File: flexml.pl

package info (click to toggle)
flexml 1.9.6-1
  • links: PTS, VCS
  • area: main
  • in suites: jessie, jessie-kfreebsd
  • size: 640 kB
  • ctags: 225
  • sloc: perl: 1,304; makefile: 261; xml: 188; ansic: 117
file content (2135 lines) | stat: -rwxr-xr-x 64,671 bytes parent folder | download | duplicates (2)
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
#!/usr/bin/env perl

# Flex(1) XML processor scanner generator.
# Copyright (C) 1999 Kristoffer Rose.  All rights reserved.
#
# This file is part of the FleXML XML processor generator system.
# Copyright (C) 1999 Kristoffer Rose.  All rights reserved.
# Copyright (C) 2003-2013 Martin Quinson.  All rights reserved.
#
# This program is free software; you can redistribute it and/or modify it
# under the terms of the GNU General Public License as published by the Free
# Software Foundation; either version 2 of the License, or (at your option)
# any later version.
#
# This program is distributed in the hope that it will be useful, but WITHOUT
# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
# FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
# more details.
#
# You should have received a copy of the GNU General Public License along
# with this program; if not, write to the Free Software Foundation, Inc., 59
# Temple Place, Suite 330, Boston, MA 02111-1307 USA.

use warnings;

my $Id = 'FLEXMLVERSION';

# IMPORTS.

use Getopt::Long;
use LWP::UserAgent;
use Carp qw/cluck confess/;

use strict;

# FILES (must be global).

use vars qw/ $SKELETON /;	# the skeleton scanner
use vars qw/ $SCANNER /;	# generated XML processor (+ application if requested)
use vars qw/ $HEADER /;		# generated XML processor API header
use vars qw/ $ACTIONS /;	# the actions file
use vars qw/ $APPLICATION /;	# generated XML application

$SKELETON = "./skel"; # default value

# OPTIONS (and other globals).

my $Use;			# usage string

my $debug;			# -d option flag
my $verbose;			# -v option flag
my $lineno;			# -L option flag
my $nofail;			# -X option flag
my $quiet_parser;		# -q option flag
my $uri;			# -u option uri
my $pubid;			# -p option string
my $sysid;			# --sysid option string
my $stacksize=100000;		# -b option flag
my $tagprefix="";      		# -P option flag
my $actbin="./flexml-act";      # -T option content
my $init_header="";             # -i option string

my $header;			# -H option flag/content
my $dummy;			# -D option flag/content
my $standalone;			# -A option flag/content
my $scanner;			# -S option flag/content
my $actions;			# -a option content

my $dryrun;                     # -n option flag

my $dtd;			# DTD file name (or URI)
my $dtdrevision;		# DTD version pruned from file
my $cdtd;			# C identifier derived from DTD name

my @inputs = ();		# input data stack (array of arrays of lines)
my @inputnames = ();		# names of files on input data stack
my @inputlinenos = ();		# line number in input files

# DTD regular expressions (extended to not mess up the counting).

my $NameChar = '[A-Za-z0-9.:_-]';
my $Name     = "[A-Za-z_:]$NameChar*";
my $Names    = "$Name(?:\\s+$Name)*";
my $Nmtoken  = "$NameChar+";
my $Nmtokens = "$Nmtoken(?:\\s+$Nmtoken)*";
my $Eq       = '\s*=\s*';
my $Literal  = '(?:\'[^\']*\'|"[^"]*")';

# DTD DESCRIPTION STRUCTURES.

my %source = ();	# DTD source lines associated to tag and tag/attribute.

my @tags = ();		# Tags of the DTD.
my %roottags = ();	# Tags that may be the root tag.
my %ctag = ();		# C variable name of each tag.

my %allstates = ();     # all existing states are key of this hash
my %states = ();	# $states{tag} is list of states used by tag element.
my %emptytrans = ();	# $emptytrans{state} contains empty transitions in automaton.

my %instates = ();	# $instates{tag} is list of states for element start/empty tag.
my %startstate = ();	# $startstate{tag} is the state entered after the start tag.
my %endstates = ();	# $endstates{tag} is list of states for element end tag.
my %exittrans = ();	# $exittrans{tag} is state transitions after end tag.

my %empty = ();		# $empty{tag} == true if the tag may be empty.
my %properempty = ();	# $empty{tag} == true if the tag is declared EMPTY
my %any = ();		# $any{tag} == true if the tag has ANY contents.
my %mixed = ();		# $mixed{tag} == true if the tag has Mixed (or ANY) contents.
my %children = ();	# $children{tag} == true if the tag has Element contents

my %inmixed = ();	# $inmixed{tag} == true if the tag occurs *in* Mixed contents.

my @attributes = ();	# Attributes of the DTD.
my %catt = ();		# C variable name for attribute.

my %atttype = ();	# XML AttType (type) of tag/attribute
my %enumtype = ();	# whether the tag/attribute is an enumeration type
my %literaltype = ();	# whether the tag/attribute is a tokenized type
my %entitytype = ();	# whether the tag/attribute is of entity type
my %typeof = ();	# C type of tag/attribute

my %attdef = ();	# XML AttDef (default value) of tag/attribute
my %required = ();	# true if tag/attribute is required
my %fixed = ();		# true if tag/attribute has fixed default
my %initof = ();	# C initial attribute value of tag/attribute, if any

my %attlist = ();	# $attlist{tag} is comma-separated list of attribute
			# names allowed in tag elements.
my %withattr = ();	# $withattr{attribute} is comma-separated list of
			# elements within which the tag element may occur.

my %entity = ();	# general entity table (C strings)
my %parameter = ();	# parameter entity table (raw string)
my %external = ();      # external entity table (uris)

my %startok = ();	# start tag action already dumped
my %endok = ();		# end tag action already dumped



# UTILITIES.


sub printsource { # Print source lines of argument.
  my ($key) = @_;
  local $_ = $source{$key};
  return if not $_;

  s:[*][/]:* /:g;		# avoid */ in output [sic]
  s/\n/\n  * /mg;
  print "\n /* " . $_ . "  */\n";
}


sub cquote { # Convert a string to C source format.
  local ($_) = @_;
  s/\\/\\\\/go;			# First replace \ to avoid interference...
  s/\"/\\\"/go;
  s/\n/\\n/go; s/\r/\\r/g; s/\t/\\t/g; s/\f/\\f/go;
  s/[\0-\037\200-\377]/ sprintf("\\%.3o",ord($&)) /ge;
  $_
}


sub variablify { # Change XML Name to legal C variable name.
  local ($_) = @_;
  s|_|___|go;
  s|-|_d_|go;
  s|:|_c_|go;
  s|/|_s_|go;
  $_
}


sub redistribute { # Print C comment with generated file "license".
                   # Notice that this is not intended to affect
                   # flexml.pl itself.
  my ($pre) = @_;
  print <<EOT;
$pre This program was generated with the FleXML XML processor generator.
$pre FleXML is Copyright (C) 1999-2005 Kristoffer Rose.  All rights reserved.
$pre FleXML is Copyright (C) 2003-2013 Martin Quinson.  All rights reserved.
$pre (FLEXMLVERSION).
$pre 
$pre There are two, intertwined parts to this program, part A and part B.
$pre
$pre Part A
$pre ------
$pre 
$pre Some parts, here collectively called "Part A", are found in the 
$pre FleXML package.  They are Copyright (C) 1999-2005 Kristoffer Rose
$pre and Copyright (C) 2003-2013 Martin Quinson. All rights reserved.
$pre
$pre You can redistribute, use, perform, display and/or modify "Part A"
$pre provided the following two conditions hold:
$pre
$pre 1. The program is distributed WITHOUT ANY WARRANTY from the author of
$pre    FleXML; without even the implied warranty of MERCHANTABILITY or
$pre    FITNESS FOR A PARTICULAR PURPOSE.
$pre
$pre 2. The program distribution conditions do not in any way affect the
$pre    distribution conditions of the FleXML system used to generate this
$pre    file or any version of FleXML derived from that system.
$pre
$pre Notice that these are explicit rights granted to you for files
$pre generated by the FleXML system.  For your rights in connection with
$pre the FleXML system itself please consult the GNU General Public License.
$pre 
$pre Part B
$pre ------
$pre 
$pre The other parts, here collectively called "Part B", and which came 
$pre from the DTD used by FleXML to generate this program, can be 
$pre distributed (or not, as the case may be) under the terms of whoever
$pre wrote them, provided these terms respect and obey the two conditions 
$pre above under the heading "Part A".
$pre
$pre The author of and contributors to FleXML specifically disclaim
$pre any copyright interest in "Part B", unless "Part B" was written 
$pre by the author of or contributors to FleXML.
$pre 
EOT
}


sub api_functions { # Print XML application interface functions.
  my ($pre,$post) = @_;
  print "/* XML application entry points. */\n" if @tags;
  for (@tags) {
    print $pre . "void STag_${tagprefix}$ctag{$_}(void)$post\n" unless $startok{$_};
    print $pre . "void ETag_${tagprefix}$ctag{$_}(void)$post\n" unless $endok{$_};
  }
}


sub api_types { # Print XML application interface types.
  print "/* XML application data. */\n" if %atttype;
  for (keys %atttype) {
    if (m.($Nmtoken)[/]($Nmtoken).xo) {
      my ($tag,$attribute) = ($1,$2);
      print "typedef $typeof{$_} AT_${tagprefix}$ctag{$tag}_$catt{$attribute};\n";
      print "#define AU_${tagprefix}$ctag{$tag}_$catt{$attribute} NULL\n"
	if not $enumtype{$_};
    }
  }
}


sub api_data { # Print XML application interface parameters.
  my ($pre) = @_; # pre should be a storage class spec like 'static' or 'extern'
  print "/* FleXML-provided data. */\n";
  print $pre . "int ${tagprefix}pcdata_ix;\n";
  print "extern char *${tagprefix}bufferstack;\n";
  print "#define ${tagprefix}pcdata (${tagprefix}bufferstack + ${tagprefix}pcdata_ix)\n";

  for (keys %atttype) {
    if (m.($Nmtoken)[/]($Nmtoken).xo) {
      print $pre . "AT_${tagprefix}$ctag{$1}_$catt{$2} AX_${tagprefix}$ctag{$1}_$catt{$2};\n";
      print "#define A_${tagprefix}$ctag{$1}_$catt{$2} ";
      if ($enumtype{$_}) {
	  print "AX_${tagprefix}$ctag{$1}_$catt{$2}\n";
      }
      else {
	  print "(${tagprefix}bufferstack + AX_${tagprefix}$ctag{$1}_$catt{$2})\n";
      }
      print $pre . "short int ${tagprefix}$ctag{$1}_$catt{$2}_isset;\n";
    }
  }
}


sub expandparametersat { # Expand parameter entities in $_ at $place.
  my ($place) = @_;
  while ( m/$place\s*%($Name);/ ) {
    if (defined $parameter{$1}) {
      s/$place(\s*)%($Name);/ ' '. $1 . $parameter{$2} . ' ' /xe;
    }
  }
}


sub geturl { # Insert contents of URL into input stream at current point

  my ($url) = @_;
  $url = "file:$url" if not $url =~ m/:/;
  local $_ = $url;
  s.([^/:]*[/:])*..g;
  s/\.dtd$//;

  print STDOUT "Fetching URL <$url>.\n" if $verbose;
  my $ua = new LWP::UserAgent;  # Create a user agent object
  $ua->agent("FleXML/1 " . $ua->agent);
  my $req = new HTTP::Request GET => $url; # Create a request
  my $res = $ua->request($req);	# Pass request to the user agent and get a response
  if ($res->is_error) {
    die place()."URL <$url> could not be fetched.\n";
  }

  # Make the data available...
  push @inputs, [ split /\r?\n/, $res->content ];
  if (@{$inputs[$#inputs]}) {
    push @inputnames, "$url";
    push @inputlinenos, 0;
  }
  else {
    pop @inputs;		# oops, empty.
  }

#  print STDOUT "Testing:\n";
#  my $i = 0;
#  for my $ref (@inputs) {
#    print STDOUT " inputs[" . $i++ . "] =\n";
#    for my $line (@{$ref}) {
#      print " | $line\n";
#    }
#  }
#  $i = 0;
#  for my $name (@inputnames) {
#    print STDOUT " inputnames[" . $i++ . "] = `$name'\n";
#  }
#  $i = 0;
#  for my $no (@inputlinenos) {
#    print STDOUT " inputlinenos[" . $i++ . "] = `$no'\n";
#  }
}

# add attribute to list of all default attributes
my @default_attributes;
my $next_att_loc = 1;
sub add_def_att {
    my ($att) = @_;
    my $retval = $next_att_loc;
    push @default_attributes, ($att);
    $next_att_loc += length($att) + 1;
    return $retval;
}

sub nextline {			# return one input line

  return undef unless @inputs;

  my $line = shift @{$inputs[$#inputs]};
  $inputlinenos[$#inputs]++;

  while (@inputs and not @{$inputs[$#inputs]}) { # discard exhausted inputs
    pop @inputs;
    pop @inputnames;
    pop @inputlinenos;
  }

  return $line;
}


sub place {
  if (@inputs) {
    local $_ = "\"$inputnames[$#inputs]\", line $inputlinenos[$#inputs]: ";
    s/"file:/"/;
    return $_;
  }
  else {
    return "";
  }
}


# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - 
# extractcp($str) - Split argument in one cp[48] (content particles) and the rest.
#
# returns ($cp,$rest)
#
sub extractcp { 

  # $_ stores the remainder of the string we're looking at
  local ($_) = @_;
  
  # shack - I noticed that the 'match one Name' pattern below
  # does not accept leading spaces, but the ( pattern does
  # This is a little warning that will enlighten me if this occurs
  m/^\s+/ and do {
    cluck("extractcp matching leading spaces!  '$_'");
  };

  if ( m/^($Name[+?*]?)\s*/o ) {    # match one Name
    return ($1,$'); #'
  }
    
  if ( m/^\s*\(/o ) {               # match the start of a choice or seq
  
    # build up one CP my matching parens
    my $cp = '('; $_ = $'; #'
    my $level = 1;

    # match nested parenthesis
    while ($level > 0 and $_) {

      if ( m/^\s*\(\s*/o ) {              # open paren
	$level++; 
        $cp .= '('; 
        $_ = $'; #'
      }
      elsif ( m/^\s*(\)[+?*]?)\s*/o ) {   # close paren
	$level--; 
        $cp .= $1; 
        $_ = $'; #'
      }
      elsif ( m/^\s+/o ) {                # skip white space
	$_ = $'; #'
      }
      else {                              # everything else
	m/[^()\s]+/o; 
        $cp .= $&; 
        $_ = $'; #'
      }
    }
    return ($cp,$_);
  }

  confess ("should not get here!");
}


my $statecounter;

sub analysechildren { # Analyse DTD children specification; return
                      # true if it may be empty.  Uses global $statecounter.

  my ($tag,$re,$in,$out) = @_;
  $allstates{$in} = 1;
  $allstates{$out} = 1;

  print "analysechildren [ $tag, $re, $in, $out ] \n" if $debug;

  local $_ = $re;

  if ( m/^\s*($Name)\s*$/o ) { # tag

    my $thetag = $1;
    my %ins = ();
    if (exists $instates{$thetag}) {
      for (split /,/,$instates{$thetag}) { $ins{$_} = 'true'; }
    }
    $ins{$in} = 'true';
    $instates{$thetag} = join(',',keys %ins);
    $exittrans{$thetag} .= ($exittrans{$thetag}?',':'') . "$in=>$out" if $in ne $out;
    return undef;

  }
  elsif ( m/^((.|\n)+)\?\s*$/o ) { # re ?

    $emptytrans{$in} .= ($emptytrans{$in}?',':'') . $out unless $in eq $out;
    analysechildren($tag,$1,$in,$out);
    return 'true';

  }
  elsif ( m/^((.|\n)+)\+\s*$/o ) { # re +

    my $re = $1;
    my $s1 = "S_$ctag{$tag}_" . (++$statecounter);
    my $s2 = "S_$ctag{$tag}_" . (++$statecounter);
    $states{$tag} .= ",$s1,$s2";
    $emptytrans{$in} .= ($emptytrans{$in}?',':'') . $s1;
    $emptytrans{$s2} = "$s1,$out";
    return analysechildren($tag,$re,$s1,$s2);

  }
  elsif ( m/^((.|\n)+)\*\s*$/o ) { # re *

    return analysechildren($tag,"$1+?",$in,$out);

  }

  elsif ( m/^\s*\(\s*((.|\n)+)\s*\)\s*$/xo ) { # choice or seq

    local $_;
    my $cp;
    ($cp,$_) = extractcp($1);

    if ( m/^\s*$/ ) { # () with single member.

      return analysechildren($tag,$cp,$in,$out);

    }
    elsif ( m/^\s*([|,])\s*/m ) {
      my $type = "[$1]";
      my $maybeempty = ($type eq '[,]');
      my $state = $in;

      while ( m/^\s*$type\s*/ ) {
	$_ = $'; #'

	if ($type eq '[|]') { # $cp is choice
	  $maybeempty = 'true' if analysechildren($tag,$cp,$in,$out);
	}
	else { # $cp is seq component
	  my $oldstate = $state;
	  $state = "S_$ctag{$tag}_" . (++$statecounter);
	  $states{$tag} .= ",$state";
	  $maybeempty = undef unless analysechildren($tag,$cp,$oldstate,$state);
	}
	($cp,$_) = extractcp($_);
      }

      # Last cp needs special treatment in sequence.
      if ($type eq '[|]') { # $cp is choice
        $maybeempty = 'true' if analysechildren($tag,$cp,$in,$out);
      }
      else { # $cp is seq component
	$maybeempty = undef unless analysechildren($tag,$cp,$state,$out);
      }

      $emptytrans{$in} .= ($emptytrans{$in}?',':'') . $out
	if $maybeempty and $in ne $out;
      return $maybeempty unless $_;
    }
  }
  die place()."DTD element `$tag' has nonsense fragment `$_'.\n";
}



# OPTIONS PROCESSING (explained in manual).


# Parse options.
$Use = "Usage: flexml [-ASHDvdqnLXV] [-s skel] [-T actbin] [--sysid sysid] "
  . "[-p pubid] [-u uri] [-i init_header]\n"
  . "       [-b stack_increment] [-r roottags] [-a actions] [-P prefix] name[.dtd]";

sub show_version {

    exit 0;
}
    
Getopt::Long::Configure ("bundling");
GetOptions(
    # Debugging and verbosity
    "debug|d" => \$debug,
    "verbose|v" => \$verbose,
    "quiet|q" => \$quiet_parser,
    
    # Version!
    "version|V" => sub { print "FleXML version FLEXMLVERSION.\n"; exit 0; },

    # dry-run ?
    "dry-run|n" => \$dryrun,

    # Line numbers?
    "lineno|L" => \$lineno,
    
    # Exit without fail message?
    "nofail|X" => \$nofail,

    # Specific root tags?
    "root-tags|r=s" => sub {
	for (split ',',$_[1]) { $roottags{$_} = 'true'; }
    },

    # Specific stack size?
    "stack-increment|b=s" => \$stacksize,
    
    # Specific tagprefix?
    "tag-prefix|P=s" => sub { $tagprefix = $_[1]."_" },
    
    # Specific actbin? (internal use)
    "act-bin|T=s" => \$actbin,
    
    # Set skeleton scanner file name and check it is readable (if needed).
    "skel|s=s" => sub {
	$SKELETON = $_[1];
	die "$0: No skeleton file $SKELETON.\n" if not -r $SKELETON and $_[1];
    },
    
    # Set document type URI and PUBID.
    "uri|u=s" => \$uri,
    "pubid|p=s" => \$pubid,
    "sysid=s" => \$sysid,

    # name of header file to be included in initial section of generated .l file
    "init_header|i=s" => \$init_header,

    # What to generate
    "header|H:s" => sub { $header = $_[1] || 'true' },
    "dummy|D:s" => sub { $dummy = $_[1] || 'true' },
    "stand-alone|A" => \$standalone,
    "scanner|S:s" => sub { $scanner = $_[1] || 'true' },
    "actions|a=s" => \$actions
    );

print "FleXML version FLEXMLVERSION.\n" if $verbose;

# Set DTD file name...and extract prefix for later
my $prefix = $ARGV[0];
if (defined $prefix and $#ARGV == 0) {
  $prefix =~ s/\.dtd$//;
  $dtd = "$prefix.dtd";		# Require .dtd extension on DTD
  geturl($dtd);			# Read the DTD
  $prefix =~ s|^([^:/]*[:/])*||;
  $cdtd = variablify($prefix);
}
else {
  die "$Use\n";
}  

# Selection options: If none of -SHDA specified then default to -SH.
# Furthermore -a implies -D.
$scanner = $header = 'true' unless ($scanner or $header or $dummy or $standalone);
$dummy ||= $actions unless $standalone;

# Set default (DTD-based) output file names.
$SCANNER =     (!defined($scanner)) || $scanner eq 'true' ? "$prefix.l"       : $scanner;
$HEADER =      (!defined($header))  || $header eq 'true'  ? "$prefix.h"       : $header;
$APPLICATION = (!defined($dummy))   || $dummy eq 'true'   ? "$prefix-dummy.c" : $dummy;

# Set actions=based output file names, if any.
if ($ACTIONS = $actions) {
  $actions =~ s/\.[a-z]+$//;
  $APPLICATION = "$actions.c";
}

# Stand-alone applications...
if ($standalone) {
  die "$0: -A conflicts with -SHD.\n" if ($scanner or $header or $dummy);
  $SCANNER = $APPLICATION;
  $SCANNER =~ s/\.c$/.l/;
}

# Dry-run?
if ($dryrun) {
  $standalone = $scanner = $header = $dummy = undef;
}


# PARSE DTD.


print STDOUT "Processing DTD in $dtd.\n" if $verbose;

$_ = '';			# Current entry

while (@inputs) {		# While there are lines...

  my $orig = "$_";		# current source line(s)

  # Skip spaces and complete comments (but save as source).
  do {
    # Skip blank lines.
    $_ = nextline() while @inputs and m/^\s*$/;

    # If we're looking at a parameter or external entity then expand it.
    if ( m/^\s*%($Name);/ ) {
      my $ent = $1;
      if ($parameter{$ent}) {
        expandparametersat('^');
      }
      elsif ($external{$ent}) {
        $_ = $'; #'
        geturl($external{$ent});
      }
      else {
        die "Unknown entity `%$ent;'\n";
      }
    }

    # Skip (but save) comments.
    while ( m/^\s*<!--/ ) {
      until (m/-->/ or not @inputs) { $_ .= "\n" . nextline(); }
      # Extract first DTD version number...
      if ( not $dtdrevision and /\$(Id|Header|Revision): [^\$]*\$/ ) {
	$dtdrevision = "$&";
	$dtdrevision =~ s/\s*\$\s*//go;
      }
      # Remove the comment to read on to next nonblank (but save as
      # source). 
      $orig .= ($orig?"\n":"").$1 if s/^\s*(<!--([^-]|-[^-]|--[^>])*-->)\s*//;
    }
    s/^\s*//;
  } until $_ or not @inputs;

  # If we're looking at a parameter or external entity then expand and retry.
  if ( m/^\s*%($Name);/ ) {
    my $ent = $1;
    if ($parameter{$ent}) {
      expandparametersat('^');
    }
    elsif ($external{$ent}) {
      $_ = $'; #'
      geturl($external{$ent});
      next;
    }
    else {
      die "Unknown entity `\%$ent;'\n";
    }
  }

  die place()."Nonsense `$_'.\n" if /^[^<]/ or /^<[^!]/;

  # Read on until a full DTD <!...> or <?...?> entry is available.
  until (m/^\s*<![^>]*>/o or m/^\s*<[?]([^?]|[?][^>])*[?]>/o or not @inputs) {
    my $line = nextline();
    $orig .= ($orig?"\n":"") . $line;
    $_ .= "\n" . $line;
  }

  unless ( m/^\s*<![^>]*>/o or m/^\s*<[?]([^?]|[?][^>])*[?]>/o ) {
    last if not @inputs;
    die place()."Could not find end of declaration.\n";
  }

  # Clean out in $orig.
  $orig =~ s/\n+/\n/g;
  $orig =~ s/^\n*//g;
  $orig =~ s/\n*$//g;

  print STDOUT " [$_]\n" if $debug;

  # - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - 
  # Processing instruction.
  if ( m/^\s*<[?]([^?]|[?][^>])*[?]>\s*/o ) {
    print STDERR place()."Warning: ignoring processing instruction $&.\n";
    $_ = $'; #'
  }

  # - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - 
  # Parse element declarations.
  elsif ( m/^<!ELEMENT\s+($Name)\s+([^>]*)>\s*/xo ) {

    my ( $tag, $token_source ) = ( $1, $2 );

    # strip off the matched code from the beginning of $_
    $_ = $'; #'

    # place the newly found tag into the list of tags @tags
    die place()."Repeated element $tag.\n" if exists $source{$tag};

    # ????? - most of the time $orig is undef
    $source{$tag} = "$orig";

    push @tags, $tag;

    # Create C-friendly tag names.
    $ctag{$tag} = variablify($tag) unless $ctag{$tag};
    my $c = $ctag{$tag};

    # start looking at the token_source ($2)
    local $_ = $token_source;
    expandparametersat(''); s/^\s+//;

    # All elements should be followed by nothing when at the root.
    # IF there is a list of roottags ($0 -r ..,..), then only add
    # the exittrans if it is in the list
    $exittrans{$tag} .= ($exittrans{$tag}?',':'') . "ROOT_${tagprefix}$c=>EPILOG"
      if not %roottags or $roottags{$tag};

    # Handle element declaration.
    if ( m/^EMPTY\s*$/o ) {
      $empty{$tag} = 'true';
      $properempty{$tag} = 'true';
      $states{$tag} = "E_$c";
      $startstate{$tag} = "E_$c";
      $endstates{$tag} = "E_$c";
    }
    elsif ( m/^ANY\s*$/o ) {
      $any{$tag} = 'true';
      $mixed{$tag} = 'true';
      $empty{$tag} = 'true';
      $states{$tag} = "IN_$c";
      $startstate{$tag} = "IN_$c";
      $endstates{$tag} = "IN_$c";
    }
    elsif ( m/^\(\s*\#PCDATA\s*\)\s*$/o
	    or m/^\(\s*\#PCDATA\s*((\|\s*$Name\s*)*)\)\*\s*$/xo ) {
      $mixed{$tag} = 'true';
      $empty{$tag} = 'true';
      if ($1) {
	my $desc = $1;
	$desc =~ s/^\s*\|\s*//o;
	for (split /\s*\|\s*/,$desc) {
	  $instates{$_} .= ($instates{$_}?',':'') . "IN_$c";
	  $inmixed{$_} = 'true';
	}
      }
      $states{$tag} = "IN_$c";
      $startstate{$tag} = "IN_$c";
      $endstates{$tag} = "IN_$c";
    }
    else {
      $children{$tag} = 'true';
      $statecounter = 0;
      $states{$tag} = "S_$c";
      $startstate{$tag} = "S_$c";
      $empty{$tag} = 'true' if analysechildren($tag,$_,"S_$c","E_$c");
      $states{$tag} .= ",E_$c";
      $endstates{$tag} = "E_$c";
    }
  }

  # - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - 
  # Parse attribute declarations.
  elsif ( m/^<!ATTLIST\s+($Name)\s+([^>]*)>\s*/o ) {

    $_ = $'; #'
    {
      my $tag = $1;
      local $_ = $2;

      expandparametersat(''); s/^\s+//;

      # Repeat while there are attribute declarations.
      while ( s/^($Name)\s+([A-Z]+|\(\s*$Nmtoken\s*(?:\|\s*$Nmtoken\s*)*\))
		(?:\s+(\#IMPLIED|\#REQUIRED|(?:\#FIXED\s+)?$Literal))?\s*//xo ) {

	my ($attribute,$type,$default) = ($1,$2,$3);

	if ($atttype{"$tag/$attribute"}) {
	  print place()."Warning: Redeclaration of element $tag attribute $attribute ignored.\n";
	}
	else {
	  if ($orig) { # to only print the source once once
	    $source{"$tag/$attribute"} = "$orig";
	    $orig = '';
	  }

	  $ctag{$tag} = variablify($tag) unless $ctag{$tag};
	  $catt{$attribute} = variablify($attribute) unless $catt{$attribute};

	  # Add atribute to the appropriate lists.
	  $attlist{$tag} .= ($attlist{$tag}?',':'') . "$attribute";
	  if ($withattr{$attribute}) {
	    $withattr{$attribute} .= ",$tag"; 
	  }
	  else {
	    push @attributes, $attribute;
	    $withattr{$attribute} = "$tag"; 
	  }

	  # Analyse default value.
	  if (defined $default) {
	    if ($default eq '#REQUIRED') {
	      $required{"$tag/$attribute"} = 'true';
	      $default = undef;
	    }
	    elsif ($default eq '#IMPLIED') {
	      $default = undef;
	    }
	    else {
	      $fixed{"$tag/$attribute"} = 'true' if $default =~ s/\#FIXED\s+//o;
	      $default =~ s/^'([^'']*)'$/$1/o unless $default =~ s/^"([^""]*)"$/$1/o;
	    }
	  }

	  # Store attribute default string and type.
	  $attdef{"$tag/$attribute"} = $default if $default;
	  $atttype{"$tag/$attribute"} = $type;

	  # Handle enumeration types...
	  if ( $type =~ m/^\(((.|\n)*)\)$/x ) {
	    local $_ = $1;
	    s/\s+//go;
	    s/\|/,/go;
	    $enumtype{"$tag/$attribute"} = "$_";
	    s/$Nmtoken/ "A_${tagprefix}$ctag{$tag}_$catt{$attribute}_" . variablify($&) /xge;
	    my $undefined = "AU_${tagprefix}$ctag{$tag}_$catt{$attribute}";
	    s/^/enum \{ $undefined, /o;
	    s/$/ \}/o;
	    $typeof{"$tag/$attribute"} = "$_";
	    if ($default) {
	      $initof{"$tag/$attribute"} = "A_${tagprefix}$ctag{$tag}_$catt{$attribute}_"
					 . variablify($default);
	    }
	    else {
	      $initof{"$tag/$attribute"} = "$undefined";
	    }
	  }
	  # ...and string/token types.
	  else {
	    $typeof{"$tag/$attribute"} = 'int';
	    if ($default) {
	      $initof{"$tag/$attribute"} = add_def_att($default);
	    }
	    else {
	      $initof{"$tag/$attribute"} = '0';
	    }

	    # Special treatment of token types.
	    if ( $type eq 'ID' or $type eq 'IDREF' ) {
	      $literaltype{"$tag/$attribute"} = '{Name}';
	      print STDERR place()."Warning: cannot validate attribute type `$type' (yet).\n";
	    }
	    elsif ( $type eq 'IDREFS' ) {
	      $literaltype{"$tag/$attribute"} = '{Names}';
	      print STDERR place()."Warning: cannot validate attribute type `$type' (yet).\n";
	    }
	    elsif ( $type eq 'NMTOKEN' ) {
	      $literaltype{"$tag/$attribute"} = '{Nmtoken}';
	    }
	    elsif ( $type eq 'NMTOKENS' ) {
	      $literaltype{"$tag/$attribute"} = '{Nmtokens}';
	    }
	    elsif ( $type eq 'ENTITY' ) {
	      #die place()."ENTITY attribute type unimplemented.\n";
	      $literaltype{"$tag/$attribute"} = '{Name}';
	      print STDERR place()."Warning: cannote validate attribute type `$type' (yet).\n";
	    }
	    elsif ( $type eq 'ENTITIES' ) {
	      #die place()."ENTITIES attribute type unimplemented.\n";
	      $literaltype{"$tag/$attribute"} = '{Names}';
	      print STDERR place()."Warning: cannot validate attribute type `$type' (yet).\n";

	    }
	    elsif ( $type ne 'CDATA' ) {
	      die place()."Unknown AttType `$type'.\n";
	    }

	  }
	}

	expandparametersat('^'); s/^\s+//; # to expand next set of declarations...
      }

      die place()."Nonsense ($_) in attribute list.\n" if $_;
    }

    $orig = '';			# in case there were no attributes...
  } # end of a <!ATTLIST> block

  # Parse internal parameter entity declaration.
  elsif ( m/^\s*<!ENTITY\s+%\s+($Name)\s+'([^'']*)'\s*>\s*/xo
	  or m/^\s*<!ENTITY\s+%\s+($Name)\s+"([^""]*)"\s*>\s*/xo ) {

    $_ = $'; #'
    $source{"%$1;"} = "$orig"; $orig = ''; # cycle

    my $name = $1;
    local $_ = $2;

    die "Entity `%$name;' doubly defined.\n" if $parameter{$name} or $external{$name};
    
    expandparametersat(''); s/^\s+//; s/\s+$//;
    s/\&\#([0-9]+|x[0-9a-fA-F]+);/
      (substr($1,0,1) eq 'x' ? chr(hex(substr($1,1))) : chr($1)) /ge;
    $parameter{$name} = $_;
  }

  # Parse external parameter entity declaration.
  elsif ( m/^<!ENTITY\s+%\s+($Name)\s+SYSTEM\s+'([^'']*)'\s*>\s*/xo
	  or m/^<!ENTITY\s+%\s+($Name)\s+SYSTEM\s+"([^""]*)"\s*>\s*/xo
	  or m/^<!ENTITY\s+%\s+($Name)\s+PUBLIC\s+$Literal\s+'([^'']*)'\s*>\s*/xo
	  or m/^<!ENTITY\s+%\s+($Name)\s+PUBLIC\s+$Literal\s+"([^""]*)"\s*>\s*/xo ) {

    $_ = $'; #'
    $source{"%$1;"} = "$orig"; $orig = ''; # cycle

    my $name = $1;
    die "Entity `%$name;' doubly defined.\n" if $parameter{$name} or $external{$name};
    $external{$name} = $2;
  }

  # Parse internal general entity declarations.
  elsif ( /^<!ENTITY\s+($Name)\s+['"]([^''""]*)["']\s*>\s*/xo ) {

    $_ = $'; #'
    $source{"&$1;"} = "$orig"; $orig = ''; # cycle

    my $name = $1;
    local $_ = $2;

    die "Entity `&$name;' doubly defined.\n" if $entity{$name};
    s/\&\#([0-9]+|x[0-9a-fA-F]+);/
      (substr($1,0,1) eq 'x' ? chr(hex(substr($1,1))) : chr($1)) /ge;
    $entity{$name} = cquote($_);
  }

  # Unrecognised declaration.
  else {
    die place()."Unrecognized declaration.\n";
  }

}

# Post-process DTD.

print STDOUT "Post-processing DTD.\n" if $verbose;

# Add transitive empty transitions until none can be found.
{ my $changed = 'true';
  while ($changed) {
    $changed = undef;
    for my $from (keys %emptytrans) {
      my %tos = (); for (split /,/,$emptytrans{$from}) { $tos{$_} = 'true'; }
      for my $to (keys %tos) {
	if (exists $emptytrans{$to}) {
	  for my $next (split /,/,$emptytrans{$to}) {
	    if (not $tos{$next}) {
	      $changed = $tos{$next} = 'true';
	    }
	  }
	}
      }
      $emptytrans{$from} = join ',',keys %tos;
    }
  }
}

# Complete all states with their `empty' equivalents.
for my $tag (@tags) {

  # Complete and prune instates and endstates...
  my %ins = ();
  if (exists $instates{$tag}) {
    for (split ',',$instates{$tag}) { $ins{$_} = 'true'; }
  }
  my %ens = ();
  if (exists $endstates{$tag}) {
    for (split ',',$endstates{$tag}) { $ens{$_} = 'true'; }
  }

  # ...and exit transitions...
  my %exits = ();
  if (exists $exittrans{$tag}) {
    for (split ',',$exittrans{$tag}) { m/^($Name)=>($Name)$/o; $exits{$1} = $2; }
  }

  # Encode ANY as Mixed contents with all tags permitted.
  for (keys %any) { $ins{"IN_$_"} = 'true'; }

  # For each empty transition A->B add A where B occurs.
  for my $from (keys %emptytrans) {
    for my $to (split /,/,$emptytrans{$from}) {
      $ins{$from} = 'true' if $ins{$to};
      $ens{$from} = 'true' if $ens{$to};
      $exits{$from} = $exits{$to} if $exits{$to};
    }
  }

  # Completion done...now store'em right back.
  $instates{$tag} = join ',', keys %ins if %ins;
  $endstates{$tag} = join ',', keys %ens if %ens;
  $exittrans{$tag} = join ',', map "$_=>$exits{$_}", keys %exits if %exits;
}

if (not %roottags) {
  for (@tags) { $roottags{$_} = 'true'; }
}

# Handling prefix
if(length($tagprefix)) {
    my($h,$k);
    my(@hashlist) = (\%states,\%emptytrans,\%instates,\%startstate,
		     \%endstates,\%exittrans);

    foreach $h (@hashlist) {
	foreach $k (keys (%$h)) {
	    $$h{$k} =~ s/^E_/E_${tagprefix}/g;
	    $$h{$k} =~ s/,E_/,E_${tagprefix}/g;
	    $$h{$k} =~ s/>E_/>E_${tagprefix}/g;
	    $$h{$k} =~ s/^S_/S_${tagprefix}/g;
	    $$h{$k} =~ s/,S_/,S_${tagprefix}/g;
	    $$h{$k} =~ s/>S_/>S_${tagprefix}/g;
	}
    }
    my %tmp = ();
    foreach $k (keys %allstates) {
	$k =~ s/^E_/E_${tagprefix}/;
	$k =~ s/^S_/S_${tagprefix}/;
	$tmp{$k} = 1;
    }
    %allstates = %tmp;
}

# Debugging: show DTD representation.

if ($debug) {

  print STDOUT "DTD debug output:\n" if $verbose;

  sub printhash {
    my ($name) = @_;

    my ($k,$v);
    my $out = '';

    while ( ($k, $v) = each(%$name) ) {
	$out .= "\n    $k => '" . ($v || "undef")."'"; 
    }

    return $out;
  }

  # display the options we got
  print "debug=".($debug||'undef')."\n";
  print "verbose=".($verbose||'undef')."\n";
  print "quiet=".($quiet_parser||'undef')."\n";

  print "dry-run=".($dryrun||'undef')."\n";
  print "lineno=".($lineno||'undef')."\n";

  print "nofail=".($nofail||'undef')."\n";

  print "stack-increment=".($stacksize||'undef')."\n";
  print "tag-prefix=".($tagprefix||'undef')."\n";

  print "act-bin=".($actbin||'undef')."\n";

  print "skel=".($SKELETON||'undef')."\n";

  print "uri=".($uri||'undef')."\n";
  print "pubid=".($pubid||'undef')."\n\n";
  print "sysid=".($sysid||'undef')."\n\n";

  print "header=".($header||'undef')."\n";
  print "dummy=".($dummy||'undef')."\n";
  print "stand-alone=".($standalone||'undef')."\n";
  print "scanner=".($scanner||'undef')."\n";
  print "actions=".($actions||'undef')."\n\n";

  print '%source = (' . printhash(\%source) . ")\n";
  print "\n";

  print '@tags = (' . join(',',@tags) . ")\n";
  print '%ctag = (' . printhash(\%ctag) . ")\n";

  print '%states = (' . printhash(\%states) . ")\n";
  print '%instates = (' . printhash(\%instates) . ")\n";
  print '%endstates = (' . printhash(\%endstates) . ")\n";

  print '%emptytrans = (' . printhash(\%emptytrans) . ")\n";
  print '%exittrans = (' . printhash(\%exittrans) . ")\n";
  print '%roottags = (' . printhash(\%roottags) . ")\n";

  print '%empty = (' . printhash(\%empty) . ")\n";
  print '%properempty = (' . printhash(\%properempty) . ")\n";
  print '%any = (' . printhash(\%any) . ")\n";
  print '%mixed = (' . printhash(\%mixed) . ")\n";
  print '%children = (' . printhash(\%children) . ")\n";
  print '%inmixed = (' . printhash(\%inmixed) . ")\n";
  print "\n";

  print '@attributes = (' . join(',',@attributes) . ")\n";
  print '%catt = (' . printhash(\%catt) . ")\n";

  print '%atttype = (' . printhash(\%atttype) . ")\n";
  print '%enumtype = (' . printhash(\%enumtype) . ")\n";
  print '%literaltype = (' . printhash(\%literaltype) . ")\n";
  print '%typeof = (' . printhash(\%typeof) . ")\n";

  print '%attdef = (' . printhash(\%attdef) . ")\n";
  print '%required = (' . printhash(\%required) . ")\n";
  print '%fixed = (' . printhash(\%fixed) . ")\n";
  print '%initof = (' . printhash(\%initof) . ")\n";

  print '%attlist = (' . printhash(\%attlist) . ")\n";
  print '%withattr = (' . printhash(\%withattr) . ")\n";
  print "\n";

  print '%entity = (' . printhash(\%entity) . ")\n";
  print '%parameter = (' . printhash(\%parameter) . ")\n";
  print '%external = (' . printhash(\%external) . ")\n";
}


# WRITE API HEADER (if requested).

if ($header) {

  print STDOUT "Generating XML processor header in `$HEADER'.\n" if $verbose;

  open HEADER, "+>$HEADER" || die "$0: cannot write $HEADER: $!\n";
  select HEADER;

  # Identification and license.
  print "/* XML processor/application API for $dtd"
      . ($dtdrevision ? " ($dtdrevision)" : "") . ".\n";
  print " * Generated " . `date +'%Y/%m/%d %T.'`;
  print " *\n";
  redistribute(" *");
  print " */\n";
  print "\n";

  # Output the declarations safeguarded againts repeated loading.
  print "#ifndef _FLEXML_${cdtd}_H\n";
  print "#define _FLEXML_${cdtd}_H\n";
  print "\n";
  api_functions('extern ',';');
  print "\n";
  api_types();
  print "\n";
  api_data('extern ');
  print "\n";

  print "/* XML application utilities. */\n";
  print "extern int ${tagprefix}element_context(int);\n";
  print "\n";
  print "/* XML processor entry point. */\n";
  print "extern int yylex(void);\n";
  print "\n";
  
  print "/* Flexml error handling function (useful only when -q flag passed to flexml) */\n";
  print "const char * ${tagprefix}parse_err_msg(void);\n";
    
  print "#endif\n";

  close HEADER || die "$0: cannot read $HEADER: $!\n"; 
}



# WRITE XML PROCESSOR (if requested).


if ($scanner or $standalone) {

  print STDOUT "Writing XML processor"
             . ($actions || $standalone ? " and application" : "")
             . " onto `$SCANNER'.\n" if $verbose;

  open SCANNER, "+>$SCANNER"|| die "$0: cannot write $SCANNER: $!\n";
  select SCANNER;

  open (SKELETON) || die "$0: cannot read $SKELETON: $!\n";

  # Identification and license.
  print "/* Validating XML processor for $dtd"
      . ($dtdrevision ? " ($dtdrevision)" : "") . ".\n";
  print " * Generated " . `date +'%Y/%m/%d %T.'`;
  print " *\n";
  redistribute(" *");
  print " */\n";
  print "\n";

  # Skip initial comment.
  while (<SKELETON>) { last if m/^\%\{/; }
  print;

  # Copy body of skeleton scanner with substitutions...
  while (<SKELETON>) {

    if ( /^FLEXML_VERSION$/ ) {

      print "const char ${tagprefix}flexml_version[] = \"FLEXMLVERSION\";\n";

      print "const char rcs_${cdtd}_dtd[] =\n"
	  . " \"\$\" \"$dtdrevision \$\";\n" if $dtdrevision;

    }
    elsif ( /^FLEXML_DEFINITIONS$/ ) {

      print "#define DEBUG\n" if $debug;
      print "#define FLEXML_yylineno\n" if $lineno;
      print "#define FLEXML_NOFAIL\n" if $nofail;
      print "#define FLEXML_quiet_parser\n" if $quiet_parser;
      print "#ifndef FLEXML_BUFFERSTACKSIZE\n";
      print "#define FLEXML_BUFFERSTACKSIZE $stacksize\n";
      print "#endif\n";
      print "#define FLEXML_NEED_BUFFERLIT\n"
	if (scalar(%literaltype) or ($#default_attributes >= 0));
      print "\n";

      if ($standalone) {
	api_functions('static ',';');
	print "\n";
	api_types();
	print "\n";
	api_data('static ');
      }
      else {
	print "/* XML processor api. */\n";
	print "#include \"$HEADER\"\n\n"
	    if ($header);
	api_data('');
      }

    }
    elsif ( /^FLEXML_INCLUDE_INIT_HEADER$/ ) {
	if ($init_header) {
	    print "/* User-supplied header */\n";
	    print "#include \"$init_header\"\n";
	}
    }

    elsif ( /^FLEXML_FLEX_OPTIONS$/ ) {

      print "%option yylineno\n" if $lineno;
      print "%option debug\n" if $debug;
      print "%option nounput\n" if not %entity;

    }
    elsif ( /^FLEXML_START_CONDITIONS$/ ) {

      for (@tags) {
	my $c = $ctag{$_};
	print "%x"
            . ($roottags{$_} ? " ROOT_${tagprefix}$c" : "")
            . " AL_${tagprefix}$c " . join(' ',split(',',$states{$_})) . "\n";
      }

    }
    elsif ( /^FLEXML_EXTRA_DEFINITIONS$/ ) {

     print "%{\n";
     print "/* State names. */\n";
     print "const char* *${tagprefix}statenames=NULL;\n";
     print "%}\n";

    }
    elsif ( /^FLEXML_EXTRA_DEFINITIONS_INIT$/ ) {

      my ($state, $tag);

      print "  /* FleXML_init */\n";
      print "  bnext = inext = 1;\n";
      for my $att (@default_attributes) {
	  print "  ${tagprefix}bufferliteral('\\0', &bnext, \"$att\");\n";
      }
      print "  if(!${tagprefix}statenames) {${tagprefix}statenames= (const char **)calloc(IMPOSSIBLE,sizeof(char*));\n";
      for ('PROLOG','DOCTYPE','EPILOG','INCOMMENT','INPI','VALUE1','VALUE2','CDATA') {
	print "  ${tagprefix}statenames[$_] = NULL;\n";
      }
      for my $tag (@tags) {
	my $c = $ctag{$tag};
	print "  ${tagprefix}statenames[ROOT_${tagprefix}$c] = NULL;\n" if $roottags{$tag};
	print "  ${tagprefix}statenames[AL_${tagprefix}$c] = NULL;\n";
	for (split ',',$states{$tag}) {
	  print "  ${tagprefix}statenames[$_] = \"$tag\";\n";
	}
      }
      print "  }\n";
    }
    elsif ( /^FLEXML_DOCTYPES$/ ) {

      $sysid = $sysid ?          "(\"'$sysid'\"|\"\\\"$sysid\\\"\")"
	              : ( $uri ? "(\"'$uri'\"|\"\\\"$uri\\\"\")"
			       : "(\"'$dtd'\"|\"\\\"$dtd\\\"\")" );

      for (keys %roottags) {
	my $c = $ctag{$_};
	print " \"<!DOCTYPE\"{S}\"$_\"{S}"
	    . "SYSTEM{S}" . $sysid . "{s}\">\" SET(ROOT_${tagprefix}$c);\n";
	if ($pubid) {
	  print " \"<!DOCTYPE\"{S}\"$_\"{S}"
	      . "PUBLIC{S}(\"'$pubid'\"|\"\\\"$pubid\\\"\"){S}"
	      . $sysid . "{s}\">\" SET(ROOT_${tagprefix}$c);\n";
	}
      }	  

    }
    elsif ( /^FLEXML_RULES$/ ) {

      # Dump all parameter entity declarations.
      for (keys %parameter) { printsource($_); }

      # Dump all start and empty tag recognition rules.
      for my $tag (@tags) {

	my $myctag = $ctag{$tag};
	my @myattributes = (exists $attlist{$tag} ? split /,/,"$attlist{$tag}" : ());
	my ($intag, $attribute);

	# Tag's source element and attribute declarations.
	printsource($tag);
	for my $attribute (@myattributes) {
	  printsource("$tag/$attribute");
	}

	# Build element exit transition command.
	my $exitswitch = "";
	if (exists $exittrans{$tag}) {
	  $exitswitch .= "  switch (YY_START) {\n";
	  my %casesto = ();
	  for (split /,/,$exittrans{$tag}) {
	    if (m/^($Name)=>($Name)$/o) {
	      $casesto{$2} .= "case $1: ";
	    }
	  }
	  for (keys %casesto) {
	    $exitswitch .= "   $casesto{$_}SET($_); break;\n" 
	  }
	  $exitswitch .= "  }\n";
	}

	# Misplaced start or empty tag
	unless ($nofail) {
	    print "\n";
	    my %ins = ();
	    foreach (keys %allstates) {
		$ins{$_} = 'false';
	    }
	    if (exists $instates{$tag}) {
		for (split /,/,$instates{$tag}) { $ins{$_} = 'true'; }
	    }
	    my $str = '<' . join(',', grep {$ins{$_} eq 'false'} keys %ins);	    
	    if ($str ne '<') {
		print "$str>\"<$tag\"{s} FAIL(\"Starting tag <$tag> is not allowed here.\");\n";
	    }
	}
	
	  
	# Start or empty tag: initialise attribute list.
	print "\n";
	if ($roottags{$tag}) {
	  print "<ROOT_${tagprefix}$myctag" . ($instates{$tag} ? ",$instates{$tag}" : "");
	}
	else {
	  print "<$instates{$tag}";
	}
# SHACK
#	print ">{ \n" .
#              "\"<$tag\"{s} {\n";
	print ">\"<$tag\"{s} {\n";

	for my $attribute (@myattributes) {
	  print "  AX_${tagprefix}${myctag}_$catt{$attribute} = " . $initof{"$tag/$attribute"} . ";\n";
	  print "  ${tagprefix}${myctag}_$catt{$attribute}_isset = 0;\n";
	}
	print "  ENTER(AL_${tagprefix}$myctag); pushbuffer(0);\n";
	print "  }\n";

#	print " .       FAIL(\"Unexpected character `%c': `<$tag' expected.\",yytext[0]);\n";
#	print " <<EOF>> FAIL(\"Premature EOF: `<$tag' expected.\");\n";
#	  #unless $mixed{$tag} or $nofail;
#	print "}\n";

	# Attribute list (of start or empty tag):
	print "\n";
	print "<AL_${tagprefix}$myctag>{\n";

	for my $attribute (@myattributes) {
	  my $type; # set by conditions
	  
	  if ($type = $enumtype{"$tag/$attribute"}) {

	    # - fixed enumeration attribute: generate one rule,
	    if ($fixed{"$tag/$attribute"}) {
		print " \"$attribute\"{Eq}\"'" . $attdef{"$tag/$attribute"} . "'\""
		    . " |\n"
		    . " \"$attribute\"{Eq}\"\\\"" . $attdef{"$tag/$attribute"} . "\\\"\""
		    . " A_${tagprefix}${myctag}_$catt{$attribute}"
		    . " = " . $initof{"$tag/$attribute"} . ";\n";
	    }
	    else {
	      # - (non-fixed) enumeration attribute: generate a rule per value,
	      for my $alternative (split /,/,$type) {
		print " \"$attribute\"{Eq}\"'$alternative'\""
		    . " |\n"
		    . " \"$attribute\"{Eq}\"\\\"$alternative\\\"\""
		    . " A_${tagprefix}${myctag}_$catt{$attribute}"
		    . " = A_${tagprefix}${myctag}_$catt{$attribute}_" . variablify($alternative) . ";\n";
	      }
	    }
	  }
	  elsif ($fixed{"$tag/$attribute"}) {

	    # - fixed (non-enumeration) attribute: generate one rule per literal form,

	    print " \"$attribute\"{Eq}\"'" . $attdef{"$tag/$attribute"} . "'\""
	        . " |\n"
		. " \"$attribute\"{Eq}\"\\\"" . $attdef{"$tag/$attribute"} . "\\\"\""
		. " AX_${tagprefix}${myctag}_$catt{$attribute}"
		. " = " . $initof{"$tag/$attribute"} . ";\n";

	  }
	  elsif ($type = $literaltype{"$tag/$attribute"}) {

	    # - (non-fixed) literal-type attribute: scan literal string directly, or
	    print " \"$attribute\"{Eq}\'$type\' BUFFERLITERAL('\\\'',AX_${tagprefix}${myctag}_$catt{$attribute});\n";

	    print " \"$attribute\"{Eq}\\\"$type\\\" BUFFERLITERAL('\"',AX_${tagprefix}${myctag}_$catt{$attribute});\n";

	  }
	  else {

	    # - (non-fixed non-literal) attribute: scan string with entity expansion.
	    print " \"$attribute\"{Eq}\\' if (${tagprefix}${myctag}_$catt{$attribute}_isset != 0) {FAIL(\"Multiple definition of attribute $attribute in <${tagprefix}${myctag}>\");} ${tagprefix}${myctag}_$catt{$attribute}_isset = 1; ENTER(VALUE1); BUFFERSET(AX_${tagprefix}${myctag}_$catt{$attribute});\n";
	    print " \"$attribute\"{Eq}\\\" if (${tagprefix}${myctag}_$catt{$attribute}_isset != 0) {FAIL(\"Multiple definition of attribute $attribute in <${tagprefix}${myctag}>\");}  ${tagprefix}${myctag}_$catt{$attribute}_isset = 1; ENTER(VALUE2); BUFFERSET(AX_${tagprefix}${myctag}_$catt{$attribute});\n";

	  }
	  print "\n";
	}
	#
	# - the end of a start tag means to enter the contents after
	#   checking that all required attributes were set.
	print " \">\" {\n";
	for my $attribute (@myattributes) {
	  if ($required{"$tag/$attribute"}) {
	    print "  if (!AX_${tagprefix}$ctag{$tag}_" . variablify($attribute) . ")"
	        . " FAIL(\"Required attribute `$attribute' not set for `$tag' element.\");\n";
	  }
	}
	print "  LEAVE; STag_${tagprefix}$myctag();"
	    . (%inmixed ? ' pushbuffer('."${tagprefix}".'pcdata_ix);' : '')
	    . ($mixed{$tag} ? 'pushbuffer('."${tagprefix}".'pcdata_ix); BUFFERSET('."${tagprefix}".'pcdata_ix);' : "${tagprefix}".'pcdata_ix = 0'). ";"
	    . " ENTER($startstate{$tag});\n";
	print " }\n";
	#
	# - accept and handle empty tags straight away,
	if ($empty{$tag}) {
	  print " \"/>\" {\n";
	  for my $attribute (@myattributes) {
	    if ($required{"$tag/$attribute"}) {
	      print "  if (!AX_${tagprefix}$ctag{$tag}_" . variablify($attribute) . ")"
		  . " FAIL(\"Required attribute `$attribute' not set for `$tag' element.\");\n";
	    }
	  }
	  print "  LEAVE; STag_${tagprefix}$myctag();"
	      . (%inmixed ? ' pushbuffer('."${tagprefix}".'pcdata_ix);' : '')
	      . " ${tagprefix}".'pcdata_ix = 0;'
	      . " ETag_${tagprefix}$myctag();"
	      . (%inmixed ? " ${tagprefix}".'pcdata_ix = popbuffer();' : '')
	      . " popbuffer(); /* attribute */\n";
	  #
	  print $exitswitch;
	  print " }\n";
	}
	elsif (not $nofail) {
	  print " \"/>\" FAIL(\"`$tag' element cannot be empty.\");\n";
	}
	#
	# - spaces are skipped, and
	print " .       FAIL(\"Unexpected character \`%c\' in attribute list of $tag element.\", yytext[0]);\n" unless $nofail;
	#
	# - other stuff is an error.
	print " {Name} FAIL(\"Bad attribute `%s' in `$tag' element start tag.\",yytext);\n" unless $nofail;
	print " <<EOF>> FAIL(\"EOF in attribute list of `$tag' element.\");\n" unless $nofail;
	print "}\n";

	# End tag.
	print "\n";
	print "<$endstates{$tag}>{\n";
	print " \"</$tag\"{s}\">\" {\n";
	print "  LEAVE;\n";
	print "  BUFFERDONE;\n" if $mixed{$tag};
	print "  ETag_${tagprefix}$myctag();\n";
	print "  ${tagprefix}pcdata_ix = popbuffer();\n" if $mixed{$tag};
	print "  ${tagprefix}pcdata_ix = popbuffer();\n" if %inmixed;
	print "  popbuffer(); /* attribute */\n";
	print $exitswitch;
	print " }\n";

	# Errors when expecting end tag.
	print " \"</\"{Name}{s}\">\" FAIL(\"Unexpected end-tag `%s': `</$tag>' expected.\",yytext);\n"
	  unless $nofail;
	print " .       FAIL(\"Unexpected character `%c': `</$tag>' expected.\",yytext[0]);\n"
	  unless $mixed{$tag} or $nofail;
	print " <<EOF>> FAIL(\"Premature EOF: `</$tag>' expected.\");\n" unless $nofail;
	print "}\n";

	# Errors when expecting root tag.
	if ($roottags{$tag} and $nofail) {
	  print "\n";
	  print "<ROOT_${tagprefix}$myctag>{\n";
	  print " .       FAIL(\"Unexpected character `%c': `$tag' element expected.\",yytext[0]);\n";
	  print " <<EOF>> FAIL(\"EOF in prolog.\");\n";
	  print "}\n";
	}
      }

    }
    elsif ( /FLEXML_MIXED([,>])/ ) {

      if (%mixed) {
	print  "$`" . join(',', map("IN_$ctag{$_}", keys %mixed)) . "$1$'";
      }
      else {
	print "$`IMPOSSIBLE$1$'";
      }

    }
    elsif ( /FLEXML_NON_MIXED([,>])/ ) {

      my $sep = $`;
      for (@tags) {
	print $sep . ($roottags{$_} ? "ROOT_${tagprefix}$ctag{$_}," : "")
            . "AL_${tagprefix}$ctag{$_}";
	print ",$states{$_}" if $properempty{$_} or $children{$_};
	$sep = ',';
      }
      print "$1$'";

    }
    elsif ( /FLEXML_COMMENTS([,>])/ ) {

      print "$`"
	  . join(',', map(($roottags{$_} ? "ROOT_${tagprefix}$ctag{$_}," : "")
			  . "AL_${tagprefix}$ctag{$_},$states{$_}", @tags))
	  . "$1$'";

    }
    elsif ( /^FLEXML_ENTITIES$/ ) {

      # Process general entities.
      for my $ent (keys %entity) {
	printsource("%$ent;");
	print " \"&$ent;\" ENTITYTEXT(\"" . $entity{$ent} . "\");\n";
      }

      print " /* Non-defined standard entities... */\n";
      print "\"&amp;\"  BUFFERPUTC('&');\n" unless $entity{"amp"};
      print "\"&lt;\"   BUFFERPUTC('<');\n" unless $entity{"lt"};
      print "\"&gt;\"   BUFFERPUTC('>');\n" unless $entity{"gt"};
      print "\"&apos;\" BUFFERPUTC('\\\'');\n" unless $entity{"apos"};
      print "\"&quot;\" BUFFERPUTC('\"');\n" unless $entity{"quot"};

    }
    elsif ( /^FLEXML_FINAL$/ and not $nofail ) {

      # Catch-all error cases.
      for my $tag (@tags) {
	 for (split ',',$states{$tag}) {
	   print "<$_>{\n";
	   print " .    FAIL(\"Unrecognized `%c' in $_.\",yytext[0]);\n";
	   print " [\\n] FAIL(\"Unrecognized newline in $_.\");\n";
	   print "}\n";
	 }
      }
      for ('PROLOG','DOCTYPE','EPILOG','INCOMMENT','INPI','VALUE1','VALUE2','CDATA','INITIAL','IMPOSSIBLE') {
	 print "<$_>{\n";
	 print " .   FAIL(\"Unrecognized `%c' in $_.\",yytext[0]);\n";
	 print " [\\n] FAIL(\"Unrecognized space in $_.\");\n";
	 print "}\n";
      }

    }
    elsif ( $nofail and /FAIL\(/ ) {
      #ignore
    }
    else {
      s/"\$Id/"\$" "Id/;
      s/statenames/${tagprefix}statenames/g;
      s/element_context/${tagprefix}element_context/g;
      s/parse_err_msg/${tagprefix}parse_err_msg/g;
      s/rcs_flexml_skeleton/rcs_${tagprefix}flexml_skeleton/g;
      s/bufferliteral/${tagprefix}bufferliteral/g;
      s/bufferstack/${tagprefix}bufferstack/g;
      print;
    }

  }

  close SKELETON || die "$0: Cannot close $SKELETON: $!\n";
  unless ($standalone) {
    close SCANNER || die "$0: Cannot close $SCANNER: $!\n";
  }
}



# WRITE APPLICATION.


if ($dummy) {

  print STDOUT "Writing XML"
             . ($actions ? "" : " dummy")
             . " application onto `$APPLICATION'.\n" if $verbose;

  open APPLICATION, "+>$APPLICATION" || die "$0: Cannot write $APPLICATION: $!\n";
  select APPLICATION;

  # Identification and license.
  print "/* XML application for $dtd"
      . ($dtdrevision ? " ($dtdrevision)" : "") . ".\n";
  print " * Includes actions from $ACTIONS.\n" if $ACTIONS;
  print " * Generated " . `date +'%Y/%m/%d %T.'`;
  print " *\n";
  redistribute(" *");
  print " */\n";
  print "\n";

  # Declarations.
  print "#include \"$HEADER\"\n";
  print "\n";

}

if ($dummy or $standalone) {

  # Get requested actions.
  if ($ACTIONS) {

    open ACTIONS, "$actbin $ACTIONS|" || die "$0: Cannot exec $actbin $ACTIONS: $!\n";

    my ($tag,$attribute);
    my @myattributes;
    my $lineno = 0;
    my $isstart = undef;

    while (<ACTIONS>) {
      ++$lineno;

      if ( m/^\#line ([0-9]+)/ ) {
	$lineno = $1;
      }
      elsif ( m/^void\s+STag_${tagprefix}($Name)\(void\)$/xo ) {
	$tag = $1;
	die "\"$ACTIONS\", line $lineno: Unknown element `$tag'.\n" unless $ctag{$tag};
	$startok{$tag} = 'true';
	@myattributes = (exists $withattr{$tag} ? split /,/,"$withattr{$tag}" : ());
	$isstart = 'true';
      }
      elsif ( m|^\}\s+\/\*\s+STag_${tagprefix}($Name)\s+\*\/$|xo ) {
	$tag = undef;
	@myattributes = ();
	$isstart = 'true';
      }
      elsif ( m/^void\s+ETag_${tagprefix}($Name)\(void\)$/xo ) {
	$tag = $1;
	$endok{$1} = 'true';
	$isstart = undef;
      }

      # Make function names C-friendly (idempotently!)
      s/(\s+[SE])Tag_($Name)\(/$1Tag_$ctag{$2}\(/xg;

      # Replace special annotations with C equivalents.
      if ($tag) {

	while ( s/\{($Name)\}/A_${tagprefix}$ctag{$tag}_$catt{$1}/x ) {
	  die "\"$ACTIONS\", line $lineno: Unknown attribute `$1' for <$tag>.\n"
	    if not $atttype{"$tag/$1"};
	}

	while ( s/\{[!]($Name)\}/AU_${tagprefix}$ctag{$tag}_$catt{$1}/x ) {
	  die "\"$ACTIONS\", line $lineno: Unknown attribute `$1' for <$tag>.\n"
	    if not $atttype{"$tag/$1"};
	}

	while ( s|\{($Name)=($Name)\}|
		  "A_${tagprefix}$ctag{$tag}_$catt{$1}_" . variablify($2); |xe ) {
	  my ($att,$elt) = ($1,$2);
	  die "\"$ACTIONS\", line $lineno: Unknown attribute $1 for <$tag>.\n"
	    if not $atttype{"$tag/$1"};
	  die "\"$ACTIONS\", line $lineno: Attribute $att does not have value $elt for <$tag>.\n"
	    if not $enumtype{"$tag/$att"} =~ m/\b$elt\b/ ;
	}

	while ( s|\{\#(PCDATA)\}|${tagprefix}pcdata| ) {
	  die "\"$ACTIONS\", line $lineno: {#PCDATA} only allowed in end tag.\n"
	    if $isstart;
	  die "\"$ACTIONS\", line $lineno: {#PCDATA} only permitted in end tag with Mixed contents.\n"
	    if not $mixed{$tag};
	}

	die "\"$ACTIONS\", line $lineno: Malformed annotation `$&' in <$tag> action.\n"
	  if m|\{[^;\s]+\}|o;
      }
      print STDERR "Action: $_" if $debug;
      print $_;

    }
    close ACTIONS || die "$0: Cannot close pipe to $actbin: $!\n";
    print "\n";
  }

  # Fill up with dummy declarations for the remaining functions.
  api_functions('',' {}');

}

if ($dummy) {
  close APPLICATION || die "$0: Cannot close $APPLICATION: $!\n";
}
elsif ($standalone) {
  close SCANNER || die "$0: Cannot close $SCANNER: $!\n";
}



=pod

=head1 NAME

flexml - generate validating XML processor and applications from DTD

=head1 SYNOPSIS

B<flexml>
[B<-ASHDvdnLXV>]
[B<-s>I<skel>]
[B<-p>I<pubid>]
[B<-i>I<init_header>]
[B<-u>I<uri>]
[B<-r>I<rootags>]
[B<-a>I<actions>]
I<name>[F<.dtd>]

=head1 DESCRIPTION

I<Flexml> reads I<name>F<.dtd> which must be a DTD (Document Type
Definition) describing the format of XML (Extensible Markup Language)
documents, and produces a "validating" XML I<processor> with an
interface to support XML I<application>s.  Proper applications can be
generated optionally from special "action files", either for linking
or textual combination with the processor.

The generated processor will only validate documents that conform
strictly to the DTD, I<without extending it>, more precisely we in
practice restrict XML rule [28] to

  [28r] doctypedecl ::= '<!DOCTYPE' S Name S ExternalID S? '>'

where the C<ExternalId> denotes the used DTD.  (One might say, in
fact, that I<flexml> implements "non-extensible" markup. :)

The generated processor is a I<flex>(1) scanner, by default named
I<name>F<.l> with a corresponding C header file I<name>F<.h> for
separate compilation of generated applications.  Optionally I<flexml>
takes an I<actions> file with per-element actions and produces a C
file with element functions for an XML application with entry points
called from the XML processor (it can also fold the XML application
into the XML processor to make stand-alone XML applications but this
prevents sharing of the processor between applications).

In L</OPTIONS>Z<> we list the possible options, in L</ACTION FILE
FORMAT>Z<> we explain how to write applications, in L</COMPILATION> we
explain how to compile produced processors and applications into
executables, and in L</BUGS> we list the current limitations of the
system before giving standard references.

=head1 OPTIONS

I<Flexml> takes the following options.

=over 4

=item B<--stand-alone>, B<-A> 

Generate a I<stand-alone> scanner application.  If combined with
B<-a>I<actions> then the application will be named as I<actions> with
the extension replaced by F<.l>, otherwise it will be in I<name>F<.l>.
Conflicts with B<-S>, B<-H>, and B<-D>.

=item B<--actions> I<actions>, B<-a> I<actions>

Uses the I<actions> file to produce an XML application in the file
with the same name as I<actions> after replacing the extension with
F<.c>.  If combined with B<-A> then instead the stand-alone
application will include the action functions.

=item B<--dummy> B<[>I<app_name>B<]>, B<-D> B<[>I<app_name>B<]>

Generate a dummy application with just empty functions to be called by the
XML processor. If I<app_name> is not specified on the command line, it
defaults to I<name>F<-dummy.c>.  If combined with B<-a> I<actions> then the
application will insert the specified actions and be named as I<actions>
with the extension replaced by F<.c>.  Conflicts with B<-A>; implied by
B<-a> unless either of B<-SHD> is specified.

=item B<--debug>, B<-d>

Turns on debug mode in the flex scanner and also prints out the
details of the DTD analysis performed by I<flexml>.

=item B<--header> B<[>I<header_name>B<]>, B<-H> B<[>I<header_name>B<]>

Generate the header file. If the I<header_name> is not specified on the
command line, defaults to I<name>F<.h>.  Conflicts with B<-A>; on by
default if none of B<-SHD> specified.

=item B<--lineno>, B<-L>

Makes the XML processor (as produced by I<flex>(1)) count the lines in
the input and keep it available to XML application actions in the
integer C<yylineno>.  (This is off by default as the performance
overhead is significant.)

=item B<--quiet>, B<-q>

Prevents the XML processor (as produced by I<flex>(1)) from reporting 
the error it runs into on stderr. Instead, users will have to pool for
error messages with the parse_err_msg() function.
By default, error messages are written on stderr.

=item B<--dry-run>, B<-n>

"Dry-run": do not produce any of the output files.

=item B<--pubid> I<pubid>, B<-p> I<pubid>

Sets the document type to be C<PUBLIC> with the identifier I<pubid>
instead of C<SYSTEM>, the default.

=item B<--init_header> I<init_header>, B<-i> I<init_header>

Puts a line containing C<#include "init_header"> in the C<%{...%}> section
at the top of the generated .l file.  This may be useful for making various
flex C<#define>s, for example C<YY_INPUT> or C<YY_DECL>.

=item B<--sysid>=I<sysid>

Overrides the C<SYSTEM> id of the accepted DTD. Sometimes useful when your
dtd is placed in a subdirectory.

=item B<--root-tags> I<roottags>, B<-r> I<roottags>

Restricts the XML processor to validate only documents with one of the
root elements listed in the comma-separated I<roottags>.

=item B<--scanner> B<[>I<scanner_name>B<]>, B<-S> B<[>I<scanner_name>B<]>

Generate the scanner. If I<scanner_name> is not given on command line, it
defaults to I<name>F<.l>.  Conflicts with B<-A>; on by default if none of
B<-SHD> specified.

=item B<--skel> I<skel>, B<-s> I<skel>

Use the skeleton scanner I<skel> instead of the default.

=item B<--act-bin> I<flexml-act>, B<-T> I<flexml-act>

This is an internal option mainly used to test versions of flexml not
installed yet.

=item B<--stack-increment> I<stack_increment>, B<-b> I<stack_increment>

Sets the FLEXML_BUFFERSTACKSIZE to stack_increment (100000 by default). This
controls how much the data stack grows in each realloc().

=item B<--tag-prefix> I<STRING>, B<-O> I<STRING>

Use STRING to differentiate multiple versions of flexml in the same C
code, just like the -P flex argument.

=item B<--uri> I<uri>, B<-u> I<uri>

Sets the URI of the DTD, used in the C<DOCTYPE> header, to the
specified I<uri> (the default is the DTD name).

=item B<--verbose>, B<-v>

Be verbose: echo each DTD declaration (after parameter expansion).

=item B<--version>, B<-V>

Print the version of I<flexml> and exit.

=back

=head1 ACTION FILE FORMAT

Action files, passed to the B<-a> option, are XML documents conforming
to the DTD F<flexml-act.dtd> which is the following:

  <!ELEMENT actions ((top|start|end)*,main?)>
  <!ENTITY % C-code "(#PCDATA)">
  <!ELEMENT top   %C-code;>
  <!ELEMENT start %C-code;>  <!ATTLIST start tag NMTOKEN #REQUIRED>
  <!ELEMENT end   %C-code;>  <!ATTLIST end   tag NMTOKEN #REQUIRED>
  <!ELEMENT main  %C-code;>

The elements should be used as follows:

=over 4

=item C<top>

Use for top-level C code such as global declarations, utility
functions, etc.

=item C<start>

Attaches the code as an action to the element with the name of the
required "C<tag>" attribute.  The "C<%C-code;>" component should be C
code suitable for inclusion in a C block (i.e., within C<{>...C<}> so
it may contain local variables); furthermore the following extensions
are available:

C<{>I<attribute>C<}>: Can be used to access the value of the
I<attribute> as set with I<attribute>C<=>I<value> in the start tag.
In C, C<{>I<attribute>C<}> will be interpreted depending on the
declaration of the attribute. If the attribute is declared as an
enumerated type like

  <!ATTLIST attrib (alt1 | alt2 |...) ...>

then the C attribute value is of an enumerated type with the elements
written C<{>I<attribute>C<=>I<alt1>C<}>,
C<{>I<attribute>C<=>I<alt2>C<}>, etc.; furthermore an I<unset>
attribute has the "value" C<{!>I<attribute>C<}>.  If the attribute is
not an enumeration then C<{>I<attribute>C<}> is a null-terminated C
string (of type C<char*>) and C<{!>I<attribute>C<}> is C<NULL>.

=item C<end>

Similarly attaches the code as an action to the end tag with the name
of the required "C<tag>" attribute; also here the "C<%C-code;>"
component should be C code suitable for inclusion in a C block.  In
case the element has "Mixed" contents, i.e, was declared to permit
C<#PCDATA>, then the following variable is available:

C<{#PCDATA}>: Contains the text (C<#PCDATA>) of the element as a
null-terminated C string (of type C<char*>).  In case the Mixed
contents element actually mixed text and child elements then C<pcdata>
contains the plain concatenation of the text fragments as one string.

=item C<main>

Finally, an optional "C<main>" element can contain the C C<main>
function of the XML application.  Normally the C<main> function should
include (at least) one call of the XML processor:

C<yylex()>:
Invokes the XML processor produced by I<flex>(1) on the XML document
found on the standard input (actually the C<yyin> file handle: see the
manual for I<flex>(1) for information on how to change this as well as
the name C<yylex>).

If no C<main> action is provided then the following is used:

  int main() { exit(yylex()); }

=back

It is advisable to use XML E<lt>C<![CDATA[> ... C<]]>E<gt> sections
for the C code to make sure that all characters are properly passed to
the output file.

Finally note that I<Flexml> handles empty elements
E<lt>I<tag>C</>E<gt> as equivalent to
E<lt>I<tag>E<gt>E<lt>C</>I<tag>E<gt>.

=head1 COMPILATION

The following I<make>(1) file fragment shows how one can compile
I<flexml>-generated programs:


  # Programs.
  FLEXML = flexml -v

  # Generate linkable XML processor with header for application.
  %.l %.h: %.dtd
	  $(FLEXML) $<

  # Generate C source from flex scanner.
  %.c: 	  %.l
	  $(FLEX) -Bs -o"$@" "$<"

  # Generate XML application C source to link with processor.
  # Note: The dependency must be of the form "appl.c: appl.act proc.dtd".
  %.c:	  %.act
	  $(FLEXML) -D -a $^

  # Direct generation of stand-alone XML processor+application.
  # Note: The dependency must be of the form "appl.l: appl.act proc.dtd".
  %.l:	  %.act
	  $(FLEXML) -A -a $^

=head1 BUGS

The present version of I<flexml> is to be considered in "early beta"
state thus bugs should be expected (and the author would like to hear
about them).  Here are some known restrictions that we hope to
overcome in the future:

=over 4

=item *

The character set is merely ASCII (actually I<flex>(1) handles 8 bit
characters but only the ASCII character set is common with the XML
default UTF-8 encoding).

=item *

C<ID> type attributes are not validated for uniqueness; C<IDREF> and
C<IDREFS> attributes are not validated for existence.

=item *

The C<ENTITY> and C<ENTITIES> attribute types are not supported.

=item *

C<NOTATION> declarations are not supported.

=item *

The various C<xml:>-attributes are treated like any other attributes;
in particular C<xml:spaces> should be supported.

=item *

The DTD parser is presently a perl hack so it may parse some DTDs
badly; in particular the expansion of parameter entities may not
conform fully to the XML specification.

=item *

A child should be able to "return" a value for the parent (also called
a I<synthesised attribute>).  Similarly an element in Mixed contents
should be able to inject text into the C<pcdata> of the parent.

=back

=head1 FILES

=over 4

=item F<./skel>

The skeleton scanner with the generic parts of XML scanning.

=item F</usr/share/doc/flexml/>

License, further documentation, and examples.

=back

=head1 SEE ALSO

I<flex>(1), Extensible Markup Language (XML) 1.0 (W3C Recommendation
REC-xml-1998-0210).

=head1 AUTHOR

I<Flexml> was written by Kristoffer Rose,
E<lt>C<krisrose@debian.org>E<gt>.

=head1 COPYRIGHT

The program is Copyright (c) 1999 Kristoffer Rose (all rights
reserved) and distributed under the GNU General Public License (GPL,
also known as "copyleft", which clarifies that the author provides
absolutely no warranty for I<flexml> and ensures that I<flexml> is and
will remain available for all uses, even comercial).

=head1 ACKNOWLEDGEMENT

I am grateful to NTSys (France) for supporting the development of
I<flexml>.  Finally extend my severe thanks to Jef Poskanzer, Vern
Paxson, and the rest of the I<flex> maintainers and GNU developers for
a great tool.

=cut