mcl.c 19.6 KB
Newer Older
1 2 3 4 5
/*
 * Wine Message Compiler lexical scanner
 *
 * Copyright 2000 Bertho A. Stultiens (BS)
 *
6 7 8 9 10 11 12 13 14 15 16 17
 * This library is free software; you can redistribute it and/or
 * modify it under the terms of the GNU Lesser General Public
 * License as published by the Free Software Foundation; either
 * version 2.1 of the License, or (at your option) any later version.
 *
 * This library is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
 * Lesser General Public License for more details.
 *
 * You should have received a copy of the GNU Lesser General Public
 * License along with this library; if not, write to the Free Software
18
 * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301, USA
19
 */
20 21 22

#include "config.h"

23 24 25 26
#include <stdio.h>
#include <stdlib.h>
#include <ctype.h>
#include <assert.h>
27
#include <string.h>
28 29 30 31 32

#include "utils.h"
#include "wmc.h"
#include "lang.h"

33
#include "mcy.tab.h"
34 35

/*
Austin English's avatar
Austin English committed
36
 * Keywords are case insensitive. All normal input is treated as
37 38 39 40 41 42 43 44 45 46 47 48 49 50 51
 * being in codepage iso-8859-1 for ascii input files (unicode
 * page 0) and as equivalent unicode if unicode input is selected.
 * All normal input, which is not part of a message text, is
 * enforced to be unicode page 0. Otherwise an error will be
 * generated. The normal file data should only be ASCII because
 * that is the basic definition of the grammar.
 *
 * Byteorder or unicode input is determined automatically by
 * reading the first 8 bytes and checking them against unicode
 * page 0 byteorder (hibyte must be 0).
 * -- FIXME --
 * Alternatively, the input is checked against a special byte
 * sequence to identify the file.
 * -- FIXME --
 *
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
 * Keywords:
 *	Codepages
 *	Facility
 *	FacilityNames
 *	LanguageNames
 *	MessageId
 *	MessageIdTypedef
 *	Severity
 *	SeverityNames
 *	SymbolicName
 *
 * Default added identifiers for classes:
 * SeverityNames:
 *	Success		= 0x0
 *	Informational	= 0x1
 *	Warning		= 0x2
 *	Error		= 0x3
 * FacilityNames:
 *	System		= 0x0FF
 *	Application	= 0xFFF
 *
 * The 'Codepages' keyword is a wmc extension.
 */

77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95
static const WCHAR ustr_application[]	= { 'A', 'p', 'p', 'l', 'i', 'c', 'a', 't', 'i', 'o', 'n', 0 };
static const WCHAR ustr_codepages[]	= { 'C', 'o', 'd', 'e', 'p', 'a', 'g', 'e', 's', 0 };
static const WCHAR ustr_english[]	= { 'E', 'n', 'g', 'l', 'i', 's', 'h', 0 };
static const WCHAR ustr_error[]		= { 'E', 'r', 'r', 'o', 'r', 0 };
static const WCHAR ustr_facility[]	= { 'F', 'a', 'c', 'i', 'l', 'i', 't', 'y', 0 };
static const WCHAR ustr_facilitynames[]	= { 'F', 'a', 'c', 'i', 'l', 'i', 't', 'y', 'N', 'a', 'm', 'e', 's', 0 };
static const WCHAR ustr_informational[]	= { 'I', 'n', 'f', 'o', 'r', 'm', 'a', 't', 'i', 'o', 'n', 'a', 'l', 0 };
static const WCHAR ustr_language[]	= { 'L', 'a', 'n', 'g', 'u', 'a', 'g', 'e', 0};
static const WCHAR ustr_languagenames[]	= { 'L', 'a', 'n', 'g', 'u', 'a', 'g', 'e', 'N', 'a', 'm', 'e', 's', 0};
static const WCHAR ustr_messageid[]	= { 'M', 'e', 's', 's', 'a', 'g', 'e', 'I', 'd', 0 };
static const WCHAR ustr_messageidtypedef[] = { 'M', 'e', 's', 's', 'a', 'g', 'e', 'I', 'd', 'T', 'y', 'p', 'e', 'd', 'e', 'f', 0 };
static const WCHAR ustr_outputbase[]	= { 'O', 'u', 't', 'p', 'u', 't', 'B', 'a', 's', 'e', 0 };
static const WCHAR ustr_severity[]	= { 'S', 'e', 'v', 'e', 'r', 'i', 't', 'y', 0 };
static const WCHAR ustr_severitynames[]	= { 'S', 'e', 'v', 'e', 'r', 'i', 't', 'y', 'N', 'a', 'm', 'e', 's', 0 };
static const WCHAR ustr_success[]	= { 'S', 'u', 'c', 'c', 'e', 's', 's', 0 };
static const WCHAR ustr_symbolicname[]	= { 'S', 'y', 'm', 'b', 'o', 'l', 'i', 'c', 'N', 'a', 'm', 'e', 0 };
static const WCHAR ustr_system[]	= { 'S', 'y', 's', 't', 'e', 'm', 0 };
static const WCHAR ustr_warning[]	= { 'W', 'a', 'r', 'n', 'i', 'n', 'g', 0 };
static const WCHAR ustr_msg00001[]	= { 'm', 's', 'g', '0', '0', '0', '0', '1', 0 };
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
/*
 * This table is to beat any form of "expression building" to check for
 * correct filename characters. It is also used for ident checks.
 * FIXME: use it more consistently.
 */

#define CH_SHORTNAME	0x01
#define CH_LONGNAME	0x02
#define CH_IDENT	0x04
#define CH_NUMBER	0x08
/*#define CH_WILDCARD	0x10*/
/*#define CH_DOT	0x20*/
#define CH_PUNCT	0x40
#define CH_INVALID	0x80

static const char char_table[256] = {
	0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, /* 0x00 - 0x07 */
	0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, /* 0x08 - 0x0F */
	0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, /* 0x10 - 0x17 */
	0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, /* 0x18 - 0x1F */
	0x80, 0x03, 0x80, 0x03, 0x03, 0x03, 0x03, 0x03, /* 0x20 - 0x27 " !"#$%&'" */
	0x43, 0x43, 0x10, 0x80, 0x03, 0x03, 0x22, 0x80, /* 0x28 - 0x2F "()*+,-./" */
	0x0b, 0x0b, 0x0b, 0x0b, 0x0b, 0x0b, 0x0b, 0x0b, /* 0x30 - 0x37 "01234567" */
	0x0b, 0x0b, 0xc0, 0x80, 0x80, 0x80, 0x80, 0x10, /* 0x38 - 0x3F "89:;<=>?" */
	0x03, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07, /* 0x40 - 0x47 "@ABCDEFG" */
	0x07, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07, /* 0x48 - 0x4F "HIJKLMNO" */
	0x07, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07, /* 0x50 - 0x57 "PQRSTUVW" */
	0x07, 0x07, 0x07, 0x80, 0x80, 0x80, 0x80, 0x07, /* 0x58 - 0x5F "XYZ[\]^_" */
	0x03, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07, /* 0x60 - 0x67 "`abcdefg" */
	0x07, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07, /* 0x68 - 0x6F "hijklmno" */
	0x07, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07, 0x07, /* 0x70 - 0x77 "pqrstuvw" */
	0x07, 0x07, 0x07, 0x03, 0x80, 0x03, 0x03, 0x80, /* 0x78 - 0x7F "xyz{|}~ " */
	0x02, 0x02, 0x02, 0x02, 0x02, 0x02, 0x02, 0x02, /* 0x80 - 0x87 */
	0x02, 0x02, 0x02, 0x02, 0x02, 0x02, 0x02, 0x02, /* 0x88 - 0x8F */
	0x02, 0x02, 0x02, 0x02, 0x02, 0x02, 0x02, 0x02, /* 0x90 - 0x97 */
	0x02, 0x02, 0x02, 0x02, 0x02, 0x02, 0x02, 0x02, /* 0x98 - 0x9F */
	0x02, 0x02, 0x02, 0x02, 0x02, 0x02, 0x02, 0x02, /* 0xA0 - 0xA7 */
	0x02, 0x02, 0x02, 0x02, 0x02, 0x02, 0x02, 0x02, /* 0xA8 - 0xAF */
	0x02, 0x02, 0x02, 0x02, 0x02, 0x02, 0x02, 0x02, /* 0xB0 - 0xB7 */
	0x02, 0x02, 0x02, 0x02, 0x02, 0x02, 0x02, 0x02, /* 0xB8 - 0xBF */
	0x02, 0x02, 0x02, 0x02, 0x02, 0x02, 0x02, 0x02, /* 0xC0 - 0xC7 */
	0x02, 0x02, 0x02, 0x02, 0x02, 0x02, 0x02, 0x02, /* 0xC8 - 0xCF */
	0x02, 0x02, 0x02, 0x02, 0x02, 0x02, 0x02, 0x02, /* 0xD0 - 0xD7 */
	0x02, 0x02, 0x02, 0x02, 0x02, 0x02, 0x02, 0x02, /* 0xD8 - 0xDF */
	0x02, 0x02, 0x02, 0x02, 0x02, 0x02, 0x02, 0x02, /* 0xE0 - 0xE7 */
	0x02, 0x02, 0x02, 0x02, 0x02, 0x02, 0x02, 0x02, /* 0xE8 - 0xEF */
	0x02, 0x02, 0x02, 0x02, 0x02, 0x02, 0x02, 0x02, /* 0xF0 - 0xF7 */
	0x02, 0x02, 0x02, 0x02, 0x02, 0x02, 0x02, 0x80, /* 0xF8 - 0xFF */
};

static int isisochar(int ch)
{
	return !(ch & (~0xff));
}

static int codepage;
static const union cptable *codepage_def;

void set_codepage(int cp)
{
	codepage = cp;
	codepage_def = find_codepage(codepage);
158
	if(!codepage_def && codepage != CP_UTF8)
159
		xyyerror("Codepage %d not found; cannot process\n", codepage);
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
}

/*
 * Input functions
 */
static int nungetstack = 0;
static int allocungetstack = 0;
static char *ungetstack = NULL;
static int ninputbuffer = 0;
static WCHAR *inputbuffer = NULL;
static char *xlatebuffer = NULL;

#define INPUTBUFFER_SIZE	2048	/* Must be larger than 4 and approx. large enough to hold a line */

/*
 * Fill the input buffer with *one* line of input.
 * The line is '\n' terminated so that scanning
 * messages with translation works as expected
 * (otherwise we cannot pre-translate because the
 * language is first known one line before the
 * actual message).
 */
static int fill_inputbuffer(void)
{
	int n;
185
	static const char err_fatalread[] = "Fatal: reading input failed";
186 187 188 189
	static int endian = -1;

	if(!inputbuffer)
	{
190
		inputbuffer = xmalloc(INPUTBUFFER_SIZE*sizeof(WCHAR));
191 192 193 194 195 196 197 198 199 200 201 202
		xlatebuffer = xmalloc(INPUTBUFFER_SIZE);
	}

try_again:
	if(!unicodein)
	{
		char *cptr;
		cptr = fgets(xlatebuffer, INPUTBUFFER_SIZE, yyin);
		if(!cptr && ferror(yyin))
			xyyerror(err_fatalread);
		else if(!cptr)
			return 0;
203 204 205 206
                if (codepage_def)
                    n = wine_cp_mbstowcs(codepage_def, 0, xlatebuffer, strlen(xlatebuffer)+1, inputbuffer, INPUTBUFFER_SIZE);
                else
                    n = wine_utf8_mbstowcs(0, xlatebuffer, strlen(xlatebuffer)+1, inputbuffer, INPUTBUFFER_SIZE);
207
		if(n < 0)
208
			internal_error(__FILE__, __LINE__, "Could not translate to unicode (%d)\n", n);
209
		if(n <= 1)
Austin English's avatar
Austin English committed
210
			goto try_again;	/* Should not happen */
211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228
		n--;	/* Strip added conversion '\0' from input length */
		/*
		 * FIXME:
		 * Detect UTF-8 in the first time we read some bytes by
		 * checking the special sequence "FE..." or something like
		 * that. I need to check www.unicode.org for details.
		 */
	}
	else
	{
		if(endian == -1)
		{
			n = fread(inputbuffer, 1, 8, yyin);
			if(n != 8)
			{
				if(!n && ferror(yyin))
					xyyerror(err_fatalread);
				else
229
					xyyerror("Fatal: file to short to determine byteorder (should never happen)\n");
230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253
			}
			if(isisochar(inputbuffer[0]) &&
				isisochar(inputbuffer[1]) &&
				isisochar(inputbuffer[2]) &&
				isisochar(inputbuffer[3]))
			{
#ifdef WORDS_BIGENDIAN
				endian = WMC_BO_BIG;
#else
				endian = WMC_BO_LITTLE;
#endif
			}
			else if(isisochar(BYTESWAP_WORD(inputbuffer[0])) &&
				isisochar(BYTESWAP_WORD(inputbuffer[1])) &&
				isisochar(BYTESWAP_WORD(inputbuffer[2])) &&
				isisochar(BYTESWAP_WORD(inputbuffer[3])))
			{
#ifdef WORDS_BIGENDIAN
				endian = WMC_BO_LITTLE;
#else
				endian = WMC_BO_BIG;
#endif
			}
			else
254
				xyyerror("Fatal: cannot determine file's byteorder\n");
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
			/* FIXME:
			 * Determine the file-endian with the leader-bytes
			 * "FF FE..."; can't remember the exact sequence.
			 */
			n /= 2;
#ifdef WORDS_BIGENDIAN
			if(endian == WMC_BO_LITTLE)
#else
			if(endian == WMC_BO_BIG)
#endif
			{
				inputbuffer[0] = BYTESWAP_WORD(inputbuffer[0]);
				inputbuffer[1] = BYTESWAP_WORD(inputbuffer[1]);
				inputbuffer[2] = BYTESWAP_WORD(inputbuffer[2]);
				inputbuffer[3] = BYTESWAP_WORD(inputbuffer[3]);
			}

		}
		else
		{
			int i;
			n = 0;
			for(i = 0; i < INPUTBUFFER_SIZE; i++)
			{
				int t;
				t = fread(&inputbuffer[i], 2, 1, yyin);
				if(!t && ferror(yyin))
					xyyerror(err_fatalread);
				else if(!t && n)
					break;
				n++;
#ifdef WORDS_BIGENDIAN
				if(endian == WMC_BO_LITTLE)
#else
				if(endian == WMC_BO_BIG)
#endif
				{
					if((inputbuffer[i] = BYTESWAP_WORD(inputbuffer[i])) == '\n')
						break;
				}
				else
				{
					if(inputbuffer[i] == '\n')
						break;
				}
			}
		}

	}

	if(!n)
	{
307
		mcy_warning("Re-read line (input was or converted to zilch)\n");
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
		goto try_again;	/* Should not happen, but could be due to stdin reading and a signal */
	}

	ninputbuffer += n;
	return 1;
}

static int get_unichar(void)
{
	static WCHAR *b = NULL;
	char_number++;

	if(nungetstack)
		return ungetstack[--nungetstack];

	if(!ninputbuffer)
	{
		if(!fill_inputbuffer())
			return EOF;
		b = inputbuffer;
	}

	ninputbuffer--;
	return (int)(*b++ & 0xffff);
}

static void unget_unichar(int ch)
{
	if(ch == EOF)
		return;

	char_number--;

	if(nungetstack == allocungetstack)
	{
		allocungetstack += 32;
		ungetstack = xrealloc(ungetstack, allocungetstack * sizeof(*ungetstack));
	}

	ungetstack[nungetstack++] = (WCHAR)ch;
}


/*
 * Normal character stack.
 * Used for number scanning.
 */
static int ncharstack = 0;
static int alloccharstack = 0;
static char *charstack = NULL;

static void empty_char_stack(void)
{
	ncharstack = 0;
}

static void push_char(int ch)
{
	if(ncharstack == alloccharstack)
	{
		alloccharstack += 32;
		charstack = xrealloc(charstack, alloccharstack * sizeof(*charstack));
	}
	charstack[ncharstack++] = (char)ch;
}

static int tos_char_stack(void)
{
	if(!ncharstack)
		return 0;
	else
		return (int)(charstack[ncharstack-1] & 0xff);
}

static char *get_char_stack(void)
{
	return charstack;
}

/*
 * Unicode character stack.
 * Used for general scanner.
 */
static int nunicharstack = 0;
static int allocunicharstack = 0;
static WCHAR *unicharstack = NULL;

static void empty_unichar_stack(void)
{
	nunicharstack = 0;
}

static void push_unichar(int ch)
{
	if(nunicharstack == allocunicharstack)
	{
		allocunicharstack += 128;
		unicharstack = xrealloc(unicharstack, allocunicharstack * sizeof(*unicharstack));
	}
	unicharstack[nunicharstack++] = (WCHAR)ch;
}

#if 0
static int tos_unichar_stack(void)
{
	if(!nunicharstack)
		return 0;
	else
		return (int)(unicharstack[nunicharstack-1] & 0xffff);
}
#endif

static WCHAR *get_unichar_stack(void)
{
	return unicharstack;
}

/*
 * Number scanner
 *
 * state |      ch         | next state
 * ------+-----------------+--------------------------
 *   0   | [0]             | 1
 *   0   | [1-9]           | 4
 *   0   | .               | error (should never occur)
 *   1   | [xX]            | 2
 *   1   | [0-7]           | 3
 *   1   | [89a-wyzA-WYZ_] | error invalid digit
 *   1   | .               | return 0
 *   2   | [0-9a-fA-F]     | 2
 *   2   | [g-zG-Z_]       | error invalid hex digit
 *   2   | .               | return (hex-number) if TOS != [xX] else error
 *   3   | [0-7]           | 3
 *   3   | [89a-zA-Z_]     | error invalid octal digit
 *   3   | .               | return (octal-number)
 *   4   | [0-9]           | 4
 *   4   | [a-zA-Z_]       | error invalid decimal digit
 *   4   | .               | return (decimal-number)
 *
 * All non-identifier characters [^a-zA-Z_0-9] terminate the scan
 * and return the value. This is not entirely correct, but close
 * enough (should check punctuators as trailing context, but the
 * char_table is not adapted to that and it is questionable whether
 * it is worth the trouble).
 * All non-iso-8859-1 characters are an error.
 */
static int scan_number(int ch)
{
	int state = 0;
	int base = 10;
	empty_char_stack();

	while(1)
	{
		if(!isisochar(ch))
463
			xyyerror("Invalid digit\n");
464 465 466 467 468 469 470 471 472 473 474 475 476

		switch(state)
		{
		case 0:
			if(isdigit(ch))
			{
				push_char(ch);
				if(ch == '0')
					state = 1;
				else
					state = 4;
			}
			else
477
				internal_error(__FILE__, __LINE__, "Non-digit in first number-scanner state\n");
478 479 480 481 482 483 484 485 486 487 488 489 490
			break;
		case 1:
			if(ch == 'x' || ch == 'X')
			{
				push_char(ch);
				state = 2;
			}
			else if(ch >= '0' && ch <= '7')
			{
				push_char(ch);
				state = 3;
			}
			else if(isalpha(ch) || ch == '_')
491
				xyyerror("Invalid number digit\n");
492 493 494
			else
			{
				unget_unichar(ch);
495
				mcy_lval.num = 0;
496 497 498 499 500 501 502
				return tNUMBER;
			}
			break;
		case 2:
			if(isxdigit(ch))
				push_char(ch);
			else if(isalpha(ch) || ch == '_' || !isxdigit(tos_char_stack()))
503
				xyyerror("Invalid hex digit\n");
504 505 506 507 508 509 510 511 512 513
			else
			{
				base = 16;
				goto finish;
			}
			break;
		case 3:
			if(ch >= '0' && ch <= '7')
				push_char(ch);
			else if(isalnum(ch) || ch == '_')
514
				xyyerror("Invalid octal digit\n");
515 516 517 518 519 520 521 522 523 524
			else
			{
				base = 8;
				goto finish;
			}
			break;
		case 4:
			if(isdigit(ch))
				push_char(ch);
			else if(isalnum(ch) || ch == '_')
525
				xyyerror("Invalid decimal digit\n");
526 527 528 529 530 531 532
			else
			{
				base = 10;
				goto finish;
			}
			break;
		default:
533
			internal_error(__FILE__, __LINE__, "Invalid state in number-scanner\n");
534 535 536 537 538 539
		}
		ch = get_unichar();
	}
finish:
	unget_unichar(ch);
	push_char(0);
540
	mcy_lval.num = strtoul(get_char_stack(), NULL, base);
541 542 543 544 545 546 547 548 549 550 551
	return tNUMBER;
}

static void newline(void)
{
	line_number++;
	char_number = 1;
}

static int unisort(const void *p1, const void *p2)
{
552
	return unistricmp(((const token_t *)p1)->name, ((const token_t *)p2)->name);
553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590
}

static token_t *tokentable = NULL;
static int ntokentable = 0;

token_t *lookup_token(const WCHAR *s)
{
	token_t tok;

	tok.name = s;
	return (token_t *)bsearch(&tok, tokentable, ntokentable, sizeof(*tokentable), unisort);
}

void add_token(tok_e type, const WCHAR *name, int tok, int cp, const WCHAR *alias, int fix)
{
	ntokentable++;
	tokentable = xrealloc(tokentable, ntokentable * sizeof(*tokentable));
	tokentable[ntokentable-1].type = type;
	tokentable[ntokentable-1].name = name;
	tokentable[ntokentable-1].token = tok;
	tokentable[ntokentable-1].codepage = cp;
	tokentable[ntokentable-1].alias = alias;
	tokentable[ntokentable-1].fixed = fix;
	qsort(tokentable, ntokentable, sizeof(*tokentable), unisort);
}

void get_tokentable(token_t **tab, int *len)
{
	assert(tab != NULL);
	assert(len != NULL);
	*tab = tokentable;
	*len = ntokentable;
}

/*
 * The scanner
 *
 */
591
int mcy_lex(void)
592
{
593 594
	static const WCHAR ustr_dot1[] = { '.', '\n', 0 };
	static const WCHAR ustr_dot2[] = { '.', '\r', '\n', 0 };
595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630
	static int isinit = 0;
	int ch;

	if(!isinit)
	{
		isinit++;
		set_codepage(WMC_DEFAULT_CODEPAGE);
		add_token(tok_keyword,	ustr_codepages,		tCODEPAGE,	0, NULL, 0);
		add_token(tok_keyword,	ustr_facility,		tFACILITY,	0, NULL, 1);
		add_token(tok_keyword,	ustr_facilitynames,	tFACNAMES,	0, NULL, 1);
		add_token(tok_keyword,	ustr_language,		tLANGUAGE,	0, NULL, 1);
		add_token(tok_keyword,	ustr_languagenames,	tLANNAMES,	0, NULL, 1);
		add_token(tok_keyword,	ustr_messageid,		tMSGID,		0, NULL, 1);
		add_token(tok_keyword,	ustr_messageidtypedef,	tTYPEDEF,	0, NULL, 1);
		add_token(tok_keyword,	ustr_outputbase,	tBASE,		0, NULL, 1);
		add_token(tok_keyword,	ustr_severity,		tSEVERITY,	0, NULL, 1);
		add_token(tok_keyword,	ustr_severitynames,	tSEVNAMES,	0, NULL, 1);
		add_token(tok_keyword,	ustr_symbolicname,	tSYMNAME,	0, NULL, 1);
		add_token(tok_severity,	ustr_error,		0x03,		0, NULL, 0);
		add_token(tok_severity,	ustr_warning,		0x02,		0, NULL, 0);
		add_token(tok_severity,	ustr_informational,	0x01,		0, NULL, 0);
		add_token(tok_severity,	ustr_success,		0x00,		0, NULL, 0);
		add_token(tok_facility,	ustr_application,	0xFFF,		0, NULL, 0);
		add_token(tok_facility,	ustr_system,		0x0FF,		0, NULL, 0);
		add_token(tok_language,	ustr_english,		0x409,		437, ustr_msg00001, 0);
	}

	empty_unichar_stack();

	while(1)
	{
		if(want_line)
		{
			while((ch = get_unichar()) != '\n')
			{
				if(ch == EOF)
631
					xyyerror("Unexpected EOF\n");
632 633 634 635 636 637 638 639 640 641 642 643
				push_unichar(ch);
			}
			newline();
			push_unichar(ch);
			push_unichar(0);
			if(!unistrcmp(ustr_dot1, get_unichar_stack()) || !unistrcmp(ustr_dot2, get_unichar_stack()))
			{
				want_line = 0;
				/* Reset the codepage to our default after each message */
				set_codepage(WMC_DEFAULT_CODEPAGE);
				return tMSGEND;
			}
644
			mcy_lval.str = xunistrdup(get_unichar_stack());
645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673
			return tLINE;
		}

		ch = get_unichar();

		if(ch == EOF)
			return EOF;

		if(ch == '\n')
		{
			newline();
			if(want_nl)
			{
				want_nl = 0;
				return tNL;
			}
			continue;
		}

		if(isisochar(ch))
		{
			if(want_file)
			{
				int n = 0;
				while(n < 8 && isisochar(ch))
				{
					int t = char_table[ch];
					if((t & CH_PUNCT) || !(t & CH_SHORTNAME))
						break;
674

675 676 677 678 679 680 681
					push_unichar(ch);
					n++;
					ch = get_unichar();
				}
				unget_unichar(ch);
				push_unichar(0);
				want_file = 0;
682
				mcy_lval.str = xunistrdup(get_unichar_stack());
683 684 685 686 687 688 689 690 691 692 693 694 695 696 697
				return tFILE;
			}

			if(char_table[ch] & CH_IDENT)
			{
				token_t *tok;
				while(isisochar(ch) && (char_table[ch] & (CH_IDENT|CH_NUMBER)))
				{
					push_unichar(ch);
					ch = get_unichar();
				}
				unget_unichar(ch);
				push_unichar(0);
				if(!(tok = lookup_token(get_unichar_stack())))
				{
698
					mcy_lval.str = xunistrdup(get_unichar_stack());
699 700 701 702 703 704 705 706 707 708 709 710
					return tIDENT;
				}
				switch(tok->type)
				{
				case tok_keyword:
					return tok->token;

				case tok_language:
					codepage = tok->codepage;
					/* Fall through */
				case tok_severity:
				case tok_facility:
711
					mcy_lval.tok = tok;
712 713 714
					return tTOKEN;

				default:
715
					internal_error(__FILE__, __LINE__, "Invalid token type encountered\n");
716 717 718 719 720
				}
			}

			if(isspace(ch))	/* Ignore space */
				continue;
721

722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742
			if(isdigit(ch))
				return scan_number(ch);
		}

		switch(ch)
		{
		case ':':
		case '=':
		case '+':
		case '(':
		case ')':
			return ch;
		case ';':
			while(ch != '\n' && ch != EOF)
			{
				push_unichar(ch);
				ch = get_unichar();
			}
			newline();
			push_unichar(ch);	/* Include the newline */
			push_unichar(0);
743
			mcy_lval.str = xunistrdup(get_unichar_stack());
744 745
			return tCOMMENT;
		default:
746
			xyyerror("Invalid character '%c' (0x%04x)\n", isisochar(ch) && isprint(ch) ? ch : '.', ch);
747 748 749
		}
	}
}