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#include <QString>
41
42#include "qcompressedwhitespace_p.h"
43
44QT_BEGIN_NAMESPACE
45
46using namespace QPatternist;
47
48CompressedWhitespace::CharIdentifier CompressedWhitespace::toIdentifier(const QChar ch)
49{
50 switch(ch.unicode())
51 {
52 case ' ':
53 return Space;
54 case '\n':
55 return LF;
56 case '\r':
57 return CR;
58 case '\t':
59 return Tab;
60 default:
61 {
62 Q_ASSERT_X(false, Q_FUNC_INFO,
63 "The caller must guarantee only whitespace is passed.");
64 return Tab;
65 }
66 }
67}
68
69bool CompressedWhitespace::isEven(const int number)
70{
71 Q_ASSERT(number >= 0);
72 return number % 2 == 0;
73}
74
75quint8 CompressedWhitespace::toCompressedChar(const QChar ch, const int len)
76{
77 Q_ASSERT(len > 0);
78 Q_ASSERT(len <= MaxCharCount);
79
80 return len + toIdentifier(ch);
81}
82
83QChar CompressedWhitespace::toChar(const CharIdentifier id)
84{
85 switch(id)
86 {
87 case Space: return QLatin1Char(' ');
88 case CR: return QLatin1Char('\r');
89 case LF: return QLatin1Char('\n');
90 case Tab: return QLatin1Char('\t');
91 default:
92 {
93 Q_ASSERT_X(false, Q_FUNC_INFO, "Unexpected input");
94 return QChar();
95 }
96 }
97}
98
99QString CompressedWhitespace::compress(const QStringRef &input)
100{
101 Q_ASSERT(!isEven(1) && isEven(0) && isEven(2));
102 Q_ASSERT(!input.isEmpty());
103
104 QString result;
105 const int len = input.length();
106
107 /* The amount of compressed characters. For instance, if input is
108 * four spaces followed by one tab, compressedChars will be 2, and the resulting
109 * QString will have a length of 1, two compressedChars stored in one QChar. */
110 int compressedChars = 0;
111
112 for(int i = 0; i < len; ++i)
113 {
114 const QChar c(input.at(i));
115
116 int start = i;
117
118 while(true)
119 {
120 if(i + 1 == input.length() || input.at(i: i + 1) != c)
121 break;
122 else
123 ++i;
124 }
125
126 /* The length of subsequent whitespace characters in the input. */
127 int wsLen = (i - start) + 1;
128
129 /* We might get a sequence of whitespace that is so long, that we can't
130 * store it in one unit/byte. In that case we chop it into as many subsequent
131 * ones that is needed. */
132 while(true)
133 {
134 const int unitLength = qMin(a: wsLen, b: int(MaxCharCount));
135 wsLen -= unitLength;
136
137 ushort resultCP = toCompressedChar(ch: c, len: unitLength);
138
139 if(isEven(number: compressedChars))
140 result += QChar(resultCP);
141 else
142 {
143 resultCP = resultCP << 8;
144 resultCP |= result.at(i: result.size() - 1).unicode();
145 result[result.size() - 1] = resultCP;
146 }
147
148 ++compressedChars;
149
150 if(wsLen == 0)
151 break;
152 }
153 }
154
155 return result;
156}
157
158QString CompressedWhitespace::decompress(const QString &input)
159{
160 Q_ASSERT(!input.isEmpty());
161 const int len = input.length() * 2;
162 QString retval;
163
164 for(int i = 0; i < len; ++i)
165 {
166 ushort cp = input.at(i: i / 2).unicode();
167
168 if(isEven(number: i))
169 cp &= Lower8Bits;
170 else
171 {
172 cp = cp >> 8;
173
174 if(cp == 0)
175 return retval;
176 }
177
178 const quint8 wsLen = cp & Lower6Bits;
179 const quint8 id = cp & UpperTwoBits;
180
181 /* Resize retval, and fill in on the top. */
182 const int oldSize = retval.size();
183 const int newSize = retval.size() + wsLen;
184 retval.resize(size: newSize);
185 const QChar ch(toChar(id: CharIdentifier(id)));
186
187 for(int f = oldSize; f < newSize; ++f)
188 retval[f] = ch;
189 }
190
191 return retval;
192}
193
194QT_END_NAMESPACE
195
196

source code of qtxmlpatterns/src/xmlpatterns/acceltree/qcompressedwhitespace.cpp