contentdb/app/utils/markdown.py

102 lines
2.3 KiB
Python
Raw Normal View History

from functools import partial
2020-01-22 23:10:02 +01:00
import bleach
from bleach import Cleaner
from bleach.linkifier import LinkifyFilter
2021-02-02 21:05:24 +01:00
from bs4 import BeautifulSoup
2020-01-22 23:10:02 +01:00
from markdown import Markdown
from flask import Markup
# Based on
2020-01-22 23:10:02 +01:00
# https://github.com/Wenzil/mdx_bleach/blob/master/mdx_bleach/whitelist.py
#
# License: MIT
2020-01-22 23:10:02 +01:00
ALLOWED_TAGS = [
"h1", "h2", "h3", "h4", "h5", "h6", "hr",
"ul", "ol", "li",
"p",
"br",
"pre",
"code",
"blockquote",
"strong",
"em",
"a",
"img",
"table", "thead", "tbody", "tr", "th", "td",
"div", "span",
]
ALLOWED_CSS = [
"highlight", "codehilite",
"hll", "c", "err", "g", "k", "l", "n", "o", "x", "p", "ch", "cm", "cp", "cpf", "c1", "cs",
"gd", "ge", "gr", "gh", "gi", "go", "gp", "gs", "gu", "gt", "kc", "kd", "kn", "kp", "kr",
"kt", "ld", "m", "s", "na", "nb", "nc", "no", "nd", "ni", "ne", "nf", "nl", "nn", "nx",
"py", "nt", "nv", "ow", "w", "mb", "mf", "mh", "mi", "mo", "sa", "sb", "sc", "dl", "sd",
"s2", "se", "sh", "si", "sx", "sr", "s1", "ss", "bp", "fm", "vc", "vg", "vi", "vm", "il",
2020-01-22 23:10:02 +01:00
]
def allow_class(_tag, name, value):
return name == "class" and value in ALLOWED_CSS
2020-01-22 23:10:02 +01:00
ALLOWED_ATTRIBUTES = {
2021-02-02 21:05:24 +01:00
"h1": ["id"],
"h2": ["id"],
"h3": ["id"],
"h4": ["id"],
"a": ["href", "title"],
"img": ["src", "title", "alt"],
"code": allow_class,
"div": allow_class,
"span": allow_class,
2020-01-22 23:10:02 +01:00
}
ALLOWED_PROTOCOLS = ["http", "https", "mailto"]
2020-01-22 23:10:02 +01:00
md = None
2020-01-22 23:10:02 +01:00
2021-02-02 21:05:24 +01:00
2020-01-22 23:10:02 +01:00
def render_markdown(source):
html = md.convert(source)
cleaner = Cleaner(
tags=ALLOWED_TAGS,
attributes=ALLOWED_ATTRIBUTES,
protocols=ALLOWED_PROTOCOLS,
filters=[partial(LinkifyFilter, callbacks=bleach.linkifier.DEFAULT_CALLBACKS)])
return cleaner.clean(html)
2020-01-22 23:10:02 +01:00
2021-02-02 21:05:24 +01:00
2020-01-22 23:10:02 +01:00
def init_app(app):
global md
md = Markdown(extensions=app.config["FLATPAGES_MARKDOWN_EXTENSIONS"], output_format="html5")
2020-01-22 23:10:02 +01:00
@app.template_filter()
def markdown(source):
return Markup(render_markdown(source))
2021-02-02 21:05:24 +01:00
def get_headings(html: str):
soup = BeautifulSoup(html, "html.parser")
headings = soup.find_all(["h1", "h2", "h3"])
root = []
stack = []
for heading in headings:
this = { "link": heading.get("id") or "", "text": heading.text, "children": [] }
this_level = int(heading.name[1:]) - 1
while this_level <= len(stack):
stack.pop()
if len(stack) > 0:
stack[-1]["children"].append(this)
else:
root.append(this)
stack.append(this)
return root