Remove Chinese comments and fix function arguments errors (#12052)

### What problem does this PR solve?

As title

### Type of change

- [x] Refactoring

Signed-off-by: Jin Hai <haijin.chn@gmail.com>

api/utils/api_utils.py

@@ -163,6 +163,7 @@ def validate_request(*args, **kwargs):
             if error_arguments:
                 error_string += "required argument values: {}".format(",".join(["{}={}".format(a[0], a[1]) for a in error_arguments]))
             return error_string
+        return None
 
     def wrapper(func):
         @wraps(func)
@@ -409,7 +410,7 @@ def get_parser_config(chunk_method, parser_config):
     if default_config is None:
         return deep_merge(base_defaults, parser_config)
 
-    # Ensure raptor and graphrag fields have default values if not provided
+    # Ensure raptor and graph_rag fields have default values if not provided
     merged_config = deep_merge(base_defaults, default_config)
     merged_config = deep_merge(merged_config, parser_config)
 

common/data_source/confluence_connector.py

@@ -186,7 +186,7 @@ class OnyxConfluence:
         # between the db and redis everywhere the credentials might be updated
         new_credential_str = json.dumps(new_credentials)
         self.redis_client.set(
-            self.credential_key, new_credential_str, nx=True, ex=self.CREDENTIAL_TTL
+            self.credential_key, new_credential_str, exp=self.CREDENTIAL_TTL
         )
         self._credentials_provider.set_credentials(new_credentials)
 
@@ -1599,8 +1599,8 @@ class ConfluenceConnector(
                 semantic_identifier=semantic_identifier,
                 extension=".html",  # Confluence pages are HTML
                 blob=page_content.encode("utf-8"),  # Encode page content as bytes
-                size_bytes=len(page_content.encode("utf-8")),  # Calculate size in bytes
                 doc_updated_at=datetime_from_string(page["version"]["when"]),
+                size_bytes=len(page_content.encode("utf-8")),  # Calculate size in bytes
                 primary_owners=primary_owners if primary_owners else None,
                 metadata=metadata if metadata else None,
             )

common/data_source/models.py

@@ -94,6 +94,7 @@ class Document(BaseModel):
     blob: bytes
     doc_updated_at: datetime
     size_bytes: int
+    primary_owners: list
     metadata: Optional[dict[str, Any]] = None
 
 

common/data_source/slack_connector.py

@@ -167,7 +167,6 @@ def get_latest_message_time(thread: ThreadType) -> datetime:
 
 
 def _build_doc_id(channel_id: str, thread_ts: str) -> str:
-    """构建文档ID"""
     return f"{channel_id}__{thread_ts}"
 
 
@@ -179,7 +178,6 @@ def thread_to_doc(
     user_cache: dict[str, BasicExpertInfo | None],
     channel_access: Any | None,
 ) -> Document:
-    """将线程转换为文档"""
     channel_id = channel["id"]
 
     initial_sender_expert_info = expert_info_from_slack_id(
@@ -237,7 +235,6 @@ def filter_channels(
     channels_to_connect: list[str] | None,
     regex_enabled: bool,
 ) -> list[ChannelType]:
-    """过滤频道"""
     if not channels_to_connect:
         return all_channels
 
@@ -381,7 +378,6 @@ def _process_message(
         [MessageType], SlackMessageFilterReason | None
     ] = default_msg_filter,
 ) -> ProcessedSlackMessage:
-    """处理消息"""
     thread_ts = message.get("thread_ts")
     thread_or_message_ts = thread_ts or message["ts"]
     try:
@@ -536,7 +532,6 @@ class SlackConnector(
         end: SecondsSinceUnixEpoch | None = None,
         callback: Any = None,
     ) -> GenerateSlimDocumentOutput:
-        """获取所有简化文档（带权限同步）"""
         if self.client is None:
             raise ConnectorMissingCredentialError("Slack")