Validating An Xmpp Jid With Python?

What is the correct way to validate an xmpp jid? The syntax is described here:, but I don't really understand it. Also, it seems pretty complicated, so using a library to do it wou

Solution 1:

First off, the current best reference for JIDs is RFC 6122.

I was just going to give you the regex in here, but got a little carried away, and implemented all of the spec:

import re
import sys
import socket
import encodings.idna
import stringprep

# These characters aren't allowed in domain names that are used# in XMPP
BAD_DOMAIN_ASCII = "".join([chr(c) for c inrange(0,0x2d) +
                    [0x2e, 0x2f] +
                    range(0x3a,0x41) +
                    range(0x5b,0x61) +
                    range(0x7b, 0x80)])

# check bi-directional character validitydefbidi(chars):
    RandAL = map(stringprep.in_table_d1, chars)
    for c in RandAL:
        if c:
            # There is a RandAL char in the string. Must perform further# tests:# 1) The characters in section 5.8 MUST be prohibited.# This is table C.8, which was already checked# 2) If a string contains any RandALCat character, the string# MUST NOT contain any LCat character.iffilter(stringprep.in_table_d2, chars):
                raise UnicodeError("Violation of BIDI requirement 2")

            # 3) If a string contains any RandALCat character, a# RandALCat character MUST be the first character of the# string, and a RandALCat character MUST be the last# character of the string.ifnot RandAL[0] ornot RandAL[-1]:
                raise UnicodeError("Violation of BIDI requirement 3")

defnodeprep(u):
    chars = list(unicode(u))
    i = 0while i < len(chars):
        c = chars[i]
        # map to nothingif stringprep.in_table_b1(c):
            del chars[i]
        else:
            # case fold
            chars[i] = stringprep.map_table_b2(c)
            i += 1# NFKC
    chars = stringprep.unicodedata.normalize("NFKC", "".join(chars))
    for c in chars:
        if (stringprep.in_table_c11(c) or
            stringprep.in_table_c12(c) or
            stringprep.in_table_c21(c) or
            stringprep.in_table_c22(c) or
            stringprep.in_table_c3(c) or
            stringprep.in_table_c4(c) or
            stringprep.in_table_c5(c) or
            stringprep.in_table_c6(c) or
            stringprep.in_table_c7(c) or
            stringprep.in_table_c8(c) or
            stringprep.in_table_c9(c) or
            c in"\"&'/:<>@"):
            raise UnicodeError("Invalid node character")

    bidi(chars)

    return chars

defresourceprep(res):
    chars = list(unicode(res))
    i = 0while i < len(chars):
        c = chars[i]
        # map to nothingif stringprep.in_table_b1(c):
            del chars[i]
        else:
            i += 1# NFKC
    chars = stringprep.unicodedata.normalize("NFKC", "".join(chars))
    for c in chars:
        if (stringprep.in_table_c12(c) or
            stringprep.in_table_c21(c) or
            stringprep.in_table_c22(c) or
            stringprep.in_table_c3(c) or
            stringprep.in_table_c4(c) or
            stringprep.in_table_c5(c) or
            stringprep.in_table_c6(c) or
            stringprep.in_table_c7(c) or
            stringprep.in_table_c8(c) or
            stringprep.in_table_c9(c)):
            raise UnicodeError("Invalid node character")

    bidi(chars)
    
    return chars

defparse_jid(jid):
    # first pass
    m = re.match("^(?:([^\"&'/:<>@]{1,1023})@)?([^/@]{1,1023})(?:/(.{1,1023}))?$", jid)
    ifnot m:
        returnFalse
    
    (node, domain, resource) = m.groups()
    try:
        # ipv4 address?
        socket.inet_pton(socket.AF_INET, domain)
    except socket.error:
        # ipv6 address?try:
            socket.inet_pton(socket.AF_INET6, domain)
        except socket.error:
            # domain name
            dom = []
            for label in domain.split("."):
                try:
                    label = encodings.idna.nameprep(unicode(label))
                    encodings.idna.ToASCII(label)
                except UnicodeError:
                    returnFalse# UseSTD3ASCIIRules is set, but Python's nameprep doesn't enforce it.# a) Verify the absence of non-LDH ASCII code points; that is, thefor c in label:
                    if c in BAD_DOMAIN_ASCII:
                        returnFalse# Verify the absence of leading and trailing hyphen-minusif label[0] == '-'or label[-1] == "-":
                    returnFalse
                dom.append(label)
            domain = ".".join(dom)
    try:
        if node isnotNone:
            node = nodeprep(node)
        if resource isnotNone:
            resource = resourceprep(resource)
    except UnicodeError:
        returnFalsereturn node, domain, resource

if __name__ == "__main__":
    results = parse_jid(sys.argv[1])
    ifnot results:
        print"FAIL"else:   
        print results

Yes, this is a lot of work. There's good reasons for all of it, but we're hoping to simplify it in the future somewhat if the précis working group bears fruit.