"""
优化任务 - 表示一个LLM优化任务
"""

import logging
from typing import Callable, Optional

# 配置日志
def setup_logger(name, level=logging.INFO):
    """设置日志记录器"""
    logger = logging.getLogger(name)
    # 清除所有已有的handler，避免重复
    if logger.handlers:
        logger.handlers.clear()
    
    # 添加新的handler
    handler = logging.StreamHandler()
    formatter = logging.Formatter('%(asctime)s - %(name)s - %(levelname)s - %(message)s')
    handler.setFormatter(formatter)
    logger.addHandler(handler)
    logger.setLevel(level)
    # 禁止传播到父logger，避免重复日志
    logger.propagate = False
    return logger

# 创建日志记录器
logger = setup_logger("optimizer.task")

class OptimizeTask:
    """
    优化任务，表示一个需要LLM优化的文本任务
    """
    
    def __init__(self, sentence_id: str, text: str, callback: Optional[Callable[[str, str, str], None]] = None):
        """
        初始化优化任务
        
        :param sentence_id: 句子ID
        :param text: 需要优化的文本
        :param callback: 优化完成后的回调函数，接收参数(sentence_id, original_text, optimized_text)
        """
        self.sentence_id = sentence_id
        self.text = text
        self.callback = callback
        logger.debug(f"创建优化任务: {sentence_id}")
    
    def __str__(self):
        """字符串表示"""
        return f"OptimizeTask(id={self.sentence_id}, text={self.text[:20]}...)"


if __name__ == "__main__":
    # 设置日志级别为DEBUG以查看详细信息
    logger.setLevel(logging.DEBUG)
    
    # 测试回调函数
    def fake_callback(sid, original_text, optimized_text):
        logger.info(f"[回调] 优化结果：({sid}) -> {optimized_text}")
    
    # 创建任务
    task = OptimizeTask("s001", "they go home maybe tomorrow", fake_callback)
    
    # 创建模型运行器
    from optimizer.llm_api_runner import ChatGPTRunner
    runner = ChatGPTRunner()
    
    # 优化文本
    optimized_text = runner.optimize(task.text)
    
    # 调用回调
    if task.callback:
        task.callback(task.sentence_id, task.text, optimized_text)
    
    logger.info("测试完成")