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

import json
import re
import datetime
import shutil

def parse_interview_questions(content):
    """解析面试题内容"""
    questions = []
    lines = content.split('\n')
    
    current_question = None
    current_answer = []
    question_id = 1
    in_answer = False
    
    for line in lines:
        line = line.strip()
        
        # 检查是否是问题行
        question_match = re.match(r'^(\d+)\.[\s　]+(.+)$', line)
        if question_match:
            # 保存上一个问题
            if current_question and current_answer:
                answer_text = '\n'.join(current_answer).strip()
                if answer_text:
                    current_question['answer'] = answer_text
                    questions.append(current_question)
                current_answer = []
            
            # 创建新问题
            question_text = question_match.group(2).rstrip('？?')
            current_question = {
                'id': f'q{question_id}',
                'question': question_text,
                'answer': ''
            }
            question_id += 1
            in_answer = False
        
        # 检查是否是答案开始
        elif '示例答案' in line or '答案：' in line or '答案:' in line:
            in_answer = True
            answer_in_line = re.sub(r'^.*?(示例答案|答案)[：:]?\s*', '', line).strip()
            if answer_in_line:
                current_answer.append(answer_in_line)
        
        # 收集答案内容
        elif in_answer and current_question and line:
            if not line.startswith('#'):
                current_answer.append(line)
        
        # 检查是否到达下一个部分
        elif line.startswith('#') and current_question and current_answer:
            answer_text = '\n'.join(current_answer).strip()
            if answer_text:
                current_question['answer'] = answer_text
                questions.append(current_question)
            current_question = None
            current_answer = []
            in_answer = False
    
    # 保存最后一个问题
    if current_question and current_answer:
        answer_text = '\n'.join(current_answer).strip()
        if answer_text:
            current_question['answer'] = answer_text
            questions.append(current_question)
    
    return questions

def generate_clean_mock():
    """生成干净的mock文件"""
    
    # 读取能源岗位简历数据
    with open("网页未导入数据/能源产业/能源岗位简历.json", 'r', encoding='utf-8') as f:
        energy_jobs = json.load(f)
    
    # 按岗位群分组
    groups = {}
    for job in energy_jobs:
        group_name = job.get("简历岗位群", "")
        if group_name:
            if group_name not in groups:
                groups[group_name] = {
                    "positions": [],
                    "questions": None
                }
            
            # 添加岗位信息
            position = {
                "id": f"energy_{len(groups)}_{len(groups[group_name]['positions'])+1}",
                "title": job.get("岗位名称", ""),
                "level": job.get("岗位级别", "基础岗"),
                "avatar": job.get("岗位头像", "https://ddcz-1315997005.cos.ap-nanjing.myqcloud.com/static/img/butler_position_avatar/recuPFYfYv4rBd.jpeg"),
                "department": group_name,
                "type": "全职",
                "experience": "1-3年",
                "education": "大专",
                "salary": "8-15K",
                "location": "北京",
                "updateTime": "2024-01-20",
                "description": f"负责{job.get('岗位名称', '')}相关工作",
                "requirements": []
            }
            groups[group_name]["positions"].append(position)
            
            # 提取面试题
            if not groups[group_name]["questions"] and "面试题内容" in job:
                questions = parse_interview_questions(job["面试题内容"])
                # 自动化控制只保留10个问题
                if group_name == "自动化控制" and len(questions) > 10:
                    questions = questions[:10]
                groups[group_name]["questions"] = questions
    
    # 生成industries数组
    industries = []
    group_id = 1
    for group_name, data in groups.items():
        industry = {
            "id": f"energy_{group_id}",
            "name": group_name,
            "positions": data["positions"],
            "questions": [
                {
                    "id": f"group_q{group_id}",
                    "question": f"# {group_name}面试题",
                    "subQuestions": data["questions"] if data["questions"] else []
                }
            ]
        }
        industries.append(industry)
        group_id += 1
    
    # 生成完整的mock文件内容
    content = '''// 简历与面试题Mock数据

// 岗位群列表
const industries = %s;

export const resumeInterviewService = {
  getIndustries: async () => {
    // 模拟API调用延迟
    await new Promise((resolve) => setTimeout(resolve, 500));
    return industries;
  },
};
''' % json.dumps(industries, ensure_ascii=False, indent=2)
    
    # 备份当前文件
    mock_file = "src/mocks/resumeInterviewMock.js"
    backup_path = f"{mock_file}.backup_{datetime.datetime.now().strftime('%Y%m%d_%H%M%S')}"
    shutil.copy(mock_file, backup_path)
    print(f"✅ 已备份文件到：{backup_path}")
    
    # 写入新文件
    with open(mock_file, 'w', encoding='utf-8') as f:
        f.write(content)
    
    print("✅ 成功生成干净的mock文件")
    
    # 统计结果
    print("\n📊 各岗位群统计：")
    total_questions = 0
    for industry in industries:
        q_count = len(industry["questions"][0]["subQuestions"]) if industry["questions"] else 0
        total_questions += q_count
        print(f"   - {industry['name']}: {len(industry['positions'])}个岗位, {q_count}个面试题")
    
    print(f"\n📈 总计：{len(industries)}个岗位群，{total_questions}个面试题")

if __name__ == "__main__":
    generate_clean_mock()