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
|
###############################################################################
#
# The MIT License (MIT)
#
# Copyright (c) Crossbar.io Technologies GmbH
#
# Permission is hereby granted, free of charge, to any person obtaining a copy
# of this software and associated documentation files (the "Software"), to deal
# in the Software without restriction, including without limitation the rights
# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
# copies of the Software, and to permit persons to whom the Software is
# furnished to do so, subject to the following conditions:
#
# The above copyright notice and this permission notice shall be included in
# all copies or substantial portions of the Software.
#
# 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.
#
###############################################################################
# Note: This code is a Python implementation of the algorithm
# "Flexible and Economical UTF-8 Decoder" by Bjoern Hoehrmann
# bjoern@hoehrmann.de, http://bjoern.hoehrmann.de/utf-8/decoder/dfa/
# flake8: noqa
__all__ = ("Utf8Validator",)
# Do NOT touch this code unless you know what you are doing!
# https://github.com/oberstet/scratchbox/tree/master/python/utf8
# DFA transitions
UTF8VALIDATOR_DFA = (
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, # 00..1f
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, # 20..3f
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, # 40..5f
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, # 60..7f
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, # 80..9f
7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, # a0..bf
8, 8, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, # c0..df
0xa, 0x3, 0x3, 0x3, 0x3, 0x3, 0x3, 0x3, 0x3, 0x3, 0x3, 0x3, 0x3, 0x4, 0x3, 0x3, # e0..ef
0xb, 0x6, 0x6, 0x6, 0x5, 0x8, 0x8, 0x8, 0x8, 0x8, 0x8, 0x8, 0x8, 0x8, 0x8, 0x8, # f0..ff
0x0, 0x1, 0x2, 0x3, 0x5, 0x8, 0x7, 0x1, 0x1, 0x1, 0x4, 0x6, 0x1, 0x1, 0x1, 0x1, # s0..s0
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 0, 1, 0, 1, 1, 1, 1, 1, 1, # s1..s2
1, 2, 1, 1, 1, 1, 1, 2, 1, 2, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 1, 1, 1, 1, 1, 1, 1, 1, # s3..s4
1, 2, 1, 1, 1, 1, 1, 1, 1, 2, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 3, 1, 3, 1, 1, 1, 1, 1, 1, # s5..s6
1, 3, 1, 1, 1, 1, 1, 3, 1, 3, 1, 1, 1, 1, 1, 1, 1, 3, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, # s7..s8
)
UTF8_ACCEPT = 0
UTF8_REJECT = 1
# convert DFA table to string (performance)
UTF8VALIDATOR_DFA_S = ''.join([chr(c) for c in UTF8VALIDATOR_DFA]) # pragma: no cover
class Utf8Validator(object):
"""
Incremental UTF-8 validator with constant memory consumption (minimal state).
Implements the algorithm "Flexible and Economical UTF-8 Decoder" by
Bjoern Hoehrmann (http://bjoern.hoehrmann.de/utf-8/decoder/dfa/).
"""
__slots__ = (
'_codepoint',
'_state',
'_index',
)
def __init__(self):
self._codepoint = None
self._state = None
self._index = None
self.reset()
def reset(self):
"""
Reset validator to start new incremental UTF-8 decode/validation.
"""
self._state = UTF8_ACCEPT # the empty string is valid UTF8
self._codepoint = 0
self._index = 0
def validate(self, ba):
"""
Incrementally validate a chunk of bytes provided as string.
Will return a quad ``(valid?, endsOnCodePoint?, currentIndex, totalIndex)``.
As soon as an octet is encountered which renders the octet sequence
invalid, a quad with ``valid? == False`` is returned. ``currentIndex`` returns
the index within the currently consumed chunk, and ``totalIndex`` the
index within the total consumed sequence that was the point of bail out.
When ``valid? == True``, currentIndex will be ``len(ba)`` and ``totalIndex`` the
total amount of consumed bytes.
"""
#
# The code here is written for optimal JITting in PyPy, not for best
# readability or particular elegance. Do NOT touch!
#
l = len(ba)
i = 0
state = self._state
while i < l:
# optimized version of decode(), since we are not interested in actual code points
state = ord(UTF8VALIDATOR_DFA_S[256 + (state << 4) + ord(UTF8VALIDATOR_DFA_S[ord(ba[i])])])
if state == UTF8_REJECT:
self._state = state
self._index += i
return False, False, i, self._index
i += 1
self._state = state
self._index += l
return True, state == UTF8_ACCEPT, l, self._index
|
