# 需求：递归遍历目录，把文件名按规则重命名，支持 dry-run 预览

import os
import json
import frontmatter

def extract_frontmatter(directory):
    result = {}
    for fname in os.listdir(directory):          # Bug: 不会递归遍历子目录
        if fname.endswith('.md'):
            with open(os.path.join(directory, fname)) as f:
                post = frontmatter.load(f)
                result[fname] = {
                    'title': post.get('title'),  # 没有处理空值
                    'tags': post.get('tags', [])
                }
    with open('index.json', 'w') as f:
        json.dump(result, f, indent=2)

#!/usr/bin/env python3
"""Extract title and tags from Markdown frontmatter across directories."""

import os
import json
import sys
from pathlib import Path
from typing import Dict, Any

try:
    import frontmatter
except ImportError:
    sys.exit("请先安装 python-frontmatter: pip install python-frontmatter")

def extract_frontmatter(root_dir: str) -> Dict[str, Dict[str, Any]]:
    """递归遍历目录，提取所有 .md 文件的 frontmatter。"""
    result = {}
    md_files = list(Path(root_dir).rglob("*.md"))  # 递归遍历

    if not md_files:
        print(f"⚠️ 在 {root_dir} 下没有找到 .md 文件")
        return result

    for md_path in md_files:
        try:
            with open(md_path, 'r', encoding='utf-8') as f:
                post = frontmatter.load(f)
            
            title = post.get('title') or md_path.stem  # 降级用文件名
            tags = post.get('tags', [])
            if isinstance(tags, str):
                tags = [tags]
            
            result[str(md_path.relative_to(root_dir))] = {
                'title': title,
                'tags': tags,
            }
        except Exception as e:
            print(f"❌ 处理 {md_path.name} 时出错: {e}")
            continue
    
    return result

def main():
    if len(sys.argv) < 2:
        root = Path.cwd()
    else:
        root = Path(sys.argv[1])
    
    if not root.is_dir():
        sys.exit(f"错误: {root} 不是有效目录")
    
    data = extract_frontmatter(str(root))
    output = root / "index.json"
    
    with open(output, 'w', encoding='utf-8') as f:
        json.dump(data, f, indent=2, ensure_ascii=False)
    
    print(f"✅ 已处理 {len(data)} 个文件 → {output}")

if __name__ == "__main__":
    main()

import os
import json
import yaml
import re
from pathlib import Path

def extract_frontmatter_md(filepath):
    """从 Markdown 文件中提取 YAML frontmatter"""
    with open(filepath, 'r', encoding='utf-8') as f:
        content = f.read()
    
    match = re.match(r'^---\s*\n(.*?)\n---\s*\n', content, re.DOTALL)
    if match:
        try:
            return yaml.safe_load(match.group(1))
        except yaml.YAMLError:
            return {}
    return {}

def build_index(root_dir, output="index.json"):
    data = {}
    for md_file in Path(root_dir).rglob("*.md"):
        fm = extract_frontmatter_md(md_file)
        relative = str(md_file.relative_to(root_dir))
        data[relative] = {
            "title": fm.get("title", md_file.stem),
            "tags": fm.get("tags", [])
        }
    
    with open(output, "w") as f:
        json.dump(data, f, indent=2)
    print(f"Indexed {len(data)} files to {output}")

if __name__ == "__main__":
    import sys
    root = sys.argv[1] if len(sys.argv) > 1 else "."
    build_index(root)