ueshin commented on code in PR #49055: URL: https://github.com/apache/spark/pull/49055#discussion_r1887723053
########## sql/core/src/main/scala/org/apache/spark/sql/TableArg.scala: ########## @@ -0,0 +1,68 @@ +/* + * 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. + */ + +package org.apache.spark.sql + +import org.apache.spark.sql.catalyst.expressions.{Ascending, Expression, FunctionTableSubqueryArgumentExpression, SortOrder} + + +class TableArg( + val expression: FunctionTableSubqueryArgumentExpression, + private val sparkSession: SparkSession +) extends UDTFArgument { + import sparkSession.toRichColumn + + def partitionBy(cols: Seq[Column]): TableArg = { + if (expression.withSinglePartition) { + throw new IllegalArgumentException( + "Cannot call partitionBy() after withSinglePartition() has been called." + ) + } + val partitionByExpressions = cols.map(_.expr) + new TableArg( + expression.copy( + partitionByExpressions = partitionByExpressions, withSinglePartition = false), + sparkSession + ) + } + + def orderBy(cols: Seq[Column]): TableArg = { + val orderByExpressions = cols.map { col => + col.expr match { + case sortOrder: SortOrder => sortOrder + case expr: Expression => SortOrder(expr, Ascending) + case other => + throw new IllegalArgumentException( + s"Unsupported expression type in orderBy: ${other.getClass.getName}" + ) + } Review Comment: In which case will this exception be thrown? ########## sql/core/src/main/scala/org/apache/spark/sql/TableArg.scala: ########## @@ -0,0 +1,68 @@ +/* + * 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. + */ + +package org.apache.spark.sql + +import org.apache.spark.sql.catalyst.expressions.{Ascending, Expression, FunctionTableSubqueryArgumentExpression, SortOrder} + + +class TableArg( + val expression: FunctionTableSubqueryArgumentExpression, + private val sparkSession: SparkSession +) extends UDTFArgument { + import sparkSession.toRichColumn + + def partitionBy(cols: Seq[Column]): TableArg = { + if (expression.withSinglePartition) { + throw new IllegalArgumentException( + "Cannot call partitionBy() after withSinglePartition() has been called." + ) + } + val partitionByExpressions = cols.map(_.expr) + new TableArg( + expression.copy( + partitionByExpressions = partitionByExpressions, withSinglePartition = false), + sparkSession + ) + } + + def orderBy(cols: Seq[Column]): TableArg = { + val orderByExpressions = cols.map { col => + col.expr match { Review Comment: Can we do this with `col.node`? ########## python/pyspark/sql/udtf_argument.py: ########## @@ -0,0 +1,27 @@ +# +# 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. +# + + +class UDTFArgument: Review Comment: How about `TVFArgument`, `TableFunctionArgument` or `TableValuedFunctionArgument`? In SQL, this is not only for UDTF but TVFs in general, although currently there is no builtin tvf. cc @dtenedor @allisonwang-db ########## sql/core/src/main/scala/org/apache/spark/sql/TableArg.scala: ########## @@ -0,0 +1,68 @@ +/* + * 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. + */ + +package org.apache.spark.sql + +import org.apache.spark.sql.catalyst.expressions.{Ascending, Expression, FunctionTableSubqueryArgumentExpression, SortOrder} + + +class TableArg( + val expression: FunctionTableSubqueryArgumentExpression, + private val sparkSession: SparkSession +) extends UDTFArgument { + import sparkSession.toRichColumn + + def partitionBy(cols: Seq[Column]): TableArg = { + if (expression.withSinglePartition) { + throw new IllegalArgumentException( + "Cannot call partitionBy() after withSinglePartition() has been called." + ) + } + val partitionByExpressions = cols.map(_.expr) + new TableArg( + expression.copy( + partitionByExpressions = partitionByExpressions, withSinglePartition = false), + sparkSession + ) + } + + def orderBy(cols: Seq[Column]): TableArg = { + val orderByExpressions = cols.map { col => + col.expr match { + case sortOrder: SortOrder => sortOrder + case expr: Expression => SortOrder(expr, Ascending) + case other => + throw new IllegalArgumentException( + s"Unsupported expression type in orderBy: ${other.getClass.getName}" + ) + } + } + new TableArg(expression.copy(orderByExpressions = orderByExpressions), Review Comment: What happens if only `.orderBy` is called without `partitionBy` or `withSinglePartition`? -- 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]
