revert removing check that was not redundant after all

NVIDIA · Nov 9, 2021 · 62992b1 · 62992b1
1 parent 65bad0f
commit 62992b1
Show file tree

Hide file tree

Showing 2 changed files with 10 additions and 1 deletion.
diff --git a/sql-plugin/src/main/scala/com/nvidia/spark/rapids/RegexParser.scala b/sql-plugin/src/main/scala/com/nvidia/spark/rapids/RegexParser.scala
@@ -462,6 +462,10 @@ class CudfRegexTranspiler {
         }
 
       case RegexSequence(parts) =>
+        if (isRegexChar(parts.head, '|') || isRegexChar(parts.last, '|')) {
+          // examples: "a|", "|b"
+          throw new RegexUnsupportedException(nothingToRepeat)
+        }
         if (isRegexChar(parts.head, '{')) {
           // example: "{"
           // cuDF would treat this as a quantifier even though in this

diff --git a/tests/src/test/scala/com/nvidia/spark/rapids/RegularExpressionTranspilerSuite.scala b/tests/src/test/scala/com/nvidia/spark/rapids/RegularExpressionTranspilerSuite.scala
@@ -233,7 +233,12 @@ class RegularExpressionTranspilerSuite extends FunSuite with Arm {
     for (javaPattern <- javaPatterns) {
       val cpu = cpuContains(javaPattern, input)
       val cudfPattern = new CudfRegexTranspiler().transpile(javaPattern)
-      val gpu = gpuContains(cudfPattern, input)
+      val gpu = try {
+        gpuContains(cudfPattern, input)
+      } catch {
+        case e: CudfException =>
+          fail(s"cuDF failed to compile pattern: $cudfPattern", e)
+      }
       for (i <- input.indices) {
         if (cpu(i) != gpu(i)) {
           fail(s"javaPattern=${toReadableString(javaPattern)}, " +