online_sys/frontend_智能制造/update_interview_questions.py

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

# 读取智能制造岗位简历数据
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:
    smart_mfg_data = json.load(f)

# 创建面试题映射字典
interview_questions_map = {}
for item in smart_mfg_data:
    job_group = item.get('简历岗位群', '')
    interview_content = item.get('面试题内容', '')
    if job_group and interview_content:
        # 存储完整的面试题内容
        interview_questions_map[job_group] = interview_content

# 打印找到的岗位群
print("找到的岗位群面试题:")
for key in interview_questions_map.keys():
    print(f"- {key}")

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

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

# 需要更新的岗位群映射
job_group_mapping = {
    'PLC': 'PLC类岗位面试题',
    '工业机器人': '工业机器人类岗位面试题', 
    '焊接工艺': '焊接工艺类岗位面试题',
    '电气设计': '电气设计类岗位面试题',
    '机器视觉': '机器视觉类岗位面试题',
    '非标自动化设计': '非标自动化类岗位面试题'
}

# 解析面试题内容为结构化数据
def parse_interview_content(content):
    """解析面试题内容为结构化数据"""
    questions = []
    lines = content.split('\n')
    
    current_section = None
    current_question = None
    current_answer = []
    
    for line in lines:
        line = line.strip()
        if not line:
            continue
            
        # 检查是否是大标题（如 # 一、xxx）
        if line.startswith('# '):
            # 保存之前的问题
            if current_question and current_section:
                answer_text = '\\n'.join(current_answer).strip()
                if not answer_text.startswith('示例答案') and not answer_text.startswith('答案'):
                    answer_text = answer_text
                else:
                    # 去掉"示例答案："或"答案："前缀
                    answer_text = re.sub(r'^(示例答案[：:]|答案[：:])\s*', '', answer_text)
                
                current_section['subQuestions'].append({
                    'question': current_question,
                    'answer': answer_text
                })
                
            # 创建新section
            if current_section:
                questions.append(current_section)
            
            section_title = line.replace('#', '').strip()
            current_section = {
                'title': section_title,
                'subQuestions': []
            }
            current_question = None
            current_answer = []
            
        # 检查是否是问题编号（如 1. xxx）
        elif re.match(r'^\d+\.\s+', line):
            # 保存之前的问题
            if current_question and current_section:
                answer_text = '\\n'.join(current_answer).strip()
                if answer_text.startswith('示例答案') or answer_text.startswith('答案'):
                    answer_text = re.sub(r'^(示例答案[：:]|答案[：:])\s*', '', answer_text)
                
                current_section['subQuestions'].append({
                    'question': current_question,
                    'answer': answer_text
                })
                
            # 提取新问题
            current_question = re.sub(r'^\d+\.\s+', '', line)
            current_answer = []
            
        # 否则是答案内容
        else:
            if current_question:
                current_answer.append(line)
    
    # 保存最后一个问题
    if current_question and current_section:
        answer_text = '\\n'.join(current_answer).strip()
        if answer_text.startswith('示例答案') or answer_text.startswith('答案'):
            answer_text = re.sub(r'^(示例答案[：:]|答案[：:])\s*', '', answer_text)
        
        current_section['subQuestions'].append({
            'question': current_question,
            'answer': answer_text
        })
    
    # 保存最后一个section
    if current_section:
        questions.append(current_section)
    
    return questions

# 更新mock文件中的面试题
def update_mock_questions(mock_content, job_group_name, interview_content):
    """更新指定岗位群的面试题"""
    
    # 解析面试题内容
    parsed_questions = parse_interview_content(interview_content)
    if not parsed_questions:
        print(f"  警告: 无法解析 {job_group_name} 的面试题内容")
        return mock_content
    
    # 查找岗位群的位置
    pattern = rf'"name":\s*"{re.escape(job_group_name)}"'
    matches = list(re.finditer(pattern, mock_content))
    
    if not matches:
        print(f"  未找到岗位群: {job_group_name}")
        return mock_content
    
    for match in matches:
        # 找到questions数组的起始位置
        start_pos = match.end()
        questions_pattern = r'"questions":\s*\['
        questions_match = re.search(questions_pattern, mock_content[start_pos:start_pos+5000])
        
        if not questions_match:
            continue
            
        questions_start = start_pos + questions_match.end()
        
        # 找到questions数组的结束位置
        bracket_count = 1
        i = questions_start
        in_string = False
        escape_next = False
        
        while i < len(mock_content) and bracket_count > 0:
            char = mock_content[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:
            questions_end = i - 1
            
            # 构建新的questions数组
            new_questions = []
            for idx, section in enumerate(parsed_questions):
                sub_questions = []
                for q_idx, q in enumerate(section['subQuestions']):
                    answer = q['answer'].replace('"', '\\"').replace('\n', '\\n')
                    sub_questions.append(f'''{{
            "id": "q{idx}_{q_idx+1}",
            "question": "{q['question']}",
            "answer": "{answer}"
          }}''')
                
                new_questions.append(f'''{{
        "id": "group_q{idx+1}",
        "question": "{section['title']}",
        "subQuestions": [
          {','.join(sub_questions)}
        ]
      }}''')
            
            # 替换原有的questions内容
            new_questions_str = ',\n      '.join(new_questions)
            mock_content = mock_content[:questions_start] + '\n      ' + new_questions_str + '\n    ' + mock_content[questions_end:]
            
            print(f"  ✓ 已更新 {job_group_name} 的面试题")
            break
    
    return mock_content

# 执行更新
print("\n开始更新面试题:")
updated_content = mock_content

for mock_group_name, json_interview_name in job_group_mapping.items():
    print(f"\n处理 {mock_group_name}:")
    
    # 查找对应的面试题内容
    found = False
    for item in smart_mfg_data:
        if item.get('面试题', '') == json_interview_name:
            interview_content = item.get('面试题内容', '')
            if interview_content:
                updated_content = update_mock_questions(updated_content, mock_group_name, interview_content)
                found = True
                break
    
    if not found:
        print(f"  未找到 {json_interview_name} 的面试题数据")

# 保存更新后的文件
with open('src/mocks/resumeInterviewMock.js', 'w', encoding='utf-8') as f:
    f.write(updated_content)

print("\n✅ 面试题更新完成！")
print("已更新的岗位群:")
for group in job_group_mapping.keys():
    print(f"  - {group}")