List of usage examples for org.apache.hadoop.mapreduce.lib.input FileInputFormat setInputDirRecursive
public static void setInputDirRecursive(Job job, boolean inputDirRecursive)
From source file:ca.uwaterloo.iss4e.hadoop.meterperfile.ThreelMain.java
License:Open Source License
public int run(String[] args) throws IOException { Configuration conf = getConf(); String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs(); if (otherArgs.length != 2) { System.err.println("Usage: ca.uwaterloo.iss4e.hadoop.meterperfile.ThreelMain <input> <output>"); System.exit(2);/*from w w w. j a v a 2 s. c o m*/ } conf.set("mapreduce.input.fileinputformat.split.maxsize", "100"); Job job = new Job(conf, "ThreelMain"); job.setJarByClass(ThreelMain.class); job.setInputFormatClass(UnsplitableTextInputFormat.class); job.setMapperClass(MyMapper.class); job.setMapOutputKeyClass(LongWritable.class); job.setMapOutputValueClass(Text.class); job.setNumReduceTasks(0); // job.setOutputKeyClass(LongWritable.class); //job.setOutputValueClass(Text.class); FileInputFormat.setInputDirRecursive(job, true); FileInputFormat.setInputPaths(job, new Path(otherArgs[0])); FileOutputFormat.setOutputPath(job, new Path(otherArgs[1])); System.out.println("\nStarting Job ..."); final long startTime = System.currentTimeMillis(); try { if (!job.waitForCompletion(true)) { System.out.println("Job failed."); System.exit(1); } } catch (Exception e) { throw new RuntimeException(e); } finally { final double duration = (System.currentTimeMillis() - startTime) / 1000.0; System.out.println("Duration is " + duration + " seconds."); } return 0; }
From source file:ca.uwaterloo.iss4e.hadoop.pointperrow.CosineMain.java
License:Open Source License
public int run(String[] args) throws IOException { Configuration conf = getConf(); String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs(); if (otherArgs.length != 2) { System.err.println("Usage: ca.uwaterloo.iss4e.hadoop.pointperrow.ConsineMain <input> <output>"); System.exit(2);/*from w ww . j a v a2 s. c o m*/ } Job job1 = new Job(conf, "ConsineMain"); job1.setJarByClass(CosineMain.class); job1.setMapperClass(AggregateReadingsMapper.class); job1.setMapOutputKeyClass(LongWritable.class); job1.setMapOutputValueClass(DoubleWritable.class); job1.setReducerClass(AggregateReadingsReducer.class); job1.setOutputKeyClass(LongWritable.class); job1.setOutputValueClass(Text.class); FileInputFormat.setInputDirRecursive(job1, true); FileInputFormat.setInputPaths(job1, new Path(otherArgs[0])); int lastIdx = otherArgs[0].lastIndexOf("/"); String tempOutput = otherArgs[0].substring(0, lastIdx) + "/temp"; FileOutputFormat.setOutputPath(job1, new Path(tempOutput)); System.out.println("\nStarting Job-1 ..."); final long startTime = System.currentTimeMillis(); try { final long startTimeJob1 = System.currentTimeMillis(); if (!job1.waitForCompletion(true)) { System.out.println("Job-1 failed."); } else { System.out.println("Duration of Job1 " + ((System.currentTimeMillis() - startTimeJob1) / 1000.0) + " seconds."); final Job job2 = new Job(conf, "ConsineMain Aggregate"); job2.setJarByClass(CosineMain.class); job2.setInputFormatClass(CartesianInputFormat.class); CartesianInputFormat.setLeftInputInfo(job2, TextInputFormat.class, tempOutput); CartesianInputFormat.setRightInputInfo(job2, TextInputFormat.class, tempOutput); FileOutputFormat.setOutputPath(job2, new Path(otherArgs[1])); job2.setMapperClass(CartesianProductMapper.class); job2.setMapOutputKeyClass(DoubleWritable.class); job2.setMapOutputValueClass(Text.class); job2.setSortComparatorClass(DescendingKeyComparator.class); job2.setReducerClass(CartesianProductReducer.class); job2.setOutputKeyClass(Text.class); job2.setOutputValueClass(DoubleWritable.class); job2.setNumReduceTasks(10); final long startTimeJob2 = System.currentTimeMillis(); System.out.println("\nStarting Job-2 ..."); if (!job2.waitForCompletion(true)) { System.out.println("Job-2 failed."); } else { System.out.println("Duration of Job2: " + ((System.currentTimeMillis() - startTimeJob2) / 1000.0) + " seconds."); } } FileSystem fs = FileSystem.get(conf); fs.delete(new Path(tempOutput), true); } catch (Exception e) { throw new RuntimeException(e); } finally { final double duration = (System.currentTimeMillis() - startTime) / 1000.0; System.out.println("Total Duration: " + duration + " seconds."); } return 0; }
From source file:ca.uwaterloo.iss4e.hadoop.pointperrow.HistogramMain.java
License:Open Source License
public int run(String[] args) throws IOException { Configuration conf = getConf(); String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs(); if (otherArgs.length != 2) { System.err.println("Usage: ca.uwaterloo.iss4e.hadoop.pointperrow.HistogramMain <input> <output>"); System.exit(2);//from www . jav a2s . co m } Job job = new Job(conf, "HistogramMain"); job.setJarByClass(HistogramMain.class); job.setMapperClass(MyMapper.class); job.setMapOutputKeyClass(LongWritable.class); job.setMapOutputValueClass(DoubleWritable.class); job.setCombinerClass(MyCombiner.class); job.setReducerClass(MyReducer.class); job.setOutputKeyClass(LongWritable.class); job.setOutputValueClass(Text.class); FileInputFormat.setInputDirRecursive(job, true); FileInputFormat.setInputPaths(job, new Path(otherArgs[0])); FileOutputFormat.setOutputPath(job, new Path(otherArgs[1])); System.out.println("\nStarting Job ..."); final long startTime = System.currentTimeMillis(); try { if (!job.waitForCompletion(true)) { System.out.println("Job failed."); System.exit(1); } } catch (Exception e) { throw new RuntimeException(e); } finally { final double duration = (System.currentTimeMillis() - startTime) / 1000.0; System.out.println("Duration is " + duration + " seconds."); } return 0; }
From source file:ca.uwaterloo.iss4e.hadoop.pointperrow.PARMain.java
License:Open Source License
public int run(String[] args) throws IOException { Configuration conf = getConf(); String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs(); if (otherArgs.length != 2) { System.err.println("Usage: ca.uwaterloo.iss4e.hadoop.pointperrow.PARMain <input> <output>"); System.exit(2);// ww w . j a v a2 s .c o m } Job job = new Job(conf, "PARMain"); job.setJarByClass(PARMain.class); job.setMapperClass(MyMapper.class); job.setMapOutputKeyClass(LongWritable.class); job.setMapOutputValueClass(DoubleWritable.class); job.setCombinerClass(MyCombiner.class); job.setReducerClass(MyReducer.class); job.setOutputKeyClass(LongWritable.class); job.setOutputValueClass(Text.class); FileInputFormat.setInputDirRecursive(job, true); FileInputFormat.setInputPaths(job, new Path(otherArgs[0])); FileOutputFormat.setOutputPath(job, new Path(otherArgs[1])); System.out.println("\nStarting Job ..."); final long startTime = System.currentTimeMillis(); try { if (!job.waitForCompletion(true)) { System.out.println("Job failed."); System.exit(1); } } catch (Exception e) { throw new RuntimeException(e); } finally { final double duration = (System.currentTimeMillis() - startTime) / 1000.0; System.out.println("Duration is " + duration + " seconds."); } return 0; }
From source file:ca.uwaterloo.iss4e.hadoop.pointperrow.ThreelMain.java
License:Open Source License
public int run(String[] args) throws IOException { Configuration conf = getConf(); String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs(); if (otherArgs.length != 2) { System.err.println("Usage: ca.uwaterloo.iss4e.hadoop.pointperrow.ThreelMain <input> <output>"); System.exit(2);/*from w ww .j av a 2 s . co m*/ } Job job = new Job(conf, "ThreelMain"); job.setJarByClass(ThreelMain.class); job.setMapperClass(MyMapper.class); job.setMapOutputKeyClass(LongWritable.class); job.setMapOutputValueClass(ArrayPrimitiveWritable.class); job.setCombinerClass(MyCombiner.class); job.setReducerClass(MyReducer.class); job.setOutputKeyClass(LongWritable.class); job.setOutputValueClass(Text.class); FileInputFormat.setInputDirRecursive(job, true); FileInputFormat.setInputPaths(job, new Path(otherArgs[0])); FileOutputFormat.setOutputPath(job, new Path(otherArgs[1])); System.out.println("\nStarting Job ..."); final long startTime = System.currentTimeMillis(); try { if (!job.waitForCompletion(true)) { System.out.println("Job failed."); System.exit(1); } } catch (Exception e) { throw new RuntimeException(e); } finally { final double duration = (System.currentTimeMillis() - startTime) / 1000.0; System.out.println("Duration is " + duration + " seconds."); } return 0; }
From source file:com.ifeng.logparser.NginxLogDriver.java
License:Apache License
@Override public int run(String[] args) throws Exception { if (args.length != 2) { System.err.printf("Usage: %s [generic options] <input> <output>\n", getClass().getSimpleName()); ToolRunner.printGenericCommandUsage(System.err); return -1; }//from www .j a va 2s . c om Job job = Job.getInstance(super.getConf()); FileInputFormat.setInputDirRecursive(job, true); //FileInputFormat.addInputPath(job, new Path(args[0])); FileOutputFormat.setOutputPath(job, new Path(args[1])); FileInputFormat.addInputPaths(job, args[0]); job.setMapperClass(NginxLogMapper.class); job.setReducerClass(NginxLogReducer.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(Text.class); return job.waitForCompletion(true) ? 0 : 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; }/*from ww w. j ava 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(), "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.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 va2 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.ov.project.dev.crawler.ClientOVSocket.java
public Map<VelibStation, Prediction> jobToDo(Map<VelibKey, Integer> iDataProvided) { System.setProperty("hadoop.home.dir", BundelUtils.get("hadoop.home")); // Create a Java version of the Spark Context from the configuration JavaSparkContext lSparkctx = SingletonWrappers.sparkContextGetInstance(); Job lJob;/* w ww. j a v a 2 s . co m*/ try { lJob = Job.getInstance(); FileInputFormat.setInputPaths(lJob, new Path(BundelUtils.get("data.frame.path"))); FileInputFormat.setInputDirRecursive(lJob, true); } catch (IOException e1) { e1.printStackTrace(); System.exit(1); } Prediction predi = new Prediction(); // com.ov.PredictionsBuilder.runPredictions(BundelUtils.get("bruteData.path"), BundelUtils.get("static.path"), BundelUtils.get("output.path"), BundelUtils.get("model.path"), BundelUtils.get("hadoop.home"), iSave, Calendar.MINUTE, new TimeStamp(), new TimeStamp(), BundelUtils.get("license.path")); // JavaRDD<Text> sourceData = lSparkctx // .newAPIHadoopRDD(lJob.getConfiguration(), TextInputFormat.class, LongWritable.class, Text.class) // .values(); // Each line will be translate to a session defined by the IP adress // JavaPairRDD<VelibStation, Prediction> lsession = sourceData // .mapToPair( // w -> new Tuple2<VelibStation, Prediction>(LogParser.getFirstToken(w), LogParser.parseTokenz(w))) // .reduceByKey((a, b) -> reduceByIP(a, b)); // Save the word count back out to a text file, causing evaluation. // FileUtils.deleteQuietly(new File(BundelUtils.get("suffix.for.result.file"))); // lsession.saveAsTextFile(BundelUtils.get("suffix.for.result.file")); return null; }
From source file:com.rw.legion.DefaultJob.java
License:Apache License
/** * Main method./*w w w .ja va 2s .co m*/ * * @param args Arguments should be: 1) input path, 2) output path, 3) * location of Legion objective file. */ public static void main(String[] args) throws Exception { Configuration conf = new Configuration(); // Load the Legion objective from the JSON doc. Path path = new Path(args[2]); FileSystem fs = FileSystem.get(new URI(args[2]), conf); BufferedReader br = new BufferedReader(new InputStreamReader(fs.open(path))); String json = ""; String line = br.readLine(); while (line != null) { json += line; line = br.readLine(); } br.close(); /* * Save the JSON for the Legion objective to the Hadoop configuration, * so we can access it in other containers. */ conf.setStrings("legion_objective", json); // De-serialize the objective so we can access the settings here. LegionObjective legionObjective = ObjectiveDeserializer.deserialize(json); // Start configuring the MapReduce job. Job hadoopJob = Job.getInstance(conf, "Legion"); hadoopJob.setJarByClass(DefaultJob.class); hadoopJob.setMapperClass(DefaultMapper.class); LazyOutputFormat.setOutputFormatClass(hadoopJob, TextOutputFormat.class); // Compress the output to speed things up. TextOutputFormat.setCompressOutput(hadoopJob, true); TextOutputFormat.setOutputCompressorClass(hadoopJob, GzipCodec.class); // What input format do we use? try { @SuppressWarnings("unchecked") Class<? extends FileInputFormat<NullWritable, LegionRecord>> inputClass = (Class<? extends FileInputFormat<NullWritable, LegionRecord>>) Class .forName(legionObjective.getInputFormat()); hadoopJob.setInputFormatClass(inputClass); } catch (Exception e) { throw new JsonParseException( "Problem loading input format " + "class '" + legionObjective.getInputFormat() + "'"); } // Should we set a max combined size? if (legionObjective.getMaxCombinedSize() != null) { CombineFileInputFormat.setMaxInputSplitSize(hadoopJob, legionObjective.getMaxCombinedSize()); } /* * These are just static convenience methods, so it doesn't matter if * they come from the wrong class. */ FileInputFormat.setInputDirRecursive(hadoopJob, true); FileInputFormat.addInputPath(hadoopJob, new Path(args[0])); FileOutputFormat.setOutputPath(hadoopJob, new Path(args[1])); // Since a Legion objective can specify multiple output tables. for (OutputTable outputTable : legionObjective.getOutputTables()) { MultipleOutputs.addNamedOutput(hadoopJob, outputTable.getTitle(), TextOutputFormat.class, NullWritable.class, Text.class); } MultipleOutputs.addNamedOutput(hadoopJob, "skipped", TextOutputFormat.class, NullWritable.class, Text.class); hadoopJob.waitForCompletion(true); }