• Home
  • Line#
  • Scopes#
  • Navigate#
  • Raw
  • Download
1# Protocol Buffers - Google's data interchange format
2# Copyright 2008 Google Inc.  All rights reserved.
3# https://developers.google.com/protocol-buffers/
4#
5# Redistribution and use in source and binary forms, with or without
6# modification, are permitted provided that the following conditions are
7# met:
8#
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
14# distribution.
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.
18#
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.
30
31"""Encoding related utilities."""
32import re
33
34_cescape_chr_to_symbol_map = {}
35_cescape_chr_to_symbol_map[9] = r'\t'  # optional escape
36_cescape_chr_to_symbol_map[10] = r'\n'  # optional escape
37_cescape_chr_to_symbol_map[13] = r'\r'  # optional escape
38_cescape_chr_to_symbol_map[34] = r'\"'  # necessary escape
39_cescape_chr_to_symbol_map[39] = r"\'"  # optional escape
40_cescape_chr_to_symbol_map[92] = r'\\'  # necessary escape
41
42# Lookup table for unicode
43_cescape_unicode_to_str = [chr(i) for i in range(0, 256)]
44for byte, string in _cescape_chr_to_symbol_map.items():
45  _cescape_unicode_to_str[byte] = string
46
47# Lookup table for non-utf8, with necessary escapes at (o >= 127 or o < 32)
48_cescape_byte_to_str = ([r'\%03o' % i for i in range(0, 32)] +
49                        [chr(i) for i in range(32, 127)] +
50                        [r'\%03o' % i for i in range(127, 256)])
51for byte, string in _cescape_chr_to_symbol_map.items():
52  _cescape_byte_to_str[byte] = string
53del byte, string
54
55
56def CEscape(text, as_utf8):
57  # type: (...) -> str
58  """Escape a bytes string for use in an text protocol buffer.
59
60  Args:
61    text: A byte string to be escaped.
62    as_utf8: Specifies if result may contain non-ASCII characters.
63        In Python 3 this allows unescaped non-ASCII Unicode characters.
64        In Python 2 the return value will be valid UTF-8 rather than only ASCII.
65  Returns:
66    Escaped string (str).
67  """
68  # Python's text.encode() 'string_escape' or 'unicode_escape' codecs do not
69  # satisfy our needs; they encodes unprintable characters using two-digit hex
70  # escapes whereas our C++ unescaping function allows hex escapes to be any
71  # length.  So, "\0011".encode('string_escape') ends up being "\\x011", which
72  # will be decoded in C++ as a single-character string with char code 0x11.
73  text_is_unicode = isinstance(text, str)
74  if as_utf8 and text_is_unicode:
75    # We're already unicode, no processing beyond control char escapes.
76    return text.translate(_cescape_chr_to_symbol_map)
77  ord_ = ord if text_is_unicode else lambda x: x  # bytes iterate as ints.
78  if as_utf8:
79    return ''.join(_cescape_unicode_to_str[ord_(c)] for c in text)
80  return ''.join(_cescape_byte_to_str[ord_(c)] for c in text)
81
82
83_CUNESCAPE_HEX = re.compile(r'(\\+)x([0-9a-fA-F])(?![0-9a-fA-F])')
84
85
86def CUnescape(text):
87  # type: (str) -> bytes
88  """Unescape a text string with C-style escape sequences to UTF-8 bytes.
89
90  Args:
91    text: The data to parse in a str.
92  Returns:
93    A byte string.
94  """
95
96  def ReplaceHex(m):
97    # Only replace the match if the number of leading back slashes is odd. i.e.
98    # the slash itself is not escaped.
99    if len(m.group(1)) & 1:
100      return m.group(1) + 'x0' + m.group(2)
101    return m.group(0)
102
103  # This is required because the 'string_escape' encoding doesn't
104  # allow single-digit hex escapes (like '\xf').
105  result = _CUNESCAPE_HEX.sub(ReplaceHex, text)
106
107  return (result.encode('utf-8')  # Make it bytes to allow decode.
108          .decode('unicode_escape')
109          # Make it bytes again to return the proper type.
110          .encode('raw_unicode_escape'))
111