Fix: validate PDF output doc indexes in bulk edit (#14083)

src/documents/bulk_edit.py

@@ -899,17 +899,26 @@ def edit_pdf(
     pdf_docs: list[pikepdf.Pdf] = []
 
     try:
+        if not operations:
+            raise ValueError("Output document index is out of bounds")
+
+        max_idx = max(op.get("doc", 0) for op in operations)
+        if update_document and max_idx > 0:
+            logger.error(
+                "Update requested but multiple output documents specified",
+            )
+            raise ValueError("Multiple output documents specified")
+
+        if any(
+            op.get("doc", 0) < 0 or op.get("doc", 0) >= len(operations)
+            for op in operations
+        ):
+            raise ValueError("Output document index is out of bounds")
+
         with pikepdf.open(pair.source_doc.source_path) as src:
             # prepare output documents
-            max_idx = max(op.get("doc", 0) for op in operations)
             pdf_docs = [pikepdf.new() for _ in range(max_idx + 1)]
 
-            if update_document and len(pdf_docs) > 1:
-                logger.error(
-                    "Update requested but multiple output documents specified",
-                )
-                raise ValueError("Multiple output documents specified")
-
             for op in operations:
                 dst = pdf_docs[op.get("doc", 0)]
                 page = src.pages[op["page"] - 1]

src/documents/serialisers.py

@@ -1750,7 +1750,7 @@ class MergeDocumentsAsVersionsSerializer(DocumentListSerializer):
 
 
 class EditPdfDocumentsSerializer(DocumentListSerializer, SourceModeValidationMixin):
-    operations = serializers.ListField(required=True)
+    operations = serializers.ListField(required=True, allow_empty=False)
     delete_original = serializers.BooleanField(required=False, default=False)
     update_document = serializers.BooleanField(required=False, default=False)
     include_metadata = serializers.BooleanField(required=False, default=True)
@@ -1788,6 +1788,12 @@ class EditPdfDocumentsSerializer(DocumentListSerializer, SourceModeValidationMix
                     "update_document only allowed with a single output document",
                 )
 
+        if any(
+            op.get("doc", 0) < 0 or op.get("doc", 0) >= len(operations)
+            for op in operations
+        ):
+            raise serializers.ValidationError("doc index is out of bounds")
+
         doc = Document.objects.get(id=documents[0])
         if doc.page_count:
             for op in operations:
@@ -2124,6 +2130,8 @@ class BulkEditSerializer(
             raise serializers.ValidationError("operations not specified")
         if not isinstance(parameters["operations"], list):
             raise serializers.ValidationError("operations must be a list")
+        if not parameters["operations"]:
+            raise serializers.ValidationError("operations must not be empty")
         for op in parameters["operations"]:
             if not isinstance(op, dict):
                 raise serializers.ValidationError("invalid operation entry")
@@ -2151,6 +2159,12 @@ class BulkEditSerializer(
                     "update_document only allowed with a single output document",
                 )
 
+        if any(
+            op.get("doc", 0) < 0 or op.get("doc", 0) >= len(parameters["operations"])
+            for op in parameters["operations"]
+        ):
+            raise serializers.ValidationError("doc index is out of bounds")
+
         doc = Document.objects.get(id=document_id)
         # doc existence is already validated
         if doc.page_count:

src/documents/tests/test_api_bulk_edit.py

@@ -1649,6 +1649,40 @@ class TestBulkEditAPI(DirectoriesMixin, APITestCase):
 
         self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
 
+    def test_legacy_bulk_edit_rejects_out_of_bounds_pdf_doc_index(self) -> None:
+        response = self.client.post(
+            "/api/documents/bulk_edit/",
+            json.dumps(
+                {
+                    "documents": [self.doc2.id],
+                    "method": "edit_pdf",
+                    "parameters": {
+                        "operations": [{"page": 1, "doc": 2**32}],
+                    },
+                },
+            ),
+            content_type="application/json",
+        )
+
+        self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
+        self.assertIn(b"doc index is out of bounds", response.content)
+
+    def test_legacy_bulk_edit_rejects_empty_pdf_operations(self) -> None:
+        response = self.client.post(
+            "/api/documents/bulk_edit/",
+            json.dumps(
+                {
+                    "documents": [self.doc2.id],
+                    "method": "edit_pdf",
+                    "parameters": {"operations": []},
+                },
+            ),
+            content_type="application/json",
+        )
+
+        self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
+        self.assertIn(b"operations must not be empty", response.content)
+
     @mock.patch("documents.views.bulk_edit.edit_pdf")
     def test_edit_pdf(self, m) -> None:
         self.setup_mock(m, "edit_pdf")
@@ -1699,6 +1733,13 @@ class TestBulkEditAPI(DirectoriesMixin, APITestCase):
         self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
         self.assertIn(b"Expected a list of items", response.content)
 
+        response = self.client.post(
+            "/api/documents/edit_pdf/",
+            {"documents": [self.doc2.id], "operations": []},
+            format="json",
+        )
+        self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
+
         response = self.client.post(
             "/api/documents/edit_pdf/",
             json.dumps(
@@ -1751,6 +1792,21 @@ class TestBulkEditAPI(DirectoriesMixin, APITestCase):
         self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
         self.assertIn(b"doc must be an integer", response.content)
 
+        for doc_index in (-1, 2**32):
+            with self.subTest(doc_index=doc_index):
+                response = self.client.post(
+                    "/api/documents/edit_pdf/",
+                    json.dumps(
+                        {
+                            "documents": [self.doc2.id],
+                            "operations": [{"page": 1, "doc": doc_index}],
+                        },
+                    ),
+                    content_type="application/json",
+                )
+                self.assertEqual(response.status_code, status.HTTP_400_BAD_REQUEST)
+                self.assertIn(b"doc index is out of bounds", response.content)
+
         response = self.client.post(
             "/api/documents/edit_pdf/",
             json.dumps(

src/documents/tests/test_bulk_edit.py

@@ -1642,6 +1642,16 @@ class TestPDFActions(DirectoriesMixin, TestCase):
         mock_group.assert_not_called()
         mock_consume_file.assert_not_called()
 
+    @mock.patch("pikepdf.open")
+    def test_edit_pdf_rejects_invalid_operations(self, mock_open) -> None:
+        for operations in ([], [{"page": 1, "doc": 2**32}]):
+            with self.subTest(operations=operations):
+                with self.assertLogs("paperless.bulk_edit", level="ERROR"):
+                    with self.assertRaisesRegex(ValueError, "index is out of bounds"):
+                        bulk_edit.edit_pdf([self.doc2.id], operations)
+
+        mock_open.assert_not_called()
+
     @mock.patch("documents.bulk_edit.update_document_content_maybe_archive_file.delay")
     @mock.patch("documents.tasks.consume_file.apply_async")
     @mock.patch("documents.bulk_edit.tempfile.mkdtemp")