Github user davies commented on a diff in the pull request:
https://github.com/apache/spark/pull/7904#discussion_r36579684
--- Diff:
sql/core/src/main/scala/org/apache/spark/sql/execution/joins/RowIterator.scala
---
@@ -0,0 +1,63 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.sql.execution.joins
+
+import java.util.NoSuchElementException
+
+import org.apache.spark.sql.catalyst.InternalRow
+
+private[sql] abstract class RowIterator {
+ def advanceNext(): Boolean
+ def getRow: InternalRow
+ def toScala: Iterator[InternalRow] = new RowIteratorToScala(this)
+}
+
+object RowIterator {
+ def fromScala(scalaIter: Iterator[InternalRow]): RowIterator = {
+ scalaIter match {
+ case wrappedRowIter: RowIteratorToScala => wrappedRowIter.rowIter
+ case _ => new RowIteratorFromScala(scalaIter)
+ }
+ }
+}
+
+private final class RowIteratorToScala(val rowIter: RowIterator) extends
Iterator[InternalRow] {
+ private [this] var _hasNext: Boolean = rowIter.advanceNext()
+ override def hasNext: Boolean = _hasNext
+ override def next(): InternalRow = {
+ if (!_hasNext) throw new NoSuchElementException
+ val row: InternalRow = rowIter.getRow.copy()
--- End diff --
I think we could provide the Iterator interface without introducing
RowIterator, while still do the dirty work in hasNext(), and hasNext() could be
call multiple times without calling next() between them.
From the doc of Scala Iterator or Java.util.Iterator, `hasNext` should
always be idempotent, and we could satisfy this even we read data in hasNext()
(by making it stateful)
see this as an example:
https://github.com/apache/spark/blob/master/sql/core/src/main/scala/org/apache/spark/sql/execution/joins/HashJoin.scala#L91
---
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]
