ALL-teach_sys/frontend_视觉设计/accurate_replace_questions.py

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

import json
import re
from datetime import datetime

def load_visual_design_data():
    """加载视觉设计岗位简历数据"""
    with open('网页未导入数据/视觉设计产业/视觉设计岗位简历.json', 'r', encoding='utf-8') as f:
        return json.load(f)

def extract_questions_with_structure(content, industry_name):
    """从面试题内容中提取问题和答案（保持subQuestions结构）"""
    questions = []

    # 提取所有问题
    pattern = r'(\d+)\.\s*问题[：:]?\s*(.*?)(?:\n\s*)?(?:参考回答[：:]?)(.*?)(?=\d+\.\s*问题|$)'
    matches = re.findall(pattern, content, re.DOTALL)

    # 创建子问题数组
    sub_questions = []
    for i, match in enumerate(matches[:10], 1):  # 限制为前10个问题
        q_num = match[0]
        question_text = match[1].strip()
        answer_text = match[2].strip()

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

    # 如果找到了问题，创建带有subQuestions的结构
    if sub_questions:
        questions.append({
            "id": "group_q1",
            "question": f"# {industry_name}面试题",
            "subQuestions": sub_questions
        })

    return questions

def main():
    print("=== 精确替换面试题数据 ===\n")

    # 创建备份
    timestamp = datetime.now().strftime('%Y%m%d_%H%M%S')
    backup_name = f'src/mocks/resumeInterviewMock.js.backup_{timestamp}_accurate'

    with open('src/mocks/resumeInterviewMock.js', 'r', encoding='utf-8') as f:
        mock_content = f.read()

    with open(backup_name, 'w', encoding='utf-8') as f:
        f.write(mock_content)
    print(f"✓ 已创建备份: {backup_name}\n")

    # 加载视觉设计数据
    visual_data = load_visual_design_data()

    # 创建岗位群到岗位名称的精确映射
    # 基于实际数据分析结果
    industry_position_map = {
        'UI设计': 'UI设计师',
        '包装设计': '包装设计师',  # 有多个，选择包装设计师
        '插画设计': '插画师',  # 有多个，选择插画师
        '灯光': '影视灯光',  # 有多个，选择影视灯光
        '动画设计': '动画师',  # 有多个，选择动画师
        '后期特效': '特效设计师',  # 有多个，选择特效设计师
        '剪辑': '剪辑师',  # 有多个，选择剪辑师
        '品牌设计': '品牌视觉内容策划',  # 有多个，选择品牌视觉内容策划
        '平面设计': '平面设计师',
        '三维设计': 'CG总监助理',  # 有多个，选择CG总监助理
        '摄影/摄像': '摄影师',  # 有多个，选择摄影师
        '室内设计': '室内设计师',
        '调色': '调色师',
        '新媒体运营': '新媒体运营专员',
        '音频处理': '录音师',
        '影视节目策划': '文案策划',
        '直播': '直播专员'  # 有多个，选择直播专员
    }

    updated_count = 0
    failed_list = []

    for industry_name, position_name in industry_position_map.items():
        print(f"处理 {industry_name}...")

        # 查找对应的面试题内容
        interview_content = None
        for item in visual_data:
            if item.get('岗位名称') == position_name and item.get('面试题内容'):
                interview_content = item.get('面试题内容')
                break

        if not interview_content:
            print(f"  ⚠️ 未找到 {position_name} 的面试题内容")
            failed_list.append(industry_name)
            continue

        # 提取问题
        questions = extract_questions_with_structure(interview_content, industry_name)

        if not questions:
            print(f"  ⚠️ 未能从 {position_name} 提取面试题")
            failed_list.append(industry_name)
            continue

        # 构建新的questions数组JSON
        questions_json = json.dumps(questions, ensure_ascii=False, indent=2)

        # 调整缩进
        lines = questions_json.split('\n')
        adjusted_lines = []
        for line in lines:
            if line.strip():
                adjusted_lines.append('    ' + line)
            else:
                adjusted_lines.append('')
        questions_json = '\n'.join(adjusted_lines)

        # 查找并替换
        # 使用更精确的模式：找到industry name后，找到其questions数组并替换
        pattern = rf'("name":\s*"{re.escape(industry_name)}"[^{{]*?"questions":\s*)\[[^\[]*?(?:\[[^\]]*?\][^\[]*?)*?\]'

        def replace_func(match):
            prefix = match.group(1)
            return prefix + questions_json.strip()

        new_mock_content = re.sub(pattern, replace_func, mock_content, count=1, flags=re.DOTALL)

        if new_mock_content != mock_content:
            mock_content = new_mock_content
            updated_count += 1
            sub_count = len(questions[0].get('subQuestions', [])) if questions else 0
            print(f"  ✓ 成功更新 (使用岗位: {position_name}, 共{sub_count}个问题)")
        else:
            print(f"  ✗ 未能更新")
            failed_list.append(industry_name)

    # 保存文件
    with open('src/mocks/resumeInterviewMock.js', 'w', encoding='utf-8') as f:
        f.write(mock_content)

    print(f"\n✅ 更新完成！")
    print(f"   成功更新: {updated_count}个岗位群")
    if failed_list:
        print(f"   失败: {len(failed_list)}个")
        for name in failed_list:
            print(f"     - {name}")

    # 验证语法
    import subprocess
    try:
        result = subprocess.run(['node', '-c', 'src/mocks/resumeInterviewMock.js'],
                              capture_output=True, text=True)
        if result.returncode == 0:
            print("\n✅ 文件语法验证通过")
        else:
            print(f"\n❌ 语法错误:\n{result.stderr}")
            print("\n恢复备份...")
            with open(backup_name, 'r', encoding='utf-8') as f:
                backup_content = f.read()
            with open('src/mocks/resumeInterviewMock.js', 'w', encoding='utf-8') as f:
                f.write(backup_content)
            print("已恢复备份")
    except Exception as e:
        print(f"⚠️ 无法验证语法: {str(e)}")

if __name__ == '__main__':
    main()