DumpRecordsExtended.java Source code

Introduction

Here is the source code for DumpRecordsExtended.java

Source

/*
 * Cloud9: A Hadoop toolkit for working with big data
 *
 * 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.
 */

import java.util.Arrays;

import org.apache.commons.cli.CommandLine;
import org.apache.commons.cli.CommandLineParser;
import org.apache.commons.cli.GnuParser;
import org.apache.commons.cli.HelpFormatter;
import org.apache.commons.cli.OptionBuilder;
import org.apache.commons.cli.Options;
import org.apache.commons.cli.ParseException;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.input.SequenceFileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;
import org.apache.log4j.Logger;

import edu.umd.cloud9.example.pagerank.PageRankNode;

public class DumpRecordsExtended extends Configured implements Tool {
    private static final Logger LOG = Logger.getLogger(DumpRecordsExtended.class);

    public DumpRecordsExtended() {
    }

    private static final String INPUT = "input";
    private static final String OUTPUT = "output";

    /**
     * Runs this tool.
     */
    @SuppressWarnings({ "static-access" })
    public int run(String[] args) throws Exception {
        Options options = new Options();

        options.addOption(OptionBuilder.withArgName("path").hasArg().withDescription("input path").create(INPUT));
        options.addOption(OptionBuilder.withArgName("path").hasArg().withDescription("output path").create(OUTPUT));

        CommandLine cmdline;
        CommandLineParser parser = new GnuParser();

        try {
            cmdline = parser.parse(options, args);
        } catch (ParseException exp) {
            System.err.println("Error parsing command line: " + exp.getMessage());
            return -1;
        }

        if (!cmdline.hasOption(INPUT) || !cmdline.hasOption(OUTPUT)) {
            System.out.println("args: " + Arrays.toString(args));
            HelpFormatter formatter = new HelpFormatter();
            formatter.setWidth(120);
            formatter.printHelp(this.getClass().getName(), options);
            ToolRunner.printGenericCommandUsage(System.out);
            return -1;
        }

        String inputPath = cmdline.getOptionValue(INPUT);
        String outputPath = cmdline.getOptionValue(OUTPUT);

        LOG.info("Tool name: " + DumpRecordsExtended.class.getSimpleName());
        LOG.info(" - input: " + inputPath);
        LOG.info(" - output: " + outputPath);

        Configuration conf = new Configuration();
        conf.setInt("mapred.min.split.size", 1024 * 1024 * 1024);

        Job job = Job.getInstance(conf);
        job.setJobName(DumpRecordsExtended.class.getSimpleName());
        job.setJarByClass(DumpRecordsExtended.class);

        job.setNumReduceTasks(0);

        FileInputFormat.addInputPath(job, new Path(inputPath));
        FileOutputFormat.setOutputPath(job, new Path(outputPath));

        job.setInputFormatClass(SequenceFileInputFormat.class);
        job.setOutputFormatClass(TextOutputFormat.class);

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

        // Delete the output directory if it exists already.
        FileSystem.get(conf).delete(new Path(outputPath), true);

        job.waitForCompletion(true);

        return 0;
    }

    /**
     * Dispatches command-line arguments to the tool via the {@code ToolRunner}.
     */
    public static void main(String[] args) throws Exception {
        ToolRunner.run(new DumpRecordsExtended(), args);
    }
}