|
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 #include <QString> |
|
43 |
|
44 #include "qcompressedwhitespace_p.h" |
|
45 |
|
46 QT_BEGIN_NAMESPACE |
|
47 |
|
48 using namespace QPatternist; |
|
49 |
|
50 CompressedWhitespace::CharIdentifier CompressedWhitespace::toIdentifier(const QChar ch) |
|
51 { |
|
52 switch(ch.unicode()) |
|
53 { |
|
54 case ' ': |
|
55 return Space; |
|
56 case '\n': |
|
57 return LF; |
|
58 case '\r': |
|
59 return CR; |
|
60 case '\t': |
|
61 return Tab; |
|
62 default: |
|
63 { |
|
64 Q_ASSERT_X(false, Q_FUNC_INFO, |
|
65 "The caller must guarantee only whitespace is passed."); |
|
66 return Tab; |
|
67 } |
|
68 } |
|
69 } |
|
70 |
|
71 bool CompressedWhitespace::isEven(const int number) |
|
72 { |
|
73 Q_ASSERT(number >= 0); |
|
74 return number % 2 == 0; |
|
75 } |
|
76 |
|
77 quint8 CompressedWhitespace::toCompressedChar(const QChar ch, const int len) |
|
78 { |
|
79 Q_ASSERT(len > 0); |
|
80 Q_ASSERT(len <= MaxCharCount); |
|
81 |
|
82 return len + toIdentifier(ch); |
|
83 } |
|
84 |
|
85 QChar CompressedWhitespace::toChar(const CharIdentifier id) |
|
86 { |
|
87 switch(id) |
|
88 { |
|
89 case Space: return QLatin1Char(' '); |
|
90 case CR: return QLatin1Char('\r'); |
|
91 case LF: return QLatin1Char('\n'); |
|
92 case Tab: return QLatin1Char('\t'); |
|
93 default: |
|
94 { |
|
95 Q_ASSERT_X(false, Q_FUNC_INFO, "Unexpected input"); |
|
96 return QChar(); |
|
97 } |
|
98 } |
|
99 } |
|
100 |
|
101 QString CompressedWhitespace::compress(const QStringRef &input) |
|
102 { |
|
103 Q_ASSERT(!isEven(1) && isEven(0) && isEven(2)); |
|
104 Q_ASSERT(!input.isEmpty()); |
|
105 |
|
106 QString result; |
|
107 const int len = input.length(); |
|
108 |
|
109 /* The amount of compressed characters. For instance, if input is |
|
110 * four spaces followed by one tab, compressedChars will be 2, and the resulting |
|
111 * QString will have a length of 1, two compressedChars stored in one QChar. */ |
|
112 int compressedChars = 0; |
|
113 |
|
114 for(int i = 0; i < len; ++i) |
|
115 { |
|
116 const QChar c(input.at(i)); |
|
117 |
|
118 int start = i; |
|
119 |
|
120 while(true) |
|
121 { |
|
122 if(i + 1 == input.length() || input.at(i + 1) != c) |
|
123 break; |
|
124 else |
|
125 ++i; |
|
126 } |
|
127 |
|
128 /* The length of subsequent whitespace characters in the input. */ |
|
129 int wsLen = (i - start) + 1; |
|
130 |
|
131 /* We might get a sequence of whitespace that is so long, that we can't |
|
132 * store it in one unit/byte. In that case we chop it into as many subsequent |
|
133 * ones that is needed. */ |
|
134 while(true) |
|
135 { |
|
136 const int unitLength = qMin(wsLen, int(MaxCharCount)); |
|
137 wsLen -= unitLength; |
|
138 |
|
139 ushort resultCP = toCompressedChar(c, unitLength); |
|
140 |
|
141 if(isEven(compressedChars)) |
|
142 result += QChar(resultCP); |
|
143 else |
|
144 { |
|
145 resultCP = resultCP << 8; |
|
146 resultCP |= result.at(result.size() - 1).unicode(); |
|
147 result[result.size() - 1] = resultCP; |
|
148 } |
|
149 |
|
150 ++compressedChars; |
|
151 |
|
152 if(wsLen == 0) |
|
153 break; |
|
154 } |
|
155 } |
|
156 |
|
157 return result; |
|
158 } |
|
159 |
|
160 QString CompressedWhitespace::decompress(const QString &input) |
|
161 { |
|
162 Q_ASSERT(!input.isEmpty()); |
|
163 const int len = input.length() * 2; |
|
164 QString retval; |
|
165 |
|
166 for(int i = 0; i < len; ++i) |
|
167 { |
|
168 ushort cp = input.at(i / 2).unicode(); |
|
169 |
|
170 if(isEven(i)) |
|
171 cp &= Lower8Bits; |
|
172 else |
|
173 { |
|
174 cp = cp >> 8; |
|
175 |
|
176 if(cp == 0) |
|
177 return retval; |
|
178 } |
|
179 |
|
180 const quint8 wsLen = cp & Lower6Bits; |
|
181 const quint8 id = cp & UpperTwoBits; |
|
182 |
|
183 /* Resize retval, and fill in on the top. */ |
|
184 const int oldSize = retval.size(); |
|
185 const int newSize = retval.size() + wsLen; |
|
186 retval.resize(newSize); |
|
187 const QChar ch(toChar(CharIdentifier(id))); |
|
188 |
|
189 for(int f = oldSize; f < newSize; ++f) |
|
190 retval[f] = ch; |
|
191 } |
|
192 |
|
193 return retval; |
|
194 } |
|
195 |
|
196 QT_END_NAMESPACE |
|
197 |