Source Code for Module lepl.regexp.binary

 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 proof-of-concept regexp implementation for binary data strings. 
32   
33  The hope is that one day we can parse binary data in the same way as text... 
34  ''' 
35   
36  from lepl.regexp.core import Compiler, Labelled 
37  from lepl.regexp.str import StrAlphabet, make_str_parser 
38   
39   
40 -class BinaryAlphabet(StrAlphabet): 
41      ''' 
42      An alphabet for binary strings. 
43      ''' 
44       
45      # pylint: disable-msg=E1002 
46      # (pylint bug?  this chains back to a new style abc) 
47 -    def __init__(self): 
48          super(BinaryAlphabet, self).__init__(0, 1) 
49       
50 -    def before(self, char):  
51          ''' 
52          Must return the character before c in the alphabet.  Never called with 
53          min (assuming input data are in range). 
54          '''  
55          return char-1 
56       
57 -    def after(self, char):  
58          ''' 
59          Must return the character after c in the alphabet.  Never called with 
60          max (assuming input data are in range). 
61          '''  
62          return char+1 
63       
64 -    def from_char(self, char): 
65          ''' 
66          Convert to 0 or 1. 
67          ''' 
68          char = int(char) 
69          assert char in (0, 1) 
70          return char 
71   
72   
73  BINARY = BinaryAlphabet() 
74   
75   
76  # pylint: disable-msg=W0105, C0103 
77  __compiled_binary_parser = make_str_parser(BINARY) 
78  ''' 
79  Cache the parser to allow efficient re-use. 
80  ''' 
81   
82 -def binary_single_parser(label, text): 
83      ''' 
84      Parse a binary regular expression, returning the associated Regexp. 
85      ''' 
86      return Compiler.single(BINARY, 
87                  Labelled(BINARY, label, *__compiled_binary_parser(text))) 
88   
89   
90 -def binary_parser(*regexps): 
91      ''' 
92      Parse a set of binary regular expressions, returning the associated Regexp. 
93      ''' 
94      return Compiler.multiple(BINARY, 
95                  [Labelled(BINARY, label, *__compiled_binary_parser(text)) 
96                   for (label, text) in regexps]) 
97