stefankandic commented on code in PR #47502:
URL: https://github.com/apache/spark/pull/47502#discussion_r1693213018
##########
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/hash.scala:
##########
@@ -565,7 +565,15 @@ abstract class InterpretedHashFunction {
case a: Array[Byte] =>
hashUnsafeBytes(a, Platform.BYTE_ARRAY_OFFSET, a.length, seed)
case s: UTF8String =>
- hashUnsafeBytes(s.getBaseObject, s.getBaseOffset, s.numBytes(), seed)
+ dataType match {
Review Comment:
this code doesn't seem properly formatted
##########
sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/HashExpressionsSuite.scala:
##########
@@ -620,6 +620,33 @@ class HashExpressionsSuite extends SparkFunSuite with
ExpressionEvalHelper {
checkHiveHashForDecimal("123456.123456789012345678901234567890", 38, 31,
1728235666)
}
+ for (collation <- Seq("UTF8_LCASE", "UNICODE_CI")) {
+ test(s"hash equality for collated $collation strings") {
+ val s1 = "aaa"
+ val s2 = "AAA"
+
+ // Interpreted hash value for s1
+ val hash = Murmur3Hash(Seq(Collate(Literal(s1), collation)), 42).eval()
+
+ // Check if interpreted hash value is same as codegen for s1
Review Comment:
won't this check for both codegen and interpreted path for s1?
##########
sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/HashExpressionsSuite.scala:
##########
@@ -620,6 +620,33 @@ class HashExpressionsSuite extends SparkFunSuite with
ExpressionEvalHelper {
checkHiveHashForDecimal("123456.123456789012345678901234567890", 38, 31,
1728235666)
}
+ for (collation <- Seq("UTF8_LCASE", "UNICODE_CI")) {
+ test(s"hash equality for collated $collation strings") {
+ val s1 = "aaa"
+ val s2 = "AAA"
+
+ // Interpreted hash value for s1
+ val hash = Murmur3Hash(Seq(Collate(Literal(s1), collation)), 42).eval()
Review Comment:
```suggestion
val interpretedHash = Murmur3Hash(Seq(Collate(Literal(s1),
collation)), 42).eval()
```
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
