ALL-teach_sys/frontend_大健康/update_interview_questions.py

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
更新简历与面试题页面的面试题数据
将大健康岗位简历.json中的面试题数据替换到resumeInterviewMock.js中
"""

import json
import re
import sys
from datetime import datetime

def load_health_resume_data():
    """加载大健康岗位简历数据"""
    try:
        with open('网页未导入数据/大健康产业/大健康岗位简历.json', 'r', encoding='utf-8') as f:
            return json.load(f)
    except Exception as e:
        print(f"Error loading health resume data: {e}")
        return None

def load_current_mock_data():
    """加载当前的resumeInterviewMock.js数据"""
    try:
        with open('src/mocks/resumeInterviewMock.js', 'r', encoding='utf-8') as f:
            content = f.read()

        # 提取JavaScript数据部分
        start_marker = "const industries = ["
        end_marker = "];"

        start_index = content.find(start_marker)
        if start_index == -1:
            print("Cannot find industries declaration in resumeInterviewMock.js")
            return None, None

        # 找到对应的结束括号
        bracket_count = 0
        in_brackets = False
        end_index = start_index + len("const industries = ")

        for i, char in enumerate(content[end_index:], end_index):
            if char == '[':
                bracket_count += 1
                in_brackets = True
            elif char == ']':
                bracket_count -= 1
                if bracket_count == 0 and in_brackets:
                    end_index = i + 1
                    break

        if bracket_count != 0:
            print("Cannot find matching bracket for industries array")
            return None, None

        js_data_part = content[start_index + len("const industries = "):end_index]

        # 查找文件剩余部分的开始
        remaining_start = content.find("\n", end_index)
        if remaining_start == -1:
            remaining_start = end_index
        other_content = content[remaining_start:]

        return js_data_part, other_content
    except Exception as e:
        print(f"Error loading current mock data: {e}")
        return None, None

def parse_interview_content(content):
    """解析面试题内容，转换为结构化数据"""
    if not content:
        return []

    questions = []

    # 按大标题分割（# 一、二、三等）
    sections = re.split(r'\n# ([一二三四五六七八九十]+、[^#\n]+)', content)

    if len(sections) < 2:
        return questions

    for i in range(1, len(sections), 2):
        if i + 1 < len(sections):
            section_title = sections[i].strip()
            section_content = sections[i + 1].strip()

            # 解析每个section中的问题
            sub_questions = []

            # 按问题编号分割 (1. 2. 3. 等)
            question_parts = re.split(r'\n\s*(\d+\.)\s+', section_content)

            for j in range(1, len(question_parts), 2):
                if j + 1 < len(question_parts):
                    question_num = question_parts[j].strip()
                    question_block = question_parts[j + 1].strip()

                    # 提取问题和答案
                    lines = question_block.split('\n')
                    question_text = ""
                    answer_text = ""
                    in_answer = False

                    for line in lines:
                        line = line.strip()
                        if line.startswith('示例答案：'):
                            in_answer = True
                            continue

                        if not in_answer and line and not line.startswith('示例答案：'):
                            if question_text:
                                question_text += " "
                            question_text += line
                        elif in_answer and line:
                            if answer_text:
                                answer_text += "\\n"
                            answer_text += line

                    if question_text:
                        sub_questions.append({
                            "id": f"q{len(questions) + 1}_{len(sub_questions) + 1}",
                            "question": question_text,
                            "answer": answer_text
                        })

            if sub_questions:
                questions.append({
                    "id": f"group_q{len(questions) + 1}",
                    "question": f"# {section_title}",
                    "subQuestions": sub_questions
                })

    return questions

def update_interview_questions(health_data):
    """更新面试题数据"""
    js_data_part, other_content = load_current_mock_data()
    if not js_data_part or not other_content:
        return False

    try:
        # 解析现有的JavaScript数据
        # 先转换成可解析的JSON格式
        json_like = js_data_part.strip().rstrip(';')

        # 替换JavaScript特有的语法
        json_like = re.sub(r'(\w+):', r'"\1":', json_like)  # 给属性名加引号
        json_like = re.sub(r'"\s*(\w+)"\s*:', r'"\1":', json_like)  # 清理多余空格

        # 解析JSON
        industries_data = json.loads(json_like)

        # 创建岗位到面试题的映射
        position_to_questions = {}
        for item in health_data:
            position_name = item.get('岗位名称', '')
            interview_content = item.get('面试题内容', '')

            if position_name and interview_content:
                questions = parse_interview_content(interview_content)
                position_to_questions[position_name] = questions

        # 更新现有数据的面试题
        for industry in industries_data:
            for position in industry.get('positions', []):
                position_title = position.get('title', '')

                if position_title in position_to_questions:
                    position['questions'] = position_to_questions[position_title]
                    print(f"Updated interview questions for position: {position_title}")

        # 将更新后的数据转换回JavaScript格式
        js_content = json.dumps(industries_data, ensure_ascii=False, indent=2)

        # 恢复JavaScript语法
        js_content = re.sub(r'"(\w+)":', r'\1:', js_content)

        # 写回文件
        full_content = f"""// 简历与面试题Mock数据

// 岗位群列表
const industries = {js_content};

{other_content}"""

        with open('src/mocks/resumeInterviewMock.js', 'w', encoding='utf-8') as f:
            f.write(full_content)

        print("Interview questions updated successfully!")
        return True

    except Exception as e:
        print(f"Error updating interview questions: {e}")
        return False

def main():
    """主函数"""
    print("Starting to update interview questions...")

    # 加载数据
    health_data = load_health_resume_data()
    if not health_data:
        print("Failed to load health resume data")
        return False

    # 更新面试题数据
    success = update_interview_questions(health_data)

    if success:
        print("Interview questions update completed!")
    else:
        print("Interview questions update failed!")

    return success

if __name__ == "__main__":
    main()