fix(auto): quick fix for auto test failing in CI (#3715)

Better fix to follow.

CHANGELOG.md

@@ -1,4 +1,4 @@
-## 0.15.14-dev13
+## 0.15.14-dev14
 
 ### Enhancements
 
@@ -18,6 +18,7 @@
 * **Remove obsolete min_partition/max_partition args from TXT and EML.** The legacy `min_partition` and `max_partition` parameters were an initial rough implementation of chunking but now interfere with chunking and are unused. Remove those parameters from `partition_text()` and `partition_email()`.
 * **Remove double-decoration on EML and MSG.** Refactor these partitioners to rely on the new `@apply_metadata()` decorator operating on partitioners they delegate to (TXT, HTML, and all others for attachments) and remove direct decoration from EML and MSG.
 * **Remove double-decoration for PPT.** Remove decorators from the delegating PPT partitioner.
+* **Quick-fix CI error in auto test-filetype.** Better fix to follow shortly.
 
 ## 0.15.13
 

test_unstructured/partition/test_auto.py

@@ -1207,35 +1207,39 @@ def test_auto_partition_overwrites_any_filetype_applied_by_file_specific_partiti
 
 
 @pytest.mark.parametrize(
-    "file_type",
+    ("file_name", "file_type"),
     [
-        t
+        ("stanley-cups.csv", FileType.CSV),
-        for t in FileType
+        ("simple.doc", FileType.DOC),
-        if t
+        ("simple.docx", FileType.DOCX),
-        not in (
+        ("fake-email.eml", FileType.EML),
-            FileType.EMPTY,
+        ("simple.epub", FileType.EPUB),
-            FileType.JSON,
+        ("fake-html.html", FileType.HTML),
-            FileType.UNK,
+        ("README.md", FileType.MD),
-            FileType.WAV,
+        ("fake-email.msg", FileType.MSG),
-            FileType.XLS,
+        ("simple.odt", FileType.ODT),
-            FileType.ZIP,
+        ("pdf/DA-1p.pdf", FileType.PDF),
-        )
+        ("fake-power-point.ppt", FileType.PPT),
-        and t.partitioner_shortname != "image"
+        ("simple.pptx", FileType.PPTX),
+        ("README.rst", FileType.RST),
+        ("fake-doc.rtf", FileType.RTF),
+        ("stanley-cups.tsv", FileType.TSV),
+        ("fake-text.txt", FileType.TXT),
+        ("tests-example.xls", FileType.XLSX),
+        ("stanley-cups.xlsx", FileType.XLSX),
+        ("factbook.xml", FileType.XML),
     ],
 )
-def test_auto_partition_applies_the_correct_filetype_for_all_filetypes(file_type: FileType):
+def test_auto_partition_applies_the_correct_filetype_for_all_filetypes(
+    file_name: str, file_type: FileType
+):
+    file_path = example_doc_path(file_name)
     partition_fn_name = file_type.partitioner_function_name
     module = import_module(file_type.partitioner_module_qname)
     partition_fn = getattr(module, partition_fn_name)
 
-    # -- partition the first example-doc with the extension for this filetype --
+    # -- partition the example-doc for this filetype --
-    elements: list[Element] = []
+    elements = partition_fn(file_path)
-    doc_path = example_doc_path("pdf") if file_type == FileType.PDF else example_doc_path("")
-    extensions = file_type._extensions
-    for file in pathlib.Path(doc_path).iterdir():
-        if file.is_file() and file.suffix in extensions:
-            elements = partition_fn(str(file))
-            break
 
     assert elements
     assert all(

unstructured/__version__.py

@@ -1 +1 @@
-__version__ = "0.15.14-dev13"  # pragma: no cover
+__version__ = "0.15.14-dev14"  # pragma: no cover