Coverage for /pythoncovmergedfiles/medio/medio/usr/local/lib/python3.11/site-packages/google/protobuf/text_encoding.py: 47%

1# Protocol Buffers - Google's data interchange format 

2# Copyright 2008 Google Inc. All rights reserved. 

3# 

4# Use of this source code is governed by a BSD-style 

5# license that can be found in the LICENSE file or at 

6# https://developers.google.com/open-source/licenses/bsd 

7"""Encoding related utilities.""" 

8 

9import re 

10 

11 

12def _AsciiIsPrint(i): 

13 return i >= 32 and i < 127 

14 

15 

16def _MakeStrEscapes(): 

17 ret = {} 

18 for i in range(0, 128): 

19 if not _AsciiIsPrint(i): 

20 ret[i] = r'\%03o' % i 

21 ret[ord('\t')] = r'\t' # optional escape 

22 ret[ord('\n')] = r'\n' # optional escape 

23 ret[ord('\r')] = r'\r' # optional escape 

24 ret[ord('"')] = r'\"' # necessary escape 

25 ret[ord("'")] = r'\'' # optional escape 

26 ret[ord('\\')] = r'\\' # necessary escape 

27 return ret 

28 

29 

30# Maps int -> char, performing string escapes. 

31_str_escapes = _MakeStrEscapes() 

32 

33# Maps int -> char, performing byte escaping and string escapes 

34_byte_escapes = {i: chr(i) for i in range(0, 256)} 

35_byte_escapes.update(_str_escapes) 

36_byte_escapes.update({i: r'\%03o' % i for i in range(128, 256)}) 

37 

38 

39def _DecodeUtf8EscapeErrors(text_bytes): 

40 ret = '' 

41 while text_bytes: 

42 try: 

43 ret += text_bytes.decode('utf-8').translate(_str_escapes) 

44 text_bytes = '' 

45 except UnicodeDecodeError as e: 

46 ret += text_bytes[: e.start].decode('utf-8').translate(_str_escapes) 

47 ret += _byte_escapes[text_bytes[e.start]] 

48 text_bytes = text_bytes[e.start + 1 :] 

49 return ret 

50 

51 

52def CEscape(text, as_utf8) -> str: 

53 """Escape a bytes string for use in an text protocol buffer. 

54 

55 Args: 

56 text: A byte string to be escaped. 

57 as_utf8: Specifies if result may contain non-ASCII characters. In Python 3 

58 this allows unescaped non-ASCII Unicode characters. In Python 2 the return 

59 value will be valid UTF-8 rather than only ASCII. 

60 

61 Returns: 

62 Escaped string (str). 

63 """ 

64 # Python's text.encode() 'string_escape' or 'unicode_escape' codecs do not 

65 # satisfy our needs; they encodes unprintable characters using two-digit hex 

66 # escapes whereas our C++ unescaping function allows hex escapes to be any 

67 # length. So, "\0011".encode('string_escape') ends up being "\\x011", which 

68 # will be decoded in C++ as a single-character string with char code 0x11. 

69 text_is_unicode = isinstance(text, str) 

70 if as_utf8: 

71 if text_is_unicode: 

72 return text.translate(_str_escapes) 

73 else: 

74 return _DecodeUtf8EscapeErrors(text) 

75 else: 

76 if text_is_unicode: 

77 text = text.encode('utf-8') 

78 return ''.join([_byte_escapes[c] for c in text]) 

79 

80 

81_CUNESCAPE_HEX = re.compile(r'(\\+)x([0-9a-fA-F])(?![0-9a-fA-F])') 

82 

83 

84def CUnescape(text: str) -> bytes: 

85 """Unescape a text string with C-style escape sequences to UTF-8 bytes. 

86 

87 Args: 

88 text: The data to parse in a str. 

89 

90 Returns: 

91 A byte string. 

92 """ 

93 

94 def ReplaceHex(m): 

95 # Only replace the match if the number of leading back slashes is odd. i.e. 

96 # the slash itself is not escaped. 

97 if len(m.group(1)) & 1: 

98 return m.group(1) + 'x0' + m.group(2) 

99 return m.group(0) 

100 

101 # This is required because the 'string_escape' encoding doesn't 

102 # allow single-digit hex escapes (like '\xf'). 

103 result = _CUNESCAPE_HEX.sub(ReplaceHex, text) 

104 

105 # Replaces Unicode escape sequences with their character equivalents. 

106 result = result.encode('raw_unicode_escape').decode('raw_unicode_escape') 

107 # Encode Unicode characters as UTF-8, then decode to Latin-1 escaping 

108 # unprintable characters. 

109 result = result.encode('utf-8').decode('unicode_escape') 

110 # Convert Latin-1 text back to a byte string (latin-1 codec also works here). 

111 return result.encode('latin-1')