nikolamand-db commented on code in PR #46104:
URL: https://github.com/apache/spark/pull/46104#discussion_r1568653835
##########
common/unsafe/src/main/java/org/apache/spark/sql/catalyst/util/CollationSupport.java:
##########
@@ -137,6 +140,105 @@ public static boolean execICU(final UTF8String l, final
UTF8String r,
}
}
+ public static class Upper {
+ public static UTF8String exec(final UTF8String v, final int collationId) {
+ CollationFactory.Collation collation =
CollationFactory.fetchCollation(collationId);
+ if (collation.supportsBinaryEquality) {
+ return execBinary(v);
+ } else if (collation.supportsLowercaseEquality) {
+ return execLowercase(v);
+ } else {
+ return execICU(v, collationId);
+ }
+ }
+ public static String genCode(final String v, final int collationId) {
+ CollationFactory.Collation collation =
CollationFactory.fetchCollation(collationId);
+ String expr = "CollationSupport.Upper.exec";
+ if (collation.supportsBinaryEquality) {
+ return String.format(expr + "Binary(%s)", v);
+ } else if (collation.supportsLowercaseEquality) {
+ return String.format(expr + "Lowercase(%s)", v);
+ } else {
+ return String.format(expr + "ICU(%s, %d)", v, collationId);
+ }
+ }
+ public static UTF8String execBinary(final UTF8String v) {
+ return v.toUpperCase();
+ }
+ public static UTF8String execLowercase(final UTF8String v) {
+ return v.toUpperCase();
+ }
+ public static UTF8String execICU(final UTF8String v, final int
collationId) {
+ return CollationAwareUTF8String.toUpperCase(v, collationId);
+ }
+ }
+
+ public static class Lower {
+ public static UTF8String exec(final UTF8String v, final int collationId) {
+ CollationFactory.Collation collation =
CollationFactory.fetchCollation(collationId);
+ if (collation.supportsBinaryEquality) {
+ return execBinary(v);
+ } else if (collation.supportsLowercaseEquality) {
+ return execLowercase(v);
+ } else {
+ return execICU(v, collationId);
+ }
+ }
+ public static String genCode(final String v, final int collationId) {
+ CollationFactory.Collation collation =
CollationFactory.fetchCollation(collationId);
+ String expr = "CollationSupport.Upper.exec";
Review Comment:
```suggestion
String expr = "CollationSupport.Lower.exec";
```
##########
common/unsafe/src/main/java/org/apache/spark/sql/catalyst/util/CollationSupport.java:
##########
@@ -16,7 +16,10 @@
*/
package org.apache.spark.sql.catalyst.util;
+import com.ibm.icu.lang.UCharacter;
import com.ibm.icu.text.StringSearch;
+import com.ibm.icu.text.Transliterator;
Review Comment:
Is this used anywhere?
##########
common/unsafe/src/main/java/org/apache/spark/sql/catalyst/util/CollationSupport.java:
##########
@@ -137,6 +140,105 @@ public static boolean execICU(final UTF8String l, final
UTF8String r,
}
}
+ public static class Upper {
+ public static UTF8String exec(final UTF8String v, final int collationId) {
+ CollationFactory.Collation collation =
CollationFactory.fetchCollation(collationId);
+ if (collation.supportsBinaryEquality) {
+ return execBinary(v);
+ } else if (collation.supportsLowercaseEquality) {
+ return execLowercase(v);
+ } else {
+ return execICU(v, collationId);
+ }
+ }
+ public static String genCode(final String v, final int collationId) {
+ CollationFactory.Collation collation =
CollationFactory.fetchCollation(collationId);
+ String expr = "CollationSupport.Upper.exec";
+ if (collation.supportsBinaryEquality) {
+ return String.format(expr + "Binary(%s)", v);
+ } else if (collation.supportsLowercaseEquality) {
+ return String.format(expr + "Lowercase(%s)", v);
+ } else {
+ return String.format(expr + "ICU(%s, %d)", v, collationId);
+ }
+ }
+ public static UTF8String execBinary(final UTF8String v) {
+ return v.toUpperCase();
+ }
+ public static UTF8String execLowercase(final UTF8String v) {
+ return v.toUpperCase();
+ }
+ public static UTF8String execICU(final UTF8String v, final int
collationId) {
+ return CollationAwareUTF8String.toUpperCase(v, collationId);
+ }
+ }
+
+ public static class Lower {
+ public static UTF8String exec(final UTF8String v, final int collationId) {
+ CollationFactory.Collation collation =
CollationFactory.fetchCollation(collationId);
+ if (collation.supportsBinaryEquality) {
+ return execBinary(v);
+ } else if (collation.supportsLowercaseEquality) {
+ return execLowercase(v);
+ } else {
+ return execICU(v, collationId);
+ }
+ }
+ public static String genCode(final String v, final int collationId) {
+ CollationFactory.Collation collation =
CollationFactory.fetchCollation(collationId);
+ String expr = "CollationSupport.Upper.exec";
+ if (collation.supportsBinaryEquality) {
+ return String.format(expr + "Binary(%s)", v);
+ } else if (collation.supportsLowercaseEquality) {
+ return String.format(expr + "Lowercase(%s)", v);
+ } else {
+ return String.format(expr + "ICU(%s, %d)", v, collationId);
+ }
+ }
+ public static UTF8String execBinary(final UTF8String v) {
+ return v.toLowerCase();
+ }
+ public static UTF8String execLowercase(final UTF8String v) {
+ return v.toLowerCase();
+ }
+ public static UTF8String execICU(final UTF8String v, final int
collationId) {
+ return CollationAwareUTF8String.toLowerCase(v, collationId);
+ }
+ }
+
+ public static class InitCap {
+ public static UTF8String exec(final UTF8String v, final int collationId) {
+ CollationFactory.Collation collation =
CollationFactory.fetchCollation(collationId);
+ if (collation.supportsBinaryEquality) {
+ return execBinary(v);
+ } else if (collation.supportsLowercaseEquality) {
+ return execLowercase(v);
+ } else {
+ return execICU(v, collationId);
+ }
+ }
+ public static String genCode(final String v, final int collationId) {
+ CollationFactory.Collation collation =
CollationFactory.fetchCollation(collationId);
+ String expr = "CollationSupport.Upper.exec";
Review Comment:
```suggestion
String expr = "CollationSupport.InitCap.exec";
```
--
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]
