List of usage examples for org.apache.hadoop.conf Configuration getInt
public int getInt(String name, int defaultValue)
name
property as an int
. From source file:com.taobao.adfs.file.FileRepository.java
License:Apache License
public FileRepository(Configuration conf) throws IOException { super(conf);/*from w w w .ja va 2 s. co m*/ nameMaxLength = conf.getInt("file.name.length.max", File.nameMaxLength); if (nameMaxLength > File.nameMaxLength) { Utilities.logInfo(logger, "file.name.length.max is ", nameMaxLength, ", large than ", File.nameMaxLength, ", limit it to be ", File.nameMaxLength); nameMaxLength = File.nameMaxLength; } nextIdForFreeId.set(new Random().nextLong()); }
From source file:com.tdunning.plume.local.lazy.MapRedExecutor.java
License:Apache License
/** * Builds the execution tree out of a {@link PlumeWorkflow} by reading its class in hadoop configuration. * Then, it identifies which MSCR step is being executed by looking at the mscr_id parameter. Finally, it returns this MSCR. * //from www . j ava 2 s . c o m * @param conf * @return */ static MSCR readMSCR(Configuration conf) { String className = conf.get(MapRedExecutor.WORKFLOW_NAME); int id = conf.getInt(MapRedExecutor.MSCR_ID, -1); if (id == -1) { throw new RuntimeException("No MSCR ID in hadoop conf."); } try { PlumeWorkflow workFlow = (PlumeWorkflow) Class.forName(className).newInstance(); Optimizer optimizer = new Optimizer(); ExecutionStep step = optimizer.optimize(workFlow); do { for (MSCR mscr : step.mscrSteps) { if (mscr.getId() == id) { return mscr; } } step = step.nextStep; } while (step != null); throw new RuntimeException("Invalid MSCR ID in hadoop conf: " + id); } catch (InstantiationException e) { throw new RuntimeException(e); } catch (IllegalAccessException e) { throw new RuntimeException(e); } catch (ClassNotFoundException e) { throw new RuntimeException(e); } }
From source file:com.tgam.hadoop.mapred.EscapedLineRecordReader.java
License:Apache License
public EscapedLineRecordReader(Configuration job, FileSplit split) throws IOException { this.maxLineLength = job.getInt("mapred.linerecordreader.maxlength", Integer.MAX_VALUE); start = split.getStart();/*from w w w . ja v a2 s. co m*/ end = start + split.getLength(); final Path file = split.getPath(); 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); FSDataInputStream fileIn = fs.open(split.getPath()); boolean skipFirstLine = false; if (codec != null) { in = new LineReader(codec.createInputStream(fileIn), job); end = Long.MAX_VALUE; } else { if (start != 0) { skipFirstLine = true; --start; fileIn.seek(start); } in = new LineReader(fileIn, job); } if (skipFirstLine) { // skip first line and re-establish "start". start += in.readLine(new Text(), 0, (int) Math.min((long) Integer.MAX_VALUE, end - start)); } this.pos = start; }
From source file:com.tgam.hadoop.mapred.EscapedLineRecordReader.java
License:Apache License
public EscapedLineRecordReader(InputStream in, long offset, long endOffset, Configuration job) throws IOException { this.maxLineLength = job.getInt("mapred.linerecordreader.maxlength", Integer.MAX_VALUE); this.in = new LineReader(in, job); this.start = offset; this.pos = offset; this.end = endOffset; }
From source file:com.tgam.hadoop.util.GenericEscapedLineReader.java
License:Apache License
/** * Create a line reader that reads from the given stream using the * <code>io.file.buffer.size</code> specified in the given * <code>Configuration</code>. * @param in input stream/*from ww w .j a v a 2 s . c o m*/ * @param conf configuration * @throws IOException */ public GenericEscapedLineReader(InputStream in, Configuration conf) throws IOException { this(in, conf.getInt("io.file.buffer.size", DEFAULT_BUFFER_SIZE)); }
From source file:com.thinkbiganalytics.inputformat.hadoop.mapred.EscapedLineReader.java
License:Open Source License
/** * Create a multi-line reader that reads from the given stream using the * <code>io.file.buffer.size</code> specified in the given * <code>Configuration</code>. * * @param in input stream/*from ww w. j a va 2 s. c o m*/ * @param conf configuration */ public EscapedLineReader(InputStream in, Configuration conf) throws IOException { this(in, conf.getInt("io.file.buffer.size", DEFAULT_BUFFER_SIZE), DEFAULT_ESCAPE_CHARACTER); }
From source file:com.thinkbiganalytics.inputformat.hadoop.mapred.EscapedLineReader.java
License:Open Source License
public EscapedLineReader(InputStream in, Configuration conf, byte escapeChar) throws IOException { this(in, conf.getInt("io.file.buffer.size", DEFAULT_BUFFER_SIZE), escapeChar); }
From source file:com.thinkbiganalytics.inputformat.hadoop.mapred.OmnitureDataFileRecordReader.java
License:Open Source License
public OmnitureDataFileRecordReader(Configuration job, FileSplit split) throws IOException { this.maxLineLength = job.getInt("mapred.escapedlinereader.maxlength", Integer.MAX_VALUE); this.start = split.getStart(); this.end = start + split.getLength(); final Path file = split.getPath(); this.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); FSDataInputStream fileIn = fs.open(split.getPath()); boolean skipFirstLine = false; if (codec != null) { lineReader = new EscapedLineReader(codec.createInputStream(fileIn), job); end = Long.MAX_VALUE;//from www. ja v a2s. co m } else { if (start != 0) { skipFirstLine = true; --start; fileIn.seek(start); } lineReader = new EscapedLineReader(fileIn, job); } if (skipFirstLine) { start += lineReader.readLine(new Text(), 0, (int) Math.min((long) Integer.MAX_VALUE, end - start)); } this.pos = start; }
From source file:com.thinkbiganalytics.kylo.catalog.azure.AzureNativeFileSystemProvider.java
License:Apache License
@Nonnull private CloudBlobClient createBlobClient(@Nonnull final URI uri, @Nonnull final Configuration conf) { // Determine endpoint final String httpScheme = StringUtils.equalsAnyIgnoreCase(uri.getScheme(), "asvs", "wasbs") ? "https" : "http"; final URI blobEndPoint = URI.create(httpScheme + "://" + uri.getRawAuthority()); // Create client final CloudBlobClient client = new CloudBlobClient(blobEndPoint, getCredentials(uri, conf)); final RetryPolicyFactory retryPolicyFactory = new RetryExponentialRetry( conf.getInt("fs.azure.io.retry.min.backoff.interval", 3 * 1000 /* 1s */), conf.getInt("fs.azure.io.retry.backoff.interval", 3 * 1000 /* 1s */), conf.getInt("fs.azure.io.retry.max.backoff.interval", 30 * 1000 /* 30s */), conf.getInt("fs.azure.io.retry.max.retries", 30)); client.getDefaultRequestOptions().setRetryPolicyFactory(retryPolicyFactory); final int storageConnectionTimeout = conf.getInt("fs.azure.storage.timeout", 0); if (storageConnectionTimeout > 0) { client.getDefaultRequestOptions().setTimeoutIntervalInMs(storageConnectionTimeout * 1000); }/*from w w w. ja va2 s . c om*/ return client; }
From source file:com.tomslabs.grid.avro.AvroFileOutputFormat.java
License:Apache License
@Override public RecordWriter<T, Object> getRecordWriter(TaskAttemptContext context) throws IOException, InterruptedException { Configuration config = context.getConfiguration(); Schema schema = getWriteSchema(config); DatumWriter<T> datumWriter = getDatumWriter(config); final DataFileWriter<T> writer = new DataFileWriter<T>(datumWriter); if (getCompressOutput(context)) { int level = config.getInt(DEFLATE_LEVEL_KEY, DEFAULT_DEFLATE_LEVEL); writer.setCodec(CodecFactory.deflateCodec(level)); }// ww w . j a v a 2 s.co m Path file = getDefaultWorkFile(context, EXT); FileSystem fs = file.getFileSystem(config); writer.create(schema, fs.create(file)); return new AvroRecordWriter<T>(writer); }