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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593
|
/*-----------------------------------------------------------------------------
| lex.c
|
| Pilrc lexer
-----------------------------------------------------------------------------*/
/***
bar: April 10, 1999
Add ability to handle nnnLU, nnnL, and nnnU type constants
bar: April 9, 1999
Add ability to handle '1234' type constants
bar: June 11, 1998
Remove GCC warnings
bar: April 22, 1998
Made clean-compile using Borland 4.5(32-bit) C++ and C.
Added more complete C string parsing, including all '\' options, hex, etc.
Max'ed octal character numbers out to 3 digits.
Do C-style comments.
***/
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <ctype.h>
#include <math.h>
#define NOPILOTINC
#include "pilrc.h"
static int wBaseCur = 10;
static char *pchLexBuf;
static char *pchLexPrev;
static char *pchLex;
static char *_pchParseError;
static BOOL _fReportErrors;
BOOL FInitLexer(char *pch, BOOL fMarkErrors)
{
pchLexBuf = pch;
pchLex = pch;
pchLexPrev = pch;
_pchParseError = NULL;
_fReportErrors = fMarkErrors;
return fTrue;
}
#if 0
static char *PchLexer(void)
{
return pchLex;
}
#endif
char *PchLexerPrev(void)
{
return pchLexPrev;
}
VOID ParseError(char *sz1, char *sz2)
{
_pchParseError = PchLexerPrev();
/* if (_fReportErrors) */
ErrorLine2(sz1, sz2);
}
#if 0
static char *PchParseError(void)
{
return _pchParseError;
}
#endif
static BOOL FSkipWhite(void)
{
if (pchLex == NULL)
return fFalse;
while (*pchLex == ' ' || *pchLex == '\t' || *pchLex == '\n' || *pchLex == '\r')
pchLex++;
return(*pchLex != '\000');
}
/*** Allow 12345678LU, for instance (should be only in .h or .hpp?!?) ***/
static void AllowLUAtEndOfConstant(int ch)
{
if ((ch == 'l') || (ch == 'L'))
ch = (BYTE) *pchLex++;
if ((ch == 'u') || (ch == 'U'))
pchLex++;
}
static BOOL FParseHex(LEX *plex, int ch)
{
LEX lex;
ch = tolower(ch);
if ((ch == '0') && ((*(pchLex) == 'x') || (*(pchLex) == 'X')))
{
pchLex++;
ch = *pchLex++;
}
if ((ch >= '0' && ch <= '9') || (ch >= 'a' && ch <= 'f'))
{
lex.lt = ltConst;
lex.val = 0;
while ((ch >= '0' && ch <= '9') || (ch >= 'a' && ch <= 'f'))
{
lex.val *= 16;
if ((ch >= '0' && ch <= '9'))
lex.val += ch-'0';
else
lex.val += ch-'a'+10;
ch = *pchLex++;
ch = tolower(ch);
}
AllowLUAtEndOfConstant(ch);
*plex = lex;
return fTrue;
}
return fFalse;
}
static BOOL FParseConst(LEX *plex, int ch)
{
char *pchStore;
pchStore = plex->szId;
Assert(wBaseCur == 10);
if ((ch >= '0' && ch <= '9') || ch == '.')
{
plex->lt = ltConst;
plex->val = 0;
if ((ch == '0') && ((*(pchLex) == 'x') || (*(pchLex) == 'X')))
{
*pchStore++ = *pchLex++;
*pchStore = (char) ch;
ch = *pchLex++;
return FParseHex(plex, ch);
}
while (ch >= '0' && ch <= '9')
{
plex->val *= 10;
plex->val += ch-'0';
*pchStore++ = (char) ch;
ch = *pchLex++;
}
}
else if (ch == '\'')
{
char szT[2];
int cc;
plex->lt = ltConst;
plex->val = 0;
*pchStore++ = (char) ch;
for (cc = 0; cc < 4; ++cc)
{
ch = (BYTE) *pchLex++;
*pchStore++ = (char) ch;
/*** printf("char=[%c]\n", ch); ***/
if (ch == '\'')
break;
if (ch < ' ')
{
szT[0] = (char) ch;
szT[1] = '\000';
ParseError("Unknown character in '' constant: ", szT);
}
plex->val *= 256;
plex->val += ch; /* high-byte first as a guess */
}
/*** Compensate for when we got a full 4 characters ***/
if (ch != '\'')
ch = (BYTE) *pchLex++;
++pchLex; /* compensate for later -- by caller */
if (ch != '\'')
{
szT[0] = (char) ch;
szT[1] = '\000';
ParseError("Unknown '' constant terminator: ", szT);
}
}
else
{
*pchStore = 0;
return fFalse;
}
/*** Note: 'pchLex' is now one past the character that's in 'ch' - the next character to parse ***/
AllowLUAtEndOfConstant(ch);
*pchStore = 0;
return fTrue;
}
static int ChParseOctal(int ch)
{
int chVal, cnt;
chVal = 0;
/*** Functionality change: 2.01b bar: only three octal chars! ***/
for (cnt = 3; cnt-- && ((ch >= '0') && (ch <= '7')); )
{
chVal *= 8;
chVal += ch-'0';
ch = *pchLex++;
}
pchLex--; /* back off to the non-octal digit */
return chVal;
}
#ifndef _within
#define _within(n, l, h) (((n) >= (l)) && ((n) <= (h)))
#endif
static int hexize(int c)/*** convert hex digit to binary ***/
{
if (_within(c, '0', '9')) return(c - '0');
if (_within(c, 'A', 'F')) return(c - ('A' - 10));
if (_within(c, 'a', 'f')) return(c - ('a' - 10));
return(-1);
}
static int ChParseHex(int ch)
{
int chVal;
chVal = 0;
for (;;)
{
int n;
ch = *pchLex;
n = hexize(ch);
if (n < 0) break;
n += (chVal * 16);
if (n >= 256) break; /* Java's \Uxxxx might take more digits (Unicode alert!!!!) */
++pchLex;
chVal = n;
}
return chVal;
}
static BOOL FParseId(LEX *plex, int ch)
{
LEX lex;
if ((ch >= 'a' && ch <= 'z') || (ch >= 'A' && ch <= 'Z') || ch == '_')
{
/* Identifier */
int cch;
lex.lt = ltId;
cch = 0;
do
{
/* if (ch != '"') */
{
lex.szId[cch] = (char) ch; /* gratuitous cast - Unicode alert!!!! */
cch++;
}
ch = *pchLex++;
if (cch == cchIdMax-1)
{
ParseError("Identifier too long", NULL);
break;
}
}
while ((ch >= 'a' && ch <= 'z') || (ch >= 'A' && ch <= 'Z') || (ch >= '0' && ch <= '9') || ch == '_');
lex.szId[cch] = '\000';
*plex = lex;
return fTrue;
}
return fFalse;
}
/*** Skip to end of C comment, if there is an end - else eat the input ***/
static BOOL FSkipToEndOfCComment(void)
{
while (*pchLex)
{
if ((pchLex[0] == '*') && (pchLex[1] == '/'))
{
pchLex += 2;
return(fTrue);
}
++pchLex;
}
return(fFalse);
}
#define SLT(ch, ltArg) case ch: lex.lt = ltArg; break;
BOOL FGetLex(LEX *plex, BOOL fInComment)
{
int ch;
char szT[2];
LEX lex;
char *pchStore;
lex.lt = plex->lt = ltNil;
pchLexPrev = pchLex;
if (!FSkipWhite())
return fFalse;
if (fInComment)
{
if (!FSkipToEndOfCComment())
lex.lt = ltCComment; /* keep going with it */
else
lex.lt = ltEndCComment; /* ok, the comment is over */
}
else
{
pchStore = lex.szId;
ch = *pchStore++ = *pchLex++;
*pchStore = 0;
switch (ch)
{
/* BUG! could use a lookup table... */
/*TODO logical operators */
SLT('+', ltPlus)
SLT('-', ltMinus)
SLT('*', ltMult)
SLT('%', ltMod)
SLT('(', ltLParen)
SLT(')', ltRParen)
SLT('[', ltLBracket)
SLT(']', ltRBracket)
SLT('{', ltLBrace)
SLT('}', ltRBrace)
SLT(',', ltComma)
SLT('?', ltQuestion)
SLT(':', ltColon)
SLT('^', ltCaret)
SLT('\\', ltBSlash)
SLT('#', ltPound)
SLT('@', ltAt)
SLT(';', ltSemi)
SLT('|', ltPipe)
case '/':
if (*pchLex == '/')
{
*pchStore++ = *pchLex++;
*pchStore = 0;
lex.lt = ltDoubleSlash;
}
else if (*pchLex == '*')
{
if (!FSkipToEndOfCComment())
lex.lt = ltCComment;
else
lex.lt = ltEndCComment; /* return place holder token */
}
else
lex.lt = ltDiv;
break;
case '<':
if (*pchLex == '=')
{
*pchStore++ = *pchLex++;
*pchStore = 0;
lex.lt = ltLTE;
}
else if (*pchLex == '>')
{
*pchStore++ = *pchLex++;
*pchStore = 0;
lex.lt = ltNE;
}
else
lex.lt = ltLT;
break;
case '>':
if (*pchLex++ == '=')
{
*pchStore++ = *pchLex++;
*pchStore = 0;
lex.lt = ltGTE;
}
else
lex.lt = ltGT;
break;
case '=':
if (*pchLex == '=')
{
*pchStore++ = *pchLex++;
*pchStore = 0;
lex.lt = ltEQ;
}
else
lex.lt = ltAssign;
break;
case '"':
lex.lt = ltStr;
pchStore = lex.szId;
while (*pchLex != '"')
{
if (*pchLex == '\\')
{
int ch;
pchLex++;
ch = *pchLex++;
switch (ch)
{
case 'a' :
ch = '\a';
break;
case 'b' :
ch = '\b';
break;
case 'f' :
ch = '\f';
break;
case 'n' :
ch = '\n';
break;
case 'r' :
ch = '\r';
break;
case 't' :
ch = '\t';
break;
case 'v' :
ch = '\v';
break;
case '0' :
case '1' :
case '2' :
case '3' :
case '4' :
case '5' :
case '6' :
case '7' :
ch = ChParseOctal(ch);
break;
case 'x' :
case 'X' :
ch = ChParseHex(ch);
break;
case '\0' : /* handle slash at the end of the line */
ch = '\\';
break;
case 'e' : /* ESC, thank you Richard Brinkerhoff */
ch = '\033';
break;
case 'z' : /* special control z'er */
ch = 'z' & 0x1f;
break;
case '_' : /* special ignore - turns to nothing */
ch = '\0';
break;
}
/*** This program does not handle nulls in strings ***/
if (ch)
*pchStore++ = (char) ch; /* gratuitous cast - Unicode alert!!!! */
}
else
*pchStore++ = *pchLex++;
if (pchStore-lex.szId == cchIdMax-1)
{
ParseError("String too long", NULL);
break;
}
if (*pchLex == 0)
{
ParseError("Unterminated string", NULL);
break;
}
}
pchLex++;
*pchStore = 0;
break;
default:
if (FParseConst(&lex, ch) || FParseId(&lex, ch))
{
/* do nuthin...code is easier to read this way */
}
else
{
szT[0] = (char) ch;
szT[1] = '\000';
ParseError("Unknown character: ", szT);
}
pchLex--;
break;
}
}
*plex = lex;
return lex.lt != ltNil;
}
#define SPLT(lt, sz) case lt: printf(sz); break;
VOID PrintLex(LEX *plex)
{
plex = plex;
#ifdef FOO
switch (plex->lt)
{
case ltConst:
printf("%d ", plex->val);
break;
case ltId:
printf("%s ", plex->szId);
break;
SPLT(ltPlus, "+");
SPLT(ltMinus, "-");
SPLT(ltMult, "*");
SPLT(ltDiv, "/");
SPLT(ltMod, "%");
SPLT(ltLParen, "(");
SPLT(ltRParen, ")");
SPLT(ltLBracket, "[");
SPLT(ltRBracket, "]");
SPLT(ltLBrace, "{");
SPLT(ltRBrace, "}");
SPLT(ltComma, ",");
SPLT(ltLT, "<");
SPLT(ltGT, ">");
SPLT(ltLTE, "<=");
SPLT(ltGTE, ">=");
SPLT(ltNE, "<>");
SPLT(ltEQ, "==");
SPLT(ltAssign, "=");
SPLT(ltQuestion, "?");
SPLT(ltColon, ":");
SPLT(ltCaret, "^");
}
#endif
}
/* eof */
|