com.sourcecode.TextInputFormat.java Source code

Introduction

Here is the source code for com.sourcecode.TextInputFormat.java

Source

/**
 * Licensed to the Apache Software Foundation (ASF) under one
 * or more contributor license agreements.  See the NOTICE file
 * distributed with this work for additional information
 * regarding copyright ownership.  The ASF licenses this file
 * to you under the Apache License, Version 2.0 (the
 * "License"); you may not use this file except in compliance
 * with the License.  You may obtain a copy of the License at
 *
 *     http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 * See the License for the specific language governing permissions and
 * limitations under the License.
 */

package com.sourcecode;

import org.apache.hadoop.classification.InterfaceAudience;
import org.apache.hadoop.classification.InterfaceStability;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.io.compress.CompressionCodec;
import org.apache.hadoop.io.compress.CompressionCodecFactory;
import org.apache.hadoop.io.compress.SplittableCompressionCodec;
import org.apache.hadoop.mapreduce.InputFormat;
import org.apache.hadoop.mapreduce.InputSplit;
import org.apache.hadoop.mapreduce.JobContext;
import org.apache.hadoop.mapreduce.RecordReader;
import org.apache.hadoop.mapreduce.TaskAttemptContext;
import org.apache.hadoop.mapreduce.lib.input.LineRecordReader;

import com.google.common.base.Charsets;

import com.sourcecode.FileInputFormat;

/** An {@link InputFormat} for plain text files.  Files are broken into lines.
 * Either linefeed or carriage-return are used to signal end of line.  Keys are
 * the position in the file, and values are the line of text.. */
@InterfaceAudience.Public
@InterfaceStability.Stable
public class TextInputFormat extends FileInputFormat<LongWritable, Text> {

    @Override
    public RecordReader<LongWritable, Text> createRecordReader(InputSplit split, TaskAttemptContext context) {
        String delimiter = context.getConfiguration().get("textinputformat.record.delimiter");
        byte[] recordDelimiterBytes = null;
        if (null != delimiter)
            recordDelimiterBytes = delimiter.getBytes(Charsets.UTF_8);
        return new LineRecordReader(recordDelimiterBytes);
    }

    @Override
    protected boolean isSplitable(JobContext context, Path file) {
        final CompressionCodec codec = new CompressionCodecFactory(context.getConfiguration()).getCodec(file);
        if (null == codec) {
            return true;
        }
        return codec instanceof SplittableCompressionCodec;
    }

}