Initial commit

docx2md/docx2md.py

@@ -0,0 +1,103 @@
+import subprocess
+import os
+import re
+import json
+from pathlib import Path
+
+def convert_compact_mode(docx_file):
+    path_obj = Path(docx_file)
+    base_name = path_obj.stem
+    output_md = f"{base_name}_Compact.md"
+    media_folder = f"{base_name}_images"
+    metadata_file = f"{base_name}_metadata.json"
+    images_list_file = f"{base_name}_images.txt"
+    
+    # 1. 关键修改：使用 gfm 格式，强制生成紧凑表格
+    cmd = ["pandoc", docx_file, "-o", output_md, 
+           "--to=gfm",  # <--- 核心改动：使用 GitHub 风格，拒绝网格表
+           "--standalone", 
+           f"--extract-media={media_folder}", 
+           "--wrap=none", 
+           "--markdown-headings=atx"]
+    
+    try:
+        subprocess.run(cmd, check=True, capture_output=True)
+    except Exception as e:
+        print(f"❌ 转换出错: {e}")
+        return
+
+    with open(output_md, 'r', encoding='utf-8') as f:
+        content = f.read()
+
+    # 2. 紧凑版正则清洗
+    # 因为 gfm 主要是 pipe table，我们只需要匹配 |...| 结构
+    # 并且不仅匹配，还要把里面为了对齐而产生的多余空格给压扁
+    
+    # 这一步将 "|  文本   |" 压缩为 "| 文本 |"
+    def compress_table_row(match):
+        row = match.group(0)
+        # 将连续的空格替换为单个空格，但保留结构
+        return re.sub(r' +', ' ', row)
+
+    # 匹配标准 Markdown 表格行
+    content = re.sub(r'^\|.*\|$', compress_table_row, content, flags=re.MULTILINE)
+
+    # 3. 标记表格 (逻辑简化，因为现在只有一种表格格式了)
+    tbl_count = 0
+    def tag_table(match):
+        nonlocal tbl_count
+        tbl_count += 1
+        return f"\n\n**[表格 {tbl_count}]**\n{match.group(0)}\n"
+
+    # 匹配连续的表格块
+    table_block_regex = r'(\|.*\|[\r\n]+)+(\|[\s\-:|]+\|[\r\n]+)(\|.*\|[\r\n]*)+'
+    content = re.sub(table_block_regex, tag_table, content)
+
+    # 4. 图片处理与清单 (保持不变)
+    img_count = 0
+    img_details = []
+    def img_replacer(m):
+        nonlocal img_count
+        img_count += 1
+        path = m.group(2) or m.group(3) or ""
+        filename = os.path.basename(path)
+        img_details.append(filename)
+        return f"\n\n**[图片 {img_count}: {filename}]**\n{m.group(0)}\n"
+    
+    content = re.sub(r'(!\[.*?\]\((.*?)\)|\[.*?\]:\s*([^\s]+\.(?:png|jpg|jpeg|gif|bmp))(\s*\{.*?\})?)', img_replacer, content)
+
+    # 5. 深度清洗噪声
+    content = re.sub(r'\[(.*?)\]\(\\l\)', r'\1', content)
+    content = re.sub(r'\[(.*?)\]\[\d+\]', r'\1', content)
+    content = re.sub(r'\{width=.*?\}', '', content)
+    content = re.sub(r'\n{3,}', '\n\n', content)
+
+    # 6. 保存元信息与清单
+    with open(images_list_file, 'w', encoding='utf-8') as f:
+        f.write(f"文档 {base_name} 图片清单：\n" + "="*30 + "\n")
+        for i, name in enumerate(img_details, 1):
+            f.write(f"{i}. {name}\n")
+
+    stats = {
+        "filename": base_name,
+        "table_count": tbl_count,
+        "image_count": img_count,
+        "char_count": len(content),
+        # 重新预估 Token，因为去掉了空格，这个值会更准
+        "estimated_tokens": int(len(content) * 0.6) 
+    }
+    with open(metadata_file, 'w', encoding='utf-8') as f:
+        json.dump(stats, f, indent=4, ensure_ascii=False)
+
+    with open(output_md, 'w', encoding='utf-8') as f:
+        f.write(content)
+
+    print(f"\n" + "="*60)
+    print(f"✅ 紧凑版转换完成！已去除冗余空格")
+    print(f"📁 文档: {output_md}")
+    print(f"📊 统计: {img_count} 图片, {tbl_count} 表格")
+    print(f"📉 Token 节省: 预估比原版节省 30% 空间")
+    print("="*60)
+
+if __name__ == "__main__":
+    convert_compact_mode("a2.docx")