hadoop KeyValueTextInputFormat 源码

  • 2022-10-20
  • 浏览 (63)

haddop KeyValueTextInputFormat 代码

文件路径:/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapred/KeyValueTextInputFormat.java

/**
 * 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 org.apache.hadoop.mapred;

import java.io.IOException;

import org.apache.hadoop.classification.InterfaceAudience;
import org.apache.hadoop.classification.InterfaceStability;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
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;

/**
 * An {@link InputFormat} for plain text files. Files are broken into lines.
 * Either linefeed or carriage-return are used to signal end of line. Each line
 * is divided into key and value parts by a separator byte. If no such a byte
 * exists, the key will be the entire line and value will be empty.
 */
@InterfaceAudience.Public
@InterfaceStability.Stable
public class KeyValueTextInputFormat extends FileInputFormat<Text, Text>
  implements JobConfigurable {

  private CompressionCodecFactory compressionCodecs = null;
  
  public void configure(JobConf conf) {
    compressionCodecs = new CompressionCodecFactory(conf);
  }
  
  protected boolean isSplitable(FileSystem fs, Path file) {
    final CompressionCodec codec = compressionCodecs.getCodec(file);
    if (null == codec) {
      return true;
    }
    return codec instanceof SplittableCompressionCodec;
  }
  
  public RecordReader<Text, Text> getRecordReader(InputSplit genericSplit,
                                                  JobConf job,
                                                  Reporter reporter)
    throws IOException {
    
    reporter.setStatus(genericSplit.toString());
    return new KeyValueLineRecordReader(job, (FileSplit) genericSplit);
  }

}

相关信息

hadoop 源码目录

相关文章

hadoop AMFeedback 源码

hadoop BackupStore 源码

hadoop BasicTypeSorterBase 源码

hadoop BufferSorter 源码

hadoop CleanupQueue 源码

hadoop Clock 源码

hadoop ClusterStatus 源码

hadoop Counters 源码

hadoop CumulativePeriodicStats 源码

hadoop DeprecatedQueueConfigurationParser 源码

0  赞