Merge remote-tracking branch 'upstream/main' into pprados/fix_password

Author: pprados

.github/workflows/ingest-test-fixtures-update-pr.yml

@@ -109,6 +109,7 @@ jobs:
           sudo apt-get install -y tesseract-ocr-kor
           sudo apt-get install diffstat
           tesseract --version
+          python -m nltk.downloader punkt_tab averaged_perceptron_tagger_eng
           ./test_unstructured_ingest/test-ingest-src.sh
 
       - name: Save branch name to environment file

CHANGELOG.md

@@ -1,3 +1,12 @@
+## 0.16.14-dev0
+
+### Enhancements
+
+### Features
+
+### Fixes
+- **Fix an issue with multiple values for `infer_table_structure`** when paritioning email with image attachements the kwarg calls into `partition` to partition the image already contains `infer_table_structure`. Now `partition` function checks if the `kwarg` has `infer_table_structure` already
+
 ## 0.16.13
 
 ### Enhancements

test_unstructured/partition/test_auto.py

@@ -570,6 +570,33 @@ def test_auto_partition_pdf_with_fast_strategy(request: FixtureRequest):
     )
 
 
+@pytest.mark.parametrize("infer_bool", [True, False])
+def test_auto_handles_kwarg_with_infer_table_structure(infer_bool):
+    with patch(
+        "unstructured.partition.pdf_image.ocr.process_file_with_ocr",
+    ) as mock_process_file_with_model:
+        partition(
+            example_doc_path("pdf/layout-parser-paper-fast.pdf"),
+            pdf_infer_table_structure=True,
+            strategy=PartitionStrategy.HI_RES,
+            infer_table_structure=infer_bool,
+        )
+        assert mock_process_file_with_model.call_args[1]["infer_table_structure"] is infer_bool
+
+
+def test_auto_handles_kwarg_with_infer_table_structure_when_none():
+    with patch(
+        "unstructured.partition.pdf_image.ocr.process_file_with_ocr",
+    ) as mock_process_file_with_model:
+        partition(
+            example_doc_path("pdf/layout-parser-paper-fast.pdf"),
+            pdf_infer_table_structure=True,
+            strategy=PartitionStrategy.HI_RES,
+            infer_table_structure=None,
+        )
+        assert mock_process_file_with_model.call_args[1]["infer_table_structure"] is True
+
+
 def test_auto_partition_pdf_uses_pdf_infer_table_structure_argument():
     with patch(
         "unstructured.partition.pdf_image.ocr.process_file_with_ocr",