cloud-fan commented on a change in pull request #27507: [SPARK-24884][SQL] Support regexp function regexp_extract_all URL: https://github.com/apache/spark/pull/27507#discussion_r378857718
########## File path: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/regexpExpressions.scala ########## @@ -419,39 +421,67 @@ object RegExpExtract { } } +abstract class RegExpExtractBase extends TernaryExpression with ImplicitCastInputTypes { + def subject: Expression + def regexp: Expression + def idx: Expression + + // last regex in string, we will update the pattern iff regexp value changed. + @transient private var lastRegex: UTF8String = _ + // last regex pattern, we cache it for performance concern + @transient private var pattern: Pattern = _ + + override def inputTypes: Seq[AbstractDataType] = Seq(StringType, StringType, IntegerType) + override def children: Seq[Expression] = subject :: regexp :: idx :: Nil + + protected def getLastMatcher(s: Any, p: Any): Matcher = { + if (!p.equals(lastRegex)) { + // regex value changed + lastRegex = p.asInstanceOf[UTF8String].clone() + pattern = Pattern.compile(lastRegex.toString) + } + pattern.matcher(s.toString) + } +} + /** * Extract a specific(idx) group identified by a Java regex. * * NOTE: this expression is not THREAD-SAFE, as it has some internal mutable status. */ @ExpressionDescription( usage = "_FUNC_(str, regexp[, idx]) - Extracts a group that matches `regexp`.", Review comment: `Extracts a group from the first match of regexp.`? ---------------------------------------------------------------- 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 With regards, Apache Git Services --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org