feat(data-management): 扩展文档解析功能支持DOC和DOCX格式

- 添加对DOC和DOCX文件类型的常量定义和支持
- 将文件类型验证逻辑从仅PDF扩展为PDF/DOC/DOCX
- 集成Docx2txtLoader用于处理Word文档解析
- 更新错误消息为中文描述以提升用户体验
- 重构文件解析方法以支持多种文档格式
- 添加解析器元数据记录以追踪使用的解析工具
- 更新文件路径验证和构建逻辑以适配新的文件类型

runtime/datamate-python/app/module/dataset/schema/pdf_extract.py

@@ -2,20 +2,20 @@ from pydantic import BaseModel, Field
 
 
 class PdfTextExtractRequest(BaseModel):
-    dataset_id: str = Field(..., alias="datasetId", description="Dataset ID")
-    file_id: str = Field(..., alias="fileId", description="PDF file ID")
+    dataset_id: str = Field(..., alias="datasetId", description="数据集ID")
+    file_id: str = Field(..., alias="fileId", description="源文件ID")
 
     class Config:
         populate_by_name = True
 
 
 class PdfTextExtractResponse(BaseModel):
-    dataset_id: str = Field(..., alias="datasetId", description="Dataset ID")
-    source_file_id: str = Field(..., alias="sourceFileId", description="Source PDF file ID")
-    text_file_id: str = Field(..., alias="textFileId", description="Generated text file ID")
-    text_file_name: str = Field(..., alias="textFileName", description="Generated text file name")
-    text_file_path: str = Field(..., alias="textFilePath", description="Generated text file path")
-    text_file_size: int = Field(..., alias="textFileSize", description="Generated text file size")
+    dataset_id: str = Field(..., alias="datasetId", description="数据集ID")
+    source_file_id: str = Field(..., alias="sourceFileId", description="源文件ID")
+    text_file_id: str = Field(..., alias="textFileId", description="解析后的文本文件ID")
+    text_file_name: str = Field(..., alias="textFileName", description="解析后的文本文件名")
+    text_file_path: str = Field(..., alias="textFilePath", description="解析后的文本文件路径")
+    text_file_size: int = Field(..., alias="textFileSize", description="解析后的文本文件大小")
 
     class Config:
         populate_by_name = True