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'''
34Abbreviation Extension for Python-Markdown
35==========================================
36
37This extension adds abbreviation handling to Python-Markdown.
38
39Simple Usage:
40
41    >>> import markdown
42    >>> text = """
43    ... Some text with an ABBR and a REF. Ignore REFERENCE and ref.
44    ...
45    ... *[ABBR]: Abbreviation
46    ... *[REF]: Abbreviation Reference
47    ... """
48    >>> print markdown.markdown(text, ['abbr'])
49    <p>Some text with an <abbr title="Abbreviation">ABBR</abbr> and a <abbr title="Abbreviation Reference">REF</abbr>. Ignore REFERENCE and ref.</p>
50
51Copyright 2007-2008
52* [Waylan Limberg](http://achinghead.com/)
53* [Seemant Kulleen](http://www.kulleen.org/)
54
55
56'''
57
58from __future__ import absolute_import
59from __future__ import unicode_literals
60from . import Extension
61from ..preprocessors import Preprocessor
62from ..inlinepatterns import Pattern
63from ..util import etree
64import re
65
66# Global Vars
67ABBR_REF_RE = re.compile(r'[*]\[(?P<abbr>[^\]]*)\][ ]?:\s*(?P<title>.*)')
68
69class AbbrExtension(Extension):
70    """ Abbreviation Extension for Python-Markdown. """
71
72    def extendMarkdown(self, md, md_globals):
73        """ Insert AbbrPreprocessor before ReferencePreprocessor. """
74        md.preprocessors.add('abbr', AbbrPreprocessor(md), '<reference')
75
76
77class AbbrPreprocessor(Preprocessor):
78    """ Abbreviation Preprocessor - parse text for abbr references. """
79
80    def run(self, lines):
81        '''
82        Find and remove all Abbreviation references from the text.
83        Each reference is set as a new AbbrPattern in the markdown instance.
84
85        '''
86        new_text = []
87        for line in lines:
88            m = ABBR_REF_RE.match(line)
89            if m:
90                abbr = m.group('abbr').strip()
91                title = m.group('title').strip()
92                self.markdown.inlinePatterns['abbr-%s'%abbr] = \
93                    AbbrPattern(self._generate_pattern(abbr), title)
94            else:
95                new_text.append(line)
96        return new_text
97
98    def _generate_pattern(self, text):
99        '''
100        Given a string, returns an regex pattern to match that string.
101
102        'HTML' -> r'(?P<abbr>[H][T][M][L])'
103
104        Note: we force each char as a literal match (in brackets) as we don't
105        know what they will be beforehand.
106
107        '''
108        chars = list(text)
109        for i in range(len(chars)):
110            chars[i] = r'[%s]' % chars[i]
111        return r'(?P<abbr>\b%s\b)' % (r''.join(chars))
112
113
114class AbbrPattern(Pattern):
115    """ Abbreviation inline pattern. """
116
117    def __init__(self, pattern, title):
118        super(AbbrPattern, self).__init__(pattern)
119        self.title = title
120
121    def handleMatch(self, m):
122        abbr = etree.Element('abbr')
123        abbr.text = m.group('abbr')
124        abbr.set('title', self.title)
125        return abbr
126
127def makeExtension(configs=None):
128    return AbbrExtension(configs=configs)
129