marcus/scour
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

Allow elements to be found via Document.getElementById() in the minidom document returned by scourXmlFile() (#68)

Browse source
This commit is contained in:
Eduard Braun 2016-08-25 21:13:09 +02:00 • committed by GitHub
parent 8d6301950b
commit 386d5d8656
3 changed files with 35 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

15
scour/scour.py
View file

@ -3126,7 +3126,20 @@ def scourXmlFile(filename, options=None):
with open(filename, "rb") as f:
in_string = f.read()
out_string = scourString(in_string, options)
return xml.dom.minidom.parseString(out_string.encode('utf-8'))
doc = xml.dom.minidom.parseString(out_string.encode('utf-8'))
# since minidom does not seem to parse DTDs properly
# manually declare all attributes with name "id" to be of type ID
# (otherwise things like doc.getElementById() won't work)
all_nodes = doc.getElementsByTagName("*")
for node in all_nodes:
try:
node.setIdAttribute('id')
except:
pass
return doc