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
|
/*
* Copyright (C) 2012-2016 Apple Inc. All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
* 1. Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* 2. Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in the
* documentation and/or other materials provided with the distribution.
*
* THIS SOFTWARE IS PROVIDED BY APPLE INC. ``AS IS'' AND ANY
* EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
* PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL APPLE INC. OR
* CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
* EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
* PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
* PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY
* OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
* (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
* OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
*/
#pragma once
#include <stdint.h>
#include <unicode/utypes.h>
WTF_ALLOW_UNSAFE_BUFFER_USAGE_BEGIN
namespace JSC { namespace Yarr {
// This set of data provides information for each UCS2 code point as to the set of code points
// that it should match under the ES6 case insensitive RegExp matching rules, specified in 21.2.2.8.2.
// The non-Unicode tables are autogenerated using YarrCanonicalize.js into YarrCanonicalize.cpp.
// The Unicode tables are autogenerated using the python script generateYarrCanonicalizeUnicode
// which creates YarrCanonicalizeUnicode.cpp.
enum UCS2CanonicalizationType {
CanonicalizeUnique, // No canonically equal values, e.g. 0x0.
CanonicalizeSet, // Value indicates a set in characterSetInfo.
CanonicalizeRangeLo, // Value is positive delta to pair, E.g. 0x41 has value 0x20, -> 0x61.
CanonicalizeRangeHi, // Value is positive delta to pair, E.g. 0x61 has value 0x20, -> 0x41.
CanonicalizeAlternatingAligned, // Aligned consequtive pair, e.g. 0x1f4,0x1f5.
CanonicalizeAlternatingUnaligned, // Unaligned consequtive pair, e.g. 0x241,0x242.
};
struct CanonicalizationRange {
char32_t begin;
char32_t end;
char32_t value;
UCS2CanonicalizationType type;
};
extern const size_t ucs2CanonicalizationRanges;
extern const char32_t* const ucs2CharacterSetInfo[];
extern const CanonicalizationRange ucs2RangeInfo[];
extern const uint16_t canonicalTableLChar[256];
extern const size_t UNICODE_CANONICALIZATION_RANGES;
extern const char32_t* const unicodeCharacterSetInfo[];
extern const CanonicalizationRange unicodeRangeInfo[];
enum class CanonicalMode { UCS2, Unicode };
inline const char32_t* canonicalCharacterSetInfo(unsigned index, CanonicalMode canonicalMode)
{
const char32_t* const* rangeInfo = canonicalMode == CanonicalMode::UCS2 ? ucs2CharacterSetInfo : unicodeCharacterSetInfo;
return rangeInfo[index];
}
// This searches in log2 time over ~400-600 entries, so should typically result in 9 compares.
inline const CanonicalizationRange* canonicalRangeInfoFor(char32_t ch, CanonicalMode canonicalMode = CanonicalMode::UCS2)
{
const CanonicalizationRange* info = canonicalMode == CanonicalMode::UCS2 ? ucs2RangeInfo : unicodeRangeInfo;
size_t entries = canonicalMode == CanonicalMode::UCS2 ? ucs2CanonicalizationRanges : UNICODE_CANONICALIZATION_RANGES;
while (true) {
size_t candidate = entries >> 1;
const CanonicalizationRange* candidateInfo = info + candidate;
if (ch < candidateInfo->begin)
entries = candidate;
else if (ch <= candidateInfo->end)
return candidateInfo;
else {
info = candidateInfo + 1;
entries -= (candidate + 1);
}
}
}
// Should only be called for characters that have one canonically matching value.
inline char32_t getCanonicalPair(const CanonicalizationRange* info, char32_t ch)
{
ASSERT(ch >= info->begin && ch <= info->end);
switch (info->type) {
case CanonicalizeRangeLo:
return ch + info->value;
case CanonicalizeRangeHi:
return ch - info->value;
case CanonicalizeAlternatingAligned:
return ch ^ 1;
case CanonicalizeAlternatingUnaligned:
return ((ch - 1) ^ 1) + 1;
default:
RELEASE_ASSERT_NOT_REACHED();
}
RELEASE_ASSERT_NOT_REACHED();
return 0;
}
// Returns true if no other UCS2 codepoint can match this value.
inline bool isCanonicallyUnique(char32_t ch, CanonicalMode canonicalMode = CanonicalMode::UCS2)
{
return canonicalRangeInfoFor(ch, canonicalMode)->type == CanonicalizeUnique;
}
// Returns true if values are equal, under the canonicalization rules.
inline bool areCanonicallyEquivalent(char32_t a, char32_t b, CanonicalMode canonicalMode = CanonicalMode::UCS2)
{
auto* info = canonicalRangeInfoFor(a, canonicalMode);
switch (info->type) {
case CanonicalizeUnique:
return a == b;
case CanonicalizeSet: {
for (auto* set = canonicalCharacterSetInfo(info->value, canonicalMode); (a = *set); ++set) {
if (a == b)
return true;
}
return false;
}
case CanonicalizeRangeLo:
return (a == b) || (a + info->value == b);
case CanonicalizeRangeHi:
return (a == b) || (a - info->value == b);
case CanonicalizeAlternatingAligned:
return (a | 1) == (b | 1);
case CanonicalizeAlternatingUnaligned:
return ((a - 1) | 1) == ((b - 1) | 1);
}
RELEASE_ASSERT_NOT_REACHED();
return false;
}
} } // JSC::Yarr
WTF_ALLOW_UNSAFE_BUFFER_USAGE_END
|
