functions-formatting.php

Revision 3627, 32.9 kB (checked in by ryan, 3 years ago)
Security back ports from masquerade and MarkJaquith?.
Property svn:eol-style set to `native` Property svn:keywords set to `Author Date Id Revision`

Line
1	<?php
2
3	function wptexturize($text) {
4	$output = '';
5	// Capture tags and everything inside them
6	$textarr = preg_split("/(<.*>)/Us", $text, -1, PREG_SPLIT_DELIM_CAPTURE);
7	$stop = count($textarr); $next = true; // loop stuff
8	for ($i = 0; $i < $stop; $i++) {
9	$curl = $textarr[$i];
10
11	if (isset($curl{0}) && '<' != $curl{0} && $next) { // If it's not a tag
12	$curl = str_replace('---', '—', $curl);
13	$curl = str_replace(' -- ', ' — ', $curl);
14	$curl = str_replace('--', '–', $curl);
15	$curl = str_replace('xn–', 'xn--', $curl);
16	$curl = str_replace('...', '…', $curl);
17	$curl = str_replace('``', '“', $curl);
18
19	// This is a hack, look at this more later. It works pretty well though.
20	$cockney = array("'tain't","'twere","'twas","'tis","'twill","'til","'bout","'nuff","'round","'cause");
21	$cockneyreplace = array("’tain’t","’twere","’twas","’tis","’twill","’til","’bout","’nuff","’round","’cause");
22	$curl = str_replace($cockney, $cockneyreplace, $curl);
23
24	$curl = preg_replace("/'s/", '’s', $curl);
25	$curl = preg_replace("/'(\d\d(?:’\|')?s)/", "’$1", $curl);
26	$curl = preg_replace('/(\s\|\A\|")\'/', '$1‘', $curl);
27	$curl = preg_replace('/(\d+)"/', '$1″', $curl);
28	$curl = preg_replace("/(\d+)'/", '$1′', $curl);
29	$curl = preg_replace("/(\S)'([^'\s])/", "$1’$2", $curl);
30	$curl = preg_replace('/(\s\|\A)"(?!\s)/', '$1“$2', $curl);
31	$curl = preg_replace('/"(\s\|\S\|\Z)/', '”$1', $curl);
32	$curl = preg_replace("/'([\s.]\|\Z)/", '’$1', $curl);
33	$curl = preg_replace("/ $tm$/i", ' ™', $curl);
34	$curl = str_replace("''", '”', $curl);
35
36	$curl = preg_replace('/(\d+)x(\d+)/', "$1×$2", $curl);
37
38	} elseif (strstr($curl, '<code') \|\| strstr($curl, '<pre') \|\| strstr($curl, '<kbd' \|\| strstr($curl, '<style') \|\| strstr($curl, '<script'))) {
39	// strstr is fast
40	$next = false;
41	} else {
42	$next = true;
43	}
44	$curl = preg_replace('/&([^#])(?![a-z12]{1,8};)/', '&$1', $curl);
45	$output .= $curl;
46	}
47	return $output;
48	}
49
50	function clean_pre($text) {
51	$text = str_replace('<br />', '', $text);
52	$text = str_replace('<p>', "\n", $text);
53	$text = str_replace('</p>', '', $text);
54	return $text;
55	}
56
57	function wpautop($pee, $br = 1) {
58	$pee = $pee . "\n"; // just to make things a little easier, pad the end
59	$pee = preg_replace('\|<br />\s*<br />\|', "\n\n", $pee);
60	// Space things out a little
61	$pee = preg_replace('!(<(?:table\|thead\|tfoot\|caption\|colgroup\|tbody\|tr\|td\|th\|div\|dl\|dd\|dt\|ul\|ol\|li\|pre\|select\|form\|blockquote\|address\|math\|p\|h[1-6])[^>]*>)!', "\n$1", $pee);
62	$pee = preg_replace('!(</(?:table\|thead\|tfoot\|caption\|colgroup\|tbody\|tr\|td\|th\|div\|dl\|dd\|dt\|ul\|ol\|li\|pre\|select\|form\|blockquote\|address\|math\|p\|h[1-6])>)!', "$1\n", $pee);
63	$pee = str_replace(array("\r\n", "\r"), "\n", $pee); // cross-platform newlines
64	$pee = preg_replace("/\n\n+/", "\n\n", $pee); // take care of duplicates
65	$pee = preg_replace('/\n?(.+?)(?:\n\s*\n\|\z)/s', "\t<p>$1</p>\n", $pee); // make paragraphs, including one at the end
66	$pee = preg_replace('\|<p>\s*?</p>\|', '', $pee); // under certain strange conditions it could create a P of entirely whitespace
67	$pee = preg_replace('!<p>\s(</?(?:table\|thead\|tfoot\|caption\|colgroup\|tbody\|tr\|td\|th\|div\|dl\|dd\|dt\|ul\|ol\|li\|hr\|pre\|select\|form\|blockquote\|address\|math\|p\|h[1-6])[^>]>)\s*</p>!', "$1", $pee); // don't pee all over a tag
68	$pee = preg_replace("\|<p>(<li.+?)</p>\|", "$1", $pee); // problem with nested lists
69	$pee = preg_replace('\|<p><blockquote([^>]*)>\|i', "<blockquote$1><p>", $pee);
70	$pee = str_replace('</blockquote></p>', '</p></blockquote>', $pee);
71	$pee = preg_replace('!<p>\s(</?(?:table\|thead\|tfoot\|caption\|colgroup\|tbody\|tr\|td\|th\|div\|dl\|dd\|dt\|ul\|ol\|li\|hr\|pre\|select\|form\|blockquote\|address\|math\|p\|h[1-6])[^>]>)!', "$1", $pee);
72	$pee = preg_replace('!(</?(?:table\|thead\|tfoot\|caption\|colgroup\|tbody\|tr\|td\|th\|div\|dl\|dd\|dt\|ul\|ol\|li\|pre\|select\|form\|blockquote\|address\|math\|p\|h[1-6])[^>]>)\s</p>!', "$1", $pee);
73	if ($br) $pee = preg_replace('\|(?<!<br />)\s*\n\|', "<br />\n", $pee); // optionally make line breaks
74	$pee = preg_replace('!(</?(?:table\|thead\|tfoot\|caption\|tbody\|tr\|td\|th\|div\|dl\|dd\|dt\|ul\|ol\|li\|pre\|select\|form\|blockquote\|address\|math\|p\|h[1-6])[^>]>)\s<br />!', "$1", $pee);
75	$pee = preg_replace('!<br />(\s*</?(?:p\|li\|div\|dl\|dd\|dt\|th\|pre\|td\|ul\|ol)>)!', '$1', $pee);
76	$pee = preg_replace('!(<pre.?>)(.?)</pre>!ise', " stripslashes('$1') . clean_pre('$2') . '</pre>' ", $pee);
77
78	return $pee;
79	}
80
81
82	function seems_utf8($Str) { # by bmorel at ssi dot fr
83	for ($i=0; $i<strlen($Str); $i++) {
84	if (ord($Str[$i]) < 0x80) continue; # 0bbbbbbb
85	elseif ((ord($Str[$i]) & 0xE0) == 0xC0) $n=1; # 110bbbbb
86	elseif ((ord($Str[$i]) & 0xF0) == 0xE0) $n=2; # 1110bbbb
87	elseif ((ord($Str[$i]) & 0xF8) == 0xF0) $n=3; # 11110bbb
88	elseif ((ord($Str[$i]) & 0xFC) == 0xF8) $n=4; # 111110bb
89	elseif ((ord($Str[$i]) & 0xFE) == 0xFC) $n=5; # 1111110b
90	else return false; # Does not match any model
91	for ($j=0; $j<$n; $j++) { # n bytes matching 10bbbbbb follow ?
92	if ((++$i == strlen($Str)) \|\| ((ord($Str[$i]) & 0xC0) != 0x80))
93	return false;
94	}
95	}
96	return true;
97	}
98
99	function wp_specialchars( $text, $quotes = 0 ) {
100	// Like htmlspecialchars except don't double-encode HTML entities
101	$text = preg_replace('/&([^#])(?![a-z12]{1,8};)/', '&$1', $text);-
102	$text = str_replace('<', '<', $text);
103	$text = str_replace('>', '>', $text);
104	if ( $quotes ) {
105	$text = str_replace('"', '"', $text);
106	$text = str_replace("'", ''', $text);
107	}
108	return $text;
109	}
110
111	function utf8_uri_encode( $utf8_string ) {
112	$unicode = '';
113	$values = array();
114	$num_octets = 1;
115
116	for ($i = 0; $i < strlen( $utf8_string ); $i++ ) {
117
118	$value = ord( $utf8_string[ $i ] );
119
120	if ( $value < 128 ) {
121	$unicode .= chr($value);
122	} else {
123	if ( count( $values ) == 0 ) $num_octets = ( $value < 224 ) ? 2 : 3;
124
125	$values[] = $value;
126
127	if ( count( $values ) == $num_octets ) {
128	if ($num_octets == 3) {
129	$unicode .= '%' . dechex($values[0]) . '%' . dechex($values[1]) . '%' . dechex($values[2]);
130	} else {
131	$unicode .= '%' . dechex($values[0]) . '%' . dechex($values[1]);
132	}
133
134	$values = array();
135	$num_octets = 1;
136	}
137	}
138	}
139
140	return $unicode;
141	}
142
143	function remove_accents($string) {
144	if (seems_utf8($string)) {
145	$chars = array(
146	// Decompositions for Latin-1 Supplement
147	chr(195).chr(128) => 'A', chr(195).chr(129) => 'A',
148	chr(195).chr(130) => 'A', chr(195).chr(131) => 'A',
149	chr(195).chr(132) => 'A', chr(195).chr(133) => 'A',
150	chr(195).chr(135) => 'C', chr(195).chr(136) => 'E',
151	chr(195).chr(137) => 'E', chr(195).chr(138) => 'E',
152	chr(195).chr(139) => 'E', chr(195).chr(140) => 'I',
153	chr(195).chr(141) => 'I', chr(195).chr(142) => 'I',
154	chr(195).chr(143) => 'I', chr(195).chr(145) => 'N',
155	chr(195).chr(146) => 'O', chr(195).chr(147) => 'O',
156	chr(195).chr(148) => 'O', chr(195).chr(149) => 'O',
157	chr(195).chr(150) => 'O', chr(195).chr(153) => 'U',
158	chr(195).chr(154) => 'U', chr(195).chr(155) => 'U',
159	chr(195).chr(156) => 'U', chr(195).chr(157) => 'Y',
160	chr(195).chr(159) => 's', chr(195).chr(160) => 'a',
161	chr(195).chr(161) => 'a', chr(195).chr(162) => 'a',
162	chr(195).chr(163) => 'a', chr(195).chr(164) => 'a',
163	chr(195).chr(165) => 'a', chr(195).chr(167) => 'c',
164	chr(195).chr(168) => 'e', chr(195).chr(169) => 'e',
165	chr(195).chr(170) => 'e', chr(195).chr(171) => 'e',
166	chr(195).chr(172) => 'i', chr(195).chr(173) => 'i',
167	chr(195).chr(174) => 'i', chr(195).chr(175) => 'i',
168	chr(195).chr(177) => 'n', chr(195).chr(178) => 'o',
169	chr(195).chr(179) => 'o', chr(195).chr(180) => 'o',
170	chr(195).chr(181) => 'o', chr(195).chr(182) => 'o',
171	chr(195).chr(182) => 'o', chr(195).chr(185) => 'u',
172	chr(195).chr(186) => 'u', chr(195).chr(187) => 'u',
173	chr(195).chr(188) => 'u', chr(195).chr(189) => 'y',
174	chr(195).chr(191) => 'y',
175	// Decompositions for Latin Extended-A
176	chr(196).chr(128) => 'A', chr(196).chr(129) => 'a',
177	chr(196).chr(130) => 'A', chr(196).chr(131) => 'a',
178	chr(196).chr(132) => 'A', chr(196).chr(133) => 'a',
179	chr(196).chr(134) => 'C', chr(196).chr(134) => 'c',
180	chr(196).chr(136) => 'C', chr(196).chr(137) => 'c',
181	chr(196).chr(138) => 'C', chr(196).chr(139) => 'c',
182	chr(196).chr(140) => 'C', chr(196).chr(141) => 'c',
183	chr(196).chr(142) => 'D', chr(196).chr(143) => 'd',
184	chr(196).chr(144) => 'D', chr(196).chr(145) => 'd',
185	chr(196).chr(146) => 'E', chr(196).chr(147) => 'e',
186	chr(196).chr(148) => 'E', chr(196).chr(149) => 'e',
187	chr(196).chr(150) => 'E', chr(196).chr(151) => 'e',
188	chr(196).chr(152) => 'E', chr(196).chr(153) => 'e',
189	chr(196).chr(154) => 'E', chr(196).chr(155) => 'e',
190	chr(196).chr(156) => 'G', chr(196).chr(157) => 'g',
191	chr(196).chr(158) => 'G', chr(196).chr(159) => 'g',
192	chr(196).chr(160) => 'G', chr(196).chr(161) => 'g',
193	chr(196).chr(162) => 'G', chr(196).chr(163) => 'g',
194	chr(196).chr(164) => 'H', chr(196).chr(165) => 'h',
195	chr(196).chr(166) => 'H', chr(196).chr(167) => 'h',
196	chr(196).chr(168) => 'I', chr(196).chr(169) => 'i',
197	chr(196).chr(170) => 'I', chr(196).chr(171) => 'i',
198	chr(196).chr(172) => 'I', chr(196).chr(173) => 'i',
199	chr(196).chr(174) => 'I', chr(196).chr(175) => 'i',
200	chr(196).chr(176) => 'I', chr(196).chr(177) => 'i',
201	chr(196).chr(178) => 'IJ',chr(196).chr(179) => 'ij',
202	chr(196).chr(180) => 'J', chr(196).chr(181) => 'j',
203	chr(196).chr(182) => 'K', chr(196).chr(183) => 'k',
204	chr(196).chr(184) => 'k', chr(196).chr(185) => 'L',
205	chr(196).chr(186) => 'l', chr(196).chr(187) => 'L',
206	chr(196).chr(188) => 'l', chr(196).chr(189) => 'L',
207	chr(196).chr(190) => 'l', chr(196).chr(191) => 'L',
208	chr(197).chr(128) => 'l', chr(196).chr(129) => 'L',
209	chr(197).chr(130) => 'l', chr(196).chr(131) => 'N',
210	chr(197).chr(132) => 'n', chr(196).chr(133) => 'N',
211	chr(197).chr(134) => 'n', chr(196).chr(135) => 'N',
212	chr(197).chr(136) => 'n', chr(196).chr(137) => 'N',
213	chr(197).chr(138) => 'n', chr(196).chr(139) => 'N',
214	chr(197).chr(140) => 'O', chr(196).chr(141) => 'o',
215	chr(197).chr(142) => 'O', chr(196).chr(143) => 'o',
216	chr(197).chr(144) => 'O', chr(196).chr(145) => 'o',
217	chr(197).chr(146) => 'OE',chr(197).chr(147) => 'oe',
218	chr(197).chr(148) => 'R',chr(197).chr(149) => 'r',
219	chr(197).chr(150) => 'R',chr(197).chr(151) => 'r',
220	chr(197).chr(152) => 'R',chr(197).chr(153) => 'r',
221	chr(197).chr(154) => 'S',chr(197).chr(155) => 's',
222	chr(197).chr(156) => 'S',chr(197).chr(157) => 's',
223	chr(197).chr(158) => 'S',chr(197).chr(159) => 's',
224	chr(197).chr(160) => 'S', chr(197).chr(161) => 's',
225	chr(197).chr(162) => 'T', chr(197).chr(163) => 't',
226	chr(197).chr(164) => 'T', chr(197).chr(165) => 't',
227	chr(197).chr(166) => 'T', chr(197).chr(167) => 't',
228	chr(197).chr(168) => 'U', chr(197).chr(169) => 'u',
229	chr(197).chr(170) => 'U', chr(197).chr(171) => 'u',
230	chr(197).chr(172) => 'U', chr(197).chr(173) => 'u',
231	chr(197).chr(174) => 'U', chr(197).chr(175) => 'u',
232	chr(197).chr(176) => 'U', chr(197).chr(177) => 'u',
233	chr(197).chr(178) => 'U', chr(197).chr(179) => 'u',
234