1/****************************************************************************
2**
3** Copyright (C) 2016 The Qt Company Ltd.
4** Contact: https://www.qt.io/licensing/
5**
6** This file is part of the QtXmlPatterns module of the Qt Toolkit.
7**
8** $QT_BEGIN_LICENSE:LGPL$
9** Commercial License Usage
10** Licensees holding valid commercial Qt licenses may use this file in
11** accordance with the commercial license agreement provided with the
12** Software or, alternatively, in accordance with the terms contained in
13** a written agreement between you and The Qt Company. For licensing terms
14** and conditions see https://www.qt.io/terms-conditions. For further
15** information use the contact form at https://www.qt.io/contact-us.
16**
17** GNU Lesser General Public License Usage
18** Alternatively, this file may be used under the terms of the GNU Lesser
19** General Public License version 3 as published by the Free Software
20** Foundation and appearing in the file LICENSE.LGPL3 included in the
21** packaging of this file. Please review the following information to
22** ensure the GNU Lesser General Public License version 3 requirements
23** will be met: https://www.gnu.org/licenses/lgpl-3.0.html.
24**
25** GNU General Public License Usage
26** Alternatively, this file may be used under the terms of the GNU
27** General Public License version 2.0 or (at your option) the GNU General
28** Public license version 3 or any later version approved by the KDE Free
29** Qt Foundation. The licenses are as published by the Free Software
30** Foundation and appearing in the file LICENSE.GPL2 and LICENSE.GPL3
31** included in the packaging of this file. Please review the following
32** information to ensure the GNU General Public License requirements will
33** be met: https://www.gnu.org/licenses/gpl-2.0.html and
34** https://www.gnu.org/licenses/gpl-3.0.html.
35**
36** $QT_END_LICENSE$
37**
38****************************************************************************/
39
40//
41// W A R N I N G
42// -------------
43//
44// This file is not part of the Qt API. It exists purely as an
45// implementation detail. This header file may change from version to
46// version without notice, or even be removed.
47//
48// We mean it.
49
50#ifndef Patternist_CompressedWhitespace_H
51#define Patternist_CompressedWhitespace_H
52
53#include <QtGlobal>
54
55QT_BEGIN_NAMESPACE
56
57class QChar;
58class QString;
59class QStringRef;
60
61namespace QPatternist
62{
63 /**
64 * @short A compression facility for whitespace nodes.
65 *
66 * CompressedWhitespace compresses and decompresses strings that consists of
67 * whitespace only, and do so with a scheme that is designed to do this
68 * specialized task in an efficient way. The approach is simple: each
69 * sequence of equal whitespace in the input gets coded into one byte,
70 * where the first two bits signals the type, CharIdentifier, and the
71 * remininding six bits is the count.
72 *
73 * For instance, this scheme manages to compress a sequence of spaces
74 * followed by a new line into 16 bits(one QChar), and QString stores
75 * strings of one QChar quite efficiently, by avoiding a heap allocation.
76 *
77 * There is no way to tell whether a QString is compressed or not.
78 *
79 * The compression scheme originates from Saxon, by Michael Kay.
80 *
81 * @author Frans Englich <frans.englich@nokia.com>
82 */
83 class Q_AUTOTEST_EXPORT CompressedWhitespace
84 {
85 public:
86 /**
87 * @short Compresses @p input into a compressed format, returned
88 * as a QString.
89 *
90 * The caller guarantees that input is not empty
91 * and consists only of whitespace.
92 *
93 * The returned format is opaque. There is no way to find out
94 * whether a QString contains compressed data or not.
95 *
96 * @see decompress()
97 */
98 static QString compress(const QStringRef &input);
99
100 /**
101 * @short Decompresses @p input into a usual QString.
102 *
103 * @p input must be a QString as per returned from compress().
104 *
105 * @see compress()
106 */
107 static QString decompress(const QString &input);
108
109 private:
110 /**
111 * We use the two upper bits for communicating what space it is.
112 */
113 enum CharIdentifier
114 {
115 Space = 0x0,
116
117 /**
118 * 0xA, \\r
119 *
120 * Binary: 10000000
121 */
122 CR = 0x80,
123
124 /**
125 * 0xD, \\n
126 *
127 * Binary: 01000000
128 */
129 LF = 0x40,
130
131 /**
132 * Binary: 11000000
133 */
134 Tab = 0xC0
135 };
136
137 enum Constants
138 {
139 /* We can at maximum store this many consecutive characters
140 * of one type. We use 6 bits for the count. */
141 MaxCharCount = (1 << 6) - 1,
142
143 /**
144 * Binary: 11111111
145 */
146 Lower8Bits = (1 << 8) - 1,
147
148 /**
149 * Binary: 111111
150 */
151 Lower6Bits = (1 << 6) - 1,
152
153 /*
154 * Binary: 11000000
155 */
156 UpperTwoBits = 3 << 6
157 };
158
159 static inline CharIdentifier toIdentifier(const QChar ch);
160
161 static inline quint8 toCompressedChar(const QChar ch, const int len);
162 static inline QChar toChar(const CharIdentifier id);
163
164 /**
165 * @short Returns @c true if @p number is an even number, otherwise
166 * @c false.
167 */
168 static inline bool isEven(const int number);
169
170 /**
171 * @short This class can only be used via its static members.
172 */
173 inline CompressedWhitespace();
174 Q_DISABLE_COPY(CompressedWhitespace)
175 };
176}
177
178QT_END_NAMESPACE
179
180#endif
181

source code of qtxmlpatterns/src/xmlpatterns/acceltree/qcompressedwhitespace_p.h