summaryrefslogtreecommitdiff
path: root/macros/texinfo/texinfo/tp/Texinfo/Convert/Converter.pm
blob: 1c18523bf12b52a03af600448c376a91a629f372 (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
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
# Converter.pm: Common code for Converters.
#
# Copyright 2011-2022 Free Software Foundation, Inc.
# 
# 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 3 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, see <http://www.gnu.org/licenses/>.
# 
# Original author: Patrice Dumas <pertusus@free.fr>

package Texinfo::Convert::Converter;

use 5.00405;
use strict;

# To check if there is no erroneous autovivification
#no autovivification qw(fetch delete exists store strict);

# for fileparse
use File::Basename;
# for file names portability
use File::Spec;
use Encode qw(decode);

use Carp qw(cluck confess);

use Texinfo::Common;

use Texinfo::Report;

use Texinfo::Convert::Utils;
use Texinfo::Convert::Unicode;
use Texinfo::Convert::Text;
use Texinfo::Convert::NodeNameNormalization;
use Texinfo::Structuring;

use Texinfo::Translations;

require Exporter;
use vars qw($VERSION @ISA @EXPORT_OK %EXPORT_TAGS);
@ISA = qw(Exporter Texinfo::Report Texinfo::Translations);

%EXPORT_TAGS = ( 'all' => [ qw(
xml_protect_text
xml_comment
xml_accent
xml_accents
) ] );

@EXPORT_OK = ( @{ $EXPORT_TAGS{'all'} } );

$VERSION = '7.0.1';

my %defaults = (
  'documentlanguage'     => undef,
);

# defaults for all converters that are not defined elsewhere.
# undef values in general marks information passed by the caller that
# is valid in the parser initialization hash, but is not considered
# as "configuration/customization". It is not available through get_conf()
# but is available directly in the converter as a hash key.
# FIXME separate the two types of information and check that those
# items are not valid customization options?
# NOTE converters for now do not add more, set converted_format, and,
# rarely, output_format.  It would be good to keep it that way and add
# customization options instead.
my %common_converters_defaults = (
  'language_config_dirs' => undef,
  'converted_format'     => undef,
  # can be different from the converted_format, for example, epub3
  # output format converted format is html.
  'output_format'        => undef,
  'structuring'          => undef,
  'translated_commands'  => {'error' => 'error@arrow{}',},

# This is the default, mainly for tests; the caller should set them.  These
# values are what is used in tests of the Converters.  These variables are
# customization options, set in the main program when a converter is
# called from the main program.
  'PACKAGE_AND_VERSION'  => 'texinfo',
  'PACKAGE_VERSION'      => '',
  'PACKAGE_URL'          => 'http://www.gnu.org/software/texinfo/',
  'PROGRAM'              => '',
);

my %all_converters_defaults
 = (%Texinfo::Common::default_converter_command_line_options,
    %Texinfo::Common::default_converter_customization,
    %Texinfo::Common::document_settable_unique_at_commands,
    %Texinfo::Common::document_settable_multiple_at_commands,
    %common_converters_defaults
);

# For translation of in document string.
if (0) {
  my $self;
  $self->gdt('error@arrow{}');
}

# This is not used as code, but used to mark months as strings to be
# translated
if (0) {
  my $self;
  my @mark_month_for_translation = (
   $self->gdt('January'),
   $self->gdt('February'),
   $self->gdt('March'),
   $self->gdt('April'),
   $self->gdt('May'),
   $self->gdt('June'),
   $self->gdt('July'),
   $self->gdt('August'),
   $self->gdt('September'),
   $self->gdt('October'),
   $self->gdt('November'),
   $self->gdt('December')
  );
}

our %default_args_code_style = (
  'email' => [1],
  'anchor' => [1],
  'uref' => [1],
  'url' => [1],
  'math' => [1],
  'inforef' => [1,undef,1],
  'image' => [1, 1, 1, undef, 1],
# and type?
  'float' => [1],
);

foreach my $code_style_command (keys(%Texinfo::Common::brace_code_commands)) {
  $default_args_code_style{$code_style_command} = [1];
}
foreach my $ref_cmd ('pxref', 'xref', 'ref') {
  $default_args_code_style{$ref_cmd} = [1, undef, undef, 1];
}

################################################################
# converter API

# convert_tree() and convert() should be implemented in converters.
# There is an implementation of output() below but in general
# output() should also be implemented by Converters.

# Functions that should be defined in specific converters
sub converter_defaults($$)
{
  return %defaults;
}

sub converter_initialize($)
{
}

sub output_internal_links($)
{
  my $self = shift;
  return undef;
}

# this function is designed so as to be used in specific Converters
sub converter(;$)
{
  my $class = shift;
  my $converter = { 'set' => {} };

  my $conf;
  my $name = 'converter';

  if (ref($class) eq 'HASH') {
    $conf = $class;
    bless $converter;
  } elsif (defined($class)) {
    bless $converter, $class;
    $name = ref($converter);
    $conf = shift;
  } else {
    bless $converter;
    $conf = shift;
    $name = ref($converter);
  }
  my %defaults = $converter->converter_defaults($conf);
  foreach my $key (keys(%all_converters_defaults)) {
    $defaults{$key} = $all_converters_defaults{$key}
                          if (!exists($defaults{$key}));
  }
  $converter->{'conf'} = {};
  foreach my $key (keys(%defaults)) {
    if (Texinfo::Common::valid_customization_option($key)) {
      $converter->{'conf'}->{$key} = $defaults{$key};
    } else {
      $converter->{$key} = $defaults{$key};
    }
  }
  #$converter->{'converter_pre_conf'} = \%defaults;
  if (defined($conf)) {
    if ($conf->{'parser'}) {
      $converter->{'global_commands'}
         = $conf->{'parser'}->global_commands_information();
      $converter->{'parser_info'} = $conf->{'parser'}->global_information();
      my $floats = $conf->{'parser'}->floats_information();
      my ($labels, $targets_list, $nodes_list)
        = $conf->{'parser'}->labels_information();

      $converter->{'floats'} = $floats if ($floats);
      $converter->{'labels'} = $labels if ($labels);
      $converter->{'indices_information'}
             = $conf->{'parser'}->indices_information();
      $converter->{'values'} = $conf->{'parser'}->{'values'};
      delete $conf->{'parser'};
    }
    foreach my $key (keys(%$conf)) {
      if (Texinfo::Common::valid_customization_option($key)) {
        $converter->{'conf'}->{$key} = $conf->{$key};
      } elsif (!exists($defaults{$key})) {
        warn "$key not a possible configuration in $name\n";
      } else {
        $converter->{$key} = $conf->{$key};
      }
      # configuration set here, in general coming from command-line
      # will not be reset by set_conf.
      $converter->{'set'}->{$key} = 1;
    }
  }
  # set $converter->{'converter_init_conf'} to the customization
  # options obtained after setting the defaults and applying
  # the customization passed as argument.
  $converter->{'converter_init_conf'} = { %{$converter->{'conf'}} };
  foreach my $key (keys (%defaults)) {
    if (defined($converter->{$key})) {
      $converter->{'converter_init_conf'}->{$key} = $converter->{$key};
    }
  }

  Texinfo::Common::set_output_encodings($converter, $converter->{'parser_info'});

  # turn the array to a hash for speed.  Not sure it really matters for such
  # a small array.
  my $expanded_formats = $converter->get_conf('EXPANDED_FORMATS');
  $converter->{'expanded_formats_hash'} = {};
  if (defined($expanded_formats)) {
    foreach my $expanded_format (@{$converter->get_conf('EXPANDED_FORMATS')}) {
      $converter->{'expanded_formats_hash'}->{$expanded_format} = 1;
    }
  }

  # used for output files information, to register opened
  # and not closed files.  Accessed through output_files_information()
  $converter->{'output_files'} = Texinfo::Common::output_files_initialize();

  $converter->Texinfo::Report::new();

  $converter->converter_initialize();

  return $converter;
}

sub _convert_document_tree_units($$;$$)
{
  my $self = shift;
  my $root = shift;
  my $tree_units = shift;
  my $fh = shift;

  if ($tree_units) {
    my $result = '';
    foreach my $tree_unit (@$tree_units) {
      $result .= $self->write_or_return($self->convert_tree($tree_unit), $fh);
    }
    return $result;
  } else {
    return $self->write_or_return($self->convert_tree($root), $fh);
  }
}

# the two following methods can be used to implement convert() in
# Converters.
sub convert_document_sections($$;$)
{
  my $self = shift;
  my $root = shift;
  my $fh = shift;

  my $tree_units = Texinfo::Structuring::split_by_section($root);
  return $self->_convert_document_tree_units($root, $tree_units, $fh);
}

sub convert_document_nodes($$;$)
{
  my $self = shift;
  my $root = shift;
  my $fh = shift;

  my $tree_units = Texinfo::Structuring::split_by_node($root);
  return $self->_convert_document_tree_units($root, $tree_units, $fh);
}

# In general, converters override this method, but simple
# converters can use it.  It is used for the plaintext
# output format.
# use file_counters and out_filepaths converter states.
sub output($$)
{
  my $self = shift;
  my $root = shift;

  my $tree_units;

  if (defined($self->get_conf('OUTFILE'))
      and ($Texinfo::Common::null_device_file{$self->get_conf('OUTFILE')}
           or $self->get_conf('OUTFILE') eq '-'
           or $self->get_conf('OUTFILE') eq '')) {
    if ($self->get_conf('SPLIT')) {
      $self->document_warn($self,
               sprintf(__("%s: output incompatible with split"),
                                   $self->get_conf('OUTFILE')));
      $self->force_conf('SPLIT', 0);
    }
  }
  if ($self->get_conf('SPLIT')) {
    $self->set_conf('NODE_FILES', 1);
  }

  my ($output_file, $destination_directory, $output_filename,
                  $document_name) = $self->determine_files_and_directory();
  my ($encoded_destination_directory, $dir_encoding)
    = $self->encoded_output_file_name($destination_directory);
  my $succeeded
    = $self->create_destination_directory($encoded_destination_directory,
                                          $destination_directory);
  return undef unless $succeeded;

  if ($self->get_conf('USE_NODES')) {
    $tree_units = Texinfo::Structuring::split_by_node($root);
  } else {
    $tree_units = Texinfo::Structuring::split_by_section($root);
  }

  Texinfo::Structuring::split_pages($tree_units, $self->get_conf('SPLIT'));

  # determine file names associated with the different pages
  if ($output_file ne '') {
    $self->_set_tree_units_files($tree_units, $output_file, $destination_directory,
                                 $output_filename, $document_name);
  }

  #print STDERR "$tree_units $tree_units->[0]->{'structure'}->{'unit_filename'}\n";

  # Now do the output
  my $fh;
  my $output = '';
  if (!$tree_units or !$tree_units->[0]->{'structure'}
      or !defined($tree_units->[0]->{'structure'}->{'unit_filename'})) {
    # no page
    my $outfile_name;
    my $encoded_outfile_name;
    if ($output_file ne '') {
      if ($self->get_conf('SPLIT')) {
        my $top_node_file_name = $self->top_node_filename($document_name);
        if (defined($destination_directory) and $destination_directory ne '') {
          $outfile_name = File::Spec->catfile($destination_directory,
                                              $top_node_file_name);
        } else {
          $outfile_name = $top_node_file_name;
        }
      } else {
        $outfile_name = $output_file;
      }
      print STDERR "DO No pages, output in $outfile_name\n"
        if ($self->get_conf('DEBUG'));
      my $path_encoding;
      ($encoded_outfile_name, $path_encoding)
        = $self->encoded_output_file_name($outfile_name);
      my $error_message;
      ($fh, $error_message) = Texinfo::Common::output_files_open_out(
                    $self->output_files_information(), $self,
                    $encoded_outfile_name);
      if (!$fh) {
        $self->document_error($self,
                 sprintf(__("could not open %s for writing: %s"),
                                      $outfile_name, $error_message));
        return undef;
      }
    } else {
      print STDERR "DO No pages, string output\n"
        if ($self->get_conf('DEBUG'));
    }

    if ($tree_units and @$tree_units) {
      foreach my $tree_unit (@$tree_units) {
        my $tree_unit_text = $self->convert_tree($tree_unit);
        $output .= $self->write_or_return($tree_unit_text, $fh);
      }
    } else {
      # FIXME this is in general better to use convert() for instance
      # to have the converter output footnotes as it cannot do is as
      # part of tree units formatting.  However, this breaks the promise
      # that only convert_tree is used in generic Converter code.
      # REMARK that right now, this code is never called, as
      # Texinfo::Structuring::split_by_node or split_by_page always return
      # an array containing at least one unit.  But this was not the case
      # in the past and could change again in the future.
      $output .= $self->write_or_return($self->convert($root), $fh);
    }
    # NOTE do not close STDOUT now to avoid a perl warning.
    # FIXME is it still true that there is such a warning?
    if ($fh and $outfile_name ne '-') {
      Texinfo::Common::output_files_register_closed(
                  $self->output_files_information(), $encoded_outfile_name);
      if (!close($fh)) {
        $self->document_error($self,
                 sprintf(__("error on closing %s: %s"),
                                      $outfile_name, $!));
      }
    }
    return $output if ($output_file eq '');
  } else {
    # output with pages
    print STDERR "DO Elements with filenames\n"
      if ($self->get_conf('DEBUG'));
    my %files_filehandle;
    
    foreach my $tree_unit (@$tree_units) {
      my $tree_unit_filename = $tree_unit->{'structure'}->{'unit_filename'};
      my $out_filepath = $self->{'out_filepaths'}->{$tree_unit_filename};
      my $file_fh;
      # open the file and output the elements
      if (!exists($files_filehandle{$tree_unit_filename})) {
        my $error_message;
        ($file_fh, $error_message) = Texinfo::Common::output_files_open_out(
                             $self->output_files_information(), $self,
                             $out_filepath);
        if (!$file_fh) {
          $self->document_error($self,
                sprintf(__("could not open %s for writing: %s"),
                       $out_filepath, $error_message));
          return undef;
        }
        $files_filehandle{$tree_unit_filename} = $file_fh;
      } else {
        $file_fh = $files_filehandle{$tree_unit_filename};
      }
      my $tree_unit_text = $self->convert_tree($tree_unit);
      print $file_fh $tree_unit_text;
      $self->{'file_counters'}->{$tree_unit_filename}--;
      if ($self->{'file_counters'}->{$tree_unit_filename} == 0) {
        # NOTE do not close STDOUT here to avoid a perl warning
        if ($out_filepath ne '-') {
          Texinfo::Common::output_files_register_closed(
            $self->output_files_information(), $out_filepath);
          if (!close($file_fh)) {
            $self->document_error($self,
                     sprintf(__("error on closing %s: %s"),
                                  $out_filepath, $!));
            return undef;
          }
        }
      }
    }
  }
}


###############################################################
# Implementation of the customization API that is used in many
# Texinfo modules

sub get_conf($$)
{
  my $self = shift;
  my $conf = shift;
  if (!Texinfo::Common::valid_customization_option($conf)) {
    confess("CBUG: unknown option $conf\n");
    #return undef;
  }
  return $self->{'conf'}->{$conf};
}

sub set_conf($$$)
{
  my $self = shift;
  my $conf = shift;
  my $value = shift;
  if (!Texinfo::Common::valid_customization_option($conf)) {
    die "BBUG: unknown option $conf\n";
    return undef;
  }
  if ($self->{'set'}->{$conf}) {
    return 0;
  } else {
    $self->{'conf'}->{$conf} = $value;
    return 1;
  }
}

sub force_conf($$$)
{
  my $self = shift;
  my $conf = shift;
  my $value = shift;
  if (!Texinfo::Common::valid_customization_option($conf)) {
    die "ABUG: unknown option $conf\n";
    return undef;
  }
  $self->{'conf'}->{$conf} = $value;
  return 1;
}

sub output_files_information($)
{
  my $self = shift;
  return $self->{'output_files'};
}


####################################################################
# Useful functions.  Those in this section are used in the module and can
# also be used in other Converter modules.

# output fo $fh if defined, otherwise return the text.
sub write_or_return($$$)
{
  my $self = shift;
  my $text = shift;
  my $fh = shift;
  if ($fh) {
    print $fh $text;
    return '';
  } else {
    return $text;
  }
}

my $STDIN_DOCU_NAME = 'stdin';

sub determine_files_and_directory($;$)
{
  my $self = shift;
  my $output_format = shift;

  if (not defined($output_format)) {
    $output_format = $self->{'output_format'};
  }

  # determine input file base name
  my $input_basefile;
  if (defined($self->{'parser_info'}->{'input_file_name'})) {
    # 'input_file_name' is not decoded, as it is derived from input
    # file which is not decoded either.  We want to return only
    # decoded character strings such that they can easily be mixed
    # with other character strings, so we decode here.
    my $input_file_name = $self->{'parser_info'}->{'input_file_name'};
    my $encoding = $self->get_conf('COMMAND_LINE_ENCODING');
    if (defined($encoding)) {
      $input_file_name = decode($encoding, $input_file_name, sub { '?' });
      # use '?' as replacement character rather than U+FFFD in case it
      # is re-encoded to an encoding without this character
    }
    my ($directories, $suffix);
    ($input_basefile, $directories, $suffix) = fileparse($input_file_name);
  } else {
    # This could happen if called on a piece of texinfo
    $input_basefile = '';
  }

  my $input_basename;
  if ($input_basefile eq '-') {
    $input_basename = $STDIN_DOCU_NAME;
  } else {
    $input_basename = $input_basefile;
    $input_basename =~ s/\.te?x(i|info)?$//;
  }

  my $setfilename;
  if (defined($self->get_conf('setfilename'))) {
    $setfilename = $self->get_conf('setfilename');
  } elsif ($self->{'global_commands'}
           and $self->{'global_commands'}->{'setfilename'}
           and $self->{'global_commands'}->{'setfilename'}->{'extra'}
           and defined($self->{'global_commands'}->{'setfilename'}->{'extra'}->{'text_arg'})) {
    $setfilename
      = $self->{'global_commands'}->{'setfilename'}->{'extra'}->{'text_arg'};
  }

  my $input_basename_for_outfile = $input_basename;
  my $setfilename_for_outfile = $setfilename;
  # PREFIX overrides both setfilename and the input file base name
  if (defined($self->get_conf('PREFIX'))) {
    $setfilename_for_outfile = undef;
    $input_basename_for_outfile = $self->get_conf('PREFIX');
  }

  # the document path, in general the outfile without
  # extension and can be set from setfilename if outfile is not set
  my $document_path;
  # determine output file and output file name
  my $output_file;
  if (!defined($self->get_conf('OUTFILE'))) {
    if (defined($setfilename_for_outfile)
        and !$self->get_conf('NO_USE_SETFILENAME')) {
      $output_file = $setfilename_for_outfile;
      $document_path = $setfilename_for_outfile;
      $document_path =~ s/\.[^\.]*$//;
      if (!$self->get_conf('USE_SETFILENAME_EXTENSION')) {
        $output_file =~ s/\.[^\.]*$//;
        $output_file .= '.'.$self->get_conf('EXTENSION')
          if (defined($self->get_conf('EXTENSION'))
              and $self->get_conf('EXTENSION') ne '');
      }
    } elsif ($input_basename_for_outfile ne '') {
      $output_file = $input_basename_for_outfile;
      $document_path = $input_basename_for_outfile;
      $output_file .= '.'.$self->get_conf('EXTENSION')
        if (defined($self->get_conf('EXTENSION'))
            and $self->get_conf('EXTENSION') ne '');
    } else {
      $output_file = '';
      $document_path = $output_file;
    }
    if (defined($self->get_conf('SUBDIR')) and $output_file ne '') {
      my $dir = File::Spec->canonpath($self->get_conf('SUBDIR'));
      $output_file = File::Spec->catfile($dir, $output_file);
    }
  } else {
    $document_path = $self->get_conf('OUTFILE');
    $document_path =~ s/\.[^\.]*$//;
    $output_file = $self->get_conf('OUTFILE');
  }

  # the output file path, in general same as the outfile but can be
  # set from setfilename if outfile is not set.
  my $output_filepath = $output_file;
  # in this case one wants to get the result in a string and there
  # is a setfilename.  The setfilename is used to get something.
  # This happens in the test suite.
  if ($output_file eq '' and defined($setfilename_for_outfile)
      and !$self->get_conf('NO_USE_SETFILENAME')) {
    $output_filepath = $setfilename_for_outfile;
    $document_path = $setfilename_for_outfile;
    $document_path =~ s/\.[^\.]*$//;
  }

  # $document_name is the name of the document, which is the output
  # file basename, $output_filename, without extension.
  my ($document_name, $output_filename, $directories, $suffix);
  # We may be handling setfilename there, so it is not obvious that we
  # want to use fileparse and not consider unixish separators.  However,
  # if this is setfilename, it should be a simple file name, so it
  # should hopefully be harmless to use fileparse
  ($document_name, $directories, $suffix) = fileparse($document_path);
  ($output_filename, $directories, $suffix) = fileparse($output_filepath);
  my $destination_directory;
  if ($self->get_conf('SPLIT')) {
    if (defined($self->get_conf('OUTFILE'))) {
      $destination_directory = $self->get_conf('OUTFILE');
    } elsif (defined($self->get_conf('SUBDIR'))) {
      $destination_directory = $self->get_conf('SUBDIR');
    } else {
      $destination_directory = $document_name;
      if (defined($output_format) and $output_format ne '') {
        $destination_directory .= '_'.$output_format;
      }
    }
  } else {
    # $output_file_filename is not used, but $output_filename should be
    # the same as long as $output_file is the same as $output_filepath
    # which is the case except if $output_file is ''.
    my ($output_file_filename, $output_dir, $suffix) = fileparse($output_file);
    if ($output_dir ne '') {
      $destination_directory = $output_dir;
    }
  }
  if (defined($destination_directory)
      and $destination_directory ne '') {
    $destination_directory = File::Spec->canonpath($destination_directory);
  }
  return ($output_file, $destination_directory, $output_filename,
          $document_name, $input_basefile);
}

sub _id_to_filename($$)
{
  my $self = shift;
  my $id = shift;
  return substr($id, 0, $self->get_conf('BASEFILENAME_LENGTH'));
}

sub normalized_sectioning_command_filename($$)
{
  my $self = shift;
  my $command = shift;
  my $no_unidecode;

  $no_unidecode = 1 if (defined($self->get_conf('USE_UNIDECODE'))
                        and !$self->get_conf('USE_UNIDECODE'));

  my $normalized_name
    = Texinfo::Convert::NodeNameNormalization::transliterate_texinfo(
         {'contents' => $command->{'args'}->[0]->{'contents'}},
                  $no_unidecode);

  my $filename = $self->_id_to_filename($normalized_name);
  $filename .= '.'.$self->get_conf('EXTENSION')
    if (defined($self->get_conf('EXTENSION'))
      and $self->get_conf('EXTENSION') ne '');
  return ($normalized_name, $filename);
}

sub node_information_filename($$)
{
  my $self = shift;
  my $node_info = shift;

  my $no_unidecode;
  $no_unidecode = 1 if (defined($self->get_conf('USE_UNIDECODE'))
                        and !$self->get_conf('USE_UNIDECODE'));

  my $filename;
  if (defined($node_info->{'normalized'})) {
    if ($self->get_conf('TRANSLITERATE_FILE_NAMES')) {
      $filename = Texinfo::Convert::NodeNameNormalization::transliterate_texinfo(
       {'contents' => $node_info->{'node_content'}},
            $no_unidecode);
    } else {
      $filename = $node_info->{'normalized'};
    }
  } elsif (defined($node_info->{'node_content'})) {
    $filename = Texinfo::Convert::NodeNameNormalization::normalize_node(
             { 'contents' => $node_info->{'node_content'} });
  } else {
    $filename = '';
  }
  $filename = $self->_id_to_filename($filename);
  return $filename;
}

sub initialize_tree_units_files($)
{
  my $self = shift;

  $self->{'out_filepaths'} = {};
  $self->{'file_counters'} = {};

  if ($self->get_conf('CASE_INSENSITIVE_FILENAMES')) {
    $self->{'filenames'} = {};
  }
}

# If CASE_INSENSITIVE_FILENAMES is set, reuse the first
# filename with the same name insensitive to the case.
sub _normalize_filename_case($$)
{
  my $self = shift;
  my $filename = shift;

  if ($self->get_conf('CASE_INSENSITIVE_FILENAMES')) {
    if (exists($self->{'filenames'}->{lc($filename)})) {
      if ($self->get_conf('DEBUG')) {
        print STDERR "Reusing ".$self->{'filenames'}->{lc($filename)}
                     ." for $filename\n";
      }
      $filename = $self->{'filenames'}->{lc($filename)};
    } else {
      $self->{'filenames'}->{lc($filename)} = $filename;
    }
  }
  return $filename;
}

# Sets $tree_unit->{'structure'}->{'unit_filename'}.
sub set_tree_unit_file($$$)
{
  my $self = shift;
  my $tree_unit = shift;
  my $filename = shift;

  if (!defined($filename)) {
    cluck("set_tree_unit_file: filename not defined\n");
  }

  $filename = $self->_normalize_filename_case($filename);

  $tree_unit->{'structure'} = {} if (!($tree_unit->{'structure'}));

  # This should never happen, set_tree_unit_file is called once per
  # tree unit.
  if (exists($tree_unit->{'structure'}->{'unit_filename'})) {
    if ($tree_unit->{'structure'}->{'unit_filename'} eq $filename) {
      print STDERR "set_tree_unit_file: already set: $filename\n"
         if ($self->get_conf('DEBUG'));
    } else {
      print STDERR  "set_tree_unit_file: unit_filename reset: "
        .$tree_unit->{'structure'}->{'unit_filename'}.", $filename\n"
           if ($self->get_conf('DEBUG'));
    }
  }
  $tree_unit->{'structure'}->{'unit_filename'} = $filename;
}

# sets out_filepaths converter state, associating a file name
# to a file path.
# $FILEPATH can be given explicitly, otherwise it is based on $FILENAME
# and $DESTINATION_DIRECTORY
sub set_file_path($$$;$)
{
  my $self = shift;
  my $filename = shift;
  my $destination_directory = shift;
  my $filepath = shift;

  if (!defined($filename)) {
    cluck("set_file_path: filename not defined\n");
  }

  $filename = $self->_normalize_filename_case($filename);

  if (not defined($filepath)) {
    if (defined($destination_directory) and $destination_directory ne '') {
      $filepath = File::Spec->catfile($destination_directory, $filename);
    } else {
      $filepath = $filename;
    }
  }
  # should not happen, the file path should be set only once
  # per file name.
  if (defined($self->{'out_filepaths'}->{$filename})) {
    if ($self->{'out_filepaths'}->{$filename} eq $filepath) {
      print STDERR "set_file_path: filepath set: $filepath\n"
         if ($self->get_conf('DEBUG'));
    } else {
      print STDERR  "set_file_path: filepath reset: "
        .$self->{'out_filepaths'}->{$filename}.", $filepath\n"
         if ($self->get_conf('DEBUG'));
    }
  }
  $self->{'out_filepaths'}->{$filename} = $filepath;
}

sub top_node_filename($$)
{
  my $self = shift;
  my $document_name = shift;

  my $top_node_filename;
  if (defined($self->get_conf('TOP_FILE'))
      and $self->get_conf('TOP_FILE') ne '') {
    $top_node_filename = $self->get_conf('TOP_FILE');
  } else {
    my $extension = '';
    $extension = '.'.$self->get_conf('EXTENSION')
      if (defined($self->get_conf('EXTENSION'))
            and $self->get_conf('EXTENSION') ne '');

    $top_node_filename = $document_name;
    if (defined($top_node_filename)) {
      $top_node_filename .= $extension;
    }
  }
  return $top_node_filename;
}

sub _get_root_element($$)
{
  my $self = shift;
  my $command = shift;
  my $find_container = shift;

  my $current = $command;

  while (1) {
    if ($current->{'type'}) {
      if ($current->{'type'} eq 'unit') {
        return $current;
      }
    }
    if ($current->{'parent'}) {
      $current = $current->{'parent'};
    } else {
      return undef;
    }
  }
}

# set file_counters converter state
sub _set_tree_units_files($$$$$$)
{
  my $self = shift;
  my $tree_units = shift;
  my $output_file = shift;
  my $destination_directory = shift;
  my $output_filename = shift;
  my $document_name = shift;

  # Ensure that the document has pages
  return undef if (!defined($tree_units) or !@$tree_units);

  $self->initialize_tree_units_files();

  my $extension = '';
  $extension = '.'.$self->get_conf('EXTENSION')
            if (defined($self->get_conf('EXTENSION'))
                and $self->get_conf('EXTENSION') ne '');

  if (!$self->get_conf('SPLIT')) {
    $self->set_file_path($output_filename, undef, $output_file);
    foreach my $tree_unit (@$tree_units) {
      $self->set_tree_unit_file($tree_unit, $output_filename);
    }
  } else {
    my $node_top;
    $node_top = $self->{'labels'}->{'Top'} if ($self->{'labels'});
  
    my $top_node_filename = $self->top_node_filename($document_name);
    # first determine the top node file name.
    if ($node_top and defined($top_node_filename)) {
      my ($node_top_unit) = $self->_get_root_element($node_top);
      die "BUG: No element for top node" if (!defined($node_top));
      $self->set_file_path($top_node_filename, $destination_directory);
      $self->set_tree_unit_file($node_top_unit, $top_node_filename);
    }
    my $file_nr = 0;
    my $previous_page;
    foreach my $tree_unit (@$tree_units) {
      # For Top node.
      next if ($tree_unit->{'structure'}
               and defined($tree_unit->{'structure'}->{'unit_filename'}));
      my $file_tree_unit = $tree_unit->{'extra'}->{'first_in_page'};
      if (!$file_tree_unit) {
        cluck ("No first_in_page for $tree_unit\n");
      }
      if (!defined($file_tree_unit->{'structure'}->{'unit_filename'})) {
        foreach my $root_command (@{$file_tree_unit->{'contents'}}) {
          if ($root_command->{'cmdname'}
              and $root_command->{'cmdname'} eq 'node') {
            my $node_filename;
            # double node are not normalized, they are handled here
            if (!defined($root_command->{'extra'}->{'normalized'})
                or !defined($self->{'labels'}->{$root_command->{'extra'}->{'normalized'}})) {
              $node_filename = 'unknown_node';
            } else {
              $node_filename
               = $self->node_information_filename($root_command->{'extra'});
            }
            $node_filename .= $extension;
            $self->set_file_path($node_filename,$destination_directory);
            $self->set_tree_unit_file($file_tree_unit, $node_filename);
            last;
          }
        }
        if (!defined($file_tree_unit->{'structure'}->{'unit_filename'})) {
          # use section to do the file name if there is no node
          my $command = $file_tree_unit->{'extra'}->{'unit_command'};
          if ($command) {
            if ($command->{'cmdname'} eq 'top' and !$node_top
                and defined($top_node_filename)) {
              $self->set_file_path($top_node_filename, $destination_directory);
              $self->set_tree_unit_file($file_tree_unit, $top_node_filename);
            } else {
              my ($normalized_name, $filename)
                 = $self->normalized_sectioning_command_filename($command);
              $self->set_file_path($filename, $destination_directory);
              $self->set_tree_unit_file($file_tree_unit, $filename);
            }
          } else {
            # when everything else has failed
            if ($file_nr == 0 and !$node_top and defined($top_node_filename)) {
              $self->set_file_path($top_node_filename, $destination_directory);
              $self->set_tree_unit_file($file_tree_unit, $top_node_filename);
            } else {
              my $filename = $document_name . "_$file_nr";
              $filename .= $extension;
              $self->set_file_path($filename, $destination_directory);
              $self->set_tree_unit_file($tree_unit, $filename);
            }
            $file_nr++;
          }
        }
      }
      $self->set_tree_unit_file($tree_unit,
                    $file_tree_unit->{'structure'}->{'unit_filename'});
    }
  }

  foreach my $tree_unit (@$tree_units) {
    my $tree_unit_filename = $tree_unit->{'structure'}->{'unit_filename'};
    $self->{'file_counters'}->{$tree_unit_filename} = 0
       if (!exists($self->{'file_counters'}->{$tree_unit_filename}));
    $self->{'file_counters'}->{$tree_unit_filename}++;
    print STDERR "Page $tree_unit "
     .Texinfo::Structuring::root_or_external_element_cmd_texi($tree_unit)
     .": $tree_unit_filename($self->{'file_counters'}->{$tree_unit_filename})\n"
              if ($self->get_conf('DEBUG'));
  }
}

sub create_destination_directory($$$)
{
  my $self = shift;
  my $destination_directory_path = shift;
  my $destination_directory_name = shift;

  if (defined($destination_directory_path)
      and ! -d $destination_directory_path) {
    if (!mkdir($destination_directory_path, oct(755))) {
      $self->document_error($self, sprintf(__(
                                "could not create directory `%s': %s"),
                                   $destination_directory_name, $!));
      return 0;
    }
  }
  return 1;
}


#############################################################
# useful methods for Converters.

# determine the default, with $INIT_CONF if set, or the default common
# to all the converters
sub _command_init($$)
{
  my $global_command = shift;
  my $init_conf = shift;
  if (exists($Texinfo::Common::document_settable_at_commands{$global_command})) {
    if (defined($init_conf->{$global_command})) {
      return $init_conf->{$global_command};
    } elsif (defined($Texinfo::Common::document_settable_at_commands{$global_command})) {
      return $Texinfo::Common::document_settable_at_commands{$global_command};
    }
  }
}

# $COMMANDS_LOCATION is 'before', 'last', 'preamble' or 'preamble_or_first'
# 'before' means setting to the values before the document commands
# (defaults and command-line).
# 'preamble' means setting sequentially to the values in the preamble.
# 'preamble_or_first'  means setting to the first value for the command
# in the document if the first command is not in the preamble, else set
# sequentially to the values in the preamble.
# 'last' means setting to the last value for the command in the document.
#
# Notice that the only effect is to use set_conf (directly or through
# set_global_document_command), no @-commands setting side effects are done
# and associated customization variables are not set/reset either.
sub set_global_document_commands($$;$)
{
  my $self = shift;
  my $commands_location = shift;
  my $selected_commands = shift;

  my $init_conf;
  if (defined($self->{'output_init_conf'})) {
    # use in priority the initial customization per output
    $init_conf = $self->{'output_init_conf'};
  } else {
    $init_conf = $self->{'converter_init_conf'};
  }

  if (not defined($selected_commands)) {
    $selected_commands = [keys(%Texinfo::Common::document_settable_at_commands)];
  }
  if ($commands_location eq 'before') {
    foreach my $global_command (@{$selected_commands}) {
      # for commands not appearing in the document, this should set the
      # same value, the converter initialization value
      $self->set_conf($global_command, _command_init($global_command, $init_conf));
      # NOTE if the variable is set from an handler, or in the converter after
      # $init_conf was set, but before starting the conversion, it is ignored here
      # and the $init_conf value is set.  The previously set value could be
      # in $self->get_conf(), but what is available from $self->get_conf() could
      # also be a value set by a previous call of set_global_document_commands.
      # There is no easy way to deal with this issue, other than making sure that
      # a customization value that is expected to be set early is set in $init_conf.
    }
  } else {
    foreach my $global_command (@{$selected_commands}) {
      if ($self->get_conf('DEBUG')) {
        print STDERR "SET_global($commands_location) $global_command\n";
      }
      my $element = Texinfo::Common::set_global_document_command($self,
               $self->{'global_commands'}, $global_command, $commands_location);
      if (not defined($element)) {
        # commands not appearing in the document, this should set the
        # same value, the converter initialization value
        # the NOTE above in 'before' holds here too.
        $self->set_conf($global_command,
                        _command_init($global_command, $init_conf));
      }
    }
  }
}

sub present_bug_message($$;$)
{
  my $self = shift;
  my $message = shift;
  my $current = shift;

  my $line_message = '';
  my $current_element_message = '';
  if ($current) {
    if ($current->{'source_info'}) {
      my $source_info = $current->{'source_info'};
      my $file = $source_info->{'file_name'};
      $line_message
        = "in: $source_info->{'file_name'}:$source_info->{'line_nr'}";
      if ($source_info->{'macro'} ne '') {
        $line_message .= " (possibly involving $source_info->{'macro'})";
      }
      $line_message .= "\n";
    }
    if ($current) {
      $current_element_message = "current: ".
        Texinfo::Common::debug_print_element($current);
    }
  }
  my $additional_information = '';
  if ($line_message.$current_element_message ne '') {
    $additional_information = "Additional information:\n".
       $line_message.$current_element_message;
  }
  warn "You found a bug: $message\n\n".$additional_information;
}

# Reverse the decoding of the file name from the input encoding.
sub encoded_input_file_name($$)
{
  my $self = shift;
  my $file_name = shift;

  my $encoding;
  my $input_file_name_encoding = $self->get_conf('INPUT_FILE_NAME_ENCODING');
  if ($input_file_name_encoding) {
    $encoding = $input_file_name_encoding;
  } elsif ($self->get_conf('DOC_ENCODING_FOR_INPUT_FILE_NAME')) {
    $encoding = $self->{'parser_info'}->{'input_perl_encoding'}
      if ($self->{'parser_info'}
        and defined($self->{'parser_info'}->{'input_perl_encoding'}));
  } else {
    $encoding = $self->get_conf('LOCALE_ENCODING');
  }

  return Texinfo::Common::encode_file_name($file_name, $encoding);
}

# A wrapper around Texinfo::Utils::encoded_output_file_name() that
# can be called in converters through an objet oriented syntax.
sub encoded_output_file_name($$)
{
  my $self = shift;
  my $file_name = shift;
  return Texinfo::Convert::Utils::encoded_output_file_name($self, $file_name);
}

sub txt_image_text($$$)
{
  my ($self, $element, $basefile) = @_;

  my ($text_file_name, $file_name_encoding)
    = $self->encoded_input_file_name($basefile.'.txt');

  my $txt_file = Texinfo::Common::locate_include_file($self, $text_file_name);
  if (!defined($txt_file)) {
    return undef;
  } else {
    my $filehandle = do { local *FH };
    if (open ($filehandle, $txt_file)) {
      my $enc = $element->{'extra'}->{'input_perl_encoding'};
      binmode($filehandle, ":encoding($enc)")
        if ($enc);
      my $result = '';
      my $max_width = 0;
      while (<$filehandle>) {
        my $width = Texinfo::Convert::Unicode::string_width($_);
        if ($width > $max_width) {
          $max_width = $width;
        }
        $result .= $_;
      }
      # remove last end of line
      chomp ($result);
      if (!close ($filehandle)) {
        $self->document_warn($self,
           sprintf(__("error on closing image text file %s: %s"),
                                     $txt_file, $!));
      }
      return ($result, $max_width);
    } else {
      $self->line_warn($self,
                  sprintf(__("\@image file `%s' unreadable: %s"),
                               $txt_file, $!), $element->{'source_info'});
    }
  }
  return undef;
}


sub float_type_number($$)
{
  my $self = shift;
  my $float = shift;

  my $type;
  if ($float->{'extra'}->{'type'}
      and $float->{'extra'}->{'type'}->{'normalized'} ne '') {
    $type = {'contents' => $float->{'extra'}->{'type'}->{'content'}};
  }

  my $tree;
  if ($type) {
    if (defined($float->{'structure'}->{'float_number'})) {
      $tree = $self->gdt("{float_type} {float_number}",
          {'float_type' => $type,
            'float_number' => $float->{'structure'}->{'float_number'}});
    } else {
      $tree = $self->gdt("{float_type}",
          {'float_type' => $type});
    }
  } elsif (defined($float->{'structure'}->{'float_number'})) {
    $tree = $self->gdt("{float_number}",
       {'float_number' => $float->{'structure'}->{'float_number'}});
  }
  return $tree;
}

sub float_name_caption($$)
{
  my $self = shift;
  my $element = shift;

  my $caption;
  if ($element->{'extra'}->{'caption'}) {
    $caption = $element->{'extra'}->{'caption'};
  } elsif ($element->{'extra'}->{'shortcaption'}) {
    $caption = $element->{'extra'}->{'shortcaption'};
  }
  #if ($self->get_conf('DEBUG')) {
  #  my $caption_texi =
  #    Texinfo::Convert::Texinfo::convert_to_texinfo({ 'contents' => $caption->{'contents'}});
  #  print STDERR "  CAPTION: $caption_texi\n";
  #}
  my $type;
  if ($element->{'extra'}->{'type'}->{'normalized'} ne '') {
    $type = {'contents' => $element->{'extra'}->{'type'}->{'content'}};
  }

  my $prepended;
  if ($type) {
    if ($caption) {
      if ($element->{'structure'}
          and defined($element->{'structure'}->{'float_number'})) {
        $prepended = $self->gdt('{float_type} {float_number}: ',
            {'float_type' => $type,
             'float_number' => $element->{'structure'}->{'float_number'}});
      } else {
        $prepended = $self->gdt('{float_type}: ',
          {'float_type' => $type});
      }
    } else {
      if ($element->{'structure'}
          and defined($element->{'structure'}->{'float_number'})) {
        $prepended = $self->gdt("{float_type} {float_number}\n",
            {'float_type' => $type,
              'float_number' => $element->{'structure'}->{'float_number'}});
      } else {
        $prepended = $self->gdt("{float_type}\n",
            {'float_type' => $type});
      }
    }
  } elsif ($element->{'structure'}
           and defined($element->{'structure'}->{'float_number'})) {
    if ($caption) {
      $prepended = $self->gdt('{float_number}: ',
          {'float_number' => $element->{'structure'}->{'float_number'}});
    } else {
      $prepended = $self->gdt("{float_number}\n",
           {'float_number' => $element->{'structure'}->{'float_number'}});
    }
  }
  return ($caption, $prepended);
}

# This is used when the formatted text has no comment nor new line, but
# one want to add the comment or new line from the original arg
sub format_comment_or_return_end_line($$)
{
  my $self = shift;
  my $element = shift;

  my $end_line;

  my $comment = $element->{'args'}->[-1]->{'extra'}->{'comment_at_end'}
    if $element->{'args'} and $element->{'args'}->[-1]->{'extra'};

  if ($comment) {
    $end_line = $self->convert_tree($comment);
  } elsif ($element->{'args'} and $element->{'args'}->[-1]->{'extra'}
      and $element->{'args'}->[-1]->{'extra'}->{'spaces_after_argument'}) {
    my $text = $element->{'args'}->[-1]->{'extra'}->{'spaces_after_argument'};
    if (chomp($text)) {
      $end_line = "\n";
    } else {
      $end_line = '';
    }
  } else {
    $end_line = '';
  }
  return $end_line;
}

sub table_item_content_tree($$$)
{
  my $self = shift;
  my $element = shift;
  my $contents = shift;

  my $table_item_tree = {'parent' => $element};

  return $table_item_tree
    if (!defined($contents));

  my $table_command = $element->{'parent'}->{'parent'}->{'parent'};
  if ($table_command->{'extra'}
     and $table_command->{'extra'}->{'command_as_argument'}) {
    my $command_as_argument
      = $table_command->{'extra'}->{'command_as_argument'};
    my $command = {'cmdname' => $command_as_argument->{'cmdname'},
               'source_info' => $element->{'source_info'},
               'parent' => $table_item_tree };
    if ($table_command->{'extra'}->{'command_as_argument_kbd_code'}) {
      $command->{'extra'} = {} if (!$command->{'extra'});
      $command->{'extra'}->{'code'} = 1;
    }
    if ($command_as_argument->{'type'} eq 'definfoenclose_command') {
      $command->{'type'} = $command_as_argument->{'type'};
      $command->{'extra'} = {} if (!$command->{'extra'});
      $command->{'extra'}->{'begin'} = $command_as_argument->{'extra'}->{'begin'};
      $command->{'extra'}->{'end'} = $command_as_argument->{'extra'}->{'end'};
    }
    my $arg = {'type' => 'brace_command_arg',
               'contents' => $contents,
               'parent' => $command,};
    $command->{'args'} = [$arg];
    $contents = [$command];
  }
  $table_item_tree->{'contents'} = $contents;
  return $table_item_tree;
}

sub convert_accents($$$;$)
{
  my $self = shift;
  my $accent = shift;
  my $format_accents = shift;
  my $in_upper_case = shift;

  my ($contents, $stack)
      = Texinfo::Convert::Utils::find_innermost_accent_contents($accent);
  my $result = $self->convert_tree({'contents' => $contents});

  my $encoded;
  if ($self->get_conf('ENABLE_ENCODING')) {
    $encoded = Texinfo::Convert::Unicode::encoded_accents($self, $result, $stack,
                                       $self->get_conf('OUTPUT_ENCODING_NAME'),
                                       $format_accents,
                                       $in_upper_case);
  }
  if (!defined($encoded)) {
    foreach my $accent_command (reverse(@$stack)) {
      $result = &$format_accents ($self, $result, $accent_command,
                                  $in_upper_case);
    }
    return $result;
  } else {
    return $encoded;
  }
}

# index sub-entries specified with @subentry, separated by commas.
sub comma_index_subentries_tree {
  my ($self, $entry) = @_;

  my @contents;
  my $tmp = $entry->{'entry_element'};
  while ($tmp->{'extra'} and $tmp->{'extra'}->{'subentry'}) {
    $tmp = $tmp->{'extra'}->{'subentry'};
    push @contents, {'text' => ', '}, $tmp->{'args'}->[0];
  }
  if (scalar(@contents)) {
    return {'contents' => \@contents};
  }
  return undef;
}

# This method allows to count words in elements and returns an array
# and a text already formatted.
sub sort_element_counts($$;$$)
{
  my $converter =  shift;
  my $tree = shift;
  my $use_sections = shift;
  my $count_words = shift;

  my $elements;
  if ($use_sections) {
    $elements = Texinfo::Structuring::split_by_section($tree);
  } else {
    $elements = Texinfo::Structuring::split_by_node($tree);
  }

  if (!$elements) {
    @$elements = ($tree);
  } elsif (scalar(@$elements) >= 1
           and not $elements->[0]->{'extra'}->{'unit_command'}) {
    shift @$elements;
  }

  my $max_count = 0;
  my @name_counts_array;

  require Texinfo::Convert::Texinfo;
  foreach my $element (@$elements) {
    my $name = 'UNNAMED tree element';
    if ($element->{'extra'} and $element->{'extra'}->{'unit_command'}) {
      my $command = $element->{'extra'}->{'unit_command'};
      if ($command->{'cmdname'} eq 'node') {
        $name = Texinfo::Convert::Texinfo::convert_to_texinfo(
    {'contents' => $command->{'extra'}->{'nodes_manuals'}->[0]->{'node_content'}});
      } else {
        $name = "\@$command->{'cmdname'}"
          .Texinfo::Convert::Texinfo::convert_to_texinfo($command->{'args'}->[0]);
      }
    }
    chomp($name);
    my $count;
    my $converted_element = $converter->convert_tree($element);
    if ($count_words) {
      my @res = split /\W+/, $converted_element;
      $count = scalar(@res);
    } else {
      my @res = split /^/, $converted_element;
      $count = scalar(@res);
    }
    push @name_counts_array, [$count, $name];
    if ($count > $max_count) {
      $max_count = $count;
    }
  }

  my @sorted_name_counts_array = sort {$a->[0] <=> $b->[0]} @name_counts_array;
  @sorted_name_counts_array = reverse(@sorted_name_counts_array);

  my $max_length = length($max_count);
  my $result = '';
  foreach my $sorted_count (@sorted_name_counts_array) {
    $result .=  sprintf("%${max_length}d  $sorted_count->[1]\n",
                        $sorted_count->[0]);
  }
  return (\@sorted_name_counts_array, $result);
}


########################################################################
# XML related methods and variables that may be used in different
# XML Converters.

my $xml_numeric_entity_mdash = '&#'.hex('2014').';';
my $xml_numeric_entity_ndash = '&#'.hex('2013').';';
my $xml_numeric_entity_ldquo = '&#'.hex('201C').';';
my $xml_numeric_entity_rdquo = '&#'.hex('201D').';';
my $xml_numeric_entity_lsquo = '&#'.hex('2018').';';
my $xml_numeric_entity_rsquo = '&#'.hex('2019').';';

sub xml_format_text_with_numeric_entities($$)
{
  my $self = shift;
  my $text = shift;
 
  $text =~ s/``/$xml_numeric_entity_ldquo/g;
  $text =~ s/\'\'/$xml_numeric_entity_rdquo/g;
  $text =~ s/`/$xml_numeric_entity_lsquo/g;
  $text =~ s/\'/$xml_numeric_entity_rsquo/g;
  $text =~ s/---/$xml_numeric_entity_mdash/g;
  $text =~ s/--/$xml_numeric_entity_ndash/g;

  return $text;
}

sub xml_protect_text($$)
{
  my $self = shift;
  my $text = shift;
  if (!defined($text)) {
    cluck;
  }
  $text =~ s/&/&amp;/g;
  $text =~ s/</&lt;/g;
  $text =~ s/>/&gt;/g;
  $text =~ s/\"/&quot;/g;
  return $text;
}

# 'today' is not set here.
our %xml_text_entity_no_arg_commands_formatting = (
               'TeX'          => 'TeX',
               'LaTeX'          => 'LaTeX',
               'bullet'       => '&bull;',
               'copyright'    => '&copy;',
               'registeredsymbol'   => '&reg;',
               'dots'         => '&hellip;',
               'enddots'      => '...',
               'equiv'        => '&equiv;',
               # in general the following is not used since error
               # appears in 'translated_commands'
               'error'        => 'error--&gt;',
               'expansion'    => '&rarr;',
               'arrow'        => '&rarr;',
               'click'        => '&rarr;',
               'minus'        => '&minus;',
               'point'        => '&lowast;',
               'print'        => '-|',
               'result'       => '&rArr;',
               'aa'           => '&aring;',
               'AA'           => '&Aring;',
               'ae'           => '&aelig;',
               'oe'           => '&oelig;', # &oelig; not in html 3.2
               'AE'           => '&AElig;',
               'OE'           => '&OElig;', # &OElig; not in html 3.2
               'o'            => '&oslash;',
               'O'            => '&Oslash;',
               'ss'           => '&szlig;',
               'DH'           => '&ETH;',
               'dh'           => '&eth;',
               'TH'           => '&THORN;',
               'th'           => '&thorn;',
               'l'            => '&#322;',
               'L'            => '&#321;',
               'exclamdown'   => '&iexcl;',
               'questiondown' => '&iquest;',
               'pounds'       => '&pound;',
               'ordf'         => '&ordf;',
               'ordm'         => '&ordm;',
               'comma'        => ',',
               'atchar'       => '@',
               'ampchar'      => '&amp;',
               'lbracechar'   => '{',
               'rbracechar'   => '}',
               'backslashchar' => '\\',
               'hashchar' => '#',
               'euro'         => '&euro;',
               'geq'          => '&ge;',
               'leq'          => '&le;',
               'tie'          => '&nbsp;',
               'textdegree'          => '&deg;',
               'quotedblleft'          => '&ldquo;',
               'quotedblright'          => '&rdquo;',
               'quoteleft'          => '&lsquo;',
               'quoteright'          => '&rsquo;',
               'quotedblbase'          => '&bdquo;',
               'quotesinglbase'          => '&sbquo;',
               'guillemetleft'          => '&laquo;',
               'guillemetright'          => '&raquo;',
               'guillemotleft'          => '&laquo;',
               'guillemotright'          => '&raquo;',
               'guilsinglleft'          => '&lsaquo;',
               'guilsinglright'          => '&rsaquo;',
);

foreach my $no_brace_command (keys(%Texinfo::Common::nobrace_symbol_text)) {
  $xml_text_entity_no_arg_commands_formatting{$no_brace_command}
    = $Texinfo::Common::nobrace_symbol_text{$no_brace_command};
}

$xml_text_entity_no_arg_commands_formatting{'&'} = '&amp;';

sub xml_comment($$)
{
  my $self = shift;
  my $text = shift;
  chomp $text;
  $text =~ s/--+/-/go;
  return '<!--' . $text . ' -->' . "\n";
}

our %xml_accent_entities = (
          '"',  'uml',
          '~',  'tilde',
          '^',  'circ',
          '`',  'grave',
          "'", 'acute',
          ",", 'cedil',
          'ringaccent', 'ring',
          'ogonek', 'ogon',
          'dotless', 'nodot',
         );

our %xml_accent_text_with_entities = (
      'ringaccent' => 'aA',
      "'"          => 'aeiouyAEIOUY',
      ','          => 'cC',
      '^'          => 'aeiouAEIOU',
      '`'          => 'aeiouAEIOU',
      '~'          => 'nNaoAO',
      '"'          => 'aeiouyAEIOU',
      'dotless'    => 'i',
# according to http://www2.lib.virginia.edu/small/vhp/download/ISO.txt
# however this doesn't seems to work in firefox
#      'ogonek'     => 'aeiuAEIU',
);

sub xml_numeric_entity_accent($$)
{
  my $accent = shift;
  my $text = shift;

  if (exists($Texinfo::Convert::Unicode::unicode_accented_letters{$accent})
      and exists($Texinfo::Convert::Unicode::unicode_accented_letters{$accent}->{$text})) {
    return '&#' .
      hex($Texinfo::Convert::Unicode::unicode_accented_letters{$accent}->{$text}). ';';
  }
  if (exists($Texinfo::Convert::Unicode::unicode_diacritics{$accent})) {
    my $diacritic = '&#'
       .hex($Texinfo::Convert::Unicode::unicode_diacritics{$accent}). ';';
    if ($accent ne 'tieaccent') {
      return $text . $diacritic;
    } else {
      # tieaccent diacritic is naturally and correctly composed
      # between two characters
      my $remaining_text = $text;
      # we consider that letters are either characters or entities
      if ($remaining_text =~ s/^([\p{L}\d]|&[a-zA-Z0-9]+;)([\p{L}\d]|&[a-zA-Z0-9]+;)(.*)$/$3/) {
        return $1.$diacritic.$2 . $remaining_text;
      } else {
        return $text . $diacritic;
      }
    }
  }
  return undef;
}

sub xml_accent($$$;$$$)
{
  my $self = shift;
  my $text = shift;
  my $command = shift;
  my $in_upper_case = shift;
  my $use_numeric_entities = shift;
  my $accent = $command->{'cmdname'};
  
  if ($in_upper_case and $text =~ /^\w$/) {
    $text = uc ($text);
  }

  # do not return a dotless i or j as such if it is further composed
  # with an accented letter, return the letter as is
  if ($accent eq 'dotless') {
    if ($Texinfo::Convert::Unicode::unicode_accented_letters{$accent}
        and exists($Texinfo::Convert::Unicode::unicode_accented_letters{$accent}->{$text})
        and ($command->{'parent'}
             and $command->{'parent'}->{'parent'}
             and $command->{'parent'}->{'parent'}->{'cmdname'}
             and $Texinfo::Convert::Unicode::unicode_accented_letters{$command->{'parent'}
                                        ->{'parent'}->{'cmdname'}})) {
      return $text;
    }
  }
 
  if ($use_numeric_entities) {
    my $formatted_accent = xml_numeric_entity_accent($accent, $text);
    if (defined($formatted_accent)) {
      return $formatted_accent;
    }
  } else {
    return "&${text}$xml_accent_entities{$accent};"
      if (defined($xml_accent_entities{$accent})
          and defined($xml_accent_text_with_entities{$accent})
          and ($text =~ /^[$xml_accent_text_with_entities{$accent}]$/));
    my $formatted_accent = xml_numeric_entity_accent($accent, $text);
    if (defined($formatted_accent)) {
      return $formatted_accent;
    }
  }

  # should never happen, there are diacritics for every accent command
  return $text . '&lt;' if ($accent eq 'v');
  # FIXME it is not possible to call xml_protect_text since what is in $text
  # may already be xml.  But this means that each time ascii_accent changes
  # it should be changed here too.
  return Texinfo::Convert::Text::ascii_accent($text, $command);
}

sub _xml_numeric_entities_accent($$$;$)
{
  my $self = shift;
  my $text = shift;
  my $command = shift;
  my $in_upper_case = shift;

  return xml_accent($self, $text, $command, $in_upper_case, 1);
}

sub xml_accents($$;$)
{
  my $self = shift;
  my $accent = shift;
  my $in_upper_case = shift;

  my $format_accents;
  if ($self->get_conf('USE_NUMERIC_ENTITY')) {
    $format_accents = \&_xml_numeric_entities_accent;
  } else {
    $format_accents = \&xml_accent;
  }
  
  return $self->convert_accents($accent, $format_accents, $in_upper_case);
}

1;

__END__

=head1 NAME

Texinfo::Convert::Converter - Parent class for Texinfo tree converters

=head1 SYNOPSIS

  package Texinfo::Convert::MyConverter;

  use Texinfo::Convert::Converter;
  @ISA = qw(Texinfo::Convert::Converter);

  sub converter_defaults ($$) {
    return %myconverter_defaults;
  }
  sub converter_initialize($) {
    my $self = shift;
    $self->{'document_context'} = [{}];
  }

  sub convert($$) {
    ...
  }
  sub convert_tree($$) {
    ...
  }
  sub output($$) {
    ...
  }

  # end of Texinfo::Convert::MyConverter

  my $converter = Texinfo::Convert::MyConverter->converter(
                                               {'parser' => $parser});
  $converter->output($texinfo_tree);

=head1 NOTES

The Texinfo Perl module main purpose is to be used in C<texi2any> to convert
Texinfo to other formats.  There is no promise of API stability.

=head1 DESCRIPTION

C<Texinfo::Convert::Converter> is a super class that can be used to
simplify converters initialization.  The class also provide some
useful methods.

In turn, the converter should define some methods.  Two are
optional, C<converter_defaults>, C<converter_initialize> and
used for initialization, to give information to C<Texinfo::Convert::Converter>.

X<C<convert_tree>> X<C<output>> X<C<convert>>
The C<convert_tree> method is mandatory and should convert portions of Texinfo
tree.  The C<output> method is used by converters as entry point for conversion
to a file with headers and so on.  Although it is is not called from other
modules, it should in general be implemented by converters. C<output> is called
from C<texi2any>.  C<convert> is not required, but customarily used by
converters as entry point for a conversion of a whole Texinfo tree without
the headers done when outputting to a file.

Existing backends may be used as examples that implement those
methods.  C<Texinfo::Convert::Texinfo> together with
C<Texinfo::Convert::PlainTexinfo>, as well as
C<Texinfo::Convert::TextContent> are trivial examples.
C<Texinfo::Convert::Text> is less trivial, although still simple,
while C<Texinfo::Convert::DocBook> is a real converter
that is also not too complex.

The documentation of L<Texinfo::Common>, L<Texinfo::Convert::Unicode>
and L<Texinfo::Report> describes modules or additional function
that may be useful for backends, while the parsed Texinfo tree is
described in L<Texinfo::Parser>.


=head1 METHODS

=head2 Initialization

X<C<converter>>
X<C<Texinfo::Convert::Converter> initialization>

A module subclassing C<Texinfo::Convert::Converter> is created by calling
the C<converter> method that should be inherited from
C<Texinfo::Convert::Converter>.

=over

=item $converter = MyConverter->converter($options)

The I<$options> hash reference holds options for the converter.  In
this option hash reference a L<parser object|Texinfo::Parser>
may be associated with the I<parser> key.  The other options
are Texinfo customization options and a few other options that can
be passed to the converter. Most of the customization options
are described in the Texinfo manual.
Those customization options, when appropriate, override the document content.
B<TODO what about the other options (all are used in converters;
'structuring' is available in HTML $converter-E<gt>get_info()?>
The parser should not be available directly anymore after getting the
associated information. B<TODO document this associated information
('parser_info', 'indices_information', 'floats'..., most available
in HTML converter, either through $converter-E<gt>get_info() or label_command())>

The C<converter> function returns a converter object (a blessed hash
reference) after checking the options and performing some initializations,
especially when a parser is given among the options.  The converter is
also initialized as a L<Texinfo::Report>.

=back

To help with these initializations, the modules subclassing C<Texinfo::Convert::Converter>
can define two methods:

=over

=item %defaults = $converter->converter_defaults($options)
X<C<converter_defaults>>

The module can provide a defaults hash for converter customization options.
The I<$options> hash reference holds options for the converter.

=item converter_initialize
X<C<converter_initialize>>

This method is called at the end of the C<Texinfo::Convert::Converter>
converter initialization.

=back

=head2 Getting and setting customization variables

C<Texinfo::Convert::Converter> implements a simple interface to
set and retrieve Texinfo customization variables.  Helper
functions from diverse Texinfo modules needing customization
information expect an object implementing C<get_conf> and/or
C<set_conf>.  The converter itself can therefore be used in
such cases.

=over

=item $converter->force_conf($variable_name, $variable_value)
X<C<force_conf>>

Set the Texinfo customization option I<$variable_name> to I<$variable_value>.
This should rarely be used, but the purpose of this method is to be able
to revert a customization that is always wrong for a given output
format, like the splitting for example.

=item $converter->get_conf($variable_name)
X<C<get_conf>>

Returns the value of the Texinfo customization variable I<$variable_name>.

=item $converter->set_conf($variable_name, $variable_value)
X<C<set_conf>>

Set the Texinfo customization option I<$variable_name> to I<$variable_value> if
not set as a converter option.

=back

=head2 Conversion to XML

Some C<Texinfo::Convert::Converter> methods target conversion to XML.
Most methods take a I<$converter> as argument to get some
information and use methods for error reporting.

=over

=item $formatted_text = $converter->xml_format_text_with_numeric_entities($text)
X<C<xml_format_text_with_numeric_entities>>

Replace quotation marks and hyphens used to represent dash in
Texinfo text with numeric XML entities.

=item $protected_text = $converter->xml_protect_text($text)
X<C<xml_protect_text>>

Protect special XML characters (&, E<lt>, E<gt>, ") of I<$text>.

=item $comment = $converter->xml_comment($text)
X<C<xml_comment>>

Returns an XML comment for I<$text>.

=item $result = xml_accent($text, $accent_command, $in_upper_case, $use_numeric_entities)
X<C<xml_accent>>

I<$text> is the text appearing within an accent command.  I<$accent_command>
should be a Texinfo tree element corresponding to an accent command taking
an argument.  I<$in_upper_case> is optional, and, if set, the text is put
in upper case.  The function returns the accented letter as XML named entity
if possible, falling back to numeric entities if there is no named entity
and to an ASCII transliteration as last resort.  I<$use_numeric_entities>
is optional.  If set, numerical entities are used instead of named entities
if possible.

=item $result = $converter->xml_accents($accent_command, $in_upper_case)
X<C<xml_accents>>

I<$accent_command> is an accent command, which may have other accent
commands nested.  If I<$in_upper_case> is set, the result should be
upper cased.  The function returns the accents formatted as XML.

=item $result = xml_numeric_entity_accent($accent_command_name, $text)
X<C<xml_numeric_entity_accent>>

I<$accent_command_name> is the name of an accent command.  I<$text> is the text
appearing within the accent command.  Returns the accented letter as XML numeric
entity, or C<undef> is there is no such entity.

=back

=head2 Helper methods

The module provides methods that may be useful for converter.
Most methods take a I<$converter> as argument to get some
information and use methods for error reporting, see L<Texinfo::Report>.  Also
to translate strings, see L<Texinfo::Translations>.  For
useful methods that need a converter optionally and can be used
in converters that do not inherit from C<Texinfo::Convert::Converter>,
see L<Texinfo::Convert::Utils>.

=over

=item $contents_array = $converter->comma_index_subentries_tree($entry)
X<C<comma_index_subentries_tree>>

I<$entry> is a Texinfo tree index entry element. The function sets up
an array with the C<@subentry> contents, separated by commas.  The
array reference is returned as I<$contents_array>, or C<undef> if there
is no such content.

=item $result = $converter->convert_accents($accent_command, \&format_accents, $in_upper_case)
X<C<convert_accents>>

I<$accent_command> is an accent command, which may have other accent
commands nested.  The function returns the accents formatted either
as encoded letters, or formatted using I<\&format_accents>.
If I<$in_upper_case> is set, the result should be uppercased.

=item $result = $converter->convert_document_sections($root, $file_handler)
X<C<convert_document_sections>>

This method splits the I<$root> Texinfo tree at sections and
calls C<convert_tree> on the elements.  If the optional I<$file_handler>
is given in argument, the result are output in I<$file_handler>, otherwise
the resulting string is returned.

=item $succeeded = $converter->create_destination_directory($destination_directory_path, $destination_directory_name)
X<C<create_destination_directory>>

Create destination directory I<$destination_directory_path>.
I<$destination_directory_path> should be a binary string, while
I<$destination_directory_name> should be a character string, that can be used in
error messages.  I<$succeeded> is true if the creation was successful or
uneeded, false otherwise.

=item ($output_file, $destination_directory, $output_filename, $document_name, $input_basefile) = $converter->determine_files_and_directory($output_format)
X<C<determine_files_and_directory>>

Determine output file and directory, as well as names related to files.  The
result depends on the presence of C<@setfilename>, on the Texinfo input file
name, and on customization options such as C<OUTPUT>, C<SUBDIR> or C<SPLIT>,
as described in the Texinfo manual.  I<$output_format> is optional.  If it is
not set the current output format, if defined, is used instead.  If not an
empty string, C<_$output_format> is prepended to the default directory name.

I<$output_file> is mainly relevant when not split and should be used as the
output file name.  In general, if not split and I<$output_file> is an empty
string, it means that text should be returned by the converter instead of being
written to an output file.  This is used in the test suite.
I<$destination_directory> is either the directory I<$output_file> is in, or if
split, the directory where the files should be created.  I<$output_filename>
is, in general, the file name portion of I<$output_file> (without directory)
but can also be set based on C<@setfilename>, in particular when
I<$output_file> is an empty string. I<$document_name> is I<$output_filename>
without extension.  I<$input_basefile> is based on the input texinfo file name,
with the file name portion only (without directory).

The strings returned are text strings.

=item ($encoded_name, $encoding) = $converter->encoded_input_file_name($character_string_name)

=item ($encoded_name, $encoding) = $converter->encoded_output_file_name($character_string_name)
X<C<encoded_input_file_name>> X<C<encoded_output_file_name>>

Encode I<$character_string_name> in the same way as other file name are
encoded in the converter, based on customization variables, and possibly
on the input file encoding.  Return the encoded name and the encoding
used to encode the name.  The C<encoded_input_file_name> and
C<encoded_output_file_name> functions use different customization variables to
determine the encoding.

Note that C<encoded_output_file_name> is a wrapper around the
function with the same name in L<<< Texinfo::Convert::Utils::encoded_output_file_name|Texinfo::Convert::Utils/($encoded_name, $encoding) = $converter->encoded_output_file_name($converter, $character_string_name) >>>.

=item ($caption, $prepended) = $converter->float_name_caption($float)
X<C<float_name_caption>>

I<$float> is a texinfo tree C<@float> element.  This function
returns the caption element that should be used for the float formatting
and the I<$prepended> texinfo tree combining the type and label
of the float.

=item $tree = $converter->float_type_number($float)
X<C<float_type_number>>

I<$float> is a texinfo tree C<@float> element.  This function
returns the type and number of the float as a texinfo tree with
translations.

=item $end_line = $converter->format_comment_or_return_end_line($element)
X<C<format_comment_or_return_end_line>>

Format comment at end of line or return the end of line associated with
the element.  In many cases, converters ignore comments and output is
better formatted with new lines added independently of the presence
of newline or comment in the initial Texinfo line, so most converters
are better off not using this method.

=item $filename = sub $converter->node_information_filename($node_info)
X<C<node_information_filename>>

Returns the normalized file name corresponding to the I<$node_info>
node element tree C<extra> field.

=item ($normalized_name, $filename) = $converter->normalized_sectioning_command_filename($element)
X<C<normalized_sectioning_command_filename>>

Returns a normalized name I<$normalized_name> corresponding to a sectioning
command tree element I<$element>, expanding the command argument using
transliteration and characters protection.  Also returns I<$filename>
the corresponding filename based on I<$normalized_name> taking into
account additional constraint on file names and adding a file extension.

=item $converter->present_bug_message($message, $element)
X<C<present_bug_message>>

Show a bug message using I<$message> text.  Use information on
I<$element> tree element if given in argument.

=item $converter->set_global_document_commands($commands_location, $selected_commands)
X<C<set_global_document_commands>>

Set the Texinfo customization options for @-commands.  I<$selected_commands>
is an optional array reference containing the @-commands set, if not given
all the global informative @-commands are set.  I<$commands_location> specifies
where in the document the value should be taken from. The possibilities are:

=over

=item before

Set to the values before document conversion, from defaults and command-line.

=item last

Set to the last value for the command.

=item preamble

Set sequentially to the values in the Texinfo preamble.

=item preamble_or_first

Set to the first value of the command if the first command is not
in the Texinfo preamble, else set as with I<preamble>,
sequentially to the values in the Texinfo preamble.

=back

Notice that the only effect of this function is to set a customization
variable value, no @-command side effects are run, no associated customization
variables are set.

For more information on the function used to set the value for each of the command, see
L<Texinfo::Common set_global_document_command|Texinfo::Common/$element = set_global_document_command($customization_information, $global_commands_information, $cmdname, $command_location)>.

=item $table_item_tree = $converter->table_item_content_tree($element, $contents)
X<C<table_item_content_tree>>

I<$element> should be an C<@item> or C<@itemx> tree element,
I<$contents> should be corresponding texinfo tree contents.
Returns a tree in which the @-command in argument of C<@*table>
of the I<$element> has been applied to I<$contents>.

=item $result = $converter->top_node_filename($document_name)
X<C<top_node_filename>>

Returns a file name for the Top node file using either C<TOP_FILE>
customization value, or C<EXTENSION> customization value and I<$document_name>.

=back

Finally, there is:

=over

=item $result = $converter->output_internal_links()
X<C<output_internal_links>>

At this level, the method just returns undef.  It is used in the HTML
output, following the C<--internal-links> option of C<texi2any>
specification.

=back

=head1 SEE ALSO

L<Texinfo::Common>, L<Texinfo::Convert::Unicode>, L<Texinfo::Report>,
L<Texinfo::Translations>, L<Texinfo::Convert::Utils> and L<Texinfo::Parser>.

=head1 AUTHOR

Patrice Dumas, E<lt>pertusus@free.frE<gt>

=head1 COPYRIGHT AND LICENSE

Copyright 2011- Free Software Foundation, Inc.  See the source file for
all copyright years.

This library is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation; either version 3 of the License, or (at
your option) any later version.

=cut