Home | History | Annotate | Download | only in extensions 
      1 '''
      2 Abbreviation Extension for Python-Markdown
      3 ==========================================
      4 
      5 This extension adds abbreviation handling to Python-Markdown.
      6 
      7 Simple Usage:
      8 
      9     >>> import markdown
     10     >>> text = """
     11     ... Some text with an ABBR and a REF. Ignore REFERENCE and ref.
     12     ...
     13     ... *[ABBR]: Abbreviation
     14     ... *[REF]: Abbreviation Reference
     15     ... """
     16     >>> markdown.markdown(text, ['abbr'])
     17     u'<p>Some text with an <abbr title="Abbreviation">ABBR</abbr> and a <abbr title="Abbreviation Reference">REF</abbr>. Ignore REFERENCE and ref.</p>'
     18 
     19 Copyright 2007-2008
     20 * [Waylan Limberg](http://achinghead.com/)
     21 * [Seemant Kulleen](http://www.kulleen.org/)
     22 	
     23 
     24 '''
     25 
     26 import markdown, re
     27 from markdown import etree
     28 
     29 # Global Vars
     30 ABBR_REF_RE = re.compile(r'[*]\[(?P<abbr>[^\]]*)\][ ]?:\s*(?P<title>.*)')
     31 
     32 class AbbrExtension(markdown.Extension):
     33     """ Abbreviation Extension for Python-Markdown. """
     34 
     35     def extendMarkdown(self, md, md_globals):
     36         """ Insert AbbrPreprocessor before ReferencePreprocessor. """
     37         md.preprocessors.add('abbr', AbbrPreprocessor(md), '<reference')
     38         
     39            
     40 class AbbrPreprocessor(markdown.preprocessors.Preprocessor):
     41     """ Abbreviation Preprocessor - parse text for abbr references. """
     42 
     43     def run(self, lines):
     44         '''
     45         Find and remove all Abbreviation references from the text.
     46         Each reference is set as a new AbbrPattern in the markdown instance.
     47         
     48         '''
     49         new_text = []
     50         for line in lines:
     51             m = ABBR_REF_RE.match(line)
     52             if m:
     53                 abbr = m.group('abbr').strip()
     54                 title = m.group('title').strip()
     55                 self.markdown.inlinePatterns['abbr-%s'%abbr] = \
     56                     AbbrPattern(self._generate_pattern(abbr), title)
     57             else:
     58                 new_text.append(line)
     59         return new_text
     60     
     61     def _generate_pattern(self, text):
     62         '''
     63         Given a string, returns an regex pattern to match that string. 
     64         
     65         'HTML' -> r'(?P<abbr>[H][T][M][L])' 
     66         
     67         Note: we force each char as a literal match (in brackets) as we don't 
     68         know what they will be beforehand.
     69 
     70         '''
     71         chars = list(text)
     72         for i in range(len(chars)):
     73             chars[i] = r'[%s]' % chars[i]
     74         return r'(?P<abbr>\b%s\b)' % (r''.join(chars))
     75 
     76 
     77 class AbbrPattern(markdown.inlinepatterns.Pattern):
     78     """ Abbreviation inline pattern. """
     79 
     80     def __init__(self, pattern, title):
     81         markdown.inlinepatterns.Pattern.__init__(self, pattern)
     82         self.title = title
     83 
     84     def handleMatch(self, m):
     85         abbr = etree.Element('abbr')
     86         abbr.text = m.group('abbr')
     87         abbr.set('title', self.title)
     88         return abbr
     89 
     90 def makeExtension(configs=None):
     91     return AbbrExtension(configs=configs)
     92 
     93 if __name__ == "__main__":
     94     import doctest
     95     doctest.testmod()
     96