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

import json
import re

def extract_questions_from_content(content):
    """从面试题内容中提取问题和答案"""
    questions = []

    # 按问题编号分割内容
    pattern = r'\d+\.\s*问题[：:]?\s*(.*?)(?=\d+\.\s*问题|$)'
    matches = re.findall(pattern, content, re.DOTALL)

    for i, match in enumerate(matches, 1):
        # 提取问题和答案
        q_a_pattern = r'^(.*?)\n\s*(?:参考回答[：:]?|回答[：:]?)\s*(.*?)$'
        q_a_match = re.search(q_a_pattern, match.strip(), re.DOTALL)

        if q_a_match:
            question_text = q_a_match.group(1).strip()
            answer_text = q_a_match.group(2).strip()

            # 保留原始格式，包括换行和列表符号
            questions.append({
                "id": f"q{i}",
                "question": question_text,
                "answer": answer_text
            })

    return questions

def process_visual_design_data():
    """处理视觉设计岗位简历数据"""

    # 读取视觉设计岗位简历.json
    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:
        data = json.load(f)

    # 为每个岗位提取面试题
    position_questions = {}

    for item in data:
        position_name = item.get('岗位名称', '')
        interview_content = item.get('面试题内容', '')

        if position_name and interview_content:
            # 提取该岗位的面试题
            questions = extract_questions_from_content(interview_content)

            # 按类别分组（专业能力类、行为经历类、情景应变类）
            grouped_questions = {
                '专业能力类': [],
                '行为经历类': [],
                '情景应变类': []
            }

            # 根据内容判断类别
            current_category = '专业能力类'
            for q in questions:
                question_text = q['question'].lower()
                if '经历' in question_text or '分享' in question_text or '描述' in question_text or '项目' in question_text:
                    current_category = '行为经历类'
                elif '如果' in question_text or '假设' in question_text or '应对' in question_text or '处理' in question_text:
                    current_category = '情景应变类'

                grouped_questions[current_category].append(q)

            position_questions[position_name] = {
                'all': questions,
                'grouped': grouped_questions
            }

    return position_questions

def update_resume_interview_mock(position_questions):
    """更新resumeInterviewMock.js文件"""

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

    # 为每个岗位更新questions字段
    for position_name, questions_data in position_questions.items():
        # 查找该岗位在mock文件中的位置
        pattern = rf'name:\s*["\']({re.escape(position_name)})["\'].*?questions:\s*\[(.*?)\]'

        # 构建新的questions数组
        new_questions = json.dumps(questions_data['all'], ensure_ascii=False, indent=6)

        # 替换questions内容
        # 这里需要更精确的处理，因为JS文件格式与JSON略有不同

    # 为了保证数据完整性，生成一个单独的JSON文件供手动整合
    output = {}
    for position_name, questions_data in position_questions.items():
        output[position_name] = questions_data['all']

    with open('visual_design_interview_questions.json', 'w', encoding='utf-8') as f:
        json.dump(output, f, ensure_ascii=False, indent=2)

    print(f"已生成visual_design_interview_questions.json，包含{len(output)}个岗位的面试题数据")
    print("请手动将这些数据整合到resumeInterviewMock.js中对应岗位的questions字段")

if __name__ == '__main__':
    position_questions = process_visual_design_data()
    update_resume_interview_mock(position_questions)