Refa: Implement centralized file name length limit using FILE_NAME_LEN_LIMIT constant (#8318)

### What problem does this PR solve?

- Replace hardcoded 255-byte file name length checks with
FILE_NAME_LEN_LIMIT constant
- Update error messages to show the actual limit value
- #8290

### Type of change

- [x] Refactoring

Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>

api/apps/document_app.py

@@ -23,7 +23,7 @@ from flask import request
 from flask_login import current_user, login_required
 
 from api import settings
-from api.constants import IMG_BASE64_PREFIX
+from api.constants import FILE_NAME_LEN_LIMIT, IMG_BASE64_PREFIX
 from api.db import VALID_FILE_TYPES, VALID_TASK_STATUS, FileSource, FileType, ParserType, TaskStatus
 from api.db.db_models import File, Task
 from api.db.services import duplicate_name
@@ -61,8 +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:
+        if len(file_obj.filename.encode("utf-8")) > FILE_NAME_LEN_LIMIT:
-            return get_json_result(data=False, message="File name must be 255 bytes or less.", code=settings.RetCode.ARGUMENT_ERROR)
+            return get_json_result(data=False, message=f"File name must be {FILE_NAME_LEN_LIMIT} bytes or less.", code=settings.RetCode.ARGUMENT_ERROR)
 
     e, kb = KnowledgebaseService.get_by_id(kb_id)
     if not e:
@@ -149,8 +149,9 @@ 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:
+    if len(req["name"].encode("utf-8")) > FILE_NAME_LEN_LIMIT:
-        return get_json_result(data=False, message="File name must be 255 bytes or less.", code=settings.RetCode.ARGUMENT_ERROR)
+        return get_json_result(data=False, message=f"File name must be {FILE_NAME_LEN_LIMIT} bytes or less.", code=settings.RetCode.ARGUMENT_ERROR)
+
     if req["name"].strip() == "":
         return get_json_result(data=False, message="File name can't be empty.", code=settings.RetCode.ARGUMENT_ERROR)
     req["name"] = req["name"].strip()
@@ -409,8 +410,8 @@ 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:
+        if len(req["name"].encode("utf-8")) > FILE_NAME_LEN_LIMIT:
-            return get_json_result(data=False, message="File name must be 255 bytes or less.", code=settings.RetCode.ARGUMENT_ERROR)
+            return get_json_result(data=False, message=f"File name must be {FILE_NAME_LEN_LIMIT} 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"]:

api/apps/sdk/doc.py

@@ -25,6 +25,7 @@ from peewee import OperationalError
 from pydantic import BaseModel, Field, validator
 
 from api import settings
+from api.constants import FILE_NAME_LEN_LIMIT
 from api.db import FileSource, FileType, LLMType, ParserType, TaskStatus
 from api.db.db_models import File, Task
 from api.db.services.document_service import DocumentService
@@ -129,8 +130,8 @@ 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")) > 255:
+        if len(file_obj.filename.encode("utf-8")) > FILE_NAME_LEN_LIMIT:
-            return get_result(message="File name must be 255 bytes or less.", code=settings.RetCode.ARGUMENT_ERROR)
+            return get_result(message=f"File name must be {FILE_NAME_LEN_LIMIT} bytes or less.", code=settings.RetCode.ARGUMENT_ERROR)
     """
     # total size
     total_size = 0
@@ -247,9 +248,9 @@ 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")) > 255:
+        if len(req["name"].encode("utf-8")) > FILE_NAME_LEN_LIMIT:
             return get_result(
-                message="File name must be 255 bytes or less.",
+                message=f"File name must be {FILE_NAME_LEN_LIMIT} bytes or less.",
                 code=settings.RetCode.ARGUMENT_ERROR,
             )
         if pathlib.Path(req["name"].lower()).suffix != pathlib.Path(doc.name.lower()).suffix:

api/constants.py

@@ -15,7 +15,7 @@
 
 NAME_LENGTH_LIMIT = 2**10
 
-IMG_BASE64_PREFIX = 'data:image/png;base64,'
+IMG_BASE64_PREFIX = "data:image/png;base64,"
 
 SERVICE_CONF = "service_conf.yaml"
 
@@ -25,4 +25,4 @@ REQUEST_WAIT_SEC = 2
 REQUEST_MAX_WAIT_SEC = 300
 
 DATASET_NAME_LIMIT = 128
-FILE_NAME_LEN_LIMIT = 256
+FILE_NAME_LEN_LIMIT = 255

api/db/services/file_service.py

@@ -21,6 +21,7 @@ from concurrent.futures import ThreadPoolExecutor
 from flask_login import current_user
 from peewee import fn
 
+from api.constants import FILE_NAME_LEN_LIMIT
 from api.db import KNOWLEDGEBASE_FOLDER_NAME, FileSource, FileType, ParserType
 from api.db.db_models import DB, Document, File, File2Document, Knowledgebase
 from api.db.services import duplicate_name
@@ -30,7 +31,7 @@ from api.db.services.file2document_service import File2DocumentService
 from api.utils import get_uuid
 from api.utils.file_utils import filename_type, read_potential_broken_pdf, thumbnail_img
 from rag.utils.storage_factory import STORAGE_IMPL
-from api.constants import FILE_NAME_LEN_LIMIT
+
 
 class FileService(CommonService):
     # Service class for managing file operations and storage
@@ -412,8 +413,8 @@ class FileService(CommonService):
                 MAX_FILE_NUM_PER_USER = int(os.environ.get("MAX_FILE_NUM_PER_USER", 0))
                 if MAX_FILE_NUM_PER_USER > 0 and DocumentService.get_doc_count(kb.tenant_id) >= MAX_FILE_NUM_PER_USER:
                     raise RuntimeError("Exceed the maximum file number of a free user!")
-                if len(file.filename.encode("utf-8")) >= FILE_NAME_LEN_LIMIT:
+                if len(file.filename.encode("utf-8")) > FILE_NAME_LEN_LIMIT:
-                    raise RuntimeError("Exceed the maximum length of file name!")
+                    raise RuntimeError(f"File name must be {FILE_NAME_LEN_LIMIT} bytes or less.")
 
                 filename = duplicate_name(DocumentService.query, name=file.filename, kb_id=kb.id)
                 filetype = filename_type(filename)
@@ -492,4 +493,3 @@ class FileService(CommonService):
         if re.search(r"\.(eml)$", filename):
             return ParserType.EMAIL.value
         return default
-