-
Notifications
You must be signed in to change notification settings - Fork 0
/
lex.c
1668 lines (1533 loc) · 35.8 KB
/
lex.c
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
/* $OpenBSD: lex.c,v 1.78 2018/01/15 14:58:05 jca Exp $ */
/*
* lexical analysis and source input
*/
#include <ctype.h>
#include <errno.h>
#include <libgen.h>
#include <stdio.h>
#include <string.h>
#include <unistd.h>
#include "sh.h"
/*
* states while lexing word
*/
#define SINVALID -1 /* invalid state */
#define SBASE 0 /* outside any lexical constructs */
#define SWORD 1 /* implicit quoting for substitute() */
#define SLETPAREN 2 /* inside (( )), implicit quoting */
#define SSQUOTE 3 /* inside '' */
#define SDQUOTE 4 /* inside "" */
#define SBRACE 5 /* inside ${} */
#define SCSPAREN 6 /* inside $() */
#define SBQUOTE 7 /* inside `` */
#define SASPAREN 8 /* inside $(( )) */
#define SHEREDELIM 9 /* parsing <<,<<- delimiter */
#define SHEREDQUOTE 10 /* parsing " in <<,<<- delimiter */
#define SPATTERN 11 /* parsing *(...|...) pattern (*+?@!) */
#define STBRACE 12 /* parsing ${..[#%]..} */
#define SBRACEQ 13 /* inside "${}" */
/* Structure to keep track of the lexing state and the various pieces of info
* needed for each particular state.
*/
typedef struct lex_state Lex_state;
struct lex_state {
int ls_state;
union {
/* $(...) */
struct scsparen_info {
int nparen; /* count open parenthesis */
int csstate; /* XXX remove */
#define ls_scsparen ls_info.u_scsparen
} u_scsparen;
/* $((...)) */
struct sasparen_info {
int nparen; /* count open parenthesis */
int start; /* marks start of $(( in output str */
#define ls_sasparen ls_info.u_sasparen
} u_sasparen;
/* ((...)) */
struct sletparen_info {
int nparen; /* count open parenthesis */
#define ls_sletparen ls_info.u_sletparen
} u_sletparen;
/* `...` */
struct sbquote_info {
int indquotes; /* true if in double quotes: "`...`" */
#define ls_sbquote ls_info.u_sbquote
} u_sbquote;
Lex_state *base; /* used to point to next state block */
} ls_info;
};
typedef struct State_info State_info;
struct State_info {
Lex_state *base;
Lex_state *end;
};
static void readhere(struct ioword *);
static int getsc__(void);
static void getsc_line(Source *);
static int getsc_bn(void);
static char *get_brace_var(XString *, char *);
static int arraysub(char **);
static const char *ungetsc(int);
static void gethere(void);
static Lex_state *push_state_(State_info *, Lex_state *);
static Lex_state *pop_state_(State_info *, Lex_state *);
static char *special_prompt_expand(char *);
static int dopprompt(const char *, int, const char **, int);
int promptlen(const char *cp, const char **spp);
static int backslash_skip;
static int ignore_backslash_newline;
Source *source; /* yyparse/yylex source */
YYSTYPE yylval; /* result from yylex */
struct ioword *heres[HERES], **herep;
char ident[IDENT+1];
char **history; /* saved commands */
char **histptr; /* last history item */
uint32_t histsize; /* history size */
/* optimized getsc_bn() */
#define getsc() (*source->str != '\0' && *source->str != '\\' \
&& !backslash_skip ? *source->str++ : getsc_bn())
/* optimized getsc__() */
#define getsc_() ((*source->str != '\0') ? *source->str++ : getsc__())
#define STATE_BSIZE 32
#define PUSH_STATE(s) do { \
if (++statep == state_info.end) \
statep = push_state_(&state_info, statep); \
state = statep->ls_state = (s); \
} while (0)
#define POP_STATE() do { \
if (--statep == state_info.base) \
statep = pop_state_(&state_info, statep); \
state = statep->ls_state; \
} while (0)
/*
* Lexical analyzer
*
* tokens are not regular expressions, they are LL(1).
* for example, "${var:-${PWD}}", and "$(size $(whence ksh))".
* hence the state stack.
*/
int
yylex(int cf)
{
Lex_state states[STATE_BSIZE], *statep;
State_info state_info;
int c, state;
XString ws; /* expandable output word */
char *wp; /* output word pointer */
char *sp, *dp;
int c2;
Again:
states[0].ls_state = SINVALID;
states[0].ls_info.base = NULL;
statep = &states[1];
state_info.base = states;
state_info.end = &states[STATE_BSIZE];
Xinit(ws, wp, 64, ATEMP);
backslash_skip = 0;
ignore_backslash_newline = 0;
if (cf&ONEWORD)
state = SWORD;
else if (cf&LETEXPR) {
*wp++ = OQUOTE; /* enclose arguments in (double) quotes */
state = SLETPAREN;
statep->ls_sletparen.nparen = 0;
} else { /* normal lexing */
state = (cf & HEREDELIM) ? SHEREDELIM : SBASE;
while ((c = getsc()) == ' ' || c == '\t')
;
if (c == '#') {
ignore_backslash_newline++;
while ((c = getsc()) != '\0' && c != '\n')
;
ignore_backslash_newline--;
}
ungetsc(c);
}
if (source->flags & SF_ALIAS) { /* trailing ' ' in alias definition */
source->flags &= ~SF_ALIAS;
/* In POSIX mode, a trailing space only counts if we are
* parsing a simple command
*/
if (!Flag(FPOSIX) || (cf & CMDWORD))
cf |= ALIAS;
}
/* Initial state: one of SBASE SHEREDELIM SWORD SASPAREN */
statep->ls_state = state;
/* collect non-special or quoted characters to form word */
while (!((c = getsc()) == 0 ||
((state == SBASE || state == SHEREDELIM) && ctype(c, C_LEX1)))) {
Xcheck(ws, wp);
switch (state) {
case SBASE:
if (Flag(FCSHHISTORY) && (source->flags & SF_TTY) &&
c == '!') {
char **replace = NULL;
int get, i;
char match[200] = { 0 }, *str = match;
size_t mlen;
c2 = getsc();
if (c2 == '\0' || c2 == ' ' || c2 == '\t')
;
else if (c2 == '!')
replace = hist_get_newest(0);
else if (isdigit(c2) || c2 == '-' ||
isalpha(c2)) {
get = !isalpha(c2);
*str++ = c2;
do {
if ((c2 = getsc()) == '\0')
break;
if (c2 == '\t' || c2 == ' ' ||
c2 == '\n') {
ungetsc(c2);
break;
}
*str++ = c2;
} while (str < &match[sizeof(match)-1]);
*str = '\0';
if (get) {
int h = findhistrel(match);
if (h >= 0)
replace = &history[h];
} else {
int h = findhist(-1, 0, match, true);
if (h >= 0)
replace = &history[h];
}
}
/*
* XXX ksh history buffer saves un-expanded
* commands. Until the history buffer code is
* changed to contain expanded commands, we
* ignore the bad commands (spinning sucks)
*/
if (replace && **replace == '!')
ungetsc(c2);
else if (replace) {
Source *s;
/* do not strdup replacement via alloc */
s = pushs(SREREAD, source->areap);
s->start = s->str = *replace;
s->next = source;
s->u.freeme = NULL;
source = s;
continue;
} else if (*match != '\0') {
/* restore what followed the '!' */
mlen = strlen(match);
for (i = mlen-1; i >= 0; i--)
ungetsc(match[i]);
} else
ungetsc(c2);
}
if (c == '[' && (cf & (VARASN|ARRAYVAR))) {
*wp = EOS; /* temporary */
if (is_wdvarname(Xstring(ws, wp), false)) {
char *p, *tmp;
if (arraysub(&tmp)) {
*wp++ = CHAR;
*wp++ = c;
for (p = tmp; *p; ) {
Xcheck(ws, wp);
*wp++ = CHAR;
*wp++ = *p++;
}
afree(tmp, ATEMP);
break;
} else {
Source *s;
s = pushs(SREREAD,
source->areap);
s->start = s->str
= s->u.freeme = tmp;
s->next = source;
source = s;
}
}
*wp++ = CHAR;
*wp++ = c;
break;
}
/* FALLTHROUGH */
Sbase1: /* includes *(...|...) pattern (*+?@!) */
if (c == '*' || c == '@' || c == '+' || c == '?' ||
c == '!') {
c2 = getsc();
if (c2 == '(' /*)*/ ) {
*wp++ = OPAT;
*wp++ = c;
PUSH_STATE(SPATTERN);
break;
}
ungetsc(c2);
}
/* FALLTHROUGH */
Sbase2: /* doesn't include *(...|...) pattern (*+?@!) */
switch (c) {
case '\\':
c = getsc();
if (c) /* trailing \ is lost */
*wp++ = QCHAR, *wp++ = c;
break;
case '\'':
if ((cf & HEREDOC) || state == SBRACEQ) {
*wp++ = CHAR, *wp++ = c;
break;
}
*wp++ = OQUOTE;
ignore_backslash_newline++;
PUSH_STATE(SSQUOTE);
break;
case '"':
*wp++ = OQUOTE;
PUSH_STATE(SDQUOTE);
break;
default:
goto Subst;
}
break;
Subst:
switch (c) {
case '\\':
c = getsc();
switch (c) {
case '\\':
case '$': case '`':
*wp++ = QCHAR, *wp++ = c;
break;
case '"':
if ((cf & HEREDOC) == 0) {
*wp++ = QCHAR, *wp++ = c;
break;
}
/* FALLTHROUGH */
default:
if (cf & UNESCAPE) {
*wp++ = QCHAR, *wp++ = c;
break;
}
Xcheck(ws, wp);
if (c) { /* trailing \ is lost */
*wp++ = CHAR, *wp++ = '\\';
*wp++ = CHAR, *wp++ = c;
}
break;
}
break;
case '$':
c = getsc();
if (c == '(') /*)*/ {
c = getsc();
if (c == '(') /*)*/ {
PUSH_STATE(SASPAREN);
statep->ls_sasparen.nparen = 2;
statep->ls_sasparen.start =
Xsavepos(ws, wp);
*wp++ = EXPRSUB;
} else {
ungetsc(c);
PUSH_STATE(SCSPAREN);
statep->ls_scsparen.nparen = 1;
statep->ls_scsparen.csstate = 0;
*wp++ = COMSUB;
}
} else if (c == '{') /*}*/ {
*wp++ = OSUBST;
*wp++ = '{'; /*}*/
wp = get_brace_var(&ws, wp);
c = getsc();
/* allow :# and :% (ksh88 compat) */
if (c == ':') {
*wp++ = CHAR, *wp++ = c;
c = getsc();
}
/* If this is a trim operation,
* treat (,|,) specially in STBRACE.
*/
if (c == '#' || c == '%') {
ungetsc(c);
PUSH_STATE(STBRACE);
} else {
ungetsc(c);
if (state == SDQUOTE ||
state == SBRACEQ)
PUSH_STATE(SBRACEQ);
else
PUSH_STATE(SBRACE);
}
} else if (ctype(c, C_ALPHA)) {
*wp++ = OSUBST;
*wp++ = 'X';
do {
Xcheck(ws, wp);
*wp++ = c;
c = getsc();
} while (ctype(c, C_ALPHA) || digit(c));
*wp++ = '\0';
*wp++ = CSUBST;
*wp++ = 'X';
ungetsc(c);
} else if (ctype(c, C_VAR1) || digit(c)) {
Xcheck(ws, wp);
*wp++ = OSUBST;
*wp++ = 'X';
*wp++ = c;
*wp++ = '\0';
*wp++ = CSUBST;
*wp++ = 'X';
} else {
*wp++ = CHAR, *wp++ = '$';
ungetsc(c);
}
break;
case '`':
PUSH_STATE(SBQUOTE);
*wp++ = COMSUB;
/* Need to know if we are inside double quotes
* since sh/at&t-ksh translate the \" to " in
* "`..\"..`".
*/
statep->ls_sbquote.indquotes = 0;
Lex_state *s = statep;
Lex_state *base = state_info.base;
while (1) {
for (; s != base; s--) {
if (s->ls_state == SDQUOTE) {
statep->ls_sbquote.indquotes = 1;
break;
}
}
if (s != base)
break;
if (!(s = s->ls_info.base))
break;
base = s-- - STATE_BSIZE;
}
break;
default:
*wp++ = CHAR, *wp++ = c;
}
break;
case SSQUOTE:
if (c == '\'') {
POP_STATE();
if (state == SBRACEQ) {
*wp++ = CHAR, *wp++ = c;
break;
}
*wp++ = CQUOTE;
ignore_backslash_newline--;
} else
*wp++ = QCHAR, *wp++ = c;
break;
case SDQUOTE:
if (c == '"') {
POP_STATE();
*wp++ = CQUOTE;
} else
goto Subst;
break;
case SCSPAREN: /* $( .. ) */
/* todo: deal with $(...) quoting properly
* kludge to partly fake quoting inside $(..): doesn't
* really work because nested $(..) or ${..} inside
* double quotes aren't dealt with.
*/
switch (statep->ls_scsparen.csstate) {
case 0: /* normal */
switch (c) {
case '(':
statep->ls_scsparen.nparen++;
break;
case ')':
statep->ls_scsparen.nparen--;
break;
case '\\':
statep->ls_scsparen.csstate = 1;
break;
case '"':
statep->ls_scsparen.csstate = 2;
break;
case '\'':
statep->ls_scsparen.csstate = 4;
ignore_backslash_newline++;
break;
}
break;
case 1: /* backslash in normal mode */
case 3: /* backslash in double quotes */
--statep->ls_scsparen.csstate;
break;
case 2: /* double quotes */
if (c == '"')
statep->ls_scsparen.csstate = 0;
else if (c == '\\')
statep->ls_scsparen.csstate = 3;
break;
case 4: /* single quotes */
if (c == '\'') {
statep->ls_scsparen.csstate = 0;
ignore_backslash_newline--;
}
break;
}
if (statep->ls_scsparen.nparen == 0) {
POP_STATE();
*wp++ = 0; /* end of COMSUB */
} else
*wp++ = c;
break;
case SASPAREN: /* $(( .. )) */
/* todo: deal with $((...); (...)) properly */
/* XXX should nest using existing state machine
* (embed "..", $(...), etc.) */
if (c == '(')
statep->ls_sasparen.nparen++;
else if (c == ')') {
statep->ls_sasparen.nparen--;
if (statep->ls_sasparen.nparen == 1) {
/*(*/
if ((c2 = getsc()) == ')') {
POP_STATE();
*wp++ = 0; /* end of EXPRSUB */
break;
} else {
char *s;
ungetsc(c2);
/* mismatched parenthesis -
* assume we were really
* parsing a $(..) expression
*/
s = Xrestpos(ws, wp,
statep->ls_sasparen.start);
memmove(s + 1, s, wp - s);
*s++ = COMSUB;
*s = '('; /*)*/
wp++;
statep->ls_scsparen.nparen = 1;
statep->ls_scsparen.csstate = 0;
state = statep->ls_state =
SCSPAREN;
}
}
}
*wp++ = c;
break;
case SBRACEQ:
/*{*/
if (c == '}') {
POP_STATE();
*wp++ = CSUBST;
*wp++ = /*{*/ '}';
} else
goto Sbase2;
break;
case SBRACE:
/*{*/
if (c == '}') {
POP_STATE();
*wp++ = CSUBST;
*wp++ = /*{*/ '}';
} else
goto Sbase1;
break;
case STBRACE:
/* Same as SBRACE, except (,|,) treated specially */
/*{*/
if (c == '}') {
POP_STATE();
*wp++ = CSUBST;
*wp++ = /*{*/ '}';
} else if (c == '|') {
*wp++ = SPAT;
} else if (c == '(') {
*wp++ = OPAT;
*wp++ = ' '; /* simile for @ */
PUSH_STATE(SPATTERN);
} else
goto Sbase1;
break;
case SBQUOTE:
if (c == '`') {
*wp++ = 0;
POP_STATE();
} else if (c == '\\') {
switch (c = getsc()) {
case '\\':
case '$': case '`':
*wp++ = c;
break;
case '"':
if (statep->ls_sbquote.indquotes) {
*wp++ = c;
break;
}
/* FALLTHROUGH */
default:
if (c) { /* trailing \ is lost */
*wp++ = '\\';
*wp++ = c;
}
break;
}
} else
*wp++ = c;
break;
case SWORD: /* ONEWORD */
goto Subst;
case SLETPAREN: /* LETEXPR: (( ... )) */
/*(*/
if (c == ')') {
if (statep->ls_sletparen.nparen > 0)
--statep->ls_sletparen.nparen;
/*(*/
else if ((c2 = getsc()) == ')') {
c = 0;
*wp++ = CQUOTE;
goto Done;
} else
ungetsc(c2);
} else if (c == '(')
/* parenthesis inside quotes and backslashes
* are lost, but at&t ksh doesn't count them
* either
*/
++statep->ls_sletparen.nparen;
goto Sbase2;
case SHEREDELIM: /* <<,<<- delimiter */
/* XXX chuck this state (and the next) - use
* the existing states ($ and \`..` should be
* stripped of their specialness after the
* fact).
*/
/* here delimiters need a special case since
* $ and `..` are not to be treated specially
*/
if (c == '\\') {
c = getsc();
if (c) { /* trailing \ is lost */
*wp++ = QCHAR;
*wp++ = c;
}
} else if (c == '\'') {
PUSH_STATE(SSQUOTE);
*wp++ = OQUOTE;
ignore_backslash_newline++;
} else if (c == '"') {
state = statep->ls_state = SHEREDQUOTE;
*wp++ = OQUOTE;
} else {
*wp++ = CHAR;
*wp++ = c;
}
break;
case SHEREDQUOTE: /* " in <<,<<- delimiter */
if (c == '"') {
*wp++ = CQUOTE;
state = statep->ls_state = SHEREDELIM;
} else {
if (c == '\\') {
switch (c = getsc()) {
case '\\': case '"':
case '$': case '`':
break;
default:
if (c) { /* trailing \ lost */
*wp++ = CHAR;
*wp++ = '\\';
}
break;
}
}
*wp++ = CHAR;
*wp++ = c;
}
break;
case SPATTERN: /* in *(...|...) pattern (*+?@!) */
if ( /*(*/ c == ')') {
*wp++ = CPAT;
POP_STATE();
} else if (c == '|') {
*wp++ = SPAT;
} else if (c == '(') {
*wp++ = OPAT;
*wp++ = ' '; /* simile for @ */
PUSH_STATE(SPATTERN);
} else
goto Sbase1;
break;
}
}
Done:
Xcheck(ws, wp);
if (statep != &states[1])
/* XXX figure out what is missing */
yyerror("no closing quote\n");
/* This done to avoid tests for SHEREDELIM wherever SBASE tested */
if (state == SHEREDELIM)
state = SBASE;
dp = Xstring(ws, wp);
if ((c == '<' || c == '>') && state == SBASE &&
((c2 = Xlength(ws, wp)) == 0 ||
(c2 == 2 && dp[0] == CHAR && digit(dp[1])))) {
struct ioword *iop = alloc(sizeof(*iop), ATEMP);
if (c2 == 2)
iop->unit = dp[1] - '0';
else
iop->unit = c == '>'; /* 0 for <, 1 for > */
c2 = getsc();
/* <<, >>, <> are ok, >< is not */
if (c == c2 || (c == '<' && c2 == '>')) {
iop->flag = c == c2 ?
(c == '>' ? IOCAT : IOHERE) : IORDWR;
if (iop->flag == IOHERE) {
if ((c2 = getsc()) == '-')
iop->flag |= IOSKIP;
else
ungetsc(c2);
}
} else if (c2 == '&')
iop->flag = IODUP | (c == '<' ? IORDUP : 0);
else {
iop->flag = c == '>' ? IOWRITE : IOREAD;
if (c == '>' && c2 == '|')
iop->flag |= IOCLOB;
else
ungetsc(c2);
}
iop->name = NULL;
iop->delim = NULL;
iop->heredoc = NULL;
Xfree(ws, wp); /* free word */
yylval.iop = iop;
return REDIR;
}
if (wp == dp && state == SBASE) {
Xfree(ws, wp); /* free word */
/* no word, process LEX1 character */
switch (c) {
default:
return c;
case '|':
case '&':
case ';':
if ((c2 = getsc()) == c)
c = (c == ';') ? BREAK :
(c == '|') ? LOGOR :
(c == '&') ? LOGAND :
YYERRCODE;
else if (c == '|' && c2 == '&')
c = COPROC;
else
ungetsc(c2);
return c;
case '\n':
gethere();
if (cf & CONTIN)
goto Again;
return c;
case '(': /*)*/
if (!Flag(FSH)) {
if ((c2 = getsc()) == '(') /*)*/
/* XXX need to handle ((...); (...)) */
c = MDPAREN;
else
ungetsc(c2);
}
return c;
/*(*/
case ')':
return c;
}
}
*wp++ = EOS; /* terminate word */
yylval.cp = Xclose(ws, wp);
if (state == SWORD || state == SLETPAREN) /* ONEWORD? */
return LWORD;
ungetsc(c); /* unget terminator */
/* copy word to unprefixed string ident */
for (sp = yylval.cp, dp = ident; dp < ident+IDENT && (c = *sp++) == CHAR; )
*dp++ = *sp++;
/* Make sure the ident array stays '\0' padded */
memset(dp, 0, (ident+IDENT) - dp + 1);
if (c != EOS)
*ident = '\0'; /* word is not unquoted */
if (*ident != '\0' && (cf&(KEYWORD|ALIAS))) {
struct tbl *p;
int h = hash(ident);
/* { */
if ((cf & KEYWORD) && (p = ktsearch(&keywords, ident, h)) &&
(!(cf & ESACONLY) || p->val.i == ESAC || p->val.i == '}')) {
afree(yylval.cp, ATEMP);
return p->val.i;
}
if ((cf & ALIAS) && (p = ktsearch(&aliases, ident, h)) &&
(p->flag & ISSET)) {
Source *s;
for (s = source; s->type == SALIAS; s = s->next)
if (s->u.tblp == p)
return LWORD;
/* push alias expansion */
s = pushs(SALIAS, source->areap);
s->start = s->str = p->val.s;
s->u.tblp = p;
s->next = source;
source = s;
afree(yylval.cp, ATEMP);
goto Again;
}
}
return LWORD;
}
static void
gethere(void)
{
struct ioword **p;
for (p = heres; p < herep; p++)
readhere(*p);
herep = heres;
}
/*
* read "<<word" text into temp file
*/
static void
readhere(struct ioword *iop)
{
int c;
char *volatile eof;
char *eofp;
int skiptabs;
XString xs;
char *xp;
int xpos;
eof = evalstr(iop->delim, 0);
if (!(iop->flag & IOEVAL))
ignore_backslash_newline++;
Xinit(xs, xp, 256, ATEMP);
for (;;) {
eofp = eof;
skiptabs = iop->flag & IOSKIP;
xpos = Xsavepos(xs, xp);
while ((c = getsc()) != 0) {
if (skiptabs) {
if (c == '\t')
continue;
skiptabs = 0;
}
if (c != *eofp)
break;
Xcheck(xs, xp);
Xput(xs, xp, c);
eofp++;
}
/* Allow EOF here so commands with out trailing newlines
* will work (eg, ksh -c '...', $(...), etc).
*/
if (*eofp == '\0' && (c == 0 || c == '\n')) {
xp = Xrestpos(xs, xp, xpos);
break;
}
ungetsc(c);
while ((c = getsc()) != '\n') {
if (c == 0)
yyerror("here document `%s' unclosed\n", eof);
Xcheck(xs, xp);
Xput(xs, xp, c);
}
Xcheck(xs, xp);
Xput(xs, xp, c);
}
Xput(xs, xp, '\0');
iop->heredoc = Xclose(xs, xp);
if (!(iop->flag & IOEVAL))
ignore_backslash_newline--;
}
void
yyerror(const char *fmt, ...)
{
va_list va;
/* pop aliases and re-reads */
while (source->type == SALIAS || source->type == SREREAD)
source = source->next;
source->str = null; /* zap pending input */
error_prefix(true);
va_start(va, fmt);
shf_vfprintf(shl_out, fmt, va);
va_end(va);
errorf(NULL);
}
/*
* input for yylex with alias expansion
*/
Source *
pushs(int type, Area *areap)
{
Source *s;
s = alloc(sizeof(Source), areap);
s->type = type;
s->str = null;
s->start = NULL;
s->line = 0;
s->cmd_offset = 0;
s->errline = 0;
s->file = NULL;
s->flags = 0;
s->next = NULL;
s->areap = areap;
if (type == SFILE || type == SSTDIN) {
char *dummy;
Xinit(s->xs, dummy, 256, s->areap);
} else
memset(&s->xs, 0, sizeof(s->xs));
return s;
}
static int
getsc__(void)
{
Source *s = source;
int c;
while ((c = *s->str++) == 0) {
s->str = NULL; /* return 0 for EOF by default */
switch (s->type) {
case SEOF:
s->str = null;
return 0;
case SSTDIN:
case SFILE:
getsc_line(s);
break;
case SWSTR:
break;
case SSTRING:
break;
case SWORDS:
s->start = s->str = *s->u.strv++;
s->type = SWORDSEP;
break;