Esempio n. 1
0
        /// <exception cref="System.Exception"/>
        private void CheckCompression(bool compressMapOutputs, SequenceFile.CompressionType
                                      redCompression, bool includeCombine)
        {
            JobConf    conf    = new JobConf(typeof(TestMapRed));
            Path       testdir = new Path(TestDir.GetAbsolutePath());
            Path       inDir   = new Path(testdir, "in");
            Path       outDir  = new Path(testdir, "out");
            FileSystem fs      = FileSystem.Get(conf);

            fs.Delete(testdir, true);
            FileInputFormat.SetInputPaths(conf, inDir);
            FileOutputFormat.SetOutputPath(conf, outDir);
            conf.SetMapperClass(typeof(TestMapRed.MyMap));
            conf.SetReducerClass(typeof(TestMapRed.MyReduce));
            conf.SetOutputKeyClass(typeof(Text));
            conf.SetOutputValueClass(typeof(Text));
            conf.SetOutputFormat(typeof(SequenceFileOutputFormat));
            conf.Set(MRConfig.FrameworkName, MRConfig.LocalFrameworkName);
            if (includeCombine)
            {
                conf.SetCombinerClass(typeof(IdentityReducer));
            }
            conf.SetCompressMapOutput(compressMapOutputs);
            SequenceFileOutputFormat.SetOutputCompressionType(conf, redCompression);
            try
            {
                if (!fs.Mkdirs(testdir))
                {
                    throw new IOException("Mkdirs failed to create " + testdir.ToString());
                }
                if (!fs.Mkdirs(inDir))
                {
                    throw new IOException("Mkdirs failed to create " + inDir.ToString());
                }
                Path             inFile = new Path(inDir, "part0");
                DataOutputStream f      = fs.Create(inFile);
                f.WriteBytes("Owen was here\n");
                f.WriteBytes("Hadoop is fun\n");
                f.WriteBytes("Is this done, yet?\n");
                f.Close();
                RunningJob rj = JobClient.RunJob(conf);
                NUnit.Framework.Assert.IsTrue("job was complete", rj.IsComplete());
                NUnit.Framework.Assert.IsTrue("job was successful", rj.IsSuccessful());
                Path output = new Path(outDir, Task.GetOutputName(0));
                NUnit.Framework.Assert.IsTrue("reduce output exists " + output, fs.Exists(output)
                                              );
                SequenceFile.Reader rdr = new SequenceFile.Reader(fs, output, conf);
                NUnit.Framework.Assert.AreEqual("is reduce output compressed " + output, redCompression
                                                != SequenceFile.CompressionType.None, rdr.IsCompressed());
                rdr.Close();
            }
            finally
            {
                fs.Delete(testdir, true);
            }
        }
Esempio n. 2
0
        /// <exception cref="System.IO.IOException"/>
        public override RecordWriter <WritableComparable, Writable> GetRecordWriter(FileSystem
                                                                                    ignored, JobConf job, string name, Progressable progress)
        {
            // get the path of the temporary output file
            Path             file  = FileOutputFormat.GetTaskOutputPath(job, name);
            FileSystem       fs    = file.GetFileSystem(job);
            CompressionCodec codec = null;

            SequenceFile.CompressionType compressionType = SequenceFile.CompressionType.None;
            if (GetCompressOutput(job))
            {
                // find the kind of compression to do
                compressionType = SequenceFileOutputFormat.GetOutputCompressionType(job);
                // find the right codec
                Type codecClass = GetOutputCompressorClass(job, typeof(DefaultCodec));
                codec = ReflectionUtils.NewInstance(codecClass, job);
            }
            // ignore the progress parameter, since MapFile is local
            MapFile.Writer @out = new MapFile.Writer(job, fs, file.ToString(), job.GetOutputKeyClass
                                                         ().AsSubclass <WritableComparable>(), job.GetOutputValueClass().AsSubclass <Writable
                                                                                                                                     >(), compressionType, codec, progress);
            return(new _RecordWriter_72(@out));
        }