File: StringHasherInlines.h

package info (click to toggle)
webkit2gtk 2.48.3-1
  • links: PTS, VCS
  • area: main
  • in suites: trixie
  • size: 429,620 kB
  • sloc: cpp: 3,696,936; javascript: 194,444; ansic: 169,997; python: 46,499; asm: 19,276; ruby: 18,528; perl: 16,602; xml: 4,650; yacc: 2,360; sh: 2,098; java: 1,993; lex: 1,327; pascal: 366; makefile: 298
file content (140 lines) | stat: -rw-r--r-- 5,094 bytes parent folder | download | duplicates (6)
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
/*
 * Copyright (C) 2023 Apple Inc. All rights reserved.
 *
 * This library is free software; you can redistribute it and/or
 * modify it under the terms of the GNU Library General Public
 * License as published by the Free Software Foundation; either
 * version 2 of the License, or (at your option) any later version.
 *
 * This library is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
 * Library General Public License for more details.
 *
 * You should have received a copy of the GNU Library General Public License
 * along with this library; see the file COPYING.LIB.  If not, write to
 * the Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor,
 * Boston, MA 02110-1301, USA.
 *
 */

#pragma once

#include <wtf/Assertions.h>
#include <wtf/text/StringHasher.h>
#include <wtf/text/SuperFastHash.h>
#include <wtf/text/WYHash.h>

WTF_ALLOW_UNSAFE_BUFFER_USAGE_BEGIN

namespace WTF {

template<typename T, typename Converter>
unsigned StringHasher::computeHashAndMaskTop8Bits(std::span<const T> data)
{
#if ENABLE(WYHASH_STRING_HASHER)
    if (LIKELY(data.size() <= smallStringThreshold))
        return SuperFastHash::computeHashAndMaskTop8Bits<T, Converter>(data);
    return WYHash::computeHashAndMaskTop8Bits<T, Converter>(data);
#else
    return SuperFastHash::computeHashAndMaskTop8Bits<T, Converter>(data);
#endif
}

template<typename T, unsigned characterCount>
constexpr unsigned StringHasher::computeLiteralHashAndMaskTop8Bits(const T (&characters)[characterCount])
{
    constexpr unsigned characterCountWithoutNull = characterCount - 1;
#if ENABLE(WYHASH_STRING_HASHER)
    if constexpr (LIKELY(characterCountWithoutNull <= smallStringThreshold))
        return SuperFastHash::computeHashAndMaskTop8Bits<T>(std::span { characters, characterCountWithoutNull });
    return WYHash::computeHashAndMaskTop8Bits<T>(std::span { characters, characterCountWithoutNull });
#else
    return SuperFastHash::computeHashAndMaskTop8Bits<T>(std::span { characters, characterCountWithoutNull });
#endif
}

inline void StringHasher::addCharacter(UChar character)
{
#if ENABLE(WYHASH_STRING_HASHER)
    if (m_bufferSize == smallStringThreshold) {
        // This algorithm must stay in sync with WYHash::hash function.
        if (!m_pendingHashValue) {
            m_seed = WYHash::initSeed();
            m_see1 = m_seed;
            m_see2 = m_seed;
            m_pendingHashValue = true;
        }
        UChar* p = m_buffer.data();
        while (m_bufferSize >= 24) {
            WYHash::consume24Characters(p, WYHash::Reader16Bit<UChar>::wyr8, m_seed, m_see1, m_see2);
            p += 24;
            m_bufferSize -= 24;
        }
        ASSERT(!m_bufferSize);
        m_numberOfProcessedCharacters += smallStringThreshold;
    }

    ASSERT(m_bufferSize < smallStringThreshold);
    m_buffer[m_bufferSize++] = character;
#else
    SuperFastHash::addCharacterImpl(character, m_hasPendingCharacter, m_pendingCharacter, m_hash);
#endif
}

inline unsigned StringHasher::hashWithTop8BitsMasked()
{
#if ENABLE(WYHASH_STRING_HASHER)
    unsigned hashValue;
    if (!m_pendingHashValue) {
        ASSERT(m_bufferSize <= smallStringThreshold);
        hashValue = SuperFastHash::computeHashAndMaskTop8Bits<UChar>(std::span { m_buffer }.first(m_bufferSize));
    } else {
        // This algorithm must stay in sync with WYHash::hash function.
        auto wyr8 = WYHash::Reader16Bit<UChar>::wyr8;
        unsigned i = m_bufferSize;
        if (i <= 24)
            m_seed ^= m_see1 ^ m_see2;
        UChar* p = m_buffer.data();
        WYHash::handleGreaterThan8CharactersCase(p, i, wyr8, m_seed, m_see1, m_see2);

        uint64_t a = 0;
        uint64_t b = 0;
        if (m_bufferSize >= 8) {
            a = wyr8(p + i - 8);
            b = wyr8(p + i - 4);
        } else {
            UChar tmp[8];
            unsigned bufferIndex = smallStringThreshold - (8 - i);
            for (unsigned tmpIndex = 0; tmpIndex < 8; tmpIndex++) {
                tmp[tmpIndex] = m_buffer[bufferIndex];
                bufferIndex = (bufferIndex + 1) % smallStringThreshold;
            }

            UChar* tmpPtr = tmp;
            a = wyr8(tmpPtr);
            b = wyr8(tmpPtr + 4);
        }

        const uint64_t totalByteCount = (static_cast<uint64_t>(m_numberOfProcessedCharacters) + static_cast<uint64_t>(m_bufferSize)) << 1;
        hashValue = StringHasher::avoidZero(WYHash::handleEndCase(a, b, m_seed, totalByteCount) & StringHasher::maskHash);

        m_pendingHashValue = false;
        m_numberOfProcessedCharacters = m_seed = m_see1 = m_see2 = 0;
    }
    m_bufferSize = 0;
    return hashValue;
#else
    unsigned hashValue = SuperFastHash::hashWithTop8BitsMaskedImpl(m_hasPendingCharacter, m_pendingCharacter, m_hash);
    m_hasPendingCharacter = false;
    m_pendingCharacter = 0;
    m_hash = stringHashingStartValue;
    return hashValue;
#endif
}

} // namespace WTF

using WTF::StringHasher;

WTF_ALLOW_UNSAFE_BUFFER_USAGE_END