refactor type hints to avoid mutable default args

Unstructured-IO · Nov 8, 2023 · 6516806 · 6516806
1 parent eaddd67
commit 6516806
Show file tree

Hide file tree

Showing 2 changed files with 6 additions and 6 deletions.
diff --git a/unstructured/partition/lang.py b/unstructured/partition/lang.py
@@ -163,7 +163,7 @@ def prepare_languages_for_tesseract(languages: Optional[List[str]] = ["eng"]):
     return "+".join(converted_languages)
 
 
-def check_user_defined_languages(languages, ocr_languages):
+def check_user_defined_languages(languages: Optional[List[str]], ocr_languages: Optional[str]):
     # The auto `partition` function uses `None` as a default because the default for
     # `partition_pdf` and `partition_img` conflict with the other partitioners that use ["auto"]
     if languages is None:

diff --git a/unstructured/partition/pdf.py b/unstructured/partition/pdf.py
@@ -117,7 +117,7 @@ def partition_pdf(
     strategy: str = "auto",
     infer_table_structure: bool = False,
     ocr_languages: Optional[str] = None,  # changing to optional for deprecation
-    languages: List[str] = ["eng"],
+    languages: Optional[List[str]] = None,
     include_metadata: bool = True,  # used by decorator
     metadata_filename: Optional[str] = None,  # used by decorator
     metadata_last_modified: Optional[str] = None,
@@ -183,7 +183,7 @@ def extractable_elements(
     filename: str = "",
     file: Optional[Union[bytes, IO[bytes]]] = None,
     include_page_breaks: bool = False,
-    languages: List[str] = None,
+    languages: Optional[List[str]] = None,
     metadata_last_modified: Optional[str] = None,
     **kwargs: Any,
 ):
@@ -219,7 +219,7 @@ def partition_pdf_or_image(
     strategy: str = "auto",
     infer_table_structure: bool = False,
     ocr_languages: Optional[str] = None,
-    languages: Optional[List[str]] = ["eng"],
+    languages: Optional[List[str]] = None,
     metadata_last_modified: Optional[str] = None,
     extract_images_in_pdf: bool = False,
     image_output_dir_path: Optional[str] = None,
@@ -463,7 +463,7 @@ def _partition_pdf_with_pdfminer(
     file: Optional[IO[bytes]] = None,
     include_page_breaks: bool = False,
     metadata_last_modified: Optional[str] = None,
-    languages: List[str] = None,
+    languages: Optional[List[str]] = None,
     **kwargs: Any,
 ) -> List[Element]:
     """Partitions a PDF using PDFMiner instead of using a layoutmodel. Used for faster
@@ -524,7 +524,7 @@ def _process_pdfminer_pages(
     fp: BinaryIO,
     filename: str = "",
     include_page_breaks: bool = False,
-    languages: List[str] = None,
+    languages: Optional[List[str]] = None,
     metadata_last_modified: Optional[str] = None,
     sort_mode: str = SORT_MODE_XY_CUT,
     **kwargs,