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 QtCore 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// Most of the code here was originally written by Hans Petter Bieker,
41// and is included in Qt with the author's permission, and the grateful
42// thanks of the Qt team.
43
44#include "qtsciicodec_p.h"
45#include "qlist.h"
46
47QT_BEGIN_NAMESPACE
48
49static unsigned char qt_UnicodeToTSCII(ushort u1, ushort u2, ushort u3);
50static unsigned int qt_TSCIIToUnicode(unsigned int code, uint *s);
51
52#define IsTSCIIChar(c) (((c) >= 0x80) && ((c) <= 0xfd))
53
54/*! \class QTsciiCodec
55 \inmodule QtCore
56 \reentrant
57 \internal
58*/
59
60/*!
61 Destroys the text codec object.
62*/
63QTsciiCodec::~QTsciiCodec()
64{
65}
66
67/*!
68 Converts the first \a len characters in \a uc from Unicode to this
69 encoding, and returns the result in a byte array. The \a state contains
70 some conversion flags, and is used by the codec to maintain state
71 information.
72*/
73QByteArray QTsciiCodec::convertFromUnicode(const QChar *uc, int len, ConverterState *state) const
74{
75 char replacement = '?';
76 if (state) {
77 if (state->flags & ConvertInvalidToNull)
78 replacement = 0;
79 }
80 int invalid = 0;
81
82 QByteArray rstr(len, Qt::Uninitialized);
83 uchar* cursor = (uchar*)rstr.data();
84 for (int i = 0; i < len; i++) {
85 QChar ch = uc[i];
86 uchar j;
87 if (ch.row() == 0x00 && ch.cell() < 0x80) {
88 // ASCII
89 j = ch.cell();
90 } else if ((j = qt_UnicodeToTSCII(u1: uc[i].unicode(),
91 u2: uc[i + 1].unicode(),
92 u3: uc[i + 2].unicode()))) {
93 // We have to check the combined chars first!
94 i += 2;
95 } else if ((j = qt_UnicodeToTSCII(u1: uc[i].unicode(),
96 u2: uc[i + 1].unicode(), u3: 0))) {
97 i++;
98 } else if ((j = qt_UnicodeToTSCII(u1: uc[i].unicode(), u2: 0, u3: 0))) {
99 } else {
100 // Error
101 j = replacement;
102 ++invalid;
103 }
104 *cursor++ = j;
105 }
106 rstr.resize(size: cursor - (const uchar*)rstr.constData());
107
108 if (state) {
109 state->invalidChars += invalid;
110 }
111 return rstr;
112}
113
114/*!
115 Converts the first \a len characters in \a chars from this encoding
116 to Unicode, and returns the result in a QString. The \a state contains
117 some conversion flags, and is used by the codec to maintain state
118 information.
119*/
120QString QTsciiCodec::convertToUnicode(const char* chars, int len, ConverterState *state) const
121{
122 QChar replacement = QChar::ReplacementCharacter;
123 if (state) {
124 if (state->flags & ConvertInvalidToNull)
125 replacement = QChar::Null;
126 }
127 int invalid = 0;
128
129 QString result;
130 for (int i = 0; i < len; i++) {
131 uchar ch = chars[i];
132 if (ch < 0x80) {
133 // ASCII
134 result += QLatin1Char(ch);
135 } else if (IsTSCIIChar(ch)) {
136 // TSCII
137 uint s[3];
138 uint u = qt_TSCIIToUnicode(code: ch, s);
139 uint *p = s;
140 while (u--) {
141 uint c = *p++;
142 if (c)
143 result += QChar(c);
144 else {
145 result += replacement;
146 ++invalid;
147 }
148 }
149 } else {
150 // Invalid
151 result += replacement;
152 ++invalid;
153 }
154 }
155
156 if (state) {
157 state->invalidChars += invalid;
158 }
159 return result;
160}
161
162/*!
163 Returns the official name for the encoding that is handled by the codec.
164
165 \sa QTextCodec::name()
166*/
167QByteArray QTsciiCodec::name() const
168{
169 return "TSCII";
170}
171
172/*!
173 Returns the MIB enum for the encoding.
174
175 \sa QTextCodec::mibEnum()
176*/
177int QTsciiCodec::mibEnum() const
178{
179 return 2107;
180}
181
182static const int UnToTsLast = 124; // 125 items -- so the last will be 124
183static const ushort UnToTs [][4] = {
184 // *Sorted* list of TSCII maping for unicode chars
185 //FIRST SECOND THIRD TSCII
186 {0x00A0, 0x0000, 0x0000, 0xA0},
187 {0x00A9, 0x0000, 0x0000, 0xA9},
188 {0x0B83, 0x0000, 0x0000, 0xB7},
189 {0x0B85, 0x0000, 0x0000, 0xAB},
190 {0x0B86, 0x0000, 0x0000, 0xAC},
191 {0x0B87, 0x0000, 0x0000, 0xAD},
192 {0x0B88, 0x0000, 0x0000, 0xAE},
193 {0x0B89, 0x0000, 0x0000, 0xAF},
194 {0x0B8A, 0x0000, 0x0000, 0xB0},
195 {0x0B8E, 0x0000, 0x0000, 0xB1},
196 {0x0B8F, 0x0000, 0x0000, 0xB2},
197 {0x0B90, 0x0000, 0x0000, 0xB3},
198 {0x0B92, 0x0000, 0x0000, 0xB4},
199 {0x0B93, 0x0000, 0x0000, 0xB5},
200 {0x0B94, 0x0000, 0x0000, 0xB6},
201 {0x0B95, 0x0000, 0x0000, 0xB8},
202 {0x0B95, 0x0B82, 0x0000, 0xEC},
203 {0x0B95, 0x0BC1, 0x0000, 0xCC},
204 {0x0B95, 0x0BC2, 0x0000, 0xDC},
205 {0x0B99, 0x0000, 0x0000, 0xB9},
206 {0x0B99, 0x0B82, 0x0000, 0xED},
207 {0x0B99, 0x0BC1, 0x0000, 0x99},
208 {0x0B99, 0x0BC2, 0x0000, 0x9B},
209 {0x0B9A, 0x0000, 0x0000, 0xBA},
210 {0x0B9A, 0x0B82, 0x0000, 0xEE},
211 {0x0B9A, 0x0BC1, 0x0000, 0xCD},
212 {0x0B9A, 0x0BC2, 0x0000, 0xDD},
213 {0x0B9C, 0x0000, 0x0000, 0x83},
214 {0x0B9C, 0x0B82, 0x0000, 0x88},
215 {0x0B9E, 0x0000, 0x0000, 0xBB},
216 {0x0B9E, 0x0B82, 0x0000, 0xEF},
217 {0x0B9E, 0x0BC1, 0x0000, 0x9A},
218 {0x0B9E, 0x0BC2, 0x0000, 0x9C},
219 {0x0B9F, 0x0000, 0x0000, 0xBC},
220 {0x0B9F, 0x0B82, 0x0000, 0xF0},
221 {0x0B9F, 0x0BBF, 0x0000, 0xCA},
222 {0x0B9F, 0x0BC0, 0x0000, 0xCB},
223 {0x0B9F, 0x0BC1, 0x0000, 0xCE},
224 {0x0B9F, 0x0BC2, 0x0000, 0xDE},
225 {0x0BA1, 0x0B82, 0x0000, 0xF2},
226 {0x0BA3, 0x0000, 0x0000, 0xBD},
227 {0x0BA3, 0x0B82, 0x0000, 0xF1},
228 {0x0BA3, 0x0BC1, 0x0000, 0xCF},
229 {0x0BA3, 0x0BC2, 0x0000, 0xDF},
230 {0x0BA4, 0x0000, 0x0000, 0xBE},
231 {0x0BA4, 0x0BC1, 0x0000, 0xD0},
232 {0x0BA4, 0x0BC2, 0x0000, 0xE0},
233 {0x0BA8, 0x0000, 0x0000, 0xBF},
234 {0x0BA8, 0x0B82, 0x0000, 0xF3},
235 {0x0BA8, 0x0BC1, 0x0000, 0xD1},
236 {0x0BA8, 0x0BC2, 0x0000, 0xE1},
237 {0x0BA9, 0x0000, 0x0000, 0xC9},
238 {0x0BA9, 0x0B82, 0x0000, 0xFD},
239 {0x0BA9, 0x0BC1, 0x0000, 0xDB},
240 {0x0BA9, 0x0BC2, 0x0000, 0xEB},
241 {0x0BAA, 0x0000, 0x0000, 0xC0},
242 {0x0BAA, 0x0B82, 0x0000, 0xF4},
243 {0x0BAA, 0x0BC1, 0x0000, 0xD2},
244 {0x0BAA, 0x0BC2, 0x0000, 0xE2},
245 {0x0BAE, 0x0000, 0x0000, 0xC1},
246 {0x0BAE, 0x0B82, 0x0000, 0xF5},
247 {0x0BAE, 0x0BC1, 0x0000, 0xD3},
248 {0x0BAE, 0x0BC2, 0x0000, 0xE3},
249 {0x0BAF, 0x0000, 0x0000, 0xC2},
250 {0x0BAF, 0x0B82, 0x0000, 0xF6},
251 {0x0BAF, 0x0BC1, 0x0000, 0xD4},
252 {0x0BAF, 0x0BC2, 0x0000, 0xE4},
253 {0x0BB0, 0x0000, 0x0000, 0xC3},
254 {0x0BB0, 0x0B82, 0x0000, 0xF7},
255 {0x0BB0, 0x0BC1, 0x0000, 0xD5},
256 {0x0BB0, 0x0BC2, 0x0000, 0xE5},
257 {0x0BB1, 0x0000, 0x0000, 0xC8},
258 {0x0BB1, 0x0B82, 0x0000, 0xFC},
259 {0x0BB1, 0x0BC1, 0x0000, 0xDA},
260 {0x0BB1, 0x0BC2, 0x0000, 0xEA},
261 {0x0BB2, 0x0000, 0x0000, 0xC4},
262 {0x0BB2, 0x0B82, 0x0000, 0xF8},
263 {0x0BB2, 0x0BC1, 0x0000, 0xD6},
264 {0x0BB2, 0x0BC2, 0x0000, 0xE6},
265 {0x0BB3, 0x0000, 0x0000, 0xC7},
266 {0x0BB3, 0x0B82, 0x0000, 0xFB},
267 {0x0BB3, 0x0BC1, 0x0000, 0xD9},
268 {0x0BB3, 0x0BC2, 0x0000, 0xE9},
269 {0x0BB4, 0x0000, 0x0000, 0xC6},
270 {0x0BB4, 0x0B82, 0x0000, 0xFA},
271 {0x0BB4, 0x0BC1, 0x0000, 0xD8},
272 {0x0BB4, 0x0BC2, 0x0000, 0xE8},
273 {0x0BB5, 0x0000, 0x0000, 0xC5},
274 {0x0BB5, 0x0B82, 0x0000, 0xF9},
275 {0x0BB5, 0x0BC1, 0x0000, 0xD7},
276 {0x0BB5, 0x0BC2, 0x0000, 0xE7},
277 {0x0BB7, 0x0000, 0x0000, 0x84},
278 {0x0BB7, 0x0B82, 0x0000, 0x89},
279 {0x0BB8, 0x0000, 0x0000, 0x85},
280 {0x0BB8, 0x0B82, 0x0000, 0x8A},
281 {0x0BB9, 0x0000, 0x0000, 0x86},
282 {0x0BB9, 0x0B82, 0x0000, 0x8B},
283 {0x0BBE, 0x0000, 0x0000, 0xA1},
284 {0x0BBF, 0x0000, 0x0000, 0xA2},
285 {0x0BC0, 0x0000, 0x0000, 0xA3},
286 {0x0BC1, 0x0000, 0x0000, 0xA4},
287 {0x0BC2, 0x0000, 0x0000, 0xA5},
288 {0x0BC6, 0x0000, 0x0000, 0xA6},
289 {0x0BC7, 0x0000, 0x0000, 0xA7},
290 {0x0BC8, 0x0000, 0x0000, 0xA8},
291 {0x0BCC, 0x0000, 0x0000, 0xAA},
292 {0x0BE6, 0x0000, 0x0000, 0x80},
293 {0x0BE7, 0x0000, 0x0000, 0x81},
294 {0x0BE7, 0x0BB7, 0x0000, 0x87},
295 {0x0BE7, 0x0BB7, 0x0B82, 0x8C},
296 {0x0BE8, 0x0000, 0x0000, 0x8D},
297 {0x0BE9, 0x0000, 0x0000, 0x8E},
298 {0x0BEA, 0x0000, 0x0000, 0x8F},
299 {0x0BEB, 0x0000, 0x0000, 0x90},
300 {0x0BEC, 0x0000, 0x0000, 0x95},
301 {0x0BED, 0x0000, 0x0000, 0x96},
302 {0x0BEE, 0x0000, 0x0000, 0x97},
303 {0x0BEF, 0x0000, 0x0000, 0x98},
304 {0x0BF0, 0x0000, 0x0000, 0x9D},
305 {0x0BF1, 0x0000, 0x0000, 0x9E},
306 {0x0BF2, 0x0000, 0x0000, 0x9F},
307 {0x2018, 0x0000, 0x0000, 0x91},
308 {0x2019, 0x0000, 0x0000, 0x92},
309 {0x201C, 0x0000, 0x0000, 0x93},
310 {0x201C, 0x0000, 0x0000, 0x94}
311};
312
313static const ushort TsToUn [][3] = {
314 // Starting at 0x80
315 {0x0BE6, 0x0000, 0x0000},
316 {0x0BE7, 0x0000, 0x0000},
317 {0x0000, 0x0000, 0x0000}, // unknown
318 {0x0B9C, 0x0000, 0x0000},
319 {0x0BB7, 0x0000, 0x0000},
320 {0x0BB8, 0x0000, 0x0000},
321 {0x0BB9, 0x0000, 0x0000},
322 {0x0BE7, 0x0BB7, 0x0000},
323 {0x0B9C, 0x0B82, 0x0000},
324 {0x0BB7, 0x0B82, 0x0000},
325 {0x0BB8, 0x0B82, 0x0000},
326 {0x0BB9, 0x0B82, 0x0000},
327 {0x0BE7, 0x0BB7, 0x0B82},
328 {0x0BE8, 0x0000, 0x0000},
329 {0x0BE9, 0x0000, 0x0000},
330 {0x0BEA, 0x0000, 0x0000},
331 {0x0BEB, 0x0000, 0x0000},
332 {0x2018, 0x0000, 0x0000},
333 {0x2019, 0x0000, 0x0000},
334 {0x201C, 0x0000, 0x0000},
335 {0x201C, 0x0000, 0x0000}, // two of the same??
336 {0x0BEC, 0x0000, 0x0000},
337 {0x0BED, 0x0000, 0x0000},
338 {0x0BEE, 0x0000, 0x0000},
339 {0x0BEF, 0x0000, 0x0000},
340 {0x0B99, 0x0BC1, 0x0000},
341 {0x0B9E, 0x0BC1, 0x0000},
342 {0x0B99, 0x0BC2, 0x0000},
343 {0x0B9E, 0x0BC2, 0x0000},
344 {0x0BF0, 0x0000, 0x0000},
345 {0x0BF1, 0x0000, 0x0000},
346 {0x0BF2, 0x0000, 0x0000},
347 {0x00A0, 0x0000, 0x0000},
348 {0x0BBE, 0x0000, 0x0000},
349 {0x0BBF, 0x0000, 0x0000},
350 {0x0BC0, 0x0000, 0x0000},
351 {0x0BC1, 0x0000, 0x0000},
352 {0x0BC2, 0x0000, 0x0000},
353 {0x0BC6, 0x0000, 0x0000},
354 {0x0BC7, 0x0000, 0x0000},
355 {0x0BC8, 0x0000, 0x0000},
356 {0x00A9, 0x0000, 0x0000},
357 {0x0BCC, 0x0000, 0x0000},
358 {0x0B85, 0x0000, 0x0000},
359 {0x0B86, 0x0000, 0x0000},
360 {0x0B87, 0x0000, 0x0000},
361 {0x0B88, 0x0000, 0x0000},
362 {0x0B89, 0x0000, 0x0000},
363 {0x0B8A, 0x0000, 0x0000},
364 {0x0B8E, 0x0000, 0x0000},
365 {0x0B8F, 0x0000, 0x0000},
366 {0x0B90, 0x0000, 0x0000},
367 {0x0B92, 0x0000, 0x0000},
368 {0x0B93, 0x0000, 0x0000},
369 {0x0B94, 0x0000, 0x0000},
370 {0x0B83, 0x0000, 0x0000},
371 {0x0B95, 0x0000, 0x0000},
372 {0x0B99, 0x0000, 0x0000},
373 {0x0B9A, 0x0000, 0x0000},
374 {0x0B9E, 0x0000, 0x0000},
375 {0x0B9F, 0x0000, 0x0000},
376 {0x0BA3, 0x0000, 0x0000},
377 {0x0BA4, 0x0000, 0x0000},
378 {0x0BA8, 0x0000, 0x0000},
379 {0x0BAA, 0x0000, 0x0000},
380 {0x0BAE, 0x0000, 0x0000},
381 {0x0BAF, 0x0000, 0x0000},
382 {0x0BB0, 0x0000, 0x0000},
383 {0x0BB2, 0x0000, 0x0000},
384 {0x0BB5, 0x0000, 0x0000},
385 {0x0BB4, 0x0000, 0x0000},
386 {0x0BB3, 0x0000, 0x0000},
387 {0x0BB1, 0x0000, 0x0000},
388 {0x0BA9, 0x0000, 0x0000},
389 {0x0B9F, 0x0BBF, 0x0000},
390 {0x0B9F, 0x0BC0, 0x0000},
391 {0x0B95, 0x0BC1, 0x0000},
392 {0x0B9A, 0x0BC1, 0x0000},
393 {0x0B9F, 0x0BC1, 0x0000},
394 {0x0BA3, 0x0BC1, 0x0000},
395 {0x0BA4, 0x0BC1, 0x0000},
396 {0x0BA8, 0x0BC1, 0x0000},
397 {0x0BAA, 0x0BC1, 0x0000},
398 {0x0BAE, 0x0BC1, 0x0000},
399 {0x0BAF, 0x0BC1, 0x0000},
400 {0x0BB0, 0x0BC1, 0x0000},
401 {0x0BB2, 0x0BC1, 0x0000},
402 {0x0BB5, 0x0BC1, 0x0000},
403 {0x0BB4, 0x0BC1, 0x0000},
404 {0x0BB3, 0x0BC1, 0x0000},
405 {0x0BB1, 0x0BC1, 0x0000},
406 {0x0BA9, 0x0BC1, 0x0000},
407 {0x0B95, 0x0BC2, 0x0000},
408 {0x0B9A, 0x0BC2, 0x0000},
409 {0x0B9F, 0x0BC2, 0x0000},
410 {0x0BA3, 0x0BC2, 0x0000},
411 {0x0BA4, 0x0BC2, 0x0000},
412 {0x0BA8, 0x0BC2, 0x0000},
413 {0x0BAA, 0x0BC2, 0x0000},
414 {0x0BAE, 0x0BC2, 0x0000},
415 {0x0BAF, 0x0BC2, 0x0000},
416 {0x0BB0, 0x0BC2, 0x0000},
417 {0x0BB2, 0x0BC2, 0x0000},
418 {0x0BB5, 0x0BC2, 0x0000},
419 {0x0BB4, 0x0BC2, 0x0000},
420 {0x0BB3, 0x0BC2, 0x0000},
421 {0x0BB1, 0x0BC2, 0x0000},
422 {0x0BA9, 0x0BC2, 0x0000},
423 {0x0B95, 0x0B82, 0x0000},
424 {0x0B99, 0x0B82, 0x0000},
425 {0x0B9A, 0x0B82, 0x0000},
426 {0x0B9E, 0x0B82, 0x0000},
427 {0x0B9F, 0x0B82, 0x0000},
428 {0x0BA3, 0x0B82, 0x0000},
429 {0x0BA1, 0x0B82, 0x0000},
430 {0x0BA8, 0x0B82, 0x0000},
431 {0x0BAA, 0x0B82, 0x0000},
432 {0x0BAE, 0x0B82, 0x0000},
433 {0x0BAF, 0x0B82, 0x0000},
434 {0x0BB0, 0x0B82, 0x0000},
435 {0x0BB2, 0x0B82, 0x0000},
436 {0x0BB5, 0x0B82, 0x0000},
437 {0x0BB4, 0x0B82, 0x0000},
438 {0x0BB3, 0x0B82, 0x0000},
439 {0x0BB1, 0x0B82, 0x0000},
440 {0x0BA9, 0x0B82, 0x0000}
441};
442
443static int cmp(const ushort *s1, const ushort *s2, size_t len)
444{
445 int diff = 0;
446
447 while (len-- && (diff = *s1++ - *s2++) == 0)
448 ;
449
450 return diff;
451}
452
453static unsigned char qt_UnicodeToTSCII(ushort u1, ushort u2, ushort u3)
454{
455 ushort s[3];
456 s[0] = u1;
457 s[1] = u2;
458 s[2] = u3;
459
460 int a = 0; // start pos
461 int b = UnToTsLast; // end pos
462
463 // do a binary search for the composed unicode in the list
464 while (a <= b) {
465 int w = (a + b) / 2;
466 int j = cmp(s1: UnToTs[w], s2: s, len: 3);
467
468 if (j == 0)
469 // found it
470 return UnToTs[w][3];
471
472 if (j < 0)
473 a = w + 1;
474 else
475 b = w - 1;
476 }
477
478 return 0;
479}
480
481static unsigned int qt_TSCIIToUnicode(uint code, uint *s)
482{
483 int len = 0;
484 for (int i = 0; i < 3; i++) {
485 uint u = TsToUn[code & 0x7f][i];
486 s[i] = u;
487 if (s[i]) len = i + 1;
488 }
489
490 return len;
491}
492
493QT_END_NAMESPACE
494

source code of qtbase/src/corelib/codecs/qtsciicodec.cpp