Put it in appname/templatetags/truncatehtml.py and load it with {% load truncatehtml %}, then for instance {{ some_story|truncatehtml:100 }} to truncate the story to 100 characters.
Tags are not counted in the length given, and character entities count as one character.
The filter should never break an open-tag text close-tag sequence without adding in the close tag. It will also preserve character entities. It won't sanitize the HTML, though: garbage in, garbage out.
There's a bit more info about how it works in a blog post I wrote.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 | from django import template
register = template.Library()
import re
tag_end_re = re.compile(r'(\w+)[^>]*>')
entity_end_re = re.compile(r'(\w+;)')
@register.filter
def truncatehtml(string, length, ellipsis='...'):
"""Truncate HTML string, preserving tag structure and character entities."""
length = int(length)
output_length = 0
i = 0
pending_close_tags = {}
while output_length < length and i < len(string):
c = string[i]
if c == '<':
# probably some kind of tag
if i in pending_close_tags:
# just pop and skip if it's closing tag we already knew about
i += len(pending_close_tags.pop(i))
else:
# else maybe add tag
i += 1
match = tag_end_re.match(string[i:])
if match:
tag = match.groups()[0]
i += match.end()
# save the end tag for possible later use if there is one
match = re.search(r'(</' + tag + '[^>]*>)', string[i:], re.IGNORECASE)
if match:
pending_close_tags[i + match.start()] = match.groups()[0]
else:
output_length += 1 # some kind of garbage, but count it in
elif c == '&':
# possible character entity, we need to skip it
i += 1
match = entity_end_re.match(string[i:])
if match:
i += match.end()
# this is either a weird character or just '&', both count as 1
output_length += 1
else:
# plain old characters
skip_to = string.find('<', i, i + length)
if skip_to == -1:
skip_to = string.find('&', i, i + length)
if skip_to == -1:
skip_to = i + length
# clamp
delta = min(skip_to - i,
length - output_length,
len(string) - i)
output_length += delta
i += delta
output = [string[:i]]
if output_length == length:
output.append(ellipsis)
for k in sorted(pending_close_tags.keys()):
output.append(pending_close_tags[k])
return "".join(output)
truncatehtml.is_safe = True
|
More like this
- Template tag - list punctuation for a list of items by shapiromatron 10 months, 3 weeks ago
- JSONRequestMiddleware adds a .json() method to your HttpRequests by cdcarter 11 months ago
- Serializer factory with Django Rest Framework by julio 1 year, 5 months ago
- Image compression before saving the new model / work with JPG, PNG by Schleidens 1 year, 6 months ago
- Help text hyperlinks by sa2812 1 year, 7 months ago
Comments
Better use of integrated tools Django.
#
Please login first before commenting.