jablonka.czprosek.czf

freenet-router

Subversion Repositories:
[/] [trunk/] [freenet-router/] [var/] [www/] [freenet-router/] [Framework/] [3rdParty/] [HtmlToText/] [h2t/] [h2t.php] - Blame information for rev 2

 

Line No. Rev Author Line
12simandl<?php
2 
3/*************************************************************************
4 * *
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 *************************************************************************/
32 
33 
34/**
35 * Takes HTML and converts it to formatted, plain text.
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 */
107class html2text
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 *
129 * Set this value to 0 (or less) to ignore word wrapping
130 * and not constrain text to a fixed-width column.
131 *
132 * @var integer $width
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
148 '/[ ]{2,}/', // Runs of spaces, pre-handling
149 '/<script[^>]*>.*?<\/script>/i', // <script>s -- which strip_tags supposedly has problems with
150 '/<style[^>]*>.*?<\/style>/i', // <style>s -- which strip_tags supposedly has problems with
151 //'/<!-- .* -->/', // Comments -- which strip_tags might have problem a with
152 '/<h[123][^>]*>(.*?)<\/h[123]>/ie', // H1 - H3
153 '/<h[456][^>]*>(.*?)<\/h[456]>/ie', // H4 - H6
154 '/<p[^>]*>/i', // <P>
155 '/<br[^>]*>/i', // <br>
156 '/<b[^>]*>(.*?)<\/b>/ie', // <b>
157 '/<strong[^>]*>(.*?)<\/strong>/ie', // <strong>
158 '/<i[^>]*>(.*?)<\/i>/i', // <i>
159 '/<em[^>]*>(.*?)<\/em>/i', // <em>
160 '/(<ul[^>]*>|<\/ul>)/i', // <ul> and </ul>
161 '/(<ol[^>]*>|<\/ol>)/i', // <ol> and </ol>
162 '/<li[^>]*>(.*?)<\/li>/i', // <li> and </li>
163 '/<li[^>]*>/i', // <li>
164 '/<a [^>]*href="([^"]+)"[^>]*>(.*?)<\/a>/ie',
165 // <a href="">
166 '/<hr[^>]*>/i', // <hr>
167 '/(<table[^>]*>|<\/table>)/i', // <table> and </table>
168 '/(<tr[^>]*>|<\/tr>)/i', // <tr> and </tr>
169 '/<td[^>]*>(.*?)<\/td>/i', // <td> and </td>
170 '/<th[^>]*>(.*?)<\/th>/ie', // <th> and </th>
171 '/&(nbsp|#160);/i', // Non-breaking space
172 '/&(quot|rdquo|ldquo|#8220|#8221|#147|#148);/i',
173 // Double quotes
174 '/&(apos|rsquo|lsquo|#8216|#8217);/i', // Single quotes
175 '/&gt;/i', // Greater-than
176 '/&lt;/i', // Less-than
177 '/&(amp|#38);/i', // Ampersand
178 '/&(copy|#169);/i', // Copyright
179 '/&(trade|#8482|#153);/i', // Trademark
180 '/&(reg|#174);/i', // Registered
181 '/&(mdash|#151|#8212);/i', // mdash
182 '/&(ndash|minus|#8211|#8722);/i', // ndash
183 '/&(bull|#149|#8226);/i', // Bullet
184 '/&(pound|#163);/i', // Pound sign
185 '/&(euro|#8364);/i', // Euro sign
186 '/&[^&;]+;/i', // Unknown/unhandled entities
187 '/[ ]{2,}/' // Runs of spaces, post-handling
188 );
189 
190 /**
191 * List of pattern replacements corresponding to patterns searched.
192 *
193 * @var array $replace
194 * @access public
195 * @see $search
196 */
197 var $replace = array(
198 '', // Non-legal carriage return
199 ' ', // Newlines and tabs
200 ' ', // Runs of spaces, pre-handling
201 '', // <script>s -- which strip_tags supposedly has problems with
202 '', // <style>s -- which strip_tags supposedly has problems with
203 //'', // Comments -- which strip_tags might have problem a with
204 "strtoupper(\"\n\n\\1\n\n\")", // H1 - H3
205 "ucwords(\"\n\n\\1\n\n\")", // H4 - H6
206 "\n\n\t", // <P>
207 "\n", // <br>
208 'strtoupper("\\1")', // <b>
209 'strtoupper("\\1")', // <strong>
210 '_\\1_', // <i>
211 '_\\1_', // <em>
212 "\n\n", // <ul> and </ul>
213 "\n\n", // <ol> and </ol>
214 "\t* \\1\n", // <li> and </li>
215 "\n\t* ", // <li>
216 '$this->_build_link_list("\\1", "\\2")',
217 // <a href="">
218 "\n-------------------------\n", // <hr>
219 "\n\n", // <table> and </table>
220 "\n", // <tr> and </tr>
221 "\t\t\\1\n", // <td> and </td>
222 "strtoupper(\"\t\t\\1\n\")", // <th> and </th>
223 ' ', // Non-breaking space
224 '"', // Double quotes
225 "'", // Single quotes
226 '>',
227 '<',
228 '&',
229 '(c)',
230 '(tm)',
231 '(R)',
232 '--',
233 '-',
234 '*',
235 'ďż˝',
236 'EUR', // Euro sign. ďż˝ ?
237 '', // Unknown/unhandled entities
238 ' ' // Runs of spaces, post-handling
239 );
240 
241 /**
242 * Contains a list of HTML tags to allow in the resulting text.
243 *
244 * @var string $allowed_tags
245 * @access public
246 * @see set_allowed_tags()
247 */
248 var $allowed_tags = '';
249 
250 /**
251 * Contains the base URL that relative links should resolve to.
252 *
253 * @var string $url
254 * @access public
255 */
256 var $url;
257 
258 /**
259 * Indicates whether content in the $html variable has been converted yet.
260 *
261 * @var boolean $_converted
262 * @access private
263 * @see $html, $text
264 */
265 var $_converted = false;
266 
267 /**
268 * Contains URL addresses from links to be rendered in plain text.
269 *
270 * @var string $_link_list
271 * @access private
272 * @see _build_link_list()
273 */
274 var $_link_list = '';
275 
276 /**
277 * Number of valid links detected in the text, used for plain text
278 * display (rendered similar to footnotes).
279 *
280 * @var integer $_link_count
281 * @access private
282 * @see _build_link_list()
283 */
284 var $_link_count = 0;
285 
286 /**
287 * Constructor.
288 *
289 * If the HTML source string (or file) is supplied, the class
290 * will instantiate with that source propagated, all that has
291 * to be done it to call get_text().
292 *
293 * @param string $source HTML content
294 * @param boolean $from_file Indicates $source is a file to pull content from
295 * @access public
296 * @return void
297 */
298 function html2text( $source = '', $from_file = false )
299 {
300 if ( !empty($source) ) {
301 $this->set_html($source, $from_file);
302 }
303 $this->set_base_url();
304 }
305 
306 /**
307 * Loads source HTML into memory, either from $source string or a file.
308 *
309 * @param string $source HTML content
310 * @param boolean $from_file Indicates $source is a file to pull content from
311 * @access public
312 * @return void
313 */
314 function set_html( $source, $from_file = false )
315 {
316 $this->html = $source;
317 
318 if ( $from_file && file_exists($source) ) {
319 $fp = fopen($source, 'r');
320 $this->html = fread($fp, filesize($source));
321 fclose($fp);
322 }
323 
324 $this->_converted = false;
325 }
326 
327 /**
328 * Returns the text, converted from HTML.
329 *
330 * @access public
331 * @return string
332 */
333 function get_text()
334 {
335 if ( !$this->_converted ) {
336 $this->_convert();
337 }
338 
339 return $this->text;
340 }
341 
342 /**
343 * Prints the text, converted from HTML.
344 *
345 * @access public
346 * @return void
347 */
348 function print_text()
349 {
350 print $this->get_text();
351 }
352 
353 /**
354 * Alias to print_text(), operates identically.
355 *
356 * @access public
357 * @return void
358 * @see print_text()
359 */
360 function p()
361 {
362 print $this->get_text();
363 }
364 
365 /**
366 * Sets the allowed HTML tags to pass through to the resulting text.
367 *
368 * Tags should be in the form "<p>", with no corresponding closing tag.
369 *
370 * @access public
371 * @return void
372 */
373 function set_allowed_tags( $allowed_tags = '' )
374 {
375 if ( !empty($allowed_tags) ) {
376 $this->allowed_tags = $allowed_tags;
377 }
378 }
379 
380 /**
381 * Sets a base URL to handle relative links.
382 *
383 * @access public
384 * @return void
385 */
386 function set_base_url( $url = '' )
387 {
388 if ( empty($url) ) {
389 if ( !empty($_SERVER['HTTP_HOST']) ) {
390 $this->url = 'http://' . $_SERVER['HTTP_HOST'];
391 } else {
392 $this->url = '';
393 }
394 } else {
395 // Strip any trailing slashes for consistency (relative
396 // URLs may already start with a slash like "/file.html")
397 if ( substr($url, -1) == '/' ) {
398 $url = substr($url, 0, -1);
399 }
400 $this->url = $url;
401 }
402 }
403 
404 /**
405 * Workhorse function that does actual conversion.
406 *
407 * First performs custom tag replacement specified by $search and
408 * $replace arrays. Then strips any remaining HTML tags, reduces whitespace
409 * and newlines to a readable format, and word wraps the text to
410 * $width characters.
411 *
412 * @access private
413 * @return void
414 */
415 function _convert()
416 {
417 // Variables used for building the link list
418 $this->_link_count = 0;
419 $this->_link_list = '';
420 
421 $text = trim(stripslashes($this->html));
422 
423 // Run our defined search-and-replace
424 $text = preg_replace($this->search, $this->replace, $text);
425 
426 // Strip any other HTML tags
427 $text = strip_tags($text, $this->allowed_tags);
428 
429 // Bring down number of empty lines to 2 max
430 $text = preg_replace("/\n\s+\n/", "\n\n", $text);
431 $text = preg_replace("/[\n]{3,}/", "\n\n", $text);
432 
433 // Add link list
434 if ( !empty($this->_link_list) ) {
435 $text .= "\n\nLinks:\n------\n" . $this->_link_list;
436 }
437 
438 // Wrap the text to a readable format
439 // for PHP versions >= 4.0.2. Default width is 75
440 // If width is 0 or less, don't wrap the text.
441 if ( $this->width > 0 ) {
442 $text = wordwrap($text, $this->width);
443 }
444 
445 $this->text = $text;
446 
447 $this->_converted = true;
448 }
449 
450 /**
451 * Helper function called by preg_replace() on link replacement.
452 *
453 * Maintains an internal list of links to be displayed at the end of the
454 * text, with numeric indices to the original point in the text they
455 * appeared. Also makes an effort at identifying and handling absolute
456 * and relative links.
457 *
458 * @param string $link URL of the link
459 * @param string $display Part of the text to associate number with
460 * @access private
461 * @return string
462 */
463 function _build_link_list( $link, $display )
464 {
465 if ( substr($link, 0, 7) == 'http://' || substr($link, 0, 8) == 'https://' ||
466 substr($link, 0, 7) == 'mailto:' ) {
467 $this->_link_count++;
468 $this->_link_list .= "[" . $this->_link_count . "] $link\n";
469 $additional = ' [' . $this->_link_count . ']';
470 } elseif ( substr($link, 0, 11) == 'javascript:' ) {
471 // Don't count the link; ignore it
472 $additional = '';
473 // what about href="#anchor" ?
474 } else {
475 $this->_link_count++;
476 $this->_link_list .= "[" . $this->_link_count . "] " . $this->url;
477 if ( substr($link, 0, 1) != '/' ) {
478 $this->_link_list .= '/';
479 }
480 $this->_link_list .= "$link\n";
481 $additional = ' [' . $this->_link_count . ']';
482 }
483 
484 return $display . $additional;
485 }
486 
487}

Powered by WebSVN 2.2.1