Github user tejasapatil commented on a diff in the pull request: https://github.com/apache/spark/pull/17062#discussion_r103300013 --- Diff: sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/HashExpressionsSuite.scala --- @@ -169,6 +171,96 @@ class HashExpressionsSuite extends SparkFunSuite with ExpressionEvalHelper { // scalastyle:on nonascii } + test("hive-hash for date type") { + def checkHiveHashForDateType(dateString: String, expected: Long): Unit = { + checkHiveHash( + DateTimeUtils.stringToDate(UTF8String.fromString(dateString)).get, + DateType, + expected) + } + + // basic case + checkHiveHashForDateType("2017-01-01", 17167) + + // boundary cases + checkHiveHashForDateType("0000-01-01", -719530) + checkHiveHashForDateType("9999-12-31", 2932896) + + // epoch + checkHiveHashForDateType("1970-01-01", 0) + + // before epoch + checkHiveHashForDateType("1800-01-01", -62091) + + // Invalid input: bad date string. Hive returns 0 for such cases --- End diff -- Spark does not allow creating `Date` which do not fit its spec and throws exception. Hive will not fail but fallback to `null` and return `0` as hash value.
--- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your project does not have this feature enabled and wishes so, or if the feature is enabled but not working, please contact infrastructure at infrastruct...@apache.org or file a JIRA ticket with INFRA. --- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org