roundabout,
created on Sunday, 2 February 2025, 19:34:31 (1738524871),
received on Sunday, 2 February 2025, 19:36:58 (1738525018)
Author identity: vlad <vlad.muntoiu@gmail.com>
28efe5148f90064c56a41b53146aad3a315ad013
ampoule_ssg/markdown.py
@@ -1,3 +1,26 @@
"""
This is a parser for a Markdown-like language, but it isn't compatible with
the CommonMark specification; check doc/enduser/Formatting messages.md for
its syntax.
Roundabout - git hosting for everyone <https://roundabout-host.com>
Copyright (C) 2023-2025 Roundabout developers <root@roundabout-host.com>
This program is free software: you can redistribute it and/or modify
it under the terms of the GNU Affero General Public License as published by
the Free Software Foundation, either version 3 of the License, or
(at your option) any later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU Affero General Public License for more details.
You should have received a copy of the GNU Affero General Public License
along with this program. If not, see <http://www.gnu.org/licenses/>.
"""
import re
import bs4 as beautifulsoup
import sys
@@ -12,10 +35,14 @@ def only_chars(string, chars):
inline_regex = r"""
(?P<imageFlag>!?) \[ (?P<urlText>[^\[\]]*) \] \((?P<urlDestination>[^\(\)]*)\) # hyperlink or media
|
<(?P<urlDestination2>[^<>]*)> # autolink
|
(?P<em>\*{1,7}) (?P<textEm>(?:\\\*|[^*])*) (?P=em) # emphasis with * not requiring space on either side
|
(?:^|\s)(?P<em2>_{1,7}) (?P<textEm2>(?:\\.|[^*])*) (?P=em2)(?=\s|$) # emphasis with _ requiring space on at least one side
|
[``] (?P<textCode2>(?:\\[``]|[^``])*) [``] # inline code (2 backticks)
|
[`] (?P<textCode>(?:\\[`]|[^`])*) [`] # inline code
|
(?P<strike>~{2}) (?P<textStrike>(?:\\[~]|[^~])*) (~{2}) # strikethrough
@@ -278,6 +305,8 @@ def parse_line(source):
tokens.append(Emphasis(i.group("textEm2"), len(i.group("em2"))))
if i.group("textCode"):
tokens.append(Code(i.group("textCode")))
if i.group("textCode2"):
tokens.append(Code(i.group("textCode2")))
if i.group("strike"):
tokens.append(Strikethrough(i.group("textStrike")))
if i.group("diff"):
@@ -287,6 +316,17 @@ def parse_line(source):
tokens.append(Image(i.group("urlText"), i.group("urlDestination")))
else:
tokens.append(Link(i.group("urlText"), i.group("urlDestination")))
if i.group("urlDestination2"):
if "://" not in i.group("urlDestination2"):
url_text = i.group("urlDestination2").partition(":")[2] # remove tel, mailto, sms prefixes
url_destination = i.group("urlDestination2")
if url_destination.startswith("mailto:"):
url_destination = url_destination.replace("@", "@") # prevent email harvesting
url_text = url_text.replace("@", "@") # prevent protocol injection
else:
url_text = url_destination = i.group("urlDestination2")
tokens.append(Link(url_text, url_destination))
tokens.append(source[lookup:])
@@ -347,9 +387,7 @@ def tokenise(source):
i += 1
marker_length = len(lines[i].split(".", 1)[0]) + 1
while i < len(lines) and lines[i].strip() and not re.match(r"^ ?\d+\.", lines[i]):
if re.match(r"^ \d+\.", lines[i]):
marker_length = 2
inner_content += lines[i][marker_length:] + "\n"
inner_content += lines[i][2:] + "\n"
i += 1
content.append(ListItem(inner_content))