summaryrefslogtreecommitdiffstatshomepage
path: root/scripts/src/tools.lua
diff options
context:
space:
mode:
Diffstat (limited to 'scripts/src/tools.lua')
0 files changed, 0 insertions, 0 deletions
ref='#n49'>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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494
// license:BSD-3-Clause
// copyright-holders:Aaron Giles
/*********************************************************************

    unicode.cpp

    Unicode related functions

***************************************************************************/

#include "unicode.h"

#ifdef _WIN32
#define UTF8PROC_DLLEXPORT
#endif

#include "utf8proc/utf8proc.h"


//-------------------------------------------------
//  uchar_isvalid - return true if a given
//  character is a legitimate unicode character
//-------------------------------------------------

bool uchar_isvalid(char32_t uchar)
{
	return (uchar < 0x110000) && !((uchar >= 0xd800) && (uchar <= 0xdfff));
}


//-------------------------------------------------
//  uchar_is_printable - tests to see if a unicode
//  char is printable
//-------------------------------------------------

bool uchar_is_printable(char32_t uchar)
{
	return
		!(0x0001f >= uchar) &&                            // C0 control
		!((0x0007f <= uchar) && (0x0009f >= uchar)) &&    // DEL and C1 control
		!((0x0fdd0 <= uchar) && (0x0fddf >= uchar)) &&    // noncharacters
		!(0x0fffe == (uchar & 0x0ffff)) &&                // byte-order detection noncharacter
		!(0x0ffff == (uchar & 0x0ffff));                  // the other noncharacter
}


//-------------------------------------------------
//  uchar_is_digit - tests to see if a unicode
//  char is a digit
//-------------------------------------------------

bool uchar_is_digit(char32_t uchar)
{
	return uchar >= '0' && uchar <= '9';
}


//-------------------------------------------------
//  uchar_from_utf8 - convert a UTF-8 sequence
//  into a unicode character
//-----------------------------------------------

int uchar_from_utf8(char32_t *uchar, const char *utf8char, size_t count)
{
	char32_t c, minchar;
	int auxlen, i;
	char auxchar;

	// validate parameters
	if (utf8char == nullptr || count == 0)
		return 0;

	// start with the first byte
	c = (unsigned char) *utf8char;
	count--;
	utf8char++;

	// based on that, determine how many additional bytes we need
	if (c < 0x80)
	{
		// unicode char 0x00000000 - 0x0000007F
		c &= 0x7f;
		auxlen = 0;
		minchar = 0x00000000;
	}
	else if (c >= 0xc0 && c < 0xe0)
	{
		// unicode char 0x00000080 - 0x000007FF
		c &= 0x1f;
		auxlen = 1;
		minchar = 0x00000080;
	}
	else if (c >= 0xe0 && c < 0xf0)
	{
		// unicode char 0x00000800 - 0x0000FFFF
		c &= 0x0f;
		auxlen = 2;
		minchar = 0x00000800;
	}
	else if (c >= 0xf0 && c < 0xf8)
	{
		// unicode char 0x00010000 - 0x001FFFFF
		c &= 0x07;
		auxlen = 3;
		minchar = 0x00010000;
	}
	else if (c >= 0xf8 && c < 0xfc)
	{
		// unicode char 0x00200000 - 0x03FFFFFF
		c &= 0x03;
		auxlen = 4;
		minchar = 0x00200000;
	}
	else if (c >= 0xfc && c < 0xfe)
	{
		// unicode char 0x04000000 - 0x7FFFFFFF
		c &= 0x01;
		auxlen = 5;
		minchar = 0x04000000;
	}
	else
	{
		// invalid
		return -1;
	}

	// exceeds the count?
	if (auxlen > count)
		return -1;

	// we now know how long the char is, now compute it
	for (i = 0; i < auxlen; i++)
	{
		auxchar = utf8char[i];

		// all auxillary chars must be between 0x80-0xbf
		if ((auxchar & 0xc0) != 0x80)
			return -1;

		c = c << 6;
		c |= auxchar & 0x3f;
	}

	// make sure that this char is above the minimum
	if (c < minchar)
		return -1;

	*uchar = c;
	return auxlen + 1;
}


//-------------------------------------------------
//  uchar_from_utf16 - convert a UTF-16 sequence
//  into a unicode character
//-------------------------------------------------

int uchar_from_utf16(char32_t *uchar, const char16_t *utf16char, size_t count)
{
	int rc = -1;

	// validate parameters
	if (utf16char == nullptr || count == 0)
	{
		rc = 0;
	}
	if (utf16char[0] >= 0xd800 && utf16char[0] <= 0xdbff)
	{
		// handle the two-byte case
		if (count > 1 && utf16char[1] >= 0xdc00 && utf16char[1] <= 0xdfff)
		{
			*uchar = 0x10000 + ((utf16char[0] & 0x3ff) * 0x400) + (utf16char[1] & 0x3ff);
			rc = 2;
		}
	}
	else if (utf16char[0] < 0xdc00 || utf16char[0] > 0xdfff)
	{
		// handle the one-byte case
		*uchar = utf16char[0];
		rc = 1;
	}

	return rc;
}


//-------------------------------------------------
//  uchar_from_utf16f - convert a UTF-16 sequence
//  into a unicode character from a flipped
//  byte order
//-------------------------------------------------

int uchar_from_utf16f(char32_t *uchar, const char16_t *utf16char, size_t count)
{
	char16_t buf[2] = {0};
	if (count > 0)
		buf[0] = flipendian_int16(utf16char[0]);
	if (count > 1)
		buf[1] = flipendian_int16(utf16char[1]);
	return uchar_from_utf16(uchar, buf, count);
}


//-------------------------------------------------
//  utf8_from_uchar - convert a unicode character
//  into a UTF-8 sequence
//-------------------------------------------------

int utf8_from_uchar(char *utf8string, size_t count, char32_t uchar)
{
	int rc = 0;

	// error on invalid characters
	if (!uchar_isvalid(uchar))
		return -1;

	// based on the value, output the appropriate number of bytes
	if (uchar < 0x80)
	{
		// unicode char 0x00000000 - 0x0000007F
		if (count < 1)
			return -1;
		utf8string[rc++] = (char) uchar;
	}
	else if (uchar < 0x800)
	{
		// unicode char 0x00000080 - 0x000007FF
		if (count < 2)
			return -1;
		utf8string[rc++] = ((char) (uchar >> 6)) | 0xC0;
		utf8string[rc++] = ((char) ((uchar >> 0) & 0x3F)) | 0x80;
	}
	else if (uchar < 0x10000)
	{
		// unicode char 0x00000800 - 0x0000FFFF
		if (count < 3)
			return -1;
		utf8string[rc++] = ((char) (uchar >> 12)) | 0xE0;
		utf8string[rc++] = ((char) ((uchar >> 6) & 0x3F)) | 0x80;
		utf8string[rc++] = ((char) ((uchar >> 0) & 0x3F)) | 0x80;
	}
	else if (uchar < 0x00200000)
	{
		// unicode char 0x00010000 - 0x001FFFFF
		if (count < 4)
			return -1;
		utf8string[rc++] = ((char) (uchar >> 18)) | 0xF0;
		utf8string[rc++] = ((char) ((uchar >> 12) & 0x3F)) | 0x80;
		utf8string[rc++] = ((char) ((uchar >> 6) & 0x3F)) | 0x80;
		utf8string[rc++] = ((char) ((uchar >> 0) & 0x3F)) | 0x80;
	}
	else if (uchar < 0x04000000)
	{
		// unicode char 0x00200000 - 0x03FFFFFF
		if (count < 5)
			return -1;
		utf8string[rc++] = ((char) (uchar >> 24)) | 0xF8;
		utf8string[rc++] = ((char) ((uchar >> 18) & 0x3F)) | 0x80;
		utf8string[rc++] = ((char) ((uchar >> 12) & 0x3F)) | 0x80;
		utf8string[rc++] = ((char) ((uchar >> 6) & 0x3F)) | 0x80;
		utf8string[rc++] = ((char) ((uchar >> 0) & 0x3F)) | 0x80;
	}
	else if (uchar < 0x80000000)
	{
		// unicode char 0x04000000 - 0x7FFFFFFF
		if (count < 6)
			return -1;
		utf8string[rc++] = ((char) (uchar >> 30)) | 0xFC;
		utf8string[rc++] = ((char) ((uchar >> 24) & 0x3F)) | 0x80;
		utf8string[rc++] = ((char) ((uchar >> 18) & 0x3F)) | 0x80;
		utf8string[rc++] = ((char) ((uchar >> 12) & 0x3F)) | 0x80;
		utf8string[rc++] = ((char) ((uchar >> 6) & 0x3F)) | 0x80;
		utf8string[rc++] = ((char) ((uchar >> 0) & 0x3F)) | 0x80;
	}
	else
		rc = -1;

	return rc;
}


//-------------------------------------------------
//  utf8_from_uchar - convert a unicode character
//  into a UTF-8 sequence
//-------------------------------------------------

std::string utf8_from_uchar(char32_t uchar)
{
	char buffer[UTF8_CHAR_MAX];
	auto len = utf8_from_uchar(buffer, ARRAY_LENGTH(buffer), uchar);
	return std::string(buffer, len);
}


//-------------------------------------------------
//  utf16_from_uchar - convert a unicode character
//  into a UTF-16 sequence
//-------------------------------------------------

int utf16_from_uchar(char16_t *utf16string, size_t count, char32_t uchar)
{
	int rc;

	// error on invalid characters
	if (!uchar_isvalid(uchar))
		return -1;

	if (uchar < 0x10000)
	{
		// single word case
		if (count < 1)
			return -1;
		utf16string[0] = (char16_t) uchar;
		rc = 1;
	}
	else if (uchar < 0x100000)
	{
		// double word case
		if (count < 2)
			return -1;
		uchar -= 0x10000;
		utf16string[0] = ((uchar >> 10) & 0x03ff) | 0xd800;
		utf16string[1] = ((uchar >>  0) & 0x03ff) | 0xdc00;
		rc = 2;
	}
	else
	{
		return -1;
	}
	return rc;
}


//-------------------------------------------------
//  utf16_from_uchar - convert a unicode character
//  into a UTF-16 sequence with flipped endianness
//-------------------------------------------------

int utf16f_from_uchar(char16_t *utf16string, size_t count, char32_t uchar)
{
	int rc;
	char16_t buf[2] = { 0, 0 };

	rc = utf16_from_uchar(buf, count, uchar);

	if (rc >= 1)
		utf16string[0] = flipendian_int16(buf[0]);
	if (rc >= 2)
		utf16string[1] = flipendian_int16(buf[1]);
	return rc;
}


//-------------------------------------------------
//  internal_normalize_unicode - uses utf8proc to
//	normalize unicode
//-------------------------------------------------

static std::string internal_normalize_unicode(const char *s, size_t length, unicode_normalization_form normalization_form, bool null_terminated)
{
	// convert the normalization form
	int options;
	switch (normalization_form)
	{
	case unicode_normalization_form::C:
		options = UTF8PROC_STABLE | UTF8PROC_COMPOSE;
		break;
	case unicode_normalization_form::D:
		options = UTF8PROC_STABLE | UTF8PROC_DECOMPOSE;
		break;
	case unicode_normalization_form::KC:
		options = UTF8PROC_STABLE | UTF8PROC_COMPOSE | UTF8PROC_COMPAT;
		break;
	case unicode_normalization_form::KD:
		options = UTF8PROC_STABLE | UTF8PROC_DECOMPOSE | UTF8PROC_COMPAT;
		break;
	default:
		throw false;
	}

	// was this null terminated?
	if (null_terminated)
		options |= UTF8PROC_NULLTERM;

	// invoke utf8proc
	utf8proc_uint8_t *utf8proc_result;
	utf8proc_ssize_t utf8proc_result_length = utf8proc_map((utf8proc_uint8_t *) s, length, &utf8proc_result, (utf8proc_option_t)options);

	// conver the result
	std::string result;
	if (utf8proc_result)
	{
		if (utf8proc_result_length > 0)
			result = std::string((const char *)utf8proc_result, utf8proc_result_length);
		free(utf8proc_result);
	}

	return result;
}


//-------------------------------------------------
//  normalize_unicode - uses utf8proc to normalize
//	unicode
//-------------------------------------------------

std::string normalize_unicode(const std::string &s, unicode_normalization_form normalization_form)
{
	return internal_normalize_unicode(s.c_str(), s.length(), normalization_form, false);
}


//-------------------------------------------------
//  normalize_unicode - uses utf8proc to normalize
//	unicode
//-------------------------------------------------

std::string normalize_unicode(const char *s, unicode_normalization_form normalization_form)
{
	return internal_normalize_unicode(s, 0, normalization_form, true);
}


//-------------------------------------------------
//  normalize_unicode - uses utf8proc to normalize
//	unicode
//-------------------------------------------------

std::string normalize_unicode(const char *s, size_t length, unicode_normalization_form normalization_form)
{
	return internal_normalize_unicode(s, length, normalization_form, false);
}


//-------------------------------------------------
//  utf8_previous_char - return a pointer to the
//  previous character in a string
//-------------------------------------------------

/**
 * @fn  const char *utf8_previous_char(const char *utf8string)
 *
 * @brief   UTF 8 previous character.
 *
 * @param   utf8string  The UTF 8string.
 *
 * @return  null if it fails, else a char*.
 */

const char *utf8_previous_char(const char *utf8string)
{
	while ((*--utf8string & 0xc0) == 0x80)
		;
	return utf8string;
}


//-------------------------------------------------
//  utf8_is_valid_string - return true if the
//  given string is a properly formed sequence of
//    UTF-8 characters
//-------------------------------------------------

/**
 * @fn  int utf8_is_valid_string(const char *utf8string)
 *
 * @brief   UTF 8 is valid string.
 *
 * @param   utf8string  The UTF 8string.
 *
 * @return  An int.
 */

bool utf8_is_valid_string(const char *utf8string)
{
	int remaining_length = strlen(utf8string);

	while (*utf8string != 0)
	{
		char32_t uchar = 0;
		int charlen;

		// extract the current character and verify it
		charlen = uchar_from_utf8(&uchar, utf8string, remaining_length);
		if (charlen <= 0 || uchar == 0 || !uchar_isvalid(uchar))
			return false;

		// advance
		utf8string += charlen;
		remaining_length -= charlen;
	}

	return true;
}