This repository was archived by the owner on Mar 7, 2024. It is now read-only.
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathHtml2Text.php
More file actions
596 lines (528 loc) · 18.9 KB
/
Html2Text.php
File metadata and controls
596 lines (528 loc) · 18.9 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
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
<?php
/*
* Copyright (c) 2005-2007 Jon Abernathy <jon@chuggnutt.com>
*
* 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.
*/
namespace Html2Text;
class Html2Text
{
const ENCODING = 'UTF-8';
/**
* Contains the HTML content to convert.
*
* @type string
*/
protected $html;
/**
* Contains the converted, formatted text.
*
* @type string
*/
protected $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.
*
* @type integer
*/
protected $width = 70;
/**
* List of preg* regular expression patterns to search for,
* used in conjunction with $replace.
*
* @type array
* @see $replace
*/
protected $search = array(
"/\r/", // Non-legal carriage return
"/[\n\t]+/", // Newlines and tabs
'/<head[^>]*>.*?<\/head>/i', // <head>
'/<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>
'/(<dl[^>]*>|<\/dl>)/i', // <dl> and </dl>
'/<li[^>]*>(.*?)<\/li>/i', // <li> and </li>
'/<dd[^>]*>(.*?)<\/dd>/i', // <dd> and </dd>
'/<dt[^>]*>(.*?)<\/dt>/i', // <dt> and </dt>
'/<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>
'/<span class="_html2text_ignore">.+?<\/span>/i', // <span class="_html2text_ignore">...</span>
);
/**
* List of pattern replacements corresponding to patterns searched.
*
* @type array
* @see $search
*/
protected $replace = array(
'', // Non-legal carriage return
' ', // Newlines and tabs
'', // <head>
'', // <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>
"\n\n", // <dl> and </dl>
"\t* \\1\n", // <li> and </li>
" \\1\n", // <dd> and </dd>
"\t* \\1", // <dt> and </dt>
"\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>
"" // <span class="_html2text_ignore">...</span>
);
/**
* List of preg* regular expression patterns to search for,
* used in conjunction with $entReplace.
*
* @type array
* @see $entReplace
*/
protected $entSearch = array(
'/™/i', // TM symbol in win-1252
'/—/i', // m-dash in win-1252
'/&(amp|#38);/i', // Ampersand: see converter()
'/[ ]{2,}/', // Runs of spaces, post-handling
);
/**
* List of pattern replacements corresponding to patterns searched.
*
* @type array
* @see $entSearch
*/
protected $entReplace = array(
'™', // TM symbol
'—', // m-dash
'|+|amp|+|', // Ampersand: see converter()
' ', // Runs of spaces, post-handling
);
/**
* List of preg* regular expression patterns to search for
* and replace using callback function.
*
* @type array
*/
protected $callbackSearch = array(
'/<(a) [^>]*href=("|\')([^"\']+)\2([^>]*)>(.*?)<\/a>/i', // <a href="">
'/<(h)[123456]( [^>]*)?>(.*?)<\/h[123456]>/i', // h1 - h6
'/<(b)( [^>]*)?>(.*?)<\/b>/i', // <b>
'/<(strong)( [^>]*)?>(.*?)<\/strong>/i', // <strong>
'/<(th)( [^>]*)?>(.*?)<\/th>/i', // <th> and </th>
);
/**
* List of preg* regular expression patterns to search for in PRE body,
* used in conjunction with $preReplace.
*
* @type array
* @see $preReplace
*/
protected $preSearch = array(
"/\n/",
"/\t/",
'/ /',
'/<pre[^>]*>/',
'/<\/pre>/'
);
/**
* List of pattern replacements corresponding to patterns searched for PRE body.
*
* @type array
* @see $preSearch
*/
protected $preReplace = array(
'<br>',
' ',
' ',
'',
'',
);
/**
* Temporary workspace used during PRE processing.
*
* @type string
*/
protected $preContent = '';
/**
* Contains the base URL that relative links should resolve to.
*
* @type string
*/
protected $baseurl = '';
/**
* Indicates whether content in the $html variable has been converted yet.
*
* @type boolean
* @see $html, $text
*/
protected $converted = false;
/**
* Contains URL addresses from links to be rendered in plain text.
*
* @type array
* @see buildlinkList()
*/
protected $linkList = array();
/**
* Various configuration options (able to be set in the constructor)
*
* @type array
*/
protected $options = array(
'do_links' => 'inline', // 'none'
// 'inline' (show links inline)
// 'nextline' (show links on the next line)
// 'table' (if a table of link URLs should be listed after the text.
'width' => 70, // Maximum width of the formatted text, in columns.
// Set this value to 0 (or less) to ignore word wrapping
// and not constrain text to a fixed-width column.
);
private function legacyConstruct($html = '', $fromFile = false, array $options = array())
{
$this->set_html($html, $fromFile);
$this->options = array_merge($this->options, $options);
}
/**
* @param string $html Source HTML
* @param array $options Set configuration options
*/
public function __construct($html = '', $options = array())
{
// for backwards compatibility
if (!is_array($options)) {
return call_user_func_array(array($this, 'legacyConstruct'), func_get_args());
}
$this->html = $html;
$this->options = array_merge($this->options, $options);
}
/**
* Set the source HTML
*
* @param string $html HTML source content
*/
public function setHtml($html)
{
$this->html = $html;
$this->converted = false;
}
/**
* @deprecated
*/
public function set_html($html, $from_file = false)
{
if ($from_file) {
throw new \InvalidArgumentException("Argument from_file no longer supported");
}
return $this->setHtml($html);
}
/**
* Returns the text, converted from HTML.
*
* @return string
*/
public function getText()
{
if (!$this->converted) {
$this->convert();
}
return $this->text;
}
/**
* @deprecated
*/
public function get_text()
{
return $this->getText();
}
/**
* @deprecated
*/
public function print_text()
{
print $this->getText();
}
/**
* @deprecated
*/
public function p()
{
return $this->print_text();
}
/**
* Sets a base URL to handle relative links.
*
* @param string $baseurl
*/
public function setBaseUrl($baseurl)
{
$this->baseurl = $baseurl;
}
/**
* @deprecated
*/
public function set_base_url($baseurl)
{
return $this->setBaseUrl($baseurl);
}
protected function convert()
{
$this->linkList = array();
$text = trim(stripslashes($this->html));
$this->converter($text);
if ($this->linkList) {
$text .= "\n\nLinks:\n------\n";
foreach ($this->linkList as $i => $url) {
$text .= '[' . ($i + 1) . '] ' . $url . "\n";
}
}
$this->text = $text;
$this->converted = true;
}
protected function converter(&$text)
{
$this->convertBlockquotes($text);
$this->convertPre($text);
$text = preg_replace($this->search, $this->replace, $text);
$text = preg_replace_callback($this->callbackSearch, array($this, 'pregCallback'), $text);
$text = strip_tags($text);
$text = preg_replace($this->entSearch, $this->entReplace, $text);
$text = html_entity_decode($text, ENT_QUOTES, self::ENCODING);
// 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);
// Normalise empty lines
$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");
if ($this->options['width'] > 0) {
$text = wordwrap($text, $this->options['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
* @param null $linkOverride
* @return string
*/
protected function buildlinkList($link, $display, $linkOverride = null)
{
$linkMethod = ($linkOverride) ? $linkOverride : $this->options['do_links'];
if ($linkMethod == 'none') {
return $display;
}
// Ignored link types
if (preg_match('!^(javascript:|mailto:|#)!i', $link)) {
return $display;
}
if (preg_match('!^([a-z][a-z0-9.+-]+:)!i', $link)) {
$url = $link;
} else {
$url = $this->baseurl;
if (substr($link, 0, 1) != '/') {
$url .= '/';
}
$url .= $link;
}
if ($linkMethod == 'table') {
if (($index = array_search($url, $this->linkList)) === false) {
$index = count($this->linkList);
$this->linkList[] = $url;
}
return $display . ' [' . ($index + 1) . ']';
} elseif ($linkMethod == 'nextline') {
return $display . "\n ".$url;
} else { // link_method defaults to inline
return $display . ' '. $url;
}
}
protected function convertPre(&$text)
{
// get the content of PRE element
while (preg_match('/<pre[^>]*>(.*)<\/pre>/ismU', $text, $matches)) {
$this->preContent = $matches[1];
// Run our defined tags search-and-replace with callback
$this->preContent = preg_replace_callback(
$this->callbackSearch,
array($this, 'pregCallback'),
$this->preContent
);
// convert the content
$this->preContent = sprintf(
'<div><br>%s<br></div>',
preg_replace($this->preSearch, $this->preReplace, $this->preContent)
);
// replace the content (use callback because content can contain $0 variable)
$text = preg_replace_callback(
'/<pre[^>]*>.*<\/pre>/ismU',
array($this, 'pregPreCallback'),
$text,
1
);
// free memory
$this->preContent = '';
}
}
/**
* Helper function for BLOCKQUOTE body conversion.
*
* @param string $text HTML content
*/
protected function convertBlockquotes(&$text)
{
if (preg_match_all('/<\/*blockquote[^>]*>/i', $text, $matches, PREG_OFFSET_CAPTURE)) {
$start = 0;
$taglen = 0;
$level = 0;
$diff = 0;
foreach ($matches[0] as $m) {
if ($m[0][0] == '<' && $m[0][1] == '/') {
$level--;
if ($level < 0) {
$level = 0; // malformed HTML: go to next blockquote
} elseif ($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
$pWidth = $this->options['width'];
if ($this->options['width'] > 0) $this->options['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->options['width'] = $pWidth;
// 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 $matches PREG matches
* @return string
*/
protected function pregCallback($matches)
{
switch (strtolower($matches[1])) {
case 'b':
case 'strong':
return $this->toupper($matches[3]);
case 'th':
return $this->toupper("\t\t" . $matches[3] . "\n");
case 'h':
return $this->toupper("\n\n" . $matches[3] . "\n\n");
case 'a':
// override the link method
$linkOverride = null;
if (preg_match('/_html2text_link_(\w+)/', $matches[4], $linkOverrideMatch)) {
$linkOverride = $linkOverrideMatch[1];
}
// Remove spaces in URL (#1487805)
$url = str_replace(' ', '', $matches[3]);
return $this->buildlinkList($url, $matches[5], $linkOverride);
}
return '';
}
/**
* Callback function for preg_replace_callback use in PRE content handler.
*
* @param array $matches PREG matches
* @return string
*/
protected function pregPreCallback(/** @noinspection PhpUnusedParameterInspection */ $matches)
{
return $this->preContent;
}
/**
* Strtoupper function with HTML tags and entities handling.
*
* @param string $str Text to convert
* @return string Converted text
*/
private function toupper($str)
{
// string can contain 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 $i => $chunk) {
if ($chunk[0] != '<') {
$chunks[$i] = $this->strtoupper($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, self::ENCODING);
if (function_exists('mb_strtoupper')) {
$str = mb_strtoupper($str, self::ENCODING);
} else {
$str = strtoupper($str);
}
$str = htmlspecialchars($str, ENT_COMPAT, self::ENCODING);
return $str;
}
}