(auron) branch master updated: [AURON #1845] Fix StringSplit conversion (#1846)

[richox]

This is an automated email from the ASF dual-hosted git repository.

richox pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/auron.git


The following commit(s) were added to refs/heads/master by this push:
     new ac1774f4 [AURON #1845] Fix StringSplit conversion (#1846)
ac1774f4 is described below

commit ac1774f46635b8a262e99d6a952e3a855c0e27ab
Author: Flyangz <flyang...@126.com>
AuthorDate: Sat Jan 17 14:30:12 2026 +0800

    [AURON #1845] Fix StringSplit conversion (#1846)
    
    # Which issue does this PR close?
    
    Closes #1845
    
    # Rationale for this change
    before: `ProjectExec [UDFWrapper(split(col1#1, ,, -1)[0]) AS #5],
    schema=[#5:Utf8;N]`
    after: `ProjectExec [(spark_ext_function_Spark_StringSplit(#1@0, ,)).[1]
    AS #5], schema=[#5:Utf8;N]`
    
    # What changes are included in this PR?
    
    # Are there any user-facing changes?
    
    # How was this patch tested?
---
 .../src/main/scala/org/apache/spark/sql/auron/ShimsImpl.scala | 11 +++++------
 1 file changed, 5 insertions(+), 6 deletions(-)

diff --git 
a/spark-extension-shims-spark/src/main/scala/org/apache/spark/sql/auron/ShimsImpl.scala
 
b/spark-extension-shims-spark/src/main/scala/org/apache/spark/sql/auron/ShimsImpl.scala
index 9cecb869..d0667164 100644
--- 
a/spark-extension-shims-spark/src/main/scala/org/apache/spark/sql/auron/ShimsImpl.scala
+++ 
b/spark-extension-shims-spark/src/main/scala/org/apache/spark/sql/auron/ShimsImpl.scala
@@ -102,9 +102,7 @@ import 
org.apache.spark.sql.execution.joins.auron.plan.NativeSortMergeJoinExecPr
 import org.apache.spark.sql.execution.metric.{SQLMetric, 
SQLShuffleReadMetricsReporter}
 import org.apache.spark.sql.execution.ui.{AuronEventUtils, 
AuronSQLAppStatusListener, AuronSQLAppStatusStore, AuronSQLTab}
 import org.apache.spark.sql.hive.execution.InsertIntoHiveTable
-import org.apache.spark.sql.types.DataType
-import org.apache.spark.sql.types.IntegerType
-import org.apache.spark.sql.types.StringType
+import org.apache.spark.sql.types.{ArrayType, DataType, IntegerType, 
StringType}
 import org.apache.spark.status.ElementTrackingStore
 import org.apache.spark.storage.BlockManagerId
 import org.apache.spark.storage.FileSegment
@@ -524,8 +522,9 @@ class ShimsImpl extends Shims with Logging {
       case StringSplit(str, pat @ Literal(_, StringType), Literal(-1, 
IntegerType))
           // native StringSplit implementation does not support regex, so only 
most frequently
           // used cases without regex are supported
-          if Seq(",", ", ", ":", ";", "#", "@", "_", "-", "\\|", 
"\\.").contains(pat.value) =>
-        val nativePat = pat.value match {
+          if Seq(",", ", ", ":", ";", "#", "@", "_", "-", "\\|", 
"\\.").contains(
+            pat.value.toString) =>
+        val nativePat = pat.value.toString match {
           case "\\|" => "|"
           case "\\." => "."
           case other => other
@@ -541,7 +540,7 @@ class ShimsImpl extends Shims with Logging {
                 .addArgs(NativeConverters.convertExprWithFallback(str, 
isPruningExpr, fallback))
                 .addArgs(NativeConverters
                   .convertExprWithFallback(Literal(nativePat), isPruningExpr, 
fallback))
-                .setReturnType(NativeConverters.convertDataType(StringType)))
+                
.setReturnType(NativeConverters.convertDataType(ArrayType(StringType))))
             .build())
 
       case e: TaggingExpression =>