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 */ 018 019 package org.apache.hadoop.mapred; 020 021 import java.io.IOException; 022 023 import org.apache.hadoop.classification.InterfaceAudience; 024 import org.apache.hadoop.classification.InterfaceStability; 025 import org.apache.hadoop.conf.Configuration; 026 import org.apache.hadoop.io.LongWritable; 027 import org.apache.hadoop.io.Text; 028 029 /** 030 * This class treats a line in the input as a key/value pair separated by a 031 * separator character. The separator can be specified in config file 032 * under the attribute name mapreduce.input.keyvaluelinerecordreader.key.value.separator. The default 033 * separator is the tab character ('\t'). 034 * 035 * @deprecated Use 036 * {@link org.apache.hadoop.mapreduce.lib.input.KeyValueLineRecordReader} 037 * instead 038 */ 039 @Deprecated 040 @InterfaceAudience.Public 041 @InterfaceStability.Stable 042 public class KeyValueLineRecordReader implements RecordReader<Text, Text> { 043 044 private final LineRecordReader lineRecordReader; 045 046 private byte separator = (byte) '\t'; 047 048 private LongWritable dummyKey; 049 050 private Text innerValue; 051 052 public Class getKeyClass() { return Text.class; } 053 054 public Text createKey() { 055 return new Text(); 056 } 057 058 public Text createValue() { 059 return new Text(); 060 } 061 062 public KeyValueLineRecordReader(Configuration job, FileSplit split) 063 throws IOException { 064 065 lineRecordReader = new LineRecordReader(job, split); 066 dummyKey = lineRecordReader.createKey(); 067 innerValue = lineRecordReader.createValue(); 068 String sepStr = job.get("mapreduce.input.keyvaluelinerecordreader.key.value.separator", "\t"); 069 this.separator = (byte) sepStr.charAt(0); 070 } 071 072 public static int findSeparator(byte[] utf, int start, int length, 073 byte sep) { 074 return org.apache.hadoop.mapreduce.lib.input. 075 KeyValueLineRecordReader.findSeparator(utf, start, length, sep); 076 } 077 078 /** Read key/value pair in a line. */ 079 public synchronized boolean next(Text key, Text value) 080 throws IOException { 081 byte[] line = null; 082 int lineLen = -1; 083 if (lineRecordReader.next(dummyKey, innerValue)) { 084 line = innerValue.getBytes(); 085 lineLen = innerValue.getLength(); 086 } else { 087 return false; 088 } 089 if (line == null) 090 return false; 091 int pos = findSeparator(line, 0, lineLen, this.separator); 092 org.apache.hadoop.mapreduce.lib.input.KeyValueLineRecordReader. 093 setKeyValue(key, value, line, lineLen, pos); 094 return true; 095 } 096 097 public float getProgress() throws IOException { 098 return lineRecordReader.getProgress(); 099 } 100 101 public synchronized long getPos() throws IOException { 102 return lineRecordReader.getPos(); 103 } 104 105 public synchronized void close() throws IOException { 106 lineRecordReader.close(); 107 } 108 }