ROTATE, FLAG_NO_ZOOM, FLAG_PRINT, LineEnding, Markup, Meta, NOTE_SIZE, NewAnnotation, OverlayLook, Rgb, Shape, StampGroup, Style, +}; +use super::{AnnotError, Dict, Document, ObjRef, Object, PdfString, appearance}; pub(crate) fn num_array(v: &[f64]) -> Object { Object::Array(v.iter().map(|x| Object::Real(*x)).collect()) @@ -203,16 +205,12 @@ pub fn callout_attach(rect: [f64; 4], knee: [f64; 2]) -> [f64; 2] { pub fn add_annotation(doc: &mut Document, new: &NewAnnotation, meta: &Meta) -> Result { let page = page_ref(doc, new.page)?; let style = &new.style; - if !finite(&style.color) || !style.opacity.is_finite() || !style.width.is_finite() { - return Err(AnnotError::Invalid("invalid style".into())); - } + validate_style(style)?; let rect = rect_for(&new.shape, style)?; let mut d = base_dict(new.shape.subtype(), rect, page, &new.contents, &new.author, meta); d.set(b"Subj".to_vec(), PdfString::text(subject(&new.shape))); let opacity = style.opacity.clamp(0.0, 1.0); - if opacity < 1.0 { - d.set(b"CA".to_vec(), Object::Real(opacity)); - } + set_non_opaque_style(&mut d, opacity); let border = |d: &mut Dict| { let mut bs = Dict::new(); bs.set(b"W".to_vec(), Object::Real(style.width.max(0.0))); @@ -232,24 +230,7 @@ pub fn add_annotation(doc: &mut Document, new: &NewAnnotation, meta: &Meta) -> R d.set(b"C".to_vec(), rgb(style.color)); d.set(b"QuadPoints".to_vec(), num_array(&quads.concat())); } - Shape::Redact { quads, overlay, look } => { - d.set(b"C".to_vec(), rgb(style.color)); - d.set(b"IC".to_vec(), rgb(style.fill.unwrap_or([0.0, 0.0, 0.0]))); - d.set(b"QuadPoints".to_vec(), num_array(&quads.concat())); - if !overlay.is_empty() { - d.set(b"OverlayText".to_vec(), PdfString::text(overlay)); - let [r, g, b] = look.color.map(|x| x.clamp(0.0, 1.0)); - let size = if look.size > 0.0 { look.size.min(400.0) } else { 0.0 }; - d.set( - b"DA".to_vec(), - PdfString::literal(format!("{} {} {} rg /{} {} Tf", n(r), n(g), n(b), look.font.resource(), n(size)).into_bytes()), - ); - d.set(b"Q".to_vec(), Object::Int(look.align.min(2) as i64)); - if look.repeat { - d.set(b"Repeat".to_vec(), Object::Bool(true)); - } - } - } + Shape::Redact { quads, overlay, look } => set_redaction_properties(&mut d, style, quads, overlay, look), Shape::Rectangle { .. } | Shape::Oval { .. } => { d.set(b"C".to_vec(), rgb(style.color)); if let Some(f) = style.fill { @@ -426,22 +407,55 @@ pub fn add_annotation(doc: &mut Document, new: &NewAnnotation, meta: &Meta) -> R let mut list = annots(doc, page); let index = list.len(); list.push(Object::Ref(r)); - if let Some(pr) = popup { - let mut p = Dict::new(); - p.set(b"Type".to_vec(), Object::name("Annot")); - p.set(b"Subtype".to_vec(), Object::name("Popup")); - p.set(b"Rect".to_vec(), num_array(&pr)); - p.set(b"Parent".to_vec(), Object::Ref(r)); - p.set(b"Open".to_vec(), Object::Bool(false)); - p.set(b"F".to_vec(), Object::Int(FLAG_PRINT | FLAG_NO_ZOOM | FLAG_NO_ROTATE)); - let pref = doc.add(Object::Dict(p)); - doc.update_dict(r, |d| d.set(b"Popup".to_vec(), Object::Ref(pref)))?; - list.push(Object::Ref(pref)); - } + add_popup(doc, r, popup, &mut list)?; set_annots(doc, page, list)?; Ok(index) } +fn validate_style(style: &Style) -> Result<(), AnnotError> { + if !finite(&style.color) || !style.opacity.is_finite() || !style.width.is_finite() { + return Err(AnnotError::Invalid("invalid style".into())); + } + Ok(()) +} + +fn set_redaction_properties(dict: &mut Dict, style: &Style, quads: &[[f64; 8]], overlay: &str, look: &OverlayLook) { + dict.set(b"C".to_vec(), rgb(style.color)); + dict.set(b"IC".to_vec(), rgb(style.fill.unwrap_or([0.0, 0.0, 0.0]))); + dict.set(b"QuadPoints".to_vec(), num_array(&quads.concat())); + if !overlay.is_empty() { + dict.set(b"OverlayText".to_vec(), PdfString::text(overlay)); + let [r, g, b] = look.color.map(|x| x.clamp(0.0, 1.0)); + let size = if look.size > 0.0 { look.size.min(400.0) } else { 0.0 }; + dict.set(b"DA".to_vec(), PdfString::literal(format!("{} {} {} rg /{} {} Tf", n(r), n(g), n(b), look.font.resource(), n(size)).into_bytes())); + dict.set(b"Q".to_vec(), Object::Int(look.align.min(2) as i64)); + if look.repeat { + dict.set(b"Repeat".to_vec(), Object::Bool(true)); + } + } +} + +fn set_non_opaque_style(dict: &mut Dict, opacity: f64) { + if opacity < 1.0 { + dict.set(b"CA".to_vec(), Object::Real(opacity)); + } +} + +fn add_popup(doc: &mut Document, parent: ObjRef, rect: Option<[f64; 4]>, annots: &mut Vec) -> Result<(), AnnotError> { + let Some(rect) = rect else { return Ok(()) }; + let mut popup = Dict::new(); + popup.set(b"Type".to_vec(), Object::name("Annot")); + popup.set(b"Subtype".to_vec(), Object::name("Popup")); + popup.set(b"Rect".to_vec(), num_array(&rect)); + popup.set(b"Parent".to_vec(), Object::Ref(parent)); + popup.set(b"Open".to_vec(), Object::Bool(false)); + popup.set(b"F".to_vec(), Object::Int(FLAG_PRINT | FLAG_NO_ZOOM | FLAG_NO_ROTATE)); + let popup_ref = doc.add(Object::Dict(popup)); + doc.update_dict(parent, |dict| dict.set(b"Popup".to_vec(), Object::Ref(popup_ref)))?; + annots.push(Object::Ref(popup_ref)); + Ok(()) +} + /// Counterrotate a newly placed picture stamp's appearance into displayed-page axes. /// The picture may be an image or a PDF page. The normal appearance's transformed bounding /// box is fitted to `/Rect` by PDF viewers. diff --git a/crates/annot/src/draw.rs b/crates/annot/src/draw.rs index 1898454415..5e698332da 100644 --- a/crates/annot/src/draw.rs +++ b/crates/annot/src/draw.rs @@ -2,7 +2,7 @@ use super::create::{finite, num_array}; use super::lookup::{annot_dict, annots, page_refs}; use super::modify::refuse_foreign_text; use super::types::NOTE_SIZE; -use super::*; +use super::{AnnotError, Dict, Document, ObjRef, Object, Stream, appearance}; /// (Re)generate `/AP /N` for the annotation `r` from its dictionary, for an edit that keeps its /// text (a restyle, a new size or colour). diff --git a/crates/annot/src/info.rs b/crates/annot/src/info.rs index bea14d9ee2..b56e0de20d 100644 --- a/crates/annot/src/info.rs +++ b/crates/annot/src/info.rs @@ -3,7 +3,7 @@ use super::draw::set_appearance; use super::lookup::{annot_dict, annot_ref, annotation_flags, annots, drawn_upright, is_fill_sign, page_ref, page_refs}; use super::modify::{fillable, touch, unlocked}; use super::types::{FLAG_LOCKED, LineEnding, Meta, NoteIcon, Rgb}; -use super::*; +use super::{AnnotError, Dict, Document, ObjRef, Object, PdfString, appearance}; // ── reading ───────────────────────────────────────────────────────────────────────────────── diff --git a/crates/annot/src/lib.rs b/crates/annot/src/lib.rs index 1d85d0bd64..e9e0359ce0 100644 --- a/crates/annot/src/lib.rs +++ b/crates/annot/src/lib.rs @@ -41,7 +41,7 @@ pub use modify::{ }; pub use types::{ AttachIcon, FillMark, LineEnding, Markup, Meta, NOTE_SIZE, NewAnnotation, NoteIcon, OverlayFont, OverlayLook, ReviewState, Rgb, Shape, - StampGroup, StampKind, Style, rect_quad, + StampGroup, StampKind, Style, StyleChange, TextReplacement, rect_quad, }; pub mod appearance; diff --git a/crates/annot/src/lookup.rs b/crates/annot/src/lookup.rs index 00ce23c37f..c81ec78ef4 100644 --- a/crates/annot/src/lookup.rs +++ b/crates/annot/src/lookup.rs @@ -1,6 +1,6 @@ use super::info::text_value; use super::types::{FLAG_HIDDEN, FLAG_NO_ROTATE, FLAG_NO_VIEW, Shape}; -use super::*; +use super::{AnnotError, Dict, Document, ObjRef, Object, appearance}; // ── pages and /Annots ─────────────────────────────────────────────────────────────────────── diff --git a/crates/annot/src/modify.rs b/crates/annot/src/modify.rs index 992b3d0c51..fc81348075 100644 --- a/crates/annot/src/modify.rs +++ b/crates/annot/src/modify.rs @@ -6,8 +6,9 @@ use super::info::{line_endings_of, text_value}; use super::lookup::{annot_dict, annot_ref, annotation_flags, annots, page_ref, set_annots}; use super::types::{ FLAG_HIDDEN, FLAG_LOCKED, FLAG_NO_ROTATE, FLAG_NO_ZOOM, FLAG_PRINT, LineEnding, Markup, Meta, NewAnnotation, ReviewState, Rgb, Shape, Style, + StyleChange, TextReplacement, }; -use super::*; +use super::{AnnotError, Dict, Document, HashMap, HashSet, ObjRef, Object, PdfString, appearance}; /// A comment another program drew, whose text the standard fonts can't draw. Redrawing it would /// replace those characters with `?`, so the edit is refused before the dictionary changes. @@ -499,17 +500,8 @@ fn border_width_of(d: &Dict) -> f64 { } /// Change a comment's colour, opacity, line width and/or line endings, and redraw it. -#[allow(clippy::too_many_arguments)] -pub fn set_style( - doc: &mut Document, - page: usize, - index: usize, - color: Option, - opacity: Option, - width: Option, - endings: Option<&[LineEnding]>, - meta: &Meta, -) -> Result<(), AnnotError> { +pub fn set_style(doc: &mut Document, page: usize, index: usize, change: StyleChange, meta: &Meta) -> Result<(), AnnotError> { + let StyleChange { color, opacity, width, endings } = change; let (_, r) = annot_ref(doc, page, index)?; unlocked(doc, r)?; let d = annot_dict(doc, r); @@ -521,7 +513,7 @@ pub fn set_style( if color.is_some_and(|c| !finite(&c)) || opacity.is_some_and(|o| !o.is_finite()) || width.is_some_and(|w| !w.is_finite()) { return Err(AnnotError::Invalid("invalid style".into())); } - if let Some(ends) = endings { + if let Some(ends) = &endings { let callout = subtype == "FreeText" && d.contains(b"CL"); let pair = matches!(subtype.as_str(), "Line" | "PolyLine"); if (callout && ends.len() != 1) || (pair && ends.len() != 2) || (!callout && !pair) { @@ -691,18 +683,8 @@ fn pair_points(d: &Dict, key: &[u8]) -> Option> { /// to, so one id for both writes `inreplyto` equal to the caret's own `name`, and a reader that /// resolves names (Acrobat, and our own importer) loses the pair. `caret_meta` is a second id /// from the caller, so the edit stays deterministic. -#[allow(clippy::too_many_arguments)] -pub fn add_text_replacement( - doc: &mut Document, - page: usize, - quads: &[[f64; 8]], - replacement: &str, - author: &str, - strike: &Style, - caret: &Style, - meta: &Meta, - caret_meta: &Meta, -) -> Result { +pub fn add_text_replacement(doc: &mut Document, replacement: TextReplacement<'_>) -> Result { + let TextReplacement { page, quads, replacement, author, strike, caret, strike_meta: meta, caret_meta } = replacement; let last = *quads.last().ok_or_else(|| AnnotError::Invalid("select the text to replace first".into()))?; let s = add_annotation( doc, diff --git a/crates/annot/src/tests.rs b/crates/annot/src/tests.rs index b9e47e5fb9..eb8d1a0f15 100644 --- a/crates/annot/src/tests.rs +++ b/crates/annot/src/tests.rs @@ -303,7 +303,7 @@ fn move_shifts_all_geometry_and_the_popup() { fn restyle_and_resize_redraw_the_appearance() { let mut doc = fixture(); let r = add_annotation(&mut doc, &new(0, Shape::Rectangle { rect: [10.0, 10.0, 110.0, 60.0] }), &meta("r")).unwrap(); - set_style(&mut doc, 0, r, Some([1.0, 0.0, 0.0]), Some(0.5), Some(4.0), None, &meta("")).unwrap(); + set_style(&mut doc, 0, r, StyleChange::new(Some([1.0, 0.0, 0.0]), Some(0.5), Some(4.0), None), &meta("")).unwrap(); set_rect(&mut doc, 0, r, [0.0, 0.0, 200.0, 100.0], &meta("")).unwrap(); let doc2 = reopen(&doc); let d = &list(&doc2, 0)[r]; @@ -313,7 +313,10 @@ fn restyle_and_resize_redraw_the_appearance() { assert_eq!(d.get(b"CA").and_then(|o| o.as_f64()), Some(0.5)); // A stamp's appearance can't be regenerated, so restyling it changes nothing. let before = list(&doc, 1)[0].clone(); - assert_eq!(set_style(&mut doc, 1, 0, Some([0.0; 3]), None, None, None, &meta("")), Err(AnnotError::Unsupported("Stamp".into()))); + assert_eq!( + set_style(&mut doc, 1, 0, StyleChange::new(Some([0.0; 3]), None, None, None), &meta("")), + Err(AnnotError::Unsupported("Stamp".into())) + ); assert_eq!(list(&doc, 1)[0], before); // Lines can't be resized as rectangles. let l = add_annotation( @@ -374,7 +377,7 @@ fn text_box_text_and_colour_changes_are_drawn() { let mut doc = fixture(); let t = add_annotation(&mut doc, &new(0, Shape::TextBox { rect: [0.0, 0.0, 300.0, 100.0], font_size: 12.0 }), &meta("t")).unwrap(); set_contents(&mut doc, 0, t, "Caf\u{e9} (draft) \u{2014} 100%", &meta("")).unwrap(); - set_style(&mut doc, 0, t, Some([1.0, 0.0, 0.0]), None, None, None, &meta("")).unwrap(); + set_style(&mut doc, 0, t, StyleChange::new(Some([1.0, 0.0, 0.0]), None, None, None), &meta("")).unwrap(); let doc = reopen(&doc); let d = &list(&doc, 0)[t]; assert_eq!(text(d, b"Contents"), "Caf\u{e9} (draft) \u{2014} 100%"); @@ -556,8 +559,8 @@ fn fill_and_sign_items_are_drawn() { assert_eq!(text(&all[s], b"Subj"), "Signature"); // Other stamps still can't be restyled; ours can. let mut doc = doc; - set_style(&mut doc, 1, marks[0], Some([0.0, 0.0, 1.0]), None, None, None, &meta("")).unwrap(); - assert!(set_style(&mut doc, 1, 0, Some([0.0; 3]), None, None, None, &meta("")).is_err()); + set_style(&mut doc, 1, marks[0], StyleChange::new(Some([0.0, 0.0, 1.0]), None, None, None), &meta("")).unwrap(); + assert!(set_style(&mut doc, 1, 0, StyleChange::new(Some([0.0; 3]), None, None, None), &meta("")).is_err()); } #[test] @@ -844,7 +847,20 @@ fn replace_text_groups_a_strikeout_and_a_caret() { let quads = [[100.0, 720.0, 200.0, 720.0, 100.0, 706.0, 200.0, 706.0]]; let red = Style { color: [0.89, 0.13, 0.13], opacity: 1.0, width: 1.0, fill: None }; let blue = Style { color: [0.0, 0.47, 0.84], opacity: 1.0, width: 1.0, fill: None }; - let i = add_text_replacement(&mut doc, 0, &quads, "new words", "Ada", &red, &blue, &meta("r"), &meta("r-caret")).unwrap(); + let i = add_text_replacement( + &mut doc, + TextReplacement { + page: 0, + quads: &quads, + replacement: "new words", + author: "Ada", + strike: &red, + caret: &blue, + strike_meta: &meta("r"), + caret_meta: &meta("r-caret"), + }, + ) + .unwrap(); let doc = reopen(&doc); let a = list(&doc, 0); let strike = &a[i]; @@ -866,7 +882,22 @@ fn replace_text_groups_a_strikeout_and_a_caret() { let mut doc = doc; delete_annotation(&mut doc, 0, i).unwrap(); assert!(!list(&doc, 0).iter().any(|d| d.name(b"Subtype") == Some(b"Caret"))); - assert!(add_text_replacement(&mut doc, 0, &[], "x", "Ada", &red, &blue, &meta("r"), &meta("r-caret")).is_err()); + assert!( + add_text_replacement( + &mut doc, + TextReplacement { + page: 0, + quads: &[], + replacement: "x", + author: "Ada", + strike: &red, + caret: &blue, + strike_meta: &meta("r"), + caret_meta: &meta("r-caret") + } + ) + .is_err() + ); } #[test] @@ -1177,7 +1208,7 @@ fn every_line_ending_is_drawn() { ) .unwrap(); let before = rect(&list(&doc, 0).into_iter().find(|d| d.name(b"Subtype") == Some(b"Line")).expect("line")); - set_style(&mut doc, 0, index, None, None, None, Some(&[LineEnding::None, LineEnding::Square]), &meta("style")).unwrap(); + set_style(&mut doc, 0, index, StyleChange::new(None, None, None, Some(vec![LineEnding::None, LineEnding::Square])), &meta("style")).unwrap(); let mut doc = reopen(&doc); let line = list(&doc, 0).into_iter().find(|d| d.name(b"Subtype") == Some(b"Line")).expect("line"); let after = rect(&line); @@ -1245,7 +1276,7 @@ fn redraw_keeps_shared_annotation_appearances_and_drops_stale_alternates() { let other_dict = list(&doc, 0)[other].clone(); let source = other_dict.get(b"AP").unwrap(); let before = doc.resolve(source); - set_style(&mut doc, 0, first, Some([1.0, 0.0, 0.0]), None, None, None, &meta("")).unwrap(); + set_style(&mut doc, 0, first, StyleChange::new(Some([1.0, 0.0, 0.0]), None, None, None), &meta("")).unwrap(); assert_eq!(doc.resolve(source), before, "a shared AP must not change"); for full in [false, true] { let bytes = if full { @@ -1367,7 +1398,7 @@ fn comment_text_the_standard_fonts_cannot_draw_is_kept_and_marked() { .unwrap(); assert_eq!(mark(&doc, s), Some('张')); // Our own `?` appearance is redrawn on a restyle; Western European text clears the mark. - set_style(&mut doc, 0, t, Some([1.0, 0.0, 0.0]), None, None, None, &meta("")).unwrap(); + set_style(&mut doc, 0, t, StyleChange::new(Some([1.0, 0.0, 0.0]), None, None, None), &meta("")).unwrap(); assert_eq!(mark(&doc, t), Some('签')); set_contents(&mut doc, 0, t, "Zürich —\nGenève", &meta("")).unwrap(); assert_eq!(mark(&doc, t), None); @@ -1395,7 +1426,7 @@ fn comment_text_the_standard_fonts_cannot_draw_is_kept_and_marked() { set_annots(&mut doc, page, on_page).unwrap(); let k = list(&doc, 0).len() - 1; let before = list(&doc, 0)[k].clone(); - let err = set_style(&mut doc, 0, k, Some([1.0, 0.0, 0.0]), Some(0.4), Some(6.0), None, &meta("")).unwrap_err(); + let err = set_style(&mut doc, 0, k, StyleChange::new(Some([1.0, 0.0, 0.0]), Some(0.4), Some(6.0), None), &meta("")).unwrap_err(); assert!(matches!(&err, AnnotError::Undrawable(m) if m.contains("can't redraw") && m.contains("\"欢\" (U+6B22)")), "{err:?}"); assert_eq!(list(&doc, 0)[k], before, "a refused restyle keeps the colour, opacity, width and appearance"); let err = set_rect(&mut doc, 0, k, [40.0, 40.0, 180.0, 90.0], &meta("")).unwrap_err(); @@ -1476,7 +1507,7 @@ fn a_comment_listed_many_times_is_drawn_once_for_display() { fn text_box_font_size_changes_the_da_and_grows_the_box() { let mut doc = fixture(); let t = add_annotation(&mut doc, &new(0, Shape::TextBox { rect: [100.0, 680.0, 220.0, 692.0], font_size: 12.0 }), &meta("t")).unwrap(); - set_style(&mut doc, 0, t, Some([1.0, 0.0, 0.0]), None, None, None, &meta("")).unwrap(); + set_style(&mut doc, 0, t, StyleChange::new(Some([1.0, 0.0, 0.0]), None, None, None), &meta("")).unwrap(); set_contents(&mut doc, 0, t, "one two three four five six seven eight nine ten eleven twelve", &meta("")).unwrap(); let height = |doc: &Document| { let rect: Vec = list(doc, 0)[t].get(b"Rect").unwrap().as_array().unwrap().iter().map(|x| x.as_f64().unwrap()).collect(); @@ -1522,7 +1553,7 @@ fn text_boxes_and_callouts_can_change_fill_and_border() { let index = add_annotation(&mut doc, &new(0, shape), &meta("test")).unwrap(); assert!(props(&doc, 0, index).unwrap().fillable); set_fill(&mut doc, 0, index, Some([1.0, 1.0, 1.0]), &meta("test")).unwrap(); - set_style(&mut doc, 0, index, None, None, Some(3.0), None, &meta("test")).unwrap(); + set_style(&mut doc, 0, index, StyleChange::new(None, None, Some(3.0), None), &meta("test")).unwrap(); let saved = reopen(&doc); let properties = props(&saved, 0, index).unwrap(); assert_eq!(properties.fill, Some([1.0; 3])); @@ -1791,7 +1822,7 @@ fn a_star_note_keeps_its_star_when_recoloured() { b"<< /Type /Annot /Subtype /Text /Rect [100 100 120 120] /Name /Star /C [1 0.82 0] /F 4 >>", ]); assert_eq!(props(&doc, 0, 0).and_then(|p| p.icon), Some(NoteIcon::Star)); - set_style(&mut doc, 0, 0, Some([0.0, 0.0, 1.0]), None, None, None, &meta("")).unwrap(); + set_style(&mut doc, 0, 0, StyleChange::new(Some([0.0, 0.0, 1.0]), None, None, None), &meta("")).unwrap(); let doc = reopen(&doc); let d = &list(&doc, 0)[0]; assert_eq!(d.name(b"Name"), Some(&b"Star"[..])); diff --git a/crates/annot/src/types.rs b/crates/annot/src/types.rs index 632e990fea..bd3409b5ae 100644 --- a/crates/annot/src/types.rs +++ b/crates/annot/src/types.rs @@ -1,5 +1,5 @@ use super::create::normalize; -use super::*; +use super::{ObjRef, appearance}; pub type Rgb = [f64; 3]; @@ -563,6 +563,33 @@ pub struct Style { pub fill: Option, } +/// The style properties changed by one annotation edit. `None` leaves a property unchanged. +#[derive(Clone, Debug, Default, PartialEq)] +pub struct StyleChange { + pub color: Option, + pub opacity: Option, + pub width: Option, + pub endings: Option>, +} + +impl StyleChange { + pub fn new(color: Option, opacity: Option, width: Option, endings: Option>) -> Self { + Self { color, opacity, width, endings } + } +} + +/// Inputs for replacing selected text with a grouped strikeout and caret annotation. +pub struct TextReplacement<'a> { + pub page: usize, + pub quads: &'a [[f64; 8]], + pub replacement: &'a str, + pub author: &'a str, + pub strike: &'a Style, + pub caret: &'a Style, + pub strike_meta: &'a Meta, + pub caret_meta: &'a Meta, +} + impl Default for Style { fn default() -> Self { Self { color: [1.0, 0.82, 0.0], opacity: 1.0, width: 1.0, fill: None } diff --git a/crates/automation/README.md b/crates/automation/README.md index cdaaa13e64..d17084aa30 100644 --- a/crates/automation/README.md +++ b/crates/automation/README.md @@ -112,13 +112,13 @@ The release packages ship `pdfcraft-cli` alongside the desktop app, so no build | Install | CLI | |---|---| -| Windows (MSI) | `C:\Program Files\PdfCraft\pdfcraft-cli.exe` by default (wherever you installed it otherwise), not on `PATH` | +| Windows (MSI) | `%LOCALAPPDATA%\Programs\ArtCraft\PdfCraft\pdfcraft-cli.exe` by default (`C:\Program Files\ArtCraft\PdfCraft\pdfcraft-cli.exe` for an all-users install, under `Program Files (x86)` instead for the 32-bit build, or wherever you installed it otherwise), not on `PATH` | | Linux (deb, rpm) | `/usr/bin/pdfcraft-cli` | | macOS | the separate `pdfcraft-cli--macos-.zip` release asset (the `.app` holds only the desktop app) | ```sh -# Windows, default install folder -claude mcp add pdfcraft -- "C:\Program Files\PdfCraft\pdfcraft-cli.exe" mcp --root +# Windows (PowerShell), default install folder +claude mcp add pdfcraft -- "$env:LOCALAPPDATA\Programs\ArtCraft\PdfCraft\pdfcraft-cli.exe" mcp --root # Linux, or macOS with the CLI unzipped onto PATH claude mcp add pdfcraft -- pdfcraft-cli mcp --root ``` diff --git a/crates/automation/src/a11y/documents.rs b/crates/automation/src/a11y/documents.rs index f623ef714e..f2c9f6b77d 100644 --- a/crates/automation/src/a11y/documents.rs +++ b/crates/automation/src/a11y/documents.rs @@ -1,4 +1,4 @@ -use super::*; +use super::{Args, Automation, Result, ToolError, Value, child, failed, json, unused, write_atomic}; impl Automation { pub(crate) fn doc_export_office(&self, a: &Args) -> Result { diff --git a/crates/automation/src/a11y/form_tools.rs b/crates/automation/src/a11y/form_tools.rs index 5fb14f136e..7272a8d669 100644 --- a/crates/automation/src/a11y/form_tools.rs +++ b/crates/automation/src/a11y/form_tools.rs @@ -1,4 +1,4 @@ -use super::*; +use super::{Args, Automation, Result, ToolError, Value, failed, json, write_atomic}; /// A script's request to the viewer as the JSON that running a script reports; a side panel /// goes by its fixed id. diff --git a/crates/automation/src/a11y/ocr.rs b/crates/automation/src/a11y/ocr.rs index afc671a8c7..82e521ddd5 100644 --- a/crates/automation/src/a11y/ocr.rs +++ b/crates/automation/src/a11y/ocr.rs @@ -1,4 +1,4 @@ -use super::*; +use super::{Args, Automation, Result, ToolError, Value, child, failed, json, write_atomic}; impl Automation { /// Recognition settings from the arguments: `dpi` (clamped to 72–600), `language` (refused diff --git a/crates/automation/src/assemble.rs b/crates/automation/src/assemble.rs index 40ae65ea87..deb2efa18a 100644 --- a/crates/automation/src/assemble.rs +++ b/crates/automation/src/assemble.rs @@ -1,7 +1,7 @@ use super::error::{Result, ToolError, failed}; use super::json::{Args, one_based, summary}; use super::paths::{child, read_input, read_input_bytes, unused, write_atomic}; -use super::*; +use super::{Arc, Automation, CombineSource, Edit, Path, PathBuf, Value, json}; impl Automation { pub(crate) fn doc_create(&mut self, a: &Args) -> Result { diff --git a/crates/automation/src/dispatch.rs b/crates/automation/src/dispatch.rs index 26e1f95365..87f47e8ebe 100644 --- a/crates/automation/src/dispatch.rs +++ b/crates/automation/src/dispatch.rs @@ -1,7 +1,7 @@ use super::error::{Result, ToolError, failed}; use super::json::{Args, document_attachment_keys, info, one_based, parse_style_ranges, security, summary}; use super::paths::{read_input, write_atomic}; -use super::*; +use super::{Arc, Automation, Edit, Value, block_overlapping, comments, json, tools}; /// One piece of a tool's result. #[derive(Clone, Debug, PartialEq)] @@ -742,7 +742,7 @@ impl Automation { let ids: Vec = pdfcraft_engine::sign::keychain::identities(None) .map_err(failed)? .iter() - .map(|id| json!({ "id": pdfcraft_engine::sign::keychain::reference(&id.certificate), "certificate": signing::cert_json(&id.certificate) })) + .map(|id| json!({ "id": pdfcraft_engine::sign::keychain::reference(&id.certificate), "certificate": super::signing::cert_json(&id.certificate) })) .collect(); #[cfg(not(target_os = "macos"))] let ids: Vec = Vec::new(); @@ -755,7 +755,7 @@ impl Automation { let ids = listing .ids .iter() - .map(|id| json!({ "id": pdfcraft_engine::sign::windows::reference(&id.certificate), "certificate": signing::cert_json(&id.certificate) })) + .map(|id| json!({ "id": pdfcraft_engine::sign::windows::reference(&id.certificate), "certificate": super::signing::cert_json(&id.certificate) })) .collect(); let unusable = listing .unusable diff --git a/crates/automation/src/documents.rs b/crates/automation/src/documents.rs index 26addfd80b..476c451028 100644 --- a/crates/automation/src/documents.rs +++ b/crates/automation/src/documents.rs @@ -1,7 +1,7 @@ use super::error::{Result, ToolError, failed}; use super::json::{Args, nest_rows, security, summary}; use super::paths::{child, read_input, write_atomic}; -use super::*; +use super::{Arc, Automation, BlockKey, DocId, Document, Edit, Path, PathBuf, TextBlock, Value, comments, file_access, json}; /// How far a watermark may be moved from the page centre, in points (a page is at most 14,400). const WATERMARK_MAX_OFFSET: f64 = 20_000.0; @@ -539,11 +539,23 @@ impl Automation { }; let mut files = Vec::new(); let mut lowered = Vec::new(); - for p in pages { - let img = ex.image(p, dpi, format).map_err(failed)?; + // A write error stops the export as it is, not as a page error. + let mut write_error = None; + let exported = ex.images(&pages, dpi, format, |p, img| { let path = child(&folder, &format!("{stem}_page_{}.{}", p + 1, format.extension())); - write_atomic(&path, &img)?; + write_atomic(&path, &img).map_err(|e| { + let message = e.to_string(); + write_error = Some(e); + message + })?; files.push(path.to_string_lossy().into_owned()); + Ok(()) + }); + if let Some(e) = write_error { + return Err(e); + } + exported.map_err(failed)?; + for &p in &pages { // A page too large for the renderer at `dpi` is drawn at the most it allows. let used = ex.dpi_used(p, dpi); if used < dpi.clamp(18.0, 1200.0) - 0.5 { diff --git a/crates/automation/src/json.rs b/crates/automation/src/json.rs index c8710aa509..6f0884226a 100644 --- a/crates/automation/src/json.rs +++ b/crates/automation/src/json.rs @@ -1,5 +1,5 @@ use super::error::{Result, ToolError}; -use super::*; +use super::{Document, Value, comments, json}; /// How far from the page's corner a bookmark's position may be given, in points (a PDF page is at /// most 14 400 across). diff --git a/crates/automation/src/pages.rs b/crates/automation/src/pages.rs index d9ea9e5c4f..647a72e1d4 100644 --- a/crates/automation/src/pages.rs +++ b/crates/automation/src/pages.rs @@ -1,7 +1,7 @@ use super::dispatch::Content; use super::error::{Result, ToolError, failed}; use super::json::{Args, one_based}; -use super::*; +use super::{Arc, Automation, DocId, HashMap, PageRenderer, PageText, RenderConfig, RenderRequest, RequestKind, Value, commands, json, tools}; /// Default and maximum resolution for `page_render`. pub(crate) const DEFAULT_DPI: f64 = 96.0; diff --git a/crates/automation/src/paths.rs b/crates/automation/src/paths.rs index fb514df69f..e13d0a1452 100644 --- a/crates/automation/src/paths.rs +++ b/crates/automation/src/paths.rs @@ -1,5 +1,5 @@ use super::error::{Result, failed}; -use super::*; +use super::{Automation, Path, PathBuf, StagingName, file_access, foreign_share, staging_suffixes}; impl Automation { // ---- paths ------------------------------------------------------------------------------- diff --git a/crates/automation/tests/it/automation.rs b/crates/automation/tests/it/automation.rs index 23351db9aa..6891cad3f1 100644 --- a/crates/automation/tests/it/automation.rs +++ b/crates/automation/tests/it/automation.rs @@ -2030,21 +2030,33 @@ fn comments_through_tools() { let dir = workdir("comments"); let mut a = auto(&dir); let doc = ok(&mut a, "doc_open", json!({ "path": "a.pdf" }))["doc"].as_u64().unwrap(); + let id = add_comment_examples(&mut a, doc); + let list = ok(&mut a, "comment_list", json!({ "doc": doc })); + let rect = verify_comment_listing(&list, &id); + edit_rectangle_comment(&mut a, doc, &rect); + edit_text_comment(&mut a, doc, &list); + verify_comment_errors(&mut a, doc, &id); + save_and_reopen_comments(&dir, &mut a, doc); +} + +fn add_comment_examples(a: &mut Automation, doc: u64) -> String { // "Page 2" sits at y = 150 (user space) = 150 from the top of the 300 pt page. - let hl = ok(&mut a, "comment_add", json!({ "doc": doc, "page": 2, "type": "highlight", "find": "page 2", "contents": "check", "author": "Ada" })); + let hl = ok(a, "comment_add", json!({ "doc": doc, "page": 2, "type": "highlight", "find": "page 2", "contents": "check", "author": "Ada" })); assert_eq!(hl["comment"]["lines"], 1); let id = hl["comment"]["id"].as_str().unwrap().to_string(); - ok(&mut a, "comment_add", json!({ "doc": doc, "page": 2, "type": "note", "at": [150, 20], "contents": "Sticky" })); - ok(&mut a, "comment_add", json!({ "doc": doc, "page": 1, "type": "rectangle", "rect": [10, 10, 60, 40], "color": "blue", "width": 3 })); - ok(&mut a, "comment_add", json!({ "doc": doc, "page": 1, "type": "textbox", "rect": [10, 200, 190, 240], "contents": "Hello", "font_size": 10 })); - ok(&mut a, "comment_add", json!({ "doc": doc, "page": 1, "type": "ink", "strokes": [[[10, 280], [50, 260], [90, 285]]] })); - ok(&mut a, "comment_add", json!({ "doc": doc, "page": 3, "type": "arrow", "from": [10, 10], "to": [100, 100] })); - ok(&mut a, "comment_reply", json!({ "doc": doc, "id": id, "text": "Looks right", "author": "Bob" })); - ok(&mut a, "comment_set_status", json!({ "doc": doc, "id": id, "status": "accepted", "author": "Bob" })); + ok(a, "comment_add", json!({ "doc": doc, "page": 2, "type": "note", "at": [150, 20], "contents": "Sticky" })); + ok(a, "comment_add", json!({ "doc": doc, "page": 1, "type": "rectangle", "rect": [10, 10, 60, 40], "color": "blue", "width": 3 })); + ok(a, "comment_add", json!({ "doc": doc, "page": 1, "type": "textbox", "rect": [10, 200, 190, 240], "contents": "Hello", "font_size": 10 })); + ok(a, "comment_add", json!({ "doc": doc, "page": 1, "type": "ink", "strokes": [[[10, 280], [50, 260], [90, 285]]] })); + ok(a, "comment_add", json!({ "doc": doc, "page": 3, "type": "arrow", "from": [10, 10], "to": [100, 100] })); + ok(a, "comment_reply", json!({ "doc": doc, "id": id, "text": "Looks right", "author": "Bob" })); + ok(a, "comment_set_status", json!({ "doc": doc, "id": id, "status": "accepted", "author": "Bob" })); + id +} - let list = ok(&mut a, "comment_list", json!({ "doc": doc })); +fn verify_comment_listing(list: &Value, id: &str) -> Value { assert_eq!(list["count"], 6, "{list}"); - let c = list["comments"].as_array().unwrap().iter().find(|c| c["id"] == id.as_str()).unwrap().clone(); + let c = list["comments"].as_array().unwrap().iter().find(|c| c["id"] == id).unwrap().clone(); assert_eq!((c["type"].as_str(), c["author"].as_str(), c["contents"].as_str()), (Some("Highlight"), Some("Ada"), Some("check"))); assert_eq!(c["status"], "Accepted"); assert_eq!(c["replies"].as_array().unwrap().len(), 1); @@ -2057,33 +2069,38 @@ fn comments_through_tools() { assert_eq!(rect["rect"], json!([10.0, 10.0, 60.0, 40.0])); let note = list["comments"].as_array().unwrap().iter().find(|c| c["type"] == "Text").unwrap().clone(); assert_eq!(note["rect"], json!([150.0, 20.0, 170.0, 40.0]), "note icon hangs from its top-left point"); + rect +} +fn edit_rectangle_comment(a: &mut Automation, doc: u64, original: &Value) { // Edit by page + index; several changes are one undo step. - let (page, index) = (rect["page"].as_u64().unwrap(), rect["index"].as_u64().unwrap()); - ok(&mut a, "comment_edit", json!({ "doc": doc, "page": page, "index": index, "color": "#FF0000", "move": [5, 5], "contents": "moved" })); - let list = ok(&mut a, "comment_list", json!({ "doc": doc, "page": 1 })); + let (page, index) = (original["page"].as_u64().unwrap(), original["index"].as_u64().unwrap()); + ok(a, "comment_edit", json!({ "doc": doc, "page": page, "index": index, "color": "#FF0000", "move": [5, 5], "contents": "moved" })); + let list = ok(a, "comment_list", json!({ "doc": doc, "page": 1 })); let rect = list["comments"].as_array().unwrap().iter().find(|c| c["type"] == "Square").unwrap().clone(); assert_eq!((rect["color"].as_str(), rect["contents"].as_str()), (Some("#FF0000"), Some("moved"))); assert_eq!(rect["rect"], json!([15.0, 15.0, 65.0, 45.0])); - let undo = ok(&mut a, "edit_undo", json!({ "doc": doc })); + let undo = ok(a, "edit_undo", json!({ "doc": doc })); assert_eq!(undo["undone"], "Edit comment"); - ok(&mut a, "edit_redo", json!({ "doc": doc })); + ok(a, "edit_redo", json!({ "doc": doc })); // Rectangles, ovals and polygons take a fill (#686); "none" removes it. Lines have none. - ok(&mut a, "comment_edit", json!({ "doc": doc, "page": page, "index": index, "fill": "yellow" })); - ok(&mut a, "comment_edit", json!({ "doc": doc, "page": page, "index": index, "fill": "none" })); + ok(a, "comment_edit", json!({ "doc": doc, "page": page, "index": index, "fill": "yellow" })); + ok(a, "comment_edit", json!({ "doc": doc, "page": page, "index": index, "fill": "none" })); assert!(matches!(a.call("comment_edit", &json!({ "doc": doc, "page": page, "index": index, "fill": "mauve" })), Err(ToolError::InvalidArgs(_)))); - let arrow = ok(&mut a, "comment_list", json!({ "doc": doc, "page": 3 }))["comments"][0].clone(); + let arrow = ok(a, "comment_list", json!({ "doc": doc, "page": 3 }))["comments"][0].clone(); assert!(matches!( a.call("comment_edit", &json!({ "doc": doc, "page": arrow["page"], "index": arrow["index"], "fill": "red" })), Err(ToolError::Failed(_)) )); +} +fn edit_text_comment(a: &mut Automation, doc: u64, original_list: &Value) { // Editing a text box re-fits its rectangle to the new text: the wrap width and top edge // stay, the height follows the wrapped lines. - let tb = list["comments"].as_array().unwrap().iter().find(|c| c["type"] == "FreeText").unwrap().clone(); + let tb = original_list["comments"].as_array().unwrap().iter().find(|c| c["type"] == "FreeText").unwrap().clone(); let long = "the quick brown fox jumps over the lazy dog ".repeat(3); - ok(&mut a, "comment_edit", json!({ "doc": doc, "page": tb["page"], "index": tb["index"], "contents": long.trim_end() })); - let list = ok(&mut a, "comment_list", json!({ "doc": doc, "page": 1 })); + ok(a, "comment_edit", json!({ "doc": doc, "page": tb["page"], "index": tb["index"], "contents": long.trim_end() })); + let list = ok(a, "comment_list", json!({ "doc": doc, "page": 1 })); let tb = list["comments"].as_array().unwrap().iter().find(|c| c["type"] == "FreeText").unwrap().clone(); let r: Vec = tb["rect"].as_array().unwrap().iter().map(|v| v.as_f64().unwrap()).collect(); assert_eq!((r[0], r[1], r[2] - r[0]), (10.0, 200.0, 180.0), "width and top edge stay: {r:?}"); @@ -2092,9 +2109,11 @@ fn comments_through_tools() { // The rendered page shows the rectangle's border. let png = a.call("page_render", &json!({ "doc": doc, "page": 1, "dpi": 72 })).unwrap(); assert!(matches!(png[0], Content::Png { .. })); +} - ok(&mut a, "comment_delete", json!({ "doc": doc, "id": id })); - assert_eq!(ok(&mut a, "comment_list", json!({ "doc": doc }))["count"], 5); +fn verify_comment_errors(a: &mut Automation, doc: u64, id: &str) { + ok(a, "comment_delete", json!({ "doc": doc, "id": id })); + assert_eq!(ok(a, "comment_list", json!({ "doc": doc }))["count"], 5); assert!(matches!(a.call("comment_delete", &json!({ "doc": doc, "id": id })), Err(ToolError::Failed(_)))); assert!(matches!(a.call("comment_add", &json!({ "doc": doc, "page": 1, "type": "highlight", "find": "nowhere" })), Err(ToolError::Failed(_)))); assert!(matches!(a.call("comment_add", &json!({ "doc": doc, "page": 1, "type": "rectangle" })), Err(ToolError::InvalidArgs(_)))); @@ -2103,10 +2122,11 @@ fn comments_through_tools() { Err(ToolError::InvalidArgs(_)) )); assert!(matches!(a.call("comment_edit", &json!({ "doc": doc, "page": 1, "index": 1 })), Err(ToolError::InvalidArgs(_)))); +} - // Comments survive a save and reopen. - ok(&mut a, "doc_save", json!({ "doc": doc, "path": "commented.pdf" })); - let mut b = auto(&dir); +fn save_and_reopen_comments(dir: &Path, a: &mut Automation, doc: u64) { + ok(a, "doc_save", json!({ "doc": doc, "path": "commented.pdf" })); + let mut b = auto(dir); let re = ok(&mut b, "doc_open", json!({ "path": "commented.pdf" }))["doc"].as_u64().unwrap(); assert_eq!(ok(&mut b, "comment_list", json!({ "doc": re }))["count"], 5); } @@ -2809,6 +2829,12 @@ fn accessibility_check_report_and_fixes_through_tools() { let manual_html = std::fs::read_to_string(dir.join("manual-report.html")).unwrap(); assert!(manual_html.contains("

Needs manual check: 1

")); assert!(!manual_html.contains("no problems")); +} + +#[test] +fn accessibility_figure_tags_and_alternative_text_through_tools() { + let dir = workdir("a11y-figures"); + let mut a = auto(&dir); // Figures: list, describe, mark decorative. std::fs::write( dir.join("figures.pdf"), @@ -5260,6 +5286,18 @@ fn local_gotor_link_open_refuses_directories_devices_and_non_pdf_targets() { #[test] fn local_gotor_link_open_applies_destinations_and_honors_root() { + let root = local_gotor_fixtures(); + let mut a = auto(&root); + assert_relative_gotor_destination(&mut a); + assert_absolute_gotor_policy(&mut a); + assert_unapplied_gotor_destinations(&mut a); + assert_encrypted_gotor_passwords(&mut a); + assert_unsupported_gotor_targets(&mut a); + assert_gotor_root_boundaries(&mut a); + assert_url_links_cannot_open_as_gotor(&mut a); +} + +fn local_gotor_fixtures() -> PathBuf { let (base, root) = sandbox("gotor-open"); std::fs::create_dir_all(root.join("sub")).unwrap(); std::fs::write(root.join("target.pdf"), fixture(3)).unwrap(); @@ -5277,12 +5315,14 @@ fn local_gotor_link_open_applies_destinations_and_honors_root() { std::fs::write(root.join("absolute.pdf"), remote_link_pdf(root.join("target.pdf").to_str().unwrap(), Some("[1 /Fit]"))).unwrap(); link_dir(&root, "outside-link", &base.join("outside")); std::fs::write(root.join("symlink.pdf"), remote_link_pdf("outside-link/secret.pdf", Some("[0 /Fit]"))).unwrap(); + root +} - let mut a = auto(&root); - let source = ok(&mut a, "doc_open", json!({ "path": "sub/source.pdf" }))["doc"].as_u64().unwrap(); - let listed = ok(&mut a, "link_list", json!({ "doc": source })); +fn assert_relative_gotor_destination(a: &mut Automation) { + let source = ok(a, "doc_open", json!({ "path": "sub/source.pdf" }))["doc"].as_u64().unwrap(); + let listed = ok(a, "link_list", json!({ "doc": source })); assert_eq!(listed["links"][0]["other"], "GoToR"); - let opened = ok(&mut a, "link_open", json!({ "doc": source, "page": 1, "index": 1 })); + let opened = ok(a, "link_open", json!({ "doc": source, "page": 1, "index": 1 })); assert_eq!(opened["path"], "target.pdf"); assert_eq!(opened["destination_applied"], true); assert_eq!(opened["destination"]["page"], 3); @@ -5290,51 +5330,63 @@ fn local_gotor_link_open_applies_destinations_and_honors_root() { assert_eq!(opened["document"]["pages"], 3); let target_id = opened["document"]["doc"].as_u64().unwrap(); assert_eq!(a.session().get(pdfcraft_engine::DocId(target_id)).unwrap().info.pages.len(), 3); +} - let absolute = ok(&mut a, "doc_open", json!({ "path": "absolute.pdf" }))["doc"].as_u64().unwrap(); +fn assert_absolute_gotor_policy(a: &mut Automation) { + let absolute = ok(a, "doc_open", json!({ "path": "absolute.pdf" }))["doc"].as_u64().unwrap(); let before = a.session().docs().len(); for args in [json!({ "doc": absolute, "page": 1, "index": 1 }), json!({ "doc": absolute, "page": 1, "index": 1, "allow_absolute": false })] { - assert!(matches!(err(&mut a, "link_open", args), ToolError::Failed(m) if m.contains("allow_absolute"))); + assert!(matches!(err(a, "link_open", args), ToolError::Failed(m) if m.contains("allow_absolute"))); assert_eq!(a.session().docs().len(), before); } - let opened = ok(&mut a, "link_open", json!({ "doc": absolute, "page": 1, "index": 1, "allow_absolute": true })); + let opened = ok(a, "link_open", json!({ "doc": absolute, "page": 1, "index": 1, "allow_absolute": true })); assert_eq!(opened["path"], "target.pdf"); assert_eq!(opened["destination"]["page"], 2); +} +fn assert_unapplied_gotor_destinations(a: &mut Automation) { for (source_path, warning) in [("named.pdf", "named destination"), ("range.pdf", "out of range")] { - let source = ok(&mut a, "doc_open", json!({ "path": source_path }))["doc"].as_u64().unwrap(); - let opened = ok(&mut a, "link_open", json!({ "doc": source, "page": 1, "index": 1 })); + let source = ok(a, "doc_open", json!({ "path": source_path }))["doc"].as_u64().unwrap(); + let opened = ok(a, "link_open", json!({ "doc": source, "page": 1, "index": 1 })); assert_eq!(opened["destination_applied"], false); assert!(opened["warning"].as_str().unwrap().contains(warning), "{opened}"); } +} - let password_source = ok(&mut a, "doc_open", json!({ "path": "password-source.pdf" }))["doc"].as_u64().unwrap(); +fn assert_encrypted_gotor_passwords(a: &mut Automation) { + let password_source = ok(a, "doc_open", json!({ "path": "password-source.pdf" }))["doc"].as_u64().unwrap(); let documents_before = a.session().docs().len(); - assert!(matches!(err(&mut a, "link_open", json!({ "doc": password_source, "page": 1, "index": 1 })), ToolError::Failed(_))); + assert!(matches!(err(a, "link_open", json!({ "doc": password_source, "page": 1, "index": 1 })), ToolError::Failed(_))); assert_eq!(a.session().docs().len(), documents_before); - assert!(matches!(err(&mut a, "link_open", json!({ "doc": password_source, "page": 1, "index": 1, "password": "wrong" })), ToolError::Failed(_))); + assert!(matches!(err(a, "link_open", json!({ "doc": password_source, "page": 1, "index": 1, "password": "wrong" })), ToolError::Failed(_))); assert_eq!(a.session().docs().len(), documents_before); - let opened = ok(&mut a, "link_open", json!({ "doc": password_source, "page": 1, "index": 1, "password": "secret" })); + let opened = ok(a, "link_open", json!({ "doc": password_source, "page": 1, "index": 1, "password": "secret" })); assert_eq!(opened["document"]["encrypted"], true); +} +fn assert_unsupported_gotor_targets(a: &mut Automation) { for source_path in ["url.pdf", "missing-source.pdf", "non-pdf-source.pdf"] { - let source = ok(&mut a, "doc_open", json!({ "path": source_path }))["doc"].as_u64().unwrap(); + let source = ok(a, "doc_open", json!({ "path": source_path }))["doc"].as_u64().unwrap(); let documents_before = a.session().docs().len(); - assert!(matches!(err(&mut a, "link_open", json!({ "doc": source, "page": 1, "index": 1 })), ToolError::Failed(_))); + assert!(matches!(err(a, "link_open", json!({ "doc": source, "page": 1, "index": 1 })), ToolError::Failed(_))); assert_eq!(a.session().docs().len(), documents_before, "a rejected target is not opened: {source_path}"); } +} +fn assert_gotor_root_boundaries(a: &mut Automation) { for source_path in ["sub/escape.pdf", "symlink.pdf"] { - let source = ok(&mut a, "doc_open", json!({ "path": source_path }))["doc"].as_u64().unwrap(); + let source = ok(a, "doc_open", json!({ "path": source_path }))["doc"].as_u64().unwrap(); let documents_before = a.session().docs().len(); - assert!(matches!(err(&mut a, "link_open", json!({ "doc": source, "page": 1, "index": 1 })), ToolError::Failed(m) if m.contains("outside"))); + assert!(matches!(err(a, "link_open", json!({ "doc": source, "page": 1, "index": 1 })), ToolError::Failed(m) if m.contains("outside"))); assert_eq!(a.session().docs().len(), documents_before, "a refused target is not opened"); } +} - let missing_source = ok(&mut a, "doc_open", json!({ "path": "a.pdf" }))["doc"].as_u64().unwrap(); - ok(&mut a, "link_add", json!({ "doc": missing_source, "page": 1, "rect": [20, 30, 80, 50], "url": "https://example.org" })); +fn assert_url_links_cannot_open_as_gotor(a: &mut Automation) { + let missing_source = ok(a, "doc_open", json!({ "path": "a.pdf" }))["doc"].as_u64().unwrap(); + ok(a, "link_add", json!({ "doc": missing_source, "page": 1, "rect": [20, 30, 80, 50], "url": "https://example.org" })); assert!( - matches!(err(&mut a, "link_open", json!({ "doc": missing_source, "page": 1, "index": 1 })), ToolError::InvalidArgs(m) if m.contains("not a supported local PDF GoToR")) + matches!(err(a, "link_open", json!({ "doc": missing_source, "page": 1, "index": 1 })), ToolError::InvalidArgs(m) if m.contains("not a supported local PDF GoToR")) ); } @@ -5887,8 +5939,14 @@ fn a_dynamic_xfa_forms_signature_box_is_signed_under_its_som_path() { fn digital_ids_signing_and_validation_through_tools() { let dir = workdir("signing"); let mut a = auto(&dir); + create_signing_identity(&mut a); + let doc = sign_document_and_verify_trust(&mut a, &dir); + verify_signature_revisions_and_bundle(&mut a, doc, &dir); +} + +fn create_signing_identity(a: &mut Automation) { let id = ok( - &mut a, + a, "sign_id_create", json!({ "name": "Ada Lovelace", "organization": "Analytical Engines", "email": "ada@example.com", "country": "GB", "key": "p256", "password": "secret12", "path": "ada.p12" }), ); @@ -5897,13 +5955,15 @@ fn digital_ids_signing_and_validation_through_tools() { assert!(matches!(a.call("sign_id_create", &json!({ "name": "X", "password": "short", "path": "x.p12" })), Err(ToolError::InvalidArgs(_)))); // Eight characters at least (#1847): seven is refused. assert!(matches!(a.call("sign_id_create", &json!({ "name": "X", "password": "seven77", "path": "x.p12" })), Err(ToolError::InvalidArgs(_)))); +} - let doc = ok(&mut a, "doc_open", json!({ "path": "a.pdf" }))["doc"].as_u64().unwrap(); - assert_eq!(ok(&mut a, "sign_list", json!({ "doc": doc }))["count"], 0); +fn sign_document_and_verify_trust(a: &mut Automation, dir: &Path) -> u64 { + let doc = ok(a, "doc_open", json!({ "path": "a.pdf" }))["doc"].as_u64().unwrap(); + assert_eq!(ok(a, "sign_list", json!({ "doc": doc }))["count"], 0); // A Keychain identity that doesn't exist (macOS) or Keychains at all (elsewhere). assert!(matches!(a.call("sign_document", &json!({ "doc": doc, "id": "keychain:No Such Signer", "out": "k.pdf" })), Err(ToolError::Failed(_)))); assert!(matches!(a.call("sign_document", &json!({ "doc": doc, "id": "windows:No Such Signer", "out": "w.pdf" })), Err(ToolError::Failed(_)))); - let store = ok(&mut a, "sign_windows_ids", json!({})); + let store = ok(a, "sign_windows_ids", json!({})); let ids = store["ids"].as_array().unwrap(); assert_eq!(store["count"].as_u64().unwrap(), ids.len() as u64); assert!(ids.iter().all(|id| id["id"].as_str().unwrap().starts_with("windows:"))); @@ -5917,7 +5977,7 @@ fn digital_ids_signing_and_validation_through_tools() { Err(ToolError::InvalidArgs(_)) )); let r = ok( - &mut a, + a, "sign_document", json!({ "doc": doc, "id": "ada.p12", "password": "secret12", "page": 2, "rect": [20, 200, 180, 250], "reason": "Approved", "location": "London", "out": "signed.pdf" }), ); @@ -5929,33 +5989,37 @@ fn digital_ids_signing_and_validation_through_tools() { assert!(dir.join("signed.pdf").exists()); // Trust the ID: valid; comment afterwards: still valid, change allowed. - let t = ok(&mut a, "sign_trust", json!({ "paths": ["ada.p12"], "password": "secret12" })); + let t = ok(a, "sign_trust", json!({ "paths": ["ada.p12"], "password": "secret12" })); assert_eq!(t["trusted"].as_array().unwrap().len(), 1); - let list = ok(&mut a, "sign_list", json!({ "doc": doc })); + let list = ok(a, "sign_list", json!({ "doc": doc })); assert_eq!((list["all_valid"].as_bool(), list["signatures"][0]["status"].as_str()), (Some(true), Some("valid"))); - ok(&mut a, "comment_add", json!({ "doc": doc, "page": 1, "type": "note", "at": [20, 20], "contents": "ok" })); - let s = &ok(&mut a, "sign_list", json!({ "doc": doc }))["signatures"][0]; + ok(a, "comment_add", json!({ "doc": doc, "page": 1, "type": "note", "at": [20, 20], "contents": "ok" })); + let s = &ok(a, "sign_list", json!({ "doc": doc }))["signatures"][0]; assert_eq!((s["status"].as_str(), s["modification"].as_str()), (Some("valid"), Some("allowed"))); + doc +} + +fn verify_signature_revisions_and_bundle(a: &mut Automation, doc: u64, dir: &Path) { // A full rewrite is refused for a signed document. assert!(matches!(a.call("doc_save", &json!({ "doc": doc, "path": "copy.pdf", "full": true })), Err(ToolError::Failed(_)))); - ok(&mut a, "doc_save", json!({ "doc": doc })); + ok(a, "doc_save", json!({ "doc": doc })); // Three revisions: the original, the signature, the comment; the middle one is signed. - let revs = ok(&mut a, "doc_revisions", json!({ "doc": doc }))["revisions"].as_array().cloned().unwrap(); + let revs = ok(a, "doc_revisions", json!({ "doc": doc }))["revisions"].as_array().cloned().unwrap(); assert_eq!(revs.len(), 3, "{revs:?}"); assert!(revs[0]["signed_by"].as_array().unwrap().is_empty() && revs[1]["signed_by"].as_array().unwrap().len() == 1, "{revs:?}"); - let old = ok(&mut a, "doc_open_revision", json!({ "doc": doc, "revision": 2 }))["doc"].as_u64().unwrap(); - assert_eq!(ok(&mut a, "comment_list", json!({ "doc": old }))["comments"].as_array().map(Vec::len), Some(0), "before the comment"); - assert_eq!(ok(&mut a, "sign_list", json!({ "doc": old }))["count"], 1); + let old = ok(a, "doc_open_revision", json!({ "doc": doc, "revision": 2 }))["doc"].as_u64().unwrap(); + assert_eq!(ok(a, "comment_list", json!({ "doc": old }))["comments"].as_array().map(Vec::len), Some(0), "before the comment"); + assert_eq!(ok(a, "sign_list", json!({ "doc": old }))["count"], 1); assert!(matches!(a.call("doc_open_revision", &json!({ "doc": doc, "revision": 4 })), Err(ToolError::Failed(_)))); - assert_eq!(ok(&mut a, "sign_trust", json!({ "clear": true }))["trusted"].as_array().unwrap().len(), 0); - assert_eq!(ok(&mut a, "sign_list", json!({ "doc": doc }))["signatures"][0]["status"], "unknown"); + assert_eq!(ok(a, "sign_trust", json!({ "clear": true }))["trusted"].as_array().unwrap().len(), 0); + assert_eq!(ok(a, "sign_list", json!({ "doc": doc }))["signatures"][0]["status"], "unknown"); // The same certificate from a PKCS #7 bundle (.p7b), as Windows, Acrobat and CAs export one. use pdfcraft_engine::sign::{cms, der, pkcs12}; let cert = pkcs12::open(&std::fs::read(dir.join("ada.p12")).unwrap(), "secret12").unwrap().certificate.raw; let sd = der::seq(&[&der::int(1), &der::set_of(&[]), &der::seq(&[&der::oid(cms::DATA)]), &der::explicit(0, &cert), &der::set_of(&[])]); std::fs::write(dir.join("ada.p7b"), der::seq(&[&der::oid(cms::SIGNED_DATA), &der::explicit(0, &sd)])).unwrap(); - assert_eq!(ok(&mut a, "sign_trust", json!({ "paths": ["ada.p7b"] }))["trusted"].as_array().unwrap().len(), 1); - assert_eq!(ok(&mut a, "sign_list", json!({ "doc": doc }))["signatures"][0]["status"], "valid"); + assert_eq!(ok(a, "sign_trust", json!({ "paths": ["ada.p7b"] }))["trusted"].as_array().unwrap().len(), 1); + assert_eq!(ok(a, "sign_list", json!({ "doc": doc }))["signatures"][0]["status"], "valid"); } /// The decoded text of every visible signature appearance (Helvetica forms) in a signed file. @@ -7881,7 +7945,7 @@ fn hebrew_text_through_tools_saves_reopens_extracts_and_renders() { let mut a = auto(&dir); let doc = ok(&mut a, "doc_open", json!({"path": "a.pdf"}))["doc"].as_u64().unwrap(); let text = "שם משפחה: שרון, טל׳ 052-1234567 (נייד)"; - let args = json!({"doc": doc, "page": 1, "text": text, "rect": [10, 20, 400, 40], "size": 11, "align": "right"}); + let args = json!({"doc": doc, "page": 1, "text": text, "rect": [10, 20, 190, 40], "size": 7, "align": "right"}); if pdfcraft_fonts::document_hebrew_font(false).is_none() { assert!(a.call("page_add_text", &args).unwrap_err().to_string().contains("U+05E9")); assert_eq!(ok(&mut a, "content_list", json!({"doc": doc}))["count"], 0); diff --git a/crates/cos/src/document/objects.rs b/crates/cos/src/document/objects.rs index 2ff729f1fb..8744a3ea3e 100644 --- a/crates/cos/src/document/objects.rs +++ b/crates/cos/src/document/objects.rs @@ -1,7 +1,7 @@ use super::reader::find; use super::state::{LENGTHS, LoadGuard, ObjStm, ObjectReader, ReadState, Slot, SourceIdentity, objstm_member, owned_bytes}; use super::xref::{Revision, XrefEntry}; -use super::*; +use super::{Arc, CosError, Dict, Document, Lexer, ObjRef, Object, is_whitespace, parse_indirect_shared}; impl Document { pub fn bytes(&self) -> &Arc> { diff --git a/crates/cos/src/document/open.rs b/crates/cos/src/document/open.rs index c90d5c0906..d41d564e33 100644 --- a/crates/cos/src/document/open.rs +++ b/crates/cos/src/document/open.rs @@ -1,7 +1,7 @@ use super::reader::{find, generated_id}; use super::state::Credentials; use super::xref::XrefIndex; -use super::*; +use super::{Arc, BTreeMap, CosError, Dict, Document, ObjRef, Object}; impl Document { /// A new document with an empty page tree (for split / extract / combine). It has no diff --git a/crates/cos/src/document/reader.rs b/crates/cos/src/document/reader.rs index ead09c36e5..66129c1423 100644 --- a/crates/cos/src/document/reader.rs +++ b/crates/cos/src/document/reader.rs @@ -3,7 +3,7 @@ use super::state::SECTION_READS; use super::xref::{ MAX_COMPACT_XREF_BYTES, MAX_COMPACT_XREF_ROWS, Revision, XrefEntry, XrefIndex, XrefRange, XrefRevisionSection, XrefSection, XrefSectionData, }; -use super::*; +use super::{Arc, BTreeMap, CosError, Dict, Document, HashMap, HashSet, Lexer, ObjRef, Object, is_whitespace, parse_indirect, parse_indirect_shared}; impl Document { #[allow(clippy::type_complexity)] diff --git a/crates/cos/src/document/state.rs b/crates/cos/src/document/state.rs index 30f193e4e6..b4323f982e 100644 --- a/crates/cos/src/document/state.rs +++ b/crates/cos/src/document/state.rs @@ -1,5 +1,5 @@ use super::xref::XrefEntry; -use super::*; +use super::{Arc, BTreeMap, CosError, Dict, Document, HashMap, ObjRef, Object, Weak}; thread_local! { /// The objects being loaded on this thread, innermost last (see `Document::try_get`). diff --git a/crates/cos/src/document/xref.rs b/crates/cos/src/document/xref.rs index 96a782c1a9..02390ff7da 100644 --- a/crates/cos/src/document/xref.rs +++ b/crates/cos/src/document/xref.rs @@ -1,4 +1,4 @@ -use super::*; +use super::{Arc, BTreeMap, Lexer}; #[derive(Clone, Copy, Debug, PartialEq, Eq)] pub enum XrefEntry { diff --git a/crates/edit/src/added/draw.rs b/crates/edit/src/added/draw.rs index 0fc7aa510d..61297bcf24 100644 --- a/crates/edit/src/added/draw.rs +++ b/crates/edit/src/added/draw.rs @@ -2,7 +2,10 @@ use super::layout::{ Piece, arabic_error, hebrew_error, is_arabic, is_hebrew, is_thai, latin_width, lines, norm, shaped_layout, text_rect, thai_error, wrapped, }; use super::types::{AddedText, Align, Family}; -use super::*; +use super::{ + Content, Dict, Document, EditError, GlyphError, GlyphOutline, HashMap, HashSet, ObjRef, Object, PdfString, ShapedCluster, ShapedScript, Stream, + literal, matrix_number, n, shaped_glyph, win_ansi, +}; fn font_name(base: &str) -> String { format!("PCF{}", base.replace('-', "")) diff --git a/crates/edit/src/added/layout.rs b/crates/edit/src/added/layout.rs index 0e971b92c7..67d80be405 100644 --- a/crates/edit/src/added/layout.rs +++ b/crates/edit/src/added/layout.rs @@ -1,5 +1,8 @@ use super::types::{AddedImage, AddedText}; -use super::*; +use super::{ + Content, Document, EditError, GlyphError, Level, ObjRef, Object, ParagraphBidiInfo, ShapedCluster, ShapedScript, shape_arabic, shape_hebrew, + shape_thai, +}; pub(super) fn nums(doc: &Document, o: Option<&Object>) -> Vec { o.map(|o| doc.resolve(o)).and_then(|a| a.as_array().map(|a| a.iter().filter_map(Object::as_f64).collect())).unwrap_or_default() diff --git a/crates/edit/src/added/store.rs b/crates/edit/src/added/store.rs index b89d429000..5ce5e15d19 100644 --- a/crates/edit/src/added/store.rs +++ b/crates/edit/src/added/store.rs @@ -1,7 +1,7 @@ use super::draw::{draw, params}; use super::layout::{first_undrawable, is_thai, nums, shaped_arabic, thai_error}; use super::types::{Added, AddedImage, AddedText, Align, CHAR_SPACING_LIMIT, Family, MarkerScan, TAG}; -use super::*; +use super::{Content, Dict, Document, EditError, GlyphError, MarkKind, ObjRef, Object, Stream, check, contents, page_list, place_tagged}; fn parse(doc: &Document, d: &Dict) -> Option { let r = nums(doc, d.get(b"Rect")); diff --git a/crates/edit/src/added/types.rs b/crates/edit/src/added/types.rs index 0a9f92f92c..28b61d5869 100644 --- a/crates/edit/src/added/types.rs +++ b/crates/edit/src/added/types.rs @@ -1,5 +1,5 @@ use super::layout::norm; -use super::*; +use super::{Content, MarkKind, ObjRef, Std14}; pub(super) const TAG: &str = "Added"; diff --git a/crates/edit/src/apply.rs b/crates/edit/src/apply.rs index 1461dc78ef..427f51f943 100644 --- a/crates/edit/src/apply.rs +++ b/crates/edit/src/apply.rs @@ -5,7 +5,7 @@ use super::place::{ END, Isolation, add_page_resources, add_resources, begin, check, check_on_top, contents, free_font_name, isolation, page_fonts, page_list, place, place_inside_wrapper, stream_tag, text_op, undrawable, wrapper_role, }; -use super::*; +use super::{Document, EditError, Object, added, helvetica_width}; /// Add a header and footer to `pages` (0-based). With `replace`, existing headers and footers on /// those pages are removed first (Acrobat's Replace Existing). diff --git a/crates/edit/src/marks.rs b/crates/edit/src/marks.rs index 507e2afa8e..00c53ec27a 100644 --- a/crates/edit/src/marks.rs +++ b/crates/edit/src/marks.rs @@ -1,4 +1,4 @@ -use super::*; +use super::{Document, EditError, Object, Rgb, added}; /// The kinds of page marks. #[derive(Clone, Copy, Debug, PartialEq, Eq)] diff --git a/crates/edit/src/place.rs b/crates/edit/src/place.rs index b6d50a6462..2f2c24c862 100644 --- a/crates/edit/src/place.rs +++ b/crates/edit/src/place.rs @@ -1,5 +1,5 @@ use super::marks::{MarkKind, matrix_number, n}; -use super::*; +use super::{Dict, Document, EditError, ObjRef, Object, Stream, literal, win_ansi}; pub(crate) fn page_list(doc: &Document) -> Vec { pdfcraft_model::pages(doc) diff --git a/crates/edit/src/tests.rs b/crates/edit/src/tests.rs index 0f8adc6514..7c78d31fc2 100644 --- a/crates/edit/src/tests.rs +++ b/crates/edit/src/tests.rs @@ -6664,12 +6664,124 @@ fn actual_text_pairs_past_the_marked_content_cap() { } } -/// #2992: the colour a page is painted with before anything else is its background, for exports -/// that keep a page colour. Edit a PDF ▸ Background's fill is found under the text it goes -/// behind; a page that paints anything else first, a fill that doesn't cover the page, a -/// translucent or clipped one, or a colour that isn't plain gray, RGB or CMYK has none. +fn page_background_from_content(content: &str, resources: &str) -> Option<[f64; 3]> { + let objects = [ + "<< /Type /Catalog /Pages 2 0 R >>".to_string(), + "<< /Type /Pages /Kids [3 0 R] /Count 1 >>".to_string(), + format!("<< /Type /Page /Parent 2 0 R /MediaBox [0 0 600 800] /CropBox [0 0 500 700] /Contents 4 0 R /Resources << {resources} >> >>"), + format!("<< /Length {} >>\nstream\n{content}\nendstream", content.len()), + ]; + let mut bytes = b"%PDF-1.7\n".to_vec(); + let mut offsets = Vec::new(); + for (index, object) in objects.iter().enumerate() { + offsets.push(bytes.len()); + bytes.extend_from_slice(format!("{} 0 obj\n{object}\nendobj\n", index + 1).as_bytes()); + } + let xref_offset = bytes.len(); + bytes.extend_from_slice(b"xref\n0 5\n0000000000 65535 f \n"); + for offset in offsets { + bytes.extend_from_slice(format!("{offset:010} 00000 n \n").as_bytes()); + } + bytes.extend_from_slice(format!("trailer\n<< /Size 5 /Root 1 0 R >>\nstartxref\n{xref_offset}\n%%EOF\n").as_bytes()); + page_background(&Document::open(Arc::new(bytes)).unwrap(), 0).unwrap() +} + +fn assert_page_background_fill_cases(gs: &str) { + assert_eq!(page_background_from_content("1 g 0 0 600 800 re f", ""), Some([1.0; 3]), "a producer's white page fill"); + assert_eq!(page_background_from_content("0 0 1 0 k 0 0 500 700 re f", ""), Some([1.0, 1.0, 0.0]), "CMYK, covering the crop box"); + assert_eq!(page_background_from_content("/DeviceRGB cs 1 0 0 sc 0 0 500 700 re f", ""), Some([1.0, 0.0, 0.0]), "cs and sc"); + assert_eq!(page_background_from_content("/Full gs q 2 0 0 2 0 0 cm 0 1 0 rg 0 0 300 400 re f Q", gs), Some([0.0, 1.0, 0.0]), "under a cm"); + assert_eq!(page_background_from_content("1 0 0 rg 0 0 300 800 re f", ""), None, "half the page"); + assert_eq!(page_background_from_content("1 0 0 rg 0 0 300 800 re 300 0 300 800 re f", ""), None, "two halves are not one covering rectangle"); + assert_eq!( + page_background_from_content("1 0 0 rg 0 0 300 800 re 0 0 600 800 re f", ""), + Some([1.0, 0.0, 0.0]), + "one of the rectangles covers it" + ); + // #2994 review: a second rectangle that cuts a hole: any one under even-odd, one wound the + // other way under nonzero. + assert_eq!(page_background_from_content("1 0 0 rg 0 0 600 800 re 100 100 200 200 re f*", ""), None, "even-odd hole"); + assert_eq!(page_background_from_content("1 0 0 rg 0 0 600 800 re 300 100 -200 200 re f", ""), None, "nonzero, reversed inner rectangle"); + assert_eq!( + page_background_from_content("1 0 0 rg 0 0 600 800 re 100 100 200 200 re f", ""), + Some([1.0, 0.0, 0.0]), + "nonzero, same winding: no hole" + ); + assert_eq!( + page_background_from_content("1 0 0 rg q -1 0 0 1 600 0 cm 0 0 600 800 re Q 100 100 200 200 re f", ""), + None, + "reversed by a mirroring cm" + ); + assert_eq!(page_background_from_content("/Half gs 1 0 0 rg 0 0 600 800 re f", gs), None, "translucent"); + assert_eq!(page_background_from_content("/Mul gs 1 0 0 rg 0 0 600 800 re f", gs), None, "blended"); + assert_eq!(page_background_from_content("0 0 100 100 re W n 1 0 0 rg 0 0 600 800 re f", ""), None, "clipped to a corner"); + assert_eq!(page_background_from_content("0 0 600 800 re W n 1 0 0 rg 0 0 600 800 re f", ""), Some([1.0, 0.0, 0.0]), "a page-sized clip"); + assert_eq!(page_background_from_content("/Pattern cs /P1 scn 0 0 600 800 re f", ""), None, "a pattern"); + assert_eq!(page_background_from_content("BT ET 0 0 600 800 re S 1 0 0 rg 0 0 600 800 re f", ""), None, "a stroke first"); + assert_eq!(page_background_from_content("0 0 m 600 0 l 600 800 l 0 800 l h f", ""), None, "a path that isn't a rectangle"); + assert_eq!( + page_background_from_content("1 0 0 rg 0 0 600 800 re 100 100 m 200 100 l 200 200 l h f*", ""), + None, + "a page fill with a hole cut in it" + ); +} + +fn assert_page_background_transform_and_clip_cases() { + // #2994 review: a rectangle turned 45° about the crop box's centre covers it only if the crop + // box's corners are inside it; its bounding box covering the crop box isn't enough. This one + // reaches 500 from the centre along each axis (its box covers the 500 × 700 crop box) but + // 354 along the diagonals, short of the corners. One reaching 707 covers them. + let turned = "0.70710678 0.70710678 -0.70710678 0.70710678 250 350 cm"; + assert_eq!( + page_background_from_content(&format!("1 0 0 rg {turned} -353.553 -353.553 707.107 707.107 re f"), ""), + None, + "a turned fill short of the corners" + ); + assert_eq!( + page_background_from_content(&format!("1 0 0 rg {turned} -500 -500 1000 1000 re f"), ""), + Some([1.0, 0.0, 0.0]), + "a turned fill over them" + ); + // The same for a clip. + assert_eq!( + page_background_from_content(&format!("{turned} -353.553 -353.553 707.107 707.107 re W n 1 0 0 rg -2000 -2000 4000 4000 re f"), ""), + None, + "a turned clip" + ); + assert_eq!( + page_background_from_content(&format!("{turned} -500 -500 1000 1000 re W n 1 0 0 rg -2000 -2000 4000 4000 re f"), ""), + Some([1.0, 0.0, 0.0]), + "a turned clip over the corners" + ); + // Clips add up: two that each cover the page leave it covered, one that doesn't among them + // doesn't. + assert_eq!( + page_background_from_content("0 0 600 800 re W n 0 0 550 750 re W n 1 0 0 rg 0 0 600 800 re f", ""), + Some([1.0, 0.0, 0.0]), + "two covering clips" + ); + assert_eq!( + page_background_from_content("0 0 600 800 re W n 0 0 300 750 re W n 1 0 0 rg 0 0 600 800 re f", ""), + None, + "the second clip doesn't cover" + ); + // Past 64 clipping rectangles the clip counts as unknown. + let clips = "0 0 600 800 re W n ".repeat(65); + assert_eq!(page_background_from_content(&format!("{clips}1 0 0 rg 0 0 600 800 re f"), ""), None, "too many clips to follow"); + // A rectangle drawn the other way round (negative width) covers the page all the same. + assert_eq!(page_background_from_content("1 0 0 rg 600 0 -600 800 re f", ""), Some([1.0, 0.0, 0.0]), "drawn clockwise"); + // The crop box counts as covered within half a percent of its size (2.5 × 3.5 here), the + // edge of that included. + assert_eq!(page_background_from_content("1 0 0 rg 2 3 496 694 re f", ""), Some([1.0, 0.0, 0.0]), "within the tolerance"); + assert_eq!(page_background_from_content("1 0 0 rg 2.5 3.5 495 693 re f", ""), Some([1.0, 0.0, 0.0]), "on the tolerance's edge"); + assert_eq!(page_background_from_content("1 0 0 rg 3 4 494 692 re f", ""), None, "past the tolerance"); +} + +/// #2992: page background detection follows the first full-page fill under text and ignores +/// partial, translucent, clipped, or unsupported fills. #[test] fn a_page_painted_first_with_a_full_page_fill_has_that_background() { + let gs = "/ExtGState << /Half << /ca 0.5 >> /Mul << /BM /Multiply >> /Full << /ca 1 /SMask /None >> >>"; let mut doc = fixture(); assert_eq!(page_background(&doc, 0).unwrap(), None, "text first"); add_background(&mut doc, &[0, 1], &Background { color: [0.0, 0.5, 0.5], opacity: 1.0, ..Background::default() }, false).unwrap(); @@ -6680,77 +6792,8 @@ fn a_page_painted_first_with_a_full_page_fill_has_that_background() { assert_eq!(page_background(&doc, 2).unwrap(), None, "a page with no content"); assert!(page_background(&doc, 9).is_err()); - let page = |content: &str, resources: &str| { - let objs: Vec = vec![ - "<< /Type /Catalog /Pages 2 0 R >>".into(), - "<< /Type /Pages /Kids [3 0 R] /Count 1 >>".into(), - format!("<< /Type /Page /Parent 2 0 R /MediaBox [0 0 600 800] /CropBox [0 0 500 700] /Contents 4 0 R /Resources << {resources} >> >>"), - format!("<< /Length {} >>\nstream\n{content}\nendstream", content.len()), - ]; - let mut out = b"%PDF-1.7\n".to_vec(); - let mut offs = Vec::new(); - for (i, o) in objs.iter().enumerate() { - offs.push(out.len()); - out.extend_from_slice(format!("{} 0 obj\n{o}\nendobj\n", i + 1).as_bytes()); - } - let x = out.len(); - out.extend_from_slice(b"xref\n0 5\n0000000000 65535 f \n"); - for o in offs { - out.extend_from_slice(format!("{o:010} 00000 n \n").as_bytes()); - } - out.extend_from_slice(format!("trailer\n<< /Size 5 /Root 1 0 R >>\nstartxref\n{x}\n%%EOF\n").as_bytes()); - page_background(&Document::open(Arc::new(out)).unwrap(), 0).unwrap() - }; - let gs = "/ExtGState << /Half << /ca 0.5 >> /Mul << /BM /Multiply >> /Full << /ca 1 /SMask /None >> >>"; - assert_eq!(page("1 g 0 0 600 800 re f", ""), Some([1.0; 3]), "a producer's white page fill"); - assert_eq!(page("0 0 1 0 k 0 0 500 700 re f", ""), Some([1.0, 1.0, 0.0]), "CMYK, covering the crop box"); - assert_eq!(page("/DeviceRGB cs 1 0 0 sc 0 0 500 700 re f", ""), Some([1.0, 0.0, 0.0]), "cs and sc"); - assert_eq!(page("/Full gs q 2 0 0 2 0 0 cm 0 1 0 rg 0 0 300 400 re f Q", gs), Some([0.0, 1.0, 0.0]), "under a cm"); - assert_eq!(page("1 0 0 rg 0 0 300 800 re f", ""), None, "half the page"); - assert_eq!(page("1 0 0 rg 0 0 300 800 re 300 0 300 800 re f", ""), None, "two halves are not one covering rectangle"); - assert_eq!(page("1 0 0 rg 0 0 300 800 re 0 0 600 800 re f", ""), Some([1.0, 0.0, 0.0]), "one of the rectangles covers it"); - // #2994 review: a second rectangle that cuts a hole: any one under even-odd, one wound the - // other way under nonzero. - assert_eq!(page("1 0 0 rg 0 0 600 800 re 100 100 200 200 re f*", ""), None, "even-odd hole"); - assert_eq!(page("1 0 0 rg 0 0 600 800 re 300 100 -200 200 re f", ""), None, "nonzero, reversed inner rectangle"); - assert_eq!(page("1 0 0 rg 0 0 600 800 re 100 100 200 200 re f", ""), Some([1.0, 0.0, 0.0]), "nonzero, same winding: no hole"); - assert_eq!(page("1 0 0 rg q -1 0 0 1 600 0 cm 0 0 600 800 re Q 100 100 200 200 re f", ""), None, "reversed by a mirroring cm"); - assert_eq!(page("/Half gs 1 0 0 rg 0 0 600 800 re f", gs), None, "translucent"); - assert_eq!(page("/Mul gs 1 0 0 rg 0 0 600 800 re f", gs), None, "blended"); - assert_eq!(page("0 0 100 100 re W n 1 0 0 rg 0 0 600 800 re f", ""), None, "clipped to a corner"); - assert_eq!(page("0 0 600 800 re W n 1 0 0 rg 0 0 600 800 re f", ""), Some([1.0, 0.0, 0.0]), "a page-sized clip"); - assert_eq!(page("/Pattern cs /P1 scn 0 0 600 800 re f", ""), None, "a pattern"); - assert_eq!(page("BT ET 0 0 600 800 re S 1 0 0 rg 0 0 600 800 re f", ""), None, "a stroke first"); - assert_eq!(page("0 0 m 600 0 l 600 800 l 0 800 l h f", ""), None, "a path that isn't a rectangle"); - assert_eq!(page("1 0 0 rg 0 0 600 800 re 100 100 m 200 100 l 200 200 l h f*", ""), None, "a page fill with a hole cut in it"); - // #2994 review: a rectangle turned 45° about the crop box's centre covers it only if the crop - // box's corners are inside it; its bounding box covering the crop box isn't enough. This one - // reaches 500 from the centre along each axis (its box covers the 500 × 700 crop box) but - // 354 along the diagonals, short of the corners. One reaching 707 covers them. - let turned = "0.70710678 0.70710678 -0.70710678 0.70710678 250 350 cm"; - assert_eq!(page(&format!("1 0 0 rg {turned} -353.553 -353.553 707.107 707.107 re f"), ""), None, "a turned fill short of the corners"); - assert_eq!(page(&format!("1 0 0 rg {turned} -500 -500 1000 1000 re f"), ""), Some([1.0, 0.0, 0.0]), "a turned fill over them"); - // The same for a clip. - assert_eq!(page(&format!("{turned} -353.553 -353.553 707.107 707.107 re W n 1 0 0 rg -2000 -2000 4000 4000 re f"), ""), None, "a turned clip"); - assert_eq!( - page(&format!("{turned} -500 -500 1000 1000 re W n 1 0 0 rg -2000 -2000 4000 4000 re f"), ""), - Some([1.0, 0.0, 0.0]), - "a turned clip over the corners" - ); - // Clips add up: two that each cover the page leave it covered, one that doesn't among them - // doesn't. - assert_eq!(page("0 0 600 800 re W n 0 0 550 750 re W n 1 0 0 rg 0 0 600 800 re f", ""), Some([1.0, 0.0, 0.0]), "two covering clips"); - assert_eq!(page("0 0 600 800 re W n 0 0 300 750 re W n 1 0 0 rg 0 0 600 800 re f", ""), None, "the second clip doesn't cover"); - // Past 64 clipping rectangles the clip counts as unknown. - let clips = "0 0 600 800 re W n ".repeat(65); - assert_eq!(page(&format!("{clips}1 0 0 rg 0 0 600 800 re f"), ""), None, "too many clips to follow"); - // A rectangle drawn the other way round (negative width) covers the page all the same. - assert_eq!(page("1 0 0 rg 600 0 -600 800 re f", ""), Some([1.0, 0.0, 0.0]), "drawn clockwise"); - // The crop box counts as covered within half a percent of its size (2.5 × 3.5 here), the - // edge of that included. - assert_eq!(page("1 0 0 rg 2 3 496 694 re f", ""), Some([1.0, 0.0, 0.0]), "within the tolerance"); - assert_eq!(page("1 0 0 rg 2.5 3.5 495 693 re f", ""), Some([1.0, 0.0, 0.0]), "on the tolerance's edge"); - assert_eq!(page("1 0 0 rg 3 4 494 692 re f", ""), None, "past the tolerance"); + assert_page_background_fill_cases(gs); + assert_page_background_transform_and_clip_cases(); } #[test] diff --git a/crates/edit/src/text/blocks.rs b/crates/edit/src/text/blocks.rs index 8d3d224da0..615e7699a2 100644 --- a/crates/edit/src/text/blocks.rs +++ b/crates/edit/src/text/blocks.rs @@ -1,7 +1,7 @@ use super::interp::{Carry, interpret}; use super::lines::{content_streams, page_dict, reading_lines, rewritten_contents, splice, text_lines}; use super::rewrite::{LineEdit, coincident_ops, rewrite_block}; -use super::*; +use super::{Document, EditError, HashMap, Object, Op, Pieces, TextLine, group_blocks, regions}; /// An editable text region: adjacent runs on visual rows, followed by aligned rows. /// A region may contain several source fonts, sizes, colours and weights. diff --git a/crates/edit/src/text/editor.rs b/crates/edit/src/text/editor.rs index b2bd2b9f97..f7aa1f47bd 100644 --- a/crates/edit/src/text/editor.rs +++ b/crates/edit/src/text/editor.rs @@ -2,7 +2,7 @@ use super::blocks::{BlockStyle, TextBlock}; use super::fallback::MAX_TYPE3_GLYPHS; use super::lines::{page_dict, text_lines}; use super::rewrite::rewrite_block_from; -use super::*; +use super::{DecodeBudget, Document, EditError, Metrics, Object, TextLine, TextSession}; /// An embedded sfnt source face, read only for the inline editor. Bytes stay in memory and /// are never installed, copied into assets, or used as a font for another document. diff --git a/crates/edit/src/text/fallback.rs b/crates/edit/src/text/fallback.rs index 0c19a6680a..b8f45a221f 100644 --- a/crates/edit/src/text/fallback.rs +++ b/crates/edit/src/text/fallback.rs @@ -1,6 +1,8 @@ use super::interp::Ts; use super::lines::page_dict; -use super::*; +use super::{ + CraftFont, Dict, Document, EditError, GlyphError, HashMap, Metrics, Object, Op, PdfString, Stream, TextLine, japanese_glyph_from, parse, +}; /// Text → the runs that show it: each run's font resource name and the bytes shown in that font. pub(super) type Encoder = Box Option)>>>; diff --git a/crates/edit/src/text/interp.rs b/crates/edit/src/text/interp.rs index ca0d63cef4..e4248aedea 100644 --- a/crates/edit/src/text/interp.rs +++ b/crates/edit/src/text/interp.rs @@ -1,6 +1,6 @@ use super::fallback::is_type3_fallback; use super::rewrite::vertical_advance; -use super::*; +use super::{Dict, Document, EditError, HashMap, Matrix, Metrics, Object, Op, Rc}; /// Text and graphics state captured for rewriting. #[derive(Clone, Debug, PartialEq)] @@ -472,6 +472,280 @@ type CachedFont = (Rc, Option, Result, String>); /// A `Do` met while interpreting: its operator index, XObject name and the state there. type Invocation = (usize, Vec, Ts); +#[derive(Default)] +struct MarkedContent { + regions: Vec>, + layers: Vec>>, + actual_text: Vec>, +} + +impl MarkedContent { + fn begin(&mut self, doc: &Document, op: &Op, index: usize, logical_text: Option<&Dict>, shown_count: usize) { + // Marked text paragraphs/headings are authoritative boundaries. Ignore artifacts and + // inner spans, which inherit their enclosing region. + let region = matches!(op.name(0), Some(b"P" | b"H" | b"H1" | b"H2" | b"H3" | b"H4" | b"H5" | b"H6" | b"LI" | b"TD" | b"TH")); + self.regions.push(if region { Some(index) } else { self.regions.last().copied().flatten() }); + // A layer named in the resources is told apart by its name, an inline one by where it opens. + let layer = op.is("BDC") && op.name(0) == Some(b"OC".as_slice()); + self.layers + .push(layer.then(|| op.operands.get(1).and_then(Object::as_name).map_or_else(|| format!("@{index}").into_bytes(), <[u8]>::to_vec))); + // The property list is inline or named in the resources' /Properties (§14.6.2). + let list = logical_text.and_then(|properties| match op.operands.get(1) { + Some(Object::Name(name)) => properties.get(name).and_then(|object| doc.dict(object)), + other => other.and_then(Object::as_dict).cloned(), + }); + let logical = list.as_ref().and_then(|dict| dict.get(b"ActualText")).and_then(|value| match value { + Object::String(value) if value.bytes.len() <= 4_000_000 => Some(value.to_text()), + _ => None, + }); + self.actual_text.push(logical.map(|text| (shown_count, index, text))); + } + + fn end(&mut self, index: usize, shown: &mut Vec) { + self.regions.pop(); + self.layers.pop(); + if let Some(Some((start, open, logical))) = self.actual_text.pop() { + let tail = shown.split_off(start.min(shown.len())); + let mut items = tail.into_iter(); + if let Some(mut first) = items.next() { + for item in items { + first.glyph_count = first.glyph_count.saturating_add(item.glyph_count); + first.extra_ops.push(item.op); + first.extra_ops.extend(item.extra_ops); + first.rect = [ + first.rect[0].min(item.rect[0]), + first.rect[1].min(item.rect[1]), + first.rect[2].max(item.rect[2]), + first.rect[3].max(item.rect[3]), + ]; + first.frame = union(first.frame, item.frame); + first.ink.extend(item.ink); + } + first.extra_ops.extend([open, index]); + // Only right-to-left ActualText is already in typing order and must stay out of + // bidi recovery. Word and Chrome also wrap Latin ligatures mid-word. + first.logical_order = logical.chars().any(crate::bidi::is_rtl); + first.actual_text = true; + first.text = logical; + first.start_x = first.rect[0]; + first.end_x = first.rect[2]; + first.end_y = first.baseline; + first.advance = (first.end_x - first.start_x) / first.tm.then(&first.state.ctm).0[0].abs().max(1e-6); + shown.push(first); + } + } + } +} + +struct TextRunState<'a> { + ts: &'a mut Ts, + tm: &'a mut Matrix, + tlm: &'a mut Matrix, + at_bt: &'a (usize, Ts), + bt: usize, + marked: &'a MarkedContent, + carry: &'a mut Carry, + out: &'a mut Vec, +} + +fn show_text(op: &Op, i: usize, state: &mut TextRunState<'_>) -> Result<(), EditError> { + let ts = &mut *state.ts; + let tm = &mut *state.tm; + let tlm = &mut *state.tlm; + let at_bt = state.at_bt; + let bt = state.bt; + let marked = state.marked; + let carry = &mut *state.carry; + let out = &mut *state.out; + if matches!(op.op.as_slice(), b"'" | b"\"") { + if op.is("\"") { + ts.word_spacing = op.num(0).unwrap_or(ts.word_spacing); + ts.char_spacing = op.num(1).unwrap_or(ts.char_spacing); + } + *tlm = Matrix([1.0, 0.0, 0.0, 1.0, 0.0, -ts.leading]).then(tlm); + *tm = *tlm; + } + let Some((name, m)) = ts.font.clone() else { return Ok(()) }; + // Pieces: strings, and TJ number adjustments. + let pieces: Vec = match op.op.as_slice() { + // A surplus array (`[(A)] [(B)] TJ`) is malformed, but the operator still + // takes the one immediately before it, as the renderer and every other + // reader here do (#3569) -- not the first, which a reader counting operands + // from the front of a surplus list would otherwise take. + b"TJ" => op.operands.last().and_then(Object::as_array).cloned().unwrap_or_default(), + _ => op.operands.last().cloned().into_iter().collect(), + }; + // Tc is already included in the pen advance; TJ may encode tracking instead. + let tracking = if op.is("TJ") { tj_tracking(&pieces, &m, ts.size, ts.scale) } else { 0.0 }; + let trm0 = tm.then(&ts.ctm); + let start = trm0.apply(0.0, ts.rise); + let mut text = String::new(); + let mut decodable = true; + let mut x_text = 0.0; + // Vertical text (§9.4.4): the pen moves along y instead, and each glyph is centred + // on it horizontally; `half` is half the widest glyph. + let vertical = ts.vertical; + let (mut y_text, mut half) = (0.0, 0.0_f64); + // Where each word's glyphs start and end along the run (text space), and whether + // the next glyph continues the last word. + let mut words: Vec<(f64, f64)> = Vec::new(); + let mut in_word = false; + let mut glyph_count = 0_usize; + for p in &pieces { + match p { + Object::String(s) => { + for (code, len) in m.codes(&s.bytes) { + glyph_count = glyph_count.saturating_add(1); + let shown = m.text_of(code); + let blank = m.is_space(code, len) || shown.as_deref().is_some_and(|t| !t.is_empty() && t.chars().all(char::is_whitespace)); + match shown { + Some(t) => { + carry.text_left = carry + .text_left + .checked_sub(t.len()) + .ok_or_else(|| EditError::Invalid("the page's text is too large to read".into()))?; + text.push_str(&t); + } + None => decodable = false, + } + let spacing = ts.char_spacing + if m.is_space(code, len) { ts.word_spacing } else { 0.0 }; + if let Some(w1) = vertical { + half = half.max((m.width(code) * ts.size * ts.scale).abs() / 2.0); + if !blank { + let ink_end = y_text + w1 * ts.size; + let (lo, hi) = (y_text.min(ink_end), y_text.max(ink_end)); + match words.last_mut() { + Some(word) if in_word => *word = (word.0.min(lo), word.1.max(hi)), + _ => words.push((lo, hi)), + } + } + in_word = !blank; + y_text += w1 * ts.size + spacing; + continue; + } + if !blank { + let ink_end = x_text + m.width(code) * ts.size * ts.scale; + // A negative font size or `Tz` runs the glyphs backwards: + // the word is the union of its glyphs, whichever way they go. + let (lo, hi) = (x_text.min(ink_end), x_text.max(ink_end)); + match words.last_mut() { + Some(word) if in_word => *word = (word.0.min(lo), word.1.max(hi)), + _ => words.push((lo, hi)), + } + } + in_word = !blank; + let w = m.width(code) * ts.size + ts.char_spacing + if m.is_space(code, len) { ts.word_spacing } else { 0.0 }; + x_text += w * ts.scale; + } + } + other => { + if let Some(n) = other.as_f64() { + if vertical.is_some() { + // Down by n/1000 em, not scaled by `Tz`. + let dy = -n / 1000.0 * ts.size; + if -dy > ts.size * 0.2 && !text.ends_with(' ') { + text.push(' '); + } + if dy.abs() > ts.size.abs() * 0.2 { + in_word = false; + } + y_text += dy; + continue; + } + let dx = -n / 1000.0 * ts.size * ts.scale; + // A large gap inside TJ reads as a space. + if dx - tracking > (ts.size * ts.scale).abs() * 0.2 && !text.ends_with(' ') { + text.push(' '); + } + // Tracking and kerning keep a word together; a larger jump + // ends it (whatever the sign of the size or `Tz`). + if dx - tracking > (ts.size * ts.scale).abs() * 0.2 || dx < -(ts.size * ts.scale).abs() * 0.2 { + in_word = false; + } + x_text += dx; + } + } + } + } + *tm = Matrix([1.0, 0.0, 0.0, 1.0, x_text, y_text]).then(tm); + let end = tm.then(&ts.ctm).apply(0.0, ts.rise); + // The box from `a` to `b` along the run: from descent to ascent across it, or for + // vertical text, the widest glyph's width centred on the pen. + let span = |a: f64, b: f64| match vertical { + Some(_) => [trm0.apply(-half, ts.rise + a), trm0.apply(half, ts.rise + a), trm0.apply(-half, ts.rise + b), trm0.apply(half, ts.rise + b)], + None => [ + trm0.apply(a, ts.rise + m.descent * ts.size), + trm0.apply(b, ts.rise + m.descent * ts.size), + trm0.apply(a, ts.rise + m.ascent * ts.size), + trm0.apply(b, ts.rise + m.ascent * ts.size), + ], + }; + let corners = span(0.0, if vertical.is_some() { y_text } else { x_text }); + let rect = corners.iter().fold([f64::MAX, f64::MAX, f64::MIN, f64::MIN], |b, p| [b[0].min(p.0), b[1].min(p.1), b[2].max(p.0), b[3].max(p.1)]); + // The same corners along and across the baseline: the run's own box, not its + // upright bounding box turned (which is wider by the box's height on a slant). + let dir = direction(&trm0); + let frame = corners + .iter() + .map(|&p| to_frame(dir, p)) + .fold([f64::MAX, f64::MAX, f64::MIN, f64::MIN], |b, p| [b[0].min(p.0), b[1].min(p.1), b[2].max(p.0), b[3].max(p.1)]); + let ink = words + .iter() + .map(|&(a, b)| { + span(a, b).iter().fold([f64::MAX, f64::MAX, f64::MIN, f64::MIN], |r, p| [r[0].min(p.0), r[1].min(p.1), r[2].max(p.0), r[3].max(p.1)]) + }) + .collect(); + let size_user = (trm0.0[2].powi(2) + trm0.0[3].powi(2)).sqrt() * ts.size; + // A numeric-only TJ adjusts the current text matrix but paints no glyphs. + // It must not create a phantom editable line or enlarge its neighbours' boxes. + if !pieces.iter().any(|p| matches!(p, Object::String(s) if !s.bytes.is_empty())) { + return Ok(()); + } + out.push(Shown { + op: i, + extra_ops: Vec::new(), + glyph_count, + // Vertical text: the TJ adjustment that undoes the run is n = -1000 y / size; the + // preview divides by size × `Tz`, so `Tz` is put back here. + advance: if vertical.is_some() { y_text * ts.scale } else { x_text }, + tracking: 0.0, + tm: Matrix([ + tm.0[0], + tm.0[1], + tm.0[2], + tm.0[3], + tm.0[4] - x_text * tm.0[0] - y_text * tm.0[2], + tm.0[5] - x_text * tm.0[1] - y_text * tm.0[3], + ]), + state: ts.clone(), + tlm: *tlm, + bt_op: at_bt.0, + bt_state: at_bt.1.clone(), + text, + rect, + frame, + ink, + baseline: start.1, + start_x: start.0, + end_x: end.0, + end_y: end.1, + bt, + font: name, + base_font: m.base_font.clone(), + face: ts.face.clone(), + size: if size_user > 0.0 { size_user } else { ts.size }, + bold: m.bold, + italic: m.italic, + visual_order: m.visual_order, + decodable, + scope: marked.regions.last().copied().flatten(), + paint: Paint { layers: marked.layers.iter().flatten().cloned().collect(), gs: ts.gs.clone() }, + logical_order: false, + actual_text: false, + }); + Ok(()) +} + pub(super) fn interpret( doc: &Document, ops: &[Op], @@ -490,66 +764,17 @@ pub(super) fn interpret( let mut stack: Vec = std::mem::take(&mut carry.stack); let (mut tm, mut tlm) = (Matrix::IDENTITY, Matrix::IDENTITY); let mut bt = 0usize; - let mut marked = std::mem::take(&mut carry.marked); - let mut layers = std::mem::take(&mut carry.layers); - let mut actual: Vec> = Vec::new(); + let mut marked = + MarkedContent { regions: std::mem::take(&mut carry.marked), layers: std::mem::take(&mut carry.layers), ..MarkedContent::default() }; for (i, op) in ops.iter().enumerate() { match op.op.as_slice() { // No depth cap: every `EMC` pops, so a capped push would pair it with the enclosing // sequence (#3573). Both stacks stay bounded by the number of operators. b"BMC" | b"BDC" => { - // Marked text paragraphs/headings are authoritative boundaries. Ignore - // artifacts and inner spans, which inherit their enclosing region. - let region = matches!(op.name(0), Some(b"P" | b"H" | b"H1" | b"H2" | b"H3" | b"H4" | b"H5" | b"H6" | b"LI" | b"TD" | b"TH")); - marked.push(if region { Some(i) } else { marked.last().copied().flatten() }); - // A layer named in the resources is told apart by its name, an inline one by where it opens. - let layer = op.is("BDC") && op.name(0) == Some(b"OC".as_slice()); - layers.push(layer.then(|| op.operands.get(1).and_then(Object::as_name).map_or_else(|| format!("@{i}").into_bytes(), <[u8]>::to_vec))); - // The property list is inline or named in the resources' /Properties (§14.6.2). - let list = logical_text.and_then(|properties| match op.operands.get(1) { - Some(Object::Name(n)) => properties.get(n).and_then(|o| doc.dict(o)), - other => other.and_then(Object::as_dict).cloned(), - }); - let logical = list.as_ref().and_then(|d| d.get(b"ActualText")).and_then(|s| match s { - Object::String(s) if s.bytes.len() <= 4_000_000 => Some(s.to_text()), - _ => None, - }); - actual.push(logical.map(|s| (out.len(), i, s))); + marked.begin(doc, op, i, logical_text, out.len()); } b"EMC" => { - marked.pop(); - layers.pop(); - if let Some(Some((start, open, logical))) = actual.pop() { - let tail = out.split_off(start.min(out.len())); - let mut items = tail.into_iter(); - if let Some(mut first) = items.next() { - for shown in items { - first.glyph_count = first.glyph_count.saturating_add(shown.glyph_count); - first.extra_ops.push(shown.op); - first.extra_ops.extend(shown.extra_ops); - first.rect = [ - first.rect[0].min(shown.rect[0]), - first.rect[1].min(shown.rect[1]), - first.rect[2].max(shown.rect[2]), - first.rect[3].max(shown.rect[3]), - ]; - first.frame = union(first.frame, shown.frame); - first.ink.extend(shown.ink); - } - first.extra_ops.extend([open, i]); - // Only right-to-left ActualText is already in typing order and must stay - // out of the line's bidi recovery. Word and Chrome wrap Latin ligatures - // (`fi`, `fl`) in ActualText spans mid-word; those keep joining their line. - first.logical_order = logical.chars().any(crate::bidi::is_rtl); - first.actual_text = true; - first.text = logical; - first.start_x = first.rect[0]; - first.end_x = first.rect[2]; - first.end_y = first.baseline; - first.advance = (first.end_x - first.start_x) / first.tm.then(&first.state.ctm).0[0].abs().max(1e-6); - out.push(first); - } - } + marked.end(i, &mut out); } b"q" => stack.push(ts.clone()), b"Q" => { @@ -650,207 +875,16 @@ pub(super) fn interpret( tm = tlm; } b"Tj" | b"TJ" | b"'" | b"\"" => { - if matches!(op.op.as_slice(), b"'" | b"\"") { - if op.is("\"") { - ts.word_spacing = op.num(0).unwrap_or(ts.word_spacing); - ts.char_spacing = op.num(1).unwrap_or(ts.char_spacing); - } - tlm = Matrix([1.0, 0.0, 0.0, 1.0, 0.0, -ts.leading]).then(&tlm); - tm = tlm; - } - let Some((name, m)) = ts.font.clone() else { continue }; - // Pieces: strings, and TJ number adjustments. - let pieces: Vec = match op.op.as_slice() { - // A surplus array (`[(A)] [(B)] TJ`) is malformed, but the operator still - // takes the one immediately before it, as the renderer and every other - // reader here do (#3569) -- not the first, which a reader counting operands - // from the front of a surplus list would otherwise take. - b"TJ" => op.operands.last().and_then(Object::as_array).cloned().unwrap_or_default(), - _ => op.operands.last().cloned().into_iter().collect(), - }; - // Tc is already included in the pen advance; TJ may encode tracking instead. - let tracking = if op.is("TJ") { tj_tracking(&pieces, &m, ts.size, ts.scale) } else { 0.0 }; - let trm0 = tm.then(&ts.ctm); - let start = trm0.apply(0.0, ts.rise); - let mut text = String::new(); - let mut decodable = true; - let mut x_text = 0.0; - // Vertical text (§9.4.4): the pen moves along y instead, and each glyph is centred - // on it horizontally; `half` is half the widest glyph. - let vertical = ts.vertical; - let (mut y_text, mut half) = (0.0, 0.0_f64); - // Where each word's glyphs start and end along the run (text space), and whether - // the next glyph continues the last word. - let mut words: Vec<(f64, f64)> = Vec::new(); - let mut in_word = false; - let mut glyph_count = 0_usize; - for p in &pieces { - match p { - Object::String(s) => { - for (code, len) in m.codes(&s.bytes) { - glyph_count = glyph_count.saturating_add(1); - let shown = m.text_of(code); - let blank = - m.is_space(code, len) || shown.as_deref().is_some_and(|t| !t.is_empty() && t.chars().all(char::is_whitespace)); - match shown { - Some(t) => { - carry.text_left = carry - .text_left - .checked_sub(t.len()) - .ok_or_else(|| EditError::Invalid("the page's text is too large to read".into()))?; - text.push_str(&t); - } - None => decodable = false, - } - let spacing = ts.char_spacing + if m.is_space(code, len) { ts.word_spacing } else { 0.0 }; - if let Some(w1) = vertical { - half = half.max((m.width(code) * ts.size * ts.scale).abs() / 2.0); - if !blank { - let ink_end = y_text + w1 * ts.size; - let (lo, hi) = (y_text.min(ink_end), y_text.max(ink_end)); - match words.last_mut() { - Some(word) if in_word => *word = (word.0.min(lo), word.1.max(hi)), - _ => words.push((lo, hi)), - } - } - in_word = !blank; - y_text += w1 * ts.size + spacing; - continue; - } - if !blank { - let ink_end = x_text + m.width(code) * ts.size * ts.scale; - // A negative font size or `Tz` runs the glyphs backwards: - // the word is the union of its glyphs, whichever way they go. - let (lo, hi) = (x_text.min(ink_end), x_text.max(ink_end)); - match words.last_mut() { - Some(word) if in_word => *word = (word.0.min(lo), word.1.max(hi)), - _ => words.push((lo, hi)), - } - } - in_word = !blank; - let w = m.width(code) * ts.size + ts.char_spacing + if m.is_space(code, len) { ts.word_spacing } else { 0.0 }; - x_text += w * ts.scale; - } - } - other => { - if let Some(n) = other.as_f64() { - if vertical.is_some() { - // Down by n/1000 em, not scaled by `Tz`. - let dy = -n / 1000.0 * ts.size; - if -dy > ts.size * 0.2 && !text.ends_with(' ') { - text.push(' '); - } - if dy.abs() > ts.size.abs() * 0.2 { - in_word = false; - } - y_text += dy; - continue; - } - let dx = -n / 1000.0 * ts.size * ts.scale; - // A large gap inside TJ reads as a space. - if dx - tracking > (ts.size * ts.scale).abs() * 0.2 && !text.ends_with(' ') { - text.push(' '); - } - // Tracking and kerning keep a word together; a larger jump - // ends it (whatever the sign of the size or `Tz`). - if dx - tracking > (ts.size * ts.scale).abs() * 0.2 || dx < -(ts.size * ts.scale).abs() * 0.2 { - in_word = false; - } - x_text += dx; - } - } - } - } - tm = Matrix([1.0, 0.0, 0.0, 1.0, x_text, y_text]).then(&tm); - let end = tm.then(&ts.ctm).apply(0.0, ts.rise); - // The box from `a` to `b` along the run: from descent to ascent across it, or for - // vertical text, the widest glyph's width centred on the pen. - let span = |a: f64, b: f64| match vertical { - Some(_) => { - [trm0.apply(-half, ts.rise + a), trm0.apply(half, ts.rise + a), trm0.apply(-half, ts.rise + b), trm0.apply(half, ts.rise + b)] - } - None => [ - trm0.apply(a, ts.rise + m.descent * ts.size), - trm0.apply(b, ts.rise + m.descent * ts.size), - trm0.apply(a, ts.rise + m.ascent * ts.size), - trm0.apply(b, ts.rise + m.ascent * ts.size), - ], - }; - let corners = span(0.0, if vertical.is_some() { y_text } else { x_text }); - let rect = corners - .iter() - .fold([f64::MAX, f64::MAX, f64::MIN, f64::MIN], |b, p| [b[0].min(p.0), b[1].min(p.1), b[2].max(p.0), b[3].max(p.1)]); - // The same corners along and across the baseline: the run's own box, not its - // upright bounding box turned (which is wider by the box's height on a slant). - let dir = direction(&trm0); - let frame = corners - .iter() - .map(|&p| to_frame(dir, p)) - .fold([f64::MAX, f64::MAX, f64::MIN, f64::MIN], |b, p| [b[0].min(p.0), b[1].min(p.1), b[2].max(p.0), b[3].max(p.1)]); - let ink = words - .iter() - .map(|&(a, b)| { - span(a, b) - .iter() - .fold([f64::MAX, f64::MAX, f64::MIN, f64::MIN], |r, p| [r[0].min(p.0), r[1].min(p.1), r[2].max(p.0), r[3].max(p.1)]) - }) - .collect(); - let size_user = (trm0.0[2].powi(2) + trm0.0[3].powi(2)).sqrt() * ts.size; - // A numeric-only TJ adjusts the current text matrix but paints no glyphs. - // It must not create a phantom editable line or enlarge its neighbours' boxes. - if !pieces.iter().any(|p| matches!(p, Object::String(s) if !s.bytes.is_empty())) { - continue; - } - out.push(Shown { - op: i, - extra_ops: Vec::new(), - glyph_count, - // Vertical text: the TJ adjustment that undoes the run is n = -1000 y / size; the - // preview divides by size × `Tz`, so `Tz` is put back here. - advance: if vertical.is_some() { y_text * ts.scale } else { x_text }, - tracking: 0.0, - tm: Matrix([ - tm.0[0], - tm.0[1], - tm.0[2], - tm.0[3], - tm.0[4] - x_text * tm.0[0] - y_text * tm.0[2], - tm.0[5] - x_text * tm.0[1] - y_text * tm.0[3], - ]), - state: ts.clone(), - tlm, - bt_op: at_bt.0, - bt_state: at_bt.1.clone(), - text, - rect, - frame, - ink, - baseline: start.1, - start_x: start.0, - end_x: end.0, - end_y: end.1, - bt, - font: name, - base_font: m.base_font.clone(), - face: ts.face.clone(), - size: if size_user > 0.0 { size_user } else { ts.size }, - bold: m.bold, - italic: m.italic, - visual_order: m.visual_order, - decodable, - scope: marked.last().copied().flatten(), - paint: Paint { layers: layers.iter().flatten().cloned().collect(), gs: ts.gs.clone() }, - logical_order: false, - actual_text: false, - }); + let mut state = TextRunState { ts: &mut ts, tm: &mut tm, tlm: &mut tlm, at_bt: &at_bt, bt, marked: &marked, carry, out: &mut out }; + show_text(op, i, &mut state)?; } _ => {} } } carry.ts = ts; carry.stack = stack; - carry.marked = marked; - carry.layers = layers; + carry.marked = marked.regions; + carry.layers = marked.layers; positioned_tracking(&mut out); Ok(out) } diff --git a/crates/edit/src/text/lines.rs b/crates/edit/src/text/lines.rs index 7543adeb39..c48522984d 100644 --- a/crates/edit/src/text/lines.rs +++ b/crates/edit/src/text/lines.rs @@ -1,6 +1,6 @@ use super::fallback::{same_font, same_paint}; use super::interp::{Carry, Origin, Pen, Shown, TextState, Ts, direction, interpret, to_frame, union}; -use super::*; +use super::{DecodeBudget, Dict, Document, EditError, HashMap, Matrix, Object, Op, Pieces, Stream, TextLine, parse, serialize_ops}; impl TextLine { /// The baseline's height in user space. diff --git a/crates/edit/src/text/rewrite.rs b/crates/edit/src/text/rewrite.rs index dd58c72898..513077a027 100644 --- a/crates/edit/src/text/rewrite.rs +++ b/crates/edit/src/text/rewrite.rs @@ -1,11 +1,14 @@ use super::blocks::{BlockStyle, TextBlock, paragraph_separator, wrap}; use super::fallback::{ - Encoder, MAX_TYPE3_GLYPHS, drop_unused_fallback_fonts, needs_type3, no_japanese_font, source_encodes, source_family, source_program_completes, - source_show, source_space, source_width, type3_encode, type3_font, + Encoder, MAX_TYPE3_GLYPHS, Type3Fallback, drop_unused_fallback_fonts, needs_type3, no_japanese_font, source_encodes, source_family, + source_program_completes, source_show, source_space, source_width, type3_encode, type3_font, }; -use super::interp::{Carry, interpret}; +use super::interp::{Carry, Origin, TextState, interpret}; use super::lines::{content_streams, page_dict, rewritten_contents, splice, text_lines}; -use super::*; +use super::{ + Dict, Document, EditError, HashMap, Matrix, Metrics, Object, Op, PdfString, Pieces, TextLine, TextSession, group_blocks, is_centred, parse, + rewrite_styled_block, +}; /// What replacing a line did. #[derive(Clone, Debug, PartialEq)] @@ -206,6 +209,532 @@ pub(crate) fn rewrite_block_with_limit( TextSession::open(doc, page, block)?.commit_with_limit(doc, text, style, max_glyphs) } +struct RewriteDispatch { + upright: bool, + use_styled_path: bool, +} + +fn choose_rewrite_path( + doc: &Document, + fonts: &Dict, + block: &TextBlock, + members: &[&TextLine], + first: &TextLine, + text: Option<&str>, + style: &BlockStyle, +) -> Result { + let registered_face = fonts.iter().any(|(name, _)| name.starts_with(b"PCFull")); + // Hebrew is written back in drawing order by the single-style path. Styled regions do not + // reorder right-to-left runs. + let hebrew = text.unwrap_or(&block.text).chars().any(crate::bidi::is_hebrew); + if hebrew && (!style.ranges.is_empty() || style.resource.is_some()) { + return Err(EditError::Invalid( + "formatting part of right-to-left (Hebrew) text, or choosing a document font for it, isn't supported yet".into(), + )); + } + // Turned text is rewritten in its own text space by the single-style path. Styled layout uses + // page x-coordinates and cannot safely apply those operations to rotated runs. + let upright = members.iter().all(|line| line.upright()); + if !upright && (!style.ranges.is_empty() || style.resource.is_some()) { + return Err(EditError::Invalid("formatting part of turned text, or choosing a document font for it, isn't supported yet".into())); + } + let visual_indic = members.iter().any(|line| line.visual_order); + let has_special_text = text.is_some_and(|draft| { + draft.contains(['\n', '\r']) + || pdfcraft_fonts::source_shaping::required(draft) + || !pdfcraft_fonts::embedding::matching_faces(&block.base_font).is_empty() + }); + let has_multiple_runs = block.rows.iter().any(|row| row.len() > 1) + || members.iter().any(|line| line.font != first.font || line.size != first.size || line.color != first.color); + let source_requires_styled_path = + has_special_text || registered_face || text.is_some_and(|draft| source_program_completes(doc, fonts, first, draft)) || has_multiple_runs; + let explicit_styled_text = !style.ranges.is_empty() || style.resource.is_some(); + Ok(RewriteDispatch { + upright, + use_styled_path: upright + && !hebrew + && !visual_indic + && (explicit_styled_text || (source_requires_styled_path && style.family.is_none() && style.bold.is_none())), + }) +} + +/// The paragraph's text for writing back: explicit line breaks stay (#1443), and so does each typed +/// U+0020 space: a run of them is not folded into one (#4199, #3797). `\r\n` and a lone `\r` are +/// breaks too; other white space is written as one space. +fn paragraph_text(text: &str) -> String { + text.replace("\r\n", "\n") + .chars() + .map(|c| match c { + '\r' => '\n', + c if c != '\n' && paragraph_separator(c) => ' ', + c => c, + }) + .collect() +} + +/// Where a paragraph sits on its page, for choosing the width it is laid out in. +struct ParaGeometry { + rect: [f64; 4], + frame: [f64; 4], + crop: [f64; 4], + upright: bool, + /// The text-to-user scale. + k: f64, + /// The size in text space. + size: f64, + /// The requested horizontal move, in points. + dx: f64, + single_line: bool, + anchored_right: bool, + centred: bool, +} + +impl ParaGeometry { + /// A paragraph keeps its width (or takes the one asked for); a single line grows to the right + /// (to the left when right-to-left), up to the page's margin. + fn width(&self, requested: Option) -> Result { + let [left, _, right, _] = self.rect; + let own = (right - left).max(self.size * self.k); + let width = match requested { + // Capped at the largest page PDF allows (14 400 pt), even for text set larger than that + // (`clamp` panics when its minimum is the larger, or NaN). + Some(w) if w.is_finite() => w.clamp((self.size * self.k).min(14_400.0), 14_400.0), + Some(_) => return Err(EditError::Invalid("the paragraph's width must be a number".into())), + // Turned text: the page's margins are along another axis. A single line grows (below). + None if !self.upright => (self.frame[2] - self.frame[0]).max(self.size * self.k), + None if self.anchored_right => own.max(right + self.dx - (self.crop[0] + 36.0)), + // A centred line is not stretched to the margin: its own box is the frame it is centred in. + None if self.single_line && !self.centred => own.max(self.crop[2] - 36.0 - (left + self.dx)), + None => own, + }; + if width.is_finite() { Ok(width) } else { Err(EditError::Invalid("the paragraph's width must be a number".into())) } + } +} + +/// How far a baseline starting at `origin` and running along `direction` goes before it is 36 pt +/// from the page edge `low` or `high`. +fn margin_reach(origin: f64, direction: f64, low: f64, high: f64) -> f64 { + if direction > 1e-6 { + (high - 36.0 - origin) / direction + } else if direction < -1e-6 { + (low + 36.0 - origin) / direction + } else { + f64::INFINITY + } +} + +/// A turned single line grows to fit, up to where its baseline reaches the page's margin. +fn turned_line_width(first: &TextLine, crop: [f64; 4], offset: [f64; 2], width: f64, text: &str, advance: &Advance<'_>) -> f64 { + let (x0, y0) = (first.origin.x + offset[0], first.origin.baseline + offset[1]); + let (ux, uy) = first.direction(); + let tx = margin_reach(x0, ux, crop[0], crop[2]); + let ty = margin_reach(y0, uy, crop[1], crop[3]); + let cap = width.max(tx.min(ty)).min(14_400.0); + text.split('\n').map(|line| advance.of(line)).fold(width, f64::max).min(cap) +} + +/// The widths of the paragraph's text in the font it will be written in, in user space. +struct Advance<'a> { + /// The source font, when its glyphs are reused. + source: Option<&'a Metrics>, + type3: Option<&'a Type3Fallback>, + family: crate::added::Family, + bold: bool, + italic: bool, + size: f64, + space: f64, + char_spacing: f64, + word_spacing: f64, + scale: f64, + k: f64, +} + +impl Advance<'_> { + fn of(&self, s: &str) -> f64 { + let extra = s.chars().count() as f64 * self.char_spacing; + let t = match (self.source, self.type3) { + (Some(m), _) => { + let visual_s = if m.visual_order { crate::indic::to_visual(s) } else { s.to_owned() }; + source_width(m, &visual_s, self.size, self.space, self.char_spacing, self.word_spacing) + } + (None, Some(fallback)) => { + // Each character's count in `s`, from one pass over `s`. + let mut counts: HashMap = HashMap::new(); + for c in s.chars() { + let count = counts.entry(c).or_insert(0); + *count = count.saturating_add(1); + } + fallback.widths.iter().map(|(ch, width)| counts.get(ch).copied().unwrap_or(0) as f64 * width * self.size).sum::() + extra + } + (None, None) => self.family.std14(self.bold, self.italic).text_width(s, self.size) + extra, + }; + t * self.scale * self.k + } +} + +/// The font a rewritten paragraph is shown in, and how its text is encoded. +struct FontChoice { + show_font: String, + encode: Encoder, + /// The stand-in face to tell the caller about. + substituted: Option, +} + +/// What [`choose_font`] needs to know about the paragraph. +struct FontInputs<'a> { + /// The source font, when its glyphs are reused. + source: Option<&'a Metrics>, + type3: Option<&'a Type3Fallback>, + font_name: &'a str, + flat: &'a str, + source_base_font: &'a str, + family: crate::added::Family, + bold: bool, + italic: bool, + family_requested: bool, +} + +fn choose_font(inputs: &FontInputs<'_>, fonts_res: &mut Dict) -> Result { + if let Some(m) = inputs.source.cloned() { + let name = inputs.font_name.to_owned(); + return Ok(FontChoice { + show_font: name.clone(), + encode: Box::new(move |s: &str| m.encode(s).map(|bytes| vec![(name.clone(), bytes)])), + substituted: None, + }); + } + if let Some(fallback) = inputs.type3.cloned() { + let substituted = Some(format!("{} Type3", fallback.family)); + let first = fallback.names.first().cloned().ok_or_else(no_japanese_font)?; + return Ok(FontChoice { show_font: first, encode: Box::new(move |s: &str| type3_encode(&fallback, s)), substituted }); + } + let flat = inputs.flat; + let win = pdfcraft_fonts::win_ansi(flat); + let back: String = win.iter().map(|c| char::from_u32(u32::from(*c)).unwrap_or('?')).collect(); + let base = inputs.family.base_font(inputs.bold, inputs.italic); + if flat.chars().zip(back.chars()).any(|(a, c)| c == '?' && a != '?') { + return Err(EditError::Invalid(format!("\"{flat}\" has characters neither {} nor {base} can show", inputs.source_base_font))); + } + let mut f = Dict::new(); + f.set(b"Type".to_vec(), Object::name("Font")); + f.set(b"Subtype".to_vec(), Object::name("Type1")); + f.set(b"BaseFont".to_vec(), Object::name(base)); + f.set(b"Encoding".to_vec(), Object::name("WinAnsiEncoding")); + // Named after its face, as the line and region rewrites name theirs: one name for every + // stand-in would repoint the paragraphs set in an earlier one at this face (#4280). + let name = format!("PCEd{}", base.replace('-', "")); + fonts_res.set(name.clone().into_bytes(), Object::Dict(f)); + let substituted = (!inputs.family_requested).then(|| base.to_string()); + let shown = name.clone(); + Ok(FontChoice { show_font: name, encode: Box::new(move |s: &str| Some(vec![(shown.clone(), pdfcraft_fonts::win_ansi(s))])), substituted }) +} + +/// The paragraph's move in the space it is drawn in: the move is in page space, so it is taken +/// back through the CTM's linear part. Checked before the fallback fonts are written: a refused +/// paragraph leaves the document as it was. +fn drawn_movement(ctm: [f64; 6], dx: f64, dy: f64) -> Result, EditError> { + if dx == 0.0 && dy == 0.0 { + return Ok(None); + } + let back = Matrix([ctm[0], ctm[1], ctm[2], ctm[3], 0.0, 0.0]) + .invert() + .ok_or_else(|| EditError::Invalid("the paragraph is drawn in a space it can't be moved in".into()))?; + Ok(Some(back.apply(dx, dy))) +} + +/// The paragraph's first text matrix, taken from where its text starts to where it is written. +fn emit_text_matrix(first: &Origin, emit: &Origin) -> Result<[f64; 6], EditError> { + if first.ctm == emit.ctm { + return Ok(first.tm); + } + let emit_inv = Matrix(emit.ctm).invert().ok_or_else(|| EditError::Invalid("the paragraph has a singular transform".into()))?; + Ok(Matrix(first.tm).then(&Matrix(first.ctm)).then(&emit_inv).0) +} + +/// Line spacing in text space: the paragraph's own (scaled with the size), or 1.2 × the size. +struct LeadScale { + k: f64, + size: f64, + old_size: f64, + leading: f64, +} + +fn line_lead(block: &TextBlock, lines: &[TextLine], style: &BlockStyle, scale: &LeadScale) -> f64 { + if let Some(m) = style.line_spacing { + return scale.size * m.clamp(0.5, 5.0); + } + // From the first two rows (a row may hold several runs). + let rows = block.rows.first().zip(block.rows.get(1)).and_then(|(upper, lower)| upper.first().zip(lower.first())); + if let Some((upper, lower)) = rows.and_then(|(upper, lower)| lines.get(*upper).zip(lines.get(*lower))) { + return (upper.frame_origin().1 - lower.frame_origin().1) / scale.k * scale.size / scale.old_size; + } + if scale.leading > 0.0 { scale.leading } else { scale.size * 1.2 } +} + +/// The stroking twin of a fill colour operator. +fn stroke_twin(fill: &Op) -> Op { + let name = match fill.op.as_slice() { + b"g" => "G", + b"rg" => "RG", + b"k" => "K", + b"cs" => "CS", + b"sc" => "SC", + _ => "SCN", + }; + Op::new(name, fill.operands.clone()) +} + +/// Underlines in text space (the paragraph's text matrix), in its fill colour. +fn underline_ops(fill: &[Op], tm: &[f64; 6], size: f64, underlines: &[(f64, f64, f64)]) -> Vec { + let n = pdfcraft_content::num; + let mut ops = vec![Op::new("q", vec![]), Op::new("cm", tm.iter().map(|v| n(*v)).collect())]; + ops.extend(fill.iter().map(stroke_twin)); + ops.push(Op::new("w", vec![n(size * 0.06)])); + for (x0, x1, y) in underlines { + ops.push(Op::new("m", vec![n(*x0), n(*y)])); + ops.push(Op::new("l", vec![n(*x1), n(*y)])); + } + ops.push(Op::new("S", vec![])); + ops.push(Op::new("Q", vec![])); + ops +} + +/// Alignment: each line's offset from the left edge. +struct Alignment { + align: Option, + width: f64, + k: f64, + anchored_right: bool, + right_edge: f64, + rtl: bool, +} + +impl Alignment { + /// `visible` is the width the line is aligned on, in user space; the offset is in text space. + fn offset(&self, visible: f64) -> f64 { + let free = (self.width - visible).max(0.0) / self.k; + match self.align { + Some(crate::added::Align::Center) => free / 2.0, + // A right-to-left line anchored at its right edge may start left of the old box. + Some(crate::added::Align::Right) if self.anchored_right => (self.right_edge - visible) / self.k, + Some(crate::added::Align::Right) => free, + // A justified right-to-left paragraph ends its last line at the right edge. + Some(crate::added::Align::Justify) if self.rtl => free, + _ => 0.0, + } + } +} + +/// Everything the wrapped lines of one paragraph are written with. +struct LineWriter<'a> { + advance: &'a Advance<'a>, + alignment: Alignment, + encode: &'a Encoder, + source: Option<&'a Metrics>, + justify: bool, + /// Whether `Tw` reaches every shown space. + word_spacing_reaches_spaces: bool, + width: f64, + scale: f64, + k: f64, + size: f64, + space: f64, + char_spacing: f64, + lead: f64, +} + +/// What carries over from one line to the next. +struct LineCursor { + x: f64, + tw_set: f64, + shown_font: String, +} + +impl LineWriter<'_> { + /// Justify: each line but the last fills the width. A stretched line shows only its words, as + /// before #4199: word spacing would reach the spaces before its first word and after its + /// last, so they are left out. Nothing to stretch over, or a paragraph drawn at `0 Tz`, isn't + /// justified. + fn stretch(&self, body: &str, last: bool) -> f64 { + let interior = body.matches(' ').count(); + if self.justify && !last && interior > 0 && self.scale.abs() > 1e-6 { + Some((self.width - self.advance.of(body)).max(0.0) / self.k / self.scale / interior as f64).filter(|tw| tw.is_finite()).unwrap_or(0.0) + } else { + 0.0 + } + } + + /// The text to show for a line and the width it is aligned on. Other lines show every space + /// typed. A left-to-right one is aligned on its width up to its last word; a right-to-left + /// one on its whole width, since the spaces typed after its last word are drawn on its left + /// and the ones before its first on its right. + fn shown<'t>(&self, line: &'t str, body: &'t str, tw: f64) -> (&'t str, f64) { + if tw > 0.0 { + (body, self.advance.of(body)) + } else if crate::bidi::rtl_base(line) { + (line, self.advance.of(line)) + } else { + (line, self.advance.of(line.trim_end_matches(' '))) + } + } + + /// Writes one wrapped line, returning its underline (x0, x1, y) in text space. + fn write_line(&self, index: usize, line: &str, last: bool, cursor: &mut LineCursor, ops: &mut Vec) -> Result<(f64, f64, f64), EditError> { + let n = pdfcraft_content::num; + let body = line.trim_matches(' '); + let interior = body.matches(' ').count(); + let tw = self.stretch(body, last); + let (shown, visible) = self.shown(line, body, tw); + let dx = if tw > 0.0 { 0.0 } else { self.alignment.offset(visible) }; + if index > 0 || dx != 0.0 { + ops.push(Op::new("Td", vec![n(dx - cursor.x), n(if index > 0 { -self.lead } else { 0.0 })])); + } + cursor.x = dx; + // Word spacing reaches only single-byte code 32 (ISO 32000-1 §9.3.3), so where a space is + // shown with another code (a composite font, a generated Type 3 font, a subset without a + // space) the extra space follows each space as a TJ adjustment instead. + let stretch = if self.word_spacing_reaches_spaces { 0.0 } else { tw }; + let tw = tw - stretch; + if tw != cursor.tw_set { + ops.push(Op::new("Tw", vec![n(tw)])); + cursor.tw_set = tw; + } + // Each wrapped line in typing order; drawn left to right (right-to-left runs reversed). + let visual = crate::bidi::to_visual(shown); + // Stretched without word spacing: shown up to and including each space, then moved on. + let pieces: Vec<&str> = if stretch > 0.0 { visual.split_inclusive(' ').collect() } else { vec![visual.as_str()] }; + for piece in pieces { + self.show_piece(piece, line, tw, cursor, ops)?; + if stretch > 0.0 && piece.ends_with(' ') { + ops.push(Op::new("TJ", vec![Object::Array(vec![n(-1000.0 * stretch / self.size)])])); + } + } + let tw = tw + stretch; + // Underlined to the line's last word, over its stretched gaps. + let w = (visible + tw * interior as f64 * self.scale * self.k) / self.k; + Ok((dx, dx + w, -(index as f64) * self.lead - self.size * 0.12)) + } + + fn show_piece(&self, piece: &str, line: &str, tw: f64, cursor: &mut LineCursor, ops: &mut Vec) -> Result<(), EditError> { + let n = pdfcraft_content::num; + if let Some(metrics) = self.source { + let indic_piece = if metrics.visual_order { crate::indic::to_visual(piece) } else { piece.to_owned() }; + ops.extend(source_show(metrics, &indic_piece, self.size, self.space, self.char_spacing, tw)?); + return Ok(()); + } + for (font, bytes) in (self.encode)(piece).ok_or_else(|| EditError::Invalid(format!("\"{line}\" can't be shown")))? { + if font != cursor.shown_font { + ops.push(Op::new("Tf", vec![Object::name(&font), n(self.size)])); + cursor.shown_font = font; + } + ops.push(Op::new("Tj", vec![Object::String(PdfString::literal(bytes))])); + } + Ok(()) + } + + /// Writes every wrapped line, returning their underlines. + fn write_all(&self, wrapped: &[String], cursor: &mut LineCursor, ops: &mut Vec) -> Result, EditError> { + wrapped.iter().enumerate().map(|(i, line)| self.write_line(i, line, i + 1 == wrapped.len(), cursor, ops)).collect() + } +} + +/// The operators that write a paragraph in its own graphics state, so a new colour (or anything +/// else) stops at the paragraph. +struct BlockPlan<'a> { + block: &'a TextBlock, + lines: &'a [TextLine], + style: &'a BlockStyle, + emit: &'a Origin, + after: &'a TextState, + movement: Option<(f64, f64)>, + state: TextState, + tm: [f64; 6], + size: f64, + underline: bool, +} + +fn block_ops(plan: &BlockPlan<'_>, writer: &LineWriter<'_>, wrapped: &[String], show_font: String) -> Result, EditError> { + let n = pdfcraft_content::num; + let mut ops = vec![Op::new("q", vec![])]; + ops.extend(reveal_ops(plan.block, plan.lines, plan.style, plan.emit.ctm)?); + // Moved: a translation inside that state. + if let Some((ax, ay)) = plan.movement { + ops.push(Op::new("cm", vec![n(1.0), n(0.0), n(0.0), n(1.0), n(ax), n(ay)])); + } + // Painted as the paragraph was, including what its text object set before the first show. + ops.extend(plan.state.paint_ops(plan.after)); + ops.push(Op::new("BT", vec![])); + let mut state = plan.state.clone(); + state.word_spacing = 0.0; + // The font the next run is shown in: the one the BT sets, until a run of another fallback subset. + let mut cursor = LineCursor { x: 0.0, tw_set: 0.0, shown_font: show_font.clone() }; + state.font = Some((show_font, plan.size)); + if let Some([r, g, bl]) = plan.style.color { + state.fill = vec![Op::new("rg", vec![n(r), n(g), n(bl)])]; + } + ops.extend(state.ops()); + ops.push(Op::new("Tm", plan.tm.iter().map(|v| n(*v)).collect())); + let underlines = writer.write_all(wrapped, &mut cursor, &mut ops)?; + ops.push(Op::new("ET", vec![])); + if plan.underline { + ops.extend(underline_ops(&state.fill, &plan.tm, plan.size, &underlines)); + } + ops.push(Op::new("Q", vec![])); + Ok(ops) +} + +/// Whether text shown earlier in the same text object stays first: the paragraph then goes where +/// its last row was, after any backgrounds between the rows, or between two halves of the text +/// object. The paragraph's own operators (and another drawing on the same baseline: a fake-bold +/// second copy, an invisible text layer) go, so the new text is all that may show. +fn shows_before_paragraph(ops: &[Op], from: usize, to: usize, dropped: &std::collections::HashSet) -> bool { + ops.get(from..to) + .unwrap_or_default() + .iter() + .enumerate() + .any(|(i, op)| matches!(op.op.as_slice(), b"Tj" | b"TJ" | b"'" | b"\"") && !dropped.contains(&(from + i))) +} + +/// A paragraph's single style, with the text-space values read from where it starts. +struct ParaStyle { + state: TextState, + size: f64, + old_size: f64, + k: f64, +} + +/// Spacing and scaling (text state), with the chosen values. +fn paragraph_style(o: &Origin, style: &BlockStyle) -> Result<(String, ParaStyle), EditError> { + let (font_name, old_size) = o.state.font.clone().ok_or_else(|| EditError::Invalid("the paragraph has no font".into()))?; + let k = o.k.max(1e-6); + // The size in text space: points ÷ the text-to-user scale. + let size = style.size.map_or(old_size, |pt| (pt / k).max(0.1)); + let mut state = o.state.clone(); + if let Some(c) = style.char_spacing { + state.char_spacing = c / k; + } + if let Some(sc) = style.scale { + state.scale = (sc / 100.0).clamp(0.1, 10.0); + } + Ok((font_name, ParaStyle { state, size, old_size, k })) +} + +/// The font the paragraph's existing runs use, for reusing its glyphs. +struct SourceFont { + metrics: Option, + reuse: bool, + space: f64, +} + +fn source_font(doc: &Document, fonts_res: &Dict, font_name: &str, first: &TextLine, flat: &str, style: &BlockStyle) -> SourceFont { + let metrics = fonts_res.get(font_name.as_bytes()).and_then(|f| doc.resolve(f).as_dict().cloned()).map(|d| Metrics::from_dict(doc, &d)); + let visual_indic = metrics.as_ref().is_some_and(|m| m.visual_order) || first.visual_order; + let indic_text = if visual_indic { crate::indic::to_visual(flat) } else { flat.to_owned() }; + let reuse = style.family.is_none() && style.bold.is_none() && metrics.as_ref().is_some_and(|m| source_encodes(m, &indic_text)); + let space = metrics.as_ref().map_or(0.33, |m| source_space(doc, fonts_res, m)); + SourceFont { metrics, reuse, space } +} + /// [`rewrite_block_with_limit`] with the page's [`text_lines`], read from `doc` as it is now. pub(crate) fn rewrite_block_from( doc: &mut Document, @@ -228,86 +757,26 @@ pub(crate) fn rewrite_block_from( let p = page_dict(doc, page)?; let mut res = p.dict.get(b"Resources").map(|r| doc.resolve(r)).and_then(|r| r.as_dict().cloned()).unwrap_or_default(); let mut fonts_res = res.get(b"Font").map(|f| doc.resolve(f)).and_then(|f| f.as_dict().cloned()).unwrap_or_default(); - let registered_face = fonts_res.iter().any(|(name, _)| name.starts_with(b"PCFull")); - // Hebrew is written back in drawing order (and with the Hebrew fallback face) by the - // single-style path below; the styled region path does not reorder right-to-left runs. - let hebrew = text.unwrap_or(&b.text).chars().any(crate::bidi::is_hebrew); - if hebrew && (!style.ranges.is_empty() || style.resource.is_some()) { - return Err(EditError::Invalid( - "formatting part of right-to-left (Hebrew) text, or choosing a document font for it, isn't supported yet".into(), - )); - } - // Text turned on the page (a landscape page drawn a quarter turn round) is rewritten in its - // own text space below; the styled region path lays rows out along the page's x axis. - let upright = members.iter().all(|line| line.upright()); - if !upright && (!style.ranges.is_empty() || style.resource.is_some()) { - return Err(EditError::Invalid("formatting part of turned text, or choosing a document font for it, isn't supported yet".into())); - } - let visual_indic = members.iter().any(|line| line.visual_order); - if upright - && !hebrew - && !visual_indic - && (!style.ranges.is_empty() - || style.resource.is_some() - || (text.is_some_and(|draft| { - // A row break, `\n` or a carriage return, takes the path that keeps untouched rows. - draft.contains(['\n', '\r']) - || pdfcraft_fonts::source_shaping::required(draft) - || !pdfcraft_fonts::embedding::matching_faces(&b.base_font).is_empty() - }) || registered_face - || text.is_some_and(|draft| source_program_completes(doc, &fonts_res, first, draft)) - || b.rows.iter().any(|row| row.len() > 1) - || members.iter().any(|line| line.font != first.font || line.size != first.size || line.color != first.color)) - && style.family.is_none() - && style.bold.is_none()) - { + let dispatch = choose_rewrite_path(doc, &fonts_res, &b, &members, first, text, style)?; + if dispatch.use_styled_path { return rewrite_styled_block(doc, page, &b, &lines, text, style, max_glyphs); } + let upright = dispatch.upright; let streams = content_streams(doc, &p.dict)?; let pieces = Pieces::join(&streams.iter().map(|(_, d)| d.as_slice()).collect::>()); let ops = pieces.parse().ops; - // Explicit line breaks stay (#1443), and so does each typed U+0020 space: a run of them is - // not folded into one (#4199, #3797). `\r\n` and a lone `\r` are breaks too; other white - // space is written as one space. - let text: String = text - .unwrap_or(&b.text) - .replace("\r\n", "\n") - .chars() - .map(|c| match c { - '\r' => '\n', - c if c != '\n' && paragraph_separator(c) => ' ', - c => c, - }) - .collect(); + let text = paragraph_text(text.unwrap_or(&b.text)); // The characters to show, for choosing fonts: the breaks are moves, not glyphs. let flat = text.replace('\n', " "); let o = &first.origin; let last = members.last().copied().unwrap_or(first); let emit = &last.origin; - let (font_name, old_size) = o.state.font.clone().ok_or_else(|| EditError::Invalid("the paragraph has no font".into()))?; - let k = o.k.max(1e-6); - // The size in text space: points ÷ the text-to-user scale. - let size = style.size.map_or(old_size, |pt| (pt / k).max(0.1)); - // Spacing and scaling (text state), with the chosen values. - let mut ts_state = o.state.clone(); - if let Some(c) = style.char_spacing { - ts_state.char_spacing = c / k; - } - if let Some(sc) = style.scale { - ts_state.scale = (sc / 100.0).clamp(0.1, 10.0); - } - let o_state = ts_state.clone(); - let metrics = fonts_res.get(font_name.as_bytes()).and_then(|f| doc.resolve(f).as_dict().cloned()).map(|d| Metrics::from_dict(doc, &d)); - let visual_indic = metrics.as_ref().is_some_and(|m| m.visual_order) || first.visual_order; - let indic_text = if visual_indic { crate::indic::to_visual(&flat) } else { flat.clone() }; - let reuse = style.family.is_none() && style.bold.is_none() && metrics.as_ref().is_some_and(|m| source_encodes(m, &indic_text)); - let space = metrics.as_ref().map_or(0.33, |m| source_space(doc, &fonts_res, m)); + let (font_name, ParaStyle { state: o_state, size, old_size, k }) = paragraph_style(o, style)?; + let source = source_font(doc, &fonts_res, &font_name, first, &flat, style); + let reuse = source.reuse; // The chosen style also determines the real Japanese fallback outlines and advances. let (family, bold, italic) = style.family.unwrap_or((source_family(&b.base_font), b.bold, b.italic)); let bold = style.bold.unwrap_or(bold); - // The face is chosen after `bold` settles, so a bold request measures with the bold metrics. - let face = family.std14(bold, italic); - let std_width = move |s: &str, size: f64| -> f64 { face.text_width(s, size) }; let [dx, dy] = style.offset.unwrap_or([0.0, 0.0]); if !(dx.is_finite() && dy.is_finite()) { return Err(EditError::Invalid("the paragraph can't be moved that far".into())); @@ -327,287 +796,79 @@ pub(crate) fn rewrite_block_from( // Turned text is left alone: its centre lives along its own baseline, not in page space. let crop = p.crop(doc); let centred = upright && !rtl && style.width.is_none() && style.align.is_none() && is_centred(&b, &lines, (crop[0] + crop[2]) / 2.0, first.size); - // A paragraph keeps its width (or takes the one asked for); a single line grows to the right - // (to the left when right-to-left), up to the page's margin. - let width = match style.width { - // Capped at the largest page PDF allows (14 400 pt), even for text set larger than that - // (`clamp` panics when its minimum is the larger, or NaN). - Some(w) if w.is_finite() => w.clamp((size * k).min(14_400.0), 14_400.0), - Some(_) => return Err(EditError::Invalid("the paragraph's width must be a number".into())), - // Turned text: the page's margins are along another axis. A single line grows (below). - None if !upright => (frame[2] - frame[0]).max(size * k), - None if anchored_right => (b.rect[2] - b.rect[0]).max(size * k).max(b.rect[2] + dx - (crop[0] + 36.0)), - // A centred line is not stretched to the margin: its own box is the frame it is centred in. - None if members.len() == 1 && !centred => (b.rect[2] - b.rect[0]).max(size * k).max(crop[2] - 36.0 - (b.rect[0] + dx)), - None => (b.rect[2] - b.rect[0]).max(size * k), - }; - if !width.is_finite() { - return Err(EditError::Invalid("the paragraph's width must be a number".into())); - } + let geometry = ParaGeometry { rect: b.rect, frame, crop, upright, k, size, dx, single_line: members.len() == 1, anchored_right, centred }; + let width = geometry.width(style.width)?; let align = if centred { Some(crate::added::Align::Center) } else { style.align.or(rtl.then_some(crate::added::Align::Right)) }; // Where a right-aligned line ends, from the paragraph's left edge (user space). let right_edge = if anchored_right { (b.rect[2] - b.rect[0]).max(0.0) } else { width }; - // The move and the width are checked here, before the fallback fonts are written: a refused - // paragraph leaves the document as it was. The move is in page space, so it is taken back through - // the CTM's linear part into the space the paragraph is drawn in. - let movement = if dx != 0.0 || dy != 0.0 { - let c = emit.ctm; - let back = Matrix([c[0], c[1], c[2], c[3], 0.0, 0.0]) - .invert() - .ok_or_else(|| EditError::Invalid("the paragraph is drawn in a space it can't be moved in".into()))?; - Some(back.apply(dx, dy)) - } else { - None - }; - let tm = if o.ctm == emit.ctm { - o.tm - } else { - let emit_inv = Matrix(emit.ctm).invert().ok_or_else(|| EditError::Invalid("the paragraph has a singular transform".into()))?; - Matrix(o.tm).then(&Matrix(o.ctm)).then(&emit_inv).0 - }; + let movement = drawn_movement(emit.ctm, dx, dy)?; + let tm = emit_text_matrix(o, emit)?; let type3 = if !reuse && needs_type3(&flat) { Some(type3_font(doc, &mut fonts_res, &flat, family, bold, max_glyphs)?) } else { None }; - let advance = |s: &str| -> f64 { - let t = match (&metrics, reuse) { - (Some(m), true) => { - let visual_s = if m.visual_order { crate::indic::to_visual(s) } else { s.to_owned() }; - source_width(m, &visual_s, size, space, o_state.char_spacing, o_state.word_spacing) - } - _ if let Some(fallback) = &type3 => { - // Each character's count in `s`, from one pass over `s`. - let mut counts: HashMap = HashMap::new(); - for c in s.chars() { - let count = counts.entry(c).or_insert(0); - *count = count.saturating_add(1); - } - fallback.widths.iter().map(|(ch, width)| counts.get(ch).copied().unwrap_or(0) as f64 * width * size).sum::() - + s.chars().count() as f64 * o_state.char_spacing - } - _ => std_width(s, size) + s.chars().count() as f64 * o_state.char_spacing, - }; - t * o_state.scale * k + let source_metrics = source.metrics.as_ref().filter(|_| reuse); + let advance = Advance { + source: source_metrics, + type3: type3.as_ref(), + family, + bold, + italic, + size, + space: source.space, + char_spacing: o_state.char_spacing, + word_spacing: o_state.word_spacing, + scale: o_state.scale, + k, }; - // A turned single line grows to fit, up to where its baseline reaches the page's margin. let width = if !upright && style.width.is_none() && members.len() == 1 { - let crop = p.crop(doc); - let (x0, y0) = (first.origin.x + dx, first.origin.baseline + dy); - let (ux, uy) = first.direction(); - let tx = if ux > 1e-6 { - (crop[2] - 36.0 - x0) / ux - } else if ux < -1e-6 { - (crop[0] + 36.0 - x0) / ux - } else { - f64::INFINITY - }; - let ty = if uy > 1e-6 { - (crop[3] - 36.0 - y0) / uy - } else if uy < -1e-6 { - (crop[1] + 36.0 - y0) / uy - } else { - f64::INFINITY - }; - let cap = width.max(tx.min(ty)).min(14_400.0); - text.split('\n').map(&advance).fold(width, f64::max).min(cap) + turned_line_width(first, crop, [dx, dy], width, &text, &advance) } else { width }; let right_edge = if anchored_right { right_edge } else { width }; - let wrapped = wrap(&text, width + 0.5, advance); - let mut substituted = None; - let new_font = !reuse; - let (show_font, encode): (String, Encoder) = if let Some(m) = metrics.clone().filter(|_| reuse) { - let name = font_name.clone(); - (font_name.clone(), Box::new(move |s: &str| m.encode(s).map(|bytes| vec![(name.clone(), bytes)]))) - } else if let Some(fallback) = type3.clone() { - substituted = Some(format!("{} Type3", fallback.family)); - let first = fallback.names.first().cloned().ok_or_else(no_japanese_font)?; - (first, Box::new(move |s: &str| type3_encode(&fallback, s))) - } else { - let win = pdfcraft_fonts::win_ansi(&flat); - let back: String = win.iter().map(|c| char::from_u32(u32::from(*c)).unwrap_or('?')).collect(); - let base = family.base_font(bold, italic); - if flat.chars().zip(back.chars()).any(|(a, c)| c == '?' && a != '?') { - return Err(EditError::Invalid(format!("\"{flat}\" has characters neither {} nor {base} can show", b.base_font))); - } - let mut f = Dict::new(); - f.set(b"Type".to_vec(), Object::name("Font")); - f.set(b"Subtype".to_vec(), Object::name("Type1")); - f.set(b"BaseFont".to_vec(), Object::name(base)); - f.set(b"Encoding".to_vec(), Object::name("WinAnsiEncoding")); - // Named after its face, as the line and region rewrites name theirs: one name for every - // stand-in would repoint the paragraphs set in an earlier one at this face (#4280). - let name = format!("PCEd{}", base.replace('-', "")); - fonts_res.set(name.clone().into_bytes(), Object::Dict(f)); - if style.family.is_none() { - substituted = Some(base.to_string()); - } - let shown = name.clone(); - (name, Box::new(move |s: &str| Some(vec![(shown.clone(), pdfcraft_fonts::win_ansi(s))]))) - }; - // Line spacing in text space: the paragraph's own (scaled with the size), or 1.2 × the size. - let lead = match style.line_spacing { - Some(m) => size * m.clamp(0.5, 5.0), - // From the first two rows (a row may hold several runs). - None if let Some((upper, lower)) = b - .rows - .first() - .zip(b.rows.get(1)) - .and_then(|(upper, lower)| upper.first().zip(lower.first())) - .and_then(|(upper, lower)| lines.get(*upper).zip(lines.get(*lower))) => - { - (upper.frame_origin().1 - lower.frame_origin().1) / k * size / old_size - } - None if o_state.leading > 0.0 => o_state.leading, - None => size * 1.2, - }; - let n = pdfcraft_content::num; - // The paragraph's operators go, and so does another drawing on the same baseline (a fake-bold - // second copy, an invisible text layer): the new text is all that may show. - let drop = dropped; - // Text shown earlier in the same text object stays first: the paragraph then goes where its - // last row was, after any backgrounds between the rows, or between two halves of the text object. + let wrapped = wrap(&text, width + 0.5, |s| advance.of(s)); + let font = choose_font( + &FontInputs { + source: source_metrics, + type3: type3.as_ref(), + font_name: &font_name, + flat: &flat, + source_base_font: &b.base_font, + family, + bold, + italic, + family_requested: style.family.is_some(), + }, + &mut fonts_res, + )?; + let lead = line_lead(&b, &lines, style, &LeadScale { k, size, old_size, leading: o_state.leading }); let start = last.ops.first().copied().unwrap_or(emit.bt_op); - let split = ops - .get(emit.bt_op..start) - .unwrap_or_default() - .iter() - .enumerate() - .any(|(i, op)| matches!(op.op.as_slice(), b"Tj" | b"TJ" | b"'" | b"\"") && !drop.contains(&(emit.bt_op + i))); + let split = shows_before_paragraph(&ops, emit.bt_op, start, &dropped); // What the text after the paragraph expects, and what is in force where the paragraph is // drawn: the state at its BT (or where it was split). let after = if split { &emit.state } else { &emit.bt_state }; - // In its own graphics state, so a new colour (or anything else) stops at the paragraph. - let mut block_ops = vec![Op::new("q", vec![])]; - block_ops.extend(reveal_ops(&b, &lines, style, emit.ctm)?); - // Moved: a translation inside that state. - if let Some((ax, ay)) = movement { - block_ops.push(Op::new("cm", vec![n(1.0), n(0.0), n(0.0), n(1.0), n(ax), n(ay)])); - } - // Painted as the paragraph was, including what its text object set before the first show. - block_ops.extend(o_state.paint_ops(after)); - block_ops.push(Op::new("BT", vec![])); - let mut state = o_state.clone(); - state.word_spacing = 0.0; - // The font the next run is shown in: the one the BT sets, until a run of another fallback subset. - let mut shown_font = show_font.clone(); - state.font = Some((show_font, size)); - if let Some([r, g, bl]) = style.color { - state.fill = vec![Op::new("rg", vec![n(r), n(g), n(bl)])]; - } - block_ops.extend(state.ops()); - block_ops.push(Op::new("Tm", tm.iter().map(|v| n(*v)).collect())); - // Alignment: each line's offset from the left edge, in text space. - // `visible` is the width the line is aligned on (see the loop below). - let offset = |visible: f64| -> f64 { - let free = (width - visible).max(0.0) / k; - match align { - Some(crate::added::Align::Center) => free / 2.0, - // A right-to-left line anchored at its right edge may start left of the old box. - Some(crate::added::Align::Right) if anchored_right => (right_edge - visible) / k, - Some(crate::added::Align::Right) => free, - // A justified right-to-left paragraph ends its last line at the right edge. - Some(crate::added::Align::Justify) if rtl => free, - _ => 0.0, - } - }; - // Justify: each line but the last fills the width. Word spacing reaches only single-byte code 32 - // (ISO 32000-1 §9.3.3), so where a space is shown with another code (a composite font, a - // generated Type 3 font, a subset without a space) the extra space follows each space as a - // TJ adjustment instead, and code 32, which may then be a letter, gets none. - let justify = align == Some(crate::added::Align::Justify); - let word_spacing_reaches_spaces = match metrics.as_ref().filter(|_| reuse) { + // Word spacing reaches only single-byte code 32 (ISO 32000-1 §9.3.3); see `write_line`. + let word_spacing_reaches_spaces = match source_metrics { Some(m) => m.encode(" ").is_some_and(|b| m.codes(&b).iter().all(|(c, len)| m.is_space(*c, *len))), None => type3.is_none(), }; - let mut x = 0.0; - let mut tw_set = 0.0; - let mut underlines: Vec<(f64, f64, f64)> = Vec::new(); // (x0, x1, y) in text space - for (i, line) in wrapped.iter().enumerate() { - // A stretched (justified) line shows only its words, as before #4199: word spacing would - // reach the spaces before its first word and after its last, so they are left out, and - // the line fills the width from the left edge. Nothing to stretch over, or a paragraph - // drawn at `0 Tz`, isn't justified. - let body = line.trim_matches(' '); - let interior = body.matches(' ').count(); - let tw = if justify && i + 1 < wrapped.len() && interior > 0 && o_state.scale.abs() > 1e-6 { - Some((width - advance(body)).max(0.0) / k / o_state.scale / interior as f64).filter(|tw| tw.is_finite()) - } else { - None - } - .unwrap_or(0.0); - // Other lines show every space typed. A left-to-right one is aligned on its width up to - // its last word; a right-to-left one on its whole width, since the spaces typed after its - // last word are drawn on its left and the ones before its first on its right. - let (shown, visible) = if tw > 0.0 { - (body, advance(body)) - } else if crate::bidi::rtl_base(line) { - (line.as_str(), advance(line)) - } else { - (line.as_str(), advance(line.trim_end_matches(' '))) - }; - let dx = if tw > 0.0 { 0.0 } else { offset(visible) }; - if i > 0 || dx != 0.0 { - block_ops.push(Op::new("Td", vec![n(dx - x), n(if i > 0 { -lead } else { 0.0 })])); - } - x = dx; - let stretch = if word_spacing_reaches_spaces { 0.0 } else { tw }; - let tw = tw - stretch; - if tw != tw_set { - block_ops.push(Op::new("Tw", vec![n(tw)])); - tw_set = tw; - } - // Each wrapped line in typing order; drawn left to right (right-to-left runs reversed). - let visual = crate::bidi::to_visual(shown); - // Stretched without word spacing: shown up to and including each space, then moved on. - let pieces = if stretch > 0.0 { visual.split_inclusive(' ').collect() } else { vec![visual.as_str()] }; - for piece in pieces { - if let Some(metrics) = metrics.as_ref().filter(|_| reuse) { - let indic_piece = if metrics.visual_order { crate::indic::to_visual(piece) } else { piece.to_owned() }; - block_ops.extend(source_show(metrics, &indic_piece, size, space, o_state.char_spacing, tw)?); - } else { - for (font, bytes) in encode(piece).ok_or_else(|| EditError::Invalid(format!("\"{line}\" can't be shown")))? { - if font != shown_font { - block_ops.push(Op::new("Tf", vec![Object::name(&font), n(size)])); - shown_font = font; - } - block_ops.push(Op::new("Tj", vec![Object::String(PdfString::literal(bytes))])); - } - } - if stretch > 0.0 && piece.ends_with(' ') { - block_ops.push(Op::new("TJ", vec![Object::Array(vec![n(-1000.0 * stretch / size)])])); - } - } - let tw = tw + stretch; - // Underlined to the line's last word, over its stretched gaps. - let w = (visible + tw * interior as f64 * o_state.scale * k) / k; - underlines.push((dx, dx + w, -(i as f64) * lead - size * 0.12)); - } - block_ops.push(Op::new("ET", vec![])); - if style.underline == Some(true) { - // In text space (the paragraph's text matrix), in its fill colour. - let colour: Vec = state - .fill - .iter() - .map(|f| match f.op.as_slice() { - b"g" => Op::new("G", f.operands.clone()), - b"rg" => Op::new("RG", f.operands.clone()), - b"k" => Op::new("K", f.operands.clone()), - b"cs" => Op::new("CS", f.operands.clone()), - b"sc" => Op::new("SC", f.operands.clone()), - _ => Op::new("SCN", f.operands.clone()), - }) - .collect(); - block_ops.push(Op::new("q", vec![])); - block_ops.push(Op::new("cm", tm.iter().map(|v| n(*v)).collect())); - block_ops.extend(colour); - block_ops.push(Op::new("w", vec![n(size * 0.06)])); - for (x0, x1, y) in underlines { - block_ops.push(Op::new("m", vec![n(x0), n(y)])); - block_ops.push(Op::new("l", vec![n(x1), n(y)])); - } - block_ops.push(Op::new("S", vec![])); - block_ops.push(Op::new("Q", vec![])); - } - block_ops.push(Op::new("Q", vec![])); + let writer = LineWriter { + advance: &advance, + alignment: Alignment { align, width, k, anchored_right, right_edge, rtl }, + encode: &font.encode, + source: source_metrics, + justify: align == Some(crate::added::Align::Justify), + word_spacing_reaches_spaces, + width, + scale: o_state.scale, + k, + size, + space: source.space, + char_spacing: o_state.char_spacing, + lead, + }; + let plan = + BlockPlan { block: &b, lines: &lines, style, emit, after, movement, state: o_state, tm, size, underline: style.underline == Some(true) }; + let mut block_ops = block_ops(&plan, &writer, &wrapped, font.show_font.clone())?; + let n = pdfcraft_content::num; block_ops.extend(after.ops().into_iter().filter(|op| !op.is("Tf") || after.font.is_some())); if split { block_ops.insert(0, Op::new("ET", vec![])); @@ -617,9 +878,10 @@ pub(crate) fn rewrite_block_from( let at = if split { start } else { emit.bt_op }; let new_data = splice(&pieces, &ops, |i| { let insert = if i == at { std::mem::take(&mut block_ops) } else { Vec::new() }; - (insert, !drop.contains(&i)) + (insert, !dropped.contains(&i)) }); let contents = rewritten_contents(doc, &streams, new_data); + let new_font = !reuse; if new_font { res.set(b"Font".to_vec(), Object::Dict(fonts_res)); } @@ -630,7 +892,7 @@ pub(crate) fn rewrite_block_from( d.set(b"Resources".to_vec(), Object::Dict(res)); } })?; - Ok(LineEdit { substituted }) + Ok(LineEdit { substituted: font.substituted }) } /// The cover (when [`BlockStyle::cover`] asks for one) and visible rendering that start a diff --git a/crates/edit/src/text_regions.rs b/crates/edit/src/text_regions.rs index 7516cb793b..be5b4dffa6 100644 --- a/crates/edit/src/text_regions.rs +++ b/crates/edit/src/text_regions.rs @@ -1,6 +1,11 @@ //! Geometry-based regions and mixed-style rewriting of existing text. -use super::*; +use super::{ + BlockStyle, CraftFont, Dict, Document, EditError, HashMap, LineEdit, MAX_TYPE3_GLYPHS, Matrix, Metrics, Object, Op, PdfString, Pieces, + RangeStyle, TextBlock, TextLine, Type3Glyph, coincident_ops, content_streams, fallback_face, japanese_glyph_from, needs_type3, no_fallback_font, + no_glyph_for, page_dict, paragraph_separator, reveal_ops, rewritten_contents, same_base_font, same_font, source_encodes, source_family, + source_program, source_show, source_space, source_width, splice, strip_subset_tag, type3_faces, type3_glyph, union, write_type3_glyphs, +}; #[path = "text_regions/grouping.rs"] mod grouping; diff --git a/crates/edit/src/text_regions/grouping.rs b/crates/edit/src/text_regions/grouping.rs index 29004b8e33..b8a5abca1e 100644 --- a/crates/edit/src/text_regions/grouping.rs +++ b/crates/edit/src/text_regions/grouping.rs @@ -1,4 +1,4 @@ -use super::*; +use super::{HashMap, Matrix, TextBlock, TextLine, paragraph_separator, same_base_font, same_font, strip_subset_tag, union}; fn same_plane(a: &TextLine, b: &TextLine) -> bool { let at = Matrix(a.origin.tm).then(&Matrix(a.origin.ctm)); diff --git a/crates/edit/src/text_regions/styled.rs b/crates/edit/src/text_regions/styled.rs index 09baf1ac7e..e8b3b683d0 100644 --- a/crates/edit/src/text_regions/styled.rs +++ b/crates/edit/src/text_regions/styled.rs @@ -1,5 +1,10 @@ use super::grouping::{across, is_centred, row_rect}; -use super::*; +use super::{ + BlockStyle, CraftFont, Dict, Document, EditError, HashMap, LineEdit, MAX_TYPE3_GLYPHS, Matrix, Metrics, Object, Op, PdfString, Pieces, + RangeStyle, TextBlock, TextLine, Type3Glyph, coincident_ops, content_streams, fallback_face, japanese_glyph_from, needs_type3, no_fallback_font, + no_glyph_for, page_dict, reveal_ops, rewritten_contents, source_encodes, source_family, source_program, source_show, source_space, source_width, + splice, type3_faces, type3_glyph, write_type3_glyphs, +}; // The draft is capped at 4 MiB; also bound the outline data prepared across all fallback faces. // A glyph budget worth 64 full batches (15,360 glyphs with the production batch size). @@ -13,6 +18,526 @@ struct FallbackGroup { positions: Vec, } +struct FallbackBuilder { + groups: Vec, + names: std::collections::BTreeMap<(String, bool, char), usize>, + glyphs: usize, + per_font: usize, + budget: usize, +} + +struct FontResolver<'a> { + doc: &'a mut Document, + fonts: &'a mut Dict, + metrics: &'a mut std::collections::BTreeMap, + full_faces: HashMap, + programs: HashMap>>>, +} + +impl FontResolver<'_> { + fn encodable_font(&mut self, source: &TextLine, text: &str, requested: Option<&str>) -> Result, EditError> { + if let Some(resource) = requested { + if !self.metrics.get(resource).is_some_and(|metrics| source_encodes(metrics, text)) { + return Err(EditError::Invalid(format!( + "the selected font resource {resource} cannot show U+{:04X}", + text.chars().next().map_or(0, u32::from) + ))); + } + return Ok(Some(resource.to_owned())); + } + if self.metrics.get(&source.font).is_some_and(|metrics| source_encodes(metrics, text)) { + return Ok(Some(source.font.clone())); + } + if let Some((name, _)) = self.metrics.iter().find(|(_, metrics)| { + pdfcraft_fonts::embedding::face_key(&metrics.base_font) == pdfcraft_fonts::embedding::face_key(&source.base_font) + && source_encodes(metrics, text) + }) { + return Ok(Some(name.clone())); + } + if let Some(face) = + pdfcraft_fonts::embedding::matching_faces(&source.base_font).into_iter().find(|face| pdfcraft_fonts::embedding::covers(face.bytes, text)) + { + return self.embed_face(face.name(), face.bytes, face.family, "the full source font could not be loaded").map(Some); + } + let Some(bytes) = self + .programs + .entry(source.font.clone()) + .or_insert_with(|| source_program(self.doc, self.fonts, &source.font).map(std::sync::Arc::new)) + .clone() + .filter(|bytes| pdfcraft_fonts::embedding::covers(bytes, text)) + else { + return Ok(None); + }; + let key = format!("source {}", source.font); + if let Some(name) = self.full_faces.get(&key) { + return Ok(Some(name.clone())); + } + let family = pdfcraft_fonts::embedding::names(&bytes).map_or_else(|_| source.base_font.clone(), |(family, _)| family); + self.embed_face(key, &bytes, &family, "the source font could not be loaded").map(Some) + } + + fn embed_face(&mut self, key: String, bytes: &[u8], family: &str, missing_message: &str) -> Result { + if let Some(name) = self.full_faces.get(&key) { + return Ok(name.clone()); + } + let name = pdfcraft_fonts::embedding::embed(self.doc, self.fonts, bytes, family).map_err(EditError::Invalid)?; + let font = + self.fonts.get(name.as_bytes()).and_then(|resource| self.doc.dict(resource)).ok_or_else(|| EditError::Invalid(missing_message.into()))?; + self.metrics.insert(name.clone(), Metrics::from_dict(self.doc, &font)); + self.full_faces.insert(key, name.clone()); + Ok(name) + } + + fn substitute_font(&mut self, source: &TextLine) -> String { + let family = source_family(&source.base_font); + let base = family.base_font(source.bold, source.italic); + let name = format!("PCEd{}", base.replace('-', "")); + let mut font = Dict::new(); + font.set(b"Type".to_vec(), Object::name("Font")); + font.set(b"Subtype".to_vec(), Object::name("Type1")); + font.set(b"BaseFont".to_vec(), Object::name(base)); + font.set(b"Encoding".to_vec(), Object::name("WinAnsiEncoding")); + self.metrics.entry(name.clone()).or_insert_with(|| Metrics::from_dict(self.doc, &font)); + self.fonts.set(name.clone().into_bytes(), Object::Dict(font)); + name + } +} + +struct PreparedCharacters { + values: Vec, + substituted: Option, +} + +struct CharacterPreparation<'a> { + doc: &'a mut Document, + first: &'a TextLine, + lines: &'a [TextLine], + draft: &'a str, + spans: Vec<(std::ops::Range, usize)>, + style: &'a BlockStyle, + overrides: &'a HashMap, + fonts: &'a mut Dict, + metrics: &'a mut std::collections::BTreeMap, + max_glyphs: usize, +} + +impl CharacterPreparation<'_> { + fn prepare(self) -> Result { + let Self { doc, first, lines, draft, spans, style, overrides, fonts, metrics, max_glyphs } = self; + let mut chars = Vec::new(); + let mut substituted = None; + let mut fallback = FallbackBuilder::new(max_glyphs); + let mut resolver = FontResolver { doc, fonts, metrics, full_faces: HashMap::new(), programs: HashMap::new() }; + for (range, index) in spans { + let source = lines.get(index).unwrap_or(first); + let start = range.start; + for (offset, ch) in draft.get(range).unwrap_or_default().char_indices() { + if ch == '\n' { + chars.push((ch, index, source.font.clone())); + continue; + } + if ch == '\r' { + let crlf = start.checked_add(offset).and_then(|at| draft.get(at.saturating_add(1)..)).is_some_and(|rest| rest.starts_with('\n')); + chars.push((if crlf { '\r' } else { '\n' }, index, source.font.clone())); + continue; + } + let text = ch.to_string(); + let requested = overrides.get(&index).and_then(|range| range.resource.as_deref()).or(style.resource.as_deref()); + let name = if let Some(name) = resolver.encodable_font(source, &text, requested)? { + name + } else if needs_type3(&text) { + fallback.prepare(source, ch, &text, chars.len())? + } else { + let name = resolver.substitute_font(source); + substituted = Some(source_family(&source.base_font).base_font(source.bold, source.italic).to_owned()); + name + }; + chars.push((ch, index, name)); + } + } + drop(resolver); + for group in fallback.groups { + let written = write_type3_glyphs(doc, fonts, group.face, false, group.glyphs, fallback.per_font); + for name in &written.names { + let font = fonts + .get(name.as_bytes()) + .and_then(|resource| doc.dict(resource)) + .ok_or_else(|| EditError::Invalid("the fallback font could not be loaded".into()))?; + metrics.insert(name.clone(), Metrics::from_dict(doc, &font)); + } + for position in group.positions { + let item = chars.get_mut(position).ok_or_else(|| EditError::Invalid("the fallback character is missing".into()))?; + let (font, _) = written.codes.get(&item.0).ok_or_else(|| EditError::Invalid("the fallback glyph is missing".into()))?; + item.2 = written.names.get(*font).cloned().ok_or_else(|| EditError::Invalid("the fallback font is missing".into()))?; + } + substituted = Some(written.family.to_owned()); + } + Ok(PreparedCharacters { values: chars, substituted }) + } +} + +impl FallbackBuilder { + fn new(max_glyphs: usize) -> Self { + let per_font = max_glyphs.clamp(1, MAX_TYPE3_GLYPHS); + Self { + groups: Vec::new(), + names: std::collections::BTreeMap::new(), + glyphs: 0, + per_font, + budget: per_font.saturating_mul(MAX_STYLED_FALLBACK_BATCHES), + } + } + + fn prepare(&mut self, source: &TextLine, ch: char, text: &str, position: usize) -> Result { + let key = (source.base_font.clone(), source.bold, ch); + let group_index = if let Some(index) = self.names.get(&key) { + *index + } else { + let (faces, _) = type3_faces(text, source_family(&source.base_font), source.bold)?; + let face = fallback_face(&faces, &[ch], |face, ch| japanese_glyph_from(face, ch).is_ok()).ok_or_else(|| no_fallback_font(text))?; + let index = self.groups.iter().position(|group| std::ptr::eq(group.face, face)).unwrap_or_else(|| { + let index = self.groups.len(); + self.groups.push(FallbackGroup { face, seen: Default::default(), glyphs: Vec::new(), positions: Vec::new() }); + index + }); + self.names.insert(key, index); + index + }; + let group = self.groups.get_mut(group_index).ok_or_else(|| EditError::Invalid("the fallback face is missing".into()))?; + if group.seen.insert(ch) { + if self.glyphs >= self.budget { + return Err(EditError::Invalid(format!( + "the replacement needs more than {} fallback glyphs; edit a smaller paragraph or load a complete font", + self.budget + ))); + } + let (path, width) = type3_glyph(group.face, ch)?.ok_or_else(|| no_glyph_for(group.face, ch))?; + let code = u8::try_from((group.glyphs.len() % self.per_font).saturating_add(1)) + .map_err(|_| EditError::Invalid("replacement text has too many unique characters".into()))?; + group.glyphs.push(Type3Glyph { code, ch, path, width }); + self.glyphs = self.glyphs.saturating_add(1); + } + group.positions.push(position); + Ok(String::new()) + } +} + +struct StyledLines<'a> { + lines: Vec, + spans: Vec<(std::ops::Range, usize)>, + underlines: HashMap, + overrides: HashMap, +} + +type StyledChar = (char, usize, String); +type StyledRows = Vec>; +type RowRanges = Vec>; +type ShapedRunCache = HashMap<(usize, usize), (Vec, pdfcraft_fonts::source_shaping::ShapedRun, String)>; + +struct ShapedRows { + runs: ShapedRunCache, + advances: HashMap<(usize, usize), f64>, +} + +fn prepare_shaped_rows( + doc: &Document, + fonts: &Dict, + rows: &[Vec], + kept: &[bool], + advance: impl Fn(&StyledChar) -> f64, +) -> Result { + let mut runs = HashMap::new(); + let mut advances = HashMap::new(); + for (row_index, row) in rows.iter().enumerate().filter(|(index, _)| !kept.get(*index).copied().unwrap_or(false)) { + let mut at = 0; + while let Some(item) = row.get(at) { + let mut end = at + 1; + while row.get(end).is_some_and(|next| next.1 == item.1 && next.2 == item.2) { + end += 1; + } + let segment = row.get(at..end).unwrap_or_default(); + advances.insert((row_index, at), segment.iter().map(&advance).sum::()); + let text: String = segment.iter().map(|character| character.0).collect(); + if let Some((bytes, shaped, family)) = shape_source(doc, fonts, &item.2, &text)? { + runs.insert((row_index, at), (bytes, shaped, family)); + } + at = end; + } + } + Ok(ShapedRows { runs, advances }) +} + +fn embed_shaped_resources(doc: &mut Document, fonts: &mut Dict, runs: &ShapedRunCache) -> Result, EditError> { + let mut resources = HashMap::new(); + for (key, (bytes, shaped, family)) in runs { + let mappings: Vec<_> = shaped.glyphs.iter().map(|glyph| (glyph.text.clone(), glyph.id)).collect(); + let resource = pdfcraft_fonts::embedding::embed_mapping(doc, fonts, bytes, family, &mappings).map_err(EditError::Invalid)?; + resources.insert(*key, resource); + } + Ok(resources) +} + +fn validate_contextual_rows(rows: &[Vec], kept: &[bool]) -> Result<(), EditError> { + for (row, _) in rows.iter().zip(kept).filter(|(_, retained)| !**retained) { + let text: String = row.iter().map(|character| character.0).collect(); + if pdfcraft_fonts::source_shaping::required(&text) + && row.first().is_some_and(|first| row.iter().any(|character| character.1 != first.1 || character.2 != first.2)) + { + return Err(EditError::Invalid( + "contextual/bidi text across font or style boundaries needs a uniform full-face row; mixed contextual runs are not yet supported" + .into(), + )); + } + } + Ok(()) +} + +fn calibration_factors( + lines: &[TextLine], + metrics: &std::collections::BTreeMap, + style: &BlockStyle, + overrides: &HashMap, + space_of: impl Fn(&str, &Metrics) -> f64, +) -> HashMap { + let mut calibration = HashMap::new(); + for (index, source) in lines.iter().enumerate() { + if let Some(metrics) = metrics.get(&source.font) { + let nominal = source_width( + metrics, + &source.text, + source.origin.state.font.as_ref().map_or(1.0, |(_, size)| *size), + space_of(&source.font, metrics), + source.origin.state.char_spacing, + source.origin.state.word_spacing, + ) * source.origin.state.scale + * across(source); + let changed_face = + style.resource.is_some() || overrides.get(&index).is_some_and(|range| range.family.is_some() || range.resource.is_some()); + let factor = if nominal > 0.0 && !changed_face { ((source.rect[2] - source.rect[0]) / nominal).clamp(0.5, 2.0) } else { 1.0 }; + calibration.insert(index, factor); + } + } + calibration +} + +fn validated_ranges<'a>(draft: &str, style: &'a BlockStyle) -> Result, EditError> { + let mut ranges: Vec<_> = style.ranges.iter().collect(); + ranges.sort_by_key(|range| range.range.start); + let invalid_range = ranges.iter().any(|range| { + range.range.start >= range.range.end + || draft.get(range.range.clone()).is_none() + || [range.size, range.char_spacing, range.scale].iter().flatten().any(|value| !value.is_finite()) + || range.size.is_some_and(|value| value <= 0.0 || value > 14_400.0) + || range.color.is_some_and(|color| color.iter().any(|value| !value.is_finite() || !(0.0..=1.0).contains(value))) + }); + if ranges.len() > 1024 || invalid_range || ranges.windows(2).any(|pair| pair[0].range.end > pair[1].range.start) { + return Err(EditError::Invalid("text style ranges must be disjoint UTF-8 boundaries with finite formatting (at most 1024 ranges)".into())); + } + Ok(ranges) +} + +fn replacement_text<'a>(block: &'a TextBlock, text: Option<&'a str>) -> Result<&'a str, EditError> { + let draft = match text { + Some(text) if text != block.text => text, + _ => &block.editor_text, + }; + if draft.len() > 4_000_000 { + return Err(EditError::Invalid("the replacement text is too large".into())); + } + Ok(draft) +} + +fn has_no_effective_style_change(block: &TextBlock, draft: &str, style: &BlockStyle) -> bool { + draft == block.editor_text && *style == BlockStyle::default() +} + +fn page_font_metrics( + doc: &Document, + resource_dict: &Dict, + block: &TextBlock, + lines: &[TextLine], +) -> (Dict, std::collections::BTreeMap) { + let mut fonts = resource_dict.get(b"Font").and_then(|resource| doc.resolve(resource).as_dict().cloned()).unwrap_or_default(); + for line in lines.iter().filter(|line| line.font.starts_with("PCRange")) { + let mut font = Dict::new(); + font.set(b"Type".to_vec(), Object::name("Font")); + font.set(b"Subtype".to_vec(), Object::name("Type1")); + font.set(b"BaseFont".to_vec(), Object::name(&line.base_font)); + font.set(b"Encoding".to_vec(), Object::name("WinAnsiEncoding")); + fonts.set(line.font.as_bytes().to_vec(), Object::Dict(font)); + } + let mut metrics = std::collections::BTreeMap::new(); + for (name, object) in fonts.iter().take(256) { + if let Some(font) = doc.resolve(object).as_dict() { + metrics.insert(String::from_utf8_lossy(name).into_owned(), Metrics::from_dict(doc, font)); + } + } + for index in &block.lines { + if let Some(line) = lines.get(*index) + && !metrics.contains_key(&line.font) + && let Some(font) = fonts.get(line.font.as_bytes()).and_then(|resource| doc.resolve(resource).as_dict().cloned()) + { + metrics.insert(line.font.clone(), Metrics::from_dict(doc, &font)); + } + } + (fonts, metrics) +} + +fn paragraph_geometry(doc: &Document, page: &pdfcraft_model::Page, block: &TextBlock, style: &BlockStyle) -> Result<(f64, f64, f64), EditError> { + if [style.size, style.line_spacing, style.char_spacing, style.scale, style.width].iter().flatten().any(|value| !value.is_finite()) + || style.color.is_some_and(|color| color.iter().any(|value| !value.is_finite())) + { + return Err(EditError::Invalid("the paragraph's formatting must use finite numbers".into())); + } + let [dx, dy] = style.offset.unwrap_or([0.0, 0.0]); + if !dx.is_finite() || !dy.is_finite() || style.width.is_some_and(|width| !width.is_finite()) { + return Err(EditError::Invalid("the paragraph's position and width must be finite".into())); + } + let natural = if block.invisible || block.rows.len() == 1 { + (page.crop(doc)[2] - 36.0 - (block.rect[0] + dx)).max(block.rect[2] - block.rect[0]) + } else { + block.rect[2] - block.rect[0] + }; + Ok((dx, dy, style.width.unwrap_or(natural).clamp(1.0, 14_400.0))) +} + +fn wrap_styled_rows( + chars: &[StyledChar], + width: f64, + measure: impl Fn(&[StyledChar]) -> Result, +) -> Result<(StyledRows, RowRanges), EditError> { + let mut rows: Vec> = Vec::new(); + let mut row_ranges = Vec::new(); + let mut row_start = 0; + let mut row = Vec::new(); + let mut row_width = 0.0; + let mut at = 0; + while at < chars.len() { + let Some(item) = chars.get(at) else { break }; + if item.0 == '\r' { + at += 1; + continue; + } + if item.0 == '\n' { + row_ranges.push(row_start..row_start + row.len()); + rows.push(std::mem::take(&mut row)); + row_width = 0.0; + at += 1; + row_start = at; + continue; + } + let mut end = at + 1; + if !item.0.is_whitespace() { + // A word ends at a space, or where Chinese or Japanese text may break between characters. + while let (Some(before), Some(current)) = (chars.get(end - 1), chars.get(end)) + && !current.0.is_whitespace() + && !crate::linebreak::between(before.0, current.0) + { + end += 1; + } + } + let word = chars.get(at..end).unwrap_or_default(); + let word_width = measure(word)?; + if !row.is_empty() && !item.0.is_whitespace() && row_width + word_width > width + 0.5 { + while row.last().is_some_and(|c: &StyledChar| c.0.is_whitespace()) { + row.pop(); + } + row_ranges.push(row_start..row_start + row.len()); + rows.push(std::mem::take(&mut row)); + row_width = 0.0; + row_start = at; + } + row.extend_from_slice(word); + row_width += word_width; + at = end; + } + if !row.is_empty() { + row_ranges.push(row_start..row_start + row.len()); + rows.push(row); + } + Ok((rows, row_ranges)) +} + +fn apply_range_styles<'a>( + first: &TextLine, + block: &TextBlock, + lines: &[TextLine], + draft: &str, + ranges: &[&'a RangeStyle], + style: &BlockStyle, +) -> StyledLines<'a> { + let mut styled_lines = lines.to_vec(); + let mut styled_spans = Vec::new(); + let mut underlines = HashMap::new(); + let mut overrides = HashMap::new(); + for (span, source) in block.edited_spans(draft) { + let mut edges = vec![span.start, span.end]; + for range in ranges { + for edge in [range.range.start, range.range.end] { + if span.contains(&edge) { + edges.push(edge); + } + } + } + edges.sort_unstable(); + edges.dedup(); + for bounds in edges.windows(2) { + let (Some(start), Some(end)) = (bounds.first().copied(), bounds.get(1).copied()) else { continue }; + let selected = ranges.iter().find(|range| range.range.contains(&start)).copied(); + let mut index = source; + if selected.is_some() || style.family.is_some() || style.bold.is_some() { + let default_range = RangeStyle { + range: start..end, + family: None, + resource: None, + size: None, + color: None, + underline: None, + char_spacing: None, + scale: None, + }; + let range = selected.unwrap_or(&default_range); + let mut line = lines.get(source).unwrap_or(first).clone(); + if let Some((family, bold, italic)) = + range.family.or(style.family).or_else(|| style.bold.map(|b| (source_family(&line.base_font), b, line.italic))) + { + let base = family.base_font(bold, italic); + line.font = format!("PCRange{}", base.replace('-', "")); + line.base_font = base.to_owned(); + line.bold = bold; + line.italic = italic; + } + if let Some(resource) = &range.resource { + line.font = resource.clone(); + } + if let Some(size) = range.size { + line.size = size; + } + if let Some(color) = range.color { + line.color = color; + line.origin.state.fill = vec![Op::new("rg", color.map(Object::Real).to_vec())]; + } + if let Some(spacing) = range.char_spacing { + line.origin.state.char_spacing = spacing / line.origin.k.max(1e-6); + } + if let Some(scale) = range.scale { + line.origin.state.scale = (scale / 100.0).clamp(0.1, 10.0); + } + index = styled_lines.len(); + styled_lines.push(line); + if let Some(range) = selected { + overrides.insert(index, range); + } + if let Some(underline) = range.underline { + underlines.insert(index, underline); + } + } + styled_spans.push((start..end, index)); + } + } + StyledLines { lines: styled_lines, spans: styled_spans, underlines, overrides } +} + /// Shape in the source or an explicitly registered matching full face. Never use interface fonts. fn shape_source( doc: &Document, @@ -84,6 +609,48 @@ fn untouched_rows(block: &TextBlock, draft: &str, rows: &[std::ops::Range .collect() } +struct RewriteAnchor<'a> { + lead: &'a TextLine, + drop: std::collections::HashSet, + start: usize, + split: bool, +} + +fn rewrite_anchor<'a>( + block: &TextBlock, + lines: &'a [TextLine], + first: &'a TextLine, + ops: &[Op], + kept_lines: &std::collections::HashSet, + kept: &mut [bool], +) -> RewriteAnchor<'a> { + let rewritten: Vec<&TextLine> = block.lines.iter().filter(|index| !kept_lines.contains(index)).filter_map(|index| lines.get(*index)).collect(); + let lead = rewritten + .last() + .copied() + .filter(|_| !rewritten.iter().flat_map(|line| &line.ops).any(|index| ops.get(*index).is_some_and(|op| op.is("'") || op.is("\"")))); + let (members, lead) = match lead { + Some(lead) if !kept_lines.is_empty() => (rewritten, lead), + _ => { + kept.iter_mut().for_each(|value| *value = false); + let all: Vec<&TextLine> = block.lines.iter().filter_map(|index| lines.get(*index)).collect(); + let last = all.last().copied().unwrap_or(first); + (all, last) + } + }; + let origin = &lead.origin; + let mut drop = coincident_ops(lines, &members); + drop.extend(members.iter().flat_map(|line| line.ops.iter().copied())); + let start = lead.ops.first().copied().unwrap_or(origin.bt_op); + let split = ops + .get(origin.bt_op..start) + .unwrap_or_default() + .iter() + .enumerate() + .any(|(index, op)| matches!(op.op.as_slice(), b"Tj" | b"TJ" | b"'" | b"\"") && !drop.contains(&(origin.bt_op + index))); + RewriteAnchor { lead, drop, start, split } +} + /// Rewrite visual rows while keeping the source style on each surviving character. Resource /// names may differ between Unicode subsets of the same face; encoding searches those subsets. pub(crate) fn rewrite_styled_block( @@ -96,291 +663,36 @@ pub(crate) fn rewrite_styled_block( max_glyphs: usize, ) -> Result { let first = block.lines.first().and_then(|i| lines.get(*i)).ok_or_else(|| EditError::Invalid("the paragraph has no source runs".into()))?; - let draft = match text { - Some(t) if t != block.text => t, - _ => &block.editor_text, - }; - if draft.len() > 4_000_000 { - return Err(EditError::Invalid("the replacement text is too large".into())); - } - if draft == block.editor_text && *style == BlockStyle::default() { + let draft = replacement_text(block, text)?; + if has_no_effective_style_change(block, draft, style) { return Ok(LineEdit { substituted: None }); } - let mut ranges: Vec<_> = style.ranges.iter().collect(); - ranges.sort_by_key(|r| r.range.start); - if ranges.len() > 1024 - || ranges.iter().any(|r| { - r.range.start >= r.range.end - || draft.get(r.range.clone()).is_none() - || [r.size, r.char_spacing, r.scale].iter().flatten().any(|n| !n.is_finite()) - || r.size.is_some_and(|n| n <= 0.0 || n > 14400.0) - || r.color.is_some_and(|c| c.iter().any(|n| !n.is_finite() || !(0.0..=1.0).contains(n))) - }) - || ranges.windows(2).any(|r| r[0].range.end > r[1].range.start) - { - return Err(EditError::Invalid("text style ranges must be disjoint UTF-8 boundaries with finite formatting (at most 1024 ranges)".into())); - } + let ranges = validated_ranges(draft, style)?; let source_count = lines.len(); - let mut styled_lines = lines.to_vec(); - let mut styled_spans = Vec::new(); - let mut underlines = HashMap::new(); - let mut overrides = HashMap::new(); - for (span, source) in block.edited_spans(draft) { - let mut edges = vec![span.start, span.end]; - for r in &ranges { - for edge in [r.range.start, r.range.end] { - if span.contains(&edge) { - edges.push(edge); - } - } - } - edges.sort_unstable(); - edges.dedup(); - for bounds in edges.windows(2) { - let (Some(start), Some(end)) = (bounds.first().copied(), bounds.get(1).copied()) else { continue }; - let mut index = source; - let selected = ranges.iter().find(|r| r.range.contains(&start)).copied(); - if selected.is_some() || style.family.is_some() || style.bold.is_some() { - let default_range = RangeStyle { - range: start..end, - family: None, - resource: None, - size: None, - color: None, - underline: None, - char_spacing: None, - scale: None, - }; - let r = selected.unwrap_or(&default_range); - let mut line = lines.get(source).unwrap_or(first).clone(); - if let Some((family, bold, italic)) = - r.family.or(style.family).or_else(|| style.bold.map(|b| (source_family(&line.base_font), b, line.italic))) - { - let base = family.base_font(bold, italic); - line.font = format!("PCRange{}", base.replace('-', "")); - line.base_font = base.to_owned(); - line.bold = bold; - line.italic = italic; - } - if let Some(resource) = &r.resource { - line.font = resource.clone(); - } - if let Some(size) = r.size { - line.size = size; - } - if let Some(color) = r.color { - line.color = color; - line.origin.state.fill = vec![Op::new("rg", color.map(Object::Real).to_vec())]; - } - if let Some(spacing) = r.char_spacing { - line.origin.state.char_spacing = spacing / line.origin.k.max(1e-6); - } - if let Some(scale) = r.scale { - line.origin.state.scale = (scale / 100.0).clamp(0.1, 10.0); - } - index = styled_lines.len(); - styled_lines.push(line); - if let Some(r) = selected { - overrides.insert(index, r); - } - if let Some(underline) = r.underline { - underlines.insert(index, underline); - } - } - styled_spans.push((start..end, index)); - } - } - let lines = styled_lines.as_slice(); + let styled = apply_range_styles(first, block, lines, draft, &ranges, style); + let lines = styled.lines.as_slice(); + let styled_spans = styled.spans; + let underlines = styled.underlines; + let overrides = styled.overrides; let p = page_dict(doc, page)?; - let mut res = p.dict.get(b"Resources").and_then(|r| doc.resolve(r).as_dict().cloned()).unwrap_or_default(); - let mut fonts = res.get(b"Font").and_then(|r| doc.resolve(r).as_dict().cloned()).unwrap_or_default(); - for line in lines.iter().filter(|line| line.font.starts_with("PCRange")) { - let mut f = Dict::new(); - f.set(b"Type".to_vec(), Object::name("Font")); - f.set(b"Subtype".to_vec(), Object::name("Type1")); - f.set(b"BaseFont".to_vec(), Object::name(&line.base_font)); - f.set(b"Encoding".to_vec(), Object::name("WinAnsiEncoding")); - fonts.set(line.font.as_bytes().to_vec(), Object::Dict(f)); - } - let mut metrics = std::collections::BTreeMap::new(); - for (name, object) in fonts.iter().take(256) { - if let Some(font) = doc.resolve(object).as_dict() { - metrics.insert(String::from_utf8_lossy(name).into_owned(), Metrics::from_dict(doc, font)); - } - } - for index in &block.lines { - if let Some(line) = lines.get(*index) - && !metrics.contains_key(&line.font) - && let Some(font) = fonts.get(line.font.as_bytes()).and_then(|f| doc.resolve(f).as_dict().cloned()) - { - metrics.insert(line.font.clone(), Metrics::from_dict(doc, &font)); - } - } - if [style.size, style.line_spacing, style.char_spacing, style.scale, style.width].iter().flatten().any(|v| !v.is_finite()) - || style.color.is_some_and(|c| c.iter().any(|v| !v.is_finite())) - { - return Err(EditError::Invalid("the paragraph's formatting must use finite numbers".into())); - } - let [dx, dy] = style.offset.unwrap_or([0.0, 0.0]); - if !dx.is_finite() || !dy.is_finite() || style.width.is_some_and(|w| !w.is_finite()) { - return Err(EditError::Invalid("the paragraph's position and width must be finite".into())); - } - // A visual row grows even when it contains several source/font runs. Multi-row - // paragraphs retain their container width; an explicit width always wins. - let natural = if block.invisible || block.rows.len() == 1 { - (p.crop(doc)[2] - 36.0 - (block.rect[0] + dx)).max(block.rect[2] - block.rect[0]) - } else { - block.rect[2] - block.rect[0] - }; - let width = style.width.unwrap_or(natural).clamp(1.0, 14_400.0); - // Each tuple is a character, its source style and an encodable resource name. - let mut chars = Vec::new(); - let mut substituted = None; - let mut fallback_groups: Vec = Vec::new(); - let mut fallback_names: std::collections::BTreeMap<(String, bool, char), usize> = std::collections::BTreeMap::new(); - let mut fallback_glyphs = 0_usize; - let per_font = max_glyphs.clamp(1, MAX_TYPE3_GLYPHS); - let fallback_budget = per_font.saturating_mul(MAX_STYLED_FALLBACK_BATCHES); - let mut full_faces: HashMap = HashMap::new(); - let mut programs: HashMap>>> = HashMap::new(); - for (range, index) in styled_spans { - let source = lines.get(index).unwrap_or(first); - let start = range.start; - for (offset, ch) in draft.get(range).unwrap_or_default().char_indices() { - if ch == '\n' { - chars.push((ch, index, source.font.clone())); - continue; - } - // A carriage return breaks the row too. Before `\n` the pair is one break, so the - // CR stays a `\r` the rows skip. Either way it keeps its place among the draft's - // characters, which rows are counted in. - if ch == '\r' { - let crlf = start.checked_add(offset).and_then(|at| draft.get(at.saturating_add(1)..)).is_some_and(|rest| rest.starts_with('\n')); - chars.push((if crlf { '\r' } else { '\n' }, index, source.font.clone())); - continue; - } - let s = ch.to_string(); - let name = if let Some(resource) = overrides.get(&index).and_then(|r| r.resource.as_ref()).or(style.resource.as_ref()) { - if !metrics.get(resource).is_some_and(|m| source_encodes(m, &s)) { - return Err(EditError::Invalid(format!("the selected font resource {resource} cannot show U+{:04X}", u32::from(ch)))); - } - resource.clone() - } else if metrics.get(&source.font).is_some_and(|m| source_encodes(m, &s)) { - source.font.clone() - } else if let Some((name, _)) = metrics.iter().find(|(_, m)| { - pdfcraft_fonts::embedding::face_key(&m.base_font) == pdfcraft_fonts::embedding::face_key(&source.base_font) && source_encodes(m, &s) - }) { - name.clone() - } else if let Some(face) = - pdfcraft_fonts::embedding::matching_faces(&source.base_font).into_iter().find(|f| pdfcraft_fonts::embedding::covers(f.bytes, &s)) - { - let key = face.name(); - if let Some(name) = full_faces.get(&key) { - name.clone() - } else { - let name = pdfcraft_fonts::embedding::embed(doc, &mut fonts, face.bytes, face.family).map_err(EditError::Invalid)?; - let font = fonts - .get(name.as_bytes()) - .and_then(|f| doc.dict(f)) - .ok_or_else(|| EditError::Invalid("the full source font could not be loaded".into()))?; - metrics.insert(name.clone(), Metrics::from_dict(doc, &font)); - full_faces.insert(key, name.clone()); - name - } - } else if let Some(bytes) = programs - .entry(source.font.clone()) - .or_insert_with(|| source_program(doc, &fonts, &source.font).map(std::sync::Arc::new)) - .clone() - .filter(|bytes| pdfcraft_fonts::embedding::covers(bytes, &s)) - { - // The document's own complete program of this font has the glyph: draw it with - // that face rather than another family's fallback. - let key = format!("source {}", source.font); - if let Some(name) = full_faces.get(&key) { - name.clone() - } else { - let family = pdfcraft_fonts::embedding::names(&bytes).map_or_else(|_| source.base_font.clone(), |(family, _)| family); - let name = pdfcraft_fonts::embedding::embed(doc, &mut fonts, &bytes, &family).map_err(EditError::Invalid)?; - let font = fonts - .get(name.as_bytes()) - .and_then(|f| doc.dict(f)) - .ok_or_else(|| EditError::Invalid("the source font could not be loaded".into()))?; - metrics.insert(name.clone(), Metrics::from_dict(doc, &font)); - full_faces.insert(key, name.clone()); - name - } - } else { - let family = source_family(&source.base_font); - if needs_type3(&s) { - let key = (source.base_font.clone(), source.bold, ch); - let group_index = if let Some(index) = fallback_names.get(&key) { - *index - } else { - // Keep the old per-character face choice: a serif Japanese character - // and a Cyrillic character may need different faces even in one style. - // Hebrew uses the separate RTL path before reaching this writer. - let (faces, _) = type3_faces(&s, family, source.bold)?; - let face = - fallback_face(&faces, &[ch], |face, ch| japanese_glyph_from(face, ch).is_ok()).ok_or_else(|| no_fallback_font(&s))?; - let index = fallback_groups.iter().position(|group| std::ptr::eq(group.face, face)).unwrap_or_else(|| { - let index = fallback_groups.len(); - fallback_groups.push(FallbackGroup { face, seen: Default::default(), glyphs: Vec::new(), positions: Vec::new() }); - index - }); - fallback_names.insert(key, index); - index - }; - let group = fallback_groups.get_mut(group_index).ok_or_else(|| EditError::Invalid("the fallback face is missing".into()))?; - if group.seen.insert(ch) { - if fallback_glyphs >= fallback_budget { - return Err(EditError::Invalid(format!( - "the replacement needs more than {fallback_budget} fallback glyphs; edit a smaller paragraph or load a complete font" - ))); - } - let (path, width) = type3_glyph(group.face, ch)?.ok_or_else(|| no_glyph_for(group.face, ch))?; - let code = u8::try_from((group.glyphs.len() % per_font).saturating_add(1)) - .map_err(|_| EditError::Invalid("replacement text has too many unique characters".into()))?; - group.glyphs.push(Type3Glyph { code, ch, path, width }); - fallback_glyphs = fallback_glyphs.saturating_add(1); - } - group.positions.push(chars.len()); - // Filled from the prepared font/code map before measuring or drawing. - String::new() - } else { - let base = family.base_font(source.bold, source.italic); - let name = format!("PCEd{}", base.replace('-', "")); - let mut f = Dict::new(); - f.set(b"Type".to_vec(), Object::name("Font")); - f.set(b"Subtype".to_vec(), Object::name("Type1")); - f.set(b"BaseFont".to_vec(), Object::name(base)); - f.set(b"Encoding".to_vec(), Object::name("WinAnsiEncoding")); - metrics.entry(name.clone()).or_insert_with(|| Metrics::from_dict(doc, &f)); - fonts.set(name.clone().into_bytes(), Object::Dict(f)); - substituted = Some(base.to_string()); - name - } - }; - chars.push((ch, index, name)); - } - } - // All fallback outlines have now succeeded. Batch by actual face, preserving source - // style indices; the existing writer then coalesces adjacent equal-font/style characters. - for group in fallback_groups { - let fallback = write_type3_glyphs(doc, &mut fonts, group.face, false, group.glyphs, per_font); - for name in &fallback.names { - let font = fonts - .get(name.as_bytes()) - .and_then(|f| doc.dict(f)) - .ok_or_else(|| EditError::Invalid("the fallback font could not be loaded".into()))?; - metrics.insert(name.clone(), Metrics::from_dict(doc, &font)); - } - for position in group.positions { - let item = chars.get_mut(position).ok_or_else(|| EditError::Invalid("the fallback character is missing".into()))?; - let (font, _) = fallback.codes.get(&item.0).ok_or_else(|| EditError::Invalid("the fallback glyph is missing".into()))?; - item.2 = fallback.names.get(*font).cloned().ok_or_else(|| EditError::Invalid("the fallback font is missing".into()))?; - } - substituted = Some(fallback.family.to_owned()); + let mut res = p.dict.get(b"Resources").and_then(|resource| doc.resolve(resource).as_dict().cloned()).unwrap_or_default(); + let (mut fonts, mut metrics) = page_font_metrics(doc, &res, block, lines); + let (dx, dy, width) = paragraph_geometry(doc, &p, block, style)?; + let prepared = CharacterPreparation { + doc, + first, + lines, + draft, + spans: styled_spans, + style, + overrides: &overrides, + fonts: &mut fonts, + metrics: &mut metrics, + max_glyphs, } + .prepare()?; + let chars = prepared.values; + let substituted = prepared.substituted; let size_of = |source: &TextLine, index: usize| { overrides.get(&index).and_then(|r| r.size).or(style.size).unwrap_or(source.size).max(0.1) / source.origin.k.max(1e-6) }; @@ -400,23 +712,7 @@ pub(crate) fn rewrite_styled_block( spaces.borrow_mut().insert(name.to_owned(), w); w }; - let mut calibration = HashMap::new(); - for (index, source) in lines.iter().enumerate() { - if let Some(m) = metrics.get(&source.font) { - let nominal = source_width( - m, - &source.text, - source.origin.state.font.as_ref().map_or(1.0, |(_, s)| *s), - space_of(&source.font, m), - source.origin.state.char_spacing, - source.origin.state.word_spacing, - ) * source.origin.state.scale - * across(source); - let changed_face = style.resource.is_some() || overrides.get(&index).is_some_and(|r| r.family.is_some() || r.resource.is_some()); - let factor = if nominal > 0.0 && !changed_face { ((source.rect[2] - source.rect[0]) / nominal).clamp(0.5, 2.0) } else { 1.0 }; - calibration.insert(index, factor); - } - } + let calibration = calibration_factors(lines, &metrics, style, &overrides, space_of); let advance = |item: &(char, usize, String)| -> f64 { let source = lines.get(item.1).unwrap_or(first); let Some(m) = metrics.get(&item.2) else { return 0.0 }; @@ -466,58 +762,7 @@ pub(crate) fn rewrite_styled_block( } Ok(width) }; - let mut rows: Vec> = Vec::new(); - // Each row's characters, as indexes into the draft's characters (`chars` holds all of them). - let mut row_ranges = Vec::new(); - let mut row_start = 0; - let mut row = Vec::new(); - let mut row_width = 0.0; - // Wrap at word boundaries, retaining explicit source row breaks and whitespace. - let mut at = 0; - while at < chars.len() { - let Some(item) = chars.get(at) else { break }; - // The CR of a CRLF: the `\n` after it breaks the row. - if item.0 == '\r' { - at += 1; - continue; - } - if item.0 == '\n' { - row_ranges.push(row_start..row_start + row.len()); - rows.push(std::mem::take(&mut row)); - row_width = 0.0; - at += 1; - row_start = at; - continue; - } - let mut end = at + 1; - if !item.0.is_whitespace() { - // A word ends at a space, or where Chinese or Japanese text may break between characters. - while let (Some(before), Some(c)) = (chars.get(end - 1), chars.get(end)) - && !c.0.is_whitespace() - && !crate::linebreak::between(before.0, c.0) - { - end += 1; - } - } - let word = chars.get(at..end).unwrap_or_default(); - let w = measure(word)?; - if !row.is_empty() && !item.0.is_whitespace() && row_width + w > width + 0.5 { - while row.last().is_some_and(|c: &(char, usize, String)| c.0.is_whitespace()) { - row.pop(); - } - row_ranges.push(row_start..row_start + row.len()); - rows.push(std::mem::take(&mut row)); - row_width = 0.0; - row_start = at; - } - row.extend_from_slice(word); - row_width += w; - at = end; - } - if !row.is_empty() { - row_ranges.push(row_start..row_start + row.len()); - rows.push(row); - } + let (rows, row_ranges) = wrap_styled_rows(&chars, width, measure)?; let streams = content_streams(doc, &p.dict)?; let pieces = Pieces::join(&streams.iter().map(|(_, d)| d.as_slice()).collect::>()); let ops = pieces.parse().ops; @@ -531,65 +776,18 @@ pub(crate) fn rewrite_styled_block( }; let kept_lines: std::collections::HashSet = kept.iter().enumerate().filter(|(_, k)| **k).filter_map(|(r, _)| block.rows.get(r)).flatten().copied().collect(); - let rewritten: Vec<&TextLine> = block.lines.iter().filter(|i| !kept_lines.contains(i)).filter_map(|i| lines.get(*i)).collect(); - // The rewrite goes where the last rewritten row was drawn, after any backgrounds painted - // between the rows. A dropped `'` or `"` also moved to the next line, which a kept row relies on. - let lead = - rewritten.last().copied().filter(|_| !rewritten.iter().flat_map(|l| &l.ops).any(|i| ops.get(*i).is_some_and(|op| op.is("'") || op.is("\"")))); - let (members, lead) = match lead { - Some(lead) if !kept_lines.is_empty() => (rewritten, lead), - _ => { - kept.iter_mut().for_each(|k| *k = false); - let all: Vec<&TextLine> = block.lines.iter().filter_map(|i| lines.get(*i)).collect(); - let last = all.last().copied().unwrap_or(first); - (all, last) - } - }; + // The rewrite is placed after the last rewritten row unless a text-show operator there + // would make a kept following row depend on that position. + let anchor = rewrite_anchor(block, lines, first, &ops, &kept_lines, &mut kept); + let RewriteAnchor { lead, drop, start, split } = anchor; let o = &lead.origin; - let mut drop = coincident_ops(lines, &members); - drop.extend(members.iter().flat_map(|l| l.ops.iter().copied())); - let start = lead.ops.first().copied().unwrap_or(o.bt_op); - let split = ops - .get(o.bt_op..start) - .unwrap_or_default() - .iter() - .enumerate() - .any(|(i, op)| matches!(op.op.as_slice(), b"Tj" | b"TJ" | b"'" | b"\"") && !drop.contains(&(o.bt_op + i))); // What is in force where the rewrite is drawn, and what the text after it expects. let after = if split { &o.state } else { &o.bt_state }; - for (row, _) in rows.iter().zip(&kept).filter(|(_, k)| !**k) { - let text: String = row.iter().map(|v| v.0).collect(); - if pdfcraft_fonts::source_shaping::required(&text) && row.first().is_some_and(|first| row.iter().any(|v| v.1 != first.1 || v.2 != first.2)) { - return Err(EditError::Invalid( - "contextual/bidi text across font or style boundaries needs a uniform full-face row; mixed contextual runs are not yet supported" - .into(), - )); - } - } - let measured: Vec<_> = rows.iter().map(|r| measure(r)).collect::>()?; - let mut shaped_runs = HashMap::new(); - let mut segment_advances = HashMap::new(); - for (row_index, row) in rows.iter().enumerate().filter(|(r, _)| !kept.get(*r).copied().unwrap_or(false)) { - let mut at = 0; - while let Some(item) = row.get(at) { - let mut end = at + 1; - while row.get(end).is_some_and(|v| v.1 == item.1 && v.2 == item.2) { - end += 1; - } - segment_advances.insert((row_index, at), row.get(at..end).unwrap_or_default().iter().map(&advance).sum::()); - let string: String = row.get(at..end).unwrap_or_default().iter().map(|v| v.0).collect(); - if let Some((bytes, shaped, family)) = shape_source(doc, &fonts, &item.2, &string)? { - shaped_runs.insert((row_index, at), (bytes, shaped, family)); - } - at = end; - } - } - let mut glyph_resources = HashMap::new(); - for (key, (bytes, shaped, family)) in &shaped_runs { - let mappings: Vec<_> = shaped.glyphs.iter().map(|g| (g.text.clone(), g.id)).collect(); - let resource = pdfcraft_fonts::embedding::embed_mapping(doc, &mut fonts, bytes, family, &mappings).map_err(EditError::Invalid)?; - glyph_resources.insert(*key, resource); - } + validate_contextual_rows(&rows, &kept)?; + let measured: Vec<_> = rows.iter().map(|row| measure(row)).collect::>()?; + let shaped = prepare_shaped_rows(doc, &fonts, &rows, &kept, advance)?; + let ShapedRows { runs: shaped_runs, advances: segment_advances } = shaped; + let glyph_resources = embed_shaped_resources(doc, &mut fonts, &shaped_runs)?; let n = pdfcraft_content::num; let mut block_ops = vec![Op::new("q", vec![])]; block_ops.extend(reveal_ops(block, lines, style, o.ctm)?); diff --git a/crates/edit/src/text_session.rs b/crates/edit/src/text_session.rs index 893a0e4d24..fe1aa78688 100644 --- a/crates/edit/src/text_session.rs +++ b/crates/edit/src/text_session.rs @@ -3,7 +3,10 @@ //! another one's output; the commit writes into the document it was opened on, and refuses if //! that document has changed since. -use super::*; +use super::{ + BlockStyle, Document, EditError, LineEdit, MAX_TYPE3_GLYPHS, TextBlock, TextEditLayout, TextLine, group_blocks, layout_draft, rewrite_block_from, + text_lines, +}; /// One paragraph being edited: the document as it was opened, and the page's lines then. pub struct TextSession { diff --git a/crates/engine/examples/export_bench.rs b/crates/engine/examples/export_bench.rs new file mode 100644 index 0000000000..41520d2ffa --- /dev/null +++ b/crates/engine/examples/export_bench.rs @@ -0,0 +1,61 @@ +//! Times Export ▸ Image over every page of a PDF, for before and after comparisons. +//! +//! Usage: `export_bench FILE [DPI] [png|jpeg|tiff] [RUNS]` (defaults: 150 dpi, PNG, 7 runs). Each +//! run exports every page through [`Exporter::images`] from a fresh exporter, as Export ▸ Image +//! does, and prints its wall time; the summary gives the median and the minimum, the total size +//! and an FNV-1a hash of every file in page order. Equal hashes mean equal output. Build with +//! `--release`; timings are diagnostic, never a CI deadline. + +use std::error::Error; +use std::sync::Arc; +use std::time::Instant; + +use pdfcraft_engine::Session; +use pdfcraft_engine::export::{Exporter, ImageFormat}; + +const FNV_OFFSET: u64 = 0xcbf2_9ce4_8422_2325; +const FNV_PRIME: u64 = 0x0000_0100_0000_01b3; + +fn main() -> Result<(), Box> { + let mut args = std::env::args().skip(1); + let path = args.next().ok_or("usage: export_bench FILE [DPI] [png|jpeg|tiff] [RUNS]")?; + let dpi: f64 = args.next().map_or(Ok(150.0), |s| s.parse())?; + let format = match args.next().as_deref() { + None | Some("png") => ImageFormat::Png, + Some("jpeg" | "jpg") => ImageFormat::Jpeg { quality: 85 }, + Some("tiff" | "tif") => ImageFormat::Tiff, + Some(other) => return Err(format!("unknown format {other:?}").into()), + }; + let runs: usize = args.next().map_or(Ok(7), |s| s.parse())?; + let mut session = Session::new(); + let id = session.open("bench.pdf", None, Arc::new(std::fs::read(&path)?), None)?; + let src = session.get(id).ok_or("the document did not open")?.export_source(); + let pages: Vec = (0..src.pages).collect(); + let mut times = Vec::new(); + let mut summary = None; + for run in 0..runs { + let start = Instant::now(); + let mut exporter = Exporter::from_source(src.clone()); + let (mut hash, mut bytes) = (FNV_OFFSET, 0usize); + exporter.images(&pages, dpi, format, |_, file| { + bytes += file.len(); + for b in file { + hash = (hash ^ u64::from(b)).wrapping_mul(FNV_PRIME); + } + Ok(()) + })?; + let ms = start.elapsed().as_secs_f64() * 1000.0; + println!("run {}: {ms:.1} ms", run + 1); + times.push(ms); + summary = Some((bytes, hash)); + } + times.sort_by(f64::total_cmp); + if let (Some(median), Some(min), Some((bytes, hash))) = (times.get(times.len() / 2), times.first(), summary) { + println!( + "{} pages, {} at {dpi} dpi: median {median:.1} ms, min {min:.1} ms ({runs} runs), {bytes} bytes, hash {hash:016x}", + pages.len(), + format.label() + ); + } + Ok(()) +} diff --git a/crates/engine/src/doc_state.rs b/crates/engine/src/doc_state.rs index d25cc65037..d28429de6f 100644 --- a/crates/engine/src/doc_state.rs +++ b/crates/engine/src/doc_state.rs @@ -1,4 +1,4 @@ -use super::*; +use super::{Arc, EditError, Hidden, SignatureInfo, TrustStore, optimize}; /// A change to an existing page image. #[derive(Clone, Debug, PartialEq)] diff --git a/crates/engine/src/edit/labels.rs b/crates/engine/src/edit/labels.rs index 5e25ae465b..ea25898068 100644 --- a/crates/engine/src/edit/labels.rs +++ b/crates/engine/src/edit/labels.rs @@ -1,4 +1,4 @@ -use super::*; +use super::{Edit, FillMark, ImageEdit, Label, LineEnding, MarkKind, Markup, PageBox, ReviewState, Shape, field_table}; /// Every wording [`Edit::label`] can produce, for an interface to translate. `Edit::Batch` is not /// here: its wording is only the hole, because a batch carries its name as text (see diff --git a/crates/engine/src/edit/run.rs b/crates/engine/src/edit/run.rs index 7901a3b7d8..49f19fa637 100644 --- a/crates/engine/src/edit/run.rs +++ b/crates/engine/src/edit/run.rs @@ -1,4 +1,7 @@ -use super::*; +use super::{ + AddedContent, Arc, Edit, EditError, FieldValue, ImageEdit, NewAnnotation, Shape, a11y, copy_image, decode_data_file, embed_image, fit_picture, + image_content_type, is_xfa_data_file, js, mark_source, measure, open_source, strip_xfa, unrestricted, xfa, xfa_after_data_change, +}; /// Whether the opening password allows an edit (§7.6.4.2, Table 22). pub(crate) fn check_permission(edit: &Edit, p: &pdfcraft_cos::Permissions) -> Result<(), EditError> { @@ -328,7 +331,19 @@ pub(crate) fn run_edit(doc: &mut pdfcraft_cos::Document, edit: &Edit, cx: &mut E // One `/NM` each: the caret replies to the strikeout, and XFDF names that reply by // the strikeout's `/NM` (#2666). let (strike_meta, caret_meta) = (cx.meta(), cx.meta()); - pdfcraft_annot::add_text_replacement(doc, *page, quads, text, author, strike, caret, &strike_meta, &caret_meta)?; + pdfcraft_annot::add_text_replacement( + doc, + pdfcraft_annot::TextReplacement { + page: *page, + quads, + replacement: text, + author, + strike, + caret, + strike_meta: &strike_meta, + caret_meta: &caret_meta, + }, + )?; } Edit::MarkAnnotation { page, index, marked, author } => { pdfcraft_annot::set_marked(doc, *page, *index, *marked, author, &cx.meta())?; @@ -338,7 +353,13 @@ pub(crate) fn run_edit(doc: &mut pdfcraft_cos::Document, edit: &Edit, cx: &mut E Edit::ReshapeAnnotation { page, index, points } => pdfcraft_annot::set_points(doc, *page, *index, points, &cx.meta())?, Edit::ResizeAnnotation { page, index, rect } => pdfcraft_annot::set_rect(doc, *page, *index, *rect, &cx.meta())?, Edit::StyleAnnotation { page, index, color, opacity, width, endings } => { - pdfcraft_annot::set_style(doc, *page, *index, *color, *opacity, *width, endings.as_deref(), &cx.meta())?; + pdfcraft_annot::set_style( + doc, + *page, + *index, + pdfcraft_annot::StyleChange { color: *color, opacity: *opacity, width: *width, endings: endings.clone() }, + &cx.meta(), + )?; } Edit::FillAnnotation { page, index, fill } => pdfcraft_annot::set_fill(doc, *page, *index, *fill, &cx.meta())?, Edit::FontSizeAnnotation { page, index, size } => pdfcraft_annot::set_font_size(doc, *page, *index, *size, &cx.meta())?, diff --git a/crates/engine/src/export.rs b/crates/engine/src/export.rs index 01159df800..1330faf272 100644 --- a/crates/engine/src/export.rs +++ b/crates/engine/src/export.rs @@ -4,13 +4,52 @@ //! text, from a //! document's working file (so unsaved edits and hidden layers are respected, as on screen). +use std::collections::BTreeMap; +use std::panic::{AssertUnwindSafe, catch_unwind}; +use std::sync::atomic::{AtomicBool, AtomicUsize, Ordering}; +use std::sync::{Condvar, Mutex, PoisonError, mpsc}; + use pdfcraft_render::{PageRenderer, RenderRequest, RequestKind}; use crate::Document; +/// At most this many pages are drawn at once by [`Exporter::images`]. +const MAX_IMAGE_WORKERS: usize = 8; +/// Bytes of rasters [`Exporter::images`] may hold at once: 1 GiB, about 16 Letter pages at 300 dpi. +/// Each worker holds one page (the raster, its RGB copy and the encoded file), so large pages run +/// on fewer workers; a page over the cap still exports, on one worker, as it did before. +const IMAGE_MEMORY: f64 = 1024.0 * 1024.0 * 1024.0; + +/// Page `page` drawn at `dpi` and encoded as `format`, saying it was drawn at `used` dpi. +fn draw_image(renderer: &mut PageRenderer, page: usize, dpi: f64, format: ImageFormat, used: f64) -> Result, String> { + let r = renderer.render(RenderRequest { page, scale: (dpi.clamp(18.0, 1200.0) / 72.0) as f32, ..Default::default() }); + if let Some(e) = r.error { + return Err(format!("page {}: {e}", page + 1)); + } + encode_image(r.width, r.height, &r.rgba, format, used) +} + +/// Tells the workers of [`Exporter::images`] to stop when dropped. +struct StopWorkers<'a> { + stop: &'a AtomicBool, + handed_over: &'a (Mutex, Condvar), +} + +impl Drop for StopWorkers<'_> { + fn drop(&mut self) { + self.stop.store(true, Ordering::Relaxed); + // Taken under the lock, so a worker between its check and its wait still sees it. + drop(self.handed_over.0.lock().unwrap_or_else(PoisonError::into_inner)); + self.handed_over.1.notify_all(); + } +} + /// Renders and extracts pages of one document state. pub struct Exporter { renderer: PageRenderer, + /// What the renderer draws, for the extra renderers [`Exporter::images`] starts. + bytes: std::sync::Arc>, + config: pdfcraft_render::RenderConfig, pages: usize, /// Each page's displayed size in points, for [`Exporter::dpi_used`]. sizes: Vec<(f32, f32)>, @@ -65,7 +104,13 @@ impl Exporter { /// resolution they allow, as the interactive Export does; [`Exporter::dpi_used`] says at what. /// A source whose `config.reject_oversize` is set refuses such pages instead. pub fn from_source(src: ExportSource) -> Self { - Self { renderer: PageRenderer::new(src.bytes, src.config), pages: src.pages, sizes: src.sizes } + Self { + renderer: PageRenderer::new(src.bytes.clone(), src.config.clone()), + bytes: src.bytes, + config: src.config, + pages: src.pages, + sizes: src.sizes, + } } /// The resolution page `page` is actually exported at when asked for `dpi`: lower than asked @@ -96,11 +141,146 @@ impl Exporter { /// Page `page` as an image file of `format`, which says the resolution it was drawn at. pub fn image(&mut self, page: usize, dpi: f64, format: ImageFormat) -> Result, String> { self.check(page)?; - let r = self.renderer.render(RenderRequest { page, scale: (dpi.clamp(18.0, 1200.0) / 72.0) as f32, ..Default::default() }); - if let Some(e) = r.error { - return Err(format!("page {}: {e}", page + 1)); + let used = self.dpi_used(page, dpi); + draw_image(&mut self.renderer, page, dpi, format, used) + } + + /// Pages `pages` as image files of `format`, handed to `sink` in order with their page + /// number: the same files as [`Exporter::image`] for each page in turn. Encoding a page costs + /// several times what drawing it does, so several pages are drawn and encoded at once on + /// worker threads, each with its own renderer, while `sink` runs on the calling thread. + /// Workers draw at most one page each ahead of `sink`, and fewer run when the pages are + /// large, so memory stays bounded. Stops at the first page that fails or the first error `sink` + /// returns, and returns it; every page before it has been handed to `sink`. + pub fn images( + &mut self, + pages: &[usize], + dpi: f64, + format: ImageFormat, + sink: impl FnMut(usize, Vec) -> Result<(), String>, + ) -> Result<(), String> { + let workers = self.image_workers(pages, dpi); + self.images_on(workers, pages, dpi, format, sink) + } + + /// [`Exporter::images`] with `workers` pages drawn at once (one: in turn, on this thread). + pub(crate) fn images_on( + &mut self, + workers: usize, + pages: &[usize], + dpi: f64, + format: ImageFormat, + mut sink: impl FnMut(usize, Vec) -> Result<(), String>, + ) -> Result<(), String> { + if workers <= 1 { + for &p in pages { + let img = self.image(p, dpi, format)?; + sink(p, img)?; + } + return Ok(()); } - encode_image(r.width, r.height, &r.rgba, format, self.dpi_used(page, dpi)) + let used: Vec = pages.iter().map(|p| self.dpi_used(*p, dpi)).collect(); + let count = self.pages; + let (bytes, config) = (&self.bytes, &self.config); + let next = AtomicUsize::new(0); + let stop = AtomicBool::new(false); + // How many pages `sink` has taken; a worker waits while its page is `workers` past it. + let handed_over = (Mutex::new(0usize), Condvar::new()); + let (tx, rx) = mpsc::channel::<(usize, Result, String>)>(); + let mut first = Some(&mut self.renderer); + std::thread::scope(|s| { + let handles: Vec<_> = (0..workers) + .map(|_| { + let tx = tx.clone(); + let (first, used, next, stop, handed_over) = (first.take(), &used, &next, &stop, &handed_over); + s.spawn(move || { + let mut own = None; + let renderer = match first { + Some(r) => r, + None => own.insert(PageRenderer::new(bytes.clone(), config.clone())), + }; + loop { + let i = next.fetch_add(1, Ordering::Relaxed); + let (Some(&page), Some(&used)) = (pages.get(i), used.get(i)) else { break }; + let mut taken = handed_over.0.lock().unwrap_or_else(PoisonError::into_inner); + while i >= taken.saturating_add(workers) && !stop.load(Ordering::Relaxed) { + taken = handed_over.1.wait(taken).unwrap_or_else(PoisonError::into_inner); + } + drop(taken); + if stop.load(Ordering::Relaxed) { + break; + } + let img = if page < count { + catch_unwind(AssertUnwindSafe(|| draw_image(renderer, page, dpi, format, used))) + .unwrap_or_else(|_| Err(format!("page {}: the export crashed", page + 1))) + } else { + Err(format!("page {} does not exist", page + 1)) + }; + if tx.send((i, img)).is_err() { + break; + } + } + }) + }) + .collect(); + drop(tx); + // Stops the workers however this ends, a panicking `sink` included: waiting ones + // would otherwise keep the scope from returning. + let stopper = StopWorkers { stop: &stop, handed_over: &handed_over }; + let mut ready = BTreeMap::new(); + let mut result = Ok(()); + let mut taken = 0; + while let Some(&page) = pages.get(taken) { + let Some(img) = ready.remove(&taken) else { + match rx.recv() { + Ok((i, img)) => { + ready.insert(i, img); + } + Err(_) => { + result = Err(format!("page {}: the export stopped unexpectedly", page + 1)); + break; + } + } + continue; + }; + if let Err(e) = img.and_then(|img| sink(page, img)) { + result = Err(e); + break; + } + taken += 1; + *handed_over.0.lock().unwrap_or_else(PoisonError::into_inner) = taken; + handed_over.1.notify_all(); + } + drop(stopper); + // Joined here, so a worker that panicked outside a page is not re-raised by the scope. + for h in handles { + let _ = h.join(); + } + result + }) + } + + /// How many pages [`Exporter::images`] draws at once: one per core but one, up to + /// [`MAX_IMAGE_WORKERS`], as many as [`IMAGE_MEMORY`] holds of the largest page, and one + /// when there is nothing to share or no threads (wasm). + fn image_workers(&self, pages: &[usize], dpi: f64) -> usize { + if cfg!(target_arch = "wasm32") || pages.len() < 2 { + return 1; + } + // One core is left for the interface, which keeps drawing while an export runs. + let cores = std::thread::available_parallelism().map_or(1, std::num::NonZeroUsize::get).saturating_sub(1).min(MAX_IMAGE_WORKERS); + // The raster (RGBA), the RGB copy the encoders take, and room for the encoded file. + let largest = pages + .iter() + .filter_map(|p| { + let (w, h) = *self.sizes.get(*p)?; + let k = self.dpi_used(*p, dpi) / 72.0; + Some((f64::from(w) * k).ceil() * (f64::from(h) * k).ceil() * 8.0) + }) + .fold(0.0, f64::max); + // A float-to-integer cast saturates (and NaN is 0). + let by_memory = if largest > 0.0 { (IMAGE_MEMORY / largest) as usize } else { cores }; + cores.min(by_memory).min(pages.len()).max(1) } /// The reading-order text of a page. diff --git a/crates/engine/src/open.rs b/crates/engine/src/open.rs index d8950d1d6d..58bc8327e2 100644 --- a/crates/engine/src/open.rs +++ b/crates/engine/src/open.rs @@ -25,6 +25,17 @@ pub struct PreparedDocument { document: Document, } +struct DocumentOpenData<'a> { + name: String, + path: Option, + bytes: Arc>, + info: DocInfo, + structure: Result, Box>, + render_password: Option, + password: Option<&'a str>, + xfa: Option, +} + impl OpenContext { /// Prepare a document without mutating the session that supplied this context. pub fn prepare_open( @@ -241,7 +252,8 @@ impl Session { }; // XFA notes survive the document being re-read after edits. let xfa_warnings: Vec = if info.xfa.is_some() { info.warnings.clone() } else { Vec::new() }; - let mut document = Self::build_document(&context.trust, name, path, bytes, info, cos, render_password, password, xfa); + let mut document = + Self::build_document(&context.trust, DocumentOpenData { name, path, bytes, info, structure: cos, render_password, password, xfa }); // A script that ran away on open turns the form's scripts off for this document. document.xfa_template = if ran_away { None } else { xfa_template }; document.js_output.append(script_output); @@ -254,18 +266,8 @@ impl Session { } /// The last step of opening: build the document record and register it. - #[allow(clippy::too_many_arguments)] - fn build_document( - trust: &Arc, - name: String, - path: Option, - bytes: Arc>, - mut info: DocInfo, - cos: Result, Box>, - render_password: Option, - password: Option<&str>, - xfa: Option, - ) -> Document { + fn build_document(trust: &Arc, data: DocumentOpenData<'_>) -> Document { + let DocumentOpenData { name, path, bytes, mut info, structure: cos, render_password, password, xfa } = data; let config = RenderConfig { password: render_password.as_deref().map(Arc::from), ..Default::default() }; let (mut editor, read_only_reason) = match cos { Ok(Ok(cos)) => { diff --git a/crates/engine/src/session/editing.rs b/crates/engine/src/session/editing.rs index 9b1a8340a5..f8d5648a2d 100644 --- a/crates/engine/src/session/editing.rs +++ b/crates/engine/src/session/editing.rs @@ -1,4 +1,11 @@ -use super::*; +#[cfg(test)] +use super::check_refresh_panic; +use super::{ + Arc, DocId, Document, Edit, EditCtx, EditError, Label, MAX_UNDO, ObjectKind, OnceLock, RenderPool, SaveOptions, Scope, Session, + XFA_REMOVED_PREFIX, XFA_SCRIPTS_OFF, check_permission, comment_list, display_bytes, guard, info_fields, inspect, js, keys_after, note_warnings, + render_threads, run_edit, scan_colours, scope_of, shown_under_redactions, signatures_of, sync_xfa_state, undrawn_notices, uses_scripts, + write_incremental, xfa, xfa_sync_datasets, +}; impl Session { /// Apply an edit. On success the previous state is undoable and the view data is refreshed. diff --git a/crates/engine/src/session/files.rs b/crates/engine/src/session/files.rs index 6d4e11d390..1e8cd9b08a 100644 --- a/crates/engine/src/session/files.rs +++ b/crates/engine/src/session/files.rs @@ -1,4 +1,8 @@ -use super::*; +use super::{ + Arc, CombineSource, Combined, DataFormat, DocId, EditError, Hidden, ImageResolution, LOW_RESOLUTION_PRINT_DPI, OptimizeReport, SaveOptions, + Session, SourceKind, SplitPart, decode_text, guard, open_source, open_source_with, optimize, print, print_raster, set_default_layer_state, + source_kind, writable, write_full, +}; impl Session { /// The page count of another PDF (Replace Pages, Insert Pages dialogs). diff --git a/crates/engine/src/session/save.rs b/crates/engine/src/session/save.rs index 23994aee37..d4156a2eb1 100644 --- a/crates/engine/src/session/save.rs +++ b/crates/engine/src/session/save.rs @@ -1,4 +1,7 @@ -use super::*; +use super::{ + Arc, DocId, EditError, Keys, OpenError, RecoverySnapshot, RenderPool, SaveOptions, Session, SignOptions, TrustStore, display_bytes, guard, + render_threads, signatures_of, writable, write_full, write_incremental, xfa_sync_datasets, +}; impl Session { /// The bytes to write for Save: an incremental update of the file as opened/last saved, diff --git a/crates/engine/src/session/view.rs b/crates/engine/src/session/view.rs index cef539189a..055437f562 100644 --- a/crates/engine/src/session/view.rs +++ b/crates/engine/src/session/view.rs @@ -1,4 +1,7 @@ -use super::*; +use super::{ + Arc, BookmarkPage, BookmarkRow, DocId, Document, EditError, LayerOp, OpenError, ReadingColors, RenderConfig, RenderPool, Session, SummarySort, + apply_layer_state, comment_summary, local_utc_offset, outline_rows, parse_ymd, render_threads, use_layer_choices, +}; impl Session { pub fn new() -> Self { diff --git a/crates/engine/src/tests.rs b/crates/engine/src/tests.rs index c622af21b4..14a61b2633 100644 --- a/crates/engine/src/tests.rs +++ b/crates/engine/src/tests.rs @@ -3068,7 +3068,12 @@ fn secondary_indexes_load_once_and_follow_edit_scopes() { assert!(doc.links().is_empty()); assert_eq!(secondary_scan_counts(), (1, 1), "repeated reads reuse the link list"); } + metadata_and_comment_edits_keep_the_indexes(&mut session, id); + link_edits_rebuild_only_the_link_list(&mut session, id); + content_and_marker_edits_rebuild_the_markers(&mut session, id); +} +fn metadata_and_comment_edits_keep_the_indexes(session: &mut Session, id: DocId) { session.apply(id, Edit::SetInfo { key: "Title".into(), value: "Changed".into() }).unwrap(); assert!(session.get(id).unwrap().links().is_empty()); assert!(session.get(id).unwrap().marks().is_empty()); @@ -3077,7 +3082,9 @@ fn secondary_indexes_load_once_and_follow_edit_scopes() { session.apply(id, rect_comment(0, [20.0, 20.0, 60.0, 60.0])).unwrap(); assert!(session.get(id).unwrap().links().is_empty()); assert_eq!(secondary_scan_counts(), (1, 2), "comment edits invalidate the annotation-position link index"); +} +fn link_edits_rebuild_only_the_link_list(session: &mut Session, id: DocId) { session .apply( id, @@ -3101,7 +3108,9 @@ fn secondary_indexes_load_once_and_follow_edit_scopes() { session.apply(id, Edit::DeleteAnnotation { page: 0, index: 0 }).unwrap(); assert_eq!(session.get(id).unwrap().links()[0].index, 0, "deleting an earlier annotation shifts link indexes"); assert_eq!(secondary_scan_counts(), (1, 6), "comment deletion rebuilds annotation-position indexes"); +} +fn content_and_marker_edits_rebuild_the_markers(session: &mut Session, id: DocId) { session .apply(id, Edit::AddText { page: 0, text: AddedText { rect: [20.0, 250.0, 100.0, 280.0], text: "Added".into(), ..Default::default() } }) .unwrap(); @@ -3410,6 +3419,70 @@ fn pages_export_as_png_jpeg_and_tiff() { assert_eq!((compression, predictor), (5, 1), "LZW, without a predictor"); } +/// Export ▸ Image draws several pages at once: each file is the one exporting that page alone +/// writes, handed over in the order asked for, whatever the number of pages drawn at once. +#[test] +fn pages_exported_at_once_are_the_files_each_page_exports_alone_in_order() { + use crate::export::{Exporter, ImageFormat}; + let (s, id) = session_with(12); + let pages = [3, 0, 11, 5, 5, 7, 1, 2, 10, 9, 8, 6, 4]; + for format in [ImageFormat::Png, ImageFormat::Jpeg { quality: 85 }, ImageFormat::Tiff] { + let alone: Vec<(usize, Vec)> = pages.iter().map(|&p| (p, Exporter::new(s.get(id).unwrap()).image(p, 96.0, format).unwrap())).collect(); + for workers in [1, 2, 4, 8] { + let mut got = Vec::new(); + let mut ex = Exporter::new(s.get(id).unwrap()); + ex.images_on(workers, &pages, 96.0, format, |p, img| { + got.push((p, img)); + Ok(()) + }) + .unwrap(); + assert!(got == alone, "{} with {workers} workers", format.label()); + } + let mut got = Vec::new(); + Exporter::new(s.get(id).unwrap()) + .images(&pages, 96.0, format, |p, img| { + got.push((p, img)); + Ok(()) + }) + .unwrap(); + assert!(got == alone, "{}", format.label()); + } +} + +/// A page that can't be exported, or a file that can't be written, stops the export there with +/// its error: every page before it is handed over, none after it. +#[test] +fn exporting_pages_at_once_stops_at_the_first_error() { + use crate::export::{Exporter, ImageFormat}; + let (s, id) = session_with(6); + for workers in [1, 4] { + let mut ex = Exporter::new(s.get(id).unwrap()); + let mut got = Vec::new(); + let result = ex.images_on(workers, &[0, 1, 99, 2, 3], 72.0, ImageFormat::Png, |p, _| { + got.push(p); + Ok(()) + }); + assert_eq!(result, Err("page 100 does not exist".to_string()), "{workers} workers"); + assert_eq!(got, [0, 1], "{workers} workers"); + + let mut got = Vec::new(); + let result = ex.images_on(workers, &[0, 1, 2, 3, 4, 5], 72.0, ImageFormat::Png, |p, _| { + got.push(p); + if p == 2 { Err("disk full".to_string()) } else { Ok(()) } + }); + assert_eq!(result, Err("disk full".to_string()), "{workers} workers"); + assert_eq!(got, [0, 1, 2], "{workers} workers"); + // The exporter is still usable afterwards. + assert!(ex.image(5, 72.0, ImageFormat::Png).is_ok()); + } + // A panicking sink stops the workers rather than leaving them waiting for it. + let mut ex = Exporter::new(s.get(id).unwrap()); + let panicked = std::panic::catch_unwind(std::panic::AssertUnwindSafe(|| { + ex.images_on(4, &[0, 1, 2, 3, 4, 5], 72.0, ImageFormat::Png, |p, _| if p == 1 { panic!("sink") } else { Ok(()) }) + })); + assert!(panicked.is_err()); +} + /// A TIFF's resolution unit (2 = inch) and its horizontal and vertical resolution. fn tiff_resolution(bytes: &[u8]) -> (u32, f64, f64) { use tiff::{decoder::ifd::Value, tags::Tag}; @@ -8042,7 +8115,12 @@ fn undo_and_redo_roll_back_on_a_refresh_panic_or_error() { // Redo now succeeds cleanly. assert_eq!(s.redo(id).unwrap().as_str(), "Rotate page"); assert_eq!(s.get(id).unwrap().info.pages[0].rotation, 90); + rolls_back_metadata_scope(&mut s, id); + rolls_back_protection_keys(&mut s, id); +} +/// Undo/redo of a metadata edit rolled back after a refresh panic. +fn rolls_back_metadata_scope(s: &mut Session, id: DocId) { // 5. Metadata scope: a panic after `doc.info.title` was written rolls back `info.title` and keeps `edit_notices`. s.apply(id, Edit::SetInfo { key: "Title".into(), value: "Draft".into() }).unwrap(); let notice = TextNotice { field: None, page: 0, ch: '☺', redrawn_elsewhere: false }; @@ -8060,7 +8138,10 @@ fn undo_and_redo_roll_back_on_a_refresh_panic_or_error() { assert_eq!(s.get(id).unwrap().info.title, None); assert_eq!(s.redo(id).unwrap().as_str(), "Change Title"); assert_eq!(s.get(id).unwrap().info.title.as_deref(), Some("Draft")); +} +/// Undo/redo of a protection edit rolled back after a refresh panic. +fn rolls_back_protection_keys(s: &mut Session, id: DocId) { // 6. Protection keys: undo/redo rollback restores `editor.keys` and `doc.password` before re-inspecting. let protect = Protection { open_password: Some("u".into()), permissions_password: Some("o".into()), ..Protection::default() }; s.apply(id, Edit::Protect(protect)).unwrap(); @@ -8656,69 +8737,69 @@ fn pdf_with_annots(annots: &[&[u8]]) -> Vec { bytes } -/// ISO 32000-2 Table 224 (`/NeedAppearances`) and Table 192 (`/MK /CA`): a form that leaves its -/// appearances to the viewer shows its check boxes and radio buttons drawn from `/MK`, over the -/// filled squares the file carries: a checked box its check mark (ZapfDingbats `4`), an unchecked -/// one its empty border, a radio button its dot (`l`), on screen and printed as an image. Without -/// `/NeedAppearances` the file's own squares show. Saving writes the file as it was. -#[test] -fn need_appearances_buttons_are_displayed_from_their_captions() { - let pdf = |need: bool| { - let flag = if need { "/NeedAppearances true " } else { "" }; - format!( - "%PDF-1.7\n\ - 1 0 obj << /Type /Catalog /Pages 2 0 R /AcroForm 4 0 R >> endobj\n\ - 2 0 obj << /Type /Pages /Kids [3 0 R] /Count 1 >> endobj\n\ - 3 0 obj << /Type /Page /Parent 2 0 R /MediaBox [0 0 400 200] /Annots [6 0 R 7 0 R 8 0 R] >> endobj\n\ - 4 0 obj << /Fields [6 0 R 7 0 R 8 0 R] {flag}/DA (/Helv 0 Tf 0 g) /DR << /Font << /Helv 5 0 R >> >> >> endobj\n\ - 5 0 obj << /Type /Font /Subtype /Type1 /BaseFont /Helvetica /Encoding /WinAnsiEncoding >> endobj\n\ - 6 0 obj << /Type /Annot /Subtype /Widget /FT /Btn /T (on) /V /Yes /AS /Yes /DA (/Helv 0 Tf 0 g) /MK << /BC [0 0 0] /CA (4) >> /Rect [20 100 60 140] /F 4 /P 3 0 R /AP << /N << /Yes 9 0 R /Off 9 0 R >> >> >> endobj\n\ - 7 0 obj << /Type /Annot /Subtype /Widget /FT /Btn /T (off) /V /Off /AS /Off /DA (/Helv 0 Tf 0 g) /MK << /BC [0 0 0] /CA (4) >> /Rect [100 100 140 140] /F 4 /P 3 0 R /AP << /N << /Yes 9 0 R /Off 9 0 R >> >> >> endobj\n\ - 8 0 obj << /Type /Annot /Subtype /Widget /FT /Btn /Ff 32768 /T (radio) /V /B /AS /B /DA (/Helv 0 Tf 0 g) /MK << /BC [0 0 0] /CA (l) >> /Rect [180 100 220 140] /F 4 /P 3 0 R /AP << /N << /B 9 0 R /Off 9 0 R >> >> >> endobj\n\ - 9 0 obj << /Type /XObject /Subtype /Form /BBox [0 0 40 40] /Length 18 >> stream\n0 g 4 4 32 32 re f\nendstream endobj\n\ - trailer << /Root 1 0 R >>\n%%EOF" - ) - .into_bytes() - }; - let render = |bytes: Arc>| { - let mut r = pdfcraft_render::PageRenderer::new(bytes, pdfcraft_render::RenderConfig::default()); - r.render(pdfcraft_render::RenderRequest { page: 0, scale: 1.0, ..Default::default() }) - }; - // Dark pixels of the page (drawn at scale 1, 400 x 200) in the user-space box x0..x1, y0..y1. - let ink = |page: &pdfcraft_render::RenderedPage, (x0, y0, x1, y1): (u32, u32, u32, u32)| { - let (px, _) = page.rgba.as_chunks::<4>(); - (200 - y1..200 - y0) - .flat_map(|y| (x0..x1).map(move |x| (x, y))) - .filter(|&(x, y)| px.get((y * page.width + x) as usize).is_some_and(|p| p[0] < 128 && p[1] < 128 && p[2] < 128)) - .count() - }; - // In a widget whose lower-left corner is (x, y): its whole inside, the top-left of its inside - // (where a check mark leaves the box empty), and the lower-left corner (outside a dot). - let inside = |x: u32, y: u32| (x + 6, y + 6, x + 34, y + 34); - let top_left = |x: u32, y: u32| (x + 6, y + 26, x + 14, y + 34); - let corner = |x: u32, y: u32| (x + 5, y + 5, x + 9, y + 9); - let mut s = Session::new(); - let id = s.open("form.pdf", None, Arc::new(pdf(true)), None).unwrap(); - let shown = render(s.get(id).unwrap().display.clone()); - let raster = pdfcraft_print::Raster { dpi: 72.0, grayscale: false }; - let pictures = crate::print_raster::rasterize(s.get(id).unwrap(), &[0], &raster, pdfcraft_print::Content::Document).unwrap(); - let printed = render(Arc::new(pictures)); - for (page, how) in [(&shown, "shown"), (&printed, "printed")] { - let (check, check_corner) = (ink(page, inside(20, 100)), ink(page, top_left(20, 100))); - assert!(check > 100 && check < 600, "{how}: a check mark, not the 28 x 28 square: {check}"); - assert_eq!(check_corner, 0, "{how}: the check mark leaves the top left empty"); - assert_eq!(ink(page, inside(100, 100)), 0, "{how}: the unchecked box is empty"); - assert!(ink(page, (100, 100, 140, 102)) > 30, "{how}: and keeps its border"); - let dot = ink(page, (188, 108, 212, 132)); - assert!(dot > 300 && ink(page, corner(180, 100)) == 0, "{how}: the radio button's dot: {dot}"); - } - let saved = s.save_bytes(id).unwrap(); - assert!(saved.windows(18).any(|w| w == b"0 g 4 4 32 32 re f"), "the file keeps its own appearances"); - - // Without /NeedAppearances the file's filled squares are shown. - let id = s.open("plain.pdf", None, Arc::new(pdf(false)), None).unwrap(); - let shown = render(s.get(id).unwrap().display.clone()); - for x in [20, 100, 180] { - assert!(ink(&shown, inside(x, 100)) > 700, "the file's square at {x}"); - } -} +/// ISO 32000-2 Table 224 (`/NeedAppearances`) and Table 192 (`/MK /CA`): a form that leaves its +/// appearances to the viewer shows its check boxes and radio buttons drawn from `/MK`, over the +/// filled squares the file carries: a checked box its check mark (ZapfDingbats `4`), an unchecked +/// one its empty border, a radio button its dot (`l`), on screen and printed as an image. Without +/// `/NeedAppearances` the file's own squares show. Saving writes the file as it was. +#[test] +fn need_appearances_buttons_are_displayed_from_their_captions() { + let pdf = |need: bool| { + let flag = if need { "/NeedAppearances true " } else { "" }; + format!( + "%PDF-1.7\n\ + 1 0 obj << /Type /Catalog /Pages 2 0 R /AcroForm 4 0 R >> endobj\n\ + 2 0 obj << /Type /Pages /Kids [3 0 R] /Count 1 >> endobj\n\ + 3 0 obj << /Type /Page /Parent 2 0 R /MediaBox [0 0 400 200] /Annots [6 0 R 7 0 R 8 0 R] >> endobj\n\ + 4 0 obj << /Fields [6 0 R 7 0 R 8 0 R] {flag}/DA (/Helv 0 Tf 0 g) /DR << /Font << /Helv 5 0 R >> >> >> endobj\n\ + 5 0 obj << /Type /Font /Subtype /Type1 /BaseFont /Helvetica /Encoding /WinAnsiEncoding >> endobj\n\ + 6 0 obj << /Type /Annot /Subtype /Widget /FT /Btn /T (on) /V /Yes /AS /Yes /DA (/Helv 0 Tf 0 g) /MK << /BC [0 0 0] /CA (4) >> /Rect [20 100 60 140] /F 4 /P 3 0 R /AP << /N << /Yes 9 0 R /Off 9 0 R >> >> >> endobj\n\ + 7 0 obj << /Type /Annot /Subtype /Widget /FT /Btn /T (off) /V /Off /AS /Off /DA (/Helv 0 Tf 0 g) /MK << /BC [0 0 0] /CA (4) >> /Rect [100 100 140 140] /F 4 /P 3 0 R /AP << /N << /Yes 9 0 R /Off 9 0 R >> >> >> endobj\n\ + 8 0 obj << /Type /Annot /Subtype /Widget /FT /Btn /Ff 32768 /T (radio) /V /B /AS /B /DA (/Helv 0 Tf 0 g) /MK << /BC [0 0 0] /CA (l) >> /Rect [180 100 220 140] /F 4 /P 3 0 R /AP << /N << /B 9 0 R /Off 9 0 R >> >> >> endobj\n\ + 9 0 obj << /Type /XObject /Subtype /Form /BBox [0 0 40 40] /Length 18 >> stream\n0 g 4 4 32 32 re f\nendstream endobj\n\ + trailer << /Root 1 0 R >>\n%%EOF" + ) + .into_bytes() + }; + let render = |bytes: Arc>| { + let mut r = pdfcraft_render::PageRenderer::new(bytes, pdfcraft_render::RenderConfig::default()); + r.render(pdfcraft_render::RenderRequest { page: 0, scale: 1.0, ..Default::default() }) + }; + // Dark pixels of the page (drawn at scale 1, 400 x 200) in the user-space box x0..x1, y0..y1. + let ink = |page: &pdfcraft_render::RenderedPage, (x0, y0, x1, y1): (u32, u32, u32, u32)| { + let (px, _) = page.rgba.as_chunks::<4>(); + (200 - y1..200 - y0) + .flat_map(|y| (x0..x1).map(move |x| (x, y))) + .filter(|&(x, y)| px.get((y * page.width + x) as usize).is_some_and(|p| p[0] < 128 && p[1] < 128 && p[2] < 128)) + .count() + }; + // In a widget whose lower-left corner is (x, y): its whole inside, the top-left of its inside + // (where a check mark leaves the box empty), and the lower-left corner (outside a dot). + let inside = |x: u32, y: u32| (x + 6, y + 6, x + 34, y + 34); + let top_left = |x: u32, y: u32| (x + 6, y + 26, x + 14, y + 34); + let corner = |x: u32, y: u32| (x + 5, y + 5, x + 9, y + 9); + let mut s = Session::new(); + let id = s.open("form.pdf", None, Arc::new(pdf(true)), None).unwrap(); + let shown = render(s.get(id).unwrap().display.clone()); + let raster = pdfcraft_print::Raster { dpi: 72.0, grayscale: false }; + let pictures = crate::print_raster::rasterize(s.get(id).unwrap(), &[0], &raster, pdfcraft_print::Content::Document).unwrap(); + let printed = render(Arc::new(pictures)); + for (page, how) in [(&shown, "shown"), (&printed, "printed")] { + let (check, check_corner) = (ink(page, inside(20, 100)), ink(page, top_left(20, 100))); + assert!(check > 100 && check < 600, "{how}: a check mark, not the 28 x 28 square: {check}"); + assert_eq!(check_corner, 0, "{how}: the check mark leaves the top left empty"); + assert_eq!(ink(page, inside(100, 100)), 0, "{how}: the unchecked box is empty"); + assert!(ink(page, (100, 100, 140, 102)) > 30, "{how}: and keeps its border"); + let dot = ink(page, (188, 108, 212, 132)); + assert!(dot > 300 && ink(page, corner(180, 100)) == 0, "{how}: the radio button's dot: {dot}"); + } + let saved = s.save_bytes(id).unwrap(); + assert!(saved.windows(18).any(|w| w == b"0 g 4 4 32 32 re f"), "the file keeps its own appearances"); + + // Without /NeedAppearances the file's filled squares are shown. + let id = s.open("plain.pdf", None, Arc::new(pdf(false)), None).unwrap(); + let shown = render(s.get(id).unwrap().display.clone()); + for x in [20, 100, 180] { + assert!(ink(&shown, inside(x, 100)) > 700, "the file's square at {x}"); + } +} diff --git a/crates/export/src/as_docx.rs b/crates/export/src/as_docx.rs index d8fb84f7d4..ab7451dc0e 100644 --- a/crates/export/src/as_docx.rs +++ b/crates/export/src/as_docx.rs @@ -1,6 +1,6 @@ +use super::Zip; use super::as_html::esc; use super::layout::{Image, Item, Page, Table, body_size, items}; -use super::*; /// A colour's 8-bit sRGB components (NaN and out-of-range values clamp; NaN reads as 0). pub(crate) fn rgb8(c: [f64; 3]) -> [u8; 3] { diff --git a/crates/export/src/as_rtf.rs b/crates/export/src/as_rtf.rs index d7495df135..61585d82fb 100644 --- a/crates/export/src/as_rtf.rs +++ b/crates/export/src/as_rtf.rs @@ -1,7 +1,7 @@ use super::as_docx::rgb8; use super::as_html::allowed; use super::layout::{Block, Item, Page, count_lookup_steps, items}; -use super::*; +use std::collections::HashMap; fn rtf_text(s: &str) -> String { let mut o = String::new(); diff --git a/crates/export/src/layout.rs b/crates/export/src/layout.rs index 8a06050898..d1d074ac61 100644 --- a/crates/export/src/layout.rs +++ b/crates/export/src/layout.rs @@ -1,4 +1,4 @@ -use super::*; +use std::collections::HashMap; /// A paragraph of a page. #[derive(Clone, Debug, PartialEq)] diff --git a/crates/export/src/lib.rs b/crates/export/src/lib.rs index cf32ea7930..5275b02439 100644 --- a/crates/export/src/lib.rs +++ b/crates/export/src/lib.rs @@ -10,8 +10,6 @@ #![deny(clippy::unwrap_used, clippy::expect_used, clippy::panic, clippy::unimplemented, clippy::todo, clippy::unreachable)] -use std::collections::HashMap; - mod pptx; mod zip; diff --git a/crates/forms/src/actions.rs b/crates/forms/src/actions.rs index 5eb57c6c1b..5ebe3269cc 100644 --- a/crates/forms/src/actions.rs +++ b/crates/forms/src/actions.rs @@ -262,17 +262,21 @@ fn write(doc: &mut Document, a: &FieldAction, pages: &[pdfcraft_cos::ObjRef]) -> /// Rewrite one trigger of a widget to `new` (`None` clears it), given the `old` value read from /// the widget. `aa` and `a_entry` are the widget's `/AA` dict and `/A` entry, updated in place. -#[allow(clippy::too_many_arguments)] +struct TriggerUpdate<'a> { + trigger: Trigger, + replacement: Option<&'a FieldAction>, + previous: Option, +} + fn replace_trigger( doc: &mut Document, pages: &[pdfcraft_cos::ObjRef], scripts: &mut pdfcraft_cos::DecodeBudget, - t: Trigger, - new: Option<&FieldAction>, - old: Option, + update: TriggerUpdate<'_>, aa: &mut Dict, a_entry: &mut Option, ) -> Result<(), FormError> { + let TriggerUpdate { trigger: t, replacement: new, previous: old } = update; let old_action = old.as_ref().and_then(|o| read(doc, o, pages, scripts)); if new.is_some() && new == old_action.as_ref() { return Ok(()); @@ -322,7 +326,7 @@ pub fn set_field_actions(doc: &mut Document, name: &str, actions: &[(Trigger, Fi None => wd.get(b"A").cloned().or_else(|| aa.get(b"U").cloned()), Some(k) => aa.get(k).cloned(), }; - replace_trigger(doc, &pages, &mut scripts, t, new, old, &mut aa, &mut a_entry)?; + replace_trigger(doc, &pages, &mut scripts, TriggerUpdate { trigger: t, replacement: new, previous: old }, &mut aa, &mut a_entry)?; } doc.update_dict(w.obj, |d| { match &a_entry { diff --git a/crates/forms/src/af/script.rs b/crates/forms/src/af/script.rs index c807f2d7d7..9aed297b45 100644 --- a/crates/forms/src/af/script.rs +++ b/crates/forms/src/af/script.rs @@ -1,6 +1,6 @@ use super::calc::{js_tokens, notation_js, notation_range}; use super::format::{DATE_PRESETS, TIME_PRESETS}; -use super::*; +use super::{CalcOp, Calculate, Format, Validate}; // ── parsing scripts ───────────────────────────────────────────────────────────────────────── diff --git a/crates/forms/src/appearances.rs b/crates/forms/src/appearances.rs index d035feb4ef..64569fa3ca 100644 --- a/crates/forms/src/appearances.rs +++ b/crates/forms/src/appearances.rs @@ -1,6 +1,6 @@ use super::read::{acroform, fields}; use super::values::merged_appearance; -use super::*; +use super::{Dict, Document, FieldKind, ObjRef, Object, Widget, appearance, name_bytes}; /// Whether the form asks viewers to draw its fields' appearances themselves (`/NeedAppearances`). pub fn need_appearances(doc: &Document) -> bool { diff --git a/crates/forms/src/author/edit.rs b/crates/forms/src/author/edit.rs index dc7d91d4fc..d61cfe28f2 100644 --- a/crates/forms/src/author/edit.rs +++ b/crates/forms/src/author/edit.rs @@ -1,6 +1,6 @@ use super::look::{BorderStyle, da_string, patch_da, patch_widget_look, redraw_widgets}; use super::tree::{attach, check_place, child_named, clash, detach, ensure_form, inherited, name_parts, own_inherited}; -use super::*; +use super::{Dict, Document, Field, FieldKind, FieldProps, FormError, MIN_FIELD_SIDE, ObjRef, Object, PdfString, fields, flags, invalid}; /// Swap width and height, keeping the center. `None` when that is not a usable widget. fn swapped_around_center(r: [f64; 4]) -> Option<[f64; 4]> { @@ -70,59 +70,7 @@ pub fn set_props(doc: &mut Document, name: &str, props: &FieldProps) -> Result own, - _ => n, - }; - if n.contains('.') { - // A full name: the field moves under the parent fields it names (#2696). - let parts = name_parts(n)?; - if let Some(why) = all.iter().filter(|x| x.obj != f.obj).find_map(|x| clash(n, &x.name)) { - return invalid(why); - } - let af = ensure_form(doc)?; - // Checked before anything changes, so a refused move leaves the field as it was. - let add = inherited(doc, f.obj); - check_place(doc, af, f.obj, &parts, &add)?; - // From here a failure (a write that `check_place` couldn't foresee) would leave the - // field half moved in `doc`. The engine runs every edit on a copy of the document and - // keeps it only when the edit succeeds (`Session::apply`), so the open document never - // sees that. - own_inherited(doc, f.obj, &add)?; - detach(doc, f.obj)?; - attach(doc, af, f.obj, &parts)?; - new_name = n.to_string(); - } else { - if n.is_empty() { - return invalid("field names can't be empty"); - } - // Rename the terminal part (the field's own /T). The parents' part stays, so the name - // that must be free is the full one: `MASTER.a` renamed to `b` takes `MASTER.b` (ISO - // 32000-2 §12.7.4.2). The field itself is no clash when it keeps its own name. - let prefix = f.name.rsplit_once('.').map(|(p, _)| format!("{p}.")).unwrap_or_default(); - new_name = format!("{prefix}{n}"); - if let Some(why) = all.iter().filter(|x| x.obj != f.obj).find_map(|x| clash(&new_name, &x.name)) { - return invalid(why); - } - // A node of that name beside it that isn't a terminal field, such as a parent - // field left empty by a move. - let af = ensure_form(doc)?; - let parent = doc.get(f.obj).as_dict().and_then(|d| d.reference(b"Parent")); - if child_named(doc, af, parent, n).is_some_and(|r| r != f.obj) { - return invalid(format!("a field named {new_name:?} already exists")); - } - doc.update_dict(f.obj, |d| d.set(b"T".to_vec(), PdfString::text(n)))?; - } - // Calculations read the field by its new name, unless another field keeps the old one. - if all.iter().filter(|x| x.name == f.name).count() == 1 { - rename_in_calculations(doc, &all, &f.name, &new_name)?; - } - } + let new_name = rename_field(doc, &all, &f, name, props)?; // The new default appearance when the size or the look changes. let size = props.font_size.unwrap_or_else(|| crate::appearance::parse_da(&f.da).size); let new_da = match &props.look { @@ -248,51 +196,7 @@ pub fn set_props(doc: &mut Document, name: &str, props: &FieldProps) -> Result mk.set(b"BC".to_vec(), arr(c)), - None => { - mk.remove(b"BC"); - } - } - match l.fill { - Some(c) => mk.set(b"BG".to_vec(), arr(c)), - None => { - mk.remove(b"BG"); - } - } - d.set(b"MK".to_vec(), Object::Dict(mk)); - let mut bs = Dict::new(); - bs.set(b"W".to_vec(), Object::Real(l.width.clamp(0.0, 12.0))); - bs.set(b"S".to_vec(), Object::name(l.style.code())); - if l.style == BorderStyle::Dashed { - bs.set(b"D".to_vec(), Object::Array(vec![Object::Int(3)])); - } - d.set(b"BS".to_vec(), Object::Dict(bs)); - })?; - } - } - if let Some(style) = props.check_style { - for w in &f.widgets { - // Resolved first: an indirect /MK keeps its colours. - let mut mk = doc.get(w.obj).as_dict().and_then(|d| d.get(b"MK").map(|m| doc.resolve(m).as_dict().cloned())).flatten().unwrap_or_default(); - mk.set(b"CA".to_vec(), PdfString::text(style.code())); - doc.update_dict(w.obj, |d| d.set(b"MK".to_vec(), Object::Dict(mk)))?; - } - } - if let Some((wi, r)) = props.rect { - let w = f.widgets.get(wi).ok_or_else(|| FormError::Invalid(format!("{name} has no widget {}", wi + 1)))?; - let r = [r[0].min(r[2]), r[1].min(r[3]), r[0].max(r[2]), r[1].max(r[3])]; - if !r.iter().all(|v| v.is_finite()) || r[2] - r[0] < MIN_FIELD_SIDE || r[3] - r[1] < MIN_FIELD_SIDE { - return invalid("the field is too small"); - } - doc.update_dict(w.obj, |d| d.set(b"Rect".to_vec(), Object::Array(r.iter().map(|v| Object::Real(*v)).collect())))?; - } + apply_widget_style_props(doc, &f, name, props)?; if props.format.is_some() || props.validate.is_some() || props.calculate.is_some() { if !matches!(f.kind, FieldKind::Text | FieldKind::Combo) { return invalid("only text fields and drop-down lists have format, validate and calculate scripts"); @@ -341,6 +245,127 @@ pub fn set_props(doc: &mut Document, name: &str, props: &FieldProps) -> Result Result { + let mut new_name = name.to_string(); + if let Some(n) = props.name.as_deref().map(str::trim).filter(|n| *n != f.name) { + // A full name under the same parents only renames the field's own part (the editor + // shows nested fields by their full name): it isn't moved, so it keeps its place and + // goes on inheriting from its parents. + let n = match (n.rsplit_once('.'), f.name.rsplit_once('.')) { + (Some((parents, own)), Some((current, _))) if parents == current => own, + _ => n, + }; + if n.contains('.') { + // A full name: the field moves under the parent fields it names (#2696). + let parts = name_parts(n)?; + if let Some(why) = all.iter().filter(|x| x.obj != f.obj).find_map(|x| clash(n, &x.name)) { + return invalid(why); + } + let af = ensure_form(doc)?; + // Checked before anything changes, so a refused move leaves the field as it was. + let add = inherited(doc, f.obj); + check_place(doc, af, f.obj, &parts, &add)?; + // From here a failure (a write that `check_place` couldn't foresee) would leave the + // field half moved in `doc`. The engine runs every edit on a copy of the document and + // keeps it only when the edit succeeds (`Session::apply`), so the open document never + // sees that. + own_inherited(doc, f.obj, &add)?; + detach(doc, f.obj)?; + attach(doc, af, f.obj, &parts)?; + new_name = n.to_string(); + } else { + if n.is_empty() { + return invalid("field names can't be empty"); + } + // Rename the terminal part (the field's own /T). The parents' part stays, so the name + // that must be free is the full one: `MASTER.a` renamed to `b` takes `MASTER.b` (ISO + // 32000-2 §12.7.4.2). The field itself is no clash when it keeps its own name. + let prefix = f.name.rsplit_once('.').map(|(p, _)| format!("{p}.")).unwrap_or_default(); + new_name = format!("{prefix}{n}"); + if let Some(why) = all.iter().filter(|x| x.obj != f.obj).find_map(|x| clash(&new_name, &x.name)) { + return invalid(why); + } + // A node of that name beside it that isn't a terminal field, such as a parent + // field left empty by a move. + let af = ensure_form(doc)?; + let parent = doc.get(f.obj).as_dict().and_then(|d| d.reference(b"Parent")); + if child_named(doc, af, parent, n).is_some_and(|r| r != f.obj) { + return invalid(format!("a field named {new_name:?} already exists")); + } + doc.update_dict(f.obj, |d| d.set(b"T".to_vec(), PdfString::text(n)))?; + } + // Calculations read the field by its new name, unless another field keeps the old one. + if all.iter().filter(|x| x.name == f.name).count() == 1 { + rename_in_calculations(doc, all, &f.name, &new_name)?; + } + } + Ok(new_name) +} + +fn apply_widget_style_props(doc: &mut Document, f: &Field, name: &str, props: &FieldProps) -> Result<(), FormError> { + if let Some(l) = &props.look { + let arr = |c: [f64; 3]| Object::Array(c.iter().map(|v| Object::Real(v.clamp(0.0, 1.0))).collect()); + for w in &f.widgets { + // Resolved first: an indirect /MK keeps its mark, rotation and other entries. + let mut mk = doc.get(w.obj).as_dict().and_then(|d| d.get(b"MK").map(|m| doc.resolve(m).as_dict().cloned())).flatten().unwrap_or_default(); + doc.update_dict(w.obj, |d| { + match l.border { + Some(c) => mk.set(b"BC".to_vec(), arr(c)), + None => { + mk.remove(b"BC"); + } + } + match l.fill { + Some(c) => mk.set(b"BG".to_vec(), arr(c)), + None => { + mk.remove(b"BG"); + } + } + d.set(b"MK".to_vec(), Object::Dict(mk)); + let mut bs = Dict::new(); + bs.set(b"W".to_vec(), Object::Real(l.width.clamp(0.0, 12.0))); + bs.set(b"S".to_vec(), Object::name(l.style.code())); + if l.style == BorderStyle::Dashed { + bs.set(b"D".to_vec(), Object::Array(vec![Object::Int(3)])); + } + d.set(b"BS".to_vec(), Object::Dict(bs)); + })?; + } + } + if let Some(style) = props.check_style { + for w in &f.widgets { + // Resolved first: an indirect /MK keeps its colours. + let mut mk = doc.get(w.obj).as_dict().and_then(|d| d.get(b"MK").map(|m| doc.resolve(m).as_dict().cloned())).flatten().unwrap_or_default(); + mk.set(b"CA".to_vec(), PdfString::text(style.code())); + doc.update_dict(w.obj, |d| d.set(b"MK".to_vec(), Object::Dict(mk)))?; + } + } + if let Some((wi, r)) = props.rect { + let w = f.widgets.get(wi).ok_or_else(|| FormError::Invalid(format!("{name} has no widget {}", wi + 1)))?; + let r = [r[0].min(r[2]), r[1].min(r[3]), r[0].max(r[2]), r[1].max(r[3])]; + if !r.iter().all(|v| v.is_finite()) || r[2] - r[0] < MIN_FIELD_SIDE || r[3] - r[1] < MIN_FIELD_SIDE { + return invalid("the field is too small"); + } + doc.update_dict(w.obj, |d| d.set(b"Rect".to_vec(), Object::Array(r.iter().map(|v| Object::Real(*v)).collect())))?; + } + Ok(()) +} + +fn apply_late_widget_props( + doc: &mut Document, + f: &Field, + props: &FieldProps, + new_da: &str, + rotated_rect: Option>, +) -> Result, FormError> { // A complete look replaces widget /DA overrides. Partial changes were patched above // against each override, including size-only changes that keep its font and colour. if props.look.is_some() { @@ -348,7 +373,7 @@ pub fn set_props(doc: &mut Document, name: &str, props: &FieldProps) -> Result Result Dict { let mut d = Dict::new(); diff --git a/crates/forms/src/author/look.rs b/crates/forms/src/author/look.rs index 6044bdc70b..23661ed70a 100644 --- a/crates/forms/src/author/look.rs +++ b/crates/forms/src/author/look.rs @@ -1,4 +1,4 @@ -use super::*; +use super::{Dict, Document, Field, FieldKind, FormError, ObjRef, Object, Stream, Widget, appearance, fields, invalid, rgb}; /// The Appearance tab: borders, colours and text. #[derive(Clone, Copy, Debug, PartialEq)] diff --git a/crates/forms/src/author/tree.rs b/crates/forms/src/author/tree.rs index 4f7db4d8e1..d8ca67ffb7 100644 --- a/crates/forms/src/author/tree.rs +++ b/crates/forms/src/author/tree.rs @@ -1,4 +1,4 @@ -use super::*; +use super::{Dict, Document, Field, FormError, ObjRef, Object, PdfString, invalid}; /// The AcroForm dictionary's reference, creating the form (with `/Helv` in `/DR`) if needed. pub(crate) fn ensure_form(doc: &mut Document) -> Result { diff --git a/crates/forms/src/read.rs b/crates/forms/src/read.rs index a962af91bd..e689c0e813 100644 --- a/crates/forms/src/read.rs +++ b/crates/forms/src/read.rs @@ -1,5 +1,5 @@ use super::tab_order::rank_tabs; -use super::*; +use super::{DecodeBudget, Dict, Document, Field, FieldKind, ObjRef, Object, PdfString, Widget, af, appearance, flags, name_text, text_of}; /// At most this many `/State` entries of a set-layer-visibility action are read. const MAX_LAYER_STATE: usize = 1024; diff --git a/crates/forms/src/tab_order.rs b/crates/forms/src/tab_order.rs index 9c5c33b694..77234ee094 100644 --- a/crates/forms/src/tab_order.rs +++ b/crates/forms/src/tab_order.rs @@ -1,5 +1,5 @@ use super::read::{fields, page_refs}; -use super::*; +use super::{Document, Field, FormError, ObjRef, Object, invalid}; /// A page's tab order (`/Tabs`). #[derive(Clone, Copy, Debug, PartialEq, Eq)] diff --git a/crates/forms/src/tests.rs b/crates/forms/src/tests.rs index 61dab131e0..d8199f15d3 100644 --- a/crates/forms/src/tests.rs +++ b/crates/forms/src/tests.rs @@ -3601,13 +3601,17 @@ fn dotted_field_names_are_made_with_parent_fields() { }) .unwrap(); + invalid_dotted_field_names_are_rejected(&mut doc, &text); +} + +fn invalid_dotted_field_names_are_rejected(doc: &mut Document, text: &NewField) { for bad in ["MASTER", "MASTER.street1.x", "MASTER..x", ".x", "x.", "MASTER. "] { - assert!(add_field(&mut doc, 0, [300.0, 200.0, 450.0, 220.0], &text, Some(bad)).is_err(), "{bad:?}"); - assert!(set_props(&mut doc, "name", &FieldProps { name: Some(bad.into()), ..FieldProps::default() }).is_err(), "{bad:?}"); + assert!(add_field(doc, 0, [300.0, 200.0, 450.0, 220.0], text, Some(bad)).is_err(), "{bad:?}"); + assert!(set_props(doc, "name", &FieldProps { name: Some(bad.into()), ..FieldProps::default() }).is_err(), "{bad:?}"); } let deep = vec!["p"; 33].join("."); - assert!(add_field(&mut doc, 0, [300.0, 200.0, 450.0, 220.0], &text, Some(&deep)).is_err(), "too deep"); - assert!(set_props(&mut doc, "name", &FieldProps { name: Some("MASTER.street1".into()), ..FieldProps::default() }).is_err(), "taken"); + assert!(add_field(doc, 0, [300.0, 200.0, 450.0, 220.0], text, Some(&deep)).is_err(), "too deep"); + assert!(set_props(doc, "name", &FieldProps { name: Some("MASTER.street1".into()), ..FieldProps::default() }).is_err(), "taken"); } /// Review on #2957: a parent left empty by a move keeps its name from the next default name @@ -3801,90 +3805,17 @@ fn existing_form_fonts_are_kept_and_an_unchanged_resource_dictionary_is_not_rewr /// - Helv, TiRo and Cour are there. #[test] fn every_shape_of_form_fonts_ends_as_objects() { - let font = |base: &str| format!("<< /Type /Font /Subtype /Type1 /BaseFont /{base} >>"); let mut cases = 0; for dr_shape in ["missing", "inline", "object"] { for font_shape in ["missing", "inline", "object", "number"] { for helv in ["missing", "inline", "object", "dangling", "null", "number"] { for mine in ["missing", "inline", "object"] { - if dr_shape == "missing" && (font_shape != "missing" || helv != "missing" || mine != "missing") { - continue; - } - if matches!(font_shape, "missing" | "number") && (helv != "missing" || mine != "missing") { + let case = FontShapeCase::new(dr_shape, font_shape, helv, mine); + if !case.is_valid() { continue; } cases += 1; - let what = format!("/DR {dr_shape}, /Font {font_shape}, /Helv {helv}, /Mine {mine}"); - let mut entries = String::new(); - match helv { - "inline" => entries += &format!("/Helv {} ", font("Arial")), - "object" => entries += "/Helv 7 0 R ", - "dangling" => entries += "/Helv 99 0 R ", - "null" => entries += "/Helv null ", - "number" => entries += "/Helv 3 ", - _ => {} - } - match mine { - "inline" => entries += &format!("/Mine {} ", font("Symbol")), - "object" => entries += "/Mine 8 0 R ", - _ => {} - } - let fonts_value = match font_shape { - "inline" => format!("<< {entries}>>"), - "object" => "6 0 R".into(), - "number" => "7".into(), - _ => String::new(), - }; - let dr_dict = if fonts_value.is_empty() { "<< >>".to_string() } else { format!("<< /Font {fonts_value} >>") }; - let dr_value = match dr_shape { - "inline" => dr_dict.clone(), - "object" => "5 0 R".into(), - _ => String::new(), - }; - let af = if dr_value.is_empty() { "<< /Fields [] >>".to_string() } else { format!("<< /Fields [] /DR {dr_value} >>") }; - let mut doc = document(&[ - "<< /Type /Catalog /Pages 2 0 R /AcroForm 4 0 R >>".into(), - "<< /Type /Pages /Kids [3 0 R] /Count 1 /MediaBox [0 0 600 800] >>".into(), - "<< /Type /Page /Parent 2 0 R >>".into(), - af, - if dr_shape == "object" { dr_dict } else { "null".into() }, - if font_shape == "object" { format!("<< {entries}>>") } else { "null".into() }, - font("Helvetica-Oblique"), - font("ZapfDingbats"), - ]); - add_field(&mut doc, 0, [40.0, 600.0, 300.0, 630.0], &NewField::Text { multiline: false }, Some("name")) - .unwrap_or_else(|e| panic!("{what}: {e}")); - let doc = reopen(&doc); - let af = acroform(&doc).unwrap(); - let dr = doc.resolve(af.get(b"DR").unwrap_or_else(|| panic!("{what}: no /DR"))); - let fonts = dr_fonts(&doc); - for (name, value) in fonts.iter() { - assert!(value.as_dict().is_none(), "{what}: {} is inline", String::from_utf8_lossy(name)); - } - for name in ["Helv", "TiRo", "Cour"] { - assert!(fonts.contains(name.as_bytes()), "{what}: no {name}"); - } - let base = - |name: &[u8]| fonts.reference(name).and_then(|r| doc.get(r).as_dict().and_then(|f| f.name(b"BaseFont").map(<[u8]>::to_vec))); - match helv { - "inline" => assert_eq!(base(b"Helv").as_deref(), Some(&b"Arial"[..]), "{what}"), - "object" => assert_eq!(fonts.reference(b"Helv"), Some(pdfcraft_cos::ObjRef::new(7, 0)), "{what}"), - "dangling" => assert_eq!(fonts.reference(b"Helv"), Some(pdfcraft_cos::ObjRef::new(99, 0)), "{what}"), - "null" => assert_eq!(fonts.get(b"Helv"), Some(&Object::Null), "{what}"), - "number" => assert_eq!(fonts.get(b"Helv"), Some(&Object::Int(3)), "{what}"), - _ => assert_eq!(base(b"Helv").as_deref(), Some(&b"Helvetica"[..]), "{what}"), - } - match mine { - "inline" => assert_eq!(base(b"Mine").as_deref(), Some(&b"Symbol"[..]), "{what}"), - "object" => assert_eq!(fonts.reference(b"Mine"), Some(pdfcraft_cos::ObjRef::new(8, 0)), "{what}"), - _ => assert!(!fonts.contains(b"Mine"), "{what}"), - } - if dr_shape == "object" { - assert_eq!(af.reference(b"DR"), Some(pdfcraft_cos::ObjRef::new(5, 0)), "{what}: /DR stays its object"); - } - if font_shape == "object" { - assert_eq!(dr.as_dict().unwrap().reference(b"Font"), Some(pdfcraft_cos::ObjRef::new(6, 0)), "{what}: /Font stays its object"); - } + assert_font_shape_case(&case); } } } @@ -3892,6 +3823,118 @@ fn every_shape_of_form_fonts_ends_as_objects() { assert_eq!(cases, 1 + 2 * (2 + 2 * 6 * 3), "every shape was tried"); } +struct FontShapeCase<'a> { + dr: &'a str, + fonts: &'a str, + helv: &'a str, + mine: &'a str, + description: String, +} + +impl<'a> FontShapeCase<'a> { + fn new(dr: &'a str, fonts: &'a str, helv: &'a str, mine: &'a str) -> Self { + Self { dr, fonts, helv, mine, description: format!("/DR {dr}, /Font {fonts}, /Helv {helv}, /Mine {mine}") } + } + + fn is_valid(&self) -> bool { + let only_default_dr = self.dr == "missing" && self.fonts == "missing" && self.helv == "missing" && self.mine == "missing"; + let invalid_fonts = matches!(self.fonts, "missing" | "number") && (self.helv != "missing" || self.mine != "missing"); + !(self.dr == "missing" && !only_default_dr || invalid_fonts) + } +} + +fn assert_font_shape_case(case: &FontShapeCase<'_>) { + let mut doc = font_shape_document(case); + add_field(&mut doc, 0, [40.0, 600.0, 300.0, 630.0], &NewField::Text { multiline: false }, Some("name")) + .unwrap_or_else(|e| panic!("{}: {e}", case.description)); + let doc = reopen(&doc); + let acro = acroform(&doc).unwrap(); + let dr = doc.resolve(acro.get(b"DR").unwrap_or_else(|| panic!("{}: no /DR", case.description))); + let fonts = dr_fonts(&doc); + assert_font_entries_are_references(&fonts, &case.description); + assert_required_form_fonts(&fonts, &case.description); + assert_requested_font_shapes(&doc, &acro, &dr, &fonts, case); +} + +fn font_shape_document(case: &FontShapeCase<'_>) -> Document { + let mut entries = String::new(); + match case.helv { + "inline" => entries += &format!("/Helv {} ", form_font("Arial")), + "object" => entries += "/Helv 7 0 R ", + "dangling" => entries += "/Helv 99 0 R ", + "null" => entries += "/Helv null ", + "number" => entries += "/Helv 3 ", + _ => {} + } + match case.mine { + "inline" => entries += &format!("/Mine {} ", form_font("Symbol")), + "object" => entries += "/Mine 8 0 R ", + _ => {} + } + let fonts_value = match case.fonts { + "inline" => format!("<< {entries}>>"), + "object" => "6 0 R".into(), + "number" => "7".into(), + _ => String::new(), + }; + let dr_dict = if fonts_value.is_empty() { "<< >>".to_string() } else { format!("<< /Font {fonts_value} >>") }; + let dr_value = match case.dr { + "inline" => dr_dict.clone(), + "object" => "5 0 R".into(), + _ => String::new(), + }; + let acroform = if dr_value.is_empty() { "<< /Fields [] >>".to_string() } else { format!("<< /Fields [] /DR {dr_value} >>") }; + document(&[ + "<< /Type /Catalog /Pages 2 0 R /AcroForm 4 0 R >>".into(), + "<< /Type /Pages /Kids [3 0 R] /Count 1 /MediaBox [0 0 600 800] >>".into(), + "<< /Type /Page /Parent 2 0 R >>".into(), + acroform, + if case.dr == "object" { dr_dict } else { "null".into() }, + if case.fonts == "object" { format!("<< {entries}>>") } else { "null".into() }, + form_font("Helvetica-Oblique"), + form_font("ZapfDingbats"), + ]) +} + +fn form_font(base: &str) -> String { + format!("<< /Type /Font /Subtype /Type1 /BaseFont /{base} >>") +} + +fn assert_font_entries_are_references(fonts: &Dict, description: &str) { + for (name, value) in fonts.iter() { + assert!(value.as_dict().is_none(), "{description}: {} is inline", String::from_utf8_lossy(name)); + } +} + +fn assert_required_form_fonts(fonts: &Dict, description: &str) { + for name in ["Helv", "TiRo", "Cour"] { + assert!(fonts.contains(name.as_bytes()), "{description}: no {name}"); + } +} + +fn assert_requested_font_shapes(doc: &Document, acro: &Dict, dr: &Object, fonts: &Dict, case: &FontShapeCase<'_>) { + let base = |name: &[u8]| fonts.reference(name).and_then(|r| doc.get(r).as_dict().and_then(|f| f.name(b"BaseFont").map(<[u8]>::to_vec))); + match case.helv { + "inline" => assert_eq!(base(b"Helv").as_deref(), Some(&b"Arial"[..]), "{}", case.description), + "object" => assert_eq!(fonts.reference(b"Helv"), Some(pdfcraft_cos::ObjRef::new(7, 0)), "{}", case.description), + "dangling" => assert_eq!(fonts.reference(b"Helv"), Some(pdfcraft_cos::ObjRef::new(99, 0)), "{}", case.description), + "null" => assert_eq!(fonts.get(b"Helv"), Some(&Object::Null), "{}", case.description), + "number" => assert_eq!(fonts.get(b"Helv"), Some(&Object::Int(3)), "{}", case.description), + _ => assert_eq!(base(b"Helv").as_deref(), Some(&b"Helvetica"[..]), "{}", case.description), + } + match case.mine { + "inline" => assert_eq!(base(b"Mine").as_deref(), Some(&b"Symbol"[..]), "{}", case.description), + "object" => assert_eq!(fonts.reference(b"Mine"), Some(pdfcraft_cos::ObjRef::new(8, 0)), "{}", case.description), + _ => assert!(!fonts.contains(b"Mine"), "{}", case.description), + } + if case.dr == "object" { + assert_eq!(acro.reference(b"DR"), Some(pdfcraft_cos::ObjRef::new(5, 0)), "{}: /DR stays its object", case.description); + } + if case.fonts == "object" { + assert_eq!(dr.as_dict().unwrap().reference(b"Font"), Some(pdfcraft_cos::ObjRef::new(6, 0)), "{}: /Font stays its object", case.description); + } +} + /// #3441 (review follow-up): filling a field converts the form's inline `/DR` fonts, so a form /// an earlier PdfCraft made works in Acrobat once it has been filled here. Nothing is added. A /// form a signature covers keeps `/DR` as the signer saw it, and a form whose fonts are objects diff --git a/crates/forms/src/values.rs b/crates/forms/src/values.rs index 9dd79f0a70..37df5502d1 100644 --- a/crates/forms/src/values.rs +++ b/crates/forms/src/values.rs @@ -1,6 +1,9 @@ use super::appearances::{declares_pdfa, need_appearances}; use super::read::{acroform, field_flags, fields, page_refs}; -use super::*; +use super::{ + Dict, Document, Field, FieldEvent, FieldKind, FieldValue, FormError, NoScripts, ObjRef, Object, PdfString, Scripts, af, appearance, author, + calc_order, flags, invalid, name_obj, scripting, +}; // ── writing ───────────────────────────────────────────────────────────────────────────────── diff --git a/crates/js/src/document.rs b/crates/js/src/document.rs index 3d0fe194ee..e977457e2b 100644 --- a/crates/js/src/document.rs +++ b/crates/js/src/document.rs @@ -1,6 +1,6 @@ use super::host::{arg, colour, error, function, host, read, s, set_value, strings, text, value_of, write}; use super::model::{DISPLAY_HIDDEN, DISPLAY_VISIBLE, FieldType, Request}; -use super::*; +use super::{Attribute, Context, JsArray, JsObject, JsResult, JsString, JsValue, NativeFunction, ObjectInitializer, js_string}; macro_rules! getter { ($ctx:expr, $name:expr, |$f:ident, $c:ident| $body:expr) => {{ diff --git a/crates/js/src/format.rs b/crates/js/src/format.rs index 5f2eed1021..7f207b1916 100644 --- a/crates/js/src/format.rs +++ b/crates/js/src/format.rs @@ -1,6 +1,6 @@ use super::host::{arg, error, s, text}; use super::run::{MAX_PRINTF_OUTPUT_BYTES, MAX_PRINTF_WIDTH_PRECISION}; -use super::*; +use super::{Context, JsDate, JsResult, JsString, JsValue, formcalc}; /// `util.printf(cFormat, …)`: `%[,n][+ 0#][width][.prec](d|f|s|x)`, where `,0` groups /// thousands with commas (the default), `,1` doesn't, `,2` uses `.` and `,`, `,3` uses `.` diff --git a/crates/js/src/formcalc/access.rs b/crates/js/src/formcalc/access.rs index 3911a5223f..bea902c752 100644 --- a/crates/js/src/formcalc/access.rs +++ b/crates/js/src/formcalc/access.rs @@ -1,6 +1,11 @@ +#[cfg(not(target_arch = "wasm32"))] +use super::CLOCK_EVERY; use super::ast::{Expr, Idx}; use super::value::{Val, num_text, parse_num}; -use super::*; +use super::{ + HNode, HashSet, Interp, LIST_TOO_LONG, MAX_LIST, MAX_PARSE_DEPTH, MAX_STEPS, R, RAN_TOO_LONG, child_named, descendants_named, instances, + resolve_som, +}; impl Interp<'_> { pub(super) fn step(&mut self) -> R<()> { diff --git a/crates/js/src/formcalc/ast.rs b/crates/js/src/formcalc/ast.rs index f9a88be798..ab453a8061 100644 --- a/crates/js/src/formcalc/ast.rs +++ b/crates/js/src/formcalc/ast.rs @@ -1,4 +1,4 @@ -use super::*; +use super::{Func, Rc}; // ── syntax ────────────────────────────────────────────────────────────────────────────────── diff --git a/crates/js/src/formcalc/builtins.rs b/crates/js/src/formcalc/builtins.rs index 1e7bb94245..c3b7c7f1f2 100644 --- a/crates/js/src/formcalc/builtins.rs +++ b/crates/js/src/formcalc/builtins.rs @@ -3,7 +3,7 @@ use super::dates::{MAX_DAYS, civil_from_days, days_from_civil, format_date, pars use super::parser::parse; use super::value::{Val, fixed, is_numeric_text, parse_num}; use super::words::word_num; -use super::*; +use super::{Interp, MAX_STRING, R, STRING_TOO_LONG, XfaKind, is_limit}; impl Interp<'_> { /// A built-in function: its result is never a string past [`MAX_STRING`], and work on @@ -22,6 +22,15 @@ impl Interp<'_> { fn builtin_inner(&mut self, name: &str, args: &[Expr]) -> R { let lower = name.to_ascii_lowercase(); let n = |v: f64| Ok(Val::Num(v)); + if let Some(value) = self.date_builtin(&lower, args)? { + return Ok(value); + } + if let Some(value) = self.financial_builtin(&lower, args)? { + return Ok(value); + } + if let Some(value) = self.unit_builtin(&lower, args)? { + return Ok(value); + } Ok(match lower.as_str() { // ── arithmetic "abs" => return n(self.arg_num(args, 0)?.abs()), @@ -271,7 +280,24 @@ impl Interp<'_> { let cleaned: String = s.chars().filter(|c| c.is_ascii_digit() || *c == '.' || *c == '-').collect(); parse_num(&cleaned).map_or(Val::Null, Val::Num) } - // ── dates and times (days since 1900-01-01 = 1; milliseconds since midnight) + "ref" => { + let Some(e) = args.first() else { return Ok(Val::Null) }; + self.eval(e)? + } + "eval" => { + let src = self.arg_str(args, 0)?; + self.charge((src.len() / 16) as u64)?; + let body = parse(&src)?; + let (_, v) = self.block(&body)?; + v + } + "get" | "post" | "put" => return Err(format!("{name}: network access is not available to form scripts")), + _ => return Err(format!("unknown function {name}")), + }) + } + + fn date_builtin(&mut self, lower: &str, args: &[Expr]) -> R> { + let value = match lower { "date" => { #[cfg(not(target_arch = "wasm32"))] { @@ -304,7 +330,7 @@ impl Interp<'_> { let days = self.arg_num(args, 0)?; let pic = if args.len() > 1 { self.arg_str(args, 1)? } else { "MMM D, YYYY".into() }; if !days.is_finite() || days.abs() >= MAX_DAYS { - return Ok(Val::Null); + return Ok(Some(Val::Null)); } let (y, m, d) = civil_from_days(days as i64); Val::Str(format_date(y, m, d, &pic)) @@ -326,7 +352,7 @@ impl Interp<'_> { "num2time" | "num2gmtime" => { let ms = self.arg_num(args, 0)?; if !ms.is_finite() || ms < 0.0 { - return Ok(Val::Null); + return Ok(Some(Val::Null)); } let s = (ms / 1000.0) as u64; Val::Str(format!("{:02}:{:02}:{:02}", (s / 3600) % 24, (s / 60) % 60, s % 60)) @@ -344,7 +370,13 @@ impl Interp<'_> { parts.next().and_then(|p| p.trim().parse::().ok()).filter(|v| v.is_finite() && *v >= 0.0).unwrap_or(0.0).min(1_000_000.0); Val::Num(((h * 3600 + m * 60) * 1000) as f64 + (sec * 1000.0).round()) } - // ── financial + _ => return Ok(None), + }; + Ok(Some(value)) + } + + fn financial_builtin(&mut self, lower: &str, args: &[Expr]) -> R> { + let value = match lower { "fv" => { let (p, r, k) = (self.arg_num(args, 0)?, self.arg_num(args, 1)?, self.arg_num(args, 2)?); Val::Num(if r == 0.0 { p * k } else { p * (((1.0 + r).powf(k) - 1.0) / r) }) @@ -428,7 +460,13 @@ impl Interp<'_> { } Val::Num((lo + hi) / 2.0 * 12.0) } - // ── units and references + _ => return Ok(None), + }; + Ok(Some(value)) + } + + fn unit_builtin(&mut self, lower: &str, args: &[Expr]) -> R> { + let value = match lower { "unittype" => { let s = self.arg_str(args, 0)?; let unit: String = s.trim().chars().skip_while(|c| c.is_ascii_digit() || *c == '.' || *c == '-' || *c == '+').collect(); @@ -459,19 +497,8 @@ impl Interp<'_> { let target = if to.trim().is_empty() { unit.clone() } else { to }; Val::Num(v / per_in(&unit) * per_in(&target)) } - "ref" => { - let Some(e) = args.first() else { return Ok(Val::Null) }; - self.eval(e)? - } - "eval" => { - let src = self.arg_str(args, 0)?; - self.charge((src.len() / 16) as u64)?; - let body = parse(&src)?; - let (_, v) = self.block(&body)?; - v - } - "get" | "post" | "put" => return Err(format!("{name}: network access is not available to form scripts")), - _ => return Err(format!("unknown function {name}")), - }) + _ => return Ok(None), + }; + Ok(Some(value)) } } diff --git a/crates/js/src/formcalc/eval.rs b/crates/js/src/formcalc/eval.rs index 23ce3ec0c1..a3218a78f6 100644 --- a/crates/js/src/formcalc/eval.rs +++ b/crates/js/src/formcalc/eval.rs @@ -1,6 +1,9 @@ use super::ast::{Expr, Stmt}; use super::value::{Val, is_numeric_text, num_text}; -use super::*; +use super::{ + CALLS_TOO_DEEP, Flow, Func, HashMap, HashSet, Interp, LIST_TOO_LONG, LOOPED_TOO_MUCH, MAX_LIST, R, Rc, TOO_DEEP, XfaEffect, child_named, clip, + descendants_named, instances, reset_names, resolve_som, +}; impl Interp<'_> { // ── expressions diff --git a/crates/js/src/formcalc/lexer.rs b/crates/js/src/formcalc/lexer.rs index ba9ae4f16a..46af19f761 100644 --- a/crates/js/src/formcalc/lexer.rs +++ b/crates/js/src/formcalc/lexer.rs @@ -1,4 +1,4 @@ -use super::*; +use super::MAX_STRING; // ── lexer ─────────────────────────────────────────────────────────────────────────────────── diff --git a/crates/js/src/formcalc/parser.rs b/crates/js/src/formcalc/parser.rs index 84cf121cde..fceedadf5f 100644 --- a/crates/js/src/formcalc/parser.rs +++ b/crates/js/src/formcalc/parser.rs @@ -1,6 +1,6 @@ use super::ast::{Expr, Idx, Stmt}; use super::lexer::{Tok, Token, lex}; -use super::*; +use super::{Func, MAX_CHAIN, MAX_PARSE_DEPTH, Rc}; struct Parser { toks: Vec, diff --git a/crates/js/src/globals.rs b/crates/js/src/globals.rs index dd487c2482..a9ad4d2b8f 100644 --- a/crates/js/src/globals.rs +++ b/crates/js/src/globals.rs @@ -2,7 +2,7 @@ use super::document::{field_object, get_field, get_nth_field_name, noop, num_fie use super::format::{printd, printf, printx, scand}; use super::host::{arg, function, host, s, text, text_line}; use super::model::{DISPLAY_HIDDEN, DISPLAY_NO_PRINT, DISPLAY_NO_VIEW, DISPLAY_VISIBLE, Event, Panel, Request}; -use super::*; +use super::{Attribute, Context, JsArray, JsObject, JsResult, JsString, JsValue, NativeFunction, ObjectInitializer, js_string}; // ── app, util, console ────────────────────────────────────────────────────────────────────── diff --git a/crates/js/src/host.rs b/crates/js/src/host.rs index 131b8851c9..6e442d2a2b 100644 --- a/crates/js/src/host.rs +++ b/crates/js/src/host.rs @@ -1,6 +1,9 @@ use super::model::{DocInfo, FieldState, FieldType, Request}; use super::run::MAX_ARRAY_LENGTH; -use super::*; +use super::{ + Arc, BTreeSet, Context, FunctionObjectBuilder, JsArray, JsError, JsFunction, JsNativeError, JsResult, JsString, JsValue, NativeFunction, RefCell, + xfa, +}; pub(crate) struct Host { pub(crate) fields: Arc>, diff --git a/crates/js/src/run.rs b/crates/js/src/run.rs index 17b5c252ff..07c0e984bb 100644 --- a/crates/js/src/run.rs +++ b/crates/js/src/run.rs @@ -1,7 +1,7 @@ use super::globals::{event_object, install}; use super::host::{Host, Shared, text}; use super::model::{DocInfo, Event, FieldState, Limits, Outcome}; -use super::*; +use super::{Arc, Attribute, BTreeSet, Context, HostHooks, JsNativeError, JsResult, JsString, Realm, RefCell, Source, js_string}; /// Longest script, in bytes. pub(crate) const MAX_SCRIPT_BYTES: usize = 256 * 1024; diff --git a/crates/js/src/tests.rs b/crates/js/src/tests.rs index 9e96dcd2e3..38cebf54ce 100644 --- a/crates/js/src/tests.rs +++ b/crates/js/src/tests.rs @@ -1017,6 +1017,14 @@ mod formcalc { #[test] fn built_in_functions_cover_the_common_set() { + assert_numeric_and_logical_builtins(); + assert_string_builtins(); + assert_format_and_date_builtins(); + assert_financial_and_unit_builtins(); + assert_builtin_errors(); + } + + fn assert_numeric_and_logical_builtins() { assert_eq!(calc("Abs(-2.5)"), "2.5"); assert_eq!(calc(r#"Decode("a%2Fb", "url")"#), "a/b"); assert_eq!(calc(r#"Decode("a%+fb", "url")"#), "a%+fb"); @@ -1034,6 +1042,9 @@ mod formcalc { assert_eq!(calc(r#"Within(5, 1, 10)"#), "1"); assert_eq!(calc(r#"HasValue("")"#), "0"); assert_eq!(calc(r#"HasValue("x")"#), "1"); + } + + fn assert_string_builtins() { assert_eq!(calc(r#"At("abcd", "c")"#), "3"); assert_eq!(calc(r#"Left("hello", 2)"#), "he"); assert_eq!(calc(r#"Right("hello", 2)"#), "lo"); @@ -1050,6 +1061,11 @@ mod formcalc { assert_eq!(calc(r#"WordNum(42)"#), "Forty-Two"); assert_eq!(calc(r#"WordNum(1.999, 2)"#), "Two Dollars And 00 Cents"); assert_eq!(calc(r#"WordNum(1.01, 2)"#), "One Dollar And 01 Cent"); + assert_eq!(calc(r#"Encode("a b&c", "url")"#), "a%20b%26c"); + assert_eq!(calc(r#"Decode("a%20b", "url")"#), "a b"); + } + + fn assert_format_and_date_builtins() { assert_eq!(calc(r#"Format("zzz,zz9.99", 1234.5)"#), "1,234.50"); assert_eq!(calc(r#"Format("$z,zz9.99", -5)"#), "-$5.00"); assert_eq!(calc(r#"Format("MM/DD/YYYY", "2024-02-29")"#), "02/29/2024"); @@ -1065,6 +1081,9 @@ mod formcalc { assert_eq!(calc(r#"IsoTime2Num("12:30:45.250")"#), "45045250"); assert_eq!(calc(r#"IsoTime2Num("T12:30:45")"#), "45045000"); assert_eq!(calc(r#"Num2Time(3661000)"#), "01:01:01"); + } + + fn assert_financial_and_unit_builtins() { assert_eq!(calc("Round(Pmt(10000, 0.01, 12), 2)"), "888.49"); assert_eq!(calc("Round(FV(100, 0.01, 12), 2)"), "1268.25"); assert_eq!(calc("Round(PV(100, 0.01, 12), 2)"), "1125.51"); @@ -1073,8 +1092,9 @@ mod formcalc { assert_eq!(calc(r#"UnitValue("72points", "in")"#), "1"); assert_eq!(calc(r#"UnitValue("25.4millimeters", "inches")"#), "1"); assert_eq!(calc(r#"UnitValue("1in", "points")"#), "72"); - assert_eq!(calc(r#"Encode("a b&c", "url")"#), "a%20b%26c"); - assert_eq!(calc(r#"Decode("a%20b", "url")"#), "a b"); + } + + fn assert_builtin_errors() { assert!(go(r#"Get("http://example.com")"#, "form1[0].page1[0].total[0]", "calculate").error.unwrap().contains("network")); assert!(go("Nope(1)", "form1[0].page1[0].total[0]", "calculate").error.unwrap().contains("unknown function")); } @@ -1147,6 +1167,13 @@ s"# #[test] fn form_objects_resolve_assign_and_record_effects() { + assert_formcalc_reads_fields_and_rows(); + assert_formcalc_reads_runtime_properties(); + assert_formcalc_records_primary_effects(); + assert_formcalc_updates_instances_and_records_requests(); + } + + fn assert_formcalc_reads_fields_and_rows() { // Fields deref to their values; `$` is the current field. assert_eq!(calc("qty * price"), "10"); assert_eq!(calc("$.name"), "total"); @@ -1170,7 +1197,6 @@ s"# assert_eq!(in_row("Sum(row[*].amount)"), "15"); assert_eq!(in_row("row[1].amount"), "5"); assert_eq!(in_row("row[-1].amount"), "10"); - // Past the ends there is no object, so a property of it is an error (as in Acrobat). let past = go("row[+1].amount", "form1[0].page1[0].table[0].row[1].amount[0]", "calculate"); assert!(past.error.unwrap().contains("no object")); assert_eq!(in_row("Exists(row[-5])"), "0"); @@ -1182,12 +1208,18 @@ s"# assert_eq!(calc("table._row.count"), "2"); assert_eq!(calc("Exists(qty) & not Exists(nothing)"), "1"); assert_eq!(calc("HasValue(total)"), "0"); + } + + fn assert_formcalc_reads_runtime_properties() { assert_eq!(calc("$host.numPages"), "3"); assert_eq!(calc("$layout.pageCount()"), "3"); assert_eq!(calc("$event.name"), "calculate"); assert_eq!(calc("xfa.resolveNode(\"page1.price\").rawValue"), "2.5"); assert_eq!(calc("$.border.fill.color.value"), ""); assert!(go("nothing + 1", "form1[0].page1[0].total[0]", "calculate").error.unwrap().contains("unknown name")); + } + + fn assert_formcalc_records_primary_effects() { // Assignment to a field (by name and by path), a property and a variable. let o = go( r#"page1.qty = 6 @@ -1215,7 +1247,9 @@ table._row.count"#, XfaEffect::AddInstance { som: "form1[0].page1[0].table[0].row[2]".into() }, ] ); - // Instance managers: remove, setInstances, count assignment, and the floor of one. + } + + fn assert_formcalc_updates_instances_and_records_requests() { let o = go( "table._row.removeInstance(0)\ntable._row.setInstances(1)\ntable._row.count = 0\ntable._row.count", "form1[0].page1[0].go[0]", @@ -1238,7 +1272,7 @@ $host.gotoURL("https://example.org")"#, ); assert_eq!( o.effects, - vec![XfaEffect::ResetData(vec!["qty".into(), "price".into()]), XfaEffect::Print, XfaEffect::LaunchUrl("https://example.org".into())] + vec![XfaEffect::ResetData(vec!["qty".into(), "price".into()]), XfaEffect::Print, XfaEffect::LaunchUrl("https://example.org".into()),] ); } @@ -1279,58 +1313,79 @@ $host.gotoURL("https://example.org")"#, #[test] fn hostile_formcalc_scripts_end_with_an_error_and_bounded_output() { - let total = "form1[0].page1[0].total[0]"; - let fast = Limits { loop_iterations: 10_000, recursion: 32 }; - let ev = XfaEvent { activity: "calculate".into(), target: total.into(), ..Default::default() }; - let doc = XfaDoc::default(); - let run = |s: &str| run_formcalc(s, &ev, &doc, &form(), fast); - assert!(run("while (1) do endwhile").error.unwrap().contains("looped")); - assert!(run("for i = 1 upto 1000000 do endfor").error.unwrap().contains("looped")); - assert!(run("func f(n) do f(n + 1) endfunc\nf(1)").error.unwrap().contains("nested")); - assert!(run(&format!("{}1{}", "(".repeat(500), ")".repeat(500))).error.is_some()); + assert_hostile_control_flow_is_bounded(); + assert_hostile_numeric_inputs_are_safe(); + assert_hostile_outputs_are_bounded(); + assert_hostile_nesting_is_bounded(); + assert_hostile_deadlines_and_parse_errors(); + assert_hostile_instance_growth_is_bounded(); + assert_hostile_message_count_is_bounded(); + assert_hostile_small_stack_is_safe(); + } + + fn assert_hostile_control_flow_is_bounded() { + assert!(run_hostile_formcalc("while (1) do endwhile").error.unwrap().contains("looped")); + assert!(run_hostile_formcalc("for i = 1 upto 1000000 do endfor").error.unwrap().contains("looped")); + assert!(run_hostile_formcalc("func f(n) do f(n + 1) endfunc\nf(1)").error.unwrap().contains("nested")); + assert!(run_hostile_formcalc(&format!("{}1{}", "(".repeat(500), ")".repeat(500))).error.is_some()); // A 120k-term chain is refused at parse time (its tree would be as deep as it is long). - assert!(run(&format!("1{}", "+1".repeat(120_000))).error.unwrap().contains("too long")); - assert!(run(&format!("$form{}", ".a".repeat(120_000))).error.unwrap().contains("too long")); - assert!(run("nothing.x = 1").error.unwrap().contains("unknown name")); - assert!(run("$form.nothing = 1").error.unwrap().contains("no nothing")); + assert!(run_hostile_formcalc(&format!("1{}", "+1".repeat(120_000))).error.unwrap().contains("too long")); + assert!(run_hostile_formcalc(&format!("$form{}", ".a".repeat(120_000))).error.unwrap().contains("too long")); + assert!(run_hostile_formcalc("nothing.x = 1").error.unwrap().contains("unknown name")); + assert!(run_hostile_formcalc("$form.nothing = 1").error.unwrap().contains("no nothing")); // Values go into fields only: a subform or the form itself is refused, nothing is recorded. - let o = run("details = \"junk\""); + let o = run_hostile_formcalc("details = \"junk\""); assert!(o.error.unwrap().contains("not a field")); assert!(o.effects.is_empty()); - assert!(run("$form = \"junk\"").error.unwrap().contains("not a field")); + assert!(run_hostile_formcalc("$form = \"junk\"").error.unwrap().contains("not a field")); + } + + fn assert_hostile_numeric_inputs_are_safe() { // Hostile numbers into the string functions. - assert_eq!(run(r#"Stuff("abc", 2, 1e300, "X")"#).result.as_deref(), Some("aX")); - assert_eq!(run(r#"Stuff("abc", -1e300, 1, "X")"#).result.as_deref(), Some("Xbc")); - assert_eq!(run(r#"Substr("abc", 1e300, 1e300)"#).result.as_deref(), Some("")); - assert_eq!(run(r#"Left("abc", -1e300)"#).result.as_deref(), Some("")); - assert!(run(r#"Str(1e300, 1e300, 1e300)"#).error.is_none()); - assert!(run(r#"Round(1e300, 1e300)"#).error.is_none()); - assert!(run(r#"Choose(1e300, 1)"#).error.is_none()); + assert_eq!(run_hostile_formcalc(r#"Stuff("abc", 2, 1e300, "X")"#).result.as_deref(), Some("aX")); + assert_eq!(run_hostile_formcalc(r#"Stuff("abc", -1e300, 1, "X")"#).result.as_deref(), Some("Xbc")); + assert_eq!(run_hostile_formcalc(r#"Substr("abc", 1e300, 1e300)"#).result.as_deref(), Some("")); + assert_eq!(run_hostile_formcalc(r#"Left("abc", -1e300)"#).result.as_deref(), Some("")); + assert!(run_hostile_formcalc(r#"Str(1e300, 1e300, 1e300)"#).error.is_none()); + assert!(run_hostile_formcalc(r#"Round(1e300, 1e300)"#).error.is_none()); + assert!(run_hostile_formcalc(r#"Choose(1e300, 1)"#).error.is_none()); + } + + fn assert_hostile_outputs_are_bounded() { // Strings can't grow past the cap through any function, and messages and values are clipped. assert!( - run("var s = Space(1000000)\nfor i = 1 upto 10 do s = Encode(Replace(s, \" \", \"&\"), \"html\") endfor\nLen(s)") + run_hostile_formcalc("var s = Space(1000000)\nfor i = 1 upto 10 do s = Encode(Replace(s, \" \", \"&\"), \"html\") endfor\nLen(s)") .error .unwrap() .contains("too long") ); - assert!(run("Upper(Concat(Space(600000), Space(600000)))").error.unwrap().contains("too long")); - let o = run("$host.messageBox(Space(100000))"); + assert!(run_hostile_formcalc("Upper(Concat(Space(600000), Space(600000)))").error.unwrap().contains("too long")); + let o = run_hostile_formcalc("$host.messageBox(Space(100000))"); assert!(matches!(o.effects.as_slice(), [XfaEffect::MessageBox(m)] if m.chars().count() <= 4100), "{:?}", o.effects.len()); - let o = run("qty = Space(100000)"); + let o = run_hostile_formcalc("qty = Space(100000)"); assert!(matches!(o.effects.as_slice(), [XfaEffect::SetValue { value, .. }] if value.chars().count() == 65_536), "{:?}", o.effects.len()); assert!(o.notes.iter().any(|n| n.contains("cut")), "{:?}", o.notes); + } + + fn assert_hostile_nesting_is_bounded() { // A comment of dashes is not deep nesting. - assert_eq!(run(&format!("; {}\n1 + 1", "-".repeat(70))).result.as_deref(), Some("2")); + assert_eq!(run_hostile_formcalc(&format!("; {}\n1 + 1", "-".repeat(70))).result.as_deref(), Some("2")); // Parentheses don't reset the chain count: a tree is never deeper than the cap. let mut nested = "1+1+1+1+1+1+1+1+1+1".to_string(); for _ in 0..30 { nested = format!("({nested}{})", "+1".repeat(40)); } - assert!(run(&nested).error.unwrap().contains("too long")); - assert_eq!(run("(1+2)*(3+4) + (5+6)").result.as_deref(), Some("32")); + assert!(run_hostile_formcalc(&nested).error.unwrap().contains("too long")); + assert_eq!(run_hostile_formcalc("(1+2)*(3+4) + (5+6)").result.as_deref(), Some("32")); // Nested statements inside recursion count against the depth limit. let deep = format!("func f(n) do\n{}return f(n - 1)\n{}endfunc\nf(1000)", "if (n > 0) then\n".repeat(20), "endif\n".repeat(20)); - assert!(run(&deep).error.unwrap().contains("nested")); + assert!(run_hostile_formcalc(&deep).error.unwrap().contains("nested")); + } + + fn assert_hostile_deadlines_and_parse_errors() { + let total = "form1[0].page1[0].total[0]"; + let ev = XfaEvent { activity: "calculate".into(), target: total.into(), ..Default::default() }; + let doc = XfaDoc::default(); // A deadline already passed stops the script at its first look at the clock. let o = crate::formcalc::run_formcalc_at( "for i = 1 upto 100000 do Eval(\"1\") endfor", @@ -1341,29 +1396,40 @@ $host.gotoURL("https://example.org")"#, Some(std::time::Duration::ZERO), ); assert!(o.error.unwrap().contains("too long")); - assert!(run(&format!("{}1{}", "-".repeat(5000), "")).error.is_some()); - assert!(run("var s = \"x\"\nfor i = 1 upto 100 do s = Concat(s, s) endfor\nLen(s)").error.unwrap().contains("too long")); - assert!(run("Space(1e12)").error.is_none()); - assert!(run("Replace(Space(100000), \" \", Space(100000))").error.unwrap().contains("too long")); - assert_eq!(run(r#"Format("YYYY-MM-DD", 1e300)"#).error, None); - assert_eq!(run(r#"Date2Num("99999999999999999999-01-01", "YYYYYYYYYYYYYYYYYYYY-MM-DD")"#).error, None); - assert_eq!(run(r#"Time2Num("99999999999999999999:0:0")"#).error, None); - assert_eq!(run(r#"Num2Date(1e300, "YYYY")"#).result.as_deref(), Some("")); - assert!(run("for i = 1 upto 1000 do nothing endfor").error.unwrap().contains("unknown name")); - assert!(run("\"unterminated").error.unwrap().contains("unterminated")); - assert!(run("1 ) 2").error.is_some()); - assert!(run("Eval(\"Eval(\"\"Eval(\"\"\"\"1\"\"\"\")\"\")\")").error.is_none()); + assert!(run_hostile_formcalc(&format!("{}1{}", "-".repeat(5000), "")).error.is_some()); + assert!(run_hostile_formcalc("var s = \"x\"\nfor i = 1 upto 100 do s = Concat(s, s) endfor\nLen(s)").error.unwrap().contains("too long")); + assert!(run_hostile_formcalc("Space(1e12)").error.is_none()); + assert!(run_hostile_formcalc("Replace(Space(100000), \" \", Space(100000))").error.unwrap().contains("too long")); + assert_eq!(run_hostile_formcalc(r#"Format("YYYY-MM-DD", 1e300)"#).error, None); + assert_eq!(run_hostile_formcalc(r#"Date2Num("99999999999999999999-01-01", "YYYYYYYYYYYYYYYYYYYY-MM-DD")"#).error, None); + assert_eq!(run_hostile_formcalc(r#"Time2Num("99999999999999999999:0:0")"#).error, None); + assert_eq!(run_hostile_formcalc(r#"Num2Date(1e300, "YYYY")"#).result.as_deref(), Some("")); + assert!(run_hostile_formcalc("for i = 1 upto 1000 do nothing endfor").error.unwrap().contains("unknown name")); + assert!(run_hostile_formcalc("\"unterminated").error.unwrap().contains("unterminated")); + assert!(run_hostile_formcalc("1 ) 2").error.is_some()); + assert!(run_hostile_formcalc("Eval(\"Eval(\"\"Eval(\"\"\"\"1\"\"\"\")\"\")\")").error.is_none()); + } + + fn assert_hostile_instance_growth_is_bounded() { // Adding rows forever stops at the instance cap with the effects it managed. - let o = run("for i = 1 upto 100000 do table._row.addInstance(1) endfor\ntable._row.count"); + let o = run_hostile_formcalc("for i = 1 upto 100000 do table._row.addInstance(1) endfor\ntable._row.count"); assert!(o.error.unwrap().contains("looped")); assert!(o.effects.iter().filter(|e| matches!(e, XfaEffect::AddInstance { .. })).count() <= 1000, "{}", o.effects.len()); - let o = run("for i = 1 upto 5000 do table._row.addInstance(1) endfor\ntable._row.count"); + let o = run_hostile_formcalc("for i = 1 upto 5000 do table._row.addInstance(1) endfor\ntable._row.count"); assert_eq!(o.error, None); assert_eq!(o.result.as_deref(), Some("1002")); + } + + fn assert_hostile_message_count_is_bounded() { // Message boxes past the cap are dropped and noted. - let o = run("for i = 1 upto 500 do $host.messageBox(i) endfor"); + let o = run_hostile_formcalc("for i = 1 upto 500 do $host.messageBox(i) endfor"); assert_eq!(o.effects.iter().filter(|e| matches!(e, XfaEffect::MessageBox(_))).count(), 100); assert!(!o.notes.is_empty()); + } + + fn assert_hostile_small_stack_is_safe() { + let ev = XfaEvent { activity: "calculate".into(), target: "form1[0].page1[0].total[0]".into(), ..Default::default() }; + let doc = XfaDoc::default(); // On a small stack (the wasm build's), the limits stop the script before the stack does. let small = std::thread::Builder::new() .stack_size(1 << 20) @@ -1400,6 +1466,13 @@ $host.gotoURL("https://example.org")"#, ); assert!(o.abandoned || o.error.is_some(), "{o:?}"); } + + fn run_hostile_formcalc(script: &str) -> XfaOutcome { + let ev = XfaEvent { activity: "calculate".into(), target: "form1[0].page1[0].total[0]".into(), ..Default::default() }; + let doc = XfaDoc::default(); + let fast = Limits { loop_iterations: 10_000, recursion: 32 }; + run_formcalc(script, &ev, &doc, &form(), fast) + } } mod session { diff --git a/crates/js/src/xfa/globals.rs b/crates/js/src/xfa/globals.rs index 2507941658..54508e6cab 100644 --- a/crates/js/src/xfa/globals.rs +++ b/crates/js/src/xfa/globals.rs @@ -2,7 +2,10 @@ use super::host::host; use super::instances::instance_manager; use super::model::{MAX_DEPTH, XfaDoc, XfaEffect, XfaEvent, clip, reset_names}; use super::nodes::{node_index, node_object, noop, resolve_som, resolver, sink}; -use super::*; +use super::{ + Attribute, Context, JsResult, JsString, JsValue, NativeFunction, ObjectInitializer, arg, js_string, platform, printd, printf, printx, s, scand, + text, +}; // ── xfa.host, xfa.layout, xfa.event, app, console ─────────────────────────────────────────── diff --git a/crates/js/src/xfa/host.rs b/crates/js/src/xfa/host.rs index 419d2141fc..ea2d4d4332 100644 --- a/crates/js/src/xfa/host.rs +++ b/crates/js/src/xfa/host.rs @@ -2,7 +2,7 @@ use super::model::{ MAX_ALERTS, MAX_CONSOLE, MAX_DEPTH, MAX_EFFECTS, MAX_NODES, MAX_PAYLOAD, MAX_VALUE, XfaDoc, XfaEffect, XfaKind, XfaNode, clip, clip_value, effect_key, payload, }; -use super::*; +use super::{Context, HashMap, JsResult, RefCell, error}; /// One node of the flattened form, shared by the JavaScript and FormCalc engines. pub(crate) struct HNode { diff --git a/crates/js/src/xfa/instances.rs b/crates/js/src/xfa/instances.rs index b03e6aef09..c099c5abe8 100644 --- a/crates/js/src/xfa/instances.rs +++ b/crates/js/src/xfa/instances.rs @@ -1,7 +1,7 @@ use super::host::{HNode, XHost, host}; use super::model::{MAX_ADDED, MAX_DEPTH, MAX_NODES, XfaEffect}; use super::nodes::{instances, node_object}; -use super::*; +use super::{Attribute, Context, JsArray, JsObject, JsResult, JsValue, NativeFunction, ObjectInitializer, arg, function, js_string, s, text}; pub(super) fn list_object(ctx: &mut Context, items: &[usize]) -> JsResult { let vals: Vec = items.iter().map(|i| JsValue::from(*i as f64)).collect(); diff --git a/crates/js/src/xfa/model.rs b/crates/js/src/xfa/model.rs index b9c6cedaae..83b2d7d149 100644 --- a/crates/js/src/xfa/model.rs +++ b/crates/js/src/xfa/model.rs @@ -1,4 +1,4 @@ -use super::*; +use super::HashSet; /// What kind of template object a node is. #[derive(Clone, Copy, Debug, PartialEq, Eq)] diff --git a/crates/js/src/xfa/nodes.rs b/crates/js/src/xfa/nodes.rs index b9483f25d1..75943352e6 100644 --- a/crates/js/src/xfa/nodes.rs +++ b/crates/js/src/xfa/nodes.rs @@ -2,7 +2,10 @@ use super::globals::{recalculate, relayout}; use super::host::{HNode, XHost, host}; use super::instances::{instance_manager, list_object}; use super::model::{MAX_DEPTH, XfaEffect}; -use super::*; +use super::{ + Attribute, Context, JsObject, JsProxy, JsResult, JsString, JsValue, NativeFunction, ObjectInitializer, arg, as_number, error, function, + js_string, s, text, +}; // ── node objects ──────────────────────────────────────────────────────────────────────────── diff --git a/crates/js/src/xfa/run.rs b/crates/js/src/xfa/run.rs index 2db77d7062..f951e02a54 100644 --- a/crates/js/src/xfa/run.rs +++ b/crates/js/src/xfa/run.rs @@ -1,7 +1,7 @@ use super::globals::install; use super::host::{Shared, XHost}; use super::model::{XfaDoc, XfaEvent, XfaNode, XfaOutcome, clip_result}; -use super::*; +use super::{Attribute, Context, JsResult, Limits, RefCell, Source, js_string, refuse, s, text}; /// Run `script` for `event` on the form `root` (the root subform), from node `event.target`. pub fn run_xfa(script: &str, event: &XfaEvent, doc: &XfaDoc, root: &XfaNode, limits: Limits) -> XfaOutcome { diff --git a/crates/measure/src/tests.rs b/crates/measure/src/tests.rs index 8d69a05cf0..5b277e5546 100644 --- a/crates/measure/src/tests.rs +++ b/crates/measure/src/tests.rs @@ -80,7 +80,7 @@ fn standard_annotations_captions_restyle_move_and_unknown_keys() { let (r, dict) = annot(&d, 0, 0).unwrap(); assert_eq!(dict.name(b"IT"), Some(&b"LineDimension"[..])); d.update_dict(r, |d| d.set(b"VendorKey".to_vec(), Object::Int(42))).unwrap(); - pdfcraft_annot::set_style(&mut d, 0, 0, Some([1.0, 0.0, 0.0]), None, Some(2.0), None, &meta).unwrap(); + pdfcraft_annot::set_style(&mut d, 0, 0, pdfcraft_annot::StyleChange::new(Some([1.0, 0.0, 0.0]), None, Some(2.0), None), &meta).unwrap(); let (_, dict) = annot(&d, 0, 0).unwrap(); assert_eq!(dict.int(b"VendorKey"), Some(42)); let ap = d.resolve(dict.get(b"AP").unwrap()); diff --git a/crates/ocr/Cargo.toml b/crates/ocr/Cargo.toml index 46bb3a1e0e..750e78b96d 100644 --- a/crates/ocr/Cargo.toml +++ b/crates/ocr/Cargo.toml @@ -13,5 +13,8 @@ workspace = true [dependencies] pdfcraft-fonts = { workspace = true } ocrs = { version = "0.13.1", default-features = false, features = ["rten"] } -rten = { version = "0.26.0", default-features = false, features = ["rten_format"] } +rten = { version = "0.26.0", default-features = false, features = ["onnx_format", "rten_format"] } thiserror.workspace = true + +[dev-dependencies] +tempfile = "3.27" diff --git a/crates/ocr/src/lib.rs b/crates/ocr/src/lib.rs index affa4ab163..7f58270e1a 100644 --- a/crates/ocr/src/lib.rs +++ b/crates/ocr/src/lib.rs @@ -15,8 +15,8 @@ use std::path::{Path, PathBuf}; pub use pdfcraft_fonts::helvetica_width; /// The model files, as named in ATTRIBUTION.toml. -pub const DETECTION_MODEL: &str = "text-detection.rten"; -pub const RECOGNITION_MODEL: &str = "text-recognition.rten"; +pub const DETECTION_MODEL: &str = "text-detection.onnx"; +pub const RECOGNITION_MODEL: &str = "text-recognition.onnx"; /// The recognition model's alphabet, as it was trained (ocrs-models' `DEFAULT_ALPHABET`): its /// output classes follow this order. The ocrs crate's own copy has an `E` where the training had @@ -48,10 +48,13 @@ pub struct Models { } impl Models { - /// The models in `dir`, if both files are there. + /// A complete model pair in `dir`, preferring current ONNX files over legacy RTEN files. + /// An incomplete update never mixes formats or hides an intact legacy pair. pub fn in_dir(dir: &Path) -> Option { - let m = Models { detection: dir.join(DETECTION_MODEL), recognition: dir.join(RECOGNITION_MODEL) }; - (m.detection.is_file() && m.recognition.is_file()).then_some(m) + [(DETECTION_MODEL, RECOGNITION_MODEL), ("text-detection.rten", "text-recognition.rten")].into_iter().find_map(|(detection, recognition)| { + let m = Models { detection: dir.join(detection), recognition: dir.join(recognition) }; + (m.detection.is_file() && m.recognition.is_file()).then_some(m) + }) } /// Look for the models: `$PDFCRAFT_MODELS`, then where the release packages install them @@ -321,6 +324,63 @@ mod tests { assert_eq!(w.up, [-10.0, 0.0]); } + /// The current ONNX pair wins when an installation also retains both legacy models. + #[test] + fn model_discovery_prefers_the_complete_onnx_pair() { + let dir = tempfile::tempdir().unwrap(); + for file in ["text-detection.onnx", "text-recognition.onnx"] { + std::fs::write(dir.path().join(file), b"model").unwrap(); + } + let expected = Some(Models { detection: dir.path().join("text-detection.onnx"), recognition: dir.path().join("text-recognition.onnx") }); + assert_eq!(Models::in_dir(dir.path()), expected, "a complete ONNX pair is sufficient"); + for file in ["text-detection.rten", "text-recognition.rten"] { + std::fs::write(dir.path().join(file), b"model").unwrap(); + } + assert_eq!(Models::in_dir(dir.path()), expected, "the complete ONNX pair takes precedence over legacy models"); + } + + /// An interrupted ONNX update still permits an intact legacy pair in the same directory. + #[test] + fn model_discovery_falls_back_to_legacy_when_the_onnx_pair_is_incomplete() { + for current in ["text-detection.onnx", "text-recognition.onnx"] { + let dir = tempfile::tempdir().unwrap(); + for file in [current, "text-detection.rten", "text-recognition.rten"] { + std::fs::write(dir.path().join(file), b"model").unwrap(); + } + assert_eq!( + Models::in_dir(dir.path()), + Some(Models { detection: dir.path().join("text-detection.rten"), recognition: dir.path().join("text-recognition.rten") }), + "{current} alone must not hide a complete legacy pair" + ); + } + } + + /// Detection and recognition must come from one complete format pair, never a mixed update. + #[test] + fn model_discovery_refuses_mixed_format_pairs() { + for pair in [["text-detection.onnx", "text-recognition.rten"], ["text-detection.rten", "text-recognition.onnx"]] { + let dir = tempfile::tempdir().unwrap(); + for file in pair { + std::fs::write(dir.path().join(file), b"model").unwrap(); + } + assert_eq!(Models::in_dir(dir.path()), None, "{pair:?} is not a complete model pair"); + } + } + + /// Existing source builds and PDFCRAFT_MODELS overrides retain their complete RTEN pair. + #[test] + fn model_discovery_keeps_legacy_only_installations() { + let dir = tempfile::tempdir().unwrap(); + assert_eq!(Models::in_dir(dir.path()), None); + std::fs::write(dir.path().join("text-detection.rten"), b"model").unwrap(); + assert_eq!(Models::in_dir(dir.path()), None, "one legacy model is incomplete"); + std::fs::write(dir.path().join("text-recognition.rten"), b"model").unwrap(); + assert_eq!( + Models::in_dir(dir.path()), + Some(Models { detection: dir.path().join("text-detection.rten"), recognition: dir.path().join("text-recognition.rten") }) + ); + } + /// #103: every release package's layout puts the models where the installed app looks. /// Mirrors packaging/{windows/package.ps1,macos/package.sh,linux/package.sh,freebsd/package.sh}. #[test] diff --git a/crates/organize/src/import/carry.rs b/crates/organize/src/import/carry.rs index 21c21b9be3..15a412e231 100644 --- a/crates/organize/src/import/carry.rs +++ b/crates/organize/src/import/carry.rs @@ -1,5 +1,5 @@ use super::copy::Copier; -use super::*; +use super::{Dict, Document, HashMap, HashSet, ObjRef, Object, OrganizeError, name_tree_entries}; /// Copy a source's document-level attachments (`/Names /EmbeddedFiles`) into `dst`. pub(super) fn collect_attachments(dst: &mut Document, src: &Document, out: &mut Vec<(Vec, Object)>) -> Result<(), OrganizeError> { diff --git a/crates/organize/src/import/combine.rs b/crates/organize/src/import/combine.rs index 09a1b0725a..06972ae101 100644 --- a/crates/organize/src/import/combine.rs +++ b/crates/organize/src/import/combine.rs @@ -1,5 +1,5 @@ use super::carry::{Mark, add_outline, collect_attachments, kept_bookmarks, set_attachments, source_outline, write_outline_level}; -use super::*; +use super::{Dict, Document, FieldConflicts, HashMap, ObjRef, Object, OrganizeError, import_pages_mapped, rebuild}; /// A new document containing copies of `pages` from `src` (Extract Pages / Split). /// Document information (title, author…) is carried over, and so is the print standard the diff --git a/crates/organize/src/import/copy.rs b/crates/organize/src/import/copy.rs index f78411806f..f4b5499625 100644 --- a/crates/organize/src/import/copy.rs +++ b/crates/organize/src/import/copy.rs @@ -1,4 +1,4 @@ -use super::*; +use super::{Dict, Document, HashMap, ObjRef, Object, OrganizeError, named_dest}; /// Keys that must not be followed when copying: they point back up or across the source /// document, and following them would drag in unrelated objects. diff --git a/crates/organize/src/import/fields.rs b/crates/organize/src/import/fields.rs index 98f69c69ec..44910d0406 100644 --- a/crates/organize/src/import/fields.rs +++ b/crates/organize/src/import/fields.rs @@ -1,5 +1,5 @@ use super::copy::WIDGET_KEYS; -use super::*; +use super::{Dict, Document, HashMap, HashSet, ObjRef, Object, OrganizeError, walk}; /// Rename the top-level fields about to be registered in `dst` whose fully-qualified names /// (`parent.T.child`) are already taken, so each imported field stays its own field instead of diff --git a/crates/preflight/src/lib.rs b/crates/preflight/src/lib.rs index 13ca8997e3..1df39ebf05 100644 --- a/crates/preflight/src/lib.rs +++ b/crates/preflight/src/lib.rs @@ -514,99 +514,163 @@ pub fn verify(doc: &Document, level: Level) -> Vec { issue("6.5.2", "Page {} has additional actions", Some((i + 1).to_string()), Some(i), true); } } - for (r, o) in &objs { - let Some(d) = dict_of(o) else { continue }; - let ty = d.name(b"Type"); - let sub = d.name(b"Subtype"); - // Actions anywhere (structure elements also have /S: their role), with the actions they - // chain to and those written directly in an /A or /OpenAction. - let own = (d.get(b"S").is_some() && is_action(d)).then_some(d); - let direct = [b"A".as_slice(), b"OpenAction"].map(|k| d.get(k).and_then(|a| a.as_dict())); - for a in [own].into_iter().chain(direct).flatten() { - if let Some(s) = chain_forbidden(doc, a) { - issue("6.5.1", "A {} action isn't allowed", Some(s), None, true); - } - } - // Annotations. - if ty == Some(b"Annot") || (sub.is_some() && d.get(b"Rect").is_some() && d.get(b"P").is_some()) { - let page = page_of(*r); - let name = sub.map(|s| String::from_utf8_lossy(s).into_owned()).unwrap_or_default(); - if sub.is_some_and(|s| FORBIDDEN_ANNOTS.contains(&s)) { - issue("6.3.1", "{} annotations aren't allowed", Some(name), page, true); - continue; - } - let f = d.int(b"F").unwrap_or(0); - if sub != Some(b"Popup") && (f & 4 == 0 || f & (1 | 2 | 32) != 0) { - issue("6.3.2", "A {} annotation isn't set to print, or is hidden", Some(name.clone()), page, true); - } - let has_ap = d.get(b"AP").map(|a| doc.resolve(a)).and_then(|a| a.as_dict().cloned()).is_some_and(|a| a.get(b"N").is_some()); - if !has_ap && !matches!(sub, Some(b"Popup") | Some(b"Link")) { - let zero = d.get(b"Rect").map(|x| doc.resolve(x)).and_then(|x| x.as_array().cloned()).is_some_and(|a| { - let v: Vec = a.iter().filter_map(|n| doc.resolve(n).as_f64()).collect(); - v.len() == 4 && (v[2] - v[0]).abs() < 1e-6 && (v[3] - v[1]).abs() < 1e-6 - }); - if !zero { - issue("6.3.3", "A {} annotation has no appearance stream", Some(name.clone()), page, false); - } - } - if d.get(b"AA").is_some() { - issue("6.5.2", "A {} annotation has additional actions", Some(name), page, true); - } - } - // Form fields with additional actions (non-widget fields). - if d.get(b"FT").is_some() && d.get(b"AA").is_some() && ty != Some(b"Annot") { - issue("6.5.2", "A form field has additional actions", None, None, true); - } - // Fonts. - if ty == Some(b"Font") || d.get(b"BaseFont").is_some() && sub.is_some() { - check_font(doc, d, &mut issue); - } - // Streams. - if let Object::Stream(s) = &**o { - let filters: Vec> = match s.dict.get(b"Filter").map(|f| doc.resolve(f)) { - Some(f) => match &*f { - Object::Name(n) => vec![n.clone()], - Object::Array(a) => a.iter().filter_map(|x| x.as_name().map(<[u8]>::to_vec)).collect(), - _ => Vec::new(), - }, - None => Vec::new(), - }; - if filters.iter().any(|f| f == b"LZWDecode") { - issue("6.1.7.2", "A stream uses LZW compression", None, None, false); - } - if s.dict.get(b"F").is_some() || s.dict.get(b"FFilter").is_some() { - issue("6.1.7.1", "A stream refers to an external file", None, None, false); - } - if sub == Some(b"Image") { - if matches!(s.dict.get(b"Interpolate"), Some(Object::Bool(true))) { - issue("6.2.8", "An image asks to be interpolated", None, None, true); - } - if s.dict.get(b"Alternates").is_some() || s.dict.get(b"OPI").is_some() { - issue("6.2.8", "An image has alternates or OPI information", None, None, true); - } - } - if sub == Some(b"PS") { - issue("6.2.9", "PostScript XObjects aren't allowed", None, None, false); - } - } - // Embedded files. - if ty == Some(b"Filespec") && d.get(b"EF").is_some() { - match level { - Level::A2b => issue("6.8", "Embedded files must be PDF/A files themselves (use PDF/A-3 for others)", None, None, false), - Level::A3b => { - if d.get(b"AFRelationship").is_none() { - issue("6.8", "An embedded file has no AFRelationship", None, None, true); - } - } - } - } - } + check_objects(doc, level, &objs, &page_of, &mut issue); // One message per kind of problem is enough for repeated ones (as preflight summaries do). let mut seen = std::collections::HashSet::new(); out.retain(|i| seen.insert((i.clause, i.message.clone(), i.page))); out } +fn check_objects( + doc: &Document, + level: Level, + objects: &[(ObjRef, std::sync::Arc)], + page_of: &impl Fn(ObjRef) -> Option, + issue: &mut impl FnMut(&'static str, &'static str, Option, Option, bool), +) { + for (r, o) in objects { + let Some(d) = dict_of(o) else { continue }; + check_one_object(doc, level, *r, d, o, page_of, issue); + } +} + +fn check_one_object( + doc: &Document, + level: Level, + reference: ObjRef, + dict: &Dict, + object: &Object, + page_of: &impl Fn(ObjRef) -> Option, + issue: &mut impl FnMut(&'static str, &'static str, Option, Option, bool), +) { + let ty = dict.name(b"Type"); + let subtype = dict.name(b"Subtype"); + check_actions(doc, dict, issue); + if is_annotation(dict, ty, subtype) && check_annotation(doc, dict, subtype, page_of(reference), issue) { + // A forbidden annotation stops every later check for its object, as the scan did before + // it was split into helpers: the rest of its own checks and the form field, font, stream + // and embedded file below all came after that `continue`. + return; + } + if dict.get(b"FT").is_some() && dict.get(b"AA").is_some() && ty != Some(b"Annot") { + issue("6.5.2", "A form field has additional actions", None, None, true); + } + if ty == Some(b"Font") || dict.get(b"BaseFont").is_some() && subtype.is_some() { + check_font(doc, dict, issue); + } + if let Object::Stream(stream) = object { + check_stream(doc, stream, subtype, issue); + } + if ty == Some(b"Filespec") && dict.get(b"EF").is_some() { + check_embedded_file(level, dict, issue); + } +} + +fn check_actions(doc: &Document, dict: &Dict, issue: &mut impl FnMut(&'static str, &'static str, Option, Option, bool)) { + let own = (dict.get(b"S").is_some() && is_action(dict)).then_some(dict); + let direct = [b"A".as_slice(), b"OpenAction"].map(|key| dict.get(key).and_then(|action| action.as_dict())); + for action in [own].into_iter().chain(direct).flatten() { + if let Some(name) = chain_forbidden(doc, action) { + issue("6.5.1", "A {} action isn't allowed", Some(name), None, true); + } + } +} + +fn is_annotation(dict: &Dict, ty: Option<&[u8]>, subtype: Option<&[u8]>) -> bool { + ty == Some(b"Annot") || (subtype.is_some() && dict.get(b"Rect").is_some() && dict.get(b"P").is_some()) +} + +fn check_annotation( + doc: &Document, + dict: &Dict, + subtype: Option<&[u8]>, + page: Option, + issue: &mut impl FnMut(&'static str, &'static str, Option, Option, bool), +) -> bool { + let name = subtype.map(|bytes| String::from_utf8_lossy(bytes).into_owned()).unwrap_or_default(); + if subtype.is_some_and(|value| FORBIDDEN_ANNOTS.contains(&value)) { + issue("6.3.1", "{} annotations aren't allowed", Some(name), page, true); + return true; + } + let flags = dict.int(b"F").unwrap_or(0); + if subtype != Some(b"Popup") && (flags & 4 == 0 || flags & (1 | 2 | 32) != 0) { + issue("6.3.2", "A {} annotation isn't set to print, or is hidden", Some(name.clone()), page, true); + } + check_annotation_appearance(doc, dict, subtype, &name, page, issue); + if dict.get(b"AA").is_some() { + issue("6.5.2", "A {} annotation has additional actions", Some(name), page, true); + } + false +} + +fn check_annotation_appearance( + doc: &Document, + dict: &Dict, + subtype: Option<&[u8]>, + name: &str, + page: Option, + issue: &mut impl FnMut(&'static str, &'static str, Option, Option, bool), +) { + let has_appearance = dict + .get(b"AP") + .map(|appearance| doc.resolve(appearance)) + .and_then(|appearance| appearance.as_dict().cloned()) + .is_some_and(|appearance| appearance.get(b"N").is_some()); + if has_appearance || matches!(subtype, Some(b"Popup") | Some(b"Link")) { + return; + } + let zero_area = dict.get(b"Rect").map(|rect| doc.resolve(rect)).and_then(|rect| rect.as_array().cloned()).is_some_and(|values| { + let values: Vec = values.iter().filter_map(|value| doc.resolve(value).as_f64()).collect(); + values.len() == 4 && (values[2] - values[0]).abs() < 1e-6 && (values[3] - values[1]).abs() < 1e-6 + }); + if !zero_area { + issue("6.3.3", "A {} annotation has no appearance stream", Some(name.to_owned()), page, false); + } +} + +fn check_stream( + doc: &Document, + stream: &pdfcraft_cos::Stream, + subtype: Option<&[u8]>, + issue: &mut impl FnMut(&'static str, &'static str, Option, Option, bool), +) { + let filters: Vec> = match stream.dict.get(b"Filter").map(|filter| doc.resolve(filter)) { + Some(filter) => match &*filter { + Object::Name(name) => vec![name.clone()], + Object::Array(filters) => filters.iter().filter_map(|filter| filter.as_name().map(<[u8]>::to_vec)).collect(), + _ => Vec::new(), + }, + None => Vec::new(), + }; + if filters.iter().any(|filter| filter == b"LZWDecode") { + issue("6.1.7.2", "A stream uses LZW compression", None, None, false); + } + if stream.dict.get(b"F").is_some() || stream.dict.get(b"FFilter").is_some() { + issue("6.1.7.1", "A stream refers to an external file", None, None, false); + } + if subtype == Some(b"Image") { + if matches!(stream.dict.get(b"Interpolate"), Some(Object::Bool(true))) { + issue("6.2.8", "An image asks to be interpolated", None, None, true); + } + if stream.dict.get(b"Alternates").is_some() || stream.dict.get(b"OPI").is_some() { + issue("6.2.8", "An image has alternates or OPI information", None, None, true); + } + } + if subtype == Some(b"PS") { + issue("6.2.9", "PostScript XObjects aren't allowed", None, None, false); + } +} + +fn check_embedded_file(level: Level, dict: &Dict, issue: &mut impl FnMut(&'static str, &'static str, Option, Option, bool)) { + match level { + Level::A2b => issue("6.8", "Embedded files must be PDF/A files themselves (use PDF/A-3 for others)", None, None, false), + Level::A3b if dict.get(b"AFRelationship").is_none() => { + issue("6.8", "An embedded file has no AFRelationship", None, None, true); + } + Level::A3b => {} + } +} + fn check_font(doc: &Document, d: &Dict, issue: &mut impl FnMut(&'static str, &'static str, Option, Option, bool)) { let sub = d.name(b"Subtype"); if sub == Some(b"Type3") { diff --git a/crates/print/src/imposition.rs b/crates/print/src/imposition.rs index 1257bcf25e..aa9a501f66 100644 --- a/crates/print/src/imposition.rs +++ b/crates/print/src/imposition.rs @@ -1,7 +1,7 @@ use super::error::PrintError; use super::settings::{Content, Settings}; use super::sheets::{Sheet, layout}; -use super::*; +use super::{DecodeBudget, Dict, Document, Matrix, ObjRef, Object, SaveOptions, Stream, write_full}; // Model-derived transforms and clipping bounds need their full PDF decimal precision. fn geometry_number(value: f64) -> String { diff --git a/crates/print/src/settings.rs b/crates/print/src/settings.rs index 7c9554f25e..0506eb5b18 100644 --- a/crates/print/src/settings.rs +++ b/crates/print/src/settings.rs @@ -1,4 +1,4 @@ -use super::*; +use super::spool; #[derive(Clone, Copy, Debug, PartialEq, Eq, Default)] pub enum Orientation { diff --git a/crates/print/src/sheets.rs b/crates/print/src/sheets.rs index ce80adc3eb..061a6ed5c3 100644 --- a/crates/print/src/sheets.rs +++ b/crates/print/src/sheets.rs @@ -1,7 +1,7 @@ use super::error::PrintError; use super::imposition::decoded_contents; use super::settings::{Binding, BookletSubset, Layout, Orientation, PAPERS, PageOrder, Settings, SizeMode}; -use super::*; +use super::{DecodeBudget, Dict, Document, Matrix, Object}; /// Whether most of page `index`'s text runs bottom-to-top as the page displays (a label laid /// sideways on a letter or A4 sheet), counting each text-showing operator once; form XObjects @@ -162,32 +162,7 @@ pub fn layout(sizes: &[(f64, f64)], settings: &Settings) -> Result, P } } Layout::Label { flip } => { - let size = oriented(paper, settings.orientation, false); - let cell = [LABEL_MARGIN, LABEL_MARGIN, size.0 - LABEL_MARGIN, size.1 - LABEL_MARGIN]; - for &p in &pages { - let d = sizes[p]; - let crop = settings.crops.get(p).copied().flatten(); - let rect = crop - .map(|c| [c.rect[0].max(0.0), c.rect[1].max(0.0), c.rect[2].min(d.0), c.rect[3].min(d.1)]) - .filter(|r| r[2] - r[0] > 1.0 && r[3] - r[1] > 1.0) - .unwrap_or([0.0, 0.0, d.0, d.1]); - let (w, h) = (rect[2] - rect[0], rect[3] - rect[1]); - let turn = (w > h) != (cell[2] - cell[0] > cell[3] - cell[1]); - let mut quarter = match (turn, crop.is_some_and(|c| c.text_up)) { - (false, _) => 0, - (true, true) => 3, - (true, false) => 1, - }; - if flip { - quarter = (quarter + 2) % 4; - } - let s = if turn { - fit_scale((h, w), (cell[2] - cell[0], cell[3] - cell[1])) - } else { - fit_scale((w, h), (cell[2] - cell[0], cell[3] - cell[1])) - }; - sheets.push(Sheet { size, placed: vec![place_crop(p, rect, cell, s, quarter)], ..Sheet::default() }); - } + sheets.extend(layout_labels(sizes, &pages, paper, settings.orientation, settings, flip)); } Layout::Multiple { cols, rows, per_sheet, order, border, auto_rotate } => { let cells = cols.checked_mul(rows).filter(|&n| n > 0 && n <= 256); @@ -348,3 +323,35 @@ pub fn layout(sizes: &[(f64, f64)], settings: &Settings) -> Result, P } Ok(sheets) } + +fn layout_labels(sizes: &[(f64, f64)], pages: &[usize], paper: (f64, f64), orientation: Orientation, settings: &Settings, flip: bool) -> Vec { + let size = oriented(paper, orientation, false); + let cell = [LABEL_MARGIN, LABEL_MARGIN, size.0 - LABEL_MARGIN, size.1 - LABEL_MARGIN]; + pages + .iter() + .map(|&p| { + let d = sizes[p]; + let crop = settings.crops.get(p).copied().flatten(); + let rect = crop + .map(|c| [c.rect[0].max(0.0), c.rect[1].max(0.0), c.rect[2].min(d.0), c.rect[3].min(d.1)]) + .filter(|r| r[2] - r[0] > 1.0 && r[3] - r[1] > 1.0) + .unwrap_or([0.0, 0.0, d.0, d.1]); + let (w, h) = (rect[2] - rect[0], rect[3] - rect[1]); + let turn = (w > h) != (cell[2] - cell[0] > cell[3] - cell[1]); + let mut quarter = match (turn, crop.is_some_and(|c| c.text_up)) { + (false, _) => 0, + (true, true) => 3, + (true, false) => 1, + }; + if flip { + quarter = (quarter + 2) % 4; + } + let s = if turn { + fit_scale((h, w), (cell[2] - cell[0], cell[3] - cell[1])) + } else { + fit_scale((w, h), (cell[2] - cell[0], cell[3] - cell[1])) + }; + Sheet { size, placed: vec![place_crop(p, rect, cell, s, quarter)], ..Sheet::default() } + }) + .collect() +} diff --git a/crates/redact/src/interp.rs b/crates/redact/src/interp.rs index 71b4684bc7..3baec29c2c 100644 --- a/crates/redact/src/interp.rs +++ b/crates/redact/src/interp.rs @@ -242,32 +242,21 @@ pub(crate) fn process(doc: &mut Document, scope: &mut Scope<'_>, streams: &[Vec< /// [`process`] from graphics state `gs`: a form XObject starts with its caller's, text state /// included (ISO 32000-2 §8.10.1), so text it shows without setting a font of its own is placed /// with the caller's font, size and spacing, as the renderer places it. -fn process_from(doc: &mut Document, scope: &mut Scope<'_>, streams: &[Vec], resources: &Dict, mut gs: Gs) -> Output { - let mut out = Output::default(); - let fallback = Rc::new(Metrics::fallback()); - let mut stack: Vec = Vec::new(); - let (mut tm, mut tlm) = (Matrix::IDENTITY, Matrix::IDENTITY); - let fonts_res = res_dict(doc, resources, b"Font"); - let ext_gstates = res_dict(doc, resources, b"ExtGState"); - let mut xobjects = res_dict(doc, resources, b"XObject"); - // The current path: its operators, its bounding box in user space, and whether it clips. - let mut path: Vec = Vec::new(); - let mut path_box: Option<[f64; 4]> = None; - let mut clip = false; - let mut forced_change = false; - +fn process_from(doc: &mut Document, scope: &mut Scope<'_>, streams: &[Vec], resources: &Dict, gs: Gs) -> Output { + let mut walk = Walk::new(doc, resources, gs); // The streams are one content stream in pieces, which may be split between any two tokens // (ISO 32000-2 §7.8.2): an operator's operands can end one piece and the operator start the // next. Parse them joined, then give each operator back to the piece its keyword is in. let joined = Pieces::join(streams); let mut parsed = joined.parse(); - out.ambiguous = parsed.ambiguous_images > 0; + walk.out.ambiguous = parsed.ambiguous_images > 0; // A rewritten piece loses its comments, so keep where they began and ended: a comment that // ran on into the next piece still hides that piece's first line. let comment_edges = joined.comment_edges(&parsed); // Layer removal also changes enclosing replacement spans, so remember the operators before // any cleanup, not just the survivors of the layer pass. let original = parsed.ops.clone(); + let mut forced_change = false; if scope.layers_enabled { let props = res_dict(doc, resources, b"Properties"); let (kept, removed) = strip_hidden_layers(doc, scope, parsed.ops, &props); @@ -277,12 +266,32 @@ fn process_from(doc: &mut Document, scope: &mut Scope<'_>, streams: &[Vec], forced_change = true; } } - let mut pieces: Vec> = streams.iter().map(|_| Vec::new()).collect(); - let mut rewrite: Vec = vec![forced_change; streams.len()]; - for op in parsed.ops { + let (pieces, rewrite) = split_into_pieces(&joined, parsed.ops, streams.len(), forced_change); + let mut processed = Vec::new(); + for (piece, changed) in pieces.into_iter().zip(rewrite) { + let mut done = Piece { ops: Vec::with_capacity(piece.len()), changed }; + for op in piece { + walk.step(doc, scope, resources, op, &mut done); + } + if !walk.path.is_empty() { + done.ops.append(&mut walk.path); + } + processed.push((done.ops, done.changed)); + } + if scope.mode == Mode::Apply { + clean_replacements(doc, resources, &original, &mut processed, scope.report); + } + walk.out.streams = processed.into_iter().zip(comment_edges).map(|((ops, changed), edges)| changed.then(|| piece_bytes(&ops, edges))).collect(); + walk.out +} + +/// Gives each operator to the piece its keyword is in. An operator split across pieces is written +/// whole into its keyword's piece, so every piece it spans is rewritten. +fn split_into_pieces(joined: &Pieces, ops: Vec, count: usize, forced_change: bool) -> (Vec>, Vec) { + let mut pieces: Vec> = (0..count).map(|_| Vec::new()).collect(); + let mut rewrite: Vec = vec![forced_change; count]; + for op in ops { let (first, last) = joined.pieces_of(&op); - // An operator split across pieces is written whole into its keyword's piece, so every - // piece it spans is rewritten. if first < last { for r in rewrite.iter_mut().take(last + 1).skip(first) { *r = true; @@ -292,228 +301,297 @@ fn process_from(doc: &mut Document, scope: &mut Scope<'_>, streams: &[Vec], p.push(op); } } + (pieces, rewrite) +} - let mut processed = Vec::new(); - for (piece, mut changed) in pieces.into_iter().zip(rewrite) { - let mut ops: Vec = Vec::with_capacity(piece.len()); - for op in piece { - let o = op.op.as_slice(); - // Path construction. - if matches!(o, b"m" | b"l" | b"c" | b"v" | b"y" | b"h" | b"re" | b"W" | b"W*") { - let pts: Vec<(f64, f64)> = match o { - b"re" => op.nums::<4>().map(|[x, y, w, h]| vec![(x, y), (x + w, y), (x, y + h), (x + w, y + h)]).unwrap_or_default(), - b"h" | b"W" | b"W*" => Vec::new(), - _ => op.operands.iter().filter_map(Object::as_f64).collect::>().as_chunks::<2>().0.iter().map(|p| (p[0], p[1])).collect(), - }; - for (x, y) in pts { - let (u, v) = gs.ctm.apply(x, y); - path_box = Some(match path_box { - None => [u, v, u, v], - Some(b) => [b[0].min(u), b[1].min(v), b[2].max(u), b[3].max(v)], - }); - } - clip |= matches!(o, b"W" | b"W*"); - path.push(op); - continue; - } - if matches!(o, b"S" | b"s" | b"f" | b"F" | b"f*" | b"B" | b"B*" | b"b" | b"b*" | b"n") { - let body = std::mem::take(&mut path); - let bbox = path_box.take(); - let clips = std::mem::replace(&mut clip, false); - let hit = scope.mode == Mode::Apply && o != b"n" && bbox.is_some_and(|b| scope.hits(b)); - if !hit { - ops.extend(body); - ops.push(op); - continue; - } - let b = bbox.unwrap_or_default(); - changed = true; - scope.report.paths_removed += 1; - if scope.covered(b) && clips { - // Keep the clipping, drop the painting. - ops.extend(body); - ops.push(Op::new("n", vec![])); - } - // Partial vector redaction must not retain underlying drawing commands - // behind clipping (F-008). Refuse partial clip retention and remove the path. - continue; - } - if !path.is_empty() { - // A path not ended by a painting operator: pass it through. - ops.append(&mut path); - path_box = None; - clip = false; - } - match o { - b"q" => stack.push(gs.clone()), - b"Q" => { - if let Some(g) = stack.pop() { - gs = g; - } - } - b"cm" => { - if let Some(m) = op.nums::<6>() { - gs.ctm = Matrix(m).then(&gs.ctm); - } - } - b"BT" => { - tm = Matrix::IDENTITY; - tlm = Matrix::IDENTITY; - } - b"Tf" => { - gs.size = op.num(1).unwrap_or(gs.size); - if let Some(name) = op.name(0) { - let font_dict = fonts_res.get(name).and_then(|f| doc.resolve(f).as_dict().cloned()); - gs.vertical = font_dict.as_ref().is_some_and(|d| is_vertical(doc, d)); - gs.font = match scope.fonts.get(name) { - Some(f) => f.clone(), - None => { - let m = font_dict.as_ref().map(|d| Rc::new(Metrics::from_dict(doc, d))).unwrap_or_else(|| fallback.clone()); - scope.fonts.insert(name.to_vec(), m.clone()); - m - } - }; - } - } - b"gs" => { - if let Some((font, vertical, size)) = op.name(0).and_then(|n| extgstate_font(doc, scope, &ext_gstates, n, &fallback)) { - (gs.font, gs.vertical, gs.size) = (font, vertical, size); - } - } - b"Tc" => gs.char_spacing = op.num(0).unwrap_or(0.0), - b"Tw" => gs.word_spacing = op.num(0).unwrap_or(0.0), - b"Tz" => gs.scale = op.num(0).unwrap_or(100.0) / 100.0, - b"TL" => gs.leading = op.num(0).unwrap_or(0.0), - b"Ts" => gs.rise = op.num(0).unwrap_or(0.0), - b"Tr" => gs.render_mode = op.num(0).unwrap_or(0.0) as i64, - b"Td" | b"TD" => { - if let Some([x, y]) = op.nums::<2>() { - if o == b"TD" { - gs.leading = -y; - } - tlm = Matrix::translate(x, y).then(&tlm); - tm = tlm; - } - } - b"Tm" => { - if let Some(m) = op.nums::<6>() { - tlm = Matrix(m); - tm = tlm; - } - } - b"T*" => { - tlm = Matrix::translate(0.0, -gs.leading).then(&tlm); - tm = tlm; - } - b"Tj" | b"TJ" | b"'" | b"\"" => { - if o == b"\"" { - gs.word_spacing = op.num(0).unwrap_or(gs.word_spacing); - gs.char_spacing = op.num(1).unwrap_or(gs.char_spacing); - } - if matches!(o, b"'" | b"\"") { - tlm = Matrix::translate(0.0, -gs.leading).then(&tlm); - tm = tlm; - } - let items: Vec = match o { - // A surplus array (`[(A)] [(B)] TJ`) is malformed, but the operator still - // takes the one immediately before it, as the renderer and every other - // reader here do (#3569), so a redaction search matches what is drawn. - b"TJ" => op.operands.last().and_then(Object::as_array).cloned().unwrap_or_default(), - _ => op.operands.last().cloned().into_iter().collect(), - }; - // Vertical-writing text is laid out horizontally by `show`, so its glyphs are - // never matched against a region. Rather than ship a document whose vertical - // text was silently left under a mark, record it so apply can fail closed. - // (Full vertical-text removal is a future enhancement.) - if gs.vertical - && scope.mode == Mode::Apply - && scope.hidden_text.is_none() - && !scope.rects.is_empty() - && items.iter().any(|o| matches!(o, Object::String(s) if !s.bytes.is_empty())) - { - out.vertical = true; - } - let (new_items, removed) = show(scope, &gs, &mut tm, &items); - if removed == 0 { - ops.push(op); - continue; - } - if scope.mode == Mode::Verify { - out.residue += removed; - ops.push(op); - continue; - } - changed = true; - scope.report.glyphs += removed; - match o { - b"\"" => { - ops.push(Op::new("Tw", vec![num(gs.word_spacing)])); - ops.push(Op::new("Tc", vec![num(gs.char_spacing)])); - ops.push(Op::new("T*", vec![])); - } - b"'" => ops.push(Op::new("T*", vec![])), - _ => {} - } - ops.push(Op::new("TJ", vec![Object::Array(new_items)])); - continue; - } - b"BI" => { - let b = gs.ctm.bbox([0.0, 0.0, 1.0, 1.0]); - if scope.hits(b) { - if scope.mode == Mode::Verify { - out.residue += 1; - } else { - scope.report.images_removed += 1; - changed = true; - continue; - } - } - } - b"sh" if scope.mode == Mode::Apply => { - // A shading fills the current clip: clip the regions out. - if let Some(c) = clip_out(scope.rects, &gs.ctm, [-1e6, -1e6, 1e6, 1e6]) { - changed = true; - ops.push(Op::new("q", vec![])); - ops.extend(c); - ops.push(op); - ops.push(Op::new("Q", vec![])); - continue; - } - } - b"Do" => { - if let Some(new) = xobject(doc, scope, &op, &gs, resources, &mut xobjects, &mut out) { - changed = true; - if let Some(n) = new { - ops.push(n); - } - continue; - } - } - _ => {} - } - ops.push(op); +/// A rewritten piece's bytes. `(comment_in, comment_out)` say whether the piece before ended +/// inside a comment, and whether this one did. +fn piece_bytes(ops: &[Op], (comment_in, comment_out): (bool, bool)) -> Vec { + // The piece before still ends inside a comment: end it before the first operator. + let mut bytes = if comment_in { b"\n".to_vec() } else { Vec::new() }; + bytes.extend(serialize_ops(ops)); + // The piece ended inside a comment that hid the start of the next one: keep it open. + if comment_out { + bytes.push(b'%'); + } + bytes +} + +/// The operators written for one piece of a scope's content, and whether they differ from the source. +struct Piece { + ops: Vec, + changed: bool, +} + +/// The interpreter state carried across the operators of a scope. +struct Walk { + gs: Gs, + stack: Vec, + tm: Matrix, + tlm: Matrix, + fonts_res: Dict, + ext_gstates: Dict, + xobjects: Dict, + fallback: Rc, + /// The current path: its operators, its bounding box in user space, and whether it clips. + path: Vec, + path_box: Option<[f64; 4]>, + clip: bool, + out: Output, +} + +impl Walk { + fn new(doc: &Document, resources: &Dict, gs: Gs) -> Self { + Self { + gs, + stack: Vec::new(), + tm: Matrix::IDENTITY, + tlm: Matrix::IDENTITY, + fonts_res: res_dict(doc, resources, b"Font"), + ext_gstates: res_dict(doc, resources, b"ExtGState"), + xobjects: res_dict(doc, resources, b"XObject"), + fallback: Rc::new(Metrics::fallback()), + path: Vec::new(), + path_box: None, + clip: false, + out: Output::default(), } - if !path.is_empty() { - ops.append(&mut path); + } + + /// Interprets one operator, writing what replaces it to `piece`. + fn step(&mut self, doc: &mut Document, scope: &mut Scope<'_>, resources: &Dict, op: Op, piece: &mut Piece) { + let o = op.op.as_slice(); + if matches!(o, b"m" | b"l" | b"c" | b"v" | b"y" | b"h" | b"re" | b"W" | b"W*") { + self.construct_path(op); + return; } - processed.push((ops, changed)); - } - if scope.mode == Mode::Apply { - clean_replacements(doc, resources, &original, &mut processed, scope.report); - } - for ((ops, changed), (comment_in, comment_out)) in processed.into_iter().zip(comment_edges) { - out.streams.push(changed.then(|| { - // The piece before still ends inside a comment: end it before the first operator. - let mut bytes = if comment_in { b"\n".to_vec() } else { Vec::new() }; - bytes.extend(serialize_ops(&ops)); - // The piece ended inside a comment that hid the start of the next one: keep it open. - if comment_out { - bytes.push(b'%'); + if matches!(o, b"S" | b"s" | b"f" | b"F" | b"f*" | b"B" | b"B*" | b"b" | b"b*" | b"n") { + self.paint_path(scope, op, piece); + return; + } + if !self.path.is_empty() { + // A path not ended by a painting operator: pass it through. + piece.ops.append(&mut self.path); + self.path_box = None; + self.clip = false; + } + let kept = match o { + b"q" | b"Q" | b"cm" | b"Tf" | b"gs" => { + self.graphics_state(doc, scope, &op); + Some(op) } - bytes - })); + b"BT" | b"Tc" | b"Tw" | b"Tz" | b"TL" | b"Ts" | b"Tr" | b"Td" | b"TD" | b"Tm" | b"T*" => { + self.text_state(&op); + Some(op) + } + b"Tj" | b"TJ" | b"'" | b"\"" => self.show_text(scope, op, piece), + b"BI" => Self::inline_image(&self.gs, scope, &mut self.out, op, piece), + b"sh" if scope.mode == Mode::Apply => Self::shading(&self.gs, scope, op, piece), + b"Do" => self.draw_xobject(doc, scope, resources, op, piece), + _ => Some(op), + }; + piece.ops.extend(kept); + } + + /// Path construction: collects the operator and grows the path's bounding box. + fn construct_path(&mut self, op: Op) { + let o = op.op.as_slice(); + let pts: Vec<(f64, f64)> = match o { + b"re" => op.nums::<4>().map(|[x, y, w, h]| vec![(x, y), (x + w, y), (x, y + h), (x + w, y + h)]).unwrap_or_default(), + b"h" | b"W" | b"W*" => Vec::new(), + _ => op.operands.iter().filter_map(Object::as_f64).collect::>().as_chunks::<2>().0.iter().map(|p| (p[0], p[1])).collect(), + }; + for (x, y) in pts { + let (u, v) = self.gs.ctm.apply(x, y); + self.path_box = Some(match self.path_box { + None => [u, v, u, v], + Some(b) => [b[0].min(u), b[1].min(v), b[2].max(u), b[3].max(v)], + }); + } + self.clip |= matches!(o, b"W" | b"W*"); + self.path.push(op); + } + + /// A painting operator ends the path; one under a region is removed (or kept as a clip). + fn paint_path(&mut self, scope: &mut Scope<'_>, op: Op, piece: &mut Piece) { + let body = std::mem::take(&mut self.path); + let bbox = self.path_box.take(); + let clips = std::mem::replace(&mut self.clip, false); + let hit = scope.mode == Mode::Apply && op.op.as_slice() != b"n" && bbox.is_some_and(|b| scope.hits(b)); + if !hit { + piece.ops.extend(body); + piece.ops.push(op); + return; + } + let b = bbox.unwrap_or_default(); + piece.changed = true; + scope.report.paths_removed += 1; + if scope.covered(b) && clips { + // Keep the clipping, drop the painting. + piece.ops.extend(body); + piece.ops.push(Op::new("n", vec![])); + } + // Partial vector redaction must not retain underlying drawing commands + // behind clipping (F-008). Refuse partial clip retention and remove the path. + } + + fn graphics_state(&mut self, doc: &Document, scope: &mut Scope<'_>, op: &Op) { + match op.op.as_slice() { + b"q" => self.stack.push(self.gs.clone()), + b"Q" => { + if let Some(g) = self.stack.pop() { + self.gs = g; + } + } + b"cm" => { + if let Some(m) = op.nums::<6>() { + self.gs.ctm = Matrix(m).then(&self.gs.ctm); + } + } + b"Tf" => self.select_font(doc, scope, op), + _ => { + if let Some((font, vertical, size)) = op.name(0).and_then(|n| extgstate_font(doc, scope, &self.ext_gstates, n, &self.fallback)) { + (self.gs.font, self.gs.vertical, self.gs.size) = (font, vertical, size); + } + } + } + } + + fn select_font(&mut self, doc: &Document, scope: &mut Scope<'_>, op: &Op) { + self.gs.size = op.num(1).unwrap_or(self.gs.size); + let Some(name) = op.name(0) else { return }; + let font_dict = self.fonts_res.get(name).and_then(|f| doc.resolve(f).as_dict().cloned()); + self.gs.vertical = font_dict.as_ref().is_some_and(|d| is_vertical(doc, d)); + self.gs.font = match scope.fonts.get(name) { + Some(f) => f.clone(), + None => { + let m = font_dict.as_ref().map_or_else(|| self.fallback.clone(), |d| Rc::new(Metrics::from_dict(doc, d))); + scope.fonts.insert(name.to_vec(), m.clone()); + m + } + }; + } + + /// Text state and text-positioning operators. + fn text_state(&mut self, op: &Op) { + let gs = &mut self.gs; + match op.op.as_slice() { + b"BT" => { + self.tm = Matrix::IDENTITY; + self.tlm = Matrix::IDENTITY; + } + b"Tc" => gs.char_spacing = op.num(0).unwrap_or(0.0), + b"Tw" => gs.word_spacing = op.num(0).unwrap_or(0.0), + b"Tz" => gs.scale = op.num(0).unwrap_or(100.0) / 100.0, + b"TL" => gs.leading = op.num(0).unwrap_or(0.0), + b"Ts" => gs.rise = op.num(0).unwrap_or(0.0), + b"Tr" => gs.render_mode = op.num(0).unwrap_or(0.0) as i64, + b"Td" | b"TD" => { + if let Some([x, y]) = op.nums::<2>() { + if op.is("TD") { + gs.leading = -y; + } + self.tlm = Matrix::translate(x, y).then(&self.tlm); + self.tm = self.tlm; + } + } + b"Tm" => { + if let Some(m) = op.nums::<6>() { + self.tlm = Matrix(m); + self.tm = self.tlm; + } + } + _ => { + self.tlm = Matrix::translate(0.0, -gs.leading).then(&self.tlm); + self.tm = self.tlm; + } + } + } + + /// `Tj`, `TJ`, `'` and `"`: glyphs under a region are cut out (or counted, when verifying). + fn show_text(&mut self, scope: &mut Scope<'_>, op: Op, piece: &mut Piece) -> Option { + let o = op.op.as_slice(); + if o == b"\"" { + self.gs.word_spacing = op.num(0).unwrap_or(self.gs.word_spacing); + self.gs.char_spacing = op.num(1).unwrap_or(self.gs.char_spacing); + } + if matches!(o, b"'" | b"\"") { + self.tlm = Matrix::translate(0.0, -self.gs.leading).then(&self.tlm); + self.tm = self.tlm; + } + let items: Vec = match o { + // A surplus array (`[(A)] [(B)] TJ`) is malformed, but the operator still + // takes the one immediately before it, as the renderer and every other + // reader here do (#3569), so a redaction search matches what is drawn. + b"TJ" => op.operands.last().and_then(Object::as_array).cloned().unwrap_or_default(), + _ => op.operands.last().cloned().into_iter().collect(), + }; + // Vertical-writing text is laid out horizontally by `show`, so its glyphs are + // never matched against a region. Rather than ship a document whose vertical + // text was silently left under a mark, record it so apply can fail closed. + // (Full vertical-text removal is a future enhancement.) + if self.gs.vertical + && scope.mode == Mode::Apply + && scope.hidden_text.is_none() + && !scope.rects.is_empty() + && items.iter().any(|o| matches!(o, Object::String(s) if !s.bytes.is_empty())) + { + self.out.vertical = true; + } + let (new_items, removed) = show(scope, &self.gs, &mut self.tm, &items); + if removed == 0 { + return Some(op); + } + if scope.mode == Mode::Verify { + self.out.residue += removed; + return Some(op); + } + piece.changed = true; + scope.report.glyphs += removed; + match op.op.as_slice() { + b"\"" => { + piece.ops.push(Op::new("Tw", vec![num(self.gs.word_spacing)])); + piece.ops.push(Op::new("Tc", vec![num(self.gs.char_spacing)])); + piece.ops.push(Op::new("T*", vec![])); + } + b"'" => piece.ops.push(Op::new("T*", vec![])), + _ => {} + } + piece.ops.push(Op::new("TJ", vec![Object::Array(new_items)])); + None + } + + /// An inline image under a region is removed (or counted, when verifying). + fn inline_image(gs: &Gs, scope: &mut Scope<'_>, out: &mut Output, op: Op, piece: &mut Piece) -> Option { + if !scope.hits(gs.ctm.bbox([0.0, 0.0, 1.0, 1.0])) { + return Some(op); + } + if scope.mode == Mode::Verify { + out.residue += 1; + return Some(op); + } + scope.report.images_removed += 1; + piece.changed = true; + None + } + + /// A shading fills the current clip: the regions are clipped out. + fn shading(gs: &Gs, scope: &Scope<'_>, op: Op, piece: &mut Piece) -> Option { + let Some(c) = clip_out(scope.rects, &gs.ctm, [-1e6, -1e6, 1e6, 1e6]) else { return Some(op) }; + piece.changed = true; + piece.ops.push(Op::new("q", vec![])); + piece.ops.extend(c); + piece.ops.push(op); + piece.ops.push(Op::new("Q", vec![])); + None + } + + fn draw_xobject(&mut self, doc: &mut Document, scope: &mut Scope<'_>, resources: &Dict, op: Op, piece: &mut Piece) -> Option { + let Some(new) = xobject(doc, scope, &op, &self.gs, resources, &mut self.xobjects, &mut self.out) else { return Some(op) }; + piece.changed = true; + piece.ops.extend(new); + None } - out } fn clean_replacements(doc: &Document, resources: &Dict, original: &[Op], processed: &mut [(Vec, bool)], report: &mut Report) { diff --git a/crates/redact/src/interp/layers.rs b/crates/redact/src/interp/layers.rs index 32d7afdf1e..88d1c4e677 100644 --- a/crates/redact/src/interp/layers.rs +++ b/crates/redact/src/interp/layers.rs @@ -1,4 +1,4 @@ -use super::*; +use super::{Dict, Document, HashSet, ObjRef, Object, Op, Scope}; impl<'a> Scope<'a> { /// Is this optional-content reference (an OCG or OCMD) hidden? diff --git a/crates/redact/src/interp/prune.rs b/crates/redact/src/interp/prune.rs index 2708a87a42..6ca5ea2803 100644 --- a/crates/redact/src/interp/prune.rs +++ b/crates/redact/src/interp/prune.rs @@ -1,4 +1,7 @@ -use super::*; +use super::{ + CosError, Dict, Document, HashMap, HashSet, MAX_DEPTH, Matrix, Metrics, ObjRef, Object, Op, Pieces, Rc, RedactError, Scope, is_vertical, num, + overlaps, page_streams, res_dict, +}; /// Drop every `replaced` resource name whose `Do` no longer appears in the rewritten `content`, /// so a full-rewrite save stops reaching the original image or form it named. A name that some diff --git a/crates/redact/src/lib.rs b/crates/redact/src/lib.rs index 6f69151d89..de9dafe7db 100644 --- a/crates/redact/src/lib.rs +++ b/crates/redact/src/lib.rs @@ -409,193 +409,24 @@ fn apply_to(doc: &mut Document, pages: Option<&[usize]>) -> Result, _>>()?; report.pages = by_page.len(); localize_resources(doc, &by_page)?; - let mut doomed_fields: Vec = Vec::new(); - // The original image and form XObjects the rewrite drops or replaces, on any page. - let mut doomed_xobjects: Vec = Vec::new(); - let mut retired_properties = Vec::new(); let widget_owner: Vec<(ObjRef, ObjRef)> = pdfcraft_forms::fields(doc).into_iter().flat_map(|f| f.widgets.iter().map(|w| (w.obj, f.obj)).collect::>()).collect(); let listed_before = listed_annotations(doc); - let mut removed_everywhere: HashSet = HashSet::new(); - + let mut applying = Applying { + report, + doomed_fields: Vec::new(), + doomed_xobjects: Vec::new(), + retired_properties: Vec::new(), + widget_owner, + removed_everywhere: HashSet::new(), + }; for &(pi, page_marks) in &groups { let page = pdfcraft_model::pages(doc).swap_remove(pi); let rects: Vec<[f64; 4]> = page_marks.iter().flat_map(|m| m.rects.iter().copied()).collect(); - - // 1. Content. - let mut budget = pdfcraft_cos::DecodeBudget::page(); - let (list, data) = page_streams_within(doc, &page.dict, pi, &mut budget)?; - let resources = page.dict.get(b"Resources").and_then(|r| doc.resolve(r).as_dict().cloned()).unwrap_or_default(); - let out = { - let mut scope = Scope::new(&rects, Mode::Apply, &mut report, budget); - process(doc, &mut scope, &data, &resources, pdfcraft_content::Matrix::IDENTITY) - }; - // Fail closed: the interpreter lays vertical-writing text out horizontally, so it cannot - // tell whether those glyphs lie under a mark. Rather than report success and possibly - // leave the text in place, refuse the whole operation (the caller keeps the previous - // document). The error does not claim the text was under the mark. Full vertical-text - // removal is a future enhancement. - if let Some(error) = out.error { - return Err(error.into()); - } - if out.vertical { - return Err(RedactError::VerticalText(pi + 1)); - } - // An inline image the renderer reads no image for (no `EI` it accepts, or parameters it - // can't read): where the page's operators resume after it is a guess, so neither removal - // nor the verify pass can be trusted on this page. - if out.ambiguous { - return Err(RedactError::Unreadable(pi + 1)); - } - doomed_xobjects.extend_from_slice(&out.doomed); - retired_properties.extend(out.retired_properties); - let mut new_list = list.clone(); - let mut changed = false; - for (i, new) in out.streams.into_iter().enumerate() { - let Some(bytes) = new else { continue }; - let mut dict = match &*doc.resolve(&list[i]) { - Object::Stream(s) => s.dict.clone(), - _ => Dict::new(), - }; - dict.remove(b"Length"); - // Edit ▸ Add content keeps an added item's source text in `/PCAdded`; once its glyphs - // are redacted, keeping it would leave the redacted text in the file. The item stays - // as plain drawn content but is no longer editable. - dict.remove(b"PCAdded"); - // A new object: the original may be shared with other pages. - new_list[i] = Object::Ref(doc.add(Object::Stream(Stream::flate(dict, &bytes)))); - changed = true; - } - if changed || !out.xobjects.is_empty() || !out.replaced.is_empty() { - let mut res = resources.clone(); - if !out.xobjects.is_empty() || !out.replaced.is_empty() { - let mut xo = res.get(b"XObject").and_then(|x| doc.resolve(x).as_dict().cloned()).unwrap_or_default(); - // A full save keeps whatever is still referenced: unlink the originals this page no - // longer draws so the removed image or form bytes cannot survive in the saved file. - let page_content: Vec> = new_list - .iter() - .map(|o| match &*doc.resolve(o) { - Object::Stream(s) => s.decoded().unwrap_or_default(), - _ => Vec::new(), - }) - .collect(); - interp::prune(&mut xo, &out.replaced, &page_content); - for (n, r) in &out.xobjects { - xo.set(n.clone(), Object::Ref(*r)); - } - res.set(b"XObject".to_vec(), Object::Dict(xo)); - } - let (_, cleaned_data) = page_streams( - doc, - &{ - let mut cleaned_page = page.dict.clone(); - cleaned_page.set(b"Contents".to_vec(), Object::Array(new_list.clone())); - cleaned_page - }, - pi, - )?; - retired_properties.extend(interp::prune_properties(doc, &mut res, &cleaned_data)?); - type3::prune_type3_from_resources(doc, &mut res, &cleaned_data)?; - doc.update_dict(page.obj, |d| { - d.set(b"Contents".to_vec(), Object::Array(new_list)); - d.set(b"Resources".to_vec(), Object::Dict(res)); - })?; - // Tags must not keep what the page no longer shows. - let after = doc.get(page.obj).as_dict().cloned().unwrap_or_default(); - let (_, new_data) = page_streams(doc, &after, pi)?; - let (changed_ids, empty_ids) = - tags::touched(doc, &resources, pdfcraft_content::Pieces::join(&data).data(), pdfcraft_content::Pieces::join(&new_data).data()); - report.tags += tags::clean(doc, page.obj, None, &changed_ids, &empty_ids)?; - } - - for (old, new, changed, empty) in out.tag_changes { - report.tags += tags::clean(doc, page.obj, Some((old, new)), &changed, &empty)?; - } - - // 2. Annotations: the marks, and whatever lies under them (with their pop-ups). - let annots = annots_of(doc, &doc.get(page.obj).as_dict().cloned().unwrap_or_default()); - let mut removed: Vec = Vec::new(); - for a in &annots { - let Some(r) = a.as_ref() else { continue }; - let obj = doc.get(r); - let Some(d) = obj.as_dict() else { continue }; - let subtype = d.name(b"Subtype").unwrap_or(b""); - if subtype == b"Redact" { - if page_marks.iter().any(|m| m.obj == r) { - removed.push(r); - } - continue; - } - if subtype == b"Popup" { - continue; - } - if rect_of(doc, d.get(b"Rect")).is_some_and(|b| rects.iter().any(|x| pdfcraft_content::overlaps(*x, b, 0.0))) { - removed.push(r); - if subtype == b"Widget" { - if let Some((_, field)) = widget_owner.iter().find(|(w, _)| *w == r) - && !doomed_fields.contains(field) - { - doomed_fields.push(*field); - } - } else { - report.annotations += 1; - } - } - } - // Replies (`/IRT`, ISO 32000-2 §12.5.6.2) to a removed annotation go too, and replies to - // those: a reply placed elsewhere would keep its parent — the comment and the QuadPoints - // of the redacted words — in the file through its `/IRT` (#2659). Each pass removes at - // least one more annotation of this page or stops, so it ends. - let replies: Vec<(ObjRef, ObjRef)> = annots - .iter() - .filter_map(Object::as_ref) - .filter_map(|r| { - let obj = doc.get(r); - let d = obj.as_dict()?; - (d.name(b"Subtype") != Some(b"Widget")).then_some(())?; - Some((r, d.get(b"IRT").and_then(Object::as_ref)?)) - }) - .collect(); - loop { - let before = removed.len(); - for (r, parent) in &replies { - if !removed.contains(r) && removed.contains(parent) { - removed.push(*r); - report.annotations += 1; - } - } - if removed.len() == before { - break; - } - } - removed_everywhere.extend(removed.iter().copied()); - // Pop-ups dropped with their parent below count too: a reply on another page may answer one. - for a in &annots { - let Some(r) = a.as_ref() else { continue }; - if doc.get(r).as_dict().and_then(|d| d.get(b"Parent")).and_then(Object::as_ref).is_some_and(|p| removed.contains(&p)) { - removed_everywhere.insert(r); - } - } - let kept: Vec = annots - .into_iter() - .filter(|a| { - let Some(r) = a.as_ref() else { return true }; - if removed.contains(&r) { - return false; - } - // Pop-ups of removed annotations go too. - let obj = doc.get(r); - !obj.as_dict().and_then(|d| d.get(b"Parent")).and_then(Object::as_ref).is_some_and(|p| removed.contains(&p)) - }) - .collect(); - doc.update_dict(page.obj, |d| { - if kept.is_empty() { - d.remove(b"Annots"); - } else { - d.set(b"Annots".to_vec(), Object::Array(kept)); - } - })?; + redact_page_content(doc, &mut applying, pi, &page, &rects)?; + remove_page_annotations(doc, &mut applying, &page, &rects, page_marks)?; } + let Applying { mut report, doomed_fields, doomed_xobjects, retired_properties, mut removed_everywhere, .. } = applying; // 2b. Replies and pop-ups of a removed annotation can be listed on another page than their // parent: their `/IRT` or `/Parent` would keep the removed comment reachable. @@ -702,6 +533,213 @@ fn apply_to(doc: &mut Document, pages: Option<&[usize]>) -> Result, + /// The original image and form XObjects the rewrite drops or replaces, on any page. + doomed_xobjects: Vec, + retired_properties: Vec, + widget_owner: Vec<(ObjRef, ObjRef)>, + removed_everywhere: HashSet, +} + +/// Step 1 for one page: rewrites its content so nothing readable stays under a mark, and cleans the tags it no longer shows. +fn redact_page_content( + doc: &mut Document, + applying: &mut Applying, + pi: usize, + page: &pdfcraft_model::Page, + rects: &[[f64; 4]], +) -> Result<(), RedactError> { + let Applying { report, doomed_xobjects, retired_properties, .. } = applying; + // 1. Content. + let mut budget = pdfcraft_cos::DecodeBudget::page(); + let (list, data) = page_streams_within(doc, &page.dict, pi, &mut budget)?; + let resources = page.dict.get(b"Resources").and_then(|r| doc.resolve(r).as_dict().cloned()).unwrap_or_default(); + let out = { + let mut scope = Scope::new(rects, Mode::Apply, report, budget); + process(doc, &mut scope, &data, &resources, pdfcraft_content::Matrix::IDENTITY) + }; + // Fail closed: the interpreter lays vertical-writing text out horizontally, so it cannot + // tell whether those glyphs lie under a mark. Rather than report success and possibly + // leave the text in place, refuse the whole operation (the caller keeps the previous + // document). The error does not claim the text was under the mark. Full vertical-text + // removal is a future enhancement. + if let Some(error) = out.error { + return Err(error.into()); + } + if out.vertical { + return Err(RedactError::VerticalText(pi + 1)); + } + // An inline image the renderer reads no image for (no `EI` it accepts, or parameters it + // can't read): where the page's operators resume after it is a guess, so neither removal + // nor the verify pass can be trusted on this page. + if out.ambiguous { + return Err(RedactError::Unreadable(pi + 1)); + } + doomed_xobjects.extend_from_slice(&out.doomed); + retired_properties.extend(out.retired_properties); + let mut new_list = list.clone(); + let mut changed = false; + for (i, new) in out.streams.into_iter().enumerate() { + let Some(bytes) = new else { continue }; + let mut dict = match &*doc.resolve(&list[i]) { + Object::Stream(s) => s.dict.clone(), + _ => Dict::new(), + }; + dict.remove(b"Length"); + // Edit ▸ Add content keeps an added item's source text in `/PCAdded`; once its glyphs + // are redacted, keeping it would leave the redacted text in the file. The item stays + // as plain drawn content but is no longer editable. + dict.remove(b"PCAdded"); + // A new object: the original may be shared with other pages. + new_list[i] = Object::Ref(doc.add(Object::Stream(Stream::flate(dict, &bytes)))); + changed = true; + } + if changed || !out.xobjects.is_empty() || !out.replaced.is_empty() { + let mut res = resources.clone(); + if !out.xobjects.is_empty() || !out.replaced.is_empty() { + let mut xo = res.get(b"XObject").and_then(|x| doc.resolve(x).as_dict().cloned()).unwrap_or_default(); + // A full save keeps whatever is still referenced: unlink the originals this page no + // longer draws so the removed image or form bytes cannot survive in the saved file. + let page_content: Vec> = new_list + .iter() + .map(|o| match &*doc.resolve(o) { + Object::Stream(s) => s.decoded().unwrap_or_default(), + _ => Vec::new(), + }) + .collect(); + interp::prune(&mut xo, &out.replaced, &page_content); + for (n, r) in &out.xobjects { + xo.set(n.clone(), Object::Ref(*r)); + } + res.set(b"XObject".to_vec(), Object::Dict(xo)); + } + let (_, cleaned_data) = page_streams( + doc, + &{ + let mut cleaned_page = page.dict.clone(); + cleaned_page.set(b"Contents".to_vec(), Object::Array(new_list.clone())); + cleaned_page + }, + pi, + )?; + retired_properties.extend(interp::prune_properties(doc, &mut res, &cleaned_data)?); + type3::prune_type3_from_resources(doc, &mut res, &cleaned_data)?; + doc.update_dict(page.obj, |d| { + d.set(b"Contents".to_vec(), Object::Array(new_list)); + d.set(b"Resources".to_vec(), Object::Dict(res)); + })?; + // Tags must not keep what the page no longer shows. + let after = doc.get(page.obj).as_dict().cloned().unwrap_or_default(); + let (_, new_data) = page_streams(doc, &after, pi)?; + let (changed_ids, empty_ids) = + tags::touched(doc, &resources, pdfcraft_content::Pieces::join(&data).data(), pdfcraft_content::Pieces::join(&new_data).data()); + report.tags += tags::clean(doc, page.obj, None, &changed_ids, &empty_ids)?; + } + + for (old, new, changed, empty) in out.tag_changes { + report.tags += tags::clean(doc, page.obj, Some((old, new)), &changed, &empty)?; + } + Ok(()) +} + +/// Step 2 for one page: the marks, and whatever lies under them (with their pop-ups). +fn remove_page_annotations( + doc: &mut Document, + applying: &mut Applying, + page: &pdfcraft_model::Page, + rects: &[[f64; 4]], + page_marks: &[&Mark], +) -> Result<(), RedactError> { + let Applying { report, doomed_fields, widget_owner, removed_everywhere, .. } = applying; + // 2. Annotations: the marks, and whatever lies under them (with their pop-ups). + let annots = annots_of(doc, &doc.get(page.obj).as_dict().cloned().unwrap_or_default()); + let mut removed: Vec = Vec::new(); + for a in &annots { + let Some(r) = a.as_ref() else { continue }; + let obj = doc.get(r); + let Some(d) = obj.as_dict() else { continue }; + let subtype = d.name(b"Subtype").unwrap_or(b""); + if subtype == b"Redact" { + if page_marks.iter().any(|m| m.obj == r) { + removed.push(r); + } + continue; + } + if subtype == b"Popup" { + continue; + } + if rect_of(doc, d.get(b"Rect")).is_some_and(|b| rects.iter().any(|x| pdfcraft_content::overlaps(*x, b, 0.0))) { + removed.push(r); + if subtype == b"Widget" { + if let Some((_, field)) = widget_owner.iter().find(|(w, _)| *w == r) + && !doomed_fields.contains(field) + { + doomed_fields.push(*field); + } + } else { + report.annotations += 1; + } + } + } + // Replies (`/IRT`, ISO 32000-2 §12.5.6.2) to a removed annotation go too, and replies to + // those: a reply placed elsewhere would keep its parent — the comment and the QuadPoints + // of the redacted words — in the file through its `/IRT` (#2659). Each pass removes at + // least one more annotation of this page or stops, so it ends. + let replies: Vec<(ObjRef, ObjRef)> = annots + .iter() + .filter_map(Object::as_ref) + .filter_map(|r| { + let obj = doc.get(r); + let d = obj.as_dict()?; + (d.name(b"Subtype") != Some(b"Widget")).then_some(())?; + Some((r, d.get(b"IRT").and_then(Object::as_ref)?)) + }) + .collect(); + loop { + let before = removed.len(); + for (r, parent) in &replies { + if !removed.contains(r) && removed.contains(parent) { + removed.push(*r); + report.annotations += 1; + } + } + if removed.len() == before { + break; + } + } + removed_everywhere.extend(removed.iter().copied()); + // Pop-ups dropped with their parent below count too: a reply on another page may answer one. + for a in &annots { + let Some(r) = a.as_ref() else { continue }; + if doc.get(r).as_dict().and_then(|d| d.get(b"Parent")).and_then(Object::as_ref).is_some_and(|p| removed.contains(&p)) { + removed_everywhere.insert(r); + } + } + let kept: Vec = annots + .into_iter() + .filter(|a| { + let Some(r) = a.as_ref() else { return true }; + if removed.contains(&r) { + return false; + } + // Pop-ups of removed annotations go too. + let obj = doc.get(r); + !obj.as_dict().and_then(|d| d.get(b"Parent")).and_then(Object::as_ref).is_some_and(|p| removed.contains(&p)) + }) + .collect(); + doc.update_dict(page.obj, |d| { + if kept.is_empty() { + d.remove(b"Annots"); + } else { + d.set(b"Annots".to_vec(), Object::Array(kept)); + } + })?; + Ok(()) +} + /// Remove redaction marks without applying them (`None` = all), with their replies and pop-ups as /// deleting a comment does: a reply left behind would keep its mark in the file through `/IRT`. /// Returns how many marks went. diff --git a/crates/redact/src/type3.rs b/crates/redact/src/type3.rs index f431dab902..57971571af 100644 --- a/crates/redact/src/type3.rs +++ b/crates/redact/src/type3.rs @@ -178,42 +178,38 @@ fn collect_used_resources_in_stream(data: &[u8], used: &mut UsedInGlyphs) -> Res Ok(()) } -fn prune_type3_font_resources(doc: &Document, font_res: &mut Dict, used: &UsedInGlyphs) -> bool { - let mut changed = false; - - macro_rules! prune_category { - ($cat:expr, $used_set:expr) => { - if let Some(sub_obj) = font_res.get($cat) { - let mut sub = doc.resolve(sub_obj).as_dict().cloned().unwrap_or_default(); - let names: Vec> = sub.iter().map(|(n, _)| n.to_vec()).collect(); - let mut cat_changed = false; - for n in names { - if !$used_set.contains(&n) { - sub.remove(&n); - cat_changed = true; - } - } - if cat_changed { - changed = true; - if sub.is_empty() { - font_res.remove($cat); - } else { - font_res.set($cat.to_vec(), Object::Dict(sub)); - } - } - } - }; +/// Removes the entries of `font_res`'s `category` sub-dictionary that `used` does not name, +/// dropping the sub-dictionary when nothing is left. Whether anything changed. +fn prune_category(doc: &Document, font_res: &mut Dict, category: &[u8], used: &HashSet>) -> bool { + let Some(sub_obj) = font_res.get(category) else { return false }; + let mut sub = doc.resolve(sub_obj).as_dict().cloned().unwrap_or_default(); + let unused: Vec> = sub.iter().map(|(n, _)| n.to_vec()).filter(|n| !used.contains(n)).collect(); + if unused.is_empty() { + return false; } + for name in &unused { + sub.remove(name); + } + if sub.is_empty() { + font_res.remove(category); + } else { + font_res.set(category.to_vec(), Object::Dict(sub)); + } + true +} - prune_category!(b"XObject", used.xobjects); - prune_category!(b"ColorSpace", used.colorspaces); - prune_category!(b"Pattern", used.patterns); - prune_category!(b"Shading", used.shadings); - prune_category!(b"ExtGState", used.extgstates); - prune_category!(b"Font", used.fonts); - prune_category!(b"Properties", used.properties); - - changed +fn prune_type3_font_resources(doc: &Document, font_res: &mut Dict, used: &UsedInGlyphs) -> bool { + let categories: [(&[u8], &HashSet>); 7] = [ + (b"XObject", &used.xobjects), + (b"ColorSpace", &used.colorspaces), + (b"Pattern", &used.patterns), + (b"Shading", &used.shadings), + (b"ExtGState", &used.extgstates), + (b"Font", &used.fonts), + (b"Properties", &used.properties), + ]; + // Every category is pruned, even after an earlier one changed. + categories.into_iter().fold(false, |changed, (category, names)| prune_category(doc, font_res, category, names) | changed) } struct ScanContext<'a> { diff --git a/crates/render/src/inspect/annotations.rs b/crates/render/src/inspect/annotations.rs index 07283c0473..603aa88110 100644 --- a/crates/render/src/inspect/annotations.rs +++ b/crates/render/src/inspect/annotations.rs @@ -1,7 +1,7 @@ use super::core::{limited_pdf_string, pretty_date, spend}; use super::model::{Annotation, AttachmentSource, DestView, Field, FieldKind, LayerOp, Link, LinkTarget, RemoteDestination, link_replies}; use super::navigation::text_string; -use super::*; +use super::{Dictionary, DocInfo, Entry, HashMap, HashSet, Inspector, Object, ObjectId}; /// At most this many `/State` entries of a set-layer-visibility action are read. const MAX_LAYER_STATE: usize = 1024; diff --git a/crates/render/src/inspect/core.rs b/crates/render/src/inspect/core.rs index 875d873654..c190dc565b 100644 --- a/crates/render/src/inspect/core.rs +++ b/crates/render/src/inspect/core.rs @@ -1,7 +1,10 @@ use super::annotations::MAX_LINK_ATTACHMENT_TEXT_BYTES; use super::model::{AttachmentSource, PageInfo, Xfa}; use super::navigation::text_string; -use super::*; +use super::{ + Arc, AssertUnwindSafe, DecryptionError, Dictionary, DocInfo, Document, HashMap, HashSet, LazyStructure, LoadOptions, LoadPdfError, Object, + ObjectId, OnceCell, OpenError, Pdf, Structure, catch_unwind, +}; /// lopdf decodes object and cross-reference streams while it loads, with no limit unless one is /// set: a few hundred bytes of nested FlateDecode then inflate to gigabytes. Real object and diff --git a/crates/render/src/inspect/model.rs b/crates/render/src/inspect/model.rs index e5f09c9242..490897b60f 100644 --- a/crates/render/src/inspect/model.rs +++ b/crates/render/src/inspect/model.rs @@ -1,4 +1,4 @@ -use super::*; +use super::HashMap; /// What kind of XFA form a document has (`/AcroForm /XFA`). #[derive(Clone, Copy, Debug, PartialEq, Eq)] diff --git a/crates/render/src/inspect/navigation.rs b/crates/render/src/inspect/navigation.rs index 173217c93b..4000a74135 100644 --- a/crates/render/src/inspect/navigation.rs +++ b/crates/render/src/inspect/navigation.rs @@ -2,7 +2,10 @@ use super::core::inspect; use super::core::spend; use super::model::{DestView, OutlineItem, PageInfo}; -use super::*; +use super::{ + BTreeMap, Dictionary, HashMap, HashSet, Inspector, MAX_LABEL_BYTES, MAX_LABEL_TOTAL_BYTES, MAX_LABEL_TREE_DEPTH, MAX_LABEL_TREE_WORK, + MAX_PREFIX_BYTES, MAX_PREFIX_TOTAL_BYTES, Object, ObjectId, alpha, roman, +}; /// `DocInfo::outline` holds the first this many bookmarks in outline order. Opening a document /// reads only this window; the rest are listed by page through `pdfcraft_organize`. diff --git a/crates/render/src/inspect/resources.rs b/crates/render/src/inspect/resources.rs index 0386c5781f..0895c64f8a 100644 --- a/crates/render/src/inspect/resources.rs +++ b/crates/render/src/inspect/resources.rs @@ -3,7 +3,7 @@ use super::core::inspect; use super::core::{Inspector, load_options}; use super::model::{Attachment, AttachmentSource, FontInfo, Layer, PageTransition, TransitionStyle}; use super::navigation::NameTreeSeen; -use super::*; +use super::{AssertUnwindSafe, Dictionary, DocInfo, Document, HashSet, Object, ObjectId, catch_unwind}; /// Decoded bytes read from an XFA form's configuration packet (or a whole-XDP `/XFA` stream) to /// find `dynamicRender`. Designer's packets are a few kilobytes; a whole XDP can hold the template. diff --git a/crates/render/src/raster/pool.rs b/crates/render/src/raster/pool.rs index 81447263d8..6da0c14d42 100644 --- a/crates/render/src/raster/pool.rs +++ b/crates/render/src/raster/pool.rs @@ -1,4 +1,10 @@ -use super::*; +use super::{ + Arc, AssertUnwindSafe, AtomicRenderStats, InterpreterSettings, JoinHandle, Mutex, Ordering, PageRenderer, Pdf, Pixels, RenderCache, RenderConfig, + RenderRequest, RenderStats, RenderedPage, RequestFailureKey, RequestKind, ResultReceiver, Stopwatch, SyncSender, WorkQueue, catch_unwind, finish, + panic_message, parse, render_page, take_warnings, warning_settings, +}; +#[cfg(not(target_arch = "wasm32"))] +use super::{AtomicBool, Receiver, sync_channel}; /// How long one page may render before the pool gives up on it (the watchdog). pub const STUCK_AFTER: std::time::Duration = std::time::Duration::from_secs(20); diff --git a/crates/render/src/text/device.rs b/crates/render/src/text/device.rs index 4079239d74..7c4881e8be 100644 --- a/crates/render/src/text/device.rs +++ b/crates/render/src/text/device.rs @@ -1,5 +1,8 @@ use super::layout::{Flow, along_baseline, arrange_flow, compatible, continues, from_upright, to_upright, unrolled}; -use super::*; +use super::{ + Affine, BezPath, BlendMode, ClipPath, Context, Device, Glyph, GlyphDrawMode, HashMap, Image, InterpreterCache, InterpreterSettings, PageText, + Paint, PathDrawMode, Pdf, Rect, Shape, SoftMask, TextFilter, TextGlyph, TransformExt, interpret_page, +}; /// Largest sine of the angle between a glyph's writing direction and a flow's for the glyph to be /// laid out in that flow's frame. Turning an em box by θ moves its edges along the line by up to diff --git a/crates/render/src/text/layout.rs b/crates/render/src/text/layout.rs index 302184aebc..00b45e266c 100644 --- a/crates/render/src/text/layout.rs +++ b/crates/render/src/text/layout.rs @@ -1,6 +1,6 @@ use super::device::{DIRECTION_TOLERANCE, Drawn, WORD_GAP}; use super::order::{NONE, REDRAW_CANDIDATES, Run, Scratch, Seg, fingerprint, place_glyphs, redraws, restarts_run, reverse_rtl}; -use super::*; +use super::{HashMap, PageText, TextGlyph}; /// Glyphs in reading order, as indices into the page's glyphs, with their lines and word gaps. pub(super) struct Flow { diff --git a/crates/render/src/text/order.rs b/crates/render/src/text/order.rs index 6892d3f2ab..d8cb65f32c 100644 --- a/crates/render/src/text/order.rs +++ b/crates/render/src/text/order.rs @@ -1,5 +1,5 @@ +use super::TextGlyph; use super::layout::{is_rtl, union}; -use super::*; /// Glyphs `start..end` of the glyph list [`arrange`] lays out, drawn one after another. #[derive(Clone, Copy, Debug, PartialEq, Eq)] diff --git a/crates/sign/src/cms.rs b/crates/sign/src/cms.rs index b148ea4d19..4e232af616 100644 --- a/crates/sign/src/cms.rs +++ b/crates/sign/src/cms.rs @@ -376,7 +376,7 @@ pub fn sign_detached( alg: DigestAlg, content_digest: &[u8], ) -> Result, SignError> { - build(key, cert, chain, alg, DATA, None, content_digest) + build(SignedDataInput { key, cert, chain, alg, content_type: DATA, content: None, content_digest }) } /// A CMS SignedData that encapsulates `content` under `content_type` (an RFC 3161 token wraps @@ -389,20 +389,23 @@ pub fn sign_encapsulated( content_type: &str, content: &[u8], ) -> Result, SignError> { - build(key, cert, chain, alg, content_type, Some(content), &alg.digest(&[content])) + let content_digest = alg.digest(&[content]); + build(SignedDataInput { key, cert, chain, alg, content_type, content: Some(content), content_digest: &content_digest }) } -// The parameters mirror the SignedData fields being assembled. -#[allow(clippy::too_many_arguments)] -fn build( - key: &PrivateKey, - cert: &Certificate, - chain: &[Certificate], +/// The values needed to assemble a CMS SignedData object. +struct SignedDataInput<'a> { + key: &'a PrivateKey, + cert: &'a Certificate, + chain: &'a [Certificate], alg: DigestAlg, - content_type: &str, - content: Option<&[u8]>, - content_digest: &[u8], -) -> Result, SignError> { + content_type: &'a str, + content: Option<&'a [u8]>, + content_digest: &'a [u8], +} + +fn build(input: SignedDataInput<'_>) -> Result, SignError> { + let SignedDataInput { key, cert, chain, alg, content_type, content, content_digest } = input; let cert_hash = DigestAlg::Sha256.digest(&[&cert.raw]); let general_names = der::seq(&[&der::explicit(4, &cert.issuer.raw)]); let ess = der::seq(&[&der::seq(&[&der::seq(&[&der::octets(&cert_hash), &der::seq(&[&general_names, &der::uint(&cert.serial)])])])]); diff --git a/crates/sign/src/pdf/changes.rs b/crates/sign/src/pdf/changes.rs index 2c66418a6c..3a10a74e41 100644 --- a/crates/sign/src/pdf/changes.rs +++ b/crates/sign/src/pdf/changes.rs @@ -1,5 +1,5 @@ use super::types::{Modification, kind}; -use super::*; +use super::{Arc, Dict, Document, HashMap, HashSet, ObjRef, Object}; /// What later revisions changed, classified as Acrobat reports it, under DocMDP `p` (or none: /// an approval signature permits form fill, comments and further signatures). @@ -72,6 +72,18 @@ pub(super) fn classify_changes(doc: &Document, old: Option, p: Option< if doc.root() != old.root() { disallowed.push(kind::STRUCTURE); } + let classifier = ChangedObjectClassifier { + doc, + old: &old, + old_content: &old_content, + old_metadata, + old_xfa_data: &old_xfa_data, + signed_pages: &signed_pages, + signed_annots: &signed_annots, + signed_resources: &signed_resources, + old_info, + dss: &dss, + }; for num in doc.object_numbers() { if same_place(num) { continue; @@ -93,75 +105,7 @@ pub(super) fn classify_changes(doc: &Document, old: Option, p: Option< // graphics state does not make that a form fill. A container (the resources dictionary, // a category dictionary) that kept every entry it had and only gained names changes // nothing the signed content draws, and is judged as before. - let kept_entries = |d: &Dict| before.as_deref().and_then(Object::as_dict).is_some_and(|b| b.iter().all(|(k, v)| d.get(k) == Some(v))); - let resource_kind = match (signed_resources.get(&r), &*new) { - (Some(false), _) => Some(kind::PAGE_CONTENT), - (Some(true), Object::Dict(d)) if kept_entries(d) => None, - (Some(true), _) => Some(kind::PAGE_CONTENT), - (None, _) => None, - }; - let what = match (resource_kind, &*new) { - (Some(k), _) => k, - // The Document Security Store's own arrays and dictionaries, when they only grew. - (_, _) if dss.contains(&num) => kind::SECURITY_STORE, - // A signed page's indirect /Annots array, still an array: what it lost, then what it - // gained. Dropping a signed annotation is never hidden behind an added signature. - (_, Object::Array(now)) if signed_annots.contains(&r) && before.as_deref().is_some_and(|b| b.as_array().is_some()) => { - let was: HashSet = - before.as_deref().and_then(Object::as_array).map(|a| a.iter().filter_map(Object::as_ref).collect()).unwrap_or_default(); - let kept: HashSet = now.iter().filter_map(Object::as_ref).collect(); - let removed: Vec = was.iter().filter(|r| !kept.contains(r)).copied().collect(); - if removed.is_empty() { - let added: Vec = now.iter().filter_map(Object::as_ref).filter(|r| !was.contains(r)).collect(); - added_annots(doc, &added) - } else if removed.iter().any(|r| old.get(*r).as_dict().is_some_and(|d| d.name(b"Subtype") == Some(b"Widget"))) { - // A form field or signature widget taken off the page: no permission covers it. - kind::OTHER - } else { - // Deleting comments is a comment change (permitted at P 3 only). - kind::COMMENTS - } - } - (_, Object::Dict(d)) => { - let was = before.as_deref().and_then(Object::as_dict); - if signed_pages.contains(&r) { - // A signed page is always judged by what the page shows, whatever it is now - // relabelled: a rewritten /Contents or /Resources is a page content change. - page_change_kind(doc, &old, d, was) - } else if was.is_some() && Some(r) == old_info { - // Only the signed revision's own /Info dictionary is a metadata change. - kind::METADATA - } else { - change_kind(doc, &old, d, was) - } - } - (_, Object::Stream(s)) => { - // File plumbing is what the stream was when signed: the /Type it has now is - // written by whoever changed it, and the renderer ignores /Type (a page's Form - // XObject relabelled /ObjStm still draws its new content). - let was_plumbing = matches!(before.as_deref(), Some(Object::Stream(b)) if matches!(b.dict.name(b"Type"), Some(b"XRef" | b"ObjStm"))); - if old_content.contains(&r) { - kind::PAGE_CONTENT - } else if before.is_none() || was_plumbing { - continue; - } else if s.dict.name(b"Type") == Some(b"Metadata") && Some(r) == old_metadata { - // Only the signed catalog's XMP stream. A /Type /Metadata label on anything - // else, even one it already had when signed (a page's Form XObject: the - // renderer ignores /Type), does not make rewriting it a metadata change. - kind::METADATA - } else if old_xfa_data.contains(&r) { - // The form's XFA data (`datasets`) or state (`form`) as the signed revision - // named it: filling an XFA form rewrites these, as a Reader Extensions (UR3) - // save of a certified form does (#2759). The role comes from the signed - // revision, so a later one can't name page content as XFA data. - kind::FORM_FILL - } else { - kind::OTHER - } - } - _ if before.is_none() => continue, - _ => kind::OTHER, - }; + let Some(what) = classifier.classify(r, &new, before.as_deref()) else { continue }; let ok = match (what, p) { (kind::SIGNATURE | kind::SECURITY_STORE, _) => true, (kind::FORM_FILL, Some(2 | 3) | None) => true, @@ -195,6 +139,102 @@ pub(super) fn classify_changes(doc: &Document, old: Option, p: Option< if disallowed.is_empty() { Modification::Allowed(allowed) } else { Modification::Disallowed(disallowed) } } +struct ChangedObjectClassifier<'a> { + doc: &'a Document, + old: &'a Document, + old_content: &'a HashSet, + old_metadata: Option, + old_xfa_data: &'a HashSet, + signed_pages: &'a HashSet, + signed_annots: &'a HashSet, + signed_resources: &'a HashMap, + old_info: Option, + dss: &'a HashSet, +} + +impl ChangedObjectClassifier<'_> { + fn classify(&self, r: ObjRef, new: &Object, before: Option<&Object>) -> Option<&'static str> { + if let Some(kind) = self.resource_kind(r, new, before) { + return Some(kind); + } + if self.dss.contains(&r.num) { + return Some(kind::SECURITY_STORE); + } + match new { + Object::Array(now) if self.is_signed_annotation_array(r, before) => Some(self.annotation_array_change(now, before)), + Object::Dict(dict) => Some(self.dictionary_change(r, dict, before)), + Object::Stream(stream) => self.stream_change(r, stream, before), + _ if before.is_none() => None, + _ => Some(kind::OTHER), + } + } + + fn resource_kind(&self, r: ObjRef, new: &Object, before: Option<&Object>) -> Option<&'static str> { + match (self.signed_resources.get(&r), new) { + (Some(false), _) => Some(kind::PAGE_CONTENT), + (Some(true), Object::Dict(dict)) if self.keeps_previous_entries(dict, before) => None, + (Some(true), _) => Some(kind::PAGE_CONTENT), + (None, _) => None, + } + } + + fn keeps_previous_entries(&self, dict: &Dict, before: Option<&Object>) -> bool { + before.and_then(Object::as_dict).is_some_and(|previous| previous.iter().all(|(key, value)| dict.get(key) == Some(value))) + } + + fn is_signed_annotation_array(&self, r: ObjRef, before: Option<&Object>) -> bool { + self.signed_annots.contains(&r) && before.is_some_and(|object| object.as_array().is_some()) + } + + fn annotation_array_change(&self, now: &[Object], before: Option<&Object>) -> &'static str { + let was: HashSet = + before.and_then(Object::as_array).map(|items| items.iter().filter_map(Object::as_ref).collect()).unwrap_or_default(); + let kept: HashSet = now.iter().filter_map(Object::as_ref).collect(); + let removed: Vec = was.iter().filter(|reference| !kept.contains(reference)).copied().collect(); + if removed.is_empty() { + let added: Vec = now.iter().filter_map(Object::as_ref).filter(|reference| !was.contains(reference)).collect(); + added_annots(self.doc, &added) + } else if removed.iter().any(|reference| self.old.get(*reference).as_dict().is_some_and(|dict| dict.name(b"Subtype") == Some(b"Widget"))) { + // A form field or signature widget taken off the page: no permission covers it. + kind::OTHER + } else { + // Deleting comments is a comment change (permitted at P 3 only). + kind::COMMENTS + } + } + + fn dictionary_change(&self, r: ObjRef, dict: &Dict, before: Option<&Object>) -> &'static str { + let previous = before.and_then(Object::as_dict); + if self.signed_pages.contains(&r) { + // A signed page is judged by what the page shows, whatever its new labels say. + page_change_kind(self.doc, self.old, dict, previous) + } else if previous.is_some() && Some(r) == self.old_info { + // Only the signed revision's own /Info dictionary is a metadata change. + kind::METADATA + } else { + change_kind(self.doc, self.old, dict, previous) + } + } + + fn stream_change(&self, r: ObjRef, stream: &pdfcraft_cos::Stream, before: Option<&Object>) -> Option<&'static str> { + // File plumbing is the stream's role when signed; a later /Type label cannot change it. + let was_plumbing = matches!(before, Some(Object::Stream(previous)) if matches!(previous.dict.name(b"Type"), Some(b"XRef" | b"ObjStm"))); + if self.old_content.contains(&r) { + Some(kind::PAGE_CONTENT) + } else if before.is_none() || was_plumbing { + None + } else if stream.dict.name(b"Type") == Some(b"Metadata") && Some(r) == self.old_metadata { + // Only the signed catalog's XMP stream is metadata. + Some(kind::METADATA) + } else if self.old_xfa_data.contains(&r) { + // Signed XFA data and state packets are changed by a form fill. + Some(kind::FORM_FILL) + } else { + Some(kind::OTHER) + } + } +} + /// The streams of `doc`'s XFA form that hold its data and state: the `datasets` and `form` /// packets of the AcroForm's `/XFA` array (name, stream, name, stream, …). A form given as one /// XFA stream holds its template too, and is not listed. diff --git a/crates/sign/src/pdf/listing.rs b/crates/sign/src/pdf/listing.rs index 88379b1836..cbcf339715 100644 --- a/crates/sign/src/pdf/listing.rs +++ b/crates/sign/src/pdf/listing.rs @@ -1,6 +1,6 @@ use super::types::{Modification, Status, TrustStore}; use super::validate::{is_doc_timestamp, validate_doc_timestamp, validate_into}; -use super::*; +use super::{Arc, Dict, DigestAlg, Document, HashMap, HashSet, ObjRef, Object, SignatureInfo}; /// Digests of signed byte ranges (and parsed signed revisions), kept across revalidations of /// one document: incremental edits only append to the file, so the signed bytes and their diff --git a/crates/sign/src/pdf/signing.rs b/crates/sign/src/pdf/signing.rs index 0d00c68a61..71dd10b302 100644 --- a/crates/sign/src/pdf/signing.rs +++ b/crates/sign/src/pdf/signing.rs @@ -1,5 +1,5 @@ use super::listing::{mk_rotation, nums, sig_fields}; -use super::*; +use super::{Certificate, Dict, DigestAlg, DigitalId, Document, HashSet, Object, PdfString, SaveOptions, SignError, SignedData, Stream}; // ── signing ───────────────────────────────────────────────────────────────────────────────── diff --git a/crates/sign/src/pdf/types.rs b/crates/sign/src/pdf/types.rs index c061bc3699..881f503573 100644 --- a/crates/sign/src/pdf/types.rs +++ b/crates/sign/src/pdf/types.rs @@ -1,4 +1,4 @@ -use super::*; +use super::Certificate; /// Certificates the user trusts for signing (Acrobat: Trusted Certificates). #[derive(Clone, Debug, Default)] diff --git a/crates/sign/src/pdf/validate.rs b/crates/sign/src/pdf/validate.rs index 1f0b8c3424..08b482c4b4 100644 --- a/crates/sign/src/pdf/validate.rs +++ b/crates/sign/src/pdf/validate.rs @@ -1,7 +1,25 @@ use super::changes::classify_changes; use super::listing::{DigestCache, list, nums, sig_fields, text}; use super::types::{Detail, Fill, Modification, Status, TrustStore}; -use super::*; +use super::{ + Certificate, Dict, DigestAlg, Document, HashSet, ObjRef, Object, SignError, SignatureInfo, SignedData, Time, build_chain, build_chain_noted, +}; + +struct SignatureValidation<'a> { + doc: &'a Document, + bytes: &'a [u8], + trust: &'a TrustStore, + info: &'a mut SignatureInfo, + cache: &'a DigestCache, +} + +struct VerifiedSignature<'a> { + covered: usize, + certificate: Certificate, + embedded: &'a [Certificate], + cms_time: Option