beliefer commented on a change in pull request #29891: URL: https://github.com/apache/spark/pull/29891#discussion_r506004054
########## File path: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/regexpExpressions.scala ########## @@ -318,16 +320,46 @@ case class StringSplit(str: Expression, regex: Expression, limit: Expression) */ // scalastyle:off line.size.limit @ExpressionDescription( - usage = "_FUNC_(str, regexp, rep) - Replaces all substrings of `str` that match `regexp` with `rep`.", + usage = "_FUNC_(str, regexp, rep[, position]) - Replaces all substrings of `str` that match `regexp` with `rep`.", + arguments = """ + Arguments: + * str - a string expression to search for a regular expression pattern match. + * regexp - a string representing a regular expression. The regex string should be a + Java regular expression. + + Since Spark 2.0, string literals (including regex patterns) are unescaped in our SQL + parser. For example, to match "\abc", a regular expression for `regexp` can be + "^\\abc$". + + There is a SQL config 'spark.sql.parser.escapedStringLiterals' that can be used to + fallback to the Spark 1.6 behavior regarding string literal parsing. For example, + if the config is enabled, the `regexp` that can match "\abc" is "^\abc$". + * rep - a string expression to replace matched substrings. + * position - a positive integer expression that indicates the position within `str` to begin searching. + The default is 1. If position is greater than the number of characters in `str`, the result is `str`. + """, examples = """ Examples: > SELECT _FUNC_('100-200', '(\\d+)', 'num'); num-num """, since = "1.5.0") // scalastyle:on line.size.limit -case class RegExpReplace(subject: Expression, regexp: Expression, rep: Expression) - extends TernaryExpression with ImplicitCastInputTypes with NullIntolerant { +case class RegExpReplace(subject: Expression, regexp: Expression, rep: Expression, pos: Expression) + extends QuaternaryExpression with ImplicitCastInputTypes with NullIntolerant { + + override def checkInputDataTypes(): TypeCheckResult = { + if (!pos.foldable) { + return TypeCheckFailure(s"Position expression must be foldable, but got $pos") + } + + val i = pos.eval().asInstanceOf[Int] Review comment: ``` WITH strings AS ( SELECT 'healthy, wealthy, and wise' s FROM dual ) SELECT s "STRING", regexp_replace( s, '\w', 'something', NULL ) "MODIFIED_STRING" FROM strings; ``` STRING | MODIFIED_STRING -- | -- healthy, wealthy, and wise | Vertica ``` dbadmin=> select regexp_replace('healthy, wealthy, and wise', '\\w', 'something', null); regexp_replace ---------------- (1 row) ``` ---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org