JcDenis/cleanURLs
1
0
Fork 0
Code Issues Pull Requests Releases 3 Activity
d85b092318
cleanURLs/inc/class.cleanurls.php

234 lines
12 KiB
PHP
Raw Normal View History

first commit from cleanURLs 0.1.1
2023-01-11 20:00:01 +00:00
<?php
/**
release 1.2
2023-01-11 20:16:35 +00:00
* @brief cleanURLs, a plugin for Dotclear 2
*
* @package Dotclear
* @subpackage Plugin
*
* @author Pierre Rudloff and contributors
*
* @copyright Jean-Christian Denis
* @copyright GPL-3.0 https://www.gnu.org/licenses/gpl-3.0.html
*/
/**
first commit from cleanURLs 0.1.1
2023-01-11 20:00:01 +00:00
* Class to remove problematic characters from URLs
release 1.2
2023-01-11 20:16:35 +00:00
*
first commit from cleanURLs 0.1.1
2023-01-11 20:00:01 +00:00
* PHP Version 5
release 1.2
2023-01-11 20:16:35 +00:00
*
first commit from cleanURLs 0.1.1
2023-01-11 20:00:01 +00:00
* @category Plugin
* @package CleanURLs
* @author Pierre Rudloff <contact@rudloff.pro>
* @license http://www.gnu.org/licenses/gpl-3.0.html GNU General Public License
* @link http://rudloff.pro
* */
class CleanURLs
{
/**
* Check if a string is UTF-8
release 1.2
2023-01-11 20:16:35 +00:00
*
first commit from cleanURLs 0.1.1
2023-01-11 20:00:01 +00:00
* @param string $str String to check
release 1.2
2023-01-11 20:16:35 +00:00
*
first commit from cleanURLs 0.1.1
2023-01-11 20:00:01 +00:00
* @return bool
release 1.2
2023-01-11 20:16:35 +00:00
*
first commit from cleanURLs 0.1.1
2023-01-11 20:00:01 +00:00
* @author WordPress
* @license https://wordpress.org/about/gpl/ GPLv2
* */
release 1.2
2023-01-11 20:16:35 +00:00
public static function seemsUtf8($str)
first commit from cleanURLs 0.1.1
2023-01-11 20:00:01 +00:00
{
$length = strlen($str);
release 1.2
2023-01-11 20:16:35 +00:00
for ($i = 0; $i < $length; $i++) {
first commit from cleanURLs 0.1.1
2023-01-11 20:00:01 +00:00
$c = ord($str[$i]);
if ($c < 0x80) {
$n = 0; // 0bbbbbbb
} elseif (($c & 0xE0) == 0xC0) {
release 1.2
2023-01-11 20:16:35 +00:00
$n = 1; // 110bbbbb
first commit from cleanURLs 0.1.1
2023-01-11 20:00:01 +00:00
} elseif (($c & 0xF0) == 0xE0) {
release 1.2
2023-01-11 20:16:35 +00:00
$n = 2; // 1110bbbb
} elseif (($c & 0xF8) == 0xF0) {
$n = 3; // 11110bbb
first commit from cleanURLs 0.1.1
2023-01-11 20:00:01 +00:00
} elseif (($c & 0xFC) == 0xF8) {
release 1.2
2023-01-11 20:16:35 +00:00
$n = 4; // 111110bb
first commit from cleanURLs 0.1.1
2023-01-11 20:00:01 +00:00
} elseif (($c & 0xFE) == 0xFC) {
release 1.2
2023-01-11 20:16:35 +00:00
$n = 5; // 1111110b
first commit from cleanURLs 0.1.1
2023-01-11 20:00:01 +00:00
} else {
return false; // Does not match any model
}
release 1.2
2023-01-11 20:16:35 +00:00
for ($j = 0; $j < $n; $j++) { // n bytes matching 10bbbbbb follow ?
first commit from cleanURLs 0.1.1
2023-01-11 20:00:01 +00:00
if ((++$i == $length) || ((ord($str[$i]) & 0xC0) != 0x80)) {
return false;
}
}
}
release 1.2
2023-01-11 20:16:35 +00:00
first commit from cleanURLs 0.1.1
2023-01-11 20:00:01 +00:00
return true;
}
/**
* Converts all accent characters to ASCII characters.
*
* If there are no accent characters, then the string given is just returned.
*
* @param string $string Text that might have accent characters
release 1.2
2023-01-11 20:16:35 +00:00
*
first commit from cleanURLs 0.1.1
2023-01-11 20:00:01 +00:00
* @return string Filtered string with replaced "nice" characters.
release 1.2
2023-01-11 20:16:35 +00:00
*
first commit from cleanURLs 0.1.1
2023-01-11 20:00:01 +00:00
* @author WordPress
* @license https://wordpress.org/about/gpl/ GPLv2
*/
release 1.2
2023-01-11 20:16:35 +00:00
public static function removeAccents($string)
first commit from cleanURLs 0.1.1
2023-01-11 20:00:01 +00:00
{
if (!preg_match('/[\x80-\xff]/', $string)) {
return $string;
}
if (self::seemsUtf8($string)) {
release 1.2
2023-01-11 20:16:35 +00:00
$chars = [
// Decompositions for Latin-1 Supplement
chr(195) . chr(128) => 'A', chr(195) . chr(129) => 'A',
chr(195) . chr(130) => 'A', chr(195) . chr(131) => 'A',
chr(195) . chr(132) => 'A', chr(195) . chr(133) => 'A',
chr(195) . chr(135) => 'C', chr(195) . chr(136) => 'E',
chr(195) . chr(137) => 'E', chr(195) . chr(138) => 'E',
chr(195) . chr(139) => 'E', chr(195) . chr(140) => 'I',
chr(195) . chr(141) => 'I', chr(195) . chr(142) => 'I',
chr(195) . chr(143) => 'I', chr(195) . chr(145) => 'N',
chr(195) . chr(146) => 'O', chr(195) . chr(147) => 'O',
chr(195) . chr(148) => 'O', chr(195) . chr(149) => 'O',
chr(195) . chr(150) => 'O', chr(195) . chr(153) => 'U',
chr(195) . chr(154) => 'U', chr(195) . chr(155) => 'U',
chr(195) . chr(156) => 'U', chr(195) . chr(157) => 'Y',
chr(195) . chr(159) => 's', chr(195) . chr(160) => 'a',
chr(195) . chr(161) => 'a', chr(195) . chr(162) => 'a',
chr(195) . chr(163) => 'a', chr(195) . chr(164) => 'a',
chr(195) . chr(165) => 'a', chr(195) . chr(167) => 'c',
chr(195) . chr(168) => 'e', chr(195) . chr(169) => 'e',
chr(195) . chr(170) => 'e', chr(195) . chr(171) => 'e',
chr(195) . chr(172) => 'i', chr(195) . chr(173) => 'i',
chr(195) . chr(174) => 'i', chr(195) . chr(175) => 'i',
chr(195) . chr(177) => 'n', chr(195) . chr(178) => 'o',
chr(195) . chr(179) => 'o', chr(195) . chr(180) => 'o',
chr(195) . chr(181) => 'o', chr(195) . chr(182) => 'o',
chr(195) . chr(182) => 'o', chr(195) . chr(185) => 'u',
chr(195) . chr(186) => 'u', chr(195) . chr(187) => 'u',
chr(195) . chr(188) => 'u', chr(195) . chr(189) => 'y',
chr(195) . chr(191) => 'y',
// Decompositions for Latin Extended-A
chr(196) . chr(128) => 'A', chr(196) . chr(129) => 'a',
chr(196) . chr(130) => 'A', chr(196) . chr(131) => 'a',
chr(196) . chr(132) => 'A', chr(196) . chr(133) => 'a',
chr(196) . chr(134) => 'C', chr(196) . chr(135) => 'c',
chr(196) . chr(136) => 'C', chr(196) . chr(137) => 'c',
chr(196) . chr(138) => 'C', chr(196) . chr(139) => 'c',
chr(196) . chr(140) => 'C', chr(196) . chr(141) => 'c',
chr(196) . chr(142) => 'D', chr(196) . chr(143) => 'd',
chr(196) . chr(144) => 'D', chr(196) . chr(145) => 'd',
chr(196) . chr(146) => 'E', chr(196) . chr(147) => 'e',
chr(196) . chr(148) => 'E', chr(196) . chr(149) => 'e',
chr(196) . chr(150) => 'E', chr(196) . chr(151) => 'e',
chr(196) . chr(152) => 'E', chr(196) . chr(153) => 'e',
chr(196) . chr(154) => 'E', chr(196) . chr(155) => 'e',
chr(196) . chr(156) => 'G', chr(196) . chr(157) => 'g',
chr(196) . chr(158) => 'G', chr(196) . chr(159) => 'g',
chr(196) . chr(160) => 'G', chr(196) . chr(161) => 'g',
chr(196) . chr(162) => 'G', chr(196) . chr(163) => 'g',
chr(196) . chr(164) => 'H', chr(196) . chr(165) => 'h',
chr(196) . chr(166) => 'H', chr(196) . chr(167) => 'h',
chr(196) . chr(168) => 'I', chr(196) . chr(169) => 'i',
chr(196) . chr(170) => 'I', chr(196) . chr(171) => 'i',
chr(196) . chr(172) => 'I', chr(196) . chr(173) => 'i',
chr(196) . chr(174) => 'I', chr(196) . chr(175) => 'i',
chr(196) . chr(176) => 'I', chr(196) . chr(177) => 'i',
chr(196) . chr(178) => 'IJ',chr(196) . chr(179) => 'ij',
chr(196) . chr(180) => 'J', chr(196) . chr(181) => 'j',
chr(196) . chr(182) => 'K', chr(196) . chr(183) => 'k',
chr(196) . chr(184) => 'k', chr(196) . chr(185) => 'L',
chr(196) . chr(186) => 'l', chr(196) . chr(187) => 'L',
chr(196) . chr(188) => 'l', chr(196) . chr(189) => 'L',
chr(196) . chr(190) => 'l', chr(196) . chr(191) => 'L',
chr(197) . chr(128) => 'l', chr(197) . chr(129) => 'L',
chr(197) . chr(130) => 'l', chr(197) . chr(131) => 'N',
chr(197) . chr(132) => 'n', chr(197) . chr(133) => 'N',
chr(197) . chr(134) => 'n', chr(197) . chr(135) => 'N',
chr(197) . chr(136) => 'n', chr(197) . chr(137) => 'N',
chr(197) . chr(138) => 'n', chr(197) . chr(139) => 'N',
chr(197) . chr(140) => 'O', chr(197) . chr(141) => 'o',
chr(197) . chr(142) => 'O', chr(197) . chr(143) => 'o',
chr(197) . chr(144) => 'O', chr(197) . chr(145) => 'o',
chr(197) . chr(146) => 'OE',chr(197) . chr(147) => 'oe',
chr(197) . chr(148) => 'R',chr(197) . chr(149) => 'r',
chr(197) . chr(150) => 'R',chr(197) . chr(151) => 'r',
chr(197) . chr(152) => 'R',chr(197) . chr(153) => 'r',
chr(197) . chr(154) => 'S',chr(197) . chr(155) => 's',
chr(197) . chr(156) => 'S',chr(197) . chr(157) => 's',
chr(197) . chr(158) => 'S',chr(197) . chr(159) => 's',
chr(197) . chr(160) => 'S', chr(197) . chr(161) => 's',
chr(197) . chr(162) => 'T', chr(197) . chr(163) => 't',
chr(197) . chr(164) => 'T', chr(197) . chr(165) => 't',
chr(197) . chr(166) => 'T', chr(197) . chr(167) => 't',
chr(197) . chr(168) => 'U', chr(197) . chr(169) => 'u',
chr(197) . chr(170) => 'U', chr(197) . chr(171) => 'u',
chr(197) . chr(172) => 'U', chr(197) . chr(173) => 'u',
chr(197) . chr(174) => 'U', chr(197) . chr(175) => 'u',
chr(197) . chr(176) => 'U', chr(197) . chr(177) => 'u',
chr(197) . chr(178) => 'U', chr(197) . chr(179) => 'u',
chr(197) . chr(180) => 'W', chr(197) . chr(181) => 'w',
chr(197) . chr(182) => 'Y', chr(197) . chr(183) => 'y',
chr(197) . chr(184) => 'Y', chr(197) . chr(185) => 'Z',
chr(197) . chr(186) => 'z', chr(197) . chr(187) => 'Z',
chr(197) . chr(188) => 'z', chr(197) . chr(189) => 'Z',
chr(197) . chr(190) => 'z', chr(197) . chr(191) => 's',
// Euro Sign
chr(226) . chr(130) . chr(172) => 'E',
// GBP (Pound) Sign
chr(194) . chr(163) => ''];
first commit from cleanURLs 0.1.1
2023-01-11 20:00:01 +00:00
$string = strtr($string, $chars);
} else {
// Assume ISO-8859-1 if not UTF-8
release 1.2
2023-01-11 20:16:35 +00:00
$chars['in'] = chr(128) . chr(131) . chr(138) . chr(142) . chr(154) . chr(158)
. chr(159) . chr(162) . chr(165) . chr(181) . chr(192) . chr(193) . chr(194)
. chr(195) . chr(196) . chr(197) . chr(199) . chr(200) . chr(201) . chr(202)
. chr(203) . chr(204) . chr(205) . chr(206) . chr(207) . chr(209) . chr(210)
. chr(211) . chr(212) . chr(213) . chr(214) . chr(216) . chr(217) . chr(218)
. chr(219) . chr(220) . chr(221) . chr(224) . chr(225) . chr(226) . chr(227)
. chr(228) . chr(229) . chr(231) . chr(232) . chr(233) . chr(234) . chr(235)
. chr(236) . chr(237) . chr(238) . chr(239) . chr(241) . chr(242) . chr(243)
. chr(244) . chr(245) . chr(246) . chr(248) . chr(249) . chr(250) . chr(251)
. chr(252) . chr(253) . chr(255);
first commit from cleanURLs 0.1.1
2023-01-11 20:00:01 +00:00
release 1.2
2023-01-11 20:16:35 +00:00
$chars['out'] = 'EfSZszYcYuAAAAAACEEEEIIIINOOOOOOUUUUY' .
'aaaaaaceeeeiiiinoooooouuuuyy';
first commit from cleanURLs 0.1.1
2023-01-11 20:00:01 +00:00
release 1.2
2023-01-11 20:16:35 +00:00
$string = strtr($string, $chars['in'], $chars['out']);
$double_chars['in'] = [
first commit from cleanURLs 0.1.1
2023-01-11 20:00:01 +00:00
chr(140), chr(156), chr(198), chr(208), chr(222),
release 1.2
2023-01-11 20:16:35 +00:00
chr(223), chr(230), chr(240), chr(254),
];
$double_chars['out'] = [
'OE', 'oe', 'AE', 'DH', 'TH', 'ss', 'ae', 'dh', 'th',
];
first commit from cleanURLs 0.1.1
2023-01-11 20:00:01 +00:00
$string = str_replace(
release 1.2
2023-01-11 20:16:35 +00:00
$double_chars['in'],
$double_chars['out'],
$string
first commit from cleanURLs 0.1.1
2023-01-11 20:00:01 +00:00
);
}
return $string;
}
release 1.2
2023-01-11 20:16:35 +00:00
first commit from cleanURLs 0.1.1
2023-01-11 20:00:01 +00:00
/**
* Clean URLs from diacritics and punctuation
release 1.2
2023-01-11 20:16:35 +00:00
*
first commit from cleanURLs 0.1.1
2023-01-11 20:00:01 +00:00
* @param object $blog Current blog
* @param object $cur Cursor
release 1.2
2023-01-11 20:16:35 +00:00
*
first commit from cleanURLs 0.1.1
2023-01-11 20:00:01 +00:00
* @return void
* */
release 1.2
2023-01-11 20:16:35 +00:00
public static function clean($blog, $cur)
first commit from cleanURLs 0.1.1
2023-01-11 20:00:01 +00:00
{
$cur->post_url = self::removeAccents($cur->post_url);
release 1.2
2023-01-11 20:16:35 +00:00
$cur->post_url = strtr($cur->post_url, ',!.?;', '-----');
first commit from cleanURLs 0.1.1
2023-01-11 20:00:01 +00:00
}
}
Reference in New Issue Copy Permalink