third_party/protobuf/python/google/protobuf/text_encoding.py

   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 #PY25 compatible for GAE.
  32 #
  33 """Encoding related utilities."""
  34
  35 import re
  36 import sys  ##PY25
  37
  38 # Lookup table for utf8
  39 _cescape_utf8_to_str = [chr(i) for i in xrange(0, 256)]
  40 _cescape_utf8_to_str[9] = r'\t'  # optional escape
  41 _cescape_utf8_to_str[10] = r'\n'  # optional escape
  42 _cescape_utf8_to_str[13] = r'\r'  # optional escape
  43 _cescape_utf8_to_str[39] = r"\'"  # optional escape
  44
  45 _cescape_utf8_to_str[34] = r'\"'  # necessary escape
  46 _cescape_utf8_to_str[92] = r'\\'  # necessary escape
  47
  48 # Lookup table for non-utf8, with necessary escapes at (o >= 127 or o < 32)
  49 _cescape_byte_to_str = ([r'\%03o' % i for i in xrange(0, 32)] +
  50                         [chr(i) for i in xrange(32, 127)] +
  51                         [r'\%03o' % i for i in xrange(127, 256)])
  52 _cescape_byte_to_str[9] = r'\t'  # optional escape
  53 _cescape_byte_to_str[10] = r'\n'  # optional escape
  54 _cescape_byte_to_str[13] = r'\r'  # optional escape
  55 _cescape_byte_to_str[39] = r"\'"  # optional escape
  56
  57 _cescape_byte_to_str[34] = r'\"'  # necessary escape
  58 _cescape_byte_to_str[92] = r'\\'  # necessary escape
  59
  60
  61 def CEscape(text, as_utf8):
  62   """Escape a bytes string for use in an ascii protocol buffer.
  63
  64   text.encode('string_escape') does not seem to satisfy our needs as it
  65   encodes unprintable characters using two-digit hex escapes whereas our
  66   C++ unescaping function allows hex escapes to be any length.  So,
  67   "\0011".encode('string_escape') ends up being "\\x011", which will be
  68   decoded in C++ as a single-character string with char code 0x11.
  69
  70   Args:
  71     text: A byte string to be escaped
  72     as_utf8: Specifies if result should be returned in UTF-8 encoding
  73   Returns:
  74     Escaped string
  75   """
  76   # PY3 hack: make Ord work for str and bytes:
  77   # //platforms/networking/data uses unicode here, hence basestring.
  78   Ord = ord if isinstance(text, basestring) else lambda x: x
  79   if as_utf8:
  80     return ''.join(_cescape_utf8_to_str[Ord(c)] for c in text)
  81   return ''.join(_cescape_byte_to_str[Ord(c)] for c in text)
  82
  83
  84 _CUNESCAPE_HEX = re.compile(r'(\\+)x([0-9a-fA-F])(?![0-9a-fA-F])')
  85 _cescape_highbit_to_str = ([chr(i) for i in range(0, 127)] +
  86                            [r'\%03o' % i for i in range(127, 256)])
  87
  88
  89 def CUnescape(text):
  90   """Unescape a text string with C-style escape sequences to UTF-8 bytes."""
  91
  92   def ReplaceHex(m):
  93     # Only replace the match if the number of leading back slashes is odd. i.e.
  94     # the slash itself is not escaped.
  95     if len(m.group(1)) & 1:
  96       return m.group(1) + 'x0' + m.group(2)
  97     return m.group(0)
  98
  99   # This is required because the 'string_escape' encoding doesn't
 100   # allow single-digit hex escapes (like '\xf').
 101   result = _CUNESCAPE_HEX.sub(ReplaceHex, text)
 102
 103   if sys.version_info[0] < 3:  ##PY25
 104 ##!PY25  if str is bytes:  # PY2
 105     return result.decode('string_escape')
 106   result = ''.join(_cescape_highbit_to_str[ord(c)] for c in result)
 107   return (result.encode('ascii')  # 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'))