[SPARK-49775][SQL][FOLLOW-UP] Use SortedSet instead of Array with sor…

…ting ### What changes were proposed in this pull request? This PR is a followup of #48235 that addresses #48235 (comment) comment. ### Why are the changes needed? For better performance (in theory) ### Does this PR introduce _any_ user-facing change? No. ### How was this patch tested? Existing tests should verify them ### Was this patch authored or co-authored using generative AI tooling? No. Closes #48245 from HyukjinKwon/SPARK-49775-followup. Authored-by: Hyukjin Kwon <[email protected]> Signed-off-by: Dongjoon Hyun <[email protected]>
apache · Sep 25, 2024 · 09209f0 · 09209f0
1 parent 1f2e7b8
commit 09209f0
Showing 1 changed file with 3 additions and 1 deletion.
diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/CharsetProvider.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/CharsetProvider.scala
@@ -18,13 +18,15 @@
  import java.nio.charset.{Charset, CharsetDecoder, CharsetEncoder, CodingErrorAction, IllegalCharsetNameException, UnsupportedCharsetException}
  import java.util.Locale
 
+ import scala.collection.SortedSet
+
  import org.apache.spark.sql.errors.QueryExecutionErrors
  import org.apache.spark.sql.internal.SQLConf
 
 private[sql] object CharsetProvider {
 
   final lazy val VALID_CHARSETS =
-    Array("us-ascii", "iso-8859-1", "utf-8", "utf-16be", "utf-16le", "utf-16", "utf-32").sorted
+    SortedSet("us-ascii", "iso-8859-1", "utf-8", "utf-16be", "utf-16le", "utf-16", "utf-32")
 
   def forName(
       charset: String,