mirror of
https://github.com/django/django.git
synced 2025-07-04 09:49:12 +00:00
unicode: Fixed #4662 -- Fixed a remaining ASCII assumption in
truncatewords_html(). Thanks, Ivan Sagalaev. git-svn-id: http://code.djangoproject.com/svn/django/branches/unicode@5533 bcc190cf-cafb-0310-a4f2-bffc1f526a37
This commit is contained in:
parent
9c5994743c
commit
daaa3a1dde
@ -59,7 +59,7 @@ def truncate_html_words(s, num):
|
|||||||
return u''
|
return u''
|
||||||
html4_singlets = ('br', 'col', 'link', 'base', 'img', 'param', 'area', 'hr', 'input')
|
html4_singlets = ('br', 'col', 'link', 'base', 'img', 'param', 'area', 'hr', 'input')
|
||||||
# Set up regular expressions
|
# Set up regular expressions
|
||||||
re_words = re.compile(r'&.*?;|<.*?>|([A-Za-z0-9][\w-]*)')
|
re_words = re.compile(r'&.*?;|<.*?>|(\w[\w-]*)', re.U)
|
||||||
re_tag = re.compile(r'<(/)?([^ ]+?)(?: (/)| .*?)?>')
|
re_tag = re.compile(r'<(/)?([^ ]+?)(?: (/)| .*?)?>')
|
||||||
# Count non-HTML words and keep note of open tags
|
# Count non-HTML words and keep note of open tags
|
||||||
pos = 0
|
pos = 0
|
||||||
|
@ -104,6 +104,9 @@ u'<p>one <a href="#">two - three <br>four</a> five</p>'
|
|||||||
>>> truncatewords_html(u'<p>one <a href="#">two - three <br>four</a> five</p>', 100)
|
>>> truncatewords_html(u'<p>one <a href="#">two - three <br>four</a> five</p>', 100)
|
||||||
u'<p>one <a href="#">two - three <br>four</a> five</p>'
|
u'<p>one <a href="#">two - three <br>four</a> five</p>'
|
||||||
|
|
||||||
|
>>> truncatewords_html(u'\xc5ngstr\xf6m was here', 1)
|
||||||
|
u'\xc5ngstr\xf6m ...'
|
||||||
|
|
||||||
>>> upper(u'Mixed case input')
|
>>> upper(u'Mixed case input')
|
||||||
u'MIXED CASE INPUT'
|
u'MIXED CASE INPUT'
|
||||||
|
|
||||||
|
Loading…
x
Reference in New Issue
Block a user