Java执行hadoop的基本操作实例代码

Java执行hadoop的基本操作实例代码

向HDFS上传本地文件

public static void uploadInputFile(String localFile) throws IOException{
   Configuration conf = new Configuration();
   String hdfsPath = "hdfs://localhost:9000/";
   String hdfsInput = "hdfs://localhost:9000/user/hadoop/input";
   FileSystem fs = FileSystem.get(URI.create(hdfsPath), conf);
   fs.copyFromLocalFile(new Path(localFile), new Path(hdfsInput));
   fs.close();
   System.out.println("已经上传文件到input文件夹啦");
 }

将output文件下载到本地

public static void getOutput(String outputfile) throws IOException{
   String remoteFile = "hdfs://localhost:9000/user/hadoop/output/part-r-00000";
   Path path = new Path(remoteFile);
   Configuration conf = new Configuration();
   String hdfsPath = "hdfs://localhost:9000/";
   FileSystem fs = FileSystem.get(URI.create(hdfsPath),conf);
   fs.copyToLocalFile(path, new Path(outputfile));
   System.out.println("已经将输出文件保留到本地文件");
   fs.close();
 }

删除hdfs中的文件

public static void deleteOutput() throws IOException{
   Configuration conf = new Configuration();
   String hdfsOutput = "hdfs://localhost:9000/user/hadoop/output";
   String hdfsPath = "hdfs://localhost:9000/";
   Path path = new Path(hdfsOutput);
   FileSystem fs = FileSystem.get(URI.create(hdfsPath), conf);
   fs.deleteOnExit(path);
   fs.close();
   System.out.println("output文件已经删除");
 }

执行mapReduce程序

创建Mapper类和Reducer类

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{
     String line = value.toString();
     line = line.replace("\\", "");
     String regex = "性别：</span><span class=\"pt_detail\">(.*?)</span>";
     Pattern pattern = Pattern.compile(regex);
     Matcher matcher = pattern.matcher(line);
     while(matcher.find()){
       String term = matcher.group(1);
       word.set(term);
       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);
   }
 }

执行mapReduce程序

public static void runMapReduce(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> <out>");
     System.exit(2);
   }
   Job job = new Job(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);
   FileInputFormat.addInputPath(job, new Path(otherArgs[0]));
   FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));
   System.out.println("mapReduce 执行完毕！");
   System.exit(job.waitForCompletion(true)?0:1);

}

感谢阅读，希望能帮助到大家，谢谢大家对本站的支持！

来源：http://blog.csdn.net/qq_30843221/article/details/54429792