summaryrefslogtreecommitdiffstats
path: root/src/interfaces/ecpg/preproc/pgc.l
blob: c06b2d6f51ef13305f94d8afb40648c12b377398 (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
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
%top{
/*-------------------------------------------------------------------------
 *
 * pgc.l
 *	  lexical scanner for ecpg
 *
 * This is a modified version of src/backend/parser/scan.l
 *
 * The ecpg scanner is not backup-free, so the fail rules are
 * only here to simplify syncing this file with scan.l.
 *
 *
 * Portions Copyright (c) 1996-2022, PostgreSQL Global Development Group
 * Portions Copyright (c) 1994, Regents of the University of California
 *
 * IDENTIFICATION
 *	  src/interfaces/ecpg/preproc/pgc.l
 *
 *-------------------------------------------------------------------------
 */
#include "postgres_fe.h"

#include <ctype.h>
#include <limits.h>

#include "common/string.h"

#include "preproc_extern.h"
#include "preproc.h"
}

%{

/* LCOV_EXCL_START */

extern YYSTYPE base_yylval;

static int		xcdepth = 0;	/* depth of nesting in slash-star comments */
static char	   *dolqstart = NULL;	/* current $foo$ quote start string */

/*
 * literalbuf is used to accumulate literal values when multiple rules
 * are needed to parse a single literal.  Call startlit to reset buffer
 * to empty, addlit to add text.  Note that the buffer is permanently
 * malloc'd to the largest size needed so far in the current run.
 */
static char	   *literalbuf = NULL;		/* expandable buffer */
static int		literallen;				/* actual current length */
static int		literalalloc;			/* current allocated buffer size */

/* Used for detecting global state together with braces_open */
static int		parenths_open;

/* Used to tell parse_include() whether the command was #include or #include_next */
static bool		include_next;

#define startlit()	(literalbuf[0] = '\0', literallen = 0)
static void addlit(char *ytext, int yleng);
static void addlitchar(unsigned char);
static int	process_integer_literal(const char *token, YYSTYPE *lval);
static void parse_include(void);
static bool ecpg_isspace(char ch);
static bool isdefine(void);
static bool isinformixdefine(void);

char *token_start;

/* vars to keep track of start conditions when scanning literals */
static int state_before_str_start;
static int state_before_str_stop;

/*
 * State for handling include files and macro expansion.  We use a new
 * flex input buffer for each level of include or macro, and create a
 * struct _yy_buffer to remember the previous level.  There is not a struct
 * for the currently active input source; that state is kept in the global
 * variables YY_CURRENT_BUFFER, yylineno, and input_filename.
 */
static struct _yy_buffer
{
	YY_BUFFER_STATE		buffer;
	long				lineno;
	char			   *filename;
	struct _yy_buffer  *next;
} *yy_buffer = NULL;

/*
 * Vars for handling ifdef/elif/endif constructs.  preproc_tos is the current
 * nesting depth of such constructs, and stacked_if_value[preproc_tos] is the
 * state for the innermost level.  (For convenience, stacked_if_value[0] is
 * initialized as though we are in the active branch of some outermost IF.)
 * The active field is true if the current branch is active (being expanded).
 * The saw_active field is true if we have found any successful branch,
 * so that all subsequent branches of this level should be skipped.
 * The else_branch field is true if we've found an 'else' (so that another
 * 'else' or 'elif' at this level is an error.)
 * For IFs nested within an inactive branch, all branches always have active
 * set to false, but saw_active and else_branch are maintained normally.
 * ifcond is valid only while evaluating an if-condition; it's true if we
 * are doing ifdef, false if ifndef.
 */
#define MAX_NESTED_IF 128
static short preproc_tos;
static bool ifcond;
static struct _if_value
{
	bool		active;
	bool		saw_active;
	bool		else_branch;
} stacked_if_value[MAX_NESTED_IF];

%}

%option 8bit
%option never-interactive
%option nodefault
%option noinput
%option noyywrap
%option warn
%option yylineno
%option prefix="base_yy"

/*
 * OK, here is a short description of lex/flex rules behavior.
 * The longest pattern which matches an input string is always chosen.
 * For equal-length patterns, the first occurring in the rules list is chosen.
 * INITIAL is the starting state, to which all non-conditional rules apply.
 * Exclusive states change parsing rules while the state is active.  When in
 * an exclusive state, only those rules defined for that state apply.
 *
 * We use exclusive states for quoted strings, extended comments,
 * and to eliminate parsing troubles for numeric strings.
 * Exclusive states:
 *  <xb> bit string literal
 *  <xc> extended C-style comments
 *  <xd> delimited identifiers (double-quoted identifiers)
 *  <xdc> double-quoted strings in C
 *  <xh> hexadecimal byte string
 *  <xn> national character quoted strings
 *  <xq> standard quoted strings
 *  <xqs> quote stop (detect continued strings)
 *  <xe> extended quoted strings (support backslash escape sequences)
 *  <xqc> single-quoted strings in C
 *  <xdolq> $foo$ quoted strings
 *  <xui> quoted identifier with Unicode escapes
 *  <xus> quoted string with Unicode escapes
 *  <xcond> condition of an EXEC SQL IFDEF construct
 *  <xskip> skipping the inactive part of an EXEC SQL IFDEF construct
 *
 * Note: we intentionally don't mimic the backend's <xeu> state; we have
 * no need to distinguish it from <xe> state.
 *
 * Remember to add an <<EOF>> case whenever you add a new exclusive state!
 * The default one is probably not the right thing.
 */

%x xb
%x xc
%x xd
%x xdc
%x xh
%x xn
%x xq
%x xqs
%x xe
%x xqc
%x xdolq
%x xui
%x xus
%x xcond
%x xskip

/* Additional exclusive states that are specific to ECPG */
%x C SQL incl def def_ident undef

/*
 * In order to make the world safe for Windows and Mac clients as well as
 * Unix ones, we accept either \n or \r as a newline.  A DOS-style \r\n
 * sequence will be seen as two successive newlines, but that doesn't cause
 * any problems.  SQL-style comments, which start with -- and extend to the
 * next newline, are treated as equivalent to a single whitespace character.
 *
 * NOTE a fine point: if there is no newline following --, we will absorb
 * everything to the end of the input as a comment.  This is correct.  Older
 * versions of Postgres failed to recognize -- as a comment if the input
 * did not end with a newline.
 *
 * XXX perhaps \f (formfeed) should be treated as a newline as well?
 *
 * XXX if you change the set of whitespace characters, fix ecpg_isspace()
 * to agree.
 */

space			[ \t\n\r\f]
horiz_space		[ \t\f]
newline			[\n\r]
non_newline		[^\n\r]

comment			("--"{non_newline}*)

whitespace		({space}+|{comment})

/*
 * SQL requires at least one newline in the whitespace separating
 * string literals that are to be concatenated.  Silly, but who are we
 * to argue?  Note that {whitespace_with_newline} should not have * after
 * it, whereas {whitespace} should generally have a * after it...
 */

horiz_whitespace		({horiz_space}|{comment})
whitespace_with_newline	({horiz_whitespace}*{newline}{whitespace}*)

quote			'
/* If we see {quote} then {quotecontinue}, the quoted string continues */
quotecontinue	{whitespace_with_newline}{quote}

/*
 * {quotecontinuefail} is needed to avoid lexer backup when we fail to match
 * {quotecontinue}.  It might seem that this could just be {whitespace}*,
 * but if there's a dash after {whitespace_with_newline}, it must be consumed
 * to see if there's another dash --- which would start a {comment} and thus
 * allow continuation of the {quotecontinue} token.
 */
quotecontinuefail	{whitespace}*"-"?

/* Bit string
 */
xbstart			[bB]{quote}
xbinside		[^']*

/* Hexadecimal byte string */
xhstart			[xX]{quote}
xhinside		[^']*

/* National character */
xnstart			[nN]{quote}

/* Quoted string that allows backslash escapes */
xestart			[eE]{quote}
xeinside		[^\\']+
xeescape		[\\][^0-7]
xeoctesc		[\\][0-7]{1,3}
xehexesc		[\\]x[0-9A-Fa-f]{1,2}
xeunicode		[\\](u[0-9A-Fa-f]{4}|U[0-9A-Fa-f]{8})

/* Extended quote
 * xqdouble implements embedded quote, ''''
 */
xqstart			{quote}
xqdouble		{quote}{quote}
xqcquote		[\\]{quote}
xqinside		[^']+

/* $foo$ style quotes ("dollar quoting")
 * The quoted string starts with $foo$ where "foo" is an optional string
 * in the form of an identifier, except that it may not contain "$",
 * and extends to the first occurrence of an identical string.
 * There is *no* processing of the quoted text.
 *
 * {dolqfailed} is an error rule to avoid scanner backup when {dolqdelim}
 * fails to match its trailing "$".
 */
dolq_start		[A-Za-z\200-\377_]
dolq_cont		[A-Za-z\200-\377_0-9]
dolqdelim		\$({dolq_start}{dolq_cont}*)?\$
dolqfailed		\${dolq_start}{dolq_cont}*
dolqinside		[^$]+

/* Double quote
 * Allows embedded spaces and other special characters into identifiers.
 */
dquote			\"
xdstart			{dquote}
xdstop			{dquote}
xddouble		{dquote}{dquote}
xdinside		[^"]+

/* Quoted identifier with Unicode escapes */
xuistart		[uU]&{dquote}

/* Quoted string with Unicode escapes */
xusstart		[uU]&{quote}

/* special stuff for C strings */
xdcqq			\\\\
xdcqdq			\\\"
xdcother		[^"]
xdcinside		({xdcqq}|{xdcqdq}|{xdcother})


/* C-style comments
 *
 * The "extended comment" syntax closely resembles allowable operator syntax.
 * The tricky part here is to get lex to recognize a string starting with
 * slash-star as a comment, when interpreting it as an operator would produce
 * a longer match --- remember lex will prefer a longer match!  Also, if we
 * have something like plus-slash-star, lex will think this is a 3-character
 * operator whereas we want to see it as a + operator and a comment start.
 * The solution is two-fold:
 * 1. append {op_chars}* to xcstart so that it matches as much text as
 *    {operator} would. Then the tie-breaker (first matching rule of same
 *    length) ensures xcstart wins.  We put back the extra stuff with yyless()
 *    in case it contains a star-slash that should terminate the comment.
 * 2. In the operator rule, check for slash-star within the operator, and
 *    if found throw it back with yyless().  This handles the plus-slash-star
 *    problem.
 * Dash-dash comments have similar interactions with the operator rule.
 */
xcstart			\/\*{op_chars}*
xcstop			\*+\/
xcinside		[^*/]+

ident_start		[A-Za-z\200-\377_]
ident_cont		[A-Za-z\200-\377_0-9\$]

identifier		{ident_start}{ident_cont}*

array			({ident_cont}|{whitespace}|[\[\]\+\-\*\%\/\(\)\>\.])*

/* Assorted special-case operators and operator-like tokens */
typecast		"::"
dot_dot			\.\.
colon_equals	":="

/*
 * These operator-like tokens (unlike the above ones) also match the {operator}
 * rule, which means that they might be overridden by a longer match if they
 * are followed by a comment start or a + or - character. Accordingly, if you
 * add to this list, you must also add corresponding code to the {operator}
 * block to return the correct token in such cases. (This is not needed in
 * psqlscan.l since the token value is ignored there.)
 */
equals_greater	"=>"
less_equals		"<="
greater_equals	">="
less_greater	"<>"
not_equals		"!="

/*
 * "self" is the set of chars that should be returned as single-character
 * tokens.  "op_chars" is the set of chars that can make up "Op" tokens,
 * which can be one or more characters long (but if a single-char token
 * appears in the "self" set, it is not to be returned as an Op).  Note
 * that the sets overlap, but each has some chars that are not in the other.
 *
 * If you change either set, adjust the character lists appearing in the
 * rule for "operator"!
 */
self			[,()\[\].;\:\+\-\*\/\%\^\<\>\=]
op_chars		[\~\!\@\#\^\&\|\`\?\+\-\*\/\%\<\>\=]
operator		{op_chars}+

/*
 * Numbers
 *
 * Unary minus is not part of a number here.  Instead we pass it separately to
 * the parser, and there it gets coerced via doNegate().
 *
 * {decimalfail} is used because we would like "1..10" to lex as 1, dot_dot, 10.
 *
 * {realfail} is added to prevent the need for scanner
 * backup when the {real} rule fails to match completely.
 */
digit			[0-9]

integer			{digit}+
decimal			(({digit}*\.{digit}+)|({digit}+\.{digit}*))
decimalfail		{digit}+\.\.
real			({integer}|{decimal})[Ee][-+]?{digit}+
realfail		({integer}|{decimal})[Ee][-+]

integer_junk	{integer}{ident_start}
decimal_junk	{decimal}{ident_start}
real_junk		{real}{ident_start}

param			\${integer}
param_junk		\${integer}{ident_start}

/* special characters for other dbms */
/* we have to react differently in compat mode */
informix_special	[\$]

other			.

/*
 * Dollar quoted strings are totally opaque, and no escaping is done on them.
 * Other quoted strings must allow some special characters such as single-quote
 *  and newline.
 * Embedded single-quotes are implemented both in the SQL standard
 *  style of two adjacent single quotes "''" and in the Postgres/Java style
 *  of escaped-quote "\'".
 * Other embedded escaped characters are matched explicitly and the leading
 *  backslash is dropped from the string.
 * Note that xcstart must appear before operator, as explained above!
 *  Also whitespace (comment) must appear before operator.
 */

/* some stuff needed for ecpg */
exec			[eE][xX][eE][cC]
sql				[sS][qQ][lL]
define			[dD][eE][fF][iI][nN][eE]
include			[iI][nN][cC][lL][uU][dD][eE]
include_next	[iI][nN][cC][lL][uU][dD][eE]_[nN][eE][xX][tT]
import			[iI][mM][pP][oO][rR][tT]
undef			[uU][nN][dD][eE][fF]

/* C version of hex number */
xch				0[xX][0-9A-Fa-f]*

ccomment		"//".*\n

if				[iI][fF]
ifdef			[iI][fF][dD][eE][fF]
ifndef			[iI][fF][nN][dD][eE][fF]
else			[eE][lL][sS][eE]
elif			[eE][lL][iI][fF]
endif			[eE][nN][dD][iI][fF]

struct			[sS][tT][rR][uU][cC][tT]

exec_sql		{exec}{space}*{sql}{space}*
ipdigit			({digit}|{digit}{digit}|{digit}{digit}{digit})
ip				{ipdigit}\.{ipdigit}\.{ipdigit}\.{ipdigit}

/* we might want to parse all cpp include files */
cppinclude		{space}*#{include}{space}*
cppinclude_next		{space}*#{include_next}{space}*

/* take care of cpp lines, they may also be continued */
/* first a general line for all commands not starting with "i" */
/* and then the other commands starting with "i", we have to add these
 * separately because the cppline production would match on "include" too
 */
cppline			{space}*#([^i][A-Za-z]*|{if}|{ifdef}|{ifndef}|{import})((\/\*[^*/]*\*+\/)|.|\\{space}*{newline})*{newline}

%%

%{
		/* code to execute during start of each call of yylex() */
		char *newdefsymbol = NULL;

		token_start = NULL;
%}

<SQL>{
{whitespace}	{
					/* ignore */
				}
} /* <SQL> */

<C,SQL>{
{xcstart}		{
					token_start = yytext;
					state_before_str_start = YYSTATE;
					xcdepth = 0;
					BEGIN(xc);
					/* Put back any characters past slash-star; see above */
					yyless(2);
					fputs("/*", yyout);
				}
} /* <C,SQL> */

<xc>{
{xcstart}		{
					if (state_before_str_start == SQL)
					{
						xcdepth++;
						/* Put back any characters past slash-star; see above */
						yyless(2);
						fputs("/_*", yyout);
					}
					else if (state_before_str_start == C)
					{
						ECHO;
					}
				}

{xcstop}		{
					if (state_before_str_start == SQL)
					{
						if (xcdepth <= 0)
						{
							ECHO;
							BEGIN(SQL);
							token_start = NULL;
						}
						else
						{
							xcdepth--;
							fputs("*_/", yyout);
						}
					}
					else if (state_before_str_start == C)
					{
						ECHO;
						BEGIN(C);
						token_start = NULL;
					}
				}

{xcinside}		{
					ECHO;
				}

{op_chars}		{
					ECHO;
				}

\*+				{
					ECHO;
				}

<<EOF>>			{
					mmfatal(PARSE_ERROR, "unterminated /* comment");
				}
} /* <xc> */

<SQL>{
{xbstart}		{
					token_start = yytext;
					state_before_str_start = YYSTATE;
					BEGIN(xb);
					startlit();
				}
} /* <SQL> */

<xh>{xhinside}	|
<xb>{xbinside}	{
					addlit(yytext, yyleng);
				}
<xb><<EOF>>		{ mmfatal(PARSE_ERROR, "unterminated bit string literal"); }

<SQL>{xhstart}	{
					token_start = yytext;
					state_before_str_start = YYSTATE;
					BEGIN(xh);
					startlit();
				}
<xh><<EOF>>		{ mmfatal(PARSE_ERROR, "unterminated hexadecimal string literal"); }

<C>{xqstart}	{
					token_start = yytext;
					state_before_str_start = YYSTATE;
					BEGIN(xqc);
					startlit();
				}

<SQL>{
{xnstart}		{
					/* National character.
					 * Transfer it as-is to the backend.
					 */
					token_start = yytext;
					state_before_str_start = YYSTATE;
					BEGIN(xn);
					startlit();
				}

{xqstart}		{
					token_start = yytext;
					state_before_str_start = YYSTATE;
					BEGIN(xq);
					startlit();
				}
{xestart}		{
					token_start = yytext;
					state_before_str_start = YYSTATE;
					BEGIN(xe);
					startlit();
				}
{xusstart}		{
					token_start = yytext;
					state_before_str_start = YYSTATE;
					BEGIN(xus);
					startlit();
				}
} /* <SQL> */

<xb,xh,xq,xqc,xe,xn,xus>{quote} {
					/*
					 * When we are scanning a quoted string and see an end
					 * quote, we must look ahead for a possible continuation.
					 * If we don't see one, we know the end quote was in fact
					 * the end of the string.  To reduce the lexer table size,
					 * we use a single "xqs" state to do the lookahead for all
					 * types of strings.
					 */
					state_before_str_stop = YYSTATE;
					BEGIN(xqs);
				}
<xqs>{quotecontinue} {
					/*
					 * Found a quote continuation, so return to the in-quote
					 * state and continue scanning the literal.  Nothing is
					 * added to the literal's contents.
					 */
					BEGIN(state_before_str_stop);
				}
<xqs>{quotecontinuefail} |
<xqs>{other} |
<xqs><<EOF>>	{
					/*
					 * Failed to see a quote continuation.  Throw back
					 * everything after the end quote, and handle the string
					 * according to the state we were in previously.
					 */
					yyless(0);
					BEGIN(state_before_str_start);

					switch (state_before_str_stop)
					{
						case xb:
							if (literalbuf[strspn(literalbuf, "01")] != '\0')
								mmerror(PARSE_ERROR, ET_ERROR, "invalid bit string literal");
							base_yylval.str = psprintf("b'%s'", literalbuf);
							return BCONST;
						case xh:
							if (literalbuf[strspn(literalbuf, "0123456789abcdefABCDEF")] != '\0')
								mmerror(PARSE_ERROR, ET_ERROR, "invalid hexadecimal string literal");
							base_yylval.str = psprintf("x'%s'", literalbuf);
							return XCONST;
						case xq:
							/* fallthrough */
						case xqc:
							base_yylval.str = psprintf("'%s'", literalbuf);
							return SCONST;
						case xe:
							base_yylval.str = psprintf("E'%s'", literalbuf);
							return SCONST;
						case xn:
							base_yylval.str = psprintf("N'%s'", literalbuf);
							return SCONST;
						case xus:
							base_yylval.str = psprintf("U&'%s'", literalbuf);
							return USCONST;
						default:
							mmfatal(PARSE_ERROR, "unhandled previous state in xqs\n");
					}
				}

<xq,xe,xn,xus>{xqdouble}	{ addlit(yytext, yyleng); }
<xqc>{xqcquote}				{ addlit(yytext, yyleng); }
<xq,xqc,xn,xus>{xqinside}	{ addlit(yytext, yyleng); }
<xe>{xeinside}  {
					addlit(yytext, yyleng);
				}
<xe>{xeunicode} {
					addlit(yytext, yyleng);
				}
<xe>{xeescape}  {
					addlit(yytext, yyleng);
				}
<xe>{xeoctesc}  {
					addlit(yytext, yyleng);
				}
<xe>{xehexesc}  {
					addlit(yytext, yyleng);
				}
<xe>.			{
					/* This is only needed for \ just before EOF */
					addlitchar(yytext[0]);
				}
<xq,xqc,xe,xn,xus><<EOF>>	{ mmfatal(PARSE_ERROR, "unterminated quoted string"); }

<SQL>{
{dolqdelim}		{
					token_start = yytext;
					if (dolqstart)
						free(dolqstart);
					dolqstart = mm_strdup(yytext);
					BEGIN(xdolq);
					startlit();
					addlit(yytext, yyleng);
				}
{dolqfailed}	{
					/* throw back all but the initial "$" */
					yyless(1);
					/* and treat it as {other} */
					return yytext[0];
				}
} /* <SQL> */

<xdolq>{dolqdelim} {
					if (strcmp(yytext, dolqstart) == 0)
					{
						addlit(yytext, yyleng);
						free(dolqstart);
						dolqstart = NULL;
						BEGIN(SQL);
						base_yylval.str = mm_strdup(literalbuf);
						return SCONST;
					}
					else
					{
						/*
						 * When we fail to match $...$ to dolqstart, transfer
						 * the $... part to the output, but put back the final
						 * $ for rescanning.  Consider $delim$...$junk$delim$
						 */
						addlit(yytext, yyleng - 1);
						yyless(yyleng - 1);
					}
				}
<xdolq>{dolqinside} {
					addlit(yytext, yyleng);
				}
<xdolq>{dolqfailed} {
					addlit(yytext, yyleng);
				}
<xdolq>.		{
					/* single quote or dollar sign */
					addlitchar(yytext[0]);
				}
<xdolq><<EOF>>	{ mmfatal(PARSE_ERROR, "unterminated dollar-quoted string"); }

<SQL>{
{xdstart}		{
					state_before_str_start = YYSTATE;
					BEGIN(xd);
					startlit();
				}
{xuistart}		{
					state_before_str_start = YYSTATE;
					BEGIN(xui);
					startlit();
				}
} /* <SQL> */

<xd>{xdstop}	{
					BEGIN(state_before_str_start);
					if (literallen == 0)
						mmerror(PARSE_ERROR, ET_ERROR, "zero-length delimited identifier");
					/*
					 * The server will truncate the identifier here.  We do
					 * not, as (1) it does not change the result; (2) we don't
					 * know what NAMEDATALEN the server might use; (3) this
					 * code path is also taken for literal query strings in
					 * PREPARE and EXECUTE IMMEDIATE, which can certainly be
					 * longer than NAMEDATALEN.
					 */
					base_yylval.str = mm_strdup(literalbuf);
					return CSTRING;
				}
<xdc>{xdstop}	{
					BEGIN(state_before_str_start);
					base_yylval.str = mm_strdup(literalbuf);
					return CSTRING;
				}
<xui>{dquote}	{
					BEGIN(state_before_str_start);
					if (literallen == 0)
						mmerror(PARSE_ERROR, ET_ERROR, "zero-length delimited identifier");
					/* The backend will truncate the identifier here. We do not as it does not change the result. */
					base_yylval.str = psprintf("U&\"%s\"", literalbuf);
					return UIDENT;
				}
<xd,xui>{xddouble}	{
					addlit(yytext, yyleng);
				}
<xd,xui>{xdinside}	{
					addlit(yytext, yyleng);
				}
<xd,xui><<EOF>>	{ mmfatal(PARSE_ERROR, "unterminated quoted identifier"); }
<C>{xdstart}	{
					state_before_str_start = YYSTATE;
					BEGIN(xdc);
					startlit();
				}
<xdc>{xdcinside}	{
					addlit(yytext, yyleng);
				}
<xdc><<EOF>>	{ mmfatal(PARSE_ERROR, "unterminated quoted string"); }

<SQL>{
{typecast}		{
					return TYPECAST;
				}

{dot_dot}		{
					return DOT_DOT;
				}

{colon_equals}	{
					return COLON_EQUALS;
				}

{equals_greater} {
					return EQUALS_GREATER;
				}

{less_equals}	{
					return LESS_EQUALS;
				}

{greater_equals} {
					return GREATER_EQUALS;
				}

{less_greater}	{
					/* We accept both "<>" and "!=" as meaning NOT_EQUALS */
					return NOT_EQUALS;
				}

{not_equals}	{
					/* We accept both "<>" and "!=" as meaning NOT_EQUALS */
					return NOT_EQUALS;
				}

{informix_special}	{
			  /* are we simulating Informix? */
				if (INFORMIX_MODE)
				{
					unput(':');
				}
				else
					return yytext[0];
				}

{self}			{
					/*
					 * We may find a ';' inside a structure
					 * definition in a TYPE or VAR statement.
					 * This is not an EOL marker.
					 */
					if (yytext[0] == ';' && struct_level == 0)
						BEGIN(C);
					return yytext[0];
				}

{operator}		{
					/*
					 * Check for embedded slash-star or dash-dash; those
					 * are comment starts, so operator must stop there.
					 * Note that slash-star or dash-dash at the first
					 * character will match a prior rule, not this one.
					 */
					int			nchars = yyleng;
					char	   *slashstar = strstr(yytext, "/*");
					char	   *dashdash = strstr(yytext, "--");

					if (slashstar && dashdash)
					{
						/* if both appear, take the first one */
						if (slashstar > dashdash)
							slashstar = dashdash;
					}
					else if (!slashstar)
						slashstar = dashdash;
					if (slashstar)
						nchars = slashstar - yytext;

					/*
					 * For SQL compatibility, '+' and '-' cannot be the
					 * last char of a multi-char operator unless the operator
					 * contains chars that are not in SQL operators.
					 * The idea is to lex '=-' as two operators, but not
					 * to forbid operator names like '?-' that could not be
					 * sequences of SQL operators.
					 */
					if (nchars > 1 &&
						(yytext[nchars - 1] == '+' ||
						 yytext[nchars - 1] == '-'))
					{
						int			ic;

						for (ic = nchars - 2; ic >= 0; ic--)
						{
							char c = yytext[ic];
							if (c == '~' || c == '!' || c == '@' ||
								c == '#' || c == '^' || c == '&' ||
								c == '|' || c == '`' || c == '?' ||
								c == '%')
								break;
						}
						if (ic < 0)
						{
							/*
							 * didn't find a qualifying character, so remove
							 * all trailing [+-]
							 */
							do {
								nchars--;
							} while (nchars > 1 &&
								 (yytext[nchars - 1] == '+' ||
								  yytext[nchars - 1] == '-'));
						}
					}

					if (nchars < yyleng)
					{
						/* Strip the unwanted chars from the token */
						yyless(nchars);
						/*
						 * If what we have left is only one char, and it's
						 * one of the characters matching "self", then
						 * return it as a character token the same way
						 * that the "self" rule would have.
						 */
						if (nchars == 1 &&
							strchr(",()[].;:+-*/%^<>=", yytext[0]))
							return yytext[0];
						/*
						 * Likewise, if what we have left is two chars, and
						 * those match the tokens ">=", "<=", "=>", "<>" or
						 * "!=", then we must return the appropriate token
						 * rather than the generic Op.
						 */
						if (nchars == 2)
						{
							if (yytext[0] == '=' && yytext[1] == '>')
								return EQUALS_GREATER;
							if (yytext[0] == '>' && yytext[1] == '=')
								return GREATER_EQUALS;
							if (yytext[0] == '<' && yytext[1] == '=')
								return LESS_EQUALS;
							if (yytext[0] == '<' && yytext[1] == '>')
								return NOT_EQUALS;
							if (yytext[0] == '!' && yytext[1] == '=')
								return NOT_EQUALS;
						}
					}

					base_yylval.str = mm_strdup(yytext);
					return Op;
				}

{param}			{
					base_yylval.ival = atol(yytext+1);
					return PARAM;
				}
{param_junk}	{
					mmfatal(PARSE_ERROR, "trailing junk after parameter");
				}

{ip}			{
					base_yylval.str = mm_strdup(yytext);
					return IP;
				}
}  /* <SQL> */

<C,SQL>{
{integer}		{
					return process_integer_literal(yytext, &base_yylval);
				}
{decimal}		{
					base_yylval.str = mm_strdup(yytext);
					return FCONST;
				}
{decimalfail}	{
					/* throw back the .., and treat as integer */
					yyless(yyleng - 2);
					return process_integer_literal(yytext, &base_yylval);
				}
{real}			{
					base_yylval.str = mm_strdup(yytext);
					return FCONST;
				}
{realfail}		{
					/*
					 * throw back the [Ee][+-], and figure out whether what
					 * remains is an {integer} or {decimal}.
					 */
					yyless(yyleng - 2);
					return process_integer_literal(yytext, &base_yylval);
				}
} /* <C,SQL> */

<SQL>{
	/*
	 * Note that some trailing junk is valid in C (such as 100LL), so we
	 * contain this to SQL mode.
	 */
{integer_junk}	{
					mmfatal(PARSE_ERROR, "trailing junk after numeric literal");
				}
{decimal_junk}	{
					mmfatal(PARSE_ERROR, "trailing junk after numeric literal");
				}
{real_junk}		{
					mmfatal(PARSE_ERROR, "trailing junk after numeric literal");
				}

:{identifier}((("->"|\.){identifier})|(\[{array}\]))*	{
					base_yylval.str = mm_strdup(yytext+1);
					return CVARIABLE;
				}

{identifier}	{
					/* First check to see if it's a define symbol to expand */
					if (!isdefine())
					{
						int		kwvalue;

						/* Is it an SQL/ECPG keyword? */
						kwvalue = ScanECPGKeywordLookup(yytext);
						if (kwvalue >= 0)
							return kwvalue;

						/* Is it a C keyword? */
						kwvalue = ScanCKeywordLookup(yytext);
						if (kwvalue >= 0)
							return kwvalue;

						/*
						 * None of the above.  Return it as an identifier.
						 *
						 * The backend will attempt to truncate and case-fold
						 * the identifier, but I see no good reason for ecpg
						 * to do so; that's just another way that ecpg could get
						 * out of step with the backend.
						 */
						base_yylval.str = mm_strdup(yytext);
						return IDENT;
					}
				}

{other}			{
					return yytext[0];
				}
} /* <SQL> */

	/*
	 * Begin ECPG-specific rules
	 */

<C>{exec_sql}		{ BEGIN(SQL); return SQL_START; }
<C>{informix_special}	{
						/* are we simulating Informix? */
						if (INFORMIX_MODE)
						{
							BEGIN(SQL);
							return SQL_START;
						}
						else
							return S_ANYTHING;
					 }
<C>{ccomment}		{ ECHO; }
<C>{xch}			{
						char* endptr;

						errno = 0;
						base_yylval.ival = strtoul((char *) yytext, &endptr, 16);
						if (*endptr != '\0' || errno == ERANGE)
						{
							errno = 0;
							base_yylval.str = mm_strdup(yytext);
							return SCONST;
						}
						return ICONST;
					}
<C>{cppinclude}		{
						if (system_includes)
						{
							include_next = false;
							BEGIN(incl);
						}
						else
						{
							base_yylval.str = mm_strdup(yytext);
							return CPP_LINE;
						}
					}
<C>{cppinclude_next}		{
						if (system_includes)
						{
							include_next = true;
							BEGIN(incl);
						}
						else
						{
							base_yylval.str = mm_strdup(yytext);
							return CPP_LINE;
						}
					}
<C,SQL>{cppline}	{
						base_yylval.str = mm_strdup(yytext);
						return CPP_LINE;
					}
<C>{identifier}		{
						/*
						 * Try to detect a function name:
						 * look for identifiers at the global scope
						 * keep the last identifier before the first '(' and '{'
						 */
						if (braces_open == 0 && parenths_open == 0)
						{
							if (current_function)
								free(current_function);
							current_function = mm_strdup(yytext);
						}
						/* Informix uses SQL defines only in SQL space */
						/* however, some defines have to be taken care of for compatibility */
						if ((!INFORMIX_MODE || !isinformixdefine()) && !isdefine())
						{
							int		kwvalue;

							kwvalue = ScanCKeywordLookup(yytext);
							if (kwvalue >= 0)
								return kwvalue;
							else
							{
								base_yylval.str = mm_strdup(yytext);
								return IDENT;
							}
						}
					}
<C>{xcstop}			{ mmerror(PARSE_ERROR, ET_ERROR, "nested /* ... */ comments"); }
<C>":"				{ return ':'; }
<C>";"				{ return ';'; }
<C>","				{ return ','; }
<C>"*"				{ return '*'; }
<C>"%"				{ return '%'; }
<C>"/"				{ return '/'; }
<C>"+"				{ return '+'; }
<C>"-"				{ return '-'; }
<C>"("				{ parenths_open++; return '('; }
<C>")"				{ parenths_open--; return ')'; }
<C,xskip>{space}		{ ECHO; }
<C>\{				{ return '{'; }
<C>\}				{ return '}'; }
<C>\[				{ return '['; }
<C>\]				{ return ']'; }
<C>\=				{ return '='; }
<C>"->"				{ return S_MEMBER; }
<C>">>"				{ return S_RSHIFT; }
<C>"<<"				{ return S_LSHIFT; }
<C>"||"				{ return S_OR; }
<C>"&&"				{ return S_AND; }
<C>"++"				{ return S_INC; }
<C>"--"				{ return S_DEC; }
<C>"=="				{ return S_EQUAL; }
<C>"!="				{ return S_NEQUAL; }
<C>"+="				{ return S_ADD; }
<C>"-="				{ return S_SUB; }
<C>"*="				{ return S_MUL; }
<C>"/="				{ return S_DIV; }
<C>"%="				{ return S_MOD; }
<C>"->*"			{ return S_MEMPOINT; }
<C>".*"				{ return S_DOTPOINT; }
<C>{other}			{ return S_ANYTHING; }
<C>{exec_sql}{define}{space}*	{ BEGIN(def_ident); }
<C>{informix_special}{define}{space}*	{
						/* are we simulating Informix? */
						if (INFORMIX_MODE)
						{
							BEGIN(def_ident);
						}
						else
						{
							yyless(1);
							return S_ANYTHING;
						}
					}
<C>{exec_sql}{undef}{space}*		{ BEGIN(undef); }
<C>{informix_special}{undef}{space}* {
						/* are we simulating Informix? */
						if (INFORMIX_MODE)
						{
							BEGIN(undef);
						}
						else
						{
							yyless(1);
							return S_ANYTHING;
						}
					}
<undef>{identifier}{space}*";" {
					struct _defines *ptr, *ptr2 = NULL;
					int i;

					/*
					 *	Skip the ";" and trailing whitespace. Note that yytext
					 *	contains at least one non-space character plus the ";"
					 */
					for (i = strlen(yytext)-2;
						 i > 0 && ecpg_isspace(yytext[i]);
						 i--)
						;
					yytext[i+1] = '\0';


					/* Find and unset any matching define; should be only 1 */
					for (ptr = defines; ptr; ptr2 = ptr, ptr = ptr->next)
					{
						if (strcmp(yytext, ptr->name) == 0)
						{
							free(ptr->value);
							ptr->value = NULL;
							/* We cannot forget it if there's a cmdvalue */
							if (ptr->cmdvalue == NULL)
							{
								if (ptr2 == NULL)
									defines = ptr->next;
								else
									ptr2->next = ptr->next;
								free(ptr->name);
								free(ptr);
							}
							break;
						}
					}

					BEGIN(C);
				}
<undef>{other}|\n {
						mmfatal(PARSE_ERROR, "missing identifier in EXEC SQL UNDEF command");
						yyterminate();
				}
<C>{exec_sql}{include}{space}*	{ BEGIN(incl); }
<C>{informix_special}{include}{space}* {
					  /* are we simulating Informix? */
					  if (INFORMIX_MODE)
					  {
						  BEGIN(incl);
					  }
					  else
					  {
						  yyless(1);
						  return S_ANYTHING;
					  }
					}
<C,xskip>{exec_sql}{ifdef}{space}* {
					  if (preproc_tos >= MAX_NESTED_IF-1)
						  mmfatal(PARSE_ERROR, "too many nested EXEC SQL IFDEF conditions");
					  preproc_tos++;
					  stacked_if_value[preproc_tos].active = false;
					  stacked_if_value[preproc_tos].saw_active = false;
					  stacked_if_value[preproc_tos].else_branch = false;
					  ifcond = true;
					  BEGIN(xcond);
					}
<C,xskip>{informix_special}{ifdef}{space}* {
					  /* are we simulating Informix? */
					  if (INFORMIX_MODE)
					  {
						  if (preproc_tos >= MAX_NESTED_IF-1)
							  mmfatal(PARSE_ERROR, "too many nested EXEC SQL IFDEF conditions");
						  preproc_tos++;
						  stacked_if_value[preproc_tos].active = false;
						  stacked_if_value[preproc_tos].saw_active = false;
						  stacked_if_value[preproc_tos].else_branch = false;
						  ifcond = true;
						  BEGIN(xcond);
					  }
					  else
					  {
						  yyless(1);
						  return S_ANYTHING;
					  }
					}
<C,xskip>{exec_sql}{ifndef}{space}* {
					  if (preproc_tos >= MAX_NESTED_IF-1)
						  mmfatal(PARSE_ERROR, "too many nested EXEC SQL IFDEF conditions");
					  preproc_tos++;
					  stacked_if_value[preproc_tos].active = false;
					  stacked_if_value[preproc_tos].saw_active = false;
					  stacked_if_value[preproc_tos].else_branch = false;
					  ifcond = false;
					  BEGIN(xcond);
					}
<C,xskip>{informix_special}{ifndef}{space}* {
					  /* are we simulating Informix? */
					  if (INFORMIX_MODE)
					  {
						  if (preproc_tos >= MAX_NESTED_IF-1)
							  mmfatal(PARSE_ERROR, "too many nested EXEC SQL IFDEF conditions");
						  preproc_tos++;
						  stacked_if_value[preproc_tos].active = false;
						  stacked_if_value[preproc_tos].saw_active = false;
						  stacked_if_value[preproc_tos].else_branch = false;
						  ifcond = false;
						  BEGIN(xcond);
					  }
					  else
					  {
						  yyless(1);
						  return S_ANYTHING;
					  }
					}
<C,xskip>{exec_sql}{elif}{space}*	{
						if (preproc_tos == 0)
							mmfatal(PARSE_ERROR, "missing matching \"EXEC SQL IFDEF\" / \"EXEC SQL IFNDEF\"");
						if (stacked_if_value[preproc_tos].else_branch)
							mmfatal(PARSE_ERROR, "missing \"EXEC SQL ENDIF;\"");
						ifcond = true;
						BEGIN(xcond);
					}
<C,xskip>{informix_special}{elif}{space}* {
					/* are we simulating Informix? */
					if (INFORMIX_MODE)
					{
						if (preproc_tos == 0)
							mmfatal(PARSE_ERROR, "missing matching \"EXEC SQL IFDEF\" / \"EXEC SQL IFNDEF\"");
						if (stacked_if_value[preproc_tos].else_branch)
							mmfatal(PARSE_ERROR, "missing \"EXEC SQL ENDIF;\"");
						ifcond = true;
						BEGIN(xcond);
					}
					else
					{
						yyless(1);
						return S_ANYTHING;
					}
				}

<C,xskip>{exec_sql}{else}{space}*";" {	/* only exec sql endif pops the stack, so take care of duplicated 'else' */
					if (preproc_tos == 0)
						mmfatal(PARSE_ERROR, "missing matching \"EXEC SQL IFDEF\" / \"EXEC SQL IFNDEF\"");
					else if (stacked_if_value[preproc_tos].else_branch)
						mmfatal(PARSE_ERROR, "more than one EXEC SQL ELSE");
					else
					{
						stacked_if_value[preproc_tos].else_branch = true;
						stacked_if_value[preproc_tos].active =
							(stacked_if_value[preproc_tos-1].active &&
							 !stacked_if_value[preproc_tos].saw_active);
						stacked_if_value[preproc_tos].saw_active = true;

						if (stacked_if_value[preproc_tos].active)
							BEGIN(C);
						else
							BEGIN(xskip);
					}
				}
<C,xskip>{informix_special}{else}{space}*";"	{
					/* are we simulating Informix? */
					if (INFORMIX_MODE)
					{
						if (preproc_tos == 0)
							mmfatal(PARSE_ERROR, "missing matching \"EXEC SQL IFDEF\" / \"EXEC SQL IFNDEF\"");
						else if (stacked_if_value[preproc_tos].else_branch)
							mmfatal(PARSE_ERROR, "more than one EXEC SQL ELSE");
						else
						{
							stacked_if_value[preproc_tos].else_branch = true;
							stacked_if_value[preproc_tos].active =
								(stacked_if_value[preproc_tos-1].active &&
								 !stacked_if_value[preproc_tos].saw_active);
							stacked_if_value[preproc_tos].saw_active = true;

							if (stacked_if_value[preproc_tos].active)
								BEGIN(C);
							else
								BEGIN(xskip);
						}
					}
					else
					{
						yyless(1);
						return S_ANYTHING;
					}
				}
<C,xskip>{exec_sql}{endif}{space}*";" {
					if (preproc_tos == 0)
						mmfatal(PARSE_ERROR, "unmatched EXEC SQL ENDIF");
					else
						preproc_tos--;

					if (stacked_if_value[preproc_tos].active)
					   BEGIN(C);
					else
					   BEGIN(xskip);
				}
<C,xskip>{informix_special}{endif}{space}*";"	{
					/* are we simulating Informix? */
					if (INFORMIX_MODE)
					{
						if (preproc_tos == 0)
							mmfatal(PARSE_ERROR, "unmatched EXEC SQL ENDIF");
						else
							preproc_tos--;

						if (stacked_if_value[preproc_tos].active)
							BEGIN(C);
						else
							BEGIN(xskip);
					}
					else
					{
						yyless(1);
						return S_ANYTHING;
					}
				}

<xskip>{other}		{ /* ignore */ }

<xcond>{identifier}{space}*";" {
					{
						struct _defines *defptr;
						unsigned int i;
						bool this_active;

						/*
						 *	Skip the ";" and trailing whitespace. Note that yytext
						 *	contains at least one non-space character plus the ";"
						 */
						for (i = strlen(yytext)-2;
							 i > 0 && ecpg_isspace(yytext[i]);
							 i--)
							;
						yytext[i+1] = '\0';

						/* Does a definition exist? */
						for (defptr = defines; defptr; defptr = defptr->next)
						{
							if (strcmp(yytext, defptr->name) == 0)
							{
								/* Found it, but is it currently undefined? */
								if (defptr->value == NULL)
									defptr = NULL; /* pretend it's not found */
								break;
							}
						}

						this_active = (defptr ? ifcond : !ifcond);
						stacked_if_value[preproc_tos].active =
							(stacked_if_value[preproc_tos-1].active &&
							 !stacked_if_value[preproc_tos].saw_active &&
							 this_active);
						stacked_if_value[preproc_tos].saw_active |= this_active;
					}

					if (stacked_if_value[preproc_tos].active)
						BEGIN(C);
					else
						BEGIN(xskip);
				}

<xcond>{other}|\n	{
				mmfatal(PARSE_ERROR, "missing identifier in EXEC SQL IFDEF command");
				yyterminate();
			}
<def_ident>{identifier} {
				newdefsymbol = mm_strdup(yytext);
				BEGIN(def);
				startlit();
			}
<def_ident>{other}|\n	{
				mmfatal(PARSE_ERROR, "missing identifier in EXEC SQL DEFINE command");
				yyterminate();
			}
<def>{space}*";"	{
						struct _defines *ptr;

						/* Does it already exist? */
						for (ptr = defines; ptr != NULL; ptr = ptr->next)
						{
							if (strcmp(newdefsymbol, ptr->name) == 0)
							{
								free(ptr->value);
								ptr->value = mm_strdup(literalbuf);
								/* Don't leak newdefsymbol */
								free(newdefsymbol);
								break;
							}
						}
						if (ptr == NULL)
						{
							/* Not present, make a new entry */
							ptr = (struct _defines *) mm_alloc(sizeof(struct _defines));

							ptr->name = newdefsymbol;
							ptr->value = mm_strdup(literalbuf);
							ptr->cmdvalue = NULL;
							ptr->used = NULL;
							ptr->next = defines;
							defines = ptr;
						}

						BEGIN(C);
					}
<def>[^;]			{ addlit(yytext, yyleng); }
<incl>\<[^\>]+\>{space}*";"?		{	parse_include(); }
<incl>{dquote}{xdinside}{dquote}{space}*";"?	{	parse_include(); }
<incl>[^;\<\>\"]+";"		{ parse_include(); }
<incl>{other}|\n		{
					mmfatal(PARSE_ERROR, "syntax error in EXEC SQL INCLUDE command");
					yyterminate();
				}

<<EOF>>				{
					if (yy_buffer == NULL)
					{
						/* No more input */
						if (preproc_tos > 0)
						{
							preproc_tos = 0;
							mmfatal(PARSE_ERROR, "missing \"EXEC SQL ENDIF;\"");
						}
						yyterminate();
					}
					else
					{
						/* Revert to previous input source */
						struct _yy_buffer *yb = yy_buffer;
						int i;
						struct _defines *ptr;

						/* Check to see if we are exiting a macro value */
						for (ptr = defines; ptr; ptr = ptr->next)
						{
							if (ptr->used == yy_buffer)
							{
								ptr->used = NULL;
								break; /* there can't be multiple matches */
							}
						}

						if (yyin != NULL)
							fclose(yyin);

						yy_delete_buffer(YY_CURRENT_BUFFER);
						yy_switch_to_buffer(yy_buffer->buffer);

						yylineno = yy_buffer->lineno;

						/* We have to output the filename only if we change files here */
						i = strcmp(input_filename, yy_buffer->filename);

						free(input_filename);
						input_filename = yy_buffer->filename;

						yy_buffer = yy_buffer->next;
						free(yb);

						if (i != 0)
							output_line_number();

					}
				}

<INITIAL>{other}|\n	{ mmfatal(PARSE_ERROR, "internal error: unreachable state; please report this to <%s>", PACKAGE_BUGREPORT); }

%%

/* LCOV_EXCL_STOP */

void
lex_init(void)
{
	braces_open = 0;
	parenths_open = 0;
	current_function = NULL;

	yylineno = 1;

	/* initialize state for if/else/endif */
	preproc_tos = 0;
	stacked_if_value[preproc_tos].active = true;
	stacked_if_value[preproc_tos].saw_active = true;
	stacked_if_value[preproc_tos].else_branch = false;

	/* initialize literal buffer to a reasonable but expansible size */
	if (literalbuf == NULL)
	{
		literalalloc = 1024;
		literalbuf = (char *) mm_alloc(literalalloc);
	}
	startlit();

	BEGIN(C);
}

static void
addlit(char *ytext, int yleng)
{
	/* enlarge buffer if needed */
	if ((literallen+yleng) >= literalalloc)
	{
		do
			literalalloc *= 2;
		while ((literallen+yleng) >= literalalloc);
		literalbuf = (char *) realloc(literalbuf, literalalloc);
	}
	/* append new data, add trailing null */
	memcpy(literalbuf+literallen, ytext, yleng);
	literallen += yleng;
	literalbuf[literallen] = '\0';
}

static void
addlitchar(unsigned char ychar)
{
	/* enlarge buffer if needed */
	if ((literallen+1) >= literalalloc)
	{
		literalalloc *= 2;
		literalbuf = (char *) realloc(literalbuf, literalalloc);
	}
	/* append new data, add trailing null */
	literalbuf[literallen] = ychar;
	literallen += 1;
	literalbuf[literallen] = '\0';
}

/*
 * Process {integer}.  Note this will also do the right thing with {decimal},
 * ie digits and a decimal point.
 */
static int
process_integer_literal(const char *token, YYSTYPE *lval)
{
	int			val;
	char	   *endptr;

	errno = 0;
	val = strtoint(token, &endptr, 10);
	if (*endptr != '\0' || errno == ERANGE)
	{
		/* integer too large (or contains decimal pt), treat it as a float */
		lval->str = mm_strdup(token);
		return FCONST;
	}
	lval->ival = val;
	return ICONST;
}

static void
parse_include(void)
{
	/* got the include file name */
	struct _yy_buffer *yb;
	struct _include_path *ip;
	char inc_file[MAXPGPATH];
	unsigned int i;

	yb = mm_alloc(sizeof(struct _yy_buffer));

	yb->buffer =	YY_CURRENT_BUFFER;
	yb->lineno = yylineno;
	yb->filename = input_filename;
	yb->next = yy_buffer;

	yy_buffer = yb;

	/*
	 * skip the ";" if there is one and trailing whitespace. Note that
	 * yytext contains at least one non-space character plus the ";"
	 */
	for (i = strlen(yytext)-2;
		 i > 0 && ecpg_isspace(yytext[i]);
		 i--)
		;

	if (yytext[i] == ';')
		i--;

	yytext[i+1] = '\0';

	yyin = NULL;

	/* If file name is enclosed in '"' remove these and look only in '.' */
	/* Informix does look into all include paths though, except filename starts with '/' */
	if (yytext[0] == '"' && yytext[i] == '"' &&
		((compat != ECPG_COMPAT_INFORMIX && compat != ECPG_COMPAT_INFORMIX_SE) || yytext[1] == '/'))
	{
		yytext[i] = '\0';
		memmove(yytext, yytext+1, strlen(yytext));

		strlcpy(inc_file, yytext, sizeof(inc_file));
		yyin = fopen(inc_file, "r");
		if (!yyin)
		{
			if (strlen(inc_file) <= 2 || strcmp(inc_file + strlen(inc_file) - 2, ".h") != 0)
			{
				strcat(inc_file, ".h");
				yyin = fopen(inc_file, "r");
			}
		}

	}
	else
	{
		if ((yytext[0] == '"' && yytext[i] == '"') || (yytext[0] == '<' && yytext[i] == '>'))
		{
			yytext[i] = '\0';
			memmove(yytext, yytext+1, strlen(yytext));
		}

		for (ip = include_paths; yyin == NULL && ip != NULL; ip = ip->next)
		{
			if (strlen(ip->path) + strlen(yytext) + 4 > MAXPGPATH)
			{
				fprintf(stderr, _("Error: include path \"%s/%s\" is too long on line %d, skipping\n"), ip->path, yytext, yylineno);
				continue;
			}
			snprintf (inc_file, sizeof(inc_file), "%s/%s", ip->path, yytext);
			yyin = fopen(inc_file, "r");
			if (!yyin)
			{
				if (strcmp(inc_file + strlen(inc_file) - 2, ".h") != 0)
				{
					strcat(inc_file, ".h");
					yyin = fopen(inc_file, "r");
				}
			}
			/* if the command was "include_next" we have to disregard the first hit */
			if (yyin && include_next)
			{
				fclose (yyin);
				yyin = NULL;
				include_next = false;
			}
		}
	}
	if (!yyin)
		mmfatal(NO_INCLUDE_FILE, "could not open include file \"%s\" on line %d", yytext, yylineno);

	input_filename = mm_strdup(inc_file);
	yy_switch_to_buffer(yy_create_buffer(yyin,YY_BUF_SIZE));
	yylineno = 1;
	output_line_number();

	BEGIN(C);
}

/*
 * ecpg_isspace() --- return true if flex scanner considers char whitespace
 */
static bool
ecpg_isspace(char ch)
{
	if (ch == ' ' ||
		ch == '\t' ||
		ch == '\n' ||
		ch == '\r' ||
		ch == '\f')
		return true;
	return false;
}

/*
 * If yytext matches a define symbol, begin scanning the symbol's value
 * and return true
 */
static bool
isdefine(void)
{
	struct _defines *ptr;

	/* is it a define? */
	for (ptr = defines; ptr; ptr = ptr->next)
	{
		/* notice we do not match anything being actively expanded */
		if (strcmp(yytext, ptr->name) == 0 &&
			ptr->value != NULL &&
			ptr->used == NULL)
		{
			/* Save state associated with the current buffer */
			struct _yy_buffer *yb;

			yb = mm_alloc(sizeof(struct _yy_buffer));

			yb->buffer =  YY_CURRENT_BUFFER;
			yb->lineno = yylineno;
			yb->filename = mm_strdup(input_filename);
			yb->next = yy_buffer;
			yy_buffer = yb;

			/* Mark symbol as being actively expanded */
			ptr->used = yb;

			/*
			 * We use yy_scan_string which will copy the value, so there's
			 * no need to worry about a possible undef happening while we
			 * are still scanning it.
			 */
			yy_scan_string(ptr->value);
			return true;
		}
	}

	return false;
}

/*
 * Handle replacement of INFORMIX built-in defines.  This works just
 * like isdefine() except for the source of the string to scan.
 */
static bool
isinformixdefine(void)
{
	const char *new = NULL;

	if (strcmp(yytext, "dec_t") == 0)
		new = "decimal";
	else if (strcmp(yytext, "intrvl_t") == 0)
		new = "interval";
	else if (strcmp(yytext, "dtime_t") == 0)
		new = "timestamp";

	if (new)
	{
		struct _yy_buffer *yb;

		yb = mm_alloc(sizeof(struct _yy_buffer));

		yb->buffer =  YY_CURRENT_BUFFER;
		yb->lineno = yylineno;
		yb->filename = mm_strdup(input_filename);
		yb->next = yy_buffer;
		yy_buffer = yb;

		yy_scan_string(new);
		return true;
	}

	return false;
}