[SPARK-8269] [SQL] string function: initcap

This PR is based on #7208 , thanks to HuJiayin

Closes #7208

Author: HuJiayin <jiayin.hu@intel.com>
Author: Davies Liu <davies@databricks.com>

Closes #7850 from davies/initcap and squashes the following commits:

54472e9 [Davies Liu] fix python test
17ffe51 [Davies Liu] Merge branch 'master' of github.com:apache/spark into initcap
ca46390 [Davies Liu] Merge branch 'master' of github.com:apache/spark into initcap
3a906e4 [Davies Liu] implement title case in UTF8String
8b2506a [HuJiayin] Update functions.py
2cd43e5 [HuJiayin] fix python style check
b616c0e [HuJiayin] add python api
1f5a0ef [HuJiayin] add codegen
7e0c604 [HuJiayin] Merge branch 'master' of https://github.com/apache/spark into initcap
6a0b958 [HuJiayin] add column
c79482d [HuJiayin] support soundex
7ce416b [HuJiayin] support initcap rebase code

5 files changed, 48 insertions, 0 deletions

diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/FunctionRegistry.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/FunctionRegistry.scala
index 6e144518bb..8fafd7778a 100644
--- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/FunctionRegistry.scala
+++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/FunctionRegistry.scala
@@ -178,6 +178,7 @@ object FunctionRegistry {
     expression[Encode]("encode"),
     expression[Decode]("decode"),
     expression[FormatNumber]("format_number"),
+    expression[InitCap]("initcap"),
     expression[Lower]("lcase"),
     expression[Lower]("lower"),
     expression[Length]("length"),
diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/stringOperations.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/stringOperations.scala
index 4d78c55497..80c64e5689 100644
--- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/stringOperations.scala
+++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/stringOperations.scala
@@ -598,6 +598,23 @@ case class FormatString(children: Expression*) extends Expression with ImplicitC
 }
 
 /**
+ * Returns string, with the first letter of each word in uppercase.
+ * Words are delimited by whitespace.
+ */
+case class InitCap(child: Expression) extends UnaryExpression with ImplicitCastInputTypes {
+
+  override def inputTypes: Seq[DataType] = Seq(StringType)
+  override def dataType: DataType = StringType
+
+  override def nullSafeEval(string: Any): Any = {
+    string.asInstanceOf[UTF8String].toTitleCase
+  }
+  override def genCode(ctx: CodeGenContext, ev: GeneratedExpressionCode): String = {
+    defineCodeGen(ctx, ev, str => s"$str.toTitleCase()")
+  }
+}
+
+/**
  * Returns the string which repeat the given string value n times.
  */
 case class StringRepeat(str: Expression, times: Expression)
diff --git a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/StringExpressionsSuite.scala b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/StringExpressionsSuite.scala
index 89c1e33420..906be701be 100644
--- a/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/StringExpressionsSuite.scala
+++ b/sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/expressions/StringExpressionsSuite.scala
@@ -377,6 +377,18 @@ class StringExpressionsSuite extends SparkFunSuite with ExpressionEvalHelper {
     checkEvaluation(Decode(b, Literal.create(null, StringType)), null, create_row(null))
   }
 
+  test("initcap unit test") {
+    checkEvaluation(InitCap(Literal.create(null, StringType)), null)
+    checkEvaluation(InitCap(Literal("a b")), "A B")
+    checkEvaluation(InitCap(Literal(" a")), " A")
+    checkEvaluation(InitCap(Literal("the test")), "The Test")
+    // scalastyle:off
+    // non ascii characters are not allowed in the code, so we disable the scalastyle here.
+    checkEvaluation(InitCap(Literal("世界")), "世界")
+    // scalastyle:on
+  }
+
+
   test("Levenshtein distance") {
     checkEvaluation(Levenshtein(Literal.create(null, StringType), Literal("")), null)
     checkEvaluation(Levenshtein(Literal(""), Literal.create(null, StringType)), null)
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/functions.scala b/sql/core/src/main/scala/org/apache/spark/sql/functions.scala
index babfe21879..818aa109f3 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/functions.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/functions.scala
@@ -1787,6 +1787,15 @@ object functions {
   }
 
   /**
+   * Returns string, with the first letter of each word in uppercase.
+   * Words are delimited by whitespace.
+   *
+   * @group string_funcs
+   * @since 1.5.0
+   */
+  def initcap(e: Column): Column = InitCap(e.expr)
+
+  /**
    * Locate the position of the first occurrence of substr column in the given string.
    * Returns null if either of the arguments are null.
    *
diff --git a/sql/core/src/test/scala/org/apache/spark/sql/StringFunctionsSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/StringFunctionsSuite.scala
index f40233db0a..1c1be0c3cc 100644
--- a/sql/core/src/test/scala/org/apache/spark/sql/StringFunctionsSuite.scala
+++ b/sql/core/src/test/scala/org/apache/spark/sql/StringFunctionsSuite.scala
@@ -315,6 +315,15 @@ class StringFunctionsSuite extends QueryTest {
     }
   }
 
+  test("initcap function") {
+    val df = Seq(("ab", "a B")).toDF("l", "r")
+    checkAnswer(
+      df.select(initcap($"l"), initcap($"r")), Row("Ab", "A B"))
+
+    checkAnswer(
+      df.selectExpr("InitCap(l)", "InitCap(r)"), Row("Ab", "A B"))
+  }
+
   test("number format function") {
     val tuple =
       ("aa", 1.asInstanceOf[Byte], 2.asInstanceOf[Short],