/usr/include/SFML/System/Unicode.inl is in libsfml-dev 1.6+dfsg1-2ubuntu2.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 | ////////////////////////////////////////////////////////////
//
// SFML - Simple and Fast Multimedia Library
// Copyright (C) 2007-2009 Laurent Gomila (laurent.gom@gmail.com)
//
// This software is provided 'as-is', without any express or implied warranty.
// In no event will the authors be held liable for any damages arising from the use of this software.
//
// Permission is granted to anyone to use this software for any purpose,
// including commercial applications, and to alter it and redistribute it freely,
// subject to the following restrictions:
//
// 1. The origin of this software must not be misrepresented;
// you must not claim that you wrote the original software.
// If you use this software in a product, an acknowledgment
// in the product documentation would be appreciated but is not required.
//
// 2. Altered source versions must be plainly marked as such,
// and must not be misrepresented as being the original software.
//
// 3. This notice may not be removed or altered from any source distribution.
//
////////////////////////////////////////////////////////////
////////////////////////////////////////////////////////////
/// Generic function to convert an UTF-32 characters range
/// to an ANSI characters range, using the given locale
////////////////////////////////////////////////////////////
template <typename In, typename Out>
inline Out Unicode::UTF32ToANSI(In Begin, In End, Out Output, char Replacement, const std::locale& Locale)
{
#ifdef __MINGW32__
// MinGW has a almost no support for unicode stuff
// As a consequence, the MinGW version of this function can only use the default locale
// and ignores the one passed as parameter
while (Begin < End)
{
char Char = 0;
if (wctomb(&Char, static_cast<wchar_t>(*Begin++)) >= 0)
*Output++ = Char;
else if (Replacement)
*Output++ = Replacement;
}
#else
// Get the facet of the locale which deals with character conversion
const std::ctype<wchar_t>& Facet = std::use_facet< std::ctype<wchar_t> >(Locale);
// Use the facet to convert each character of the input string
while (Begin < End)
*Output++ = Facet.narrow(static_cast<wchar_t>(*Begin++), Replacement);
#endif
return Output;
}
////////////////////////////////////////////////////////////
/// Generic function to convert an ANSI characters range
/// to an UTF-32 characters range, using the given locale
////////////////////////////////////////////////////////////
template <typename In, typename Out>
inline Out Unicode::ANSIToUTF32(In Begin, In End, Out Output, const std::locale& Locale)
{
#ifdef __MINGW32__
// MinGW has a almost no support for unicode stuff
// As a consequence, the MinGW version of this function can only use the default locale
// and ignores the one passed as parameter
while (Begin < End)
{
wchar_t Char = 0;
mbtowc(&Char, &*Begin, 1);
Begin++;
*Output++ = static_cast<Uint32>(Char);
}
#else
// Get the facet of the locale which deals with character conversion
const std::ctype<wchar_t>& Facet = std::use_facet< std::ctype<wchar_t> >(Locale);
// Use the facet to convert each character of the input string
while (Begin < End)
*Output++ = static_cast<Uint32>(Facet.widen(*Begin++));
#endif
return Output;
}
////////////////////////////////////////////////////////////
/// Generic function to convert an UTF-8 characters range
/// to an UTF-16 characters range, using the given locale
////////////////////////////////////////////////////////////
template <typename In, typename Out>
inline Out Unicode::UTF8ToUTF16(In Begin, In End, Out Output, Uint16 Replacement)
{
while (Begin < End)
{
Uint32 c = 0;
int TrailingBytes = UTF8TrailingBytes[static_cast<int>(*Begin)];
if (Begin + TrailingBytes < End)
{
// First decode the UTF-8 character
switch (TrailingBytes)
{
case 5 : c += *Begin++; c <<= 6;
case 4 : c += *Begin++; c <<= 6;
case 3 : c += *Begin++; c <<= 6;
case 2 : c += *Begin++; c <<= 6;
case 1 : c += *Begin++; c <<= 6;
case 0 : c += *Begin++;
}
c -= UTF8Offsets[TrailingBytes];
// Then encode it in UTF-16
if (c < 0xFFFF)
{
// Character can be converted directly to 16 bits, just need to check it's in the valid range
if ((c >= 0xD800) && (c <= 0xDFFF))
{
// Invalid character (this range is reserved)
if (Replacement)
*Output++ = Replacement;
}
else
{
// Valid character directly convertible to 16 bits
*Output++ = static_cast<Uint16>(c);
}
}
else if (c > 0x0010FFFF)
{
// Invalid character (greater than the maximum unicode value)
if (Replacement)
*Output++ = Replacement;
}
else
{
// Character will be converted to 2 UTF-16 elements
c -= 0x0010000;
*Output++ = static_cast<Uint16>((c >> 10) + 0xD800);
*Output++ = static_cast<Uint16>((c & 0x3FFUL) + 0xDC00);
}
}
}
return Output;
}
////////////////////////////////////////////////////////////
/// Generic function to convert an UTF-8 characters range
/// to an UTF-32 characters range, using the given locale
////////////////////////////////////////////////////////////
template <typename In, typename Out>
inline Out Unicode::UTF8ToUTF32(In Begin, In End, Out Output, Uint32 Replacement)
{
while (Begin < End)
{
Uint32 c = 0;
int TrailingBytes = UTF8TrailingBytes[static_cast<int>(*Begin)];
if (Begin + TrailingBytes < End)
{
// First decode the UTF-8 character
switch (TrailingBytes)
{
case 5 : c += *Begin++; c <<= 6;
case 4 : c += *Begin++; c <<= 6;
case 3 : c += *Begin++; c <<= 6;
case 2 : c += *Begin++; c <<= 6;
case 1 : c += *Begin++; c <<= 6;
case 0 : c += *Begin++;
}
c -= UTF8Offsets[TrailingBytes];
// Then write it if valid
if ((c < 0xD800) || (c > 0xDFFF))
{
// Valid UTF-32 character
*Output++ = c;
}
else
{
// Invalid UTF-32 character
if (Replacement)
*Output++ = Replacement;
}
}
}
return Output;
}
////////////////////////////////////////////////////////////
/// Generic function to convert an UTF-16 characters range
/// to an UTF-8 characters range, using the given locale
////////////////////////////////////////////////////////////
template <typename In, typename Out>
inline Out Unicode::UTF16ToUTF8(In Begin, In End, Out Output, Uint8 Replacement)
{
while (Begin < End)
{
Uint32 c = *Begin++;
// If it's a surrogate pair, first convert to a single UTF-32 character
if ((c >= 0xD800) && (c <= 0xDBFF))
{
if (Begin < End)
{
// The second element is valid : convert the two elements to a UTF-32 character
Uint32 d = *Begin++;
if ((d >= 0xDC00) && (d <= 0xDFFF))
c = static_cast<Uint32>(((c - 0xD800) << 10) + (d - 0xDC00) + 0x0010000);
}
else
{
// Invalid second element
if (Replacement)
*Output++ = Replacement;
}
}
// Then convert to UTF-8
if (c > 0x0010FFFF)
{
// Invalid character (greater than the maximum unicode value)
if (Replacement)
*Output++ = Replacement;
}
else
{
// Valid character
// Get number of bytes to write
int BytesToWrite = 1;
if (c < 0x80) BytesToWrite = 1;
else if (c < 0x800) BytesToWrite = 2;
else if (c < 0x10000) BytesToWrite = 3;
else if (c <= 0x0010FFFF) BytesToWrite = 4;
// Extract bytes to write
Uint8 Bytes[4];
switch (BytesToWrite)
{
case 4 : Bytes[3] = static_cast<Uint8>((c | 0x80) & 0xBF); c >>= 6;
case 3 : Bytes[2] = static_cast<Uint8>((c | 0x80) & 0xBF); c >>= 6;
case 2 : Bytes[1] = static_cast<Uint8>((c | 0x80) & 0xBF); c >>= 6;
case 1 : Bytes[0] = static_cast<Uint8> (c | UTF8FirstBytes[BytesToWrite]);
}
// Add them to the output
const Uint8* CurByte = Bytes;
switch (BytesToWrite)
{
case 4 : *Output++ = *CurByte++;
case 3 : *Output++ = *CurByte++;
case 2 : *Output++ = *CurByte++;
case 1 : *Output++ = *CurByte++;
}
}
}
return Output;
}
////////////////////////////////////////////////////////////
/// Generic function to convert an UTF-16 characters range
/// to an UTF-32 characters range, using the given locale
////////////////////////////////////////////////////////////
template <typename In, typename Out>
inline Out Unicode::UTF16ToUTF32(In Begin, In End, Out Output, Uint32 Replacement)
{
while (Begin < End)
{
Uint16 c = *Begin++;
if ((c >= 0xD800) && (c <= 0xDBFF))
{
// We have a surrogate pair, ie. a character composed of two elements
if (Begin < End)
{
Uint16 d = *Begin++;
if ((d >= 0xDC00) && (d <= 0xDFFF))
{
// The second element is valid : convert the two elements to a UTF-32 character
*Output++ = static_cast<Uint32>(((c - 0xD800) << 10) + (d - 0xDC00) + 0x0010000);
}
else
{
// Invalid second element
if (Replacement)
*Output++ = Replacement;
}
}
}
else if ((c >= 0xDC00) && (c <= 0xDFFF))
{
// Invalid character
if (Replacement)
*Output++ = Replacement;
}
else
{
// Valid character directly convertible to UTF-32
*Output++ = static_cast<Uint32>(c);
}
}
return Output;
}
////////////////////////////////////////////////////////////
/// Generic function to convert an UTF-32 characters range
/// to an UTF-8 characters range, using the given locale
////////////////////////////////////////////////////////////
template <typename In, typename Out>
inline Out Unicode::UTF32ToUTF8(In Begin, In End, Out Output, Uint8 Replacement)
{
while (Begin < End)
{
Uint32 c = *Begin++;
if (c > 0x0010FFFF)
{
// Invalid character (greater than the maximum unicode value)
if (Replacement)
*Output++ = Replacement;
}
else
{
// Valid character
// Get number of bytes to write
int BytesToWrite = 1;
if (c < 0x80) BytesToWrite = 1;
else if (c < 0x800) BytesToWrite = 2;
else if (c < 0x10000) BytesToWrite = 3;
else if (c <= 0x0010FFFF) BytesToWrite = 4;
// Extract bytes to write
Uint8 Bytes[4];
switch (BytesToWrite)
{
case 4 : Bytes[3] = static_cast<Uint8>((c | 0x80) & 0xBF); c >>= 6;
case 3 : Bytes[2] = static_cast<Uint8>((c | 0x80) & 0xBF); c >>= 6;
case 2 : Bytes[1] = static_cast<Uint8>((c | 0x80) & 0xBF); c >>= 6;
case 1 : Bytes[0] = static_cast<Uint8> (c | UTF8FirstBytes[BytesToWrite]);
}
// Add them to the output
const Uint8* CurByte = Bytes;
switch (BytesToWrite)
{
case 4 : *Output++ = *CurByte++;
case 3 : *Output++ = *CurByte++;
case 2 : *Output++ = *CurByte++;
case 1 : *Output++ = *CurByte++;
}
}
}
return Output;
}
////////////////////////////////////////////////////////////
/// Generic function to convert an UTF-32 characters range
/// to an UTF-16 characters range, using the given locale
////////////////////////////////////////////////////////////
template <typename In, typename Out>
inline Out Unicode::UTF32ToUTF16(In Begin, In End, Out Output, Uint16 Replacement)
{
while (Begin < End)
{
Uint32 c = *Begin++;
if (c < 0xFFFF)
{
// Character can be converted directly to 16 bits, just need to check it's in the valid range
if ((c >= 0xD800) && (c <= 0xDFFF))
{
// Invalid character (this range is reserved)
if (Replacement)
*Output++ = Replacement;
}
else
{
// Valid character directly convertible to 16 bits
*Output++ = static_cast<Uint16>(c);
}
}
else if (c > 0x0010FFFF)
{
// Invalid character (greater than the maximum unicode value)
if (Replacement)
*Output++ = Replacement;
}
else
{
// Character will be converted to 2 UTF-16 elements
c -= 0x0010000;
*Output++ = static_cast<Uint16>((c >> 10) + 0xD800);
*Output++ = static_cast<Uint16>((c & 0x3FFUL) + 0xDC00);
}
}
return Output;
}
////////////////////////////////////////////////////////////
/// Get the number of characters composing an UTF-8 string
////////////////////////////////////////////////////////////
template <typename In>
inline std::size_t Unicode::GetUTF8Length(In Begin, In End)
{
std::size_t Length = 0;
while (Begin < End)
{
int NbBytes = UTF8TrailingBytes[static_cast<int>(*Begin)];
if (Begin + NbBytes < End)
++Length;
Begin += NbBytes + 1;
}
return Length;
}
////////////////////////////////////////////////////////////
/// Get the number of characters composing an UTF-16 string
////////////////////////////////////////////////////////////
template <typename In>
inline std::size_t Unicode::GetUTF16Length(In Begin, In End)
{
std::size_t Length = 0;
while (Begin < End)
{
if ((*Begin >= 0xD800) && (*Begin <= 0xDBFF))
{
++Begin;
if ((Begin < End) && ((*Begin >= 0xDC00) && (*Begin <= 0xDFFF)))
{
++Length;
}
}
else
{
++Length;
}
++Begin;
}
return Length;
}
////////////////////////////////////////////////////////////
/// Get the number of characters composing an UTF-32 string
////////////////////////////////////////////////////////////
template <typename In>
inline std::size_t Unicode::GetUTF32Length(In Begin, In End)
{
return End - Begin;
}
|