third_party/markdown/blockparser.py

# markdown is released under the BSD license
# Copyright 2007, 2008 The Python Markdown Project (v. 1.7 and later)
# Copyright 2004, 2005, 2006 Yuri Takhteyev (v. 0.2-1.6b)
# Copyright 2004 Manfred Stienstra (the original version)
# 
# All rights reserved.
# 
# Redistribution and use in source and binary forms, with or without
# modification, are permitted provided that the following conditions are met:
# 
# *   Redistributions of source code must retain the above copyright
#     notice, this list of conditions and the following disclaimer.
# *   Redistributions in binary form must reproduce the above copyright
#     notice, this list of conditions and the following disclaimer in the
#     documentation and/or other materials provided with the distribution.
# *   Neither the name of the <organization> nor the
#     names of its contributors may be used to endorse or promote products
#     derived from this software without specific prior written permission.
# 
# THIS SOFTWARE IS PROVIDED BY THE PYTHON MARKDOWN PROJECT ''AS IS'' AND ANY
# EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
# WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
# DISCLAIMED. IN NO EVENT SHALL ANY CONTRIBUTORS TO THE PYTHON MARKDOWN PROJECT
# BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
# CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
# SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
# INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
# CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
# POSSIBILITY OF SUCH DAMAGE.


from __future__ import unicode_literals
from __future__ import absolute_import
from . import util
from . import odict

class State(list):
    """ Track the current and nested state of the parser. 
    
    This utility class is used to track the state of the BlockParser and 
    support multiple levels if nesting. It's just a simple API wrapped around
    a list. Each time a state is set, that state is appended to the end of the
    list. Each time a state is reset, that state is removed from the end of
    the list.

    Therefore, each time a state is set for a nested block, that state must be 
    reset when we back out of that level of nesting or the state could be
    corrupted.

    While all the methods of a list object are available, only the three
    defined below need be used.

    """

    def set(self, state):
        """ Set a new state. """
        self.append(state)

    def reset(self):
        """ Step back one step in nested state. """
        self.pop()

    def isstate(self, state):
        """ Test that top (current) level is of given state. """
        if len(self):
            return self[-1] == state
        else:
            return False

class BlockParser:
    """ Parse Markdown blocks into an ElementTree object. 
    
    A wrapper class that stitches the various BlockProcessors together,
    looping through them and creating an ElementTree object.
    """

    def __init__(self, markdown):
        self.blockprocessors = odict.OrderedDict()
        self.state = State()
        self.markdown = markdown

    def parseDocument(self, lines):
        """ Parse a markdown document into an ElementTree. 
        
        Given a list of lines, an ElementTree object (not just a parent Element)
        is created and the root element is passed to the parser as the parent.
        The ElementTree object is returned.
        
        This should only be called on an entire document, not pieces.

        """
        # Create a ElementTree from the lines
        self.root = util.etree.Element(self.markdown.doc_tag)
        self.parseChunk(self.root, '\n'.join(lines))
        return util.etree.ElementTree(self.root)

    def parseChunk(self, parent, text):
        """ Parse a chunk of markdown text and attach to given etree node. 
        
        While the ``text`` argument is generally assumed to contain multiple
        blocks which will be split on blank lines, it could contain only one
        block. Generally, this method would be called by extensions when
        block parsing is required. 
        
        The ``parent`` etree Element passed in is altered in place. 
        Nothing is returned.

        """
        self.parseBlocks(parent, text.split('\n\n'))

    def parseBlocks(self, parent, blocks):
        """ Process blocks of markdown text and attach to given etree node. 
        
        Given a list of ``blocks``, each blockprocessor is stepped through
        until there are no blocks left. While an extension could potentially
        call this method directly, it's generally expected to be used internally.

        This is a public method as an extension may need to add/alter additional
        BlockProcessors which call this method to recursively parse a nested
        block.

        """
        while blocks:
            for processor in self.blockprocessors.values():
                if processor.test(parent, blocks[0]):
                    if processor.run(parent, blocks) is not False:
                        # run returns True or None
                        break