Phase 2: 轉換管線 — 五個本地轉換器 + convert.py 統一入口 + selfcheck

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

tools/convert/from_pptx.py

@@ -0,0 +1,74 @@
+"""PowerPoint (.pptx) → Markdown。每張投影片一節，含表格、圖片佔位與講者備註。
+
+可獨立執行：python tools/convert/from_pptx.py <file.pptx> [-o out.md] [--dry-run]
+"""
+import argparse
+import pathlib
+
+from pptx import Presentation
+from pptx.enum.shapes import MSO_SHAPE_TYPE
+
+
+def _table_md(tbl):
+    rows = [
+        [c.text.strip().replace("|", "\\|").replace("\n", " ") for c in row.cells]
+        for row in tbl.rows
+    ]
+    if not rows:
+        return ""
+    width = len(rows[0])
+    out = ["| " + " | ".join(rows[0]) + " |", "|" + " --- |" * width]
+    out += ["| " + " | ".join(r) + " |" for r in rows[1:]]
+    return "\n".join(out)
+
+
+def convert(src, assets_dir=None, md_dir=None):
+    """回傳 (markdown, status)。status 恆為 'ok'。"""
+    src = pathlib.Path(src)
+    md_dir = pathlib.Path(md_dir) if md_dir else src.parent
+    prs = Presentation(str(src))
+    counter = 0
+    sections = []
+    for i, slide in enumerate(prs.slides, 1):
+        blocks = [f"## Slide {i}"]
+        for shape in slide.shapes:
+            if shape.has_text_frame and shape.text_frame.text.strip():
+                blocks.append(shape.text_frame.text.strip())
+            elif shape.has_table:
+                blocks.append(_table_md(shape.table))
+            elif shape.shape_type == MSO_SHAPE_TYPE.PICTURE:
+                counter += 1
+                name = f"img{counter}.{shape.image.ext}"
+                if assets_dir is not None:
+                    assets_dir.mkdir(parents=True, exist_ok=True)
+                    (assets_dir / name).write_bytes(shape.image.blob)
+                    rel = (assets_dir / name).relative_to(md_dir).as_posix()
+                else:
+                    rel = name
+                blocks.append(f"![{name}]({rel})")
+        if slide.has_notes_slide:
+            notes = slide.notes_slide.notes_text_frame.text.strip()
+            if notes:
+                blocks.append(f"### 講者備註\n\n{notes}")
+        sections.append("\n\n".join(blocks))
+    return "\n\n".join(sections), "ok"
+
+
+def main(argv=None):
+    ap = argparse.ArgumentParser(description=__doc__)
+    ap.add_argument("src")
+    ap.add_argument("-o", "--output")
+    ap.add_argument("--dry-run", action="store_true")
+    a = ap.parse_args(argv)
+    if a.dry_run:
+        md, status = convert(a.src)
+        print(f"[dry-run] {a.src}: status={status}, {len(md)} chars")
+        return
+    out = pathlib.Path(a.output) if a.output else pathlib.Path(a.src).with_suffix(".md")
+    md, _ = convert(a.src, assets_dir=out.parent / f"{out.stem}-assets", md_dir=out.parent)
+    out.write_text(md, encoding="utf-8")
+    print(out)
+
+
+if __name__ == "__main__":
+    main()