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 34import six 35 36# Lookup table for utf8 37_cescape_utf8_to_str = [chr(i) for i in range(0, 256)] 38_cescape_utf8_to_str[9] = r'\t' # optional escape 39_cescape_utf8_to_str[10] = r'\n' # optional escape 40_cescape_utf8_to_str[13] = r'\r' # optional escape 41_cescape_utf8_to_str[39] = r"\'" # optional escape 42 43_cescape_utf8_to_str[34] = r'\"' # necessary escape 44_cescape_utf8_to_str[92] = r'\\' # necessary escape 45 46# Lookup table for non-utf8, with necessary escapes at (o >= 127 or o < 32) 47_cescape_byte_to_str = ([r'\%03o' % i for i in range(0, 32)] + 48 [chr(i) for i in range(32, 127)] + 49 [r'\%03o' % i for i in range(127, 256)]) 50_cescape_byte_to_str[9] = r'\t' # optional escape 51_cescape_byte_to_str[10] = r'\n' # optional escape 52_cescape_byte_to_str[13] = r'\r' # optional escape 53_cescape_byte_to_str[39] = r"\'" # optional escape 54 55_cescape_byte_to_str[34] = r'\"' # necessary escape 56_cescape_byte_to_str[92] = r'\\' # necessary escape 57 58 59def CEscape(text, as_utf8): 60 """Escape a bytes string for use in an ascii protocol buffer. 61 62 text.encode('string_escape') does not seem to satisfy our needs as it 63 encodes unprintable characters using two-digit hex escapes whereas our 64 C++ unescaping function allows hex escapes to be any length. So, 65 "\0011".encode('string_escape') ends up being "\\x011", which will be 66 decoded in C++ as a single-character string with char code 0x11. 67 68 Args: 69 text: A byte string to be escaped 70 as_utf8: Specifies if result should be returned in UTF-8 encoding 71 Returns: 72 Escaped string 73 """ 74 # PY3 hack: make Ord work for str and bytes: 75 # //platforms/networking/data uses unicode here, hence basestring. 76 Ord = ord if isinstance(text, six.string_types) else lambda x: x 77 if as_utf8: 78 return ''.join(_cescape_utf8_to_str[Ord(c)] for c in text) 79 return ''.join(_cescape_byte_to_str[Ord(c)] for c in text) 80 81 82_CUNESCAPE_HEX = re.compile(r'(\\+)x([0-9a-fA-F])(?![0-9a-fA-F])') 83_cescape_highbit_to_str = ([chr(i) for i in range(0, 127)] + 84 [r'\%03o' % i for i in range(127, 256)]) 85 86 87def CUnescape(text): 88 """Unescape a text string with C-style escape sequences to UTF-8 bytes.""" 89 90 def ReplaceHex(m): 91 # Only replace the match if the number of leading back slashes is odd. i.e. 92 # the slash itself is not escaped. 93 if len(m.group(1)) & 1: 94 return m.group(1) + 'x0' + m.group(2) 95 return m.group(0) 96 97 # This is required because the 'string_escape' encoding doesn't 98 # allow single-digit hex escapes (like '\xf'). 99 result = _CUNESCAPE_HEX.sub(ReplaceHex, text) 100 101 if str is bytes: # PY2 102 return result.decode('string_escape') 103 result = ''.join(_cescape_highbit_to_str[ord(c)] for c in result) 104 return (result.encode('ascii') # Make it bytes to allow decode. 105 .decode('unicode_escape') 106 # Make it bytes again to return the proper type. 107 .encode('raw_unicode_escape')) 108