python (3.11.7)
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
28 from typing import Union
29
30 from .chardistribution import SJISDistributionAnalysis
31 from .codingstatemachine import CodingStateMachine
32 from .enums import MachineState, ProbingState
33 from .jpcntx import SJISContextAnalysis
34 from .mbcharsetprober import MultiByteCharSetProber
35 from .mbcssm import SJIS_SM_MODEL
36
37
38 class ESC[4;38;5;81mSJISProber(ESC[4;38;5;149mMultiByteCharSetProber):
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)
Browse
Usage
Versions