File: Reform.pm

package info (click to toggle)
libtext-reform-perl 1.20-5
  • links: PTS, VCS
  • area: main
  • in suites: bookworm, forky, sid, trixie
  • size: 288 kB
  • sloc: perl: 1,261; makefile: 2
file content (1923 lines) | stat: -rw-r--r-- 60,406 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
package Text::Reform;

use strict; use vars qw($VERSION @ISA @EXPORT @EXPORT_OK); use Carp;
use 5.005;
#use version;
$VERSION = '1.20';

require Exporter;

@ISA = qw(Exporter);
@EXPORT = qw( form );
@EXPORT_OK = qw( columns tag break_with break_at break_wrap break_TeX debug );

my @bspecials = qw( [ | ] );
my @lspecials = qw( < ^ > );
my $ljustified = '[<]{2,}[>]{2,}';
my $bjustified = '[[]{2,}[]]{2,}';
my $bsingle    = '~+';
my @specials = (@bspecials, @lspecials);
my $fixed_fieldpat = join('|', ($ljustified, $bjustified,
				$bsingle,
				map { "\\$_\{2,}" } @specials));
my ($lfieldmark, $bfieldmark, $fieldmark, $fieldpat, $decimal);
my $emptyref = '';

sub import
{
	#$decimal = localeconv()->{decimal_point} || '.';
	$decimal = '.';

	my $lnumerical = '[>]+(?:'.quotemeta($decimal).'[<]{1,})';
	my $bnumerical = '[]]+(?:'.quotemeta($decimal).'[[]{1,})';

	$fieldpat = join('|', ($lnumerical, $bnumerical,$fixed_fieldpat));

	$lfieldmark = join '|', ($lnumerical, $ljustified, map { "\\$_\{2}" } @lspecials);
	$bfieldmark = join '|', ($bnumerical, $bjustified, $bsingle, map { "\\$_\{2}" } @bspecials);
	$fieldmark  = join '|', ($lnumerical, $bnumerical,
				 $bsingle,
				 $ljustified, $bjustified,
				 $lfieldmark, $bfieldmark);

	Text::Reform->export_to_level(1, @_);
}

sub carpfirst {
	use vars '%carped';
	my ($msg) = @_;
	return if $carped{$msg}++;
	carp $msg;
}

###### USEFUL TOOLS ######################################

#===== form =============================================#

sub BAD_CONFIG { 'Configuration hash not allowed between format and data' }

sub break_with
{
	my $hyphen = $_[0];
	my $hylen = length($hyphen);
	my @ret;
	sub
	{
		if ($_[2]<=$hylen)
		{
			@ret = (substr($_[0],0,1), substr($_[0],1))
		}
		else
		{
			@ret = (substr($_[0],0,$_[1]-$hylen),
				substr($_[0],$_[1]-$hylen))
		}
		if ($ret[0] =~ /\A\s*\Z/) { return ("",$_[0]); }
		else { return ($ret[0].$hyphen,$ret[1]); }
	}

}

sub break_at {
	my ($hyphen, $opts_ref) = @_;
	my $hylen = length($hyphen);
	my $except = $opts_ref->{except};
	my @ret;
	sub
	{
		my $max = $_[2]-$hylen;
		if ($max <= 0) {
			@ret = (substr($_[0],0,1), substr($_[0],1))
		}
        elsif (defined $except && $_[0] =~ m/\A (.{1,$max}) ($except .*)/xms) {
			@ret = ($1,$2);
        }
        elsif (defined $except && $_[0] =~ m/\A ($except) (.*)/xms) {
			@ret = ($1,$2);
        }
		elsif ($_[0] =~ /\A (.{1,$max}$hyphen) (.*)/xms) {
			@ret = ($1,$2);
		}
		elsif (length($_[0])>$_[2]) {
			@ret = (substr($_[0],0,$_[1]-$hylen).$hyphen,
				substr($_[0],$_[1]-$hylen))
		}
		else {
			@ret = ("",$_[0]);
		}
		if ($ret[0] =~ /\A\s*\Z/) { return ("",$_[0]); }
		else { return @ret; }
	}
}

sub break_wrap
{
	return \&break_wrap unless @_;
	my ($text, $reqlen, $fldlen) = @_;
	if ($reqlen==$fldlen) { $text =~ m/\A(\s*\S*)(.*)/s }
	else                  { ("", $text) }
}

my %hyp;
sub break_TeX
{
	my $file = $_[0] || "";

	croak "Can't find TeX::Hyphen module"
		unless require "TeX/Hyphen.pm";

	$hyp{$file} = TeX::Hyphen->new($file||undef)
			|| croak "Can't open hyphenation file $file"
		unless $hyp{$file};

	return sub {
		for (reverse $hyp{$file}->hyphenate($_[0])) {
			if ($_ < $_[1]) {
				return (substr($_[0],0,$_).'-',
					substr($_[0],$_) );
			}
		}
		return ("",$_[0]);
	}
}

my $debug = 0;
sub _debug { print STDERR @_, "\n" if $debug }
sub debug { $debug = 1; }

sub notempty
{
	my $ne = ${$_[0]} =~ /\S/;
	_debug("\tnotempty('${$_[0]}') = $ne\n");
	return $ne;
}

sub strtod1 {
  my $n=shift;
  my $real_re='((?:[+-]?)(?:(?=[0123456789]|[.])(?:[0123456789]*)(?:(?:[.])(?:[0123456789]{0,}))?)'.
  '(?:(?:[eE])(?:(?:[+-]?)(?:[0123456789]+))|))';
  if ($n=~/^\s*$real_re(.*)$/os) {
    return ($1,length($2 || ''));
  } else {
    return (undef,length($n));
  }
}

sub replace($$$$)   # ($fmt, $len, $argref, $config)
{
	my $ref = $_[2];
	my $text = '';
	my $rem = $_[1];
	my $config = $_[3];
	my $filled = 0;

	if ($config->{fill}) { $$ref =~ s/\A\s*// }
	else		     { $$ref =~ s/\A[ \t]*// }

	my $fmtnum = length $_[0];

	if ($$ref =~ /\S/ && $fmtnum>2)
	{
	NUMERICAL:{
		my ($ilen,$dlen) = map {length} $_[0] =~ m/([]>]+)\Q$decimal\E([[<]+)/;
		my ($num,$unconsumed) = strtod1($$ref);

		if ($unconsumed == length $$ref)
		{
			$$ref =~ s/\s*\S*//;
			redo NUMERICAL if $config->{numeric} =~ m/\bSkipNaN\b/i
				       && $$ref =~ m/\S/;
			$text = '?' x $ilen . $decimal . '?' x $dlen;
			$rem = 0;
			return $text;
		}
		my $formatted = sprintf "%$fmtnum.${dlen}f", $num;
		$text = (length $formatted > $fmtnum)
			? '#' x $ilen . $decimal . '#' x $dlen
			: $formatted;
		$text =~ s/(\Q$decimal\E\d+?)(0+)$/$1 . " " x length $2/e
			unless $config->{numeric} =~ m/\bAllPlaces\b/i
			    || $num =~ /\Q$decimal\E\d\d{$dlen,}$/;
		if ($unconsumed)
		{
			if ($unconsumed == length $$ref)
				{ $$ref =~ s/\A.[^0-9.+-]*// }
			else
				{ substr($$ref,0,-$unconsumed) = ""}
		}
		else            { $$ref = "" }
		$rem = 0;
	    }
	}
	else
	{
		while ($$ref =~ /\S/)
		{
			if (!$config->{fill} && $$ref=~s/\A[ \t]*\n//)
				{ $filled = 2; last }
			last unless $$ref =~ /\A(\s*)(\S+)(.*)\z/s;
			my ($ws, $word, $extra) = ($1,$2,$3);
			my $nonnl = $ws =~ /[^\n]/;
			$ws =~ s/\n/$nonnl? "" : " "/ge if $config->{fill};
			my $lead = ($config->{squeeze} ? ($ws ? " " : "") : $ws);
			my $match = $lead . $word;
			_debug "Extracted [$match]";
			last if $text && $match =~ /\n/;
			my $len1 = length($match);
			if ($len1 <= $rem)
			{
				_debug "Accepted [$match]";
				$text .= $match;
				$rem  -= $len1;
				$$ref = $extra;
			}
			else
			{
				_debug "Need to break [$match]";
				# was: if ($len1 > $_[1] and $rem-length($lead)>$config->{minbreak})
				if ($rem-length($lead)>$config->{minbreak})
				{
					_debug "Trying to break '$match'";
					my ($broken,$left) =
						$config->{break}->($match,$rem,$_[1]);	
					$text .= $broken;
					_debug "Broke as: [$broken][$left]";
					$$ref = $left.$extra;
					$rem -= length $broken;
				}
				last;
			}
		}
		continue { $filled=1 }
	}

	if (!$filled && $rem>0 && $$ref=~/\S/ && length $text == 0)
	{
		$$ref =~ s/^\s*(.{1,$rem})//;
		$text = $1;
		$rem -= length $text;
	}

	if ( $text=~/ / && $_[0] eq 'J' && $$ref=~/\S/ && $filled!=2 ) {
							# FULLY JUSTIFIED
		$text = reverse $text;
		$text =~ s/( +)/($rem-->0?" ":"").$1/ge while $rem>0;
		$text = reverse $text;
	}
	elsif ( $_[0] =~ /\>|\]/ ) {			# RIGHT JUSTIFIED
		substr($text,0,0) =
			substr($config->{filler}{left} x $rem, -$rem)
				if $rem > 0;
	}
	elsif ( $_[0] =~ /\^|\|/ ) {			# CENTRE JUSTIFIED
	    if ($rem>0) {
		my $halfrem = int($rem/2);
		substr($text,0,0) =
			substr($config->{filler}{left}x$halfrem, -$halfrem);
		$halfrem = $rem-$halfrem;
		$text .= substr($config->{filler}{right}x$halfrem, 0, $halfrem);
	    }
	}
	else {						# LEFT JUSTIFIED
		$text .= substr($config->{filler}{right}x$rem, 0, $rem)
			if $rem > 0;
	}

	return $text;
}

my %std_config =
(
	header	   => sub{""},
	footer	   => sub{""},
	pagefeed   => sub{""},
	pagelen	   => 0,
	pagenum	   => undef,
	pagewidth  => 72,
	break	   => break_with('-'),
	minbreak   => 2,
	squeeze	   => 0,
	filler     => {left=>' ', right=>' '},
	interleave => 0,
	numeric	   => "",
	_used      => 1,
);

sub lcr {
	my ($data, $pagewidth, $header) = @_;
	$data->{width}  ||= $pagewidth;
	$data->{left}   ||= "";
	$data->{centre} ||= $data->{center}||"";
	$data->{right}  ||= "";
	return sub {
		my @l = split "\n", (ref $data->{left} eq 'CODE'
				? $data->{left}->(@_) : $data->{left}), -1;
		my @c = split "\n", (ref $data->{centre} eq 'CODE'
				? $data->{centre}->(@_) : $data->{centre}), -1;
		my @r = split "\n", (ref $data->{right} eq 'CODE'
				? $data->{right}->(@_) : $data->{right}), -1;
		my $text = "";
		while (@l||@c||@r) {
			my $l = @l ? shift(@l) : "";
			my $c = @c ? shift(@c) : "";
			my $r = @r ? shift(@r) : "";
			my $gap = int(($data->{width}-length($c))/2-length($l));
			if ($gap < 0) {
				$gap = 0;
				carpfirst "\nWarning: $header is wider than specified page width ($data->{width} chars)" if $^W;
			}
			$text .= $l . " " x $gap
			       . $c . " " x ($data->{width}-length($l)-length($c)-$gap-length($r))
			       . $r
			       . "\n";
		}
		return $text;
	}
}

sub fix_config(\%)
{
	my ($config) = @_;
	if (ref $config->{header} eq 'HASH') {
		$config->{header} =
			lcr $config->{header}, $config->{pagewidth}, 'header';
	}
	elsif (ref $config->{header} eq 'CODE') {
		my $tmp = $config->{header};
		$config->{header} = sub {
			my $header = &$tmp;
			return (ref $header eq 'HASH')
				? lcr($header,$config->{pagewidth},'header')->()
				: $header;
		}
	}
	else {
		my $tmp = $config->{header};
		$config->{header} = sub { $tmp }
	}
	if (ref $config->{footer} eq 'HASH') {
		$config->{footer} =
			lcr $config->{footer}, $config->{pagewidth}, 'footer';
	}
	elsif (ref $config->{footer} eq 'CODE') {
		my $tmp = $config->{footer};
		$config->{footer} = sub {
			my $footer = &$tmp;
			return (ref $footer eq 'HASH')
				? lcr($footer,$config->{pagewidth},'footer')->()
				: $footer;
		}
	}
	else {
		my $tmp = $config->{footer};
		$config->{footer} = sub { $tmp }
	}
	unless (ref $config->{pagefeed} eq 'CODE')
		{ my $tmp = $config->{pagefeed}; $config->{pagefeed} = sub { $tmp } }
	unless (ref $config->{break} eq 'CODE')
		{ $config->{break} = break_at($config->{break}) }
	if (defined $config->{pagenum} && ref $config->{pagenum} ne 'SCALAR') 
		{ my $tmp = $config->{pagenum}+0; $config->{pagenum} = \$tmp }
	unless (ref $config->{filler} eq 'HASH') {
		$config->{filler} = { left  => "$config->{filler}",
			  	      right => "$config->{filler}" }
	}
}

sub FormOpt::DESTROY
{
	print STDERR "\nWarning: lexical &form configuration at $std_config{_line} was never used.\n"
		if $^W && !$std_config{_used};
	%std_config = %{$std_config{_prev}};
}

sub form
{
	use vars '%carped';
	local %carped;
	my $config = {%std_config};
	my $startidx = 0;
	if (@_ && ref($_[0]) eq 'HASH')		# RESETTING CONFIG
	{
		if (@_ > 1)			# TEMPORARY RESET
		{
			$config = {%$config, %{$_[$startidx++]}};
			fix_config(%$config);
			$startidx = 1;
		}
		elsif (defined wantarray)	# CONTEXT BEING CAPTURED
		{
			$_[0]->{_prev} = { %std_config };
			$_[0]->{_used} = 0;
			$_[0]->{_line} = join " line ", (caller)[1..2];;
			%{$_[0]} = %std_config = (%std_config, %{$_[0]});
			fix_config(%std_config);
			return bless $_[0], 'FormOpt';
		}
		else				# PERMANENT RESET
		{
			$_[0]->{_used} = 1;
			$_[0]->{_line} = join " line ", (caller)[1..2];;
			%std_config = (%std_config, %{$_[0]});
			fix_config(%std_config);
			return;
		}
	}
	$config->{pagenum} = do{\(my $tmp=1)}
		unless defined $config->{pagenum};

	$std_config{_used}++;
	my @ref = map { ref } @_;
	my @orig = @_;
	my $caller = caller;
	no strict;

	for (my $nextarg=0; $nextarg<@_; $nextarg++)
	{
		my $next = $_[$nextarg];
		if (!defined $next) {
			my $tmp = "";
			splice @_, $nextarg, 1, \$tmp;
		}
		elsif ($ref[$nextarg] eq 'ARRAY') {
			splice @_, $nextarg, 1, \join("\n", @$next)
		}
		elsif ($ref[$nextarg] eq 'HASH' && $next->{cols} ) {
			croak "Missing 'from' data for 'cols' option"
				unless $next->{from};
			croak "Can't mix other options with 'cols' option"
				if keys %$next > 2;
			my ($cols, $data) = @{$next}{'cols','from'};
			croak "Invalid 'cols' option.\nExpected reference to array of column specifiers but found " . (ref($cols)||"'$cols'")
				unless ref $cols eq 'ARRAY';
			croak "Invalid 'from' data for 'cols' option.\nExpected reference to array of hashes or arrays but found " . (ref($data)||"'$data'")
				unless ref $data eq 'ARRAY';
			splice @_, $nextarg, 2, columns(@$cols,@$data);
			splice @ref, $nextarg, 2, ('ARRAY')x@$cols;
			$nextarg--;
		}
		elsif (!defined eval { local $SIG{__DIE__};
				       $_[$nextarg] = $next;
				       _debug "writeable: [$_[$nextarg]]";
				       1})
		{
		        _debug "unwriteable: [$_[$nextarg]]";
			my $arg = $_[$nextarg];
			splice @_, $nextarg, 1, \$arg;
		}
		elsif (!$ref[$nextarg]) {
			splice @_, $nextarg, 1, \$_[$nextarg];
		}
                elsif ($ref[$nextarg] ne 'HASH' and $ref[$nextarg] ne 'SCALAR')
                {
			splice @_, $nextarg, 1, \"$next";
                }
	}

	my $header = $config->{header}->(${$config->{pagenum}});
	$header.="\n" if $header && substr($header,-1,1) ne "\n";

	my $footer = $config->{footer}->(${$config->{pagenum}});
	$footer.="\n" if $footer && substr($footer,-1,1) ne "\n";

	my $prevfooter = $footer;

	my $linecount = $header=~tr/\n/\n/ + $footer=~tr/\n/\n/;
	my $hfcount = $linecount;

	my $text = $header;
	my @format_stack;

	LINE: while ($startidx < @_ || @format_stack)
	{
		if (($ref[$startidx]||'') eq 'HASH')
		{
			$config = {%$config, %{$_[$startidx++]}};
			fix_config(%$config);
			next;
		}
		unless (@format_stack) {
			@format_stack = $config->{interleave}
				? map "$_\n", split /\n/, ${$_[$startidx++]}||""
				: ${$_[$startidx++]}||"";
		}
		my $format = shift @format_stack;
		_debug("format: [$format]");
	
		my @parts = split /(\n|(?:\\.)+|$fieldpat)/, $format;
		push @parts, "\n" unless @parts && $parts[-1] eq "\n";
		my $fieldcount = 0;
		my $filled = 0;
		my $firstline = 1;
		while (!$filled)
		{
			my $nextarg = $startidx;
			my @data;
			foreach my $part ( @parts )
			{
				if ($part =~ /\A(?:\\.)+/)
				{
					_debug("esc literal: [$part]");
					my $tmp = $part;
					$tmp =~ s/\\(.)/$1/g;
					$text .= $tmp;
				}
				elsif ($part =~ /($lfieldmark)/)
				{
					if ($firstline)
					{
						$fieldcount++;
						if ($nextarg > $#_)
							{ push @_,\$emptyref; push @ref, '' }
						my $type = $1;
						$type = 'J' if $part =~ /$ljustified/;
						croak BAD_CONFIG if ($ref[$startidx] eq 'HASH');
						_debug("once field: [$part]");
						_debug("data was: [${$_[$nextarg]}]");
						$text .= replace($type,length($part),$_[$nextarg],$config);
						_debug("data now: [${$_[$nextarg]}]");
					}
					else
					{
						$text .= substr($config->{filler}{left} x length($part), -length($part));
						_debug("missing once field: [$part]");
					}
					$nextarg++;
				}
				elsif ($part =~ /($fieldmark)/ and substr($part,0,2) ne '~~')
				{
					$fieldcount++ if $firstline;
					if ($nextarg > $#_)
						{ push @_,\$emptyref; push @ref, '' }
					my $type = $1;
					$type = 'J' if $part =~ /$bjustified/;
					croak BAD_CONFIG if ($ref[$startidx] eq 'HASH');
					_debug("multi field: [$part]");
					_debug("data was: [${$_[$nextarg]}]");
					$text .= replace($type,length($part),$_[$nextarg],$config);
					_debug("data now: [${$_[$nextarg]}]");
					push @data, $_[$nextarg];
					$nextarg++;
				}
				else
				{
					_debug("literal: [$part]");
					my $tmp = $part;
					$tmp =~ s/\0(\0*)/$1/g;
					$text .= $tmp;
					if ($part eq "\n")
					{
						$linecount++;
						if ($config->{pagelen} && $linecount>=$config->{pagelen})
						{
							_debug("\tejecting page:  $config->{pagenum}");
							carpfirst "\nWarning: could not format page ${$config->{pagenum}} within specified page length"
								if $^W && $config->{pagelen} && $linecount > $config->{pagelen};
							${$config->{pagenum}}++;
							my $pagefeed = $config->{pagefeed}->(${$config->{pagenum}});
							$header = $config->{header}->(${$config->{pagenum}});
							$header.="\n" if $header && substr($header,-1,1) ne "\n";
							$text .= $footer
							       . $pagefeed
							       . $header;
							$prevfooter = $footer;
							$footer = $config->{footer}->(${$config->{pagenum}});
							$footer.="\n" if $footer && substr($footer,-1,1) ne "\n";
							$linecount = $hfcount =
								$header=~tr/\n/\n/ + $footer=~tr/\n/\n/;
							$header = $pagefeed
								. $header;
						}
					}
				}
				_debug("\tnextarg now:  $nextarg");
				_debug("\tstartidx now: $startidx");
			}
			$firstline = 0;
			$filled = ! grep { notempty $_ } @data;
		}
		$startidx += $fieldcount;
	}

	# ADJUST FINAL PAGE HEADER OR FOOTER AS REQUIRED
	if ($hfcount && $linecount == $hfcount)		# UNNEEDED HEADER
	{
		$text =~ s/\Q$header\E\Z//;
	}
	elsif ($linecount && $config->{pagelen})	# MISSING FOOTER
	{
		$text .= "\n" x ($config->{pagelen}-$linecount)
		       . $footer;
		$prevfooter = $footer;
	}

	# REPLACE LAST FOOTER
	
	if ($prevfooter) {
		my $lastfooter = $config->{footer}->(${$config->{pagenum}},1);
		$lastfooter.="\n"
			if $lastfooter && substr($lastfooter,-1,1) ne "\n";
		my $footerdiff = ($lastfooter =~ tr/\n/\n/)
			       - ($prevfooter =~ tr/\n/\n/);
		# Enough space to squeeze longer final footer in?
		my $tail = '^[^\S\n]*\n' x $footerdiff;
		if ($footerdiff > 0 && $text =~ /($tail\Q$prevfooter\E)\Z/m) {
			$prevfooter = $1;
			$footerdiff = 0;
		}
		# Apparently, not, so create an extra (empty) page for it
		if ($footerdiff > 0) {
			${$config->{pagenum}}++;
			my $lastheader = $config->{header}->(${$config->{pagenum}});
			$lastheader.="\n"
				if $lastheader && substr($lastheader,-1,1) ne "\n";
			$lastfooter = $config->{footer}->(${$config->{pagenum}},1);
			$lastfooter.="\n"
				if $lastfooter && substr($lastfooter,-1,1) ne "\n";

			$text .= $lastheader
			       . ("\n" x ( $config->{pagelen}
					- ($lastheader =~ tr/\n/\n/)
				        - ($lastfooter =~ tr/\n/\n/)
					)
				 )
			       . $lastfooter;
		}
		else {
                        $lastfooter = ("\n"x-$footerdiff).$lastfooter;
                        substr($text, -length($prevfooter)) = $lastfooter;
		}
	}

        # RESTORE ARG LIST
        for my $i (0..$#orig)
        {
                if ($ref[$i] eq 'ARRAY')
                        { eval { @{$orig[$i]} = map "$_\n", split /\n/, ${$_[$i]} } }
                elsif (!$ref[$i])
                        { eval { _debug("restoring $i (".$_[$i].") to " .
                                 defined($orig[$i]) ? $orig[$i] : "<undef>");
                                 ${$_[$i]} = $orig[$i] } }
        }

        ${$config->{pagenum}}++;
        $text =~ s/[ ]+$//gm if $config->{trim};
        return $text unless wantarray;
        return map "$_\n", split /\n/, $text;
}


#==== columns ========================================#

sub columns {
        my @cols;
        my (@fullres, @res);
        while (@_) {
                my $arg = shift @_;
                my $type = ref $arg;
                if ($type eq 'HASH') {
                        push @{$res[$_]}, $arg->{$cols[$_]} for 0..$#cols;
                }
                elsif ($type eq 'ARRAY') {
                        push @{$res[$_]}, $arg->[$cols[$_]] for 0..$#cols;
                }
                else {
                        if (@res) {
                                push @fullres, @res;
                                @res = @cols = ();
                        }
                        push @cols, $arg;
                }
        }
        return @fullres, @res;
}


#==== tag ============================================#

sub invert($)
{
        my $inversion = reverse $_[0];
        $inversion =~ tr/{[<(/}]>)/;
        return $inversion;
}

sub tag         # ($tag, $text; $opt_endtag)
{
        my ($tagleader,$tagindent,$ldelim,$tag,$tagargs,$tagtrailer) = 
                ( $_[0] =~ /\A((?:[ \t]*\n)*)([ \t]*)(\W*)(\w+)(.*?)(\s*)\Z/ );

        $ldelim = '<' unless $ldelim;
        $tagtrailer =~ s/([ \t]*)\Z//;
        my $textindent = $1||"";

        my $rdelim = invert $ldelim;

        my $i;
        for ($i = -1; -1-$i < length $rdelim && -1-$i < length $tagargs; $i--)
        {
                last unless substr($tagargs,$i,1) eq substr($rdelim,$i,1);
        }
        if ($i < -1)
        {
                $i++;
                $tagargs = substr($tagargs,0,$i);
                $rdelim = substr($rdelim,$i);
        }

        my $endtag = $_[2] || "$ldelim/$tag$rdelim";

        return "$tagleader$tagindent$ldelim$tag$tagargs$rdelim$tagtrailer".
                join("\n",map { "$tagindent$textindent$_" } split /\n/, $_[1]).
                "$tagtrailer$tagindent$endtag$tagleader";

}


1;

__END__

=head1 NAME

Text::Reform - Manual text wrapping and reformatting

=head1 VERSION

This document describes version 1.20 of Text::Reform,
released 2009-09-06.

=head1 SYNOPSIS

        use Text::Reform;

        print form $template,
                   $data, $to, $fill, $it, $with;


        use Text::Reform qw( tag );

        print tag 'B', $enboldened_text;


=head1 DESCRIPTION

=head2 The C<form> sub

The C<form()> subroutine may be exported from the module.
It takes a series of format (or "picture") strings followed by
replacement values, interpolates those values into each picture string,
and returns the result. The effect is similar to the inbuilt perl
C<format> mechanism, although the field specification syntax is
simpler and some of the formatting behaviour is more sophisticated.

A picture string consists of sequences of the following characters:

=over 8

=item <

Left-justified field indicator.
A series of two or more sequential <'s specify
a left-justified field to be filled by a subsequent value.
A single < is formatted as the literal character '<'

=item >

Right-justified field indicator.
A series of two or more sequential >'s specify
a right-justified field to be filled by a subsequent value.
A single > is formatted as the literal character '>'

=item <<<>>>

Fully-justified field indicator.
Field may be of any width, and brackets need not balance, but there
must be at least 2 '<' and 2 '>'.

=item ^

Centre-justified field indicator.
A series of two or more sequential ^'s specify
a centred field to be filled by a subsequent value.
A single ^ is formatted as the literal character '^'

=item >>>.<<<<

A numerically formatted field with the specified number of digits to
either side of the decimal place. See L<Numerical formatting> below.


=item [

Left-justified block field indicator.
Just like a < field, except it repeats as required on subsequent lines. See
below.
A single [ is formatted as the literal character '['

=item ]

Right-justified block field indicator.
Just like a > field, except it repeats as required on subsequent lines. See
below.
A single ] is formatted as the literal character ']'

=item [[[]]]

Fully-justified block field indicator.
Just like a <<<>>> field, except it repeats as required on subsequent lines. See
below.
Field may be of any width, and brackets need not balance, but there
must be at least 2 '[' and 2 ']'.

=item |

Centre-justified block field indicator.
Just like a ^ field, except it repeats as required on subsequent lines. See
below.
A single | is formatted as the literal character '|'

=item ]]].[[[[

A numerically formatted block field with the specified number of digits to
either side of the decimal place.
Just like a >>>.<<<< field, except it repeats as required on
subsequent lines. See below. 


=item ~

A one-character wide block field.

=item \

Literal escape of next character (e.g. C<\~> is formatted as '~', not a one
character wide block field).

=item Any other character

That literal character.

=back

Any substitution value which is C<undef> (either explicitly so, or because it
is missing) is replaced by an empty string.



=head2 Controlling line filling.

Note that, unlike the a perl C<format>, C<form> preserves whitespace
(including newlines) unless called with certain options.

The "squeeze" option (when specified with a true value) causes any sequence
of spaces and/or tabs (but not newlines) in an interpolated string to be
replaced with a single space.

A true value for the "fill" option causes (only) newlines to be squeezed.

To minimize all whitespace, you need to specify both options. Hence:

        $format = "EG> [[[[[[[[[[[[[[[[[[[[[";
        $data   = "h  e\t l lo\nworld\t\t\t\t\t";

        print form $format, $data;              # all whitespace preserved:
                                                #
                                                # EG> h  e            l lo
                                                # EG> world


        print form {squeeze=>1},                # only newlines preserved:
                   $format, $data;              #
                                                # EG> h e l lo
                                                # EG> world


        print form {fill=>1},                   # only spaces/tabs preserved:
                    $format, $data;             #
                                                # EG> h  e        l lo world


        print form {squeeze=>1, fill=>1},       # no whitespace preserved:
                   $format, $data;              #
                                                # EG> h e l lo world


Whether or not filling or squeezing is in effect, C<form> can also be
directed to trim any extra whitespace from the end of each line it
formats, using the "trim" option. If this option is specified with a
true value, every line returned by C<form> will automatically have the
substitution C<s/[ \t]+$//gm> applied to it.

Hence:

        print length form "[[[[[[[[[[", "short";
        # 11

        print length form {trim=>1}, "[[[[[[[[[[", "short";
        # 6


It is also possible to control the character used to fill lines that are
too short, using the 'filler' option. If this option is specified the
value of the 'filler' flag is used as the fill string, rather than the
default C<" ">.

For example:

        print form { filler=>'*' },
                "Pay bearer: ^^^^^^^^^^^^^^^^^^^",
                '$123.45';

prints:

        Pay bearer: ******$123.45******

If the filler string is longer than one character, it is truncated
to the appropriate length. So:

        print form { filler=>'-->' },
                "Pay bearer: ]]]]]]]]]]]]]]]]]]]",
                ['$1234.50', '$123.45', '$12.34'];

prints:

        Pay bearer: ->-->-->-->$1234.50
        Pay bearer: -->-->-->-->$123.45
        Pay bearer: >-->-->-->-->$12.34

If the value of the 'filler' option is a hash, then it's 'left' and
'right' entries specify separate filler strings for each side of
an interpolated value. So:

        print form { filler=>{left=>'->', right=>'*'} },
                "Pay bearer: <<<<<<<<<<<<<<<<<<",
                '$123.45',
                "Pay bearer: >>>>>>>>>>>>>>>>>>",
                '$123.45',
                "Pay bearer: ^^^^^^^^^^^^^^^^^^",
                '$123.45';

prints:

        Pay bearer: $123.45***********
        Pay bearer: >->->->->->$123.45
        Pay bearer: >->->$123.45******


=head2 Temporary and permanent default options

If C<form> is called with options, but no template string or data, it resets
it's defaults to the options specified. If called in a void context:

        form { squeeze => 1, trim => 1 };

the options become permanent defaults.

However, when called with only options in non-void context, C<form>
resets its defaults to those options and returns an object. The reset
default values persist only until that returned object is destroyed.
Hence to temporarily reset C<form>'s defaults within a single subroutine:

        sub single {
                my $tmp = form { squeeze => 1, trim => 1 };

                # do formatting with the obove defaults

        } # form's defaults revert to previous values as $tmp object destroyed



=head2 Multi-line format specifiers and interleaving

By default, if a format specifier contains two or more lines
(i.e. one or more newline characters), the entire format specifier
is repeatedly filled as a unit, until all block fields have consumed
their corresponding arguments. For example, to build a simple
look-up table:

        my @values   = (1..12);

        my @squares  = map { sprintf "%.6g", $_**2    } @values;
        my @roots    = map { sprintf "%.6g", sqrt($_) } @values;
        my @logs     = map { sprintf "%.6g", log($_)  } @values;
        my @inverses = map { sprintf "%.6g", 1/$_     } @values;

        print form
        "  N      N**2    sqrt(N)      log(N)      1/N",
        "=====================================================",
        "| [[  |  [[[  |  [[[[[[[[[[ | [[[[[[[[[ | [[[[[[[[[ |
        -----------------------------------------------------",
        \@values, \@squares, \@roots, \@logs, \@inverses;

The multiline format specifier:

        "| [[  |  [[[  |  [[[[[[[[[[ | [[[[[[[[[ | [[[[[[[[[ |
        -----------------------------------------------------",

is treated as a single logical line. So C<form> alternately fills the
first physical line (interpolating one value from each of the arrays)
and the second physical line (which puts a line of dashes between each
row of the table) producing:

          N      N**2    sqrt(N)      log(N)      1/N
        =====================================================
        | 1   |  1    |  1          | 0         | 1         |
        -----------------------------------------------------
        | 2   |  4    |  1.41421    | 0.693147  | 0.5       |
        -----------------------------------------------------
        | 3   |  9    |  1.73205    | 1.09861   | 0.333333  |
        -----------------------------------------------------
        | 4   |  16   |  2          | 1.38629   | 0.25      |
        -----------------------------------------------------
        | 5   |  25   |  2.23607    | 1.60944   | 0.2       |
        -----------------------------------------------------
        | 6   |  36   |  2.44949    | 1.79176   | 0.166667  |
        -----------------------------------------------------
        | 7   |  49   |  2.64575    | 1.94591   | 0.142857  |
        -----------------------------------------------------
        | 8   |  64   |  2.82843    | 2.07944   | 0.125     |
        -----------------------------------------------------
        | 9   |  81   |  3          | 2.19722   | 0.111111  |
        -----------------------------------------------------
        | 10  |  100  |  3.16228    | 2.30259   | 0.1       |
        -----------------------------------------------------
        | 11  |  121  |  3.31662    | 2.3979    | 0.0909091 |
        -----------------------------------------------------
        | 12  |  144  |  3.4641     | 2.48491   | 0.0833333 |
        -----------------------------------------------------

This implies that formats and the variables from which they're filled
need to be interleaved. That is, a multi-line specification like this:

        print form
        "Passed:                      ##
           [[[[[[[[[[[[[[[             # single format specification
        Failed:                        # (needs two sets of data)
           [[[[[[[[[[[[[[[",          ##

        \@passes, \@fails;            ##  data for previous format

would print:

        Passed:
           <pass 1>
        Failed:
           <fail 1>
        Passed:
           <pass 2>
        Failed:
           <fail 2>
        Passed:
           <pass 3>
        Failed:
           <fail 3>

because the four-line format specifier is treated as a single unit,
to be repeatedly filled until all the data in C<@passes> and C<@fails>
has been consumed.

Unlike the table example, where this unit filling correctly put a
line of dashes between lines of data, in this case the alternation of passes
and fails is probably I<not> the desired effect.

Judging by the labels, it is far more likely that the user wanted:

        Passed:
           <pass 1>
           <pass 2>
           <pass 3>
        Failed:
           <fail 4>
           <fail 5>
           <fail 6>

To achieve that, either explicitly interleave the formats and their data
sources:

        print form 
        "Passed:",               ## single format (no data required)
        "   [[[[[[[[[[[[[[[",    ## single format (needs one set of data)
            \@passes,            ## data for previous format
        "Failed:",               ## single format (no data required)
        "   [[[[[[[[[[[[[[[",    ## single format (needs one set of data)
            \@fails;             ## data for previous format


or instruct C<form> to do it for you automagically, by setting the
'interleave' flag true:

        print form {interleave=>1}
        "Passed:                 ##
           [[[[[[[[[[[[[[[        # single format
        Failed:                   # (needs two sets of data)
           [[[[[[[[[[[[[[[",     ##

                                 ## data to be automagically interleaved
        \@passes, \@fails;        # as necessary between lines of previous
                                 ## format


=head2 How C<form> hyphenates

Any line with a block field repeats on subsequent lines until all block fields
on that line have consumed all their data. Non-block fields on these lines are
replaced by the appropriate number of spaces.

Words are wrapped whole, unless they will not fit into the field at
all, in which case they are broken and (by default) hyphenated. Simple
hyphenation is used (i.e. break at the I<N-1>th character and insert a
'-'), unless a suitable alternative subroutine is specified instead.

Words will not be broken if the break would leave less than 2 characters on
the current line. This minimum can be varied by setting the 'minbreak' option
to a numeric value indicating the minimum total broken characters (including
hyphens) required on the current line. Note that, for very narrow fields,
words will still be broken (but I<unhyphenated>). For example:

        print form '~', 'split';

would print:

        s
        p
        l
        i
        t

whilst:

        print form {minbreak=>1}, '~', 'split';

would print:

        s-
        p-
        l-
        i-
        t

Alternative breaking subroutines can be specified using the "break" option in a
configuration hash. For example:

        form { break => \&my_line_breaker }
             $format_str,
             @data;

C<form> expects any user-defined line-breaking subroutine to take three
arguments (the string to be broken, the maximum permissible length of
the initial section, and the total width of the field being filled).
The C<hypenate> sub must return a list of two strings: the initial
(broken) section of the word, and the remainder of the string
respectively).

For example:

        sub tilde_break = sub($$$)
        {
                (substr($_[0],0,$_[1]-1).'~', substr($_[0],$_[1]-1));
        }

        form { break => \&tilde_break }
             $format_str,
             @data;


makes '~' the hyphenation character, whilst:

        sub wrap_and_slop = sub($$$)
        {
                my ($text, $reqlen, $fldlen) = @_;
                if ($reqlen==$fldlen) { $text =~ m/\A(\s*\S*)(.*)/s }
                else                  { ("", $text) }
        }

        form { break => \&wrap_and_slop }
             $format_str,
             @data;

wraps excessively long words to the next line and "slops" them over
the right margin if necessary.

The Text::Reform package provides three functions to simplify the use
of variant hyphenation schemes. The exportable subroutine
C<Text::Reform::break_wrap> generates a reference to a subroutine
implementing the "wrap-and-slop" algorithm shown in the last example,
which could therefore be rewritten:

        use Text::Reform qw( form break_wrap );

        form { break => break_wrap }
             $format_str,
             @data;

The subroutine C<Text::Reform::break_with> takes a single string
argument and returns a reference to a sub which hyphenates by cutting 
off the text at the right margin and appending the string argument.
Hence the first of the two examples could be rewritten:

        use Text::Reform qw( form break_with );

        form { break => break_with('~') }
             $format_str,
             @data;

The subroutine C<Text::Reform::break_at> takes a single string
argument and returns a reference to a sub which hyphenates by
breaking immediately after that string. For example:

        use Text::Reform qw( form break_at );

        form { break => break_at('-') }
               "[[[[[[[[[[[[[[",
	       "The Newton-Raphson methodology";

	# returns:
	#
	#       "The Newton-
	#        Raphson 
	#        methodology"

Note that this differs from the behaviour of C<break_with>, which
would be:

        form { break => break_with('-') }
               "[[[[[[[[[[[[[[",
	       "The Newton-Raphson methodology";

	# returns:
	#
	#       "The Newton-R-
	#        aphson metho-
	#        dology"

Hence C<break_at> is generally a better choice.

C<break_at> also takes an 'except' option, which tells the resulting
subroutine not to break in the middle of certain strings. For example:

        form { break => break_at('-', {except=>qr/Newton-Raphson/}) }
               "[[[[[[[[[[[[[[",
	       "The Newton-Raphson methodology";

	# returns:
	#
	#       "The
    #        Newton-Raphson 
	#        methodology"

This option is particularly useful for preserving URLs.

The subroutine C<Text::Reform::break_TeX> 
returns a reference to a sub which hyphenates using 
Jan Pazdziora's TeX::Hyphen module. For example:

        use Text::Reform qw( form break_wrap );

        form { break => break_TeX }
             $format_str,
             @data;

Note that in the previous examples there is no leading '\&' before
C<break_wrap>, C<break_with>, or C<break_TeX>, since each is being
directly I<called> (and returns a reference to some other suitable
subroutine);


=head2 The C<form> formatting algorithm

The algorithm C<form> uses is:

        1. If interleaving is specified, split the first string in the
           argument list into individual format lines and add a
           terminating newline (unless one is already present).
           Otherwise, treat the entire string as a single "line" (like
           /s does in regexes)

        2. For each format line...

                2.1. determine the number of fields and shift
                     that many values off the argument list and
                     into the filling list. If insufficient
                     arguments are available, generate as many 
                     empty strings as are required.

                2.2. generate a text line by filling each field
                     in the format line with the initial contents
                     of the corresponding arg in the filling list
                     (and remove those initial contents from the arg).

                2.3. replace any <,>, or ^ fields by an equivalent
                     number of spaces. Splice out the corresponding
                     args from the filling list.

                2.4. Repeat from step 2.2 until all args in the
                     filling list are empty.

        3. concatenate the text lines generated in step 2

        4. repeat from step 1 until the argument list is empty


=head2 C<form> examples

As an example of the use of C<form>, the following:

        $count = 1;
        $text = "A big long piece of text to be formatted exquisitely";

        print form q
        q{       ||||  <<<<<<<<<<   },
        $count, $text,
        q{       ----------------   },
        q{       ^^^^  ]]]]]]]]]]|  },
        $count+11, $text,
        q{                       =  
                 ]]].[[[            },
        "123 123.4\n123.456789";

produces the following output:

                 1    A big long
                ----------------
                 12     piece of|
                      text to be|
                       formatted|
                      exquisite-|
                              ly|
                                =
                123.0
                                =
                123.4
                                =
                123.456

Note that block fields in a multi-line format string,
cause the entire multi-line format to be repeated as
often as necessary.

Picture strings and replacement values are interleaved in the
traditional C<format> format, but care is needed to ensure that the
correct number of substitution values are provided. Another
example:

        $report = form
                'Name           Rank    Serial Number',
                '====           ====    =============',
                '<<<<<<<<<<<<<  ^^^^    <<<<<<<<<<<<<',
                 $name,         $rank,  $serial_number,
                ''
                'Age    Sex     Description',
                '===    ===     ===========',
                '^^^    ^^^     [[[[[[[[[[[',
                 $age,  $sex,   $description;


=head2 How C<form> consumes strings

Unlike C<format>, within C<form> non-block fields I<do> consume the text
they format, so the following:

        $text = "a line of text to be formatted over three lines";
        print form "<<<<<<<<<<\n  <<<<<<<<\n    <<<<<<\n",
                    $text,        $text,        $text;

produces:

        a line of
          text to
            be fo-

not:

        a line of
          a line 
            a line

To achieve the latter effect, convert the variable arguments
to independent literals (by double-quoted interpolation):

        $text = "a line of text to be formatted over three lines";
        print form "<<<<<<<<<<\n  <<<<<<<<\n    <<<<<<\n",
                   "$text",      "$text",      "$text";

Although values passed from variable arguments are progressively consumed
I<within> C<form>, the values of the original variables passed to C<form>
are I<not> altered.  Hence:

        $text = "a line of text to be formatted over three lines";
        print form "<<<<<<<<<<\n  <<<<<<<<\n    <<<<<<\n",
                    $text,        $text,        $text;
        print $text, "\n";

will print:

        a line of
          text to
            be fo-
        a line of text to be formatted over three lines

To cause C<form> to consume the values of the original variables passed to
it, pass them as references. Thus:

        $text = "a line of text to be formatted over three lines";
        print form "<<<<<<<<<<\n  <<<<<<<<\n    <<<<<<\n",
                    \$text,       \$text,       \$text;
        print $text, "\n";

will print:

        a line of
          text to
            be fo-
        rmatted over three lines

Note that, for safety, the "non-consuming" behaviour takes precedence,
so if a variable is passed to C<form> both by reference I<and> by value,
its final value will be unchanged.

=head2 Numerical formatting

The ">>>.<<<" and "]]].[[[" field specifiers may be used to format
numeric values about a fixed decimal place marker. For example:

        print form '(]]]]].[[)', <<EONUMS;
                   1
                   1.0
                   1.001
                   1.009
                   123.456
                   1234567
                   one two
        EONUMS

would print:

        (    1.0 )
        (    1.0 )
        (    1.00)
        (    1.01)
        (  123.46)
        (#####.##)
        (?????.??)
        (?????.??)

Fractions are rounded to the specified number of places after the
decimal, but only significant digits are shown. That's why, in the
above example, 1 and 1.0 are formatted as "1.0", whilst 1.001 is
formatted as "1.00".

You can specify that the maximal number of decimal places always be used
by giving the configuration option 'numeric' a value that matches
/\bAllPlaces\b/i. For example:

        print form { numeric => AllPlaces },
                   '(]]]]].[[)', <<'EONUMS';
                   1
                   1.0
        EONUMS

would print:

        (    1.00)
        (    1.00)

Note that although decimal digits are rounded to fit the specified width, the
integral part of a number is never modified. If there are not enough places
before the decimal place to represent the number, the entire number is 
replaced with hashes.

If a non-numeric sequence is passed as data for a numeric field, it is
formatted as a series of question marks. This querulous behaviour can be
changed by giving the configuration option 'numeric' a value that
matches /\bSkipNaN\b/i in which case, any invalid numeric data is simply
ignored. For example:


        print form { numeric => 'SkipNaN' }
                   '(]]]]].[[)',
                   <<EONUMS;
                   1
                   two three
                   4
        EONUMS

would print:

        (    1.0 )
        (    4.0 )


=head2 Filling block fields with lists of values

If an argument corresponding to a field is an array reference, then C<form>
automatically joins the elements of the array into a single string, separating
each element with a newline character. As a result, a call like this:

        @values = qw( 1 10 100 1000 );
        print form "(]]]].[[)", \@values;

will print out

         (   1.00)
         (  10.00)
         ( 100.00)
         (1000.00)

as might be expected.

Note however that arrays must be passed by reference (so that C<form>
knows that the entire array holds data for a single field). If the previous
example had not passed @values by reference:

        @values = qw( 1 10 100 1000 );
        print form "(]]]].[[)", @values;

the output would have been:

         (   1.00)
         10
         100
         1000

This is because @values would have been interpolated into C<form>'s
argument list, so only $value[0] would have been used as the data for
the initial format string. The remaining elements of @value would have
been treated as separate format strings, and printed out "verbatim".

Note too that, because arrays must be passed using a reference, their
original contents are consumed by C<form>, just like the contents of
scalars passed by reference.

To avoid having an array consumed by C<form>, pass it as an anonymous
array:

        print form "(]]]].[[)", [@values];


=head2 Headers, footers, and pages

The C<form> subroutine can also insert headers, footers, and page-feeds
as it formats. These features are controlled by the "header", "footer",
"pagefeed", "pagelen", and "pagenum" options.

The "pagenum" option takes a scalar value or a reference to a scalar
variable and starts page numbering at that value. If a reference to a
scalar variable is specified, the value of that variable is updated as
the formatting proceeds, so that the final page number is available in
it after formatting. This can be useful for multi-part reports.

The "pagelen" option specifies the total number of lines in a page (including
headers, footers, and page-feeds).

The "pagewidth" option specifies the total number of columns in a page.

If the "header" option is specified with a string value, that string is
used as the header of every page generated. If it is specified as a reference
to a subroutine, that subroutine is called at the start of every page and
its return value used as the header string. When called, the subroutine is
passed the current page number.

Likewise, if the "footer" option is specified with a string value, that
string is used as the footer of every page generated. If it is specified
as a reference to a subroutine, that subroutine is called at the I<start>
of every page and its return value used as the footer string. When called,
the footer subroutine is passed the current page number.

Both the header and footer options can also be specified as hash references.
In this case the hash entries for keys "left", "centre" (or "center"), and
"right" specify what is to appear on the left, centre, and right of the
header/footer. The entry for the key "width" specifies how wide the
footer is to be. If the "width" key is omitted, the "pagewidth" configuration
option (which defaults to 72 characters) is used.

The  "left", "centre", and "right" values may be literal
strings, or subroutines (just as a normal header/footer specification may
be.) See the second example, below.

Another alternative for header and footer options is to specify them as a
subroutine that returns a hash reference. The subroutine is called for each
page, then the resulting hash is treated like the hashes described in the
preceding paragraph. See the third example, below.

The "pagefeed" option acts in exactly the same way, to produce a
pagefeed which is appended after the footer. But note that the pagefeed
is not counted as part of the page length.

All three of these page components are recomputed at the start of each
new page, before the page contents are formatted (recomputing the header
and footer first makes it possible to determine how many lines of data to
format so as to adhere to the specified page length).

When the call to C<form> is complete and the data has been fully formatted,
the footer subroutine is called one last time, with an extra argument of 1.
The string returned by this final call is used as the final footer.

So for example, a 60-line per page report, starting at page 7,
with appropriate headers and footers might be set up like so:

        $page = 7;

        form { header => sub { "Page $_[0]\n\n" },
               footer => sub { my ($pagenum, $lastpage) = @_;
                               return "" if $lastpage;
                               return "-"x50 . "\n"
                                             .form ">"x50, "...".($pagenum+1);
                              },
               pagefeed => "\n\n",
               pagelen  => 60
               pagenum => \$page,
             },
             $template,
             @data;

Note the recursive use of C<form> within the "footer" option!

Alternatively, to set up headers and footers such that the running
head is right justified in the header and the page number is centred
in the footer:

        form { header => { right => "Running head" },
               footer => { centre => sub { "Page $_[0]" } },
               pagelen  => 60
             },
             $template,
             @data;

The footer in the previous example could also have been specified the other
way around, as a subroutine that returns a hash (rather than a hash containing
a subroutine):

        form { header => { right => "Running head" },
               footer => sub { return {centre => "Page $_[0]"} },
               pagelen  => 60
             },
             $template,
             @data;


=head2 The C<cols> option

Sometimes data to be used in a C<form> call needs to be extracted from a
nested data structure. For example, whilst it's easy to print a table if
you already have the data in columns:

        @name  = qw(Tom Dick Harry);
        @score = qw( 88   54    99);
        @time  = qw( 15   13    18);

        print form
        '-------------------------------',
        'Name             Score     Time',
        '-------------------------------',
        '[[[[[[[[[[[[[[   |||||     ||||',
         \@name,          \@score,  \@time;


if the data is aggregrated by rows:

        @data = (
            { name=>'Tom',   score=>88, time=>15 },
            { name=>'Dick',  score=>54, time=>13 },
            { name=>'Harry', score=>99, time=>18 },
        );

you need to do some fancy mapping before it can be fed to C<form>:

        print form
        '-------------------------------',
        'Name             Score     Time',
        '-------------------------------',
        '[[[[[[[[[[[[[[   |||||     ||||',
        [map $$_{name},  @data],
        [map $$_{score}, @data],
        [map $$_{time} , @data];

Or you could just use the C<'cols'> option:

        use Text::Reform qw(form columns);

        print form
        '-------------------------------',
        'Name             Score     Time',
        '-------------------------------',
        '[[[[[[[[[[[[[[   |||||     ||||',
        { cols => [qw(name score time)],
          from => \@data
        };

This option takes an array of strings that specifies the keys of the
hash entries to be extracted into columns. The C<'from'> entry (which
must be present) also takes an array, which is expected to contain a
list of references to hashes. For each key specified, this option
inserts into C<form>'s argument list a reference to an array containing
the entries for that key, extracted from each of the hash references
supplied by C<'from'>. So, for example, the option:

        { cols => [qw(name score time)],
          from => \@data
        }

is replaced by three array references, the first containing the C<'name'>
entries for each hash inside C<@data>, the second containing the
C<'score'> entries for each hash inside C<@data>, and the third
containing the C<'time'> entries for each hash inside C<@data>.

If, instead, you have a list of arrays containing the data:

        @data = (
                # Time  Name     Score
                [ 15,   'Tom',   88 ],
                [ 13,   'Dick',  54 ],
                [ 18,   'Harry', 99 ],
        );

the C<'cols'> option can extract the appropriate columns for that too. You
just specify the required indices, rather than keys:

        print form
        '-----------------------------',   
        'Name             Score   Time',   
        '-----------------------------',   
        '[[[[[[[[[[[[[[   |||||   ||||',
        { cols => [1,2,0],
          from => \@data
        }

Note that the indices can be in any order, and the resulting arrays are
returned in the same order.

If you need to merge columns extracted from two hierarchical 
data structures, just concatenate the data structures first,
like so:

        print form
        '---------------------------------------',   
        'Name             Score   Time   Ranking
        '---------------------------------------',   
        '[[[[[[[[[[[[[[   |||||   ||||   |||||||',
        { cols => [1,2,0],
          from => [@data, @olddata],
        }

Of course, this only works if the columns are in the same positions in
both data sets (and both datasets are stored in arrays) or if the
columns have the same keys (and both datasets are in hashes). If not,
you would need to format each dataset separately, like so:

        print form
        '-----------------------------',   
        'Name             Score   Time'
        '-----------------------------',   
        '[[[[[[[[[[[[[[   |||||   ||||',
        { cols=>[1,2,0],  from=>\@data },
        '[[[[[[[[[[[[[[   |||||   ||||',
        { cols=>[3,8,1],  from=>\@olddata },
        '[[[[[[[[[[[[[[   |||||   ||||',
        { cols=>[qw(name score time)],  from=>\@otherdata };


=head2 The C<tag> sub

The C<tag> subroutine may be exported from the module.
It takes two arguments: a tag specifier and a text to be
entagged. The tag specifier indicates the indenting of the tag, and of the
text. The sub generates an end-tag (using the usual "/I<tag>" variant),
unless an explicit end-tag is provided as the third argument.

The tag specifier consists of the following components (in order):

=over 4

=item An optional vertical spacer (zero or more whitespace-separated newlines)

One or more whitespace characters up to a final mandatory newline. This
vertical space is inserted before the tag and after the end-tag

=item An optional tag indent

Zero or more whitespace characters. Both the tag and the end-tag are indented
by this whitespace.

=item An optional left (opening) tag delimiter

Zero or more non-"word" characters (not alphanumeric or '_').
If the opening delimiter is omitted, the character '<' is used.

=item A tag

One or more "word" characters (alphanumeric or '_').

=item Optional tag arguments

Any number of any characters

=item An optional right (closing) tag delimiter

Zero or more non-"word" characters which balance some sequential portion
of the opening tag delimiter. For example, if the opening delimiter
is "<-(" then any of the following are acceptible closing delimiters:
")->", "->", or ">".
If the closing delimiter is omitted, the "inverse" of the opening delimiter 
is used (for example, ")->"),

=item An optional vertical spacer (zero or more newlines)

One or more whitespace characters up to a mandatory newline. This
vertical space is inserted before and after the complete text.

=item An optional text indent

Zero or more space of tab characters. Each line of text is indented
by this whitespace (in addition to the tag indent).


=back

For example:

        $text = "three lines\nof tagged\ntext";

        print tag "A HREF=#nextsection", $text;

prints:

        <A HREF=#nextsection>three lines
        of tagged
        text</A>

whereas:

        print tag "[-:GRIN>>>\n", $text;

prints:

        [-:GRIN>>>:-]
        three lines
        of tagged
        text
        [-:/GRIN>>>:-]

and:

        print tag "\n\n   <BOLD>\n\n   ", $text, "<END BOLD>";

prints:

S< >

           <BOLD>

              three lines
              of tagged
              text

           <END BOLD>

S< >

(with the indicated spacing fore and aft).

=head1 AUTHOR

Damian Conway (damian@conway.org)

=head1 BUGS

The module uses C<POSIX::strtod>, which may be broken under certain versions
of Windows. Applying the WINDOWS_PATCH patch to Reform.pm will replace the
POSIX function with a copycat subroutine.

There are undoubtedly serious bugs lurking somewhere in code this funky :-)
Bug reports and other feedback are most welcome.

=head1 LICENCE AND COPYRIGHT

Copyright (c) 1997-2007, Damian Conway C<< <DCONWAY@CPAN.org> >>. All rights reserved.

This module is free software; you can redistribute it and/or
modify it under the same terms as Perl itself. See L<perlartistic>.


=head1 DISCLAIMER OF WARRANTY

BECAUSE THIS SOFTWARE IS LICENSED FREE OF CHARGE, THERE IS NO WARRANTY
FOR THE SOFTWARE, TO THE EXTENT PERMITTED BY APPLICABLE LAW. EXCEPT WHEN
OTHERWISE STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR OTHER PARTIES
PROVIDE THE SOFTWARE "AS IS" WITHOUT WARRANTY OF ANY KIND, EITHER
EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE. THE
ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE SOFTWARE IS WITH
YOU. SHOULD THE SOFTWARE PROVE DEFECTIVE, YOU ASSUME THE COST OF ALL
NECESSARY SERVICING, REPAIR, OR CORRECTION.

IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MAY MODIFY AND/OR
REDISTRIBUTE THE SOFTWARE AS PERMITTED BY THE ABOVE LICENCE, BE
LIABLE TO YOU FOR DAMAGES, INCLUDING ANY GENERAL, SPECIAL, INCIDENTAL,
OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE USE OR INABILITY TO USE
THE SOFTWARE (INCLUDING BUT NOT LIMITED TO LOSS OF DATA OR DATA BEING
RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD PARTIES OR A
FAILURE OF THE SOFTWARE TO OPERATE WITH ANY OTHER SOFTWARE), EVEN IF
SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF
SUCH DAMAGES.