Github user mateiz commented on a diff in the pull request:
https://github.com/apache/spark/pull/455#discussion_r13148883
--- Diff:
core/src/main/scala/org/apache/spark/api/python/WriteInputFormatTestDataGenerator.scala
---
@@ -0,0 +1,137 @@
+/*
+ * 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.SparkContext
+import org.apache.hadoop.io._
+import scala.Array
+import java.io.{DataOutput, DataInput}
+import org.apache.hadoop.mapreduce.lib.output.SequenceFileOutputFormat
+import org.apache.spark.api.java.JavaSparkContext
+
+/**
+ * A class to test MsgPack serialization on the Scala side, that will be
deserialized
+ * in Python
+ * @param str
+ * @param int
+ * @param double
+ */
+case class TestWritable(var str: String, var int: Int, var double: Double)
extends Writable {
+ def this() = this("", 0, 0.0)
+
+ def getStr = str
+ def setStr(str: String) { this.str = str }
+ def getInt = int
+ def setInt(int: Int) { this.int = int }
+ def getDouble = double
+ def setDouble(double: Double) { this.double = double }
+
+ def write(out: DataOutput) = {
+ out.writeUTF(str)
+ out.writeInt(int)
+ out.writeDouble(double)
+ }
+
+ def readFields(in: DataInput) = {
+ str = in.readUTF()
+ int = in.readInt()
+ double = in.readDouble()
+ }
+}
+
+/**
+ * This object contains method to generate SequenceFile test data and
write it to a
+ * given directory (probably a temp directory)
+ */
+object WriteInputFormatTestDataGenerator extends App {
+ import SparkContext._
+
+ def generateData(path: String, jsc: JavaSparkContext) {
+ val sc = jsc.sc
+
+ val basePath = s"$path/sftestdata/"
+ val textPath = s"$basePath/sftext/"
+ val intPath = s"$basePath/sfint/"
+ val doublePath = s"$basePath/sfdouble/"
+ val arrPath = s"$basePath/sfarray/"
+ val mapPath = s"$basePath/sfmap/"
+ val classPath = s"$basePath/sfclass/"
+ val bytesPath = s"$basePath/sfbytes/"
+ val boolPath = s"$basePath/sfbool/"
+ val nullPath = s"$basePath/sfnull/"
+
+ /*
+ * Create test data for IntWritable, DoubleWritable, Text,
BytesWritable,
+ * BooleanWritable and NullWritable
+ */
+ val intKeys = Seq((1, "aa"), (2, "bb"), (2, "aa"), (3, "cc"), (2,
"bb"), (1, "aa"))
+ sc.parallelize(intKeys).saveAsSequenceFile(intPath)
+ sc.parallelize(intKeys.map{ case (k, v) => (k.toDouble, v)
}).saveAsSequenceFile(doublePath)
+ sc.parallelize(intKeys.map{ case (k, v) => (k.toString, v)
}).saveAsSequenceFile(textPath)
+ sc.parallelize(intKeys.map{ case (k, v) => (k, v.getBytes)
}).saveAsSequenceFile(bytesPath)
+ val bools = Seq((1, true), (2, true), (2, false), (3, true), (2,
false), (1, false))
+ sc.parallelize(bools).saveAsSequenceFile(boolPath)
+ sc.parallelize(intKeys).map{ case (k, v) =>
+ (new IntWritable(k), NullWritable.get())
+ }.saveAsSequenceFile(nullPath)
+
+ // Create test data for ArrayWritable
+ val data = Seq(
+ (1, Array(1.0, 2.0, 3.0)),
+ (2, Array(3.0, 4.0, 5.0)),
+ (3, Array(4.0, 5.0, 6.0))
+ )
+ sc.parallelize(data, numSlices = 2)
+ .map{ case (k, v) =>
+ (new IntWritable(k), new ArrayWritable(classOf[DoubleWritable],
v.map(new DoubleWritable(_))))
+ }
+ .saveAsNewAPIHadoopFile[SequenceFileOutputFormat[IntWritable,
ArrayWritable]](arrPath)
--- End diff --
Formatting here is weird, perhaps due to tabs. It would look better as
```
sc.parallelize(data, numSlices = 2)
.map { case (k, v) =>
(new IntWritable(k), new ArrayWritable(classOf[DoubleWritable],
v.map(new DoubleWritable(_))))
}.saveAsNewAPIHadoopFile[SequenceFileOutputFormat[IntWritable,
ArrayWritable]](arrPath)
```
---
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.
---
