dtenedor commented on code in PR #48047: URL: https://github.com/apache/spark/pull/48047#discussion_r1758156279
########## sql/core/src/test/resources/sql-tests/inputs/pipe-operators.sql: ########## @@ -0,0 +1,99 @@ +-- Prepare some test data. +-------------------------- +drop table if exists t; +create table t(x int, y string) using csv; +insert into t values (0, 'abc'), (1, 'def'); + +drop table if exists other; +create table other(a int, b int) using json; +insert into other values (1, 1), (1, 2), (2, 4); + +drop table if exists st; +create table st(x int, col struct<i1:int, i2:int>) using parquet; +insert into st values (1, (2, 3)); + +-- Selection operators: positive tests. +--------------------------------------- + +-- Selecting a constant. +table t +|> select 1 as x; + +-- Selecting attributes. +table t +|> select x, y; + +-- Chained pipe SELECT operators. +table t +|> select x, y +|> select x + length(y) as z; + +-- Using the VALUES list as the source relation. +values (0), (1) tab(col) +|> select col * 2 as result; + +-- Using a table subquery as the source relation. +(select * from t union all select * from t) +|> select x + length(y) as result; + +-- Enclosing the result of a pipe SELECT operation in a table subquery. +(table t + |> select x, y + |> select x) +union all +select x from t where x < 1; + +-- Selecting struct fields. +(select col from st) +|> select col.i1; + +table st +|> select st.col.i1; + +-- Expression subqueries in the pipe operator SELECT list. +table t +|> select (select a from other where x = a limit 1) as result; Review Comment: Sure, sounds good. ########## sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/PipeSelect.scala: ########## @@ -0,0 +1,47 @@ +/* + * 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.catalyst.expressions + +import org.apache.spark.sql.catalyst.expressions.aggregate.AggregateFunction +import org.apache.spark.sql.catalyst.trees.TreePattern.{PIPE_OPERATOR_SELECT, RUNTIME_REPLACEABLE, TreePattern} +import org.apache.spark.sql.errors.QueryCompilationErrors + +/** + * Represents a SELECT clause when used with the |> SQL pipe operator. + * We use this to make sure that no aggregate functions exist in the SELECT expressions. + */ +case class PipeSelect(child: Expression) + extends UnaryExpression with RuntimeReplaceable { + final override val nodePatterns: Seq[TreePattern] = Seq(PIPE_OPERATOR_SELECT, RUNTIME_REPLACEABLE) + override def withNewChildInternal(newChild: Expression): Expression = PipeSelect(newChild) + override def replacement: Expression = { Review Comment: Good idea, this is done ########## sql/core/src/test/scala/org/apache/spark/sql/execution/SparkSqlParserSuite.scala: ########## @@ -880,4 +880,13 @@ class SparkSqlParserSuite extends AnalysisTest with SharedSparkSession { parser.parsePlan("SELECT\u30001") // Unicode ideographic space } // scalastyle:on + + test("Operator pipe SQL syntax") { + withSQLConf(SQLConf.OPERATOR_PIPE_SYNTAX_ENABLED.key -> "true") { + // Basic selection. Review Comment: Sounds good, I added some checks. I don't want to compare all the parts of the plan because it's going to be a bit tedious and brittle, but I checked that the essential operators are there :) ########## sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/parser/AstBuilder.scala: ########## @@ -5711,6 +5711,47 @@ class AstBuilder extends DataTypeAstBuilder visitSetVariableImpl(ctx.query(), ctx.multipartIdentifierList(), ctx.assignmentList()) } + override def visitOperatorPipeStatement(ctx: OperatorPipeStatementContext): LogicalPlan = { + visitOperatorPipeRightSide(ctx.operatorPipeRightSide(), plan(ctx.left)) + } + + private def visitOperatorPipeRightSide( + ctx: OperatorPipeRightSideContext, left: LogicalPlan): LogicalPlan = { + if (!SQLConf.get.getConf(SQLConf.OPERATOR_PIPE_SYNTAX_ENABLED)) { + operationNotAllowed("Operator pipe SQL syntax using |>", ctx) + } + Option(ctx.selectClause).map { c => + def updateProject(p: Project): Project = { + val newProjectList: Seq[NamedExpression] = p.projectList.map { + case a: Alias => + a.withNewChildren(Seq(PipeSelect(a.child))) + .asInstanceOf[NamedExpression] Review Comment: Done ########## sql/catalyst/src/main/scala/org/apache/spark/sql/internal/SQLConf.scala: ########## @@ -4989,6 +4989,15 @@ object SQLConf { .stringConf .createWithDefault("versionAsOf") + val OPERATOR_PIPE_SYNTAX_ENABLED = + buildConf("spark.sql.operatorPipeSyntaxEnabled") + .doc("If true, enable operator pipe syntax for Apache Spark SQL. This uses the operator " + + "pipe marker |> to indicate separation between clauses of SQL in a manner that describes " + + "the sequence of steps that the query performs in a composable fashion.") + .version("4.0.0") + .booleanConf + .createWithDefault(false) Review Comment: Sure, this makes tests simpler too. Done. -- 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]
