Example usage for org.apache.hadoop.io.compress GzipCodec GzipCodec

Introduction

In this page you can find the example usage for org.apache.hadoop.io.compress GzipCodec GzipCodec.

Prototype

GzipCodec

Source Link

Usage

From source file:tests.it.crs4.seal.common.TestSamInputFormat.java

License:Open Source License

@Test
public void testGzCompressedInput() throws IOException {
    // write gzip-compressed data
    GzipCodec codec = new GzipCodec();
    PrintWriter out = new PrintWriter(
            new BufferedOutputStream(codec.createOutputStream(new FileOutputStream(tempGz))));
    out.write(twoRecords);//from  w  w  w  . j av  a2s.co  m
    out.close();

    // now try to read it
    split = new FileSplit(new Path(tempGz.toURI().toString()), 0, twoRecords.length(), null);

    SamRecordReader reader = new SamRecordReader();
    reader.initialize(split, Utils.getTaskAttemptContext(conf));

    boolean retval = reader.nextKeyValue();
    assertTrue(retval);
    assertEquals("Read/2", reader.getCurrentValue().getAnyRead().getName());

    retval = reader.nextKeyValue();
    assertTrue(retval);
    assertEquals("Read/1", reader.getCurrentValue().getAnyRead().getName());
}

From source file:tests.it.crs4.seal.common.TestSamInputFormat.java

License:Open Source License

@Test(expected = RuntimeException.class)
public void testCompressedSplit() throws IOException {
    // write gzip-compressed data
    GzipCodec codec = new GzipCodec();
    PrintWriter out = new PrintWriter(
            new BufferedOutputStream(codec.createOutputStream(new FileOutputStream(tempGz))));
    out.write(twoRecords);/*  w ww.ja v  a 2s.  c o  m*/
    out.close();

    // now try to read it starting from the middle

    SamInputFormat inputFormat = new SamInputFormat();

    split = new FileSplit(new Path(tempGz.toURI().toString()), 10, twoRecords.length(), null);
    RecordReader<LongWritable, ReadPair> reader = inputFormat.createRecordReader(split,
            Utils.getTaskAttemptContext(conf));
}