Created
April 19, 2011 17:31
-
-
Save jl2/928952 to your computer and use it in GitHub Desktop.
Use lxml and Python3 to validate XML against a DTD.The DTD can be specified on the command line, or as an optional parameter to the script.
This file contains hidden or 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
#!/usr/bin/env python3 | |
# Use lxml to validate XML against a DTD | |
import re | |
import sys | |
import os.path | |
import codecs | |
from lxml import etree | |
def main(args): | |
if len(args)<1: | |
print("Not enough arguments given. Expected:") | |
print("\tvalidatexml <xml file name> [<dtd file name>]\n") | |
exit(1) | |
dtdRe = re.compile('.*<!DOCTYPE .* ["\'](.*\.dtd)["\']>.*') | |
theDtd = None | |
inFile = args[0] | |
fdir = os.path.abspath(os.path.dirname(inFile)) | |
if len(args)==2: | |
theDtd = os.path.abspath(args[1]) | |
else: | |
with codecs.open(args[0], 'r', 'utf-8') as inf: | |
for ln in inf: | |
mtch = dtdRe.match(ln) | |
if mtch: | |
if os.path.isabs(mtch.group(1)): | |
theDtd = mtch.group(1) | |
else: | |
theDtd = os.path.abspath(fdir + '/' + mtch.group(1)) | |
break | |
if theDtd is None: | |
print("No DTD specified!") | |
exit(2) | |
if not os.path.exists(theDtd): | |
print("The DTD ({}) does not exist!".format(theDtd)) | |
exit(3) | |
print('Using DTD:', theDtd) | |
parser = etree.XMLParser(dtd_validation=True) | |
dtd = etree.DTD(open(theDtd)) | |
tree = etree.parse(args[0]) | |
valid = dtd.validate(tree) | |
if (valid): | |
print("XML was valid!") | |
else: | |
print("XML was not valid:") | |
print(dtd.error_log.filter_from_errors()) | |
if __name__ == '__main__': | |
main(sys.argv[1:]) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Can't parse xml file without the DTD fixing up the character entities first. Otherwise you get errors like Ø not recognised.
Is there a way to pass the external DTD file reference to the parser to say use this DTD?
This is so you can use an external DTD file on an xml file that doesn't have a reference to the DTD in its xml?