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

import json
import re
from datetime import datetime

def create_backup(file_path):
    """创建备份文件"""
    timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
    backup_path = f"{file_path}.backup_complete_{timestamp}"
    with open(file_path, 'r', encoding='utf-8') as f:
        content = f.read()
    with open(backup_path, 'w', encoding='utf-8') as f:
        f.write(content)
    print(f"已创建备份: {backup_path}")
    return backup_path

def load_chemical_data():
    """加载化工岗位简历数据"""
    with open('网页未导入数据/化工产业/化工岗位简历.json', 'r', encoding='utf-8') as f:
        return json.load(f)

def parse_interview_questions(content):
    """解析面试题内容，提取问题和答案"""
    questions = []
    
    if not content:
        return questions
    
    # 提取模拟问答题
    if "模拟问答题" in content:
        # 分割问题部分
        sim_section = content.split("# 二、")[0] if "# 二、" in content else content
        
        # 查找每个问题
        pattern = r'(\d+)\.\s*([^？?]+[？?])'
        matches = re.findall(pattern, sim_section)
        
        for i, (num, question) in enumerate(matches[:3]):  # 取前3个
            # 查找对应的示例答案
            answer_pattern = rf'{num}\.[^示]*示例答案[：:]\s*([^。；！？\n]+[。；！？])'
            answer_match = re.search(answer_pattern, sim_section)
            
            if answer_match:
                answer = answer_match.group(1).strip()[:150]  # 限制长度
            else:
                answer = "请参考专业培训资料获取详细解答。"
            
            questions.append({
                "id": f"q{i+1}",
                "question": question.strip(),
                "answer": answer
            })
    
    # 提取选择题
    if "选择题" in content and len(questions) < 5:
        choice_section = content.split("# 二、选择题")[1] if "# 二、选择题" in content else ""
        if choice_section:
            # 查找选择题
            choice_pattern = r'(\d+)\.\s*([^？?（]+[^？?\n]*[？?])'
            choice_matches = re.findall(choice_pattern, choice_section)
            
            for i, (num, question) in enumerate(choice_matches[:2]):  # 取前2个
                # 查找答案
                answer_pattern = rf'正确[答案选项][：:]\s*([A-D,、\s]+)'
                answer_match = re.search(answer_pattern, choice_section[choice_section.find(question):])
                
                if answer_match:
                    answer = f"正确答案：{answer_match.group(1).strip()}"
                else:
                    answer = "请查看答案解析"
                
                questions.append({
                    "id": f"choice{i+1}",
                    "question": question.strip()[:100],
                    "answer": answer
                })
    
    # 如果没有找到题目，创建默认题目
    if not questions:
        questions = [
            {
                "id": "default1",
                "question": "请介绍一下你对该岗位的理解和认识",
                "answer": "需要掌握专业知识，注重安全生产，不断学习提升。"
            },
            {
                "id": "default2", 
                "question": "你为什么选择化工行业",
                "answer": "化工行业是国民经济的重要支柱，发展前景广阔。"
            }
        ]
    
    return questions

def update_interview_questions():
    """更新面试题数据"""
    mock_file = 'src/mocks/resumeInterviewMock.js'
    
    # 创建备份
    backup_path = create_backup(mock_file)
    
    # 加载化工数据
    chemical_data = load_chemical_data()
    
    # 按岗位群整理面试题
    questions_by_group = {}
    for item in chemical_data:
        group = item.get('简历岗位群', '')
        if group and group not in questions_by_group:
            content = item.get('面试题内容', '')
            questions = parse_interview_questions(content)
            if questions:
                questions_by_group[group] = questions
                print(f"✓ 为 {group} 解析了 {len(questions)} 个面试题")
    
    # 读取mock文件
    with open(mock_file, 'r', encoding='utf-8') as f:
        lines = f.readlines()
    
    # 逐行处理，更新subQuestions
    new_lines = []
    i = 0
    while i < len(lines):
        line = lines[i]
        new_lines.append(line)
        
        # 查找 "subQuestions": []
        if '"subQuestions": []' in line or '"subQuestions": [' in line:
            # 查找对应的岗位群
            group_name = None
            for j in range(max(0, i-15), i):
                if '"name":' in lines[j]:
                    match = re.search(r'"name":\s*"([^"]+)"', lines[j])
                    if match:
                        group_name = match.group(1)
                        break
            
            if group_name and group_name in questions_by_group:
                # 如果是空数组，替换为有内容的数组
                if '[]' in line:
                    questions = questions_by_group[group_name]
                    
                    # 生成格式化的JSON
                    questions_json = json.dumps(questions, ensure_ascii=False, indent=10)
                    lines_json = questions_json.split('\n')
                    
                    # 替换当前行
                    new_lines[-1] = line.replace('[]', '[\n')
                    
                    # 添加问题数据
                    for json_line in lines_json[1:-1]:  # 跳过首尾的[]
                        new_lines.append('        ' + json_line + '\n')
                    
                    new_lines.append('        ]\n')
                    print(f"  已更新 {group_name} 的面试题")
                else:
                    # 如果已经有内容，跳过到结束
                    bracket_count = 1
                    i += 1
                    while i < len(lines) and bracket_count > 0:
                        if '[' in lines[i]:
                            bracket_count += lines[i].count('[')
                        if ']' in lines[i]:
                            bracket_count -= lines[i].count(']')
                        new_lines.append(lines[i])
                        if bracket_count == 0:
                            break
                        i += 1
        
        i += 1
    
    # 写回文件
    with open(mock_file, 'w', encoding='utf-8') as f:
        f.writelines(new_lines)
    
    print("\n检查语法...")
    # 验证语法
    import subprocess
    result = subprocess.run(['node', '-c', mock_file], capture_output=True, text=True)
    if result.returncode == 0:
        print("✓ 语法检查通过")
        return True
    else:
        print("✗ 语法检查失败:")
        print(result.stderr[:300])
        # 恢复备份
        with open(backup_path, 'r', encoding='utf-8') as f:
            backup_content = f.read()
        with open(mock_file, 'w', encoding='utf-8') as f:
            f.write(backup_content)
        print("已恢复备份文件")
        return False

def main():
    """主函数"""
    print("开始添加完整的面试题数据...\n")
    
    if update_interview_questions():
        print("\n✅ 面试题数据添加成功！")
    else:
        print("\n❌ 面试题数据添加失败")

if __name__ == "__main__":
    main()