Github user nongli commented on a diff in the pull request:
https://github.com/apache/spark/pull/11742#discussion_r56277373
--- Diff:
sql/core/src/main/scala/org/apache/spark/sql/execution/joins/BroadcastHashJoin.scala
---
@@ -322,4 +327,70 @@ case class BroadcastHashJoin(
""".stripMargin
}
}
+
+ /**
+ * Generates the code for left semi join.
+ */
+ private def codegenSemi(ctx: CodegenContext, input: Seq[ExprCode]):
String = {
+ val (broadcastRelation, relationTerm) = prepareBroadcast(ctx)
+ val (keyEv, anyNull) = genStreamSideJoinKey(ctx, input)
+ val matched = ctx.freshName("matched")
+ val buildVars = genBuildSideVars(ctx, matched)
+ val numOutput = metricTerm(ctx, "numOutputRows")
+
+ val checkCondition = if (condition.isDefined) {
+ val expr = condition.get
+ // evaluate the variables from build side that used by condition
+ val eval = evaluateRequiredVariables(buildPlan.output, buildVars,
expr.references)
+ // filter the output via condition
+ ctx.currentVars = input ++ buildVars
+ val ev = BindReferences.bindReference(expr, streamedPlan.output ++
buildPlan.output).gen(ctx)
+ s"""
+ |$eval
+ |${ev.code}
+ |if (${ev.isNull} || !${ev.value}) continue;
+ """.stripMargin
+ } else {
+ ""
+ }
+
+ if (broadcastRelation.value.isInstanceOf[UniqueHashedRelation]) {
+ s"""
+ |// generate join key for stream side
+ |${keyEv.code}
+ |// find matches from HashedRelation
+ |UnsafeRow $matched = $anyNull ? null:
(UnsafeRow)$relationTerm.getValue(${keyEv.value});
+ |if ($matched == null) continue;
+ |$checkCondition
+ |$numOutput.add(1);
+ |${consume(ctx, input)}
+ """.stripMargin
+
+ } else {
+ val matches = ctx.freshName("matches")
+ val bufferType = classOf[CompactBuffer[UnsafeRow]].getName
+ val i = ctx.freshName("i")
+ val size = ctx.freshName("size")
+ val found = ctx.freshName("found")
+ s"""
+ |// generate join key for stream side
+ |${keyEv.code}
+ |// find matches from HashRelation
+ |$bufferType $matches = $anyNull ? null :
($bufferType)$relationTerm.get(${keyEv.value});
+ |if ($matches == null) continue;
+ |int $size = $matches.size();
+ |boolean $found = false;
+ |for (int $i = 0; $i < $size; $i++) {
+ | UnsafeRow $matched = (UnsafeRow) $matches.apply($i);
+ | $checkCondition
+ | $found = true;
+ | break;
+ |}
+ |if (!$found) continue;
+ |$numOutput.add(1);
+ |${consume(ctx, input)}
+ """.stripMargin
+
--- End diff --
and here
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
