Validating EMailAdresses for syntactical correctness

[Jason Voegele]

Michael.W.Dietrich at modulo3.de (Michael W. Dietrich) wrote in message news:<54da4e24.0201241019.4a4b222e at posting.google.com>...
> Has anyone ever written a class, function or regular expression, that
> validates EMail-Addresses (e.g. such entered in Web Forms) for their
> syntactical correctness? If so, is that algorithm available? Where?
> 
> Any comments on this matter are appreciated.

If you really want to ensure 100% syntactical correctness, here's the
regular expression for matching email addresses, from Jeffrey Friedl's
"Mastering Regular Expressions" book ;-)

    [\040\t]*(?:\([^\\\x80-\xff\n\015()]*(?:(?:\\[^\x80-\xff]|\([^\\\x80-\
    xff\n\015()]*(?:\\[^\x80-\xff][^\\\x80-\xff\n\015()]*)*\))[^\\\x80-\xf
    f\n\015()]*)*\)[\040\t]*)*(?:(?:[^(\040)<>@,;:".\\\[\]\000-\037\x80-\x
    ff]+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff])|"[^\\\x80-\xff\n\015
    "]*(?:\\[^\x80-\xff][^\\\x80-\xff\n\015"]*)*")[\040\t]*(?:\([^\\\x80-\
    xff\n\015()]*(?:(?:\\[^\x80-\xff]|\([^\\\x80-\xff\n\015()]*(?:\\[^\x80
    -\xff][^\\\x80-\xff\n\015()]*)*\))[^\\\x80-\xff\n\015()]*)*\)[\040\t]*
    )*(?:\.[\040\t]*(?:\([^\\\x80-\xff\n\015()]*(?:(?:\\[^\x80-\xff]|\([^\
    \\x80-\xff\n\015()]*(?:\\[^\x80-\xff][^\\\x80-\xff\n\015()]*)*\))[^\\\
    x80-\xff\n\015()]*)*\)[\040\t]*)*(?:[^(\040)<>@,;:".\\\[\]\000-\037\x8
    0-\xff]+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff])|"[^\\\x80-\xff\n
    \015"]*(?:\\[^\x80-\xff][^\\\x80-\xff\n\015"]*)*")[\040\t]*(?:\([^\\\x
    80-\xff\n\015()]*(?:(?:\\[^\x80-\xff]|\([^\\\x80-\xff\n\015()]*(?:\\[^
    \x80-\xff][^\\\x80-\xff\n\015()]*)*\))[^\\\x80-\xff\n\015()]*)*\)[\040
    \t]*)*)*@[\040\t]*(?:\([^\\\x80-\xff\n\015()]*(?:(?:\\[^\x80-\xff]|\([
    ^\\\x80-\xff\n\015()]*(?:\\[^\x80-\xff][^\\\x80-\xff\n\015()]*)*\))[^\
    \\x80-\xff\n\015()]*)*\)[\040\t]*)*(?:[^(\040)<>@,;:".\\\[\]\000-\037\
    x80-\xff]+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff])|\[(?:[^\\\x80-
    \xff\n\015\[\]]|\\[^\x80-\xff])*\])[\040\t]*(?:\([^\\\x80-\xff\n\015()
    ]*(?:(?:\\[^\x80-\xff]|\([^\\\x80-\xff\n\015()]*(?:\\[^\x80-\xff][^\\\
    x80-\xff\n\015()]*)*\))[^\\\x80-\xff\n\015()]*)*\)[\040\t]*)*(?:\.[\04
    0\t]*(?:\([^\\\x80-\xff\n\015()]*(?:(?:\\[^\x80-\xff]|\([^\\\x80-\xff\
    n\015()]*(?:\\[^\x80-\xff][^\\\x80-\xff\n\015()]*)*\))[^\\\x80-\xff\n\
    015()]*)*\)[\040\t]*)*(?:[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+(?!
    [^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff])|\[(?:[^\\\x80-\xff\n\015\[\
    ]]|\\[^\x80-\xff])*\])[\040\t]*(?:\([^\\\x80-\xff\n\015()]*(?:(?:\\[^\
    x80-\xff]|\([^\\\x80-\xff\n\015()]*(?:\\[^\x80-\xff][^\\\x80-\xff\n\01
    5()]*)*\))[^\\\x80-\xff\n\015()]*)*\)[\040\t]*)*)*|(?:[^(\040)<>@,;:".
    \\\[\]\000-\037\x80-\xff]+(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]
    )|"[^\\\x80-\xff\n\015"]*(?:\\[^\x80-\xff][^\\\x80-\xff\n\015"]*)*")[^
    ()<>@,;:".\\\[\]\x80-\xff\000-\010\012-\037]*(?:(?:\([^\\\x80-\xff\n\0
    15()]*(?:(?:\\[^\x80-\xff]|\([^\\\x80-\xff\n\015()]*(?:\\[^\x80-\xff][
    ^\\\x80-\xff\n\015()]*)*\))[^\\\x80-\xff\n\015()]*)*\)|"[^\\\x80-\xff\
    n\015"]*(?:\\[^\x80-\xff][^\\\x80-\xff\n\015"]*)*")[^()<>@,;:".\\\[\]\
    x80-\xff\000-\010\012-\037]*)*<[\040\t]*(?:\([^\\\x80-\xff\n\015()]*(?
    :(?:\\[^\x80-\xff]|\([^\\\x80-\xff\n\015()]*(?:\\[^\x80-\xff][^\\\x80-
    \xff\n\015()]*)*\))[^\\\x80-\xff\n\015()]*)*\)[\040\t]*)*(?:@[\040\t]*
    (?:\([^\\\x80-\xff\n\015()]*(?:(?:\\[^\x80-\xff]|\([^\\\x80-\xff\n\015
    ()]*(?:\\[^\x80-\xff][^\\\x80-\xff\n\015()]*)*\))[^\\\x80-\xff\n\015()
    ]*)*\)[\040\t]*)*(?:[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+(?![^(\0
    40)<>@,;:".\\\[\]\000-\037\x80-\xff])|\[(?:[^\\\x80-\xff\n\015\[\]]|\\
    [^\x80-\xff])*\])[\040\t]*(?:\([^\\\x80-\xff\n\015()]*(?:(?:\\[^\x80-\
    xff]|\([^\\\x80-\xff\n\015()]*(?:\\[^\x80-\xff][^\\\x80-\xff\n\015()]*
    )*\))[^\\\x80-\xff\n\015()]*)*\)[\040\t]*)*(?:\.[\040\t]*(?:\([^\\\x80
    -\xff\n\015()]*(?:(?:\\[^\x80-\xff]|\([^\\\x80-\xff\n\015()]*(?:\\[^\x
    80-\xff][^\\\x80-\xff\n\015()]*)*\))[^\\\x80-\xff\n\015()]*)*\)[\040\t
    ]*)*(?:[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+(?![^(\040)<>@,;:".\\
    \[\]\000-\037\x80-\xff])|\[(?:[^\\\x80-\xff\n\015\[\]]|\\[^\x80-\xff])
    *\])[\040\t]*(?:\([^\\\x80-\xff\n\015()]*(?:(?:\\[^\x80-\xff]|\([^\\\x
    80-\xff\n\015()]*(?:\\[^\x80-\xff][^\\\x80-\xff\n\015()]*)*\))[^\\\x80
    -\xff\n\015()]*)*\)[\040\t]*)*)*(?:,[\040\t]*(?:\([^\\\x80-\xff\n\015(
    )]*(?:(?:\\[^\x80-\xff]|\([^\\\x80-\xff\n\015()]*(?:\\[^\x80-\xff][^\\
    \x80-\xff\n\015()]*)*\))[^\\\x80-\xff\n\015()]*)*\)[\040\t]*)*@[\040\t
    ]*(?:\([^\\\x80-\xff\n\015()]*(?:(?:\\[^\x80-\xff]|\([^\\\x80-\xff\n\0
    15()]*(?:\\[^\x80-\xff][^\\\x80-\xff\n\015()]*)*\))[^\\\x80-\xff\n\015
    ()]*)*\)[\040\t]*)*(?:[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+(?![^(
    \040)<>@,;:".\\\[\]\000-\037\x80-\xff])|\[(?:[^\\\x80-\xff\n\015\[\]]|
    \\[^\x80-\xff])*\])[\040\t]*(?:\([^\\\x80-\xff\n\015()]*(?:(?:\\[^\x80
    -\xff]|\([^\\\x80-\xff\n\015()]*(?:\\[^\x80-\xff][^\\\x80-\xff\n\015()
    ]*)*\))[^\\\x80-\xff\n\015()]*)*\)[\040\t]*)*(?:\.[\040\t]*(?:\([^\\\x
    80-\xff\n\015()]*(?:(?:\\[^\x80-\xff]|\([^\\\x80-\xff\n\015()]*(?:\\[^
    \x80-\xff][^\\\x80-\xff\n\015()]*)*\))[^\\\x80-\xff\n\015()]*)*\)[\040
    \t]*)*(?:[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+(?![^(\040)<>@,;:".
    \\\[\]\000-\037\x80-\xff])|\[(?:[^\\\x80-\xff\n\015\[\]]|\\[^\x80-\xff
    ])*\])[\040\t]*(?:\([^\\\x80-\xff\n\015()]*(?:(?:\\[^\x80-\xff]|\([^\\
    \x80-\xff\n\015()]*(?:\\[^\x80-\xff][^\\\x80-\xff\n\015()]*)*\))[^\\\x
    80-\xff\n\015()]*)*\)[\040\t]*)*)*)*:[\040\t]*(?:\([^\\\x80-\xff\n\015
    ()]*(?:(?:\\[^\x80-\xff]|\([^\\\x80-\xff\n\015()]*(?:\\[^\x80-\xff][^\
    \\x80-\xff\n\015()]*)*\))[^\\\x80-\xff\n\015()]*)*\)[\040\t]*)*)?(?:[^
    (\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+(?![^(\040)<>@,;:".\\\[\]\000-
    \037\x80-\xff])|"[^\\\x80-\xff\n\015"]*(?:\\[^\x80-\xff][^\\\x80-\xff\
    n\015"]*)*")[\040\t]*(?:\([^\\\x80-\xff\n\015()]*(?:(?:\\[^\x80-\xff]|
    \([^\\\x80-\xff\n\015()]*(?:\\[^\x80-\xff][^\\\x80-\xff\n\015()]*)*\))
    [^\\\x80-\xff\n\015()]*)*\)[\040\t]*)*(?:\.[\040\t]*(?:\([^\\\x80-\xff
    \n\015()]*(?:(?:\\[^\x80-\xff]|\([^\\\x80-\xff\n\015()]*(?:\\[^\x80-\x
    ff][^\\\x80-\xff\n\015()]*)*\))[^\\\x80-\xff\n\015()]*)*\)[\040\t]*)*(
    ?:[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+(?![^(\040)<>@,;:".\\\[\]\
    000-\037\x80-\xff])|"[^\\\x80-\xff\n\015"]*(?:\\[^\x80-\xff][^\\\x80-\
    xff\n\015"]*)*")[\040\t]*(?:\([^\\\x80-\xff\n\015()]*(?:(?:\\[^\x80-\x
    ff]|\([^\\\x80-\xff\n\015()]*(?:\\[^\x80-\xff][^\\\x80-\xff\n\015()]*)
    *\))[^\\\x80-\xff\n\015()]*)*\)[\040\t]*)*)*@[\040\t]*(?:\([^\\\x80-\x
    ff\n\015()]*(?:(?:\\[^\x80-\xff]|\([^\\\x80-\xff\n\015()]*(?:\\[^\x80-
    \xff][^\\\x80-\xff\n\015()]*)*\))[^\\\x80-\xff\n\015()]*)*\)[\040\t]*)
    *(?:[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+(?![^(\040)<>@,;:".\\\[\
    ]\000-\037\x80-\xff])|\[(?:[^\\\x80-\xff\n\015\[\]]|\\[^\x80-\xff])*\]
    )[\040\t]*(?:\([^\\\x80-\xff\n\015()]*(?:(?:\\[^\x80-\xff]|\([^\\\x80-
    \xff\n\015()]*(?:\\[^\x80-\xff][^\\\x80-\xff\n\015()]*)*\))[^\\\x80-\x
    ff\n\015()]*)*\)[\040\t]*)*(?:\.[\040\t]*(?:\([^\\\x80-\xff\n\015()]*(
    ?:(?:\\[^\x80-\xff]|\([^\\\x80-\xff\n\015()]*(?:\\[^\x80-\xff][^\\\x80
    -\xff\n\015()]*)*\))[^\\\x80-\xff\n\015()]*)*\)[\040\t]*)*(?:[^(\040)<
    >@,;:".\\\[\]\000-\037\x80-\xff]+(?![^(\040)<>@,;:".\\\[\]\000-\037\x8
    0-\xff])|\[(?:[^\\\x80-\xff\n\015\[\]]|\\[^\x80-\xff])*\])[\040\t]*(?:
    \([^\\\x80-\xff\n\015()]*(?:(?:\\[^\x80-\xff]|\([^\\\x80-\xff\n\015()]
    *(?:\\[^\x80-\xff][^\\\x80-\xff\n\015()]*)*\))[^\\\x80-\xff\n\015()]*)
    *\)[\040\t]*)*)*>)

Jason Voegele