WordCount

2019独角兽企业重金招聘Python工程师标准>>>

WordCount

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<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();
String HADOOP_HOME = System.getenv("HADOOP_HOME");
String HADOOP_CONF_DIR = HADOOP_HOME + "/etc/hadoop";
conf.addResource(new Path(HADOOP_CONF_DIR + "/core-site.xml" ));
conf.addResource(new Path(HADOOP_CONF_DIR + "/hdfs-site.xml" ));
conf.addResource(new Path(HADOOP_CONF_DIR + "/yarn-site.xml" ));
conf.set("mapreduce.job.ubertask.enable", "true");
String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
if (otherArgs.length < 2) {
  System.err.println("Usage: wordcount <in> [<in>...] <out>");
  System.exit(2);
}
//调用Job.getInstance静态方法，获得job构造方法的实例，定义jobName为'word count'。
Job job = Job.getInstance(conf, "word count");
//Set the Jar by finding where a given class came from.
//通过寻找一个给定类来设置Jar。
//如果不设置，在执行hadoop jar时会出现Caused by: java.lang.ClassNotFoundException: Class WordCount$TokenizerMapper not found
job.setJarByClass(WordCount.class);
//设置Job运行的Map、Combiner以及Reduce的处理类。
job.setMapperClass(TokenizerMapper.class);
job.setCombinerClass(IntSumReducer.class);
job.setReducerClass(IntSumReducer.class);
//设置Job输出结果<key,value>的中key数据类型和value数据类型，key表示单词，设置为Text类型，相当于Java中String类型。Value表示数目，设置为IntWritable类型，相当于Java中int类型。
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
//设置输入路径
for (int i = 0; i < otherArgs.length - 1; ++i) {
  FileInputFormat.addInputPath(job, new Path(otherArgs[i]));
}
//设置输出目录
FileOutputFormat.setOutputPath(job,
  new Path(otherArgs[otherArgs.length - 1]));
//调用job.waitForCompletion方法运行任务
System.exit(job.waitForCompletion(true) ? 0 : 1);
  }
}

转载于:https://my.oschina.net/yulongblog/blog/739359