chore: add missing @override decorator to api/core/rag/extractor (#37013)

Co-authored-by: mac <mac@1234.local>

api/core/rag/extractor/unstructured/unstructured_doc_extractor.py

@@ -1,5 +1,6 @@
 import logging
 import os
+from typing import override
 
 from configs import dify_config
 from core.rag.extractor.extractor_base import BaseExtractor
@@ -17,6 +18,7 @@ class UnstructuredWordExtractor(BaseExtractor):
         self._api_url = api_url
         self._api_key = api_key
 
+    @override
     def extract(self) -> list[Document]:
         from unstructured.__version__ import __version__ as __unstructured_version__
         from unstructured.file_utils.filetype import (

api/core/rag/extractor/unstructured/unstructured_eml_extractor.py

@@ -1,6 +1,7 @@
 import base64
 import contextlib
 import logging
+from typing import override
 
 from bs4 import BeautifulSoup
 
@@ -23,6 +24,7 @@ class UnstructuredEmailExtractor(BaseExtractor):
         self._api_url = api_url
         self._api_key = api_key
 
+    @override
     def extract(self) -> list[Document]:
         if self._api_url:
             from unstructured.partition.api import partition_via_api

api/core/rag/extractor/unstructured/unstructured_epub_extractor.py

@@ -1,4 +1,5 @@
 import logging
+from typing import override
 
 import pypandoc  # type: ignore
 
@@ -28,6 +29,7 @@ class UnstructuredEpubExtractor(BaseExtractor):
         self._api_url = api_url
         self._api_key = api_key
 
+    @override
     def extract(self) -> list[Document]:
         if self._api_url:
             from unstructured.partition.api import partition_via_api

api/core/rag/extractor/unstructured/unstructured_markdown_extractor.py

@@ -1,4 +1,5 @@
 import logging
+from typing import override
 
 from configs import dify_config
 from core.rag.extractor.extractor_base import BaseExtractor
@@ -22,6 +23,7 @@ class UnstructuredMarkdownExtractor(BaseExtractor):
         self._api_url = api_url
         self._api_key = api_key
 
+    @override
     def extract(self) -> list[Document]:
         if self._api_url:
             from unstructured.partition.api import partition_via_api

api/core/rag/extractor/unstructured/unstructured_msg_extractor.py

@@ -1,4 +1,5 @@
 import logging
+from typing import override
 
 from configs import dify_config
 from core.rag.extractor.extractor_base import BaseExtractor
@@ -21,6 +22,7 @@ class UnstructuredMsgExtractor(BaseExtractor):
         self._api_url = api_url
         self._api_key = api_key
 
+    @override
     def extract(self) -> list[Document]:
         if self._api_url:
             from unstructured.partition.api import partition_via_api

api/core/rag/extractor/unstructured/unstructured_ppt_extractor.py

@@ -1,4 +1,5 @@
 import logging
+from typing import override
 
 from core.rag.extractor.extractor_base import BaseExtractor
 from core.rag.models.document import Document
@@ -20,6 +21,7 @@ class UnstructuredPPTExtractor(BaseExtractor):
         self._api_url = api_url
         self._api_key = api_key
 
+    @override
     def extract(self) -> list[Document]:
         if self._api_url:
             from unstructured.partition.api import partition_via_api

api/core/rag/extractor/unstructured/unstructured_pptx_extractor.py

@@ -1,4 +1,5 @@
 import logging
+from typing import override
 
 from core.rag.extractor.extractor_base import BaseExtractor
 from core.rag.models.document import Document
@@ -20,6 +21,7 @@ class UnstructuredPPTXExtractor(BaseExtractor):
         self._api_url = api_url
         self._api_key = api_key
 
+    @override
     def extract(self) -> list[Document]:
         if self._api_url:
             from unstructured.partition.api import partition_via_api

api/core/rag/extractor/unstructured/unstructured_xml_extractor.py

@@ -1,4 +1,5 @@
 import logging
+from typing import override
 
 from configs import dify_config
 from core.rag.extractor.extractor_base import BaseExtractor
@@ -21,6 +22,7 @@ class UnstructuredXmlExtractor(BaseExtractor):
         self._api_url = api_url
         self._api_key = api_key
 
+    @override
     def extract(self) -> list[Document]:
         if self._api_url:
             from unstructured.partition.api import partition_via_api