List of usage examples for org.apache.hadoop.mapreduce Job getInstance
@Deprecated public static Job getInstance(Cluster ignored, Configuration conf) throws IOException
From source file:com.marklogic.mapreduce.examples.WikiLoader.java
License:Apache License
public static void main(String[] args) throws Exception { Configuration conf = new Configuration(); if (args.length < 2) { System.err.println("Usage: WikiLoader configFile inputDir"); System.exit(2);/*ww w . j a v a 2 s. c om*/ } String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs(); Job job = Job.getInstance(conf, "wiki loader"); job.setJarByClass(WikiLoader.class); job.setInputFormatClass(WikiInputFormat.class); job.setMapperClass(ArticleMapper.class); job.setMapOutputKeyClass(DocumentURI.class); job.setMapOutputValueClass(Text.class); job.setOutputFormatClass(ContentOutputFormat.class); ContentInputFormat.setInputPaths(job, new Path(otherArgs[1])); conf = job.getConfiguration(); conf.addResource(otherArgs[0]); System.exit(job.waitForCompletion(true) ? 0 : 1); }
From source file:com.marklogic.mapreduce.examples.ZipContentLoader.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 != 2) { System.err.println("Usage: ZipContentLoader configFile inputDir"); System.exit(2);//from w w w. j a va 2 s .c o m } Job job = Job.getInstance(conf, "zip content loader"); job.setJarByClass(ZipContentLoader.class); job.setInputFormatClass(ZipContentInputFormat.class); job.setMapperClass(ZipContentMapper.class); job.setMapOutputKeyClass(DocumentURI.class); job.setMapOutputValueClass(Text.class); job.setOutputFormatClass(ContentOutputFormat.class); ZipContentInputFormat.setInputPaths(job, new Path(otherArgs[1])); conf = job.getConfiguration(); conf.addResource(otherArgs[0]); System.exit(job.waitForCompletion(true) ? 0 : 1); }
From source file:com.marklogic.mapreduce.test.CustomQuery.java
License:Apache License
public static void main(String[] args) throws Exception { Configuration conf = new Configuration(); if (args.length < 1) { System.err.println("Usage: CustomQuery configFile"); System.exit(2);//from w ww . ja v a 2 s . c o m } String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs(); Job job = Job.getInstance(conf, "custom query"); job.setJarByClass(CustomQuery.class); job.setInputFormatClass(NodeInputFormat.class); job.setMapperClass(QueryMapper.class); job.setMapOutputKeyClass(IntWritable.class); job.setMapOutputValueClass(Text.class); job.setReducerClass(QueryReducer.class); job.setOutputFormatClass(KeyValueOutputFormat.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(Text.class); conf = job.getConfiguration(); conf.addResource(otherArgs[0]); System.exit(job.waitForCompletion(true) ? 0 : 1); }
From source file:com.michaeljones.hellohadoopworldmaven.HelloMapReduce.java
public static Job RunJobAsync(Path inputPath, Path outputPath, Configuration conf) throws Exception { Job job = Job.getInstance(conf, "word count"); job.setJarByClass(HelloMapReduce.class); job.setMapperClass(TokenizerMapper.class); job.setCombinerClass(IntSumReducer.class); job.setReducerClass(IntSumReducer.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(IntWritable.class); FileInputFormat.addInputPath(job, inputPath); FileOutputFormat.setOutputPath(job, outputPath); return job;//from ww w. j a va 2 s . com }
From source file:com.michaeljones.hellohadoopworldmaven.HelloMapReduce.java
public static Job RunJobAnalysisAsync(Path inputPath, Path outputPath, Configuration conf) throws Exception { Job job = Job.getInstance(conf, "word count"); job.setJarByClass(HelloMapReduce.class); job.setMapperClass(TokenizerMapper.class); job.setCombinerClass(IntSumCombinerAnalyser.class); job.setReducerClass(IntSumReducerAnalyser.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(IntWritable.class); FileInputFormat.addInputPath(job, inputPath); FileOutputFormat.setOutputPath(job, outputPath); return job;//www.j a v a 2 s. co m }
From source file:com.mongodb.hadoop.util.MongoTool.java
License:Apache License
private int runMapReduceJob(final Configuration conf) throws IOException { final Job job = Job.getInstance(conf, getJobName()); /**//w ww .j ava 2 s .c o m * Any arguments specified with -D <property>=<value> * on the CLI will be picked up and set here * They override any XML level values * Note that -D<space> is important - no space will * not work as it gets picked up by Java itself */ // TODO - Do we need to set job name somehow more specifically? // This may or may not be correct/sane job.setJarByClass(getClass()); final Class<? extends Mapper> mapper = MongoConfigUtil.getMapper(conf); LOG.debug("Mapper Class: " + mapper); LOG.debug("Input URI: " + conf.get(MongoConfigUtil.INPUT_URI)); job.setMapperClass(mapper); Class<? extends Reducer> combiner = MongoConfigUtil.getCombiner(conf); if (combiner != null) { job.setCombinerClass(combiner); } job.setReducerClass(MongoConfigUtil.getReducer(conf)); job.setOutputFormatClass(MongoConfigUtil.getOutputFormat(conf)); job.setOutputKeyClass(MongoConfigUtil.getOutputKey(conf)); job.setOutputValueClass(MongoConfigUtil.getOutputValue(conf)); job.setInputFormatClass(MongoConfigUtil.getInputFormat(conf)); Class mapOutputKeyClass = MongoConfigUtil.getMapperOutputKey(conf); Class mapOutputValueClass = MongoConfigUtil.getMapperOutputValue(conf); if (mapOutputKeyClass != null) { job.setMapOutputKeyClass(mapOutputKeyClass); } if (mapOutputValueClass != null) { job.setMapOutputValueClass(mapOutputValueClass); } /** * Determines if the job will run verbosely e.g. print debug output * Only works with foreground jobs */ final boolean verbose = MongoConfigUtil.isJobVerbose(conf); /** * Run job in foreground aka wait for completion or background? */ final boolean background = MongoConfigUtil.isJobBackground(conf); try { if (background) { LOG.info("Setting up and running MapReduce job in background."); job.submit(); return 0; } else { LOG.info("Setting up and running MapReduce job in foreground, will wait for results. {Verbose? " + verbose + "}"); return job.waitForCompletion(true) ? 0 : 1; } } catch (final Exception e) { LOG.error("Exception while executing job... ", e); return 1; } }
From source file:com.msd.gin.halyard.tools.HalyardBulkLoad.java
License:Apache License
@Override public int run(String[] args) throws Exception { if (args.length != 3) { System.err.println("Usage: bulkload [-D" + MRJobConfig.QUEUE_NAME + "=proofofconcepts] [-D" + SKIP_INVALID_PROPERTY + "=true] [-D" + SPLIT_BITS_PROPERTY + "=8] [-D" + DEFAULT_CONTEXT_PROPERTY + "=http://new_context] [-D" + OVERRIDE_CONTEXT_PROPERTY + "=true] <input_path(s)> <output_path> <table_name>"); return -1; }/* w w w. j a va 2s . c o 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(), "HalyardBulkLoad -> " + args[1] + " -> " + args[2]); job.setJarByClass(HalyardBulkLoad.class); job.setMapperClass(RDFMapper.class); job.setMapOutputKeyClass(ImmutableBytesWritable.class); job.setMapOutputValueClass(KeyValue.class); job.setInputFormatClass(RioFileInputFormat.class); job.setSpeculativeExecution(false); job.setReduceSpeculativeExecution(false); Map<String, Integer> contextSplitsMap = new HashMap<>(); for (Map.Entry<String, String> me : getConf().getValByRegex(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(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.HalyardBulkUpdate.java
License:Apache License
@Override public int run(String[] args) throws Exception { if (args.length != 3) { System.err.println("Usage: bulkupdate [-D" + MRJobConfig.QUEUE_NAME + "=proofofconcepts] [-D" + DEFAULT_CONTEXT_PROPERTY + "=http://new_context] [-D" + OVERRIDE_CONTEXT_PROPERTY + "=true] <input_file_with_SPARQL_queries> <output_path> <table_name>"); return -1; }//from w w w .java2 s . c o m TableMapReduceUtil.addDependencyJars(getConf(), NTriplesUtil.class, Rio.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); getConf().setStrings(TABLE_NAME_PROPERTY, args[2]); Job job = Job.getInstance(getConf(), "HalyardBulkUpdate -> " + args[1] + " -> " + args[2]); NLineInputFormat.setNumLinesPerSplit(job, 1); job.setJarByClass(HalyardBulkUpdate.class); job.setMapperClass(SPARQLMapper.class); job.setMapOutputKeyClass(ImmutableBytesWritable.class); job.setMapOutputValueClass(KeyValue.class); job.setInputFormatClass(NLineInputFormat.class); job.setSpeculativeExecution(false); job.setReduceSpeculativeExecution(false); try (HTable hTable = HalyardTableUtils.getTable(getConf(), args[2], false, 0, null)) { HFileOutputFormat2.configureIncrementalLoad(job, hTable.getTableDescriptor(), hTable.getRegionLocator()); 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 Update Completed.."); return 0; } } return -1; }
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 www . j a v a 2 s . c o 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 {/*from w ww .j a va 2 s .com*/ 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; } }