hadoop示例程序Grep分析

haishi

　　该程序实现的是对指定文档中指定单词的词频进行计算



  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 package org.apache.hadoop.examples;
19
20 import java.util.Random;
21
22 import org.apache.hadoop.conf.Configuration;
23 import org.apache.hadoop.conf.Configured;
24 import org.apache.hadoop.fs.FileSystem;
25 import org.apache.hadoop.fs.Path;
26 import org.apache.hadoop.io.LongWritable;
27 import org.apache.hadoop.io.Text;
28 import org.apache.hadoop.mapred.*;
29 import org.apache.hadoop.mapred.lib.*;
30 import org.apache.hadoop.util.Tool;
31 import org.apache.hadoop.util.ToolRunner;
32
33 /* Extracts matching regexs from input files and counts them. */
34 /* 从input中提取与表达式相符的单词并计算词频*/
35 publicclass Grep extends Configured implements Tool {
36 private Grep() {}                               // singleton
37 /** 继承自配置基类Configured,并扩展接口Tool
38         *Configured类中有一个变量conf用于存储配置文件
39         *Tool中只有一个方法需要实现
40       *int run(String [] args)用于运行输入参数
41 */
42 publicint run(String[] args) throws Exception {
43 if (args.length