From d570f4624bb8c5dc75f0009775925fdaa40defb0 Mon Sep 17 00:00:00 2001
From: Philippe PRADOS <github@prados.fr>
Date: Mon, 7 Apr 2025 17:57:20 +0200
Subject: [PATCH] Fix sort_page_element. ensures that sorting is stable and not
 random. (#3978)

The sort_page_element() use the element id to sort the elements.
Two executions of the same code, on the same file, produce different
results. The order of the elements is random.
This makes it impossible to write stable unit tests, for example, or to
obtain reproducible results.
---
 CHANGELOG.md                                  |  3 +++
 .../partition/pdf_image/test_pdf.py           | 21 +++++++++++++++++++
 unstructured/partition/utils/sorting.py       |  1 -
 3 files changed, 24 insertions(+), 1 deletion(-)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index baa69aae9..4da58bbc9 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -5,6 +5,9 @@
 ### Features
 
 ### Fixes
+- The sort_page_element() use the element id to sort the elements.
+Two executions of the same code, on the same file, produce different results. The order of the elements is random.
+This makes it impossible to write stable unit tests, for example, or to obtain reproducible results.
 - **Do not use NLP to determine element types for extracted elements with hi_res.** This avoids extraneous Title elements in hi_res outputs. This only applies to *extracted* elements, meaning text objects that are found outside of Object Detection objects which get mapped to *inferred* elements. (*extracted* and *inferred* elements get merged together to form the list of `Element`s returned by `pdf_partition()`)
 
 ## 0.17.5
diff --git a/test_unstructured/partition/pdf_image/test_pdf.py b/test_unstructured/partition/pdf_image/test_pdf.py
index 7a0c8ff29..70eec35fd 100644
--- a/test_unstructured/partition/pdf_image/test_pdf.py
+++ b/test_unstructured/partition/pdf_image/test_pdf.py
@@ -1603,3 +1603,24 @@ def test_partition_pdf_with_specified_ocr_agents(mocker):
 
     assert spy.call_args_list[0][1] == {"language": "eng", "ocr_agent_module": OCR_AGENT_TESSERACT}
     assert spy.call_args_list[1][1] == {"language": "en", "ocr_agent_module": OCR_AGENT_PADDLE}
+
+
+def test_reproductible_pdf_loader():
+    from glob import glob
+
+    for f in glob(example_doc_path("pdf/layout-parser-paper.pdf")):
+        elements_1 = pdf.partition_pdf(
+            filename=f,
+            strategy=PartitionStrategy.AUTO,
+            infer_table_structure=False,
+        )
+        for _ in range(4):
+            elements_2 = pdf.partition_pdf(
+                filename=f,
+                strategy=PartitionStrategy.AUTO,
+                infer_table_structure=False,
+            )
+            for e1, e2 in zip(elements_1, elements_2):
+                assert e1.text == e2.text, f"load two time {f=} return differents results"
+            else:
+                break
diff --git a/unstructured/partition/utils/sorting.py b/unstructured/partition/utils/sorting.py
index 8cdc885dd..59d550958 100644
--- a/unstructured/partition/utils/sorting.py
+++ b/unstructured/partition/utils/sorting.py
@@ -179,7 +179,6 @@ def sort_page_elements(
             key=lambda el: (
                 el.metadata.coordinates.points[0][1] if el.metadata.coordinates else float("inf"),
                 el.metadata.coordinates.points[0][0] if el.metadata.coordinates else float("inf"),
-                el.id,
             ),
         )
     else: