List of usage examples for org.apache.hadoop.mapred JobConf setOutputKeyComparatorClass
public void setOutputKeyComparatorClass(Class<? extends RawComparator> theClass)
From source file:org.terrier.applications.HadoopIndexing.java
License:Mozilla Public License
/** Starts the MapReduce indexing. * @param args// w w w . ja va 2 s . co m * @throws Exception */ public static void main(String[] args) throws Exception { long time = System.currentTimeMillis(); boolean docPartitioned = false; int numberOfReducers = Integer .parseInt(ApplicationSetup.getProperty("terrier.hadoop.indexing.reducers", "26")); final HadoopPlugin.JobFactory jf = HadoopPlugin.getJobFactory("HOD-TerrierIndexing"); if (args.length == 2 && args[0].equals("-p")) { logger.info("Document-partitioned Mode, " + numberOfReducers + " output indices."); numberOfReducers = Integer.parseInt(args[1]); docPartitioned = true; } else if (args.length == 1 && args[0].equals("--merge")) { if (numberOfReducers > 1) mergeLexiconInvertedFiles(ApplicationSetup.TERRIER_INDEX_PATH, numberOfReducers); else logger.error("No point merging 1 reduce task output"); return; } else if (args.length == 0) { logger.info("Term-partitioned Mode, " + numberOfReducers + " reducers creating one inverted index."); docPartitioned = false; if (numberOfReducers > MAX_REDUCE) { logger.warn("Excessive reduce tasks (" + numberOfReducers + ") in use " + "- SplitEmittedTerm.SETPartitionerLowercaseAlphaTerm can use " + MAX_REDUCE + " at most"); } } else { logger.fatal(usage()); return; } if (!(CompressionFactory.getCompressionConfiguration("inverted", new String[0], false) instanceof BitCompressionConfiguration)) { logger.error("Sorry, only default BitCompressionConfiguration is supported by HadoopIndexing" + " - you can recompress the inverted index later using IndexRecompressor"); return; } if (jf == null) throw new Exception("Could not get JobFactory from HadoopPlugin"); final JobConf conf = jf.newJob(); conf.setJobName("terrierIndexing"); if (Files.exists(ApplicationSetup.TERRIER_INDEX_PATH) && Index.existsIndex(ApplicationSetup.TERRIER_INDEX_PATH, ApplicationSetup.TERRIER_INDEX_PREFIX)) { logger.fatal("Cannot index while index exists at " + ApplicationSetup.TERRIER_INDEX_PATH + "," + ApplicationSetup.TERRIER_INDEX_PREFIX); return; } boolean blockIndexing = ApplicationSetup.BLOCK_INDEXING; if (blockIndexing) { conf.setMapperClass(Hadoop_BlockSinglePassIndexer.class); conf.setReducerClass(Hadoop_BlockSinglePassIndexer.class); } else { conf.setMapperClass(Hadoop_BasicSinglePassIndexer.class); conf.setReducerClass(Hadoop_BasicSinglePassIndexer.class); } FileOutputFormat.setOutputPath(conf, new Path(ApplicationSetup.TERRIER_INDEX_PATH)); conf.set("indexing.hadoop.prefix", ApplicationSetup.TERRIER_INDEX_PREFIX); conf.setMapOutputKeyClass(SplitEmittedTerm.class); conf.setMapOutputValueClass(MapEmittedPostingList.class); conf.setBoolean("indexing.hadoop.multiple.indices", docPartitioned); if (!conf.get("mapred.job.tracker").equals("local")) { conf.setMapOutputCompressorClass(GzipCodec.class); conf.setCompressMapOutput(true); } else { conf.setCompressMapOutput(false); } conf.setInputFormat(MultiFileCollectionInputFormat.class); conf.setOutputFormat(NullOutputFormat.class); conf.setOutputKeyComparatorClass(SplitEmittedTerm.SETRawComparatorTermSplitFlush.class); conf.setOutputValueGroupingComparator(SplitEmittedTerm.SETRawComparatorTerm.class); conf.setReduceSpeculativeExecution(false); //parse the collection.spec BufferedReader specBR = Files.openFileReader(ApplicationSetup.COLLECTION_SPEC); String line = null; List<Path> paths = new ArrayList<Path>(); while ((line = specBR.readLine()) != null) { if (line.startsWith("#")) continue; paths.add(new Path(line)); } specBR.close(); FileInputFormat.setInputPaths(conf, paths.toArray(new Path[paths.size()])); conf.setNumReduceTasks(numberOfReducers); if (numberOfReducers > 1) { if (docPartitioned) conf.setPartitionerClass(SplitEmittedTerm.SETPartitioner.class); else conf.setPartitionerClass(SplitEmittedTerm.SETPartitionerLowercaseAlphaTerm.class); } else { //for JUnit tests, we seem to need to restore the original partitioner class conf.setPartitionerClass(HashPartitioner.class); } JobID jobId = null; boolean ranOK = true; try { RunningJob rj = JobClient.runJob(conf); jobId = rj.getID(); HadoopUtility.finishTerrierJob(conf); } catch (Exception e) { logger.error("Problem running job", e); ranOK = false; } if (jobId != null) { deleteTaskFiles(ApplicationSetup.TERRIER_INDEX_PATH, jobId); } if (ranOK) { if (!docPartitioned) { if (numberOfReducers > 1) mergeLexiconInvertedFiles(ApplicationSetup.TERRIER_INDEX_PATH, numberOfReducers); } Hadoop_BasicSinglePassIndexer.finish(ApplicationSetup.TERRIER_INDEX_PATH, docPartitioned ? numberOfReducers : 1, jf); } System.out.println("Time Taken = " + ((System.currentTimeMillis() - time) / 1000) + " seconds"); jf.close(); }
From source file:ucsc.hadoop.mapreduce.apache.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; }//from ww w .java2 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); // second job 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])); // sort by decreasing freq sortJob.setOutputKeyComparatorClass(LongWritable.DecreasingComparator.class); JobClient.runJob(sortJob); } finally { FileSystem.get(grepJob).delete(tempDir, true); } return 0; }
From source file:voldemort.store.readonly.mr.serialization.JsonMapper.java
License:Apache License
public void configure(JobConf conf) { setInputKeySerializer(getSchemaFromJob(conf, "mapper.input.key.schema")); setInputValueSerializer(getSchemaFromJob(conf, "mapper.input.value.schema")); setOutputKeySerializer(getSchemaFromJob(conf, "mapper.output.key.schema")); setOutputValueSerializer(getSchemaFromJob(conf, "mapper.output.value.schema")); // set comparator for input Key Schema if (conf.getBoolean("use.json.comparator", false)) { conf.setOutputKeyComparatorClass(JsonDeserializerComparator.class); conf.set("json.schema", conf.get("mapper.output.key.schema")); }//from ww w . j ava 2s .co m setConfigured(true); }
From source file:voldemort.store.readonly.mr.serialization.JsonReducer.java
License:Apache License
public void configure(JobConf conf) { setInputKeySerializer(getSchemaFromJob(conf, "mapper.output.key.schema")); setInputValueSerializer(getSchemaFromJob(conf, "mapper.output.value.schema")); setOutputKeySerializer(getSchemaFromJob(conf, "reducer.output.key.schema")); setOutputValueSerializer(getSchemaFromJob(conf, "reducer.output.value.schema")); // set comparator for input Key Schema if (conf.getBoolean("use.json.comparator", false)) { conf.setOutputKeyComparatorClass(JsonDeserializerComparator.class); conf.set("json.schema", conf.get("mapper.output.key.schema")); }/*from w w w. j a va 2 s . c o m*/ setConfigured(true); }