AngersZhuuuu commented on a change in pull request #29414:
URL: https://github.com/apache/spark/pull/29414#discussion_r469781475
##########
File path:
sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/parser/PlanParserSuite.scala
##########
@@ -1031,4 +1031,115 @@ class PlanParserSuite extends AnalysisTest {
assertEqual("select a, b from db.c;;;", table("db", "c").select('a, 'b))
assertEqual("select a, b from db.c; ;; ;", table("db", "c").select('a,
'b))
}
+
+ test("SPARK-32106: TRANSFORM plan") {
+ // verify schema less
+ assertEqual(
+ """
+ |SELECT TRANSFORM(a, b, c)
+ |USING 'cat'
+ |FROM testData
+ """.stripMargin,
+ ScriptTransformation(
+ Seq('a, 'b, 'c),
+ "cat",
+ Seq(AttributeReference("key", StringType)(),
+ AttributeReference("value", StringType)()),
+ UnresolvedRelation(TableIdentifier("testData")),
+ ScriptInputOutputSchema(List.empty, List.empty, None, None,
+ List.empty, List.empty, None, None, true))
+ )
+
+ // verify without output schema
+ assertEqual(
+ """
+ |SELECT TRANSFORM(a, b, c)
+ |USING 'cat' AS (a, b, c)
+ |FROM testData
+ """.stripMargin,
+ ScriptTransformation(
+ Seq('a, 'b, 'c),
+ "cat",
+ Seq(AttributeReference("a", StringType)(),
+ AttributeReference("b", StringType)(),
+ AttributeReference("c", StringType)()),
+ UnresolvedRelation(TableIdentifier("testData")),
+ ScriptInputOutputSchema(List.empty, List.empty, None, None,
+ List.empty, List.empty, None, None, false)))
+
+ // verify with output schema
+ assertEqual(
+ """
+ |SELECT TRANSFORM(a, b, c)
+ |USING 'cat' AS (a int, b string, c long)
+ |FROM testData
+ """.stripMargin,
+ ScriptTransformation(
+ Seq('a, 'b, 'c),
+ "cat",
+ Seq(AttributeReference("a", IntegerType)(),
+ AttributeReference("b", StringType)(),
+ AttributeReference("c", LongType)()),
+ UnresolvedRelation(TableIdentifier("testData")),
+ ScriptInputOutputSchema(List.empty, List.empty, None, None,
+ List.empty, List.empty, None, None, false)))
+
+ // verify with ROW FORMAT DELIMETED
+ assertEqual(
+ """
+ |SELECT TRANSFORM(a, b, c)
+ |ROW FORMAT DELIMITED
+ |FIELDS TERMINATED BY '\t'
+ |COLLECTION ITEMS TERMINATED BY '\u0002'
+ |MAP KEYS TERMINATED BY '\u0003'
+ |LINES TERMINATED BY '\n'
+ |NULL DEFINED AS 'null'
+ |USING 'cat' AS (a, b, c)
+ |ROW FORMAT DELIMITED
+ |FIELDS TERMINATED BY '\t'
+ |COLLECTION ITEMS TERMINATED BY '\u0004'
+ |MAP KEYS TERMINATED BY '\u0005'
+ |LINES TERMINATED BY '\n'
+ |NULL DEFINED AS 'NULL'
+ |FROM testData
+ """.stripMargin,
+ ScriptTransformation(
+ Seq('a, 'b, 'c),
+ "cat",
+ Seq(AttributeReference("a", StringType)(),
+ AttributeReference("b", StringType)(),
+ AttributeReference("c", StringType)()),
+ UnresolvedRelation(TableIdentifier("testData")),
+ ScriptInputOutputSchema(
+ Seq(("TOK_TABLEROWFORMATFIELD", "'\\t'"),
+ ("TOK_TABLEROWFORMATCOLLITEMS", "'\u0002'"),
+ ("TOK_TABLEROWFORMATMAPKEYS", "'\u0003'"),
+ ("TOK_TABLEROWFORMATLINES", "'\\n'"),
+ ("TOK_TABLEROWFORMATNULL", "'null'")),
+ Seq(("TOK_TABLEROWFORMATFIELD", "'\\t'"),
+ ("TOK_TABLEROWFORMATCOLLITEMS", "'\u0004'"),
+ ("TOK_TABLEROWFORMATMAPKEYS", "'\u0005'"),
+ ("TOK_TABLEROWFORMATLINES", "'\\n'"),
+ ("TOK_TABLEROWFORMATNULL", "'NULL'")), None, None,
+ List.empty, List.empty, None, None, false)))
+
+ // verify with ROW FORMAT SERDE
+ intercept(
+ """
+ |SELECT TRANSFORM(a, b, c)
+ |ROW FORMAT SERDE 'org.apache.hadoop.hive.serde2.OpenCSVSerde'
+ |WITH SERDEPROPERTIES(
+ | "separatorChar" = "\t",
+ | "quoteChar" = "'",
+ | "escapeChar" = "\\")
+ |USING 'cat' AS (a, b, c)
+ |ROW FORMAT SERDE 'org.apache.hadoop.hive.serde2.OpenCSVSerde'
+ |WITH SERDEPROPERTIES(
+ | "separatorChar" = "\t",
+ | "quoteChar" = "'",
+ | "escapeChar" = "\\")
+ |FROM testData
+ """.stripMargin,
+ "TRANSFORM with serde is only supported in hive mode")
Review comment:
Done
##########
File path:
sql/core/src/main/scala/org/apache/spark/sql/execution/SparkScriptTransformationExec.scala
##########
@@ -0,0 +1,89 @@
+/*
+ * 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.execution
+
+import java.io._
+
+import org.apache.hadoop.conf.Configuration
+
+import org.apache.spark.TaskContext
+import org.apache.spark.sql.catalyst.InternalRow
+import org.apache.spark.sql.catalyst.expressions._
+import org.apache.spark.sql.types._
+import org.apache.spark.util.CircularBuffer
+
+/**
+ * Transforms the input by forking and running the specified script.
+ *
+ * @param input the set of expression that should be passed to the script.
+ * @param script the command that should be executed.
+ * @param output the attributes that are produced by the script.
+ */
+case class SparkScriptTransformationExec(
+ input: Seq[Expression],
+ script: String,
+ output: Seq[Attribute],
+ child: SparkPlan,
+ ioschema: ScriptTransformationIOSchema)
Review comment:
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.
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
