|
1 /**************************************************************************** |
|
2 ** |
|
3 ** Copyright (C) 2009 Nokia Corporation and/or its subsidiary(-ies). |
|
4 ** All rights reserved. |
|
5 ** Contact: Nokia Corporation (qt-info@nokia.com) |
|
6 ** |
|
7 ** This file is part of the QtXmlPatterns module of the Qt Toolkit. |
|
8 ** |
|
9 ** $QT_BEGIN_LICENSE:LGPL$ |
|
10 ** No Commercial Usage |
|
11 ** This file contains pre-release code and may not be distributed. |
|
12 ** You may use this file in accordance with the terms and conditions |
|
13 ** contained in the Technology Preview License Agreement accompanying |
|
14 ** this package. |
|
15 ** |
|
16 ** GNU Lesser General Public License Usage |
|
17 ** Alternatively, this file may be used under the terms of the GNU Lesser |
|
18 ** General Public License version 2.1 as published by the Free Software |
|
19 ** Foundation and appearing in the file LICENSE.LGPL included in the |
|
20 ** packaging of this file. Please review the following information to |
|
21 ** ensure the GNU Lesser General Public License version 2.1 requirements |
|
22 ** will be met: http://www.gnu.org/licenses/old-licenses/lgpl-2.1.html. |
|
23 ** |
|
24 ** In addition, as a special exception, Nokia gives you certain additional |
|
25 ** rights. These rights are described in the Nokia Qt LGPL Exception |
|
26 ** version 1.1, included in the file LGPL_EXCEPTION.txt in this package. |
|
27 ** |
|
28 ** If you have questions regarding the use of this file, please contact |
|
29 ** Nokia at qt-info@nokia.com. |
|
30 ** |
|
31 ** |
|
32 ** |
|
33 ** |
|
34 ** |
|
35 ** |
|
36 ** |
|
37 ** |
|
38 ** $QT_END_LICENSE$ |
|
39 ** |
|
40 ****************************************************************************/ |
|
41 |
|
42 // |
|
43 // W A R N I N G |
|
44 // ------------- |
|
45 // |
|
46 // This file is not part of the Qt API. It exists purely as an |
|
47 // implementation detail. This header file may change from version to |
|
48 // version without notice, or even be removed. |
|
49 // |
|
50 // We mean it. |
|
51 |
|
52 #ifndef Patternist_CompressedWhitespace_H |
|
53 #define Patternist_CompressedWhitespace_H |
|
54 |
|
55 #include <QtGlobal> |
|
56 |
|
57 QT_BEGIN_HEADER |
|
58 |
|
59 QT_BEGIN_NAMESPACE |
|
60 |
|
61 class QChar; |
|
62 class QString; |
|
63 class QStringRef; |
|
64 |
|
65 namespace QPatternist |
|
66 { |
|
67 /** |
|
68 * @short A compression facility for whitespace nodes. |
|
69 * |
|
70 * CompressedWhitespace compresses and decompresses strings that consists of |
|
71 * whitespace only, and do so with a scheme that is designed to do this |
|
72 * specialized task in an efficient way. The approach is simple: each |
|
73 * sequence of equal whitespace in the input gets coded into one byte, |
|
74 * where the first two bits signals the type, CharIdentifier, and the |
|
75 * remininding six bits is the count. |
|
76 * |
|
77 * For instance, this scheme manages to compress a sequence of spaces |
|
78 * followed by a new line into 16 bits(one QChar), and QString stores |
|
79 * strings of one QChar quite efficiently, by avoiding a heap allocation. |
|
80 * |
|
81 * There is no way to tell whether a QString is compressed or not. |
|
82 * |
|
83 * The compression scheme originates from Saxon, by Michael Kay. |
|
84 * |
|
85 * @author Frans Englich <frans.englich@nokia.com> |
|
86 */ |
|
87 class CompressedWhitespace |
|
88 { |
|
89 public: |
|
90 /** |
|
91 * @short Compresses @p input into a compressed format, returned |
|
92 * as a QString. |
|
93 * |
|
94 * The caller guarantees that input is not empty |
|
95 * and consists only of whitespace. |
|
96 * |
|
97 * The returned format is opaque. There is no way to find out |
|
98 * whether a QString contains compressed data or not. |
|
99 * |
|
100 * @see decompress() |
|
101 */ |
|
102 static QString compress(const QStringRef &input); |
|
103 |
|
104 /** |
|
105 * @short Decompresses @p input into a usual QString. |
|
106 * |
|
107 * @p input must be a QString as per returned from compress(). |
|
108 * |
|
109 * @see compress() |
|
110 */ |
|
111 static QString decompress(const QString &input); |
|
112 |
|
113 private: |
|
114 /** |
|
115 * We use the two upper bits for communicating what space it is. |
|
116 */ |
|
117 enum CharIdentifier |
|
118 { |
|
119 Space = 0x0, |
|
120 |
|
121 /** |
|
122 * 0xA, \\r |
|
123 * |
|
124 * Binary: 10000000 |
|
125 */ |
|
126 CR = 0x80, |
|
127 |
|
128 /** |
|
129 * 0xD, \\n |
|
130 * |
|
131 * Binary: 01000000 |
|
132 */ |
|
133 LF = 0x40, |
|
134 |
|
135 /** |
|
136 * Binary: 11000000 |
|
137 */ |
|
138 Tab = 0xC0 |
|
139 }; |
|
140 |
|
141 enum Constants |
|
142 { |
|
143 /* We can at maximum store this many consecutive characters |
|
144 * of one type. We use 6 bits for the count. */ |
|
145 MaxCharCount = (1 << 6) - 1, |
|
146 |
|
147 /** |
|
148 * Binary: 11111111 |
|
149 */ |
|
150 Lower8Bits = (1 << 8) - 1, |
|
151 |
|
152 /** |
|
153 * Binary: 111111 |
|
154 */ |
|
155 Lower6Bits = (1 << 6) - 1, |
|
156 |
|
157 /* |
|
158 * Binary: 11000000 |
|
159 */ |
|
160 UpperTwoBits = 3 << 6 |
|
161 }; |
|
162 |
|
163 static inline CharIdentifier toIdentifier(const QChar ch); |
|
164 |
|
165 static inline quint8 toCompressedChar(const QChar ch, const int len); |
|
166 static inline QChar toChar(const CharIdentifier id); |
|
167 |
|
168 /** |
|
169 * @short Returns @c true if @p number is an even number, otherwise |
|
170 * @c false. |
|
171 */ |
|
172 static inline bool isEven(const int number); |
|
173 |
|
174 /** |
|
175 * @short This class can only be used via its static members. |
|
176 */ |
|
177 inline CompressedWhitespace(); |
|
178 Q_DISABLE_COPY(CompressedWhitespace) |
|
179 }; |
|
180 } |
|
181 |
|
182 QT_END_NAMESPACE |
|
183 |
|
184 QT_END_HEADER |
|
185 |
|
186 #endif |