#!/usr/bin/env python3
"""
Anchor Vault Sync & Search
轻量级 Obsidian Vault 索引与检索脚本
路径: ~/.hermes/anchor_vault_sync.py
"""
import os
import sys
import json
import re
from datetime import datetime
from pathlib import Path

VAULT_PATH = "/Users/fyah/Documents/如梦初醒/memory/test"
INDEX_PATH = os.path.expanduser("~/.hermes/anchor_vault_index.json")
SKIP_DIRS = {".obsidian", ".trash", ".smart-env", ".space", ".makemd", ".git"}
PREVIEW_LEN = 300

def parse_yaml_frontmatter(content):
    """极简 YAML 解析，只取 tags 和 title"""
    tags = []
    title = ""
    if content.startswith("---"):
        parts = content.split("---", 2)
        if len(parts) >= 2:
            yaml_block = parts[1]
            for line in yaml_block.splitlines():
                if line.startswith("tags:"):
                    # 处理 tags: [a, b] 或 tags:\n  - a\n  - b
                    rest = line[5:].strip()
                    if rest.startswith("["):
                        tags = [t.strip().strip("'\"") for t in rest[1:-1].split(",")]
                    else:
                        tags = []
                elif line.startswith("  - "):
                    if "tags" in locals() and tags is not None: # 简单判断是否在 tags 块下
                        tags.append(line.strip().strip("- ").strip("'\""))
                elif line.startswith("title:"):
                    title = line[6:].strip().strip("'\"")
    return tags, title

def scan_vault():
    """扫描 Vault 并生成索引"""
    print(f"[*] 开始扫描: {VAULT_PATH}")
    index = []
    count = 0
    
    for root, dirs, files in os.walk(VAULT_PATH):
        # 过滤隐藏目录
        dirs[:] = [d for d in dirs if d not in SKIP_DIRS and not d.startswith(".")]
        
        for file in files:
            if not file.endswith(".md"):
                continue
            
            filepath = os.path.join(root, file)
            rel_path = os.path.relpath(filepath, VAULT_PATH)
            
            try:
                with open(filepath, "r", encoding="utf-8") as f:
                    content = f.read()
                
                tags, title = parse_yaml_frontmatter(content)
                mtime = os.path.getmtime(filepath)
                mtime_str = datetime.fromtimestamp(mtime).strftime("%Y-%m-%d %H:%M")
                
                # 提取预览（去掉 YAML 头和空行）
                body = content.split("---", 2)[-1].strip()
                preview = body[:PREVIEW_LEN].replace("\n", " ").strip()
                if len(body) > PREVIEW_LEN:
                    preview += "..."
                
                index.append({
                    "path": rel_path,
                    "title": title or Path(file).stem,
                    "tags": tags,
                    "mtime": mtime_str,
                    "preview": preview
                })
                count += 1
            except Exception as e:
                print(f"[!] 读取失败 {rel_path}: {e}")
    
    # 保存索引
    with open(INDEX_PATH, "w", encoding="utf-8") as f:
        json.dump(index, f, ensure_ascii=False, indent=2)
        
    print(f"[+] 同步完成。共索引 {count} 个文件。")
    print(f"[+] 索引已保存至: {INDEX_PATH}")
    return index

def search_vault(query):
    """基于关键词搜索索引"""
    if not os.path.exists(INDEX_PATH):
        print("[-] 索引不存在，请先运行 sync。")
        return []
        
    with open(INDEX_PATH, "r", encoding="utf-8") as f:
        index = json.load(f)
        
    results = []
    q_lower = query.lower()
    
    for item in index:
        # 匹配标题、标签、预览
        score = 0
        if q_lower in item["title"].lower(): score += 3
        if any(q_lower in t.lower() for t in item["tags"]): score += 2
        if q_lower in item["preview"].lower(): score += 1
        
        if score > 0:
            item["score"] = score
            results.append(item)
            
    # 按分数排序
    results.sort(key=lambda x: x["score"], reverse=True)
    
    if not results:
        print(f"[-] 未找到与 '{query}' 相关的内容。")
        return []
        
    print(f"[+] 找到 {len(results)} 条相关记忆（Top 5）：")
    for r in results[:5]:
        print(f"\n📄 {r['title']} ({r['path']})")
        print(f"🏷️ 标签: {', '.join(r['tags']) if r['tags'] else '无'}")
        print(f"🕒 更新: {r['mtime']}")
        print(f"👁️ 预览: {r['preview'][:100]}...")
        
    return results

if __name__ == "__main__":
    if len(sys.argv) < 2:
        print("用法: python3 anchor_vault_sync.py [sync|search <关键词>]")
        sys.exit(1)
        
    cmd = sys.argv[1]
    if cmd == "sync":
        scan_vault()
    elif cmd == "search":
        if len(sys.argv) < 3:
            print("[-] 搜索需要关键词。用法: search <关键词>")
            sys.exit(1)
        query = " ".join(sys.argv[2:])
        search_vault(query)
    else:
        print(f"[-] 未知命令: {cmd}")