diff --git a/mateclaw-desktop/scripts/README.md b/mateclaw-desktop/scripts/README.md new file mode 100644 index 00000000..b6ed4528 --- /dev/null +++ b/mateclaw-desktop/scripts/README.md @@ -0,0 +1,170 @@ +# MateClaw Desktop - Build & Publish Scripts + +## Scripts + +| Script | Description | +|--------|-------------| +| `build.sh` | Build backend JAR (frontend + Spring Boot) | +| `download-jre.sh` | Download Adoptium JRE 21 for target platform | +| `build-all-platforms.sh` | One-click build for all platforms (macOS + Windows) | +| `publish-github.sh` | Publish release artifacts to GitHub Releases | + +## Quick Start + +### Full Build + Publish (recommended) + +```bash +cd mateclaw-desktop + +# Step 1: Build for all platforms (no publish) +bash scripts/build-all-platforms.sh --all + +# Step 2: Publish to GitHub (via proxy) +bash scripts/publish-github.sh --proxy +``` + +### Step-by-Step Build + +```bash +cd mateclaw-desktop + +# 1. Build backend JAR (frontend + Spring Boot) +bash scripts/build.sh + +# 2. Download JRE for target platform +bash scripts/download-jre.sh mac-arm64 # Apple Silicon +bash scripts/download-jre.sh mac-x64 # Intel Mac +bash scripts/download-jre.sh win-x64 # Windows x64 +bash scripts/download-jre.sh win-arm64 # Windows ARM + +# 3. Build frontend and package +npm run build +npx electron-builder --mac # macOS +npx electron-builder --win --x64 # Windows x64 +npx electron-builder --win --arm64 # Windows ARM +``` + +## build.sh + +Build the backend JAR, includes three steps: + +1. Build Vue 3 frontend to `mateclaw-server/src/main/resources/static` +2. Package Spring Boot fat JAR via Maven +3. Copy JAR to `mateclaw-desktop/resources/app.jar` + +```bash +bash scripts/build.sh +``` + +**Prerequisites:** Node.js (pnpm or npm), Maven (or mvnw) + +## download-jre.sh + +Download Adoptium JRE 21 for the target platform. + +```bash +# Auto-detect current platform +bash scripts/download-jre.sh + +# Specify platform +bash scripts/download-jre.sh mac-arm64 +bash scripts/download-jre.sh mac-x64 +bash scripts/download-jre.sh win-x64 +bash scripts/download-jre.sh win-arm64 +``` + +JRE will be saved to `resources/jre/{os}-{arch}/`. + +## build-all-platforms.sh + +Orchestrates the full build pipeline: JAR build -> JRE download -> frontend compile -> electron-builder package. + +```bash +bash scripts/build-all-platforms.sh --all # macOS + Windows +bash scripts/build-all-platforms.sh --mac-only # macOS only +bash scripts/build-all-platforms.sh --win-only # Windows only +``` + +Build artifacts are output to `release/` directory. + +## publish-github.sh + +Publish build artifacts from `release/` to GitHub Releases via `gh` CLI. + +### Basic Usage + +```bash +bash scripts/publish-github.sh # Direct upload +bash scripts/publish-github.sh --draft # Create draft release +bash scripts/publish-github.sh --tag=v1.1.0 # Custom tag +``` + +### With Proxy (for slow or restricted networks) + +```bash +bash scripts/publish-github.sh --proxy # Default proxy: 127.0.0.1:7890 +bash scripts/publish-github.sh --proxy=192.168.1.1:8080 # Custom proxy +bash scripts/publish-github.sh --proxy --draft # Draft + proxy +``` + +### Retry Failed Upload + +```bash +bash scripts/publish-github.sh --proxy --retry # Delete old release, re-upload +bash scripts/publish-github.sh --proxy --retry --draft # Retry as draft +``` + +### All Options + +| Option | Description | +|--------|-------------| +| `--proxy` | Use proxy `127.0.0.1:7890` for GitHub upload | +| `--proxy=host:port` | Use custom proxy address | +| `--draft` | Create as draft release | +| `--tag=vX.Y.Z` | Custom tag (default: `v{version}` from package.json) | +| `--retry` | Delete existing release for this tag before re-uploading | + +**Prerequisites:** [gh CLI](https://cli.github.com/) installed and authenticated (`gh auth login`) + +## npm Scripts + +These scripts are also available as npm commands: + +```bash +npm run setup:jar # build.sh +npm run setup:jre # download-jre.sh +npm run setup # build.sh + download-jre.sh +npm run package:mac # Build frontend + electron-builder --mac +npm run package:win # Build frontend + electron-builder --win +npm run package:all # build-all-platforms.sh --all +npm run publish:github # publish-github.sh +npm run publish:github:draft # publish-github.sh --draft +``` + +## Typical Workflow + +``` +build.sh download-jre.sh + | | + v v +resources/app.jar resources/jre/{os}-{arch}/ + | | + +--------- electron-builder ---+ + | + v + release/ + ├── MateClaw_1.0.0_arm64.dmg + ├── MateClaw_1.0.0_x64.dmg + ├── MateClaw_1.0.0_arm64.zip + ├── MateClaw_1.0.0_x64.zip + ├── MateClaw_1.0.0_arm64_Setup.exe + ├── MateClaw_1.0.0_x64_Setup.exe + ├── latest-mac.yml + └── latest.yml + | + v + publish-github.sh + | + v + GitHub Releases +``` diff --git a/mateclaw-desktop/scripts/__tests__/trim-playwright-driver.test.cjs b/mateclaw-desktop/scripts/__tests__/trim-playwright-driver.test.cjs new file mode 100644 index 00000000..2167f258 --- /dev/null +++ b/mateclaw-desktop/scripts/__tests__/trim-playwright-driver.test.cjs @@ -0,0 +1,151 @@ +const assert = require('node:assert/strict') +const fs = require('node:fs') +const os = require('node:os') +const path = require('node:path') +const test = require('node:test') + +const { + createZipBuffer, + readZipEntries, + resolveDriverDirectory, + trimDriverBundleInAppJar, + ZIP_STORED, + default: afterPack, +} = require('../trim-playwright-driver.cjs') + +test('resolveDriverDirectory maps electron platform and arch to Playwright driver folder', () => { + assert.equal(resolveDriverDirectory('darwin', 'x64'), 'driver/mac') + assert.equal(resolveDriverDirectory('darwin', 'arm64'), 'driver/mac-arm64') + assert.equal(resolveDriverDirectory('linux', 'x64'), 'driver/linux') + assert.equal(resolveDriverDirectory('linux', 'arm64'), 'driver/linux-arm64') + assert.equal(resolveDriverDirectory('win32', 'x64'), 'driver/win32_x64') + assert.equal(resolveDriverDirectory('win32', 'arm64'), 'driver/win32_x64') + assert.deepEqual(resolveDriverDirectory('darwin', 'universal'), ['driver/mac', 'driver/mac-arm64']) +}) + +test('trimDriverBundleInAppJar keeps only the target driver and preserves nested jar as STORED', async () => { + const tmp = fs.mkdtempSync(path.join(os.tmpdir(), 'mateclaw-driver-trim-')) + const appJarPath = path.join(tmp, 'app.jar') + + const driverBundle = createZipBuffer([ + entry('META-INF/MANIFEST.MF', 'Manifest-Version: 1.0\n'), + entry('driver/mac/node', 'mac'), + entry('driver/mac-arm64/node', 'mac-arm64'), + entry('driver/linux/node', 'linux'), + entry('driver/linux-arm64/node', 'linux-arm64'), + entry('driver/win32_x64/node.exe', 'win32'), + entry('com/microsoft/playwright/Driver.class', 'class'), + ]) + + const appJar = createZipBuffer([ + entry('BOOT-INF/classpath.idx', '- "BOOT-INF/lib/driver-bundle-1.52.0.jar"\n'), + entry('BOOT-INF/lib/driver-bundle-1.52.0.jar', driverBundle, ZIP_STORED), + entry('BOOT-INF/lib/other.jar', 'other', ZIP_STORED), + ]) + + fs.writeFileSync(appJarPath, appJar) + + const result = await trimDriverBundleInAppJar(appJarPath, 'driver/mac-arm64') + assert.equal(result.removedDriverEntries, 4) + + const outerEntries = readZipEntries(fs.readFileSync(appJarPath)) + const nestedEntry = outerEntries.find((item) => item.name === 'BOOT-INF/lib/driver-bundle-1.52.0.jar') + assert.equal(nestedEntry.method, ZIP_STORED) + + const innerEntries = readZipEntries(nestedEntry.data) + const names = innerEntries.map((item) => item.name).sort() + + assert.deepEqual(names, [ + 'META-INF/MANIFEST.MF', + 'com/microsoft/playwright/Driver.class', + 'driver/mac-arm64/node', + ]) +}) + +test('trimDriverBundleInAppJar throws when driver-bundle is missing', async () => { + const tmp = fs.mkdtempSync(path.join(os.tmpdir(), 'mateclaw-driver-trim-')) + const appJarPath = path.join(tmp, 'app.jar') + + fs.writeFileSync(appJarPath, createZipBuffer([ + entry('BOOT-INF/lib/other.jar', 'other', ZIP_STORED), + ])) + + await assert.rejects( + () => trimDriverBundleInAppJar(appJarPath, 'driver/mac-arm64'), + /Playwright driver-bundle jar not found/ + ) +}) + +test('trimDriverBundleInAppJar throws when no target driver entries are kept', async () => { + const tmp = fs.mkdtempSync(path.join(os.tmpdir(), 'mateclaw-driver-trim-')) + const appJarPath = path.join(tmp, 'app.jar') + fs.writeFileSync(appJarPath, createAppJarWithDriverBundle()) + + await assert.rejects( + () => trimDriverBundleInAppJar(appJarPath, 'driver/mac-arm64-v2'), + /No entries kept under driver\/mac-arm64-v2/ + ) +}) + +test('trimDriverBundleInAppJar can keep both mac drivers for universal builds', async () => { + const tmp = fs.mkdtempSync(path.join(os.tmpdir(), 'mateclaw-driver-trim-')) + const appJarPath = path.join(tmp, 'app.jar') + fs.writeFileSync(appJarPath, createAppJarWithDriverBundle()) + + const result = await trimDriverBundleInAppJar(appJarPath, ['driver/mac', 'driver/mac-arm64']) + assert.equal(result.keptDriverEntries, 2) + + const outerEntries = readZipEntries(fs.readFileSync(appJarPath)) + const nestedEntry = outerEntries.find((item) => item.name === 'BOOT-INF/lib/driver-bundle-1.52.0.jar') + const driverNames = readZipEntries(nestedEntry.data) + .filter((item) => item.name.startsWith('driver/')) + .map((item) => item.name) + .sort() + + assert.deepEqual(driverNames, [ + 'driver/mac-arm64/node', + 'driver/mac/node', + ]) +}) + +test('afterPack throws when app.jar is missing', async () => { + const tmp = fs.mkdtempSync(path.join(os.tmpdir(), 'mateclaw-driver-trim-')) + + await assert.rejects( + () => afterPack({ + appOutDir: tmp, + arch: 'arm64', + electronPlatformName: 'darwin', + packager: { + appInfo: { productFilename: 'MateClaw' }, + }, + }), + /app\.jar not found/ + ) +}) + +function entry(name, data, method) { + return { + name, + data: Buffer.isBuffer(data) ? data : Buffer.from(data), + method, + } +} + +function createAppJarWithDriverBundle() { + const driverBundle = createZipBuffer([ + entry('META-INF/MANIFEST.MF', 'Manifest-Version: 1.0\n'), + entry('driver/mac/node', 'mac'), + entry('driver/mac-arm64/node', 'mac-arm64'), + entry('driver/linux/node', 'linux'), + entry('driver/linux-arm64/node', 'linux-arm64'), + entry('driver/win32_x64/node.exe', 'win32'), + entry('com/microsoft/playwright/Driver.class', 'class'), + ]) + + return createZipBuffer([ + entry('BOOT-INF/classpath.idx', '- "BOOT-INF/lib/driver-bundle-1.52.0.jar"\n'), + entry('BOOT-INF/lib/driver-bundle-1.52.0.jar', driverBundle, ZIP_STORED), + entry('BOOT-INF/lib/other.jar', 'other', ZIP_STORED), + ]) +} diff --git a/mateclaw-desktop/scripts/publish-github.sh b/mateclaw-desktop/scripts/publish-github.sh new file mode 100755 index 00000000..777db90a --- /dev/null +++ b/mateclaw-desktop/scripts/publish-github.sh @@ -0,0 +1,324 @@ +#!/usr/bin/env bash +# +# Publish MateClaw Desktop release artifacts to GitHub Releases +# +# Prerequisites: +# - gh CLI installed and authenticated (gh auth login) +# - Build artifacts exist in release/ directory (run build-all-platforms.sh first) +# +# Usage: +# bash scripts/publish-github.sh # Create release (direct) +# bash scripts/publish-github.sh --proxy # Create release via proxy (127.0.0.1:7890) +# bash scripts/publish-github.sh --proxy=host:port # Create release via custom proxy +# bash scripts/publish-github.sh --draft # Create draft release +# bash scripts/publish-github.sh --tag=v1.1.0 # Custom tag (default: v{version} from package.json) +# bash scripts/publish-github.sh --retry # Delete existing release and re-upload +# bash scripts/publish-github.sh --proxy --retry --draft # Combine options +# + +set -euo pipefail + +SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)" +DESKTOP_DIR="$(cd "$SCRIPT_DIR/.." && pwd)" +RELEASE_DIR="$DESKTOP_DIR/release" + +# ─── Parse arguments ─────────────────────────────────────────────────────── + +DRAFT="" +CUSTOM_TAG="" +USE_PROXY="" +PROXY_ADDR="127.0.0.1:7890" +RETRY=false +NOTES_FILE_OVERRIDE="" +NOTES_LANG="en" + +for arg in "$@"; do + case "$arg" in + --draft) DRAFT="--draft" ;; + --tag=*) CUSTOM_TAG="${arg#--tag=}" ;; + --proxy) USE_PROXY=true ;; + --proxy=*) USE_PROXY=true; PROXY_ADDR="${arg#--proxy=}" ;; + --retry) RETRY=true ;; + --notes-file=*) NOTES_FILE_OVERRIDE="${arg#--notes-file=}" ;; + --notes-lang=*) NOTES_LANG="${arg#--notes-lang=}" ;; + -h|--help) + echo "Usage: $0 [--draft] [--tag=vX.Y.Z] [--proxy[=host:port]] [--retry] [--notes-file=path] [--notes-lang=en|zh]" + echo "" + echo "Options:" + echo " --draft Create as draft release" + echo " --tag=vX.Y.Z Custom tag (default: v{version} from package.json)" + echo " --proxy Use proxy 127.0.0.1:7890 for uploading to GitHub" + echo " --proxy=host:port Use custom proxy address" + echo " --retry Delete existing release for this tag before uploading" + echo " --notes-file=path Use this markdown file as release notes (highest priority)" + echo " --notes-lang=en|zh Preferred language for auto-detected notes (default: en)" + echo "" + echo "Release notes resolution order:" + echo " 1. --notes-file=path (explicit override)" + echo " 2. ../docs/{notes-lang}/releases/X.Y.Z.md (curated, preferred lang)" + echo " 3. ../docs/{other-lang}/releases/X.Y.Z.md (curated, fallback lang)" + echo " 4. Tag annotation (if multi-line) (legacy)" + echo " 5. Tagged commit message body (legacy)" + echo " 6. --generate-notes (GitHub auto)" + echo "" + echo "Examples:" + echo " # Step 1: Build locally (no publish)" + echo " bash scripts/build-all-platforms.sh --all" + echo "" + echo " # Step 2: Publish to GitHub" + echo " bash scripts/publish-github.sh --proxy # via proxy, en notes" + echo " bash scripts/publish-github.sh --proxy --notes-lang=zh # zh notes" + echo " bash scripts/publish-github.sh --proxy --draft # draft (preview)" + echo " bash scripts/publish-github.sh --proxy --retry # delete + re-upload" + echo " bash scripts/publish-github.sh --notes-file=NOTES.md # custom notes file" + echo "" + echo "Run build-all-platforms.sh first to generate artifacts." + exit 0 + ;; + *) + echo "Unknown option: $arg" + echo "Usage: $0 [--draft] [--tag=vX.Y.Z] [--proxy[=host:port]] [--retry] [--notes-file=path] [--notes-lang=en|zh]" + exit 1 + ;; + esac +done + +if [ "$NOTES_LANG" != "en" ] && [ "$NOTES_LANG" != "zh" ]; then + echo "❌ --notes-lang must be 'en' or 'zh' (got: $NOTES_LANG)" + exit 1 +fi + +# ─── Setup proxy ─────────────────────────────────────────────────────────── + +if [ "$USE_PROXY" = true ]; then + export https_proxy="http://${PROXY_ADDR}" + export http_proxy="http://${PROXY_ADDR}" + export HTTPS_PROXY="http://${PROXY_ADDR}" + export HTTP_PROXY="http://${PROXY_ADDR}" + echo "🌐 Proxy enabled: ${PROXY_ADDR}" + echo "" +fi + +# ─── Check prerequisites ────────────────────────────────────────────────── + +if ! command -v gh &>/dev/null; then + echo "❌ gh CLI not found. Install: https://cli.github.com/" + exit 1 +fi + +if ! gh auth status &>/dev/null; then + echo "❌ gh not authenticated. Run: gh auth login" + exit 1 +fi + +# ─── Read version from package.json ─────────────────────────────────────── + +VERSION=$(node -p "require('$DESKTOP_DIR/package.json').version") +TAG="${CUSTOM_TAG:-v${VERSION}}" + +echo "╔════════════════════════════════════════════════════════╗" +echo "║ MateClaw Desktop - Publish to GitHub ║" +echo "╚════════════════════════════════════════════════════════╝" +echo "" +echo " Version: $VERSION" +echo " Tag: $TAG" +echo " Mode: ${DRAFT:-release}" +echo " Proxy: ${USE_PROXY:+${PROXY_ADDR}}${USE_PROXY:-off}" +echo " Retry: $RETRY" +echo "" + +# ─── Retry: delete existing release ─────────────────────────────────────── + +if [ "$RETRY" = true ]; then + echo "🔄 Checking for existing release $TAG ..." + if gh release view "$TAG" &>/dev/null; then + echo " Found existing release, deleting..." + gh release delete "$TAG" --yes --cleanup-tag 2>/dev/null || gh release delete "$TAG" --yes 2>/dev/null + echo " ✅ Old release deleted." + else + echo " No existing release found, proceeding." + fi + echo "" +fi + +# ─── Collect release artifacts ───────────────────────────────────────────── + +if [ ! -d "$RELEASE_DIR" ]; then + echo "❌ Release directory not found: $RELEASE_DIR" + echo " Run build-all-platforms.sh first." + exit 1 +fi + +ARTIFACTS=() + +# macOS artifacts +for pattern in "MateClaw*.dmg" "MateClaw*.zip"; do + while IFS= read -r -d '' f; do + ARTIFACTS+=("$f") + done < <(find "$RELEASE_DIR" -maxdepth 1 -name "$pattern" -print0 2>/dev/null) +done + +# Windows artifacts (skip the architecture-merged installer — only ship per-arch builds) +while IFS= read -r -d '' f; do + ARTIFACTS+=("$f") +done < <(find "$RELEASE_DIR" -maxdepth 1 -name "MateClaw*Setup*.exe" \ + ! -name "MateClaw_${VERSION}_Setup.exe" -print0 2>/dev/null) + +# Linux artifacts +while IFS= read -r -d '' f; do + ARTIFACTS+=("$f") +done < <(find "$RELEASE_DIR" -maxdepth 1 -name "MateClaw*.AppImage" -print0 2>/dev/null) + +# Auto-update metadata files +for pattern in "latest-mac.yml" "latest.yml" "latest-linux.yml"; do + if [ -f "$RELEASE_DIR/$pattern" ]; then + ARTIFACTS+=("$RELEASE_DIR/$pattern") + fi +done + +# blockmap files (for differential updates) — also skip merged installer's blockmap +while IFS= read -r -d '' f; do + ARTIFACTS+=("$f") +done < <(find "$RELEASE_DIR" -maxdepth 1 -name "*.blockmap" \ + ! -name "MateClaw_${VERSION}_Setup.exe.blockmap" -print0 2>/dev/null) + +if [ ${#ARTIFACTS[@]} -eq 0 ]; then + echo "❌ No release artifacts found in $RELEASE_DIR" + echo " Run build-all-platforms.sh first." + exit 1 +fi + +echo " Artifacts to upload:" +TOTAL_SIZE=0 +for f in "${ARTIFACTS[@]}"; do + SIZE_BYTES=$(stat -f%z "$f" 2>/dev/null || stat -c%s "$f" 2>/dev/null || echo 0) + SIZE_HUMAN=$(du -h "$f" | cut -f1) + TOTAL_SIZE=$((TOTAL_SIZE + SIZE_BYTES)) + echo " • $(basename "$f") ($SIZE_HUMAN)" +done +TOTAL_HUMAN=$(echo "$TOTAL_SIZE" | awk '{ + if ($1 >= 1073741824) printf "%.1f GB", $1/1073741824; + else if ($1 >= 1048576) printf "%.0f MB", $1/1048576; + else printf "%.0f KB", $1/1024; +}') +echo "" +echo " Total: $TOTAL_HUMAN" +echo "" + +# ─── Resolve release notes (priority chain) ─────────────────────────────── +# 1. --notes-file=path (explicit override) +# 2. ../docs/{notes-lang}/releases/X.Y.Z.md (curated, preferred lang) +# 3. ../docs/{other-lang}/releases/X.Y.Z.md (curated, fallback lang) +# 4. Tag annotation (if multi-line) (legacy fallback) +# 5. Tagged commit message body (legacy fallback) +# 6. --generate-notes (GitHub auto) + +NOTES_FILE=$(mktemp) +trap "rm -f '$NOTES_FILE'" EXIT + +REPO_ROOT="$(cd "$DESKTOP_DIR/.." && pwd)" +NOTES_LANG_OTHER=$([ "$NOTES_LANG" = "en" ] && echo "zh" || echo "en") +NOTES_PRIMARY="$REPO_ROOT/docs/${NOTES_LANG}/releases/${VERSION}.md" +NOTES_FALLBACK="$REPO_ROOT/docs/${NOTES_LANG_OTHER}/releases/${VERSION}.md" + +if [ -n "$NOTES_FILE_OVERRIDE" ]; then + if [ ! -f "$NOTES_FILE_OVERRIDE" ]; then + echo "❌ --notes-file path not found: $NOTES_FILE_OVERRIDE" + exit 1 + fi + cat "$NOTES_FILE_OVERRIDE" > "$NOTES_FILE" + echo "📝 Using --notes-file: $NOTES_FILE_OVERRIDE" +elif [ -f "$NOTES_PRIMARY" ]; then + cat "$NOTES_PRIMARY" > "$NOTES_FILE" + echo "📝 Using docs/${NOTES_LANG}/releases/${VERSION}.md as release notes." +elif [ -f "$NOTES_FALLBACK" ]; then + cat "$NOTES_FALLBACK" > "$NOTES_FILE" + echo "📝 Using docs/${NOTES_LANG_OTHER}/releases/${VERSION}.md as release notes (preferred '$NOTES_LANG' not found)." +else + # Legacy fallback: tag annotation, then commit body + TAG_MSG=$(git tag -l --format='%(contents)' "$TAG" 2>/dev/null | sed '/^$/d') + if [ -n "$TAG_MSG" ] && [ "$(echo "$TAG_MSG" | wc -l)" -gt 2 ]; then + echo "$TAG_MSG" > "$NOTES_FILE" + echo "📝 Using tag annotation as release notes." + else + COMMIT_MSG=$(git log -1 --format='%B' "$TAG" 2>/dev/null | tail -n +2 | sed '/^$/d') + if [ -n "$COMMIT_MSG" ]; then + echo "$COMMIT_MSG" > "$NOTES_FILE" + echo "📝 Using commit message as release notes." + else + echo "⚠️ No release notes found (no docs/X.Y.Z.md, tag annotation, or commit body), using --generate-notes." + fi + fi +fi +echo "" + +# ─── Rewrite latest.yml so it does not reference the merged installer ───── +# +# electron-builder generates a multi-arch merged Windows installer +# (MateClaw_X.Y.Z_Setup.exe, ~600 MB) alongside the per-arch installers +# (MateClaw_X.Y.Z_x64_Setup.exe, MateClaw_X.Y.Z_arm64_Setup.exe). The +# merged build is too large to be worth uploading, but the default +# latest.yml top-level `path:` and `files[0]` both point at it. If we +# upload latest.yml as-is while skipping the merged exe, electron-updater +# on Windows hits 404 on every check and the whole update path breaks. +# +# Fix: rewrite latest.yml in place so `path` / `sha512` / `files[]` only +# reference assets that are actually being uploaded. Use x64 as the +# default top-level target (arm64 clients still match via files[]). + +LATEST_YML="$RELEASE_DIR/latest.yml" +MERGED_EXE_NAME="MateClaw_${VERSION}_Setup.exe" +X64_EXE_NAME="MateClaw_${VERSION}_x64_Setup.exe" +ARM64_EXE_NAME="MateClaw_${VERSION}_arm64_Setup.exe" + +if [ -f "$LATEST_YML" ]; then + echo "🧹 Rewriting latest.yml to drop the merged installer ..." + (cd "$DESKTOP_DIR" && node -e " + const fs = require('fs'); + const yaml = require('js-yaml'); + const file = '$LATEST_YML'; + const merged = '$MERGED_EXE_NAME'; + const x64 = '$X64_EXE_NAME'; + const arm64 = '$ARM64_EXE_NAME'; + const doc = yaml.load(fs.readFileSync(file, 'utf8')); + const before = (doc.files || []).length; + doc.files = (doc.files || []).filter(f => f.url !== merged); + const x64Entry = doc.files.find(f => f.url === x64); + const arm64Entry = doc.files.find(f => f.url === arm64); + if (!x64Entry || !arm64Entry) { + console.error('FATAL: per-arch installer entries missing from latest.yml'); + console.error(' files:', doc.files.map(f => f.url)); + process.exit(1); + } + doc.path = x64Entry.url; + doc.sha512 = x64Entry.sha512; + fs.writeFileSync(file, yaml.dump(doc, { lineWidth: -1 })); + console.log(' files[] entries: ' + before + ' → ' + doc.files.length); + console.log(' top-level path: ' + doc.path); + ") + echo "" +fi + +# ─── Create GitHub Release ───────────────────────────────────────────────── + +echo "🚀 Creating GitHub Release $TAG ..." +echo "" + +if [ -s "$NOTES_FILE" ]; then + gh release create "$TAG" \ + --title "MateClaw $VERSION" \ + --notes-file "$NOTES_FILE" \ + $DRAFT \ + "${ARTIFACTS[@]}" +else + gh release create "$TAG" \ + --title "MateClaw $VERSION" \ + --generate-notes \ + $DRAFT \ + "${ARTIFACTS[@]}" +fi + +echo "" +echo "✅ Release published successfully!" +echo "" +gh release view "$TAG" --json url -q '.url' diff --git a/mateclaw-desktop/scripts/trim-playwright-driver.cjs b/mateclaw-desktop/scripts/trim-playwright-driver.cjs index 56f351b2..9f4c2bd3 100644 --- a/mateclaw-desktop/scripts/trim-playwright-driver.cjs +++ b/mateclaw-desktop/scripts/trim-playwright-driver.cjs @@ -1,6 +1,360 @@ -// afterPack hook: no-op placeholder -// The original trim-playwright-driver.cjs was not included in the open-source release. -// This no-op allows electron-builder to complete packaging. -exports.default = async function () { - // intentionally empty +const fs = require('node:fs') +const path = require('node:path') +const zlib = require('node:zlib') + +const ZIP_STORED = 0 +const ZIP_DEFLATED = 8 +const DRIVER_BUNDLE_PATTERN = /^BOOT-INF\/lib\/driver-bundle-[^/]+\.jar$/ + +const ARCH_X64 = 1 +const ARCH_ARM64 = 3 + +async function afterPack(context) { + const platform = context.electronPlatformName || context.packager?.platform?.name + const arch = normalizeArch(context.arch) + const keepDriverDirectory = resolveDriverDirectory(platform, arch) + const appJarPath = findAppJar(context) + + if (!appJarPath) { + throw new Error(`[trim-playwright-driver] app.jar not found in ${context.appOutDir}`) + } + + const result = await trimDriverBundleInAppJar(appJarPath, keepDriverDirectory) + const keptLabel = asArray(keepDriverDirectory).join(', ') + console.log( + `[trim-playwright-driver] ${path.relative(process.cwd(), appJarPath)}: ` + + `kept ${keptLabel}, removed ${result.removedDriverEntries} driver entries, ` + + `${formatBytes(result.beforeBytes)} -> ${formatBytes(result.afterBytes)}` + ) } + +function findAppJar(context) { + const appOutDir = context.appOutDir + const productFilename = context.packager?.appInfo?.productFilename || context.packager?.appInfo?.productName || 'MateClaw' + const platform = context.electronPlatformName || context.packager?.platform?.name + + const candidates = [] + if (platform === 'darwin') { + candidates.push(path.join(appOutDir, `${productFilename}.app`, 'Contents', 'Resources', 'app.jar')) + } + candidates.push(path.join(appOutDir, 'resources', 'app.jar')) + + for (const candidate of candidates) { + if (fs.existsSync(candidate)) return candidate + } + + const found = findFirstFile(appOutDir, 'app.jar', 4) + return found +} + +function findFirstFile(root, fileName, maxDepth, depth = 0) { + if (!root || depth > maxDepth || !fs.existsSync(root)) return null + for (const dirent of fs.readdirSync(root, { withFileTypes: true })) { + const fullPath = path.join(root, dirent.name) + if (dirent.isFile() && dirent.name === fileName) return fullPath + if (dirent.isDirectory()) { + const found = findFirstFile(fullPath, fileName, maxDepth, depth + 1) + if (found) return found + } + } + return null +} + +async function trimDriverBundleInAppJar(appJarPath, keepDriverDirectory) { + const appJarBuffer = fs.readFileSync(appJarPath) + const outerEntries = readZipEntries(appJarBuffer) + const driverBundleEntry = outerEntries.find((entry) => DRIVER_BUNDLE_PATTERN.test(entry.name)) + const keepDriverDirectories = asArray(keepDriverDirectory) + + if (!driverBundleEntry) { + throw new Error(`Playwright driver-bundle jar not found in ${appJarPath}`) + } + + const innerEntries = readZipEntries(driverBundleEntry.data) + let removedDriverEntries = 0 + let keptDriverEntries = 0 + + const trimmedInnerEntries = innerEntries.filter((entry) => { + if (!entry.name.startsWith('driver/')) return true + if (keepDriverDirectories.some((directory) => entry.name.startsWith(`${directory}/`))) { + keptDriverEntries += 1 + return true + } + removedDriverEntries += 1 + return false + }) + + if (keptDriverEntries === 0) { + throw new Error( + `No entries kept under ${keepDriverDirectories.join(', ')}; Playwright driver layout may have changed` + ) + } + + const trimmedDriverBundle = createZipBuffer(trimmedInnerEntries.map(cloneEntryForWrite)) + const rewrittenOuterEntries = outerEntries.map((entry) => { + if (entry.name !== driverBundleEntry.name) return cloneEntryForWrite(entry) + return { + ...cloneEntryForWrite(entry), + data: trimmedDriverBundle, + method: ZIP_STORED, + } + }) + + const rewrittenAppJar = createZipBuffer(rewrittenOuterEntries) + fs.writeFileSync(appJarPath, rewrittenAppJar) + + return { + beforeBytes: appJarBuffer.length, + afterBytes: rewrittenAppJar.length, + driverBundleName: driverBundleEntry.name, + keptDriverEntries, + removedDriverEntries, + } +} + +function cloneEntryForWrite(entry) { + return { + name: entry.name, + data: Buffer.from(entry.data), + method: entry.method, + date: entry.date, + comment: entry.comment, + externalAttributes: entry.externalAttributes, + } +} + +function resolveDriverDirectory(platform, arch) { + const normalizedArch = normalizeArch(arch) + + if (platform === 'darwin') { + if (normalizedArch === 'arm64') return 'driver/mac-arm64' + if (normalizedArch === 'x64') return 'driver/mac' + if (normalizedArch === 'universal') return ['driver/mac', 'driver/mac-arm64'] + } + + if (platform === 'linux') { + if (normalizedArch === 'arm64') return 'driver/linux-arm64' + if (normalizedArch === 'x64') return 'driver/linux' + } + + if (platform === 'win32') { + return 'driver/win32_x64' + } + + throw new Error(`Unsupported platform/arch for Playwright driver trim: ${platform}/${arch}`) +} + +function asArray(value) { + return Array.isArray(value) ? value : [value] +} + +function normalizeArch(arch) { + if (arch === ARCH_X64 || arch === 'x64') return 'x64' + if (arch === ARCH_ARM64 || arch === 'arm64') return 'arm64' + if (arch === 'universal' || arch === 4) return 'universal' + return String(arch) +} + +function readZipEntries(buffer) { + const eocdOffset = findEndOfCentralDirectory(buffer) + const centralDirectorySize = buffer.readUInt32LE(eocdOffset + 12) + const centralDirectoryOffset = buffer.readUInt32LE(eocdOffset + 16) + const entries = [] + + let offset = centralDirectoryOffset + const centralDirectoryEnd = centralDirectoryOffset + centralDirectorySize + + while (offset < centralDirectoryEnd) { + const signature = buffer.readUInt32LE(offset) + if (signature !== 0x02014b50) { + throw new Error(`Invalid central directory signature at offset ${offset}`) + } + + const flags = buffer.readUInt16LE(offset + 8) + const method = buffer.readUInt16LE(offset + 10) + const dosTime = buffer.readUInt16LE(offset + 12) + const dosDate = buffer.readUInt16LE(offset + 14) + const crc = buffer.readUInt32LE(offset + 16) + const compressedSize = buffer.readUInt32LE(offset + 20) + const uncompressedSize = buffer.readUInt32LE(offset + 24) + const fileNameLength = buffer.readUInt16LE(offset + 28) + const extraLength = buffer.readUInt16LE(offset + 30) + const commentLength = buffer.readUInt16LE(offset + 32) + const externalAttributes = buffer.readUInt32LE(offset + 38) + const localHeaderOffset = buffer.readUInt32LE(offset + 42) + const name = buffer.toString('utf8', offset + 46, offset + 46 + fileNameLength) + const comment = buffer.subarray(offset + 46 + fileNameLength + extraLength, offset + 46 + fileNameLength + extraLength + commentLength) + + const localSignature = buffer.readUInt32LE(localHeaderOffset) + if (localSignature !== 0x04034b50) { + throw new Error(`Invalid local file header signature for ${name}`) + } + + const localNameLength = buffer.readUInt16LE(localHeaderOffset + 26) + const localExtraLength = buffer.readUInt16LE(localHeaderOffset + 28) + const dataOffset = localHeaderOffset + 30 + localNameLength + localExtraLength + const compressedData = buffer.subarray(dataOffset, dataOffset + compressedSize) + + let data + if (method === ZIP_STORED) { + data = Buffer.from(compressedData) + } else if (method === ZIP_DEFLATED) { + data = zlib.inflateRawSync(compressedData) + } else { + throw new Error(`Unsupported ZIP method ${method} for ${name}`) + } + + if (data.length !== uncompressedSize) { + throw new Error(`Unexpected uncompressed size for ${name}: ${data.length} !== ${uncompressedSize}`) + } + + entries.push({ + name, + data, + method, + flags, + crc, + date: dosToDate(dosDate, dosTime), + comment: Buffer.from(comment), + externalAttributes, + }) + + offset += 46 + fileNameLength + extraLength + commentLength + } + + return entries +} + +function createZipBuffer(entries) { + const localParts = [] + const centralParts = [] + let offset = 0 + + for (const entry of entries) { + const nameBuffer = Buffer.from(entry.name) + const data = Buffer.isBuffer(entry.data) ? entry.data : Buffer.from(entry.data || '') + const method = entry.method ?? ZIP_DEFLATED + const compressedData = method === ZIP_STORED ? data : zlib.deflateRawSync(data) + const crc = crc32(data) + const { dosDate, dosTime } = dateToDos(entry.date) + + const localHeader = Buffer.alloc(30 + nameBuffer.length) + localHeader.writeUInt32LE(0x04034b50, 0) + localHeader.writeUInt16LE(20, 4) + localHeader.writeUInt16LE(0x0800, 6) + localHeader.writeUInt16LE(method, 8) + localHeader.writeUInt16LE(dosTime, 10) + localHeader.writeUInt16LE(dosDate, 12) + localHeader.writeUInt32LE(crc, 14) + localHeader.writeUInt32LE(compressedData.length, 18) + localHeader.writeUInt32LE(data.length, 22) + localHeader.writeUInt16LE(nameBuffer.length, 26) + localHeader.writeUInt16LE(0, 28) + nameBuffer.copy(localHeader, 30) + + localParts.push(localHeader, compressedData) + + const comment = Buffer.isBuffer(entry.comment) ? entry.comment : Buffer.alloc(0) + const centralHeader = Buffer.alloc(46 + nameBuffer.length + comment.length) + centralHeader.writeUInt32LE(0x02014b50, 0) + centralHeader.writeUInt16LE(20, 4) + centralHeader.writeUInt16LE(20, 6) + centralHeader.writeUInt16LE(0x0800, 8) + centralHeader.writeUInt16LE(method, 10) + centralHeader.writeUInt16LE(dosTime, 12) + centralHeader.writeUInt16LE(dosDate, 14) + centralHeader.writeUInt32LE(crc, 16) + centralHeader.writeUInt32LE(compressedData.length, 20) + centralHeader.writeUInt32LE(data.length, 24) + centralHeader.writeUInt16LE(nameBuffer.length, 28) + centralHeader.writeUInt16LE(0, 30) + centralHeader.writeUInt16LE(comment.length, 32) + centralHeader.writeUInt16LE(0, 34) + centralHeader.writeUInt16LE(0, 36) + centralHeader.writeUInt32LE(entry.externalAttributes || 0, 38) + centralHeader.writeUInt32LE(offset, 42) + nameBuffer.copy(centralHeader, 46) + comment.copy(centralHeader, 46 + nameBuffer.length) + centralParts.push(centralHeader) + + offset += localHeader.length + compressedData.length + } + + const centralDirectoryOffset = offset + const centralDirectory = Buffer.concat(centralParts) + const centralDirectorySize = centralDirectory.length + + const eocd = Buffer.alloc(22) + eocd.writeUInt32LE(0x06054b50, 0) + eocd.writeUInt16LE(0, 4) + eocd.writeUInt16LE(0, 6) + eocd.writeUInt16LE(entries.length, 8) + eocd.writeUInt16LE(entries.length, 10) + eocd.writeUInt32LE(centralDirectorySize, 12) + eocd.writeUInt32LE(centralDirectoryOffset, 16) + eocd.writeUInt16LE(0, 20) + + return Buffer.concat([...localParts, centralDirectory, eocd]) +} + +function findEndOfCentralDirectory(buffer) { + const minOffset = Math.max(0, buffer.length - 0xffff - 22) + for (let offset = buffer.length - 22; offset >= minOffset; offset -= 1) { + if (buffer.readUInt32LE(offset) === 0x06054b50) return offset + } + throw new Error('End of central directory not found') +} + +function dateToDos(date) { + const value = date instanceof Date ? date : new Date(1980, 0, 1, 0, 0, 0) + const year = Math.max(1980, value.getFullYear()) + return { + dosDate: ((year - 1980) << 9) | ((value.getMonth() + 1) << 5) | value.getDate(), + dosTime: (value.getHours() << 11) | (value.getMinutes() << 5) | Math.floor(value.getSeconds() / 2), + } +} + +function dosToDate(dosDate, dosTime) { + const day = dosDate & 0x1f + const month = (dosDate >> 5) & 0x0f + const year = ((dosDate >> 9) & 0x7f) + 1980 + const second = (dosTime & 0x1f) * 2 + const minute = (dosTime >> 5) & 0x3f + const hour = (dosTime >> 11) & 0x1f + return new Date(year, Math.max(0, month - 1), day || 1, hour, minute, second) +} + +function crc32(buffer) { + let crc = 0xffffffff + for (let i = 0; i < buffer.length; i += 1) { + crc = CRC_TABLE[(crc ^ buffer[i]) & 0xff] ^ (crc >>> 8) + } + return (crc ^ 0xffffffff) >>> 0 +} + +function makeCrcTable() { + const table = new Uint32Array(256) + for (let i = 0; i < 256; i += 1) { + let value = i + for (let bit = 0; bit < 8; bit += 1) { + value = value & 1 ? 0xedb88320 ^ (value >>> 1) : value >>> 1 + } + table[i] = value >>> 0 + } + return table +} + +function formatBytes(bytes) { + return `${(bytes / 1024 / 1024).toFixed(1)} MB` +} + +const CRC_TABLE = makeCrcTable() + +module.exports = afterPack +module.exports.default = afterPack +module.exports.createZipBuffer = createZipBuffer +module.exports.readZipEntries = readZipEntries +module.exports.resolveDriverDirectory = resolveDriverDirectory +module.exports.trimDriverBundleInAppJar = trimDriverBundleInAppJar +module.exports.ZIP_STORED = ZIP_STORED +module.exports.ZIP_DEFLATED = ZIP_DEFLATED diff --git a/mateclaw-server/src/main/resources/skill-template-bundles/obsidian-vault/scripts/helper.sh b/mateclaw-server/src/main/resources/skill-template-bundles/obsidian-vault/scripts/helper.sh new file mode 100644 index 00000000..41bb453a --- /dev/null +++ b/mateclaw-server/src/main/resources/skill-template-bundles/obsidian-vault/scripts/helper.sh @@ -0,0 +1,24 @@ +#!/usr/bin/env bash +# Helper for the obsidian-vault wizard template — lists recently-modified +# .md files in a vault. Copied into the new skill's workspace at +# ${workspace_root}/${slug}/scripts/helper.sh by SkillBundleMaterializer. + +set -euo pipefail + +VAULT="${1:-}" +if [[ -z "$VAULT" ]]; then + echo "usage: helper.sh " + echo "lists *.md files under the vault, sorted by mtime (newest first)" + exit 1 +fi + +if [[ ! -d "$VAULT" ]]; then + echo "vault not found: $VAULT" >&2 + exit 1 +fi + +find "$VAULT" -type f -name '*.md' -not -path '*/.*' \ + -exec stat -f '%m %N' {} + 2>/dev/null \ + | sort -rn \ + | head -20 \ + | awk '{ $1=""; sub(/^ /, ""); print }' diff --git a/mateclaw-server/src/main/resources/skills/arxiv/scripts/search_arxiv.py b/mateclaw-server/src/main/resources/skills/arxiv/scripts/search_arxiv.py new file mode 100644 index 00000000..57442b88 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/arxiv/scripts/search_arxiv.py @@ -0,0 +1,114 @@ +#!/usr/bin/env python3 +"""Search arXiv and display results in a clean format. + +Usage: + python search_arxiv.py "GRPO reinforcement learning" + python search_arxiv.py "GRPO reinforcement learning" --max 10 + python search_arxiv.py "GRPO reinforcement learning" --sort date + python search_arxiv.py --author "Yann LeCun" --max 5 + python search_arxiv.py --category cs.AI --sort date --max 10 + python search_arxiv.py --id 2402.03300 + python search_arxiv.py --id 2402.03300,2401.12345 +""" +import sys +import urllib.request +import urllib.parse +import xml.etree.ElementTree as ET + +NS = {'a': 'http://www.w3.org/2005/Atom'} + +def search(query=None, author=None, category=None, ids=None, max_results=5, sort="relevance"): + params = {} + + if ids: + params['id_list'] = ids + else: + parts = [] + if query: + parts.append(f'all:{urllib.parse.quote(query)}') + if author: + parts.append(f'au:{urllib.parse.quote(author)}') + if category: + parts.append(f'cat:{category}') + if not parts: + print("Error: provide a query, --author, --category, or --id") + sys.exit(1) + params['search_query'] = '+AND+'.join(parts) + + params['max_results'] = str(max_results) + + sort_map = {"relevance": "relevance", "date": "submittedDate", "updated": "lastUpdatedDate"} + params['sortBy'] = sort_map.get(sort, sort) + params['sortOrder'] = 'descending' + + url = "https://export.arxiv.org/api/query?" + "&".join(f"{k}={v}" for k, v in params.items()) + + req = urllib.request.Request(url, headers={'User-Agent': 'MateClaw/1.0'}) + with urllib.request.urlopen(req, timeout=15) as resp: + data = resp.read() + + root = ET.fromstring(data) + entries = root.findall('a:entry', NS) + + if not entries: + print("No results found.") + return + + total = root.find('{http://a9.com/-/spec/opensearch/1.1/}totalResults') + if total is not None: + print(f"Found {total.text} results (showing {len(entries)})\n") + + for i, entry in enumerate(entries): + title = entry.find('a:title', NS).text.strip().replace('\n', ' ') + raw_id = entry.find('a:id', NS).text.strip() + full_id = raw_id.split('/abs/')[-1] if '/abs/' in raw_id else raw_id + arxiv_id = full_id.split('v')[0] # base ID for links + published = entry.find('a:published', NS).text[:10] + updated = entry.find('a:updated', NS).text[:10] + authors = ', '.join(a.find('a:name', NS).text for a in entry.findall('a:author', NS)) + summary = entry.find('a:summary', NS).text.strip().replace('\n', ' ') + cats = ', '.join(c.get('term') for c in entry.findall('a:category', NS)) + + version = full_id[len(arxiv_id):] if full_id != arxiv_id else "" + print(f"{i+1}. {title}") + print(f" ID: {arxiv_id}{version} | Published: {published} | Updated: {updated}") + print(f" Authors: {authors}") + print(f" Categories: {cats}") + print(f" Abstract: {summary[:300]}{'...' if len(summary) > 300 else ''}") + print(f" Links: https://arxiv.org/abs/{arxiv_id} | https://arxiv.org/pdf/{arxiv_id}") + print() + + +if __name__ == "__main__": + args = sys.argv[1:] + if not args or args[0] in ("-h", "--help"): + print(__doc__) + sys.exit(0) + + query = None + author = None + category = None + ids = None + max_results = 5 + sort = "relevance" + + i = 0 + positional = [] + while i < len(args): + if args[i] == "--max" and i + 1 < len(args): + max_results = int(args[i + 1]); i += 2 + elif args[i] == "--sort" and i + 1 < len(args): + sort = args[i + 1]; i += 2 + elif args[i] == "--author" and i + 1 < len(args): + author = args[i + 1]; i += 2 + elif args[i] == "--category" and i + 1 < len(args): + category = args[i + 1]; i += 2 + elif args[i] == "--id" and i + 1 < len(args): + ids = args[i + 1]; i += 2 + else: + positional.append(args[i]); i += 1 + + if positional: + query = " ".join(positional) + + search(query=query, author=author, category=category, ids=ids, max_results=max_results, sort=sort) diff --git a/mateclaw-server/src/main/resources/skills/deai_humanize/scripts/ai_trace_score.py b/mateclaw-server/src/main/resources/skills/deai_humanize/scripts/ai_trace_score.py new file mode 100644 index 00000000..1138ad7e --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/deai_humanize/scripts/ai_trace_score.py @@ -0,0 +1,299 @@ +#!/usr/bin/env python3 +"""Heuristic scorer for AI-writing traces in Chinese text (stdlib only). + +Reads a single JSON argument from argv[1], or from stdin if no argument +is given: + + {"text": "...", "platform": "gzh" | "xhs"} + +Prints a JSON report to stdout: + + { + "score": 0-100, # higher = more AI-like + "signals": [ {name, value, weight, note}, ... ], + "spans": ["offending substring", ...], + "verdict": "human-like" | "some-ai" | "strong-ai" + } + +The score is a deterministic, explainable quality signal built from +surface features of the text. It is a writing-quality heuristic to guide +rewriting, NOT a guarantee about the output of any external AI detector. +""" + +import sys +import json +import re + +# --- Feature vocabularies --------------------------------------------------- + +# Discourse connectors: a few are natural, but a high density reads as +# machine-organized "listy" prose. +CONNECTORS = [ + "首先", "其次", "再次", "然后", "最后", "综上所述", "总而言之", + "总的来说", "总体而言", "值得注意的是", "需要注意的是", + "由此可见", "换句话说", "简而言之", "一方面", "另一方面", + "此外", "与此同时", "不仅如此", +] + +# Cliché templates. Entries with "[^...]{0,n}" allow a bounded gap so +# "在<任意短语>的今天" and friends match without crossing a clause boundary. +CLICHE_PATTERNS = [ + r"在[^，。！？；\n]{0,12}的今天", + r"在这个[^，。！？；\n]{0,10}的时代", + r"随着[^，。！？；\n]{0,16}的(发展|到来|普及|推进)", + r"让我们", + r"赋能", + r"注入(新的)?活力", + r"[^，。！？；\n]{0,8}是[^，。！？；\n]{0,6}的关键", + r"众所周知", + r"不难发现", + r"不可否认", + r"数字化转型", + r"深度融合", + r"保驾护航", + r"打造[^，。！？；\n]{0,6}新(生态|格局|范式|标杆)", + r"开启[^，。！？；\n]{0,6}新(篇章|征程)", +] + +# Concreteness markers: first-person voice, digits, and time words signal +# lived, specific writing rather than abstract summary. +FIRST_PERSON = ["我们", "咱们", "我", "咱"] +TIME_WORDS = [ + "今天", "昨天", "明天", "前天", "后天", "上周", "下周", "上午", + "下午", "早上", "中午", "晚上", "凌晨", "刚才", "去年", "今年", + "星期", "周一", "周二", "周三", "周四", "周五", "周六", "周日", + "分钟", "小时", "点钟", +] + +CJK_RE = re.compile(r"[一-鿿]") +SENT_SPLIT_RE = re.compile(r"[。！？；!?;\n]+") +DIGIT_RE = re.compile(r"[0-9０-９]") +DASH_RE = re.compile(r"[—–\-]{1,2}|•|·") + +# Per-platform signal weights. They sum to 100 within each platform. +# xhs (Xiaohongshu) prizes short, bursty fragments, so sentence-length and +# paragraph-uniformity carry less weight there. +WEIGHTS = { + "gzh": { + "cliche": 28, "connector": 26, "concreteness": 14, + "burstiness": 12, "list_dash": 8, "para_uniform": 12, + }, + "xhs": { + "cliche": 32, "connector": 24, "concreteness": 20, + "burstiness": 6, "list_dash": 8, "para_uniform": 10, + }, +} + +NEUTRAL = 0.3 # sub-score used when a signal lacks enough data +MIN_SENTS_FOR_BURST = 4 # burstiness needs enough sentences to be meaningful +MIN_PARAS_FOR_UNIFORM = 3 + + +def clamp01(x): + """Clamp a float into the [0, 1] range.""" + if x < 0.0: + return 0.0 + if x > 1.0: + return 1.0 + return x + + +def cjk_len(s): + """Count CJK characters in a string.""" + return len(CJK_RE.findall(s)) + + +def std(values): + """Population standard deviation of a list of numbers.""" + n = len(values) + if n == 0: + return 0.0 + mean = sum(values) / n + variance = sum((v - mean) ** 2 for v in values) / n + return variance ** 0.5 + + +def count_occurrences(text, needles): + """Total non-overlapping occurrences of any needle, plus matched spans.""" + total = 0 + spans = [] + for needle in needles: + start = 0 + while True: + idx = text.find(needle, start) + if idx < 0: + break + total += 1 + spans.append(needle) + start = idx + len(needle) + return total, spans + + +def score_text(text, platform): + """Compute the AI-trace report for a piece of text.""" + weights = WEIGHTS.get(platform, WEIGHTS["gzh"]) + signals = [] + spans = [] + + total_cjk = cjk_len(text) + # Guard against empty / whitespace-only input. + if total_cjk == 0: + return { + "score": 0, + "signals": [], + "spans": [], + "verdict": "human-like", + } + per100 = total_cjk / 100.0 # divisor to express "hits per 100 CJK chars" + + sentences = [s for s in SENT_SPLIT_RE.split(text) if s.strip()] + + # 1) Connector density ------------------------------------------------- + conn_hits, conn_spans = count_occurrences(text, CONNECTORS) + conn_value = clamp01((conn_hits / per100) / 2.5) # target ~2.5 / 100 chars + signals.append({ + "name": "connector_density", + "value": round(conn_value, 3), + "weight": weights["connector"], + "note": f"{conn_hits} discourse connectors", + }) + spans.extend(conn_spans) + + # 2) Cliché phrase hits ------------------------------------------------ + cliche_hits = 0 + for pattern in CLICHE_PATTERNS: + for m in re.finditer(pattern, text): + cliche_hits += 1 + spans.append(m.group(0)) + cliche_value = clamp01((cliche_hits / per100) / 1.2) # target ~1.2 / 100 + signals.append({ + "name": "cliche_phrases", + "value": round(cliche_value, 3), + "weight": weights["cliche"], + "note": f"{cliche_hits} cliché template hits", + }) + + # 3) Concreteness deficit ---------------------------------------------- + digits = len(DIGIT_RE.findall(text)) + fp_hits, _ = count_occurrences(text, FIRST_PERSON) + time_hits, _ = count_occurrences(text, TIME_WORDS) + concrete_raw = digits + fp_hits + time_hits + richness = clamp01((concrete_raw / per100) / 6.0) # target ~6 / 100 chars + concrete_value = 1.0 - richness # deficit: less concreteness = more AI + signals.append({ + "name": "concreteness_deficit", + "value": round(concrete_value, 3), + "weight": weights["concreteness"], + "note": f"{digits} digits, {fp_hits} first-person, {time_hits} time words", + }) + + # 4) Sentence-length burstiness ---------------------------------------- + lengths = [cjk_len(s) for s in sentences] + lengths = [n for n in lengths if n > 0] + if len(lengths) >= MIN_SENTS_FOR_BURST: + mean = sum(lengths) / len(lengths) + cv = (std(lengths) / mean) if mean > 0 else 0.0 + # Low coefficient of variation = uniform lengths = more AI-like. + burst_value = clamp01(1.0 - cv / 0.5) + note = f"{len(lengths)} sentences, cv={round(cv, 3)}" + else: + burst_value = NEUTRAL + note = f"{len(lengths)} sentences (too few to judge)" + signals.append({ + "name": "sentence_burstiness", + "value": round(burst_value, 3), + "weight": weights["burstiness"], + "note": note, + }) + + # 5) List / dash overuse ----------------------------------------------- + dash_hits = len(DASH_RE.findall(text)) + bullet_lines = sum( + 1 for line in text.splitlines() + if re.match(r"^\s*([-*•·\d]+[.、)]?)\s+", line) + ) + list_raw = dash_hits + bullet_lines + list_value = clamp01((list_raw / per100) / 2.0) # target ~2 / 100 chars + signals.append({ + "name": "list_dash_overuse", + "value": round(list_value, 3), + "weight": weights["list_dash"], + "note": f"{dash_hits} dashes, {bullet_lines} bullet lines", + }) + + # 6) Paragraph-length uniformity --------------------------------------- + paragraphs = [p for p in re.split(r"\n\s*\n", text) if p.strip()] + para_lengths = [cjk_len(p) for p in paragraphs] + para_lengths = [n for n in para_lengths if n > 0] + if len(para_lengths) >= MIN_PARAS_FOR_UNIFORM: + mean = sum(para_lengths) / len(para_lengths) + cv = (std(para_lengths) / mean) if mean > 0 else 0.0 + para_value = clamp01(1.0 - cv / 0.5) + note = f"{len(para_lengths)} paragraphs, cv={round(cv, 3)}" + else: + para_value = NEUTRAL + note = f"{len(para_lengths)} paragraphs (too few to judge)" + signals.append({ + "name": "paragraph_uniformity", + "value": round(para_value, 3), + "weight": weights["para_uniform"], + "note": note, + }) + + # --- Aggregate -------------------------------------------------------- + score = sum(s["value"] * s["weight"] for s in signals) + score = int(round(clamp01(score / 100.0) * 100)) + + if score < 40: + verdict = "human-like" + elif score < 60: + verdict = "some-ai" + else: + verdict = "strong-ai" + + # De-duplicate spans while preserving order, and cap the list length. + seen = set() + unique_spans = [] + for sp in spans: + if sp not in seen: + seen.add(sp) + unique_spans.append(sp) + unique_spans = unique_spans[:30] + + return { + "score": score, + "signals": signals, + "spans": unique_spans, + "verdict": verdict, + } + + +def load_input(): + """Load the JSON payload from argv[1] or stdin.""" + if len(sys.argv) > 1 and sys.argv[1].strip(): + raw = sys.argv[1] + else: + raw = sys.stdin.read() + if not raw or not raw.strip(): + return {"text": "", "platform": "gzh"} + return json.loads(raw) + + +def main(): + try: + payload = load_input() + except (ValueError, json.JSONDecodeError) as exc: + print(json.dumps({"error": f"invalid JSON input: {exc}"}, ensure_ascii=False)) + sys.exit(1) + + text = payload.get("text", "") or "" + platform = payload.get("platform", "gzh") or "gzh" + if platform not in WEIGHTS: + platform = "gzh" + + report = score_text(text, platform) + print(json.dumps(report, ensure_ascii=False)) + + +if __name__ == "__main__": + main() diff --git a/mateclaw-server/src/main/resources/skills/docx/scripts/__init__.py b/mateclaw-server/src/main/resources/skills/docx/scripts/__init__.py new file mode 100755 index 00000000..8b137891 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/docx/scripts/__init__.py @@ -0,0 +1 @@ + diff --git a/mateclaw-server/src/main/resources/skills/docx/scripts/accept_changes.py b/mateclaw-server/src/main/resources/skills/docx/scripts/accept_changes.py new file mode 100755 index 00000000..bfad3cd1 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/docx/scripts/accept_changes.py @@ -0,0 +1,138 @@ +"""Accept all tracked changes in a DOCX file using LibreOffice. + +Requires LibreOffice (soffice) to be installed. +""" + +import argparse +import logging +import shutil +import subprocess +import tempfile +from pathlib import Path + +from office.soffice import get_soffice_cmd, get_soffice_env + +logger = logging.getLogger(__name__) + +LIBREOFFICE_PROFILE = str(Path(tempfile.gettempdir()) / "libreoffice_docx_profile") +MACRO_DIR = str(Path(LIBREOFFICE_PROFILE) / "user" / "basic" / "Standard") + +ACCEPT_CHANGES_MACRO = """ + + + Sub AcceptAllTrackedChanges() + Dim document As Object + Dim dispatcher As Object + + document = ThisComponent.CurrentController.Frame + dispatcher = createUnoService("com.sun.star.frame.DispatchHelper") + + dispatcher.executeDispatch(document, ".uno:AcceptAllTrackedChanges", "", 0, Array()) + ThisComponent.store() + ThisComponent.close(True) + End Sub +""" + + +def accept_changes( + input_file: str, + output_file: str, +) -> tuple[None, str]: + input_path = Path(input_file) + output_path = Path(output_file) + + if not input_path.exists(): + return None, f"Error: Input file not found: {input_file}" + + if not input_path.suffix.lower() == ".docx": + return None, f"Error: Input file is not a DOCX file: {input_file}" + + try: + output_path.parent.mkdir(parents=True, exist_ok=True) + shutil.copy2(input_path, output_path) + except Exception as e: + return None, f"Error: Failed to copy input file to output location: {e}" + + if not _setup_libreoffice_macro(): + return None, "Error: Failed to setup LibreOffice macro" + + profile_uri = Path(LIBREOFFICE_PROFILE).as_uri() + cmd = [ + get_soffice_cmd(), + "--headless", + f"-env:UserInstallation={profile_uri}", + "--norestore", + "vnd.sun.star.script:Standard.Module1.AcceptAllTrackedChanges?language=Basic&location=application", + str(output_path.absolute()), + ] + + try: + result = subprocess.run( + cmd, + capture_output=True, + text=True, + timeout=30, + check=False, + env=get_soffice_env(), + ) + except subprocess.TimeoutExpired: + return ( + None, + f"Successfully accepted all tracked changes: {input_file} -> {output_file}", + ) + + if result.returncode != 0: + return None, f"Error: LibreOffice failed: {result.stderr}" + + return ( + None, + f"Successfully accepted all tracked changes: {input_file} -> {output_file}", + ) + + +def _setup_libreoffice_macro() -> bool: + macro_dir = Path(MACRO_DIR) + macro_file = macro_dir / "Module1.xba" + + if macro_file.exists() and "AcceptAllTrackedChanges" in macro_file.read_text(): + return True + + if not macro_dir.exists(): + profile_uri = Path(LIBREOFFICE_PROFILE).as_uri() + subprocess.run( + [ + get_soffice_cmd(), + "--headless", + f"-env:UserInstallation={profile_uri}", + "--terminate_after_init", + ], + capture_output=True, + timeout=10, + check=False, + env=get_soffice_env(), + ) + macro_dir.mkdir(parents=True, exist_ok=True) + + try: + macro_file.write_text(ACCEPT_CHANGES_MACRO) + return True + except Exception as e: + logger.warning(f"Failed to setup LibreOffice macro: {e}") + return False + + +if __name__ == "__main__": + parser = argparse.ArgumentParser( + description="Accept all tracked changes in a DOCX file" + ) + parser.add_argument("input_file", help="Input DOCX file with tracked changes") + parser.add_argument( + "output_file", help="Output DOCX file (clean, no tracked changes)" + ) + args = parser.parse_args() + + _, message = accept_changes(args.input_file, args.output_file) + print(message) + + if "Error" in message: + raise SystemExit(1) diff --git a/mateclaw-server/src/main/resources/skills/docx/scripts/comment.py b/mateclaw-server/src/main/resources/skills/docx/scripts/comment.py new file mode 100755 index 00000000..36e1c935 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/docx/scripts/comment.py @@ -0,0 +1,318 @@ +"""Add comments to DOCX documents. + +Usage: + python comment.py unpacked/ 0 "Comment text" + python comment.py unpacked/ 1 "Reply text" --parent 0 + +Text should be pre-escaped XML (e.g., & for &, ’ for smart quotes). + +After running, add markers to document.xml: + + ... commented content ... + + +""" + +import argparse +import random +import shutil +import sys +from datetime import datetime, timezone +from pathlib import Path + +import defusedxml.minidom + +TEMPLATE_DIR = Path(__file__).parent / "templates" +NS = { + "w": "http://schemas.openxmlformats.org/wordprocessingml/2006/main", + "w14": "http://schemas.microsoft.com/office/word/2010/wordml", + "w15": "http://schemas.microsoft.com/office/word/2012/wordml", + "w16cid": "http://schemas.microsoft.com/office/word/2016/wordml/cid", + "w16cex": "http://schemas.microsoft.com/office/word/2018/wordml/cex", +} + +COMMENT_XML = """\ + + + + + + + + + + + + + {text} + + +""" + +COMMENT_MARKER_TEMPLATE = """ +Add to document.xml (markers must be direct children of w:p, never inside w:r): + + ... + + """ + +REPLY_MARKER_TEMPLATE = """ +Nest markers inside parent {pid}'s markers (markers must be direct children of w:p, never inside w:r): + + ... + + + """ + + +def _generate_hex_id() -> str: + return f"{random.randint(0, 0x7FFFFFFE):08X}" + + +SMART_QUOTE_ENTITIES = { + "\u201c": "“", + "\u201d": "”", + "\u2018": "‘", + "\u2019": "’", +} + + +def _encode_smart_quotes(text: str) -> str: + for char, entity in SMART_QUOTE_ENTITIES.items(): + text = text.replace(char, entity) + return text + + +def _append_xml(xml_path: Path, root_tag: str, content: str) -> None: + dom = defusedxml.minidom.parseString(xml_path.read_text(encoding="utf-8")) + root = dom.getElementsByTagName(root_tag)[0] + ns_attrs = " ".join(f'xmlns:{k}="{v}"' for k, v in NS.items()) + wrapper_dom = defusedxml.minidom.parseString(f"{content}") + for child in wrapper_dom.documentElement.childNodes: + if child.nodeType == child.ELEMENT_NODE: + root.appendChild(dom.importNode(child, True)) + output = _encode_smart_quotes(dom.toxml(encoding="UTF-8").decode("utf-8")) + xml_path.write_text(output, encoding="utf-8") + + +def _find_para_id(comments_path: Path, comment_id: int) -> str | None: + dom = defusedxml.minidom.parseString(comments_path.read_text(encoding="utf-8")) + for c in dom.getElementsByTagName("w:comment"): + if c.getAttribute("w:id") == str(comment_id): + for p in c.getElementsByTagName("w:p"): + if pid := p.getAttribute("w14:paraId"): + return pid + return None + + +def _get_next_rid(rels_path: Path) -> int: + dom = defusedxml.minidom.parseString(rels_path.read_text(encoding="utf-8")) + max_rid = 0 + for rel in dom.getElementsByTagName("Relationship"): + rid = rel.getAttribute("Id") + if rid and rid.startswith("rId"): + try: + max_rid = max(max_rid, int(rid[3:])) + except ValueError: + pass + return max_rid + 1 + + +def _has_relationship(rels_path: Path, target: str) -> bool: + dom = defusedxml.minidom.parseString(rels_path.read_text(encoding="utf-8")) + for rel in dom.getElementsByTagName("Relationship"): + if rel.getAttribute("Target") == target: + return True + return False + + +def _has_content_type(ct_path: Path, part_name: str) -> bool: + dom = defusedxml.minidom.parseString(ct_path.read_text(encoding="utf-8")) + for override in dom.getElementsByTagName("Override"): + if override.getAttribute("PartName") == part_name: + return True + return False + + +def _ensure_comment_relationships(unpacked_dir: Path) -> None: + rels_path = unpacked_dir / "word" / "_rels" / "document.xml.rels" + if not rels_path.exists(): + return + + if _has_relationship(rels_path, "comments.xml"): + return + + dom = defusedxml.minidom.parseString(rels_path.read_text(encoding="utf-8")) + root = dom.documentElement + next_rid = _get_next_rid(rels_path) + + rels = [ + ( + "http://schemas.openxmlformats.org/officeDocument/2006/relationships/comments", + "comments.xml", + ), + ( + "http://schemas.microsoft.com/office/2011/relationships/commentsExtended", + "commentsExtended.xml", + ), + ( + "http://schemas.microsoft.com/office/2016/09/relationships/commentsIds", + "commentsIds.xml", + ), + ( + "http://schemas.microsoft.com/office/2018/08/relationships/commentsExtensible", + "commentsExtensible.xml", + ), + ] + + for rel_type, target in rels: + rel = dom.createElement("Relationship") + rel.setAttribute("Id", f"rId{next_rid}") + rel.setAttribute("Type", rel_type) + rel.setAttribute("Target", target) + root.appendChild(rel) + next_rid += 1 + + rels_path.write_bytes(dom.toxml(encoding="UTF-8")) + + +def _ensure_comment_content_types(unpacked_dir: Path) -> None: + ct_path = unpacked_dir / "[Content_Types].xml" + if not ct_path.exists(): + return + + if _has_content_type(ct_path, "/word/comments.xml"): + return + + dom = defusedxml.minidom.parseString(ct_path.read_text(encoding="utf-8")) + root = dom.documentElement + + overrides = [ + ( + "/word/comments.xml", + "application/vnd.openxmlformats-officedocument.wordprocessingml.comments+xml", + ), + ( + "/word/commentsExtended.xml", + "application/vnd.openxmlformats-officedocument.wordprocessingml.commentsExtended+xml", + ), + ( + "/word/commentsIds.xml", + "application/vnd.openxmlformats-officedocument.wordprocessingml.commentsIds+xml", + ), + ( + "/word/commentsExtensible.xml", + "application/vnd.openxmlformats-officedocument.wordprocessingml.commentsExtensible+xml", + ), + ] + + for part_name, content_type in overrides: + override = dom.createElement("Override") + override.setAttribute("PartName", part_name) + override.setAttribute("ContentType", content_type) + root.appendChild(override) + + ct_path.write_bytes(dom.toxml(encoding="UTF-8")) + + +def add_comment( + unpacked_dir: str, + comment_id: int, + text: str, + author: str = "Claude", + initials: str = "C", + parent_id: int | None = None, +) -> tuple[str, str]: + word = Path(unpacked_dir) / "word" + if not word.exists(): + return "", f"Error: {word} not found" + + para_id, durable_id = _generate_hex_id(), _generate_hex_id() + ts = datetime.now(timezone.utc).strftime("%Y-%m-%dT%H:%M:%SZ") + + comments = word / "comments.xml" + first_comment = not comments.exists() + if first_comment: + shutil.copy(TEMPLATE_DIR / "comments.xml", comments) + _ensure_comment_relationships(Path(unpacked_dir)) + _ensure_comment_content_types(Path(unpacked_dir)) + _append_xml( + comments, + "w:comments", + COMMENT_XML.format( + id=comment_id, + author=author, + date=ts, + initials=initials, + para_id=para_id, + text=text, + ), + ) + + ext = word / "commentsExtended.xml" + if not ext.exists(): + shutil.copy(TEMPLATE_DIR / "commentsExtended.xml", ext) + if parent_id is not None: + parent_para = _find_para_id(comments, parent_id) + if not parent_para: + return "", f"Error: Parent comment {parent_id} not found" + _append_xml( + ext, + "w15:commentsEx", + f'', + ) + else: + _append_xml( + ext, + "w15:commentsEx", + f'', + ) + + ids = word / "commentsIds.xml" + if not ids.exists(): + shutil.copy(TEMPLATE_DIR / "commentsIds.xml", ids) + _append_xml( + ids, + "w16cid:commentsIds", + f'', + ) + + extensible = word / "commentsExtensible.xml" + if not extensible.exists(): + shutil.copy(TEMPLATE_DIR / "commentsExtensible.xml", extensible) + _append_xml( + extensible, + "w16cex:commentsExtensible", + f'', + ) + + action = "reply" if parent_id is not None else "comment" + return para_id, f"Added {action} {comment_id} (para_id={para_id})" + + +if __name__ == "__main__": + p = argparse.ArgumentParser(description="Add comments to DOCX documents") + p.add_argument("unpacked_dir", help="Unpacked DOCX directory") + p.add_argument("comment_id", type=int, help="Comment ID (must be unique)") + p.add_argument("text", help="Comment text") + p.add_argument("--author", default="Claude", help="Author name") + p.add_argument("--initials", default="C", help="Author initials") + p.add_argument("--parent", type=int, help="Parent comment ID (for replies)") + args = p.parse_args() + + para_id, msg = add_comment( + args.unpacked_dir, + args.comment_id, + args.text, + args.author, + args.initials, + args.parent, + ) + print(msg) + if "Error" in msg: + sys.exit(1) + cid = args.comment_id + if args.parent is not None: + print(REPLY_MARKER_TEMPLATE.format(pid=args.parent, cid=cid)) + else: + print(COMMENT_MARKER_TEMPLATE.format(cid=cid)) diff --git a/mateclaw-server/src/main/resources/skills/docx/scripts/office/helpers/__init__.py b/mateclaw-server/src/main/resources/skills/docx/scripts/office/helpers/__init__.py new file mode 100644 index 00000000..e69de29b diff --git a/mateclaw-server/src/main/resources/skills/docx/scripts/office/helpers/merge_runs.py b/mateclaw-server/src/main/resources/skills/docx/scripts/office/helpers/merge_runs.py new file mode 100644 index 00000000..ad7c25ee --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/docx/scripts/office/helpers/merge_runs.py @@ -0,0 +1,199 @@ +"""Merge adjacent runs with identical formatting in DOCX. + +Merges adjacent elements that have identical properties. +Works on runs in paragraphs and inside tracked changes (, ). + +Also: +- Removes rsid attributes from runs (revision metadata that doesn't affect rendering) +- Removes proofErr elements (spell/grammar markers that block merging) +""" + +from pathlib import Path + +import defusedxml.minidom + + +def merge_runs(input_dir: str) -> tuple[int, str]: + doc_xml = Path(input_dir) / "word" / "document.xml" + + if not doc_xml.exists(): + return 0, f"Error: {doc_xml} not found" + + try: + dom = defusedxml.minidom.parseString(doc_xml.read_text(encoding="utf-8")) + root = dom.documentElement + + _remove_elements(root, "proofErr") + _strip_run_rsid_attrs(root) + + containers = {run.parentNode for run in _find_elements(root, "r")} + + merge_count = 0 + for container in containers: + merge_count += _merge_runs_in(container) + + doc_xml.write_bytes(dom.toxml(encoding="UTF-8")) + return merge_count, f"Merged {merge_count} runs" + + except Exception as e: + return 0, f"Error: {e}" + + + + +def _find_elements(root, tag: str) -> list: + results = [] + + def traverse(node): + if node.nodeType == node.ELEMENT_NODE: + name = node.localName or node.tagName + if name == tag or name.endswith(f":{tag}"): + results.append(node) + for child in node.childNodes: + traverse(child) + + traverse(root) + return results + + +def _get_child(parent, tag: str): + for child in parent.childNodes: + if child.nodeType == child.ELEMENT_NODE: + name = child.localName or child.tagName + if name == tag or name.endswith(f":{tag}"): + return child + return None + + +def _get_children(parent, tag: str) -> list: + results = [] + for child in parent.childNodes: + if child.nodeType == child.ELEMENT_NODE: + name = child.localName or child.tagName + if name == tag or name.endswith(f":{tag}"): + results.append(child) + return results + + +def _is_adjacent(elem1, elem2) -> bool: + node = elem1.nextSibling + while node: + if node == elem2: + return True + if node.nodeType == node.ELEMENT_NODE: + return False + if node.nodeType == node.TEXT_NODE and node.data.strip(): + return False + node = node.nextSibling + return False + + + + +def _remove_elements(root, tag: str): + for elem in _find_elements(root, tag): + if elem.parentNode: + elem.parentNode.removeChild(elem) + + +def _strip_run_rsid_attrs(root): + for run in _find_elements(root, "r"): + for attr in list(run.attributes.values()): + if "rsid" in attr.name.lower(): + run.removeAttribute(attr.name) + + + + +def _merge_runs_in(container) -> int: + merge_count = 0 + run = _first_child_run(container) + + while run: + while True: + next_elem = _next_element_sibling(run) + if next_elem and _is_run(next_elem) and _can_merge(run, next_elem): + _merge_run_content(run, next_elem) + container.removeChild(next_elem) + merge_count += 1 + else: + break + + _consolidate_text(run) + run = _next_sibling_run(run) + + return merge_count + + +def _first_child_run(container): + for child in container.childNodes: + if child.nodeType == child.ELEMENT_NODE and _is_run(child): + return child + return None + + +def _next_element_sibling(node): + sibling = node.nextSibling + while sibling: + if sibling.nodeType == sibling.ELEMENT_NODE: + return sibling + sibling = sibling.nextSibling + return None + + +def _next_sibling_run(node): + sibling = node.nextSibling + while sibling: + if sibling.nodeType == sibling.ELEMENT_NODE: + if _is_run(sibling): + return sibling + sibling = sibling.nextSibling + return None + + +def _is_run(node) -> bool: + name = node.localName or node.tagName + return name == "r" or name.endswith(":r") + + +def _can_merge(run1, run2) -> bool: + rpr1 = _get_child(run1, "rPr") + rpr2 = _get_child(run2, "rPr") + + if (rpr1 is None) != (rpr2 is None): + return False + if rpr1 is None: + return True + return rpr1.toxml() == rpr2.toxml() + + +def _merge_run_content(target, source): + for child in list(source.childNodes): + if child.nodeType == child.ELEMENT_NODE: + name = child.localName or child.tagName + if name != "rPr" and not name.endswith(":rPr"): + target.appendChild(child) + + +def _consolidate_text(run): + t_elements = _get_children(run, "t") + + for i in range(len(t_elements) - 1, 0, -1): + curr, prev = t_elements[i], t_elements[i - 1] + + if _is_adjacent(prev, curr): + prev_text = prev.firstChild.data if prev.firstChild else "" + curr_text = curr.firstChild.data if curr.firstChild else "" + merged = prev_text + curr_text + + if prev.firstChild: + prev.firstChild.data = merged + else: + prev.appendChild(run.ownerDocument.createTextNode(merged)) + + if merged.startswith(" ") or merged.endswith(" "): + prev.setAttribute("xml:space", "preserve") + elif prev.hasAttribute("xml:space"): + prev.removeAttribute("xml:space") + + run.removeChild(curr) diff --git a/mateclaw-server/src/main/resources/skills/docx/scripts/office/helpers/simplify_redlines.py b/mateclaw-server/src/main/resources/skills/docx/scripts/office/helpers/simplify_redlines.py new file mode 100644 index 00000000..db963bb9 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/docx/scripts/office/helpers/simplify_redlines.py @@ -0,0 +1,197 @@ +"""Simplify tracked changes by merging adjacent w:ins or w:del elements. + +Merges adjacent elements from the same author into a single element. +Same for elements. This makes heavily-redlined documents easier to +work with by reducing the number of tracked change wrappers. + +Rules: +- Only merges w:ins with w:ins, w:del with w:del (same element type) +- Only merges if same author (ignores timestamp differences) +- Only merges if truly adjacent (only whitespace between them) +""" + +import xml.etree.ElementTree as ET +import zipfile +from pathlib import Path + +import defusedxml.minidom + +WORD_NS = "http://schemas.openxmlformats.org/wordprocessingml/2006/main" + + +def simplify_redlines(input_dir: str) -> tuple[int, str]: + doc_xml = Path(input_dir) / "word" / "document.xml" + + if not doc_xml.exists(): + return 0, f"Error: {doc_xml} not found" + + try: + dom = defusedxml.minidom.parseString(doc_xml.read_text(encoding="utf-8")) + root = dom.documentElement + + merge_count = 0 + + containers = _find_elements(root, "p") + _find_elements(root, "tc") + + for container in containers: + merge_count += _merge_tracked_changes_in(container, "ins") + merge_count += _merge_tracked_changes_in(container, "del") + + doc_xml.write_bytes(dom.toxml(encoding="UTF-8")) + return merge_count, f"Simplified {merge_count} tracked changes" + + except Exception as e: + return 0, f"Error: {e}" + + +def _merge_tracked_changes_in(container, tag: str) -> int: + merge_count = 0 + + tracked = [ + child + for child in container.childNodes + if child.nodeType == child.ELEMENT_NODE and _is_element(child, tag) + ] + + if len(tracked) < 2: + return 0 + + i = 0 + while i < len(tracked) - 1: + curr = tracked[i] + next_elem = tracked[i + 1] + + if _can_merge_tracked(curr, next_elem): + _merge_tracked_content(curr, next_elem) + container.removeChild(next_elem) + tracked.pop(i + 1) + merge_count += 1 + else: + i += 1 + + return merge_count + + +def _is_element(node, tag: str) -> bool: + name = node.localName or node.tagName + return name == tag or name.endswith(f":{tag}") + + +def _get_author(elem) -> str: + author = elem.getAttribute("w:author") + if not author: + for attr in elem.attributes.values(): + if attr.localName == "author" or attr.name.endswith(":author"): + return attr.value + return author + + +def _can_merge_tracked(elem1, elem2) -> bool: + if _get_author(elem1) != _get_author(elem2): + return False + + node = elem1.nextSibling + while node and node != elem2: + if node.nodeType == node.ELEMENT_NODE: + return False + if node.nodeType == node.TEXT_NODE and node.data.strip(): + return False + node = node.nextSibling + + return True + + +def _merge_tracked_content(target, source): + while source.firstChild: + child = source.firstChild + source.removeChild(child) + target.appendChild(child) + + +def _find_elements(root, tag: str) -> list: + results = [] + + def traverse(node): + if node.nodeType == node.ELEMENT_NODE: + name = node.localName or node.tagName + if name == tag or name.endswith(f":{tag}"): + results.append(node) + for child in node.childNodes: + traverse(child) + + traverse(root) + return results + + +def get_tracked_change_authors(doc_xml_path: Path) -> dict[str, int]: + if not doc_xml_path.exists(): + return {} + + try: + tree = ET.parse(doc_xml_path) + root = tree.getroot() + except ET.ParseError: + return {} + + namespaces = {"w": WORD_NS} + author_attr = f"{{{WORD_NS}}}author" + + authors: dict[str, int] = {} + for tag in ["ins", "del"]: + for elem in root.findall(f".//w:{tag}", namespaces): + author = elem.get(author_attr) + if author: + authors[author] = authors.get(author, 0) + 1 + + return authors + + +def _get_authors_from_docx(docx_path: Path) -> dict[str, int]: + try: + with zipfile.ZipFile(docx_path, "r") as zf: + if "word/document.xml" not in zf.namelist(): + return {} + with zf.open("word/document.xml") as f: + tree = ET.parse(f) + root = tree.getroot() + + namespaces = {"w": WORD_NS} + author_attr = f"{{{WORD_NS}}}author" + + authors: dict[str, int] = {} + for tag in ["ins", "del"]: + for elem in root.findall(f".//w:{tag}", namespaces): + author = elem.get(author_attr) + if author: + authors[author] = authors.get(author, 0) + 1 + return authors + except (zipfile.BadZipFile, ET.ParseError): + return {} + + +def infer_author(modified_dir: Path, original_docx: Path, default: str = "Claude") -> str: + modified_xml = modified_dir / "word" / "document.xml" + modified_authors = get_tracked_change_authors(modified_xml) + + if not modified_authors: + return default + + original_authors = _get_authors_from_docx(original_docx) + + new_changes: dict[str, int] = {} + for author, count in modified_authors.items(): + original_count = original_authors.get(author, 0) + diff = count - original_count + if diff > 0: + new_changes[author] = diff + + if not new_changes: + return default + + if len(new_changes) == 1: + return next(iter(new_changes)) + + raise ValueError( + f"Multiple authors added new changes: {new_changes}. " + "Cannot infer which author to validate." + ) diff --git a/mateclaw-server/src/main/resources/skills/docx/scripts/office/pack.py b/mateclaw-server/src/main/resources/skills/docx/scripts/office/pack.py new file mode 100755 index 00000000..db29ed8b --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/docx/scripts/office/pack.py @@ -0,0 +1,159 @@ +"""Pack a directory into a DOCX, PPTX, or XLSX file. + +Validates with auto-repair, condenses XML formatting, and creates the Office file. + +Usage: + python pack.py [--original ] [--validate true|false] + +Examples: + python pack.py unpacked/ output.docx --original input.docx + python pack.py unpacked/ output.pptx --validate false +""" + +import argparse +import sys +import shutil +import tempfile +import zipfile +from pathlib import Path + +import defusedxml.minidom + +from validators import DOCXSchemaValidator, PPTXSchemaValidator, RedliningValidator + +def pack( + input_directory: str, + output_file: str, + original_file: str | None = None, + validate: bool = True, + infer_author_func=None, +) -> tuple[None, str]: + input_dir = Path(input_directory) + output_path = Path(output_file) + suffix = output_path.suffix.lower() + + if not input_dir.is_dir(): + return None, f"Error: {input_dir} is not a directory" + + if suffix not in {".docx", ".pptx", ".xlsx"}: + return None, f"Error: {output_file} must be a .docx, .pptx, or .xlsx file" + + if validate and original_file: + original_path = Path(original_file) + if original_path.exists(): + success, output = _run_validation( + input_dir, original_path, suffix, infer_author_func + ) + if output: + print(output) + if not success: + return None, f"Error: Validation failed for {input_dir}" + + with tempfile.TemporaryDirectory() as temp_dir: + temp_content_dir = Path(temp_dir) / "content" + shutil.copytree(input_dir, temp_content_dir) + + for pattern in ["*.xml", "*.rels"]: + for xml_file in temp_content_dir.rglob(pattern): + _condense_xml(xml_file) + + output_path.parent.mkdir(parents=True, exist_ok=True) + with zipfile.ZipFile(output_path, "w", zipfile.ZIP_DEFLATED) as zf: + for f in temp_content_dir.rglob("*"): + if f.is_file(): + zf.write(f, f.relative_to(temp_content_dir)) + + return None, f"Successfully packed {input_dir} to {output_file}" + + +def _run_validation( + unpacked_dir: Path, + original_file: Path, + suffix: str, + infer_author_func=None, +) -> tuple[bool, str | None]: + output_lines = [] + validators = [] + + if suffix == ".docx": + author = "Claude" + if infer_author_func: + try: + author = infer_author_func(unpacked_dir, original_file) + except ValueError as e: + print(f"Warning: {e} Using default author 'Claude'.", file=sys.stderr) + + validators = [ + DOCXSchemaValidator(unpacked_dir, original_file), + RedliningValidator(unpacked_dir, original_file, author=author), + ] + elif suffix == ".pptx": + validators = [PPTXSchemaValidator(unpacked_dir, original_file)] + + if not validators: + return True, None + + total_repairs = sum(v.repair() for v in validators) + if total_repairs: + output_lines.append(f"Auto-repaired {total_repairs} issue(s)") + + success = all(v.validate() for v in validators) + + if success: + output_lines.append("All validations PASSED!") + + return success, "\n".join(output_lines) if output_lines else None + + +def _condense_xml(xml_file: Path) -> None: + try: + with open(xml_file, encoding="utf-8") as f: + dom = defusedxml.minidom.parse(f) + + for element in dom.getElementsByTagName("*"): + if element.tagName.endswith(":t"): + continue + + for child in list(element.childNodes): + if ( + child.nodeType == child.TEXT_NODE + and child.nodeValue + and child.nodeValue.strip() == "" + ) or child.nodeType == child.COMMENT_NODE: + element.removeChild(child) + + xml_file.write_bytes(dom.toxml(encoding="UTF-8")) + except Exception as e: + print(f"ERROR: Failed to parse {xml_file.name}: {e}", file=sys.stderr) + raise + + +if __name__ == "__main__": + parser = argparse.ArgumentParser( + description="Pack a directory into a DOCX, PPTX, or XLSX file" + ) + parser.add_argument("input_directory", help="Unpacked Office document directory") + parser.add_argument("output_file", help="Output Office file (.docx/.pptx/.xlsx)") + parser.add_argument( + "--original", + help="Original file for validation comparison", + ) + parser.add_argument( + "--validate", + type=lambda x: x.lower() == "true", + default=True, + metavar="true|false", + help="Run validation with auto-repair (default: true)", + ) + args = parser.parse_args() + + _, message = pack( + args.input_directory, + args.output_file, + original_file=args.original, + validate=args.validate, + ) + print(message) + + if "Error" in message: + sys.exit(1) diff --git a/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-chart.xsd b/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-chart.xsd new file mode 100644 index 00000000..6454ef9a --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-chart.xsd @@ -0,0 +1,1499 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-chartDrawing.xsd b/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-chartDrawing.xsd new file mode 100644 index 00000000..afa4f463 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-chartDrawing.xsd @@ -0,0 +1,146 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-diagram.xsd b/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-diagram.xsd new file mode 100644 index 00000000..64e66b8a --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-diagram.xsd @@ -0,0 +1,1085 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-lockedCanvas.xsd b/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-lockedCanvas.xsd new file mode 100644 index 00000000..687eea82 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-lockedCanvas.xsd @@ -0,0 +1,11 @@ + + + + + diff --git a/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-main.xsd b/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-main.xsd new file mode 100644 index 00000000..6ac81b06 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-main.xsd @@ -0,0 +1,3081 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-picture.xsd b/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-picture.xsd new file mode 100644 index 00000000..1dbf0514 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-picture.xsd @@ -0,0 +1,23 @@ + + + + + + + + + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-spreadsheetDrawing.xsd b/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-spreadsheetDrawing.xsd new file mode 100644 index 00000000..f1af17db --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-spreadsheetDrawing.xsd @@ -0,0 +1,185 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-wordprocessingDrawing.xsd b/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-wordprocessingDrawing.xsd new file mode 100644 index 00000000..0a185ab6 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-wordprocessingDrawing.xsd @@ -0,0 +1,287 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/pml.xsd b/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/pml.xsd new file mode 100644 index 00000000..14ef4888 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/pml.xsd @@ -0,0 +1,1676 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-additionalCharacteristics.xsd b/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-additionalCharacteristics.xsd new file mode 100644 index 00000000..c20f3bf1 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-additionalCharacteristics.xsd @@ -0,0 +1,28 @@ + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-bibliography.xsd b/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-bibliography.xsd new file mode 100644 index 00000000..ac602522 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-bibliography.xsd @@ -0,0 +1,144 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-commonSimpleTypes.xsd b/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-commonSimpleTypes.xsd new file mode 100644 index 00000000..424b8ba8 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-commonSimpleTypes.xsd @@ -0,0 +1,174 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-customXmlDataProperties.xsd b/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-customXmlDataProperties.xsd new file mode 100644 index 00000000..2bddce29 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-customXmlDataProperties.xsd @@ -0,0 +1,25 @@ + + + + + + + + + + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-customXmlSchemaProperties.xsd b/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-customXmlSchemaProperties.xsd new file mode 100644 index 00000000..8a8c18ba --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-customXmlSchemaProperties.xsd @@ -0,0 +1,18 @@ + + + + + + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesCustom.xsd b/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesCustom.xsd new file mode 100644 index 00000000..5c42706a --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesCustom.xsd @@ -0,0 +1,59 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesExtended.xsd b/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesExtended.xsd new file mode 100644 index 00000000..853c341c --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesExtended.xsd @@ -0,0 +1,56 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesVariantTypes.xsd b/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesVariantTypes.xsd new file mode 100644 index 00000000..da835ee8 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesVariantTypes.xsd @@ -0,0 +1,195 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-math.xsd b/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-math.xsd new file mode 100644 index 00000000..87ad2658 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-math.xsd @@ -0,0 +1,582 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-relationshipReference.xsd b/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-relationshipReference.xsd new file mode 100644 index 00000000..9e86f1b2 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-relationshipReference.xsd @@ -0,0 +1,25 @@ + + + + + + + + + + + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/sml.xsd b/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/sml.xsd new file mode 100644 index 00000000..d0be42e7 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/sml.xsd @@ -0,0 +1,4439 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-main.xsd b/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-main.xsd new file mode 100644 index 00000000..8821dd18 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-main.xsd @@ -0,0 +1,570 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-officeDrawing.xsd b/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-officeDrawing.xsd new file mode 100644 index 00000000..ca2575c7 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-officeDrawing.xsd @@ -0,0 +1,509 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-presentationDrawing.xsd b/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-presentationDrawing.xsd new file mode 100644 index 00000000..dd079e60 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-presentationDrawing.xsd @@ -0,0 +1,12 @@ + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-spreadsheetDrawing.xsd b/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-spreadsheetDrawing.xsd new file mode 100644 index 00000000..3dd6cf62 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-spreadsheetDrawing.xsd @@ -0,0 +1,108 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-wordprocessingDrawing.xsd b/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-wordprocessingDrawing.xsd new file mode 100644 index 00000000..f1041e34 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-wordprocessingDrawing.xsd @@ -0,0 +1,96 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/wml.xsd b/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/wml.xsd new file mode 100644 index 00000000..9c5b7a63 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/wml.xsd @@ -0,0 +1,3646 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/xml.xsd b/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/xml.xsd new file mode 100644 index 00000000..0f13678d --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/ISO-IEC29500-4_2016/xml.xsd @@ -0,0 +1,116 @@ + + + + + + See http://www.w3.org/XML/1998/namespace.html and + http://www.w3.org/TR/REC-xml for information about this namespace. + + This schema document describes the XML namespace, in a form + suitable for import by other schema documents. + + Note that local names in this namespace are intended to be defined + only by the World Wide Web Consortium or its subgroups. The + following names are currently defined in this namespace and should + not be used with conflicting semantics by any Working Group, + specification, or document instance: + + base (as an attribute name): denotes an attribute whose value + provides a URI to be used as the base for interpreting any + relative URIs in the scope of the element on which it + appears; its value is inherited. This name is reserved + by virtue of its definition in the XML Base specification. + + lang (as an attribute name): denotes an attribute whose value + is a language code for the natural language of the content of + any element; its value is inherited. This name is reserved + by virtue of its definition in the XML specification. + + space (as an attribute name): denotes an attribute whose + value is a keyword indicating what whitespace processing + discipline is intended for the content of the element; its + value is inherited. This name is reserved by virtue of its + definition in the XML specification. + + Father (in any context at all): denotes Jon Bosak, the chair of + the original XML Working Group. This name is reserved by + the following decision of the W3C XML Plenary and + XML Coordination groups: + + In appreciation for his vision, leadership and dedication + the W3C XML Plenary on this 10th day of February, 2000 + reserves for Jon Bosak in perpetuity the XML name + xml:Father + + + + + This schema defines attributes and an attribute group + suitable for use by + schemas wishing to allow xml:base, xml:lang or xml:space attributes + on elements they define. + + To enable this, such a schema must import this schema + for the XML namespace, e.g. as follows: + <schema . . .> + . . . + <import namespace="http://www.w3.org/XML/1998/namespace" + schemaLocation="http://www.w3.org/2001/03/xml.xsd"/> + + Subsequently, qualified reference to any of the attributes + or the group defined below will have the desired effect, e.g. + + <type . . .> + . . . + <attributeGroup ref="xml:specialAttrs"/> + + will define a type which will schema-validate an instance + element with any of those attributes + + + + In keeping with the XML Schema WG's standard versioning + policy, this schema document will persist at + http://www.w3.org/2001/03/xml.xsd. + At the date of issue it can also be found at + http://www.w3.org/2001/xml.xsd. + The schema document at that URI may however change in the future, + in order to remain compatible with the latest version of XML Schema + itself. In other words, if the XML Schema namespace changes, the version + of this document at + http://www.w3.org/2001/xml.xsd will change + accordingly; the version at + http://www.w3.org/2001/03/xml.xsd will not change. + + + + + + In due course, we should install the relevant ISO 2- and 3-letter + codes as the enumerated possible values . . . + + + + + + + + + + + + + + + See http://www.w3.org/TR/xmlbase/ for + information about this attribute. + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/ecma/fouth-edition/opc-contentTypes.xsd b/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/ecma/fouth-edition/opc-contentTypes.xsd new file mode 100644 index 00000000..a6de9d27 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/ecma/fouth-edition/opc-contentTypes.xsd @@ -0,0 +1,42 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/ecma/fouth-edition/opc-coreProperties.xsd b/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/ecma/fouth-edition/opc-coreProperties.xsd new file mode 100644 index 00000000..10e978b6 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/ecma/fouth-edition/opc-coreProperties.xsd @@ -0,0 +1,50 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/ecma/fouth-edition/opc-digSig.xsd b/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/ecma/fouth-edition/opc-digSig.xsd new file mode 100644 index 00000000..4248bf7a --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/ecma/fouth-edition/opc-digSig.xsd @@ -0,0 +1,49 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/ecma/fouth-edition/opc-relationships.xsd b/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/ecma/fouth-edition/opc-relationships.xsd new file mode 100644 index 00000000..56497467 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/ecma/fouth-edition/opc-relationships.xsd @@ -0,0 +1,33 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/mce/mc.xsd b/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/mce/mc.xsd new file mode 100644 index 00000000..ef725457 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/mce/mc.xsd @@ -0,0 +1,75 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/microsoft/wml-2010.xsd b/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/microsoft/wml-2010.xsd new file mode 100644 index 00000000..f65f7777 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/microsoft/wml-2010.xsd @@ -0,0 +1,560 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/microsoft/wml-2012.xsd b/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/microsoft/wml-2012.xsd new file mode 100644 index 00000000..6b00755a --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/microsoft/wml-2012.xsd @@ -0,0 +1,67 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/microsoft/wml-2018.xsd b/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/microsoft/wml-2018.xsd new file mode 100644 index 00000000..f321d333 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/microsoft/wml-2018.xsd @@ -0,0 +1,14 @@ + + + + + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/microsoft/wml-cex-2018.xsd b/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/microsoft/wml-cex-2018.xsd new file mode 100644 index 00000000..364c6a9b --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/microsoft/wml-cex-2018.xsd @@ -0,0 +1,20 @@ + + + + + + + + + + + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/microsoft/wml-cid-2016.xsd b/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/microsoft/wml-cid-2016.xsd new file mode 100644 index 00000000..fed9d15b --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/microsoft/wml-cid-2016.xsd @@ -0,0 +1,13 @@ + + + + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/microsoft/wml-sdtdatahash-2020.xsd b/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/microsoft/wml-sdtdatahash-2020.xsd new file mode 100644 index 00000000..680cf154 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/microsoft/wml-sdtdatahash-2020.xsd @@ -0,0 +1,4 @@ + + + + diff --git a/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/microsoft/wml-symex-2015.xsd b/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/microsoft/wml-symex-2015.xsd new file mode 100644 index 00000000..89ada908 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/docx/scripts/office/schemas/microsoft/wml-symex-2015.xsd @@ -0,0 +1,8 @@ + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/docx/scripts/office/soffice.py b/mateclaw-server/src/main/resources/skills/docx/scripts/office/soffice.py new file mode 100644 index 00000000..d64118bb --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/docx/scripts/office/soffice.py @@ -0,0 +1,220 @@ +""" +Helper for running LibreOffice (soffice) in environments where AF_UNIX +sockets may be blocked (e.g., sandboxed VMs). Detects the restriction +at runtime and applies an LD_PRELOAD shim if needed. + +Usage: + from office.soffice import run_soffice, get_soffice_cmd, get_soffice_env + + # Option 1 – run soffice directly + result = run_soffice(["--headless", "--convert-to", "pdf", "input.docx"]) + + # Option 2 – get env dict for your own subprocess calls + env = get_soffice_env() + subprocess.run([get_soffice_cmd(), ...], env=env) +""" + +import os +import platform +import shutil +import socket +import subprocess +import tempfile +from pathlib import Path + + +def get_soffice_cmd() -> str: + """Return the soffice command name for the current platform.""" + # Prefer PATH first on all platforms. + path_cmd = shutil.which("soffice") + if path_cmd: + return path_cmd + + if platform.system() == "Windows": + # Windows can expose soffice as .com or .exe; try both on PATH first. + for candidate_name in ("soffice.com", "soffice.exe"): + path_candidate = shutil.which(candidate_name) + if path_candidate: + return path_candidate + + # On Windows, try to find soffice.exe via common install paths + for prog_dir in ( + os.environ.get("PROGRAMFILES", r"C:\Program Files"), + os.environ.get("PROGRAMFILES(X86)", r"C:\Program Files (x86)"), + ): + if not prog_dir: + continue + program_dir = Path(prog_dir) / "LibreOffice" / "program" + for exe_name in ("soffice.com", "soffice.exe"): + candidate = program_dir / exe_name + if candidate.exists(): + return str(candidate) + return "soffice" # fallback, hope it's on PATH + return "soffice" + + +def get_soffice_env() -> dict: + env = os.environ.copy() + # SAL_USE_VCLPLUGIN=svp is Linux-only (headless rendering) + if platform.system() == "Linux": + env["SAL_USE_VCLPLUGIN"] = "svp" + + if _needs_shim(): + shim = _ensure_shim() + env["LD_PRELOAD"] = str(shim) + + return env + + +def run_soffice(args: list[str], **kwargs) -> subprocess.CompletedProcess: + env = get_soffice_env() + return subprocess.run([get_soffice_cmd()] + args, env=env, **kwargs) + + + +_SHIM_SO = Path(tempfile.gettempdir()) / "lo_socket_shim.so" + + +def _needs_shim() -> bool: + # AF_UNIX / LD_PRELOAD shim is Linux-only; skip on Windows and macOS + if not hasattr(socket, "AF_UNIX"): + return False + try: + s = socket.socket(socket.AF_UNIX, socket.SOCK_STREAM) + s.close() + return False + except OSError: + return True + + +def _ensure_shim() -> Path: + if _SHIM_SO.exists(): + return _SHIM_SO + + src = Path(tempfile.gettempdir()) / "lo_socket_shim.c" + src.write_text(_SHIM_SOURCE) + subprocess.run( + ["gcc", "-shared", "-fPIC", "-o", str(_SHIM_SO), str(src), "-ldl"], + check=True, + capture_output=True, + ) + src.unlink() + return _SHIM_SO + + + +_SHIM_SOURCE = r""" +#define _GNU_SOURCE +#include +#include +#include +#include +#include +#include +#include + +static int (*real_socket)(int, int, int); +static int (*real_socketpair)(int, int, int, int[2]); +static int (*real_listen)(int, int); +static int (*real_accept)(int, struct sockaddr *, socklen_t *); +static int (*real_close)(int); +static int (*real_read)(int, void *, size_t); + +/* Per-FD bookkeeping (FDs >= 1024 are passed through unshimmed). */ +static int is_shimmed[1024]; +static int peer_of[1024]; +static int wake_r[1024]; /* accept() blocks reading this */ +static int wake_w[1024]; /* close() writes to this */ +static int listener_fd = -1; /* FD that received listen() */ + +__attribute__((constructor)) +static void init(void) { + real_socket = dlsym(RTLD_NEXT, "socket"); + real_socketpair = dlsym(RTLD_NEXT, "socketpair"); + real_listen = dlsym(RTLD_NEXT, "listen"); + real_accept = dlsym(RTLD_NEXT, "accept"); + real_close = dlsym(RTLD_NEXT, "close"); + real_read = dlsym(RTLD_NEXT, "read"); + for (int i = 0; i < 1024; i++) { + peer_of[i] = -1; + wake_r[i] = -1; + wake_w[i] = -1; + } +} + +/* ---- socket ---------------------------------------------------------- */ +int socket(int domain, int type, int protocol) { + if (domain == AF_UNIX) { + int fd = real_socket(domain, type, protocol); + if (fd >= 0) return fd; + /* socket(AF_UNIX) blocked – fall back to socketpair(). */ + int sv[2]; + if (real_socketpair(domain, type, protocol, sv) == 0) { + if (sv[0] >= 0 && sv[0] < 1024) { + is_shimmed[sv[0]] = 1; + peer_of[sv[0]] = sv[1]; + int wp[2]; + if (pipe(wp) == 0) { + wake_r[sv[0]] = wp[0]; + wake_w[sv[0]] = wp[1]; + } + } + return sv[0]; + } + errno = EPERM; + return -1; + } + return real_socket(domain, type, protocol); +} + +/* ---- listen ---------------------------------------------------------- */ +int listen(int sockfd, int backlog) { + if (sockfd >= 0 && sockfd < 1024 && is_shimmed[sockfd]) { + listener_fd = sockfd; + return 0; + } + return real_listen(sockfd, backlog); +} + +/* ---- accept ---------------------------------------------------------- */ +int accept(int sockfd, struct sockaddr *addr, socklen_t *addrlen) { + if (sockfd >= 0 && sockfd < 1024 && is_shimmed[sockfd]) { + /* Block until close() writes to the wake pipe. */ + if (wake_r[sockfd] >= 0) { + char buf; + real_read(wake_r[sockfd], &buf, 1); + } + errno = ECONNABORTED; + return -1; + } + return real_accept(sockfd, addr, addrlen); +} + +/* ---- close ----------------------------------------------------------- */ +int close(int fd) { + if (fd >= 0 && fd < 1024 && is_shimmed[fd]) { + int was_listener = (fd == listener_fd); + is_shimmed[fd] = 0; + + if (wake_w[fd] >= 0) { /* unblock accept() */ + char c = 0; + write(wake_w[fd], &c, 1); + real_close(wake_w[fd]); + wake_w[fd] = -1; + } + if (wake_r[fd] >= 0) { real_close(wake_r[fd]); wake_r[fd] = -1; } + if (peer_of[fd] >= 0) { real_close(peer_of[fd]); peer_of[fd] = -1; } + + if (was_listener) + _exit(0); /* conversion done – exit */ + } + return real_close(fd); +} +""" + + + +if __name__ == "__main__": + import sys + result = run_soffice(sys.argv[1:]) + sys.exit(result.returncode) diff --git a/mateclaw-server/src/main/resources/skills/docx/scripts/office/unpack.py b/mateclaw-server/src/main/resources/skills/docx/scripts/office/unpack.py new file mode 100755 index 00000000..00152533 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/docx/scripts/office/unpack.py @@ -0,0 +1,132 @@ +"""Unpack Office files (DOCX, PPTX, XLSX) for editing. + +Extracts the ZIP archive, pretty-prints XML files, and optionally: +- Merges adjacent runs with identical formatting (DOCX only) +- Simplifies adjacent tracked changes from same author (DOCX only) + +Usage: + python unpack.py [options] + +Examples: + python unpack.py document.docx unpacked/ + python unpack.py presentation.pptx unpacked/ + python unpack.py document.docx unpacked/ --merge-runs false +""" + +import argparse +import sys +import zipfile +from pathlib import Path + +import defusedxml.minidom + +from helpers.merge_runs import merge_runs as do_merge_runs +from helpers.simplify_redlines import simplify_redlines as do_simplify_redlines + +SMART_QUOTE_REPLACEMENTS = { + "\u201c": "“", + "\u201d": "”", + "\u2018": "‘", + "\u2019": "’", +} + + +def unpack( + input_file: str, + output_directory: str, + merge_runs: bool = True, + simplify_redlines: bool = True, +) -> tuple[None, str]: + input_path = Path(input_file) + output_path = Path(output_directory) + suffix = input_path.suffix.lower() + + if not input_path.exists(): + return None, f"Error: {input_file} does not exist" + + if suffix not in {".docx", ".pptx", ".xlsx"}: + return None, f"Error: {input_file} must be a .docx, .pptx, or .xlsx file" + + try: + output_path.mkdir(parents=True, exist_ok=True) + + with zipfile.ZipFile(input_path, "r") as zf: + zf.extractall(output_path) + + xml_files = list(output_path.rglob("*.xml")) + list(output_path.rglob("*.rels")) + for xml_file in xml_files: + _pretty_print_xml(xml_file) + + message = f"Unpacked {input_file} ({len(xml_files)} XML files)" + + if suffix == ".docx": + if simplify_redlines: + simplify_count, _ = do_simplify_redlines(str(output_path)) + message += f", simplified {simplify_count} tracked changes" + + if merge_runs: + merge_count, _ = do_merge_runs(str(output_path)) + message += f", merged {merge_count} runs" + + for xml_file in xml_files: + _escape_smart_quotes(xml_file) + + return None, message + + except zipfile.BadZipFile: + return None, f"Error: {input_file} is not a valid Office file" + except Exception as e: + return None, f"Error unpacking: {e}" + + +def _pretty_print_xml(xml_file: Path) -> None: + try: + content = xml_file.read_text(encoding="utf-8") + dom = defusedxml.minidom.parseString(content) + xml_file.write_bytes(dom.toprettyxml(indent=" ", encoding="utf-8")) + except Exception: + pass + + +def _escape_smart_quotes(xml_file: Path) -> None: + try: + content = xml_file.read_text(encoding="utf-8") + for char, entity in SMART_QUOTE_REPLACEMENTS.items(): + content = content.replace(char, entity) + xml_file.write_text(content, encoding="utf-8") + except Exception: + pass + + +if __name__ == "__main__": + parser = argparse.ArgumentParser( + description="Unpack an Office file (DOCX, PPTX, XLSX) for editing" + ) + parser.add_argument("input_file", help="Office file to unpack") + parser.add_argument("output_directory", help="Output directory") + parser.add_argument( + "--merge-runs", + type=lambda x: x.lower() == "true", + default=True, + metavar="true|false", + help="Merge adjacent runs with identical formatting (DOCX only, default: true)", + ) + parser.add_argument( + "--simplify-redlines", + type=lambda x: x.lower() == "true", + default=True, + metavar="true|false", + help="Merge adjacent tracked changes from same author (DOCX only, default: true)", + ) + args = parser.parse_args() + + _, message = unpack( + args.input_file, + args.output_directory, + merge_runs=args.merge_runs, + simplify_redlines=args.simplify_redlines, + ) + print(message) + + if "Error" in message: + sys.exit(1) diff --git a/mateclaw-server/src/main/resources/skills/docx/scripts/office/validate.py b/mateclaw-server/src/main/resources/skills/docx/scripts/office/validate.py new file mode 100755 index 00000000..03b01f6e --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/docx/scripts/office/validate.py @@ -0,0 +1,111 @@ +""" +Command line tool to validate Office document XML files against XSD schemas and tracked changes. + +Usage: + python validate.py [--original ] [--auto-repair] [--author NAME] + +The first argument can be either: +- An unpacked directory containing the Office document XML files +- A packed Office file (.docx/.pptx/.xlsx) which will be unpacked to a temp directory + +Auto-repair fixes: +- paraId/durableId values that exceed OOXML limits +- Missing xml:space="preserve" on w:t elements with whitespace +""" + +import argparse +import sys +import tempfile +import zipfile +from pathlib import Path + +from validators import DOCXSchemaValidator, PPTXSchemaValidator, RedliningValidator + + +def main(): + parser = argparse.ArgumentParser(description="Validate Office document XML files") + parser.add_argument( + "path", + help="Path to unpacked directory or packed Office file (.docx/.pptx/.xlsx)", + ) + parser.add_argument( + "--original", + required=False, + default=None, + help="Path to original file (.docx/.pptx/.xlsx). If omitted, all XSD errors are reported and redlining validation is skipped.", + ) + parser.add_argument( + "-v", + "--verbose", + action="store_true", + help="Enable verbose output", + ) + parser.add_argument( + "--auto-repair", + action="store_true", + help="Automatically repair common issues (hex IDs, whitespace preservation)", + ) + parser.add_argument( + "--author", + default="Claude", + help="Author name for redlining validation (default: Claude)", + ) + args = parser.parse_args() + + path = Path(args.path) + assert path.exists(), f"Error: {path} does not exist" + + original_file = None + if args.original: + original_file = Path(args.original) + assert original_file.is_file(), f"Error: {original_file} is not a file" + assert original_file.suffix.lower() in [".docx", ".pptx", ".xlsx"], ( + f"Error: {original_file} must be a .docx, .pptx, or .xlsx file" + ) + + file_extension = (original_file or path).suffix.lower() + assert file_extension in [".docx", ".pptx", ".xlsx"], ( + f"Error: Cannot determine file type from {path}. Use --original or provide a .docx/.pptx/.xlsx file." + ) + + if path.is_file() and path.suffix.lower() in [".docx", ".pptx", ".xlsx"]: + temp_dir = tempfile.mkdtemp() + with zipfile.ZipFile(path, "r") as zf: + zf.extractall(temp_dir) + unpacked_dir = Path(temp_dir) + else: + assert path.is_dir(), f"Error: {path} is not a directory or Office file" + unpacked_dir = path + + match file_extension: + case ".docx": + validators = [ + DOCXSchemaValidator(unpacked_dir, original_file, verbose=args.verbose), + ] + if original_file: + validators.append( + RedliningValidator(unpacked_dir, original_file, verbose=args.verbose, author=args.author) + ) + case ".pptx": + validators = [ + PPTXSchemaValidator(unpacked_dir, original_file, verbose=args.verbose), + ] + case _: + print(f"Error: Validation not supported for file type {file_extension}") + sys.exit(1) + + if args.auto_repair: + total_repairs = sum(v.repair() for v in validators) + if total_repairs: + print(f"Auto-repaired {total_repairs} issue(s)") + + success = all(v.validate() for v in validators) + + if success: + print("All validations PASSED!") + + sys.exit(0 if success else 1) + + +if __name__ == "__main__": + main() diff --git a/mateclaw-server/src/main/resources/skills/docx/scripts/office/validators/__init__.py b/mateclaw-server/src/main/resources/skills/docx/scripts/office/validators/__init__.py new file mode 100644 index 00000000..db092ece --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/docx/scripts/office/validators/__init__.py @@ -0,0 +1,15 @@ +""" +Validation modules for Word document processing. +""" + +from .base import BaseSchemaValidator +from .docx import DOCXSchemaValidator +from .pptx import PPTXSchemaValidator +from .redlining import RedliningValidator + +__all__ = [ + "BaseSchemaValidator", + "DOCXSchemaValidator", + "PPTXSchemaValidator", + "RedliningValidator", +] diff --git a/mateclaw-server/src/main/resources/skills/docx/scripts/office/validators/base.py b/mateclaw-server/src/main/resources/skills/docx/scripts/office/validators/base.py new file mode 100644 index 00000000..db4a06a2 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/docx/scripts/office/validators/base.py @@ -0,0 +1,847 @@ +""" +Base validator with common validation logic for document files. +""" + +import re +from pathlib import Path + +import defusedxml.minidom +import lxml.etree + + +class BaseSchemaValidator: + + IGNORED_VALIDATION_ERRORS = [ + "hyphenationZone", + "purl.org/dc/terms", + ] + + UNIQUE_ID_REQUIREMENTS = { + "comment": ("id", "file"), + "commentrangestart": ("id", "file"), + "commentrangeend": ("id", "file"), + "bookmarkstart": ("id", "file"), + "bookmarkend": ("id", "file"), + "sldid": ("id", "file"), + "sldmasterid": ("id", "global"), + "sldlayoutid": ("id", "global"), + "cm": ("authorid", "file"), + "sheet": ("sheetid", "file"), + "definedname": ("id", "file"), + "cxnsp": ("id", "file"), + "sp": ("id", "file"), + "pic": ("id", "file"), + "grpsp": ("id", "file"), + } + + EXCLUDED_ID_CONTAINERS = { + "sectionlst", + } + + ELEMENT_RELATIONSHIP_TYPES = {} + + SCHEMA_MAPPINGS = { + "word": "ISO-IEC29500-4_2016/wml.xsd", + "ppt": "ISO-IEC29500-4_2016/pml.xsd", + "xl": "ISO-IEC29500-4_2016/sml.xsd", + "[Content_Types].xml": "ecma/fouth-edition/opc-contentTypes.xsd", + "app.xml": "ISO-IEC29500-4_2016/shared-documentPropertiesExtended.xsd", + "core.xml": "ecma/fouth-edition/opc-coreProperties.xsd", + "custom.xml": "ISO-IEC29500-4_2016/shared-documentPropertiesCustom.xsd", + ".rels": "ecma/fouth-edition/opc-relationships.xsd", + "people.xml": "microsoft/wml-2012.xsd", + "commentsIds.xml": "microsoft/wml-cid-2016.xsd", + "commentsExtensible.xml": "microsoft/wml-cex-2018.xsd", + "commentsExtended.xml": "microsoft/wml-2012.xsd", + "chart": "ISO-IEC29500-4_2016/dml-chart.xsd", + "theme": "ISO-IEC29500-4_2016/dml-main.xsd", + "drawing": "ISO-IEC29500-4_2016/dml-main.xsd", + } + + MC_NAMESPACE = "http://schemas.openxmlformats.org/markup-compatibility/2006" + XML_NAMESPACE = "http://www.w3.org/XML/1998/namespace" + + PACKAGE_RELATIONSHIPS_NAMESPACE = ( + "http://schemas.openxmlformats.org/package/2006/relationships" + ) + OFFICE_RELATIONSHIPS_NAMESPACE = ( + "http://schemas.openxmlformats.org/officeDocument/2006/relationships" + ) + CONTENT_TYPES_NAMESPACE = ( + "http://schemas.openxmlformats.org/package/2006/content-types" + ) + + MAIN_CONTENT_FOLDERS = {"word", "ppt", "xl"} + + OOXML_NAMESPACES = { + "http://schemas.openxmlformats.org/officeDocument/2006/math", + "http://schemas.openxmlformats.org/officeDocument/2006/relationships", + "http://schemas.openxmlformats.org/schemaLibrary/2006/main", + "http://schemas.openxmlformats.org/drawingml/2006/main", + "http://schemas.openxmlformats.org/drawingml/2006/chart", + "http://schemas.openxmlformats.org/drawingml/2006/chartDrawing", + "http://schemas.openxmlformats.org/drawingml/2006/diagram", + "http://schemas.openxmlformats.org/drawingml/2006/picture", + "http://schemas.openxmlformats.org/drawingml/2006/spreadsheetDrawing", + "http://schemas.openxmlformats.org/drawingml/2006/wordprocessingDrawing", + "http://schemas.openxmlformats.org/wordprocessingml/2006/main", + "http://schemas.openxmlformats.org/presentationml/2006/main", + "http://schemas.openxmlformats.org/spreadsheetml/2006/main", + "http://schemas.openxmlformats.org/officeDocument/2006/sharedTypes", + "http://www.w3.org/XML/1998/namespace", + } + + def __init__(self, unpacked_dir, original_file=None, verbose=False): + self.unpacked_dir = Path(unpacked_dir).resolve() + self.original_file = Path(original_file) if original_file else None + self.verbose = verbose + + self.schemas_dir = Path(__file__).parent.parent / "schemas" + + patterns = ["*.xml", "*.rels"] + self.xml_files = [ + f for pattern in patterns for f in self.unpacked_dir.rglob(pattern) + ] + + if not self.xml_files: + print(f"Warning: No XML files found in {self.unpacked_dir}") + + def validate(self): + raise NotImplementedError("Subclasses must implement the validate method") + + def repair(self) -> int: + return self.repair_whitespace_preservation() + + def repair_whitespace_preservation(self) -> int: + repairs = 0 + + for xml_file in self.xml_files: + try: + content = xml_file.read_text(encoding="utf-8") + dom = defusedxml.minidom.parseString(content) + modified = False + + for elem in dom.getElementsByTagName("*"): + if elem.tagName.endswith(":t") and elem.firstChild: + text = elem.firstChild.nodeValue + if text and (text.startswith((' ', '\t')) or text.endswith((' ', '\t'))): + if elem.getAttribute("xml:space") != "preserve": + elem.setAttribute("xml:space", "preserve") + text_preview = repr(text[:30]) + "..." if len(text) > 30 else repr(text) + print(f" Repaired: {xml_file.name}: Added xml:space='preserve' to {elem.tagName}: {text_preview}") + repairs += 1 + modified = True + + if modified: + xml_file.write_bytes(dom.toxml(encoding="UTF-8")) + + except Exception: + pass + + return repairs + + def validate_xml(self): + errors = [] + + for xml_file in self.xml_files: + try: + lxml.etree.parse(str(xml_file)) + except lxml.etree.XMLSyntaxError as e: + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: " + f"Line {e.lineno}: {e.msg}" + ) + except Exception as e: + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: " + f"Unexpected error: {str(e)}" + ) + + if errors: + print(f"FAILED - Found {len(errors)} XML violations:") + for error in errors: + print(error) + return False + else: + if self.verbose: + print("PASSED - All XML files are well-formed") + return True + + def validate_namespaces(self): + errors = [] + + for xml_file in self.xml_files: + try: + root = lxml.etree.parse(str(xml_file)).getroot() + declared = set(root.nsmap.keys()) - {None} + + for attr_val in [ + v for k, v in root.attrib.items() if k.endswith("Ignorable") + ]: + undeclared = set(attr_val.split()) - declared + errors.extend( + f" {xml_file.relative_to(self.unpacked_dir)}: " + f"Namespace '{ns}' in Ignorable but not declared" + for ns in undeclared + ) + except lxml.etree.XMLSyntaxError: + continue + + if errors: + print(f"FAILED - {len(errors)} namespace issues:") + for error in errors: + print(error) + return False + if self.verbose: + print("PASSED - All namespace prefixes properly declared") + return True + + def validate_unique_ids(self): + errors = [] + global_ids = {} + + for xml_file in self.xml_files: + try: + root = lxml.etree.parse(str(xml_file)).getroot() + file_ids = {} + + mc_elements = root.xpath( + ".//mc:AlternateContent", namespaces={"mc": self.MC_NAMESPACE} + ) + for elem in mc_elements: + elem.getparent().remove(elem) + + for elem in root.iter(): + tag = ( + elem.tag.split("}")[-1].lower() + if "}" in elem.tag + else elem.tag.lower() + ) + + if tag in self.UNIQUE_ID_REQUIREMENTS: + in_excluded_container = any( + ancestor.tag.split("}")[-1].lower() in self.EXCLUDED_ID_CONTAINERS + for ancestor in elem.iterancestors() + ) + if in_excluded_container: + continue + + attr_name, scope = self.UNIQUE_ID_REQUIREMENTS[tag] + + id_value = None + for attr, value in elem.attrib.items(): + attr_local = ( + attr.split("}")[-1].lower() + if "}" in attr + else attr.lower() + ) + if attr_local == attr_name: + id_value = value + break + + if id_value is not None: + if scope == "global": + if id_value in global_ids: + prev_file, prev_line, prev_tag = global_ids[ + id_value + ] + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: " + f"Line {elem.sourceline}: Global ID '{id_value}' in <{tag}> " + f"already used in {prev_file} at line {prev_line} in <{prev_tag}>" + ) + else: + global_ids[id_value] = ( + xml_file.relative_to(self.unpacked_dir), + elem.sourceline, + tag, + ) + elif scope == "file": + key = (tag, attr_name) + if key not in file_ids: + file_ids[key] = {} + + if id_value in file_ids[key]: + prev_line = file_ids[key][id_value] + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: " + f"Line {elem.sourceline}: Duplicate {attr_name}='{id_value}' in <{tag}> " + f"(first occurrence at line {prev_line})" + ) + else: + file_ids[key][id_value] = elem.sourceline + + except (lxml.etree.XMLSyntaxError, Exception) as e: + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: Error: {e}" + ) + + if errors: + print(f"FAILED - Found {len(errors)} ID uniqueness violations:") + for error in errors: + print(error) + return False + else: + if self.verbose: + print("PASSED - All required IDs are unique") + return True + + def validate_file_references(self): + errors = [] + + rels_files = list(self.unpacked_dir.rglob("*.rels")) + + if not rels_files: + if self.verbose: + print("PASSED - No .rels files found") + return True + + all_files = [] + for file_path in self.unpacked_dir.rglob("*"): + if ( + file_path.is_file() + and file_path.name != "[Content_Types].xml" + and not file_path.name.endswith(".rels") + ): + all_files.append(file_path.resolve()) + + all_referenced_files = set() + + if self.verbose: + print( + f"Found {len(rels_files)} .rels files and {len(all_files)} target files" + ) + + for rels_file in rels_files: + try: + rels_root = lxml.etree.parse(str(rels_file)).getroot() + + rels_dir = rels_file.parent + + referenced_files = set() + broken_refs = [] + + for rel in rels_root.findall( + ".//ns:Relationship", + namespaces={"ns": self.PACKAGE_RELATIONSHIPS_NAMESPACE}, + ): + target = rel.get("Target") + if target and not target.startswith( + ("http", "mailto:") + ): + if target.startswith("/"): + target_path = self.unpacked_dir / target.lstrip("/") + elif rels_file.name == ".rels": + target_path = self.unpacked_dir / target + else: + base_dir = rels_dir.parent + target_path = base_dir / target + + try: + target_path = target_path.resolve() + if target_path.exists() and target_path.is_file(): + referenced_files.add(target_path) + all_referenced_files.add(target_path) + else: + broken_refs.append((target, rel.sourceline)) + except (OSError, ValueError): + broken_refs.append((target, rel.sourceline)) + + if broken_refs: + rel_path = rels_file.relative_to(self.unpacked_dir) + for broken_ref, line_num in broken_refs: + errors.append( + f" {rel_path}: Line {line_num}: Broken reference to {broken_ref}" + ) + + except Exception as e: + rel_path = rels_file.relative_to(self.unpacked_dir) + errors.append(f" Error parsing {rel_path}: {e}") + + unreferenced_files = set(all_files) - all_referenced_files + + if unreferenced_files: + for unref_file in sorted(unreferenced_files): + unref_rel_path = unref_file.relative_to(self.unpacked_dir) + errors.append(f" Unreferenced file: {unref_rel_path}") + + if errors: + print(f"FAILED - Found {len(errors)} relationship validation errors:") + for error in errors: + print(error) + print( + "CRITICAL: These errors will cause the document to appear corrupt. " + + "Broken references MUST be fixed, " + + "and unreferenced files MUST be referenced or removed." + ) + return False + else: + if self.verbose: + print( + "PASSED - All references are valid and all files are properly referenced" + ) + return True + + def validate_all_relationship_ids(self): + import lxml.etree + + errors = [] + + for xml_file in self.xml_files: + if xml_file.suffix == ".rels": + continue + + rels_dir = xml_file.parent / "_rels" + rels_file = rels_dir / f"{xml_file.name}.rels" + + if not rels_file.exists(): + continue + + try: + rels_root = lxml.etree.parse(str(rels_file)).getroot() + rid_to_type = {} + + for rel in rels_root.findall( + f".//{{{self.PACKAGE_RELATIONSHIPS_NAMESPACE}}}Relationship" + ): + rid = rel.get("Id") + rel_type = rel.get("Type", "") + if rid: + if rid in rid_to_type: + rels_rel_path = rels_file.relative_to(self.unpacked_dir) + errors.append( + f" {rels_rel_path}: Line {rel.sourceline}: " + f"Duplicate relationship ID '{rid}' (IDs must be unique)" + ) + type_name = ( + rel_type.split("/")[-1] if "/" in rel_type else rel_type + ) + rid_to_type[rid] = type_name + + xml_root = lxml.etree.parse(str(xml_file)).getroot() + + r_ns = self.OFFICE_RELATIONSHIPS_NAMESPACE + rid_attrs_to_check = ["id", "embed", "link"] + for elem in xml_root.iter(): + for attr_name in rid_attrs_to_check: + rid_attr = elem.get(f"{{{r_ns}}}{attr_name}") + if not rid_attr: + continue + xml_rel_path = xml_file.relative_to(self.unpacked_dir) + elem_name = ( + elem.tag.split("}")[-1] if "}" in elem.tag else elem.tag + ) + + if rid_attr not in rid_to_type: + errors.append( + f" {xml_rel_path}: Line {elem.sourceline}: " + f"<{elem_name}> r:{attr_name} references non-existent relationship '{rid_attr}' " + f"(valid IDs: {', '.join(sorted(rid_to_type.keys())[:5])}{'...' if len(rid_to_type) > 5 else ''})" + ) + elif attr_name == "id" and self.ELEMENT_RELATIONSHIP_TYPES: + expected_type = self._get_expected_relationship_type( + elem_name + ) + if expected_type: + actual_type = rid_to_type[rid_attr] + if expected_type not in actual_type.lower(): + errors.append( + f" {xml_rel_path}: Line {elem.sourceline}: " + f"<{elem_name}> references '{rid_attr}' which points to '{actual_type}' " + f"but should point to a '{expected_type}' relationship" + ) + + except Exception as e: + xml_rel_path = xml_file.relative_to(self.unpacked_dir) + errors.append(f" Error processing {xml_rel_path}: {e}") + + if errors: + print(f"FAILED - Found {len(errors)} relationship ID reference errors:") + for error in errors: + print(error) + print("\nThese ID mismatches will cause the document to appear corrupt!") + return False + else: + if self.verbose: + print("PASSED - All relationship ID references are valid") + return True + + def _get_expected_relationship_type(self, element_name): + elem_lower = element_name.lower() + + if elem_lower in self.ELEMENT_RELATIONSHIP_TYPES: + return self.ELEMENT_RELATIONSHIP_TYPES[elem_lower] + + if elem_lower.endswith("id") and len(elem_lower) > 2: + prefix = elem_lower[:-2] + if prefix.endswith("master"): + return prefix.lower() + elif prefix.endswith("layout"): + return prefix.lower() + else: + if prefix == "sld": + return "slide" + return prefix.lower() + + if elem_lower.endswith("reference") and len(elem_lower) > 9: + prefix = elem_lower[:-9] + return prefix.lower() + + return None + + def validate_content_types(self): + errors = [] + + content_types_file = self.unpacked_dir / "[Content_Types].xml" + if not content_types_file.exists(): + print("FAILED - [Content_Types].xml file not found") + return False + + try: + root = lxml.etree.parse(str(content_types_file)).getroot() + declared_parts = set() + declared_extensions = set() + + for override in root.findall( + f".//{{{self.CONTENT_TYPES_NAMESPACE}}}Override" + ): + part_name = override.get("PartName") + if part_name is not None: + declared_parts.add(part_name.lstrip("/")) + + for default in root.findall( + f".//{{{self.CONTENT_TYPES_NAMESPACE}}}Default" + ): + extension = default.get("Extension") + if extension is not None: + declared_extensions.add(extension.lower()) + + declarable_roots = { + "sld", + "sldLayout", + "sldMaster", + "presentation", + "document", + "workbook", + "worksheet", + "theme", + } + + media_extensions = { + "png": "image/png", + "jpg": "image/jpeg", + "jpeg": "image/jpeg", + "gif": "image/gif", + "bmp": "image/bmp", + "tiff": "image/tiff", + "wmf": "image/x-wmf", + "emf": "image/x-emf", + } + + all_files = list(self.unpacked_dir.rglob("*")) + all_files = [f for f in all_files if f.is_file()] + + for xml_file in self.xml_files: + path_str = str(xml_file.relative_to(self.unpacked_dir)).replace( + "\\", "/" + ) + + if any( + skip in path_str + for skip in [".rels", "[Content_Types]", "docProps/", "_rels/"] + ): + continue + + try: + root_tag = lxml.etree.parse(str(xml_file)).getroot().tag + root_name = root_tag.split("}")[-1] if "}" in root_tag else root_tag + + if root_name in declarable_roots and path_str not in declared_parts: + errors.append( + f" {path_str}: File with <{root_name}> root not declared in [Content_Types].xml" + ) + + except Exception: + continue + + for file_path in all_files: + if file_path.suffix.lower() in {".xml", ".rels"}: + continue + if file_path.name == "[Content_Types].xml": + continue + if "_rels" in file_path.parts or "docProps" in file_path.parts: + continue + + extension = file_path.suffix.lstrip(".").lower() + if extension and extension not in declared_extensions: + if extension in media_extensions: + relative_path = file_path.relative_to(self.unpacked_dir) + errors.append( + f' {relative_path}: File with extension \'{extension}\' not declared in [Content_Types].xml - should add: ' + ) + + except Exception as e: + errors.append(f" Error parsing [Content_Types].xml: {e}") + + if errors: + print(f"FAILED - Found {len(errors)} content type declaration errors:") + for error in errors: + print(error) + return False + else: + if self.verbose: + print( + "PASSED - All content files are properly declared in [Content_Types].xml" + ) + return True + + def validate_file_against_xsd(self, xml_file, verbose=False): + xml_file = Path(xml_file).resolve() + unpacked_dir = self.unpacked_dir.resolve() + + is_valid, current_errors = self._validate_single_file_xsd( + xml_file, unpacked_dir + ) + + if is_valid is None: + return None, set() + elif is_valid: + return True, set() + + original_errors = self._get_original_file_errors(xml_file) + + assert current_errors is not None + new_errors = current_errors - original_errors + + new_errors = { + e for e in new_errors + if not any(pattern in e for pattern in self.IGNORED_VALIDATION_ERRORS) + } + + if new_errors: + if verbose: + relative_path = xml_file.relative_to(unpacked_dir) + print(f"FAILED - {relative_path}: {len(new_errors)} new error(s)") + for error in list(new_errors)[:3]: + truncated = error[:250] + "..." if len(error) > 250 else error + print(f" - {truncated}") + return False, new_errors + else: + if verbose: + print( + f"PASSED - No new errors (original had {len(current_errors)} errors)" + ) + return True, set() + + def validate_against_xsd(self): + new_errors = [] + original_error_count = 0 + valid_count = 0 + skipped_count = 0 + + for xml_file in self.xml_files: + relative_path = str(xml_file.relative_to(self.unpacked_dir)) + is_valid, new_file_errors = self.validate_file_against_xsd( + xml_file, verbose=False + ) + + if is_valid is None: + skipped_count += 1 + continue + elif is_valid and not new_file_errors: + valid_count += 1 + continue + elif is_valid: + original_error_count += 1 + valid_count += 1 + continue + + new_errors.append(f" {relative_path}: {len(new_file_errors)} new error(s)") + for error in list(new_file_errors)[:3]: + new_errors.append( + f" - {error[:250]}..." if len(error) > 250 else f" - {error}" + ) + + if self.verbose: + print(f"Validated {len(self.xml_files)} files:") + print(f" - Valid: {valid_count}") + print(f" - Skipped (no schema): {skipped_count}") + if original_error_count: + print(f" - With original errors (ignored): {original_error_count}") + print( + f" - With NEW errors: {len(new_errors) > 0 and len([e for e in new_errors if not e.startswith(' ')]) or 0}" + ) + + if new_errors: + print("\nFAILED - Found NEW validation errors:") + for error in new_errors: + print(error) + return False + else: + if self.verbose: + print("\nPASSED - No new XSD validation errors introduced") + return True + + def _get_schema_path(self, xml_file): + if xml_file.name in self.SCHEMA_MAPPINGS: + return self.schemas_dir / self.SCHEMA_MAPPINGS[xml_file.name] + + if xml_file.suffix == ".rels": + return self.schemas_dir / self.SCHEMA_MAPPINGS[".rels"] + + if "charts/" in str(xml_file) and xml_file.name.startswith("chart"): + return self.schemas_dir / self.SCHEMA_MAPPINGS["chart"] + + if "theme/" in str(xml_file) and xml_file.name.startswith("theme"): + return self.schemas_dir / self.SCHEMA_MAPPINGS["theme"] + + if xml_file.parent.name in self.MAIN_CONTENT_FOLDERS: + return self.schemas_dir / self.SCHEMA_MAPPINGS[xml_file.parent.name] + + return None + + def _clean_ignorable_namespaces(self, xml_doc): + xml_string = lxml.etree.tostring(xml_doc, encoding="unicode") + xml_copy = lxml.etree.fromstring(xml_string) + + for elem in xml_copy.iter(): + attrs_to_remove = [] + + for attr in elem.attrib: + if "{" in attr: + ns = attr.split("}")[0][1:] + if ns not in self.OOXML_NAMESPACES: + attrs_to_remove.append(attr) + + for attr in attrs_to_remove: + del elem.attrib[attr] + + self._remove_ignorable_elements(xml_copy) + + return lxml.etree.ElementTree(xml_copy) + + def _remove_ignorable_elements(self, root): + elements_to_remove = [] + + for elem in list(root): + if not hasattr(elem, "tag") or callable(elem.tag): + continue + + tag_str = str(elem.tag) + if tag_str.startswith("{"): + ns = tag_str.split("}")[0][1:] + if ns not in self.OOXML_NAMESPACES: + elements_to_remove.append(elem) + continue + + self._remove_ignorable_elements(elem) + + for elem in elements_to_remove: + root.remove(elem) + + def _preprocess_for_mc_ignorable(self, xml_doc): + root = xml_doc.getroot() + + if f"{{{self.MC_NAMESPACE}}}Ignorable" in root.attrib: + del root.attrib[f"{{{self.MC_NAMESPACE}}}Ignorable"] + + return xml_doc + + def _validate_single_file_xsd(self, xml_file, base_path): + schema_path = self._get_schema_path(xml_file) + if not schema_path: + return None, None + + try: + with open(schema_path, "rb") as xsd_file: + parser = lxml.etree.XMLParser() + xsd_doc = lxml.etree.parse( + xsd_file, parser=parser, base_url=str(schema_path) + ) + schema = lxml.etree.XMLSchema(xsd_doc) + + with open(xml_file, "r") as f: + xml_doc = lxml.etree.parse(f) + + xml_doc, _ = self._remove_template_tags_from_text_nodes(xml_doc) + xml_doc = self._preprocess_for_mc_ignorable(xml_doc) + + relative_path = xml_file.relative_to(base_path) + if ( + relative_path.parts + and relative_path.parts[0] in self.MAIN_CONTENT_FOLDERS + ): + xml_doc = self._clean_ignorable_namespaces(xml_doc) + + if schema.validate(xml_doc): + return True, set() + else: + errors = set() + for error in schema.error_log: + errors.add(error.message) + return False, errors + + except Exception as e: + return False, {str(e)} + + def _get_original_file_errors(self, xml_file): + if self.original_file is None: + return set() + + import tempfile + import zipfile + + xml_file = Path(xml_file).resolve() + unpacked_dir = self.unpacked_dir.resolve() + relative_path = xml_file.relative_to(unpacked_dir) + + with tempfile.TemporaryDirectory() as temp_dir: + temp_path = Path(temp_dir) + + with zipfile.ZipFile(self.original_file, "r") as zip_ref: + zip_ref.extractall(temp_path) + + original_xml_file = temp_path / relative_path + + if not original_xml_file.exists(): + return set() + + is_valid, errors = self._validate_single_file_xsd( + original_xml_file, temp_path + ) + return errors if errors else set() + + def _remove_template_tags_from_text_nodes(self, xml_doc): + warnings = [] + template_pattern = re.compile(r"\{\{[^}]*\}\}") + + xml_string = lxml.etree.tostring(xml_doc, encoding="unicode") + xml_copy = lxml.etree.fromstring(xml_string) + + def process_text_content(text, content_type): + if not text: + return text + matches = list(template_pattern.finditer(text)) + if matches: + for match in matches: + warnings.append( + f"Found template tag in {content_type}: {match.group()}" + ) + return template_pattern.sub("", text) + return text + + for elem in xml_copy.iter(): + if not hasattr(elem, "tag") or callable(elem.tag): + continue + tag_str = str(elem.tag) + if tag_str.endswith("}t") or tag_str == "t": + continue + + elem.text = process_text_content(elem.text, "text content") + elem.tail = process_text_content(elem.tail, "tail content") + + return lxml.etree.ElementTree(xml_copy), warnings + + +if __name__ == "__main__": + raise RuntimeError("This module should not be run directly.") diff --git a/mateclaw-server/src/main/resources/skills/docx/scripts/office/validators/docx.py b/mateclaw-server/src/main/resources/skills/docx/scripts/office/validators/docx.py new file mode 100644 index 00000000..0a0b0bfd --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/docx/scripts/office/validators/docx.py @@ -0,0 +1,447 @@ +""" +Validator for Word document XML files against XSD schemas. +""" + +import os +import random +import re +import tempfile +import zipfile + +import defusedxml.minidom +import lxml.etree + +from .base import BaseSchemaValidator + + +class DOCXSchemaValidator(BaseSchemaValidator): + + WORD_2006_NAMESPACE = "http://schemas.openxmlformats.org/wordprocessingml/2006/main" + W14_NAMESPACE = "http://schemas.microsoft.com/office/word/2010/wordml" + W16CID_NAMESPACE = "http://schemas.microsoft.com/office/word/2016/wordml/cid" + + ELEMENT_RELATIONSHIP_TYPES = {} + + def validate(self): + if not self.validate_xml(): + return False + + all_valid = True + if not self.validate_namespaces(): + all_valid = False + + if not self.validate_unique_ids(): + all_valid = False + + if not self.validate_file_references(): + all_valid = False + + if not self.validate_content_types(): + all_valid = False + + if not self.validate_against_xsd(): + all_valid = False + + if not self.validate_whitespace_preservation(): + all_valid = False + + if not self.validate_deletions(): + all_valid = False + + if not self.validate_insertions(): + all_valid = False + + if not self.validate_all_relationship_ids(): + all_valid = False + + if not self.validate_id_constraints(): + all_valid = False + + if not self.validate_comment_markers(): + all_valid = False + + self.compare_paragraph_counts() + + return all_valid + + def validate_whitespace_preservation(self): + errors = [] + + for xml_file in self.xml_files: + if xml_file.name != "document.xml": + continue + + try: + root = lxml.etree.parse(str(xml_file)).getroot() + + for elem in root.iter(f"{{{self.WORD_2006_NAMESPACE}}}t"): + if elem.text: + text = elem.text + if re.search(r"^[ \t\n\r]", text) or re.search( + r"[ \t\n\r]$", text + ): + xml_space_attr = f"{{{self.XML_NAMESPACE}}}space" + if ( + xml_space_attr not in elem.attrib + or elem.attrib[xml_space_attr] != "preserve" + ): + text_preview = ( + repr(text)[:50] + "..." + if len(repr(text)) > 50 + else repr(text) + ) + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: " + f"Line {elem.sourceline}: w:t element with whitespace missing xml:space='preserve': {text_preview}" + ) + + except (lxml.etree.XMLSyntaxError, Exception) as e: + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: Error: {e}" + ) + + if errors: + print(f"FAILED - Found {len(errors)} whitespace preservation violations:") + for error in errors: + print(error) + return False + else: + if self.verbose: + print("PASSED - All whitespace is properly preserved") + return True + + def validate_deletions(self): + errors = [] + + for xml_file in self.xml_files: + if xml_file.name != "document.xml": + continue + + try: + root = lxml.etree.parse(str(xml_file)).getroot() + namespaces = {"w": self.WORD_2006_NAMESPACE} + + for t_elem in root.xpath(".//w:del//w:t", namespaces=namespaces): + if t_elem.text: + text_preview = ( + repr(t_elem.text)[:50] + "..." + if len(repr(t_elem.text)) > 50 + else repr(t_elem.text) + ) + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: " + f"Line {t_elem.sourceline}: found within : {text_preview}" + ) + + for instr_elem in root.xpath( + ".//w:del//w:instrText", namespaces=namespaces + ): + text_preview = ( + repr(instr_elem.text or "")[:50] + "..." + if len(repr(instr_elem.text or "")) > 50 + else repr(instr_elem.text or "") + ) + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: " + f"Line {instr_elem.sourceline}: found within (use ): {text_preview}" + ) + + except (lxml.etree.XMLSyntaxError, Exception) as e: + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: Error: {e}" + ) + + if errors: + print(f"FAILED - Found {len(errors)} deletion validation violations:") + for error in errors: + print(error) + return False + else: + if self.verbose: + print("PASSED - No w:t elements found within w:del elements") + return True + + def count_paragraphs_in_unpacked(self): + count = 0 + + for xml_file in self.xml_files: + if xml_file.name != "document.xml": + continue + + try: + root = lxml.etree.parse(str(xml_file)).getroot() + paragraphs = root.findall(f".//{{{self.WORD_2006_NAMESPACE}}}p") + count = len(paragraphs) + except Exception as e: + print(f"Error counting paragraphs in unpacked document: {e}") + + return count + + def count_paragraphs_in_original(self): + original = self.original_file + if original is None: + return 0 + + count = 0 + + try: + with tempfile.TemporaryDirectory() as temp_dir: + with zipfile.ZipFile(original, "r") as zip_ref: + zip_ref.extractall(temp_dir) + + doc_xml_path = os.path.join(temp_dir, "word", "document.xml") + root = lxml.etree.parse(doc_xml_path).getroot() + + paragraphs = root.findall(f".//{{{self.WORD_2006_NAMESPACE}}}p") + count = len(paragraphs) + + except Exception as e: + print(f"Error counting paragraphs in original document: {e}") + + return count + + def validate_insertions(self): + errors = [] + + for xml_file in self.xml_files: + if xml_file.name != "document.xml": + continue + + try: + root = lxml.etree.parse(str(xml_file)).getroot() + namespaces = {"w": self.WORD_2006_NAMESPACE} + + invalid_elements = root.xpath( + ".//w:ins//w:delText[not(ancestor::w:del)]", namespaces=namespaces + ) + + for elem in invalid_elements: + text_preview = ( + repr(elem.text or "")[:50] + "..." + if len(repr(elem.text or "")) > 50 + else repr(elem.text or "") + ) + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: " + f"Line {elem.sourceline}: within : {text_preview}" + ) + + except (lxml.etree.XMLSyntaxError, Exception) as e: + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: Error: {e}" + ) + + if errors: + print(f"FAILED - Found {len(errors)} insertion validation violations:") + for error in errors: + print(error) + return False + else: + if self.verbose: + print("PASSED - No w:delText elements within w:ins elements") + return True + + def compare_paragraph_counts(self): + original_count = self.count_paragraphs_in_original() + new_count = self.count_paragraphs_in_unpacked() + + diff = new_count - original_count + diff_str = f"+{diff}" if diff > 0 else str(diff) + print(f"\nParagraphs: {original_count} → {new_count} ({diff_str})") + + def _parse_id_value(self, val: str, base: int = 16) -> int: + return int(val, base) + + def validate_id_constraints(self): + errors = [] + para_id_attr = f"{{{self.W14_NAMESPACE}}}paraId" + durable_id_attr = f"{{{self.W16CID_NAMESPACE}}}durableId" + + for xml_file in self.xml_files: + try: + for elem in lxml.etree.parse(str(xml_file)).iter(): + if val := elem.get(para_id_attr): + if self._parse_id_value(val, base=16) >= 0x80000000: + errors.append( + f" {xml_file.name}:{elem.sourceline}: paraId={val} >= 0x80000000" + ) + + if val := elem.get(durable_id_attr): + if xml_file.name == "numbering.xml": + try: + if self._parse_id_value(val, base=10) >= 0x7FFFFFFF: + errors.append( + f" {xml_file.name}:{elem.sourceline}: " + f"durableId={val} >= 0x7FFFFFFF" + ) + except ValueError: + errors.append( + f" {xml_file.name}:{elem.sourceline}: " + f"durableId={val} must be decimal in numbering.xml" + ) + else: + if self._parse_id_value(val, base=16) >= 0x7FFFFFFF: + errors.append( + f" {xml_file.name}:{elem.sourceline}: " + f"durableId={val} >= 0x7FFFFFFF" + ) + except Exception: + pass + + if errors: + print(f"FAILED - {len(errors)} ID constraint violations:") + for e in errors: + print(e) + elif self.verbose: + print("PASSED - All paraId/durableId values within constraints") + return not errors + + def validate_comment_markers(self): + errors = [] + + document_xml = None + comments_xml = None + for xml_file in self.xml_files: + if xml_file.name == "document.xml" and "word" in str(xml_file): + document_xml = xml_file + elif xml_file.name == "comments.xml": + comments_xml = xml_file + + if not document_xml: + if self.verbose: + print("PASSED - No document.xml found (skipping comment validation)") + return True + + try: + doc_root = lxml.etree.parse(str(document_xml)).getroot() + namespaces = {"w": self.WORD_2006_NAMESPACE} + + range_starts = { + elem.get(f"{{{self.WORD_2006_NAMESPACE}}}id") + for elem in doc_root.xpath( + ".//w:commentRangeStart", namespaces=namespaces + ) + } + range_ends = { + elem.get(f"{{{self.WORD_2006_NAMESPACE}}}id") + for elem in doc_root.xpath( + ".//w:commentRangeEnd", namespaces=namespaces + ) + } + references = { + elem.get(f"{{{self.WORD_2006_NAMESPACE}}}id") + for elem in doc_root.xpath( + ".//w:commentReference", namespaces=namespaces + ) + } + + orphaned_ends = range_ends - range_starts + for comment_id in sorted( + orphaned_ends, key=lambda x: int(x) if x and x.isdigit() else 0 + ): + errors.append( + f' document.xml: commentRangeEnd id="{comment_id}" has no matching commentRangeStart' + ) + + orphaned_starts = range_starts - range_ends + for comment_id in sorted( + orphaned_starts, key=lambda x: int(x) if x and x.isdigit() else 0 + ): + errors.append( + f' document.xml: commentRangeStart id="{comment_id}" has no matching commentRangeEnd' + ) + + comment_ids = set() + if comments_xml and comments_xml.exists(): + comments_root = lxml.etree.parse(str(comments_xml)).getroot() + comment_ids = { + elem.get(f"{{{self.WORD_2006_NAMESPACE}}}id") + for elem in comments_root.xpath( + ".//w:comment", namespaces=namespaces + ) + } + + marker_ids = range_starts | range_ends | references + invalid_refs = marker_ids - comment_ids + for comment_id in sorted( + invalid_refs, key=lambda x: int(x) if x and x.isdigit() else 0 + ): + if comment_id: + errors.append( + f' document.xml: marker id="{comment_id}" references non-existent comment' + ) + + except (lxml.etree.XMLSyntaxError, Exception) as e: + errors.append(f" Error parsing XML: {e}") + + if errors: + print(f"FAILED - {len(errors)} comment marker violations:") + for error in errors: + print(error) + return False + else: + if self.verbose: + print("PASSED - All comment markers properly paired") + return True + + def repair(self) -> int: + repairs = super().repair() + repairs += self.repair_durableId() + return repairs + + def repair_durableId(self) -> int: + repairs = 0 + + for xml_file in self.xml_files: + try: + content = xml_file.read_text(encoding="utf-8") + dom = defusedxml.minidom.parseString(content) + modified = False + + for elem in dom.getElementsByTagName("*"): + if not elem.hasAttribute("w16cid:durableId"): + continue + + durable_id = elem.getAttribute("w16cid:durableId") + needs_repair = False + + if xml_file.name == "numbering.xml": + try: + needs_repair = ( + self._parse_id_value(durable_id, base=10) >= 0x7FFFFFFF + ) + except ValueError: + needs_repair = True + else: + try: + needs_repair = ( + self._parse_id_value(durable_id, base=16) >= 0x7FFFFFFF + ) + except ValueError: + needs_repair = True + + if needs_repair: + value = random.randint(1, 0x7FFFFFFE) + if xml_file.name == "numbering.xml": + new_id = str(value) + else: + new_id = f"{value:08X}" + + elem.setAttribute("w16cid:durableId", new_id) + print( + f" Repaired: {xml_file.name}: durableId {durable_id} → {new_id}" + ) + repairs += 1 + modified = True + + if modified: + xml_file.write_bytes(dom.toxml(encoding="UTF-8")) + + except Exception: + pass + + return repairs + + +if __name__ == "__main__": + raise RuntimeError("This module should not be run directly.") diff --git a/mateclaw-server/src/main/resources/skills/docx/scripts/office/validators/pptx.py b/mateclaw-server/src/main/resources/skills/docx/scripts/office/validators/pptx.py new file mode 100644 index 00000000..09842aa9 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/docx/scripts/office/validators/pptx.py @@ -0,0 +1,275 @@ +""" +Validator for PowerPoint presentation XML files against XSD schemas. +""" + +import re + +from .base import BaseSchemaValidator + + +class PPTXSchemaValidator(BaseSchemaValidator): + + PRESENTATIONML_NAMESPACE = ( + "http://schemas.openxmlformats.org/presentationml/2006/main" + ) + + ELEMENT_RELATIONSHIP_TYPES = { + "sldid": "slide", + "sldmasterid": "slidemaster", + "notesmasterid": "notesmaster", + "sldlayoutid": "slidelayout", + "themeid": "theme", + "tablestyleid": "tablestyles", + } + + def validate(self): + if not self.validate_xml(): + return False + + all_valid = True + if not self.validate_namespaces(): + all_valid = False + + if not self.validate_unique_ids(): + all_valid = False + + if not self.validate_uuid_ids(): + all_valid = False + + if not self.validate_file_references(): + all_valid = False + + if not self.validate_slide_layout_ids(): + all_valid = False + + if not self.validate_content_types(): + all_valid = False + + if not self.validate_against_xsd(): + all_valid = False + + if not self.validate_notes_slide_references(): + all_valid = False + + if not self.validate_all_relationship_ids(): + all_valid = False + + if not self.validate_no_duplicate_slide_layouts(): + all_valid = False + + return all_valid + + def validate_uuid_ids(self): + import lxml.etree + + errors = [] + uuid_pattern = re.compile( + r"^[\{\(]?[0-9A-Fa-f]{8}-?[0-9A-Fa-f]{4}-?[0-9A-Fa-f]{4}-?[0-9A-Fa-f]{4}-?[0-9A-Fa-f]{12}[\}\)]?$" + ) + + for xml_file in self.xml_files: + try: + root = lxml.etree.parse(str(xml_file)).getroot() + + for elem in root.iter(): + for attr, value in elem.attrib.items(): + attr_name = attr.split("}")[-1].lower() + if attr_name == "id" or attr_name.endswith("id"): + if self._looks_like_uuid(value): + if not uuid_pattern.match(value): + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: " + f"Line {elem.sourceline}: ID '{value}' appears to be a UUID but contains invalid hex characters" + ) + + except (lxml.etree.XMLSyntaxError, Exception) as e: + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: Error: {e}" + ) + + if errors: + print(f"FAILED - Found {len(errors)} UUID ID validation errors:") + for error in errors: + print(error) + return False + else: + if self.verbose: + print("PASSED - All UUID-like IDs contain valid hex values") + return True + + def _looks_like_uuid(self, value): + clean_value = value.strip("{}()").replace("-", "") + return len(clean_value) == 32 and all(c.isalnum() for c in clean_value) + + def validate_slide_layout_ids(self): + import lxml.etree + + errors = [] + + slide_masters = list(self.unpacked_dir.glob("ppt/slideMasters/*.xml")) + + if not slide_masters: + if self.verbose: + print("PASSED - No slide masters found") + return True + + for slide_master in slide_masters: + try: + root = lxml.etree.parse(str(slide_master)).getroot() + + rels_file = slide_master.parent / "_rels" / f"{slide_master.name}.rels" + + if not rels_file.exists(): + errors.append( + f" {slide_master.relative_to(self.unpacked_dir)}: " + f"Missing relationships file: {rels_file.relative_to(self.unpacked_dir)}" + ) + continue + + rels_root = lxml.etree.parse(str(rels_file)).getroot() + + valid_layout_rids = set() + for rel in rels_root.findall( + f".//{{{self.PACKAGE_RELATIONSHIPS_NAMESPACE}}}Relationship" + ): + rel_type = rel.get("Type", "") + if "slideLayout" in rel_type: + valid_layout_rids.add(rel.get("Id")) + + for sld_layout_id in root.findall( + f".//{{{self.PRESENTATIONML_NAMESPACE}}}sldLayoutId" + ): + r_id = sld_layout_id.get( + f"{{{self.OFFICE_RELATIONSHIPS_NAMESPACE}}}id" + ) + layout_id = sld_layout_id.get("id") + + if r_id and r_id not in valid_layout_rids: + errors.append( + f" {slide_master.relative_to(self.unpacked_dir)}: " + f"Line {sld_layout_id.sourceline}: sldLayoutId with id='{layout_id}' " + f"references r:id='{r_id}' which is not found in slide layout relationships" + ) + + except (lxml.etree.XMLSyntaxError, Exception) as e: + errors.append( + f" {slide_master.relative_to(self.unpacked_dir)}: Error: {e}" + ) + + if errors: + print(f"FAILED - Found {len(errors)} slide layout ID validation errors:") + for error in errors: + print(error) + print( + "Remove invalid references or add missing slide layouts to the relationships file." + ) + return False + else: + if self.verbose: + print("PASSED - All slide layout IDs reference valid slide layouts") + return True + + def validate_no_duplicate_slide_layouts(self): + import lxml.etree + + errors = [] + slide_rels_files = list(self.unpacked_dir.glob("ppt/slides/_rels/*.xml.rels")) + + for rels_file in slide_rels_files: + try: + root = lxml.etree.parse(str(rels_file)).getroot() + + layout_rels = [ + rel + for rel in root.findall( + f".//{{{self.PACKAGE_RELATIONSHIPS_NAMESPACE}}}Relationship" + ) + if "slideLayout" in rel.get("Type", "") + ] + + if len(layout_rels) > 1: + errors.append( + f" {rels_file.relative_to(self.unpacked_dir)}: has {len(layout_rels)} slideLayout references" + ) + + except Exception as e: + errors.append( + f" {rels_file.relative_to(self.unpacked_dir)}: Error: {e}" + ) + + if errors: + print("FAILED - Found slides with duplicate slideLayout references:") + for error in errors: + print(error) + return False + else: + if self.verbose: + print("PASSED - All slides have exactly one slideLayout reference") + return True + + def validate_notes_slide_references(self): + import lxml.etree + + errors = [] + notes_slide_references = {} + + slide_rels_files = list(self.unpacked_dir.glob("ppt/slides/_rels/*.xml.rels")) + + if not slide_rels_files: + if self.verbose: + print("PASSED - No slide relationship files found") + return True + + for rels_file in slide_rels_files: + try: + root = lxml.etree.parse(str(rels_file)).getroot() + + for rel in root.findall( + f".//{{{self.PACKAGE_RELATIONSHIPS_NAMESPACE}}}Relationship" + ): + rel_type = rel.get("Type", "") + if "notesSlide" in rel_type: + target = rel.get("Target", "") + if target: + normalized_target = target.replace("../", "") + + slide_name = rels_file.stem.replace( + ".xml", "" + ) + + if normalized_target not in notes_slide_references: + notes_slide_references[normalized_target] = [] + notes_slide_references[normalized_target].append( + (slide_name, rels_file) + ) + + except (lxml.etree.XMLSyntaxError, Exception) as e: + errors.append( + f" {rels_file.relative_to(self.unpacked_dir)}: Error: {e}" + ) + + for target, references in notes_slide_references.items(): + if len(references) > 1: + slide_names = [ref[0] for ref in references] + errors.append( + f" Notes slide '{target}' is referenced by multiple slides: {', '.join(slide_names)}" + ) + for slide_name, rels_file in references: + errors.append(f" - {rels_file.relative_to(self.unpacked_dir)}") + + if errors: + print( + f"FAILED - Found {len([e for e in errors if not e.startswith(' ')])} notes slide reference validation errors:" + ) + for error in errors: + print(error) + print("Each slide may optionally have its own slide file.") + return False + else: + if self.verbose: + print("PASSED - All notes slide references are unique") + return True + + +if __name__ == "__main__": + raise RuntimeError("This module should not be run directly.") diff --git a/mateclaw-server/src/main/resources/skills/docx/scripts/office/validators/redlining.py b/mateclaw-server/src/main/resources/skills/docx/scripts/office/validators/redlining.py new file mode 100644 index 00000000..71c81b6b --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/docx/scripts/office/validators/redlining.py @@ -0,0 +1,247 @@ +""" +Validator for tracked changes in Word documents. +""" + +import subprocess +import tempfile +import zipfile +from pathlib import Path + + +class RedliningValidator: + + def __init__(self, unpacked_dir, original_docx, verbose=False, author="Claude"): + self.unpacked_dir = Path(unpacked_dir) + self.original_docx = Path(original_docx) + self.verbose = verbose + self.author = author + self.namespaces = { + "w": "http://schemas.openxmlformats.org/wordprocessingml/2006/main" + } + + def repair(self) -> int: + return 0 + + def validate(self): + modified_file = self.unpacked_dir / "word" / "document.xml" + if not modified_file.exists(): + print(f"FAILED - Modified document.xml not found at {modified_file}") + return False + + try: + import xml.etree.ElementTree as ET + + tree = ET.parse(modified_file) + root = tree.getroot() + + del_elements = root.findall(".//w:del", self.namespaces) + ins_elements = root.findall(".//w:ins", self.namespaces) + + author_del_elements = [ + elem + for elem in del_elements + if elem.get(f"{{{self.namespaces['w']}}}author") == self.author + ] + author_ins_elements = [ + elem + for elem in ins_elements + if elem.get(f"{{{self.namespaces['w']}}}author") == self.author + ] + + if not author_del_elements and not author_ins_elements: + if self.verbose: + print(f"PASSED - No tracked changes by {self.author} found.") + return True + + except Exception: + pass + + with tempfile.TemporaryDirectory() as temp_dir: + temp_path = Path(temp_dir) + + try: + with zipfile.ZipFile(self.original_docx, "r") as zip_ref: + zip_ref.extractall(temp_path) + except Exception as e: + print(f"FAILED - Error unpacking original docx: {e}") + return False + + original_file = temp_path / "word" / "document.xml" + if not original_file.exists(): + print( + f"FAILED - Original document.xml not found in {self.original_docx}" + ) + return False + + try: + import xml.etree.ElementTree as ET + + modified_tree = ET.parse(modified_file) + modified_root = modified_tree.getroot() + original_tree = ET.parse(original_file) + original_root = original_tree.getroot() + except ET.ParseError as e: + print(f"FAILED - Error parsing XML files: {e}") + return False + + self._remove_author_tracked_changes(original_root) + self._remove_author_tracked_changes(modified_root) + + modified_text = self._extract_text_content(modified_root) + original_text = self._extract_text_content(original_root) + + if modified_text != original_text: + error_message = self._generate_detailed_diff( + original_text, modified_text + ) + print(error_message) + return False + + if self.verbose: + print(f"PASSED - All changes by {self.author} are properly tracked") + return True + + def _generate_detailed_diff(self, original_text, modified_text): + error_parts = [ + f"FAILED - Document text doesn't match after removing {self.author}'s tracked changes", + "", + "Likely causes:", + " 1. Modified text inside another author's or tags", + " 2. Made edits without proper tracked changes", + " 3. Didn't nest inside when deleting another's insertion", + "", + "For pre-redlined documents, use correct patterns:", + " - To reject another's INSERTION: Nest inside their ", + " - To restore another's DELETION: Add new AFTER their ", + "", + ] + + git_diff = self._get_git_word_diff(original_text, modified_text) + if git_diff: + error_parts.extend(["Differences:", "============", git_diff]) + else: + error_parts.append("Unable to generate word diff (git not available)") + + return "\n".join(error_parts) + + def _get_git_word_diff(self, original_text, modified_text): + try: + with tempfile.TemporaryDirectory() as temp_dir: + temp_path = Path(temp_dir) + + original_file = temp_path / "original.txt" + modified_file = temp_path / "modified.txt" + + original_file.write_text(original_text, encoding="utf-8") + modified_file.write_text(modified_text, encoding="utf-8") + + result = subprocess.run( + [ + "git", + "diff", + "--word-diff=plain", + "--word-diff-regex=.", + "-U0", + "--no-index", + str(original_file), + str(modified_file), + ], + capture_output=True, + text=True, + ) + + if result.stdout.strip(): + lines = result.stdout.split("\n") + content_lines = [] + in_content = False + for line in lines: + if line.startswith("@@"): + in_content = True + continue + if in_content and line.strip(): + content_lines.append(line) + + if content_lines: + return "\n".join(content_lines) + + result = subprocess.run( + [ + "git", + "diff", + "--word-diff=plain", + "-U0", + "--no-index", + str(original_file), + str(modified_file), + ], + capture_output=True, + text=True, + ) + + if result.stdout.strip(): + lines = result.stdout.split("\n") + content_lines = [] + in_content = False + for line in lines: + if line.startswith("@@"): + in_content = True + continue + if in_content and line.strip(): + content_lines.append(line) + return "\n".join(content_lines) + + except (subprocess.CalledProcessError, FileNotFoundError, Exception): + pass + + return None + + def _remove_author_tracked_changes(self, root): + ins_tag = f"{{{self.namespaces['w']}}}ins" + del_tag = f"{{{self.namespaces['w']}}}del" + author_attr = f"{{{self.namespaces['w']}}}author" + + for parent in root.iter(): + to_remove = [] + for child in parent: + if child.tag == ins_tag and child.get(author_attr) == self.author: + to_remove.append(child) + for elem in to_remove: + parent.remove(elem) + + deltext_tag = f"{{{self.namespaces['w']}}}delText" + t_tag = f"{{{self.namespaces['w']}}}t" + + for parent in root.iter(): + to_process = [] + for child in parent: + if child.tag == del_tag and child.get(author_attr) == self.author: + to_process.append((child, list(parent).index(child))) + + for del_elem, del_index in reversed(to_process): + for elem in del_elem.iter(): + if elem.tag == deltext_tag: + elem.tag = t_tag + + for child in reversed(list(del_elem)): + parent.insert(del_index, child) + parent.remove(del_elem) + + def _extract_text_content(self, root): + p_tag = f"{{{self.namespaces['w']}}}p" + t_tag = f"{{{self.namespaces['w']}}}t" + + paragraphs = [] + for p_elem in root.findall(f".//{p_tag}"): + text_parts = [] + for t_elem in p_elem.findall(f".//{t_tag}"): + if t_elem.text: + text_parts.append(t_elem.text) + paragraph_text = "".join(text_parts) + if paragraph_text: + paragraphs.append(paragraph_text) + + return "\n".join(paragraphs) + + +if __name__ == "__main__": + raise RuntimeError("This module should not be run directly.") diff --git a/mateclaw-server/src/main/resources/skills/docx/scripts/templates/comments.xml b/mateclaw-server/src/main/resources/skills/docx/scripts/templates/comments.xml new file mode 100644 index 00000000..cd01a7d7 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/docx/scripts/templates/comments.xml @@ -0,0 +1,3 @@ + + + diff --git a/mateclaw-server/src/main/resources/skills/docx/scripts/templates/commentsExtended.xml b/mateclaw-server/src/main/resources/skills/docx/scripts/templates/commentsExtended.xml new file mode 100644 index 00000000..411003cc --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/docx/scripts/templates/commentsExtended.xml @@ -0,0 +1,3 @@ + + + diff --git a/mateclaw-server/src/main/resources/skills/docx/scripts/templates/commentsExtensible.xml b/mateclaw-server/src/main/resources/skills/docx/scripts/templates/commentsExtensible.xml new file mode 100644 index 00000000..f5572d71 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/docx/scripts/templates/commentsExtensible.xml @@ -0,0 +1,3 @@ + + + diff --git a/mateclaw-server/src/main/resources/skills/docx/scripts/templates/commentsIds.xml b/mateclaw-server/src/main/resources/skills/docx/scripts/templates/commentsIds.xml new file mode 100644 index 00000000..32f1629f --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/docx/scripts/templates/commentsIds.xml @@ -0,0 +1,3 @@ + + + diff --git a/mateclaw-server/src/main/resources/skills/docx/scripts/templates/people.xml b/mateclaw-server/src/main/resources/skills/docx/scripts/templates/people.xml new file mode 100644 index 00000000..3803d2de --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/docx/scripts/templates/people.xml @@ -0,0 +1,3 @@ + + + diff --git a/mateclaw-server/src/main/resources/skills/p5js/scripts/export-frames.js b/mateclaw-server/src/main/resources/skills/p5js/scripts/export-frames.js new file mode 100755 index 00000000..0e4078da --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/p5js/scripts/export-frames.js @@ -0,0 +1,179 @@ +#!/usr/bin/env node +/** + * p5.js Skill — Headless Frame Export + * + * Captures frames from a p5.js sketch using Puppeteer (headless Chrome). + * Uses noLoop() + redraw() for DETERMINISTIC frame-by-frame control. + * + * IMPORTANT: Your sketch must call noLoop() in setup() and set + * window._p5Ready = true when initialized. This script calls redraw() + * for each frame capture, ensuring exact 1:1 correspondence between + * frameCount and captured frames. + * + * If the sketch does NOT set window._p5Ready, the script falls back to + * a timed capture mode (less precise, may drop/duplicate frames). + * + * Usage: + * node export-frames.js sketch.html [options] + * + * Options: + * --output Output directory (default: ./frames) + * --width Canvas width (default: 1920) + * --height Canvas height (default: 1080) + * --frames Number of frames to capture (default: 1) + * --fps Target FPS for timed fallback mode (default: 30) + * --wait Wait before first capture (default: 2000) + * --selector Canvas CSS selector (default: canvas) + * + * Examples: + * node export-frames.js sketch.html --frames 1 # single PNG + * node export-frames.js sketch.html --frames 300 --fps 30 # 10s at 30fps + * node export-frames.js sketch.html --width 3840 --height 2160 # 4K still + * + * Sketch template for deterministic capture: + * function setup() { + * createCanvas(1920, 1080); + * pixelDensity(1); + * noLoop(); // REQUIRED for deterministic capture + * window._p5Ready = true; // REQUIRED to signal readiness + * } + * function draw() { ... } + */ + +const puppeteer = require('puppeteer'); +const path = require('path'); +const fs = require('fs'); + +// Parse CLI arguments +function parseArgs() { + const args = process.argv.slice(2); + const opts = { + input: null, + output: './frames', + width: 1920, + height: 1080, + frames: 1, + fps: 30, + wait: 2000, + selector: 'canvas', + }; + + for (let i = 0; i < args.length; i++) { + if (args[i].startsWith('--')) { + const key = args[i].slice(2); + const val = args[i + 1]; + if (key in opts && val !== undefined) { + opts[key] = isNaN(Number(val)) ? val : Number(val); + i++; + } + } else if (!opts.input) { + opts.input = args[i]; + } + } + + if (!opts.input) { + console.error('Usage: node export-frames.js [options]'); + process.exit(1); + } + + return opts; +} + +async function main() { + const opts = parseArgs(); + const inputPath = path.resolve(opts.input); + + if (!fs.existsSync(inputPath)) { + console.error(`File not found: ${inputPath}`); + process.exit(1); + } + + // Create output directory + fs.mkdirSync(opts.output, { recursive: true }); + + console.log(`Capturing ${opts.frames} frame(s) from ${opts.input}`); + console.log(`Resolution: ${opts.width}x${opts.height}`); + console.log(`Output: ${opts.output}/`); + + const browser = await puppeteer.launch({ + headless: 'new', + args: [ + '--no-sandbox', + '--disable-setuid-sandbox', + '--disable-gpu', + '--disable-dev-shm-usage', + '--disable-web-security', + '--allow-file-access-from-files', + ], + }); + + const page = await browser.newPage(); + + await page.setViewport({ + width: opts.width, + height: opts.height, + deviceScaleFactor: 1, + }); + + // Navigate to sketch + const fileUrl = `file://${inputPath}`; + await page.goto(fileUrl, { waitUntil: 'networkidle0', timeout: 30000 }); + + // Wait for canvas to appear + await page.waitForSelector(opts.selector, { timeout: 10000 }); + + // Detect capture mode: deterministic (noLoop+redraw) vs timed (fallback) + let deterministic = false; + try { + await page.waitForFunction('window._p5Ready === true', { timeout: 5000 }); + deterministic = true; + console.log(`Mode: deterministic (noLoop + redraw)`); + } catch { + console.log(`Mode: timed fallback (sketch does not set window._p5Ready)`); + console.log(` For frame-perfect capture, add noLoop() and window._p5Ready=true to setup()`); + await new Promise(r => setTimeout(r, opts.wait)); + } + + const startTime = Date.now(); + + for (let i = 0; i < opts.frames; i++) { + if (deterministic) { + // Advance exactly one frame + await page.evaluate(() => { redraw(); }); + // Brief settle time for render to complete + await new Promise(r => setTimeout(r, 20)); + } + + const frameName = `frame-${String(i).padStart(4, '0')}.png`; + const framePath = path.join(opts.output, frameName); + + // Capture the canvas element + const canvas = await page.$(opts.selector); + if (!canvas) { + console.error('Canvas element not found'); + break; + } + + await canvas.screenshot({ path: framePath, type: 'png' }); + + // Progress + if (i % 30 === 0 || i === opts.frames - 1) { + const pct = ((i + 1) / opts.frames * 100).toFixed(1); + const elapsed = ((Date.now() - startTime) / 1000).toFixed(1); + process.stdout.write(`\r Frame ${i + 1}/${opts.frames} (${pct}%) — ${elapsed}s`); + } + + // In timed mode, wait between frames + if (!deterministic && i < opts.frames - 1) { + await new Promise(r => setTimeout(r, 1000 / opts.fps)); + } + } + + console.log('\n Done.'); + await browser.close(); +} + +main().catch(err => { + console.error('Error:', err.message); + process.exit(1); +}); diff --git a/mateclaw-server/src/main/resources/skills/p5js/scripts/render.sh b/mateclaw-server/src/main/resources/skills/p5js/scripts/render.sh new file mode 100755 index 00000000..81e65cf2 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/p5js/scripts/render.sh @@ -0,0 +1,108 @@ +#!/bin/bash +# p5.js Skill — Headless Render Pipeline +# Renders a p5.js sketch to MP4 video via Puppeteer + ffmpeg +# +# Usage: +# bash scripts/render.sh sketch.html output.mp4 [options] +# +# Options: +# --width Canvas width (default: 1920) +# --height Canvas height (default: 1080) +# --fps Frames per second (default: 30) +# --duration Duration in seconds (default: 10) +# --quality CRF value 0-51 (default: 18, lower = better) +# --frames-only Only export frames, skip MP4 encoding +# +# Examples: +# bash scripts/render.sh sketch.html output.mp4 +# bash scripts/render.sh sketch.html output.mp4 --duration 30 --fps 60 +# bash scripts/render.sh sketch.html output.mp4 --width 3840 --height 2160 + +set -euo pipefail + +# Defaults +WIDTH=1920 +HEIGHT=1080 +FPS=30 +DURATION=10 +CRF=18 +FRAMES_ONLY=false + +# Parse arguments +INPUT="${1:?Usage: render.sh [options]}" +OUTPUT="${2:?Usage: render.sh [options]}" +shift 2 + +while [[ $# -gt 0 ]]; do + case $1 in + --width) WIDTH="$2"; shift 2 ;; + --height) HEIGHT="$2"; shift 2 ;; + --fps) FPS="$2"; shift 2 ;; + --duration) DURATION="$2"; shift 2 ;; + --quality) CRF="$2"; shift 2 ;; + --frames-only) FRAMES_ONLY=true; shift ;; + *) echo "Unknown option: $1"; exit 1 ;; + esac +done + +TOTAL_FRAMES=$((FPS * DURATION)) +SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)" +FRAME_DIR=$(mktemp -d) + +echo "=== p5.js Render Pipeline ===" +echo "Input: $INPUT" +echo "Output: $OUTPUT" +echo "Resolution: ${WIDTH}x${HEIGHT}" +echo "FPS: $FPS" +echo "Duration: ${DURATION}s (${TOTAL_FRAMES} frames)" +echo "Quality: CRF $CRF" +echo "Frame dir: $FRAME_DIR" +echo "" + +# Check dependencies +command -v node >/dev/null 2>&1 || { echo "Error: Node.js required"; exit 1; } +if [ "$FRAMES_ONLY" = false ]; then + command -v ffmpeg >/dev/null 2>&1 || { echo "Error: ffmpeg required for MP4"; exit 1; } +fi + +# Step 1: Capture frames via Puppeteer +echo "Step 1/2: Capturing ${TOTAL_FRAMES} frames..." +node "$SCRIPT_DIR/export-frames.js" \ + "$INPUT" \ + --output "$FRAME_DIR" \ + --width "$WIDTH" \ + --height "$HEIGHT" \ + --frames "$TOTAL_FRAMES" \ + --fps "$FPS" + +echo "Frames captured to $FRAME_DIR" + +if [ "$FRAMES_ONLY" = true ]; then + echo "Frames saved to: $FRAME_DIR" + echo "To encode manually:" + echo " ffmpeg -framerate $FPS -i $FRAME_DIR/frame-%04d.png -c:v libx264 -crf $CRF -pix_fmt yuv420p $OUTPUT" + exit 0 +fi + +# Step 2: Encode to MP4 +echo "Step 2/2: Encoding MP4..." +ffmpeg -y \ + -framerate "$FPS" \ + -i "$FRAME_DIR/frame-%04d.png" \ + -c:v libx264 \ + -preset slow \ + -crf "$CRF" \ + -pix_fmt yuv420p \ + -movflags +faststart \ + "$OUTPUT" \ + 2>"$FRAME_DIR/ffmpeg.log" + +# Cleanup +rm -rf "$FRAME_DIR" + +# Report +FILE_SIZE=$(ls -lh "$OUTPUT" | awk '{print $5}') +echo "" +echo "=== Done ===" +echo "Output: $OUTPUT ($FILE_SIZE)" +echo "Duration: ${DURATION}s at ${FPS}fps, ${WIDTH}x${HEIGHT}" diff --git a/mateclaw-server/src/main/resources/skills/p5js/scripts/serve.sh b/mateclaw-server/src/main/resources/skills/p5js/scripts/serve.sh new file mode 100755 index 00000000..34055d59 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/p5js/scripts/serve.sh @@ -0,0 +1,28 @@ +#!/bin/bash +# p5.js Skill — Local Development Server +# Serves the current directory over HTTP for loading local assets (fonts, images) +# +# Usage: +# bash scripts/serve.sh [port] [directory] +# +# Examples: +# bash scripts/serve.sh # serve CWD on port 8080 +# bash scripts/serve.sh 3000 # serve CWD on port 3000 +# bash scripts/serve.sh 8080 ./my-project # serve specific directory + +PORT="${1:-8080}" +DIR="${2:-.}" + +echo "=== p5.js Dev Server ===" +echo "Serving: $(cd "$DIR" && pwd)" +echo "URL: http://localhost:$PORT" +echo "Press Ctrl+C to stop" +echo "" + +cd "$DIR" && python3 -m http.server "$PORT" 2>/dev/null || { + echo "Python3 not found. Trying Node.js..." + npx serve -l "$PORT" "$DIR" 2>/dev/null || { + echo "Error: Need python3 or npx (Node.js) for local server" + exit 1 + } +} diff --git a/mateclaw-server/src/main/resources/skills/p5js/scripts/setup.sh b/mateclaw-server/src/main/resources/skills/p5js/scripts/setup.sh new file mode 100755 index 00000000..33f9e0e1 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/p5js/scripts/setup.sh @@ -0,0 +1,87 @@ +#!/bin/bash +# p5.js Skill — Dependency Verification +# Run: bash skills/creative/p5js/scripts/setup.sh + +set -euo pipefail + +RED='\033[0;31m' +GREEN='\033[0;32m' +YELLOW='\033[1;33m' +NC='\033[0m' + +ok() { echo -e "${GREEN}[OK]${NC} $1"; } +warn() { echo -e "${YELLOW}[WARN]${NC} $1"; } +fail() { echo -e "${RED}[FAIL]${NC} $1"; } + +echo "=== p5.js Skill — Setup Check ===" +echo "" + +# Required: Node.js (for Puppeteer headless export) +if command -v node &>/dev/null; then + NODE_VER=$(node -v) + ok "Node.js $NODE_VER" +else + warn "Node.js not found — optional, needed for headless export" + echo " Install: https://nodejs.org/ or 'brew install node'" +fi + +# Required: npm (for Puppeteer install) +if command -v npm &>/dev/null; then + NPM_VER=$(npm -v) + ok "npm $NPM_VER" +else + warn "npm not found — optional, needed for headless export" +fi + +# Optional: Puppeteer +if node -e "require('puppeteer')" 2>/dev/null; then + ok "Puppeteer installed" +else + warn "Puppeteer not installed — needed for headless export" + echo " Install: npm install puppeteer" +fi + +# Optional: ffmpeg (for MP4 encoding from frame sequences) +if command -v ffmpeg &>/dev/null; then + FFMPEG_VER=$(ffmpeg -version 2>&1 | head -1 | awk '{print $3}') + ok "ffmpeg $FFMPEG_VER" +else + warn "ffmpeg not found — needed for MP4 export" + echo " Install: brew install ffmpeg (macOS) or apt install ffmpeg (Linux)" +fi + +# Optional: Python3 (for local server) +if command -v python3 &>/dev/null; then + PY_VER=$(python3 --version 2>&1 | awk '{print $2}') + ok "Python $PY_VER (for local server: python3 -m http.server)" +else + warn "Python3 not found — needed for local file serving" +fi + +# Browser check (macOS) +if [[ "$(uname)" == "Darwin" ]]; then + if open -Ra "Google Chrome" 2>/dev/null; then + ok "Google Chrome found" + elif open -Ra "Safari" 2>/dev/null; then + ok "Safari found" + else + warn "No browser detected" + fi +fi + +echo "" +echo "=== Core Requirements ===" +echo " A modern browser (Chrome/Firefox/Safari/Edge)" +echo " p5.js loaded via CDN — no local install needed" +echo "" +echo "=== Optional (for export) ===" +echo " Node.js + Puppeteer — headless frame capture" +echo " ffmpeg — frame sequence to MP4" +echo " Python3 — local development server" +echo "" +echo "=== Quick Start ===" +echo " 1. Create an HTML file with inline p5.js sketch" +echo " 2. Open in browser: open sketch.html" +echo " 3. Press 's' to save PNG, 'g' to save GIF" +echo "" +echo "Setup check complete." diff --git a/mateclaw-server/src/main/resources/skills/pdf/scripts/check_bounding_boxes.py b/mateclaw-server/src/main/resources/skills/pdf/scripts/check_bounding_boxes.py new file mode 100644 index 00000000..2cc5e348 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/pdf/scripts/check_bounding_boxes.py @@ -0,0 +1,65 @@ +from dataclasses import dataclass +import json +import sys + + + + +@dataclass +class RectAndField: + rect: list[float] + rect_type: str + field: dict + + +def get_bounding_box_messages(fields_json_stream) -> list[str]: + messages = [] + fields = json.load(fields_json_stream) + messages.append(f"Read {len(fields['form_fields'])} fields") + + def rects_intersect(r1, r2): + disjoint_horizontal = r1[0] >= r2[2] or r1[2] <= r2[0] + disjoint_vertical = r1[1] >= r2[3] or r1[3] <= r2[1] + return not (disjoint_horizontal or disjoint_vertical) + + rects_and_fields = [] + for f in fields["form_fields"]: + rects_and_fields.append(RectAndField(f["label_bounding_box"], "label", f)) + rects_and_fields.append(RectAndField(f["entry_bounding_box"], "entry", f)) + + has_error = False + for i, ri in enumerate(rects_and_fields): + for j in range(i + 1, len(rects_and_fields)): + rj = rects_and_fields[j] + if ri.field["page_number"] == rj.field["page_number"] and rects_intersect(ri.rect, rj.rect): + has_error = True + if ri.field is rj.field: + messages.append(f"FAILURE: intersection between label and entry bounding boxes for `{ri.field['description']}` ({ri.rect}, {rj.rect})") + else: + messages.append(f"FAILURE: intersection between {ri.rect_type} bounding box for `{ri.field['description']}` ({ri.rect}) and {rj.rect_type} bounding box for `{rj.field['description']}` ({rj.rect})") + if len(messages) >= 20: + messages.append("Aborting further checks; fix bounding boxes and try again") + return messages + if ri.rect_type == "entry": + if "entry_text" in ri.field: + font_size = ri.field["entry_text"].get("font_size", 14) + entry_height = ri.rect[3] - ri.rect[1] + if entry_height < font_size: + has_error = True + messages.append(f"FAILURE: entry bounding box height ({entry_height}) for `{ri.field['description']}` is too short for the text content (font size: {font_size}). Increase the box height or decrease the font size.") + if len(messages) >= 20: + messages.append("Aborting further checks; fix bounding boxes and try again") + return messages + + if not has_error: + messages.append("SUCCESS: All bounding boxes are valid") + return messages + +if __name__ == "__main__": + if len(sys.argv) != 2: + print("Usage: check_bounding_boxes.py [fields.json]") + sys.exit(1) + with open(sys.argv[1]) as f: + messages = get_bounding_box_messages(f) + for msg in messages: + print(msg) diff --git a/mateclaw-server/src/main/resources/skills/pdf/scripts/check_fillable_fields.py b/mateclaw-server/src/main/resources/skills/pdf/scripts/check_fillable_fields.py new file mode 100644 index 00000000..36dfb951 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/pdf/scripts/check_fillable_fields.py @@ -0,0 +1,11 @@ +import sys +from pypdf import PdfReader + + + + +reader = PdfReader(sys.argv[1]) +if (reader.get_fields()): + print("This PDF has fillable form fields") +else: + print("This PDF does not have fillable form fields; you will need to visually determine where to enter data") diff --git a/mateclaw-server/src/main/resources/skills/pdf/scripts/convert_pdf_to_images.py b/mateclaw-server/src/main/resources/skills/pdf/scripts/convert_pdf_to_images.py new file mode 100644 index 00000000..7939cef5 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/pdf/scripts/convert_pdf_to_images.py @@ -0,0 +1,33 @@ +import os +import sys + +from pdf2image import convert_from_path + + + + +def convert(pdf_path, output_dir, max_dim=1000): + images = convert_from_path(pdf_path, dpi=200) + + for i, image in enumerate(images): + width, height = image.size + if width > max_dim or height > max_dim: + scale_factor = min(max_dim / width, max_dim / height) + new_width = int(width * scale_factor) + new_height = int(height * scale_factor) + image = image.resize((new_width, new_height)) + + image_path = os.path.join(output_dir, f"page_{i+1}.png") + image.save(image_path) + print(f"Saved page {i+1} as {image_path} (size: {image.size})") + + print(f"Converted {len(images)} pages to PNG images") + + +if __name__ == "__main__": + if len(sys.argv) != 3: + print("Usage: convert_pdf_to_images.py [input pdf] [output directory]") + sys.exit(1) + pdf_path = sys.argv[1] + output_directory = sys.argv[2] + convert(pdf_path, output_directory) diff --git a/mateclaw-server/src/main/resources/skills/pdf/scripts/create_validation_image.py b/mateclaw-server/src/main/resources/skills/pdf/scripts/create_validation_image.py new file mode 100644 index 00000000..10eadd81 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/pdf/scripts/create_validation_image.py @@ -0,0 +1,37 @@ +import json +import sys + +from PIL import Image, ImageDraw + + + + +def create_validation_image(page_number, fields_json_path, input_path, output_path): + with open(fields_json_path, 'r') as f: + data = json.load(f) + + img = Image.open(input_path) + draw = ImageDraw.Draw(img) + num_boxes = 0 + + for field in data["form_fields"]: + if field["page_number"] == page_number: + entry_box = field['entry_bounding_box'] + label_box = field['label_bounding_box'] + draw.rectangle(entry_box, outline='red', width=2) + draw.rectangle(label_box, outline='blue', width=2) + num_boxes += 2 + + img.save(output_path) + print(f"Created validation image at {output_path} with {num_boxes} bounding boxes") + + +if __name__ == "__main__": + if len(sys.argv) != 5: + print("Usage: create_validation_image.py [page number] [fields.json file] [input image path] [output image path]") + sys.exit(1) + page_number = int(sys.argv[1]) + fields_json_path = sys.argv[2] + input_image_path = sys.argv[3] + output_image_path = sys.argv[4] + create_validation_image(page_number, fields_json_path, input_image_path, output_image_path) diff --git a/mateclaw-server/src/main/resources/skills/pdf/scripts/extract_form_field_info.py b/mateclaw-server/src/main/resources/skills/pdf/scripts/extract_form_field_info.py new file mode 100644 index 00000000..64cd4703 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/pdf/scripts/extract_form_field_info.py @@ -0,0 +1,122 @@ +import json +import sys + +from pypdf import PdfReader + + + + +def get_full_annotation_field_id(annotation): + components = [] + while annotation: + field_name = annotation.get('/T') + if field_name: + components.append(field_name) + annotation = annotation.get('/Parent') + return ".".join(reversed(components)) if components else None + + +def make_field_dict(field, field_id): + field_dict = {"field_id": field_id} + ft = field.get('/FT') + if ft == "/Tx": + field_dict["type"] = "text" + elif ft == "/Btn": + field_dict["type"] = "checkbox" + states = field.get("/_States_", []) + if len(states) == 2: + if "/Off" in states: + field_dict["checked_value"] = states[0] if states[0] != "/Off" else states[1] + field_dict["unchecked_value"] = "/Off" + else: + print(f"Unexpected state values for checkbox `${field_id}`. Its checked and unchecked values may not be correct; if you're trying to check it, visually verify the results.") + field_dict["checked_value"] = states[0] + field_dict["unchecked_value"] = states[1] + elif ft == "/Ch": + field_dict["type"] = "choice" + states = field.get("/_States_", []) + field_dict["choice_options"] = [{ + "value": state[0], + "text": state[1], + } for state in states] + else: + field_dict["type"] = f"unknown ({ft})" + return field_dict + + +def get_field_info(reader: PdfReader): + fields = reader.get_fields() + + field_info_by_id = {} + possible_radio_names = set() + + for field_id, field in fields.items(): + if field.get("/Kids"): + if field.get("/FT") == "/Btn": + possible_radio_names.add(field_id) + continue + field_info_by_id[field_id] = make_field_dict(field, field_id) + + + radio_fields_by_id = {} + + for page_index, page in enumerate(reader.pages): + annotations = page.get('/Annots', []) + for ann in annotations: + field_id = get_full_annotation_field_id(ann) + if field_id in field_info_by_id: + field_info_by_id[field_id]["page"] = page_index + 1 + field_info_by_id[field_id]["rect"] = ann.get('/Rect') + elif field_id in possible_radio_names: + try: + on_values = [v for v in ann["/AP"]["/N"] if v != "/Off"] + except KeyError: + continue + if len(on_values) == 1: + rect = ann.get("/Rect") + if field_id not in radio_fields_by_id: + radio_fields_by_id[field_id] = { + "field_id": field_id, + "type": "radio_group", + "page": page_index + 1, + "radio_options": [], + } + radio_fields_by_id[field_id]["radio_options"].append({ + "value": on_values[0], + "rect": rect, + }) + + fields_with_location = [] + for field_info in field_info_by_id.values(): + if "page" in field_info: + fields_with_location.append(field_info) + else: + print(f"Unable to determine location for field id: {field_info.get('field_id')}, ignoring") + + def sort_key(f): + if "radio_options" in f: + rect = f["radio_options"][0]["rect"] or [0, 0, 0, 0] + else: + rect = f.get("rect") or [0, 0, 0, 0] + adjusted_position = [-rect[1], rect[0]] + return [f.get("page"), adjusted_position] + + sorted_fields = fields_with_location + list(radio_fields_by_id.values()) + sorted_fields.sort(key=sort_key) + + return sorted_fields + + +def write_field_info(pdf_path: str, json_output_path: str): + reader = PdfReader(pdf_path) + field_info = get_field_info(reader) + with open(json_output_path, "w") as f: + json.dump(field_info, f, indent=2) + print(f"Wrote {len(field_info)} fields to {json_output_path}") + + +if __name__ == "__main__": + if len(sys.argv) != 3: + print("Usage: extract_form_field_info.py [input pdf] [output json]") + sys.exit(1) + write_field_info(sys.argv[1], sys.argv[2]) diff --git a/mateclaw-server/src/main/resources/skills/pdf/scripts/extract_form_structure.py b/mateclaw-server/src/main/resources/skills/pdf/scripts/extract_form_structure.py new file mode 100755 index 00000000..f219e7d5 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/pdf/scripts/extract_form_structure.py @@ -0,0 +1,115 @@ +""" +Extract form structure from a non-fillable PDF. + +This script analyzes the PDF to find: +- Text labels with their exact coordinates +- Horizontal lines (row boundaries) +- Checkboxes (small rectangles) + +Output: A JSON file with the form structure that can be used to generate +accurate field coordinates for filling. + +Usage: python extract_form_structure.py +""" + +import json +import sys +import pdfplumber + + +def extract_form_structure(pdf_path): + structure = { + "pages": [], + "labels": [], + "lines": [], + "checkboxes": [], + "row_boundaries": [] + } + + with pdfplumber.open(pdf_path) as pdf: + for page_num, page in enumerate(pdf.pages, 1): + structure["pages"].append({ + "page_number": page_num, + "width": float(page.width), + "height": float(page.height) + }) + + words = page.extract_words() + for word in words: + structure["labels"].append({ + "page": page_num, + "text": word["text"], + "x0": round(float(word["x0"]), 1), + "top": round(float(word["top"]), 1), + "x1": round(float(word["x1"]), 1), + "bottom": round(float(word["bottom"]), 1) + }) + + for line in page.lines: + if abs(float(line["x1"]) - float(line["x0"])) > page.width * 0.5: + structure["lines"].append({ + "page": page_num, + "y": round(float(line["top"]), 1), + "x0": round(float(line["x0"]), 1), + "x1": round(float(line["x1"]), 1) + }) + + for rect in page.rects: + width = float(rect["x1"]) - float(rect["x0"]) + height = float(rect["bottom"]) - float(rect["top"]) + if 5 <= width <= 15 and 5 <= height <= 15 and abs(width - height) < 2: + structure["checkboxes"].append({ + "page": page_num, + "x0": round(float(rect["x0"]), 1), + "top": round(float(rect["top"]), 1), + "x1": round(float(rect["x1"]), 1), + "bottom": round(float(rect["bottom"]), 1), + "center_x": round((float(rect["x0"]) + float(rect["x1"])) / 2, 1), + "center_y": round((float(rect["top"]) + float(rect["bottom"])) / 2, 1) + }) + + lines_by_page = {} + for line in structure["lines"]: + page = line["page"] + if page not in lines_by_page: + lines_by_page[page] = [] + lines_by_page[page].append(line["y"]) + + for page, y_coords in lines_by_page.items(): + y_coords = sorted(set(y_coords)) + for i in range(len(y_coords) - 1): + structure["row_boundaries"].append({ + "page": page, + "row_top": y_coords[i], + "row_bottom": y_coords[i + 1], + "row_height": round(y_coords[i + 1] - y_coords[i], 1) + }) + + return structure + + +def main(): + if len(sys.argv) != 3: + print("Usage: extract_form_structure.py ") + sys.exit(1) + + pdf_path = sys.argv[1] + output_path = sys.argv[2] + + print(f"Extracting structure from {pdf_path}...") + structure = extract_form_structure(pdf_path) + + with open(output_path, "w") as f: + json.dump(structure, f, indent=2) + + print(f"Found:") + print(f" - {len(structure['pages'])} pages") + print(f" - {len(structure['labels'])} text labels") + print(f" - {len(structure['lines'])} horizontal lines") + print(f" - {len(structure['checkboxes'])} checkboxes") + print(f" - {len(structure['row_boundaries'])} row boundaries") + print(f"Saved to {output_path}") + + +if __name__ == "__main__": + main() diff --git a/mateclaw-server/src/main/resources/skills/pdf/scripts/fill_fillable_fields.py b/mateclaw-server/src/main/resources/skills/pdf/scripts/fill_fillable_fields.py new file mode 100644 index 00000000..51c2600f --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/pdf/scripts/fill_fillable_fields.py @@ -0,0 +1,98 @@ +import json +import sys + +from pypdf import PdfReader, PdfWriter + +from extract_form_field_info import get_field_info + + + + +def fill_pdf_fields(input_pdf_path: str, fields_json_path: str, output_pdf_path: str): + with open(fields_json_path) as f: + fields = json.load(f) + fields_by_page = {} + for field in fields: + if "value" in field: + field_id = field["field_id"] + page = field["page"] + if page not in fields_by_page: + fields_by_page[page] = {} + fields_by_page[page][field_id] = field["value"] + + reader = PdfReader(input_pdf_path) + + has_error = False + field_info = get_field_info(reader) + fields_by_ids = {f["field_id"]: f for f in field_info} + for field in fields: + existing_field = fields_by_ids.get(field["field_id"]) + if not existing_field: + has_error = True + print(f"ERROR: `{field['field_id']}` is not a valid field ID") + elif field["page"] != existing_field["page"]: + has_error = True + print(f"ERROR: Incorrect page number for `{field['field_id']}` (got {field['page']}, expected {existing_field['page']})") + else: + if "value" in field: + err = validation_error_for_field_value(existing_field, field["value"]) + if err: + print(err) + has_error = True + if has_error: + sys.exit(1) + + writer = PdfWriter(clone_from=reader) + for page, field_values in fields_by_page.items(): + writer.update_page_form_field_values(writer.pages[page - 1], field_values, auto_regenerate=False) + + writer.set_need_appearances_writer(True) + + with open(output_pdf_path, "wb") as f: + writer.write(f) + + +def validation_error_for_field_value(field_info, field_value): + field_type = field_info["type"] + field_id = field_info["field_id"] + if field_type == "checkbox": + checked_val = field_info["checked_value"] + unchecked_val = field_info["unchecked_value"] + if field_value != checked_val and field_value != unchecked_val: + return f'ERROR: Invalid value "{field_value}" for checkbox field "{field_id}". The checked value is "{checked_val}" and the unchecked value is "{unchecked_val}"' + elif field_type == "radio_group": + option_values = [opt["value"] for opt in field_info["radio_options"]] + if field_value not in option_values: + return f'ERROR: Invalid value "{field_value}" for radio group field "{field_id}". Valid values are: {option_values}' + elif field_type == "choice": + choice_values = [opt["value"] for opt in field_info["choice_options"]] + if field_value not in choice_values: + return f'ERROR: Invalid value "{field_value}" for choice field "{field_id}". Valid values are: {choice_values}' + return None + + +def monkeypatch_pydpf_method(): + from pypdf.generic import DictionaryObject + from pypdf.constants import FieldDictionaryAttributes + + original_get_inherited = DictionaryObject.get_inherited + + def patched_get_inherited(self, key: str, default = None): + result = original_get_inherited(self, key, default) + if key == FieldDictionaryAttributes.Opt: + if isinstance(result, list) and all(isinstance(v, list) and len(v) == 2 for v in result): + result = [r[0] for r in result] + return result + + DictionaryObject.get_inherited = patched_get_inherited + + +if __name__ == "__main__": + if len(sys.argv) != 4: + print("Usage: fill_fillable_fields.py [input pdf] [field_values.json] [output pdf]") + sys.exit(1) + monkeypatch_pydpf_method() + input_pdf = sys.argv[1] + fields_json = sys.argv[2] + output_pdf = sys.argv[3] + fill_pdf_fields(input_pdf, fields_json, output_pdf) diff --git a/mateclaw-server/src/main/resources/skills/pdf/scripts/fill_pdf_form_with_annotations.py b/mateclaw-server/src/main/resources/skills/pdf/scripts/fill_pdf_form_with_annotations.py new file mode 100644 index 00000000..b430069f --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/pdf/scripts/fill_pdf_form_with_annotations.py @@ -0,0 +1,107 @@ +import json +import sys + +from pypdf import PdfReader, PdfWriter +from pypdf.annotations import FreeText + + + + +def transform_from_image_coords(bbox, image_width, image_height, pdf_width, pdf_height): + x_scale = pdf_width / image_width + y_scale = pdf_height / image_height + + left = bbox[0] * x_scale + right = bbox[2] * x_scale + + top = pdf_height - (bbox[1] * y_scale) + bottom = pdf_height - (bbox[3] * y_scale) + + return left, bottom, right, top + + +def transform_from_pdf_coords(bbox, pdf_height): + left = bbox[0] + right = bbox[2] + + pypdf_top = pdf_height - bbox[1] + pypdf_bottom = pdf_height - bbox[3] + + return left, pypdf_bottom, right, pypdf_top + + +def fill_pdf_form(input_pdf_path, fields_json_path, output_pdf_path): + + with open(fields_json_path, "r") as f: + fields_data = json.load(f) + + reader = PdfReader(input_pdf_path) + writer = PdfWriter() + + writer.append(reader) + + pdf_dimensions = {} + for i, page in enumerate(reader.pages): + mediabox = page.mediabox + pdf_dimensions[i + 1] = [mediabox.width, mediabox.height] + + annotations = [] + for field in fields_data["form_fields"]: + page_num = field["page_number"] + + page_info = next(p for p in fields_data["pages"] if p["page_number"] == page_num) + pdf_width, pdf_height = pdf_dimensions[page_num] + + if "pdf_width" in page_info: + transformed_entry_box = transform_from_pdf_coords( + field["entry_bounding_box"], + float(pdf_height) + ) + else: + image_width = page_info["image_width"] + image_height = page_info["image_height"] + transformed_entry_box = transform_from_image_coords( + field["entry_bounding_box"], + image_width, image_height, + float(pdf_width), float(pdf_height) + ) + + if "entry_text" not in field or "text" not in field["entry_text"]: + continue + entry_text = field["entry_text"] + text = entry_text["text"] + if not text: + continue + + font_name = entry_text.get("font", "Arial") + font_size = str(entry_text.get("font_size", 14)) + "pt" + font_color = entry_text.get("font_color", "000000") + + annotation = FreeText( + text=text, + rect=transformed_entry_box, + font=font_name, + font_size=font_size, + font_color=font_color, + border_color=None, + background_color=None, + ) + annotations.append(annotation) + writer.add_annotation(page_number=page_num - 1, annotation=annotation) + + with open(output_pdf_path, "wb") as output: + writer.write(output) + + print(f"Successfully filled PDF form and saved to {output_pdf_path}") + print(f"Added {len(annotations)} text annotations") + + +if __name__ == "__main__": + if len(sys.argv) != 4: + print("Usage: fill_pdf_form_with_annotations.py [input pdf] [fields.json] [output pdf]") + sys.exit(1) + input_pdf = sys.argv[1] + fields_json = sys.argv[2] + output_pdf = sys.argv[3] + + fill_pdf_form(input_pdf, fields_json, output_pdf) diff --git a/mateclaw-server/src/main/resources/skills/pixel-art/scripts/__init__.py b/mateclaw-server/src/main/resources/skills/pixel-art/scripts/__init__.py new file mode 100644 index 00000000..e69de29b diff --git a/mateclaw-server/src/main/resources/skills/pixel-art/scripts/palettes.py b/mateclaw-server/src/main/resources/skills/pixel-art/scripts/palettes.py new file mode 100644 index 00000000..adf0f1b3 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/pixel-art/scripts/palettes.py @@ -0,0 +1,167 @@ +"""Named RGB palettes for pixel_art() and pixel_art_video(). + +Palette RGB values sourced from pixel-art-studio (MIT License) +https://github.com/Synero/pixel-art-studio — see ATTRIBUTION.md. +""" + +PALETTES = { + # ── Hardware palettes ─────────────────────────────────────────────── + "NES": [ + (0, 0, 0), (124, 124, 124), (0, 0, 252), (0, 0, 188), (68, 40, 188), + (148, 0, 132), (168, 0, 32), (168, 16, 0), (136, 20, 0), (0, 116, 0), + (0, 148, 0), (0, 120, 0), (0, 88, 0), (0, 64, 88), (188, 188, 188), + (0, 120, 248), (0, 88, 248), (104, 68, 252), (216, 0, 204), (228, 0, 88), + (248, 56, 0), (228, 92, 16), (172, 124, 0), (0, 184, 0), (0, 168, 0), + (0, 168, 68), (0, 136, 136), (248, 248, 248), (60, 188, 252), + (104, 136, 252), (152, 120, 248), (248, 120, 248), (248, 88, 152), + (248, 120, 88), (252, 160, 68), (248, 184, 0), (184, 248, 24), + (88, 216, 84), (88, 248, 152), (0, 232, 216), (120, 120, 120), + (252, 252, 252), (164, 228, 252), (184, 184, 248), (216, 184, 248), + (248, 184, 248), (248, 164, 192), (240, 208, 176), (252, 224, 168), + (248, 216, 120), (216, 248, 120), (184, 248, 184), (184, 248, 216), + (0, 252, 252), (216, 216, 216), + ], + "C64": [ + (0, 0, 0), (255, 255, 255), (161, 77, 67), (106, 191, 199), + (161, 87, 164), (92, 172, 95), (64, 64, 223), (191, 206, 137), + (161, 104, 60), (108, 80, 21), (203, 126, 117), (98, 98, 98), + (137, 137, 137), (154, 226, 155), (124, 124, 255), (173, 173, 173), + ], + "COMMODORE_64": [ + (0, 0, 0), (255, 255, 255), (161, 77, 67), (106, 192, 200), + (161, 87, 165), (92, 172, 95), (64, 68, 227), (203, 214, 137), + (163, 104, 58), (110, 84, 11), (204, 127, 118), (99, 99, 99), + (139, 139, 139), (154, 227, 157), (139, 127, 205), (175, 175, 175), + ], + "ZX_SPECTRUM": [ + (0, 0, 0), (0, 39, 251), (252, 48, 22), (255, 63, 252), + (0, 249, 44), (0, 252, 254), (255, 253, 51), (255, 255, 255), + ], + "APPLE_II_LO": [ + (0, 0, 0), (133, 59, 81), (80, 71, 137), (234, 93, 240), + (0, 104, 82), (146, 146, 146), (0, 168, 241), (202, 195, 248), + (81, 92, 15), (235, 127, 35), (146, 146, 146), (246, 185, 202), + (0, 202, 41), (203, 211, 155), (155, 220, 203), (255, 255, 255), + ], + "APPLE_II_HI": [ + (0, 0, 0), (255, 0, 255), (0, 255, 0), (255, 255, 255), + (0, 175, 255), (255, 80, 0), + ], + "GAMEBOY_ORIGINAL": [ + (0, 63, 0), (46, 115, 32), (140, 191, 10), (160, 207, 10), + ], + "GAMEBOY_POCKET": [ + (0, 0, 0), (85, 85, 85), (170, 170, 170), (255, 255, 255), + ], + "GAMEBOY_VIRTUALBOY": [ + (239, 0, 0), (164, 0, 0), (85, 0, 0), (0, 0, 0), + ], + "PICO_8": [ + (0, 0, 0), (29, 43, 83), (126, 37, 83), (0, 135, 81), (171, 82, 54), + (95, 87, 79), (194, 195, 199), (255, 241, 232), (255, 0, 77), + (255, 163, 0), (255, 236, 39), (0, 228, 54), (41, 173, 255), + (131, 118, 156), (255, 119, 168), (255, 204, 170), + ], + "TELETEXT": [ + (0, 0, 0), (255, 0, 0), (0, 128, 0), (255, 255, 0), + (0, 0, 255), (255, 0, 255), (0, 255, 255), (255, 255, 255), + ], + "CGA_MODE4_PAL1": [ + (0, 0, 0), (255, 255, 255), (0, 255, 255), (255, 0, 255), + ], + "MSX": [ + (0, 0, 0), (62, 184, 73), (116, 208, 125), (89, 85, 224), + (128, 118, 241), (185, 94, 81), (101, 219, 239), (219, 101, 89), + (255, 137, 125), (204, 195, 94), (222, 208, 135), (58, 162, 65), + (183, 102, 181), (204, 204, 204), (255, 255, 255), + ], + "MICROSOFT_WINDOWS_16": [ + (0, 0, 0), (128, 0, 0), (0, 128, 0), (128, 128, 0), (0, 0, 128), + (128, 0, 128), (0, 128, 128), (192, 192, 192), (128, 128, 128), + (255, 0, 0), (0, 255, 0), (255, 255, 0), (0, 0, 255), + (255, 0, 255), (0, 255, 255), (255, 255, 255), + ], + "MICROSOFT_WINDOWS_PAINT": [ + (0, 0, 0), (255, 255, 255), (123, 123, 123), (189, 189, 189), + (123, 12, 2), (255, 37, 0), (123, 123, 2), (255, 251, 2), + (0, 123, 2), (2, 249, 2), (0, 123, 122), (2, 253, 254), + (2, 19, 122), (5, 50, 255), (123, 25, 122), (255, 64, 254), + (122, 57, 2), (255, 122, 57), (123, 123, 56), (255, 252, 122), + (2, 57, 57), (5, 250, 123), (0, 123, 255), (255, 44, 123), + ], + "MONO_BW": [(0, 0, 0), (255, 255, 255)], + "MONO_AMBER": [(40, 40, 40), (255, 176, 0)], + "MONO_GREEN": [(40, 40, 40), (51, 255, 51)], + + # ── Artistic palettes ─────────────────────────────────────────────── + "PASTEL_DREAM": [ + (255, 218, 233), (255, 229, 204), (255, 255, 204), (204, 255, 229), + (204, 229, 255), (229, 204, 255), (255, 204, 229), (204, 255, 255), + (255, 245, 220), (230, 230, 250), + ], + "NEON_CYBER": [ + (0, 0, 0), (255, 0, 128), (0, 255, 255), (255, 0, 255), + (0, 255, 128), (255, 255, 0), (128, 0, 255), (255, 128, 0), + (0, 128, 255), (255, 255, 255), + ], + "RETRO_WARM": [ + (62, 39, 35), (139, 69, 19), (210, 105, 30), (244, 164, 96), + (255, 218, 185), (255, 245, 238), (178, 34, 34), (205, 92, 92), + (255, 99, 71), (255, 160, 122), + ], + "OCEAN_DEEP": [ + (0, 25, 51), (0, 51, 102), (0, 76, 153), (0, 102, 178), + (0, 128, 204), (51, 153, 204), (102, 178, 204), (153, 204, 229), + (204, 229, 255), (229, 245, 255), + ], + "FOREST_MOSS": [ + (34, 51, 34), (51, 76, 51), (68, 102, 51), (85, 128, 68), + (102, 153, 85), (136, 170, 102), (170, 196, 136), (204, 221, 170), + (238, 238, 204), (245, 245, 220), + ], + "SUNSET_FIRE": [ + (51, 0, 0), (102, 0, 0), (153, 0, 0), (204, 0, 0), (255, 0, 0), + (255, 51, 0), (255, 102, 0), (255, 153, 0), (255, 204, 0), + (255, 255, 51), + ], + "ARCTIC_ICE": [ + (0, 0, 51), (0, 0, 102), (0, 51, 153), (0, 102, 153), + (51, 153, 204), (102, 204, 255), (153, 229, 255), (204, 242, 255), + (229, 247, 255), (255, 255, 255), + ], + "VINTAGE_ROSE": [ + (103, 58, 63), (137, 72, 81), (170, 91, 102), (196, 113, 122), + (219, 139, 147), (232, 168, 175), (240, 196, 199), (245, 215, 217), + (249, 232, 233), (255, 245, 245), + ], + "EARTH_CLAY": [ + (62, 39, 35), (89, 56, 47), (116, 73, 59), (143, 90, 71), + (170, 107, 83), (197, 124, 95), (210, 155, 126), (222, 186, 160), + (235, 217, 196), (248, 248, 232), + ], + "ELECTRIC_VIOLET": [ + (26, 0, 51), (51, 0, 102), (76, 0, 153), (102, 0, 204), + (128, 0, 255), (153, 51, 255), (178, 102, 255), (204, 153, 255), + (229, 204, 255), (245, 229, 255), + ], +} + + +def build_palette_image(palette_name): + """Build a 1x1 PIL 'P'-mode image with the named palette for Image.quantize(palette=...).""" + from PIL import Image + + if palette_name not in PALETTES: + raise ValueError( + f"Unknown palette {palette_name!r}. " + f"Choose from: {sorted(PALETTES)}" + ) + flat = [] + for (r, g, b) in PALETTES[palette_name]: + flat.extend([r, g, b]) + # Pad to 768 bytes (256 colors) as PIL requires + while len(flat) < 768: + flat.append(0) + pal_img = Image.new("P", (1, 1)) + pal_img.putpalette(flat) + return pal_img diff --git a/mateclaw-server/src/main/resources/skills/pixel-art/scripts/pixel_art.py b/mateclaw-server/src/main/resources/skills/pixel-art/scripts/pixel_art.py new file mode 100644 index 00000000..67987e41 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/pixel-art/scripts/pixel_art.py @@ -0,0 +1,162 @@ +"""Pixel art converter — Floyd-Steinberg dithering with preset or named palette. + +Named hardware palettes (NES, GameBoy, PICO-8, C64, etc.) ported from +pixel-art-studio (MIT) — see ATTRIBUTION.md. + +Usage (import): + from pixel_art import pixel_art + pixel_art("in.png", "out.png", preset="arcade") + pixel_art("in.png", "out.png", preset="nes") + pixel_art("in.png", "out.png", palette="PICO_8", block=6) + +Usage (CLI): + python pixel_art.py in.png out.png --preset nes +""" + +from PIL import Image, ImageEnhance, ImageOps + +try: + from .palettes import PALETTES, build_palette_image +except ImportError: + from palettes import PALETTES, build_palette_image + + +PRESETS = { + # ── Original presets (adaptive palette) ───────────────────────────── + "arcade": { + "contrast": 1.8, "color": 1.5, "sharpness": 1.2, + "posterize_bits": 5, "block": 8, "palette": 16, + }, + "snes": { + "contrast": 1.6, "color": 1.4, "sharpness": 1.2, + "posterize_bits": 6, "block": 4, "palette": 32, + }, + # ── Hardware-accurate presets (named palette) ─────────────────────── + "nes": { + "contrast": 1.5, "color": 1.4, "sharpness": 1.2, + "posterize_bits": 6, "block": 8, "palette": "NES", + }, + "gameboy": { + "contrast": 1.5, "color": 1.0, "sharpness": 1.2, + "posterize_bits": 6, "block": 8, "palette": "GAMEBOY_ORIGINAL", + }, + "gameboy_pocket": { + "contrast": 1.5, "color": 1.0, "sharpness": 1.2, + "posterize_bits": 6, "block": 8, "palette": "GAMEBOY_POCKET", + }, + "pico8": { + "contrast": 1.6, "color": 1.3, "sharpness": 1.2, + "posterize_bits": 6, "block": 6, "palette": "PICO_8", + }, + "c64": { + "contrast": 1.6, "color": 1.3, "sharpness": 1.2, + "posterize_bits": 6, "block": 8, "palette": "C64", + }, + "apple2": { + "contrast": 1.8, "color": 1.4, "sharpness": 1.2, + "posterize_bits": 5, "block": 10, "palette": "APPLE_II_HI", + }, + "teletext": { + "contrast": 1.8, "color": 1.5, "sharpness": 1.2, + "posterize_bits": 5, "block": 10, "palette": "TELETEXT", + }, + "mspaint": { + "contrast": 1.6, "color": 1.4, "sharpness": 1.2, + "posterize_bits": 6, "block": 8, "palette": "MICROSOFT_WINDOWS_PAINT", + }, + "mono_green": { + "contrast": 1.8, "color": 0.0, "sharpness": 1.2, + "posterize_bits": 5, "block": 6, "palette": "MONO_GREEN", + }, + "mono_amber": { + "contrast": 1.8, "color": 0.0, "sharpness": 1.2, + "posterize_bits": 5, "block": 6, "palette": "MONO_AMBER", + }, + # ── Artistic palette presets ──────────────────────────────────────── + "neon": { + "contrast": 1.8, "color": 1.6, "sharpness": 1.2, + "posterize_bits": 5, "block": 6, "palette": "NEON_CYBER", + }, + "pastel": { + "contrast": 1.2, "color": 1.3, "sharpness": 1.1, + "posterize_bits": 6, "block": 6, "palette": "PASTEL_DREAM", + }, +} + + +def pixel_art(input_path, output_path, preset="arcade", **overrides): + """Convert an image to retro pixel art. + + Args: + input_path: path to source image + output_path: path to save the resulting PNG + preset: one of PRESETS (arcade, snes, nes, gameboy, pico8, c64, ...) + **overrides: optionally override any preset field. In particular: + palette: int (adaptive N colors) OR str (named palette from PALETTES) + block: int pixel block size + contrast / color / sharpness / posterize_bits: numeric enhancers + + Returns: + The resulting PIL.Image. + """ + if preset not in PRESETS: + raise ValueError( + f"Unknown preset {preset!r}. Choose from: {sorted(PRESETS)}" + ) + cfg = {**PRESETS[preset], **overrides} + + img = Image.open(input_path).convert("RGB") + + img = ImageEnhance.Contrast(img).enhance(cfg["contrast"]) + img = ImageEnhance.Color(img).enhance(cfg["color"]) + img = ImageEnhance.Sharpness(img).enhance(cfg["sharpness"]) + img = ImageOps.posterize(img, cfg["posterize_bits"]) + + w, h = img.size + block = cfg["block"] + small = img.resize( + (max(1, w // block), max(1, h // block)), + Image.NEAREST, + ) + + # Quantize AFTER downscale so Floyd-Steinberg aligns with final pixel grid. + pal = cfg["palette"] + if isinstance(pal, str): + # Named hardware/artistic palette + pal_img = build_palette_image(pal) + quantized = small.quantize(palette=pal_img, dither=Image.FLOYDSTEINBERG) + else: + # Adaptive N-color palette (original behavior) + quantized = small.quantize(colors=int(pal), dither=Image.FLOYDSTEINBERG) + + result = quantized.resize((w, h), Image.NEAREST) + result.save(output_path, "PNG") + return result + + +def main(): + import argparse + p = argparse.ArgumentParser(description="Convert image to pixel art.") + p.add_argument("input") + p.add_argument("output") + p.add_argument("--preset", default="arcade", choices=sorted(PRESETS)) + p.add_argument("--palette", default=None, + help=f"Override palette: int or name from {sorted(PALETTES)}") + p.add_argument("--block", type=int, default=None) + args = p.parse_args() + + overrides = {} + if args.palette is not None: + try: + overrides["palette"] = int(args.palette) + except ValueError: + overrides["palette"] = args.palette + if args.block is not None: + overrides["block"] = args.block + + pixel_art(args.input, args.output, preset=args.preset, **overrides) + print(f"Wrote {args.output}") + + +if __name__ == "__main__": + main() diff --git a/mateclaw-server/src/main/resources/skills/pixel-art/scripts/pixel_art_video.py b/mateclaw-server/src/main/resources/skills/pixel-art/scripts/pixel_art_video.py new file mode 100644 index 00000000..3721c193 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/pixel-art/scripts/pixel_art_video.py @@ -0,0 +1,345 @@ +"""Pixel art video — overlay procedural animations onto a source image. + +Takes any image (typically pre-processed with pixel_art()) and overlays +animated pixel effects (stars, rain, fireflies, etc.), then encodes to MP4 +(and optionally GIF) via ffmpeg. + +Scene animations ported from pixel-art-studio (MIT) — see ATTRIBUTION.md. +The generative/Pollinations code is intentionally dropped — the agent uses +`image_generate` + `pixel_art()` for base frames instead. + +Usage (import): + from pixel_art_video import pixel_art_video + pixel_art_video("frame.png", "out.mp4", scene="night", duration=6) + +Usage (CLI): + python pixel_art_video.py frame.png out.mp4 --scene night --duration 6 --gif +""" + +import math +import os +import random +import shutil +import subprocess +import tempfile + +from PIL import Image, ImageDraw + + +# ── Pixel drawing helpers ────────────────────────────────────────────── + +def _px(draw, x, y, color, size=2): + x, y = int(x), int(y) + W, H = draw.im.size + if 0 <= x < W and 0 <= y < H: + draw.rectangle([x, y, x + size - 1, y + size - 1], fill=color) + + +def _pixel_cross(draw, x, y, color, arm=2): + x, y = int(x), int(y) + for i in range(-arm, arm + 1): + _px(draw, x + i, y, color, 1) + _px(draw, x, y + i, color, 1) + + +# ── Animation init/draw pairs ────────────────────────────────────────── + +def init_stars(rng, W, H): + return [(rng.randint(0, W), rng.randint(0, H // 2)) for _ in range(15)] + +def draw_stars(draw, stars, t, W, H): + for i, (sx, sy) in enumerate(stars): + if math.sin(t * 2.0 + i * 0.7) > 0.65: + _pixel_cross(draw, sx, sy, (255, 255, 220), arm=2) + + +def init_fireflies(rng, W, H): + return [{"x": rng.randint(20, W - 20), "y": rng.randint(H // 4, H - 20), + "phase": rng.uniform(0, 6.28), "speed": rng.uniform(0.3, 0.8)} + for _ in range(10)] + +def draw_fireflies(draw, ff, t, W, H): + for f in ff: + if math.sin(t * 1.5 + f["phase"]) < 0.15: + continue + _px(draw, + f["x"] + math.sin(t * f["speed"] + f["phase"]) * 3, + f["y"] + math.cos(t * f["speed"] * 0.7) * 2, + (200, 255, 100), 2) + + +def init_leaves(rng, W, H): + return [{"x": rng.randint(0, W), "y": rng.randint(-H, 0), + "speed": rng.uniform(0.5, 1.5), "wobble": rng.uniform(0.02, 0.05), + "phase": rng.uniform(0, 6.28), + "color": rng.choice([(180, 120, 50), (160, 100, 40), (200, 140, 60)])} + for _ in range(12)] + +def draw_leaves(draw, leaves, t, W, H): + for leaf in leaves: + _px(draw, + leaf["x"] + math.sin(t * leaf["wobble"] + leaf["phase"]) * 15, + (leaf["y"] + t * leaf["speed"] * 20) % (H + 40) - 20, + leaf["color"], 2) + + +def init_dust_motes(rng, W, H): + return [{"x": rng.randint(30, W - 30), "y": rng.randint(30, H - 30), + "phase": rng.uniform(0, 6.28), "speed": rng.uniform(0.2, 0.5), + "amp": rng.uniform(2, 6)} for _ in range(20)] + +def draw_dust_motes(draw, motes, t, W, H): + for m in motes: + if math.sin(t * 2.0 + m["phase"]) > 0.3: + _px(draw, + m["x"] + math.sin(t * 0.3 + m["phase"]) * m["amp"], + m["y"] - (m["speed"] * t * 15) % H, + (255, 210, 100), 1) + + +def init_sparkles(rng, W, H): + return [(rng.randint(W // 4, 3 * W // 4), rng.randint(H // 4, 3 * H // 4), + rng.uniform(0, 6.28), + rng.choice([(180, 200, 255), (255, 220, 150), (200, 180, 255)])) + for _ in range(10)] + +def draw_sparkles(draw, sparkles, t, W, H): + for sx, sy, phase, color in sparkles: + if math.sin(t * 1.8 + phase) > 0.6: + _pixel_cross(draw, sx, sy, color, arm=2) + + +def init_rain(rng, W, H): + return [{"x": rng.randint(0, W), "y": rng.randint(0, H), + "speed": rng.uniform(4, 8)} for _ in range(30)] + +def draw_rain(draw, rain, t, W, H): + for r in rain: + y = (r["y"] + t * r["speed"] * 20) % H + _px(draw, r["x"], y, (120, 150, 200), 1) + _px(draw, r["x"], y + 4, (100, 130, 180), 1) + + +def init_lightning(rng, W, H): + return {"timer": 0, "flash": False, "rng": rng} + +def draw_lightning(draw, state, t, W, H): + state["timer"] += 1 + if state["timer"] > 45 and state["rng"].random() < 0.04: + state["flash"] = True + state["timer"] = 0 + if state["flash"]: + for x in range(0, W, 4): + for y in range(0, H // 3, 3): + if state["rng"].random() < 0.12: + _px(draw, x, y, (255, 255, 240), 2) + state["flash"] = False + + +def init_bubbles(rng, W, H): + return [{"x": rng.randint(20, W - 20), "y": rng.randint(H, H * 2), + "speed": rng.uniform(0.3, 0.8), "size": rng.choice([1, 2, 2])} + for _ in range(15)] + +def draw_bubbles(draw, bubbles, t, W, H): + for b in bubbles: + x = b["x"] + math.sin(t * 0.5 + b["x"]) * 3 + y = b["y"] - (t * b["speed"] * 20) % (H + 40) + if 0 < y < H: + _px(draw, x, y, (150, 200, 255), b["size"]) + + +def init_embers(rng, W, H): + return [{"x": rng.randint(0, W), "y": rng.randint(0, H), + "speed": rng.uniform(0.3, 0.9), "phase": rng.uniform(0, 6.28), + "color": rng.choice([(255, 150, 30), (255, 100, 20), (255, 200, 50)])} + for _ in range(18)] + +def draw_embers(draw, embers, t, W, H): + for e in embers: + x = e["x"] + math.sin(t * 0.4 + e["phase"]) * 5 + y = e["y"] - (t * e["speed"] * 15) % H + if math.sin(t * 2.5 + e["phase"]) > 0.2: + _px(draw, x, y, e["color"], 2) + + +def init_snowflakes(rng, W, H): + return [{"x": rng.randint(0, W), "y": rng.randint(-H, 0), + "speed": rng.uniform(0.3, 0.6), "wobble": rng.uniform(0.04, 0.09), + "size": rng.choice([2, 2, 3])} + for _ in range(40)] + +def draw_snowflakes(draw, flakes, t, W, H): + for f in flakes: + x = f["x"] + math.sin(t * f["wobble"] + f["x"]) * 20 + y = (f["y"] + t * f["speed"] * 8) % (H + 20) - 10 + if f["size"] >= 3: + _pixel_cross(draw, x, y, (230, 235, 255), arm=1) + else: + _px(draw, x, y, (230, 235, 255), 2) + + +def init_neon_pulse(rng, W, H): + return [(rng.randint(0, W), rng.randint(0, H), rng.uniform(0, 6.28), + rng.choice([(255, 0, 200), (0, 255, 255), (255, 50, 150)])) + for _ in range(8)] + +def draw_neon_pulse(draw, points, t, W, H): + for x, y, phase, color in points: + if math.sin(t * 2.5 + phase) > 0.5: + _pixel_cross(draw, x, y, color, arm=3) + + +def init_heat_shimmer(rng, W, H): + return [{"x": rng.randint(0, W), "y": rng.randint(H // 2, H), + "phase": rng.uniform(0, 6.28)} for _ in range(12)] + +def draw_heat_shimmer(draw, points, t, W, H): + for p in points: + x = p["x"] + math.sin(t * 0.8 + p["phase"]) * 2 + y = p["y"] + math.sin(t * 1.2 + p["phase"]) * 1 + if abs(math.sin(t * 1.5 + p["phase"])) > 0.6: + _px(draw, x, y, (255, 200, 100), 1) + + +# ── Scene → animation mapping ────────────────────────────────────────── + +SCENES = { + "night": ["stars", "fireflies", "leaves"], + "dusk": ["fireflies", "sparkles"], + "tavern": ["dust_motes", "sparkles"], + "indoor": ["dust_motes"], + "urban": ["rain", "neon_pulse"], + "nature": ["leaves", "fireflies"], + "magic": ["sparkles", "fireflies"], + "storm": ["rain", "lightning"], + "underwater": ["bubbles", "sparkles"], + "fire": ["embers", "sparkles"], + "snow": ["snowflakes", "sparkles"], + "desert": ["heat_shimmer", "dust_motes"], +} + +# Map scene layer name to (init_fn, draw_fn). +_LAYERS = { + "stars": (init_stars, draw_stars), + "fireflies": (init_fireflies, draw_fireflies), + "leaves": (init_leaves, draw_leaves), + "dust_motes": (init_dust_motes, draw_dust_motes), + "sparkles": (init_sparkles, draw_sparkles), + "rain": (init_rain, draw_rain), + "lightning": (init_lightning, draw_lightning), + "bubbles": (init_bubbles, draw_bubbles), + "embers": (init_embers, draw_embers), + "snowflakes": (init_snowflakes, draw_snowflakes), + "neon_pulse": (init_neon_pulse, draw_neon_pulse), + "heat_shimmer": (init_heat_shimmer, draw_heat_shimmer), +} + + +def _ensure_ffmpeg(): + if shutil.which("ffmpeg") is None: + raise RuntimeError( + "ffmpeg not found on PATH. Install via your package manager or " + "download from https://ffmpeg.org/" + ) + + +def pixel_art_video( + base_image, + output_path, + scene="night", + duration=6, + fps=15, + seed=None, + export_gif=False, +): + """Overlay pixel animations onto a base image and encode to MP4. + + Args: + base_image: path to source image (ideally already pixel-art styled) + output_path: path to MP4 output (GIF sibling written if export_gif=True) + scene: key from SCENES (night, urban, storm, snow, fire, ...) + duration: seconds of animation + fps: frames per second (default 15 for retro feel) + seed: optional int for reproducible animation placement + export_gif: also write a GIF alongside the MP4 + + Returns: + (mp4_path, gif_path_or_None) + """ + if scene not in SCENES: + raise ValueError( + f"Unknown scene {scene!r}. Choose from: {sorted(SCENES)}" + ) + _ensure_ffmpeg() + + base = Image.open(base_image).convert("RGB") + W, H = base.size + + rng = random.Random(seed if seed is not None else 42) + layers = [] + for name in SCENES[scene]: + init_fn, draw_fn = _LAYERS[name] + layers.append((draw_fn, init_fn(rng, W, H))) + + n_frames = fps * duration + os.makedirs(os.path.dirname(os.path.abspath(output_path)) or ".", exist_ok=True) + + with tempfile.TemporaryDirectory(prefix="pixelart_frames_") as frames_dir: + for frame_idx in range(n_frames): + canvas = base.copy() + draw = ImageDraw.Draw(canvas) + t = frame_idx / fps + for draw_fn, state in layers: + draw_fn(draw, state, t, W, H) + canvas.save(os.path.join(frames_dir, f"frame_{frame_idx:04d}.png")) + + subprocess.run( + ["ffmpeg", "-y", "-loglevel", "error", + "-framerate", str(fps), + "-i", os.path.join(frames_dir, "frame_%04d.png"), + "-c:v", "libx264", "-pix_fmt", "yuv420p", "-crf", "18", + output_path], + check=True, + ) + + gif_path = None + if export_gif: + gif_path = output_path.rsplit(".", 1)[0] + ".gif" + subprocess.run( + ["ffmpeg", "-y", "-loglevel", "error", + "-framerate", str(fps), + "-i", os.path.join(frames_dir, "frame_%04d.png"), + "-vf", + "scale=320:-1:flags=neighbor,split[s0][s1];[s0]palettegen[p];[s1][p]paletteuse", + "-loop", "0", + gif_path], + check=True, + ) + + return output_path, gif_path + + +def main(): + import argparse + p = argparse.ArgumentParser(description="Overlay pixel animations onto an image → MP4.") + p.add_argument("base_image") + p.add_argument("output") + p.add_argument("--scene", default="night", choices=sorted(SCENES)) + p.add_argument("--duration", type=int, default=6) + p.add_argument("--fps", type=int, default=15) + p.add_argument("--seed", type=int, default=None) + p.add_argument("--gif", action="store_true") + args = p.parse_args() + mp4, gif = pixel_art_video( + args.base_image, args.output, + scene=args.scene, duration=args.duration, + fps=args.fps, seed=args.seed, export_gif=args.gif, + ) + print(f"Wrote {mp4}") + if gif: + print(f"Wrote {gif}") + + +if __name__ == "__main__": + main() diff --git a/mateclaw-server/src/main/resources/skills/pptx/scripts/__init__.py b/mateclaw-server/src/main/resources/skills/pptx/scripts/__init__.py new file mode 100644 index 00000000..e69de29b diff --git a/mateclaw-server/src/main/resources/skills/pptx/scripts/add_slide.py b/mateclaw-server/src/main/resources/skills/pptx/scripts/add_slide.py new file mode 100755 index 00000000..13700df0 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/pptx/scripts/add_slide.py @@ -0,0 +1,195 @@ +"""Add a new slide to an unpacked PPTX directory. + +Usage: python add_slide.py + +The source can be: + - A slide file (e.g., slide2.xml) - duplicates the slide + - A layout file (e.g., slideLayout2.xml) - creates from layout + +Examples: + python add_slide.py unpacked/ slide2.xml + # Duplicates slide2, creates slide5.xml + + python add_slide.py unpacked/ slideLayout2.xml + # Creates slide5.xml from slideLayout2.xml + +To see available layouts: ls unpacked/ppt/slideLayouts/ + +Prints the element to add to presentation.xml. +""" + +import re +import shutil +import sys +from pathlib import Path + + +def get_next_slide_number(slides_dir: Path) -> int: + existing = [int(m.group(1)) for f in slides_dir.glob("slide*.xml") + if (m := re.match(r"slide(\d+)\.xml", f.name))] + return max(existing) + 1 if existing else 1 + + +def create_slide_from_layout(unpacked_dir: Path, layout_file: str) -> None: + slides_dir = unpacked_dir / "ppt" / "slides" + rels_dir = slides_dir / "_rels" + layouts_dir = unpacked_dir / "ppt" / "slideLayouts" + + layout_path = layouts_dir / layout_file + if not layout_path.exists(): + print(f"Error: {layout_path} not found", file=sys.stderr) + sys.exit(1) + + next_num = get_next_slide_number(slides_dir) + dest = f"slide{next_num}.xml" + dest_slide = slides_dir / dest + dest_rels = rels_dir / f"{dest}.rels" + + slide_xml = ''' + + + + + + + + + + + + + + + + + + + + + +''' + dest_slide.write_text(slide_xml, encoding="utf-8") + + rels_dir.mkdir(exist_ok=True) + rels_xml = f''' + + +''' + dest_rels.write_text(rels_xml, encoding="utf-8") + + _add_to_content_types(unpacked_dir, dest) + + rid = _add_to_presentation_rels(unpacked_dir, dest) + + next_slide_id = _get_next_slide_id(unpacked_dir) + + print(f"Created {dest} from {layout_file}") + print(f'Add to presentation.xml : ') + + +def duplicate_slide(unpacked_dir: Path, source: str) -> None: + slides_dir = unpacked_dir / "ppt" / "slides" + rels_dir = slides_dir / "_rels" + + source_slide = slides_dir / source + + if not source_slide.exists(): + print(f"Error: {source_slide} not found", file=sys.stderr) + sys.exit(1) + + next_num = get_next_slide_number(slides_dir) + dest = f"slide{next_num}.xml" + dest_slide = slides_dir / dest + + source_rels = rels_dir / f"{source}.rels" + dest_rels = rels_dir / f"{dest}.rels" + + shutil.copy2(source_slide, dest_slide) + + if source_rels.exists(): + shutil.copy2(source_rels, dest_rels) + + rels_content = dest_rels.read_text(encoding="utf-8") + rels_content = re.sub( + r'\s*]*Type="[^"]*notesSlide"[^>]*/>\s*', + "\n", + rels_content, + ) + dest_rels.write_text(rels_content, encoding="utf-8") + + _add_to_content_types(unpacked_dir, dest) + + rid = _add_to_presentation_rels(unpacked_dir, dest) + + next_slide_id = _get_next_slide_id(unpacked_dir) + + print(f"Created {dest} from {source}") + print(f'Add to presentation.xml : ') + + +def _add_to_content_types(unpacked_dir: Path, dest: str) -> None: + content_types_path = unpacked_dir / "[Content_Types].xml" + content_types = content_types_path.read_text(encoding="utf-8") + + new_override = f'' + + if f"/ppt/slides/{dest}" not in content_types: + content_types = content_types.replace("", f" {new_override}\n") + content_types_path.write_text(content_types, encoding="utf-8") + + +def _add_to_presentation_rels(unpacked_dir: Path, dest: str) -> str: + pres_rels_path = unpacked_dir / "ppt" / "_rels" / "presentation.xml.rels" + pres_rels = pres_rels_path.read_text(encoding="utf-8") + + rids = [int(m) for m in re.findall(r'Id="rId(\d+)"', pres_rels)] + next_rid = max(rids) + 1 if rids else 1 + rid = f"rId{next_rid}" + + new_rel = f'' + + if f"slides/{dest}" not in pres_rels: + pres_rels = pres_rels.replace("", f" {new_rel}\n") + pres_rels_path.write_text(pres_rels, encoding="utf-8") + + return rid + + +def _get_next_slide_id(unpacked_dir: Path) -> int: + pres_path = unpacked_dir / "ppt" / "presentation.xml" + pres_content = pres_path.read_text(encoding="utf-8") + slide_ids = [int(m) for m in re.findall(r']*id="(\d+)"', pres_content)] + return max(slide_ids) + 1 if slide_ids else 256 + + +def parse_source(source: str) -> tuple[str, str | None]: + if source.startswith("slideLayout") and source.endswith(".xml"): + return ("layout", source) + + return ("slide", None) + + +if __name__ == "__main__": + if len(sys.argv) != 3: + print("Usage: python add_slide.py ", file=sys.stderr) + print("", file=sys.stderr) + print("Source can be:", file=sys.stderr) + print(" slide2.xml - duplicate an existing slide", file=sys.stderr) + print(" slideLayout2.xml - create from a layout template", file=sys.stderr) + print("", file=sys.stderr) + print("To see available layouts: ls /ppt/slideLayouts/", file=sys.stderr) + sys.exit(1) + + unpacked_dir = Path(sys.argv[1]) + source = sys.argv[2] + + if not unpacked_dir.exists(): + print(f"Error: {unpacked_dir} not found", file=sys.stderr) + sys.exit(1) + + source_type, layout_file = parse_source(source) + + if source_type == "layout" and layout_file is not None: + create_slide_from_layout(unpacked_dir, layout_file) + else: + duplicate_slide(unpacked_dir, source) diff --git a/mateclaw-server/src/main/resources/skills/pptx/scripts/clean.py b/mateclaw-server/src/main/resources/skills/pptx/scripts/clean.py new file mode 100755 index 00000000..3d13994c --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/pptx/scripts/clean.py @@ -0,0 +1,286 @@ +"""Remove unreferenced files from an unpacked PPTX directory. + +Usage: python clean.py + +Example: + python clean.py unpacked/ + +This script removes: +- Orphaned slides (not in sldIdLst) and their relationships +- [trash] directory (unreferenced files) +- Orphaned .rels files for deleted resources +- Unreferenced media, embeddings, charts, diagrams, drawings, ink files +- Unreferenced theme files +- Unreferenced notes slides +- Content-Type overrides for deleted files +""" + +import sys +from pathlib import Path + +import defusedxml.minidom + + +import re + + +def get_slides_in_sldidlst(unpacked_dir: Path) -> set[str]: + pres_path = unpacked_dir / "ppt" / "presentation.xml" + pres_rels_path = unpacked_dir / "ppt" / "_rels" / "presentation.xml.rels" + + if not pres_path.exists() or not pres_rels_path.exists(): + return set() + + rels_dom = defusedxml.minidom.parse(str(pres_rels_path)) + rid_to_slide = {} + for rel in rels_dom.getElementsByTagName("Relationship"): + rid = rel.getAttribute("Id") + target = rel.getAttribute("Target") + rel_type = rel.getAttribute("Type") + if "slide" in rel_type and target.startswith("slides/"): + rid_to_slide[rid] = target.replace("slides/", "") + + pres_content = pres_path.read_text(encoding="utf-8") + referenced_rids = set(re.findall(r']*r:id="([^"]+)"', pres_content)) + + return {rid_to_slide[rid] for rid in referenced_rids if rid in rid_to_slide} + + +def remove_orphaned_slides(unpacked_dir: Path) -> list[str]: + slides_dir = unpacked_dir / "ppt" / "slides" + slides_rels_dir = slides_dir / "_rels" + pres_rels_path = unpacked_dir / "ppt" / "_rels" / "presentation.xml.rels" + + if not slides_dir.exists(): + return [] + + referenced_slides = get_slides_in_sldidlst(unpacked_dir) + removed = [] + + for slide_file in slides_dir.glob("slide*.xml"): + if slide_file.name not in referenced_slides: + rel_path = slide_file.relative_to(unpacked_dir) + slide_file.unlink() + removed.append(str(rel_path)) + + rels_file = slides_rels_dir / f"{slide_file.name}.rels" + if rels_file.exists(): + rels_file.unlink() + removed.append(str(rels_file.relative_to(unpacked_dir))) + + if removed and pres_rels_path.exists(): + rels_dom = defusedxml.minidom.parse(str(pres_rels_path)) + changed = False + + for rel in list(rels_dom.getElementsByTagName("Relationship")): + target = rel.getAttribute("Target") + if target.startswith("slides/"): + slide_name = target.replace("slides/", "") + if slide_name not in referenced_slides: + if rel.parentNode: + rel.parentNode.removeChild(rel) + changed = True + + if changed: + with open(pres_rels_path, "wb") as f: + f.write(rels_dom.toxml(encoding="utf-8")) + + return removed + + +def remove_trash_directory(unpacked_dir: Path) -> list[str]: + trash_dir = unpacked_dir / "[trash]" + removed = [] + + if trash_dir.exists() and trash_dir.is_dir(): + for file_path in trash_dir.iterdir(): + if file_path.is_file(): + rel_path = file_path.relative_to(unpacked_dir) + removed.append(str(rel_path)) + file_path.unlink() + trash_dir.rmdir() + + return removed + + +def get_slide_referenced_files(unpacked_dir: Path) -> set: + referenced = set() + slides_rels_dir = unpacked_dir / "ppt" / "slides" / "_rels" + + if not slides_rels_dir.exists(): + return referenced + + for rels_file in slides_rels_dir.glob("*.rels"): + dom = defusedxml.minidom.parse(str(rels_file)) + for rel in dom.getElementsByTagName("Relationship"): + target = rel.getAttribute("Target") + if not target: + continue + target_path = (rels_file.parent.parent / target).resolve() + try: + referenced.add(target_path.relative_to(unpacked_dir.resolve())) + except ValueError: + pass + + return referenced + + +def remove_orphaned_rels_files(unpacked_dir: Path) -> list[str]: + resource_dirs = ["charts", "diagrams", "drawings"] + removed = [] + slide_referenced = get_slide_referenced_files(unpacked_dir) + + for dir_name in resource_dirs: + rels_dir = unpacked_dir / "ppt" / dir_name / "_rels" + if not rels_dir.exists(): + continue + + for rels_file in rels_dir.glob("*.rels"): + resource_file = rels_dir.parent / rels_file.name.replace(".rels", "") + try: + resource_rel_path = resource_file.resolve().relative_to(unpacked_dir.resolve()) + except ValueError: + continue + + if not resource_file.exists() or resource_rel_path not in slide_referenced: + rels_file.unlink() + rel_path = rels_file.relative_to(unpacked_dir) + removed.append(str(rel_path)) + + return removed + + +def get_referenced_files(unpacked_dir: Path) -> set: + referenced = set() + + for rels_file in unpacked_dir.rglob("*.rels"): + dom = defusedxml.minidom.parse(str(rels_file)) + for rel in dom.getElementsByTagName("Relationship"): + target = rel.getAttribute("Target") + if not target: + continue + target_path = (rels_file.parent.parent / target).resolve() + try: + referenced.add(target_path.relative_to(unpacked_dir.resolve())) + except ValueError: + pass + + return referenced + + +def remove_orphaned_files(unpacked_dir: Path, referenced: set) -> list[str]: + resource_dirs = ["media", "embeddings", "charts", "diagrams", "tags", "drawings", "ink"] + removed = [] + + for dir_name in resource_dirs: + dir_path = unpacked_dir / "ppt" / dir_name + if not dir_path.exists(): + continue + + for file_path in dir_path.glob("*"): + if not file_path.is_file(): + continue + rel_path = file_path.relative_to(unpacked_dir) + if rel_path not in referenced: + file_path.unlink() + removed.append(str(rel_path)) + + theme_dir = unpacked_dir / "ppt" / "theme" + if theme_dir.exists(): + for file_path in theme_dir.glob("theme*.xml"): + rel_path = file_path.relative_to(unpacked_dir) + if rel_path not in referenced: + file_path.unlink() + removed.append(str(rel_path)) + theme_rels = theme_dir / "_rels" / f"{file_path.name}.rels" + if theme_rels.exists(): + theme_rels.unlink() + removed.append(str(theme_rels.relative_to(unpacked_dir))) + + notes_dir = unpacked_dir / "ppt" / "notesSlides" + if notes_dir.exists(): + for file_path in notes_dir.glob("*.xml"): + if not file_path.is_file(): + continue + rel_path = file_path.relative_to(unpacked_dir) + if rel_path not in referenced: + file_path.unlink() + removed.append(str(rel_path)) + + notes_rels_dir = notes_dir / "_rels" + if notes_rels_dir.exists(): + for file_path in notes_rels_dir.glob("*.rels"): + notes_file = notes_dir / file_path.name.replace(".rels", "") + if not notes_file.exists(): + file_path.unlink() + removed.append(str(file_path.relative_to(unpacked_dir))) + + return removed + + +def update_content_types(unpacked_dir: Path, removed_files: list[str]) -> None: + ct_path = unpacked_dir / "[Content_Types].xml" + if not ct_path.exists(): + return + + dom = defusedxml.minidom.parse(str(ct_path)) + changed = False + + for override in list(dom.getElementsByTagName("Override")): + part_name = override.getAttribute("PartName").lstrip("/") + if part_name in removed_files: + if override.parentNode: + override.parentNode.removeChild(override) + changed = True + + if changed: + with open(ct_path, "wb") as f: + f.write(dom.toxml(encoding="utf-8")) + + +def clean_unused_files(unpacked_dir: Path) -> list[str]: + all_removed = [] + + slides_removed = remove_orphaned_slides(unpacked_dir) + all_removed.extend(slides_removed) + + trash_removed = remove_trash_directory(unpacked_dir) + all_removed.extend(trash_removed) + + while True: + removed_rels = remove_orphaned_rels_files(unpacked_dir) + referenced = get_referenced_files(unpacked_dir) + removed_files = remove_orphaned_files(unpacked_dir, referenced) + + total_removed = removed_rels + removed_files + if not total_removed: + break + + all_removed.extend(total_removed) + + if all_removed: + update_content_types(unpacked_dir, all_removed) + + return all_removed + + +if __name__ == "__main__": + if len(sys.argv) != 2: + print("Usage: python clean.py ", file=sys.stderr) + print("Example: python clean.py unpacked/", file=sys.stderr) + sys.exit(1) + + unpacked_dir = Path(sys.argv[1]) + + if not unpacked_dir.exists(): + print(f"Error: {unpacked_dir} not found", file=sys.stderr) + sys.exit(1) + + removed = clean_unused_files(unpacked_dir) + + if removed: + print(f"Removed {len(removed)} unreferenced files:") + for f in removed: + print(f" {f}") + else: + print("No unreferenced files found") diff --git a/mateclaw-server/src/main/resources/skills/pptx/scripts/office/helpers/__init__.py b/mateclaw-server/src/main/resources/skills/pptx/scripts/office/helpers/__init__.py new file mode 100644 index 00000000..e69de29b diff --git a/mateclaw-server/src/main/resources/skills/pptx/scripts/office/helpers/merge_runs.py b/mateclaw-server/src/main/resources/skills/pptx/scripts/office/helpers/merge_runs.py new file mode 100644 index 00000000..ad7c25ee --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/pptx/scripts/office/helpers/merge_runs.py @@ -0,0 +1,199 @@ +"""Merge adjacent runs with identical formatting in DOCX. + +Merges adjacent elements that have identical properties. +Works on runs in paragraphs and inside tracked changes (, ). + +Also: +- Removes rsid attributes from runs (revision metadata that doesn't affect rendering) +- Removes proofErr elements (spell/grammar markers that block merging) +""" + +from pathlib import Path + +import defusedxml.minidom + + +def merge_runs(input_dir: str) -> tuple[int, str]: + doc_xml = Path(input_dir) / "word" / "document.xml" + + if not doc_xml.exists(): + return 0, f"Error: {doc_xml} not found" + + try: + dom = defusedxml.minidom.parseString(doc_xml.read_text(encoding="utf-8")) + root = dom.documentElement + + _remove_elements(root, "proofErr") + _strip_run_rsid_attrs(root) + + containers = {run.parentNode for run in _find_elements(root, "r")} + + merge_count = 0 + for container in containers: + merge_count += _merge_runs_in(container) + + doc_xml.write_bytes(dom.toxml(encoding="UTF-8")) + return merge_count, f"Merged {merge_count} runs" + + except Exception as e: + return 0, f"Error: {e}" + + + + +def _find_elements(root, tag: str) -> list: + results = [] + + def traverse(node): + if node.nodeType == node.ELEMENT_NODE: + name = node.localName or node.tagName + if name == tag or name.endswith(f":{tag}"): + results.append(node) + for child in node.childNodes: + traverse(child) + + traverse(root) + return results + + +def _get_child(parent, tag: str): + for child in parent.childNodes: + if child.nodeType == child.ELEMENT_NODE: + name = child.localName or child.tagName + if name == tag or name.endswith(f":{tag}"): + return child + return None + + +def _get_children(parent, tag: str) -> list: + results = [] + for child in parent.childNodes: + if child.nodeType == child.ELEMENT_NODE: + name = child.localName or child.tagName + if name == tag or name.endswith(f":{tag}"): + results.append(child) + return results + + +def _is_adjacent(elem1, elem2) -> bool: + node = elem1.nextSibling + while node: + if node == elem2: + return True + if node.nodeType == node.ELEMENT_NODE: + return False + if node.nodeType == node.TEXT_NODE and node.data.strip(): + return False + node = node.nextSibling + return False + + + + +def _remove_elements(root, tag: str): + for elem in _find_elements(root, tag): + if elem.parentNode: + elem.parentNode.removeChild(elem) + + +def _strip_run_rsid_attrs(root): + for run in _find_elements(root, "r"): + for attr in list(run.attributes.values()): + if "rsid" in attr.name.lower(): + run.removeAttribute(attr.name) + + + + +def _merge_runs_in(container) -> int: + merge_count = 0 + run = _first_child_run(container) + + while run: + while True: + next_elem = _next_element_sibling(run) + if next_elem and _is_run(next_elem) and _can_merge(run, next_elem): + _merge_run_content(run, next_elem) + container.removeChild(next_elem) + merge_count += 1 + else: + break + + _consolidate_text(run) + run = _next_sibling_run(run) + + return merge_count + + +def _first_child_run(container): + for child in container.childNodes: + if child.nodeType == child.ELEMENT_NODE and _is_run(child): + return child + return None + + +def _next_element_sibling(node): + sibling = node.nextSibling + while sibling: + if sibling.nodeType == sibling.ELEMENT_NODE: + return sibling + sibling = sibling.nextSibling + return None + + +def _next_sibling_run(node): + sibling = node.nextSibling + while sibling: + if sibling.nodeType == sibling.ELEMENT_NODE: + if _is_run(sibling): + return sibling + sibling = sibling.nextSibling + return None + + +def _is_run(node) -> bool: + name = node.localName or node.tagName + return name == "r" or name.endswith(":r") + + +def _can_merge(run1, run2) -> bool: + rpr1 = _get_child(run1, "rPr") + rpr2 = _get_child(run2, "rPr") + + if (rpr1 is None) != (rpr2 is None): + return False + if rpr1 is None: + return True + return rpr1.toxml() == rpr2.toxml() + + +def _merge_run_content(target, source): + for child in list(source.childNodes): + if child.nodeType == child.ELEMENT_NODE: + name = child.localName or child.tagName + if name != "rPr" and not name.endswith(":rPr"): + target.appendChild(child) + + +def _consolidate_text(run): + t_elements = _get_children(run, "t") + + for i in range(len(t_elements) - 1, 0, -1): + curr, prev = t_elements[i], t_elements[i - 1] + + if _is_adjacent(prev, curr): + prev_text = prev.firstChild.data if prev.firstChild else "" + curr_text = curr.firstChild.data if curr.firstChild else "" + merged = prev_text + curr_text + + if prev.firstChild: + prev.firstChild.data = merged + else: + prev.appendChild(run.ownerDocument.createTextNode(merged)) + + if merged.startswith(" ") or merged.endswith(" "): + prev.setAttribute("xml:space", "preserve") + elif prev.hasAttribute("xml:space"): + prev.removeAttribute("xml:space") + + run.removeChild(curr) diff --git a/mateclaw-server/src/main/resources/skills/pptx/scripts/office/helpers/simplify_redlines.py b/mateclaw-server/src/main/resources/skills/pptx/scripts/office/helpers/simplify_redlines.py new file mode 100644 index 00000000..db963bb9 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/pptx/scripts/office/helpers/simplify_redlines.py @@ -0,0 +1,197 @@ +"""Simplify tracked changes by merging adjacent w:ins or w:del elements. + +Merges adjacent elements from the same author into a single element. +Same for elements. This makes heavily-redlined documents easier to +work with by reducing the number of tracked change wrappers. + +Rules: +- Only merges w:ins with w:ins, w:del with w:del (same element type) +- Only merges if same author (ignores timestamp differences) +- Only merges if truly adjacent (only whitespace between them) +""" + +import xml.etree.ElementTree as ET +import zipfile +from pathlib import Path + +import defusedxml.minidom + +WORD_NS = "http://schemas.openxmlformats.org/wordprocessingml/2006/main" + + +def simplify_redlines(input_dir: str) -> tuple[int, str]: + doc_xml = Path(input_dir) / "word" / "document.xml" + + if not doc_xml.exists(): + return 0, f"Error: {doc_xml} not found" + + try: + dom = defusedxml.minidom.parseString(doc_xml.read_text(encoding="utf-8")) + root = dom.documentElement + + merge_count = 0 + + containers = _find_elements(root, "p") + _find_elements(root, "tc") + + for container in containers: + merge_count += _merge_tracked_changes_in(container, "ins") + merge_count += _merge_tracked_changes_in(container, "del") + + doc_xml.write_bytes(dom.toxml(encoding="UTF-8")) + return merge_count, f"Simplified {merge_count} tracked changes" + + except Exception as e: + return 0, f"Error: {e}" + + +def _merge_tracked_changes_in(container, tag: str) -> int: + merge_count = 0 + + tracked = [ + child + for child in container.childNodes + if child.nodeType == child.ELEMENT_NODE and _is_element(child, tag) + ] + + if len(tracked) < 2: + return 0 + + i = 0 + while i < len(tracked) - 1: + curr = tracked[i] + next_elem = tracked[i + 1] + + if _can_merge_tracked(curr, next_elem): + _merge_tracked_content(curr, next_elem) + container.removeChild(next_elem) + tracked.pop(i + 1) + merge_count += 1 + else: + i += 1 + + return merge_count + + +def _is_element(node, tag: str) -> bool: + name = node.localName or node.tagName + return name == tag or name.endswith(f":{tag}") + + +def _get_author(elem) -> str: + author = elem.getAttribute("w:author") + if not author: + for attr in elem.attributes.values(): + if attr.localName == "author" or attr.name.endswith(":author"): + return attr.value + return author + + +def _can_merge_tracked(elem1, elem2) -> bool: + if _get_author(elem1) != _get_author(elem2): + return False + + node = elem1.nextSibling + while node and node != elem2: + if node.nodeType == node.ELEMENT_NODE: + return False + if node.nodeType == node.TEXT_NODE and node.data.strip(): + return False + node = node.nextSibling + + return True + + +def _merge_tracked_content(target, source): + while source.firstChild: + child = source.firstChild + source.removeChild(child) + target.appendChild(child) + + +def _find_elements(root, tag: str) -> list: + results = [] + + def traverse(node): + if node.nodeType == node.ELEMENT_NODE: + name = node.localName or node.tagName + if name == tag or name.endswith(f":{tag}"): + results.append(node) + for child in node.childNodes: + traverse(child) + + traverse(root) + return results + + +def get_tracked_change_authors(doc_xml_path: Path) -> dict[str, int]: + if not doc_xml_path.exists(): + return {} + + try: + tree = ET.parse(doc_xml_path) + root = tree.getroot() + except ET.ParseError: + return {} + + namespaces = {"w": WORD_NS} + author_attr = f"{{{WORD_NS}}}author" + + authors: dict[str, int] = {} + for tag in ["ins", "del"]: + for elem in root.findall(f".//w:{tag}", namespaces): + author = elem.get(author_attr) + if author: + authors[author] = authors.get(author, 0) + 1 + + return authors + + +def _get_authors_from_docx(docx_path: Path) -> dict[str, int]: + try: + with zipfile.ZipFile(docx_path, "r") as zf: + if "word/document.xml" not in zf.namelist(): + return {} + with zf.open("word/document.xml") as f: + tree = ET.parse(f) + root = tree.getroot() + + namespaces = {"w": WORD_NS} + author_attr = f"{{{WORD_NS}}}author" + + authors: dict[str, int] = {} + for tag in ["ins", "del"]: + for elem in root.findall(f".//w:{tag}", namespaces): + author = elem.get(author_attr) + if author: + authors[author] = authors.get(author, 0) + 1 + return authors + except (zipfile.BadZipFile, ET.ParseError): + return {} + + +def infer_author(modified_dir: Path, original_docx: Path, default: str = "Claude") -> str: + modified_xml = modified_dir / "word" / "document.xml" + modified_authors = get_tracked_change_authors(modified_xml) + + if not modified_authors: + return default + + original_authors = _get_authors_from_docx(original_docx) + + new_changes: dict[str, int] = {} + for author, count in modified_authors.items(): + original_count = original_authors.get(author, 0) + diff = count - original_count + if diff > 0: + new_changes[author] = diff + + if not new_changes: + return default + + if len(new_changes) == 1: + return next(iter(new_changes)) + + raise ValueError( + f"Multiple authors added new changes: {new_changes}. " + "Cannot infer which author to validate." + ) diff --git a/mateclaw-server/src/main/resources/skills/pptx/scripts/office/pack.py b/mateclaw-server/src/main/resources/skills/pptx/scripts/office/pack.py new file mode 100755 index 00000000..db29ed8b --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/pptx/scripts/office/pack.py @@ -0,0 +1,159 @@ +"""Pack a directory into a DOCX, PPTX, or XLSX file. + +Validates with auto-repair, condenses XML formatting, and creates the Office file. + +Usage: + python pack.py [--original ] [--validate true|false] + +Examples: + python pack.py unpacked/ output.docx --original input.docx + python pack.py unpacked/ output.pptx --validate false +""" + +import argparse +import sys +import shutil +import tempfile +import zipfile +from pathlib import Path + +import defusedxml.minidom + +from validators import DOCXSchemaValidator, PPTXSchemaValidator, RedliningValidator + +def pack( + input_directory: str, + output_file: str, + original_file: str | None = None, + validate: bool = True, + infer_author_func=None, +) -> tuple[None, str]: + input_dir = Path(input_directory) + output_path = Path(output_file) + suffix = output_path.suffix.lower() + + if not input_dir.is_dir(): + return None, f"Error: {input_dir} is not a directory" + + if suffix not in {".docx", ".pptx", ".xlsx"}: + return None, f"Error: {output_file} must be a .docx, .pptx, or .xlsx file" + + if validate and original_file: + original_path = Path(original_file) + if original_path.exists(): + success, output = _run_validation( + input_dir, original_path, suffix, infer_author_func + ) + if output: + print(output) + if not success: + return None, f"Error: Validation failed for {input_dir}" + + with tempfile.TemporaryDirectory() as temp_dir: + temp_content_dir = Path(temp_dir) / "content" + shutil.copytree(input_dir, temp_content_dir) + + for pattern in ["*.xml", "*.rels"]: + for xml_file in temp_content_dir.rglob(pattern): + _condense_xml(xml_file) + + output_path.parent.mkdir(parents=True, exist_ok=True) + with zipfile.ZipFile(output_path, "w", zipfile.ZIP_DEFLATED) as zf: + for f in temp_content_dir.rglob("*"): + if f.is_file(): + zf.write(f, f.relative_to(temp_content_dir)) + + return None, f"Successfully packed {input_dir} to {output_file}" + + +def _run_validation( + unpacked_dir: Path, + original_file: Path, + suffix: str, + infer_author_func=None, +) -> tuple[bool, str | None]: + output_lines = [] + validators = [] + + if suffix == ".docx": + author = "Claude" + if infer_author_func: + try: + author = infer_author_func(unpacked_dir, original_file) + except ValueError as e: + print(f"Warning: {e} Using default author 'Claude'.", file=sys.stderr) + + validators = [ + DOCXSchemaValidator(unpacked_dir, original_file), + RedliningValidator(unpacked_dir, original_file, author=author), + ] + elif suffix == ".pptx": + validators = [PPTXSchemaValidator(unpacked_dir, original_file)] + + if not validators: + return True, None + + total_repairs = sum(v.repair() for v in validators) + if total_repairs: + output_lines.append(f"Auto-repaired {total_repairs} issue(s)") + + success = all(v.validate() for v in validators) + + if success: + output_lines.append("All validations PASSED!") + + return success, "\n".join(output_lines) if output_lines else None + + +def _condense_xml(xml_file: Path) -> None: + try: + with open(xml_file, encoding="utf-8") as f: + dom = defusedxml.minidom.parse(f) + + for element in dom.getElementsByTagName("*"): + if element.tagName.endswith(":t"): + continue + + for child in list(element.childNodes): + if ( + child.nodeType == child.TEXT_NODE + and child.nodeValue + and child.nodeValue.strip() == "" + ) or child.nodeType == child.COMMENT_NODE: + element.removeChild(child) + + xml_file.write_bytes(dom.toxml(encoding="UTF-8")) + except Exception as e: + print(f"ERROR: Failed to parse {xml_file.name}: {e}", file=sys.stderr) + raise + + +if __name__ == "__main__": + parser = argparse.ArgumentParser( + description="Pack a directory into a DOCX, PPTX, or XLSX file" + ) + parser.add_argument("input_directory", help="Unpacked Office document directory") + parser.add_argument("output_file", help="Output Office file (.docx/.pptx/.xlsx)") + parser.add_argument( + "--original", + help="Original file for validation comparison", + ) + parser.add_argument( + "--validate", + type=lambda x: x.lower() == "true", + default=True, + metavar="true|false", + help="Run validation with auto-repair (default: true)", + ) + args = parser.parse_args() + + _, message = pack( + args.input_directory, + args.output_file, + original_file=args.original, + validate=args.validate, + ) + print(message) + + if "Error" in message: + sys.exit(1) diff --git a/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-chart.xsd b/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-chart.xsd new file mode 100644 index 00000000..6454ef9a --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-chart.xsd @@ -0,0 +1,1499 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-chartDrawing.xsd b/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-chartDrawing.xsd new file mode 100644 index 00000000..afa4f463 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-chartDrawing.xsd @@ -0,0 +1,146 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-diagram.xsd b/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-diagram.xsd new file mode 100644 index 00000000..64e66b8a --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-diagram.xsd @@ -0,0 +1,1085 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-lockedCanvas.xsd b/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-lockedCanvas.xsd new file mode 100644 index 00000000..687eea82 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-lockedCanvas.xsd @@ -0,0 +1,11 @@ + + + + + diff --git a/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-main.xsd b/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-main.xsd new file mode 100644 index 00000000..6ac81b06 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-main.xsd @@ -0,0 +1,3081 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-picture.xsd b/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-picture.xsd new file mode 100644 index 00000000..1dbf0514 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-picture.xsd @@ -0,0 +1,23 @@ + + + + + + + + + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-spreadsheetDrawing.xsd b/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-spreadsheetDrawing.xsd new file mode 100644 index 00000000..f1af17db --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-spreadsheetDrawing.xsd @@ -0,0 +1,185 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-wordprocessingDrawing.xsd b/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-wordprocessingDrawing.xsd new file mode 100644 index 00000000..0a185ab6 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-wordprocessingDrawing.xsd @@ -0,0 +1,287 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/pml.xsd b/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/pml.xsd new file mode 100644 index 00000000..14ef4888 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/pml.xsd @@ -0,0 +1,1676 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-additionalCharacteristics.xsd b/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-additionalCharacteristics.xsd new file mode 100644 index 00000000..c20f3bf1 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-additionalCharacteristics.xsd @@ -0,0 +1,28 @@ + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-bibliography.xsd b/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-bibliography.xsd new file mode 100644 index 00000000..ac602522 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-bibliography.xsd @@ -0,0 +1,144 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-commonSimpleTypes.xsd b/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-commonSimpleTypes.xsd new file mode 100644 index 00000000..424b8ba8 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-commonSimpleTypes.xsd @@ -0,0 +1,174 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-customXmlDataProperties.xsd b/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-customXmlDataProperties.xsd new file mode 100644 index 00000000..2bddce29 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-customXmlDataProperties.xsd @@ -0,0 +1,25 @@ + + + + + + + + + + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-customXmlSchemaProperties.xsd b/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-customXmlSchemaProperties.xsd new file mode 100644 index 00000000..8a8c18ba --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-customXmlSchemaProperties.xsd @@ -0,0 +1,18 @@ + + + + + + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesCustom.xsd b/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesCustom.xsd new file mode 100644 index 00000000..5c42706a --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesCustom.xsd @@ -0,0 +1,59 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesExtended.xsd b/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesExtended.xsd new file mode 100644 index 00000000..853c341c --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesExtended.xsd @@ -0,0 +1,56 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesVariantTypes.xsd b/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesVariantTypes.xsd new file mode 100644 index 00000000..da835ee8 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesVariantTypes.xsd @@ -0,0 +1,195 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-math.xsd b/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-math.xsd new file mode 100644 index 00000000..87ad2658 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-math.xsd @@ -0,0 +1,582 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-relationshipReference.xsd b/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-relationshipReference.xsd new file mode 100644 index 00000000..9e86f1b2 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-relationshipReference.xsd @@ -0,0 +1,25 @@ + + + + + + + + + + + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/sml.xsd b/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/sml.xsd new file mode 100644 index 00000000..d0be42e7 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/sml.xsd @@ -0,0 +1,4439 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-main.xsd b/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-main.xsd new file mode 100644 index 00000000..8821dd18 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-main.xsd @@ -0,0 +1,570 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-officeDrawing.xsd b/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-officeDrawing.xsd new file mode 100644 index 00000000..ca2575c7 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-officeDrawing.xsd @@ -0,0 +1,509 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-presentationDrawing.xsd b/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-presentationDrawing.xsd new file mode 100644 index 00000000..dd079e60 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-presentationDrawing.xsd @@ -0,0 +1,12 @@ + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-spreadsheetDrawing.xsd b/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-spreadsheetDrawing.xsd new file mode 100644 index 00000000..3dd6cf62 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-spreadsheetDrawing.xsd @@ -0,0 +1,108 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-wordprocessingDrawing.xsd b/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-wordprocessingDrawing.xsd new file mode 100644 index 00000000..f1041e34 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-wordprocessingDrawing.xsd @@ -0,0 +1,96 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/wml.xsd b/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/wml.xsd new file mode 100644 index 00000000..9c5b7a63 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/wml.xsd @@ -0,0 +1,3646 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/xml.xsd b/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/xml.xsd new file mode 100644 index 00000000..0f13678d --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/ISO-IEC29500-4_2016/xml.xsd @@ -0,0 +1,116 @@ + + + + + + See http://www.w3.org/XML/1998/namespace.html and + http://www.w3.org/TR/REC-xml for information about this namespace. + + This schema document describes the XML namespace, in a form + suitable for import by other schema documents. + + Note that local names in this namespace are intended to be defined + only by the World Wide Web Consortium or its subgroups. The + following names are currently defined in this namespace and should + not be used with conflicting semantics by any Working Group, + specification, or document instance: + + base (as an attribute name): denotes an attribute whose value + provides a URI to be used as the base for interpreting any + relative URIs in the scope of the element on which it + appears; its value is inherited. This name is reserved + by virtue of its definition in the XML Base specification. + + lang (as an attribute name): denotes an attribute whose value + is a language code for the natural language of the content of + any element; its value is inherited. This name is reserved + by virtue of its definition in the XML specification. + + space (as an attribute name): denotes an attribute whose + value is a keyword indicating what whitespace processing + discipline is intended for the content of the element; its + value is inherited. This name is reserved by virtue of its + definition in the XML specification. + + Father (in any context at all): denotes Jon Bosak, the chair of + the original XML Working Group. This name is reserved by + the following decision of the W3C XML Plenary and + XML Coordination groups: + + In appreciation for his vision, leadership and dedication + the W3C XML Plenary on this 10th day of February, 2000 + reserves for Jon Bosak in perpetuity the XML name + xml:Father + + + + + This schema defines attributes and an attribute group + suitable for use by + schemas wishing to allow xml:base, xml:lang or xml:space attributes + on elements they define. + + To enable this, such a schema must import this schema + for the XML namespace, e.g. as follows: + <schema . . .> + . . . + <import namespace="http://www.w3.org/XML/1998/namespace" + schemaLocation="http://www.w3.org/2001/03/xml.xsd"/> + + Subsequently, qualified reference to any of the attributes + or the group defined below will have the desired effect, e.g. + + <type . . .> + . . . + <attributeGroup ref="xml:specialAttrs"/> + + will define a type which will schema-validate an instance + element with any of those attributes + + + + In keeping with the XML Schema WG's standard versioning + policy, this schema document will persist at + http://www.w3.org/2001/03/xml.xsd. + At the date of issue it can also be found at + http://www.w3.org/2001/xml.xsd. + The schema document at that URI may however change in the future, + in order to remain compatible with the latest version of XML Schema + itself. In other words, if the XML Schema namespace changes, the version + of this document at + http://www.w3.org/2001/xml.xsd will change + accordingly; the version at + http://www.w3.org/2001/03/xml.xsd will not change. + + + + + + In due course, we should install the relevant ISO 2- and 3-letter + codes as the enumerated possible values . . . + + + + + + + + + + + + + + + See http://www.w3.org/TR/xmlbase/ for + information about this attribute. + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/ecma/fouth-edition/opc-contentTypes.xsd b/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/ecma/fouth-edition/opc-contentTypes.xsd new file mode 100644 index 00000000..a6de9d27 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/ecma/fouth-edition/opc-contentTypes.xsd @@ -0,0 +1,42 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/ecma/fouth-edition/opc-coreProperties.xsd b/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/ecma/fouth-edition/opc-coreProperties.xsd new file mode 100644 index 00000000..10e978b6 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/ecma/fouth-edition/opc-coreProperties.xsd @@ -0,0 +1,50 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/ecma/fouth-edition/opc-digSig.xsd b/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/ecma/fouth-edition/opc-digSig.xsd new file mode 100644 index 00000000..4248bf7a --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/ecma/fouth-edition/opc-digSig.xsd @@ -0,0 +1,49 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/ecma/fouth-edition/opc-relationships.xsd b/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/ecma/fouth-edition/opc-relationships.xsd new file mode 100644 index 00000000..56497467 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/ecma/fouth-edition/opc-relationships.xsd @@ -0,0 +1,33 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/mce/mc.xsd b/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/mce/mc.xsd new file mode 100644 index 00000000..ef725457 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/mce/mc.xsd @@ -0,0 +1,75 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/microsoft/wml-2010.xsd b/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/microsoft/wml-2010.xsd new file mode 100644 index 00000000..f65f7777 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/microsoft/wml-2010.xsd @@ -0,0 +1,560 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/microsoft/wml-2012.xsd b/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/microsoft/wml-2012.xsd new file mode 100644 index 00000000..6b00755a --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/microsoft/wml-2012.xsd @@ -0,0 +1,67 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/microsoft/wml-2018.xsd b/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/microsoft/wml-2018.xsd new file mode 100644 index 00000000..f321d333 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/microsoft/wml-2018.xsd @@ -0,0 +1,14 @@ + + + + + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/microsoft/wml-cex-2018.xsd b/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/microsoft/wml-cex-2018.xsd new file mode 100644 index 00000000..364c6a9b --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/microsoft/wml-cex-2018.xsd @@ -0,0 +1,20 @@ + + + + + + + + + + + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/microsoft/wml-cid-2016.xsd b/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/microsoft/wml-cid-2016.xsd new file mode 100644 index 00000000..fed9d15b --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/microsoft/wml-cid-2016.xsd @@ -0,0 +1,13 @@ + + + + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/microsoft/wml-sdtdatahash-2020.xsd b/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/microsoft/wml-sdtdatahash-2020.xsd new file mode 100644 index 00000000..680cf154 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/microsoft/wml-sdtdatahash-2020.xsd @@ -0,0 +1,4 @@ + + + + diff --git a/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/microsoft/wml-symex-2015.xsd b/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/microsoft/wml-symex-2015.xsd new file mode 100644 index 00000000..89ada908 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/pptx/scripts/office/schemas/microsoft/wml-symex-2015.xsd @@ -0,0 +1,8 @@ + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/pptx/scripts/office/soffice.py b/mateclaw-server/src/main/resources/skills/pptx/scripts/office/soffice.py new file mode 100644 index 00000000..072354fb --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/pptx/scripts/office/soffice.py @@ -0,0 +1,218 @@ +""" +Helper for running LibreOffice (soffice) in environments where AF_UNIX +sockets may be blocked (e.g., sandboxed VMs). Detects the restriction +at runtime and applies an LD_PRELOAD shim if needed. + +Usage: + from office.soffice import run_soffice, get_soffice_cmd, get_soffice_env + + # Option 1 – run soffice directly + result = run_soffice(["--headless", "--convert-to", "pdf", "input.docx"]) + + # Option 2 – get env dict for your own subprocess calls + env = get_soffice_env() + subprocess.run([get_soffice_cmd(), ...], env=env) +""" + +import os +import platform +import shutil +import socket +import subprocess +import tempfile +from pathlib import Path + + +def get_soffice_cmd() -> str: + """Return the soffice command name for the current platform.""" + # Prefer PATH first on all platforms. + path_cmd = shutil.which("soffice") + if path_cmd: + return path_cmd + + if platform.system() == "Windows": + # Windows can expose soffice as .com or .exe; try both on PATH first. + for candidate_name in ("soffice.com", "soffice.exe"): + path_candidate = shutil.which(candidate_name) + if path_candidate: + return path_candidate + + for prog_dir in ( + os.environ.get("PROGRAMFILES", r"C:\Program Files"), + os.environ.get("PROGRAMFILES(X86)", r"C:\Program Files (x86)"), + ): + if not prog_dir: + continue + program_dir = Path(prog_dir) / "LibreOffice" / "program" + for exe_name in ("soffice.com", "soffice.exe"): + candidate = program_dir / exe_name + if candidate.exists(): + return str(candidate) + return "soffice" + return "soffice" + + +def get_soffice_env() -> dict: + env = os.environ.copy() + if platform.system() == "Linux": + env["SAL_USE_VCLPLUGIN"] = "svp" + + if _needs_shim(): + shim = _ensure_shim() + env["LD_PRELOAD"] = str(shim) + + return env + + +def run_soffice(args: list[str], **kwargs) -> subprocess.CompletedProcess: + env = get_soffice_env() + return subprocess.run([get_soffice_cmd()] + args, env=env, **kwargs) + + + +_SHIM_SO = Path(tempfile.gettempdir()) / "lo_socket_shim.so" + + +def _needs_shim() -> bool: + # AF_UNIX / LD_PRELOAD shim is Linux-only; skip on Windows and macOS + if not hasattr(socket, "AF_UNIX"): + return False + try: + s = socket.socket(socket.AF_UNIX, socket.SOCK_STREAM) + s.close() + return False + except OSError: + return True + + +def _ensure_shim() -> Path: + if _SHIM_SO.exists(): + return _SHIM_SO + + src = Path(tempfile.gettempdir()) / "lo_socket_shim.c" + src.write_text(_SHIM_SOURCE) + subprocess.run( + ["gcc", "-shared", "-fPIC", "-o", str(_SHIM_SO), str(src), "-ldl"], + check=True, + capture_output=True, + ) + src.unlink() + return _SHIM_SO + + + +_SHIM_SOURCE = r""" +#define _GNU_SOURCE +#include +#include +#include +#include +#include +#include +#include + +static int (*real_socket)(int, int, int); +static int (*real_socketpair)(int, int, int, int[2]); +static int (*real_listen)(int, int); +static int (*real_accept)(int, struct sockaddr *, socklen_t *); +static int (*real_close)(int); +static int (*real_read)(int, void *, size_t); + +/* Per-FD bookkeeping (FDs >= 1024 are passed through unshimmed). */ +static int is_shimmed[1024]; +static int peer_of[1024]; +static int wake_r[1024]; /* accept() blocks reading this */ +static int wake_w[1024]; /* close() writes to this */ +static int listener_fd = -1; /* FD that received listen() */ + +__attribute__((constructor)) +static void init(void) { + real_socket = dlsym(RTLD_NEXT, "socket"); + real_socketpair = dlsym(RTLD_NEXT, "socketpair"); + real_listen = dlsym(RTLD_NEXT, "listen"); + real_accept = dlsym(RTLD_NEXT, "accept"); + real_close = dlsym(RTLD_NEXT, "close"); + real_read = dlsym(RTLD_NEXT, "read"); + for (int i = 0; i < 1024; i++) { + peer_of[i] = -1; + wake_r[i] = -1; + wake_w[i] = -1; + } +} + +/* ---- socket ---------------------------------------------------------- */ +int socket(int domain, int type, int protocol) { + if (domain == AF_UNIX) { + int fd = real_socket(domain, type, protocol); + if (fd >= 0) return fd; + /* socket(AF_UNIX) blocked – fall back to socketpair(). */ + int sv[2]; + if (real_socketpair(domain, type, protocol, sv) == 0) { + if (sv[0] >= 0 && sv[0] < 1024) { + is_shimmed[sv[0]] = 1; + peer_of[sv[0]] = sv[1]; + int wp[2]; + if (pipe(wp) == 0) { + wake_r[sv[0]] = wp[0]; + wake_w[sv[0]] = wp[1]; + } + } + return sv[0]; + } + errno = EPERM; + return -1; + } + return real_socket(domain, type, protocol); +} + +/* ---- listen ---------------------------------------------------------- */ +int listen(int sockfd, int backlog) { + if (sockfd >= 0 && sockfd < 1024 && is_shimmed[sockfd]) { + listener_fd = sockfd; + return 0; + } + return real_listen(sockfd, backlog); +} + +/* ---- accept ---------------------------------------------------------- */ +int accept(int sockfd, struct sockaddr *addr, socklen_t *addrlen) { + if (sockfd >= 0 && sockfd < 1024 && is_shimmed[sockfd]) { + /* Block until close() writes to the wake pipe. */ + if (wake_r[sockfd] >= 0) { + char buf; + real_read(wake_r[sockfd], &buf, 1); + } + errno = ECONNABORTED; + return -1; + } + return real_accept(sockfd, addr, addrlen); +} + +/* ---- close ----------------------------------------------------------- */ +int close(int fd) { + if (fd >= 0 && fd < 1024 && is_shimmed[fd]) { + int was_listener = (fd == listener_fd); + is_shimmed[fd] = 0; + + if (wake_w[fd] >= 0) { /* unblock accept() */ + char c = 0; + write(wake_w[fd], &c, 1); + real_close(wake_w[fd]); + wake_w[fd] = -1; + } + if (wake_r[fd] >= 0) { real_close(wake_r[fd]); wake_r[fd] = -1; } + if (peer_of[fd] >= 0) { real_close(peer_of[fd]); peer_of[fd] = -1; } + + if (was_listener) + _exit(0); /* conversion done – exit */ + } + return real_close(fd); +} +""" + + + +if __name__ == "__main__": + import sys + result = run_soffice(sys.argv[1:]) + sys.exit(result.returncode) diff --git a/mateclaw-server/src/main/resources/skills/pptx/scripts/office/unpack.py b/mateclaw-server/src/main/resources/skills/pptx/scripts/office/unpack.py new file mode 100755 index 00000000..00152533 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/pptx/scripts/office/unpack.py @@ -0,0 +1,132 @@ +"""Unpack Office files (DOCX, PPTX, XLSX) for editing. + +Extracts the ZIP archive, pretty-prints XML files, and optionally: +- Merges adjacent runs with identical formatting (DOCX only) +- Simplifies adjacent tracked changes from same author (DOCX only) + +Usage: + python unpack.py [options] + +Examples: + python unpack.py document.docx unpacked/ + python unpack.py presentation.pptx unpacked/ + python unpack.py document.docx unpacked/ --merge-runs false +""" + +import argparse +import sys +import zipfile +from pathlib import Path + +import defusedxml.minidom + +from helpers.merge_runs import merge_runs as do_merge_runs +from helpers.simplify_redlines import simplify_redlines as do_simplify_redlines + +SMART_QUOTE_REPLACEMENTS = { + "\u201c": "“", + "\u201d": "”", + "\u2018": "‘", + "\u2019": "’", +} + + +def unpack( + input_file: str, + output_directory: str, + merge_runs: bool = True, + simplify_redlines: bool = True, +) -> tuple[None, str]: + input_path = Path(input_file) + output_path = Path(output_directory) + suffix = input_path.suffix.lower() + + if not input_path.exists(): + return None, f"Error: {input_file} does not exist" + + if suffix not in {".docx", ".pptx", ".xlsx"}: + return None, f"Error: {input_file} must be a .docx, .pptx, or .xlsx file" + + try: + output_path.mkdir(parents=True, exist_ok=True) + + with zipfile.ZipFile(input_path, "r") as zf: + zf.extractall(output_path) + + xml_files = list(output_path.rglob("*.xml")) + list(output_path.rglob("*.rels")) + for xml_file in xml_files: + _pretty_print_xml(xml_file) + + message = f"Unpacked {input_file} ({len(xml_files)} XML files)" + + if suffix == ".docx": + if simplify_redlines: + simplify_count, _ = do_simplify_redlines(str(output_path)) + message += f", simplified {simplify_count} tracked changes" + + if merge_runs: + merge_count, _ = do_merge_runs(str(output_path)) + message += f", merged {merge_count} runs" + + for xml_file in xml_files: + _escape_smart_quotes(xml_file) + + return None, message + + except zipfile.BadZipFile: + return None, f"Error: {input_file} is not a valid Office file" + except Exception as e: + return None, f"Error unpacking: {e}" + + +def _pretty_print_xml(xml_file: Path) -> None: + try: + content = xml_file.read_text(encoding="utf-8") + dom = defusedxml.minidom.parseString(content) + xml_file.write_bytes(dom.toprettyxml(indent=" ", encoding="utf-8")) + except Exception: + pass + + +def _escape_smart_quotes(xml_file: Path) -> None: + try: + content = xml_file.read_text(encoding="utf-8") + for char, entity in SMART_QUOTE_REPLACEMENTS.items(): + content = content.replace(char, entity) + xml_file.write_text(content, encoding="utf-8") + except Exception: + pass + + +if __name__ == "__main__": + parser = argparse.ArgumentParser( + description="Unpack an Office file (DOCX, PPTX, XLSX) for editing" + ) + parser.add_argument("input_file", help="Office file to unpack") + parser.add_argument("output_directory", help="Output directory") + parser.add_argument( + "--merge-runs", + type=lambda x: x.lower() == "true", + default=True, + metavar="true|false", + help="Merge adjacent runs with identical formatting (DOCX only, default: true)", + ) + parser.add_argument( + "--simplify-redlines", + type=lambda x: x.lower() == "true", + default=True, + metavar="true|false", + help="Merge adjacent tracked changes from same author (DOCX only, default: true)", + ) + args = parser.parse_args() + + _, message = unpack( + args.input_file, + args.output_directory, + merge_runs=args.merge_runs, + simplify_redlines=args.simplify_redlines, + ) + print(message) + + if "Error" in message: + sys.exit(1) diff --git a/mateclaw-server/src/main/resources/skills/pptx/scripts/office/validate.py b/mateclaw-server/src/main/resources/skills/pptx/scripts/office/validate.py new file mode 100755 index 00000000..03b01f6e --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/pptx/scripts/office/validate.py @@ -0,0 +1,111 @@ +""" +Command line tool to validate Office document XML files against XSD schemas and tracked changes. + +Usage: + python validate.py [--original ] [--auto-repair] [--author NAME] + +The first argument can be either: +- An unpacked directory containing the Office document XML files +- A packed Office file (.docx/.pptx/.xlsx) which will be unpacked to a temp directory + +Auto-repair fixes: +- paraId/durableId values that exceed OOXML limits +- Missing xml:space="preserve" on w:t elements with whitespace +""" + +import argparse +import sys +import tempfile +import zipfile +from pathlib import Path + +from validators import DOCXSchemaValidator, PPTXSchemaValidator, RedliningValidator + + +def main(): + parser = argparse.ArgumentParser(description="Validate Office document XML files") + parser.add_argument( + "path", + help="Path to unpacked directory or packed Office file (.docx/.pptx/.xlsx)", + ) + parser.add_argument( + "--original", + required=False, + default=None, + help="Path to original file (.docx/.pptx/.xlsx). If omitted, all XSD errors are reported and redlining validation is skipped.", + ) + parser.add_argument( + "-v", + "--verbose", + action="store_true", + help="Enable verbose output", + ) + parser.add_argument( + "--auto-repair", + action="store_true", + help="Automatically repair common issues (hex IDs, whitespace preservation)", + ) + parser.add_argument( + "--author", + default="Claude", + help="Author name for redlining validation (default: Claude)", + ) + args = parser.parse_args() + + path = Path(args.path) + assert path.exists(), f"Error: {path} does not exist" + + original_file = None + if args.original: + original_file = Path(args.original) + assert original_file.is_file(), f"Error: {original_file} is not a file" + assert original_file.suffix.lower() in [".docx", ".pptx", ".xlsx"], ( + f"Error: {original_file} must be a .docx, .pptx, or .xlsx file" + ) + + file_extension = (original_file or path).suffix.lower() + assert file_extension in [".docx", ".pptx", ".xlsx"], ( + f"Error: Cannot determine file type from {path}. Use --original or provide a .docx/.pptx/.xlsx file." + ) + + if path.is_file() and path.suffix.lower() in [".docx", ".pptx", ".xlsx"]: + temp_dir = tempfile.mkdtemp() + with zipfile.ZipFile(path, "r") as zf: + zf.extractall(temp_dir) + unpacked_dir = Path(temp_dir) + else: + assert path.is_dir(), f"Error: {path} is not a directory or Office file" + unpacked_dir = path + + match file_extension: + case ".docx": + validators = [ + DOCXSchemaValidator(unpacked_dir, original_file, verbose=args.verbose), + ] + if original_file: + validators.append( + RedliningValidator(unpacked_dir, original_file, verbose=args.verbose, author=args.author) + ) + case ".pptx": + validators = [ + PPTXSchemaValidator(unpacked_dir, original_file, verbose=args.verbose), + ] + case _: + print(f"Error: Validation not supported for file type {file_extension}") + sys.exit(1) + + if args.auto_repair: + total_repairs = sum(v.repair() for v in validators) + if total_repairs: + print(f"Auto-repaired {total_repairs} issue(s)") + + success = all(v.validate() for v in validators) + + if success: + print("All validations PASSED!") + + sys.exit(0 if success else 1) + + +if __name__ == "__main__": + main() diff --git a/mateclaw-server/src/main/resources/skills/pptx/scripts/office/validators/__init__.py b/mateclaw-server/src/main/resources/skills/pptx/scripts/office/validators/__init__.py new file mode 100644 index 00000000..db092ece --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/pptx/scripts/office/validators/__init__.py @@ -0,0 +1,15 @@ +""" +Validation modules for Word document processing. +""" + +from .base import BaseSchemaValidator +from .docx import DOCXSchemaValidator +from .pptx import PPTXSchemaValidator +from .redlining import RedliningValidator + +__all__ = [ + "BaseSchemaValidator", + "DOCXSchemaValidator", + "PPTXSchemaValidator", + "RedliningValidator", +] diff --git a/mateclaw-server/src/main/resources/skills/pptx/scripts/office/validators/base.py b/mateclaw-server/src/main/resources/skills/pptx/scripts/office/validators/base.py new file mode 100644 index 00000000..db4a06a2 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/pptx/scripts/office/validators/base.py @@ -0,0 +1,847 @@ +""" +Base validator with common validation logic for document files. +""" + +import re +from pathlib import Path + +import defusedxml.minidom +import lxml.etree + + +class BaseSchemaValidator: + + IGNORED_VALIDATION_ERRORS = [ + "hyphenationZone", + "purl.org/dc/terms", + ] + + UNIQUE_ID_REQUIREMENTS = { + "comment": ("id", "file"), + "commentrangestart": ("id", "file"), + "commentrangeend": ("id", "file"), + "bookmarkstart": ("id", "file"), + "bookmarkend": ("id", "file"), + "sldid": ("id", "file"), + "sldmasterid": ("id", "global"), + "sldlayoutid": ("id", "global"), + "cm": ("authorid", "file"), + "sheet": ("sheetid", "file"), + "definedname": ("id", "file"), + "cxnsp": ("id", "file"), + "sp": ("id", "file"), + "pic": ("id", "file"), + "grpsp": ("id", "file"), + } + + EXCLUDED_ID_CONTAINERS = { + "sectionlst", + } + + ELEMENT_RELATIONSHIP_TYPES = {} + + SCHEMA_MAPPINGS = { + "word": "ISO-IEC29500-4_2016/wml.xsd", + "ppt": "ISO-IEC29500-4_2016/pml.xsd", + "xl": "ISO-IEC29500-4_2016/sml.xsd", + "[Content_Types].xml": "ecma/fouth-edition/opc-contentTypes.xsd", + "app.xml": "ISO-IEC29500-4_2016/shared-documentPropertiesExtended.xsd", + "core.xml": "ecma/fouth-edition/opc-coreProperties.xsd", + "custom.xml": "ISO-IEC29500-4_2016/shared-documentPropertiesCustom.xsd", + ".rels": "ecma/fouth-edition/opc-relationships.xsd", + "people.xml": "microsoft/wml-2012.xsd", + "commentsIds.xml": "microsoft/wml-cid-2016.xsd", + "commentsExtensible.xml": "microsoft/wml-cex-2018.xsd", + "commentsExtended.xml": "microsoft/wml-2012.xsd", + "chart": "ISO-IEC29500-4_2016/dml-chart.xsd", + "theme": "ISO-IEC29500-4_2016/dml-main.xsd", + "drawing": "ISO-IEC29500-4_2016/dml-main.xsd", + } + + MC_NAMESPACE = "http://schemas.openxmlformats.org/markup-compatibility/2006" + XML_NAMESPACE = "http://www.w3.org/XML/1998/namespace" + + PACKAGE_RELATIONSHIPS_NAMESPACE = ( + "http://schemas.openxmlformats.org/package/2006/relationships" + ) + OFFICE_RELATIONSHIPS_NAMESPACE = ( + "http://schemas.openxmlformats.org/officeDocument/2006/relationships" + ) + CONTENT_TYPES_NAMESPACE = ( + "http://schemas.openxmlformats.org/package/2006/content-types" + ) + + MAIN_CONTENT_FOLDERS = {"word", "ppt", "xl"} + + OOXML_NAMESPACES = { + "http://schemas.openxmlformats.org/officeDocument/2006/math", + "http://schemas.openxmlformats.org/officeDocument/2006/relationships", + "http://schemas.openxmlformats.org/schemaLibrary/2006/main", + "http://schemas.openxmlformats.org/drawingml/2006/main", + "http://schemas.openxmlformats.org/drawingml/2006/chart", + "http://schemas.openxmlformats.org/drawingml/2006/chartDrawing", + "http://schemas.openxmlformats.org/drawingml/2006/diagram", + "http://schemas.openxmlformats.org/drawingml/2006/picture", + "http://schemas.openxmlformats.org/drawingml/2006/spreadsheetDrawing", + "http://schemas.openxmlformats.org/drawingml/2006/wordprocessingDrawing", + "http://schemas.openxmlformats.org/wordprocessingml/2006/main", + "http://schemas.openxmlformats.org/presentationml/2006/main", + "http://schemas.openxmlformats.org/spreadsheetml/2006/main", + "http://schemas.openxmlformats.org/officeDocument/2006/sharedTypes", + "http://www.w3.org/XML/1998/namespace", + } + + def __init__(self, unpacked_dir, original_file=None, verbose=False): + self.unpacked_dir = Path(unpacked_dir).resolve() + self.original_file = Path(original_file) if original_file else None + self.verbose = verbose + + self.schemas_dir = Path(__file__).parent.parent / "schemas" + + patterns = ["*.xml", "*.rels"] + self.xml_files = [ + f for pattern in patterns for f in self.unpacked_dir.rglob(pattern) + ] + + if not self.xml_files: + print(f"Warning: No XML files found in {self.unpacked_dir}") + + def validate(self): + raise NotImplementedError("Subclasses must implement the validate method") + + def repair(self) -> int: + return self.repair_whitespace_preservation() + + def repair_whitespace_preservation(self) -> int: + repairs = 0 + + for xml_file in self.xml_files: + try: + content = xml_file.read_text(encoding="utf-8") + dom = defusedxml.minidom.parseString(content) + modified = False + + for elem in dom.getElementsByTagName("*"): + if elem.tagName.endswith(":t") and elem.firstChild: + text = elem.firstChild.nodeValue + if text and (text.startswith((' ', '\t')) or text.endswith((' ', '\t'))): + if elem.getAttribute("xml:space") != "preserve": + elem.setAttribute("xml:space", "preserve") + text_preview = repr(text[:30]) + "..." if len(text) > 30 else repr(text) + print(f" Repaired: {xml_file.name}: Added xml:space='preserve' to {elem.tagName}: {text_preview}") + repairs += 1 + modified = True + + if modified: + xml_file.write_bytes(dom.toxml(encoding="UTF-8")) + + except Exception: + pass + + return repairs + + def validate_xml(self): + errors = [] + + for xml_file in self.xml_files: + try: + lxml.etree.parse(str(xml_file)) + except lxml.etree.XMLSyntaxError as e: + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: " + f"Line {e.lineno}: {e.msg}" + ) + except Exception as e: + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: " + f"Unexpected error: {str(e)}" + ) + + if errors: + print(f"FAILED - Found {len(errors)} XML violations:") + for error in errors: + print(error) + return False + else: + if self.verbose: + print("PASSED - All XML files are well-formed") + return True + + def validate_namespaces(self): + errors = [] + + for xml_file in self.xml_files: + try: + root = lxml.etree.parse(str(xml_file)).getroot() + declared = set(root.nsmap.keys()) - {None} + + for attr_val in [ + v for k, v in root.attrib.items() if k.endswith("Ignorable") + ]: + undeclared = set(attr_val.split()) - declared + errors.extend( + f" {xml_file.relative_to(self.unpacked_dir)}: " + f"Namespace '{ns}' in Ignorable but not declared" + for ns in undeclared + ) + except lxml.etree.XMLSyntaxError: + continue + + if errors: + print(f"FAILED - {len(errors)} namespace issues:") + for error in errors: + print(error) + return False + if self.verbose: + print("PASSED - All namespace prefixes properly declared") + return True + + def validate_unique_ids(self): + errors = [] + global_ids = {} + + for xml_file in self.xml_files: + try: + root = lxml.etree.parse(str(xml_file)).getroot() + file_ids = {} + + mc_elements = root.xpath( + ".//mc:AlternateContent", namespaces={"mc": self.MC_NAMESPACE} + ) + for elem in mc_elements: + elem.getparent().remove(elem) + + for elem in root.iter(): + tag = ( + elem.tag.split("}")[-1].lower() + if "}" in elem.tag + else elem.tag.lower() + ) + + if tag in self.UNIQUE_ID_REQUIREMENTS: + in_excluded_container = any( + ancestor.tag.split("}")[-1].lower() in self.EXCLUDED_ID_CONTAINERS + for ancestor in elem.iterancestors() + ) + if in_excluded_container: + continue + + attr_name, scope = self.UNIQUE_ID_REQUIREMENTS[tag] + + id_value = None + for attr, value in elem.attrib.items(): + attr_local = ( + attr.split("}")[-1].lower() + if "}" in attr + else attr.lower() + ) + if attr_local == attr_name: + id_value = value + break + + if id_value is not None: + if scope == "global": + if id_value in global_ids: + prev_file, prev_line, prev_tag = global_ids[ + id_value + ] + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: " + f"Line {elem.sourceline}: Global ID '{id_value}' in <{tag}> " + f"already used in {prev_file} at line {prev_line} in <{prev_tag}>" + ) + else: + global_ids[id_value] = ( + xml_file.relative_to(self.unpacked_dir), + elem.sourceline, + tag, + ) + elif scope == "file": + key = (tag, attr_name) + if key not in file_ids: + file_ids[key] = {} + + if id_value in file_ids[key]: + prev_line = file_ids[key][id_value] + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: " + f"Line {elem.sourceline}: Duplicate {attr_name}='{id_value}' in <{tag}> " + f"(first occurrence at line {prev_line})" + ) + else: + file_ids[key][id_value] = elem.sourceline + + except (lxml.etree.XMLSyntaxError, Exception) as e: + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: Error: {e}" + ) + + if errors: + print(f"FAILED - Found {len(errors)} ID uniqueness violations:") + for error in errors: + print(error) + return False + else: + if self.verbose: + print("PASSED - All required IDs are unique") + return True + + def validate_file_references(self): + errors = [] + + rels_files = list(self.unpacked_dir.rglob("*.rels")) + + if not rels_files: + if self.verbose: + print("PASSED - No .rels files found") + return True + + all_files = [] + for file_path in self.unpacked_dir.rglob("*"): + if ( + file_path.is_file() + and file_path.name != "[Content_Types].xml" + and not file_path.name.endswith(".rels") + ): + all_files.append(file_path.resolve()) + + all_referenced_files = set() + + if self.verbose: + print( + f"Found {len(rels_files)} .rels files and {len(all_files)} target files" + ) + + for rels_file in rels_files: + try: + rels_root = lxml.etree.parse(str(rels_file)).getroot() + + rels_dir = rels_file.parent + + referenced_files = set() + broken_refs = [] + + for rel in rels_root.findall( + ".//ns:Relationship", + namespaces={"ns": self.PACKAGE_RELATIONSHIPS_NAMESPACE}, + ): + target = rel.get("Target") + if target and not target.startswith( + ("http", "mailto:") + ): + if target.startswith("/"): + target_path = self.unpacked_dir / target.lstrip("/") + elif rels_file.name == ".rels": + target_path = self.unpacked_dir / target + else: + base_dir = rels_dir.parent + target_path = base_dir / target + + try: + target_path = target_path.resolve() + if target_path.exists() and target_path.is_file(): + referenced_files.add(target_path) + all_referenced_files.add(target_path) + else: + broken_refs.append((target, rel.sourceline)) + except (OSError, ValueError): + broken_refs.append((target, rel.sourceline)) + + if broken_refs: + rel_path = rels_file.relative_to(self.unpacked_dir) + for broken_ref, line_num in broken_refs: + errors.append( + f" {rel_path}: Line {line_num}: Broken reference to {broken_ref}" + ) + + except Exception as e: + rel_path = rels_file.relative_to(self.unpacked_dir) + errors.append(f" Error parsing {rel_path}: {e}") + + unreferenced_files = set(all_files) - all_referenced_files + + if unreferenced_files: + for unref_file in sorted(unreferenced_files): + unref_rel_path = unref_file.relative_to(self.unpacked_dir) + errors.append(f" Unreferenced file: {unref_rel_path}") + + if errors: + print(f"FAILED - Found {len(errors)} relationship validation errors:") + for error in errors: + print(error) + print( + "CRITICAL: These errors will cause the document to appear corrupt. " + + "Broken references MUST be fixed, " + + "and unreferenced files MUST be referenced or removed." + ) + return False + else: + if self.verbose: + print( + "PASSED - All references are valid and all files are properly referenced" + ) + return True + + def validate_all_relationship_ids(self): + import lxml.etree + + errors = [] + + for xml_file in self.xml_files: + if xml_file.suffix == ".rels": + continue + + rels_dir = xml_file.parent / "_rels" + rels_file = rels_dir / f"{xml_file.name}.rels" + + if not rels_file.exists(): + continue + + try: + rels_root = lxml.etree.parse(str(rels_file)).getroot() + rid_to_type = {} + + for rel in rels_root.findall( + f".//{{{self.PACKAGE_RELATIONSHIPS_NAMESPACE}}}Relationship" + ): + rid = rel.get("Id") + rel_type = rel.get("Type", "") + if rid: + if rid in rid_to_type: + rels_rel_path = rels_file.relative_to(self.unpacked_dir) + errors.append( + f" {rels_rel_path}: Line {rel.sourceline}: " + f"Duplicate relationship ID '{rid}' (IDs must be unique)" + ) + type_name = ( + rel_type.split("/")[-1] if "/" in rel_type else rel_type + ) + rid_to_type[rid] = type_name + + xml_root = lxml.etree.parse(str(xml_file)).getroot() + + r_ns = self.OFFICE_RELATIONSHIPS_NAMESPACE + rid_attrs_to_check = ["id", "embed", "link"] + for elem in xml_root.iter(): + for attr_name in rid_attrs_to_check: + rid_attr = elem.get(f"{{{r_ns}}}{attr_name}") + if not rid_attr: + continue + xml_rel_path = xml_file.relative_to(self.unpacked_dir) + elem_name = ( + elem.tag.split("}")[-1] if "}" in elem.tag else elem.tag + ) + + if rid_attr not in rid_to_type: + errors.append( + f" {xml_rel_path}: Line {elem.sourceline}: " + f"<{elem_name}> r:{attr_name} references non-existent relationship '{rid_attr}' " + f"(valid IDs: {', '.join(sorted(rid_to_type.keys())[:5])}{'...' if len(rid_to_type) > 5 else ''})" + ) + elif attr_name == "id" and self.ELEMENT_RELATIONSHIP_TYPES: + expected_type = self._get_expected_relationship_type( + elem_name + ) + if expected_type: + actual_type = rid_to_type[rid_attr] + if expected_type not in actual_type.lower(): + errors.append( + f" {xml_rel_path}: Line {elem.sourceline}: " + f"<{elem_name}> references '{rid_attr}' which points to '{actual_type}' " + f"but should point to a '{expected_type}' relationship" + ) + + except Exception as e: + xml_rel_path = xml_file.relative_to(self.unpacked_dir) + errors.append(f" Error processing {xml_rel_path}: {e}") + + if errors: + print(f"FAILED - Found {len(errors)} relationship ID reference errors:") + for error in errors: + print(error) + print("\nThese ID mismatches will cause the document to appear corrupt!") + return False + else: + if self.verbose: + print("PASSED - All relationship ID references are valid") + return True + + def _get_expected_relationship_type(self, element_name): + elem_lower = element_name.lower() + + if elem_lower in self.ELEMENT_RELATIONSHIP_TYPES: + return self.ELEMENT_RELATIONSHIP_TYPES[elem_lower] + + if elem_lower.endswith("id") and len(elem_lower) > 2: + prefix = elem_lower[:-2] + if prefix.endswith("master"): + return prefix.lower() + elif prefix.endswith("layout"): + return prefix.lower() + else: + if prefix == "sld": + return "slide" + return prefix.lower() + + if elem_lower.endswith("reference") and len(elem_lower) > 9: + prefix = elem_lower[:-9] + return prefix.lower() + + return None + + def validate_content_types(self): + errors = [] + + content_types_file = self.unpacked_dir / "[Content_Types].xml" + if not content_types_file.exists(): + print("FAILED - [Content_Types].xml file not found") + return False + + try: + root = lxml.etree.parse(str(content_types_file)).getroot() + declared_parts = set() + declared_extensions = set() + + for override in root.findall( + f".//{{{self.CONTENT_TYPES_NAMESPACE}}}Override" + ): + part_name = override.get("PartName") + if part_name is not None: + declared_parts.add(part_name.lstrip("/")) + + for default in root.findall( + f".//{{{self.CONTENT_TYPES_NAMESPACE}}}Default" + ): + extension = default.get("Extension") + if extension is not None: + declared_extensions.add(extension.lower()) + + declarable_roots = { + "sld", + "sldLayout", + "sldMaster", + "presentation", + "document", + "workbook", + "worksheet", + "theme", + } + + media_extensions = { + "png": "image/png", + "jpg": "image/jpeg", + "jpeg": "image/jpeg", + "gif": "image/gif", + "bmp": "image/bmp", + "tiff": "image/tiff", + "wmf": "image/x-wmf", + "emf": "image/x-emf", + } + + all_files = list(self.unpacked_dir.rglob("*")) + all_files = [f for f in all_files if f.is_file()] + + for xml_file in self.xml_files: + path_str = str(xml_file.relative_to(self.unpacked_dir)).replace( + "\\", "/" + ) + + if any( + skip in path_str + for skip in [".rels", "[Content_Types]", "docProps/", "_rels/"] + ): + continue + + try: + root_tag = lxml.etree.parse(str(xml_file)).getroot().tag + root_name = root_tag.split("}")[-1] if "}" in root_tag else root_tag + + if root_name in declarable_roots and path_str not in declared_parts: + errors.append( + f" {path_str}: File with <{root_name}> root not declared in [Content_Types].xml" + ) + + except Exception: + continue + + for file_path in all_files: + if file_path.suffix.lower() in {".xml", ".rels"}: + continue + if file_path.name == "[Content_Types].xml": + continue + if "_rels" in file_path.parts or "docProps" in file_path.parts: + continue + + extension = file_path.suffix.lstrip(".").lower() + if extension and extension not in declared_extensions: + if extension in media_extensions: + relative_path = file_path.relative_to(self.unpacked_dir) + errors.append( + f' {relative_path}: File with extension \'{extension}\' not declared in [Content_Types].xml - should add: ' + ) + + except Exception as e: + errors.append(f" Error parsing [Content_Types].xml: {e}") + + if errors: + print(f"FAILED - Found {len(errors)} content type declaration errors:") + for error in errors: + print(error) + return False + else: + if self.verbose: + print( + "PASSED - All content files are properly declared in [Content_Types].xml" + ) + return True + + def validate_file_against_xsd(self, xml_file, verbose=False): + xml_file = Path(xml_file).resolve() + unpacked_dir = self.unpacked_dir.resolve() + + is_valid, current_errors = self._validate_single_file_xsd( + xml_file, unpacked_dir + ) + + if is_valid is None: + return None, set() + elif is_valid: + return True, set() + + original_errors = self._get_original_file_errors(xml_file) + + assert current_errors is not None + new_errors = current_errors - original_errors + + new_errors = { + e for e in new_errors + if not any(pattern in e for pattern in self.IGNORED_VALIDATION_ERRORS) + } + + if new_errors: + if verbose: + relative_path = xml_file.relative_to(unpacked_dir) + print(f"FAILED - {relative_path}: {len(new_errors)} new error(s)") + for error in list(new_errors)[:3]: + truncated = error[:250] + "..." if len(error) > 250 else error + print(f" - {truncated}") + return False, new_errors + else: + if verbose: + print( + f"PASSED - No new errors (original had {len(current_errors)} errors)" + ) + return True, set() + + def validate_against_xsd(self): + new_errors = [] + original_error_count = 0 + valid_count = 0 + skipped_count = 0 + + for xml_file in self.xml_files: + relative_path = str(xml_file.relative_to(self.unpacked_dir)) + is_valid, new_file_errors = self.validate_file_against_xsd( + xml_file, verbose=False + ) + + if is_valid is None: + skipped_count += 1 + continue + elif is_valid and not new_file_errors: + valid_count += 1 + continue + elif is_valid: + original_error_count += 1 + valid_count += 1 + continue + + new_errors.append(f" {relative_path}: {len(new_file_errors)} new error(s)") + for error in list(new_file_errors)[:3]: + new_errors.append( + f" - {error[:250]}..." if len(error) > 250 else f" - {error}" + ) + + if self.verbose: + print(f"Validated {len(self.xml_files)} files:") + print(f" - Valid: {valid_count}") + print(f" - Skipped (no schema): {skipped_count}") + if original_error_count: + print(f" - With original errors (ignored): {original_error_count}") + print( + f" - With NEW errors: {len(new_errors) > 0 and len([e for e in new_errors if not e.startswith(' ')]) or 0}" + ) + + if new_errors: + print("\nFAILED - Found NEW validation errors:") + for error in new_errors: + print(error) + return False + else: + if self.verbose: + print("\nPASSED - No new XSD validation errors introduced") + return True + + def _get_schema_path(self, xml_file): + if xml_file.name in self.SCHEMA_MAPPINGS: + return self.schemas_dir / self.SCHEMA_MAPPINGS[xml_file.name] + + if xml_file.suffix == ".rels": + return self.schemas_dir / self.SCHEMA_MAPPINGS[".rels"] + + if "charts/" in str(xml_file) and xml_file.name.startswith("chart"): + return self.schemas_dir / self.SCHEMA_MAPPINGS["chart"] + + if "theme/" in str(xml_file) and xml_file.name.startswith("theme"): + return self.schemas_dir / self.SCHEMA_MAPPINGS["theme"] + + if xml_file.parent.name in self.MAIN_CONTENT_FOLDERS: + return self.schemas_dir / self.SCHEMA_MAPPINGS[xml_file.parent.name] + + return None + + def _clean_ignorable_namespaces(self, xml_doc): + xml_string = lxml.etree.tostring(xml_doc, encoding="unicode") + xml_copy = lxml.etree.fromstring(xml_string) + + for elem in xml_copy.iter(): + attrs_to_remove = [] + + for attr in elem.attrib: + if "{" in attr: + ns = attr.split("}")[0][1:] + if ns not in self.OOXML_NAMESPACES: + attrs_to_remove.append(attr) + + for attr in attrs_to_remove: + del elem.attrib[attr] + + self._remove_ignorable_elements(xml_copy) + + return lxml.etree.ElementTree(xml_copy) + + def _remove_ignorable_elements(self, root): + elements_to_remove = [] + + for elem in list(root): + if not hasattr(elem, "tag") or callable(elem.tag): + continue + + tag_str = str(elem.tag) + if tag_str.startswith("{"): + ns = tag_str.split("}")[0][1:] + if ns not in self.OOXML_NAMESPACES: + elements_to_remove.append(elem) + continue + + self._remove_ignorable_elements(elem) + + for elem in elements_to_remove: + root.remove(elem) + + def _preprocess_for_mc_ignorable(self, xml_doc): + root = xml_doc.getroot() + + if f"{{{self.MC_NAMESPACE}}}Ignorable" in root.attrib: + del root.attrib[f"{{{self.MC_NAMESPACE}}}Ignorable"] + + return xml_doc + + def _validate_single_file_xsd(self, xml_file, base_path): + schema_path = self._get_schema_path(xml_file) + if not schema_path: + return None, None + + try: + with open(schema_path, "rb") as xsd_file: + parser = lxml.etree.XMLParser() + xsd_doc = lxml.etree.parse( + xsd_file, parser=parser, base_url=str(schema_path) + ) + schema = lxml.etree.XMLSchema(xsd_doc) + + with open(xml_file, "r") as f: + xml_doc = lxml.etree.parse(f) + + xml_doc, _ = self._remove_template_tags_from_text_nodes(xml_doc) + xml_doc = self._preprocess_for_mc_ignorable(xml_doc) + + relative_path = xml_file.relative_to(base_path) + if ( + relative_path.parts + and relative_path.parts[0] in self.MAIN_CONTENT_FOLDERS + ): + xml_doc = self._clean_ignorable_namespaces(xml_doc) + + if schema.validate(xml_doc): + return True, set() + else: + errors = set() + for error in schema.error_log: + errors.add(error.message) + return False, errors + + except Exception as e: + return False, {str(e)} + + def _get_original_file_errors(self, xml_file): + if self.original_file is None: + return set() + + import tempfile + import zipfile + + xml_file = Path(xml_file).resolve() + unpacked_dir = self.unpacked_dir.resolve() + relative_path = xml_file.relative_to(unpacked_dir) + + with tempfile.TemporaryDirectory() as temp_dir: + temp_path = Path(temp_dir) + + with zipfile.ZipFile(self.original_file, "r") as zip_ref: + zip_ref.extractall(temp_path) + + original_xml_file = temp_path / relative_path + + if not original_xml_file.exists(): + return set() + + is_valid, errors = self._validate_single_file_xsd( + original_xml_file, temp_path + ) + return errors if errors else set() + + def _remove_template_tags_from_text_nodes(self, xml_doc): + warnings = [] + template_pattern = re.compile(r"\{\{[^}]*\}\}") + + xml_string = lxml.etree.tostring(xml_doc, encoding="unicode") + xml_copy = lxml.etree.fromstring(xml_string) + + def process_text_content(text, content_type): + if not text: + return text + matches = list(template_pattern.finditer(text)) + if matches: + for match in matches: + warnings.append( + f"Found template tag in {content_type}: {match.group()}" + ) + return template_pattern.sub("", text) + return text + + for elem in xml_copy.iter(): + if not hasattr(elem, "tag") or callable(elem.tag): + continue + tag_str = str(elem.tag) + if tag_str.endswith("}t") or tag_str == "t": + continue + + elem.text = process_text_content(elem.text, "text content") + elem.tail = process_text_content(elem.tail, "tail content") + + return lxml.etree.ElementTree(xml_copy), warnings + + +if __name__ == "__main__": + raise RuntimeError("This module should not be run directly.") diff --git a/mateclaw-server/src/main/resources/skills/pptx/scripts/office/validators/docx.py b/mateclaw-server/src/main/resources/skills/pptx/scripts/office/validators/docx.py new file mode 100644 index 00000000..0a0b0bfd --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/pptx/scripts/office/validators/docx.py @@ -0,0 +1,447 @@ +""" +Validator for Word document XML files against XSD schemas. +""" + +import os +import random +import re +import tempfile +import zipfile + +import defusedxml.minidom +import lxml.etree + +from .base import BaseSchemaValidator + + +class DOCXSchemaValidator(BaseSchemaValidator): + + WORD_2006_NAMESPACE = "http://schemas.openxmlformats.org/wordprocessingml/2006/main" + W14_NAMESPACE = "http://schemas.microsoft.com/office/word/2010/wordml" + W16CID_NAMESPACE = "http://schemas.microsoft.com/office/word/2016/wordml/cid" + + ELEMENT_RELATIONSHIP_TYPES = {} + + def validate(self): + if not self.validate_xml(): + return False + + all_valid = True + if not self.validate_namespaces(): + all_valid = False + + if not self.validate_unique_ids(): + all_valid = False + + if not self.validate_file_references(): + all_valid = False + + if not self.validate_content_types(): + all_valid = False + + if not self.validate_against_xsd(): + all_valid = False + + if not self.validate_whitespace_preservation(): + all_valid = False + + if not self.validate_deletions(): + all_valid = False + + if not self.validate_insertions(): + all_valid = False + + if not self.validate_all_relationship_ids(): + all_valid = False + + if not self.validate_id_constraints(): + all_valid = False + + if not self.validate_comment_markers(): + all_valid = False + + self.compare_paragraph_counts() + + return all_valid + + def validate_whitespace_preservation(self): + errors = [] + + for xml_file in self.xml_files: + if xml_file.name != "document.xml": + continue + + try: + root = lxml.etree.parse(str(xml_file)).getroot() + + for elem in root.iter(f"{{{self.WORD_2006_NAMESPACE}}}t"): + if elem.text: + text = elem.text + if re.search(r"^[ \t\n\r]", text) or re.search( + r"[ \t\n\r]$", text + ): + xml_space_attr = f"{{{self.XML_NAMESPACE}}}space" + if ( + xml_space_attr not in elem.attrib + or elem.attrib[xml_space_attr] != "preserve" + ): + text_preview = ( + repr(text)[:50] + "..." + if len(repr(text)) > 50 + else repr(text) + ) + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: " + f"Line {elem.sourceline}: w:t element with whitespace missing xml:space='preserve': {text_preview}" + ) + + except (lxml.etree.XMLSyntaxError, Exception) as e: + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: Error: {e}" + ) + + if errors: + print(f"FAILED - Found {len(errors)} whitespace preservation violations:") + for error in errors: + print(error) + return False + else: + if self.verbose: + print("PASSED - All whitespace is properly preserved") + return True + + def validate_deletions(self): + errors = [] + + for xml_file in self.xml_files: + if xml_file.name != "document.xml": + continue + + try: + root = lxml.etree.parse(str(xml_file)).getroot() + namespaces = {"w": self.WORD_2006_NAMESPACE} + + for t_elem in root.xpath(".//w:del//w:t", namespaces=namespaces): + if t_elem.text: + text_preview = ( + repr(t_elem.text)[:50] + "..." + if len(repr(t_elem.text)) > 50 + else repr(t_elem.text) + ) + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: " + f"Line {t_elem.sourceline}: found within : {text_preview}" + ) + + for instr_elem in root.xpath( + ".//w:del//w:instrText", namespaces=namespaces + ): + text_preview = ( + repr(instr_elem.text or "")[:50] + "..." + if len(repr(instr_elem.text or "")) > 50 + else repr(instr_elem.text or "") + ) + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: " + f"Line {instr_elem.sourceline}: found within (use ): {text_preview}" + ) + + except (lxml.etree.XMLSyntaxError, Exception) as e: + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: Error: {e}" + ) + + if errors: + print(f"FAILED - Found {len(errors)} deletion validation violations:") + for error in errors: + print(error) + return False + else: + if self.verbose: + print("PASSED - No w:t elements found within w:del elements") + return True + + def count_paragraphs_in_unpacked(self): + count = 0 + + for xml_file in self.xml_files: + if xml_file.name != "document.xml": + continue + + try: + root = lxml.etree.parse(str(xml_file)).getroot() + paragraphs = root.findall(f".//{{{self.WORD_2006_NAMESPACE}}}p") + count = len(paragraphs) + except Exception as e: + print(f"Error counting paragraphs in unpacked document: {e}") + + return count + + def count_paragraphs_in_original(self): + original = self.original_file + if original is None: + return 0 + + count = 0 + + try: + with tempfile.TemporaryDirectory() as temp_dir: + with zipfile.ZipFile(original, "r") as zip_ref: + zip_ref.extractall(temp_dir) + + doc_xml_path = os.path.join(temp_dir, "word", "document.xml") + root = lxml.etree.parse(doc_xml_path).getroot() + + paragraphs = root.findall(f".//{{{self.WORD_2006_NAMESPACE}}}p") + count = len(paragraphs) + + except Exception as e: + print(f"Error counting paragraphs in original document: {e}") + + return count + + def validate_insertions(self): + errors = [] + + for xml_file in self.xml_files: + if xml_file.name != "document.xml": + continue + + try: + root = lxml.etree.parse(str(xml_file)).getroot() + namespaces = {"w": self.WORD_2006_NAMESPACE} + + invalid_elements = root.xpath( + ".//w:ins//w:delText[not(ancestor::w:del)]", namespaces=namespaces + ) + + for elem in invalid_elements: + text_preview = ( + repr(elem.text or "")[:50] + "..." + if len(repr(elem.text or "")) > 50 + else repr(elem.text or "") + ) + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: " + f"Line {elem.sourceline}: within : {text_preview}" + ) + + except (lxml.etree.XMLSyntaxError, Exception) as e: + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: Error: {e}" + ) + + if errors: + print(f"FAILED - Found {len(errors)} insertion validation violations:") + for error in errors: + print(error) + return False + else: + if self.verbose: + print("PASSED - No w:delText elements within w:ins elements") + return True + + def compare_paragraph_counts(self): + original_count = self.count_paragraphs_in_original() + new_count = self.count_paragraphs_in_unpacked() + + diff = new_count - original_count + diff_str = f"+{diff}" if diff > 0 else str(diff) + print(f"\nParagraphs: {original_count} → {new_count} ({diff_str})") + + def _parse_id_value(self, val: str, base: int = 16) -> int: + return int(val, base) + + def validate_id_constraints(self): + errors = [] + para_id_attr = f"{{{self.W14_NAMESPACE}}}paraId" + durable_id_attr = f"{{{self.W16CID_NAMESPACE}}}durableId" + + for xml_file in self.xml_files: + try: + for elem in lxml.etree.parse(str(xml_file)).iter(): + if val := elem.get(para_id_attr): + if self._parse_id_value(val, base=16) >= 0x80000000: + errors.append( + f" {xml_file.name}:{elem.sourceline}: paraId={val} >= 0x80000000" + ) + + if val := elem.get(durable_id_attr): + if xml_file.name == "numbering.xml": + try: + if self._parse_id_value(val, base=10) >= 0x7FFFFFFF: + errors.append( + f" {xml_file.name}:{elem.sourceline}: " + f"durableId={val} >= 0x7FFFFFFF" + ) + except ValueError: + errors.append( + f" {xml_file.name}:{elem.sourceline}: " + f"durableId={val} must be decimal in numbering.xml" + ) + else: + if self._parse_id_value(val, base=16) >= 0x7FFFFFFF: + errors.append( + f" {xml_file.name}:{elem.sourceline}: " + f"durableId={val} >= 0x7FFFFFFF" + ) + except Exception: + pass + + if errors: + print(f"FAILED - {len(errors)} ID constraint violations:") + for e in errors: + print(e) + elif self.verbose: + print("PASSED - All paraId/durableId values within constraints") + return not errors + + def validate_comment_markers(self): + errors = [] + + document_xml = None + comments_xml = None + for xml_file in self.xml_files: + if xml_file.name == "document.xml" and "word" in str(xml_file): + document_xml = xml_file + elif xml_file.name == "comments.xml": + comments_xml = xml_file + + if not document_xml: + if self.verbose: + print("PASSED - No document.xml found (skipping comment validation)") + return True + + try: + doc_root = lxml.etree.parse(str(document_xml)).getroot() + namespaces = {"w": self.WORD_2006_NAMESPACE} + + range_starts = { + elem.get(f"{{{self.WORD_2006_NAMESPACE}}}id") + for elem in doc_root.xpath( + ".//w:commentRangeStart", namespaces=namespaces + ) + } + range_ends = { + elem.get(f"{{{self.WORD_2006_NAMESPACE}}}id") + for elem in doc_root.xpath( + ".//w:commentRangeEnd", namespaces=namespaces + ) + } + references = { + elem.get(f"{{{self.WORD_2006_NAMESPACE}}}id") + for elem in doc_root.xpath( + ".//w:commentReference", namespaces=namespaces + ) + } + + orphaned_ends = range_ends - range_starts + for comment_id in sorted( + orphaned_ends, key=lambda x: int(x) if x and x.isdigit() else 0 + ): + errors.append( + f' document.xml: commentRangeEnd id="{comment_id}" has no matching commentRangeStart' + ) + + orphaned_starts = range_starts - range_ends + for comment_id in sorted( + orphaned_starts, key=lambda x: int(x) if x and x.isdigit() else 0 + ): + errors.append( + f' document.xml: commentRangeStart id="{comment_id}" has no matching commentRangeEnd' + ) + + comment_ids = set() + if comments_xml and comments_xml.exists(): + comments_root = lxml.etree.parse(str(comments_xml)).getroot() + comment_ids = { + elem.get(f"{{{self.WORD_2006_NAMESPACE}}}id") + for elem in comments_root.xpath( + ".//w:comment", namespaces=namespaces + ) + } + + marker_ids = range_starts | range_ends | references + invalid_refs = marker_ids - comment_ids + for comment_id in sorted( + invalid_refs, key=lambda x: int(x) if x and x.isdigit() else 0 + ): + if comment_id: + errors.append( + f' document.xml: marker id="{comment_id}" references non-existent comment' + ) + + except (lxml.etree.XMLSyntaxError, Exception) as e: + errors.append(f" Error parsing XML: {e}") + + if errors: + print(f"FAILED - {len(errors)} comment marker violations:") + for error in errors: + print(error) + return False + else: + if self.verbose: + print("PASSED - All comment markers properly paired") + return True + + def repair(self) -> int: + repairs = super().repair() + repairs += self.repair_durableId() + return repairs + + def repair_durableId(self) -> int: + repairs = 0 + + for xml_file in self.xml_files: + try: + content = xml_file.read_text(encoding="utf-8") + dom = defusedxml.minidom.parseString(content) + modified = False + + for elem in dom.getElementsByTagName("*"): + if not elem.hasAttribute("w16cid:durableId"): + continue + + durable_id = elem.getAttribute("w16cid:durableId") + needs_repair = False + + if xml_file.name == "numbering.xml": + try: + needs_repair = ( + self._parse_id_value(durable_id, base=10) >= 0x7FFFFFFF + ) + except ValueError: + needs_repair = True + else: + try: + needs_repair = ( + self._parse_id_value(durable_id, base=16) >= 0x7FFFFFFF + ) + except ValueError: + needs_repair = True + + if needs_repair: + value = random.randint(1, 0x7FFFFFFE) + if xml_file.name == "numbering.xml": + new_id = str(value) + else: + new_id = f"{value:08X}" + + elem.setAttribute("w16cid:durableId", new_id) + print( + f" Repaired: {xml_file.name}: durableId {durable_id} → {new_id}" + ) + repairs += 1 + modified = True + + if modified: + xml_file.write_bytes(dom.toxml(encoding="UTF-8")) + + except Exception: + pass + + return repairs + + +if __name__ == "__main__": + raise RuntimeError("This module should not be run directly.") diff --git a/mateclaw-server/src/main/resources/skills/pptx/scripts/office/validators/pptx.py b/mateclaw-server/src/main/resources/skills/pptx/scripts/office/validators/pptx.py new file mode 100644 index 00000000..09842aa9 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/pptx/scripts/office/validators/pptx.py @@ -0,0 +1,275 @@ +""" +Validator for PowerPoint presentation XML files against XSD schemas. +""" + +import re + +from .base import BaseSchemaValidator + + +class PPTXSchemaValidator(BaseSchemaValidator): + + PRESENTATIONML_NAMESPACE = ( + "http://schemas.openxmlformats.org/presentationml/2006/main" + ) + + ELEMENT_RELATIONSHIP_TYPES = { + "sldid": "slide", + "sldmasterid": "slidemaster", + "notesmasterid": "notesmaster", + "sldlayoutid": "slidelayout", + "themeid": "theme", + "tablestyleid": "tablestyles", + } + + def validate(self): + if not self.validate_xml(): + return False + + all_valid = True + if not self.validate_namespaces(): + all_valid = False + + if not self.validate_unique_ids(): + all_valid = False + + if not self.validate_uuid_ids(): + all_valid = False + + if not self.validate_file_references(): + all_valid = False + + if not self.validate_slide_layout_ids(): + all_valid = False + + if not self.validate_content_types(): + all_valid = False + + if not self.validate_against_xsd(): + all_valid = False + + if not self.validate_notes_slide_references(): + all_valid = False + + if not self.validate_all_relationship_ids(): + all_valid = False + + if not self.validate_no_duplicate_slide_layouts(): + all_valid = False + + return all_valid + + def validate_uuid_ids(self): + import lxml.etree + + errors = [] + uuid_pattern = re.compile( + r"^[\{\(]?[0-9A-Fa-f]{8}-?[0-9A-Fa-f]{4}-?[0-9A-Fa-f]{4}-?[0-9A-Fa-f]{4}-?[0-9A-Fa-f]{12}[\}\)]?$" + ) + + for xml_file in self.xml_files: + try: + root = lxml.etree.parse(str(xml_file)).getroot() + + for elem in root.iter(): + for attr, value in elem.attrib.items(): + attr_name = attr.split("}")[-1].lower() + if attr_name == "id" or attr_name.endswith("id"): + if self._looks_like_uuid(value): + if not uuid_pattern.match(value): + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: " + f"Line {elem.sourceline}: ID '{value}' appears to be a UUID but contains invalid hex characters" + ) + + except (lxml.etree.XMLSyntaxError, Exception) as e: + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: Error: {e}" + ) + + if errors: + print(f"FAILED - Found {len(errors)} UUID ID validation errors:") + for error in errors: + print(error) + return False + else: + if self.verbose: + print("PASSED - All UUID-like IDs contain valid hex values") + return True + + def _looks_like_uuid(self, value): + clean_value = value.strip("{}()").replace("-", "") + return len(clean_value) == 32 and all(c.isalnum() for c in clean_value) + + def validate_slide_layout_ids(self): + import lxml.etree + + errors = [] + + slide_masters = list(self.unpacked_dir.glob("ppt/slideMasters/*.xml")) + + if not slide_masters: + if self.verbose: + print("PASSED - No slide masters found") + return True + + for slide_master in slide_masters: + try: + root = lxml.etree.parse(str(slide_master)).getroot() + + rels_file = slide_master.parent / "_rels" / f"{slide_master.name}.rels" + + if not rels_file.exists(): + errors.append( + f" {slide_master.relative_to(self.unpacked_dir)}: " + f"Missing relationships file: {rels_file.relative_to(self.unpacked_dir)}" + ) + continue + + rels_root = lxml.etree.parse(str(rels_file)).getroot() + + valid_layout_rids = set() + for rel in rels_root.findall( + f".//{{{self.PACKAGE_RELATIONSHIPS_NAMESPACE}}}Relationship" + ): + rel_type = rel.get("Type", "") + if "slideLayout" in rel_type: + valid_layout_rids.add(rel.get("Id")) + + for sld_layout_id in root.findall( + f".//{{{self.PRESENTATIONML_NAMESPACE}}}sldLayoutId" + ): + r_id = sld_layout_id.get( + f"{{{self.OFFICE_RELATIONSHIPS_NAMESPACE}}}id" + ) + layout_id = sld_layout_id.get("id") + + if r_id and r_id not in valid_layout_rids: + errors.append( + f" {slide_master.relative_to(self.unpacked_dir)}: " + f"Line {sld_layout_id.sourceline}: sldLayoutId with id='{layout_id}' " + f"references r:id='{r_id}' which is not found in slide layout relationships" + ) + + except (lxml.etree.XMLSyntaxError, Exception) as e: + errors.append( + f" {slide_master.relative_to(self.unpacked_dir)}: Error: {e}" + ) + + if errors: + print(f"FAILED - Found {len(errors)} slide layout ID validation errors:") + for error in errors: + print(error) + print( + "Remove invalid references or add missing slide layouts to the relationships file." + ) + return False + else: + if self.verbose: + print("PASSED - All slide layout IDs reference valid slide layouts") + return True + + def validate_no_duplicate_slide_layouts(self): + import lxml.etree + + errors = [] + slide_rels_files = list(self.unpacked_dir.glob("ppt/slides/_rels/*.xml.rels")) + + for rels_file in slide_rels_files: + try: + root = lxml.etree.parse(str(rels_file)).getroot() + + layout_rels = [ + rel + for rel in root.findall( + f".//{{{self.PACKAGE_RELATIONSHIPS_NAMESPACE}}}Relationship" + ) + if "slideLayout" in rel.get("Type", "") + ] + + if len(layout_rels) > 1: + errors.append( + f" {rels_file.relative_to(self.unpacked_dir)}: has {len(layout_rels)} slideLayout references" + ) + + except Exception as e: + errors.append( + f" {rels_file.relative_to(self.unpacked_dir)}: Error: {e}" + ) + + if errors: + print("FAILED - Found slides with duplicate slideLayout references:") + for error in errors: + print(error) + return False + else: + if self.verbose: + print("PASSED - All slides have exactly one slideLayout reference") + return True + + def validate_notes_slide_references(self): + import lxml.etree + + errors = [] + notes_slide_references = {} + + slide_rels_files = list(self.unpacked_dir.glob("ppt/slides/_rels/*.xml.rels")) + + if not slide_rels_files: + if self.verbose: + print("PASSED - No slide relationship files found") + return True + + for rels_file in slide_rels_files: + try: + root = lxml.etree.parse(str(rels_file)).getroot() + + for rel in root.findall( + f".//{{{self.PACKAGE_RELATIONSHIPS_NAMESPACE}}}Relationship" + ): + rel_type = rel.get("Type", "") + if "notesSlide" in rel_type: + target = rel.get("Target", "") + if target: + normalized_target = target.replace("../", "") + + slide_name = rels_file.stem.replace( + ".xml", "" + ) + + if normalized_target not in notes_slide_references: + notes_slide_references[normalized_target] = [] + notes_slide_references[normalized_target].append( + (slide_name, rels_file) + ) + + except (lxml.etree.XMLSyntaxError, Exception) as e: + errors.append( + f" {rels_file.relative_to(self.unpacked_dir)}: Error: {e}" + ) + + for target, references in notes_slide_references.items(): + if len(references) > 1: + slide_names = [ref[0] for ref in references] + errors.append( + f" Notes slide '{target}' is referenced by multiple slides: {', '.join(slide_names)}" + ) + for slide_name, rels_file in references: + errors.append(f" - {rels_file.relative_to(self.unpacked_dir)}") + + if errors: + print( + f"FAILED - Found {len([e for e in errors if not e.startswith(' ')])} notes slide reference validation errors:" + ) + for error in errors: + print(error) + print("Each slide may optionally have its own slide file.") + return False + else: + if self.verbose: + print("PASSED - All notes slide references are unique") + return True + + +if __name__ == "__main__": + raise RuntimeError("This module should not be run directly.") diff --git a/mateclaw-server/src/main/resources/skills/pptx/scripts/office/validators/redlining.py b/mateclaw-server/src/main/resources/skills/pptx/scripts/office/validators/redlining.py new file mode 100644 index 00000000..71c81b6b --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/pptx/scripts/office/validators/redlining.py @@ -0,0 +1,247 @@ +""" +Validator for tracked changes in Word documents. +""" + +import subprocess +import tempfile +import zipfile +from pathlib import Path + + +class RedliningValidator: + + def __init__(self, unpacked_dir, original_docx, verbose=False, author="Claude"): + self.unpacked_dir = Path(unpacked_dir) + self.original_docx = Path(original_docx) + self.verbose = verbose + self.author = author + self.namespaces = { + "w": "http://schemas.openxmlformats.org/wordprocessingml/2006/main" + } + + def repair(self) -> int: + return 0 + + def validate(self): + modified_file = self.unpacked_dir / "word" / "document.xml" + if not modified_file.exists(): + print(f"FAILED - Modified document.xml not found at {modified_file}") + return False + + try: + import xml.etree.ElementTree as ET + + tree = ET.parse(modified_file) + root = tree.getroot() + + del_elements = root.findall(".//w:del", self.namespaces) + ins_elements = root.findall(".//w:ins", self.namespaces) + + author_del_elements = [ + elem + for elem in del_elements + if elem.get(f"{{{self.namespaces['w']}}}author") == self.author + ] + author_ins_elements = [ + elem + for elem in ins_elements + if elem.get(f"{{{self.namespaces['w']}}}author") == self.author + ] + + if not author_del_elements and not author_ins_elements: + if self.verbose: + print(f"PASSED - No tracked changes by {self.author} found.") + return True + + except Exception: + pass + + with tempfile.TemporaryDirectory() as temp_dir: + temp_path = Path(temp_dir) + + try: + with zipfile.ZipFile(self.original_docx, "r") as zip_ref: + zip_ref.extractall(temp_path) + except Exception as e: + print(f"FAILED - Error unpacking original docx: {e}") + return False + + original_file = temp_path / "word" / "document.xml" + if not original_file.exists(): + print( + f"FAILED - Original document.xml not found in {self.original_docx}" + ) + return False + + try: + import xml.etree.ElementTree as ET + + modified_tree = ET.parse(modified_file) + modified_root = modified_tree.getroot() + original_tree = ET.parse(original_file) + original_root = original_tree.getroot() + except ET.ParseError as e: + print(f"FAILED - Error parsing XML files: {e}") + return False + + self._remove_author_tracked_changes(original_root) + self._remove_author_tracked_changes(modified_root) + + modified_text = self._extract_text_content(modified_root) + original_text = self._extract_text_content(original_root) + + if modified_text != original_text: + error_message = self._generate_detailed_diff( + original_text, modified_text + ) + print(error_message) + return False + + if self.verbose: + print(f"PASSED - All changes by {self.author} are properly tracked") + return True + + def _generate_detailed_diff(self, original_text, modified_text): + error_parts = [ + f"FAILED - Document text doesn't match after removing {self.author}'s tracked changes", + "", + "Likely causes:", + " 1. Modified text inside another author's or tags", + " 2. Made edits without proper tracked changes", + " 3. Didn't nest inside when deleting another's insertion", + "", + "For pre-redlined documents, use correct patterns:", + " - To reject another's INSERTION: Nest inside their ", + " - To restore another's DELETION: Add new AFTER their ", + "", + ] + + git_diff = self._get_git_word_diff(original_text, modified_text) + if git_diff: + error_parts.extend(["Differences:", "============", git_diff]) + else: + error_parts.append("Unable to generate word diff (git not available)") + + return "\n".join(error_parts) + + def _get_git_word_diff(self, original_text, modified_text): + try: + with tempfile.TemporaryDirectory() as temp_dir: + temp_path = Path(temp_dir) + + original_file = temp_path / "original.txt" + modified_file = temp_path / "modified.txt" + + original_file.write_text(original_text, encoding="utf-8") + modified_file.write_text(modified_text, encoding="utf-8") + + result = subprocess.run( + [ + "git", + "diff", + "--word-diff=plain", + "--word-diff-regex=.", + "-U0", + "--no-index", + str(original_file), + str(modified_file), + ], + capture_output=True, + text=True, + ) + + if result.stdout.strip(): + lines = result.stdout.split("\n") + content_lines = [] + in_content = False + for line in lines: + if line.startswith("@@"): + in_content = True + continue + if in_content and line.strip(): + content_lines.append(line) + + if content_lines: + return "\n".join(content_lines) + + result = subprocess.run( + [ + "git", + "diff", + "--word-diff=plain", + "-U0", + "--no-index", + str(original_file), + str(modified_file), + ], + capture_output=True, + text=True, + ) + + if result.stdout.strip(): + lines = result.stdout.split("\n") + content_lines = [] + in_content = False + for line in lines: + if line.startswith("@@"): + in_content = True + continue + if in_content and line.strip(): + content_lines.append(line) + return "\n".join(content_lines) + + except (subprocess.CalledProcessError, FileNotFoundError, Exception): + pass + + return None + + def _remove_author_tracked_changes(self, root): + ins_tag = f"{{{self.namespaces['w']}}}ins" + del_tag = f"{{{self.namespaces['w']}}}del" + author_attr = f"{{{self.namespaces['w']}}}author" + + for parent in root.iter(): + to_remove = [] + for child in parent: + if child.tag == ins_tag and child.get(author_attr) == self.author: + to_remove.append(child) + for elem in to_remove: + parent.remove(elem) + + deltext_tag = f"{{{self.namespaces['w']}}}delText" + t_tag = f"{{{self.namespaces['w']}}}t" + + for parent in root.iter(): + to_process = [] + for child in parent: + if child.tag == del_tag and child.get(author_attr) == self.author: + to_process.append((child, list(parent).index(child))) + + for del_elem, del_index in reversed(to_process): + for elem in del_elem.iter(): + if elem.tag == deltext_tag: + elem.tag = t_tag + + for child in reversed(list(del_elem)): + parent.insert(del_index, child) + parent.remove(del_elem) + + def _extract_text_content(self, root): + p_tag = f"{{{self.namespaces['w']}}}p" + t_tag = f"{{{self.namespaces['w']}}}t" + + paragraphs = [] + for p_elem in root.findall(f".//{p_tag}"): + text_parts = [] + for t_elem in p_elem.findall(f".//{t_tag}"): + if t_elem.text: + text_parts.append(t_elem.text) + paragraph_text = "".join(text_parts) + if paragraph_text: + paragraphs.append(paragraph_text) + + return "\n".join(paragraphs) + + +if __name__ == "__main__": + raise RuntimeError("This module should not be run directly.") diff --git a/mateclaw-server/src/main/resources/skills/pptx/scripts/thumbnail.py b/mateclaw-server/src/main/resources/skills/pptx/scripts/thumbnail.py new file mode 100755 index 00000000..bf4782fa --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/pptx/scripts/thumbnail.py @@ -0,0 +1,306 @@ +"""Create thumbnail grids from PowerPoint presentation slides. + +Creates a grid layout of slide thumbnails for quick visual analysis. +Labels each thumbnail with its XML filename (e.g., slide1.xml). +Hidden slides are shown with a placeholder pattern. + +Usage: + python thumbnail.py input.pptx [output_prefix] [--cols N] + +Examples: + python thumbnail.py presentation.pptx + # Creates: thumbnails.jpg + + python thumbnail.py template.pptx grid --cols 4 + # Creates: grid.jpg (or grid-1.jpg, grid-2.jpg for large decks) +""" + +import argparse +import subprocess +import sys +import tempfile +import zipfile +from pathlib import Path + +import defusedxml.minidom +from office.soffice import run_soffice +from PIL import Image, ImageDraw, ImageFont + +THUMBNAIL_WIDTH = 300 +CONVERSION_DPI = 100 +MAX_COLS = 6 +DEFAULT_COLS = 3 +JPEG_QUALITY = 95 +GRID_PADDING = 20 +BORDER_WIDTH = 2 +FONT_SIZE_RATIO = 0.10 +LABEL_PADDING_RATIO = 0.4 + + +def main(): + parser = argparse.ArgumentParser( + description="Create thumbnail grids from PowerPoint slides." + ) + parser.add_argument("input", help="Input PowerPoint file (.pptx)") + parser.add_argument( + "output_prefix", + nargs="?", + default="thumbnails", + help="Output prefix for image files (default: thumbnails)", + ) + parser.add_argument( + "--cols", + type=int, + default=DEFAULT_COLS, + help=f"Number of columns (default: {DEFAULT_COLS}, max: {MAX_COLS})", + ) + + args = parser.parse_args() + + cols = min(args.cols, MAX_COLS) + if args.cols > MAX_COLS: + print(f"Warning: Columns limited to {MAX_COLS}") + + input_path = Path(args.input) + if not input_path.exists() or input_path.suffix.lower() != ".pptx": + print(f"Error: Invalid PowerPoint file: {args.input}", file=sys.stderr) + sys.exit(1) + + output_path = Path(f"{args.output_prefix}.jpg") + + try: + slide_info = get_slide_info(input_path) + + with tempfile.TemporaryDirectory() as temp_dir: + temp_path = Path(temp_dir) + visible_images = convert_to_images(input_path, temp_path) + + if not visible_images and not any(s["hidden"] for s in slide_info): + print("Error: No slides found", file=sys.stderr) + sys.exit(1) + + slides = build_slide_list(slide_info, visible_images, temp_path) + + grid_files = create_grids(slides, cols, THUMBNAIL_WIDTH, output_path) + + print(f"Created {len(grid_files)} grid(s):") + for grid_file in grid_files: + print(f" {grid_file}") + + except Exception as e: + print(f"Error: {e}", file=sys.stderr) + sys.exit(1) + + +def get_slide_info(pptx_path: Path) -> list[dict]: + with zipfile.ZipFile(pptx_path, "r") as zf: + rels_content = zf.read("ppt/_rels/presentation.xml.rels").decode("utf-8") + rels_dom = defusedxml.minidom.parseString(rels_content) + + rid_to_slide = {} + for rel in rels_dom.getElementsByTagName("Relationship"): + rid = rel.getAttribute("Id") + target = rel.getAttribute("Target") + rel_type = rel.getAttribute("Type") + if "slide" in rel_type and target.startswith("slides/"): + rid_to_slide[rid] = target.replace("slides/", "") + + pres_content = zf.read("ppt/presentation.xml").decode("utf-8") + pres_dom = defusedxml.minidom.parseString(pres_content) + + slides = [] + for sld_id in pres_dom.getElementsByTagName("p:sldId"): + rid = sld_id.getAttribute("r:id") + if rid in rid_to_slide: + hidden = sld_id.getAttribute("show") == "0" + slides.append({"name": rid_to_slide[rid], "hidden": hidden}) + + return slides + + +def build_slide_list( + slide_info: list[dict], + visible_images: list[Path], + temp_dir: Path, +) -> list[tuple[Path, str]]: + if visible_images: + with Image.open(visible_images[0]) as img: + placeholder_size = img.size + else: + placeholder_size = (1920, 1080) + + slides = [] + visible_idx = 0 + + for info in slide_info: + if info["hidden"]: + placeholder_path = temp_dir / f"hidden-{info['name']}.jpg" + placeholder_img = create_hidden_placeholder(placeholder_size) + placeholder_img.save(placeholder_path, "JPEG") + slides.append((placeholder_path, f"{info['name']} (hidden)")) + else: + if visible_idx < len(visible_images): + slides.append((visible_images[visible_idx], info["name"])) + visible_idx += 1 + + return slides + + +def create_hidden_placeholder(size: tuple[int, int]) -> Image.Image: + img = Image.new("RGB", size, color="#F0F0F0") + draw = ImageDraw.Draw(img) + line_width = max(5, min(size) // 100) + draw.line([(0, 0), size], fill="#CCCCCC", width=line_width) + draw.line([(size[0], 0), (0, size[1])], fill="#CCCCCC", width=line_width) + return img + + +def convert_to_images(pptx_path: Path, temp_dir: Path) -> list[Path]: + pdf_path = temp_dir / f"{pptx_path.stem}.pdf" + + result = run_soffice( + [ + "--headless", + "--convert-to", + "pdf", + "--outdir", + str(temp_dir), + str(pptx_path), + ], + capture_output=True, + text=True, + ) + if result.returncode != 0 or not pdf_path.exists(): + raise RuntimeError("PDF conversion failed") + + # Try pdftoppm first, fall back to pdf2image (cross-platform) + try: + result = subprocess.run( + [ + "pdftoppm", + "-jpeg", + "-r", + str(CONVERSION_DPI), + str(pdf_path), + str(temp_dir / "slide"), + ], + capture_output=True, + text=True, + ) + except FileNotFoundError: + # pdftoppm not available (e.g. Windows without Poppler); use pdf2image + try: + from pdf2image import convert_from_path as _pdf_convert + + images = _pdf_convert(str(pdf_path), dpi=CONVERSION_DPI) + for idx, img in enumerate(images, start=1): + out = temp_dir / f"slide-{idx:02d}.jpg" + img.save(str(out), "JPEG") + except ImportError: + raise RuntimeError( + "Image conversion failed: pdftoppm not found and " + "pdf2image package is not installed. " + "Install poppler or run: pip install pdf2image" + ) + else: + if result.returncode != 0: + stderr = (result.stderr or "").strip() or "unknown pdftoppm error" + raise RuntimeError(f"Image conversion failed: {stderr}") + + return sorted(temp_dir.glob("slide-*.jpg")) + + +def create_grids( + slides: list[tuple[Path, str]], + cols: int, + width: int, + output_path: Path, +) -> list[str]: + max_per_grid = cols * (cols + 1) + grid_files = [] + + for chunk_idx, start_idx in enumerate(range(0, len(slides), max_per_grid)): + end_idx = min(start_idx + max_per_grid, len(slides)) + chunk_slides = slides[start_idx:end_idx] + + grid = create_grid(chunk_slides, cols, width) + + if len(slides) <= max_per_grid: + grid_filename = output_path + else: + stem = output_path.stem + suffix = output_path.suffix + grid_filename = output_path.parent / f"{stem}-{chunk_idx + 1}{suffix}" + + grid_filename.parent.mkdir(parents=True, exist_ok=True) + grid.save(str(grid_filename), quality=JPEG_QUALITY) + grid_files.append(str(grid_filename)) + + return grid_files + + +def create_grid( + slides: list[tuple[Path, str]], + cols: int, + width: int, +) -> Image.Image: + font_size = int(width * FONT_SIZE_RATIO) + label_padding = int(font_size * LABEL_PADDING_RATIO) + + with Image.open(slides[0][0]) as img: + aspect = img.height / img.width + height = int(width * aspect) + + rows = (len(slides) + cols - 1) // cols + grid_w = cols * width + (cols + 1) * GRID_PADDING + grid_h = rows * (height + font_size + label_padding * 2) + (rows + 1) * GRID_PADDING + + grid = Image.new("RGB", (grid_w, grid_h), "white") + draw = ImageDraw.Draw(grid) + + try: + font = ImageFont.load_default(size=font_size) + except Exception: + font = ImageFont.load_default() + + for i, (img_path, slide_name) in enumerate(slides): + row, col = i // cols, i % cols + x = col * width + (col + 1) * GRID_PADDING + y_base = ( + row * (height + font_size + label_padding * 2) + (row + 1) * GRID_PADDING + ) + + label = slide_name + bbox = draw.textbbox((0, 0), label, font=font) + text_w = bbox[2] - bbox[0] + draw.text( + (x + (width - text_w) // 2, y_base + label_padding), + label, + fill="black", + font=font, + ) + + y_thumbnail = y_base + label_padding + font_size + label_padding + + with Image.open(img_path) as img: + img.thumbnail((width, height), Image.Resampling.LANCZOS) + w, h = img.size + tx = x + (width - w) // 2 + ty = y_thumbnail + (height - h) // 2 + grid.paste(img, (tx, ty)) + + if BORDER_WIDTH > 0: + draw.rectangle( + [ + (tx - BORDER_WIDTH, ty - BORDER_WIDTH), + (tx + w + BORDER_WIDTH - 1, ty + h + BORDER_WIDTH - 1), + ], + outline="gray", + width=BORDER_WIDTH, + ) + + return grid + + +if __name__ == "__main__": + main() diff --git a/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/helpers/__init__.py b/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/helpers/__init__.py new file mode 100644 index 00000000..e69de29b diff --git a/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/helpers/merge_runs.py b/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/helpers/merge_runs.py new file mode 100644 index 00000000..ad7c25ee --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/helpers/merge_runs.py @@ -0,0 +1,199 @@ +"""Merge adjacent runs with identical formatting in DOCX. + +Merges adjacent elements that have identical properties. +Works on runs in paragraphs and inside tracked changes (, ). + +Also: +- Removes rsid attributes from runs (revision metadata that doesn't affect rendering) +- Removes proofErr elements (spell/grammar markers that block merging) +""" + +from pathlib import Path + +import defusedxml.minidom + + +def merge_runs(input_dir: str) -> tuple[int, str]: + doc_xml = Path(input_dir) / "word" / "document.xml" + + if not doc_xml.exists(): + return 0, f"Error: {doc_xml} not found" + + try: + dom = defusedxml.minidom.parseString(doc_xml.read_text(encoding="utf-8")) + root = dom.documentElement + + _remove_elements(root, "proofErr") + _strip_run_rsid_attrs(root) + + containers = {run.parentNode for run in _find_elements(root, "r")} + + merge_count = 0 + for container in containers: + merge_count += _merge_runs_in(container) + + doc_xml.write_bytes(dom.toxml(encoding="UTF-8")) + return merge_count, f"Merged {merge_count} runs" + + except Exception as e: + return 0, f"Error: {e}" + + + + +def _find_elements(root, tag: str) -> list: + results = [] + + def traverse(node): + if node.nodeType == node.ELEMENT_NODE: + name = node.localName or node.tagName + if name == tag or name.endswith(f":{tag}"): + results.append(node) + for child in node.childNodes: + traverse(child) + + traverse(root) + return results + + +def _get_child(parent, tag: str): + for child in parent.childNodes: + if child.nodeType == child.ELEMENT_NODE: + name = child.localName or child.tagName + if name == tag or name.endswith(f":{tag}"): + return child + return None + + +def _get_children(parent, tag: str) -> list: + results = [] + for child in parent.childNodes: + if child.nodeType == child.ELEMENT_NODE: + name = child.localName or child.tagName + if name == tag or name.endswith(f":{tag}"): + results.append(child) + return results + + +def _is_adjacent(elem1, elem2) -> bool: + node = elem1.nextSibling + while node: + if node == elem2: + return True + if node.nodeType == node.ELEMENT_NODE: + return False + if node.nodeType == node.TEXT_NODE and node.data.strip(): + return False + node = node.nextSibling + return False + + + + +def _remove_elements(root, tag: str): + for elem in _find_elements(root, tag): + if elem.parentNode: + elem.parentNode.removeChild(elem) + + +def _strip_run_rsid_attrs(root): + for run in _find_elements(root, "r"): + for attr in list(run.attributes.values()): + if "rsid" in attr.name.lower(): + run.removeAttribute(attr.name) + + + + +def _merge_runs_in(container) -> int: + merge_count = 0 + run = _first_child_run(container) + + while run: + while True: + next_elem = _next_element_sibling(run) + if next_elem and _is_run(next_elem) and _can_merge(run, next_elem): + _merge_run_content(run, next_elem) + container.removeChild(next_elem) + merge_count += 1 + else: + break + + _consolidate_text(run) + run = _next_sibling_run(run) + + return merge_count + + +def _first_child_run(container): + for child in container.childNodes: + if child.nodeType == child.ELEMENT_NODE and _is_run(child): + return child + return None + + +def _next_element_sibling(node): + sibling = node.nextSibling + while sibling: + if sibling.nodeType == sibling.ELEMENT_NODE: + return sibling + sibling = sibling.nextSibling + return None + + +def _next_sibling_run(node): + sibling = node.nextSibling + while sibling: + if sibling.nodeType == sibling.ELEMENT_NODE: + if _is_run(sibling): + return sibling + sibling = sibling.nextSibling + return None + + +def _is_run(node) -> bool: + name = node.localName or node.tagName + return name == "r" or name.endswith(":r") + + +def _can_merge(run1, run2) -> bool: + rpr1 = _get_child(run1, "rPr") + rpr2 = _get_child(run2, "rPr") + + if (rpr1 is None) != (rpr2 is None): + return False + if rpr1 is None: + return True + return rpr1.toxml() == rpr2.toxml() + + +def _merge_run_content(target, source): + for child in list(source.childNodes): + if child.nodeType == child.ELEMENT_NODE: + name = child.localName or child.tagName + if name != "rPr" and not name.endswith(":rPr"): + target.appendChild(child) + + +def _consolidate_text(run): + t_elements = _get_children(run, "t") + + for i in range(len(t_elements) - 1, 0, -1): + curr, prev = t_elements[i], t_elements[i - 1] + + if _is_adjacent(prev, curr): + prev_text = prev.firstChild.data if prev.firstChild else "" + curr_text = curr.firstChild.data if curr.firstChild else "" + merged = prev_text + curr_text + + if prev.firstChild: + prev.firstChild.data = merged + else: + prev.appendChild(run.ownerDocument.createTextNode(merged)) + + if merged.startswith(" ") or merged.endswith(" "): + prev.setAttribute("xml:space", "preserve") + elif prev.hasAttribute("xml:space"): + prev.removeAttribute("xml:space") + + run.removeChild(curr) diff --git a/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/helpers/simplify_redlines.py b/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/helpers/simplify_redlines.py new file mode 100644 index 00000000..db963bb9 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/helpers/simplify_redlines.py @@ -0,0 +1,197 @@ +"""Simplify tracked changes by merging adjacent w:ins or w:del elements. + +Merges adjacent elements from the same author into a single element. +Same for elements. This makes heavily-redlined documents easier to +work with by reducing the number of tracked change wrappers. + +Rules: +- Only merges w:ins with w:ins, w:del with w:del (same element type) +- Only merges if same author (ignores timestamp differences) +- Only merges if truly adjacent (only whitespace between them) +""" + +import xml.etree.ElementTree as ET +import zipfile +from pathlib import Path + +import defusedxml.minidom + +WORD_NS = "http://schemas.openxmlformats.org/wordprocessingml/2006/main" + + +def simplify_redlines(input_dir: str) -> tuple[int, str]: + doc_xml = Path(input_dir) / "word" / "document.xml" + + if not doc_xml.exists(): + return 0, f"Error: {doc_xml} not found" + + try: + dom = defusedxml.minidom.parseString(doc_xml.read_text(encoding="utf-8")) + root = dom.documentElement + + merge_count = 0 + + containers = _find_elements(root, "p") + _find_elements(root, "tc") + + for container in containers: + merge_count += _merge_tracked_changes_in(container, "ins") + merge_count += _merge_tracked_changes_in(container, "del") + + doc_xml.write_bytes(dom.toxml(encoding="UTF-8")) + return merge_count, f"Simplified {merge_count} tracked changes" + + except Exception as e: + return 0, f"Error: {e}" + + +def _merge_tracked_changes_in(container, tag: str) -> int: + merge_count = 0 + + tracked = [ + child + for child in container.childNodes + if child.nodeType == child.ELEMENT_NODE and _is_element(child, tag) + ] + + if len(tracked) < 2: + return 0 + + i = 0 + while i < len(tracked) - 1: + curr = tracked[i] + next_elem = tracked[i + 1] + + if _can_merge_tracked(curr, next_elem): + _merge_tracked_content(curr, next_elem) + container.removeChild(next_elem) + tracked.pop(i + 1) + merge_count += 1 + else: + i += 1 + + return merge_count + + +def _is_element(node, tag: str) -> bool: + name = node.localName or node.tagName + return name == tag or name.endswith(f":{tag}") + + +def _get_author(elem) -> str: + author = elem.getAttribute("w:author") + if not author: + for attr in elem.attributes.values(): + if attr.localName == "author" or attr.name.endswith(":author"): + return attr.value + return author + + +def _can_merge_tracked(elem1, elem2) -> bool: + if _get_author(elem1) != _get_author(elem2): + return False + + node = elem1.nextSibling + while node and node != elem2: + if node.nodeType == node.ELEMENT_NODE: + return False + if node.nodeType == node.TEXT_NODE and node.data.strip(): + return False + node = node.nextSibling + + return True + + +def _merge_tracked_content(target, source): + while source.firstChild: + child = source.firstChild + source.removeChild(child) + target.appendChild(child) + + +def _find_elements(root, tag: str) -> list: + results = [] + + def traverse(node): + if node.nodeType == node.ELEMENT_NODE: + name = node.localName or node.tagName + if name == tag or name.endswith(f":{tag}"): + results.append(node) + for child in node.childNodes: + traverse(child) + + traverse(root) + return results + + +def get_tracked_change_authors(doc_xml_path: Path) -> dict[str, int]: + if not doc_xml_path.exists(): + return {} + + try: + tree = ET.parse(doc_xml_path) + root = tree.getroot() + except ET.ParseError: + return {} + + namespaces = {"w": WORD_NS} + author_attr = f"{{{WORD_NS}}}author" + + authors: dict[str, int] = {} + for tag in ["ins", "del"]: + for elem in root.findall(f".//w:{tag}", namespaces): + author = elem.get(author_attr) + if author: + authors[author] = authors.get(author, 0) + 1 + + return authors + + +def _get_authors_from_docx(docx_path: Path) -> dict[str, int]: + try: + with zipfile.ZipFile(docx_path, "r") as zf: + if "word/document.xml" not in zf.namelist(): + return {} + with zf.open("word/document.xml") as f: + tree = ET.parse(f) + root = tree.getroot() + + namespaces = {"w": WORD_NS} + author_attr = f"{{{WORD_NS}}}author" + + authors: dict[str, int] = {} + for tag in ["ins", "del"]: + for elem in root.findall(f".//w:{tag}", namespaces): + author = elem.get(author_attr) + if author: + authors[author] = authors.get(author, 0) + 1 + return authors + except (zipfile.BadZipFile, ET.ParseError): + return {} + + +def infer_author(modified_dir: Path, original_docx: Path, default: str = "Claude") -> str: + modified_xml = modified_dir / "word" / "document.xml" + modified_authors = get_tracked_change_authors(modified_xml) + + if not modified_authors: + return default + + original_authors = _get_authors_from_docx(original_docx) + + new_changes: dict[str, int] = {} + for author, count in modified_authors.items(): + original_count = original_authors.get(author, 0) + diff = count - original_count + if diff > 0: + new_changes[author] = diff + + if not new_changes: + return default + + if len(new_changes) == 1: + return next(iter(new_changes)) + + raise ValueError( + f"Multiple authors added new changes: {new_changes}. " + "Cannot infer which author to validate." + ) diff --git a/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/pack.py b/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/pack.py new file mode 100755 index 00000000..db29ed8b --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/pack.py @@ -0,0 +1,159 @@ +"""Pack a directory into a DOCX, PPTX, or XLSX file. + +Validates with auto-repair, condenses XML formatting, and creates the Office file. + +Usage: + python pack.py [--original ] [--validate true|false] + +Examples: + python pack.py unpacked/ output.docx --original input.docx + python pack.py unpacked/ output.pptx --validate false +""" + +import argparse +import sys +import shutil +import tempfile +import zipfile +from pathlib import Path + +import defusedxml.minidom + +from validators import DOCXSchemaValidator, PPTXSchemaValidator, RedliningValidator + +def pack( + input_directory: str, + output_file: str, + original_file: str | None = None, + validate: bool = True, + infer_author_func=None, +) -> tuple[None, str]: + input_dir = Path(input_directory) + output_path = Path(output_file) + suffix = output_path.suffix.lower() + + if not input_dir.is_dir(): + return None, f"Error: {input_dir} is not a directory" + + if suffix not in {".docx", ".pptx", ".xlsx"}: + return None, f"Error: {output_file} must be a .docx, .pptx, or .xlsx file" + + if validate and original_file: + original_path = Path(original_file) + if original_path.exists(): + success, output = _run_validation( + input_dir, original_path, suffix, infer_author_func + ) + if output: + print(output) + if not success: + return None, f"Error: Validation failed for {input_dir}" + + with tempfile.TemporaryDirectory() as temp_dir: + temp_content_dir = Path(temp_dir) / "content" + shutil.copytree(input_dir, temp_content_dir) + + for pattern in ["*.xml", "*.rels"]: + for xml_file in temp_content_dir.rglob(pattern): + _condense_xml(xml_file) + + output_path.parent.mkdir(parents=True, exist_ok=True) + with zipfile.ZipFile(output_path, "w", zipfile.ZIP_DEFLATED) as zf: + for f in temp_content_dir.rglob("*"): + if f.is_file(): + zf.write(f, f.relative_to(temp_content_dir)) + + return None, f"Successfully packed {input_dir} to {output_file}" + + +def _run_validation( + unpacked_dir: Path, + original_file: Path, + suffix: str, + infer_author_func=None, +) -> tuple[bool, str | None]: + output_lines = [] + validators = [] + + if suffix == ".docx": + author = "Claude" + if infer_author_func: + try: + author = infer_author_func(unpacked_dir, original_file) + except ValueError as e: + print(f"Warning: {e} Using default author 'Claude'.", file=sys.stderr) + + validators = [ + DOCXSchemaValidator(unpacked_dir, original_file), + RedliningValidator(unpacked_dir, original_file, author=author), + ] + elif suffix == ".pptx": + validators = [PPTXSchemaValidator(unpacked_dir, original_file)] + + if not validators: + return True, None + + total_repairs = sum(v.repair() for v in validators) + if total_repairs: + output_lines.append(f"Auto-repaired {total_repairs} issue(s)") + + success = all(v.validate() for v in validators) + + if success: + output_lines.append("All validations PASSED!") + + return success, "\n".join(output_lines) if output_lines else None + + +def _condense_xml(xml_file: Path) -> None: + try: + with open(xml_file, encoding="utf-8") as f: + dom = defusedxml.minidom.parse(f) + + for element in dom.getElementsByTagName("*"): + if element.tagName.endswith(":t"): + continue + + for child in list(element.childNodes): + if ( + child.nodeType == child.TEXT_NODE + and child.nodeValue + and child.nodeValue.strip() == "" + ) or child.nodeType == child.COMMENT_NODE: + element.removeChild(child) + + xml_file.write_bytes(dom.toxml(encoding="UTF-8")) + except Exception as e: + print(f"ERROR: Failed to parse {xml_file.name}: {e}", file=sys.stderr) + raise + + +if __name__ == "__main__": + parser = argparse.ArgumentParser( + description="Pack a directory into a DOCX, PPTX, or XLSX file" + ) + parser.add_argument("input_directory", help="Unpacked Office document directory") + parser.add_argument("output_file", help="Output Office file (.docx/.pptx/.xlsx)") + parser.add_argument( + "--original", + help="Original file for validation comparison", + ) + parser.add_argument( + "--validate", + type=lambda x: x.lower() == "true", + default=True, + metavar="true|false", + help="Run validation with auto-repair (default: true)", + ) + args = parser.parse_args() + + _, message = pack( + args.input_directory, + args.output_file, + original_file=args.original, + validate=args.validate, + ) + print(message) + + if "Error" in message: + sys.exit(1) diff --git a/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-chart.xsd b/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-chart.xsd new file mode 100644 index 00000000..6454ef9a --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-chart.xsd @@ -0,0 +1,1499 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-chartDrawing.xsd b/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-chartDrawing.xsd new file mode 100644 index 00000000..afa4f463 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-chartDrawing.xsd @@ -0,0 +1,146 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-diagram.xsd b/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-diagram.xsd new file mode 100644 index 00000000..64e66b8a --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-diagram.xsd @@ -0,0 +1,1085 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-lockedCanvas.xsd b/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-lockedCanvas.xsd new file mode 100644 index 00000000..687eea82 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-lockedCanvas.xsd @@ -0,0 +1,11 @@ + + + + + diff --git a/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-main.xsd b/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-main.xsd new file mode 100644 index 00000000..6ac81b06 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-main.xsd @@ -0,0 +1,3081 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-picture.xsd b/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-picture.xsd new file mode 100644 index 00000000..1dbf0514 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-picture.xsd @@ -0,0 +1,23 @@ + + + + + + + + + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-spreadsheetDrawing.xsd b/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-spreadsheetDrawing.xsd new file mode 100644 index 00000000..f1af17db --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-spreadsheetDrawing.xsd @@ -0,0 +1,185 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-wordprocessingDrawing.xsd b/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-wordprocessingDrawing.xsd new file mode 100644 index 00000000..0a185ab6 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/dml-wordprocessingDrawing.xsd @@ -0,0 +1,287 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/pml.xsd b/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/pml.xsd new file mode 100644 index 00000000..14ef4888 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/pml.xsd @@ -0,0 +1,1676 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-additionalCharacteristics.xsd b/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-additionalCharacteristics.xsd new file mode 100644 index 00000000..c20f3bf1 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-additionalCharacteristics.xsd @@ -0,0 +1,28 @@ + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-bibliography.xsd b/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-bibliography.xsd new file mode 100644 index 00000000..ac602522 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-bibliography.xsd @@ -0,0 +1,144 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-commonSimpleTypes.xsd b/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-commonSimpleTypes.xsd new file mode 100644 index 00000000..424b8ba8 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-commonSimpleTypes.xsd @@ -0,0 +1,174 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-customXmlDataProperties.xsd b/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-customXmlDataProperties.xsd new file mode 100644 index 00000000..2bddce29 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-customXmlDataProperties.xsd @@ -0,0 +1,25 @@ + + + + + + + + + + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-customXmlSchemaProperties.xsd b/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-customXmlSchemaProperties.xsd new file mode 100644 index 00000000..8a8c18ba --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-customXmlSchemaProperties.xsd @@ -0,0 +1,18 @@ + + + + + + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesCustom.xsd b/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesCustom.xsd new file mode 100644 index 00000000..5c42706a --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesCustom.xsd @@ -0,0 +1,59 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesExtended.xsd b/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesExtended.xsd new file mode 100644 index 00000000..853c341c --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesExtended.xsd @@ -0,0 +1,56 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesVariantTypes.xsd b/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesVariantTypes.xsd new file mode 100644 index 00000000..da835ee8 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesVariantTypes.xsd @@ -0,0 +1,195 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-math.xsd b/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-math.xsd new file mode 100644 index 00000000..87ad2658 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-math.xsd @@ -0,0 +1,582 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-relationshipReference.xsd b/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-relationshipReference.xsd new file mode 100644 index 00000000..9e86f1b2 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/shared-relationshipReference.xsd @@ -0,0 +1,25 @@ + + + + + + + + + + + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/sml.xsd b/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/sml.xsd new file mode 100644 index 00000000..d0be42e7 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/sml.xsd @@ -0,0 +1,4439 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-main.xsd b/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-main.xsd new file mode 100644 index 00000000..8821dd18 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-main.xsd @@ -0,0 +1,570 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-officeDrawing.xsd b/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-officeDrawing.xsd new file mode 100644 index 00000000..ca2575c7 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-officeDrawing.xsd @@ -0,0 +1,509 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-presentationDrawing.xsd b/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-presentationDrawing.xsd new file mode 100644 index 00000000..dd079e60 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-presentationDrawing.xsd @@ -0,0 +1,12 @@ + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-spreadsheetDrawing.xsd b/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-spreadsheetDrawing.xsd new file mode 100644 index 00000000..3dd6cf62 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-spreadsheetDrawing.xsd @@ -0,0 +1,108 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-wordprocessingDrawing.xsd b/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-wordprocessingDrawing.xsd new file mode 100644 index 00000000..f1041e34 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/vml-wordprocessingDrawing.xsd @@ -0,0 +1,96 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/wml.xsd b/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/wml.xsd new file mode 100644 index 00000000..9c5b7a63 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/wml.xsd @@ -0,0 +1,3646 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/xml.xsd b/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/xml.xsd new file mode 100644 index 00000000..0f13678d --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/ISO-IEC29500-4_2016/xml.xsd @@ -0,0 +1,116 @@ + + + + + + See http://www.w3.org/XML/1998/namespace.html and + http://www.w3.org/TR/REC-xml for information about this namespace. + + This schema document describes the XML namespace, in a form + suitable for import by other schema documents. + + Note that local names in this namespace are intended to be defined + only by the World Wide Web Consortium or its subgroups. The + following names are currently defined in this namespace and should + not be used with conflicting semantics by any Working Group, + specification, or document instance: + + base (as an attribute name): denotes an attribute whose value + provides a URI to be used as the base for interpreting any + relative URIs in the scope of the element on which it + appears; its value is inherited. This name is reserved + by virtue of its definition in the XML Base specification. + + lang (as an attribute name): denotes an attribute whose value + is a language code for the natural language of the content of + any element; its value is inherited. This name is reserved + by virtue of its definition in the XML specification. + + space (as an attribute name): denotes an attribute whose + value is a keyword indicating what whitespace processing + discipline is intended for the content of the element; its + value is inherited. This name is reserved by virtue of its + definition in the XML specification. + + Father (in any context at all): denotes Jon Bosak, the chair of + the original XML Working Group. This name is reserved by + the following decision of the W3C XML Plenary and + XML Coordination groups: + + In appreciation for his vision, leadership and dedication + the W3C XML Plenary on this 10th day of February, 2000 + reserves for Jon Bosak in perpetuity the XML name + xml:Father + + + + + This schema defines attributes and an attribute group + suitable for use by + schemas wishing to allow xml:base, xml:lang or xml:space attributes + on elements they define. + + To enable this, such a schema must import this schema + for the XML namespace, e.g. as follows: + <schema . . .> + . . . + <import namespace="http://www.w3.org/XML/1998/namespace" + schemaLocation="http://www.w3.org/2001/03/xml.xsd"/> + + Subsequently, qualified reference to any of the attributes + or the group defined below will have the desired effect, e.g. + + <type . . .> + . . . + <attributeGroup ref="xml:specialAttrs"/> + + will define a type which will schema-validate an instance + element with any of those attributes + + + + In keeping with the XML Schema WG's standard versioning + policy, this schema document will persist at + http://www.w3.org/2001/03/xml.xsd. + At the date of issue it can also be found at + http://www.w3.org/2001/xml.xsd. + The schema document at that URI may however change in the future, + in order to remain compatible with the latest version of XML Schema + itself. In other words, if the XML Schema namespace changes, the version + of this document at + http://www.w3.org/2001/xml.xsd will change + accordingly; the version at + http://www.w3.org/2001/03/xml.xsd will not change. + + + + + + In due course, we should install the relevant ISO 2- and 3-letter + codes as the enumerated possible values . . . + + + + + + + + + + + + + + + See http://www.w3.org/TR/xmlbase/ for + information about this attribute. + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/ecma/fouth-edition/opc-contentTypes.xsd b/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/ecma/fouth-edition/opc-contentTypes.xsd new file mode 100644 index 00000000..a6de9d27 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/ecma/fouth-edition/opc-contentTypes.xsd @@ -0,0 +1,42 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/ecma/fouth-edition/opc-coreProperties.xsd b/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/ecma/fouth-edition/opc-coreProperties.xsd new file mode 100644 index 00000000..10e978b6 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/ecma/fouth-edition/opc-coreProperties.xsd @@ -0,0 +1,50 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/ecma/fouth-edition/opc-digSig.xsd b/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/ecma/fouth-edition/opc-digSig.xsd new file mode 100644 index 00000000..4248bf7a --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/ecma/fouth-edition/opc-digSig.xsd @@ -0,0 +1,49 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/ecma/fouth-edition/opc-relationships.xsd b/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/ecma/fouth-edition/opc-relationships.xsd new file mode 100644 index 00000000..56497467 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/ecma/fouth-edition/opc-relationships.xsd @@ -0,0 +1,33 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/mce/mc.xsd b/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/mce/mc.xsd new file mode 100644 index 00000000..ef725457 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/mce/mc.xsd @@ -0,0 +1,75 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/microsoft/wml-2010.xsd b/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/microsoft/wml-2010.xsd new file mode 100644 index 00000000..f65f7777 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/microsoft/wml-2010.xsd @@ -0,0 +1,560 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/microsoft/wml-2012.xsd b/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/microsoft/wml-2012.xsd new file mode 100644 index 00000000..6b00755a --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/microsoft/wml-2012.xsd @@ -0,0 +1,67 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/microsoft/wml-2018.xsd b/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/microsoft/wml-2018.xsd new file mode 100644 index 00000000..f321d333 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/microsoft/wml-2018.xsd @@ -0,0 +1,14 @@ + + + + + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/microsoft/wml-cex-2018.xsd b/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/microsoft/wml-cex-2018.xsd new file mode 100644 index 00000000..364c6a9b --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/microsoft/wml-cex-2018.xsd @@ -0,0 +1,20 @@ + + + + + + + + + + + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/microsoft/wml-cid-2016.xsd b/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/microsoft/wml-cid-2016.xsd new file mode 100644 index 00000000..fed9d15b --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/microsoft/wml-cid-2016.xsd @@ -0,0 +1,13 @@ + + + + + + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/microsoft/wml-sdtdatahash-2020.xsd b/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/microsoft/wml-sdtdatahash-2020.xsd new file mode 100644 index 00000000..680cf154 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/microsoft/wml-sdtdatahash-2020.xsd @@ -0,0 +1,4 @@ + + + + diff --git a/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/microsoft/wml-symex-2015.xsd b/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/microsoft/wml-symex-2015.xsd new file mode 100644 index 00000000..89ada908 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/schemas/microsoft/wml-symex-2015.xsd @@ -0,0 +1,8 @@ + + + + + + + + diff --git a/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/soffice.py b/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/soffice.py new file mode 100644 index 00000000..072354fb --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/soffice.py @@ -0,0 +1,218 @@ +""" +Helper for running LibreOffice (soffice) in environments where AF_UNIX +sockets may be blocked (e.g., sandboxed VMs). Detects the restriction +at runtime and applies an LD_PRELOAD shim if needed. + +Usage: + from office.soffice import run_soffice, get_soffice_cmd, get_soffice_env + + # Option 1 – run soffice directly + result = run_soffice(["--headless", "--convert-to", "pdf", "input.docx"]) + + # Option 2 – get env dict for your own subprocess calls + env = get_soffice_env() + subprocess.run([get_soffice_cmd(), ...], env=env) +""" + +import os +import platform +import shutil +import socket +import subprocess +import tempfile +from pathlib import Path + + +def get_soffice_cmd() -> str: + """Return the soffice command name for the current platform.""" + # Prefer PATH first on all platforms. + path_cmd = shutil.which("soffice") + if path_cmd: + return path_cmd + + if platform.system() == "Windows": + # Windows can expose soffice as .com or .exe; try both on PATH first. + for candidate_name in ("soffice.com", "soffice.exe"): + path_candidate = shutil.which(candidate_name) + if path_candidate: + return path_candidate + + for prog_dir in ( + os.environ.get("PROGRAMFILES", r"C:\Program Files"), + os.environ.get("PROGRAMFILES(X86)", r"C:\Program Files (x86)"), + ): + if not prog_dir: + continue + program_dir = Path(prog_dir) / "LibreOffice" / "program" + for exe_name in ("soffice.com", "soffice.exe"): + candidate = program_dir / exe_name + if candidate.exists(): + return str(candidate) + return "soffice" + return "soffice" + + +def get_soffice_env() -> dict: + env = os.environ.copy() + if platform.system() == "Linux": + env["SAL_USE_VCLPLUGIN"] = "svp" + + if _needs_shim(): + shim = _ensure_shim() + env["LD_PRELOAD"] = str(shim) + + return env + + +def run_soffice(args: list[str], **kwargs) -> subprocess.CompletedProcess: + env = get_soffice_env() + return subprocess.run([get_soffice_cmd()] + args, env=env, **kwargs) + + + +_SHIM_SO = Path(tempfile.gettempdir()) / "lo_socket_shim.so" + + +def _needs_shim() -> bool: + # AF_UNIX / LD_PRELOAD shim is Linux-only; skip on Windows and macOS + if not hasattr(socket, "AF_UNIX"): + return False + try: + s = socket.socket(socket.AF_UNIX, socket.SOCK_STREAM) + s.close() + return False + except OSError: + return True + + +def _ensure_shim() -> Path: + if _SHIM_SO.exists(): + return _SHIM_SO + + src = Path(tempfile.gettempdir()) / "lo_socket_shim.c" + src.write_text(_SHIM_SOURCE) + subprocess.run( + ["gcc", "-shared", "-fPIC", "-o", str(_SHIM_SO), str(src), "-ldl"], + check=True, + capture_output=True, + ) + src.unlink() + return _SHIM_SO + + + +_SHIM_SOURCE = r""" +#define _GNU_SOURCE +#include +#include +#include +#include +#include +#include +#include + +static int (*real_socket)(int, int, int); +static int (*real_socketpair)(int, int, int, int[2]); +static int (*real_listen)(int, int); +static int (*real_accept)(int, struct sockaddr *, socklen_t *); +static int (*real_close)(int); +static int (*real_read)(int, void *, size_t); + +/* Per-FD bookkeeping (FDs >= 1024 are passed through unshimmed). */ +static int is_shimmed[1024]; +static int peer_of[1024]; +static int wake_r[1024]; /* accept() blocks reading this */ +static int wake_w[1024]; /* close() writes to this */ +static int listener_fd = -1; /* FD that received listen() */ + +__attribute__((constructor)) +static void init(void) { + real_socket = dlsym(RTLD_NEXT, "socket"); + real_socketpair = dlsym(RTLD_NEXT, "socketpair"); + real_listen = dlsym(RTLD_NEXT, "listen"); + real_accept = dlsym(RTLD_NEXT, "accept"); + real_close = dlsym(RTLD_NEXT, "close"); + real_read = dlsym(RTLD_NEXT, "read"); + for (int i = 0; i < 1024; i++) { + peer_of[i] = -1; + wake_r[i] = -1; + wake_w[i] = -1; + } +} + +/* ---- socket ---------------------------------------------------------- */ +int socket(int domain, int type, int protocol) { + if (domain == AF_UNIX) { + int fd = real_socket(domain, type, protocol); + if (fd >= 0) return fd; + /* socket(AF_UNIX) blocked – fall back to socketpair(). */ + int sv[2]; + if (real_socketpair(domain, type, protocol, sv) == 0) { + if (sv[0] >= 0 && sv[0] < 1024) { + is_shimmed[sv[0]] = 1; + peer_of[sv[0]] = sv[1]; + int wp[2]; + if (pipe(wp) == 0) { + wake_r[sv[0]] = wp[0]; + wake_w[sv[0]] = wp[1]; + } + } + return sv[0]; + } + errno = EPERM; + return -1; + } + return real_socket(domain, type, protocol); +} + +/* ---- listen ---------------------------------------------------------- */ +int listen(int sockfd, int backlog) { + if (sockfd >= 0 && sockfd < 1024 && is_shimmed[sockfd]) { + listener_fd = sockfd; + return 0; + } + return real_listen(sockfd, backlog); +} + +/* ---- accept ---------------------------------------------------------- */ +int accept(int sockfd, struct sockaddr *addr, socklen_t *addrlen) { + if (sockfd >= 0 && sockfd < 1024 && is_shimmed[sockfd]) { + /* Block until close() writes to the wake pipe. */ + if (wake_r[sockfd] >= 0) { + char buf; + real_read(wake_r[sockfd], &buf, 1); + } + errno = ECONNABORTED; + return -1; + } + return real_accept(sockfd, addr, addrlen); +} + +/* ---- close ----------------------------------------------------------- */ +int close(int fd) { + if (fd >= 0 && fd < 1024 && is_shimmed[fd]) { + int was_listener = (fd == listener_fd); + is_shimmed[fd] = 0; + + if (wake_w[fd] >= 0) { /* unblock accept() */ + char c = 0; + write(wake_w[fd], &c, 1); + real_close(wake_w[fd]); + wake_w[fd] = -1; + } + if (wake_r[fd] >= 0) { real_close(wake_r[fd]); wake_r[fd] = -1; } + if (peer_of[fd] >= 0) { real_close(peer_of[fd]); peer_of[fd] = -1; } + + if (was_listener) + _exit(0); /* conversion done – exit */ + } + return real_close(fd); +} +""" + + + +if __name__ == "__main__": + import sys + result = run_soffice(sys.argv[1:]) + sys.exit(result.returncode) diff --git a/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/unpack.py b/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/unpack.py new file mode 100755 index 00000000..00152533 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/unpack.py @@ -0,0 +1,132 @@ +"""Unpack Office files (DOCX, PPTX, XLSX) for editing. + +Extracts the ZIP archive, pretty-prints XML files, and optionally: +- Merges adjacent runs with identical formatting (DOCX only) +- Simplifies adjacent tracked changes from same author (DOCX only) + +Usage: + python unpack.py [options] + +Examples: + python unpack.py document.docx unpacked/ + python unpack.py presentation.pptx unpacked/ + python unpack.py document.docx unpacked/ --merge-runs false +""" + +import argparse +import sys +import zipfile +from pathlib import Path + +import defusedxml.minidom + +from helpers.merge_runs import merge_runs as do_merge_runs +from helpers.simplify_redlines import simplify_redlines as do_simplify_redlines + +SMART_QUOTE_REPLACEMENTS = { + "\u201c": "“", + "\u201d": "”", + "\u2018": "‘", + "\u2019": "’", +} + + +def unpack( + input_file: str, + output_directory: str, + merge_runs: bool = True, + simplify_redlines: bool = True, +) -> tuple[None, str]: + input_path = Path(input_file) + output_path = Path(output_directory) + suffix = input_path.suffix.lower() + + if not input_path.exists(): + return None, f"Error: {input_file} does not exist" + + if suffix not in {".docx", ".pptx", ".xlsx"}: + return None, f"Error: {input_file} must be a .docx, .pptx, or .xlsx file" + + try: + output_path.mkdir(parents=True, exist_ok=True) + + with zipfile.ZipFile(input_path, "r") as zf: + zf.extractall(output_path) + + xml_files = list(output_path.rglob("*.xml")) + list(output_path.rglob("*.rels")) + for xml_file in xml_files: + _pretty_print_xml(xml_file) + + message = f"Unpacked {input_file} ({len(xml_files)} XML files)" + + if suffix == ".docx": + if simplify_redlines: + simplify_count, _ = do_simplify_redlines(str(output_path)) + message += f", simplified {simplify_count} tracked changes" + + if merge_runs: + merge_count, _ = do_merge_runs(str(output_path)) + message += f", merged {merge_count} runs" + + for xml_file in xml_files: + _escape_smart_quotes(xml_file) + + return None, message + + except zipfile.BadZipFile: + return None, f"Error: {input_file} is not a valid Office file" + except Exception as e: + return None, f"Error unpacking: {e}" + + +def _pretty_print_xml(xml_file: Path) -> None: + try: + content = xml_file.read_text(encoding="utf-8") + dom = defusedxml.minidom.parseString(content) + xml_file.write_bytes(dom.toprettyxml(indent=" ", encoding="utf-8")) + except Exception: + pass + + +def _escape_smart_quotes(xml_file: Path) -> None: + try: + content = xml_file.read_text(encoding="utf-8") + for char, entity in SMART_QUOTE_REPLACEMENTS.items(): + content = content.replace(char, entity) + xml_file.write_text(content, encoding="utf-8") + except Exception: + pass + + +if __name__ == "__main__": + parser = argparse.ArgumentParser( + description="Unpack an Office file (DOCX, PPTX, XLSX) for editing" + ) + parser.add_argument("input_file", help="Office file to unpack") + parser.add_argument("output_directory", help="Output directory") + parser.add_argument( + "--merge-runs", + type=lambda x: x.lower() == "true", + default=True, + metavar="true|false", + help="Merge adjacent runs with identical formatting (DOCX only, default: true)", + ) + parser.add_argument( + "--simplify-redlines", + type=lambda x: x.lower() == "true", + default=True, + metavar="true|false", + help="Merge adjacent tracked changes from same author (DOCX only, default: true)", + ) + args = parser.parse_args() + + _, message = unpack( + args.input_file, + args.output_directory, + merge_runs=args.merge_runs, + simplify_redlines=args.simplify_redlines, + ) + print(message) + + if "Error" in message: + sys.exit(1) diff --git a/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/validate.py b/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/validate.py new file mode 100755 index 00000000..03b01f6e --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/validate.py @@ -0,0 +1,111 @@ +""" +Command line tool to validate Office document XML files against XSD schemas and tracked changes. + +Usage: + python validate.py [--original ] [--auto-repair] [--author NAME] + +The first argument can be either: +- An unpacked directory containing the Office document XML files +- A packed Office file (.docx/.pptx/.xlsx) which will be unpacked to a temp directory + +Auto-repair fixes: +- paraId/durableId values that exceed OOXML limits +- Missing xml:space="preserve" on w:t elements with whitespace +""" + +import argparse +import sys +import tempfile +import zipfile +from pathlib import Path + +from validators import DOCXSchemaValidator, PPTXSchemaValidator, RedliningValidator + + +def main(): + parser = argparse.ArgumentParser(description="Validate Office document XML files") + parser.add_argument( + "path", + help="Path to unpacked directory or packed Office file (.docx/.pptx/.xlsx)", + ) + parser.add_argument( + "--original", + required=False, + default=None, + help="Path to original file (.docx/.pptx/.xlsx). If omitted, all XSD errors are reported and redlining validation is skipped.", + ) + parser.add_argument( + "-v", + "--verbose", + action="store_true", + help="Enable verbose output", + ) + parser.add_argument( + "--auto-repair", + action="store_true", + help="Automatically repair common issues (hex IDs, whitespace preservation)", + ) + parser.add_argument( + "--author", + default="Claude", + help="Author name for redlining validation (default: Claude)", + ) + args = parser.parse_args() + + path = Path(args.path) + assert path.exists(), f"Error: {path} does not exist" + + original_file = None + if args.original: + original_file = Path(args.original) + assert original_file.is_file(), f"Error: {original_file} is not a file" + assert original_file.suffix.lower() in [".docx", ".pptx", ".xlsx"], ( + f"Error: {original_file} must be a .docx, .pptx, or .xlsx file" + ) + + file_extension = (original_file or path).suffix.lower() + assert file_extension in [".docx", ".pptx", ".xlsx"], ( + f"Error: Cannot determine file type from {path}. Use --original or provide a .docx/.pptx/.xlsx file." + ) + + if path.is_file() and path.suffix.lower() in [".docx", ".pptx", ".xlsx"]: + temp_dir = tempfile.mkdtemp() + with zipfile.ZipFile(path, "r") as zf: + zf.extractall(temp_dir) + unpacked_dir = Path(temp_dir) + else: + assert path.is_dir(), f"Error: {path} is not a directory or Office file" + unpacked_dir = path + + match file_extension: + case ".docx": + validators = [ + DOCXSchemaValidator(unpacked_dir, original_file, verbose=args.verbose), + ] + if original_file: + validators.append( + RedliningValidator(unpacked_dir, original_file, verbose=args.verbose, author=args.author) + ) + case ".pptx": + validators = [ + PPTXSchemaValidator(unpacked_dir, original_file, verbose=args.verbose), + ] + case _: + print(f"Error: Validation not supported for file type {file_extension}") + sys.exit(1) + + if args.auto_repair: + total_repairs = sum(v.repair() for v in validators) + if total_repairs: + print(f"Auto-repaired {total_repairs} issue(s)") + + success = all(v.validate() for v in validators) + + if success: + print("All validations PASSED!") + + sys.exit(0 if success else 1) + + +if __name__ == "__main__": + main() diff --git a/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/validators/__init__.py b/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/validators/__init__.py new file mode 100644 index 00000000..db092ece --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/validators/__init__.py @@ -0,0 +1,15 @@ +""" +Validation modules for Word document processing. +""" + +from .base import BaseSchemaValidator +from .docx import DOCXSchemaValidator +from .pptx import PPTXSchemaValidator +from .redlining import RedliningValidator + +__all__ = [ + "BaseSchemaValidator", + "DOCXSchemaValidator", + "PPTXSchemaValidator", + "RedliningValidator", +] diff --git a/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/validators/base.py b/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/validators/base.py new file mode 100644 index 00000000..db4a06a2 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/validators/base.py @@ -0,0 +1,847 @@ +""" +Base validator with common validation logic for document files. +""" + +import re +from pathlib import Path + +import defusedxml.minidom +import lxml.etree + + +class BaseSchemaValidator: + + IGNORED_VALIDATION_ERRORS = [ + "hyphenationZone", + "purl.org/dc/terms", + ] + + UNIQUE_ID_REQUIREMENTS = { + "comment": ("id", "file"), + "commentrangestart": ("id", "file"), + "commentrangeend": ("id", "file"), + "bookmarkstart": ("id", "file"), + "bookmarkend": ("id", "file"), + "sldid": ("id", "file"), + "sldmasterid": ("id", "global"), + "sldlayoutid": ("id", "global"), + "cm": ("authorid", "file"), + "sheet": ("sheetid", "file"), + "definedname": ("id", "file"), + "cxnsp": ("id", "file"), + "sp": ("id", "file"), + "pic": ("id", "file"), + "grpsp": ("id", "file"), + } + + EXCLUDED_ID_CONTAINERS = { + "sectionlst", + } + + ELEMENT_RELATIONSHIP_TYPES = {} + + SCHEMA_MAPPINGS = { + "word": "ISO-IEC29500-4_2016/wml.xsd", + "ppt": "ISO-IEC29500-4_2016/pml.xsd", + "xl": "ISO-IEC29500-4_2016/sml.xsd", + "[Content_Types].xml": "ecma/fouth-edition/opc-contentTypes.xsd", + "app.xml": "ISO-IEC29500-4_2016/shared-documentPropertiesExtended.xsd", + "core.xml": "ecma/fouth-edition/opc-coreProperties.xsd", + "custom.xml": "ISO-IEC29500-4_2016/shared-documentPropertiesCustom.xsd", + ".rels": "ecma/fouth-edition/opc-relationships.xsd", + "people.xml": "microsoft/wml-2012.xsd", + "commentsIds.xml": "microsoft/wml-cid-2016.xsd", + "commentsExtensible.xml": "microsoft/wml-cex-2018.xsd", + "commentsExtended.xml": "microsoft/wml-2012.xsd", + "chart": "ISO-IEC29500-4_2016/dml-chart.xsd", + "theme": "ISO-IEC29500-4_2016/dml-main.xsd", + "drawing": "ISO-IEC29500-4_2016/dml-main.xsd", + } + + MC_NAMESPACE = "http://schemas.openxmlformats.org/markup-compatibility/2006" + XML_NAMESPACE = "http://www.w3.org/XML/1998/namespace" + + PACKAGE_RELATIONSHIPS_NAMESPACE = ( + "http://schemas.openxmlformats.org/package/2006/relationships" + ) + OFFICE_RELATIONSHIPS_NAMESPACE = ( + "http://schemas.openxmlformats.org/officeDocument/2006/relationships" + ) + CONTENT_TYPES_NAMESPACE = ( + "http://schemas.openxmlformats.org/package/2006/content-types" + ) + + MAIN_CONTENT_FOLDERS = {"word", "ppt", "xl"} + + OOXML_NAMESPACES = { + "http://schemas.openxmlformats.org/officeDocument/2006/math", + "http://schemas.openxmlformats.org/officeDocument/2006/relationships", + "http://schemas.openxmlformats.org/schemaLibrary/2006/main", + "http://schemas.openxmlformats.org/drawingml/2006/main", + "http://schemas.openxmlformats.org/drawingml/2006/chart", + "http://schemas.openxmlformats.org/drawingml/2006/chartDrawing", + "http://schemas.openxmlformats.org/drawingml/2006/diagram", + "http://schemas.openxmlformats.org/drawingml/2006/picture", + "http://schemas.openxmlformats.org/drawingml/2006/spreadsheetDrawing", + "http://schemas.openxmlformats.org/drawingml/2006/wordprocessingDrawing", + "http://schemas.openxmlformats.org/wordprocessingml/2006/main", + "http://schemas.openxmlformats.org/presentationml/2006/main", + "http://schemas.openxmlformats.org/spreadsheetml/2006/main", + "http://schemas.openxmlformats.org/officeDocument/2006/sharedTypes", + "http://www.w3.org/XML/1998/namespace", + } + + def __init__(self, unpacked_dir, original_file=None, verbose=False): + self.unpacked_dir = Path(unpacked_dir).resolve() + self.original_file = Path(original_file) if original_file else None + self.verbose = verbose + + self.schemas_dir = Path(__file__).parent.parent / "schemas" + + patterns = ["*.xml", "*.rels"] + self.xml_files = [ + f for pattern in patterns for f in self.unpacked_dir.rglob(pattern) + ] + + if not self.xml_files: + print(f"Warning: No XML files found in {self.unpacked_dir}") + + def validate(self): + raise NotImplementedError("Subclasses must implement the validate method") + + def repair(self) -> int: + return self.repair_whitespace_preservation() + + def repair_whitespace_preservation(self) -> int: + repairs = 0 + + for xml_file in self.xml_files: + try: + content = xml_file.read_text(encoding="utf-8") + dom = defusedxml.minidom.parseString(content) + modified = False + + for elem in dom.getElementsByTagName("*"): + if elem.tagName.endswith(":t") and elem.firstChild: + text = elem.firstChild.nodeValue + if text and (text.startswith((' ', '\t')) or text.endswith((' ', '\t'))): + if elem.getAttribute("xml:space") != "preserve": + elem.setAttribute("xml:space", "preserve") + text_preview = repr(text[:30]) + "..." if len(text) > 30 else repr(text) + print(f" Repaired: {xml_file.name}: Added xml:space='preserve' to {elem.tagName}: {text_preview}") + repairs += 1 + modified = True + + if modified: + xml_file.write_bytes(dom.toxml(encoding="UTF-8")) + + except Exception: + pass + + return repairs + + def validate_xml(self): + errors = [] + + for xml_file in self.xml_files: + try: + lxml.etree.parse(str(xml_file)) + except lxml.etree.XMLSyntaxError as e: + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: " + f"Line {e.lineno}: {e.msg}" + ) + except Exception as e: + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: " + f"Unexpected error: {str(e)}" + ) + + if errors: + print(f"FAILED - Found {len(errors)} XML violations:") + for error in errors: + print(error) + return False + else: + if self.verbose: + print("PASSED - All XML files are well-formed") + return True + + def validate_namespaces(self): + errors = [] + + for xml_file in self.xml_files: + try: + root = lxml.etree.parse(str(xml_file)).getroot() + declared = set(root.nsmap.keys()) - {None} + + for attr_val in [ + v for k, v in root.attrib.items() if k.endswith("Ignorable") + ]: + undeclared = set(attr_val.split()) - declared + errors.extend( + f" {xml_file.relative_to(self.unpacked_dir)}: " + f"Namespace '{ns}' in Ignorable but not declared" + for ns in undeclared + ) + except lxml.etree.XMLSyntaxError: + continue + + if errors: + print(f"FAILED - {len(errors)} namespace issues:") + for error in errors: + print(error) + return False + if self.verbose: + print("PASSED - All namespace prefixes properly declared") + return True + + def validate_unique_ids(self): + errors = [] + global_ids = {} + + for xml_file in self.xml_files: + try: + root = lxml.etree.parse(str(xml_file)).getroot() + file_ids = {} + + mc_elements = root.xpath( + ".//mc:AlternateContent", namespaces={"mc": self.MC_NAMESPACE} + ) + for elem in mc_elements: + elem.getparent().remove(elem) + + for elem in root.iter(): + tag = ( + elem.tag.split("}")[-1].lower() + if "}" in elem.tag + else elem.tag.lower() + ) + + if tag in self.UNIQUE_ID_REQUIREMENTS: + in_excluded_container = any( + ancestor.tag.split("}")[-1].lower() in self.EXCLUDED_ID_CONTAINERS + for ancestor in elem.iterancestors() + ) + if in_excluded_container: + continue + + attr_name, scope = self.UNIQUE_ID_REQUIREMENTS[tag] + + id_value = None + for attr, value in elem.attrib.items(): + attr_local = ( + attr.split("}")[-1].lower() + if "}" in attr + else attr.lower() + ) + if attr_local == attr_name: + id_value = value + break + + if id_value is not None: + if scope == "global": + if id_value in global_ids: + prev_file, prev_line, prev_tag = global_ids[ + id_value + ] + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: " + f"Line {elem.sourceline}: Global ID '{id_value}' in <{tag}> " + f"already used in {prev_file} at line {prev_line} in <{prev_tag}>" + ) + else: + global_ids[id_value] = ( + xml_file.relative_to(self.unpacked_dir), + elem.sourceline, + tag, + ) + elif scope == "file": + key = (tag, attr_name) + if key not in file_ids: + file_ids[key] = {} + + if id_value in file_ids[key]: + prev_line = file_ids[key][id_value] + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: " + f"Line {elem.sourceline}: Duplicate {attr_name}='{id_value}' in <{tag}> " + f"(first occurrence at line {prev_line})" + ) + else: + file_ids[key][id_value] = elem.sourceline + + except (lxml.etree.XMLSyntaxError, Exception) as e: + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: Error: {e}" + ) + + if errors: + print(f"FAILED - Found {len(errors)} ID uniqueness violations:") + for error in errors: + print(error) + return False + else: + if self.verbose: + print("PASSED - All required IDs are unique") + return True + + def validate_file_references(self): + errors = [] + + rels_files = list(self.unpacked_dir.rglob("*.rels")) + + if not rels_files: + if self.verbose: + print("PASSED - No .rels files found") + return True + + all_files = [] + for file_path in self.unpacked_dir.rglob("*"): + if ( + file_path.is_file() + and file_path.name != "[Content_Types].xml" + and not file_path.name.endswith(".rels") + ): + all_files.append(file_path.resolve()) + + all_referenced_files = set() + + if self.verbose: + print( + f"Found {len(rels_files)} .rels files and {len(all_files)} target files" + ) + + for rels_file in rels_files: + try: + rels_root = lxml.etree.parse(str(rels_file)).getroot() + + rels_dir = rels_file.parent + + referenced_files = set() + broken_refs = [] + + for rel in rels_root.findall( + ".//ns:Relationship", + namespaces={"ns": self.PACKAGE_RELATIONSHIPS_NAMESPACE}, + ): + target = rel.get("Target") + if target and not target.startswith( + ("http", "mailto:") + ): + if target.startswith("/"): + target_path = self.unpacked_dir / target.lstrip("/") + elif rels_file.name == ".rels": + target_path = self.unpacked_dir / target + else: + base_dir = rels_dir.parent + target_path = base_dir / target + + try: + target_path = target_path.resolve() + if target_path.exists() and target_path.is_file(): + referenced_files.add(target_path) + all_referenced_files.add(target_path) + else: + broken_refs.append((target, rel.sourceline)) + except (OSError, ValueError): + broken_refs.append((target, rel.sourceline)) + + if broken_refs: + rel_path = rels_file.relative_to(self.unpacked_dir) + for broken_ref, line_num in broken_refs: + errors.append( + f" {rel_path}: Line {line_num}: Broken reference to {broken_ref}" + ) + + except Exception as e: + rel_path = rels_file.relative_to(self.unpacked_dir) + errors.append(f" Error parsing {rel_path}: {e}") + + unreferenced_files = set(all_files) - all_referenced_files + + if unreferenced_files: + for unref_file in sorted(unreferenced_files): + unref_rel_path = unref_file.relative_to(self.unpacked_dir) + errors.append(f" Unreferenced file: {unref_rel_path}") + + if errors: + print(f"FAILED - Found {len(errors)} relationship validation errors:") + for error in errors: + print(error) + print( + "CRITICAL: These errors will cause the document to appear corrupt. " + + "Broken references MUST be fixed, " + + "and unreferenced files MUST be referenced or removed." + ) + return False + else: + if self.verbose: + print( + "PASSED - All references are valid and all files are properly referenced" + ) + return True + + def validate_all_relationship_ids(self): + import lxml.etree + + errors = [] + + for xml_file in self.xml_files: + if xml_file.suffix == ".rels": + continue + + rels_dir = xml_file.parent / "_rels" + rels_file = rels_dir / f"{xml_file.name}.rels" + + if not rels_file.exists(): + continue + + try: + rels_root = lxml.etree.parse(str(rels_file)).getroot() + rid_to_type = {} + + for rel in rels_root.findall( + f".//{{{self.PACKAGE_RELATIONSHIPS_NAMESPACE}}}Relationship" + ): + rid = rel.get("Id") + rel_type = rel.get("Type", "") + if rid: + if rid in rid_to_type: + rels_rel_path = rels_file.relative_to(self.unpacked_dir) + errors.append( + f" {rels_rel_path}: Line {rel.sourceline}: " + f"Duplicate relationship ID '{rid}' (IDs must be unique)" + ) + type_name = ( + rel_type.split("/")[-1] if "/" in rel_type else rel_type + ) + rid_to_type[rid] = type_name + + xml_root = lxml.etree.parse(str(xml_file)).getroot() + + r_ns = self.OFFICE_RELATIONSHIPS_NAMESPACE + rid_attrs_to_check = ["id", "embed", "link"] + for elem in xml_root.iter(): + for attr_name in rid_attrs_to_check: + rid_attr = elem.get(f"{{{r_ns}}}{attr_name}") + if not rid_attr: + continue + xml_rel_path = xml_file.relative_to(self.unpacked_dir) + elem_name = ( + elem.tag.split("}")[-1] if "}" in elem.tag else elem.tag + ) + + if rid_attr not in rid_to_type: + errors.append( + f" {xml_rel_path}: Line {elem.sourceline}: " + f"<{elem_name}> r:{attr_name} references non-existent relationship '{rid_attr}' " + f"(valid IDs: {', '.join(sorted(rid_to_type.keys())[:5])}{'...' if len(rid_to_type) > 5 else ''})" + ) + elif attr_name == "id" and self.ELEMENT_RELATIONSHIP_TYPES: + expected_type = self._get_expected_relationship_type( + elem_name + ) + if expected_type: + actual_type = rid_to_type[rid_attr] + if expected_type not in actual_type.lower(): + errors.append( + f" {xml_rel_path}: Line {elem.sourceline}: " + f"<{elem_name}> references '{rid_attr}' which points to '{actual_type}' " + f"but should point to a '{expected_type}' relationship" + ) + + except Exception as e: + xml_rel_path = xml_file.relative_to(self.unpacked_dir) + errors.append(f" Error processing {xml_rel_path}: {e}") + + if errors: + print(f"FAILED - Found {len(errors)} relationship ID reference errors:") + for error in errors: + print(error) + print("\nThese ID mismatches will cause the document to appear corrupt!") + return False + else: + if self.verbose: + print("PASSED - All relationship ID references are valid") + return True + + def _get_expected_relationship_type(self, element_name): + elem_lower = element_name.lower() + + if elem_lower in self.ELEMENT_RELATIONSHIP_TYPES: + return self.ELEMENT_RELATIONSHIP_TYPES[elem_lower] + + if elem_lower.endswith("id") and len(elem_lower) > 2: + prefix = elem_lower[:-2] + if prefix.endswith("master"): + return prefix.lower() + elif prefix.endswith("layout"): + return prefix.lower() + else: + if prefix == "sld": + return "slide" + return prefix.lower() + + if elem_lower.endswith("reference") and len(elem_lower) > 9: + prefix = elem_lower[:-9] + return prefix.lower() + + return None + + def validate_content_types(self): + errors = [] + + content_types_file = self.unpacked_dir / "[Content_Types].xml" + if not content_types_file.exists(): + print("FAILED - [Content_Types].xml file not found") + return False + + try: + root = lxml.etree.parse(str(content_types_file)).getroot() + declared_parts = set() + declared_extensions = set() + + for override in root.findall( + f".//{{{self.CONTENT_TYPES_NAMESPACE}}}Override" + ): + part_name = override.get("PartName") + if part_name is not None: + declared_parts.add(part_name.lstrip("/")) + + for default in root.findall( + f".//{{{self.CONTENT_TYPES_NAMESPACE}}}Default" + ): + extension = default.get("Extension") + if extension is not None: + declared_extensions.add(extension.lower()) + + declarable_roots = { + "sld", + "sldLayout", + "sldMaster", + "presentation", + "document", + "workbook", + "worksheet", + "theme", + } + + media_extensions = { + "png": "image/png", + "jpg": "image/jpeg", + "jpeg": "image/jpeg", + "gif": "image/gif", + "bmp": "image/bmp", + "tiff": "image/tiff", + "wmf": "image/x-wmf", + "emf": "image/x-emf", + } + + all_files = list(self.unpacked_dir.rglob("*")) + all_files = [f for f in all_files if f.is_file()] + + for xml_file in self.xml_files: + path_str = str(xml_file.relative_to(self.unpacked_dir)).replace( + "\\", "/" + ) + + if any( + skip in path_str + for skip in [".rels", "[Content_Types]", "docProps/", "_rels/"] + ): + continue + + try: + root_tag = lxml.etree.parse(str(xml_file)).getroot().tag + root_name = root_tag.split("}")[-1] if "}" in root_tag else root_tag + + if root_name in declarable_roots and path_str not in declared_parts: + errors.append( + f" {path_str}: File with <{root_name}> root not declared in [Content_Types].xml" + ) + + except Exception: + continue + + for file_path in all_files: + if file_path.suffix.lower() in {".xml", ".rels"}: + continue + if file_path.name == "[Content_Types].xml": + continue + if "_rels" in file_path.parts or "docProps" in file_path.parts: + continue + + extension = file_path.suffix.lstrip(".").lower() + if extension and extension not in declared_extensions: + if extension in media_extensions: + relative_path = file_path.relative_to(self.unpacked_dir) + errors.append( + f' {relative_path}: File with extension \'{extension}\' not declared in [Content_Types].xml - should add: ' + ) + + except Exception as e: + errors.append(f" Error parsing [Content_Types].xml: {e}") + + if errors: + print(f"FAILED - Found {len(errors)} content type declaration errors:") + for error in errors: + print(error) + return False + else: + if self.verbose: + print( + "PASSED - All content files are properly declared in [Content_Types].xml" + ) + return True + + def validate_file_against_xsd(self, xml_file, verbose=False): + xml_file = Path(xml_file).resolve() + unpacked_dir = self.unpacked_dir.resolve() + + is_valid, current_errors = self._validate_single_file_xsd( + xml_file, unpacked_dir + ) + + if is_valid is None: + return None, set() + elif is_valid: + return True, set() + + original_errors = self._get_original_file_errors(xml_file) + + assert current_errors is not None + new_errors = current_errors - original_errors + + new_errors = { + e for e in new_errors + if not any(pattern in e for pattern in self.IGNORED_VALIDATION_ERRORS) + } + + if new_errors: + if verbose: + relative_path = xml_file.relative_to(unpacked_dir) + print(f"FAILED - {relative_path}: {len(new_errors)} new error(s)") + for error in list(new_errors)[:3]: + truncated = error[:250] + "..." if len(error) > 250 else error + print(f" - {truncated}") + return False, new_errors + else: + if verbose: + print( + f"PASSED - No new errors (original had {len(current_errors)} errors)" + ) + return True, set() + + def validate_against_xsd(self): + new_errors = [] + original_error_count = 0 + valid_count = 0 + skipped_count = 0 + + for xml_file in self.xml_files: + relative_path = str(xml_file.relative_to(self.unpacked_dir)) + is_valid, new_file_errors = self.validate_file_against_xsd( + xml_file, verbose=False + ) + + if is_valid is None: + skipped_count += 1 + continue + elif is_valid and not new_file_errors: + valid_count += 1 + continue + elif is_valid: + original_error_count += 1 + valid_count += 1 + continue + + new_errors.append(f" {relative_path}: {len(new_file_errors)} new error(s)") + for error in list(new_file_errors)[:3]: + new_errors.append( + f" - {error[:250]}..." if len(error) > 250 else f" - {error}" + ) + + if self.verbose: + print(f"Validated {len(self.xml_files)} files:") + print(f" - Valid: {valid_count}") + print(f" - Skipped (no schema): {skipped_count}") + if original_error_count: + print(f" - With original errors (ignored): {original_error_count}") + print( + f" - With NEW errors: {len(new_errors) > 0 and len([e for e in new_errors if not e.startswith(' ')]) or 0}" + ) + + if new_errors: + print("\nFAILED - Found NEW validation errors:") + for error in new_errors: + print(error) + return False + else: + if self.verbose: + print("\nPASSED - No new XSD validation errors introduced") + return True + + def _get_schema_path(self, xml_file): + if xml_file.name in self.SCHEMA_MAPPINGS: + return self.schemas_dir / self.SCHEMA_MAPPINGS[xml_file.name] + + if xml_file.suffix == ".rels": + return self.schemas_dir / self.SCHEMA_MAPPINGS[".rels"] + + if "charts/" in str(xml_file) and xml_file.name.startswith("chart"): + return self.schemas_dir / self.SCHEMA_MAPPINGS["chart"] + + if "theme/" in str(xml_file) and xml_file.name.startswith("theme"): + return self.schemas_dir / self.SCHEMA_MAPPINGS["theme"] + + if xml_file.parent.name in self.MAIN_CONTENT_FOLDERS: + return self.schemas_dir / self.SCHEMA_MAPPINGS[xml_file.parent.name] + + return None + + def _clean_ignorable_namespaces(self, xml_doc): + xml_string = lxml.etree.tostring(xml_doc, encoding="unicode") + xml_copy = lxml.etree.fromstring(xml_string) + + for elem in xml_copy.iter(): + attrs_to_remove = [] + + for attr in elem.attrib: + if "{" in attr: + ns = attr.split("}")[0][1:] + if ns not in self.OOXML_NAMESPACES: + attrs_to_remove.append(attr) + + for attr in attrs_to_remove: + del elem.attrib[attr] + + self._remove_ignorable_elements(xml_copy) + + return lxml.etree.ElementTree(xml_copy) + + def _remove_ignorable_elements(self, root): + elements_to_remove = [] + + for elem in list(root): + if not hasattr(elem, "tag") or callable(elem.tag): + continue + + tag_str = str(elem.tag) + if tag_str.startswith("{"): + ns = tag_str.split("}")[0][1:] + if ns not in self.OOXML_NAMESPACES: + elements_to_remove.append(elem) + continue + + self._remove_ignorable_elements(elem) + + for elem in elements_to_remove: + root.remove(elem) + + def _preprocess_for_mc_ignorable(self, xml_doc): + root = xml_doc.getroot() + + if f"{{{self.MC_NAMESPACE}}}Ignorable" in root.attrib: + del root.attrib[f"{{{self.MC_NAMESPACE}}}Ignorable"] + + return xml_doc + + def _validate_single_file_xsd(self, xml_file, base_path): + schema_path = self._get_schema_path(xml_file) + if not schema_path: + return None, None + + try: + with open(schema_path, "rb") as xsd_file: + parser = lxml.etree.XMLParser() + xsd_doc = lxml.etree.parse( + xsd_file, parser=parser, base_url=str(schema_path) + ) + schema = lxml.etree.XMLSchema(xsd_doc) + + with open(xml_file, "r") as f: + xml_doc = lxml.etree.parse(f) + + xml_doc, _ = self._remove_template_tags_from_text_nodes(xml_doc) + xml_doc = self._preprocess_for_mc_ignorable(xml_doc) + + relative_path = xml_file.relative_to(base_path) + if ( + relative_path.parts + and relative_path.parts[0] in self.MAIN_CONTENT_FOLDERS + ): + xml_doc = self._clean_ignorable_namespaces(xml_doc) + + if schema.validate(xml_doc): + return True, set() + else: + errors = set() + for error in schema.error_log: + errors.add(error.message) + return False, errors + + except Exception as e: + return False, {str(e)} + + def _get_original_file_errors(self, xml_file): + if self.original_file is None: + return set() + + import tempfile + import zipfile + + xml_file = Path(xml_file).resolve() + unpacked_dir = self.unpacked_dir.resolve() + relative_path = xml_file.relative_to(unpacked_dir) + + with tempfile.TemporaryDirectory() as temp_dir: + temp_path = Path(temp_dir) + + with zipfile.ZipFile(self.original_file, "r") as zip_ref: + zip_ref.extractall(temp_path) + + original_xml_file = temp_path / relative_path + + if not original_xml_file.exists(): + return set() + + is_valid, errors = self._validate_single_file_xsd( + original_xml_file, temp_path + ) + return errors if errors else set() + + def _remove_template_tags_from_text_nodes(self, xml_doc): + warnings = [] + template_pattern = re.compile(r"\{\{[^}]*\}\}") + + xml_string = lxml.etree.tostring(xml_doc, encoding="unicode") + xml_copy = lxml.etree.fromstring(xml_string) + + def process_text_content(text, content_type): + if not text: + return text + matches = list(template_pattern.finditer(text)) + if matches: + for match in matches: + warnings.append( + f"Found template tag in {content_type}: {match.group()}" + ) + return template_pattern.sub("", text) + return text + + for elem in xml_copy.iter(): + if not hasattr(elem, "tag") or callable(elem.tag): + continue + tag_str = str(elem.tag) + if tag_str.endswith("}t") or tag_str == "t": + continue + + elem.text = process_text_content(elem.text, "text content") + elem.tail = process_text_content(elem.tail, "tail content") + + return lxml.etree.ElementTree(xml_copy), warnings + + +if __name__ == "__main__": + raise RuntimeError("This module should not be run directly.") diff --git a/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/validators/docx.py b/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/validators/docx.py new file mode 100644 index 00000000..0a0b0bfd --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/validators/docx.py @@ -0,0 +1,447 @@ +""" +Validator for Word document XML files against XSD schemas. +""" + +import os +import random +import re +import tempfile +import zipfile + +import defusedxml.minidom +import lxml.etree + +from .base import BaseSchemaValidator + + +class DOCXSchemaValidator(BaseSchemaValidator): + + WORD_2006_NAMESPACE = "http://schemas.openxmlformats.org/wordprocessingml/2006/main" + W14_NAMESPACE = "http://schemas.microsoft.com/office/word/2010/wordml" + W16CID_NAMESPACE = "http://schemas.microsoft.com/office/word/2016/wordml/cid" + + ELEMENT_RELATIONSHIP_TYPES = {} + + def validate(self): + if not self.validate_xml(): + return False + + all_valid = True + if not self.validate_namespaces(): + all_valid = False + + if not self.validate_unique_ids(): + all_valid = False + + if not self.validate_file_references(): + all_valid = False + + if not self.validate_content_types(): + all_valid = False + + if not self.validate_against_xsd(): + all_valid = False + + if not self.validate_whitespace_preservation(): + all_valid = False + + if not self.validate_deletions(): + all_valid = False + + if not self.validate_insertions(): + all_valid = False + + if not self.validate_all_relationship_ids(): + all_valid = False + + if not self.validate_id_constraints(): + all_valid = False + + if not self.validate_comment_markers(): + all_valid = False + + self.compare_paragraph_counts() + + return all_valid + + def validate_whitespace_preservation(self): + errors = [] + + for xml_file in self.xml_files: + if xml_file.name != "document.xml": + continue + + try: + root = lxml.etree.parse(str(xml_file)).getroot() + + for elem in root.iter(f"{{{self.WORD_2006_NAMESPACE}}}t"): + if elem.text: + text = elem.text + if re.search(r"^[ \t\n\r]", text) or re.search( + r"[ \t\n\r]$", text + ): + xml_space_attr = f"{{{self.XML_NAMESPACE}}}space" + if ( + xml_space_attr not in elem.attrib + or elem.attrib[xml_space_attr] != "preserve" + ): + text_preview = ( + repr(text)[:50] + "..." + if len(repr(text)) > 50 + else repr(text) + ) + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: " + f"Line {elem.sourceline}: w:t element with whitespace missing xml:space='preserve': {text_preview}" + ) + + except (lxml.etree.XMLSyntaxError, Exception) as e: + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: Error: {e}" + ) + + if errors: + print(f"FAILED - Found {len(errors)} whitespace preservation violations:") + for error in errors: + print(error) + return False + else: + if self.verbose: + print("PASSED - All whitespace is properly preserved") + return True + + def validate_deletions(self): + errors = [] + + for xml_file in self.xml_files: + if xml_file.name != "document.xml": + continue + + try: + root = lxml.etree.parse(str(xml_file)).getroot() + namespaces = {"w": self.WORD_2006_NAMESPACE} + + for t_elem in root.xpath(".//w:del//w:t", namespaces=namespaces): + if t_elem.text: + text_preview = ( + repr(t_elem.text)[:50] + "..." + if len(repr(t_elem.text)) > 50 + else repr(t_elem.text) + ) + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: " + f"Line {t_elem.sourceline}: found within : {text_preview}" + ) + + for instr_elem in root.xpath( + ".//w:del//w:instrText", namespaces=namespaces + ): + text_preview = ( + repr(instr_elem.text or "")[:50] + "..." + if len(repr(instr_elem.text or "")) > 50 + else repr(instr_elem.text or "") + ) + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: " + f"Line {instr_elem.sourceline}: found within (use ): {text_preview}" + ) + + except (lxml.etree.XMLSyntaxError, Exception) as e: + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: Error: {e}" + ) + + if errors: + print(f"FAILED - Found {len(errors)} deletion validation violations:") + for error in errors: + print(error) + return False + else: + if self.verbose: + print("PASSED - No w:t elements found within w:del elements") + return True + + def count_paragraphs_in_unpacked(self): + count = 0 + + for xml_file in self.xml_files: + if xml_file.name != "document.xml": + continue + + try: + root = lxml.etree.parse(str(xml_file)).getroot() + paragraphs = root.findall(f".//{{{self.WORD_2006_NAMESPACE}}}p") + count = len(paragraphs) + except Exception as e: + print(f"Error counting paragraphs in unpacked document: {e}") + + return count + + def count_paragraphs_in_original(self): + original = self.original_file + if original is None: + return 0 + + count = 0 + + try: + with tempfile.TemporaryDirectory() as temp_dir: + with zipfile.ZipFile(original, "r") as zip_ref: + zip_ref.extractall(temp_dir) + + doc_xml_path = os.path.join(temp_dir, "word", "document.xml") + root = lxml.etree.parse(doc_xml_path).getroot() + + paragraphs = root.findall(f".//{{{self.WORD_2006_NAMESPACE}}}p") + count = len(paragraphs) + + except Exception as e: + print(f"Error counting paragraphs in original document: {e}") + + return count + + def validate_insertions(self): + errors = [] + + for xml_file in self.xml_files: + if xml_file.name != "document.xml": + continue + + try: + root = lxml.etree.parse(str(xml_file)).getroot() + namespaces = {"w": self.WORD_2006_NAMESPACE} + + invalid_elements = root.xpath( + ".//w:ins//w:delText[not(ancestor::w:del)]", namespaces=namespaces + ) + + for elem in invalid_elements: + text_preview = ( + repr(elem.text or "")[:50] + "..." + if len(repr(elem.text or "")) > 50 + else repr(elem.text or "") + ) + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: " + f"Line {elem.sourceline}: within : {text_preview}" + ) + + except (lxml.etree.XMLSyntaxError, Exception) as e: + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: Error: {e}" + ) + + if errors: + print(f"FAILED - Found {len(errors)} insertion validation violations:") + for error in errors: + print(error) + return False + else: + if self.verbose: + print("PASSED - No w:delText elements within w:ins elements") + return True + + def compare_paragraph_counts(self): + original_count = self.count_paragraphs_in_original() + new_count = self.count_paragraphs_in_unpacked() + + diff = new_count - original_count + diff_str = f"+{diff}" if diff > 0 else str(diff) + print(f"\nParagraphs: {original_count} → {new_count} ({diff_str})") + + def _parse_id_value(self, val: str, base: int = 16) -> int: + return int(val, base) + + def validate_id_constraints(self): + errors = [] + para_id_attr = f"{{{self.W14_NAMESPACE}}}paraId" + durable_id_attr = f"{{{self.W16CID_NAMESPACE}}}durableId" + + for xml_file in self.xml_files: + try: + for elem in lxml.etree.parse(str(xml_file)).iter(): + if val := elem.get(para_id_attr): + if self._parse_id_value(val, base=16) >= 0x80000000: + errors.append( + f" {xml_file.name}:{elem.sourceline}: paraId={val} >= 0x80000000" + ) + + if val := elem.get(durable_id_attr): + if xml_file.name == "numbering.xml": + try: + if self._parse_id_value(val, base=10) >= 0x7FFFFFFF: + errors.append( + f" {xml_file.name}:{elem.sourceline}: " + f"durableId={val} >= 0x7FFFFFFF" + ) + except ValueError: + errors.append( + f" {xml_file.name}:{elem.sourceline}: " + f"durableId={val} must be decimal in numbering.xml" + ) + else: + if self._parse_id_value(val, base=16) >= 0x7FFFFFFF: + errors.append( + f" {xml_file.name}:{elem.sourceline}: " + f"durableId={val} >= 0x7FFFFFFF" + ) + except Exception: + pass + + if errors: + print(f"FAILED - {len(errors)} ID constraint violations:") + for e in errors: + print(e) + elif self.verbose: + print("PASSED - All paraId/durableId values within constraints") + return not errors + + def validate_comment_markers(self): + errors = [] + + document_xml = None + comments_xml = None + for xml_file in self.xml_files: + if xml_file.name == "document.xml" and "word" in str(xml_file): + document_xml = xml_file + elif xml_file.name == "comments.xml": + comments_xml = xml_file + + if not document_xml: + if self.verbose: + print("PASSED - No document.xml found (skipping comment validation)") + return True + + try: + doc_root = lxml.etree.parse(str(document_xml)).getroot() + namespaces = {"w": self.WORD_2006_NAMESPACE} + + range_starts = { + elem.get(f"{{{self.WORD_2006_NAMESPACE}}}id") + for elem in doc_root.xpath( + ".//w:commentRangeStart", namespaces=namespaces + ) + } + range_ends = { + elem.get(f"{{{self.WORD_2006_NAMESPACE}}}id") + for elem in doc_root.xpath( + ".//w:commentRangeEnd", namespaces=namespaces + ) + } + references = { + elem.get(f"{{{self.WORD_2006_NAMESPACE}}}id") + for elem in doc_root.xpath( + ".//w:commentReference", namespaces=namespaces + ) + } + + orphaned_ends = range_ends - range_starts + for comment_id in sorted( + orphaned_ends, key=lambda x: int(x) if x and x.isdigit() else 0 + ): + errors.append( + f' document.xml: commentRangeEnd id="{comment_id}" has no matching commentRangeStart' + ) + + orphaned_starts = range_starts - range_ends + for comment_id in sorted( + orphaned_starts, key=lambda x: int(x) if x and x.isdigit() else 0 + ): + errors.append( + f' document.xml: commentRangeStart id="{comment_id}" has no matching commentRangeEnd' + ) + + comment_ids = set() + if comments_xml and comments_xml.exists(): + comments_root = lxml.etree.parse(str(comments_xml)).getroot() + comment_ids = { + elem.get(f"{{{self.WORD_2006_NAMESPACE}}}id") + for elem in comments_root.xpath( + ".//w:comment", namespaces=namespaces + ) + } + + marker_ids = range_starts | range_ends | references + invalid_refs = marker_ids - comment_ids + for comment_id in sorted( + invalid_refs, key=lambda x: int(x) if x and x.isdigit() else 0 + ): + if comment_id: + errors.append( + f' document.xml: marker id="{comment_id}" references non-existent comment' + ) + + except (lxml.etree.XMLSyntaxError, Exception) as e: + errors.append(f" Error parsing XML: {e}") + + if errors: + print(f"FAILED - {len(errors)} comment marker violations:") + for error in errors: + print(error) + return False + else: + if self.verbose: + print("PASSED - All comment markers properly paired") + return True + + def repair(self) -> int: + repairs = super().repair() + repairs += self.repair_durableId() + return repairs + + def repair_durableId(self) -> int: + repairs = 0 + + for xml_file in self.xml_files: + try: + content = xml_file.read_text(encoding="utf-8") + dom = defusedxml.minidom.parseString(content) + modified = False + + for elem in dom.getElementsByTagName("*"): + if not elem.hasAttribute("w16cid:durableId"): + continue + + durable_id = elem.getAttribute("w16cid:durableId") + needs_repair = False + + if xml_file.name == "numbering.xml": + try: + needs_repair = ( + self._parse_id_value(durable_id, base=10) >= 0x7FFFFFFF + ) + except ValueError: + needs_repair = True + else: + try: + needs_repair = ( + self._parse_id_value(durable_id, base=16) >= 0x7FFFFFFF + ) + except ValueError: + needs_repair = True + + if needs_repair: + value = random.randint(1, 0x7FFFFFFE) + if xml_file.name == "numbering.xml": + new_id = str(value) + else: + new_id = f"{value:08X}" + + elem.setAttribute("w16cid:durableId", new_id) + print( + f" Repaired: {xml_file.name}: durableId {durable_id} → {new_id}" + ) + repairs += 1 + modified = True + + if modified: + xml_file.write_bytes(dom.toxml(encoding="UTF-8")) + + except Exception: + pass + + return repairs + + +if __name__ == "__main__": + raise RuntimeError("This module should not be run directly.") diff --git a/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/validators/pptx.py b/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/validators/pptx.py new file mode 100644 index 00000000..09842aa9 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/validators/pptx.py @@ -0,0 +1,275 @@ +""" +Validator for PowerPoint presentation XML files against XSD schemas. +""" + +import re + +from .base import BaseSchemaValidator + + +class PPTXSchemaValidator(BaseSchemaValidator): + + PRESENTATIONML_NAMESPACE = ( + "http://schemas.openxmlformats.org/presentationml/2006/main" + ) + + ELEMENT_RELATIONSHIP_TYPES = { + "sldid": "slide", + "sldmasterid": "slidemaster", + "notesmasterid": "notesmaster", + "sldlayoutid": "slidelayout", + "themeid": "theme", + "tablestyleid": "tablestyles", + } + + def validate(self): + if not self.validate_xml(): + return False + + all_valid = True + if not self.validate_namespaces(): + all_valid = False + + if not self.validate_unique_ids(): + all_valid = False + + if not self.validate_uuid_ids(): + all_valid = False + + if not self.validate_file_references(): + all_valid = False + + if not self.validate_slide_layout_ids(): + all_valid = False + + if not self.validate_content_types(): + all_valid = False + + if not self.validate_against_xsd(): + all_valid = False + + if not self.validate_notes_slide_references(): + all_valid = False + + if not self.validate_all_relationship_ids(): + all_valid = False + + if not self.validate_no_duplicate_slide_layouts(): + all_valid = False + + return all_valid + + def validate_uuid_ids(self): + import lxml.etree + + errors = [] + uuid_pattern = re.compile( + r"^[\{\(]?[0-9A-Fa-f]{8}-?[0-9A-Fa-f]{4}-?[0-9A-Fa-f]{4}-?[0-9A-Fa-f]{4}-?[0-9A-Fa-f]{12}[\}\)]?$" + ) + + for xml_file in self.xml_files: + try: + root = lxml.etree.parse(str(xml_file)).getroot() + + for elem in root.iter(): + for attr, value in elem.attrib.items(): + attr_name = attr.split("}")[-1].lower() + if attr_name == "id" or attr_name.endswith("id"): + if self._looks_like_uuid(value): + if not uuid_pattern.match(value): + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: " + f"Line {elem.sourceline}: ID '{value}' appears to be a UUID but contains invalid hex characters" + ) + + except (lxml.etree.XMLSyntaxError, Exception) as e: + errors.append( + f" {xml_file.relative_to(self.unpacked_dir)}: Error: {e}" + ) + + if errors: + print(f"FAILED - Found {len(errors)} UUID ID validation errors:") + for error in errors: + print(error) + return False + else: + if self.verbose: + print("PASSED - All UUID-like IDs contain valid hex values") + return True + + def _looks_like_uuid(self, value): + clean_value = value.strip("{}()").replace("-", "") + return len(clean_value) == 32 and all(c.isalnum() for c in clean_value) + + def validate_slide_layout_ids(self): + import lxml.etree + + errors = [] + + slide_masters = list(self.unpacked_dir.glob("ppt/slideMasters/*.xml")) + + if not slide_masters: + if self.verbose: + print("PASSED - No slide masters found") + return True + + for slide_master in slide_masters: + try: + root = lxml.etree.parse(str(slide_master)).getroot() + + rels_file = slide_master.parent / "_rels" / f"{slide_master.name}.rels" + + if not rels_file.exists(): + errors.append( + f" {slide_master.relative_to(self.unpacked_dir)}: " + f"Missing relationships file: {rels_file.relative_to(self.unpacked_dir)}" + ) + continue + + rels_root = lxml.etree.parse(str(rels_file)).getroot() + + valid_layout_rids = set() + for rel in rels_root.findall( + f".//{{{self.PACKAGE_RELATIONSHIPS_NAMESPACE}}}Relationship" + ): + rel_type = rel.get("Type", "") + if "slideLayout" in rel_type: + valid_layout_rids.add(rel.get("Id")) + + for sld_layout_id in root.findall( + f".//{{{self.PRESENTATIONML_NAMESPACE}}}sldLayoutId" + ): + r_id = sld_layout_id.get( + f"{{{self.OFFICE_RELATIONSHIPS_NAMESPACE}}}id" + ) + layout_id = sld_layout_id.get("id") + + if r_id and r_id not in valid_layout_rids: + errors.append( + f" {slide_master.relative_to(self.unpacked_dir)}: " + f"Line {sld_layout_id.sourceline}: sldLayoutId with id='{layout_id}' " + f"references r:id='{r_id}' which is not found in slide layout relationships" + ) + + except (lxml.etree.XMLSyntaxError, Exception) as e: + errors.append( + f" {slide_master.relative_to(self.unpacked_dir)}: Error: {e}" + ) + + if errors: + print(f"FAILED - Found {len(errors)} slide layout ID validation errors:") + for error in errors: + print(error) + print( + "Remove invalid references or add missing slide layouts to the relationships file." + ) + return False + else: + if self.verbose: + print("PASSED - All slide layout IDs reference valid slide layouts") + return True + + def validate_no_duplicate_slide_layouts(self): + import lxml.etree + + errors = [] + slide_rels_files = list(self.unpacked_dir.glob("ppt/slides/_rels/*.xml.rels")) + + for rels_file in slide_rels_files: + try: + root = lxml.etree.parse(str(rels_file)).getroot() + + layout_rels = [ + rel + for rel in root.findall( + f".//{{{self.PACKAGE_RELATIONSHIPS_NAMESPACE}}}Relationship" + ) + if "slideLayout" in rel.get("Type", "") + ] + + if len(layout_rels) > 1: + errors.append( + f" {rels_file.relative_to(self.unpacked_dir)}: has {len(layout_rels)} slideLayout references" + ) + + except Exception as e: + errors.append( + f" {rels_file.relative_to(self.unpacked_dir)}: Error: {e}" + ) + + if errors: + print("FAILED - Found slides with duplicate slideLayout references:") + for error in errors: + print(error) + return False + else: + if self.verbose: + print("PASSED - All slides have exactly one slideLayout reference") + return True + + def validate_notes_slide_references(self): + import lxml.etree + + errors = [] + notes_slide_references = {} + + slide_rels_files = list(self.unpacked_dir.glob("ppt/slides/_rels/*.xml.rels")) + + if not slide_rels_files: + if self.verbose: + print("PASSED - No slide relationship files found") + return True + + for rels_file in slide_rels_files: + try: + root = lxml.etree.parse(str(rels_file)).getroot() + + for rel in root.findall( + f".//{{{self.PACKAGE_RELATIONSHIPS_NAMESPACE}}}Relationship" + ): + rel_type = rel.get("Type", "") + if "notesSlide" in rel_type: + target = rel.get("Target", "") + if target: + normalized_target = target.replace("../", "") + + slide_name = rels_file.stem.replace( + ".xml", "" + ) + + if normalized_target not in notes_slide_references: + notes_slide_references[normalized_target] = [] + notes_slide_references[normalized_target].append( + (slide_name, rels_file) + ) + + except (lxml.etree.XMLSyntaxError, Exception) as e: + errors.append( + f" {rels_file.relative_to(self.unpacked_dir)}: Error: {e}" + ) + + for target, references in notes_slide_references.items(): + if len(references) > 1: + slide_names = [ref[0] for ref in references] + errors.append( + f" Notes slide '{target}' is referenced by multiple slides: {', '.join(slide_names)}" + ) + for slide_name, rels_file in references: + errors.append(f" - {rels_file.relative_to(self.unpacked_dir)}") + + if errors: + print( + f"FAILED - Found {len([e for e in errors if not e.startswith(' ')])} notes slide reference validation errors:" + ) + for error in errors: + print(error) + print("Each slide may optionally have its own slide file.") + return False + else: + if self.verbose: + print("PASSED - All notes slide references are unique") + return True + + +if __name__ == "__main__": + raise RuntimeError("This module should not be run directly.") diff --git a/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/validators/redlining.py b/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/validators/redlining.py new file mode 100644 index 00000000..71c81b6b --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/xlsx/scripts/office/validators/redlining.py @@ -0,0 +1,247 @@ +""" +Validator for tracked changes in Word documents. +""" + +import subprocess +import tempfile +import zipfile +from pathlib import Path + + +class RedliningValidator: + + def __init__(self, unpacked_dir, original_docx, verbose=False, author="Claude"): + self.unpacked_dir = Path(unpacked_dir) + self.original_docx = Path(original_docx) + self.verbose = verbose + self.author = author + self.namespaces = { + "w": "http://schemas.openxmlformats.org/wordprocessingml/2006/main" + } + + def repair(self) -> int: + return 0 + + def validate(self): + modified_file = self.unpacked_dir / "word" / "document.xml" + if not modified_file.exists(): + print(f"FAILED - Modified document.xml not found at {modified_file}") + return False + + try: + import xml.etree.ElementTree as ET + + tree = ET.parse(modified_file) + root = tree.getroot() + + del_elements = root.findall(".//w:del", self.namespaces) + ins_elements = root.findall(".//w:ins", self.namespaces) + + author_del_elements = [ + elem + for elem in del_elements + if elem.get(f"{{{self.namespaces['w']}}}author") == self.author + ] + author_ins_elements = [ + elem + for elem in ins_elements + if elem.get(f"{{{self.namespaces['w']}}}author") == self.author + ] + + if not author_del_elements and not author_ins_elements: + if self.verbose: + print(f"PASSED - No tracked changes by {self.author} found.") + return True + + except Exception: + pass + + with tempfile.TemporaryDirectory() as temp_dir: + temp_path = Path(temp_dir) + + try: + with zipfile.ZipFile(self.original_docx, "r") as zip_ref: + zip_ref.extractall(temp_path) + except Exception as e: + print(f"FAILED - Error unpacking original docx: {e}") + return False + + original_file = temp_path / "word" / "document.xml" + if not original_file.exists(): + print( + f"FAILED - Original document.xml not found in {self.original_docx}" + ) + return False + + try: + import xml.etree.ElementTree as ET + + modified_tree = ET.parse(modified_file) + modified_root = modified_tree.getroot() + original_tree = ET.parse(original_file) + original_root = original_tree.getroot() + except ET.ParseError as e: + print(f"FAILED - Error parsing XML files: {e}") + return False + + self._remove_author_tracked_changes(original_root) + self._remove_author_tracked_changes(modified_root) + + modified_text = self._extract_text_content(modified_root) + original_text = self._extract_text_content(original_root) + + if modified_text != original_text: + error_message = self._generate_detailed_diff( + original_text, modified_text + ) + print(error_message) + return False + + if self.verbose: + print(f"PASSED - All changes by {self.author} are properly tracked") + return True + + def _generate_detailed_diff(self, original_text, modified_text): + error_parts = [ + f"FAILED - Document text doesn't match after removing {self.author}'s tracked changes", + "", + "Likely causes:", + " 1. Modified text inside another author's or tags", + " 2. Made edits without proper tracked changes", + " 3. Didn't nest inside when deleting another's insertion", + "", + "For pre-redlined documents, use correct patterns:", + " - To reject another's INSERTION: Nest inside their ", + " - To restore another's DELETION: Add new AFTER their ", + "", + ] + + git_diff = self._get_git_word_diff(original_text, modified_text) + if git_diff: + error_parts.extend(["Differences:", "============", git_diff]) + else: + error_parts.append("Unable to generate word diff (git not available)") + + return "\n".join(error_parts) + + def _get_git_word_diff(self, original_text, modified_text): + try: + with tempfile.TemporaryDirectory() as temp_dir: + temp_path = Path(temp_dir) + + original_file = temp_path / "original.txt" + modified_file = temp_path / "modified.txt" + + original_file.write_text(original_text, encoding="utf-8") + modified_file.write_text(modified_text, encoding="utf-8") + + result = subprocess.run( + [ + "git", + "diff", + "--word-diff=plain", + "--word-diff-regex=.", + "-U0", + "--no-index", + str(original_file), + str(modified_file), + ], + capture_output=True, + text=True, + ) + + if result.stdout.strip(): + lines = result.stdout.split("\n") + content_lines = [] + in_content = False + for line in lines: + if line.startswith("@@"): + in_content = True + continue + if in_content and line.strip(): + content_lines.append(line) + + if content_lines: + return "\n".join(content_lines) + + result = subprocess.run( + [ + "git", + "diff", + "--word-diff=plain", + "-U0", + "--no-index", + str(original_file), + str(modified_file), + ], + capture_output=True, + text=True, + ) + + if result.stdout.strip(): + lines = result.stdout.split("\n") + content_lines = [] + in_content = False + for line in lines: + if line.startswith("@@"): + in_content = True + continue + if in_content and line.strip(): + content_lines.append(line) + return "\n".join(content_lines) + + except (subprocess.CalledProcessError, FileNotFoundError, Exception): + pass + + return None + + def _remove_author_tracked_changes(self, root): + ins_tag = f"{{{self.namespaces['w']}}}ins" + del_tag = f"{{{self.namespaces['w']}}}del" + author_attr = f"{{{self.namespaces['w']}}}author" + + for parent in root.iter(): + to_remove = [] + for child in parent: + if child.tag == ins_tag and child.get(author_attr) == self.author: + to_remove.append(child) + for elem in to_remove: + parent.remove(elem) + + deltext_tag = f"{{{self.namespaces['w']}}}delText" + t_tag = f"{{{self.namespaces['w']}}}t" + + for parent in root.iter(): + to_process = [] + for child in parent: + if child.tag == del_tag and child.get(author_attr) == self.author: + to_process.append((child, list(parent).index(child))) + + for del_elem, del_index in reversed(to_process): + for elem in del_elem.iter(): + if elem.tag == deltext_tag: + elem.tag = t_tag + + for child in reversed(list(del_elem)): + parent.insert(del_index, child) + parent.remove(del_elem) + + def _extract_text_content(self, root): + p_tag = f"{{{self.namespaces['w']}}}p" + t_tag = f"{{{self.namespaces['w']}}}t" + + paragraphs = [] + for p_elem in root.findall(f".//{p_tag}"): + text_parts = [] + for t_elem in p_elem.findall(f".//{t_tag}"): + if t_elem.text: + text_parts.append(t_elem.text) + paragraph_text = "".join(text_parts) + if paragraph_text: + paragraphs.append(paragraph_text) + + return "\n".join(paragraphs) + + +if __name__ == "__main__": + raise RuntimeError("This module should not be run directly.") diff --git a/mateclaw-server/src/main/resources/skills/xlsx/scripts/recalc.py b/mateclaw-server/src/main/resources/skills/xlsx/scripts/recalc.py new file mode 100755 index 00000000..1501abc0 --- /dev/null +++ b/mateclaw-server/src/main/resources/skills/xlsx/scripts/recalc.py @@ -0,0 +1,209 @@ +""" +Excel Formula Recalculation Script +Recalculates all formulas in an Excel file using LibreOffice +""" + +import json +import os +import platform +import subprocess +import sys +from pathlib import Path + +from office.soffice import get_soffice_cmd, get_soffice_env + +from openpyxl import load_workbook + +MACRO_DIR_MACOS = "~/Library/Application Support/LibreOffice/4/user/basic/Standard" +MACRO_DIR_LINUX = "~/.config/libreoffice/4/user/basic/Standard" +MACRO_DIR_WINDOWS = "~/AppData/Roaming/LibreOffice/4/user/basic/Standard" +MACRO_FILENAME = "Module1.xba" + +RECALCULATE_MACRO = """ + + + Sub RecalculateAndSave() + ThisComponent.calculateAll() + ThisComponent.store() + ThisComponent.close(True) + End Sub +""" + + +def has_gtimeout(): + try: + subprocess.run( + ["gtimeout", "--version"], capture_output=True, timeout=1, check=False + ) + return True + except (FileNotFoundError, subprocess.TimeoutExpired): + return False + + +def _get_macro_dir() -> str: + """Return the LibreOffice macro directory for the current platform.""" + system = platform.system() + if system == "Darwin": + return MACRO_DIR_MACOS + elif system == "Windows": + return MACRO_DIR_WINDOWS + else: + return MACRO_DIR_LINUX + + +def setup_libreoffice_macro(): + macro_dir = os.path.expanduser(_get_macro_dir()) + macro_file = os.path.join(macro_dir, MACRO_FILENAME) + + if ( + os.path.exists(macro_file) + and "RecalculateAndSave" in Path(macro_file).read_text() + ): + return True + + if not os.path.exists(macro_dir): + subprocess.run( + [get_soffice_cmd(), "--headless", "--terminate_after_init"], + capture_output=True, + timeout=10, + env=get_soffice_env(), + ) + os.makedirs(macro_dir, exist_ok=True) + + try: + Path(macro_file).write_text(RECALCULATE_MACRO) + return True + except Exception: + return False + + +def recalc(filename, timeout=30): + if not Path(filename).exists(): + return {"error": f"File {filename} does not exist"} + + abs_path = str(Path(filename).absolute()) + + if not setup_libreoffice_macro(): + return {"error": "Failed to setup LibreOffice macro"} + + cmd = [ + get_soffice_cmd(), + "--headless", + "--norestore", + "vnd.sun.star.script:Standard.Module1.RecalculateAndSave?language=Basic&location=application", + abs_path, + ] + + system = platform.system() + if system == "Linux": + cmd = ["timeout", str(timeout)] + cmd + elif system == "Darwin" and has_gtimeout(): + cmd = ["gtimeout", str(timeout)] + cmd + # On Windows, rely on subprocess timeout parameter instead of external tool + + try: + result = subprocess.run( + cmd, + capture_output=True, + text=True, + env=get_soffice_env(), + timeout=timeout if system == "Windows" else None, + ) + except subprocess.TimeoutExpired: + return { + "error": ( + f"LibreOffice recalculation timed out after {timeout} seconds" + ), + } + + if result.returncode != 0 and result.returncode != 124: + error_msg = result.stderr or "Unknown error during recalculation" + if "Module1" in error_msg or "RecalculateAndSave" not in error_msg: + return {"error": "LibreOffice macro not configured properly"} + return {"error": error_msg} + + try: + wb = load_workbook(filename, data_only=True) + + excel_errors = [ + "#VALUE!", + "#DIV/0!", + "#REF!", + "#NAME?", + "#NULL!", + "#NUM!", + "#N/A", + ] + error_details = {err: [] for err in excel_errors} + total_errors = 0 + + for sheet_name in wb.sheetnames: + ws = wb[sheet_name] + for row in ws.iter_rows(): + for cell in row: + if cell.value is not None and isinstance(cell.value, str): + for err in excel_errors: + if err in cell.value: + location = f"{sheet_name}!{cell.coordinate}" + error_details[err].append(location) + total_errors += 1 + break + + wb.close() + + result = { + "status": "success" if total_errors == 0 else "errors_found", + "total_errors": total_errors, + "error_summary": {}, + } + + for err_type, locations in error_details.items(): + if locations: + result["error_summary"][err_type] = { + "count": len(locations), + "locations": locations[:20], + } + + wb_formulas = load_workbook(filename, data_only=False) + formula_count = 0 + for sheet_name in wb_formulas.sheetnames: + ws = wb_formulas[sheet_name] + for row in ws.iter_rows(): + for cell in row: + if ( + cell.value + and isinstance(cell.value, str) + and cell.value.startswith("=") + ): + formula_count += 1 + wb_formulas.close() + + result["total_formulas"] = formula_count + + return result + + except Exception as e: + return {"error": str(e)} + + +def main(): + if len(sys.argv) < 2: + print("Usage: python recalc.py [timeout_seconds]") + print("\nRecalculates all formulas in an Excel file using LibreOffice") + print("\nReturns JSON with error details:") + print(" - status: 'success' or 'errors_found'") + print(" - total_errors: Total number of Excel errors found") + print(" - total_formulas: Number of formulas in the file") + print(" - error_summary: Breakdown by error type with locations") + print(" - #VALUE!, #DIV/0!, #REF!, #NAME?, #NULL!, #NUM!, #N/A") + sys.exit(1) + + filename = sys.argv[1] + timeout = int(sys.argv[2]) if len(sys.argv) > 2 else 30 + + result = recalc(filename, timeout) + print(json.dumps(result, indent=2)) + + +if __name__ == "__main__": + main()