Source Code for Module lepl.regexp.unicode

  1   
  2  # The contents of this file are subject to the Mozilla Public License 
  3  # (MPL) Version 1.1 (the "License"); you may not use this file except 
  4  # in compliance with the License. You may obtain a copy of the License 
  5  # at http://www.mozilla.org/MPL/ 
  6  # 
  7  # Software distributed under the License is distributed on an "AS IS" 
  8  # basis, WITHOUT WARRANTY OF ANY KIND, either express or implied. See 
  9  # the License for the specific language governing rights and 
 10  # limitations under the License. 
 11  # 
 12  # The Original Code is LEPL (http://www.acooke.org/lepl) 
 13  # The Initial Developer of the Original Code is Andrew Cooke. 
 14  # Portions created by the Initial Developer are Copyright (C) 2009-2010 
 15  # Andrew Cooke (andrew@acooke.org). All Rights Reserved. 
 16  # 
 17  # Alternatively, the contents of this file may be used under the terms 
 18  # of the LGPL license (the GNU Lesser General Public License, 
 19  # http://www.gnu.org/licenses/lgpl.html), in which case the provisions 
 20  # of the LGPL License are applicable instead of those above. 
 21  # 
 22  # If you wish to allow use of your version of this file only under the 
 23  # terms of the LGPL License and not to allow others to use your version 
 24  # of this file under the MPL, indicate your decision by deleting the 
 25  # provisions above and replace them with the notice and other provisions 
 26  # required by the LGPL License.  If you do not delete the provisions 
 27  # above, a recipient may use your version of this file under either the 
 28  # MPL or the LGPL License. 
 29   
 30  ''' 
 31  A regexp implementation for unicode strings. 
 32  ''' 
 33   
 34  from sys import maxunicode 
 35   
 36  from lepl.regexp.str import StrAlphabet, ILLEGAL 
 37  from lepl.support.lib import chr, lmap, fmt 
 38   
 39  _WHITESPACE = '\u0009\u000A\u000B\u000C\u000D\u0020\u0085\u00A0\u1680' \ 
 40                  '\u180E\u2000\u2001\u2002\u2003\u2004\u2005\u2006\u2007' \ 
 41                  '\u2008\u2009\u200a\u2028\u2029\u202F\u205F\u3000' 
 42  '''http://en.wikipedia.org/wiki/Whitespace_character''' 
 43   
 44   
 45 -class UnicodeAlphabet(StrAlphabet): 
 46      ''' 
 47      An alphabet for unicode strings. 
 48      ''' 
 49       
 50      __cached_instance = None 
 51       
 52      # pylint: disable-msg=E1002 
 53      # (pylint bug?  this chains back to a new style abc) 
 54 -    def __init__(self): 
 55          from lepl.matchers.core import Any 
 56          from lepl.matchers.combine import Or 
 57          max_ = chr(maxunicode) 
 58          def mkhex(char, n): 
 59              from lepl.matchers.derived import Drop 
 60              return Drop(Any(char)) + Any('0123456789abcdefABCDEF')[n,...] >> \ 
 61                          (lambda x: chr(int(x, 16))) 
 62          def mkchr(char, range, invert=False): 
 63              from lepl.matchers.core import Literal 
 64              from lepl.matchers.derived import Map 
 65              from lepl.regexp.core import Character 
 66              intervals = lmap(lambda x: (x, x), range) 
 67              if invert: 
 68                  # this delays call to invert until after creation of self 
 69                  func = lambda _: Character(self.invert(intervals), self) 
 70              else: 
 71                  func = lambda _: Character(intervals, self) 
 72              return Map(Literal(char), func) 
 73          range = Or(mkchr('s', _WHITESPACE), 
 74                     mkchr('S', _WHITESPACE, invert=True)) 
 75          escaped = Any(ILLEGAL) | mkhex('x', 2) | mkhex('u', 4) | mkhex('U', 8) 
 76          super(UnicodeAlphabet, self).__init__(chr(0), max_, escaped=escaped, 
 77                                                range=range) 
 78           
 79 -    def before(self, char): 
 80          ''' 
 81          Must return the character before char in the alphabet.  Never called  
 82          with min (assuming input data are in range). 
 83          '''  
 84          return chr(ord(char)-1) 
 85       
 86 -    def after(self, char):  
 87          ''' 
 88          Must return the character after c in the alphabet.  Never called with 
 89          max (assuming input data are in range). 
 90          '''  
 91          return chr(ord(char)+1) 
 92       
 93      @classmethod 
 94 -    def instance(cls): 
 95          ''' 
 96          Get an instance of this alphabet (avoids creating new objects). 
 97          ''' 
 98          if cls.__cached_instance is None: 
 99              cls.__cached_instance = UnicodeAlphabet() 
100          return cls.__cached_instance 
101   
102 -    def __repr__(self): 
103          return '<Unicode>' 
104