Ticket #5025: 5025.diff

django/template/defaultfilters.py

@@ -239 +239 @@
 title.is_safe = True
 title = stringfilter(title)
 
+def truncatechars(value, arg):
+    """
+    Truncates a string after a certain number of characters.
+    
+    Argument: Number of characters to truncate after.
+    """
+    from django.utils.text import truncate_chars
+    try:
+        length = int(arg)
+    except ValueError: # Invalid literal for int().
+        return value # Fail silently.
+    return truncate_chars(value, length)
+truncatechars.is_safe = True
+truncatechars = stringfilter(truncatechars)
+
 def truncatewords(value, arg):
     """
     Truncates a string after a certain number of words.

django/utils/text.py

@@ -1 +1 @@
 import re
+import unicodedata
 from django.utils.encoding import force_unicode
 from django.utils.functional import allow_lazy
 from django.utils.translation import ugettext_lazy, ugettext as _
@@ -36 +37 @@
     return u''.join(_generator())
 wrap = allow_lazy(wrap, unicode)
 
+def truncate_chars(s, num, end_text=ugettext_lazy('...')):
+    """Truncates a string to be no longer than the specified number of
+    characters. Takes an optional argument of what should be used to notify
+    that the string has been truncated, defaulting to a translatable string of
+    an ellipsis (...)
+    """
+    s = unicodedata.normalize('NFC', force_unicode(s))
+    length = int(num)
+    end_text = unicodedata.normalize('NFC', force_unicode(end_text))
+
+    # Calculate the length to truncate to (max length - end_text length)
+    truncate_len = length
+    for char in end_text:
+        if not unicodedata.combining(char):
+            truncate_len -= 1
+            if truncate_len == 0:
+                break
+
+    s_len = 0
+    end_index = None
+    for i, char in enumerate(s):
+        if unicodedata.combining(char):
+            # Don't consider combining characters as adding to the string
+            # length
+            continue
+        s_len += 1
+        if end_index is None and s_len > truncate_len:
+            end_index = i
+        if s_len > length:
+            # Return the truncated string
+            return u'%s%s' % (s[:end_index or 0], end_text)
+
+    # Return the original string since no truncation was necessary
+    return s
+truncate_chars = allow_lazy(truncate_chars, unicode)
+
 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

docs/ref/templates/builtins.txt

@@ -2024 +2024 @@
 
 If ``value`` is ``"my first post"``, the output will be ``"My First Post"``.
 
+.. templatefilter:: truncatechars
+
+truncatechars
+~~~~~~~~~~~~~
+
+Truncates a string if it is longer than the specified number of characters.
+Truncated strings will end with a translatable ellipsis sequence ("...").
+
+**Argument:** Number of characters to truncate to
+
+For example::
+
+    {{ value|truncatechars:9 }}
+
+If ``value`` is ``"Joel is a slug"``, the output will be ``"Joel i..."``.
+
 .. templatefilter:: truncatewords
 
 truncatewords

docs/releases/1.4.txt

@@ -60 +60 @@
 ``template.Library`` to ease the creation of template tags that store some
 data in a specified context variable.
 
+``truncatechars`` template filter
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Added a filter which truncates a string to be no longer than the specified
+number of characters. Truncated strings end with a translatable ellipsis
+sequence ("...").
+
 .. _backwards-incompatible-changes-1.4:
 
 Backwards incompatible changes in 1.4

tests/regressiontests/utils/text.py

@@ +1 @@
+# -*- coding: utf-8 -*-
 import unittest
 
 from django.utils import text
 
 class TestUtilsText(unittest.TestCase):
 
+    def test_truncate_chars(self):
+        self.assertEqual(u'The quick brown fox jumped over the lazy dog.',
+            text.truncate_chars(u'The quick brown fox jumped over the lazy dog.', 100))
+        self.assertEqual(u'The quick brown fox ...',
+            text.truncate_chars('The quick brown fox jumped over the lazy dog.', 23))
+        self.assertEqual(u'The quick brown fo.....',
+            text.truncate_chars('The quick brown fox jumped over the lazy dog.', 23, '.....'))
+        
+        # Ensure that we normalize our unicode data first
+        nfc = u'o\xfco\xfco\xfco\xfc'
+        nfd = u'ou\u0308ou\u0308ou\u0308ou\u0308'
+        self.assertEqual(u'oüoüoüoü', text.truncate_chars(nfc, 8))
+        self.assertEqual(u'oüoüoüoü', text.truncate_chars(nfd, 8))
+        self.assertEqual(u'oü...', text.truncate_chars(nfc, 5))
+        self.assertEqual(u'oü...', text.truncate_chars(nfd, 5))
+        
+        # Ensure the final length is calculated correctly when there are
+        # combining characters with no precomposed form, and that combining
+        # characters are not split up.
+        self.assertEqual(u'-B\u030A...',
+            text.truncate_chars(u'-B\u030AB\u030A----8', 5))
+        self.assertEqual(u'-B\u030AB\u030A-...',
+            text.truncate_chars(u'-B\u030AB\u030A----8', 7))
+        self.assertEqual(u'-B\u030AB\u030A----8',
+            text.truncate_chars(u'-B\u030AB\u030A----8', 8))
+
+        # Ensure the length of the end text is correctly calculated when it
+        # contains combining characters with no precomposed form.
+        self.assertEqual(u'---B\u030A',
+            text.truncate_chars(u'-----', 4, end_text=u'B\u030A'))
+        self.assertEqual(u'-----',
+            text.truncate_chars(u'-----', 5, end_text=u'B\u030A'))
+
+        # Make a best effort to shorten to the desired length, but requesting
+        # a length shorter than the ellipsis shouldn't break
+        self.assertEqual(u'...', text.truncate_chars(u'asdf', 1))
+
     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))