Fix file detection when spooled file is pased (#3932)

This pull request fixes the scenario when SpooledTemporaryFile is passed
to detect_file type. In such cases some weird number was assigned as
'name' (and it couldn't be overwritten as SpooledTemporaryFile can't
have fields assigned 😩 ) so I added in our object factory just another
scenario where we parse this type of file.
For BytesIo `name` attr is None as it should be and some other metadata
fields are leveraged for file type recognition

Author: plutasnyy

CHANGELOG.md

@@ -1,3 +1,13 @@
+## 0.16.23
+
+### Enhancements
+
+### Features
+
+### Fixes
+- **Fixes detect_filetype when SpooledTemporaryFile is passed**. Previously some random name would get assigned to the file and the function raised error.
+
+
 ## 0.16.22
 
 ### Enhancements

test_unstructured/partition/test_auto.py

@@ -9,7 +9,7 @@
 import warnings
 from importlib import import_module
 from typing import Iterator
-from unittest.mock import patch
+from unittest.mock import MagicMock, patch
 
 import pytest
 from PIL import Image
@@ -42,6 +42,7 @@
     Text,
     Title,
 )
+from unstructured.file_utils.filetype import detect_filetype
 from unstructured.file_utils.model import FileType
 from unstructured.partition.auto import _PartitionerLoader, partition
 from unstructured.partition.common import UnsupportedFileFormatError
@@ -1241,6 +1242,17 @@ def test_auto_partition_applies_the_correct_filetype_for_all_filetypes(
     )
 
 
+def test_detect_filetype_maps_file_to_bytes_io_when_spooled_temp_file_used(mocker):
+    detect_filetype_mock = MagicMock(return_value=FileType.JSON)
+    mocker.patch("unstructured.file_utils.filetype._FileTypeDetector", detect_filetype_mock)
+    with tempfile.SpooledTemporaryFile() as f:
+        f.write(b'{"text": Hello, world!}')
+        f.seek(0)
+        detect_filetype(file=f)
+    file_detection_context = detect_filetype_mock.file_type.call_args[0][0]
+    assert file_detection_context.text_head == '{"text": Hello, world!}'
+
+
 # -- .languages -----------------------------------------------------------
 
 

unstructured/__version__.py

@@ -1 +1 @@
-__version__ = "0.16.22"  # pragma: no cover
+__version__ = "0.16.23"  # pragma: no cover

unstructured/file_utils/filetype.py

@@ -31,9 +31,11 @@
 import contextlib
 import functools
 import importlib.util
+import io
 import json
 import os
 import re
+import tempfile
 import zipfile
 from typing import IO, Callable, Iterator, Optional
 
@@ -60,7 +62,7 @@
 
 def detect_filetype(
     file_path: str | None = None,
-    file: IO[bytes] | None = None,
+    file: IO[bytes] | tempfile.SpooledTemporaryFile | None = None,
     encoding: str | None = None,
     content_type: str | None = None,
     metadata_file_path: Optional[str] = None,
@@ -92,9 +94,14 @@ def detect_filetype(
           filesystem.
         - Neither `file_path` nor `file` were specified.
     """
+    file_buffer = file
+    if isinstance(file, tempfile.SpooledTemporaryFile):
+        file_buffer = io.BytesIO(file.read())
+        file.seek(0)
+
     ctx = _FileTypeDetectionContext.new(
         file_path=file_path,
-        file=file,
+        file=file_buffer,
         encoding=encoding,
         content_type=content_type,
         metadata_file_path=metadata_file_path,