Github user mengxr commented on a diff in the pull request: https://github.com/apache/spark/pull/164#discussion_r10865895 --- Diff: mllib/src/test/scala/org/apache/spark/mllib/util/WholeTextFileRecordReaderSuite.scala --- @@ -0,0 +1,114 @@ +/* + * 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.mllib.util + + +import java.io.DataOutputStream +import java.io.FileOutputStream +import java.nio.file.Files +import java.nio.file.Path +import java.nio.file.Paths + +import scala.collection.immutable.IndexedSeq + +import org.scalatest.BeforeAndAfterAll +import org.scalatest.FunSuite + +import org.apache.hadoop.io.Text + +import org.apache.spark.mllib.util.MLUtils._ +import org.apache.spark.SparkContext + +/** + * Tests the correctness of [[org.apache.spark.mllib.input.WholeTextFileRecordReader]]. A temporary + * directory is created as fake input. Temporal storage would be deleted in the end. + */ +class WholeTextFileRecordReaderSuite extends FunSuite with BeforeAndAfterAll { + private var sc: SparkContext = _ + + override def beforeAll() { + sc = new SparkContext("local", "test") + } + + override def afterAll() { + sc.stop() + } + + private def createNativeFile(inputDir: Path, fileName: String, contents: Array[Byte]) = { + val out = new DataOutputStream(new FileOutputStream(s"${inputDir.toString}/$fileName")) + out.write(contents, 0, contents.length) + out.close() + println("Wrote native file") + } + + /** + * This code will test the behaviors of WholeTextFileRecordReader based on local disk. There are + * three aspects to check: + * 1) is all files are read. --- End diff -- whether all files are read
--- 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. ---