59 lines
1.8 KiB
Python
59 lines
1.8 KiB
Python
#!/usr/bin/env python3
|
||
# -*- coding: utf-8 -*-
|
||
|
||
"""
|
||
AI响应解析器模块
|
||
"""
|
||
|
||
import logging
|
||
import json
|
||
from typing import List, Dict, Any
|
||
from utils.file_io import process_llm_json_text
|
||
|
||
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...")
|
||
|
||
# 使用通用JSON解析函数解析原始文本
|
||
parsed_json = process_llm_json_text(raw_text)
|
||
|
||
if not parsed_json:
|
||
logger.error("解析AI响应失败，无法获取JSON数据")
|
||
return []
|
||
|
||
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...")
|
||
|
||
# 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", "targetAudience"}
|
||
optional_keys = {"productLogic", "styleLogic", "targetAudienceLogic"}
|
||
|
||
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 |