| 1 | /******************************************************************************
|
|---|
| 2 | *
|
|---|
| 3 | * A component of the Greenstone digital library software from the New Zealand
|
|---|
| 4 | * Digital Library Project at the # University of Waikato, New Zealand.
|
|---|
| 5 | * Copyright (C) 2006 New Zealand Digital Library Project
|
|---|
| 6 | *
|
|---|
| 7 | * This program is free software; you can redistribute it and/or modify it
|
|---|
| 8 | * under the terms of the GNU General Public License as published by the Free
|
|---|
| 9 | * Software Foundation; either version 2 of the License, or (at your option)
|
|---|
| 10 | * any later version.
|
|---|
| 11 | *
|
|---|
| 12 | * This program is distributed in the hope that it will be useful, but
|
|---|
| 13 | * WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
|
|---|
| 14 | * or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
|
|---|
| 15 | * for more details.
|
|---|
| 16 | *
|
|---|
| 17 | * You should have received a copy of the GNU General Public License along
|
|---|
| 18 | * with this program; if not, write to the Free Software Foundation, Inc.,
|
|---|
| 19 | * 675 Mass Ave, Cambridge, MA 02139, USA.
|
|---|
| 20 | *****************************************************************************/
|
|---|
| 21 | /** @author jmt12, GSDL **/
|
|---|
| 22 | package org.nzdl.gsdl;
|
|---|
| 23 |
|
|---|
| 24 | import org.apache.hadoop.io.Text;
|
|---|
| 25 | import org.apache.hadoop.mapreduce.Partitioner;
|
|---|
| 26 |
|
|---|
| 27 | /** @class GSPartitioner
|
|---|
| 28 | */
|
|---|
| 29 | public class GSPartitioner
|
|---|
| 30 | extends Partitioner<Text, Text>
|
|---|
| 31 | {
|
|---|
| 32 |
|
|---|
| 33 | /** @function getPartition()
|
|---|
| 34 | */
|
|---|
| 35 | public int getPartition(Text key, Text value, int num_reduce_tasks)
|
|---|
| 36 | {
|
|---|
| 37 | int index = 0;
|
|---|
| 38 | String key_string = key.toString();
|
|---|
| 39 | String[] key_parts = key_string.split(" ");
|
|---|
| 40 | String type = key_parts[0];
|
|---|
| 41 | if (type.equals("datestamp"))
|
|---|
| 42 | {
|
|---|
| 43 | index = 1;
|
|---|
| 44 | }
|
|---|
| 45 | if (type.equals("doc"))
|
|---|
| 46 | {
|
|---|
| 47 | index = 2;
|
|---|
| 48 | }
|
|---|
| 49 | if (type.equals("rss"))
|
|---|
| 50 | {
|
|---|
| 51 | index = 3;
|
|---|
| 52 | }
|
|---|
| 53 | if (type.equals("src"))
|
|---|
| 54 | {
|
|---|
| 55 | index = 4;
|
|---|
| 56 | }
|
|---|
| 57 | return index % num_reduce_tasks;
|
|---|
| 58 | }
|
|---|
| 59 | /** getPartition(Text, Text, int) **/
|
|---|
| 60 |
|
|---|
| 61 | }
|
|---|
| 62 | /** class GSPartitioner **/ |
|---|
