Merge xml files with nested elements without external libraries
What the code you posted is doing is combining all the elements regardless of whether or not an element with the same tag already exists. So you need to iterate over the elements and manually check and combine them the way you see fit, because it is not a standard way of handling XML files. I can't explain it better than code, so here it is, more or less commented:
from xml.etree import ElementTree as et
class XMLCombiner(object):
def __init__(self, filenames):
assert len(filenames) > 0, 'No filenames!'
# save all the roots, in order, to be processed later
self.roots = [et.parse(f).getroot() for f in filenames]
def combine(self):
for r in self.roots[1:]:
# combine each element with the first one, and update that
self.combine_element(self.roots[0], r)
# return the string representation
return et.tostring(self.roots[0])
def combine_element(self, one, other):
"""
This function recursively updates either the text or the children
of an element if another element is found in `one`, or adds it
from `other` if not found.
"""
# Create a mapping from tag name to element, as that's what we are fltering with
mapping = {el.tag: el for el in one}
for el in other:
if len(el) == 0:
# Not nested
try:
# Update the text
mapping[el.tag].text = el.text
except KeyError:
# An element with this name is not in the mapping
mapping[el.tag] = el
# Add it
one.append(el)
else:
try:
# Recursively process the element, and update it in the same way
self.combine_element(mapping[el.tag], el)
except KeyError:
# Not in the mapping
mapping[el.tag] = el
# Just add it
one.append(el)
if __name__ == '__main__':
r = XMLCombiner(('sample1.xml', 'sample2.xml')).combine()
print '-'*20
print r
Thank you, but my problem was to merge by considering the attributes also. here is the code after my patch:
import sys
from xml.etree import ElementTree as et
class hashabledict(dict):
def __hash__(self):
return hash(tuple(sorted(self.items())))
class XMLCombiner(object):
def __init__(self, filenames):
assert len(filenames) > 0, 'No filenames!'
# save all the roots, in order, to be processed later
self.roots = [et.parse(f).getroot() for f in filenames]
def combine(self):
for r in self.roots[1:]:
# combine each element with the first one, and update that
self.combine_element(self.roots[0], r)
# return the string representation
return et.ElementTree(self.roots[0])
def combine_element(self, one, other):
"""
This function recursively updates either the text or the children
of an element if another element is found in `one`, or adds it
from `other` if not found.
"""
# Create a mapping from tag name to element, as that's what we are fltering with
mapping = {(el.tag, hashabledict(el.attrib)): el for el in one}
for el in other:
if len(el) == 0:
# Not nested
try:
# Update the text
mapping[(el.tag, hashabledict(el.attrib))].text = el.text
except KeyError:
# An element with this name is not in the mapping
mapping[(el.tag, hashabledict(el.attrib))] = el
# Add it
one.append(el)
else:
try:
# Recursively process the element, and update it in the same way
self.combine_element(mapping[(el.tag, hashabledict(el.attrib))], el)
except KeyError:
# Not in the mapping
mapping[(el.tag, hashabledict(el.attrib))] = el
# Just add it
one.append(el)
if __name__ == '__main__':
r = XMLCombiner(sys.argv[1:-1]).combine()
print '-'*20
print et.tostring(r.getroot())
r.write(sys.argv[-1], encoding="iso-8859-1", xml_declaration=True)
Extending @jadkik94 's answer to create a utility method which doesn't change its argument and also updates the attributes:
Note the code works only in Py2 as copy() method of Element class is not yet supported in Py3.
def combine_xmltree_element(element_1, element_2):
"""
Recursively combines the given two xmltree elements. Common properties will be overridden by values of those
properties in element_2.
:param element_1: A xml Element
:type element_1: L{Element}
:param element_2: A xml Element
:type element_2: L{Element}
:return: A xml element with properties combined.
"""
if element_1 is None:
return element_2.copy()
if element_2 is None:
return element_1.copy()
if element_1.tag != element_2.tag:
raise TypeError(
"The two XMLtree elements of type {t1} and {t2} cannot be combined".format(
t1=element_1.tag,
t2=element_2.tag
)
)
combined_element = Element(tag=element_1.tag, attrib=element_1.attrib)
combined_element.attrib.update(element_2.attrib)
# Create a mapping from tag name to child element
element_1_child_mapping = {child.tag: child for child in element_1}
element_2_child_mapping = {child.tag: child for child in element_2}
for child in element_1:
if child.tag not in element_2_child_mapping:
combined_element.append(child.copy())
for child in element_2:
if child.tag not in element_1_child_mapping:
combined_element.append(child.copy())
else:
if len(child) == 0: # Leaf element
combined_child = element_1_child_mapping[child.tag].copy()
combined_child.text = child.text
combined_child.attrib.update(child.attrib)
else:
# Recursively process the element, and update it in the same way
combined_child = combine_xmltree_element(element_1_child_mapping[child.tag], child)
combined_element.append(combined_child)
return combined_element