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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888
|
/* $Id: forlex.c,v 1.41 2001/11/03 00:55:37 moniot Exp $
Tokenizing routines for Fortran program checker.
*/
/*
Copyright (c) 2001 by Robert K. Moniot.
Permission is hereby granted, free of charge, to any person
obtaining a copy of this software and associated documentation
files (the "Software"), to deal in the Software without
restriction, including without limitation the rights to use,
copy, modify, merge, publish, distribute, sublicense, and/or
sell copies of the Software, and to permit persons to whom the
Software is furnished to do so, subject to the following
conditions:
The above copyright notice and this permission notice shall be
included in all copies or substantial portions of the
Software.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY
KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE
WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR
PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR
COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
Acknowledgement: the above permission notice is what is known
as the "MIT License."
*/
#include <stdio.h>
#include <ctype.h>
#include <string.h>
/* Some older mac compilers need compat.h to use memset. If
needed, add `` -d MAC_MPW '' to compilation options.
*/
#ifdef MAC_MPW
#include <compat.h>
#endif
#include "ftnchek.h"
#define FORLEX
#include "symtab.h"
#include "tokdefs.h"
#include "forlex.h"
extern int complex_const_allowed, /* shared flags operated by fortran.y */
inside_format,
integer_context;
PROTO(PRIVATE void make_legal_char,( char *s ));
/*
Part I. yylex()
Shared functions defined:
yylex() Returns next token. Called from yyparse().
implied_id_token(t,s) Creates token for blank common declaration.
get_binary_const(t, c ) Creates token for binary constant
get_string(t) Creates token for a string
Note: compilation options LEX_STORE_STRINGS and LEX_STORE_HOLLERITHS:
Define the macro name LEX_STORE_STRINGS to build a version of ftnchek that
stores string constants, and LEX_STORE_HOLLERITHS to store hollerith
constants. Now that INCLUDE statements are supported, strings must
be stored. Holleriths are not used, so they need not be stored.
*/
#ifndef LEX_STORE_STRINGS
#define LEX_STORE_STRINGS
#endif
#ifdef DEBUG_FORLEX /* For maintaining the program */
#define LEX_STORE_HOLLERITHS
#endif
#ifdef DEBUG_FORLEX
#include <math.h> /* Only used for pow() in debug mode */
#endif
PRIVATE int closeup_saw_whitespace;
/* The following macro says whether a given character is legal,
* i.e. one of the stream control chars or a valid ANSI Fortran
* character. Lower case letters are considered legal too.
* Nondigits in columns 1-6 (except EOF,EOS) are illegal in fixed form.
* Hopefully this works for EBCDIC too.
*/
#define islegal(C) ( ((C) == EOF) || ((C) == EOS) || \
( (col_num >= 6 || free_form || isdigit(C)) && \
(toascii((int)(C)) >= toascii(' ') && \
toascii((int)(C)) <= toascii('z') && \
legal_chars[toascii((int)(C))-toascii(' ')] == (C))) )
/* Array has x where ASCII character is not valid.
This defn is not exactly standard f77, since it includes
supported extensions: $ in format,
<> in variable formats, and " in strings.
*/
PRIVATE char f77_legal_chars[]=
" x\"x$xx'()*+,-./0123456789:x<=>xx\
ABCDEFGHIJKLMNOPQRSTUVWXYZxxxxxxabcdefghijklmnopqrstuvwxyzxxxxx";
/* This is the working copy of list of legal chars, with
< any chars in idletter_list made legal.
*/
PRIVATE char legal_chars[sizeof(f77_legal_chars)];
/* Routine to fix up list of legal chars */
void make_legal_char_list(VOID)
{
int i;
/* Start with the f77 list */
(void)strcpy(legal_chars,f77_legal_chars);
/* Verify idletter_list has only punctuation chars.
If violators, reset to default of "$_"
*/
for(i=0; idletter_list[i] != '\0'; i++) {
if( !ispunct(idletter_list[i]) ) {
(void)fprintf(stderr,
"\n%cidentifier setting specifies invalid character %c: setting ignored",
#ifdef OPTION_PREFIX_SLASH
'/',
#else
'-',
#endif
idletter_list[i]);
idletter_list = DEF_IDLETTER_LIST; /* restore to default */
break;
}
}
/* Add nonstd nonalpha chars allowed in identifiers */
make_legal_char(idletter_list);
}
/* Routines to alter the default status of characters,
to support various extensions to f77. */
PRIVATE void
#if HAVE_STDC
make_legal_char(char *s)
#else /* K&R style */
make_legal_char(s)
char *s; /* List of legal chars */
#endif /* HAVE_STDC */
{
int i;
while( *s != '\0' ) {
i = toascii((int)(*s));
if(i >= toascii(' ') && i <= toascii('~')) {
legal_chars[i-' '] = *s;
}
s++;
}
}
#if 0
/* Routines to alter the default status of characters,
to support various extensions to f77. Not used now.*/
PROTO(void make_illegal_char,( char *s ));
void
make_illegal_char(s)
char *s; /* List of illegal chars */
{
int i;
while( *s != '\0' ) {
i = toascii((int)(*s));
if(i >= toascii(' ') && i <= toascii('~')) {
legal_chars[i-toascii(' ')] = ( (*s != 'x')? 'x': 'X');
}
s++;
}
}
#endif
/* local functions defined */
PROTO(PRIVATE void closeup,( void ));
PROTO(PRIVATE void get_complex_const,( Token *token ));
#ifdef ALLOW_UNIX_CPP
PROTO(PRIVATE void get_cpp_directive,( void ));
#endif
PROTO(PRIVATE void get_dot,( Token *token ));
PROTO(PRIVATE void get_dotted_keyword,( Token *token));
PROTO(PRIVATE void get_edit_descriptor,( Token *token ));
PROTO(PRIVATE void get_hollerith,( Token *token, int n ));
PROTO(PRIVATE void get_illegal_token,( Token *token ));
PROTO(PRIVATE void get_label,( Token *token ));
PROTO(PRIVATE void get_letter,( Token *token ));
PROTO(PRIVATE void get_number,( Token *token ));
PROTO(PRIVATE void get_punctuation,( Token *token ));
PROTO(PRIVATE void get_simple_punctuation,( Token *token ));
PROTO(PRIVATE int f90_relop, ( Token *token, int *multichar ) );
/* Gets next token for Yacc. Return value is token.class,
* and a copy of the token is stored in yylval.
*/
int
yylex(VOID)
{
Token token;
extern int in_attrbased_typedecl; /* shared with fortran.y */
/* Initialize token fields to scratch. */
#if HAVE_MEMSET
(void)memset(&token,0,sizeof(token));
#else
#if HAVE_BZERO
bzero((char *)&token,sizeof(token));
#else
token = (Token){0}; /* If neither one, hope compiler likes this */
#endif
#endif
src_text_len = 0;
if(curr_char == EOF) {
token.tclass = EOF;
token.line_num = line_num;
token.col_num = col_num;
}
else /* not EOF */ {
/* Skip leading spaces, and give error message if non-ANSI
* characters are found.
*/
while(iswhitespace(curr_char) || (! islegal(curr_char)) ) {
if(!iswhitespace(curr_char)) {
#ifdef ALLOW_UNIX_CPP
if(curr_char == '#' && col_num == 1) {
get_cpp_directive(); /* turn # line into EOS */
break;
}
else
#endif
lex_error("Illegal character");
}
advance();
}
token.line_num = line_num;
token.col_num = col_num;
closeup_saw_whitespace = FALSE;
if(inside_format) { /* Handle format stuff here to avoid trouble */
get_edit_descriptor(&token);
}
else if(isadigit(curr_char)) {
/* Identify label:
Fixed form: Number in cols 1-5.
Free form: Number at start of statement.
*/
if( (free_form)? (initial_flag && !in_attrbased_typedecl): (col_num < 6))
get_label(&token); /* Stmt label */
else
get_number(&token); /* Numeric or hollerith const */
}
else if(isidletter(curr_char)) {
if(implicit_letter_flag)
get_letter(&token); /* letter in IMPLICIT list */
else
get_identifier(&token); /* Identifier or keyword */
}
else if(isaquote(curr_char)) {
get_string(&token); /* Quoted string */
}
else if(curr_char == '.') {
get_dot(&token); /* '.' lead-in */
}
else {
get_punctuation(&token); /* Punctuation character or EOS */
}
}/*end not EOF*/
if(token.tclass == EOS) {
implicit_flag=FALSE; /* in case of errors, reset flags */
implicit_letter_flag = FALSE;
}
prev_token_class = token.tclass;
yylval = token;
return token.tclass;
} /* yylex */
/* closeup: Advances input stream till next_char is nonspace. Fudges
things so that curr_char remains as it was.
*/
PRIVATE void
closeup(VOID)
{
int
save_curr_char = curr_char,
save_prev_char = prev_char;
LINENO_t
save_line_num = line_num;
COLNO_t
save_col_num = col_num;
int next_space = iswhitespace(next_char);
closeup_saw_whitespace = next_space; /* Record for free-format warnings */
while(next_space) {
advance();
next_space = iswhitespace(next_char);
}
curr_char = save_curr_char;
prev_char = save_prev_char;
line_num = save_line_num;
col_num = save_col_num;
}
/* Fills argument with token for an identifer, as if an identifer
* with name given by string s had been lexed. This will
* be called by parser when blank common declaration is seen,
* and when a main prog without program statement is found,
* and when an unnamed block data statement is found,
* so processing of named and unnamed cases can be handled uniformly.
*/
void
#if HAVE_STDC
implied_id_token(Token *t, char *s)
#else /* K&R style */
implied_id_token(t,s)
Token *t;
char *s;
#endif /* HAVE_STDC */
{
int h;
unsigned long hnum;
hnum = hash(s);
while( h=hnum%HASHSZ, hashtab[h].name != NULL &&
strcmp(hashtab[h].name,s) != 0)
hnum = rehash(hnum);
if(hashtab[h].name == NULL) { /* not seen before */
hashtab[h].name = s;
hashtab[h].loc_symtab = NULL;
hashtab[h].glob_symtab = NULL;
hashtab[h].com_loc_symtab = NULL;
hashtab[h].com_glob_symtab = NULL;
}
t->tclass = tok_identifier;
t->value.integer = h;
t->src_text = new_src_text("",0);
} /* implied_id_token */
#ifdef ALLOW_UNIX_CPP
/* This does not create a token but just performs the
actions needed when a cpp directive is seen. It
advances curr_char to the EOS. The setting of
filename is delayed to this point because it is not
stored in tokens but is external, so changing it
must wait till the previous statement is fully
parsed and any error messages printed and arg or
com list headers completed.
*/
PRIVATE void
get_cpp_directive(VOID)
{
if(next_filename != (char *)NULL) {
/* A #line directive on first line of toplevel source file
gives name of real original file. Replace our idea
of top_filename with that. But ignore an initial
# 1 "" since that means cpp was working with stdin,
probably from ftnpp. Likewise ignore # 1 "stdin"
which is a variant form, e.g. from fpp.
*/
if( cpp_start_of_file ) {
if( next_filename[0] != '\0' &&
strcmp(next_filename,"stdin") != 0 ) {
top_filename = next_filename;
current_filename = next_filename;
cpp_start_of_file = FALSE;
}
}
else {
if( cpp_inc_depth > 0 &&
next_filename == cpp_include_stack[cpp_inc_depth-1].filename ) {
--cpp_inc_depth;
}
else {
if( cpp_inc_depth == 0 ) {
top_file_line_num = next_top_file_line_num;
}
/* Avoid overrun, but it will recover
even if max depth is exceeded.
*/
if(cpp_inc_depth < MAX_INCLUDE_DEPTH)
cpp_include_stack[cpp_inc_depth++].filename = current_filename;
}
current_filename = next_filename;
}
}
do { /* Skip to end of directive. It will become an EOS */
advance();
} while( curr_char != EOS);
if(f77_unix_cpp || f90_unix_cpp || !cpp_handled) {
nonstandard(line_num,col_num,f90_unix_cpp,0);
msg_tail(": preprocessor directive");
if(!cpp_handled)
msg_tail("(not processed)");
}
}/*get_cpp_directive*/
#endif
PRIVATE void
#if HAVE_STDC
get_dot(Token *token)
#else /* K&R style */
get_dot(token)
Token *token;
#endif /* HAVE_STDC */
{
if(src_text_len < MAX_SRC_TEXT)
src_text_buf[src_text_len++] = curr_char;
closeup(); /* Advance till nonspace char in next_char */
if(isadigit(next_char))
get_number(token); /* Numeric const */
else if(isaletter(next_char))
get_dotted_keyword(token); /* .EQ. etc. */
else
get_simple_punctuation(token); /* "." out of place */
}
PRIVATE const struct {
char *name;
int tclass,tsubclass;
} dotted_keywords[]={
{".EQ.",tok_relop,relop_EQ},
{".NE.",tok_relop,relop_NE},
{".LE.",tok_relop,relop_LE},
{".LT.",tok_relop,relop_LT},
{".GE.",tok_relop,relop_GE},
{".GT.",tok_relop,relop_GT},
{".AND.",tok_AND,0},
{".OR.",tok_OR,0},
{".NOT.",tok_NOT,0},
{".FALSE.",tok_logical_const,FALSE},
{".TRUE.",tok_logical_const,TRUE},
{".EQV.",tok_EQV,0},
{".NEQV.",tok_NEQV,0},
{NULL,0,0}
};
PRIVATE void
#if HAVE_STDC
get_dotted_keyword(Token *token)
#else /* K&R style */
get_dotted_keyword(token)
Token *token;
#endif /* HAVE_STDC */
{
int i,
has_embedded_space, /* Spaces inside keyword */
space_seen_lately; /* Flag for catching embedded space */
initial_flag = FALSE;
/* Watch for embedded space, but not
(in fixed form)
between dots and letters of keyword.
I.e. ". eq ." is OK, but not ".e q." */
has_embedded_space = FALSE;
bi_advance(); /* gobble the initial '.' */
space_seen_lately = (!free_form? FALSE:
closeup_saw_whitespace);
while(isaletter(curr_char)) {
if(src_text_len < MAX_SRC_TEXT)
src_text_buf[src_text_len++] = (char)makeupper(curr_char);
if(space_seen_lately)
has_embedded_space = TRUE;
bi_advance();
space_seen_lately = iswhitespace(prev_char);
}
/* Free form complains about space before last dot */
if(free_form && space_seen_lately)
has_embedded_space = TRUE;
if(src_text_len < MAX_SRC_TEXT)
src_text_buf[src_text_len++] = '.'; /* make it complete */
if(curr_char != '.') {
lex_error("Badly formed logical/relational operator or constant");
}
else {
advance(); /* gobble the final '.' */
}
if( (pretty_extra_space || (free_form && f90_freeform_space))
&& has_embedded_space) {
space_violation(token->line_num,token->col_num,
"keyword has embedded space");
}
for(i=0; dotted_keywords[i].name != NULL; i++) {
if(strncmp(src_text_buf+1, /* only compare the significant parts */
dotted_keywords[i].name+1,
src_text_len-2) == 0) {
token->tclass = dotted_keywords[i].tclass;
token->tsubclass = dotted_keywords[i].tsubclass;
token->value.string = token->src_text = dotted_keywords[i].name;
#ifdef DEBUG_FORLEX
if(debug_lexer)
(void)fprintf(list_fd,"\nDotted keyword:\t\t%s",
token->src_text);
#endif
return;
}
}
/* Match not found: signal an error */
lex_error("Unknown logical/relational operator or constant");
get_illegal_token(token);
} /* get_dotted_keyword */
PRIVATE void
#if HAVE_STDC
get_edit_descriptor(Token *token)
#else /* K&R style */
get_edit_descriptor(token)
Token *token;
#endif /* HAVE_STDC */
{
int c;
long repeat_spec;
int Ee_allowed=FALSE; /* true if edit descr can have Ee after w.d */
if(isadigit(curr_char)) { /* Digit: repeat spec or holl or kP or nX */
repeat_spec = 0;
do {
if(src_text_len < MAX_SRC_TEXT)
src_text_buf[src_text_len++] = curr_char;
repeat_spec = repeat_spec*10L + (long)BCD(curr_char);
if( makeupper(next_char) == 'H' )
inside_hollerith = TRUE;/* get ready for hollerith*/
bi_advance();
} while(isadigit(curr_char));
if( makeupper(curr_char) == 'H' ) {
/* nH... pass off to hollerith routine */
get_hollerith(token, (int)repeat_spec);
return;
}
else {
/* Otherwise it is a repeat spec or the
numeric part of kP or nX which we treat
as repeat specs too */
token->tclass = tok_integer_const;
token->value.integer = repeat_spec;
token->src_text = new_src_text(src_text_buf,src_text_len);
#ifdef DEBUG_FORLEX
if(debug_lexer)
(void)fprintf(list_fd,"\nInteger const:\t\t%ld (from %s)",
repeat_spec,
token->src_text);
#endif
}
}/* end if digit */
else if(isaletter(curr_char)) {
c = makeupper(curr_char);
if(src_text_len < MAX_SRC_TEXT)
src_text_buf[src_text_len++] = c;
bi_advance();
switch(c) {
case 'P': /* P of kP k seen previously */
if(prev_token_class != tok_integer_const) {
if(f77_format_extensions || f90_format_extensions){
nonstandard(token->line_num,token->col_num,f90_format_extensions,0);
msg_tail(": P must follow a number");
}
}
break;
case 'X': /* X or nX */
break;
case 'S': /* S or SP or SS */
c = makeupper(curr_char);
if(c == 'S' || c == 'P') {
if(src_text_len < MAX_SRC_TEXT)
src_text_buf[src_text_len++] = c;
bi_advance();
}
break;
case 'B': /* BN or BZ */
c = makeupper(curr_char);
if(c == 'N' || c == 'Z') {
if(src_text_len < MAX_SRC_TEXT)
src_text_buf[src_text_len++] = c;
bi_advance();
}
else {
if(f77_format_extensions){
nonstandard(token->line_num,token->col_num,0,0);
msg_tail(": N or Z expected after B");
}
goto get_w_d; /* F90 has Bw.d: allow that */
}
break;
case 'T': /* Tc or TLc or TRc */
c = makeupper(curr_char);
if(c == 'L' || c == 'R') {
if(src_text_len < MAX_SRC_TEXT)
src_text_buf[src_text_len++] = c;
bi_advance();
}
case 'E': /* In F90, E can be followed by N or S */
c = makeupper(curr_char);
if( c == 'N' || c == 'S' ) {
if(src_text_len < MAX_SRC_TEXT)
src_text_buf[src_text_len++] = c;
bi_advance();
if(f77_format_extensions){
nonstandard(token->line_num,token->col_num,0,0);
}
}
Ee_allowed = TRUE;
goto get_w_d;
case 'O': /* These are OK in f90 but not f77 */
case 'Z':
if(f77_format_extensions){
nonstandard(token->line_num,token->col_num,0,0);
}
goto get_w_d;
/* Iw, Fw.c and similar forms */
case 'G':
Ee_allowed = TRUE; /* OK in F90 to have Ee trailer */
/*FALLTHRU*/
case 'A':
case 'D':
case 'F':
case 'I':
case 'L':
get_w_d: /* Get the w field if any */
while( isadigit(curr_char) ){
if(src_text_len < MAX_SRC_TEXT)
src_text_buf[src_text_len++] = curr_char;
bi_advance();
}
/* Include any dot followed by number (e.g. F10.5)
*/
if( curr_char == '.' ) {
do {
if(src_text_len < MAX_SRC_TEXT)
src_text_buf[src_text_len++] = curr_char;
bi_advance();
} while( isadigit(curr_char) );
}
/* w.d can sometimes be followed by Ee */
if( Ee_allowed && (c=makeupper(curr_char)) == 'E' ) {
if(src_text_len < MAX_SRC_TEXT)
src_text_buf[src_text_len++] = c;
bi_advance();
while( isadigit(curr_char) ){
if(src_text_len < MAX_SRC_TEXT)
src_text_buf[src_text_len++] = curr_char;
bi_advance();
}
}
break;
default:
if(f77_format_extensions || f90_format_extensions) {
nonstandard(token->line_num,token->col_num,f90_format_extensions,0);
msg_tail(": edit descriptor");
src_text_buf[src_text_len++] = '\0';
msg_tail(src_text_buf);
}
goto get_w_d;
}/*end switch*/
token->tclass = tok_edit_descriptor;
token->value.string = NULL;
token->src_text = new_src_text(src_text_buf,src_text_len);
#ifdef DEBUG_FORLEX
if(debug_lexer)
(void)fprintf(list_fd,"\nEdit descriptor:\t%s",token->src_text);
#endif
}/*end else if isaletter*/
/* Apostrophe or quote mark means a string. */
else if( isaquote(curr_char) ) {
get_string(token);
}
/* Otherwise it is mere punctuation. Handle
it here ourself to avoid complications. */
else {
src_text_buf[src_text_len++] = curr_char;
get_simple_punctuation(token);
}
}
PRIVATE void
#if HAVE_STDC
get_hollerith(Token *token, int n) /* Gets string of form nHaaaa */
#else /* K&R style */
get_hollerith(token,n) /* Gets string of form nHaaaa */
Token *token;
int n;
#endif /* HAVE_STDC */
{
int i;
LINENO_t last_line_num;
COLNO_t last_col_num;
/* strsize = length of only the string being defined
fullsize = length of whole hollerith const, which includes
length spec already stored in src_text_buf plus the
H plus the text plus final nul. */
int strsize=n,
leadin=src_text_len+1,
fullsize=leadin+strsize+1;
char *s;
initial_flag = FALSE;
s = new_src_text_alloc(fullsize);
for(i=0; i<src_text_len; i++) /* Copy the leadin already saved */
s[i] = src_text_buf[i];
s[i++] = 'H'; /* store the 'H' */
if(n==1)
inside_hollerith=FALSE;/* turn off flag ahead of next_char */
advance();/* Gobble the 'H' */
last_col_num = col_num;
last_line_num = line_num;
for(i=0; i<n; i++) {
while(curr_char == EOL) {
/* Treat short line as if extended with blanks */
COLNO_t col;
for(col=last_col_num; i<n && col<(COLNO_t)max_stmt_col; i++,col++) {
s[leadin+i] = ' ';
}
last_col_num = col_num;
advance();
}
if(i==n) break;
if(curr_char == EOS || curr_char == EOF) {
COLNO_t col;
for(col=last_col_num; i<n && col<(COLNO_t)max_stmt_col; i++,col++) {
if(i < strsize)
s[leadin+i] = ' ';
}
if(i < n) { /* If it did not fill up */
syntax_error((LINENO_t)last_line_num,(COLNO_t)last_col_num,
"Hollerith constant ends prematurely");
strsize=i;
}
break;
}
else {
s[leadin+i] = curr_char;
last_col_num = col_num;
last_line_num = line_num;
if(i==n-2)/* turn flag off ahead of next_char*/
inside_hollerith = FALSE;
advance();
}
}
if(strsize > 0)
s[leadin+strsize] = '\0';
inside_hollerith = FALSE;
token->tclass = tok_hollerith;
token->value.string = s + leadin;
token->size = n;
token->src_text = s;
#ifdef DEBUG_FORLEX
if(debug_lexer)
(void)fprintf(list_fd,"\nHollerith:\t\t%s (from %s)",
token->value.string,
token->src_text);
#endif
} /* get_hollerith */
PRIVATE void
#if HAVE_STDC
get_illegal_token(Token *token) /* Handle an illegal input situation */
#else /* K&R style */
get_illegal_token(token) /* Handle an illegal input situation */
Token *token;
#endif /* HAVE_STDC */
{
token->tclass = tok_illegal;
token->src_text = new_src_text("",0);
#ifdef DEBUG_FORLEX
if(debug_lexer)
(void)fprintf(list_fd,"\nILLEGAL TOKEN");
#endif
} /* get_illegal_token */
/* Read a label from label field. */
PRIVATE void
#if HAVE_STDC
get_label(Token *token)
#else /* K&R style */
get_label(token)
Token *token;
#endif /* HAVE_STDC */
{
int value=0;
int space_seen=FALSE, has_embedded_space=FALSE;
if( !free_form ) {
while( isadigit(curr_char) && col_num < 6 ) {
if(space_seen)
has_embedded_space = TRUE;
value = value*10 + BCD(curr_char);
src_text_buf[src_text_len++] = curr_char;
advance();
while(curr_char==' ' && col_num < 6) {
space_seen = TRUE;
advance();
}
}
if((pretty_extra_space || (free_form && f90_freeform_space))
&& has_embedded_space) {
space_violation(token->line_num,token->col_num,
"label has embedded space");
}
}
else { /* free form */
int numdigits=0;
while( isadigit(curr_char) ) {
value = value*10 + BCD(curr_char);
if(src_text_len < MAX_SRC_TEXT)
src_text_buf[src_text_len++] = curr_char;
++numdigits;
advance();
}
/* label can have only up to 5 digits */
if( numdigits > 5 && misc_warn) {
syntax_error(token->line_num,token->col_num,
"statement label exceeds 5 digits");
}
}
token->tclass = tok_label;
token->value.integer = value;
token->src_text = new_src_text(src_text_buf,src_text_len);
#ifdef DEBUG_FORLEX
if(debug_lexer)
(void)fprintf(list_fd,"\nLabel:\t\t\t%d (from %s)",
value,
token->src_text);
#endif
} /* get_label */
PRIVATE void
#if HAVE_STDC
get_letter(Token *token) /* Gets letter in IMPLICIT list */
#else /* K&R style */
get_letter(token) /* Gets letter in IMPLICIT list */
Token *token;
#endif /* HAVE_STDC */
{
token->tclass = tok_letter;
token->tsubclass = src_text_buf[src_text_len++] = makeupper(curr_char);
token->src_text = new_src_text(src_text_buf,src_text_len);
#ifdef DEBUG_FORLEX
if(debug_lexer)
(void)fprintf(list_fd,"\nLetter:\t\t\t%s",token->src_text);
#endif
advance();
} /* get_letter */
/* get_number reads a number and determines data type: integer,
* real, or double precision.
*/
/* This belongs in ftnchek.h, perhaps. Defines number of significant
figures that are reasonable for a single-precision real constant.
Works out to 9 for wordsize=4, 21 for wordsize=8. These allow
for a couple of extra digits for rounding. Used in -trunc warning. */
#define REAL_SIGFIGS (local_wordsize==0? 8: (local_wordsize-1)*3)
PRIVATE int getting_complex_const=FALSE;
PRIVATE void
#if HAVE_STDC
get_number(Token *token)
#else /* K&R style */
get_number(token)
Token *token;
#endif /* HAVE_STDC */
{
DBLVAL dvalue,leftside,rightside,pwr_of_ten;
int exponent,datatype,c;
#ifdef DEBUG_FORLEX
int expsign;
#endif
int numdigits, /* Count of digits in integer, significant or not */
sigfigs; /* Count of significant digits */
/* For freeform warnings, this gets set when we
arrive here via a leading '.', otherwise is false.
*/
int space_seen_lately = closeup_saw_whitespace;
int has_embedded_space = FALSE;
initial_flag = FALSE;
leftside = (DBLVAL)0;
numdigits = sigfigs = 0;
datatype = tok_integer_const;
while(isadigit(curr_char)) {
if(space_seen_lately)
has_embedded_space = TRUE;
leftside = leftside*(DBLVAL)10 + (DBLVAL)BCD(curr_char);
++numdigits;
/* Do not count leading zeroes as significant */
if(sigfigs > 0 || curr_char != '0')
++sigfigs;
if( !integer_context && makeupper(next_char) == 'H' )
inside_hollerith = TRUE;/* get ready for hollerith*/
if(src_text_len < MAX_SRC_TEXT)
src_text_buf[src_text_len++] = curr_char;
/* Embedded space is worth preserving since
it is often used in long numbers. Any
amount of blanks + tabs -> 1 blank.
Exception: integer_context says upcoming
item is a label or datatype length spec. */
if(! integer_context &&
(next_char == ' ' || next_char == '\t')) {
if(src_text_len < MAX_SRC_TEXT)
src_text_buf[src_text_len++] = ' ';
}
bi_advance();
space_seen_lately = iswhitespace(prev_char);
}
/* If context specifies integer expected, skip to end.
Otherwise scan on ahead for more. */
if( integer_context) {
if(numdigits == 0) {
lex_error("integer expected");
advance(); /* gobble something to avoid infinite loop */
}
}
else {/* not integer_context */
if( makeupper(curr_char) == 'H' ){ /* nnH means hollerith */
if(leftside == (DBLVAL)0) {
lex_error("Zero-length hollerith constant");
inside_hollerith = FALSE;
advance();
get_illegal_token(token);
}
else {
if(src_text_buf[src_text_len-1] == ' ')
--src_text_len;
get_hollerith(token, (int)leftside);
}
return;
}
rightside = (DBLVAL)0;
pwr_of_ten = (DBLVAL)1;
closeup(); /* Pull in the lookahead character */
if( curr_char == '.' &&
/* don't be fooled by 1.eq.N or
I.eq.1.and. etc */
!looking_at_relop() ) {
datatype = tok_real_const;
if( space_seen_lately )
has_embedded_space = TRUE;
if(numdigits > 0) /* if dot is initial it is already stored */
if(src_text_len < MAX_SRC_TEXT)
src_text_buf[src_text_len++] = curr_char;
bi_advance();
space_seen_lately = closeup_saw_whitespace || iswhitespace(prev_char);
closeup_saw_whitespace = FALSE;
while(isadigit(curr_char)) {
if( space_seen_lately )
has_embedded_space = TRUE;
rightside = rightside*(DBLVAL)10 + (DBLVAL)BCD(curr_char);
++numdigits; /* not used past here, but maintain it anyway */
if(sigfigs > 0 || curr_char != '0')
++sigfigs;
pwr_of_ten /= (DBLVAL)10;
if(src_text_len < MAX_SRC_TEXT)
src_text_buf[src_text_len++] = curr_char;
if(next_char == ' ' || next_char == '\t')
if(src_text_len < MAX_SRC_TEXT)
src_text_buf[src_text_len++] = ' ';
bi_advance();
space_seen_lately = iswhitespace(prev_char);
}
}
#ifdef DEBUG_FORLEX
if(debug_lexer)
dvalue = leftside + rightside*pwr_of_ten;
else
#endif
dvalue = (DBLVAL)0;
exponent = 0;
#ifdef DEBUG_FORLEX
expsign = 1;
#endif
/* Integer followed by E or D gives a real/d.p constant.
We also accept Q for quad (real*16) constants. */
space_seen_lately = space_seen_lately || closeup_saw_whitespace;
if( ( (c = makeupper(curr_char)) == 'E' || c == 'D' || c == 'Q') )
{
datatype = ((c == 'E')? tok_real_const:
((c == 'D')? tok_dp_const:
tok_quad_const));
if( space_seen_lately )
has_embedded_space = TRUE;
if(src_text_len < MAX_SRC_TEXT)
src_text_buf[src_text_len++] = c;
bi_advance();
space_seen_lately = iswhitespace(prev_char);
if(curr_char == '+') {
#ifdef DEBUG_FORLEX
expsign = 1;
#endif
if(src_text_len < MAX_SRC_TEXT)
src_text_buf[src_text_len++] = curr_char;
bi_advance();
space_seen_lately = space_seen_lately || iswhitespace(prev_char);
}
else if(curr_char == '-') {
#ifdef DEBUG_FORLEX
expsign = -1;
#endif
if( iswhitespace(prev_char) )
has_embedded_space = TRUE;
if(src_text_len < MAX_SRC_TEXT)
src_text_buf[src_text_len++] = curr_char;
bi_advance();
space_seen_lately = space_seen_lately || iswhitespace(prev_char);
}
if(!isadigit(curr_char)) {
lex_error("Badly formed real constant");
}
else while(isadigit(curr_char)) {
if( space_seen_lately )
has_embedded_space = TRUE;
exponent = exponent*10 + (curr_char-'0');
if(src_text_len < MAX_SRC_TEXT)
src_text_buf[src_text_len++] = curr_char;
bi_advance();
space_seen_lately = iswhitespace(prev_char);
}
/* Compute real value only if debugging. If it exceeds max magnitude,
computing it may cause crash. At this time, value of real const
is not used for anything. */
#ifdef DEBUG_FORLEX
if(debug_lexer)
dvalue *= pow(10.0, (double)(exponent*expsign));
else
#endif
dvalue = (DBLVAL)0;
}
}/* end if(!integer_context) */
if(src_text_buf[src_text_len-1] == ' ') /* remove any trailing blank */
--src_text_len;
token->tclass = datatype;
/* If this is part of complex const,
do not store src_text but arrange
so debugging works. */
if(!getting_complex_const) {
token->src_text = new_src_text(src_text_buf,src_text_len);
}
#ifdef DEBUG_FORLEX
else {
src_text_buf[src_text_len] = '\0';
token->src_text = src_text_buf;
}
#endif
if( free_form && (pretty_extra_space || f90_freeform_space)
&& has_embedded_space ) {
space_violation(token->line_num,token->col_num,
"Numeric constant has embedded space");
}
switch(datatype) {
case tok_integer_const:
token->value.integer = (long)leftside;
#ifdef DEBUG_FORLEX
if(debug_lexer)
(void)fprintf(list_fd,"\nInteger const:\t\t%ld (from %s)",
token->value.integer,
token->src_text);
#endif
break;
case tok_real_const:
/* store single as double lest it overflow */
token->value.dbl = dvalue;
if(trunc_sigfigs && sigfigs >= REAL_SIGFIGS) {
warning(token->line_num,token->col_num,
"Single-precision real constant has more digits than are stored");
}
#ifdef DEBUG_FORLEX
if(debug_lexer)
(void)fprintf(list_fd,"\nReal const:\t\t%g (from %s)",
(double)token->value.dbl,
token->src_text);
#endif
break;
case tok_dp_const:
token->value.dbl = dvalue;
#ifdef DEBUG_FORLEX
if(debug_lexer)
(void)fprintf(list_fd,"\nDouble const:\t\t%g (from %s)",
(double)token->value.dbl,
token->src_text);
#endif
break;
case tok_quad_const:
/* store quad as double in case host doesn't do quad */
token->value.dbl = dvalue;
#ifdef DEBUG_FORLEX
if(debug_lexer)
(void)fprintf(list_fd,"\nQuad const:\t\t%g (from %s)",
(double)token->value.dbl,
token->src_text);
#endif
break;
}
} /* get_number */
/* get_complex_constant reads an entity of the form (num,num)
where num is any [signed] numeric constant. It will only be
called when looking_at() has guaranteed that there is one there.
The token receives the real part as a number. The imaginary part
is not stored. Whitespace is allowed between ( and num, around
the comma, and between num and ) but not within num. */
PRIVATE void
#if HAVE_STDC
get_complex_const(Token *token)
#else /* K&R style */
get_complex_const(token)
Token *token;
#endif /* HAVE_STDC */
{
Token imag_part; /* temporary to hold imag part */
#ifdef DEBUG_FORLEX
double sign=(DBLVAL)1;
#endif
int dble_size=FALSE; /* flag to set if parts are D floats */
int imag_dble_size; /* if imaginary part D float */
LINENO_t comma_line_num;
COLNO_t comma_col_num;
getting_complex_const = TRUE;
initial_flag = FALSE;
bi_advance(); /* skip over the initial paren (already stored) */
if(curr_char == '+' || curr_char == '-') {
#ifdef DEBUG_FORLEX
if(curr_char == '-') sign = (DBLVAL)(-1);
#endif
if(src_text_len < MAX_SRC_TEXT)
src_text_buf[src_text_len++] = curr_char;
bi_advance();
}
#ifdef DEBUG_FORLEX
if(debug_lexer){
(void)fprintf(list_fd,"\nComplex const:(");
if(sign < 0.0) (void)fprintf(list_fd," -");
}
#endif
closeup_saw_whitespace = FALSE;
get_number(token);
switch((short)token->tclass) {
case tok_integer_const:
#ifdef DEBUG_FORLEX
if(debug_lexer)
token->value.dbl = sign*(double)token->value.integer;
else
#endif
token->value.dbl = (DBLVAL)0;
break;
case tok_dp_const:
dble_size=TRUE;
/*FALLTHRU*/
case tok_real_const:
#ifdef DEBUG_FORLEX
if(debug_lexer)
token->value.dbl = sign*token->value.dbl;
else
#endif
token->value.dbl = (DBLVAL)0;
break;
}
while(iswhitespace(curr_char))
advance();
comma_line_num = line_num;
comma_col_num = col_num;
if(src_text_len < MAX_SRC_TEXT)
src_text_buf[src_text_len++] = curr_char;
if(next_char == ' ' || next_char == '\t') /* preserve space after , */
if(src_text_len < MAX_SRC_TEXT)
src_text_buf[src_text_len++] = ' ';
bi_advance(); /* skip over the comma */
if(curr_char == '+' || curr_char == '-') {
#ifdef DEBUG_FORLEX
if(curr_char == '-') sign = (DBLVAL)(-1);
#endif
if(src_text_len < MAX_SRC_TEXT)
src_text_buf[src_text_len++] = curr_char;
bi_advance();
}
#ifdef DEBUG_FORLEX
if(debug_lexer){
(void)fprintf(list_fd,"\n,");
if(sign < 0.0) (void)fprintf(list_fd," -");
}
#endif
closeup_saw_whitespace = FALSE;
get_number(&imag_part);
imag_dble_size = (imag_part.tclass == tok_dp_const);
if(dble_size != imag_dble_size) {
warning(comma_line_num,comma_col_num,
"different precision in real and imaginary parts");
}
else if(f77_double_complex) {
if(dble_size)
warning(token->line_num,token->col_num,
"nonstandard double precision complex constant");
}
dble_size = (dble_size || imag_dble_size);
while(iswhitespace(curr_char))
advance();
if(src_text_len < MAX_SRC_TEXT)
src_text_buf[src_text_len++] = curr_char;
advance(); /* skip over final paren */
if(dble_size)
token->tclass = tok_dcomplex_const;
else
token->tclass = tok_complex_const;
token->src_text = new_src_text(src_text_buf,src_text_len);
#ifdef DEBUG_FORLEX
if(debug_lexer) {
(void)fprintf(list_fd,"\n\t\t\tsource text=%s",
token->src_text);
(void)fprintf(list_fd,"\n)");
}
#endif
getting_complex_const = FALSE;
}
#ifdef ALLOW_TYPELESS_CONSTANTS
/* Routine to get constants of the forms:
B'nnnn' (f90std) 'nnnn'B (nonf90) -- binary
O'nnnn' (f90std) 'nnnn'O (nonf90) -- octal
Z'nnnn' (f90std) X'nnnn' 'nnnn'X 'nnnn'Z (nonf90) -- hex
No check of whether digits are less than base.
Warning is issued here instead of in parser since constant
looks like a normal integer by the time the parser sees it.
*/
void
get_binary_const(Token *token, int c, int space_seen_lately)
/* c is base character: madeupper'ed by caller */
{
long value=0;
int base,digit;
int badly_formed=FALSE;
int i,j; /* indices in src_text_buf for repacking */
if(c == 'O') base = 8;
else if(c == 'X' || c == 'Z') base = 16;
else if(c == 'B') base = 2;
else {
syntax_error(token->line_num,token->col_num,
"Unknown base for typeless constant -- octal assumed");
base = 8;
}
/* F90 allows initial B, O, Z but not X */
if( c == 'X' && f90_typeless_constants ) {
nonstandard(token->line_num,token->col_num,f90_typeless_constants,0);
}
/* Advance i to starting digit */
i = 0;
while( ! isaquote(src_text_buf[i]) ) {
++i;
}
j = ++i; /* Input = Output to start */
/* Scan the string, moving chars down
to change multi spaces to single
blanks, and converting digits. */
while( ! isaquote(src_text_buf[i]) ) {
digit=src_text_buf[i++];
if( ishex(digit) ){
value = value*base + HEX(digit);
src_text_buf[j++] = digit;
}
else { /* Anything else should be space */
if( isspace(digit) ) {
if( free_form )
space_seen_lately = TRUE; /* blanks not OK in free form */
src_text_buf[j++] = ' ';
while( isspace(src_text_buf[i]) ) {
++i;
}
}
else {
badly_formed = TRUE;
}
}
}
if( badly_formed ) {
syntax_error(token->line_num,token->col_num,
"badly formed typeless constant");
}
else if((pretty_extra_space || (free_form && f90_freeform_space))
&& space_seen_lately) {
space_violation(token->line_num,token->col_num,
"typeless constant has embedded space");
}
while(i < src_text_len)
src_text_buf[j++] = src_text_buf[i++]; /* Copy the rest over */
src_text_len = j;
token->tclass = tok_integer_const;
token->value.integer = value;
token->src_text = new_src_text(src_text_buf,src_text_len);
if(f77_typeless_constants) {
nonstandard(token->line_num,token->col_num,0,0);
}
#ifdef DEBUG_FORLEX
if(debug_lexer)
(void)fprintf(list_fd,"\nInteger const:\t\t%ld (from %s)",
token->value.integer,
token->src_text);
#endif
}/*get_binary_const*/
#endif/*ALLOW_TYPELESS_CONSTANTS*/
PRIVATE void
#if HAVE_STDC
get_punctuation(Token *token)
#else /* K&R style */
get_punctuation(token)
Token *token;
#endif /* HAVE_STDC */
{
int multichar, /* Flags To catch spaces inside multi-char token */
space_seen_lately;
extern int in_attrbased_typedecl; /* shared with fortran.y */
multichar = FALSE;
src_text_buf[src_text_len++] = curr_char;
/* If lexing attr-based type decl, turn off the flag when
the double colon is reached...
*/
if( in_attrbased_typedecl && curr_char == ':' ) {
in_attrbased_typedecl = FALSE;
}
/* ...whereas turn initial_flag back on if a comma is found. */
if( in_attrbased_typedecl && curr_char == ',' ) {
initial_flag = TRUE;
}
if( !in_attrbased_typedecl )
initial_flag = FALSE;
space_seen_lately = iswhitespace(next_char);
closeup();
if(curr_char == '*' && next_char == '*') {
token->tclass = tok_power;
multichar = TRUE;
advance();
src_text_buf[src_text_len++] = curr_char;
}
else if(curr_char == '/' && next_char == '/' ) {
/* If this is COMMON / / list, then embedded space is OK */
if( prev_token_class == tok_COMMON ) {
space_seen_lately = FALSE;
}
/* Otherwise it is concatenation operator */
else {
extern int in_assignment_stmt;
/* for obscure rule check */
if(in_assignment_stmt)
make_true(IN_ASSIGN,token->TOK_flags);
}
token->tclass = tok_concat;
multichar = TRUE;
advance();
src_text_buf[src_text_len++] = curr_char;
}
/* recognize F90 rel-ops here */
else if( f90_relop(token,&multichar) ) {
token->tclass = tok_relop;
if(f77_relops) {
nonstandard(token->line_num,token->col_num,0,0);
msg_tail("for relational operator");
}
}
/* paren can be the start of complex constant if everything
is just right. Maybe more tests needed here. */
else if(complex_const_allowed && curr_char == '(' &&
( (prev_token_class<256 && ispunct(prev_token_class))
|| prev_token_class == tok_relop
|| prev_token_class == tok_power )
&& looking_at_cplx()) {
get_complex_const(token);
return;
}
else {
/* Provide special left parenthesis to avoid s/r
conflict in grammar.
*/
if( need_special_lparen ) {
/* ASSERT ( curr_char == '(' ) */
token->tclass = tok_lparen;
need_special_lparen = FALSE;
}
else {
token->tclass = curr_char;
}
}
token->src_text = new_src_text(src_text_buf,src_text_len);
if((pretty_extra_space || (free_form && f90_freeform_space))
&& multichar && space_seen_lately) {
space_violation(token->line_num,token->col_num,
"multi-character operator has embedded space");
}
advance();
#ifdef DEBUG_FORLEX
if(debug_lexer) {
if(token->tclass == EOS)
(void)fprintf(list_fd,"\n\t\t\tEOS");
else {
(void)fprintf(list_fd,"\nPunctuation:\t\t");
if(token->tclass == tok_lparen)
(void)fprintf(list_fd,"special ");
(void)fprintf(list_fd,"%s",token->src_text);
}
}
#endif
} /* get_punctuation */
PRIVATE void
#if HAVE_STDC
get_simple_punctuation(Token *token)
#else /* K&R style */
get_simple_punctuation(token)
Token *token;
#endif /* HAVE_STDC */
{
/* Like get_punctuation but lacks special cases. Just
gets the punctuation character. Text is already in
src_text_buf. */
token->tclass = curr_char;
token->src_text = new_src_text(src_text_buf,src_text_len);
advance();
#ifdef DEBUG_FORLEX
if(debug_lexer) {
if(token->tclass == EOS)
(void)fprintf(list_fd,"\n\t\t\tEOS");
else
(void)fprintf(list_fd,"\nPunctuation:\t\t%s",token->src_text);
}
#endif
} /* get_simple_punctuation */
PRIVATE int
#if HAVE_STDC
f90_relop(Token *token, int *multichar)
#else /* K&R style */
f90_relop(token, multichar)
Token *token;
int *multichar;
#endif /* HAVE_STDC */
{
*multichar = FALSE;
if( curr_char == '>' ) {
if( next_char == '=' ) {
token->tsubclass = relop_GE;
token->src_text = ">=";
goto twochar_relop;
}
else {
token->tsubclass = relop_GT;
token->value.string = ">";
return TRUE;
}
}
if( curr_char == '<' ) {
if( next_char == '=' ) {
token->tsubclass = relop_LE;
token->value.string = "<=";
goto twochar_relop;
}
else {
token->tsubclass = relop_LT;
token->value.string = "<";
return TRUE;
}
}
if( curr_char == '=' && next_char == '=' ) {
token->tsubclass = relop_EQ;
token->value.string = "==";
goto twochar_relop;
}
if( curr_char == '/' && next_char == '=' ) {
token->tsubclass = relop_NE;
token->value.string = "/=";
goto twochar_relop;
}
return FALSE;
/* Two-character relops: need to gobble 2nd char */
twochar_relop:
*multichar = TRUE;
advance();
src_text_buf[src_text_len++] = curr_char;
return TRUE;
}
void
#if HAVE_STDC
get_string(Token *token) /* Gets string of form 'aaaa' */
#else /* K&R style */
get_string(token) /* Gets string of form 'aaaa' */
Token *token;
#endif /* HAVE_STDC */
{
int len;
COLNO_t last_col_num;
int has_backslash = FALSE; /* for portability check */
quote_char = curr_char; /* remember the delimiter */
initial_flag = FALSE;
inside_string = TRUE;
last_col_num=col_num;
src_text_buf[src_text_len++] = curr_char; /* store leading quote */
advance(); /* Gobble leading quote */
len = 0;
for(;;) {
while(curr_char == EOL) {
/* Fixed form: treat short line as if extended with
blanks to 72 columns. Free form: line ends at EOL */
if( ! free_form ) {
COLNO_t col;
for(col=last_col_num; col<(COLNO_t)max_stmt_col; col++) {
if(src_text_len < MAX_SRC_TEXT)
src_text_buf[src_text_len++] = ' ';
++len;
}
}
last_col_num=col_num;
advance();
}
if(curr_char == EOS || curr_char == EOF) {
lex_error("Closing quote missing from string");
break;
}
if(curr_char == quote_char) {
inside_string = FALSE;/* assume so for now */
/* If LEX_RAWSTRINGS defined, stores doubled quotes and final quote.
Otherwise initial quote is stored and doubled quotes are reduced to one. */
#ifdef LEX_RAWSTRINGS
/* Store the quote */
if(src_text_len < MAX_SRC_TEXT)
src_text_buf[src_text_len++] = curr_char;
#endif
/* Handle possible continuation */
if(next_char == EOL &&
(free_form || col_num == (COLNO_t)max_stmt_col))
advance();
last_col_num=col_num;
advance();
if(curr_char == quote_char){/* '' becomes ' in string */
inside_string = TRUE; /* not a closing quote */
if(src_text_len < MAX_SRC_TEXT)
src_text_buf[src_text_len++] = curr_char;
++len;
last_col_num=col_num;
advance();
}
else {
break; /* It was a closing quote after all */
}
}
else { /* ordinary character within quotes */
int value=curr_char;
if(curr_char == '\\') {
if(!has_backslash) {/* only warn once per string */
if(port_backslash)
nonportable(line_num,col_num,
"backslash treated incompatibly by some compilers");
}
has_backslash = TRUE;
#ifdef ALLOW_UNIX_BACKSLASH /* This has problems: undigesting
a string gets complicated. */
if(source_unix_backslash) {
if(f77_unix_backslash || f90_unix_backslash) {
nonstandard(line_num,col_num,f90_unix_backslash,0);
msg_tail(": backslash escape sequence");
}
#ifdef LEX_RAWSTRINGS
/* Store the backslash */
if(src_text_len < MAX_SRC_TEXT)
src_text_buf[src_text_len++] = curr_char;
#endif
inside_string = FALSE;/* so inline_comment works */
advance(); /* gobble the backslash */
inside_string = TRUE;
#ifdef LEX_RAWSTRINGS
value = curr_char;
#else /* !LEX_RAWSTRINGS*/
if(isadigit(curr_char)) { /* \octal digits */
value = BCD(curr_char);
while(isadigit(next_char)) {
advance();
value = value*8 + BCD(curr_char);
}
}
else if(curr_char == 'x') {
advance(); /* gobble the 'x' */
value = HEX(curr_char);
while(ishex(next_char)) {
advance();
value = value*16 + HEX(curr_char);
}
}/* end if octal or hex */
else switch(curr_char) {
#if __STDC__ + 0
case 'a': value = '\a'; break; /* alarm */
#else
case 'a': value = '\007'; break; /* alarm */
#endif
case 'b': value = '\b'; break; /* backspace */
case 'f': value = '\f'; break; /* formfeed */
case 'n': value = '\n'; break; /* newline */
case 'r': value = '\r'; break; /* carr return */
case 't': value = '\t'; break; /* h tab */
case 'v': value = '\v'; break; /* v tab */
case EOS: value = '\n'; break; /* a no-no */
/* All others: \c --> c */
default: value = curr_char; break;
}
#endif /* !LEX_RAWSTRINGS*/
}/* end if source_unix_backslash */
#endif /*ALLOW_UNIX_BACKSLASH*/
}/* end if curr_char == backslash */
if(src_text_len < MAX_SRC_TEXT)
src_text_buf[src_text_len++] = value;
++len;
last_col_num=col_num;
advance();
}
}
#ifdef ALLOW_TYPELESS_CONSTANTS
/* Watch for const like 'nnn'X */
if(!inside_format) {
int space_seen_lately = iswhitespace(curr_char);
while(iswhitespace(curr_char))
advance();
if(isaletter(curr_char)) {
int c=makeupper(curr_char);
#ifndef LEX_RAWSTRINGS
if(src_text_len < MAX_SRC_TEXT)
src_text_buf[src_text_len++] = quote_char;
#endif
if(src_text_len < MAX_SRC_TEXT)
src_text_buf[src_text_len++] = c;
advance(); /* Gobble the base character */
/* F90 does not allow forms 'ddd'[BOZ].
Suppress message here if letter is not in [BOZ]
since that gets a warning in get_binary_const
*/
if( f90_typeless_constants && (c=='Z' || c=='O' || c=='B') ) {
nonstandard(token->line_num,token->col_num,f90_typeless_constants,0);
}
get_binary_const(token,c,space_seen_lately);
return;
}
}
#endif /*ALLOW_TYPELESS_CONSTANTS*/
if(len == 0) {
warning(line_num,col_num,
"Zero-length string not allowed\n");
len = 1;
}
if(quote_char != '\'') { /* Warn if quote is used instead of apost */
if(f77_quotemarks) {
nonstandard(token->line_num,token->col_num,0,0);
msg_tail(": character string should be delimited by apostrophes");
}
}
inside_string = FALSE;
token->tclass = tok_string;
token->size = len;
token->src_text = new_src_text(src_text_buf,src_text_len);
#ifdef LEX_RAWSTRINGS
token->value.string = token->src_text; /* Includes the initial quote */
#else
token->value.string = token->src_text+1; /* Skips the initial quote */
#endif
/* Under -port warn if char size > 255 */
if(port_long_string) {
if(len > 255)
nonportable(line_num,col_num,
"character constant length exceeds 255");
}
#ifdef DEBUG_FORLEX
if(debug_lexer
&& src_text_buf[0] == quote_char) { /* skip if doing X'nnnn' */
(void)fprintf(list_fd,"\nString:\t\t\t%s",token->value.string);
(void)fprintf(list_fd,"\n\t\t(from\t%s)",token->src_text);
}
#endif
} /* get_string */
/* This routine is called when -pretty=extra-space or
missing-space are in effect, or when in free form
mode. It figures out the right kind of warning to issue.
*/
void space_violation( LINENO_t lineno, COLNO_t colno, const char *s )
{
if(free_form && f90_freeform_space) {
syntax_error(lineno,colno,s);
}
else {
ugly_code(lineno,colno,s);
}
}
/* End of Forlex module */
|