hadoop mapreduce 例子

package test;


import java.io.IOException;
import java.text.ParseException;
import java.text.SimpleDateFormat;
import java.util.Date;




import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.io.NullWritable;
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.mrunit.mapreduce.MapReduceDriver;
import org.bson.BSONObject;
import org.bson.BasicBSONObject;
import org.bson.types.BasicBSONList;
import org.codehaus.jettison.json.JSONException;


import com.mongodb.DBObject;
import com.mongodb.hadoop.MongoInputFormat;
import com.mongodb.hadoop.MongoOutputFormat;
import com.mongodb.hadoop.io.BSONWritable;
import com.mongodb.util.JSON;


public class TestCount {


public static class AppMap extends Mapper<Object, BSONObject, Text, Text> {
public void map(Object key, BSONObject dbObjectFromDB, Context context) {
try {

context.write(new Text(“111111”), new Text("22222222222"));

} catch (Exception e) {
e.printStackTrace();
}
}
}


/* reduce处理map传送的数据，进行计算 */
public static class Reduce extends Reducer<Text, Text, NullWritable, BSONWritable> {
public void reduce(Text key, Iterable<Text> values, Context context) {
try {


BSONWritable bson = new BSONWritable();

context.write(NullWritable.get(), bson);
} catch (Exception e) {
e.printStackTrace();
}
}
}


// 运行作业
public static void main(String[] args) throws Exception {


Configuration conf = new Configuration();
conf.set("mongo.input.uri", "mongodb://u2:27017/test.test_table1");
conf.set("mongo.output.uri", "mongodb://u2:27017/test.test_table2");



Job job = Job.getInstance(conf, "TestCount ");
job.setJarByClass(AppCount.class);
job.setMapperClass(AppMap.class);
job.setReducerClass(Reduce.class);
job.setInputFormatClass(MongoInputFormat.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(Text.class);
job.setOutputKeyClass(NullWritable.class);
job.setOutputValueClass(BSONWritable.class);
job.setOutputFormatClass(MongoOutputFormat.class);


System.exit(job.waitForCompletion(true) ? 0 : 1);
}



}