wordcount和sort代码
2016-08-18 22:26
155 查看
程序1:WordCount.java package com.wordcount.test; 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.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; import org.apache.hadoop.mapreduce.lib.output.SequenceFileOutputFormat; import org.apache.hadoop.util.GenericOptionsParser; 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 IntSumCombiner extends Reducer<Text,IntWritable,Text,IntWritable>{ private IntWritable result = new IntWritable(); @Override protected void reduce(Text key, Iterable<IntWritable> values, Reducer<Text, IntWritable, Text, IntWritable>.Context context) throws IOException, InterruptedException { int sum = 0; for(IntWritable val : values){ sum += val.get(); } result.set(sum); context.write(key,result); } } public static class IntSumReducer extends Reducer<Text,IntWritable,IntWritable,Text> { 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(result, key); } } public static void main(String[] args) throws Exception { Configuration conf = new Configuration(); String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs(); if (otherArgs.length < 2) { System.err.println("Usage: wordcount <in> [<in>...] <out>"); System.exit(2); } Job job = new Job(conf, "word count"); job.setJarByClass(WordCount.class); job.setMapperClass(TokenizerMapper.class); job.setCombinerClass(IntSumCombiner.class); job.setReducerClass(IntSumReducer.class); job.setMapOutputKeyClass(Text.class); job.setMapOutputValueClass(IntWritable.class); job.setOutputKeyClass(IntWritable.class); job.setOutputValueClass(Text.class); job.setOutputFormatClass(SequenceFileOutputFormat.class); FileInputFormat.addInputPath(job, new Path(otherArgs[0])); FileOutputFormat.setOutputPath(job,new Path(otherArgs[1])); System.exit(job.waitForCompletion(true) ? 0 : 1); } } 程序2:Sort.java package com.wordcount.test; import java.io.DataInput; import java.io.DataOutput; 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.io.WritableComparable; 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.SequenceFileInputFormat; import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat; import org.apache.hadoop.util.GenericOptionsParser; public class Sort { public static class SimpleMapper extends Mapper<IntWritable,Text,RevertKey,Text>{ protected void map(IntWritable key, Text value, Mapper<IntWritable, Text, RevertKey, Text>.Context context) throws IOException, InterruptedException { RevertKey newkey = new RevertKey(key); context.write(newkey,value); } } public static class SimpleReducer extends Reducer<RevertKey,Text,Text,IntWritable>{ protected void reduce(RevertKey key, java.lang.Iterable<Text> values, org.apache.hadoop.mapreduce.Reducer<RevertKey,Text,Text,IntWritable>.Context context) throws IOException ,InterruptedException { for(Text val : values){ context.write(val,key.getKey()); } }; } public static class RevertKey implements WritableComparable<RevertKey>{ private IntWritable key; public RevertKey(){ key = new IntWritable(); } public RevertKey(IntWritable key){ this.key = key; } public IntWritable getKey(){ return key; } @Override public void readFields(DataInput in) throws IOException { key.readFields(in); } @Override public void write(DataOutput out) throws IOException { key.write(out); } @Override public int compareTo(RevertKey o) { return -key.compareTo(o.getKey()); } } public static void main(String[] args) throws Exception { Configuration conf = new Configuration(); String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs(); if (otherArgs.length < 2) { System.err.println("Usage: wordcount <in> [<in>...] <out>"); System.exit(2); } Job job = new Job(conf, "word count"); job.setJarByClass(Sort.class); job.setMapperClass(SimpleMapper.class); job.setReducerClass(SimpleReducer.class); job.setMapOutputKeyClass(RevertKey.class); job.setMapOutputValueClass(Text.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(IntWritable.class); job.setInputFormatClass(SequenceFileInputFormat.class); FileInputFormat.addInputPath(job, new Path(otherArgs[0])); FileOutputFormat.setOutputPath(job,new Path(otherArgs[1])); System.exit(job.waitForCompletion(true) ? 0 : 1); } }
今天在远程桌面上跑了这两个程序
导入jar包 hadoop-2.6.2 share/hadoop 中的common hdfs mapreduce yarn 各自jar包及其lib里的(都倒进去避免麻烦
导入jar包。
执行bin/hadoop jar /liyanan/Desktop/wordcounta.jar com.wordcount.test.WordCount /tmp/wordcount tmp/wordcounta
可以用bin/hadoop fs -ls tmp/
bin/hadoop fs -cat tmp/
查看,之前linux没学好
尽快补上。
执行完wordcount之后,调试sort,注意输入文件是之前输出的part-r-00000
bin/hadoop jar /liyanan/Desktop/wordcounta.jar com.wordcount.test.Sort tmp/wordcounta/part-r-00000 tmp/sorta
相关文章推荐
- Hadoop入门WordCount代码
- hadoop wordcount 代码
- 010-spark standalone模式JAVA版本WordCount代码
- hadoop自带wordcount代码详解
- Trident WordCount代码示例
- hadoop学习之WordCount.java代码解读
- spark streaming 接收 kafka 数据java代码WordCount示例
- spark streaming 接收 kafka 数据java代码WordCount示例
- 010-spark standalone模式Scala版本WordCount代码
- Hadoop中WordCount代码-直接加载hadoop的配置文件
- WordCount运行原理结合代码详细分析
- 5行代码怎么实现Hadoop的WordCount?
- 5行代码怎么实现Hadoop的WordCount?
- Hadoop WordCount代码
- hadoop之WordCount代码编写
- hadoop学习之WordCount.java代码解读
- 5行代码怎么实现Hadoop的WordCount?
- hadoop2.0 wordcount代码讲解
- 【3-3】Wordcount代码编写
- Hadoop2.x实战:WordCount、Sort、去重复、average实例MapRedure编写