List of usage examples for org.apache.hadoop.mapreduce Job setOutputFormatClass
public void setOutputFormatClass(Class<? extends OutputFormat> cls) throws IllegalStateException
From source file:com.aliyun.openservices.tablestore.hadoop.TableStoreOutputFormatExample.java
License:Apache License
public static void main(String[] args) throws Exception { if (!parseArgs(args)) { printUsage();// www. j a v a 2s .c o m System.exit(1); } if (endpoint == null || accessKeyId == null || accessKeySecret == null || inputTable == null || outputTable == null) { printUsage(); System.exit(1); } Configuration conf = new Configuration(); Job job = Job.getInstance(conf, TableStoreOutputFormatExample.class.getName()); job.setMapperClass(OwnerMapper.class); job.setReducerClass(IntoTableReducer.class); job.setMapOutputKeyClass(Text.class); job.setMapOutputValueClass(MapWritable.class); job.setInputFormatClass(TableStoreInputFormat.class); job.setOutputFormatClass(TableStoreOutputFormat.class); TableStore.setCredential(job, accessKeyId, accessKeySecret, securityToken); TableStore.setEndpoint(job, endpoint, instance); TableStoreInputFormat.addCriteria(job, fetchCriteria()); TableStoreOutputFormat.setOutputTable(job, outputTable); System.exit(job.waitForCompletion(true) ? 0 : 1); }
From source file:com.antbrains.crf.hadoop.CalcFeatureWeights.java
License:Apache License
public static void main(String[] args) throws Exception { Configuration conf = new Configuration(); String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs(); if (otherArgs.length != 3 && otherArgs.length != 4) { System.err.println("CalcFeatureWeights <inDir> <tmpDir> <outDir> [startStep]"); System.exit(-1);// w w w. j a v a2s.com } int startStep = 1; if (otherArgs.length == 4) { startStep = Integer.valueOf(otherArgs[otherArgs.length - 1]); } FileSystem fs = FileSystem.get(conf); if (startStep <= 1) { System.out.println("calc"); fs.delete(new Path(otherArgs[1]), true); Job job = new Job(conf, CalcFeatureWeights.class.getSimpleName()); job.setNumReduceTasks(1); job.setJarByClass(CalcFeatureWeights.class); job.setMapperClass(CalcFeatureMapper.class); job.setReducerClass(CalcFeatureReducer.class); job.setOutputFormatClass(SequenceFileOutputFormat.class); job.setInputFormatClass(SequenceFileInputFormat.class); job.setMapOutputKeyClass(IntWritable.class); job.setMapOutputValueClass(MyKey.class); job.setOutputKeyClass(MyKey.class); job.setOutputValueClass(MyValue.class); FileInputFormat.setInputPaths(job, new Path(otherArgs[0])); FileOutputFormat.setOutputPath(job, new Path(otherArgs[1])); boolean res = job.waitForCompletion(true); if (!res) { System.err.println("step1 failed"); return; } } if (startStep <= 2) // sort { fs.delete(new Path(otherArgs[2]), true); System.out.println("sort"); Job job = new Job(conf, CalcFeatureWeights.class.getSimpleName()); job.setNumReduceTasks(1); job.setJarByClass(CalcFeatureWeights.class); job.setMapperClass(IdentityMapper.class); job.setReducerClass(IdentityReducer.class); job.setOutputFormatClass(SequenceFileOutputFormat.class); job.setInputFormatClass(SequenceFileInputFormat.class); job.setMapOutputKeyClass(MyKey.class); job.setMapOutputValueClass(MyValue.class); job.setOutputKeyClass(MyKey.class); job.setOutputValueClass(MyValue.class); FileInputFormat.setInputPaths(job, new Path(otherArgs[1])); FileOutputFormat.setOutputPath(job, new Path(otherArgs[2])); boolean res = job.waitForCompletion(true); if (!res) { System.err.println("step2 failed"); return; } } }
From source file:com.antbrains.crf.hadoop.ParallelTraining.java
License:Apache License
public static void main(String[] args) throws Exception { Configuration conf = new Configuration(); String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs(); if (otherArgs.length != 4) { System.err.println("ParallelTraining <instanceDir> <outDir> <featurecount> <training-params>"); System.exit(-1);// w w w .j a v a 2 s.c om } int featureCount = Integer.valueOf(otherArgs[2]); // conf.set("tc", object2String(tc)); conf.set("pt.iterate", "1"); conf.set("pt.featureCount", featureCount + ""); TrainingParams params = SgdCrf.loadParams(otherArgs[3]); System.out.println(new Gson().toJson(params)); conf.set("pt.params", object2String(params)); Job job = new Job(conf, ParallelTraining.class.getSimpleName()); job.setJarByClass(ParallelTraining.class); job.setMapperClass(TrainingMapper.class); job.setReducerClass(TrainingReducer.class); job.setOutputFormatClass(SequenceFileOutputFormat.class); job.setOutputKeyClass(NullWritable.class); job.setOutputValueClass(TrainingWeights.class); FileInputFormat.addInputPath(job, new Path(otherArgs[0])); FileOutputFormat.setOutputPath(job, new Path(otherArgs[1])); System.exit(job.waitForCompletion(true) ? 0 : 1); }
From source file:com.antbrains.crf.hadoop.ParallelTraining2.java
License:Apache License
public static void main(String[] args) throws Exception { Configuration conf = new Configuration(); String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs(); FileSystem fs = FileSystem.get(conf); TrainingParams params = SgdCrf.loadParams(otherArgs[3]); System.out.println(new Gson().toJson(params)); if (otherArgs.length != 5) { System.err.println(/*from w w w. ja v a2 s . c o m*/ "ParallelTraining2 <instanceDir> <outDir> <featurecount> <training-params> <out-iter>"); System.exit(-1); } int featureCount = Integer.valueOf(otherArgs[2]); // conf.set("tc", object2String(tc)); int outIter = Integer.valueOf(otherArgs[4]); String prevOutDir = ""; for (int i = 1; i <= outIter; i++) { System.out.println("iterator: " + i); conf.set("pt.iterate", i + ""); conf.set("pt.featureCount", featureCount + ""); conf.set("pt.params", object2String(params)); String outDir = otherArgs[1] + "/result" + i; if (i > 1) { conf.set("paramDir", prevOutDir); } prevOutDir = outDir; fs.delete(new Path(outDir), true); Job job = new Job(conf, ParallelTraining2.class.getSimpleName()); job.setJarByClass(ParallelTraining2.class); job.setMapperClass(TrainingMapper.class); job.setReducerClass(TrainingReducer.class); job.setOutputFormatClass(SequenceFileOutputFormat.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(DoubleWritable.class); FileInputFormat.addInputPath(job, new Path(otherArgs[0])); System.out.println("outDir: " + outDir); FileOutputFormat.setOutputPath(job, new Path(outDir)); boolean res = job.waitForCompletion(true); if (!res) { System.err.println("iter " + i + " failed"); break; } } }
From source file:com.architecting.ch07.MapReduceIndexerTool.java
License:Apache License
/** API for Java clients;visible for testing;may become a public API eventually */ int run(Options options) throws Exception { if (getConf().getBoolean("isMR1", false) && "local".equals(getConf().get("mapred.job.tracker"))) { throw new IllegalStateException( "Running with LocalJobRunner (i.e. all of Hadoop inside a single JVM) is not supported " + "because LocalJobRunner does not (yet) implement the Hadoop Distributed Cache feature, " + "which is required for passing files via --files and --libjars"); }/*from w ww . ja va 2 s.com*/ long programStartTime = System.nanoTime(); getConf().setInt(SolrOutputFormat.SOLR_RECORD_WRITER_MAX_SEGMENTS, options.maxSegments); // switch off a false warning about allegedly not implementing Tool // also see http://hadoop.6.n7.nabble.com/GenericOptionsParser-warning-td8103.html // also see https://issues.apache.org/jira/browse/HADOOP-8183 getConf().setBoolean("mapred.used.genericoptionsparser", true); if (options.log4jConfigFile != null) { Utils.setLogConfigFile(options.log4jConfigFile, getConf()); addDistributedCacheFile(options.log4jConfigFile, getConf()); } Configuration config = HBaseConfiguration.create(); Job job = Job.getInstance(config); job.setJarByClass(getClass()); // To be able to run this example from eclipse, we need to make sure // the built jar is distributed to the map-reduce tasks from the // local file system. job.addCacheArchive(new URI("file:///home/cloudera/ahae/target/ahae.jar")); FileSystem fs = options.outputDir.getFileSystem(job.getConfiguration()); if (fs.exists(options.outputDir) && !delete(options.outputDir, true, fs)) { return -1; } Path outputResultsDir = new Path(options.outputDir, RESULTS_DIR); Path outputReduceDir = new Path(options.outputDir, "reducers"); int reducers = 1; Scan scan = new Scan(); scan.addFamily(CF); // tag::SETUP[] scan.setCaching(500); // <1> scan.setCacheBlocks(false); // <2> TableMapReduceUtil.initTableMapperJob( // <3> options.inputTable, // Input HBase table name scan, // Scan instance to control what to index HBaseAvroToSOLRMapper.class, // Mapper to parse cells content. Text.class, // Mapper output key SolrInputDocumentWritable.class, // Mapper output value job); FileOutputFormat.setOutputPath(job, outputReduceDir); job.setJobName(getClass().getName() + "/" + Utils.getShortClassName(HBaseAvroToSOLRMapper.class)); job.setReducerClass(SolrReducer.class); // <4> job.setPartitionerClass(SolrCloudPartitioner.class); // <5> job.getConfiguration().set(SolrCloudPartitioner.ZKHOST, options.zkHost); job.getConfiguration().set(SolrCloudPartitioner.COLLECTION, options.collection); job.getConfiguration().setInt(SolrCloudPartitioner.SHARDS, options.shards); job.setOutputFormatClass(SolrOutputFormat.class); SolrOutputFormat.setupSolrHomeCache(options.solrHomeDir, job); job.setOutputKeyClass(Text.class); job.setOutputValueClass(SolrInputDocumentWritable.class); job.setSpeculativeExecution(false); // end::SETUP[] job.setNumReduceTasks(reducers); // Set the number of reducers based on the number of shards we have. if (!waitForCompletion(job, true)) { return -1;// job failed } // ------------------------------------------------------------------------------------------------------------------------------------- assert reducers == options.shards; // normalize output shard dir prefix, i.e. // rename part-r-00000 to part-00000 (stems from zero tree merge iterations) // rename part-m-00000 to part-00000 (stems from > 0 tree merge iterations) for (FileStatus stats : fs.listStatus(outputReduceDir)) { String dirPrefix = SolrOutputFormat.getOutputName(job); Path srcPath = stats.getPath(); if (stats.isDirectory() && srcPath.getName().startsWith(dirPrefix)) { String dstName = dirPrefix + srcPath.getName().substring(dirPrefix.length() + "-m".length()); Path dstPath = new Path(srcPath.getParent(), dstName); if (!rename(srcPath, dstPath, fs)) { return -1; } } } ; // publish results dir if (!rename(outputReduceDir, outputResultsDir, fs)) { return -1; } if (options.goLive && !new GoLive().goLive(options, listSortedOutputShardDirs(job, outputResultsDir, fs))) { return -1; } goodbye(job, programStartTime); return 0; }
From source file:com.asakusafw.runtime.mapreduce.simple.SimpleJobRunnerTest.java
License:Apache License
/** * Test for map only job./*from w w w .j ava 2s. c o m*/ * @throws Exception if failed */ @Test public void map_only() throws Exception { Job job = newJob(); job.setInputFormatClass(TextInputFormat.class); job.setOutputFormatClass(TextOutputFormat.class); job.setMapperClass(SimpleMapper.class); job.setNumReduceTasks(0); job.setOutputKeyClass(LongWritable.class); job.setOutputValueClass(Text.class); File inputDir = folder.newFolder(); File inputFile = new File(inputDir, "input.txt"); write(inputFile, "Hello, world!"); File outputDir = folder.newFolder(); outputDir.delete(); FileInputFormat.setInputPaths(job, new Path(inputFile.toURI())); FileOutputFormat.setOutputPath(job, new Path(outputDir.toURI())); assertThat(new SimpleJobRunner().run(job), is(true)); assertThat(trimHead(read(outputDir)), is(set("Hello, world!"))); }
From source file:com.asakusafw.runtime.mapreduce.simple.SimpleJobRunnerTest.java
License:Apache License
/** * Test for map-reduce job./*from w w w . j a va 2 s . c o m*/ * @throws Exception if failed */ @Test public void map_reduce() throws Exception { Job job = newJob(); job.setInputFormatClass(TextInputFormat.class); job.setOutputFormatClass(TextOutputFormat.class); job.setMapperClass(WordCountMapper.class); job.setMapOutputKeyClass(Text.class); job.setMapOutputValueClass(LongWritable.class); job.setSortComparatorClass(Text.Comparator.class); job.setGroupingComparatorClass(Text.Comparator.class); job.setReducerClass(WordCountReducer.class); job.setNumReduceTasks(1); job.setOutputKeyClass(Text.class); job.setOutputValueClass(LongWritable.class); File inputDir = folder.newFolder(); File inputFile = new File(inputDir, "input.txt"); write(inputFile, new String[] { "a b c d", "a a b c", "c", }); File outputDir = folder.newFolder(); outputDir.delete(); FileInputFormat.setInputPaths(job, new Path(inputFile.toURI())); FileOutputFormat.setOutputPath(job, new Path(outputDir.toURI())); assertThat(new SimpleJobRunner().run(job), is(true)); assertThat(toMap(read(outputDir)), is(map(new String[] { "a", "3", "b", "2", "c", "3", "d", "1", }))); }
From source file:com.asakusafw.runtime.mapreduce.simple.SimpleJobRunnerTest.java
License:Apache License
/** * Test for wrong job./*from www . j av a 2 s . c o m*/ * @throws Exception if failed */ @Test public void exception() throws Exception { Job job = newJob(); job.setJobName("w/ exception"); job.setInputFormatClass(TextInputFormat.class); job.setOutputFormatClass(TextOutputFormat.class); job.setMapperClass(InvalidMapper.class); job.setNumReduceTasks(0); job.setOutputKeyClass(LongWritable.class); job.setOutputValueClass(Text.class); File inputDir = folder.newFolder(); File inputFile = new File(inputDir, "input.txt"); write(inputFile, "testing"); File outputDir = folder.newFolder(); outputDir.delete(); FileInputFormat.setInputPaths(job, new Path(inputFile.toURI())); FileOutputFormat.setOutputPath(job, new Path(outputDir.toURI())); assertThat(new SimpleJobRunner().run(job), is(false)); }
From source file:com.asakusafw.runtime.stage.AbstractStageClient.java
License:Apache License
private void configureStageOutput(Job job, VariableTable variables) throws IOException { String outputPath = variables.parse(getStageOutputPath()); List<StageOutput> outputList = new ArrayList<>(); for (StageOutput output : getStageOutputs()) { String name = output.getName(); Class<?> keyClass = output.getKeyClass(); Class<?> valueClass = output.getValueClass(); Class<? extends OutputFormat<?, ?>> formatClass = output.getFormatClass(); Map<String, String> attributes = output.getAttributes(); if (LOG.isDebugEnabled()) { LOG.debug(MessageFormat.format( "Output: path={0}/{1}-*, format={2}, key={3}, value={4}, attributes={5}", //$NON-NLS-1$ outputPath, name, formatClass.getName(), keyClass.getName(), valueClass.getName(), attributes));//from ww w . j a v a 2 s.c o m } outputList.add(new StageOutput(name, keyClass, valueClass, formatClass, attributes)); } StageOutputDriver.set(job, outputPath, outputList); job.setOutputKeyClass(NullWritable.class); job.setOutputValueClass(NullWritable.class); job.setOutputFormatClass(StageOutputFormat.class); job.getConfiguration().setClass("mapred.output.committer.class", //$NON-NLS-1$ LegacyBridgeOutputCommitter.class, org.apache.hadoop.mapred.OutputCommitter.class); }
From source file:com.asakusafw.runtime.stage.output.StageOutputDriver.java
License:Apache License
private ResultOutput<?> buildNormalSink(String name, @SuppressWarnings("rawtypes") Class<? extends OutputFormat> formatClass, Class<?> keyClass, Class<?> valueClass, List<Counter> counters) throws IOException, InterruptedException { assert context != null; assert name != null; assert formatClass != null; assert keyClass != null; assert valueClass != null; assert counters != null; Job job = JobCompatibility.newJob(context.getConfiguration()); job.setOutputFormatClass(formatClass); job.setOutputKeyClass(keyClass);//from w w w . j a va 2 s . c om job.setOutputValueClass(valueClass); TaskAttemptContext localContext = JobCompatibility.newTaskAttemptContext(job.getConfiguration(), context.getTaskAttemptID()); if (FileOutputFormat.class.isAssignableFrom(formatClass)) { setOutputFilePrefix(localContext, name); } OutputFormat<?, ?> format = ReflectionUtils.newInstance(formatClass, localContext.getConfiguration()); RecordWriter<?, ?> writer = format.getRecordWriter(localContext); return new ResultOutput<Writable>(localContext, writer); }