[GitHub] [spark] cloud-fan commented on a change in pull request #27507: [SPARK-24884][SQL] Support regexp function regexp_extract_all

[GitBox <gi...@apache.org>]

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_r377613299
 
 

 ##########
 File path: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/regexpExpressions.scala
 ##########
 @@ -452,6 +454,46 @@ case class RegExpReplace(subject: Expression, regexp: Expression, rep: Expressio
   }
 }
 
+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)
+  }
+
+  protected def getGenCodeVals(ctx: CodegenContext, ev: ExprCode) = {
+    val classNamePattern = classOf[Pattern].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 {
+      ""
+    }
+
+    (classNamePattern, matcher, matchResult, termLastRegex, termPattern, setEvNotNull)
 
 Review comment:
   this is a little hard to read at the caller side.
   
   can we implement `doGenCode` in the base class, which calls an abstract method. Sub-classes need to implement the abstract method.

----------------------------------------------------------------
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:
users@infra.apache.org


With regards,
Apache Git Services

---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org