public class WordCount
{
public static class TokenizerMapper extends Mapper
{
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
{
private IntWritable result = new IntWritable();
public void reduce(Text key, Iterable 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: wordcount ");
System.exit(2);
}
Job job = new Job(conf, "word count");
job.setJarByClass(WordCount.class);
job.setMapperClass(TokenizerMapper.class);
job.setCombinerClass(IntSumReducer.class);
job.setReducerClass(IntSumReducer.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);
}
}
InputFormat:读取输入文件,以自定义map的输入数据格式,传给map.(如下红色字体)
public static class TokenizerMapper extends Mapper
MapOutputKeyClass,MapOutputValueClass:定义了map的输出数据的格式,reduce的输入数据格式
public static class TokenizerMapper extends Mapper
public static class IntSumReducer extends Reducer
OutputKeyClass,OutputValueClass:定义了reduce的输出数据格式,OutputFormat的输入格式
public static class IntSumReducer extends Reducer