0.90/src/main/java/org/apache/hadoop/hbase/mapreduce/Import.java

/**
 * Copyright 2009 The Apache Software Foundation
 *
 * Licensed to the Apache Software Foundation (ASF) under one
 * or more contributor license agreements.  See the NOTICE file
 * distributed with this work for additional information
 * regarding copyright ownership.  The ASF licenses this file
 * to you under the Apache License, Version 2.0 (the
 * "License"); you may not use this file except in compliance
 * with the License.  You may obtain a copy of the License at
 *
 *     http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 * See the License for the specific language governing permissions and
 * limitations under the License.
 */
package org.apache.hadoop.hbase.mapreduce;

import java.io.IOException;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.hbase.HBaseConfiguration;
import org.apache.hadoop.hbase.KeyValue;
import org.apache.hadoop.hbase.client.Put;
import org.apache.hadoop.hbase.client.Result;
import org.apache.hadoop.hbase.io.ImmutableBytesWritable;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.input.SequenceFileInputFormat;
import org.apache.hadoop.util.GenericOptionsParser;

/**
 * Import data written by {@link Export}.
 */
public class Import {
  final static String NAME = "import";

  /**
   * Write table content out to files in hdfs.
   */
  static class Importer
  extends TableMapper<ImmutableBytesWritable, Put> {
    /**
     * @param row  The current table row key.
     * @param value  The columns.
     * @param context  The current context.
     * @throws IOException When something is broken with the data.
     * @see org.apache.hadoop.mapreduce.Mapper#map(KEYIN, VALUEIN,
     *   org.apache.hadoop.mapreduce.Mapper.Context)
     */
    @Override
    public void map(ImmutableBytesWritable row, Result value,
      Context context)
    throws IOException {
      try {
        context.write(row, resultToPut(row, value));
      } catch (InterruptedException e) {
        e.printStackTrace();
      }
    }

    private static Put resultToPut(ImmutableBytesWritable key, Result result)
    throws IOException {
      Put put = new Put(key.get());
      for (KeyValue kv : result.raw()) {
        put.add(kv);
      }
      return put;
    }
  }

  /**
   * Sets up the actual job.
   *
   * @param conf  The current configuration.
   * @param args  The command line parameters.
   * @return The newly created job.
   * @throws IOException When setting up the job fails.
   */
  public static Job createSubmittableJob(Configuration conf, String[] args)
  throws IOException {
    String tableName = args[0];
    Path inputDir = new Path(args[1]);
    Job job = new Job(conf, NAME + "_" + tableName);
    job.setJarByClass(Importer.class);
    FileInputFormat.setInputPaths(job, inputDir);
    job.setInputFormatClass(SequenceFileInputFormat.class);
    job.setMapperClass(Importer.class);
    // No reducers.  Just write straight to table.  Call initTableReducerJob
    // because it sets up the TableOutputFormat.
    TableMapReduceUtil.initTableReducerJob(tableName, null, job);
    job.setNumReduceTasks(0);
    return job;
  }

  /*
   * @param errorMsg Error message.  Can be null.
   */
  private static void usage(final String errorMsg) {
    if (errorMsg != null && errorMsg.length() > 0) {
      System.err.println("ERROR: " + errorMsg);
    }
    System.err.println("Usage: Import <tablename> <inputdir>");
  }

  /**
   * Main entry point.
   *
   * @param args  The command line parameters.
   * @throws Exception When running the job fails.
   */
  public static void main(String[] args) throws Exception {
    Configuration conf = HBaseConfiguration.create();
    String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
    if (otherArgs.length < 2) {
      usage("Wrong number of arguments: " + otherArgs.length);
      System.exit(-1);
    }
    Job job = createSubmittableJob(conf, otherArgs);
    System.exit(job.waitForCompletion(true) ? 0 : 1);
  }
}