package org.apache.hadoop.example;
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 {
//输入键类型、输入值类型、输出键类型和输出值类型,在本例中分别为普通对象(Object)、字符串(Text)、字符串和整数型(IntWritable)
public static class TokenizerMapper extends Mapper<Object, Text, Text, IntWritable> {
private final static IntWritable one = new IntWritable(1);
private Text word = new Text();
//输入键key、输入值value和环境变量context。输入键默认为行号,输入值为每一行的文本字符串
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());//设置键的值
context.write(word, one);//函数context.write()输出键为单词值为1
}
}
}
//输入键类型、输入值类型、输出键类型和输出值类型,在本例中分别为字符串、整数型、字符串和整数型
public static class IntSumReducer extends Reducer<Text, IntWritable, Text, IntWritable> {
private IntWritable result = new IntWritable();
//输入键key、输入值列表values和环境变量context
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);//输出键为单词值为单词出现次数的键值对
}
}
public static void main(String[] args) throws Exception {
Configuration conf = new Configuration(); //初始化hadoop集群组件配置
String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();//解析命令行参数
if (otherArgs.length < 2) {
System.err.println("Usage: wordcount <in> [<in>...] <out>");
System.exit(2);
}
@SuppressWarnings("deprecation")
Job job = new Job(conf, "word count"); //Job命名为"word count"
job.setJarByClass(WordCount.class); //设置主类
job.setMapperClass(TokenizerMapper.class);//设置mapper类
job.setReducerClass(IntSumReducer.class);//设置reducer类
job.setOutputKeyClass(Text.class);//设置键输出类
job.setOutputValueClass(IntWritable.class);//设置值输出类
for (int i = 0; i < otherArgs.length - 1; ++i) {
FileInputFormat.addInputPath(job, new Path(otherArgs[i]));//设置作业输入路径
}
FileOutputFormat.setOutputPath(job, new Path(otherArgs[otherArgs.length - 1]));//设置作业输出路径
System.exit(job.waitForCompletion(true) ? 0 : 1);//调用函数System.exit()等待作业退出,并给出退出状态。
}
}
eclipse使用wordcount
最新推荐文章于 2023-04-17 22:10:31 发布