cloud-fan commented on code in PR #44110:
URL: https://github.com/apache/spark/pull/44110#discussion_r1414260156
##########
sql/api/src/main/scala/org/apache/spark/sql/catalyst/util/SparkDateTimeUtils.scala:
##########
@@ -305,21 +305,32 @@ trait SparkDateTimeUtils {
(segment == 0 && digits >= 4 && digits <= maxDigitsYear) ||
(segment != 0 && digits > 0 && digits <= 2)
}
- if (s == null || s.trimAll().numBytes() == 0) {
+ if (s == null) {
return None
}
+
val segments: Array[Int] = Array[Int](1, 1, 1)
var sign = 1
var i = 0
var currentSegmentValue = 0
var currentSegmentDigits = 0
- val bytes = s.trimAll().getBytes
+ val bytes = s.getBytes
var j = 0
+
+ while (j < bytes.length && UTF8String.isWhitespaceOrISOControl(bytes(j))) {
+ j += 1;
+ }
+
+ if (j == bytes.length) {
+ return None;
+ }
+
if (bytes(j) == '-' || bytes(j) == '+') {
sign = if (bytes(j) == '-') -1 else 1
j += 1
}
- while (j < bytes.length && (i < 3 && !(bytes(j) == ' ' || bytes(j) ==
'T'))) {
+ while (j < bytes.length &&
+ (i < 3 && !(UTF8String.isWhitespaceOrISOControl(bytes(j)) || bytes(j) ==
'T'))) {
Review Comment:
Let's not change any behavior but only improve the perf. i.e. only allow ' '
and 'T' in the middle.
--
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
