online_sys/frontend_智能制造/import_all_interview_questions.py

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
完整导入所有岗位群的面试题
将智能制造岗位简历.json中的所有面试题导入到mock文件
"""

import json
import re
from datetime import datetime

print("=== 完整面试题导入工具 ===\n")

# 1. 读取源数据
print("1. 读取智能制造岗位简历.json...")
with open('网页未导入数据/智能制造产业/智能制造岗位简历.json', 'r', encoding='utf-8') as f:
    source_data = json.load(f)

# 2. 解析所有面试题
print("2. 解析面试题数据...")
interview_questions_map = {}

for item in source_data:
    job_group = item.get('简历岗位群', '')
    interview_content = item.get('面试题内容', '')

    if not job_group or not interview_content:
        continue

    # 收集所有问题（不分章节，统一放在一起）
    all_questions = []

    # 使用更宽松的正则表达式匹配问题
    lines = interview_content.split('\n')
    i = 0
    while i < len(lines):
        line = lines[i].strip()

        # 匹配问题编号（1. 或 1、）
        question_match = re.match(r'^(\d+)[\.、]\s*(.+)', line)
        if question_match:
            question_num = question_match.group(1)
            question_text = question_match.group(2).strip()

            # 查找答案
            answer = ""
            i += 1

            # 继续查找答案，直到遇到下一个问题或章节
            while i < len(lines):
                next_line = lines[i].strip()

                # 如果遇到下一个问题编号或章节标题，停止
                if re.match(r'^\d+[\.、]\s*', next_line) or next_line.startswith('#'):
                    i -= 1  # 回退，让外层循环处理
                    break

                # 如果是答案标记
                if next_line and (next_line.startswith('答案') or next_line.startswith('示例答案')):
                    # 提取答案内容
                    answer = re.sub(r'^(答案|示例答案)[：:]?\s*', '', next_line).strip()
                    if not answer:
                        # 答案可能在下一行
                        i += 1
                        if i < len(lines):
                            answer = lines[i].strip()
                    break
                elif next_line and not answer:
                    # 如果没有答案标记，下一个非空行可能就是答案
                    if '：' not in next_line or not next_line.startswith('A.'):
                        answer = next_line
                        break

                i += 1

            # 如果没有找到答案，提供默认答案
            if not answer:
                answer = "请根据实际情况回答"

            all_questions.append({
                'question': question_text,
                'answer': answer
            })

        i += 1

    if all_questions:
        interview_questions_map[job_group] = all_questions
        print(f"  - {job_group}: 解析到 {len(all_questions)} 道题")

print(f"\n共解析 {len(interview_questions_map)} 个岗位群的面试题")

# 3. 读取当前mock文件
print("\n3. 读取当前mock文件...")
with open('src/mocks/resumeInterviewMock.js', 'r', encoding='utf-8') as f:
    mock_content = f.read()

# 4. 备份
backup_time = datetime.now().strftime('%Y%m%d_%H%M%S')
backup_file = f'src/mocks/resumeInterviewMock.js.backup_full_import_{backup_time}'
print(f"4. 创建备份: {backup_file}")
with open(backup_file, 'w', encoding='utf-8') as f:
    f.write(mock_content)

# 5. 更新每个岗位群的面试题
print("\n5. 更新mock文件...")
def update_questions(match):
    industry_name = match.group(1)

    if industry_name not in interview_questions_map:
        return match.group(0)

    questions = interview_questions_map[industry_name]

    # 构建新的questions数组（统一放在一个章节下）
    sub_questions = []
    for idx, q in enumerate(questions, 1):
        # 转义特殊字符
        question_text = q['question'].replace('\\', '\\\\').replace('"', '\\"')
        answer_text = q['answer'].replace('\\', '\\\\').replace('"', '\\"').replace('\n', ' ')

        sub_questions.append(f'''{{
            "id": "q1_{idx}",
            "question": "{question_text}",
            "answer": "{answer_text}"
          }}''')

    # 构建完整的questions结构
    questions_str = f'''[
      {{
        "id": "group_q1",
        "question": "# {industry_name}岗位面试题",
        "subQuestions": [
          {','.join(sub_questions)}
        ]
      }}
    ]'''

    # 构建替换内容
    before = match.group(0).split('"questions": [')[0]
    result = before + '"questions": ' + questions_str

    print(f"  - {industry_name}: 更新为 {len(questions)} 道题")
    return result

# 执行替换
pattern = r'"name":\s*"([^"]+)"[^}]*?"questions":\s*\[.*?\]\s*(?=\s*\})'
new_content = re.sub(pattern, update_questions, mock_content, flags=re.DOTALL)

# 6. 保存文件
print("\n6. 保存更新后的文件...")
with open('src/mocks/resumeInterviewMock.js', 'w', encoding='utf-8') as f:
    f.write(new_content)

# 7. 验证
print("\n7. 验证结果...")
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！")

    # 统计最终结果
    with open('src/mocks/resumeInterviewMock.js', 'r', encoding='utf-8') as f:
        final_content = f.read()

    print("\n=== 最终统计 ===")
    for group in interview_questions_map.keys():
        pattern = rf'"name": "{re.escape(group)}".*?"questions": \[(.*?)\]\s*\}}'
        match = re.search(pattern, final_content, re.DOTALL)
        if match:
            count = len(re.findall(r'"id": "q1_\d+', match.group(1)))
            print(f"  - {group}: {count} 道题")

    print("\n✅ 所有岗位群的面试题已完整导入！")
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:
        mock_content = f.read()
    with open('src/mocks/resumeInterviewMock.js', 'w', encoding='utf-8') as f:
        f.write(mock_content)
    print("已恢复到备份版本")