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.
@@ -314,9 +314,6 @@ 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
@@ -327,14 +324,6 @@ def test_initcap():
             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}')
-    assert_gpu_and_cpu_are_equal_collect(
-            lambda spark: unary_op_df(spark, gen).select(
-                f.initcap(f.col('a'))))
-
 @pytest.mark.xfail(reason='https://github.com/NVIDIA/spark-rapids/issues/119')
 def test_like_null_xfail():
     gen = mk_str_gen('.{0,3}a[|b*.$\r\n]{0,2}c.{0,3}')\

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

@@ -1250,10 +1250,7 @@ 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."),
+      }).incompat(CASE_MODIFICATION_INCOMPAT),
     expr[Log](
       "Natural log",
       ExprChecks.mathUnary,

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(