Last active
September 6, 2022 14:01
-
-
Save bagder/dac962c022171a212c54221afc4b99d2 to your computer and use it in GitHub Desktop.
speedparse -- bechmark the the libcurl URL parser
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
/*************************************************************************** | |
* _ _ ____ _ | |
* Project ___| | | | _ \| | | |
* / __| | | | |_) | | | |
* | (__| |_| | _ <| |___ | |
* \___|\___/|_| \_\_____| | |
* | |
* Copyright (C) 1998 - 2022, Daniel Stenberg, <[email protected]>, 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 <curl/curl.h> | |
static const char *list[] = { | |
"https://user:[email protected]/get?this=and#but frag then", | |
"https://user:[email protected]/get?this=and what", | |
"https://user:[email protected]/ge t?this=and-what", | |
"https://user:pass [email protected]/get?this=and-what", | |
"https://u ser:[email protected]/get?this=and-what", | |
"imap://user:pass;opt ion@server/path", | |
"htt ps://user:[email protected]/get?this=and-what", | |
"https://user:[email protected]/get?this=and what", | |
"https://user:[email protected]/ge t?this=and-what", | |
"https://user:pass [email protected]/get?this=and-what", | |
"https://u ser:[email protected]/get?this=and-what", | |
"https://user:[email protected]/ge t?this=and-what", | |
"[0:0:0:0:0:0:0:1]", | |
"[::1]", | |
"[::]", | |
"https://[::1]", | |
"user:[email protected]/color/#green?no-red", | |
"ftp.user:[email protected]/color/#green?no-red", | |
"file:/C:\\programs\\foo", | |
"file://C:\\programs\\foo", | |
"file:///C:\\programs\\foo", | |
"file://host.example.com/Share/path/to/file.txt", | |
"https://example.com/color/#green?no-red", | |
"https://example.com/color/#green#no-red", | |
"https://example.com/color/?green#no-red", | |
"https://example.com/#color/?green#no-red", | |
"https://example.#com/color/?green#no-red", | |
"http://[ab.be:1]/x", "", | |
"http://[ab.be]/x", "", | |
"http://a:b@/x", "", | |
"boing:80", | |
"http://[fd00:a41::50]:8080", | |
"http://[fd00:a41::50]/", | |
"http://[fd00:a41::50]", | |
"https://[::1%252]:1234", | |
"https://[fe80::20c:29ff:fe9c:409b%eth0]:1234", | |
"https://127.0.0.1:443", | |
"http://%3a:%3a@ex4mple/%3f+?+%3f+%23#+%23%3f%g7", | |
"http://%3a:%3a@ex4mple/%3f?%3f%35#%35%3f%g7", | |
"http://HO0_-st%41/", | |
"file://hello.html", | |
"http://HO0_-st/", | |
"imap://user:pass;option@server/path", | |
"http://user:pass;option@server/path", | |
"file:/hello.html", | |
"file:/h", | |
"file:/", | |
"file://127.0.0.1/hello.html", | |
"file:////hello.html", | |
"file:///hello.html", | |
"https://127.0.0.1", | |
"https://127.0.0.1", | |
"https://[::1]:1234", | |
"https://127abc.com", | |
"https:// example.com?check", "", | |
"https://e x a m p l e.com?check", "", | |
"https://example.com?check", | |
"https://example.com:65536", | |
"https://example.com:-1#moo", | |
"https://example.com:0#moo", | |
"https://example.com:01#moo", | |
"https://example.com:1#moo", | |
"http://example.com#moo", | |
"http://example.com", | |
"http://example.com/path/html", | |
"http://example.com/path/html?query=name", | |
"http://example.com/path/html?query=name#anchor", | |
"http://example.com:1234/path/html?query=name#anchor", | |
"http:///user:[email protected]:1234/path/html?query=name#anchor", | |
"https://user:[email protected]:1234/path/html?query=name#anchor", | |
"http://user:[email protected]:1234/path/html?query=name#anchor", | |
"http:/user:[email protected]:1234/path/html?query=name#anchor", | |
"http:////user:[email protected]:1234/path/html?query=name#anchor", | |
"http://example.com%40127.0.0.1/", | |
"http://example.com%21127.0.0.1/", | |
"http://example.com%3f127.0.0.1/", | |
"http://example.com%23127.0.0.1/", | |
"http://example.com%3a127.0.0.1/", | |
"http://example.com%09127.0.0.1/", | |
"http://example.com%2F127.0.0.1/", | |
"https://%this", | |
"https://h%c", | |
"https://%%%%%%", | |
"https://%41", | |
"https://%20", | |
"https://%41%0d", | |
"https://%25", | |
"https://_%c0_", | |
"https://_%c0_", | |
"https://16843009", | |
"https://0x7f.1", | |
"https://0177.1", | |
"https://0111.02.0x3", | |
"https://0xff.0xff.0377.255", | |
"https://1.0xffffff", | |
"https://+127.0.0.1", | |
"https://+127.0.0.1", | |
"https://127.-0.0.1", | |
"https://127.0. 1", | |
"https://1.0x1000000", | |
"https://1.2.3.256", | |
"https://1.2.3.4.5", | |
"https://1.2.0x100.3", | |
"https://4294967296", | |
"AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA://hostname/path", | |
"AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA://hostname/path", | |
"https://[fe80::20c:29ff:fe9c:409b%]:1234", | |
"https://[fe80::20c:29ff:fe9c:409b%25]:1234", | |
"https://[fe80::20c:29ff:fe9c:409b%eth0]:1234", | |
"https://[::%25fakeit]/moo", | |
"smtp.example.com/path/html", | |
"https.example.com/path/html", | |
"dict.example.com/path/html", | |
"pop3.example.com/path/html", | |
"ldap.example.com/path/html", | |
"imap.example.com/path/html", | |
"ftp.example.com/path/html", | |
"example.com/path/html", | |
"HTTP://test/", | |
"http://HO0_-st..~./", | |
"http:/@example.com: 123/", | |
"http:/@example.com:123 /", | |
"http:/@example.com:123a/", | |
"http://host/file\r", | |
"http://host/file\n\x03", | |
"htt\x02://host/file", | |
" http://host/file", | |
"imap://user:pass;word@host/file", | |
"http://user:pass;word@host/file", | |
"file:///file.txt#moo", | |
"file:////file.txt", | |
"file:///file.txt", | |
"file:./", | |
"http://example.com/hello/../here", | |
"http://example.com/hello/../here", | |
"http://example.com:80", | |
"tp://example.com/path/html", | |
"http://hello:[email protected]", | |
"http:/@example.com:123", | |
"http:/:[email protected]", | |
"http://[email protected]?#", | |
"http://[email protected]?", | |
"http://[email protected]#anchor", | |
"example.com/path/html", | |
"example.com/path/html", | |
"http://user:[email protected]:1234/path/html?query=name#anchor", | |
"http://example.com:1234/path/html?query=name#anchor", | |
"http://example.com/path/html?query=name#anchor", | |
"http://example.com/path/html?query=name", | |
"http://example.com/path/html", | |
"tp://example.com/path/html", | |
"custom-scheme://host?expected=test-good", | |
"custom-scheme://?expected=test-bad", | |
"custom-scheme://?expected=test-new-good", | |
"custom-scheme://host?expected=test-still-good", | |
"https://www.microsoft.com", | |
"https://opensource.org", | |
"https://www.google.com", | |
"https://www.yahoo.com", | |
"https://www.ibm.com", | |
"https://www.mysql.com", | |
"https://www.oracle.com", | |
"https://www.ripe.net", | |
"https://www.iana.org", | |
"https://www.amazon.com", | |
"https://www.netcraft.com", | |
"https://www.heise.de", | |
"https://www.chip.de", | |
"https://www.ca.com", | |
"https://www.cnet.com", | |
"https://www.mozilla.org", | |
"https://www.cnn.com", | |
"https://www.wikipedia.org", | |
"https://www.dell.com", | |
"https://www.hp.com", | |
"https://www.cert.org", | |
"https://www.mit.edu", | |
"https://www.nist.gov", | |
"https://www.ebay.com", | |
"https://www.playstation.com", | |
"https://www.uefa.com", | |
"https://www.ieee.org", | |
"https://www.apple.com", | |
"https://www.symantec.com", | |
"https://www.zdnet.com", | |
"https://www.fujitsu.com/global/", | |
"https://www.supermicro.com", | |
"https://www.hotmail.com", | |
"https://www.ietf.org", | |
"https://www.bbc.co.uk", | |
"https://news.google.com", | |
"https://www.foxnews.com", | |
"https://www.msn.com", | |
"https://www.wired.com", | |
"https://www.sky.com", | |
"https://www.usatoday.com", | |
"https://www.cbs.com", | |
"https://www.nbc.com/", | |
"https://slashdot.org", | |
"https://www.informationweek.com", | |
"https://apache.org", | |
"https://www.un.org", | |
"https://aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa.bbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbb/ccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccccc?ddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddddd#eeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeee", | |
NULL | |
}; | |
#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, 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]); | |
gettimeofday(&start, NULL); | |
//curl_dbg_memdebug("dump"); | |
for(l = 0; l < laps; l++) { | |
for(o = 0; options[o] != END_OF_LIST; o++) { | |
for(u = 0; list[u]; u++) { | |
CURLU *p = curl_url(); | |
curl_url_set(p, CURLUPART_URL, list[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, %.3f us/URL, %.3f URLs/sec\n", | |
count, (double)us/1000000.0, (double)us/count, count / (us/1000000.0)); | |
return 0; | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment