001/*
002 * Licensed to the Apache Software Foundation (ASF) under one
003 * or more contributor license agreements.  See the NOTICE file
004 * distributed with this work for additional information
005 * regarding copyright ownership.  The ASF licenses this file
006 * to you under the Apache License, Version 2.0 (the
007 * "License"); you may not use this file except in compliance
008 * with the License.  You may obtain a copy of the License at
009 *
010 *     http://www.apache.org/licenses/LICENSE-2.0
011 *
012 * Unless required by applicable law or agreed to in writing, software
013 * distributed under the License is distributed on an "AS IS" BASIS,
014 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
015 * See the License for the specific language governing permissions and
016 * limitations under the License.
017 */
018package org.apache.hadoop.hbase.mapreduce;
019
020import java.io.IOException;
021import java.nio.charset.StandardCharsets;
022import org.apache.hadoop.hbase.KeyValue;
023import org.apache.hadoop.hbase.client.Durability;
024import org.apache.hadoop.hbase.client.Put;
025import org.apache.hadoop.hbase.io.ImmutableBytesWritable;
026import org.apache.hadoop.hbase.util.Bytes;
027import org.apache.hadoop.io.LongWritable;
028import org.apache.hadoop.io.Text;
029
030/**
031 * Dummy mapper used for unit tests to verify that the mapper can be injected. This approach would
032 * be used if a custom transformation needed to be done after reading the input data before writing
033 * it to HFiles.
034 */
035public class TsvImporterCustomTestMapper extends TsvImporterMapper {
036  @Override
037  protected void setup(Context context) {
038    doSetup(context);
039  }
040
041  /**
042   * Convert a line of TSV text into an HBase table row after transforming the values by multiplying
043   * them by 3.
044   */
045  @Override
046  public void map(LongWritable offset, Text value, Context context) throws IOException {
047    byte[] family = Bytes.toBytes("FAM");
048    final byte[][] qualifiers = { Bytes.toBytes("A"), Bytes.toBytes("B") };
049
050    // do some basic line parsing
051    byte[] lineBytes = value.getBytes();
052    String[] valueTokens = new String(lineBytes, StandardCharsets.UTF_8).split("\u001b");
053
054    // create the rowKey and Put
055    ImmutableBytesWritable rowKey = new ImmutableBytesWritable(Bytes.toBytes(valueTokens[0]));
056    Put put = new Put(rowKey.copyBytes());
057    put.setDurability(Durability.SKIP_WAL);
058
059    // The value should look like this: VALUE1 or VALUE2. Let's multiply
060    // the integer by 3
061    for (int i = 1; i < valueTokens.length; i++) {
062      String prefix = valueTokens[i].substring(0, "VALUE".length());
063      String suffix = valueTokens[i].substring("VALUE".length());
064      String newValue = prefix + Integer.parseInt(suffix) * 3;
065
066      KeyValue kv =
067        new KeyValue(rowKey.copyBytes(), family, qualifiers[i - 1], Bytes.toBytes(newValue));
068      put.add(kv);
069    }
070
071    try {
072      context.write(rowKey, put);
073    } catch (InterruptedException e) {
074      e.printStackTrace();
075    }
076  }
077}