Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

Ensure pmlz output is converting unicode characters to character codes.

Browse Source
This commit is contained in:
John Schember 2009-05-09 14:43:52 -04:00
parent 02c7fb0209
commit 2df4d01923
1 changed files with 8 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
src/calibre/ebooks/pml/pmlconverter.py
View File

@ -88,7 +88,7 @@ HTML_PML_RULES = [
(re.compile('<a.*?href="(?P<target>#.+?).*?">(?P<text>)</a>', re.DOTALL), lambda match: '\\q="%s"%s\\q' % (match.group('target'), match.group('text'))), (re.compile('<a.*?href="(?P<target>#.+?).*?">(?P<text>)</a>', re.DOTALL), lambda match: '\\q="%s"%s\\q' % (match.group('target'), match.group('text'))),
#(re.compile('<img.*?src="images/(?P<name>.+?)".*?>'), lambda match: '\\m="%s"' % match.group('name')), #(re.compile('<img.*?src="images/(?P<name>.+?)".*?>'), lambda match: '\\m="%s"' % match.group('name')),
(re.compile('<img.*?src="(?P<name>.+?)".*?>(.*?</img>)*'), lambda match: '\\m="%s"' % image_name(match.group('name').strip('\x00'))), (re.compile('<img.*?src="(?P<name>.+?)".*?>(.*?</img>)*'), lambda match: '\\m="%s"' % image_name(match.group('name').strip('\x00'))),
#(re.compile('&#(?P<num>\d\d\d\d);'), lambda match: '\\U%s' % int(match.group('num'))), (re.compile('&#(?P<num>\d\d\d\d);'), lambda match: '\\U%s' % int(match.group('num'))),
(re.compile('&#(?P<num>\d\d\d);'), lambda match: '\\a%s' % match.group('num')), (re.compile('&#(?P<num>\d\d\d);'), lambda match: '\\a%s' % match.group('num')),
(re.compile('<small .*?>(?P<text>.+?)</small>', re.DOTALL), lambda match: '\\k%s\\k' % match.group('text')), (re.compile('<small .*?>(?P<text>.+?)</small>', re.DOTALL), lambda match: '\\k%s\\k' % match.group('text')),
(re.compile('<small>(?P<text>.+?)</small>', re.DOTALL), lambda match: '\\k%s\\k' % match.group('text')), (re.compile('<small>(?P<text>.+?)</small>', re.DOTALL), lambda match: '\\k%s\\k' % match.group('text')),
@ -163,5 +163,12 @@ def html_to_pml(html):
pml += body pml += body
# Replace symbols outside of cp1512 wtih \Uxxxx # Replace symbols outside of cp1512 wtih \Uxxxx
chars = set(pml)
unichars = []
for c in chars:
if ord(c) > 128:
unichars.append(c)
for u in unichars:
pml = pml.replace(u, '\U%s' % hex(ord(u))[2:].rjust(4, '0'))
return pml return pml