measure libcurl URL parsing speed

speedparse.c

/***************************************************************************
 *                                  _   _ ____  _
 *  Project                     ___| | | |  _ \| |
 *                             / __| | | | |_) | |
 *                            | (__| |_| |  _ <| |___
 *                             \___|\___/|_| \_\_____|
 *
 * Copyright (C) Daniel Stenberg, <daniel@haxx.se>, et al.
 *
 * This software is licensed as described in the file COPYING, which
 * you should have received as part of this distribution. The terms
 * are also available at https://curl.se/docs/copyright.html.
 *
 * You may opt to use, copy, modify, merge, publish, distribute and/or sell
 * copies of the Software, and permit persons to whom the Software is
 * furnished to do so, under the terms of the COPYING file.
 *
 * This software is distributed on an "AS IS" basis, WITHOUT WARRANTY OF ANY
 * KIND, either express or implied.
 *
 * SPDX-License-Identifier: curl
 *
 ***************************************************************************/

#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <sys/stat.h>
#include <curl/curl.h>

#define FILENAME "URLs"

void *mem;
char **urls;
size_t url_num;
size_t url_alloc;

static void load_urls()
{
  struct stat st;
  size_t memsize;
  size_t left;
  FILE *fp;
  char *ptr;

  stat(FILENAME, &st);
  memsize = st.st_size;
  mem = malloc(memsize + 1);

  fp = fopen(FILENAME, "rb");
  fread(mem, memsize, 1, fp);

  for(ptr = mem, left = memsize; left; ) {
    char *nl;

    if(url_alloc == url_num) {
      if(!url_alloc) {
        url_alloc = 10000;
      }
      url_alloc *= 2;
      urls = realloc(urls, url_alloc * sizeof(char *));
    }

    urls[url_num++] = ptr;
    nl = memchr(ptr, '\n', left);
    if(!nl)
      break;
    *nl++ = 0;
    left -= nl - ptr;
    ptr = nl;
  }
  printf("Loaded %u URLs from %s\n", url_num, FILENAME);
}


#define END_OF_LIST 0xffffff

const static int options[] = {
  CURLU_DEFAULT_PORT,
  CURLU_NO_DEFAULT_PORT,
  CURLU_DEFAULT_SCHEME,
  CURLU_NON_SUPPORT_SCHEME,
  CURLU_ALLOW_SPACE,
  CURLU_GUESS_SCHEME,
  CURLU_PATH_AS_IS,
  CURLU_DISALLOW_USER,
  END_OF_LIST
};


int main(int argc, char **argv)
{
  int l, o = 0, u;
  int count = 0;
  struct timeval start;
  struct timeval end;
  time_t diff;
  long us;
  int laps = 100;

  if(argc > 1)
    laps = atoi(argv[1]);

  load_urls();
  gettimeofday(&start, NULL);

#if DEBUG
  if(argc > 2)
    curl_dbg_memdebug("dump");
#endif
  for(l = 0; l < laps; l++) {
//    for(o = 0; options[o] != END_OF_LIST; o++) {
      for(u = 0; u < url_num; u++) {
        CURLU *p = curl_url();
        curl_url_set(p, CURLUPART_URL, urls[u], options[o]);
        curl_url_cleanup(p);
        count++;
      }
//    }
  }
  gettimeofday(&end, NULL);
  diff = end.tv_sec-start.tv_sec;
  us = diff * 1000000 + end.tv_usec-start.tv_usec;
  printf("%d URLs in %.5f secs, %.1f ns/URL, %.3f URLs/sec\n",
         count, (double)us/1000000.0, (double)us*1000/count, count / (us/1000000.0));
  return 0;
}