Skip to content

Commit

Permalink
Browse files Browse the repository at this point in the history
Fixed #2027 -- added truncatewords_html filter that respects HTML tag…
…s whilst

truncating. Patch from SmileyChris.


git-svn-id: http://code.djangoproject.com/svn/django/trunk@4468 bcc190cf-cafb-0310-a4f2-bffc1f526a37
  • Loading branch information
malcolmt committed Feb 10, 2007
1 parent 2a14daf commit 5a0b72a
Show file tree
Hide file tree
Showing 3 changed files with 90 additions and 0 deletions.
16 changes: 16 additions & 0 deletions django/template/defaultfilters.py
Expand Up @@ -119,6 +119,21 @@ def truncatewords(value, arg):
value = str(value)
return truncate_words(value, length)

def truncatewords_html(value, arg):
"""
Truncates HTML after a certain number of words
Argument: Number of words to truncate after
"""
from django.utils.text import truncate_html_words
try:
length = int(arg)
except ValueError: # invalid literal for int()
return value # Fail silently.
if not isinstance(value, basestring):
value = str(value)
return truncate_html_words(value, length)

def upper(value):
"Converts a string into all uppercase"
return value.upper()
Expand Down Expand Up @@ -534,6 +549,7 @@ def pprint(value):
register.filter(timeuntil)
register.filter(title)
register.filter(truncatewords)
register.filter(truncatewords_html)
register.filter(unordered_list)
register.filter(upper)
register.filter(urlencode)
Expand Down
60 changes: 60 additions & 0 deletions django/utils/text.py
Expand Up @@ -41,6 +41,66 @@ def truncate_words(s, num):
words.append('...')
return ' '.join(words)

def truncate_html_words(s, num):
"""
Truncates html to a certain number of words (not counting tags and comments).
Closes opened tags if they were correctly closed in the given html.
"""
length = int(num)
if length <= 0:
return ''
html4_singlets = ('br', 'col', 'link', 'base', 'img', 'param', 'area', 'hr', 'input')
# Set up regular expressions
re_words = re.compile(r'&.*?;|<.*?>|([A-Za-z0-9][\w-]*)')
re_tag = re.compile(r'<(/)?([^ ]+?)(?: (/)| .*?)?>')
# Count non-HTML words and keep note of open tags
pos = 0
ellipsis_pos = 0
words = 0
open_tags = []
while words <= length:
m = re_words.search(s, pos)
if not m:
# Checked through whole string
break
pos = m.end(0)
if m.group(1):
# It's an actual non-HTML word
words += 1
if words == length:
ellipsis_pos = pos
continue
# Check for tag
tag = re_tag.match(m.group(0))
if not tag or ellipsis_pos:
# Don't worry about non tags or tags after our truncate point
continue
closing_tag, tagname, self_closing = tag.groups()
tagname = tagname.lower() # Element names are always case-insensitive
if self_closing or tagname in html4_singlets:
pass
elif closing_tag:
# Check for match in open tags list
try:
i = open_tags.index(tagname)
except ValueError:
pass
else:
# SGML: An end tag closes, back to the matching start tag, all unclosed intervening start tags with omitted end tags
open_tags = open_tags[i+1:]
else:
# Add it to the start of the open tags list
open_tags.insert(0, tagname)
if words <= length:
# Don't try to close tags if we don't need to truncate
return s
out = s[:ellipsis_pos] + ' ...'
# Close any tags still open
for tag in open_tags:
out += '</%s>' % tag
# Return string
return out

def get_valid_filename(s):
"""
Returns the given string converted to a string that can be used for a clean
Expand Down
14 changes: 14 additions & 0 deletions tests/regressiontests/defaultfilters/tests.py
Expand Up @@ -87,6 +87,20 @@
>>> truncatewords('A sentence with a few words in it', 'not a number')
'A sentence with a few words in it'
>>> truncatewords_html('<p>one <a href="#">two - three <br>four</a> five</p>', 0)
''
>>> truncatewords_html('<p>one <a href="#">two - three <br>four</a> five</p>', 2)
'<p>one <a href="#">two ...</a></p>'
>>> truncatewords_html('<p>one <a href="#">two - three <br>four</a> five</p>', 4)
'<p>one <a href="#">two - three <br>four ...</a></p>'
>>> truncatewords_html('<p>one <a href="#">two - three <br>four</a> five</p>', 5)
'<p>one <a href="#">two - three <br>four</a> five</p>'
>>> truncatewords_html('<p>one <a href="#">two - three <br>four</a> five</p>', 100)
'<p>one <a href="#">two - three <br>four</a> five</p>'
>>> upper('Mixed case input')
'MIXED CASE INPUT'
Expand Down

0 comments on commit 5a0b72a

Please sign in to comment.