案例说明:
orders是订单信息的文件,pdts是商品编码和商品名称。
获取订单对应商品的商品名称。
orders.txt
1001 pd001 300
1001 pd002 20
1002 pd003 40
1003 pd002 50
pdts.txt
pd001,apple
pd002,banana
pd003,orange
import java.io.BufferedReader;
import java.io.FileInputStream;
import java.io.FileReader;
import java.io.IOException;
import java.io.InputStreamReader;
import java.net.URI;
import java.net.URISyntaxException;
import java.util.Map;
import javax.imageio.stream.FileImageInputStream;
import org.apache.commons.collections.map.HashedMap;
import org.apache.commons.lang.StringUtils;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
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.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import commonFriends.SharedFriendsStepTwo;
public class MapSideJoin {
static class MapSideJoinMapper extends Mapper<LongWritable, Text, Text, NullWritable>{
//setup在maptask运行前调用一次,可进行初始化工作
Map<String,String> pd = new HashedMap();
Text k = new Text();
//用hashmap家在保存产品信息表
@Override
protected void setup(Context context)
throws IOException, InterruptedException {
Path[] cacheFiles = context.getLocalCacheFiles();
BufferedReader bfr = new BufferedReader(new InputStreamReader(new FileInputStream(cacheFiles[0].toUri().getPath())));
String line;
while(StringUtils.isNotEmpty(line=bfr.readLine())) {
String[] fields = line.split(",");
pd.put(fields[0], fields[1]);
}
bfr.close();
}
//
@Override
protected void map(LongWritable key, Text value, Context context)
throws IOException, InterruptedException {
String orderLine = value.toString();
String info[] = orderLine.split("\t");
//得到产品name
String pdName = pd.get(info[1]);
k.set(orderLine+"\t"+pdName);
context.write(k, NullWritable.get());
}
}
public static void main(String[] args) throws IllegalArgumentException, IOException, URISyntaxException, ClassNotFoundException, InterruptedException {
Configuration conf = new Configuration();
Job job = Job.getInstance(conf);
job.setJarByClass(MapSideJoin.class);
job.setMapperClass(MapSideJoinMapper.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(NullWritable.class);
//指定job 输出结果
FileInputFormat.setInputPaths(job, new Path("g:/testjoin"));
FileOutputFormat.setOutputPath(job, new Path("g:/testjoinout"));
job.addCacheFile(new URI("file:/g:/testjoinfile/pdts.txt"));
job.setNumReduceTasks(0);
boolean res = job.waitForCompletion(true);
System.exit(res?0:1);
}
}