用maven插件编写程序,下载相关依赖:
package my.hadoopstudy;
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;
import java.io.IOException;
public class Wordcount {
public static class MyMapper extends Mapper<Object, Text, Text, IntWritable>{
private final static IntWritable one = new IntWritable(1);
public void map(Object key, Text value, Context context) throws IOException, InterruptedException {
String[] e = value.toString().split(" ");
for(int i=0;i<e.length;i++){
context.write(new Text(e[i]), one);
}
}
}
public static class MyReducer 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[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
if (otherArgs.length < 2) {
System.err.println("Usage: EventCount <in> <out>");
System.exit(2);
}
Job job = Job.getInstance(conf, "word count");
job.setJarByClass(Wordcount.class);
job.setMapperClass(MyMapper.class);
job.setCombinerClass(MyReducer.class);
job.setReducerClass(MyReducer.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
FileInputFormat.addInputPath(job, new Path(otherArgs[0]));
FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));
System.exit(job.waitForCompletion(true) ? 0 : 1);
}
}
将程序用打包成jar文件
统计文件:
运行:
结果: