{
  "file_path": "tweet/topic_parser.py",
  "file_size": 1544,
  "line_count": 58,
  "functions": [
    {
      "name": "parse",
      "line_start": 22,
      "line_end": 59,
      "args": [
        {
          "name": "raw_text",
          "type_hint": "str"
        }
      ],
      "return_type": "List[Dict[str, Any]]",
      "docstring": "从原始文本解析、修复和验证JSON\n\nArgs:\n    raw_text: AI模型返回的原始字符串\n\nReturns:\n    一个字典列表，每个字典代表一个有效的选题",
      "is_async": false,
      "decorators": [
        "staticmethod"
      ],
      "code": "    def parse(raw_text: str) -> List[Dict[str, Any]]:\n        \"\"\"\n        从原始文本解析、修复和验证JSON\n\n        Args:\n            raw_text: AI模型返回的原始字符串\n\n        Returns:\n            一个字典列表，每个字典代表一个有效的选题\n        \"\"\"\n        logger.info(\"开始解析AI生成的选题...\")\n        \n        # 使用通用JSON解析函数解析原始文本\n        parsed_json = process_llm_json_text(raw_text)\n        \n        if not parsed_json:\n            logger.error(\"解析AI响应失败，无法获取JSON数据\")\n            return []\n            \n        if not isinstance(parsed_json, list):\n            logger.error(f\"解析结果不是列表，而是 {type(parsed_json)}\")\n            return []\n        \n        logger.info(f\"成功解析 {len(parsed_json)} 个选题对象。开始验证...\")\n        \n        # 验证每个选题是否包含所有必需的键\n        valid_topics = []\n        required_keys = {\"index\", \"date\", \"logic\", \"object\", \"product\", \"style\", \"targetAudience\"}\n        optional_keys = {\"productLogic\", \"styleLogic\", \"targetAudienceLogic\"}\n        \n        for i, item in enumerate(parsed_json):\n            if isinstance(item, dict) and required_keys.issubset(item.keys()):\n                valid_topics.append(item)\n            else:\n                logger.warning(f\"第 {i+1} 个选题缺少必需键或格式不正确: {item}\")\n        \n        logger.info(f\"验证完成，获得 {len(valid_topics)} 个有效选题。\")\n        return valid_topics ",
      "code_hash": "b764577bd884f9a327e661e58d893403"
    }
  ],
  "classes": [
    {
      "name": "TopicParser",
      "line_start": 16,
      "line_end": 59,
      "bases": [],
      "methods": [
        {
          "name": "parse",
          "line_start": 22,
          "line_end": 59,
          "args": [
            {
              "name": "raw_text",
              "type_hint": "str"
            }
          ],
          "return_type": "List[Dict[str, Any]]",
          "docstring": "从原始文本解析、修复和验证JSON\n\nArgs:\n    raw_text: AI模型返回的原始字符串\n\nReturns:\n    一个字典列表，每个字典代表一个有效的选题",
          "is_async": false,
          "decorators": [
            "staticmethod"
          ],
          "code": "    def parse(raw_text: str) -> List[Dict[str, Any]]:\n        \"\"\"\n        从原始文本解析、修复和验证JSON\n\n        Args:\n            raw_text: AI模型返回的原始字符串\n\n        Returns:\n            一个字典列表，每个字典代表一个有效的选题\n        \"\"\"\n        logger.info(\"开始解析AI生成的选题...\")\n        \n        # 使用通用JSON解析函数解析原始文本\n        parsed_json = process_llm_json_text(raw_text)\n        \n        if not parsed_json:\n            logger.error(\"解析AI响应失败，无法获取JSON数据\")\n            return []\n            \n        if not isinstance(parsed_json, list):\n            logger.error(f\"解析结果不是列表，而是 {type(parsed_json)}\")\n            return []\n        \n        logger.info(f\"成功解析 {len(parsed_json)} 个选题对象。开始验证...\")\n        \n        # 验证每个选题是否包含所有必需的键\n        valid_topics = []\n        required_keys = {\"index\", \"date\", \"logic\", \"object\", \"product\", \"style\", \"targetAudience\"}\n        optional_keys = {\"productLogic\", \"styleLogic\", \"targetAudienceLogic\"}\n        \n        for i, item in enumerate(parsed_json):\n            if isinstance(item, dict) and required_keys.issubset(item.keys()):\n                valid_topics.append(item)\n            else:\n                logger.warning(f\"第 {i+1} 个选题缺少必需键或格式不正确: {item}\")\n        \n        logger.info(f\"验证完成，获得 {len(valid_topics)} 个有效选题。\")\n        return valid_topics ",
          "code_hash": "b764577bd884f9a327e661e58d893403"
        }
      ],
      "docstring": "解析和验证由AI模型生成的选题列表",
      "decorators": [],
      "code": "class TopicParser:\n    \"\"\"\n    解析和验证由AI模型生成的选题列表\n    \"\"\"\n\n    @staticmethod\n    def parse(raw_text: str) -> List[Dict[str, Any]]:\n        \"\"\"\n        从原始文本解析、修复和验证JSON\n\n        Args:\n            raw_text: AI模型返回的原始字符串\n\n        Returns:\n            一个字典列表，每个字典代表一个有效的选题\n        \"\"\"\n        logger.info(\"开始解析AI生成的选题...\")\n        \n        # 使用通用JSON解析函数解析原始文本\n        parsed_json = process_llm_json_text(raw_text)\n        \n        if not parsed_json:\n            logger.error(\"解析AI响应失败，无法获取JSON数据\")\n            return []\n            \n        if not isinstance(parsed_json, list):\n            logger.error(f\"解析结果不是列表，而是 {type(parsed_json)}\")\n            return []\n        \n        logger.info(f\"成功解析 {len(parsed_json)} 个选题对象。开始验证...\")\n        \n        # 验证每个选题是否包含所有必需的键\n        valid_topics = []\n        required_keys = {\"index\", \"date\", \"logic\", \"object\", \"product\", \"style\", \"targetAudience\"}\n        optional_keys = {\"productLogic\", \"styleLogic\", \"targetAudienceLogic\"}\n        \n        for i, item in enumerate(parsed_json):\n            if isinstance(item, dict) and required_keys.issubset(item.keys()):\n                valid_topics.append(item)\n            else:\n                logger.warning(f\"第 {i+1} 个选题缺少必需键或格式不正确: {item}\")\n        \n        logger.info(f\"验证完成，获得 {len(valid_topics)} 个有效选题。\")\n        return valid_topics ",
      "code_hash": "8ea78a1b3f8cfa61023ecbaf1638bfd5"
    }
  ],
  "imports": [
    {
      "type": "import",
      "modules": [
        "logging"
      ],
      "aliases": []
    },
    {
      "type": "import",
      "modules": [
        "json"
      ],
      "aliases": []
    },
    {
      "type": "from_import",
      "module": "typing",
      "names": [
        "List",
        "Dict",
        "Any"
      ],
      "aliases": [],
      "level": 0
    },
    {
      "type": "from_import",
      "module": "utils.file_io",
      "names": [
        "process_llm_json_text"
      ],
      "aliases": [],
      "level": 0
    }
  ],
  "constants": [],
  "docstring": "AI响应解析器模块",
  "content_hash": "ef155d2ff5e2ef181d534b9d314c4cee"
}