Fixed #19496 -- Added truncatechars_html filter.

Thanks esevece for the suggestion and  Nick Sandford and Martin Warne
for the inital work on the patch.

django/template/defaultfilters.py

@@ -279,6 +279,23 @@ def truncatechars(value, arg):
     return Truncator(value).chars(length)
 
 
+@register.filter(is_safe=True)
+@stringfilter
+def truncatechars_html(value, arg):
+    """
+    Truncates HTML after a certain number of chars.
+
+    Argument: Number of chars to truncate after.
+
+    Newlines in the HTML are preserved.
+    """
+    try:
+        length = int(arg)
+    except ValueError:  # invalid literal for int()
+        return value  # Fail silently.
+    return Truncator(value).chars(length, html=True)
+
+
 @register.filter(is_safe=True)
 @stringfilter
 def truncatewords(value, arg):

django/utils/text.py

@@ -24,6 +24,7 @@ capfirst = allow_lazy(capfirst, six.text_type)
 
 # Set up regular expressions
 re_words = re.compile(r'<.*?>|((?:\w[-\w]*|&.*?;)+)', re.U | re.S)
+re_chars = re.compile(r'<.*?>|(.)', re.U | re.S)
 re_tag = re.compile(r'<(/)?([^ ]+?)(?:(\s*/)| .*?)?>', re.S)
 re_newlines = re.compile(r'\r\n|\r')  # Used in normalize_newlines
 re_camel_case = re.compile(r'(((?<=[a-z])[A-Z])|([A-Z](?![A-Z]|$)))')
@@ -82,7 +83,7 @@ class Truncator(SimpleLazyObject):
             return text
         return '%s%s' % (text, truncate)
 
-    def chars(self, num, truncate=None):
+    def chars(self, num, truncate=None, html=False):
         """
         Returns the text truncated to be no longer than the specified number
         of characters.
@@ -101,7 +102,15 @@ class Truncator(SimpleLazyObject):
                 truncate_len -= 1
                 if truncate_len == 0:
                     break
+        if html:
+            return self._truncate_html(length, truncate, text, truncate_len, False)
+        return self._text_chars(length, truncate, text, truncate_len)
+    chars = allow_lazy(chars)
 
+    def _text_chars(self, length, truncate, text, truncate_len):
+        """
+        Truncates a string after a certain number of chars.
+        """
         s_len = 0
         end_index = None
         for i, char in enumerate(text):
@@ -119,7 +128,6 @@ class Truncator(SimpleLazyObject):
 
         # Return the original string since no truncation was necessary
         return text
-    chars = allow_lazy(chars)
 
     def words(self, num, truncate=None, html=False):
         """
@@ -129,7 +137,7 @@ class Truncator(SimpleLazyObject):
         """
         length = int(num)
         if html:
-            return self._html_words(length, truncate)
+            return self._truncate_html(length, truncate, self._wrapped, length, True)
         return self._text_words(length, truncate)
     words = allow_lazy(words)
 
@@ -145,40 +153,45 @@ class Truncator(SimpleLazyObject):
             return self.add_truncation_text(' '.join(words), truncate)
         return ' '.join(words)
 
-    def _html_words(self, length, truncate):
+    def _truncate_html(self, length, truncate, text, truncate_len, words):
         """
-        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.
+        Truncates HTML to a certain number of chars (not counting tags and
+        comments), or, if words is True, then to a certain number of words.
+        Closes opened tags if they were correctly closed in the given HTML.
 
         Newlines in the HTML are preserved.
         """
-        if length <= 0:
+        if words and length <= 0:
             return ''
+
         html4_singlets = (
             'br', 'col', 'link', 'base', 'img',
             'param', 'area', 'hr', 'input'
         )
-        # Count non-HTML words and keep note of open tags
+
+        # Count non-HTML chars/words and keep note of open tags
         pos = 0
         end_text_pos = 0
-        words = 0
+        current_len = 0
         open_tags = []
-        while words <= length:
-            m = re_words.search(self._wrapped, pos)
+
+        regex = re_words if words else re_chars
+
+        while current_len <= length:
+            m = regex.search(text, 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:
+                # It's an actual non-HTML word or char
+                current_len += 1
+                if current_len == truncate_len:
                     end_text_pos = pos
                 continue
             # Check for tag
             tag = re_tag.match(m.group(0))
-            if not tag or end_text_pos:
+            if not tag or current_len >= truncate_len:
                 # Don't worry about non tags or tags after our truncate point
                 continue
             closing_tag, tagname, self_closing = tag.groups()
@@ -199,10 +212,10 @@ class Truncator(SimpleLazyObject):
             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 self._wrapped
-        out = self._wrapped[:end_text_pos]
+
+        if current_len <= length:
+            return text
+        out = text[:end_text_pos]
         truncate_text = self.add_truncation_text('', truncate)
         if truncate_text:
             out += truncate_text

docs/ref/templates/builtins.txt

@@ -2172,6 +2172,26 @@ For example::
 
 If ``value`` is ``"Joel is a slug"``, the output will be ``"Joel i..."``.
 
+.. templatefilter:: truncatechars_html
+
+truncatechars_html
+^^^^^^^^^^^^^^^^^^
+
+.. versionadded:: 1.7
+
+Similar to :tfilter:`truncatechars`, except that it is aware of HTML tags. Any
+tags that are opened in the string and not closed before the truncation point
+are closed immediately after the truncation.
+
+For example::
+
+    {{ value|truncatechars_html:9 }}
+
+If ``value`` is ``"<p>Joel is a slug</p>"``, the output will be
+``"<p>Joel i...</p>"``.
+
+Newlines in the HTML content will be preserved.
+
 .. templatefilter:: truncatewords
 
 truncatewords

docs/releases/1.7.txt

@@ -657,7 +657,7 @@ Templates
   * :func:`django.shortcuts.render()`
   * :func:`django.shortcuts.render_to_response()`
 
-* The :tfilter:`time` filter now accepts timzone-related :ref:`format
+* The :tfilter:`time` filter now accepts timezone-related :ref:`format
   specifiers <date-and-time-formatting-specifiers>` ``'e'``, ``'O'`` , ``'T'``
   and ``'Z'`` and is able to digest :ref:`time-zone-aware
   <naive_vs_aware_datetimes>` ``datetime`` instances performing the expected
@@ -668,6 +668,9 @@ Templates
   otherwise. It also now accepts an optional ``using`` keyword argument to
   control which cache it uses.
 
+* The new :tfilter:`truncatechars_html` filter truncates a string to be no
+  longer than the specified number of characters, taking HTML into account.
+
 Requests
 ^^^^^^^^
 

tests/defaultfilters/tests.py

@@ -13,8 +13,8 @@ from django.template.defaultfilters import (
     linebreaks_filter, linenumbers, ljust, lower, make_list,
     phone2numeric_filter, pluralize, removetags, rjust, slice_filter, slugify,
     stringformat, striptags, time, timesince_filter, timeuntil_filter, title,
-    truncatewords, truncatewords_html, unordered_list, upper, urlencode,
-    urlize, urlizetrunc, wordcount, wordwrap, yesno,
+    truncatechars_html, truncatewords, truncatewords_html, unordered_list,
+    upper, urlencode, urlize, urlizetrunc, wordcount, wordwrap, yesno,
 )
 from django.test import TestCase
 from django.utils import six
@@ -195,6 +195,23 @@ class DefaultFiltersTests(TestCase):
             '&#x00bf;C&oacute;mo est&aacute;?</i>', 3),
             '<i>Buenos d&iacute;as! &#x00bf;C&oacute;mo ...</i>')
 
+    def test_truncatechars_html(self):
+        self.assertEqual(truncatechars_html(
+            '<p>one <a href="#">two - three <br>four</a> five</p>', 0), '...')
+        self.assertEqual(truncatechars_html('<p>one <a href="#">two - '
+            'three <br>four</a> five</p>', 6),
+            '<p>one...</p>')
+        self.assertEqual(truncatechars_html(
+            '<p>one <a href="#">two - three <br>four</a> five</p>', 11),
+            '<p>one <a href="#">two ...</a></p>')
+        self.assertEqual(truncatechars_html(
+            '<p>one <a href="#">two - three <br>four</a> five</p>', 100),
+            '<p>one <a href="#">two - three <br>four</a> five</p>')
+        self.assertEqual(truncatechars_html(
+            '<b>\xc5ngstr\xf6m</b> was here', 5), '<b>\xc5n...</b>')
+        self.assertEqual(truncatechars_html(
+            'a<b>b</b>c', 3), 'a<b>b</b>c')
+
     def test_upper(self):
         self.assertEqual(upper('Mixed case input'), 'MIXED CASE INPUT')
         # lowercase e umlaut