sqlmap/thirdparty/chardet/utf8prober.py

81 lines
2.7 KiB
Python
Raw Permalink Normal View History

2012-07-14 18:53:15 +04:00
######################## BEGIN LICENSE BLOCK ########################
# The Original Code is mozilla.org code.
#
# The Initial Developer of the Original Code is
# Netscape Communications Corporation.
# Portions created by the Initial Developer are Copyright (C) 1998
# the Initial Developer. All Rights Reserved.
#
# Contributor(s):
# Mark Pilgrim - port to Python
#
# 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.
2015-10-09 14:35:48 +03:00
#
2012-07-14 18:53:15 +04:00
# 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.
2015-10-09 14:35:48 +03:00
#
2012-07-14 18:53:15 +04:00
# 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 #########################
2019-03-28 17:14:16 +03:00
import sys
2015-10-09 14:35:48 +03:00
from . import constants
from .charsetprober import CharSetProber
from .codingstatemachine import CodingStateMachine
from .mbcssm import UTF8SMModel
2012-07-14 18:53:15 +04:00
2019-03-29 00:54:05 +03:00
if sys.version_info >= (3, 0):
2019-03-28 17:14:16 +03:00
xrange = range
2012-07-14 18:53:15 +04:00
ONE_CHAR_PROB = 0.5
2015-10-09 14:35:48 +03:00
2012-07-14 18:53:15 +04:00
class UTF8Prober(CharSetProber):
def __init__(self):
CharSetProber.__init__(self)
self._mCodingSM = CodingStateMachine(UTF8SMModel)
self.reset()
def reset(self):
CharSetProber.reset(self)
self._mCodingSM.reset()
self._mNumOfMBChar = 0
def get_charset_name(self):
return "utf-8"
def feed(self, aBuf):
for c in aBuf:
codingState = self._mCodingSM.next_state(c)
2015-10-09 14:35:48 +03:00
if codingState == constants.eError:
2012-07-14 18:53:15 +04:00
self._mState = constants.eNotMe
break
2015-10-09 14:35:48 +03:00
elif codingState == constants.eItsMe:
2012-07-14 18:53:15 +04:00
self._mState = constants.eFoundIt
break
2015-10-09 14:35:48 +03:00
elif codingState == constants.eStart:
2012-07-14 18:53:15 +04:00
if self._mCodingSM.get_current_charlen() >= 2:
self._mNumOfMBChar += 1
if self.get_state() == constants.eDetecting:
if self.get_confidence() > constants.SHORTCUT_THRESHOLD:
self._mState = constants.eFoundIt
return self.get_state()
def get_confidence(self):
unlike = 0.99
if self._mNumOfMBChar < 6:
2015-10-09 14:48:21 +03:00
for i in xrange(0, self._mNumOfMBChar):
2012-07-14 18:53:15 +04:00
unlike = unlike * ONE_CHAR_PROB
return 1.0 - unlike
else:
return unlike