del doc support (#2494)

Co-authored-by: jyong <jyong@dify.ai>

api/core/data_loader/file_extractor.py

@@ -69,7 +69,7 @@ class FileExtractor:
                     else MarkdownLoader(file_path, autodetect_encoding=True)
             elif file_extension in ['.htm', '.html']:
                 loader = HTMLLoader(file_path)
-            elif file_extension in ['.docx', '.doc']:
+            elif file_extension in ['.docx']:
                 loader = Docx2txtLoader(file_path)
             elif file_extension == '.csv':
                 loader = CSVLoader(file_path, autodetect_encoding=True)
@@ -96,7 +96,7 @@ class FileExtractor:
                 loader = MarkdownLoader(file_path, autodetect_encoding=True)
             elif file_extension in ['.htm', '.html']:
                 loader = HTMLLoader(file_path)
-            elif file_extension in ['.docx', '.doc']:
+            elif file_extension in ['.docx']:
                 loader = Docx2txtLoader(file_path)
             elif file_extension == '.csv':
                 loader = CSVLoader(file_path, autodetect_encoding=True)

api/services/file_service.py

@@ -20,9 +20,9 @@ from services.errors.file import FileTooLargeError, UnsupportedFileTypeError
 IMAGE_EXTENSIONS = ['jpg', 'jpeg', 'png', 'webp', 'gif', 'svg']
 IMAGE_EXTENSIONS.extend([ext.upper() for ext in IMAGE_EXTENSIONS])
 
-ALLOWED_EXTENSIONS = ['txt', 'markdown', 'md', 'pdf', 'html', 'htm', 'xlsx', 'docx', 'doc', 'csv'] + IMAGE_EXTENSIONS
+ALLOWED_EXTENSIONS = ['txt', 'markdown', 'md', 'pdf', 'html', 'htm', 'xlsx', 'docx', 'csv'] + IMAGE_EXTENSIONS
 UNSTRUSTURED_ALLOWED_EXTENSIONS = ['txt', 'markdown', 'md', 'pdf', 'html', 'htm', 'xlsx',
-                                      'docx', 'doc', 'csv', 'eml', 'msg', 'pptx', 'ppt', 'xml'] + IMAGE_EXTENSIONS
+                                   'docx', 'csv', 'eml', 'msg', 'pptx', 'ppt', 'xml'] + IMAGE_EXTENSIONS
 PREVIEW_WORDS_LIMIT = 3000