summaryrefslogtreecommitdiff
path: root/program/include/rcube_charset.php
blob: fc1685d28f5f30162b56fba91465628db20b4450 (plain)
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
746
747
748
749
750
751
752
753
754
<?php

/*
 +-----------------------------------------------------------------------+
 | program/include/rcube_charset.php                                     |
 |                                                                       |
 | This file is part of the Roundcube Webmail client                     |
 | Copyright (C) 2005-2012, The Roundcube Dev Team                       |
 | Copyright (C) 2011-2012, Kolab Systems AG                             |
 | Copyright (C) 2000 Edmund Grimley Evans <edmundo@rano.org>            |
 |                                                                       |
 | Licensed under the GNU General Public License version 3 or            |
 | any later version with exceptions for skins & plugins.                |
 | See the README file for a full license statement.                     |
 |                                                                       |
 | PURPOSE:                                                              |
 |   Provide charset conversion functionality                            |
 |                                                                       |
 +-----------------------------------------------------------------------+
 | Author: Thomas Bruederli <roundcube@gmail.com>                        |
 | Author: Aleksander Machniak <alec@alec.pl>                            |
 +-----------------------------------------------------------------------+

 $Id$

*/

/**
 * Character sets conversion functionality
 *
 * @package Core
 * @author Thomas Bruederli <roundcube@gmail.com>
 * @author Aleksander Machniak <alec@alec.pl>
 * @author Edmund Grimley Evans <edmundo@rano.org>
 */
class rcube_charset
{
    // Aliases: some of them from HTML5 spec.
    static public $aliases = array(
        'USASCII'       => 'WINDOWS-1252',
        'ANSIX31101983' => 'WINDOWS-1252',
        'ANSIX341968'   => 'WINDOWS-1252',
        'UNKNOWN8BIT'   => 'ISO-8859-15',
        'UNKNOWN'       => 'ISO-8859-15',
        'USERDEFINED'   => 'ISO-8859-15',
        'KSC56011987'   => 'EUC-KR',
        'GB2312' 	    => 'GBK',
        'GB231280'	    => 'GBK',
        'UNICODE'	    => 'UTF-8',
        'UTF7IMAP'	    => 'UTF7-IMAP',
        'TIS620'	    => 'WINDOWS-874',
        'ISO88599'	    => 'WINDOWS-1254',
        'ISO885911'	    => 'WINDOWS-874',
        'MACROMAN'	    => 'MACINTOSH',
        '77'            => 'MAC',
        '128'           => 'SHIFT-JIS',
        '129'           => 'CP949',
        '130'           => 'CP1361',
        '134'           => 'GBK',
        '136'           => 'BIG5',
        '161'           => 'WINDOWS-1253',
        '162'           => 'WINDOWS-1254',
        '163'           => 'WINDOWS-1258',
        '177'           => 'WINDOWS-1255',
        '178'           => 'WINDOWS-1256',
        '186'           => 'WINDOWS-1257',
        '204'           => 'WINDOWS-1251',
        '222'           => 'WINDOWS-874',
        '238'           => 'WINDOWS-1250',
        'MS950'         => 'CP950',
        'WINDOWS949'    => 'UHC',
    );


    /**
     * Catch an error and throw an exception.
     *
     * @param  int    Level of the error
     * @param  string Error message
     */
    public static function error_handler($errno, $errstr)
    {
        throw new ErrorException($errstr, 0, $errno);
    }


    /**
     * Parse and validate charset name string (see #1485758).
     * Sometimes charset string is malformed, there are also charset aliases 
     * but we need strict names for charset conversion (specially utf8 class)
     *
     * @param  string Input charset name
     *
     * @return string The validated charset name
     */
    public static function parse($input)
    {
        static $charsets = array();
        $charset = strtoupper($input);

        if (isset($charsets[$input])) {
            return $charsets[$input];
        }

        $charset = preg_replace(array(
            '/^[^0-9A-Z]+/',    // e.g. _ISO-8859-JP$SIO
            '/\$.*$/',          // e.g. _ISO-8859-JP$SIO
            '/UNICODE-1-1-*/',  // RFC1641/1642
            '/^X-/',            // X- prefix (e.g. X-ROMAN8 => ROMAN8)
        ), '', $charset);

        if ($charset == 'BINARY') {
            return $charsets[$input] = null;
        }

        // allow A-Z and 0-9 only
        $str = preg_replace('/[^A-Z0-9]/', '', $charset);

        if (isset(self::$aliases[$str])) {
            $result = self::$aliases[$str];
        }
        // UTF
        else if (preg_match('/U[A-Z][A-Z](7|8|16|32)(BE|LE)*/', $str, $m)) {
            $result = 'UTF-' . $m[1] . $m[2];
        }
        // ISO-8859
        else if (preg_match('/ISO8859([0-9]{0,2})/', $str, $m)) {
            $iso = 'ISO-8859-' . ($m[1] ? $m[1] : 1);
            // some clients sends windows-1252 text as latin1,
            // it is safe to use windows-1252 for all latin1
            $result = $iso == 'ISO-8859-1' ? 'WINDOWS-1252' : $iso;
        }
        // handle broken charset names e.g. WINDOWS-1250HTTP-EQUIVCONTENT-TYPE
        else if (preg_match('/(WIN|WINDOWS)([0-9]+)/', $str, $m)) {
            $result = 'WINDOWS-' . $m[2];
        }
        // LATIN
        else if (preg_match('/LATIN(.*)/', $str, $m)) {
            $aliases = array('2' => 2, '3' => 3, '4' => 4, '5' => 9, '6' => 10,
                '7' => 13, '8' => 14, '9' => 15, '10' => 16,
                'ARABIC' => 6, 'CYRILLIC' => 5, 'GREEK' => 7, 'GREEK1' => 7, 'HEBREW' => 8
            );

            // some clients sends windows-1252 text as latin1,
            // it is safe to use windows-1252 for all latin1
            if ($m[1] == 1) {
                $result = 'WINDOWS-1252';
            }
            // if iconv is not supported we need ISO labels, it's also safe for iconv
            else if (!empty($aliases[$m[1]])) {
                $result = 'ISO-8859-'.$aliases[$m[1]];
            }
            // iconv requires convertion of e.g. LATIN-1 to LATIN1
            else {
                $result = $str;
            }
        }
        else {
            $result = $charset;
        }

        $charsets[$input] = $result;

        return $result;
    }


    /**
     * Convert a string from one charset to another.
     * Uses mbstring and iconv functions if possible
     *
     * @param  string Input string
     * @param  string Suspected charset of the input string
     * @param  string Target charset to convert to; defaults to RCMAIL_CHARSET
     *
     * @return string Converted string
     */
    public static function convert($str, $from, $to = null)
    {
        static $iconv_options   = null;
        static $mbstring_loaded = null;
        static $mbstring_list   = null;
        static $conv            = null;

        $to   = empty($to) ? strtoupper(RCMAIL_CHARSET) : self::parse($to);
        $from = self::parse($from);

        // It is a common case when UTF-16 charset is used with US-ASCII content (#1488654)
        // In that case we can just skip the conversion (use UTF-8)
        if ($from == 'UTF-16' && !preg_match('/[^\x00-\x7F]/', $str)) {
            $from = 'UTF-8';
        }

        if ($from == $to || empty($str) || empty($from)) {
            return $str;
        }

        // convert charset using iconv module
        if (function_exists('iconv') && $from != 'UTF7-IMAP' && $to != 'UTF7-IMAP') {
            if ($iconv_options === null) {
                // ignore characters not available in output charset
                $iconv_options = '//IGNORE';
                if (iconv('', $iconv_options, '') === false) {
                    // iconv implementation does not support options
                    $iconv_options = '';
                }
            }

            // throw an exception if iconv reports an illegal character in input
            // it means that input string has been truncated
            set_error_handler(array('rcube_charset', 'error_handler'), E_NOTICE);
            try {
                $_iconv = iconv($from, $to . $iconv_options, $str);
            } catch (ErrorException $e) {
                $_iconv = false;
            }
            restore_error_handler();

            if ($_iconv !== false) {
                return $_iconv;
            }
        }

        if ($mbstring_loaded === null) {
            $mbstring_loaded = extension_loaded('mbstring');
        }

        // convert charset using mbstring module
        if ($mbstring_loaded) {
            $aliases['WINDOWS-1257'] = 'ISO-8859-13';

            if ($mbstring_list === null) {
                $mbstring_list = mb_list_encodings();
                $mbstring_list = array_map('strtoupper', $mbstring_list);
            }

            $mb_from = $aliases[$from] ? $aliases[$from] : $from;
            $mb_to   = $aliases[$to] ? $aliases[$to] : $to;

            // return if encoding found, string matches encoding and convert succeeded
            if (in_array($mb_from, $mbstring_list) && in_array($mb_to, $mbstring_list)) {
                if (mb_check_encoding($str, $mb_from) && ($out = mb_convert_encoding($str, $mb_to, $mb_from))) {
                    return $out;
                }
            }
        }

        // convert charset using bundled classes/functions
        if ($to == 'UTF-8') {
            if ($from == 'UTF7-IMAP') {
                if ($_str = self::utf7imap_to_utf8($str)) {
                    return $_str;
                }
            }
            else if ($from == 'UTF-7') {
                if ($_str = self::utf7_to_utf8($str)) {
                    return $_str;
                }
            }
            else if ($from == 'ISO-8859-1' && function_exists('utf8_encode')) {
                return utf8_encode($str);
            }
            else if (class_exists('utf8')) {
                if (!$conv) {
                    $conv = new utf8($from);
                }
                else {
                    $conv->loadCharset($from);
                }

                if ($_str = $conv->strToUtf8($str)) {
                    return $_str;
                }
            }
        }

        // encode string for output
        if ($from == 'UTF-8') {
            // @TODO: we need a function for UTF-7 (RFC2152) conversion
            if ($to == 'UTF7-IMAP' || $to == 'UTF-7') {
                if ($_str = self::utf8_to_utf7imap($str)) {
                    return $_str;
                }
            }
            else if ($to == 'ISO-8859-1' && function_exists('utf8_decode')) {
                return utf8_decode($str);
            }
            else if (class_exists('utf8')) {
                if (!$conv) {
                    $conv = new utf8($to);
                }
                else {
                    $conv->loadCharset($from);
                }

                if ($_str = $conv->strToUtf8($str)) {
                    return $_str;
                }
            }
        }

        // return original string
        return $str;
    }


    /**
     * Converts string from standard UTF-7 (RFC 2152) to UTF-8.
     *
     * @param  string  Input string (UTF-7)
     *
     * @return string  Converted string (UTF-8)
     */
    public static function utf7_to_utf8($str)
    {
        $Index_64 = array(
            0,0,0,0, 0,0,0,0, 0,0,0,0, 0,0,0,0,
            0,0,0,0, 0,0,0,0, 0,0,0,0, 0,0,0,0,
            0,0,0,0, 0,0,0,0, 0,0,0,1, 0,0,0,0,
            1,1,1,1, 1,1,1,1, 1,1,0,0, 0,0,0,0,
            0,1,1,1, 1,1,1,1, 1,1,1,1, 1,1,1,1,
            1,1,1,1, 1,1,1,1, 1,1,1,0, 0,0,0,0,
            0,1,1,1, 1,1,1,1, 1,1,1,1, 1,1,1,1,
            1,1,1,1, 1,1,1,1, 1,1,1,0, 0,0,0,0,
        );

        $u7len = strlen($str);
        $str   = strval($str);
        $res   = '';

        for ($i=0; $u7len > 0; $i++, $u7len--) {
            $u7 = $str[$i];
            if ($u7 == '+') {
                $i++;
                $u7len--;
                $ch = '';

                for (; $u7len > 0; $i++, $u7len--) {
                    $u7 = $str[$i];

                    if (!$Index_64[ord($u7)]) {
                        break;
                    }

	                $ch .= $u7;
                }

                if ($ch == '') {
                    if ($u7 == '-') {
                        $res .= '+';
                    }

                    continue;
                }

                $res .= self::utf16_to_utf8(base64_decode($ch));
            }
            else {
                $res .= $u7;
            }
        }

        return $res;
    }


    /**
     * Converts string from UTF-16 to UTF-8 (helper for utf-7 to utf-8 conversion)
     *
     * @param  string  Input string
     *
     * @return string  The converted string
     */
    public static function utf16_to_utf8($str)
    {
        $len = strlen($str);
        $dec = '';

        for ($i = 0; $i < $len; $i += 2) {
            $c = ord($str[$i]) << 8 | ord($str[$i + 1]);
            if ($c >= 0x0001 && $c <= 0x007F) {
                $dec .= chr($c);
            }
            else if ($c > 0x07FF) {
                $dec .= chr(0xE0 | (($c >> 12) & 0x0F));
                $dec .= chr(0x80 | (($c >>  6) & 0x3F));
                $dec .= chr(0x80 | (($c >>  0) & 0x3F));
            }
            else {
                $dec .= chr(0xC0 | (($c >>  6) & 0x1F));
                $dec .= chr(0x80 | (($c >>  0) & 0x3F));
            }
        }

        return $dec;
    }


    /**
     * Convert the data ($str) from RFC 2060's UTF-7 to UTF-8.
     * If input data is invalid, return the original input string.
     * RFC 2060 obviously intends the encoding to be unique (see
     * point 5 in section 5.1.3), so we reject any non-canonical
     * form, such as &ACY- (instead of &-) or &AMA-&AMA- (instead
     * of &AMAAwA-).
     *
     * Translated from C to PHP by Thomas Bruederli <roundcube@gmail.com>
     *
     * @param string $str Input string (UTF7-IMAP)
     *
     * @return string Output string (UTF-8)
     */
    public static function utf7imap_to_utf8($str)
    {
        $Index_64 = array(
            -1,-1,-1,-1, -1,-1,-1,-1, -1,-1,-1,-1, -1,-1,-1,-1,
            -1,-1,-1,-1, -1,-1,-1,-1, -1,-1,-1,-1, -1,-1,-1,-1,
            -1,-1,-1,-1, -1,-1,-1,-1, -1,-1,-1,62, 63,-1,-1,-1,
            52,53,54,55, 56,57,58,59, 60,61,-1,-1, -1,-1,-1,-1,
            -1, 0, 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,-1, -1,-1,-1,-1,
            -1,26,27,28, 29,30,31,32, 33,34,35,36, 37,38,39,40,
            41,42,43,44, 45,46,47,48, 49,50,51,-1, -1,-1,-1,-1
        );

        $u7len = strlen($str);
        $str   = strval($str);
        $p     = '';
        $err   = '';

        for ($i=0; $u7len > 0; $i++, $u7len--) {
            $u7 = $str[$i];
            if ($u7 == '&') {
                $i++;
                $u7len--;
                $u7 = $str[$i];

                if ($u7len && $u7 == '-') {
                    $p .= '&';
                    continue;
                }

                $ch = 0;
                $k = 10;
                for (; $u7len > 0; $i++, $u7len--) {
                    $u7 = $str[$i];

                    if ((ord($u7) & 0x80) || ($b = $Index_64[ord($u7)]) == -1) {
                        break;
                    }

                    if ($k > 0) {
                        $ch |= $b << $k;
                        $k -= 6;
                    }
                    else {
                        $ch |= $b >> (-$k);
                        if ($ch < 0x80) {
                            // Printable US-ASCII
                            if (0x20 <= $ch && $ch < 0x7f) {
                                return $err;
                            }
                            $p .= chr($ch);
                        }
                        else if ($ch < 0x800) {
                            $p .= chr(0xc0 | ($ch >> 6));
                            $p .= chr(0x80 | ($ch & 0x3f));
                        }
                        else {
                            $p .= chr(0xe0 | ($ch >> 12));
                            $p .= chr(0x80 | (($ch >> 6) & 0x3f));
                            $p .= chr(0x80 | ($ch & 0x3f));
                        }

                        $ch = ($b << (16 + $k)) & 0xffff;
                        $k += 10;
                    }
                }

                // Non-zero or too many extra bits
                if ($ch || $k < 6) {
                    return $err;
                }

                // BASE64 not properly terminated
                if (!$u7len || $u7 != '-') {
                    return $err;
                }

                // Adjacent BASE64 sections
                if ($u7len > 2 && $str[$i+1] == '&' && $str[$i+2] != '-') {
                    return $err;
                }
            }
            // Not printable US-ASCII
            else if (ord($u7) < 0x20 || ord($u7) >= 0x7f) {
                return $err;
            }
            else {
                $p .= $u7;
            }
        }

        return $p;
    }


    /**
     * Convert the data ($str) from UTF-8 to RFC 2060's UTF-7.
     * Unicode characters above U+FFFF are replaced by U+FFFE.
     * If input data is invalid, return an empty string.
     *
     * Translated from C to PHP by Thomas Bruederli <roundcube@gmail.com>
     *
     * @param string $str Input string (UTF-8)
     *
     * @return string Output string (UTF7-IMAP)
     */
    public static function utf8_to_utf7imap($str)
    {
        $B64Chars = array(
            'A', 'B', 'C', 'D', 'E', 'F', 'G', 'H', 'I', 'J', 'K', 'L', 'M', 'N', 'O',
            'P', 'Q', 'R', 'S', 'T', 'U', 'V', 'W', 'X', 'Y', 'Z', 'a', 'b', 'c', 'd',
            'e', 'f', 'g', 'h', 'i', 'j', 'k', 'l', 'm', 'n', 'o', 'p', 'q', 'r', 's',
            't', 'u', 'v', 'w', 'x', 'y', 'z', '0', '1', '2', '3', '4', '5', '6', '7',
            '8', '9', '+', ','
        );

        $u8len  = strlen($str);
        $base64 = 0;
        $i      = 0;
        $p      = '';
        $err    = '';

        while ($u8len) {
            $u8 = $str[$i];
            $c  = ord($u8);

            if ($c < 0x80) {
                $ch = $c;
                $n  = 0;
            }
            else if ($c < 0xc2) {
                return $err;
            }
            else if ($c < 0xe0) {
                $ch = $c & 0x1f;
                $n  = 1;
            }
            else if ($c < 0xf0) {
                $ch = $c & 0x0f;
                $n  = 2;
            }
            else if ($c < 0xf8) {
                $ch = $c & 0x07;
                $n  = 3;
            }
            else if ($c < 0xfc) {
                $ch = $c & 0x03;
                $n  = 4;
            }
            else if ($c < 0xfe) {
                $ch = $c & 0x01;
                $n  = 5;
            }
            else {
                return $err;
            }

            $i++;
            $u8len--;

            if ($n > $u8len) {
                return $err;
            }

            for ($j=0; $j < $n; $j++) {
                $o = ord($str[$i+$j]);
                if (($o & 0xc0) != 0x80) {
                    return $err;
                }
                $ch = ($ch << 6) | ($o & 0x3f);
            }

            if ($n > 1 && !($ch >> ($n * 5 + 1))) {
                return $err;
            }

            $i += $n;
            $u8len -= $n;

            if ($ch < 0x20 || $ch >= 0x7f) {
                if (!$base64) {
                    $p .= '&';
                    $base64 = 1;
                    $b = 0;
                    $k = 10;
                }
                if ($ch & ~0xffff) {
                    $ch = 0xfffe;
                }

                $p .= $B64Chars[($b | $ch >> $k)];
                $k -= 6;
                for (; $k >= 0; $k -= 6) {
                    $p .= $B64Chars[(($ch >> $k) & 0x3f)];
                }

                $b = ($ch << (-$k)) & 0x3f;
                $k += 16;
            }
            else {
                if ($base64) {
                    if ($k > 10) {
                        $p .= $B64Chars[$b];
                    }
                    $p .= '-';
                    $base64 = 0;
                }

                $p .= chr($ch);
                if (chr($ch) == '&') {
                    $p .= '-';
                }
            }
        }

        if ($base64) {
            if ($k > 10) {
                $p .= $B64Chars[$b];
            }
            $p .= '-';
        }

        return $p;
    }


    /**
     * A method to guess character set of a string.
     *
     * @param string $string    String.
     * @param string $failover 	Default result for failover.
     *
     * @return string Charset name
     */
    public static function detect($string, $failover='')
    {
        if (!function_exists('mb_detect_encoding')) {
            return $failover;
        }

        // FIXME: the order is important, because sometimes 
        // iso string is detected as euc-jp and etc.
        $enc = array(
            'UTF-8', 'SJIS', 'BIG5', 'GB2312',
            'ISO-8859-1', 'ISO-8859-2', 'ISO-8859-3', 'ISO-8859-4',
            'ISO-8859-5', 'ISO-8859-6', 'ISO-8859-7', 'ISO-8859-8', 'ISO-8859-9',
            'ISO-8859-10', 'ISO-8859-13', 'ISO-8859-14', 'ISO-8859-15', 'ISO-8859-16',
            'WINDOWS-1252', 'WINDOWS-1251', 'EUC-JP', 'EUC-TW', 'KOI8-R', 
            'ISO-2022-KR', 'ISO-2022-JP'
        );

        $result = mb_detect_encoding($string, join(',', $enc));

        return $result ? $result : $failover;
    }


    /**
     * Removes non-unicode characters from input.
     *
     * @param mixed $input String or array.
     *
     * @return mixed String or array
     */
    public static function clean($input)
    {
        // handle input of type array
        if (is_array($input)) {
            foreach ($input as $idx => $val) {
                $input[$idx] = self::clean($val);
            }
            return $input;
        }

        if (!is_string($input) || $input == '') {
            return $input;
        }

        // iconv/mbstring are much faster (especially with long strings)
        if (function_exists('mb_convert_encoding')) {
            if (($res = mb_convert_encoding($input, 'UTF-8', 'UTF-8')) !== false) {
                return $res;
            }
        }

        if (function_exists('iconv')) {
            if (($res = @iconv('UTF-8', 'UTF-8//IGNORE', $input)) !== false) {
                return $res;
            }
        }

        $seq    = '';
        $out    = '';
        $regexp = '/^('.
//          '[\x00-\x7F]'.                                  // UTF8-1
            '|[\xC2-\xDF][\x80-\xBF]'.                      // UTF8-2
            '|\xE0[\xA0-\xBF][\x80-\xBF]'.                  // UTF8-3
            '|[\xE1-\xEC][\x80-\xBF][\x80-\xBF]'.           // UTF8-3
            '|\xED[\x80-\x9F][\x80-\xBF]'.                  // UTF8-3
            '|[\xEE-\xEF][\x80-\xBF][\x80-\xBF]'.           // UTF8-3
            '|\xF0[\x90-\xBF][\x80-\xBF][\x80-\xBF]'.       // UTF8-4
            '|[\xF1-\xF3][\x80-\xBF][\x80-\xBF][\x80-\xBF]'.// UTF8-4
            '|\xF4[\x80-\x8F][\x80-\xBF][\x80-\xBF]'.       // UTF8-4
            ')$/';

        for ($i = 0, $len = strlen($input); $i < $len; $i++) {
            $chr = $input[$i];
            $ord = ord($chr);

            // 1-byte character
            if ($ord <= 0x7F) {
                if ($seq) {
                    $out .= preg_match($regexp, $seq) ? $seq : '';
                }
                $seq = '';
                $out .= $chr;
            // first (or second) byte of multibyte sequence
            }
            else if ($ord >= 0xC0) {
                if (strlen($seq) > 1) {
	                $out .= preg_match($regexp, $seq) ? $seq : '';
                    $seq = '';
                }
                else if ($seq && ord($seq) < 0xC0) {
                    $seq = '';
                }
                $seq .= $chr;
            // next byte of multibyte sequence
            }
            else if ($seq) {
                $seq .= $chr;
            }
        }

        if ($seq) {
            $out .= preg_match($regexp, $seq) ? $seq : '';
        }

        return $out;
    }

}