summaryrefslogtreecommitdiffstats
path: root/system/libraries/Typography.php
blob: 3ff0d2f58f4a8b02ddb813aa422f263fa1983b8e (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
<?php  if ( ! defined('BASEPATH')) exit('No direct script access allowed');
/**
 * CodeIgniter
 *
 * An open source application development framework for PHP 4.3.2 or newer
 *
 * @package		CodeIgniter
 * @author		ExpressionEngine Dev Team
 * @copyright	Copyright (c) 2008, EllisLab, Inc.
 * @license		http://codeigniter.com/user_guide/license.html
 * @link		http://codeigniter.com
 * @since		Version 1.0
 * @filesource
 */

// ------------------------------------------------------------------------

/**
 * Typography Class
 *
 *
 * @access		private
 * @category	Helpers
 * @author		ExpressionEngine Dev Team
 * @link		http://codeigniter.com/user_guide/helpers/
 */
class CI_Typography {

	// Block level elements that should not be wrapped inside <p> tags
	var $block_elements = 'address|blockquote|div|dl|fieldset|form|h\d|hr|noscript|object|ol|p|pre|script|table|ul';
	
	// Elements that should not have <p> and <br /> tags within them.
	var $skip_elements	= 'p|pre|ol|ul|dl|object|table';
	
	// Tags we want the parser to completely ignore when splitting the string.
	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';

	// whether or not to protect quotes within { curly braces }
	var $protect_braced_quotes = FALSE;
	
	/**
	 * Nothing to do here...
	 *
	 */
	function CI_Typography()
	{
	}

	/**
	 * Auto Typography
	 *
	 * This function converts text, making it typographically correct:
	 * 	- Converts double spaces into paragraphs.
	 * 	- Converts single line breaks into <br /> tags
	 * 	- Converts single and double quotes into correctly facing curly quote entities.
	 * 	- Converts three dots into ellipsis.
	 * 	- Converts double dashes into em-dashes.
	 *  - Converts two spaces into entities
	 *
	 * @access	public
	 * @param	string
	 * @param	bool	whether to reduce more then two consecutive newlines to two
	 * @return	string
	 */
	function auto_typography($str, $reduce_linebreaks = FALSE)
	{
		if ($str == '')
		{
			return '';
		}

		// Standardize Newlines to make matching easier
		if (strpos($str, "\r") !== FALSE)
		{
			$str = str_replace(array("\r\n", "\r"), "\n", $str);			
		}
			
		// Reduce line breaks.  If there are more than two consecutive linebreaks
		// we'll compress them down to a maximum of two since there's no benefit to more.
		if ($reduce_linebreaks === TRUE)
		{
			$str = preg_replace("/\n\n+/", "\n\n", $str);
		} 

		// Convert quotes within tags to temporary markers. We don't want quotes converted 
		// within tags so we'll temporarily convert them to {@DQ} and {@SQ}
		// and we don't want double dashes converted to emdash entities, so they are marked with {@DD}
		// likewise double spaces are converted to {@NBS} to prevent entity conversion
		if (preg_match_all("#\<.+?>#si", $str, $matches))
		{
			for ($i = 0, $total = count($matches[0]); $i < $total; $i++)
			{
				$str = str_replace($matches[0][$i],
									str_replace(array("'",'"','--','  '), array('{@SQ}', '{@DQ}', '{@DD}', '{@NBS}'), $matches[0][$i]),
									$str);
			}
		}
		
		if ($this->protect_braced_quotes === TRUE)
		{
			if (preg_match_all("#\{.+?}#si", $str, $matches))
			{
				for ($i = 0, $total = count($matches[0]); $i < $total; $i++)
				{
					$str = str_replace($matches[0][$i],
										str_replace(array("'",'"'), array('{@SQ}', '{@DQ}'), $matches[0][$i]),
										$str);
				}
			}			
		}
		
		// Convert "ignore" tags to temporary marker.  The parser splits out the string at every tag 
		// it encounters.  Certain inline tags, like image tags, links, span tags, etc. will be 
		// adversely affected if they are split out so we'll convert the opening bracket < temporarily to: {@TAG}
		$str = preg_replace("#<(/*)(".$this->inline_elements.")([ >])#i", "{@TAG}\\1\\2\\3", $str);

		// Split the string at every tag.  This expression creates an array with this prototype:
		// 
		// 	[array]
		// 	{
		// 		[0] = <opening tag>
		// 		[1] = Content...
		// 		[2] = <closing tag>
		// 		Etc...
		// 	}	
		$chunks = preg_split('/(<(?:[^<>]+(?:"[^"]*"|\'[^\']*\')?)+>)/', $str, -1, PREG_SPLIT_DELIM_CAPTURE|PREG_SPLIT_NO_EMPTY);
		
		// Build our finalized string.  We cycle through the array, skipping tags, and processing the contained text	
		$str = '';
		$process = TRUE;
		$paragraph = FALSE;
		foreach ($chunks as $chunk)
		{
			// Are we dealing with a tag? If so, we'll skip the processing for this cycle.
			// Well also set the "process" flag which allows us to skip <pre> tags and a few other things.
			if (preg_match("#<(/*)(".$this->block_elements.").*?>#", $chunk, $match))
			{
				if (preg_match("#".$this->skip_elements."#", $match[2]))
				{
					$process =  ($match[1] == '/') ? TRUE : FALSE;
				}
				
				$str .= $chunk;
				continue;
			}
			elseif (preg_match('/<(\/?)([a-z]*).*?>/s', $chunk, $tagmatch))
			{
				if ($tagmatch[1] == '/' && $tagmatch[2] == $this->last_tag)
				{
					$process = FALSE;
				}
				else
				{
					$process = TRUE;
					$this->last_tag = $tagmatch[2];					
				}
			}

			if ($process == FALSE)
			{
				$str .= $chunk;
				continue;
			}
			
			//  Convert Newlines into <p> and <br /> tags
			$str .= $this->format_characters($this->_format_newlines($chunk));			
		}

		// is the whole of the content inside a block level element?
		if ( ! preg_match("/^<(?:".$this->block_elements.")/i", $str, $match))
		{
			$str = "<p>{$str}</p>";
		}


		// some special linebreak cleanup
		$str = preg_replace_callback('#<(?!/|'.$this->block_elements.')([^>]*)><p>(.*?)</p><(\w*)#si', array($this, '_linebreak_cleanup'), $str);
		
		// and cleanup empty paragraph tags sitting between two closing tags
		$str = preg_replace('#(</\w+>)<p>(\s*)</p>(</\w+>)#si', '$1$2$3', $str);
		
		// Final clean up
		$table = array(
		
						// If the user submitted their own paragraph tags within the text
						// we will retain them instead of using our tags.
						'/(<p[^>*?]>)<p>/'	=> '$1', // <?php BBEdit syntax coloring bug fix
						
						// Reduce multiple instances of opening/closing paragraph tags to a single one
						'#(</p>)+#'			=> '</p>',
						'/(<p>\W*<p>)+/'	=> '<p>',
						
						// Clean up stray paragraph tags that appear before block level elements
						'#<p></p><('.$this->block_elements.')#'	=> '<$1',
						
						// Clean up open paragraph tags that appear before block level elements
						'#<p>(\W)<('.$this->block_elements.')#'	=> '<p></p>$1<$2',

						// Clean up stray non-breaking spaces preceeding block elements
						'#[&nbsp; ]+<('.$this->block_elements.')#'	=> '  <$1',
			
						// Replace the temporary markers we added earlier
						'/\{@TAG\}/'		=> '<',
						'/\{@DQ\}/'			=> '"',
						'/\{@SQ\}/'			=> "'",
						'/\{@DD\}/'			=> '--',
						'/\{@NBS\}/'		=> '  '

						);

		// Do we need to reduce empty lines?
		if ($reduce_linebreaks === TRUE)
		{
			$table['#<p>\n*</p>#'] = '';
		}
		else
		{
			// If we have empty paragraph tags we add a non-breaking space
			// otherwise most browsers won't treat them as true paragraphs
			$table['#<p></p>#'] = '<p>&nbsp;</p>';
		}
	
		return preg_replace(array_keys($table), $table, $str);

	}
	
	// --------------------------------------------------------------------
	
	/**
	 * Linebreak Cleanup
	 *
	 * Removes paragraph and line break tags inserted inbetween
	 * inline content and a new opening block level element
	 *
	 * @access	private
	 * @param	array
	 * @return	string
	 */
	function _linebreak_cleanup($match)
	{
		if (in_array($match[3], explode('|', $this->block_elements)))
		{
			return "<{$match[1]}>".str_replace('<br />', '', $match[2])."<{$match[3]}";
		}
		else
		{
			return $match[0];
		}
	}

	// --------------------------------------------------------------------
	
	/**
	 * Format Characters
	 *
	 * This function mainly converts double and single quotes
	 * to curly entities, but it also converts em-dashes,
	 * double spaces, and ampersands
	 *
	 * @access	public
	 * @param	string
	 * @return	string
	 */
	function format_characters($str)
	{
		static $table;
		
		if ( ! isset($table))
		{
	        $table = array(					
							// nested smart quotes, opening and closing
							// note that rules for grammar (English) allow only for two levels deep
							// and that single quotes are _supposed_ to always be on the outside
							// but we'll accommodate both
							'/(^|\W|\s)\'"/'				=> '$1&#8216;&#8220;',
							'/\'"(\s|\W|$)/'				=> '&#8217;&#8221;$1',
							'/(^|\W|\s)"\'/'				=> '$1&#8220;&#8216;',
							'/"\'(\s|\W|$)/'				=> '&#8221;&#8217;$1',

							// single quote smart quotes
							'/\'(\s|\W|$)/'					=> '&#8217;$1',
							'/(^|\W|\s)\'/'					=> '$1&#8216;',

							// double quote smart quotes
							'/"(\s|\W|$)/'					=> '&#8221;$1',
							'/(^|\W|\s)"/'					=> '$1&#8220;',

							// apostrophes
							"/(\w)'(\w)/"       	    	=> '$1&#8217;$2',

							// Em dash and ellipses dots
							'/\s?\-\-\s?/'					=> '&#8212;',
							'/(\w)\.{3}/'					=> '$1&#8230;',

							// double space after sentences
							'/(\W)  /'						=> '$1&nbsp; ',

							// ampersands, if not a character entity
							'/&(?!#?[a-zA-Z0-9]{2,};)/'		=> '&amp;'
	        			);			
		}	

		return preg_replace(array_keys($table), $table, $str);
	}
	
	// --------------------------------------------------------------------

	/**
	 * Format Newlines
	 *
	 * Converts newline characters into either <p> tags or <br />
	 *
	 * @access	public
	 * @param	string
	 * @return	string
	 */	
	function _format_newlines($str)
	{
		if ($str == '')
		{
			return $str;
		}

		if (strpos($str, "\n") === FALSE)
		{
			return $str;
		}
		
		// Convert two consecutive newlines to paragraphs
		$str = str_replace("\n\n", "</p>\n\n<p>", $str);
		
		// Convert single spaces to <br /> tags
		$str = preg_replace("/([^\n])(\n)([^\n])/", "\\1<br />\\2\\3", $str);
		
		// Wrap the whole enchilada in enclosing paragraphs
		if ($str != "\n")
		{
			$str =  '<p>'.$str.'</p>';
		}

		// Remove empty paragraphs if they are on the first line, as this
		// is a potential unintended consequence of the previous code
		$str = preg_replace("/<p><\/p>(.*)/", "\\1", $str, 1);
		
		return $str;
	}
	
	// ------------------------------------------------------------------------
	
	/**
	 * Convert newlines to HTML line breaks except within PRE tags
	 *
	 * @access	public
	 * @param	string
	 * @return	string
	 */		
	function nl2br_except_pre($str)
	{
		$ex = explode("pre>",$str);
		$ct = count($ex);
	
		$newstr = "";
		for ($i = 0; $i < $ct; $i++)
		{
			if (($i % 2) == 0)
			{
				$newstr .= nl2br($ex[$i]);
			}
			else
			{
				$newstr .= $ex[$i];
			}
		
			if ($ct - 1 != $i)
				$newstr .= "pre>";
		}
	
		return $newstr;
	}
	
}
// END Typography Class

/* End of file Typography.php */
/* Location: ./system/libraries/Typography.php */