codewave-openclaw-installer 1.0.2 → 2.1.0

package/skills/ppt-master/scripts/doc_to_md.py

@@ -0,0 +1,232 @@
+#!/usr/bin/env python3
+"""
+Document to Markdown Converter (Pandoc-based)
+
+Uses Pandoc to convert various document formats to Markdown.
+Primary use case: DOCX lecture notes / manuscripts → Markdown for PPT generation.
+
+Dependency: pandoc must be installed
+   macOS:   brew install pandoc
+   Ubuntu:  sudo apt install pandoc
+   Windows: https://pandoc.org/installing.html
+"""
+
+import argparse
+import re
+import shutil
+import subprocess
+import sys
+from pathlib import Path
+
+
+# Supported input formats
+SUPPORTED_FORMATS = {
+    # Office documents
+    ".docx": ("docx", "Microsoft Word"),
+    ".doc": ("doc", "Microsoft Word 97-2003"),
+    ".odt": ("odt", "OpenDocument Text"),
+    ".rtf": ("rtf", "Rich Text Format"),
+    # eBooks
+    ".epub": ("epub", "EPUB"),
+    # Web
+    ".html": ("html", "HTML"),
+    ".htm": ("html", "HTML"),
+    # Academic / technical
+    ".tex": ("latex", "LaTeX"),
+    ".latex": ("latex", "LaTeX"),
+    ".rst": ("rst", "reStructuredText"),
+    ".org": ("org", "Emacs Org-mode"),
+    ".ipynb": ("ipynb", "Jupyter Notebook"),
+    ".typ": ("typst", "Typst"),
+}
+
+# Formats that may contain embedded media
+MEDIA_FORMATS = {".docx", ".odt", ".epub", ".html", ".htm"}
+
+
+def check_pandoc() -> bool:
+    """Check if pandoc is installed."""
+    return shutil.which("pandoc") is not None
+
+
+def convert_to_markdown(input_path: str, output_path: str | None = None) -> str:
+    """
+    Convert a document to Markdown using Pandoc.
+
+    Args:
+        input_path: Path to the input document.
+        output_path: Path to write the output Markdown (default: same dir, .md extension).
+
+    Returns:
+        The generated Markdown content.
+    """
+    input_file = Path(input_path)
+
+    if not input_file.exists():
+        print(f"[ERROR] File not found: {input_path}")
+        return ""
+
+    suffix = input_file.suffix.lower()
+    if suffix not in SUPPORTED_FORMATS:
+        supported = ", ".join(sorted(SUPPORTED_FORMATS.keys()))
+        print(f"[ERROR] Unsupported format: {suffix}")
+        print(f"   Supported: {supported}")
+        return ""
+
+    input_format, format_desc = SUPPORTED_FORMATS[suffix]
+    print(f"[INFO] Converting {format_desc} file: {input_file.name}")
+
+    # Determine output path
+    if output_path:
+        out_file = Path(output_path)
+    else:
+        out_file = input_file.with_suffix(".md")
+
+    # Media extraction directory (use name only — pandoc writes relative paths)
+    rel_media_dir = f"{out_file.stem}_files"
+    media_dir = out_file.parent / rel_media_dir
+
+    # Build pandoc command — use resolved absolute paths for input/output,
+    # but a relative directory name for --extract-media so pandoc writes
+    # relative image references in the markdown.
+    cmd = [
+        "pandoc",
+        "-f", input_format,
+        "-t", "gfm",
+        str(input_file.resolve()),
+        "-o", str(out_file.resolve()),
+        "--wrap", "none",
+        "--strip-comments",
+    ]
+
+    # Extract embedded media for formats that support it
+    if suffix in MEDIA_FORMATS:
+        cmd.extend(["--extract-media", rel_media_dir])
+
+    try:
+        result = subprocess.run(cmd, capture_output=True, text=True,
+                                cwd=str(out_file.parent))
+    except FileNotFoundError:
+        print("[ERROR] pandoc not found! Please install it first:")
+        print("   macOS:   brew install pandoc")
+        print("   Ubuntu:  sudo apt install pandoc")
+        print("   Windows: https://pandoc.org/installing.html")
+        return ""
+
+    if result.returncode != 0:
+        print(f"[ERROR] Pandoc conversion failed:\n{result.stderr}")
+        return ""
+
+    # Read generated markdown
+    if not out_file.exists():
+        print("[ERROR] Conversion completed but no output file was generated")
+        return ""
+
+    markdown_content = out_file.read_text(encoding="utf-8")
+
+    # --- Post-processing: fix media paths ---
+
+    # 1. Flatten nested media/ subdirectory that pandoc creates
+    nested_media = media_dir / "media"
+    if nested_media.exists():
+        for f in nested_media.iterdir():
+            if f.is_file():
+                target = media_dir / f.name
+                shutil.move(str(f), str(target))
+        try:
+            nested_media.rmdir()
+        except OSError:
+            pass
+        # Fix references: {dir}/media/img.png → {dir}/img.png
+        markdown_content = markdown_content.replace(
+            f"{rel_media_dir}/media/", f"{rel_media_dir}/"
+        )
+
+    # 2. Convert any absolute paths to relative (safety net)
+    abs_media_str = str(media_dir.resolve()).replace("\\", "/")
+    if abs_media_str in markdown_content:
+        markdown_content = markdown_content.replace(abs_media_str, rel_media_dir)
+    # Also handle backslash variant on Windows
+    abs_media_str_bs = str(media_dir.resolve())
+    if abs_media_str_bs in markdown_content:
+        markdown_content = markdown_content.replace(abs_media_str_bs, rel_media_dir)
+
+    # 3. Convert <img> HTML tags to Markdown ![alt](src) syntax
+    #    Pandoc generates <img> when the source has styling (width/height)
+    def _img_to_md(match: re.Match[str]) -> str:
+        src = match.group("src")
+        alt = match.group("alt") or Path(src).stem
+        return f"![{alt}]({src})"
+
+    markdown_content = re.sub(
+        r'<img\s[^>]*?src="(?P<src>[^"]+)"[^>]*?(?:alt="(?P<alt>[^"]*)")?[^>]*/?\s*>',
+        _img_to_md,
+        markdown_content,
+    )
+    # Handle alt before src order as well
+    markdown_content = re.sub(
+        r'<img\s[^>]*?alt="(?P<alt>[^"]*)"[^>]*?src="(?P<src>[^"]+)"[^>]*/?\s*>',
+        _img_to_md,
+        markdown_content,
+    )
+
+    out_file.write_text(markdown_content, encoding="utf-8")
+
+    # Report results
+    size = out_file.stat().st_size
+    print(f"[OK] Saved Markdown to: {out_file} ({_format_size(size)})")
+
+    if media_dir.exists():
+        media_files = [f for f in media_dir.rglob("*") if f.is_file()]
+        if media_files:
+            print(f"   Extracted {len(media_files)} media file(s) → {media_dir}")
+
+    return markdown_content
+
+
+def _format_size(size: int) -> str:
+    """Format file size for display."""
+    for unit in ("B", "KB", "MB"):
+        if size < 1024:
+            return f"{size:.0f} {unit}"
+        size /= 1024
+    return f"{size:.1f} GB"
+
+
+def main() -> None:
+    """Run the CLI entry point."""
+    parser = argparse.ArgumentParser(
+        description="Convert documents to Markdown using Pandoc",
+        formatter_class=argparse.RawDescriptionHelpFormatter,
+        epilog="""
+Examples:
+  python doc_to_md.py lecture.docx                # Convert Word document
+  python doc_to_md.py lecture.docx -o output.md   # Specify output path
+  python doc_to_md.py notes.odt                   # Convert OpenDocument
+
+Supported formats:
+  Office:    .docx  .doc  .odt  .rtf
+  eBooks:    .epub
+  Web:       .html  .htm
+  Academic:  .tex  .rst  .org  .ipynb  .typ
+        """,
+    )
+
+    parser.add_argument("input", help="Input document file")
+    parser.add_argument("-o", "--output", help="Output Markdown file path")
+
+    args = parser.parse_args()
+
+    if not check_pandoc():
+        print("[ERROR] pandoc not found! Please install it first:")
+        print("   macOS:   brew install pandoc")
+        print("   Ubuntu:  sudo apt install pandoc")
+        print("   Windows: https://pandoc.org/installing.html")
+        sys.exit(1)
+
+    result = convert_to_markdown(args.input, args.output)
+    sys.exit(0 if result else 1)
+
+
+if __name__ == "__main__":
+    main()

package/skills/ppt-master/scripts/docs/conversion.md

@@ -0,0 +1,89 @@
+# Conversion Tools
+
+Source conversion tools turn PDFs, documents, and web pages into Markdown before project creation.
+
+## `pdf_to_md.py`
+
+Recommended first choice for native PDFs.
+
+```bash
+python3 scripts/pdf_to_md.py book.pdf
+python3 scripts/pdf_to_md.py book.pdf -o output.md
+python3 scripts/pdf_to_md.py ./pdfs
+python3 scripts/pdf_to_md.py ./pdfs -o ./markdown
+```
+
+Use cases:
+- Native PDFs exported from Word, PowerPoint, LaTeX, or similar tools
+- Privacy-sensitive documents that should stay local
+- Fast first-pass extraction before falling back to OCR-heavy tools
+
+Prefer MinerU or another OCR/layout tool when:
+- The PDF is scanned or image-based
+- Multi-column layout parsing is poor
+- Encoding is garbled
+
+Dependency:
+
+```bash
+pip install PyMuPDF
+```
+
+## `doc_to_md.py`
+
+Pandoc-based converter for office and markup formats.
+
+Supported formats include:
+- `.docx`, `.doc`, `.odt`, `.rtf`
+- `.epub`, `.html`, `.tex`, `.rst`, `.org`, `.ipynb`, `.typ`
+
+```bash
+python3 scripts/doc_to_md.py lecture.docx
+python3 scripts/doc_to_md.py lecture.docx -o output.md
+python3 scripts/doc_to_md.py notes.epub
+python3 scripts/doc_to_md.py paper.tex -o paper.md
+```
+
+Dependency:
+
+```bash
+# macOS
+brew install pandoc
+
+# Ubuntu
+sudo apt install pandoc
+```
+
+## `web_to_md.py` / `web_to_md.cjs`
+
+Convert web pages to Markdown and download images locally.
+
+Python version:
+
+```bash
+python3 scripts/web_to_md.py https://example.com/article
+python3 scripts/web_to_md.py https://url1.com https://url2.com
+python3 scripts/web_to_md.py -f urls.txt
+python3 scripts/web_to_md.py https://example.com -o output.md
+```
+
+Node.js version for WeChat or anti-bot pages:
+
+```bash
+node scripts/web_to_md.cjs https://mp.weixin.qq.com/s/xxxx
+node scripts/web_to_md.cjs https://url1.com https://url2.com
+```
+
+Use the Node.js version first for WeChat Official Accounts and similar high-security sites.
+
+## `rotate_images.py`
+
+Fix image EXIF orientation in downloaded or imported assets.
+
+```bash
+python3 scripts/rotate_images.py auto projects/xxx_files
+python3 scripts/rotate_images.py gen projects/xxx_files
+python3 scripts/rotate_images.py fix fixes.json
+```
+
+Use this when extracted photos appear sideways after conversion or import.

package/skills/ppt-master/scripts/docs/image.md

@@ -0,0 +1,96 @@
+# Image Tools
+
+Image tools cover prompt-based generation, image inspection, and Gemini watermark removal.
+
+## `image_gen.py`
+
+Unified image generation entry point.
+
+```bash
+python3 scripts/image_gen.py "A modern futuristic workspace"
+python3 scripts/image_gen.py "Abstract tech background" --aspect_ratio 16:9 --image_size 4K
+python3 scripts/image_gen.py "Concept car" -o projects/demo/images
+python3 scripts/image_gen.py "Beautiful landscape" -n "low quality, blurry, watermark"
+python3 scripts/image_gen.py --list-backends
+```
+
+Support tiers:
+- Core: `gemini`, `openai`, `qwen`, `zhipu`, `volcengine`
+- Extended: `stability`, `bfl`, `ideogram`
+- Experimental: `siliconflow`, `fal`, `replicate`
+
+Backend selection:
+
+```bash
+python3 scripts/image_gen.py "A cat" --backend openai
+python3 scripts/image_gen.py "A product launch hero image" --backend qwen
+python3 scripts/image_gen.py "科技感背景图" --backend zhipu
+python3 scripts/image_gen.py "A product KV in cinematic style" --backend volcengine
+```
+
+Configuration sources:
+
+1. Current process environment variables
+2. Repo-root `.env` as a fallback
+
+The active backend must always be selected explicitly via `IMAGE_BACKEND`.
+
+Example `.env`:
+
+```env
+IMAGE_BACKEND=gemini
+GEMINI_API_KEY=your-api-key
+GEMINI_BASE_URL=https://your-proxy-url.com/v1beta
+GEMINI_MODEL=gemini-3.1-flash-image-preview
+```
+
+Example process environment:
+
+```bash
+export IMAGE_BACKEND=gemini
+export GEMINI_API_KEY=your-api-key
+export GEMINI_MODEL=gemini-3.1-flash-image-preview
+```
+
+Current process environment wins over `.env`.
+
+Use provider-specific keys only, such as `GEMINI_API_KEY`, `OPENAI_API_KEY`, `QWEN_API_KEY`, `ZHIPU_API_KEY`, `VOLCENGINE_API_KEY`, `FAL_KEY`, or `REPLICATE_API_TOKEN`.
+
+`IMAGE_API_KEY`, `IMAGE_MODEL`, and `IMAGE_BASE_URL` are intentionally unsupported.
+
+If you keep multiple providers in one `.env` or environment, `IMAGE_BACKEND` must explicitly select the active provider.
+
+Recommendation:
+- Default to the Core tier for routine PPT work
+- Use Extended only when you need a specific model style
+- Treat Experimental backends as opt-in
+
+## `analyze_images.py`
+
+Analyze images in a project directory before writing the design spec or composing slide layouts.
+
+```bash
+python3 scripts/analyze_images.py <project_path>/images
+```
+
+Use this instead of opening image files directly when following the project workflow.
+
+## `gemini_watermark_remover.py`
+
+Remove Gemini watermark assets after manual download.
+
+```bash
+python3 scripts/gemini_watermark_remover.py <image_path>
+python3 scripts/gemini_watermark_remover.py <image_path> -o output_path.png
+python3 scripts/gemini_watermark_remover.py <image_path> -q
+```
+
+Notes:
+- Requires `scripts/assets/bg_48.png` and `scripts/assets/bg_96.png`
+- Best used after downloading “full size” Gemini images
+
+Dependencies:
+
+```bash
+pip install Pillow numpy
+```

package/skills/ppt-master/scripts/docs/project.md

@@ -0,0 +1,84 @@
+# Project Tools
+
+Project tools create, validate, and inspect the standard PPT Master workspace.
+
+## `project_manager.py`
+
+Main entry point for project setup and validation.
+
+```bash
+python3 scripts/project_manager.py init <project_name> --format ppt169
+python3 scripts/project_manager.py import-sources <project_path> <source1> [<source2> ...]
+python3 scripts/project_manager.py validate <project_path>
+python3 scripts/project_manager.py info <project_path>
+```
+
+Notes:
+- Files outside the workspace are copied into `sources/` by default
+- With `--move`, files outside the workspace are moved into `sources/`
+- Files already inside the workspace are moved directly
+
+Common formats:
+- `ppt169`
+- `ppt43`
+- `xiaohongshu`
+- `moments`
+- `story`
+- `banner`
+- `a4`
+
+Examples:
+
+```bash
+python3 scripts/project_manager.py init my_presentation --format ppt169
+python3 scripts/project_manager.py validate projects/my_presentation_ppt169_20251116
+python3 scripts/project_manager.py info projects/my_presentation_ppt169_20251116
+```
+
+## `project_utils.py`
+
+Shared helper module used by other scripts.
+
+Typical use:
+
+```python
+from project_utils import get_project_info, validate_project_structure
+```
+
+You can also run it directly for quick checks:
+
+```bash
+python3 scripts/project_utils.py <project_path>
+```
+
+## `batch_validate.py`
+
+Batch-check project structure and compliance.
+
+```bash
+python3 scripts/batch_validate.py examples
+python3 scripts/batch_validate.py examples projects
+python3 scripts/batch_validate.py --all
+python3 scripts/batch_validate.py examples --export
+```
+
+Use this for repository-wide health checks before release or cleanup.
+
+## `generate_examples_index.py`
+
+Rebuild `examples/README.md` automatically.
+
+```bash
+python3 scripts/generate_examples_index.py
+python3 scripts/generate_examples_index.py examples
+```
+
+## `error_helper.py`
+
+Show standardized fixes for common project errors.
+
+```bash
+python3 scripts/error_helper.py
+python3 scripts/error_helper.py missing_readme
+python3 scripts/error_helper.py missing_readme project_path=my_project
+```

package/skills/ppt-master/scripts/docs/svg-pipeline.md

@@ -0,0 +1,161 @@
+# SVG Pipeline Tools
+
+These tools cover post-processing, SVG validation, speaker notes, and PPTX export.
+
+## Recommended Pipeline
+
+Run these steps in order:
+
+```bash
+python3 scripts/total_md_split.py <project_path>
+python3 scripts/finalize_svg.py <project_path>
+python3 scripts/svg_to_pptx.py <project_path> -s final
+```
+
+## `finalize_svg.py`
+
+Unified post-processing entry point. This is the preferred way to run SVG cleanup.
+
+It aggregates:
+- `embed_icons.py`
+- `crop_images.py`
+- `fix_image_aspect.py`
+- `embed_images.py`
+- `flatten_tspan.py`
+- `svg_rect_to_path.py`
+
+Typical usage:
+
+```bash
+python3 scripts/finalize_svg.py <project_path>
+```
+
+Use standalone sub-tools only when you need advanced debugging or one-off fixes.
+
+## `svg_to_pptx.py`
+
+Convert project SVGs into PPTX.
+
+```bash
+python3 scripts/svg_to_pptx.py <project_path> -s final
+python3 scripts/svg_to_pptx.py <project_path> -s final --only native
+python3 scripts/svg_to_pptx.py <project_path> -s final --only legacy
+python3 scripts/svg_to_pptx.py <project_path> -s final --no-notes
+python3 scripts/svg_to_pptx.py <project_path> -t none
+python3 scripts/svg_to_pptx.py <project_path> -s final --auto-advance 3
+```
+
+Behavior:
+- Default output: native editable PPTX + SVG reference PPTX
+- Recommended source directory: `svg_final/`
+- Speaker notes are embedded automatically unless `--no-notes` is used
+
+Dependency:
+
+```bash
+pip install python-pptx
+```
+
+## `total_md_split.py`
+
+Split `total.md` into per-slide note files.
+
+```bash
+python3 scripts/total_md_split.py <project_path>
+python3 scripts/total_md_split.py <project_path> -o <output_directory>
+python3 scripts/total_md_split.py <project_path> -q
+```
+
+Requirements:
+- Each section begins with `# `
+- Heading text matches the SVG filename
+- Sections are separated by `---`
+
+## `svg_quality_checker.py`
+
+Validate SVG technical compliance.
+
+```bash
+python3 scripts/svg_quality_checker.py examples/project/svg_output/01_cover.svg
+python3 scripts/svg_quality_checker.py examples/project/svg_output
+python3 scripts/svg_quality_checker.py examples/project
+python3 scripts/svg_quality_checker.py examples/project --format ppt169
+python3 scripts/svg_quality_checker.py --all examples
+python3 scripts/svg_quality_checker.py examples/project --export
+```
+
+Checks include:
+- `viewBox`
+- banned elements
+- width/height consistency
+- line-break structure
+
+## `svg_position_calculator.py`
+
+Analyze or pre-calculate chart coordinates.
+
+Common commands:
+
+```bash
+python3 scripts/svg_position_calculator.py analyze <svg_file>
+python3 scripts/svg_position_calculator.py interactive
+python3 scripts/svg_position_calculator.py calc bar --data "East:185,South:142"
+python3 scripts/svg_position_calculator.py calc pie --data "A:35,B:25,C:20"
+python3 scripts/svg_position_calculator.py from-json config.json
+```
+
+Use this when chart geometry needs to be verified before or after AI generation.
+
+## Advanced Standalone Tools
+
+### `flatten_tspan.py`
+
+```bash
+python3 scripts/svg_finalize/flatten_tspan.py examples/<project>/svg_output
+python3 scripts/svg_finalize/flatten_tspan.py path/to/input.svg path/to/output.svg
+```
+
+### `svg_rect_to_path.py`
+
+```bash
+python3 scripts/svg_finalize/svg_rect_to_path.py <project_path>
+python3 scripts/svg_finalize/svg_rect_to_path.py <project_path> -s final
+python3 scripts/svg_finalize/svg_rect_to_path.py path/to/file.svg
+```
+
+Use when rounded corners must survive PowerPoint shape conversion.
+
+### `fix_image_aspect.py`
+
+```bash
+python3 scripts/svg_finalize/fix_image_aspect.py path/to/slide.svg
+python3 scripts/svg_finalize/fix_image_aspect.py 01_cover.svg 02_toc.svg
+python3 scripts/svg_finalize/fix_image_aspect.py --dry-run path/to/slide.svg
+```
+
+Use when embedded images stretch after PowerPoint shape conversion.
+
+### `embed_icons.py`
+
+```bash
+python3 scripts/svg_finalize/embed_icons.py output.svg
+python3 scripts/svg_finalize/embed_icons.py svg_output/*.svg
+python3 scripts/svg_finalize/embed_icons.py --dry-run svg_output/*.svg
+```
+
+Use for manual icon embedding checks outside `finalize_svg.py`.
+
+## PPT Compatibility Rules
+
+Use PowerPoint-safe transparency syntax:
+
+| Avoid | Use instead |
+|------|-------------|
+| `fill=\"rgba(...)\"` | `fill=\"#hex\"` + `fill-opacity` |
+| `<g opacity=\"...\">` | Set opacity on each child |
+| `<image opacity=\"...\">` | Overlay with a mask layer |
+
+PowerPoint also has trouble with:
+- marker-based arrows
+- unsupported filters
+- direct SVG features not mapped to DrawingML