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_xlsx.py

@@ -0,0 +1,56 @@
+"""Excel (.xlsx) → Markdown。每個工作表一節，內容輸出為 Markdown 表格。
+
+可獨立執行：python tools/convert/from_xlsx.py <file.xlsx> [-o out.md] [--dry-run]
+"""
+import argparse
+import pathlib
+
+import openpyxl
+
+
+def _cell(v):
+    return "" if v is None else str(v).replace("|", "\\|").replace("\n", " ").strip()
+
+
+def convert(src, assets_dir=None, md_dir=None):
+    """回傳 (markdown, status)。status 恆為 'ok'。
+
+    ponytail: merged cell 只有左上角有值（openpyxl read_only 行為），不展開；
+    升級路徑：非 read_only 模式讀 merged_cells.ranges 補值。
+    """
+    wb = openpyxl.load_workbook(str(src), data_only=True, read_only=True)
+    sections = []
+    for ws in wb.worksheets:
+        rows = [[_cell(v) for v in row] for row in ws.iter_rows(values_only=True)]
+        rows = [r for r in rows if any(r)]  # 去除全空列
+        body = f"## 工作表：{ws.title}\n\n"
+        if not rows:
+            body += "（空白工作表）"
+        else:
+            width = max(len(r) for r in rows)
+            rows = [r + [""] * (width - len(r)) for r in rows]
+            lines = ["| " + " | ".join(rows[0]) + " |", "|" + " --- |" * width]
+            lines += ["| " + " | ".join(r) + " |" for r in rows[1:]]
+            body += "\n".join(lines)
+        sections.append(body)
+    wb.close()
+    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)
+    md, status = convert(a.src)
+    if a.dry_run:
+        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")
+    out.write_text(md, encoding="utf-8")
+    print(out)
+
+
+if __name__ == "__main__":
+    main()