escprober.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
28from . import constants
29from .escsm import (HZSMModel, ISO2022CNSMModel, ISO2022JPSMModel,
30                    ISO2022KRSMModel)
31from .charsetprober import CharSetProber
32from .codingstatemachine import CodingStateMachine
33from .compat import wrap_ord
34
35
36class EscCharSetProber(CharSetProber):
37    def __init__(self):
38        CharSetProber.__init__(self)
39        self._mCodingSM = [
40            CodingStateMachine(HZSMModel),
41            CodingStateMachine(ISO2022CNSMModel),
42            CodingStateMachine(ISO2022JPSMModel),
43            CodingStateMachine(ISO2022KRSMModel)
44        ]
45        self.reset()
46
47    def reset(self):
48        CharSetProber.reset(self)
49        for codingSM in self._mCodingSM:
50            if not codingSM:
51                continue
52            codingSM.active = True
53            codingSM.reset()
54        self._mActiveSM = len(self._mCodingSM)
55        self._mDetectedCharset = None
56
57    def get_charset_name(self):
58        return self._mDetectedCharset
59
60    def get_confidence(self):
61        if self._mDetectedCharset:
62            return 0.99
63        else:
64            return 0.00
65
66    def feed(self, aBuf):
67        for c in aBuf:
68            # PY3K: aBuf is a byte array, so c is an int, not a byte
69            for codingSM in self._mCodingSM:
70                if not codingSM:
71                    continue
72                if not codingSM.active:
73                    continue
74                codingState = codingSM.next_state(wrap_ord(c))
75                if codingState == constants.eError:
76                    codingSM.active = False
77                    self._mActiveSM -= 1
78                    if self._mActiveSM <= 0:
79                        self._mState = constants.eNotMe
80                        return self.get_state()
81                elif codingState == constants.eItsMe:
82                    self._mState = constants.eFoundIt
83                    self._mDetectedCharset = codingSM.get_coding_state_machine()  # nopep8
84                    return self.get_state()
85
86        return self.get_state()
87