From ad28af4f4f96fc2df8d5f6943f298865f5eaf537 Mon Sep 17 00:00:00 2001 From: Mayur Singal <39544459+ulixius9@users.noreply.github.com> Date: Fri, 22 Mar 2024 12:13:26 +0530 Subject: [PATCH] MINOR: Fix sample data upload - binary data error (#15659) --- .../src/metadata/profiler/processor/sample_data_handler.py | 3 +++ 1 file changed, 3 insertions(+) diff --git a/ingestion/src/metadata/profiler/processor/sample_data_handler.py b/ingestion/src/metadata/profiler/processor/sample_data_handler.py index a7e906de9f0..f029d2836c9 100644 --- a/ingestion/src/metadata/profiler/processor/sample_data_handler.py +++ b/ingestion/src/metadata/profiler/processor/sample_data_handler.py @@ -17,6 +17,8 @@ from datetime import datetime from functools import singledispatch from io import BytesIO +from pydantic.json import ENCODERS_BY_TYPE + from metadata.clients.aws_client import AWSClient from metadata.generated.schema.entity.data.table import Table, TableData from metadata.generated.schema.entity.services.connections.connectionBasicType import ( @@ -81,6 +83,7 @@ def upload_sample_data(data: TableData, profiler_interface: ProfilerInterface) - sample_storage_config: DataStorageConfig = profiler_interface.storage_config if not sample_storage_config: return + ENCODERS_BY_TYPE[bytes] = lambda v: v.decode("utf-8", "ignore") deserialized_data = json.loads(data.json()) df = pd.DataFrame( data=deserialized_data.get("rows", []),