eu.dicodeproject.analysis.hbase.HBaseDocumentProcessor 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.hbase;

import java.io.IOException;
import java.io.StringReader;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.hbase.HBaseConfiguration;
import org.apache.hadoop.hbase.KeyValue;
import org.apache.hadoop.hbase.client.Result;
import org.apache.hadoop.hbase.client.Scan;
import org.apache.hadoop.hbase.io.ImmutableBytesWritable;
import org.apache.hadoop.hbase.mapreduce.TableMapReduceUtil;
import org.apache.hadoop.hbase.mapreduce.TableMapper;
import org.apache.hadoop.hbase.util.Bytes;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.SequenceFileOutputFormat;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.tokenattributes.TermAttribute;
import org.apache.mahout.common.StringTuple;
import org.apache.mahout.vectorizer.DefaultAnalyzer;
import org.apache.mahout.vectorizer.DocumentProcessor;

public final class HBaseDocumentProcessor {
  public static final String ANALYZER_CLASS = "analyzer.class";

  private HBaseDocumentProcessor() {

  }

  private static class HBaseDocumentProcessorMapper extends TableMapper {
    private Analyzer analyzer;

    @Override
    public void setup(Context context) throws IOException, InterruptedException {
      super.setup(context);
      try {
        ClassLoader ccl = Thread.currentThread().getContextClassLoader();
        Class cl = ccl.loadClass(context.getConfiguration().get(DocumentProcessor.ANALYZER_CLASS,
            DefaultAnalyzer.class.getName()));
        analyzer = (Analyzer) cl.newInstance();
      } catch (ClassNotFoundException e) {
        throw new IllegalStateException(e);
      } catch (InstantiationException e) {
        throw new IllegalStateException(e);
      } catch (IllegalAccessException e) {
        throw new IllegalStateException(e);
      }
    }

    @Override
    public void map(ImmutableBytesWritable row, Result values, Mapper.Context context) throws IOException,
        InterruptedException {
      for (KeyValue keyValue : values.list()) {
        String key = new String(keyValue.getKey());
        String value = new String(keyValue.getValue());
        TokenStream stream = analyzer.tokenStream(key, new StringReader(value));
        TermAttribute termAtt = stream.addAttribute(TermAttribute.class);
        StringTuple document = new StringTuple();
        while (stream.incrementToken()) {
          if (termAtt.termLength() > 0) {
            document.add(new String(termAtt.termBuffer(), 0, termAtt.termLength()));
          }
        }
        context.write(new Text(key), document);
      }
    }
  }

  public static void tokenizeDocuments(String table, String family, String column,
      Class analyzerClass, Path output) throws IOException, InterruptedException,
      ClassNotFoundException {
    Configuration conf = HBaseConfiguration.create();
    conf.set(ANALYZER_CLASS, analyzerClass.getName());

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

    Scan scan = new Scan();
    scan.addColumn(Bytes.toBytes(family), Bytes.toBytes(column));
    TableMapReduceUtil.initTableMapperJob(table, scan, HBaseDocumentProcessorMapper.class, Text.class,
        StringTuple.class, job);

    job.setJobName("HBaseDocumentProcessor::DocumentTokenizer");
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(StringTuple.class);

    FileOutputFormat.setOutputPath(job, output);
    job.setOutputFormatClass(SequenceFileOutputFormat.class);

    job.setNumReduceTasks(0);

    job.waitForCompletion(true);
  }
}