eu.dicodeproject.analysis.export.TwitterExportDriver 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.export;

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.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.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Reducer;
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;

/**
 * Reads text from a configurable HBase table and column and writes row key and
 * column content to HDFS.
 */
public final class TwitterExportDriver extends AbstractJob {

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

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

  @Override
  public int run(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
    addOutputOption();
    addOption(DefaultOptionCreator.numReducersOption().create());
    addOption("table", "t", "The hbase table holding our data.", "twittertracker");
    addOption("family", "f", "The column family holding our data.", "textFamily");
    addOption("column", "c", "The column holding our data.", "text");
    addOption("query", "q", "The query, a simple string representing the topic.", "Dicode");

    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 query = argMap.get("--query");

    Path output = getOutputPath();

    Configuration conf = HBaseConfiguration.create();
    Job job = new Job(conf);
    job.setJarByClass(TwitterExportDriver.class);

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

    // TODO: check URL encoding
    scan.setFilter(new ValueFilter(CompareFilter.CompareOp.EQUAL, new RegexStringComparator(query)));
    // scan.setFilter(new ValueFilter(CompareFilter.CompareOp.EQUAL, new
    // RegexStringComparator("("+query+"[\\s\\.,;?!]+) | (" +query + "^)")));

    TableMapReduceUtil.initTableMapperJob(table, scan, TwitterExportMapper.class, Text.class, Text.class, job);

    job.setJobName("TwitterExport");
    job.setReducerClass(Reducer.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(Text.class);

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