python/google/net/proto2/python/public/text_encoding.py

   1 #!/usr/bin/env python
   2 #
   3 # Copyright 2007 Google Inc.
   4 #
   5 # Licensed under the Apache License, Version 2.0 (the "License");
   6 # you may not use this file except in compliance with the License.
   7 # You may obtain a copy of the License at
   8 #
   9 #     http://www.apache.org/licenses/LICENSE-2.0
  10 #
  11 # Unless required by applicable law or agreed to in writing, software
  12 # distributed under the License is distributed on an "AS IS" BASIS,
  13 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
  14 # See the License for the specific language governing permissions and
  15 # limitations under the License.
  16 #
  17
  18
  19 """Encoding related utilities."""
  20
  21 import re
  22 import sys
  23
  24
  25 _cescape_utf8_to_str = [chr(i) for i in xrange(0, 256)]
  26 _cescape_utf8_to_str[9] = r'\t'
  27 _cescape_utf8_to_str[10] = r'\n'
  28 _cescape_utf8_to_str[13] = r'\r'
  29 _cescape_utf8_to_str[39] = r"\'"
  30
  31 _cescape_utf8_to_str[34] = r'\"'
  32 _cescape_utf8_to_str[92] = r'\\'
  33
  34
  35 _cescape_byte_to_str = ([r'\%03o' % i for i in xrange(0, 32)] +
  36                         [chr(i) for i in xrange(32, 127)] +
  37                         [r'\%03o' % i for i in xrange(127, 256)])
  38 _cescape_byte_to_str[9] = r'\t'
  39 _cescape_byte_to_str[10] = r'\n'
  40 _cescape_byte_to_str[13] = r'\r'
  41 _cescape_byte_to_str[39] = r"\'"
  42
  43 _cescape_byte_to_str[34] = r'\"'
  44 _cescape_byte_to_str[92] = r'\\'
  45
  46
  47 def CEscape(text, as_utf8):
  48   """Escape a bytes string for use in an ascii protocol buffer.
  49
  50   text.encode('string_escape') does not seem to satisfy our needs as it
  51   encodes unprintable characters using two-digit hex escapes whereas our
  52   C++ unescaping function allows hex escapes to be any length.  So,
  53   "\0011".encode('string_escape') ends up being "\\x011", which will be
  54   decoded in C++ as a single-character string with char code 0x11.
  55
  56   Args:
  57     text: A byte string to be escaped
  58     as_utf8: Specifies if result should be returned in UTF-8 encoding
  59   Returns:
  60     Escaped string
  61   """
  62
  63
  64   Ord = ord if isinstance(text, basestring) else lambda x: x
  65   if as_utf8:
  66     return ''.join(_cescape_utf8_to_str[Ord(c)] for c in text)
  67   return ''.join(_cescape_byte_to_str[Ord(c)] for c in text)
  68
  69
  70 _CUNESCAPE_HEX = re.compile(r'(\\+)x([0-9a-fA-F])(?![0-9a-fA-F])')
  71 _cescape_highbit_to_str = ([chr(i) for i in range(0, 127)] +
  72                            [r'\%03o' % i for i in range(127, 256)])
  73
  74
  75 def CUnescape(text):
  76   """Unescape a text string with C-style escape sequences to UTF-8 bytes."""
  77
  78   def ReplaceHex(m):
  79
  80
  81     if len(m.group(1)) & 1:
  82       return m.group(1) + 'x0' + m.group(2)
  83     return m.group(0)
  84
  85
  86
  87   result = _CUNESCAPE_HEX.sub(ReplaceHex, text)
  88
  89   if sys.version_info[0] < 3:
  90
  91     return result.decode('string_escape')
  92   result = ''.join(_cescape_highbit_to_str[ord(c)] for c in result)
  93   return (result.encode('ascii')
  94           .decode('unicode_escape')
  95
  96           .encode('raw_unicode_escape'))