1
######################## BEGIN LICENSE BLOCK ########################
2
# The Original Code is Mozilla Universal charset detector code.
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.
10
# Mark Pilgrim - port to Python
11
# Shy Shalom - original C code
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.
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.
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
27
######################### END LICENSE BLOCK #########################
29
from . import constants
37
self._mState = constants.eDetecting
39
def get_charset_name(self):
48
def get_confidence(self):
51
def filter_high_bit_only(self, aBuf):
52
aBuf = re.sub(b'([\x00-\x7F])+', b' ', aBuf)
55
def filter_without_english_letters(self, aBuf):
56
aBuf = re.sub(b'([A-Za-z])+', b' ', aBuf)
59
def filter_with_english_letters(self, aBuf):