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.util.ArrayList; 022import java.util.List; 023 024import org.apache.yetus.audience.InterfaceAudience; 025import org.apache.hadoop.conf.Configurable; 026import org.apache.hadoop.conf.Configuration; 027import org.apache.hadoop.hbase.client.Scan; 028 029/** 030 * Convert HBase tabular data from multiple scanners into a format that 031 * is consumable by Map/Reduce. 032 * 033 * <p> 034 * Usage example 035 * </p> 036 * 037 * <pre> 038 * List<Scan> scans = new ArrayList<Scan>(); 039 * 040 * Scan scan1 = new Scan(); 041 * scan1.setStartRow(firstRow1); 042 * scan1.setStopRow(lastRow1); 043 * scan1.setAttribute(Scan.SCAN_ATTRIBUTES_TABLE_NAME, table1); 044 * scans.add(scan1); 045 * 046 * Scan scan2 = new Scan(); 047 * scan2.setStartRow(firstRow2); 048 * scan2.setStopRow(lastRow2); 049 * scan1.setAttribute(Scan.SCAN_ATTRIBUTES_TABLE_NAME, table2); 050 * scans.add(scan2); 051 * 052 * TableMapReduceUtil.initTableMapperJob(scans, TableMapper.class, Text.class, 053 * IntWritable.class, job); 054 * </pre> 055 */ 056@InterfaceAudience.Public 057public class MultiTableInputFormat extends MultiTableInputFormatBase implements 058 Configurable { 059 060 /** Job parameter that specifies the scan list. */ 061 public static final String SCANS = "hbase.mapreduce.scans"; 062 063 /** The configuration. */ 064 private Configuration conf = null; 065 066 /** 067 * Returns the current configuration. 068 * 069 * @return The current configuration. 070 * @see org.apache.hadoop.conf.Configurable#getConf() 071 */ 072 @Override 073 public Configuration getConf() { 074 return conf; 075 } 076 077 /** 078 * Sets the configuration. This is used to set the details for the tables to 079 * be scanned. 080 * 081 * @param configuration The configuration to set. 082 * @see org.apache.hadoop.conf.Configurable#setConf( 083 * org.apache.hadoop.conf.Configuration) 084 */ 085 @Override 086 public void setConf(Configuration configuration) { 087 this.conf = configuration; 088 String[] rawScans = conf.getStrings(SCANS); 089 if (rawScans.length <= 0) { 090 throw new IllegalArgumentException("There must be at least 1 scan configuration set to : " 091 + SCANS); 092 } 093 List<Scan> scans = new ArrayList<>(); 094 095 for (int i = 0; i < rawScans.length; i++) { 096 try { 097 scans.add(TableMapReduceUtil.convertStringToScan(rawScans[i])); 098 } catch (IOException e) { 099 throw new RuntimeException("Failed to convert Scan : " + rawScans[i] + " to string", e); 100 } 101 } 102 this.setScans(scans); 103 } 104}