Shulou(Shulou.com)06/03 Report--

Jai package

Org.apache.hadoop hadoop-core 1.2.1

After 2.x, it will be broken into some scattered packages, and there will be no core packages.

Code:

Package of package org.conan.myhadoop.mr;import java.io.IOException;import org.apache.hadoop.conf.Configuration;//org.apache.hadoop.mapred old system / / org.apache.hadoop.mapreduce package import org.apache.hadoop.conf.Configured;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 of new system Import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;import org.apache.hadoop.mapreduce.lib.input.TextInputFormat;import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;import org.apache.hadoop.util.Tool;import org.apache.hadoop.util.ToolRunner / * * ModuleMapReduce Class * simple comment * / public class ModuleMapReduce extends Configured implements Tool {/ * * ModuleMapper Class not only has the function of annotation, but also if you mouse over your annotation method, it will show the content of your comment. * * / public static class ModuleMapper extends Mapper {@ Override public void setup (Context context) throws IOException, InterruptedException {super.setup (context) @ Override public void map (LongWritable key, Text value, Context context) throws IOException, InterruptedException {/ / TODO} @ Override public void cleanup (Context context) throws IOException, InterruptedException {super.cleanup (context) }} / * * ModuleReducer Class * * / public static class ModuleReducer extends Reducer {@ Override public void setup (Context context) throws IOException, InterruptedException {/ / TODO Auto-generated method stub super.setup (context) @ Override protected void reduce (LongWritable key, Iterable value, Context context) throws IOException, InterruptedException {/ / TODO} @ Override protected void cleanup (Context context) throws IOException, InterruptedException {super.cleanup (context) }} / / Driver driver / / @ Override / / when implementing the interface, the JDK of keywords 1.5 and 1.7 will report errors, only 1.6 will not report errors public int run (String [] args) throws Exception {Job job = parseInputAndOutput (this, this.getConf (), args); / / 2.set job / / step 1:set input job.setInputFormatClass (TextInputFormat.class) / / step 3:set mappper class job.setMapperClass (ModuleMapper.class); / / step 4:set mapout key/value class job.setMapOutputKeyClass (LongWritable.class); job.setMapOutputValueClass (Text.class); / / step 5:set shuffle (sort,combiner,group) / / set sort job.setSortComparatorClass (LongWritable.Comparator.class) / / set combiner (optional,default is unset) must be a subclass of Reducer job.setCombinerClass (ModuleReducer.class); / / set grouping job.setGroupingComparatorClass (LongWritable.Comparator.class); / / step 6 set reducer class job.setReducerClass (ModuleReducer.class); / / step 7:set job output key/value class job.setOutputKeyClass (LongWritable.class); job.setOutputValueClass (Text.class) / / step 8:set output format job.setOutputFormatClass (FileOutputFormat.class); / / step 10: submit job Boolean isCompletion = job.waitForCompletion (true); / / submit job return isCompletion? 0: 1 } public Job parseInputAndOutput (Tool tool, Configuration conf, String [] args) throws IOException {/ / validity of input parameters if (args.length! = 2) {System.err.printf ("Usage:% s [generic options]\ n", tool .getClass (). GetSimpleName ()) / /% s represents the output string, that is, replacing% s ToolRunner.printGenericCommandUsage (System.err); return null;} / / 1.create job Job job = Job.getInstance (conf, this.getClass (). GetSimpleName ()); job.setJarByClass (ModuleMapReduce.class) / / step 2:set input path Path inputPath = new Path (args [0]); FileInputFormat.addInputPath (job, inputPath); / / step 9:set output path Path outputPath = new Path (args [0]); FileOutputFormat.setOutputPath (job, outputPath); return job;} public static void main (String [] args) {try {int status = ToolRunner.run (new ModuleMapReduce (), args) / / the return value is isCompletion? 0: 1 System.exit (status); / / System.exit (0) interrupts the operation of the virtual machine and exits the application. 0 means there is no abnormal normal exit. } catch (Exception e) {e.printStackTrace ();}

Inverted index code

The input file is as follows:

13588888888 112

13678987879 13509098987

18987655436 110

2543789 112

15699807656 110

011-678987 112

Description: each action has a telephone call record, and the number on the left (marked as a) is called to the number on the right (marked as b), separated by a space.

Request:

Output the above files in the following format:

110 18987655436 | 15699807656

112 13588888888 | 011-678987

13509098987 13678987879

Description: the number b is called on the left, and the number an of call b on the right is divided by "|"

Package org.conan.myhadoop.mr;import java.io.IOException;import java.text.DateFormat;import java.text.SimpleDateFormat;import java.util.Date;import org.apache.hadoop.conf.Configuration;import org.apache.hadoop.conf.Configured;import org.apache.hadoop.fs.Path;import org.apache.hadoop.io.*;import org.apache.hadoop.mapreduce.*;import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;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;public class ReverseIndex extends Configured implements Tool {enum Counter {LINESKIP, / / Line in error} public static class Map extends Mapper {public void map (LongWritable key, Text value, Context context) throws IOException, InterruptedException {String line = value.toString () / / read source data try {/ / data processing String [] lineSplit = line.split (""); String anum = lineSplit [0]; String bnum = lineSplit [1]; context.write (new Text (bnum), new Text (anum)) / / output} catch (java.lang.ArrayIndexOutOfBoundsException e) {context.getCounter (Counter.LINESKIP) .increment (1); / / error hang counter + 1 return;}} public static class Reduce extends Reducer {public void reduce (Text key, Iterable values, Context context) throws IOException, InterruptedException {String valueString String out = ""; for (Text value: values) {valueString = value.toString (); out + = valueString + "|"; System.out.println ("Ruduce:key=" + key + "value=" + value);} context.write (key, new Text (out)) } @ Override public int run (String [] args) throws Exception {Configuration conf = this.getConf (); Job job = new Job (conf, "ReverseIndex"); / / Task name job.setJarByClass (ReverseIndex.class); / / specify Class FileInputFormat.addInputPath (job, new Path (args [0])); / / enter path FileOutputFormat.setOutputPath (job, new Path (args [1])) / / output path job.setMapperClass (Map.class); / / call the above Map class as the Map task code job.setReducerClass (ReverseIndex.Reduce.class); / / call the above Reduce class as the Reduce task code job.setOutputFormatClass (TextOutputFormat.class); job.setOutputKeyClass (Text.class); / / specify the format job.setOutputValueClass (Text.class) of the output KEY / / specify the format of the output VALUE job.waitForCompletion (true); / / output task completion System.out.println ("task name:" + job.getJobName ()); System.out.println ("task success:" + (job.isSuccessful ()? "Yes": "No"); System.out.println ("enter number of lines:" + job.getCounters () .findCounter ("org.apache.hadoop.mapred.Task$Counter", "MAP_INPUT_RECORDS") .getValue ()) System.out.println ("output lines:" + job.getCounters () .findCounter ("org.apache.hadoop.mapred.Task$Counter", "MAP_OUTPUT_RECORDS") .getValue (); System.out.println ("skipped lines:" + job.getCounters () .findCounter (Counter.LINESKIP) .getValue () Return job.isSuccessful ()? 0: 1;} public static void main (String [] args) throws Exception {/ / determine whether the number of parameters is correct / / if there are no parameters, it will be displayed for program description if (args.length! = 2) {System.err.println ("); System.err.println (" Usage: ReverseIndex

"); System.err .println (" Example: hadoop jar ~ / ReverseIndex.jar hdfs://localhost:9000/in/telephone.txt hdfs://localhost:9000/out "); System.exit (- 1);} / / recording start time DateFormat formatter = new SimpleDateFormat (" yyyy-MM-dd HH:mm:ss "); Date start = new Date () / / run task int res = ToolRunner.run (new Configuration (), new ReverseIndex (), args); / / output task time Date end = new Date (); float time = (float) ((end.getTime ()-start.getTime ()) / 60000.0); System.out.println ("Task start:" + formatter.format (start)) System.out.println ("Task end:" + formatter.format (end)); System.out.println ("Task time:" + String.valueOf (time) + "minutes"); System.exit (res);}}

De-duplicating code

/ / Mapper task static class DDMap extends Mapper {private static Text line = new Text (); protected void map (LongWritable K1MagneText v1Magna context context) {line = v1; Text text = new Text (""); try {context.write (line,text);} catch (IOException e) {/ / TODO Auto-generated catch block e.printStackTrace () } catch (InterruptedException e) {/ / TODO Auto-generated catch block e.printStackTrace ();}};} / / Reducer task static class DDReduce extends Reducer {protected void reduce (Text K2Magic Iterable v2sMagna context context) {Text text = new Text (""); try {context.write (K2, text) } catch (IOException e) {/ / TODO Auto-generated catch block e.printStackTrace ();} catch (InterruptedException e) {/ / TODO Auto-generated catch block e.printStackTrace ();};}

Reference article

A classic MapReduce template code, inverted index (ReverseIndex)

Http://blog.itpub.net/26400547/viewspace-1214945/

Explain in detail the application scenario of data deduplication and inverted indexing by MapReduce.

Http://www.tuicool.com/articles/emi6Fb

Welcome to subscribe "Shulou Technology Information " to get latest news, interesting things and hot topics in the IT industry, and controls the hottest and latest Internet news, technology news and IT industry trends.