Coverage for /pythoncovmergedfiles/medio/medio/usr/local/lib/python3.11/site-packages/IPython/utils/openpy.py: 26%

1""" 

2Tools to open .py files as Unicode, using the encoding specified within the file, 

3as per PEP 263. 

4 

5Much of the code is taken from the tokenize module in Python 3.2. 

6""" 

7 

8import io 

9from io import TextIOWrapper, BytesIO 

10from pathlib import Path 

11import re 

12from tokenize import open, detect_encoding 

13 

14cookie_re = re.compile(r"coding[:=]\s*([-\w.]+)", re.UNICODE) 

15cookie_comment_re = re.compile(r"^\s*#.*coding[:=]\s*([-\w.]+)", re.UNICODE) 

16 

17def source_to_unicode(txt, errors='replace', skip_encoding_cookie=True): 

18 """Converts a bytes string with python source code to unicode. 

19 

20 Unicode strings are passed through unchanged. Byte strings are checked 

21 for the python source file encoding cookie to determine encoding. 

22 txt can be either a bytes buffer or a string containing the source 

23 code. 

24 """ 

25 if isinstance(txt, str): 

26 return txt 

27 if isinstance(txt, bytes): 

28 buffer = BytesIO(txt) 

29 else: 

30 buffer = txt 

31 try: 

32 encoding, _ = detect_encoding(buffer.readline) 

33 except SyntaxError: 

34 encoding = "ascii" 

35 buffer.seek(0) 

36 with TextIOWrapper(buffer, encoding, errors=errors, line_buffering=True) as text: 

37 text.mode = 'r' 

38 if skip_encoding_cookie: 

39 return u"".join(strip_encoding_cookie(text)) 

40 else: 

41 return text.read() 

42 

43def strip_encoding_cookie(filelike): 

44 """Generator to pull lines from a text-mode file, skipping the encoding 

45 cookie if it is found in the first two lines. 

46 """ 

47 it = iter(filelike) 

48 try: 

49 first = next(it) 

50 if not cookie_comment_re.match(first): 

51 yield first 

52 second = next(it) 

53 if not cookie_comment_re.match(second): 

54 yield second 

55 except StopIteration: 

56 return 

57 

58 yield from it 

59 

60def read_py_file(filename, skip_encoding_cookie=True): 

61 """Read a Python file, using the encoding declared inside the file. 

62 

63 Parameters 

64 ---------- 

65 filename : str 

66 The path to the file to read. 

67 skip_encoding_cookie : bool 

68 If True (the default), and the encoding declaration is found in the first 

69 two lines, that line will be excluded from the output. 

70 

71 Returns 

72 ------- 

73 A unicode string containing the contents of the file. 

74 """ 

75 filepath = Path(filename) 

76 with open(filepath) as f: # the open function defined in this module. 

77 if skip_encoding_cookie: 

78 return "".join(strip_encoding_cookie(f)) 

79 else: 

80 return f.read() 

81 

82def read_py_url(url, errors='replace', skip_encoding_cookie=True): 

83 """Read a Python file from a URL, using the encoding declared inside the file. 

84 

85 Parameters 

86 ---------- 

87 url : str 

88 The URL from which to fetch the file. 

89 errors : str 

90 How to handle decoding errors in the file. Options are the same as for 

91 bytes.decode(), but here 'replace' is the default. 

92 skip_encoding_cookie : bool 

93 If True (the default), and the encoding declaration is found in the first 

94 two lines, that line will be excluded from the output. 

95 

96 Returns 

97 ------- 

98 A unicode string containing the contents of the file. 

99 """ 

100 # Deferred import for faster start 

101 from urllib.request import urlopen 

102 response = urlopen(url) 

103 buffer = io.BytesIO(response.read()) 

104 return source_to_unicode(buffer, errors, skip_encoding_cookie)