Check in a simple pure-python based Markdown previewer.

third_party/Python-Markdown/markdown/extensions/attr_list.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.
-
-
 """
 Attribute List Extension for Python-Markdown
 ============================================
 
-Adds attribute list syntax. Inspired by 
+Adds attribute list syntax. Inspired by
 [maruku](http://maruku.rubyforge.org/proposal.html#attribute_lists)'s
 feature of the same name.
 
-Copyright 2011 [Waylan Limberg](http://achinghead.com/).
+See <https://pythonhosted.org/Markdown/extensions/attr_list.html>
+for documentation.
 
-Contact: markdown@freewisdom.org
+Original code Copyright 2011 [Waylan Limberg](http://achinghead.com/).
 
-License: BSD (see ../LICENSE.md for details) 
+All changes Copyright 2011-2014 The Python Markdown Project
 
-Dependencies:
-* [Python 2.4+](http://python.org)
-* [Markdown 2.1+](http://packages.python.org/Markdown/)
+License: [BSD](http://www.opensource.org/licenses/bsd-license.php)
 
 """
 
 from __future__ import absolute_import
 from __future__ import unicode_literals
 from . import Extension
 from ..treeprocessors import Treeprocessor
 from ..util import isBlockLevel
 import re
 
 try:
     Scanner = re.Scanner
-except AttributeError:
+except AttributeError:  # pragma: no cover
     # must be on Python 2.4
     from sre import Scanner
 
+
 def _handle_double_quote(s, t):
     k, v = t.split('=')
     return k, v.strip('"')
 
+
 def _handle_single_quote(s, t):
     k, v = t.split('=')
     return k, v.strip("'")
 
-def _handle_key_value(s, t): 
+
+def _handle_key_value(s, t):
     return t.split('=')
 
+
 def _handle_word(s, t):
     if t.startswith('.'):
         return '.', t[1:]
     if t.startswith('#'):
         return 'id', t[1:]
     return t, t
 
 _scanner = Scanner([
     (r'[^ ]+=".*?"', _handle_double_quote),
     (r"[^ ]+='.*?'", _handle_single_quote),
-    (r'[^ ]+=[^ ]*', _handle_key_value),
-    (r'[^ ]+', _handle_word),
+    (r'[^ ]+=[^ =]+', _handle_key_value),
+    (r'[^ =]+', _handle_word),
     (r' ', None)
 ])
 
+
 def get_attrs(str):
     """ Parse attribute list and return a list of attribute tuples. """
     return _scanner.scan(str)[0]
 
+
 def isheader(elem):
     return elem.tag in ['h1', 'h2', 'h3', 'h4', 'h5', 'h6']
 
+
 class AttrListTreeprocessor(Treeprocessor):
-    
+
     BASE_RE = r'\{\:?([^\}]*)\}'
-    HEADER_RE = re.compile(r'[ ]*%s[ ]*$' % BASE_RE)
+    HEADER_RE = re.compile(r'[ ]+%s[ ]*$' % BASE_RE)
     BLOCK_RE = re.compile(r'\n[ ]*%s[ ]*$' % BASE_RE)
     INLINE_RE = re.compile(r'^%s' % BASE_RE)
-    NAME_RE = re.compile(r'[^A-Z_a-z\u00c0-\u00d6\u00d8-\u00f6\u00f8-\u02ff\u0370-\u037d'
-                         r'\u037f-\u1fff\u200c-\u200d\u2070-\u218f\u2c00-\u2fef'
-                         r'\u3001-\ud7ff\uf900-\ufdcf\ufdf0-\ufffd'
+    NAME_RE = re.compile(r'[^A-Z_a-z\u00c0-\u00d6\u00d8-\u00f6\u00f8-\u02ff'
+                         r'\u0370-\u037d\u037f-\u1fff\u200c-\u200d'
+                         r'\u2070-\u218f\u2c00-\u2fef\u3001-\ud7ff'
+                         r'\uf900-\ufdcf\ufdf0-\ufffd'
                          r'\:\-\.0-9\u00b7\u0300-\u036f\u203f-\u2040]+')
 
     def run(self, doc):
         for elem in doc.getiterator():
             if isBlockLevel(elem.tag):
                 # Block level: check for attrs on last line of text
                 RE = self.BLOCK_RE
-                if isheader(elem):
-                    # header: check for attrs at end of line
+                if isheader(elem) or elem.tag == 'dt':
+                    # header or def-term: check for attrs at end of line
                     RE = self.HEADER_RE
-                if len(elem) and elem[-1].tail:
+                if len(elem) and elem.tag == 'li':
+                    # special case list items. children may include a ul or ol.
+                    pos = None
+                    # find the ul or ol position
+                    for i, child in enumerate(elem):
+                        if child.tag in ['ul', 'ol']:
+                            pos = i
+                            break
+                    if pos is None and elem[-1].tail:
+                        # use tail of last child. no ul or ol.
+                        m = RE.search(elem[-1].tail)
+                        if m:
+                            self.assign_attrs(elem, m.group(1))
+                            elem[-1].tail = elem[-1].tail[:m.start()]
+                    elif pos is not None and pos > 0 and elem[pos-1].tail:
+                        # use tail of last child before ul or ol
+                        m = RE.search(elem[pos-1].tail)
+                        if m:
+                            self.assign_attrs(elem, m.group(1))
+                            elem[pos-1].tail = elem[pos-1].tail[:m.start()]
+                    elif elem.text:
+                        # use text. ul is first child.
+                        m = RE.search(elem.text)
+                        if m:
+                            self.assign_attrs(elem, m.group(1))
+                            elem.text = elem.text[:m.start()]
+                elif len(elem) and elem[-1].tail:
                     # has children. Get from tail of last child
                     m = RE.search(elem[-1].tail)
                     if m:
                         self.assign_attrs(elem, m.group(1))
                         elem[-1].tail = elem[-1].tail[:m.start()]
                         if isheader(elem):
                             # clean up trailing #s
                             elem[-1].tail = elem[-1].tail.rstrip('#').rstrip()
                 elif elem.text:
                     # no children. Get from text.
                     m = RE.search(elem.text)
+                    if not m and elem.tag == 'td':
+                        m = re.search(self.BASE_RE, elem.text)
                     if m:
                         self.assign_attrs(elem, m.group(1))
                         elem.text = elem.text[:m.start()]
                         if isheader(elem):
                             # clean up trailing #s
                             elem.text = elem.text.rstrip('#').rstrip()
             else:
                 # inline: check for attrs at start of tail
                 if elem.tail:
                     m = self.INLINE_RE.match(elem.tail)
@@ skipping 18 matching lines @@
     def sanitize_name(self, name):
         """
         Sanitize name as 'an XML Name, minus the ":"'.
         See http://www.w3.org/TR/REC-xml-names/#NT-NCName
         """
         return self.NAME_RE.sub('_', name)
 
 
 class AttrListExtension(Extension):
     def extendMarkdown(self, md, md_globals):
-        md.treeprocessors.add('attr_list', AttrListTreeprocessor(md), '>prettify')
+        md.treeprocessors.add(
+            'attr_list', AttrListTreeprocessor(md), '>prettify'
+        )
 
 
-def makeExtension(configs={}):
-    return AttrListExtension(configs=configs)
+def makeExtension(*args, **kwargs):
+    return AttrListExtension(*args, **kwargs)