#!/usr/bin/env python3
"""
路径探子 · Path Scout · ICE-GL-ZY-AGT-PATH-002

铸渊需要找文件？路径探子瞬间定位。
不需要grep翻遍整个仓库——探子知道每个角落。

用法:
  python3 scout.py find gatekeeper        # 模糊搜索文件名
  python3 scout.py where brain/            # 列出目录结构
  python3 scout.py index                   # 重建文件索引
"""

import json
import os
import sys
from pathlib import Path

REPO_ROOT = Path(__file__).resolve().parent.parent.parent
INDEX_FILE = Path(__file__).resolve().parent / "file-index.json"

# 忽略目录
IGNORE_DIRS = {".git", "node_modules", "__pycache__", ".DS_Store", "output", "dist", ".next"}

def build_index():
    """扫描整个仓库，建立文件索引"""
    index = {"files": {}, "dirs": {}}

    for root, dirs, files in os.walk(REPO_ROOT):
        # 过滤忽略目录
        dirs[:] = [d for d in dirs if d not in IGNORE_DIRS]

        rel_root = os.path.relpath(root, REPO_ROOT)
        if rel_root == ".":
            rel_root = ""

        # 记录目录
        if rel_root:
            index["dirs"][rel_root] = {
                "file_count": len(files),
                "subdir_count": len(dirs)
            }

        # 记录文件
        for f in files:
            rel_path = os.path.join(rel_root, f) if rel_root else f
            full_path = os.path.join(root, f)
            try:
                size = os.path.getsize(full_path)
            except:
                size = 0
            index["files"][rel_path] = {
                "size": size,
                "ext": os.path.splitext(f)[1]
            }

    # 保存索引
    INDEX_FILE.parent.mkdir(parents=True, exist_ok=True)
    with open(INDEX_FILE, "w") as f:
        json.dump(index, f, indent=2, ensure_ascii=False)

    return {
        "status": "ok",
        "total_files": len(index["files"]),
        "total_dirs": len(index["dirs"]),
        "index_file": str(INDEX_FILE)
    }

def load_index():
    """加载已有索引"""
    if INDEX_FILE.exists():
        with open(INDEX_FILE) as f:
            return json.load(f)
    return None

def find_file(pattern):
    """搜索文件"""
    index = load_index()
    if not index:
        return {"error": "索引不存在，先运行 scout.py index"}

    matches = []
    pattern_lower = pattern.lower()
    for path, info in index["files"].items():
        if pattern_lower in path.lower():
            matches.append({"path": path, "size": info["size"]})

    # 按路径排序
    matches.sort(key=lambda x: x["path"])
    return {"pattern": pattern, "matches": matches, "count": len(matches)}

def list_dir(path=""):
    """列出目录结构"""
    index = load_index()
    if not index:
        return {"error": "索引不存在，先运行 scout.py index"}

    # 列出直接子目录和文件
    subdirs = []
    files = []

    prefix = path.rstrip("/") + "/" if path else ""

    for d in index["dirs"]:
        if d.startswith(prefix) and d != prefix.rstrip("/"):
            rel = d[len(prefix):]
            if "/" not in rel:
                subdirs.append(d)

    for f in index["files"]:
        if f.startswith(prefix):
            rel = f[len(prefix):]
            if "/" not in rel:
                files.append({"name": rel, "size": index["files"][f]["size"]})

    return {"path": path or "/", "subdirs": subdirs, "files": files}

def search_content(pattern, file_pattern="*"):
    """在文件中搜索内容"""
    import subprocess
    cmd = ["grep", "-rl", "--include=" + file_pattern, pattern, str(REPO_ROOT)]
    try:
        result = subprocess.run(cmd, capture_output=True, text=True, timeout=30)
        files = [os.path.relpath(f, REPO_ROOT) for f in result.stdout.strip().split("\n") if f]
        return {"pattern": pattern, "matches": files, "count": len(files)}
    except:
        return {"error": "搜索失败"}

if __name__ == "__main__":
    if len(sys.argv) < 2:
        print("用法: scout.py <index|find|where|grep> [参数]")
        sys.exit(1)

    action = sys.argv[1]

    if action == "index":
        result = build_index()
        print(json.dumps(result, ensure_ascii=False, indent=2))

    elif action == "find" and len(sys.argv) > 2:
        result = find_file(sys.argv[2])
        print(json.dumps(result, ensure_ascii=False, indent=2))

    elif action == "where":
        path = sys.argv[2] if len(sys.argv) > 2 else ""
        result = list_dir(path)
        print(json.dumps(result, ensure_ascii=False, indent=2))

    elif action == "grep" and len(sys.argv) > 2:
        pattern = sys.argv[2]
        fp = sys.argv[3] if len(sys.argv) > 3 else "*"
        result = search_content(pattern, fp)
        print(json.dumps(result, ensure_ascii=False, indent=2))