Repository: spark Updated Branches: refs/heads/master b1b35ca2e -> 119f45d61
http://git-wip-us.apache.org/repos/asf/spark/blob/119f45d6/sql/core/src/test/scala/org/apache/spark/sql/execution/TgfSuite.scala ---------------------------------------------------------------------- diff --git a/sql/core/src/test/scala/org/apache/spark/sql/execution/TgfSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/execution/TgfSuite.scala deleted file mode 100644 index 272c0d4..0000000 --- a/sql/core/src/test/scala/org/apache/spark/sql/execution/TgfSuite.scala +++ /dev/null @@ -1,65 +0,0 @@ -/* - * 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 org.apache.spark.sql.QueryTest -import org.apache.spark.sql.catalyst.expressions._ -import org.apache.spark.sql.catalyst.plans._ - -/* Implicit conversions */ -import org.apache.spark.sql.test.TestSQLContext._ - -/** - * This is an example TGF that uses UnresolvedAttributes 'name and 'age to access specific columns - * from the input data. These will be replaced during analysis with specific AttributeReferences - * and then bound to specific ordinals during query planning. While TGFs could also access specific - * columns using hand-coded ordinals, doing so violates data independence. - * - * Note: this is only a rough example of how TGFs can be expressed, the final version will likely - * involve a lot more sugar for cleaner use in Scala/Java/etc. - */ -case class ExampleTGF(input: Seq[Expression] = Seq('name, 'age)) extends Generator { - def children = input - protected def makeOutput() = 'nameAndAge.string :: Nil - - val Seq(nameAttr, ageAttr) = input - - override def eval(input: Row): TraversableOnce[Row] = { - val name = nameAttr.eval(input) - val age = ageAttr.eval(input).asInstanceOf[Int] - - Iterator( - new GenericRow(Array[Any](s"$name is $age years old")), - new GenericRow(Array[Any](s"Next year, $name will be ${age + 1} years old"))) - } -} - -class TgfSuite extends QueryTest { - val inputData = - logical.LocalRelation('name.string, 'age.int).loadData( - ("michael", 29) :: Nil - ) - - test("simple tgf example") { - checkAnswer( - inputData.generate(ExampleTGF()), - Seq( - Row("michael is 29 years old"), - Row("Next year, michael will be 30 years old"))) - } -} http://git-wip-us.apache.org/repos/asf/spark/blob/119f45d6/sql/core/src/test/scala/org/apache/spark/sql/json/JsonSuite.scala ---------------------------------------------------------------------- diff --git a/sql/core/src/test/scala/org/apache/spark/sql/json/JsonSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/json/JsonSuite.scala index 94d14ac..ef198f8 100644 --- a/sql/core/src/test/scala/org/apache/spark/sql/json/JsonSuite.scala +++ b/sql/core/src/test/scala/org/apache/spark/sql/json/JsonSuite.scala @@ -21,11 +21,12 @@ import java.sql.{Date, Timestamp} import org.apache.spark.sql.TestData._ import org.apache.spark.sql.catalyst.util._ +import org.apache.spark.sql.dsl._ import org.apache.spark.sql.json.JsonRDD.{compatibleType, enforceCorrectType} import org.apache.spark.sql.test.TestSQLContext import org.apache.spark.sql.test.TestSQLContext._ import org.apache.spark.sql.types._ -import org.apache.spark.sql.{QueryTest, Row, SQLConf} +import org.apache.spark.sql.{Literal, QueryTest, Row, SQLConf} class JsonSuite extends QueryTest { import org.apache.spark.sql.json.TestJsonData._ @@ -463,8 +464,8 @@ class JsonSuite extends QueryTest { // in the Project. checkAnswer( jsonSchemaRDD. - where('num_str > BigDecimal("92233720368547758060")). - select('num_str + 1.2 as Symbol("num")), + where('num_str > Literal(BigDecimal("92233720368547758060"))). + select(('num_str + Literal(1.2)).as("num")), Row(new java.math.BigDecimal("92233720368547758061.2")) ) @@ -820,7 +821,7 @@ class JsonSuite extends QueryTest { val schemaRDD1 = applySchema(rowRDD1, schema1) schemaRDD1.registerTempTable("applySchema1") - val schemaRDD2 = schemaRDD1.toSchemaRDD + val schemaRDD2 = schemaRDD1.toDF val result = schemaRDD2.toJSON.collect() assert(result(0) == "{\"f1\":1,\"f2\":\"A1\",\"f3\":true,\"f4\":[\"1\",\" A1\",\" true\",\" null\"]}") assert(result(3) == "{\"f1\":4,\"f2\":\"D4\",\"f3\":true,\"f4\":[\"4\",\" D4\",\" true\",\" 2147483644\"],\"f5\":2147483644}") @@ -841,7 +842,7 @@ class JsonSuite extends QueryTest { val schemaRDD3 = applySchema(rowRDD2, schema2) schemaRDD3.registerTempTable("applySchema2") - val schemaRDD4 = schemaRDD3.toSchemaRDD + val schemaRDD4 = schemaRDD3.toDF val result2 = schemaRDD4.toJSON.collect() assert(result2(1) == "{\"f1\":{\"f11\":2,\"f12\":false},\"f2\":{\"B2\":null}}") http://git-wip-us.apache.org/repos/asf/spark/blob/119f45d6/sql/core/src/test/scala/org/apache/spark/sql/parquet/ParquetFilterSuite.scala ---------------------------------------------------------------------- diff --git a/sql/core/src/test/scala/org/apache/spark/sql/parquet/ParquetFilterSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/parquet/ParquetFilterSuite.scala index 1e7d3e0..c9bc559 100644 --- a/sql/core/src/test/scala/org/apache/spark/sql/parquet/ParquetFilterSuite.scala +++ b/sql/core/src/test/scala/org/apache/spark/sql/parquet/ParquetFilterSuite.scala @@ -23,7 +23,7 @@ import parquet.filter2.predicate.{FilterPredicate, Operators} import org.apache.spark.sql.catalyst.dsl.expressions._ import org.apache.spark.sql.catalyst.expressions.{Attribute, Literal, Predicate, Row} import org.apache.spark.sql.test.TestSQLContext -import org.apache.spark.sql.{QueryTest, SQLConf, SchemaRDD} +import org.apache.spark.sql.{DataFrame, QueryTest, SQLConf} /** * A test suite that tests Parquet filter2 API based filter pushdown optimization. @@ -41,15 +41,17 @@ class ParquetFilterSuite extends QueryTest with ParquetTest { val sqlContext = TestSQLContext private def checkFilterPredicate( - rdd: SchemaRDD, + rdd: DataFrame, predicate: Predicate, filterClass: Class[_ <: FilterPredicate], - checker: (SchemaRDD, Seq[Row]) => Unit, + checker: (DataFrame, Seq[Row]) => Unit, expected: Seq[Row]): Unit = { val output = predicate.collect { case a: Attribute => a }.distinct withSQLConf(SQLConf.PARQUET_FILTER_PUSHDOWN_ENABLED -> "true") { - val query = rdd.select(output: _*).where(predicate) + val query = rdd + .select(output.map(e => new org.apache.spark.sql.Column(e)): _*) + .where(new org.apache.spark.sql.Column(predicate)) val maybeAnalyzedPredicate = query.queryExecution.executedPlan.collect { case plan: ParquetTableScan => plan.columnPruningPred @@ -71,13 +73,13 @@ class ParquetFilterSuite extends QueryTest with ParquetTest { private def checkFilterPredicate (predicate: Predicate, filterClass: Class[_ <: FilterPredicate], expected: Seq[Row]) - (implicit rdd: SchemaRDD): Unit = { + (implicit rdd: DataFrame): Unit = { checkFilterPredicate(rdd, predicate, filterClass, checkAnswer(_, _: Seq[Row]), expected) } private def checkFilterPredicate[T] (predicate: Predicate, filterClass: Class[_ <: FilterPredicate], expected: T) - (implicit rdd: SchemaRDD): Unit = { + (implicit rdd: DataFrame): Unit = { checkFilterPredicate(predicate, filterClass, Seq(Row(expected)))(rdd) } @@ -93,24 +95,24 @@ class ParquetFilterSuite extends QueryTest with ParquetTest { test("filter pushdown - integer") { withParquetRDD((1 to 4).map(i => Tuple1(Option(i)))) { implicit rdd => - checkFilterPredicate('_1.isNull, classOf[Eq [_]], Seq.empty[Row]) + checkFilterPredicate('_1.isNull, classOf[Eq[_]], Seq.empty[Row]) checkFilterPredicate('_1.isNotNull, classOf[NotEq[_]], (1 to 4).map(Row.apply(_))) - checkFilterPredicate('_1 === 1, classOf[Eq [_]], 1) + checkFilterPredicate('_1 === 1, classOf[Eq[_]], 1) checkFilterPredicate('_1 !== 1, classOf[NotEq[_]], (2 to 4).map(Row.apply(_))) - checkFilterPredicate('_1 < 2, classOf[Lt [_]], 1) - checkFilterPredicate('_1 > 3, classOf[Gt [_]], 4) + checkFilterPredicate('_1 < 2, classOf[Lt[_]], 1) + checkFilterPredicate('_1 > 3, classOf[Gt[_]], 4) checkFilterPredicate('_1 <= 1, classOf[LtEq[_]], 1) checkFilterPredicate('_1 >= 4, classOf[GtEq[_]], 4) checkFilterPredicate(Literal(1) === '_1, classOf[Eq [_]], 1) - checkFilterPredicate(Literal(2) > '_1, classOf[Lt [_]], 1) - checkFilterPredicate(Literal(3) < '_1, classOf[Gt [_]], 4) - checkFilterPredicate(Literal(1) >= '_1, classOf[LtEq[_]], 1) - checkFilterPredicate(Literal(4) <= '_1, classOf[GtEq[_]], 4) + checkFilterPredicate(Literal(2) > '_1, classOf[Lt [_]], 1) + checkFilterPredicate(Literal(3) < '_1, classOf[Gt [_]], 4) + checkFilterPredicate(Literal(1) >= '_1, classOf[LtEq[_]], 1) + checkFilterPredicate(Literal(4) <= '_1, classOf[GtEq[_]], 4) - checkFilterPredicate(!('_1 < 4), classOf[GtEq[_]], 4) + checkFilterPredicate(!('_1 < 4), classOf[GtEq[_]], 4) checkFilterPredicate('_1 > 2 && '_1 < 4, classOf[Operators.And], 3) checkFilterPredicate('_1 < 2 || '_1 > 3, classOf[Operators.Or], Seq(Row(1), Row(4))) } @@ -118,24 +120,24 @@ class ParquetFilterSuite extends QueryTest with ParquetTest { test("filter pushdown - long") { withParquetRDD((1 to 4).map(i => Tuple1(Option(i.toLong)))) { implicit rdd => - checkFilterPredicate('_1.isNull, classOf[Eq [_]], Seq.empty[Row]) + checkFilterPredicate('_1.isNull, classOf[Eq[_]], Seq.empty[Row]) checkFilterPredicate('_1.isNotNull, classOf[NotEq[_]], (1 to 4).map(Row.apply(_))) - checkFilterPredicate('_1 === 1, classOf[Eq[_]], 1) + checkFilterPredicate('_1 === 1, classOf[Eq[_]], 1) checkFilterPredicate('_1 !== 1, classOf[NotEq[_]], (2 to 4).map(Row.apply(_))) - checkFilterPredicate('_1 < 2, classOf[Lt [_]], 1) - checkFilterPredicate('_1 > 3, classOf[Gt [_]], 4) + checkFilterPredicate('_1 < 2, classOf[Lt[_]], 1) + checkFilterPredicate('_1 > 3, classOf[Gt[_]], 4) checkFilterPredicate('_1 <= 1, classOf[LtEq[_]], 1) checkFilterPredicate('_1 >= 4, classOf[GtEq[_]], 4) - checkFilterPredicate(Literal(1) === '_1, classOf[Eq [_]], 1) - checkFilterPredicate(Literal(2) > '_1, classOf[Lt [_]], 1) - checkFilterPredicate(Literal(3) < '_1, classOf[Gt [_]], 4) + checkFilterPredicate(Literal(1) === '_1, classOf[Eq[_]], 1) + checkFilterPredicate(Literal(2) > '_1, classOf[Lt[_]], 1) + checkFilterPredicate(Literal(3) < '_1, classOf[Gt[_]], 4) checkFilterPredicate(Literal(1) >= '_1, classOf[LtEq[_]], 1) checkFilterPredicate(Literal(4) <= '_1, classOf[GtEq[_]], 4) - checkFilterPredicate(!('_1 < 4), classOf[GtEq[_]], 4) + checkFilterPredicate(!('_1 < 4), classOf[GtEq[_]], 4) checkFilterPredicate('_1 > 2 && '_1 < 4, classOf[Operators.And], 3) checkFilterPredicate('_1 < 2 || '_1 > 3, classOf[Operators.Or], Seq(Row(1), Row(4))) } @@ -143,24 +145,24 @@ class ParquetFilterSuite extends QueryTest with ParquetTest { test("filter pushdown - float") { withParquetRDD((1 to 4).map(i => Tuple1(Option(i.toFloat)))) { implicit rdd => - checkFilterPredicate('_1.isNull, classOf[Eq [_]], Seq.empty[Row]) + checkFilterPredicate('_1.isNull, classOf[Eq[_]], Seq.empty[Row]) checkFilterPredicate('_1.isNotNull, classOf[NotEq[_]], (1 to 4).map(Row.apply(_))) - checkFilterPredicate('_1 === 1, classOf[Eq [_]], 1) + checkFilterPredicate('_1 === 1, classOf[Eq[_]], 1) checkFilterPredicate('_1 !== 1, classOf[NotEq[_]], (2 to 4).map(Row.apply(_))) - checkFilterPredicate('_1 < 2, classOf[Lt [_]], 1) - checkFilterPredicate('_1 > 3, classOf[Gt [_]], 4) + checkFilterPredicate('_1 < 2, classOf[Lt[_]], 1) + checkFilterPredicate('_1 > 3, classOf[Gt[_]], 4) checkFilterPredicate('_1 <= 1, classOf[LtEq[_]], 1) checkFilterPredicate('_1 >= 4, classOf[GtEq[_]], 4) - checkFilterPredicate(Literal(1) === '_1, classOf[Eq [_]], 1) - checkFilterPredicate(Literal(2) > '_1, classOf[Lt [_]], 1) - checkFilterPredicate(Literal(3) < '_1, classOf[Gt [_]], 4) - checkFilterPredicate(Literal(1) >= '_1, classOf[LtEq[_]], 1) - checkFilterPredicate(Literal(4) <= '_1, classOf[GtEq[_]], 4) + checkFilterPredicate(Literal(1) === '_1, classOf[Eq[_]], 1) + checkFilterPredicate(Literal(2) > '_1, classOf[Lt[_]], 1) + checkFilterPredicate(Literal(3) < '_1, classOf[Gt[_]], 4) + checkFilterPredicate(Literal(1) >= '_1, classOf[LtEq[_]], 1) + checkFilterPredicate(Literal(4) <= '_1, classOf[GtEq[_]], 4) - checkFilterPredicate(!('_1 < 4), classOf[GtEq[_]], 4) + checkFilterPredicate(!('_1 < 4), classOf[GtEq[_]], 4) checkFilterPredicate('_1 > 2 && '_1 < 4, classOf[Operators.And], 3) checkFilterPredicate('_1 < 2 || '_1 > 3, classOf[Operators.Or], Seq(Row(1), Row(4))) } @@ -168,24 +170,24 @@ class ParquetFilterSuite extends QueryTest with ParquetTest { test("filter pushdown - double") { withParquetRDD((1 to 4).map(i => Tuple1(Option(i.toDouble)))) { implicit rdd => - checkFilterPredicate('_1.isNull, classOf[Eq[_]], Seq.empty[Row]) + checkFilterPredicate('_1.isNull, classOf[Eq[_]], Seq.empty[Row]) checkFilterPredicate('_1.isNotNull, classOf[NotEq[_]], (1 to 4).map(Row.apply(_))) - checkFilterPredicate('_1 === 1, classOf[Eq [_]], 1) + checkFilterPredicate('_1 === 1, classOf[Eq[_]], 1) checkFilterPredicate('_1 !== 1, classOf[NotEq[_]], (2 to 4).map(Row.apply(_))) - checkFilterPredicate('_1 < 2, classOf[Lt [_]], 1) - checkFilterPredicate('_1 > 3, classOf[Gt [_]], 4) + checkFilterPredicate('_1 < 2, classOf[Lt[_]], 1) + checkFilterPredicate('_1 > 3, classOf[Gt[_]], 4) checkFilterPredicate('_1 <= 1, classOf[LtEq[_]], 1) checkFilterPredicate('_1 >= 4, classOf[GtEq[_]], 4) checkFilterPredicate(Literal(1) === '_1, classOf[Eq [_]], 1) - checkFilterPredicate(Literal(2) > '_1, classOf[Lt [_]], 1) - checkFilterPredicate(Literal(3) < '_1, classOf[Gt [_]], 4) - checkFilterPredicate(Literal(1) >= '_1, classOf[LtEq[_]], 1) - checkFilterPredicate(Literal(4) <= '_1, classOf[GtEq[_]], 4) + checkFilterPredicate(Literal(2) > '_1, classOf[Lt [_]], 1) + checkFilterPredicate(Literal(3) < '_1, classOf[Gt [_]], 4) + checkFilterPredicate(Literal(1) >= '_1, classOf[LtEq[_]], 1) + checkFilterPredicate(Literal(4) <= '_1, classOf[GtEq[_]], 4) - checkFilterPredicate(!('_1 < 4), classOf[GtEq[_]], 4) + checkFilterPredicate(!('_1 < 4), classOf[GtEq[_]], 4) checkFilterPredicate('_1 > 2 && '_1 < 4, classOf[Operators.And], 3) checkFilterPredicate('_1 < 2 || '_1 > 3, classOf[Operators.Or], Seq(Row(1), Row(4))) } @@ -197,30 +199,30 @@ class ParquetFilterSuite extends QueryTest with ParquetTest { checkFilterPredicate( '_1.isNotNull, classOf[NotEq[_]], (1 to 4).map(i => Row.apply(i.toString))) - checkFilterPredicate('_1 === "1", classOf[Eq [_]], "1") + checkFilterPredicate('_1 === "1", classOf[Eq[_]], "1") checkFilterPredicate('_1 !== "1", classOf[NotEq[_]], (2 to 4).map(i => Row.apply(i.toString))) - checkFilterPredicate('_1 < "2", classOf[Lt [_]], "1") - checkFilterPredicate('_1 > "3", classOf[Gt [_]], "4") + checkFilterPredicate('_1 < "2", classOf[Lt[_]], "1") + checkFilterPredicate('_1 > "3", classOf[Gt[_]], "4") checkFilterPredicate('_1 <= "1", classOf[LtEq[_]], "1") checkFilterPredicate('_1 >= "4", classOf[GtEq[_]], "4") - checkFilterPredicate(Literal("1") === '_1, classOf[Eq [_]], "1") - checkFilterPredicate(Literal("2") > '_1, classOf[Lt [_]], "1") - checkFilterPredicate(Literal("3") < '_1, classOf[Gt [_]], "4") - checkFilterPredicate(Literal("1") >= '_1, classOf[LtEq[_]], "1") - checkFilterPredicate(Literal("4") <= '_1, classOf[GtEq[_]], "4") + checkFilterPredicate(Literal("1") === '_1, classOf[Eq[_]], "1") + checkFilterPredicate(Literal("2") > '_1, classOf[Lt[_]], "1") + checkFilterPredicate(Literal("3") < '_1, classOf[Gt[_]], "4") + checkFilterPredicate(Literal("1") >= '_1, classOf[LtEq[_]], "1") + checkFilterPredicate(Literal("4") <= '_1, classOf[GtEq[_]], "4") - checkFilterPredicate(!('_1 < "4"), classOf[GtEq[_]], "4") + checkFilterPredicate(!('_1 < "4"), classOf[GtEq[_]], "4") checkFilterPredicate('_1 > "2" && '_1 < "4", classOf[Operators.And], "3") - checkFilterPredicate('_1 < "2" || '_1 > "3", classOf[Operators.Or], Seq(Row("1"), Row("4"))) + checkFilterPredicate('_1 < "2" || '_1 > "3", classOf[Operators.Or], Seq(Row("1"), Row("4"))) } } def checkBinaryFilterPredicate (predicate: Predicate, filterClass: Class[_ <: FilterPredicate], expected: Seq[Row]) - (implicit rdd: SchemaRDD): Unit = { - def checkBinaryAnswer(rdd: SchemaRDD, expected: Seq[Row]) = { + (implicit rdd: DataFrame): Unit = { + def checkBinaryAnswer(rdd: DataFrame, expected: Seq[Row]) = { assertResult(expected.map(_.getAs[Array[Byte]](0).mkString(",")).toSeq.sorted) { rdd.map(_.getAs[Array[Byte]](0).mkString(",")).collect().toSeq.sorted } @@ -231,7 +233,7 @@ class ParquetFilterSuite extends QueryTest with ParquetTest { def checkBinaryFilterPredicate (predicate: Predicate, filterClass: Class[_ <: FilterPredicate], expected: Array[Byte]) - (implicit rdd: SchemaRDD): Unit = { + (implicit rdd: DataFrame): Unit = { checkBinaryFilterPredicate(predicate, filterClass, Seq(Row(expected)))(rdd) } @@ -249,16 +251,16 @@ class ParquetFilterSuite extends QueryTest with ParquetTest { checkBinaryFilterPredicate( '_1 !== 1.b, classOf[NotEq[_]], (2 to 4).map(i => Row.apply(i.b)).toSeq) - checkBinaryFilterPredicate('_1 < 2.b, classOf[Lt [_]], 1.b) - checkBinaryFilterPredicate('_1 > 3.b, classOf[Gt [_]], 4.b) + checkBinaryFilterPredicate('_1 < 2.b, classOf[Lt[_]], 1.b) + checkBinaryFilterPredicate('_1 > 3.b, classOf[Gt[_]], 4.b) checkBinaryFilterPredicate('_1 <= 1.b, classOf[LtEq[_]], 1.b) checkBinaryFilterPredicate('_1 >= 4.b, classOf[GtEq[_]], 4.b) - checkBinaryFilterPredicate(Literal(1.b) === '_1, classOf[Eq [_]], 1.b) - checkBinaryFilterPredicate(Literal(2.b) > '_1, classOf[Lt [_]], 1.b) - checkBinaryFilterPredicate(Literal(3.b) < '_1, classOf[Gt [_]], 4.b) - checkBinaryFilterPredicate(Literal(1.b) >= '_1, classOf[LtEq[_]], 1.b) - checkBinaryFilterPredicate(Literal(4.b) <= '_1, classOf[GtEq[_]], 4.b) + checkBinaryFilterPredicate(Literal(1.b) === '_1, classOf[Eq[_]], 1.b) + checkBinaryFilterPredicate(Literal(2.b) > '_1, classOf[Lt[_]], 1.b) + checkBinaryFilterPredicate(Literal(3.b) < '_1, classOf[Gt[_]], 4.b) + checkBinaryFilterPredicate(Literal(1.b) >= '_1, classOf[LtEq[_]], 1.b) + checkBinaryFilterPredicate(Literal(4.b) <= '_1, classOf[GtEq[_]], 4.b) checkBinaryFilterPredicate(!('_1 < 4.b), classOf[GtEq[_]], 4.b) checkBinaryFilterPredicate('_1 > 2.b && '_1 < 4.b, classOf[Operators.And], 3.b) http://git-wip-us.apache.org/repos/asf/spark/blob/119f45d6/sql/core/src/test/scala/org/apache/spark/sql/parquet/ParquetIOSuite.scala ---------------------------------------------------------------------- diff --git a/sql/core/src/test/scala/org/apache/spark/sql/parquet/ParquetIOSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/parquet/ParquetIOSuite.scala index a57e4e8..f03b3a3 100644 --- a/sql/core/src/test/scala/org/apache/spark/sql/parquet/ParquetIOSuite.scala +++ b/sql/core/src/test/scala/org/apache/spark/sql/parquet/ParquetIOSuite.scala @@ -32,12 +32,13 @@ import parquet.schema.{MessageType, MessageTypeParser} import org.apache.hadoop.conf.Configuration import org.apache.hadoop.fs.{FileSystem, Path} +import org.apache.spark.sql.{DataFrame, QueryTest, SQLConf} +import org.apache.spark.sql.dsl._ import org.apache.spark.sql.catalyst.ScalaReflection import org.apache.spark.sql.catalyst.expressions.Row import org.apache.spark.sql.test.TestSQLContext import org.apache.spark.sql.test.TestSQLContext._ import org.apache.spark.sql.types.DecimalType -import org.apache.spark.sql.{QueryTest, SQLConf, SchemaRDD} // Write support class for nested groups: ParquetWriter initializes GroupWriteSupport // with an empty configuration (it is after all not intended to be used in this way?) @@ -97,11 +98,11 @@ class ParquetIOSuite extends QueryTest with ParquetTest { } test("fixed-length decimals") { - def makeDecimalRDD(decimal: DecimalType): SchemaRDD = + def makeDecimalRDD(decimal: DecimalType): DataFrame = sparkContext .parallelize(0 to 1000) .map(i => Tuple1(i / 100.0)) - .select('_1 cast decimal) + .select($"_1" cast decimal as "abcd") for ((precision, scale) <- Seq((5, 2), (1, 0), (1, 1), (18, 10), (18, 17))) { withTempPath { dir => http://git-wip-us.apache.org/repos/asf/spark/blob/119f45d6/sql/core/src/test/scala/org/apache/spark/sql/sources/PrunedScanSuite.scala ---------------------------------------------------------------------- diff --git a/sql/core/src/test/scala/org/apache/spark/sql/sources/PrunedScanSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/sources/PrunedScanSuite.scala index 7900b3e..a33cf11 100644 --- a/sql/core/src/test/scala/org/apache/spark/sql/sources/PrunedScanSuite.scala +++ b/sql/core/src/test/scala/org/apache/spark/sql/sources/PrunedScanSuite.scala @@ -17,6 +17,8 @@ package org.apache.spark.sql.sources +import scala.language.existentials + import org.apache.spark.sql._ import org.apache.spark.sql.types._ http://git-wip-us.apache.org/repos/asf/spark/blob/119f45d6/sql/hive-thriftserver/src/main/scala/org/apache/spark/sql/hive/thriftserver/SparkSQLCLIDriver.scala ---------------------------------------------------------------------- diff --git a/sql/hive-thriftserver/src/main/scala/org/apache/spark/sql/hive/thriftserver/SparkSQLCLIDriver.scala b/sql/hive-thriftserver/src/main/scala/org/apache/spark/sql/hive/thriftserver/SparkSQLCLIDriver.scala index 7385952..bb19ac2 100755 --- a/sql/hive-thriftserver/src/main/scala/org/apache/spark/sql/hive/thriftserver/SparkSQLCLIDriver.scala +++ b/sql/hive-thriftserver/src/main/scala/org/apache/spark/sql/hive/thriftserver/SparkSQLCLIDriver.scala @@ -23,6 +23,7 @@ import java.io._ import java.util.{ArrayList => JArrayList} import jline.{ConsoleReader, History} + import org.apache.commons.lang.StringUtils import org.apache.commons.logging.LogFactory import org.apache.hadoop.conf.Configuration @@ -39,7 +40,6 @@ import org.apache.thrift.transport.TSocket import org.apache.spark.Logging import org.apache.spark.sql.hive.HiveShim -import org.apache.spark.sql.hive.thriftserver.HiveThriftServerShim private[hive] object SparkSQLCLIDriver { private var prompt = "spark-sql" http://git-wip-us.apache.org/repos/asf/spark/blob/119f45d6/sql/hive-thriftserver/v0.12.0/src/main/scala/org/apache/spark/sql/hive/thriftserver/Shim12.scala ---------------------------------------------------------------------- diff --git a/sql/hive-thriftserver/v0.12.0/src/main/scala/org/apache/spark/sql/hive/thriftserver/Shim12.scala b/sql/hive-thriftserver/v0.12.0/src/main/scala/org/apache/spark/sql/hive/thriftserver/Shim12.scala index 166c56b..ea9d61d 100644 --- a/sql/hive-thriftserver/v0.12.0/src/main/scala/org/apache/spark/sql/hive/thriftserver/Shim12.scala +++ b/sql/hive-thriftserver/v0.12.0/src/main/scala/org/apache/spark/sql/hive/thriftserver/Shim12.scala @@ -32,7 +32,7 @@ import org.apache.hive.service.cli.operation.ExecuteStatementOperation import org.apache.hive.service.cli.session.HiveSession import org.apache.spark.Logging -import org.apache.spark.sql.{SQLConf, SchemaRDD, Row => SparkRow} +import org.apache.spark.sql.{DataFrame, SQLConf, Row => SparkRow} import org.apache.spark.sql.execution.SetCommand import org.apache.spark.sql.hive.thriftserver.ReflectionUtils._ import org.apache.spark.sql.hive.{HiveContext, HiveMetastoreTypes} @@ -71,7 +71,7 @@ private[hive] class SparkExecuteStatementOperation( sessionToActivePool: SMap[SessionHandle, String]) extends ExecuteStatementOperation(parentSession, statement, confOverlay) with Logging { - private var result: SchemaRDD = _ + private var result: DataFrame = _ private var iter: Iterator[SparkRow] = _ private var dataTypes: Array[DataType] = _ @@ -202,7 +202,7 @@ private[hive] class SparkExecuteStatementOperation( val useIncrementalCollect = hiveContext.getConf("spark.sql.thriftServer.incrementalCollect", "false").toBoolean if (useIncrementalCollect) { - result.toLocalIterator + result.rdd.toLocalIterator } else { result.collect().iterator } http://git-wip-us.apache.org/repos/asf/spark/blob/119f45d6/sql/hive-thriftserver/v0.13.1/src/main/scala/org/apache/spark/sql/hive/thriftserver/Shim13.scala ---------------------------------------------------------------------- diff --git a/sql/hive-thriftserver/v0.13.1/src/main/scala/org/apache/spark/sql/hive/thriftserver/Shim13.scala b/sql/hive-thriftserver/v0.13.1/src/main/scala/org/apache/spark/sql/hive/thriftserver/Shim13.scala index eaf7a1d..71e3954 100644 --- a/sql/hive-thriftserver/v0.13.1/src/main/scala/org/apache/spark/sql/hive/thriftserver/Shim13.scala +++ b/sql/hive-thriftserver/v0.13.1/src/main/scala/org/apache/spark/sql/hive/thriftserver/Shim13.scala @@ -30,7 +30,7 @@ import org.apache.hive.service.cli.operation.ExecuteStatementOperation import org.apache.hive.service.cli.session.HiveSession import org.apache.spark.Logging -import org.apache.spark.sql.{Row => SparkRow, SQLConf, SchemaRDD} +import org.apache.spark.sql.{DataFrame, Row => SparkRow, SQLConf} import org.apache.spark.sql.execution.SetCommand import org.apache.spark.sql.hive.thriftserver.ReflectionUtils._ import org.apache.spark.sql.hive.{HiveContext, HiveMetastoreTypes} @@ -72,7 +72,7 @@ private[hive] class SparkExecuteStatementOperation( // NOTE: `runInBackground` is set to `false` intentionally to disable asynchronous execution extends ExecuteStatementOperation(parentSession, statement, confOverlay, false) with Logging { - private var result: SchemaRDD = _ + private var result: DataFrame = _ private var iter: Iterator[SparkRow] = _ private var dataTypes: Array[DataType] = _ @@ -173,7 +173,7 @@ private[hive] class SparkExecuteStatementOperation( val useIncrementalCollect = hiveContext.getConf("spark.sql.thriftServer.incrementalCollect", "false").toBoolean if (useIncrementalCollect) { - result.toLocalIterator + result.rdd.toLocalIterator } else { result.collect().iterator } http://git-wip-us.apache.org/repos/asf/spark/blob/119f45d6/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveContext.scala ---------------------------------------------------------------------- diff --git a/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveContext.scala b/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveContext.scala index 9d2cfd8..b746942 100644 --- a/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveContext.scala +++ b/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveContext.scala @@ -64,15 +64,15 @@ class HiveContext(sc: SparkContext) extends SQLContext(sc) { getConf("spark.sql.hive.convertMetastoreParquet", "true") == "true" override protected[sql] def executePlan(plan: LogicalPlan): this.QueryExecution = - new this.QueryExecution { val logical = plan } + new this.QueryExecution(plan) - override def sql(sqlText: String): SchemaRDD = { + override def sql(sqlText: String): DataFrame = { val substituted = new VariableSubstitution().substitute(hiveconf, sqlText) // TODO: Create a framework for registering parsers instead of just hardcoding if statements. if (conf.dialect == "sql") { super.sql(substituted) } else if (conf.dialect == "hiveql") { - new SchemaRDD(this, ddlParser(sqlText, false).getOrElse(HiveQl.parseSql(substituted))) + new DataFrame(this, ddlParser(sqlText, false).getOrElse(HiveQl.parseSql(substituted))) } else { sys.error(s"Unsupported SQL dialect: ${conf.dialect}. Try 'sql' or 'hiveql'") } @@ -352,7 +352,8 @@ class HiveContext(sc: SparkContext) extends SQLContext(sc) { override protected[sql] val planner = hivePlanner /** Extends QueryExecution with hive specific features. */ - protected[sql] abstract class QueryExecution extends super.QueryExecution { + protected[sql] class QueryExecution(logicalPlan: LogicalPlan) + extends super.QueryExecution(logicalPlan) { /** * Returns the result as a hive compatible sequence of strings. For native commands, the http://git-wip-us.apache.org/repos/asf/spark/blob/119f45d6/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveStrategies.scala ---------------------------------------------------------------------- diff --git a/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveStrategies.scala b/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveStrategies.scala index 6952b12..ace9329 100644 --- a/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveStrategies.scala +++ b/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveStrategies.scala @@ -20,7 +20,7 @@ package org.apache.spark.sql.hive import scala.collection.JavaConversions._ import org.apache.spark.annotation.Experimental -import org.apache.spark.sql.{SQLContext, SchemaRDD, Strategy} +import org.apache.spark.sql.{Column, DataFrame, SQLContext, Strategy} import org.apache.spark.sql.catalyst.analysis.UnresolvedAttribute import org.apache.spark.sql.catalyst.expressions._ import org.apache.spark.sql.catalyst.expressions.codegen.GeneratePredicate @@ -55,16 +55,15 @@ private[hive] trait HiveStrategies { */ @Experimental object ParquetConversion extends Strategy { - implicit class LogicalPlanHacks(s: SchemaRDD) { - def lowerCase = - new SchemaRDD(s.sqlContext, s.logicalPlan) + implicit class LogicalPlanHacks(s: DataFrame) { + def lowerCase = new DataFrame(s.sqlContext, s.logicalPlan) def addPartitioningAttributes(attrs: Seq[Attribute]) = { // Don't add the partitioning key if its already present in the data. if (attrs.map(_.name).toSet.subsetOf(s.logicalPlan.output.map(_.name).toSet)) { s } else { - new SchemaRDD( + new DataFrame( s.sqlContext, s.logicalPlan transform { case p: ParquetRelation => p.copy(partitioningAttributes = attrs) @@ -97,13 +96,13 @@ private[hive] trait HiveStrategies { // We are going to throw the predicates and projection back at the whole optimization // sequence so lets unresolve all the attributes, allowing them to be rebound to the // matching parquet attributes. - val unresolvedOtherPredicates = otherPredicates.map(_ transform { + val unresolvedOtherPredicates = new Column(otherPredicates.map(_ transform { case a: AttributeReference => UnresolvedAttribute(a.name) - }).reduceOption(And).getOrElse(Literal(true)) + }).reduceOption(And).getOrElse(Literal(true))) - val unresolvedProjection = projectList.map(_ transform { + val unresolvedProjection: Seq[Column] = projectList.map(_ transform { case a: AttributeReference => UnresolvedAttribute(a.name) - }) + }).map(new Column(_)) try { if (relation.hiveQlTable.isPartitioned) { http://git-wip-us.apache.org/repos/asf/spark/blob/119f45d6/sql/hive/src/main/scala/org/apache/spark/sql/hive/TestHive.scala ---------------------------------------------------------------------- diff --git a/sql/hive/src/main/scala/org/apache/spark/sql/hive/TestHive.scala b/sql/hive/src/main/scala/org/apache/spark/sql/hive/TestHive.scala index 47431ce..8e70ae8 100644 --- a/sql/hive/src/main/scala/org/apache/spark/sql/hive/TestHive.scala +++ b/sql/hive/src/main/scala/org/apache/spark/sql/hive/TestHive.scala @@ -99,7 +99,7 @@ class TestHiveContext(sc: SparkContext) extends HiveContext(sc) { override def runSqlHive(sql: String): Seq[String] = super.runSqlHive(rewritePaths(sql)) override def executePlan(plan: LogicalPlan): this.QueryExecution = - new this.QueryExecution { val logical = plan } + new this.QueryExecution(plan) /** Fewer partitions to speed up testing. */ protected[sql] override lazy val conf: SQLConf = new SQLConf { @@ -150,8 +150,8 @@ class TestHiveContext(sc: SparkContext) extends HiveContext(sc) { val describedTable = "DESCRIBE (\\w+)".r - protected[hive] class HiveQLQueryExecution(hql: String) extends this.QueryExecution { - lazy val logical = HiveQl.parseSql(hql) + protected[hive] class HiveQLQueryExecution(hql: String) + extends this.QueryExecution(HiveQl.parseSql(hql)) { def hiveExec() = runSqlHive(hql) override def toString = hql + "\n" + super.toString } @@ -159,7 +159,8 @@ class TestHiveContext(sc: SparkContext) extends HiveContext(sc) { /** * Override QueryExecution with special debug workflow. */ - abstract class QueryExecution extends super.QueryExecution { + class QueryExecution(logicalPlan: LogicalPlan) + extends super.QueryExecution(logicalPlan) { override lazy val analyzed = { val describedTables = logical match { case HiveNativeCommand(describedTable(tbl)) => tbl :: Nil http://git-wip-us.apache.org/repos/asf/spark/blob/119f45d6/sql/hive/src/test/scala/org/apache/spark/sql/QueryTest.scala ---------------------------------------------------------------------- diff --git a/sql/hive/src/test/scala/org/apache/spark/sql/QueryTest.scala b/sql/hive/src/test/scala/org/apache/spark/sql/QueryTest.scala index f320d73..ba39129 100644 --- a/sql/hive/src/test/scala/org/apache/spark/sql/QueryTest.scala +++ b/sql/hive/src/test/scala/org/apache/spark/sql/QueryTest.scala @@ -36,12 +36,12 @@ class QueryTest extends PlanTest { /** * Runs the plan and makes sure the answer contains all of the keywords, or the * none of keywords are listed in the answer - * @param rdd the [[SchemaRDD]] to be executed + * @param rdd the [[DataFrame]] to be executed * @param exists true for make sure the keywords are listed in the output, otherwise * to make sure none of the keyword are not listed in the output * @param keywords keyword in string array */ - def checkExistence(rdd: SchemaRDD, exists: Boolean, keywords: String*) { + def checkExistence(rdd: DataFrame, exists: Boolean, keywords: String*) { val outputs = rdd.collect().map(_.mkString).mkString for (key <- keywords) { if (exists) { @@ -54,10 +54,10 @@ class QueryTest extends PlanTest { /** * Runs the plan and makes sure the answer matches the expected result. - * @param rdd the [[SchemaRDD]] to be executed + * @param rdd the [[DataFrame]] to be executed * @param expectedAnswer the expected result, can either be an Any, Seq[Product], or Seq[ Seq[Any] ]. */ - protected def checkAnswer(rdd: SchemaRDD, expectedAnswer: Seq[Row]): Unit = { + protected def checkAnswer(rdd: DataFrame, expectedAnswer: Seq[Row]): Unit = { val isSorted = rdd.logicalPlan.collect { case s: logical.Sort => s }.nonEmpty def prepareAnswer(answer: Seq[Row]): Seq[Row] = { // Converts data to types that we can do equality comparison using Scala collections. @@ -101,7 +101,7 @@ class QueryTest extends PlanTest { } } - protected def checkAnswer(rdd: SchemaRDD, expectedAnswer: Row): Unit = { + protected def checkAnswer(rdd: DataFrame, expectedAnswer: Row): Unit = { checkAnswer(rdd, Seq(expectedAnswer)) } http://git-wip-us.apache.org/repos/asf/spark/blob/119f45d6/sql/hive/src/test/scala/org/apache/spark/sql/hive/CachedTableSuite.scala ---------------------------------------------------------------------- diff --git a/sql/hive/src/test/scala/org/apache/spark/sql/hive/CachedTableSuite.scala b/sql/hive/src/test/scala/org/apache/spark/sql/hive/CachedTableSuite.scala index f95a6b4..61e5117 100644 --- a/sql/hive/src/test/scala/org/apache/spark/sql/hive/CachedTableSuite.scala +++ b/sql/hive/src/test/scala/org/apache/spark/sql/hive/CachedTableSuite.scala @@ -20,7 +20,7 @@ package org.apache.spark.sql.hive import org.apache.spark.sql.columnar.{InMemoryColumnarTableScan, InMemoryRelation} import org.apache.spark.sql.hive.test.TestHive import org.apache.spark.sql.hive.test.TestHive._ -import org.apache.spark.sql.{QueryTest, SchemaRDD} +import org.apache.spark.sql.{DataFrame, QueryTest} import org.apache.spark.storage.RDDBlockId class CachedTableSuite extends QueryTest { @@ -28,7 +28,7 @@ class CachedTableSuite extends QueryTest { * Throws a test failed exception when the number of cached tables differs from the expected * number. */ - def assertCached(query: SchemaRDD, numCachedTables: Int = 1): Unit = { + def assertCached(query: DataFrame, numCachedTables: Int = 1): Unit = { val planWithCaching = query.queryExecution.withCachedData val cachedData = planWithCaching collect { case cached: InMemoryRelation => cached http://git-wip-us.apache.org/repos/asf/spark/blob/119f45d6/sql/hive/src/test/scala/org/apache/spark/sql/hive/InsertIntoHiveTableSuite.scala ---------------------------------------------------------------------- diff --git a/sql/hive/src/test/scala/org/apache/spark/sql/hive/InsertIntoHiveTableSuite.scala b/sql/hive/src/test/scala/org/apache/spark/sql/hive/InsertIntoHiveTableSuite.scala index 0e6636d..5775d83 100644 --- a/sql/hive/src/test/scala/org/apache/spark/sql/hive/InsertIntoHiveTableSuite.scala +++ b/sql/hive/src/test/scala/org/apache/spark/sql/hive/InsertIntoHiveTableSuite.scala @@ -52,7 +52,7 @@ class InsertIntoHiveTableSuite extends QueryTest { // Make sure the table has been updated. checkAnswer( sql("SELECT * FROM createAndInsertTest"), - testData.toSchemaRDD.collect().toSeq ++ testData.toSchemaRDD.collect().toSeq + testData.toDF.collect().toSeq ++ testData.toDF.collect().toSeq ) // Now overwrite. http://git-wip-us.apache.org/repos/asf/spark/blob/119f45d6/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveQuerySuite.scala ---------------------------------------------------------------------- diff --git a/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveQuerySuite.scala b/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveQuerySuite.scala index df72be7..d67b00b 100644 --- a/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveQuerySuite.scala +++ b/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveQuerySuite.scala @@ -27,11 +27,12 @@ import scala.util.Try import org.apache.hadoop.hive.conf.HiveConf.ConfVars import org.apache.spark.{SparkFiles, SparkException} +import org.apache.spark.sql.{DataFrame, Row} import org.apache.spark.sql.catalyst.plans.logical.Project +import org.apache.spark.sql.dsl._ import org.apache.spark.sql.hive._ import org.apache.spark.sql.hive.test.TestHive import org.apache.spark.sql.hive.test.TestHive._ -import org.apache.spark.sql.{SQLConf, Row, SchemaRDD} case class TestData(a: Int, b: String) @@ -473,7 +474,7 @@ class HiveQuerySuite extends HiveComparisonTest with BeforeAndAfter { } } - def isExplanation(result: SchemaRDD) = { + def isExplanation(result: DataFrame) = { val explanation = result.select('plan).collect().map { case Row(plan: String) => plan } explanation.contains("== Physical Plan ==") } @@ -842,7 +843,7 @@ class HiveQuerySuite extends HiveComparisonTest with BeforeAndAfter { val testVal = "test.val.0" val nonexistentKey = "nonexistent" val KV = "([^=]+)=([^=]*)".r - def collectResults(rdd: SchemaRDD): Set[(String, String)] = + def collectResults(rdd: DataFrame): Set[(String, String)] = rdd.collect().map { case Row(key: String, value: String) => key -> value case Row(KV(key, value)) => key -> value http://git-wip-us.apache.org/repos/asf/spark/blob/119f45d6/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveTableScanSuite.scala ---------------------------------------------------------------------- diff --git a/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveTableScanSuite.scala b/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveTableScanSuite.scala index 16f77a4..a081227 100644 --- a/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveTableScanSuite.scala +++ b/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveTableScanSuite.scala @@ -17,9 +17,10 @@ package org.apache.spark.sql.hive.execution +import org.apache.spark.sql.Row +import org.apache.spark.sql.dsl._ import org.apache.spark.sql.hive.test.TestHive import org.apache.spark.sql.hive.test.TestHive._ -import org.apache.spark.sql.Row import org.apache.spark.util.Utils @@ -82,10 +83,10 @@ class HiveTableScanSuite extends HiveComparisonTest { sql("create table spark_4959 (col1 string)") sql("""insert into table spark_4959 select "hi" from src limit 1""") table("spark_4959").select( - 'col1.as('CaseSensitiveColName), - 'col1.as('CaseSensitiveColName2)).registerTempTable("spark_4959_2") + 'col1.as("CaseSensitiveColName"), + 'col1.as("CaseSensitiveColName2")).registerTempTable("spark_4959_2") - assert(sql("select CaseSensitiveColName from spark_4959_2").first() === Row("hi")) - assert(sql("select casesensitivecolname from spark_4959_2").first() === Row("hi")) + assert(sql("select CaseSensitiveColName from spark_4959_2").head() === Row("hi")) + assert(sql("select casesensitivecolname from spark_4959_2").head() === Row("hi")) } } http://git-wip-us.apache.org/repos/asf/spark/blob/119f45d6/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveUdfSuite.scala ---------------------------------------------------------------------- diff --git a/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveUdfSuite.scala b/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveUdfSuite.scala index f2374a2..dd0df1a 100644 --- a/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveUdfSuite.scala +++ b/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveUdfSuite.scala @@ -58,7 +58,7 @@ class HiveUdfSuite extends QueryTest { | getStruct(1).f3, | getStruct(1).f4, | getStruct(1).f5 FROM src LIMIT 1 - """.stripMargin).first() === Row(1, 2, 3, 4, 5)) + """.stripMargin).head() === Row(1, 2, 3, 4, 5)) } test("SPARK-4785 When called with arguments referring column fields, PMOD throws NPE") { --------------------------------------------------------------------- To unsubscribe, e-mail: commits-unsubscr...@spark.apache.org For additional commands, e-mail: commits-h...@spark.apache.org