#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
HTTP 错误日志分析脚本

扫描 logs/*/dashboard.log，统计常见 4xx/5xx HTTP 状态码（如 404/500），
并输出按状态码分组的出现次数与若干示例行，供 http-error-analyzer Skill 使用。
"""

import os
import re
from pathlib import Path
from typing import Dict, List, Tuple


LOG_ROOT = Path("logs")
LOG_FILENAME = "dashboard.log"
MAX_FILES = 5  # 最多分析最近 N 个日志文件

# 简单匹配常见 HTTP 错误码；根据你实际日志格式可以再调整
ERROR_CODES = [404, 500, 502, 503]
CODE_PATTERNS: Dict[int, re.Pattern] = {
    code: re.compile(rf"\b{code}\b") for code in ERROR_CODES
}


def find_log_files() -> List[Path]:
    if not LOG_ROOT.exists():
        return []

    candidates: List[Tuple[float, Path]] = []
    for root, dirs, files in os.walk(LOG_ROOT):
        if LOG_FILENAME in files:
            p = Path(root) / LOG_FILENAME
            try:
                mtime = p.stat().st_mtime
            except OSError:
                continue
            candidates.append((mtime, p))

    candidates.sort(key=lambda x: x[0], reverse=True)
    return [p for _, p in candidates[:MAX_FILES]]


def analyze_file(path: Path):
    """
    返回:
      counts: {status_code: 次数}
      samples: {status_code: [示例行1, 示例行2, ...]}
    """
    counts: Dict[int, int] = {code: 0 for code in ERROR_CODES}
    samples: Dict[int, List[str]] = {code: [] for code in ERROR_CODES}

    try:
        with path.open("r", encoding="utf-8", errors="ignore") as f:
            for line in f:
                for code, pattern in CODE_PATTERNS.items():
                    if pattern.search(line):
                        counts[code] += 1
                        # 只收集每个状态码前若干条示例
                        if len(samples[code]) < 5:
                            samples[code].append(line.strip()[:300])
                        break
    except OSError as e:
        print(f"[!] 读取日志失败 {path}: {e}")
        return None

    return counts, samples


def main():
    log_files = find_log_files()
    if not log_files:
        print("未找到任何日志文件（logs/*/dashboard.log）。")
        return

    overall_counts: Dict[int, int] = {code: 0 for code in ERROR_CODES}
    overall_samples: Dict[int, List[str]] = {code: [] for code in ERROR_CODES}

    print(f"=== HTTP 错误日志分析（最近最多 {MAX_FILES} 个日志文件）===\n")

    for idx, path in enumerate(log_files, start=1):
        print(f"[{idx}] 日志文件: {path}")
        result = analyze_file(path)
        if result is None:
            print("    无法读取该日志文件。\n")
            continue

        counts, samples = result
        any_error = any(counts[code] > 0 for code in ERROR_CODES)

        if not any_error:
            print("    未发现 404/500/502/503 等 HTTP 错误。")
            print()
            continue

        for code in ERROR_CODES:
            c = counts[code]
            if c == 0:
                continue
            overall_counts[code] += c
            overall_samples[code].extend(samples[code])
            print(f"    状态码 {code}: {c} 次")
            if samples[code]:
                print("      示例：")
                for line in samples[code]:
                    print(f"        {line}")

        print()

    print("=== 汇总统计 ===")
    any_overall = any(overall_counts[code] > 0 for code in ERROR_CODES)
    if not any_overall:
        print("  未在最近的日志文件中发现任何配置的 HTTP 错误状态码。")
        return

    for code in ERROR_CODES:
        c = overall_counts[code]
        if c == 0:
            continue
        print(f"  状态码 {code}: {c} 次")

    print("\n提示：以上为按状态码汇总的次数与部分示例行，")
    print("你可以结合 URL 路径、接口名称、堆栈片段来推断可能的路由配置问题、权限问题或后端异常。")


if __name__ == "__main__":
    main()