legalmd/legalmd/legal_token.py

154 lines
3.8 KiB
Python

# legalmd: Markdown-based legal markup
# Copyright © 2019 Lee Yingtong Li (RunasSudo)
#
# 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 <https://www.gnu.org/licenses/>.
import re
import mistletoe
mistletoe.block_token.remove_token(mistletoe.block_token.BlockCode)
class Heading(mistletoe.block_token.BlockToken):
pattern = re.compile(r'(#{1,6})\s*([0-9A-Z]+)\s+(.+)')
def __init__(self, match):
self.level, self.label, content = match
self.children = mistletoe.span_token.tokenize_inner(content)
@classmethod
def start(cls, line):
return cls.pattern.match(line)
@classmethod
def read(cls, lines):
line = next(lines)
match = cls.pattern.match(line)
level = len(match.group(1))
label = match.group(2)
content = match.group(3)
if content == '***':
content = '★★★'
return level, label, content
mistletoe.block_token.remove_token(mistletoe.block_token.Heading)
mistletoe.block_token.add_token(Heading)
class Subrules(mistletoe.block_token.BlockToken):
pattern = re.compile(r'\t*\(([0-9A-Za-z–]+)\)\s+.')
def __init__(self, children):
self.children = children
@classmethod
def start(cls, line):
return cls.pattern.match(line)
@classmethod
def read(cls, lines):
children = []
while True:
lines.anchor()
try:
line = next(lines)
except StopIteration:
break
if len(line.strip()) == 0:
continue
lines.reset()
if not SubrulesItem.start(line):
break
children.append(SubrulesItem(*SubrulesItem.read(lines)))
return children
mistletoe.block_token.add_token(Subrules)
class SubrulesItem(mistletoe.block_token.BlockToken):
pattern = re.compile(r'(\t*)(\([0-9A-Za-z–]+\))?\s*(.+)')
def __init__(self, level, label, children):
self.level = level
self.label = label
self.children = children
@classmethod
def start(cls, line):
match = cls.pattern.match(line)
if not match.group(1) and not match.group(2):
# Neither an indent nor a label
return False
return True
@classmethod
def read(cls, lines):
line = next(lines)
lead_in, label, content = cls.pattern.match(line).group(1, 2, 3)
if content == '***':
content = '★★★'
level = len(lead_in)
children = mistletoe.span_token.tokenize_inner(content)
if label is None:
level -= 1
return level, label, children
class Note(mistletoe.block_token.BlockToken):
pattern = re.compile(r'([0-9A-Z ]+):\s+(.+)')
def __init__(self, match):
self.label, content = match
self.children = mistletoe.span_token.tokenize_inner(content)
@classmethod
def start(cls, line):
return cls.pattern.match(line)
@classmethod
def read(cls, lines):
line = next(lines)
match = cls.pattern.match(line)
label, content = match.group(1, 2)
label = label[0].upper() + label[1:].lower()
return label, content
mistletoe.block_token.add_token(Note)
class Definition(mistletoe.block_token.BlockToken):
pattern = re.compile(r'\*\*\*(.+)\*\*\*(:|.*means)')
def __init__(self, match):
self.children = mistletoe.span_token.tokenize_inner(match)
@classmethod
def start(cls, line):
return cls.pattern.match(line)
@classmethod
def read(cls, lines):
return next(lines).rstrip('\n')
mistletoe.block_token.add_token(Definition)