1 | <?php if ( ! defined('BASEPATH')) exit('No direct script access allowed'); |
---|
2 | /** |
---|
3 | * CodeIgniter |
---|
4 | * |
---|
5 | * An open source application development framework for PHP 5.1.6 or newer |
---|
6 | * |
---|
7 | * @package CodeIgniter |
---|
8 | * @author ExpressionEngine Dev Team |
---|
9 | * @copyright Copyright (c) 2008 - 2011, EllisLab, Inc. |
---|
10 | * @license http://codeigniter.com/user_guide/license.html |
---|
11 | * @link http://codeigniter.com |
---|
12 | * @since Version 1.0 |
---|
13 | * @filesource |
---|
14 | */ |
---|
15 | |
---|
16 | // ------------------------------------------------------------------------ |
---|
17 | |
---|
18 | /** |
---|
19 | * Typography Class |
---|
20 | * |
---|
21 | * |
---|
22 | * @access private |
---|
23 | * @category Helpers |
---|
24 | * @author ExpressionEngine Dev Team |
---|
25 | * @link http://codeigniter.com/user_guide/helpers/ |
---|
26 | */ |
---|
27 | class CI_Typography { |
---|
28 | |
---|
29 | // Block level elements that should not be wrapped inside <p> tags |
---|
30 | var $block_elements = 'address|blockquote|div|dl|fieldset|form|h\d|hr|noscript|object|ol|p|pre|script|table|ul'; |
---|
31 | |
---|
32 | // Elements that should not have <p> and <br /> tags within them. |
---|
33 | var $skip_elements = 'p|pre|ol|ul|dl|object|table|h\d'; |
---|
34 | |
---|
35 | // Tags we want the parser to completely ignore when splitting the string. |
---|
36 | var $inline_elements = 'a|abbr|acronym|b|bdo|big|br|button|cite|code|del|dfn|em|i|img|ins|input|label|map|kbd|q|samp|select|small|span|strong|sub|sup|textarea|tt|var'; |
---|
37 | |
---|
38 | // array of block level elements that require inner content to be within another block level element |
---|
39 | var $inner_block_required = array('blockquote'); |
---|
40 | |
---|
41 | // the last block element parsed |
---|
42 | var $last_block_element = ''; |
---|
43 | |
---|
44 | // whether or not to protect quotes within { curly braces } |
---|
45 | var $protect_braced_quotes = FALSE; |
---|
46 | |
---|
47 | /** |
---|
48 | * Auto Typography |
---|
49 | * |
---|
50 | * This function converts text, making it typographically correct: |
---|
51 | * - Converts double spaces into paragraphs. |
---|
52 | * - Converts single line breaks into <br /> tags |
---|
53 | * - Converts single and double quotes into correctly facing curly quote entities. |
---|
54 | * - Converts three dots into ellipsis. |
---|
55 | * - Converts double dashes into em-dashes. |
---|
56 | * - Converts two spaces into entities |
---|
57 | * |
---|
58 | * @access public |
---|
59 | * @param string |
---|
60 | * @param bool whether to reduce more then two consecutive newlines to two |
---|
61 | * @return string |
---|
62 | */ |
---|
63 | function auto_typography($str, $reduce_linebreaks = FALSE) |
---|
64 | { |
---|
65 | if ($str == '') |
---|
66 | { |
---|
67 | return ''; |
---|
68 | } |
---|
69 | |
---|
70 | // Standardize Newlines to make matching easier |
---|
71 | if (strpos($str, "\r") !== FALSE) |
---|
72 | { |
---|
73 | $str = str_replace(array("\r\n", "\r"), "\n", $str); |
---|
74 | } |
---|
75 | |
---|
76 | // Reduce line breaks. If there are more than two consecutive linebreaks |
---|
77 | // we'll compress them down to a maximum of two since there's no benefit to more. |
---|
78 | if ($reduce_linebreaks === TRUE) |
---|
79 | { |
---|
80 | $str = preg_replace("/\n\n+/", "\n\n", $str); |
---|
81 | } |
---|
82 | |
---|
83 | // HTML comment tags don't conform to patterns of normal tags, so pull them out separately, only if needed |
---|
84 | $html_comments = array(); |
---|
85 | if (strpos($str, '<!--') !== FALSE) |
---|
86 | { |
---|
87 | if (preg_match_all("#(<!\-\-.*?\-\->)#s", $str, $matches)) |
---|
88 | { |
---|
89 | for ($i = 0, $total = count($matches[0]); $i < $total; $i++) |
---|
90 | { |
---|
91 | $html_comments[] = $matches[0][$i]; |
---|
92 | $str = str_replace($matches[0][$i], '{@HC'.$i.'}', $str); |
---|
93 | } |
---|
94 | } |
---|
95 | } |
---|
96 | |
---|
97 | // match and yank <pre> tags if they exist. It's cheaper to do this separately since most content will |
---|
98 | // not contain <pre> tags, and it keeps the PCRE patterns below simpler and faster |
---|
99 | if (strpos($str, '<pre') !== FALSE) |
---|
100 | { |
---|
101 | $str = preg_replace_callback("#<pre.*?>.*?</pre>#si", array($this, '_protect_characters'), $str); |
---|
102 | } |
---|
103 | |
---|
104 | // Convert quotes within tags to temporary markers. |
---|
105 | $str = preg_replace_callback("#<.+?>#si", array($this, '_protect_characters'), $str); |
---|
106 | |
---|
107 | // Do the same with braces if necessary |
---|
108 | if ($this->protect_braced_quotes === TRUE) |
---|
109 | { |
---|
110 | $str = preg_replace_callback("#\{.+?\}#si", array($this, '_protect_characters'), $str); |
---|
111 | } |
---|
112 | |
---|
113 | // Convert "ignore" tags to temporary marker. The parser splits out the string at every tag |
---|
114 | // it encounters. Certain inline tags, like image tags, links, span tags, etc. will be |
---|
115 | // adversely affected if they are split out so we'll convert the opening bracket < temporarily to: {@TAG} |
---|
116 | $str = preg_replace("#<(/*)(".$this->inline_elements.")([ >])#i", "{@TAG}\\1\\2\\3", $str); |
---|
117 | |
---|
118 | // Split the string at every tag. This expression creates an array with this prototype: |
---|
119 | // |
---|
120 | // [array] |
---|
121 | // { |
---|
122 | // [0] = <opening tag> |
---|
123 | // [1] = Content... |
---|
124 | // [2] = <closing tag> |
---|
125 | // Etc... |
---|
126 | // } |
---|
127 | $chunks = preg_split('/(<(?:[^<>]+(?:"[^"]*"|\'[^\']*\')?)+>)/', $str, -1, PREG_SPLIT_DELIM_CAPTURE|PREG_SPLIT_NO_EMPTY); |
---|
128 | |
---|
129 | // Build our finalized string. We cycle through the array, skipping tags, and processing the contained text |
---|
130 | $str = ''; |
---|
131 | $process = TRUE; |
---|
132 | $paragraph = FALSE; |
---|
133 | $current_chunk = 0; |
---|
134 | $total_chunks = count($chunks); |
---|
135 | |
---|
136 | foreach ($chunks as $chunk) |
---|
137 | { |
---|
138 | $current_chunk++; |
---|
139 | |
---|
140 | // Are we dealing with a tag? If so, we'll skip the processing for this cycle. |
---|
141 | // Well also set the "process" flag which allows us to skip <pre> tags and a few other things. |
---|
142 | if (preg_match("#<(/*)(".$this->block_elements.").*?>#", $chunk, $match)) |
---|
143 | { |
---|
144 | if (preg_match("#".$this->skip_elements."#", $match[2])) |
---|
145 | { |
---|
146 | $process = ($match[1] == '/') ? TRUE : FALSE; |
---|
147 | } |
---|
148 | |
---|
149 | if ($match[1] == '') |
---|
150 | { |
---|
151 | $this->last_block_element = $match[2]; |
---|
152 | } |
---|
153 | |
---|
154 | $str .= $chunk; |
---|
155 | continue; |
---|
156 | } |
---|
157 | |
---|
158 | if ($process == FALSE) |
---|
159 | { |
---|
160 | $str .= $chunk; |
---|
161 | continue; |
---|
162 | } |
---|
163 | |
---|
164 | // Force a newline to make sure end tags get processed by _format_newlines() |
---|
165 | if ($current_chunk == $total_chunks) |
---|
166 | { |
---|
167 | $chunk .= "\n"; |
---|
168 | } |
---|
169 | |
---|
170 | // Convert Newlines into <p> and <br /> tags |
---|
171 | $str .= $this->_format_newlines($chunk); |
---|
172 | } |
---|
173 | |
---|
174 | // No opening block level tag? Add it if needed. |
---|
175 | if ( ! preg_match("/^\s*<(?:".$this->block_elements.")/i", $str)) |
---|
176 | { |
---|
177 | $str = preg_replace("/^(.*?)<(".$this->block_elements.")/i", '<p>$1</p><$2', $str); |
---|
178 | } |
---|
179 | |
---|
180 | // Convert quotes, elipsis, em-dashes, non-breaking spaces, and ampersands |
---|
181 | $str = $this->format_characters($str); |
---|
182 | |
---|
183 | // restore HTML comments |
---|
184 | for ($i = 0, $total = count($html_comments); $i < $total; $i++) |
---|
185 | { |
---|
186 | // remove surrounding paragraph tags, but only if there's an opening paragraph tag |
---|
187 | // otherwise HTML comments at the ends of paragraphs will have the closing tag removed |
---|
188 | // if '<p>{@HC1}' then replace <p>{@HC1}</p> with the comment, else replace only {@HC1} with the comment |
---|
189 | $str = preg_replace('#(?(?=<p>\{@HC'.$i.'\})<p>\{@HC'.$i.'\}(\s*</p>)|\{@HC'.$i.'\})#s', $html_comments[$i], $str); |
---|
190 | } |
---|
191 | |
---|
192 | // Final clean up |
---|
193 | $table = array( |
---|
194 | |
---|
195 | // If the user submitted their own paragraph tags within the text |
---|
196 | // we will retain them instead of using our tags. |
---|
197 | '/(<p[^>*?]>)<p>/' => '$1', // <?php BBEdit syntax coloring bug fix |
---|
198 | |
---|
199 | // Reduce multiple instances of opening/closing paragraph tags to a single one |
---|
200 | '#(</p>)+#' => '</p>', |
---|
201 | '/(<p>\W*<p>)+/' => '<p>', |
---|
202 | |
---|
203 | // Clean up stray paragraph tags that appear before block level elements |
---|
204 | '#<p></p><('.$this->block_elements.')#' => '<$1', |
---|
205 | |
---|
206 | // Clean up stray non-breaking spaces preceeding block elements |
---|
207 | '#( \s*)+<('.$this->block_elements.')#' => ' <$2', |
---|
208 | |
---|
209 | // Replace the temporary markers we added earlier |
---|
210 | '/\{@TAG\}/' => '<', |
---|
211 | '/\{@DQ\}/' => '"', |
---|
212 | '/\{@SQ\}/' => "'", |
---|
213 | '/\{@DD\}/' => '--', |
---|
214 | '/\{@NBS\}/' => ' ', |
---|
215 | |
---|
216 | // An unintended consequence of the _format_newlines function is that |
---|
217 | // some of the newlines get truncated, resulting in <p> tags |
---|
218 | // starting immediately after <block> tags on the same line. |
---|
219 | // This forces a newline after such occurrences, which looks much nicer. |
---|
220 | "/><p>\n/" => ">\n<p>", |
---|
221 | |
---|
222 | // Similarly, there might be cases where a closing </block> will follow |
---|
223 | // a closing </p> tag, so we'll correct it by adding a newline in between |
---|
224 | "#</p></#" => "</p>\n</" |
---|
225 | ); |
---|
226 | |
---|
227 | // Do we need to reduce empty lines? |
---|
228 | if ($reduce_linebreaks === TRUE) |
---|
229 | { |
---|
230 | $table['#<p>\n*</p>#'] = ''; |
---|
231 | } |
---|
232 | else |
---|
233 | { |
---|
234 | // If we have empty paragraph tags we add a non-breaking space |
---|
235 | // otherwise most browsers won't treat them as true paragraphs |
---|
236 | $table['#<p></p>#'] = '<p> </p>'; |
---|
237 | } |
---|
238 | |
---|
239 | return preg_replace(array_keys($table), $table, $str); |
---|
240 | |
---|
241 | } |
---|
242 | |
---|
243 | // -------------------------------------------------------------------- |
---|
244 | |
---|
245 | /** |
---|
246 | * Format Characters |
---|
247 | * |
---|
248 | * This function mainly converts double and single quotes |
---|
249 | * to curly entities, but it also converts em-dashes, |
---|
250 | * double spaces, and ampersands |
---|
251 | * |
---|
252 | * @access public |
---|
253 | * @param string |
---|
254 | * @return string |
---|
255 | */ |
---|
256 | function format_characters($str) |
---|
257 | { |
---|
258 | static $table; |
---|
259 | |
---|
260 | if ( ! isset($table)) |
---|
261 | { |
---|
262 | $table = array( |
---|
263 | // nested smart quotes, opening and closing |
---|
264 | // note that rules for grammar (English) allow only for two levels deep |
---|
265 | // and that single quotes are _supposed_ to always be on the outside |
---|
266 | // but we'll accommodate both |
---|
267 | // Note that in all cases, whitespace is the primary determining factor |
---|
268 | // on which direction to curl, with non-word characters like punctuation |
---|
269 | // being a secondary factor only after whitespace is addressed. |
---|
270 | '/\'"(\s|$)/' => '’”$1', |
---|
271 | '/(^|\s|<p>)\'"/' => '$1‘“', |
---|
272 | '/\'"(\W)/' => '’”$1', |
---|
273 | '/(\W)\'"/' => '$1‘“', |
---|
274 | '/"\'(\s|$)/' => '”’$1', |
---|
275 | '/(^|\s|<p>)"\'/' => '$1“‘', |
---|
276 | '/"\'(\W)/' => '”’$1', |
---|
277 | '/(\W)"\'/' => '$1“‘', |
---|
278 | |
---|
279 | // single quote smart quotes |
---|
280 | '/\'(\s|$)/' => '’$1', |
---|
281 | '/(^|\s|<p>)\'/' => '$1‘', |
---|
282 | '/\'(\W)/' => '’$1', |
---|
283 | '/(\W)\'/' => '$1‘', |
---|
284 | |
---|
285 | // double quote smart quotes |
---|
286 | '/"(\s|$)/' => '”$1', |
---|
287 | '/(^|\s|<p>)"/' => '$1“', |
---|
288 | '/"(\W)/' => '”$1', |
---|
289 | '/(\W)"/' => '$1“', |
---|
290 | |
---|
291 | // apostrophes |
---|
292 | "/(\w)'(\w)/" => '$1’$2', |
---|
293 | |
---|
294 | // Em dash and ellipses dots |
---|
295 | '/\s?\-\-\s?/' => '—', |
---|
296 | '/(\w)\.{3}/' => '$1…', |
---|
297 | |
---|
298 | // double space after sentences |
---|
299 | '/(\W) /' => '$1 ', |
---|
300 | |
---|
301 | // ampersands, if not a character entity |
---|
302 | '/&(?!#?[a-zA-Z0-9]{2,};)/' => '&' |
---|
303 | ); |
---|
304 | } |
---|
305 | |
---|
306 | return preg_replace(array_keys($table), $table, $str); |
---|
307 | } |
---|
308 | |
---|
309 | // -------------------------------------------------------------------- |
---|
310 | |
---|
311 | /** |
---|
312 | * Format Newlines |
---|
313 | * |
---|
314 | * Converts newline characters into either <p> tags or <br /> |
---|
315 | * |
---|
316 | * @access public |
---|
317 | * @param string |
---|
318 | * @return string |
---|
319 | */ |
---|
320 | function _format_newlines($str) |
---|
321 | { |
---|
322 | if ($str == '') |
---|
323 | { |
---|
324 | return $str; |
---|
325 | } |
---|
326 | |
---|
327 | if (strpos($str, "\n") === FALSE && ! in_array($this->last_block_element, $this->inner_block_required)) |
---|
328 | { |
---|
329 | return $str; |
---|
330 | } |
---|
331 | |
---|
332 | // Convert two consecutive newlines to paragraphs |
---|
333 | $str = str_replace("\n\n", "</p>\n\n<p>", $str); |
---|
334 | |
---|
335 | // Convert single spaces to <br /> tags |
---|
336 | $str = preg_replace("/([^\n])(\n)([^\n])/", "\\1<br />\\2\\3", $str); |
---|
337 | |
---|
338 | // Wrap the whole enchilada in enclosing paragraphs |
---|
339 | if ($str != "\n") |
---|
340 | { |
---|
341 | // We trim off the right-side new line so that the closing </p> tag |
---|
342 | // will be positioned immediately following the string, matching |
---|
343 | // the behavior of the opening <p> tag |
---|
344 | $str = '<p>'.rtrim($str).'</p>'; |
---|
345 | } |
---|
346 | |
---|
347 | // Remove empty paragraphs if they are on the first line, as this |
---|
348 | // is a potential unintended consequence of the previous code |
---|
349 | $str = preg_replace("/<p><\/p>(.*)/", "\\1", $str, 1); |
---|
350 | |
---|
351 | return $str; |
---|
352 | } |
---|
353 | |
---|
354 | // ------------------------------------------------------------------------ |
---|
355 | |
---|
356 | /** |
---|
357 | * Protect Characters |
---|
358 | * |
---|
359 | * Protects special characters from being formatted later |
---|
360 | * We don't want quotes converted within tags so we'll temporarily convert them to {@DQ} and {@SQ} |
---|
361 | * and we don't want double dashes converted to emdash entities, so they are marked with {@DD} |
---|
362 | * likewise double spaces are converted to {@NBS} to prevent entity conversion |
---|
363 | * |
---|
364 | * @access public |
---|
365 | * @param array |
---|
366 | * @return string |
---|
367 | */ |
---|
368 | function _protect_characters($match) |
---|
369 | { |
---|
370 | return str_replace(array("'",'"','--',' '), array('{@SQ}', '{@DQ}', '{@DD}', '{@NBS}'), $match[0]); |
---|
371 | } |
---|
372 | |
---|
373 | // -------------------------------------------------------------------- |
---|
374 | |
---|
375 | /** |
---|
376 | * Convert newlines to HTML line breaks except within PRE tags |
---|
377 | * |
---|
378 | * @access public |
---|
379 | * @param string |
---|
380 | * @return string |
---|
381 | */ |
---|
382 | function nl2br_except_pre($str) |
---|
383 | { |
---|
384 | $ex = explode("pre>",$str); |
---|
385 | $ct = count($ex); |
---|
386 | |
---|
387 | $newstr = ""; |
---|
388 | for ($i = 0; $i < $ct; $i++) |
---|
389 | { |
---|
390 | if (($i % 2) == 0) |
---|
391 | { |
---|
392 | $newstr .= nl2br($ex[$i]); |
---|
393 | } |
---|
394 | else |
---|
395 | { |
---|
396 | $newstr .= $ex[$i]; |
---|
397 | } |
---|
398 | |
---|
399 | if ($ct - 1 != $i) |
---|
400 | $newstr .= "pre>"; |
---|
401 | } |
---|
402 | |
---|
403 | return $newstr; |
---|
404 | } |
---|
405 | |
---|
406 | } |
---|
407 | // END Typography Class |
---|
408 | |
---|
409 | /* End of file Typography.php */ |
---|
410 | /* Location: ./system/libraries/Typography.php */ |
---|