還拿經典字計數爲例:
org.apache.hadoop.mapred.JobConf
是舊的,在新版本中,我們使用Configuration
和Job
實現。
請使用org.apache.hadoop.mapreduce.lib.*
(這是新的API),而不是org.apache.hadoop.mapred.TextInputFormat
(這是舊的)。
Mapper
和Reducer
不是什麼新東西,請看main
的功能,它包含了比較全面的配置,可以根據自己的具體要求隨意更改。
import java.io.IOException;
import java.util.StringTokenizer;
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;
class TokenizerMapper extends Mapper<Object, Text, Text, IntWritable> {
private Text outputKey;
private IntWritable outputVal;
@Override
public void setup(Context context) {
outputKey = new Text();
outputVal = new IntWritable(1);
}
@Override
public void map(Object key, Text value, Context context) throws IOException, InterruptedException {
StringTokenizer stk = new StringTokenizer(value.toString());
while(stk.hasMoreTokens()) {
outputKey.set(stk.nextToken());
context.write(outputKey, outputVal);
}
}
}
class IntSumReducer extends Reducer<Text, IntWritable, Text, IntWritable> {
private IntWritable result;
@Override
public void setup(Context context) {
result = new IntWritable();
}
@Override
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 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);
}
}
的可能的複製[運行Hadoop的作業,而不使用JobConf](http://stackoverflow.com/questions/2115292/run-hadoop-job-without-using-jobconf) – chess007 2011-12-22 12:30:31
不,其similar.But我想要配置類的例子,它是jobconf類的替代。 – CodeBanger 2011-12-22 13:08:34