List of usage examples for org.apache.hadoop.mapred JobConf setInputFormat
public void setInputFormat(Class<? extends InputFormat> theClass)
From source file:com.ricemap.spateDB.util.RandomSpatialGenerator.java
License:Apache License
public static void generateMapReduce(Path file, Prism mbr, long size, long blocksize, Shape shape, String sindex, long seed, int rectsize, RandomShapeGenerator.DistributionType type, boolean overwrite) throws IOException { JobConf job = new JobConf(RandomSpatialGenerator.class); job.setJobName("Generator"); FileSystem outFs = file.getFileSystem(job); // Overwrite output file if (outFs.exists(file)) { if (overwrite) outFs.delete(file, true);/*from ww w. ja v a 2 s .co m*/ else throw new RuntimeException( "Output file '" + file + "' already exists and overwrite flag is not set"); } // Set generation parameters in job job.setLong(RandomShapeGenerator.GenerationSize, size); SpatialSite.setPrism(job, RandomShapeGenerator.GenerationMBR, mbr); if (seed != 0) job.setLong(RandomShapeGenerator.GenerationSeed, seed); if (rectsize != 0) job.setInt(RandomShapeGenerator.GenerationRectSize, rectsize); if (type != null) job.set(RandomShapeGenerator.GenerationType, type.toString()); ClusterStatus clusterStatus = new JobClient(job).getClusterStatus(); // Set input format and map class job.setInputFormat(RandomInputFormat.class); job.setMapperClass(Repartition.RepartitionMap.class); job.setMapOutputKeyClass(IntWritable.class); job.setMapOutputValueClass(shape.getClass()); job.setNumMapTasks(10 * Math.max(1, clusterStatus.getMaxMapTasks())); SpatialSite.setShapeClass(job, shape.getClass()); if (blocksize != 0) { job.setLong(SpatialSite.LOCAL_INDEX_BLOCK_SIZE, blocksize); } CellInfo[] cells; if (sindex == null) { cells = new CellInfo[] { new CellInfo(1, mbr) }; } else if (sindex.equals("grid")) { GridInfo gridInfo = new GridInfo(mbr.t1, mbr.x1, mbr.y1, mbr.t2, mbr.x2, mbr.y2); FileSystem fs = file.getFileSystem(job); if (blocksize == 0) { blocksize = fs.getDefaultBlockSize(file); } int numOfCells = Repartition.calculateNumberOfPartitions(job, size, fs, file, blocksize); gridInfo.calculateCellDimensions(numOfCells); cells = gridInfo.getAllCells(); } else { throw new RuntimeException("Unsupported spatial index: " + sindex); } SpatialSite.setCells(job, cells); // Do not set a reduce function. Use the default identity reduce function if (cells.length == 1) { // All objects are in one partition. No need for a reduce phase job.setNumReduceTasks(0); } else { // More than one partition. Need a reduce phase to group shapes of the // same partition together job.setReducerClass(RepartitionReduce.class); job.setNumReduceTasks( Math.max(1, Math.min(cells.length, (clusterStatus.getMaxReduceTasks() * 9 + 5) / 10))); } // Set output path FileOutputFormat.setOutputPath(job, file); if (sindex == null || sindex.equals("grid")) { job.setOutputFormat(GridOutputFormat.class); } else { throw new RuntimeException("Unsupported spatial index: " + sindex); } JobClient.runJob(job); // Concatenate all master files into one file FileStatus[] resultFiles = outFs.listStatus(file, new PathFilter() { @Override public boolean accept(Path path) { return path.getName().contains("_master"); } }); String ext = resultFiles[0].getPath().getName() .substring(resultFiles[0].getPath().getName().lastIndexOf('.')); Path masterPath = new Path(file, "_master" + ext); OutputStream destOut = outFs.create(masterPath); byte[] buffer = new byte[4096]; for (FileStatus f : resultFiles) { InputStream in = outFs.open(f.getPath()); int bytes_read; do { bytes_read = in.read(buffer); if (bytes_read > 0) destOut.write(buffer, 0, bytes_read); } while (bytes_read > 0); in.close(); outFs.delete(f.getPath(), false); } destOut.close(); // Plot an image for the partitions used in file Path imagePath = new Path(file, "_partitions.png"); int imageSize = (int) (Math.sqrt(cells.length) * 300); Plot.plotLocal(masterPath, imagePath, new Partition(), imageSize, imageSize, Color.BLACK, false, false, false); }
From source file:com.scaleoutsoftware.soss.hserver.Test_MapToMapCopyMapred.java
License:Apache License
public int run(String[] args) throws Exception { final NamedMap<IntWritable, Text> inputMap = NamedMapFactory.getMap("mapr-i", new WritableSerializer(IntWritable.class), new WritableSerializer(Text.class)); final NamedMap<IntWritable, Text> outputMap = NamedMapFactory.getMap("mapr-o", new WritableSerializer(IntWritable.class), new WritableSerializer(Text.class)); inputMap.clear();/*from www . java2 s . c o m*/ outputMap.clear(); Thread.sleep(15000); BulkLoader<IntWritable, Text> put = inputMap.getBulkLoader(); String content = "xcccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx"; Text contentW = new Text(content); IntWritable count = new IntWritable(); int expectedSize = 10000; for (int i = 0; i < expectedSize; i++) { count.set(i); put.put(count, contentW); } put.close(); InvocationGrid grid = HServerJob.getInvocationGridBuilder("MyGrid" + System.currentTimeMillis()) .addClass(Test_MapToMapCopyMapred.class).load(); JobConf configuration = new JobConf(getConf(), Test_MapToMapCopyMapred.class); configuration.setInt("mapred.hserver.setting.reducer.usememorymappedfiles", 0); configuration.setMapOutputKeyClass(IntWritable.class); configuration.setMapOutputValueClass(Text.class); configuration.setOutputKeyClass(IntWritable.class); configuration.setOutputValueClass(Text.class); configuration.setInputFormat(NamedMapInputFormatMapred.class); configuration.setOutputFormat(NamedMapOutputFormatMapred.class); NamedMapInputFormatMapred.setNamedMap(configuration, inputMap); NamedMapOutputFormatMapred.setNamedMap(configuration, outputMap); assertEquals(inputMap.size(), outputMap.size() + expectedSize); // should be 0 + expected HServerJobClient.runJob(configuration, false, grid); assertEquals(inputMap.size(), outputMap.size()); inputMap.clear(); outputMap.clear(); grid.unload(); return 1; }
From source file:com.spotify.hdfs2cass.BulkLoader.java
License:Apache License
public int run(String[] args) throws Exception { CommandLine cmdLine = parseOptions(args); String[] inputPaths = cmdLine.getOptionValues('i'); String seedNodeHost = cmdLine.getOptionValue('h'); String seedNodePort = cmdLine.getOptionValue('p', "9160"); String keyspace = cmdLine.getOptionValue('k'); String colfamily = cmdLine.getOptionValue('c'); int mappers = Integer.parseInt(cmdLine.getOptionValue('m', "0")); Integer copiers = Integer.parseInt(cmdLine.getOptionValue('P', "0")); String poolName = cmdLine.getOptionValue("pool"); ClusterInfo clusterInfo = new ClusterInfo(seedNodeHost, seedNodePort); clusterInfo.init(keyspace);/*from w ww . j a v a 2s . c om*/ final String partitionerClass = clusterInfo.getPartitionerClass(); final int reducers = adjustReducers(Integer.parseInt(cmdLine.getOptionValue('r', "0")), clusterInfo.getNumClusterNodes()); Configuration conf = new Configuration(); ConfigHelper.setOutputColumnFamily(conf, keyspace, colfamily); ConfigHelper.setOutputInitialAddress(conf, seedNodeHost); ConfigHelper.setOutputRpcPort(conf, seedNodePort); ConfigHelper.setOutputPartitioner(conf, partitionerClass); if (cmdLine.hasOption('s')) { conf.set("mapreduce.output.bulkoutputformat.buffersize", cmdLine.getOptionValue('s', "32")); } if (cmdLine.hasOption('M')) { conf.set("mapreduce.output.bulkoutputformat.streamthrottlembits", cmdLine.getOptionValue('M')); } if (cmdLine.hasOption('C')) { ConfigHelper.setOutputCompressionClass(conf, cmdLine.getOptionValue('C')); } if (cmdLine.hasOption('b')) { conf.setBoolean("com.spotify.hdfs2cass.base64", true); } JobConf job = new JobConf(conf); if (mappers > 0) job.setNumMapTasks(mappers); if (reducers > 0) job.setNumReduceTasks(reducers); if (copiers > 0) job.set("mapred.reduce.parallel.copies", copiers.toString()); if (poolName != null) job.set("mapred.fairscheduler.pool", poolName); // set the nodes as a param for the other hadoop nodes clusterInfo.setConf(job); String jobName = "bulkloader-hdfs-to-cassandra"; if (cmdLine.hasOption('n')) jobName += "-" + cmdLine.getOptionValue('n'); job.setJobName(jobName); job.setJarByClass(BulkLoader.class); job.setInputFormat(AvroAsTextInputFormat.class); for (String inputPath : inputPaths) { FileInputFormat.addInputPath(job, new Path(inputPath)); } //map just outputs text, reduce sends to cassandra job.setMapperClass(MapToText.class); job.setMapOutputKeyClass(Text.class); job.setMapOutputValueClass(Text.class); job.setPartitionerClass(CassandraPartitioner.class); job.setReducerClass(ReduceTextToCassandra.class); job.setOutputKeyClass(ByteBuffer.class); job.setOutputValueClass(List.class); if (cmdLine.hasOption('s')) job.setOutputFormat(BulkOutputFormat.class); else job.setOutputFormat(ColumnFamilyOutputFormat.class); JobClient.runJob(job); return 0; }
From source file:com.TCG.Nutch_DNS.Generator.java
License:Apache License
/** * Generate fetchlists in one or more segments. Whether to filter URLs or not * is read from the crawl.generate.filter property in the configuration files. * If the property is not found, the URLs are filtered. Same for the * normalisation.//from w ww. ja va 2 s .c om * * @param dbDir * Crawl database directory * @param segments * Segments directory * @param numLists * Number of reduce tasks * @param topN * Number of top URLs to be selected * @param curTime * Current time in milliseconds * * @return Path to generated segment or null if no entries were selected * * @throws IOException * When an I/O error occurs */ public Path[] generate(Path dbDir, Path segments, int numLists, long topN, long curTime, boolean filter, boolean norm, boolean force, int maxNumSegments) throws IOException { Path tempDir = new Path( getConf().get("mapred.temp.dir", ".") + "/generate-temp-" + UUID.randomUUID().toString()); Path lock = new Path(dbDir, CrawlDb.LOCK_NAME); FileSystem fs = FileSystem.get(getConf()); LockUtil.createLockFile(fs, lock, force); SimpleDateFormat sdf = new SimpleDateFormat("yyyy-MM-dd HH:mm:ss"); long start = System.currentTimeMillis(); LOG.info("Generator: starting at " + sdf.format(start)); LOG.info("Generator: Selecting best-scoring urls due for fetch."); LOG.info("Generator: filtering: " + filter); LOG.info("Generator: normalizing: " + norm); if (topN != Long.MAX_VALUE) { LOG.info("Generator: topN: " + topN); } // map to inverted subset due for fetch, sort by score JobConf job = new NutchJob(getConf()); job.setJobName("generate: select from " + dbDir); if (numLists == -1) { // for politeness make numLists = job.getNumMapTasks(); // a partition per fetch task } if ("local".equals(job.get("mapred.job.tracker")) && numLists != 1) { // override LOG.info("Generator: jobtracker is 'local', generating exactly one partition."); numLists = 1; } job.setLong(GENERATOR_CUR_TIME, curTime); // record real generation time long generateTime = System.currentTimeMillis(); job.setLong(Nutch.GENERATE_TIME_KEY, generateTime); job.setLong(GENERATOR_TOP_N, topN); job.setBoolean(GENERATOR_FILTER, filter); job.setBoolean(GENERATOR_NORMALISE, norm); job.setInt(GENERATOR_MAX_NUM_SEGMENTS, maxNumSegments); FileInputFormat.addInputPath(job, new Path(dbDir, CrawlDb.CURRENT_NAME)); job.setInputFormat(SequenceFileInputFormat.class); job.setMapperClass(Selector.class); job.setPartitionerClass(Selector.class); job.setReducerClass(Selector.class); FileOutputFormat.setOutputPath(job, tempDir); job.setOutputFormat(SequenceFileOutputFormat.class); job.setOutputKeyClass(FloatWritable.class); job.setOutputKeyComparatorClass(DecreasingFloatComparator.class); job.setOutputValueClass(SelectorEntry.class); job.setOutputFormat(GeneratorOutputFormat.class); try { JobClient.runJob(job); } catch (IOException e) { LockUtil.removeLockFile(fs, lock); fs.delete(tempDir, true); throw e; } // read the subdirectories generated in the temp // output and turn them into segments List<Path> generatedSegments = new ArrayList<Path>(); FileStatus[] status = fs.listStatus(tempDir); try { for (FileStatus stat : status) { Path subfetchlist = stat.getPath(); if (!subfetchlist.getName().startsWith("fetchlist-")) continue; // start a new partition job for this segment Path newSeg = partitionSegment(fs, segments, subfetchlist, numLists); generatedSegments.add(newSeg); } } catch (Exception e) { LOG.warn("Generator: exception while partitioning segments, exiting ..."); fs.delete(tempDir, true); return null; } if (generatedSegments.size() == 0) { LOG.warn("Generator: 0 records selected for fetching, exiting ..."); LockUtil.removeLockFile(fs, lock); fs.delete(tempDir, true); return null; } if (getConf().getBoolean(GENERATE_UPDATE_CRAWLDB, false)) { // update the db from tempDir Path tempDir2 = new Path( getConf().get("mapred.temp.dir", ".") + "/generate-temp-" + UUID.randomUUID().toString()); job = new NutchJob(getConf()); job.setJobName("generate: updatedb " + dbDir); job.setLong(Nutch.GENERATE_TIME_KEY, generateTime); for (Path segmpaths : generatedSegments) { Path subGenDir = new Path(segmpaths, CrawlDatum.GENERATE_DIR_NAME); FileInputFormat.addInputPath(job, subGenDir); } FileInputFormat.addInputPath(job, new Path(dbDir, CrawlDb.CURRENT_NAME)); job.setInputFormat(SequenceFileInputFormat.class); job.setMapperClass(CrawlDbUpdater.class); job.setReducerClass(CrawlDbUpdater.class); job.setOutputFormat(MapFileOutputFormat.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(CrawlDatum.class); FileOutputFormat.setOutputPath(job, tempDir2); try { JobClient.runJob(job); CrawlDb.install(job, dbDir); } catch (IOException e) { LockUtil.removeLockFile(fs, lock); fs.delete(tempDir, true); fs.delete(tempDir2, true); throw e; } fs.delete(tempDir2, true); } LockUtil.removeLockFile(fs, lock); fs.delete(tempDir, true); long end = System.currentTimeMillis(); LOG.info("Generator: finished at " + sdf.format(end) + ", elapsed: " + TimingUtil.elapsedTime(start, end)); Path[] patharray = new Path[generatedSegments.size()]; return generatedSegments.toArray(patharray); }
From source file:com.TCG.Nutch_DNS.HostDb.java
License:Apache License
public static JobConf createJob(Configuration config, Path crawlDb) throws IOException { Path newCrawlDb = new Path(crawlDb, Integer.toString(new Random().nextInt(Integer.MAX_VALUE))); JobConf job = new NutchJob(config); job.setJobName("crawldb " + crawlDb); Path current = new Path(crawlDb, CURRENT_NAME); if (FileSystem.get(job).exists(current)) { FileInputFormat.addInputPath(job, current); }/*from ww w . j ava 2 s . co m*/ job.setInputFormat(SequenceFileInputFormat.class); job.setMapperClass(HostDbFilter.class); job.setReducerClass(HostDbReducer.class); FileOutputFormat.setOutputPath(job, newCrawlDb); job.setOutputFormat(MapFileOutputFormat.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(CrawlDatum.class); // https://issues.apache.org/jira/browse/NUTCH-1110 job.setBoolean("mapreduce.fileoutputcommitter.marksuccessfuljobs", false); return job; }
From source file:com.test.hadoop.JhhSort.java
License:Apache License
/** * The main driver for sort program. Invoke this method to submit the * map/reduce job./* w w w . j a v a 2 s. com*/ * * @throws IOException * When there is communication problems with the job tracker. */ @SuppressWarnings({ "rawtypes" }) public int run(String[] args) throws Exception { JobConf jobConf = new JobConf(getConf(), JhhSort.class); jobConf.setJobName("sorter"); jobConf.set("mapred.job.tracker", "192.168.12.200:9001"); jobConf.set("fs.default.name", "hdfs://192.168.12.200:9000"); jobConf.setMapperClass(IdentityMapper.class); jobConf.setReducerClass(IdentityReducer.class); JobClient client = new JobClient(jobConf); ClusterStatus cluster = client.getClusterStatus(); int num_reduces = (int) (cluster.getMaxReduceTasks() * 0.5); String sort_reduces = jobConf.get("test.sort.reduces_per_host"); if (sort_reduces != null) { num_reduces = cluster.getTaskTrackers() * Integer.parseInt(sort_reduces); } Class<? extends InputFormat> inputFormatClass = TextInputFormat.class; Class<? extends OutputFormat> outputFormatClass = TextOutputFormat.class; Class<? extends WritableComparable> outputKeyClass = LongWritable.class; Class<? extends Writable> outputValueClass = LongWritable.class; List<String> otherArgs = new ArrayList<String>(); InputSampler.Sampler<K, V> sampler = null; for (int i = 0; i < args.length; ++i) { try { if ("-m".equals(args[i])) { jobConf.setNumMapTasks(Integer.parseInt(args[++i])); } else 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 ("-totalOrder".equals(args[i])) { double pcnt = Double.parseDouble(args[++i]); int numSamples = Integer.parseInt(args[++i]); int maxSplits = Integer.parseInt(args[++i]); if (0 >= maxSplits) maxSplits = Integer.MAX_VALUE; sampler = new InputSampler.RandomSampler<K, V>(pcnt, numSamples, maxSplits); } 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 jobConf.setNumReduceTasks(num_reduces); jobConf.setInputFormat(inputFormatClass); jobConf.setOutputFormat(outputFormatClass); jobConf.setOutputKeyClass(outputKeyClass); jobConf.setOutputValueClass(outputValueClass); // Make sure there are exactly 2 parameters left. if (otherArgs.size() != 2) { System.out.println("ERROR: Wrong number of parameters: " + otherArgs.size() + " instead of 2."); return printUsage(); } FileInputFormat.setInputPaths(jobConf, otherArgs.get(0)); FileOutputFormat.setOutputPath(jobConf, new Path(otherArgs.get(1))); if (sampler != null) { System.out.println("Sampling input to effect total-order sort..."); jobConf.setPartitionerClass(TotalOrderPartitioner.class); Path inputDir = FileInputFormat.getInputPaths(jobConf)[0]; inputDir = inputDir.makeQualified(inputDir.getFileSystem(jobConf)); Path partitionFile = new Path(inputDir, "_sortPartitioning"); TotalOrderPartitioner.setPartitionFile(jobConf, partitionFile); InputSampler.<K, V>writePartitionFile(jobConf, sampler); URI partitionUri = new URI(partitionFile.toString() + "#" + "_sortPartitioning"); DistributedCache.addCacheFile(partitionUri, jobConf); DistributedCache.createSymlink(jobConf); } System.out.println("Running on " + cluster.getTaskTrackers() + " nodes to sort from " + FileInputFormat.getInputPaths(jobConf)[0] + " into " + FileOutputFormat.getOutputPath(jobConf) + " with " + num_reduces + " reduces."); Date startTime = new Date(); System.out.println("Job started: " + startTime); jobResult = JobClient.runJob(jobConf); 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 0; }
From source file:com.test.hadoop.JhhSum.java
License:Apache License
@SuppressWarnings({ "rawtypes" })
public int run(String[] args) throws Exception {
JobConf jobConf = new JobConf(getConf(), JhhSum.class);
jobConf.setJobName("sum");
jobConf.set("mapred.job.tracker", "192.168.12.200:9001");
jobConf.set("fs.default.name", "hdfs://192.168.12.200:9000");
jobConf.setMapperClass(IdentityMapper.class);
jobConf.setReducerClass(LongSumReducer.class);
JobClient client = new JobClient(jobConf);
ClusterStatus cluster = client.getClusterStatus();
int num_reduces = (int) (cluster.getMaxReduceTasks() * 0.5);
String sort_reduces = jobConf.get("test.sort.reduces_per_host");
if (sort_reduces != null) {
num_reduces = cluster.getTaskTrackers() * Integer.parseInt(sort_reduces);
}//from w w w .j a va2 s . com
Class<? extends InputFormat> inputFormatClass = JhhInputFormat.class;
Class<? extends OutputFormat> outputFormatClass = TextOutputFormat.class;
Class<? extends WritableComparable> outputKeyClass = Text.class;
Class<? extends Writable> outputValueClass = LongWritable.class;
List<String> otherArgs = new ArrayList<String>();
for (int i = 0; i < args.length; ++i) {
otherArgs.add(args[i]);
}
// Set user-supplied (possibly default) job configs
jobConf.setNumReduceTasks(num_reduces);
jobConf.setInputFormat(inputFormatClass);
jobConf.setOutputFormat(outputFormatClass);
jobConf.setOutputKeyClass(outputKeyClass);
jobConf.setOutputValueClass(outputValueClass);
if (otherArgs.size() != 2) {
System.out.println("ERROR: Wrong number of parameters: " + otherArgs.size() + " instead of 2.");
}
FileInputFormat.setInputPaths(jobConf, otherArgs.get(0));
FileOutputFormat.setOutputPath(jobConf, new Path(otherArgs.get(1)));
System.out.println("Running on " + cluster.getTaskTrackers() + " nodes to sort from "
+ FileInputFormat.getInputPaths(jobConf)[0] + " into " + FileOutputFormat.getOutputPath(jobConf)
+ " with " + num_reduces + " reduces.");
Date startTime = new Date();
System.out.println("Job started: " + startTime);
jobResult = JobClient.runJob(jobConf);
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 0;
}
From source file:com.test.PiEstimatorKrb.java
License:Apache License
/** * Run a map/reduce job for estimating Pi. * * @return the estimated value of Pi// w w w. j ava2 s .com */ public static BigDecimal estimate(int numMaps, long numPoints, JobConf jobConf) throws IOException { //setup job conf jobConf.setJobName(PiEstimatorKrb.class.getSimpleName()); jobConf.setInputFormat(SequenceFileInputFormat.class); jobConf.setOutputKeyClass(BooleanWritable.class); jobConf.setOutputValueClass(LongWritable.class); jobConf.setOutputFormat(SequenceFileOutputFormat.class); jobConf.setMapperClass(PiMapper.class); jobConf.setNumMapTasks(numMaps); jobConf.setReducerClass(PiReducer.class); jobConf.setNumReduceTasks(1); // turn off speculative execution, because DFS doesn't handle // multiple writers to the same file. jobConf.setSpeculativeExecution(false); //setup input/output directories final Path inDir = new Path(TMP_DIR, "in"); final Path outDir = new Path(TMP_DIR, "out"); FileInputFormat.setInputPaths(jobConf, inDir); FileOutputFormat.setOutputPath(jobConf, outDir); final FileSystem fs = FileSystem.get(jobConf); if (fs.exists(TMP_DIR)) { throw new IOException( "Tmp directory " + fs.makeQualified(TMP_DIR) + " already exists. Please remove it first."); } if (!fs.mkdirs(inDir)) { throw new IOException("Cannot create input directory " + inDir); } try { //generate an input file for each map task for (int i = 0; i < numMaps; ++i) { final Path file = new Path(inDir, "part" + i); final LongWritable offset = new LongWritable(i * numPoints); final LongWritable size = new LongWritable(numPoints); final SequenceFile.Writer writer = SequenceFile.createWriter(fs, jobConf, file, LongWritable.class, LongWritable.class, CompressionType.NONE); try { writer.append(offset, size); } finally { writer.close(); } sLogger.info("Wrote input for Map #" + i); } //start a map/reduce job sLogger.info("Starting Job"); final long startTime = System.currentTimeMillis(); if (System.getenv("HADOOP_TOKEN_FILE_LOCATION") != null) { jobConf.set("mapreduce.job.credentials.binary", System.getenv("HADOOP_TOKEN_FILE_LOCATION")); } JobClient.runJob(jobConf); final double duration = (System.currentTimeMillis() - startTime) / 1000.0; sLogger.info("Job Finished in " + duration + " seconds"); //read outputs Path inFile = new Path(outDir, "reduce-out"); LongWritable numInside = new LongWritable(); LongWritable numOutside = new LongWritable(); SequenceFile.Reader reader = new SequenceFile.Reader(fs, inFile, jobConf); try { reader.next(numInside, numOutside); } finally { reader.close(); } //compute estimated value return BigDecimal.valueOf(4).setScale(20).multiply(BigDecimal.valueOf(numInside.get())) .divide(BigDecimal.valueOf(numMaps)).divide(BigDecimal.valueOf(numPoints)); } finally { fs.delete(TMP_DIR, true); } }
From source file:com.trace.hadoop.examples.Grep.java
License:Apache License
public int run(String[] args) throws Exception { if (args.length < 3) { System.out.println("Grep <inDir> <outDir> <regex> [<group>]"); ToolRunner.printGenericCommandUsage(System.out); return -1; }// w ww .j a v a 2 s.c o m Path tempDir = new Path("grep-temp-" + Integer.toString(new Random().nextInt(Integer.MAX_VALUE))); JobConf grepJob = new JobConf(getConf(), Grep.class); try { grepJob.setJobName("grep-search"); FileInputFormat.setInputPaths(grepJob, args[0]); grepJob.setMapperClass(RegexMapper.class); grepJob.set("mapred.mapper.regex", args[2]); if (args.length == 4) grepJob.set("mapred.mapper.regex.group", args[3]); grepJob.setCombinerClass(LongSumReducer.class); grepJob.setReducerClass(LongSumReducer.class); FileOutputFormat.setOutputPath(grepJob, tempDir); grepJob.setOutputFormat(SequenceFileOutputFormat.class); grepJob.setOutputKeyClass(Text.class); grepJob.setOutputValueClass(LongWritable.class); JobClient.runJob(grepJob); JobConf sortJob = new JobConf(getConf(), Grep.class); sortJob.setJobName("grep-sort"); FileInputFormat.setInputPaths(sortJob, tempDir); sortJob.setInputFormat(SequenceFileInputFormat.class); sortJob.setMapperClass(InverseMapper.class); sortJob.setNumReduceTasks(1); // write a single file FileOutputFormat.setOutputPath(sortJob, new Path(args[1])); sortJob.setOutputKeyComparatorClass // sort by decreasing freq (LongWritable.DecreasingComparator.class); JobClient.runJob(sortJob); } finally { FileSystem.get(grepJob).delete(tempDir, true); } return 0; }
From source file:com.twitter.scalding.parquet.scrooge.ParquetScroogeScheme.java
License:Apache License
@Override public void sourceConfInit(FlowProcess<JobConf> fp, Tap<JobConf, RecordReader, OutputCollector> tap, JobConf jobConf) { super.sourceConfInit(fp, tap, jobConf); jobConf.setInputFormat(DeprecatedParquetInputFormat.class); ParquetInputFormat.setReadSupportClass(jobConf, ScroogeReadSupport.class); ThriftReadSupport.setRecordConverterClass(jobConf, ScroogeRecordConverter.class); }