hadoop hellokitty 单词统计

直接上代码

maven

 <dependencies>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-client</artifactId>
            <version>2.5.1</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-hdfs</artifactId>
            <version>2.5.1</version>
            <exclusions>
                <exclusion>
                    <groupId>com.sun.jersey</groupId>
                    <artifactId>jersey-server</artifactId>
                </exclusion>
            </exclusions>
        </dependency>
    </dependencies>

/**
 * @author lorabit
 * @since 15-12-25
 */
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapred.*;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;

import java.io.IOException;
import java.util.ArrayList;
import java.util.Iterator;
import java.util.List;
import java.util.StringTokenizer;

/**
 * @author lorabit
 * @since 15-12-25
 */
public class WordCount extends Configured implements Tool {

    /**
     * Counts the words in each line.
     * For each line of input, break the line into words and emit them as
     * (<b>word</b>, <b>1</b>).
     */
    public static class MapClass extends MapReduceBase implements Mapper<LongWritable, Text, Text, IntWritable> {

        private final static IntWritable one = new IntWritable(1);
        private Text word = new Text();

        public void map(LongWritable key, Text value,
                        OutputCollector<Text, IntWritable> output,
                        Reporter reporter) throws IOException {
            String line = value.toString();
            StringTokenizer itr = new StringTokenizer(line);
            while (itr.hasMoreTokens()) {
                word.set(itr.nextToken());
                output.collect(word, one);
            }
        }
    }

    /**
     * A reducer class that just emits the sum of the input values.
     */
    public static class Reduce extends MapReduceBase
            implements Reducer<Text, IntWritable, Text, IntWritable> {

        public void reduce(Text key, Iterator<IntWritable> values,
                           OutputCollector<Text, IntWritable> output,
                           Reporter reporter) throws IOException {
            int sum = 0;
            while (values.hasNext()) {
                sum += values.next().get();
            }
            output.collect(key, new IntWritable(sum));
        }

    }

    static int printUsage() {
        System.out.println("wordcount [-m <maps>] [-r <reduces>] <input> <output>");
        ToolRunner.printGenericCommandUsage(System.out);
        return -1;
    }

    /**
     * The main driver for word count map/reduce program.
     * Invoke this method to submit the map/reduce job.
     * @throws IOException When there is communication problems with the
     *                     job tracker.
     */
    public int run(String[] args) throws Exception {
        JobConf conf = new JobConf(getConf(), WordCount.class);
        conf.setJobName("wordcount");

        // the keys are words (strings)
        conf.setOutputKeyClass(Text.class);
        // the values are counts (ints)
        conf.setOutputValueClass(IntWritable.class);

        conf.setMapperClass(MapClass.class);
        conf.setCombinerClass(Reduce.class);
        conf.setReducerClass(Reduce.class);

        List<String> other_args = new ArrayList<String>();
        for(int i=0; i < args.length; ++i) {
            try {
                if ("-m".equals(args[i])) {
                    conf.setNumMapTasks(Integer.parseInt(args[++i]));
                } else if ("-r".equals(args[i])) {
                    conf.setNumReduceTasks(Integer.parseInt(args[++i]));
                } else {
                    other_args.add(args[i]);
                }
            } catch (NumberFormatException except) {
                System.out.println("ERROR: Integer expected instead of " + args[i]);
                return printUsage();
            } catch (ArrayIndexOutOfBoundsException except) {
                System.out.println("ERROR: Required parameter missing from " +
                        args[i-1]);
                return printUsage();
            }
        }
        // Make sure there are exactly 2 parameters left.
        if (other_args.size() != 2) {
            System.out.println("ERROR: Wrong number of parameters: " +
                    other_args.size() + " instead of 2.");
            return printUsage();
        }
        FileInputFormat.setInputPaths(conf, other_args.get(0));
//        FileInputFormat.setInputPaths(conf, new Path("/example/wordcount.txt"));
        FileOutputFormat.setOutputPath(conf, new Path(other_args.get(1)));
//        FileOutputFormat.setOutputPath(conf, new Path("/example/wordcountoutput.txt"));

        JobClient.runJob(conf);
        return 0;
    }


    public static void main(String[] args) throws Exception {
        args= new String[]{"/home/hellokitty/桌面/wordcount.txt","/home/hellokitty/桌面/output/"};
        int res = ToolRunner.run(new Configuration(), new WordCount(), args);
        System.exit(res);
    }

}