Coverage for /pythoncovmergedfiles/medio/medio/usr/local/lib/python3.10/site-packages/charset_normalizer/legacy.py: 27%

1from __future__ import annotations 

2 

3from typing import TYPE_CHECKING, Any, Optional 

4from warnings import warn 

5 

6from .api import from_bytes 

7from .constant import CHARDET_CORRESPONDENCE 

8 

9# TODO: remove this check when dropping Python 3.7 support 

10if TYPE_CHECKING: 

11 from typing_extensions import TypedDict 

12 

13 class ResultDict(TypedDict): 

14 encoding: Optional[str] 

15 language: str 

16 confidence: Optional[float] 

17 

18 

19def detect( 

20 byte_str: bytes, should_rename_legacy: bool = False, **kwargs: Any 

21) -> ResultDict: 

22 """ 

23 chardet legacy method 

24 Detect the encoding of the given byte string. It should be mostly backward-compatible. 

25 Encoding name will match Chardet own writing whenever possible. (Not on encoding name unsupported by it) 

26 This function is deprecated and should be used to migrate your project easily, consult the documentation for 

27 further information. Not planned for removal. 

28 

29 :param byte_str: The byte sequence to examine. 

30 :param should_rename_legacy: Should we rename legacy encodings 

31 to their more modern equivalents? 

32 """ 

33 if len(kwargs): 

34 warn( 

35 f"charset-normalizer disregard arguments '{','.join(list(kwargs.keys()))}' in legacy function detect()" 

36 ) 

37 

38 if not isinstance(byte_str, (bytearray, bytes)): 

39 raise TypeError( # pragma: nocover 

40 "Expected object of type bytes or bytearray, got: " 

41 "{0}".format(type(byte_str)) 

42 ) 

43 

44 if isinstance(byte_str, bytearray): 

45 byte_str = bytes(byte_str) 

46 

47 r = from_bytes(byte_str).best() 

48 

49 encoding = r.encoding if r is not None else None 

50 language = r.language if r is not None and r.language != "Unknown" else "" 

51 confidence = 1.0 - r.chaos if r is not None else None 

52 

53 # Note: CharsetNormalizer does not return 'UTF-8-SIG' as the sig get stripped in the detection/normalization process 

54 # but chardet does return 'utf-8-sig' and it is a valid codec name. 

55 if r is not None and encoding == "utf_8" and r.bom: 

56 encoding += "_sig" 

57 

58 if should_rename_legacy is False and encoding in CHARDET_CORRESPONDENCE: 

59 encoding = CHARDET_CORRESPONDENCE[encoding] 

60 

61 return { 

62 "encoding": encoding, 

63 "language": language, 

64 "confidence": confidence, 

65 }