[
https://issues.apache.org/jira/browse/SPARK-6570?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Jon Chase updated SPARK-6570:
-----------------------------
Summary: Spark SQL arrays: "explode()" fails and cannot save array type to
Parquet (was: Spark SQL "explode()" fails, assumes underlying SQL array is
represented by Scala Seq)
> Spark SQL arrays: "explode()" fails and cannot save array type to Parquet
> -------------------------------------------------------------------------
>
> Key: SPARK-6570
> URL: https://issues.apache.org/jira/browse/SPARK-6570
> Project: Spark
> Issue Type: Bug
> Components: SQL
> Affects Versions: 1.3.0
> Reporter: Jon Chase
>
> {code}
> @Rule
> public TemporaryFolder tmp = new TemporaryFolder();
> @Test
> public void testPercentileWithExplode() throws Exception {
> StructType schema = DataTypes.createStructType(Lists.newArrayList(
> DataTypes.createStructField("col1", DataTypes.StringType,
> false),
> DataTypes.createStructField("col2s",
> DataTypes.createArrayType(DataTypes.IntegerType, true), true)
> ));
> JavaRDD<Row> rowRDD = sc.parallelize(Lists.newArrayList(
> RowFactory.create("test", new int[]{1, 2, 3})
> ));
> DataFrame df = sql.createDataFrame(rowRDD, schema);
> df.registerTempTable("df");
> df.printSchema();
> List<int[]> ints = sql.sql("select col2s from df").javaRDD()
> .map(row -> (int[]) row.get(0)).collect();
> assertEquals(1, ints.size());
> assertArrayEquals(new int[]{1, 2, 3}, ints.get(0));
> // fails: lateral view explode does not work:
> java.lang.ClassCastException: [I cannot be cast to scala.collection.Seq
> List<Integer> explodedInts = sql.sql("select col2 from df lateral
> view explode(col2s) splode as col2").javaRDD()
> .map(row -> row.getInt(0)).collect();
> assertEquals(3, explodedInts.size());
> assertEquals(Lists.newArrayList(1, 2, 3), explodedInts);
> // fails: java.lang.ClassCastException: [I cannot be cast to
> scala.collection.Seq
> df.saveAsParquetFile(tmp.getRoot().getAbsolutePath() + "/parquet");
> DataFrame loadedDf = sql.load(tmp.getRoot().getAbsolutePath() +
> "/parquet");
> loadedDf.registerTempTable("loadedDf");
> List<int[]> moreInts = sql.sql("select col2s from loadedDf").javaRDD()
> .map(row -> (int[]) row.get(0)).collect();
> assertEquals(1, moreInts.size());
> assertArrayEquals(new int[]{1, 2, 3}, moreInts.get(0));
> }
> {code}
> {code}
> root
> |-- col1: string (nullable = false)
> |-- col2s: array (nullable = true)
> | |-- element: integer (containsNull = true)
> ERROR org.apache.spark.executor.Executor Exception in task 7.0 in stage 1.0
> (TID 15)
> java.lang.ClassCastException: [I cannot be cast to scala.collection.Seq
> at
> org.apache.spark.sql.catalyst.expressions.Explode.eval(generators.scala:125)
> ~[spark-catalyst_2.10-1.3.0.jar:1.3.0]
> at
> org.apache.spark.sql.execution.Generate$$anonfun$2$$anonfun$apply$1.apply(Generate.scala:70)
> ~[spark-sql_2.10-1.3.0.jar:1.3.0]
> at
> org.apache.spark.sql.execution.Generate$$anonfun$2$$anonfun$apply$1.apply(Generate.scala:69)
> ~[spark-sql_2.10-1.3.0.jar:1.3.0]
> at scala.collection.Iterator$$anon$13.hasNext(Iterator.scala:371)
> ~[scala-library-2.10.4.jar:na]
> at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
> ~[scala-library-2.10.4.jar:na]
> at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
> ~[scala-library-2.10.4.jar:na]
> at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
> ~[scala-library-2.10.4.jar:na]
> at scala.collection.Iterator$class.foreach(Iterator.scala:727)
> ~[scala-library-2.10.4.jar:na]
> at scala.collection.AbstractIterator.foreach(Iterator.scala:1157)
> ~[scala-library-2.10.4.jar:na]
> {code}
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
