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_r378239327
##########
File path:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/regexpExpressions.scala
##########
@@ -419,39 +421,104 @@ 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)
+ }
+
+ override protected def doGenCode(ctx: CodegenContext, ev: ExprCode):
ExprCode = {
+ val classNamePattern = classOf[Pattern].getCanonicalName
+ val classNameRegExpExtractBase =
classOf[RegExpExtractBase].getCanonicalName
+ val matcher = ctx.freshName("matcher")
+ val matchResult = ctx.freshName("matchResult")
+
+ val termLastRegex = ctx.addMutableState("UTF8String", "lastRegex")
+ val termPattern = ctx.addMutableState(classNamePattern, "pattern")
+
+ val setEvNotNull = if (nullable) {
+ s"${ev.isNull} = false;"
+ } else {
+ ""
+ }
+ doNullSafeCodeGen(
+ ctx,
+ ev,
+ classNamePattern,
+ classNameRegExpExtractBase,
+ matcher,
+ matchResult,
+ termLastRegex,
+ termPattern,
+ setEvNotNull)
+ }
+
+ def doNullSafeCodeGen(
+ ctx: CodegenContext,
+ ev: ExprCode,
+ classNamePattern: String,
+ classNameRegExpExtractBase: String,
+ matcher: String,
+ matchResult: String,
+ termLastRegex: String,
+ termPattern: String,
+ setEvNotNull: String): ExprCode
+}
+
/**
* Extract a specific(idx) group identified by a Java regex.
*
* NOTE: this expression is not THREAD-SAFE, as it has some internal mutable
status.
*/
@ExpressionDescription(
usage = "_FUNC_(str, regexp[, idx]) - Extracts a group that matches
`regexp`.",
+ arguments = """
+ Arguments:
+ * str - a string expression
+ * regexp - a string expression. The regex string should be a Java
regular expression.
+
+ Since Spark 2.0, string literals (including regex patterns) are
unescaped in our SQL
+ parser. For example, to match "\abc", a regular expression for
`regexp` can be
+ "^\\abc$".
+
+ 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 - a int expression. The regex maybe contains multiple groups.
`idx` represents the
Review comment:
`an int expression of the regex group index.`
----------------------------------------------------------------
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]
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
