<\/strong>|<\/?smallcaps>|<\/?uppercase>)', re.IGNORECASE)
hard_coded_bullets_re = re.compile(r'((?:(?:%s).*?[a-zA-Z].*?
\s*)+)' % '|'.join([re.escape(x) for x in DOTS]), re.DOTALL)
trailing_empty_content_re = re.compile(r'(?:(?: |\s|
)*?
\s*)+\Z')
del x # Temporary variable
def escape(html):
"""
Returns the given HTML with ampersands, quotes and angle brackets encoded.
"""
return mark_safe(force_unicode(html).replace('&', '&').replace('<', '<').replace('>', '>').replace('"', '"').replace("'", '''))
escape = allow_lazy(escape, unicode)
_base_js_escapes = (
('\\', r'\u005C'),
('\'', r'\u0027'),
('"', r'\u0022'),
('>', r'\u003E'),
('<', r'\u003C'),
('&', r'\u0026'),
('=', r'\u003D'),
('-', r'\u002D'),
(';', r'\u003B'),
(u'\u2028', r'\u2028'),
(u'\u2029', r'\u2029')
)
# Escape every ASCII character with a value less than 32.
_js_escapes = (_base_js_escapes +
tuple([('%c' % z, '\\u%04X' % z) for z in range(32)]))
def escapejs(value):
"""Hex encodes characters for use in JavaScript strings."""
for bad, good in _js_escapes:
value = mark_safe(force_unicode(value).replace(bad, good))
return value
escapejs = allow_lazy(escapejs, unicode)
def conditional_escape(html):
"""
Similar to escape(), except that it doesn't operate on pre-escaped strings.
"""
if isinstance(html, SafeData):
return html
else:
return escape(html)
def linebreaks(value, autoescape=False):
"""Converts newlines into and
s."""
value = normalize_newlines(value)
paras = re.split('\n{2,}', value)
if autoescape:
paras = [u'
%s
' % escape(p).replace('\n', '
') for p in paras]
else:
paras = [u'%s
' % p.replace('\n', '
') for p in paras]
return u'\n\n'.join(paras)
linebreaks = allow_lazy(linebreaks, unicode)
def strip_tags(value):
"""Returns the given HTML with all tags stripped."""
return re.sub(r'<[^>]*?>', '', force_unicode(value))
strip_tags = allow_lazy(strip_tags)
def strip_spaces_between_tags(value):
"""Returns the given HTML with spaces between tags removed."""
return re.sub(r'>\s+<', '><', force_unicode(value))
strip_spaces_between_tags = allow_lazy(strip_spaces_between_tags, unicode)
def strip_entities(value):
"""Returns the given HTML with all entities (&something;) stripped."""
return re.sub(r'&(?:\w+|#\d+);', '', force_unicode(value))
strip_entities = allow_lazy(strip_entities, unicode)
def fix_ampersands(value):
"""Returns the given HTML with all unencoded ampersands encoded correctly."""
return unencoded_ampersands_re.sub('&', force_unicode(value))
fix_ampersands = allow_lazy(fix_ampersands, unicode)
def smart_urlquote(url):
"""Quotes an URL if it isn't already quoted."""
# Handle IDN before quoting.
scheme, netloc, path, query, fragment = urlparse.urlsplit(url)
try:
netloc = netloc.encode('idna') # IDN -> ACE
except UnicodeError: # invalid domain part
pass
else:
url = urlparse.urlunsplit((scheme, netloc, path, query, fragment))
# An URL is considered unquoted if it contains no % character, or if it
# contains a % not followed by two hexadecimal digits. See #9655.
if '%' not in url or unquoted_percents_re.search(url):
# See http://bugs.python.org/issue2637
url = urllib.quote(smart_str(url), safe='!*\'();:@&=+$,/?#[]~')
return force_unicode(url)
def urlize(text, trim_url_limit=None, nofollow=False, autoescape=False):
"""
Converts any URLs in text into clickable links.
Works on http://, https://, www. links, and also on links ending in one of
the original seven gTLDs (.com, .edu, .gov, .int, .mil, .net, and .org) or
a two-letter ccTLD. Links can have trailing punctuation (periods, commas,
close-parens) and leading punctuation (opening parens) and it'll still do
the right thing.
If trim_url_limit is not None, the URLs in link text longer than this limit
will truncated to trim_url_limit-3 characters and appended with an elipsis.
If nofollow is True, the URLs in link text will get a rel="nofollow"
attribute.
If autoescape is True, the link text and URLs will get autoescaped.
"""
trim_url = lambda x, limit=trim_url_limit: limit is not None and (len(x) > limit and ('%s...' % x[:max(0, limit - 3)])) or x
safe_input = isinstance(text, SafeData)
words = word_split_re.split(force_unicode(text))
for i, word in enumerate(words):
match = None
if '.' in word or '@' in word or ':' in word:
# Deal with punctuation.
lead, middle, trail = '', word, ''
for punctuation in TRAILING_PUNCTUATION:
if middle.endswith(punctuation):
middle = middle[:-len(punctuation)]
trail = punctuation + trail
for opening, closing in WRAPPING_PUNCTUATION:
if middle.startswith(opening):
middle = middle[len(opening):]
lead = lead + opening
# Keep parentheses at the end only if they're balanced.
if (middle.endswith(closing)
and middle.count(closing) == middle.count(opening) + 1):
middle = middle[:-len(closing)]
trail = closing + trail
# Make URL we want to point to.
url = None
nofollow_attr = ' rel="nofollow"' if nofollow else ''
if simple_url_re.match(middle):
url = smart_urlquote(middle)
elif simple_url_2_re.match(middle):
url = smart_urlquote('http://%s' % middle)
elif not ':' in middle and simple_email_re.match(middle):
local, domain = middle.rsplit('@', 1)
domain = domain.encode('idna')
url = 'mailto:%s@%s' % (local, domain)
nofollow_attr = ''
# Make link.
if url:
trimmed = trim_url(middle)
if autoescape and not safe_input:
lead, trail = escape(lead), escape(trail)
url, trimmed = escape(url), escape(trimmed)
middle = '%s' % (url, nofollow_attr, trimmed)
words[i] = mark_safe('%s%s%s' % (lead, middle, trail))
else:
if safe_input:
words[i] = mark_safe(word)
elif autoescape:
words[i] = escape(word)
elif safe_input:
words[i] = mark_safe(word)
elif autoescape:
words[i] = escape(word)
return u''.join(words)
urlize = allow_lazy(urlize, unicode)
def clean_html(text):
"""
Clean the given HTML. Specifically, do the following:
* Convert and to and .
* Encode all ampersands correctly.
* Remove all "target" attributes from tags.
* Remove extraneous HTML, such as presentational tags that open and
immediately close and
.
* Convert hard-coded bullets into HTML unordered lists.
* Remove stuff like "
", but only if it's at the
bottom of the text.
"""
from django.utils.text import normalize_newlines
text = normalize_newlines(force_unicode(text))
text = re.sub(r'<(/?)\s*b\s*>', '<\\1strong>', text)
text = re.sub(r'<(/?)\s*i\s*>', '<\\1em>', text)
text = fix_ampersands(text)
# Remove all target="" attributes from tags.
text = link_target_attribute_re.sub('\\1', text)
# Trim stupid HTML such as
.
text = html_gunk_re.sub('', text)
# Convert hard-coded bullets into HTML unordered lists.
def replace_p_tags(match):
s = match.group().replace(u'', u'')
for d in DOTS:
s = s.replace(u'%s' % d, u'
')
return u'' % s
text = hard_coded_bullets_re.sub(replace_p_tags, text)
# Remove stuff like "
", but only if it's at the bottom
# of the text.
text = trailing_empty_content_re.sub(u'', text)
return text
clean_html = allow_lazy(clean_html, unicode)