ALL-teach_sys/frontend_智能制造/merge_interview_questions.py

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
import re
import json
from datetime import datetime

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

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

def merge_questions_in_industry(industry_data):
    """将一个岗位群的多个questions组合并成一个"""

    # 找到questions数组的起始和结束位置
    questions_start = industry_data.find('"questions": [')
    if questions_start == -1:
        return industry_data

    questions_start += len('"questions": [')

    # 找到questions数组的结束
    bracket_count = 1
    i = questions_start
    in_string = False
    escape_next = False

    while i < len(industry_data) and bracket_count > 0:
        char = industry_data[i]

        if escape_next:
            escape_next = False
        elif char == '\\':
            escape_next = True
        elif char == '"' and not escape_next:
            in_string = not in_string
        elif not in_string:
            if char == '[':
                bracket_count += 1
            elif char == ']':
                bracket_count -= 1
        i += 1

    if bracket_count != 0:
        return industry_data

    questions_end = i - 1
    questions_content = industry_data[questions_start:questions_end]

    # 解析questions数组内容
    # 提取所有subQuestions
    all_sub_questions = []
    question_counter = 1

    # 查找所有的subQuestions
    pattern = r'"subQuestions":\s*\[(.*?)\](?:\s*}\s*]|\s*}\s*,)'
    matches = re.finditer(pattern, questions_content, re.DOTALL)

    for match in matches:
        sub_questions_str = match.group(1)

        # 解析每个子问题
        sub_pattern = r'"question":\s*"([^"\\]*(?:\\.[^"\\]*)*)",\s*"answer":\s*"([^"\\]*(?:\\.[^"\\]*)*)"'
        sub_matches = re.finditer(sub_pattern, sub_questions_str)

        for sub_match in sub_matches:
            question_text = sub_match.group(1)
            answer_text = sub_match.group(2)

            # 处理答案格式
            # 1. 如果是选择题答案（如 "A" 或 "B" 等单个字母），保持原样
            # 2. 其他答案需要处理换行
            if len(answer_text.strip()) == 1 and answer_text.strip() in 'ABCDEFGH':
                # 选择题答案，保持原样
                formatted_answer = answer_text
            else:
                # 处理换行符，确保正确显示
                formatted_answer = answer_text.replace('\\n', '<br/>')
                # 如果答案包含选项（A. B. C. 等），只保留文字说明
                if re.search(r'\s*[A-H]\.\s*', formatted_answer):
                    # 移除选项标识，保留内容
                    formatted_answer = re.sub(r'\s*[A-H]\.\s*', '', formatted_answer)

            all_sub_questions.append({
                'id': f'q_{question_counter}',
                'question': question_text,
                'answer': formatted_answer
            })
            question_counter += 1

    # 构建新的questions数组（只包含一个大的question对象）
    merged_question = {
        'id': 'merged_questions',
        'question': '综合面试题集',
        'subQuestions': all_sub_questions
    }

    # 生成新的questions数组字符串
    new_questions_str = '\n      {\n'
    new_questions_str += '        "id": "merged_questions",\n'
    new_questions_str += '        "question": "综合面试题集",\n'
    new_questions_str += '        "subQuestions": [\n'

    for idx, q in enumerate(all_sub_questions):
        question_escaped = q['question'].replace('"', '\\"')
        answer_escaped = q['answer'].replace('"', '\\"')

        new_questions_str += '          {\n'
        new_questions_str += f'            "id": "{q["id"]}",\n'
        new_questions_str += f'            "question": "{question_escaped}",\n'
        new_questions_str += f'            "answer": "{answer_escaped}"\n'
        new_questions_str += '          }'

        if idx < len(all_sub_questions) - 1:
            new_questions_str += ','
        new_questions_str += '\n'

    new_questions_str += '        ]\n'
    new_questions_str += '      }\n    '

    # 替换原来的questions数组内容
    before_questions = industry_data[:questions_start]
    after_questions = industry_data[questions_end:]

    return before_questions + new_questions_str + after_questions

# 处理每个岗位群
industries_pattern = r'(\{\s*"id":\s*"manufacturing_\d+".*?"questions":\s*\[.*?\]\s*\})'

def replace_industry(match):
    industry_data = match.group(1)
    return merge_questions_in_industry(industry_data)

# 分段处理以避免递归深度问题
lines = content.split('\n')
in_industry = False
industry_lines = []
result_lines = []
industry_start = -1

for i, line in enumerate(lines):
    if '"id": "manufacturing_' in line and not in_industry:
        in_industry = True
        industry_start = i
        industry_lines = [line]
    elif in_industry:
        industry_lines.append(line)
        # 检查是否是industry的结束
        if '    },' in line or '    }' in line:
            # 如果下一行是positions或questions，说明还没结束
            if i + 1 < len(lines):
                next_line = lines[i + 1]
                if '"positions":' in next_line or '"questions":' in next_line:
                    continue

            # 处理这个industry
            industry_text = '\n'.join(industry_lines)
            processed_industry = merge_questions_in_industry(industry_text)

            # 将处理后的内容添加到结果
            result_lines.extend(processed_industry.split('\n'))

            in_industry = False
            industry_lines = []
    else:
        result_lines.append(line)

# 如果最后还有未处理的industry
if industry_lines:
    industry_text = '\n'.join(industry_lines)
    processed_industry = merge_questions_in_industry(industry_text)
    result_lines.extend(processed_industry.split('\n'))

# 合并结果
final_content = '\n'.join(result_lines)

# 保存处理后的文件
with open('src/mocks/resumeInterviewMock.js', 'w', encoding='utf-8') as f:
    f.write(final_content)

print("✅ 面试题合并完成！")
print("- 所有题目已合并到同一张卡片")
print("- 答案换行已转换为<br/>标签")
print("- 选择题答案已处理为只显示正确答案")