Hadoop中利用自身类实现json格式转换为对象。

我就是我 2022-06-06 02:16 131阅读 0赞

假如在大数据中我们遇到了下面JSON格式的数据，我们想统计每部电影rate的综合。比较正规的做法是通过json解析成为对象的格式。虽然我们可以通过JSON-Simple导入jar包的方式处理，但实际上最方便的还是利用

hadoop自身  org.codehaus.jackson.map.ObjectMapper;类直接处理最为简单

{"movie":"1193","rate":"5","timeStamp":"978300760","uid":"1"}
    {"movie":"661","rate":"3","timeStamp":"978302109","uid":"1"}
    {"movie":"914","rate":"3","timeStamp":"978301968","uid":"1"}
    {"movie":"3408","rate":"4","timeStamp":"978300275","uid":"1"}
    {"movie":"2355","rate":"5","timeStamp":"978824291","uid":"1"}
    {"movie":"1197","rate":"3","timeStamp":"978302268","uid":"1"}

首先你需要定义一个javabean用来存储数据，这个bean需要实现Writable接口，因为网络直接传输对象是需要序列化的。

不了解序列化的同学，可以复习一下java序列化的知识。

package com.mre.moviecount;
    
    import java.io.DataInput;
    import java.io.DataOutput;
    import java.io.IOException;
    
    import org.apache.hadoop.io.Writable;
    
    public class MovieBean implements Writable{
    	private long movie;
    	private long rate;
    	private long timeStamp;
    	private long uid;
    	
    	public MovieBean(){}
    	public MovieBean(long movie,long rate){
    		this.movie=movie;
    		this.rate = rate;
    	}
    	public long getMovie() {
    		return movie;
    	}
    	public void setMovie(long movie) {
    		this.movie = movie;
    	}
    	public long getRate() {
    		return rate;
    	}
    	public void setRate(long rate) {
    		this.rate = rate;
    	}
    	public long gettimeStamp() {
    		return timeStamp;
    	}
    	public void settimeStamp(long timeStamp) {
    		this.timeStamp = timeStamp;
    	}
    	public long getUid() {
    		return uid;
    	}
    	public void setUid(long uid) {
    		this.uid = uid;
    	}
    	
    	@Override
    	public void write(DataOutput out) throws IOException {
    		//把对象序列化的过程
    		out.writeLong(movie);
    		out.writeLong(rate);
    		out.writeLong(timeStamp);
    		out.writeLong(uid);
    		
    	}
    	@Override
    	public void readFields(DataInput in) throws IOException {
    		//把把序列化的对象读取到内存中
    		movie = in.readLong();
    	    rate =in.readLong();
    		timeStamp =in.readLong();
    		uid=in.readLong();
    	}
    	
    	
    	@Override
    	public String toString() {
    		return "movie：" + movie + ", rate=" + rate;
    	}
    	
    }

然后就是正常的流程mapper和reducer来实现具体的机能。

package com.mre.moviecount;
    
    import java.io.IOException;
    
    import org.apache.hadoop.fs.Path;
    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.output.FileOutputFormat;
    import org.codehaus.jackson.map.ObjectMapper;
    
    public class RateCount {
    	public static class MyMapper extends Mapper<Object, Text, LongWritable, MovieBean> {
    
    		protected void map(Object key, Text value,	Context context) throws IOException, InterruptedException {
    			String line = value.toString();	
    			ObjectMapper om = new ObjectMapper();//把读取的json转化为对象
    			MovieBean moviebean = om.readValue(line, MovieBean.class);
    			//把movie对象和和id放入map处理   ※可以直接放rate，
    			context.write(new LongWritable(moviebean.getMovie()), moviebean);
    		}
    		
    	}
    	
    	public static class MyReducer extends Reducer<LongWritable, MovieBean, LongWritable, MovieBean> {
    
    		@Override
    		protected void reduce(LongWritable key, Iterable<MovieBean> values, Context context) 
    					throws IOException, InterruptedException {
    				
    				long count =0;
    				for(MovieBean mb:values){
    					count+=mb.getRate();//把movie为单位的rate累加
    				}
    				
    				//我们把count和movie存入对象，最终把对象输出到hdfs的文件中
    				//输出的格式就是我们在MovieBean中的toString方法定义的格式。
    				MovieBean moviebean = new MovieBean(key.get(),count);
    				context.write(key, moviebean);
    		}
    		
    	}
    	
    	public static void main(String[] args) throws Exception{
    		Job job = Job.getInstance();
    		job.setJarByClass(RateCount.class);
    		job.setMapperClass(MyMapper.class);
    		job.setReducerClass(MyReducer.class); 
    		
    //		job.setMapOutputKeyClass(Text.class);
    //		job.setMapOutputValueClass(NullWritable.class);
    		
    		job.setOutputKeyClass(LongWritable.class);
    		job.setOutputValueClass(MovieBean.class);
    		
    		FileInputFormat.addInputPath(job, new Path("hdfs://192.168.32.30:9000/input/movie.json" ));
    		
    		FileOutputFormat.setOutputPath(job, new Path("hdfs://192.168.32.30:9000/output6"));
    		job.waitForCompletion(true);
    	}
    }

最后输出的结果

379	movie：379, rate=1260
    380	movie：380, rate=5088
    381	movie：381, rate=688
    382	movie：382, rate=798
    383	movie：383, rate=882
    384	movie：384, rate=116
    385	movie：385, rate=34
    386	movie：386, rate=78
    387	movie：387, rate=280
    388	movie：388, rate=353
    389	movie：389, rate=74
    390	movie：390, rate=209
    391	movie：391, rate=131
    392	movie：392, rate=70
    393	movie：393, rate=195
    394	movie：394, rate=66
    396	movie：396, rate=4