#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
验证清理后的答案
"""

import re

print("=== 验证清理后的答案 ===\n")

# 读取文件
with open('src/mocks/resumeInterviewMock.js', 'r', encoding='utf-8') as f:
    content = f.read()

# 统计总答案数
total_answers = len(re.findall(r'"answer":\s*"[^"]*"', content))
print(f"总答案数: {total_answers}")

# 检查是否还有选项格式
option_patterns = [
    (r'"answer":\s*"[^"]*[A-D][\.、][^"]*"', "包含 A. B. C. D. 格式"),
    (r'"answer":\s*"选项[：:][^"]*"', "以'选项：'开头"),
    (r'"answer":\s*"[A-D]\s+[^"]*"', "以单个字母开头"),
]

print("\n检查剩余的选项格式：")
has_options = False
for pattern, description in option_patterns:
    matches = re.findall(pattern, content)
    if matches:
        print(f"\n{description}: {len(matches)} 个")
        for match in matches[:3]:  # 显示前3个示例
            # 提取答案内容
            answer_text = re.search(r'"answer":\s*"([^"]*)"', match)
            if answer_text:
                print(f"  - {answer_text.group(1)[:80]}...")
        has_options = True

if not has_options:
    print("✅ 没有发现明显的选项格式")

# 显示一些成功清理的例子
print("\n\n成功清理的示例：")
examples = [
    "示教器操作时，必须佩戴",
    "机器人运行时，人员应",
    "安全围栏的作用是",
    "工具标定不准确会导致",
    "每日交接班必须做的是"
]

for question in examples:
    pattern = f'"question":\s*"{question}",\s*\n\s*"answer":\s*"([^"]*)"'
    match = re.search(pattern, content)
    if match:
        print(f"问题: {question}")
        print(f"答案: {match.group(1)}")
        print("-" * 40)

print("\n✅ 验证完成！")