Created
October 12, 2017 20:44
-
-
Save dirkjot/bd25b037b33bba6187e99d76792ceb90 to your computer and use it in GitHub Desktop.
Using lmxl/etree to merge two xml trees
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from lxml import etree | |
from copy import deepcopy | |
""" | |
This is an attempt to merge to XML trees. It works but it probably doesn't do what you want because XML elements are not only identified | |
by their tag. Take a POM for example, it will have many <dependency> nodes that are only distinguished by the text on their daughter | |
node 'GroupId'. This code does not take that into account. | |
""" | |
def treeMerge(a, b): | |
"""Merge two xml trees A and B, so that each recursively found leaf element of B is added to A. If the element | |
already exists in A, it is replaced with B's version. Tree structure is created in A as required to reflect the | |
position of the leaf element in B. | |
Given <top><first><a/><b/></first></top> and <top><first><c/></first></top>, a merge results in | |
<top><first><a/><b/><c/></first></top> (order not guaranteed) | |
""" | |
def inner(aparent, bparent): | |
for bchild in bparent: | |
achild = aparent.xpath('./' + bchild.tag) | |
if not achild: | |
aparent.append(bchild) | |
elif bchild.getchildren(): | |
inner(achild[0], bchild) | |
res = deepcopy(a) | |
inner(res, b) | |
return res |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
lass Test_TreeMerge(unittest.TestCase): | |
def test_level_zero(self): | |
a = etree.fromstring("""<top></top>""") | |
b = etree.fromstring("""<top2></top2>""") | |
#result = donkey.treeMerge(a, b) | |
# should give us an error | |
def test_level_one(self): | |
a = etree.fromstring("""<top><a/><b/><d><d2/></d></top>""") | |
b = etree.fromstring("""<top><c/></top>""") | |
result = donkey.treeMerge(a, b) | |
self.assertEqual(len(result.xpath("/top")[0]), 4) | |
self.assertEqual(len(result.xpath("/top/d/d2")), 1) | |
def test_no_duplicates(self): | |
a = etree.fromstring("""<top><a/></top>""") | |
b = etree.fromstring("""<top><a/></top>""") | |
result = donkey.treeMerge(a, b) | |
self.assertEqual(len(result.xpath("/top")[0]), 1) | |
def test_level_two(self): | |
a = etree.fromstring("""<top><a/><b><b1/></b></top>""") | |
b = etree.fromstring("""<top><b><b2/></b></top>""") | |
result = donkey.treeMerge(a, b) | |
print(etree.tostring(result)) | |
self.assertEqual(len(result.xpath("/top/a")), 1) | |
self.assertEqual(len(result.xpath("/top/b/b1")), 1) | |
self.assertEqual(len(result.xpath("/top/b/b2")), 1) | |
def test_level_three(self): | |
a = etree.fromstring("""<top><a/><b><b1><b11/><b22/></b1></b></top>""") | |
b = etree.fromstring("""<top><a/><b><b1><b12/><b22/></b1></b></top>""") | |
result = donkey.treeMerge(a, b) | |
print(etree.tostring(result)) | |
self.assertEqual(len(result.xpath("/top/a")), 1) | |
self.assertEqual(len(result.xpath("/top/b/b1/b11")), 1) | |
self.assertEqual(len(result.xpath("/top/b/b1/b12")), 1) | |
self.assertEqual(len(result.xpath("/top/b/b1/b22")), 1) | |
def test_replaces_same_named_child(self): | |
a = etree.fromstring("""<top><b foo=1></top>""") | |
b = etree.fromstring("""<top><b foo=2></top>""") | |
result = donkey.treeMerge(a, b) | |
print(etree.tostring(result)) | |
self.assertEqual(len(result.xpath("/top/b[@foo=1]")), 0) | |
self.assertEqual(len(result.xpath("/top/b[@foo=2]")), 1) | |
def deal_with_namespaces(self): | |
pass |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment