#!/usr/bin/env python3 """Lightweight AI工作区 project lookup index updater. Writes only inside /Users/bot1/Volumes/root_for_ai/AI工作区/00_AI工作区项目索引. It does not create Git repos, push, or touch the old remote-repository mapping folder. """ from __future__ import annotations import argparse import json import re import sys from datetime import datetime from pathlib import Path from typing import Any AI_WORK_ROOT = Path("/Users/bot1/Volumes/root_for_ai/AI工作区") INDEX_ROOT = AI_WORK_ROOT / "00_AI工作区项目索引" PROJECTS_DIR = INDEX_ROOT / "projects" INDEX_JSON = INDEX_ROOT / "project_index.json" INDEX_MD = INDEX_ROOT / "AI工作区项目映射表.md" def now_local() -> str: return datetime.now().astimezone().isoformat(timespec="seconds") def slugify_folder_name(path: Path) -> str: name = path.name.strip() # Keep Chinese and common readable chars; replace unsafe separators. name = re.sub(r"[\\/:*?\"<>|\s]+", "_", name) name = re.sub(r"_+", "_", name).strip("_") return name or "unnamed_project" def split_keywords(text: str) -> list[str]: if not text: return [] parts = re.split(r"[,，、;；\n]+", text) return [p.strip() for p in parts if p.strip()] def read_index() -> dict[str, Any]: if not INDEX_JSON.exists(): return {"version": 1, "updated_at": now_local(), "projects": {}} try: data = json.loads(INDEX_JSON.read_text(encoding="utf-8")) if not isinstance(data, dict): raise ValueError("index root is not object") data.setdefault("version", 1) data.setdefault("projects", {}) return data except Exception: # Do not destroy unreadable old index silently; keep a backup name. backup = INDEX_JSON.with_suffix(INDEX_JSON.suffix + f".unreadable_{datetime.now():%Y%m%d_%H%M%S}.bak") INDEX_JSON.rename(backup) return {"version": 1, "updated_at": now_local(), "projects": {}} def project_card(record: dict[str, Any]) -> str: deliverables = record.get("key_deliverables") or [] deliverable_lines = "\n".join(f"- `{x}`" for x in deliverables) if deliverables else "- 暂无" keywords = ", ".join(record.get("keywords") or []) aliases = ", ".join(record.get("aliases") or []) events = record.get("events") or [] event_lines = "\n".join( f"- {e.get('time','')}｜{e.get('profile','')}｜{e.get('event','')}" for e in events[-8:] ) or "- 暂无" return f"""# {record.get('title') or record['folder_name']} ```yaml folder_name: "{record['folder_name']}" project_id: "{record['project_id']}" status: "{record.get('status','active')}" path: "{record['path']}" created_at: "{record.get('created_at','')}" last_updated: "{record.get('last_updated','')}" owner_profile: "{record.get('owner_profile','')}" related_org_or_ip: "{record.get('related_org_or_ip','')}" use_case: "{record.get('use_case','')}" ``` ## Summary {record.get('summary') or '暂无摘要。'} ## Keywords {keywords or '暂无'} ## Aliases {aliases or '暂无'} ## Key deliverables / current useful files {deliverable_lines} ## Maintenance events {event_lines} ## Robot lookup note 优先返回本卡片的 `path`，再在该项目目录内做限定范围搜索。不要把本索引等同于 Git/远程仓库映射；本索引只服务 AI工作区项目查找和 RAG 检索。 """ def write_outputs(data: dict[str, Any]) -> None: PROJECTS_DIR.mkdir(parents=True, exist_ok=True) data["updated_at"] = now_local() INDEX_JSON.write_text(json.dumps(data, ensure_ascii=False, indent=2, sort_keys=True) + "\n", encoding="utf-8") rows = sorted(data.get("projects", {}).values(), key=lambda r: (r.get("last_updated", ""), r.get("folder_name", "")), reverse=True) lines = [ "# AI工作区项目映射表", "", f"更新时间：{data['updated_at']}", "", "用途：给机器人和 RAG 快速查询 `/Users/bot1/Volumes/root_for_ai/AI工作区` 下的项目位置、关键词、当前状态和关键交付物。", "", "维护边界：这是轻量项目查找索引，不是 Git/Gitee/远程仓库映射表；不要在这里记录密钥、长聊天记录、过程日志或大段临时草稿。", "", "| 项目 | 路径 | 关键词 | 状态 | 更新 |", "| --- | --- | --- | --- | --- |", ] for r in rows: kws = "、".join((r.get("keywords") or [])[:10]) lines.append(f"| {r.get('title') or r.get('folder_name')} | `{r.get('path')}` | {kws} | {r.get('status','active')} | {r.get('last_updated','')} |") lines.append("") lines.append("## 项目卡片") lines.append("") for r in rows: card_name = slugify_folder_name(Path(r["path"])) + ".md" rel = f"projects/{card_name}" lines.append(f"- [{r.get('title') or r.get('folder_name')}]({rel})") (PROJECTS_DIR / card_name).write_text(project_card(r), encoding="utf-8") INDEX_MD.write_text("\n".join(lines) + "\n", encoding="utf-8") def main(argv=None) -> int: ap = argparse.ArgumentParser(description="Update lightweight AI工作区 project lookup index") ap.add_argument("--path", required=True, help="Project folder path under AI工作区") ap.add_argument("--title", default="", help="Human-readable project title") ap.add_argument("--summary", default="", help="Short current-state summary") ap.add_argument("--keywords", default="", help="Comma/Chinese-comma separated lookup keywords") ap.add_argument("--aliases", default="", help="Comma/Chinese-comma separated aliases") ap.add_argument("--owner-profile", default="", help="Profile/bot maintaining this record") ap.add_argument("--related-org-or-ip", default="", help="所属项目/IP/客户，如 良渚、国博") ap.add_argument("--use-case", default="", help="用途，如 详情页、主图、吉祥物、头像") ap.add_argument("--status", default="active") ap.add_argument("--event", default="", help="Maintenance event description") ap.add_argument("--deliverable", action="append", default=[], help="Key deliverable/current file path, relative or absolute") args = ap.parse_args(argv) path = Path(args.path).expanduser().resolve() try: path.relative_to(AI_WORK_ROOT.resolve()) except ValueError: print(f"ERROR: path must be under {AI_WORK_ROOT}: {path}", file=sys.stderr) return 2 if not path.exists() or not path.is_dir(): print(f"ERROR: project path does not exist or is not a directory: {path}", file=sys.stderr) return 3 if path == INDEX_ROOT or INDEX_ROOT in path.parents: print("ERROR: do not register the index folder as a project", file=sys.stderr) return 4 data = read_index() projects = data.setdefault("projects", {}) project_id = slugify_folder_name(path) existing = projects.get(project_id, {}) now = now_local() keywords = list(dict.fromkeys((existing.get("keywords") or []) + split_keywords(args.keywords))) aliases = list(dict.fromkeys((existing.get("aliases") or []) + split_keywords(args.aliases))) deliverables = list(dict.fromkeys((existing.get("key_deliverables") or []) + list(args.deliverable or []))) events = existing.get("events") or [] if args.event: events.append({"time": now, "profile": args.owner_profile or existing.get("owner_profile", ""), "event": args.event}) record = { "project_id": project_id, "folder_name": path.name, "title": args.title or existing.get("title") or path.name, "path": str(path), "status": args.status or existing.get("status") or "active", "created_at": existing.get("created_at") or now, "last_updated": now, "owner_profile": args.owner_profile or existing.get("owner_profile", ""), "related_org_or_ip": args.related_org_or_ip or existing.get("related_org_or_ip", ""), "use_case": args.use_case or existing.get("use_case", ""), "summary": args.summary or existing.get("summary", ""), "keywords": keywords, "aliases": aliases, "key_deliverables": deliverables, "events": events[-20:], } projects[project_id] = record write_outputs(data) print(json.dumps({"ok": True, "project_id": project_id, "index": str(INDEX_MD), "card": str(PROJECTS_DIR / (project_id + '.md'))}, ensure_ascii=False, indent=2)) return 0 if __name__ == "__main__": raise SystemExit(main())