Coverage for /pythoncovmergedfiles/medio/medio/usr/local/lib/python3.11/site-packages/chardet/eucjpprober.py: 94%

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 EUCJPDistributionAnalysis 

30from .codingstatemachine import CodingStateMachine 

31from .enums import MachineState, ProbingState 

32from .jpcntx import EUCJPContextAnalysis 

33from .mbcharsetprober import MultiByteCharSetProber 

34from .mbcssm import EUCJP_SM_MODEL 

35 

36 

37class EUCJPProber(MultiByteCharSetProber): 

38 def __init__(self) -> None: 

39 super().__init__() 

40 self.coding_sm = CodingStateMachine(EUCJP_SM_MODEL) 

41 self.distribution_analyzer = EUCJPDistributionAnalysis() 

42 self.context_analyzer = EUCJPContextAnalysis() 

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 "EUC-JP" 

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 # PY3K: byte_str is a byte array, so byte is an int, not a byte 

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(self._last_char, char_len) 

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

82 else: 

83 self.context_analyzer.feed(byte_str[i - 1 : i + 1], char_len) 

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

85 

86 self._last_char[0] = byte_str[-1] 

87 

88 if self.state == ProbingState.DETECTING: 

89 if self.context_analyzer.got_enough_data() and ( 

90 self.get_confidence() > self.SHORTCUT_THRESHOLD 

91 ): 

92 self._state = ProbingState.FOUND_IT 

93 

94 return self.state 

95 

96 def get_confidence(self) -> float: 

97 assert self.distribution_analyzer is not None 

98 

99 context_conf = self.context_analyzer.get_confidence() 

100 distrib_conf = self.distribution_analyzer.get_confidence() 

101 return max(context_conf, distrib_conf)