Typography.php 12.9 KB
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417
<?php
/**
 * CodeIgniter
 *
 * An open source application development framework for PHP 5.2.4 or newer
 *
 * NOTICE OF LICENSE
 *
 * Licensed under the Open Software License version 3.0
 *
 * This source file is subject to the Open Software License (OSL 3.0) that is
 * bundled with this package in the files license.txt / license.rst.  It is
 * also available through the world wide web at this URL:
 * http://opensource.org/licenses/OSL-3.0
 * If you did not receive a copy of the license and are unable to obtain it
 * through the world wide web, please send an email to
 * licensing@ellislab.com so we can send you a copy immediately.
 *
 * @package		CodeIgniter
 * @author		EllisLab Dev Team
 * @copyright	Copyright (c) 2008 - 2014, EllisLab, Inc. (http://ellislab.com/)
 * @license		http://opensource.org/licenses/OSL-3.0 Open Software License (OSL 3.0)
 * @link		http://codeigniter.com
 * @since		Version 1.0
 * @filesource
 */
defined('BASEPATH') OR exit('No direct script access allowed');

/**
 * Typography Class
 *
 * @package		CodeIgniter
 * @subpackage	Libraries
 * @category	Helpers
 * @author		EllisLab Dev Team
 * @link		http://codeigniter.com/user_guide/libraries/typography.html
 */
class CI_Typography {

	/**
	 * Block level elements that should not be wrapped inside <p> tags
	 *
	 * @var string
	 */
	public $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 string
	 */
	public $skip_elements	= 'p|pre|ol|ul|dl|object|table|h\d';

	/**
	 * Tags we want the parser to completely ignore when splitting the string.
	 *
	 * @var string
	 */
	public $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';

	/**
	 * array of block level elements that require inner content to be within another block level element
	 *
	 * @var array
	 */
	public $inner_block_required = array('blockquote');

	/**
	 * the last block element parsed
	 *
	 * @var string
	 */
	public $last_block_element = '';

	/**
	 * whether or not to protect quotes within { curly braces }
	 *
	 * @var bool
	 */
	public $protect_braced_quotes = FALSE;

	/**
	 * 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
	 *
	 * @param	string
	 * @param	bool	whether to reduce more then two consecutive newlines to two
	 * @return	string
	 */
	public 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);
		}

		// HTML comment tags don't conform to patterns of normal tags, so pull them out separately, only if needed
		$html_comments = array();
		if (strpos($str, '<!--') !== FALSE && preg_match_all('#(<!\-\-.*?\-\->)#s', $str, $matches))
		{
			for ($i = 0, $total = count($matches[0]); $i < $total; $i++)
			{
				$html_comments[] = $matches[0][$i];
				$str = str_replace($matches[0][$i], '{@HC'.$i.'}', $str);
			}
		}

		// match and yank <pre> tags if they exist.  It's cheaper to do this separately since most content will
		// not contain <pre> tags, and it keeps the PCRE patterns below simpler and faster
		if (strpos($str, '<pre') !== FALSE)
		{
			$str = preg_replace_callback('#<pre.*?>.*?</pre>#si', array($this, '_protect_characters'), $str);
		}

		// Convert quotes within tags to temporary markers.
		$str = preg_replace_callback('#<.+?>#si', array($this, '_protect_characters'), $str);

		// Do the same with braces if necessary
		if ($this->protect_braced_quotes === TRUE)
		{
			$str = preg_replace_callback('#\{.+?\}#si', array($this, '_protect_characters'), $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;

		for ($i = 0, $c = count($chunks) - 1; $i <= $c; $i++)
		{
			// Are we dealing with a tag? If so, we'll skip the processing for this cycle.
			// Well also set the "process" flag which allows us to skip <pre> tags and a few other things.
			if (preg_match('#<(/*)('.$this->block_elements.').*?>#', $chunks[$i], $match))
			{
				if (preg_match('#'.$this->skip_elements.'#', $match[2]))
				{
					$process = ($match[1] === '/');
				}

				if ($match[1] === '')
				{
					$this->last_block_element = $match[2];
				}

				$str .= $chunks[$i];
				continue;
			}

			if ($process === FALSE)
			{
				$str .= $chunks[$i];
				continue;
			}

			//  Force a newline to make sure end tags get processed by _format_newlines()
			if ($i === $c)
			{
				$chunks[$i] .= "\n";
			}

			//  Convert Newlines into <p> and <br /> tags
			$str .= $this->_format_newlines($chunks[$i]);
		}

		// No opening block level tag? Add it if needed.
		if ( ! preg_match('/^\s*<(?:'.$this->block_elements.')/i', $str))
		{
			$str = preg_replace('/^(.*?)<('.$this->block_elements.')/i', '<p>$1</p><$2', $str);
		}

		// Convert quotes, elipsis, em-dashes, non-breaking spaces, and ampersands
		$str = $this->format_characters($str);

		// restore HTML comments
		for ($i = 0, $total = count($html_comments); $i < $total; $i++)
		{
			// remove surrounding paragraph tags, but only if there's an opening paragraph tag
			// otherwise HTML comments at the ends of paragraphs will have the closing tag removed
			// if '<p>{@HC1}' then replace <p>{@HC1}</p> with the comment, else replace only {@HC1} with the comment
			$str = preg_replace('#(?(?=<p>\{@HC'.$i.'\})<p>\{@HC'.$i.'\}(\s*</p>)|\{@HC'.$i.'\})#s', $html_comments[$i], $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 stray non-breaking spaces preceeding block elements
						'#(&nbsp;\s*)+<('.$this->block_elements.')#'	=> '  <$2',

						// Replace the temporary markers we added earlier
						'/\{@TAG\}/'		=> '<',
						'/\{@DQ\}/'			=> '"',
						'/\{@SQ\}/'			=> "'",
						'/\{@DD\}/'			=> '--',
						'/\{@NBS\}/'		=> '  ',

						// An unintended consequence of the _format_newlines function is that
						// some of the newlines get truncated, resulting in <p> tags
						// starting immediately after <block> tags on the same line.
						// This forces a newline after such occurrences, which looks much nicer.
						"/><p>\n/"			=> ">\n<p>",

						// Similarly, there might be cases where a closing </block> will follow
						// a closing </p> tag, so we'll correct it by adding a newline in between
						'#</p></#'			=> "</p>\n</"
						);

		// 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);

	}

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

	/**
	 * Format Characters
	 *
	 * This function mainly converts double and single quotes
	 * to curly entities, but it also converts em-dashes,
	 * double spaces, and ampersands
	 *
	 * @param	string
	 * @return	string
	 */
	public function format_characters($str)
	{
		static $table;

		if ( ! isset($table))
		{
			$table = array(
							// nested smart quotes, opening and closing
							// note that rules for grammar (English) allow only for two levels deep
							// and that single quotes are _supposed_ to always be on the outside
							// but we'll accommodate both
							// Note that in all cases, whitespace is the primary determining factor
							// on which direction to curl, with non-word characters like punctuation
							// being a secondary factor only after whitespace is addressed.
							'/\'"(\s|$)/'					=> '&#8217;&#8221;$1',
							'/(^|\s|<p>)\'"/'				=> '$1&#8216;&#8220;',
							'/\'"(\W)/'						=> '&#8217;&#8221;$1',
							'/(\W)\'"/'						=> '$1&#8216;&#8220;',
							'/"\'(\s|$)/'					=> '&#8221;&#8217;$1',
							'/(^|\s|<p>)"\'/'				=> '$1&#8220;&#8216;',
							'/"\'(\W)/'						=> '&#8221;&#8217;$1',
							'/(\W)"\'/'						=> '$1&#8220;&#8216;',

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

							// double quote smart quotes
							'/"(\s|$)/'						=> '&#8221;$1',
							'/(^|\s|<p>)"/'					=> '$1&#8220;',
							'/"(\W)/'						=> '&#8221;$1',
							'/(\W)"/'						=> '$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 />
	 *
	 * @param	string
	 * @return	string
	 */
	protected function _format_newlines($str)
	{
		if ($str === '' OR (strpos($str, "\n") === FALSE && ! in_array($this->last_block_element, $this->inner_block_required)))
		{
			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")
		{
			// We trim off the right-side new line so that the closing </p> tag
			// will be positioned immediately following the string, matching
			// the behavior of the opening <p> tag
			$str =  '<p>'.rtrim($str).'</p>';
		}

		// Remove empty paragraphs if they are on the first line, as this
		// is a potential unintended consequence of the previous code
		return preg_replace('/<p><\/p>(.*)/', '\\1', $str, 1);
	}

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

	/**
	 * Protect Characters
	 *
	 * Protects special characters from being formatted later
	 * 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
	 *
	 * @param	array
	 * @return	string
	 */
	protected function _protect_characters($match)
	{
		return str_replace(array("'",'"','--','  '), array('{@SQ}', '{@DQ}', '{@DD}', '{@NBS}'), $match[0]);
	}

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

	/**
	 * Convert newlines to HTML line breaks except within PRE tags
	 *
	 * @param	string
	 * @return	string
	 */
	public function nl2br_except_pre($str)
	{
		$newstr = '';
		for ($ex = explode('pre>', $str), $ct = count($ex), $i = 0; $i < $ct; $i++)
		{
			$newstr .= (($i % 2) === 0) ? nl2br($ex[$i]) : $ex[$i];
			if ($ct - 1 !== $i)
			{
				$newstr .= 'pre>';
			}
		}

		return $newstr;
	}

}

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