Replace toTitle with capitalize for GpuInitCap

integration_tests/src/main/python/string_test.py

@@ -1,4 +1,4 @@
-# Copyright (c) 2020, NVIDIA CORPORATION.
+# Copyright (c) 2020-2021, NVIDIA CORPORATION.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -314,23 +314,12 @@ def test_length():
                 'CHAR_LENGTH(a)',
                 'CHARACTER_LENGTH(a)'))
 
-# Once the xfail is fixed this can replace test_initcap_space
-@incompat
-@pytest.mark.xfail(reason='https://github.com/NVIDIA/spark-rapids/issues/120')
 def test_initcap():
     # Because we don't use the same unicode version we need to limit
     # the charicter set to something more reasonable
     # upper and lower should cover the corner cases, this is mostly to
     # see if there are issues with spaces
-    gen = mk_str_gen('([aAbB]{0,5}[ \r\n\t]{1,2}){1,5}')
-    assert_gpu_and_cpu_are_equal_collect(
-            lambda spark: unary_op_df(spark, gen).select(
-                f.initcap(f.col('a'))))
-
-@incompat
-def test_initcap_space():
-    # we see a lot more space delim
-    gen = StringGen('([aAbB]{0,5}[ ]{1,2}){1,5}')
+    gen = mk_str_gen('([aAbB1357_@%-ȺéʼnŸ]{0,16}[ \r\n\t]{1,2}){1,5}')
     assert_gpu_and_cpu_are_equal_collect(
             lambda spark: unary_op_df(spark, gen).select(
                 f.initcap(f.col('a'))))

sql-plugin/src/main/scala/com/nvidia/spark/rapids/GpuOverrides.scala

@@ -432,10 +432,6 @@ object GpuOverrides {
   val FLOAT_DIFFERS_GROUP_INCOMPAT =
     "when enabling these, there may be extra groups produced for floating point grouping " +
     "keys (e.g. -0.0, and 0.0)"
-  val CASE_MODIFICATION_INCOMPAT =
-    "in some cases unicode characters change byte width when changing the case. The GPU string " +
-    "conversion does not support these characters. For a full list of unsupported characters " +
-    "see https://github.com/rapidsai/cudf/issues/3132"
   val UTC_TIMEZONE_ID = ZoneId.of("UTC").normalized()
   // Based on https://docs.oracle.com/javase/8/docs/api/java/util/regex/Pattern.html
   private[this] lazy val regexList: Seq[String] = Seq("\\", "\u0000", "\\x", "\t", "\n", "\r",
@@ -1250,10 +1246,7 @@ object GpuOverrides {
       ExprChecks.unaryProjectNotLambdaInputMatchesOutput(TypeSig.STRING, TypeSig.STRING),
       (a, conf, p, r) => new UnaryExprMeta[InitCap](a, conf, p, r) {
         override def convertToGpu(child: Expression): GpuExpression = GpuInitCap(child)
-      }).incompat(CASE_MODIFICATION_INCOMPAT + " Spark also only sees the space character as " +
-      "a word deliminator, but this will capitalize any character after a non-alphabetic " + 
-      "character.  The behavior will be aligned to match Spark in the future per " +
-      "https://github.com/NVIDIA/spark-rapids/issues/2786."),
+      }),
     expr[Log](
       "Natural log",
       ExprChecks.mathUnary,
@@ -2201,15 +2194,13 @@ object GpuOverrides {
       ExprChecks.unaryProjectNotLambdaInputMatchesOutput(TypeSig.STRING, TypeSig.STRING),
       (a, conf, p, r) => new UnaryExprMeta[Upper](a, conf, p, r) {
         override def convertToGpu(child: Expression): GpuExpression = GpuUpper(child)
-      })
-      .incompat(CASE_MODIFICATION_INCOMPAT),
+      }),
     expr[Lower](
       "String lowercase operator",
       ExprChecks.unaryProjectNotLambdaInputMatchesOutput(TypeSig.STRING, TypeSig.STRING),
       (a, conf, p, r) => new UnaryExprMeta[Lower](a, conf, p, r) {
         override def convertToGpu(child: Expression): GpuExpression = GpuLower(child)
-      })
-      .incompat(CASE_MODIFICATION_INCOMPAT),
+      }),
     expr[StringLPad](
       "Pad a string on the left",
       ExprChecks.projectNotLambda(TypeSig.STRING, TypeSig.STRING,

sql-plugin/src/main/scala/org/apache/spark/sql/rapids/stringFunctions.scala

@@ -481,7 +481,10 @@ case class GpuInitCap(child: Expression) extends GpuUnaryExpression with Implici
   override def inputTypes: Seq[DataType] = Seq(StringType)
   override def dataType: DataType = StringType
   override protected def doColumnar(input: GpuColumnVector): ColumnVector =
-    input.getBase.toTitle
+    withResource(Scalar.fromString(" ")) { space =>
+      // Spark only sees the space character as a word deliminator.
+      input.getBase.capitalize(space)
+    }
 }
 
 case class GpuStringReplace(