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
|
/*
* Copyright (C) 2012 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.
*/
#ifndef YarrCanonicalizeUCS2_H
#define YarrCanonicalizeUCS2_H
#include <stdint.h>
#include <wtf/unicode/Unicode.h>
namespace JSC { namespace Yarr {
// This set of data (autogenerated using YarrCanonicalizeUCS2.js into YarrCanonicalizeUCS2.cpp)
// provides information for each UCS2 code point as to the set of code points that it should
// match under the ES5.1 case insensitive RegExp matching rules, specified in 15.10.2.8.
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 UCS2CanonicalizationRange { uint16_t begin, end, value, type; };
extern const size_t UCS2_CANONICALIZATION_RANGES;
extern uint16_t* characterSetInfo[];
extern UCS2CanonicalizationRange rangeInfo[];
// This table is similar to the full rangeInfo table, however this maps from UCS2 codepoints to
// the set of Latin1 codepoints that could match.
enum LatinCanonicalizationType {
CanonicalizeLatinSelf, // This character is in the Latin1 range, but has no canonical equivalent in the range.
CanonicalizeLatinMask0x20, // One of a pair of characters, under the mask 0x20.
CanonicalizeLatinOther, // This character is not in the Latin1 range, but canonicalizes to another that is.
CanonicalizeLatinInvalid, // Cannot match against Latin1 input.
};
struct LatinCanonicalizationRange { uint16_t begin, end, value, type; };
extern const size_t LATIN_CANONICALIZATION_RANGES;
extern LatinCanonicalizationRange latinRangeInfo[];
// This searches in log2 time over ~364 entries, so should typically result in 8 compares.
inline UCS2CanonicalizationRange* rangeInfoFor(UChar ch)
{
UCS2CanonicalizationRange* info = rangeInfo;
size_t entries = UCS2_CANONICALIZATION_RANGES;
while (true) {
size_t candidate = entries >> 1;
UCS2CanonicalizationRange* 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 UChar getCanonicalPair(UCS2CanonicalizationRange* info, UChar 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:
ASSERT_NOT_REACHED();
}
ASSERT_NOT_REACHED();
return 0;
}
// Returns true if no other UCS2 codepoint can match this value.
inline bool isCanonicallyUnique(UChar ch)
{
return rangeInfoFor(ch)->type == CanonicalizeUnique;
}
// Returns true if values are equal, under the canonicalization rules.
inline bool areCanonicallyEquivalent(UChar a, UChar b)
{
UCS2CanonicalizationRange* info = rangeInfoFor(a);
switch (info->type) {
case CanonicalizeUnique:
return a == b;
case CanonicalizeSet: {
for (uint16_t* set = characterSetInfo[info->value]; (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);
}
ASSERT_NOT_REACHED();
return false;
}
} } // JSC::Yarr
#endif
|
