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
|
/* parse.y - parser for flex input */
%token CHAR NUMBER SECTEND SCDECL XSCDECL NAME PREVCCL EOF_OP
%token OPTION_OP OPT_OUTFILE OPT_PREFIX OPT_YYCLASS OPT_HEADER OPT_EXTRA_TYPE
%token OPT_TABLES
%token CCE_ALNUM CCE_ALPHA CCE_BLANK CCE_CNTRL CCE_DIGIT CCE_GRAPH
%token CCE_LOWER CCE_PRINT CCE_PUNCT CCE_SPACE CCE_UPPER CCE_XDIGIT
%token CCE_NEG_ALNUM CCE_NEG_ALPHA CCE_NEG_BLANK CCE_NEG_CNTRL CCE_NEG_DIGIT CCE_NEG_GRAPH
%token CCE_NEG_LOWER CCE_NEG_PRINT CCE_NEG_PUNCT CCE_NEG_SPACE CCE_NEG_UPPER CCE_NEG_XDIGIT
%left CCL_OP_DIFF CCL_OP_UNION
/*
*POSIX and AT&T lex place the
* precedence of the repeat operator, {}, below that of concatenation.
* Thus, ab{3} is ababab. Most other POSIX utilities use an Extended
* Regular Expression (ERE) precedence that has the repeat operator
* higher than concatenation. This causes ab{3} to yield abbb.
*
* In order to support the POSIX and AT&T precedence and the flex
* precedence we define two token sets for the begin and end tokens of
* the repeat operator, '{' and '}'. The lexical scanner chooses
* which tokens to return based on whether posix_compat or lex_compat
* are specified. Specifying either posix_compat or lex_compat will
* cause flex to parse scanner files as per the AT&T and
* POSIX-mandated behavior.
*/
%token BEGIN_REPEAT_POSIX END_REPEAT_POSIX BEGIN_REPEAT_FLEX END_REPEAT_FLEX
%{
/* Copyright (c) 1990 The Regents of the University of California. */
/* All rights reserved. */
/* This code is derived from software contributed to Berkeley by */
/* Vern Paxson. */
/* The United States Government has rights in this work pursuant */
/* to contract no. DE-AC03-76SF00098 between the United States */
/* Department of Energy and the University of California. */
/* This file is part of flex. */
/* Redistribution and use in source and binary forms, with or without */
/* modification, are permitted provided that the following conditions */
/* are met: */
/* 1. Redistributions of source code must retain the above copyright */
/* notice, this list of conditions and the following disclaimer. */
/* 2. Redistributions in binary form must reproduce the above copyright */
/* notice, this list of conditions and the following disclaimer in the */
/* documentation and/or other materials provided with the distribution. */
/* Neither the name of the University nor the names of its contributors */
/* may be used to endorse or promote products derived from this software */
/* without specific prior written permission. */
/* THIS SOFTWARE IS PROVIDED ``AS IS'' AND WITHOUT ANY EXPRESS OR */
/* IMPLIED WARRANTIES, INCLUDING, WITHOUT LIMITATION, THE IMPLIED */
/* WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR */
/* PURPOSE. */
#include "flexdef.h"
#include "tables.h"
int pat, scnum, eps, headcnt, trailcnt, lastchar, i, rulelen;
int trlcontxt, xcluflg, currccl, cclsorted, varlength, variable_trail_rule;
int *scon_stk;
int scon_stk_ptr;
static int madeany = false; /* whether we've made the '.' character class */
static int ccldot, cclany;
int previous_continued_action; /* whether the previous rule's action was '|' */
#define format_warn3(fmt, a1, a2) \
do{ \
char fw3_msg[MAXLINE];\
snprintf( fw3_msg, MAXLINE,(fmt), (a1), (a2) );\
warn( fw3_msg );\
}while(0)
/* Expand a POSIX character class expression. */
#define CCL_EXPR(func) \
do{ \
int c; \
for ( c = 0; c < csize; ++c ) \
if ( isascii(c) && func(c) ) \
ccladd( currccl, c ); \
}while(0)
/* negated class */
#define CCL_NEG_EXPR(func) \
do{ \
int c; \
for ( c = 0; c < csize; ++c ) \
if ( !func(c) ) \
ccladd( currccl, c ); \
}while(0)
/* While POSIX defines isblank(), it's not ANSI C. */
#define IS_BLANK(c) ((c) == ' ' || (c) == '\t')
/* On some over-ambitious machines, such as DEC Alpha's, the default
* token type is "long" instead of "int"; this leads to problems with
* declaring yylval in flexdef.h. But so far, all the yacc's I've seen
* wrap their definitions of YYSTYPE with "#ifndef YYSTYPE"'s, so the
* following should ensure that the default token type is "int".
*/
#define YYSTYPE int
%}
%%
goal : initlex sect1 sect1end sect2 initforrule
{ /* add default rule */
int def_rule;
pat = cclinit();
cclnegate( pat );
def_rule = mkstate( -pat );
/* Remember the number of the default rule so we
* don't generate "can't match" warnings for it.
*/
default_rule = num_rules;
finish_rule( def_rule, false, 0, 0, 0);
for ( i = 1; i <= lastsc; ++i )
scset[i] = mkbranch( scset[i], def_rule );
if ( spprdflt )
add_action(
"YY_FATAL_ERROR( \"flex scanner jammed\" )" );
else
add_action( "ECHO" );
add_action( ";\n\tYY_BREAK\n" );
}
;
initlex :
{ /* initialize for processing rules */
/* Create default DFA start condition. */
scinstal( "INITIAL", false );
}
;
sect1 : sect1 startconddecl namelist1
| sect1 options
|
| error
{ synerr( _("unknown error processing section 1") ); }
;
sect1end : SECTEND
{
check_options();
scon_stk = allocate_integer_array( lastsc + 1 );
scon_stk_ptr = 0;
}
;
startconddecl : SCDECL
{ xcluflg = false; }
| XSCDECL
{ xcluflg = true; }
;
namelist1 : namelist1 NAME
{ scinstal( nmstr, xcluflg ); }
| NAME
{ scinstal( nmstr, xcluflg ); }
| error
{ synerr( _("bad start condition list") ); }
;
options : OPTION_OP optionlist
;
optionlist : optionlist option
|
;
option : OPT_OUTFILE '=' NAME
{
outfilename = copy_string( nmstr );
did_outfilename = 1;
}
| OPT_EXTRA_TYPE '=' NAME
{ extra_type = copy_string( nmstr ); }
| OPT_PREFIX '=' NAME
{ prefix = copy_string( nmstr ); }
| OPT_YYCLASS '=' NAME
{ yyclass = copy_string( nmstr ); }
| OPT_HEADER '=' NAME
{ headerfilename = copy_string( nmstr ); }
| OPT_TABLES '=' NAME
{ tablesext = true; tablesfilename = copy_string( nmstr ); }
;
sect2 : sect2 scon initforrule flexrule '\n'
{ scon_stk_ptr = $2; }
| sect2 scon '{' sect2 '}'
{ scon_stk_ptr = $2; }
|
;
initforrule :
{
/* Initialize for a parse of one rule. */
trlcontxt = variable_trail_rule = varlength = false;
trailcnt = headcnt = rulelen = 0;
current_state_type = STATE_NORMAL;
previous_continued_action = continued_action;
in_rule = true;
new_rule();
}
;
flexrule : '^' rule
{
pat = $2;
finish_rule( pat, variable_trail_rule,
headcnt, trailcnt , previous_continued_action);
if ( scon_stk_ptr > 0 )
{
for ( i = 1; i <= scon_stk_ptr; ++i )
scbol[scon_stk[i]] =
mkbranch( scbol[scon_stk[i]],
pat );
}
else
{
/* Add to all non-exclusive start conditions,
* including the default (0) start condition.
*/
for ( i = 1; i <= lastsc; ++i )
if ( ! scxclu[i] )
scbol[i] = mkbranch( scbol[i],
pat );
}
if ( ! bol_needed )
{
bol_needed = true;
if ( performance_report > 1 )
pinpoint_message(
"'^' operator results in sub-optimal performance" );
}
}
| rule
{
pat = $1;
finish_rule( pat, variable_trail_rule,
headcnt, trailcnt , previous_continued_action);
if ( scon_stk_ptr > 0 )
{
for ( i = 1; i <= scon_stk_ptr; ++i )
scset[scon_stk[i]] =
mkbranch( scset[scon_stk[i]],
pat );
}
else
{
for ( i = 1; i <= lastsc; ++i )
if ( ! scxclu[i] )
scset[i] =
mkbranch( scset[i],
pat );
}
}
| EOF_OP
{
if ( scon_stk_ptr > 0 )
build_eof_action();
else
{
/* This EOF applies to all start conditions
* which don't already have EOF actions.
*/
for ( i = 1; i <= lastsc; ++i )
if ( ! sceof[i] )
scon_stk[++scon_stk_ptr] = i;
if ( scon_stk_ptr == 0 )
warn(
"all start conditions already have <<EOF>> rules" );
else
build_eof_action();
}
}
| error
{ synerr( _("unrecognized rule") ); }
;
scon_stk_ptr :
{ $$ = scon_stk_ptr; }
;
scon : '<' scon_stk_ptr namelist2 '>'
{ $$ = $2; }
| '<' '*' '>'
{
$$ = scon_stk_ptr;
for ( i = 1; i <= lastsc; ++i )
{
int j;
for ( j = 1; j <= scon_stk_ptr; ++j )
if ( scon_stk[j] == i )
break;
if ( j > scon_stk_ptr )
scon_stk[++scon_stk_ptr] = i;
}
}
|
{ $$ = scon_stk_ptr; }
;
namelist2 : namelist2 ',' sconname
| sconname
| error
{ synerr( _("bad start condition list") ); }
;
sconname : NAME
{
if ( (scnum = sclookup( nmstr )) == 0 )
format_pinpoint_message(
"undeclared start condition %s",
nmstr );
else
{
for ( i = 1; i <= scon_stk_ptr; ++i )
if ( scon_stk[i] == scnum )
{
format_warn(
"<%s> specified twice",
scname[scnum] );
break;
}
if ( i > scon_stk_ptr )
scon_stk[++scon_stk_ptr] = scnum;
}
}
;
rule : re2 re
{
if ( transchar[lastst[$2]] != SYM_EPSILON )
/* Provide final transition \now/ so it
* will be marked as a trailing context
* state.
*/
$2 = link_machines( $2,
mkstate( SYM_EPSILON ) );
mark_beginning_as_normal( $2 );
current_state_type = STATE_NORMAL;
if ( previous_continued_action )
{
/* We need to treat this as variable trailing
* context so that the backup does not happen
* in the action but before the action switch
* statement. If the backup happens in the
* action, then the rules "falling into" this
* one's action will *also* do the backup,
* erroneously.
*/
if ( ! varlength || headcnt != 0 )
warn(
"trailing context made variable due to preceding '|' action" );
/* Mark as variable. */
varlength = true;
headcnt = 0;
}
if ( lex_compat || (varlength && headcnt == 0) )
{ /* variable trailing context rule */
/* Mark the first part of the rule as the
* accepting "head" part of a trailing
* context rule.
*
* By the way, we didn't do this at the
* beginning of this production because back
* then current_state_type was set up for a
* trail rule, and add_accept() can create
* a new state ...
*/
add_accept( $1,
num_rules | YY_TRAILING_HEAD_MASK );
variable_trail_rule = true;
}
else
trailcnt = rulelen;
$$ = link_machines( $1, $2 );
}
| re2 re '$'
{ synerr( _("trailing context used twice") ); }
| re '$'
{
headcnt = 0;
trailcnt = 1;
rulelen = 1;
varlength = false;
current_state_type = STATE_TRAILING_CONTEXT;
if ( trlcontxt )
{
synerr( _("trailing context used twice") );
$$ = mkstate( SYM_EPSILON );
}
else if ( previous_continued_action )
{
/* See the comment in the rule for "re2 re"
* above.
*/
warn(
"trailing context made variable due to preceding '|' action" );
varlength = true;
}
if ( lex_compat || varlength )
{
/* Again, see the comment in the rule for
* "re2 re" above.
*/
add_accept( $1,
num_rules | YY_TRAILING_HEAD_MASK );
variable_trail_rule = true;
}
trlcontxt = true;
eps = mkstate( SYM_EPSILON );
$$ = link_machines( $1,
link_machines( eps, mkstate( '\n' ) ) );
}
| re
{
$$ = $1;
if ( trlcontxt )
{
if ( lex_compat || (varlength && headcnt == 0) )
/* Both head and trail are
* variable-length.
*/
variable_trail_rule = true;
else
trailcnt = rulelen;
}
}
;
re : re '|' series
{
varlength = true;
$$ = mkor( $1, $3 );
}
| series
{ $$ = $1; }
;
re2 : re '/'
{
/* This rule is written separately so the
* reduction will occur before the trailing
* series is parsed.
*/
if ( trlcontxt )
synerr( _("trailing context used twice") );
else
trlcontxt = true;
if ( varlength )
/* We hope the trailing context is
* fixed-length.
*/
varlength = false;
else
headcnt = rulelen;
rulelen = 0;
current_state_type = STATE_TRAILING_CONTEXT;
$$ = $1;
}
;
series : series singleton
{
/* This is where concatenation of adjacent patterns
* gets done.
*/
$$ = link_machines( $1, $2 );
}
| singleton
{ $$ = $1; }
| series BEGIN_REPEAT_POSIX NUMBER ',' NUMBER END_REPEAT_POSIX
{
varlength = true;
if ( $3 > $5 || $3 < 0 )
{
synerr( _("bad iteration values") );
$$ = $1;
}
else
{
if ( $3 == 0 )
{
if ( $5 <= 0 )
{
synerr(
_("bad iteration values") );
$$ = $1;
}
else
$$ = mkopt(
mkrep( $1, 1, $5 ) );
}
else
$$ = mkrep( $1, $3, $5 );
}
}
| series BEGIN_REPEAT_POSIX NUMBER ',' END_REPEAT_POSIX
{
varlength = true;
if ( $3 <= 0 )
{
synerr( _("iteration value must be positive") );
$$ = $1;
}
else
$$ = mkrep( $1, $3, INFINITE_REPEAT );
}
| series BEGIN_REPEAT_POSIX NUMBER END_REPEAT_POSIX
{
/* The series could be something like "(foo)",
* in which case we have no idea what its length
* is, so we punt here.
*/
varlength = true;
if ( $3 <= 0 )
{
synerr( _("iteration value must be positive")
);
$$ = $1;
}
else
$$ = link_machines( $1,
copysingl( $1, $3 - 1 ) );
}
;
singleton : singleton '*'
{
varlength = true;
$$ = mkclos( $1 );
}
| singleton '+'
{
varlength = true;
$$ = mkposcl( $1 );
}
| singleton '?'
{
varlength = true;
$$ = mkopt( $1 );
}
| singleton BEGIN_REPEAT_FLEX NUMBER ',' NUMBER END_REPEAT_FLEX
{
varlength = true;
if ( $3 > $5 || $3 < 0 )
{
synerr( _("bad iteration values") );
$$ = $1;
}
else
{
if ( $3 == 0 )
{
if ( $5 <= 0 )
{
synerr(
_("bad iteration values") );
$$ = $1;
}
else
$$ = mkopt(
mkrep( $1, 1, $5 ) );
}
else
$$ = mkrep( $1, $3, $5 );
}
}
| singleton BEGIN_REPEAT_FLEX NUMBER ',' END_REPEAT_FLEX
{
varlength = true;
if ( $3 <= 0 )
{
synerr( _("iteration value must be positive") );
$$ = $1;
}
else
$$ = mkrep( $1, $3, INFINITE_REPEAT );
}
| singleton BEGIN_REPEAT_FLEX NUMBER END_REPEAT_FLEX
{
/* The singleton could be something like "(foo)",
* in which case we have no idea what its length
* is, so we punt here.
*/
varlength = true;
if ( $3 <= 0 )
{
synerr( _("iteration value must be positive") );
$$ = $1;
}
else
$$ = link_machines( $1,
copysingl( $1, $3 - 1 ) );
}
| '.'
{
if ( ! madeany )
{
/* Create the '.' character class. */
ccldot = cclinit();
ccladd( ccldot, '\n' );
cclnegate( ccldot );
if ( useecs )
mkeccl( ccltbl + cclmap[ccldot],
ccllen[ccldot], nextecm,
ecgroup, csize, csize );
/* Create the (?s:'.') character class. */
cclany = cclinit();
cclnegate( cclany );
if ( useecs )
mkeccl( ccltbl + cclmap[cclany],
ccllen[cclany], nextecm,
ecgroup, csize, csize );
madeany = true;
}
++rulelen;
if (sf_dot_all())
$$ = mkstate( -cclany );
else
$$ = mkstate( -ccldot );
}
| fullccl
{
/* Sort characters for fast searching.
*/
qsort( ccltbl + cclmap[$1], ccllen[$1], sizeof (*ccltbl), cclcmp );
if ( useecs )
mkeccl( ccltbl + cclmap[$1], ccllen[$1],
nextecm, ecgroup, csize, csize );
++rulelen;
if (ccl_has_nl[$1])
rule_has_nl[num_rules] = true;
$$ = mkstate( -$1 );
}
| PREVCCL
{
++rulelen;
if (ccl_has_nl[$1])
rule_has_nl[num_rules] = true;
$$ = mkstate( -$1 );
}
| '"' string '"'
{ $$ = $2; }
| '(' re ')'
{ $$ = $2; }
| CHAR
{
++rulelen;
if ($1 == nlch)
rule_has_nl[num_rules] = true;
if (sf_case_ins() && has_case($1))
/* create an alternation, as in (a|A) */
$$ = mkor (mkstate($1), mkstate(reverse_case($1)));
else
$$ = mkstate( $1 );
}
;
fullccl:
fullccl CCL_OP_DIFF braceccl { $$ = ccl_set_diff ($1, $3); }
| fullccl CCL_OP_UNION braceccl { $$ = ccl_set_union ($1, $3); }
| braceccl
;
braceccl:
'[' ccl ']' { $$ = $2; }
| '[' '^' ccl ']'
{
cclnegate( $3 );
$$ = $3;
}
;
ccl : ccl CHAR '-' CHAR
{
if (sf_case_ins())
{
/* If one end of the range has case and the other
* does not, or the cases are different, then we're not
* sure what range the user is trying to express.
* Examples: [@-z] or [S-t]
*/
if (has_case ($2) != has_case ($4)
|| (has_case ($2) && (b_islower ($2) != b_islower ($4)))
|| (has_case ($2) && (b_isupper ($2) != b_isupper ($4))))
format_warn3 (
_("the character range [%c-%c] is ambiguous in a case-insensitive scanner"),
$2, $4);
/* If the range spans uppercase characters but not
* lowercase (or vice-versa), then should we automatically
* include lowercase characters in the range?
* Example: [@-_] spans [a-z] but not [A-Z]
*/
else if (!has_case ($2) && !has_case ($4) && !range_covers_case ($2, $4))
format_warn3 (
_("the character range [%c-%c] is ambiguous in a case-insensitive scanner"),
$2, $4);
}
if ( $2 > $4 )
synerr( _("negative range in character class") );
else
{
for ( i = $2; i <= $4; ++i )
ccladd( $1, i );
/* Keep track if this ccl is staying in
* alphabetical order.
*/
cclsorted = cclsorted && ($2 > lastchar);
lastchar = $4;
/* Do it again for upper/lowercase */
if (sf_case_ins() && has_case($2) && has_case($4)){
$2 = reverse_case ($2);
$4 = reverse_case ($4);
for ( i = $2; i <= $4; ++i )
ccladd( $1, i );
cclsorted = cclsorted && ($2 > lastchar);
lastchar = $4;
}
}
$$ = $1;
}
| ccl CHAR
{
ccladd( $1, $2 );
cclsorted = cclsorted && ($2 > lastchar);
lastchar = $2;
/* Do it again for upper/lowercase */
if (sf_case_ins() && has_case($2)){
$2 = reverse_case ($2);
ccladd ($1, $2);
cclsorted = cclsorted && ($2 > lastchar);
lastchar = $2;
}
$$ = $1;
}
| ccl ccl_expr
{
/* Too hard to properly maintain cclsorted. */
cclsorted = false;
$$ = $1;
}
|
{
cclsorted = true;
lastchar = 0;
currccl = $$ = cclinit();
}
;
ccl_expr:
CCE_ALNUM { CCL_EXPR(isalnum); }
| CCE_ALPHA { CCL_EXPR(isalpha); }
| CCE_BLANK { CCL_EXPR(IS_BLANK); }
| CCE_CNTRL { CCL_EXPR(iscntrl); }
| CCE_DIGIT { CCL_EXPR(isdigit); }
| CCE_GRAPH { CCL_EXPR(isgraph); }
| CCE_LOWER {
CCL_EXPR(islower);
if (sf_case_ins())
CCL_EXPR(isupper);
}
| CCE_PRINT { CCL_EXPR(isprint); }
| CCE_PUNCT { CCL_EXPR(ispunct); }
| CCE_SPACE { CCL_EXPR(isspace); }
| CCE_XDIGIT { CCL_EXPR(isxdigit); }
| CCE_UPPER {
CCL_EXPR(isupper);
if (sf_case_ins())
CCL_EXPR(islower);
}
| CCE_NEG_ALNUM { CCL_NEG_EXPR(isalnum); }
| CCE_NEG_ALPHA { CCL_NEG_EXPR(isalpha); }
| CCE_NEG_BLANK { CCL_NEG_EXPR(IS_BLANK); }
| CCE_NEG_CNTRL { CCL_NEG_EXPR(iscntrl); }
| CCE_NEG_DIGIT { CCL_NEG_EXPR(isdigit); }
| CCE_NEG_GRAPH { CCL_NEG_EXPR(isgraph); }
| CCE_NEG_PRINT { CCL_NEG_EXPR(isprint); }
| CCE_NEG_PUNCT { CCL_NEG_EXPR(ispunct); }
| CCE_NEG_SPACE { CCL_NEG_EXPR(isspace); }
| CCE_NEG_XDIGIT { CCL_NEG_EXPR(isxdigit); }
| CCE_NEG_LOWER {
if ( sf_case_ins() )
warn(_("[:^lower:] is ambiguous in case insensitive scanner"));
else
CCL_NEG_EXPR(islower);
}
| CCE_NEG_UPPER {
if ( sf_case_ins() )
warn(_("[:^upper:] ambiguous in case insensitive scanner"));
else
CCL_NEG_EXPR(isupper);
}
;
string : string CHAR
{
if ( $2 == nlch )
rule_has_nl[num_rules] = true;
++rulelen;
if (sf_case_ins() && has_case($2))
$$ = mkor (mkstate($2), mkstate(reverse_case($2)));
else
$$ = mkstate ($2);
$$ = link_machines( $1, $$);
}
|
{ $$ = mkstate( SYM_EPSILON ); }
;
%%
/* build_eof_action - build the "<<EOF>>" action for the active start
* conditions
*/
void build_eof_action()
{
register int i;
char action_text[MAXLINE];
for ( i = 1; i <= scon_stk_ptr; ++i )
{
if ( sceof[scon_stk[i]] )
format_pinpoint_message(
"multiple <<EOF>> rules for start condition %s",
scname[scon_stk[i]] );
else
{
sceof[scon_stk[i]] = true;
if (previous_continued_action /* && previous action was regular */)
add_action("YY_RULE_SETUP\n");
snprintf( action_text, sizeof(action_text), "case YY_STATE_EOF(%s):\n",
scname[scon_stk[i]] );
add_action( action_text );
}
}
line_directive_out( (FILE *) 0, 1 );
/* This isn't a normal rule after all - don't count it as
* such, so we don't have any holes in the rule numbering
* (which make generating "rule can never match" warnings
* more difficult.
*/
--num_rules;
++num_eof_rules;
}
/* format_synerr - write out formatted syntax error */
void format_synerr( msg, arg )
const char *msg, arg[];
{
char errmsg[MAXLINE];
(void) snprintf( errmsg, sizeof(errmsg), msg, arg );
synerr( errmsg );
}
/* synerr - report a syntax error */
void synerr( str )
const char *str;
{
syntaxerror = true;
pinpoint_message( str );
}
/* format_warn - write out formatted warning */
void format_warn( msg, arg )
const char *msg, arg[];
{
char warn_msg[MAXLINE];
snprintf( warn_msg, sizeof(warn_msg), msg, arg );
warn( warn_msg );
}
/* warn - report a warning, unless -w was given */
void warn( str )
const char *str;
{
line_warning( str, linenum );
}
/* format_pinpoint_message - write out a message formatted with one string,
* pinpointing its location
*/
void format_pinpoint_message( msg, arg )
const char *msg, arg[];
{
char errmsg[MAXLINE];
snprintf( errmsg, sizeof(errmsg), msg, arg );
pinpoint_message( errmsg );
}
/* pinpoint_message - write out a message, pinpointing its location */
void pinpoint_message( str )
const char *str;
{
line_pinpoint( str, linenum );
}
/* line_warning - report a warning at a given line, unless -w was given */
void line_warning( str, line )
const char *str;
int line;
{
char warning[MAXLINE];
if ( ! nowarn )
{
snprintf( warning, sizeof(warning), "warning, %s", str );
line_pinpoint( warning, line );
}
}
/* line_pinpoint - write out a message, pinpointing it at the given line */
void line_pinpoint( str, line )
const char *str;
int line;
{
fprintf( stderr, "%s:%d: %s\n", infilename, line, str );
}
/* yyerror - eat up an error message from the parser;
* currently, messages are ignore
*/
void yyerror( msg )
const char *msg;
{
}
|