Github user mateiz commented on a diff in the pull request:
https://github.com/apache/spark/pull/455#discussion_r13148051
--- Diff:
core/src/main/scala/org/apache/spark/api/python/PythonHadoopUtil.scala ---
@@ -0,0 +1,86 @@
+/*
+ * 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.apache.spark.rdd.RDD
+import org.apache.spark.SparkContext
+import org.apache.hadoop.conf.Configuration
+import org.apache.hadoop.io._
+
+
+/**
+ * Utilities for working with Python objects -> Hadoop-related objects
+ */
+private[python] object PythonHadoopUtil {
+
+ /**
+ * Convert a Map of properties to a
[[org.apache.hadoop.conf.Configuration]]
+ */
+ def mapToConf(map: java.util.Map[String, String]) = {
+ import collection.JavaConversions._
+ val conf = new Configuration()
+ map.foreach{ case (k, v) => conf.set(k, v) }
+ conf
+ }
+
+ /**
+ * Merges two configurations, returns a copy of left with keys from
right overwriting
+ * any matching keys in left
+ */
+ def mergeConfs(left: Configuration, right: Configuration) = {
+ import collection.JavaConversions._
+ val copy = new Configuration(left)
+ right.iterator().foreach(entry => copy.set(entry.getKey,
entry.getValue))
+ copy
+ }
+
+ /**
+ * Converts an RDD of key-value pairs, where key and/or value could be
instances of
+ * [[org.apache.hadoop.io.Writable]], into an RDD[(K, V)]
+ */
+ def convertRDD[K, V](rdd: RDD[(K, V)]) = {
+ rdd.map{
--- End diff --
Space before {
---
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.
---
