1/****************************************************************************
2**
3** Copyright (C) 2020 The Qt Company Ltd.
4** Copyright (C) 2013 Aleix Pol Gonzalez <aleixpol@kde.org>
5** Contact: https://www.qt.io/licensing/
6**
7** This file is part of the QtCore module of the Qt Toolkit.
8**
9** $QT_BEGIN_LICENSE:LGPL$
10** Commercial License Usage
11** Licensees holding valid commercial Qt licenses may use this file in
12** accordance with the commercial license agreement provided with the
13** Software or, alternatively, in accordance with the terms contained in
14** a written agreement between you and The Qt Company. For licensing terms
15** and conditions see https://www.qt.io/terms-conditions. For further
16** information use the contact form at https://www.qt.io/contact-us.
17**
18** GNU Lesser General Public License Usage
19** Alternatively, this file may be used under the terms of the GNU Lesser
20** General Public License version 3 as published by the Free Software
21** Foundation and appearing in the file LICENSE.LGPL3 included in the
22** packaging of this file. Please review the following information to
23** ensure the GNU Lesser General Public License version 3 requirements
24** will be met: https://www.gnu.org/licenses/lgpl-3.0.html.
25**
26** GNU General Public License Usage
27** Alternatively, this file may be used under the terms of the GNU
28** General Public License version 2.0 or (at your option) the GNU General
29** Public license version 3 or any later version approved by the KDE Free
30** Qt Foundation. The licenses are as published by the Free Software
31** Foundation and appearing in the file LICENSE.GPL2 and LICENSE.GPL3
32** included in the packaging of this file. Please review the following
33** information to ensure the GNU General Public License requirements will
34** be met: https://www.gnu.org/licenses/gpl-2.0.html and
35** https://www.gnu.org/licenses/gpl-3.0.html.
36**
37** $QT_END_LICENSE$
38**
39****************************************************************************/
40
41#include "qcollator_p.h"
42#include "qlocale_p.h"
43#include "qstringlist.h"
44#include "qstring.h"
45
46#include <unicode/utypes.h>
47#include <unicode/ucol.h>
48#include <unicode/ustring.h>
49#include <unicode/ures.h>
50
51#include "qdebug.h"
52
53QT_BEGIN_NAMESPACE
54
55void QCollatorPrivate::init()
56{
57 cleanup();
58 if (isC())
59 return;
60
61 UErrorCode status = U_ZERO_ERROR;
62 QByteArray name = QLocalePrivate::get(l&: locale)->bcp47Name(separator: '_');
63 collator = ucol_open(loc: name.constData(), status: &status);
64 if (U_FAILURE(code: status)) {
65 qWarning(msg: "Could not create collator: %d", status);
66 collator = nullptr;
67 dirty = false;
68 return;
69 }
70
71 // enable normalization by default
72 ucol_setAttribute(coll: collator, attr: UCOL_NORMALIZATION_MODE, value: UCOL_ON, status: &status);
73
74 // The strength attribute in ICU is rather badly documented. Basically UCOL_PRIMARY
75 // ignores differences between base characters and accented characters as well as case.
76 // So A and A-umlaut would compare equal.
77 // UCOL_SECONDARY ignores case differences. UCOL_TERTIARY is the default in most languages
78 // and does case sensitive comparison.
79 // UCOL_QUATERNARY is used as default in a few languages such as Japanese to take care of some
80 // additional differences in those languages.
81 UColAttributeValue val = (caseSensitivity == Qt::CaseSensitive)
82 ? UCOL_DEFAULT_STRENGTH : UCOL_SECONDARY;
83
84 status = U_ZERO_ERROR;
85 ucol_setAttribute(coll: collator, attr: UCOL_STRENGTH, value: val, status: &status);
86 if (U_FAILURE(code: status))
87 qWarning(msg: "ucol_setAttribute: Case First failed: %d", status);
88
89 status = U_ZERO_ERROR;
90 ucol_setAttribute(coll: collator, attr: UCOL_NUMERIC_COLLATION, value: numericMode ? UCOL_ON : UCOL_OFF, status: &status);
91 if (U_FAILURE(code: status))
92 qWarning(msg: "ucol_setAttribute: numeric collation failed: %d", status);
93
94 status = U_ZERO_ERROR;
95 ucol_setAttribute(coll: collator, attr: UCOL_ALTERNATE_HANDLING,
96 value: ignorePunctuation ? UCOL_SHIFTED : UCOL_NON_IGNORABLE, status: &status);
97 if (U_FAILURE(code: status))
98 qWarning(msg: "ucol_setAttribute: Alternate handling failed: %d", status);
99
100 dirty = false;
101}
102
103void QCollatorPrivate::cleanup()
104{
105 if (collator)
106 ucol_close(coll: collator);
107 collator = nullptr;
108}
109
110int QCollator::compare(QStringView s1, QStringView s2) const
111{
112 if (!s1.size())
113 return s2.size() ? -1 : 0;
114 if (!s2.size())
115 return +1;
116
117 if (d->dirty)
118 d->init();
119
120 if (d->collator) {
121 return ucol_strcoll(coll: d->collator,
122 source: reinterpret_cast<const UChar *>(s1.data()), sourceLength: s1.size(),
123 target: reinterpret_cast<const UChar *>(s2.data()), targetLength: s2.size());
124 }
125
126 return QString::compare_helper(data1: s1.data(), length1: s1.size(),
127 data2: s2.data(), length2: s2.size(),
128 cs: d->caseSensitivity);
129}
130
131QCollatorSortKey QCollator::sortKey(const QString &string) const
132{
133 if (d->dirty)
134 d->init();
135 if (d->isC())
136 return QCollatorSortKey(new QCollatorSortKeyPrivate(string.toUtf8()));
137
138 if (d->collator) {
139 QByteArray result(16 + string.size() + (string.size() >> 2), Qt::Uninitialized);
140 int size = ucol_getSortKey(coll: d->collator, source: (const UChar *)string.constData(),
141 sourceLength: string.size(), result: (uint8_t *)result.data(), resultLength: result.size());
142 if (size > result.size()) {
143 result.resize(size);
144 size = ucol_getSortKey(coll: d->collator, source: (const UChar *)string.constData(),
145 sourceLength: string.size(), result: (uint8_t *)result.data(), resultLength: result.size());
146 }
147 result.truncate(pos: size);
148 return QCollatorSortKey(new QCollatorSortKeyPrivate(std::move(result)));
149 }
150
151 return QCollatorSortKey(new QCollatorSortKeyPrivate(QByteArray()));
152}
153
154int QCollatorSortKey::compare(const QCollatorSortKey &otherKey) const
155{
156 return qstrcmp(str1: d->m_key, str2: otherKey.d->m_key);
157}
158
159QT_END_NAMESPACE
160

source code of qtbase/src/corelib/text/qcollator_icu.cpp