fix: add Field

Author: liningping

parsers/base_models.py

@@ -3,7 +3,7 @@
 from enum import Enum
 from typing import Any
 
-from pydantic import BaseModel
+from pydantic import BaseModel, Field
 
 logger = logging.getLogger(__name__)
 
@@ -19,9 +19,9 @@ class TableDataItem(BaseModel):
     """表格数据类"""
     rows: int  # 行数
     columns: int  # 列数
-    row_headers: list[Any] = []  # 行头
-    column_headers: list[Any] = []  # 列头
-    data: list[list[str]] = []  # 数据
+    row_headers: list[Any] = Field(default_factory=list)  # 行头
+    column_headers: list[Any] = Field(default_factory=list)  # 列头
+    data: list[list[str]] = Field(default_factory=list)  # 数据
 
 class ChunkData(BaseModel):
     """块数据类"""
@@ -33,10 +33,10 @@ class ChunkData(BaseModel):
 class DocumentData(BaseModel):
     """解析结果类"""
     title: str = ""
-    texts: list[ChunkData] = []
-    tables: list[ChunkData] = []
-    images: list[ChunkData] = []
-    formulas: list[ChunkData] = []
+    texts: list[ChunkData] = Field(default_factory=list)
+    tables: list[ChunkData] = Field(default_factory=list)
+    images: list[ChunkData] = Field(default_factory=list)
+    formulas: list[ChunkData] = Field(default_factory=list)
     processing_time: float = 0
     success: bool
     error_message: str | None = None
@@ -45,7 +45,7 @@ class DocumentParser(ABC):
     """文档解析器基类"""
 
     def __init__(self) -> None:
-        self.supported_formats: list[str] = []
+        self.supported_formats: list[str] = Field(default_factory=list)
 
     @abstractmethod
     async def parse(self, file_path: str) -> DocumentData:
@@ -55,4 +55,4 @@ async def parse(self, file_path: str) -> DocumentData:
     @abstractmethod
     def can_parse(self, file_path: str) -> bool:
         """检查是否可以解析该文件"""
-        pass
+        return any(file_path.lower().endswith(fmt) for fmt in self.supported_formats)