xinrong-meng commented on code in PR #49424: URL: https://github.com/apache/spark/pull/49424#discussion_r1936127710
########## python/pyspark/sql/connect/table_arg.py: ########## @@ -0,0 +1,101 @@ +# +# 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 typing import ( + Iterable, + TYPE_CHECKING, + Union, + Sequence, + List, + Tuple, + cast, +) + +import pyspark.sql.connect.proto as proto +from pyspark.sql.column import Column +from pyspark.sql.connect.expressions import SubqueryExpression, SortOrder +from pyspark.sql.connect.functions import builtin as F +from pyspark.sql.table_arg import TableArg as ParentTableArg + +from pyspark.errors import PySparkValueError + +if TYPE_CHECKING: + from pyspark.sql._typing import ColumnOrName + from pyspark.sql.connect.client import SparkConnectClient + + +def _to_cols(cols: Tuple[Union["ColumnOrName", Sequence["ColumnOrName"]], ...]) -> List[Column]: + if len(cols) == 1 and isinstance(cols[0], list): + cols = cols[0] # type: ignore[assignment] + return [F._to_col(c) for c in cast(Iterable["ColumnOrName"], cols)] + + +class TableArg(ParentTableArg): Review Comment: Removed thanks ########## python/pyspark/sql/connect/table_arg.py: ########## @@ -0,0 +1,101 @@ +# +# 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 typing import ( + Iterable, + TYPE_CHECKING, + Union, + Sequence, + List, + Tuple, + cast, +) + +import pyspark.sql.connect.proto as proto +from pyspark.sql.column import Column +from pyspark.sql.connect.expressions import SubqueryExpression, SortOrder +from pyspark.sql.connect.functions import builtin as F +from pyspark.sql.table_arg import TableArg as ParentTableArg + +from pyspark.errors import PySparkValueError + +if TYPE_CHECKING: + from pyspark.sql._typing import ColumnOrName + from pyspark.sql.connect.client import SparkConnectClient + + +def _to_cols(cols: Tuple[Union["ColumnOrName", Sequence["ColumnOrName"]], ...]) -> List[Column]: + if len(cols) == 1 and isinstance(cols[0], list): + cols = cols[0] # type: ignore[assignment] + return [F._to_col(c) for c in cast(Iterable["ColumnOrName"], cols)] + + +class TableArg(ParentTableArg): + def __init__(self, subquery_expr: SubqueryExpression): + self._subquery_expr = subquery_expr + + def _is_partitioned(self) -> bool: + """Checks if partitioning is already applied.""" + return ( + bool(self._subquery_expr._partition_spec) or self._subquery_expr._with_single_partition + ) + + def partitionBy(self, *cols: "ColumnOrName") -> "TableArg": + if self._is_partitioned(): + raise PySparkValueError( Review Comment: Changed to pyspark.errors.IllegalArgumentException, that's good to know! -- 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: reviews-unsubscr...@spark.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org
