Replace toTitle with capitalize for GpuInitCap

docs/configs.md

@@ -197,7 +197,7 @@ Name | SQL Function(s) | Description | Default Value | Notes
 <a name="sql.expression.If"></a>spark.rapids.sql.expression.If|`if`|IF expression|true|None|
 <a name="sql.expression.In"></a>spark.rapids.sql.expression.In|`in`|IN operator|true|None|
 <a name="sql.expression.InSet"></a>spark.rapids.sql.expression.InSet| |INSET operator|true|None|
-<a name="sql.expression.InitCap"></a>spark.rapids.sql.expression.InitCap|`initcap`|Returns str with the first letter of each word in uppercase. All other letters are in lowercase|false|This is not 100% compatible with the Spark version because in some cases Unicode characters change byte width when changing the case. The GPU string conversion does not support these characters for capitalize now. This will be fixed in the future per https://github.com/rapidsai/cudf/issues/8644. For a full list of unsupported characters see https://github.com/rapidsai/cudf/issues/3132.|
+<a name="sql.expression.InitCap"></a>spark.rapids.sql.expression.InitCap|`initcap`|Returns str with the first letter of each word in uppercase. All other letters are in lowercase|false|This is not 100% compatible with the Spark version because the Unicode version used by cuDF and the JVM may differ, resulting in some corner-case characters not changing case correctly.|
 <a name="sql.expression.InputFileBlockLength"></a>spark.rapids.sql.expression.InputFileBlockLength|`input_file_block_length`|Returns the length of the block being read, or -1 if not available|true|None|
 <a name="sql.expression.InputFileBlockStart"></a>spark.rapids.sql.expression.InputFileBlockStart|`input_file_block_start`|Returns the start offset of the block being read, or -1 if not available|true|None|
 <a name="sql.expression.InputFileName"></a>spark.rapids.sql.expression.InputFileName|`input_file_name`|Returns the name of the file being read, or empty string if not available|true|None|

docs/supported_ops.md

@@ -8013,7 +8013,7 @@ Accelerator support is described below.
 <td rowSpan="4">InitCap</td>
 <td rowSpan="4">`initcap`</td>
 <td rowSpan="4">Returns str with the first letter of each word in uppercase. All other letters are in lowercase</td>
-<td rowSpan="4">This is not 100% compatible with the Spark version because in some cases Unicode characters change byte width when changing the case. The GPU string conversion does not support these characters for capitalize now. This will be fixed in the future per https://github.com/rapidsai/cudf/issues/8644. For a full list of unsupported characters see https://github.com/rapidsai/cudf/issues/3132.</td>
+<td rowSpan="4">This is not 100% compatible with the Spark version because the Unicode version used by cuDF and the JVM may differ, resulting in some corner-case characters not changing case correctly.</td>
 <td rowSpan="2">project</td>
 <td>input</td>
 <td> </td>

integration_tests/src/main/python/string_test.py

@@ -320,15 +320,15 @@ def test_initcap():
     # 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('([aAbB1357_@%-]{0,12}[ \r\n\t]{1,2}){1,5}')
+    gen = mk_str_gen('([aAbB1357ȺéŸ_@%-]{0,15}[ \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
-@pytest.mark.xfail(reason='https://github.com/rapidsai/cudf/issues/8644')
-def test_initcap_width_change():
-    gen = mk_str_gen('ʼn([aAbB13ʼnȺéʼnŸ]{0,5}){1,5}')
+@pytest.mark.xfail(reason='Spark initcap will not convert ʼn to ʼN')
+def test_initcap_special_chars():
+    gen = mk_str_gen('ʼn([aAbB13ȺéŸ]{0,5}){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

@@ -1249,10 +1249,7 @@ 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("in some cases Unicode characters change byte width when changing the case." +
-      " The GPU string conversion does not support these characters for capitalize now. This" +
-      " will be fixed in the future per https://github.com/rapidsai/cudf/issues/8644. For a" +
-      " full list of unsupported characters see https://github.com/rapidsai/cudf/issues/3132."),
+      }).incompat(CASE_MODIFICATION_INCOMPAT),
     expr[Log](
       "Natural log",
       ExprChecks.mathUnary,