|
1
|
|
|
<?php |
|
2
|
|
|
|
|
3
|
|
|
/* |
|
4
|
|
|
htmLawed 1.1.17, 11 March 2014 |
|
5
|
|
|
Copyright Santosh Patnaik |
|
6
|
|
|
Dual licensed with LGPL 3 and GPL 2+ |
|
7
|
|
|
A PHP Labware internal utility; www.bioinformatics.org/phplabware/internal_utilities/htmLawed |
|
8
|
|
|
|
|
9
|
|
|
See htmLawed_README.txt/htm |
|
10
|
|
|
*/ |
|
11
|
|
|
|
|
12
|
|
|
function htmLawed($t, $C=1, $S=array()){ |
|
|
|
|
|
|
13
|
|
|
$C = is_array($C) ? $C : array(); |
|
14
|
|
|
if(!empty($C['valid_xhtml'])){ |
|
15
|
|
|
$C['elements'] = empty($C['elements']) ? '*-center-dir-font-isindex-menu-s-strike-u' : $C['elements']; |
|
16
|
|
|
$C['make_tag_strict'] = isset($C['make_tag_strict']) ? $C['make_tag_strict'] : 2; |
|
17
|
|
|
$C['xml:lang'] = isset($C['xml:lang']) ? $C['xml:lang'] : 2; |
|
18
|
|
|
} |
|
19
|
|
|
// config eles |
|
20
|
|
|
$e = array('a'=>1, 'abbr'=>1, 'acronym'=>1, 'address'=>1, 'applet'=>1, 'area'=>1, 'b'=>1, 'bdo'=>1, 'big'=>1, 'blockquote'=>1, 'br'=>1, 'button'=>1, 'caption'=>1, 'center'=>1, 'cite'=>1, 'code'=>1, 'col'=>1, 'colgroup'=>1, 'dd'=>1, 'del'=>1, 'dfn'=>1, 'dir'=>1, 'div'=>1, 'dl'=>1, 'dt'=>1, 'em'=>1, 'embed'=>1, 'fieldset'=>1, 'font'=>1, 'form'=>1, 'h1'=>1, 'h2'=>1, 'h3'=>1, 'h4'=>1, 'h5'=>1, 'h6'=>1, 'hr'=>1, 'i'=>1, 'iframe'=>1, 'img'=>1, 'input'=>1, 'ins'=>1, 'isindex'=>1, 'kbd'=>1, 'label'=>1, 'legend'=>1, 'li'=>1, 'map'=>1, 'menu'=>1, 'noscript'=>1, 'object'=>1, 'ol'=>1, 'optgroup'=>1, 'option'=>1, 'p'=>1, 'param'=>1, 'pre'=>1, 'q'=>1, 'rb'=>1, 'rbc'=>1, 'rp'=>1, 'rt'=>1, 'rtc'=>1, 'ruby'=>1, 's'=>1, 'samp'=>1, 'script'=>1, 'select'=>1, 'small'=>1, 'span'=>1, 'strike'=>1, 'strong'=>1, 'sub'=>1, 'sup'=>1, 'table'=>1, 'tbody'=>1, 'td'=>1, 'textarea'=>1, 'tfoot'=>1, 'th'=>1, 'thead'=>1, 'tr'=>1, 'tt'=>1, 'u'=>1, 'ul'=>1, 'var'=>1); // 86/deprecated+embed+ruby |
|
21
|
|
|
if(!empty($C['safe'])){ |
|
22
|
|
|
unset($e['applet'], $e['embed'], $e['iframe'], $e['object'], $e['script']); |
|
23
|
|
|
} |
|
24
|
|
|
$x = !empty($C['elements']) ? str_replace(array("\n", "\r", "\t", ' '), '', $C['elements']) : '*'; |
|
25
|
|
|
if($x == '-*'){$e = array();} |
|
26
|
|
|
elseif(strpos($x, '*') === false){$e = array_flip(explode(',', $x));} |
|
27
|
|
|
else{ |
|
28
|
|
|
if(isset($x[1])){ |
|
29
|
|
|
preg_match_all('`(?:^|-|\+)[^\-+]+?(?=-|\+|$)`', $x, $m, PREG_SET_ORDER); |
|
30
|
|
|
for($i=count($m); --$i>=0;){$m[$i] = $m[$i][0];} |
|
31
|
|
|
foreach($m as $v){ |
|
|
|
|
|
|
32
|
|
|
if($v[0] == '+'){$e[substr($v, 1)] = 1;} |
|
33
|
|
|
if($v[0] == '-' && isset($e[($v = substr($v, 1))]) && !in_array('+'. $v, $m)){unset($e[$v]);} |
|
34
|
|
|
} |
|
35
|
|
|
} |
|
36
|
|
|
} |
|
37
|
|
|
$C['elements'] =& $e; |
|
38
|
|
|
// config attrs |
|
39
|
|
|
$x = !empty($C['deny_attribute']) ? str_replace(array("\n", "\r", "\t", ' '), '', $C['deny_attribute']) : ''; |
|
40
|
|
|
$x = array_flip((isset($x[0]) && $x[0] == '*') ? explode('-', $x) : explode(',', $x. (!empty($C['safe']) ? ',on*' : ''))); |
|
41
|
|
|
if(isset($x['on*'])){ |
|
42
|
|
|
unset($x['on*']); |
|
43
|
|
|
$x += array('onblur'=>1, 'onchange'=>1, 'onclick'=>1, 'ondblclick'=>1, 'onfocus'=>1, 'onkeydown'=>1, 'onkeypress'=>1, 'onkeyup'=>1, 'onmousedown'=>1, 'onmousemove'=>1, 'onmouseout'=>1, 'onmouseover'=>1, 'onmouseup'=>1, 'onreset'=>1, 'onselect'=>1, 'onsubmit'=>1); |
|
44
|
|
|
} |
|
45
|
|
|
$C['deny_attribute'] = $x; |
|
46
|
|
|
// config URL |
|
47
|
|
|
$x = (isset($C['schemes'][2]) && strpos($C['schemes'], ':')) ? strtolower($C['schemes']) : 'href: aim, feed, file, ftp, gopher, http, https, irc, mailto, news, nntp, sftp, ssh, telnet; *:file, http, https'; |
|
48
|
|
|
$C['schemes'] = array(); |
|
49
|
|
|
foreach(explode(';', str_replace(array(' ', "\t", "\r", "\n"), '', $x)) as $v){ |
|
50
|
|
|
$x = $x2 = null; list($x, $x2) = explode(':', $v, 2); |
|
51
|
|
|
if($x2){$C['schemes'][$x] = array_flip(explode(',', $x2));} |
|
52
|
|
|
} |
|
53
|
|
|
if(!isset($C['schemes']['*'])){$C['schemes']['*'] = array('file'=>1, 'http'=>1, 'https'=>1,);} |
|
54
|
|
|
if(!empty($C['safe']) && empty($C['schemes']['style'])){$C['schemes']['style'] = array('!'=>1);} |
|
55
|
|
|
$C['abs_url'] = isset($C['abs_url']) ? $C['abs_url'] : 0; |
|
56
|
|
|
if(!isset($C['base_url']) or !preg_match('`^[a-zA-Z\d.+\-]+://[^/]+/(.+?/)?$`', $C['base_url'])){ |
|
|
|
|
|
|
57
|
|
|
$C['base_url'] = $C['abs_url'] = 0; |
|
58
|
|
|
} |
|
59
|
|
|
// config rest |
|
60
|
|
|
$C['and_mark'] = empty($C['and_mark']) ? 0 : 1; |
|
61
|
|
|
$C['anti_link_spam'] = (isset($C['anti_link_spam']) && is_array($C['anti_link_spam']) && count($C['anti_link_spam']) == 2 && (empty($C['anti_link_spam'][0]) or hl_regex($C['anti_link_spam'][0])) && (empty($C['anti_link_spam'][1]) or hl_regex($C['anti_link_spam'][1]))) ? $C['anti_link_spam'] : 0; |
|
|
|
|
|
|
62
|
|
|
$C['anti_mail_spam'] = isset($C['anti_mail_spam']) ? $C['anti_mail_spam'] : 0; |
|
63
|
|
|
$C['balance'] = isset($C['balance']) ? (bool)$C['balance'] : 1; |
|
64
|
|
|
$C['cdata'] = isset($C['cdata']) ? $C['cdata'] : (empty($C['safe']) ? 3 : 0); |
|
65
|
|
|
$C['clean_ms_char'] = empty($C['clean_ms_char']) ? 0 : $C['clean_ms_char']; |
|
66
|
|
|
$C['comment'] = isset($C['comment']) ? $C['comment'] : (empty($C['safe']) ? 3 : 0); |
|
67
|
|
|
$C['css_expression'] = empty($C['css_expression']) ? 0 : 1; |
|
68
|
|
|
$C['direct_list_nest'] = empty($C['direct_list_nest']) ? 0 : 1; |
|
69
|
|
|
$C['hexdec_entity'] = isset($C['hexdec_entity']) ? $C['hexdec_entity'] : 1; |
|
70
|
|
|
$C['hook'] = (!empty($C['hook']) && function_exists($C['hook'])) ? $C['hook'] : 0; |
|
71
|
|
|
$C['hook_tag'] = (!empty($C['hook_tag']) && function_exists($C['hook_tag'])) ? $C['hook_tag'] : 0; |
|
72
|
|
|
$C['keep_bad'] = isset($C['keep_bad']) ? $C['keep_bad'] : 6; |
|
73
|
|
|
$C['lc_std_val'] = isset($C['lc_std_val']) ? (bool)$C['lc_std_val'] : 1; |
|
74
|
|
|
$C['make_tag_strict'] = isset($C['make_tag_strict']) ? $C['make_tag_strict'] : 1; |
|
75
|
|
|
$C['named_entity'] = isset($C['named_entity']) ? (bool)$C['named_entity'] : 1; |
|
76
|
|
|
$C['no_deprecated_attr'] = isset($C['no_deprecated_attr']) ? $C['no_deprecated_attr'] : 1; |
|
77
|
|
|
$C['parent'] = isset($C['parent'][0]) ? strtolower($C['parent']) : 'body'; |
|
78
|
|
|
$C['show_setting'] = !empty($C['show_setting']) ? $C['show_setting'] : 0; |
|
79
|
|
|
$C['style_pass'] = empty($C['style_pass']) ? 0 : 1; |
|
80
|
|
|
$C['tidy'] = empty($C['tidy']) ? 0 : $C['tidy']; |
|
81
|
|
|
$C['unique_ids'] = isset($C['unique_ids']) ? $C['unique_ids'] : 1; |
|
82
|
|
|
$C['xml:lang'] = isset($C['xml:lang']) ? $C['xml:lang'] : 0; |
|
83
|
|
|
|
|
84
|
|
|
if(isset($GLOBALS['C'])){$reC = $GLOBALS['C'];} |
|
85
|
|
|
$GLOBALS['C'] = $C; |
|
86
|
|
|
$S = is_array($S) ? $S : hl_spec($S); |
|
87
|
|
|
if(isset($GLOBALS['S'])){$reS = $GLOBALS['S'];} |
|
88
|
|
|
$GLOBALS['S'] = $S; |
|
89
|
|
|
|
|
90
|
|
|
$t = preg_replace('`[\x00-\x08\x0b-\x0c\x0e-\x1f]`', '', $t); |
|
91
|
|
|
if($C['clean_ms_char']){ |
|
92
|
|
|
$x = array("\x7f"=>'', "\x80"=>'€', "\x81"=>'', "\x83"=>'ƒ', "\x85"=>'…', "\x86"=>'†', "\x87"=>'‡', "\x88"=>'ˆ', "\x89"=>'‰', "\x8a"=>'Š', "\x8b"=>'‹', "\x8c"=>'Œ', "\x8d"=>'', "\x8e"=>'Ž', "\x8f"=>'', "\x90"=>'', "\x95"=>'•', "\x96"=>'–', "\x97"=>'—', "\x98"=>'˜', "\x99"=>'™', "\x9a"=>'š', "\x9b"=>'›', "\x9c"=>'œ', "\x9d"=>'', "\x9e"=>'ž', "\x9f"=>'Ÿ'); |
|
93
|
|
|
$x = $x + ($C['clean_ms_char'] == 1 ? array("\x82"=>'‚', "\x84"=>'„', "\x91"=>'‘', "\x92"=>'’', "\x93"=>'“', "\x94"=>'”') : array("\x82"=>'\'', "\x84"=>'"', "\x91"=>'\'', "\x92"=>'\'', "\x93"=>'"', "\x94"=>'"')); |
|
94
|
|
|
$t = strtr($t, $x); |
|
95
|
|
|
} |
|
96
|
|
|
if($C['cdata'] or $C['comment']){$t = preg_replace_callback('`<!(?:(?:--.*?--)|(?:\[CDATA\[.*?\]\]))>`sm', 'hl_cmtcd', $t);} |
|
|
|
|
|
|
97
|
|
|
$t = preg_replace_callback('`&([A-Za-z][A-Za-z0-9]{1,30}|#(?:[0-9]{1,8}|[Xx][0-9A-Fa-f]{1,7}));`', 'hl_ent', str_replace('&', '&', $t)); |
|
98
|
|
|
if($C['unique_ids'] && !isset($GLOBALS['hl_Ids'])){$GLOBALS['hl_Ids'] = array();} |
|
99
|
|
|
if($C['hook']){$t = $C['hook']($t, $C, $S);} |
|
100
|
|
|
if($C['show_setting'] && preg_match('`^[a-z][a-z0-9_]*$`i', $C['show_setting'])){ |
|
101
|
|
|
$GLOBALS[$C['show_setting']] = array('config'=>$C, 'spec'=>$S, 'time'=>microtime()); |
|
102
|
|
|
} |
|
103
|
|
|
// main |
|
104
|
|
|
$t = preg_replace_callback('`<(?:(?:\s|$)|(?:[^>]*(?:>|$)))|>`m', 'hl_tag', $t); |
|
105
|
|
|
$t = $C['balance'] ? hl_bal($t, $C['keep_bad'], $C['parent']) : $t; |
|
106
|
|
|
$t = (($C['cdata'] or $C['comment']) && strpos($t, "\x01") !== false) ? str_replace(array("\x01", "\x02", "\x03", "\x04", "\x05"), array('', '', '&', '<', '>'), $t) : $t; |
|
|
|
|
|
|
107
|
|
|
$t = $C['tidy'] ? hl_tidy($t, $C['tidy'], $C['parent']) : $t; |
|
108
|
|
|
unset($C, $e); |
|
109
|
|
|
if(isset($reC)){$GLOBALS['C'] = $reC;} |
|
110
|
|
|
if(isset($reS)){$GLOBALS['S'] = $reS;} |
|
111
|
|
|
return $t; |
|
112
|
|
|
// eof |
|
113
|
|
|
} |
|
114
|
|
|
|
|
115
|
|
|
function hl_attrval($t, $p){ |
|
116
|
|
|
// check attr val against $S |
|
117
|
|
|
$o = 1; $l = strlen($t); |
|
118
|
|
|
foreach($p as $k=>$v){ |
|
119
|
|
|
switch($k){ |
|
120
|
|
|
case 'maxlen':if($l > $v){$o = 0;} |
|
|
|
|
|
|
121
|
|
|
break; case 'minlen': if($l < $v){$o = 0;} |
|
|
|
|
|
|
122
|
|
|
break; case 'maxval': if((float)($t) > $v){$o = 0;} |
|
|
|
|
|
|
123
|
|
|
break; case 'minval': if((float)($t) < $v){$o = 0;} |
|
|
|
|
|
|
124
|
|
|
break; case 'match': if(!preg_match($v, $t)){$o = 0;} |
|
|
|
|
|
|
125
|
|
|
break; case 'nomatch': if(preg_match($v, $t)){$o = 0;} |
|
|
|
|
|
|
126
|
|
|
break; case 'oneof': |
|
127
|
|
|
$m = 0; |
|
128
|
|
|
foreach(explode('|', $v) as $n){if($t == $n){$m = 1; break;}} |
|
129
|
|
|
$o = $m; |
|
130
|
|
|
break; case 'noneof': |
|
131
|
|
|
$m = 1; |
|
132
|
|
|
foreach(explode('|', $v) as $n){if($t == $n){$m = 0; break;}} |
|
133
|
|
|
$o = $m; |
|
134
|
|
|
break; default: |
|
135
|
|
|
break; |
|
136
|
|
|
} |
|
137
|
|
|
if(!$o){break;} |
|
138
|
|
|
} |
|
139
|
|
|
return ($o ? $t : (isset($p['default']) ? $p['default'] : 0)); |
|
140
|
|
|
// eof |
|
141
|
|
|
} |
|
142
|
|
|
|
|
143
|
|
|
function hl_bal($t, $do=1, $in='div'){ |
|
|
|
|
|
|
144
|
|
|
// balance tags |
|
145
|
|
|
// by content |
|
146
|
|
|
$cB = array('blockquote'=>1, 'form'=>1, 'map'=>1, 'noscript'=>1); // Block |
|
147
|
|
|
$cE = array('area'=>1, 'br'=>1, 'col'=>1, 'embed'=>1, 'hr'=>1, 'img'=>1, 'input'=>1, 'isindex'=>1, 'param'=>1); // Empty |
|
148
|
|
|
$cF = array('button'=>1, 'del'=>1, 'div'=>1, 'dd'=>1, 'fieldset'=>1, 'iframe'=>1, 'ins'=>1, 'li'=>1, 'noscript'=>1, 'object'=>1, 'td'=>1, 'th'=>1); // Flow; later context-wise dynamic move of ins & del to $cI |
|
149
|
|
|
$cI = array('a'=>1, 'abbr'=>1, 'acronym'=>1, 'address'=>1, 'b'=>1, 'bdo'=>1, 'big'=>1, 'caption'=>1, 'cite'=>1, 'code'=>1, 'dfn'=>1, 'dt'=>1, 'em'=>1, 'font'=>1, 'h1'=>1, 'h2'=>1, 'h3'=>1, 'h4'=>1, 'h5'=>1, 'h6'=>1, 'i'=>1, 'kbd'=>1, 'label'=>1, 'legend'=>1, 'p'=>1, 'pre'=>1, 'q'=>1, 'rb'=>1, 'rt'=>1, 's'=>1, 'samp'=>1, 'small'=>1, 'span'=>1, 'strike'=>1, 'strong'=>1, 'sub'=>1, 'sup'=>1, 'tt'=>1, 'u'=>1, 'var'=>1); // Inline |
|
150
|
|
|
$cN = array('a'=>array('a'=>1), 'button'=>array('a'=>1, 'button'=>1, 'fieldset'=>1, 'form'=>1, 'iframe'=>1, 'input'=>1, 'label'=>1, 'select'=>1, 'textarea'=>1), 'fieldset'=>array('fieldset'=>1), 'form'=>array('form'=>1), 'label'=>array('label'=>1), 'noscript'=>array('script'=>1), 'pre'=>array('big'=>1, 'font'=>1, 'img'=>1, 'object'=>1, 'script'=>1, 'small'=>1, 'sub'=>1, 'sup'=>1), 'rb'=>array('ruby'=>1), 'rt'=>array('ruby'=>1)); // Illegal |
|
151
|
|
|
$cN2 = array_keys($cN); |
|
152
|
|
|
$cR = array('blockquote'=>1, 'dir'=>1, 'dl'=>1, 'form'=>1, 'map'=>1, 'menu'=>1, 'noscript'=>1, 'ol'=>1, 'optgroup'=>1, 'rbc'=>1, 'rtc'=>1, 'ruby'=>1, 'select'=>1, 'table'=>1, 'tbody'=>1, 'tfoot'=>1, 'thead'=>1, 'tr'=>1, 'ul'=>1); |
|
|
|
|
|
|
153
|
|
|
$cS = array('colgroup'=>array('col'=>1), 'dir'=>array('li'=>1), 'dl'=>array('dd'=>1, 'dt'=>1), 'menu'=>array('li'=>1), 'ol'=>array('li'=>1), 'optgroup'=>array('option'=>1), 'option'=>array('#pcdata'=>1), 'rbc'=>array('rb'=>1), 'rp'=>array('#pcdata'=>1), 'rtc'=>array('rt'=>1), 'ruby'=>array('rb'=>1, 'rbc'=>1, 'rp'=>1, 'rt'=>1, 'rtc'=>1), 'select'=>array('optgroup'=>1, 'option'=>1), 'script'=>array('#pcdata'=>1), 'table'=>array('caption'=>1, 'col'=>1, 'colgroup'=>1, 'tfoot'=>1, 'tbody'=>1, 'tr'=>1, 'thead'=>1), 'tbody'=>array('tr'=>1), 'tfoot'=>array('tr'=>1), 'textarea'=>array('#pcdata'=>1), 'thead'=>array('tr'=>1), 'tr'=>array('td'=>1, 'th'=>1), 'ul'=>array('li'=>1)); // Specific - immediate parent-child |
|
154
|
|
|
if($GLOBALS['C']['direct_list_nest']){$cS['ol'] = $cS['ul'] += array('ol'=>1, 'ul'=>1);} |
|
155
|
|
|
$cO = array('address'=>array('p'=>1), 'applet'=>array('param'=>1), 'blockquote'=>array('script'=>1), 'fieldset'=>array('legend'=>1, '#pcdata'=>1), 'form'=>array('script'=>1), 'map'=>array('area'=>1), 'object'=>array('param'=>1, 'embed'=>1)); // Other |
|
156
|
|
|
$cT = array('colgroup'=>1, 'dd'=>1, 'dt'=>1, 'li'=>1, 'option'=>1, 'p'=>1, 'td'=>1, 'tfoot'=>1, 'th'=>1, 'thead'=>1, 'tr'=>1); // Omitable closing |
|
157
|
|
|
// block/inline type; ins & del both type; #pcdata: text |
|
158
|
|
|
$eB = array('address'=>1, 'blockquote'=>1, 'center'=>1, 'del'=>1, 'dir'=>1, 'dl'=>1, 'div'=>1, 'fieldset'=>1, 'form'=>1, 'ins'=>1, 'h1'=>1, 'h2'=>1, 'h3'=>1, 'h4'=>1, 'h5'=>1, 'h6'=>1, 'hr'=>1, 'isindex'=>1, 'menu'=>1, 'noscript'=>1, 'ol'=>1, 'p'=>1, 'pre'=>1, 'table'=>1, 'ul'=>1); |
|
159
|
|
|
$eI = array('#pcdata'=>1, 'a'=>1, 'abbr'=>1, 'acronym'=>1, 'applet'=>1, 'b'=>1, 'bdo'=>1, 'big'=>1, 'br'=>1, 'button'=>1, 'cite'=>1, 'code'=>1, 'del'=>1, 'dfn'=>1, 'em'=>1, 'embed'=>1, 'font'=>1, 'i'=>1, 'iframe'=>1, 'img'=>1, 'input'=>1, 'ins'=>1, 'kbd'=>1, 'label'=>1, 'map'=>1, 'object'=>1, 'q'=>1, 'ruby'=>1, 's'=>1, 'samp'=>1, 'select'=>1, 'script'=>1, 'small'=>1, 'span'=>1, 'strike'=>1, 'strong'=>1, 'sub'=>1, 'sup'=>1, 'textarea'=>1, 'tt'=>1, 'u'=>1, 'var'=>1); |
|
160
|
|
|
$eN = array('a'=>1, 'big'=>1, 'button'=>1, 'fieldset'=>1, 'font'=>1, 'form'=>1, 'iframe'=>1, 'img'=>1, 'input'=>1, 'label'=>1, 'object'=>1, 'ruby'=>1, 'script'=>1, 'select'=>1, 'small'=>1, 'sub'=>1, 'sup'=>1, 'textarea'=>1); // Exclude from specific ele; $cN values |
|
161
|
|
|
$eO = array('area'=>1, 'caption'=>1, 'col'=>1, 'colgroup'=>1, 'dd'=>1, 'dt'=>1, 'legend'=>1, 'li'=>1, 'optgroup'=>1, 'option'=>1, 'param'=>1, 'rb'=>1, 'rbc'=>1, 'rp'=>1, 'rt'=>1, 'rtc'=>1, 'script'=>1, 'tbody'=>1, 'td'=>1, 'tfoot'=>1, 'thead'=>1, 'th'=>1, 'tr'=>1); // Missing in $eB & $eI |
|
162
|
|
|
$eF = $eB + $eI; |
|
163
|
|
|
|
|
164
|
|
|
// $in sets allowed child |
|
165
|
|
|
$in = ((isset($eF[$in]) && $in != '#pcdata') or isset($eO[$in])) ? $in : 'div'; |
|
|
|
|
|
|
166
|
|
|
if(isset($cE[$in])){ |
|
167
|
|
|
return (!$do ? '' : str_replace(array('<', '>'), array('<', '>'), $t)); |
|
168
|
|
|
} |
|
169
|
|
|
if(isset($cS[$in])){$inOk = $cS[$in];} |
|
170
|
|
|
elseif(isset($cI[$in])){$inOk = $eI; $cI['del'] = 1; $cI['ins'] = 1;} |
|
171
|
|
|
elseif(isset($cF[$in])){$inOk = $eF; unset($cI['del'], $cI['ins']);} |
|
172
|
|
|
elseif(isset($cB[$in])){$inOk = $eB; unset($cI['del'], $cI['ins']);} |
|
173
|
|
|
if(isset($cO[$in])){$inOk = $inOk + $cO[$in];} |
|
|
|
|
|
|
174
|
|
|
if(isset($cN[$in])){$inOk = array_diff_assoc($inOk, $cN[$in]);} |
|
175
|
|
|
|
|
176
|
|
|
$t = explode('<', $t); |
|
177
|
|
|
$ok = $q = array(); // $q seq list of open non-empty ele |
|
178
|
|
|
ob_start(); |
|
179
|
|
|
|
|
180
|
|
|
for($i=-1, $ci=count($t); ++$i<$ci;){ |
|
181
|
|
|
// allowed $ok in parent $p |
|
182
|
|
View Code Duplication |
if($ql = count($q)){ |
|
|
|
|
|
|
183
|
|
|
$p = array_pop($q); |
|
184
|
|
|
$q[] = $p; |
|
185
|
|
|
if(isset($cS[$p])){$ok = $cS[$p];} |
|
186
|
|
|
elseif(isset($cI[$p])){$ok = $eI; $cI['del'] = 1; $cI['ins'] = 1;} |
|
187
|
|
|
elseif(isset($cF[$p])){$ok = $eF; unset($cI['del'], $cI['ins']);} |
|
188
|
|
|
elseif(isset($cB[$p])){$ok = $eB; unset($cI['del'], $cI['ins']);} |
|
189
|
|
|
if(isset($cO[$p])){$ok = $ok + $cO[$p];} |
|
190
|
|
|
if(isset($cN[$p])){$ok = array_diff_assoc($ok, $cN[$p]);} |
|
191
|
|
|
}else{$ok = $inOk; unset($cI['del'], $cI['ins']);} |
|
192
|
|
|
// bad tags, & ele content |
|
193
|
|
View Code Duplication |
if(isset($e) && ($do == 1 or (isset($ok['#pcdata']) && ($do == 3 or $do == 5)))){ |
|
|
|
|
|
|
194
|
|
|
echo '<', $s, $e, $a, '>'; |
|
|
|
|
|
|
195
|
|
|
} |
|
196
|
|
View Code Duplication |
if(isset($x[0])){ |
|
|
|
|
|
|
197
|
|
|
if(strlen(trim($x)) && (($ql && isset($cB[$p])) or (isset($cB[$in]) && !$ql))){ |
|
|
|
|
|
|
198
|
|
|
echo '<div>', $x, '</div>'; |
|
199
|
|
|
} |
|
200
|
|
|
elseif($do < 3 or isset($ok['#pcdata'])){echo $x;} |
|
|
|
|
|
|
201
|
|
|
elseif(strpos($x, "\x02\x04")){ |
|
202
|
|
|
foreach(preg_split('`(\x01\x02[^\x01\x02]+\x02\x01)`', $x, -1, PREG_SPLIT_DELIM_CAPTURE | PREG_SPLIT_NO_EMPTY) as $v){ |
|
203
|
|
|
echo (substr($v, 0, 2) == "\x01\x02" ? $v : ($do > 4 ? preg_replace('`\S`', '', $v) : '')); |
|
204
|
|
|
} |
|
205
|
|
|
}elseif($do > 4){echo preg_replace('`\S`', '', $x);} |
|
206
|
|
|
} |
|
207
|
|
|
// get markup |
|
208
|
|
|
if(!preg_match('`^(/?)([a-z1-6]+)([^>]*)>(.*)`sm', $t[$i], $r)){$x = $t[$i]; continue;} |
|
209
|
|
|
$s = null; $e = null; $a = null; $x = null; list($all, $s, $e, $a, $x) = $r; |
|
|
|
|
|
|
210
|
|
|
// close tag |
|
211
|
|
|
if($s){ |
|
212
|
|
|
if(isset($cE[$e]) or !in_array($e, $q)){continue;} // Empty/unopen |
|
|
|
|
|
|
213
|
|
|
if($p == $e){array_pop($q); echo '</', $e, '>'; unset($e); continue;} // Last open |
|
|
|
|
|
|
214
|
|
|
$add = ''; // Nesting - close open tags that need to be |
|
215
|
|
|
for($j=-1, $cj=count($q); ++$j<$cj;){ |
|
216
|
|
|
if(($d = array_pop($q)) == $e){break;} |
|
217
|
|
|
else{$add .= "</{$d}>";} |
|
218
|
|
|
} |
|
219
|
|
|
echo $add, '</', $e, '>'; unset($e); continue; |
|
220
|
|
|
} |
|
221
|
|
|
// open tag |
|
222
|
|
|
// $cB ele needs $eB ele as child |
|
223
|
|
|
if(isset($cB[$e]) && strlen(trim($x))){ |
|
224
|
|
|
$t[$i] = "{$e}{$a}>"; |
|
225
|
|
|
array_splice($t, $i+1, 0, 'div>'. $x); unset($e, $x); ++$ci; --$i; continue; |
|
226
|
|
|
} |
|
227
|
|
|
if((($ql && isset($cB[$p])) or (isset($cB[$in]) && !$ql)) && !isset($eB[$e]) && !isset($ok[$e])){ |
|
|
|
|
|
|
228
|
|
|
array_splice($t, $i, 0, 'div>'); unset($e, $x); ++$ci; --$i; continue; |
|
229
|
|
|
} |
|
230
|
|
|
// if no open ele, $in = parent; mostly immediate parent-child relation should hold |
|
231
|
|
|
if(!$ql or !isset($eN[$e]) or !array_intersect($q, $cN2)){ |
|
|
|
|
|
|
232
|
|
|
if(!isset($ok[$e])){ |
|
233
|
|
|
if($ql && isset($cT[$p])){echo '</', array_pop($q), '>'; unset($e, $x); --$i;} |
|
234
|
|
|
continue; |
|
235
|
|
|
} |
|
236
|
|
|
if(!isset($cE[$e])){$q[] = $e;} |
|
237
|
|
|
echo '<', $e, $a, '>'; unset($e); continue; |
|
238
|
|
|
} |
|
239
|
|
|
// specific parent-child |
|
240
|
|
|
if(isset($cS[$p][$e])){ |
|
241
|
|
|
if(!isset($cE[$e])){$q[] = $e;} |
|
242
|
|
|
echo '<', $e, $a, '>'; unset($e); continue; |
|
243
|
|
|
} |
|
244
|
|
|
// nesting |
|
245
|
|
|
$add = ''; |
|
246
|
|
|
$q2 = array(); |
|
247
|
|
|
for($k=-1, $kc=count($q); ++$k<$kc;){ |
|
248
|
|
|
$d = $q[$k]; |
|
249
|
|
|
$ok2 = array(); |
|
|
|
|
|
|
250
|
|
|
if(isset($cS[$d])){$q2[] = $d; continue;} |
|
251
|
|
|
$ok2 = isset($cI[$d]) ? $eI : $eF; |
|
252
|
|
|
if(isset($cO[$d])){$ok2 = $ok2 + $cO[$d];} |
|
253
|
|
|
if(isset($cN[$d])){$ok2 = array_diff_assoc($ok2, $cN[$d]);} |
|
254
|
|
|
if(!isset($ok2[$e])){ |
|
255
|
|
|
if(!$k && !isset($inOk[$e])){continue 2;} |
|
256
|
|
|
$add = "</{$d}>"; |
|
257
|
|
|
for(;++$k<$kc;){$add = "</{$q[$k]}>{$add}";} |
|
258
|
|
|
break; |
|
259
|
|
|
} |
|
260
|
|
|
else{$q2[] = $d;} |
|
261
|
|
|
} |
|
262
|
|
|
$q = $q2; |
|
263
|
|
|
if(!isset($cE[$e])){$q[] = $e;} |
|
264
|
|
|
echo $add, '<', $e, $a, '>'; unset($e); continue; |
|
265
|
|
|
} |
|
266
|
|
|
|
|
267
|
|
|
// end |
|
268
|
|
View Code Duplication |
if($ql = count($q)){ |
|
|
|
|
|
|
269
|
|
|
$p = array_pop($q); |
|
270
|
|
|
$q[] = $p; |
|
271
|
|
|
if(isset($cS[$p])){$ok = $cS[$p];} |
|
272
|
|
|
elseif(isset($cI[$p])){$ok = $eI; $cI['del'] = 1; $cI['ins'] = 1;} |
|
273
|
|
|
elseif(isset($cF[$p])){$ok = $eF; unset($cI['del'], $cI['ins']);} |
|
274
|
|
|
elseif(isset($cB[$p])){$ok = $eB; unset($cI['del'], $cI['ins']);} |
|
275
|
|
|
if(isset($cO[$p])){$ok = $ok + $cO[$p];} |
|
276
|
|
|
if(isset($cN[$p])){$ok = array_diff_assoc($ok, $cN[$p]);} |
|
277
|
|
|
}else{$ok = $inOk; unset($cI['del'], $cI['ins']);} |
|
278
|
|
View Code Duplication |
if(isset($e) && ($do == 1 or (isset($ok['#pcdata']) && ($do == 3 or $do == 5)))){ |
|
|
|
|
|
|
279
|
|
|
echo '<', $s, $e, $a, '>'; |
|
280
|
|
|
} |
|
281
|
|
View Code Duplication |
if(isset($x[0])){ |
|
|
|
|
|
|
282
|
|
|
if(strlen(trim($x)) && (($ql && isset($cB[$p])) or (isset($cB[$in]) && !$ql))){ |
|
|
|
|
|
|
283
|
|
|
echo '<div>', $x, '</div>'; |
|
284
|
|
|
} |
|
285
|
|
|
elseif($do < 3 or isset($ok['#pcdata'])){echo $x;} |
|
|
|
|
|
|
286
|
|
|
elseif(strpos($x, "\x02\x04")){ |
|
287
|
|
|
foreach(preg_split('`(\x01\x02[^\x01\x02]+\x02\x01)`', $x, -1, PREG_SPLIT_DELIM_CAPTURE | PREG_SPLIT_NO_EMPTY) as $v){ |
|
288
|
|
|
echo (substr($v, 0, 2) == "\x01\x02" ? $v : ($do > 4 ? preg_replace('`\S`', '', $v) : '')); |
|
289
|
|
|
} |
|
290
|
|
|
}elseif($do > 4){echo preg_replace('`\S`', '', $x);} |
|
291
|
|
|
} |
|
292
|
|
|
while(!empty($q) && ($e = array_pop($q))){echo '</', $e, '>';} |
|
293
|
|
|
$o = ob_get_contents(); |
|
294
|
|
|
ob_end_clean(); |
|
295
|
|
|
return $o; |
|
296
|
|
|
// eof |
|
297
|
|
|
} |
|
298
|
|
|
|
|
299
|
|
|
function hl_cmtcd($t){ |
|
300
|
|
|
// comment/CDATA sec handler |
|
301
|
|
|
$t = $t[0]; |
|
302
|
|
|
global $C; |
|
|
|
|
|
|
303
|
|
|
if(!($v = $C[$n = $t[3] == '-' ? 'comment' : 'cdata'])){return $t;} |
|
304
|
|
|
if($v == 1){return '';} |
|
305
|
|
|
if($n == 'comment'){ |
|
306
|
|
|
if(substr(($t = preg_replace('`--+`', '-', substr($t, 4, -3))), -1) != ' '){$t .= ' ';} |
|
307
|
|
|
} |
|
308
|
|
|
else{$t = substr($t, 1, -1);} |
|
309
|
|
|
$t = $v == 2 ? str_replace(array('&', '<', '>'), array('&', '<', '>'), $t) : $t; |
|
310
|
|
|
return str_replace(array('&', '<', '>'), array("\x03", "\x04", "\x05"), ($n == 'comment' ? "\x01\x02\x04!--$t--\x05\x02\x01" : "\x01\x01\x04$t\x05\x01\x01")); |
|
311
|
|
|
// eof |
|
312
|
|
|
} |
|
313
|
|
|
|
|
314
|
|
|
function hl_ent($t){ |
|
315
|
|
|
// entitity handler |
|
316
|
|
|
global $C; |
|
|
|
|
|
|
317
|
|
|
$t = $t[1]; |
|
318
|
|
|
static $U = array('quot'=>1,'amp'=>1,'lt'=>1,'gt'=>1); |
|
319
|
|
|
static $N = array('fnof'=>'402', 'Alpha'=>'913', 'Beta'=>'914', 'Gamma'=>'915', 'Delta'=>'916', 'Epsilon'=>'917', 'Zeta'=>'918', 'Eta'=>'919', 'Theta'=>'920', 'Iota'=>'921', 'Kappa'=>'922', 'Lambda'=>'923', 'Mu'=>'924', 'Nu'=>'925', 'Xi'=>'926', 'Omicron'=>'927', 'Pi'=>'928', 'Rho'=>'929', 'Sigma'=>'931', 'Tau'=>'932', 'Upsilon'=>'933', 'Phi'=>'934', 'Chi'=>'935', 'Psi'=>'936', 'Omega'=>'937', 'alpha'=>'945', 'beta'=>'946', 'gamma'=>'947', 'delta'=>'948', 'epsilon'=>'949', 'zeta'=>'950', 'eta'=>'951', 'theta'=>'952', 'iota'=>'953', 'kappa'=>'954', 'lambda'=>'955', 'mu'=>'956', 'nu'=>'957', 'xi'=>'958', 'omicron'=>'959', 'pi'=>'960', 'rho'=>'961', 'sigmaf'=>'962', 'sigma'=>'963', 'tau'=>'964', 'upsilon'=>'965', 'phi'=>'966', 'chi'=>'967', 'psi'=>'968', 'omega'=>'969', 'thetasym'=>'977', 'upsih'=>'978', 'piv'=>'982', 'bull'=>'8226', 'hellip'=>'8230', 'prime'=>'8242', 'Prime'=>'8243', 'oline'=>'8254', 'frasl'=>'8260', 'weierp'=>'8472', 'image'=>'8465', 'real'=>'8476', 'trade'=>'8482', 'alefsym'=>'8501', 'larr'=>'8592', 'uarr'=>'8593', 'rarr'=>'8594', 'darr'=>'8595', 'harr'=>'8596', 'crarr'=>'8629', 'lArr'=>'8656', 'uArr'=>'8657', 'rArr'=>'8658', 'dArr'=>'8659', 'hArr'=>'8660', 'forall'=>'8704', 'part'=>'8706', 'exist'=>'8707', 'empty'=>'8709', 'nabla'=>'8711', 'isin'=>'8712', 'notin'=>'8713', 'ni'=>'8715', 'prod'=>'8719', 'sum'=>'8721', 'minus'=>'8722', 'lowast'=>'8727', 'radic'=>'8730', 'prop'=>'8733', 'infin'=>'8734', 'ang'=>'8736', 'and'=>'8743', 'or'=>'8744', 'cap'=>'8745', 'cup'=>'8746', 'int'=>'8747', 'there4'=>'8756', 'sim'=>'8764', 'cong'=>'8773', 'asymp'=>'8776', 'ne'=>'8800', 'equiv'=>'8801', 'le'=>'8804', 'ge'=>'8805', 'sub'=>'8834', 'sup'=>'8835', 'nsub'=>'8836', 'sube'=>'8838', 'supe'=>'8839', 'oplus'=>'8853', 'otimes'=>'8855', 'perp'=>'8869', 'sdot'=>'8901', 'lceil'=>'8968', 'rceil'=>'8969', 'lfloor'=>'8970', 'rfloor'=>'8971', 'lang'=>'9001', 'rang'=>'9002', 'loz'=>'9674', 'spades'=>'9824', 'clubs'=>'9827', 'hearts'=>'9829', 'diams'=>'9830', 'apos'=>'39', 'OElig'=>'338', 'oelig'=>'339', 'Scaron'=>'352', 'scaron'=>'353', 'Yuml'=>'376', 'circ'=>'710', 'tilde'=>'732', 'ensp'=>'8194', 'emsp'=>'8195', 'thinsp'=>'8201', 'zwnj'=>'8204', 'zwj'=>'8205', 'lrm'=>'8206', 'rlm'=>'8207', 'ndash'=>'8211', 'mdash'=>'8212', 'lsquo'=>'8216', 'rsquo'=>'8217', 'sbquo'=>'8218', 'ldquo'=>'8220', 'rdquo'=>'8221', 'bdquo'=>'8222', 'dagger'=>'8224', 'Dagger'=>'8225', 'permil'=>'8240', 'lsaquo'=>'8249', 'rsaquo'=>'8250', 'euro'=>'8364', 'nbsp'=>'160', 'iexcl'=>'161', 'cent'=>'162', 'pound'=>'163', 'curren'=>'164', 'yen'=>'165', 'brvbar'=>'166', 'sect'=>'167', 'uml'=>'168', 'copy'=>'169', 'ordf'=>'170', 'laquo'=>'171', 'not'=>'172', 'shy'=>'173', 'reg'=>'174', 'macr'=>'175', 'deg'=>'176', 'plusmn'=>'177', 'sup2'=>'178', 'sup3'=>'179', 'acute'=>'180', 'micro'=>'181', 'para'=>'182', 'middot'=>'183', 'cedil'=>'184', 'sup1'=>'185', 'ordm'=>'186', 'raquo'=>'187', 'frac14'=>'188', 'frac12'=>'189', 'frac34'=>'190', 'iquest'=>'191', 'Agrave'=>'192', 'Aacute'=>'193', 'Acirc'=>'194', 'Atilde'=>'195', 'Auml'=>'196', 'Aring'=>'197', 'AElig'=>'198', 'Ccedil'=>'199', 'Egrave'=>'200', 'Eacute'=>'201', 'Ecirc'=>'202', 'Euml'=>'203', 'Igrave'=>'204', 'Iacute'=>'205', 'Icirc'=>'206', 'Iuml'=>'207', 'ETH'=>'208', 'Ntilde'=>'209', 'Ograve'=>'210', 'Oacute'=>'211', 'Ocirc'=>'212', 'Otilde'=>'213', 'Ouml'=>'214', 'times'=>'215', 'Oslash'=>'216', 'Ugrave'=>'217', 'Uacute'=>'218', 'Ucirc'=>'219', 'Uuml'=>'220', 'Yacute'=>'221', 'THORN'=>'222', 'szlig'=>'223', 'agrave'=>'224', 'aacute'=>'225', 'acirc'=>'226', 'atilde'=>'227', 'auml'=>'228', 'aring'=>'229', 'aelig'=>'230', 'ccedil'=>'231', 'egrave'=>'232', 'eacute'=>'233', 'ecirc'=>'234', 'euml'=>'235', 'igrave'=>'236', 'iacute'=>'237', 'icirc'=>'238', 'iuml'=>'239', 'eth'=>'240', 'ntilde'=>'241', 'ograve'=>'242', 'oacute'=>'243', 'ocirc'=>'244', 'otilde'=>'245', 'ouml'=>'246', 'divide'=>'247', 'oslash'=>'248', 'ugrave'=>'249', 'uacute'=>'250', 'ucirc'=>'251', 'uuml'=>'252', 'yacute'=>'253', 'thorn'=>'254', 'yuml'=>'255'); |
|
320
|
|
|
if($t[0] != '#'){ |
|
321
|
|
|
return ($C['and_mark'] ? "\x06" : '&'). (isset($U[$t]) ? $t : (isset($N[$t]) ? (!$C['named_entity'] ? '#'. ($C['hexdec_entity'] > 1 ? 'x'. dechex($N[$t]) : $N[$t]) : $t) : 'amp;'. $t)). ';'; |
|
322
|
|
|
} |
|
323
|
|
|
if(($n = ctype_digit($t = substr($t, 1)) ? intval($t) : hexdec(substr($t, 1))) < 9 or ($n > 13 && $n < 32) or $n == 11 or $n == 12 or ($n > 126 && $n < 160 && $n != 133) or ($n > 55295 && ($n < 57344 or ($n > 64975 && $n < 64992) or $n == 65534 or $n == 65535 or $n > 1114111))){ |
|
|
|
|
|
|
324
|
|
|
return ($C['and_mark'] ? "\x06" : '&'). "amp;#{$t};"; |
|
325
|
|
|
} |
|
326
|
|
|
return ($C['and_mark'] ? "\x06" : '&'). '#'. (((ctype_digit($t) && $C['hexdec_entity'] < 2) or !$C['hexdec_entity']) ? $n : 'x'. dechex($n)). ';'; |
|
|
|
|
|
|
327
|
|
|
// eof |
|
328
|
|
|
} |
|
329
|
|
|
|
|
330
|
|
|
function hl_prot($p, $c=null){ |
|
331
|
|
|
// check URL scheme |
|
332
|
|
|
global $C; |
|
|
|
|
|
|
333
|
|
|
$b = $a = ''; |
|
334
|
|
|
if($c == null){$c = 'style'; $b = $p[1]; $a = $p[3]; $p = trim($p[2]);} |
|
335
|
|
|
$c = isset($C['schemes'][$c]) ? $C['schemes'][$c] : $C['schemes']['*']; |
|
336
|
|
|
static $d = 'denied:'; |
|
337
|
|
|
if(isset($c['!']) && substr($p, 0, 7) != $d){$p = "$d$p";} |
|
338
|
|
|
if(isset($c['*']) or !strcspn($p, '#?;') or (substr($p, 0, 7) == $d)){return "{$b}{$p}{$a}";} // All ok, frag, query, param |
|
|
|
|
|
|
339
|
|
|
if(preg_match('`^([^:?[@!$()*,=/\'\]]+?)(:|&#(58|x3a);|%3a|\\\\0{0,4}3a).`i', $p, $m) && !isset($c[strtolower($m[1])])){ // Denied prot |
|
340
|
|
|
return "{$b}{$d}{$p}{$a}"; |
|
341
|
|
|
} |
|
342
|
|
|
if($C['abs_url']){ |
|
343
|
|
|
if($C['abs_url'] == -1 && strpos($p, $C['base_url']) === 0){ // Make url rel |
|
344
|
|
|
$p = substr($p, strlen($C['base_url'])); |
|
345
|
|
|
}elseif(empty($m[1])){ // Make URL abs |
|
346
|
|
|
if(substr($p, 0, 2) == '//'){$p = substr($C['base_url'], 0, strpos($C['base_url'], ':')+1). $p;} |
|
347
|
|
|
elseif($p[0] == '/'){$p = preg_replace('`(^.+?://[^/]+)(.*)`', '$1', $C['base_url']). $p;} |
|
348
|
|
|
elseif(strcspn($p, './')){$p = $C['base_url']. $p;} |
|
349
|
|
|
else{ |
|
350
|
|
|
preg_match('`^([a-zA-Z\d\-+.]+://[^/]+)(.*)`', $C['base_url'], $m); |
|
351
|
|
|
$p = preg_replace('`(?<=/)\./`', '', $m[2]. $p); |
|
352
|
|
|
while(preg_match('`(?<=/)([^/]{3,}|[^/.]+?|\.[^/.]|[^/.]\.)/\.\./`', $p)){ |
|
353
|
|
|
$p = preg_replace('`(?<=/)([^/]{3,}|[^/.]+?|\.[^/.]|[^/.]\.)/\.\./`', '', $p); |
|
354
|
|
|
} |
|
355
|
|
|
$p = $m[1]. $p; |
|
356
|
|
|
} |
|
357
|
|
|
} |
|
358
|
|
|
} |
|
359
|
|
|
return "{$b}{$p}{$a}"; |
|
360
|
|
|
// eof |
|
361
|
|
|
} |
|
362
|
|
|
|
|
363
|
|
|
function hl_regex($p){ |
|
364
|
|
|
// ?regex |
|
365
|
|
|
if(empty($p)){return 0;} |
|
366
|
|
|
if($t = ini_get('track_errors')){$o = isset($php_errormsg) ? $php_errormsg : null;} |
|
367
|
|
|
else{ini_set('track_errors', 1);} |
|
368
|
|
|
unset($php_errormsg); |
|
369
|
|
|
if(($d = ini_get('display_errors'))){ini_set('display_errors', 0);} |
|
370
|
|
|
preg_match($p, ''); |
|
371
|
|
|
if($d){ini_set('display_errors', 1);} |
|
372
|
|
|
$r = isset($php_errormsg) ? 0 : 1; |
|
373
|
|
|
if($t){$php_errormsg = isset($o) ? $o : null;} |
|
|
|
|
|
|
374
|
|
|
else{ini_set('track_errors', 0);} |
|
375
|
|
|
return $r; |
|
376
|
|
|
// eof |
|
377
|
|
|
} |
|
378
|
|
|
|
|
379
|
|
|
function hl_spec($t){ |
|
380
|
|
|
// final $spec |
|
381
|
|
|
$s = array(); |
|
382
|
|
|
$t = str_replace(array("\t", "\r", "\n", ' '), '', preg_replace_callback('/"(?>(`.|[^"])*)"/sm', create_function('$m', 'return substr(str_replace(array(";", "|", "~", " ", ",", "/", "(", ")", \'`"\'), array("\x01", "\x02", "\x03", "\x04", "\x05", "\x06", "\x07", "\x08", "\""), $m[0]), 1, -1);'), trim($t))); |
|
|
|
|
|
|
383
|
|
|
for($i = count(($t = explode(';', $t))); --$i>=0;){ |
|
384
|
|
|
$w = $t[$i]; |
|
385
|
|
|
if(empty($w) or ($e = strpos($w, '=')) === false or !strlen(($a = substr($w, $e+1)))){continue;} |
|
|
|
|
|
|
386
|
|
|
$y = $n = array(); |
|
387
|
|
|
foreach(explode(',', $a) as $v){ |
|
388
|
|
|
if(!preg_match('`^([a-z:\-\*]+)(?:\((.*?)\))?`i', $v, $m)){continue;} |
|
389
|
|
|
if(($x = strtolower($m[1])) == '-*'){$n['*'] = 1; continue;} |
|
390
|
|
|
if($x[0] == '-'){$n[substr($x, 1)] = 1; continue;} |
|
391
|
|
|
if(!isset($m[2])){$y[$x] = 1; continue;} |
|
392
|
|
|
foreach(explode('/', $m[2]) as $m){ |
|
393
|
|
|
if(empty($m) or ($p = strpos($m, '=')) == 0 or $p < 5){$y[$x] = 1; continue;} |
|
|
|
|
|
|
394
|
|
|
$y[$x][strtolower(substr($m, 0, $p))] = str_replace(array("\x01", "\x02", "\x03", "\x04", "\x05", "\x06", "\x07", "\x08"), array(";", "|", "~", " ", ",", "/", "(", ")"), substr($m, $p+1)); |
|
395
|
|
|
} |
|
396
|
|
View Code Duplication |
if(isset($y[$x]['match']) && !hl_regex($y[$x]['match'])){unset($y[$x]['match']);} |
|
|
|
|
|
|
397
|
|
View Code Duplication |
if(isset($y[$x]['nomatch']) && !hl_regex($y[$x]['nomatch'])){unset($y[$x]['nomatch']);} |
|
|
|
|
|
|
398
|
|
|
} |
|
399
|
|
|
if(!count($y) && !count($n)){continue;} |
|
400
|
|
|
foreach(explode(',', substr($w, 0, $e)) as $v){ |
|
401
|
|
|
if(!strlen(($v = strtolower($v)))){continue;} |
|
402
|
|
|
if(count($y)){$s[$v] = $y;} |
|
403
|
|
|
if(count($n)){$s[$v]['n'] = $n;} |
|
404
|
|
|
} |
|
405
|
|
|
} |
|
406
|
|
|
return $s; |
|
407
|
|
|
// eof |
|
408
|
|
|
} |
|
409
|
|
|
|
|
410
|
|
|
function hl_tag($t){ |
|
|
|
|
|
|
411
|
|
|
// tag/attribute handler |
|
412
|
|
|
global $C; |
|
|
|
|
|
|
413
|
|
|
$t = $t[0]; |
|
414
|
|
|
// invalid < > |
|
415
|
|
|
if($t == '< '){return '< ';} |
|
416
|
|
|
if($t == '>'){return '>';} |
|
417
|
|
|
if(!preg_match('`^<(/?)([a-zA-Z][a-zA-Z1-6]*)([^>]*?)\s?>$`m', $t, $m)){ |
|
418
|
|
|
return str_replace(array('<', '>'), array('<', '>'), $t); |
|
419
|
|
|
}elseif(!isset($C['elements'][($e = strtolower($m[2]))])){ |
|
420
|
|
|
return (($C['keep_bad']%2) ? str_replace(array('<', '>'), array('<', '>'), $t) : ''); |
|
421
|
|
|
} |
|
422
|
|
|
// attr string |
|
423
|
|
|
$a = str_replace(array("\n", "\r", "\t"), ' ', trim($m[3])); |
|
424
|
|
|
// tag transform |
|
425
|
|
|
static $eD = array('applet'=>1, 'center'=>1, 'dir'=>1, 'embed'=>1, 'font'=>1, 'isindex'=>1, 'menu'=>1, 's'=>1, 'strike'=>1, 'u'=>1); // Deprecated |
|
426
|
|
|
if($C['make_tag_strict'] && isset($eD[$e])){ |
|
427
|
|
|
$trt = hl_tag2($e, $a, $C['make_tag_strict']); |
|
428
|
|
|
if(!$e){return (($C['keep_bad']%2) ? str_replace(array('<', '>'), array('<', '>'), $t) : '');} |
|
429
|
|
|
} |
|
430
|
|
|
// close tag |
|
431
|
|
|
static $eE = array('area'=>1, 'br'=>1, 'col'=>1, 'embed'=>1, 'hr'=>1, 'img'=>1, 'input'=>1, 'isindex'=>1, 'param'=>1); // Empty ele |
|
432
|
|
|
if(!empty($m[1])){ |
|
433
|
|
|
return (!isset($eE[$e]) ? (empty($C['hook_tag']) ? "</$e>" : $C['hook_tag']($e)) : (($C['keep_bad'])%2 ? str_replace(array('<', '>'), array('<', '>'), $t) : '')); |
|
434
|
|
|
} |
|
435
|
|
|
|
|
436
|
|
|
// open tag & attr |
|
437
|
|
|
static $aN = array('abbr'=>array('td'=>1, 'th'=>1), 'accept-charset'=>array('form'=>1), 'accept'=>array('form'=>1, 'input'=>1), 'accesskey'=>array('a'=>1, 'area'=>1, 'button'=>1, 'input'=>1, 'label'=>1, 'legend'=>1, 'textarea'=>1), 'action'=>array('form'=>1), 'align'=>array('caption'=>1, 'embed'=>1, 'applet'=>1, 'iframe'=>1, 'img'=>1, 'input'=>1, 'object'=>1, 'legend'=>1, 'table'=>1, 'hr'=>1, 'div'=>1, 'h1'=>1, 'h2'=>1, 'h3'=>1, 'h4'=>1, 'h5'=>1, 'h6'=>1, 'p'=>1, 'col'=>1, 'colgroup'=>1, 'tbody'=>1, 'td'=>1, 'tfoot'=>1, 'th'=>1, 'thead'=>1, 'tr'=>1), 'alt'=>array('applet'=>1, 'area'=>1, 'img'=>1, 'input'=>1), 'archive'=>array('applet'=>1, 'object'=>1), 'axis'=>array('td'=>1, 'th'=>1), 'bgcolor'=>array('embed'=>1, 'table'=>1, 'tr'=>1, 'td'=>1, 'th'=>1), 'border'=>array('table'=>1, 'img'=>1, 'object'=>1), 'bordercolor'=>array('table'=>1, 'td'=>1, 'tr'=>1), 'cellpadding'=>array('table'=>1), 'cellspacing'=>array('table'=>1), 'char'=>array('col'=>1, 'colgroup'=>1, 'tbody'=>1, 'td'=>1, 'tfoot'=>1, 'th'=>1, 'thead'=>1, 'tr'=>1), 'charoff'=>array('col'=>1, 'colgroup'=>1, 'tbody'=>1, 'td'=>1, 'tfoot'=>1, 'th'=>1, 'thead'=>1, 'tr'=>1), 'charset'=>array('a'=>1, 'script'=>1), 'checked'=>array('input'=>1), 'cite'=>array('blockquote'=>1, 'q'=>1, 'del'=>1, 'ins'=>1), 'classid'=>array('object'=>1), 'clear'=>array('br'=>1), 'code'=>array('applet'=>1), 'codebase'=>array('object'=>1, 'applet'=>1), 'codetype'=>array('object'=>1), 'color'=>array('font'=>1), 'cols'=>array('textarea'=>1), 'colspan'=>array('td'=>1, 'th'=>1), 'compact'=>array('dir'=>1, 'dl'=>1, 'menu'=>1, 'ol'=>1, 'ul'=>1), 'coords'=>array('area'=>1, 'a'=>1), 'data'=>array('object'=>1), 'datetime'=>array('del'=>1, 'ins'=>1), 'declare'=>array('object'=>1), 'defer'=>array('script'=>1), 'dir'=>array('bdo'=>1), 'disabled'=>array('button'=>1, 'input'=>1, 'optgroup'=>1, 'option'=>1, 'select'=>1, 'textarea'=>1), 'enctype'=>array('form'=>1), 'face'=>array('font'=>1), 'flashvars'=>array('embed'=>1), 'for'=>array('label'=>1), 'frame'=>array('table'=>1), 'frameborder'=>array('iframe'=>1), 'headers'=>array('td'=>1, 'th'=>1), 'height'=>array('embed'=>1, 'iframe'=>1, 'td'=>1, 'th'=>1, 'img'=>1, 'object'=>1, 'applet'=>1), 'href'=>array('a'=>1, 'area'=>1), 'hreflang'=>array('a'=>1), 'hspace'=>array('applet'=>1, 'img'=>1, 'object'=>1), 'ismap'=>array('img'=>1, 'input'=>1), 'label'=>array('option'=>1, 'optgroup'=>1), 'language'=>array('script'=>1), 'longdesc'=>array('img'=>1, 'iframe'=>1), 'marginheight'=>array('iframe'=>1), 'marginwidth'=>array('iframe'=>1), 'maxlength'=>array('input'=>1), 'method'=>array('form'=>1), 'model'=>array('embed'=>1), 'multiple'=>array('select'=>1), 'name'=>array('button'=>1, 'embed'=>1, 'textarea'=>1, 'applet'=>1, 'select'=>1, 'form'=>1, 'iframe'=>1, 'img'=>1, 'a'=>1, 'input'=>1, 'object'=>1, 'map'=>1, 'param'=>1), 'nohref'=>array('area'=>1), 'noshade'=>array('hr'=>1), 'nowrap'=>array('td'=>1, 'th'=>1), 'object'=>array('applet'=>1), 'onblur'=>array('a'=>1, 'area'=>1, 'button'=>1, 'input'=>1, 'label'=>1, 'select'=>1, 'textarea'=>1), 'onchange'=>array('input'=>1, 'select'=>1, 'textarea'=>1), 'onfocus'=>array('a'=>1, 'area'=>1, 'button'=>1, 'input'=>1, 'label'=>1, 'select'=>1, 'textarea'=>1), 'onreset'=>array('form'=>1), 'onselect'=>array('input'=>1, 'textarea'=>1), 'onsubmit'=>array('form'=>1), 'pluginspage'=>array('embed'=>1), 'pluginurl'=>array('embed'=>1), 'prompt'=>array('isindex'=>1), 'readonly'=>array('textarea'=>1, 'input'=>1), 'rel'=>array('a'=>1), 'rev'=>array('a'=>1), 'rows'=>array('textarea'=>1), 'rowspan'=>array('td'=>1, 'th'=>1), 'rules'=>array('table'=>1), 'scope'=>array('td'=>1, 'th'=>1), 'scrolling'=>array('iframe'=>1), 'selected'=>array('option'=>1), 'shape'=>array('area'=>1, 'a'=>1), 'size'=>array('hr'=>1, 'font'=>1, 'input'=>1, 'select'=>1), 'span'=>array('col'=>1, 'colgroup'=>1), 'src'=>array('embed'=>1, 'script'=>1, 'input'=>1, 'iframe'=>1, 'img'=>1), 'standby'=>array('object'=>1), 'start'=>array('ol'=>1), 'summary'=>array('table'=>1), 'tabindex'=>array('a'=>1, 'area'=>1, 'button'=>1, 'input'=>1, 'object'=>1, 'select'=>1, 'textarea'=>1), 'target'=>array('a'=>1, 'area'=>1, 'form'=>1), 'type'=>array('a'=>1, 'embed'=>1, 'object'=>1, 'param'=>1, 'script'=>1, 'input'=>1, 'li'=>1, 'ol'=>1, 'ul'=>1, 'button'=>1), 'usemap'=>array('img'=>1, 'input'=>1, 'object'=>1), 'valign'=>array('col'=>1, 'colgroup'=>1, 'tbody'=>1, 'td'=>1, 'tfoot'=>1, 'th'=>1, 'thead'=>1, 'tr'=>1), 'value'=>array('input'=>1, 'option'=>1, 'param'=>1, 'button'=>1, 'li'=>1), 'valuetype'=>array('param'=>1), 'vspace'=>array('applet'=>1, 'img'=>1, 'object'=>1), 'width'=>array('embed'=>1, 'hr'=>1, 'iframe'=>1, 'img'=>1, 'object'=>1, 'table'=>1, 'td'=>1, 'th'=>1, 'applet'=>1, 'col'=>1, 'colgroup'=>1, 'pre'=>1), 'wmode'=>array('embed'=>1), 'xml:space'=>array('pre'=>1, 'script'=>1, 'style'=>1)); // Ele-specific |
|
438
|
|
|
static $aNE = array('checked'=>1, 'compact'=>1, 'declare'=>1, 'defer'=>1, 'disabled'=>1, 'ismap'=>1, 'multiple'=>1, 'nohref'=>1, 'noresize'=>1, 'noshade'=>1, 'nowrap'=>1, 'readonly'=>1, 'selected'=>1); // Empty |
|
439
|
|
|
static $aNP = array('action'=>1, 'cite'=>1, 'classid'=>1, 'codebase'=>1, 'data'=>1, 'href'=>1, 'longdesc'=>1, 'model'=>1, 'pluginspage'=>1, 'pluginurl'=>1, 'usemap'=>1); // Need scheme check; excludes style, on* & src |
|
440
|
|
|
static $aNU = array('class'=>array('param'=>1, 'script'=>1), 'dir'=>array('applet'=>1, 'bdo'=>1, 'br'=>1, 'iframe'=>1, 'param'=>1, 'script'=>1), 'id'=>array('script'=>1), 'lang'=>array('applet'=>1, 'br'=>1, 'iframe'=>1, 'param'=>1, 'script'=>1), 'xml:lang'=>array('applet'=>1, 'br'=>1, 'iframe'=>1, 'param'=>1, 'script'=>1), 'onclick'=>array('applet'=>1, 'bdo'=>1, 'br'=>1, 'font'=>1, 'iframe'=>1, 'isindex'=>1, 'param'=>1, 'script'=>1), 'ondblclick'=>array('applet'=>1, 'bdo'=>1, 'br'=>1, 'font'=>1, 'iframe'=>1, 'isindex'=>1, 'param'=>1, 'script'=>1), 'onkeydown'=>array('applet'=>1, 'bdo'=>1, 'br'=>1, 'font'=>1, 'iframe'=>1, 'isindex'=>1, 'param'=>1, 'script'=>1), 'onkeypress'=>array('applet'=>1, 'bdo'=>1, 'br'=>1, 'font'=>1, 'iframe'=>1, 'isindex'=>1, 'param'=>1, 'script'=>1), 'onkeyup'=>array('applet'=>1, 'bdo'=>1, 'br'=>1, 'font'=>1, 'iframe'=>1, 'isindex'=>1, 'param'=>1, 'script'=>1), 'onmousedown'=>array('applet'=>1, 'bdo'=>1, 'br'=>1, 'font'=>1, 'iframe'=>1, 'isindex'=>1, 'param'=>1, 'script'=>1), 'onmousemove'=>array('applet'=>1, 'bdo'=>1, 'br'=>1, 'font'=>1, 'iframe'=>1, 'isindex'=>1, 'param'=>1, 'script'=>1), 'onmouseout'=>array('applet'=>1, 'bdo'=>1, 'br'=>1, 'font'=>1, 'iframe'=>1, 'isindex'=>1, 'param'=>1, 'script'=>1), 'onmouseover'=>array('applet'=>1, 'bdo'=>1, 'br'=>1, 'font'=>1, 'iframe'=>1, 'isindex'=>1, 'param'=>1, 'script'=>1), 'onmouseup'=>array('applet'=>1, 'bdo'=>1, 'br'=>1, 'font'=>1, 'iframe'=>1, 'isindex'=>1, 'param'=>1, 'script'=>1), 'style'=>array('param'=>1, 'script'=>1), 'title'=>array('param'=>1, 'script'=>1)); // Univ & exceptions |
|
441
|
|
|
|
|
442
|
|
|
if($C['lc_std_val']){ |
|
443
|
|
|
// predef attr vals for $eAL & $aNE ele |
|
444
|
|
|
static $aNL = array('all'=>1, 'baseline'=>1, 'bottom'=>1, 'button'=>1, 'center'=>1, 'char'=>1, 'checkbox'=>1, 'circle'=>1, 'col'=>1, 'colgroup'=>1, 'cols'=>1, 'data'=>1, 'default'=>1, 'file'=>1, 'get'=>1, 'groups'=>1, 'hidden'=>1, 'image'=>1, 'justify'=>1, 'left'=>1, 'ltr'=>1, 'middle'=>1, 'none'=>1, 'object'=>1, 'password'=>1, 'poly'=>1, 'post'=>1, 'preserve'=>1, 'radio'=>1, 'rect'=>1, 'ref'=>1, 'reset'=>1, 'right'=>1, 'row'=>1, 'rowgroup'=>1, 'rows'=>1, 'rtl'=>1, 'submit'=>1, 'text'=>1, 'top'=>1); |
|
445
|
|
|
static $eAL = array('a'=>1, 'area'=>1, 'bdo'=>1, 'button'=>1, 'col'=>1, 'form'=>1, 'img'=>1, 'input'=>1, 'object'=>1, 'optgroup'=>1, 'option'=>1, 'param'=>1, 'script'=>1, 'select'=>1, 'table'=>1, 'td'=>1, 'tfoot'=>1, 'th'=>1, 'thead'=>1, 'tr'=>1, 'xml:space'=>1); |
|
446
|
|
|
$lcase = isset($eAL[$e]) ? 1 : 0; |
|
447
|
|
|
} |
|
448
|
|
|
|
|
449
|
|
|
$depTr = 0; |
|
450
|
|
|
if($C['no_deprecated_attr']){ |
|
451
|
|
|
// dep attr:applicable ele |
|
452
|
|
|
static $aND = array('align'=>array('caption'=>1, 'div'=>1, 'h1'=>1, 'h2'=>1, 'h3'=>1, 'h4'=>1, 'h5'=>1, 'h6'=>1, 'hr'=>1, 'img'=>1, 'input'=>1, 'legend'=>1, 'object'=>1, 'p'=>1, 'table'=>1), 'bgcolor'=>array('table'=>1, 'td'=>1, 'th'=>1, 'tr'=>1), 'border'=>array('img'=>1, 'object'=>1), 'bordercolor'=>array('table'=>1, 'td'=>1, 'tr'=>1), 'clear'=>array('br'=>1), 'compact'=>array('dl'=>1, 'ol'=>1, 'ul'=>1), 'height'=>array('td'=>1, 'th'=>1), 'hspace'=>array('img'=>1, 'object'=>1), 'language'=>array('script'=>1), 'name'=>array('a'=>1, 'form'=>1, 'iframe'=>1, 'img'=>1, 'map'=>1), 'noshade'=>array('hr'=>1), 'nowrap'=>array('td'=>1, 'th'=>1), 'size'=>array('hr'=>1), 'start'=>array('ol'=>1), 'type'=>array('li'=>1, 'ol'=>1, 'ul'=>1), 'value'=>array('li'=>1), 'vspace'=>array('img'=>1, 'object'=>1), 'width'=>array('hr'=>1, 'pre'=>1, 'td'=>1, 'th'=>1)); |
|
453
|
|
|
static $eAD = array('a'=>1, 'br'=>1, 'caption'=>1, 'div'=>1, 'dl'=>1, 'form'=>1, 'h1'=>1, 'h2'=>1, 'h3'=>1, 'h4'=>1, 'h5'=>1, 'h6'=>1, 'hr'=>1, 'iframe'=>1, 'img'=>1, 'input'=>1, 'legend'=>1, 'li'=>1, 'map'=>1, 'object'=>1, 'ol'=>1, 'p'=>1, 'pre'=>1, 'script'=>1, 'table'=>1, 'td'=>1, 'th'=>1, 'tr'=>1, 'ul'=>1); |
|
454
|
|
|
$depTr = isset($eAD[$e]) ? 1 : 0; |
|
455
|
|
|
} |
|
456
|
|
|
|
|
457
|
|
|
// attr name-vals |
|
458
|
|
|
if(strpos($a, "\x01") !== false){$a = preg_replace('`\x01[^\x01]*\x01`', '', $a);} // No comment/CDATA sec |
|
459
|
|
|
$mode = 0; $a = trim($a, ' /'); $aA = array(); |
|
460
|
|
|
while(strlen($a)){ |
|
461
|
|
|
$w = 0; |
|
462
|
|
|
switch($mode){ |
|
463
|
|
|
case 0: // Name |
|
464
|
|
|
if(preg_match('`^[a-zA-Z][\-a-zA-Z:]+`', $a, $m)){ |
|
465
|
|
|
$nm = strtolower($m[0]); |
|
466
|
|
|
$w = $mode = 1; $a = ltrim(substr_replace($a, '', 0, strlen($m[0]))); |
|
467
|
|
|
} |
|
468
|
|
|
break; case 1: |
|
469
|
|
|
if($a[0] == '='){ // = |
|
470
|
|
|
$w = 1; $mode = 2; $a = ltrim($a, '= '); |
|
471
|
|
|
}else{ // No val |
|
472
|
|
|
$w = 1; $mode = 0; $a = ltrim($a); |
|
473
|
|
|
$aA[$nm] = ''; |
|
|
|
|
|
|
474
|
|
|
} |
|
475
|
|
|
break; case 2: // Val |
|
476
|
|
|
if(preg_match('`^((?:"[^"]*")|(?:\'[^\']*\')|(?:\s*[^\s"\']+))(.*)`', $a, $m)){ |
|
477
|
|
|
$a = ltrim($m[2]); $m = $m[1]; $w = 1; $mode = 0; |
|
478
|
|
|
$aA[$nm] = trim(($m[0] == '"' or $m[0] == '\'') ? substr($m, 1, -1) : $m); |
|
|
|
|
|
|
479
|
|
|
} |
|
480
|
|
|
break; |
|
481
|
|
|
} |
|
482
|
|
|
if($w == 0){ // Parse errs, deal with space, " & ' |
|
483
|
|
|
$a = preg_replace('`^(?:"[^"]*("|$)|\'[^\']*(\'|$)|\S)*\s*`', '', $a); |
|
484
|
|
|
$mode = 0; |
|
485
|
|
|
} |
|
486
|
|
|
} |
|
487
|
|
|
if($mode == 1){$aA[$nm] = '';} |
|
488
|
|
|
|
|
489
|
|
|
// clean attrs |
|
490
|
|
|
global $S; |
|
|
|
|
|
|
491
|
|
|
$rl = isset($S[$e]) ? $S[$e] : array(); |
|
492
|
|
|
$a = array(); $nfr = 0; |
|
493
|
|
|
foreach($aA as $k=>$v){ |
|
494
|
|
|
if(((isset($C['deny_attribute']['*']) ? isset($C['deny_attribute'][$k]) : !isset($C['deny_attribute'][$k])) && (isset($aN[$k][$e]) or (isset($aNU[$k]) && !isset($aNU[$k][$e]))) && !isset($rl['n'][$k]) && !isset($rl['n']['*'])) or isset($rl[$k])){ |
|
|
|
|
|
|
495
|
|
|
if(isset($aNE[$k])){$v = $k;} |
|
496
|
|
|
elseif(!empty($lcase) && (($e != 'button' or $e != 'input') or $k == 'type')){ // Rather loose but ?not cause issues |
|
|
|
|
|
|
497
|
|
|
$v = (isset($aNL[($v2 = strtolower($v))])) ? $v2 : $v; |
|
498
|
|
|
} |
|
499
|
|
|
if($k == 'style' && !$C['style_pass']){ |
|
500
|
|
|
if(false !== strpos($v, '&#')){ |
|
501
|
|
|
static $sC = array(' '=>' ', ' '=>' ', 'E'=>'e', 'E'=>'e', 'e'=>'e', 'e'=>'e', 'X'=>'x', 'X'=>'x', 'x'=>'x', 'x'=>'x', 'P'=>'p', 'P'=>'p', 'p'=>'p', 'p'=>'p', 'S'=>'s', 'S'=>'s', 's'=>'s', 's'=>'s', 'I'=>'i', 'I'=>'i', 'i'=>'i', 'i'=>'i', 'O'=>'o', 'O'=>'o', 'o'=>'o', 'o'=>'o', 'N'=>'n', 'N'=>'n', 'n'=>'n', 'n'=>'n', 'U'=>'u', 'U'=>'u', 'u'=>'u', 'u'=>'u', 'R'=>'r', 'R'=>'r', 'r'=>'r', 'r'=>'r', 'L'=>'l', 'L'=>'l', 'l'=>'l', 'l'=>'l', '('=>'(', '('=>'(', ')'=>')', ')'=>')', ' '=>':', ' '=>':', '"'=>'"', '"'=>'"', '''=>"'", '''=>"'", '/'=>'/', '/'=>'/', '*'=>'*', '*'=>'*', '\'=>'\\', '\'=>'\\'); |
|
502
|
|
|
$v = strtr($v, $sC); |
|
503
|
|
|
} |
|
504
|
|
|
$v = preg_replace_callback('`(url(?:\()(?: )*(?:\'|"|&(?:quot|apos);)?)(.+?)((?:\'|"|&(?:quot|apos);)?(?: )*(?:\)))`iS', 'hl_prot', $v); |
|
505
|
|
|
$v = !$C['css_expression'] ? preg_replace('`expression`i', ' ', preg_replace('`\\\\\S|(/|(%2f))(\*|(%2a))`i', ' ', $v)) : $v; |
|
506
|
|
|
}elseif(isset($aNP[$k]) or strpos($k, 'src') !== false or $k[0] == 'o'){ |
|
|
|
|
|
|
507
|
|
|
$v = str_replace("\xad", ' ', (strpos($v, '&') !== false ? str_replace(array('­', '­', '­'), ' ', $v) : $v)); |
|
508
|
|
|
$v = hl_prot($v, $k); |
|
509
|
|
|
if($k == 'href'){ // X-spam |
|
510
|
|
|
if($C['anti_mail_spam'] && strpos($v, 'mailto:') === 0){ |
|
511
|
|
|
$v = str_replace('@', htmlspecialchars($C['anti_mail_spam']), $v); |
|
512
|
|
|
}elseif($C['anti_link_spam']){ |
|
513
|
|
|
$r1 = $C['anti_link_spam'][1]; |
|
514
|
|
|
if(!empty($r1) && preg_match($r1, $v)){continue;} |
|
515
|
|
|
$r0 = $C['anti_link_spam'][0]; |
|
516
|
|
|
if(!empty($r0) && preg_match($r0, $v)){ |
|
517
|
|
|
if(isset($a['rel'])){ |
|
518
|
|
|
if(!preg_match('`\bnofollow\b`i', $a['rel'])){$a['rel'] .= ' nofollow';} |
|
519
|
|
|
}elseif(isset($aA['rel'])){ |
|
520
|
|
|
if(!preg_match('`\bnofollow\b`i', $aA['rel'])){$nfr = 1;} |
|
521
|
|
|
}else{$a['rel'] = 'nofollow';} |
|
522
|
|
|
} |
|
523
|
|
|
} |
|
524
|
|
|
} |
|
525
|
|
|
} |
|
526
|
|
|
if(isset($rl[$k]) && is_array($rl[$k]) && ($v = hl_attrval($v, $rl[$k])) === 0){continue;} |
|
527
|
|
|
$a[$k] = str_replace('"', '"', $v); |
|
528
|
|
|
} |
|
529
|
|
|
} |
|
530
|
|
|
if($nfr){$a['rel'] = isset($a['rel']) ? $a['rel']. ' nofollow' : 'nofollow';} |
|
531
|
|
|
|
|
532
|
|
|
// rqd attr |
|
533
|
|
|
static $eAR = array('area'=>array('alt'=>'area'), 'bdo'=>array('dir'=>'ltr'), 'form'=>array('action'=>''), 'img'=>array('src'=>'', 'alt'=>'image'), 'map'=>array('name'=>''), 'optgroup'=>array('label'=>''), 'param'=>array('name'=>''), 'script'=>array('type'=>'text/javascript'), 'textarea'=>array('rows'=>'10', 'cols'=>'50')); |
|
534
|
|
|
if(isset($eAR[$e])){ |
|
535
|
|
|
foreach($eAR[$e] as $k=>$v){ |
|
536
|
|
|
if(!isset($a[$k])){$a[$k] = isset($v[0]) ? $v : $k;} |
|
537
|
|
|
} |
|
538
|
|
|
} |
|
539
|
|
|
|
|
540
|
|
|
// depr attrs |
|
541
|
|
|
if($depTr){ |
|
542
|
|
|
$c = array(); |
|
543
|
|
|
foreach($a as $k=>$v){ |
|
544
|
|
|
if($k == 'style' or !isset($aND[$k][$e])){continue;} |
|
|
|
|
|
|
545
|
|
|
if($k == 'align'){ |
|
546
|
|
|
unset($a['align']); |
|
547
|
|
|
if($e == 'img' && ($v == 'left' or $v == 'right')){$c[] = 'float: '. $v;} |
|
|
|
|
|
|
548
|
|
|
elseif(($e == 'div' or $e == 'table') && $v == 'center'){$c[] = 'margin: auto';} |
|
|
|
|
|
|
549
|
|
|
else{$c[] = 'text-align: '. $v;} |
|
550
|
|
|
}elseif($k == 'bgcolor'){ |
|
551
|
|
|
unset($a['bgcolor']); |
|
552
|
|
|
$c[] = 'background-color: '. $v; |
|
553
|
|
|
}elseif($k == 'border'){ |
|
554
|
|
|
unset($a['border']); $c[] = "border: {$v}px"; |
|
555
|
|
|
}elseif($k == 'bordercolor'){ |
|
556
|
|
|
unset($a['bordercolor']); $c[] = 'border-color: '. $v; |
|
557
|
|
View Code Duplication |
}elseif($k == 'clear'){ |
|
|
|
|
|
|
558
|
|
|
unset($a['clear']); $c[] = 'clear: '. ($v != 'all' ? $v : 'both'); |
|
559
|
|
|
}elseif($k == 'compact'){ |
|
560
|
|
|
unset($a['compact']); $c[] = 'font-size: 85%'; |
|
561
|
|
|
}elseif($k == 'height' or $k == 'width'){ |
|
|
|
|
|
|
562
|
|
|
unset($a[$k]); $c[] = $k. ': '. ($v[0] != '*' ? $v. (ctype_digit($v) ? 'px' : '') : 'auto'); |
|
563
|
|
|
}elseif($k == 'hspace'){ |
|
564
|
|
|
unset($a['hspace']); $c[] = "margin-left: {$v}px; margin-right: {$v}px"; |
|
565
|
|
|
}elseif($k == 'language' && !isset($a['type'])){ |
|
566
|
|
|
unset($a['language']); |
|
567
|
|
|
$a['type'] = 'text/'. strtolower($v); |
|
568
|
|
|
}elseif($k == 'name'){ |
|
569
|
|
|
if($C['no_deprecated_attr'] == 2 or ($e != 'a' && $e != 'map')){unset($a['name']);} |
|
|
|
|
|
|
570
|
|
|
if(!isset($a['id']) && preg_match('`[a-zA-Z][a-zA-Z\d.:_\-]*`', $v)){$a['id'] = $v;} |
|
571
|
|
|
}elseif($k == 'noshade'){ |
|
572
|
|
|
unset($a['noshade']); $c[] = 'border-style: none; border: 0; background-color: gray; color: gray'; |
|
573
|
|
|
}elseif($k == 'nowrap'){ |
|
574
|
|
|
unset($a['nowrap']); $c[] = 'white-space: nowrap'; |
|
575
|
|
View Code Duplication |
}elseif($k == 'size'){ |
|
|
|
|
|
|
576
|
|
|
unset($a['size']); $c[] = 'size: '. $v. 'px'; |
|
577
|
|
|
}elseif($k == 'start' or $k == 'value'){ |
|
|
|
|
|
|
578
|
|
|
unset($a[$k]); |
|
579
|
|
|
}elseif($k == 'type'){ |
|
580
|
|
|
unset($a['type']); |
|
581
|
|
|
static $ol_type = array('i'=>'lower-roman', 'I'=>'upper-roman', 'a'=>'lower-latin', 'A'=>'upper-latin', '1'=>'decimal'); |
|
582
|
|
|
$c[] = 'list-style-type: '. (isset($ol_type[$v]) ? $ol_type[$v] : 'decimal'); |
|
583
|
|
|
}elseif($k == 'vspace'){ |
|
584
|
|
|
unset($a['vspace']); $c[] = "margin-top: {$v}px; margin-bottom: {$v}px"; |
|
585
|
|
|
} |
|
586
|
|
|
} |
|
587
|
|
|
if(count($c)){ |
|
588
|
|
|
$c = implode('; ', $c); |
|
589
|
|
|
$a['style'] = isset($a['style']) ? rtrim($a['style'], ' ;'). '; '. $c. ';': $c. ';'; |
|
590
|
|
|
} |
|
591
|
|
|
} |
|
592
|
|
|
// unique ID |
|
593
|
|
|
if($C['unique_ids'] && isset($a['id'])){ |
|
594
|
|
|
if(!preg_match('`^[A-Za-z][A-Za-z0-9_\-.:]*$`', ($id = $a['id'])) or (isset($GLOBALS['hl_Ids'][$id]) && $C['unique_ids'] == 1)){unset($a['id']); |
|
|
|
|
|
|
595
|
|
|
}else{ |
|
596
|
|
|
while(isset($GLOBALS['hl_Ids'][$id])){$id = $C['unique_ids']. $id;} |
|
597
|
|
|
$GLOBALS['hl_Ids'][($a['id'] = $id)] = 1; |
|
598
|
|
|
} |
|
599
|
|
|
} |
|
600
|
|
|
// xml:lang |
|
601
|
|
|
if($C['xml:lang'] && isset($a['lang'])){ |
|
602
|
|
|
$a['xml:lang'] = isset($a['xml:lang']) ? $a['xml:lang'] : $a['lang']; |
|
603
|
|
|
if($C['xml:lang'] == 2){unset($a['lang']);} |
|
604
|
|
|
} |
|
605
|
|
|
// for transformed tag |
|
606
|
|
|
if(!empty($trt)){ |
|
607
|
|
|
$a['style'] = isset($a['style']) ? rtrim($a['style'], ' ;'). '; '. $trt : $trt; |
|
608
|
|
|
} |
|
609
|
|
|
// return with empty ele / |
|
610
|
|
|
if(empty($C['hook_tag'])){ |
|
611
|
|
|
$aA = ''; |
|
612
|
|
|
foreach($a as $k=>$v){$aA .= " {$k}=\"{$v}\"";} |
|
613
|
|
|
return "<{$e}{$aA}". (isset($eE[$e]) ? ' /' : ''). '>'; |
|
614
|
|
|
} |
|
615
|
|
|
else{return $C['hook_tag']($e, $a);} |
|
616
|
|
|
// eof |
|
617
|
|
|
} |
|
618
|
|
|
|
|
619
|
|
|
function hl_tag2(&$e, &$a, $t=1){ |
|
620
|
|
|
// transform tag |
|
621
|
|
|
if($e == 'center'){$e = 'div'; return 'text-align: center;';} |
|
622
|
|
|
if($e == 'dir' or $e == 'menu'){$e = 'ul'; return '';} |
|
|
|
|
|
|
623
|
|
|
if($e == 's' or $e == 'strike'){$e = 'span'; return 'text-decoration: line-through;';} |
|
|
|
|
|
|
624
|
|
|
if($e == 'u'){$e = 'span'; return 'text-decoration: underline;';} |
|
625
|
|
|
static $fs = array('0'=>'xx-small', '1'=>'xx-small', '2'=>'small', '3'=>'medium', '4'=>'large', '5'=>'x-large', '6'=>'xx-large', '7'=>'300%', '-1'=>'smaller', '-2'=>'60%', '+1'=>'larger', '+2'=>'150%', '+3'=>'200%', '+4'=>'300%'); |
|
626
|
|
|
if($e == 'font'){ |
|
627
|
|
|
$a2 = ''; |
|
628
|
|
|
if(preg_match('`face\s*=\s*(\'|")([^=]+?)\\1`i', $a, $m) or preg_match('`face\s*=(\s*)(\S+)`i', $a, $m)){ |
|
|
|
|
|
|
629
|
|
|
$a2 .= ' font-family: '. str_replace('"', '\'', trim($m[2])). ';'; |
|
630
|
|
|
} |
|
631
|
|
|
if(preg_match('`color\s*=\s*(\'|")?(.+?)(\\1|\s|$)`i', $a, $m)){ |
|
632
|
|
|
$a2 .= ' color: '. trim($m[2]). ';'; |
|
633
|
|
|
} |
|
634
|
|
|
if(preg_match('`size\s*=\s*(\'|")?(.+?)(\\1|\s|$)`i', $a, $m) && isset($fs[($m = trim($m[2]))])){ |
|
635
|
|
|
$a2 .= ' font-size: '. $fs[$m]. ';'; |
|
636
|
|
|
} |
|
637
|
|
|
$e = 'span'; return ltrim($a2); |
|
638
|
|
|
} |
|
639
|
|
|
if($t == 2){$e = 0; return 0;} |
|
640
|
|
|
return ''; |
|
641
|
|
|
// eof |
|
642
|
|
|
} |
|
643
|
|
|
|
|
644
|
|
|
function hl_tidy($t, $w, $p){ |
|
645
|
|
|
// Tidy/compact HTM |
|
646
|
|
|
if(strpos(' pre,script,textarea', "$p,")){return $t;} |
|
647
|
|
|
$t = preg_replace('`\s+`', ' ', preg_replace_callback(array('`(<(!\[CDATA\[))(.+?)(\]\]>)`sm', '`(<(!--))(.+?)(-->)`sm', '`(<(pre|script|textarea)[^>]*?>)(.+?)(</\2>)`sm'), create_function('$m', 'return $m[1]. str_replace(array("<", ">", "\n", "\r", "\t", " "), array("\x01", "\x02", "\x03", "\x04", "\x05", "\x07"), $m[3]). $m[4];'), $t)); |
|
|
|
|
|
|
648
|
|
|
if(($w = strtolower($w)) == -1){ |
|
649
|
|
|
return str_replace(array("\x01", "\x02", "\x03", "\x04", "\x05", "\x07"), array('<', '>', "\n", "\r", "\t", ' '), $t); |
|
650
|
|
|
} |
|
651
|
|
|
$s = strpos(" $w", 't') ? "\t" : ' '; |
|
652
|
|
|
$s = preg_match('`\d`', $w, $m) ? str_repeat($s, $m[0]) : str_repeat($s, ($s == "\t" ? 1 : 2)); |
|
653
|
|
|
$N = preg_match('`[ts]([1-9])`', $w, $m) ? $m[1] : 0; |
|
654
|
|
|
$a = array('br'=>1); |
|
655
|
|
|
$b = array('button'=>1, 'input'=>1, 'option'=>1, 'param'=>1); |
|
656
|
|
|
$c = array('caption'=>1, 'dd'=>1, 'dt'=>1, 'h1'=>1, 'h2'=>1, 'h3'=>1, 'h4'=>1, 'h5'=>1, 'h6'=>1, 'isindex'=>1, 'label'=>1, 'legend'=>1, 'li'=>1, 'object'=>1, 'p'=>1, 'pre'=>1, 'td'=>1, 'textarea'=>1, 'th'=>1); |
|
657
|
|
|
$d = array('address'=>1, 'blockquote'=>1, 'center'=>1, 'colgroup'=>1, 'dir'=>1, 'div'=>1, 'dl'=>1, 'fieldset'=>1, 'form'=>1, 'hr'=>1, 'iframe'=>1, 'map'=>1, 'menu'=>1, 'noscript'=>1, 'ol'=>1, 'optgroup'=>1, 'rbc'=>1, 'rtc'=>1, 'ruby'=>1, 'script'=>1, 'select'=>1, 'table'=>1, 'tbody'=>1, 'tfoot'=>1, 'thead'=>1, 'tr'=>1, 'ul'=>1); |
|
658
|
|
|
$T = explode('<', $t); |
|
659
|
|
|
$X = 1; |
|
660
|
|
|
while($X){ |
|
661
|
|
|
$n = $N; |
|
662
|
|
|
$t = $T; |
|
663
|
|
|
ob_start(); |
|
664
|
|
|
if(isset($d[$p])){echo str_repeat($s, ++$n);} |
|
665
|
|
|
echo ltrim(array_shift($t)); |
|
666
|
|
|
for($i=-1, $j=count($t); ++$i<$j;){ |
|
667
|
|
|
$r = ''; list($e, $r) = explode('>', $t[$i]); |
|
668
|
|
|
$x = $e[0] == '/' ? 0 : (substr($e, -1) == '/' ? 1 : ($e[0] != '!' ? 2 : -1)); |
|
669
|
|
|
$y = !$x ? ltrim($e, '/') : ($x > 0 ? substr($e, 0, strcspn($e, ' ')) : 0); |
|
670
|
|
|
$e = "<$e>"; |
|
671
|
|
|
if(isset($d[$y])){ |
|
672
|
|
|
if(!$x){ |
|
673
|
|
|
if($n){echo "\n", str_repeat($s, --$n), "$e\n", str_repeat($s, $n);} |
|
674
|
|
|
else{++$N; ob_end_clean(); continue 2;} |
|
675
|
|
|
} |
|
676
|
|
|
else{echo "\n", str_repeat($s, $n), "$e\n", str_repeat($s, ($x != 1 ? ++$n : $n));} |
|
677
|
|
|
echo $r; continue; |
|
678
|
|
|
} |
|
679
|
|
|
$f = "\n". str_repeat($s, $n); |
|
680
|
|
|
if(isset($c[$y])){ |
|
681
|
|
|
if(!$x){echo $e, $f, $r;} |
|
682
|
|
|
else{echo $f, $e, $r;} |
|
683
|
|
|
}elseif(isset($b[$y])){echo $f, $e, $r; |
|
684
|
|
|
}elseif(isset($a[$y])){echo $e, $f, $r; |
|
685
|
|
|
}elseif(!$y){echo $f, $e, $f, $r; |
|
686
|
|
|
}else{echo $e, $r;} |
|
687
|
|
|
} |
|
688
|
|
|
$X = 0; |
|
689
|
|
|
} |
|
690
|
|
|
$t = str_replace(array("\n ", " \n"), "\n", preg_replace('`[\n]\s*?[\n]+`', "\n", ob_get_contents())); |
|
691
|
|
|
ob_end_clean(); |
|
692
|
|
|
if(($l = strpos(" $w", 'r') ? (strpos(" $w", 'n') ? "\r\n" : "\r") : 0)){ |
|
693
|
|
|
$t = str_replace("\n", $l, $t); |
|
694
|
|
|
} |
|
695
|
|
|
return str_replace(array("\x01", "\x02", "\x03", "\x04", "\x05", "\x07"), array('<', '>', "\n", "\r", "\t", ' '), $t); |
|
696
|
|
|
// eof |
|
697
|
|
|
} |
|
698
|
|
|
|
|
699
|
|
|
function hl_version(){ |
|
700
|
|
|
// rel |
|
701
|
|
|
return '1.1.17'; |
|
702
|
|
|
// eof |
|
703
|
|
|
} |
|
704
|
|
|
|
|
705
|
|
|
function kses($t, $h, $p=array('http', 'https', 'ftp', 'news', 'nntp', 'telnet', 'gopher', 'mailto')){ |
|
706
|
|
|
// kses compat |
|
707
|
|
|
foreach($h as $k=>$v){ |
|
708
|
|
|
$h[$k]['n']['*'] = 1; |
|
709
|
|
|
} |
|
710
|
|
|
$C['cdata'] = $C['comment'] = $C['make_tag_strict'] = $C['no_deprecated_attr'] = $C['unique_ids'] = 0; |
|
|
|
|
|
|
711
|
|
|
$C['keep_bad'] = 1; |
|
712
|
|
|
$C['elements'] = count($h) ? strtolower(implode(',', array_keys($h))) : '-*'; |
|
713
|
|
|
$C['hook'] = 'kses_hook'; |
|
714
|
|
|
$C['schemes'] = '*:'. implode(',', $p); |
|
715
|
|
|
return htmLawed($t, $C, $h); |
|
|
|
|
|
|
716
|
|
|
// eof |
|
717
|
|
|
} |
|
718
|
|
|
|
|
719
|
|
|
function kses_hook($t, &$C, &$S){ |
|
|
|
|
|
|
720
|
|
|
// kses compat |
|
721
|
|
|
return $t; |
|
722
|
|
|
// eof |
|
723
|
|
|
} |
thinktomorrow /
squanto
Loading history...
Instead of super-globals, we recommend to explicitly inject the dependencies of your class. This makes your code less dependent on global state and it becomes generally more testable: