chore: changed type IO to IO[bytes] (#878)

Co-authored-by: Nathan Chappell <[email protected]>
Co-authored-by: Matt Robinson <[email protected]>

Author: 3 people

unstructured/file_utils/encoding.py

@@ -51,7 +51,7 @@ def format_encoding_str(encoding: str) -> str:
 
 def detect_file_encoding(
     filename: str = "",
-    file: Optional[Union[bytes, IO]] = None,
+    file: Optional[Union[bytes, IO[bytes]]] = None,
 ) -> Tuple[str, str]:
     if filename:
         with open(filename, "rb") as f:
@@ -98,7 +98,7 @@ def detect_file_encoding(
 
 def read_txt_file(
     filename: str = "",
-    file: Optional[Union[bytes, IO]] = None,
+    file: Optional[Union[bytes, IO[bytes]]] = None,
     encoding: Optional[str] = None,
 ) -> Tuple[str, str]:
     """Extracts document metadata from a plain text document."""

unstructured/file_utils/file_conversion.py

@@ -25,7 +25,7 @@ def convert_file_to_text(filename: str, source_format: str, target_format: str)
 def convert_file_to_html_text(
     source_format: str,
     filename: Optional[str] = None,
-    file: Optional[IO] = None,
+    file: Optional[IO[bytes]] = None,
 ) -> str:
     """Converts a document to HTML raw text. Enables the doucment to be
     processed using the partition_html function."""

unstructured/file_utils/filetype.py

@@ -207,7 +207,7 @@ def _resolve_symlink(file_path):
 def detect_filetype(
     filename: Optional[str] = None,
     content_type: Optional[str] = None,
-    file: Optional[IO] = None,
+    file: Optional[IO[bytes]] = None,
     file_filename: Optional[str] = None,
     encoding: Optional[str] = "utf-8",
 ) -> Optional[FileType]:
@@ -370,7 +370,7 @@ def _detect_filetype_from_octet_stream(file: IO) -> FileType:
 
 def _read_file_start_for_type_check(
     filename: Optional[str] = None,
-    file: Optional[IO] = None,
+    file: Optional[IO[bytes]] = None,
     encoding: Optional[str] = "utf-8",
 ) -> str:
     """Reads the start of the file and returns the text content."""
@@ -396,7 +396,7 @@ def _read_file_start_for_type_check(
 
 def _is_text_file_a_json(
     filename: Optional[str] = None,
-    file: Optional[IO] = None,
+    file: Optional[IO[bytes]] = None,
     encoding: Optional[str] = "utf-8",
 ):
     """Detects if a file that has a text/plain MIME type is a JSON file."""
@@ -413,7 +413,7 @@ def _count_commas(text: str):
 
 def _is_text_file_a_csv(
     filename: Optional[str] = None,
-    file: Optional[IO] = None,
+    file: Optional[IO[bytes]] = None,
     encoding: Optional[str] = "utf-8",
 ):
     """Detects if a file that has a text/plain MIME type is a CSV file."""

unstructured/file_utils/metadata.py

@@ -41,7 +41,7 @@ def to_dict(self):
 
 def get_docx_metadata(
     filename: str = "",
-    file: Optional[IO] = None,
+    file: Optional[IO[bytes]] = None,
 ) -> Metadata:
     """Extracts document metadata from a Microsoft .docx document."""
     if filename:
@@ -74,7 +74,7 @@ def get_docx_metadata(
 
 def get_xlsx_metadata(
     filename: str = "",
-    file: Optional[IO] = None,
+    file: Optional[IO[bytes]] = None,
 ) -> Metadata:
     """Extracts document metadata from a Microsoft .xlsx document."""
     if filename:
@@ -108,7 +108,7 @@ def get_xlsx_metadata(
 
 def get_jpg_metadata(
     filename: str = "",
-    file: Optional[IO] = None,
+    file: Optional[IO[bytes]] = None,
 ) -> Metadata:
     """Extracts metadata from a JPG image, including EXIF metadata."""
     if filename:

unstructured/partition/api.py

@@ -15,7 +15,7 @@
 def partition_via_api(
     filename: Optional[str] = None,
     content_type: Optional[str] = None,
-    file: Optional[IO] = None,
+    file: Optional[IO[bytes]] = None,
     file_filename: Optional[str] = None,
     api_url: str = "https://api.unstructured.io/general/v0/general",
     api_key: str = "",

unstructured/partition/auto.py

@@ -38,7 +38,7 @@
 def partition(
     filename: Optional[str] = None,
     content_type: Optional[str] = None,
-    file: Optional[IO] = None,
+    file: Optional[IO[bytes]] = None,
     file_filename: Optional[str] = None,
     url: Optional[str] = None,
     include_page_breaks: bool = False,

unstructured/partition/common.py

@@ -218,7 +218,7 @@ def spooled_to_bytes_io_if_needed(
 
 
 def convert_to_bytes(
-    file: Optional[Union[bytes, SpooledTemporaryFile, IO]] = None,
+    file: Optional[Union[bytes, SpooledTemporaryFile, IO[bytes]]] = None,
 ) -> bytes:
     if isinstance(file, bytes):
         f_bytes = file

unstructured/partition/csv.py

@@ -18,7 +18,7 @@
 @add_metadata_with_filetype(FileType.CSV)
 def partition_csv(
     filename: Optional[str] = None,
-    file: Optional[Union[IO, SpooledTemporaryFile]] = None,
+    file: Optional[Union[IO[bytes], SpooledTemporaryFile]] = None,
     metadata_filename: Optional[str] = None,
     include_metadata: bool = True,
     **kwargs,

unstructured/partition/doc.py

@@ -12,7 +12,7 @@
 @add_metadata_with_filetype(FileType.DOC)
 def partition_doc(
     filename: Optional[str] = None,
-    file: Optional[IO] = None,
+    file: Optional[IO[bytes]] = None,
     include_page_breaks: bool = True,
     include_metadata: bool = True,
     metadata_filename: Optional[str] = None,

unstructured/partition/docx.py

@@ -107,7 +107,7 @@ def _get_runs(node, parent):
 @add_metadata_with_filetype(FileType.DOCX)
 def partition_docx(
     filename: Optional[str] = None,
-    file: Optional[Union[IO, SpooledTemporaryFile]] = None,
+    file: Optional[Union[IO[bytes], SpooledTemporaryFile]] = None,
     metadata_filename: Optional[str] = None,
     include_page_breaks: bool = True,
     include_metadata: bool = True,
@@ -288,7 +288,7 @@ def _get_headers_and_footers(
 def convert_and_partition_docx(
     source_format: str,
     filename: Optional[str] = None,
-    file: Optional[IO] = None,
+    file: Optional[IO[bytes]] = None,
     include_metadata: bool = True,
     metadata_filename: Optional[str] = None,
 ) -> List[Element]: