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 typing import Union
29
30from .chardistribution import SJISDistributionAnalysis
31from .codingstatemachine import CodingStateMachine
32from .enums import MachineState, ProbingState
33from .jpcntx import SJISContextAnalysis
34from .mbcharsetprober import MultiByteCharSetProber
35from .mbcssm import SJIS_SM_MODEL
36
37
38class SJISProber(MultiByteCharSetProber):
39 def __init__(self) -> None:
40 super().__init__()
41 self.coding_sm = CodingStateMachine(SJIS_SM_MODEL)
42 self.distribution_analyzer = SJISDistributionAnalysis()
43 self.context_analyzer = SJISContextAnalysis()
44 self.reset()
45
46 def reset(self) -> None:
47 super().reset()
48 self.context_analyzer.reset()
49
50 @property
51 def charset_name(self) -> str:
52 return self.context_analyzer.charset_name
53
54 @property
55 def language(self) -> str:
56 return "Japanese"
57
58 def feed(self, byte_str: Union[bytes, bytearray]) -> ProbingState:
59 assert self.coding_sm is not None
60 assert self.distribution_analyzer is not None
61
62 for i, byte in enumerate(byte_str):
63 coding_state = self.coding_sm.next_state(byte)
64 if coding_state == MachineState.ERROR:
65 self.logger.debug(
66 "%s %s prober hit error at byte %s",
67 self.charset_name,
68 self.language,
69 i,
70 )
71 self._state = ProbingState.NOT_ME
72 break
73 if coding_state == MachineState.ITS_ME:
74 self._state = ProbingState.FOUND_IT
75 break
76 if coding_state == MachineState.START:
77 char_len = self.coding_sm.get_current_charlen()
78 if i == 0:
79 self._last_char[1] = byte
80 self.context_analyzer.feed(
81 self._last_char[2 - char_len :], char_len
82 )
83 self.distribution_analyzer.feed(self._last_char, char_len)
84 else:
85 self.context_analyzer.feed(
86 byte_str[i + 1 - char_len : i + 3 - char_len], char_len
87 )
88 self.distribution_analyzer.feed(byte_str[i - 1 : i + 1], char_len)
89
90 self._last_char[0] = byte_str[-1]
91
92 if self.state == ProbingState.DETECTING:
93 if self.context_analyzer.got_enough_data() and (
94 self.get_confidence() > self.SHORTCUT_THRESHOLD
95 ):
96 self._state = ProbingState.FOUND_IT
97
98 return self.state
99
100 def get_confidence(self) -> float:
101 assert self.distribution_analyzer is not None
102
103 context_conf = self.context_analyzer.get_confidence()
104 distrib_conf = self.distribution_analyzer.get_confidence()
105 return max(context_conf, distrib_conf)