wordcount项目在包solution 下由三个文件组成,一个是包含主类的WordCount.java,一个是mapper文件WordMapper.java,一个是reducer文件SumReducer.java。
WordCount.java文件源码如下:
package solution;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.Job;
public class WordCount {
public static void main(String[] args) throws Exception {
if (args.length != 2) {
System.out.printf(
"Usage: WordCount <input dir> <output dir>\n");
System.exit(-1);
}
Job job = new Job();
job.setJarByClass(WordCount.class);
job.setJobName("Word Count");
FileInputFormat.setInputPaths(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, new Path(args[1]));