1<?php
2/**
3 * RFC 822 Email address list validation Utility
4 *
5 * PHP version 5
6 *
7 * LICENSE:
8 *
9 * Copyright (c) 2001-2017, Chuck Hagenbuch & Richard Heyes
10 * All rights reserved.
11 *
12 * Redistribution and use in source and binary forms, with or without
13 * modification, are permitted provided that the following conditions
14 * are met:
15 *
16 * 1. Redistributions of source code must retain the above copyright
17 *   notice, this list of conditions and the following disclaimer.
18 *
19 * 2. Redistributions in binary form must reproduce the above copyright
20 *   notice, this list of conditions and the following disclaimer in the
21 *   documentation and/or other materials provided with the distribution.
22 *
23 * 3. Neither the name of the copyright holder nor the names of its
24 *    contributors may be used to endorse or promote products derived from
25 *    this software without specific prior written permission.
26 *
27 * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
28 * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
29 * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
30 * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
31 * HOLDER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
32 * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
33 * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
34 * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
35 * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
36 * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
37 * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
38 *
39 * @category    Mail
40 * @package     Mail
41 * @author      Richard Heyes <richard@phpguru.org>
42 * @author      Chuck Hagenbuch <chuck@horde.org
43 * @copyright   2001-2017 Richard Heyes
44 * @license     http://opensource.org/licenses/BSD-3-Clause New BSD License
45 * @version     CVS: $Id$
46 * @link        http://pear.php.net/package/Mail/
47 */
48
49/**
50 * RFC 822 Email address list validation Utility
51 *
52 * What is it?
53 *
54 * This class will take an address string, and parse it into it's consituent
55 * parts, be that either addresses, groups, or combinations. Nested groups
56 * are not supported. The structure it returns is pretty straight forward,
57 * and is similar to that provided by the imap_rfc822_parse_adrlist(). Use
58 * print_r() to view the structure.
59 *
60 * How do I use it?
61 *
62 * $address_string = 'My Group: "Richard" <richard@localhost> (A comment), ted@example.com (Ted Bloggs), Barney;';
63 * $structure = Mail_RFC822::parseAddressList($address_string, 'example.com', true)
64 * print_r($structure);
65 *
66 * @author  Richard Heyes <richard@phpguru.org>
67 * @author  Chuck Hagenbuch <chuck@horde.org>
68 * @version $Revision$
69 * @license BSD
70 * @package Mail
71 */
72class Mail_RFC822
73{
74
75    /**
76     * The address being parsed by the RFC822 object.
77     * @var string $address
78     */
79    public $address = '';
80
81    /**
82     * The default domain to use for unqualified addresses.
83     * @var string $default_domain
84     */
85    public $default_domain = 'localhost';
86
87    /**
88     * Should we return a nested array showing groups, or flatten everything?
89     * @var boolean $nestGroups
90     */
91    public $nestGroups = true;
92
93    /**
94     * Whether or not to validate atoms for non-ascii characters.
95     * @var boolean $validate
96     */
97    public $validate = true;
98
99    /**
100     * The array of raw addresses built up as we parse.
101     * @var array $addresses
102     */
103    public $addresses = array();
104
105    /**
106     * The final array of parsed address information that we build up.
107     * @var array $structure
108     */
109    public $structure = array();
110
111    /**
112     * The current error message, if any.
113     * @var string $error
114     */
115    public $error = null;
116
117    /**
118     * An internal counter/pointer.
119     * @var integer $index
120     */
121    public $index = null;
122
123    /**
124     * The number of groups that have been found in the address list.
125     * @var integer $num_groups
126     * @access public
127     */
128    public $num_groups = 0;
129
130    /**
131     * A variable so that we can tell whether or not we're inside a
132     * Mail_RFC822 object.
133     * @var boolean $mailRFC822
134     */
135    public $mailRFC822 = true;
136
137    /**
138    * A limit after which processing stops
139    * @var int $limit
140    */
141    public $limit = null;
142
143    /**
144     * Sets up the object. The address must either be set here or when
145     * calling parseAddressList(). One or the other.
146     *
147     * @param string  $address         The address(es) to validate.
148     * @param string  $default_domain  Default domain/host etc. If not supplied, will be set to localhost.
149     * @param boolean $nest_groups     Whether to return the structure with groups nested for easier viewing.
150     * @param boolean $validate        Whether to validate atoms. Turn this off if you need to run addresses through before encoding the personal names, for instance.
151     *
152     * @return object Mail_RFC822 A new Mail_RFC822 object.
153     */
154    public function __construct($address = null, $default_domain = null, $nest_groups = null, $validate = null, $limit = null)
155    {
156        if (isset($address)) {
157            $this->address = $address;
158        }
159        if (isset($default_domain)) {
160            $this->default_domain = $default_domain;
161        }
162        if (isset($nest_groups)) {
163            $this->nestGroups = $nest_groups;
164        }
165        if (isset($validate)) {
166            $this->validate = $validate;
167        }
168        if (isset($limit)) {
169            $this->limit = $limit;
170        }
171    }
172
173    /**
174     * Starts the whole process. The address must either be set here
175     * or when creating the object. One or the other.
176     *
177     * @param string  $address         The address(es) to validate.
178     * @param string  $default_domain  Default domain/host etc.
179     * @param boolean $nest_groups     Whether to return the structure with groups nested for easier viewing.
180     * @param boolean $validate        Whether to validate atoms. Turn this off if you need to run addresses through before encoding the personal names, for instance.
181     *
182     * @return array A structured array of addresses.
183     */
184    public function parseAddressList($address = null, $default_domain = null, $nest_groups = null, $validate = null, $limit = null)
185    {
186        if (!isset($this) || !isset($this->mailRFC822)) {
187            $obj = new Mail_RFC822($address, $default_domain, $nest_groups, $validate, $limit);
188            return $obj->parseAddressList();
189        }
190
191        if (isset($address)) {
192            $this->address = $address;
193        }
194        if (isset($default_domain)) {
195            $this->default_domain = $default_domain;
196        }
197        if (isset($nest_groups)) {
198            $this->nestGroups = $nest_groups;
199        }
200        if (isset($validate)) {
201            $this->validate = $validate;
202        }
203        if (isset($limit)) {
204            $this->limit = $limit;
205        }
206
207        $this->structure = array();
208        $this->addresses = array();
209        $this->error = null;
210        $this->index = null;
211
212        // Unfold any long lines in $this->address.
213        $this->address = preg_replace('/\r?\n/', "\r\n", $this->address);
214        $this->address = preg_replace('/\r\n(\t| )+/', ' ', $this->address);
215
216        while ($this->address = $this->_splitAddresses($this->address));
217
218        if ($this->address === false || isset($this->error)) {
219            // mjansen patch 14 Ap 2016 start
220            throw new \ilMailException($this->error);
221            // mjansen patch 14 Ap 2016 end
222        }
223
224        // Validate each address individually.  If we encounter an invalid
225        // address, stop iterating and return an error immediately.
226        foreach ($this->addresses as $address) {
227            $valid = $this->_validateAddress($address);
228
229            if ($valid === false || isset($this->error)) {
230                // mjansen patch 14 Ap 2016 start
231                throw new \ilMailException($this->error);
232                // mjansen patch 14 Ap 2016 end
233            }
234
235            if (!$this->nestGroups) {
236                $this->structure = array_merge($this->structure, $valid);
237            } else {
238                $this->structure[] = $valid;
239            }
240        }
241
242        return $this->structure;
243    }
244
245    /**
246     * Splits an address into separate addresses.
247     *
248     * @param string $address The addresses to split.
249     * @return boolean Success or failure.
250     */
251    protected function _splitAddresses($address)
252    {
253        if (!empty($this->limit) && count($this->addresses) == $this->limit) {
254            return '';
255        }
256
257        if ($this->_isGroup($address) && !isset($this->error)) {
258            $split_char = ';';
259            $is_group = true;
260        } elseif (!isset($this->error)) {
261            $split_char = ',';
262            $is_group = false;
263        } elseif (isset($this->error)) {
264            return false;
265        }
266
267        // Split the string based on the above ten or so lines.
268        $parts = explode($split_char, $address);
269        $string = $this->_splitCheck($parts, $split_char);
270
271        // If a group...
272        if ($is_group) {
273            // If $string does not contain a colon outside of
274            // brackets/quotes etc then something's fubar.
275
276            // First check there's a colon at all:
277            if (strpos($string, ':') === false) {
278                $this->error = 'Invalid address: ' . $string;
279                return false;
280            }
281
282            // Now check it's outside of brackets/quotes:
283            if (!$this->_splitCheck(explode(':', $string), ':')) {
284                return false;
285            }
286
287            // We must have a group at this point, so increase the counter:
288            $this->num_groups++;
289        }
290
291        // $string now contains the first full address/group.
292        // Add to the addresses array.
293        $this->addresses[] = array(
294                                   'address' => trim($string),
295                                   'group' => $is_group
296                                   );
297
298        // Remove the now stored address from the initial line, the +1
299        // is to account for the explode character.
300        $address = trim(substr($address, strlen($string) + 1));
301
302        // If the next char is a comma and this was a group, then
303        // there are more addresses, otherwise, if there are any more
304        // chars, then there is another address.
305        if ($is_group && substr($address, 0, 1) == ',') {
306            $address = trim(substr($address, 1));
307            return $address;
308        } elseif (strlen($address) > 0) {
309            return $address;
310        } else {
311            return '';
312        }
313
314        // If you got here then something's off
315        return false;
316    }
317
318    /**
319     * Checks for a group at the start of the string.
320     *
321     * @param string $address The address to check.
322     * @return boolean Whether or not there is a group at the start of the string.
323     */
324    protected function _isGroup($address)
325    {
326        // First comma not in quotes, angles or escaped:
327        $parts = explode(',', $address);
328        $string = $this->_splitCheck($parts, ',');
329
330        // Now we have the first address, we can reliably check for a
331        // group by searching for a colon that's not escaped or in
332        // quotes or angle brackets.
333        if (count($parts = explode(':', $string)) > 1) {
334            $string2 = $this->_splitCheck($parts, ':');
335            return ($string2 !== $string);
336        } else {
337            return false;
338        }
339    }
340
341    /**
342     * A common function that will check an exploded string.
343     *
344     * @param array $parts The exloded string.
345     * @param string $char  The char that was exploded on.
346     * @return mixed False if the string contains unclosed quotes/brackets, or the string on success.
347     */
348    protected function _splitCheck($parts, $char)
349    {
350        $string = $parts[0];
351
352        for ($i = 0; $i < count($parts); $i++) {
353            if ($this->_hasUnclosedQuotes($string)
354                || $this->_hasUnclosedBrackets($string, '<>')
355                || $this->_hasUnclosedBrackets($string, '[]')
356                || $this->_hasUnclosedBrackets($string, '()')
357                || substr($string, -1) == '\\') {
358                if (isset($parts[$i + 1])) {
359                    $string = $string . $char . $parts[$i + 1];
360                } else {
361                    $this->error = 'Invalid address spec. Unclosed bracket or quotes';
362                    return false;
363                }
364            } else {
365                $this->index = $i;
366                break;
367            }
368        }
369
370        return $string;
371    }
372
373    /**
374     * Checks if a string has unclosed quotes or not.
375     *
376     * @param string $string  The string to check.
377     * @return boolean  True if there are unclosed quotes inside the string,
378     *                  false otherwise.
379     */
380    protected function _hasUnclosedQuotes($string)
381    {
382        $string = trim($string);
383        $iMax = strlen($string);
384        $in_quote = false;
385        $i = $slashes = 0;
386
387        for (; $i < $iMax; ++$i) {
388            switch ($string[$i]) {
389            case '\\':
390                ++$slashes;
391                break;
392
393            case '"':
394                if ($slashes % 2 == 0) {
395                    $in_quote = !$in_quote;
396                }
397                // Fall through to default action below.
398
399                // no break
400            default:
401                $slashes = 0;
402                break;
403            }
404        }
405
406        return $in_quote;
407    }
408
409    /**
410     * Checks if a string has an unclosed brackets or not. IMPORTANT:
411     * This function handles both angle brackets and square brackets;
412     *
413     * @param string $string The string to check.
414     * @param string $chars  The characters to check for.
415     * @return boolean True if there are unclosed brackets inside the string, false otherwise.
416     */
417    protected function _hasUnclosedBrackets($string, $chars)
418    {
419        $num_angle_start = substr_count($string, $chars[0]);
420        $num_angle_end = substr_count($string, $chars[1]);
421
422        $this->_hasUnclosedBracketsSub($string, $num_angle_start, $chars[0]);
423        $this->_hasUnclosedBracketsSub($string, $num_angle_end, $chars[1]);
424
425        if ($num_angle_start < $num_angle_end) {
426            $this->error = 'Invalid address spec. Unmatched quote or bracket (' . $chars . ')';
427            return false;
428        } else {
429            return ($num_angle_start > $num_angle_end);
430        }
431    }
432
433    /**
434     * Sub function that is used only by hasUnclosedBrackets().
435     *
436     * @param string $string The string to check.
437     * @param integer &$num    The number of occurences.
438     * @param string $char   The character to count.
439     * @return integer The number of occurences of $char in $string, adjusted for backslashes.
440     */
441    protected function _hasUnclosedBracketsSub($string, &$num, $char)
442    {
443        $parts = explode($char, $string);
444        for ($i = 0; $i < count($parts); $i++) {
445            if (substr($parts[$i], -1) == '\\' || $this->_hasUnclosedQuotes($parts[$i])) {
446                $num--;
447            }
448            if (isset($parts[$i + 1])) {
449                $parts[$i + 1] = $parts[$i] . $char . $parts[$i + 1];
450            }
451        }
452
453        return $num;
454    }
455
456    /**
457     * Function to begin checking the address.
458     *
459     * @param string $address The address to validate.
460     * @return mixed False on failure, or a structured array of address information on success.
461     */
462    protected function _validateAddress($address)
463    {
464        $is_group = false;
465        $addresses = array();
466
467        if ($address['group']) {
468            $is_group = true;
469
470            // Get the group part of the name
471            $parts = explode(':', $address['address']);
472            $groupname = $this->_splitCheck($parts, ':');
473            $structure = array();
474
475            // And validate the group part of the name.
476            if (!$this->_validatePhrase($groupname)) {
477                $this->error = 'Group name did not validate.';
478                return false;
479            } else {
480                // Don't include groups if we are not nesting
481                // them. This avoids returning invalid addresses.
482                if ($this->nestGroups) {
483                    $structure = new stdClass;
484                    $structure->groupname = $groupname;
485                }
486            }
487
488            $address['address'] = ltrim(substr($address['address'], strlen($groupname . ':')));
489        }
490
491        // If a group then split on comma and put into an array.
492        // Otherwise, Just put the whole address in an array.
493        if ($is_group) {
494            while (strlen($address['address']) > 0) {
495                $parts = explode(',', $address['address']);
496                $addresses[] = $this->_splitCheck($parts, ',');
497                $address['address'] = trim(substr($address['address'], strlen(end($addresses) . ',')));
498            }
499        } else {
500            $addresses[] = $address['address'];
501        }
502
503        // Trim the whitespace from all of the address strings.
504        array_map('trim', $addresses);
505
506        // Validate each mailbox.
507        // Format could be one of: name <geezer@domain.com>
508        //                         geezer@domain.com
509        //                         geezer
510        // ... or any other format valid by RFC 822.
511        for ($i = 0; $i < count($addresses); $i++) {
512            if (!$this->validateMailbox($addresses[$i])) {
513                if (empty($this->error)) {
514                    $this->error = 'Validation failed for: ' . $addresses[$i];
515                }
516                return false;
517            }
518        }
519
520        // Nested format
521        if ($this->nestGroups) {
522            if ($is_group) {
523                $structure->addresses = $addresses;
524            } else {
525                $structure = $addresses[0];
526            }
527
528            // Flat format
529        } else {
530            if ($is_group) {
531                $structure = array_merge($structure, $addresses);
532            } else {
533                $structure = $addresses;
534            }
535        }
536
537        return $structure;
538    }
539
540    /**
541     * Function to validate a phrase.
542     *
543     * @param string $phrase The phrase to check.
544     * @return boolean Success or failure.
545     */
546    protected function _validatePhrase($phrase)
547    {
548        // Splits on one or more Tab or space.
549        $parts = preg_split('/[ \\x09]+/', $phrase, -1, PREG_SPLIT_NO_EMPTY);
550
551        $phrase_parts = array();
552        while (count($parts) > 0) {
553            $phrase_parts[] = $this->_splitCheck($parts, ' ');
554            for ($i = 0; $i < $this->index + 1; $i++) {
555                array_shift($parts);
556            }
557        }
558
559        foreach ($phrase_parts as $part) {
560            // If quoted string:
561            if (substr($part, 0, 1) == '"') {
562                if (!$this->_validateQuotedString($part)) {
563                    return false;
564                }
565                continue;
566            }
567
568            // Otherwise it's an atom:
569            if (!$this->_validateAtom($part)) {
570                return false;
571            }
572        }
573
574        return true;
575    }
576
577    /**
578     * Function to validate an atom which from rfc822 is:
579     * atom = 1*<any CHAR except specials, SPACE and CTLs>
580     *
581     * If validation ($this->validate) has been turned off, then
582     * validateAtom() doesn't actually check anything. This is so that you
583     * can split a list of addresses up before encoding personal names
584     * (umlauts, etc.), for example.
585     *
586     * @param string $atom The string to check.
587     * @return boolean Success or failure.
588     */
589    protected function _validateAtom($atom)
590    {
591        if (!$this->validate) {
592            // Validation has been turned off; assume the atom is okay.
593            return true;
594        }
595
596        // Check for any char from ASCII 0 - ASCII 127
597        // mjansen patch 16 Sep 2015 start
598        // Check for specials:
599        if (preg_match('/[][()<>@,;\\:". ]/', $atom)) {
600            return false;
601        }
602
603        // Check for control characters (ASCII 0-31):
604        if (preg_match('/[\\x00-\\x1F]+/', $atom)) {
605            return false;
606        }
607        #16291
608        #17618
609        if (!(bool) preg_match('//u', $atom)) {
610            return false;
611        }
612        // mjansen patch 16 Sep 2015 end
613
614        return true;
615    }
616
617    /**
618     * Function to validate quoted string, which is:
619     * quoted-string = <"> *(qtext/quoted-pair) <">
620     *
621     * @param string $qstring The string to check
622     * @return boolean Success or failure.
623     */
624    protected function _validateQuotedString($qstring)
625    {
626        // Leading and trailing "
627        $qstring = substr($qstring, 1, -1);
628
629        // Perform check, removing quoted characters first.
630        return !preg_match('/[\x0D\\\\"]/', preg_replace('/\\\\./', '', $qstring));
631    }
632
633    /**
634     * Function to validate a mailbox, which is:
635     * mailbox =   addr-spec         ; simple address
636     *           / phrase route-addr ; name and route-addr
637     *
638     * @param string &$mailbox The string to check.
639     * @return boolean Success or failure.
640     */
641    public function validateMailbox(&$mailbox)
642    {
643        // A couple of defaults.
644        $phrase = '';
645        $comment = '';
646        $comments = array();
647
648        // Catch any RFC822 comments and store them separately.
649        $_mailbox = $mailbox;
650        while (strlen(trim($_mailbox)) > 0) {
651            $parts = explode('(', $_mailbox);
652            $before_comment = $this->_splitCheck($parts, '(');
653            if ($before_comment != $_mailbox) {
654                // First char should be a (.
655                $comment = substr(str_replace($before_comment, '', $_mailbox), 1);
656                $parts = explode(')', $comment);
657                $comment = $this->_splitCheck($parts, ')');
658                $comments[] = $comment;
659
660                // +2 is for the brackets
661                $_mailbox = substr($_mailbox, strpos($_mailbox, '(' . $comment) + strlen($comment) + 2);
662            } else {
663                break;
664            }
665        }
666
667        foreach ($comments as $comment) {
668            $mailbox = str_replace("($comment)", '', $mailbox);
669        }
670
671        $mailbox = trim($mailbox);
672
673        // Check for name + route-addr
674        if (substr($mailbox, -1) == '>' && substr($mailbox, 0, 1) != '<') {
675            $parts = explode('<', $mailbox);
676            $name = $this->_splitCheck($parts, '<');
677
678            $phrase = trim($name);
679            $route_addr = trim(substr($mailbox, strlen($name . '<'), -1));
680
681            if ($this->_validatePhrase($phrase) === false || ($route_addr = $this->_validateRouteAddr($route_addr)) === false) {
682                return false;
683            }
684
685            // Only got addr-spec
686        } else {
687            // First snip angle brackets if present.
688            if (substr($mailbox, 0, 1) == '<' && substr($mailbox, -1) == '>') {
689                $addr_spec = substr($mailbox, 1, -1);
690            } else {
691                $addr_spec = $mailbox;
692            }
693
694            if (($addr_spec = $this->_validateAddrSpec($addr_spec)) === false) {
695                return false;
696            }
697        }
698
699        // Construct the object that will be returned.
700        $mbox = new stdClass();
701
702        // Add the phrase (even if empty) and comments
703        $mbox->personal = $phrase;
704        $mbox->comment = isset($comments) ? $comments : array();
705
706        if (isset($route_addr)) {
707            $mbox->mailbox = $route_addr['local_part'];
708            $mbox->host = $route_addr['domain'];
709            $route_addr['adl'] !== '' ? $mbox->adl = $route_addr['adl'] : '';
710        } else {
711            $mbox->mailbox = $addr_spec['local_part'];
712            $mbox->host = $addr_spec['domain'];
713        }
714
715        $mailbox = $mbox;
716        return true;
717    }
718
719    /**
720     * This function validates a route-addr which is:
721     * route-addr = "<" [route] addr-spec ">"
722     *
723     * Angle brackets have already been removed at the point of
724     * getting to this function.
725     *
726     * @param string $route_addr The string to check.
727     * @return mixed False on failure, or an array containing validated address/route information on success.
728     */
729    protected function _validateRouteAddr($route_addr)
730    {
731        // Check for colon.
732        if (strpos($route_addr, ':') !== false) {
733            $parts = explode(':', $route_addr);
734            $route = $this->_splitCheck($parts, ':');
735        } else {
736            $route = $route_addr;
737        }
738
739        // If $route is same as $route_addr then the colon was in
740        // quotes or brackets or, of course, non existent.
741        if ($route === $route_addr) {
742            unset($route);
743            $addr_spec = $route_addr;
744            if (($addr_spec = $this->_validateAddrSpec($addr_spec)) === false) {
745                return false;
746            }
747        } else {
748            // Validate route part.
749            if (($route = $this->_validateRoute($route)) === false) {
750                return false;
751            }
752
753            $addr_spec = substr($route_addr, strlen($route . ':'));
754
755            // Validate addr-spec part.
756            if (($addr_spec = $this->_validateAddrSpec($addr_spec)) === false) {
757                return false;
758            }
759        }
760
761        if (isset($route)) {
762            $return['adl'] = $route;
763        } else {
764            $return['adl'] = '';
765        }
766
767        $return = array_merge($return, $addr_spec);
768        return $return;
769    }
770
771    /**
772     * Function to validate a route, which is:
773     * route = 1#("@" domain) ":"
774     *
775     * @param string $route The string to check.
776     * @return mixed False on failure, or the validated $route on success.
777     */
778    protected function _validateRoute($route)
779    {
780        // Split on comma.
781        $domains = explode(',', trim($route));
782
783        foreach ($domains as $domain) {
784            $domain = str_replace('@', '', trim($domain));
785            if (!$this->_validateDomain($domain)) {
786                return false;
787            }
788        }
789
790        return $route;
791    }
792
793    /**
794     * Function to validate a domain, though this is not quite what
795     * you expect of a strict internet domain.
796     *
797     * domain = sub-domain *("." sub-domain)
798     *
799     * @param string $domain The string to check.
800     * @return mixed False on failure, or the validated domain on success.
801     */
802    protected function _validateDomain($domain)
803    {
804        // Note the different use of $subdomains and $sub_domains
805        $subdomains = explode('.', $domain);
806
807        while (count($subdomains) > 0) {
808            $sub_domains[] = $this->_splitCheck($subdomains, '.');
809            for ($i = 0; $i < $this->index + 1; $i++) {
810                array_shift($subdomains);
811            }
812        }
813
814        foreach ($sub_domains as $sub_domain) {
815            if (!$this->_validateSubdomain(trim($sub_domain))) {
816                return false;
817            }
818        }
819
820        // Managed to get here, so return input.
821        return $domain;
822    }
823
824    /**
825     * Function to validate a subdomain:
826     *   subdomain = domain-ref / domain-literal
827     *
828     * @param string $subdomain The string to check.
829     * @return boolean Success or failure.
830     */
831    protected function _validateSubdomain($subdomain)
832    {
833        if (preg_match('|^\[(.*)]$|', $subdomain, $arr)) {
834            if (!$this->_validateDliteral($arr[1])) {
835                return false;
836            }
837        } else {
838            if (!$this->_validateAtom($subdomain)) {
839                return false;
840            }
841        }
842
843        // Got here, so return successful.
844        return true;
845    }
846
847    /**
848     * Function to validate a domain literal:
849     *   domain-literal =  "[" *(dtext / quoted-pair) "]"
850     *
851     * @param string $dliteral The string to check.
852     * @return boolean Success or failure.
853     */
854    protected function _validateDliteral($dliteral)
855    {
856        return !preg_match('/(.)[][\x0D\\\\]/', $dliteral, $matches) && ((!isset($matches[1])) || $matches[1] != '\\');
857    }
858
859    /**
860     * Function to validate an addr-spec.
861     *
862     * addr-spec = local-part "@" domain
863     *
864     * @param string $addr_spec The string to check.
865     * @return mixed False on failure, or the validated addr-spec on success.
866     */
867    protected function _validateAddrSpec($addr_spec)
868    {
869        $addr_spec = trim($addr_spec);
870
871        // mjansen patch 16 Sep 2016 start
872        $validateState = $this->validate;
873        // mjansen patch 16 Sep 2016 end
874        // Split on @ sign if there is one.
875        if (strpos($addr_spec, '@') !== false) {
876            $parts = explode('@', $addr_spec);
877            $local_part = $this->_splitCheck($parts, '@');
878            $domain = substr($addr_spec, strlen($local_part . '@'));
879            // mjansen patch 16 Sep 2016 start
880            if (substr_count($addr_spec, '@') != 1 && $local_part == '') {
881                $this->validate = false;
882                $local_part = $addr_spec;
883                $domain = $this->default_domain;
884            }
885            // mjansen patch 16 Sep 2016 end
886        // No @ sign so assume the default domain.
887        } else {
888            $local_part = $addr_spec;
889            $domain = $this->default_domain;
890        }
891
892        if (($local_part = $this->_validateLocalPart($local_part)) === false) {
893            return false;
894        }
895        // mjansen patch 16 Sep 2016 start
896        if ($validateState != $this->validate) {
897            $this->validate = $validateState;
898        }
899        // mjansen patch 16 Sep 2016 end
900        if (($domain = $this->_validateDomain($domain)) === false) {
901            return false;
902        }
903
904        // Got here so return successful.
905        return array('local_part' => $local_part, 'domain' => $domain);
906    }
907
908    /**
909     * Function to validate the local part of an address:
910     *   local-part = word *("." word)
911     *
912     * @access private
913     * @param string $local_part
914     * @return mixed False on failure, or the validated local part on success.
915     */
916    protected function _validateLocalPart($local_part)
917    {
918        $parts = explode('.', $local_part);
919        $words = array();
920
921        // Split the local_part into words.
922        while (count($parts) > 0) {
923            $words[] = $this->_splitCheck($parts, '.');
924            for ($i = 0; $i < $this->index + 1; $i++) {
925                array_shift($parts);
926            }
927        }
928
929        // Validate each word.
930        foreach ($words as $word) {
931            // iszmais patch 19 May 2020 start
932            // word cannot be empty (#17317)
933            //if ($word === '') {
934            //    return false;
935            //}
936            // iszmais patch 19 May 2020 end
937            // If this word contains an unquoted space, it is invalid. (6.2.4)
938            if (strpos($word, ' ') && $word[0] !== '"') {
939                // mjansen patch 24 Feb 2016 start
940                // Mantis issue #18018
941                // # http://haacked.com/archive/2007/08/21/i-knew-how-to-validate-an-email-address-until-i.aspx/
942                //return false;
943                // mjansen patch 24 Feb 2016 end
944            }
945
946            if ($this->_validatePhrase(trim($word)) === false) {
947                return false;
948            }
949        }
950
951        // Managed to get here, so return the input.
952        return $local_part;
953    }
954
955    /**
956     * Returns an approximate count of how many addresses are in the
957     * given string. This is APPROXIMATE as it only splits based on a
958     * comma which has no preceding backslash. Could be useful as
959     * large amounts of addresses will end up producing *large*
960     * structures when used with parseAddressList().
961     *
962     * @param  string $data Addresses to count
963     * @return int          Approximate count
964     */
965    public function approximateCount($data)
966    {
967        return count(preg_split('/(?<!\\\\),/', $data));
968    }
969
970    /**
971     * This is a email validating function separate to the rest of the
972     * class. It simply validates whether an email is of the common
973     * internet form: <user>@<domain>. This can be sufficient for most
974     * people. Optional stricter mode can be utilised which restricts
975     * mailbox characters allowed to alphanumeric, full stop, hyphen
976     * and underscore.
977     *
978     * @param  string  $data   Address to check
979     * @param  boolean $strict Optional stricter mode
980     * @return mixed           False if it fails, an indexed array
981     *                         username/domain if it matches
982     */
983    public function isValidInetAddress($data, $strict = false)
984    {
985        $regex = $strict ? '/^([.0-9a-z_+-]+)@(([0-9a-z-]+\.)+[0-9a-z]{2,})$/i' : '/^([*+!.&#$|\'\\%\/0-9a-z^_`{}=?~:-]+)@(([0-9a-z-]+\.)+[0-9a-z]{2,})$/i';
986        if (preg_match($regex, trim($data), $matches)) {
987            return array($matches[1], $matches[2]);
988        } else {
989            return false;
990        }
991    }
992}
993