List of usage examples for org.apache.hadoop.fs FileSystem get
public static FileSystem get(Configuration conf) throws IOException
From source file:Brush.RemoveLowCoverage.java
License:Apache License
public RunningJob run(String inputPath, String outputPath) throws Exception { sLogger.info("Tool name: RemoveLowCoverage"); sLogger.info(" - input: " + inputPath); sLogger.info(" - output: " + outputPath); JobConf conf = new JobConf(RemoveLowCoverage.class); conf.setJobName("RemoveLowCoverage " + inputPath + " " + BrushConfig.K); BrushConfig.initializeConfiguration(conf); FileInputFormat.addInputPath(conf, new Path(inputPath)); FileOutputFormat.setOutputPath(conf, new Path(outputPath)); conf.setInputFormat(TextInputFormat.class); conf.setOutputFormat(TextOutputFormat.class); conf.setMapOutputKeyClass(Text.class); conf.setMapOutputValueClass(Text.class); conf.setOutputKeyClass(Text.class); conf.setOutputValueClass(Text.class); conf.setMapperClass(RemoveLowCoverageMapper.class); conf.setReducerClass(RemoveLowCoverageReducer.class); //delete the output directory if it exists already FileSystem.get(conf).delete(new Path(outputPath), true); return JobClient.runJob(conf); }
From source file:Brush.Stats.java
License:Apache License
public RunningJob run(String inputPath, String outputPath) throws Exception { sLogger.info("Tool name: Stats"); sLogger.info(" - input: " + inputPath); sLogger.info(" - output: " + outputPath); JobConf conf = new JobConf(Stats.class); conf.setJobName("Stats " + inputPath); BrushConfig.initializeConfiguration(conf); conf.setNumReduceTasks(1);/*ww w .ja v a 2 s. c o m*/ FileInputFormat.addInputPath(conf, new Path(inputPath)); FileOutputFormat.setOutputPath(conf, new Path(outputPath)); conf.setInputFormat(TextInputFormat.class); conf.setOutputFormat(TextOutputFormat.class); conf.setMapOutputKeyClass(Text.class); conf.setMapOutputValueClass(Text.class); conf.setOutputKeyClass(Text.class); conf.setOutputValueClass(Text.class); conf.setMapperClass(StatsMapper.class); conf.setReducerClass(StatsReducer.class); //delete the output directory if it exists already FileSystem.get(conf).delete(new Path(outputPath), true); return JobClient.runJob(conf); }
From source file:Brush.TipsRemoval.java
License:Apache License
public RunningJob run(String inputPath, String outputPath) throws Exception { sLogger.info("Tool name: TipsRemoval"); sLogger.info(" - input: " + inputPath); sLogger.info(" - output: " + outputPath); JobConf conf = new JobConf(TipsRemoval.class); conf.setJobName("RemoveTips " + inputPath + " " + BrushConfig.K); BrushConfig.initializeConfiguration(conf); FileInputFormat.addInputPath(conf, new Path(inputPath)); FileOutputFormat.setOutputPath(conf, new Path(outputPath)); conf.setInputFormat(TextInputFormat.class); conf.setOutputFormat(TextOutputFormat.class); conf.setMapOutputKeyClass(Text.class); conf.setMapOutputValueClass(Text.class); conf.setOutputKeyClass(Text.class); conf.setOutputValueClass(Text.class); //conf.setBoolean("mapred.output.compress", true); conf.setMapperClass(TipsRemovalMapper.class); conf.setReducerClass(TipsRemovalReducer.class); //delete the output directory if it exists already FileSystem.get(conf).delete(new Path(outputPath), true); return JobClient.runJob(conf); }
From source file:Brush.TransitiveReduction.java
License:Apache License
public RunningJob run(String inputPath, String outputPath) throws Exception { sLogger.info("Tool name: TransitiveReduction"); sLogger.info(" - input: " + inputPath); sLogger.info(" - output: " + outputPath); //JobConf conf = new JobConf(Stats.class); JobConf conf = new JobConf(TransitiveReduction.class); conf.setJobName("TransitiveReduction " + inputPath); BrushConfig.initializeConfiguration(conf); FileInputFormat.addInputPath(conf, new Path(inputPath)); FileOutputFormat.setOutputPath(conf, new Path(outputPath)); conf.setInputFormat(TextInputFormat.class); conf.setOutputFormat(TextOutputFormat.class); conf.setMapOutputKeyClass(Text.class); conf.setMapOutputValueClass(Text.class); conf.setOutputKeyClass(Text.class); conf.setOutputValueClass(Text.class); //conf.setBoolean("mapred.output.compress", true); conf.setMapperClass(TransitiveReductionMapper.class); conf.setReducerClass(TransitiveReductionReducer.class); //delete the output directory if it exists already FileSystem.get(conf).delete(new Path(outputPath), true); return JobClient.runJob(conf); }
From source file:Brush.VerifyOverlap.java
License:Apache License
public RunningJob run(String inputPath, String outputPath) throws Exception { sLogger.info("Tool name: VerifyOverlap"); sLogger.info(" - input: " + inputPath); sLogger.info(" - output: " + outputPath); //JobConf conf = new JobConf(Stats.class); JobConf conf = new JobConf(VerifyOverlap.class); conf.setJobName("VerifyOverlap " + inputPath); BrushConfig.initializeConfiguration(conf); FileInputFormat.addInputPath(conf, new Path(inputPath)); FileOutputFormat.setOutputPath(conf, new Path(outputPath)); conf.setInputFormat(TextInputFormat.class); conf.setOutputFormat(TextOutputFormat.class); conf.setMapOutputKeyClass(Text.class); conf.setMapOutputValueClass(Text.class); conf.setOutputKeyClass(Text.class); conf.setOutputValueClass(Text.class); //conf.setBoolean("mapred.output.compress", true); //conf.setClass("mapred.output.compression.codec", GzipCodec.class,CompressionCodec.class); conf.setMapperClass(VerifyOverlapMapper.class); conf.setReducerClass(VerifyOverlapReducer.class); //delete the output directory if it exists already FileSystem.get(conf).delete(new Path(outputPath), true); return JobClient.runJob(conf); }
From source file:bulkload.ImportTsv.java
License:Apache License
/** * Sets up the actual job./* w w w .j a v a 2 s .co m*/ * * @param conf * The current configuration. * @param args * The command line parameters. * @return The newly created job. * @throws IOException * When setting up the job fails. */ public static Job createSubmittableJob(Configuration conf, String[] args) throws IOException { Job job = null; try (Connection connection = ConnectionFactory.createConnection(conf)) { try (Admin admin = connection.getAdmin()) { // Support non-XML supported characters // by re-encoding the passed separator as a Base64 string. String actualSeparator = conf.get(SEPARATOR_CONF_KEY); if (actualSeparator != null) { conf.set(SEPARATOR_CONF_KEY, Base64.encodeBytes(actualSeparator.getBytes())); } TableName tableName = TableName.valueOf(args[0]); if (!admin.tableExists(tableName)) { String errorMsg = format("Table '%s' does not exist.", tableName); LOG.error(errorMsg); throw new TableNotFoundException(errorMsg); } Path inputDir = new Path(args[1]); String jobName = conf.get(JOB_NAME_CONF_KEY, NAME + "_" + tableName.getNameAsString()); job = Job.getInstance(conf, jobName); job.setJarByClass(TsvImporter.class); FileInputFormat.setInputPaths(job, inputDir); job.setInputFormatClass(TextInputFormat.class); job.setMapperClass(TsvImporter.class); String hfileOutPath = conf.get(BULK_OUTPUT_CONF_KEY); if (hfileOutPath != null) { try (HTable table = (HTable) connection.getTable(tableName)) { Path outputDir = new Path(hfileOutPath); FileSystem fs = FileSystem.get(conf); if (fs.exists(outputDir)) { if (!fs.delete(outputDir, true)) { throw new IllegalStateException("delete path:" + outputDir + " failed"); } } FileOutputFormat.setOutputPath(job, outputDir); job.setMapOutputKeyClass(ImmutableBytesWritable.class); job.setMapOutputValueClass(Put.class); job.setReducerClass(PutSortReducer.class); HFileOutputFormat2.configureIncrementalLoad(job, table, table); } } else { // No reducers. Just write straight to table. Call // initTableReducerJob // to set up the TableOutputFormat. TableMapReduceUtil.initTableReducerJob(tableName.getNameAsString(), null, job); job.setNumReduceTasks(0); // TableMapReduceUtil.addDependencyJars(job); // TableMapReduceUtil.addDependencyJars(job.getConfiguration(), // com.google.common.base.Function.class /* Guava used by TsvParser */); } // Workaround to remove unnecessary hadoop dependencies String[] jars = job.getConfiguration().get("tmpjars").split(",", -1); StringBuilder filteredJars = new StringBuilder(); for (String j : jars) { String[] parts = j.split("/", -1); String fileName = parts[parts.length - 1]; if (fileName.indexOf("hadoop-") != 0) { filteredJars.append(j); filteredJars.append(","); } } job.getConfiguration().set("tmpjars", filteredJars.toString()); } } return job; }
From source file:byte_import.HexastoreBulkImport.java
License:Open Source License
public Job createSubmittableJob(String[] args) { TABLE_NAME = args[1];//from w ww. j ava 2s . c o m Job job = null; try { job = new Job(new Configuration(), NAME); job.setJarByClass(HexastoreBulkImport.class); job.setMapperClass(sampler.TotalOrderPrep.Map.class); job.setReducerClass(Reduce.class); job.setCombinerClass(Combiner.class); job.setMapOutputKeyClass(ImmutableBytesWritable.class); job.setMapOutputValueClass(ImmutableBytesWritable.class); job.setPartitionerClass(TotalOrderPartitioner.class); //TotalOrderPartitioner.setPartitionFile(job.getConfiguration(), new Path("/user/npapa/"+regions+"partitions/part-r-00000")); TotalOrderPartitioner.setPartitionFile(job.getConfiguration(), new Path("partitions/part-r-00000")); job.setInputFormatClass(TextInputFormat.class); job.setOutputFormatClass(HFileOutputFormat.class); Path out = new Path("out"); FileOutputFormat.setOutputPath(job, out); Configuration conf = new Configuration(); FileSystem fs; try { fs = FileSystem.get(conf); if (fs.exists(out)) { fs.delete(out, true); } } catch (IOException e) { e.printStackTrace(); } HBaseAdmin hadmin = new HBaseAdmin(conf); HTableDescriptor desc = new HTableDescriptor(TABLE_NAME + "_stats"); HColumnDescriptor family = new HColumnDescriptor("size"); desc.addFamily(family); conf.setInt("zookeeper.session.timeout", 600000); if (hadmin.tableExists(TABLE_NAME + "_stats")) { //hadmin.disableTable(TABLE_NAME+"_stats"); //hadmin.deleteTable(TABLE_NAME+"_stats"); } else { hadmin.createTable(desc); } FileInputFormat.setInputPaths(job, new Path(args[0])); //job.getConfiguration().setInt("mapred.map.tasks", 18); job.getConfiguration().set("h2rdf.tableName", TABLE_NAME); job.getConfiguration().setInt("mapred.reduce.tasks", (int) TotalOrderPrep.regions); job.getConfiguration().setBoolean("mapred.map.tasks.speculative.execution", false); job.getConfiguration().setBoolean("mapred.reduce.tasks.speculative.execution", false); job.getConfiguration().setInt("io.sort.mb", 100); job.getConfiguration().setInt("io.file.buffer.size", 131072); job.getConfiguration().setInt("mapred.job.reuse.jvm.num.tasks", -1); //job.getConfiguration().setInt("hbase.hregion.max.filesize", 67108864); job.getConfiguration().setInt("hbase.hregion.max.filesize", 33554432); job.getConfiguration().setInt("mapred.tasktracker.map.tasks.maximum", 5); job.getConfiguration().setInt("mapred.tasktracker.reduce.tasks.maximum", 5); //job.getConfiguration().setInt("io.sort.mb", 100); } catch (IOException e2) { e2.printStackTrace(); } return job; }
From source file:c5db.tablet.hregionbridge.HRegionServicesBridge.java
License:Apache License
@Override public FileSystem getFileSystem() { try {/*from www . ja v a 2s. c o m*/ FileSystem fileSystem = FileSystem.get(conf); return fileSystem; } catch (IOException e) { e.printStackTrace(); } return null; }
From source file:ca.uwaterloo.cs.bigdata2017w.assignment0.PerfectX.java
License:Apache License
/** * Runs this tool.//from w ww. ja v a 2s .c o m */ @Override public int run(String[] argv) throws Exception { final Args args = new Args(); CmdLineParser parser = new CmdLineParser(args, ParserProperties.defaults().withUsageWidth(100)); try { parser.parseArgument(argv); } catch (CmdLineException e) { System.err.println(e.getMessage()); parser.printUsage(System.err); return -1; } LOG.info("Tool: " + PerfectX.class.getSimpleName()); LOG.info(" - input path: " + args.input); LOG.info(" - output path: " + args.output); LOG.info(" - number of reducers: " + args.numReducers); LOG.info(" - use in-mapper combining: " + args.imc); Configuration conf = getConf(); Job job = Job.getInstance(conf); job.setJobName(PerfectX.class.getSimpleName()); job.setJarByClass(PerfectX.class); job.setNumReduceTasks(args.numReducers); FileInputFormat.setInputPaths(job, new Path(args.input)); FileOutputFormat.setOutputPath(job, new Path(args.output)); job.setMapOutputKeyClass(Text.class); job.setMapOutputValueClass(IntWritable.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(IntWritable.class); job.setOutputFormatClass(TextOutputFormat.class); job.setMapperClass(args.imc ? MyMapperIMC.class : MyMapper.class); job.setCombinerClass(MyReducer.class); job.setReducerClass(MyReducer.class); // Delete the output directory if it exists already. Path outputDir = new Path(args.output); FileSystem.get(conf).delete(outputDir, true); long startTime = System.currentTimeMillis(); job.waitForCompletion(true); LOG.info("Job Finished in " + (System.currentTimeMillis() - startTime) / 1000.0 + " seconds"); return 0; }
From source file:ca.uwaterloo.cs.bigdata2017w.assignment0.WordCount.java
License:Apache License
/** * Runs this tool./*from ww w . j a va2 s . co m*/ */ @Override public int run(String[] argv) throws Exception { final Args args = new Args(); CmdLineParser parser = new CmdLineParser(args, ParserProperties.defaults().withUsageWidth(100)); try { parser.parseArgument(argv); } catch (CmdLineException e) { System.err.println(e.getMessage()); parser.printUsage(System.err); return -1; } LOG.info("Tool: " + WordCount.class.getSimpleName()); LOG.info(" - input path: " + args.input); LOG.info(" - output path: " + args.output); LOG.info(" - number of reducers: " + args.numReducers); LOG.info(" - use in-mapper combining: " + args.imc); Configuration conf = getConf(); Job job = Job.getInstance(conf); job.setJobName(WordCount.class.getSimpleName()); job.setJarByClass(WordCount.class); job.setNumReduceTasks(args.numReducers); FileInputFormat.setInputPaths(job, new Path(args.input)); FileOutputFormat.setOutputPath(job, new Path(args.output)); job.setMapOutputKeyClass(Text.class); job.setMapOutputValueClass(IntWritable.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(IntWritable.class); job.setOutputFormatClass(TextOutputFormat.class); job.setMapperClass(args.imc ? MyMapperIMC.class : MyMapper.class); job.setCombinerClass(MyReducer.class); job.setReducerClass(MyReducer.class); // Delete the output directory if it exists already. Path outputDir = new Path(args.output); FileSystem.get(conf).delete(outputDir, true); long startTime = System.currentTimeMillis(); job.waitForCompletion(true); LOG.info("Job Finished in " + (System.currentTimeMillis() - startTime) / 1000.0 + " seconds"); return 0; }