代码如下:
import java.io.IOException;
import java.util.StringTokenizer;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
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.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;
public class WordCountNew extends Configured implements Tool{
public static class WordCountReduceMapper extends Mapper<LongWritable, Text, Text, IntWritable> {
private final static IntWritable one = new IntWritable(1);
private Text word = new Text();
@Override
protected void map(LongWritable key, Text value, Context context)throws IOException, InterruptedException {
// 读取一行数据
String line = value.toString();
// 用空格分割成单词
StringTokenizer st = new StringTokenizer(line);
// 将单词与数量输出
while (st.hasMoreTokens()) {
word.set(st.nextToken());
context.write(word, one);
}
}
}
public static class WordCountReduce extends Reducer<Text, IntWritable, Text, IntWritable> {
private IntWritable result = new IntWritable();
/**
* 相同key的数据会一起传送给reduce,因此reduce阶段中的key值是相同,values 可以是多个,其值都是1
*/
@Override
protected void reduce(Text key, Iterable<IntWritable> values,Context context) throws IOException, InterruptedException {
int sum = 0;
// 通过循环,得出values的和
for (IntWritable value : values) {
sum += value.get();
}
result.set(sum);
context.write(key, result);
}
}
@Override
public int run(String[] args) throws Exception {
Job job = new Job(getConf());
job.setJarByClass(WordCountNew.class);
job.setJobName("mywordcount");
job.setInputFormatClass(TextInputFormat.class);
job.setOutputFormatClass(TextOutputFormat.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
job.setMapperClass(WordCountReduceMapper.class);
job.setReducerClass(WordCountReduce.class);
job.setCombinerClass(WordCountReduce.class);
FileInputFormat.setInputPaths(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, new Path(args[1]));
boolean success = job.waitForCompletion(true);
return success ? 0:1;
}
public static void main(String[] args) throws Exception {
int result = ToolRunner.run(new WordCountNew(), args);
System.exit(result);
}
}