Fix/fix ocr region to elements bug (#3891)

This PR fixes a bug in `build_layout_elements_from_ocr_regions` where
texts are joint in incorrect orders.

The bug is due to incorrect masking of the `ocr_regions` after some are
already selected as one of the final groups. The fix uses simpler method
to mask the indices by simply use the same indices that adds the regions
to the final groups to mask them so they are not considered again.

## Testing

This PR adds a unit test specifically aimed for this bug. Without the
fix the test would fail.
Additionally any PDF files with repeated texts has a potential to
trigger this bug. e.g., create a simple pdf use the test text

```python
"LayoutParser: \n\nA Unified Toolkit for Deep Learning Based Document Image\n\nLayoutParser for Deep Learning"
```
and partition with `ocr_only` mode on main branch would hit this bug and
output text where position of the second "LayoutParser" is incorrect.
```python
[
    'LayoutParser:', 
    'A Unified Toolkit for Deep Learning Based Document Image',
    'for Deep Learning LayoutParser',
]
```

CHANGELOG.md

@@ -1,4 +1,4 @@
-## 0.16.17-dev1
+## 0.16.17-dev2
 
 ### Enhancements
 - **Refactoring the VoyageAI integration** to use voyageai package directly, allowing extra features.
@@ -6,6 +6,7 @@
 ### Features
 
 ### Fixes
+- **Fix a bug where `build_layout_elements_from_cor_regions` incorrectly joins texts in wrong order**.
 
 ## 0.16.16
 

test_unstructured/partition/pdf_image/test_inference_utils.py

@@ -91,3 +91,79 @@ def test_build_layout_elements_from_ocr_regions_with_multi_line_text(mock_embedd
             ),
         ]
     )
+
+
+def test_build_layout_elements_from_ocr_regions_with_repeated_texts(mock_embedded_text_regions):
+    mock_embedded_text_regions.extend(
+        [
+            LayoutElement.from_coords(
+                x1=453.00277777777774,
+                y1=417.319341111111,
+                x2=711.5338541666665,
+                y2=458.28571222222206,
+                text="LayoutParser",
+                type=ElementType.UNCATEGORIZED_TEXT,
+            ),
+            LayoutElement.from_coords(
+                x1=453.00277777777774,
+                y1=468.319341111111,
+                x2=711.5338541666665,
+                y2=478.28571222222206,
+                text="for",
+                type=ElementType.UNCATEGORIZED_TEXT,
+            ),
+            LayoutElement.from_coords(
+                x1=453.00277777777774,
+                y1=488.319341111111,
+                x2=711.5338541666665,
+                y2=500.28571222222206,
+                text="Deep",
+                type=ElementType.UNCATEGORIZED_TEXT,
+            ),
+            LayoutElement.from_coords(
+                x1=453.00277777777774,
+                y1=510.319341111111,
+                x2=711.5338541666665,
+                y2=550.28571222222206,
+                text="Learning",
+                type=ElementType.UNCATEGORIZED_TEXT,
+            ),
+        ]
+    )
+    text = (
+        "LayoutParser: \n\nA Unified Toolkit for Deep Learning Based Document Image\n\n"
+        "LayoutParser for Deep Learning"
+    )
+    elements = build_layout_elements_from_ocr_regions(
+        TextRegions.from_list(mock_embedded_text_regions),
+        text,
+        group_by_ocr_text=True,
+    )
+    assert elements == LayoutElements.from_list(
+        [
+            LayoutElement.from_coords(
+                x1=453.00277777777774,
+                y1=317.319341111111,
+                x2=711.5338541666665,
+                y2=358.28571222222206,
+                text="LayoutParser:",
+                type=ElementType.UNCATEGORIZED_TEXT,
+            ),
+            LayoutElement.from_coords(
+                x1=437.83888888888885,
+                y1=317.319341111111,
+                x2=1256.334784222222,
+                y2=406.9837855555556,
+                text="A Unified Toolkit for Deep Learning Based Document Image",
+                type=ElementType.UNCATEGORIZED_TEXT,
+            ),
+            LayoutElement.from_coords(
+                x1=453.00277777777774,
+                y1=417.319341111111,
+                x2=711.5338541666665,
+                y2=550.28571222222206,
+                text="LayoutParser for Deep Learning",
+                type=ElementType.UNCATEGORIZED_TEXT,
+            ),
+        ]
+    )

unstructured/__version__.py

@@ -1 +1 @@
-__version__ = "0.16.17-dev1"  # pragma: no cover
+__version__ = "0.16.17-dev2"  # pragma: no cover

unstructured/partition/pdf_image/inference_utils.py

@@ -62,12 +62,12 @@ def build_layout_elements_from_ocr_regions(
                     break
                 if text in words:
                     regions.append(indices[mask][i])
-                    mask[mask][i] = False
                     words.remove(text)
 
             if not regions:
                 continue
 
+            mask[regions] = False
             grouped_regions.append(ocr_regions.slice(regions))
     else:
         grouped_regions = partition_groups_from_regions(ocr_regions)