Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-07 18:24:30 -04:00
Code Issues Packages Projects Releases Wiki Activity

Fix html5 conversion parser not handling ascii control chars

Browse Source
This commit is contained in:
Kovid Goyal 2013-10-25 14:22:05 +05:30
parent 62d042d9d4
commit d3352aeec9
2 changed files with 8 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
src/calibre/ebooks/oeb/parse_utils.py
View File

@ -91,7 +91,11 @@ def html5_parse(data, max_nesting_depth=100):
with warnings.catch_warnings(): with warnings.catch_warnings():
warnings.simplefilter('ignore') warnings.simplefilter('ignore')
try:
data = html5lib.parse(data, treebuilder='lxml').getroot() data = html5lib.parse(data, treebuilder='lxml').getroot()
except ValueError:
from calibre.utils.cleantext import clean_xml_chars
data = html5lib.parse(clean_xml_chars(data), treebuilder='lxml').getroot()
# Check that the asinine HTML 5 algorithm did not result in a tree with # Check that the asinine HTML 5 algorithm did not result in a tree with
# insane nesting depths # insane nesting depths

4
src/calibre/ebooks/oeb/polish/tests/parsing.py
View File

@ -94,8 +94,10 @@ def space_characters(test, parse_function):
root = parse_function(markup) root = parse_function(markup)
err = 'form feed character not converted, parsed markup:\n' + etree.tostring(root) err = 'form feed character not converted, parsed markup:\n' + etree.tostring(root)
test.assertNotIn('\u000c', root.xpath('//*[local-name()="p"]')[0].text, err) test.assertNotIn('\u000c', root.xpath('//*[local-name()="p"]')[0].text, err)
markup = '<html><p>\u000b\u000c</p>' markup = '<html><p>a\u000b\u000c</p>'
root = parse_function(markup) # Should strip non XML safe control code \u000b root = parse_function(markup) # Should strip non XML safe control code \u000b
test.assertNotIn('\u000b', root.xpath('//*[local-name()="p"]')[0].text, err)
test.assertNotIn('\u000c', root.xpath('//*[local-name()="p"]')[0].text, err)
def case_insensitive_element_names(test, parse_function): def case_insensitive_element_names(test, parse_function):
markup = '<HTML><P> </p>' markup = '<HTML><P> </p>'