analy

#!/usr/bin/env python3
# -*- coding: utf-8 -*-

import sys
import re
import io

# 设置默认编码为utf-8
sys.stdout = io.TextIOWrapper(sys.stdout.buffer, encoding='utf-8')

def analyze_file(filename):
    try:
        with io.open(filename, 'r', encoding='utf-8') as file, io.open('res.txt', 'w', encoding='utf-8') as res_file:
            transactions = {}
            batch_id = None
            txn_id = None

            required_patterns = {
                'rc': re.compile(r'rc\s*=\s*\d+'),
                'enqueue': re.compile(r'enqueue work_queue'),
                'taken': re.compile(r'has been taken by worker'),
                'process': re.compile(r'will be process by worker'),
                'run': re.compile(r'enter into run_calvin_txn\(\)'),
                'wrapup': re.compile(r'enter into calvin_wrapup\(\)'),
                'return': re.compile(r'will return msg to sequencer')
            }

            for line in file:
                # 匹配事务开始的行
                start_match = re.match(r'batch_id\s*=\s*(\d+)\s*,\s*txn_id\s*=\s*(\d+)', line)
                if start_match:
                    batch_id, txn_id = start_match.groups()
                    key = (batch_id, txn_id)
                    if key not in transactions:
                        transactions[key] = {k: False for k in required_patterns}

                # 检查每个必须的模式
                if batch_id and txn_id:
                    key = (batch_id, txn_id)
                    for k, pattern in required_patterns.items():
                        if pattern.search(line):
                            transactions[key][k] = True

            # 检查每个事务并输出结果
            for (batch_id, txn_id), status in transactions.items():
                missing = [k for k, v in status.items() if not v]
                # 必须的行
                required_missing = ['rc', 'taken', 'wrapup', 'return']
                missing_required = [item for item in missing if item in required_missing]
                if missing_required:
                    res_file.write(f"batch_id = {batch_id} , txn_id = {txn_id} 欠缺带有{', '.join([required_patterns[item].pattern for item in missing_required])}的轨迹记录\n")

        print("分析完成，结果已写入res.txt。")

    except FileNotFoundError:
        print(f"文件 {filename} 不存在。")
    except Exception as e:
        print(f"发生错误：{e}")

if __name__ == "__main__":
    if len(sys.argv) != 2:
        print("使用方法: python3 analy <filename>")
        sys.exit(1)

    filename = sys.argv[1]
    analyze_file(filename)