| commit | author | age | ||
| 4e17e6 | 1 | <?php |
| T | 2 | |
| 3 | /************************************************************************* | |
| 8ac6fd | 4 | * * |
| A | 5 | * class.html2text.inc * |
| 6 | * * | |
| 7 | ************************************************************************* | |
| 8 | * * | |
| 9 | * Converts HTML to formatted plain text * | |
| 10 | * * | |
| 11 | * Copyright (c) 2005-2007 Jon Abernathy <jon@chuggnutt.com> * | |
| 12 | * All rights reserved. * | |
| 13 | * * | |
| 14 | * This script is free software; you can redistribute it and/or modify * | |
| 15 | * it under the terms of the GNU General Public License as published by * | |
| 16 | * the Free Software Foundation; either version 2 of the License, or * | |
| 17 | * (at your option) any later version. * | |
| 18 | * * | |
| 19 | * The GNU General Public License can be found at * | |
| 20 | * http://www.gnu.org/copyleft/gpl.html. * | |
| 21 | * * | |
| 22 | * This script is distributed in the hope that it will be useful, * | |
| 23 | * but WITHOUT ANY WARRANTY; without even the implied warranty of * | |
| 24 | * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * | |
| 25 | * GNU General Public License for more details. * | |
| 26 | * * | |
| 27 | * Author(s): Jon Abernathy <jon@chuggnutt.com> * | |
| 28 | * * | |
| 29 | * Last modified: 08/08/07 * | |
| 30 | * * | |
| 31 | *************************************************************************/ | |
| 4e17e6 | 32 | |
| T | 33 | |
| 34 | /** | |
| 8ac6fd | 35 | * Takes HTML and converts it to formatted, plain text. |
| A | 36 | * |
| 37 | * Thanks to Alexander Krug (http://www.krugar.de/) to pointing out and | |
| 38 | * correcting an error in the regexp search array. Fixed 7/30/03. | |
| 39 | * | |
| 40 | * Updated set_html() function's file reading mechanism, 9/25/03. | |
| 41 | * | |
| 42 | * Thanks to Joss Sanglier (http://www.dancingbear.co.uk/) for adding | |
| 43 | * several more HTML entity codes to the $search and $replace arrays. | |
| 44 | * Updated 11/7/03. | |
| 45 | * | |
| 46 | * Thanks to Darius Kasperavicius (http://www.dar.dar.lt/) for | |
| 47 | * suggesting the addition of $allowed_tags and its supporting function | |
| 48 | * (which I slightly modified). Updated 3/12/04. | |
| 49 | * | |
| 50 | * Thanks to Justin Dearing for pointing out that a replacement for the | |
| 51 | * <TH> tag was missing, and suggesting an appropriate fix. | |
| 52 | * Updated 8/25/04. | |
| 53 | * | |
| 54 | * Thanks to Mathieu Collas (http://www.myefarm.com/) for finding a | |
| 55 | * display/formatting bug in the _build_link_list() function: email | |
| 56 | * readers would show the left bracket and number ("[1") as part of the | |
| 57 | * rendered email address. | |
| 58 | * Updated 12/16/04. | |
| 59 | * | |
| 60 | * Thanks to Wojciech Bajon (http://histeria.pl/) for submitting code | |
| 61 | * to handle relative links, which I hadn't considered. I modified his | |
| 62 | * code a bit to handle normal HTTP links and MAILTO links. Also for | |
| 63 | * suggesting three additional HTML entity codes to search for. | |
| 64 | * Updated 03/02/05. | |
| 65 | * | |
| 66 | * Thanks to Jacob Chandler for pointing out another link condition | |
| 67 | * for the _build_link_list() function: "https". | |
| 68 | * Updated 04/06/05. | |
| 69 | * | |
| 70 | * Thanks to Marc Bertrand (http://www.dresdensky.com/) for | |
| 71 | * suggesting a revision to the word wrapping functionality; if you | |
| 72 | * specify a $width of 0 or less, word wrapping will be ignored. | |
| 73 | * Updated 11/02/06. | |
| 74 | * | |
| 75 | * *** Big housecleaning updates below: | |
| 76 | * | |
| 77 | * Thanks to Colin Brown (http://www.sparkdriver.co.uk/) for | |
| 78 | * suggesting the fix to handle </li> and blank lines (whitespace). | |
| 79 | * Christian Basedau (http://www.movetheweb.de/) also suggested the | |
| 80 | * blank lines fix. | |
| 81 | * | |
| 82 | * Special thanks to Marcus Bointon (http://www.synchromedia.co.uk/), | |
| 83 | * Christian Basedau, Norbert Laposa (http://ln5.co.uk/), | |
| 84 | * Bas van de Weijer, and Marijn van Butselaar | |
| 85 | * for pointing out my glaring error in the <th> handling. Marcus also | |
| 86 | * supplied a host of fixes. | |
| 87 | * | |
| 88 | * Thanks to Jeffrey Silverman (http://www.newtnotes.com/) for pointing | |
| 89 | * out that extra spaces should be compressed--a problem addressed with | |
| 90 | * Marcus Bointon's fixes but that I had not yet incorporated. | |
| 91 | * | |
| 92 | * Thanks to Daniel Schledermann (http://www.typoconsult.dk/) for | |
| 93 | * suggesting a valuable fix with <a> tag handling. | |
| 94 | * | |
| 95 | * Thanks to Wojciech Bajon (again!) for suggesting fixes and additions, | |
| 96 | * including the <a> tag handling that Daniel Schledermann pointed | |
| 97 | * out but that I had not yet incorporated. I haven't (yet) | |
| 98 | * incorporated all of Wojciech's changes, though I may at some | |
| 99 | * future time. | |
| 100 | * | |
| 101 | * *** End of the housecleaning updates. Updated 08/08/07. | |
| 102 | * | |
| 103 | * @author Jon Abernathy <jon@chuggnutt.com> | |
| 104 | * @version 1.0.0 | |
| 105 | * @since PHP 4.0.2 | |
| 106 | */ | |
| 4e17e6 | 107 | class html2text |
| T | 108 | { |
| 109 | ||
| 110 | /** | |
| 111 | * Contains the HTML content to convert. | |
| 112 | * | |
| 113 | * @var string $html | |
| 114 | * @access public | |
| 115 | */ | |
| 116 | var $html; | |
| 117 | ||
| 118 | /** | |
| 119 | * Contains the converted, formatted text. | |
| 120 | * | |
| 121 | * @var string $text | |
| 122 | * @access public | |
| 123 | */ | |
| 124 | var $text; | |
| 125 | ||
| 126 | /** | |
| 127 | * Maximum width of the formatted text, in columns. | |
| 128 | * | |
| 8ac6fd | 129 | * Set this value to 0 (or less) to ignore word wrapping |
| A | 130 | * and not constrain text to a fixed-width column. |
| 131 | * | |
| 4e17e6 | 132 | * @var integer $width |
| T | 133 | * @access public |
| 134 | */ | |
| 135 | var $width = 70; | |
| 136 | ||
| 137 | /** | |
| 138 | * List of preg* regular expression patterns to search for, | |
| 139 | * used in conjunction with $replace. | |
| 140 | * | |
| 141 | * @var array $search | |
| 142 | * @access public | |
| 143 | * @see $replace | |
| 144 | */ | |
| 145 | var $search = array( | |
| 146 | "/\r/", // Non-legal carriage return | |
| 147 | "/[\n\t]+/", // Newlines and tabs | |
| 8ac6fd | 148 | '/[ ]{2,}/', // Runs of spaces, pre-handling |
| 4e17e6 | 149 | '/<script[^>]*>.*?<\/script>/i', // <script>s -- which strip_tags supposedly has problems with |
| 8ac6fd | 150 | '/<style[^>]*>.*?<\/style>/i', // <style>s -- which strip_tags supposedly has problems with |
| 4e17e6 | 151 | '/<p[^>]*>/i', // <P> |
| T | 152 | '/<br[^>]*>/i', // <br> |
| 8ac6fd | 153 | '/<i[^>]*>(.*?)<\/i>/i', // <i> |
| A | 154 | '/<em[^>]*>(.*?)<\/em>/i', // <em> |
| 4e17e6 | 155 | '/(<ul[^>]*>|<\/ul>)/i', // <ul> and </ul> |
| T | 156 | '/(<ol[^>]*>|<\/ol>)/i', // <ol> and </ol> |
| 8ac6fd | 157 | '/<li[^>]*>(.*?)<\/li>/i', // <li> and </li> |
| 4e17e6 | 158 | '/<li[^>]*>/i', // <li> |
| T | 159 | '/<hr[^>]*>/i', // <hr> |
| f6b282 | 160 | '/<div[^>]*>/i', // <div> |
| 4e17e6 | 161 | '/(<table[^>]*>|<\/table>)/i', // <table> and </table> |
| T | 162 | '/(<tr[^>]*>|<\/tr>)/i', // <tr> and </tr> |
| 8ac6fd | 163 | '/<td[^>]*>(.*?)<\/td>/i', // <td> and </td> |
| A | 164 | '/&(nbsp|#160);/i', // Non-breaking space |
| 165 | '/&(quot|rdquo|ldquo|#8220|#8221|#147|#148);/i', | |
| 166 | // Double quotes | |
| 167 | '/&(apos|rsquo|lsquo|#8216|#8217);/i', // Single quotes | |
| 168 | '/>/i', // Greater-than | |
| 169 | '/</i', // Less-than | |
| 170 | '/&(copy|#169);/i', // Copyright | |
| 171 | '/&(trade|#8482|#153);/i', // Trademark | |
| 172 | '/&(reg|#174);/i', // Registered | |
| 173 | '/&(mdash|#151|#8212);/i', // mdash | |
| 174 | '/&(ndash|minus|#8211|#8722);/i', // ndash | |
| 175 | '/&(bull|#149|#8226);/i', // Bullet | |
| 176 | '/&(pound|#163);/i', // Pound sign | |
| 177 | '/&(euro|#8364);/i', // Euro sign | |
| 6084d7 | 178 | '/&(amp|#38);/i', // Ampersand: see _converter() |
| 8ac6fd | 179 | '/[ ]{2,}/' // Runs of spaces, post-handling |
| 4e17e6 | 180 | ); |
| T | 181 | |
| 182 | /** | |
| 183 | * List of pattern replacements corresponding to patterns searched. | |
| 184 | * | |
| 185 | * @var array $replace | |
| 186 | * @access public | |
| 187 | * @see $search | |
| 188 | */ | |
| 189 | var $replace = array( | |
| 190 | '', // Non-legal carriage return | |
| 191 | ' ', // Newlines and tabs | |
| 8ac6fd | 192 | ' ', // Runs of spaces, pre-handling |
| 4e17e6 | 193 | '', // <script>s -- which strip_tags supposedly has problems with |
| 8ac6fd | 194 | '', // <style>s -- which strip_tags supposedly has problems with |
| f6b282 | 195 | "\n\n", // <P> |
| 4e17e6 | 196 | "\n", // <br> |
| T | 197 | '_\\1_', // <i> |
| 8ac6fd | 198 | '_\\1_', // <em> |
| 4e17e6 | 199 | "\n\n", // <ul> and </ul> |
| T | 200 | "\n\n", // <ol> and </ol> |
| 8ac6fd | 201 | "\t* \\1\n", // <li> and </li> |
| A | 202 | "\n\t* ", // <li> |
| 6972cc | 203 | "\n-------------------------\n", // <hr> |
| 11bcac | 204 | "<div>\n", // <div> |
| 6972cc | 205 | "\n\n", // <table> and </table> |
| 4e17e6 | 206 | "\n", // <tr> and </tr> |
| T | 207 | "\t\t\\1\n", // <td> and </td> |
| 8ac6fd | 208 | ' ', // Non-breaking space |
| A | 209 | '"', // Double quotes |
| 210 | "'", // Single quotes | |
| 4e17e6 | 211 | '>', |
| T | 212 | '<', |
| 213 | '(c)', | |
| 214 | '(tm)', | |
| 215 | '(R)', | |
| 8ac6fd | 216 | '--', |
| A | 217 | '-', |
| 4e17e6 | 218 | '*', |
| 300fc6 | 219 | '£', |
| 8ac6fd | 220 | 'EUR', // Euro sign. € ? |
| 6084d7 | 221 | '|+|amp|+|', // Ampersand: see _converter() |
| 8ac6fd | 222 | ' ' // Runs of spaces, post-handling |
| f50cc7 | 223 | ); |
| A | 224 | |
| 225 | /** | |
| 226 | * List of preg* regular expression patterns to search for | |
| 227 | * and replace using callback function. | |
| 228 | * | |
| 229 | * @var array $callback_search | |
| 230 | * @access public | |
| 231 | */ | |
| 232 | var $callback_search = array( | |
| 233 | '/<(h)[123456][^>]*>(.*?)<\/h[123456]>/i', // H1 - H3 | |
| 234 | '/<(b)[^>]*>(.*?)<\/b>/i', // <b> | |
| 235 | '/<(strong)[^>]*>(.*?)<\/strong>/i', // <strong> | |
| 236 | '/<(a) [^>]*href=("|\')([^"\']+)\2[^>]*>(.*?)<\/a>/i', | |
| 237 | // <a href=""> | |
| 238 | '/<(th)[^>]*>(.*?)<\/th>/i', // <th> and </th> | |
| 7353fa | 239 | ); |
| A | 240 | |
| 8ac6fd | 241 | /** |
| A | 242 | * List of preg* regular expression patterns to search for in PRE body, |
| 243 | * used in conjunction with $pre_replace. | |
| 244 | * | |
| 245 | * @var array $pre_search | |
| 246 | * @access public | |
| 247 | * @see $pre_replace | |
| 248 | */ | |
| 7789fd | 249 | var $pre_search = array( |
| 6972cc | 250 | "/\n/", |
| T | 251 | "/\t/", |
| 252 | '/ /', | |
| 253 | '/<pre[^>]*>/', | |
| 254 | '/<\/pre>/' | |
| 7353fa | 255 | ); |
| A | 256 | |
| 257 | /** | |
| 258 | * List of pattern replacements corresponding to patterns searched for PRE body. | |
| 259 | * | |
| 260 | * @var array $pre_replace | |
| 261 | * @access public | |
| 262 | * @see $pre_search | |
| 263 | */ | |
| 7789fd | 264 | var $pre_replace = array( |
| 6972cc | 265 | '<br>', |
| T | 266 | ' ', |
| 267 | ' ', | |
| 268 | '', | |
| 269 | '' | |
| 4e17e6 | 270 | ); |
| T | 271 | |
| 272 | /** | |
| 273 | * Contains a list of HTML tags to allow in the resulting text. | |
| 274 | * | |
| 275 | * @var string $allowed_tags | |
| 276 | * @access public | |
| 277 | * @see set_allowed_tags() | |
| 278 | */ | |
| 279 | var $allowed_tags = ''; | |
| 280 | ||
| 281 | /** | |
| 282 | * Contains the base URL that relative links should resolve to. | |
| 283 | * | |
| 284 | * @var string $url | |
| 285 | * @access public | |
| 286 | */ | |
| 287 | var $url; | |
| 288 | ||
| 289 | /** | |
| 290 | * Indicates whether content in the $html variable has been converted yet. | |
| 291 | * | |
| 8ac6fd | 292 | * @var boolean $_converted |
| 4e17e6 | 293 | * @access private |
| T | 294 | * @see $html, $text |
| 295 | */ | |
| 296 | var $_converted = false; | |
| 297 | ||
| 298 | /** | |
| 299 | * Contains URL addresses from links to be rendered in plain text. | |
| 300 | * | |
| 8ac6fd | 301 | * @var string $_link_list |
| 4e17e6 | 302 | * @access private |
| T | 303 | * @see _build_link_list() |
| 304 | */ | |
| 8ac6fd | 305 | var $_link_list = ''; |
| dd792e | 306 | |
| S | 307 | /** |
| 8ac6fd | 308 | * Number of valid links detected in the text, used for plain text |
| A | 309 | * display (rendered similar to footnotes). |
| 310 | * | |
| 311 | * @var integer $_link_count | |
| 312 | * @access private | |
| 313 | * @see _build_link_list() | |
| dd792e | 314 | */ |
| 8ac6fd | 315 | var $_link_count = 0; |
| 4e17e6 | 316 | |
| e7f85b | 317 | /** |
| A | 318 | * Boolean flag, true if a table of link URLs should be listed after the text. |
| 319 | * | |
| 320 | * @var boolean $_do_links | |
| 321 | * @access private | |
| 322 | * @see html2text() | |
| 323 | */ | |
| 324 | var $_do_links = true; | |
| 325 | ||
| 4e17e6 | 326 | /** |
| T | 327 | * Constructor. |
| 328 | * | |
| 329 | * If the HTML source string (or file) is supplied, the class | |
| 330 | * will instantiate with that source propagated, all that has | |
| 331 | * to be done it to call get_text(). | |
| 332 | * | |
| 333 | * @param string $source HTML content | |
| 334 | * @param boolean $from_file Indicates $source is a file to pull content from | |
| e7f85b | 335 | * @param boolean $do_links Indicate whether a table of link URLs is desired |
| A | 336 | * @param integer $width Maximum width of the formatted text, 0 for no limit |
| 4e17e6 | 337 | * @access public |
| T | 338 | * @return void |
| 339 | */ | |
| e7f85b | 340 | function html2text( $source = '', $from_file = false, $do_links = true, $width = 75 ) |
| 4e17e6 | 341 | { |
| T | 342 | if ( !empty($source) ) { |
| 343 | $this->set_html($source, $from_file); | |
| 344 | } | |
| 6972cc | 345 | |
| 4e17e6 | 346 | $this->set_base_url(); |
| 6972cc | 347 | $this->_do_links = $do_links; |
| T | 348 | $this->width = $width; |
| 4e17e6 | 349 | } |
| T | 350 | |
| 351 | /** | |
| 352 | * Loads source HTML into memory, either from $source string or a file. | |
| 353 | * | |
| 354 | * @param string $source HTML content | |
| 355 | * @param boolean $from_file Indicates $source is a file to pull content from | |
| 356 | * @access public | |
| 357 | * @return void | |
| 358 | */ | |
| 359 | function set_html( $source, $from_file = false ) | |
| 360 | { | |
| 361 | if ( $from_file && file_exists($source) ) { | |
| 6972cc | 362 | $this->html = file_get_contents($source); |
| 4e17e6 | 363 | } |
| 8ac6fd | 364 | else |
| 6972cc | 365 | $this->html = $source; |
| 4e17e6 | 366 | |
| T | 367 | $this->_converted = false; |
| 368 | } | |
| 369 | ||
| 370 | /** | |
| 371 | * Returns the text, converted from HTML. | |
| 372 | * | |
| 373 | * @access public | |
| 374 | * @return string | |
| 375 | */ | |
| 376 | function get_text() | |
| 377 | { | |
| 378 | if ( !$this->_converted ) { | |
| 379 | $this->_convert(); | |
| 380 | } | |
| 381 | ||
| 382 | return $this->text; | |
| 383 | } | |
| 384 | ||
| 385 | /** | |
| 386 | * Prints the text, converted from HTML. | |
| 387 | * | |
| 388 | * @access public | |
| 389 | * @return void | |
| 390 | */ | |
| 391 | function print_text() | |
| 392 | { | |
| 393 | print $this->get_text(); | |
| 394 | } | |
| 395 | ||
| 396 | /** | |
| 397 | * Alias to print_text(), operates identically. | |
| 398 | * | |
| 399 | * @access public | |
| 400 | * @return void | |
| 401 | * @see print_text() | |
| 402 | */ | |
| 403 | function p() | |
| 404 | { | |
| 405 | print $this->get_text(); | |
| 406 | } | |
| 407 | ||
| 408 | /** | |
| 409 | * Sets the allowed HTML tags to pass through to the resulting text. | |
| 410 | * | |
| 411 | * Tags should be in the form "<p>", with no corresponding closing tag. | |
| 412 | * | |
| 413 | * @access public | |
| 414 | * @return void | |
| 415 | */ | |
| 416 | function set_allowed_tags( $allowed_tags = '' ) | |
| 417 | { | |
| 418 | if ( !empty($allowed_tags) ) { | |
| 419 | $this->allowed_tags = $allowed_tags; | |
| 420 | } | |
| 421 | } | |
| 422 | ||
| 423 | /** | |
| 424 | * Sets a base URL to handle relative links. | |
| 425 | * | |
| 426 | * @access public | |
| 427 | * @return void | |
| 428 | */ | |
| 429 | function set_base_url( $url = '' ) | |
| 430 | { | |
| 431 | if ( empty($url) ) { | |
| 8ac6fd | 432 | if ( !empty($_SERVER['HTTP_HOST']) ) { |
| A | 433 | $this->url = 'http://' . $_SERVER['HTTP_HOST']; |
| 434 | } else { | |
| 435 | $this->url = ''; | |
| 436 | } | |
| 4e17e6 | 437 | } else { |
| T | 438 | // Strip any trailing slashes for consistency (relative |
| 439 | // URLs may already start with a slash like "/file.html") | |
| 440 | if ( substr($url, -1) == '/' ) { | |
| 441 | $url = substr($url, 0, -1); | |
| 442 | } | |
| 443 | $this->url = $url; | |
| 444 | } | |
| 445 | } | |
| 446 | ||
| 447 | /** | |
| 11bcac | 448 | * Workhorse function that does actual conversion (calls _converter() method). |
| 4e17e6 | 449 | * |
| T | 450 | * @access private |
| 451 | * @return void | |
| 452 | */ | |
| 453 | function _convert() | |
| 454 | { | |
| 455 | // Variables used for building the link list | |
| 8ac6fd | 456 | $this->_link_count = 0; |
| A | 457 | $this->_link_list = ''; |
| 4e17e6 | 458 | |
| T | 459 | $text = trim(stripslashes($this->html)); |
| 11bcac | 460 | |
| A | 461 | // Convert HTML to TXT |
| 462 | $this->_converter($text); | |
| 463 | ||
| 464 | // Add link list | |
| 465 | if ( !empty($this->_link_list) ) { | |
| 466 | $text .= "\n\nLinks:\n------\n" . $this->_link_list; | |
| 467 | } | |
| 468 | ||
| 469 | $this->text = $text; | |
| 470 | ||
| 471 | $this->_converted = true; | |
| 472 | } | |
| 473 | ||
| 474 | /** | |
| 475 | * Workhorse function that does actual conversion. | |
| 476 | * | |
| 477 | * First performs custom tag replacement specified by $search and | |
| 478 | * $replace arrays. Then strips any remaining HTML tags, reduces whitespace | |
| 479 | * and newlines to a readable format, and word wraps the text to | |
| 480 | * $width characters. | |
| 481 | * | |
| 482 | * @param string Reference to HTML content string | |
| 483 | * | |
| 484 | * @access private | |
| 485 | * @return void | |
| 486 | */ | |
| 487 | function _converter(&$text) | |
| 488 | { | |
| 489 | // Convert <BLOCKQUOTE> (before PRE!) | |
| 490 | $this->_convert_blockquotes($text); | |
| 4e17e6 | 491 | |
| 6972cc | 492 | // Convert <PRE> |
| 8ac6fd | 493 | $this->_convert_pre($text); |
| 300fc6 | 494 | |
| 4e17e6 | 495 | // Run our defined search-and-replace |
| T | 496 | $text = preg_replace($this->search, $this->replace, $text); |
| 497 | ||
| 6972cc | 498 | // Replace known html entities |
| T | 499 | $text = html_entity_decode($text, ENT_COMPAT, 'UTF-8'); |
| da1722 | 500 | |
| A | 501 | // Run our defined search-and-replace with callback |
| 502 | $text = preg_replace_callback($this->callback_search, array('html2text', '_preg_callback'), $text); | |
| 4e0419 | 503 | |
| 755900 | 504 | // Remove unknown/unhandled entities (this cannot be done in search-and-replace block) |
| 6084d7 | 505 | $text = preg_replace('/&([a-zA-Z0-9]{2,6}|#[0-9]{2,4});/', '', $text); |
| A | 506 | |
| 507 | // Convert "|+|amp|+|" into "&", need to be done after handling of unknown entities | |
| 508 | // This properly handles situation of "&quot;" in input string | |
| 509 | $text = str_replace('|+|amp|+|', '&', $text); | |
| 755900 | 510 | |
| 4e17e6 | 511 | // Strip any other HTML tags |
| T | 512 | $text = strip_tags($text, $this->allowed_tags); |
| 513 | ||
| 514 | // Bring down number of empty lines to 2 max | |
| 8ac6fd | 515 | $text = preg_replace("/\n\s+\n/", "\n\n", $text); |
| 4e17e6 | 516 | $text = preg_replace("/[\n]{3,}/", "\n\n", $text); |
| T | 517 | |
| 4d7fbd | 518 | // remove leading empty lines (can be produced by eg. P tag on the beginning) |
| A | 519 | $text = preg_replace('/^\n+/', '', $text); |
| 520 | ||
| 4e17e6 | 521 | // Wrap the text to a readable format |
| T | 522 | // for PHP versions >= 4.0.2. Default width is 75 |
| 8ac6fd | 523 | // If width is 0 or less, don't wrap the text. |
| A | 524 | if ( $this->width > 0 ) { |
| 525 | $text = wordwrap($text, $this->width); | |
| 526 | } | |
| 4e17e6 | 527 | } |
| T | 528 | |
| 529 | /** | |
| 530 | * Helper function called by preg_replace() on link replacement. | |
| 531 | * | |
| 532 | * Maintains an internal list of links to be displayed at the end of the | |
| 533 | * text, with numeric indices to the original point in the text they | |
| 534 | * appeared. Also makes an effort at identifying and handling absolute | |
| 535 | * and relative links. | |
| 536 | * | |
| 537 | * @param string $link URL of the link | |
| 538 | * @param string $display Part of the text to associate number with | |
| 539 | * @access private | |
| 540 | * @return string | |
| 8ac6fd | 541 | */ |
| A | 542 | function _build_link_list( $link, $display ) |
| 543 | { | |
| 11bcac | 544 | if ( !$this->_do_links ) |
| A | 545 | return $display; |
| 546 | ||
| 547 | if ( substr($link, 0, 7) == 'http://' || substr($link, 0, 8) == 'https://' || | |
| 548 | substr($link, 0, 7) == 'mailto:' | |
| 549 | ) { | |
| 8ac6fd | 550 | $this->_link_count++; |
| 11bcac | 551 | $this->_link_list .= '[' . $this->_link_count . "] $link\n"; |
| 8ac6fd | 552 | $additional = ' [' . $this->_link_count . ']'; |
| 11bcac | 553 | } elseif ( substr($link, 0, 11) == 'javascript:' ) { |
| A | 554 | // Don't count the link; ignore it |
| 555 | $additional = ''; | |
| 8ac6fd | 556 | // what about href="#anchor" ? |
| A | 557 | } else { |
| 558 | $this->_link_count++; | |
| 11bcac | 559 | $this->_link_list .= '[' . $this->_link_count . '] ' . $this->url; |
| 8ac6fd | 560 | if ( substr($link, 0, 1) != '/' ) { |
| A | 561 | $this->_link_list .= '/'; |
| 4e17e6 | 562 | } |
| 8ac6fd | 563 | $this->_link_list .= "$link\n"; |
| A | 564 | $additional = ' [' . $this->_link_count . ']'; |
| 4e17e6 | 565 | } |
| T | 566 | |
| 8ac6fd | 567 | return $display . $additional; |
| A | 568 | } |
| 11bcac | 569 | |
| 7353fa | 570 | /** |
| A | 571 | * Helper function for PRE body conversion. |
| 572 | * | |
| 573 | * @param string HTML content | |
| 574 | * @access private | |
| 8ac6fd | 575 | */ |
| 7353fa | 576 | function _convert_pre(&$text) |
| 8ac6fd | 577 | { |
| d483cd | 578 | // get the content of PRE element |
| 11bcac | 579 | while (preg_match('/<pre[^>]*>(.*)<\/pre>/ismU', $text, $matches)) { |
| d483cd | 580 | // convert the content |
| A | 581 | $this->pre_content = sprintf('<div><br>%s<br></div>', |
| 582 | preg_replace($this->pre_search, $this->pre_replace, $matches[1])); | |
| 583 | // replace the content (use callback because content can contain $0 variable) | |
| 584 | $text = preg_replace_callback('/<pre[^>]*>.*<\/pre>/ismU', | |
| 585 | array('html2text', '_preg_pre_callback'), $text, 1); | |
| 586 | // free memory | |
| 587 | $this->pre_content = ''; | |
| 11bcac | 588 | } |
| A | 589 | } |
| 590 | ||
| 591 | /** | |
| 592 | * Helper function for BLOCKQUOTE body conversion. | |
| 593 | * | |
| 594 | * @param string HTML content | |
| 595 | * @access private | |
| 596 | */ | |
| 597 | function _convert_blockquotes(&$text) | |
| 598 | { | |
| 599 | if (preg_match_all('/<\/*blockquote[^>]*>/i', $text, $matches, PREG_OFFSET_CAPTURE)) { | |
| 600 | $level = 0; | |
| 601 | $diff = 0; | |
| 602 | foreach ($matches[0] as $m) { | |
| 603 | if ($m[0][0] == '<' && $m[0][1] == '/') { | |
| 604 | $level--; | |
| 605 | if ($level < 0) { | |
| 606 | $level = 0; // malformed HTML: go to next blockquote | |
| 607 | } | |
| 608 | else if ($level > 0) { | |
| 609 | // skip inner blockquote | |
| 610 | } | |
| 611 | else { | |
| 612 | $end = $m[1]; | |
| 613 | $len = $end - $taglen - $start; | |
| 614 | // Get blockquote content | |
| 615 | $body = substr($text, $start + $taglen - $diff, $len); | |
| 616 | ||
| 617 | // Set text width | |
| 618 | $p_width = $this->width; | |
| 619 | if ($this->width > 0) $this->width -= 2; | |
| 620 | // Convert blockquote content | |
| 621 | $body = trim($body); | |
| 622 | $this->_converter($body); | |
| 623 | // Add citation markers and create PRE block | |
| 624 | $body = preg_replace('/((^|\n)>*)/', '\\1> ', trim($body)); | |
| 625 | $body = '<pre>' . htmlspecialchars($body) . '</pre>'; | |
| 626 | // Re-set text width | |
| 627 | $this->width = $p_width; | |
| 628 | // Replace content | |
| 629 | $text = substr($text, 0, $start - $diff) | |
| 630 | . $body . substr($text, $end + strlen($m[0]) - $diff); | |
| 631 | ||
| 632 | $diff = $len + $taglen + strlen($m[0]) - strlen($body); | |
| 633 | unset($body); | |
| 634 | } | |
| 635 | } | |
| 636 | else { | |
| 637 | if ($level == 0) { | |
| 638 | $start = $m[1]; | |
| 639 | $taglen = strlen($m[0]); | |
| 640 | } | |
| 641 | $level ++; | |
| 642 | } | |
| 643 | } | |
| 6972cc | 644 | } |
| 8ac6fd | 645 | } |
| f50cc7 | 646 | |
| A | 647 | /** |
| 648 | * Callback function for preg_replace_callback use. | |
| 649 | * | |
| 650 | * @param array PREG matches | |
| 651 | * @return string | |
| 652 | */ | |
| d483cd | 653 | private function _preg_callback($matches) |
| f50cc7 | 654 | { |
| 6972cc | 655 | switch($matches[1]) { |
| T | 656 | case 'b': |
| 657 | case 'strong': | |
| 658 | return $this->_strtoupper($matches[2]); | |
| da1722 | 659 | case 'th': |
| 6972cc | 660 | return $this->_strtoupper("\t\t". $matches[2] ."\n"); |
| T | 661 | case 'h': |
| 662 | return $this->_strtoupper("\n\n". $matches[2] ."\n\n"); | |
| 663 | case 'a': | |
| 29c542 | 664 | // Remove spaces in URL (#1487805) |
| A | 665 | $url = str_replace(' ', '', $matches[3]); |
| 666 | return $this->_build_link_list($url, $matches[4]); | |
| 6972cc | 667 | } |
| f50cc7 | 668 | } |
| 29c542 | 669 | |
| f50cc7 | 670 | /** |
| d483cd | 671 | * Callback function for preg_replace_callback use in PRE content handler. |
| A | 672 | * |
| 673 | * @param array PREG matches | |
| 674 | * @return string | |
| 675 | */ | |
| 676 | private function _preg_pre_callback($matches) | |
| 677 | { | |
| 678 | return $this->pre_content; | |
| 679 | } | |
| 680 | ||
| 681 | /** | |
| f50cc7 | 682 | * Strtoupper multibyte wrapper function |
| A | 683 | * |
| 684 | * @param string | |
| 685 | * @return string | |
| 686 | */ | |
| d483cd | 687 | private function _strtoupper($str) |
| f50cc7 | 688 | { |
| 6972cc | 689 | if (function_exists('mb_strtoupper')) |
| T | 690 | return mb_strtoupper($str); |
| 691 | else | |
| 692 | return strtoupper($str); | |
| f50cc7 | 693 | } |
| 4e17e6 | 694 | } |
