Commit 1d078be4 authored by Jacob Kaplan-Moss's avatar Jacob Kaplan-Moss
Browse files

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
parent 75789816

django/utils/text.py

+16 −14
Original line number Diff line number Diff line 
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

tests/regressiontests/utils/tests.py

+19 −1
Original line number Diff line number Diff line
@@ -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()