我想了解一个java代码。 (Java的基本知识)如何在下面的代码中生成对象?
这里的是
WordCountMapper类
package com.company;
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;
public class WordCountMapper extends Mapper<LongWritable, Text, Text, IntWritable> {
@Override
public void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
String line = value.toString();
for (String word : line.split(" ")) {
if (word.length() > 0) {
context.write(new Text(word), new IntWritable(1));
}
}
映射类
package org.apache.hadoop.mapreduce;
import java.io.IOException;
import org.apache.hadoop.classification.InterfaceAudience.Public;
import org.apache.hadoop.classification.InterfaceStability.Stable;
@InterfaceAudience.Public
@InterfaceStability.Stable
public class Mapper<KEYIN, VALUEIN, KEYOUT, VALUEOUT> {
public Mapper() {
}
protected void setup(Mapper<KEYIN, VALUEIN, KEYOUT, VALUEOUT>.Context context)
throws IOException, InterruptedException {
}
protected void map(KEYIN key, VALUEIN value, Mapper<KEYIN, VALUEIN, KEYOUT, VALUEOUT>.Context context)
throws IOException, InterruptedException {
context.write(key, value);
}
protected void cleanup(Mapper<KEYIN, VALUEIN, KEYOUT, VALUEOUT>.Context context)
throws IOException, InterruptedException {
}
public void run(Mapper<KEYIN, VALUEIN, KEYOUT, VALUEOUT>.Context context) throws IOException, InterruptedException {
setup(context);
while (context.nextKeyValue()) {
map(context.getCurrentKey(), context.getCurrentValue(), context);
}
cleanup(context);
}
public abstract class Context implements MapContext<KEYIN, VALUEIN, KEYOUT, VALUEOUT> {
public Context() {
}
}
}
主要方法类
package com.company;
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;
public class WordCount {
public static void main(String[] args) throws Exception {
if(args.length !=2){
System.err.println("Invalid Command");
System.err.println("Usage: WordCount <input path> <output path>");
System.exit(0);
}
Configuration conf = new Configuration();
Job job = new Job(conf, "wordcount");
job.setJarByClass(WordCount.class);
FileInputFormat.addInputPath(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, new Path(args[1]));
job.setMapperClass(WordCountMapper.class);
job.setReducerClass(WordCountReducer.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
}
我的疑问是字计数类如何文本值进入所有脑干?我的意思是它的一个对象,但是在它生成的地方,主类方法没有实例化Text类的实例。
这意味着什么 - ,我从来没有低于格式
public class Mapper<KEYIN, VALUEIN, KEYOUT, VALUEOUT>
{
任何建议,如建立课前看到了这一点?
这份工作,我认为你是在问两个问题被创建。由于语法错误,您的代码不会生成。 – nicomp
您的代码也不可读,因为它没有正确缩进。 –
@nicomp,可能不会建立起来,但这里只是试图理解文本价值是如何产生的? – JonyLinux