rougail/creole/xml_compare.py

try:
    import doctest
    doctest.OutputChecker
except (AttributeError, ImportError): # Python < 2.4
    import util.doctest24 as doctest
try:
    import xml.etree.ElementTree as ET
except ImportError:
    import elementtree.ElementTree as ET
from xml.parsers.expat import ExpatError as XMLParseError

RealOutputChecker = doctest.OutputChecker


def debug(*msg):
    import sys
    print >> sys.stderr, ' '.join(map(str, msg))


class HTMLOutputChecker(RealOutputChecker):

    def check_output(self, want, got, optionflags):
        normal = RealOutputChecker.check_output(self, want, got, optionflags)
        if normal or not got:
            return normal
        try:
            want_xml = make_xml(want)
        except XMLParseError:
            pass
        else:
            try:
                got_xml = make_xml(got)
            except XMLParseError:
                pass
            else:
                if xml_compare(want_xml, got_xml):
                    return True
        return False

    def output_difference(self, example, got, optionflags):
        actual = RealOutputChecker.output_difference(
            self, example, got, optionflags)
        want_xml = got_xml = None
        try:
            want_xml = make_xml(example.want)
            want_norm = make_string(want_xml)
        except XMLParseError as e:
            if example.want.startswith('<'):
                want_norm = '(bad XML: %s)' % e
                #  '<xml>%s</xml>' % example.want
            else:
                return actual
        try:
            got_xml = make_xml(got)
            got_norm = make_string(got_xml)
        except XMLParseError as e:
            if example.want.startswith('<'):
                got_norm = '(bad XML: %s)' % e
            else:
                return actual
        s = '%s\nXML Wanted: %s\nXML Got   : %s\n' % (
            actual, want_norm, got_norm)
        if got_xml and want_xml:
            result = []
            xml_compare(want_xml, got_xml, result.append)
            s += 'Difference report:\n%s\n' % '\n'.join(result)
        return s


def xml_sort(children):
    tcl1 = {}
    #idx = 0

    for child in children:
        if 'name' in child.attrib:
            key = child.attrib['name']
        else:
            key = child.tag
        if key not in tcl1:
            tcl1[key] = []
        tcl1[key].append(child)
    cl1_keys = list(tcl1.keys())
    cl1_keys.sort()
    cl1 = []
    for key in cl1_keys:
        cl1.extend(tcl1[key])
    return cl1

def xml_compare(x1, x2):
    if x1.tag != x2.tag:
        print ('Tags do not match: %s and %s' % (x1.tag, x2.tag))
        return False
    for name, value in x1.attrib.items():
        if x2.attrib.get(name) != value:
            print ('Attributes do not match: %s=%r, %s=%r'
                     % (name, value, name, x2.attrib.get(name)))
            return False
    for name in x2.attrib:
        if name not in x1.attrib:
            print ('x2 has an attribute x1 is missing: %s'
                     % name)
            return False
    if not text_compare(x1.text, x2.text):
        print ('text: %r != %r' % (x1.text, x2.text))
        return False
    if not text_compare(x1.tail, x2.tail):
        print ('tail: %r != %r' % (x1.tail, x2.tail))
        return False

    cl1 = xml_sort(x1.getchildren())
    cl2 = xml_sort(x2.getchildren())

    if len(cl1) != len(cl2):
        cl1_tags = []
        for c in cl1:
            cl1_tags.append(c.tag)
        cl2_tags = []
        for c in cl2:
            cl2_tags.append(c.tag)
        print ('children length differs, %i != %i (%s != %s)'
                 % (len(cl1), len(cl2), cl1_tags, cl2_tags))
        return False
    i = 0
    for c1, c2 in zip(cl1, cl2):
        i += 1
        if not xml_compare(c1, c2):
            if 'name' in c1.attrib:
                name = c1.attrib['name']
            else:
                name = i
            print ('in tag "%s" with name "%s"'
                     % (c1.tag, name))
            return False
    return True


def text_compare(t1, t2):
    if not t1 and not t2:
        return True
    if t1 == '*' or t2 == '*':
        return True
    return (t1 or '').strip() == (t2 or '').strip()


def make_xml(s):
    return ET.XML('<xml>%s</xml>' % s)


def make_string(xml):
    if isinstance(xml, (str, unicode)):
        xml = make_xml(xml)
    s = ET.tostring(xml)
    if s == '<xml />':
        return ''
    assert s.startswith('<xml>') and s.endswith('</xml>'), repr(s)
    return s[5:-6]


def install():
    doctest.OutputChecker = HTMLOutputChecker