fork download
copy 
  1. //printenv
  2. // JAVA_HOME=/usr/java/jdk1.7.0_67-cloudera
  3. // PATH=/usr/java/jdk1.7.0_67-cloudera/bin
  4. // export HADOOP_CLASSPATH=${JAVA_HOME}/lib/tools.jar
  5.  
  6. // hadoop com.sun.tools.javac.Main WordCount3.java
  7. // jar cf WordCount2.jar WordCount2*.class
  8. // hadoop jar WordCount2.jar WordCount2 big.txt outWCBig
  9. // hadoop jar WordCount2.jar WordCount2 t8.shakespeare.txt outWCShake
  10.  
  11. // t8.shakespeare
  12.  
  13. // Remove the previous results.
  14. // $ hadoop fs -rm -r -f /user/cloudera/wordcount/output
  15.  
  16.  
  17. import java.io.* ;
  18. import java.util.StringTokenizer;
  19.  
  20. import org.apache.hadoop.conf.Configured;
  21. import org.apache.hadoop.conf.Configuration ;
  22. import org.apache.hadoop.fs.Path;
  23. import org.apache.hadoop.io.IntWritable;
  24. import org.apache.hadoop.io.LongWritable;
  25. import org.apache.hadoop.io.Text;
  26. import org.apache.hadoop.mapreduce.jobWordCount;
  27. import org.apache.hadoop.mapreduce.Mapper;
  28. import org.apache.hadoop.mapreduce.Reducer;
  29. import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
  30. import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
  31. import org.apache.hadoop.mapreduce.lib.chain.ChainMapper;
  32. import org.apache.hadoop.util.GenericOptionsParser;
  33. import org.apache.hadoop.util.Tool;
  34. import org.apache.hadoop.util.ToolRunner;
  35.  
  36.  
  37. import org.apache.hadoop.mapreduce.Job;
  38. import org.apache.hadoop.mapreduce.lib.input.SequenceFileInputFormat;
  39. import org.apache.hadoop.mapreduce.lib.input.TextInputFormat;
  40. import org.apache.hadoop.mapreduce.lib.output.SequenceFileOutputFormat;
  41. import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
  42. import org.apache.hadoop.mapreduce.lib.partition.InputSampler;
  43. import org.apache.hadoop.mapreduce.lib.partition.TotalOrderPartitioner;
  44.  
  45. public class WordCount2 extends Configured implements Tool
  46. {
  47. 	private static final Logger LOG = Logger.getLogger(WordCount2.class);
  48.  
  49. 	public static void main(String[] args) throws Exception {
  50.         int exitCode = ToolRunner.run(new WordCount2(), args);
  51.         System.exit(exitCode);
  52.     }
  53.  
  54. 	public static boolean isNullOrEmpty(String str) {
  55.         if(str != null && !str.trim().isEmpty())
  56.             return false;
  57.         return true;
  58.     }
  59.  
  60.  
  61.   public static class PunctuationMapper 
  62.       extends Mapper<Object, Text, NullWritable, Text> {
  63.  
  64.     private Text punctd = new Text();  
  65. 	//private static fin//al String PunctuationMarks="\"\'\\[\\]\\\\!$&@~#%:;`<>(){}/!|?*-+=^,.";
  66. 	private static final String PunctuationMarks="\"\\[\\]\\\\!$&@~#%:;`<>(){}/!|?*-+=^,.";
  67. 	//DON'T
  68.     public void map(Object key, Text value, Context context) throws IOException, InterruptedException {
  69.       String word= value.toString();
  70. 	  word=word.replaceAll("-", "");
  71. 	  //word=word.replaceAll("'", "");
  72. 	  word=word.replaceAll("["+PunctuationMarks+"]", " ");
  73. 	  //word = word.replaceAll("[^a-zA-Z\\s+]", " ").toLowerCase();
  74. 	  //word = curr.trim();
  75. 	  //punctd.set(Regex.Replace(word.toString(),[^\w\d\s-]," "));
  76. 	  //String word_punc=word.replaceAll("[^\\w\\d\\s-]", " ");
  77. 	  //word=word.replace( "/\s\s+/g", "" );//     ->  390ms
  78. 	  punctd.set(word);      
  79. 	  context.write(new IntWritable(1), punctd);	  
  80. 	  }
  81.   } 
  82.  
  83.    public static class TrimMapper 
  84.       extends Mapper<Object, Text, NullWritable, Text> {
  85.  
  86.     private Text trimd = new Text();  	
  87.     public void map(Object key, Text value, Context context) throws IOException, InterruptedException {
  88.       String word= value.toString().trim();	  	  
  89. 	  //word=word.replaceAll( "/\s\s+/g", "" );//     ->  390ms
  90.       word=word.replaceAll("^ +| +$|( )+", "$1");
  91. 	  trimd.set(word);      
  92. 	  context.write(new IntWritable(1), trimd);	  
  93. 	  }
  94.   }   
  95.    public static class LowerCaseMapper 
  96.       extends Mapper<Object, Text, NullWritable, Text> {
  97.  
  98.     private Text lowercased = new Text();
  99.     public void map(Object key, Text value, Context context) throws IOException, InterruptedException {
  100.         lowercased.set(value.toString().toLowerCase());
  101.         context.write(new IntWritable(1), lowercased);
  102.     }
  103.   }  
  104.  
  105.   public static class TokenizerMapper
  106.        extends Mapper<IntWritable, Text, Text, IntWritable>{
  107.  
  108. 	private static final java.util.regex.Pattern WORD_BOUNDARY = java.util.regex.Pattern.compile("\\s");
  109.  
  110. 	private final static IntWritable one = new IntWritable(1);
  111.     private Text word = new Text();
  112.  
  113.     public void map(IntWritable key, Text lineText, Context context
  114.                     ) throws IOException, InterruptedException {
  115. 	  String line = lineText.toString();
  116.       Text currentWord = new Text();
  117.       for (String word : WORD_BOUNDARY.split(line)) {
  118.         if (WordCount2.isNullOrEmpty(word)) {
  119.             continue;
  120.         }
  121.             currentWord = new Text(word);
  122.             context.write(currentWord,one);
  123.         }      
  124.     }
  125.   }
  126.  
  127.   public static class IntSumReducer
  128.        extends Reducer<Text,IntWritable,Text,IntWritable> {
  129.     private IntWritable result = new IntWritable();
  130.  
  131.     public void reduce(Text key_word, Iterable<IntWritable> counts,
  132.                        Context context
  133.                        ) throws IOException, InterruptedException {
  134.       int sum = 0;
  135.       for (IntWritable count : counts) {
  136.         sum += count.get();
  137.       }
  138.       result.set(sum);
  139.       context.write(key_word, result);
  140.     }
  141.   }
  142.   //////////////////////////////////////
  143.   public static class TopTenMapper extends Mapper<Object, Text, NullWritable, Text>
  144.     {
  145.         private TreeMap<Integer, Text> topN = new TreeMap<Integer, Text>(); //Collections.reverseOrder()
  146.  
  147.         private final static IntWritable one = new IntWritable(1);
  148.         private Text word = new Text();
  149.         public void map(Object key, Text value, Context context)
  150.                throws IOException, InterruptedException {
  151.             // (word, count) tuple
  152.             String[] words = value.toString().split("\t") ;
  153.                 if (words.length < 2) {
  154.                     return;
  155.             }
  156.  
  157.             topN.put(Integer.parseInt(words[1]), new Text(value));
  158.  
  159.             if (topN.size() > 10) {
  160.                     topN.remove(topN.firstKey());
  161. 					//topN.remove(topN.lastKey());
  162.             }
  163.         }	
  164.  
  165.  
  166.         @Override
  167.         protected void cleanup(Context context) throws IOException,
  168.                 InterruptedException {
  169.             for (Text t : topN.values()) {
  170.                 context.write(NullWritable.get(), t);
  171.             }
  172.         }
  173.     }
  174.  
  175.   public static class TopTenReducer extends
  176.             Reducer<NullWritable, Text, NullWritable, Text> {
  177.  
  178.         private TreeMap<Integer, Text> topN = new TreeMap<Integer, Text>();
  179.  
  180.         @Override
  181.         public void reduce(NullWritable key, Iterable<Text> values,
  182.                            Context context) throws IOException, InterruptedException {
  183.             for (Text value : values) {
  184.                 String[] words = value.toString().split("\t") ;
  185.  
  186.                 topN.put(Integer.parseInt(words[1]), new Text(value));
  187.  
  188.                 if (topN.size() > 10) {
  189.                     topN.remove(topN.firstKey());
  190.                 }
  191.             }
  192.  
  193.             for (Text word : topN.descendingMap().values()) {
  194.                 context.write(NullWritable.get(), word);
  195.             }
  196.         }
  197.     }
  198.   //////////////////////////////////////
  199.  
  200.     public int run(String[] args) throws Exception {
  201.         Configuration conf = getConf();
  202. 		//////////////
  203. 		FileSystem fs = FileSystem.get(conf);
  204. 		Path tmpPath = new Path("/w1/tmp");
  205. 		fs.delete(tmpPath, true);
  206.  
  207. 		Path inputPath = new Path(args[0]);
  208. 		//Path partitionFile = new Path(args[1] + "_partitions.lst");
  209. 		//Path outputStage = new Path(args[1] + "_staging");
  210. 		Path outputStage = new Path("/w1/tmp");
  211. 		Path outputOrder = new Path(args[1]);
  212. 		//////////////
  213.  
  214.         args = new GenericOptionsParser(conf, args).getRemainingArgs();
  215.  
  216. 		// creating a word count jobWordCount
  217.         jobWordCount jobWordCount = jobWordCount.getInstance(conf,"wordcount");
  218. 		//jobWordCount jobWordCount = jobWordCount.getInstance(getConf(), "wordcount");
  219.         //jobWordCount.setJarByClass(WordCount2.class);
  220. 		jobWordCount.setJarByClass(this.getClass());
  221.     // Use TextInputFormat, the default unless jobWordCount.setInputFormatClass is used
  222.  
  223. 		//public static class PunctuationMapper 
  224. 		//extends Mapper<Object, Text, NullWritable, Text> 
  225. 		Configuration punctuationMapperConf = new Configuration(false);
  226.         ChainMapper.addMapper(jobWordCount,
  227.           PunctuationMapper.class,
  228.           Object.class, Text.class,
  229.           IntWritable.class, Text.class,
  230.           punctuationMapperConf);
  231.  
  232. 		  //public static class TrimMapper 
  233.       //extends Mapper<Object, Text, NullWritable, Text>
  234. 		  Configuration trimMapperConf = new Configuration(false);
  235.         ChainMapper.addMapper(jobWordCount,
  236.           TrimMapper.class,
  237.           Object.class, Text.class,
  238.           IntWritable.class, Text.class,
  239.           trimMapperConf);
  240.  
  241. 		//public static class LowerCaseMapper 
  242.       //extends Mapper<Object, Text, NullWritable, Text> 		
  243. 		Configuration lowerCaseMapperConf = new Configuration(false);
  244.         ChainMapper.addMapper(jobWordCount,
  245.           LowerCaseMapper.class,
  246.           Object.class, Text.class,
  247. 		  //IntWritable.class, Text.class,
  248.           IntWritable.class, Text.class,
  249.           lowerCaseMapperConf);  
  250.  
  251. 		//public static class TokenizerMapper
  252.       // extends Mapper<IntWritable, Text, Text, IntWritable>
  253.         Configuration tokenizerConf = new Configuration(false);
  254.         ChainMapper.addMapper(jobWordCount,
  255.           TokenizerMapper.class,
  256.           IntWritable.class,Text.class,
  257.           Text.class, IntWritable.class,
  258.           tokenizerConf);
  259.  
  260. 		  //public static class IntSumReducer
  261.        //extends Reducer<Text,IntWritable,Text,IntWritable>	   
  262.         jobWordCount.setReducerClass(IntSumReducer.class);      
  263. 		jobWordCount.setOutputKeyClass(Text.class);
  264.         jobWordCount.setOutputValueClass(IntWritable.class);
  265.  
  266.         //FileInputFormat.addInputPath(jobWordCount, new Path(args[0]));
  267.         TextInputFormat.setInputPaths(jobWordCount, inputPath);
  268.  
  269. 		//FileOutputFormat.setOutputPath(jobWordCount, new Path(args[1]));
  270. 		FileOutputFormat.setOutputPath(jobWordCount, tmpPath);
  271. 		// Set the output format to a sequence file
  272. 		//jobWordCount.setOutputFormatClass(SequenceFileOutputFormat.class);
  273. 		//SequenceFileOutputFormat.setOutputPath(jobWordCount, outputStage);
  274.  
  275. 		int code = jobWordCount.waitForCompletion(true) ? 0 : 1;
  276.  
  277. 		if (code == 0) {
  278.  
  279. 			//Now that we have extracted column to sort
  280.  
  281. 			Job orderJob = new Job(conf, "TopWords");
  282. 			orderJob.setJarByClass(WordCount2.class);
  283.  
  284. 			// Here, use the identity mapper to output the key/value pairs in
  285. 			// the SequenceFile
  286. 			orderJob.setMapperClass(TopTenMapper.class);
  287. 			orderJob.setReducerClass(TopTenReducer.class);
  288. 			//********************
  289. 			//public static class TopTenMapper 
  290. 			//extends Mapper<Object, Text, NullWritable, Text>
  291.  
  292. 			jobB.setMapOutputKeyClass(NullWritable.class);
  293. 			jobB.setMapOutputValueClass(Text.class);
  294. 			//********************
  295. 			// Set the number of reduce tasks to an appropriate number for the
  296. 			// amount of data being sorted
  297. 			orderJob.setNumReduceTasks(10);
  298. 			// Use Hadoop's TotalOrderPartitioner class
  299. 			//orderJob.setPartitionerClass(TotalOrderPartitioner.class);
  300. 			// Set the partition file
  301. 			//TotalOrderPartitioner.setPartitionFile(orderJob.getConfiguration(),
  302. 			//		partitionFile);
  303. 			//********************
  304. 			//public static class TopTenReducer 
  305. 			//extends Reducer<NullWritable, Text, NullWritable, Text>
  306.  
  307. 			//orderJob.setOutputKeyClass(Text.class);
  308. 			//orderJob.setOutputValueClass(IntWritable.class);  
  309. 			//********************		
  310. 			orderJob.setOutputKeyClass(NullWritable.class);
  311. 			orderJob.setOutputValueClass(Text.class);
  312. 			//********************
  313. 			// Set the input to the previous job's output
  314. 			//orderJob.setInputFormatClass(SequenceFileInputFormat.class);
  315. 			orderJob.setInputFormatClass(KeyValueTextInputFormat.class);
  316. 			orderJob.setOutputFormatClass(TextOutputFormat.class);
  317.  
  318. 			//SequenceFileInputFormat.setInputPaths(orderJob, outputStage);
  319. 			// Set the output path to the command line parameter
  320. 			TextOutputFormat.setOutputPath(orderJob, outputOrder);
  321. 			// Set the separator to an empty string
  322. 			//orderJob.getConfiguration().set(
  323. 			//		"mapred.textoutputformat.separator", "");
  324. 			// Use the InputSampler to go through the output of the previous
  325. 			// job, sample it, and create the partition file
  326. 			//InputSampler.writePartitionFile(orderJob,
  327. 			//		new InputSampler.RandomSampler(.1, 10000));
  328. 			  FileInputFormat.setInputPaths(orderJob, tmpPath);
  329. 			  FileOutputFormat.setOutputPath(orderJob, new Path(args[1]));
  330.  
  331. 			  // Submit the job
  332. 			code = orderJob.waitForCompletion(true) ? 0 : 2;
  333. 		}
  334.  
  335. 		// Clean up the partition file and the staging directory
  336. 		// FileSystem.get(new Configuration()).delete(partitionFile, false);
  337. 		// FileSystem.get(new Configuration()).delete(outputStage, true);
  338. 		System.exit(code);
  339.  
  340.         return (jobWordCount.waitForCompletion(true) ? 0 : 1);
  341.     }   
  342. } 
  343.  
Success #stdin #stdout #stderr 0.01s 5304KB
comments (?)
stdin
copy 
Standard input is empty
stdout
copy 
Standard output is empty
stderr
copy 
Error: near line 1: near "/": syntax error
Error: near line 18: near "import": syntax error
Error: near line 20: near "import": syntax error
Error: near line 21: near "import": syntax error
Error: near line 22: near "import": syntax error
Error: near line 23: near "import": syntax error
Error: near line 24: near "import": syntax error
Error: near line 25: near "import": syntax error
Error: near line 26: near "import": syntax error
Error: near line 27: near "import": syntax error
Error: near line 28: near "import": syntax error
Error: near line 29: near "import": syntax error
Error: near line 30: near "import": syntax error
Error: near line 31: near "import": syntax error
Error: near line 32: near "import": syntax error
Error: near line 33: near "import": syntax error
Error: near line 34: near "import": syntax error
Error: near line 37: near "import": syntax error
Error: near line 38: near "import": syntax error
Error: near line 39: near "import": syntax error
Error: near line 40: near "import": syntax error
Error: near line 41: near "import": syntax error
Error: near line 42: near "import": syntax error
Error: near line 43: near "import": syntax error
Error: near line 45: near "public": syntax error
Error: near line 49: near "public": syntax error
Error: near line 51: near "System": syntax error
Error: near line 52: unrecognized token: "}"
Error: near line 57: near "return": syntax error
Error: near line 58: unrecognized token: "}"
Error: near line 65: near "/": syntax error
Error: near line 70: near "word": syntax error
Error: near line 71: near "/": syntax error
Error: near line 72: near "word": syntax error
Error: near line 73: near "/": syntax error
Error: near line 74: near "/": syntax error
Error: near line 75: near "/": syntax error
Error: near line 76: near "/": syntax error
Error: near line 77: near "/": syntax error
Error: near line 79: near "context": syntax error
Error: near line 80: unrecognized token: "}"
Error: near line 87: near "public": syntax error
Error: near line 89: near "/": syntax error
Error: near line 91: near "trimd": syntax error
Error: near line 92: near "context": syntax error
Error: near line 93: unrecognized token: "}"
Error: near line 99: near "public": syntax error
Error: near line 101: near "context": syntax error
Error: near line 102: unrecognized token: "}"
Error: near line 110: near "private": syntax error
Error: near line 111: near "private": syntax error
Error: near line 113: near "public": syntax error
Error: near line 116: near "Text": syntax error
Error: near line 117: near "for": syntax error
Error: near line 120: unrecognized token: "}"
Error: near line 122: near "context": syntax error
Error: near line 123: unrecognized token: "}"
Error: near line 131: near "public": syntax error
Error: near line 135: near "for": syntax error
Error: near line 137: unrecognized token: "}"
Error: near line 139: near "context": syntax error
Error: near line 140: unrecognized token: "}"
Error: near line 148: near "private": syntax error
Error: near line 149: near "public": syntax error
Error: near line 153: near "if": syntax error
Error: near line 155: unrecognized token: "}"
Error: near line 159: near "if": syntax error
Error: near line 161: near "/": syntax error
Error: near line 162: unrecognized token: "}"
Error: near line 171: unrecognized token: "}"
Error: near line 180: near "@Override": syntax error
Error: near line 186: near "topN": syntax error
Error: near line 188: near "if": syntax error
Error: near line 190: unrecognized token: "}"
Error: near line 195: unrecognized token: "}"
Error: near line 202: near "/": syntax error
Error: near line 204: near "Path": syntax error
Error: near line 205: near "fs": syntax error
Error: near line 207: near "Path": syntax error
Error: near line 208: near "/": syntax error
Error: near line 209: near "/": syntax error
Error: near line 210: near "Path": syntax error
Error: near line 211: near "Path": syntax error
Error: near line 212: near "/": syntax error
Error: near line 216: near "/": syntax error
Error: near line 218: near "/": syntax error
Error: near line 219: near "/": syntax error
Error: near line 220: near "jobWordCount": syntax error
Error: near line 221: near "/": syntax error
Error: near line 226: near "ChainMapper": syntax error
Error: near line 232: near "/": syntax error
Error: near line 235: near "ChainMapper": syntax error
Error: near line 241: near "/": syntax error
Error: near line 244: near "ChainMapper": syntax error
Error: near line 251: near "/": syntax error
Error: near line 254: near "ChainMapper": syntax error
Error: near line 260: near "/": syntax error
Error: near line 263: near "jobWordCount": syntax error
Error: near line 264: near "jobWordCount": syntax error
Error: near line 266: near "/": syntax error
Error: near line 267: near "TextInputFormat": syntax error
Error: near line 269: near "/": syntax error
Error: near line 270: near "FileOutputFormat": syntax error
Error: near line 271: near "/": syntax error
Error: near line 273: near "/": syntax error
Error: near line 275: near "int": syntax error
Error: near line 277: near "if": syntax error
Error: near line 282: near "orderJob": syntax error
Error: near line 284: near "/": syntax error
Error: near line 287: near "orderJob": syntax error
Error: near line 288: near "/": syntax error
https://ideone.com/SEJclc
language:
SQLite (sqlite 3.27.2)
created:
8 days ago
visibility:
public

Share or Embed source code

Discover > Sphere Engine API

The brand new service which powers Ideone!

Discover > IDE Widget

Widget for compiling and running the source code in a web browser!