waylan

"""
DocData

A Meta-Data handler for lightweight markup languages.

Note: This was an experiment which was rejected in favor of a different API.
See the better implementation here: <https://github.com/waylan/docdata>

An implementation of Meta-Data as defined by MultiMarkdown. However, it can
work with any lightweight markup language and the various keys can have

waylan

"""
HTML5Parser

The HTML5Parser **mostly** replicates the behavior and API of the
`htmlparser.HTMLParser` class. However, it uses the html5lib tokenizer
to parser the source HTML. Note that it only takes the raw tokens
and does not run the entire html5lib parser which normalizes the tokens,
etc. In other words, if invalid (improperly nested) elements exist in the
source HTML, they will be feed to HTML5Parser as they appear in the source
document.

waylan

import unittest 
import os
import markdown
import codecs
import difflib
try:
    import tidylib
except ImportError:
    tidylib = None

waylan

try:
    from html.parser import HTMLParser
except ImportError:
    from HTMLParser import HTMLParser
from enchant.checker import SpellChecker


class HTMLSpellChecker(HTMLParser):
    """
    Check the spelling of an HTML document using the given SpellChecker.

waylan

*.pyc

waylan

"""
backtick `*
escape \\.
stem ***
st **
em *
stem ___
st __
em _
linkstart ]

waylan

# -*- coding: utf-8 -*-
#
# HTMLTree
#
# An HTML Node Tree toolkit.
#
# --------------------------------------------------------------------
#
# Copyright (c) 2015 by Waylan Limberg. All rights reserved.
#

waylan

"""
A crazy Idea!

Just maybe, the way to parse HTML within a Markdown document is to run the document
through an HTML Parser first. Some parsers, like the HTMLParser included in the
Python Standard lib will properly parse the plain text not wrapped in HTML tags
as plain text and simply return it unaltered. The problem is with Markdown's
autolinks (`<foo@bar.com>` and `<http://example.com>`).

However, as of Python 2.7.3 and 3.2.2, the HTMLParser can now handle invalid HTML

waylan

from bs4.element import Tag, NavigableString


class Doc(Tag):
    """
    Dumby Document Root.
    
    This class provides a document root object without a parser.
    The document will need to be built mannually by adding Tags,
    NavigableStrings, Comments and the like. This class assumes

waylan

try:
    from HTMLParser import HTMLParser
except ImportError:
    from html.parser import HTMLParser


HTML_BLOCK = set([
    'p', 'div', 'h1', 'h2', 'h3', 'h4', 'h5', 'h6', 'blockquote',
    'pre', 'table', 'dl', 'ol', 'ul', 'script', 'noscript', 'form',
    'fieldset', 'iframe', 'math', 'hr', 'style', 'li', 'dt', 'dd',