cloud-fan commented on code in PR #45290:
URL: https://github.com/apache/spark/pull/45290#discussion_r1507922548
##########
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/UnsafeRowUtils.scala:
##########
@@ -197,4 +197,21 @@ object UnsafeRowUtils {
s"rowSizeInBytes: ${row.getSizeInBytes}\nfieldStatus:\n" +
fieldStatusArr.mkString("\n")
}
+
+ /**
+ * True if comparisons, equality and hashing can be done purely on binary
representation of
+ * Unsafe row. i.e. binary(e1) = binary(e2) <=> e1 = e2.
+ * e.g. this is not true for non-binary collations (any case/accent
insensitive collation
+ * can lead to rows being semantically equal even though their binary
representations differ).
+ */
+ def isBinaryStable(dataType: DataType): Boolean = dataType match {
+ case st: StringType =>
CollationFactory.fetchCollation(st.collationId).isBinaryCollation
+ case _: AtomicType => true
+ case _: ArrayType =>
isBinaryStable(dataType.asInstanceOf[ArrayType].elementType)
+ case _: MapType => isBinaryStable(dataType.asInstanceOf[MapType].keyType)
&&
+ isBinaryStable(dataType.asInstanceOf[MapType].valueType)
+ case _: StructType =>
Review Comment:
ditto, `case StructType(fields) => ...`
--
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
