1 # Protocol Buffers - Google's data interchange format
2 # Copyright 2008 Google Inc. All rights reserved.
3 # https://developers.google.com/protocol-buffers/
5 # Redistribution and use in source and binary forms, with or without
6 # modification, are permitted provided that the following conditions are
9 # * Redistributions of source code must retain the above copyright
10 # notice, this list of conditions and the following disclaimer.
11 # * Redistributions in binary form must reproduce the above
12 # copyright notice, this list of conditions and the following disclaimer
13 # in the documentation and/or other materials provided with the
15 # * Neither the name of Google Inc. nor the names of its
16 # contributors may be used to endorse or promote products derived from
17 # this software without specific prior written permission.
19 # THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
20 # "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
21 # LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
22 # A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
23 # OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
24 # SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
25 # LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
26 # DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
27 # THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
28 # (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
29 # OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
31 """Encoding related utilities."""
36 _cescape_chr_to_symbol_map = {}
37 _cescape_chr_to_symbol_map[9] = r'\t' # optional escape
38 _cescape_chr_to_symbol_map[10] = r'\n' # optional escape
39 _cescape_chr_to_symbol_map[13] = r'\r' # optional escape
40 _cescape_chr_to_symbol_map[34] = r'\"' # necessary escape
41 _cescape_chr_to_symbol_map[39] = r"\'" # optional escape
42 _cescape_chr_to_symbol_map[92] = r'\\' # necessary escape
44 # Lookup table for unicode
45 _cescape_unicode_to_str = [chr(i) for i in range(0, 256)]
46 for byte, string in _cescape_chr_to_symbol_map.items():
47 _cescape_unicode_to_str[byte] = string
49 # Lookup table for non-utf8, with necessary escapes at (o >= 127 or o < 32)
50 _cescape_byte_to_str = ([r'\%03o' % i for i in range(0, 32)] +
51 [chr(i) for i in range(32, 127)] +
52 [r'\%03o' % i for i in range(127, 256)])
53 for byte, string in _cescape_chr_to_symbol_map.items():
54 _cescape_byte_to_str[byte] = string
58 def CEscape(text, as_utf8):
60 """Escape a bytes string for use in an text protocol buffer.
63 text: A byte string to be escaped.
64 as_utf8: Specifies if result may contain non-ASCII characters.
65 In Python 3 this allows unescaped non-ASCII Unicode characters.
66 In Python 2 the return value will be valid UTF-8 rather than only ASCII.
70 # Python's text.encode() 'string_escape' or 'unicode_escape' codecs do not
71 # satisfy our needs; they encodes unprintable characters using two-digit hex
72 # escapes whereas our C++ unescaping function allows hex escapes to be any
73 # length. So, "\0011".encode('string_escape') ends up being "\\x011", which
74 # will be decoded in C++ as a single-character string with char code 0x11.
76 text_is_unicode = isinstance(text, str)
77 if as_utf8 and text_is_unicode:
78 # We're already unicode, no processing beyond control char escapes.
79 return text.translate(_cescape_chr_to_symbol_map)
80 ord_ = ord if text_is_unicode else lambda x: x # bytes iterate as ints.
84 return ''.join(_cescape_unicode_to_str[ord_(c)] for c in text)
85 return ''.join(_cescape_byte_to_str[ord_(c)] for c in text)
88 _CUNESCAPE_HEX = re.compile(r'(\\+)x([0-9a-fA-F])(?![0-9a-fA-F])')
92 # type: (str) -> bytes
93 """Unescape a text string with C-style escape sequences to UTF-8 bytes.
96 text: The data to parse in a str.
102 # Only replace the match if the number of leading back slashes is odd. i.e.
103 # the slash itself is not escaped.
104 if len(m.group(1)) & 1:
105 return m.group(1) + 'x0' + m.group(2)
108 # This is required because the 'string_escape' encoding doesn't
109 # allow single-digit hex escapes (like '\xf').
110 result = _CUNESCAPE_HEX.sub(ReplaceHex, text)
113 return result.decode('string_escape')
114 return (result.encode('utf-8') # PY3: Make it bytes to allow decode.
115 .decode('unicode_escape')
116 # Make it bytes again to return the proper type.
117 .encode('raw_unicode_escape'))