Github user davies commented on a diff in the pull request:
https://github.com/apache/spark/pull/6762#discussion_r34170486
--- Diff:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/stringOperations.scala
---
@@ -188,6 +189,302 @@ case class EndsWith(left: Expression, right:
Expression)
}
/**
+ * A function that trim the spaces from both ends for the specified string.
+ */
+case class StringTrim(child: Expression)
+ extends UnaryExpression with String2StringExpression {
+
+ def convert(v: UTF8String): UTF8String = v.trim()
+
+ override def toString: String = s"TRIM($child)"
+
+ override def genCode(ctx: CodeGenContext, ev: GeneratedExpressionCode):
String = {
+ defineCodeGen(ctx, ev, c => s"($c).trim()")
+ }
+}
+
+/**
+ * A function that trim the spaces from left end for given string.
+ */
+case class StringTrimLeft(child: Expression)
+ extends UnaryExpression with String2StringExpression {
+
+ def convert(v: UTF8String): UTF8String = v.trimLeft()
+
+ override def toString: String = s"LTRIM($child)"
+
+ override def genCode(ctx: CodeGenContext, ev: GeneratedExpressionCode):
String = {
+ defineCodeGen(ctx, ev, c => s"($c).trimLeft()")
+ }
+}
+
+/**
+ * A function that trim the spaces from right end for given string.
+ */
+case class StringTrimRight(child: Expression)
+ extends UnaryExpression with String2StringExpression {
+
+ def convert(v: UTF8String): UTF8String = v.trimRight()
+
+ override def toString: String = s"RTRIM($child)"
+
+ override def genCode(ctx: CodeGenContext, ev: GeneratedExpressionCode):
String = {
+ defineCodeGen(ctx, ev, c => s"($c).trimRight()")
+ }
+}
+
+/**
+ * A function that returns the position of the first occurrence of substr
in the given string.
+ * Returns null if either of the arguments are null and
+ * returns 0 if substr could not be found in str.
+ *
+ * NOTE: that this is not zero based, but 1-based index. The first
character in str has index 1.
+ */
+case class StringInstr(str: Expression, substr: Expression)
+ extends BinaryExpression with ExpectsInputTypes {
+
+ override def left: Expression = str
+ override def right: Expression = substr
+ override def dataType: DataType = IntegerType
+ override def inputTypes: Seq[DataType] = Seq(StringType, StringType)
+
+ override def nullSafeEval(string: Any, sub: Any): Any = {
+ string.asInstanceOf[UTF8String].instr(sub.asInstanceOf[UTF8String], 0)
+ 1
+ }
+
+ override def toString: String = s"INSTR($str, $substr)"
+
+ override def genCode(ctx: CodeGenContext, ev: GeneratedExpressionCode):
String = {
+ defineCodeGen(ctx, ev, (l, r) =>
+ s"($l).instr($r, 0) + 1")
+ }
+}
+
+/**
+ * A function that returns the position of the first occurrence of substr
+ * in given string after position pos.
+ */
+case class StringLocate(substr: Expression, str: Expression, start:
Expression)
+ extends Expression with ExpectsInputTypes {
+
+ def this(substr: Expression, str: Expression) = {
+ this(substr, str, Literal(0))
+ }
+
+ override def children: Seq[Expression] = substr :: str :: start :: Nil
+ override def foldable: Boolean = children.forall(_.foldable)
+ override def nullable: Boolean = substr.nullable || str.nullable
+ override def dataType: DataType = IntegerType
+ override def inputTypes: Seq[DataType] = Seq(StringType, StringType,
IntegerType)
+
+ override def eval(input: InternalRow): Any = {
+ val s = start.eval(input)
+ if (s == null) {
+ // if the start position is null, we need to return 0, (keep it
conform to Hive)
+ 0
+ } else {
+ val r = substr.eval(input)
+ if (r == null) {
+ null
+ } else {
+ val l = str.eval(input)
+ if (l == null) {
+ null
+ } else {
+ l.asInstanceOf[UTF8String].instr(
+ r.asInstanceOf[UTF8String],
+ s.asInstanceOf[Int]) + 1
+ }
+ }
+ }
+ }
+
+ override def toString: String = s"LOCATE($substr, $str[, $start])"
+}
+
+/**
+ * Returns str, left-padded with pad to a length of len.
+ */
+case class StringLPad(str: Expression, len: Expression, pad: Expression)
+ extends Expression with ExpectsInputTypes {
+
+ override def children: Seq[Expression] = str :: len :: pad :: Nil
+ override def foldable: Boolean = children.forall(_.foldable)
+ override def nullable: Boolean = children.exists(_.nullable)
+ override def dataType: DataType = StringType
+ override def inputTypes: Seq[DataType] = Seq(StringType, IntegerType,
StringType)
+
+ override def eval(input: InternalRow): Any = {
+ val s = str.eval(input)
+ if (s == null) {
+ null
+ } else {
+ val l = len.eval(input)
+ if (l == null) {
+ null
+ } else {
+ val p = pad.eval(input)
+ if (p == null) {
+ null
+ } else {
+ val len = l.asInstanceOf[Int]
+ val str = s.asInstanceOf[UTF8String]
+ val pad = p.asInstanceOf[UTF8String]
+
+ str.lpad(len, pad)
+ }
+ }
+ }
+ }
+
+ override def toString: String = s"LPAD($str, $len, $pad)"
+}
+
+/**
+ * Returns str, right-padded with pad to a length of len.
+ */
+case class StringRPad(str: Expression, len: Expression, pad: Expression)
+ extends Expression with ExpectsInputTypes {
+
+ override def children: Seq[Expression] = str :: len :: pad :: Nil
+ override def foldable: Boolean = children.forall(_.foldable)
+ override def nullable: Boolean = children.exists(_.nullable)
+ override def dataType: DataType = StringType
+ override def inputTypes: Seq[DataType] = Seq(StringType, IntegerType,
StringType)
+
+ override def eval(input: InternalRow): Any = {
+ val s = str.eval(input)
+ if (s == null) {
+ null
+ } else {
+ val l = len.eval(input)
+ if (l == null) {
+ null
+ } else {
+ val p = pad.eval(input)
+ if (p == null) {
+ null
+ } else {
+ val len = l.asInstanceOf[Int]
+ val str = s.asInstanceOf[UTF8String]
+ val pad = p.asInstanceOf[UTF8String]
+
+ str.rpad(len, pad)
+ }
+ }
+ }
+ }
+
+ override def toString: String = s"RPAD($str, $len, $pad)"
+}
+
+/**
+ * Returns the input formatted according do printf-style format strings
+ */
+case class StringFormat(children: Expression*) extends Expression {
+
+ require(children.length >=1, "printf() should take at least 1 argument")
+
+ override def foldable: Boolean = children.forall(_.foldable)
+ override def nullable: Boolean = children(0).nullable
+ override def dataType: DataType = StringType
+ private def format: Expression = children(0)
+ private def args: Seq[Expression] = children.tail
+
+ override def eval(input: InternalRow): Any = {
+ val pattern = format.eval(input)
+ if (pattern == null) {
+ null
+ } else {
+ val sb = new StringBuffer()
+ val formatter = new java.util.Formatter(sb, Locale.US)
+
+ val arglist = args.map(_.eval(input).asInstanceOf[AnyRef])
+ formatter.format(pattern.asInstanceOf[UTF8String].toString(),
arglist: _*)
+
+ UTF8String.fromString(sb.toString)
+ }
+ }
+
+ override def toString: String = s"printf($format, $args)"
+}
+
+/**
+ * Returns the string which repeat the given string value n times.
+ */
+case class StringRepeat(str: Expression, times: Expression)
+ extends BinaryExpression with ExpectsInputTypes {
+
+ override def left: Expression = str
+ override def right: Expression = times
+ override def dataType: DataType = StringType
+ override def inputTypes: Seq[DataType] = Seq(StringType, IntegerType)
+
+ override def nullSafeEval(string: Any, n: Any): Any = {
+ string.asInstanceOf[UTF8String].repeat(n.asInstanceOf[Integer])
+ }
+
+ override def toString: String = s"repeat($str, $times)"
+
+ override def genCode(ctx: CodeGenContext, ev: GeneratedExpressionCode):
String = {
+ defineCodeGen(ctx, ev, (l, r) =>
+ s"($l).repeat($r)")
--- End diff --
Nit: put these in one line?
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
