MapReduce程序的开发过程

1. 在linux(虚拟机环境)下安装hadoop2.8.3

1.1 安装JDK环境

1.2 安装hadoop

1.3 进行配置：core-site.xml，hdfs-site.xml设置

1.4 初始化namenode

1.5 启动dfs和yarn

2. 在主机WIN10下安装STS及maven

3. 在将linux下hadoop目录全部拷贝到WIN10下，设置HADOOP-HOME环境变量，并将HADOOP-HOME/bin加入PATH

4. 将hadoop-eclipse-plugin-2.8.3插件拷贝到STS的plugin目录下，并将winutils.exe放入win10中hadoop/bin目录下，将hadoop.dll加入到windows/system32目录下

5. 启动STS安装hadoop-eclipse-plugin-2.8.3插件（在sts中设置hadoop的安装目录，并建立一个linux下hadoop服务器的实例，设置其dfs server的IP和port），可以看到所有hadoop的节点内目录

6. 生成一个mapreduce项目，在项目的src中新建一个wordcount.java文件

7. 将代码加入其中：

package helloWordCount;

public class WordCount {

public static class TokenizerMapper
extends Mapper<Object, Text, Text, IntWritable>{

private final static IntWritable one = new IntWritable(1);
private Text word = new Text();

public void map(Object key, Text value, Context context
) throws IOException, InterruptedException {
StringTokenizer itr = new StringTokenizer(value.toString());
while (itr.hasMoreTokens()) {
word.set(itr.nextToken());
context.write(word, one);
}
}
}

public static class IntSumReducer
extends Reducer<Text,IntWritable,Text,IntWritable> {
private IntWritable result = new IntWritable();

public void reduce(Text key, Iterable<IntWritable> values,
Context context
) throws IOException, InterruptedException {
int sum = 0;
for (IntWritable val : values) {
sum += val.get();
}
result.set(sum);
context.write(key, result);
}
}

public static void main(String[] args) throws Exception {
Configuration conf = new Configuration();
conf.addResource("../core-site.xml");//将hadoop的设置导入，这样就不会出现找不到目录的情况了
conf.addResource("../hdfs-site.xml");//将hadoop的设置导入，这样就不会出现找不到目录的情况了
//String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
String[] otherArgs = new String[] {"/input", "/output"};
if (otherArgs.length < 2) {
System.err.println("Usage: wordcount <in> [<in>...] <out>");
System.exit(2);
}
Job job = Job.getInstance(conf, "word count");
job.setJarByClass(WordCount.class);
job.setMapperClass(TokenizerMapper.class);
job.setCombinerClass(IntSumReducer.class);
job.setReducerClass(IntSumReducer.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
for (int i = 0; i < otherArgs.length - 1; ++i) {
FileInputFormat.addInputPath(job, new Path(otherArgs[i]));
}
FileOutputFormat.setOutputPath(job,
new Path(otherArgs[otherArgs.length - 1]));
System.exit(job.waitForCompletion(true) ? 0 : 1);
}
}

8.完成后，右击文件wordcount.java，点击Run As-》run on hadoop运行

第一次运行时出现找不到指定的文件夹的异常，其原因是没有将hadoop的基本设置导入，这时需要加入上面带有下划线的两行，一切OK！