eu.dicodeproject.analysis.wordcount.WordCountDriver 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.wordcount;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.hbase.HBaseConfiguration;
import org.apache.hadoop.hbase.client.Scan;
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.util.ToolRunner;
import org.apache.mahout.common.AbstractJob;

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

/**
 * 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 WordCountDriver extends AbstractJob {

  private String targetWordsConfKey = "targetWords";

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

  @Override
  public int run(String[] args) throws ClassNotFoundException, InterruptedException, IOException {
    addOption("inputTable",   "i",  "The hbase table holding our data.",                            "thtweets");
    addOption("family",       "f",  "The column family holding our data.",                          "d");
    addOption("textColumn",   "c",  "The column qualifier holding our text.",                       "text");
    addOption("timeColumn",   "d",  "The column qualifier holding our creationDate.",               "creationDate");
    addOption("outputTable",  "t",  "The resulting hbase table in which the histogram is written.", "thtweets-wordCounts");
    addOption("targetWords",  "w",  "The comma-separated targetWords that should be searched for.", "Berlin,Paris,Athens");

    Map argMap = parseArguments(args);
    if (argMap == null) {
      return -1;
    }

    String inputTable = argMap.get("--inputTable");
    String dataFamily = argMap.get("--family");
    String textColumn = argMap.get("--textColumn");
    String timeColumn = argMap.get("--timeColumn");
    String outputTable = argMap.get("--outputTable");
    String targetWords = argMap.get("--targetWords");

    checkWords(targetWords); //TODO implement searching for phrases

    boolean success = generateWordHistogramData(inputTable, dataFamily, textColumn, targetWords, timeColumn, outputTable);

    return (success ? 0 : 1);
  }

  private boolean generateWordHistogramData(String inputTable, String dataFamily, String textColumn,
                                            String targetWords, String timeColumn, String outputTable)
      throws IOException, InterruptedException, ClassNotFoundException {

    Configuration conf = HBaseConfiguration.create();
    conf.set(targetWordsConfKey, targetWords.replace(",", " "));  // comma -> whitespace to ensure that analyzer yields separate tokens
    Job job = new Job(conf, "WordCountDriver::GenerateWordCountData");
    job.setJarByClass(WordCountDriver.class);

    Scan scan = new Scan();
    scan.addColumn(Bytes.toBytes(dataFamily), Bytes.toBytes(textColumn));
    scan.addColumn(Bytes.toBytes(dataFamily), Bytes.toBytes(timeColumn));
    scan.setMaxVersions(1);

    TableMapReduceUtil.initTableMapperJob(inputTable, scan, WordCountMapper.class, Text.class, IntWritable.class, job);
    TableMapReduceUtil.initTableReducerJob(outputTable, WordCountReducer.class, job);

    job.setNumReduceTasks(10);

    return job.waitForCompletion(true);
  }

  private void checkWords(String words) {
    for (String word : words.split(",")) {
      if (word.trim().contains(" ")) {
        throw new IllegalArgumentException("only single words allowed as target; got "+word);
      }
    }
  }

}