Попробуйте использовать Configuration
и Job
. Вот пример:
(Замените ваши Mapper
, Combiner
, Reducer
классы и другие конфигурации)
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.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
public class WordCount {
public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
Configuration conf = new Configuration();
if(args.length != 2) {
System.err.println("Usage: <in> <out>");
System.exit(2);
}
Job job = Job.getInstance(conf, "Word Count");
// set jar
job.setJarByClass(WordCount.class);
// set Mapper, Combiner, Reducer
job.setMapperClass(TokenizerMapper.class);
job.setCombinerClass(IntSumReducer.class);
job.setReducerClass(IntSumReducer.class);
/* Optional, set customer defined Partioner:
* job.setPartitionerClass(MyPartioner.class);
*/
// set output key
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(IntWritable.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
// set input and output path
FileInputFormat.addInputPath(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, new Path(args[1]));
// by default, Hadoop use TextInputFormat and TextOutputFormat
// any customer defined input and output class must implement InputFormat/OutputFormat interface
job.setInputFormatClass(TextInputFormat.class);
job.setOutputFormatClass(TextOutputFormat.class);
System.exit(job.waitForCompletion(true) ? 0 : 1);
}
}