fix test failure

apache · May 4, 2024 · c62a7b0 · c62a7b0
1 parent 9cdb571
commit c62a7b0
Show file tree

Hide file tree

Showing 3 changed files with 18 additions and 3 deletions.
diff --git a/spark/src/main/scala/org/apache/comet/expressions/CometCast.scala b/spark/src/main/scala/org/apache/comet/expressions/CometCast.scala
@@ -148,7 +148,7 @@ object CometCast {
               "instead of 1.4E-45"))
       case DataTypes.BinaryType =>
         // https://github.com/apache/datafusion-comet/issues/377
-        Unsupported
+        Incompatible(Some("Only works for binary data representing valid UTF-8 strings"))
       case _ => Unsupported
     }
   }

diff --git a/spark/src/test/scala/org/apache/comet/CometCastSuite.scala b/spark/src/test/scala/org/apache/comet/CometCastSuite.scala
@@ -623,8 +623,12 @@ class CometCastSuite extends CometTestBase with AdaptiveSparkPlanHelper {
   // CAST from BinaryType
 
   ignore("cast BinaryType to StringType") {
-    // TODO implement this
     // https://github.com/apache/datafusion-comet/issues/377
+    castTest(generateBinary(), DataTypes.StringType)
+  }
+
+  test("cast BinaryType to StringType - valid UTF-8 inputs") {
+    castTest(generateStrings(numericPattern, 8).toDF("a"), DataTypes.StringType)
   }
 
   // CAST from DateType
@@ -831,6 +835,16 @@ class CometCastSuite extends CometTestBase with AdaptiveSparkPlanHelper {
     Range(0, dataSize).map(_ => generateString(r, chars, maxLen))
   }
 
+  private def generateBinary(): DataFrame = {
+    val r = new Random(0)
+    val bytes = new Array[Byte](8)
+    val values: Seq[Array[Byte]] = Range(0, dataSize).map(_ => {
+      r.nextBytes(bytes)
+      bytes.clone()
+    })
+    values.toDF("a")
+  }
+
   private def withNulls[T](values: Seq[T]): Seq[Option[T]] = {
     values.map(v => Some(v)) ++ Seq(None)
   }

diff --git a/spark/src/test/scala/org/apache/comet/exec/CometExecSuite.scala b/spark/src/test/scala/org/apache/comet/exec/CometExecSuite.scala
@@ -253,7 +253,8 @@ class CometExecSuite extends CometTestBase {
     dataTypes.map { subqueryType =>
       withSQLConf(
         CometConf.COMET_EXEC_SHUFFLE_ENABLED.key -> "true",
-        CometConf.COMET_COLUMNAR_SHUFFLE_ENABLED.key -> "true") {
+        CometConf.COMET_COLUMNAR_SHUFFLE_ENABLED.key -> "true",
+        CometConf.COMET_CAST_ALLOW_INCOMPATIBLE.key -> "true") {
         withParquetTable((0 until 5).map(i => (i, i + 1)), "tbl") {
           var column1 = s"CAST(max(_1) AS $subqueryType)"
           if (subqueryType == "BINARY") {