[Python-Dev] Escaping CDATA

[Ka-Ping Yee]

Here's what i'm playing with, if you want to mess with it too:



import string

def replace(text, old, new, join=string.join, split=string.split):
    return join(split(text, old), new)

la, ra = "@@", "@@]"
lb, rb = "]]>", "@@>"

la, ra = "<]", "<]>"
lb, rb = "]]>", "<]["

def escape(text):
    cdata = replace(text, la, ra)
    cdata = replace(cdata, lb, rb)
    return cdata

def unescape(cdata):
    text = replace(cdata, rb, lb)
    text = replace(text, ra, la)
    return text

chars = ""
for ch in la + ra + lb + rb:
    if ch not in chars: chars = chars + ch

if __name__ == "__main__":
    class Tester:
        def __init__(self):
            self.failed = []
            self.count = 0

        def test(self, s, find=string.find):
            cdata = escape(s)
            text = unescape(cdata)
            print "%s -e-> %s -u-> %s" % (s, cdata, text)
            if find(cdata, "]]>") >= 0:
                print "EXPOSURE!"
                self.failed.append(s)
            elif s != text:
                print "MISMATCH!"
                self.failed.append(s)
            self.count = self.count + 1

    tester = Tester()
    test = tester.test
    for a in chars:
        for b in chars:
            for c in chars:
                for d in chars:
                    for e in chars:
                        for f in chars:
                            for g in chars:
                                for h in chars:
                                    test(a+b+c+d+e+f+g+h)

    print
    if tester.failed == []: print "All tests succeeded."
    else:
        print "Failed %d of %d tests." % (len(tester.failed), tester.count)
        for t in tester.failed: tester.test(t)