數據算法-hadoop4 左鏈接

左鏈接很簡單的，主要是把左表的id和右表關聯id分別放入map的key中，value分別放入兩邊要關聯出來的其他值，在reduce時拼接起來。
書上PairOfStrings類，我找了半天，竟然找到了edu.umd.cloud9的jar包，也不知道這個jar包是幹嘛的。這個類就是兩個成員變量，一個left一個right，左邊是標識左邊還是右邊，右邊是值。

    public static void main(String[] args) throws Exception {
        Configuration conf1 = new Configuration();
        System.setProperty("hadoop.home.dir", "D:\\hadoop-2.5.2");

        conf1.setBoolean("dfs.permissions", false);

        Job job = Job.getInstance(conf1, "LeftJoin");

        job.setReducerClass(LeftJoinReducer.class);
        job.setOutputKeyClass(NullWritable.class);
        job.setOutputValueClass(Text.class);

        job.setNumReduceTasks(1);

        MultipleInputs.addInputPath(job, new Path("C:\\demo\\04\\transactions.txt"),
                TextInputFormat.class, LeftJoinTransactionMapper.class);
        MultipleInputs.addInputPath(job, new Path("C:\\demo\\04\\users.txt"),
                TextInputFormat.class, LeftJoinUserMapper.class);

        job.setMapOutputKeyClass(PairOfStrings.class);
        job.setMapOutputValueClass(PairOfStrings.class);
        FileOutputFormat.setOutputPath(job, new Path("C:\\demo\\04\\out"));
        if (job.waitForCompletion(true)) {
            log.info("MR run successfully");

        } else {
            log.error("MR run failed");

        }

    }

public class LeftJoinUserMapper extends
        Mapper<Object, Text, PairOfStrings, PairOfStrings> {

    PairOfStrings outputKey = new PairOfStrings();
    PairOfStrings outputValue = new PairOfStrings();

    public void map(Object key, Text value, Context context)
            throws IOException, InterruptedException {
        String[] tokens = value.toString().split("\t");
        String userID = tokens[0];
        String locationID = tokens[1];
        outputKey.set(userID, "1");
        outputValue.set("L", locationID);
        context.write(outputKey, outputValue);
    }

public class LeftJoinTransactionMapper extends
        Mapper<Object, Text, PairOfStrings, PairOfStrings> {

    PairOfStrings outputKey = new PairOfStrings();
    PairOfStrings outputValue = new PairOfStrings();

    public void map(Object key, Text value, Context context)
            throws IOException, InterruptedException {
        String[] tokens = value.toString().split("\t");
        String productID = tokens[1];
        String userID = tokens[2];
        outputKey.set(userID, "2");
        outputValue.set("P", productID);
        context.write(outputKey, outputValue);
    }

}

public class LeftJoinReducer extends
        Reducer<PairOfStrings, PairOfStrings, Text, Text> {

    Text productID = new Text();
    Text locationID = new Text("undefined");

    @Override
    public void reduce(PairOfStrings key, Iterable<PairOfStrings> values,
            Context context) throws java.io.IOException, InterruptedException {

        for (PairOfStrings pos : values) {
            PairOfStrings p = new PairOfStrings(pos.getLeftElement(), pos.getRightElement());
            if (pos.getLeftElement().equals("L")) {
                locationID.set(p.getRightElement());
                continue;
            }
            productID.set(p.getRightElement());
            context.write(productID, locationID);
        }
    }

}

輸入
user
u1 UT
u2 GA
u3 CA
u4 CA
u5 GA
transations

t1  p3  u1
t2  p1  u2
t3  p1  u1
t4  p2  u2
t5  p4  u4
t6  p1  u1
t7  p4  u1
t8  p4  u5

結果

u1  UT
u2  GA
u3  CA
u4  CA
u5  GA