Coverage for /pythoncovmergedfiles/medio/medio/usr/local/lib/python3.8/site-packages/charset_normalizer/legacy.py: 26%

1from typing import Any, Dict, Optional, Union 

2from warnings import warn 

3 

4from .api import from_bytes 

5from .constant import CHARDET_CORRESPONDENCE 

6 

7 

8def detect( 

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

10) -> Dict[str, Optional[Union[str, float]]]: 

11 """ 

12 chardet legacy method 

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

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

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

16 further information. Not planned for removal. 

17 

18 :param byte_str: The byte sequence to examine. 

19 :param should_rename_legacy: Should we rename legacy encodings 

20 to their more modern equivalents? 

21 """ 

22 if len(kwargs): 

23 warn( 

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

25 ) 

26 

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

28 raise TypeError( # pragma: nocover 

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

30 "{0}".format(type(byte_str)) 

31 ) 

32 

33 if isinstance(byte_str, bytearray): 

34 byte_str = bytes(byte_str) 

35 

36 r = from_bytes(byte_str).best() 

37 

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

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

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

41 

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

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

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

45 encoding += "_sig" 

46 

47 if should_rename_legacy is False and encoding in CHARDET_CORRESPONDENCE: 

48 encoding = CHARDET_CORRESPONDENCE[encoding] 

49 

50 return { 

51 "encoding": encoding, 

52 "language": language, 

53 "confidence": confidence, 

54 }