mirror of
https://github.com/zulip/zulip.git
synced 2025-11-04 05:53:43 +00:00
c863bb83a0
We were using Google's diff-match-patch library to diff HTML. The problem with that approach is that it is a text differ, not an HTML differ and so it ends up messing up the HTML tags. `lxml` is a safer option. Fixes: #7219.
26 lines
824 B
Python
26 lines
824 B
Python
import lxml
|
|
|
|
from lxml.html.diff import htmldiff
|
|
from typing import Optional, Text
|
|
|
|
def highlight_with_class(text, klass):
|
|
# type: (Text, Text) -> Text
|
|
return '<span class="%s">%s</span>' % (klass, text)
|
|
|
|
def highlight_html_differences(s1, s2, msg_id=None):
|
|
# type: (Text, Text, Optional[int]) -> Text
|
|
retval = htmldiff(s1, s2)
|
|
fragment = lxml.html.fromstring(retval) # type: ignore # https://github.com/python/typeshed/issues/525
|
|
|
|
for elem in fragment.cssselect('del'):
|
|
elem.tag = 'span'
|
|
elem.set('class', 'highlight_text_deleted')
|
|
|
|
for elem in fragment.cssselect('ins'):
|
|
elem.tag = 'span'
|
|
elem.set('class', 'highlight_text_inserted')
|
|
|
|
retval = lxml.html.tostring(fragment) # type: ignore # https://github.com/python/typeshed/issues/525
|
|
|
|
return retval
|