sjisprober.py revision 420216e5
1######################## BEGIN LICENSE BLOCK ########################
2# The Original Code is mozilla.org 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) 1998
7# the Initial Developer. All Rights Reserved.
8#
9# Contributor(s):
10#   Mark Pilgrim - port to Python
11#
12# This library is free software; you can redistribute it and/or
13# modify it under the terms of the GNU Lesser General Public
14# License as published by the Free Software Foundation; either
15# version 2.1 of the License, or (at your option) any later version.
16#
17# This library is distributed in the hope that it will be useful,
18# but WITHOUT ANY WARRANTY; without even the implied warranty of
19# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
20# Lesser General Public License for more details.
21#
22# You should have received a copy of the GNU Lesser General Public
23# License along with this library; if not, write to the Free Software
24# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
25# 02110-1301  USA
26######################### END LICENSE BLOCK #########################
27
28import sys
29from .mbcharsetprober import MultiByteCharSetProber
30from .codingstatemachine import CodingStateMachine
31from .chardistribution import SJISDistributionAnalysis
32from .jpcntx import SJISContextAnalysis
33from .mbcssm import SJISSMModel
34from . import constants
35
36
37class SJISProber(MultiByteCharSetProber):
38    def __init__(self):
39        MultiByteCharSetProber.__init__(self)
40        self._mCodingSM = CodingStateMachine(SJISSMModel)
41        self._mDistributionAnalyzer = SJISDistributionAnalysis()
42        self._mContextAnalyzer = SJISContextAnalysis()
43        self.reset()
44
45    def reset(self):
46        MultiByteCharSetProber.reset(self)
47        self._mContextAnalyzer.reset()
48
49    def get_charset_name(self):
50        return self._mContextAnalyzer.get_charset_name()
51
52    def feed(self, aBuf):
53        aLen = len(aBuf)
54        for i in range(0, aLen):
55            codingState = self._mCodingSM.next_state(aBuf[i])
56            if codingState == constants.eError:
57                if constants._debug:
58                    sys.stderr.write(self.get_charset_name()
59                                     + ' prober hit error at byte ' + str(i)
60                                     + '\n')
61                self._mState = constants.eNotMe
62                break
63            elif codingState == constants.eItsMe:
64                self._mState = constants.eFoundIt
65                break
66            elif codingState == constants.eStart:
67                charLen = self._mCodingSM.get_current_charlen()
68                if i == 0:
69                    self._mLastChar[1] = aBuf[0]
70                    self._mContextAnalyzer.feed(self._mLastChar[2 - charLen:],
71                                                charLen)
72                    self._mDistributionAnalyzer.feed(self._mLastChar, charLen)
73                else:
74                    self._mContextAnalyzer.feed(aBuf[i + 1 - charLen:i + 3
75                                                     - charLen], charLen)
76                    self._mDistributionAnalyzer.feed(aBuf[i - 1:i + 1],
77                                                     charLen)
78
79        self._mLastChar[0] = aBuf[aLen - 1]
80
81        if self.get_state() == constants.eDetecting:
82            if (self._mContextAnalyzer.got_enough_data() and
83               (self.get_confidence() > constants.SHORTCUT_THRESHOLD)):
84                self._mState = constants.eFoundIt
85
86        return self.get_state()
87
88    def get_confidence(self):
89        contxtCf = self._mContextAnalyzer.get_confidence()
90        distribCf = self._mDistributionAnalyzer.get_confidence()
91        return max(contxtCf, distribCf)
92