Fix: Enforce 255-byte filename limit (#8290)

### What problem does this PR solve?

- Add filename length validation (<=255 bytes) for document
upload/rename in both HTTP and SDK APIs
- Update error messages for consistency
- Fix comparison operator in SDK from '>=' to '>' for filename length
check

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)

api/apps/document_app.py

@@ -61,6 +61,8 @@ def upload():
     for file_obj in file_objs:
         if file_obj.filename == "":
             return get_json_result(data=False, message="No file selected!", code=settings.RetCode.ARGUMENT_ERROR)
+        if len(file_obj.filename.encode("utf-8")) > 255:
+            return get_json_result(data=False, message="File name must be 255 bytes or less.", code=settings.RetCode.ARGUMENT_ERROR)
 
     e, kb = KnowledgebaseService.get_by_id(kb_id)
     if not e:
@@ -147,6 +149,8 @@ def create():
     kb_id = req["kb_id"]
     if not kb_id:
         return get_json_result(data=False, message='Lack of "KB ID"', code=settings.RetCode.ARGUMENT_ERROR)
+    if len(req["name"].encode("utf-8")) > 255:
+        return get_json_result(data=False, message="File name must be 255 bytes or less.", code=settings.RetCode.ARGUMENT_ERROR)
 
     try:
         e, kb = KnowledgebaseService.get_by_id(kb_id)
@@ -402,6 +406,9 @@ def rename():
             return get_data_error_result(message="Document not found!")
         if pathlib.Path(req["name"].lower()).suffix != pathlib.Path(doc.name.lower()).suffix:
             return get_json_result(data=False, message="The extension of file can't be changed", code=settings.RetCode.ARGUMENT_ERROR)
+        if len(req["name"].encode("utf-8")) > 255:
+            return get_json_result(data=False, message="File name must be 255 bytes or less.", code=settings.RetCode.ARGUMENT_ERROR)
+
         for d in DocumentService.query(name=req["name"], kb_id=doc.kb_id):
             if d.name == req["name"]:
                 return get_data_error_result(message="Duplicated document name in the same knowledgebase.")

api/apps/sdk/doc.py

@@ -129,8 +129,8 @@ def upload(dataset_id, tenant_id):
     for file_obj in file_objs:
         if file_obj.filename == "":
             return get_result(message="No file selected!", code=settings.RetCode.ARGUMENT_ERROR)
-        if len(file_obj.filename.encode("utf-8")) >= 128:
-            return get_result(message="File name should be less than 128 bytes.", code=settings.RetCode.ARGUMENT_ERROR)
+        if len(file_obj.filename.encode("utf-8")) > 255:
+            return get_result(message="File name must be 255 bytes or less.", code=settings.RetCode.ARGUMENT_ERROR)
     """
     # total size
     total_size = 0
@@ -247,9 +247,9 @@ def update_doc(tenant_id, dataset_id, document_id):
         DocumentService.update_meta_fields(document_id, req["meta_fields"])
 
     if "name" in req and req["name"] != doc.name:
-        if len(req["name"].encode("utf-8")) >= 128:
+        if len(req["name"].encode("utf-8")) > 255:
             return get_result(
-                message="The name should be less than 128 bytes.",
+                message="File name must be 255 bytes or less.",
                 code=settings.RetCode.ARGUMENT_ERROR,
             )
         if pathlib.Path(req["name"].lower()).suffix != pathlib.Path(doc.name.lower()).suffix:

test/configs.py

@@ -31,6 +31,6 @@ X8f7fp9c7vUsfOCkM+gHY3PadG+QHa7KI7mzTKgUTZImK6BZtfRBATDTthEUbbaTewY4H0MnWiCeeDhc
 
 INVALID_API_TOKEN = "invalid_key_123"
 DATASET_NAME_LIMIT = 128
-DOCUMENT_NAME_LIMIT = 128
+DOCUMENT_NAME_LIMIT = 255
 CHAT_ASSISTANT_NAME_LIMIT = 255
 SESSION_WITH_CHAT_NAME_LIMIT = 255

test/testcases/test_http_api/test_file_management_within_dataset/test_update_document.py

@@ -47,9 +47,9 @@ class TestDocumentsUpdated:
         [
             ("new_name.txt", 0, ""),
             (
-                f"{'a' * (DOCUMENT_NAME_LIMIT - 3)}.txt",
-                101,
-                "The name should be less than 128 bytes.",
+                f"{'a' * (DOCUMENT_NAME_LIMIT - 4)}.txt",
+                0,
+                "",
             ),
             (
                 0,

test/testcases/test_http_api/test_file_management_within_dataset/test_upload_documents.py

@@ -13,7 +13,6 @@
 #  See the License for the specific language governing permissions and
 #  limitations under the License.
 #
-
 import string
 from concurrent.futures import ThreadPoolExecutor, as_completed
 
@@ -128,13 +127,12 @@ class TestDocumentsUpload:
         assert res.json()["message"] == "No file selected!"
 
     @pytest.mark.p2
-    def test_filename_exceeds_max_length(self, HttpApiAuth, add_dataset_func, tmp_path):
+    def test_filename_max_length(self, HttpApiAuth, add_dataset_func, tmp_path):
         dataset_id = add_dataset_func
-        # filename_length = 129
-        fp = create_txt_file(tmp_path / f"{'a' * (DOCUMENT_NAME_LIMIT - 3)}.txt")
+        fp = create_txt_file(tmp_path / f"{'a' * (DOCUMENT_NAME_LIMIT - 4)}.txt")
         res = upload_documents(HttpApiAuth, dataset_id, [fp])
-        assert res["code"] == 101
-        assert res["message"] == "File name should be less than 128 bytes."
+        assert res["code"] == 0
+        assert res["data"][0]["name"] == fp.name
 
     @pytest.mark.p2
     def test_invalid_dataset_id(self, HttpApiAuth, tmp_path):

test/testcases/test_sdk_api/test_file_management_within_dataset/test_update_document.py

@@ -25,7 +25,7 @@ class TestDocumentsUpdated:
         "name, expected_message",
         [
             ("new_name.txt", ""),
-            (f"{'a' * (DOCUMENT_NAME_LIMIT - 3)}.txt", "The name should be less than 128 bytes"),
+            (f"{'a' * (DOCUMENT_NAME_LIMIT - 4)}.txt", ""),
             (0, "AttributeError"),
             (None, "AttributeError"),
             ("", "The extension of file can't be changed"),

test/testcases/test_sdk_api/test_file_management_within_dataset/test_upload_documents.py

@@ -113,16 +113,17 @@ class TestDocumentsUpload:
         assert str(excinfo.value) == "No file selected!", str(excinfo.value)
 
     @pytest.mark.p2
-    def test_filename_exceeds_max_length(self, add_dataset_func, tmp_path):
+    def test_filename_max_length(self, add_dataset_func, tmp_path):
         dataset = add_dataset_func
-        fp = create_txt_file(tmp_path / f"{'a' * (DOCUMENT_NAME_LIMIT - 3)}.txt")
+        fp = create_txt_file(tmp_path / f"{'a' * (DOCUMENT_NAME_LIMIT - 4)}.txt")
 
         with fp.open("rb") as f:
             blob = f.read()
 
-        with pytest.raises(Exception) as excinfo:
-            dataset.upload_documents([{"display_name": fp.name, "blob": blob}])
-        assert str(excinfo.value) == "File name should be less than 128 bytes.", str(excinfo.value)
+        documents = dataset.upload_documents([{"display_name": fp.name, "blob": blob}])
+        for document in documents:
+            assert document.dataset_id == dataset.id, str(document)
+            assert document.name == fp.name, str(document)
 
     @pytest.mark.p2
     def test_duplicate_files(self, add_dataset_func, tmp_path):