fix(rdbms): use brackets around field names to preserve distinction after chunking (#13010)

Fix RDBMS field separation after chunking by wrapping field names in
brackets (【field】: value). This ensures fields remain distinguishable
even when TxtParser strips newline delimiters during chunk merging.

Closes  #13001

Co-authored-by: mkdev11 <YOUR_GITHUB_ID+MkDev11@users.noreply.github.com>
This commit is contained in:
MkDev11
2026-02-05 22:44:58 -08:00
committed by GitHub
parent 5333e764fc
commit 13a6545e48

View File

@ -204,7 +204,9 @@ class RDBMSConnector(LoadConnector, PollConnector):
value = row_dict[col]
if isinstance(value, (dict, list)):
value = json.dumps(value, ensure_ascii=False)
content_parts.append(f"{col}: {value}")
# Use brackets around field name to ensure it's distinguishable
# after chunking (TxtParser strips \n delimiters during merge)
content_parts.append(f"{col}】: {value}")
content = "\n".join(content_parts)