Re: Counting words in text file (Mirek Fidler -- : was Java - c++, IO)

I have a new java verion that is much faster than previous verion!
Try this verion for benchmarking..

My old verion with 40 meg file

C:\>java -server WordCount bible2.txt>log.txt
Time: 4797 ms

My new version with 40 meg file

C:\>java -server WordCount2 bible2.txt>log.txt
Time: 3125 ms

:) :) :)

The C++ verion with 40 meg bible2.txt

C:\>wc1 bible2.txt>log.txt
Time: 5390 ms

Pardon me while I laugh :))

Ha ha ha ha ha

The new verion below

-----
Also, if the folliwng doesn't work
source can be found here too
http://www.pastebin.ca/963017

//counts the words in a text file...
//combined effort: wlfshmn from #java on IRC
//Undernet and Razii
 
import java.io.*;
import java.util.*;
 
public final class WordCount2
{
 private static final Map<String, int[]> dictionary =
         new HashMap<String, int[]>(800000);
 private static int tWords = 0;
 private static int tLines = 0;
 private static long tBytes = 0;
 
 public static void main(final String[] args) throws Exception
 {
  System.out.println("Lines\tWords\tBytes\tFile\n");
  
  //TIME STARTS HERE final
  long start = System.currentTimeMillis();
  for (String arg : args)
  {
   File file = new File(arg);
   if (!file.isFile())
   {
    continue;
   }
   int numLines = 0;
   int numWords = 0;
   long numBytes = file.length();
   BufferedReader input = new BufferedReader(new
        InputStreamReader(new FileInputStream(arg),
             "ISO-8859-1"));
   StreamTokenizer st = new StreamTokenizer(input);
   st.ordinaryChar('/'); st.ordinaryChar('.');
   st.ordinaryChar('-'); st.ordinaryChar('"');
   st.ordinaryChar('\''); st.eolIsSignificant(true);
   
   while (st.nextToken() != StreamTokenizer.TT_EOF)
   {
    if (st.ttype == StreamTokenizer.TT_EOL)
    {
     numLines++;
    }
     else if (st.ttype == StreamTokenizer.TT_WORD)
     {
        numWords++;
        int[] count = dictionary.get(st.sval);
        if (count != null)
         { count[0]++;}
         else
         { dictionary.put(st.sval, new int[]{1});}
     }
  }
   System.out.println( numLines + "\t" + numWords + "\t" + numBytes +
"\t" + arg);
   tLines += numLines;
   tWords += numWords;
   tBytes += numBytes;
  }
  
  //only converting it to TreepMap so the result
  //appear ordered, I could have
  //moved this part down to printing phase
  //(i.e. not include it in time).
  TreeMap<String, int[] > sort = new TreeMap<String, int[]>
(dictionary);
  
  //TIME ENDS HERE final
  long end = System.currentTimeMillis();
  
  System.out.println("---------------------------------------");
  if (args.length > 1)
  {
  System.out.println(tLines + "\t" + tWords + "\t" + tBytes +
"\tTotal");
   System.out.println("---------------------------------------");
  }
  for (Map.Entry<String, int[]> pairs : sort.entrySet())
  {
   System.out.println(pairs.getValue()[0] + "\t" + pairs.getKey());
  }
     System.out.println("Time: " + (end - start) + " ms");
 }
}