third_party/markdown/extensions/tables.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.


"""
Tables Extension for Python-Markdown
====================================

Added parsing of tables to Python-Markdown.

A simple example:

    First Header  | Second Header
    ------------- | -------------
    Content Cell  | Content Cell
    Content Cell  | Content Cell

Copyright 2009 - [Waylan Limberg](http://achinghead.com)
"""

from __future__ import absolute_import
from __future__ import unicode_literals
from . import Extension
from ..blockprocessors import BlockProcessor
from ..util import etree

class TableProcessor(BlockProcessor):
    """ Process Tables. """

    def test(self, parent, block):
        rows = block.split('\n')
        return (len(rows) > 2 and '|' in rows[0] and 
                '|' in rows[1] and '-' in rows[1] and 
                rows[1].strip()[0] in ['|', ':', '-'])

    def run(self, parent, blocks):
        """ Parse a table block and build table. """
        block = blocks.pop(0).split('\n')
        header = block[0].strip()
        seperator = block[1].strip()
        rows = block[2:]
        # Get format type (bordered by pipes or not)
        border = False
        if header.startswith('|'):
            border = True
        # Get alignment of columns
        align = []
        for c in self._split_row(seperator, border):
            if c.startswith(':') and c.endswith(':'):
                align.append('center')
            elif c.startswith(':'):
                align.append('left')
            elif c.endswith(':'):
                align.append('right')
            else:
                align.append(None)
        # Build table
        table = etree.SubElement(parent, 'table')
        thead = etree.SubElement(table, 'thead')
        self._build_row(header, thead, align, border)
        tbody = etree.SubElement(table, 'tbody')
        for row in rows:
            self._build_row(row.strip(), tbody, align, border)

    def _build_row(self, row, parent, align, border):
        """ Given a row of text, build table cells. """
        tr = etree.SubElement(parent, 'tr')
        tag = 'td'
        if parent.tag == 'thead':
            tag = 'th'
        cells = self._split_row(row, border)
        # We use align here rather than cells to ensure every row 
        # contains the same number of columns.
        for i, a in enumerate(align):
            c = etree.SubElement(tr, tag)
            try:
                c.text = cells[i].strip()
            except IndexError:
                c.text = ""
            if a:
                c.set('align', a)

    def _split_row(self, row, border):
        """ split a row of text into list of cells. """
        if border:
            if row.startswith('|'):
                row = row[1:]
            if row.endswith('|'):
                row = row[:-1]
        return row.split('|')


class TableExtension(Extension):
    """ Add tables to Markdown. """

    def extendMarkdown(self, md, md_globals):
        """ Add an instance of TableProcessor to BlockParser. """
        md.parser.blockprocessors.add('table', 
                                      TableProcessor(md.parser),
                                      '<hashheader')


def makeExtension(configs={}):
    return TableExtension(configs=configs)