view sat/plugins/plugin_comp_ap_gateway/regex.py @ 3879:46930301f0c1

tools: renamed module `sat.tools.datetime` to `date.tools.xmpp_datetime` to avoid conflict with Python's standard lib
author Goffi <goffi@goffi.org>
date Wed, 31 Aug 2022 13:18:56 +0200
parents 381340b9a9ee
children
line wrap: on
line source

#!/usr/bin/env python3

# Libervia ActivityPub Gateway
# Copyright (C) 2009-2022 Jérôme Poisson (goffi@goffi.org)

# 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/>.

"""Various Regular Expression for AP gateway"""

import re

## "Signature" header parsing

# those expression have been generated with abnf-to-regex
# (https://github.com/aas-core-works/abnf-to-regexp)

# the base RFC 7320 ABNF rules come from https://github.com/EricGT/ABNF

# here is the ABNF file used:
# ---
# BWS = OWS
# OWS = *( SP / HTAB )
# tchar = "!" / "#" / "$" / "%" / "&" / "`" / "*" / "+" / "-" / "." / "^" / "_" / "\'" / "|" / "~" / DIGIT / ALPHA
# token = 1*tchar
# sig-param = token BWS "=" BWS ( token / quoted-string )
# quoted-string = DQUOTE *( qdtext / quoted-pair ) DQUOTE
# qdtext = HTAB / SP / "!" / %x23-5B ; '#'-'['
#  / %x5D-7E ; ']'-'~'
#  / obs-text
# quoted-pair = "\" ( HTAB / SP / VCHAR / obs-text )
# obs-text = %x80-FF
# ---

ows = '[ \t]*'
bws = f'{ows}'
obs_text = '[\\x80-\\xff]'
qdtext = f'([\t !#-\\[\\]-~]|{obs_text})'
quoted_pair = f'\\\\([\t !-~]|{obs_text})'
quoted_string = f'"({qdtext}|{quoted_pair})*"'
tchar = "([!#$%&`*+\\-.^_]|\\\\'|[|~0-9a-zA-Z])"
token = f'({tchar})+'
RE_SIG_PARAM = re.compile(
    f'(?P<key>{token}{bws})={bws}'
    f'((?P<uq_value>{token})|(?P<quoted_value>{quoted_string}))'
)


## Account/Mention

# FIXME: naive regex, should be approved following webfinger, but popular implementations
#   such as Mastodon use a very restricted subset
RE_ACCOUNT = re.compile(r"[a-zA-Z0-9._-]+@[a-zA-Z0-9-]+.[a-zA-Z0-9-]+")
RE_MENTION = re.compile(rf"(?<!\w)@{RE_ACCOUNT.pattern}\b")