Coverage for /pythoncovmergedfiles/medio/medio/usr/local/lib/python3.11/site-packages/chardet/__init__.py: 36%

1######################## BEGIN LICENSE BLOCK ######################## 

2# This library is free software; you can redistribute it and/or 

3# modify it under the terms of the GNU Lesser General Public 

4# License as published by the Free Software Foundation; either 

5# version 2.1 of the License, or (at your option) any later version. 

6# 

7# This library is distributed in the hope that it will be useful, 

8# but WITHOUT ANY WARRANTY; without even the implied warranty of 

9# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU 

10# Lesser General Public License for more details. 

11# 

12# You should have received a copy of the GNU Lesser General Public 

13# License along with this library; if not, see 

14# <https://www.gnu.org/licenses/>. 

15######################### END LICENSE BLOCK ######################### 

16 

17from typing import List, Union 

18 

19from .charsetgroupprober import CharSetGroupProber 

20from .charsetprober import CharSetProber 

21from .enums import InputState 

22from .resultdict import ResultDict 

23from .universaldetector import UniversalDetector 

24from .version import VERSION, __version__ 

25 

26__all__ = ["UniversalDetector", "detect", "detect_all", "__version__", "VERSION"] 

27 

28 

29def detect( 

30 byte_str: Union[bytes, bytearray], should_rename_legacy: bool = False 

31) -> ResultDict: 

32 """ 

33 Detect the encoding of the given byte string. 

34 

35 :param byte_str: The byte sequence to examine. 

36 :type byte_str: ``bytes`` or ``bytearray`` 

37 :param should_rename_legacy: Should we rename legacy encodings 

38 to their more modern equivalents? 

39 :type should_rename_legacy: ``bool`` 

40 """ 

41 if not isinstance(byte_str, bytearray): 

42 if not isinstance(byte_str, bytes): 

43 raise TypeError( 

44 f"Expected object of type bytes or bytearray, got: {type(byte_str)}" 

45 ) 

46 byte_str = bytearray(byte_str) 

47 detector = UniversalDetector(should_rename_legacy=should_rename_legacy) 

48 detector.feed(byte_str) 

49 return detector.close() 

50 

51 

52def detect_all( 

53 byte_str: Union[bytes, bytearray], 

54 ignore_threshold: bool = False, 

55 should_rename_legacy: bool = False, 

56) -> List[ResultDict]: 

57 """ 

58 Detect all the possible encodings of the given byte string. 

59 

60 :param byte_str: The byte sequence to examine. 

61 :type byte_str: ``bytes`` or ``bytearray`` 

62 :param ignore_threshold: Include encodings that are below 

63 ``UniversalDetector.MINIMUM_THRESHOLD`` 

64 in results. 

65 :type ignore_threshold: ``bool`` 

66 :param should_rename_legacy: Should we rename legacy encodings 

67 to their more modern equivalents? 

68 :type should_rename_legacy: ``bool`` 

69 """ 

70 if not isinstance(byte_str, bytearray): 

71 if not isinstance(byte_str, bytes): 

72 raise TypeError( 

73 f"Expected object of type bytes or bytearray, got: {type(byte_str)}" 

74 ) 

75 byte_str = bytearray(byte_str) 

76 

77 detector = UniversalDetector(should_rename_legacy=should_rename_legacy) 

78 detector.feed(byte_str) 

79 detector.close() 

80 

81 if detector.input_state == InputState.HIGH_BYTE: 

82 results: List[ResultDict] = [] 

83 probers: List[CharSetProber] = [] 

84 for prober in detector.charset_probers: 

85 if isinstance(prober, CharSetGroupProber): 

86 probers.extend(p for p in prober.probers) 

87 else: 

88 probers.append(prober) 

89 for prober in probers: 

90 if ignore_threshold or prober.get_confidence() > detector.MINIMUM_THRESHOLD: 

91 charset_name = prober.charset_name or "" 

92 lower_charset_name = charset_name.lower() 

93 # Use Windows encoding name instead of ISO-8859 if we saw any 

94 # extra Windows-specific bytes 

95 if lower_charset_name.startswith("iso-8859") and detector.has_win_bytes: 

96 charset_name = detector.ISO_WIN_MAP.get( 

97 lower_charset_name, charset_name 

98 ) 

99 # Rename legacy encodings with superset encodings if asked 

100 if should_rename_legacy: 

101 charset_name = detector.LEGACY_MAP.get( 

102 charset_name.lower(), charset_name 

103 ) 

104 results.append({ 

105 "encoding": charset_name, 

106 "confidence": prober.get_confidence(), 

107 "language": prober.language, 

108 }) 

109 if len(results) > 0: 

110 return sorted(results, key=lambda result: -result["confidence"]) 

111 

112 return [detector.result]