Method parse_amount_with_unit

agent/amount_normalizer.py:123–158

解析包含单位的用量字符串 Args: amount_str: 如"300毫升"、"适量盐"等 Returns: Tuple[数量, 单位, 估算数值]

(self, amount_str: str)

        return normalized, estimated
    
    def parse_amount_with_unit(self, amount_str: str) -> Tuple[str, str, Optional[float]]:
        """
        解析包含单位的用量字符串
        
        Args:
            amount_str: 如"300毫升"、"适量盐"等
            
        Returns:
            Tuple[数量, 单位, 估算数值]
        """
        if not amount_str:
            return "", "", None
        
        # 常见单位模式
        unit_patterns = [
            r'(\d+(?:\.\d+)?)\s*(克|千克|斤|两|钱)',      # 重量
            r'(\d+(?:\.\d+)?)\s*(毫升|升|杯|勺|茶匙|汤匙)', # 体积  
            r'(\d+(?:\.\d+)?)\s*(个|只|条|片|根|瓣|颗)',   # 数量
            r'(\d+(?:\.\d+)?)\s*(把|撮|滴)',             # 特殊
        ]
        
        # 尝试匹配数字+单位
        for pattern in unit_patterns:
            match = re.search(pattern, amount_str)
            if match:
                amount = match.group(1)
                unit = match.group(2)
                try:
                    numeric_value = float(amount)
                    return amount, unit, numeric_value
                except ValueError:
                    pass
        
        # 处理纯文字表达
        normalized, estimated = self.normalize_amount(amount_str)
        return normalized, "", estimated
    
    def get_comparable_value(self, amount: str, unit: str = "") -> Optional[float]:
        """