MapReduce Sort Output

The Hadoop map is a continuous learning ~ with output auto-sorting function ~

Importorg.apache.hadoop.conf.Configuration;Importorg.apache.hadoop.conf.Configured;ImportOrg.apache.hadoop.fs.Path;Importorg.apache.hadoop.io.IntWritable;ImportOrg.apache.hadoop.io.Text;ImportOrg.apache.hadoop.mapreduce.Job;ImportOrg.apache.hadoop.mapreduce.Mapper;ImportOrg.apache.hadoop.mapreduce.Reducer;ImportOrg.apache.hadoop.mapreduce.lib.input.FileInputFormat;ImportOrg.apache.hadoop.mapreduce.lib.input.TextInputFormat;ImportOrg.apache.hadoop.mapreduce.lib.output.FileOutputFormat;ImportOrg.apache.hadoop.util.Tool;ImportOrg.apache.hadoop.util.ToolRunner;Importjava.io.IOException; Public classSortextendsConfiguredImplementsTool {
Here the map converts the input value to the Intwritable type as the output key Public Static classMapextendsMapper<object,text,intwritable,intwritable> {        Private Staticintwritable data =Newintwritable ();  Public voidMap (Object key,text value,context Context)throwsioexception,interruptedexception {String line=value.tostring (); System.out.println ("Line" +Line );            Data.set (Integer.parseint (line)); Context.write (data,NewIntwritable (1)); }}//reduce copies the input key to the output value, and then determines the number of key outputs based on the number of elements in the input value-list Public Static classReduceextendsReducer<intwritable,intwritable,intwritable,intwritable> {
Global linenum to represent Key's precedencePrivate StaticIntwritable LineNum =NewIntwritable (1);  Public voidReduce (intwritable key,iterable<intwritable> values,context Context)throwsioexception,interruptedexception{ for(intwritable val:values) {context.write (Linenum,key); System.out.println (LineNum+"    "+key); LineNum=NewIntwritable (Linenum.get () +1); }        }    }     Public  intRun (string[] args)throwsexception{Configuration AAA=NewConfiguration (); Job Job=job.getinstance (AAA); String inputpaths= "/usr/local/idea-ic-139.1117.1/hadoop/out/datainput/sort.txt"; String OutputPath= "/usr/local/idea-ic-139.1117.1/hadoop/out/dataout/"; Job.setjarbyclass (Sort.class); Job.setjobname ("Sort"); Job.setoutputkeyclass (Text.class); Job.setoutputvalueclass (intwritable.class); Job.setmapperclass (Map.class); Job.setreducerclass (Reduce.class); Fileinputformat.setinputpaths (Job,NewPath (inputpaths)); Fileoutputformat.setoutputpath (Job,NewPath (OutputPath)); Job.setoutputkeyclass (intwritable.class); Job.setoutputvalueclass (intwritable.class); BooleanSuccess = Job.waitforcompletion (true); returnSuccess? 0:1; }     Public Static voidMain (string[] args)throwsexception{intret = Toolrunner.run (NewSort (), args);    System.exit (ret); }}

MapReduce Sort Output