fix(file): confirm or correct asserted DOCX, PPTX, and XLSX content types (#3434)

**Summary**
The `content_type` argument received by `partition()` from the API is
sometimes unreliable for MS-Office 2007+ MIME-types. What we've observed
is that it gets the MS-Office bit right but falls down on distinguishing
PPTX from DOCX or XLSX.

Confirmation of these types is simple, fast, and reliable. Confirm all
MS-Office `content_type` argument values asserted by callers of
`detect_filetype()` and correct swapped values.

CHANGELOG.md

@@ -13,6 +13,7 @@
 * **EML files specified as a file-path are detected correctly.** Resolved a bug where an EML file submitted to `partition()` as a file-path was identified as TXT and partitioned using `partition_text()`. EML files specified by path are now identified and processed correctly, including processing any attachments.
 * **A DOCX, PPTX, or XLSX file specified by path and ambiguously identified as MIME-type "application/octet-stream" is identified correctly.** Resolves a shortcoming where a file specified by path immediately fell back to filename-extension based identification when misidentified as "application/octet-stream", either by asserted content type or a mis-guess by libmagic. An MS Office file misidentified in this way is now correctly identified regardless of its filename and whether it is specified by path or file-like object.
 * **Textual content retrieved from a URL with gzip transport compression now partitions correctly.** Resolves a bug where a textual file-type (such as Markdown) retrieved by passing a URL to `partition()` would raise when `gzip` compression was used for transport by the server.
+* **A DOCX, PPTX, or XLSX content-type asserted on partition is confirmed or fixed.** Resolves a bug where calling `partition()` with a swapped MS-Office `content_type` would cause the file-type to be misidentified. A DOCX, PPTX, or XLSX MIME-type received by `partition()` is now checked for accuracy and corrected if the file is for a different MS-Office 2007+ type.
 
 ## 0.15.0
 

test_unstructured/file_utils/test_filetype.py

@@ -153,6 +153,38 @@ def test_it_detects_correct_file_type_from_file_no_name_with_correct_asserted_co
     assert file_type is expected_value
 
 
+@pytest.mark.parametrize(
+    ("expected_value", "file_name"),
+    [
+        (FileType.DOCX, "simple.docx"),
+        (FileType.PPTX, "fake-power-point.pptx"),
+        (FileType.XLSX, "stanley-cups.xlsx"),
+    ],
+)
+@pytest.mark.parametrize(
+    "content_type",
+    [
+        "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
+        "application/vnd.openxmlformats-officedocument.presentationml.presentation",
+        "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet",
+    ],
+)
+def test_it_detects_correct_file_type_from_file_no_name_with_swapped_ms_office_content_type(
+    file_name: str, content_type: str, expected_value: FileType, ctx_mime_type_: Mock
+):
+    # -- disable strategies 2 & 3, content-type strategy should get this on its own --
+    ctx_mime_type_.return_value = None
+    with open(example_doc_path(file_name), "rb") as f:
+        file = io.BytesIO(f.read())
+
+    file_type = detect_filetype(file=file, content_type=content_type)
+
+    # -- Strategy 1 should not need to refer to guessed MIME-type and detection should not
+    # -- fall-back to strategy 2 for any of these test cases.
+    ctx_mime_type_.assert_not_called()
+    assert file_type is expected_value
+
+
 # ================================================================================================
 # STRATEGY #2 - GUESS MIME-TYPE WITH LIBMAGIC
 # ================================================================================================
@@ -664,13 +696,13 @@ class Describe_FileTypeDetectionContext:
 
     # -- .file_head ---------------------------------------------
 
-    def it_grabs_the_first_4k_bytes_of_the_file_for_use_by_magic(self):
+    def it_grabs_the_first_8k_bytes_of_the_file_for_use_by_magic(self):
         ctx = _FileTypeDetectionContext(file_path=example_doc_path("norwich-city.txt"))
 
         head = ctx.file_head
 
         assert isinstance(head, bytes)
-        assert len(head) == 4096
+        assert len(head) == 8192
         assert head.startswith(b"Iwan Roberts\nRoberts celebrating after")
 
     # -- .file_path ---------------------------------------------

unstructured/file_utils/filetype.py

@@ -161,6 +161,10 @@ class _FileTypeDetector:
         if not content_type:
             return None
 
+        # -- MS-Office 2007+ (OpenXML) content_type value is sometimes unreliable --
+        if differentiator := _ZipFileDifferentiator.applies(self._ctx, content_type):
+            return differentiator.file_type
+
         # -- otherwise we trust the passed `content_type` as long as `FileType` recognizes it --
         return FileType.from_mime_type(content_type)
 
@@ -307,7 +311,7 @@ class _FileTypeDetectionContext:
     def file_head(self) -> bytes:
         """The initial bytes of the file to be recognized, for use with libmagic detection."""
         with self.open() as file:
-            return file.read(4096)
+            return file.read(8192)
 
     @lazyproperty
     def file_path(self) -> str | None: