Varia's website
https://varia.zone
You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
100 lines
3.1 KiB
100 lines
3.1 KiB
1 week ago
|
'''
|
||
|
|
Abbreviation Extension for Python-Markdown
|
||
|
|
==========================================
|
||
|
|
|
||
|
|
This extension adds abbreviation handling to Python-Markdown.
|
||
|
|
|
||
|
|
See <https://Python-Markdown.github.io/extensions/abbreviations>
|
||
|
|
for documentation.
|
||
|
|
|
||
|
|
Oringinal code Copyright 2007-2008 [Waylan Limberg](http://achinghead.com/) and
|
||
|
|
[Seemant Kulleen](http://www.kulleen.org/)
|
||
|
|
|
||
|
|
All changes Copyright 2008-2014 The Python Markdown Project
|
||
|
|
|
||
|
|
License: [BSD](https://opensource.org/licenses/bsd-license.php)
|
||
|
|
|
||
|
|
'''
|
||
|
|
|
||
|
|
from . import Extension
|
||
|
|
from ..blockprocessors import BlockProcessor
|
||
|
|
from ..inlinepatterns import InlineProcessor
|
||
|
|
from ..util import AtomicString
|
||
|
|
import re
|
||
|
|
import xml.etree.ElementTree as etree
|
||
|
|
|
||
|
|
|
||
|
|
class AbbrExtension(Extension):
|
||
|
|
""" Abbreviation Extension for Python-Markdown. """
|
||
|
|
|
||
|
|
def extendMarkdown(self, md):
|
||
|
|
""" Insert AbbrPreprocessor before ReferencePreprocessor. """
|
||
|
|
md.parser.blockprocessors.register(AbbrPreprocessor(md.parser), 'abbr', 16)
|
||
|
|
|
||
|
|
|
||
|
|
class AbbrPreprocessor(BlockProcessor):
|
||
|
|
""" Abbreviation Preprocessor - parse text for abbr references. """
|
||
|
|
|
||
|
|
RE = re.compile(r'^[*]\[(?P<abbr>[^\]]*)\][ ]?:[ ]*\n?[ ]*(?P<title>.*)$', re.MULTILINE)
|
||
|
|
|
||
|
|
def test(self, parent, block):
|
||
|
|
return True
|
||
|
|
|
||
|
|
def run(self, parent, blocks):
|
||
|
|
'''
|
||
|
|
Find and remove all Abbreviation references from the text.
|
||
|
|
Each reference is set as a new AbbrPattern in the markdown instance.
|
||
|
|
|
||
|
|
'''
|
||
|
|
block = blocks.pop(0)
|
||
|
|
m = self.RE.search(block)
|
||
|
|
if m:
|
||
|
|
abbr = m.group('abbr').strip()
|
||
|
|
title = m.group('title').strip()
|
||
|
|
self.parser.md.inlinePatterns.register(
|
||
|
|
AbbrInlineProcessor(self._generate_pattern(abbr), title), 'abbr-%s' % abbr, 2
|
||
|
|
)
|
||
|
|
if block[m.end():].strip():
|
||
|
|
# Add any content after match back to blocks as separate block
|
||
|
|
blocks.insert(0, block[m.end():].lstrip('\n'))
|
||
|
|
if block[:m.start()].strip():
|
||
|
|
# Add any content before match back to blocks as separate block
|
||
|
|
blocks.insert(0, block[:m.start()].rstrip('\n'))
|
||
|
|
return True
|
||
|
|
# No match. Restore block.
|
||
|
|
blocks.insert(0, block)
|
||
|
|
return False
|
||
|
|
|
||
|
|
def _generate_pattern(self, text):
|
||
|
|
'''
|
||
|
|
Given a string, returns an regex pattern to match that string.
|
||
|
|
|
||
|
|
'HTML' -> r'(?P<abbr>[H][T][M][L])'
|
||
|
|
|
||
|
|
Note: we force each char as a literal match (in brackets) as we don't
|
||
|
|
know what they will be beforehand.
|
||
|
|
|
||
|
|
'''
|
||
|
|
chars = list(text)
|
||
|
|
for i in range(len(chars)):
|
||
|
|
chars[i] = r'[%s]' % chars[i]
|
||
|
|
return r'(?P<abbr>\b%s\b)' % (r''.join(chars))
|
||
|
|
|
||
|
|
|
||
|
|
class AbbrInlineProcessor(InlineProcessor):
|
||
|
|
""" Abbreviation inline pattern. """
|
||
|
|
|
||
|
|
def __init__(self, pattern, title):
|
||
|
|
super().__init__(pattern)
|
||
|
|
self.title = title
|
||
|
|
|
||
|
|
def handleMatch(self, m, data):
|
||
|
|
abbr = etree.Element('abbr')
|
||
|
|
abbr.text = AtomicString(m.group('abbr'))
|
||
|
|
abbr.set('title', self.title)
|
||
|
|
return abbr, m.start(0), m.end(0)
|
||
|
|
|
||
|
|
|
||
|
|
def makeExtension(**kwargs): # pragma: no cover
|
||
|
|
return AbbrExtension(**kwargs)
|