Coverage for /pythoncovmergedfiles/medio/medio/usr/local/lib/python3.11/site-packages/chardet/escprober.py: 98%

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 Optional, Union 

28 

29from .charsetprober import CharSetProber 

30from .codingstatemachine import CodingStateMachine 

31from .enums import EncodingEra, LanguageFilter, MachineState, ProbingState 

32from .escsm import ( 

33 HZ_SM_MODEL, 

34 ISO2022JP_SM_MODEL, 

35 ISO2022KR_SM_MODEL, 

36) 

37 

38 

39class EscCharSetProber(CharSetProber): 

40 """ 

41 This CharSetProber uses a "code scheme" approach for detecting encodings, 

42 whereby easily recognizable escape or shift sequences are relied on to 

43 identify these encodings. 

44 """ 

45 

46 def __init__( 

47 self, 

48 lang_filter: LanguageFilter = LanguageFilter.ALL, 

49 encoding_era: EncodingEra = EncodingEra.ALL, 

50 ) -> None: 

51 super().__init__(lang_filter=lang_filter, encoding_era=encoding_era) 

52 self.coding_sm = [] 

53 if self.lang_filter & LanguageFilter.CHINESE_SIMPLIFIED: 

54 self.coding_sm.append(CodingStateMachine(HZ_SM_MODEL)) 

55 if self.lang_filter & LanguageFilter.JAPANESE: 

56 self.coding_sm.append(CodingStateMachine(ISO2022JP_SM_MODEL)) 

57 if self.lang_filter & LanguageFilter.KOREAN: 

58 self.coding_sm.append(CodingStateMachine(ISO2022KR_SM_MODEL)) 

59 self.active_sm_count = 0 

60 self._detected_charset: Optional[str] = None 

61 self._detected_language: Optional[str] = None 

62 self._state = ProbingState.DETECTING 

63 self.reset() 

64 

65 def reset(self) -> None: 

66 super().reset() 

67 for coding_sm in self.coding_sm: 

68 coding_sm.active = True 

69 coding_sm.reset() 

70 self.active_sm_count = len(self.coding_sm) 

71 self._detected_charset = None 

72 self._detected_language = None 

73 

74 @property 

75 def charset_name(self) -> Optional[str]: 

76 return self._detected_charset 

77 

78 @property 

79 def language(self) -> Optional[str]: 

80 return self._detected_language 

81 

82 def get_confidence(self) -> float: 

83 return 0.99 if self._detected_charset else 0.00 

84 

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

86 for c in byte_str: 

87 for coding_sm in self.coding_sm: 

88 if not coding_sm.active: 

89 continue 

90 coding_state = coding_sm.next_state(c) 

91 if coding_state == MachineState.ERROR: 

92 coding_sm.active = False 

93 self.active_sm_count -= 1 

94 if self.active_sm_count <= 0: 

95 self._state = ProbingState.NOT_ME 

96 return self.state 

97 elif coding_state == MachineState.ITS_ME: 

98 self._state = ProbingState.FOUND_IT 

99 self._detected_charset = coding_sm.get_coding_state_machine() 

100 self._detected_language = coding_sm.language 

101 return self.state 

102 

103 return self.state