support repetition of \d and \D in regexp functions (#4469)

Signed-off-by: Andy Grove <[email protected]>
NVIDIA · Jan 7, 2022 · 54c0f94 · 54c0f94
1 parent 657acd3
commit 54c0f94
Show file tree

Hide file tree

Showing 2 changed files with 19 additions and 3 deletions.
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
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2021, NVIDIA CORPORATION.
+ * Copyright (c) 2021-2022, NVIDIA CORPORATION.
  *
  * Licensed under the Apache License, Version 2.0 (the "License");
  * you may not use this file except in compliance with the License.
@@ -571,10 +571,11 @@ class CudfRegexTranspiler(replace: Boolean) {
           // example: pattern " ?", input "] b[", replace with "X":
           // java: X]XXbX[X
           // cuDF: XXXX] b[
+          // see https://github.com/NVIDIA/spark-rapids/issues/4468
           throw new RegexUnsupportedException(
             "regexp_replace on GPU does not support repetition with ? or *")
 
-        case (RegexEscaped(_), _) =>
+        case (RegexEscaped(ch), _) if ch != 'd' && ch != 'D' =>
           // example: "\B?"
           throw new RegexUnsupportedException(nothingToRepeat)
 

diff --git a/tests/src/test/scala/com/nvidia/spark/rapids/RegularExpressionTranspilerSuite.scala b/tests/src/test/scala/com/nvidia/spark/rapids/RegularExpressionTranspilerSuite.scala
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2021, NVIDIA CORPORATION.
+ * Copyright (c) 2021-2022, NVIDIA CORPORATION.
  *
  * Licensed under the Apache License, Version 2.0 (the "License");
  * you may not use this file except in compliance with the License.
@@ -232,6 +232,21 @@ class RegularExpressionTranspilerSuite extends FunSuite with Arm {
     assertCpuGpuMatchesRegexpFind(patterns, inputs)
   }
 
+  test("compare CPU and GPU: find digits") {
+    val patterns = Seq("\\d", "\\d+", "\\d*", "\\d?",
+      "\\D", "\\D+", "\\D*", "\\D?")
+    val inputs = Seq("a", "1", "12", "a12z", "1az2")
+    assertCpuGpuMatchesRegexpFind(patterns, inputs)
+  }
+
+  test("compare CPU and GPU: replace digits") {
+    // note that we do not test with quantifiers `?` or `*` due
+    // to https://github.com/NVIDIA/spark-rapids/issues/4468
+    val patterns = Seq("\\d", "\\d+", "\\D", "\\D+")
+    val inputs = Seq("a", "1", "12", "a12z", "1az2")
+    assertCpuGpuMatchesRegexpReplace(patterns, inputs)
+  }
+
   private val REGEXP_LIMITED_CHARS = "|()[]{},.^$*+?abc123x\\ \tBsdwSDW"
 
   test("compare CPU and GPU: regexp find fuzz test with limited chars") {