hadoopwordcount新API例子

内容导读

互联网集市收集整理的这篇技术教程文章主要介绍了hadoopwordcount新API例子，小编现在分享给大家，供广大互联网技能从业者学习和参考。文章包含3829字，纯文字阅读大概需要6分钟。

内容图文

准备 准备一些输入文件，可以用hdfs dfs -put xxx/*?/user/fatkun/input上传文件 代码 package com.fatkun;?import java.io.IOException;import java.util.ArrayList;import java.util.List;import java.util.StringTokenizer;?import org.apache.commons.lo

准备

准备一些输入文件，可以用hdfs dfs -put xxx/*?/user/fatkun/input上传文件

代码

package com.fatkun;
?
import java.io.IOException;
import java.util.ArrayList;
import java.util.List;
import java.util.StringTokenizer;
?
import org.apache.commons.logging.Log;
import org.apache.commons.logging.LogFactory;
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.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.Tool;
import org.apache.hadoop.util.ToolRunner;
?
public class WordCount extends Configured implements Tool {
    static enum Counters {
        INPUT_WORDS // 计数器
    } 
?
    static Log logger = LogFactory.getLog(WordCount.class);
?
    public static class CountMapper extends
            Mapper {
        private final IntWritable one = new IntWritable(1);
        private Text word = new Text();
        private boolean caseSensitive = true;
?
        @Override
        protected void setup(Context context) throws IOException,
                InterruptedException {
            // 读取配置
            Configuration conf = context.getConfiguration();
            caseSensitive = conf.getBoolean("wordcount.case.sensitive", true);
            super.setup(context);
        }
?
        @Override
        protected void map(LongWritable key, Text value, Context context)
                throws IOException, InterruptedException {
            StringTokenizer itr = new StringTokenizer(value.toString());
            while (itr.hasMoreTokens()) {
                if (caseSensitive) { // 是否大小写敏感
                    word.set(itr.nextToken());
                } else {
                    word.set(itr.nextToken().toLowerCase());
                }
                context.write(word, one);
                context.getCounter(Counters.INPUT_WORDS).increment(1);
            }
        }
    }
?
    public static class CountReducer extends
            Reducer {
?
        @Override
        protected void reduce(Text text, Iterable values,
                Context context) throws IOException, InterruptedException {
            int sum = 0;
            for (IntWritable value : values) {
                sum += value.get();
            }
            context.write(text, new IntWritable(sum));
        }
?
    }
?
    @Override
    public int run(String[] args) throws Exception {
        Configuration conf = new Configuration(getConf());
        Job job = Job.getInstance(conf, "Example Hadoop WordCount");
        job.setJarByClass(WordCount.class);
        job.setMapperClass(CountMapper.class);
        job.setCombinerClass(CountReducer.class);
        job.setReducerClass(CountReducer.class);
?
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);
?
        List other_args = new ArrayList();
        for (int i = 0; i < args.length; ++i) {
            other_args.add(args[i]);
        }
?
        FileInputFormat.addInputPath(job, new Path(other_args.get(0)));
        FileOutputFormat.setOutputPath(job, new Path(other_args.get(1)));
        int ret = job.waitForCompletion(true) ? 0 : 1;
?
        long inputWord = job.getCounters().findCounter(Counters.INPUT_WORDS)
                .getValue();
        System.out.println("INPUT_WORDS:" + inputWord);
        logger.info("test log: " + inputWord);
        return ret;
    }
?
    public static void main(String[] args) throws Exception {
        int res = ToolRunner.run(new Configuration(), new WordCount(), args);
?
        System.exit(res);
    }
?
}

运行

在eclipse导出jar包，执行以下命令

hadoop jar wordcount.jar com.fatkun.WordCount -Dwordcount.case.sensitive=false /user/fatkun/input /user/fatkun/output

参考

http://cxwangyi.blogspot.com/2009/12/wordcount-tutorial-for-hadoop-0201.html

http://hadoop.apache.org/docs/r1.2.1/mapred_tutorial.html#Example%3A+WordCount+v2.0

原文地址：hadoop wordcount新API例子, 感谢原作者分享。

内容总结

以上是互联网集市为您收集整理的hadoopwordcount新API例子全部内容，希望文章能够帮你解决hadoopwordcount新API例子所遇到的程序开发问题。 如果觉得互联网集市技术教程内容还不错，欢迎将互联网集市网站推荐给程序员好友。

内容备注

版权声明：本文内容由互联网用户自发贡献，该文观点与技术仅代表作者本人。本站仅提供信息存储空间服务，不拥有所有权，不承担相关法律责任。如发现本站有涉嫌侵权/违法违规的内容， 请发送邮件至 gblab@vip.qq.com 举报，一经查实，本站将立刻删除。

内容手机端

---