aboutsummaryrefslogtreecommitdiff
path: root/frozen_deps/Cryptodome/Util/py3compat.py
blob: 40ef752eec9abf3632d2475849421a6759ae39ce (plain) (blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
# -*- coding: utf-8 -*-
#
#  Util/py3compat.py : Compatibility code for handling Py3k / Python 2.x
#
# Written in 2010 by Thorsten Behrens
#
# ===================================================================
# The contents of this file are dedicated to the public domain.  To
# the extent that dedication to the public domain is not available,
# everyone is granted a worldwide, perpetual, royalty-free,
# non-exclusive license to exercise all rights associated with the
# contents of this file for any purpose whatsoever.
# No rights are reserved.
#
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
# NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
# BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
# ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
# CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
# SOFTWARE.
# ===================================================================

"""Compatibility code for handling string/bytes changes from Python 2.x to Py3k

In Python 2.x, strings (of type ''str'') contain binary data, including encoded
Unicode text (e.g. UTF-8).  The separate type ''unicode'' holds Unicode text.
Unicode literals are specified via the u'...' prefix.  Indexing or slicing
either type always produces a string of the same type as the original.
Data read from a file is always of '''str'' type.

In Python 3.x, strings (type ''str'') may only contain Unicode text. The u'...'
prefix and the ''unicode'' type are now redundant.  A new type (called
''bytes'') has to be used for binary data (including any particular
''encoding'' of a string).  The b'...' prefix allows one to specify a binary
literal.  Indexing or slicing a string produces another string.  Slicing a byte
string produces another byte string, but the indexing operation produces an
integer.  Data read from a file is of '''str'' type if the file was opened in
text mode, or of ''bytes'' type otherwise.

Since PyCryptodome aims at supporting both Python 2.x and 3.x, the following helper
functions are used to keep the rest of the library as independent as possible
from the actual Python version.

In general, the code should always deal with binary strings, and use integers
instead of 1-byte character strings.

b(s)
    Take a text string literal (with no prefix or with u'...' prefix) and
    make a byte string.
bchr(c)
    Take an integer and make a 1-character byte string.
bord(c)
    Take the result of indexing on a byte string and make an integer.
tobytes(s)
    Take a text string, a byte string, or a sequence of character taken from
    a byte string and make a byte string.
"""

import sys
import abc


if sys.version_info[0] == 2:
    def b(s):
        return s
    def bchr(s):
        return chr(s)
    def bstr(s):
        return str(s)
    def bord(s):
        return ord(s)
    def tobytes(s, encoding="latin-1"):
        if isinstance(s, unicode):
            return s.encode(encoding)
        elif isinstance(s, str):
            return s
        elif isinstance(s, bytearray):
            return bytes(s)
        else:
            return ''.join(s)
    def tostr(bs):
        return bs
    def byte_string(s):
        return isinstance(s, str)

    # In Pyton 2.x, StringIO is a stand-alone module
    from StringIO import StringIO as BytesIO

    from sys import maxint

    if sys.version_info[1] < 7:
        import types
        _memoryview = types.NoneType
    else:
        _memoryview = memoryview
    
    iter_range = xrange

    def is_native_int(x):
        return isinstance(x, (int, long))

    def is_string(x):
        return isinstance(x, basestring)

    ABC = abc.ABCMeta('ABC', (object,), {'__slots__': ()})

else:
    def b(s):
       return s.encode("latin-1") # utf-8 would cause some side-effects we don't want
    def bchr(s):
        return bytes([s])
    def bstr(s):
        if isinstance(s,str):
            return bytes(s,"latin-1")
        else:
            return bytes(s)
    def bord(s):
        return s
    def tobytes(s, encoding="latin-1"):
        if isinstance(s, bytes):
            return s
        elif isinstance(s, bytearray):
            return bytes(s)
        elif isinstance(s,str):
            return s.encode(encoding)
        else:
            return bytes([s])
    def tostr(bs):
        return bs.decode("latin-1")
    def byte_string(s):
        return isinstance(s, bytes)

    # In Python 3.x, StringIO is a sub-module of io
    from io import BytesIO
    from sys import maxsize as maxint

    _memoryview = memoryview

    iter_range = range

    def is_native_int(x):
        return isinstance(x, int)

    def is_string(x):
        return isinstance(x, str)

    from abc import ABC


def _copy_bytes(start, end, seq):
    """Return an immutable copy of a sequence (byte string, byte array, memoryview)
    in a certain interval [start:seq]"""

    if isinstance(seq, _memoryview):
        return seq[start:end].tobytes()
    elif isinstance(seq, bytearray):
        return bytes(seq[start:end])
    else:
        return seq[start:end]

del sys
del abc