zhengruifeng commented on code in PR #48603: URL: https://github.com/apache/spark/pull/48603#discussion_r1811643973
########## python/pyspark/sql/tvf.py: ########## @@ -0,0 +1,714 @@ +# +# 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 Optional, TYPE_CHECKING + +from pyspark.errors import PySparkValueError +from pyspark.sql.dataframe import DataFrame +from pyspark.sql.session import SparkSession + +if TYPE_CHECKING: + from pyspark.sql._typing import ColumnOrName + +__all__ = ["TableValuedFunction"] + + +class TableValuedFunction: + """ + Interface for invoking table-valued functions in Spark SQL. + """ + + def __init__(self, sparkSession: SparkSession): + self._sparkSession = sparkSession + + def range( + self, + start: int, + end: Optional[int] = None, + step: int = 1, + numPartitions: Optional[int] = None, + ) -> DataFrame: + """ + Create a :class:`DataFrame` with single :class:`pyspark.sql.types.LongType` column named + ``id``, containing elements in a range from ``start`` to ``end`` (exclusive) with + step value ``step``. + + .. versionadded:: 4.0.0 + + Parameters + ---------- + start : int + the start value + end : int, optional + the end value (exclusive) + step : int, optional + the incremental step (default: 1) + numPartitions : int, optional + the number of partitions of the DataFrame + + Returns + ------- + :class:`DataFrame` + + Examples + -------- + >>> spark.tvf.range(1, 7, 2).show() + +---+ + | id| + +---+ + | 1| + | 3| + | 5| + +---+ + + If only one argument is specified, it will be used as the end value. + + >>> spark.tvf.range(3).show() + +---+ + | id| + +---+ + | 0| + | 1| + | 2| + +---+ + """ + return self._sparkSession.range(start, end, step, numPartitions) + + def explode(self, collection: "ColumnOrName") -> DataFrame: Review Comment: qq: how could `collection` support a column name? should it be `Column`? ########## sql/connect/common/src/main/protobuf/spark/connect/relations.proto: ########## @@ -902,6 +903,14 @@ message Transpose { repeated Expression index_columns = 2; } +message UnresolvedTableValuedFunction { Review Comment: I guess we can deprecate message `Relation Range` after this PR. ########## python/pyspark/sql/tvf.py: ########## @@ -0,0 +1,714 @@ +# +# 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 Optional, TYPE_CHECKING + +from pyspark.errors import PySparkValueError +from pyspark.sql.dataframe import DataFrame +from pyspark.sql.session import SparkSession + +if TYPE_CHECKING: + from pyspark.sql._typing import ColumnOrName + +__all__ = ["TableValuedFunction"] + + +class TableValuedFunction: + """ + Interface for invoking table-valued functions in Spark SQL. + """ + + def __init__(self, sparkSession: SparkSession): + self._sparkSession = sparkSession + + def range( Review Comment: nit: we may make `spark.range` an alias for this new implementaion. ########## python/pyspark/sql/tvf.py: ########## @@ -0,0 +1,714 @@ +# +# 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 Optional, TYPE_CHECKING + +from pyspark.errors import PySparkValueError +from pyspark.sql.dataframe import DataFrame +from pyspark.sql.session import SparkSession + +if TYPE_CHECKING: + from pyspark.sql._typing import ColumnOrName + +__all__ = ["TableValuedFunction"] + + +class TableValuedFunction: + """ + Interface for invoking table-valued functions in Spark SQL. + """ + + def __init__(self, sparkSession: SparkSession): + self._sparkSession = sparkSession + + def range( + self, + start: int, + end: Optional[int] = None, + step: int = 1, + numPartitions: Optional[int] = None, + ) -> DataFrame: + """ + Create a :class:`DataFrame` with single :class:`pyspark.sql.types.LongType` column named + ``id``, containing elements in a range from ``start`` to ``end`` (exclusive) with + step value ``step``. + + .. versionadded:: 4.0.0 + + Parameters + ---------- + start : int + the start value + end : int, optional + the end value (exclusive) + step : int, optional + the incremental step (default: 1) + numPartitions : int, optional + the number of partitions of the DataFrame + + Returns + ------- + :class:`DataFrame` + + Examples + -------- + >>> spark.tvf.range(1, 7, 2).show() + +---+ + | id| + +---+ + | 1| + | 3| + | 5| + +---+ + + If only one argument is specified, it will be used as the end value. + + >>> spark.tvf.range(3).show() + +---+ + | id| + +---+ + | 0| + | 1| + | 2| + +---+ + """ + return self._sparkSession.range(start, end, step, numPartitions) + + def explode(self, collection: "ColumnOrName") -> DataFrame: Review Comment: or shall we add some examples with column names? -- 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]
