commit 3fecae738ce90f9c137c5b7523218809b12f94a3 Author: Zhongwei Li Date: Sat Nov 29 18:15:44 2025 +0800 Initial commit diff --git a/.claude-plugin/plugin.json b/.claude-plugin/plugin.json new file mode 100644 index 0000000..3b9b6a9 --- /dev/null +++ b/.claude-plugin/plugin.json @@ -0,0 +1,12 @@ +{ + "name": "document-skills-pptx", + "description": "Skills for working with PowerPoint presentations including creation, editing, and formatting using PPTX format.", + "version": "0.0.0-2025.11.28", + "author": { + "name": "ComposioHQ", + "email": "tech@composio.dev" + }, + "skills": [ + "./" + ] +} \ No newline at end of file diff --git a/LICENSE.txt b/LICENSE.txt new file mode 100644 index 0000000..c55ab42 --- /dev/null +++ b/LICENSE.txt @@ -0,0 +1,30 @@ +© 2025 Anthropic, PBC. All rights reserved. + +LICENSE: Use of these materials (including all code, prompts, assets, files, +and other components of this Skill) is governed by your agreement with +Anthropic regarding use of Anthropic's services. If no separate agreement +exists, use is governed by Anthropic's Consumer Terms of Service or +Commercial Terms of Service, as applicable: +https://www.anthropic.com/legal/consumer-terms +https://www.anthropic.com/legal/commercial-terms +Your applicable agreement is referred to as the "Agreement." "Services" are +as defined in the Agreement. + +ADDITIONAL RESTRICTIONS: Notwithstanding anything in the Agreement to the +contrary, users may not: + +- Extract these materials from the Services or retain copies of these + materials outside the Services +- Reproduce or copy these materials, except for temporary copies created + automatically during authorized use of the Services +- Create derivative works based on these materials +- Distribute, sublicense, or transfer these materials to any third party +- Make, offer to sell, sell, or import any inventions embodied in these + materials +- Reverse engineer, decompile, or disassemble these materials + +The receipt, viewing, or possession of these materials does not convey or +imply any license or right beyond those expressly granted above. + +Anthropic retains all right, title, and interest in these materials, +including all copyrights, patents, and other intellectual property rights. diff --git a/README.md b/README.md new file mode 100644 index 0000000..d5b4c36 --- /dev/null +++ b/README.md @@ -0,0 +1,3 @@ +# document-skills-pptx + +Skills for working with PowerPoint presentations including creation, editing, and formatting using PPTX format. diff --git a/SKILL.md b/SKILL.md new file mode 100644 index 0000000..b93b875 --- /dev/null +++ b/SKILL.md @@ -0,0 +1,484 @@ +--- +name: pptx +description: "Presentation creation, editing, and analysis. When Claude needs to work with presentations (.pptx files) for: (1) Creating new presentations, (2) Modifying or editing content, (3) Working with layouts, (4) Adding comments or speaker notes, or any other presentation tasks" +license: Proprietary. LICENSE.txt has complete terms +--- + +# PPTX creation, editing, and analysis + +## Overview + +A user may ask you to create, edit, or analyze the contents of a .pptx file. A .pptx file is essentially a ZIP archive containing XML files and other resources that you can read or edit. You have different tools and workflows available for different tasks. + +## Reading and analyzing content + +### Text extraction +If you just need to read the text contents of a presentation, you should convert the document to markdown: + +```bash +# Convert document to markdown +python -m markitdown path-to-file.pptx +``` + +### Raw XML access +You need raw XML access for: comments, speaker notes, slide layouts, animations, design elements, and complex formatting. For any of these features, you'll need to unpack a presentation and read its raw XML contents. + +#### Unpacking a file +`python ooxml/scripts/unpack.py ` + +**Note**: The unpack.py script is located at `skills/pptx/ooxml/scripts/unpack.py` relative to the project root. If the script doesn't exist at this path, use `find . -name "unpack.py"` to locate it. + +#### Key file structures +* `ppt/presentation.xml` - Main presentation metadata and slide references +* `ppt/slides/slide{N}.xml` - Individual slide contents (slide1.xml, slide2.xml, etc.) +* `ppt/notesSlides/notesSlide{N}.xml` - Speaker notes for each slide +* `ppt/comments/modernComment_*.xml` - Comments for specific slides +* `ppt/slideLayouts/` - Layout templates for slides +* `ppt/slideMasters/` - Master slide templates +* `ppt/theme/` - Theme and styling information +* `ppt/media/` - Images and other media files + +#### Typography and color extraction +**When given an example design to emulate**: Always analyze the presentation's typography and colors first using the methods below: +1. **Read theme file**: Check `ppt/theme/theme1.xml` for colors (``) and fonts (``) +2. **Sample slide content**: Examine `ppt/slides/slide1.xml` for actual font usage (``) and colors +3. **Search for patterns**: Use grep to find color (``, ``) and font references across all XML files + +## Creating a new PowerPoint presentation **without a template** + +When creating a new PowerPoint presentation from scratch, use the **html2pptx** workflow to convert HTML slides to PowerPoint with accurate positioning. + +### Design Principles + +**CRITICAL**: Before creating any presentation, analyze the content and choose appropriate design elements: +1. **Consider the subject matter**: What is this presentation about? What tone, industry, or mood does it suggest? +2. **Check for branding**: If the user mentions a company/organization, consider their brand colors and identity +3. **Match palette to content**: Select colors that reflect the subject +4. **State your approach**: Explain your design choices before writing code + +**Requirements**: +- ✅ State your content-informed design approach BEFORE writing code +- ✅ Use web-safe fonts only: Arial, Helvetica, Times New Roman, Georgia, Courier New, Verdana, Tahoma, Trebuchet MS, Impact +- ✅ Create clear visual hierarchy through size, weight, and color +- ✅ Ensure readability: strong contrast, appropriately sized text, clean alignment +- ✅ Be consistent: repeat patterns, spacing, and visual language across slides + +#### Color Palette Selection + +**Choosing colors creatively**: +- **Think beyond defaults**: What colors genuinely match this specific topic? Avoid autopilot choices. +- **Consider multiple angles**: Topic, industry, mood, energy level, target audience, brand identity (if mentioned) +- **Be adventurous**: Try unexpected combinations - a healthcare presentation doesn't have to be green, finance doesn't have to be navy +- **Build your palette**: Pick 3-5 colors that work together (dominant colors + supporting tones + accent) +- **Ensure contrast**: Text must be clearly readable on backgrounds + +**Example color palettes** (use these to spark creativity - choose one, adapt it, or create your own): + +1. **Classic Blue**: Deep navy (#1C2833), slate gray (#2E4053), silver (#AAB7B8), off-white (#F4F6F6) +2. **Teal & Coral**: Teal (#5EA8A7), deep teal (#277884), coral (#FE4447), white (#FFFFFF) +3. **Bold Red**: Red (#C0392B), bright red (#E74C3C), orange (#F39C12), yellow (#F1C40F), green (#2ECC71) +4. **Warm Blush**: Mauve (#A49393), blush (#EED6D3), rose (#E8B4B8), cream (#FAF7F2) +5. **Burgundy Luxury**: Burgundy (#5D1D2E), crimson (#951233), rust (#C15937), gold (#997929) +6. **Deep Purple & Emerald**: Purple (#B165FB), dark blue (#181B24), emerald (#40695B), white (#FFFFFF) +7. **Cream & Forest Green**: Cream (#FFE1C7), forest green (#40695B), white (#FCFCFC) +8. **Pink & Purple**: Pink (#F8275B), coral (#FF574A), rose (#FF737D), purple (#3D2F68) +9. **Lime & Plum**: Lime (#C5DE82), plum (#7C3A5F), coral (#FD8C6E), blue-gray (#98ACB5) +10. **Black & Gold**: Gold (#BF9A4A), black (#000000), cream (#F4F6F6) +11. **Sage & Terracotta**: Sage (#87A96B), terracotta (#E07A5F), cream (#F4F1DE), charcoal (#2C2C2C) +12. **Charcoal & Red**: Charcoal (#292929), red (#E33737), light gray (#CCCBCB) +13. **Vibrant Orange**: Orange (#F96D00), light gray (#F2F2F2), charcoal (#222831) +14. **Forest Green**: Black (#191A19), green (#4E9F3D), dark green (#1E5128), white (#FFFFFF) +15. **Retro Rainbow**: Purple (#722880), pink (#D72D51), orange (#EB5C18), amber (#F08800), gold (#DEB600) +16. **Vintage Earthy**: Mustard (#E3B448), sage (#CBD18F), forest green (#3A6B35), cream (#F4F1DE) +17. **Coastal Rose**: Old rose (#AD7670), beaver (#B49886), eggshell (#F3ECDC), ash gray (#BFD5BE) +18. **Orange & Turquoise**: Light orange (#FC993E), grayish turquoise (#667C6F), white (#FCFCFC) + +#### Visual Details Options + +**Geometric Patterns**: +- Diagonal section dividers instead of horizontal +- Asymmetric column widths (30/70, 40/60, 25/75) +- Rotated text headers at 90° or 270° +- Circular/hexagonal frames for images +- Triangular accent shapes in corners +- Overlapping shapes for depth + +**Border & Frame Treatments**: +- Thick single-color borders (10-20pt) on one side only +- Double-line borders with contrasting colors +- Corner brackets instead of full frames +- L-shaped borders (top+left or bottom+right) +- Underline accents beneath headers (3-5pt thick) + +**Typography Treatments**: +- Extreme size contrast (72pt headlines vs 11pt body) +- All-caps headers with wide letter spacing +- Numbered sections in oversized display type +- Monospace (Courier New) for data/stats/technical content +- Condensed fonts (Arial Narrow) for dense information +- Outlined text for emphasis + +**Chart & Data Styling**: +- Monochrome charts with single accent color for key data +- Horizontal bar charts instead of vertical +- Dot plots instead of bar charts +- Minimal gridlines or none at all +- Data labels directly on elements (no legends) +- Oversized numbers for key metrics + +**Layout Innovations**: +- Full-bleed images with text overlays +- Sidebar column (20-30% width) for navigation/context +- Modular grid systems (3×3, 4×4 blocks) +- Z-pattern or F-pattern content flow +- Floating text boxes over colored shapes +- Magazine-style multi-column layouts + +**Background Treatments**: +- Solid color blocks occupying 40-60% of slide +- Gradient fills (vertical or diagonal only) +- Split backgrounds (two colors, diagonal or vertical) +- Edge-to-edge color bands +- Negative space as a design element + +### Layout Tips +**When creating slides with charts or tables:** +- **Two-column layout (PREFERRED)**: Use a header spanning the full width, then two columns below - text/bullets in one column and the featured content in the other. This provides better balance and makes charts/tables more readable. Use flexbox with unequal column widths (e.g., 40%/60% split) to optimize space for each content type. +- **Full-slide layout**: Let the featured content (chart/table) take up the entire slide for maximum impact and readability +- **NEVER vertically stack**: Do not place charts/tables below text in a single column - this causes poor readability and layout issues + +### Workflow +1. **MANDATORY - READ ENTIRE FILE**: Read [`html2pptx.md`](html2pptx.md) completely from start to finish. **NEVER set any range limits when reading this file.** Read the full file content for detailed syntax, critical formatting rules, and best practices before proceeding with presentation creation. +2. Create an HTML file for each slide with proper dimensions (e.g., 720pt × 405pt for 16:9) + - Use `

`, `

`-`

`, `
    `, `
      ` for all text content + - Use `class="placeholder"` for areas where charts/tables will be added (render with gray background for visibility) + - **CRITICAL**: Rasterize gradients and icons as PNG images FIRST using Sharp, then reference in HTML + - **LAYOUT**: For slides with charts/tables/images, use either full-slide layout or two-column layout for better readability +3. Create and run a JavaScript file using the [`html2pptx.js`](scripts/html2pptx.js) library to convert HTML slides to PowerPoint and save the presentation + - Use the `html2pptx()` function to process each HTML file + - Add charts and tables to placeholder areas using PptxGenJS API + - Save the presentation using `pptx.writeFile()` +4. **Visual validation**: Generate thumbnails and inspect for layout issues + - Create thumbnail grid: `python scripts/thumbnail.py output.pptx workspace/thumbnails --cols 4` + - Read and carefully examine the thumbnail image for: + - **Text cutoff**: Text being cut off by header bars, shapes, or slide edges + - **Text overlap**: Text overlapping with other text or shapes + - **Positioning issues**: Content too close to slide boundaries or other elements + - **Contrast issues**: Insufficient contrast between text and backgrounds + - If issues found, adjust HTML margins/spacing/colors and regenerate the presentation + - Repeat until all slides are visually correct + +## Editing an existing PowerPoint presentation + +When edit slides in an existing PowerPoint presentation, you need to work with the raw Office Open XML (OOXML) format. This involves unpacking the .pptx file, editing the XML content, and repacking it. + +### Workflow +1. **MANDATORY - READ ENTIRE FILE**: Read [`ooxml.md`](ooxml.md) (~500 lines) completely from start to finish. **NEVER set any range limits when reading this file.** Read the full file content for detailed guidance on OOXML structure and editing workflows before any presentation editing. +2. Unpack the presentation: `python ooxml/scripts/unpack.py ` +3. Edit the XML files (primarily `ppt/slides/slide{N}.xml` and related files) +4. **CRITICAL**: Validate immediately after each edit and fix any validation errors before proceeding: `python ooxml/scripts/validate.py --original ` +5. Pack the final presentation: `python ooxml/scripts/pack.py ` + +## Creating a new PowerPoint presentation **using a template** + +When you need to create a presentation that follows an existing template's design, you'll need to duplicate and re-arrange template slides before then replacing placeholder context. + +### Workflow +1. **Extract template text AND create visual thumbnail grid**: + * Extract text: `python -m markitdown template.pptx > template-content.md` + * Read `template-content.md`: Read the entire file to understand the contents of the template presentation. **NEVER set any range limits when reading this file.** + * Create thumbnail grids: `python scripts/thumbnail.py template.pptx` + * See [Creating Thumbnail Grids](#creating-thumbnail-grids) section for more details + +2. **Analyze template and save inventory to a file**: + * **Visual Analysis**: Review thumbnail grid(s) to understand slide layouts, design patterns, and visual structure + * Create and save a template inventory file at `template-inventory.md` containing: + ```markdown + # Template Inventory Analysis + **Total Slides: [count]** + **IMPORTANT: Slides are 0-indexed (first slide = 0, last slide = count-1)** + + ## [Category Name] + - Slide 0: [Layout code if available] - Description/purpose + - Slide 1: [Layout code] - Description/purpose + - Slide 2: [Layout code] - Description/purpose + [... EVERY slide must be listed individually with its index ...] + ``` + * **Using the thumbnail grid**: Reference the visual thumbnails to identify: + - Layout patterns (title slides, content layouts, section dividers) + - Image placeholder locations and counts + - Design consistency across slide groups + - Visual hierarchy and structure + * This inventory file is REQUIRED for selecting appropriate templates in the next step + +3. **Create presentation outline based on template inventory**: + * Review available templates from step 2. + * Choose an intro or title template for the first slide. This should be one of the first templates. + * Choose safe, text-based layouts for the other slides. + * **CRITICAL: Match layout structure to actual content**: + - Single-column layouts: Use for unified narrative or single topic + - Two-column layouts: Use ONLY when you have exactly 2 distinct items/concepts + - Three-column layouts: Use ONLY when you have exactly 3 distinct items/concepts + - Image + text layouts: Use ONLY when you have actual images to insert + - Quote layouts: Use ONLY for actual quotes from people (with attribution), never for emphasis + - Never use layouts with more placeholders than you have content + - If you have 2 items, don't force them into a 3-column layout + - If you have 4+ items, consider breaking into multiple slides or using a list format + * Count your actual content pieces BEFORE selecting the layout + * Verify each placeholder in the chosen layout will be filled with meaningful content + * Select one option representing the **best** layout for each content section. + * Save `outline.md` with content AND template mapping that leverages available designs + * Example template mapping: + ``` + # Template slides to use (0-based indexing) + # WARNING: Verify indices are within range! Template with 73 slides has indices 0-72 + # Mapping: slide numbers from outline -> template slide indices + template_mapping = [ + 0, # Use slide 0 (Title/Cover) + 34, # Use slide 34 (B1: Title and body) + 34, # Use slide 34 again (duplicate for second B1) + 50, # Use slide 50 (E1: Quote) + 54, # Use slide 54 (F2: Closing + Text) + ] + ``` + +4. **Duplicate, reorder, and delete slides using `rearrange.py`**: + * Use the `scripts/rearrange.py` script to create a new presentation with slides in the desired order: + ```bash + python scripts/rearrange.py template.pptx working.pptx 0,34,34,50,52 + ``` + * The script handles duplicating repeated slides, deleting unused slides, and reordering automatically + * Slide indices are 0-based (first slide is 0, second is 1, etc.) + * The same slide index can appear multiple times to duplicate that slide + +5. **Extract ALL text using the `inventory.py` script**: + * **Run inventory extraction**: + ```bash + python scripts/inventory.py working.pptx text-inventory.json + ``` + * **Read text-inventory.json**: Read the entire text-inventory.json file to understand all shapes and their properties. **NEVER set any range limits when reading this file.** + + * The inventory JSON structure: + ```json + { + "slide-0": { + "shape-0": { + "placeholder_type": "TITLE", // or null for non-placeholders + "left": 1.5, // position in inches + "top": 2.0, + "width": 7.5, + "height": 1.2, + "paragraphs": [ + { + "text": "Paragraph text", + // Optional properties (only included when non-default): + "bullet": true, // explicit bullet detected + "level": 0, // only included when bullet is true + "alignment": "CENTER", // CENTER, RIGHT (not LEFT) + "space_before": 10.0, // space before paragraph in points + "space_after": 6.0, // space after paragraph in points + "line_spacing": 22.4, // line spacing in points + "font_name": "Arial", // from first run + "font_size": 14.0, // in points + "bold": true, + "italic": false, + "underline": false, + "color": "FF0000" // RGB color + } + ] + } + } + } + ``` + + * Key features: + - **Slides**: Named as "slide-0", "slide-1", etc. + - **Shapes**: Ordered by visual position (top-to-bottom, left-to-right) as "shape-0", "shape-1", etc. + - **Placeholder types**: TITLE, CENTER_TITLE, SUBTITLE, BODY, OBJECT, or null + - **Default font size**: `default_font_size` in points extracted from layout placeholders (when available) + - **Slide numbers are filtered**: Shapes with SLIDE_NUMBER placeholder type are automatically excluded from inventory + - **Bullets**: When `bullet: true`, `level` is always included (even if 0) + - **Spacing**: `space_before`, `space_after`, and `line_spacing` in points (only included when set) + - **Colors**: `color` for RGB (e.g., "FF0000"), `theme_color` for theme colors (e.g., "DARK_1") + - **Properties**: Only non-default values are included in the output + +6. **Generate replacement text and save the data to a JSON file** + Based on the text inventory from the previous step: + - **CRITICAL**: First verify which shapes exist in the inventory - only reference shapes that are actually present + - **VALIDATION**: The replace.py script will validate that all shapes in your replacement JSON exist in the inventory + - If you reference a non-existent shape, you'll get an error showing available shapes + - If you reference a non-existent slide, you'll get an error indicating the slide doesn't exist + - All validation errors are shown at once before the script exits + - **IMPORTANT**: The replace.py script uses inventory.py internally to identify ALL text shapes + - **AUTOMATIC CLEARING**: ALL text shapes from the inventory will be cleared unless you provide "paragraphs" for them + - Add a "paragraphs" field to shapes that need content (not "replacement_paragraphs") + - Shapes without "paragraphs" in the replacement JSON will have their text cleared automatically + - Paragraphs with bullets will be automatically left aligned. Don't set the `alignment` property on when `"bullet": true` + - Generate appropriate replacement content for placeholder text + - Use shape size to determine appropriate content length + - **CRITICAL**: Include paragraph properties from the original inventory - don't just provide text + - **IMPORTANT**: When bullet: true, do NOT include bullet symbols (•, -, *) in text - they're added automatically + - **ESSENTIAL FORMATTING RULES**: + - Headers/titles should typically have `"bold": true` + - List items should have `"bullet": true, "level": 0` (level is required when bullet is true) + - Preserve any alignment properties (e.g., `"alignment": "CENTER"` for centered text) + - Include font properties when different from default (e.g., `"font_size": 14.0`, `"font_name": "Lora"`) + - Colors: Use `"color": "FF0000"` for RGB or `"theme_color": "DARK_1"` for theme colors + - The replacement script expects **properly formatted paragraphs**, not just text strings + - **Overlapping shapes**: Prefer shapes with larger default_font_size or more appropriate placeholder_type + - Save the updated inventory with replacements to `replacement-text.json` + - **WARNING**: Different template layouts have different shape counts - always check the actual inventory before creating replacements + + Example paragraphs field showing proper formatting: + ```json + "paragraphs": [ + { + "text": "New presentation title text", + "alignment": "CENTER", + "bold": true + }, + { + "text": "Section Header", + "bold": true + }, + { + "text": "First bullet point without bullet symbol", + "bullet": true, + "level": 0 + }, + { + "text": "Red colored text", + "color": "FF0000" + }, + { + "text": "Theme colored text", + "theme_color": "DARK_1" + }, + { + "text": "Regular paragraph text without special formatting" + } + ] + ``` + + **Shapes not listed in the replacement JSON are automatically cleared**: + ```json + { + "slide-0": { + "shape-0": { + "paragraphs": [...] // This shape gets new text + } + // shape-1 and shape-2 from inventory will be cleared automatically + } + } + ``` + + **Common formatting patterns for presentations**: + - Title slides: Bold text, sometimes centered + - Section headers within slides: Bold text + - Bullet lists: Each item needs `"bullet": true, "level": 0` + - Body text: Usually no special properties needed + - Quotes: May have special alignment or font properties + +7. **Apply replacements using the `replace.py` script** + ```bash + python scripts/replace.py working.pptx replacement-text.json output.pptx + ``` + + The script will: + - First extract the inventory of ALL text shapes using functions from inventory.py + - Validate that all shapes in the replacement JSON exist in the inventory + - Clear text from ALL shapes identified in the inventory + - Apply new text only to shapes with "paragraphs" defined in the replacement JSON + - Preserve formatting by applying paragraph properties from the JSON + - Handle bullets, alignment, font properties, and colors automatically + - Save the updated presentation + + Example validation errors: + ``` + ERROR: Invalid shapes in replacement JSON: + - Shape 'shape-99' not found on 'slide-0'. Available shapes: shape-0, shape-1, shape-4 + - Slide 'slide-999' not found in inventory + ``` + + ``` + ERROR: Replacement text made overflow worse in these shapes: + - slide-0/shape-2: overflow worsened by 1.25" (was 0.00", now 1.25") + ``` + +## Creating Thumbnail Grids + +To create visual thumbnail grids of PowerPoint slides for quick analysis and reference: + +```bash +python scripts/thumbnail.py template.pptx [output_prefix] +``` + +**Features**: +- Creates: `thumbnails.jpg` (or `thumbnails-1.jpg`, `thumbnails-2.jpg`, etc. for large decks) +- Default: 5 columns, max 30 slides per grid (5×6) +- Custom prefix: `python scripts/thumbnail.py template.pptx my-grid` + - Note: The output prefix should include the path if you want output in a specific directory (e.g., `workspace/my-grid`) +- Adjust columns: `--cols 4` (range: 3-6, affects slides per grid) +- Grid limits: 3 cols = 12 slides/grid, 4 cols = 20, 5 cols = 30, 6 cols = 42 +- Slides are zero-indexed (Slide 0, Slide 1, etc.) + +**Use cases**: +- Template analysis: Quickly understand slide layouts and design patterns +- Content review: Visual overview of entire presentation +- Navigation reference: Find specific slides by their visual appearance +- Quality check: Verify all slides are properly formatted + +**Examples**: +```bash +# Basic usage +python scripts/thumbnail.py presentation.pptx + +# Combine options: custom name, columns +python scripts/thumbnail.py template.pptx analysis --cols 4 +``` + +## Converting Slides to Images + +To visually analyze PowerPoint slides, convert them to images using a two-step process: + +1. **Convert PPTX to PDF**: + ```bash + soffice --headless --convert-to pdf template.pptx + ``` + +2. **Convert PDF pages to JPEG images**: + ```bash + pdftoppm -jpeg -r 150 template.pdf slide + ``` + This creates files like `slide-1.jpg`, `slide-2.jpg`, etc. + +Options: +- `-r 150`: Sets resolution to 150 DPI (adjust for quality/size balance) +- `-jpeg`: Output JPEG format (use `-png` for PNG if preferred) +- `-f N`: First page to convert (e.g., `-f 2` starts from page 2) +- `-l N`: Last page to convert (e.g., `-l 5` stops at page 5) +- `slide`: Prefix for output files + +Example for specific range: +```bash +pdftoppm -jpeg -r 150 -f 2 -l 5 template.pdf slide # Converts only pages 2-5 +``` + +## Code Style Guidelines +**IMPORTANT**: When generating code for PPTX operations: +- Write concise code +- Avoid verbose variable names and redundant operations +- Avoid unnecessary print statements + +## Dependencies + +Required dependencies (should already be installed): + +- **markitdown**: `pip install "markitdown[pptx]"` (for text extraction from presentations) +- **pptxgenjs**: `npm install -g pptxgenjs` (for creating presentations via html2pptx) +- **playwright**: `npm install -g playwright` (for HTML rendering in html2pptx) +- **react-icons**: `npm install -g react-icons react react-dom` (for icons) +- **sharp**: `npm install -g sharp` (for SVG rasterization and image processing) +- **LibreOffice**: `sudo apt-get install libreoffice` (for PDF conversion) +- **Poppler**: `sudo apt-get install poppler-utils` (for pdftoppm to convert PDF to images) +- **defusedxml**: `pip install defusedxml` (for secure XML parsing) \ No newline at end of file diff --git a/html2pptx.md b/html2pptx.md new file mode 100644 index 0000000..106adf7 --- /dev/null +++ b/html2pptx.md @@ -0,0 +1,625 @@ +# HTML to PowerPoint Guide + +Convert HTML slides to PowerPoint presentations with accurate positioning using the `html2pptx.js` library. + +## Table of Contents + +1. [Creating HTML Slides](#creating-html-slides) +2. [Using the html2pptx Library](#using-the-html2pptx-library) +3. [Using PptxGenJS](#using-pptxgenjs) + +--- + +## Creating HTML Slides + +Every HTML slide must include proper body dimensions: + +### Layout Dimensions + +- **16:9** (default): `width: 720pt; height: 405pt` +- **4:3**: `width: 720pt; height: 540pt` +- **16:10**: `width: 720pt; height: 450pt` + +### Supported Elements + +- `

      `, `

      `-`

      ` - Text with styling +- `
        `, `
          ` - Lists (never use manual bullets •, -, *) +- ``, `` - Bold text (inline formatting) +- ``, `` - Italic text (inline formatting) +- `` - Underlined text (inline formatting) +- `` - Inline formatting with CSS styles (bold, italic, underline, color) +- `
          ` - Line breaks +- `
          ` with bg/border - Becomes shape +- `` - Images +- `class="placeholder"` - Reserved space for charts (returns `{ id, x, y, w, h }`) + +### Critical Text Rules + +**ALL text MUST be inside `

          `, `

          `-`

          `, `
            `, or `
              ` tags:** +- ✅ Correct: `

              Text here

              ` +- ❌ Wrong: `
              Text here
              ` - **Text will NOT appear in PowerPoint** +- ❌ Wrong: `Text` - **Text will NOT appear in PowerPoint** +- Text in `
              ` or `` without a text tag will be silently ignored + +**NEVER use manual bullet symbols (•, -, *, etc.)** - Use `
                ` or `
                  ` lists instead + +**ONLY use web-safe fonts that are universally available:** +- ✅ Web-safe fonts: `Arial`, `Helvetica`, `Times New Roman`, `Georgia`, `Courier New`, `Verdana`, `Tahoma`, `Trebuchet MS`, `Impact`, `Comic Sans MS` +- ❌ Wrong: `'Segoe UI'`, `'SF Pro'`, `'Roboto'`, custom fonts - **Might cause rendering issues** + +### Styling + +- Use `display: flex` on body to prevent margin collapse from breaking overflow validation +- Use `margin` for spacing (padding included in size) +- Inline formatting: Use ``, ``, `` tags OR `` with CSS styles + - `` supports: `font-weight: bold`, `font-style: italic`, `text-decoration: underline`, `color: #rrggbb` + - `` does NOT support: `margin`, `padding` (not supported in PowerPoint text runs) + - Example: `Bold blue text` +- Flexbox works - positions calculated from rendered layout +- Use hex colors with `#` prefix in CSS +- **Text alignment**: Use CSS `text-align` (`center`, `right`, etc.) when needed as a hint to PptxGenJS for text formatting if text lengths are slightly off + +### Shape Styling (DIV elements only) + +**IMPORTANT: Backgrounds, borders, and shadows only work on `
                  ` elements, NOT on text elements (`

                  `, `

                  `-`

                  `, `
                    `, `
                      `)** + +- **Backgrounds**: CSS `background` or `background-color` on `
                      ` elements only + - Example: `
                      ` - Creates a shape with background +- **Borders**: CSS `border` on `
                      ` elements converts to PowerPoint shape borders + - Supports uniform borders: `border: 2px solid #333333` + - Supports partial borders: `border-left`, `border-right`, `border-top`, `border-bottom` (rendered as line shapes) + - Example: `
                      ` +- **Border radius**: CSS `border-radius` on `
                      ` elements for rounded corners + - `border-radius: 50%` or higher creates circular shape + - Percentages <50% calculated relative to shape's smaller dimension + - Supports px and pt units (e.g., `border-radius: 8pt;`, `border-radius: 12px;`) + - Example: `
                      ` on 100x200px box = 25% of 100px = 25px radius +- **Box shadows**: CSS `box-shadow` on `
                      ` elements converts to PowerPoint shadows + - Supports outer shadows only (inset shadows are ignored to prevent corruption) + - Example: `
                      ` + - Note: Inset/inner shadows are not supported by PowerPoint and will be skipped + +### Icons & Gradients + +- **CRITICAL: Never use CSS gradients (`linear-gradient`, `radial-gradient`)** - They don't convert to PowerPoint +- **ALWAYS create gradient/icon PNGs FIRST using Sharp, then reference in HTML** +- For gradients: Rasterize SVG to PNG background images +- For icons: Rasterize react-icons SVG to PNG images +- All visual effects must be pre-rendered as raster images before HTML rendering + +**Rasterizing Icons with Sharp:** + +```javascript +const React = require('react'); +const ReactDOMServer = require('react-dom/server'); +const sharp = require('sharp'); +const { FaHome } = require('react-icons/fa'); + +async function rasterizeIconPng(IconComponent, color, size = "256", filename) { + const svgString = ReactDOMServer.renderToStaticMarkup( + React.createElement(IconComponent, { color: `#${color}`, size: size }) + ); + + // Convert SVG to PNG using Sharp + await sharp(Buffer.from(svgString)) + .png() + .toFile(filename); + + return filename; +} + +// Usage: Rasterize icon before using in HTML +const iconPath = await rasterizeIconPng(FaHome, "4472c4", "256", "home-icon.png"); +// Then reference in HTML: +``` + +**Rasterizing Gradients with Sharp:** + +```javascript +const sharp = require('sharp'); + +async function createGradientBackground(filename) { + const svg = ` + + + + + + + + `; + + await sharp(Buffer.from(svg)) + .png() + .toFile(filename); + + return filename; +} + +// Usage: Create gradient background before HTML +const bgPath = await createGradientBackground("gradient-bg.png"); +// Then in HTML: +``` + +### Example + +```html + + + + + + +
                      +

                      Recipe Title

                      +
                        +
                      • Item: Description
                        • +
                      +

                      Text with bold, italic, underline.

                      +
                      + + +
                      +

                      5

                      +
                      +
                      + + +``` + +## Using the html2pptx Library + +### Dependencies + +These libraries have been globally installed and are available to use: +- `pptxgenjs` +- `playwright` +- `sharp` + +### Basic Usage + +```javascript +const pptxgen = require('pptxgenjs'); +const html2pptx = require('./html2pptx'); + +const pptx = new pptxgen(); +pptx.layout = 'LAYOUT_16x9'; // Must match HTML body dimensions + +const { slide, placeholders } = await html2pptx('slide1.html', pptx); + +// Add chart to placeholder area +if (placeholders.length > 0) { + slide.addChart(pptx.charts.LINE, chartData, placeholders[0]); +} + +await pptx.writeFile('output.pptx'); +``` + +### API Reference + +#### Function Signature +```javascript +await html2pptx(htmlFile, pres, options) +``` + +#### Parameters +- `htmlFile` (string): Path to HTML file (absolute or relative) +- `pres` (pptxgen): PptxGenJS presentation instance with layout already set +- `options` (object, optional): + - `tmpDir` (string): Temporary directory for generated files (default: `process.env.TMPDIR || '/tmp'`) + - `slide` (object): Existing slide to reuse (default: creates new slide) + +#### Returns +```javascript +{ + slide: pptxgenSlide, // The created/updated slide + placeholders: [ // Array of placeholder positions + { id: string, x: number, y: number, w: number, h: number }, + ... + ] +} +``` + +### Validation + +The library automatically validates and collects all errors before throwing: + +1. **HTML dimensions must match presentation layout** - Reports dimension mismatches +2. **Content must not overflow body** - Reports overflow with exact measurements +3. **CSS gradients** - Reports unsupported gradient usage +4. **Text element styling** - Reports backgrounds/borders/shadows on text elements (only allowed on divs) + +**All validation errors are collected and reported together** in a single error message, allowing you to fix all issues at once instead of one at a time. + +### Working with Placeholders + +```javascript +const { slide, placeholders } = await html2pptx('slide.html', pptx); + +// Use first placeholder +slide.addChart(pptx.charts.BAR, data, placeholders[0]); + +// Find by ID +const chartArea = placeholders.find(p => p.id === 'chart-area'); +slide.addChart(pptx.charts.LINE, data, chartArea); +``` + +### Complete Example + +```javascript +const pptxgen = require('pptxgenjs'); +const html2pptx = require('./html2pptx'); + +async function createPresentation() { + const pptx = new pptxgen(); + pptx.layout = 'LAYOUT_16x9'; + pptx.author = 'Your Name'; + pptx.title = 'My Presentation'; + + // Slide 1: Title + const { slide: slide1 } = await html2pptx('slides/title.html', pptx); + + // Slide 2: Content with chart + const { slide: slide2, placeholders } = await html2pptx('slides/data.html', pptx); + + const chartData = [{ + name: 'Sales', + labels: ['Q1', 'Q2', 'Q3', 'Q4'], + values: [4500, 5500, 6200, 7100] + }]; + + slide2.addChart(pptx.charts.BAR, chartData, { + ...placeholders[0], + showTitle: true, + title: 'Quarterly Sales', + showCatAxisTitle: true, + catAxisTitle: 'Quarter', + showValAxisTitle: true, + valAxisTitle: 'Sales ($000s)' + }); + + // Save + await pptx.writeFile({ fileName: 'presentation.pptx' }); + console.log('Presentation created successfully!'); +} + +createPresentation().catch(console.error); +``` + +## Using PptxGenJS + +After converting HTML to slides with `html2pptx`, you'll use PptxGenJS to add dynamic content like charts, images, and additional elements. + +### ⚠️ Critical Rules + +#### Colors +- **NEVER use `#` prefix** with hex colors in PptxGenJS - causes file corruption +- ✅ Correct: `color: "FF0000"`, `fill: { color: "0066CC" }` +- ❌ Wrong: `color: "#FF0000"` (breaks document) + +### Adding Images + +Always calculate aspect ratios from actual image dimensions: + +```javascript +// Get image dimensions: identify image.png | grep -o '[0-9]* x [0-9]*' +const imgWidth = 1860, imgHeight = 1519; // From actual file +const aspectRatio = imgWidth / imgHeight; + +const h = 3; // Max height +const w = h * aspectRatio; +const x = (10 - w) / 2; // Center on 16:9 slide + +slide.addImage({ path: "chart.png", x, y: 1.5, w, h }); +``` + +### Adding Text + +```javascript +// Rich text with formatting +slide.addText([ + { text: "Bold ", options: { bold: true } }, + { text: "Italic ", options: { italic: true } }, + { text: "Normal" } +], { + x: 1, y: 2, w: 8, h: 1 +}); +``` + +### Adding Shapes + +```javascript +// Rectangle +slide.addShape(pptx.shapes.RECTANGLE, { + x: 1, y: 1, w: 3, h: 2, + fill: { color: "4472C4" }, + line: { color: "000000", width: 2 } +}); + +// Circle +slide.addShape(pptx.shapes.OVAL, { + x: 5, y: 1, w: 2, h: 2, + fill: { color: "ED7D31" } +}); + +// Rounded rectangle +slide.addShape(pptx.shapes.ROUNDED_RECTANGLE, { + x: 1, y: 4, w: 3, h: 1.5, + fill: { color: "70AD47" }, + rectRadius: 0.2 +}); +``` + +### Adding Charts + +**Required for most charts:** Axis labels using `catAxisTitle` (category) and `valAxisTitle` (value). + +**Chart Data Format:** +- Use **single series with all labels** for simple bar/line charts +- Each series creates a separate legend entry +- Labels array defines X-axis values + +**Time Series Data - Choose Correct Granularity:** +- **< 30 days**: Use daily grouping (e.g., "10-01", "10-02") - avoid monthly aggregation that creates single-point charts +- **30-365 days**: Use monthly grouping (e.g., "2024-01", "2024-02") +- **> 365 days**: Use yearly grouping (e.g., "2023", "2024") +- **Validate**: Charts with only 1 data point likely indicate incorrect aggregation for the time period + +```javascript +const { slide, placeholders } = await html2pptx('slide.html', pptx); + +// CORRECT: Single series with all labels +slide.addChart(pptx.charts.BAR, [{ + name: "Sales 2024", + labels: ["Q1", "Q2", "Q3", "Q4"], + values: [4500, 5500, 6200, 7100] +}], { + ...placeholders[0], // Use placeholder position + barDir: 'col', // 'col' = vertical bars, 'bar' = horizontal + showTitle: true, + title: 'Quarterly Sales', + showLegend: false, // No legend needed for single series + // Required axis labels + showCatAxisTitle: true, + catAxisTitle: 'Quarter', + showValAxisTitle: true, + valAxisTitle: 'Sales ($000s)', + // Optional: Control scaling (adjust min based on data range for better visualization) + valAxisMaxVal: 8000, + valAxisMinVal: 0, // Use 0 for counts/amounts; for clustered data (e.g., 4500-7100), consider starting closer to min value + valAxisMajorUnit: 2000, // Control y-axis label spacing to prevent crowding + catAxisLabelRotate: 45, // Rotate labels if crowded + dataLabelPosition: 'outEnd', + dataLabelColor: '000000', + // Use single color for single-series charts + chartColors: ["4472C4"] // All bars same color +}); +``` + +#### Scatter Chart + +**IMPORTANT**: Scatter chart data format is unusual - first series contains X-axis values, subsequent series contain Y-values: + +```javascript +// Prepare data +const data1 = [{ x: 10, y: 20 }, { x: 15, y: 25 }, { x: 20, y: 30 }]; +const data2 = [{ x: 12, y: 18 }, { x: 18, y: 22 }]; + +const allXValues = [...data1.map(d => d.x), ...data2.map(d => d.x)]; + +slide.addChart(pptx.charts.SCATTER, [ + { name: 'X-Axis', values: allXValues }, // First series = X values + { name: 'Series 1', values: data1.map(d => d.y) }, // Y values only + { name: 'Series 2', values: data2.map(d => d.y) } // Y values only +], { + x: 1, y: 1, w: 8, h: 4, + lineSize: 0, // 0 = no connecting lines + lineDataSymbol: 'circle', + lineDataSymbolSize: 6, + showCatAxisTitle: true, + catAxisTitle: 'X Axis', + showValAxisTitle: true, + valAxisTitle: 'Y Axis', + chartColors: ["4472C4", "ED7D31"] +}); +``` + +#### Line Chart + +```javascript +slide.addChart(pptx.charts.LINE, [{ + name: "Temperature", + labels: ["Jan", "Feb", "Mar", "Apr"], + values: [32, 35, 42, 55] +}], { + x: 1, y: 1, w: 8, h: 4, + lineSize: 4, + lineSmooth: true, + // Required axis labels + showCatAxisTitle: true, + catAxisTitle: 'Month', + showValAxisTitle: true, + valAxisTitle: 'Temperature (°F)', + // Optional: Y-axis range (set min based on data range for better visualization) + valAxisMinVal: 0, // For ranges starting at 0 (counts, percentages, etc.) + valAxisMaxVal: 60, + valAxisMajorUnit: 20, // Control y-axis label spacing to prevent crowding (e.g., 10, 20, 25) + // valAxisMinVal: 30, // PREFERRED: For data clustered in a range (e.g., 32-55 or ratings 3-5), start axis closer to min value to show variation + // Optional: Chart colors + chartColors: ["4472C4", "ED7D31", "A5A5A5"] +}); +``` + +#### Pie Chart (No Axis Labels Required) + +**CRITICAL**: Pie charts require a **single data series** with all categories in the `labels` array and corresponding values in the `values` array. + +```javascript +slide.addChart(pptx.charts.PIE, [{ + name: "Market Share", + labels: ["Product A", "Product B", "Other"], // All categories in one array + values: [35, 45, 20] // All values in one array +}], { + x: 2, y: 1, w: 6, h: 4, + showPercent: true, + showLegend: true, + legendPos: 'r', // right + chartColors: ["4472C4", "ED7D31", "A5A5A5"] +}); +``` + +#### Multiple Data Series + +```javascript +slide.addChart(pptx.charts.LINE, [ + { + name: "Product A", + labels: ["Q1", "Q2", "Q3", "Q4"], + values: [10, 20, 30, 40] + }, + { + name: "Product B", + labels: ["Q1", "Q2", "Q3", "Q4"], + values: [15, 25, 20, 35] + } +], { + x: 1, y: 1, w: 8, h: 4, + showCatAxisTitle: true, + catAxisTitle: 'Quarter', + showValAxisTitle: true, + valAxisTitle: 'Revenue ($M)' +}); +``` + +### Chart Colors + +**CRITICAL**: Use hex colors **without** the `#` prefix - including `#` causes file corruption. + +**Align chart colors with your chosen design palette**, ensuring sufficient contrast and distinctiveness for data visualization. Adjust colors for: +- Strong contrast between adjacent series +- Readability against slide backgrounds +- Accessibility (avoid red-green only combinations) + +```javascript +// Example: Ocean palette-inspired chart colors (adjusted for contrast) +const chartColors = ["16A085", "FF6B9D", "2C3E50", "F39C12", "9B59B6"]; + +// Single-series chart: Use one color for all bars/points +slide.addChart(pptx.charts.BAR, [{ + name: "Sales", + labels: ["Q1", "Q2", "Q3", "Q4"], + values: [4500, 5500, 6200, 7100] +}], { + ...placeholders[0], + chartColors: ["16A085"], // All bars same color + showLegend: false +}); + +// Multi-series chart: Each series gets a different color +slide.addChart(pptx.charts.LINE, [ + { name: "Product A", labels: ["Q1", "Q2", "Q3"], values: [10, 20, 30] }, + { name: "Product B", labels: ["Q1", "Q2", "Q3"], values: [15, 25, 20] } +], { + ...placeholders[0], + chartColors: ["16A085", "FF6B9D"] // One color per series +}); +``` + +### Adding Tables + +Tables can be added with basic or advanced formatting: + +#### Basic Table + +```javascript +slide.addTable([ + ["Header 1", "Header 2", "Header 3"], + ["Row 1, Col 1", "Row 1, Col 2", "Row 1, Col 3"], + ["Row 2, Col 1", "Row 2, Col 2", "Row 2, Col 3"] +], { + x: 0.5, + y: 1, + w: 9, + h: 3, + border: { pt: 1, color: "999999" }, + fill: { color: "F1F1F1" } +}); +``` + +#### Table with Custom Formatting + +```javascript +const tableData = [ + // Header row with custom styling + [ + { text: "Product", options: { fill: { color: "4472C4" }, color: "FFFFFF", bold: true } }, + { text: "Revenue", options: { fill: { color: "4472C4" }, color: "FFFFFF", bold: true } }, + { text: "Growth", options: { fill: { color: "4472C4" }, color: "FFFFFF", bold: true } } + ], + // Data rows + ["Product A", "$50M", "+15%"], + ["Product B", "$35M", "+22%"], + ["Product C", "$28M", "+8%"] +]; + +slide.addTable(tableData, { + x: 1, + y: 1.5, + w: 8, + h: 3, + colW: [3, 2.5, 2.5], // Column widths + rowH: [0.5, 0.6, 0.6, 0.6], // Row heights + border: { pt: 1, color: "CCCCCC" }, + align: "center", + valign: "middle", + fontSize: 14 +}); +``` + +#### Table with Merged Cells + +```javascript +const mergedTableData = [ + [ + { text: "Q1 Results", options: { colspan: 3, fill: { color: "4472C4" }, color: "FFFFFF", bold: true } } + ], + ["Product", "Sales", "Market Share"], + ["Product A", "$25M", "35%"], + ["Product B", "$18M", "25%"] +]; + +slide.addTable(mergedTableData, { + x: 1, + y: 1, + w: 8, + h: 2.5, + colW: [3, 2.5, 2.5], + border: { pt: 1, color: "DDDDDD" } +}); +``` + +### Table Options + +Common table options: +- `x, y, w, h` - Position and size +- `colW` - Array of column widths (in inches) +- `rowH` - Array of row heights (in inches) +- `border` - Border style: `{ pt: 1, color: "999999" }` +- `fill` - Background color (no # prefix) +- `align` - Text alignment: "left", "center", "right" +- `valign` - Vertical alignment: "top", "middle", "bottom" +- `fontSize` - Text size +- `autoPage` - Auto-create new slides if content overflows \ No newline at end of file diff --git a/ooxml.md b/ooxml.md new file mode 100644 index 0000000..951b3cf --- /dev/null +++ b/ooxml.md @@ -0,0 +1,427 @@ +# Office Open XML Technical Reference for PowerPoint + +**Important: Read this entire document before starting.** Critical XML schema rules and formatting requirements are covered throughout. Incorrect implementation can create invalid PPTX files that PowerPoint cannot open. + +## Technical Guidelines + +### Schema Compliance +- **Element ordering in ``**: ``, ``, `` +- **Whitespace**: Add `xml:space='preserve'` to `` elements with leading/trailing spaces +- **Unicode**: Escape characters in ASCII content: `"` becomes `“` +- **Images**: Add to `ppt/media/`, reference in slide XML, set dimensions to fit slide bounds +- **Relationships**: Update `ppt/slides/_rels/slideN.xml.rels` for each slide's resources +- **Dirty attribute**: Add `dirty="0"` to `` and `` elements to indicate clean state + +## Presentation Structure + +### Basic Slide Structure +```xml + + + + + ... + ... + + + + +``` + +### Text Box / Shape with Text +```xml + + + + + + + + + + + + + + + + + + + + + + Slide Title + + + + +``` + +### Text Formatting +```xml + + + + Bold Text + + + + + + Italic Text + + + + + + Underlined + + + + + + + + + + Highlighted Text + + + + + + + + + + Colored Arial 24pt + + + + + + + + + + Formatted text + +``` + +### Lists +```xml + + + + + + + First bullet point + + + + + + + + + + First numbered item + + + + + + + + + + Indented bullet + + +``` + +### Shapes +```xml + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +``` + +### Images +```xml + + + + + + + + + + + + + + + + + + + + + + + + + + +``` + +### Tables +```xml + + + + + + + + + + + + + + + + + + + + + + + + + + + Cell 1 + + + + + + + + + + + Cell 2 + + + + + + + + + +``` + +### Slide Layouts + +```xml + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +``` + +## File Updates + +When adding content, update these files: + +**`ppt/_rels/presentation.xml.rels`:** +```xml + + +``` + +**`ppt/slides/_rels/slide1.xml.rels`:** +```xml + + +``` + +**`[Content_Types].xml`:** +```xml + + + +``` + +**`ppt/presentation.xml`:** +```xml + + + + +``` + +**`docProps/app.xml`:** Update slide count and statistics +```xml +2 +10 +50 +``` + +## Slide Operations + +### Adding a New Slide +When adding a slide to the end of the presentation: + +1. **Create the slide file** (`ppt/slides/slideN.xml`) +2. **Update `[Content_Types].xml`**: Add Override for the new slide +3. **Update `ppt/_rels/presentation.xml.rels`**: Add relationship for the new slide +4. **Update `ppt/presentation.xml`**: Add slide ID to `` +5. **Create slide relationships** (`ppt/slides/_rels/slideN.xml.rels`) if needed +6. **Update `docProps/app.xml`**: Increment slide count and update statistics (if present) + +### Duplicating a Slide +1. Copy the source slide XML file with a new name +2. Update all IDs in the new slide to be unique +3. Follow the "Adding a New Slide" steps above +4. **CRITICAL**: Remove or update any notes slide references in `_rels` files +5. Remove references to unused media files + +### Reordering Slides +1. **Update `ppt/presentation.xml`**: Reorder `` elements in `` +2. The order of `` elements determines slide order +3. Keep slide IDs and relationship IDs unchanged + +Example: +```xml + + + + + + + + + + + + + +``` + +### Deleting a Slide +1. **Remove from `ppt/presentation.xml`**: Delete the `` entry +2. **Remove from `ppt/_rels/presentation.xml.rels`**: Delete the relationship +3. **Remove from `[Content_Types].xml`**: Delete the Override entry +4. **Delete files**: Remove `ppt/slides/slideN.xml` and `ppt/slides/_rels/slideN.xml.rels` +5. **Update `docProps/app.xml`**: Decrement slide count and update statistics +6. **Clean up unused media**: Remove orphaned images from `ppt/media/` + +Note: Don't renumber remaining slides - keep their original IDs and filenames. + + +## Common Errors to Avoid + +- **Encodings**: Escape unicode characters in ASCII content: `"` becomes `“` +- **Images**: Add to `ppt/media/` and update relationship files +- **Lists**: Omit bullets from list headers +- **IDs**: Use valid hexadecimal values for UUIDs +- **Themes**: Check all themes in `theme` directory for colors + +## Validation Checklist for Template-Based Presentations + +### Before Packing, Always: +- **Clean unused resources**: Remove unreferenced media, fonts, and notes directories +- **Fix Content_Types.xml**: Declare ALL slides, layouts, and themes present in the package +- **Fix relationship IDs**: + - Remove font embed references if not using embedded fonts +- **Remove broken references**: Check all `_rels` files for references to deleted resources + +### Common Template Duplication Pitfalls: +- Multiple slides referencing the same notes slide after duplication +- Image/media references from template slides that no longer exist +- Font embedding references when fonts aren't included +- Missing slideLayout declarations for layouts 12-25 +- docProps directory may not unpack - this is optional \ No newline at end of file diff --git a/ooxml/schemas/ISO-IEC29500-4_2016/dml-chart.xsd b/ooxml/schemas/ISO-IEC29500-4_2016/dml-chart.xsd new file mode 100644 index 0000000..6454ef9 --- /dev/null +++ b/ooxml/schemas/ISO-IEC29500-4_2016/dml-chart.xsd @@ -0,0 +1,1499 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/ooxml/schemas/ISO-IEC29500-4_2016/dml-chartDrawing.xsd b/ooxml/schemas/ISO-IEC29500-4_2016/dml-chartDrawing.xsd new file mode 100644 index 0000000..afa4f46 --- /dev/null +++ b/ooxml/schemas/ISO-IEC29500-4_2016/dml-chartDrawing.xsd @@ -0,0 +1,146 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/ooxml/schemas/ISO-IEC29500-4_2016/dml-diagram.xsd b/ooxml/schemas/ISO-IEC29500-4_2016/dml-diagram.xsd new file mode 100644 index 0000000..64e66b8 --- /dev/null +++ b/ooxml/schemas/ISO-IEC29500-4_2016/dml-diagram.xsd @@ -0,0 +1,1085 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/ooxml/schemas/ISO-IEC29500-4_2016/dml-lockedCanvas.xsd b/ooxml/schemas/ISO-IEC29500-4_2016/dml-lockedCanvas.xsd new file mode 100644 index 0000000..687eea8 --- /dev/null +++ b/ooxml/schemas/ISO-IEC29500-4_2016/dml-lockedCanvas.xsd @@ -0,0 +1,11 @@ + + + + + diff --git a/ooxml/schemas/ISO-IEC29500-4_2016/dml-main.xsd b/ooxml/schemas/ISO-IEC29500-4_2016/dml-main.xsd new file mode 100644 index 0000000..6ac81b0 --- /dev/null +++ b/ooxml/schemas/ISO-IEC29500-4_2016/dml-main.xsd @@ -0,0 +1,3081 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/ooxml/schemas/ISO-IEC29500-4_2016/dml-picture.xsd b/ooxml/schemas/ISO-IEC29500-4_2016/dml-picture.xsd new file mode 100644 index 0000000..1dbf051 --- /dev/null +++ b/ooxml/schemas/ISO-IEC29500-4_2016/dml-picture.xsd @@ -0,0 +1,23 @@ + + + + + + + + + + + + + + + + + + diff --git a/ooxml/schemas/ISO-IEC29500-4_2016/dml-spreadsheetDrawing.xsd b/ooxml/schemas/ISO-IEC29500-4_2016/dml-spreadsheetDrawing.xsd new file mode 100644 index 0000000..f1af17d --- /dev/null +++ b/ooxml/schemas/ISO-IEC29500-4_2016/dml-spreadsheetDrawing.xsd @@ -0,0 +1,185 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/ooxml/schemas/ISO-IEC29500-4_2016/dml-wordprocessingDrawing.xsd b/ooxml/schemas/ISO-IEC29500-4_2016/dml-wordprocessingDrawing.xsd new file mode 100644 index 0000000..0a185ab --- /dev/null +++ b/ooxml/schemas/ISO-IEC29500-4_2016/dml-wordprocessingDrawing.xsd @@ -0,0 +1,287 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/ooxml/schemas/ISO-IEC29500-4_2016/pml.xsd b/ooxml/schemas/ISO-IEC29500-4_2016/pml.xsd new file mode 100644 index 0000000..14ef488 --- /dev/null +++ b/ooxml/schemas/ISO-IEC29500-4_2016/pml.xsd @@ -0,0 +1,1676 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/ooxml/schemas/ISO-IEC29500-4_2016/shared-additionalCharacteristics.xsd b/ooxml/schemas/ISO-IEC29500-4_2016/shared-additionalCharacteristics.xsd new file mode 100644 index 0000000..c20f3bf --- /dev/null +++ b/ooxml/schemas/ISO-IEC29500-4_2016/shared-additionalCharacteristics.xsd @@ -0,0 +1,28 @@ + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/ooxml/schemas/ISO-IEC29500-4_2016/shared-bibliography.xsd b/ooxml/schemas/ISO-IEC29500-4_2016/shared-bibliography.xsd new file mode 100644 index 0000000..ac60252 --- /dev/null +++ b/ooxml/schemas/ISO-IEC29500-4_2016/shared-bibliography.xsd @@ -0,0 +1,144 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/ooxml/schemas/ISO-IEC29500-4_2016/shared-commonSimpleTypes.xsd b/ooxml/schemas/ISO-IEC29500-4_2016/shared-commonSimpleTypes.xsd new file mode 100644 index 0000000..424b8ba --- /dev/null +++ b/ooxml/schemas/ISO-IEC29500-4_2016/shared-commonSimpleTypes.xsd @@ -0,0 +1,174 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/ooxml/schemas/ISO-IEC29500-4_2016/shared-customXmlDataProperties.xsd b/ooxml/schemas/ISO-IEC29500-4_2016/shared-customXmlDataProperties.xsd new file mode 100644 index 0000000..2bddce2 --- /dev/null +++ b/ooxml/schemas/ISO-IEC29500-4_2016/shared-customXmlDataProperties.xsd @@ -0,0 +1,25 @@ + + + + + + + + + + + + + + + + + + + diff --git a/ooxml/schemas/ISO-IEC29500-4_2016/shared-customXmlSchemaProperties.xsd b/ooxml/schemas/ISO-IEC29500-4_2016/shared-customXmlSchemaProperties.xsd new file mode 100644 index 0000000..8a8c18b --- /dev/null +++ b/ooxml/schemas/ISO-IEC29500-4_2016/shared-customXmlSchemaProperties.xsd @@ -0,0 +1,18 @@ + + + + + + + + + + + + + + + diff --git a/ooxml/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesCustom.xsd b/ooxml/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesCustom.xsd new file mode 100644 index 0000000..5c42706 --- /dev/null +++ b/ooxml/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesCustom.xsd @@ -0,0 +1,59 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/ooxml/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesExtended.xsd b/ooxml/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesExtended.xsd new file mode 100644 index 0000000..853c341 --- /dev/null +++ b/ooxml/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesExtended.xsd @@ -0,0 +1,56 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/ooxml/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesVariantTypes.xsd b/ooxml/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesVariantTypes.xsd new file mode 100644 index 0000000..da835ee --- /dev/null +++ b/ooxml/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesVariantTypes.xsd @@ -0,0 +1,195 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/ooxml/schemas/ISO-IEC29500-4_2016/shared-math.xsd b/ooxml/schemas/ISO-IEC29500-4_2016/shared-math.xsd new file mode 100644 index 0000000..87ad265 --- /dev/null +++ b/ooxml/schemas/ISO-IEC29500-4_2016/shared-math.xsd @@ -0,0 +1,582 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/ooxml/schemas/ISO-IEC29500-4_2016/shared-relationshipReference.xsd b/ooxml/schemas/ISO-IEC29500-4_2016/shared-relationshipReference.xsd new file mode 100644 index 0000000..9e86f1b --- /dev/null +++ b/ooxml/schemas/ISO-IEC29500-4_2016/shared-relationshipReference.xsd @@ -0,0 +1,25 @@ + + + + + + + + + + + + + + + + + + + + diff --git a/ooxml/schemas/ISO-IEC29500-4_2016/sml.xsd b/ooxml/schemas/ISO-IEC29500-4_2016/sml.xsd new file mode 100644 index 0000000..d0be42e --- /dev/null +++ b/ooxml/schemas/ISO-IEC29500-4_2016/sml.xsd @@ -0,0 +1,4439 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/ooxml/schemas/ISO-IEC29500-4_2016/vml-main.xsd b/ooxml/schemas/ISO-IEC29500-4_2016/vml-main.xsd new file mode 100644 index 0000000..8821dd1 --- /dev/null +++ b/ooxml/schemas/ISO-IEC29500-4_2016/vml-main.xsd @@ -0,0 +1,570 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/ooxml/schemas/ISO-IEC29500-4_2016/vml-officeDrawing.xsd b/ooxml/schemas/ISO-IEC29500-4_2016/vml-officeDrawing.xsd new file mode 100644 index 0000000..ca2575c --- /dev/null +++ b/ooxml/schemas/ISO-IEC29500-4_2016/vml-officeDrawing.xsd @@ -0,0 +1,509 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/ooxml/schemas/ISO-IEC29500-4_2016/vml-presentationDrawing.xsd b/ooxml/schemas/ISO-IEC29500-4_2016/vml-presentationDrawing.xsd new file mode 100644 index 0000000..dd079e6 --- /dev/null +++ b/ooxml/schemas/ISO-IEC29500-4_2016/vml-presentationDrawing.xsd @@ -0,0 +1,12 @@ + + + + + + + + + diff --git a/ooxml/schemas/ISO-IEC29500-4_2016/vml-spreadsheetDrawing.xsd b/ooxml/schemas/ISO-IEC29500-4_2016/vml-spreadsheetDrawing.xsd new file mode 100644 index 0000000..3dd6cf6 --- /dev/null +++ b/ooxml/schemas/ISO-IEC29500-4_2016/vml-spreadsheetDrawing.xsd @@ -0,0 +1,108 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/ooxml/schemas/ISO-IEC29500-4_2016/vml-wordprocessingDrawing.xsd b/ooxml/schemas/ISO-IEC29500-4_2016/vml-wordprocessingDrawing.xsd new file mode 100644 index 0000000..f1041e3 --- /dev/null +++ b/ooxml/schemas/ISO-IEC29500-4_2016/vml-wordprocessingDrawing.xsd @@ -0,0 +1,96 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/ooxml/schemas/ISO-IEC29500-4_2016/wml.xsd b/ooxml/schemas/ISO-IEC29500-4_2016/wml.xsd new file mode 100644 index 0000000..9c5b7a6 --- /dev/null +++ b/ooxml/schemas/ISO-IEC29500-4_2016/wml.xsd @@ -0,0 +1,3646 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/ooxml/schemas/ISO-IEC29500-4_2016/xml.xsd b/ooxml/schemas/ISO-IEC29500-4_2016/xml.xsd new file mode 100644 index 0000000..0f13678 --- /dev/null +++ b/ooxml/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/ooxml/schemas/ecma/fouth-edition/opc-contentTypes.xsd b/ooxml/schemas/ecma/fouth-edition/opc-contentTypes.xsd new file mode 100644 index 0000000..a6de9d2 --- /dev/null +++ b/ooxml/schemas/ecma/fouth-edition/opc-contentTypes.xsd @@ -0,0 +1,42 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/ooxml/schemas/ecma/fouth-edition/opc-coreProperties.xsd b/ooxml/schemas/ecma/fouth-edition/opc-coreProperties.xsd new file mode 100644 index 0000000..10e978b --- /dev/null +++ b/ooxml/schemas/ecma/fouth-edition/opc-coreProperties.xsd @@ -0,0 +1,50 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/ooxml/schemas/ecma/fouth-edition/opc-digSig.xsd b/ooxml/schemas/ecma/fouth-edition/opc-digSig.xsd new file mode 100644 index 0000000..4248bf7 --- /dev/null +++ b/ooxml/schemas/ecma/fouth-edition/opc-digSig.xsd @@ -0,0 +1,49 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/ooxml/schemas/ecma/fouth-edition/opc-relationships.xsd b/ooxml/schemas/ecma/fouth-edition/opc-relationships.xsd new file mode 100644 index 0000000..5649746 --- /dev/null +++ b/ooxml/schemas/ecma/fouth-edition/opc-relationships.xsd @@ -0,0 +1,33 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/ooxml/schemas/mce/mc.xsd b/ooxml/schemas/mce/mc.xsd new file mode 100644 index 0000000..ef72545 --- /dev/null +++ b/ooxml/schemas/mce/mc.xsd @@ -0,0 +1,75 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/ooxml/schemas/microsoft/wml-2010.xsd b/ooxml/schemas/microsoft/wml-2010.xsd new file mode 100644 index 0000000..f65f777 --- /dev/null +++ b/ooxml/schemas/microsoft/wml-2010.xsd @@ -0,0 +1,560 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/ooxml/schemas/microsoft/wml-2012.xsd b/ooxml/schemas/microsoft/wml-2012.xsd new file mode 100644 index 0000000..6b00755 --- /dev/null +++ b/ooxml/schemas/microsoft/wml-2012.xsd @@ -0,0 +1,67 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/ooxml/schemas/microsoft/wml-2018.xsd b/ooxml/schemas/microsoft/wml-2018.xsd new file mode 100644 index 0000000..f321d33 --- /dev/null +++ b/ooxml/schemas/microsoft/wml-2018.xsd @@ -0,0 +1,14 @@ + + + + + + + + + + + + + + diff --git a/ooxml/schemas/microsoft/wml-cex-2018.xsd b/ooxml/schemas/microsoft/wml-cex-2018.xsd new file mode 100644 index 0000000..364c6a9 --- /dev/null +++ b/ooxml/schemas/microsoft/wml-cex-2018.xsd @@ -0,0 +1,20 @@ + + + + + + + + + + + + + + + + + + + + diff --git a/ooxml/schemas/microsoft/wml-cid-2016.xsd b/ooxml/schemas/microsoft/wml-cid-2016.xsd new file mode 100644 index 0000000..fed9d15 --- /dev/null +++ b/ooxml/schemas/microsoft/wml-cid-2016.xsd @@ -0,0 +1,13 @@ + + + + + + + + + + + + + diff --git a/ooxml/schemas/microsoft/wml-sdtdatahash-2020.xsd b/ooxml/schemas/microsoft/wml-sdtdatahash-2020.xsd new file mode 100644 index 0000000..680cf15 --- /dev/null +++ b/ooxml/schemas/microsoft/wml-sdtdatahash-2020.xsd @@ -0,0 +1,4 @@ + + + + diff --git a/ooxml/schemas/microsoft/wml-symex-2015.xsd b/ooxml/schemas/microsoft/wml-symex-2015.xsd new file mode 100644 index 0000000..89ada90 --- /dev/null +++ b/ooxml/schemas/microsoft/wml-symex-2015.xsd @@ -0,0 +1,8 @@ + + + + + + + + diff --git a/ooxml/scripts/pack.py b/ooxml/scripts/pack.py new file mode 100755 index 0000000..68bc088 --- /dev/null +++ b/ooxml/scripts/pack.py @@ -0,0 +1,159 @@ +#!/usr/bin/env python3 +""" +Tool to pack a directory into a .docx, .pptx, or .xlsx file with XML formatting undone. + +Example usage: + python pack.py [--force] +""" + +import argparse +import shutil +import subprocess +import sys +import tempfile +import defusedxml.minidom +import zipfile +from pathlib import Path + + +def main(): + parser = argparse.ArgumentParser(description="Pack a directory into an Office 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("--force", action="store_true", help="Skip validation") + args = parser.parse_args() + + try: + success = pack_document( + args.input_directory, args.output_file, validate=not args.force + ) + + # Show warning if validation was skipped + if args.force: + print("Warning: Skipped validation, file may be corrupt", file=sys.stderr) + # Exit with error if validation failed + elif not success: + print("Contents would produce a corrupt file.", file=sys.stderr) + print("Please validate XML before repacking.", file=sys.stderr) + print("Use --force to skip validation and pack anyway.", file=sys.stderr) + sys.exit(1) + + except ValueError as e: + sys.exit(f"Error: {e}") + + +def pack_document(input_dir, output_file, validate=False): + """Pack a directory into an Office file (.docx/.pptx/.xlsx). + + Args: + input_dir: Path to unpacked Office document directory + output_file: Path to output Office file + validate: If True, validates with soffice (default: False) + + Returns: + bool: True if successful, False if validation failed + """ + input_dir = Path(input_dir) + output_file = Path(output_file) + + if not input_dir.is_dir(): + raise ValueError(f"{input_dir} is not a directory") + if output_file.suffix.lower() not in {".docx", ".pptx", ".xlsx"}: + raise ValueError(f"{output_file} must be a .docx, .pptx, or .xlsx file") + + # Work in temporary directory to avoid modifying original + with tempfile.TemporaryDirectory() as temp_dir: + temp_content_dir = Path(temp_dir) / "content" + shutil.copytree(input_dir, temp_content_dir) + + # Process XML files to remove pretty-printing whitespace + for pattern in ["*.xml", "*.rels"]: + for xml_file in temp_content_dir.rglob(pattern): + condense_xml(xml_file) + + # Create final Office file as zip archive + output_file.parent.mkdir(parents=True, exist_ok=True) + with zipfile.ZipFile(output_file, "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)) + + # Validate if requested + if validate: + if not validate_document(output_file): + output_file.unlink() # Delete the corrupt file + return False + + return True + + +def validate_document(doc_path): + """Validate document by converting to HTML with soffice.""" + # Determine the correct filter based on file extension + match doc_path.suffix.lower(): + case ".docx": + filter_name = "html:HTML" + case ".pptx": + filter_name = "html:impress_html_Export" + case ".xlsx": + filter_name = "html:HTML (StarCalc)" + + with tempfile.TemporaryDirectory() as temp_dir: + try: + result = subprocess.run( + [ + "soffice", + "--headless", + "--convert-to", + filter_name, + "--outdir", + temp_dir, + str(doc_path), + ], + capture_output=True, + timeout=10, + text=True, + ) + if not (Path(temp_dir) / f"{doc_path.stem}.html").exists(): + error_msg = result.stderr.strip() or "Document validation failed" + print(f"Validation error: {error_msg}", file=sys.stderr) + return False + return True + except FileNotFoundError: + print("Warning: soffice not found. Skipping validation.", file=sys.stderr) + return True + except subprocess.TimeoutExpired: + print("Validation error: Timeout during conversion", file=sys.stderr) + return False + except Exception as e: + print(f"Validation error: {e}", file=sys.stderr) + return False + + +def condense_xml(xml_file): + """Strip unnecessary whitespace and remove comments.""" + with open(xml_file, "r", encoding="utf-8") as f: + dom = defusedxml.minidom.parse(f) + + # Process each element to remove whitespace and comments + for element in dom.getElementsByTagName("*"): + # Skip w:t elements and their processing + if element.tagName.endswith(":t"): + continue + + # Remove whitespace-only text nodes and comment nodes + 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) + + # Write back the condensed XML + with open(xml_file, "wb") as f: + f.write(dom.toxml(encoding="UTF-8")) + + +if __name__ == "__main__": + main() diff --git a/ooxml/scripts/unpack.py b/ooxml/scripts/unpack.py new file mode 100755 index 0000000..4938798 --- /dev/null +++ b/ooxml/scripts/unpack.py @@ -0,0 +1,29 @@ +#!/usr/bin/env python3 +"""Unpack and format XML contents of Office files (.docx, .pptx, .xlsx)""" + +import random +import sys +import defusedxml.minidom +import zipfile +from pathlib import Path + +# Get command line arguments +assert len(sys.argv) == 3, "Usage: python unpack.py " +input_file, output_dir = sys.argv[1], sys.argv[2] + +# Extract and format +output_path = Path(output_dir) +output_path.mkdir(parents=True, exist_ok=True) +zipfile.ZipFile(input_file).extractall(output_path) + +# Pretty print all XML files +xml_files = list(output_path.rglob("*.xml")) + list(output_path.rglob("*.rels")) +for xml_file in xml_files: + content = xml_file.read_text(encoding="utf-8") + dom = defusedxml.minidom.parseString(content) + xml_file.write_bytes(dom.toprettyxml(indent=" ", encoding="ascii")) + +# For .docx files, suggest an RSID for tracked changes +if input_file.endswith(".docx"): + suggested_rsid = "".join(random.choices("0123456789ABCDEF", k=8)) + print(f"Suggested RSID for edit session: {suggested_rsid}") diff --git a/ooxml/scripts/validate.py b/ooxml/scripts/validate.py new file mode 100755 index 0000000..508c589 --- /dev/null +++ b/ooxml/scripts/validate.py @@ -0,0 +1,69 @@ +#!/usr/bin/env python3 +""" +Command line tool to validate Office document XML files against XSD schemas and tracked changes. + +Usage: + python validate.py --original +""" + +import argparse +import sys +from pathlib import Path + +from validation import DOCXSchemaValidator, PPTXSchemaValidator, RedliningValidator + + +def main(): + parser = argparse.ArgumentParser(description="Validate Office document XML files") + parser.add_argument( + "unpacked_dir", + help="Path to unpacked Office document directory", + ) + parser.add_argument( + "--original", + required=True, + help="Path to original file (.docx/.pptx/.xlsx)", + ) + parser.add_argument( + "-v", + "--verbose", + action="store_true", + help="Enable verbose output", + ) + args = parser.parse_args() + + # Validate paths + unpacked_dir = Path(args.unpacked_dir) + original_file = Path(args.original) + file_extension = original_file.suffix.lower() + assert unpacked_dir.is_dir(), f"Error: {unpacked_dir} is not a directory" + assert original_file.is_file(), f"Error: {original_file} is not a file" + assert file_extension in [".docx", ".pptx", ".xlsx"], ( + f"Error: {original_file} must be a .docx, .pptx, or .xlsx file" + ) + + # Run validations + match file_extension: + case ".docx": + validators = [DOCXSchemaValidator, RedliningValidator] + case ".pptx": + validators = [PPTXSchemaValidator] + case _: + print(f"Error: Validation not supported for file type {file_extension}") + sys.exit(1) + + # Run validators + success = True + for V in validators: + validator = V(unpacked_dir, original_file, verbose=args.verbose) + if not validator.validate(): + success = False + + if success: + print("All validations PASSED!") + + sys.exit(0 if success else 1) + + +if __name__ == "__main__": + main() diff --git a/ooxml/scripts/validation/__init__.py b/ooxml/scripts/validation/__init__.py new file mode 100644 index 0000000..db092ec --- /dev/null +++ b/ooxml/scripts/validation/__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/ooxml/scripts/validation/base.py b/ooxml/scripts/validation/base.py new file mode 100644 index 0000000..0681b19 --- /dev/null +++ b/ooxml/scripts/validation/base.py @@ -0,0 +1,951 @@ +""" +Base validator with common validation logic for document files. +""" + +import re +from pathlib import Path + +import lxml.etree + + +class BaseSchemaValidator: + """Base validator with common validation logic for document files.""" + + # Elements whose 'id' attributes must be unique within their file + # Format: element_name -> (attribute_name, scope) + # scope can be 'file' (unique within file) or 'global' (unique across all files) + UNIQUE_ID_REQUIREMENTS = { + # Word elements + "comment": ("id", "file"), # Comment IDs in comments.xml + "commentrangestart": ("id", "file"), # Must match comment IDs + "commentrangeend": ("id", "file"), # Must match comment IDs + "bookmarkstart": ("id", "file"), # Bookmark start IDs + "bookmarkend": ("id", "file"), # Bookmark end IDs + # Note: ins and del (track changes) can share IDs when part of same revision + # PowerPoint elements + "sldid": ("id", "file"), # Slide IDs in presentation.xml + "sldmasterid": ("id", "global"), # Slide master IDs must be globally unique + "sldlayoutid": ("id", "global"), # Slide layout IDs must be globally unique + "cm": ("authorid", "file"), # Comment author IDs + # Excel elements + "sheet": ("sheetid", "file"), # Sheet IDs in workbook.xml + "definedname": ("id", "file"), # Named range IDs + # Drawing/Shape elements (all formats) + "cxnsp": ("id", "file"), # Connection shape IDs + "sp": ("id", "file"), # Shape IDs + "pic": ("id", "file"), # Picture IDs + "grpsp": ("id", "file"), # Group shape IDs + } + + # Mapping of element names to expected relationship types + # Subclasses should override this with format-specific mappings + ELEMENT_RELATIONSHIP_TYPES = {} + + # Unified schema mappings for all Office document types + SCHEMA_MAPPINGS = { + # Document type specific schemas + "word": "ISO-IEC29500-4_2016/wml.xsd", # Word documents + "ppt": "ISO-IEC29500-4_2016/pml.xsd", # PowerPoint presentations + "xl": "ISO-IEC29500-4_2016/sml.xsd", # Excel spreadsheets + # Common file types + "[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", + # Word-specific files + "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 files (common across document types) + "chart": "ISO-IEC29500-4_2016/dml-chart.xsd", + # Theme files (common across document types) + "theme": "ISO-IEC29500-4_2016/dml-main.xsd", + # Drawing and media files + "drawing": "ISO-IEC29500-4_2016/dml-main.xsd", + } + + # Unified namespace constants + MC_NAMESPACE = "http://schemas.openxmlformats.org/markup-compatibility/2006" + XML_NAMESPACE = "http://www.w3.org/XML/1998/namespace" + + # Common OOXML namespaces used across validators + 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" + ) + + # Folders where we should clean ignorable namespaces + MAIN_CONTENT_FOLDERS = {"word", "ppt", "xl"} + + # All allowed OOXML namespaces (superset of all document types) + 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, verbose=False): + self.unpacked_dir = Path(unpacked_dir).resolve() + self.original_file = Path(original_file) + self.verbose = verbose + + # Set schemas directory + self.schemas_dir = Path(__file__).parent.parent.parent / "schemas" + + # Get all XML and .rels files + 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): + """Run all validation checks and return True if all pass.""" + raise NotImplementedError("Subclasses must implement the validate method") + + def validate_xml(self): + """Validate that all XML files are well-formed.""" + errors = [] + + for xml_file in self.xml_files: + try: + # Try to parse the XML file + 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): + """Validate that namespace prefixes in Ignorable attributes are declared.""" + errors = [] + + for xml_file in self.xml_files: + try: + root = lxml.etree.parse(str(xml_file)).getroot() + declared = set(root.nsmap.keys()) - {None} # Exclude default namespace + + 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): + """Validate that specific IDs are unique according to OOXML requirements.""" + errors = [] + global_ids = {} # Track globally unique IDs across all files + + for xml_file in self.xml_files: + try: + root = lxml.etree.parse(str(xml_file)).getroot() + file_ids = {} # Track IDs that must be unique within this file + + # Remove all mc:AlternateContent elements from the tree + mc_elements = root.xpath( + ".//mc:AlternateContent", namespaces={"mc": self.MC_NAMESPACE} + ) + for elem in mc_elements: + elem.getparent().remove(elem) + + # Now check IDs in the cleaned tree + for elem in root.iter(): + # Get the element name without namespace + tag = ( + elem.tag.split("}")[-1].lower() + if "}" in elem.tag + else elem.tag.lower() + ) + + # Check if this element type has ID uniqueness requirements + if tag in self.UNIQUE_ID_REQUIREMENTS: + attr_name, scope = self.UNIQUE_ID_REQUIREMENTS[tag] + + # Look for the specified attribute + 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": + # Check global uniqueness + 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": + # Check file-level uniqueness + 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): + """ + Validate that all .rels files properly reference files and that all files are referenced. + """ + errors = [] + + # Find all .rels files + rels_files = list(self.unpacked_dir.rglob("*.rels")) + + if not rels_files: + if self.verbose: + print("PASSED - No .rels files found") + return True + + # Get all files in the unpacked directory (excluding reference files) + 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") + ): # This file is not referenced by .rels + all_files.append(file_path.resolve()) + + # Track all files that are referenced by any .rels file + all_referenced_files = set() + + if self.verbose: + print( + f"Found {len(rels_files)} .rels files and {len(all_files)} target files" + ) + + # Check each .rels file + for rels_file in rels_files: + try: + # Parse relationships file + rels_root = lxml.etree.parse(str(rels_file)).getroot() + + # Get the directory where this .rels file is located + rels_dir = rels_file.parent + + # Find all relationships and their targets + 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:") + ): # Skip external URLs + # Resolve the target path relative to the .rels file location + if rels_file.name == ".rels": + # Root .rels file - targets are relative to unpacked_dir + target_path = self.unpacked_dir / target + else: + # Other .rels files - targets are relative to their parent's parent + # e.g., word/_rels/document.xml.rels -> targets relative to word/ + base_dir = rels_dir.parent + target_path = base_dir / target + + # Normalize the path and check if it exists + 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)) + + # Report broken references + 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}") + + # Check for unreferenced files (files that exist but are not referenced anywhere) + 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): + """ + Validate that all r:id attributes in XML files reference existing IDs + in their corresponding .rels files, and optionally validate relationship types. + """ + import lxml.etree + + errors = [] + + # Process each XML file that might contain r:id references + for xml_file in self.xml_files: + # Skip .rels files themselves + if xml_file.suffix == ".rels": + continue + + # Determine the corresponding .rels file + # For dir/file.xml, it's dir/_rels/file.xml.rels + rels_dir = xml_file.parent / "_rels" + rels_file = rels_dir / f"{xml_file.name}.rels" + + # Skip if there's no corresponding .rels file (that's okay) + if not rels_file.exists(): + continue + + try: + # Parse the .rels file to get valid relationship IDs and their types + 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: + # Check for duplicate rIds + 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)" + ) + # Extract just the type name from the full URL + type_name = ( + rel_type.split("/")[-1] if "/" in rel_type else rel_type + ) + rid_to_type[rid] = type_name + + # Parse the XML file to find all r:id references + xml_root = lxml.etree.parse(str(xml_file)).getroot() + + # Find all elements with r:id attributes + for elem in xml_root.iter(): + # Check for r:id attribute (relationship ID) + rid_attr = elem.get(f"{{{self.OFFICE_RELATIONSHIPS_NAMESPACE}}}id") + if rid_attr: + xml_rel_path = xml_file.relative_to(self.unpacked_dir) + elem_name = ( + elem.tag.split("}")[-1] if "}" in elem.tag else elem.tag + ) + + # Check if the ID exists + if rid_attr not in rid_to_type: + errors.append( + f" {xml_rel_path}: Line {elem.sourceline}: " + f"<{elem_name}> references non-existent relationship '{rid_attr}' " + f"(valid IDs: {', '.join(sorted(rid_to_type.keys())[:5])}{'...' if len(rid_to_type) > 5 else ''})" + ) + # Check if we have type expectations for this element + elif self.ELEMENT_RELATIONSHIP_TYPES: + expected_type = self._get_expected_relationship_type( + elem_name + ) + if expected_type: + actual_type = rid_to_type[rid_attr] + # Check if the actual type matches or contains the expected type + 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): + """ + Get the expected relationship type for an element. + First checks the explicit mapping, then tries pattern detection. + """ + # Normalize element name to lowercase + elem_lower = element_name.lower() + + # Check explicit mapping first + if elem_lower in self.ELEMENT_RELATIONSHIP_TYPES: + return self.ELEMENT_RELATIONSHIP_TYPES[elem_lower] + + # Try pattern detection for common patterns + # Pattern 1: Elements ending in "Id" often expect a relationship of the prefix type + if elem_lower.endswith("id") and len(elem_lower) > 2: + # e.g., "sldId" -> "sld", "sldMasterId" -> "sldMaster" + prefix = elem_lower[:-2] # Remove "id" + # Check if this might be a compound like "sldMasterId" + if prefix.endswith("master"): + return prefix.lower() + elif prefix.endswith("layout"): + return prefix.lower() + else: + # Simple case like "sldId" -> "slide" + # Common transformations + if prefix == "sld": + return "slide" + return prefix.lower() + + # Pattern 2: Elements ending in "Reference" expect a relationship of the prefix type + if elem_lower.endswith("reference") and len(elem_lower) > 9: + prefix = elem_lower[:-9] # Remove "reference" + return prefix.lower() + + return None + + def validate_content_types(self): + """Validate that all content files are properly declared in [Content_Types].xml.""" + errors = [] + + # Find [Content_Types].xml file + 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: + # Parse and get all declared parts and extensions + root = lxml.etree.parse(str(content_types_file)).getroot() + declared_parts = set() + declared_extensions = set() + + # Get Override declarations (specific files) + 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("/")) + + # Get Default declarations (by extension) + 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()) + + # Root elements that require content type declaration + declarable_roots = { + "sld", + "sldLayout", + "sldMaster", + "presentation", # PowerPoint + "document", # Word + "workbook", + "worksheet", # Excel + "theme", # Common + } + + # Common media file extensions that should be declared + 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", + } + + # Get all files in the unpacked directory + all_files = list(self.unpacked_dir.rglob("*")) + all_files = [f for f in all_files if f.is_file()] + + # Check all XML files for Override declarations + for xml_file in self.xml_files: + path_str = str(xml_file.relative_to(self.unpacked_dir)).replace( + "\\", "/" + ) + + # Skip non-content files + 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 # Skip unparseable files + + # Check all non-XML files for Default extension declarations + for file_path in all_files: + # Skip XML files and metadata files (already checked above) + 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: + # Check if it's a known media extension that should be declared + 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): + """Validate a single XML file against XSD schema, comparing with original. + + Args: + xml_file: Path to XML file to validate + verbose: Enable verbose output + + Returns: + tuple: (is_valid, new_errors_set) where is_valid is True/False/None (skipped) + """ + # Resolve both paths to handle symlinks + xml_file = Path(xml_file).resolve() + unpacked_dir = self.unpacked_dir.resolve() + + # Validate current file + is_valid, current_errors = self._validate_single_file_xsd( + xml_file, unpacked_dir + ) + + if is_valid is None: + return None, set() # Skipped + elif is_valid: + return True, set() # Valid, no errors + + # Get errors from original file for this specific file + original_errors = self._get_original_file_errors(xml_file) + + # Compare with original (both are guaranteed to be sets here) + assert current_errors is not None + new_errors = current_errors - original_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: + # All errors existed in original + if verbose: + print( + f"PASSED - No new errors (original had {len(current_errors)} errors)" + ) + return True, set() + + def validate_against_xsd(self): + """Validate XML files against XSD schemas, showing only new errors compared to original.""" + 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: + # Had errors but all existed in original + original_error_count += 1 + valid_count += 1 + continue + + # Has new errors + new_errors.append(f" {relative_path}: {len(new_file_errors)} new error(s)") + for error in list(new_file_errors)[:3]: # Show first 3 errors + new_errors.append( + f" - {error[:250]}..." if len(error) > 250 else f" - {error}" + ) + + # Print summary + 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): + """Determine the appropriate schema path for an XML file.""" + # Check exact filename match + if xml_file.name in self.SCHEMA_MAPPINGS: + return self.schemas_dir / self.SCHEMA_MAPPINGS[xml_file.name] + + # Check .rels files + if xml_file.suffix == ".rels": + return self.schemas_dir / self.SCHEMA_MAPPINGS[".rels"] + + # Check chart files + if "charts/" in str(xml_file) and xml_file.name.startswith("chart"): + return self.schemas_dir / self.SCHEMA_MAPPINGS["chart"] + + # Check theme files + if "theme/" in str(xml_file) and xml_file.name.startswith("theme"): + return self.schemas_dir / self.SCHEMA_MAPPINGS["theme"] + + # Check if file is in a main content folder and use appropriate schema + 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): + """Remove attributes and elements not in allowed namespaces.""" + # Create a clean copy + xml_string = lxml.etree.tostring(xml_doc, encoding="unicode") + xml_copy = lxml.etree.fromstring(xml_string) + + # Remove attributes not in allowed namespaces + for elem in xml_copy.iter(): + attrs_to_remove = [] + + for attr in elem.attrib: + # Check if attribute is from a namespace other than allowed ones + if "{" in attr: + ns = attr.split("}")[0][1:] + if ns not in self.OOXML_NAMESPACES: + attrs_to_remove.append(attr) + + # Remove collected attributes + for attr in attrs_to_remove: + del elem.attrib[attr] + + # Remove elements not in allowed namespaces + self._remove_ignorable_elements(xml_copy) + + return lxml.etree.ElementTree(xml_copy) + + def _remove_ignorable_elements(self, root): + """Recursively remove all elements not in allowed namespaces.""" + elements_to_remove = [] + + # Find elements to remove + for elem in list(root): + # Skip non-element nodes (comments, processing instructions, etc.) + 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 + + # Recursively clean child elements + self._remove_ignorable_elements(elem) + + # Remove collected elements + for elem in elements_to_remove: + root.remove(elem) + + def _preprocess_for_mc_ignorable(self, xml_doc): + """Preprocess XML to handle mc:Ignorable attribute properly.""" + # Remove mc:Ignorable attributes before validation + root = xml_doc.getroot() + + # Remove mc:Ignorable attribute from root + 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): + """Validate a single XML file against XSD schema. Returns (is_valid, errors_set).""" + schema_path = self._get_schema_path(xml_file) + if not schema_path: + return None, None # Skip file + + try: + # Load schema + 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) + + # Load and preprocess XML + 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) + + # Clean ignorable namespaces if needed + 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) + + # Validate + if schema.validate(xml_doc): + return True, set() + else: + errors = set() + for error in schema.error_log: + # Store normalized error message (without line numbers for comparison) + errors.add(error.message) + return False, errors + + except Exception as e: + return False, {str(e)} + + def _get_original_file_errors(self, xml_file): + """Get XSD validation errors from a single file in the original document. + + Args: + xml_file: Path to the XML file in unpacked_dir to check + + Returns: + set: Set of error messages from the original file + """ + import tempfile + import zipfile + + # Resolve both paths to handle symlinks (e.g., /var vs /private/var on macOS) + 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) + + # Extract original file + with zipfile.ZipFile(self.original_file, "r") as zip_ref: + zip_ref.extractall(temp_path) + + # Find corresponding file in original + original_xml_file = temp_path / relative_path + + if not original_xml_file.exists(): + # File didn't exist in original, so no original errors + return set() + + # Validate the specific file in original + 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): + """Remove template tags from XML text nodes and collect warnings. + + Template tags follow the pattern {{ ... }} and are used as placeholders + for content replacement. They should be removed from text content before + XSD validation while preserving XML structure. + + Returns: + tuple: (cleaned_xml_doc, warnings_list) + """ + warnings = [] + template_pattern = re.compile(r"\{\{[^}]*\}\}") + + # Create a copy of the document to avoid modifying the original + 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 + + # Process all text nodes in the document + for elem in xml_copy.iter(): + # Skip processing if this is a w:t element + 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/ooxml/scripts/validation/docx.py b/ooxml/scripts/validation/docx.py new file mode 100644 index 0000000..602c470 --- /dev/null +++ b/ooxml/scripts/validation/docx.py @@ -0,0 +1,274 @@ +""" +Validator for Word document XML files against XSD schemas. +""" + +import re +import tempfile +import zipfile + +import lxml.etree + +from .base import BaseSchemaValidator + + +class DOCXSchemaValidator(BaseSchemaValidator): + """Validator for Word document XML files against XSD schemas.""" + + # Word-specific namespace + WORD_2006_NAMESPACE = "http://schemas.openxmlformats.org/wordprocessingml/2006/main" + + # Word-specific element to relationship type mappings + # Start with empty mapping - add specific cases as we discover them + ELEMENT_RELATIONSHIP_TYPES = {} + + def validate(self): + """Run all validation checks and return True if all pass.""" + # Test 0: XML well-formedness + if not self.validate_xml(): + return False + + # Test 1: Namespace declarations + all_valid = True + if not self.validate_namespaces(): + all_valid = False + + # Test 2: Unique IDs + if not self.validate_unique_ids(): + all_valid = False + + # Test 3: Relationship and file reference validation + if not self.validate_file_references(): + all_valid = False + + # Test 4: Content type declarations + if not self.validate_content_types(): + all_valid = False + + # Test 5: XSD schema validation + if not self.validate_against_xsd(): + all_valid = False + + # Test 6: Whitespace preservation + if not self.validate_whitespace_preservation(): + all_valid = False + + # Test 7: Deletion validation + if not self.validate_deletions(): + all_valid = False + + # Test 8: Insertion validation + if not self.validate_insertions(): + all_valid = False + + # Test 9: Relationship ID reference validation + if not self.validate_all_relationship_ids(): + all_valid = False + + # Count and compare paragraphs + self.compare_paragraph_counts() + + return all_valid + + def validate_whitespace_preservation(self): + """ + Validate that w:t elements with whitespace have xml:space='preserve'. + """ + errors = [] + + for xml_file in self.xml_files: + # Only check document.xml files + if xml_file.name != "document.xml": + continue + + try: + root = lxml.etree.parse(str(xml_file)).getroot() + + # Find all w:t elements + for elem in root.iter(f"{{{self.WORD_2006_NAMESPACE}}}t"): + if elem.text: + text = elem.text + # Check if text starts or ends with whitespace + if re.match(r"^\s.*", text) or re.match(r".*\s$", text): + # Check if xml:space="preserve" attribute exists + xml_space_attr = f"{{{self.XML_NAMESPACE}}}space" + if ( + xml_space_attr not in elem.attrib + or elem.attrib[xml_space_attr] != "preserve" + ): + # Show a preview of the text + 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): + """ + Validate that w:t elements are not within w:del elements. + For some reason, XSD validation does not catch this, so we do it manually. + """ + errors = [] + + for xml_file in self.xml_files: + # Only check document.xml files + if xml_file.name != "document.xml": + continue + + try: + root = lxml.etree.parse(str(xml_file)).getroot() + + # Find all w:t elements that are descendants of w:del elements + namespaces = {"w": self.WORD_2006_NAMESPACE} + xpath_expression = ".//w:del//w:t" + problematic_t_elements = root.xpath( + xpath_expression, namespaces=namespaces + ) + for t_elem in problematic_t_elements: + if t_elem.text: + # Show a preview of the 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}" + ) + + 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 the number of paragraphs in the unpacked document.""" + count = 0 + + for xml_file in self.xml_files: + # Only check document.xml files + if xml_file.name != "document.xml": + continue + + try: + root = lxml.etree.parse(str(xml_file)).getroot() + # Count all w:p elements + 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): + """Count the number of paragraphs in the original docx file.""" + count = 0 + + try: + # Create temporary directory to unpack original + with tempfile.TemporaryDirectory() as temp_dir: + # Unpack original docx + with zipfile.ZipFile(self.original_file, "r") as zip_ref: + zip_ref.extractall(temp_dir) + + # Parse document.xml + doc_xml_path = temp_dir + "/word/document.xml" + root = lxml.etree.parse(doc_xml_path).getroot() + + # Count all w:p elements + 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): + """ + Validate that w:delText elements are not within w:ins elements. + w:delText is only allowed in w:ins if nested within a w:del. + """ + 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} + + # Find w:delText in w:ins that are NOT within w:del + 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): + """Compare paragraph counts between original and new document.""" + 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})") + + +if __name__ == "__main__": + raise RuntimeError("This module should not be run directly.") diff --git a/ooxml/scripts/validation/pptx.py b/ooxml/scripts/validation/pptx.py new file mode 100644 index 0000000..66d5b1e --- /dev/null +++ b/ooxml/scripts/validation/pptx.py @@ -0,0 +1,315 @@ +""" +Validator for PowerPoint presentation XML files against XSD schemas. +""" + +import re + +from .base import BaseSchemaValidator + + +class PPTXSchemaValidator(BaseSchemaValidator): + """Validator for PowerPoint presentation XML files against XSD schemas.""" + + # PowerPoint presentation namespace + PRESENTATIONML_NAMESPACE = ( + "http://schemas.openxmlformats.org/presentationml/2006/main" + ) + + # PowerPoint-specific element to relationship type mappings + ELEMENT_RELATIONSHIP_TYPES = { + "sldid": "slide", + "sldmasterid": "slidemaster", + "notesmasterid": "notesmaster", + "sldlayoutid": "slidelayout", + "themeid": "theme", + "tablestyleid": "tablestyles", + } + + def validate(self): + """Run all validation checks and return True if all pass.""" + # Test 0: XML well-formedness + if not self.validate_xml(): + return False + + # Test 1: Namespace declarations + all_valid = True + if not self.validate_namespaces(): + all_valid = False + + # Test 2: Unique IDs + if not self.validate_unique_ids(): + all_valid = False + + # Test 3: UUID ID validation + if not self.validate_uuid_ids(): + all_valid = False + + # Test 4: Relationship and file reference validation + if not self.validate_file_references(): + all_valid = False + + # Test 5: Slide layout ID validation + if not self.validate_slide_layout_ids(): + all_valid = False + + # Test 6: Content type declarations + if not self.validate_content_types(): + all_valid = False + + # Test 7: XSD schema validation + if not self.validate_against_xsd(): + all_valid = False + + # Test 8: Notes slide reference validation + if not self.validate_notes_slide_references(): + all_valid = False + + # Test 9: Relationship ID reference validation + if not self.validate_all_relationship_ids(): + all_valid = False + + # Test 10: Duplicate slide layout references validation + if not self.validate_no_duplicate_slide_layouts(): + all_valid = False + + return all_valid + + def validate_uuid_ids(self): + """Validate that ID attributes that look like UUIDs contain only hex values.""" + import lxml.etree + + errors = [] + # UUID pattern: 8-4-4-4-12 hex digits with optional braces/hyphens + 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() + + # Check all elements for ID attributes + for elem in root.iter(): + for attr, value in elem.attrib.items(): + # Check if this is an ID attribute + attr_name = attr.split("}")[-1].lower() + if attr_name == "id" or attr_name.endswith("id"): + # Check if value looks like a UUID (has the right length and pattern structure) + if self._looks_like_uuid(value): + # Validate that it contains only hex characters in the right positions + 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): + """Check if a value has the general structure of a UUID.""" + # Remove common UUID delimiters + clean_value = value.strip("{}()").replace("-", "") + # Check if it's 32 hex-like characters (could include invalid hex chars) + return len(clean_value) == 32 and all(c.isalnum() for c in clean_value) + + def validate_slide_layout_ids(self): + """Validate that sldLayoutId elements in slide masters reference valid slide layouts.""" + import lxml.etree + + errors = [] + + # Find all slide master files + 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: + # Parse the slide master file + root = lxml.etree.parse(str(slide_master)).getroot() + + # Find the corresponding _rels file for this slide master + 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 + + # Parse the relationships file + rels_root = lxml.etree.parse(str(rels_file)).getroot() + + # Build a set of valid relationship IDs that point to slide layouts + 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")) + + # Find all sldLayoutId elements in the slide master + 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): + """Validate that each slide has exactly one slideLayout reference.""" + 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() + + # Find all slideLayout relationships + 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): + """Validate that each notesSlide file is referenced by only one slide.""" + import lxml.etree + + errors = [] + notes_slide_references = {} # Track which slides reference each notesSlide + + # Find all slide relationship files + 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: + # Parse the relationships file + root = lxml.etree.parse(str(rels_file)).getroot() + + # Find all notesSlide relationships + 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: + # Normalize the target path to handle relative paths + normalized_target = target.replace("../", "") + + # Track which slide references this notesSlide + slide_name = rels_file.stem.replace( + ".xml", "" + ) # e.g., "slide1" + + 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}" + ) + + # Check for duplicate references + 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/ooxml/scripts/validation/redlining.py b/ooxml/scripts/validation/redlining.py new file mode 100644 index 0000000..7ed425e --- /dev/null +++ b/ooxml/scripts/validation/redlining.py @@ -0,0 +1,279 @@ +""" +Validator for tracked changes in Word documents. +""" + +import subprocess +import tempfile +import zipfile +from pathlib import Path + + +class RedliningValidator: + """Validator for tracked changes in Word documents.""" + + def __init__(self, unpacked_dir, original_docx, verbose=False): + self.unpacked_dir = Path(unpacked_dir) + self.original_docx = Path(original_docx) + self.verbose = verbose + self.namespaces = { + "w": "http://schemas.openxmlformats.org/wordprocessingml/2006/main" + } + + def validate(self): + """Main validation method that returns True if valid, False otherwise.""" + # Verify unpacked directory exists and has correct structure + 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 + + # First, check if there are any tracked changes by Claude to validate + try: + import xml.etree.ElementTree as ET + + tree = ET.parse(modified_file) + root = tree.getroot() + + # Check for w:del or w:ins tags authored by Claude + del_elements = root.findall(".//w:del", self.namespaces) + ins_elements = root.findall(".//w:ins", self.namespaces) + + # Filter to only include changes by Claude + claude_del_elements = [ + elem + for elem in del_elements + if elem.get(f"{{{self.namespaces['w']}}}author") == "Claude" + ] + claude_ins_elements = [ + elem + for elem in ins_elements + if elem.get(f"{{{self.namespaces['w']}}}author") == "Claude" + ] + + # Redlining validation is only needed if tracked changes by Claude have been used. + if not claude_del_elements and not claude_ins_elements: + if self.verbose: + print("PASSED - No tracked changes by Claude found.") + return True + + except Exception: + # If we can't parse the XML, continue with full validation + pass + + # Create temporary directory for unpacking original docx + with tempfile.TemporaryDirectory() as temp_dir: + temp_path = Path(temp_dir) + + # Unpack original docx + 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 + + # Parse both XML files using xml.etree.ElementTree for redlining validation + 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 + + # Remove Claude's tracked changes from both documents + self._remove_claude_tracked_changes(original_root) + self._remove_claude_tracked_changes(modified_root) + + # Extract and compare text content + modified_text = self._extract_text_content(modified_root) + original_text = self._extract_text_content(original_root) + + if modified_text != original_text: + # Show detailed character-level differences for each paragraph + error_message = self._generate_detailed_diff( + original_text, modified_text + ) + print(error_message) + return False + + if self.verbose: + print("PASSED - All changes by Claude are properly tracked") + return True + + def _generate_detailed_diff(self, original_text, modified_text): + """Generate detailed word-level differences using git word diff.""" + error_parts = [ + "FAILED - Document text doesn't match after removing Claude'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 ", + "", + ] + + # Show git word diff + 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): + """Generate word diff using git with character-level precision.""" + try: + with tempfile.TemporaryDirectory() as temp_dir: + temp_path = Path(temp_dir) + + # Create two files + 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") + + # Try character-level diff first for precise differences + result = subprocess.run( + [ + "git", + "diff", + "--word-diff=plain", + "--word-diff-regex=.", # Character-by-character diff + "-U0", # Zero lines of context - show only changed lines + "--no-index", + str(original_file), + str(modified_file), + ], + capture_output=True, + text=True, + ) + + if result.stdout.strip(): + # Clean up the output - remove git diff header lines + lines = result.stdout.split("\n") + # Skip the header lines (diff --git, index, +++, ---, @@) + 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) + + # Fallback to word-level diff if character-level is too verbose + result = subprocess.run( + [ + "git", + "diff", + "--word-diff=plain", + "-U0", # Zero lines of context + "--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): + # Git not available or other error, return None to use fallback + pass + + return None + + def _remove_claude_tracked_changes(self, root): + """Remove tracked changes authored by Claude from the XML root.""" + ins_tag = f"{{{self.namespaces['w']}}}ins" + del_tag = f"{{{self.namespaces['w']}}}del" + author_attr = f"{{{self.namespaces['w']}}}author" + + # Remove w:ins elements + for parent in root.iter(): + to_remove = [] + for child in parent: + if child.tag == ins_tag and child.get(author_attr) == "Claude": + to_remove.append(child) + for elem in to_remove: + parent.remove(elem) + + # Unwrap content in w:del elements where author is "Claude" + 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) == "Claude": + to_process.append((child, list(parent).index(child))) + + # Process in reverse order to maintain indices + for del_elem, del_index in reversed(to_process): + # Convert w:delText to w:t before moving + for elem in del_elem.iter(): + if elem.tag == deltext_tag: + elem.tag = t_tag + + # Move all children of w:del to its parent before removing w:del + for child in reversed(list(del_elem)): + parent.insert(del_index, child) + parent.remove(del_elem) + + def _extract_text_content(self, root): + """Extract text content from Word XML, preserving paragraph structure. + + Empty paragraphs are skipped to avoid false positives when tracked + insertions add only structural elements without text content. + """ + p_tag = f"{{{self.namespaces['w']}}}p" + t_tag = f"{{{self.namespaces['w']}}}t" + + paragraphs = [] + for p_elem in root.findall(f".//{p_tag}"): + # Get all text elements within this paragraph + 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) + # Skip empty paragraphs - they don't affect content validation + 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/plugin.lock.json b/plugin.lock.json new file mode 100644 index 0000000..46013a4 --- /dev/null +++ b/plugin.lock.json @@ -0,0 +1,265 @@ +{ + "$schema": "internal://schemas/plugin.lock.v1.json", + "pluginId": "gh:ComposioHQ/awesome-claude-skills:document-skills/pptx", + "normalized": { + "repo": null, + "ref": "refs/tags/v20251128.0", + "commit": "63100e87bc58d506b18d9f9958fef2457a3ac044", + "treeHash": "e173fa0dea199d8acfc9c4c90bdedd7b7d02c412168b64ea47b347423fb075b1", + "generatedAt": "2025-11-28T10:10:08.999546Z", + "toolVersion": "publish_plugins.py@0.2.0" + }, + "origin": { + "remote": "git@github.com:zhongweili/42plugin-data.git", + "branch": "master", + "commit": "aa1497ed0949fd50e99e70d6324a29c5b34f9390", + "repoRoot": "/Users/zhongweili/projects/openmind/42plugin-data" + }, + "manifest": { + "name": "document-skills-pptx", + "description": "Skills for working with PowerPoint presentations including creation, editing, and formatting using PPTX format.", + "version": null + }, + "content": { + "files": [ + { + "path": "ooxml.md", + "sha256": "09868e9f1786765421ecf3f0f49c77006738efda82a76df43ed87f7a9bfe2467" + }, + { + "path": "README.md", + "sha256": "a55abc7629a29be9d05f6f09b961ad1a7b807c055060611ea22ee9ab28d294b7" + }, + { + "path": "SKILL.md", + "sha256": "b6f25545bfb358739f1532f793458b5dbc87ee009933cb7c306b2d951ab6617f" + }, + { + "path": "html2pptx.md", + "sha256": "f08ed7580969b796d9cd5ade93e2cdee981dcaf13cc5eb12e8d4a3700c2d6047" + }, + { + "path": "LICENSE.txt", + "sha256": "79f6d8f5b427252fa3b1c11ecdbdb6bf610b944f7530b4de78f770f38741cfaa" + }, + { + "path": "ooxml/schemas/microsoft/wml-sdtdatahash-2020.xsd", + "sha256": "842e7163409c8d74f4d7088a8bc99500d80bc75332681a0980055b08f374a604" + }, + { + "path": "ooxml/schemas/microsoft/wml-2012.xsd", + "sha256": "0fa75578a000439a7988ba0c59fdc69f774bbd416cbacc14d07125b3f686cb74" + }, + { + "path": "ooxml/schemas/microsoft/wml-2010.xsd", + "sha256": "568b26ee156cb9549aa439ca2158965f77b7c1602b7e0316f40ac6cf586e35f2" + }, + { + "path": "ooxml/schemas/microsoft/wml-cid-2016.xsd", + "sha256": "127ca209fa73d7cb708449cb355c871867948a96e4a74f7bf5811ef62d17991d" + }, + { + "path": "ooxml/schemas/microsoft/wml-symex-2015.xsd", + "sha256": "16f6f8072249f431370723c2cd8974672e0d9c897e00e97dd918079df934871b" + }, + { + "path": "ooxml/schemas/microsoft/wml-cex-2018.xsd", + "sha256": "fddc2b880cabb9005aebbc7e783e53c19fec1c03df7d0e2f2076a33a0fdfd081" + }, + { + "path": "ooxml/schemas/microsoft/wml-2018.xsd", + "sha256": "be0ff793a22dd31384650c3a4da14c2fa8062751c2e97b0e5ee852bda13c60ad" + }, + { + "path": "ooxml/schemas/mce/mc.xsd", + "sha256": "3a37e461ecf5a8670fdec34029703401f8728ab9c96ec1739a6ae58d55212413" + }, + { + "path": "ooxml/schemas/ecma/fouth-edition/opc-coreProperties.xsd", + "sha256": "451958454e8588dfc7cd945981ada142ca06ff3307937f5700df059c2b307fa8" + }, + { + "path": "ooxml/schemas/ecma/fouth-edition/opc-relationships.xsd", + "sha256": "f565adfef5a502044abc3a9153e157edc25af78304d335994afb958874b15e26" + }, + { + "path": "ooxml/schemas/ecma/fouth-edition/opc-contentTypes.xsd", + "sha256": "9e0b7209fc69ab11987900404540969976000c5ebe4d4f58c43dc3842886bf3a" + }, + { + "path": "ooxml/schemas/ecma/fouth-edition/opc-digSig.xsd", + "sha256": "6de111e11403f7cd49027400755bae0ea1cabef2815f09bd40a24f0017613b24" + }, + { + "path": "ooxml/schemas/ISO-IEC29500-4_2016/vml-presentationDrawing.xsd", + "sha256": "133c9f64a5c5d573b78d0a474122b22506d8eadb5e063f67cdbbb8fa2f161d0e" + }, + { + "path": "ooxml/schemas/ISO-IEC29500-4_2016/vml-officeDrawing.xsd", + "sha256": "585bedc1313b40888dcc544cb74cd939a105ee674f3b1d3aa1cc6d34f70ff155" + }, + { + "path": "ooxml/schemas/ISO-IEC29500-4_2016/shared-customXmlSchemaProperties.xsd", + "sha256": "0d103b99a4a8652f8871552a69d42d2a3760ac6a5e3ef02d979c4273257ff6a4" + }, + { + "path": "ooxml/schemas/ISO-IEC29500-4_2016/pml.xsd", + "sha256": "d173c3e5d61e42e2e3a97226c632fd2ab7cc481fc4e492365b87024ab546daff" + }, + { + "path": "ooxml/schemas/ISO-IEC29500-4_2016/dml-lockedCanvas.xsd", + "sha256": "5cb76dabd8b97d1e9308a1700b90c20139be4d50792d21a7f09789f5cccd6026" + }, + { + "path": "ooxml/schemas/ISO-IEC29500-4_2016/dml-chart.xsd", + "sha256": "41b93bd8857cc68b1e43be2806a872d736a9bdd6566900062d8fdb57d7bbb354" + }, + { + "path": "ooxml/schemas/ISO-IEC29500-4_2016/dml-chartDrawing.xsd", + "sha256": "3fd0586f2637b98bb9886f0e0b67d89e1cc987c2d158cc7deb5f5b9890ced412" + }, + { + "path": "ooxml/schemas/ISO-IEC29500-4_2016/sml.xsd", + "sha256": "beffeed56945c22a77440122c8bdc426f3fcbe7f3b12ea0976c770d1f8d54578" + }, + { + "path": "ooxml/schemas/ISO-IEC29500-4_2016/vml-spreadsheetDrawing.xsd", + "sha256": "6bdeb169c3717eb01108853bd9fc5a3750fb1fa5b82abbdd854d49855a40f519" + }, + { + "path": "ooxml/schemas/ISO-IEC29500-4_2016/wml.xsd", + "sha256": "c2dd9f61f892deae6acd8d20771ea79b12018af25f3bf8d06639c8542d218cfd" + }, + { + "path": "ooxml/schemas/ISO-IEC29500-4_2016/dml-picture.xsd", + "sha256": "5d389d42befbebd91945d620242347caecd3367f9a3a7cf8d97949507ae1f53c" + }, + { + "path": "ooxml/schemas/ISO-IEC29500-4_2016/dml-diagram.xsd", + "sha256": "29b254ee0d10414a8504b5a08149c7baec35a60d5ff607d6b3f492aa36815f40" + }, + { + "path": "ooxml/schemas/ISO-IEC29500-4_2016/dml-main.xsd", + "sha256": "5375417f0f5394b8dd1a7035b9679151f19a6b65df309dec10cfb4a420cb00e9" + }, + { + "path": "ooxml/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesCustom.xsd", + "sha256": "9c085407751b9061c1f996f6c39ce58451be22a8d334f09175f0e89e42736285" + }, + { + "path": "ooxml/schemas/ISO-IEC29500-4_2016/dml-spreadsheetDrawing.xsd", + "sha256": "b4532b6d258832953fbb3ee4c711f4fe25d3faf46a10644b2505f17010d01e88" + }, + { + "path": "ooxml/schemas/ISO-IEC29500-4_2016/shared-commonSimpleTypes.xsd", + "sha256": "e2abacbb9a55ce1365f8961bc1b1395bbc811e512b111000d8c333f98458dece" + }, + { + "path": "ooxml/schemas/ISO-IEC29500-4_2016/dml-wordprocessingDrawing.xsd", + "sha256": "bdad416b096b61d37b71603b2c949484f9070c830bdaeba93bf35e15c8900614" + }, + { + "path": "ooxml/schemas/ISO-IEC29500-4_2016/vml-wordprocessingDrawing.xsd", + "sha256": "475dcae1e7d1ea46232db6f8481040c15e53a52a3c256831d3df204212b0e831" + }, + { + "path": "ooxml/schemas/ISO-IEC29500-4_2016/shared-bibliography.xsd", + "sha256": "0b364451dc36a48dd6dae0f3b6ada05fd9b71e5208211f8ee5537d7e51a587e2" + }, + { + "path": "ooxml/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesExtended.xsd", + "sha256": "bc92e36ccd233722d4c5869bec71ddc7b12e2df56059942cce5a39065cc9c368" + }, + { + "path": "ooxml/schemas/ISO-IEC29500-4_2016/vml-main.xsd", + "sha256": "f5ee623b08b6a66935e5aced2f5d8ad0fc71bf9e8e833cd490150c0fa94b8763" + }, + { + "path": "ooxml/schemas/ISO-IEC29500-4_2016/xml.xsd", + "sha256": "a539aa2fb154fa50e0f5cc97e6ad7cbc66f8ec3e3746f61ec6a8b0d5d15ecdf2" + }, + { + "path": "ooxml/schemas/ISO-IEC29500-4_2016/shared-relationshipReference.xsd", + "sha256": "12264f3c03d738311cd9237d212f1c07479e70f0cbe1ae725d29b36539aef637" + }, + { + "path": "ooxml/schemas/ISO-IEC29500-4_2016/shared-customXmlDataProperties.xsd", + "sha256": "0ef4bb354ff44b923564c4ddbdda5987919d220225129ec94614a618ceafc281" + }, + { + "path": "ooxml/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesVariantTypes.xsd", + "sha256": "7b5b7413e2c895b1e148e82e292a117d53c7ec65b0696c992edca57b61b4a74b" + }, + { + "path": "ooxml/schemas/ISO-IEC29500-4_2016/shared-math.xsd", + "sha256": "3213ef1631606250f5010b42cad7ef716f7c59426367798e33c374c0ec391d3a" + }, + { + "path": "ooxml/schemas/ISO-IEC29500-4_2016/shared-additionalCharacteristics.xsd", + "sha256": "3c6709101c6aaa82888df5d8795c33f9e857196790eb320d9194e64be2b6bdd8" + }, + { + "path": "ooxml/scripts/pack.py", + "sha256": "6fe762f45aff8c63fd95b9fcb1337b28921d6fa454e18a0e8158d4c8708d6d00" + }, + { + "path": "ooxml/scripts/validate.py", + "sha256": "1ec252de8b14b07d16966c48906ccb1c45c68bcd23557ad31d8c50a27f5f8c0f" + }, + { + "path": "ooxml/scripts/unpack.py", + "sha256": "0bd17f76a1a4c388aba42c6d1d39015fa84e405c3e0692397fe12762bd632b58" + }, + { + "path": "ooxml/scripts/validation/docx.py", + "sha256": "e65d6cda0525866a24cc847b2e883bd2416ae6f87b3f5b9e2784dfbb0ec13093" + }, + { + "path": "ooxml/scripts/validation/__init__.py", + "sha256": "83e0f035c5abea238d3f2c3968afbd511ed022b527b7c9cb60a9434cc34ff987" + }, + { + "path": "ooxml/scripts/validation/redlining.py", + "sha256": "97abfdff4f08f43f9a4bb5c8a2f8fd483398b5b339592724e8635153b5507967" + }, + { + "path": "ooxml/scripts/validation/pptx.py", + "sha256": "00bf2623da1177b3948143a4ade2f1cda7cb389dee31960861913fa42ef1b00f" + }, + { + "path": "ooxml/scripts/validation/base.py", + "sha256": "f2c70d481613456e32b43869d1604b05c236c8da34b5b3967677a661cac7ba63" + }, + { + "path": "scripts/html2pptx.js", + "sha256": "c675d09a54d6a002e8ca5917b9d24a6568aa8d455bb7abeb212d4f564dd07a34" + }, + { + "path": "scripts/thumbnail.py", + "sha256": "c21fd950b6ada7bd2f029885d3e56bc66b7ff061cc8404c492eb301664aa9e5d" + }, + { + "path": "scripts/rearrange.py", + "sha256": "c04ac37916f398ba621b2d9e1e4c1a69225eaad6d7fb0ad116c237ddeb1b2b68" + }, + { + "path": "scripts/inventory.py", + "sha256": "adead8fe6270e520c397cec9fbee4d606ab10bb80f749e018b42ec894c60d2e5" + }, + { + "path": "scripts/replace.py", + "sha256": "8a590747551be847a904e3296fb2f35aa4e7feeb4970a61596c2375306462820" + }, + { + "path": ".claude-plugin/plugin.json", + "sha256": "fa4633b53ca8b4b69f8af8cd238f32273d718d3752f3d80945c2f5225a67cbad" + } + ], + "dirSha256": "e173fa0dea199d8acfc9c4c90bdedd7b7d02c412168b64ea47b347423fb075b1" + }, + "security": { + "scannedAt": null, + "scannerVersion": null, + "flags": [] + } +} \ No newline at end of file diff --git a/scripts/html2pptx.js b/scripts/html2pptx.js new file mode 100755 index 0000000..437bf7c --- /dev/null +++ b/scripts/html2pptx.js @@ -0,0 +1,979 @@ +/** + * html2pptx - Convert HTML slide to pptxgenjs slide with positioned elements + * + * USAGE: + * const pptx = new pptxgen(); + * pptx.layout = 'LAYOUT_16x9'; // Must match HTML body dimensions + * + * const { slide, placeholders } = await html2pptx('slide.html', pptx); + * slide.addChart(pptx.charts.LINE, data, placeholders[0]); + * + * await pptx.writeFile('output.pptx'); + * + * FEATURES: + * - Converts HTML to PowerPoint with accurate positioning + * - Supports text, images, shapes, and bullet lists + * - Extracts placeholder elements (class="placeholder") with positions + * - Handles CSS gradients, borders, and margins + * + * VALIDATION: + * - Uses body width/height from HTML for viewport sizing + * - Throws error if HTML dimensions don't match presentation layout + * - Throws error if content overflows body (with overflow details) + * + * RETURNS: + * { slide, placeholders } where placeholders is an array of { id, x, y, w, h } + */ + +const { chromium } = require('playwright'); +const path = require('path'); +const sharp = require('sharp'); + +const PT_PER_PX = 0.75; +const PX_PER_IN = 96; +const EMU_PER_IN = 914400; + +// Helper: Get body dimensions and check for overflow +async function getBodyDimensions(page) { + const bodyDimensions = await page.evaluate(() => { + const body = document.body; + const style = window.getComputedStyle(body); + + return { + width: parseFloat(style.width), + height: parseFloat(style.height), + scrollWidth: body.scrollWidth, + scrollHeight: body.scrollHeight + }; + }); + + const errors = []; + const widthOverflowPx = Math.max(0, bodyDimensions.scrollWidth - bodyDimensions.width - 1); + const heightOverflowPx = Math.max(0, bodyDimensions.scrollHeight - bodyDimensions.height - 1); + + const widthOverflowPt = widthOverflowPx * PT_PER_PX; + const heightOverflowPt = heightOverflowPx * PT_PER_PX; + + if (widthOverflowPt > 0 || heightOverflowPt > 0) { + const directions = []; + if (widthOverflowPt > 0) directions.push(`${widthOverflowPt.toFixed(1)}pt horizontally`); + if (heightOverflowPt > 0) directions.push(`${heightOverflowPt.toFixed(1)}pt vertically`); + const reminder = heightOverflowPt > 0 ? ' (Remember: leave 0.5" margin at bottom of slide)' : ''; + errors.push(`HTML content overflows body by ${directions.join(' and ')}${reminder}`); + } + + return { ...bodyDimensions, errors }; +} + +// Helper: Validate dimensions match presentation layout +function validateDimensions(bodyDimensions, pres) { + const errors = []; + const widthInches = bodyDimensions.width / PX_PER_IN; + const heightInches = bodyDimensions.height / PX_PER_IN; + + if (pres.presLayout) { + const layoutWidth = pres.presLayout.width / EMU_PER_IN; + const layoutHeight = pres.presLayout.height / EMU_PER_IN; + + if (Math.abs(layoutWidth - widthInches) > 0.1 || Math.abs(layoutHeight - heightInches) > 0.1) { + errors.push( + `HTML dimensions (${widthInches.toFixed(1)}" × ${heightInches.toFixed(1)}") ` + + `don't match presentation layout (${layoutWidth.toFixed(1)}" × ${layoutHeight.toFixed(1)}")` + ); + } + } + return errors; +} + +function validateTextBoxPosition(slideData, bodyDimensions) { + const errors = []; + const slideHeightInches = bodyDimensions.height / PX_PER_IN; + const minBottomMargin = 0.5; // 0.5 inches from bottom + + for (const el of slideData.elements) { + // Check text elements (p, h1-h6, list) + if (['p', 'h1', 'h2', 'h3', 'h4', 'h5', 'h6', 'list'].includes(el.type)) { + const fontSize = el.style?.fontSize || 0; + const bottomEdge = el.position.y + el.position.h; + const distanceFromBottom = slideHeightInches - bottomEdge; + + if (fontSize > 12 && distanceFromBottom < minBottomMargin) { + const getText = () => { + if (typeof el.text === 'string') return el.text; + if (Array.isArray(el.text)) return el.text.find(t => t.text)?.text || ''; + if (Array.isArray(el.items)) return el.items.find(item => item.text)?.text || ''; + return ''; + }; + const textPrefix = getText().substring(0, 50) + (getText().length > 50 ? '...' : ''); + + errors.push( + `Text box "${textPrefix}" ends too close to bottom edge ` + + `(${distanceFromBottom.toFixed(2)}" from bottom, minimum ${minBottomMargin}" required)` + ); + } + } + } + + return errors; +} + +// Helper: Add background to slide +async function addBackground(slideData, targetSlide, tmpDir) { + if (slideData.background.type === 'image' && slideData.background.path) { + let imagePath = slideData.background.path.startsWith('file://') + ? slideData.background.path.replace('file://', '') + : slideData.background.path; + targetSlide.background = { path: imagePath }; + } else if (slideData.background.type === 'color' && slideData.background.value) { + targetSlide.background = { color: slideData.background.value }; + } +} + +// Helper: Add elements to slide +function addElements(slideData, targetSlide, pres) { + for (const el of slideData.elements) { + if (el.type === 'image') { + let imagePath = el.src.startsWith('file://') ? el.src.replace('file://', '') : el.src; + targetSlide.addImage({ + path: imagePath, + x: el.position.x, + y: el.position.y, + w: el.position.w, + h: el.position.h + }); + } else if (el.type === 'line') { + targetSlide.addShape(pres.ShapeType.line, { + x: el.x1, + y: el.y1, + w: el.x2 - el.x1, + h: el.y2 - el.y1, + line: { color: el.color, width: el.width } + }); + } else if (el.type === 'shape') { + const shapeOptions = { + x: el.position.x, + y: el.position.y, + w: el.position.w, + h: el.position.h, + shape: el.shape.rectRadius > 0 ? pres.ShapeType.roundRect : pres.ShapeType.rect + }; + + if (el.shape.fill) { + shapeOptions.fill = { color: el.shape.fill }; + if (el.shape.transparency != null) shapeOptions.fill.transparency = el.shape.transparency; + } + if (el.shape.line) shapeOptions.line = el.shape.line; + if (el.shape.rectRadius > 0) shapeOptions.rectRadius = el.shape.rectRadius; + if (el.shape.shadow) shapeOptions.shadow = el.shape.shadow; + + targetSlide.addText(el.text || '', shapeOptions); + } else if (el.type === 'list') { + const listOptions = { + x: el.position.x, + y: el.position.y, + w: el.position.w, + h: el.position.h, + fontSize: el.style.fontSize, + fontFace: el.style.fontFace, + color: el.style.color, + align: el.style.align, + valign: 'top', + lineSpacing: el.style.lineSpacing, + paraSpaceBefore: el.style.paraSpaceBefore, + paraSpaceAfter: el.style.paraSpaceAfter, + margin: el.style.margin + }; + if (el.style.margin) listOptions.margin = el.style.margin; + targetSlide.addText(el.items, listOptions); + } else { + // Check if text is single-line (height suggests one line) + const lineHeight = el.style.lineSpacing || el.style.fontSize * 1.2; + const isSingleLine = el.position.h <= lineHeight * 1.5; + + let adjustedX = el.position.x; + let adjustedW = el.position.w; + + // Make single-line text 2% wider to account for underestimate + if (isSingleLine) { + const widthIncrease = el.position.w * 0.02; + const align = el.style.align; + + if (align === 'center') { + // Center: expand both sides + adjustedX = el.position.x - (widthIncrease / 2); + adjustedW = el.position.w + widthIncrease; + } else if (align === 'right') { + // Right: expand to the left + adjustedX = el.position.x - widthIncrease; + adjustedW = el.position.w + widthIncrease; + } else { + // Left (default): expand to the right + adjustedW = el.position.w + widthIncrease; + } + } + + const textOptions = { + x: adjustedX, + y: el.position.y, + w: adjustedW, + h: el.position.h, + fontSize: el.style.fontSize, + fontFace: el.style.fontFace, + color: el.style.color, + bold: el.style.bold, + italic: el.style.italic, + underline: el.style.underline, + valign: 'top', + lineSpacing: el.style.lineSpacing, + paraSpaceBefore: el.style.paraSpaceBefore, + paraSpaceAfter: el.style.paraSpaceAfter, + inset: 0 // Remove default PowerPoint internal padding + }; + + if (el.style.align) textOptions.align = el.style.align; + if (el.style.margin) textOptions.margin = el.style.margin; + if (el.style.rotate !== undefined) textOptions.rotate = el.style.rotate; + if (el.style.transparency !== null && el.style.transparency !== undefined) textOptions.transparency = el.style.transparency; + + targetSlide.addText(el.text, textOptions); + } + } +} + +// Helper: Extract slide data from HTML page +async function extractSlideData(page) { + return await page.evaluate(() => { + const PT_PER_PX = 0.75; + const PX_PER_IN = 96; + + // Fonts that are single-weight and should not have bold applied + // (applying bold causes PowerPoint to use faux bold which makes text wider) + const SINGLE_WEIGHT_FONTS = ['impact']; + + // Helper: Check if a font should skip bold formatting + const shouldSkipBold = (fontFamily) => { + if (!fontFamily) return false; + const normalizedFont = fontFamily.toLowerCase().replace(/['"]/g, '').split(',')[0].trim(); + return SINGLE_WEIGHT_FONTS.includes(normalizedFont); + }; + + // Unit conversion helpers + const pxToInch = (px) => px / PX_PER_IN; + const pxToPoints = (pxStr) => parseFloat(pxStr) * PT_PER_PX; + const rgbToHex = (rgbStr) => { + // Handle transparent backgrounds by defaulting to white + if (rgbStr === 'rgba(0, 0, 0, 0)' || rgbStr === 'transparent') return 'FFFFFF'; + + const match = rgbStr.match(/rgba?\((\d+),\s*(\d+),\s*(\d+)/); + if (!match) return 'FFFFFF'; + return match.slice(1).map(n => parseInt(n).toString(16).padStart(2, '0')).join(''); + }; + + const extractAlpha = (rgbStr) => { + const match = rgbStr.match(/rgba\((\d+),\s*(\d+),\s*(\d+),\s*([\d.]+)\)/); + if (!match || !match[4]) return null; + const alpha = parseFloat(match[4]); + return Math.round((1 - alpha) * 100); + }; + + const applyTextTransform = (text, textTransform) => { + if (textTransform === 'uppercase') return text.toUpperCase(); + if (textTransform === 'lowercase') return text.toLowerCase(); + if (textTransform === 'capitalize') { + return text.replace(/\b\w/g, c => c.toUpperCase()); + } + return text; + }; + + // Extract rotation angle from CSS transform and writing-mode + const getRotation = (transform, writingMode) => { + let angle = 0; + + // Handle writing-mode first + // PowerPoint: 90° = text rotated 90° clockwise (reads top to bottom, letters upright) + // PowerPoint: 270° = text rotated 270° clockwise (reads bottom to top, letters upright) + if (writingMode === 'vertical-rl') { + // vertical-rl alone = text reads top to bottom = 90° in PowerPoint + angle = 90; + } else if (writingMode === 'vertical-lr') { + // vertical-lr alone = text reads bottom to top = 270° in PowerPoint + angle = 270; + } + + // Then add any transform rotation + if (transform && transform !== 'none') { + // Try to match rotate() function + const rotateMatch = transform.match(/rotate\((-?\d+(?:\.\d+)?)deg\)/); + if (rotateMatch) { + angle += parseFloat(rotateMatch[1]); + } else { + // Browser may compute as matrix - extract rotation from matrix + const matrixMatch = transform.match(/matrix\(([^)]+)\)/); + if (matrixMatch) { + const values = matrixMatch[1].split(',').map(parseFloat); + // matrix(a, b, c, d, e, f) where rotation = atan2(b, a) + const matrixAngle = Math.atan2(values[1], values[0]) * (180 / Math.PI); + angle += Math.round(matrixAngle); + } + } + } + + // Normalize to 0-359 range + angle = angle % 360; + if (angle < 0) angle += 360; + + return angle === 0 ? null : angle; + }; + + // Get position/dimensions accounting for rotation + const getPositionAndSize = (el, rect, rotation) => { + if (rotation === null) { + return { x: rect.left, y: rect.top, w: rect.width, h: rect.height }; + } + + // For 90° or 270° rotations, swap width and height + // because PowerPoint applies rotation to the original (unrotated) box + const isVertical = rotation === 90 || rotation === 270; + + if (isVertical) { + // The browser shows us the rotated dimensions (tall box for vertical text) + // But PowerPoint needs the pre-rotation dimensions (wide box that will be rotated) + // So we swap: browser's height becomes PPT's width, browser's width becomes PPT's height + const centerX = rect.left + rect.width / 2; + const centerY = rect.top + rect.height / 2; + + return { + x: centerX - rect.height / 2, + y: centerY - rect.width / 2, + w: rect.height, + h: rect.width + }; + } + + // For other rotations, use element's offset dimensions + const centerX = rect.left + rect.width / 2; + const centerY = rect.top + rect.height / 2; + return { + x: centerX - el.offsetWidth / 2, + y: centerY - el.offsetHeight / 2, + w: el.offsetWidth, + h: el.offsetHeight + }; + }; + + // Parse CSS box-shadow into PptxGenJS shadow properties + const parseBoxShadow = (boxShadow) => { + if (!boxShadow || boxShadow === 'none') return null; + + // Browser computed style format: "rgba(0, 0, 0, 0.3) 2px 2px 8px 0px [inset]" + // CSS format: "[inset] 2px 2px 8px 0px rgba(0, 0, 0, 0.3)" + + const insetMatch = boxShadow.match(/inset/); + + // IMPORTANT: PptxGenJS/PowerPoint doesn't properly support inset shadows + // Only process outer shadows to avoid file corruption + if (insetMatch) return null; + + // Extract color first (rgba or rgb at start) + const colorMatch = boxShadow.match(/rgba?\([^)]+\)/); + + // Extract numeric values (handles both px and pt units) + const parts = boxShadow.match(/([-\d.]+)(px|pt)/g); + + if (!parts || parts.length < 2) return null; + + const offsetX = parseFloat(parts[0]); + const offsetY = parseFloat(parts[1]); + const blur = parts.length > 2 ? parseFloat(parts[2]) : 0; + + // Calculate angle from offsets (in degrees, 0 = right, 90 = down) + let angle = 0; + if (offsetX !== 0 || offsetY !== 0) { + angle = Math.atan2(offsetY, offsetX) * (180 / Math.PI); + if (angle < 0) angle += 360; + } + + // Calculate offset distance (hypotenuse) + const offset = Math.sqrt(offsetX * offsetX + offsetY * offsetY) * PT_PER_PX; + + // Extract opacity from rgba + let opacity = 0.5; + if (colorMatch) { + const opacityMatch = colorMatch[0].match(/[\d.]+\)$/); + if (opacityMatch) { + opacity = parseFloat(opacityMatch[0].replace(')', '')); + } + } + + return { + type: 'outer', + angle: Math.round(angle), + blur: blur * 0.75, // Convert to points + color: colorMatch ? rgbToHex(colorMatch[0]) : '000000', + offset: offset, + opacity + }; + }; + + // Parse inline formatting tags (, , , , , ) into text runs + const parseInlineFormatting = (element, baseOptions = {}, runs = [], baseTextTransform = (x) => x) => { + let prevNodeIsText = false; + + element.childNodes.forEach((node) => { + let textTransform = baseTextTransform; + + const isText = node.nodeType === Node.TEXT_NODE || node.tagName === 'BR'; + if (isText) { + const text = node.tagName === 'BR' ? '\n' : textTransform(node.textContent.replace(/\s+/g, ' ')); + const prevRun = runs[runs.length - 1]; + if (prevNodeIsText && prevRun) { + prevRun.text += text; + } else { + runs.push({ text, options: { ...baseOptions } }); + } + + } else if (node.nodeType === Node.ELEMENT_NODE && node.textContent.trim()) { + const options = { ...baseOptions }; + const computed = window.getComputedStyle(node); + + // Handle inline elements with computed styles + if (node.tagName === 'SPAN' || node.tagName === 'B' || node.tagName === 'STRONG' || node.tagName === 'I' || node.tagName === 'EM' || node.tagName === 'U') { + const isBold = computed.fontWeight === 'bold' || parseInt(computed.fontWeight) >= 600; + if (isBold && !shouldSkipBold(computed.fontFamily)) options.bold = true; + if (computed.fontStyle === 'italic') options.italic = true; + if (computed.textDecoration && computed.textDecoration.includes('underline')) options.underline = true; + if (computed.color && computed.color !== 'rgb(0, 0, 0)') { + options.color = rgbToHex(computed.color); + const transparency = extractAlpha(computed.color); + if (transparency !== null) options.transparency = transparency; + } + if (computed.fontSize) options.fontSize = pxToPoints(computed.fontSize); + + // Apply text-transform on the span element itself + if (computed.textTransform && computed.textTransform !== 'none') { + const transformStr = computed.textTransform; + textTransform = (text) => applyTextTransform(text, transformStr); + } + + // Validate: Check for margins on inline elements + if (computed.marginLeft && parseFloat(computed.marginLeft) > 0) { + errors.push(`Inline element <${node.tagName.toLowerCase()}> has margin-left which is not supported in PowerPoint. Remove margin from inline elements.`); + } + if (computed.marginRight && parseFloat(computed.marginRight) > 0) { + errors.push(`Inline element <${node.tagName.toLowerCase()}> has margin-right which is not supported in PowerPoint. Remove margin from inline elements.`); + } + if (computed.marginTop && parseFloat(computed.marginTop) > 0) { + errors.push(`Inline element <${node.tagName.toLowerCase()}> has margin-top which is not supported in PowerPoint. Remove margin from inline elements.`); + } + if (computed.marginBottom && parseFloat(computed.marginBottom) > 0) { + errors.push(`Inline element <${node.tagName.toLowerCase()}> has margin-bottom which is not supported in PowerPoint. Remove margin from inline elements.`); + } + + // Recursively process the child node. This will flatten nested spans into multiple runs. + parseInlineFormatting(node, options, runs, textTransform); + } + } + + prevNodeIsText = isText; + }); + + // Trim leading space from first run and trailing space from last run + if (runs.length > 0) { + runs[0].text = runs[0].text.replace(/^\s+/, ''); + runs[runs.length - 1].text = runs[runs.length - 1].text.replace(/\s+$/, ''); + } + + return runs.filter(r => r.text.length > 0); + }; + + // Extract background from body (image or color) + const body = document.body; + const bodyStyle = window.getComputedStyle(body); + const bgImage = bodyStyle.backgroundImage; + const bgColor = bodyStyle.backgroundColor; + + // Collect validation errors + const errors = []; + + // Validate: Check for CSS gradients + if (bgImage && (bgImage.includes('linear-gradient') || bgImage.includes('radial-gradient'))) { + errors.push( + 'CSS gradients are not supported. Use Sharp to rasterize gradients as PNG images first, ' + + 'then reference with background-image: url(\'gradient.png\')' + ); + } + + let background; + if (bgImage && bgImage !== 'none') { + // Extract URL from url("...") or url(...) + const urlMatch = bgImage.match(/url\(["']?([^"')]+)["']?\)/); + if (urlMatch) { + background = { + type: 'image', + path: urlMatch[1] + }; + } else { + background = { + type: 'color', + value: rgbToHex(bgColor) + }; + } + } else { + background = { + type: 'color', + value: rgbToHex(bgColor) + }; + } + + // Process all elements + const elements = []; + const placeholders = []; + const textTags = ['P', 'H1', 'H2', 'H3', 'H4', 'H5', 'H6', 'UL', 'OL', 'LI']; + const processed = new Set(); + + document.querySelectorAll('*').forEach((el) => { + if (processed.has(el)) return; + + // Validate text elements don't have backgrounds, borders, or shadows + if (textTags.includes(el.tagName)) { + const computed = window.getComputedStyle(el); + const hasBg = computed.backgroundColor && computed.backgroundColor !== 'rgba(0, 0, 0, 0)'; + const hasBorder = (computed.borderWidth && parseFloat(computed.borderWidth) > 0) || + (computed.borderTopWidth && parseFloat(computed.borderTopWidth) > 0) || + (computed.borderRightWidth && parseFloat(computed.borderRightWidth) > 0) || + (computed.borderBottomWidth && parseFloat(computed.borderBottomWidth) > 0) || + (computed.borderLeftWidth && parseFloat(computed.borderLeftWidth) > 0); + const hasShadow = computed.boxShadow && computed.boxShadow !== 'none'; + + if (hasBg || hasBorder || hasShadow) { + errors.push( + `Text element <${el.tagName.toLowerCase()}> has ${hasBg ? 'background' : hasBorder ? 'border' : 'shadow'}. ` + + 'Backgrounds, borders, and shadows are only supported on
                      elements, not text elements.' + ); + return; + } + } + + // Extract placeholder elements (for charts, etc.) + if (el.className && el.className.includes('placeholder')) { + const rect = el.getBoundingClientRect(); + if (rect.width === 0 || rect.height === 0) { + errors.push( + `Placeholder "${el.id || 'unnamed'}" has ${rect.width === 0 ? 'width: 0' : 'height: 0'}. Check the layout CSS.` + ); + } else { + placeholders.push({ + id: el.id || `placeholder-${placeholders.length}`, + x: pxToInch(rect.left), + y: pxToInch(rect.top), + w: pxToInch(rect.width), + h: pxToInch(rect.height) + }); + } + processed.add(el); + return; + } + + // Extract images + if (el.tagName === 'IMG') { + const rect = el.getBoundingClientRect(); + if (rect.width > 0 && rect.height > 0) { + elements.push({ + type: 'image', + src: el.src, + position: { + x: pxToInch(rect.left), + y: pxToInch(rect.top), + w: pxToInch(rect.width), + h: pxToInch(rect.height) + } + }); + processed.add(el); + return; + } + } + + // Extract DIVs with backgrounds/borders as shapes + const isContainer = el.tagName === 'DIV' && !textTags.includes(el.tagName); + if (isContainer) { + const computed = window.getComputedStyle(el); + const hasBg = computed.backgroundColor && computed.backgroundColor !== 'rgba(0, 0, 0, 0)'; + + // Validate: Check for unwrapped text content in DIV + for (const node of el.childNodes) { + if (node.nodeType === Node.TEXT_NODE) { + const text = node.textContent.trim(); + if (text) { + errors.push( + `DIV element contains unwrapped text "${text.substring(0, 50)}${text.length > 50 ? '...' : ''}". ` + + 'All text must be wrapped in

                      ,

                      -

                      ,
                        , or
                          tags to appear in PowerPoint.' + ); + } + } + } + + // Check for background images on shapes + const bgImage = computed.backgroundImage; + if (bgImage && bgImage !== 'none') { + errors.push( + 'Background images on DIV elements are not supported. ' + + 'Use solid colors or borders for shapes, or use slide.addImage() in PptxGenJS to layer images.' + ); + return; + } + + // Check for borders - both uniform and partial + const borderTop = computed.borderTopWidth; + const borderRight = computed.borderRightWidth; + const borderBottom = computed.borderBottomWidth; + const borderLeft = computed.borderLeftWidth; + const borders = [borderTop, borderRight, borderBottom, borderLeft].map(b => parseFloat(b) || 0); + const hasBorder = borders.some(b => b > 0); + const hasUniformBorder = hasBorder && borders.every(b => b === borders[0]); + const borderLines = []; + + if (hasBorder && !hasUniformBorder) { + const rect = el.getBoundingClientRect(); + const x = pxToInch(rect.left); + const y = pxToInch(rect.top); + const w = pxToInch(rect.width); + const h = pxToInch(rect.height); + + // Collect lines to add after shape (inset by half the line width to center on edge) + if (parseFloat(borderTop) > 0) { + const widthPt = pxToPoints(borderTop); + const inset = (widthPt / 72) / 2; // Convert points to inches, then half + borderLines.push({ + type: 'line', + x1: x, y1: y + inset, x2: x + w, y2: y + inset, + width: widthPt, + color: rgbToHex(computed.borderTopColor) + }); + } + if (parseFloat(borderRight) > 0) { + const widthPt = pxToPoints(borderRight); + const inset = (widthPt / 72) / 2; + borderLines.push({ + type: 'line', + x1: x + w - inset, y1: y, x2: x + w - inset, y2: y + h, + width: widthPt, + color: rgbToHex(computed.borderRightColor) + }); + } + if (parseFloat(borderBottom) > 0) { + const widthPt = pxToPoints(borderBottom); + const inset = (widthPt / 72) / 2; + borderLines.push({ + type: 'line', + x1: x, y1: y + h - inset, x2: x + w, y2: y + h - inset, + width: widthPt, + color: rgbToHex(computed.borderBottomColor) + }); + } + if (parseFloat(borderLeft) > 0) { + const widthPt = pxToPoints(borderLeft); + const inset = (widthPt / 72) / 2; + borderLines.push({ + type: 'line', + x1: x + inset, y1: y, x2: x + inset, y2: y + h, + width: widthPt, + color: rgbToHex(computed.borderLeftColor) + }); + } + } + + if (hasBg || hasBorder) { + const rect = el.getBoundingClientRect(); + if (rect.width > 0 && rect.height > 0) { + const shadow = parseBoxShadow(computed.boxShadow); + + // Only add shape if there's background or uniform border + if (hasBg || hasUniformBorder) { + elements.push({ + type: 'shape', + text: '', // Shape only - child text elements render on top + position: { + x: pxToInch(rect.left), + y: pxToInch(rect.top), + w: pxToInch(rect.width), + h: pxToInch(rect.height) + }, + shape: { + fill: hasBg ? rgbToHex(computed.backgroundColor) : null, + transparency: hasBg ? extractAlpha(computed.backgroundColor) : null, + line: hasUniformBorder ? { + color: rgbToHex(computed.borderColor), + width: pxToPoints(computed.borderWidth) + } : null, + // Convert border-radius to rectRadius (in inches) + // % values: 50%+ = circle (1), <50% = percentage of min dimension + // pt values: divide by 72 (72pt = 1 inch) + // px values: divide by 96 (96px = 1 inch) + rectRadius: (() => { + const radius = computed.borderRadius; + const radiusValue = parseFloat(radius); + if (radiusValue === 0) return 0; + + if (radius.includes('%')) { + if (radiusValue >= 50) return 1; + // Calculate percentage of smaller dimension + const minDim = Math.min(rect.width, rect.height); + return (radiusValue / 100) * pxToInch(minDim); + } + + if (radius.includes('pt')) return radiusValue / 72; + return radiusValue / PX_PER_IN; + })(), + shadow: shadow + } + }); + } + + // Add partial border lines + elements.push(...borderLines); + + processed.add(el); + return; + } + } + } + + // Extract bullet lists as single text block + if (el.tagName === 'UL' || el.tagName === 'OL') { + const rect = el.getBoundingClientRect(); + if (rect.width === 0 || rect.height === 0) return; + + const liElements = Array.from(el.querySelectorAll('li')); + const items = []; + const ulComputed = window.getComputedStyle(el); + const ulPaddingLeftPt = pxToPoints(ulComputed.paddingLeft); + + // Split: margin-left for bullet position, indent for text position + // margin-left + indent = ul padding-left + const marginLeft = ulPaddingLeftPt * 0.5; + const textIndent = ulPaddingLeftPt * 0.5; + + liElements.forEach((li, idx) => { + const isLast = idx === liElements.length - 1; + const runs = parseInlineFormatting(li, { breakLine: false }); + // Clean manual bullets from first run + if (runs.length > 0) { + runs[0].text = runs[0].text.replace(/^[•\-\*▪▸]\s*/, ''); + runs[0].options.bullet = { indent: textIndent }; + } + // Set breakLine on last run + if (runs.length > 0 && !isLast) { + runs[runs.length - 1].options.breakLine = true; + } + items.push(...runs); + }); + + const computed = window.getComputedStyle(liElements[0] || el); + + elements.push({ + type: 'list', + items: items, + position: { + x: pxToInch(rect.left), + y: pxToInch(rect.top), + w: pxToInch(rect.width), + h: pxToInch(rect.height) + }, + style: { + fontSize: pxToPoints(computed.fontSize), + fontFace: computed.fontFamily.split(',')[0].replace(/['"]/g, '').trim(), + color: rgbToHex(computed.color), + transparency: extractAlpha(computed.color), + align: computed.textAlign === 'start' ? 'left' : computed.textAlign, + lineSpacing: computed.lineHeight && computed.lineHeight !== 'normal' ? pxToPoints(computed.lineHeight) : null, + paraSpaceBefore: 0, + paraSpaceAfter: pxToPoints(computed.marginBottom), + // PptxGenJS margin array is [left, right, bottom, top] + margin: [marginLeft, 0, 0, 0] + } + }); + + liElements.forEach(li => processed.add(li)); + processed.add(el); + return; + } + + // Extract text elements (P, H1, H2, etc.) + if (!textTags.includes(el.tagName)) return; + + const rect = el.getBoundingClientRect(); + const text = el.textContent.trim(); + if (rect.width === 0 || rect.height === 0 || !text) return; + + // Validate: Check for manual bullet symbols in text elements (not in lists) + if (el.tagName !== 'LI' && /^[•\-\*▪▸○●◆◇■□]\s/.test(text.trimStart())) { + errors.push( + `Text element <${el.tagName.toLowerCase()}> starts with bullet symbol "${text.substring(0, 20)}...". ` + + 'Use
                            or
                              lists instead of manual bullet symbols.' + ); + return; + } + + const computed = window.getComputedStyle(el); + const rotation = getRotation(computed.transform, computed.writingMode); + const { x, y, w, h } = getPositionAndSize(el, rect, rotation); + + const baseStyle = { + fontSize: pxToPoints(computed.fontSize), + fontFace: computed.fontFamily.split(',')[0].replace(/['"]/g, '').trim(), + color: rgbToHex(computed.color), + align: computed.textAlign === 'start' ? 'left' : computed.textAlign, + lineSpacing: pxToPoints(computed.lineHeight), + paraSpaceBefore: pxToPoints(computed.marginTop), + paraSpaceAfter: pxToPoints(computed.marginBottom), + // PptxGenJS margin array is [left, right, bottom, top] (not [top, right, bottom, left] as documented) + margin: [ + pxToPoints(computed.paddingLeft), + pxToPoints(computed.paddingRight), + pxToPoints(computed.paddingBottom), + pxToPoints(computed.paddingTop) + ] + }; + + const transparency = extractAlpha(computed.color); + if (transparency !== null) baseStyle.transparency = transparency; + + if (rotation !== null) baseStyle.rotate = rotation; + + const hasFormatting = el.querySelector('b, i, u, strong, em, span, br'); + + if (hasFormatting) { + // Text with inline formatting + const transformStr = computed.textTransform; + const runs = parseInlineFormatting(el, {}, [], (str) => applyTextTransform(str, transformStr)); + + // Adjust lineSpacing based on largest fontSize in runs + const adjustedStyle = { ...baseStyle }; + if (adjustedStyle.lineSpacing) { + const maxFontSize = Math.max( + adjustedStyle.fontSize, + ...runs.map(r => r.options?.fontSize || 0) + ); + if (maxFontSize > adjustedStyle.fontSize) { + const lineHeightMultiplier = adjustedStyle.lineSpacing / adjustedStyle.fontSize; + adjustedStyle.lineSpacing = maxFontSize * lineHeightMultiplier; + } + } + + elements.push({ + type: el.tagName.toLowerCase(), + text: runs, + position: { x: pxToInch(x), y: pxToInch(y), w: pxToInch(w), h: pxToInch(h) }, + style: adjustedStyle + }); + } else { + // Plain text - inherit CSS formatting + const textTransform = computed.textTransform; + const transformedText = applyTextTransform(text, textTransform); + + const isBold = computed.fontWeight === 'bold' || parseInt(computed.fontWeight) >= 600; + + elements.push({ + type: el.tagName.toLowerCase(), + text: transformedText, + position: { x: pxToInch(x), y: pxToInch(y), w: pxToInch(w), h: pxToInch(h) }, + style: { + ...baseStyle, + bold: isBold && !shouldSkipBold(computed.fontFamily), + italic: computed.fontStyle === 'italic', + underline: computed.textDecoration.includes('underline') + } + }); + } + + processed.add(el); + }); + + return { background, elements, placeholders, errors }; + }); +} + +async function html2pptx(htmlFile, pres, options = {}) { + const { + tmpDir = process.env.TMPDIR || '/tmp', + slide = null + } = options; + + try { + // Use Chrome on macOS, default Chromium on Unix + const launchOptions = { env: { TMPDIR: tmpDir } }; + if (process.platform === 'darwin') { + launchOptions.channel = 'chrome'; + } + + const browser = await chromium.launch(launchOptions); + + let bodyDimensions; + let slideData; + + const filePath = path.isAbsolute(htmlFile) ? htmlFile : path.join(process.cwd(), htmlFile); + const validationErrors = []; + + try { + const page = await browser.newPage(); + page.on('console', (msg) => { + // Log the message text to your test runner's console + console.log(`Browser console: ${msg.text()}`); + }); + + await page.goto(`file://${filePath}`); + + bodyDimensions = await getBodyDimensions(page); + + await page.setViewportSize({ + width: Math.round(bodyDimensions.width), + height: Math.round(bodyDimensions.height) + }); + + slideData = await extractSlideData(page); + } finally { + await browser.close(); + } + + // Collect all validation errors + if (bodyDimensions.errors && bodyDimensions.errors.length > 0) { + validationErrors.push(...bodyDimensions.errors); + } + + const dimensionErrors = validateDimensions(bodyDimensions, pres); + if (dimensionErrors.length > 0) { + validationErrors.push(...dimensionErrors); + } + + const textBoxPositionErrors = validateTextBoxPosition(slideData, bodyDimensions); + if (textBoxPositionErrors.length > 0) { + validationErrors.push(...textBoxPositionErrors); + } + + if (slideData.errors && slideData.errors.length > 0) { + validationErrors.push(...slideData.errors); + } + + // Throw all errors at once if any exist + if (validationErrors.length > 0) { + const errorMessage = validationErrors.length === 1 + ? validationErrors[0] + : `Multiple validation errors found:\n${validationErrors.map((e, i) => ` ${i + 1}. ${e}`).join('\n')}`; + throw new Error(errorMessage); + } + + const targetSlide = slide || pres.addSlide(); + + await addBackground(slideData, targetSlide, tmpDir); + addElements(slideData, targetSlide, pres); + + return { slide: targetSlide, placeholders: slideData.placeholders }; + } catch (error) { + if (!error.message.startsWith(htmlFile)) { + throw new Error(`${htmlFile}: ${error.message}`); + } + throw error; + } +} + +module.exports = html2pptx; \ No newline at end of file diff --git a/scripts/inventory.py b/scripts/inventory.py new file mode 100755 index 0000000..edda390 --- /dev/null +++ b/scripts/inventory.py @@ -0,0 +1,1020 @@ +#!/usr/bin/env python3 +""" +Extract structured text content from PowerPoint presentations. + +This module provides functionality to: +- Extract all text content from PowerPoint shapes +- Preserve paragraph formatting (alignment, bullets, fonts, spacing) +- Handle nested GroupShapes recursively with correct absolute positions +- Sort shapes by visual position on slides +- Filter out slide numbers and non-content placeholders +- Export to JSON with clean, structured data + +Classes: + ParagraphData: Represents a text paragraph with formatting + ShapeData: Represents a shape with position and text content + +Main Functions: + extract_text_inventory: Extract all text from a presentation + save_inventory: Save extracted data to JSON + +Usage: + python inventory.py input.pptx output.json +""" + +import argparse +import json +import platform +import sys +from dataclasses import dataclass +from pathlib import Path +from typing import Any, Dict, List, Optional, Tuple, Union + +from PIL import Image, ImageDraw, ImageFont +from pptx import Presentation +from pptx.enum.text import PP_ALIGN +from pptx.shapes.base import BaseShape + +# Type aliases for cleaner signatures +JsonValue = Union[str, int, float, bool, None] +ParagraphDict = Dict[str, JsonValue] +ShapeDict = Dict[ + str, Union[str, float, bool, List[ParagraphDict], List[str], Dict[str, Any], None] +] +InventoryData = Dict[ + str, Dict[str, "ShapeData"] +] # Dict of slide_id -> {shape_id -> ShapeData} +InventoryDict = Dict[str, Dict[str, ShapeDict]] # JSON-serializable inventory + + +def main(): + """Main entry point for command-line usage.""" + parser = argparse.ArgumentParser( + description="Extract text inventory from PowerPoint with proper GroupShape support.", + formatter_class=argparse.RawDescriptionHelpFormatter, + epilog=""" +Examples: + python inventory.py presentation.pptx inventory.json + Extracts text inventory with correct absolute positions for grouped shapes + + python inventory.py presentation.pptx inventory.json --issues-only + Extracts only text shapes that have overflow or overlap issues + +The output JSON includes: + - All text content organized by slide and shape + - Correct absolute positions for shapes in groups + - Visual position and size in inches + - Paragraph properties and formatting + - Issue detection: text overflow and shape overlaps + """, + ) + + parser.add_argument("input", help="Input PowerPoint file (.pptx)") + parser.add_argument("output", help="Output JSON file for inventory") + parser.add_argument( + "--issues-only", + action="store_true", + help="Include only text shapes that have overflow or overlap issues", + ) + + args = parser.parse_args() + + input_path = Path(args.input) + if not input_path.exists(): + print(f"Error: Input file not found: {args.input}") + sys.exit(1) + + if not input_path.suffix.lower() == ".pptx": + print("Error: Input must be a PowerPoint file (.pptx)") + sys.exit(1) + + try: + print(f"Extracting text inventory from: {args.input}") + if args.issues_only: + print( + "Filtering to include only text shapes with issues (overflow/overlap)" + ) + inventory = extract_text_inventory(input_path, issues_only=args.issues_only) + + output_path = Path(args.output) + output_path.parent.mkdir(parents=True, exist_ok=True) + save_inventory(inventory, output_path) + + print(f"Output saved to: {args.output}") + + # Report statistics + total_slides = len(inventory) + total_shapes = sum(len(shapes) for shapes in inventory.values()) + if args.issues_only: + if total_shapes > 0: + print( + f"Found {total_shapes} text elements with issues in {total_slides} slides" + ) + else: + print("No issues discovered") + else: + print( + f"Found text in {total_slides} slides with {total_shapes} text elements" + ) + + except Exception as e: + print(f"Error processing presentation: {e}") + import traceback + + traceback.print_exc() + sys.exit(1) + + +@dataclass +class ShapeWithPosition: + """A shape with its absolute position on the slide.""" + + shape: BaseShape + absolute_left: int # in EMUs + absolute_top: int # in EMUs + + +class ParagraphData: + """Data structure for paragraph properties extracted from a PowerPoint paragraph.""" + + def __init__(self, paragraph: Any): + """Initialize from a PowerPoint paragraph object. + + Args: + paragraph: The PowerPoint paragraph object + """ + self.text: str = paragraph.text.strip() + self.bullet: bool = False + self.level: Optional[int] = None + self.alignment: Optional[str] = None + self.space_before: Optional[float] = None + self.space_after: Optional[float] = None + self.font_name: Optional[str] = None + self.font_size: Optional[float] = None + self.bold: Optional[bool] = None + self.italic: Optional[bool] = None + self.underline: Optional[bool] = None + self.color: Optional[str] = None + self.theme_color: Optional[str] = None + self.line_spacing: Optional[float] = None + + # Check for bullet formatting + if ( + hasattr(paragraph, "_p") + and paragraph._p is not None + and paragraph._p.pPr is not None + ): + pPr = paragraph._p.pPr + ns = "{http://schemas.openxmlformats.org/drawingml/2006/main}" + if ( + pPr.find(f"{ns}buChar") is not None + or pPr.find(f"{ns}buAutoNum") is not None + ): + self.bullet = True + if hasattr(paragraph, "level"): + self.level = paragraph.level + + # Add alignment if not LEFT (default) + if hasattr(paragraph, "alignment") and paragraph.alignment is not None: + alignment_map = { + PP_ALIGN.CENTER: "CENTER", + PP_ALIGN.RIGHT: "RIGHT", + PP_ALIGN.JUSTIFY: "JUSTIFY", + } + if paragraph.alignment in alignment_map: + self.alignment = alignment_map[paragraph.alignment] + + # Add spacing properties if set + if hasattr(paragraph, "space_before") and paragraph.space_before: + self.space_before = paragraph.space_before.pt + if hasattr(paragraph, "space_after") and paragraph.space_after: + self.space_after = paragraph.space_after.pt + + # Extract font properties from first run + if paragraph.runs: + first_run = paragraph.runs[0] + if hasattr(first_run, "font"): + font = first_run.font + if font.name: + self.font_name = font.name + if font.size: + self.font_size = font.size.pt + if font.bold is not None: + self.bold = font.bold + if font.italic is not None: + self.italic = font.italic + if font.underline is not None: + self.underline = font.underline + + # Handle color - both RGB and theme colors + try: + # Try RGB color first + if font.color.rgb: + self.color = str(font.color.rgb) + except (AttributeError, TypeError): + # Fall back to theme color + try: + if font.color.theme_color: + self.theme_color = font.color.theme_color.name + except (AttributeError, TypeError): + pass + + # Add line spacing if set + if hasattr(paragraph, "line_spacing") and paragraph.line_spacing is not None: + if hasattr(paragraph.line_spacing, "pt"): + self.line_spacing = round(paragraph.line_spacing.pt, 2) + else: + # Multiplier - convert to points + font_size = self.font_size if self.font_size else 12.0 + self.line_spacing = round(paragraph.line_spacing * font_size, 2) + + def to_dict(self) -> ParagraphDict: + """Convert to dictionary for JSON serialization, excluding None values.""" + result: ParagraphDict = {"text": self.text} + + # Add optional fields only if they have values + if self.bullet: + result["bullet"] = self.bullet + if self.level is not None: + result["level"] = self.level + if self.alignment: + result["alignment"] = self.alignment + if self.space_before is not None: + result["space_before"] = self.space_before + if self.space_after is not None: + result["space_after"] = self.space_after + if self.font_name: + result["font_name"] = self.font_name + if self.font_size is not None: + result["font_size"] = self.font_size + if self.bold is not None: + result["bold"] = self.bold + if self.italic is not None: + result["italic"] = self.italic + if self.underline is not None: + result["underline"] = self.underline + if self.color: + result["color"] = self.color + if self.theme_color: + result["theme_color"] = self.theme_color + if self.line_spacing is not None: + result["line_spacing"] = self.line_spacing + + return result + + +class ShapeData: + """Data structure for shape properties extracted from a PowerPoint shape.""" + + @staticmethod + def emu_to_inches(emu: int) -> float: + """Convert EMUs (English Metric Units) to inches.""" + return emu / 914400.0 + + @staticmethod + def inches_to_pixels(inches: float, dpi: int = 96) -> int: + """Convert inches to pixels at given DPI.""" + return int(inches * dpi) + + @staticmethod + def get_font_path(font_name: str) -> Optional[str]: + """Get the font file path for a given font name. + + Args: + font_name: Name of the font (e.g., 'Arial', 'Calibri') + + Returns: + Path to the font file, or None if not found + """ + system = platform.system() + + # Common font file variations to try + font_variations = [ + font_name, + font_name.lower(), + font_name.replace(" ", ""), + font_name.replace(" ", "-"), + ] + + # Define font directories and extensions by platform + if system == "Darwin": # macOS + font_dirs = [ + "/System/Library/Fonts/", + "/Library/Fonts/", + "~/Library/Fonts/", + ] + extensions = [".ttf", ".otf", ".ttc", ".dfont"] + else: # Linux + font_dirs = [ + "/usr/share/fonts/truetype/", + "/usr/local/share/fonts/", + "~/.fonts/", + ] + extensions = [".ttf", ".otf"] + + # Try to find the font file + from pathlib import Path + + for font_dir in font_dirs: + font_dir_path = Path(font_dir).expanduser() + if not font_dir_path.exists(): + continue + + # First try exact matches + for variant in font_variations: + for ext in extensions: + font_path = font_dir_path / f"{variant}{ext}" + if font_path.exists(): + return str(font_path) + + # Then try fuzzy matching - find files containing the font name + try: + for file_path in font_dir_path.iterdir(): + if file_path.is_file(): + file_name_lower = file_path.name.lower() + font_name_lower = font_name.lower().replace(" ", "") + if font_name_lower in file_name_lower and any( + file_name_lower.endswith(ext) for ext in extensions + ): + return str(file_path) + except (OSError, PermissionError): + continue + + return None + + @staticmethod + def get_slide_dimensions(slide: Any) -> tuple[Optional[int], Optional[int]]: + """Get slide dimensions from slide object. + + Args: + slide: Slide object + + Returns: + Tuple of (width_emu, height_emu) or (None, None) if not found + """ + try: + prs = slide.part.package.presentation_part.presentation + return prs.slide_width, prs.slide_height + except (AttributeError, TypeError): + return None, None + + @staticmethod + def get_default_font_size(shape: BaseShape, slide_layout: Any) -> Optional[float]: + """Extract default font size from slide layout for a placeholder shape. + + Args: + shape: Placeholder shape + slide_layout: Slide layout containing the placeholder definition + + Returns: + Default font size in points, or None if not found + """ + try: + if not hasattr(shape, "placeholder_format"): + return None + + shape_type = shape.placeholder_format.type # type: ignore + for layout_placeholder in slide_layout.placeholders: + if layout_placeholder.placeholder_format.type == shape_type: + # Find first defRPr element with sz (size) attribute + for elem in layout_placeholder.element.iter(): + if "defRPr" in elem.tag and (sz := elem.get("sz")): + return float(sz) / 100.0 # Convert EMUs to points + break + except Exception: + pass + return None + + def __init__( + self, + shape: BaseShape, + absolute_left: Optional[int] = None, + absolute_top: Optional[int] = None, + slide: Optional[Any] = None, + ): + """Initialize from a PowerPoint shape object. + + Args: + shape: The PowerPoint shape object (should be pre-validated) + absolute_left: Absolute left position in EMUs (for shapes in groups) + absolute_top: Absolute top position in EMUs (for shapes in groups) + slide: Optional slide object to get dimensions and layout information + """ + self.shape = shape # Store reference to original shape + self.shape_id: str = "" # Will be set after sorting + + # Get slide dimensions from slide object + self.slide_width_emu, self.slide_height_emu = ( + self.get_slide_dimensions(slide) if slide else (None, None) + ) + + # Get placeholder type if applicable + self.placeholder_type: Optional[str] = None + self.default_font_size: Optional[float] = None + if hasattr(shape, "is_placeholder") and shape.is_placeholder: # type: ignore + if shape.placeholder_format and shape.placeholder_format.type: # type: ignore + self.placeholder_type = ( + str(shape.placeholder_format.type).split(".")[-1].split(" ")[0] # type: ignore + ) + + # Get default font size from layout + if slide and hasattr(slide, "slide_layout"): + self.default_font_size = self.get_default_font_size( + shape, slide.slide_layout + ) + + # Get position information + # Use absolute positions if provided (for shapes in groups), otherwise use shape's position + left_emu = ( + absolute_left + if absolute_left is not None + else (shape.left if hasattr(shape, "left") else 0) + ) + top_emu = ( + absolute_top + if absolute_top is not None + else (shape.top if hasattr(shape, "top") else 0) + ) + + self.left: float = round(self.emu_to_inches(left_emu), 2) # type: ignore + self.top: float = round(self.emu_to_inches(top_emu), 2) # type: ignore + self.width: float = round( + self.emu_to_inches(shape.width if hasattr(shape, "width") else 0), + 2, # type: ignore + ) + self.height: float = round( + self.emu_to_inches(shape.height if hasattr(shape, "height") else 0), + 2, # type: ignore + ) + + # Store EMU positions for overflow calculations + self.left_emu = left_emu + self.top_emu = top_emu + self.width_emu = shape.width if hasattr(shape, "width") else 0 + self.height_emu = shape.height if hasattr(shape, "height") else 0 + + # Calculate overflow status + self.frame_overflow_bottom: Optional[float] = None + self.slide_overflow_right: Optional[float] = None + self.slide_overflow_bottom: Optional[float] = None + self.overlapping_shapes: Dict[ + str, float + ] = {} # Dict of shape_id -> overlap area in sq inches + self.warnings: List[str] = [] + self._estimate_frame_overflow() + self._calculate_slide_overflow() + self._detect_bullet_issues() + + @property + def paragraphs(self) -> List[ParagraphData]: + """Calculate paragraphs from the shape's text frame.""" + if not self.shape or not hasattr(self.shape, "text_frame"): + return [] + + paragraphs = [] + for paragraph in self.shape.text_frame.paragraphs: # type: ignore + if paragraph.text.strip(): + paragraphs.append(ParagraphData(paragraph)) + return paragraphs + + def _get_default_font_size(self) -> int: + """Get default font size from theme text styles or use conservative default.""" + try: + if not ( + hasattr(self.shape, "part") and hasattr(self.shape.part, "slide_layout") + ): + return 14 + + slide_master = self.shape.part.slide_layout.slide_master # type: ignore + if not hasattr(slide_master, "element"): + return 14 + + # Determine theme style based on placeholder type + style_name = "bodyStyle" # Default + if self.placeholder_type and "TITLE" in self.placeholder_type: + style_name = "titleStyle" + + # Find font size in theme styles + for child in slide_master.element.iter(): + tag = child.tag.split("}")[-1] if "}" in child.tag else child.tag + if tag == style_name: + for elem in child.iter(): + if "sz" in elem.attrib: + return int(elem.attrib["sz"]) // 100 + except Exception: + pass + + return 14 # Conservative default for body text + + def _get_usable_dimensions(self, text_frame) -> Tuple[int, int]: + """Get usable width and height in pixels after accounting for margins.""" + # Default PowerPoint margins in inches + margins = {"top": 0.05, "bottom": 0.05, "left": 0.1, "right": 0.1} + + # Override with actual margins if set + if hasattr(text_frame, "margin_top") and text_frame.margin_top: + margins["top"] = self.emu_to_inches(text_frame.margin_top) + if hasattr(text_frame, "margin_bottom") and text_frame.margin_bottom: + margins["bottom"] = self.emu_to_inches(text_frame.margin_bottom) + if hasattr(text_frame, "margin_left") and text_frame.margin_left: + margins["left"] = self.emu_to_inches(text_frame.margin_left) + if hasattr(text_frame, "margin_right") and text_frame.margin_right: + margins["right"] = self.emu_to_inches(text_frame.margin_right) + + # Calculate usable area + usable_width = self.width - margins["left"] - margins["right"] + usable_height = self.height - margins["top"] - margins["bottom"] + + # Convert to pixels + return ( + self.inches_to_pixels(usable_width), + self.inches_to_pixels(usable_height), + ) + + def _wrap_text_line(self, line: str, max_width_px: int, draw, font) -> List[str]: + """Wrap a single line of text to fit within max_width_px.""" + if not line: + return [""] + + # Use textlength for efficient width calculation + if draw.textlength(line, font=font) <= max_width_px: + return [line] + + # Need to wrap - split into words + wrapped = [] + words = line.split(" ") + current_line = "" + + for word in words: + test_line = current_line + (" " if current_line else "") + word + if draw.textlength(test_line, font=font) <= max_width_px: + current_line = test_line + else: + if current_line: + wrapped.append(current_line) + current_line = word + + if current_line: + wrapped.append(current_line) + + return wrapped + + def _estimate_frame_overflow(self) -> None: + """Estimate if text overflows the shape bounds using PIL text measurement.""" + if not self.shape or not hasattr(self.shape, "text_frame"): + return + + text_frame = self.shape.text_frame # type: ignore + if not text_frame or not text_frame.paragraphs: + return + + # Get usable dimensions after accounting for margins + usable_width_px, usable_height_px = self._get_usable_dimensions(text_frame) + if usable_width_px <= 0 or usable_height_px <= 0: + return + + # Set up PIL for text measurement + dummy_img = Image.new("RGB", (1, 1)) + draw = ImageDraw.Draw(dummy_img) + + # Get default font size from placeholder or use conservative estimate + default_font_size = self._get_default_font_size() + + # Calculate total height of all paragraphs + total_height_px = 0 + + for para_idx, paragraph in enumerate(text_frame.paragraphs): + if not paragraph.text.strip(): + continue + + para_data = ParagraphData(paragraph) + + # Load font for this paragraph + font_name = para_data.font_name or "Arial" + font_size = int(para_data.font_size or default_font_size) + + font = None + font_path = self.get_font_path(font_name) + if font_path: + try: + font = ImageFont.truetype(font_path, size=font_size) + except Exception: + font = ImageFont.load_default() + else: + font = ImageFont.load_default() + + # Wrap all lines in this paragraph + all_wrapped_lines = [] + for line in paragraph.text.split("\n"): + wrapped = self._wrap_text_line(line, usable_width_px, draw, font) + all_wrapped_lines.extend(wrapped) + + if all_wrapped_lines: + # Calculate line height + if para_data.line_spacing: + # Custom line spacing explicitly set + line_height_px = para_data.line_spacing * 96 / 72 + else: + # PowerPoint default single spacing (1.0x font size) + line_height_px = font_size * 96 / 72 + + # Add space_before (except first paragraph) + if para_idx > 0 and para_data.space_before: + total_height_px += para_data.space_before * 96 / 72 + + # Add paragraph text height + total_height_px += len(all_wrapped_lines) * line_height_px + + # Add space_after + if para_data.space_after: + total_height_px += para_data.space_after * 96 / 72 + + # Check for overflow (ignore negligible overflows <= 0.05") + if total_height_px > usable_height_px: + overflow_px = total_height_px - usable_height_px + overflow_inches = round(overflow_px / 96.0, 2) + if overflow_inches > 0.05: # Only report significant overflows + self.frame_overflow_bottom = overflow_inches + + def _calculate_slide_overflow(self) -> None: + """Calculate if shape overflows the slide boundaries.""" + if self.slide_width_emu is None or self.slide_height_emu is None: + return + + # Check right overflow (ignore negligible overflows <= 0.01") + right_edge_emu = self.left_emu + self.width_emu + if right_edge_emu > self.slide_width_emu: + overflow_emu = right_edge_emu - self.slide_width_emu + overflow_inches = round(self.emu_to_inches(overflow_emu), 2) + if overflow_inches > 0.01: # Only report significant overflows + self.slide_overflow_right = overflow_inches + + # Check bottom overflow (ignore negligible overflows <= 0.01") + bottom_edge_emu = self.top_emu + self.height_emu + if bottom_edge_emu > self.slide_height_emu: + overflow_emu = bottom_edge_emu - self.slide_height_emu + overflow_inches = round(self.emu_to_inches(overflow_emu), 2) + if overflow_inches > 0.01: # Only report significant overflows + self.slide_overflow_bottom = overflow_inches + + def _detect_bullet_issues(self) -> None: + """Detect bullet point formatting issues in paragraphs.""" + if not self.shape or not hasattr(self.shape, "text_frame"): + return + + text_frame = self.shape.text_frame # type: ignore + if not text_frame or not text_frame.paragraphs: + return + + # Common bullet symbols that indicate manual bullets + bullet_symbols = ["•", "●", "○"] + + for paragraph in text_frame.paragraphs: + text = paragraph.text.strip() + # Check for manual bullet symbols + if text and any(text.startswith(symbol + " ") for symbol in bullet_symbols): + self.warnings.append( + "manual_bullet_symbol: use proper bullet formatting" + ) + break + + @property + def has_any_issues(self) -> bool: + """Check if shape has any issues (overflow, overlap, or warnings).""" + return ( + self.frame_overflow_bottom is not None + or self.slide_overflow_right is not None + or self.slide_overflow_bottom is not None + or len(self.overlapping_shapes) > 0 + or len(self.warnings) > 0 + ) + + def to_dict(self) -> ShapeDict: + """Convert to dictionary for JSON serialization.""" + result: ShapeDict = { + "left": self.left, + "top": self.top, + "width": self.width, + "height": self.height, + } + + # Add optional fields if present + if self.placeholder_type: + result["placeholder_type"] = self.placeholder_type + + if self.default_font_size: + result["default_font_size"] = self.default_font_size + + # Add overflow information only if there is overflow + overflow_data = {} + + # Add frame overflow if present + if self.frame_overflow_bottom is not None: + overflow_data["frame"] = {"overflow_bottom": self.frame_overflow_bottom} + + # Add slide overflow if present + slide_overflow = {} + if self.slide_overflow_right is not None: + slide_overflow["overflow_right"] = self.slide_overflow_right + if self.slide_overflow_bottom is not None: + slide_overflow["overflow_bottom"] = self.slide_overflow_bottom + if slide_overflow: + overflow_data["slide"] = slide_overflow + + # Only add overflow field if there is overflow + if overflow_data: + result["overflow"] = overflow_data + + # Add overlap field if there are overlapping shapes + if self.overlapping_shapes: + result["overlap"] = {"overlapping_shapes": self.overlapping_shapes} + + # Add warnings field if there are warnings + if self.warnings: + result["warnings"] = self.warnings + + # Add paragraphs after placeholder_type + result["paragraphs"] = [para.to_dict() for para in self.paragraphs] + + return result + + +def is_valid_shape(shape: BaseShape) -> bool: + """Check if a shape contains meaningful text content.""" + # Must have a text frame with content + if not hasattr(shape, "text_frame") or not shape.text_frame: # type: ignore + return False + + text = shape.text_frame.text.strip() # type: ignore + if not text: + return False + + # Skip slide numbers and numeric footers + if hasattr(shape, "is_placeholder") and shape.is_placeholder: # type: ignore + if shape.placeholder_format and shape.placeholder_format.type: # type: ignore + placeholder_type = ( + str(shape.placeholder_format.type).split(".")[-1].split(" ")[0] # type: ignore + ) + if placeholder_type == "SLIDE_NUMBER": + return False + if placeholder_type == "FOOTER" and text.isdigit(): + return False + + return True + + +def collect_shapes_with_absolute_positions( + shape: BaseShape, parent_left: int = 0, parent_top: int = 0 +) -> List[ShapeWithPosition]: + """Recursively collect all shapes with valid text, calculating absolute positions. + + For shapes within groups, their positions are relative to the group. + This function calculates the absolute position on the slide by accumulating + parent group offsets. + + Args: + shape: The shape to process + parent_left: Accumulated left offset from parent groups (in EMUs) + parent_top: Accumulated top offset from parent groups (in EMUs) + + Returns: + List of ShapeWithPosition objects with absolute positions + """ + if hasattr(shape, "shapes"): # GroupShape + result = [] + # Get this group's position + group_left = shape.left if hasattr(shape, "left") else 0 + group_top = shape.top if hasattr(shape, "top") else 0 + + # Calculate absolute position for this group + abs_group_left = parent_left + group_left + abs_group_top = parent_top + group_top + + # Process children with accumulated offsets + for child in shape.shapes: # type: ignore + result.extend( + collect_shapes_with_absolute_positions( + child, abs_group_left, abs_group_top + ) + ) + return result + + # Regular shape - check if it has valid text + if is_valid_shape(shape): + # Calculate absolute position + shape_left = shape.left if hasattr(shape, "left") else 0 + shape_top = shape.top if hasattr(shape, "top") else 0 + + return [ + ShapeWithPosition( + shape=shape, + absolute_left=parent_left + shape_left, + absolute_top=parent_top + shape_top, + ) + ] + + return [] + + +def sort_shapes_by_position(shapes: List[ShapeData]) -> List[ShapeData]: + """Sort shapes by visual position (top-to-bottom, left-to-right). + + Shapes within 0.5 inches vertically are considered on the same row. + """ + if not shapes: + return shapes + + # Sort by top position first + shapes = sorted(shapes, key=lambda s: (s.top, s.left)) + + # Group shapes by row (within 0.5 inches vertically) + result = [] + row = [shapes[0]] + row_top = shapes[0].top + + for shape in shapes[1:]: + if abs(shape.top - row_top) <= 0.5: + row.append(shape) + else: + # Sort current row by left position and add to result + result.extend(sorted(row, key=lambda s: s.left)) + row = [shape] + row_top = shape.top + + # Don't forget the last row + result.extend(sorted(row, key=lambda s: s.left)) + return result + + +def calculate_overlap( + rect1: Tuple[float, float, float, float], + rect2: Tuple[float, float, float, float], + tolerance: float = 0.05, +) -> Tuple[bool, float]: + """Calculate if and how much two rectangles overlap. + + Args: + rect1: (left, top, width, height) of first rectangle in inches + rect2: (left, top, width, height) of second rectangle in inches + tolerance: Minimum overlap in inches to consider as overlapping (default: 0.05") + + Returns: + Tuple of (overlaps, overlap_area) where: + - overlaps: True if rectangles overlap by more than tolerance + - overlap_area: Area of overlap in square inches + """ + left1, top1, w1, h1 = rect1 + left2, top2, w2, h2 = rect2 + + # Calculate overlap dimensions + overlap_width = min(left1 + w1, left2 + w2) - max(left1, left2) + overlap_height = min(top1 + h1, top2 + h2) - max(top1, top2) + + # Check if there's meaningful overlap (more than tolerance) + if overlap_width > tolerance and overlap_height > tolerance: + # Calculate overlap area in square inches + overlap_area = overlap_width * overlap_height + return True, round(overlap_area, 2) + + return False, 0 + + +def detect_overlaps(shapes: List[ShapeData]) -> None: + """Detect overlapping shapes and update their overlapping_shapes dictionaries. + + This function requires each ShapeData to have its shape_id already set. + It modifies the shapes in-place, adding shape IDs with overlap areas in square inches. + + Args: + shapes: List of ShapeData objects with shape_id attributes set + """ + n = len(shapes) + + # Compare each pair of shapes + for i in range(n): + for j in range(i + 1, n): + shape1 = shapes[i] + shape2 = shapes[j] + + # Ensure shape IDs are set + assert shape1.shape_id, f"Shape at index {i} has no shape_id" + assert shape2.shape_id, f"Shape at index {j} has no shape_id" + + rect1 = (shape1.left, shape1.top, shape1.width, shape1.height) + rect2 = (shape2.left, shape2.top, shape2.width, shape2.height) + + overlaps, overlap_area = calculate_overlap(rect1, rect2) + + if overlaps: + # Add shape IDs with overlap area in square inches + shape1.overlapping_shapes[shape2.shape_id] = overlap_area + shape2.overlapping_shapes[shape1.shape_id] = overlap_area + + +def extract_text_inventory( + pptx_path: Path, prs: Optional[Any] = None, issues_only: bool = False +) -> InventoryData: + """Extract text content from all slides in a PowerPoint presentation. + + Args: + pptx_path: Path to the PowerPoint file + prs: Optional Presentation object to use. If not provided, will load from pptx_path. + issues_only: If True, only include shapes that have overflow or overlap issues + + Returns a nested dictionary: {slide-N: {shape-N: ShapeData}} + Shapes are sorted by visual position (top-to-bottom, left-to-right). + The ShapeData objects contain the full shape information and can be + converted to dictionaries for JSON serialization using to_dict(). + """ + if prs is None: + prs = Presentation(str(pptx_path)) + inventory: InventoryData = {} + + for slide_idx, slide in enumerate(prs.slides): + # Collect all valid shapes from this slide with absolute positions + shapes_with_positions = [] + for shape in slide.shapes: # type: ignore + shapes_with_positions.extend(collect_shapes_with_absolute_positions(shape)) + + if not shapes_with_positions: + continue + + # Convert to ShapeData with absolute positions and slide reference + shape_data_list = [ + ShapeData( + swp.shape, + swp.absolute_left, + swp.absolute_top, + slide, + ) + for swp in shapes_with_positions + ] + + # Sort by visual position and assign stable IDs in one step + sorted_shapes = sort_shapes_by_position(shape_data_list) + for idx, shape_data in enumerate(sorted_shapes): + shape_data.shape_id = f"shape-{idx}" + + # Detect overlaps using the stable shape IDs + if len(sorted_shapes) > 1: + detect_overlaps(sorted_shapes) + + # Filter for issues only if requested (after overlap detection) + if issues_only: + sorted_shapes = [sd for sd in sorted_shapes if sd.has_any_issues] + + if not sorted_shapes: + continue + + # Create slide inventory using the stable shape IDs + inventory[f"slide-{slide_idx}"] = { + shape_data.shape_id: shape_data for shape_data in sorted_shapes + } + + return inventory + + +def get_inventory_as_dict(pptx_path: Path, issues_only: bool = False) -> InventoryDict: + """Extract text inventory and return as JSON-serializable dictionaries. + + This is a convenience wrapper around extract_text_inventory that returns + dictionaries instead of ShapeData objects, useful for testing and direct + JSON serialization. + + Args: + pptx_path: Path to the PowerPoint file + issues_only: If True, only include shapes that have overflow or overlap issues + + Returns: + Nested dictionary with all data serialized for JSON + """ + inventory = extract_text_inventory(pptx_path, issues_only=issues_only) + + # Convert ShapeData objects to dictionaries + dict_inventory: InventoryDict = {} + for slide_key, shapes in inventory.items(): + dict_inventory[slide_key] = { + shape_key: shape_data.to_dict() for shape_key, shape_data in shapes.items() + } + + return dict_inventory + + +def save_inventory(inventory: InventoryData, output_path: Path) -> None: + """Save inventory to JSON file with proper formatting. + + Converts ShapeData objects to dictionaries for JSON serialization. + """ + # Convert ShapeData objects to dictionaries + json_inventory: InventoryDict = {} + for slide_key, shapes in inventory.items(): + json_inventory[slide_key] = { + shape_key: shape_data.to_dict() for shape_key, shape_data in shapes.items() + } + + with open(output_path, "w", encoding="utf-8") as f: + json.dump(json_inventory, f, indent=2, ensure_ascii=False) + + +if __name__ == "__main__": + main() diff --git a/scripts/rearrange.py b/scripts/rearrange.py new file mode 100755 index 0000000..2519911 --- /dev/null +++ b/scripts/rearrange.py @@ -0,0 +1,231 @@ +#!/usr/bin/env python3 +""" +Rearrange PowerPoint slides based on a sequence of indices. + +Usage: + python rearrange.py template.pptx output.pptx 0,34,34,50,52 + +This will create output.pptx using slides from template.pptx in the specified order. +Slides can be repeated (e.g., 34 appears twice). +""" + +import argparse +import shutil +import sys +from copy import deepcopy +from pathlib import Path + +import six +from pptx import Presentation + + +def main(): + parser = argparse.ArgumentParser( + description="Rearrange PowerPoint slides based on a sequence of indices.", + formatter_class=argparse.RawDescriptionHelpFormatter, + epilog=""" +Examples: + python rearrange.py template.pptx output.pptx 0,34,34,50,52 + Creates output.pptx using slides 0, 34 (twice), 50, and 52 from template.pptx + + python rearrange.py template.pptx output.pptx 5,3,1,2,4 + Creates output.pptx with slides reordered as specified + +Note: Slide indices are 0-based (first slide is 0, second is 1, etc.) + """, + ) + + parser.add_argument("template", help="Path to template PPTX file") + parser.add_argument("output", help="Path for output PPTX file") + parser.add_argument( + "sequence", help="Comma-separated sequence of slide indices (0-based)" + ) + + args = parser.parse_args() + + # Parse the slide sequence + try: + slide_sequence = [int(x.strip()) for x in args.sequence.split(",")] + except ValueError: + print( + "Error: Invalid sequence format. Use comma-separated integers (e.g., 0,34,34,50,52)" + ) + sys.exit(1) + + # Check template exists + template_path = Path(args.template) + if not template_path.exists(): + print(f"Error: Template file not found: {args.template}") + sys.exit(1) + + # Create output directory if needed + output_path = Path(args.output) + output_path.parent.mkdir(parents=True, exist_ok=True) + + try: + rearrange_presentation(template_path, output_path, slide_sequence) + except ValueError as e: + print(f"Error: {e}") + sys.exit(1) + except Exception as e: + print(f"Error processing presentation: {e}") + sys.exit(1) + + +def duplicate_slide(pres, index): + """Duplicate a slide in the presentation.""" + source = pres.slides[index] + + # Use source's layout to preserve formatting + new_slide = pres.slides.add_slide(source.slide_layout) + + # Collect all image and media relationships from the source slide + image_rels = {} + for rel_id, rel in six.iteritems(source.part.rels): + if "image" in rel.reltype or "media" in rel.reltype: + image_rels[rel_id] = rel + + # CRITICAL: Clear placeholder shapes to avoid duplicates + for shape in new_slide.shapes: + sp = shape.element + sp.getparent().remove(sp) + + # Copy all shapes from source + for shape in source.shapes: + el = shape.element + new_el = deepcopy(el) + new_slide.shapes._spTree.insert_element_before(new_el, "p:extLst") + + # Handle picture shapes - need to update the blip reference + # Look for all blip elements (they can be in pic or other contexts) + # Using the element's own xpath method without namespaces argument + blips = new_el.xpath(".//a:blip[@r:embed]") + for blip in blips: + old_rId = blip.get( + "{http://schemas.openxmlformats.org/officeDocument/2006/relationships}embed" + ) + if old_rId in image_rels: + # Create a new relationship in the destination slide for this image + old_rel = image_rels[old_rId] + # get_or_add returns the rId directly, or adds and returns new rId + new_rId = new_slide.part.rels.get_or_add( + old_rel.reltype, old_rel._target + ) + # Update the blip's embed reference to use the new relationship ID + blip.set( + "{http://schemas.openxmlformats.org/officeDocument/2006/relationships}embed", + new_rId, + ) + + # Copy any additional image/media relationships that might be referenced elsewhere + for rel_id, rel in image_rels.items(): + try: + new_slide.part.rels.get_or_add(rel.reltype, rel._target) + except Exception: + pass # Relationship might already exist + + return new_slide + + +def delete_slide(pres, index): + """Delete a slide from the presentation.""" + rId = pres.slides._sldIdLst[index].rId + pres.part.drop_rel(rId) + del pres.slides._sldIdLst[index] + + +def reorder_slides(pres, slide_index, target_index): + """Move a slide from one position to another.""" + slides = pres.slides._sldIdLst + + # Remove slide element from current position + slide_element = slides[slide_index] + slides.remove(slide_element) + + # Insert at target position + slides.insert(target_index, slide_element) + + +def rearrange_presentation(template_path, output_path, slide_sequence): + """ + Create a new presentation with slides from template in specified order. + + Args: + template_path: Path to template PPTX file + output_path: Path for output PPTX file + slide_sequence: List of slide indices (0-based) to include + """ + # Copy template to preserve dimensions and theme + if template_path != output_path: + shutil.copy2(template_path, output_path) + prs = Presentation(output_path) + else: + prs = Presentation(template_path) + + total_slides = len(prs.slides) + + # Validate indices + for idx in slide_sequence: + if idx < 0 or idx >= total_slides: + raise ValueError(f"Slide index {idx} out of range (0-{total_slides - 1})") + + # Track original slides and their duplicates + slide_map = [] # List of actual slide indices for final presentation + duplicated = {} # Track duplicates: original_idx -> [duplicate_indices] + + # Step 1: DUPLICATE repeated slides + print(f"Processing {len(slide_sequence)} slides from template...") + for i, template_idx in enumerate(slide_sequence): + if template_idx in duplicated and duplicated[template_idx]: + # Already duplicated this slide, use the duplicate + slide_map.append(duplicated[template_idx].pop(0)) + print(f" [{i}] Using duplicate of slide {template_idx}") + elif slide_sequence.count(template_idx) > 1 and template_idx not in duplicated: + # First occurrence of a repeated slide - create duplicates + slide_map.append(template_idx) + duplicates = [] + count = slide_sequence.count(template_idx) - 1 + print( + f" [{i}] Using original slide {template_idx}, creating {count} duplicate(s)" + ) + for _ in range(count): + duplicate_slide(prs, template_idx) + duplicates.append(len(prs.slides) - 1) + duplicated[template_idx] = duplicates + else: + # Unique slide or first occurrence already handled, use original + slide_map.append(template_idx) + print(f" [{i}] Using original slide {template_idx}") + + # Step 2: DELETE unwanted slides (work backwards) + slides_to_keep = set(slide_map) + print(f"\nDeleting {len(prs.slides) - len(slides_to_keep)} unused slides...") + for i in range(len(prs.slides) - 1, -1, -1): + if i not in slides_to_keep: + delete_slide(prs, i) + # Update slide_map indices after deletion + slide_map = [idx - 1 if idx > i else idx for idx in slide_map] + + # Step 3: REORDER to final sequence + print(f"Reordering {len(slide_map)} slides to final sequence...") + for target_pos in range(len(slide_map)): + # Find which slide should be at target_pos + current_pos = slide_map[target_pos] + if current_pos != target_pos: + reorder_slides(prs, current_pos, target_pos) + # Update slide_map: the move shifts other slides + for i in range(len(slide_map)): + if slide_map[i] > current_pos and slide_map[i] <= target_pos: + slide_map[i] -= 1 + elif slide_map[i] < current_pos and slide_map[i] >= target_pos: + slide_map[i] += 1 + slide_map[target_pos] = target_pos + + # Save the presentation + prs.save(output_path) + print(f"\nSaved rearranged presentation to: {output_path}") + print(f"Final presentation has {len(prs.slides)} slides") + + +if __name__ == "__main__": + main() diff --git a/scripts/replace.py b/scripts/replace.py new file mode 100755 index 0000000..8f7a8b1 --- /dev/null +++ b/scripts/replace.py @@ -0,0 +1,385 @@ +#!/usr/bin/env python3 +"""Apply text replacements to PowerPoint presentation. + +Usage: + python replace.py + +The replacements JSON should have the structure output by inventory.py. +ALL text shapes identified by inventory.py will have their text cleared +unless "paragraphs" is specified in the replacements for that shape. +""" + +import json +import sys +from pathlib import Path +from typing import Any, Dict, List + +from inventory import InventoryData, extract_text_inventory +from pptx import Presentation +from pptx.dml.color import RGBColor +from pptx.enum.dml import MSO_THEME_COLOR +from pptx.enum.text import PP_ALIGN +from pptx.oxml.xmlchemy import OxmlElement +from pptx.util import Pt + + +def clear_paragraph_bullets(paragraph): + """Clear bullet formatting from a paragraph.""" + pPr = paragraph._element.get_or_add_pPr() + + # Remove existing bullet elements + for child in list(pPr): + if ( + child.tag.endswith("buChar") + or child.tag.endswith("buNone") + or child.tag.endswith("buAutoNum") + or child.tag.endswith("buFont") + ): + pPr.remove(child) + + return pPr + + +def apply_paragraph_properties(paragraph, para_data: Dict[str, Any]): + """Apply formatting properties to a paragraph.""" + # Get the text but don't set it on paragraph directly yet + text = para_data.get("text", "") + + # Get or create paragraph properties + pPr = clear_paragraph_bullets(paragraph) + + # Handle bullet formatting + if para_data.get("bullet", False): + level = para_data.get("level", 0) + paragraph.level = level + + # Calculate font-proportional indentation + font_size = para_data.get("font_size", 18.0) + level_indent_emu = int((font_size * (1.6 + level * 1.6)) * 12700) + hanging_indent_emu = int(-font_size * 0.8 * 12700) + + # Set indentation + pPr.attrib["marL"] = str(level_indent_emu) + pPr.attrib["indent"] = str(hanging_indent_emu) + + # Add bullet character + buChar = OxmlElement("a:buChar") + buChar.set("char", "•") + pPr.append(buChar) + + # Default to left alignment for bullets if not specified + if "alignment" not in para_data: + paragraph.alignment = PP_ALIGN.LEFT + else: + # Remove indentation for non-bullet text + pPr.attrib["marL"] = "0" + pPr.attrib["indent"] = "0" + + # Add buNone element + buNone = OxmlElement("a:buNone") + pPr.insert(0, buNone) + + # Apply alignment + if "alignment" in para_data: + alignment_map = { + "LEFT": PP_ALIGN.LEFT, + "CENTER": PP_ALIGN.CENTER, + "RIGHT": PP_ALIGN.RIGHT, + "JUSTIFY": PP_ALIGN.JUSTIFY, + } + if para_data["alignment"] in alignment_map: + paragraph.alignment = alignment_map[para_data["alignment"]] + + # Apply spacing + if "space_before" in para_data: + paragraph.space_before = Pt(para_data["space_before"]) + if "space_after" in para_data: + paragraph.space_after = Pt(para_data["space_after"]) + if "line_spacing" in para_data: + paragraph.line_spacing = Pt(para_data["line_spacing"]) + + # Apply run-level formatting + if not paragraph.runs: + run = paragraph.add_run() + run.text = text + else: + run = paragraph.runs[0] + run.text = text + + # Apply font properties + apply_font_properties(run, para_data) + + +def apply_font_properties(run, para_data: Dict[str, Any]): + """Apply font properties to a text run.""" + if "bold" in para_data: + run.font.bold = para_data["bold"] + if "italic" in para_data: + run.font.italic = para_data["italic"] + if "underline" in para_data: + run.font.underline = para_data["underline"] + if "font_size" in para_data: + run.font.size = Pt(para_data["font_size"]) + if "font_name" in para_data: + run.font.name = para_data["font_name"] + + # Apply color - prefer RGB, fall back to theme_color + if "color" in para_data: + color_hex = para_data["color"].lstrip("#") + if len(color_hex) == 6: + r = int(color_hex[0:2], 16) + g = int(color_hex[2:4], 16) + b = int(color_hex[4:6], 16) + run.font.color.rgb = RGBColor(r, g, b) + elif "theme_color" in para_data: + # Get theme color by name (e.g., "DARK_1", "ACCENT_1") + theme_name = para_data["theme_color"] + try: + run.font.color.theme_color = getattr(MSO_THEME_COLOR, theme_name) + except AttributeError: + print(f" WARNING: Unknown theme color name '{theme_name}'") + + +def detect_frame_overflow(inventory: InventoryData) -> Dict[str, Dict[str, float]]: + """Detect text overflow in shapes (text exceeding shape bounds). + + Returns dict of slide_key -> shape_key -> overflow_inches. + Only includes shapes that have text overflow. + """ + overflow_map = {} + + for slide_key, shapes_dict in inventory.items(): + for shape_key, shape_data in shapes_dict.items(): + # Check for frame overflow (text exceeding shape bounds) + if shape_data.frame_overflow_bottom is not None: + if slide_key not in overflow_map: + overflow_map[slide_key] = {} + overflow_map[slide_key][shape_key] = shape_data.frame_overflow_bottom + + return overflow_map + + +def validate_replacements(inventory: InventoryData, replacements: Dict) -> List[str]: + """Validate that all shapes in replacements exist in inventory. + + Returns list of error messages. + """ + errors = [] + + for slide_key, shapes_data in replacements.items(): + if not slide_key.startswith("slide-"): + continue + + # Check if slide exists + if slide_key not in inventory: + errors.append(f"Slide '{slide_key}' not found in inventory") + continue + + # Check each shape + for shape_key in shapes_data.keys(): + if shape_key not in inventory[slide_key]: + # Find shapes without replacements defined and show their content + unused_with_content = [] + for k in inventory[slide_key].keys(): + if k not in shapes_data: + shape_data = inventory[slide_key][k] + # Get text from paragraphs as preview + paragraphs = shape_data.paragraphs + if paragraphs and paragraphs[0].text: + first_text = paragraphs[0].text[:50] + if len(paragraphs[0].text) > 50: + first_text += "..." + unused_with_content.append(f"{k} ('{first_text}')") + else: + unused_with_content.append(k) + + errors.append( + f"Shape '{shape_key}' not found on '{slide_key}'. " + f"Shapes without replacements: {', '.join(sorted(unused_with_content)) if unused_with_content else 'none'}" + ) + + return errors + + +def check_duplicate_keys(pairs): + """Check for duplicate keys when loading JSON.""" + result = {} + for key, value in pairs: + if key in result: + raise ValueError(f"Duplicate key found in JSON: '{key}'") + result[key] = value + return result + + +def apply_replacements(pptx_file: str, json_file: str, output_file: str): + """Apply text replacements from JSON to PowerPoint presentation.""" + + # Load presentation + prs = Presentation(pptx_file) + + # Get inventory of all text shapes (returns ShapeData objects) + # Pass prs to use same Presentation instance + inventory = extract_text_inventory(Path(pptx_file), prs) + + # Detect text overflow in original presentation + original_overflow = detect_frame_overflow(inventory) + + # Load replacement data with duplicate key detection + with open(json_file, "r") as f: + replacements = json.load(f, object_pairs_hook=check_duplicate_keys) + + # Validate replacements + errors = validate_replacements(inventory, replacements) + if errors: + print("ERROR: Invalid shapes in replacement JSON:") + for error in errors: + print(f" - {error}") + print("\nPlease check the inventory and update your replacement JSON.") + print( + "You can regenerate the inventory with: python inventory.py " + ) + raise ValueError(f"Found {len(errors)} validation error(s)") + + # Track statistics + shapes_processed = 0 + shapes_cleared = 0 + shapes_replaced = 0 + + # Process each slide from inventory + for slide_key, shapes_dict in inventory.items(): + if not slide_key.startswith("slide-"): + continue + + slide_index = int(slide_key.split("-")[1]) + + if slide_index >= len(prs.slides): + print(f"Warning: Slide {slide_index} not found") + continue + + # Process each shape from inventory + for shape_key, shape_data in shapes_dict.items(): + shapes_processed += 1 + + # Get the shape directly from ShapeData + shape = shape_data.shape + if not shape: + print(f"Warning: {shape_key} has no shape reference") + continue + + # ShapeData already validates text_frame in __init__ + text_frame = shape.text_frame # type: ignore + + text_frame.clear() # type: ignore + shapes_cleared += 1 + + # Check for replacement paragraphs + replacement_shape_data = replacements.get(slide_key, {}).get(shape_key, {}) + if "paragraphs" not in replacement_shape_data: + continue + + shapes_replaced += 1 + + # Add replacement paragraphs + for i, para_data in enumerate(replacement_shape_data["paragraphs"]): + if i == 0: + p = text_frame.paragraphs[0] # type: ignore + else: + p = text_frame.add_paragraph() # type: ignore + + apply_paragraph_properties(p, para_data) + + # Check for issues after replacements + # Save to a temporary file and reload to avoid modifying the presentation during inventory + # (extract_text_inventory accesses font.color which adds empty elements) + import tempfile + + with tempfile.NamedTemporaryFile(suffix=".pptx", delete=False) as tmp: + tmp_path = Path(tmp.name) + prs.save(str(tmp_path)) + + try: + updated_inventory = extract_text_inventory(tmp_path) + updated_overflow = detect_frame_overflow(updated_inventory) + finally: + tmp_path.unlink() # Clean up temp file + + # Check if any text overflow got worse + overflow_errors = [] + for slide_key, shape_overflows in updated_overflow.items(): + for shape_key, new_overflow in shape_overflows.items(): + # Get original overflow (0 if there was no overflow before) + original = original_overflow.get(slide_key, {}).get(shape_key, 0.0) + + # Error if overflow increased + if new_overflow > original + 0.01: # Small tolerance for rounding + increase = new_overflow - original + overflow_errors.append( + f'{slide_key}/{shape_key}: overflow worsened by {increase:.2f}" ' + f'(was {original:.2f}", now {new_overflow:.2f}")' + ) + + # Collect warnings from updated shapes + warnings = [] + for slide_key, shapes_dict in updated_inventory.items(): + for shape_key, shape_data in shapes_dict.items(): + if shape_data.warnings: + for warning in shape_data.warnings: + warnings.append(f"{slide_key}/{shape_key}: {warning}") + + # Fail if there are any issues + if overflow_errors or warnings: + print("\nERROR: Issues detected in replacement output:") + if overflow_errors: + print("\nText overflow worsened:") + for error in overflow_errors: + print(f" - {error}") + if warnings: + print("\nFormatting warnings:") + for warning in warnings: + print(f" - {warning}") + print("\nPlease fix these issues before saving.") + raise ValueError( + f"Found {len(overflow_errors)} overflow error(s) and {len(warnings)} warning(s)" + ) + + # Save the presentation + prs.save(output_file) + + # Report results + print(f"Saved updated presentation to: {output_file}") + print(f"Processed {len(prs.slides)} slides") + print(f" - Shapes processed: {shapes_processed}") + print(f" - Shapes cleared: {shapes_cleared}") + print(f" - Shapes replaced: {shapes_replaced}") + + +def main(): + """Main entry point for command-line usage.""" + if len(sys.argv) != 4: + print(__doc__) + sys.exit(1) + + input_pptx = Path(sys.argv[1]) + replacements_json = Path(sys.argv[2]) + output_pptx = Path(sys.argv[3]) + + if not input_pptx.exists(): + print(f"Error: Input file '{input_pptx}' not found") + sys.exit(1) + + if not replacements_json.exists(): + print(f"Error: Replacements JSON file '{replacements_json}' not found") + sys.exit(1) + + try: + apply_replacements(str(input_pptx), str(replacements_json), str(output_pptx)) + except Exception as e: + print(f"Error applying replacements: {e}") + import traceback + + traceback.print_exc() + sys.exit(1) + + +if __name__ == "__main__": + main() diff --git a/scripts/thumbnail.py b/scripts/thumbnail.py new file mode 100755 index 0000000..5c7fdf1 --- /dev/null +++ b/scripts/thumbnail.py @@ -0,0 +1,450 @@ +#!/usr/bin/env python3 +""" +Create thumbnail grids from PowerPoint presentation slides. + +Creates a grid layout of slide thumbnails with configurable columns (max 6). +Each grid contains up to cols×(cols+1) images. For presentations with more +slides, multiple numbered grid files are created automatically. + +The program outputs the names of all files created. + +Output: +- Single grid: {prefix}.jpg (if slides fit in one grid) +- Multiple grids: {prefix}-1.jpg, {prefix}-2.jpg, etc. + +Grid limits by column count: +- 3 cols: max 12 slides per grid (3×4) +- 4 cols: max 20 slides per grid (4×5) +- 5 cols: max 30 slides per grid (5×6) [default] +- 6 cols: max 42 slides per grid (6×7) + +Usage: + python thumbnail.py input.pptx [output_prefix] [--cols N] [--outline-placeholders] + +Examples: + python thumbnail.py presentation.pptx + # Creates: thumbnails.jpg (using default prefix) + # Outputs: + # Created 1 grid(s): + # - thumbnails.jpg + + python thumbnail.py large-deck.pptx grid --cols 4 + # Creates: grid-1.jpg, grid-2.jpg, grid-3.jpg + # Outputs: + # Created 3 grid(s): + # - grid-1.jpg + # - grid-2.jpg + # - grid-3.jpg + + python thumbnail.py template.pptx analysis --outline-placeholders + # Creates thumbnail grids with red outlines around text placeholders +""" + +import argparse +import subprocess +import sys +import tempfile +from pathlib import Path + +from inventory import extract_text_inventory +from PIL import Image, ImageDraw, ImageFont +from pptx import Presentation + +# Constants +THUMBNAIL_WIDTH = 300 # Fixed thumbnail width in pixels +CONVERSION_DPI = 100 # DPI for PDF to image conversion +MAX_COLS = 6 # Maximum number of columns +DEFAULT_COLS = 5 # Default number of columns +JPEG_QUALITY = 95 # JPEG compression quality + +# Grid layout constants +GRID_PADDING = 20 # Padding between thumbnails +BORDER_WIDTH = 2 # Border width around thumbnails +FONT_SIZE_RATIO = 0.12 # Font size as fraction of thumbnail width +LABEL_PADDING_RATIO = 0.4 # Label padding as fraction of font size + + +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, will create prefix.jpg or prefix-N.jpg)", + ) + parser.add_argument( + "--cols", + type=int, + default=DEFAULT_COLS, + help=f"Number of columns (default: {DEFAULT_COLS}, max: {MAX_COLS})", + ) + parser.add_argument( + "--outline-placeholders", + action="store_true", + help="Outline text placeholders with a colored border", + ) + + args = parser.parse_args() + + # Validate columns + cols = min(args.cols, MAX_COLS) + if args.cols > MAX_COLS: + print(f"Warning: Columns limited to {MAX_COLS} (requested {args.cols})") + + # Validate input + input_path = Path(args.input) + if not input_path.exists() or input_path.suffix.lower() != ".pptx": + print(f"Error: Invalid PowerPoint file: {args.input}") + sys.exit(1) + + # Construct output path (always JPG) + output_path = Path(f"{args.output_prefix}.jpg") + + print(f"Processing: {args.input}") + + try: + with tempfile.TemporaryDirectory() as temp_dir: + # Get placeholder regions if outlining is enabled + placeholder_regions = None + slide_dimensions = None + if args.outline_placeholders: + print("Extracting placeholder regions...") + placeholder_regions, slide_dimensions = get_placeholder_regions( + input_path + ) + if placeholder_regions: + print(f"Found placeholders on {len(placeholder_regions)} slides") + + # Convert slides to images + slide_images = convert_to_images(input_path, Path(temp_dir), CONVERSION_DPI) + if not slide_images: + print("Error: No slides found") + sys.exit(1) + + print(f"Found {len(slide_images)} slides") + + # Create grids (max cols×(cols+1) images per grid) + grid_files = create_grids( + slide_images, + cols, + THUMBNAIL_WIDTH, + output_path, + placeholder_regions, + slide_dimensions, + ) + + # Print saved files + 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}") + sys.exit(1) + + +def create_hidden_slide_placeholder(size): + """Create placeholder image for hidden slides.""" + 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 get_placeholder_regions(pptx_path): + """Extract ALL text regions from the presentation. + + Returns a tuple of (placeholder_regions, slide_dimensions). + text_regions is a dict mapping slide indices to lists of text regions. + Each region is a dict with 'left', 'top', 'width', 'height' in inches. + slide_dimensions is a tuple of (width_inches, height_inches). + """ + prs = Presentation(str(pptx_path)) + inventory = extract_text_inventory(pptx_path, prs) + placeholder_regions = {} + + # Get actual slide dimensions in inches (EMU to inches conversion) + slide_width_inches = (prs.slide_width or 9144000) / 914400.0 + slide_height_inches = (prs.slide_height or 5143500) / 914400.0 + + for slide_key, shapes in inventory.items(): + # Extract slide index from "slide-N" format + slide_idx = int(slide_key.split("-")[1]) + regions = [] + + for shape_key, shape_data in shapes.items(): + # The inventory only contains shapes with text, so all shapes should be highlighted + regions.append( + { + "left": shape_data.left, + "top": shape_data.top, + "width": shape_data.width, + "height": shape_data.height, + } + ) + + if regions: + placeholder_regions[slide_idx] = regions + + return placeholder_regions, (slide_width_inches, slide_height_inches) + + +def convert_to_images(pptx_path, temp_dir, dpi): + """Convert PowerPoint to images via PDF, handling hidden slides.""" + # Detect hidden slides + print("Analyzing presentation...") + prs = Presentation(str(pptx_path)) + total_slides = len(prs.slides) + + # Find hidden slides (1-based indexing for display) + hidden_slides = { + idx + 1 + for idx, slide in enumerate(prs.slides) + if slide.element.get("show") == "0" + } + + print(f"Total slides: {total_slides}") + if hidden_slides: + print(f"Hidden slides: {sorted(hidden_slides)}") + + pdf_path = temp_dir / f"{pptx_path.stem}.pdf" + + # Convert to PDF + print("Converting to PDF...") + result = subprocess.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") + + # Convert PDF to images + print(f"Converting to images at {dpi} DPI...") + result = subprocess.run( + ["pdftoppm", "-jpeg", "-r", str(dpi), str(pdf_path), str(temp_dir / "slide")], + capture_output=True, + text=True, + ) + if result.returncode != 0: + raise RuntimeError("Image conversion failed") + + visible_images = sorted(temp_dir.glob("slide-*.jpg")) + + # Create full list with placeholders for hidden slides + all_images = [] + visible_idx = 0 + + # Get placeholder dimensions from first visible slide + if visible_images: + with Image.open(visible_images[0]) as img: + placeholder_size = img.size + else: + placeholder_size = (1920, 1080) + + for slide_num in range(1, total_slides + 1): + if slide_num in hidden_slides: + # Create placeholder image for hidden slide + placeholder_path = temp_dir / f"hidden-{slide_num:03d}.jpg" + placeholder_img = create_hidden_slide_placeholder(placeholder_size) + placeholder_img.save(placeholder_path, "JPEG") + all_images.append(placeholder_path) + else: + # Use the actual visible slide image + if visible_idx < len(visible_images): + all_images.append(visible_images[visible_idx]) + visible_idx += 1 + + return all_images + + +def create_grids( + image_paths, + cols, + width, + output_path, + placeholder_regions=None, + slide_dimensions=None, +): + """Create multiple thumbnail grids from slide images, max cols×(cols+1) images per grid.""" + # Maximum images per grid is cols × (cols + 1) for better proportions + max_images_per_grid = cols * (cols + 1) + grid_files = [] + + print( + f"Creating grids with {cols} columns (max {max_images_per_grid} images per grid)" + ) + + # Split images into chunks + for chunk_idx, start_idx in enumerate( + range(0, len(image_paths), max_images_per_grid) + ): + end_idx = min(start_idx + max_images_per_grid, len(image_paths)) + chunk_images = image_paths[start_idx:end_idx] + + # Create grid for this chunk + grid = create_grid( + chunk_images, cols, width, start_idx, placeholder_regions, slide_dimensions + ) + + # Generate output filename + if len(image_paths) <= max_images_per_grid: + # Single grid - use base filename without suffix + grid_filename = output_path + else: + # Multiple grids - insert index before extension with dash + stem = output_path.stem + suffix = output_path.suffix + grid_filename = output_path.parent / f"{stem}-{chunk_idx + 1}{suffix}" + + # Save grid + 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( + image_paths, + cols, + width, + start_slide_num=0, + placeholder_regions=None, + slide_dimensions=None, +): + """Create thumbnail grid from slide images with optional placeholder outlining.""" + font_size = int(width * FONT_SIZE_RATIO) + label_padding = int(font_size * LABEL_PADDING_RATIO) + + # Get dimensions + with Image.open(image_paths[0]) as img: + aspect = img.height / img.width + height = int(width * aspect) + + # Calculate grid size + rows = (len(image_paths) + cols - 1) // cols + grid_w = cols * width + (cols + 1) * GRID_PADDING + grid_h = rows * (height + font_size + label_padding * 2) + (rows + 1) * GRID_PADDING + + # Create grid + grid = Image.new("RGB", (grid_w, grid_h), "white") + draw = ImageDraw.Draw(grid) + + # Load font with size based on thumbnail width + try: + # Use Pillow's default font with size + font = ImageFont.load_default(size=font_size) + except Exception: + # Fall back to basic default font if size parameter not supported + font = ImageFont.load_default() + + # Place thumbnails + for i, img_path in enumerate(image_paths): + 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 + ) + + # Add label with actual slide number + label = f"{start_slide_num + i}" + 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, + ) + + # Add thumbnail below label with proportional spacing + y_thumbnail = y_base + label_padding + font_size + label_padding + + with Image.open(img_path) as img: + # Get original dimensions before thumbnail + orig_w, orig_h = img.size + + # Apply placeholder outlines if enabled + if placeholder_regions and (start_slide_num + i) in placeholder_regions: + # Convert to RGBA for transparency support + if img.mode != "RGBA": + img = img.convert("RGBA") + + # Get the regions for this slide + regions = placeholder_regions[start_slide_num + i] + + # Calculate scale factors using actual slide dimensions + if slide_dimensions: + slide_width_inches, slide_height_inches = slide_dimensions + else: + # Fallback: estimate from image size at CONVERSION_DPI + slide_width_inches = orig_w / CONVERSION_DPI + slide_height_inches = orig_h / CONVERSION_DPI + + x_scale = orig_w / slide_width_inches + y_scale = orig_h / slide_height_inches + + # Create a highlight overlay + overlay = Image.new("RGBA", img.size, (255, 255, 255, 0)) + overlay_draw = ImageDraw.Draw(overlay) + + # Highlight each placeholder region + for region in regions: + # Convert from inches to pixels in the original image + px_left = int(region["left"] * x_scale) + px_top = int(region["top"] * y_scale) + px_width = int(region["width"] * x_scale) + px_height = int(region["height"] * y_scale) + + # Draw highlight outline with red color and thick stroke + # Using a bright red outline instead of fill + stroke_width = max( + 5, min(orig_w, orig_h) // 150 + ) # Thicker proportional stroke width + overlay_draw.rectangle( + [(px_left, px_top), (px_left + px_width, px_top + px_height)], + outline=(255, 0, 0, 255), # Bright red, fully opaque + width=stroke_width, + ) + + # Composite the overlay onto the image using alpha blending + img = Image.alpha_composite(img, overlay) + # Convert back to RGB for JPEG saving + img = img.convert("RGB") + + 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)) + + # Add border + 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()