test0908
/
django
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Fixed #6799 - added an `end_text` argument to `truncate_words`/`truncate_html_words`. 

This allows customizing the standard "..." end text. Yes, this is technically a
feature sneaking in after the deadline, but I just couldn't bring myself to punt
it again: we already used that excuse for not getting it into 1.1.

Thanks to Adam Fast and Travis Cline for work on this patch.

git-svn-id: http://code.djangoproject.com/svn/django/trunk@12431 bcc190cf-cafb-0310-a4f2-bffc1f526a37
This commit is contained in:
Jacob Kaplan-Moss 2010-02-14 18:36:48 +00:00
parent 7578981626
commit 1d078be448
2 changed files with 35 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

30
django/utils/text.py
View File

@ -1,5 +1,4 @@
import re
from django.conf import settings
from django.utils.encoding import force_unicode
from django.utils.functional import allow_lazy
from django.utils.translation import ugettext_lazy
@ -37,24 +36,25 @@ def wrap(text, width):
return u''.join(_generator())
wrap = allow_lazy(wrap, unicode)
def truncate_words(s, num):
"Truncates a string after a certain number of words."
def truncate_words(s, num, end_text='...'):
"""Truncates a string after a certain number of words. Takes an optional
argument of what should be used to notify that the string has been
truncated, defaults to ellipsis (...)"""
s = force_unicode(s)
length = int(num)
words = s.split()
if len(words) > length:
words = words[:length]
if not words[-1].endswith('...'):
words.append('...')
if not words[-1].endswith(end_text):
words.append(end_text)
return u' '.join(words)
truncate_words = allow_lazy(truncate_words, unicode)
def truncate_html_words(s, num):
"""
Truncates html to a certain number of words (not counting tags and
def truncate_html_words(s, num, end_text='...'):
"""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.
"""
html. Takes an optional argument of what should be used to notify that the
string has been truncated, defaults to ellipsis (...)."""
s = force_unicode(s)
length = int(num)
if length <= 0:
@ -65,7 +65,7 @@ def truncate_html_words(s, num):
re_tag = re.compile(r'<(/)?([^ ]+?)(?: (/)| .*?)?>')
# Count non-HTML words and keep note of open tags
pos = 0
ellipsis_pos = 0
end_text_pos = 0
words = 0
open_tags = []
while words <= length:
@ -78,11 +78,11 @@ def truncate_html_words(s, num):
# It's an actual non-HTML word
words += 1
if words == length:
ellipsis_pos = pos
end_text_pos = pos
continue
# Check for tag
tag = re_tag.match(m.group(0))
if not tag or ellipsis_pos:
if not tag or end_text_pos:
# Don't worry about non tags or tags after our truncate point
continue
closing_tag, tagname, self_closing = tag.groups()
@ -104,7 +104,9 @@ def truncate_html_words(s, num):
if words <= length:
# Don't try to close tags if we don't need to truncate
return s
out = s[:ellipsis_pos] + ' ...'
out = s[:end_text_pos]
if end_text:
out += ' ' + end_text
# Close any tags still open
for tag in open_tags:
out += '</%s>' % tag

20
tests/regressiontests/utils/tests.py
View File

@ -4,7 +4,7 @@ Tests for django.utils.
from unittest import TestCase
from django.utils import html, checksums
from django.utils import html, checksums, text
from django.utils.functional import SimpleLazyObject
import timesince
@ -244,6 +244,24 @@ class TestUtilsSimpleLazyObject(TestCase):
s3 = copy.deepcopy(s)
self.assertEqual(s3, complex_object())
class TestUtilsText(TestCase):
def test_truncate_words(self):
self.assertEqual(u'The quick brown fox jumped over the lazy dog.',
text.truncate_words(u'The quick brown fox jumped over the lazy dog.', 10))
self.assertEqual(u'The quick brown fox ...',
text.truncate_words('The quick brown fox jumped over the lazy dog.', 4))
self.assertEqual(u'The quick brown fox ....',
text.truncate_words('The quick brown fox jumped over the lazy dog.', 4, '....'))
self.assertEqual(u'<p><strong><em>The quick brown fox jumped over the lazy dog.</em></strong></p>',
text.truncate_html_words('<p><strong><em>The quick brown fox jumped over the lazy dog.</em></strong></p>', 10))
self.assertEqual(u'<p><strong><em>The quick brown fox ...</em></strong></p>',
text.truncate_html_words('<p><strong><em>The quick brown fox jumped over the lazy dog.</em></strong></p>', 4))
self.assertEqual(u'<p><strong><em>The quick brown fox ....</em></strong></p>',
text.truncate_html_words('<p><strong><em>The quick brown fox jumped over the lazy dog.</em></strong></p>', 4, '....'))
self.assertEqual(u'<p><strong><em>The quick brown fox</em></strong></p>',
text.truncate_html_words('<p><strong><em>The quick brown fox jumped over the lazy dog.</em></strong></p>', 4, None))
if __name__ == "__main__":
import doctest
doctest.testmod()