Skip to content

[SPARK-53812][SDP] Refactor DefineDataset and DefineFlow protos to group related properties and future-proof #52532

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
+357 −207
Open

[SPARK-53812][SDP] Refactor DefineDataset and DefineFlow protos to group related properties and future-proof #52532

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
48 changes: 27 additions & 21 deletions python/pyspark/pipelines/spark_connect_graph_element_registry.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -45,10 +45,12 @@ def __init__(self, spark: SparkSession, dataflow_graph_id: str) -> None:

def register_dataset(self, dataset: Dataset) -> None:
if isinstance(dataset, Table):
table_properties = dataset.table_properties
partition_cols = dataset.partition_cols
schema = None # TODO
format = dataset.format
table_details = pb2.PipelineCommand.DefineDataset.TableDetails(
table_properties=dataset.table_properties,
partition_cols=dataset.partition_cols,
schema=None, # TODO
format=dataset.format,
)

if isinstance(dataset, MaterializedView):
dataset_type = pb2.DatasetType.MATERIALIZED_VIEW
Expand All @@ -59,29 +61,29 @@ def register_dataset(self, dataset: Dataset) -> None:
errorClass="UNSUPPORTED_PIPELINES_DATASET_TYPE",
messageParameters={"dataset_type": type(dataset).__name__},
)

inner_command = pb2.PipelineCommand.DefineDataset(
dataflow_graph_id=self._dataflow_graph_id,
dataset_name=dataset.name,
dataset_type=dataset_type,
comment=dataset.comment,
table_details=table_details,
source_code_location=source_code_location_to_proto(dataset.source_code_location),
)
elif isinstance(dataset, TemporaryView):
table_properties = None
partition_cols = None
schema = None
format = None
dataset_type = pb2.DatasetType.TEMPORARY_VIEW
inner_command = pb2.PipelineCommand.DefineDataset(
dataflow_graph_id=self._dataflow_graph_id,
dataset_name=dataset.name,
dataset_type=dataset_type,
comment=dataset.comment,
source_code_location=source_code_location_to_proto(dataset.source_code_location),
)
else:
raise PySparkTypeError(
errorClass="UNSUPPORTED_PIPELINES_DATASET_TYPE",
messageParameters={"dataset_type": type(dataset).__name__},
)

inner_command = pb2.PipelineCommand.DefineDataset(
dataflow_graph_id=self._dataflow_graph_id,
dataset_name=dataset.name,
dataset_type=dataset_type,
comment=dataset.comment,
table_properties=table_properties,
partition_cols=partition_cols,
schema=schema,
format=format,
source_code_location=source_code_location_to_proto(dataset.source_code_location),
)
command = pb2.Command()
command.pipeline_command.define_dataset.CopyFrom(inner_command)
self._client.execute_command(command)
Expand All @@ -91,11 +93,15 @@ def register_flow(self, flow: Flow) -> None:
df = flow.func()
relation = cast(ConnectDataFrame, df)._plan.plan(self._client)

relation_flow_details = pb2.PipelineCommand.DefineFlow.WriteRelationFlowDetails(
relation=relation,
)

inner_command = pb2.PipelineCommand.DefineFlow(
dataflow_graph_id=self._dataflow_graph_id,
flow_name=flow.name,
target_dataset_name=flow.target,
relation=relation,
relation_flow_details=relation_flow_details,
sql_conf=flow.spark_conf,
source_code_location=source_code_location_to_proto(flow.source_code_location),
)
Expand Down
Loading