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 Optional, Union
29
30from .charsetprober import CharSetProber
31from .codingstatemachine import CodingStateMachine
32from .enums import LanguageFilter, MachineState, ProbingState
33from .escsm import (
34 HZ_SM_MODEL,
35 ISO2022CN_SM_MODEL,
36 ISO2022JP_SM_MODEL,
37 ISO2022KR_SM_MODEL,
38)
39
40
41class EscCharSetProber(CharSetProber):
42 """
43 This CharSetProber uses a "code scheme" approach for detecting encodings,
44 whereby easily recognizable escape or shift sequences are relied on to
45 identify these encodings.
46 """
47
48 def __init__(self, lang_filter: LanguageFilter = LanguageFilter.NONE) -> None:
49 super().__init__(lang_filter=lang_filter)
50 self.coding_sm = []
51 if self.lang_filter & LanguageFilter.CHINESE_SIMPLIFIED:
52 self.coding_sm.append(CodingStateMachine(HZ_SM_MODEL))
53 self.coding_sm.append(CodingStateMachine(ISO2022CN_SM_MODEL))
54 if self.lang_filter & LanguageFilter.JAPANESE:
55 self.coding_sm.append(CodingStateMachine(ISO2022JP_SM_MODEL))
56 if self.lang_filter & LanguageFilter.KOREAN:
57 self.coding_sm.append(CodingStateMachine(ISO2022KR_SM_MODEL))
58 self.active_sm_count = 0
59 self._detected_charset: Optional[str] = None
60 self._detected_language: Optional[str] = None
61 self._state = ProbingState.DETECTING
62 self.reset()
63
64 def reset(self) -> None:
65 super().reset()
66 for coding_sm in self.coding_sm:
67 coding_sm.active = True
68 coding_sm.reset()
69 self.active_sm_count = len(self.coding_sm)
70 self._detected_charset = None
71 self._detected_language = None
72
73 @property
74 def charset_name(self) -> Optional[str]:
75 return self._detected_charset
76
77 @property
78 def language(self) -> Optional[str]:
79 return self._detected_language
80
81 def get_confidence(self) -> float:
82 return 0.99 if self._detected_charset else 0.00
83
84 def feed(self, byte_str: Union[bytes, bytearray]) -> ProbingState:
85 for c in byte_str:
86 for coding_sm in self.coding_sm:
87 if not coding_sm.active:
88 continue
89 coding_state = coding_sm.next_state(c)
90 if coding_state == MachineState.ERROR:
91 coding_sm.active = False
92 self.active_sm_count -= 1
93 if self.active_sm_count <= 0:
94 self._state = ProbingState.NOT_ME
95 return self.state
96 elif coding_state == MachineState.ITS_ME:
97 self._state = ProbingState.FOUND_IT
98 self._detected_charset = coding_sm.get_coding_state_machine()
99 self._detected_language = coding_sm.language
100 return self.state
101
102 return self.state