lib/libxml2
1
0
Fork 0
mirror of https://gitlab.gnome.org/GNOME/libxml2.git synced 2025-10-24 13:33:01 +03:00
Code Activity

html: Ignore U+0000 in body text

Browse Source 
Align with HTML5. Fixes #908.
This commit is contained in:
Nick Wellnhofer
2025-05-07 14:32:42 +02:00
parent a1e83b2401
commit f3a080bc48
6 changed files with 29 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
tools/genHtml5LibTests.py
View File

@@ -43,6 +43,9 @@ for filename in sorted(glob.glob('../html5lib-tests/tokenizer/*.test')):
output = ''
for token in test['output']:
if token[1] == '\0':
continue
output += token[0] + '\n'
if token[0] == 'DOCTYPE':
@@ -61,7 +64,11 @@ for filename in sorted(glob.glob('../html5lib-tests/tokenizer/*.test')):
output = re.sub(r'\\u([A-Fa-f0-9]{4})',
lambda m: chr(int(m[1], 16)),
output)
output = re.sub(r'\x00', '\uFFFD', output)
# The HTML5 spec splits handling of U+0000 across
# tokenizer and tree builder. We already ignore
# U+0000 in body text when tokenizing.
output = re.sub(r'\x00', '', output)
for state in test.get('initialStates', ['Data state']):
state_no = state_map.get(state)