Fix: bulk reprocess latest version for root documents

src/documents/bulk_edit.py

@@ -408,10 +408,16 @@ def reprocess(doc_ids: list[int], *, remote_ocr: bool = False) -> Literal["OK"]:
 
     Consumption workflows do not run here, so ``remote_ocr`` is how the user
     asks for the remote engine when it is not configured to handle everything.
+
+    A root document with versions reprocesses its latest version, which is the
+    file whose content, archive and thumbnail are shown for it.
     """
-    for document_id in doc_ids:
+    for doc in Document.objects.select_related("root_document").filter(
+        id__in=doc_ids,
+    ):
+        pair = _resolve_root_and_source_doc(doc)
         update_document_content_maybe_archive_file.apply_async(
-            kwargs={"document_id": document_id, "remote_ocr": remote_ocr},
+            kwargs={"document_id": pair.source_doc.id, "remote_ocr": remote_ocr},
             headers={"trigger_source": PaperlessTask.TriggerSource.MANUAL},
         )
 

src/documents/tasks.py

@@ -490,18 +490,23 @@ def update_document_content_maybe_archive_file(
                     shutil.move(thumbnail, document.thumbnail_path)
 
             document.refresh_from_db()
+            root_document = (
+                document.root_document if document.root_document_id else document
+            )
             logger.info(
-                f"Updating index for document {document_id} ({document.archive_checksum})",
+                f"Updating index for document {root_document.pk} ({document.archive_checksum})",
             )
             from documents.search import get_backend
 
-            get_backend().add_or_update(document)
+            get_backend().add_or_update(root_document)
 
             ai_config = AIConfig()
             if ai_config.llm_index_enabled:
-                llm_index_add_or_update_document(document)
+                llm_index_add_or_update_document(root_document)
 
             clear_document_caches(document.pk)
+            if root_document.pk != document.pk:
+                clear_document_caches(root_document.pk)
 
         except Exception:
             logger.exception(

src/documents/tests/test_bulk_edit.py

@@ -2021,3 +2021,69 @@ class TestBulkEditReprocess(DirectoriesMixin, TestCase):
         self.assertEqual(mock_task.apply_async.call_count, 2)
         for call in mock_task.apply_async.call_args_list:
             self.assertTrue(call.kwargs["kwargs"]["remote_ocr"])
+
+    @mock.patch("documents.bulk_edit.update_document_content_maybe_archive_file")
+    def test_reprocess_root_uses_latest_version(self, mock_task: mock.Mock) -> None:
+        """
+        GIVEN:
+            - A root document with two versions
+        WHEN:
+            - reprocess is called with the root document
+        THEN:
+            - The latest version is reprocessed, not the root's original file
+        """
+        Document.objects.create(
+            title="test",
+            checksum="A-v1",
+            mime_type="application/pdf",
+            root_document=self.doc,
+            version_index=1,
+        )
+        latest = Document.objects.create(
+            title="test",
+            checksum="A-v2",
+            mime_type="application/pdf",
+            root_document=self.doc,
+            version_index=2,
+        )
+
+        bulk_edit.reprocess([self.doc.id])
+
+        mock_task.apply_async.assert_called_once()
+        self.assertEqual(
+            mock_task.apply_async.call_args.kwargs["kwargs"]["document_id"],
+            latest.id,
+        )
+
+    @mock.patch("documents.bulk_edit.update_document_content_maybe_archive_file")
+    def test_reprocess_explicit_version(self, mock_task: mock.Mock) -> None:
+        """
+        GIVEN:
+            - A root document with two versions
+        WHEN:
+            - reprocess is called with the older version
+        THEN:
+            - That version is reprocessed
+        """
+        older = Document.objects.create(
+            title="test",
+            checksum="A-v1",
+            mime_type="application/pdf",
+            root_document=self.doc,
+            version_index=1,
+        )
+        Document.objects.create(
+            title="test",
+            checksum="A-v2",
+            mime_type="application/pdf",
+            root_document=self.doc,
+            version_index=2,
+        )
+
+        bulk_edit.reprocess([older.id])
+
+        mock_task.apply_async.assert_called_once()
+        self.assertEqual(
+            mock_task.apply_async.call_args.kwargs["kwargs"]["document_id"],
+            older.id,
+        )

src/documents/tests/test_tasks.py

@@ -287,6 +287,61 @@ class TestUpdateContent(DirectoriesMixin, TestCase):
         tasks.update_document_content_maybe_archive_file(doc.pk)
         self.assertNotEqual(Document.objects.get(pk=doc.pk).content, "test")
 
+    @mock.patch("documents.tasks.clear_document_caches")
+    @mock.patch("documents.search.get_backend")
+    def test_update_content_version_indexes_root(
+        self,
+        mock_get_backend: mock.Mock,
+        mock_clear_caches: mock.Mock,
+    ) -> None:
+        """
+        GIVEN:
+            - A root document with a version
+        WHEN:
+            - Update content task is called for the version
+        THEN:
+            - The version's content is updated
+            - The root document is indexed rather than the version
+            - Caches are cleared for both
+        """
+        sample1 = self.dirs.scratch_dir / "sample.pdf"
+        shutil.copy(
+            Path(__file__).parent
+            / "samples"
+            / "documents"
+            / "originals"
+            / "0000001.pdf",
+            sample1,
+        )
+        root = Document.objects.create(
+            title="test",
+            content="root content",
+            checksum="root",
+            mime_type="application/pdf",
+        )
+        version = Document.objects.create(
+            title="test",
+            content="my document",
+            checksum="wow",
+            filename=sample1,
+            mime_type="application/pdf",
+            root_document=root,
+            version_index=1,
+        )
+
+        tasks.update_document_content_maybe_archive_file(version.pk)
+
+        self.assertNotEqual(
+            Document.objects.get(pk=version.pk).content,
+            "my document",
+        )
+        self.assertEqual(Document.objects.get(pk=root.pk).content, "root content")
+        indexed = mock_get_backend.return_value.add_or_update.call_args.args[0]
+        self.assertEqual(indexed.pk, root.pk)
+        mock_clear_caches.assert_has_calls(
+            [mock.call(version.pk), mock.call(root.pk)],
+        )
+
 
 class TestUpdateContentRemoteOCR(DirectoriesMixin, TestCase):
     """