[ruby-talk:12753] Re: email address regexp

>>>>> "jjthrash" == jjthrash  <[e-mail]> writes:

jjthrash> Now, this is assuming an email address can only be made up of
jjthrash> chracters from a-zA-Z0-9_.  I don't know if that's a real
jjthrash> limitation.

Nope.  Totally your hallucination.

jjthrash>   I think it is a limitation on the domain name, so
jjthrash> the following might work:

jjthrash> /.+@\w+(\.\w+)+/

Nope.  \w matches both too little and too much, presuming it's
like Perl's \w.

The Perl regex to match an email address (or at least
a useful subset of them) can be found many places,
including

        http://www.foad.org/~abigail/Perl/url3.regex

which I include here to show that it's not a simple regex:

    (?:http://(?:(?:(?:(?:(?:[a-zA-Z\d](?:(?:[a-zA-Z\d]|-)*[a-zA-Z\d])?)\.
    )*(?:[a-zA-Z](?:(?:[a-zA-Z\d]|-)*[a-zA-Z\d])?))|(?:(?:\d+)(?:\.(?:\d+)
    ){3}))(?::(?:\d+))?)(?:/(?:(?:(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:%[a-fA-F
    \d]{2}))|[;:@&=])*)(?:/(?:(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:%[a-fA-F\d]{
    2}))|[;:@&=])*))*)(?:\?(?:(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:%[a-fA-F\d]{
    2}))|[;:@&=])*))?)?)|(?:ftp://(?:(?:(?:(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?
    :%[a-fA-F\d]{2}))|[;?&=])*)(?::(?:(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:%[a-
    fA-F\d]{2}))|[;?&=])*))?@)?(?:(?:(?:(?:(?:[a-zA-Z\d](?:(?:[a-zA-Z\d]|-
    )*[a-zA-Z\d])?)\.)*(?:[a-zA-Z](?:(?:[a-zA-Z\d]|-)*[a-zA-Z\d])?))|(?:(?
    :\d+)(?:\.(?:\d+)){3}))(?::(?:\d+))?))(?:/(?:(?:(?:(?:[a-zA-Z\d$\-_.+!
    *'(),]|(?:%[a-fA-F\d]{2}))|[?:@&=])*)(?:/(?:(?:(?:[a-zA-Z\d$\-_.+!*'()
    ,]|(?:%[a-fA-F\d]{2}))|[?:@&=])*))*)(?:;type=[AIDaid])?)?)|(?:news:(?:
    (?:(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:%[a-fA-F\d]{2}))|[;/?:&=])+@(?:(?:(
    ?:(?:[a-zA-Z\d](?:(?:[a-zA-Z\d]|-)*[a-zA-Z\d])?)\.)*(?:[a-zA-Z](?:(?:[
    a-zA-Z\d]|-)*[a-zA-Z\d])?))|(?:(?:\d+)(?:\.(?:\d+)){3})))|(?:[a-zA-Z](
    ?:[a-zA-Z\d]|[_.+-])*)|\*))|(?:nntp://(?:(?:(?:(?:(?:[a-zA-Z\d](?:(?:[
    a-zA-Z\d]|-)*[a-zA-Z\d])?)\.)*(?:[a-zA-Z](?:(?:[a-zA-Z\d]|-)*[a-zA-Z\d
    ])?))|(?:(?:\d+)(?:\.(?:\d+)){3}))(?::(?:\d+))?)/(?:[a-zA-Z](?:[a-zA-Z
    \d]|[_.+-])*)(?:/(?:\d+))?)|(?:telnet://(?:(?:(?:(?:(?:[a-zA-Z\d$\-_.+
    !*'(),]|(?:%[a-fA-F\d]{2}))|[;?&=])*)(?::(?:(?:(?:[a-zA-Z\d$\-_.+!*'()
    ,]|(?:%[a-fA-F\d]{2}))|[;?&=])*))?@)?(?:(?:(?:(?:(?:[a-zA-Z\d](?:(?:[a
    -zA-Z\d]|-)*[a-zA-Z\d])?)\.)*(?:[a-zA-Z](?:(?:[a-zA-Z\d]|-)*[a-zA-Z\d]
    )?))|(?:(?:\d+)(?:\.(?:\d+)){3}))(?::(?:\d+))?))/?)|(?:gopher://(?:(?:
    (?:(?:(?:[a-zA-Z\d](?:(?:[a-zA-Z\d]|-)*[a-zA-Z\d])?)\.)*(?:[a-zA-Z](?:
    (?:[a-zA-Z\d]|-)*[a-zA-Z\d])?))|(?:(?:\d+)(?:\.(?:\d+)){3}))(?::(?:\d+
    ))?)(?:/(?:[a-zA-Z\d$\-_.+!*'(),;/?:@&=]|(?:%[a-fA-F\d]{2}))(?:(?:(?:[
    a-zA-Z\d$\-_.+!*'(),;/?:@&=]|(?:%[a-fA-F\d]{2}))*)(?:%09(?:(?:(?:[a-zA
    -Z\d$\-_.+!*'(),]|(?:%[a-fA-F\d]{2}))|[;:@&=])*)(?:%09(?:(?:[a-zA-Z\d$
    \-_.+!*'(),;/?:@&=]|(?:%[a-fA-F\d]{2}))*))?)?)?)?)|(?:wais://(?:(?:(?:
    (?:(?:[a-zA-Z\d](?:(?:[a-zA-Z\d]|-)*[a-zA-Z\d])?)\.)*(?:[a-zA-Z](?:(?:
    [a-zA-Z\d]|-)*[a-zA-Z\d])?))|(?:(?:\d+)(?:\.(?:\d+)){3}))(?::(?:\d+))?
    )/(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:%[a-fA-F\d]{2}))*)(?:(?:/(?:(?:[a-zA
    -Z\d$\-_.+!*'(),]|(?:%[a-fA-F\d]{2}))*)/(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(
    ?:%[a-fA-F\d]{2}))*))|\?(?:(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:%[a-fA-F\d]
    {2}))|[;:@&=])*))?)|(?:mailto:(?:(?:[a-zA-Z\d$\-_.+!*'(),;/?:@&=]|(?:%
    [a-fA-F\d]{2}))+))|(?:file://(?:(?:(?:(?:(?:[a-zA-Z\d](?:(?:[a-zA-Z\d]
    |-)*[a-zA-Z\d])?)\.)*(?:[a-zA-Z](?:(?:[a-zA-Z\d]|-)*[a-zA-Z\d])?))|(?:
    (?:\d+)(?:\.(?:\d+)){3}))|localhost)?/(?:(?:(?:(?:[a-zA-Z\d$\-_.+!*'()
    ,]|(?:%[a-fA-F\d]{2}))|[?:@&=])*)(?:/(?:(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(
    ?:%[a-fA-F\d]{2}))|[?:@&=])*))*))|(?:prospero://(?:(?:(?:(?:(?:[a-zA-Z
    \d](?:(?:[a-zA-Z\d]|-)*[a-zA-Z\d])?)\.)*(?:[a-zA-Z](?:(?:[a-zA-Z\d]|-)
    *[a-zA-Z\d])?))|(?:(?:\d+)(?:\.(?:\d+)){3}))(?::(?:\d+))?)/(?:(?:(?:(?
    :[a-zA-Z\d$\-_.+!*'(),]|(?:%[a-fA-F\d]{2}))|[?:@&=])*)(?:/(?:(?:(?:[a-
    zA-Z\d$\-_.+!*'(),]|(?:%[a-fA-F\d]{2}))|[?:@&=])*))*)(?:(?:;(?:(?:(?:[
    a-zA-Z\d$\-_.+!*'(),]|(?:%[a-fA-F\d]{2}))|[?:@&])*)=(?:(?:(?:[a-zA-Z\d
    $\-_.+!*'(),]|(?:%[a-fA-F\d]{2}))|[?:@&])*)))*)|(?:ldap://(?:(?:(?:(?:
    (?:(?:[a-zA-Z\d](?:(?:[a-zA-Z\d]|-)*[a-zA-Z\d])?)\.)*(?:[a-zA-Z](?:(?:
    [a-zA-Z\d]|-)*[a-zA-Z\d])?))|(?:(?:\d+)(?:\.(?:\d+)){3}))(?::(?:\d+))?
    ))?/(?:(?:(?:(?:(?:(?:(?:[a-zA-Z\d]|%(?:3\d|[46][a-fA-F\d]|[57][Aa\d])
    )|(?:%20))+|(?:OID|oid)\.(?:(?:\d+)(?:\.(?:\d+))*))(?:(?:%0[Aa])?(?:%2
    0)*)=(?:(?:%0[Aa])?(?:%20)*))?(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:%[a-fA-F
    \d]{2}))*))(?:(?:(?:%0[Aa])?(?:%20)*)\+(?:(?:%0[Aa])?(?:%20)*)(?:(?:(?
    :(?:(?:[a-zA-Z\d]|%(?:3\d|[46][a-fA-F\d]|[57][Aa\d]))|(?:%20))+|(?:OID
    |oid)\.(?:(?:\d+)(?:\.(?:\d+))*))(?:(?:%0[Aa])?(?:%20)*)=(?:(?:%0[Aa])
    ?(?:%20)*))?(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:%[a-fA-F\d]{2}))*)))*)(?:(
    ?:(?:(?:%0[Aa])?(?:%20)*)(?:[;,])(?:(?:%0[Aa])?(?:%20)*))(?:(?:(?:(?:(
    ?:(?:[a-zA-Z\d]|%(?:3\d|[46][a-fA-F\d]|[57][Aa\d]))|(?:%20))+|(?:OID|o
    id)\.(?:(?:\d+)(?:\.(?:\d+))*))(?:(?:%0[Aa])?(?:%20)*)=(?:(?:%0[Aa])?(
    ?:%20)*))?(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:%[a-fA-F\d]{2}))*))(?:(?:(?:
    %0[Aa])?(?:%20)*)\+(?:(?:%0[Aa])?(?:%20)*)(?:(?:(?:(?:(?:[a-zA-Z\d]|%(
    ?:3\d|[46][a-fA-F\d]|[57][Aa\d]))|(?:%20))+|(?:OID|oid)\.(?:(?:\d+)(?:
    \.(?:\d+))*))(?:(?:%0[Aa])?(?:%20)*)=(?:(?:%0[Aa])?(?:%20)*))?(?:(?:[a
    -zA-Z\d$\-_.+!*'(),]|(?:%[a-fA-F\d]{2}))*)))*))*(?:(?:(?:%0[Aa])?(?:%2
    0)*)(?:[;,])(?:(?:%0[Aa])?(?:%20)*))?)(?:\?(?:(?:(?:(?:[a-zA-Z\d$\-_.+
    !*'(),]|(?:%[a-fA-F\d]{2}))+)(?:,(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:%[a-f
    A-F\d]{2}))+))*)?)(?:\?(?:base|one|sub)(?:\?(?:((?:[a-zA-Z\d$\-_.+!*'(
    ),;/?:@&=]|(?:%[a-fA-F\d]{2}))+)))?)?)?)|(?:(?:z39\.50[rs])://(?:(?:(?
    :(?:(?:[a-zA-Z\d](?:(?:[a-zA-Z\d]|-)*[a-zA-Z\d])?)\.)*(?:[a-zA-Z](?:(?
    :[a-zA-Z\d]|-)*[a-zA-Z\d])?))|(?:(?:\d+)(?:\.(?:\d+)){3}))(?::(?:\d+))
    ?)(?:/(?:(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:%[a-fA-F\d]{2}))+)(?:\+(?:(?:
    [a-zA-Z\d$\-_.+!*'(),]|(?:%[a-fA-F\d]{2}))+))*(?:\?(?:(?:[a-zA-Z\d$\-_
    .+!*'(),]|(?:%[a-fA-F\d]{2}))+))?)?(?:;esn=(?:(?:[a-zA-Z\d$\-_.+!*'(),
    ]|(?:%[a-fA-F\d]{2}))+))?(?:;rs=(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:%[a-fA
    -F\d]{2}))+)(?:\+(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:%[a-fA-F\d]{2}))+))*)
    ?))|(?:cid:(?:(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:%[a-fA-F\d]{2}))|[;?:@&=
    ])*))|(?:mid:(?:(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:%[a-fA-F\d]{2}))|[;?:@
    &=])*)(?:/(?:(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:%[a-fA-F\d]{2}))|[;?:@&=]
    )*))?)|(?:vemmi://(?:(?:(?:(?:(?:[a-zA-Z\d](?:(?:[a-zA-Z\d]|-)*[a-zA-Z
    \d])?)\.)*(?:[a-zA-Z](?:(?:[a-zA-Z\d]|-)*[a-zA-Z\d])?))|(?:(?:\d+)(?:\
    .(?:\d+)){3}))(?::(?:\d+))?)(?:/(?:(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:%[a
    -fA-F\d]{2}))|[/?:@&=])*)(?:(?:;(?:(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:%[a
    -fA-F\d]{2}))|[/?:@&])*)=(?:(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:%[a-fA-F\d
    ]{2}))|[/?:@&])*))*))?)|(?:imap://(?:(?:(?:(?:(?:(?:(?:[a-zA-Z\d$\-_.+
    !*'(),]|(?:%[a-fA-F\d]{2}))|[&=~])+)(?:(?:;[Aa][Uu][Tt][Hh]=(?:\*|(?:(
    ?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:%[a-fA-F\d]{2}))|[&=~])+))))?)|(?:(?:;[
    Aa][Uu][Tt][Hh]=(?:\*|(?:(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:%[a-fA-F\d]{2
    }))|[&=~])+)))(?:(?:(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:%[a-fA-F\d]{2}))|[
    &=~])+))?))@)?(?:(?:(?:(?:(?:[a-zA-Z\d](?:(?:[a-zA-Z\d]|-)*[a-zA-Z\d])
    ?)\.)*(?:[a-zA-Z](?:(?:[a-zA-Z\d]|-)*[a-zA-Z\d])?))|(?:(?:\d+)(?:\.(?:
    \d+)){3}))(?::(?:\d+))?))/(?:(?:(?:(?:(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:
    %[a-fA-F\d]{2}))|[&=~:@/])+)?;[Tt][Yy][Pp][Ee]=(?:[Ll](?:[Ii][Ss][Tt]|
    [Ss][Uu][Bb])))|(?:(?:(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:%[a-fA-F\d]{2}))
    |[&=~:@/])+)(?:\?(?:(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:%[a-fA-F\d]{2}))|[
    &=~:@/])+))?(?:(?:;[Uu][Ii][Dd][Vv][Aa][Ll][Ii][Dd][Ii][Tt][Yy]=(?:[1-
    9]\d*)))?)|(?:(?:(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:%[a-fA-F\d]{2}))|[&=~
    :@/])+)(?:(?:;[Uu][Ii][Dd][Vv][Aa][Ll][Ii][Dd][Ii][Tt][Yy]=(?:[1-9]\d*
    )))?(?:/;[Uu][Ii][Dd]=(?:[1-9]\d*))(?:(?:/;[Ss][Ee][Cc][Tt][Ii][Oo][Nn
    ]=(?:(?:(?:[a-zA-Z\d$\-_.+!*'(),]|(?:%[a-fA-F\d]{2}))|[&=~:@/])+)))?))
    )?)|(?:nfs:(?:(?://(?:(?:(?:(?:(?:[a-zA-Z\d](?:(?:[a-zA-Z\d]|-)*[a-zA-
    Z\d])?)\.)*(?:[a-zA-Z](?:(?:[a-zA-Z\d]|-)*[a-zA-Z\d])?))|(?:(?:\d+)(?:
    \.(?:\d+)){3}))(?::(?:\d+))?)(?:(?:/(?:(?:(?:(?:(?:[a-zA-Z\d\$\-_.!~*'
    (),])|(?:%[a-fA-F\d]{2})|[:@&=+])*)(?:/(?:(?:(?:[a-zA-Z\d\$\-_.!~*'(),
    ])|(?:%[a-fA-F\d]{2})|[:@&=+])*))*)?)))?)|(?:/(?:(?:(?:(?:(?:[a-zA-Z\d
    \$\-_.!~*'(),])|(?:%[a-fA-F\d]{2})|[:@&=+])*)(?:/(?:(?:(?:[a-zA-Z\d\$\
    -_.!~*'(),])|(?:%[a-fA-F\d]{2})|[:@&=+])*))*)?))|(?:(?:(?:(?:(?:[a-zA-
    Z\d\$\-_.!~*'(),])|(?:%[a-fA-F\d]{2})|[:@&=+])*)(?:/(?:(?:(?:[a-zA-Z\d
    \$\-_.!~*'(),])|(?:%[a-fA-F\d]{2})|[:@&=+])*))*)?)))

You'll need to remove all the ending newlines from that.  It's one
long single-line string.

-- 
Randal L. Schwartz - Stonehenge Consulting Services, Inc. - [phone]
<[e-mail]> <URL:http://www.stonehenge.com/merlyn/>
Perl/Unix/security consulting, Technical writing, Comedy, etc. etc.
See PerlTraining.Stonehenge.com for onsite and open-enrollment Perl training!