summaryrefslogtreecommitdiffstats
path: root/eshtrans/frontend/lexer.esh
blob: 6eb168a79d034375cc7de415cc0687e11d4b0fb4 (plain)
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
# Eggshell lexer
#
# Copyright (C) 2016  Patrick "P. J." McDermott
#
# This file is part of the Eggshell Compiler.
#
# The Eggshell Compiler 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 of
# the License, or (at your option) any later version.
#
# The Eggshell Compiler 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 the Eggshell Compiler.  If not, see
# <http://www.gnu.org/licenses/>.

#dbg=false

fname=
lineno=
ln_off=
start=
c=
wordexp=
here_queue=
here_awaiting_end=
here_awaiting_word=
tok=

#dbg()
#{
#	if ${dbg}; then
#		printf 'DEBUG: %s\n' "${@}" >&2
#	fi
#}

#
# Error handling (used by scanning and interface functions)
#

error()
{
	local fmt="${1}"
	shift 1

	case "${fname}" in
		'-')
			printf "stdin:%d: ${fmt}\n" ${lineno} "${@}" >&2
			;;
		*)
			printf "%s:%d: ${fmt}\n" "${fname}" ${lineno} "${@}" >&2
			;;
	esac

	# The parser and lexer run in a subshell, so this just returns up to the
	# caller like an exception.
	exit 1
}

synexp()
{
	local t="${1}"
	shift 1

	if [ "x${t}" = 'x' ]; then
		synerr '%s unexpected' "$(tokname "${tok}")"
	else
		synerr '%s unexpected (expecting %s)' "$(tokname "${tok}")" \
			"$(tokname "${t}")"
	fi
}

synerr()
{
	local fmt="${1}"
	shift 1

	error "Syntax error: ${fmt}" "${@}"
}

#
# Input reading
#

lgetc()
{
	if [ ${lbufi} -ge ${lbufc} ]; then
		c=''
	else
		eval "c=\${lbufv_${lbufi}}"
		#echo "LGETC:$lineno: $lbufi '$c'" >&2
		lbufi=$((${lbufi} + 1))
	fi
}

lungetc()
{
	lbufi=$((${lbufi} - 2))
	eval "c=\${lbufv_${lbufi}}"
	#echo "LUNGETC:$lineno: $lbufi '$c'" >&2
	lbufi=$((${lbufi} + 1))
}

lsetc()
{
	lbufi=$((${lbufi} - 1))
	eval "c=\${lbufv_${lbufi}}"
	#echo "LSETC:$lineno: $lbufi '$c'" >&2
	lbufi=$((${lbufi} + 1))
}

#
# Token recognition
#

next()
{
	if ${here_awaiting_word}; then
		next_here
		return
	fi
	while :; do
		#dbg "parsing char '$c' at lineno $lineno"
		case "${c}" in
			'')
				lgetc
				tok=T_EOF
				return
				;;
			"${LF}")
				if ${here_awaiting_end}; then
					synexp ''
				else
					case "${here_queue}" in *"${RS}"*)
						here_awaiting_end=false
						here_awaiting_word=true
						;;
					esac
				fi
				lgetc
				lineno=$((${lineno} + 1))
				tok=T_NEWLINE
				return
				;;
			' '|"${HT}")
				lgetc
				continue
				;;
			\\)
				lgetc
				case "${c}" in "${LF}")
					lineno=$((${lineno} + 1))
					lgetc
					continue
					;;
				esac
				lungetc
				next_word
				return
				;;
			'#')
				lgetc
				while :; do
					case "${c}" in "${LF}"|'')
						break
						;;
					esac
					lgetc
				done
				continue
				;;
			'&')
				lgetc
				case "${c}" in '&')
					lgetc
					tok=T_AND_IF
					return
					;;
				esac
				tok=T_AND
				return
				;;
			'|')
				lgetc
				case "${c}" in '|')
					lgetc
					tok=T_OR_IF
					return
					;;
				esac
				tok=T_PIPE
				return
				;;
			';')
				lgetc
				case "${c}" in ';')
					lgetc
					tok=T_DSEMI
					return
					;;
				esac
				#dbg T_SEMI
				tok=T_SEMI
				return
				;;
			'(')
				lgetc
				tok=T_LPAREN
				return
				;;
			')')
				lgetc
				tok=T_RPAREN
				return
				;;
			'<'|'>')
				next_io
				return
				;;
			*)
				next_word
				return
				;;
		esac
		lgetc
	done
}

next_here()
{
	local here=
	local here_strip_tabs=
	local here_end=
	local here_escaped=
	local line=
	local word=
	local res=

	# Dequeue the here-document.
	here="${here_queue%%${RS}*}"
	here_strip_tabs="${here%%${US}*}"
	here_end="${here%${US}*}"
	here_end="$(printf '%s' "${here_end#*${US}}" | \
		sed 's/\\//g; s/"//g; s/'\''//g;')"  # Stupid Vim: ')"
	here_escaped="${here##*${US}}"
	here_queue="${here_queue#*${RS}}"
	here_awaiting_word=false

	line=''
	word=''
	while :; do
		case "${c}" in
			'')
				# Bash throws a warning when EOF occurs in a
				# here document.  mksh throws an error.  dash,
				# BusyBox ash, ksh93, and zsh accept EOF as a
				# delimiter.  We aim for the lowest common
				# denominator, so throw an error like mksh does.
				synerr 'Here-document "%s" unclosed' \
					"${here_end}"
				;;
			"${LF}")
				word="${word}${line}"
				case "${line}" in "${here_end}")
					tok="T_WORD${US}${word}"
					return
					;;
				esac
				word="${word}${c}"
				line=''
				;;
			"${HT}")
				if ${here_strip_tabs}; then
					case "${line}" in
						'')
							;;
						*)
							line="${line}${c}"
							;;
					esac
				else
					line="${line}${c}"
				fi
				;;
			'$')
				if ! ${here_escaped}; then
					lgetc
					if ! res="$(scan_wordexp)"; then
						exit 1
					fi
					ln_off=${res%%${RS}*}
					res="${res#*${RS}}"
					lbufi="${res%%${RS}*}"
					lsetc
					res="${res#*${RS}}"
					lineno=$((${lineno} + ${ln_off}))
					line="${line}${res}"
					continue
				else
					line="${line}${c}"
				fi
				;;
			*)
				line="${line}${c}"
				;;
		esac
		lgetc
	done
}

next_io()
{
	case "${c}" in
		'<')
			lgetc
			case "${c}" in
				'<')
					lgetc
					case "${c}" in '-')
						lgetc
						tok=T_DLESSDASH
						here_queue="${here_queue}true"
						here_awaiting_end=true
						here_awaiting_word=false
						break
						;;
					esac
					tok=T_DLESS
					here_queue="${here_queue}false"
					here_awaiting_end=true
					here_awaiting_word=false
					break
					;;
				'&')
					lgetc
					tok=T_LESSAND
					break
					;;
				'>')
					lgetc
					tok=T_LESSGREAT
					break
					;;
			esac
			tok=T_LESS
			break
			;;
		'>')
			lgetc
			case "${c}" in
				'>')
					lgetc
					tok=T_DGREAT
					break
					;;
				'&')
					lgetc
					tok=T_GREATAND
					break
					;;
				'|')
					lgetc
					tok=T_CLOBBER
					break
					;;
			esac
			tok=T_GREAT
			break
			;;
	esac
}

next_word()
{
	local res=

	if ! res="$(scan_word false)"; then
		exit 1
	fi
	ln_off=${res%%${RS}*}
	res="${res#*${RS}}"
	lbufi="${res%%${RS}*}"
	lsetc
	res="${res#*${RS}}"

	# We must advance lineno because scan_word() was run in a subshell.
	lineno=$((${lineno} + ${ln_off}))
	tok="T_WORD${US}${res}"

	if ${here_awaiting_end}; then
		here_queue="${here_queue}${US}${res}"
		case "${res}" in
			*\\*|*'"'*|*"'"*)
				here_queue="${here_queue}${US}true"
				;;
			*)
				here_queue="${here_queue}${US}false"
				;;
		esac
		here_queue="${here_queue}${RS}"
		here_awaiting_end=false
	fi
}

#
# Token scanning
#

scan_word()
{
	local in_param="${1}"
	shift 1
	local lines=
	local word=
	local quoted=
	local tmp_c=
	local res=

	lines=0
	word=''
	quoted=false

	while :; do
		#dbg "parsing word char '$c' at lineno $lineno"
		case "${c}" in
			'')
				break
				;;
			"${LF}")
				if ! ${in_param} && ! ${quoted}; then
					break
				fi
				lineno=$((${lineno} + 1))
				lines=$((${lines} + 1))
				word="${word}${c}"
				;;
			' '|"${HT}"|'&'|'|'|';'|'('|')'|'<'|'>')
				if ! ${in_param} && ! ${quoted}; then
					break
				fi
				word="${word}${c}"
				;;
			'$')
				case "${here_queue}" in *"${RS}"*)
					if ${here_awaiting_end}; then
						synerr '%s %s %s %s' \
							'Word expansions' \
							'not supported in' \
							'here-document' \
							'delimiters'
					fi
					;;
				esac
				lgetc
				if ! res="$(scan_wordexp)"; then
					exit 1
				fi
				ln_off=${res%%${RS}*}
				res="${res#*${RS}}"
				lbufi="${res%%${RS}*}"
				lsetc
				res="${res#*${RS}}"
				# We must advance lineno because scan_wordexp()
				# was run in a subshell.
				lineno=$((${lineno} + ${ln_off}))
				lines=$((${lines} + ${ln_off}))
				word="${word}${res}"
				# scan_wordexp() leaves behind an unused
				# character, so we should skip the lgetc() call
				# below.
				continue
				;;
			'`')
				synerr 'Backquoted (old-style) %s' \
					'command substitution not supported'
				break
				;;
			\\)
				#dbg 'first backslash in word'
				word="${word}${c}"
				lgetc
				#dbg "next char: '$c'"
				case "${c}" in '')
					# Bash, ksh93, mksh, and zsh ignore a
					# backslash at the end of a file, but
					# dash and BusyBox ash include it in the
					# word.  To help with script
					# portability, we'll throw an error
					# (which is a reasonable thing to do
					# anyway).
					synerr 'Unexpected end of file %s' \
						'after "\"'
					;;
				esac
				word="${word}${c}"
				;;
			\')
				word="${word}${c}"
				if ${quoted}; then
					lgetc
					continue
				fi
				while :; do
					lgetc
					word="${word}${c}"
					case "${c}" in
						'')
							synerr '%s %s' \
								'Unterminated' \
								'quoted string'
							;;
						"${LF}")
							lineno=$((${lineno} +1))
							lines=$((${lines} + 1))
							;;
						\')
							break
							;;
					esac
				done
				;;
			'"')
				word="${word}${c}"
				if ${quoted}; then
					quoted=false
				else
					quoted=true
				fi
				;;
			'}')
				if ${in_param} && ! ${quoted}; then
					break
				fi
				word="${word}${c}"
				;;
			*)
				word="${word}${c}"
				;;
		esac
		lgetc
	done

	if ${quoted}; then
		synerr 'Unterminated quoted string'
	fi

	printf "%d${RS}%d${RS}%s" ${lines} ${lbufi} "${word}"
}

scan_wordexp()
{
	local res=

	wordexp=''
	ln_off=0
	case "${c}" in
		'{')
			# Parameter expansion brace
			scan_wordexp_param_brace
			;;
		'(')
			# Arithmetic expansion or command substitution
			lgetc
			case "${c}" in
				'(')
					# Arithmetic expansion
					scan_wordexp_arith
					;;
				*)
					# Command substitution
					if ! res="$(run_sublexer "sub${fname}" \
							${lineno} "${start}" \
							${lbufi})"; then
						exit 1
					fi
					lbufi="${res##*${RS}}"
					lsetc
					res="${res%${RS}*}"
					ln_off=${res##*${RS}}
					res="${res%${RS}*}"
					ln_off=$((${ln_off} - ${lineno}))
					lineno=$((${lineno} + ${ln_off}))
					wordexp="\$(${SOH}C${STX}${res}"
					wordexp="${wordexp}${ETX})"
					# ")" is recognized in run_sublexer().
					;;
			esac
			;;
		[@*#?\$!A-Za-z0-9_-])
			if ! res="$(scan_param)"; then
				exit 1
			fi
			ln_off=${res%%${RS}*}
			res="${res#*${RS}}"
			lbufi="${res%%${RS}*}"
			lsetc
			res="${res#*${RS}}"
			lineno=$((${lineno} + ${ln_off}))
			wordexp="\$${res}"
			;;
	esac

	printf "%d${RS}%d${RS}%s" ${ln_off} ${lbufi} "${wordexp}"
	return 0
}

scan_wordexp_param_brace()
{
	local mod=
	local res=
	local param=

	mod=true

	lgetc
	case "${c}" in
		'#')
			lgetc
			case "${c}" in
				[@*#?\$!A-Za-z0-9_-])
					# String length expansion
					if ! res="$(scan_param)"; then
						exit 1
					fi
					ln_off=${res%%${RS}*}
					res="${res#*${RS}}"
					lbufi="${res%%${RS}*}"
					lsetc
					res="${res#*${RS}}"
					param="#${res}"
					lineno=$((${lineno} + ${ln_off}))
					# Disable modifications.
					mod=false
					;;
				*)
					# Special parameter "#"
					param='#'
					;;
			esac
			;;
		*)
			if ! res="$(scan_param)"; then
				exit 1
			fi
			ln_off=${res%%${RS}*}
			res="${res#*${RS}}"
			lbufi="${res%%${RS}*}"
			lsetc
			res="${res#*${RS}}"
			param="${res}"
			lineno=$((${lineno} + ${ln_off}))
			;;
	esac
	wordexp="\${${param}"

	# If modifications are allowed
	if ${mod}; then
		# Check for modifications.
		mod=false
		case "${c}" in
			':')
				mod=true
				wordexp="${wordexp}${c}"
				lgetc
				case "${c}" in '-'|'='|'?'|'+')
					wordexp="${wordexp}${c}"
					lgetc
				;;
				esac
				;;
			'-'|'='|'?'|'+')
				mod=true
				wordexp="${wordexp}${c}"
				lgetc
				;;
			'%')
				mod=true
				wordexp="${wordexp}${c}"
				lgetc
				case "${c}" in '%')
					wordexp="${wordexp}${c}"
					lgetc
					;;
				esac
				;;
			'#')
				mod=true
				wordexp="${wordexp}${c}"
				lgetc
				case "${c}" in '#')
					wordexp="${wordexp}${c}"
					lgetc
					;;
				esac
				;;
		esac
	fi

	# If a modification was found
	if ${mod}; then
		# Get word.
		if ! res="$(scan_word true)"; then
			exit 1
		fi
		ln_off=${res%%${RS}*}
		res="${res#*${RS}}"
		lbufi="${res%%${RS}*}"
		lsetc
		res="${res#*${RS}}"
		# We must advance lineno because scan_word() was run in a
		# subshell.
		lineno=$((${lineno} + ${ln_off}))
		wordexp="${wordexp}${res}"
		#dbg "param mod word: '$res'"
	fi

	# Check for right brace.
	case "${c}" in
		'}')
			wordexp="${wordexp}${c}"
			lgetc
			;;
		*)
			synerr 'Missing "}"'
			;;
	esac

	return 0
}

scan_param()
{
	local param=

	param=''
	case "${c}" in
		[@*#?\$!0-])
			# Special parameter
			param="${c}"
			lgetc
			;;
		[1-9])
			# Positional parameter
			param="${param}${c}"
			lgetc
			while :; do
				case "${c}" in [!0-9])
					break
					;;
				esac
				param="${param}${c}"
				lgetc
			done
			;;
		[A-Za-z_])
			# Parameter name
			param="${param}${c}"
			lgetc
			while :; do
				case "${c}" in [!A-Za-z0-9_])
					break
					;;
				esac
				param="${param}${c}"
				lgetc
			done
			;;
		*)
			synerr 'Bad parameter name'
			;;
	esac

	printf "%d${RS}%d${RS}%s" 0 ${lbufi} "${param}"
	return 0
}

scan_wordexp_arith()
{
	local arith=
	local paren_lvl=
	local res=

	arith=''
	paren_lvl=0
	lgetc
	while :; do
		case "${c}" in
			'')
				synerr 'end of file unexpected (%s)' \
					'expecting "))"'
				;;
			'(')
				arith="${arith}${c}"
				paren_lvl=$((${paren_lvl} + 1))
				;;
			')')
				if [ ${paren_lvl} -eq 0 ]; then
					lgetc
					case "${c}" in ')')
						wordexp="\$((${arith}))"
						lgetc
						return 0
						;;
					esac
					synerr 'Arithmetic expansion: ")" %s' \
						'unexpected'
				fi
				arith="${arith}${c}"
				paren_lvl=$((${paren_lvl} - 1))
				;;
			'$')
				lgetc
				if ! res="$(scan_wordexp)"; then
					exit 1
				fi
				ln_off=${res%%${RS}*}
				res="${res#*${RS}}"
				lbufi="${res%%${RS}*}"
				lsetc
				res="${res#*${RS}}"
				# We must advance lineno because scan_wordexp()
				# was run in a subshell.
				lineno=$((${lineno} + ${ln_off}))
				arith="${arith}${res}"
				continue
				;;
			*)
				arith="${arith}${c}"
				;;
		esac
		lgetc
	done
}

run_sublexer()
{
	local fn="${1}"
	local ln="${2}"
	local st="${3}"
	local i="${4}"
	shift 4

	# Initialize global variables.
	fname="${fn}"
	lineno=${ln}
	start="${st}"
	here_queue=''
	here_awaiting_end=false
	here_awaiting_word=false

	lbufi="${i}"
	lsetc
	next

	#dbg=true
	# If this returns (does not exit), there are no errors.
	${start}
	case "${tok%${US}*}" in
		T_RPAREN)
			;;
		*)
			synerr 'Missing ")"'
			;;
	esac

	printf "${RS}%d${RS}%d" ${lineno} ${lbufi}
	return 0
}

#
# Interface
#

run_lexer()
{
	local fn="${1}"
	local buf="${2}"
	local st="${3}"
	shift 3

	# Initialize global variables.
	fname="${fn}"
	lineno=1
	start="${st}"
	here_queue=''
	here_awaiting_end=false
	here_awaiting_word=false

	# Read file into array
	eval "$(printf '%s' "${buf}" | awk -v FS='' -v j=0 \
		-v squote="'" -v esc_squote="'\\\\''" '
		{
			for (i = 1; i <= NF; ++i) {
				sub(squote, esc_squote, $i);
				printf("lbufv_%d='\''%s'\''\n", j++, $i);
			};
			printf("lbufv_%d='\''\n'\''\n", j++);
		}
		')"
	lbufi=0
	lbufc=${#buf}

	# Read the first character and recognize the first token.
	lgetc
	next

	if ! ${start}; then
		# Unexpected EOF
		synexp ''
	fi
	if ! accept T_EOF; then
		synexp ''
	fi

	return 0
}

accept()
{
	local t="${1}"
	shift 1
	local rw=

	#dbg "looking for $t, current tok ${tok%%${US}*}"
	case "${t}" in
		T_IF|T_THEN|T_ELSE|T_ELIF|T_FI|T_DO|T_DONE|\
		T_CASE|T_ESAC|T_WHILE|T_UNTIL|T_FOR|\
		T_LBRACE|T_RBRACE|T_BANG|T_IN|\
		T_USE|T_STATIC|T_LOCAL|T_RETURN)
			#dbg "looking for reserved word $t, have '$tok'"
			if ! [ "x${tok%%${US}*}" = "x${t}" ]; then
				# Reserved words are recognized as literal
				# T_WORDs.
				if ! [ "x${tok%%${US}*}" = 'xT_WORD' ]; then
					return 1
				fi
				# T_WORD data unit must match reserved word
				# exactly.
				if ! [ "x${tok#T_WORD${US}}" = \
						"x$(toktext "${t}")" ]; then
					return 1
				fi
				# If the token matches the reserved word,
				# replace it with the reserved word token.
				tok="${t}"
			fi
			;;
		T_NAME)
			# Names are recognized as literal T_WORDs.
			if ! [ "x${tok%%${US}*}" = 'xT_WORD' ]; then
				return 1
			fi
			# Validate name.
			case "${tok#*${US}}" in
				[!A-Za-z_]*)
					return 1
					;;
				*[!0-9A-Za-z_]*)
					return 1
					;;
			esac
			tok="T_NAME${US}${tok#T_WORD${US}}"
			;;
		T_FNAME)
			# Function names are recognized as literal T_WORDs.
			if ! [ "x${tok%%${US}*}" = 'xT_WORD' ]; then
				return 1
			fi
			# Validate name.
			case "${tok#*${US}}" in
				[!A-Za-z_]*)
					return 1
					;;
				*[!0-9A-Za-z_]*)
					return 1
					;;
			esac
			# Verify that the function name doesn't match any
			# reserved words.
			for rw in T_IF T_THEN T_ELSE T_ELIF T_FI T_DO T_DONE \
					T_CASE T_ESAC T_WHILE T_UNTIL T_FOR \
					T_LBRACE T_RBRACE T_BANG T_IN \
					T_USE T_STATIC T_LOCAL T_RETURN; do
				if [ "x${tok#T_WORD${US}}" = \
						"x$(toktext "${rw}")" ]; then
					tok="${rw}"
					return 1
				fi
			done
			tok="T_FNAME${US}${tok#T_WORD${US}}"
			;;
		T_CMDNAME)
			# The first word of a simple command is to be checked
			# for reserved words.
			if ! [ "x${tok%%${US}*}" = 'xT_WORD' ]; then
				return 1
			fi
			# Verify that the word doesn't match any reserved words.
			for rw in T_IF T_THEN T_ELSE T_ELIF T_FI T_DO T_DONE \
					T_CASE T_ESAC T_WHILE T_UNTIL T_FOR \
					T_LBRACE T_RBRACE T_BANG T_IN \
					T_USE T_STATIC T_LOCAL T_RETURN; do
				if [ "x${tok#T_WORD${US}}" = \
						"x$(toktext "${rw}")" ]; then
					tok="${rw}"
					return 1
				fi
			done
			tok="T_CMDNAME${US}${tok#T_WORD${US}}"
			;;
		T_IO_NUMBER)
			# I/O numbers are recognized as literal T_WORDs.
			if ! [ "x${tok%%${US}*}" = 'xT_WORD' ]; then
				return 1
			fi
			# Validate number.
			case "${tok#*${US}}" in
				*[!0-9]*)
					return 1
					;;
			esac
			tok="T_IO_NUMBER${US}${tok#T_WORD${US}}"
			;;
		*)
			if ! [ "x${tok%%${US}*}" = "x${t}" ]; then
				return 1
			fi
			;;
	esac

	#dbg "accept $t"
	printf '%s' "${tok}${RS}"
	next
	return 0
}

expect()
{
	local t="${1}"
	shift 1

	if accept "${t}"; then
		return 0
	else
		synexp "${t}"
	fi
}

inject()
{
	local t="${1}"
	shift 1

	printf '%s' "${t}${RS}"
	return 0
}