List of usage examples for org.apache.hadoop.mapreduce TaskAttemptContext getConfiguration
public Configuration getConfiguration();
From source file:BamRecordReader.java
License:Apache License
public void initialize(InputSplit genericSplit, TaskAttemptContext context) throws IOException { FileSplit split = (FileSplit) genericSplit; Configuration job = context.getConfiguration(); this.maxLineLength = job.getInt("mapred.linerecordreader.maxlength", Integer.MAX_VALUE); start = split.getStart();//from w w w .java 2s. com split_length = split.getLength(); System.out.println("start: " + start); System.out.println("split_length: " + split_length); fileInfo = split.getPath(); //String fileName = fileInfo.toString().split("-")[0]; //Path file = new Path(fileName); //compressionCodecs = new CompressionCodecFactory(job); //final CompressionCodec codec = compressionCodecs.getCodec(file); // open the file and seek to the start of the split //FileSystem fs = file.getFileSystem(job); //fileIn = fs.open(file); //fileIn.seek(start); //this.pos = start; }
From source file:HtmlInputFormat.java
License:Apache License
@Override public RecordReader<LongWritable, Text> createRecordReader(InputSplit split, TaskAttemptContext context) { try {/*from ww w.j a v a 2 s . c o m*/ return new HtmlRecordReader((FileSplit) split, context.getConfiguration()); } catch (IOException ioe) { return null; } }
From source file:ZipFileRecordReader.java
License:Apache License
/** * Initialise and open the ZIP file from the FileSystem *///www.ja v a 2 s . c o m @Override public void initialize(InputSplit inputSplit, TaskAttemptContext taskAttemptContext) throws IOException, InterruptedException { FileSplit split = (FileSplit) inputSplit; Configuration conf = taskAttemptContext.getConfiguration(); Path path = split.getPath(); FileSystem fs = path.getFileSystem(conf); // Open the stream fsin = fs.open(path); zip = new ZipInputStream(fsin); }
From source file:alluxio.hadoop.mapreduce.KeyValueOutputCommitter.java
License:Apache License
/** * @param taskContext MapReduce task configuration * @return true if the task output directory exists, otherwise false * @throws IOException if fails to determine whether the output directory exists *//* w w w.j a v a 2s. com*/ @Override public boolean needsTaskCommit(TaskAttemptContext taskContext) throws IOException { Path taskOutputPath = new Path(KeyValueOutputFormat.getTaskOutputURI(taskContext).toString()); FileSystem fs = taskOutputPath.getFileSystem(taskContext.getConfiguration()); return fs.exists(taskOutputPath); }
From source file:andromache.hadoop.CassandraRecordReader.java
License:Apache License
public void initialize(InputSplit split, TaskAttemptContext context) throws IOException { this.context = context; this.split = (CassandraSplit) split; Configuration conf = context.getConfiguration(); KeyRange jobRange = CassandraConfigHelper.getInputKeyRange(conf); filter = jobRange == null ? null : jobRange.row_filter; predicate = CassandraConfigHelper.getInputSlicePredicate(conf); boolean widerows = CassandraConfigHelper.getInputIsWide(conf); isEmptyPredicate = isEmptyPredicate(predicate); totalRowCount = CassandraConfigHelper.getInputSplitSize(conf); batchSize = CassandraConfigHelper.getRangeBatchSize(conf); cfName = ((CassandraSplit) split).getCf(); consistencyLevel = CassandraConfigHelper.getReadConsistencyLevel(conf); keyspace = CassandraConfigHelper.getInputKeyspace(conf); try {/*from ww w . j a v a 2 s.c o m*/ // only need to connect once if (socket != null && socket.isOpen()) { return; } // create connection using thrift String location = getLocation(); socket = new TSocket(location, CassandraConfigHelper.getInputRpcPort(conf), timemout); TTransport transport = CassandraConfigHelper.getInputTransportFactory(conf).openTransport(socket); TBinaryProtocol binaryProtocol = new TBinaryProtocol(transport); client = new Cassandra.Client(binaryProtocol); // log in client.set_keyspace(keyspace); if (CassandraConfigHelper.getInputKeyspaceUserName(conf) != null) { Map<String, String> creds = new HashMap<String, String>(); creds.put(IAuthenticator.USERNAME_KEY, CassandraConfigHelper.getInputKeyspaceUserName(conf)); creds.put(IAuthenticator.PASSWORD_KEY, CassandraConfigHelper.getInputKeyspacePassword(conf)); AuthenticationRequest authRequest = new AuthenticationRequest(creds); client.login(authRequest); } } catch (Exception e) { throw new RuntimeException(e); } iter = widerows ? new WideRowIterator() : new StaticRowIterator(); logger.debug("created {}", iter); }
From source file:andromache.hadoop.CassandraRecordWriter.java
License:Apache License
CassandraRecordWriter(TaskAttemptContext context) throws IOException { this.progressable = context; Configuration conf = context.getConfiguration(); int queueSize = conf.getInt(QUEUE_SIZE, 256); int batchSize = conf.getInt(BATCH_SIZE, 32); long batchDelay = conf.getLong(BATCH_DELAY_MS, 200); ConsistencyLevel consistencyLevel = CassandraConfigHelper.getWriteConsistencyLevel(conf); CassandraClientFactory cassandraClientFactory = new CassandraClientFactory( CassandraConfigHelper.getOutputTransportFactory(conf), CassandraConfigHelper.getOutputRpcPort(conf)); this.rangeThreadsCache = new RangeThreadsCache(conf, cassandraClientFactory, queueSize, batchSize, batchDelay, progressable, consistencyLevel); log.info("Using consistency level of {}", consistencyLevel); }
From source file:authordetect.input.SingleBookReader.java
/** * @param inputSplit//from w w w . ja v a 2 s .c o m * @param context the information about the task * @throws java.io.IOException * @throws InterruptedException */ @Override public void initialize(InputSplit inputSplit, TaskAttemptContext context) throws IOException, InterruptedException { FileSplit split = (FileSplit) inputSplit; Configuration configuration = context.getConfiguration(); // get the option from configuration: // 0 for group by author, 1 for group by book int option = configuration.getInt("GROUP_OPTION", 0); Path path = split.getPath(); filename = path.getName(); FileSystem fileSystem = path.getFileSystem(configuration); FSDataInputStream inputStream = fileSystem.open(path); lineReader = new LineReader(inputStream, configuration); //initial start point and end point start = split.getStart(); end = start + split.getLength(); inputStream.seek(start); if (start != 0) { start += lineReader.readLine(new Text(), 0, (int) Math.min(Integer.MAX_VALUE, end - start)); } start += lineReader.readLine(currentLine); prepareToScanBook(option); }
From source file:authors.XmlInputFormat.java
License:Apache License
@Override public RecordReader<LongWritable, Text> createRecordReader(InputSplit split, TaskAttemptContext context) { try {// www.j a v a 2 s . co m return new XmlRecordReader((FileSplit) split, context.getConfiguration()); } catch (IOException ioe) { log.warn("Error while creating XmlRecordReader", ioe); return null; } }
From source file:be.ugent.intec.halvade.uploader.mapreduce.MyFastqOutputFormat.java
public RecordWriter<PairedIdWritable, FastqRecord> getRecordWriter(TaskAttemptContext task) throws IOException { Configuration conf = task.getConfiguration(); boolean isCompressed = getCompressOutput(task); CompressionCodec codec = null;/* w ww . j a v a 2 s .com*/ String extension = ""; if (isCompressed) { Class<? extends CompressionCodec> codecClass = getOutputCompressorClass(task, GzipCodec.class); codec = (CompressionCodec) ReflectionUtils.newInstance(codecClass, conf); extension = codec.getDefaultExtension(); } Path file = getDefaultWorkFile(task, extension); FileSystem fs = file.getFileSystem(conf); OutputStream output; if (isCompressed) { FSDataOutputStream fileOut = fs.create(file, false); output = new DataOutputStream(codec.createOutputStream(fileOut)); } else { output = fs.create(file, false); } return new FastqRecordWriter(conf, output); }
From source file:br.ufpr.inf.hpath.XmlItemInputFormat.java
License:Apache License
@Override public RecordReader<LongWritable, Text> createRecordReader(InputSplit split, TaskAttemptContext context) { try {/*from w w w . j av a 2 s .c om*/ return new XmlRecordReader((FileSplit) split, context.getConfiguration()); } catch (IOException ioe) { log.warn("Error while creating XmlRecordReader", ioe); return null; } catch (Exception e) { e.printStackTrace(); return null; } }