diff options
author | YanTangZhai <hakeemzhai@tencent.com> | 2014-12-18 20:13:46 -0800 |
---|---|---|
committer | Michael Armbrust <michael@databricks.com> | 2014-12-18 20:13:46 -0800 |
commit | e7de7e5f46821e1ba3b070b21d6bcf6d5ec8a796 (patch) | |
tree | c295d8cdb4286a1833ee6dcb83f0dd11c70624f7 | |
parent | 22ddb6e0338f4d101389a0655424a8fde6c4cff4 (diff) | |
download | spark-e7de7e5f46821e1ba3b070b21d6bcf6d5ec8a796.tar.gz spark-e7de7e5f46821e1ba3b070b21d6bcf6d5ec8a796.tar.bz2 spark-e7de7e5f46821e1ba3b070b21d6bcf6d5ec8a796.zip |
[SPARK-4693] [SQL] PruningPredicates may be wrong if predicates contains an empty AttributeSet() references
The sql "select * from spark_test::for_test where abs(20141202) is not null" has predicates=List(IS NOT NULL HiveSimpleUdf#org.apache.hadoop.hive.ql.udf.UDFAbs(20141202)) and
partitionKeyIds=AttributeSet(). PruningPredicates is List(IS NOT NULL HiveSimpleUdf#org.apache.hadoop.hive.ql.udf.UDFAbs(20141202)). Then the exception "java.lang.IllegalArgumentException: requirement failed: Partition pruning predicates only supported for partitioned tables." is thrown.
The sql "select * from spark_test::for_test_partitioned_table where abs(20141202) is not null and type_id=11 and platform = 3" with partitioned key insert_date has predicates=List(IS NOT NULL HiveSimpleUdf#org.apache.hadoop.hive.ql.udf.UDFAbs(20141202), (type_id#12 = 11), (platform#8 = 3)) and partitionKeyIds=AttributeSet(insert_date#24). PruningPredicates is List(IS NOT NULL HiveSimpleUdf#org.apache.hadoop.hive.ql.udf.UDFAbs(20141202)).
Author: YanTangZhai <hakeemzhai@tencent.com>
Author: yantangzhai <tyz0303@163.com>
Closes #3556 from YanTangZhai/SPARK-4693 and squashes the following commits:
620ebe3 [yantangzhai] [SPARK-4693] [SQL] PruningPredicates may be wrong if predicates contains an empty AttributeSet() references
37cfdf5 [yantangzhai] [SPARK-4693] [SQL] PruningPredicates may be wrong if predicates contains an empty AttributeSet() references
70a3544 [yantangzhai] [SPARK-4693] [SQL] PruningPredicates may be wrong if predicates contains an empty AttributeSet() references
efa9b03 [YanTangZhai] Update HiveQuerySuite.scala
72accf1 [YanTangZhai] Update HiveQuerySuite.scala
e572b9a [YanTangZhai] Update HiveStrategies.scala
6e643f8 [YanTangZhai] Merge pull request #11 from apache/master
e249846 [YanTangZhai] Merge pull request #10 from apache/master
d26d982 [YanTangZhai] Merge pull request #9 from apache/master
76d4027 [YanTangZhai] Merge pull request #8 from apache/master
03b62b0 [YanTangZhai] Merge pull request #7 from apache/master
8a00106 [YanTangZhai] Merge pull request #6 from apache/master
cbcba66 [YanTangZhai] Merge pull request #3 from apache/master
cdef539 [YanTangZhai] Merge pull request #1 from apache/master
3 files changed, 14 insertions, 2 deletions
diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/AttributeSet.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/AttributeSet.scala index 2b4969b7cf..171845ad14 100644 --- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/AttributeSet.scala +++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/AttributeSet.scala @@ -112,4 +112,6 @@ class AttributeSet private (val baseSet: Set[AttributeEquals]) override def toSeq: Seq[Attribute] = baseSet.map(_.a).toArray.toSeq override def toString = "{" + baseSet.map(_.a).mkString(", ") + "}" + + override def isEmpty: Boolean = baseSet.isEmpty } 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 5f02e95ac3..4ebd59db83 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 @@ -210,8 +210,9 @@ private[hive] trait HiveStrategies { // Filter out all predicates that only deal with partition keys, these are given to the // hive table scan operator to be used for partition pruning. val partitionKeyIds = AttributeSet(relation.partitionKeys) - val (pruningPredicates, otherPredicates) = predicates.partition { - _.references.subsetOf(partitionKeyIds) + val (pruningPredicates, otherPredicates) = predicates.partition { predicate => + !predicate.references.isEmpty && + predicate.references.subsetOf(partitionKeyIds) } pruneFilterProject( 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 63eb07c257..4d81acc753 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 @@ -411,6 +411,15 @@ class HiveQuerySuite extends HiveComparisonTest with BeforeAndAfter { createQueryTest("select null from table", "SELECT null FROM src LIMIT 1") + test("predicates contains an empty AttributeSet() references") { + sql( + """ + |SELECT a FROM ( + | SELECT 1 AS a FROM src LIMIT 1 ) table + |WHERE abs(20141202) is not null + """.stripMargin).collect() + } + test("implement identity function using case statement") { val actual = sql("SELECT (CASE key WHEN key THEN key END) FROM src") .map { case Row(i: Int) => i } |