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

import re

print("安全清理重复的questions数组...")

# 读取文件
with open('/Users/apple/Documents/cursor/教务系统/frontend_大健康/src/mocks/resumeInterviewMock.js', 'r', encoding='utf-8') as f:
    content = f.read()

# 备份
with open('/Users/apple/Documents/cursor/教务系统/frontend_大健康/src/mocks/resumeInterviewMock.js.backup_clean_safe', 'w', encoding='utf-8') as f:
    f.write(content)

# 对每个岗位群，找到并删除第二个questions数组
industries = ['health_1', 'health_2', 'health_3', 'health_4', 'health_5',
              'health_6', 'health_7', 'health_8', 'health_9', 'health_10', 'health_11']

for industry_id in industries:
    print(f"处理 {industry_id}...")

    # 找到该岗位群
    pattern = rf'"id":\s*"{industry_id}"'
    match = re.search(pattern, content)

    if not match:
        continue

    start = match.start()

    # 找到下一个岗位群或数组结束
    next_pattern = rf'"id":\s*"health_\d+"'
    next_matches = list(re.finditer(next_pattern, content[start + 10:]))

    if next_matches:
        end = start + 10 + next_matches[0].start()
    else:
        # 最后一个岗位群
        end_match = re.search(r'\n\];', content[start:])
        if end_match:
            end = start + end_match.start()
        else:
            end = len(content)

    # 获取该岗位群的内容
    industry_content = content[start:end]

    # 查找所有questions数组的开始位置
    questions_matches = list(re.finditer(r'"questions":\s*\[', industry_content))

    if len(questions_matches) > 1:
        print(f"  发现 {len(questions_matches)} 个questions数组")

        # 找到第二个questions的开始和结束
        second_start = questions_matches[1].start()

        # 计算括号平衡找到第二个questions的结束
        bracket_count = 0
        in_array = False
        second_end = -1

        for i in range(second_start, len(industry_content)):
            if industry_content[i] == '[':
                if not in_array and '"questions"' in industry_content[max(0, i-20):i]:
                    in_array = True
                    bracket_count = 1
                elif in_array:
                    bracket_count += 1
            elif industry_content[i] == ']' and in_array:
                bracket_count -= 1
                if bracket_count == 0:
                    second_end = i + 1
                    break

        if second_end > 0:
            # 找到第二个questions前的逗号
            comma_before = industry_content.rfind(',', 0, second_start)

            # 删除从逗号到questions结束的内容
            if comma_before > 0:
                new_industry_content = industry_content[:comma_before] + industry_content[second_end:]

                # 替换原内容
                content = content[:start] + new_industry_content + content[end:]

                print(f"  ✓ 删除了 {industry_id} 的第二个questions数组")

# 写回文件
with open('/Users/apple/Documents/cursor/教务系统/frontend_大健康/src/mocks/resumeInterviewMock.js', 'w', encoding='utf-8') as f:
    f.write(content)

print("✓ 清理完成！")