[HIVE-10532] SpecificMutableRow doesn't handle Date Type correctly

• Type: Bug
• Status: Resolved
• Priority: Major
• Resolution: Invalid
• Assignee: Unassigned
• Reporter: Cheng Hao
• Created: 29/Apr/15 07:45
• Updated: 29/Apr/15 07:46
• Resolved: 29/Apr/15 07:46

Description

  test("test DATE types in cache") {
    val rows = TestSQLContext.jdbc(urlWithUserAndPass, "TEST.TIMETYPES").collect()
    TestSQLContext.jdbc(urlWithUserAndPass, "TEST.TIMETYPES").cache().registerTempTable("mycached_date")
    val cachedRows = sql("select * from mycached_date").collect()
    assert(rows(0).getAs[java.sql.Date](1) === java.sql.Date.valueOf("1996-01-01"))
    assert(cachedRows(0).getAs[java.sql.Date](1) === java.sql.Date.valueOf("1996-01-01"))
  }

java.lang.ClassCastException: org.apache.spark.sql.catalyst.expressions.MutableAny cannot be cast to org.apache.spark.sql.catalyst.expressions.MutableInt
at org.apache.spark.sql.catalyst.expressions.SpecificMutableRow.getInt(SpecificMutableRow.scala:252)
at org.apache.spark.sql.columnar.IntColumnStats.gatherStats(ColumnStats.scala:208)
at org.apache.spark.sql.columnar.NullableColumnBuilder$class.appendFrom(NullableColumnBuilder.scala:56)
at org.apache.spark.sql.columnar.NativeColumnBuilder.org$apache$spark$sql$columnar$compression$CompressibleColumnBuilder$$super$appendFrom(ColumnBuilder.scala:87)
at org.apache.spark.sql.columnar.compression.CompressibleColumnBuilder$class.appendFrom(CompressibleColumnBuilder.scala:78)
at org.apache.spark.sql.columnar.NativeColumnBuilder.appendFrom(ColumnBuilder.scala:87)
at org.apache.spark.sql.columnar.InMemoryRelation$$anonfun$3$$anon$1.next(InMemoryColumnarTableScan.scala:148)
at org.apache.spark.sql.columnar.InMemoryRelation$$anonfun$3$$anon$1.next(InMemoryColumnarTableScan.scala:124)
at org.apache.spark.storage.MemoryStore.unrollSafely(MemoryStore.scala:277)
at org.apache.spark.CacheManager.putInBlockManager(CacheManager.scala:171)
at org.apache.spark.CacheManager.getOrCompute(CacheManager.scala:78)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:242)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:277)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:244)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:277)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:244)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:63)
at org.apache.spark.scheduler.Task.run(Task.scala:64)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:209)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1110)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:603)
at java.lang.Thread.run(Thread.java:722)