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

From:

Razii <DONTwhatevere3e@hotmail.com>

Newsgroups:

comp.lang.c++,comp.lang.java.programmer

Date:

Sun, 30 Mar 2008 04:27:52 -0500

Message-ID:

<q5nuu31c8d4hiu569vqlm0n4p1bjl6kcod@4ax.com>

On Sun, 30 Mar 2008 04:12:52 -0500, Razii
<DONTwhatevere3e@hotmail.com> wrote:

C:\>WCUPP bible2.txt
Time: 843 ms

Gosh! that's fast. Just for fun, I tried this:

C:\>WCUPP bible2.txt bible2.txt bible2.txt bible2.txt bible2.txt
bible2.txt

Time: 4937 ms

C:\>java -server WordCount2 bible2.txt bible2.txt bible2.txt
bible2.txt bible2.txt

Time: 14375 ms

U++ is almost 3 times faster!

At least when compared to VC++

C:\>wc1 bible2.txt bible2.txt bible2.txt bible2.txt bible2.txt

Time: 28515 ms

My version is twice faster :) I am waiting for C++ gurus to show me
C++ version that uses standard library and is faster than my version.

And I am on Windows and was using this. only thing I changed was added
internal timer

--------
#include <Core/Core.h>

using namespace Upp;

#include <ctime>

int main(int argc, const char *argv[])

{

    int n;

    VectorMap<String, int> map;

    Cout() << " lines words bytes file\n";

    //TIME STARTS HERE
    clock_t start=clock();

    int total_lines = 0;

    int total_words = 0;

    int total_bytes = 0;

    for(int i = 1; i < argc; i++) {

        String f = LoadFile(argv[i]);

        int lines = 0;

        int words = 0;

        const char *q = f;

        for(;;) {

            int c = *q;

            if(IsAlpha(c)) {

                const char *b = q++;

                while(IsAlNum(*q)) q++;

                map.GetAdd(String(b, q), 0)++;

                words++;

            }

            else {

                if(!c) break;

                if(c == '\n')

                    ++lines;

                q++;

            }

        }

        Cout() << Format("%8d%8d%8d %s\n", lines, words, f.GetCount(),
argv[i]);

        total_lines += lines;

        total_words += words;

        total_bytes += f.GetCount();

    }

    Vector<int> order = GetSortOrder(map.GetKeys());

    //TIME ENDS HERE
    clock_t end=clock();

    Cout() << Format("--------------------------------------%8d%8d%8d
total\n", total_lines, total_words, total_bytes);

    for(int i = 0; i < order.GetCount(); i++)

        Cout() << map.GetKey(order[i]) << ": " << map[order[i]] <<
'\n';

      Cout()<<"Time: " <<
          double(end-start)/CLOCKS_PER_SEC * 1000 << " ms\n";

    return 0;

}