1234567891011121314151617181920212223242526272829303132333435363738394041424344454647484950515253545556575859606162 |
- ######################## BEGIN LICENSE BLOCK ########################
- # The Original Code is Mozilla Universal charset detector code.
- #
- # The Initial Developer of the Original Code is
- # Netscape Communications Corporation.
- # Portions created by the Initial Developer are Copyright (C) 2001
- # the Initial Developer. All Rights Reserved.
- #
- # Contributor(s):
- # Mark Pilgrim - port to Python
- # Shy Shalom - original C code
- #
- # This library is free software; you can redistribute it and/or
- # modify it under the terms of the GNU Lesser General Public
- # License as published by the Free Software Foundation; either
- # version 2.1 of the License, or (at your option) any later version.
- #
- # This library is distributed in the hope that it will be useful,
- # but WITHOUT ANY WARRANTY; without even the implied warranty of
- # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- # Lesser General Public License for more details.
- #
- # You should have received a copy of the GNU Lesser General Public
- # License along with this library; if not, write to the Free Software
- # Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
- # 02110-1301 USA
- ######################### END LICENSE BLOCK #########################
-
- from . import constants
- import re
-
-
- class CharSetProber:
- def __init__(self):
- pass
-
- def reset(self):
- self._mState = constants.eDetecting
-
- def get_charset_name(self):
- return None
-
- def feed(self, aBuf):
- pass
-
- def get_state(self):
- return self._mState
-
- def get_confidence(self):
- return 0.0
-
- def filter_high_bit_only(self, aBuf):
- aBuf = re.sub(b'([\x00-\x7F])+', b' ', aBuf)
- return aBuf
-
- def filter_without_english_letters(self, aBuf):
- aBuf = re.sub(b'([A-Za-z])+', b' ', aBuf)
- return aBuf
-
- def filter_with_english_letters(self, aBuf):
- # TODO
- return aBuf
|