List of usage examples for org.apache.hadoop.mapreduce Job setInputFormatClass
public void setInputFormatClass(Class<? extends InputFormat> cls) throws IllegalStateException
From source file:com.msd.gin.halyard.tools.HalyardHiveLoad.java
License:Apache License
@Override public int run(String[] args) throws Exception { if (args.length != 3) { System.err.println("Usage: hiveload -D" + RDF_MIME_TYPE_PROPERTY + "='application/ld+json' [-D" + MRJobConfig.QUEUE_NAME + "=proofofconcepts] [-D" + HIVE_DATA_COLUMN_INDEX_PROPERTY + "=3] [-D" + BASE_URI_PROPERTY + "='http://my_base_uri/'] [-D" + HalyardBulkLoad.SPLIT_BITS_PROPERTY + "=8] [-D" + HalyardBulkLoad.DEFAULT_CONTEXT_PROPERTY + "=http://new_context] [-D" + HalyardBulkLoad.OVERRIDE_CONTEXT_PROPERTY + "=true] <hive_table_name> <output_path> <hbase_table_name>"); return -1; }//from w w w . j a va 2 s . co m TableMapReduceUtil.addDependencyJars(getConf(), NTriplesUtil.class, Rio.class, AbstractRDFHandler.class, RDFFormat.class, RDFParser.class); HBaseConfiguration.addHbaseResources(getConf()); if (SnappyCodec.isNativeCodeLoaded()) { getConf().setBoolean(MRJobConfig.MAP_OUTPUT_COMPRESS, true); getConf().setClass(MRJobConfig.MAP_OUTPUT_COMPRESS_CODEC, SnappyCodec.class, CompressionCodec.class); } getConf().setDouble(MRJobConfig.COMPLETED_MAPS_FOR_REDUCE_SLOWSTART, 1.0); getConf().setLong(MRJobConfig.TASK_TIMEOUT, 3600000l); getConf().setInt(MRJobConfig.IO_SORT_FACTOR, 100); getConf().setInt(MRJobConfig.IO_SORT_MB, 1000); getConf().setInt(FileInputFormat.SPLIT_MAXSIZE, 1000000000); getConf().setInt(LoadIncrementalHFiles.MAX_FILES_PER_REGION_PER_FAMILY, 2048); Job job = Job.getInstance(getConf(), "HalyardHiveLoad -> " + args[1] + " -> " + args[2]); int i = args[0].indexOf('.'); HCatInputFormat.setInput(job, i > 0 ? args[0].substring(0, i) : null, args[0].substring(i + 1)); job.setJarByClass(HalyardHiveLoad.class); job.setMapperClass(HiveMapper.class); job.setMapOutputKeyClass(ImmutableBytesWritable.class); job.setMapOutputValueClass(KeyValue.class); job.setInputFormatClass(HCatInputFormat.class); job.setSpeculativeExecution(false); job.setReduceSpeculativeExecution(false); Map<String, Integer> contextSplitsMap = new HashMap<>(); for (Map.Entry<String, String> me : getConf().getValByRegex(HalyardBulkLoad.CONTEXT_SPLIT_REGEXP) .entrySet()) { int splits = Integer.parseInt(me.getKey().substring(me.getKey().lastIndexOf('.') + 1)); StringTokenizer stk = new StringTokenizer(me.getValue(), ","); while (stk.hasMoreTokens()) { contextSplitsMap.put(stk.nextToken(), splits); } } try (HTable hTable = HalyardTableUtils.getTable(getConf(), args[2], true, getConf().getInt(HalyardBulkLoad.SPLIT_BITS_PROPERTY, 3), contextSplitsMap)) { HFileOutputFormat2.configureIncrementalLoad(job, hTable.getTableDescriptor(), hTable.getRegionLocator()); FileInputFormat.setInputDirRecursive(job, true); FileInputFormat.setInputPaths(job, args[0]); FileOutputFormat.setOutputPath(job, new Path(args[1])); TableMapReduceUtil.addDependencyJars(job); TableMapReduceUtil.initCredentials(job); if (job.waitForCompletion(true)) { new LoadIncrementalHFiles(getConf()).doBulkLoad(new Path(args[1]), hTable); LOG.info("Bulk Load Completed.."); return 0; } } return -1; }
From source file:com.msd.gin.halyard.tools.HalyardParallelExport.java
License:Apache License
@Override public int run(String[] args) throws Exception { Options options = new Options(); options.addOption(newOption("h", null, "Prints this help")); options.addOption(newOption("v", null, "Prints version")); options.addOption(newOption("s", "source_htable", "Source HBase table with Halyard RDF store")); options.addOption(newOption("q", "sparql_query", "SPARQL tuple or graph query with use of '" + PARALLEL_SPLIT_FUNCTION_URI + "' function")); options.addOption(newOption("t", "target_url", "file://<path>/<file_name>{0}.<ext> or hdfs://<path>/<file_name>{0}.<ext> or jdbc:<jdbc_connection>/<table_name>")); options.addOption(newOption("p", "property=value", "JDBC connection properties")); options.addOption(newOption("l", "driver_classpath", "JDBC driver classpath delimited by ':'")); options.addOption(newOption("c", "driver_class", "JDBC driver class name")); try {/* w w w . j av a 2s . c o m*/ CommandLine cmd = new PosixParser().parse(options, args); if (args.length == 0 || cmd.hasOption('h')) { printHelp(options); return -1; } if (cmd.hasOption('v')) { Properties p = new Properties(); try (InputStream in = HalyardExport.class .getResourceAsStream("/META-INF/maven/com.msd.gin.halyard/hbasesail/pom.properties")) { if (in != null) p.load(in); } System.out.println("Halyard Parallel Export version " + p.getProperty("version", "unknown")); return 0; } if (!cmd.getArgList().isEmpty()) throw new ExportException("Unknown arguments: " + cmd.getArgList().toString()); for (char c : "sqt".toCharArray()) { if (!cmd.hasOption(c)) throw new ExportException("Missing mandatory option: " + c); } for (char c : "sqtlc".toCharArray()) { String s[] = cmd.getOptionValues(c); if (s != null && s.length > 1) throw new ExportException("Multiple values for option: " + c); } String source = cmd.getOptionValue('s'); String query = cmd.getOptionValue('q'); if (!query.contains(PARALLEL_SPLIT_FUNCTION_NAME)) { throw new ExportException("Parallel export SPARQL query must contain '" + PARALLEL_SPLIT_FUNCTION_URI + "' function."); } String target = cmd.getOptionValue('t'); if ((target.startsWith("file:") || target.startsWith("hdfs:")) && !target.contains("{0}")) { throw new ExportException( "Parallel export file target must contain '{0}' counter in the file path or name."); } getConf().set(SOURCE, source); getConf().set(QUERY, query); getConf().set(TARGET, target); String driver = cmd.getOptionValue('c'); if (driver != null) { getConf().set(JDBC_DRIVER, driver); } String props[] = cmd.getOptionValues('p'); if (props != null) { for (int i = 0; i < props.length; i++) { props[i] = Base64.encodeBase64String(props[i].getBytes(UTF8)); } getConf().setStrings(JDBC_PROPERTIES, props); } TableMapReduceUtil.addDependencyJars(getConf(), HalyardExport.class, NTriplesUtil.class, Rio.class, AbstractRDFHandler.class, RDFFormat.class, RDFParser.class, HTable.class, HBaseConfiguration.class, AuthenticationProtos.class, Trace.class); HBaseConfiguration.addHbaseResources(getConf()); Job job = Job.getInstance(getConf(), "HalyardParallelExport " + source + " -> " + target); String cp = cmd.getOptionValue('l'); if (cp != null) { String jars[] = cp.split(":"); for (int i = 0; i < jars.length; i++) { File f = new File(jars[i]); if (!f.isFile()) throw new ExportException("Invalid JDBC driver classpath element: " + jars[i]); job.addFileToClassPath(new Path(f.toURI())); jars[i] = f.getName(); } job.getConfiguration().setStrings(JDBC_CLASSPATH, jars); } job.setJarByClass(HalyardParallelExport.class); job.setMaxMapAttempts(1); job.setMapperClass(ParallelExportMapper.class); job.setMapOutputKeyClass(NullWritable.class); job.setMapOutputValueClass(Void.class); job.setNumReduceTasks(0); job.setInputFormatClass(IndexedInputFormat.class); job.setOutputFormatClass(NullOutputFormat.class); TableMapReduceUtil.initCredentials(job); if (job.waitForCompletion(true)) { LOG.info("Parallel Export Completed.."); return 0; } return -1; } catch (RuntimeException exp) { System.out.println(exp.getMessage()); printHelp(options); throw exp; } }
From source file:com.mvdb.platform.action.VersionMerge.java
License:Apache License
public static void main(String[] args) throws Exception { logger.error("error1"); logger.warn("warning1"); logger.info("info1"); logger.debug("debug1"); logger.trace("trace1"); ActionUtils.setUpInitFileProperty(); // LoggerContext lc = (LoggerContext) LoggerFactory.getILoggerFactory(); // StatusPrinter.print(lc); Configuration conf = new Configuration(); String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs(); //Also add lastMergedTimeStamp and mergeUptoTimestamp and passive db name which would be mv1 or mv2 if (otherArgs.length != 3) { System.err.println("Usage: versionmerge <customer-directory>"); System.exit(2);// w ww . jav a 2 s. c o m } //Example: file:/home/umesh/.mvdb/etl/data/alpha //Example: hdfs://localhost:9000/data/alpha String customerDirectory = otherArgs[0]; String lastMergedDirName = otherArgs[1]; String lastCopiedDirName = otherArgs[2]; org.apache.hadoop.conf.Configuration conf1 = new org.apache.hadoop.conf.Configuration(); //conf1.addResource(new Path("/home/umesh/ops/hadoop-1.2.0/conf/core-site.xml")); FileSystem hdfsFileSystem = FileSystem.get(conf1); Path topPath = new Path(customerDirectory); //Clean scratch db Path passiveDbPath = new Path(topPath, "db/mv1"); Path tempDbPath = new Path(topPath, "db/tmp-" + (int) (Math.random() * 100000)); if (hdfsFileSystem.exists(tempDbPath)) { boolean success = hdfsFileSystem.delete(tempDbPath, true); if (success == false) { System.err.println(String.format("Unable to delete temp directory %s", tempDbPath.toString())); System.exit(1); } } //last three parameters are hardcoded and the nulls must be replaced later after changing inout parameters. Path[] inputPaths = getInputPaths(hdfsFileSystem, topPath, lastMergedDirName, lastCopiedDirName, null); Set<String> tableNameSet = new HashSet<String>(); for (Path path : inputPaths) { tableNameSet.add(path.getName()); } Job job = new Job(conf, "versionmerge"); job.setJarByClass(VersionMerge.class); job.setMapperClass(VersionMergeMapper.class); job.setReducerClass(VersionMergeReducer.class); job.setMapOutputKeyClass(MergeKey.class); job.setMapOutputValueClass(BytesWritable.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(BytesWritable.class); job.setInputFormatClass(SequenceFileInputFormat.class); job.setOutputFormatClass(SequenceFileOutputFormat.class); String lastDirName = null; if (inputPaths != null && inputPaths.length > 1) { lastDirName = inputPaths[(inputPaths.length) - 2].getParent().getName(); } for (Path inputPath : inputPaths) { FileInputFormat.addInputPath(job, inputPath); } FileOutputFormat.setOutputPath(job, tempDbPath); for (String table : tableNameSet) { if (table.endsWith(".dat") == false) { continue; } table = table.replaceAll("-", ""); table = table.replaceAll(".dat", ""); MultipleOutputs.addNamedOutput(job, table, SequenceFileOutputFormat.class, Text.class, BytesWritable.class); } boolean success = job.waitForCompletion(true); System.out.println("Success:" + success); System.out.println(ManagementFactory.getRuntimeMXBean().getName()); if (success && lastDirName != null) { ActionUtils.setConfigurationValue(new Path(customerDirectory).getName(), ConfigurationKeys.LAST_MERGE_TO_MVDB_DIRNAME, lastDirName); } //hdfsFileSystem.delete(passiveDbPath, true); //hdfsFileSystem.rename(tempDbPath, passiveDbPath); System.exit(success ? 0 : 1); }
From source file:com.mycompany.hadooptrain.WordCount.java
public static void main(String[] args) throws IOException, InterruptedException, ClassNotFoundException { Path inputPath = new Path(args[0]); Path outputDir = new Path(args[1]); // Create configuration Configuration conf = new Configuration(true); // Create job Job job = new Job(conf, "WordCount"); job.setJarByClass(WordCountMapper.class); // Setup MapReduce job.setMapperClass(WordCountMapper.class); job.setReducerClass(WordCountReducer.class); job.setNumReduceTasks(1);// ww w . ja va2s . co m // Specify key / value job.setOutputKeyClass(Text.class); job.setOutputValueClass(IntWritable.class); // Input FileInputFormat.addInputPath(job, inputPath); job.setInputFormatClass(TextInputFormat.class); // Output FileOutputFormat.setOutputPath(job, outputDir); job.setOutputFormatClass(TextOutputFormat.class); // Delete output if exists FileSystem hdfs = FileSystem.get(conf); if (hdfs.exists(outputDir)) hdfs.delete(outputDir, true); // Execute job int code = job.waitForCompletion(true) ? 0 : 1; System.exit(code); }
From source file:com.mycompany.keywordsearch.KeywordSearch.java
public static void main(String[] args) throws Exception { Configuration conf = new Configuration(); conf.set(FileInputFormat.INPUT_DIR_RECURSIVE, String.valueOf(true)); Path input = new Path(args[0]); Path output = new Path(args[1]); BufferedReader in = new BufferedReader(new InputStreamReader(System.in, "UTF-8")); System.out.print("Keyword:\t"); conf.set(KEYWORD, in.readLine());/* w w w . j a v a2 s . c om*/ Job job = Job.getInstance(conf, "word count"); job.setJarByClass(KeywordSearch.class); job.setInputFormatClass(TextInputFormatV2.class); job.setMapperClass(TokenizerMapper.class); job.setCombinerClass(IntSumReducer.class); job.setReducerClass(IntSumReducer.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(IntWritable.class); clearOutput(conf, output); FileInputFormat.addInputPath(job, input); FileOutputFormat.setOutputPath(job, output); System.exit(job.waitForCompletion(true) ? 0 : 1); }
From source file:com.nearinfinity.blur.mapreduce.example.BlurExampleIndexerRebuild.java
License:Apache License
public static void main(String[] args) throws IOException, InterruptedException, ClassNotFoundException { Configuration configuration = new Configuration(); String[] otherArgs = new GenericOptionsParser(configuration, args).getRemainingArgs(); if (otherArgs.length != 2) { System.err.println("Usage: blurindexer <in> <out>"); System.exit(2);/*from ww w . j a v a 2s . co m*/ } AnalyzerDefinition ad = new AnalyzerDefinition(); ad.defaultDefinition = new ColumnDefinition(StandardAnalyzer.class.getName(), true, null); TableDescriptor descriptor = new TableDescriptor(); descriptor.analyzerDefinition = ad; descriptor.compressionBlockSize = 32768; descriptor.compressionClass = DefaultCodec.class.getName(); descriptor.isEnabled = true; descriptor.name = "test-table"; descriptor.shardCount = 1; descriptor.cluster = "default"; descriptor.tableUri = "./blur-testing"; BlurTask blurTask = new BlurTask(); blurTask.setTableDescriptor(descriptor); blurTask.setIndexingType(INDEXING_TYPE.REBUILD); blurTask.setOptimize(false); Job job = blurTask.configureJob(configuration); job.setJarByClass(BlurExampleIndexerRebuild.class); job.setMapperClass(BlurExampleMapper.class); job.setInputFormatClass(TextInputFormat.class); job.setOutputFormatClass(TextOutputFormat.class); FileInputFormat.addInputPath(job, new Path(otherArgs[0])); FileOutputFormat.setOutputPath(job, new Path(otherArgs[1], "job-" + System.currentTimeMillis())); long s = System.currentTimeMillis(); boolean waitForCompletion = job.waitForCompletion(true); long e = System.currentTimeMillis(); System.out.println("Completed in [" + (e - s) + " ms]"); System.exit(waitForCompletion ? 0 : 1); }
From source file:com.nearinfinity.blur.mapreduce.example.BlurExampleIndexerUpdate.java
License:Apache License
public static void main(String[] args) throws IOException, InterruptedException, ClassNotFoundException { Configuration configuration = new Configuration(); String[] otherArgs = new GenericOptionsParser(configuration, args).getRemainingArgs(); if (otherArgs.length != 2) { System.err.println("Usage: blurindexer <in> <out>"); System.exit(2);//w w w . j av a 2 s. com } AnalyzerDefinition ad = new AnalyzerDefinition(); ad.defaultDefinition = new ColumnDefinition(StandardAnalyzer.class.getName(), true, null); ZookeeperClusterStatus status = new ZookeeperClusterStatus("localhost"); TableDescriptor descriptor = status.getTableDescriptor(false, "default", "test-table"); BlurTask blurTask = new BlurTask(); blurTask.setTableDescriptor(descriptor); blurTask.setIndexingType(INDEXING_TYPE.UPDATE); Job job = blurTask.configureJob(configuration); job.setJarByClass(BlurExampleIndexerUpdate.class); job.setMapperClass(BlurExampleMapper.class); job.setInputFormatClass(TextInputFormat.class); job.setOutputFormatClass(TextOutputFormat.class); FileInputFormat.addInputPath(job, new Path(otherArgs[0])); FileOutputFormat.setOutputPath(job, new Path(otherArgs[1], "job-" + System.currentTimeMillis())); boolean waitForCompletion = job.waitForCompletion(true); System.exit(waitForCompletion ? 0 : 1); }
From source file:com.netflix.Aegisthus.java
License:Apache License
@Override public int run(String[] args) throws Exception { Job job = new Job(getConf()); job.setJarByClass(Aegisthus.class); CommandLine cl = getOptions(args);// w w w. j av a2 s .c o m if (cl == null) { return 1; } job.setInputFormatClass(AegisthusInputFormat.class); job.setMapOutputKeyClass(Text.class); job.setMapOutputValueClass(Text.class); job.setOutputFormatClass(TextOutputFormat.class); job.setMapperClass(Map.class); job.setReducerClass(CassReducer.class); List<Path> paths = Lists.newArrayList(); if (cl.hasOption(OPT_INPUT)) { for (String input : cl.getOptionValues(OPT_INPUT)) { paths.add(new Path(input)); } } if (cl.hasOption(OPT_INPUTDIR)) { paths.addAll(getDataFiles(job.getConfiguration(), cl.getOptionValue(OPT_INPUTDIR))); } TextInputFormat.setInputPaths(job, paths.toArray(new Path[0])); TextOutputFormat.setOutputPath(job, new Path(cl.getOptionValue(OPT_OUTPUT))); job.submit(); System.out.println(job.getJobID()); System.out.println(job.getTrackingURL()); boolean success = job.waitForCompletion(true); return success ? 0 : 1; }
From source file:com.netflix.bdp.s3.TestMRJob.java
License:Apache License
@Test public void testMRJob() throws Exception { FileSystem mockS3 = mock(FileSystem.class); FileSystem s3 = S3_OUTPUT_PATH.getFileSystem(getConfiguration()); if (s3 instanceof MockS3FileSystem) { ((MockS3FileSystem) s3).setMock(mockS3); } else {/*from w w w. j a v a2 s . c o m*/ throw new RuntimeException("Cannot continue: S3 not mocked"); } String commitUUID = UUID.randomUUID().toString(); int numFiles = 3; Set<String> expectedFiles = Sets.newHashSet(); for (int i = 0; i < numFiles; i += 1) { File file = temp.newFile(String.valueOf(i) + ".text"); try (FileOutputStream out = new FileOutputStream(file)) { out.write(("file " + i).getBytes(StandardCharsets.UTF_8)); } expectedFiles.add(new Path(S3_OUTPUT_PATH, "part-m-0000" + i + "-" + commitUUID).toString()); } Job mrJob = Job.getInstance(MR_CLUSTER.getConfig(), "test-committer-job"); Configuration conf = mrJob.getConfiguration(); mrJob.setOutputFormatClass(S3TextOutputFormat.class); S3TextOutputFormat.setOutputPath(mrJob, S3_OUTPUT_PATH); File mockResultsFile = temp.newFile("committer.bin"); mockResultsFile.delete(); String committerPath = "file:" + mockResultsFile; conf.set("mock-results-file", committerPath); conf.set(UPLOAD_UUID, commitUUID); mrJob.setInputFormatClass(TextInputFormat.class); TextInputFormat.addInputPath(mrJob, new Path("file:" + temp.getRoot().toString())); mrJob.setMapperClass(M.class); mrJob.setNumReduceTasks(0); mrJob.submit(); Assert.assertTrue("MR job should succeed", mrJob.waitForCompletion(true)); TestUtil.ClientResults results; try (ObjectInputStream in = new ObjectInputStream( FileSystem.getLocal(conf).open(new Path(committerPath)))) { results = (TestUtil.ClientResults) in.readObject(); } Assert.assertEquals("Should not delete files", 0, results.deletes.size()); Assert.assertEquals("Should not abort commits", 0, results.aborts.size()); Assert.assertEquals("Should commit task output files", numFiles, results.commits.size()); Set<String> actualFiles = Sets.newHashSet(); for (CompleteMultipartUploadRequest commit : results.commits) { actualFiles.add("s3://" + commit.getBucketName() + "/" + commit.getKey()); } Assert.assertEquals("Should commit the correct file paths", expectedFiles, actualFiles); }
From source file:com.neu.cs6240.Xml2csv.java
License:Apache License
public static void main(String[] args) throws Exception { Configuration conf = new Configuration(); // Setting up the xml tag configurator for splitter conf.set("xmlinput.start", "<row "); conf.set("xmlinput.end", " />"); String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs(); if (otherArgs.length != 2) { System.err.println("Usage: Xml2csv <in> <out>"); System.exit(2);//from w w w .ja v a2s . com } Job job = new Job(conf, "Converts Posts.xml to .csv"); job.setJarByClass(Xml2csv.class); job.setInputFormatClass(XmlInputFormat.class); job.setMapperClass(PostsMapper.class); job.setOutputKeyClass(NullWritable.class); job.setOutputValueClass(IntWritable.class); job.setNumReduceTasks(0); FileInputFormat.addInputPath(job, new Path(otherArgs[0])); FileOutputFormat.setOutputPath(job, new Path(otherArgs[1])); System.exit(job.waitForCompletion(true) ? 0 : 1); }