| author | Dremov Kirill (Nokia-D-MSW/Tampere) <kirill.dremov@nokia.com> |
| Mon, 03 May 2010 13:17:34 +0300 | |
| changeset 19 | fcece45ef507 |
| parent 18 | 2f34d5167611 |
| child 30 | 5dc02b23752f |
| permissions | -rw-r--r-- |
| 0 | 1 |
/**************************************************************************** |
2 |
** |
|
|
18
2f34d5167611
Revision: 201011
Dremov Kirill (Nokia-D-MSW/Tampere) <kirill.dremov@nokia.com>
parents:
0
diff
changeset
|
3 |
** Copyright (C) 2010 Nokia Corporation and/or its subsidiary(-ies). |
| 0 | 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 |
||
42 |
// Don't define it while compiling this module, or USERS of Qt will |
|
43 |
// not be able to link. |
|
44 |
#ifdef QT_NO_CAST_FROM_ASCII |
|
45 |
#undef QT_NO_CAST_FROM_ASCII |
|
46 |
#endif |
|
47 |
#ifdef QT_NO_CAST_TO_ASCII |
|
48 |
#undef QT_NO_CAST_TO_ASCII |
|
49 |
#endif |
|
50 |
#include "qchar.h" |
|
51 |
#include "qdatastream.h" |
|
52 |
#include "qtextcodec.h" |
|
53 |
||
54 |
#include "qunicodetables_p.h" |
|
55 |
||
56 |
#include "qunicodetables.cpp" |
|
57 |
||
58 |
QT_BEGIN_NAMESPACE |
|
59 |
||
60 |
#define LAST_UNICODE_CHAR 0x10ffff |
|
61 |
||
62 |
#ifndef QT_NO_CODEC_FOR_C_STRINGS |
|
63 |
#ifdef QT_NO_TEXTCODEC |
|
64 |
#define QT_NO_CODEC_FOR_C_STRINGS |
|
65 |
#endif |
|
66 |
#endif |
|
67 |
||
68 |
#define FLAG(x) (1 << (x)) |
|
69 |
||
70 |
/*! \class QLatin1Char |
|
71 |
\brief The QLatin1Char class provides an 8-bit ASCII/Latin-1 character. |
|
72 |
||
73 |
\ingroup string-processing |
|
74 |
||
75 |
This class is only useful to avoid the codec for C strings business |
|
76 |
in the QChar(ch) constructor. You can avoid it by writing |
|
77 |
QChar(ch, 0). |
|
78 |
||
79 |
\sa QChar, QLatin1String, QString |
|
80 |
*/ |
|
81 |
||
82 |
/*! |
|
83 |
\fn const char QLatin1Char::toLatin1() const |
|
84 |
||
85 |
Converts a Latin-1 character to an 8-bit ASCII representation of |
|
86 |
the character. |
|
87 |
*/ |
|
88 |
||
89 |
/*! |
|
90 |
\fn const ushort QLatin1Char::unicode() const |
|
91 |
||
92 |
Converts a Latin-1 character to an 16-bit-encoded Unicode representation |
|
93 |
of the character. |
|
94 |
*/ |
|
95 |
||
96 |
/*! |
|
97 |
\fn QLatin1Char::QLatin1Char(char c) |
|
98 |
||
99 |
Constructs a Latin-1 character for \a c. This constructor should be |
|
100 |
used when the encoding of the input character is known to be Latin-1. |
|
101 |
*/ |
|
102 |
||
103 |
/*! |
|
104 |
\class QChar |
|
105 |
\brief The QChar class provides a 16-bit Unicode character. |
|
106 |
||
107 |
\ingroup string-processing |
|
108 |
\reentrant |
|
109 |
||
110 |
In Qt, Unicode characters are 16-bit entities without any markup |
|
111 |
or structure. This class represents such an entity. It is |
|
112 |
lightweight, so it can be used everywhere. Most compilers treat |
|
113 |
it like a \c{unsigned short}.
|
|
114 |
||
115 |
QChar provides a full complement of testing/classification |
|
116 |
functions, converting to and from other formats, converting from |
|
117 |
composed to decomposed Unicode, and trying to compare and |
|
118 |
case-convert if you ask it to. |
|
119 |
||
120 |
The classification functions include functions like those in the |
|
121 |
standard C++ header \<cctype\> (formerly \<ctype.h\>), but |
|
122 |
operating on the full range of Unicode characters. They all |
|
123 |
return true if the character is a certain type of character; |
|
124 |
otherwise they return false. These classification functions are |
|
125 |
isNull() (returns true if the character is '\\0'), isPrint() |
|
126 |
(true if the character is any sort of printable character, |
|
127 |
including whitespace), isPunct() (any sort of punctation), |
|
128 |
isMark() (Unicode Mark), isLetter() (a letter), isNumber() (any |
|
129 |
sort of numeric character, not just 0-9), isLetterOrNumber(), and |
|
130 |
isDigit() (decimal digits). All of these are wrappers around |
|
131 |
category() which return the Unicode-defined category of each |
|
132 |
character. |
|
133 |
||
134 |
QChar also provides direction(), which indicates the "natural" |
|
135 |
writing direction of this character. The joining() function |
|
136 |
indicates how the character joins with its neighbors (needed |
|
137 |
mostly for Arabic) and finally hasMirrored(), which indicates |
|
138 |
whether the character needs to be mirrored when it is printed in |
|
139 |
its "unnatural" writing direction. |
|
140 |
||
141 |
Composed Unicode characters (like \aring) can be converted to |
|
142 |
decomposed Unicode ("a" followed by "ring above") by using
|
|
143 |
decomposition(). |
|
144 |
||
145 |
In Unicode, comparison is not necessarily possible and case |
|
146 |
conversion is very difficult at best. Unicode, covering the |
|
147 |
"entire" world, also includes most of the world's case and |
|
148 |
sorting problems. operator==() and friends will do comparison |
|
149 |
based purely on the numeric Unicode value (code point) of the |
|
150 |
characters, and toUpper() and toLower() will do case changes when |
|
151 |
the character has a well-defined uppercase/lowercase equivalent. |
|
152 |
For locale-dependent comparisons, use |
|
153 |
QString::localeAwareCompare(). |
|
154 |
||
155 |
The conversion functions include unicode() (to a scalar), |
|
156 |
toLatin1() (to scalar, but converts all non-Latin-1 characters to |
|
157 |
0), row() (gives the Unicode row), cell() (gives the Unicode |
|
158 |
cell), digitValue() (gives the integer value of any of the |
|
159 |
numerous digit characters), and a host of constructors. |
|
160 |
||
161 |
QChar provides constructors and cast operators that make it easy |
|
162 |
to convert to and from traditional 8-bit \c{char}s. If you
|
|
163 |
defined \c QT_NO_CAST_FROM_ASCII and \c QT_NO_CAST_TO_ASCII, as |
|
164 |
explained in the QString documentation, you will need to |
|
165 |
explicitly call fromAscii() or fromLatin1(), or use QLatin1Char, |
|
166 |
to construct a QChar from an 8-bit \c char, and you will need to |
|
167 |
call toAscii() or toLatin1() to get the 8-bit value back. |
|
168 |
||
169 |
\sa QString, Unicode, QLatin1Char |
|
170 |
*/ |
|
171 |
||
172 |
/*! |
|
173 |
\enum QChar::UnicodeVersion |
|
174 |
||
175 |
Specifies which version of the \l{http://www.unicode.org/}{Unicode standard}
|
|
176 |
introduced a certain character. |
|
177 |
||
178 |
\value Unicode_1_1 Version 1.1 |
|
179 |
\value Unicode_2_0 Version 2.0 |
|
180 |
\value Unicode_2_1_2 Version 2.1.2 |
|
181 |
\value Unicode_3_0 Version 3.0 |
|
182 |
\value Unicode_3_1 Version 3.1 |
|
183 |
\value Unicode_3_2 Version 3.2 |
|
184 |
\value Unicode_4_0 Version 4.0 |
|
185 |
\value Unicode_4_1 Version 4.1 |
|
186 |
\value Unicode_5_0 Version 5.0 |
|
187 |
\value Unicode_Unassigned The value is not assigned to any character |
|
188 |
in version 5.0 of Unicode. |
|
189 |
||
190 |
\sa unicodeVersion() |
|
191 |
*/ |
|
192 |
||
193 |
/*! |
|
194 |
\enum QChar::Category |
|
195 |
||
196 |
This enum maps the Unicode character categories. |
|
197 |
||
198 |
The following characters are normative in Unicode: |
|
199 |
||
200 |
\value Mark_NonSpacing Unicode class name Mn |
|
201 |
||
202 |
\value Mark_SpacingCombining Unicode class name Mc |
|
203 |
||
204 |
\value Mark_Enclosing Unicode class name Me |
|
205 |
||
206 |
\value Number_DecimalDigit Unicode class name Nd |
|
207 |
||
208 |
\value Number_Letter Unicode class name Nl |
|
209 |
||
210 |
\value Number_Other Unicode class name No |
|
211 |
||
212 |
\value Separator_Space Unicode class name Zs |
|
213 |
||
214 |
\value Separator_Line Unicode class name Zl |
|
215 |
||
216 |
\value Separator_Paragraph Unicode class name Zp |
|
217 |
||
218 |
\value Other_Control Unicode class name Cc |
|
219 |
||
220 |
\value Other_Format Unicode class name Cf |
|
221 |
||
222 |
\value Other_Surrogate Unicode class name Cs |
|
223 |
||
224 |
\value Other_PrivateUse Unicode class name Co |
|
225 |
||
226 |
\value Other_NotAssigned Unicode class name Cn |
|
227 |
||
228 |
||
229 |
The following categories are informative in Unicode: |
|
230 |
||
231 |
\value Letter_Uppercase Unicode class name Lu |
|
232 |
||
233 |
\value Letter_Lowercase Unicode class name Ll |
|
234 |
||
235 |
\value Letter_Titlecase Unicode class name Lt |
|
236 |
||
237 |
\value Letter_Modifier Unicode class name Lm |
|
238 |
||
239 |
\value Letter_Other Unicode class name Lo |
|
240 |
||
241 |
\value Punctuation_Connector Unicode class name Pc |
|
242 |
||
243 |
\value Punctuation_Dash Unicode class name Pd |
|
244 |
||
245 |
\value Punctuation_Open Unicode class name Ps |
|
246 |
||
247 |
\value Punctuation_Close Unicode class name Pe |
|
248 |
||
249 |
\value Punctuation_InitialQuote Unicode class name Pi |
|
250 |
||
251 |
\value Punctuation_FinalQuote Unicode class name Pf |
|
252 |
||
253 |
\value Punctuation_Other Unicode class name Po |
|
254 |
||
255 |
\value Symbol_Math Unicode class name Sm |
|
256 |
||
257 |
\value Symbol_Currency Unicode class name Sc |
|
258 |
||
259 |
\value Symbol_Modifier Unicode class name Sk |
|
260 |
||
261 |
\value Symbol_Other Unicode class name So |
|
262 |
||
263 |
\value NoCategory Qt cannot find an appropriate category for the character. |
|
264 |
||
265 |
\omitvalue Punctuation_Dask |
|
266 |
||
267 |
\sa category() |
|
268 |
*/ |
|
269 |
||
270 |
/*! |
|
271 |
\enum QChar::Direction |
|
272 |
||
273 |
This enum type defines the Unicode direction attributes. See the |
|
274 |
\l{http://www.unicode.org/}{Unicode Standard} for a description
|
|
275 |
of the values. |
|
276 |
||
277 |
In order to conform to C/C++ naming conventions "Dir" is prepended |
|
278 |
to the codes used in the Unicode Standard. |
|
279 |
||
280 |
\value DirAL |
|
281 |
\value DirAN |
|
282 |
\value DirB |
|
283 |
\value DirBN |
|
284 |
\value DirCS |
|
285 |
\value DirEN |
|
286 |
\value DirES |
|
287 |
\value DirET |
|
288 |
\value DirL |
|
289 |
\value DirLRE |
|
290 |
\value DirLRO |
|
291 |
\value DirNSM |
|
292 |
\value DirON |
|
293 |
\value DirPDF |
|
294 |
\value DirR |
|
295 |
\value DirRLE |
|
296 |
\value DirRLO |
|
297 |
\value DirS |
|
298 |
\value DirWS |
|
299 |
||
300 |
\sa direction() |
|
301 |
*/ |
|
302 |
||
303 |
/*! |
|
304 |
\enum QChar::Decomposition |
|
305 |
||
306 |
This enum type defines the Unicode decomposition attributes. See |
|
307 |
the \l{http://www.unicode.org/}{Unicode Standard} for a
|
|
308 |
description of the values. |
|
309 |
||
310 |
\value NoDecomposition |
|
311 |
\value Canonical |
|
312 |
\value Circle |
|
313 |
\value Compat |
|
314 |
\value Final |
|
315 |
\value Font |
|
316 |
\value Fraction |
|
317 |
\value Initial |
|
318 |
\value Isolated |
|
319 |
\value Medial |
|
320 |
\value Narrow |
|
321 |
\value NoBreak |
|
322 |
\value Small |
|
323 |
\value Square |
|
324 |
\value Sub |
|
325 |
\value Super |
|
326 |
\value Vertical |
|
327 |
\value Wide |
|
328 |
||
329 |
\omitvalue Single |
|
330 |
||
331 |
\sa decomposition() |
|
332 |
*/ |
|
333 |
||
334 |
/*! |
|
335 |
\enum QChar::Joining |
|
336 |
||
337 |
This enum type defines the Unicode joining attributes. See the |
|
338 |
\l{http://www.unicode.org/}{Unicode Standard} for a description
|
|
339 |
of the values. |
|
340 |
||
341 |
\value Center |
|
342 |
\value Dual |
|
343 |
\value OtherJoining |
|
344 |
\value Right |
|
345 |
||
346 |
\sa joining() |
|
347 |
*/ |
|
348 |
||
349 |
/*! |
|
350 |
\enum QChar::CombiningClass |
|
351 |
||
352 |
\internal |
|
353 |
||
354 |
This enum type defines names for some of the Unicode combining |
|
355 |
classes. See the \l{http://www.unicode.org/}{Unicode Standard}
|
|
356 |
for a description of the values. |
|
357 |
||
358 |
\value Combining_Above |
|
359 |
\value Combining_AboveAttached |
|
360 |
\value Combining_AboveLeft |
|
361 |
\value Combining_AboveLeftAttached |
|
362 |
\value Combining_AboveRight |
|
363 |
\value Combining_AboveRightAttached |
|
364 |
\value Combining_Below |
|
365 |
\value Combining_BelowAttached |
|
366 |
\value Combining_BelowLeft |
|
367 |
\value Combining_BelowLeftAttached |
|
368 |
\value Combining_BelowRight |
|
369 |
\value Combining_BelowRightAttached |
|
370 |
\value Combining_DoubleAbove |
|
371 |
\value Combining_DoubleBelow |
|
372 |
\value Combining_IotaSubscript |
|
373 |
\value Combining_Left |
|
374 |
\value Combining_LeftAttached |
|
375 |
\value Combining_Right |
|
376 |
\value Combining_RightAttached |
|
377 |
*/ |
|
378 |
||
379 |
/*! |
|
380 |
\enum QChar::SpecialCharacter |
|
381 |
||
382 |
\value Null A QChar with this value isNull(). |
|
383 |
\value Nbsp Non-breaking space. |
|
|
19
fcece45ef507
Revision: 201015
Dremov Kirill (Nokia-D-MSW/Tampere) <kirill.dremov@nokia.com>
parents:
18
diff
changeset
|
384 |
\value ReplacementCharacter The character shown when a font has no glyph |
|
fcece45ef507
Revision: 201015
Dremov Kirill (Nokia-D-MSW/Tampere) <kirill.dremov@nokia.com>
parents:
18
diff
changeset
|
385 |
for a certain codepoint. A special question mark character is often |
|
fcece45ef507
Revision: 201015
Dremov Kirill (Nokia-D-MSW/Tampere) <kirill.dremov@nokia.com>
parents:
18
diff
changeset
|
386 |
used. Codecs use this codepoint when input data cannot be |
|
fcece45ef507
Revision: 201015
Dremov Kirill (Nokia-D-MSW/Tampere) <kirill.dremov@nokia.com>
parents:
18
diff
changeset
|
387 |
represented in Unicode. |
|
fcece45ef507
Revision: 201015
Dremov Kirill (Nokia-D-MSW/Tampere) <kirill.dremov@nokia.com>
parents:
18
diff
changeset
|
388 |
\value ObjectReplacementCharacter Used to represent an object such as an |
|
fcece45ef507
Revision: 201015
Dremov Kirill (Nokia-D-MSW/Tampere) <kirill.dremov@nokia.com>
parents:
18
diff
changeset
|
389 |
image when such objects cannot be presented. |
| 0 | 390 |
\value ByteOrderMark |
391 |
\value ByteOrderSwapped |
|
392 |
\value ParagraphSeparator |
|
393 |
\value LineSeparator |
|
394 |
||
395 |
\omitvalue null |
|
396 |
\omitvalue replacement |
|
397 |
\omitvalue byteOrderMark |
|
398 |
\omitvalue byteOrderSwapped |
|
399 |
\omitvalue nbsp |
|
400 |
*/ |
|
401 |
||
402 |
/*! |
|
403 |
\fn void QChar::setCell(uchar cell) |
|
404 |
\internal |
|
405 |
*/ |
|
406 |
||
407 |
/*! |
|
408 |
\fn void QChar::setRow(uchar row) |
|
409 |
\internal |
|
410 |
*/ |
|
411 |
||
412 |
/*! |
|
413 |
\fn QChar::QChar() |
|
414 |
||
415 |
Constructs a null QChar ('\\0').
|
|
416 |
||
417 |
\sa isNull() |
|
418 |
*/ |
|
419 |
||
420 |
/*! |
|
421 |
\fn QChar::QChar(QLatin1Char ch) |
|
422 |
||
423 |
Constructs a QChar corresponding to ASCII/Latin-1 character \a ch. |
|
424 |
*/ |
|
425 |
||
426 |
/*! |
|
427 |
\fn QChar::QChar(SpecialCharacter ch) |
|
428 |
||
429 |
Constructs a QChar for the predefined character value \a ch. |
|
430 |
*/ |
|
431 |
||
432 |
/*! |
|
433 |
Constructs a QChar corresponding to ASCII/Latin-1 character \a |
|
434 |
ch. |
|
435 |
*/ |
|
436 |
QChar::QChar(char ch) |
|
437 |
{
|
|
438 |
#ifndef QT_NO_CODEC_FOR_C_STRINGS |
|
439 |
if (QTextCodec::codecForCStrings()) |
|
440 |
// ##### |
|
441 |
ucs = QTextCodec::codecForCStrings()->toUnicode(&ch, 1).at(0).unicode(); |
|
442 |
else |
|
443 |
#endif |
|
444 |
ucs = uchar(ch); |
|
445 |
} |
|
446 |
||
447 |
/*! |
|
448 |
Constructs a QChar corresponding to ASCII/Latin-1 character \a ch. |
|
449 |
*/ |
|
450 |
QChar::QChar(uchar ch) |
|
451 |
{
|
|
452 |
#ifndef QT_NO_CODEC_FOR_C_STRINGS |
|
453 |
if (QTextCodec::codecForCStrings()) {
|
|
454 |
// ##### |
|
455 |
char c = char(ch); |
|
456 |
ucs = QTextCodec::codecForCStrings()->toUnicode(&c, 1).at(0).unicode(); |
|
457 |
} else |
|
458 |
#endif |
|
459 |
ucs = ch; |
|
460 |
} |
|
461 |
||
462 |
/*! |
|
463 |
\fn QChar::QChar(uchar cell, uchar row) |
|
464 |
||
465 |
Constructs a QChar for Unicode cell \a cell in row \a row. |
|
466 |
||
467 |
\sa cell(), row() |
|
468 |
*/ |
|
469 |
||
470 |
/*! |
|
471 |
\fn QChar::QChar(ushort code) |
|
472 |
||
473 |
Constructs a QChar for the character with Unicode code point \a |
|
474 |
code. |
|
475 |
*/ |
|
476 |
||
477 |
||
478 |
/*! |
|
479 |
\fn QChar::QChar(short code) |
|
480 |
||
481 |
Constructs a QChar for the character with Unicode code point \a |
|
482 |
code. |
|
483 |
*/ |
|
484 |
||
485 |
||
486 |
/*! |
|
487 |
\fn QChar::QChar(uint code) |
|
488 |
||
489 |
Constructs a QChar for the character with Unicode code point \a |
|
490 |
code. |
|
491 |
*/ |
|
492 |
||
493 |
||
494 |
/*! |
|
495 |
\fn QChar::QChar(int code) |
|
496 |
||
497 |
Constructs a QChar for the character with Unicode code point \a |
|
498 |
code. |
|
499 |
*/ |
|
500 |
||
501 |
||
502 |
/*! |
|
503 |
\fn bool QChar::isNull() const |
|
504 |
||
505 |
Returns true if the character is the Unicode character 0x0000 |
|
506 |
('\\0'); otherwise returns false.
|
|
507 |
*/ |
|
508 |
||
509 |
/*! |
|
510 |
\fn uchar QChar::cell() const |
|
511 |
||
512 |
Returns the cell (least significant byte) of the Unicode |
|
513 |
character. |
|
514 |
||
515 |
\sa row() |
|
516 |
*/ |
|
517 |
||
518 |
/*! |
|
519 |
\fn uchar QChar::row() const |
|
520 |
||
521 |
Returns the row (most significant byte) of the Unicode character. |
|
522 |
||
523 |
\sa cell() |
|
524 |
*/ |
|
525 |
||
526 |
/*! |
|
527 |
Returns true if the character is a printable character; otherwise |
|
528 |
returns false. This is any character not of category Cc or Cn. |
|
529 |
||
530 |
Note that this gives no indication of whether the character is |
|
531 |
available in a particular font. |
|
532 |
*/ |
|
533 |
bool QChar::isPrint() const |
|
534 |
{
|
|
535 |
const int test = FLAG(Other_Control) | |
|
536 |
FLAG(Other_NotAssigned); |
|
537 |
return !(FLAG(qGetProp(ucs)->category) & test); |
|
538 |
} |
|
539 |
||
540 |
/*! |
|
541 |
Returns true if the character is a separator character |
|
542 |
(Separator_* categories); otherwise returns false. |
|
543 |
*/ |
|
544 |
bool QChar::isSpace() const |
|
545 |
{
|
|
546 |
if(ucs >= 9 && ucs <=13) |
|
547 |
return true; |
|
548 |
const int test = FLAG(Separator_Space) | |
|
549 |
FLAG(Separator_Line) | |
|
550 |
FLAG(Separator_Paragraph); |
|
551 |
return FLAG(qGetProp(ucs)->category) & test; |
|
552 |
} |
|
553 |
||
554 |
/*! |
|
555 |
Returns true if the character is a mark (Mark_* categories); |
|
556 |
otherwise returns false. |
|
557 |
||
558 |
See QChar::Category for more information regarding marks. |
|
559 |
*/ |
|
560 |
bool QChar::isMark() const |
|
561 |
{
|
|
562 |
const int test = FLAG(Mark_NonSpacing) | |
|
563 |
FLAG(Mark_SpacingCombining) | |
|
564 |
FLAG(Mark_Enclosing); |
|
565 |
return FLAG(qGetProp(ucs)->category) & test; |
|
566 |
} |
|
567 |
||
568 |
/*! |
|
569 |
Returns true if the character is a punctuation mark (Punctuation_* |
|
570 |
categories); otherwise returns false. |
|
571 |
*/ |
|
572 |
bool QChar::isPunct() const |
|
573 |
{
|
|
574 |
const int test = FLAG(Punctuation_Connector) | |
|
575 |
FLAG(Punctuation_Dash) | |
|
576 |
FLAG(Punctuation_Open) | |
|
577 |
FLAG(Punctuation_Close) | |
|
578 |
FLAG(Punctuation_InitialQuote) | |
|
579 |
FLAG(Punctuation_FinalQuote) | |
|
580 |
FLAG(Punctuation_Other); |
|
581 |
return FLAG(qGetProp(ucs)->category) & test; |
|
582 |
} |
|
583 |
||
584 |
/*! |
|
585 |
Returns true if the character is a letter (Letter_* categories); |
|
586 |
otherwise returns false. |
|
587 |
*/ |
|
588 |
bool QChar::isLetter() const |
|
589 |
{
|
|
590 |
const int test = FLAG(Letter_Uppercase) | |
|
591 |
FLAG(Letter_Lowercase) | |
|
592 |
FLAG(Letter_Titlecase) | |
|
593 |
FLAG(Letter_Modifier) | |
|
594 |
FLAG(Letter_Other); |
|
595 |
return FLAG(qGetProp(ucs)->category) & test; |
|
596 |
} |
|
597 |
||
598 |
/*! |
|
599 |
Returns true if the character is a number (Number_* categories, |
|
600 |
not just 0-9); otherwise returns false. |
|
601 |
||
602 |
\sa isDigit() |
|
603 |
*/ |
|
604 |
bool QChar::isNumber() const |
|
605 |
{
|
|
606 |
const int test = FLAG(Number_DecimalDigit) | |
|
607 |
FLAG(Number_Letter) | |
|
608 |
FLAG(Number_Other); |
|
609 |
return FLAG(qGetProp(ucs)->category) & test; |
|
610 |
} |
|
611 |
||
612 |
/*! |
|
613 |
Returns true if the character is a letter or number (Letter_* or |
|
614 |
Number_* categories); otherwise returns false. |
|
615 |
*/ |
|
616 |
bool QChar::isLetterOrNumber() const |
|
617 |
{
|
|
618 |
const int test = FLAG(Letter_Uppercase) | |
|
619 |
FLAG(Letter_Lowercase) | |
|
620 |
FLAG(Letter_Titlecase) | |
|
621 |
FLAG(Letter_Modifier) | |
|
622 |
FLAG(Letter_Other) | |
|
623 |
FLAG(Number_DecimalDigit) | |
|
624 |
FLAG(Number_Letter) | |
|
625 |
FLAG(Number_Other); |
|
626 |
return FLAG(qGetProp(ucs)->category) & test; |
|
627 |
} |
|
628 |
||
629 |
||
630 |
/*! |
|
631 |
Returns true if the character is a decimal digit |
|
632 |
(Number_DecimalDigit); otherwise returns false. |
|
633 |
*/ |
|
634 |
bool QChar::isDigit() const |
|
635 |
{
|
|
636 |
return (qGetProp(ucs)->category == Number_DecimalDigit); |
|
637 |
} |
|
638 |
||
639 |
||
640 |
/*! |
|
641 |
Returns true if the character is a symbol (Symbol_* categories); |
|
642 |
otherwise returns false. |
|
643 |
*/ |
|
644 |
bool QChar::isSymbol() const |
|
645 |
{
|
|
646 |
const int test = FLAG(Symbol_Math) | |
|
647 |
FLAG(Symbol_Currency) | |
|
648 |
FLAG(Symbol_Modifier) | |
|
649 |
FLAG(Symbol_Other); |
|
650 |
return FLAG(qGetProp(ucs)->category) & test; |
|
651 |
} |
|
652 |
||
653 |
/*! |
|
654 |
\fn bool QChar::isHighSurrogate() const |
|
655 |
||
656 |
Returns true if the QChar is the high part of a utf16 surrogate |
|
657 |
(ie. if its code point is between 0xd800 and 0xdbff). |
|
658 |
*/ |
|
659 |
||
660 |
/*! |
|
661 |
\fn bool QChar::isLowSurrogate() const |
|
662 |
||
663 |
Returns true if the QChar is the low part of a utf16 surrogate |
|
664 |
(ie. if its code point is between 0xdc00 and 0xdfff). |
|
665 |
*/ |
|
666 |
||
667 |
/*! |
|
668 |
\fn static uint QChar::surrogateToUcs4(ushort high, ushort low) |
|
669 |
||
670 |
Converts a UTF16 surrogate pair with the given \a high and \a low values |
|
671 |
to its UCS-4 code point. |
|
672 |
*/ |
|
673 |
||
674 |
/*! |
|
675 |
\fn static uint QChar::surrogateToUcs4(QChar high, QChar low) |
|
676 |
||
677 |
Converts a utf16 surrogate pair (\a high, \a low) to its ucs4 code |
|
678 |
point. |
|
679 |
*/ |
|
680 |
||
681 |
/*! |
|
682 |
\fn static ushort QChar::highSurrogate(uint ucs4) |
|
683 |
||
684 |
Returns the high surrogate value of a ucs4 code point. |
|
685 |
The returned result is undefined if \a ucs4 is smaller than 0x10000. |
|
686 |
*/ |
|
687 |
||
688 |
/*! |
|
689 |
\fn static ushort QChar::lowSurrogate(uint ucs4) |
|
690 |
||
691 |
Returns the low surrogate value of a ucs4 code point. |
|
692 |
The returned result is undefined if \a ucs4 is smaller than 0x10000. |
|
693 |
*/ |
|
694 |
||
695 |
/*! |
|
696 |
Returns the numeric value of the digit, or -1 if the character is |
|
697 |
not a digit. |
|
698 |
*/ |
|
699 |
int QChar::digitValue() const |
|
700 |
{
|
|
701 |
return qGetProp(ucs)->digitValue; |
|
702 |
} |
|
703 |
||
704 |
/*! |
|
705 |
\overload |
|
706 |
Returns the numeric value of the digit, specified by the UCS-2-encoded |
|
707 |
character, \a ucs2, or -1 if the character is not a digit. |
|
708 |
*/ |
|
709 |
int QChar::digitValue(ushort ucs2) |
|
710 |
{
|
|
711 |
return qGetProp(ucs2)->digitValue; |
|
712 |
} |
|
713 |
||
714 |
/*! |
|
715 |
\overload |
|
716 |
Returns the numeric value of the digit specified by the UCS-4-encoded |
|
717 |
character, \a ucs4, or -1 if the character is not a digit. |
|
718 |
*/ |
|
719 |
int QChar::digitValue(uint ucs4) |
|
720 |
{
|
|
721 |
if (ucs4 > LAST_UNICODE_CHAR) |
|
722 |
return 0; |
|
723 |
return qGetProp(ucs4)->digitValue; |
|
724 |
} |
|
725 |
||
726 |
/*! |
|
727 |
Returns the character's category. |
|
728 |
*/ |
|
729 |
QChar::Category QChar::category() const |
|
730 |
{
|
|
731 |
return (QChar::Category) qGetProp(ucs)->category; |
|
732 |
} |
|
733 |
||
734 |
/*! |
|
735 |
\overload |
|
736 |
\since 4.3 |
|
737 |
Returns the category of the UCS-4-encoded character specified by \a ucs4. |
|
738 |
*/ |
|
739 |
QChar::Category QChar::category(uint ucs4) |
|
740 |
{
|
|
741 |
if (ucs4 > LAST_UNICODE_CHAR) |
|
742 |
return QChar::NoCategory; |
|
743 |
return (QChar::Category) qGetProp(ucs4)->category; |
|
744 |
} |
|
745 |
||
746 |
/*! |
|
747 |
\overload |
|
748 |
Returns the category of the UCS-2-encoded character specified by \a ucs2. |
|
749 |
*/ |
|
750 |
QChar::Category QChar::category(ushort ucs2) |
|
751 |
{
|
|
752 |
return (QChar::Category) qGetProp(ucs2)->category; |
|
753 |
} |
|
754 |
||
755 |
||
756 |
/*! |
|
757 |
Returns the character's direction. |
|
758 |
*/ |
|
759 |
QChar::Direction QChar::direction() const |
|
760 |
{
|
|
761 |
return (QChar::Direction) qGetProp(ucs)->direction; |
|
762 |
} |
|
763 |
||
764 |
/*! |
|
765 |
\overload |
|
766 |
Returns the direction of the UCS-4-encoded character specified by \a ucs4. |
|
767 |
*/ |
|
768 |
QChar::Direction QChar::direction(uint ucs4) |
|
769 |
{
|
|
770 |
if (ucs4 > LAST_UNICODE_CHAR) |
|
771 |
return QChar::DirL; |
|
772 |
return (QChar::Direction) qGetProp(ucs4)->direction; |
|
773 |
} |
|
774 |
||
775 |
/*! |
|
776 |
\overload |
|
777 |
Returns the direction of the UCS-2-encoded character specified by \a ucs2. |
|
778 |
*/ |
|
779 |
QChar::Direction QChar::direction(ushort ucs2) |
|
780 |
{
|
|
781 |
return (QChar::Direction) qGetProp(ucs2)->direction; |
|
782 |
} |
|
783 |
||
784 |
/*! |
|
785 |
Returns information about the joining properties of the character |
|
786 |
(needed for certain languages such as Arabic). |
|
787 |
*/ |
|
788 |
QChar::Joining QChar::joining() const |
|
789 |
{
|
|
790 |
return (QChar::Joining) qGetProp(ucs)->joining; |
|
791 |
} |
|
792 |
||
793 |
/*! |
|
794 |
\overload |
|
795 |
Returns information about the joining properties of the UCS-4-encoded |
|
796 |
character specified by \a ucs4 (needed for certain languages such as |
|
797 |
Arabic). |
|
798 |
*/ |
|
799 |
QChar::Joining QChar::joining(uint ucs4) |
|
800 |
{
|
|
801 |
if (ucs4 > LAST_UNICODE_CHAR) |
|
802 |
return QChar::OtherJoining; |
|
803 |
return (QChar::Joining) qGetProp(ucs4)->joining; |
|
804 |
} |
|
805 |
||
806 |
/*! |
|
807 |
\overload |
|
808 |
Returns information about the joining properties of the UCS-2-encoded |
|
809 |
character specified by \a ucs2 (needed for certain languages such as |
|
810 |
Arabic). |
|
811 |
*/ |
|
812 |
QChar::Joining QChar::joining(ushort ucs2) |
|
813 |
{
|
|
814 |
return (QChar::Joining) qGetProp(ucs2)->joining; |
|
815 |
} |
|
816 |
||
817 |
||
818 |
/*! |
|
819 |
Returns true if the character should be reversed if the text |
|
820 |
direction is reversed; otherwise returns false. |
|
821 |
||
822 |
Same as (ch.mirroredChar() != ch). |
|
823 |
||
824 |
\sa mirroredChar() |
|
825 |
*/ |
|
826 |
bool QChar::hasMirrored() const |
|
827 |
{
|
|
828 |
return qGetProp(ucs)->mirrorDiff != 0; |
|
829 |
} |
|
830 |
||
831 |
/*! |
|
832 |
\fn bool QChar::isLower() const |
|
833 |
||
834 |
Returns true if the character is a lowercase letter, i.e. |
|
835 |
category() is Letter_Lowercase. |
|
836 |
||
837 |
\sa isUpper(), toLower(), toUpper() |
|
838 |
*/ |
|
839 |
||
840 |
/*! |
|
841 |
\fn bool QChar::isUpper() const |
|
842 |
||
843 |
Returns true if the character is an uppercase letter, i.e. |
|
844 |
category() is Letter_Uppercase. |
|
845 |
||
846 |
\sa isLower(), toUpper(), toLower() |
|
847 |
*/ |
|
848 |
||
849 |
/*! |
|
850 |
\fn bool QChar::isTitleCase() const |
|
851 |
\since 4.3 |
|
852 |
||
853 |
Returns true if the character is a titlecase letter, i.e. |
|
854 |
category() is Letter_Titlecase. |
|
855 |
||
856 |
\sa isLower(), toUpper(), toLower(), toTitleCase() |
|
857 |
*/ |
|
858 |
||
859 |
/*! |
|
860 |
Returns the mirrored character if this character is a mirrored |
|
861 |
character; otherwise returns the character itself. |
|
862 |
||
863 |
\sa hasMirrored() |
|
864 |
*/ |
|
865 |
QChar QChar::mirroredChar() const |
|
866 |
{
|
|
867 |
return ucs + qGetProp(ucs)->mirrorDiff; |
|
868 |
} |
|
869 |
||
870 |
/*! \overload |
|
871 |
Returns the mirrored character if the UCS-4-encoded character specified |
|
872 |
by \a ucs4 is a mirrored character; otherwise returns the character itself. |
|
873 |
||
874 |
\sa hasMirrored() |
|
875 |
*/ |
|
876 |
uint QChar::mirroredChar(uint ucs4) |
|
877 |
{
|
|
878 |
if (ucs4 > LAST_UNICODE_CHAR) |
|
879 |
return ucs4; |
|
880 |
return ucs4 + qGetProp(ucs4)->mirrorDiff; |
|
881 |
} |
|
882 |
||
883 |
/*! |
|
884 |
\overload |
|
885 |
Returns the mirrored character if the UCS-2-encoded character specified |
|
886 |
by \a ucs2 is a mirrored character; otherwise returns the character itself. |
|
887 |
||
888 |
\sa hasMirrored() |
|
889 |
*/ |
|
890 |
ushort QChar::mirroredChar(ushort ucs2) |
|
891 |
{
|
|
892 |
return ucs2 + qGetProp(ucs2)->mirrorDiff; |
|
893 |
} |
|
894 |
||
895 |
||
896 |
enum {
|
|
897 |
Hangul_SBase = 0xac00, |
|
898 |
Hangul_LBase = 0x1100, |
|
899 |
Hangul_VBase = 0x1161, |
|
900 |
Hangul_TBase = 0x11a7, |
|
901 |
Hangul_SCount = 11172, |
|
902 |
Hangul_LCount = 19, |
|
903 |
Hangul_VCount = 21, |
|
904 |
Hangul_TCount = 28, |
|
905 |
Hangul_NCount = 21*28 |
|
906 |
}; |
|
907 |
||
908 |
// buffer has to have a length of 3. It's needed for Hangul decomposition |
|
909 |
static const unsigned short * QT_FASTCALL decompositionHelper |
|
910 |
(uint ucs4, int *length, int *tag, unsigned short *buffer) |
|
911 |
{
|
|
912 |
*length = 0; |
|
913 |
if (ucs4 > LAST_UNICODE_CHAR) |
|
914 |
return 0; |
|
915 |
if (ucs4 >= Hangul_SBase && ucs4 < Hangul_SBase + Hangul_SCount) {
|
|
916 |
int SIndex = ucs4 - Hangul_SBase; |
|
917 |
buffer[0] = Hangul_LBase + SIndex / Hangul_NCount; // L |
|
918 |
buffer[1] = Hangul_VBase + (SIndex % Hangul_NCount) / Hangul_TCount; // V |
|
919 |
buffer[2] = Hangul_TBase + SIndex % Hangul_TCount; // T |
|
920 |
*length = buffer[2] == Hangul_TBase ? 2 : 3; |
|
921 |
*tag = QChar::Canonical; |
|
922 |
return buffer; |
|
923 |
} |
|
924 |
||
925 |
const unsigned short index = GET_DECOMPOSITION_INDEX(ucs4); |
|
926 |
if (index == 0xffff) |
|
927 |
return 0; |
|
928 |
const unsigned short *decomposition = uc_decomposition_map+index; |
|
929 |
*tag = (*decomposition) & 0xff; |
|
930 |
*length = (*decomposition) >> 8; |
|
931 |
return decomposition+1; |
|
932 |
} |
|
933 |
||
934 |
/*! |
|
935 |
Decomposes a character into its parts. Returns an empty string if |
|
936 |
no decomposition exists. |
|
937 |
*/ |
|
938 |
QString QChar::decomposition() const |
|
939 |
{
|
|
940 |
return decomposition(ucs); |
|
941 |
} |
|
942 |
||
943 |
/*! |
|
944 |
\overload |
|
945 |
Decomposes the UCS-4-encoded character specified by \a ucs4 into its |
|
946 |
constituent parts. Returns an empty string if no decomposition exists. |
|
947 |
*/ |
|
948 |
QString QChar::decomposition(uint ucs4) |
|
949 |
{
|
|
950 |
unsigned short buffer[3]; |
|
951 |
int length; |
|
952 |
int tag; |
|
953 |
const unsigned short *d = decompositionHelper(ucs4, &length, &tag, buffer); |
|
954 |
return QString::fromUtf16(d, length); |
|
955 |
} |
|
956 |
||
957 |
/*! |
|
958 |
Returns the tag defining the composition of the character. Returns |
|
959 |
QChar::Single if no decomposition exists. |
|
960 |
*/ |
|
961 |
QChar::Decomposition QChar::decompositionTag() const |
|
962 |
{
|
|
963 |
return decompositionTag(ucs); |
|
964 |
} |
|
965 |
||
966 |
/*! |
|
967 |
\overload |
|
968 |
Returns the tag defining the composition of the UCS-4-encoded character |
|
969 |
specified by \a ucs4. Returns QChar::Single if no decomposition exists. |
|
970 |
*/ |
|
971 |
QChar::Decomposition QChar::decompositionTag(uint ucs4) |
|
972 |
{
|
|
973 |
if (ucs4 > LAST_UNICODE_CHAR) |
|
974 |
return QChar::NoDecomposition; |
|
975 |
const unsigned short index = GET_DECOMPOSITION_INDEX(ucs4); |
|
976 |
if (index == 0xffff) |
|
977 |
return QChar::NoDecomposition; |
|
978 |
return (QChar::Decomposition)(uc_decomposition_map[index] & 0xff); |
|
979 |
} |
|
980 |
||
981 |
/*! |
|
982 |
Returns the combining class for the character as defined in the |
|
983 |
Unicode standard. This is mainly useful as a positioning hint for |
|
984 |
marks attached to a base character. |
|
985 |
||
986 |
The Qt text rendering engine uses this information to correctly |
|
987 |
position non-spacing marks around a base character. |
|
988 |
*/ |
|
989 |
unsigned char QChar::combiningClass() const |
|
990 |
{
|
|
991 |
return (unsigned char) qGetProp(ucs)->combiningClass; |
|
992 |
} |
|
993 |
||
994 |
/*! \overload |
|
995 |
Returns the combining class for the UCS-4-encoded character specified by |
|
996 |
\a ucs4, as defined in the Unicode standard. |
|
997 |
*/ |
|
998 |
unsigned char QChar::combiningClass(uint ucs4) |
|
999 |
{
|
|
1000 |
if (ucs4 > LAST_UNICODE_CHAR) |
|
1001 |
return 0; |
|
1002 |
return (unsigned char) qGetProp(ucs4)->combiningClass; |
|
1003 |
} |
|
1004 |
||
1005 |
/*! \overload |
|
1006 |
Returns the combining class for the UCS-2-encoded character specified by |
|
1007 |
\a ucs2, as defined in the Unicode standard. |
|
1008 |
*/ |
|
1009 |
unsigned char QChar::combiningClass(ushort ucs2) |
|
1010 |
{
|
|
1011 |
return (unsigned char) qGetProp(ucs2)->combiningClass; |
|
1012 |
} |
|
1013 |
||
1014 |
||
1015 |
/*! |
|
1016 |
Returns the Unicode version that introduced this character. |
|
1017 |
*/ |
|
1018 |
QChar::UnicodeVersion QChar::unicodeVersion() const |
|
1019 |
{
|
|
1020 |
return (QChar::UnicodeVersion) qGetProp(ucs)->unicodeVersion; |
|
1021 |
} |
|
1022 |
||
1023 |
/*! \overload |
|
1024 |
Returns the Unicode version that introduced the character specified in |
|
1025 |
its UCS-4-encoded form as \a ucs4. |
|
1026 |
*/ |
|
1027 |
QChar::UnicodeVersion QChar::unicodeVersion(uint ucs4) |
|
1028 |
{
|
|
1029 |
if (ucs4 > LAST_UNICODE_CHAR) |
|
1030 |
return QChar::Unicode_Unassigned; |
|
1031 |
return (QChar::UnicodeVersion) qGetProp(ucs4)->unicodeVersion; |
|
1032 |
} |
|
1033 |
||
1034 |
/*! \overload |
|
1035 |
Returns the Unicode version that introduced the character specified in |
|
1036 |
its UCS-2-encoded form as \a ucs2. |
|
1037 |
*/ |
|
1038 |
QChar::UnicodeVersion QChar::unicodeVersion(ushort ucs2) |
|
1039 |
{
|
|
1040 |
return (QChar::UnicodeVersion) qGetProp(ucs2)->unicodeVersion; |
|
1041 |
} |
|
1042 |
||
1043 |
||
1044 |
/*! |
|
1045 |
Returns the lowercase equivalent if the character is uppercase or titlecase; |
|
1046 |
otherwise returns the character itself. |
|
1047 |
*/ |
|
1048 |
QChar QChar::toLower() const |
|
1049 |
{
|
|
1050 |
const QUnicodeTables::Properties *p = qGetProp(ucs); |
|
1051 |
if (!p->lowerCaseSpecial) |
|
1052 |
return ucs + p->lowerCaseDiff; |
|
1053 |
return ucs; |
|
1054 |
} |
|
1055 |
||
1056 |
/*! \overload |
|
1057 |
Returns the lowercase equivalent of the UCS-4-encoded character specified |
|
1058 |
by \a ucs4 if the character is uppercase or titlecase; otherwise returns |
|
1059 |
the character itself. |
|
1060 |
*/ |
|
1061 |
uint QChar::toLower(uint ucs4) |
|
1062 |
{
|
|
1063 |
if (ucs4 > LAST_UNICODE_CHAR) |
|
1064 |
return ucs4; |
|
1065 |
const QUnicodeTables::Properties *p = qGetProp(ucs4); |
|
1066 |
if (!p->lowerCaseSpecial) |
|
1067 |
return ucs4 + p->lowerCaseDiff; |
|
1068 |
return ucs4; |
|
1069 |
} |
|
1070 |
||
1071 |
/*! \overload |
|
1072 |
Returns the lowercase equivalent of the UCS-2-encoded character specified |
|
1073 |
by \a ucs2 if the character is uppercase or titlecase; otherwise returns |
|
1074 |
the character itself. |
|
1075 |
*/ |
|
1076 |
ushort QChar::toLower(ushort ucs2) |
|
1077 |
{
|
|
1078 |
const QUnicodeTables::Properties *p = qGetProp(ucs2); |
|
1079 |
if (!p->lowerCaseSpecial) |
|
1080 |
return ucs2 + p->lowerCaseDiff; |
|
1081 |
return ucs2; |
|
1082 |
} |
|
1083 |
||
1084 |
/*! |
|
1085 |
Returns the uppercase equivalent if the character is lowercase or titlecase; |
|
1086 |
otherwise returns the character itself. |
|
1087 |
*/ |
|
1088 |
QChar QChar::toUpper() const |
|
1089 |
{
|
|
1090 |
const QUnicodeTables::Properties *p = qGetProp(ucs); |
|
1091 |
if (!p->upperCaseSpecial) |
|
1092 |
return ucs + p->upperCaseDiff; |
|
1093 |
return ucs; |
|
1094 |
} |
|
1095 |
||
1096 |
/*! \overload |
|
1097 |
Returns the uppercase equivalent of the UCS-4-encoded character specified |
|
1098 |
by \a ucs4 if the character is lowercase or titlecase; otherwise returns |
|
1099 |
the character itself. |
|
1100 |
*/ |
|
1101 |
uint QChar::toUpper(uint ucs4) |
|
1102 |
{
|
|
1103 |
if (ucs4 > LAST_UNICODE_CHAR) |
|
1104 |
return ucs4; |
|
1105 |
const QUnicodeTables::Properties *p = qGetProp(ucs4); |
|
1106 |
if (!p->upperCaseSpecial) |
|
1107 |
return ucs4 + p->upperCaseDiff; |
|
1108 |
return ucs4; |
|
1109 |
} |
|
1110 |
||
1111 |
/*! \overload |
|
1112 |
Returns the uppercase equivalent of the UCS-2-encoded character specified |
|
1113 |
by \a ucs2 if the character is lowercase or titlecase; otherwise returns |
|
1114 |
the character itself. |
|
1115 |
*/ |
|
1116 |
ushort QChar::toUpper(ushort ucs2) |
|
1117 |
{
|
|
1118 |
const QUnicodeTables::Properties *p = qGetProp(ucs2); |
|
1119 |
if (!p->upperCaseSpecial) |
|
1120 |
return ucs2 + p->upperCaseDiff; |
|
1121 |
return ucs2; |
|
1122 |
} |
|
1123 |
||
1124 |
/*! |
|
1125 |
Returns the title case equivalent if the character is lowercase or uppercase; |
|
1126 |
otherwise returns the character itself. |
|
1127 |
*/ |
|
1128 |
QChar QChar::toTitleCase() const |
|
1129 |
{
|
|
1130 |
const QUnicodeTables::Properties *p = qGetProp(ucs); |
|
1131 |
if (!p->titleCaseSpecial) |
|
1132 |
return ucs + p->titleCaseDiff; |
|
1133 |
return ucs; |
|
1134 |
} |
|
1135 |
||
1136 |
/*! |
|
1137 |
\overload |
|
1138 |
Returns the title case equivalent of the UCS-4-encoded character specified |
|
1139 |
by \a ucs4 if the character is lowercase or uppercase; otherwise returns |
|
1140 |
the character itself. |
|
1141 |
*/ |
|
1142 |
uint QChar::toTitleCase(uint ucs4) |
|
1143 |
{
|
|
1144 |
if (ucs4 > LAST_UNICODE_CHAR) |
|
1145 |
return ucs4; |
|
1146 |
const QUnicodeTables::Properties *p = qGetProp(ucs4); |
|
1147 |
if (!p->titleCaseSpecial) |
|
1148 |
return ucs4 + p->titleCaseDiff; |
|
1149 |
return ucs4; |
|
1150 |
} |
|
1151 |
||
1152 |
/*! |
|
1153 |
\overload |
|
1154 |
Returns the title case equivalent of the UCS-2-encoded character specified |
|
1155 |
by \a ucs2 if the character is lowercase or uppercase; otherwise returns |
|
1156 |
the character itself. |
|
1157 |
*/ |
|
1158 |
ushort QChar::toTitleCase(ushort ucs2) |
|
1159 |
{
|
|
1160 |
const QUnicodeTables::Properties *p = qGetProp(ucs2); |
|
1161 |
if (!p->titleCaseSpecial) |
|
1162 |
return ucs2 + p->titleCaseDiff; |
|
1163 |
return ucs2; |
|
1164 |
} |
|
1165 |
||
1166 |
||
1167 |
static inline uint foldCase(const ushort *ch, const ushort *start) |
|
1168 |
{
|
|
1169 |
uint c = *ch; |
|
1170 |
if (QChar(c).isLowSurrogate() && ch > start && QChar(*(ch - 1)).isHighSurrogate()) |
|
1171 |
c = QChar::surrogateToUcs4(*(ch - 1), c); |
|
1172 |
return *ch + qGetProp(c)->caseFoldDiff; |
|
1173 |
} |
|
1174 |
||
1175 |
static inline uint foldCase(uint ch, uint &last) |
|
1176 |
{
|
|
1177 |
uint c = ch; |
|
1178 |
if (QChar(c).isLowSurrogate() && QChar(last).isHighSurrogate()) |
|
1179 |
c = QChar::surrogateToUcs4(last, c); |
|
1180 |
last = ch; |
|
1181 |
return ch + qGetProp(c)->caseFoldDiff; |
|
1182 |
} |
|
1183 |
||
1184 |
static inline ushort foldCase(ushort ch) |
|
1185 |
{
|
|
1186 |
return ch + qGetProp(ch)->caseFoldDiff; |
|
1187 |
} |
|
1188 |
||
1189 |
/*! |
|
1190 |
Returns the case folded equivalent of the character. For most Unicode characters this |
|
1191 |
is the same as toLowerCase(). |
|
1192 |
*/ |
|
1193 |
QChar QChar::toCaseFolded() const |
|
1194 |
{
|
|
1195 |
return ucs + qGetProp(ucs)->caseFoldDiff; |
|
1196 |
} |
|
1197 |
||
1198 |
/*! |
|
1199 |
\overload |
|
1200 |
Returns the case folded equivalent of the UCS-4-encoded character specified |
|
1201 |
by \a ucs4. For most Unicode characters this is the same as toLowerCase(). |
|
1202 |
*/ |
|
1203 |
uint QChar::toCaseFolded(uint ucs4) |
|
1204 |
{
|
|
1205 |
if (ucs4 > LAST_UNICODE_CHAR) |
|
1206 |
return ucs4; |
|
1207 |
return ucs4 + qGetProp(ucs4)->caseFoldDiff; |
|
1208 |
} |
|
1209 |
||
1210 |
/*! |
|
1211 |
\overload |
|
1212 |
Returns the case folded equivalent of the UCS-2-encoded character specified |
|
1213 |
by \a ucs2. For most Unicode characters this is the same as toLowerCase(). |
|
1214 |
*/ |
|
1215 |
ushort QChar::toCaseFolded(ushort ucs2) |
|
1216 |
{
|
|
1217 |
return ucs2 + qGetProp(ucs2)->caseFoldDiff; |
|
1218 |
} |
|
1219 |
||
1220 |
||
1221 |
/*! |
|
1222 |
\fn char QChar::latin1() const |
|
1223 |
||
1224 |
Use toLatin1() instead. |
|
1225 |
*/ |
|
1226 |
||
1227 |
/*! |
|
1228 |
\fn char QChar::ascii() const |
|
1229 |
||
1230 |
Use toAscii() instead. |
|
1231 |
*/ |
|
1232 |
||
1233 |
/*! |
|
1234 |
\fn char QChar::toLatin1() const |
|
1235 |
||
1236 |
Returns the Latin-1 character equivalent to the QChar, or 0. This |
|
1237 |
is mainly useful for non-internationalized software. |
|
1238 |
||
1239 |
\sa toAscii(), unicode(), QTextCodec::codecForCStrings() |
|
1240 |
*/ |
|
1241 |
||
1242 |
/*! |
|
1243 |
\fn char QChar::toAscii() const |
|
1244 |
Returns the character value of the QChar obtained using the current |
|
1245 |
codec used to read C strings, or 0 if the character is not representable |
|
1246 |
using this codec. The default codec handles Latin-1 encoded text, |
|
1247 |
but this can be changed to assist developers writing source code using |
|
1248 |
other encodings. |
|
1249 |
||
1250 |
The main purpose of this function is to preserve ASCII characters used |
|
1251 |
in C strings. This is mainly useful for developers of non-internationalized |
|
1252 |
software. |
|
1253 |
||
1254 |
\sa toLatin1(), unicode(), QTextCodec::codecForCStrings() |
|
1255 |
*/ |
|
1256 |
#ifdef Q_COMPILER_MANGLES_RETURN_TYPE |
|
1257 |
const char QChar::toAscii() const |
|
1258 |
#else |
|
1259 |
char QChar::toAscii() const |
|
1260 |
#endif |
|
1261 |
{
|
|
1262 |
#ifndef QT_NO_CODEC_FOR_C_STRINGS |
|
1263 |
if (QTextCodec::codecForCStrings()) |
|
1264 |
// ##### |
|
1265 |
return QTextCodec::codecForCStrings()->fromUnicode(QString(*this)).at(0); |
|
1266 |
#endif |
|
1267 |
return ucs > 0xff ? 0 : char(ucs); |
|
1268 |
} |
|
1269 |
||
1270 |
/*! |
|
1271 |
\fn QChar QChar::fromLatin1(char c) |
|
1272 |
||
1273 |
Converts the Latin-1 character \a c to its equivalent QChar. This |
|
1274 |
is mainly useful for non-internationalized software. |
|
1275 |
||
1276 |
\sa fromAscii(), unicode(), QTextCodec::codecForCStrings() |
|
1277 |
*/ |
|
1278 |
||
1279 |
/*! |
|
1280 |
Converts the ASCII character \a c to its equivalent QChar. This |
|
1281 |
is mainly useful for non-internationalized software. |
|
1282 |
||
1283 |
An alternative is to use QLatin1Char. |
|
1284 |
||
1285 |
\sa fromLatin1(), unicode(), QTextCodec::codecForCStrings() |
|
1286 |
*/ |
|
1287 |
QChar QChar::fromAscii(char c) |
|
1288 |
{
|
|
1289 |
#ifndef QT_NO_CODEC_FOR_C_STRINGS |
|
1290 |
if (QTextCodec::codecForCStrings()) |
|
1291 |
// ##### |
|
1292 |
return QTextCodec::codecForCStrings()->toUnicode(&c, 1).at(0).unicode(); |
|
1293 |
#endif |
|
1294 |
return QChar(ushort((uchar)c)); |
|
1295 |
} |
|
1296 |
||
1297 |
#ifndef QT_NO_DATASTREAM |
|
1298 |
/*! |
|
1299 |
\relates QChar |
|
1300 |
||
1301 |
Writes the char \a chr to the stream \a out. |
|
1302 |
||
1303 |
\sa {Format of the QDataStream operators}
|
|
1304 |
*/ |
|
1305 |
||
1306 |
QDataStream &operator<<(QDataStream &out, const QChar &chr) |
|
1307 |
{
|
|
1308 |
out << quint16(chr.unicode()); |
|
1309 |
return out; |
|
1310 |
} |
|
1311 |
||
1312 |
||
1313 |
/*! |
|
1314 |
\relates QChar |
|
1315 |
||
1316 |
Reads a char from the stream \a in into char \a chr. |
|
1317 |
||
1318 |
\sa {Format of the QDataStream operators}
|
|
1319 |
*/ |
|
1320 |
||
1321 |
QDataStream &operator>>(QDataStream &in, QChar &chr) |
|
1322 |
{
|
|
1323 |
quint16 u; |
|
1324 |
in >> u; |
|
1325 |
chr.unicode() = ushort(u); |
|
1326 |
return in; |
|
1327 |
} |
|
1328 |
#endif // QT_NO_DATASTREAM |
|
1329 |
||
1330 |
/*! |
|
1331 |
\fn ushort & QChar::unicode() |
|
1332 |
||
1333 |
Returns a reference to the numeric Unicode value of the QChar. |
|
1334 |
*/ |
|
1335 |
||
1336 |
/*! |
|
1337 |
\fn ushort QChar::unicode() const |
|
1338 |
||
1339 |
\overload |
|
1340 |
*/ |
|
1341 |
||
1342 |
/***************************************************************************** |
|
1343 |
Documentation of QChar related functions |
|
1344 |
*****************************************************************************/ |
|
1345 |
||
1346 |
/*! |
|
1347 |
\fn bool operator==(QChar c1, QChar c2) |
|
1348 |
||
1349 |
\relates QChar |
|
1350 |
||
1351 |
Returns true if \a c1 and \a c2 are the same Unicode character; |
|
1352 |
otherwise returns false. |
|
1353 |
*/ |
|
1354 |
||
1355 |
/*! |
|
1356 |
\fn int operator!=(QChar c1, QChar c2) |
|
1357 |
||
1358 |
\relates QChar |
|
1359 |
||
1360 |
Returns true if \a c1 and \a c2 are not the same Unicode |
|
1361 |
character; otherwise returns false. |
|
1362 |
*/ |
|
1363 |
||
1364 |
/*! |
|
1365 |
\fn int operator<=(QChar c1, QChar c2) |
|
1366 |
||
1367 |
\relates QChar |
|
1368 |
||
1369 |
Returns true if the numeric Unicode value of \a c1 is less than |
|
1370 |
or equal to that of \a c2; otherwise returns false. |
|
1371 |
*/ |
|
1372 |
||
1373 |
/*! |
|
1374 |
\fn int operator>=(QChar c1, QChar c2) |
|
1375 |
||
1376 |
\relates QChar |
|
1377 |
||
1378 |
Returns true if the numeric Unicode value of \a c1 is greater than |
|
1379 |
or equal to that of \a c2; otherwise returns false. |
|
1380 |
*/ |
|
1381 |
||
1382 |
/*! |
|
1383 |
\fn int operator<(QChar c1, QChar c2) |
|
1384 |
||
1385 |
\relates QChar |
|
1386 |
||
1387 |
Returns true if the numeric Unicode value of \a c1 is less than |
|
1388 |
that of \a c2; otherwise returns false. |
|
1389 |
*/ |
|
1390 |
||
1391 |
/*! |
|
1392 |
\fn int operator>(QChar c1, QChar c2) |
|
1393 |
||
1394 |
\relates QChar |
|
1395 |
||
1396 |
Returns true if the numeric Unicode value of \a c1 is greater than |
|
1397 |
that of \a c2; otherwise returns false. |
|
1398 |
*/ |
|
1399 |
||
1400 |
/*! |
|
1401 |
\fn bool QChar::mirrored() const |
|
1402 |
||
1403 |
Use hasMirrored() instead. |
|
1404 |
*/ |
|
1405 |
||
1406 |
/*! |
|
1407 |
\fn QChar QChar::lower() const |
|
1408 |
||
1409 |
Use toLower() instead. |
|
1410 |
*/ |
|
1411 |
||
1412 |
/*! |
|
1413 |
\fn QChar QChar::upper() const |
|
1414 |
||
1415 |
Use toUpper() instead. |
|
1416 |
*/ |
|
1417 |
||
1418 |
/*! |
|
1419 |
\fn bool QChar::networkOrdered() |
|
1420 |
||
1421 |
See if QSysInfo::ByteOrder == QSysInfo::BigEndian instead. |
|
1422 |
*/ |
|
1423 |
||
1424 |
||
1425 |
// --------------------------------------------------------------------------- |
|
1426 |
||
1427 |
||
1428 |
static void decomposeHelper(QString *str, bool canonical, QChar::UnicodeVersion version, int from) |
|
1429 |
{
|
|
1430 |
unsigned short buffer[3]; |
|
1431 |
||
1432 |
QString &s = *str; |
|
1433 |
||
1434 |
const unsigned short *utf16 = reinterpret_cast<unsigned short *>(s.data()); |
|
1435 |
const unsigned short *uc = utf16 + s.length(); |
|
1436 |
while (uc != utf16 + from) {
|
|
1437 |
uint ucs4 = *(--uc); |
|
1438 |
if (QChar(ucs4).isLowSurrogate() && uc != utf16) {
|
|
1439 |
ushort high = *(uc - 1); |
|
1440 |
if (QChar(high).isHighSurrogate()) {
|
|
1441 |
--uc; |
|
1442 |
ucs4 = QChar::surrogateToUcs4(high, ucs4); |
|
1443 |
} |
|
1444 |
} |
|
1445 |
if (QChar::unicodeVersion(ucs4) > version) |
|
1446 |
continue; |
|
1447 |
int length; |
|
1448 |
int tag; |
|
1449 |
const unsigned short *d = decompositionHelper(ucs4, &length, &tag, buffer); |
|
1450 |
if (!d || (canonical && tag != QChar::Canonical)) |
|
1451 |
continue; |
|
1452 |
||
1453 |
s.replace(uc - utf16, ucs4 > 0x10000 ? 2 : 1, (const QChar *)d, length); |
|
1454 |
// since the insert invalidates the pointers and we do decomposition recursive |
|
1455 |
int pos = uc - utf16; |
|
1456 |
utf16 = reinterpret_cast<unsigned short *>(s.data()); |
|
1457 |
uc = utf16 + pos + length; |
|
1458 |
} |
|
1459 |
} |
|
1460 |
||
1461 |
||
1462 |
static ushort ligatureHelper(ushort u1, ushort u2) |
|
1463 |
{
|
|
1464 |
// hangul L-V pair |
|
1465 |
int LIndex = u1 - Hangul_LBase; |
|
1466 |
if (0 <= LIndex && LIndex < Hangul_LCount) {
|
|
1467 |
int VIndex = u2 - Hangul_VBase; |
|
1468 |
if (0 <= VIndex && VIndex < Hangul_VCount) |
|
1469 |
return Hangul_SBase + (LIndex * Hangul_VCount + VIndex) * Hangul_TCount; |
|
1470 |
} |
|
1471 |
||
1472 |
// hangul LV-T pair |
|
1473 |
int SIndex = u1 - Hangul_SBase; |
|
1474 |
if (0 <= SIndex && SIndex < Hangul_SCount && (SIndex % Hangul_TCount) == 0) {
|
|
1475 |
int TIndex = u2 - Hangul_TBase; |
|
1476 |
if (0 <= TIndex && TIndex <= Hangul_TCount) |
|
1477 |
return u1 + TIndex; |
|
1478 |
} |
|
1479 |
||
1480 |
const unsigned short index = GET_LIGATURE_INDEX(u2); |
|
1481 |
if (index == 0xffff) |
|
1482 |
return 0; |
|
1483 |
const unsigned short *ligatures = uc_ligature_map+index; |
|
1484 |
ushort length = *ligatures; |
|
1485 |
++ligatures; |
|
1486 |
// ### use bsearch |
|
1487 |
for (uint i = 0; i < length; ++i) |
|
1488 |
if (ligatures[2*i] == u1) |
|
1489 |
return ligatures[2*i+1]; |
|
1490 |
return 0; |
|
1491 |
} |
|
1492 |
||
1493 |
static void composeHelper(QString *str, int from) |
|
1494 |
{
|
|
1495 |
QString &s = *str; |
|
1496 |
||
1497 |
if (s.length() - from < 2) |
|
1498 |
return; |
|
1499 |
||
1500 |
// the loop can partly ignore high Unicode as all ligatures are in the BMP |
|
1501 |
int starter = 0; |
|
1502 |
int lastCombining = 0; |
|
1503 |
int pos = from; |
|
1504 |
while (pos < s.length()) {
|
|
1505 |
uint uc = s.at(pos).unicode(); |
|
1506 |
if (QChar(uc).isHighSurrogate() && pos < s.length()-1) {
|
|
1507 |
ushort low = s.at(pos+1).unicode(); |
|
1508 |
if (QChar(low).isLowSurrogate()) {
|
|
1509 |
uc = QChar::surrogateToUcs4(uc, low); |
|
1510 |
++pos; |
|
1511 |
} |
|
1512 |
} |
|
1513 |
int combining = QChar::combiningClass(uc); |
|
1514 |
if (starter == pos - 1 || combining > lastCombining) {
|
|
1515 |
// allowed to form ligature with S |
|
1516 |
QChar ligature = ligatureHelper(s.at(starter).unicode(), uc); |
|
1517 |
if (ligature.unicode()) {
|
|
1518 |
s[starter] = ligature; |
|
1519 |
s.remove(pos, 1); |
|
1520 |
continue; |
|
1521 |
} |
|
1522 |
} |
|
1523 |
if (!combining) |
|
1524 |
starter = pos; |
|
1525 |
lastCombining = combining; |
|
1526 |
++pos; |
|
1527 |
} |
|
1528 |
} |
|
1529 |
||
1530 |
||
1531 |
static void canonicalOrderHelper(QString *str, QChar::UnicodeVersion version, int from) |
|
1532 |
{
|
|
1533 |
QString &s = *str; |
|
1534 |
const int l = s.length()-1; |
|
1535 |
int pos = from; |
|
1536 |
while (pos < l) {
|
|
1537 |
int p2 = pos+1; |
|
1538 |
uint u1 = s.at(pos).unicode(); |
|
1539 |
if (QChar(u1).isHighSurrogate()) {
|
|
1540 |
ushort low = s.at(pos+1).unicode(); |
|
1541 |
if (QChar(low).isLowSurrogate()) {
|
|
1542 |
p2++; |
|
1543 |
u1 = QChar::surrogateToUcs4(u1, low); |
|
1544 |
if (p2 >= l) |
|
1545 |
break; |
|
1546 |
} |
|
1547 |
} |
|
1548 |
uint u2 = s.at(p2).unicode(); |
|
1549 |
if (QChar(u2).isHighSurrogate() && p2 < l-1) {
|
|
1550 |
ushort low = s.at(p2+1).unicode(); |
|
1551 |
if (QChar(low).isLowSurrogate()) {
|
|
1552 |
p2++; |
|
1553 |
u2 = QChar::surrogateToUcs4(u2, low); |
|
1554 |
} |
|
1555 |
} |
|
1556 |
||
1557 |
int c2 = QChar::combiningClass(u2); |
|
1558 |
if (QChar::unicodeVersion(u2) > version) |
|
1559 |
c2 = 0; |
|
1560 |
||
1561 |
if (c2 == 0) {
|
|
1562 |
pos = p2+1; |
|
1563 |
continue; |
|
1564 |
} |
|
1565 |
int c1 = QChar::combiningClass(u1); |
|
1566 |
if (QChar::unicodeVersion(u1) > version) |
|
1567 |
c1 = 0; |
|
1568 |
||
1569 |
if (c1 > c2) {
|
|
1570 |
QChar *uc = s.data(); |
|
1571 |
int p = pos; |
|
1572 |
// exchange characters |
|
1573 |
if (u2 < 0x10000) {
|
|
1574 |
uc[p++] = u2; |
|
1575 |
} else {
|
|
1576 |
uc[p++] = QChar::highSurrogate(u2); |
|
1577 |
uc[p++] = QChar::lowSurrogate(u2); |
|
1578 |
} |
|
1579 |
if (u1 < 0x10000) {
|
|
1580 |
uc[p++] = u1; |
|
1581 |
} else {
|
|
1582 |
uc[p++] = QChar::highSurrogate(u1); |
|
1583 |
uc[p++] = QChar::lowSurrogate(u1); |
|
1584 |
} |
|
1585 |
if (pos > 0) |
|
1586 |
--pos; |
|
1587 |
if (pos > 0 && s.at(pos).isLowSurrogate()) |
|
1588 |
--pos; |
|
1589 |
} else {
|
|
1590 |
++pos; |
|
1591 |
if (u1 > 0x10000) |
|
1592 |
++pos; |
|
1593 |
} |
|
1594 |
} |
|
1595 |
} |
|
1596 |
||
1597 |
int QT_FASTCALL QUnicodeTables::script(unsigned int uc) |
|
1598 |
{
|
|
1599 |
if (uc > 0xffff) |
|
1600 |
return Common; |
|
1601 |
int script = uc_scripts[uc >> 7]; |
|
1602 |
if (script < ScriptSentinel) |
|
1603 |
return script; |
|
1604 |
script = (((script - ScriptSentinel) * UnicodeBlockSize) + UnicodeBlockCount); |
|
1605 |
script = uc_scripts[script + (uc & 0x7f)]; |
|
1606 |
return script; |
|
1607 |
} |
|
1608 |
||
1609 |
||
1610 |
Q_CORE_EXPORT QUnicodeTables::LineBreakClass QT_FASTCALL QUnicodeTables::lineBreakClass(uint ucs4) |
|
1611 |
{
|
|
1612 |
return (QUnicodeTables::LineBreakClass) qGetProp(ucs4)->line_break_class; |
|
1613 |
} |
|
1614 |
||
1615 |
||
1616 |
QT_END_NAMESPACE |