feat: nerd-Brain (呆脑子) - 初始提交

- anchor_writer.py: 记忆写入与情感打标 - anchor_search.py: 多维语义检索引擎 - anchor_decay.py: 遗忘曲线 + 归档 + 随机返场 - anchor_vault_sync.py: Vault 索引生成 - README.md: 项目说明文档
2026-04-26 22:19:40 +08:00
commit 837c5f66fb
5 changed files with 702 additions and 0 deletions
--- a/anchor_vault_sync.py
+++ b/anchor_vault_sync.py
@@ -0,0 +1,146 @@
+#!/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}")