9.Hadoop MapReduce例子(单词计数)-Java

1.编写java代码

（1）创建wordcount测试目录

          mkdir -p ~/wordcount/input

（2）切换至wordcount测试目录

           cd ~/wordcount

（3）复制java代码

         sudo gedit WordCount.java

       

        https://hadoop.apache.org/docs/r2.7.7/hadoop-mapreduce-client/hadoop-mapreduce-client-core/MapReduceTutorial.html

        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; public class WordCount { public static class TokenizerMapper extends Mapper<Object, Text, Text, IntWritable>{ 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); } } } public static class IntSumReducer extends Reducer<Text,IntWritable,Text,IntWritable> { private IntWritable result = new IntWritable(); public void reduce(Text key, Iterable<IntWritable> values, Context context ) throws IOException, InterruptedException { int sum = 0; for (IntWritable val : values) { sum += val.get(); } result.set(sum); context.write(key, result); } } public static void main(String[] args) throws Exception { Configuration conf = new Configuration(); Job job = Job.getInstance(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(args[0])); FileOutputFormat.setOutputPath(job, new Path(args[1])); System.exit(job.waitForCompletion(true) ? 0 : 1); } }        

2.编译java代码

（1）修改~/.bashrc

          sudo gedit ~/.bashrc

         export PATH=${JAVA_HOME}/bin:${PATH}

         export HADOOP_CLASSPATH=${JAVA_HOME}/lib/tools.jar

（2）~/.bashrc生效

        source ~/.bashrc

（3）编译

        hadoop com.sun.tools.javac.Main WordCount.java

（4）打包

        jar cf wc.jar WordCount*.class

3.编写测试文本

（1）以LICENSE.txt为例

        cp /usr/local/hadoop/LICENSE.txt ~/wordcount/input

        ll ~/wordcount/input

4.上传测试文件至HDFS

（1）在HDFS创建目录

          hadoop fs -mkdir -p /user/hduser/wordcount/input

（2）切换至~/wordcount/input目录

          cd ~/wordcount/input

（3）上传文件到HDFS

          hadoop fs -copyFromLocal LICENSE.txt /user/hduser/wordcount/input

（4）列出HDFS文件

          hadoop fs -ls  /user/hduser/wordcount/input

5.运行

（1）切换目录

          cd ~/wordcount

（2）运行程序

           hadoop jar wc.jar WordCount /user/hduser/wordcount/input/LICENSE.txt /user/hduser/wordcount/output

6.查看运行结果

（1）查看HDFS目录

          hadoop fs -ls /user/hduser/wordcount/output

（2）查看运行结果

          hadoop fs -cat /user/hduser/wordcount/output/part-r-00000|more

          或

          hadoop fs -get /user/hduser/wordcount/output/part-r-00000