Tutorial_6 运行结果

1.buyer_favorites.txt

2.代码

package mapreduce;

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

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;
import org.apache.hadoop.util.GenericOptionsParser;

public class WordCount {
    public WordCount() {
    }

    public static void main(String[] args) throws Exception {
        Configuration conf = new Configuration();
//        String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
        String input = "hdfs://192.168.1.102:9000/user/hadoop/input/buyer_favorite1.txt";
        String output = "hdfs://192.168.1.102:9000/user/hadoop/output";
        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.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(), "\t");

            while (itr.hasMoreTokens()) {
                this.word.set(itr.nextToken().split("   ")[0]);
                context.write(this.word, one);
            }

        }
    }
}

 

3.运行结果

4.遇到的问题

解决办法：

分析：

    C:\Windows\System32下缺少hadoop.dll,把这个文件拷贝到C:\Windows\System32下面即可。

 解决：

    hadoop-common-2.2.0-bin-master下的bin的hadoop.dll放到C:\Windows\System32下，然后重启电脑，也许还没那么简单，还是出现这样的问题。（原博主是这么写的，实际上只是将hadoop.dll粘到了             C:\Windows\System32目录下就行了）

————————————————
声明：仅解决办法参考CSDN博客，文末附原文链接。
原文链接：https://blog.csdn.net/congcong68/article/details/42043093