:Unique サンプル

1. テストプログラムの JAR パッケージを準備します。 パッケージの名前を "mapreduce-examples.jar" 、ローカルストレージパスを "data\resources" とします。
2. Unique 操作をテストするためのテーブルとリソースを準備します。
   • テーブルを作成します。

     create table ss_in(key bigint, value bigint);
     create table ss_out(key bigint, value bigint);

   • リソースを追加します。

     add jar data\resources\mapreduce-examples.jar -f;

3. tunnel コマンドを使用してデータをインポートします。

   tunnel upload data ss_in;

   データファイルの内容がテーブル " ss_in " にインポートされます。

    1,1
    1,1
    2,2
    2,2

jar -resources mapreduce-examples.jar -classpath data\resources\mapreduce-examples.jar
com.aliyun.odps.mapred.open.example.Unique ss_in ss_out key;

+------------+------------+
| key | value |
+------------+------------+
| 1 | 1 |
| 2 | 2 |
+------------+------------+

    package com.aliyun.odps.mapred.open.example;
    import java.io.IOException;
    Import java. util. iterator;
    Import com. aliyun. ODPS. Data. record;
    import com.aliyun.odps.data.TableInfo;
    import com.aliyun.odps.mapred.JobClient;
    import com.aliyun.odps.mapred.MapperBase;
    import com.aliyun.odps.mapred.ReducerBase;
    import com.aliyun.odps.mapred.TaskContext;
    import com.aliyun.odps.mapred.conf.JobConf;
    import com.aliyun.odps.mapred.utils.InputUtils;
    import com.aliyun.odps.mapred.utils.OutputUtils;
    import com.aliyun.odps.mapred.utils.SchemaUtils;
    /**
     * Unique で重複ワードを削除
     *
     **/
    public class Unique {
      public static class OutputSchemaMapper extends MapperBase {
        private Record key;
        private Record value;
        @Override
        public void setup(TaskContext context) throws IOException{
          key = context.createMapOutputKeyRecord();
          value = context.createMapOutputValueRecord();
        }
        @Override
        public void map(long recordNum, Record record, TaskContext context)
            Throws ioexception {
          long left = 0;
          long right = 0;
          if (record.getColumnCount() > 0) {
            left = (Long) record.get(0);
            if (record.getColumnCount() > 1) {
              right = (Long) record.get(1);
            }
            key.set(new Object[] { (Long) left, (Long) right });
            value.set(new Object[] { (Long) left, (Long) right });
            context.write(key, value);
          }
        }
      }
      public static class OutputSchemaReducer extends ReducerBase {
        private Record result = null;
        @Override
        public void setup(TaskContext context) throws IOException{
          result = context.createOutputRecord();
        }
        @Override
        public void reduce(Record key,Iterator<Record>values,TaskContext context)
            Throws ioexception {
          result.set(0, key.get(0));
          while(values.hasNext()) {
            Record value = values.next();
            result.set(1, value.get(1));
          }
          context.write(result);
        }
      }
      public static void main(String[] args) throws Exception {
        if (args.length > 3 || args.length < 2) {
          System.err.println("Usage: unique <in> <out> [key|value|all]");
          System.exit(2);
        }
        String ops = "all";
        if (args.length == 3) {
          Ops = ARGs [2];
        }
        // Reduce 入力グルーピングは、スキャナーの設定に基づき決定されます。このパラメーターが設定されていない場合、
        /Default は mapoutputkeyschema です
        // キー Unique
        if (ops.equals("key")) {
          JobConf job = new JobConf();
          job.setMapperClass(OutputSchemaMapper.class);
          job.setReducerClass(OutputSchemaReducer.class);
          job.setMapOutputKeySchema(SchemaUtils.fromString("key:bigint,value:bigint"));
          job.setMapOutputValueSchema(SchemaUtils.fromString("key:bigint,value:bigint"));
          job.setPartitionColumns(new String[] { "key" });
          job.setOutputKeySortColumns(new String[] { "key", "value" });
          job.setOutputGroupingColumns(new String[] { "key" });
          job.set("tablename2", args[1]);
          job.setNumReduceTasks(1);
          job.setInt("table.counter", 0);
          InputUtils.addTable(TableInfo.builder().tableName(args[0]).build(), job);
          OutputUtils.addTable(TableInfo.builder().tableName(args[1]).build(), job);
          Jobclient. runjob (job );
        }
        // キーと値 Unique
        if (ops.equals("all")) {
          JobConf job = new JobConf();
          job.setMapperClass(OutputSchemaMapper.class);
          job.setReducerClass(OutputSchemaReducer.class);
          job.setMapOutputKeySchema(SchemaUtils.fromString("key:bigint,value:bigint"));
          job.setMapOutputValueSchema(SchemaUtils.fromString("key:bigint,value:bigint"));
          job.setPartitionColumns(new String[] { "key" });
          job.setOutputKeySortColumns(new String[] { "key", "value" });
          job.setOutputGroupingColumns(new String[] { "key", "value" });
          Job. Set ("tablename2", argS [1]);
          job.setNumReduceTasks(1);
          job.setInt("table.counter", 0);
          InputUtils.addTable(TableInfo.builder().tableName(args[0]).build(), job);
          OutputUtils.addTable(TableInfo.builder().tableName(args[1]).build(), job);
          Jobclient. runjob (job );
        }
        // 値 Unique
        if (ops.equals("value")) {
          JobConf job = new JobConf();
          job.setMapperClass(OutputSchemaMapper.class);
          job.setReducerClass(OutputSchemaReducer.class);
          job.setMapOutputKeySchema(SchemaUtils.fromString("key:bigint,value:bigint"));
          job.setMapOutputValueSchema(SchemaUtils.fromString("key:bigint,value:bigint"));
          job.setPartitionColumns(new String[] { "value" });
          job.setOutputKeySortColumns(new String[] { "value" });
          job.setOutputGroupingColumns(new String[] { "value" });
          job.set("tablename2", args[1]);-
          job.setNumReduceTasks(1);
          job.setInt("table.counter", 0);
          InputUtils.addTable(TableInfo.builder().tableName(args[0]).build(), job);
          OutputUtils.addTable(TableInfo.builder().tableName(args[1]).build(), job);
          Jobclient. runjob (job );
        }
      }
    }