|
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 QtCore 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 #include "qisciicodec_p.h" |
|
42 #include "qlist.h" |
|
43 |
|
44 #ifndef QT_NO_CODECS |
|
45 |
|
46 QT_BEGIN_NAMESPACE |
|
47 |
|
48 /*! |
|
49 \class QIsciiCodec |
|
50 \brief The QIsciiCodec class provides conversion to and from the ISCII encoding. |
|
51 |
|
52 \internal |
|
53 */ |
|
54 |
|
55 |
|
56 struct Codecs { |
|
57 const char name[10]; |
|
58 ushort base; |
|
59 }; |
|
60 |
|
61 static const Codecs codecs [] = { |
|
62 { "Iscii-Dev", 0x900 }, |
|
63 { "Iscii-Bng", 0x980 }, |
|
64 { "Iscii-Pnj", 0xa00 }, |
|
65 { "Iscii-Gjr", 0xa80 }, |
|
66 { "Iscii-Ori", 0xb00 }, |
|
67 { "Iscii-Tml", 0xb80 }, |
|
68 { "Iscii-Tlg", 0xc00 }, |
|
69 { "Iscii-Knd", 0xc80 }, |
|
70 { "Iscii-Mlm", 0xd00 } |
|
71 }; |
|
72 |
|
73 QIsciiCodec::~QIsciiCodec() |
|
74 { |
|
75 } |
|
76 |
|
77 QByteArray QIsciiCodec::name() const |
|
78 { |
|
79 return codecs[idx].name; |
|
80 } |
|
81 |
|
82 int QIsciiCodec::mibEnum() const |
|
83 { |
|
84 /* There is no MIBEnum for Iscii */ |
|
85 return -3000-idx; |
|
86 } |
|
87 |
|
88 static const uchar inv = 0xFF; |
|
89 |
|
90 /* iscii range from 0xa0 - 0xff */ |
|
91 static const uchar iscii_to_uni_table[0x60] = { |
|
92 0x00, 0x01, 0x02, 0x03, |
|
93 0x05, 0x06, 0x07, 0x08, |
|
94 0x09, 0x0a, 0x0b, 0x0e, |
|
95 0x0f, 0x20, 0x0d, 0x12, |
|
96 |
|
97 0x13, 0x14, 0x11, 0x15, |
|
98 0x16, 0x17, 0x18, 0x19, |
|
99 0x1a, 0x1b, 0x1c, 0x1d, |
|
100 0x1e, 0x1f, 0x20, 0x21, |
|
101 |
|
102 0x22, 0x23, 0x24, 0x25, |
|
103 0x26, 0x27, 0x28, 0x29, |
|
104 0x2a, 0x2b, 0x2c, 0x2d, |
|
105 0x2e, 0x2f, 0x5f, 0x30, |
|
106 |
|
107 0x31, 0x32, 0x33, 0x34, |
|
108 0x35, 0x36, 0x37, 0x38, |
|
109 0x39, inv, 0x3e, 0x3f, |
|
110 0x40, 0x41, 0x42, 0x43, |
|
111 |
|
112 0x46, 0x47, 0x48, 0x45, |
|
113 0x4a, 0x4b, 0x4c, 0x49, |
|
114 0x4d, 0x3c, 0x64, 0x00, |
|
115 0x00, 0x00, 0x00, 0x00, |
|
116 |
|
117 0x00, 0x66, 0x67, 0x68, |
|
118 0x69, 0x6a, 0x6b, 0x6c, |
|
119 0x6d, 0x6e, 0x6f, 0x00, |
|
120 0x00, 0x00, 0x00, 0x00 |
|
121 }; |
|
122 |
|
123 static const uchar uni_to_iscii_table[0x80] = { |
|
124 0x00, 0xa1, 0xa2, 0xa3, |
|
125 0x00, 0xa4, 0xa5, 0xa6, |
|
126 0xa7, 0xa8, 0xa9, 0xaa, |
|
127 0x00, 0xae, 0xab, 0xac, |
|
128 |
|
129 0xad, 0xb2, 0xaf, 0xb0, |
|
130 0xb1, 0xb3, 0xb4, 0xb5, |
|
131 0xb6, 0xb7, 0xb8, 0xb9, |
|
132 0xba, 0xbb, 0xbc, 0xbd, |
|
133 |
|
134 0xbe, 0xbf, 0xc0, 0xc1, |
|
135 0xc2, 0xc3, 0xc4, 0xc5, |
|
136 0xc6, 0xc7, 0xc8, 0xc9, |
|
137 0xca, 0xcb, 0xcc, 0xcd, |
|
138 |
|
139 0xcf, 0xd0, 0xd1, 0xd2, |
|
140 0xd3, 0xd4, 0xd5, 0xd6, |
|
141 0xd7, 0xd8, 0x00, 0x00, |
|
142 0xe9, 0x00, 0xda, 0xdb, |
|
143 |
|
144 0xdc, 0xdd, 0xde, 0xdf, |
|
145 0x00, 0xe3, 0xe0, 0xe1, |
|
146 0xe2, 0xe7, 0xe4, 0xe5, |
|
147 0xe6, 0xe8, 0x00, 0x00, |
|
148 |
|
149 0x00, 0x00, 0x00, 0x00, |
|
150 0x00, 0x00, 0x00, 0x00, |
|
151 0x01, 0x02, 0x03, 0x04, // decomposable into the uc codes listed here + nukta |
|
152 0x05, 0x06, 0x07, 0xce, |
|
153 |
|
154 0x00, 0x00, 0x00, 0x00, |
|
155 0xea, 0x08, 0xf1, 0xf2, |
|
156 0xf3, 0xf4, 0xf5, 0xf6, |
|
157 0xf7, 0xf8, 0xf9, 0xfa, |
|
158 |
|
159 0x00, 0x00, 0x00, 0x00, |
|
160 0x00, 0x00, 0x00, 0x00, |
|
161 0x00, 0x00, 0x00, 0x00, |
|
162 0x00, 0x00, 0x00, 0x00 |
|
163 }; |
|
164 |
|
165 static const uchar uni_to_iscii_pairs[] = { |
|
166 0x00, 0x00, |
|
167 0x15, 0x3c, // 0x958 |
|
168 0x16, 0x3c, // 0x959 |
|
169 0x17, 0x3c, // 0x95a |
|
170 0x1c, 0x3c, // 0x95b |
|
171 0x21, 0x3c, // 0x95c |
|
172 0x22, 0x3c, // 0x95d |
|
173 0x2b, 0x3c, // 0x95e |
|
174 0x64, 0x64 // 0x965 |
|
175 }; |
|
176 |
|
177 |
|
178 QByteArray QIsciiCodec::convertFromUnicode(const QChar *uc, int len, ConverterState *state) const |
|
179 { |
|
180 char replacement = '?'; |
|
181 bool halant = false; |
|
182 if (state) { |
|
183 if (state->flags & ConvertInvalidToNull) |
|
184 replacement = 0; |
|
185 halant = state->state_data[0]; |
|
186 } |
|
187 int invalid = 0; |
|
188 |
|
189 QByteArray result(2 * len, Qt::Uninitialized); //worst case |
|
190 |
|
191 uchar *ch = reinterpret_cast<uchar *>(result.data()); |
|
192 |
|
193 const int base = codecs[idx].base; |
|
194 |
|
195 for (int i =0; i < len; ++i) { |
|
196 const ushort codePoint = uc[i].unicode(); |
|
197 |
|
198 /* The low 7 bits of ISCII is plain ASCII. However, we go all the |
|
199 * way up to 0xA0 such that we can roundtrip with convertToUnicode()'s |
|
200 * behavior. */ |
|
201 if(codePoint < 0xA0) { |
|
202 *ch++ = static_cast<uchar>(codePoint); |
|
203 continue; |
|
204 } |
|
205 |
|
206 const int pos = codePoint - base; |
|
207 if (pos > 0 && pos < 0x80) { |
|
208 uchar iscii = uni_to_iscii_table[pos]; |
|
209 if (iscii > 0x80) { |
|
210 *ch++ = iscii; |
|
211 } else if (iscii) { |
|
212 const uchar *pair = uni_to_iscii_pairs + 2*iscii; |
|
213 *ch++ = *pair++; |
|
214 *ch++ = *pair++; |
|
215 } else { |
|
216 *ch++ = replacement; |
|
217 ++invalid; |
|
218 } |
|
219 } else { |
|
220 if (uc[i].unicode() == 0x200c) { // ZWNJ |
|
221 if (halant) |
|
222 // Consonant Halant ZWNJ -> Consonant Halant Halant |
|
223 *ch++ = 0xe8; |
|
224 } else if (uc[i].unicode() == 0x200d) { // ZWJ |
|
225 if (halant) |
|
226 // Consonant Halant ZWJ -> Consonant Halant Nukta |
|
227 *ch++ = 0xe9; |
|
228 } else { |
|
229 *ch++ = replacement; |
|
230 ++invalid; |
|
231 } |
|
232 } |
|
233 halant = (pos == 0x4d); |
|
234 } |
|
235 result.truncate(ch - (uchar *)result.data()); |
|
236 |
|
237 if (state) { |
|
238 state->invalidChars += invalid; |
|
239 state->state_data[0] = halant; |
|
240 } |
|
241 return result; |
|
242 } |
|
243 |
|
244 QString QIsciiCodec::convertToUnicode(const char* chars, int len, ConverterState *state) const |
|
245 { |
|
246 bool halant = false; |
|
247 if (state) { |
|
248 halant = state->state_data[0]; |
|
249 } |
|
250 |
|
251 QString result(len, Qt::Uninitialized); |
|
252 QChar *uc = result.data(); |
|
253 |
|
254 const int base = codecs[idx].base; |
|
255 |
|
256 for (int i = 0; i < len; ++i) { |
|
257 ushort ch = (uchar) chars[i]; |
|
258 if (ch < 0xa0) |
|
259 *uc++ = ch; |
|
260 else { |
|
261 ushort c = iscii_to_uni_table[ch - 0xa0]; |
|
262 if (halant && (c == inv || c == 0xe9)) { |
|
263 // Consonant Halant inv -> Consonant Halant ZWJ |
|
264 // Consonant Halant Nukta -> Consonant Halant ZWJ |
|
265 *uc++ = QChar(0x200d); |
|
266 } else if (halant && c == 0xe8) { |
|
267 // Consonant Halant Halant -> Consonant Halant ZWNJ |
|
268 *uc++ = QChar(0x200c); |
|
269 } else { |
|
270 *uc++ = QChar(c+base); |
|
271 } |
|
272 } |
|
273 halant = ((uchar)chars[i] == 0xe8); |
|
274 } |
|
275 result.resize(uc - result.unicode()); |
|
276 |
|
277 if (state) { |
|
278 state->state_data[0] = halant; |
|
279 } |
|
280 return result; |
|
281 } |
|
282 |
|
283 QT_END_NAMESPACE |
|
284 |
|
285 #endif // QT_NO_CODECS |