AcidMap/app/log/error.py

import os
import re
import time
from datetime import datetime
from pathlib import Path
from typing import List, Dict, Optional
from fastapi import APIRouter, HTTPException
from pydantic import BaseModel

router = APIRouter()

# 获取项目根目录
project_root = Path(__file__).parent.parent.resolve()

# 构建日志目录路径
log_dir = project_root / "log"
log_dir.mkdir(parents=True, exist_ok=True)

ERROR_LOG_FILE = log_dir / "errors.log"


class ErrorDetailResponse(BaseModel):
    id: str
    timestamp: str
    level: str
    message: str
    traceback: List[str] = []
    related_entries: List[Dict] = []


def find_error_by_id(error_id: str) -> Optional[Dict]:
    """在错误日志文件中查找特定错误ID的条目"""
    if not ERROR_LOG_FILE.exists():
        return None

    # 日志格式: [时间戳] [级别] [模块] - 消息
    pattern = r"$$(?P<timestamp>\d{4}-\d{2}-\d{2} \d{2}:\d{2}:\d{2})$$\s+$$(?P<level>\w+)$$\s+$$.*?$$\s+-\s+(?P<message>.*)"

    with open(ERROR_LOG_FILE, 'r', encoding='utf-8') as f:
        for line in f:
            # 如果错误ID直接出现在行中
            if error_id in line:
                # 尝试匹配标准格式
                match = re.search(pattern, line)
                if match:
                    return {
                        "raw": line.strip(),
                        "timestamp": match.group("timestamp"),
                        "level": match.group("level"),
                        "id": error_id,
                        "full_line": line.strip(),
                        "message": match.group("message")
                    }
                else:
                    # 如果标准格式匹配失败，使用回退方法
                    # 尝试提取时间戳和级别
                    ts_match = re.search(r"$$(\d{4}-\d{2}-\d{2} \d{2}:\d{2}:\d{2})$$", line)
                    level_match = re.search(r"$$(\w+)$$", line)

                    return {
                        "raw": line.strip(),
                        "timestamp": ts_match.group(1) if ts_match else "Unknown",
                        "level": level_match.group(1) if level_match else "UNKNOWN",
                        "id": error_id,
                        "full_line": line.strip(),
                        "message": line.strip()
                    }

    return None


def extract_traceback(log_file: Path, error_id: str) -> List[str]:
    """提取错误相关的堆栈跟踪信息"""
    traceback_lines = []
    if not log_file.exists():
        return traceback_lines

    try:
        # 读取整个日志文件
        with open(log_file, 'r', encoding='utf-8') as f:
            lines = f.readlines()

        # 查找错误ID所在的行
        error_line_index = -1
        for i, line in enumerate(lines):
            if error_id in line:
                error_line_index = i
                break

        if error_line_index == -1:
            return traceback_lines

        # 向前查找堆栈跟踪开始
        start_index = error_line_index
        while start_index > 0:
            if "Traceback (most recent call last):" in lines[start_index]:
                break
            start_index -= 1

        # 向后查找堆栈跟踪结束
        end_index = error_line_index
        while end_index < len(lines) - 1:
            # 检查下一行是否是新日志条目开始
            next_line = lines[end_index + 1]
            if re.match(r"$$\d{4}-\d{2}-\d{2} \d{2}:\d{2}:\d{2}$$", next_line):
                break
            end_index += 1

        # 提取堆栈跟踪
        if start_index <= end_index:
            traceback_lines = [line.strip() for line in lines[start_index:end_index + 1]]
        else:
            traceback_lines = []

    except Exception as e:
        print(f"提取堆栈跟踪失败: {str(e)}")

    return traceback_lines


@router.get("/{error_id}", response_model=ErrorDetailResponse)
async def get_error_details(error_id: str):
    """根据错误ID查询完整错误信息"""
    print(f"正在查询错误ID: {error_id}")
    print(f"日志文件路径: {ERROR_LOG_FILE}")
    print(f"文件存在: {ERROR_LOG_FILE.exists()}")

    # 检查日志文件是否存在
    if not ERROR_LOG_FILE.exists():
        print(f"错误日志文件不存在: {ERROR_LOG_FILE}")
        raise HTTPException(status_code=500, detail="错误日志文件不存在")

    # 1. 查找主错误条目
    error_entry = find_error_by_id(error_id)

    if not error_entry:
        print(f"未找到错误ID: {error_id} 的日志条目")
        # 尝试直接搜索文件内容
        found = False
        try:
            with open(ERROR_LOG_FILE, 'r', encoding='utf-8') as f:
                for i, line in enumerate(f):
                    if error_id in line:
                        print(f"在行 {i} 找到包含错误ID的行: {line.strip()}")
                        found = True
            if not found:
                print("在日志文件中未找到包含错误ID的行")
        except Exception as e:
            print(f"读取日志文件失败: {str(e)}")

        raise HTTPException(status_code=404, detail="未找到指定的错误ID")

    # 2. 提取堆栈跟踪信息
    traceback_lines = extract_traceback(ERROR_LOG_FILE, error_id)

    # 如果没有找到堆栈跟踪，使用错误条目作为回退
    if not traceback_lines:
        traceback_lines = [error_entry["full_line"]]

    # 3. 解析错误消息
    # 如果已经有提取的消息，使用它
    if "message" in error_entry:
        message = error_entry["message"]
    else:
        # 否则尝试从完整行中提取消息
        message = error_entry["full_line"]
        # 尝试移除前面的时间戳和级别
        if " - " in message:
            message = message.split(" - ", 1)[-1]

    return ErrorDetailResponse(
        id=error_id,
        timestamp=error_entry["timestamp"],
        level=error_entry["level"],
        message=message,
        traceback=traceback_lines,
        related_entries=[]
    )