com.neu.cs6240.Xml2csv.java Source code

Introduction

Here is the source code for com.neu.cs6240.Xml2csv.java

Source

/**
 *  Licensed under 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 com.neu.cs6240;

import java.io.IOException;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.NullWritable;
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.output.FileOutputFormat;
import org.apache.hadoop.util.GenericOptionsParser;
import org.apache.mahout.text.wikipedia.XmlInputFormat;

/**
 * This class provides functionality to transform stack-overflow data dump's xml
 * to csv format using Apache Hadoop
 * 
 * @author vishrut
 * 
 */
public class Xml2csv {

    // Mapper class that reads line as a individual row
    public static class PostsMapper extends Mapper<LongWritable, Text, NullWritable, Text> {

        public void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
            // We need to parse xml row and emit only required fields
            context.write(NullWritable.get(), new Text(value.toString()));
        }
    }

    public static void main(String[] args) throws Exception {
        Configuration conf = new Configuration();
        // Setting up the xml tag configurator for splitter
        conf.set("xmlinput.start", "<row ");
        conf.set("xmlinput.end", " />");

        String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
        if (otherArgs.length != 2) {
            System.err.println("Usage: Xml2csv <in> <out>");
            System.exit(2);
        }
        Job job = new Job(conf, "Converts Posts.xml to .csv");
        job.setJarByClass(Xml2csv.class);
        job.setInputFormatClass(XmlInputFormat.class);
        job.setMapperClass(PostsMapper.class);
        job.setOutputKeyClass(NullWritable.class);
        job.setOutputValueClass(IntWritable.class);
        job.setNumReduceTasks(0);
        FileInputFormat.addInputPath(job, new Path(otherArgs[0]));
        FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));
        System.exit(job.waitForCompletion(true) ? 0 : 1);
    }
}