WholeFileRecordReader.java

package de.l3s.common.hadoop;
/*
 * TIMETool - Large-scale Temporal Search in MapReduce
 *
 * Licensed 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.
 */

/*
 * THIS SOFTWARE IS PROVIDED BY THE LEMUR PROJECT AS PART OF THE CLUEWEB09
 * PROJECT AND OTHER CONTRIBUTORS "AS IS" AND ANY EXPRESS OR IMPLIED
 * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
 * MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN
 * NO EVENT SHALL THE COPYRIGHT HOLDERS OR CONTRIBUTORS BE LIABLE FOR ANY
 * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT,
 * STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING
 * IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
 * POSSIBILITY OF SUCH DAMAGE.
 *
 * @author 
 */

import java.io.IOException;

import org.apache.hadoop.io.BytesWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;

import org.apache.hadoop.mapreduce.lib.input.FileSplit;
import org.apache.hadoop.mapreduce.InputSplit;
import org.apache.hadoop.mapreduce.RecordReader;
import org.apache.hadoop.mapreduce.TaskAttemptContext;
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.log4j.Logger;

class WholeFileRecordReader extends RecordReader<LongWritable, Text> {
  
    private FileSplit fileSplit;
    private Configuration conf;
    private boolean processed = false;
  
    private LongWritable key = new LongWritable();
    private Text value = new Text();
    
    private static final Logger logger = Logger
	.getLogger(WholeFileRecordReader.class);
    @Override
    public void initialize(InputSplit inputSplit, TaskAttemptContext taskAttemptContext) throws IOException, InterruptedException {
        this.fileSplit = (FileSplit) inputSplit;
        this.conf = taskAttemptContext.getConfiguration();
    }
    @Override
    public boolean nextKeyValue() throws IOException {
        if (!processed) {
            byte[] contents = new byte[(int) fileSplit.getLength()];

            Path file = fileSplit.getPath();
            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 LongWritable getCurrentKey() throws IOException, InterruptedException {
        return key;
    }

    @Override
    public Text getCurrentValue() throws IOException, InterruptedException {
        return value;
    }
    
    @Override
    public float getProgress() throws IOException, InterruptedException  {
        return processed ? 1.0f : 0.0f;
    }

    @Override
    public void close() throws IOException {
        // do nothing
    }
}