beliefer commented on a change in pull request #27507:
URL: https://github.com/apache/spark/pull/27507#discussion_r463060500
##########
File path:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/regexpExpressions.scala
##########
@@ -518,3 +546,106 @@ case class RegExpExtract(subject: Expression, regexp:
Expression, idx: Expressio
})
}
}
+
+/**
+ * Extract all specific(idx) groups 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]) - Extract all strings in the `str` that match
the `regexp`
+ expression and corresponding to the regex group index.
+ """,
+ arguments = """
+ Arguments:
+ * str - a string expression.
+ * 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$".
+
+ There is a SQL config 'spark.sql.parser.escapedStringLiterals' that
can be used to
+ fallback to the Spark 1.6 behavior regarding string literal parsing.
For example,
+ if the config is enabled, the `regexp` that can match "\abc" is
"^\abc$".
+ * idx - an integer expression that representing the group index. The
regex may contains
+ multiple groups. `idx` indicates which regex group to extract. The
group index should
+ be non-negative. If `idx` is not specified, the default group index
value is 1. The
+ `idx` parameter is the Java regex Matcher group() method index. See
+ docs/api/java/util/regex/Matcher.html for more information on the
`idx` or Java regex
+ group() method.
+ """,
+ examples = """
+ Examples:
+ > SELECT _FUNC_('100-200, 300-400', '(\\d+)-(\\d+)', 1);
+ ["100","300"]
+ """,
+ since = "3.0.0")
+case class RegExpExtractAll(subject: Expression, regexp: Expression, idx:
Expression)
+ extends RegExpExtractBase {
+ def this(s: Expression, r: Expression) = this(s, r, Literal(1))
+
+ override def nullSafeEval(s: Any, p: Any, r: Any): Any = {
+ val m = getLastMatcher(s, p)
+ val matchResults = new ArrayBuffer[UTF8String]()
+ while(m.find) {
+ val mr: MatchResult = m.toMatchResult
+ val index = r.asInstanceOf[Int]
+ RegExpExtractBase.checkGroupIndex(mr.groupCount, index)
+ val group = mr.group(index)
+ if (group == null) { // Pattern matched, but not optional group
Review comment:
I just reference
https://github.com/apache/spark/blob/5250f988a32a8b5599f6038702da7e31dcbaccd8/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/regexpExpressions.scala#L497
----------------------------------------------------------------
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:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
