1 /** 2 * Licensed to the Apache Software Foundation (ASF) under one 3 * or more contributor license agreements. See the NOTICE file 4 * distributed with this work for additional information 5 * regarding copyright ownership. The ASF licenses this file 6 * to you under the Apache License, Version 2.0 (the 7 * "License"); you may not use this file except in compliance 8 * with the License. You may obtain a copy of the License at 9 * 10 * http://www.apache.org/licenses/LICENSE-2.0 11 * 12 * Unless required by applicable law or agreed to in writing, software 13 * distributed under the License is distributed on an "AS IS" BASIS, 14 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 15 * See the License for the specific language governing permissions and 16 * limitations under the License. 17 */ 18 19 package org.apache.hadoop.mapreduce.lib.input; 20 21 import org.apache.hadoop.classification.InterfaceAudience; 22 import org.apache.hadoop.classification.InterfaceStability; 23 import org.apache.hadoop.fs.Path; 24 import org.apache.hadoop.io.LongWritable; 25 import org.apache.hadoop.io.Text; 26 import org.apache.hadoop.io.compress.CompressionCodec; 27 import org.apache.hadoop.io.compress.CompressionCodecFactory; 28 import org.apache.hadoop.io.compress.SplittableCompressionCodec; 29 import org.apache.hadoop.mapreduce.InputFormat; 30 import org.apache.hadoop.mapreduce.InputSplit; 31 import org.apache.hadoop.mapreduce.JobContext; 32 import org.apache.hadoop.mapreduce.RecordReader; 33 import org.apache.hadoop.mapreduce.TaskAttemptContext; 34 35 import com.google.common.base.Charsets; 36 37 /** An {@link InputFormat} for plain text files. Files are broken into lines. 38 * Either linefeed or carriage-return are used to signal end of line. Keys are 39 * the position in the file, and values are the line of text.. */ 40 @InterfaceAudience.Public 41 @InterfaceStability.Stable 42 public class TextInputFormat extends FileInputFormat<LongWritable, Text> { 43 44 @Override 45 public RecordReader<LongWritable, Text> 46 createRecordReader(InputSplit split, 47 TaskAttemptContext context) { 48 String delimiter = context.getConfiguration().get( 49 "textinputformat.record.delimiter"); 50 byte[] recordDelimiterBytes = null; 51 if (null != delimiter) 52 recordDelimiterBytes = delimiter.getBytes(Charsets.UTF_8); 53 return new LineRecordReader(recordDelimiterBytes); 54 } 55 56 @Override 57 protected boolean isSplitable(JobContext context, Path file) { 58 final CompressionCodec codec = 59 new CompressionCodecFactory(context.getConfiguration()).getCodec(file); 60 if (null == codec) { 61 return true; 62 } 63 return codec instanceof SplittableCompressionCodec; 64 } 65 66 }
相关文章：