一、安装Hadoop插件
1. 所需环境
hadoop2.0伪分布式环境平台正常运行
所需压缩包:eclipse-jee-luna-SR2-linux-gtk-x86_64.tar.gz
在Linux环境下运行的eclipse软件压缩包,解压后文件名为eclipse
hadoop2x-eclipse-plugin-master.zip
在eclipse中需要安装的Hadoop插件,解压后文件名为hadoop2x-eclipse-plugin-master
如图所示,将所有的压缩包放在同一个文件夹下并解压。
2.编译jar包
编译hadoop2x-eclipse-plugin-master的plugin 的插件源码,需要先安装ant工具
接着输入命令(注意ant命令在什么路径下使用,具体路径在下一张截图中,不然这个命令会用不了):
ant jar -Dversion=2.6.0 -Declipse.home=\'/home/xiaow/hadoop2.0/eclipse\' # 刚才放进去的eclipse软件包的路径 -Dversion=2.6.0 hadoop的版本号 -Dhadoop.home=\'/home/xiaow/hadoop2.0/hadoop-2.6.0\' # hadoop安装文件的路径
等待一小会时间就好了
编译成功后,找到放在 /home/xiaow/ hadoop2.0/hadoop2x-eclipse-pluginmaster/build/contrib/eclipse-plugin下, 名为hadoop-eclipse-plugin-2.6.0.jar的jar包, 并将其拷贝到/hadoop2.0/eclipse/plugins下
输入命令:
cp -r /home/xiaow/hadoop2.0/hadoop2x-eclipse-plugin-master/build/contrib/eclipse-plugin/hadoop-eclipse-plugin-2.6.0.jar /home/xiaow/hadoop2.0/eclipse/plugins/
二、Eclipse配置
接下来打开eclipse软件
一定要出现这个图标,没有出现的话前面步骤可能错了,或者重新启动几次Eclipse
然后按照下面的截图操作:
如此,Eclipse环境搭建完成。
三、wordcount程序
建工程:
输入如下代码:
package wordcount; import java.io.IOException; import java.util.StringTokenizer; import org.apache.hadoop.conf.Configuration; import org.apache.hadoop.fs.Path; import org.apache.hadoop.io.IntWritable; import org.apache.hadoop.io.LongWritable; import org.apache.hadoop.io.Text; import org.apache.hadoop.mapreduce.Job; import org.apache.hadoop.mapreduce.Mapper; import org.apache.hadoop.mapreduce.Reducer; import org.apache.hadoop.mapreduce.lib.input.FileInputFormat; import org.apache.hadoop.mapreduce.lib.input.TextInputFormat; import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat; import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat; import org.apache.hadoop.mapreduce.lib.reduce.IntSumReducer; import org.apache.hadoop.util.GenericOptionsParser; public class wordcount { // 自定义的mapper,继承org.apache.hadoop.mapreduce.Mapper public static class WordCountMap extends Mapper<LongWritable, Text, Text, IntWritable> { private final IntWritable one = new IntWritable(1); private Text word = new Text(); // Mapper<LongWritable, Text, Text, LongWritable>.Context context public void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException { String line = value.toString(); System.out.println(line); // split 函数是用于按指定字符(串)或正则去分割某个字符串,结果以字符串数组形式返回,这里按照“\t”来分割text文件中字符,即一个制表符 // ,这就是为什么我在文本中用了空格分割,导致最后的结果有很大的出入 StringTokenizer token = new StringTokenizer(line); while (token.hasMoreTokens()) { word.set(token.nextToken()); context.write(word, one); } } } // 自定义的reducer,继承org.apache.hadoop.mapreduce.Reducer public static class WordCountReduce extends Reducer<Text, IntWritable, Text, IntWritable> { // Reducer<Text, LongWritable, Text, LongWritable>.Context context public void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException { System.out.println(key); System.out.println(values); int sum = 0; for (IntWritable val : values) { sum += val.get(); } context.write(key, new IntWritable(sum)); } } // 客户端代码,写完交给ResourceManager框架去执行 public static void main(String[] args) throws Exception { Configuration conf = new Configuration(); Job job = new Job(conf,"word count"); // 打成jar执行 job.setJarByClass(wordcount.class); // 数据在哪里? FileInputFormat.addInputPath(job, new Path(args[0])); // 使用哪个mapper处理输入的数据? job.setMapperClass(WordCountMap.class); // map输出的数据类型是什么? //job.setMapOutputKeyClass(Text.class); //job.setMapOutputValueClass(LongWritable.class); job.setCombinerClass(IntSumReducer.class); // 使用哪个reducer处理输入的数据 job.setReducerClass(WordCountReduce.class); // reduce输出的数据类型是什么? job.setOutputKeyClass(Text.class); job.setOutputValueClass(IntWritable.class); // job.setInputFormatClass(TextInputFormat.class); // job.setOutputFormatClass(TextOutputFormat.class); // 数据输出到哪里? FileOutputFormat.setOutputPath(job, new Path(args[1])); // 交给yarn去执行,直到执行结束才退出本程序 job.waitForCompletion(true); /* String[] otherArgs = new GenericOptionsParser(conf,args).getRemainingArgs(); if(otherArgs.length<2){ System.out.println("Usage:wordcount <in> [<in>...] <out>"); System.exit(2); } for(int i=0;i<otherArgs.length-1;i++){ FileInputFormat.addInputPath(job, new Path(otherArgs[i])); } System.exit(job.waitForCompletion(tr0ue)?0:1); */ } }
将准备到的文档导入进去
目录结构如下:
运行mapreduce程序
OK,搞定收工!!!