XML sort script

sort-xml.py

#!python3
# https://stackoverflow.com/a/66596507/7643972
import os
import sys

from lxml import etree


if len(sys.argv) < 2:
    print("usage : sort_xml.py file_in.xml [file_in_sorted.xml]")
    exit(0)

filename_in = sys.argv[1]
filename_out = ((len(sys.argv) == 3) and sys.argv[2]) or f"{os.path.splitext(filename_in)[0]}_sorted.xml"


def getSortValue(elem):
    if isinstance(elem, etree._Comment):
        # sort comment by its content
        return elem.text
    else:
        # sort entities by tag and then by name
        return elem.tag + elem.attrib.get("id", "")

parser = etree.XMLParser(strip_cdata=False)
doc = etree.parse(filename_in, parser=parser)

for parent in doc.xpath("//*[./*]"):  # Search for parent elements
    parent[:] = sorted(parent, key=lambda x: getSortValue(x))

with open(filename_out, "wb") as file:
    file.write(etree.tostring(doc, pretty_print=True))