third_party/markdown/extensions/attr_list.py

   1 # markdown is released under the BSD license
   2 # Copyright 2007, 2008 The Python Markdown Project (v. 1.7 and later)
   3 # Copyright 2004, 2005, 2006 Yuri Takhteyev (v. 0.2-1.6b)
   4 # Copyright 2004 Manfred Stienstra (the original version)
   5 #
   6 # All rights reserved.
   7 #
   8 # Redistribution and use in source and binary forms, with or without
   9 # modification, are permitted provided that the following conditions are met:
  10 #
  11 # *   Redistributions of source code must retain the above copyright
  12 #     notice, this list of conditions and the following disclaimer.
  13 # *   Redistributions in binary form must reproduce the above copyright
  14 #     notice, this list of conditions and the following disclaimer in the
  15 #     documentation and/or other materials provided with the distribution.
  16 # *   Neither the name of the <organization> nor the
  17 #     names of its contributors may be used to endorse or promote products
  18 #     derived from this software without specific prior written permission.
  19 #
  20 # THIS SOFTWARE IS PROVIDED BY THE PYTHON MARKDOWN PROJECT ''AS IS'' AND ANY
  21 # EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
  22 # WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
  23 # DISCLAIMED. IN NO EVENT SHALL ANY CONTRIBUTORS TO THE PYTHON MARKDOWN PROJECT
  24 # BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
  25 # CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
  26 # SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
  27 # INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
  28 # CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
  29 # ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
  30 # POSSIBILITY OF SUCH DAMAGE.
  31
  32
  33 """
  34 Attribute List Extension for Python-Markdown
  35 ============================================
  36
  37 Adds attribute list syntax. Inspired by
  38 [maruku](http://maruku.rubyforge.org/proposal.html#attribute_lists)'s
  39 feature of the same name.
  40
  41 Copyright 2011 [Waylan Limberg](http://achinghead.com/).
  42
  43 Contact: markdown@freewisdom.org
  44
  45 License: BSD (see ../LICENSE.md for details)
  46
  47 Dependencies:
  48 * [Python 2.4+](http://python.org)
  49 * [Markdown 2.1+](http://packages.python.org/Markdown/)
  50
  51 """
  52
  53 from __future__ import absolute_import
  54 from __future__ import unicode_literals
  55 from . import Extension
  56 from ..treeprocessors import Treeprocessor
  57 from ..util import isBlockLevel
  58 import re
  59
  60 try:
  61     Scanner = re.Scanner
  62 except AttributeError:
  63     # must be on Python 2.4
  64     from sre import Scanner
  65
  66 def _handle_double_quote(s, t):
  67     k, v = t.split('=')
  68     return k, v.strip('"')
  69
  70 def _handle_single_quote(s, t):
  71     k, v = t.split('=')
  72     return k, v.strip("'")
  73
  74 def _handle_key_value(s, t):
  75     return t.split('=')
  76
  77 def _handle_word(s, t):
  78     if t.startswith('.'):
  79         return '.', t[1:]
  80     if t.startswith('#'):
  81         return 'id', t[1:]
  82     return t, t
  83
  84 _scanner = Scanner([
  85     (r'[^ ]+=".*?"', _handle_double_quote),
  86     (r"[^ ]+='.*?'", _handle_single_quote),
  87     (r'[^ ]+=[^ ]*', _handle_key_value),
  88     (r'[^ ]+', _handle_word),
  89     (r' ', None)
  90 ])
  91
  92 def get_attrs(str):
  93     """ Parse attribute list and return a list of attribute tuples. """
  94     return _scanner.scan(str)[0]
  95
  96 def isheader(elem):
  97     return elem.tag in ['h1', 'h2', 'h3', 'h4', 'h5', 'h6']
  98
  99 class AttrListTreeprocessor(Treeprocessor):
 100
 101     BASE_RE = r'\{\:?([^\}]*)\}'
 102     HEADER_RE = re.compile(r'[ ]*%s[ ]*$' % BASE_RE)
 103     BLOCK_RE = re.compile(r'\n[ ]*%s[ ]*$' % BASE_RE)
 104     INLINE_RE = re.compile(r'^%s' % BASE_RE)
 105     NAME_RE = re.compile(r'[^A-Z_a-z\u00c0-\u00d6\u00d8-\u00f6\u00f8-\u02ff\u0370-\u037d'
 106                          r'\u037f-\u1fff\u200c-\u200d\u2070-\u218f\u2c00-\u2fef'
 107                          r'\u3001-\ud7ff\uf900-\ufdcf\ufdf0-\ufffd'
 108                          r'\:\-\.0-9\u00b7\u0300-\u036f\u203f-\u2040]+')
 109
 110     def run(self, doc):
 111         for elem in doc.getiterator():
 112             if isBlockLevel(elem.tag):
 113                 # Block level: check for attrs on last line of text
 114                 RE = self.BLOCK_RE
 115                 if isheader(elem):
 116                     # header: check for attrs at end of line
 117                     RE = self.HEADER_RE
 118                 if len(elem) and elem[-1].tail:
 119                     # has children. Get from tail of last child
 120                     m = RE.search(elem[-1].tail)
 121                     if m:
 122                         self.assign_attrs(elem, m.group(1))
 123                         elem[-1].tail = elem[-1].tail[:m.start()]
 124                         if isheader(elem):
 125                             # clean up trailing #s
 126                             elem[-1].tail = elem[-1].tail.rstrip('#').rstrip()
 127                 elif elem.text:
 128                     # no children. Get from text.
 129                     m = RE.search(elem.text)
 130                     if m:
 131                         self.assign_attrs(elem, m.group(1))
 132                         elem.text = elem.text[:m.start()]
 133                         if isheader(elem):
 134                             # clean up trailing #s
 135                             elem.text = elem.text.rstrip('#').rstrip()
 136             else:
 137                 # inline: check for attrs at start of tail
 138                 if elem.tail:
 139                     m = self.INLINE_RE.match(elem.tail)
 140                     if m:
 141                         self.assign_attrs(elem, m.group(1))
 142                         elem.tail = elem.tail[m.end():]
 143
 144     def assign_attrs(self, elem, attrs):
 145         """ Assign attrs to element. """
 146         for k, v in get_attrs(attrs):
 147             if k == '.':
 148                 # add to class
 149                 cls = elem.get('class')
 150                 if cls:
 151                     elem.set('class', '%s %s' % (cls, v))
 152                 else:
 153                     elem.set('class', v)
 154             else:
 155                 # assign attr k with v
 156                 elem.set(self.sanitize_name(k), v)
 157
 158     def sanitize_name(self, name):
 159         """
 160         Sanitize name as 'an XML Name, minus the ":"'.
 161         See http://www.w3.org/TR/REC-xml-names/#NT-NCName
 162         """
 163         return self.NAME_RE.sub('_', name)
 164
 165
 166 class AttrListExtension(Extension):
 167     def extendMarkdown(self, md, md_globals):
 168         md.treeprocessors.add('attr_list', AttrListTreeprocessor(md), '>prettify')
 169
 170
 171 def makeExtension(configs={}):
 172     return AttrListExtension(configs=configs)