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 

8"""Encoding related utilities.""" 

9import re 

10 

11def _AsciiIsPrint(i): 

12 return i >= 32 and i < 127 

13 

14def _MakeStrEscapes(): 

15 ret = {} 

16 for i in range(0, 128): 

17 if not _AsciiIsPrint(i): 

18 ret[i] = r'\%03o' % i 

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

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

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

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

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

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

25 return ret 

26 

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

28_str_escapes = _MakeStrEscapes() 

29 

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

31_byte_escapes = {i: chr(i) for i in range(0, 256)} 

32_byte_escapes.update(_str_escapes) 

33_byte_escapes.update({i: r'\%03o' % i for i in range(128, 256)}) 

34 

35 

36def _DecodeUtf8EscapeErrors(text_bytes): 

37 ret = '' 

38 while text_bytes: 

39 try: 

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

41 text_bytes = '' 

42 except UnicodeDecodeError as e: 

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

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

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

46 return ret 

47 

48 

49def CEscape(text, as_utf8) -> str: 

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

51 

52 Args: 

53 text: A byte string to be escaped. 

54 as_utf8: Specifies if result may contain non-ASCII characters. 

55 In Python 3 this allows unescaped non-ASCII Unicode characters. 

56 In Python 2 the return value will be valid UTF-8 rather than only ASCII. 

57 Returns: 

58 Escaped string (str). 

59 """ 

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

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

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

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

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

65 text_is_unicode = isinstance(text, str) 

66 if as_utf8: 

67 if text_is_unicode: 

68 return text.translate(_str_escapes) 

69 else: 

70 return _DecodeUtf8EscapeErrors(text) 

71 else: 

72 if text_is_unicode: 

73 text = text.encode('utf-8') 

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

75 

76 

77_CUNESCAPE_HEX = re.compile(r'(\\+)x([0-9a-fA-F])(?![0-9a-fA-F])') 

78 

79 

80def CUnescape(text: str) -> bytes: 

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

82 

83 Args: 

84 text: The data to parse in a str. 

85 Returns: 

86 A byte string. 

87 """ 

88 

89 def ReplaceHex(m): 

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

91 # the slash itself is not escaped. 

92 if len(m.group(1)) & 1: 

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

94 return m.group(0) 

95 

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

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

98 result = _CUNESCAPE_HEX.sub(ReplaceHex, text) 

99 

100 # Replaces Unicode escape sequences with their character equivalents. 

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

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

103 # unprintable characters. 

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

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

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