uros-db commented on code in PR #46206:
URL: https://github.com/apache/spark/pull/46206#discussion_r1578909387
##########
common/unsafe/src/main/java/org/apache/spark/sql/catalyst/util/CollationSupport.java:
##########
@@ -214,6 +214,207 @@ public static int execICU(final UTF8String string, final
UTF8String substring,
}
}
+ public static class StringTrim {
+ public static UTF8String exec(
+ final UTF8String srcString,
+ final int collationId) {
+ CollationFactory.Collation collation =
CollationFactory.fetchCollation(collationId);
+ if (collation.supportsBinaryEquality) {
+ return execBinary(srcString);
+ } else {
+ return execICU(srcString, collationId);
+ }
+ }
+ public static UTF8String exec(
+ final UTF8String srcString,
+ final UTF8String trimString,
+ final int collationId) {
+ CollationFactory.Collation collation =
CollationFactory.fetchCollation(collationId);
+ if (collation.supportsBinaryEquality) {
+ return execBinary(srcString, trimString);
+ } else {
+ return execICU(srcString, trimString, collationId);
+ }
+ }
+ public static String genCode(
+ final String srcString,
+ final int collationId) {
+ CollationFactory.Collation collation =
CollationFactory.fetchCollation(collationId);
+ String expr = "CollationSupport.StringTrim.exec";
+ if (collation.supportsBinaryEquality) {
+ return String.format(expr + "Binary(%s)", srcString);
+ } else {
+ return String.format(expr + "ICU(%s, %d)", srcString, collationId);
+ }
+ }
+ public static String genCode(
+ final String srcString,
+ final String trimString,
+ final int collationId) {
+ CollationFactory.Collation collation =
CollationFactory.fetchCollation(collationId);
+ String expr = "CollationSupport.StringTrim.exec";
+ if (collation.supportsBinaryEquality) {
+ return String.format(expr + "Binary(%s, %s)", srcString, trimString);
+ } else {
+ return String.format(expr + "ICU(%s, %s, %d)", srcString, trimString,
collationId);
+ }
+ }
+ public static UTF8String execBinary(
+ final UTF8String srcString) {
+ return srcString.trim();
+ }
+ public static UTF8String execBinary(
+ final UTF8String srcString,
+ final UTF8String trimString) {
+ return srcString.trim(trimString);
+ }
+ public static UTF8String execICU(
+ final UTF8String srcString,
+ int collationId) {
+ return CollationAwareUTF8String.trim(srcString, collationId);
+ }
+ public static UTF8String execICU(
+ final UTF8String srcString,
+ final UTF8String trimString,
+ int collationId) {
+ return CollationAwareUTF8String.trim(srcString, trimString, collationId);
+ }
+ }
+
+ public static class StringTrimLeft {
+ public static UTF8String exec(
+ final UTF8String srcString,
+ final int collationId) {
+ CollationFactory.Collation collation =
CollationFactory.fetchCollation(collationId);
+ if (collation.supportsBinaryEquality) {
+ return execBinary(srcString);
+ } else {
+ return execICU(srcString, collationId);
+ }
Review Comment:
why do we not have an `lcase` implementation?
--
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]
