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

"""
AI响应解析器模块
"""

import logging
import json
import re
from typing import List, Dict, Any
from json_repair import loads as json_repair_loads

logger = logging.getLogger(__name__)


class TopicParser:
    """
    解析和验证由AI模型生成的选题列表
    """

    @staticmethod
    def parse(raw_text: str) -> List[Dict[str, Any]]:
        """
        从原始文本解析、修复和验证JSON

        Args:
            raw_text: AI模型返回的原始字符串

        Returns:
            一个字典列表，每个字典代表一个有效的选题
        """
        logger.info("开始解析AI生成的选题...")
        
        # 1. 移除AI思考过程的 <think> 块
        if "</think>" in raw_text:
            raw_text = raw_text.split("</think>", 1)[-1]
        
        # 2. 移除Markdown代码块标记 (e.g., ```json ... ```)
        cleaned_text = re.sub(r'```json\s*|\s*```', '', raw_text.strip(), flags=re.MULTILINE)

        if not cleaned_text:
            logger.error("移除元数据后，解析内容为空")
            return []

        try:
            # 3. 使用json_repair修复可能不规范的JSON并解析
            parsed_json = json_repair_loads(cleaned_text)
            
            if not isinstance(parsed_json, list):
                logger.error(f"解析结果不是列表，而是 {type(parsed_json)}")
                return []
            
            logger.info(f"成功解析 {len(parsed_json)} 个选题对象。开始验证...")
            
            # 4. 验证每个选题是否包含所有必需的键
            valid_topics = []
            required_keys = {"index", "date", "logic", "object", "product", "style", "target_audience"}
            
            for i, item in enumerate(parsed_json):
                if isinstance(item, dict) and required_keys.issubset(item.keys()):
                    valid_topics.append(item)
                else:
                    logger.warning(f"第 {i+1} 个选题缺少必需键或格式不正确: {item}")
            
            logger.info(f"验证完成，获得 {len(valid_topics)} 个有效选题。")
            return valid_topics

        except (json.JSONDecodeError, ValueError) as e:
            logger.error(f"解析JSON失败: {e}", exc_info=True)
            return []