eu.dicodeproject.analysis.generic.GenericTableDriver Maven / Gradle / Ivy

Go to download

Show more of this group Show more artifacts with this name
Show all versions of integration Show documentation

The examples module provides glue code implementation for extracting common phrases, key word distributions and more from tweets stored on HDFS/HBase. It builds on Mahout for more sophisticated analysis.

The newest version!

/**
 * Copyright (C) 2010, 2011 Neofonie GmbH
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of 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 eu.dicodeproject.analysis.generic;

import java.io.IOException;
import java.util.Map;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.hbase.HBaseConfiguration;
import org.apache.hadoop.hbase.mapreduce.TableMapReduceUtil;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.input.SequenceFileInputFormat;
import org.apache.hadoop.util.ToolRunner;
import org.apache.mahout.common.AbstractJob;
import org.apache.mahout.common.commandline.DefaultOptionCreator;



/**
 * Reads text from a configurable HBase table and column, extracts the content 
 * (or in some cases single items from a list seperated by a separator like '#')
 * and writes the counts to HDFS.
 */
public final class GenericTableDriver extends AbstractJob {

  private GenericTableDriver() {
    // don't instantiate drivers
  }

  public static void main(String args[]) throws Exception {
    ToolRunner.run(new GenericTableDriver(), args);
  }

  @Override
  public int run(String[] args) throws ClassNotFoundException, InterruptedException, IOException {
    addOption(DefaultOptionCreator.numReducersOption().create());
    addOption("input", "i", "The directory holding word/count pairs", "tmp");
    addOption("table", "t", "The hbase table storing the results.", "dummy-results");    
    addOption("resultId", "r", "The result which will be the row prefix.", "");

    Map argMap = parseArguments(args);
    if (argMap == null) {
      return -1;
    }
    String input = argMap.get("--input");
    String table = argMap.get("--table");

    Configuration conf = HBaseConfiguration.create();
    conf.set("resultId", argMap.get("--resultId")); // for the reducer
    Job job = new Job(conf);

    job.setJarByClass(GenericTableDriver.class);
    job.setInputFormatClass(SequenceFileInputFormat.class);

    FileInputFormat.addInputPath(job, new Path(input));
    job.setJobName("HBaseDocumentProcessor::GenericTableWriter");

    job.setMapperClass(Mapper.class);
    job.setMapOutputKeyClass(IntWritable.class);
    job.setMapOutputValueClass(Text.class);

    TableMapReduceUtil.initTableReducerJob(table, GenericTableReducer.class, job);

    job.setNumReduceTasks(1);
    job.waitForCompletion(true);
    return 0;
  }
}