|
1
|
|
|
<?php |
|
2
|
|
|
/** |
|
3
|
|
|
* This file is part of the O2System PHP Framework package. |
|
4
|
|
|
* |
|
5
|
|
|
* For the full copyright and license information, please view the LICENSE |
|
6
|
|
|
* file that was distributed with this source code. |
|
7
|
|
|
* |
|
8
|
|
|
* @author Steeve Andrian Salim |
|
9
|
|
|
* @copyright Copyright (c) Steeve Andrian Salim |
|
10
|
|
|
*/ |
|
11
|
|
|
// ------------------------------------------------------------------------ |
|
12
|
|
|
/** |
|
13
|
|
|
* Security Helper |
|
14
|
|
|
* |
|
15
|
|
|
* A collection of helper function for security purposes. |
|
16
|
|
|
*/ |
|
17
|
|
|
// ------------------------------------------------------------------------ |
|
18
|
|
|
|
|
19
|
|
|
if ( ! function_exists('strip_image_tags')) { |
|
20
|
|
|
/** |
|
21
|
|
|
* strip_image_tags |
|
22
|
|
|
* |
|
23
|
|
|
* Strip all image tags from string of HTML source code. |
|
24
|
|
|
* |
|
25
|
|
|
* @param string $source_code The string of HTML source code. |
|
26
|
|
|
* |
|
27
|
|
|
* @return string |
|
28
|
|
|
*/ |
|
29
|
|
|
function strip_image_tags($source_code) |
|
30
|
|
|
{ |
|
31
|
|
|
return preg_replace( |
|
32
|
|
|
[ |
|
33
|
|
|
'#<img[\s/]+.*?src\s*=\s*(["\'])([^\\1]+?)\\1.*?\>#i', |
|
34
|
|
|
'#<img[\s/]+.*?src\s*=\s*?(([^\s"\'=<>`]+)).*?\>#i', |
|
35
|
|
|
], |
|
36
|
|
|
'\\2', |
|
37
|
|
|
$source_code |
|
38
|
|
|
); |
|
39
|
|
|
} |
|
40
|
|
|
} |
|
41
|
|
|
|
|
42
|
|
|
//-------------------------------------------------------------------- |
|
43
|
|
|
|
|
44
|
|
|
if ( ! function_exists('strip_cdata')) { |
|
45
|
|
|
/** |
|
46
|
|
|
* strip_cdata |
|
47
|
|
|
* |
|
48
|
|
|
* Strip all CDATA encapsulation from string of HTML source code. |
|
49
|
|
|
* |
|
50
|
|
|
* @param string $source_code The string of HTML source code. |
|
51
|
|
|
* |
|
52
|
|
|
* @return string |
|
53
|
|
|
*/ |
|
54
|
|
|
function strip_cdata($source_code) |
|
55
|
|
|
{ |
|
56
|
|
|
preg_match_all('/<!\[cdata\[(.*?)\]\]>/is', $source_code, $matches); |
|
57
|
|
|
|
|
58
|
|
|
return str_replace($matches[ 0 ], $matches[ 1 ], $source_code); |
|
59
|
|
|
} |
|
60
|
|
|
} |
|
61
|
|
|
// ------------------------------------------------------------------------ |
|
62
|
|
|
|
|
63
|
|
|
if ( ! function_exists('strips_all_tags')) { |
|
64
|
|
|
/** |
|
65
|
|
|
* strips_all_tags |
|
66
|
|
|
* |
|
67
|
|
|
* Strip all HTML tags from string of HTML source code but keep safe |
|
68
|
|
|
* the original content. |
|
69
|
|
|
* |
|
70
|
|
|
* @param string $source_code The string of HTML source code. |
|
71
|
|
|
* |
|
72
|
|
|
* @return string |
|
73
|
|
|
*/ |
|
74
|
|
|
function strips_all_tags($source_code) |
|
75
|
|
|
{ |
|
76
|
|
|
return preg_replace([ |
|
77
|
|
|
'@<script[^>]*?>.*?</script>@si', // Strip out javascript |
|
78
|
|
|
'@<[\/\!]*?[^<>]*?>@si', // Strip out HTML tags |
|
79
|
|
|
'@<style[^>]*?>.*?</style>@siU', // Strip style tags properly |
|
80
|
|
|
'@<![\s\S]*?--[ \t\n\r]*>@' // Strip multi-line comments including CDATA |
|
81
|
|
|
], '', $source_code); |
|
82
|
|
|
} |
|
83
|
|
|
} |
|
84
|
|
|
|
|
85
|
|
|
// ------------------------------------------------------------------------ |
|
86
|
|
|
|
|
87
|
|
|
if ( ! function_exists('strips_tags')) { |
|
88
|
|
|
/** |
|
89
|
|
|
* strips_tags |
|
90
|
|
|
* |
|
91
|
|
|
* Strips all HTML tags and its content at the defined tags. |
|
92
|
|
|
* Strip out all the content between any tag that has an opening and closing tag, like <table>, <object>, etc. |
|
93
|
|
|
* |
|
94
|
|
|
* @param string $source_code The string of HTML source code. |
|
95
|
|
|
* @param string $disallowed_tags The list of disallowed HTML tags, separated with |. |
|
96
|
|
|
* @param string $allowed_tags The list of allowed HTML tags, separated with |. |
|
97
|
|
|
* |
|
98
|
|
|
* @return string |
|
99
|
|
|
*/ |
|
100
|
|
|
function strips_tags($source_code, $disallowed_tags = 'script|style|noframes|select|option', $allowed_tags = '') |
|
101
|
|
|
{ |
|
102
|
|
|
//prep the string |
|
103
|
|
|
$source_code = ' ' . $source_code; |
|
104
|
|
|
|
|
105
|
|
|
//initialize keep tag logic |
|
106
|
|
|
if (strlen($allowed_tags) > 0) { |
|
107
|
|
|
$k = explode('|', $allowed_tags); |
|
108
|
|
|
for ($i = 0; $i < count($k); $i++) { |
|
|
|
|
|
|
109
|
|
|
$source_code = str_replace('<' . $k[ $i ], '[{(' . $k[ $i ], $source_code); |
|
110
|
|
|
$source_code = str_replace('</' . $k[ $i ], '[{(/' . $k[ $i ], $source_code); |
|
111
|
|
|
} |
|
112
|
|
|
} |
|
113
|
|
|
//begin removal |
|
114
|
|
|
//remove comment blocks |
|
115
|
|
|
while (stripos($source_code, '<!--') > 0) { |
|
116
|
|
|
$pos[ 1 ] = stripos($source_code, '<!--'); |
|
117
|
|
|
$pos[ 2 ] = stripos($source_code, '-->', $pos[ 1 ]); |
|
118
|
|
|
$len[ 1 ] = $pos[ 2 ] - $pos[ 1 ] + 3; |
|
119
|
|
|
$x = substr($source_code, $pos[ 1 ], $len[ 1 ]); |
|
120
|
|
|
$source_code = str_replace($x, '', $source_code); |
|
121
|
|
|
} |
|
122
|
|
|
//remove tags with content between them |
|
123
|
|
|
if (strlen($disallowed_tags) > 0) { |
|
124
|
|
|
$e = explode('|', $disallowed_tags); |
|
125
|
|
|
for ($i = 0; $i < count($e); $i++) { |
|
|
|
|
|
|
126
|
|
|
while (stripos($source_code, '<' . $e[ $i ]) > 0) { |
|
127
|
|
|
$len[ 1 ] = strlen('<' . $e[ $i ]); |
|
128
|
|
|
$pos[ 1 ] = stripos($source_code, '<' . $e[ $i ]); |
|
129
|
|
|
$pos[ 2 ] = stripos($source_code, $e[ $i ] . '>', $pos[ 1 ] + $len[ 1 ]); |
|
130
|
|
|
$len[ 2 ] = $pos[ 2 ] - $pos[ 1 ] + $len[ 1 ]; |
|
131
|
|
|
$x = substr($source_code, $pos[ 1 ], $len[ 2 ]); |
|
132
|
|
|
$source_code = str_replace($x, '', $source_code); |
|
133
|
|
|
} |
|
134
|
|
|
} |
|
135
|
|
|
} |
|
136
|
|
|
//remove remaining tags |
|
137
|
|
|
while (stripos($source_code, '<') > 0) { |
|
138
|
|
|
$pos[ 1 ] = stripos($source_code, '<'); |
|
139
|
|
|
$pos[ 2 ] = stripos($source_code, '>', $pos[ 1 ]); |
|
140
|
|
|
$len[ 1 ] = $pos[ 2 ] - $pos[ 1 ] + 1; |
|
141
|
|
|
$x = substr($source_code, $pos[ 1 ], $len[ 1 ]); |
|
142
|
|
|
$source_code = str_replace($x, '', $source_code); |
|
143
|
|
|
} |
|
144
|
|
|
//finalize keep tag |
|
145
|
|
|
if (strlen($allowed_tags) > 0) { |
|
146
|
|
|
for ($i = 0; $i < count($k); $i++) { |
|
|
|
|
|
|
147
|
|
|
$source_code = str_replace('[{(' . $k[ $i ], '<' . $k[ $i ], $source_code); |
|
148
|
|
|
$source_code = str_replace('[{(/' . $k[ $i ], '</' . $k[ $i ], $source_code); |
|
149
|
|
|
} |
|
150
|
|
|
} |
|
151
|
|
|
|
|
152
|
|
|
return trim($source_code); |
|
153
|
|
|
} |
|
154
|
|
|
} |
|
155
|
|
|
|
|
156
|
|
|
// ------------------------------------------------------------------------ |
|
157
|
|
|
|
|
158
|
|
|
if ( ! function_exists('strip_word_doc')) { |
|
159
|
|
|
/** |
|
160
|
|
|
* strip_word_doc |
|
161
|
|
|
* |
|
162
|
|
|
* Strip all word doc tags from string of source code. |
|
163
|
|
|
* |
|
164
|
|
|
* @param string $source_code The string of HTML source code. |
|
165
|
|
|
* @param string $allowed_tags The list of disallowed HTML tags, separated with |. |
|
166
|
|
|
* |
|
167
|
|
|
* @return string |
|
168
|
|
|
*/ |
|
169
|
|
|
function strip_word_doc($source_code, $allowed_tags = '') |
|
170
|
|
|
{ |
|
171
|
|
|
mb_regex_encoding('UTF-8'); |
|
172
|
|
|
|
|
173
|
|
|
//replace MS special characters first |
|
174
|
|
|
$search = [ |
|
175
|
|
|
'/‘/u', |
|
176
|
|
|
'/’/u', |
|
177
|
|
|
'/“/u', |
|
178
|
|
|
'/”/u', |
|
179
|
|
|
'/—/u', |
|
180
|
|
|
]; |
|
181
|
|
|
$replace = [ |
|
182
|
|
|
'\'', |
|
183
|
|
|
'\'', |
|
184
|
|
|
'"', |
|
185
|
|
|
'"', |
|
186
|
|
|
'-', |
|
187
|
|
|
]; |
|
188
|
|
|
$source_code = preg_replace($search, $replace, $source_code); |
|
189
|
|
|
|
|
190
|
|
|
//make sure _all_ html entities are converted to the plain ascii equivalents - it appears |
|
191
|
|
|
//in some MS headers, some html entities are encoded and some aren't |
|
192
|
|
|
$source_code = html_entity_decode($source_code, ENT_QUOTES, 'UTF-8'); |
|
193
|
|
|
|
|
194
|
|
|
//try to strip out any C style comments first, since these, embedded in html comments, seem to |
|
195
|
|
|
//prevent strip_tags from removing html comments (MS Word introduced combination) |
|
196
|
|
|
if (mb_stripos($source_code, '/*') !== false) { |
|
197
|
|
|
$source_code = mb_eregi_replace('#/\*.*?\*/#s', '', $source_code, 'm'); |
|
198
|
|
|
} |
|
199
|
|
|
|
|
200
|
|
|
//introduce a space into any arithmetic expressions that could be caught by strip_tags so that they won't be |
|
201
|
|
|
//'<1' becomes '< 1'(note: somewhat application specific) |
|
202
|
|
|
$source_code = preg_replace( |
|
203
|
|
|
[ |
|
204
|
|
|
'/<([0-9]+)/', |
|
205
|
|
|
], |
|
206
|
|
|
[ |
|
207
|
|
|
'< $1', |
|
208
|
|
|
], |
|
209
|
|
|
$source_code |
|
210
|
|
|
); |
|
211
|
|
|
$source_code = strip_tags($source_code, $allowed_tags); |
|
212
|
|
|
|
|
213
|
|
|
//eliminate extraneous whitespace from start and end of line, or anywhere there are two or more spaces, convert it to one |
|
214
|
|
|
$source_code = preg_replace( |
|
215
|
|
|
[ |
|
216
|
|
|
'/^\s\s+/', |
|
217
|
|
|
'/\s\s+$/', |
|
218
|
|
|
'/\s\s+/u', |
|
219
|
|
|
], |
|
220
|
|
|
[ |
|
221
|
|
|
'', |
|
222
|
|
|
'', |
|
223
|
|
|
' ', |
|
224
|
|
|
], |
|
225
|
|
|
$source_code |
|
226
|
|
|
); |
|
227
|
|
|
|
|
228
|
|
|
//strip out inline css and simplify style tags |
|
229
|
|
|
$search = [ |
|
230
|
|
|
'#<(strong|b)[^>]*>(.*?)</(strong|b)>#isu', |
|
231
|
|
|
'#<(em|i)[^>]*>(.*?)</(em|i)>#isu', |
|
232
|
|
|
'#<u[^>]*>(.*?)</u>#isu', |
|
233
|
|
|
]; |
|
234
|
|
|
$replace = [ |
|
235
|
|
|
'<b>$2</b>', |
|
236
|
|
|
'<i>$2</i>', |
|
237
|
|
|
'<u>$1</u>', |
|
238
|
|
|
]; |
|
239
|
|
|
$source_code = preg_replace($search, $replace, $source_code); |
|
240
|
|
|
|
|
241
|
|
|
//on some of the ?newer MS Word exports, where you get conditionals of the form 'if gte mso 9', etc., it appears |
|
242
|
|
|
//that whatever is in one of the html comments prevents strip_tags from eradicating the html comment that contains |
|
243
|
|
|
//some MS Style Definitions - this last bit gets rid of any leftover comments */ |
|
244
|
|
|
$num_matches = preg_match_all("/\<!--/u", $source_code, $matches); |
|
245
|
|
|
if ($num_matches) { |
|
246
|
|
|
$source_code = preg_replace('/\<!--(.)*--\>/isu', '', $source_code); |
|
247
|
|
|
} |
|
248
|
|
|
|
|
249
|
|
|
return $source_code; |
|
250
|
|
|
} |
|
251
|
|
|
} |
|
252
|
|
|
|
|
253
|
|
|
//-------------------------------------------------------------------- |
|
254
|
|
|
|
|
255
|
|
|
if ( ! function_exists('strip_slashes_recursive')) { |
|
256
|
|
|
/** |
|
257
|
|
|
* strip_slashes_recursive |
|
258
|
|
|
* |
|
259
|
|
|
* Recursive Strip Slashes |
|
260
|
|
|
* |
|
261
|
|
|
* Un-quotes a quoted string |
|
262
|
|
|
* |
|
263
|
|
|
* @link http://php.net/manual/en/function.stripslashes.php |
|
264
|
|
|
* |
|
265
|
|
|
* @param string $string <p> |
|
266
|
|
|
* The input string. |
|
267
|
|
|
* </p> |
|
268
|
|
|
* |
|
269
|
|
|
* @return string a string with backslashes stripped off. |
|
270
|
|
|
* (\' becomes ' and so on.) |
|
271
|
|
|
* Double backslashes (\\) are made into a single |
|
272
|
|
|
* backslash (\). |
|
273
|
|
|
* @since 4.0 |
|
274
|
|
|
* @since 5.0 |
|
275
|
|
|
*/ |
|
276
|
|
|
function strip_slashes_recursive($string) |
|
277
|
|
|
{ |
|
278
|
|
|
$string = is_array($string) ? array_map('strip_slashes_recursive', $string) : stripslashes($string); |
|
|
|
|
|
|
279
|
|
|
|
|
280
|
|
|
return $string; |
|
281
|
|
|
} |
|
282
|
|
|
} |
|
283
|
|
|
|
|
284
|
|
|
// ------------------------------------------------------------------------ |
|
285
|
|
|
|
|
286
|
|
|
if ( ! function_exists('strip_comments')) { |
|
287
|
|
|
/** |
|
288
|
|
|
* strip_comments |
|
289
|
|
|
* |
|
290
|
|
|
* Strip HTML Comments |
|
291
|
|
|
* |
|
292
|
|
|
* @param string $source_code HTML Source Code |
|
293
|
|
|
* |
|
294
|
|
|
* @return string |
|
295
|
|
|
*/ |
|
296
|
|
|
function strip_comments($source_code) |
|
297
|
|
|
{ |
|
298
|
|
|
return preg_replace('/<!--[\s\S]*?-->/', '', $source_code); |
|
299
|
|
|
} |
|
300
|
|
|
} |
|
301
|
|
|
|
|
302
|
|
|
// ------------------------------------------------------------------------ |
|
303
|
|
|
|
|
304
|
|
|
if ( ! function_exists('clean_white_space')) { |
|
305
|
|
|
/** |
|
306
|
|
|
* clean_white_space |
|
307
|
|
|
* |
|
308
|
|
|
* Clean HTML Whitespace |
|
309
|
|
|
* |
|
310
|
|
|
* @param string $source_code HTML Source Code |
|
311
|
|
|
* |
|
312
|
|
|
* @return string |
|
313
|
|
|
*/ |
|
314
|
|
|
function clean_white_space($source_code) |
|
315
|
|
|
{ |
|
316
|
|
|
$source_code = str_replace(["\n", "\r", ' ', "\t"], '', $source_code); |
|
317
|
|
|
|
|
318
|
|
|
return preg_replace('| +|', ' ', $source_code); |
|
319
|
|
|
} |
|
320
|
|
|
} |
|
321
|
|
|
|
|
322
|
|
|
// ------------------------------------------------------------------------ |
|
323
|
|
|
|
|
324
|
|
|
if ( ! function_exists('encode_php_tags')) { |
|
325
|
|
|
/** |
|
326
|
|
|
* encode_php_tags |
|
327
|
|
|
* |
|
328
|
|
|
* Encode PHP tags to entities. |
|
329
|
|
|
* |
|
330
|
|
|
* @param string $string The string tobe encoded. |
|
331
|
|
|
* |
|
332
|
|
|
* @return string |
|
333
|
|
|
*/ |
|
334
|
|
|
function encode_php_tags($string) |
|
335
|
|
|
{ |
|
336
|
|
|
return str_replace(['<?', '?>'], ['<?', '?>'], $string); |
|
337
|
|
|
} |
|
338
|
|
|
} |
|
339
|
|
|
|
|
340
|
|
|
// ------------------------------------------------------------------------ |
|
341
|
|
|
|
|
342
|
|
|
if ( ! function_exists('escape_html')) { |
|
343
|
|
|
/** |
|
344
|
|
|
* escape_html |
|
345
|
|
|
* |
|
346
|
|
|
* Returns HTML escaped variable. |
|
347
|
|
|
* |
|
348
|
|
|
* @param mixed $source_code The input string or array of strings to be escaped. |
|
349
|
|
|
* @param bool $double_encode $double_encode set to FALSE prevents escaping twice. |
|
350
|
|
|
* |
|
351
|
|
|
* @return mixed The escaped string or array of strings as a result. |
|
352
|
|
|
*/ |
|
353
|
|
|
function escape_html($source_code, $encoding = 'UTF-8', $double_encode = true) |
|
354
|
|
|
{ |
|
355
|
|
|
if (is_array($source_code)) { |
|
356
|
|
|
return array_map('escape_html', $source_code, array_fill(0, count($source_code), $double_encode)); |
|
357
|
|
|
} |
|
358
|
|
|
|
|
359
|
|
|
return htmlspecialchars($source_code, ENT_QUOTES, $encoding, $double_encode); |
|
360
|
|
|
} |
|
361
|
|
|
} |
If the size of the collection does not change during the iteration, it is generally a good practice to compute it beforehand, and not on each iteration: