org.broadinstitute.sting.gatk.hadoop.hadoopsrc.LineRecordReader.java Source code

Introduction

Here is the source code for org.broadinstitute.sting.gatk.hadoop.hadoopsrc.LineRecordReader.java

Source

/**
 * Licensed to the Apache Software Foundation (ASF) under one
 * or more contributor license agreements.  See the NOTICE file
 * distributed with this work for additional information
 * regarding copyright ownership.  The ASF licenses this file
 * to you under the Apache License, Version 2.0 (the
 * "License"); you may not use this file except in compliance
 * with the License.  You may obtain a copy of the License at
 *
 *     http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 * See the License for the specific language governing permissions and
 * limitations under the License.
 */

package org.broadinstitute.sting.gatk.hadoop.hadoopsrc;

import java.io.IOException;

// Removed logging
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FSDataInputStream;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.InputSplit;
import org.apache.hadoop.mapreduce.RecordReader;
import org.apache.hadoop.mapreduce.TaskAttemptContext;
import org.apache.hadoop.util.LineReader;
import org.broadinstitute.sting.gatk.hadoop.XFileSplit;

/**
 * Treats keys as offset in file and value as line.
 */
public class LineRecordReader extends RecordReader<LongWritable, Text> {

    private long start;
    private long pos;
    private long end;
    private LineReader in;
    private int maxLineLength;
    private LongWritable key = null;
    private Text value = null;

    public void initialize(InputSplit genericSplit, TaskAttemptContext context) throws IOException {
        XFileSplit split = (XFileSplit) genericSplit;
        Configuration job = context.getConfiguration();
        final Path file = split.getPath();

        // open the file and seek to the start of the split
        FileSystem fs = file.getFileSystem(job);
        FSDataInputStream fileIn = fs.open(split.getPath());
        this.start = split.getStart();
        fileIn.seek(this.start);
        this.maxLineLength = job.getInt("mapred.linerecordreader.maxlength", Integer.MAX_VALUE);
        in = new LineReader(fileIn, job);
        this.pos = start;
        this.end = Long.MAX_VALUE;
    }

    public boolean nextKeyValue() throws IOException {
        if (key == null) {
            key = new LongWritable();
        }
        key.set(pos);
        if (value == null) {
            value = new Text();
        }
        int newSize = 0;
        while (pos < end) {
            newSize = in.readLine(value, maxLineLength,
                    Math.max((int) Math.min(Integer.MAX_VALUE, end - pos), maxLineLength));
            if (newSize == 0) {
                break;
            }
            pos += newSize;
            if (newSize < maxLineLength) {
                break;
            }

        }
        if (newSize == 0) {
            key = null;
            value = null;
            return false;
        } else {
            return true;
        }
    }

    @Override
    public LongWritable getCurrentKey() {
        return key;
    }

    @Override
    public Text getCurrentValue() {
        return value;
    }

    /**
     * Get the progress within the split
     */
    public float getProgress() {
        if (start == end) {
            return 0.0f;
        } else {
            return Math.min(1.0f, (pos - start) / (float) (end - start));
        }
    }

    public synchronized void close() throws IOException {
        if (in != null) {
            in.close();
        }
    }
}