com.marcolotz.lung.io.inputFormat.WholeFileRecordReader.java Source code

Introduction

Here is the source code for com.marcolotz.lung.io.inputFormat.WholeFileRecordReader.java

Source

/*******************************************************************************
 * Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International
 * 
 * Copyright (c) 2014 Marco Aurelio Barbosa Fagnani Gomes Lotz (marcolotz.com)
 * 
 * The source code in this document is licensed under Creative Commons
 * Attribution-NonCommercial-ShareAlike 4.0 International License. You must 
 * credit the author of the source code in the way specified by the author or
 * licenser (but not in a way to suggest that the author or licenser has given 
 * you allowance to you or to your use of the source code). If you modify,
 * transform or create using this source code as basis, you can only distribute
 * the new source code under the same license or a similar license to this one.
 * 
 * The above copyright notice and this permission notice shall be included in
 * all copies or substantial portions of the Software.
 * 
 * To see a copy of the license, access:
 * creativecommons.org/licenses/by-nc-sa/4.0/legalcode
 ******************************************************************************/
package com.marcolotz.lung.io.inputFormat;

import java.io.IOException;

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.IOUtils;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.BytesWritable;
import org.apache.hadoop.mapreduce.InputSplit;
import org.apache.hadoop.mapreduce.TaskAttemptContext;
import org.apache.hadoop.mapreduce.RecordReader;
import org.apache.hadoop.mapreduce.lib.input.FileSplit;

/**
 * Writes the whole file as a value for a Null key. This implementation is
 * described in the Tom White Hadoop book.
 * 
 * This WholeFileRecordReader may the compatible with the
 * {@link MultipleFilesInputFormat}, but no checks were performed so far.
 * 
 * @author Marco Aurelio Lotz
 * 
 */

class WholeFileRecordReader extends RecordReader<NullWritable, BytesWritable> {
    private FileSplit fileSplit;
    private Configuration conf;
    private BytesWritable value = new BytesWritable();
    private boolean processed = false;

    @Override
    public void initialize(InputSplit split, TaskAttemptContext context) throws IOException, InterruptedException {
        this.fileSplit = (FileSplit) split;
        this.conf = context.getConfiguration();
    }

    @Override
    public boolean nextKeyValue() throws IOException, InterruptedException {
        /* if that record reader for that input split was not called yet */
        if (!processed) {
            byte[] contents = new byte[(int) fileSplit.getLength()];

            Path file = fileSplit.getPath();

            // Reads from the conf file what is the desired file system.
            FileSystem fs = file.getFileSystem(conf);

            FSDataInputStream in = null;

            try {
                in = fs.open(file);
                IOUtils.readFully(in, contents, 0, contents.length);
                value.set(contents, 0, contents.length);
            } finally {
                IOUtils.closeStream(in);
            }

            processed = true;
            return true;
        }
        return false;
    }

    @Override
    public NullWritable getCurrentKey() throws IOException, InterruptedException {
        return NullWritable.get();
    }

    @Override
    public BytesWritable getCurrentValue() throws IOException, InterruptedException {
        return value;
    }

    @Override
    public float getProgress() throws IOException {
        return processed ? 1.0f : 0.0f;
    }

    @Override
    public void close() throws IOException {
        /*
         * The file should closed right after it has been read. Thus performs
         * nothing.
         */
    }

}