這篇文章主要介紹了hadoop中如何實(shí)現(xiàn)GenericWritable,具有一定借鑒價(jià)值,感興趣的朋友可以參考下,希望大家閱讀完這篇文章之后大有收獲,下面讓小編帶著大家一起了解一下。
創(chuàng)新互聯(lián)公司長(zhǎng)期為上千客戶提供的網(wǎng)站建設(shè)服務(wù),團(tuán)隊(duì)從業(yè)經(jīng)驗(yàn)10年,關(guān)注不同地域、不同群體,并針對(duì)不同對(duì)象提供差異化的產(chǎn)品和服務(wù);打造開(kāi)放共贏平臺(tái),與合作伙伴共同營(yíng)造健康的互聯(lián)網(wǎng)生態(tài)環(huán)境。為龍川企業(yè)提供專(zhuān)業(yè)的做網(wǎng)站、網(wǎng)站建設(shè),龍川網(wǎng)站改版等技術(shù)服務(wù)。擁有十載豐富建站經(jīng)驗(yàn)和眾多成功案例,為您定制開(kāi)發(fā)。
package com.test; import java.io.IOException; import java.util.Iterator; import java.util.StringTokenizer; import org.apache.hadoop.conf.Configuration; import org.apache.hadoop.conf.Configured; import org.apache.hadoop.fs.Path; import org.apache.hadoop.io.GenericWritable; import org.apache.hadoop.io.IntWritable; import org.apache.hadoop.io.LongWritable; import org.apache.hadoop.io.Text; import org.apache.hadoop.io.Writable; 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.KeyValueTextInputFormat; import org.apache.hadoop.mapreduce.lib.input.MultipleInputs; import org.apache.hadoop.mapreduce.lib.input.TextInputFormat; import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat; import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat; import org.apache.hadoop.util.Tool; import org.apache.hadoop.util.ToolRunner; /** * 業(yè)務(wù)場(chǎng)景: * 含有兩個(gè)文件,兩個(gè)文件中單詞之間的分隔方式不一樣,但是統(tǒng)計(jì)出單詞在兩個(gè)文件中公共出現(xiàn)的次數(shù) * * 文件來(lái)源1,逗號(hào)分隔text1.txt * hello,what * you,haha * 文件來(lái)源2,制表符分隔text2.txt * girl boy * father mother */ public class WordCountGenericWritable extends Configured implements Tool { public static class Map1 extends Mapper{ public void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException { String line = value.toString(); StringTokenizer st = new StringTokenizer(line, ","); while(st.hasMoreElements()) { context.write(new Text(st.nextElement().toString()), new MyGenericWritable(new LongWritable(1))); } } } public static class Map2 extends Mapper { public void map(Text key, Text value, Context context) throws IOException, InterruptedException { context.write(key, new MyGenericWritable(new Text("1"))); context.write(value, new MyGenericWritable(new Text("1"))); } } public static class Reduce extends Reducer { public void reduce(Text key, Iterable values, Context context) throws IOException, InterruptedException { int count = 0; Iterator it = values.iterator(); while(it.hasNext()) { MyGenericWritable myGw = it.next(); Writable value = myGw.get(); if(value instanceof LongWritable) { count = count + Long.valueOf(((LongWritable)value).get()).intValue(); } if(value instanceof Text) { count = count + Long.valueOf(((Text)value).toString()).intValue(); } } context.write(key, new IntWritable(count)); } } public int run(String[] args) throws IOException, InterruptedException, ClassNotFoundException { Configuration conf = this.getConf(); Job job = new Job(conf); job.setJobName(WordCountGenericWritable.class.getSimpleName()); job.setJarByClass(WordCountGenericWritable.class); MultipleInputs.addInputPath(job, new Path("hdfs://grid131:9000/text1.txt"), TextInputFormat.class, Map1.class); MultipleInputs.addInputPath(job, new Path("hdfs://grid131:9000/text2.txt"), KeyValueTextInputFormat.class, Map2.class); FileOutputFormat.setOutputPath(job, new Path(args[1])); job.setReducerClass(Reduce.class); job.setOutputFormatClass(TextOutputFormat.class); //當(dāng)map的輸出類(lèi)型和reduce的輸出類(lèi)型不一致的時(shí)候,需要單獨(dú)設(shè)置map輸出類(lèi)型 job.setMapOutputKeyClass(Text.class); job.setMapOutputValueClass(MyGenericWritable.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(IntWritable.class); job.waitForCompletion(true); return job.isSuccessful()?0:1; } public static void main(String[] args) throws Exception { int exit = ToolRunner.run(new WordCount(), args); System.exit(exit); } } class MyGenericWritable extends GenericWritable { public MyGenericWritable() { } public MyGenericWritable(LongWritable longWritable) { super.set(longWritable); } public MyGenericWritable(Text text) { super.set(text); } @Override protected Class extends Writable>[] getTypes() { return new Class[]{LongWritable.class, Text.class}; } }
感謝你能夠認(rèn)真閱讀完這篇文章,希望小編分享的“hadoop中如何實(shí)現(xiàn)GenericWritable”這篇文章對(duì)大家有幫助,同時(shí)也希望大家多多支持創(chuàng)新互聯(lián),關(guān)注創(chuàng)新互聯(lián)行業(yè)資訊頻道,更多相關(guān)知識(shí)等著你來(lái)學(xué)習(xí)!