Coverage for /pythoncovmergedfiles/medio/medio/usr/local/lib/python3.11/site-packages/chardet/sjisprober.py: 93%

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, see 

24# <https://www.gnu.org/licenses/>. 

25######################### END LICENSE BLOCK ######################### 

26 

27from typing import Union 

28 

29from .chardistribution import SJISDistributionAnalysis 

30from .codingstatemachine import CodingStateMachine 

31from .enums import MachineState, ProbingState 

32from .jpcntx import SJISContextAnalysis 

33from .mbcharsetprober import MultiByteCharSetProber 

34from .mbcssm import SJIS_SM_MODEL 

35 

36 

37class SJISProber(MultiByteCharSetProber): 

38 def __init__(self) -> None: 

39 super().__init__() 

40 self.coding_sm = CodingStateMachine(SJIS_SM_MODEL) 

41 self.distribution_analyzer = SJISDistributionAnalysis() 

42 self.context_analyzer = SJISContextAnalysis() 

43 self.reset() 

44 

45 def reset(self) -> None: 

46 super().reset() 

47 self.context_analyzer.reset() 

48 

49 @property 

50 def charset_name(self) -> str: 

51 return self.context_analyzer.charset_name 

52 

53 @property 

54 def language(self) -> str: 

55 return "Japanese" 

56 

57 def feed(self, byte_str: Union[bytes, bytearray]) -> ProbingState: 

58 assert self.coding_sm is not None 

59 assert self.distribution_analyzer is not None 

60 

61 for i, byte in enumerate(byte_str): 

62 coding_state = self.coding_sm.next_state(byte) 

63 if coding_state == MachineState.ERROR: 

64 self.logger.debug( 

65 "%s %s prober hit error at byte %s", 

66 self.charset_name, 

67 self.language, 

68 i, 

69 ) 

70 self._state = ProbingState.NOT_ME 

71 break 

72 if coding_state == MachineState.ITS_ME: 

73 self._state = ProbingState.FOUND_IT 

74 break 

75 if coding_state == MachineState.START: 

76 char_len = self.coding_sm.get_current_charlen() 

77 if i == 0: 

78 self._last_char[1] = byte 

79 self.context_analyzer.feed( 

80 self._last_char[2 - char_len :], char_len 

81 ) 

82 self.distribution_analyzer.feed(self._last_char, char_len) 

83 else: 

84 self.context_analyzer.feed( 

85 byte_str[i + 1 - char_len : i + 3 - char_len], char_len 

86 ) 

87 self.distribution_analyzer.feed(byte_str[i - 1 : i + 1], char_len) 

88 

89 self._last_char[0] = byte_str[-1] 

90 

91 if self.state == ProbingState.DETECTING: 

92 if self.context_analyzer.got_enough_data() and ( 

93 self.get_confidence() > self.SHORTCUT_THRESHOLD 

94 ): 

95 self._state = ProbingState.FOUND_IT 

96 

97 return self.state 

98 

99 def get_confidence(self) -> float: 

100 assert self.distribution_analyzer is not None 

101 

102 context_conf = self.context_analyzer.get_confidence() 

103 distrib_conf = self.distribution_analyzer.get_confidence() 

104 return max(context_conf, distrib_conf)