List of usage examples for org.apache.hadoop.mapreduce Job setJarByClass
public void setJarByClass(Class<?> cls)
From source file:com.cloudera.recordservice.examples.mapreduce.MapReduceColorCount.java
License:Apache License
@Override public int run(String[] args) throws Exception { org.apache.log4j.BasicConfigurator.configure(); if (args.length != 2) { System.err.println("Usage: MapReduceColorCount <input path> <output path>"); return -1; }/*from w w w.ja va 2s .c o m*/ Job job = Job.getInstance(getConf()); job.setJarByClass(MapReduceColorCount.class); job.setJobName("Color Count"); // RECORDSERVICE: // To read from a table instead of a path, comment out // FileInputFormat.setInputPaths() and instead use: //FileInputFormat.setInputPaths(job, new Path(args[0])); RecordServiceConfig.setInputTable(job.getConfiguration(), "rs", "users"); // RECORDSERVICE: // Use the RecordService version of the AvroKeyInputFormat job.setInputFormatClass(com.cloudera.recordservice.avro.mapreduce.AvroKeyInputFormat.class); //job.setInputFormatClass(AvroKeyInputFormat.class); FileOutputFormat.setOutputPath(job, new Path(args[1])); job.setMapperClass(ColorCountMapper.class); AvroJob.setInputKeySchema(job, User.getClassSchema()); job.setMapOutputKeyClass(Text.class); job.setMapOutputValueClass(IntWritable.class); job.setOutputFormatClass(AvroKeyValueOutputFormat.class); job.setReducerClass(ColorCountReducer.class); AvroJob.setOutputKeySchema(job, Schema.create(Schema.Type.STRING)); AvroJob.setOutputValueSchema(job, Schema.create(Schema.Type.INT)); return (job.waitForCompletion(true) ? 0 : 1); }
From source file:com.cloudera.recordservice.examples.mapreduce.RecordCount.java
License:Apache License
@Override public int run(String[] args) throws Exception { if (args.length != 2) { System.err.println("Usage: RecordCount <input_query> <output_path>"); System.exit(1);//from w w w .ja v a 2s . com } String inputQuery = args[0]; String output = args[1]; Job job = Job.getInstance(getConf()); job.setJobName("recordcount"); job.setJarByClass(RecordCount.class); job.setMapperClass(Map.class); job.setCombinerClass(Reduce.class); job.setReducerClass(Reduce.class); job.setNumReduceTasks(1); job.setOutputKeyClass(NullWritable.class); job.setOutputValueClass(LongWritable.class); RecordServiceConfig.setInputQuery(job.getConfiguration(), inputQuery); job.setInputFormatClass(RecordServiceInputFormat.class); job.setOutputFormatClass(TextOutputFormat.class); FileSystem fs = FileSystem.get(job.getConfiguration()); Path outputPath = new Path(output); if (fs.exists(outputPath)) fs.delete(outputPath, true); FileOutputFormat.setOutputPath(job, outputPath); return job.waitForCompletion(true) ? 0 : 1; }
From source file:com.cloudera.recordservice.examples.terasort.TeraChecksum.java
License:Apache License
@Override public int run(String[] args) throws Exception { boolean useRecordService = false; Job job = Job.getInstance(getConf()); if (args.length != 2 && args.length != 3) { usage();//from w w w. j a va 2s . c o m return 2; } if (args.length == 3) { useRecordService = Boolean.parseBoolean(args[2]); } FileOutputFormat.setOutputPath(job, new Path(args[1])); job.setJobName("TeraSum"); job.setJarByClass(TeraChecksum.class); job.setMapperClass(ChecksumMapper.class); job.setReducerClass(ChecksumReducer.class); job.setOutputKeyClass(NullWritable.class); job.setOutputValueClass(Unsigned16.class); // force a single reducer job.setNumReduceTasks(1); if (useRecordService) { RecordServiceConfig.setInputTable(job.getConfiguration(), null, args[0]); job.setInputFormatClass(RecordServiceTeraInputFormat.class); } else { TeraInputFormat.setInputPaths(job, new Path(args[0])); job.setInputFormatClass(TeraInputFormat.class); } return job.waitForCompletion(true) ? 0 : 1; }
From source file:com.cloudera.recordservice.examples.terasort.TeraGen.java
License:Apache License
/** * @param args the cli arguments/*from w w w . j a v a2s . co m*/ */ @Override public int run(String[] args) throws IOException, InterruptedException, ClassNotFoundException { Job job = Job.getInstance(getConf()); if (args.length != 2) { usage(); return 2; } setNumberOfRows(job, parseHumanLong(args[0])); Path outputDir = new Path(args[1]); if (outputDir.getFileSystem(getConf()).exists(outputDir)) { throw new IOException("Output directory " + outputDir + " already exists."); } FileOutputFormat.setOutputPath(job, outputDir); job.setJobName("TeraGen"); job.setJarByClass(TeraGen.class); job.setMapperClass(SortGenMapper.class); job.setNumReduceTasks(0); job.setOutputKeyClass(Text.class); job.setOutputValueClass(Text.class); job.setInputFormatClass(RangeInputFormat.class); job.setOutputFormatClass(TeraOutputFormat.class); return job.waitForCompletion(true) ? 0 : 1; }
From source file:com.cloudera.recordservice.examples.terasort.TeraSort.java
License:Apache License
@Override public int run(String[] args) throws Exception { boolean useRecordService = false; if (args.length != 2 && args.length != 3) { usage();//w w w. j a v a 2s .c o m return 1; } if (args.length == 3) { useRecordService = Boolean.parseBoolean(args[2]); } LOG.info("starting"); Job job = Job.getInstance(getConf()); boolean useSimplePartitioner = getUseSimplePartitioner(job); if (useRecordService) { RecordServiceConfig.setInputTable(job.getConfiguration(), null, args[0]); job.setInputFormatClass(RecordServiceTeraInputFormat.class); useSimplePartitioner = true; } else { Path inputDir = new Path(args[0]); TeraInputFormat.setInputPaths(job, inputDir); job.setInputFormatClass(TeraInputFormat.class); } Path outputDir = new Path(args[1]); FileOutputFormat.setOutputPath(job, outputDir); job.setJobName("TeraSort"); job.setJarByClass(TeraSort.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(Text.class); job.setOutputFormatClass(TeraOutputFormat.class); if (useSimplePartitioner) { job.setPartitionerClass(SimplePartitioner.class); } else { long start = System.currentTimeMillis(); Path partitionFile = new Path(outputDir, TeraInputFormat.PARTITION_FILENAME); URI partitionUri = new URI(partitionFile.toString() + "#" + TeraInputFormat.PARTITION_FILENAME); try { TeraInputFormat.writePartitionFile(job, partitionFile); } catch (Throwable e) { LOG.error(e.getMessage()); return -1; } job.addCacheFile(partitionUri); long end = System.currentTimeMillis(); System.out.println("Spent " + (end - start) + "ms computing partitions."); job.setPartitionerClass(TotalOrderPartitioner.class); } job.getConfiguration().setInt("dfs.replication", getOutputReplication(job)); TeraOutputFormat.setFinalSync(job, true); int ret = job.waitForCompletion(true) ? 0 : 1; LOG.info("done"); return ret; }
From source file:com.cloudera.recordservice.examples.terasort.TeraValidate.java
License:Apache License
@Override public int run(String[] args) throws Exception { boolean useRecordService = false; if (args.length != 2 && args.length != 3) { usage();//from w ww .j av a 2 s . c om return 1; } if (args.length == 3) { useRecordService = Boolean.parseBoolean(args[2]); } Job job = Job.getInstance(getConf()); FileOutputFormat.setOutputPath(job, new Path(args[1])); job.setJobName("TeraValidate"); job.setJarByClass(TeraValidate.class); job.setMapperClass(ValidateMapper.class); job.setReducerClass(ValidateReducer.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(Text.class); // force a single reducer job.setNumReduceTasks(1); // force a single split FileInputFormat.setMinInputSplitSize(job, Long.MAX_VALUE); if (useRecordService) { RecordServiceConfig.setInputTable(job.getConfiguration(), null, args[0]); job.setInputFormatClass(RecordServiceTeraInputFormat.class); } else { TeraInputFormat.setInputPaths(job, new Path(args[0])); job.setInputFormatClass(TeraInputFormat.class); } return job.waitForCompletion(true) ? 0 : 1; }
From source file:com.cloudera.sa.hbasebulkload.HBASEBulkLoadDriver.java
@Override public int run(String[] args) throws Exception { Configuration config = getConf(); args = new GenericOptionsParser(config, args).getRemainingArgs(); if (args.length < 6) { /*System.out.println("hadoop jar HBASEBulkLoad.jar " + "com.cloudera.sa.hbasebulkload.HBASEBulkLoadDriver" + " <inputpath> <outputpath> <hbaseTable> <hbaseColumnFamily" + " \"<hbaseColumns (delimiter seperated)>\" <column delimiter>");*/ ToolRunner.printGenericCommandUsage(System.out); return 2; }/*from w w w . j a v a 2 s . c o m*/ String hbaseTab = args[2]; String hbaseColumnFamily = args[3]; String hbaseColumns = args[4]; String hbaseColumnSeperator = args[5]; config.set(HBASEBulkLoadConstants.HBASE_TABLE_KEY, hbaseTab.trim().toLowerCase(Locale.ENGLISH)); config.set(HBASEBulkLoadConstants.HBASE_COLUMN_FAMILY_KEY, hbaseColumnFamily); config.set(HBASEBulkLoadConstants.HBASE_COLUMNS_KEY, hbaseColumns.trim().toLowerCase(Locale.ENGLISH)); config.set(HBASEBulkLoadConstants.HBASE_COLUMN_SEPERATOR_KEY, hbaseColumnSeperator); System.out.println(2); Job job = Job.getInstance(config, this.getClass().getName() + "-" + hbaseTab); HBaseConfiguration.addHbaseResources(config); job.setInputFormatClass(TextInputFormat.class); job.setJarByClass(HBASEBulkLoadDriver.class); job.setMapperClass(HBASEBulkLoadKeyValueMapper.class); job.setMapOutputKeyClass(ImmutableBytesWritable.class); job.setMapOutputValueClass(Put.class); job.setCombinerClass(PutCombiner.class); job.setReducerClass(PutSortReducer.class); Connection connection = ConnectionFactory.createConnection(config); Table hTab = connection.getTable(TableName.valueOf(hbaseTab)); FileSystem.get(getConf()).delete(new Path(args[1]), true); FileInputFormat.addInputPath(job, new Path(args[0])); FileOutputFormat.setOutputPath(job, new Path(args[1])); //job.setOutputFormatClass(HFileOutputFormat2.class); TableMapReduceUtil.initTableReducerJob(hTab.getName().getNameAsString(), null, job); //job.setNumReduceTasks(0); TableMapReduceUtil.addDependencyJars(job); HFileOutputFormat2.configureIncrementalLoadMap(job, hTab); int exitCode = job.waitForCompletion(true) ? HBASEBulkLoadConstants.SUCCESS : HBASEBulkLoadConstants.FAILURE; System.out.println(8); if (HBASEBulkLoadConstants.SUCCESS == exitCode) { LoadIncrementalHFiles loader = new LoadIncrementalHFiles(config); loader.doBulkLoad(new Path(args[1]), (HTable) hTab); connection.close(); } return exitCode; }
From source file:com.cloudera.sa.securewordcount.SecureWordCountDriver.java
@Override public int run(String[] args) throws Exception { Configuration config = getConf(); args = new GenericOptionsParser(config, args).getRemainingArgs(); if (args.length < 2) { ToolRunner.printGenericCommandUsage(System.out); return 2; }/*w ww. j a v a 2 s.com*/ Job job = Job.getInstance(config, this.getClass().getName() + "-wordcount"); job.setJarByClass(SecureWordCountDriver.class); job.setInputFormatClass(TextInputFormat.class); job.setMapperClass(TokenizerMapper.class); job.setCombinerClass(IntSumReducer.class); job.setReducerClass(IntSumReducer.class); job.setMapOutputKeyClass(Text.class); job.setMapOutputValueClass(IntWritable.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(IntWritable.class); FileInputFormat.addInputPath(job, new Path(args[0])); FileOutputFormat.setOutputPath(job, new Path(args[1])); return job.waitForCompletion(true) ? 0 : 1; }
From source file:com.cloudera.test.UseHCat.java
License:Apache License
public int run(String[] args) throws Exception { Configuration conf = getConf(); args = new GenericOptionsParser(conf, args).getRemainingArgs(); // Get the input and output table names as arguments String inputTableName = args[0]; String outputTableName = args[1]; // Assume the default database String dbName = null;//from ww w . j a v a2s . c o m Job job = new Job(conf, "UseHCat"); HCatInputFormat.setInput(job, dbName, inputTableName); job.setJarByClass(UseHCat.class); job.setMapperClass(Map.class); job.setReducerClass(Reduce.class); // An HCatalog record as input job.setInputFormatClass(HCatInputFormat.class); // Mapper emits a string as key and an integer as value job.setMapOutputKeyClass(Text.class); job.setMapOutputValueClass(IntWritable.class); // Ignore the key for the reducer output; emitting an HCatalog record as value job.setOutputKeyClass(WritableComparable.class); job.setOutputValueClass(DefaultHCatRecord.class); job.setOutputFormatClass(HCatOutputFormat.class); HCatOutputFormat.setOutput(job, OutputJobInfo.create(dbName, outputTableName, null)); HCatSchema s = HCatOutputFormat.getTableSchema(job); System.err.println("INFO: output schema explicitly set for writing:" + s); HCatOutputFormat.setSchema(job, s); return (job.waitForCompletion(true) ? 0 : 1); }
From source file:com.cloudera.traffic.AveragerRunner.java
License:Apache License
public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException { Configuration conf = new Configuration(); String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs(); Job job = new Job(conf); job.setJarByClass(AveragerRunner.class); job.setMapperClass(AveragerMapper.class); job.setReducerClass(AveragerReducer.class); job.setCombinerClass(AveragerReducer.class); job.setMapOutputKeyClass(Text.class); job.setMapOutputValueClass(AverageWritable.class); job.setInputFormatClass(TextInputFormat.class); FileInputFormat.addInputPath(job, new Path(otherArgs[0])); FileOutputFormat.setOutputPath(job, new Path(otherArgs[1])); job.waitForCompletion(true);/* w w w. j av a2s . c om*/ }