#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
清理面试题答案中的选项，只保留正确答案
"""

import re
from datetime import datetime

print("=== 清理面试题答案中的选项 ===\n")

# 1. 读取当前mock文件
print("1. 读取当前mock文件...")
with open('src/mocks/resumeInterviewMock.js', 'r', encoding='utf-8') as f:
    content = f.read()

# 2. 备份
backup_time = datetime.now().strftime('%Y%m%d_%H%M%S')
backup_file = f'src/mocks/resumeInterviewMock.js.backup_clean_options_{backup_time}'
print(f"2. 创建备份: {backup_file}")
with open(backup_file, 'w', encoding='utf-8') as f:
    f.write(content)

# 3. 处理答案中的选项
print("\n3. 开始清理答案中的选项...")

def clean_answer(match):
    """清理答案中的选项格式"""
    full_match = match.group(0)
    answer_content = match.group(1)

    # 检查是否包含选项格式（A. B. C. 或 A、B、C、等）
    if re.search(r'[A-D][\.、]', answer_content):
        # 尝试提取正确答案
        # 模式1: "正确答案是A" 或 "答案：A"
        correct_match = re.search(r'(?:正确答案[是为：:]*|答案[是为：:]*)\s*([A-D])', answer_content)
        if correct_match:
            option_letter = correct_match.group(1)
            # 查找该选项的内容
            option_pattern = rf'{option_letter}[\.、]\s*([^A-D\n]+?)(?=[A-D][\.、]|$)'
            option_content = re.search(option_pattern, answer_content)
            if option_content:
                # 返回只包含正确答案内容的版本
                cleaned_answer = option_content.group(1).strip()
                # 去除可能的句号或其他标点
                cleaned_answer = re.sub(r'[。；;]+$', '', cleaned_answer)
                return f'"answer": "{cleaned_answer}"'

        # 模式2: 选项列表后跟正确答案说明
        # 例如："A. 选项1 B. 选项2 C. 选项3 D. 选项4。正确答案是C"
        if '正确答案' in answer_content or '答案' in answer_content:
            # 提取所有选项
            options = {}
            option_matches = re.findall(r'([A-D])[\.、]\s*([^A-D\n]+?)(?=[A-D][\.、]|正确答案|答案|$)', answer_content)
            for letter, content in option_matches:
                options[letter] = content.strip().rstrip('。；;')

            # 找出正确答案
            correct_match = re.search(r'(?:正确答案|答案)[是为：:]*\s*([A-D])', answer_content)
            if correct_match and correct_match.group(1) in options:
                return f'"answer": "{options[correct_match.group(1)]}"'

    # 如果没有选项格式或无法处理，返回原始内容
    return full_match

# 4. 执行替换
original_content = content
# 匹配 "answer": "..." 模式
pattern = r'"answer":\s*"([^"]*(?:\\.[^"]*)*)"'

# 统计处理的答案数量
matches = re.findall(pattern, content)
total_answers = len(matches)
print(f"找到 {total_answers} 个答案")

# 处理包含选项的答案
processed = 0
for match in re.finditer(pattern, content):
    answer_text = match.group(1)
    if re.search(r'[A-D][\.、]', answer_text):
        processed += 1

print(f"其中 {processed} 个答案包含选项格式")

# 执行替换
content = re.sub(pattern, clean_answer, content)

# 5. 额外的清理模式
print("\n4. 执行额外的清理模式...")

# 清理常见的选项格式
def additional_clean(text):
    """额外的清理规则"""
    # 移除"选项："开头
    text = re.sub(r'"answer":\s*"选项[：:]\s*', '"answer": "', text)

    # 如果答案以单个字母开头（如"A 内容"），去掉字母
    text = re.sub(r'"answer":\s*"[A-D]\s+([^"]+)"', r'"answer": "\1"', text)

    # 如果答案以"A."或"A、"开头，去掉
    text = re.sub(r'"answer":\s*"[A-D][\.、]\s*([^"]+)"', r'"answer": "\1"', text)

    return text

content = additional_clean(content)

# 6. 保存文件
print("\n5. 保存更新后的文件...")
with open('src/mocks/resumeInterviewMock.js', 'w', encoding='utf-8') as f:
    f.write(content)

# 7. 验证语法
print("\n6. 验证语法...")
import subprocess
result = subprocess.run(['node', '-c', 'src/mocks/resumeInterviewMock.js'],
                       capture_output=True, text=True)

if result.returncode == 0:
    print("✅ 语法检查通过！")

    # 检查是否有变化
    if content != original_content:
        # 再次统计包含选项的答案
        remaining_options = len(re.findall(r'"answer":\s*"[^"]*[A-D][\.、]', content))
        print(f"\n清理结果：")
        print(f"- 原始包含选项的答案: {processed} 个")
        print(f"- 剩余包含选项的答案: {remaining_options} 个")
        print(f"- 成功清理: {processed - remaining_options} 个")
    else:
        print("\n未发现需要清理的选项格式")
else:
    print("❌ 语法错误：")
    print(result.stderr)
    print("\n正在恢复备份...")
    with open(backup_file, 'r', encoding='utf-8') as f:
        content = f.read()
    with open('src/mocks/resumeInterviewMock.js', 'w', encoding='utf-8') as f:
        f.write(content)
    print("已恢复到备份版本")

print("\n✅ 清理完成！")