Github user mingyukim commented on a diff in the pull request:
https://github.com/apache/spark/pull/5603#discussion_r28986083
--- Diff: core/src/main/scala/org/apache/spark/rdd/InputSourceRDD.scala ---
@@ -0,0 +1,84 @@
+/*
+ * 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.rdd
+
+import scala.reflect.ClassTag
+import scala.util.control.NonFatal
+
+import org.apache.spark.{Logging, TaskContext, Partition, SparkContext}
+import org.apache.spark.io.{InputPartition, InputSource}
+
+
+private final class InputSourcePartition(val underlying: InputPartition,
override val index: Int)
+ extends Partition
+
+
+private[spark] class InputSourceRDD[T: ClassTag](sc: SparkContext,
inputSource: InputSource[T])
+ extends RDD[T](sc, Nil) with Logging {
+
+ override def compute(split: Partition, context: TaskContext):
Iterator[T] = {
+ val p =
split.asInstanceOf[InputSourcePartition].underlying.asInstanceOf[InputPartition]
+ val reader = inputSource.createRecordReader(p, context)
+
+ new Iterator[T] {
+
+ // Used to check whether we are done and make sure we only call
underlying.close() once.
+ private[this] var finished = false
+
+ context.addTaskCompletionListener(_ => close())
+
+ override def hasNext: Boolean = {
+ if (!finished) {
+ finished = !reader.fetchNext()
--- End diff --
Calling hasNext multiple times will advance the iterator by doing something
similar to what Spark's own NextIterator does or extending NextIterator.
---
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 infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
