test: add check crop box padding to save_elements test (#4123)

Updated `save_elements` test to check the behavior of the environment
variables `EXTRACT_IMAGE_BLOCK_CROP_HORIZONTAL_PAD` and
`EXTRACT_IMAGE_BLOCK_CROP_VERTICAL_PAD` that pad the crop box for image
extraction.

<!-- CURSOR_SUMMARY -->
---

> [!NOTE]
> Enhances save_elements tests to validate crop-box padding via env vars
and image dimensions for both payload and file outputs; bumps version
and updates changelog.
> 
> - **Tests (pdf_image_utils)**:
> - `test_save_elements` now parametrizes
`horizontal_padding`/`vertical_padding`, sets
`EXTRACT_IMAGE_BLOCK_CROP_HORIZONTAL_PAD` and
`EXTRACT_IMAGE_BLOCK_CROP_VERTICAL_PAD`, and asserts padded image
dimensions for both `extract_image_block_to_payload` paths (decoding
`image_base64` or reading saved file).
>   - Adds required imports (`base64`, `io`).
> - **Versioning**:
>   - Update `unstructured/__version__.py` to `0.18.21-dev0`.
>   - Add CHANGELOG entry noting the unit test enhancement.
> 
> <sup>Written by [Cursor
Bugbot](https://cursor.com/dashboard?tab=bugbot) for commit
a23bf6a. This will update automatically
on new commits. Configure
[here](https://cursor.com/dashboard?tab=bugbot).</sup>
<!-- /CURSOR_SUMMARY -->

Author: qued

CHANGELOG.md

@@ -1,8 +1,25 @@
+## 0.18.21-dev0
+
+### Enhancement
+- Update save_elements unit test to check crop box padding behavior
+
+### Features
+
+### Fixes
+
 ## 0.18.20
 
 ### Enhancement
 - Improve the VoyageAI integration
 - Add voyage-context-3 support
+
+### Features
+
+### Fixes
+
+## 0.18.19
+
+### Enhancement
 - Flag extracted elements as such in the metadata for downstream use
 
 ### Features

test_unstructured/partition/pdf_image/test_pdf_image_utils.py

@@ -1,3 +1,5 @@
+import base64
+import io
 import os
 import tempfile
 from unittest.mock import MagicMock, patch
@@ -78,12 +80,21 @@ def test_convert_pdf_to_image_raises_error():
 )
 @pytest.mark.parametrize("element_category_to_save", [ElementType.IMAGE, ElementType.TABLE])
 @pytest.mark.parametrize("extract_image_block_to_payload", [False, True])
+@pytest.mark.parametrize("horizontal_padding", [0, 20])
+@pytest.mark.parametrize("vertical_padding", [0, 10])
 def test_save_elements(
     element_category_to_save,
     extract_image_block_to_payload,
     filename,
     is_image,
+    horizontal_padding,
+    vertical_padding,
+    monkeypatch,
 ):
+    if horizontal_padding > 0:
+        monkeypatch.setenv("EXTRACT_IMAGE_BLOCK_CROP_HORIZONTAL_PAD", str(horizontal_padding))
+    if vertical_padding > 0:
+        monkeypatch.setenv("EXTRACT_IMAGE_BLOCK_CROP_VERTICAL_PAD", str(vertical_padding))
     with tempfile.TemporaryDirectory() as tmpdir:
         elements = [
             Image(
@@ -136,10 +147,25 @@ def test_save_elements(
             if extract_image_block_to_payload:
                 assert isinstance(el.metadata.image_base64, str)
                 assert isinstance(el.metadata.image_mime_type, str)
+                image_bytes = base64.b64decode(el.metadata.image_base64)
+                image = PILImg.open(io.BytesIO(image_bytes))
+                x1, y1 = el.metadata.coordinates.points[0]
+                x2, y2 = el.metadata.coordinates.points[2]
+                width = x2 - x1
+                height = y2 - y1
+                assert image.width == width + 2 * horizontal_padding
+                assert image.height == height + 2 * vertical_padding
                 assert not el.metadata.image_path
                 assert not os.path.isfile(expected_image_path)
             else:
                 assert os.path.isfile(expected_image_path)
+                image = PILImg.open(expected_image_path)
+                x1, y1 = el.metadata.coordinates.points[0]
+                x2, y2 = el.metadata.coordinates.points[2]
+                width = x2 - x1
+                height = y2 - y1
+                assert image.width == width + 2 * horizontal_padding
+                assert image.height == height + 2 * vertical_padding
                 assert el.metadata.image_path == expected_image_path
                 assert not el.metadata.image_base64
                 assert not el.metadata.image_mime_type

unstructured/__version__.py

@@ -1 +1 @@
-__version__ = "0.18.20"  # pragma: no cover
+__version__ = "0.18.21-dev0"  # pragma: no cover