<\/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')
def escape(text):
"""
Returns the given text with ampersands, quotes and angle brackets encoded for use in HTML.
"""
return mark_safe(force_text(text).replace('&', '&').replace('<', '<').replace('>', '>').replace('"', '"').replace("'", '''))
escape = allow_lazy(escape, six.text_type)
_js_escapes = {
ord('\\'): '\\u005C',
ord('\''): '\\u0027',
ord('"'): '\\u0022',
ord('>'): '\\u003E',
ord('<'): '\\u003C',
ord('&'): '\\u0026',
ord('='): '\\u003D',
ord('-'): '\\u002D',
ord(';'): '\\u003B',
ord('\u2028'): '\\u2028',
ord('\u2029'): '\\u2029'
}
# Escape every ASCII character with a value less than 32.
_js_escapes.update((ord('%c' % z), '\\u%04X' % z) for z in range(32))
def escapejs(value):
"""Hex encodes characters for use in JavaScript strings."""
return mark_safe(force_text(value).translate(_js_escapes))
escapejs = allow_lazy(escapejs, six.text_type)
def conditional_escape(text):
"""
Similar to escape(), except that it doesn't operate on pre-escaped strings.
"""
if hasattr(text, '__html__'):
return text.__html__()
else:
return escape(text)
def format_html(format_string, *args, **kwargs):
"""
Similar to str.format, but passes all arguments through conditional_escape,
and calls 'mark_safe' on the result. This function should be used instead
of str.format or % interpolation to build up small HTML fragments.
"""
args_safe = map(conditional_escape, args)
kwargs_safe = dict((k, conditional_escape(v)) for (k, v) in six.iteritems(kwargs))
return mark_safe(format_string.format(*args_safe, **kwargs_safe))
def format_html_join(sep, format_string, args_generator):
"""
A wrapper of format_html, for the common case of a group of arguments that
need to be formatted using the same format string, and then joined using
'sep'. 'sep' is also passed through conditional_escape.
'args_generator' should be an iterator that returns the sequence of 'args'
that will be passed to format_html.
Example:
format_html_join('\n', "{0} {1}", ((u.first_name, u.last_name)
for u in users))
"""
return mark_safe(conditional_escape(sep).join(
format_html(format_string, *tuple(args))
for args in args_generator))
def linebreaks(value, autoescape=False):
"""Converts newlines into and
s."""
value = normalize_newlines(value)
paras = re.split('\n{2,}', value)
if autoescape:
paras = ['
%s
' % escape(p).replace('\n', '
') for p in paras]
else:
paras = ['%s
' % p.replace('\n', '
') for p in paras]
return '\n\n'.join(paras)
linebreaks = allow_lazy(linebreaks, six.text_type)
class MLStripper(HTMLParser):
def __init__(self):
HTMLParser.__init__(self)
self.reset()
self.fed = []
def handle_data(self, d):
self.fed.append(d)
def handle_entityref(self, name):
self.fed.append('&%s;' % name)
def handle_charref(self, name):
self.fed.append('&#%s;' % name)
def get_data(self):
return ''.join(self.fed)
def strip_tags(value):
"""Returns the given HTML with all tags stripped."""
s = MLStripper()
try:
s.feed(value)
s.close()
except HTMLParseError:
return value
else:
return s.get_data()
strip_tags = allow_lazy(strip_tags)
def remove_tags(html, tags):
"""Returns the given HTML with given tags removed."""
tags = [re.escape(tag) for tag in tags.split()]
tags_re = '(%s)' % '|'.join(tags)
starttag_re = re.compile(r'<%s(/?>|(\s+[^>]*>))' % tags_re, re.U)
endtag_re = re.compile('' % tags_re)
html = starttag_re.sub('', html)
html = endtag_re.sub('', html)
return html
remove_tags = allow_lazy(remove_tags, six.text_type)
def strip_spaces_between_tags(value):
"""Returns the given HTML with spaces between tags removed."""
return re.sub(r'>\s+<', '><', force_text(value))
strip_spaces_between_tags = allow_lazy(strip_spaces_between_tags, six.text_type)
def strip_entities(value):
"""Returns the given HTML with all entities (&something;) stripped."""
return re.sub(r'&(?:\w+|#\d+);', '', force_text(value))
strip_entities = allow_lazy(strip_entities, six.text_type)
def fix_ampersands(value):
"""Returns the given HTML with all unencoded ampersands encoded correctly."""
return unencoded_ampersands_re.sub('&', force_text(value))
fix_ampersands = allow_lazy(fix_ampersands, six.text_type)
def smart_urlquote(url):
"Quotes a URL if it isn't already quoted."
# Handle IDN before quoting.
try:
scheme, netloc, path, query, fragment = urlsplit(url)
try:
netloc = netloc.encode('idna').decode('ascii') # IDN -> ACE
except UnicodeError: # invalid domain part
pass
else:
url = urlunsplit((scheme, netloc, path, query, fragment))
except ValueError:
# invalid IPv6 URL (normally square brackets in hostname part).
pass
url = unquote(force_str(url))
# See http://bugs.python.org/issue2637
url = quote(url, safe=b'!*\'();:@&=+$,/?#[]~')
return force_text(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).
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.
"""
def trim_url(x, limit=trim_url_limit):
if limit is None or len(x) <= limit:
return x
return '%s...' % x[:max(0, limit - 3)]
safe_input = isinstance(text, SafeData)
words = word_split_re.split(force_text(text))
for i, word in enumerate(words):
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)
try:
domain = domain.encode('idna').decode('ascii')
except UnicodeError:
continue
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 ''.join(words)
urlize = allow_lazy(urlize, six.text_type)
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.
"""
text = normalize_newlines(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('', '')
for d in DOTS:
s = s.replace('%s' % d, '
')
return '' % 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('', text)
return text
clean_html = allow_lazy(clean_html, six.text_type)
def avoid_wrapping(value):
"""
Avoid text wrapping in the middle of a phrase by adding non-breaking
spaces where there previously were normal spaces.
"""
return value.replace(" ", "\xa0")