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
|
/* This is the Assembler Pre-Processor
Copyright (C) 1987-2018 Free Software Foundation, Inc.
This file is part of GAS, the GNU Assembler.
GAS is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation; either version 3, or (at your option)
any later version.
GAS 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 General Public
License for more details.
You should have received a copy of the GNU General Public License
along with GAS; see the file COPYING. If not, write to the Free
Software Foundation, 51 Franklin Street - Fifth Floor, Boston, MA
02110-1301, USA. */
/* Modified by Allen Wirfs-Brock, Instantiations Inc 2/90. */
/* App, the assembler pre-processor. This pre-processor strips out
excess spaces, turns single-quoted characters into a decimal
constant, and turns the # in # <number> <filename> <garbage> into a
.linefile. This needs better error-handling. */
#include "as.h"
#if (__STDC__ != 1)
#ifndef const
#define const /* empty */
#endif
#endif
#ifdef H_TICK_HEX
int enable_h_tick_hex = 0;
#endif
#ifdef TC_M68K
/* Whether we are scrubbing in m68k MRI mode. This is different from
flag_m68k_mri, because the two flags will be affected by the .mri
pseudo-op at different times. */
static int scrub_m68k_mri;
/* The pseudo-op which switches in and out of MRI mode. See the
comment in do_scrub_chars. */
static const char mri_pseudo[] = ".mri 0";
#else
#define scrub_m68k_mri 0
#endif
#if defined TC_ARM && defined OBJ_ELF
/* The pseudo-op for which we need to special-case `@' characters.
See the comment in do_scrub_chars. */
static const char symver_pseudo[] = ".symver";
static const char * symver_state;
#endif
#ifdef TC_ARM
static char last_char;
#endif
static char lex[256];
static const char symbol_chars[] =
"$._ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789";
#define LEX_IS_SYMBOL_COMPONENT 1
#define LEX_IS_WHITESPACE 2
#define LEX_IS_LINE_SEPARATOR 3
#define LEX_IS_COMMENT_START 4
#define LEX_IS_LINE_COMMENT_START 5
#define LEX_IS_TWOCHAR_COMMENT_1ST 6
#define LEX_IS_STRINGQUOTE 8
#define LEX_IS_COLON 9
#define LEX_IS_NEWLINE 10
#define LEX_IS_ONECHAR_QUOTE 11
#ifdef TC_V850
#define LEX_IS_DOUBLEDASH_1ST 12
#endif
#ifdef TC_M32R
#define DOUBLEBAR_PARALLEL
#endif
#ifdef DOUBLEBAR_PARALLEL
#define LEX_IS_DOUBLEBAR_1ST 13
#endif
#define LEX_IS_PARALLEL_SEPARATOR 14
#ifdef H_TICK_HEX
#define LEX_IS_H 15
#endif
#define IS_SYMBOL_COMPONENT(c) (lex[c] == LEX_IS_SYMBOL_COMPONENT)
#define IS_WHITESPACE(c) (lex[c] == LEX_IS_WHITESPACE)
#define IS_LINE_SEPARATOR(c) (lex[c] == LEX_IS_LINE_SEPARATOR)
#define IS_PARALLEL_SEPARATOR(c) (lex[c] == LEX_IS_PARALLEL_SEPARATOR)
#define IS_COMMENT(c) (lex[c] == LEX_IS_COMMENT_START)
#define IS_LINE_COMMENT(c) (lex[c] == LEX_IS_LINE_COMMENT_START)
#define IS_NEWLINE(c) (lex[c] == LEX_IS_NEWLINE)
static int process_escape (int);
/* FIXME-soon: The entire lexer/parser thingy should be
built statically at compile time rather than dynamically
each and every time the assembler is run. xoxorich. */
void
do_scrub_begin (int m68k_mri ATTRIBUTE_UNUSED)
{
const char *p;
int c;
lex[' '] = LEX_IS_WHITESPACE;
lex['\t'] = LEX_IS_WHITESPACE;
lex['\r'] = LEX_IS_WHITESPACE;
lex['\n'] = LEX_IS_NEWLINE;
lex[':'] = LEX_IS_COLON;
#ifdef TC_M68K
scrub_m68k_mri = m68k_mri;
if (! m68k_mri)
#endif
{
lex['"'] = LEX_IS_STRINGQUOTE;
#if ! defined (TC_HPPA)
lex['\''] = LEX_IS_ONECHAR_QUOTE;
#endif
#ifdef SINGLE_QUOTE_STRINGS
lex['\''] = LEX_IS_STRINGQUOTE;
#endif
}
/* Note: if any other character can be LEX_IS_STRINGQUOTE, the loop
in state 5 of do_scrub_chars must be changed. */
/* Note that these override the previous defaults, e.g. if ';' is a
comment char, then it isn't a line separator. */
for (p = symbol_chars; *p; ++p)
lex[(unsigned char) *p] = LEX_IS_SYMBOL_COMPONENT;
for (c = 128; c < 256; ++c)
lex[c] = LEX_IS_SYMBOL_COMPONENT;
#ifdef tc_symbol_chars
/* This macro permits the processor to specify all characters which
may appears in an operand. This will prevent the scrubber from
discarding meaningful whitespace in certain cases. The i386
backend uses this to support prefixes, which can confuse the
scrubber as to whether it is parsing operands or opcodes. */
for (p = tc_symbol_chars; *p; ++p)
lex[(unsigned char) *p] = LEX_IS_SYMBOL_COMPONENT;
#endif
/* The m68k backend wants to be able to change comment_chars. */
#ifndef tc_comment_chars
#define tc_comment_chars comment_chars
#endif
for (p = tc_comment_chars; *p; p++)
lex[(unsigned char) *p] = LEX_IS_COMMENT_START;
for (p = line_comment_chars; *p; p++)
lex[(unsigned char) *p] = LEX_IS_LINE_COMMENT_START;
#ifndef tc_line_separator_chars
#define tc_line_separator_chars line_separator_chars
#endif
for (p = tc_line_separator_chars; *p; p++)
lex[(unsigned char) *p] = LEX_IS_LINE_SEPARATOR;
#ifdef tc_parallel_separator_chars
/* This macro permits the processor to specify all characters which
separate parallel insns on the same line. */
for (p = tc_parallel_separator_chars; *p; p++)
lex[(unsigned char) *p] = LEX_IS_PARALLEL_SEPARATOR;
#endif
/* Only allow slash-star comments if slash is not in use.
FIXME: This isn't right. We should always permit them. */
if (lex['/'] == 0)
lex['/'] = LEX_IS_TWOCHAR_COMMENT_1ST;
#ifdef TC_M68K
if (m68k_mri)
{
lex['\''] = LEX_IS_STRINGQUOTE;
lex[';'] = LEX_IS_COMMENT_START;
lex['*'] = LEX_IS_LINE_COMMENT_START;
/* The MRI documentation says '!' is LEX_IS_COMMENT_START, but
then it can't be used in an expression. */
lex['!'] = LEX_IS_LINE_COMMENT_START;
}
#endif
#ifdef TC_V850
lex['-'] = LEX_IS_DOUBLEDASH_1ST;
#endif
#ifdef DOUBLEBAR_PARALLEL
lex['|'] = LEX_IS_DOUBLEBAR_1ST;
#endif
#ifdef TC_D30V
/* Must do this is we want VLIW instruction with "->" or "<-". */
lex['-'] = LEX_IS_SYMBOL_COMPONENT;
#endif
#ifdef H_TICK_HEX
if (enable_h_tick_hex)
{
lex['h'] = LEX_IS_H;
lex['H'] = LEX_IS_H;
}
#endif
}
/* Saved state of the scrubber. */
static int state;
static int old_state;
static const char *out_string;
static char out_buf[20];
static int add_newlines;
static char *saved_input;
static size_t saved_input_len;
static char input_buffer[32 * 1024];
static const char *mri_state;
static char mri_last_ch;
/* Data structure for saving the state of app across #include's. Note that
app is called asynchronously to the parsing of the .include's, so our
state at the time .include is interpreted is completely unrelated.
That's why we have to save it all. */
struct app_save
{
int state;
int old_state;
const char * out_string;
char out_buf[sizeof (out_buf)];
int add_newlines;
char * saved_input;
size_t saved_input_len;
#ifdef TC_M68K
int scrub_m68k_mri;
#endif
const char * mri_state;
char mri_last_ch;
#if defined TC_ARM && defined OBJ_ELF
const char * symver_state;
#endif
#ifdef TC_ARM
char last_char;
#endif
};
char *
app_push (void)
{
struct app_save *saved;
saved = XNEW (struct app_save);
saved->state = state;
saved->old_state = old_state;
saved->out_string = out_string;
memcpy (saved->out_buf, out_buf, sizeof (out_buf));
saved->add_newlines = add_newlines;
if (saved_input == NULL)
saved->saved_input = NULL;
else
{
saved->saved_input = XNEWVEC (char, saved_input_len);
memcpy (saved->saved_input, saved_input, saved_input_len);
saved->saved_input_len = saved_input_len;
}
#ifdef TC_M68K
saved->scrub_m68k_mri = scrub_m68k_mri;
#endif
saved->mri_state = mri_state;
saved->mri_last_ch = mri_last_ch;
#if defined TC_ARM && defined OBJ_ELF
saved->symver_state = symver_state;
#endif
#ifdef TC_ARM
saved->last_char = last_char;
#endif
/* do_scrub_begin() is not useful, just wastes time. */
state = 0;
saved_input = NULL;
add_newlines = 0;
return (char *) saved;
}
void
app_pop (char *arg)
{
struct app_save *saved = (struct app_save *) arg;
/* There is no do_scrub_end (). */
state = saved->state;
old_state = saved->old_state;
out_string = saved->out_string;
memcpy (out_buf, saved->out_buf, sizeof (out_buf));
add_newlines = saved->add_newlines;
if (saved->saved_input == NULL)
saved_input = NULL;
else
{
gas_assert (saved->saved_input_len <= sizeof (input_buffer));
memcpy (input_buffer, saved->saved_input, saved->saved_input_len);
saved_input = input_buffer;
saved_input_len = saved->saved_input_len;
free (saved->saved_input);
}
#ifdef TC_M68K
scrub_m68k_mri = saved->scrub_m68k_mri;
#endif
mri_state = saved->mri_state;
mri_last_ch = saved->mri_last_ch;
#if defined TC_ARM && defined OBJ_ELF
symver_state = saved->symver_state;
#endif
#ifdef TC_ARM
last_char = saved->last_char;
#endif
free (arg);
}
/* @@ This assumes that \n &c are the same on host and target. This is not
necessarily true. */
static int
process_escape (int ch)
{
switch (ch)
{
case 'b':
return '\b';
case 'f':
return '\f';
case 'n':
return '\n';
case 'r':
return '\r';
case 't':
return '\t';
case '\'':
return '\'';
case '"':
return '\"';
default:
return ch;
}
}
/* This function is called to process input characters. The GET
parameter is used to retrieve more input characters. GET should
set its parameter to point to a buffer, and return the length of
the buffer; it should return 0 at end of file. The scrubbed output
characters are put into the buffer starting at TOSTART; the TOSTART
buffer is TOLEN bytes in length. The function returns the number
of scrubbed characters put into TOSTART. This will be TOLEN unless
end of file was seen. This function is arranged as a state
machine, and saves its state so that it may return at any point.
This is the way the old code used to work. */
size_t
do_scrub_chars (size_t (*get) (char *, size_t), char *tostart, size_t tolen)
{
char *to = tostart;
char *toend = tostart + tolen;
char *from;
char *fromend;
size_t fromlen;
int ch, ch2 = 0;
/* Character that started the string we're working on. */
static char quotechar;
/*State 0: beginning of normal line
1: After first whitespace on line (flush more white)
2: After first non-white (opcode) on line (keep 1white)
3: after second white on line (into operands) (flush white)
4: after putting out a .linefile, put out digits
5: parsing a string, then go to old-state
6: putting out \ escape in a "d string.
7: no longer used
8: no longer used
9: After seeing symbol char in state 3 (keep 1white after symchar)
10: After seeing whitespace in state 9 (keep white before symchar)
11: After seeing a symbol character in state 0 (eg a label definition)
-1: output string in out_string and go to the state in old_state
-2: flush text until a '*' '/' is seen, then go to state old_state
#ifdef TC_V850
12: After seeing a dash, looking for a second dash as a start
of comment.
#endif
#ifdef DOUBLEBAR_PARALLEL
13: After seeing a vertical bar, looking for a second
vertical bar as a parallel expression separator.
#endif
#ifdef TC_PREDICATE_START_CHAR
14: After seeing a predicate start character at state 0, looking
for a predicate end character as predicate.
15: After seeing a predicate start character at state 1, looking
for a predicate end character as predicate.
#endif
#ifdef TC_Z80
16: After seeing an 'a' or an 'A' at the start of a symbol
17: After seeing an 'f' or an 'F' in state 16
#endif
*/
/* I added states 9 and 10 because the MIPS ECOFF assembler uses
constructs like ``.loc 1 20''. This was turning into ``.loc
120''. States 9 and 10 ensure that a space is never dropped in
between characters which could appear in an identifier. Ian
Taylor, ian@cygnus.com.
I added state 11 so that something like "Lfoo add %r25,%r26,%r27" works
correctly on the PA (and any other target where colons are optional).
Jeff Law, law@cs.utah.edu.
I added state 13 so that something like "cmp r1, r2 || trap #1" does not
get squashed into "cmp r1,r2||trap#1", with the all important space
between the 'trap' and the '#1' being eliminated. nickc@cygnus.com */
/* This macro gets the next input character. */
#define GET() \
(from < fromend \
? * (unsigned char *) (from++) \
: (saved_input = NULL, \
fromlen = (*get) (input_buffer, sizeof input_buffer), \
from = input_buffer, \
fromend = from + fromlen, \
(fromlen == 0 \
? EOF \
: * (unsigned char *) (from++))))
/* This macro pushes a character back on the input stream. */
#define UNGET(uch) (*--from = (uch))
/* This macro puts a character into the output buffer. If this
character fills the output buffer, this macro jumps to the label
TOFULL. We use this rather ugly approach because we need to
handle two different termination conditions: EOF on the input
stream, and a full output buffer. It would be simpler if we
always read in the entire input stream before processing it, but
I don't want to make such a significant change to the assembler's
memory usage. */
#define PUT(pch) \
do \
{ \
*to++ = (pch); \
if (to >= toend) \
goto tofull; \
} \
while (0)
if (saved_input != NULL)
{
from = saved_input;
fromend = from + saved_input_len;
}
else
{
fromlen = (*get) (input_buffer, sizeof input_buffer);
if (fromlen == 0)
return 0;
from = input_buffer;
fromend = from + fromlen;
}
while (1)
{
/* The cases in this switch end with continue, in order to
branch back to the top of this while loop and generate the
next output character in the appropriate state. */
switch (state)
{
case -1:
ch = *out_string++;
if (*out_string == '\0')
{
state = old_state;
old_state = 3;
}
PUT (ch);
continue;
case -2:
for (;;)
{
do
{
ch = GET ();
if (ch == EOF)
{
as_warn (_("end of file in comment"));
goto fromeof;
}
if (ch == '\n')
PUT ('\n');
}
while (ch != '*');
while ((ch = GET ()) == '*')
;
if (ch == EOF)
{
as_warn (_("end of file in comment"));
goto fromeof;
}
if (ch == '/')
break;
UNGET (ch);
}
state = old_state;
UNGET (' ');
continue;
case 4:
ch = GET ();
if (ch == EOF)
goto fromeof;
else if (ch >= '0' && ch <= '9')
PUT (ch);
else
{
while (ch != EOF && IS_WHITESPACE (ch))
ch = GET ();
if (ch == '"')
{
quotechar = ch;
state = 5;
old_state = 3;
PUT (ch);
}
else
{
while (ch != EOF && ch != '\n')
ch = GET ();
state = 0;
PUT (ch);
}
}
continue;
case 5:
/* We are going to copy everything up to a quote character,
with special handling for a backslash. We try to
optimize the copying in the simple case without using the
GET and PUT macros. */
{
char *s;
ptrdiff_t len;
for (s = from; s < fromend; s++)
{
ch = *s;
if (ch == '\\'
|| ch == quotechar
|| ch == '\n')
break;
}
len = s - from;
if (len > toend - to)
len = toend - to;
if (len > 0)
{
memcpy (to, from, len);
to += len;
from += len;
if (to >= toend)
goto tofull;
}
}
ch = GET ();
if (ch == EOF)
{
/* This buffer is here specifically so
that the UNGET below will work. */
static char one_char_buf[1];
as_warn (_("end of file in string; '%c' inserted"), quotechar);
state = old_state;
from = fromend = one_char_buf + 1;
fromlen = 1;
UNGET ('\n');
PUT (quotechar);
}
else if (ch == quotechar)
{
state = old_state;
PUT (ch);
}
#ifndef NO_STRING_ESCAPES
else if (ch == '\\')
{
state = 6;
PUT (ch);
}
#endif
else if (scrub_m68k_mri && ch == '\n')
{
/* Just quietly terminate the string. This permits lines like
bne label loop if we haven't reach end yet. */
state = old_state;
UNGET (ch);
PUT ('\'');
}
else
{
PUT (ch);
}
continue;
case 6:
state = 5;
ch = GET ();
switch (ch)
{
/* Handle strings broken across lines, by turning '\n' into
'\\' and 'n'. */
case '\n':
UNGET ('n');
add_newlines++;
PUT ('\\');
continue;
case EOF:
as_warn (_("end of file in string; '%c' inserted"), quotechar);
PUT (quotechar);
continue;
case '"':
case '\\':
case 'b':
case 'f':
case 'n':
case 'r':
case 't':
case 'v':
case 'x':
case 'X':
case '0':
case '1':
case '2':
case '3':
case '4':
case '5':
case '6':
case '7':
break;
default:
#ifdef ONLY_STANDARD_ESCAPES
as_warn (_("unknown escape '\\%c' in string; ignored"), ch);
#endif
break;
}
PUT (ch);
continue;
#ifdef DOUBLEBAR_PARALLEL
case 13:
ch = GET ();
if (ch != '|')
abort ();
/* Reset back to state 1 and pretend that we are parsing a
line from just after the first white space. */
state = 1;
PUT ('|');
#ifdef TC_TIC6X
/* "||^" is used for SPMASKed instructions. */
ch = GET ();
if (ch == EOF)
goto fromeof;
else if (ch == '^')
PUT ('^');
else
UNGET (ch);
#endif
continue;
#endif
#ifdef TC_Z80
case 16:
/* We have seen an 'a' at the start of a symbol, look for an 'f'. */
ch = GET ();
if (ch == 'f' || ch == 'F')
{
state = 17;
PUT (ch);
}
else
{
state = 9;
break;
}
/* Fall through. */
case 17:
/* We have seen "af" at the start of a symbol,
a ' here is a part of that symbol. */
ch = GET ();
state = 9;
if (ch == '\'')
/* Change to avoid warning about unclosed string. */
PUT ('`');
else if (ch != EOF)
UNGET (ch);
break;
#endif
}
/* OK, we are somewhere in states 0 through 4 or 9 through 11. */
/* flushchar: */
ch = GET ();
#ifdef TC_PREDICATE_START_CHAR
if (ch == TC_PREDICATE_START_CHAR && (state == 0 || state == 1))
{
state += 14;
PUT (ch);
continue;
}
else if (state == 14 || state == 15)
{
if (ch == TC_PREDICATE_END_CHAR)
{
state -= 14;
PUT (ch);
ch = GET ();
}
else
{
PUT (ch);
continue;
}
}
#endif
recycle:
#if defined TC_ARM && defined OBJ_ELF
/* We need to watch out for .symver directives. See the comment later
in this function. */
if (symver_state == NULL)
{
if ((state == 0 || state == 1) && ch == symver_pseudo[0])
symver_state = symver_pseudo + 1;
}
else
{
/* We advance to the next state if we find the right
character. */
if (ch != '\0' && (*symver_state == ch))
++symver_state;
else if (*symver_state != '\0')
/* We did not get the expected character, or we didn't
get a valid terminating character after seeing the
entire pseudo-op, so we must go back to the beginning. */
symver_state = NULL;
else
{
/* We've read the entire pseudo-op. If this is the end
of the line, go back to the beginning. */
if (IS_NEWLINE (ch))
symver_state = NULL;
}
}
#endif /* TC_ARM && OBJ_ELF */
#ifdef TC_M68K
/* We want to have pseudo-ops which control whether we are in
MRI mode or not. Unfortunately, since m68k MRI mode affects
the scrubber, that means that we need a special purpose
recognizer here. */
if (mri_state == NULL)
{
if ((state == 0 || state == 1)
&& ch == mri_pseudo[0])
mri_state = mri_pseudo + 1;
}
else
{
/* We advance to the next state if we find the right
character, or if we need a space character and we get any
whitespace character, or if we need a '0' and we get a
'1' (this is so that we only need one state to handle
``.mri 0'' and ``.mri 1''). */
if (ch != '\0'
&& (*mri_state == ch
|| (*mri_state == ' '
&& lex[ch] == LEX_IS_WHITESPACE)
|| (*mri_state == '0'
&& ch == '1')))
{
mri_last_ch = ch;
++mri_state;
}
else if (*mri_state != '\0'
|| (lex[ch] != LEX_IS_WHITESPACE
&& lex[ch] != LEX_IS_NEWLINE))
{
/* We did not get the expected character, or we didn't
get a valid terminating character after seeing the
entire pseudo-op, so we must go back to the
beginning. */
mri_state = NULL;
}
else
{
/* We've read the entire pseudo-op. mips_last_ch is
either '0' or '1' indicating whether to enter or
leave MRI mode. */
do_scrub_begin (mri_last_ch == '1');
mri_state = NULL;
/* We continue handling the character as usual. The
main gas reader must also handle the .mri pseudo-op
to control expression parsing and the like. */
}
}
#endif
if (ch == EOF)
{
if (state != 0)
{
as_warn (_("end of file not at end of a line; newline inserted"));
state = 0;
PUT ('\n');
}
goto fromeof;
}
switch (lex[ch])
{
case LEX_IS_WHITESPACE:
do
{
ch = GET ();
}
while (ch != EOF && IS_WHITESPACE (ch));
if (ch == EOF)
goto fromeof;
if (state == 0)
{
/* Preserve a single whitespace character at the
beginning of a line. */
state = 1;
UNGET (ch);
PUT (' ');
break;
}
#ifdef KEEP_WHITE_AROUND_COLON
if (lex[ch] == LEX_IS_COLON)
{
/* Only keep this white if there's no white *after* the
colon. */
ch2 = GET ();
if (ch2 != EOF)
UNGET (ch2);
if (!IS_WHITESPACE (ch2))
{
state = 9;
UNGET (ch);
PUT (' ');
break;
}
}
#endif
if (IS_COMMENT (ch)
|| ch == '/'
|| IS_LINE_SEPARATOR (ch)
|| IS_PARALLEL_SEPARATOR (ch))
{
if (scrub_m68k_mri)
{
/* In MRI mode, we keep these spaces. */
UNGET (ch);
PUT (' ');
break;
}
goto recycle;
}
/* If we're in state 2 or 11, we've seen a non-white
character followed by whitespace. If the next character
is ':', this is whitespace after a label name which we
normally must ignore. In MRI mode, though, spaces are
not permitted between the label and the colon. */
if ((state == 2 || state == 11)
&& lex[ch] == LEX_IS_COLON
&& ! scrub_m68k_mri)
{
state = 1;
PUT (ch);
break;
}
switch (state)
{
case 1:
/* We can arrive here if we leave a leading whitespace
character at the beginning of a line. */
goto recycle;
case 2:
state = 3;
if (to + 1 < toend)
{
/* Optimize common case by skipping UNGET/GET. */
PUT (' '); /* Sp after opco */
goto recycle;
}
UNGET (ch);
PUT (' ');
break;
case 3:
#ifndef TC_KEEP_OPERAND_SPACES
/* For TI C6X, we keep these spaces as they may separate
functional unit specifiers from operands. */
if (scrub_m68k_mri)
#endif
{
/* In MRI mode, we keep these spaces. */
UNGET (ch);
PUT (' ');
break;
}
goto recycle; /* Sp in operands */
case 9:
case 10:
#ifndef TC_KEEP_OPERAND_SPACES
if (scrub_m68k_mri)
#endif
{
/* In MRI mode, we keep these spaces. */
state = 3;
UNGET (ch);
PUT (' ');
break;
}
state = 10; /* Sp after symbol char */
goto recycle;
case 11:
if (LABELS_WITHOUT_COLONS || flag_m68k_mri)
state = 1;
else
{
/* We know that ch is not ':', since we tested that
case above. Therefore this is not a label, so it
must be the opcode, and we've just seen the
whitespace after it. */
state = 3;
}
UNGET (ch);
PUT (' '); /* Sp after label definition. */
break;
default:
BAD_CASE (state);
}
break;
case LEX_IS_TWOCHAR_COMMENT_1ST:
ch2 = GET ();
if (ch2 == '*')
{
for (;;)
{
do
{
ch2 = GET ();
if (ch2 != EOF && IS_NEWLINE (ch2))
add_newlines++;
}
while (ch2 != EOF && ch2 != '*');
while (ch2 == '*')
ch2 = GET ();
if (ch2 == EOF || ch2 == '/')
break;
/* This UNGET will ensure that we count newlines
correctly. */
UNGET (ch2);
}
if (ch2 == EOF)
as_warn (_("end of file in multiline comment"));
ch = ' ';
goto recycle;
}
#ifdef DOUBLESLASH_LINE_COMMENTS
else if (ch2 == '/')
{
do
{
ch = GET ();
}
while (ch != EOF && !IS_NEWLINE (ch));
if (ch == EOF)
as_warn ("end of file in comment; newline inserted");
state = 0;
PUT ('\n');
break;
}
#endif
else
{
if (ch2 != EOF)
UNGET (ch2);
if (state == 9 || state == 10)
state = 3;
PUT (ch);
}
break;
case LEX_IS_STRINGQUOTE:
quotechar = ch;
if (state == 10)
{
/* Preserve the whitespace in foo "bar". */
UNGET (ch);
state = 3;
PUT (' ');
/* PUT didn't jump out. We could just break, but we
know what will happen, so optimize a bit. */
ch = GET ();
old_state = 3;
}
else if (state == 9)
old_state = 3;
else
old_state = state;
state = 5;
PUT (ch);
break;
case LEX_IS_ONECHAR_QUOTE:
#ifdef H_TICK_HEX
if (state == 9 && enable_h_tick_hex)
{
char c;
c = GET ();
as_warn ("'%c found after symbol", c);
UNGET (c);
}
#endif
if (state == 10)
{
/* Preserve the whitespace in foo 'b'. */
UNGET (ch);
state = 3;
PUT (' ');
break;
}
ch = GET ();
if (ch == EOF)
{
as_warn (_("end of file after a one-character quote; \\0 inserted"));
ch = 0;
}
if (ch == '\\')
{
ch = GET ();
if (ch == EOF)
{
as_warn (_("end of file in escape character"));
ch = '\\';
}
else
ch = process_escape (ch);
}
sprintf (out_buf, "%d", (int) (unsigned char) ch);
/* None of these 'x constants for us. We want 'x'. */
if ((ch = GET ()) != '\'')
{
#ifdef REQUIRE_CHAR_CLOSE_QUOTE
as_warn (_("missing close quote; (assumed)"));
#else
if (ch != EOF)
UNGET (ch);
#endif
}
if (strlen (out_buf) == 1)
{
PUT (out_buf[0]);
break;
}
if (state == 9)
old_state = 3;
else
old_state = state;
state = -1;
out_string = out_buf;
PUT (*out_string++);
break;
case LEX_IS_COLON:
#ifdef KEEP_WHITE_AROUND_COLON
state = 9;
#else
if (state == 9 || state == 10)
state = 3;
else if (state != 3)
state = 1;
#endif
PUT (ch);
break;
case LEX_IS_NEWLINE:
/* Roll out a bunch of newlines from inside comments, etc. */
if (add_newlines)
{
--add_newlines;
UNGET (ch);
}
/* Fall through. */
case LEX_IS_LINE_SEPARATOR:
state = 0;
PUT (ch);
break;
case LEX_IS_PARALLEL_SEPARATOR:
state = 1;
PUT (ch);
break;
#ifdef TC_V850
case LEX_IS_DOUBLEDASH_1ST:
ch2 = GET ();
if (ch2 != '-')
{
if (ch2 != EOF)
UNGET (ch2);
goto de_fault;
}
/* Read and skip to end of line. */
do
{
ch = GET ();
}
while (ch != EOF && ch != '\n');
if (ch == EOF)
as_warn (_("end of file in comment; newline inserted"));
state = 0;
PUT ('\n');
break;
#endif
#ifdef DOUBLEBAR_PARALLEL
case LEX_IS_DOUBLEBAR_1ST:
ch2 = GET ();
if (ch2 != EOF)
UNGET (ch2);
if (ch2 != '|')
goto de_fault;
/* Handle '||' in two states as invoking PUT twice might
result in the first one jumping out of this loop. We'd
then lose track of the state and one '|' char. */
state = 13;
PUT ('|');
break;
#endif
case LEX_IS_LINE_COMMENT_START:
/* FIXME-someday: The two character comment stuff was badly
thought out. On i386, we want '/' as line comment start
AND we want C style comments. hence this hack. The
whole lexical process should be reworked. xoxorich. */
if (ch == '/')
{
ch2 = GET ();
if (ch2 == '*')
{
old_state = 3;
state = -2;
break;
}
else if (ch2 != EOF)
{
UNGET (ch2);
}
}
if (state == 0 || state == 1) /* Only comment at start of line. */
{
int startch;
startch = ch;
do
{
ch = GET ();
}
while (ch != EOF && IS_WHITESPACE (ch));
if (ch == EOF)
{
as_warn (_("end of file in comment; newline inserted"));
PUT ('\n');
break;
}
if (ch < '0' || ch > '9' || state != 0 || startch != '#')
{
/* Not a cpp line. */
while (ch != EOF && !IS_NEWLINE (ch))
ch = GET ();
if (ch == EOF)
{
as_warn (_("end of file in comment; newline inserted"));
PUT ('\n');
}
else /* IS_NEWLINE (ch) */
{
/* To process non-zero add_newlines. */
UNGET (ch);
}
state = 0;
break;
}
/* Looks like `# 123 "filename"' from cpp. */
UNGET (ch);
old_state = 4;
state = -1;
if (scrub_m68k_mri)
out_string = "\tlinefile ";
else
out_string = "\t.linefile ";
PUT (*out_string++);
break;
}
#ifdef TC_D10V
/* All insns end in a char for which LEX_IS_SYMBOL_COMPONENT is true.
Trap is the only short insn that has a first operand that is
neither register nor label.
We must prevent exef0f ||trap #1 to degenerate to exef0f ||trap#1 .
We can't make '#' LEX_IS_SYMBOL_COMPONENT because it is
already LEX_IS_LINE_COMMENT_START. However, it is the
only character in line_comment_chars for d10v, hence we
can recognize it as such. */
/* An alternative approach would be to reset the state to 1 when
we see '||', '<'- or '->', but that seems to be overkill. */
if (state == 10)
PUT (' ');
#endif
/* We have a line comment character which is not at the
start of a line. If this is also a normal comment
character, fall through. Otherwise treat it as a default
character. */
if (strchr (tc_comment_chars, ch) == NULL
&& (! scrub_m68k_mri
|| (ch != '!' && ch != '*')))
goto de_fault;
if (scrub_m68k_mri
&& (ch == '!' || ch == '*' || ch == '#')
&& state != 1
&& state != 10)
goto de_fault;
/* Fall through. */
case LEX_IS_COMMENT_START:
#if defined TC_ARM && defined OBJ_ELF
/* On the ARM, `@' is the comment character.
Unfortunately this is also a special character in ELF .symver
directives (and .type, though we deal with those another way).
So we check if this line is such a directive, and treat
the character as default if so. This is a hack. */
if ((symver_state != NULL) && (*symver_state == 0))
goto de_fault;
#endif
#ifdef TC_ARM
/* For the ARM, care is needed not to damage occurrences of \@
by stripping the @ onwards. Yuck. */
if ((to > tostart ? to[-1] : last_char) == '\\')
/* Do not treat the @ as a start-of-comment. */
goto de_fault;
#endif
#ifdef WARN_COMMENTS
if (!found_comment)
found_comment_file = as_where (&found_comment);
#endif
do
{
ch = GET ();
}
while (ch != EOF && !IS_NEWLINE (ch));
if (ch == EOF)
as_warn (_("end of file in comment; newline inserted"));
state = 0;
PUT ('\n');
break;
#ifdef H_TICK_HEX
case LEX_IS_H:
/* Look for strings like H'[0-9A-Fa-f] and if found, replace
the H' with 0x to make them gas-style hex characters. */
if (enable_h_tick_hex)
{
char quot;
quot = GET ();
if (quot == '\'')
{
UNGET ('x');
ch = '0';
}
else
UNGET (quot);
}
#endif
/* Fall through. */
case LEX_IS_SYMBOL_COMPONENT:
if (state == 10)
{
/* This is a symbol character following another symbol
character, with whitespace in between. We skipped
the whitespace earlier, so output it now. */
UNGET (ch);
state = 3;
PUT (' ');
break;
}
#ifdef TC_Z80
/* "af'" is a symbol containing '\''. */
if (state == 3 && (ch == 'a' || ch == 'A'))
{
state = 16;
PUT (ch);
ch = GET ();
if (ch == 'f' || ch == 'F')
{
state = 17;
PUT (ch);
break;
}
else
{
state = 9;
if (ch == EOF || !IS_SYMBOL_COMPONENT (ch))
{
if (ch != EOF)
UNGET (ch);
break;
}
}
}
#endif
if (state == 3)
state = 9;
/* This is a common case. Quickly copy CH and all the
following symbol component or normal characters. */
if (to + 1 < toend
&& mri_state == NULL
#if defined TC_ARM && defined OBJ_ELF
&& symver_state == NULL
#endif
)
{
char *s;
ptrdiff_t len;
for (s = from; s < fromend; s++)
{
int type;
ch2 = *(unsigned char *) s;
type = lex[ch2];
if (type != 0
&& type != LEX_IS_SYMBOL_COMPONENT)
break;
}
if (s > from)
/* Handle the last character normally, for
simplicity. */
--s;
len = s - from;
if (len > (toend - to) - 1)
len = (toend - to) - 1;
if (len > 0)
{
PUT (ch);
memcpy (to, from, len);
to += len;
from += len;
if (to >= toend)
goto tofull;
ch = GET ();
}
}
/* Fall through. */
default:
de_fault:
/* Some relatively `normal' character. */
if (state == 0)
{
state = 11; /* Now seeing label definition. */
}
else if (state == 1)
{
state = 2; /* Ditto. */
}
else if (state == 9)
{
if (!IS_SYMBOL_COMPONENT (ch))
state = 3;
}
else if (state == 10)
{
if (ch == '\\')
{
/* Special handling for backslash: a backslash may
be the beginning of a formal parameter (of a
macro) following another symbol character, with
whitespace in between. If that is the case, we
output a space before the parameter. Strictly
speaking, correct handling depends upon what the
macro parameter expands into; if the parameter
expands into something which does not start with
an operand character, then we don't want to keep
the space. We don't have enough information to
make the right choice, so here we are making the
choice which is more likely to be correct. */
if (to + 1 >= toend)
{
/* If we're near the end of the buffer, save the
character for the next time round. Otherwise
we'll lose our state. */
UNGET (ch);
goto tofull;
}
*to++ = ' ';
}
state = 3;
}
PUT (ch);
break;
}
}
/*NOTREACHED*/
fromeof:
/* We have reached the end of the input. */
#ifdef TC_ARM
if (to > tostart)
last_char = to[-1];
#endif
return to - tostart;
tofull:
/* The output buffer is full. Save any input we have not yet
processed. */
if (fromend > from)
{
saved_input = from;
saved_input_len = fromend - from;
}
else
saved_input = NULL;
#ifdef TC_ARM
if (to > tostart)
last_char = to[-1];
#endif
return to - tostart;
}
|