summary refs log tree commit diff
path: root/Src/lex.c
blob: e0935bf05ea7f52bbb1f4af0feb1bc5d5ac11ff8 (plain) (blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
/*
 * lex.c - lexical analysis
 *
 * This file is part of zsh, the Z shell.
 *
 * Copyright (c) 1992-1997 Paul Falstad
 * All rights reserved.
 *
 * Permission is hereby granted, without written agreement and without
 * license or royalty fees, to use, copy, modify, and distribute this
 * software and to distribute modified versions of this software for any
 * purpose, provided that the above copyright notice and the following
 * two paragraphs appear in all copies of this software.
 *
 * In no event shall Paul Falstad or the Zsh Development Group be liable
 * to any party for direct, indirect, special, incidental, or consequential
 * damages arising out of the use of this software and its documentation,
 * even if Paul Falstad and the Zsh Development Group have been advised of
 * the possibility of such damage.
 *
 * Paul Falstad and the Zsh Development Group specifically disclaim any
 * warranties, including, but not limited to, the implied warranties of
 * merchantability and fitness for a particular purpose.  The software
 * provided hereunder is on an "as is" basis, and Paul Falstad and the
 * Zsh Development Group have no obligation to provide maintenance,
 * support, updates, enhancements, or modifications.
 *
 */

#include "zsh.mdh"
#include "lex.pro"

#define LEX_HEAP_SIZE (32)

/* tokens */

/**/
mod_export char ztokens[] = "#$^*(())$=|{}[]`<>>?~`,-!'\"\\\\";

/* parts of the current token */

/**/
char *zshlextext;
/**/
mod_export char *tokstr;
/**/
mod_export enum lextok tok;
/**/
mod_export int tokfd;

/*
 * Line number at which the first character of a token was found.
 * We always set this in gettok(), which is always called from
 * zshlex() unless we have reached an error.  So it is always
 * valid when parsing.  It is not useful during execution
 * of the parsed structure.
 */

/**/
zlong toklineno;

/* lexical analyzer error flag */
 
/**/
mod_export int lexstop;

/* if != 0, this is the first line of the command */
 
/**/
mod_export int isfirstln;
 
/* if != 0, this is the first char of the command (not including white space) */
 
/**/
int isfirstch;

/* flag that an alias should be expanded after expansion ending in space */

/**/
int inalmore;

/*
 * Don't do spelling correction.
 * Bit 1 is only valid for the current word.  It's
 * set when we detect a lookahead that stops the word from
 * needing correction.
 */
 
/**/
int nocorrect;

/*
 * TBD: the following exported variables are part of the non-interface
 * with ZLE for completion.  They are poorly named and the whole
 * scheme is incredibly brittle.  One piece of robustness is applied:
 * the variables are only set if LEXFLAGS_ZLE is set.  Improvements
 * should therefore concentrate on areas with this flag set.
 *
 * Cursor position and line length in zle when the line is
 * metafied for access from the main shell.
 */

/**/
mod_export int zlemetacs, zlemetall;

/* inwhat says what exactly we are in     *
 * (its value is one of the IN_* things). */

/**/
mod_export int inwhat;

/* 1 if x added to complete in a blank between words */

/**/
mod_export int addedx;

/* wb and we hold the beginning/end position of the word we are completing. */

/**/
mod_export int wb, we;

/**/
mod_export int wordbeg;

/**/
mod_export int parbegin;

/**/
mod_export int parend;


/* 1 if aliases should not be expanded */

/**/
mod_export int noaliases;

/*
 * If non-zero, we are parsing a line sent to use by the editor, or some
 * other string that's not part of standard command input (e.g. eval is
 * part of normal command input).
 *
 * Set of bits from LEXFLAGS_*.
 *
 * Note that although it is passed into the lexer as an input, the
 * lexer can set it to zero after finding the word it's searching for.
 * This only happens if the line being parsed actually does come from
 * ZLE, and hence the bit LEXFLAGS_ZLE is set.
 */

/**/
mod_export int lexflags;

/* don't recognize comments */

/**/
mod_export int nocomments;

/* add raw input characters while parsing command substitution */

/**/
static int lex_add_raw;

/* variables associated with the above */

static char *tokstr_raw;
static struct lexbufstate lexbuf_raw;

/* text of punctuation tokens */

/**/
mod_export char *tokstrings[WHILE + 1] = {
    NULL,	/* NULLTOK	  0  */
    ";",	/* SEPER	     */
    "\\n",	/* NEWLIN	     */
    ";",	/* SEMI		     */
    ";;",	/* DSEMI	     */
    "&",	/* AMPER	  5  */
    "(",	/* INPAR	     */
    ")",	/* OUTPAR	     */
    "||",	/* DBAR		     */
    "&&",	/* DAMPER	     */
    ">",	/* OUTANG	  10 */
    ">|",	/* OUTANGBANG	     */
    ">>",	/* DOUTANG	     */
    ">>|",	/* DOUTANGBANG	     */
    "<",	/* INANG	     */
    "<>",	/* INOUTANG	  15 */
    "<<",	/* DINANG	     */
    "<<-",	/* DINANGDASH	     */
    "<&",	/* INANGAMP	     */
    ">&",	/* OUTANGAMP	     */
    "&>",	/* AMPOUTANG	  20 */
    "&>|",	/* OUTANGAMPBANG     */
    ">>&",	/* DOUTANGAMP	     */
    ">>&|",	/* DOUTANGAMPBANG    */
    "<<<",	/* TRINANG	     */
    "|",	/* BAR		  25 */
    "|&",	/* BARAMP	     */
    "()",	/* INOUTPAR	     */
    "((",	/* DINPAR	     */
    "))",	/* DOUTPAR	     */
    "&|",	/* AMPERBANG	  30 */
    ";&",	/* SEMIAMP	     */
    ";|",	/* SEMIBAR	     */
};

/* lexical state */

static int dbparens;
static struct lexbufstate lexbuf = { NULL, 256, 0 };

/* save lexical context */

/**/
void
lex_context_save(struct lex_stack *ls, int toplevel)
{
    (void)toplevel;

    ls->dbparens = dbparens;
    ls->isfirstln = isfirstln;
    ls->isfirstch = isfirstch;
    ls->lexflags = lexflags;

    ls->tok = tok;
    ls->tokstr = tokstr;
    ls->zshlextext = zshlextext;
    ls->lexbuf = lexbuf;
    ls->lex_add_raw = lex_add_raw;
    ls->tokstr_raw = tokstr_raw;
    ls->lexbuf_raw = lexbuf_raw;
    ls->lexstop = lexstop;
    ls->toklineno = toklineno;

    tokstr = zshlextext = lexbuf.ptr = NULL;
    lexbuf.siz = 256;
    tokstr_raw = lexbuf_raw.ptr = NULL;
    lexbuf_raw.siz = lexbuf_raw.len = lex_add_raw = 0;
}

/* restore lexical context */

/**/
mod_export void
lex_context_restore(const struct lex_stack *ls, int toplevel)
{
    (void)toplevel;

    dbparens = ls->dbparens;
    isfirstln = ls->isfirstln;
    isfirstch = ls->isfirstch;
    lexflags = ls->lexflags;
    tok = ls->tok;
    tokstr = ls->tokstr;
    zshlextext = ls->zshlextext;
    lexbuf = ls->lexbuf;
    lex_add_raw = ls->lex_add_raw;
    tokstr_raw = ls->tokstr_raw;
    lexbuf_raw = ls->lexbuf_raw;
    lexstop = ls->lexstop;
    toklineno = ls->toklineno;
}

/**/
void
zshlex(void)
{
    if (tok == LEXERR)
	return;
    do {
	if (inrepeat_)
	    ++inrepeat_;
	if (inrepeat_ == 3 && isset(SHORTLOOPS))
	    incmdpos = 1;
	tok = gettok();
    } while (tok != ENDINPUT && exalias());
    nocorrect &= 1;
    if (tok == NEWLIN || tok == ENDINPUT) {
	while (hdocs) {
	    struct heredocs *next = hdocs->next;
	    char *doc, *munged_term;

	    hwbegin(0);
	    cmdpush(hdocs->type == REDIR_HEREDOC ? CS_HEREDOC : CS_HEREDOCD);
	    munged_term = dupstring(hdocs->str);
	    STOPHIST
	    doc = gethere(&munged_term, hdocs->type);
	    ALLOWHIST
	    cmdpop();
	    hwend();
	    if (!doc) {
		zerr("here document too large");
		while (hdocs) {
		    next = hdocs->next;
		    zfree(hdocs, sizeof(struct heredocs));
		    hdocs = next;
		}
		tok = LEXERR;
		break;
	    }
	    setheredoc(hdocs->pc, REDIR_HERESTR, doc, hdocs->str,
		       munged_term);
	    zfree(hdocs, sizeof(struct heredocs));
	    hdocs = next;
	}
    }
    if (tok != NEWLIN)
	isnewlin = 0;
    else
	isnewlin = (inbufct) ? -1 : 1;
    if (tok == SEMI || (tok == NEWLIN && !(lexflags & LEXFLAGS_NEWLINE)))
	tok = SEPER;
}

/**/
mod_export void
ctxtlex(void)
{
    static int oldpos;

    zshlex();
    switch (tok) {
    case SEPER:
    case NEWLIN:
    case SEMI:
    case DSEMI:
    case SEMIAMP:
    case SEMIBAR:
    case AMPER:
    case AMPERBANG:
    case INPAR:
    case INBRACE:
    case DBAR:
    case DAMPER:
    case BAR:
    case BARAMP:
    case INOUTPAR:
    case DOLOOP:
    case THEN:
    case ELIF:
    case ELSE:
    case DOUTBRACK:
	incmdpos = 1;
	break;
    case STRING:
    case TYPESET:
 /* case ENVSTRING: */
    case ENVARRAY:
    case OUTPAR:
    case CASE:
    case DINBRACK:
	incmdpos = 0;
	break;

    default:
	/* nothing to do, keep compiler happy */
	break;
    }
    if (tok != DINPAR)
	infor = tok == FOR ? 2 : 0;
    if (IS_REDIROP(tok) || tok == FOR || tok == FOREACH || tok == SELECT) {
	inredir = 1;
	oldpos = incmdpos;
	incmdpos = 0;
    } else if (inredir) {
	incmdpos = oldpos;
	inredir = 0;
    }
}

#define LX1_BKSLASH 0
#define LX1_COMMENT 1
#define LX1_NEWLIN 2
#define LX1_SEMI 3
#define LX1_AMPER 5
#define LX1_BAR 6
#define LX1_INPAR 7
#define LX1_OUTPAR 8
#define LX1_INANG 13
#define LX1_OUTANG 14
#define LX1_OTHER 15

#define LX2_BREAK 0
#define LX2_OUTPAR 1
#define LX2_BAR 2
#define LX2_STRING 3
#define LX2_INBRACK 4
#define LX2_OUTBRACK 5
#define LX2_TILDE 6
#define LX2_INPAR 7
#define LX2_INBRACE 8
#define LX2_OUTBRACE 9
#define LX2_OUTANG 10
#define LX2_INANG 11
#define LX2_EQUALS 12
#define LX2_BKSLASH 13
#define LX2_QUOTE 14
#define LX2_DQUOTE 15
#define LX2_BQUOTE 16
#define LX2_COMMA 17
#define LX2_DASH 18
#define LX2_BANG 19
#define LX2_OTHER 20
#define LX2_META 21

static unsigned char lexact1[256], lexact2[256], lextok2[256];

/**/
void
initlextabs(void)
{
    int t0;
    static char *lx1 = "\\q\n;!&|(){}[]<>";
    static char *lx2 = ";)|$[]~({}><=\\\'\"`,-!";

    for (t0 = 0; t0 != 256; t0++) {
       lexact1[t0] = LX1_OTHER;
	lexact2[t0] = LX2_OTHER;
	lextok2[t0] = t0;
    }
    for (t0 = 0; lx1[t0]; t0++)
	lexact1[(int)lx1[t0]] = t0;
    for (t0 = 0; lx2[t0]; t0++)
	lexact2[(int)lx2[t0]] = t0;
    lexact2['&'] = LX2_BREAK;
    lexact2[STOUC(Meta)] = LX2_META;
    lextok2['*'] = Star;
    lextok2['?'] = Quest;
    lextok2['{'] = Inbrace;
    lextok2['['] = Inbrack;
    lextok2['$'] = String;
    lextok2['~'] = Tilde;
    lextok2['#'] = Pound;
    lextok2['^'] = Hat;
}

/* initialize lexical state */

/**/
void
lexinit(void)
{
    nocorrect = dbparens = lexstop = 0;
    tok = ENDINPUT;
}

/* add a char to the string buffer */

/**/
void
add(int c)
{
    *lexbuf.ptr++ = c;
    if (lexbuf.siz == ++lexbuf.len) {
	int newbsiz = lexbuf.siz * 2;

	if (newbsiz > inbufct && inbufct > lexbuf.siz)
	    newbsiz = inbufct;

	tokstr = (char *)hrealloc(tokstr, lexbuf.siz, newbsiz);
	lexbuf.ptr = tokstr + lexbuf.len;
	/* len == bsiz, so bptr is at the start of newly allocated memory */
	memset(lexbuf.ptr, 0, newbsiz - lexbuf.siz);
	lexbuf.siz = newbsiz;
    }
}

#define SETPARBEGIN {							\
	if ((lexflags & LEXFLAGS_ZLE) && !(inbufflags & INP_ALIAS) &&	\
	    zlemetacs >= zlemetall+1-inbufct)				\
	    parbegin = inbufct;		      \
    }
#define SETPAREND {						      \
	if ((lexflags & LEXFLAGS_ZLE) && !(inbufflags & INP_ALIAS) && \
	    parbegin != -1 && parend == -1) {			      \
	    if (zlemetacs >= zlemetall + 1 - inbufct)		      \
		parbegin = -1;					      \
	    else						      \
		parend = inbufct;				      \
	}							      \
    }

enum {
    CMD_OR_MATH_CMD,
    CMD_OR_MATH_MATH,
    CMD_OR_MATH_ERR
};

/*
 * Return one of the above.  If it couldn't be
 * parsed as math, but there was no gross error, it's a command.
 */

static int
cmd_or_math(int cs_type)
{
    int oldlen = lexbuf.len;
    int c;
    int oinflags = inbufflags;

    cmdpush(cs_type);
    inbufflags |= INP_APPEND;
    c = dquote_parse(')', 0);
    if (!(oinflags & INP_APPEND))
	inbufflags &= ~INP_APPEND;
    cmdpop();
    *lexbuf.ptr = '\0';
    if (!c) {
	/* Successfully parsed, see if it was math */
	c = hgetc();
	if (c == ')')
	    return CMD_OR_MATH_MATH; /* yes */
	hungetc(c);
	lexstop = 0;
	c = ')';
    } else if (lexstop) {
	/* we haven't got anything to unget */
	return CMD_OR_MATH_ERR;
    }
    /* else unsuccessful: unget the whole thing */
    hungetc(c);
    lexstop = 0;
    while (lexbuf.len > oldlen && !(errflag & ERRFLAG_ERROR)) {
	lexbuf.len--;
	hungetc(itok(*--lexbuf.ptr) ?
		ztokens[*lexbuf.ptr - Pound] : *lexbuf.ptr);
    }
    if (errflag)
	return CMD_OR_MATH_ERR;
    hungetc('(');
    return errflag ? CMD_OR_MATH_ERR : CMD_OR_MATH_CMD;
}


/*
 * Parse either a $(( ... )) or a $(...)
 * Return the same as cmd_or_math().
 */
static int
cmd_or_math_sub(void)
{
    int c = hgetc(), ret;

    if (c == '(') {
	int lexpos = (int)(lexbuf.ptr - tokstr);
	add(Inpar);
	add('(');
	if ((ret = cmd_or_math(CS_MATHSUBST)) == CMD_OR_MATH_MATH) {
	    tokstr[lexpos] = Inparmath;
	    add(')');
	    return CMD_OR_MATH_MATH;
	}
	if (ret == CMD_OR_MATH_ERR)
	    return CMD_OR_MATH_ERR;
	lexbuf.ptr -= 2;
	lexbuf.len -= 2;
    } else {
	hungetc(c);
	lexstop = 0;
    }
    return skipcomm() ? CMD_OR_MATH_ERR : CMD_OR_MATH_CMD;
}

/* Check whether we're looking at valid numeric globbing syntax      *
 * (/\<[0-9]*-[0-9]*\>/).  Call pointing just after the opening "<". *
 * Leaves the input in the same place, returning 0 or 1.             */

/**/
static int
isnumglob(void)
{
    int c, ec = '-', ret = 0;
    int tbs = 256, n = 0;
    char *tbuf = (char *)zalloc(tbs);

    while(1) {
	c = hgetc();
	if(lexstop) {
	    lexstop = 0;
	    break;
	}
	tbuf[n++] = c;
	if(!idigit(c)) {
	    if(c != ec)
		break;
	    if(ec == '>') {
		ret = 1;
		break;
	    }
	    ec = '>';
	}
	if(n == tbs)
	    tbuf = (char *)realloc(tbuf, tbs *= 2);
    }
    while(n--)
	hungetc(tbuf[n]);
    zfree(tbuf, tbs);
    return ret;
}

/**/
static enum lextok
gettok(void)
{
    int c, d;
    int peekfd = -1;
    enum lextok peek;

  beginning:
    tokstr = NULL;
    while (iblank(c = hgetc()) && !lexstop);
    toklineno = lineno;
    if (lexstop)
	return (errflag) ? LEXERR : ENDINPUT;
    isfirstln = 0;
    if ((lexflags & LEXFLAGS_ZLE) && !(inbufflags & INP_ALIAS))
	wordbeg = inbufct - (qbang && c == bangchar);
    hwbegin(-1-(qbang && c == bangchar));
    /* word includes the last character read and possibly \ before ! */
    if (dbparens) {
	lexbuf.len = 0;
	lexbuf.ptr = tokstr = (char *) hcalloc(lexbuf.siz = LEX_HEAP_SIZE);
	hungetc(c);
	cmdpush(CS_MATH);
	c = dquote_parse(infor ? ';' : ')', 0);
	cmdpop();
	*lexbuf.ptr = '\0';
	if (!c && infor) {
	    infor--;
	    return DINPAR;
	}
	if (c || (c = hgetc()) != ')') {
	    hungetc(c);
	    return LEXERR;
	}
	dbparens = 0;
	return DOUTPAR;
    } else if (idigit(c)) {	/* handle 1< foo */
	d = hgetc();
	if(d == '&') {
	    d = hgetc();
	    if(d == '>') {
		peekfd = c - '0';
		hungetc('>');
		c = '&';
	    } else {
		hungetc(d);
		lexstop = 0;
		hungetc('&');
	    }
	} else if (d == '>' || d == '<') {
	    peekfd = c - '0';
	    c = d;
	} else {
	    hungetc(d);
	    lexstop = 0;
	}
    }

    /* chars in initial position in word */

    /*
     * Handle comments.  There are some special cases when this
     * is not normal command input: lexflags implies we are examining
     * a line lexically without it being used for normal command input.
     */
    if (c == hashchar && !nocomments &&
	(isset(INTERACTIVECOMMENTS) ||
	 ((!lexflags || (lexflags & LEXFLAGS_COMMENTS)) && !expanding &&
	  (!interact || unset(SHINSTDIN) || strin)))) {
	/* History is handled here to prevent extra  *
	 * newlines being inserted into the history. */

	if (lexflags & LEXFLAGS_COMMENTS_KEEP) {
	    lexbuf.len = 0;
	    lexbuf.ptr = tokstr =
		(char *)hcalloc(lexbuf.siz = LEX_HEAP_SIZE);
	    add(c);
	}
	hwend();
	while ((c = ingetc()) != '\n' && !lexstop) {
	    hwaddc(c);
	    addtoline(c);
	    if (lexflags & LEXFLAGS_COMMENTS_KEEP)
		add(c);
	}

	if (errflag)
	    peek = LEXERR;
	else {
	    if (lexflags & LEXFLAGS_COMMENTS_KEEP) {
		*lexbuf.ptr = '\0';
		if (!lexstop)
		    hungetc(c);
		peek = STRING;
	    } else {
		hwend();
		hwbegin(0);
		hwaddc('\n');
		addtoline('\n');
		/*
		 * If splitting a line and removing comments,
		 * we don't want a newline token since it's
		 * treated specially.
		 */
		if ((lexflags & LEXFLAGS_COMMENTS_STRIP) && lexstop)
		    peek = ENDINPUT;
		else
		    peek = NEWLIN;
	    }
	}
	return peek;
    }
    switch (lexact1[STOUC(c)]) {
    case LX1_BKSLASH:
	d = hgetc();
	if (d == '\n')
	    goto beginning;
	hungetc(d);
	lexstop = 0;
	break;
    case LX1_NEWLIN:
	return NEWLIN;
    case LX1_SEMI:
	d = hgetc();
	if(d == ';')
	    return DSEMI;
	else if(d == '&')
	    return SEMIAMP;
	else if (d == '|')
	    return SEMIBAR;
	hungetc(d);
	lexstop = 0;
	return SEMI;
    case LX1_AMPER:
	d = hgetc();
	if (d == '&')
	    return DAMPER;
	else if (d == '!' || d == '|')
	    return AMPERBANG;
	else if (d == '>') {
	    tokfd = peekfd;
	    d = hgetc();
	    if (d == '!' || d == '|')
		return OUTANGAMPBANG;
	    else if (d == '>') {
		d = hgetc();
		if (d == '!' || d == '|')
		    return DOUTANGAMPBANG;
		hungetc(d);
		lexstop = 0;
		return DOUTANGAMP;
	    }
	    hungetc(d);
	    lexstop = 0;
	    return AMPOUTANG;
	}
	hungetc(d);
	lexstop = 0;
	return AMPER;
    case LX1_BAR:
	d = hgetc();
	if (d == '|')
	    return DBAR;
	else if (d == '&')
	    return BARAMP;
	hungetc(d);
	lexstop = 0;
	return BAR;
    case LX1_INPAR:
	d = hgetc();
	if (d == '(') {
	    if (infor) {
		dbparens = 1;
		return DINPAR;
	    }
	    if (incmdpos || (isset(SHGLOB) && !isset(KSHGLOB))) {
		lexbuf.len = 0;
		lexbuf.ptr = tokstr = (char *)
		    hcalloc(lexbuf.siz = LEX_HEAP_SIZE);
		switch (cmd_or_math(CS_MATH)) {
		case CMD_OR_MATH_MATH:
		    return DINPAR;

		case CMD_OR_MATH_CMD:
		    /*
		     * Not math, so we don't return the contents
		     * as a string in this case.
		     */
		    tokstr = NULL;
		    return INPAR;
		    
		case CMD_OR_MATH_ERR:
		    /*
		     * LEXFLAGS_ACTIVE means we came from bufferwords(),
		     * so we treat as an incomplete math expression
		     */
		    if (lexflags & LEXFLAGS_ACTIVE)
			tokstr = dyncat("((", tokstr ? tokstr : "");
		    /* fall through */

		default:
		    return LEXERR;
		}
	    }
	} else if (d == ')')
	    return INOUTPAR;
	hungetc(d);
	lexstop = 0;
	if (!(isset(SHGLOB) || incond == 1 || incmdpos))
	    break;
	return INPAR;
    case LX1_OUTPAR:
	return OUTPAR;
    case LX1_INANG:
	d = hgetc();
	if (d == '(') {
	    hungetc(d);
	    lexstop = 0;
	    unpeekfd:
	    if(peekfd != -1) {
		hungetc(c);
		c = '0' + peekfd;
	    }
	    break;
	}
	if (d == '>') {
	    peek = INOUTANG;
	} else if (d == '<') {
	    int e = hgetc();

	    if (e == '(') {
		hungetc(e);
		hungetc(d);
		peek = INANG;
	    } else if (e == '<')
		peek = TRINANG;
	    else if (e == '-')
		peek = DINANGDASH;
	    else {
		hungetc(e);
		lexstop = 0;
		peek = DINANG;
	    }
	} else if (d == '&') {
	    peek = INANGAMP;
	} else {
	    hungetc(d);
	    if(isnumglob())
		goto unpeekfd;
	    peek = INANG;
	}
	tokfd = peekfd;
	return peek;
    case LX1_OUTANG:
	d = hgetc();
	if (d == '(') {
	    hungetc(d);
	    goto unpeekfd;
	} else if (d == '&') {
	    d = hgetc();
	    if (d == '!' || d == '|')
		peek = OUTANGAMPBANG;
	    else {
		hungetc(d);
		lexstop = 0;
		peek = OUTANGAMP;
	    }
	} else if (d == '!' || d == '|')
	    peek = OUTANGBANG;
	else if (d == '>') {
	    d = hgetc();
	    if (d == '&') {
		d = hgetc();
		if (d == '!' || d == '|')
		    peek = DOUTANGAMPBANG;
		else {
		    hungetc(d);
		    lexstop = 0;
		    peek = DOUTANGAMP;
		}
	    } else if (d == '!' || d == '|')
		peek = DOUTANGBANG;
	    else if (d == '(') {
		hungetc(d);
		hungetc('>');
		peek = OUTANG;
	    } else {
		hungetc(d);
		lexstop = 0;
		peek = DOUTANG;
		if (isset(HISTALLOWCLOBBER))
		    hwaddc('|');
	    }
	} else {
	    hungetc(d);
	    lexstop = 0;
	    peek = OUTANG;
	    if (!incond && isset(HISTALLOWCLOBBER))
		hwaddc('|');
	}
	tokfd = peekfd;
	return peek;
    }

    /* we've started a string, now get the *
     * rest of it, performing tokenization */
    return gettokstr(c, 0);
}

/*
 * Get the remains of a token string.  This has two uses.
 * When called from gettok(), with sub = 0, we have already identified
 * any interesting initial character and want to get the rest of
 * what we now know is a string.  However, the string may still include
 * metacharacters and potentially substitutions.
 *
 * When called from parse_subst_string() with sub = 1, we are not
 * fully parsing a command line, merely tokenizing a string.
 * In this case we always add characters to the parsed string
 * unless there is a parse error.
 */

/**/
static enum lextok
gettokstr(int c, int sub)
{
    int bct = 0, pct = 0, brct = 0, seen_brct = 0, fdpar = 0;
    int intpos = 1, in_brace_param = 0;
    int inquote, unmatched = 0;
    enum lextok peek;
#ifdef DEBUG
    int ocmdsp = cmdsp;
#endif

    peek = STRING;
    if (!sub) {
	lexbuf.len = 0;
	lexbuf.ptr = tokstr = (char *) hcalloc(lexbuf.siz = LEX_HEAP_SIZE);
    }
    for (;;) {
	int act;
	int e;
	int inbl = inblank(c);
	
	if (fdpar && !inbl && c != ')')
	    fdpar = 0;

	if (inbl && !in_brace_param && !pct)
	    act = LX2_BREAK;
	else {
	    act = lexact2[STOUC(c)];
	    c = lextok2[STOUC(c)];
	}
	switch (act) {
	case LX2_BREAK:
	    if (!in_brace_param && !sub)
		goto brk;
	    break;
	case LX2_META:
	    c = hgetc();
#ifdef DEBUG
	    if (lexstop) {
		fputs("BUG: input terminated by Meta\n", stderr);
		fflush(stderr);
		goto brk;
	    }
#endif
	    add(Meta);
	    break;
	case LX2_OUTPAR:
	    if (fdpar) {
		/* this is a single word `(   )', treat as INOUTPAR */
		add(c);
		*lexbuf.ptr = '\0';
		return INOUTPAR;
	    }
	    if ((sub || in_brace_param) && isset(SHGLOB))
		break;
	    if (!in_brace_param && !pct--) {
		if (sub) {
		    pct = 0;
		    break;
		} else
		    goto brk;
	    }
	    c = Outpar;
	    break;
	case LX2_BAR:
	    if (!pct && !in_brace_param) {
		if (sub)
		    break;
		else
		    goto brk;
	    }
	    if (unset(SHGLOB) || (!sub && !in_brace_param))
		c = Bar;
	    break;
	case LX2_STRING:
	    e = hgetc();
	    if (e == '[') {
		cmdpush(CS_MATHSUBST);
		add(String);
		add(Inbrack);
		c = dquote_parse(']', sub);
		cmdpop();
		if (c) {
		    peek = LEXERR;
		    goto brk;
		}
		c = Outbrack;
	    } else if (e == '(') {
		add(String);
		switch (cmd_or_math_sub()) {
		case CMD_OR_MATH_CMD:
		    c = Outpar;
		    break;

		case CMD_OR_MATH_MATH:
		    c = Outparmath;
		    break;

		default:
		    peek = LEXERR;
		    goto brk;
		}
	    } else {
		if (e == '{') {
		    add(c);
		    c = Inbrace;
		    ++bct;
		    cmdpush(CS_BRACEPAR);
		    if (!in_brace_param) {
			if ((in_brace_param = bct))
			    seen_brct = 0;
		    }
		} else {
		    hungetc(e);
		    lexstop = 0;
		}
	    }
	    break;
	case LX2_INBRACK:
	    if (!in_brace_param) {
		brct++;
		seen_brct = 1;
	    }
	    c = Inbrack;
	    break;
	case LX2_OUTBRACK:
	    if (!in_brace_param)
		brct--;
	    if (brct < 0)
		brct = 0;
	    c = Outbrack;
	    break;
	case LX2_INPAR:
	    if (isset(SHGLOB)) {
		if (sub || in_brace_param)
		    break;
		if (incasepat && !lexbuf.len)
		    return INPAR;
		if (!isset(KSHGLOB) && lexbuf.len)
		    goto brk;
	    }
	    if (!in_brace_param) {
		if (!sub) {
		    e = hgetc();
		    hungetc(e);
		    lexstop = 0;
		    /* For command words, parentheses are only
		     * special at the start.  But now we're tokenising
		     * the remaining string.  So I don't see what
		     * the old incmdpos test here is for.
		     *   pws 1999/6/8
		     *
		     * Oh, no.
		     *  func1(   )
		     * is a valid function definition in [k]sh.  The best
		     * thing we can do, without really nasty lookahead tricks,
		     * is break if we find a blank after a parenthesis.  At
		     * least this can't happen inside braces or brackets.  We
		     * only allow this with SHGLOB (set for both sh and ksh).
		     *
		     * Things like `print @( |foo)' should still
		     * work, because [k]sh don't allow multiple words
		     * in a function definition, so we only do this
		     * in command position.
		     *   pws 1999/6/14
		     */
		    if (e == ')' || (isset(SHGLOB) && inblank(e) && !bct &&
				     !brct && !intpos && incmdpos)) {
			/*
			 * Either a () token, or a command word with
			 * something suspiciously like a ksh function
			 * definition.
			 * The current word isn't spellcheckable.
			 */
			nocorrect |= 2;
			goto brk;
		    }
		}
		/*
		 * This also handles the [k]sh `foo( )' function definition.
		 * Maintain a variable fdpar, set as long as a single set of
		 * parentheses contains only space.  Then if we get to the
		 * closing parenthesis and it is still set, we can assume we
		 * have a function definition.  Only do this at the start of
		 * the word, since the (...) must be a separate token.
		 */
		if (!pct++ && isset(SHGLOB) && intpos && !bct && !brct)
		    fdpar = 1;
	    }
	    c = Inpar;
	    break;
	case LX2_INBRACE:
	    if (isset(IGNOREBRACES) || sub)
		c = '{';
	    else {
		if (!lexbuf.len && incmdpos) {
		    add('{');
		    *lexbuf.ptr = '\0';
		    return STRING;
		}
		if (in_brace_param) {
		    cmdpush(CS_BRACE);
		}
		bct++;
	    }
	    break;
	case LX2_OUTBRACE:
	    if ((isset(IGNOREBRACES) || sub) && !in_brace_param)
		break;
	    if (!bct)
		break;
	    if (in_brace_param) {
		cmdpop();
	    }
	    if (bct-- == in_brace_param)
		in_brace_param = 0;
	    c = Outbrace;
	    break;
	case LX2_COMMA:
	    if (unset(IGNOREBRACES) && !sub && bct > in_brace_param)
		c = Comma;
	    break;
	case LX2_OUTANG:
	    if (in_brace_param || sub)
		break;
	    e = hgetc();
	    if (e != '(') {
		hungetc(e);
		lexstop = 0;
		goto brk;
	    }
	    add(OutangProc);
	    if (skipcomm()) {
		peek = LEXERR;
		goto brk;
	    }
	    c = Outpar;
	    break;
	case LX2_INANG:
	    if (isset(SHGLOB) && sub)
		break;
	    e = hgetc();
	    if (!(in_brace_param || sub) && e == '(') {
		add(Inang);
		if (skipcomm()) {
		    peek = LEXERR;
		    goto brk;
		}
		c = Outpar;
		break;
	    }
	    hungetc(e);
	    if(isnumglob()) {
		add(Inang);
		while ((c = hgetc()) != '>')
		    add(c);
		c = Outang;
		break;
	    }
	    lexstop = 0;
	    if (in_brace_param || sub)
		break;
	    goto brk;
	case LX2_EQUALS:
	    if (!sub) {
		if (intpos) {
		    e = hgetc();
		    if (e != '(') {
			hungetc(e);
			lexstop = 0;
			c = Equals;
		    } else {
			add(Equals);
			if (skipcomm()) {
			    peek = LEXERR;
			    goto brk;
			}
			c = Outpar;
		    }
		} else if (peek != ENVSTRING &&
			   (incmdpos || intypeset) && !bct && !brct) {
		    char *t = tokstr;
		    if (idigit(*t))
			while (++t < lexbuf.ptr && idigit(*t));
		    else {
			int sav = *lexbuf.ptr;
			*lexbuf.ptr = '\0';
			t = itype_end(t, IIDENT, 0);
			if (t < lexbuf.ptr) {
			    skipparens(Inbrack, Outbrack, &t);
			} else {
			    *lexbuf.ptr = sav;
			}
		    }
		    if (*t == '+')
			t++;
		    if (t == lexbuf.ptr) {
			e = hgetc();
			if (e == '(') {
			    *lexbuf.ptr = '\0';
			    return ENVARRAY;
			}
			hungetc(e);
			lexstop = 0;
			peek = ENVSTRING;
			intpos = 2;
		    } else
			c = Equals;
		} else
		    c = Equals;
	    }
	    break;
	case LX2_BKSLASH:
	    c = hgetc();
	    if (c == '\n') {
		c = hgetc();
		if (!lexstop)
		    continue;
	    } else {
		add(Bnull);
		if (c == STOUC(Meta)) {
		    c = hgetc();
#ifdef DEBUG
		    if (lexstop) {
			fputs("BUG: input terminated by Meta\n", stderr);
			fflush(stderr);
			goto brk;
		    }
#endif
		    add(Meta);
		}
	    }
	    if (lexstop)
		goto brk;
	    break;
	case LX2_QUOTE: {
	    int strquote = (lexbuf.len && lexbuf.ptr[-1] == String);

	    add(Snull);
	    cmdpush(CS_QUOTE);
	    for (;;) {
		STOPHIST
		while ((c = hgetc()) != '\'' && !lexstop) {
		    if (strquote && c == '\\') {
			c = hgetc();
			if (lexstop)
			    break;
			/*
			 * Mostly we don't need to do anything special
			 * with escape backslashes or closing quotes
			 * inside $'...'; however in completion we
			 * need to be able to strip multiple backslashes
			 * neatly.
			 */
			if (c == '\\' || c == '\'')
			    add(Bnull);
			else
			    add('\\');
		    } else if (!sub && isset(CSHJUNKIEQUOTES) && c == '\n') {
			if (lexbuf.ptr[-1] == '\\')
			    lexbuf.ptr--, lexbuf.len--;
			else
			    break;
		    }
		    add(c);
		}
		ALLOWHIST
		if (c != '\'') {
		    unmatched = '\'';
		    peek = LEXERR;
		    cmdpop();
		    goto brk;
		}
		e = hgetc();
		if (e != '\'' || unset(RCQUOTES) || strquote)
		    break;
		add(c);
	    }
	    cmdpop();
	    hungetc(e);
	    lexstop = 0;
	    c = Snull;
	    break;
	}
	case LX2_DQUOTE:
	    add(Dnull);
	    cmdpush(CS_DQUOTE);
	    c = dquote_parse('"', sub);
	    cmdpop();
	    if (c) {
		unmatched = '"';
		peek = LEXERR;
		goto brk;
	    }
	    c = Dnull;
	    break;
	case LX2_BQUOTE:
	    add(Tick);
	    cmdpush(CS_BQUOTE);
	    SETPARBEGIN
	    inquote = 0;
	    while ((c = hgetc()) != '`' && !lexstop) {
		if (c == '\\') {
		    c = hgetc();
		    if (c != '\n') {
			add(c == '`' || c == '\\' || c == '$' ? Bnull : '\\');
			add(c);
		    }
		    else if (!sub && isset(CSHJUNKIEQUOTES))
			add(c);
		} else {
		    if (!sub && isset(CSHJUNKIEQUOTES) && c == '\n') {
			break;
		    }
		    add(c);
		    if (c == '\'') {
			if ((inquote = !inquote))
			    STOPHIST
			else
			    ALLOWHIST
		    }
		}
	    }
	    if (inquote)
		ALLOWHIST
	    cmdpop();
	    if (c != '`') {
		unmatched = '`';
		peek = LEXERR;
		goto brk;
	    }
	    c = Tick;
	    SETPAREND
	    break;
	case LX2_DASH:
	    /*
	     * - shouldn't be treated as a special character unless
	     * we're in a pattern.  Howeve,simply  counting "[" doesn't
	     * work as []a-z] is a valid expression and we don't know
	     * down here what this "[" is for as $foo[stuff] is valid
	     * in zsh.  So just detect an opening [, which is enough
	     * to turn this into a pattern; the Dash will be harmlessly
	     * untokenised if not wanted.
	     */
	    if (seen_brct)
		c = Dash;
           else
               c = '-';
           break;
       case LX2_BANG:
           /*
            * Same logic as Dash, for ! to perform negation in range.
            */
           if (seen_brct)
               c = Bang;
           else
               c = '!';
       }
       add(c);
       c = hgetc();
	if (intpos)
	    intpos--;
	if (lexstop)
	    break;
    }
  brk:
    if (errflag) {
	if (in_brace_param) {
	    while(bct-- >= in_brace_param)
		cmdpop();
	}
	return LEXERR;
    }
    hungetc(c);
    if (unmatched)
	zerr("unmatched %c", unmatched);
    if (in_brace_param) {
	while(bct-- >= in_brace_param)
	    cmdpop();
	zerr("closing brace expected");
    } else if (unset(IGNOREBRACES) && !sub && lexbuf.len > 1 &&
	       peek == STRING && lexbuf.ptr[-1] == '}' &&
	       lexbuf.ptr[-2] != Bnull) {
	/* hack to get {foo} command syntax work */
	lexbuf.ptr--;
	lexbuf.len--;
	lexstop = 0;
	hungetc('}');
    }
    *lexbuf.ptr = '\0';
    DPUTS(cmdsp != ocmdsp, "BUG: gettok: cmdstack changed.");
    return peek;
}


/*
 * Parse input as if in double quotes.
 * endchar is the end character to expect.
 * sub has got something to do with whether we are doing quoted substitution.
 * Return non-zero for error (character to unget), else zero
 */

/**/
static int
dquote_parse(char endchar, int sub)
{
    int pct = 0, brct = 0, bct = 0, intick = 0, err = 0;
    int c;
    int math = endchar == ')' || endchar == ']' || infor;
    int zlemath = math && zlemetacs > zlemetall + addedx - inbufct;

    while (((c = hgetc()) != endchar || bct ||
	    (math && ((pct > 0) || (brct > 0))) ||
	    intick) && !lexstop) {
      cont:
	switch (c) {
	case '\\':
	    c = hgetc();
	    if (c != '\n') {
		if (c == '$' || c == '\\' || (c == '}' && !intick && bct) ||
		    c == endchar || c == '`' ||
		    (endchar == ']' && (c == '[' || c == ']' ||
					c == '(' || c == ')' ||
					c == '{' || c == '}' ||
					(c == '"' && sub))))
		    add(Bnull);
		else {
		    /* lexstop is implicitly handled here */
		    add('\\');
		    goto cont;
		}
	    } else if (sub || unset(CSHJUNKIEQUOTES) || endchar != '"')
		continue;
	    break;
	case '\n':
	    err = !sub && isset(CSHJUNKIEQUOTES) && endchar == '"';
	    break;
	case '$':
	    if (intick)
		break;
	    c = hgetc();
	    if (c == '(') {
		add(Qstring);
		switch (cmd_or_math_sub()) {
		case CMD_OR_MATH_CMD:
		    c = Outpar;
		    break;

		case CMD_OR_MATH_MATH:
		    c = Outparmath;
		    break;

		default:
		    err = 1;
		    break;
		}
	    } else if (c == '[') {
		add(String);
		add(Inbrack);
		cmdpush(CS_MATHSUBST);
		err = dquote_parse(']', sub);
		cmdpop();
		c = Outbrack;
	    } else if (c == '{') {
		add(Qstring);
		c = Inbrace;
		cmdpush(CS_BRACEPAR);
		bct++;
	    } else if (c == '$')
		add(Qstring);
	    else {
		hungetc(c);
		lexstop = 0;
		c = Qstring;
	    }
	    break;
	case '}':
	    if (intick || !bct)
		break;
	    c = Outbrace;
	    bct--;
	    cmdpop();
	    break;
	case '`':
	    c = Qtick;
	    if (intick == 2)
		ALLOWHIST
	    if ((intick = !intick)) {
		SETPARBEGIN
		cmdpush(CS_BQUOTE);
	    } else {
		SETPAREND
	        cmdpop();
	    }
	    break;
	case '\'':
	    if (!intick)
		break;
	    if (intick == 1)
		intick = 2, STOPHIST
	    else
		intick = 1, ALLOWHIST
	    break;
	case '(':
	    if (!math || !bct)
		pct++;
	    break;
	case ')':
	    if (!math || !bct)
		err = (!pct-- && math);
	    break;
	case '[':
	    if (!math || !bct)
		brct++;
	    break;
	case ']':
	    if (!math || !bct)
		err = (!brct-- && math);
	    break;
	case '"':
	    if (intick || (endchar != '"' && !bct))
		break;
	    if (bct) {
		add(Dnull);
		cmdpush(CS_DQUOTE);
		err = dquote_parse('"', sub);
		cmdpop();
		c = Dnull;
	    } else
		err = 1;
	    break;
	}
	if (err || lexstop)
	    break;
	add(c);
    }
    if (intick == 2)
	ALLOWHIST
    if (intick) {
	cmdpop();
    }
    while (bct--)
	cmdpop();
    if (lexstop)
	err = intick || endchar || err;
    else if (err == 1) {
	/*
	 * TODO: as far as I can see, this hack is used in gettokstr()
	 * to hungetc() a character on an error.  However, I don't
	 * understand what that actually gets us, and we can't guarantee
	 * it's a character anyway, because of the previous test.
	 *
	 * We use the same feature in cmd_or_math where we actually do
	 * need to unget if we decide it's really a command substitution.
	 * We try to handle the other case by testing for lexstop.
	 */
	err = c;
    }
    if (zlemath && zlemetacs <= zlemetall + 1 - inbufct)
	inwhat = IN_MATH;
    return err;
}

/*
 * Tokenize a string given in s. Parsing is done as in double
 * quotes.  This is usually called before singsub().
 *
 * parsestr() is noisier, reporting an error if the parse failed.
 *
 * On entry, *s must point to a string allocated from the stack of
 * exactly the right length, i.e. strlen(*s) + 1, as the string
 * is used as the lexical token string whose memory management
 * demands this.  Usually the input string will therefore be
 * the result of an immediately preceding dupstring().
 */

/**/
mod_export int
parsestr(char **s)
{
    int err;

    if ((err = parsestrnoerr(s))) {
	untokenize(*s);
	if (!(errflag & ERRFLAG_INT)) {
	    if (err > 32 && err < 127)
		zerr("parse error near `%c'", err);
	    else
		zerr("parse error");
	}
    }
    return err;
}

/**/
mod_export int
parsestrnoerr(char **s)
{
    int l = strlen(*s), err;

    zcontext_save();
    untokenize(*s);
    inpush(dupstring(*s), 0, NULL);
    strinbeg(0);
    lexbuf.len = 0;
    lexbuf.ptr = tokstr = *s;
    lexbuf.siz = l + 1;
    err = dquote_parse('\0', 1);
    if (tokstr)
	*s = tokstr;
    *lexbuf.ptr = '\0';
    strinend();
    inpop();
    DPUTS(cmdsp, "BUG: parsestr: cmdstack not empty.");
    zcontext_restore();
    return err;
}

/*
 * Parse a subscript in string s.
 * sub is passed down to dquote_parse().
 * endchar is the final character.
 * Return the next character, or NULL.
 */
/**/
mod_export char *
parse_subscript(char *s, int sub, int endchar)
{
    int l = strlen(s), err, toklen;
    char *t;

    if (!*s || *s == endchar)
	return 0;
    zcontext_save();
    untokenize(t = dupstring(s));
    inpush(t, 0, NULL);
    strinbeg(0);
    /*
     * Warning to Future Generations:
     *
     * This way of passing the subscript through the lexer is brittle.
     * Code above this for several layers assumes that when we tokenise
     * the input it goes into the same place as the original string.
     * However, the lexer may overwrite later bits of the string or
     * reallocate it, in particular when expanding aliaes.  To get
     * around this, we copy the string and then copy it back.  This is a
     * bit more robust but still relies on the underlying assumption of
     * length preservation.
     */
    lexbuf.len = 0;
    lexbuf.ptr = tokstr = dupstring(s);
    lexbuf.siz = l + 1;
    err = dquote_parse(endchar, sub);
    toklen = (int)(lexbuf.ptr - tokstr);
    DPUTS(toklen > l, "Bad length for parsed subscript");
    memcpy(s, tokstr, toklen);
    if (err) {
	char *strend = s + toklen;
	err = *strend;
	*strend = '\0';
	untokenize(s);
	*strend = err;
	s = NULL;
    } else {
	s += toklen;
    }
    strinend();
    inpop();
    DPUTS(cmdsp, "BUG: parse_subscript: cmdstack not empty.");
    zcontext_restore();
    return s;
}

/* Tokenize a string given in s. Parsing is done as if s were a normal *
 * command-line argument but it may contain separators.  This is used  *
 * to parse the right-hand side of ${...%...} substitutions.           */

/**/
mod_export int
parse_subst_string(char *s)
{
    int c, l = strlen(s), err;
    char *ptr;
    enum lextok ctok;

    if (!*s || !strcmp(s, nulstring))
	return 0;
    zcontext_save();
    untokenize(s);
    inpush(dupstring(s), 0, NULL);
    strinbeg(0);
    lexbuf.len = 0;
    lexbuf.ptr = tokstr = s;
    lexbuf.siz = l + 1;
    c = hgetc();
    ctok = gettokstr(c, 1);
    err = errflag;
    strinend();
    inpop();
    DPUTS(cmdsp, "BUG: parse_subst_string: cmdstack not empty.");
    zcontext_restore();
    /* Keep any interrupt error status */
    errflag = err | (errflag & ERRFLAG_INT);
    if (ctok == LEXERR) {
	untokenize(s);
	return 1;
    }
#ifdef DEBUG
    /*
     * Historical note: we used to check here for olen (the value of lexbuf.len
     * before zcontext_restore()) == l, but that's not necessarily the case if
     * we stripped an RCQUOTE.
     */
    if (ctok != STRING || (errflag && !noerrs)) {
	fprintf(stderr, "Oops. Bug in parse_subst_string: %s\n",
		errflag ? "errflag" : "ctok != STRING");
	fflush(stderr);
	untokenize(s);
	return 1;
    }
#endif
    /* Check for $'...' quoting.  This needs special handling. */
    for (ptr = s; *ptr; )
    {
	if (*ptr == String && ptr[1] == Snull)
	{
	    char *t;
	    int len, tlen, diff;
	    t = getkeystring(ptr + 2, &len, GETKEYS_DOLLARS_QUOTE, NULL);
	    len += 2;
	    tlen = strlen(t);
	    diff = len - tlen;
	    /*
	     * Yuk.
	     * parse_subst_string() currently handles strings in-place.
	     * That's not so easy to fix without knowing whether
	     * additional memory should come off the heap or
	     * otherwise.  So we cheat by copying the unquoted string
	     * into place, unless it's too long.  That's not the
	     * normal case, but I'm worried there are pathological
	     * cases with converting metafied multibyte strings.
	     * If someone can prove there aren't I will be very happy.
	     */
	    if (diff < 0) {
		DPUTS(1, "$'...' subst too long: fix get_parse_string()");
		return 1;
	    }
	    memcpy(ptr, t, tlen);
	    ptr += tlen;
	    if (diff > 0) {
		char *dptr = ptr;
		char *sptr = ptr + diff;
		while ((*dptr++ = *sptr++))
		    ;
	    }
	} else
	    ptr++;
    }
    return 0;
}

/* Called below to report word positions. */

/**/
static void
gotword(void)
{
    int nwe = zlemetall + 1 - inbufct + (addedx == 2 ? 1 : 0);
    if (zlemetacs <= nwe) {
	int nwb = zlemetall - wordbeg + addedx;
	if (zlemetacs >= nwb) {
	    wb = nwb;
	    we = nwe;
	} else {
	    wb = zlemetacs + addedx;
	    if (we < wb)
		we = wb;
	}
	lexflags = 0;
    }
}

/* Check if current lex text matches an alias: 1 if so, else 0 */

static int
checkalias(void)
{
    Alias an;

    if (!zshlextext)
	return 0;

    if (!noaliases && isset(ALIASESOPT) &&
	(!isset(POSIXALIASES) ||
	 (tok == STRING && !reswdtab->getnode(reswdtab, zshlextext)))) {
	char *suf;

	an = (Alias) aliastab->getnode(aliastab, zshlextext);
	if (an && !an->inuse &&
	    ((an->node.flags & ALIAS_GLOBAL) ||
	     (incmdpos && tok == STRING) || inalmore)) {
	    if (!lexstop) {
		/*
		 * Tokens that don't require a space after, get one,
		 * because they are treated as if preceded by one.
		 */
		int c = hgetc();
		hungetc(c);
		if (!iblank(c))
		    inpush(" ", INP_ALIAS, 0);
	    }
	    inpush(an->text, INP_ALIAS, an);
	    if (an->text[0] == ' ' && !(an->node.flags & ALIAS_GLOBAL))
		aliasspaceflag = 1;
	    lexstop = 0;
	    return 1;
	}
	if ((suf = strrchr(zshlextext, '.')) && suf[1] &&
	    suf > zshlextext && suf[-1] != Meta &&
	    (an = (Alias)sufaliastab->getnode(sufaliastab, suf+1)) &&
	    !an->inuse && incmdpos) {
	    inpush(dupstring(zshlextext), INP_ALIAS, an);
	    inpush(" ", INP_ALIAS, NULL);
	    inpush(an->text, INP_ALIAS, NULL);
	    lexstop = 0;
	    return 1;
	}
    }

    return 0;
}

/* expand aliases and reserved words */

/**/
int
exalias(void)
{
    Reswd rw;

    hwend();
    if (interact && isset(SHINSTDIN) && !strin && !incasepat &&
	tok == STRING && !nocorrect && !(inbufflags & INP_ALIAS) &&
	(isset(CORRECTALL) || (isset(CORRECT) && incmdpos)))
	spckword(&tokstr, 1, incmdpos, 1);

    if (!tokstr) {
	zshlextext = tokstrings[tok];

	if (tok == NEWLIN)
	    return 0;
	return checkalias();
    } else {
	VARARR(char, copy, (strlen(tokstr) + 1));

	if (has_token(tokstr)) {
	    char *p, *t;

	    zshlextext = p = copy;
	    for (t = tokstr;
		 (*p++ = itok(*t) ? ztokens[*t++ - Pound] : *t++););
	} else
	    zshlextext = tokstr;

	if ((lexflags & LEXFLAGS_ZLE) && !(inbufflags & INP_ALIAS)) {
	    int zp = lexflags;

	    gotword();
	    if ((zp & LEXFLAGS_ZLE) && !lexflags) {
		if (zshlextext == copy)
		    zshlextext = tokstr;
		return 0;
	    }
	}

	if (tok == STRING) {
	    /* Check for an alias */
	    if ((zshlextext != copy || !isset(POSIXALIASES)) && checkalias()) {
		if (zshlextext == copy)
		    zshlextext = tokstr;
		return 1;
	    }

	    /* Then check for a reserved word */
	    if ((incmdpos ||
		 (unset(IGNOREBRACES) && unset(IGNORECLOSEBRACES) &&
		  zshlextext[0] == '}' && !zshlextext[1])) &&
		(rw = (Reswd) reswdtab->getnode(reswdtab, zshlextext))) {
		tok = rw->token;
		inrepeat_ = (tok == REPEAT);
		if (tok == DINBRACK)
		    incond = 1;
	    } else if (incond && !strcmp(zshlextext, "]]")) {
		tok = DOUTBRACK;
		incond = 0;
	    } else if (incond == 1 && zshlextext[0] == '!' && !zshlextext[1])
		tok = BANG;
	}
	inalmore = 0;
	if (zshlextext == copy)
	    zshlextext = tokstr;
    }
    return 0;
}

/**/
void
zshlex_raw_add(int c)
{
    if (!lex_add_raw)
	return;

    *lexbuf_raw.ptr++ = c;
    if (lexbuf_raw.siz == ++lexbuf_raw.len) {
	int newbsiz = lexbuf_raw.siz * 2;

	tokstr_raw = (char *)hrealloc(tokstr_raw, lexbuf_raw.siz, newbsiz);
	lexbuf_raw.ptr = tokstr_raw + lexbuf_raw.len;
	memset(lexbuf_raw.ptr, 0, newbsiz - lexbuf_raw.siz);
	lexbuf_raw.siz = newbsiz;
    }
}

/**/
void
zshlex_raw_back(void)
{
    if (!lex_add_raw)
	return;
    lexbuf_raw.ptr--;
    lexbuf_raw.len--;
}

/**/
int
zshlex_raw_mark(int offset)
{
    if (!lex_add_raw)
	return 0;
    return lexbuf_raw.len + offset;
}

/**/
void
zshlex_raw_back_to_mark(int mark)
{
    if (!lex_add_raw)
	return;
    lexbuf_raw.ptr = tokstr_raw + mark;
    lexbuf_raw.len = mark;
}

/*
 * Skip (...) for command-style substitutions: $(...), <(...), >(...)
 *
 * In order to ensure we don't stop at closing parentheses with
 * some other syntactic significance, we'll parse the input until
 * we find an unmatched closing parenthesis.  However, we'll throw
 * away the result of the parsing and just keep the string we've built
 * up on the way.
 */

/**/
static int
skipcomm(void)
{
#ifdef ZSH_OLD_SKIPCOMM
    int pct = 1, c, start = 1;

    cmdpush(CS_CMDSUBST);
    SETPARBEGIN
    c = Inpar;
    do {
	int iswhite;
	add(c);
	c = hgetc();
	if (itok(c) || lexstop)
	    break;
	iswhite = inblank(c);
	switch (c) {
	case '(':
	    pct++;
	    break;
	case ')':
	    pct--;
	    break;
	case '\\':
	    add(c);
	    c = hgetc();
	    break;
	case '\'': {
	    int strquote = lexbuf.ptr[-1] == '$';
	    add(c);
	    STOPHIST
	    while ((c = hgetc()) != '\'' && !lexstop) {
		if (c == '\\' && strquote) {
		    add(c);
		    c = hgetc();
		}
		add(c);
	    }
	    ALLOWHIST
	    break;
	}
	case '\"':
	    add(c);
	    while ((c = hgetc()) != '\"' && !lexstop)
		if (c == '\\') {
		    add(c);
		    add(hgetc());
		} else
		    add(c);
	    break;
	case '`':
	    add(c);
	    while ((c = hgetc()) != '`' && !lexstop)
		if (c == '\\')
		    add(c), add(hgetc());
		else
		    add(c);
	    break;
	case '#':
	    if (start) {
		add(c);
		while ((c = hgetc()) != '\n' && !lexstop)
		    add(c);
		iswhite = 1;
	    }
	    break;
	}
	start = iswhite;
    }
    while (pct);
    if (!lexstop)
	SETPAREND
    cmdpop();
    return lexstop;
#else
    char *new_tokstr;
    int new_lexstop, new_lex_add_raw;
    int save_infor = infor;
    struct lexbufstate new_lexbuf;
    int noalias = noaliases;

    noaliases = 1;
    infor = 0;
    cmdpush(CS_CMDSUBST);
    SETPARBEGIN
    add(Inpar);

    new_lex_add_raw = lex_add_raw + 1;
    if (!lex_add_raw) {
	/*
	 * We'll combine the string so far with the input
	 * read in for the command substitution.  To do this
	 * we'll just propagate the current tokstr etc. as the
	 * variables used for adding raw input, and
	 * ensure we swap those for the real tokstr etc. at the end.
	 *
	 * However, we need to save and restore the rest of the
	 * lexical and parse state as we're effectively parsing
	 * an internal string.  Because we're still parsing it from
	 * the original input source (we have to --- we don't know
	 * when to stop inputting it otherwise and can't rely on
	 * the input being recoverable until we've read it) we need
	 * to keep the same history context.
	 */
	new_tokstr = tokstr;
	new_lexbuf = lexbuf;

	/*
	 * If we're expanding an alias at this point, we need the whole
	 * remaining text as part of the string for the command in
	 * parentheses, so don't backtrack.  This is different from the
	 * usual case where the alias is fully within the command, where
	 * we want the unexpanded text so that it will be expanded
	 * again when the command in the parentheses is executed.
	 *
	 * I never wanted to be a software engineer, you know.
	 */
	if (inbufflags & INP_ALIAS)
	    inbufflags |= INP_RAW_KEEP;
	zcontext_save_partial(ZCONTEXT_LEX|ZCONTEXT_PARSE);
	hist_in_word(1);
    } else {
	/*
	 * Set up for nested command subsitution, however
	 * we don't actually need the string until we get
	 * back to the top level and recover the lot.
	 * The $() body just appears empty.
	 *
	 * We do need to propagate the raw variables which would
	 * otherwise by cleared, though.
	 */
	new_tokstr = tokstr_raw;
	new_lexbuf = lexbuf_raw;

	zcontext_save_partial(ZCONTEXT_LEX|ZCONTEXT_PARSE);
    }
    tokstr_raw = new_tokstr;
    lexbuf_raw = new_lexbuf;
    lex_add_raw = new_lex_add_raw;
    /*
     * Don't do any ZLE specials down here: they're only needed
     * when we return the string from the recursive parse.
     * (TBD: this probably means we should be initialising lexflags
     * more consistently.)
     *
     * Note that in that case we're still using the ZLE line reading
     * function at the history layer --- this is consistent with the
     * intention of maintaining the history and input layers across
     * the recursive parsing.
     */
    lexflags &= ~LEXFLAGS_ZLE;
    dbparens = 0;	/* restored by zcontext_restore_partial() */

    if (!parse_event(OUTPAR) || tok != OUTPAR)
	lexstop = 1;
     /* Outpar lexical token gets added in caller if present */

    /*
     * We're going to keep the full raw input string
     * as the current token string after popping the stack.
     */
    new_tokstr = tokstr_raw;
    new_lexbuf = lexbuf_raw;
    /*
     * We're also going to propagate the lexical state:
     * if we couldn't parse the command substitution we
     * can't continue.
     */
    new_lexstop = lexstop;

    zcontext_restore_partial(ZCONTEXT_LEX|ZCONTEXT_PARSE);

    if (lex_add_raw) {
	/*
	 * Keep going, so retain the raw variables.
	 */
	tokstr_raw = new_tokstr;
	lexbuf_raw = new_lexbuf;
    } else {
	if (!new_lexstop) {
	    /* Ignore the ')' added on input */
	    new_lexbuf.len--;
	    *--new_lexbuf.ptr = '\0';
	}

	/*
	 * Convince the rest of lex.c we were examining a string
	 * all along.
	 */
	tokstr = new_tokstr;
	lexbuf = new_lexbuf;
	lexstop = new_lexstop;
	hist_in_word(0);
    }

    if (!lexstop)
	SETPAREND
    cmdpop();
    infor = save_infor;
    noaliases = noalias;

    return lexstop;
#endif
}