add fuzz test with unsupported date filtering

apache · May 15, 2024 · cdf8888 · cdf8888
1 parent 362363f
commit cdf8888
Showing 1 changed file with 6 additions and 7 deletions.
diff --git a/spark/src/test/scala/org/apache/comet/CometCastSuite.scala b/spark/src/test/scala/org/apache/comet/CometCastSuite.scala
@@ -22,6 +22,7 @@ package org.apache.comet
 import java.io.File
 
 import scala.util.Random
+import scala.util.matching.Regex
 
 import org.apache.spark.sql.{CometTestBase, DataFrame, SaveMode}
 import org.apache.spark.sql.catalyst.expressions.Cast
@@ -566,7 +567,6 @@ class CometCastSuite extends CometTestBase with AdaptiveSparkPlanHelper {
   }
 
   test("cast StringType to DateType") {
-    // https://github.com/apache/datafusion-comet/issues/327
     val validDates = Seq(
       "262142-01-01",
       "262142-01-01 ",
@@ -607,13 +607,12 @@ class CometCastSuite extends CometTestBase with AdaptiveSparkPlanHelper {
       "2020-mar-20",
       "not_a_date",
       "T2")
-    castTest((validDates ++ invalidDates).toDF("a"), DataTypes.DateType)
-  }
 
-  // due to limitations of NaiveDate we only support years between 262143 BC and 262142 AD"
-  // we can't test all possible fuzz dates
-  ignore("cast StringType to DataType - Fuzz Test") {
-    castTest(generateStrings(datePattern, 8).toDF("a"), DataTypes.DateType)
+    // due to limitations of NaiveDate we only support years between 262143 BC and 262142 AD"
+    val unsupportedYearPattern: Regex = "^\\s*[0-9]{5,}".r
+    val fuzzDates = generateStrings(datePattern, 8)
+      .filterNot(str => unsupportedYearPattern.findFirstMatchIn(str).isDefined)
+    castTest((validDates ++ invalidDates ++ fuzzDates).toDF("a"), DataTypes.DateType)
   }
 
   test("cast StringType to TimestampType disabled by default") {