奔跑的大象，Hadoop之WordCount源代码

Hadoop.jpg

本文有新版和旧版两个版本的源代码。

hadoop_logo.png

WordCount旧版源代码

    //package org.apache.hadoop.examples;
    import java.io.IOException;
    import java.util.Iterator;
    import java.util.StringTokenizer;
    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.FileInputFormat;
    import org.apache.hadoop.mapred.FileOutputFormat;
    import org.apache.hadoop.mapred.JobClient;
    import org.apache.hadoop.mapred.JobConf;
    import org.apache.hadoop.mapred.MapReduceBase;
    import org.apache.hadoop.mapred.Mapper;
    import org.apache.hadoop.mapred.OutputCollector;
    import org.apache.hadoop.mapred.Reducer;
    import org.apache.hadoop.mapred.Reporter;
    import org.apache.hadoop.mapred.TextInputFormat;
    import org.apache.hadoop.mapred.TextOutputFormat;
    
    public class WordCount {
        public static class Map extends MapReduceBase implements Mapper {
            private final static IntWritable one = new IntWritable(1);
            private Text word = new Text();
            public void map(LongWritable key, Text value, OutputCollector output, Reporter reporter)throws IOException {
                String line = value.toString();
                StringTokenizer tokenizer = new StringTokenizer(line);
                while (tokenizer.hasMoreTokens()) {
                    word.set(tokenizer.nextToken());
                    output.collect(word, one);
                } //while
            } //map()
        } //static class Map
    
        public static class Reduce extends MapReduceBase implements Reducer {
            public void reduce(Text key, Iterator values, OutputCollector output, Reporter reporter)throws IOException {
                int sum = 0;
                while (values.hasNext()) {
                    sum += values.next().get();
                }
                output.collect(key, new IntWritable(sum));
            } //reduce()
        } //static class Reduce
        public static void main(String[] args) throws Exception {
            JobConf conf = new JobConf(WordCount.class);
            conf.setJobName("wordcount");
            conf.setOutputKeyClass(Text.class);
            conf.setOutputValueClass(IntWritable.class);
            conf.setMapperClass(Map.class);
            conf.setCombinerClass(Reduce.class);
            conf.setReducerClass(Reduce.class);
            conf.setInputFormat(TextInputFormat.class);
            conf.setOutputFormat(TextOutputFormat.class);
            FileInputFormat.setInputPaths(conf, new Path(args[0]));

---

Hadoop3.jpg

WordCount新版源代码

    //package org.apache.hadoop.examples;
    import java.io.IOException;
    import java.util.StringTokenizer;
    import org.apache.hadoop.conf.Configuration;
    import org.apache.hadoop.fs.Path;
    import org.apache.hadoop.io.IntWritable;
    import org.apache.hadoop.io.Text;
    import org.apache.hadoop.mapreduce.Job;
    import org.apache.hadoop.mapreduce.Mapper;
    import org.apache.hadoop.mapreduce.Reducer;
    import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
    import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
    import org.apache.hadoop.util.GenericOptionsParser;
    public class WordCount {
        public static class TokenizerMapper
                extends Mapper{
                private final static IntWritable one = new IntWritable(1);
                private Text word = new Text();
                public void map(Object key, Text value, Context context)throws IOException, InterruptedException {
                    StringTokenizer itr = new StringTokenizer(value.toString());
                    while (itr.hasMoreTokens()) {
                        word.set(itr.nextToken());
                        context.write(word, one);
                    } //while
                } //map()
        } //static class TokenizerMapper
        public static class IntSumReducer extends Reducer {
            private IntWritable result = new IntWritable();
            public void reduce(Text key, Iterable values,Context context)throws IOException, InterruptedException {
                int sum = 0;
                for (IntWritable val : values) {
                    sum += val.get();
                }
                result.set(sum);
                context.write(key, result);
            } //reduce
        } //static class IntSumReducer
        public static void main(String[] args) throws Exception {
        Configuration conf = new Configuration();
        String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
        if (otherArgs.length != 2) {
            System.err.println("Usage: wordcount  ");
            System.exit(2);
        }
        Job job = new Job(conf, "word count");
        job.setJarByClass(WordCount.class);
        job.setMapperClass(TokenizerMapper.class);
        job.setCombinerClass(IntSumReducer.class);
        job.setReducerClass(IntSumReducer.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);
        FileInputFormat.addInputPath(job, new Path(otherArgs[0]));
        FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));
        System.exit(job.waitForCompletion(true) ? 0 : 1);
    } //main()
    } //class WordCount

Hadoop3.jpg

参考：Apache Hadoop