1 ######################## BEGIN LICENSE BLOCK ########################
2 # The Original Code is Mozilla Communicator client code.
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.
10 # Mark Pilgrim - port to Python
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.
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.
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
26 ######################### END LICENSE BLOCK #########################
28 from typing import List, Optional, Union
30 from .charsetprober import CharSetProber
31 from .enums import LanguageFilter, ProbingState
34 class CharSetGroupProber(CharSetProber):
35 def __init__(self, lang_filter: LanguageFilter = LanguageFilter.NONE) -> None:
36 super().__init__(lang_filter=lang_filter)
38 self.probers: List[CharSetProber] = []
39 self._best_guess_prober: Optional[CharSetProber] = None
41 def reset(self) -> None:
44 for prober in self.probers:
48 self._best_guess_prober = None
51 def charset_name(self) -> Optional[str]:
52 if not self._best_guess_prober:
54 if not self._best_guess_prober:
56 return self._best_guess_prober.charset_name
59 def language(self) -> Optional[str]:
60 if not self._best_guess_prober:
62 if not self._best_guess_prober:
64 return self._best_guess_prober.language
66 def feed(self, byte_str: Union[bytes, bytearray]) -> ProbingState:
67 for prober in self.probers:
70 state = prober.feed(byte_str)
73 if state == ProbingState.FOUND_IT:
74 self._best_guess_prober = prober
75 self._state = ProbingState.FOUND_IT
77 if state == ProbingState.NOT_ME:
80 if self._active_num <= 0:
81 self._state = ProbingState.NOT_ME
85 def get_confidence(self) -> float:
87 if state == ProbingState.FOUND_IT:
89 if state == ProbingState.NOT_ME:
92 self._best_guess_prober = None
93 for prober in self.probers:
95 self.logger.debug("%s not active", prober.charset_name)
97 conf = prober.get_confidence()
99 "%s %s confidence = %s", prober.charset_name, prober.language, conf
103 self._best_guess_prober = prober
104 if not self._best_guess_prober: