mkaravel commented on code in PR #46732:
URL: https://github.com/apache/spark/pull/46732#discussion_r1616427922
##########
common/unsafe/src/test/java/org/apache/spark/unsafe/types/CollationSupportSuite.java:
##########
@@ -526,10 +526,40 @@ public void testInitCap() throws SparkException {
assertInitCap("aB 世 de", "UNICODE_CI", "Ab 世 De");
assertInitCap("ÄBĆΔE", "UNICODE_CI", "Äbćδe");
// Case-variable character length
- assertInitCap("İo", "UTF8_BINARY", "İo");
- assertInitCap("İo", "UTF8_BINARY_LCASE", "İo");
- assertInitCap("İo", "UNICODE", "İo");
- assertInitCap("İo", "UNICODE_CI", "İo");
+ assertInitCap("İo", "UTF8_BINARY", "I\u0307o");
+ assertInitCap("İo", "UTF8_BINARY_LCASE", "İo");
+ assertInitCap("İo", "UNICODE", "I\u0307o");
Review Comment:
I don't understand why this has changed. It should not have.
##########
common/unsafe/src/test/java/org/apache/spark/unsafe/types/CollationSupportSuite.java:
##########
@@ -526,10 +526,40 @@ public void testInitCap() throws SparkException {
assertInitCap("aB 世 de", "UNICODE_CI", "Ab 世 De");
assertInitCap("ÄBĆΔE", "UNICODE_CI", "Äbćδe");
// Case-variable character length
- assertInitCap("İo", "UTF8_BINARY", "İo");
- assertInitCap("İo", "UTF8_BINARY_LCASE", "İo");
- assertInitCap("İo", "UNICODE", "İo");
- assertInitCap("İo", "UNICODE_CI", "İo");
+ assertInitCap("İo", "UTF8_BINARY", "I\u0307o");
+ assertInitCap("İo", "UTF8_BINARY_LCASE", "İo");
+ assertInitCap("İo", "UNICODE", "I\u0307o");
+ assertInitCap("İo", "UNICODE_CI", "İo");
+ assertInitCap("i\u0307o", "UTF8_BINARY", "I\u0307o");
+ assertInitCap("i\u0307o", "UTF8_BINARY_LCASE", "I\u0307o");
+ assertInitCap("i\u0307o", "UNICODE", "I\u0307o");
+ assertInitCap("i\u0307o", "UNICODE_CI", "I\u0307o");
+ // Different possible word boundaries
+ assertInitCap("a b c", "UTF8_BINARY", "A B C");
+ assertInitCap("a b c", "UNICODE", "A B C");
+ assertInitCap("a b c", "UTF8_BINARY_LCASE", "A B C");
+ assertInitCap("a b c", "UNICODE_CI", "A B C");
+ assertInitCap("a.b,c", "UTF8_BINARY", "A.b,c");
+ assertInitCap("a.b,c", "UNICODE", "A.b,c");
+ assertInitCap("a.b,c", "UTF8_BINARY_LCASE", "A.b,C");
+ assertInitCap("a.b,c", "UNICODE_CI", "A.b,C");
Review Comment:
I don't understand why the CI versions capitalize `c` but the non-CI ones do
not.
##########
common/unsafe/src/test/java/org/apache/spark/unsafe/types/CollationSupportSuite.java:
##########
@@ -526,10 +526,40 @@ public void testInitCap() throws SparkException {
assertInitCap("aB 世 de", "UNICODE_CI", "Ab 世 De");
assertInitCap("ÄBĆΔE", "UNICODE_CI", "Äbćδe");
// Case-variable character length
- assertInitCap("İo", "UTF8_BINARY", "İo");
- assertInitCap("İo", "UTF8_BINARY_LCASE", "İo");
- assertInitCap("İo", "UNICODE", "İo");
- assertInitCap("İo", "UNICODE_CI", "İo");
+ assertInitCap("İo", "UTF8_BINARY", "I\u0307o");
+ assertInitCap("İo", "UTF8_BINARY_LCASE", "İo");
+ assertInitCap("İo", "UNICODE", "I\u0307o");
+ assertInitCap("İo", "UNICODE_CI", "İo");
+ assertInitCap("i\u0307o", "UTF8_BINARY", "I\u0307o");
+ assertInitCap("i\u0307o", "UTF8_BINARY_LCASE", "I\u0307o");
+ assertInitCap("i\u0307o", "UNICODE", "I\u0307o");
+ assertInitCap("i\u0307o", "UNICODE_CI", "I\u0307o");
+ // Different possible word boundaries
+ assertInitCap("a b c", "UTF8_BINARY", "A B C");
+ assertInitCap("a b c", "UNICODE", "A B C");
+ assertInitCap("a b c", "UTF8_BINARY_LCASE", "A B C");
+ assertInitCap("a b c", "UNICODE_CI", "A B C");
+ assertInitCap("a.b,c", "UTF8_BINARY", "A.b,c");
+ assertInitCap("a.b,c", "UNICODE", "A.b,c");
+ assertInitCap("a.b,c", "UTF8_BINARY_LCASE", "A.b,C");
+ assertInitCap("a.b,c", "UNICODE_CI", "A.b,C");
+ assertInitCap("a. b-c", "UTF8_BINARY", "A. B-c");
+ assertInitCap("a. b-c", "UNICODE", "A. B-c");
+ assertInitCap("a. b-c", "UTF8_BINARY_LCASE", "A. B-C");
+ assertInitCap("a. b-c", "UNICODE_CI", "A. B-C");
+ assertInitCap("a?b世c", "UTF8_BINARY", "A?b世c");
+ assertInitCap("a?b世c", "UNICODE", "A?b世c");
+ assertInitCap("a?b世c", "UTF8_BINARY_LCASE", "A?B世C");
+ assertInitCap("a?b世c", "UNICODE_CI", "A?B世C");
Review Comment:
And here.
##########
common/unsafe/src/test/java/org/apache/spark/unsafe/types/CollationSupportSuite.java:
##########
@@ -526,10 +526,40 @@ public void testInitCap() throws SparkException {
assertInitCap("aB 世 de", "UNICODE_CI", "Ab 世 De");
assertInitCap("ÄBĆΔE", "UNICODE_CI", "Äbćδe");
// Case-variable character length
- assertInitCap("İo", "UTF8_BINARY", "İo");
- assertInitCap("İo", "UTF8_BINARY_LCASE", "İo");
- assertInitCap("İo", "UNICODE", "İo");
- assertInitCap("İo", "UNICODE_CI", "İo");
+ assertInitCap("İo", "UTF8_BINARY", "I\u0307o");
+ assertInitCap("İo", "UTF8_BINARY_LCASE", "İo");
+ assertInitCap("İo", "UNICODE", "I\u0307o");
+ assertInitCap("İo", "UNICODE_CI", "İo");
+ assertInitCap("i\u0307o", "UTF8_BINARY", "I\u0307o");
+ assertInitCap("i\u0307o", "UTF8_BINARY_LCASE", "I\u0307o");
+ assertInitCap("i\u0307o", "UNICODE", "I\u0307o");
+ assertInitCap("i\u0307o", "UNICODE_CI", "I\u0307o");
+ // Different possible word boundaries
+ assertInitCap("a b c", "UTF8_BINARY", "A B C");
+ assertInitCap("a b c", "UNICODE", "A B C");
+ assertInitCap("a b c", "UTF8_BINARY_LCASE", "A B C");
+ assertInitCap("a b c", "UNICODE_CI", "A B C");
+ assertInitCap("a.b,c", "UTF8_BINARY", "A.b,c");
+ assertInitCap("a.b,c", "UNICODE", "A.b,c");
+ assertInitCap("a.b,c", "UTF8_BINARY_LCASE", "A.b,C");
+ assertInitCap("a.b,c", "UNICODE_CI", "A.b,C");
+ assertInitCap("a. b-c", "UTF8_BINARY", "A. B-c");
+ assertInitCap("a. b-c", "UNICODE", "A. B-c");
+ assertInitCap("a. b-c", "UTF8_BINARY_LCASE", "A. B-C");
+ assertInitCap("a. b-c", "UNICODE_CI", "A. B-C");
Review Comment:
Same here.
--
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: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
