Geek Answers Handbook

Why is ruby ​​scanf so slow?

I am working on some text conversion procedures that parse time values ​​in different formats in Ruby. This procedure is growing in complexity, and I'm currently testing the best approach to this problem.

I am currently testing a use case scanf. What for? I always thought this was faster than regex, but what happened in Ruby? It was a lot slower!

What am I doing wrong?

Note. I am using ruby-1.9.2-p290 [x86_64] (MRI)

First Ruby Test:

require "scanf"
require 'benchmark'

def duration_in_seconds_regex(duration)
  if duration =~ /^\d{2,}\:\d{2}:\d{2}$/
    h, m, s = duration.split(":").map{ |n| n.to_i }
    h * 3600 + m * 60 + s
  end
end

def duration_in_seconds_scanf(duration)
  a = duration.scanf("%d:%d:%d")
  a[0] * 3600 + a[1] * 60 + a[2]
end

n = 500000
Benchmark.bm do |x|
  x.report { for i in 1..n; duration_in_seconds_scanf("00:10:30"); end }
end

Benchmark.bm do |x|
  x.report { for i in 1..n; duration_in_seconds_regex("00:10:30"); end }
end

This is what I got with the scanffirst and second regular expression:

      user     system      total        real
  95.020000   0.280000  95.300000 ( 96.364077)
       user     system      total        real
   2.820000   0.000000   2.820000 (  2.835170)

Second test using C:

#include <stdio.h>
#include <stdlib.h>
#include <time.h>
#include <sys/types.h>
#include <string.h>
#include <regex.h>

char *regexp(char *string, char *patrn, int *begin, int *end) {
    int i, w = 0, len;
    char *word = NULL;
    regex_t rgT;
    regmatch_t match;
    regcomp(&rgT, patrn, REG_EXTENDED);
    if ((regexec(&rgT, string, 1, &match, 0)) == 0) {
        *begin = (int) match.rm_so;
        *end = (int) match.rm_eo;
        len = *end - *begin;
        word = malloc(len + 1);
        for (i = *begin; i<*end; i++) {
            word[w] = string[i];
            w++;
        }
        word[w] = 0;
    }
    regfree(&rgT);
    return word;
}

int main(int argc, char** argv) {
    char * str = "00:01:30";
    int h, m, s;
    int i, b, e;
    float start_time, end_time, time_elapsed;
    regex_t regex;
    regmatch_t * pmatch;
    char msgbuf[100];
    char *pch;
    char *str2;
    char delims[] = ":";
    char *result = NULL;

    start_time = (float) clock() / CLOCKS_PER_SEC;
    for (i = 0; i < 500000; i++) {
        if (sscanf(str, "%d:%d:%d", &h, &m, &s) == 3) {
            s = h * 3600L + m * 60L + s;
        }
    }
    end_time = (float) clock() / CLOCKS_PER_SEC;
    time_elapsed = end_time - start_time;
    printf("sscanf_time (500k iterations): %.4f", time_elapsed);

    start_time = (float) clock() / CLOCKS_PER_SEC;
    for (i = 0; i < 500000; i++) {
        char * match = regexp(str, "[0-9]{2,}:[0-9]{2}:[0-9]{2}", &b, &e);
        if (strcmp(match, str) == 0) {
            str2 = (char*) malloc(sizeof (str));
            strcpy(str2, str);
            h = strtok(str2, delims);
            m = strtok(NULL, delims);
            s = strtok(NULL, delims);
            s = h * 3600L + m * 60L + s;
        }
    }
    end_time = (float) clock() / CLOCKS_PER_SEC;
    time_elapsed = end_time - start_time;
    printf("\n\nregex_time (500k iterations): %.4f", time_elapsed);

    return (EXIT_SUCCESS);
}

The results of the C code are obviously faster, and the regex results are slower than the results scanf, as expected:

sscanf_time (500k iterations): 0.1774

regex_time (500k iterations): 3.9692

, C , , , , Ruby - .

gist.

+5
2

, , Ruby - . "scanf.rb" Ruby scanf- C.

Ruby- scanf RegExp. , "% d", , C . , , / .

+4

, : scanf Ruby (scanf.rb), , 10 ( !). split, map, C.

+2

More articles:


All Articles