Validate email address form

Of cause I looked a moment these looping without loop tests and could leave them as original:

# -*- coding: latin1 -*-
def validateEmail(a):
    sep=[x for x in a if not x.isalpha()]
    sepjoined=''.join(sep)
    ## sep joined must be ..@.... form
    if sepjoined.strip('.') != '@': return False
    end=a
    for i in sep:
        part,i,end=end.partition(i)
        if len(part)<2: return False
    return True

if __name__ == '__main__':
    emails = [ "test.@web.com","test+john@web.museum", "test+john@web.m",
               "a@n.dk", "and.bun@webben.de","marjaliisa.hamalainen@hel.fi",
               "marja-liisa.hämäläinen@hel.fi", "marjaliisa.hämäläinen@hel.fi"]
    print "Valid emails are:"
    for i in filter(validateEmail,emails): print '\t',i
    print "Non-ascii letters are nowadays allowed also in names!"
""" Output:
Valid emails are:
	and.bun@webben.de
	marjaliisa.hamalainen@hel.fi
	marjaliisa.hämäläinen@hel.fi
Non-ascii letters are nowadays allowed also in names!
"""

Why not regex?

def validateEmail(address):
	pattern = "[\.\w]{2,}[@]\w+[.]\w+"
	if re.match(pattern, address):
		return True
	else:
		return False

The problem is that it won't detect test.@test.com as a false one. If anyone has an idea. Please suggest it.

OK, my code has bug, it does not check the last part which is left in end variable before returning from function for valid length. Luckily, because I reused the logic for other check, I noticed the bug in debuging it, Here correction:

# -*- coding: latin1 -*-
import re
def validateEmail(a):
    sep=[x for x in a if not x.isalpha()]
    sepjoined=''.join(sep)
    ## sep joined must be ..@.... form
    if sepjoined.strip('.') != '@': return False
    end=a
    for i in sep:
        part,i,end=end.partition(i)
        if len(part)<2: return False
    return len(end)>1

def emailval(address):
	pattern = "[\.\w]{2,}[@]\w+[.]\w+"
	if re.match(pattern, address):
		return True
	else:
		return False    

if __name__ == '__main__':
    emails = [ "test.@web.com","test+john@web.museum", "test+john@web.m",
               "a@n.dk", "and.bun@webben.de","marjaliisa.hämäläinen@hel.fi",
               "marja-liisa.hämäläinen@hel.fi", "marjaliisah@hel.",'tony@localhost']
    print "Valid emails are:"
    for i in filter(validateEmail,emails): print '\t',i
    print "Regexp gives wrong answer:"
    for i in filter(emailval,emails):  print '\t',i
"""
Valid emails are:
	and.bun@webben.de
	marjaliisa.hämäläinen@hel.fi
	tony@localhost
Regexp gives wrong answer:
	test.@web.com
	and.bun@webben.de
"""

Here also confirmation that the regexp posted is even more wrong than previous check.

Update with better style than this newbie did and changing the match to be similar to this better regular expression, which is little restricted version from
http://www.regular-expressions.info/email.html (no test.@web.com accepted)

Here you see some examples that standard would pass:
http://en.wikipedia.org/wiki/Email_address#Valid_email_addresses

# -*- coding: latin1 -*-
import re

def validate_email(address):
    """ Validate by python equivalent to regular expression below """
    #to not allow single letter parts increase len_limit to 2 or more
    len_limit, max_domain = 1, 4
    # only ascii values not all alpha
    sep = [code for code in address if not code.isalpha() or ord(code) > 128]
    if (# sep joined must be ..@.... form
        ''.join(sep).strip('.') != '@' or
        # must have point after @
        sep[-1] == '@'):
        return False
    else:
        end = address
        for s in sep:
            part, s, end = end.partition(s)
            if len(part) < len_limit:
                return False
            
    return max_domain >= len(end)>1

def email_validate_re(address):
    """ from http://www.regular-expressions.info/email.html """
    pattern = r"\b[a-zA-Z0-9._%+-]*[a-zA-Z0-9_%+-]+@[a-zA-Z0-9.-]+\.[a-zA-Z]{2,4}\b"
    return re.match(pattern, address)

if __name__ == '__main__':
    emails = [ "test.@web.com","test@com", "test+john@web.museum", "test+john@web.m",
               "address@n.dk", "and.bun@webben.de","marjaliisa.hamalainen@hel.fi",
               "marja-liisa.hämäläinen@hel.fi", "marjaliisah@hel.",'tony@veijalainen.localhost']
    print("Valid emails by my function are:")
    print('\t' + '\n\t'.join(email for email in emails if validate_email(email)))
    print("\nRegexp answer:")
    print('\t' + '\n\t'.join(email for email in emails if email_validate_re(email)))

"""
Valid emails by my function are:
	address@n.dk
	and.bun@webben.de
	marjaliisa.hamalainen@hel.fi

Regexp answer:
	address@n.dk
	and.bun@webben.de
	marjaliisa.hamalainen@hel.fi
"""

Here you can see those email addresses that standard would allow, but you have never seen:
http://en.wikipedia.org/wiki/Email_address

Update with better style than this newbie did and changing the match to be similar to this better regular expression, which is little restricted version from
http://www.regular-expressions.info/email.html (no test.@web.com accepted)

Here you see some examples that standard would pass:
http://en.wikipedia.org/wiki/Email_address#Valid_email_addresses

# -*- coding: latin1 -*-
import re

def validate_email(address):
    """ Validate by python equivalent to regular expression below """
    #to not allow single letter parts increase len_limit to 2 or more
    len_limit, max_domain = 1, 4
    # only ascii values not all alpha
    sep = [code for code in address if not code.isalpha() or ord(code) > 128]
    if (# sep joined must be ..@.... form
        ''.join(sep).strip('.') != '@' or
        # must have point after @
        sep[-1] == '@'):
        return False
    else:
        end = address
        for s in sep:
            part, s, end = end.partition(s)
            if len(part) < len_limit:
                return False
            
    return max_domain >= len(end)>1

def email_validate_re(address):
    """ from http://www.regular-expressions.info/email.html """
    pattern = r"\b[a-zA-Z0-9._%+-]*[a-zA-Z0-9_%+-]+@[a-zA-Z0-9.-]+\.[a-zA-Z]{2,4}\b"
    return re.match(pattern, address)

if __name__ == '__main__':
    emails = [ "test.@web.com","test@com", "test+john@web.museum", "test+john@web.m",
               "address@n.dk", "and.bun@webben.de","marjaliisa.hamalainen@hel.fi",
               "marja-liisa.hämäläinen@hel.fi", "marjaliisah@hel.",'tony@veijalainen.localhost']
    print("Valid emails by my function are:")
    print('\t' + '\n\t'.join(email for email in emails if validate_email(email)))
    print("\nRegexp answer:")
    print('\t' + '\n\t'.join(email for email in emails if email_validate_re(email)))

"""
Valid emails by my function are:
	address@n.dk
	and.bun@webben.de
	marjaliisa.hamalainen@hel.fi

Regexp answer:
	address@n.dk
	and.bun@webben.de
	marjaliisa.hamalainen@hel.fi
"""

Though i like your function pytony, there are alot of emails your function may reject which will be very alarmin. consider this .....

# -*- coding: latin1 -*-
import re

def validate_email(address):
    """ Validate by python equivalent to regular expression below """
    #to not allow single letter parts increase len_limit to 2 or more
    len_limit, max_domain = 1, 4
    # only ascii values not all alpha
    sep = [code for code in address if not code.isalpha() or ord(code) > 128]
    if (# sep joined must be ..@.... form
        ''.join(sep).strip('.') != '@' or
        # must have point after @
        sep[-1] == '@'):
        return False
    else:
        end = address
        for s in sep:
            part, s, end = end.partition(s)
            if len(part) < len_limit:
                return False
            
    return max_domain >= len(end)>1

def email_validate_re(address):
    """ from http://www.regular-expressions.info/email.html """
    pattern = r"\b[a-zA-Z0-9._%+-]*[a-zA-Z0-9_%+-]+@[a-zA-Z0-9.-]+\.[a-zA-Z]{2,4}\b"
    return re.match(pattern, address)

if __name__ == '__main__':
    emails = [ "test.@web.com","test@com", "test+john@web.museum", "test+john@web.m",
               "address@n.dk", "and.bun@webben.de","marjaliisa.hamalainen@hel.fi",
               "marja-liisa.hämäläinen@hel.fi", "marjaliisah@hel.",'tony@veijalainen.localhost','richie_@ya.com']
    print("Valid emails by my function are:")
    print('\t' + '\n\t'.join(email for email in emails if validate_email(email)))
    print("\nRegexp answer:")
    print('\t' + '\n\t'.join(email for email in emails if email_validate_re(email)))




Valid emails by my function are:
	address@n.dk
	and.bun@webben.de
	marjaliisa.hamalainen@hel.fi

Regexp answer:
	address@n.dk
	and.bun@webben.de
	marjaliisa.hamalainen@hel.fi
	richie_@ya.com

at the end of the list for email. i added a well accepted email but your function rejected it. [ richie_@ya.com ].
But nice move anyway.

You must then relax the limitation:

def validate_email(address):
    """ Validate by python equivalent to regular expression below """
    # to not allow single letter parts increase len_limit to 2 or more
    len_limit, max_domain = 1, 4
    # acceptable in left side in username
    accept_username = '_-'
    # only ascii values not all alpha
    sep = [code for code in address if ((not code.isalpha() and code not in accept_username)
                                        or ord(code) > 128)]
    if (# sep joined must be ..@.... form
        ''.join(sep).strip('.') != '@' or
        # must have point after @
        sep[-1].strip() == '@'):
        return False
    else:
        end = address
        for s in sep:
            part, s, end = end.partition(s)
            if len(part) < len_limit:
                return False
            
    return max_domain >= len(end) > 1