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

"""
选题生成模块
"""

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

from core.ai import AIAgent
from core.config import GenerateTopicConfig
from utils.prompts import TopicPromptBuilder
from utils.file_io import OutputManager

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 <think> 块
        if "</think>" in raw_text:
            raw_text = raw_text.split("</think>", 1)[-1]
        
        # 2. 移除Markdown代码块标记
        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修复并解析JSON
            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. 验证和清理每个选题
            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()):
                    # 可选地清理或转换字段值
                    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 []


class TopicGenerator:
    """负责生成、解析和保存选题"""

    def __init__(self, ai_agent: AIAgent, config: GenerateTopicConfig, output_manager: OutputManager):
        self.ai_agent = ai_agent
        self.config = config
        self.output_manager = output_manager
        self.prompt_builder = TopicPromptBuilder(config)

    def generate(self) -> Optional[List[Dict[str, Any]]]:
        """
        执行完整的选题生成流程：构建提示 -> 调用AI -> 解析结果 -> 保存产物
        """
        logger.info("开始执行选题生成流程...")

        # 1. 构建提示
        prompts = self.prompt_builder.build_prompts()
        self.output_manager.save_text(prompts["system"], "topic_system_prompt.txt")
        self.output_manager.save_text(prompts["user"], "topic_user_prompt.txt")
        
        # 2. 调用AI生成
        try:
            raw_result, _, _, _ = self.ai_agent.work(
                system_prompt=prompts["system"],
                user_prompt=prompts["user"]
            )
            self.output_manager.save_text(raw_result, "topics_raw_response.txt")
        except Exception as e:
            logger.critical(f"AI调用失败，无法生成选题: {e}", exc_info=True)
            return None

        # 3. 解析结果
        topics = TopicParser.parse(raw_result)
        if not topics:
            logger.error("未能从AI响应中解析出任何有效选题")
            return None
            
        # 4. 保存解析后的结果
        self.output_manager.save_json(topics, "topics_generated.json")
        
        # 5. （可选）保存为易于阅读的 .txt 格式
        topics_text = self._format_topics_to_text(topics)
        self.output_manager.save_text(topics_text, "topics_generated.txt")
        
        logger.info(f"选题生成流程成功完成，共生成 {len(topics)} 个选题。")
        return topics

    def _format_topics_to_text(self, topics: List[Dict[str, Any]]) -> str:
        """将选题列表格式化为人类可读的文本"""
        text_parts = [f"# 选题列表 (Run ID: {self.output_manager.run_id})\n"]
        for topic in topics:
            text_parts.append(f"## 选题 {topic.get('index', 'N/A')}")
            text_parts.append(f"- 日期: {topic.get('date', 'N/A')}")
            text_parts.append(f"- 对象: {topic.get('object', 'N/A')}")
            text_parts.append(f"- 产品: {topic.get('product', 'N/A')}")
            text_parts.append(f"- 风格: {topic.get('style', 'N/A')}")
            text_parts.append(f"- 目标受众: {topic.get('target_audience', 'N/A')}")
            text_parts.append(f"- 逻辑: {topic.get('logic', 'N/A')}")
        return "\n".join(text_parts)