eu.dicodeproject.analysis.generic.GenericDriver 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.Calendar;
import java.util.Date;
import java.util.Locale;
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.client.Scan;
import org.apache.hadoop.hbase.filter.CompareFilter;
import org.apache.hadoop.hbase.filter.RegexStringComparator;
import org.apache.hadoop.hbase.filter.ValueFilter;
import org.apache.hadoop.hbase.mapreduce.TableMapReduceUtil;
import org.apache.hadoop.hbase.util.Bytes;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.SequenceFileOutputFormat;
import org.apache.hadoop.util.ToolRunner;
import org.apache.mahout.common.AbstractJob;
import org.apache.mahout.common.commandline.DefaultOptionCreator;

/**
 * Simple "word count" for HBase columns: Aggregates values from a configurable
 * HBase table and column TODO: add Filters, e.g. for language etc.
 * 
 */
public final class GenericDriver extends AbstractJob {

  private static final String NONE = "none";

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

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

  @Override
  public int run(String[] args) throws ClassNotFoundException, InterruptedException, IOException {
    addOutputOption();
    addOption(DefaultOptionCreator.numReducersOption().create());
    addOption("table", "t", "The hbase table holding our data.", "thtweets");
    addOption("family", "f", "The column family holding our data.", "d");
    addOption("column", "c", "The column holding our data.", "lang");
    addOption("separator", "s", "Separator used for splitting in column", NONE);
    addOption("query", "q", "The query, a simple string representing the topic.", "");
    addOption("daysBack", "d", "Number of Days - starting from last midnight - we want to scan", "1");

    Map argMap = parseArguments(args);
    if (argMap == null) {
      return -1;
    }
    String table = argMap.get("--table");
    String family = argMap.get("--family");
    String column = argMap.get("--column");
    String separator = argMap.get("--separator");
    String query = argMap.get("--query");
    String daysBack = argMap.get("--daysBack");

    Path output = getOutputPath();

    Configuration conf = HBaseConfiguration.create();

    if (separator != NONE) {
      conf.set("separator", argMap.get("--separator")); // for the reducer
    }

    Job job = new Job(conf);
    job.setJarByClass(GenericDriver.class);

    Scan scan = new Scan();
    scan.addColumn(Bytes.toBytes(family), Bytes.toBytes(column));

    if (query != null && !query.equals("")) {
      scan.setFilter(new ValueFilter(CompareFilter.CompareOp.EQUAL, new RegexStringComparator(query)));
    }
    
    if (daysBack != null && !daysBack.equals("")) {
      try {
        Calendar cal = this.getEndOfTimeRange();
        long maxStamp = cal.getTimeInMillis();
        int days = Integer.parseInt(daysBack);
        cal.add(Calendar.DAY_OF_MONTH, days * -1);
        long minStamp = cal.getTimeInMillis();
        scan.setTimeRange(minStamp, maxStamp);
      } catch (NumberFormatException e) {
        System.out.println("Error: "+e.getMessage());
      }
    }
    TableMapReduceUtil.initTableMapperJob(table, scan, GenericMapper.class, Text.class, IntWritable.class,
        job);

    job.setJobName("GenericCounter::" + column); 

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

    job.setReducerClass(GenericReducer.class);
    job.setOutputKeyClass(IntWritable.class);
    job.setOutputValueClass(Text.class);

    job.setOutputFormatClass(SequenceFileOutputFormat.class);
    FileOutputFormat.setOutputPath(job, output);
    job.setNumReduceTasks(1);
    job.waitForCompletion(true);
    return 0;
  }

  /**
   * Returns a calender set to the start of today (midnight)
   * 
   * @return calendar set to end of time range
   */
  private Calendar getEndOfTimeRange() {
    Date d = new Date();
    Calendar cal = Calendar.getInstance(Locale.GERMANY);
    cal.setTime(d);
    cal.set(Calendar.HOUR_OF_DAY, 0);
    cal.set(Calendar.MINUTE, 0);
    cal.set(Calendar.SECOND, 0);
    cal.set(Calendar.MILLISECOND, 0);
    return cal;
  }

}