List of usage examples for org.apache.hadoop.mapreduce Job setOutputKeyClass
public void setOutputKeyClass(Class<?> theClass) throws IllegalStateException
From source file:com.ery.hadoop.mrddx.hive.HiveSequenceFileOutputFormat.java
License:Apache License
@Override public void handle(Job conf) throws Exception { super.handle(conf); conf.setOutputKeyClass(LongWritable.class); conf.setOutputValueClass(Text.class); conf.setOutputFormatClass(HiveSequenceFileOutputFormat.class); }
From source file:com.example.bigtable.sample.CellCounter.java
License:Apache License
/** * Sets up the actual job./*from ww w.j a va 2 s .co m*/ * * @param conf The current configuration. * @param args The command line parameters. * @return The newly created job. * @throws IOException When setting up the job fails. */ public static Job createSubmittableJob(Configuration conf, String[] args) throws IOException { String tableName = args[0]; Path outputDir = new Path(args[1]); String reportSeparatorString = (args.length > 2) ? args[2] : ":"; conf.set("ReportSeparator", reportSeparatorString); Job job = Job.getInstance(conf, conf.get(JOB_NAME_CONF_KEY, NAME + "_" + tableName)); job.setJarByClass(CellCounter.class); Scan scan = getConfiguredScanForJob(conf, args); TableMapReduceUtil.initTableMapperJob(tableName, scan, CellCounterMapper.class, ImmutableBytesWritable.class, Result.class, job); job.setNumReduceTasks(1); job.setMapOutputKeyClass(Text.class); job.setMapOutputValueClass(IntWritable.class); job.setOutputFormatClass(TextOutputFormat.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(IntWritable.class); FileOutputFormat.setOutputPath(job, outputDir); job.setReducerClass(IntSumReducer.class); return job; }
From source file:com.example.Driver.java
License:Open Source License
public int run(String[] args) throws Exception { Configuration conf = new Configuration(); Job job = Job.getInstance(conf, "Your job name"); job.setJarByClass(Driver.class); logger.info("job " + job.getJobName() + " [" + job.getJar() + "] started with the following arguments: " + Arrays.toString(args)); if (args.length < 2) { logger.warn("to run this jar are necessary at 2 parameters \"" + job.getJar() + " input_files output_directory"); return 1; }//from w w w .j a va 2 s. c o m job.setMapperClass(WordcountMapper.class); logger.info("mapper class is " + job.getMapperClass()); //job.setMapOutputKeyClass(Text.class); //job.setMapOutputValueClass(IntWritable.class); logger.info("mapper output key class is " + job.getMapOutputKeyClass()); logger.info("mapper output value class is " + job.getMapOutputValueClass()); job.setReducerClass(WordcountReducer.class); logger.info("reducer class is " + job.getReducerClass()); job.setCombinerClass(WordcountReducer.class); logger.info("combiner class is " + job.getCombinerClass()); //When you are not runnign any Reducer //OR job.setNumReduceTasks(0); // logger.info("number of reduce task is " + job.getNumReduceTasks()); job.setOutputKeyClass(Text.class); job.setOutputValueClass(IntWritable.class); logger.info("output key class is " + job.getOutputKeyClass()); logger.info("output value class is " + job.getOutputValueClass()); job.setInputFormatClass(TextInputFormat.class); logger.info("input format class is " + job.getInputFormatClass()); job.setOutputFormatClass(TextOutputFormat.class); logger.info("output format class is " + job.getOutputFormatClass()); Path filePath = new Path(args[0]); logger.info("input path " + filePath); FileInputFormat.setInputPaths(job, filePath); Path outputPath = new Path(args[1]); logger.info("output path " + outputPath); FileOutputFormat.setOutputPath(job, outputPath); job.waitForCompletion(true); return 0; }
From source file:com.examples.ch03.ParseWeblogs_Ex_1.java
public int run(String[] args) throws Exception { Path inputPath = new Path("apache_clf.txt"); Path outputPath = new Path("output"); Configuration conf = getConf(); Job weblogJob = Job.getInstance(conf); weblogJob.setJobName("Weblog Transformer"); weblogJob.setJarByClass(getClass()); weblogJob.setNumReduceTasks(0);/*from w w w. j a v a 2s. c om*/ weblogJob.setMapperClass(CLFMapper_Ex_1.class); weblogJob.setMapOutputKeyClass(Text.class); weblogJob.setMapOutputValueClass(Text.class); weblogJob.setOutputKeyClass(Text.class); weblogJob.setOutputValueClass(Text.class); weblogJob.setInputFormatClass(TextInputFormat.class); weblogJob.setOutputFormatClass(TextOutputFormat.class); FileInputFormat.setInputPaths(weblogJob, inputPath); FileOutputFormat.setOutputPath(weblogJob, outputPath); if (weblogJob.waitForCompletion(true)) { return 0; } return 1; }
From source file:com.fanlehai.hadoop.join.CompositeJoin.java
License:Apache License
/** * The main driver for sort program. Invoke this method to submit the * map/reduce job.// w w w .j a va2 s . c o m * * @throws IOException * When there is communication problems with the job tracker. */ @SuppressWarnings("rawtypes") public int run(String[] args) throws Exception { Configuration conf = getConf(); JobClient client = new JobClient(conf); ClusterStatus cluster = client.getClusterStatus(); int num_reduces = (int) (cluster.getMaxReduceTasks() * 0.9); String join_reduces = conf.get(REDUCES_PER_HOST); if (join_reduces != null) { num_reduces = cluster.getTaskTrackers() * Integer.parseInt(join_reduces); } Job job = Job.getInstance(conf); job.setJobName("join"); job.setJarByClass(CompositeJoin.class); job.setMapperClass(Mapper.class); job.setReducerClass(Reducer.class); Class<? extends InputFormat> inputFormatClass = KeyValueTextInputFormat.class;// SequenceFileInputFormat.class; Class<? extends OutputFormat> outputFormatClass = SequenceFileOutputFormat.class; Class<? extends WritableComparable> outputKeyClass = Text.class;// BytesWritable.class; Class<? extends Writable> outputValueClass = Text.class;//TupleWritable.class; String op = "inner"; List<String> otherArgs = new ArrayList<String>(); for (int i = 0; i < args.length; ++i) { try { if ("-r".equals(args[i])) { num_reduces = Integer.parseInt(args[++i]); } else if ("-inFormat".equals(args[i])) { inputFormatClass = Class.forName(args[++i]).asSubclass(InputFormat.class); } else if ("-outFormat".equals(args[i])) { outputFormatClass = Class.forName(args[++i]).asSubclass(OutputFormat.class); } else if ("-outKey".equals(args[i])) { outputKeyClass = Class.forName(args[++i]).asSubclass(WritableComparable.class); } else if ("-outValue".equals(args[i])) { outputValueClass = Class.forName(args[++i]).asSubclass(Writable.class); } else if ("-joinOp".equals(args[i])) { op = args[++i]; } else { otherArgs.add(args[i]); } } catch (NumberFormatException except) { System.out.println("ERROR: Integer expected instead of " + args[i]); return printUsage(); } catch (ArrayIndexOutOfBoundsException except) { System.out.println("ERROR: Required parameter missing from " + args[i - 1]); return printUsage(); // exits } } // Set user-supplied (possibly default) job configs job.setNumReduceTasks(num_reduces); if (otherArgs.size() < 2) { System.out.println("ERROR: Wrong number of parameters: "); return printUsage(); } String strOut = otherArgs.remove(otherArgs.size() - 1); FileSystem.get(new Configuration()).delete(new Path(strOut), true); FileOutputFormat.setOutputPath(job, new Path(strOut)); List<Path> plist = new ArrayList<Path>(otherArgs.size()); for (String s : otherArgs) { plist.add(new Path(s)); } job.setInputFormatClass(CompositeInputFormat.class); job.getConfiguration().set(CompositeInputFormat.JOIN_EXPR, CompositeInputFormat.compose(op, inputFormatClass, plist.toArray(new Path[0]))); job.setOutputFormatClass(outputFormatClass); job.setMapperClass(MapComposite.class); job.setOutputKeyClass(outputKeyClass); job.setOutputValueClass(outputValueClass); Date startTime = new Date(); System.out.println("Job started: " + startTime); int ret = job.waitForCompletion(true) ? 0 : 1; Date end_time = new Date(); System.out.println("Job ended: " + end_time); System.out.println("The job took " + (end_time.getTime() - startTime.getTime()) / 1000 + " seconds."); return ret; }
From source file:com.flipkart.fdp.migration.distcp.core.MirrorDistCPDriver.java
License:Apache License
private Job createJob(Configuration configuration) throws Exception { System.out.println("Initializing BlueShift v 2.0..."); System.out.println("Configuration: " + dcmConfig.toString()); Job job = Job.getInstance(configuration, "BlueShift v 2.0 - " + dcmConfig.getBatchName()); job.setJarByClass(MirrorDistCPDriver.class); job.setMapOutputKeyClass(Text.class); job.setMapOutputValueClass(Text.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(Text.class); job.setMapperClass(MirrorMapper.class); job.setReducerClass(MirrorReducer.class); job.setInputFormatClass(MirrorFileInputFormat.class); job.setOutputFormatClass(TextOutputFormat.class); FileOutputFormat.setOutputPath(job, stateManager.getReportPath()); job.setNumReduceTasks(configuration.getInt("mapreduce.reduce.tasks", 1)); System.out.println("Job Initialization Complete, The status of the Mirror job will be written to: " + stateManager.getReportPath()); return job;//from ww w .java 2 s .c o m }
From source file:com.flytxt.yesbank.processor.HdfsToHbaseEngine.java
License:Open Source License
public static void main(String[] args) throws Exception { if (args.length < 1) { System.out.println("Hdfs to Hbase Engine requires the model Id as Input ..."); System.exit(1);//w ww .jav a2s . com } String modelId = args[0]; DBConnection dbConnection = DBConnection.getInstance(); dbConnection.loadDbProperties(); dbConnection.initializeDataBaseConnection(); String hfdsInputLoc = dbConnection.getHdfsInputDirectory(modelId); if (hfdsInputLoc != null) { Configuration conf = new Configuration(); String params = args[0]; conf.set("test", params); Job job = new Job(conf); // Configuration conf = new Configuration(); // Job job = Job.getInstance(conf, "hfds to hbase Engine"); job.setJarByClass(HdfsToHbaseEngine.class); job.setMapperClass(HdfsEngineMapper.class); // job.setCombinerClass(test.class); // job.setReducerClass(test.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(IntWritable.class); FileInputFormat.addInputPath(job, new Path(hfdsInputLoc)); job.setOutputFormatClass(NullOutputFormat.class); // FileOutputFormat.setOutputPath(job, new Path("/output_dir")); // conf.set("argParamValue", args[2]); // System.out.println("second argument value ------" + args[0]); // System.out.println(" in main method conf.getStrings --------" + // conf.get("argParamValue")); System.exit(job.waitForCompletion(true) ? 0 : 1); } else { System.out.println(" Hdfs Input Location deos not exists .. Unable to process the Request ...."); System.exit(0); } }
From source file:com.flytxt.yesbank.test.ModelProcessor.java
License:Open Source License
public static void main(String[] args) throws Exception { String modelId = args[0];// w w w . j av a 2 s . co m ModelProcessor modelProcessor = new ModelProcessor(); modelProcessor.loadDbProperties(); modelProcessor.initializeDataBaseConnection(); String hfdsInputLoc = modelProcessor.getHdfsInputDirectory(modelId); if (hfdsInputLoc != null) { Configuration conf = new Configuration(); String params = args[0]; conf.set("test", params); Job job = new Job(conf); // Configuration conf = new Configuration(); // Job job = Job.getInstance(conf, "word count"); job.setJarByClass(ModelProcessor.class); job.setMapperClass(HdfsProcessMapper.class); // job.setCombinerClass(IntSumReducer.class); // job.setReducerClass(IntSumReducer.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(IntWritable.class); FileInputFormat.addInputPath(job, new Path(hfdsInputLoc)); job.setOutputFormatClass(NullOutputFormat.class); // FileOutputFormat.setOutputPath(job, new Path("/output_dir")); // conf.set("argParamValue", args[2]); // System.out.println("second argument value ------" + args[0]); // System.out.println(" in main method conf.getStrings --------" + // conf.get("argParamValue")); System.exit(job.waitForCompletion(true) ? 0 : 1); } else { System.out.println(" Hdfs Input Location deos not exists .. Unable to process the Request ...."); System.exit(0); } }
From source file:com.frdeso.app.Sleepy.java
License:Apache License
/** * Performs integer summation of all the values for each key. *//*from w w w . j a v a2 s. c om*/ @Override public int run(String[] args) throws Exception { if (args.length != 3) { System.err.println("Usage: wordmean <in> <out> <number second>"); return 0; } Configuration conf = getConf(); conf.set("mapSleepTime", args[2]); @SuppressWarnings("deprecation") Job job = new Job(conf, "joba"); job.setJarByClass(Sleepy.class); job.setMapperClass(SleepyMapper.class); job.setCombinerClass(Reducer.class); job.setReducerClass(Reducer.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(IntWritable.class); FileInputFormat.addInputPath(job, new Path(args[0])); Path outputpath = new Path(args[1]); FileOutputFormat.setOutputPath(job, outputpath); boolean result = job.waitForCompletion(true); return (result ? 0 : 1); }
From source file:com.github.libsml.commons.util.HadoopUtils.java
License:Apache License
/** * Create a map-only Hadoop Job out of the passed in parameters. Does not set the * Job name./*www .j av a2 s .c o m*/ * * @see #getCustomJobName(String, JobContext, Class, Class) */ public static Job prepareJob(Path inputPath, Path outputPath, Class<? extends InputFormat> inputFormat, Class<? extends Mapper> mapper, Class<? extends Writable> mapperKey, Class<? extends Writable> mapperValue, Class<? extends OutputFormat> outputFormat, Configuration conf) throws IOException { // Job job = new Job(new Configuration(conf)); Job job = Job.getInstance(conf); Configuration jobConf = job.getConfiguration(); if (mapper.equals(Mapper.class)) { throw new IllegalStateException("Can't figure out the user class jar file from mapper/reducer"); } job.setJarByClass(mapper); job.setInputFormatClass(inputFormat); jobConf.set("mapred.input.dir", inputPath.toString()); job.setMapperClass(mapper); job.setMapOutputKeyClass(mapperKey); job.setMapOutputValueClass(mapperValue); job.setOutputKeyClass(mapperKey); job.setOutputValueClass(mapperValue); jobConf.setBoolean("mapred.compress.map.output", true); job.setNumReduceTasks(0); job.setOutputFormatClass(outputFormat); jobConf.set("mapred.output.dir", outputPath.toString()); return job; }