gistfile1.java

package net.barik.spreadsheet;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.NLineInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;

public class WARCExtractJob extends Configured implements Tool {
    @Override
    public int run(String[] args) throws Exception {

        if (args.length != 2) {
            System.err.printf("Usage: %s [generic options] <input> <output>\n",
                    getClass().getSimpleName());
            ToolRunner.printGenericCommandUsage(System.err);

            return -1;
        }

        Configuration conf = getConf();
        conf.set("mapreduce.input.lineinputformat.linespermap", "400");

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

        job.setInputFormatClass(NLineInputFormat.class);
        job.setMapperClass(WARCExportMapper.class);

        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(Text.class);

        NLineInputFormat.setInputPaths(job, new Path(args[0]));
        FileOutputFormat.setOutputPath(job, new Path(args[1]));

        return job.waitForCompletion(true) ? 0 : 1;
    }

    public static void main(String[] args) throws Exception {
        int exitCode = ToolRunner.run(new WARCExtractJob(), args);
        System.exit(exitCode);
    }
}