hadoop TokenCountMapper 源码
haddop TokenCountMapper 代码
文件路径：/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapred/lib/TokenCountMapper.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.lib;
import java.io.IOException;
import java.util.StringTokenizer;
import org.apache.hadoop.classification.InterfaceAudience;
import org.apache.hadoop.classification.InterfaceStability;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapred.MapReduceBase;
import org.apache.hadoop.mapred.Mapper;
import org.apache.hadoop.mapred.OutputCollector;
import org.apache.hadoop.mapred.Reporter;
/**
* A {@link Mapper} that maps text values into <token,freq> pairs. Uses
* {@link StringTokenizer} to break text into tokens.
*/
@InterfaceAudience.Public
@InterfaceStability.Stable
public class TokenCountMapper<K> extends MapReduceBase
implements Mapper<K, Text, Text, LongWritable> {
public void map(K key, Text value,
OutputCollector<Text, LongWritable> output,
Reporter reporter)
throws IOException {
// get input text
String text = value.toString(); // value is line of text
// tokenize the value
StringTokenizer st = new StringTokenizer(text);
while (st.hasMoreTokens()) {
// output <token,1> pairs
output.collect(new Text(st.nextToken()), new LongWritable(1));
}
}
}
相关信息
相关文章
hadoop CombineFileInputFormat 源码
hadoop CombineFileRecordReader 源码
hadoop CombineFileRecordReaderWrapper 源码
0
赞
热门推荐
-
2、 - 优质文章
-
3、 gate.io
-
8、 golang
-
9、 openharmony
-
10、 Vue中input框自动聚焦