Example usage for org.apache.hadoop.mapreduce.lib.input SequenceFileRecordReader SequenceFileRecordReader

List of usage examples for org.apache.hadoop.mapreduce.lib.input SequenceFileRecordReader SequenceFileRecordReader

Introduction

In this page you can find the example usage for org.apache.hadoop.mapreduce.lib.input SequenceFileRecordReader SequenceFileRecordReader.

Prototype

SequenceFileRecordReader

Source Link

Usage

From source file:com.alexholmes.hadooputils.combine.seqfile.mapreduce.CombineSequenceFileInputFormat.java

License:Apache License

@Override
public RecordReader createRecordReader(InputSplit split, TaskAttemptContext context) throws IOException {
    return new CommonCombineFileRecordReader<K, V>(
            new CommonCombineFileRecordReader.RecordReaderEngineerer<K, V>() {
                @Override/*from  w  w  w .  j a v a  2 s .  co m*/
                public RecordReader<K, V> createRecordReader() {
                    return new SequenceFileRecordReader<K, V>();
                }
            });
}

From source file:com.conductor.hadoop.WritableValueInputFormat.java

License:Apache License

@Override
public RecordReader<NullWritable, V> createRecordReader(final InputSplit split,
        final TaskAttemptContext context) throws IOException, InterruptedException {
    final SequenceFileRecordReader<NullWritable, V> reader = new SequenceFileRecordReader<NullWritable, V>();
    reader.initialize(split, context);//  ww  w . ja v  a  2  s . co  m
    return reader;
}

From source file:com.conductor.s3.S3SequenceFileInputFormat.java

License:Apache License

@Override
public RecordReader<K, V> createRecordReader(InputSplit split, TaskAttemptContext context) throws IOException {
    return new SequenceFileRecordReader<K, V>();
}

From source file:com.inmobi.conduit.distcp.tools.mapred.lib.DynamicInputChunk.java

License:Apache License

private void openForRead(TaskAttemptContext taskAttemptContext) throws IOException, InterruptedException {
    reader = new SequenceFileRecordReader<K, V>();
    reader.initialize(/* w w  w  .j av  a 2  s  .  c om*/
            new FileSplit(chunkFilePath, 0, DistCpUtils.getFileSize(chunkFilePath, chunkSet.getConf()), null),
            taskAttemptContext);
}

From source file:com.inmobi.conduit.distcp.tools.mapred.UniformSizeInputFormat.java

License:Apache License

/**
 * Implementation of InputFormat::createRecordReader().
 * @param split: The split for which the RecordReader is sought.
 * @param context: The context of the current task-attempt.
 * @return A SequenceFileRecordReader instance, (since the copy-listing is a
 * simple sequence-file.)/*  w  w w.  ja  v a 2 s  . c  o  m*/
 * @throws IOException
 * @throws InterruptedException
 */
@Override
public RecordReader<Text, FileStatus> createRecordReader(InputSplit split, TaskAttemptContext context)
        throws IOException, InterruptedException {
    return new SequenceFileRecordReader<Text, FileStatus>();
}

From source file:jp.ac.u.tokyo.m.dpc.pig.udf.load.path.MultiFileInputFormat.java

License:Apache License

/**
 * return reader which accepted extension. <br>
 * <br>/*from  w  w w . j  a  v  a 2  s .c  om*/
 * ???? reader ??? <br>
 * SequenceFile : .seq? <br>
 *  : .txt??????????? <br>
 */
@Override
public RecordReader<LongWritable, Text> createRecordReader(InputSplit aSplit, TaskAttemptContext aContext) {
    // FileSplit ??????
    if (aSplit instanceof FileSplit) {
        FileSplit tFileSplit = (FileSplit) aSplit;
        Path tPath = tFileSplit.getPath();
        String tFileName = tPath.getName();
        String tExtension = tFileName.substring(tFileName.lastIndexOf("."));
        // ???? RecordReader ?
        if (tExtension != null) {
            if (tExtension.equals(PathConstants.EXTENSION_TEXT)) {
                return new LineRecordReader();
            } else if (tExtension.equals(PathConstants.EXTENSION_SEQUENCE)) {
                return new SequenceFileRecordReader<LongWritable, Text>();
            }
        }
    }
    // ? Text ? RecordReader
    return new LineRecordReader();
}

From source file:org.apache.beam.sdk.io.hadoop.format.HadoopFormatIOSequenceFileTest.java

License:Apache License

private Stream<KV<Text, LongWritable>> extractResultsFromFile(String fileName) {
    try (SequenceFileRecordReader<Text, LongWritable> reader = new SequenceFileRecordReader<>()) {
        Path path = new Path(fileName);
        TaskAttemptContext taskContext = HadoopFormats.createTaskAttemptContext(new Configuration(),
                new JobID("readJob", 0), 0);
        reader.initialize(new FileSplit(path, 0L, Long.MAX_VALUE, new String[] { "localhost" }), taskContext);
        List<KV<Text, LongWritable>> result = new ArrayList<>();

        while (reader.nextKeyValue()) {
            result.add(KV.of(new Text(reader.getCurrentKey().toString()),
                    new LongWritable(reader.getCurrentValue().get())));
        }//from  w w  w  .  ja v a 2s.co m

        return result.stream();
    } catch (Exception e) {
        throw new RuntimeException(e);
    }
}

From source file:org.godhuli.rhipe.SequenceFileAsRHTextRecordReader.java

License:Apache License

public SequenceFileAsRHTextRecordReader() throws IOException {
    sequenceFileRecordReader = new SequenceFileRecordReader<WritableComparable<?>, Writable>();
}