File: CSV_XS.pm

package info (click to toggle)
libtext-csv-xs-perl 0.73-1
  • links: PTS, VCS
  • area: main
  • in suites: squeeze
  • size: 620 kB
  • ctags: 826
  • sloc: perl: 3,241; makefile: 15
file content (1738 lines) | stat: -rw-r--r-- 50,805 bytes parent folder | download
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
package Text::CSV_XS;

# Copyright (c) 2007-2010 H.Merijn Brand.  All rights reserved.
# Copyright (c) 1998-2001 Jochen Wiedmann. All rights reserved.
# Portions Copyright (c) 1997 Alan Citterman. All rights reserved.
#
# This program is free software; you can redistribute it and/or
# modify it under the same terms as Perl itself.

################################################################################
# HISTORY
#
# Written by:
#    Jochen Wiedmann <joe@ispsoft.de>
#
# Based on Text::CSV by:
#    Alan Citterman <alan@mfgrtl.com>
#
# Extended and Remodelled by:
#    H.Merijn Brand (h.m.brand@xs4all.nl)
#
############################################################################

require 5.005;

use strict;
use warnings;

use DynaLoader ();
use Carp;

use vars   qw( $VERSION @ISA );
$VERSION = "0.73";
@ISA     = qw( DynaLoader );
bootstrap Text::CSV_XS $VERSION;

sub PV { 0 }
sub IV { 1 }
sub NV { 2 }

# version
#
#   class/object method expecting no arguments and returning the version
#   number of Text::CSV.  there are no side-effects.

sub version
{
    return $VERSION;
    } # version

# new
#
#   class/object method expecting no arguments and returning a reference to
#   a newly created Text::CSV object.

my %def_attr = (
    quote_char		=> '"',
    escape_char		=> '"',
    sep_char		=> ',',
    eol			=> '',
    always_quote	=> 0,
    quote_space		=> 1,
    quote_null		=> 1,
    binary		=> 0,
    keep_meta_info	=> 0,
    allow_loose_quotes	=> 0,
    allow_loose_escapes	=> 0,
    allow_whitespace	=> 0,
    blank_is_undef	=> 0,
    empty_is_undef	=> 0,
    verbatim		=> 0,
    auto_diag		=> 0,
    types		=> undef,

    _EOF		=> 0,
    _STATUS		=> undef,
    _FIELDS		=> undef,
    _FFLAGS		=> undef,
    _STRING		=> undef,
    _ERROR_INPUT	=> undef,
    _COLUMN_NAMES	=> undef,
    _BOUND_COLUMNS	=> undef,
    _AHEAD		=> undef,
    );
my $last_new_err = Text::CSV_XS->SetDiag (0);

sub _check_sanity
{
    my $attr = shift;
    for (qw( sep_char quote_char escape_char )) {
	exists $attr->{$_} && defined $attr->{$_} && $attr->{$_} =~ m/[\r\n]/ and
	    return 1003;
	}
    $attr->{allow_whitespace} and
      (defined $attr->{quote_char}  && $attr->{quote_char}  =~ m/^[ \t]$/) ||
      (defined $attr->{escape_char} && $attr->{escape_char} =~ m/^[ \t]$/) and
	return 1002;
    return 0;
    } # _check_sanity

sub new
{
    $last_new_err = SetDiag (undef, 1000,
	"usage: my \$csv = Text::CSV_XS->new ([{ option => value, ... }]);");

    my $proto = shift;
    my $class = ref ($proto) || $proto	or  return;
    @_ > 0 &&   ref $_[0] ne "HASH"	and return;
    my $attr  = shift || {};

    for (keys %{$attr}) {
	if (m/^[a-z]/ && exists $def_attr{$_}) {
	    $] >= 5.008002 && m/_char$/ and utf8::decode ($attr->{$_});
	    next;
	    }
#	croak?
	$last_new_err = SetDiag (undef, 1000, "INI - Unknown attribute '$_'");
	$attr->{auto_diag} and error_diag ();
	return;
	}

    my $self  = {%def_attr, %{$attr}};
    if (my $ec = _check_sanity ($self)) {
	$last_new_err = SetDiag (undef, $ec);
	$attr->{auto_diag} and error_diag ();
	return;
	}

    $last_new_err = SetDiag (undef, 0);
    defined $\ && !exists $attr->{eol} and $self->{eol} = $\;
    bless $self, $class;
    defined $self->{types} and $self->types ($self->{types});
    $self;
    } # new

# Keep in sync with XS!
my %_cache_id = ( # Only expose what is accessed from within PM
    quote_char		=>  0,
    escape_char		=>  1,
    sep_char		=>  2,
    binary		=>  3,
    keep_meta_info	=>  4,
    always_quote	=>  5,
    allow_loose_quotes	=>  6,
    allow_loose_escapes	=>  7,
    allow_double_quoted	=>  8,
    allow_whitespace	=>  9,
    blank_is_undef	=> 10,
    eol			=> 11,	# 11 .. 18
    verbatim		=> 22,
    empty_is_undef	=> 23,
    auto_diag		=> 24,
    quote_space		=> 25,
    quote_null		=> 31,
    _is_bound		=> 26,	# 26 .. 29
    );

# A `character'
sub _set_attr_C
{
    my ($self, $name, $val, $ec) = @_;
    defined $val or $val = 0;
    $] >= 5.008002 and utf8::decode ($val);
    $self->{$name} = $val;
    $ec = _check_sanity ($self) and
	croak ($self->SetDiag ($ec));
    $self->_cache_set ($_cache_id{$name}, $val);
    } # _set_attr_C

# A flag
sub _set_attr_X
{
    my ($self, $name, $val) = @_;
    defined $val or $val = 0;
    $self->{$name} = $val;
    $self->_cache_set ($_cache_id{$name}, 0 + $val);
    } # _set_attr_X

# A number
sub _set_attr_N
{
    my ($self, $name, $val) = @_;
    $self->{$name} = $val;
    $self->_cache_set ($_cache_id{$name}, 0 + $val);
    } # _set_attr_N

# Accessor methods.
#   It is unwise to change them halfway through a single file!
sub quote_char
{
    my $self = shift;
    if (@_) {
	my $qc = shift;
	$self->_set_attr_C ("quote_char", $qc);
	}
    $self->{quote_char};
    } # quote_char

sub escape_char
{
    my $self = shift;
    if (@_) {
	my $ec = shift;
	$self->_set_attr_C ("escape_char", $ec);
	}
    $self->{escape_char};
    } # escape_char

sub sep_char
{
    my $self = shift;
    @_ and $self->_set_attr_C ("sep_char", shift);
    $self->{sep_char};
    } # sep_char

sub eol
{
    my $self = shift;
    if (@_) {
	my $eol = shift;
	defined $eol or $eol = "";
	$self->{eol} = $eol;
	$self->_cache_set ($_cache_id{eol}, $eol);
	}
    $self->{eol};
    } # eol

sub always_quote
{
    my $self = shift;
    @_ and $self->_set_attr_X ("always_quote", shift);
    $self->{always_quote};
    } # always_quote

sub quote_space
{
    my $self = shift;
    @_ and $self->_set_attr_X ("quote_space", shift);
    $self->{quote_space};
    } # quote_space

sub quote_null
{
    my $self = shift;
    @_ and $self->_set_attr_X ("quote_null", shift);
    $self->{quote_null};
    } # quote_null

sub binary
{
    my $self = shift;
    @_ and $self->_set_attr_X ("binary", shift);
    $self->{binary};
    } # binary

sub keep_meta_info
{
    my $self = shift;
    @_ and $self->_set_attr_X ("keep_meta_info", shift);
    $self->{keep_meta_info};
    } # keep_meta_info

sub allow_loose_quotes
{
    my $self = shift;
    @_ and $self->_set_attr_X ("allow_loose_quotes", shift);
    $self->{allow_loose_quotes};
    } # allow_loose_quotes

sub allow_loose_escapes
{
    my $self = shift;
    @_ and $self->_set_attr_X ("allow_loose_escapes", shift);
    $self->{allow_loose_escapes};
    } # allow_loose_escapes

sub allow_whitespace
{
    my $self = shift;
    if (@_) {
	my $aw = shift;
	$aw and
	  (defined $self->{quote_char}  && $self->{quote_char}  =~ m/^[ \t]$/) ||
	  (defined $self->{escape_char} && $self->{escape_char} =~ m/^[ \t]$/) and
	    croak ($self->SetDiag (1002));
	$self->_set_attr_X ("allow_whitespace", $aw);
	}
    $self->{allow_whitespace};
    } # allow_whitespace

sub blank_is_undef
{
    my $self = shift;
    @_ and $self->_set_attr_X ("blank_is_undef", shift);
    $self->{blank_is_undef};
    } # blank_is_undef

sub empty_is_undef
{
    my $self = shift;
    @_ and $self->_set_attr_X ("empty_is_undef", shift);
    $self->{empty_is_undef};
    } # empty_is_undef

sub verbatim
{
    my $self = shift;
    @_ and $self->_set_attr_X ("verbatim", shift);
    $self->{verbatim};
    } # verbatim

sub auto_diag
{
    my $self = shift;
    @_ and $self->_set_attr_X ("auto_diag", shift);
    $self->{auto_diag};
    } # auto_diag

# status
#
#   object method returning the success or failure of the most recent
#   combine () or parse ().  there are no side-effects.

sub status
{
    my $self = shift;
    return $self->{_STATUS};
    } # status

sub eof
{
    my $self = shift;
    return $self->{_EOF};
    } # status

# error_input
#
#   object method returning the first invalid argument to the most recent
#   combine () or parse ().  there are no side-effects.

sub error_input
{
    my $self = shift;
    return $self->{_ERROR_INPUT};
    } # error_input

# erro_diag
#
#   If (and only if) an error occured, this function returns a code that
#   indicates the reason of failure

sub error_diag
{
    my $self = shift;
    my @diag = (0 + $last_new_err, $last_new_err, 0);

    if ($self && ref $self && # Not a class method or direct call
	 $self->isa (__PACKAGE__) && exists $self->{_ERROR_DIAG}) {
	@diag = (0 + $self->{_ERROR_DIAG}, $self->{_ERROR_DIAG});
	exists $self->{_ERROR_POS} and $diag[2] = 1 + $self->{_ERROR_POS};
	}

    my $context = wantarray;
    unless (defined $context) {	# Void context, auto-diag
	if ($diag[0] && $diag[0] != 2012) {
	    my $msg = "# CSV_XS ERROR: $diag[0] - $diag[1] \@ pos $diag[2]\n";
	    if ($self && ref $self) {	# auto_diag

		my $lvl = $self->{auto_diag};
		if ($lvl < 2) {
		    my @c = caller (2);
		    if (@c >= 11 && $c[10] && ref $c[10] eq "HASH") {
			my $hints = $c[10];
			(exists $hints->{autodie} && $hints->{autodie} or
			 exists $hints->{"guard Fatal"} &&
			!exists $hints->{"no Fatal"}) and
			    $lvl++;
			# Future releases of autodie will probably set $^H{autodie}
			#  to "autodie @args", like "autodie :all" or "autodie open"
			#  so we can/should check for "open" or "new"
			}
		    }
		$lvl > 1 ? die $msg : warn $msg;
		}
	    else {	# called without args in void context
		warn $msg;
		}
	    }
	return;
	}
    return $context ? @diag : $diag[1];
    } # error_diag

# string
#
#   object method returning the result of the most recent combine () or the
#   input to the most recent parse (), whichever is more recent.  there are
#   no side-effects.

sub string
{
    my $self = shift;
    return ref $self->{_STRING} ? ${$self->{_STRING}} : undef;
    } # string

# fields
#
#   object method returning the result of the most recent parse () or the
#   input to the most recent combine (), whichever is more recent.  there
#   are no side-effects.

sub fields
{
    my $self = shift;
    return ref $self->{_FIELDS} ? @{$self->{_FIELDS}} : undef;
    } # fields

# meta_info
#
#   object method returning the result of the most recent parse () or the
#   input to the most recent combine (), whichever is more recent.  there
#   are no side-effects. meta_info () returns (if available)  some of the
#   field's properties

sub meta_info
{
    my $self = shift;
    return ref $self->{_FFLAGS} ? @{$self->{_FFLAGS}} : undef;
    } # meta_info

sub is_quoted
{
    my ($self, $idx, $val) = @_;
    ref $self->{_FFLAGS} &&
	$idx >= 0 && $idx < @{$self->{_FFLAGS}} or return;
    $self->{_FFLAGS}[$idx] & 0x0001 ? 1 : 0;
    } # is_quoted

sub is_binary
{
    my ($self, $idx, $val) = @_;
    ref $self->{_FFLAGS} &&
	$idx >= 0 && $idx < @{$self->{_FFLAGS}} or return;
    $self->{_FFLAGS}[$idx] & 0x0002 ? 1 : 0;
    } # is_binary

# combine
#
#   object method returning success or failure.  the given arguments are
#   combined into a single comma-separated value.  failure can be the
#   result of no arguments or an argument containing an invalid character.
#   side-effects include:
#      setting status ()
#      setting fields ()
#      setting string ()
#      setting error_input ()

sub combine
{
    my $self = shift;
    my $str  = "";
    $self->{_FIELDS} = \@_;
    $self->{_FFLAGS} = undef;
    $self->{_STATUS} = (@_ > 0) && $self->Combine (\$str, \@_, 0);
    $self->{_STRING} = \$str;
    $self->{_STATUS};
    } # combine

# parse
#
#   object method returning success or failure.  the given argument is
#   expected to be a valid comma-separated value.  failure can be the
#   result of no arguments or an argument containing an invalid sequence
#   of characters. side-effects include:
#      setting status ()
#      setting fields ()
#      setting meta_info ()
#      setting string ()
#      setting error_input ()

sub parse
{
    my ($self, $str) = @_;

    my $fields = [];
    my $fflags = [];
    $self->{_STRING} = \$str;
    if (defined $str && $self->Parse ($str, $fields, $fflags)) {
	$self->{_ERROR_INPUT} = undef;
	$self->{_FIELDS} = $fields;
	$self->{_FFLAGS} = $fflags;
	$self->{_STATUS} = 1;
	}
    else {
	$self->{_FIELDS} = undef;
	$self->{_FFLAGS} = undef;
	$self->{_STATUS} = 0;
	}
    $self->{_STATUS};
    } # parse

sub column_names
{
    my ($self, @keys) = @_;
    @keys or
	return defined $self->{_COLUMN_NAMES} ? @{$self->{_COLUMN_NAMES}} : undef;

    @keys == 1 && ! defined $keys[0] and
	return $self->{_COLUMN_NAMES} = undef;

    if (@keys == 1 && ref $keys[0] eq "ARRAY") {
	@keys = @{$keys[0]};
	}
    elsif (join "", map { defined $_ ? ref $_ : "" } @keys) {
	croak ($self->SetDiag (3001));
	}

    $self->{_BOUND_COLUMNS} && @keys != @{$self->{_BOUND_COLUMNS}} and
	croak ($self->SetDiag (3003));

    $self->{_COLUMN_NAMES} = [ map { defined $_ ? $_ : "\cAUNDEF\cA" } @keys ];
    @{$self->{_COLUMN_NAMES}};
    } # column_names

sub bind_columns
{
    my ($self, @refs) = @_;
    @refs or
	return defined $self->{_BOUND_COLUMNS} ? @{$self->{_BOUND_COLUMNS}} : undef;

    @refs == 1 && ! defined $refs[0] and
	return $self->{_BOUND_COLUMNS} = undef;

    $self->{_COLUMN_NAMES} && @refs != @{$self->{_COLUMN_NAMES}} and
	croak ($self->SetDiag (3003));

    join "", map { ref $_ eq "SCALAR" ? "" : "*" } @refs and
	croak ($self->SetDiag (3004));

    $self->_set_attr_N ("_is_bound", scalar @refs);
    $self->{_BOUND_COLUMNS} = [ @refs ];
    @refs;
    } # bind_columns

sub getline_hr
{
    my ($self, @args, %hr) = @_;
    $self->{_COLUMN_NAMES} or croak ($self->SetDiag (3002));
    my $fr = $self->getline (@args) or return;
    @hr{@{$self->{_COLUMN_NAMES}}} = @$fr;
    \%hr;
    } # getline_hr

sub types
{
    my $self = shift;
    if (@_) {
	if (my $types = shift) {
	    $self->{_types} = join "", map { chr $_ } @{$types};
	    $self->{types}  = $types;
	    }
	else {
	    delete $self->{types};
	    delete $self->{_types};
	    undef;
	    }
	}
    else {
	$self->{types};
	}
    } # types

1;

__END__

=head1 NAME

Text::CSV_XS - comma-separated values manipulation routines

=head1 SYNOPSIS

 use Text::CSV_XS;

 my @rows;
 my $csv = Text::CSV_XS->new ({ binary => 1 }) or
     die "Cannot use CSV: ".Text::CSV->error_diag ();
 open my $fh, "<:encoding(utf8)", "test.csv" or die "test.csv: $!";
 while (my $row = $csv->getline ($fh)) {
     $row->[2] =~ m/pattern/ or next; # 3rd field should match
     push @rows, $row;
     }
 $csv->eof or $csv->error_diag ();
 close $fh;

 $csv->eol ("\r\n");
 open $fh, ">:encoding(utf8)", "new.csv" or die "new.csv: $!";
 $csv->print ($fh, $_) for @rows;
 close $fh or die "new.csv: $!";

=head1 DESCRIPTION

Text::CSV_XS provides facilities for the composition and decomposition of
comma-separated values.  An instance of the Text::CSV_XS class can combine
fields into a CSV string and parse a CSV string into fields.

The module accepts either strings or files as input and can utilize any
user-specified characters as delimiters, separators, and escapes so it is
perhaps better called ASV (anything separated values) rather than just CSV.

=head2 Embedded newlines

B<Important Note>: The default behavior is to only accept ascii characters.
This means that fields can not contain newlines. If your data contains
newlines embedded in fields, or characters above 0x7e (tilde), or binary data,
you *must* set C<< binary => 1 >> in the call to C<new ()>.  To cover the widest
range of parsing options, you will always want to set binary.

But you still have the problem that you have to pass a correct line to the
C<parse ()> method, which is more complicated from the usual point of
usage:

 my $csv = Text::CSV_XS->new ({ binary => 1, eol => $/ });
 while (<>) {		#  WRONG!
     $csv->parse ($_);
     my @fields = $csv->fields ();

will break, as the while might read broken lines, as that doesn't care
about the quoting. If you need to support embedded newlines, the way to go
is either

 my $csv = Text::CSV_XS->new ({ binary => 1, eol => $/ });
 while (my $row = $csv->getline (*ARGV)) {
     my @fields = @$row;

or, more safely in perl 5.6 and up

 my $csv = Text::CSV_XS->new ({ binary => 1, eol => $/ });
 open my $io, "<", $file or die "$file: $!";
 while (my $row = $csv->getline ($io)) {
     my @fields = @$row;

=head2 Unicode (UTF8)

On parsing (both for C<getline ()> and C<parse ()>), if the source is
marked being UTF8, then all fields that are marked binary will also be
be marked UTF8.

On combining (C<print ()> and C<combine ()>), if any of the combining
fields was marked UTF8, the resulting string will be marked UTF8.

For complete control over encoding, please use Text::CSV::Encoded:

    use Text::CSV::Encoded;
    my $csv = Text::CSV::Encoded->new ({
        encoding_in  => "iso-8859-1", # the encoding comes into   Perl
        encoding_out => "cp1252",     # the encoding comes out of Perl
        });

    $csv = Text::CSV::Encoded->new ({ encoding  => "utf8" });
    # combine () and print () accept *literally* utf8 encoded data
    # parse () and getline () return *literally* utf8 encoded data

    $csv = Text::CSV::Encoded->new ({ encoding  => undef }); # default
    # combine () and print () accept UTF8 marked data
    # parse () and getline () return UTF8 marked data

=head1 SPECIFICATION

While no formal specification for CSV exists, RFC 4180 1) describes a common
format and establishes "text/csv" as the MIME type registered with the IANA.

Many informal documents exist that describe the CSV format. How To: The Comma
Separated Value (CSV) File Format 2) provides an overview of the CSV format in
the most widely used applications and explains how it can best be used and
supported.

 1) http://tools.ietf.org/html/rfc4180
 2) http://www.creativyst.com/Doc/Articles/CSV/CSV01.htm

The basic rules are as follows:

B<CSV> is a delimited data format that has fields/columns separated by the comma
character and records/rows separated by newlines. Fields that contain a special
character (comma, newline, or double quote), must be enclosed in double quotes.
However, if a line contains a single entry which is the empty string, it may be
enclosed in double quotes. If a field's value contains a double quote character
it is escaped by placing another double quote character next to it. The CSV file
format does not require a specific character encoding, byte order, or line
terminator format.

=over 2

=item *

Each record is one line terminated by a line feed (ASCII/LF=0x0A) or a
carriage return and line feed pair (ASCII/CRLF=0x0D 0x0A), however,
line-breaks can be embedded.

=item *

Fields are separated by commas.

=item *

Allowable characters within a CSV field include 0x09 (tab) and the inclusive
range of 0x20 (space) through 0x7E (tilde). In binary mode all characters
are accepted, at least in quoted fields.

=item *

A field within CSV must be surrounded by double-quotes to contain a
the separator character (comma).

=back

Though this is the most clear and restrictive definition, Text::CSV_XS is way
more liberal than this, and allows extension:

=over 2

=item *

Line termination by a single carriage return is accepted by default

=item *

The separation-, escape-, and escape- characters can be any ASCII character
in the range from 0x20 (space) to 0x7E (tilde). Characters outside this range
may or may not work as expected. Multibyte characters, like U+060c (ARABIC
COMMA), U+FF0C (FULLWIDTH COMMA), U+241B (SYMBOL FOR ESCAPE), U+2424 (SYMBOL
FOR NEWLINE), U+FF02 (FULLWIDTH QUOTATION MARK), and U+201C (LEFT DOUBLE
QUOTATION MARK) (to give some examples of what might look promising) are
therefor not allowed.

If you use perl-5.8.2 or higher, these three attributes are utf8-decoded, to
increase the likelihood of success. This way U+00FE will be allowed as a
quote character.

=item *

A field within CSV must be surrounded by double-quotes to contain an embedded
double-quote, represented by a pair of consecutive double-quotes. In binary
mode you may additionally use the sequence C<"0> for representation of a
NULL byte.

=item *

Several violations of the above specification may be allowed by passing
options to the object creator.

=back

=head1 FUNCTIONS

=head2 version ()

(Class method) Returns the current module version.

=head2 new (\%attr)

(Class method) Returns a new instance of Text::CSV_XS. The objects
attributes are described by the (optional) hash ref C<\%attr>.
Currently the following attributes are available:

=over 4

=item eol

An end-of-line string to add to rows. C<undef> is replaced with an
empty string. The default is C<$\>. Common values for C<eol> are
C<"\012"> (Line Feed) or C<"\015\012"> (Carriage Return, Line Feed).
Cannot be longer than 7 (ASCII) characters.

If both C<$/> and C<eol> equal C<"\015">, parsing lines that end on
only a Carriage Return without Line Feed, will be C<parse>d correct.
Line endings, whether in C<$/> or C<eol>, other than C<undef>,
C<"\n">, C<"\r\n">, or C<"\r"> are not (yet) supported for parsing.

=item sep_char

The char used for separating fields, by default a comma. (C<,>).
Limited to a single-byte character, usually in the range from 0x20
(space) to 0x7e (tilde).

The separation character can not be equal to the quote character.
The separation character can not be equal to the escape character.

See also CAVEATS

=item allow_whitespace

When this option is set to true, whitespace (TAB's and SPACE's)
surrounding the separation character is removed when parsing. If
either TAB or SPACE is one of the three major characters C<sep_char>,
C<quote_char>, or C<escape_char> it will not be considered whitespace.

So lines like:

  1 , "foo" , bar , 3 , zapp

are now correctly parsed, even though it violates the CSV specs.

Note that B<all> whitespace is stripped from start and end of each
field. That would make it more a I<feature> than a way to be able
to parse bad CSV lines, as

 1,   2.0,  3,   ape  , monkey

will now be parsed as

 ("1", "2.0", "3", "ape", "monkey")

even if the original line was perfectly sane CSV.

=item blank_is_undef

Under normal circumstances, CSV data makes no distinction between
quoted- and unquoted empty fields. They both end up in an empty
string field once read, so

 1,"",," ",2

is read as

 ("1", "", "", " ", "2")

When I<writing> CSV files with C<always_quote> set, the unquoted empty
field is the result of an undefined value. To make it possible to also
make this distinction when reading CSV data, the C<blank_is_undef> option
will cause unquoted empty fields to be set to undef, causing the above to
be parsed as

 ("1", "", undef, " ", "2")

=item empty_is_undef

Going one step further than C<blank_is_undef>, this attribute converts
all empty fields to undef, so

 1,"",," ",2

is read as

 (1, undef, undef, " ", 2)

Note that this only effects fields that are I<realy> empty, not fields
that are empty after stripping allowed whitespace. YMMV.

=item quote_char

The char used for quoting fields containing blanks, by default the
double quote character (C<">). A value of undef suppresses
quote chars. (For simple cases only).
Limited to a single-byte character, usually in the range from 0x20
(space) to 0x7e (tilde).

The quote character can not be equal to the separation character.

=item allow_loose_quotes

By default, parsing fields that have C<quote_char> characters inside
an unquoted field, like

 1,foo "bar" baz,42

would result in a parse error. Though it is still bad practice to
allow this format, we cannot help there are some vendors that make
their applications spit out lines styled like this.

In case there is B<really> bad CSV data, like

 1,"foo "bar" baz",42

or

 1,""foo bar baz"",42

there is a way to get that parsed, and leave the quotes inside the quoted
field as-is. This can be achieved by setting C<allow_loose_quotes> B<AND>
making sure that the C<escape_char> is I<not> equal to C<quote_char>.

=item escape_char

The character used for escaping certain characters inside quoted fields.
Limited to a single-byte character, usually in the range from 0x20
(space) to 0x7e (tilde).

The C<escape_char> defaults to being the literal double-quote mark (C<">)
in other words, the same as the default C<quote_char>. This means that
doubling the quote mark in a field escapes it:

  "foo","bar","Escape ""quote mark"" with two ""quote marks""","baz"

If you change the default quote_char without changing the default
escape_char, the escape_char will still be the quote mark.  If instead
you want to escape the quote_char by doubling it, you will need to change
the escape_char to be the same as what you changed the quote_char to.

The escape character can not be equal to the separation character.

=item allow_loose_escapes

By default, parsing fields that have C<escape_char> characters that
escape characters that do not need to be escaped, like:

 my $csv = Text::CSV_XS->new ({ escape_char => "\\" });
 $csv->parse (qq{1,"my bar\'s",baz,42});

would result in a parse error. Though it is still bad practice to
allow this format, this option enables you to treat all escape character
sequences equal.

=item binary

If this attribute is TRUE, you may use binary characters in quoted fields,
including line feeds, carriage returns and NULL bytes. (The latter must
be escaped as C<"0>.) By default this feature is off.

If a string is marked UTF8, binary will be turned on automatically when
binary characters other than CR or NL are encountered. Note that a simple
string like C<"\x{00a0}"> might still be binary, but not marked UTF8, so
setting C<{ binary => 1 }> is still a wise option.

=item types

A set of column types; this attribute is immediately passed to the
I<types> method below. You must not set this attribute otherwise,
except for using the I<types> method. For details see the description
of the I<types> method below.

=item always_quote

By default the generated fields are quoted only, if they need to, for
example, if they contain the separator. If you set this attribute to
a TRUE value, then all fields will be quoted. This is typically easier
to handle in external applications. (Poor creatures who aren't using
Text::CSV_XS. :-)

=item quote_space

By default, a space in a field would trigger quotation. As no rule
exists this to be forced in CSV, nor any for the opposite, the default
is true for safety. You can exclude the space from this trigger by
setting this attribute to 0.

=item quote_null

By default, a NULL byte in a field would be escaped. This attribute
enables you to treat the NULL byte as a simple binary character in
binary mode (the C<{ binary => 1 }> is set). The default is true.
You can prevent NULL escapes by setting this attribute to 0.

=item keep_meta_info

By default, the parsing of input lines is as simple and fast as
possible. However, some parsing information - like quotation of
the original field - is lost in that process. Set this flag to
true to be able to retrieve that information after parsing with
the methods C<meta_info ()>, C<is_quoted ()>, and C<is_binary ()>
described below.  Default is false.

=item verbatim

This is a quite controversial attribute to set, but it makes hard
things possible.

The basic thought behind this is to tell the parser that the normally
special characters newline (NL) and Carriage Return (CR) will not be
special when this flag is set, and be dealt with as being ordinary
binary characters. This will ease working with data with embedded
newlines.

When C<verbatim> is used with C<getline ()>, C<getline ()>
auto-chomp's every line.

Imagine a file format like

  M^^Hans^Janssen^Klas 2\n2A^Ja^11-06-2007#\r\n

where, the line ending is a very specific "#\r\n", and the sep_char
is a ^ (caret). None of the fields is quoted, but embedded binary
data is likely to be present. With the specific line ending, that
shouldn't be too hard to detect.

By default, Text::CSV_XS' parse function however is instructed to only
know about "\n" and "\r" to be legal line endings, and so has to deal
with the embedded newline as a real end-of-line, so it can scan the next
line if binary is true, and the newline is inside a quoted field.
With this attribute however, we can tell parse () to parse the line
as if \n is just nothing more than a binary character.

For parse () this means that the parser has no idea about line ending
anymore, and getline () chomps line endings on reading.

=item auto_diag

Set to true will cause C<error_diag ()> to be automatically be called
in void context upon errors.

In case of error C<2012 - EOF>, this call will be void.

If set to a value greater than 1, it will die on errors instead of
warn.

Future extensions to this feature will include more reliable auto-detection
of the C<autodie> module being enabled, which will raise the value of
C<auto_diag> with C<1> on the moment the error is detected.

=back

To sum it up,

 $csv = Text::CSV_XS->new ();

is equivalent to

 $csv = Text::CSV_XS->new ({
     quote_char          => '"',
     escape_char         => '"',
     sep_char            => ',',
     eol                 => $\,
     always_quote        => 0,
     quote_space         => 1,
     quote_null	         => 1,
     binary              => 0,
     keep_meta_info      => 0,
     allow_loose_quotes  => 0,
     allow_loose_escapes => 0,
     allow_whitespace    => 0,
     blank_is_undef      => 0,
     empty_is_undef      => 0,
     verbatim            => 0,
     auto_diag           => 0,
     });

For all of the above mentioned flags, there is an accessor method
available where you can inquire for the current value, or change
the value

 my $quote = $csv->quote_char;
 $csv->binary (1);

It is unwise to change these settings halfway through writing CSV
data to a stream. If however, you want to create a new stream using
the available CSV object, there is no harm in changing them.

If the C<new ()> constructor call fails, it returns C<undef>, and makes
the fail reason available through the C<error_diag ()> method.

 $csv = Text::CSV_XS->new ({ ecs_char => 1 }) or
     die "".Text::CSV_XS->error_diag ();

C<error_diag ()> will return a string like

 "INI - Unknown attribute 'ecs_char'"

=head2 print

 $status = $csv->print ($io, $colref);

Similar to C<combine () + string () + print>, but more efficient. It
expects an array ref as input (not an array!) and the resulting string is
not really created, but immediately written to the I<$io> object, typically
an IO handle or any other object that offers a I<print> method. Note, this
implies that the following is wrong in perl 5.005_xx and older:

 open FILE, ">", "whatever";
 $status = $csv->print (\*FILE, $colref);

as in perl 5.005 and older, the glob C<\*FILE> is not an object, thus it
doesn't have a print method. The solution is to use an IO::File object or
to hide the glob behind an IO::Wrap object. See L<IO::File> and L<IO::Wrap>
for details.

For performance reasons the print method doesn't create a result string.
In particular the I<$csv-E<gt>string ()>, I<$csv-E<gt>status ()>,
I<$csv->fields ()> and I<$csv-E<gt>error_input ()> methods are meaningless
after executing this method.

=head2 combine

 $status = $csv->combine (@columns);

This object function constructs a CSV string from the arguments, returning
success or failure.  Failure can result from lack of arguments or an argument
containing an invalid character.  Upon success, C<string ()> can be called to
retrieve the resultant CSV string.  Upon failure, the value returned by
C<string ()> is undefined and C<error_input ()> can be called to retrieve an
invalid argument.

=head2 string

 $line = $csv->string ();

This object function returns the input to C<parse ()> or the resultant CSV
string of C<combine ()>, whichever was called more recently.

=head2 getline

 $colref = $csv->getline ($io);

This is the counterpart to print, like parse is the counterpart to
combine: It reads a row from the IO object $io using $io->getline ()
and parses this row into an array ref. This array ref is returned
by the function or undef for failure.

When fields are bound with C<bind_columns ()>, the return value is a
reference to an empty list.

The I<$csv-E<gt>string ()>, I<$csv-E<gt>fields ()> and I<$csv-E<gt>status ()>
methods are meaningless, again.

=head2 parse

 $status = $csv->parse ($line);

This object function decomposes a CSV string into fields, returning
success or failure.  Failure can result from a lack of argument or the
given CSV string is improperly formatted.  Upon success, C<fields ()> can
be called to retrieve the decomposed fields .  Upon failure, the value
returned by C<fields ()> is undefined and C<error_input ()> can be called
to retrieve the invalid argument.

You may use the I<types ()> method for setting column types. See the
description below.

=head2 getline_hr

The C<getline_hr ()> and C<column_names ()> methods work together to allow
you to have rows returned as hashrefs. You must call C<column_names ()>
first to declare your column names.

 $csv->column_names (qw( code name price description ));
 $hr = $csv->getline_hr ($io);
 print "Price for $hr->{name} is $hr->{price} EUR\n";

C<getline_hr ()> will croak if called before C<column_names ()>.

=head2 column_names

Set the keys that will be used in the C<getline_hr ()> calls. If no keys
(column names) are passed, it'll return the current setting.

C<column_names ()> accepts a list of scalars (the column names) or a
single array_ref, so you can pass C<getline ()>

  $csv->column_names ($csv->getline ($io));

C<column_names ()> does B<no> checking on duplicates at all, which might
lead to unwanted results. Undefined entries will be replaced with the
string C<"\cAUNDEF\cA">, so

  $csv->column_names (undef, "", "name", "name");
  $hr = $csv->getline_hr ($io);

Will set C<$hr->{"\cAUNDEF\cA"}> to the 1st field, C<$hr->{""}> to the
2nd field, and C<$hr->{name}> to the 4th field, discarding the 3rd field.

C<column_names ()> croaks on invalid arguments.

=head2 bind_columns

Takes a list of references to scalars to store the fields fetched
C<getline ()> in. When you don't pass enough references to store the
fetched fields in, C<getline ()> will fail. If you pass more than there are
fields to return, the remaining references are left untouched.

  $csv->bind_columns (\$code, \$name, \$price, \$description);
  while ($csv->getline ($io)) {
      print "The price of a $name is \x{20ac} $price\n";
      }

=head2 eof

 $eof = $csv->eof ();

If C<parse ()> or C<getline ()> was used with an IO stream, this
method will return true (1) if the last call hit end of file, otherwise
it will return false (''). This is useful to see the difference between
a failure and end of file.

=head2 types

 $csv->types (\@tref);

This method is used to force that columns are of a given type. For
example, if you have an integer column, two double columns and a
string column, then you might do a

 $csv->types ([Text::CSV_XS::IV (),
               Text::CSV_XS::NV (),
               Text::CSV_XS::NV (),
               Text::CSV_XS::PV ()]);

Column types are used only for decoding columns, in other words
by the I<parse ()> and I<getline ()> methods.

You can unset column types by doing a

 $csv->types (undef);

or fetch the current type settings with

 $types = $csv->types ();

=over 4

=item IV

Set field type to integer.

=item NV

Set field type to numeric/float.

=item PV

Set field type to string.

=back

=head2 fields

 @columns = $csv->fields ();

This object function returns the input to C<combine ()> or the resultant
decomposed fields of C successful <parse ()>, whichever was called more
recently.

Note that the return value is undefined after using C<getline ()>, which
does not fill the data structures returned by C<parse ()>.

=head2 meta_info

 @flags = $csv->meta_info ();

This object function returns the flags of the input to C<combine ()> or
the flags of the resultant decomposed fields of C<parse ()>, whichever
was called more recently.

For each field, a meta_info field will hold flags that tell something about
the field returned by the C<fields ()> method or passed to the C<combine ()>
method. The flags are bitwise-or'd like:

=over 4

=item 0x0001

The field was quoted.

=item 0x0002

The field was binary.

=back

See the C<is_*** ()> methods below.

=head2 is_quoted

  my $quoted = $csv->is_quoted ($column_idx);

Where C<$column_idx> is the (zero-based) index of the column in the
last result of C<parse ()>.

This returns a true value if the data in the indicated column was
enclosed in C<quote_char> quotes. This might be important for data
where C<,20070108,> is to be treated as a numeric value, and where
C<,"20070108",> is explicitly marked as character string data.

=head2 is_binary

  my $binary = $csv->is_binary ($column_idx);

Where C<$column_idx> is the (zero-based) index of the column in the
last result of C<parse ()>.

This returns a true value if the data in the indicated column
contained any byte in the range [\x00-\x08,\x10-\x1F,\x7F-\xFF]

=head2 status

 $status = $csv->status ();

This object function returns success (or failure) of C<combine ()> or
C<parse ()>, whichever was called more recently.

=head2 error_input

 $bad_argument = $csv->error_input ();

This object function returns the erroneous argument (if it exists) of
C<combine ()> or C<parse ()>, whichever was called more recently.

=head2 error_diag

 Text::CSV_XS->error_diag ();
 $csv->error_diag ();
 $error_code   = 0  + $csv->error_diag ();
 $error_str    = "" . $csv->error_diag ();
 ($cde, $str, $pos) = $csv->error_diag ();

If (and only if) an error occured, this function returns the diagnostics
of that error.

If called in void context, it will print the internal error code and the
associated error message to STDERR.

If called in list context, it will return the error code and the error
message in that order. If the last error was from parsing, the third
value returned is a best guess at the location within the line that was
being parsed. It's value is 1-based. See C<examples/csv-check> for how
this can be used.

If called in scalar context, it will return the diagnostics in a single
scalar, a-la $!. It will contain the error code in numeric context, and
the diagnostics message in string context.

When called as a class method or a direct function call, the error diag
is that of the last C<new ()> call.

=head2 SetDiag

 $csv->SetDiag (0);

Use to reset the diagnostics if you are dealing with errors.

=head1 INTERNALS

=over 4

=item Combine (...)

=item Parse (...)

=back

The arguments to these two internal functions are deliberately not
described or documented to enable the module author(s) to change it
when they feel the need for it and using them is highly discouraged
as the API may change in future releases.

=head1 EXAMPLES

Reading a CSV file line by line:

  my $csv = Text::CSV_XS->new ({ binary => 1 });
  open my $fh, "<", "file.csv" or die "file.csv: $!";
  while (my $row = $csv->getline ($fh)) {
      # do something with @$row
      }
  $csv->eof or $csv->error_diag;
  close $fh or die "file.csv: $!";

Parsing CSV strings:

  my $csv = Text::CSV_XS->new ({ keep_meta_info => 1, binary => 1 });

  my $sample_input_string =
      qq{"I said, ""Hi!""",Yes,"",2.34,,"1.09","\x{20ac}",};
  if ($csv->parse ($sample_input_string)) {
      my @field = $csv->fields;
      foreach my $col (0 .. $#field) {
          my $quo = $csv->is_quoted ($col) ? $csv->{quote_char} : "";
          printf "%2d: %s%s%s\n", $col, $quo, $field[$col], $quo;
          }
      }
  else {
      print STDERR "parse () failed on argument: ",
	  $csv->error_input, "\n";
      $csv->error_diag ();
      }

An example for creating CSV files using the C<print ()> method, like in
dumping the content of a database ($dbh) table ($tbl) to CSV:

  my $csv = Text::CSV_XS->new ({ binary => 1, eol => $/ });
  open my $fh, ">", "$tbl.csv" or die "$tbl.csv: $!";
  my $sth = $dbh->prepare ("select * from $tbl");
  $sth->execute;
  $csv->print ($fh, $sth->{NAME_lc});
  while (my $row = $sth->fetch) {
      $csv->print ($fh, $row) or $csv->error_diag;
      }
  close $fh or die "$tbl.csv: $!";

or using the slower C<combine ()> and C<string ()> methods:

  my $csv = Text::CSV_XS->new;

  open my $csv_fh, ">", "hello.csv" or die "hello.csv: $!";

  my @sample_input_fields = (
      'You said, "Hello!"',   5.67,
      '"Surely"',   '',   '3.14159');
  if ($csv->combine (@sample_input_fields)) {
      print $csv_fh $csv->string, "\n";
      }
  else {
      print "combine () failed on argument: ",
	  $csv->error_input, "\n";
      }
  close $csv_fh or die "hello.csv: $!";

For more extended examples, see the C<examples/> subdirectory in the
original distribution or the git repository at
http://repo.or.cz/w/Text-CSV_XS.git?a=tree;f=examples. The following files
can be found there:

=over 2

=item parser-xs.pl

This can be used as a boilerplate to `fix' bad CSV and parse beyond errors.

  $ perl examples/parser-xs.pl bad.csv >good.csv

=item csv-check

This is a command-line tool that uses parser-xs.pl techniques to check the
CSV file and report on its content.

  $ csv-check files/utf8.csv
  Checked with examples/csv-check 1.2 using Text::CSV_XS 0.61
  OK: rows: 1, columns: 2
      sep = <,>, quo = <">, bin = <1>

=item csv2xls

A script to convert CSV to Microsoft Excel. This requires L<Date::Calc>
and L<Spreadsheet::WriteExcel>. The converter accepts various options and
can produce UTF-8 Excel files.

=item csvdiff

A script that provides colorized diff on sorted CSV files, assuming first
line is header and first field is the key. Output options include colorized
ANSI escape codes or HTML.

  $ csvdiff --html --output=diff.html file1.csv file2.csv

=back

=head1 CAVEATS

C<Text::CSV_XS> is not designed to detect the characters used for field
separation and quoting. The parsing is done using predefined settings. In
the examples subdirectory, you can find scripts that demonstrate how you
can try to detect these characters yourself.

=head2 Microsoft Excel

The import/export from Microsoft Excel is a I<risky task>, according to the
documentation in C<Text::CSV::Separator>. Microsoft uses the system's default
list separator defined in the regional settings, which happens to be a
semicolon for Dutch, German and Spanish (and probably some others as well).
For the English locale, the default is a comma. In Windows however, the user
is free to choose a predefined locale, and then change every individual
setting in it, so checking the locale is no solution.

=head1 TODO

=over 2

=item More Errors & Warnings

New extensions ought to be clear and concise in reporting what error
occurred where and why, and possibly also tell a remedy to the problem.
error_diag is a (very) good start, but there is more work to be done here.

Basic calls should croak or warn on illegal parameters. Errors should be
documented.

=item setting meta info

Future extensions might include extending the C<meta_info ()>,
C<is_quoted ()>, and C<is_binary ()> to accept setting these flags
for fields, so you can specify which fields are quoted in the
combine ()/string () combination.

  $csv->meta_info (0, 1, 1, 3, 0, 0);
  $csv->is_quoted (3, 1);

=item combined methods

Requests for adding means (methods) that combine C<combine ()> and
C<string ()> in a single call will B<not> be honored. Likewise for
C<parse ()> and C<fields ()>. Given the trouble with embedded newlines,
Using C<getline ()> and C<print ()> instead is the preferred way to go.

=item Parse the whole file at once

Implement a new methods that enables the parsing of a complete file
at once, returning a lis of hashes. Possible extension to this could
be to enable a column selection on the call:

   my @AoH = $csv->parse_file ($filename, { cols => [ 1, 4..8, 12 ]});

Returning something like

   [ { fields => [ 1, 2, "foo", 4.5, undef, "", 8 ],
       flags  => [ ... ],
       errors => [ ... ],
       },
     { fields => [ ... ],
       .
       .
       },
     ]

=item EBCDIC

The hard-coding of characters and character ranges makes this module
unusable on EBCDIC system. Using some #ifdef structure could enable
these again without loosing speed. Testing would be the hard part.

Opening EBCDIC encode files on ASCII+ systems is likely to succeed
using Encode's cp37, cp1047, or posix-bc:

  open my $fh, "<:encoding(cp1047)", "ebcdic_file.csv" or die "...";

=back

=head1 Release plan

No guarantees, but this is what I have in mind right now:

=over 2

=item next

 - This might very well be 1.00
 - DIAGNOSTICS setction in pod to *describe* the errors (see below)
 - croak / carp

=item next + 1

 - csv2csv - a script to regenerate a CSV file to follow standards
 - EBCDIC support

=back

=head1 DIAGNOSTICS

Still under construction ...

If an error occured, C<$csv->error_diag ()> can be used to get more information
on the cause of the failure. Note that for speed reasons, the internal value
is never cleared on success, so using the value returned by C<error_diag ()> in
normal cases - when no error occured - may cause unexpected results.

If the constructor failed, the cause can be found using C<error_diag ()> as a
class method, like C<Text::CSV_XS->error_diag ()>.

C<$csv->error_diag ()> is automatically called upon error when the contractor
was called with C<auto_diag> set to 1 or 2, or when C<autodie> is in effect.
When set to 1, this will cause a C<warn ()> with the error message, when set
to 2, it will C<die ()>. C<2012 - EOF> is excluded from C<auto_diag> reports.

Currently errors as described below are available. I've tried to make the error
itself explanatory enough, but more descriptions will be added. For most of
these errors, the first three capitals describe the error category:

=over 2

=item INI

Initialization error or option conflict.

=item ECR

Carriage-Return related parse error.

=item EOF

End-Of-File related parse error.

=item EIQ

Parse error inside quotation.

=item EIF

Parse error inside field.

=item ECB

Combine error.

=item EHR

HashRef parse related error.

=back

=over 2

=item 1001 "INI - sep_char is equal to quote_char or escape_char"

The separation character cannot be equal to either the quotation character
or the escape character, as that will invalidate all parsing rules.

=item 1002 "INI - allow_whitespace with escape_char or quote_char SP or TAB"

Using C<allow_whitespace> when either C<escape_char> or C<quote_char> is
equal to SPACE or TAB is too ambiguous to allow.

=item 1003 "INI - \r or \n in main attr not allowed"

Using default C<eol> characters in either C<sep_char>, C<quote_char>, or
C<escape_char> is not allowed.

=item 2010 "ECR - QUO char inside quotes followed by CR not part of EOL"

When C<eol> has been set to something specific, other than the default,
like C<"\r\t\n">, and the C<"\r"> is following the B<second> (closing)
C<quote_char>, where the characters following the C<"\r"> do not make up
the C<eol> sequence, this is an error.

=item 2011 "ECR - Characters after end of quoted field"

Sequences like C<1,foo,"bar"baz,2> are not allowed. C<"bar"> is a quoted
field, and after the closing quote, there should be either a new-line
sequence or a separation character.

=item 2012 "EOF - End of data in parsing input stream"

Self-explaining. End-of-file while inside parsing a stream. Can only
happen when reading from streams with C<getline ()>, as using C<parse ()>
is done on strings that are not required to have a trailing C<eol>.

=item 2021 "EIQ - NL char inside quotes, binary off"

Sequences like C<1,"foo\nbar",2> are only allowed when the binary option
has been selected with the constructor.

=item 2022 "EIQ - CR char inside quotes, binary off"

Sequences like C<1,"foo\rbar",2> are only allowed when the binary option
has been selected with the constructor.

=item 2023 "EIQ - QUO character not allowed"

Sequences like C<"foo "bar" baz",quux> and C<2023,",2008-04-05,"Foo, Bar",\n>
will cause this error.

=item 2024 "EIQ - EOF cannot be escaped, not even inside quotes"

The escape character is not allowed as last character in an input stream.

=item 2025 "EIQ - Loose unescaped escape"

An escape character should escape only characters that need escaping. Allowing
the escape for other characters is possible with the C<allow_loose_escape>
attribute.

=item 2026 "EIQ - Binary character inside quoted field, binary off"

Binary characters are not allowed by default. Exceptions are fields that
contain valid UTF-8, that will automatically be upgraded is the content is
valid UTF-8. Pass the C<binary> attribute with a true value to accept binary
characters.

=item 2027 "EIQ - Quoted field not terminated"

When parsing a field that started with a quotation character, the field is
expected to be closed with a quotation character. When the parsed line is
exhausted before the quote is found, that field is not terminated.

=item 2030 "EIF - NL char inside unquoted verbatim, binary off"

=item 2031 "EIF - CR char is first char of field, not part of EOL"

=item 2032 "EIF - CR char inside unquoted, not part of EOL"

=item 2034 "EIF - Loose unescaped quote"

=item 2035 "EIF - Escaped EOF in unquoted field"

=item 2036 "EIF - ESC error"

=item 2037 "EIF - Binary character in unquoted field, binary off"

=item 2110 "ECB - Binary character in Combine, binary off"

=item 2200 "EIO - print to IO failed. See errno"

=item 3001 "EHR - Unsupported syntax for column_names ()"

=item 3002 "EHR - getline_hr () called before column_names ()"

=item 3003 "EHR - bind_columns () and column_names () fields count mismatch"

=item 3004 "EHR - bind_columns () only accepts refs to scalars"

=item 3006 "EHR - bind_columns () did not pass enough refs for parsed fields"

=item 3007 "EHR - bind_columns needs refs to writeable scalars"

=item 3008 "EHR - unexpected error in bound fields"

=back

=head1 SEE ALSO

L<perl>, L<IO::File>, L<IO::Handle>, L<IO::Wrap>, L<Text::CSV>,
L<Text::CSV_PP>, L<Text::CSV::Encoded>, L<Text::CSV::Separator>,
and L<Spreadsheet::Read>.

=head1 AUTHORS and MAINTAINERS

Alan Citterman F<E<lt>alan@mfgrtl.comE<gt>> wrote the original Perl
module. Please don't send mail concerning Text::CSV_XS to Alan, as
he's not involved in the C part which is now the main part of the
module.

Jochen Wiedmann F<E<lt>joe@ispsoft.deE<gt>> rewrote the encoding and
decoding in C by implementing a simple finite-state machine and added
the variable quote, escape and separator characters, the binary mode
and the print and getline methods. See ChangeLog releases 0.10 through
0.23.

H.Merijn Brand F<E<lt>h.m.brand@xs4all.nlE<gt>> cleaned up the code,
added the field flags methods, wrote the major part of the test suite,
completed the documentation, fixed some RT bugs and added all the allow
flags. See ChangeLog releases 0.25 and on.

=head1 COPYRIGHT AND LICENSE

Copyright (C) 2007-2010 H.Merijn Brand for PROCURA B.V.
Copyright (C) 1998-2001 Jochen Wiedmann. All rights reserved.
Portions Copyright (C) 1997 Alan Citterman. All rights reserved.

This library is free software; you can redistribute it and/or modify
it under the same terms as Perl itself.

=cut