def test_truncate_html_words(self):
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
),
)
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))
def test_old_truncate_html_words(self):
with warnings.catch_warnings(record=True) as w:
warnings.simplefilter("always")
self.assertEqual(
"<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(
"<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(
"<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(
"<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
),
)
self.assertGreater(len(w), 0)
def test_old_truncate_html_words(self):
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))
def test_old_truncate_html_words(self):
with warnings.catch_warnings(record=True) as w:
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))
self.assertEqual(len(w), 4)
def test_old_truncate_html_words(self):
with warnings.catch_warnings(record=True) as w:
warnings.simplefilter("always")
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))
self.assertGreater(len(w), 0)
def summary(self):
"""Returns a summary of the blog post."""
match = re.search("<!--.*cut.*-->", self.body)
if match:
return self.body[:match.start(0)]
else:
return text.truncate_html_words(self.body, config.summary_length)
def yvcut(string, o):
n = len(string)
s = postcut(string, o)
if len(s) == len(string):
return text.truncate_html_words(string, 256)
else:
return s
def yvcut(string, o):
n = len(string)
s = postcut(string, o)
if len(s) == len(string):
return text.truncate_html_words(string, 256)
else:
return s
def truncate_entry(entry, words=100):
end_text = '... <a href="%s">more</a>' % entry.get_absolute_url()
content = entry.html_content
try:
return truncate_html_words(content, int(words), end_text=end_text)
except ValueError: # invalid literal for int()
return value # Fail silently.
def truncatewords_html_remove_end(value,arg):
arg_list = arg.split(',')
try:
length = int(arg_list[0])
except ValueError:
return value
return mark_safe(truncate_html_words(value,length,''))
def readmore(value, arg):
""" Add a Readmore link to the content"""
from django.utils.text import truncate_html_words
length = 100
readmore = _('Read more')
end_text = '...<a href="' + arg + '" style="font-size: 75%;">' + readmore + '</a>'
return truncate_html_words(value, length, end_text)
def render_excerpt(post):
from bs4 import BeautifulSoup
from django.utils import text, html
VALID_TAGS = ['p']
content = post.content
has_more = content.find('<!-- more -->')
if has_more == -1:
has_more = content.find('<!--more-->') # Might be Wordpress style
if has_more > -1:
content = content[:has_more]
content = re.sub(r"(\[caption)([^\]]*)(])(.*)(\[/caption\])", '', content)
content = re.sub(r'(\[source((code)*? lang(uage)*?)*?=([\'"]*?)(python)([\'"]*?)])(.*?)(\[/source(code)*?\])', '', content, flags=re.MULTILINE|re.DOTALL)
content = re.sub(r"(\[caption)([^\]]*)(])(.*)(\[/caption\])", '', content)
content = re.sub(r"(\[youtube:)([^\]]*)(])", '', content)
soup = BeautifulSoup(content, "html.parser")
for tag in soup.findAll(True):
if tag.name not in VALID_TAGS:
tag.replaceWithChildren()
stripped_html = force_unicode(soup.renderContents())
return force_unicode(text.truncate_html_words(stripped_html, 50))
def find_post_content(feed_obj, entry):
"""Find the correct content field for a post."""
try:
content = entry["content"][0]["value"]
except (IndexError, KeyError):
content = entry.get("description") or entry.get("summary") or ""
if '<img' not in content:
# if there's no image and the we add an image to the feed
def build_img(img_dict):
try:
# The tag is url instead of src... pain
img = "<img src='%s'" % img_dict.get("url")
except KeyError:
return ''
img_dict.pop('url')
for attr in img_dict.items():
img += "%s='%s'" % (attr[0], attr[1])
img += ">"
return img
try:
thumbnail = entry["media_thumbnail"][0]
img = build_img(thumbnail)
except (IndexError, KeyError):
img = ""
content = img + content
try:
content = truncate_html_words(content, conf.DEFAULT_ENTRY_WORD_LIMIT)
except UnicodeDecodeError:
content = ""
return feed_content_optimizer.optimize(content)
def get_teaser(self):
if self.description:
teaser = formatter(self.description, filter_name=self.markup)
else:
teaser = self.rendered_content
return truncate_html_words(teaser, 50)
def control_trunc(value, max_words):
if BLOG['truncater'] in value:
return value[:value.find(BLOG['truncater'])]
if wordcount(value) > max_words :
return truncate_html_words(value, max_words)
else:
return value
def truncate_html_post(post_html):
"""truncates html if it is longer than 100 words"""
post_html = truncate_html_words(post_html, 5)
post_html = '<div class="truncated-post">' + post_html
post_html += '<span class="expander">(<a>' + _("more") + "</a>)</span>"
post_html += '<div class="clearfix"></div></div>'
return post_html
def truncate_html_post(post_html):
"""truncates html if it is longer than 100 words"""
post_html = truncate_html_words(post_html, 5)
post_html = '<div class="truncated-post">' + post_html
post_html += '<span class="expander">(<a>' + _('more') + '</a>)</span>'
post_html += '<div class="clearfix"></div></div>'
return post_html
def summary(self):
"""Returns a summary of the blog post."""
match = re.search("<!--.*cut.*-->", self.body)
if match:
return self.body[:match.start(0)]
else:
return text.truncate_html_words(self.body, config.summary_length)
def find_post_content(feed_obj, entry):
"""Find the correct content field for a post."""
try:
content = entry["content"][0]["value"]
except (IndexError, KeyError):
content = entry.get("description") or entry.get("summary") or ""
if '<img' not in content:
# if there's no image and the we add an image to the feed
def build_img(img_dict):
try:
# The tag is url instead of src... pain
img = "<img src='%s'" % img_dict.get("url")
except KeyError:
return ''
img_dict.pop('url')
for attr in img_dict.items():
img += "%s='%s'" % (attr[0], attr[1])
img += ">"
return img
try:
thumbnail = entry["media_thumbnail"][0]
img = build_img(thumbnail)
except (IndexError, KeyError):
img = ""
content = img + content
try:
content = truncate_html_words(content, conf.DEFAULT_ENTRY_WORD_LIMIT)
except UnicodeDecodeError:
content = ""
return feed_content_optimizer.optimize(content)
def truncatewords_html(value, length):
try:
from django.utils.text import Truncator
except ImportError:
from django.utils.text import truncate_html_words # Django < 1.6
else:
truncate_html_words = lambda value, length: Truncator(value).words(length, html=True)
return truncate_html_words(value, int(length))
def render_summary(post):
"""Return the post's summary rendered to HTML."""
renderer = get_renderer(post)
match = re.search(CUT_SEPARATOR_REGEX, post.body)
if match:
return renderer(post.body[: match.start(0)])
else:
return text.truncate_html_words(renderer(clean_content(post.body)), config.summary_length)
def excerpt(html, num, end_text='...'):
"""Return excerpt of html data.
"""
if truncate_html_words:
excerpt = truncate_html_words(html, num, end_text)
else:
excerpt = html
return excerpt
def excerpt(html, num, end_text='...'):
"""Return excerpt of html data.
"""
if truncate_html_words:
excerpt = truncate_html_words(html, num, end_text)
else:
excerpt = html
return excerpt
def truncatewords_link(value, size, obj):
"""Truncates a string to the given size
using the dots, and if it oversize the given length, is shows
a Read More link"""
content = {"value": truncate_html_words(value, size)}
words = value.split()
if len(words) > size:
content["obj"] = obj
return content
def truncatewords_link(value, size, obj):
"""Truncates a string to the given size
using the dots, and if it oversize the given length, is shows
a Read More link"""
content = {"value": truncate_html_words(value, size)}
words = value.split()
if len(words) > size:
content["obj"] = obj
return content
def truncatewords_html(value, length):
try:
from django.utils.text import Truncator
except ImportError:
from django.utils.text import truncate_html_words # Django < 1.6
else:
truncate_html_words = lambda value, length: Truncator(value).words(
length, html=True)
return truncate_html_words(value, int(length))
def render_summary(post):
"""Return the post's summary rendered to HTML."""
renderer = get_renderer(post)
match = re.search(CUT_SEPARATOR_REGEX, post.body)
if match:
return renderer(post.body[:match.start(0)])
else:
return text.truncate_html_words(renderer(clean_content(post.body)),
config.summary_length)
def get_teaser(self, truncate=30):
if self.description:
teaser = formatter(self.description, filter_name=self.markup)
else:
teaser = self.rendered_content
if truncate:
return truncate_html_words(teaser, truncate)
else:
return teaser
def truncatehtml(string, length):
"""
Truncate the text to a certain length, honoring html.
Usage:
{{ my_variable|truncatehtml:250 }}
"""
return text.truncate_html_words(string, length)
def _get_teaser(self):
"""
Retrieve some part of the article or the article's description.
"""
if not self._teaser:
if len(self.description.strip()):
self._teaser = self.description
else:
self._teaser = truncate_html_words(self.rendered_content, WORD_LIMIT)
return self._teaser
def truncate_html_words(value, num_words):
"""Backwords compatibility shim."""
try:
# Django 1.4+
from django.utils.text import Truncator
except ImportError:
# Django 1.3
from django.utils.text import truncate_html_words
return truncate_html_words(value, num_words)
else:
return Truncator(value).words(num_words, html=True)
def _get_teaser(self):
"""
Retrieve some part of the article or the article's description.
"""
if not self._teaser:
if len(self.description.strip()):
self._teaser = self.description
else:
self._teaser = truncate_html_words(self.rendered_content, WORD_LIMIT)
return self._teaser
def truncatehtml(string, length):
"""
Truncate the text to a certain length, honoring html.
Usage:
{{ my_variable|truncatehtml:250 }}
"""
return text.truncate_html_words(string, length)
def truncatewords_html(value, arg):
"""
Truncates HTML after a certain number of words.
Argument: Number of words to truncate after.
"""
from django.utils.text import truncate_html_words
try:
length = int(arg)
except ValueError: # invalid literal for int()
return value # Fail silently.
return truncate_html_words(value, length)
def truncatewords_html(value, arg):
"""
Truncates HTML after a certain number of words.
Argument: Number of words to truncate after.
"""
from django.utils.text import truncate_html_words
try:
length = int(arg)
except ValueError: # invalid literal for int()
return value # Fail silently.
return truncate_html_words(value, length)
def truncatewords_html(value, arg):
"""
Truncates HTML after a certain number of words.
Argument: Number of words to truncate after.
Newlines in the HTML are preserved.
"""
try:
length = int(arg)
except ValueError: # invalid literal for int()
return value # Fail silently.
return truncate_html_words(value, length)
def render(self, context):
from django.utils.text import truncate_html_words
length = self.length.resolve(context)
context.push()
original = self.nodelist.render(context)
output = truncate_html_words(original, length)
context.pop()
if len(output) < len(original):
context.push()
output = output + self.more.render(context)
context.pop()
return output
def format_history_text(text):
"""Run history text through some cleaning and add ellipsis if it's too long."""
full = mark_safe(text)
if text.startswith("This was part of a ballot set with:"):
full = urlize_ietf_docs(full)
full = mark_safe(keep_spacing(linebreaksbr(urlize(sanitize_html(full)))))
snippet = truncate_html_words(full, 25)
if snippet != full:
return mark_safe(
u'<div class="snippet">%s<span class="show-all">[show all]</span></div><div style="display:none" class="full">%s</div>'
% (snippet, full))
return full
def getBlurb(request,blurbID,wordCount):
"""
Retunr the conetnt of the blurb identified by the ID.
Will return up to work count. IF wourd count is 0
return the entire blurb.
"""
theBlurb = Blurb.objects.get(id=blurbID)
if int(wordCount) == 0:
crap = theBlurb.crap
else:
from django.utils.text import truncate_html_words
crap = truncate_html_words(theBlurb.crap, wordCount)
return HttpResponse(crap)
def short_desc(request, news_id):
"""
view untuk menampilkan penjelasan singkat berita dengan format txt
untuk id => news_id
"""
news = get_object_or_404(News, id=news_id, active=True)
return render_to_response('news/short_desc.html',
{"lon": news.location.x,
"lat": news.location.y,
"title": news.title,
"description": truncate_html_words(news.content_html, 10),
"icon": "abc.png",
"icon_width": 50,
"icon_height": 50},
context_instance=RequestContext(request))
def lead_in(self):
"""
Returns a truncated version of the excerpt or main content with an
appended 'read more...' link
"""
if self.excerpt:
html = self.excerpt
else:
html = truncate_html_words(self.body, 50, end_text='')
permalink = self.permalink(text=ugettext("read more…"), title=ugettext("Read full article"))
content = "%s %s" % (html, permalink)
if self.markup == Entry.MARKDOWN:
return mark_safe(markdown(self.excerpt, ['codehilite']))
elif self.markup == Entry.TEXTILE:
return mark_safe(textile.textile(content))
def __unicode__(self):
if self.slug:
return self.slug
else:
return strip_tags(truncate_html_words(self.content, 5))
def item_description(self, item):
return truncate_html_words(item.body, 25)
def truncatehtml(string, length):
return text.truncate_html_words(string, length)
def item_description(self, item):
return text.truncate_html_words(item.content, 50)
def truncatewords_html(value, length):
from django.utils.text import truncate_html_words
return truncate_html_words(value, int(length))
def item_description(self, item):
return truncate_html_words(item.body,25)
def truncatewords_html(value, length):
from django.utils.text import truncate_html_words
return truncate_html_words(value, int(length))
