fix: Fix for Pillow error when extracting PNG images

CHANGELOG.md

@@ -1,3 +1,12 @@
+## 0.17.7-dev0
+
+### Enhancements
+
+### Features
+
+### Fixes
+- **Fix image extraction for PNG files.** When `extract_image_block_to_payload` is True, and the image is a PNG, we get a Pillow error. We need to remove the PNG transparency layer before saving the image.
+
 ## 0.17.6
 
 ### Enhancements

test_unstructured/partition/pdf_image/test_pdf_image_utils.py

@@ -73,6 +73,7 @@ def test_convert_pdf_to_image_raises_error(filename=example_doc_path("embedded-i
     [
         (example_doc_path("pdf/layout-parser-paper-fast.pdf"), False),
         (example_doc_path("img/layout-parser-paper-fast.jpg"), True),
+        (example_doc_path("img/english-and-korean.png"), True),
     ],
 )
 @pytest.mark.parametrize("element_category_to_save", [ElementType.IMAGE, ElementType.TABLE])

unstructured/__version__.py

@@ -1 +1 @@
-__version__ = "0.17.6"  # pragma: no cover
+__version__ = "0.17.7-dev0"  # pragma: no cover

unstructured/partition/pdf_image/pdf_image_utils.py

@@ -204,6 +204,11 @@ def save_elements(
                 image_path = image_paths[page_index]
                 image = Image.open(image_path)
                 cropped_image = image.crop(padded_bbox)
+
+                # PNG images with transparency need to be converted before saving
+                if cropped_image.mode == "RGBA":
+                    cropped_image = cropped_image.convert("RGB")
+
                 if extract_image_block_to_payload:
                     buffered = BytesIO()
                     cropped_image.save(buffered, format="JPEG")