forked from moodle/moodle
-
Notifications
You must be signed in to change notification settings - Fork 0
/
html2text.php
745 lines (681 loc) · 25 KB
/
html2text.php
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
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
<?php
/*************************************************************************
* *
* class.html2text.inc *
* *
*************************************************************************
* *
* Converts HTML to formatted plain text *
* *
* Copyright (c) 2005-2007 Jon Abernathy <jon@chuggnutt.com> *
* All rights reserved. *
* *
* This script is free software; you can redistribute it and/or modify *
* it under the terms of the GNU General Public License as published by *
* the Free Software Foundation; either version 2 of the License, or *
* (at your option) any later version. *
* *
* The GNU General Public License can be found at *
* http://www.gnu.org/copyleft/gpl.html. *
* *
* This script is distributed in the hope that it will be useful, *
* but WITHOUT ANY WARRANTY; without even the implied warranty of *
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the *
* GNU General Public License for more details. *
* *
* Author(s): Jon Abernathy <jon@chuggnutt.com> *
* *
* Last modified: 08/08/07 *
* *
*************************************************************************/
if (!defined('RCMAIL_CHARSET')) {
define('RCMAIL_CHARSET', 'UTF-8');
}
/**
* Takes HTML and converts it to formatted, plain text.
*
* Thanks to Alexander Krug (http://www.krugar.de/) to pointing out and
* correcting an error in the regexp search array. Fixed 7/30/03.
*
* Updated set_html() function's file reading mechanism, 9/25/03.
*
* Thanks to Joss Sanglier (http://www.dancingbear.co.uk/) for adding
* several more HTML entity codes to the $search and $replace arrays.
* Updated 11/7/03.
*
* Thanks to Darius Kasperavicius (http://www.dar.dar.lt/) for
* suggesting the addition of $allowed_tags and its supporting function
* (which I slightly modified). Updated 3/12/04.
*
* Thanks to Justin Dearing for pointing out that a replacement for the
* <TH> tag was missing, and suggesting an appropriate fix.
* Updated 8/25/04.
*
* Thanks to Mathieu Collas (http://www.myefarm.com/) for finding a
* display/formatting bug in the _build_link_list() function: email
* readers would show the left bracket and number ("[1") as part of the
* rendered email address.
* Updated 12/16/04.
*
* Thanks to Wojciech Bajon (http://histeria.pl/) for submitting code
* to handle relative links, which I hadn't considered. I modified his
* code a bit to handle normal HTTP links and MAILTO links. Also for
* suggesting three additional HTML entity codes to search for.
* Updated 03/02/05.
*
* Thanks to Jacob Chandler for pointing out another link condition
* for the _build_link_list() function: "https".
* Updated 04/06/05.
*
* Thanks to Marc Bertrand (http://www.dresdensky.com/) for
* suggesting a revision to the word wrapping functionality; if you
* specify a $width of 0 or less, word wrapping will be ignored.
* Updated 11/02/06.
*
* *** Big housecleaning updates below:
*
* Thanks to Colin Brown (http://www.sparkdriver.co.uk/) for
* suggesting the fix to handle </li> and blank lines (whitespace).
* Christian Basedau (http://www.movetheweb.de/) also suggested the
* blank lines fix.
*
* Special thanks to Marcus Bointon (http://www.synchromedia.co.uk/),
* Christian Basedau, Norbert Laposa (http://ln5.co.uk/),
* Bas van de Weijer, and Marijn van Butselaar
* for pointing out my glaring error in the <th> handling. Marcus also
* supplied a host of fixes.
*
* Thanks to Jeffrey Silverman (http://www.newtnotes.com/) for pointing
* out that extra spaces should be compressed--a problem addressed with
* Marcus Bointon's fixes but that I had not yet incorporated.
*
* Thanks to Daniel Schledermann (http://www.typoconsult.dk/) for
* suggesting a valuable fix with <a> tag handling.
*
* Thanks to Wojciech Bajon (again!) for suggesting fixes and additions,
* including the <a> tag handling that Daniel Schledermann pointed
* out but that I had not yet incorporated. I haven't (yet)
* incorporated all of Wojciech's changes, though I may at some
* future time.
*
* *** End of the housecleaning updates. Updated 08/08/07.
*
* @author Jon Abernathy <jon@chuggnutt.com>
* @version 1.0.0
* @since PHP 4.0.2
*/
class html2text
{
/**
* Contains the HTML content to convert.
*
* @var string $html
* @access public
*/
var $html;
/**
* Contains the converted, formatted text.
*
* @var string $text
* @access public
*/
var $text;
/**
* Maximum width of the formatted text, in columns.
*
* Set this value to 0 (or less) to ignore word wrapping
* and not constrain text to a fixed-width column.
*
* @var integer $width
* @access public
*/
var $width = 70;
/**
* List of preg* regular expression patterns to search for,
* used in conjunction with $replace.
*
* @var array $search
* @access public
* @see $replace
*/
var $search = array(
"/\r/", // Non-legal carriage return
"/[\n\t]+/", // Newlines and tabs
'/<script[^>]*>.*?<\/script>/i', // <script>s -- which strip_tags supposedly has problems with
'/<style[^>]*>.*?<\/style>/i', // <style>s -- which strip_tags supposedly has problems with
'/<p[^>]*>/i', // <P>
'/<br[^>]*>/i', // <br>
'/<i[^>]*>(.*?)<\/i>/i', // <i>
'/<em[^>]*>(.*?)<\/em>/i', // <em>
'/(<ul[^>]*>|<\/ul>)/i', // <ul> and </ul>
'/(<ol[^>]*>|<\/ol>)/i', // <ol> and </ol>
'/<li[^>]*>(.*?)<\/li>/i', // <li> and </li>
'/<li[^>]*>/i', // <li>
'/<hr[^>]*>/i', // <hr>
'/<div[^>]*>/i', // <div>
'/(<table[^>]*>|<\/table>)/i', // <table> and </table>
'/(<tr[^>]*>|<\/tr>)/i', // <tr> and </tr>
'/<td[^>]*>(.*?)<\/td>/i', // <td> and </td>
);
/**
* List of pattern replacements corresponding to patterns searched.
*
* @var array $replace
* @access public
* @see $search
*/
var $replace = array(
'', // Non-legal carriage return
' ', // Newlines and tabs
'', // <script>s -- which strip_tags supposedly has problems with
'', // <style>s -- which strip_tags supposedly has problems with
"\n\n", // <P>
"\n", // <br>
'_\\1_', // <i>
'_\\1_', // <em>
"\n\n", // <ul> and </ul>
"\n\n", // <ol> and </ol>
"\t* \\1\n", // <li> and </li>
"\n\t* ", // <li>
"\n-------------------------\n", // <hr>
"<div>\n", // <div>
"\n\n", // <table> and </table>
"\n", // <tr> and </tr>
"\t\t\\1\n", // <td> and </td>
);
/**
* List of preg* regular expression patterns to search for,
* used in conjunction with $ent_replace.
*
* @var array $ent_search
* @access public
* @see $ent_replace
*/
var $ent_search = array(
'/&(nbsp|#160);/i', // Non-breaking space
'/&(quot|rdquo|ldquo|#8220|#8221|#147|#148);/i',
// Double quotes
'/&(apos|rsquo|lsquo|#8216|#8217);/i', // Single quotes
'/>/i', // Greater-than
'/</i', // Less-than
'/&(copy|#169);/i', // Copyright
'/&(trade|#8482|#153);/i', // Trademark
'/&(reg|#174);/i', // Registered
'/&(mdash|#151|#8212);/i', // mdash
'/&(ndash|minus|#8211|#8722);/i', // ndash
'/&(bull|#149|#8226);/i', // Bullet
'/&(pound|#163);/i', // Pound sign
'/&(euro|#8364);/i', // Euro sign
'/&(amp|#38);/i', // Ampersand: see _converter()
'/[ ]{2,}/', // Runs of spaces, post-handling
);
/**
* List of pattern replacements corresponding to patterns searched.
*
* @var array $ent_replace
* @access public
* @see $ent_search
*/
var $ent_replace = array(
' ', // Non-breaking space
'"', // Double quotes
"'", // Single quotes
'>',
'<',
'(c)',
'(tm)',
'(R)',
'--',
'-',
'*',
'£',
'EUR', // Euro sign. € ?
'|+|amp|+|', // Ampersand: see _converter()
' ', // Runs of spaces, post-handling
);
/**
* List of preg* regular expression patterns to search for
* and replace using callback function.
*
* @var array $callback_search
* @access public
*/
var $callback_search = array(
'/<(a) [^>]*href=("|\')([^"\']+)\2[^>]*>(.*?)<\/a>/i',
// <a href="">
'/<(h)[123456][^>]*>(.*?)<\/h[123456]>/i', // H1 - H3
'/<(b)[^>]*>(.*?)<\/b>/i', // <b>
'/<(strong)[^>]*>(.*?)<\/strong>/i', // <strong>
'/<(th)[^>]*>(.*?)<\/th>/i', // <th> and </th>
'/<(img)[^>]*alt=\"([^>"]+)\"[^>]*>/i', // <img> with alt
);
/**
* List of preg* regular expression patterns to search for in PRE body,
* used in conjunction with $pre_replace.
*
* @var array $pre_search
* @access public
* @see $pre_replace
*/
var $pre_search = array(
"/\n/",
"/\t/",
'/ /',
'/<pre[^>]*>/',
'/<\/pre>/'
);
/**
* List of pattern replacements corresponding to patterns searched for PRE body.
*
* @var array $pre_replace
* @access public
* @see $pre_search
*/
var $pre_replace = array(
'<br>',
' ',
' ',
'',
''
);
/**
* Contains a list of HTML tags to allow in the resulting text.
*
* @var string $allowed_tags
* @access public
* @see set_allowed_tags()
*/
var $allowed_tags = '';
/**
* Contains the base URL that relative links should resolve to.
*
* @var string $url
* @access public
*/
var $url;
/**
* Indicates whether content in the $html variable has been converted yet.
*
* @var boolean $_converted
* @access private
* @see $html, $text
*/
var $_converted = false;
/**
* Contains URL addresses from links to be rendered in plain text.
*
* @var array $_link_list
* @access private
* @see _build_link_list()
*/
var $_link_list = array();
/**
* Boolean flag, true if a table of link URLs should be listed after the text.
*
* @var boolean $_do_links
* @access private
* @see html2text()
*/
var $_do_links = true;
/**
* Constructor.
*
* If the HTML source string (or file) is supplied, the class
* will instantiate with that source propagated, all that has
* to be done it to call get_text().
*
* @param string $source HTML content
* @param boolean $from_file Indicates $source is a file to pull content from
* @param boolean $do_links Indicate whether a table of link URLs is desired
* @param integer $width Maximum width of the formatted text, 0 for no limit
* @access public
* @return void
*/
function html2text( $source = '', $from_file = false, $do_links = true, $width = 75 )
{
if ( $source !== '' ) {
$this->set_html($source, $from_file);
}
$this->set_base_url();
$this->_do_links = $do_links;
$this->width = $width;
}
/**
* Loads source HTML into memory, either from $source string or a file.
*
* @param string $source HTML content
* @param boolean $from_file Indicates $source is a file to pull content from
* @access public
* @return void
*/
function set_html( $source, $from_file = false )
{
if ( $from_file && file_exists($source) ) {
$this->html = file_get_contents($source);
}
else
$this->html = $source;
$this->_converted = false;
}
/**
* Returns the text, converted from HTML.
*
* @access public
* @return string
*/
function get_text()
{
if ( !$this->_converted ) {
$this->_convert();
}
return $this->text;
}
/**
* Prints the text, converted from HTML.
*
* @access public
* @return void
*/
function print_text()
{
print $this->get_text();
}
/**
* Alias to print_text(), operates identically.
*
* @access public
* @return void
* @see print_text()
*/
function p()
{
print $this->get_text();
}
/**
* Sets the allowed HTML tags to pass through to the resulting text.
*
* Tags should be in the form "<p>", with no corresponding closing tag.
*
* @access public
* @return void
*/
function set_allowed_tags( $allowed_tags = '' )
{
if ( !empty($allowed_tags) ) {
$this->allowed_tags = $allowed_tags;
}
}
/**
* Sets a base URL to handle relative links.
*
* @access public
* @return void
*/
function set_base_url( $url = '' )
{
if ( empty($url) ) {
if ( !empty($_SERVER['HTTP_HOST']) ) {
$this->url = 'http://' . $_SERVER['HTTP_HOST'];
} else {
$this->url = '';
}
} else {
// Strip any trailing slashes for consistency (relative
// URLs may already start with a slash like "/file.html")
if ( substr($url, -1) == '/' ) {
$url = substr($url, 0, -1);
}
$this->url = $url;
}
}
/**
* Workhorse function that does actual conversion (calls _converter() method).
*
* @access private
* @return void
*/
function _convert()
{
// Variables used for building the link list
$this->_link_list = array();
$text = trim($this->html);
// Convert HTML to TXT
$this->_converter($text);
// Add link list
if (!empty($this->_link_list)) {
$text .= "\n\nLinks:\n------\n";
foreach ($this->_link_list as $idx => $url) {
$text .= '[' . ($idx+1) . '] ' . $url . "\n";
}
}
$this->text = $text;
$this->_converted = true;
}
/**
* Workhorse function that does actual conversion.
*
* First performs custom tag replacement specified by $search and
* $replace arrays. Then strips any remaining HTML tags, reduces whitespace
* and newlines to a readable format, and word wraps the text to
* $width characters.
*
* @param string Reference to HTML content string
*
* @access private
* @return void
*/
function _converter(&$text)
{
// Convert <BLOCKQUOTE> (before PRE!)
$this->_convert_blockquotes($text);
// Convert <PRE>
$this->_convert_pre($text);
// Run our defined tags search-and-replace
$text = preg_replace($this->search, $this->replace, $text);
// Run our defined tags search-and-replace with callback
$text = preg_replace_callback($this->callback_search, array('html2text', '_preg_callback'), $text);
// Strip any other HTML tags
$text = strip_tags($text, $this->allowed_tags);
// Run our defined entities/characters search-and-replace
$text = preg_replace($this->ent_search, $this->ent_replace, $text);
// Replace known html entities
$text = html_entity_decode($text, ENT_COMPAT, 'UTF-8');
// Remove unknown/unhandled entities (this cannot be done in search-and-replace block)
$text = preg_replace('/&([a-zA-Z0-9]{2,6}|#[0-9]{2,4});/', '', $text);
// Convert "|+|amp|+|" into "&", need to be done after handling of unknown entities
// This properly handles situation of "&quot;" in input string
$text = str_replace('|+|amp|+|', '&', $text);
// Bring down number of empty lines to 2 max
$text = preg_replace("/\n\s+\n/", "\n\n", $text);
$text = preg_replace("/[\n]{3,}/", "\n\n", $text);
// remove leading empty lines (can be produced by eg. P tag on the beginning)
$text = ltrim($text, "\n");
// Wrap the text to a readable format
// for PHP versions >= 4.0.2. Default width is 75
// If width is 0 or less, don't wrap the text.
if ( $this->width > 0 ) {
$text = wordwrap($text, $this->width);
}
}
/**
* Helper function called by preg_replace() on link replacement.
*
* Maintains an internal list of links to be displayed at the end of the
* text, with numeric indices to the original point in the text they
* appeared. Also makes an effort at identifying and handling absolute
* and relative links.
*
* @param string $link URL of the link
* @param string $display Part of the text to associate number with
* @access private
* @return string
*/
function _build_link_list( $link, $display )
{
if (!$this->_do_links || empty($link)) {
return $display;
}
// Ignored link types
if (preg_match('!^(javascript|mailto|#):!i', $link)) {
return $display;
}
if (preg_match('!^(https?://)!i', $link)) {
$url = $link;
}
else {
$url = $this->url;
if (substr($link, 0, 1) != '/') {
$url .= '/';
}
$url .= "$link";
}
if (($index = array_search($url, $this->_link_list)) === false) {
$this->_link_list[] = $url;
$index = count($this->_link_list);
}
return $display . ' [' . ($index+1) . ']';
}
/**
* Helper function for PRE body conversion.
*
* @param string HTML content
* @access private
*/
function _convert_pre(&$text)
{
// get the content of PRE element
while (preg_match('/<pre[^>]*>(.*)<\/pre>/ismU', $text, $matches)) {
// convert the content
$this->pre_content = sprintf('<div><br>%s<br></div>',
preg_replace($this->pre_search, $this->pre_replace, $matches[1]));
// replace the content (use callback because content can contain $0 variable)
$text = preg_replace_callback('/<pre[^>]*>.*<\/pre>/ismU',
array('html2text', '_preg_pre_callback'), $text, 1);
// free memory
$this->pre_content = '';
}
}
/**
* Helper function for BLOCKQUOTE body conversion.
*
* @param string HTML content
* @access private
*/
function _convert_blockquotes(&$text)
{
if (preg_match_all('/<\/*blockquote[^>]*>/i', $text, $matches, PREG_OFFSET_CAPTURE)) {
$level = 0;
$diff = 0;
foreach ($matches[0] as $m) {
if ($m[0][0] == '<' && $m[0][1] == '/') {
$level--;
if ($level < 0) {
$level = 0; // malformed HTML: go to next blockquote
}
else if ($level > 0) {
// skip inner blockquote
}
else {
$end = $m[1];
$len = $end - $taglen - $start;
// Get blockquote content
$body = substr($text, $start + $taglen - $diff, $len);
// Set text width
$p_width = $this->width;
if ($this->width > 0) $this->width -= 2;
// Convert blockquote content
$body = trim($body);
$this->_converter($body);
// Add citation markers and create PRE block
$body = preg_replace('/((^|\n)>*)/', '\\1> ', trim($body));
$body = '<pre>' . htmlspecialchars($body) . '</pre>';
// Re-set text width
$this->width = $p_width;
// Replace content
$text = substr($text, 0, $start - $diff)
. $body . substr($text, $end + strlen($m[0]) - $diff);
$diff = $len + $taglen + strlen($m[0]) - strlen($body);
unset($body);
}
}
else {
if ($level == 0) {
$start = $m[1];
$taglen = strlen($m[0]);
}
$level ++;
}
}
}
}
/**
* Callback function for preg_replace_callback use.
*
* @param array PREG matches
* @return string
*/
private function _preg_callback($matches)
{
switch($matches[1]) {
case 'b':
case 'strong':
return $this->_toupper($matches[2]);
case 'th':
return $this->_toupper("\t\t". $matches[2] ."\n");
case 'h':
return $this->_toupper("\n\n". $matches[2] ."\n\n");
case 'a':
// Remove spaces in URL (#1487805)
$url = str_replace(' ', '', $matches[3]);
return $this->_build_link_list($url, $matches[4]);
case 'img':
return '[' . $matches[2] . ']';
}
}
/**
* Callback function for preg_replace_callback use in PRE content handler.
*
* @param array PREG matches
* @return string
*/
private function _preg_pre_callback($matches)
{
return $this->pre_content;
}
/**
* Strtoupper function with HTML tags and entities handling.
*
* @param string $str Text to convert
* @return string Converted text
*/
private function _toupper($str)
{
// string can containg HTML tags
$chunks = preg_split('/(<[^>]*>)/', $str, null, PREG_SPLIT_NO_EMPTY | PREG_SPLIT_DELIM_CAPTURE);
// convert toupper only the text between HTML tags
foreach ($chunks as $idx => $chunk) {
if ($chunk[0] != '<') {
$chunks[$idx] = $this->_strtoupper($chunk);
}
}
return implode($chunks);
}
/**
* Strtoupper multibyte wrapper function with HTML entities handling.
*
* @param string $str Text to convert
* @return string Converted text
*/
private function _strtoupper($str)
{
$str = html_entity_decode($str, ENT_COMPAT, RCMAIL_CHARSET);
if (class_exists('textlib'))
$str = textlib::strtoupper($str);
else if (function_exists('mb_strtoupper'))
$str = mb_strtoupper($str);
else
$str = strtoupper($str);
$str = htmlspecialchars($str, ENT_COMPAT, RCMAIL_CHARSET);
return $str;
}
}