Ticket #1919: truncate_words.diff

django/utils/text.py

@@ -36 +36 @@
     return u''.join(_generator())
 wrap = allow_lazy(wrap, unicode)
 
+word_re = re.compile(r'\S+', re.UNICODE)
 def truncate_words(s, num):
     "Truncates a string after a certain number of words."
     s = force_unicode(s)
     length = int(num)
-    words = s.split()
-    if len(words) > length:
-        words = words[:length]
-        if not words[-1].endswith('...'):
-            words.append('...')
-    return u' '.join(words)
+    if length < 1:
+        return u''
+    for count, match in enumerate(word_re.finditer(s)):
+        if count + 1 == length: # count is 0-based
+            end = match.end()
+            if end < len(s):
+                s = s[:end]
+                if not s.endswith('...'):
+                    s += ' ...'
+            break
+    return s
 truncate_words = allow_lazy(truncate_words, unicode)
 
 def truncate_html_words(s, num):

tests/regressiontests/defaultfilters/tests.py

@@ -98 +98 @@
 >>> truncatewords(u'A sentence with a few words in it', 'not a number')
 u'A sentence with a few words in it'
 
+>>> truncatewords(u'Double-spaced  sentence  with  a  few  words', 2)
+u'Double-spaced  sentence ...'
+
+>>> truncatewords(u'  Two leading spaces for this sentence', 3)
+u'  Two leading spaces ...'
+
+>>> truncatewords(u'Some text\non two lines', 4)
+u'Some text\non two ...'
+
 >>> truncatewords_html(u'<p>one <a href="#">two - three <br>four</a> five</p>', 0)
 u''