1 /****************************************************************************
3 ** Copyright (C) 2011 Nokia Corporation and/or its subsidiary(-ies).
4 ** All rights reserved.
5 ** Contact: Nokia Corporation (qt-info@nokia.com)
7 ** This file is part of the QtXmlPatterns module of the Qt Toolkit.
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
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.
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.
28 ** If you have questions regarding the use of this file, please contact
29 ** Nokia at qt-info@nokia.com.
40 ****************************************************************************/
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.
52 #ifndef Patternist_CompressedWhitespace_H
53 #define Patternist_CompressedWhitespace_H
68 * @short A compression facility for whitespace nodes.
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.
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.
81 * There is no way to tell whether a QString is compressed or not.
83 * The compression scheme originates from Saxon, by Michael Kay.
85 * @author Frans Englich <frans.englich@nokia.com>
87 class Q_AUTOTEST_EXPORT CompressedWhitespace
91 * @short Compresses @p input into a compressed format, returned
94 * The caller guarantees that input is not empty
95 * and consists only of whitespace.
97 * The returned format is opaque. There is no way to find out
98 * whether a QString contains compressed data or not.
102 static QString compress(const QStringRef &input);
105 * @short Decompresses @p input into a usual QString.
107 * @p input must be a QString as per returned from compress().
111 static QString decompress(const QString &input);
115 * We use the two upper bits for communicating what space it is.
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,
150 Lower8Bits = (1 << 8) - 1,
155 Lower6Bits = (1 << 6) - 1,
160 UpperTwoBits = 3 << 6
163 static inline CharIdentifier toIdentifier(const QChar ch);
165 static inline quint8 toCompressedChar(const QChar ch, const int len);
166 static inline QChar toChar(const CharIdentifier id);
169 * @short Returns @c true if @p number is an even number, otherwise
172 static inline bool isEven(const int number);
175 * @short This class can only be used via its static members.
177 inline CompressedWhitespace();
178 Q_DISABLE_COPY(CompressedWhitespace)