Coverage for /pythoncovmergedfiles/medio/medio/usr/local/lib/python3.11/site-packages/chardet/escprober.py: 95%

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 LanguageFilter, MachineState, ProbingState 

32from .escsm import ( 

33 HZ_SM_MODEL, 

34 ISO2022CN_SM_MODEL, 

35 ISO2022JP_SM_MODEL, 

36 ISO2022KR_SM_MODEL, 

37) 

38 

39 

40class EscCharSetProber(CharSetProber): 

41 """ 

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

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

44 identify these encodings. 

45 """ 

46 

47 def __init__(self, lang_filter: LanguageFilter = LanguageFilter.NONE) -> None: 

48 super().__init__(lang_filter=lang_filter) 

49 self.coding_sm = [] 

50 if self.lang_filter & LanguageFilter.CHINESE_SIMPLIFIED: 

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

52 self.coding_sm.append(CodingStateMachine(ISO2022CN_SM_MODEL)) 

53 if self.lang_filter & LanguageFilter.JAPANESE: 

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

55 if self.lang_filter & LanguageFilter.KOREAN: 

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

57 self.active_sm_count = 0 

58 self._detected_charset: Optional[str] = None 

59 self._detected_language: Optional[str] = None 

60 self._state = ProbingState.DETECTING 

61 self.reset() 

62 

63 def reset(self) -> None: 

64 super().reset() 

65 for coding_sm in self.coding_sm: 

66 coding_sm.active = True 

67 coding_sm.reset() 

68 self.active_sm_count = len(self.coding_sm) 

69 self._detected_charset = None 

70 self._detected_language = None 

71 

72 @property 

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

74 return self._detected_charset 

75 

76 @property 

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

78 return self._detected_language 

79 

80 def get_confidence(self) -> float: 

81 return 0.99 if self._detected_charset else 0.00 

82 

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

84 for c in byte_str: 

85 for coding_sm in self.coding_sm: 

86 if not coding_sm.active: 

87 continue 

88 coding_state = coding_sm.next_state(c) 

89 if coding_state == MachineState.ERROR: 

90 coding_sm.active = False 

91 self.active_sm_count -= 1 

92 if self.active_sm_count <= 0: 

93 self._state = ProbingState.NOT_ME 

94 return self.state 

95 elif coding_state == MachineState.ITS_ME: 

96 self._state = ProbingState.FOUND_IT 

97 self._detected_charset = coding_sm.get_coding_state_machine() 

98 self._detected_language = coding_sm.language 

99 return self.state 

100 

101 return self.state