API tools faq
paste
Advertisement
carbonize

Email validation

carbonize
Nov 30th, 2013
103
0
Never
Add comment
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
PHP 12.59 KB | None | 0 0
raw download clone embed print report
  1. <?php
  2.  
  3.     #
  4.     # RFC 822/2822/5322 Email Parser
  5.     #
  6.     # By Cal Henderson <[email protected]>
  7.     #
  8.     # This code is dual licensed:
  9.     # CC Attribution-ShareAlike 2.5 - http://creativecommons.org/licenses/by-sa/2.5/
  10.     # GPLv3 - http://www.gnu.org/copyleft/gpl.html
  11.     #
  12.     # $Revision$
  13.     #
  14.  
  15.     ##################################################################################
  16.  
  17.     function is_valid_email_address($email, $options=array()){
  18.  
  19.         #
  20.         # you can pass a few different named options as a second argument,
  21.         # but the defaults are usually a good choice.
  22.         #
  23.  
  24.         $defaults = array(
  25.             'allow_comments'    => true,
  26.             'public_internet'   => true, # turn this off for 'strict' mode
  27.         );
  28.  
  29.         $opts = array();
  30.         foreach ($defaults as $k => $v) $opts[$k] = isset($options[$k]) ? $options[$k] : $v;
  31.         $options = $opts;
  32.        
  33.  
  34.  
  35.         ####################################################################################
  36.         #
  37.         # NO-WS-CTL       =       %d1-8 /         ; US-ASCII control characters
  38.         #                         %d11 /          ;  that do not include the
  39.         #                         %d12 /          ;  carriage return, line feed,
  40.         #                         %d14-31 /       ;  and white space characters
  41.         #                         %d127
  42.         # ALPHA          =  %x41-5A / %x61-7A   ; A-Z / a-z
  43.         # DIGIT          =  %x30-39
  44.  
  45.         $no_ws_ctl  = "[\\x01-\\x08\\x0b\\x0c\\x0e-\\x1f\\x7f]";
  46.         $alpha      = "[\\x41-\\x5a\\x61-\\x7a]";
  47.         $digit      = "[\\x30-\\x39]";
  48.         $cr     = "\\x0d";
  49.         $lf     = "\\x0a";
  50.         $crlf       = "(?:$cr$lf)";
  51.  
  52.  
  53.         ####################################################################################
  54.         #
  55.         # obs-char        =       %d0-9 / %d11 /          ; %d0-127 except CR and
  56.         #                         %d12 / %d14-127         ;  LF
  57.         # obs-text        =       *LF *CR *(obs-char *LF *CR)
  58.         # text            =       %d1-9 /         ; Characters excluding CR and LF
  59.         #                         %d11 /
  60.         #                         %d12 /
  61.         #                         %d14-127 /
  62.         #                         obs-text
  63.         # obs-qp          =       "\" (%d0-127)
  64.         # quoted-pair     =       ("\" text) / obs-qp
  65.  
  66.         $obs_char   = "[\\x00-\\x09\\x0b\\x0c\\x0e-\\x7f]";
  67.         $obs_text   = "(?:$lf*$cr*(?:$obs_char$lf*$cr*)*)";
  68.         $text       = "(?:[\\x01-\\x09\\x0b\\x0c\\x0e-\\x7f]|$obs_text)";
  69.  
  70.         #
  71.         # there's an issue with the definition of 'text', since 'obs_text' can
  72.         # be blank and that allows qp's with no character after the slash. we're
  73.         # treating that as bad, so this just checks we have at least one
  74.         # (non-CRLF) character
  75.         #
  76.  
  77.         $text       = "(?:$lf*$cr*$obs_char$lf*$cr*)";
  78.         $obs_qp     = "(?:\\x5c[\\x00-\\x7f])";
  79.         $quoted_pair    = "(?:\\x5c$text|$obs_qp)";
  80.  
  81.  
  82.         ####################################################################################
  83.         #
  84.         # obs-FWS         =       1*WSP *(CRLF 1*WSP)
  85.         # FWS             =       ([*WSP CRLF] 1*WSP) /   ; Folding white space
  86.         #                         obs-FWS
  87.         # ctext           =       NO-WS-CTL /     ; Non white space controls
  88.         #                         %d33-39 /       ; The rest of the US-ASCII
  89.         #                         %d42-91 /       ;  characters not including "(",
  90.         #                         %d93-126        ;  ")", or "\"
  91.         # ccontent        =       ctext / quoted-pair / comment
  92.         # comment         =       "(" *([FWS] ccontent) [FWS] ")"
  93.         # CFWS            =       *([FWS] comment) (([FWS] comment) / FWS)
  94.  
  95.         #
  96.         # note: we translate ccontent only partially to avoid an infinite loop
  97.         # instead, we'll recursively strip *nested* comments before processing
  98.         # the input. that will leave 'plain old comments' to be matched during
  99.         # the main parse.
  100.         #
  101.  
  102.         $wsp        = "[\\x20\\x09]";
  103.         $obs_fws    = "(?:$wsp+(?:$crlf$wsp+)*)";
  104.         $fws        = "(?:(?:(?:$wsp*$crlf)?$wsp+)|$obs_fws)";
  105.         $ctext      = "(?:$no_ws_ctl|[\\x21-\\x27\\x2A-\\x5b\\x5d-\\x7e])";
  106.         $ccontent   = "(?:$ctext|$quoted_pair)";
  107.         $comment    = "(?:\\x28(?:$fws?$ccontent)*$fws?\\x29)";
  108.         $cfws       = "(?:(?:$fws?$comment)*(?:$fws?$comment|$fws))";
  109.  
  110.  
  111.         #
  112.         # these are the rules for removing *nested* comments. we'll just detect
  113.         # outer comment and replace it with an empty comment, and recurse until
  114.         # we stop.
  115.         #
  116.  
  117.         $outer_ccontent_dull    = "(?:$fws?$ctext|$quoted_pair)";
  118.         $outer_ccontent_nest    = "(?:$fws?$comment)";
  119.         $outer_comment      = "(?:\\x28$outer_ccontent_dull*(?:$outer_ccontent_nest$outer_ccontent_dull*)+$fws?\\x29)";
  120.  
  121.  
  122.         ####################################################################################
  123.         #
  124.         # atext           =       ALPHA / DIGIT / ; Any character except controls,
  125.         #                         "!" / "#" /     ;  SP, and specials.
  126.         #                         "$" / "%" /     ;  Used for atoms
  127.         #                         "&" / "'" /
  128.         #                         "*" / "+" /
  129.         #                         "-" / "/" /
  130.         #                         "=" / "?" /
  131.         #                         "^" / "_" /
  132.         #                         "`" / "{" /
  133.         #                         "|" / "}" /
  134.         #                         "~"
  135.         # atom            =       [CFWS] 1*atext [CFWS]
  136.  
  137.         $atext      = "(?:$alpha|$digit|[\\x21\\x23-\\x27\\x2a\\x2b\\x2d\\x2f\\x3d\\x3f\\x5e\\x5f\\x60\\x7b-\\x7e])";
  138.         $atom       = "(?:$cfws?(?:$atext)+$cfws?)";
  139.  
  140.  
  141.         ####################################################################################
  142.         #
  143.         # qtext           =       NO-WS-CTL /     ; Non white space controls
  144.         #                         %d33 /          ; The rest of the US-ASCII
  145.         #                         %d35-91 /       ;  characters not including "\"
  146.         #                         %d93-126        ;  or the quote character
  147.         # qcontent        =       qtext / quoted-pair
  148.         # quoted-string   =       [CFWS]
  149.         #                         DQUOTE *([FWS] qcontent) [FWS] DQUOTE
  150.         #                         [CFWS]
  151.         # word            =       atom / quoted-string
  152.  
  153.         $qtext      = "(?:$no_ws_ctl|[\\x21\\x23-\\x5b\\x5d-\\x7e])";
  154.         $qcontent   = "(?:$qtext|$quoted_pair)";
  155.         $quoted_string  = "(?:$cfws?\\x22(?:$fws?$qcontent)*$fws?\\x22$cfws?)";
  156.  
  157.         #
  158.         # changed the '*' to a '+' to require that quoted strings are not empty
  159.         #
  160.  
  161.         $quoted_string  = "(?:$cfws?\\x22(?:$fws?$qcontent)+$fws?\\x22$cfws?)";
  162.         $word       = "(?:$atom|$quoted_string)";
  163.  
  164.  
  165.         ####################################################################################
  166.         #
  167.         # obs-local-part  =       word *("." word)
  168.         # obs-domain      =       atom *("." atom)
  169.  
  170.         $obs_local_part = "(?:$word(?:\\x2e$word)*)";
  171.         $obs_domain = "(?:$atom(?:\\x2e$atom)*)";
  172.  
  173.  
  174.         ####################################################################################
  175.         #
  176.         # dot-atom-text   =       1*atext *("." 1*atext)
  177.         # dot-atom        =       [CFWS] dot-atom-text [CFWS]
  178.  
  179.         $dot_atom_text  = "(?:$atext+(?:\\x2e$atext+)*)";
  180.         $dot_atom   = "(?:$cfws?$dot_atom_text$cfws?)";
  181.  
  182.  
  183.         ####################################################################################
  184.         #
  185.         # domain-literal  =       [CFWS] "[" *([FWS] dcontent) [FWS] "]" [CFWS]
  186.         # dcontent        =       dtext / quoted-pair
  187.         # dtext           =       NO-WS-CTL /     ; Non white space controls
  188.         #
  189.         #                         %d33-90 /       ; The rest of the US-ASCII
  190.         #                         %d94-126        ;  characters not including "[",
  191.         #                                         ;  "]", or "\"
  192.  
  193.         $dtext      = "(?:$no_ws_ctl|[\\x21-\\x5a\\x5e-\\x7e])";
  194.         $dcontent   = "(?:$dtext|$quoted_pair)";
  195.         $domain_literal = "(?:$cfws?\\x5b(?:$fws?$dcontent)*$fws?\\x5d$cfws?)";
  196.  
  197.  
  198.         ####################################################################################
  199.         #
  200.         # local-part      =       dot-atom / quoted-string / obs-local-part
  201.         # domain          =       dot-atom / domain-literal / obs-domain
  202.         # addr-spec       =       local-part "@" domain
  203.  
  204.         $local_part = "(($dot_atom)|($quoted_string)|($obs_local_part))";
  205.         $domain     = "(($dot_atom)|($domain_literal)|($obs_domain))";
  206.         $addr_spec  = "$local_part\\x40$domain";
  207.  
  208.  
  209.  
  210.         #
  211.         # this was previously 256 based on RFC3696, but dominic's errata was accepted.
  212.         #
  213.  
  214.         if (strlen($email) > 254) return 0;
  215.  
  216.  
  217.         #
  218.         # we need to strip nested comments first - we replace them with a simple comment
  219.         #
  220.  
  221.         if ($options['allow_comments']){
  222.  
  223.             $email = email_strip_comments($outer_comment, $email, "(x)");
  224.         }
  225.  
  226.  
  227.         #
  228.         # now match what's left
  229.         #
  230.  
  231.         if (!preg_match("!^$addr_spec$!", $email, $m)){
  232.  
  233.             return 0;
  234.         }
  235.  
  236.         $bits = array(
  237.             'local'         => isset($m[1]) ? $m[1] : '',
  238.             'local-atom'        => isset($m[2]) ? $m[2] : '',
  239.             'local-quoted'      => isset($m[3]) ? $m[3] : '',
  240.             'local-obs'     => isset($m[4]) ? $m[4] : '',
  241.             'domain'        => isset($m[5]) ? $m[5] : '',
  242.             'domain-atom'       => isset($m[6]) ? $m[6] : '',
  243.             'domain-literal'    => isset($m[7]) ? $m[7] : '',
  244.             'domain-obs'        => isset($m[8]) ? $m[8] : '',
  245.         );
  246.  
  247.  
  248.         #
  249.         # we need to now strip comments from $bits[local] and $bits[domain],
  250.         # since we know they're in the right place and we want them out of the
  251.         # way for checking IPs, label sizes, etc
  252.         #
  253.  
  254.         if ($options['allow_comments']){
  255.             $bits['local']  = email_strip_comments($comment, $bits['local']);
  256.             $bits['domain'] = email_strip_comments($comment, $bits['domain']);
  257.         }
  258.  
  259.  
  260.         #
  261.         # length limits on segments
  262.         #
  263.  
  264.         if (strlen($bits['local']) > 64) return 0;
  265.         if (strlen($bits['domain']) > 255) return 0;
  266.  
  267.  
  268.         #
  269.         # restrictions on domain-literals from RFC2821 section 4.1.3
  270.         #
  271.         # RFC4291 changed the meaning of :: in IPv6 addresses - i can mean one or
  272.         # more zero groups (updated from 2 or more).
  273.         #
  274.  
  275.         if (strlen($bits['domain-literal'])){
  276.  
  277.             $Snum           = "(\d{1,3})";
  278.             $IPv4_address_literal   = "$Snum\.$Snum\.$Snum\.$Snum";
  279.  
  280.             $IPv6_hex       = "(?:[0-9a-fA-F]{1,4})";
  281.  
  282.             $IPv6_full      = "IPv6\:$IPv6_hex(?:\:$IPv6_hex){7}";
  283.  
  284.             $IPv6_comp_part     = "(?:$IPv6_hex(?:\:$IPv6_hex){0,7})?";
  285.             $IPv6_comp      = "IPv6\:($IPv6_comp_part\:\:$IPv6_comp_part)";
  286.  
  287.             $IPv6v4_full        = "IPv6\:$IPv6_hex(?:\:$IPv6_hex){5}\:$IPv4_address_literal";
  288.  
  289.             $IPv6v4_comp_part   = "$IPv6_hex(?:\:$IPv6_hex){0,5}";
  290.             $IPv6v4_comp        = "IPv6\:((?:$IPv6v4_comp_part)?\:\:(?:$IPv6v4_comp_part\:)?)$IPv4_address_literal";
  291.  
  292.  
  293.             #
  294.             # IPv4 is simple
  295.             #
  296.  
  297.             if (preg_match("!^\[$IPv4_address_literal\]$!", $bits['domain'], $m)){
  298.  
  299.                 if (intval($m[1]) > 255) return 0;
  300.                 if (intval($m[2]) > 255) return 0;
  301.                 if (intval($m[3]) > 255) return 0;
  302.                 if (intval($m[4]) > 255) return 0;
  303.  
  304.             }else{
  305.  
  306.                 #
  307.                 # this should be IPv6 - a bunch of tests are needed here :)
  308.                 #
  309.  
  310.                 while (1){
  311.  
  312.                     if (preg_match("!^\[$IPv6_full\]$!", $bits['domain'])){
  313.                         break;
  314.                     }
  315.  
  316.                     if (preg_match("!^\[$IPv6_comp\]$!", $bits['domain'], $m)){
  317.                         list($a, $b) = explode('::', $m[1]);
  318.                         $folded = (strlen($a) && strlen($b)) ? "$a:$b" : "$a$b";
  319.                         $groups = explode(':', $folded);
  320.                         if (count($groups) > 7) return 0;
  321.                         break;
  322.                     }
  323.  
  324.                     if (preg_match("!^\[$IPv6v4_full\]$!", $bits['domain'], $m)){
  325.  
  326.                         if (intval($m[1]) > 255) return 0;
  327.                         if (intval($m[2]) > 255) return 0;
  328.                         if (intval($m[3]) > 255) return 0;
  329.                         if (intval($m[4]) > 255) return 0;
  330.                         break;
  331.                     }
  332.  
  333.                     if (preg_match("!^\[$IPv6v4_comp\]$!", $bits['domain'], $m)){
  334.                         list($a, $b) = explode('::', $m[1]);
  335.                         $b = substr($b, 0, -1); # remove the trailing colon before the IPv4 address
  336.                         $folded = (strlen($a) && strlen($b)) ? "$a:$b" : "$a$b";
  337.                         $groups = explode(':', $folded);
  338.                         if (count($groups) > 5) return 0;
  339.                         break;
  340.                     }
  341.  
  342.                     return 0;
  343.                 }
  344.             }          
  345.         }else{
  346.  
  347.             #
  348.             # the domain is either dot-atom or obs-domain - either way, it's
  349.             # made up of simple labels and we split on dots
  350.             #
  351.  
  352.             $labels = explode('.', $bits['domain']);
  353.  
  354.  
  355.             #
  356.             # this is allowed by both dot-atom and obs-domain, but is un-routeable on the
  357.             # public internet, so we'll fail it (e.g. user@localhost)
  358.             #
  359.  
  360.             if ($options['public_internet']){
  361.                 if (count($labels) == 1) return 0;
  362.             }
  363.  
  364.  
  365.             #
  366.             # checks on each label
  367.             #
  368.  
  369.             foreach ($labels as $label){
  370.  
  371.                 if (strlen($label) > 63) return 0;
  372.                 if (substr($label, 0, 1) == '-') return 0;
  373.                 if (substr($label, -1) == '-') return 0;
  374.             }
  375.  
  376.  
  377.             #
  378.             # last label can't be all numeric
  379.             #
  380.  
  381.             if ($options['public_internet']){
  382.                 if (preg_match('!^[0-9]+$!', array_pop($labels))) return 0;
  383.             }
  384.         }
  385.  
  386.  
  387.         return 1;
  388.     }
  389.  
  390.     ##################################################################################
  391.  
  392.     function email_strip_comments($comment, $email, $replace=''){
  393.  
  394.         while (1){
  395.             $new = preg_replace("!$comment!", $replace, $email);
  396.             if (strlen($new) == strlen($email)){
  397.                 return $email;
  398.             }
  399.             $email = $new;
  400.         }
  401.     }
  402.  
  403.     ##################################################################################
  404. ?>
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement
Public Pastes
Advertisement
We use cookies for various purposes including analytics. By continuing to use Pastebin, you agree to our use of cookies as described in the Cookies Policy.  OK, I Understand
Not a member of Pastebin yet?
Sign Up, it unlocks many cool features!