自己編寫的WordCound如何在Linux執行
阿新 • • 發佈:2018-11-14
首先寫上自己的程式碼,在eclipse編譯完成
package com.jie; import java.io.IOException; 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.Mapper; import org.apache.hadoop.mapreduce.Reducer; import org.apache.hadoop.mapreduce.lib.input.FileInputFormat; import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat; public class WordCount { public static class TokenizerMapper extends Mapper<Object, Text, Text, IntWritable>{ private final IntWritable one = new IntWritable(1); private Text word = new Text(); @Override public void map(Object key, Text value, Context context ) throws IOException, InterruptedException { String str = value.toString(); int len = str.length(); for (int i = 0; i < len; i++) { char c = str.charAt(i); if(!Character.isWhitespace(c)){ word.set(String.valueOf(c)); context.write(word, one); } } } } public static class IntSumReducer extends Reducer<Text, IntWritable, Text, IntWritable>{ private IntWritable result = new IntWritable(); @Override protected void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException { int sum = 0; for (IntWritable one : values) { sum += one.get(); } result.set(sum); context.write(key, result); } } public static void main(String[] args) throws Exception{ Configuration cfg = new Configuration(); if(args.length < 2){ System.err.println("Usage: <in> <out>"); System.exit(2); } Job job = Job.getInstance(cfg, "myCharCount"); job.setJarByClass(WordCount.class); job.setMapperClass(TokenizerMapper.class); job.setCombinerClass(IntSumReducer.class); job.setReducerClass(IntSumReducer.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(IntWritable.class); FileInputFormat.addInputPath(job, new Path(args[0])); FileOutputFormat.setOutputPath(job, new Path(args[1])); System.exit(job.waitForCompletion(true) ? 0 : 1 ); } }
編譯完之後打包
上傳檔案後
執行
hadoop jar hp.jar /usr/test/word /usr/test/output