1、新建一个IDEA的Maven工程
2、引入依赖
3、Mapper类
package com.motoon; import org.apache.hadoop.io.IntWritable; import org.apache.hadoop.io.LongWritable; import org.apache.hadoop.io.Text; import org.apache.hadoop.mapreduce.Mapper; import java.io.IOException; /** * @author rjsong */ public class WordCountMapper extends Mapper<LongWritable, Text, Text, IntWritable> { /** * map阶段的业务逻辑就写在自定义的map()方法中 * maptask会对每一行输入数据调用一次我们自定义的map()方法 */ protected void map(LongWritable key, Text value, Context context) throws IOException,InterruptedException{ //将maptask传过来的文本先转换成String String line = value.toString(); //根据空格将这一行分成单词 String[] words =line.split(" "); //将单词输出为<单词,1> for (String word:words){ //将单词作为key,将次数1作为value,以便于后续的数据开发,可以根据单词分发,以便于相同单词会到相同的reduce task context.write(new Text(word), new IntWritable(1)); } } }
4、Reducer类
package com.motoon; import org.apache.hadoop.io.IntWritable; import org.apache.hadoop.io.Text; import org.apache.hadoop.mapreduce.Reducer; import java.io.IOException; /** * @author rjsong */ public class WordCountReducer extends Reducer<Text, IntWritable, Text, IntWritable>{ public void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException,InterruptedException{ int count = 0; for (IntWritable value:values){ count+=value.get(); } context.write(key, new IntWritable(count)); } }
5、main类
package com.motoon; import org.apache.hadoop.conf.Configuration; import org.apache.hadoop.fs.Path; import org.apache.hadoop.io.IntWritable; import org.apache.hadoop.io.Text; import org.apache.hadoop.mapreduce.Job; import org.apache.hadoop.mapreduce.lib.input.FileInputFormat; import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat; /** * @author rjsong */ public class WordCountDriver { public static void main(String[] args) throws Exception { Configuration conf = new Configuration(); Job wordCountJob = Job.getInstance(conf); //重要:指定本job所在的jar包 wordCountJob.setJarByClass(WordCountDriver.class); //设置wordCountJob所用的mapper逻辑类为哪个类 wordCountJob.setMapperClass(WordCountMapper.class); //设置wordCountJob所用的reducer逻辑类为哪个类 wordCountJob.setReducerClass(WordCountReducer.class); //设置map阶段输出的kv数据类型 wordCountJob.setMapOutputKeyClass(Text.class); wordCountJob.setMapOutputValueClass(IntWritable.class); //设置最终输出的kv数据类型 wordCountJob.setOutputKeyClass(Text.class); wordCountJob.setOutputValueClass(IntWritable.class); //设置要处理的文本数据所存放的路径 FileInputFormat.setInputPaths(wordCountJob, "hdfs://192.168.61.138:9000/wordcount/input/"); FileOutputFormat.setOutputPath(wordCountJob, new Path("hdfs://192.168.61.138:9000/wordcount/output/")); //提交job给hadoop wordCountJob.waitForCompletion(true); } } 6、导出jar包,在工作区间目录下会产生一个out目录,里面有相应的jar文件。 7、将jar文件上传到linux服务器上 8、创建文本数据 9、将文本数据上传到hdfs上 10、运行jar文件 11、显示结果