fix: no UserWarning when partition_pdf is called (#179)

CHANGELOG.md

@@ -1,4 +1,4 @@
-## 0.4.5-dev0
+## 0.4.5-dev1
 
 * Loosen the default cap threshold to `0.5`.
 * Add a `NARRATIVE_TEXT_CAP_THRESHOLD` environment variable for controlling the cap ratio threshold.
@@ -7,6 +7,7 @@
   is insufficient to determine that the text is narrative.
 * Upper cased text is lower cased before checking for verbs. This helps avoid some missed verbs.
 * Adds an `Address` element for capturing elements that only contain an address.
+* Suppress the `UserWarning` when detectron is called
 
 ## 0.4.4
 

test_unstructured/partition/test_auto.py

@@ -1,6 +1,7 @@
 import os
 import pathlib
 import pytest
+import warnings
 
 import docx
 
@@ -136,6 +137,9 @@ def test_auto_partition_text_from_file():
         elements = partition(file=f)
     assert len(elements) > 0
     assert elements == EXPECTED_TEXT_OUTPUT
+
+
+def test_auto_partition_pdf_from_filename():
     filename = os.path.join(EXAMPLE_DOCS_DIRECTORY, "layout-parser-paper-fast.pdf")
     elements = partition(filename=filename)
 
@@ -150,7 +154,23 @@ def test_auto_partition_pdf_from_file():
     filename = os.path.join(EXAMPLE_DOCS_DIRECTORY, "layout-parser-paper-fast.pdf")
     with open(filename, "rb") as f:
         elements = partition(file=f)
-    assert len(elements) > 0
+
+    assert isinstance(elements[0], Title)
+    assert elements[0].text.startswith("LayoutParser")
+
+    assert isinstance(elements[1], NarrativeText)
+    assert elements[1].text.startswith("Zejiang Shen 1")
+
+
+def test_partition_pdf_doesnt_raise_warning():
+    filename = os.path.join(EXAMPLE_DOCS_DIRECTORY, "layout-parser-paper-fast.pdf")
+    # NOTE(robinson): This is the recommended way to check that no warning is emitted,
+    # per the pytest docs.
+    # ref: https://docs.pytest.org/en/7.0.x/how-to/capture-warnings.html
+    #      #additional-use-cases-of-warnings-in-tests
+    with warnings.catch_warnings():
+        warnings.simplefilter("error")
+        partition(filename=filename)
 
 
 def test_auto_partition_jpg():

unstructured/__version__.py

@@ -1 +1 @@
-__version__ = "0.4.5-dev0"  # pragma: no cover
+__version__ = "0.4.5-dev1"  # pragma: no cover

unstructured/partition/pdf.py

@@ -1,4 +1,5 @@
 from typing import List, Optional
+import warnings
 
 from unstructured.documents.elements import Element
 from unstructured.partition import _partition_via_api
@@ -54,9 +55,13 @@ def partition_pdf_or_image(
         out_template: Optional[str] = template
         if route_args[0] == "layout":
             out_template = None
-        layout_elements = _partition_pdf_or_image_local(
-            filename=filename, file=file, template=out_template, is_image=is_image
-        )
+
+        # NOTE(robinson): Catches a UserWarning that occurs when detectron is called
+        with warnings.catch_warnings():
+            warnings.simplefilter("ignore")
+            layout_elements = _partition_pdf_or_image_local(
+                filename=filename, file=file, template=out_template, is_image=is_image
+            )
     else:
         # NOTE(alan): Remove these lines after different models are handled by routing
         if template == "checkbox":