[SPARK-12480][SQL] add Hash expression that can calculate hash value for a group of expressions

just write the arguments into unsafe row and use murmur3 to calculate hash code

Author: Wenchen Fan <wenchen@databricks.com>

Closes #10435 from cloud-fan/hash-expr.

1 files changed, 3 insertions, 0 deletions

diff --git a/sql/hive/compatibility/src/test/scala/org/apache/spark/sql/hive/execution/HiveCompatibilitySuite.scala b/sql/hive/compatibility/src/test/scala/org/apache/spark/sql/hive/execution/HiveCompatibilitySuite.scala
index 2b0e48dbfc..bd1a52e5f3 100644
--- a/sql/hive/compatibility/src/test/scala/org/apache/spark/sql/hive/execution/HiveCompatibilitySuite.scala
+++ b/sql/hive/compatibility/src/test/scala/org/apache/spark/sql/hive/execution/HiveCompatibilitySuite.scala
@@ -53,6 +53,8 @@ class HiveCompatibilitySuite extends HiveQueryFileTest with BeforeAndAfter {
     TestHive.setConf(SQLConf.COLUMN_BATCH_SIZE, 5)
     // Enable in-memory partition pruning for testing purposes
     TestHive.setConf(SQLConf.IN_MEMORY_PARTITION_PRUNING, true)
+    // Use Hive hash expression instead of the native one
+    TestHive.functionRegistry.unregisterFunction("hash")
     RuleExecutor.resetTime()
   }
 
@@ -62,6 +64,7 @@ class HiveCompatibilitySuite extends HiveQueryFileTest with BeforeAndAfter {
     Locale.setDefault(originalLocale)
     TestHive.setConf(SQLConf.COLUMN_BATCH_SIZE, originalColumnBatchSize)
     TestHive.setConf(SQLConf.IN_MEMORY_PARTITION_PRUNING, originalInMemoryPartitionPruning)
+    TestHive.functionRegistry.restore()
 
     // For debugging dump some statistics about how much time was spent in various optimizer rules.
     logWarning(RuleExecutor.dumpTimeSpent())