Fix ClassCastException in regular expression transpiler (#5506)

NVIDIA · May 18, 2022 · c0fe6e4 · c0fe6e4
1 parent dbca151
commit c0fe6e4
Show file tree

Hide file tree

Showing 2 changed files with 21 additions and 4 deletions.
diff --git a/integration_tests/src/main/python/string_test.py b/integration_tests/src/main/python/string_test.py
@@ -547,6 +547,16 @@ def test_re_replace():
                 'REGEXP_REPLACE(a, "TEST", NULL)'),
         conf=_regexp_conf)
 
+@allow_non_gpu('ProjectExec', 'RegExpReplace')
+def test_re_replace_issue_5492():
+    # https://github.com/NVIDIA/spark-rapids/issues/5492
+    gen = mk_str_gen('.{0,5}TEST[\ud720 A]{0,5}')
+    assert_gpu_fallback_collect(
+        lambda spark: unary_op_df(spark, gen).selectExpr(
+            'REGEXP_REPLACE(a, "[^\\\\sa-zA-Z0-9]", "x")'),
+        'RegExpReplace',
+        conf=_regexp_conf)
+
 def test_re_replace_backrefs():
     gen = mk_str_gen('.{0,5}TEST[\ud720 A]{0,5}TEST')
     assert_gpu_and_cpu_are_equal_collect(

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
@@ -846,10 +846,17 @@ class CudfRegexTranspiler(mode: RegexMode) {
           case _ =>
         }
         val components: Seq[RegexCharacterClassComponent] = characters
-          .map(x => x match {
-            case RegexChar(ch) if "^$".contains(ch) => x
-            case _ => rewrite(x, replacement, None).asInstanceOf[RegexCharacterClassComponent]
-          })
+          .map {
+            case r @ RegexChar(ch) if "^$".contains(ch) => r
+            case ch => rewrite(ch, replacement, None) match {
+              case valid: RegexCharacterClassComponent => valid
+              case _ =>
+                // this can happen when a character class contains a meta-sequence such as
+                // `\s` that gets transpiled into another character class
+                throw new RegexUnsupportedException("Character class contains one or more " +
+                  "characters that cannot be transpiled to supported character-class components")
+            }
+          }
 
         if (negated) {
           // There are differences between cuDF and Java handling of newlines