Project

General

Profile

« Previous | Next » 

Revision 10278

Added by Aaron Marcuse-Kubitza over 11 years ago

bin/*: replaced confusing regexp constructs involving \W inside [] with the much clearer explicit character class [:alnum:] . this avoids adding or subtracting from an inverted class in order to reach a subset of the corresponding positive class, because the subset can just be named explicitly instead.

View differences:

bin/repl
43 43 
        if in_ != '':
44 44 
            if text or re.match(r'^\w+$', in_): # match word
45 45 
                in_ = (r'(?:^|(?<=[\s,"])|^:|(?<=[\s,"]):)'+re.escape(in_)
46 
                    +r'(?![^\W_])')
46 
                    +r'(?![[:alnum:]])')
47 47 
            repls.append((r'(?m)'+in_, out))
48 48 
    stream.close()
49 49 
    def repl_all(str_):
bin/filter_out_ci
7 7 
import re
8 8 
import sys
9 9 

  		




  10
  
  
    
def simplify(str_): return re.sub(r'#.*$|[\W_]+', r'', str_.lower())


  		




  
  10
  
    
def simplify(str_): return re.sub(r'#.*$|[^[:alnum:]]+', r'', str_.lower())


  		




  11
  11
  
    

  		




  12
  12
  
    
def main():


  		




  13
  13
  
    
    try: _prog_name, col_num, vocab_path = sys.argv


  		












  

    
      bin/canon
    
  





  17
  17
  
    
        if key in self: raise KeyError(key)


  		




  18
  18
  
    
        dict.__setitem__(self, key, value)


  		




  19
  19
  
    

  		




  20
  
  
    
def simplify(str_): return re.sub(r'[\W_]+', r'', str_.lower())


  		




  
  20
  
    
def simplify(str_): return re.sub(r'[^[:alnum:]]+', r'', str_.lower())


  		




  21
  21
  
    

  		




  22
  22
  
    
def main():


  		




  23
  23
  
    
    try: _prog_name, col_num, vocab_path = sys.argv


  		












Also available in:  Unified diff