WordCount.java

系统管理员 2023-07-08 14:29 6阅读 0赞

import java.io.IOException;
    import java.util.Iterator;
    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;
    
    
    public class WordCount {
        public WordCount() {
        }
     
        public static void main(String[] otherArgs) throws Exception {
            Configuration conf = new Configuration();
            conf.set("mapreduce.app-submission.cross-platform", "true"); 
            //String[] otherArgs=new String[]{"input","output"}; // 直接设置输入参数 
            if(otherArgs.length < 2) {
                System.err.println("Usage: wordcount <in> [<in>...] <out>");
                System.err.println("java -jar WordCount.jar input output");
                System.exit(2);
            }
    
    
            
            Job job = Job.getInstance(conf, "word count");
            job.setJarByClass(WordCount.class);
            job.setMapperClass(WordCount.TokenizerMapper.class);
            job.setCombinerClass(WordCount.IntSumReducer.class);
            job.setReducerClass(WordCount.IntSumReducer.class);
            job.setOutputKeyClass(Text.class);
            job.setOutputValueClass(IntWritable.class);
     
            for(int i = 0; i < otherArgs.length - 1; ++i) {
                FileInputFormat.addInputPath(job, new Path(otherArgs[i]));
            }
     
            FileOutputFormat.setOutputPath(job, new Path(otherArgs[otherArgs.length - 1]));
            System.exit(job.waitForCompletion(true)?0:1);
        }
     
        public static class IntSumReducer extends Reducer<Text, IntWritable, Text, IntWritable> {
            private IntWritable result = new IntWritable();
     
            public IntSumReducer() {
            }
     
            public void reduce(Text key, Iterable<IntWritable> values, Reducer<Text, IntWritable, Text, IntWritable>.Context context) throws IOException, InterruptedException {
                int sum = 0;
     
                IntWritable val;
                for(Iterator i$ = values.iterator(); i$.hasNext(); sum += val.get()) {
                    val = (IntWritable)i$.next();
                }
     
                this.result.set(sum);
                context.write(key, this.result);
            }
        }
     
        public static class TokenizerMapper extends Mapper<Object, Text, Text, IntWritable> {
            private static final IntWritable one = new IntWritable(1);
            private Text word = new Text();
     
            public TokenizerMapper() {
            }
     
            public void map(Object key, Text value, Mapper<Object, Text, Text, IntWritable>.Context context) throws IOException, InterruptedException {
                StringTokenizer itr = new StringTokenizer(value.toString());
     
                while(itr.hasMoreTokens()) {
                    this.word.set(itr.nextToken());
                    context.write(this.word, one);
                }
     
            }
        }
    }

WordCount.java

发表评论取消回复

还没有评论，来说两句吧...

相关阅读