[wp-hackers] is_email

[Brian Dupuis]

John Sinteur wrote:

>
> On Mar 25, 2005, at 18:00, Dougal Campbell wrote:
>
>> And '-' has always been a valid character for domains/hosts and in 
>> usernames for most systems.
>>
>
> To do all of this right, we should validate email addresses according 
> to the RFC 822 grammar.
>
> See http://www.ietf.org/rfc/rfc0822.txt?number=822  for details.
>
> The grammar described in RFC 822 is suprisingly complex. Implementing 
> validation with regular expressions somewhat pushes the limits of what 
> it is sensible to do with regular expressions.
>
> I'm about to paste the full regular expression into this mail below, 
> if your mail reader borks on it, visit 
> http://www.ex-parrot.com/~pdw/Mail-RFC822-Address.html
>
> (?:(?:\r\n)?[ \t])*(?:(?:(?:[^()<>@,;:\\".\[\] 
> \000-\031]+(?:(?:(?:\r\n)?[ \t] 
> )+|\Z|(?=[\["()<>@,;:\\".\[\]]))|"(?:[^\"\r\\]|\\.|(?:(?:\r\n)?[ 
> \t]))*"(?:(?: \r\n)?[ \t])*)(?:\.(?:(?:\r\n)?[ 
> \t])*(?:[^()<>@,;:\\".\[\] \000-\031]+(?:(?:( ?:\r\n)?[ 
> \t])+|\Z|(?=[\["()<>@,;:\\".\[\]]))|"(?:[^\"\r\\]|\\.|(?:(?:\r\n)?[ 
> \t]))*"(?:(?:\r\n)?[ \t])*))*@(?:(?:\r\n)?[ \t])*(?:[^()<>@,;:\\".\[\] 
> \000-\0 31]+(?:(?:(?:\r\n)?[ 
> \t])+|\Z|(?=[\["()<>@,;:\\".\[\]]))|\[([^\[\]\r\\]|\\.)*\ 
> ](?:(?:\r\n)?[ \t])*)(?:\.(?:(?:\r\n)?[ \t])*(?:[^()<>@,;:\\".\[\] 
> \000-\031]+ (?:(?:(?:\r\n)?[ 
> \t])+|\Z|(?=[\["()<>@,;:\\".\[\]]))|\[([^\[\]\r\\]|\\.)*\](?: 
> (?:\r\n)?[ \t])*))*|(?:[^()<>@,;:\\".\[\] \000-\031]+(?:(?:(?:\r\n)?[ 
> \t])+|\Z |(?=[\["()<>@,;:\\".\[\]]))|"(?:[^\"\r\\]|\\.|(?:(?:\r\n)?[ 
> \t]))*"(?:(?:\r\n) ?[ \t])*)*\<(?:(?:\r\n)?[ 
> \t])*(?:@(?:[^()<>@,;:\\".\[\] \000-\031]+(?:(?:(?:\ r\n)?[ 
> \t])+|\Z|(?=[\["()<>@,;:\\".\[\]]))|\[([^\[\]\r\\]|\\.)*\](?:(?:\r\n)?[ 
> \t])*)(?:\.(?:(?:\r\n)?[ \t])*(?:[^()<>@,;:\\".\[\] 
> \000-\031]+(?:(?:(?:\r\n) ?[ 
> \t])+|\Z|(?=[\["()<>@,;:\\".\[\]]))|\[([^\[\]\r\\]|\\.)*\](?:(?:\r\n)?[ 
> \t] )*))*(?:,@(?:(?:\r\n)?[ \t])*(?:[^()<>@,;:\\".\[\] 
> \000-\031]+(?:(?:(?:\r\n)?[ 
> \t])+|\Z|(?=[\["()<>@,;:\\".\[\]]))|\[([^\[\]\r\\]|\\.)*\](?:(?:\r\n)?[ 
> \t])* )(?:\.(?:(?:\r\n)?[ \t])*(?:[^()<>@,;:\\".\[\] 
> \000-\031]+(?:(?:(?:\r\n)?[ \t] 
> )+|\Z|(?=[\["()<>@,;:\\".\[\]]))|\[([^\[\]\r\\]|\\.)*\](?:(?:\r\n)?[ 
> \t])*))*) *:(?:(?:\r\n)?[ \t])*)?(?:[^()<>@,;:\\".\[\] 
> \000-\031]+(?:(?:(?:\r\n)?[ \t])+ 
> |\Z|(?=[\["()<>@,;:\\".\[\]]))|"(?:[^\"\r\\]|\\.|(?:(?:\r\n)?[ 
> \t]))*"(?:(?:\r \n)?[ \t])*)(?:\.(?:(?:\r\n)?[ 
> \t])*(?:[^()<>@,;:\\".\[\] \000-\031]+(?:(?:(?: \r\n)?[ 
> \t])+|\Z|(?=[\["()<>@,;:\\".\[\]]))|"(?:[^\"\r\\]|\\.|(?:(?:\r\n)?[ \t 
> ]))*"(?:(?:\r\n)?[ \t])*))*@(?:(?:\r\n)?[ \t])*(?:[^()<>@,;:\\".\[\] 
> \000-\031 ]+(?:(?:(?:\r\n)?[ 
> \t])+|\Z|(?=[\["()<>@,;:\\".\[\]]))|\[([^\[\]\r\\]|\\.)*\]( 
> ?:(?:\r\n)?[ \t])*)(?:\.(?:(?:\r\n)?[ \t])*(?:[^()<>@,;:\\".\[\] 
> \000-\031]+(? :(?:(?:\r\n)?[ 
> \t])+|\Z|(?=[\["()<>@,;:\\".\[\]]))|\[([^\[\]\r\\]|\\.)*\](?:(? 
> :\r\n)?[ \t])*))*\>(?:(?:\r\n)?[ \t])*)|(?:[^()<>@,;:\\".\[\] 
> \000-\031]+(?:(? :(?:\r\n)?[ 
> \t])+|\Z|(?=[\["()<>@,;:\\".\[\]]))|"(?:[^\"\r\\]|\\.|(?:(?:\r\n)? [ 
> \t]))*"(?:(?:\r\n)?[ \t])*)*:(?:(?:\r\n)?[ 
> \t])*(?:(?:(?:[^()<>@,;:\\".\[\] \000-\031]+(?:(?:(?:\r\n)?[ 
> \t])+|\Z|(?=[\["()<>@,;:\\".\[\]]))|"(?:[^\"\r\\]| \\.|(?:(?:\r\n)?[ 
> \t]))*"(?:(?:\r\n)?[ \t])*)(?:\.(?:(?:\r\n)?[ \t])*(?:[^()<> 
> @,;:\\".\[\] \000-\031]+(?:(?:(?:\r\n)?[ 
> \t])+|\Z|(?=[\["()<>@,;:\\".\[\]]))|" (?:[^\"\r\\]|\\.|(?:(?:\r\n)?[ 
> \t]))*"(?:(?:\r\n)?[ \t])*))*@(?:(?:\r\n)?[ \t] 
> )*(?:[^()<>@,;:\\".\[\] \000-\031]+(?:(?:(?:\r\n)?[ 
> \t])+|\Z|(?=[\["()<>@,;:\\ 
> ".\[\]]))|\[([^\[\]\r\\]|\\.)*\](?:(?:\r\n)?[ \t])*)(?:\.(?:(?:\r\n)?[ 
> \t])*(? :[^()<>@,;:\\".\[\] \000-\031]+(?:(?:(?:\r\n)?[ 
> \t])+|\Z|(?=[\["()<>@,;:\\".\[ 
> \]]))|\[([^\[\]\r\\]|\\.)*\](?:(?:\r\n)?[ 
> \t])*))*|(?:[^()<>@,;:\\".\[\] \000- \031]+(?:(?:(?:\r\n)?[ 
> \t])+|\Z|(?=[\["()<>@,;:\\".\[\]]))|"(?:[^\"\r\\]|\\.|( ?:(?:\r\n)?[ 
> \t]))*"(?:(?:\r\n)?[ \t])*)*\<(?:(?:\r\n)?[ \t])*(?:@(?:[^()<>@,; 
> :\\".\[\] \000-\031]+(?:(?:(?:\r\n)?[ 
> \t])+|\Z|(?=[\["()<>@,;:\\".\[\]]))|\[([ 
> ^\[\]\r\\]|\\.)*\](?:(?:\r\n)?[ \t])*)(?:\.(?:(?:\r\n)?[ 
> \t])*(?:[^()<>@,;:\\" .\[\] \000-\031]+(?:(?:(?:\r\n)?[ 
> \t])+|\Z|(?=[\["()<>@,;:\\".\[\]]))|\[([^\[\ 
> ]\r\\]|\\.)*\](?:(?:\r\n)?[ \t])*))*(?:,@(?:(?:\r\n)?[ 
> \t])*(?:[^()<>@,;:\\".\ [\] \000-\031]+(?:(?:(?:\r\n)?[ 
> \t])+|\Z|(?=[\["()<>@,;:\\".\[\]]))|\[([^\[\]\ 
> r\\]|\\.)*\](?:(?:\r\n)?[ \t])*)(?:\.(?:(?:\r\n)?[ 
> \t])*(?:[^()<>@,;:\\".\[\] \000-\031]+(?:(?:(?:\r\n)?[ 
> \t])+|\Z|(?=[\["()<>@,;:\\".\[\]]))|\[([^\[\]\r\\] 
> |\\.)*\](?:(?:\r\n)?[ \t])*))*)*:(?:(?:\r\n)?[ 
> \t])*)?(?:[^()<>@,;:\\".\[\] \0 00-\031]+(?:(?:(?:\r\n)?[ 
> \t])+|\Z|(?=[\["()<>@,;:\\".\[\]]))|"(?:[^\"\r\\]|\\ .|(?:(?:\r\n)?[ 
> \t]))*"(?:(?:\r\n)?[ \t])*)(?:\.(?:(?:\r\n)?[ \t])*(?:[^()<>@, 
> ;:\\".\[\] \000-\031]+(?:(?:(?:\r\n)?[ 
> \t])+|\Z|(?=[\["()<>@,;:\\".\[\]]))|"(? :[^\"\r\\]|\\.|(?:(?:\r\n)?[ 
> \t]))*"(?:(?:\r\n)?[ \t])*))*@(?:(?:\r\n)?[ \t])* 
> (?:[^()<>@,;:\\".\[\] \000-\031]+(?:(?:(?:\r\n)?[ 
> \t])+|\Z|(?=[\["()<>@,;:\\". 
> \[\]]))|\[([^\[\]\r\\]|\\.)*\](?:(?:\r\n)?[ \t])*)(?:\.(?:(?:\r\n)?[ 
> \t])*(?:[ ^()<>@,;:\\".\[\] \000-\031]+(?:(?:(?:\r\n)?[ 
> \t])+|\Z|(?=[\["()<>@,;:\\".\[\] 
> ]))|\[([^\[\]\r\\]|\\.)*\](?:(?:\r\n)?[ \t])*))*\>(?:(?:\r\n)?[ 
> \t])*)(?:,\s*( ?:(?:[^()<>@,;:\\".\[\] \000-\031]+(?:(?:(?:\r\n)?[ 
> \t])+|\Z|(?=[\["()<>@,;:\\ ".\[\]]))|"(?:[^\"\r\\]|\\.|(?:(?:\r\n)?[ 
> \t]))*"(?:(?:\r\n)?[ \t])*)(?:\.(?:( ?:\r\n)?[ 
> \t])*(?:[^()<>@,;:\\".\[\] \000-\031]+(?:(?:(?:\r\n)?[ \t])+|\Z|(?=[ 
> \["()<>@,;:\\".\[\]]))|"(?:[^\"\r\\]|\\.|(?:(?:\r\n)?[ 
> \t]))*"(?:(?:\r\n)?[ \t ])*))*@(?:(?:\r\n)?[ 
> \t])*(?:[^()<>@,;:\\".\[\] \000-\031]+(?:(?:(?:\r\n)?[ \t 
> ])+|\Z|(?=[\["()<>@,;:\\".\[\]]))|\[([^\[\]\r\\]|\\.)*\](?:(?:\r\n)?[ 
> \t])*)(? :\.(?:(?:\r\n)?[ \t])*(?:[^()<>@,;:\\".\[\] 
> \000-\031]+(?:(?:(?:\r\n)?[ \t])+| 
> \Z|(?=[\["()<>@,;:\\".\[\]]))|\[([^\[\]\r\\]|\\.)*\](?:(?:\r\n)?[ 
> \t])*))*|(?: [^()<>@,;:\\".\[\] \000-\031]+(?:(?:(?:\r\n)?[ 
> \t])+|\Z|(?=[\["()<>@,;:\\".\[\ ]]))|"(?:[^\"\r\\]|\\.|(?:(?:\r\n)?[ 
> \t]))*"(?:(?:\r\n)?[ \t])*)*\<(?:(?:\r\n) ?[ 
> \t])*(?:@(?:[^()<>@,;:\\".\[\] \000-\031]+(?:(?:(?:\r\n)?[ 
> \t])+|\Z|(?=[\[" 
> ()<>@,;:\\".\[\]]))|\[([^\[\]\r\\]|\\.)*\](?:(?:\r\n)?[ 
> \t])*)(?:\.(?:(?:\r\n) ?[ \t])*(?:[^()<>@,;:\\".\[\] 
> \000-\031]+(?:(?:(?:\r\n)?[ \t])+|\Z|(?=[\["()<> 
> @,;:\\".\[\]]))|\[([^\[\]\r\\]|\\.)*\](?:(?:\r\n)?[ 
> \t])*))*(?:,@(?:(?:\r\n)?[ \t])*(?:[^()<>@,;:\\".\[\] 
> \000-\031]+(?:(?:(?:\r\n)?[ \t])+|\Z|(?=[\["()<>@, 
> ;:\\".\[\]]))|\[([^\[\]\r\\]|\\.)*\](?:(?:\r\n)?[ 
> \t])*)(?:\.(?:(?:\r\n)?[ \t] )*(?:[^()<>@,;:\\".\[\] 
> \000-\031]+(?:(?:(?:\r\n)?[ \t])+|\Z|(?=[\["()<>@,;:\\ 
> ".\[\]]))|\[([^\[\]\r\\]|\\.)*\](?:(?:\r\n)?[ \t])*))*)*:(?:(?:\r\n)?[ 
> \t])*)? (?:[^()<>@,;:\\".\[\] \000-\031]+(?:(?:(?:\r\n)?[ 
> \t])+|\Z|(?=[\["()<>@,;:\\". \[\]]))|"(?:[^\"\r\\]|\\.|(?:(?:\r\n)?[ 
> \t]))*"(?:(?:\r\n)?[ \t])*)(?:\.(?:(?: \r\n)?[ 
> \t])*(?:[^()<>@,;:\\".\[\] \000-\031]+(?:(?:(?:\r\n)?[ \t])+|\Z|(?=[\[ 
> "()<>@,;:\\".\[\]]))|"(?:[^\"\r\\]|\\.|(?:(?:\r\n)?[ 
> \t]))*"(?:(?:\r\n)?[ \t]) *))*@(?:(?:\r\n)?[ 
> \t])*(?:[^()<>@,;:\\".\[\] \000-\031]+(?:(?:(?:\r\n)?[ \t]) 
> +|\Z|(?=[\["()<>@,;:\\".\[\]]))|\[([^\[\]\r\\]|\\.)*\](?:(?:\r\n)?[ 
> \t])*)(?:\ .(?:(?:\r\n)?[ \t])*(?:[^()<>@,;:\\".\[\] 
> \000-\031]+(?:(?:(?:\r\n)?[ \t])+|\Z 
> |(?=[\["()<>@,;:\\".\[\]]))|\[([^\[\]\r\\]|\\.)*\](?:(?:\r\n)?[ 
> \t])*))*\>(?:( ?:\r\n)?[ \t])*))*)?;\s*)

Wow. At that point I think I'd just do a "if( strpos( $email, "@" ) )" 
and call it a day. That's just incredible.