Github user chenghao-intel commented on a diff in the pull request: https://github.com/apache/spark/pull/6762#discussion_r34213184 --- 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 --- End diff -- I think that's a general problem for `foldable`, we probable never know whether the `substr` is a constant null/empty value, until the optimizer triggered, but the optimizer also reply on the `foldable`... We need to figure out how to do that, but maybe not in this PR.
--- 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