[置顶] 第四个MapReduce程序----两表join

需求:两个表,一个有id和name,一个有id和phoneNum,得到name和与之对应的phoneNum

package club.drguo.mapreduce.joinquery;

import java.io.IOException;
import java.util.ArrayList;

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.Text;
import org.apache.hadoop.mapred.FileSplit;
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.output.FileOutputFormat;

public class JoinQuery {
	public static class JoinQueryMapper extends Mapper<LongWritable, Text, Text, Text> {
		@Override
		protected void map(LongWritable key, Text value, Mapper<LongWritable, Text, Text, Text>.Context context)
				throws IOException, InterruptedException {
			String line = value.toString();
			String[] strings = StringUtils.split(line, " ");
			String id = strings[0];
			String phoneNum = strings[1];
			FileSplit fileSplit = (FileSplit) context.getInputSplit();
			String filename = fileSplit.getPath().getName();
			context.write(new Text(id), new Text(phoneNum + "---" + filename));// K:001
																				// V:123---a.txt
		}
	}

	public static class JoinQueryReducer extends Reducer<Text, Text, Text, Text> {
		// K:001 V:{123---a.txt,124---b.txt}
		@Override
		protected void reduce(Text key, Iterable<Text> values, Reducer<Text, Text, Text, Text>.Context context)
				throws IOException, InterruptedException {
			// 第一次循环拿出a表中的那个字段
			String leftKey = "";
			ArrayList<String> rightFields = new ArrayList<>();
			for (Text value : values) {
				if (value.toString().contains("a.txt")) {
					leftKey = StringUtils.split(value.toString(), "---")[0];
				} else {
					rightFields.add(value.toString());
				}

			}

			// 再用leftkey去遍历拼接b表中的字段,并输出结果
			for (String field : rightFields) {
				String result = "";
				result += leftKey + "\t" + StringUtils.split(field.toString(), "---")[0];
				context.write(new Text(leftKey), new Text(result));
			}
		}

	}

	public static void main(String[] args) throws Exception {

		Configuration conf = new Configuration();

		Job joinjob = Job.getInstance(conf);

		joinjob.setJarByClass(JoinQuery.class);

		joinjob.setMapperClass(JoinQueryMapper.class);
		joinjob.setReducerClass(JoinQueryReducer.class);

		joinjob.setOutputKeyClass(Text.class);
		joinjob.setOutputValueClass(Text.class);

		FileInputFormat.setInputPaths(joinjob, new Path(args[0]));
		FileOutputFormat.setOutputPath(joinjob, new Path(args[1]));

		joinjob.waitForCompletion(true);

	}
}


你可能感兴趣的:([置顶] 第四个MapReduce程序----两表join)