chardet/charsetprober.py

   1 ######################## BEGIN LICENSE BLOCK ########################
   2 # The Original Code is Mozilla Universal charset detector code.
   3 #
   4 # The Initial Developer of the Original Code is
   5 # Netscape Communications Corporation.
   6 # Portions created by the Initial Developer are Copyright (C) 2001
   7 # the Initial Developer. All Rights Reserved.
   8 #
   9 # Contributor(s):
  10 #   Mark Pilgrim - port to Python
  11 #   Shy Shalom - original C code
  12 #
  13 # This library is free software; you can redistribute it and/or
  14 # modify it under the terms of the GNU Lesser General Public
  15 # License as published by the Free Software Foundation; either
  16 # version 2.1 of the License, or (at your option) any later version.
  17 #
  18 # This library is distributed in the hope that it will be useful,
  19 # but WITHOUT ANY WARRANTY; without even the implied warranty of
  20 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
  21 # Lesser General Public License for more details.
  22 #
  23 # You should have received a copy of the GNU Lesser General Public
  24 # License along with this library; if not, write to the Free Software
  25 # Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
  26 # 02110-1301  USA
  27 ######################### END LICENSE BLOCK #########################
  28
  29 import constants, re
  30
  31 class CharSetProber:
  32     def __init__(self):
  33         pass
  34
  35     def reset(self):
  36         self._mState = constants.eDetecting
  37
  38     def get_charset_name(self):
  39         return None
  40
  41     def feed(self, aBuf):
  42         pass
  43
  44     def get_state(self):
  45         return self._mState
  46
  47     def get_confidence(self):
  48         return 0.0
  49
  50     def filter_high_bit_only(self, aBuf):
  51         aBuf = re.sub(r'([\x00-\x7F])+', ' ', aBuf)
  52         return aBuf
  53
  54     def filter_without_english_letters(self, aBuf):
  55         aBuf = re.sub(r'([A-Za-z])+', ' ', aBuf)
  56         return aBuf
  57
  58     def filter_with_english_letters(self, aBuf):
  59         # TODO
  60         return aBuf