Compare XML snippets?

Question

Building on another SO question, how can one check whether two well-formed XML snippets are semantically equal. All I need is \"equal\" or not, since I\'m using this for un

Answer 1

I had the same problem: two documents I wanted to compare that had the same attributes but in different orders.

It seems that XML Canonicalization (C14N) in lxml works well for this, but I'm definitely not an XML expert. I'm curious to know if somebody else can point out drawbacks to this approach.

parser = etree.XMLParser(remove_blank_text=True)

xml1 = etree.fromstring(xml_string1, parser)
xml2 = etree.fromstring(xml_string2, parser)

print "xml1 == xml2: " + str(xml1 == xml2)

ppxml1 = etree.tostring(xml1, pretty_print=True)
ppxml2 = etree.tostring(xml2, pretty_print=True)

print "pretty(xml1) == pretty(xml2): " + str(ppxml1 == ppxml2)

xml_string_io1 = StringIO()
xml1.getroottree().write_c14n(xml_string_io1)
cxml1 = xml_string_io1.getvalue()

xml_string_io2 = StringIO()
xml2.getroottree().write_c14n(xml_string_io2)
cxml2 = xml_string_io2.getvalue()

print "canonicalize(xml1) == canonicalize(xml2): " + str(cxml1 == cxml2)

Running this gives me:

$ python test.py 
xml1 == xml2: false
pretty(xml1) == pretty(xml2): false
canonicalize(xml1) == canonicalize(xml2): true

Answer 2

Adapting Anentropic's great answer to Python 3 (basically, change iteritems() to items(), and basestring to string):

from lxml import etree
import xmltodict  # pip install xmltodict

def normalise_dict(d):
    """
    Recursively convert dict-like object (eg OrderedDict) into plain dict.
    Sorts list values.
    """
    out = {}
    for k, v in dict(d).items():
        if hasattr(v, 'iteritems'):
            out[k] = normalise_dict(v)
        elif isinstance(v, list):
            out[k] = []
            for item in sorted(v):
                if hasattr(item, 'iteritems'):
                    out[k].append(normalise_dict(item))
                else:
                    out[k].append(item)
        else:
            out[k] = v
    return out


def xml_compare(a, b):
    """
    Compares two XML documents (as string or etree)

    Does not care about element order
    """
    if not isinstance(a, str):
        a = etree.tostring(a)
    if not isinstance(b, str):
        b = etree.tostring(b)
    a = normalise_dict(xmltodict.parse(a))
    b = normalise_dict(xmltodict.parse(b))
    return a == b

Answer 3

Here a simple solution, convert XML into dictionaries (with xmltodict) and compare dictionaries together

import json
import xmltodict

class XmlDiff(object):
    def __init__(self, xml1, xml2):
        self.dict1 = json.loads(json.dumps((xmltodict.parse(xml1))))
        self.dict2 = json.loads(json.dumps((xmltodict.parse(xml2))))

    def equal(self):
        return self.dict1 == self.dict2

unit test

import unittest

class XMLDiffTestCase(unittest.TestCase):

    def test_xml_equal(self):
        xml1 = """<?xml version='1.0' encoding='utf-8' standalone='yes'?>
        <Stats start="1275955200" end="1276041599">
        </Stats>"""
        xml2 = """<?xml version='1.0' encoding='utf-8' standalone='yes'?>
        <Stats end="1276041599" start="1275955200" >
        </Stats>"""
        self.assertTrue(XmlDiff(xml1, xml2).equal())

    def test_xml_not_equal(self):
        xml1 = """<?xml version='1.0' encoding='utf-8' standalone='yes'?>
        <Stats start="1275955200">
        </Stats>"""
        xml2 = """<?xml version='1.0' encoding='utf-8' standalone='yes'?>
        <Stats end="1276041599" start="1275955200" >
        </Stats>"""
        self.assertFalse(XmlDiff(xml1, xml2).equal())

or in simple python method :

import json
import xmltodict

def xml_equal(a, b):
    """
    Compares two XML documents (as string or etree)

    Does not care about element order
    """
    return json.loads(json.dumps((xmltodict.parse(a)))) == json.loads(json.dumps((xmltodict.parse(b))))

Answer 4

Thinking about this problem, I came up with the following solution that renders XML elements comparable and sortable:

import xml.etree.ElementTree as ET
def cmpElement(x, y):
    # compare type
    r = cmp(type(x), type(y))
    if r: return r 
    # compare tag
    r = cmp(x.tag, y.tag)
    if r: return r
    # compare tag attributes
    r = cmp(x.attrib, y.attrib)
    if r: return r
    # compare stripped text content
    xtext = (x.text and x.text.strip()) or None
    ytext = (y.text and y.text.strip()) or None
    r = cmp(xtext, ytext)
    if r: return r
    # compare sorted children
    if len(x) or len(y):
        return cmp(sorted(x.getchildren()), sorted(y.getchildren()))
    return 0

ET._ElementInterface.__lt__ = lambda self, other: cmpElement(self, other) == -1
ET._ElementInterface.__gt__ = lambda self, other: cmpElement(self, other) == 1
ET._ElementInterface.__le__ = lambda self, other: cmpElement(self, other) <= 0
ET._ElementInterface.__ge__ = lambda self, other: cmpElement(self, other) >= 0
ET._ElementInterface.__eq__ = lambda self, other: cmpElement(self, other) == 0
ET._ElementInterface.__ne__ = lambda self, other: cmpElement(self, other) != 0