def linkify(html):
links = set()
from .page import Page
def clean_link(attrs, new=False):
if (None, "href") not in attrs:
return None
href = attrs[(None, "href")]
thread_title = get_thread_title(href)
if thread_title is None:
_fnm, ext = os.path.splitext(urlparse(href).path)
if ext.lower() in img_exts:
attrs["_text"] = sanitize_html("<img src='{}'>".format(href))
else:
attrs["_text"] = sanitize_text(href)
else:
try:
# TODO: improve performance here
page = Page.find(thread_title)
attrs["_text"] = sanitize_text(page.name)
except PageNotFound:
attrs["_text"] = sanitize_text(title_to_name(thread_title))
links.add(thread_title)
return attrs
linker = bleach.Linker(
callbacks=[clean_link],
url_re=bleach.linkifier.build_url_re(tlds=["[a-z]+"]))
return links, normalize(linker.linkify(html))
def rich_text(text: str, excluded_tags=""):
"""
Processes markdown and cleans HTML in a text input.
"""
text = str(text)
linker = bleach.Linker(parse_email=True)
body_md = linker.linkify(markdown_compile(text, excluded_tags=excluded_tags))
return mark_safe(body_md)
def rich_text_snippet(text: str, **kwargs):
"""
Processes markdown and cleans HTML in a text input.
"""
text = str(text)
linker = bleach.Linker(
url_re=URL_RE,
email_re=EMAIL_RE,
callbacks=DEFAULT_CALLBACKS + ([truelink_callback, safelink_callback] if kwargs.get('safelinks', True) else [truelink_callback, abslink_callback]),
parse_email=True
)
body_md = linker.linkify(markdown_compile(text, snippet=True))
return mark_safe(body_md)
def markdown_compile_email(source):
linker = bleach.Linker(url_re=URL_RE, email_re=EMAIL_RE, parse_email=True)
return linker.linkify(
bleach.clean(
markdown.markdown(
source,
extensions=[
'markdown.extensions.sane_lists',
# 'markdown.extensions.nl2br' # disabled for backwards-compatibility
]),
tags=ALLOWED_TAGS,
attributes=ALLOWED_ATTRIBUTES,
protocols=ALLOWED_PROTOCOLS,
))
