jyapayne/glymur
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Adjusted some comments in XML box parsing. #213

Browse source
This commit is contained in:
John Evans 2014-04-04 13:54:58 -04:00
commit 2e1af15cb1
1 changed files with 4 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

5
glymur/jp2box.py
View file

@ -2738,6 +2738,7 @@ class XMLBox(Jp2kBox):
# Try to search for <?xml and go from there.
decl_start = read_buffer.find(b'<?xml')
if decl_start <= -1:
# Nope, that's not it. All is lost.
msg = 'A problem was encountered while parsing an XML box:'
msg += '\n\n\t"{0}"\n\nNo XML was retrieved.'
warnings.warn(msg.format(str(err)))
@ -2752,14 +2753,16 @@ class XMLBox(Jp2kBox):
warnings.warn(msg, UserWarning)
# Strip out any trailing nulls, as they can foul up XML parsing.
# Remove any byte order markers.
text = text.rstrip(chr(0))
# Remove any byte order markers.
if u'\ufeff' in text:
msg = 'An illegal BOM (byte order marker) was detected and '
msg += 'removed from the XML contents in the box starting at byte '
msg += 'offset {0}'.format(offset)
warnings.warn(msg)
text = text.replace(u'\ufeff', '')
# Remove any encoding declaration.
if text.startswith('<?xml version="1.0" encoding="UTF-8"?>'):
text = text[38:]