sryza commented on code in PR #53024: URL: https://github.com/apache/spark/pull/53024#discussion_r2520066341
########## python/pyspark/pipelines/add_pipeline_analysis_context.py: ########## @@ -0,0 +1,43 @@ +# +# Licensed to the Apache Software Foundation (ASF) under one or more +# contributor license agreements. See the NOTICE file distributed with +# this work for additional information regarding copyright ownership. +# The ASF licenses this file to You under the Apache License, Version 2.0 +# (the "License"); you may not use this file except in compliance with +# the License. You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. +# +from contextlib import contextmanager +from typing import Generator +from pyspark.sql import SparkSession + +@contextmanager +def add_pipeline_analysis_context(spark: SparkSession, dataflow_graph_id: str, flow_name: str) -> Generator[None, None, None]: + """ + Context manager that add PipelineAnalysisContext extension to the user context + used for pipeline specific analysis. + """ + extension_id = None + try: + import pyspark.sql.connect.proto as pb2 + from google.protobuf import any_pb2 + + analysis_context = pb2.PipelineAnalysisContext( + dataflow_graph_id=dataflow_graph_id, + flow_name=flow_name + ) + + extension = any_pb2.Any() + extension.Pack(analysis_context) + + extension_id = spark.addThreadlocalUserContextExtension(extension) Review Comment: See my comment here: https://github.com/apache/spark/pull/53020#discussion_r2519895195 ########## python/pyspark/pipelines/add_pipeline_analysis_context.py: ########## @@ -0,0 +1,43 @@ +# +# Licensed to the Apache Software Foundation (ASF) under one or more +# contributor license agreements. See the NOTICE file distributed with +# this work for additional information regarding copyright ownership. +# The ASF licenses this file to You under the Apache License, Version 2.0 +# (the "License"); you may not use this file except in compliance with +# the License. You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. +# +from contextlib import contextmanager +from typing import Generator +from pyspark.sql import SparkSession + +@contextmanager +def add_pipeline_analysis_context(spark: SparkSession, dataflow_graph_id: str, flow_name: str) -> Generator[None, None, None]: Review Comment: Probably need to run dev/reformat-python to get this line to acceptable length -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
