List of usage examples for org.apache.hadoop.fs Path Path
public Path(URI aUri)
From source file:HDFSRandomAccessFile.java
License:Apache License
public HDFSRandomAccessFile(String fileSystemURI, String location, int bufferSize) throws IOException { super(bufferSize); fsURI = URI.create(fileSystemURI); filePath = new Path(location); this.location = location; if (debugLeaks) { openFiles.add(location);// ww w .ja v a2 s. c om } FileSystem fs = FileSystem.get(fsURI, new Configuration()); hfile = fs.open(filePath); fileStatus = fs.getFileStatus(filePath); }
From source file:LookupPostingsCompressed1.java
License:Apache License
@SuppressWarnings({ "static-access" })
public static void main(String[] args) throws IOException {
Options options = new Options();
options.addOption(OptionBuilder.withArgName("path").hasArg().withDescription("input path").create(INDEX));
options.addOption(//from w w w. j ava2 s . c o m
OptionBuilder.withArgName("path").hasArg().withDescription("output path").create(COLLECTION));
CommandLine cmdline = null;
CommandLineParser parser = new GnuParser();
try {
cmdline = parser.parse(options, args);
} catch (ParseException exp) {
System.err.println("Error parsing command line: " + exp.getMessage());
System.exit(-1);
}
if (!cmdline.hasOption(INDEX) || !cmdline.hasOption(COLLECTION)) {
System.out.println("args: " + Arrays.toString(args));
HelpFormatter formatter = new HelpFormatter();
formatter.setWidth(120);
formatter.printHelp(LookupPostingsCompressed1.class.getName(), options);
ToolRunner.printGenericCommandUsage(System.out);
System.exit(-1);
}
String indexPath = cmdline.getOptionValue(INDEX);
String collectionPath = cmdline.getOptionValue(COLLECTION);
if (collectionPath.endsWith(".gz")) {
System.out.println("gzipped collection is not seekable: use compressed version!");
System.exit(-1);
}
Configuration config = new Configuration();
FileSystem fs = FileSystem.get(config);
MapFile.Reader reader = new MapFile.Reader(new Path(indexPath + "/part-r-00000"), config);
FSDataInputStream collection = fs.open(new Path(collectionPath));
BufferedReader d = new BufferedReader(new InputStreamReader(collection));
Text key = new Text();
PairOfWritables<VIntWritable, ArrayListWritable<PairOfVInts>> value = new PairOfWritables<VIntWritable, ArrayListWritable<PairOfVInts>>();
System.out.println("Looking up postings for the term \"starcross'd\"");
key.set("starcross'd");
reader.get(key, value);
ArrayListWritable<PairOfVInts> postings = value.getRightElement();
for (PairOfVInts pair : postings) {
System.out.println(pair);
collection.seek(pair.getLeftElement());
System.out.println(d.readLine());
}
key.set("gold");
reader.get(key, value);
System.out.println("Complete postings list for 'gold': " + value);
Int2IntFrequencyDistribution goldHist = new Int2IntFrequencyDistributionEntry();
postings = value.getRightElement();
for (PairOfVInts pair : postings) {
goldHist.increment(pair.getRightElement());
}
System.out.println("histogram of tf values for gold");
for (PairOfInts pair : goldHist) {
System.out.println(pair.getLeftElement() + "\t" + pair.getRightElement());
}
key.set("silver");
reader.get(key, value);
System.out.println("Complete postings list for 'silver': " + value);
Int2IntFrequencyDistribution silverHist = new Int2IntFrequencyDistributionEntry();
postings = value.getRightElement();
for (PairOfVInts pair : postings) {
silverHist.increment(pair.getRightElement());
}
System.out.println("histogram of tf values for silver");
for (PairOfInts pair : silverHist) {
System.out.println(pair.getLeftElement() + "\t" + pair.getRightElement());
}
key.set("bronze");
Writable w = reader.get(key, value);
if (w == null) {
System.out.println("the term bronze does not appear in the collection");
}
collection.close();
reader.close();
}
From source file:LoadClue.java
License:Apache License
/** * Job configuration.// w w w. j a v a 2 s. co m */ public static Job configureJob(Configuration conf, String[] args) throws IOException { Path inputPath = new Path(args[0]); String tableName = args[1]; Job job = new Job(conf, NAME + "_" + tableName); job.setJarByClass(Uploader.class); FileInputFormat.setInputPaths(job, inputPath); job.setInputFormatClass(ClueWebInputFormat.class); job.setMapperClass(Uploader.class); LoadClue.setTableName(tableName); // No reducers. Just write straight to table. Call initTableReducerJob // because it sets up the TableOutputFormat. TableMapReduceUtil.initTableReducerJob(tableName, null, job); TableMapReduceUtil.addDependencyJars(conf, TableOutputFormat.class); job.setNumReduceTasks(0); return job; }
From source file:Text2FormatStorageMR.java
License:Open Source License
@SuppressWarnings("deprecation") public static void main(String[] args) throws Exception { if (args.length != 2) { System.out.println("FormatFileMR <input> <output>"); System.exit(-1);//from w w w . j a va 2s .c o m } JobConf conf = new JobConf(FormatStorageMR.class); conf.setJobName("Text2FormatMR"); conf.setNumMapTasks(1); conf.setNumReduceTasks(4); conf.setOutputKeyClass(LongWritable.class); conf.setOutputValueClass(Unit.Record.class); conf.setMapperClass(TextFileTestMapper.class); conf.setReducerClass(FormatFileTestReducer.class); conf.setInputFormat(TextInputFormat.class); conf.setOutputFormat(FormatStorageOutputFormat.class); conf.set("mapred.output.compress", "flase"); Head head = new Head(); initHead(head); head.toJobConf(conf); FileInputFormat.setInputPaths(conf, args[0]); Path outputPath = new Path(args[1]); FileOutputFormat.setOutputPath(conf, outputPath); FileSystem fs = outputPath.getFileSystem(conf); fs.delete(outputPath, true); JobClient jc = new JobClient(conf); RunningJob rj = null; rj = jc.submitJob(conf); String lastReport = ""; SimpleDateFormat dateFormat = new SimpleDateFormat("yyyy-MM-dd hh:mm:ss,SSS"); long reportTime = System.currentTimeMillis(); long maxReportInterval = 3 * 1000; while (!rj.isComplete()) { try { Thread.sleep(1000); } catch (InterruptedException e) { } int mapProgress = Math.round(rj.mapProgress() * 100); int reduceProgress = Math.round(rj.reduceProgress() * 100); String report = " map = " + mapProgress + "%, reduce = " + reduceProgress + "%"; if (!report.equals(lastReport) || System.currentTimeMillis() >= reportTime + maxReportInterval) { String output = dateFormat.format(Calendar.getInstance().getTime()) + report; System.out.println(output); lastReport = report; reportTime = System.currentTimeMillis(); } } System.exit(0); }
From source file:WriteHdfs.java
License:Open Source License
static void writehdfs(String filename, long length) throws IOException { FileSystem fs = FileSystem.get(new Configuration()); FSDataOutputStream fos = fs.create(new Path(filename), true, 1024 * 1024, null); for (int i = 0; i < length / data.length; i++) { fos.write(data);//from w ww.j av a2s .c om } fos.close(); }
From source file:AnalyzeBigramRelativeFrequency.java
License:Apache License
public static void main(String[] args) { if (args.length != 1) { System.out.println("usage: [input-path]"); System.exit(-1);//from w w w .ja v a 2 s . c o m } System.out.println("input path: " + args[0]); List<PairOfWritables<PairOfStrings, FloatWritable>> pairs = SequenceFileUtils .readDirectory(new Path(args[0])); List<PairOfWritables<PairOfStrings, FloatWritable>> list1 = Lists.newArrayList(); List<PairOfWritables<PairOfStrings, FloatWritable>> list2 = Lists.newArrayList(); for (PairOfWritables<PairOfStrings, FloatWritable> p : pairs) { PairOfStrings bigram = p.getLeftElement(); if (bigram.getLeftElement().equals("light")) { list1.add(p); } if (bigram.getLeftElement().equals("contain")) { list2.add(p); } } Collections.sort(list1, new Comparator<PairOfWritables<PairOfStrings, FloatWritable>>() { public int compare(PairOfWritables<PairOfStrings, FloatWritable> e1, PairOfWritables<PairOfStrings, FloatWritable> e2) { if (e1.getRightElement().compareTo(e2.getRightElement()) == 0) { return e1.getLeftElement().compareTo(e2.getLeftElement()); } return e2.getRightElement().compareTo(e1.getRightElement()); } }); int i = 0; for (PairOfWritables<PairOfStrings, FloatWritable> p : list1) { PairOfStrings bigram = p.getLeftElement(); System.out.println(bigram + "\t" + p.getRightElement()); i++; if (i > 10) { break; } } Collections.sort(list2, new Comparator<PairOfWritables<PairOfStrings, FloatWritable>>() { public int compare(PairOfWritables<PairOfStrings, FloatWritable> e1, PairOfWritables<PairOfStrings, FloatWritable> e2) { if (e1.getRightElement().compareTo(e2.getRightElement()) == 0) { return e1.getLeftElement().compareTo(e2.getLeftElement()); } return e2.getRightElement().compareTo(e1.getRightElement()); } }); i = 0; for (PairOfWritables<PairOfStrings, FloatWritable> p : list2) { PairOfStrings bigram = p.getLeftElement(); System.out.println(bigram + "\t" + p.getRightElement()); i++; if (i > 10) { break; } } }
From source file:BigramRelativeFrequency.java
License:Apache License
/** * Runs this tool.//from w w w. j a v a 2 s . co m */ @SuppressWarnings({ "static-access" }) public int run(String[] args) throws Exception { Options options = new Options(); options.addOption(OptionBuilder.withArgName("path").hasArg().withDescription("input path").create(INPUT)); options.addOption(OptionBuilder.withArgName("path").hasArg().withDescription("output path").create(OUTPUT)); options.addOption(OptionBuilder.withArgName("num").hasArg().withDescription("number of reducers") .create(NUM_REDUCERS)); CommandLine cmdline; CommandLineParser parser = new GnuParser(); try { cmdline = parser.parse(options, args); } catch (ParseException exp) { System.err.println("Error parsing command line: " + exp.getMessage()); return -1; } if (!cmdline.hasOption(INPUT) || !cmdline.hasOption(OUTPUT)) { System.out.println("args: " + Arrays.toString(args)); HelpFormatter formatter = new HelpFormatter(); formatter.setWidth(120); formatter.printHelp(this.getClass().getName(), options); ToolRunner.printGenericCommandUsage(System.out); return -1; } String inputPath = cmdline.getOptionValue(INPUT); String outputPath = cmdline.getOptionValue(OUTPUT); int reduceTasks = cmdline.hasOption(NUM_REDUCERS) ? Integer.parseInt(cmdline.getOptionValue(NUM_REDUCERS)) : 1; LOG.info("Tool name: " + BigramRelativeFrequency.class.getSimpleName()); LOG.info(" - input path: " + inputPath); LOG.info(" - output path: " + outputPath); LOG.info(" - num reducers: " + reduceTasks); Job job = Job.getInstance(getConf()); job.setJobName(BigramRelativeFrequency.class.getSimpleName()); job.setJarByClass(BigramRelativeFrequency.class); job.setNumReduceTasks(reduceTasks); FileInputFormat.setInputPaths(job, new Path(inputPath)); FileOutputFormat.setOutputPath(job, new Path(outputPath)); job.setMapOutputKeyClass(PairOfStrings.class); job.setMapOutputValueClass(FloatWritable.class); job.setOutputKeyClass(PairOfStrings.class); job.setOutputValueClass(FloatWritable.class); //job.setOutputFormatClass(SequenceFileOutputFormat.class); job.setMapperClass(MyMapper.class); job.setCombinerClass(MyCombiner.class); job.setReducerClass(MyReducer.class); job.setPartitionerClass(MyPartitioner.class); // Delete the output directory if it exists already. Path outputDir = new Path(outputPath); FileSystem.get(getConf()).delete(outputDir, true); long startTime = System.currentTimeMillis(); job.waitForCompletion(true); System.out.println("Job Finished in " + (System.currentTimeMillis() - startTime) / 1000.0 + " seconds"); return 0; }
From source file:TestFormatStorageInputFormat.java
License:Open Source License
public static void main(String[] argv) throws IOException, SerDeException { try {//from w ww . j a v a 2 s . co m if (argv.length != 2) { System.out.println("TestFormatStorageInputFormat <input> <output>"); System.exit(-1); } JobConf conf = new JobConf(TestFormatStorageInputFormat.class); conf.setJobName("TestFormatStorageInputFormat"); conf.setNumMapTasks(1); conf.setNumReduceTasks(1); conf.setOutputKeyClass(LongWritable.class); conf.setOutputValueClass(Unit.Record.class); conf.setInputFormat(TextInputFormat.class); conf.setOutputFormat(FormatStorageOutputFormat.class); conf.set("mapred.output.compress", "flase"); conf.set("mapred.input.dir", argv[0]); Head head = new Head(); initHead(head); head.toJobConf(conf); FormatStorageSerDe serDe = initSerDe(conf); StandardStructObjectInspector oi = (StandardStructObjectInspector) serDe.getObjectInspector(); List<? extends StructField> fieldRefs = oi.getAllStructFieldRefs(); FileInputFormat.setInputPaths(conf, argv[0]); Path outputPath = new Path(argv[1]); FileOutputFormat.setOutputPath(conf, outputPath); InputFormat inputFormat = new FormatStorageInputFormat(); InputSplit[] inputSplits = inputFormat.getSplits(conf, 1); if (inputSplits.length == 0) { System.out.println("inputSplits is empty"); return; } else { System.out.println("get Splits:" + inputSplits.length); } int size = inputSplits.length; System.out.println("getSplits return size:" + size); for (int i = 0; i < size; i++) { FormatStorageSplit split = (FormatStorageSplit) inputSplits[i]; System.out.printf("split:" + i + "offset:" + split.getStart() + "len:" + split.getLength() + "path:" + conf.get(ConstVar.InputPath) + "beginLine:" + split.getBeginLine() + "endLine:" + split.getEndLine() + "\n"); } { int totalDelay = 0; RecordReader<WritableComparable, Writable> currRecReader = null; for (int i = 0; i < inputSplits.length; i++) { currRecReader = inputFormat.getRecordReader(inputSplits[i], conf, Reporter.NULL); WritableComparable key; Writable value; key = currRecReader.createKey(); value = currRecReader.createValue(); long begin = System.currentTimeMillis(); int count = 0; while (currRecReader.next(key, value)) { Record record = (Record) value; Object row = serDe.deserialize(record); count++; } long end = System.currentTimeMillis(); long delay = (end - begin) / 1000; totalDelay += delay; System.out.println(count + " record read over, delay " + delay + " s"); } System.out.println("total delay:" + totalDelay); } } catch (Exception e) { e.printStackTrace(); System.out.println("get exception:" + e.getMessage()); } }
From source file:CategoriesInvertedIndex.java
public static void main(String[] args) throws Exception { Configuration conf = new Configuration(); Job job = Job.getInstance(conf, "Inverted Index"); job.setJarByClass(CategoriesInvertedIndex.class); job.setMapperClass(CategoriesMapper.class); job.setReducerClass(CategoriesReducer.class); job.setCombinerClass(CategoriesReducer.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(Text.class); FileInputFormat.addInputPath(job, new Path(args[0])); FileOutputFormat.setOutputPath(job, new Path(args[1])); System.exit(job.waitForCompletion(true) ? 0 : 1); }
From source file:ComRoughSetApproInputSampler.java
License:Apache License
/** * Write a partition file for the given job, using the Sampler provided. * Queries the sampler for a sample keyset, sorts by the output key * comparator, selects the keys for each rank, and writes to the destination * returned from {@link TotalOrderPartitioner#getPartitionFile}. *///from ww w . j a v a 2 s .c o m @SuppressWarnings("unchecked") // getInputFormat, getOutputKeyComparator public static <K, V> void writePartitionFile(Job job, Sampler<K, V> sampler) throws IOException, ClassNotFoundException, InterruptedException { Configuration conf = job.getConfiguration(); final InputFormat inf = ReflectionUtils.newInstance(job.getInputFormatClass(), conf); int numPartitions = job.getNumReduceTasks(); K[] samples = (K[]) sampler.getSample(inf, job); LOG.info("Using " + samples.length + " samples"); RawComparator<K> comparator = (RawComparator<K>) job.getSortComparator(); Arrays.sort(samples, comparator); Path dst = new Path(TotalOrderPartitioner.getPartitionFile(conf)); FileSystem fs = dst.getFileSystem(conf); if (fs.exists(dst)) { fs.delete(dst, false); } SequenceFile.Writer writer = SequenceFile.createWriter(fs, conf, dst, job.getMapOutputKeyClass(), NullWritable.class); NullWritable nullValue = NullWritable.get(); float stepSize = samples.length / (float) numPartitions; int last = -1; for (int i = 1; i < numPartitions; ++i) { int k = Math.round(stepSize * i); while (last >= k && comparator.compare(samples[last], samples[k]) == 0) { ++k; } writer.append(samples[k], nullValue); last = k; } writer.close(); }