You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@spark.apache.org by jo...@apache.org on 2015/01/28 23:01:42 UTC

spark git commit: [SPARK-5441][pyspark] Make SerDeUtil PairRDD to Python conversions more robust

Repository: spark
Updated Branches:
  refs/heads/master 3bead67d5 -> e023112d3


[SPARK-5441][pyspark] Make SerDeUtil PairRDD to Python conversions more robust

SerDeUtil.pairRDDToPython and SerDeUtil.pythonToPairRDD now both support empty RDDs by checking the result of take(1) instead of calling first which throws an exception.

Author: Michael Nazario <mn...@palantir.com>

Closes #4236 from mnazario/feature/empty-first and squashes the following commits:

a531c0c [Michael Nazario] Added regression tests for SPARK-5441
e3b2fb6 [Michael Nazario] Added acceptance of the empty case


Project: http://git-wip-us.apache.org/repos/asf/spark/repo
Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/e023112d
Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/e023112d
Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/e023112d

Branch: refs/heads/master
Commit: e023112d332e47c6a6d1b301288d0d7d7ac66d0c
Parents: 3bead67
Author: Michael Nazario <mn...@palantir.com>
Authored: Wed Jan 28 13:55:01 2015 -0800
Committer: Josh Rosen <jo...@databricks.com>
Committed: Wed Jan 28 13:58:46 2015 -0800

----------------------------------------------------------------------
 .../org/apache/spark/api/python/SerDeUtil.scala | 13 ++++---
 .../spark/api/python/SerDeUtilSuite.scala       | 38 ++++++++++++++++++++
 2 files changed, 47 insertions(+), 4 deletions(-)
----------------------------------------------------------------------


http://git-wip-us.apache.org/repos/asf/spark/blob/e023112d/core/src/main/scala/org/apache/spark/api/python/SerDeUtil.scala
----------------------------------------------------------------------
diff --git a/core/src/main/scala/org/apache/spark/api/python/SerDeUtil.scala b/core/src/main/scala/org/apache/spark/api/python/SerDeUtil.scala
index 19ca2bb..fb52a96 100644
--- a/core/src/main/scala/org/apache/spark/api/python/SerDeUtil.scala
+++ b/core/src/main/scala/org/apache/spark/api/python/SerDeUtil.scala
@@ -202,7 +202,10 @@ private[spark] object SerDeUtil extends Logging {
    * representation is serialized
    */
   def pairRDDToPython(rdd: RDD[(Any, Any)], batchSize: Int): RDD[Array[Byte]] = {
-    val (keyFailed, valueFailed) = checkPickle(rdd.first())
+    val (keyFailed, valueFailed) = rdd.take(1) match {
+      case Array() => (false, false)
+      case Array(first) => checkPickle(first)
+    }
 
     rdd.mapPartitions { iter =>
       val cleaned = iter.map { case (k, v) =>
@@ -229,10 +232,12 @@ private[spark] object SerDeUtil extends Logging {
     }
 
     val rdd = pythonToJava(pyRDD, batched).rdd
-    rdd.first match {
-      case obj if isPair(obj) =>
+    rdd.take(1) match {
+      case Array(obj) if isPair(obj) =>
         // we only accept (K, V)
-      case other => throw new SparkException(
+      case Array() =>
+        // we also accept empty collections
+      case Array(other) => throw new SparkException(
         s"RDD element of type ${other.getClass.getName} cannot be used")
     }
     rdd.map { obj =>

http://git-wip-us.apache.org/repos/asf/spark/blob/e023112d/core/src/test/scala/org/apache/spark/api/python/SerDeUtilSuite.scala
----------------------------------------------------------------------
diff --git a/core/src/test/scala/org/apache/spark/api/python/SerDeUtilSuite.scala b/core/src/test/scala/org/apache/spark/api/python/SerDeUtilSuite.scala
new file mode 100644
index 0000000..f8c3932
--- /dev/null
+++ b/core/src/test/scala/org/apache/spark/api/python/SerDeUtilSuite.scala
@@ -0,0 +1,38 @@
+/*
+ * 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.api.python
+
+import org.scalatest.FunSuite
+
+import org.apache.spark.SharedSparkContext
+
+class SerDeUtilSuite extends FunSuite with SharedSparkContext {
+
+  test("Converting an empty pair RDD to python does not throw an exception (SPARK-5441)") {
+    val emptyRdd = sc.makeRDD(Seq[(Any, Any)]())
+    SerDeUtil.pairRDDToPython(emptyRdd, 10)
+  }
+
+  test("Converting an empty python RDD to pair RDD does not throw an exception (SPARK-5441)") {
+    val emptyRdd = sc.makeRDD(Seq[(Any, Any)]())
+    val javaRdd = emptyRdd.toJavaRDD()
+    val pythonRdd = SerDeUtil.javaToPython(javaRdd)
+    SerDeUtil.pythonToPairRDD(pythonRdd, false)
+  }
+}
+


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