Java Code Examples for org.apache.hadoop.mapreduce.lib.input.NLineInputFormat#getSplitsForFile()

The following examples show how to use org.apache.hadoop.mapreduce.lib.input.NLineInputFormat#getSplitsForFile() . You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may check out the related API usage on the sidebar.
Example 1
Source File: InterleaveMulti.java    From ViraPipe with MIT License 6 votes vote down vote up 
private static void splitFastq(FileStatus fst, String fqPath, String splitDir, int splitlen, JavaSparkContext sc) throws IOException {
  Path fqpath = new Path(fqPath);
  String fqname = fqpath.getName();
  String[] ns = fqname.split("\\.");
  //TODO: Handle also compressed files
  List<FileSplit> nlif = NLineInputFormat.getSplitsForFile(fst, sc.hadoopConfiguration(), splitlen);

  JavaRDD<FileSplit> splitRDD = sc.parallelize(nlif);

  splitRDD.foreach( split ->  {

    FastqRecordReader fqreader = new FastqRecordReader(new Configuration(), split);
    writeFastqFile(fqreader, new Configuration(), splitDir + "/split_" + split.getStart() + "." + ns[1]);

   });
}
Example 2
Source File: InterleaveMulti.java    From ViraPipe with MIT License 6 votes vote down vote up 
public static void interleaveSplitFastq(FileStatus fst, FileStatus fst2, String splitDir, int splitlen, JavaSparkContext sc) throws IOException {

    List<FileSplit> nlif = NLineInputFormat.getSplitsForFile(fst, sc.hadoopConfiguration(), splitlen);
    List<FileSplit> nlif2 = NLineInputFormat.getSplitsForFile(fst2, sc.hadoopConfiguration(), splitlen);

    JavaRDD<FileSplit> splitRDD = sc.parallelize(nlif);
    JavaRDD<FileSplit> splitRDD2 = sc.parallelize(nlif2);
    JavaPairRDD<FileSplit, FileSplit> zips = splitRDD.zip(splitRDD2);

    zips.foreach( splits ->  {
      Path path = splits._1.getPath();
      FastqRecordReader fqreader = new FastqRecordReader(new Configuration(), splits._1);
      FastqRecordReader fqreader2 = new FastqRecordReader(new Configuration(), splits._2);
      writeInterleavedSplits(fqreader, fqreader2, new Configuration(), splitDir+"/"+path.getParent().getName()+"_"+splits._1.getStart()+".fq");
    });
  }
Example 3
Source File: Decompress.java    From ViraPipe with MIT License 6 votes vote down vote up 
public static void interleaveSplitFastq(FileStatus fst, FileStatus fst2, String splitDir, int splitlen, JavaSparkContext sc) throws IOException {

    List<FileSplit> nlif = NLineInputFormat.getSplitsForFile(fst, sc.hadoopConfiguration(), splitlen);
    List<FileSplit> nlif2 = NLineInputFormat.getSplitsForFile(fst2, sc.hadoopConfiguration(), splitlen);

    JavaRDD<FileSplit> splitRDD = sc.parallelize(nlif);
    JavaRDD<FileSplit> splitRDD2 = sc.parallelize(nlif2);
    JavaPairRDD<FileSplit, FileSplit> zips = splitRDD.zip(splitRDD2);

    zips.foreach( splits ->  {
      Path path = splits._1.getPath();
      FastqRecordReader fqreader = new FastqRecordReader(new Configuration(), splits._1);
      FastqRecordReader fqreader2 = new FastqRecordReader(new Configuration(), splits._2);

      writeInterleavedSplits(fqreader, fqreader2, new Configuration(), splitDir+"/"+path.getParent().getName()+"_"+splits._1.getStart()+".fq");
    });
  }
Example 4
Source File: DecompressInterleave.java    From ViraPipe with MIT License 6 votes vote down vote up 
public static void interleaveSplitFastq(FileStatus fst, FileStatus fst2, String splitDir, int splitlen, JavaSparkContext sc) throws IOException {

    String[] ns = fst.getPath().getName().split("\\.");
    //TODO: Handle also compressed files
    List<FileSplit> nlif = NLineInputFormat.getSplitsForFile(fst, sc.hadoopConfiguration(), splitlen);
    List<FileSplit> nlif2 = NLineInputFormat.getSplitsForFile(fst2, sc.hadoopConfiguration(), splitlen);

    JavaRDD<FileSplit> splitRDD = sc.parallelize(nlif);
    JavaRDD<FileSplit> splitRDD2 = sc.parallelize(nlif2);
    JavaPairRDD<FileSplit, FileSplit> zips = splitRDD.zip(splitRDD2);

    zips.foreach( splits ->  {
      Path path = splits._1.getPath();
      FastqRecordReader fqreader = new FastqRecordReader(new Configuration(), splits._1);
      FastqRecordReader fqreader2 = new FastqRecordReader(new Configuration(), splits._2);
      writeInterleavedSplits(fqreader, fqreader2, new Configuration(), splitDir, path.getParent().getName()+"_"+splits._1.getStart()+".fq");
    });
  }
Example 5
Source File: Interleave.java    From ViraPipe with MIT License 6 votes vote down vote up 
public static void interleaveSplitFastq(FileStatus fst, FileStatus fst2, String splitDir, int splitlen, JavaSparkContext sc) throws IOException {

    List<FileSplit> nlif = NLineInputFormat.getSplitsForFile(fst, sc.hadoopConfiguration(), splitlen);
    List<FileSplit> nlif2 = NLineInputFormat.getSplitsForFile(fst2, sc.hadoopConfiguration(), splitlen);

    JavaRDD<FileSplit> splitRDD = sc.parallelize(nlif);
    JavaRDD<FileSplit> splitRDD2 = sc.parallelize(nlif2);
    JavaPairRDD<FileSplit, FileSplit> zips = splitRDD.zip(splitRDD2);

    zips.foreach( splits ->  {
      Path path = splits._1.getPath();
      FastqRecordReader fqreader = new FastqRecordReader(new Configuration(), splits._1);
      FastqRecordReader fqreader2 = new FastqRecordReader(new Configuration(), splits._2);
      writeInterleavedSplits(fqreader, fqreader2, new Configuration(), splitDir+"/"+path.getParent().getName()+"_"+splits._1.getStart()+".fq");
    });
  }
Example 6
Source File: Decompress.java    From ViraPipe with MIT License 5 votes vote down vote up 
private static void splitFastq(FileStatus fst, String fqPath, String splitDir, int splitlen, JavaSparkContext sc) throws IOException {
  Path fqpath = new Path(fqPath);
  String fqname = fqpath.getName();
  String[] ns = fqname.split("\\.");
  List<FileSplit> nlif = NLineInputFormat.getSplitsForFile(fst, sc.hadoopConfiguration(), splitlen);

  JavaRDD<FileSplit> splitRDD = sc.parallelize(nlif);

  splitRDD.foreach( split ->  {

    FastqRecordReader fqreader = new FastqRecordReader(new Configuration(), split);
    writeFastqFile(fqreader, new Configuration(), splitDir + "/split_" + split.getStart() + "." + ns[1]);

   });
}
Example 7
Source File: Interleave.java    From ViraPipe with MIT License 5 votes vote down vote up 
private static void splitFastq(FileStatus fst, String fqPath, String splitDir, int splitlen, JavaSparkContext sc) throws IOException {
  Path fqpath = new Path(fqPath);
  String fqname = fqpath.getName();
  String[] ns = fqname.split("\\.");
  List<FileSplit> nlif = NLineInputFormat.getSplitsForFile(fst, sc.hadoopConfiguration(), splitlen);

  JavaRDD<FileSplit> splitRDD = sc.parallelize(nlif);

  splitRDD.foreach( split ->  {

    FastqRecordReader fqreader = new FastqRecordReader(new Configuration(), split);
    writeFastqFile(fqreader, new Configuration(), splitDir + "/split_" + split.getStart() + "." + ns[1]);

   });
}
Example 8
Source File: HDFSWriter.java    From ViraPipe with MIT License 4 votes vote down vote up 
private static JavaPairRDD<Text, SequencedFragment> interleaveReads(String fastq, String fastq2, int splitlen, JavaSparkContext sc) throws IOException {

        FileSystem fs = FileSystem.get(new Configuration());

        FileStatus fst = fs.getFileStatus(new Path(fastq));
        FileStatus fst2 = fs.getFileStatus(new Path(fastq2));

        List<FileSplit> nlif = NLineInputFormat.getSplitsForFile(fst, sc.hadoopConfiguration(), splitlen);
        List<FileSplit> nlif2 = NLineInputFormat.getSplitsForFile(fst2, sc.hadoopConfiguration(), splitlen);

        JavaRDD<FileSplit> splitRDD = sc.parallelize(nlif);
        JavaRDD<FileSplit> splitRDD2 = sc.parallelize(nlif2);
        JavaPairRDD<FileSplit, FileSplit> zips = splitRDD.zip(splitRDD2);

        return zips.flatMapToPair( splits ->  {

            FastqInputFormat.FastqRecordReader fqreader = new FastqInputFormat.FastqRecordReader(new Configuration(), splits._1);
            FastqInputFormat.FastqRecordReader fqreader2 = new FastqInputFormat.FastqRecordReader(new Configuration(), splits._2);

            ArrayList<Tuple2<Text, SequencedFragment>> reads = new ArrayList<Tuple2<Text, SequencedFragment>>();
            while (fqreader.nextKeyValue()) {
                String key = fqreader.getCurrentKey().toString();
                String[] keysplit = key.split(" ");
                key = keysplit[0];

                SequencedFragment sf = new SequencedFragment();
                sf.setQuality(new Text(fqreader.getCurrentValue().getQuality().toString()));
                sf.setSequence(new Text(fqreader.getCurrentValue().getSequence().toString()));

                if (fqreader2.nextKeyValue()) {

                    String key2 = fqreader2.getCurrentKey().toString();
                    String[] keysplit2 = key2.split(" ");
                    key2 = keysplit2[0];
                    //key2 = key2.replace(" 2:N:0:1","/2");

                    SequencedFragment sf2 = new SequencedFragment();
                    sf2.setQuality(new Text(fqreader2.getCurrentValue().getQuality().toString()));
                    sf2.setSequence(new Text(fqreader2.getCurrentValue().getSequence().toString()));
                    reads.add(new Tuple2<Text, SequencedFragment>(new Text(key), sf));
                    reads.add(new Tuple2<Text, SequencedFragment>(new Text(key2), sf2));
                }
            }

            return reads.iterator();

        });
    }
Example 9
Source File: DecompressInterleave.java    From ViraPipe with MIT License 3 votes vote down vote up 
private static void splitFastq(FileStatus fst, String splitDir, int splitlen, JavaSparkContext sc) throws IOException {

    //TODO: Handle also compressed files
    List<FileSplit> nlif = NLineInputFormat.getSplitsForFile(fst, new Configuration(), splitlen);

    JavaRDD<FileSplit> splitRDD = sc.parallelize(nlif);

    splitRDD.foreach( split ->  {

      FastqRecordReader fqreader = new FastqRecordReader(new Configuration(), split);
      writeFastqFile(fqreader, new Configuration(), splitDir + "/" + split.getPath().getName()+"_"+split.getStart() + ".fq");

     });
  }