/usr/share/perl5/Bio/SeqIO/embl.pm is in libbio-perl-perl 1.6.923-1.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
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 | #
# BioPerl module for Bio::SeqIO::EMBL
#
# Please direct questions and support issues to <bioperl-l@bioperl.org>
#
# Cared for by Ewan Birney <birney@ebi.ac.uk>
#
# Copyright Ewan Birney
#
# You may distribute this module under the same terms as perl itself
# POD documentation - main docs before the code
=head1 NAME
Bio::SeqIO::embl - EMBL sequence input/output stream
=head1 SYNOPSIS
It is probably best not to use this object directly, but
rather go through the SeqIO handler system. Go:
$stream = Bio::SeqIO->new(-file => $filename, -format => 'EMBL');
while ( (my $seq = $stream->next_seq()) ) {
# do something with $seq
}
=head1 DESCRIPTION
This object can transform Bio::Seq objects to and from EMBL flat
file databases.
There is a lot of flexibility here about how to dump things which
should be documented more fully.
There should be a common object that this and Genbank share (probably
with Swissprot). Too much of the magic is identical.
=head2 Optional functions
=over 3
=item _show_dna()
(output only) shows the dna or not
=item _post_sort()
(output only) provides a sorting func which is applied to the FTHelpers
before printing
=item _id_generation_func()
This is function which is called as
print "ID ", $func($annseq), "\n";
To generate the ID line. If it is not there, it generates a sensible ID
line using a number of tools.
If you want to output annotations in EMBL format they need to be
stored in a Bio::Annotation::Collection object which is accessible
through the Bio::SeqI interface method L<annotation()|annotation>.
The following are the names of the keys which are polled from a
L<Bio::Annotation::Collection> object.
reference - Should contain Bio::Annotation::Reference objects
comment - Should contain Bio::Annotation::Comment objects
dblink - Should contain Bio::Annotation::DBLink objects
=back
=head1 FEEDBACK
=head2 Mailing Lists
User feedback is an integral part of the evolution of this and other
Bioperl modules. Send your comments and suggestions preferably to one
of the Bioperl mailing lists. Your participation is much appreciated.
bioperl-l@bioperl.org - General discussion
http://bioperl.org/wiki/Mailing_lists - About the mailing lists
=head2 Support
Please direct usage questions or support issues to the mailing list:
I<bioperl-l@bioperl.org>
rather than to the module maintainer directly. Many experienced and
reponsive experts will be able look at the problem and quickly
address it. Please include a thorough description of the problem
with code and data examples if at all possible.
=head2 Reporting Bugs
Report bugs to the Bioperl bug tracking system to help us keep track
the bugs and their resolution. Bug reports can be submitted via
the web:
https://redmine.open-bio.org/projects/bioperl/
=head1 AUTHOR - Ewan Birney
Email birney@ebi.ac.uk
=head1 APPENDIX
The rest of the documentation details each of the object
methods. Internal methods are usually preceded with a _
=cut
# Let the code begin...
package Bio::SeqIO::embl;
use vars qw(%FTQUAL_NO_QUOTE);
use strict;
use Bio::SeqIO::FTHelper;
use Bio::SeqFeature::Generic;
use Bio::Species;
use Bio::Seq::SeqFactory;
use Bio::Annotation::Collection;
use Bio::Annotation::Comment;
use Bio::Annotation::Reference;
use Bio::Annotation::DBLink;
use base qw(Bio::SeqIO);
# Note that a qualifier that exceeds one line (i.e. a long label) will
# automatically be quoted regardless:
%FTQUAL_NO_QUOTE=(
'anticodon'=>1,
'citation'=>1,
'codon'=>1,
'codon_start'=>1,
'cons_splice'=>1,
'direction'=>1,
'evidence'=>1,
'label'=>1,
'mod_base'=> 1,
'number'=> 1,
'rpt_type'=> 1,
'rpt_unit'=> 1,
'transl_except'=> 1,
'transl_table'=> 1,
'usedin'=> 1,
);
sub _initialize {
my($self,@args) = @_;
$self->SUPER::_initialize(@args);
# hash for functions for decoding keys.
$self->{'_func_ftunit_hash'} = {};
# sets this to one by default. People can change it
$self->_show_dna(1);
if ( ! defined $self->sequence_factory ) {
$self->sequence_factory(Bio::Seq::SeqFactory->new
(-verbose => $self->verbose(),
-type => 'Bio::Seq::RichSeq'));
}
}
=head2 next_seq
Title : next_seq
Usage : $seq = $stream->next_seq()
Function: returns the next sequence in the stream
Returns : Bio::Seq object
Args :
=cut
sub next_seq {
my ($self,@args) = @_;
my ($pseq,$c,$line,$name,$desc,$acc,$seqc,$mol,$div,
$date, $comment, @date_arr);
my ($annotation, %params, @features) =
Bio::Annotation::Collection->new();
$line = $self->_readline;
# This needs to be before the first eof() test
if ( !defined $line ) {
return; # no throws - end of file
}
if ( $line =~ /^\s+$/ ) {
while ( defined ($line = $self->_readline) ) {
$line =~/^\S/ && last;
}
# return without error if the whole next sequence was just a single
# blank line and then eof
return unless $line;
}
# no ID as 1st non-blank line, need short circuit and exit routine
$self->throw("EMBL stream with no ID. Not embl in my book")
unless $line =~ /^ID\s+\S+/;
# At this point we are sure that $line contains an ID header line
my $alphabet;
if ( $line =~ tr/;/;/ == 6) { # New style headers contain exactly six semicolons.
# New style header (EMBL Release >= 87, after June 2006)
my $topology;
my $sv;
# ID DQ299383; SV 1; linear; mRNA; STD; MAM; 431 BP.
# This regexp comes from the new2old.pl conversion script, from EBI
if ($line =~ m/^ID (\w+);\s+SV (\d+); (\w+); ([^;]+); (\w{3}); (\w{3}); (\d+) BP./) {
($name, $sv, $topology, $mol, $div) = ($1, $2, $3, $4, $6);
}
if (defined $sv) {
$params{'-seq_version'} = $sv;
$params{'-version'} = $sv;
}
if (defined $topology && $topology eq 'circular') {
$params{'-is_circular'} = 1;
}
if (defined $mol ) {
if ($mol =~ /DNA/) {
$alphabet = 'dna';
} elsif ($mol =~ /RNA/) {
$alphabet = 'rna';
} elsif ($mol =~ /AA/) {
$alphabet = 'protein';
}
}
} else {
# Old style header (EMBL Release < 87, before June 2006)
if ($line =~ /^ID\s+(\S+)[^;]*;\s+(\S+)[^;]*;\s+(\S+)[^;]*;/) {
($name, $mol, $div) = ($1, $2, $3);
}
if ($mol) {
if ( $mol =~ /circular/ ) {
$params{'-is_circular'} = 1;
$mol =~ s|circular ||;
}
if (defined $mol ) {
if ($mol =~ /DNA/) {
$alphabet='dna';
} elsif ($mol =~ /RNA/) {
$alphabet='rna';
} elsif ($mol =~ /AA/) {
$alphabet='protein';
}
}
}
}
unless( defined $name && length($name) ) {
$name = "unknown_id";
}
# $self->warn("not parsing upper annotation in EMBL file yet!");
my $buffer = $line;
local $_;
BEFORE_FEATURE_TABLE :
my $ncbi_taxid;
until ( !defined $buffer ) {
$_ = $buffer;
# Exit at start of Feature table
if ( /^(F[HT]|SQ)/ ) {
$self->_pushback($_) if( $1 eq 'SQ' || $1 eq 'FT');
last;
}
# Description line(s)
if (/^DE\s+(\S.*\S)/) {
$desc .= $desc ? " $1" : $1;
}
#accession number
if ( /^AC\s+(.*)?/ || /^PA\s+(.*)?/) {
my @accs = split(/[; ]+/, $1); # allow space in addition
$params{'-accession_number'} = shift @accs
unless defined $params{'-accession_number'};
push @{$params{'-secondary_accessions'}}, @accs;
}
#version number
if ( /^SV\s+\S+\.(\d+);?/ ) {
my $sv = $1;
#$sv =~ s/\;//;
$params{'-seq_version'} = $sv;
$params{'-version'} = $sv;
}
#date (NOTE: takes last date line)
if ( /^DT\s+(.+)$/ ) {
my $line = $1;
my ($date, $version) = split(' ', $line, 2);
$date =~ tr/,//d; # remove comma if new version
if ($version) {
if ($version =~ /\(Rel\. (\d+), Created\)/xms ) {
my $release = Bio::Annotation::SimpleValue->new(
-tagname => 'creation_release',
-value => $1
);
$annotation->add_Annotation($release);
} elsif ($version =~ /\(Rel\. (\d+), Last updated, Version (\d+)\)/xms ) {
my $release = Bio::Annotation::SimpleValue->new(
-tagname => 'update_release',
-value => $1
);
$annotation->add_Annotation($release);
my $update = Bio::Annotation::SimpleValue->new(
-tagname => 'update_version',
-value => $2
);
$annotation->add_Annotation($update);
}
}
push @{$params{'-dates'}}, $date;
}
#keywords
if ( /^KW (.*)\S*$/ ) {
my @kw = split(/\s*\;\s*/,$1);
push @{$params{'-keywords'}}, @kw;
}
# Organism name and phylogenetic information
elsif (/^O[SC]/) {
# pass the accession number so we can give an informative throw message if necessary
my $species = $self->_read_EMBL_Species(\$buffer, $params{'-accession_number'});
$params{'-species'}= $species;
}
# NCBI TaxID Xref
elsif (/^OX/) {
if (/NCBI_TaxID=(\d+)/) {
$ncbi_taxid=$1;
}
my @links = $self->_read_EMBL_TaxID_DBLink(\$buffer);
foreach my $dblink ( @links ) {
$annotation->add_Annotation('dblink',$dblink);
}
}
# References
elsif (/^R/) {
my @refs = $self->_read_EMBL_References(\$buffer);
foreach my $ref ( @refs ) {
$annotation->add_Annotation('reference',$ref);
}
}
# DB Xrefs
elsif (/^DR/) {
my @links = $self->_read_EMBL_DBLink(\$buffer);
foreach my $dblink ( @links ) {
$annotation->add_Annotation('dblink',$dblink);
}
}
# Comments
elsif (/^CC\s+(.*)/) {
$comment .= $1;
$comment .= " ";
while (defined ($_ = $self->_readline) ) {
if (/^CC\s+(.*)/) {
$comment .= $1;
$comment .= " ";
} else {
last;
}
}
my $commobj = Bio::Annotation::Comment->new();
$commobj->text($comment);
$annotation->add_Annotation('comment',$commobj);
$comment = "";
}
# Get next line.
$buffer = $self->_readline;
}
while ( defined ($_ = $self->_readline) ) {
/^FT\s{3}\w/ && last;
/^SQ / && last;
/^CO / && last;
}
$buffer = $_;
if (defined($buffer) && $buffer =~ /^FT /) {
until ( !defined ($buffer) ) {
my $ftunit = $self->_read_FTHelper_EMBL(\$buffer);
# process ftunit
my $feat =
$ftunit->_generic_seqfeature($self->location_factory(), $name);
# add taxon_id from source if available
# Notice, this will override what is found in the OX line.
# this is by design as this seems to be the official way
# of specifying a TaxID
if ($params{'-species'} && ($feat->primary_tag eq 'source')
&& $feat->has_tag('db_xref')
&& (! $params{'-species'}->ncbi_taxid())) {
foreach my $tagval ($feat->get_tag_values('db_xref')) {
if (index($tagval,"taxon:") == 0) {
$params{'-species'}->ncbi_taxid(substr($tagval,6));
last;
}
}
}
# add feature to list of features
push(@features, $feat);
if ( $buffer !~ /^FT/ ) {
last;
}
}
}
# Set taxid found in OX line
if ($params{'-species'} && defined $ncbi_taxid
&& (! $params{'-species'}->ncbi_taxid())) {
$params{'-species'}->ncbi_taxid($ncbi_taxid);
}
# skip comments
while ( defined ($buffer) && $buffer =~ /^XX/ ) {
$buffer = $self->_readline();
}
if ( $buffer =~ /^CO/ ) {
# bug#2982
# special : create contig as annotation
while ( defined ($buffer) ) {
$annotation->add_Annotation($_) for $self->_read_EMBL_Contig(\$buffer);
if ( !$buffer || $buffer !~ /^CO/ ) {
last;
}
}
$buffer ||= '';
}
if ($buffer !~ /^\/\//) { # if no SQ lines following CO (bug#2958)
if ( $buffer !~ /^SQ/ ) {
while ( defined ($_ = $self->_readline) ) {
/^SQ/ && last;
}
}
$seqc = "";
while ( defined ($_ = $self->_readline) ) {
m{^//} && last;
$_ = uc($_);
s/[^A-Za-z]//g;
$seqc .= $_;
}
}
my $seq = $self->sequence_factory->create
(-verbose => $self->verbose(),
-division => $div,
-seq => $seqc,
-desc => $desc,
-display_id => $name,
-annotation => $annotation,
-molecule => $mol,
-alphabet => $alphabet,
-features => \@features,
%params);
return $seq;
}
=head2 _write_ID_line
Title : _write_ID_line
Usage : $self->_write_ID_line($seq);
Function: Writes the EMBL Release 87 format ID line to the stream, unless
: there is a user-supplied ID line generation function in which
: case that is used instead.
: ( See Bio::SeqIO::embl::_id_generation_function(). )
Returns : nothing
Args : Bio::Seq object
=cut
sub _write_ID_line {
my ($self, $seq) = @_;
my $id_line;
# If there is a user-supplied ID generation function, use it.
if ( $self->_id_generation_func ) {
$id_line = "ID " . &{$self->_id_generation_func}($seq) . "\nXX\n";
}
# Otherwise, generate a standard EMBL release 87 (June 2006) ID line.
else {
# The sequence name is supposed to be the primary accession number,
my $name = $seq->accession_number();
if ( not(defined $name) || $name eq 'unknown') {
# but if it is not present, use the sequence ID or the empty string
$name = $seq->id() || '';
}
$self->warn("No whitespace allowed in EMBL id [". $name. "]") if $name =~ /\s/;
# Use the sequence version, or default to 1.
my $version = $seq->version() || 1;
my $len = $seq->length();
# Taxonomic division.
my $div;
if ( $seq->can('division') && defined($seq->division) &&
$self->_is_valid_division($seq->division) ) {
$div = $seq->division();
} else {
$div ||= 'UNC'; # 'UNC' is the EMBL division code for 'unclassified'.
}
my $mol;
# If the molecule type is a valid EMBL type, use it.
if ( $seq->can('molecule')
&& defined($seq->molecule)
&& $self->_is_valid_molecule_type($seq->molecule)
) {
$mol = $seq->molecule();
}
# Otherwise, choose unassigned DNA or RNA based on the alphabet.
elsif ($seq->can('primary_seq') && defined $seq->primary_seq->alphabet) {
my $alphabet =$seq->primary_seq->alphabet;
if ($alphabet eq 'dna') {
$mol ='unassigned DNA';
} elsif ($alphabet eq 'rna') {
$mol='unassigned RNA';
} elsif ($alphabet eq 'protein') {
$self->warn("Protein sequence found; EMBL is a nucleotide format.");
$mol='AA'; # AA is not a valid EMBL molecule type.
}
}
my $topology = 'linear';
if ($seq->is_circular) {
$topology = 'circular';
}
$mol ||= ''; # 'unassigned'; ?
$id_line = "ID $name; SV $version; $topology; $mol; STD; $div; $len BP.\nXX\n";
$self->_print($id_line);
}
}
=head2 _is_valid_division
Title : _is_valid_division
Usage : $self->_is_valid_division($div)
Function: tests division code for validity
Returns : true if $div is a valid EMBL release 87 taxonomic division.
Args : taxonomic division code string
=cut
sub _is_valid_division {
my ($self, $division) = @_;
my %EMBL_divisions = (
"PHG" => 1, # Bacteriophage
"ENV" => 1, # Environmental Sample
"FUN" => 1, # Fungal
"HUM" => 1, # Human
"INV" => 1, # Invertebrate
"MAM" => 1, # Other Mammal
"VRT" => 1, # Other Vertebrate
"MUS" => 1, # Mus musculus
"PLN" => 1, # Plant
"PRO" => 1, # Prokaryote
"ROD" => 1, # Other Rodent
"SYN" => 1, # Synthetic
"UNC" => 1, # Unclassified
"VRL" => 1 # Viral
);
return exists($EMBL_divisions{$division});
}
=head2 _is_valid_molecule_type
Title : _is_valid_molecule_type
Usage : $self->_is_valid_molecule_type($mol)
Function: tests molecule type for validity
Returns : true if $mol is a valid EMBL release 87 molecule type.
Args : molecule type string
=cut
sub _is_valid_molecule_type {
my ($self, $moltype) = @_;
my %EMBL_molecule_types = (
"genomic DNA" => 1,
"genomic RNA" => 1,
"mRNA" => 1,
"tRNA" => 1,
"rRNA" => 1,
"snoRNA" => 1,
"snRNA" => 1,
"scRNA" => 1,
"pre-RNA" => 1,
"other RNA" => 1,
"other DNA" => 1,
"unassigned DNA" => 1,
"unassigned RNA" => 1
);
return exists($EMBL_molecule_types{$moltype});
}
=head2 write_seq
Title : write_seq
Usage : $stream->write_seq($seq)
Function: writes the $seq object (must be seq) to the stream
Returns : 1 for success and undef for error
Args : array of 1 to n Bio::SeqI objects
=cut
sub write_seq {
my ($self,@seqs) = @_;
foreach my $seq ( @seqs ) {
$self->throw("Attempting to write with no seq!") unless defined $seq;
unless ( ref $seq && $seq->isa('Bio::SeqI' ) ) {
$self->warn("$seq is not a SeqI compliant sequence object!")
if $self->verbose >= 0;
unless ( ref $seq && $seq->isa('Bio::PrimarySeqI' ) ) {
$self->throw("$seq is not a PrimarySeqI compliant sequence object!");
}
}
my $str = $seq->seq || '';
# Write the ID line.
$self->_write_ID_line($seq);
# Write the accession line if present
my( $acc );
{
if ( my $func = $self->_ac_generation_func ) {
$acc = &{$func}($seq);
} elsif ( $seq->isa('Bio::Seq::RichSeqI') &&
defined($seq->accession_number) ) {
$acc = $seq->accession_number;
$acc = join("; ", $acc, $seq->get_secondary_accessions);
} elsif ( $seq->can('accession_number') ) {
$acc = $seq->accession_number;
}
if (defined $acc) {
$self->_print("AC $acc;\n",
"XX\n") || return;
}
}
# Date lines
my $switch=0;
if ( $seq->can('get_dates') ) {
my @dates = $seq->get_dates();
my $ct = 1;
my $date_flag = 0;
my ($cr) = $seq->annotation->get_Annotations("creation_release");
my ($ur) = $seq->annotation->get_Annotations("update_release");
my ($uv) = $seq->annotation->get_Annotations("update_version");
unless ($cr && $ur && $ur) {
$date_flag = 1;
}
foreach my $dt (@dates) {
if (!$date_flag) {
$self->_write_line_EMBL_regex("DT ","DT ",
$dt." (Rel. $cr, Created)",
'\s+|$',80) if $ct == 1;
$self->_write_line_EMBL_regex("DT ","DT ",
$dt." (Rel. $ur, Last updated, Version $uv)",
'\s+|$',80) if $ct == 2;
} else { # other formats?
$self->_write_line_EMBL_regex("DT ","DT ",
$dt,'\s+|$',80);
}
$switch =1;
$ct++;
}
if ($switch == 1) {
$self->_print("XX\n") || return;
}
}
# Description lines
$self->_write_line_EMBL_regex("DE ","DE ",$seq->desc(),'\s+|$',80) || return; #'
$self->_print( "XX\n") || return;
# if there, write the kw line
{
my( $kw );
if ( my $func = $self->_kw_generation_func ) {
$kw = &{$func}($seq);
} elsif ( $seq->can('keywords') ) {
$kw = $seq->keywords;
}
if (defined $kw) {
$self->_write_line_EMBL_regex("KW ", "KW ", $kw, '\s+|$', 80) || return; #'
$self->_print( "XX\n") || return;
}
}
# Organism lines
if ($seq->can('species') && (my $spec = $seq->species)) {
my @class = $spec->classification();
shift @class; # get rid of species name. Some embl files include
# the species name in the OC lines, but this seems
# more like an error than something we need to
# emulate
my $OS = $spec->scientific_name;
if ($spec->common_name) {
$OS .= ' ('.$spec->common_name.')';
}
$self->_print("OS $OS\n") || return;
my $OC = join('; ', reverse(@class)) .'.';
$self->_write_line_EMBL_regex("OC ","OC ",$OC,'; |$',80) || return;
if ($spec->organelle) {
$self->_write_line_EMBL_regex("OG ","OG ",$spec->organelle,'; |$',80) || return;
}
my $ncbi_taxid = $spec->ncbi_taxid;
if ($ncbi_taxid) {
$self->_print("OX NCBI_TaxID=$ncbi_taxid\n") || return;
}
$self->_print("XX\n") || return;
}
# Reference lines
my $t = 1;
if ( $seq->can('annotation') && defined $seq->annotation ) {
foreach my $ref ( $seq->annotation->get_Annotations('reference') ) {
$self->_print( "RN [$t]\n") || return;
# Having no RP line is legal, but we need both
# start and end for a valid location.
if ($ref->comment) {
$self->_write_line_EMBL_regex("RC ", "RC ", $ref->comment, '\s+|$', 80) || return; #'
}
my $start = $ref->start;
my $end = $ref->end;
if ($start and $end) {
$self->_print( "RP $start-$end\n") || return;
} elsif ($start or $end) {
$self->throw("Both start and end are needed for a valid RP line.".
" Got: start='$start' end='$end'");
}
if (my $med = $ref->medline) {
$self->_print( "RX MEDLINE; $med.\n") || return;
}
if (my $pm = $ref->pubmed) {
$self->_print( "RX PUBMED; $pm.\n") || return;
}
my $authors = $ref->authors;
$authors =~ s/([\w\.]) (\w)/$1#$2/g; # add word wrap protection char '#'
$self->_write_line_EMBL_regex("RA ", "RA ",
$authors . ";",
'\s+|$', 80) || return; #'
# If there is no title to the reference, it appears
# as a single semi-colon. All titles must end in
# a semi-colon.
my $ref_title = $ref->title || '';
$ref_title =~ s/[\s;]*$/;/;
$self->_write_line_EMBL_regex("RT ", "RT ", $ref_title, '\s+|$', 80) || return; #'
$self->_write_line_EMBL_regex("RL ", "RL ", $ref->location, '\s+|$', 80) || return; #'
$self->_print("XX\n") || return;
$t++;
}
# DB Xref lines
if (my @db_xref = $seq->annotation->get_Annotations('dblink') ) {
for my $dr (@db_xref) {
my $db_name = $dr->database;
my $prim = $dr->primary_id;
my $opt = $dr->optional_id || '';
my $line = $opt ? "$db_name; $prim; $opt." : "$db_name; $prim.";
$self->_write_line_EMBL_regex("DR ", "DR ", $line, '\s+|$', 80) || return; #'
}
$self->_print("XX\n") || return;
}
# Comment lines
foreach my $comment ( $seq->annotation->get_Annotations('comment') ) {
$self->_write_line_EMBL_regex("CC ", "CC ", $comment->text, '\s+|$', 80) || return; #'
$self->_print("XX\n") || return;
}
}
# "\\s\+\|\$"
## FEATURE TABLE
$self->_print("FH Key Location/Qualifiers\n") || return;
$self->_print("FH\n") || return;
my @feats = $seq->can('top_SeqFeatures') ? $seq->top_SeqFeatures : ();
if ($feats[0]) {
if ( defined $self->_post_sort ) {
# we need to read things into an array.
# Process. Sort them. Print 'em
my $post_sort_func = $self->_post_sort();
my @fth;
foreach my $sf ( @feats ) {
push(@fth,Bio::SeqIO::FTHelper::from_SeqFeature($sf,$seq));
}
@fth = sort { &$post_sort_func($a,$b) } @fth;
foreach my $fth ( @fth ) {
$self->_print_EMBL_FTHelper($fth) || return;
}
} else {
# not post sorted. And so we can print as we get them.
# lower memory load...
foreach my $sf ( @feats ) {
my @fth = Bio::SeqIO::FTHelper::from_SeqFeature($sf,$seq);
foreach my $fth ( @fth ) {
if ( $fth->key eq 'CONTIG') {
$self->_show_dna(0);
}
$self->_print_EMBL_FTHelper($fth) || return;
}
}
}
}
if ( $self->_show_dna() == 0 ) {
$self->_print( "//\n") || return;
return;
}
$self->_print( "XX\n") || return;
# finished printing features.
# print contig if present : bug#2982
if ( $seq->can('annotation') && defined $seq->annotation) {
foreach my $ctg ( $seq->annotation->get_Annotations('contig') ) {
if ($ctg->value) {
$self->_write_line_EMBL_regex("CO ","CO ", $ctg->value,
'[,]|$', 80) || return;
}
}
}
# print sequence lines only if sequence is present! bug#2982
if (length($str)) {
$str =~ tr/A-Z/a-z/;
# Count each nucleotide
my $alen = $str =~ tr/a/a/;
my $clen = $str =~ tr/c/c/;
my $glen = $str =~ tr/g/g/;
my $tlen = $str =~ tr/t/t/;
my $len = $seq->length();
my $olen = $seq->length() - ($alen + $tlen + $clen + $glen);
if ( $olen < 0 ) {
$self->warn("Weird. More atgc than bases. Problem!");
}
$self->_print("SQ Sequence $len BP; $alen A; $clen C; $glen G; $tlen T; $olen other;\n") || return;
my $nuc = 60; # Number of nucleotides per line
my $whole_pat = 'a10' x 6; # Pattern for unpacking a whole line
my $out_pat = 'A11' x 6; # Pattern for packing a line
my $length = length($str);
# Calculate the number of nucleotides which fit on whole lines
my $whole = int($length / $nuc) * $nuc;
# Print the whole lines
my( $i );
for ($i = 0; $i < $whole; $i += $nuc) {
my $blocks = pack $out_pat,
unpack $whole_pat,
substr($str, $i, $nuc);
$self->_print(sprintf(" $blocks%9d\n", $i + $nuc)) || return;
}
# Print the last line
if (my $last = substr($str, $i)) {
my $last_len = length($last);
my $last_pat = 'a10' x int($last_len / 10) .'a'. $last_len % 10;
my $blocks = pack $out_pat,
unpack($last_pat, $last);
$self->_print(sprintf(" $blocks%9d\n", $length)) ||
return; # Add the length to the end
}
}
$self->_print( "//\n") || return;
$self->flush if $self->_flush_on_write && defined $self->_fh;
}
return 1;
}
=head2 _print_EMBL_FTHelper
Title : _print_EMBL_FTHelper
Usage :
Function: Internal function
Returns : 1 if writing suceeded, otherwise undef
Args :
=cut
sub _print_EMBL_FTHelper {
my ($self,$fth) = @_;
if ( ! ref $fth || ! $fth->isa('Bio::SeqIO::FTHelper') ) {
$fth->warn("$fth is not a FTHelper class. Attempting to print, but there could be tears!");
}
#$self->_print( "FH Key Location/Qualifiers\n");
#$self->_print( sprintf("FT %-15s %s\n",$fth->key,$fth->loc));
# let
if ( $fth->key eq 'CONTIG' ) {
$self->_print("XX\n") || return;
$self->_write_line_EMBL_regex("CO ",
"CO ",$fth->loc,
'\,|$',80) || return; #'
return 1;
}
$self->_write_line_EMBL_regex(sprintf("FT %-15s ",$fth->key),
"FT ",$fth->loc,
'\,|$',80) || return; #'
foreach my $tag ( keys %{$fth->field} ) {
if ( ! defined $fth->field->{$tag} ) {
next;
}
foreach my $value ( @{$fth->field->{$tag}} ) {
$value =~ s/\"/\"\"/g;
if ($value eq "_no_value") {
$self->_write_line_EMBL_regex("FT ",
"FT ",
"/$tag",'.|$',80) || return; #'
}
# there are almost 3x more quoted qualifier values and they
# are more common too so we take quoted ones first
#
# Long qualifiers, that will be line wrapped, are always quoted
elsif (!$FTQUAL_NO_QUOTE{$tag} or length("/$tag=$value")>=60) {
my $pat = $value =~ /\s/ ? '\s|\-|$' : '.|\-|$';
$self->_write_line_EMBL_regex("FT ",
"FT ",
"/$tag=\"$value\"",$pat,80) || return;
} else {
$self->_write_line_EMBL_regex("FT ",
"FT ",
"/$tag=$value",'.|$',80) || return; #'
}
}
}
return 1;
}
=head2 _read_EMBL_Contig()
Title : _read_EMBL_Contig
Usage :
Function: convert CO lines into annotations
Returns :
Args :
=cut
sub _read_EMBL_Contig {
my ($self, $buffer) = @_;
my @ret;
if ( $$buffer !~ /^CO/ ) {
warn("Not parsing line '$$buffer' which maybe important");
}
$self->_pushback($$buffer);
while ( defined ($_ = $self->_readline) ) {
/^C/ || last;
/^CO\s+(.*)/ && do {
push @ret, Bio::Annotation::SimpleValue->new( -tagname => 'contig',
-value => $1);
};
}
$$buffer = $_;
return @ret;
}
#'
=head2 _read_EMBL_References
Title : _read_EMBL_References
Usage :
Function: Reads references from EMBL format. Internal function really
Example :
Returns :
Args :
=cut
sub _read_EMBL_References {
my ($self,$buffer) = @_;
my (@refs);
# assume things are starting with RN
if ( $$buffer !~ /^RN/ ) {
warn("Not parsing line '$$buffer' which maybe important");
}
my $b1;
my $b2;
my $title;
my $loc;
my $au;
my $med;
my $pm;
my $com;
while ( defined ($_ = $self->_readline) ) {
/^R/ || last;
/^RP (\d+)-(\d+)/ && do {$b1=$1;$b2=$2;};
/^RX MEDLINE;\s+(\d+)/ && do {$med=$1};
/^RX PUBMED;\s+(\d+)/ && do {$pm=$1};
/^RA (.*)/ && do {
$au = $self->_concatenate_lines($au,$1); next;
};
/^RT (.*)/ && do {
$title = $self->_concatenate_lines($title,$1); next;
};
/^RL (.*)/ && do {
$loc = $self->_concatenate_lines($loc,$1); next;
};
/^RC (.*)/ && do {
$com = $self->_concatenate_lines($com,$1); next;
};
}
my $ref = Bio::Annotation::Reference->new();
$au =~ s/;\s*$//g;
$title =~ s/;\s*$//g;
$ref->start($b1);
$ref->end($b2);
$ref->authors($au);
$ref->title($title);
$ref->location($loc);
$ref->medline($med);
$ref->comment($com);
$ref->pubmed($pm);
push(@refs,$ref);
$$buffer = $_;
return @refs;
}
=head2 _read_EMBL_Species
Title : _read_EMBL_Species
Usage :
Function: Reads the EMBL Organism species and classification
lines.
Example :
Returns : A Bio::Species object
Args : a reference to the current line buffer, accession number
=cut
sub _read_EMBL_Species {
my( $self, $buffer, $acc ) = @_;
my $org;
$_ = $$buffer;
my( $sub_species, $species, $genus, $common, $sci_name, $class_lines );
while (defined( $_ ||= $self->_readline )) {
if (/^OS\s+(.+)/) {
$sci_name .= ($sci_name) ? ' '.$1 : $1;
} elsif (s/^OC\s+(.+)$//) {
$class_lines .= $1;
} elsif (/^OG\s+(.*)/) {
$org = $1;
} else {
last;
}
$_ = undef; # Empty $_ to trigger read of next line
}
# $$buffer = $_;
$self->_pushback($_);
$sci_name =~ s{\.$}{};
$sci_name || return;
# Convert data in classification lines into classification array.
# only split on ';' or '.' so that classification that is 2 or more words
# will still get matched, use map() to remove trailing/leading/intervening
# spaces
my @class = map { s/^\s+//; s/\s+$//; s/\s{2,}/ /g; $_; } split /(?<!subgen)[;\.]+/, $class_lines;
# do we have a genus?
my $possible_genus = $class[-1];
$possible_genus .= "|$class[-2]" if $class[-2];
if ($sci_name =~ /^($possible_genus)/) {
$genus = $1;
($species) = $sci_name =~ /^$genus\s+(.+)/;
} else {
$species = $sci_name;
}
# Don't make a species object if it is "Unknown" or "None"
if ($genus) {
return if $genus =~ /^(Unknown|None)$/i;
}
# is this organism of rank species or is it lower?
# (doesn't catch everything, but at least the guess isn't dangerous)
if ($species =~ /subsp\.|var\./) {
($species, $sub_species) = $species =~ /(.+)\s+((?:subsp\.|var\.).+)/;
}
# sometimes things have common name in brackets, like
# Schizosaccharomyces pombe (fission yeast), so get rid of the common
# name bit. Probably dangerous if real scientific species name ends in
# bracketed bit.
unless ($class[-1] eq 'Viruses') {
($species, $common) = $species =~ /^(.+)\s+\((.+)\)$/;
$sci_name =~ s/\s+\(.+\)$// if $common;
}
# Bio::Species array needs array in Species -> Kingdom direction
unless ($class[-1] eq $sci_name) {
push(@class, $sci_name);
}
@class = reverse @class;
# do minimal sanity checks before we hand off to Bio::Species which won't
# be able to give informative throw messages if it has to throw because
# of problems here
$self->throw("$acc seems to be missing its OS line: invalid.") unless $sci_name;
my %names;
foreach my $i (0..$#class) {
my $name = $class[$i];
$names{$name}++;
# this code breaks examples like: Xenopus (Silurana) tropicalis
# commenting out, see bug 3158
#if ($names{$name} > 1 && ($name ne $class[$i - 1])) {
# $self->warn("$acc seems to have an invalid species classification:$name ne $class[$i - 1]");
#}
}
my $make = Bio::Species->new();
$make->scientific_name($sci_name);
$make->classification(@class);
unless ($class[-1] eq 'Viruses') {
$make->genus($genus) if $genus;
$make->species($species) if $species;
$make->sub_species($sub_species) if $sub_species;
$make->common_name($common) if $common;
}
$make->organelle($org) if $org;
return $make;
}
=head2 _read_EMBL_DBLink
Title : _read_EMBL_DBLink
Usage :
Function: Reads the EMBL database cross reference ("DR") lines
Example :
Returns : A list of Bio::Annotation::DBLink objects
Args :
=cut
sub _read_EMBL_DBLink {
my( $self,$buffer ) = @_;
my( @db_link );
$_ = $$buffer;
while (defined( $_ ||= $self->_readline )) {
if ( /^DR ([^\s;]+);\s*([^\s;]+);?\s*([^\s;]+)?\.$/) {
my ($databse, $prim_id, $sec_id) = ($1,$2,$3);
my $link = Bio::Annotation::DBLink->new(-database => $databse,
-primary_id => $prim_id,
-optional_id => $sec_id);
push(@db_link, $link);
} else {
last;
}
$_ = undef; # Empty $_ to trigger read of next line
}
$$buffer = $_;
return @db_link;
}
=head2 _read_EMBL_TaxID_DBLink
Title : _read_EMBL_TaxID_DBLink
Usage :
Function: Reads the EMBL database cross reference to NCBI TaxID ("OX") lines
Example :
Returns : A list of Bio::Annotation::DBLink objects
Args :
=cut
sub _read_EMBL_TaxID_DBLink {
my( $self,$buffer ) = @_;
my( @db_link );
$_ = $$buffer;
while (defined( $_ ||= $self->_readline )) {
if ( /^OX (\S+)=(\d+);$/ ) {
my ($databse, $prim_id) = ($1,$2);
my $link = Bio::Annotation::DBLink->new(-database => $databse,
-primary_id => $prim_id,);
push(@db_link, $link);
} else {
last;
}
$_ = undef; # Empty $_ to trigger read of next line
}
$$buffer = $_;
return @db_link;
}
=head2 _filehandle
Title : _filehandle
Usage : $obj->_filehandle($newval)
Function:
Example :
Returns : value of _filehandle
Args : newvalue (optional)
=cut
sub _filehandle{
my ($obj,$value) = @_;
if ( defined $value) {
$obj->{'_filehandle'} = $value;
}
return $obj->{'_filehandle'};
}
=head2 _read_FTHelper_EMBL
Title : _read_FTHelper_EMBL
Usage : _read_FTHelper_EMBL($buffer)
Function: reads the next FT key line
Example :
Returns : Bio::SeqIO::FTHelper object
Args : filehandle and reference to a scalar
=cut
sub _read_FTHelper_EMBL {
my ($self,$buffer) = @_;
my ($key, # The key of the feature
$loc, # The location line from the feature
@qual, # An arrray of lines making up the qualifiers
);
if ($$buffer =~ /^FT\s{3}(\S+)\s+(\S+)/ ) {
$key = $1;
$loc = $2;
# Read all the lines up to the next feature
while ( defined($_ = $self->_readline) ) {
if (/^FT(\s+)(.+?)\s*$/) {
# Lines inside features are preceeded by 19 spaces
# A new feature is preceeded by 3 spaces
if (length($1) > 4) {
# Add to qualifiers if we're in the qualifiers
if (@qual) {
push(@qual, $2);
}
# Start the qualifier list if it's the first qualifier
elsif (substr($2, 0, 1) eq '/') {
@qual = ($2);
}
# We're still in the location line, so append to location
else {
$loc .= $2;
}
} else {
# We've reached the start of the next feature
last;
}
} else {
# We're at the end of the feature table
last;
}
}
} elsif ( $$buffer =~ /^CO\s+(\S+)/) {
$key = 'CONTIG';
$loc = $1;
# Read all the lines up to the next feature
while ( defined($_ = $self->_readline) ) {
if (/^CO\s+(\S+)\s*$/) {
$loc .= $1;
} else {
# We've reached the start of the next feature
last;
}
}
} else {
# No feature key
return;
}
# Put the first line of the next feature into the buffer
$$buffer = $_;
# Make the new FTHelper object
my $out = Bio::SeqIO::FTHelper->new();
$out->verbose($self->verbose());
$out->key($key);
$out->loc($loc);
# Now parse and add any qualifiers. (@qual is kept
# intact to provide informative error messages.)
QUAL: for (my $i = 0; $i < @qual; $i++) {
$_ = $qual[$i];
my( $qualifier, $value ) = m{^/([^=]+)(?:=(.+))?}
or $self->throw("Can't see new qualifier in: $_\nfrom:\n"
. join('', map "$_\n", @qual));
if (defined $value) {
# Do we have a quoted value?
if (substr($value, 0, 1) eq '"') {
# Keep adding to value until we find the trailing quote
# and the quotes are balanced
QUOTES:
while ($value !~ /"$/ or $value =~ tr/"/"/ % 2) { #"
$i++;
my $next = $qual[$i];
if (!defined($next)) {
$self->warn("Unbalanced quote in:\n".join("\n", @qual).
"\nAdding quote to close...".
"Check sequence quality!");
$value .= '"';
last QUOTES;
}
# Protein sequence translations need to be joined without spaces,
# other qualifiers need those.
if ($qualifier eq "translation") {
$value .= $next;
} else {
$value .= " $next";
}
}
# Trim leading and trailing quotes
$value =~ s/^"|"$//g;
# Undouble internal quotes
$value =~ s/""/"/g; #"
}
} else {
$value = '_no_value';
}
# Store the qualifier
$out->field->{$qualifier} ||= [];
push(@{$out->field->{$qualifier}},$value);
}
return $out;
}
=head2 _write_line_EMBL
Title : _write_line_EMBL
Usage :
Function: internal function
Example :
Returns : 1 if writing suceeded, else undef
Args :
=cut
sub _write_line_EMBL {
my ($self,$pre1,$pre2,$line,$length) = @_;
$length || $self->throw("Miscalled write_line_EMBL without length. Programming error!");
my $subl = $length - length $pre2;
my $linel = length $line;
my $i;
my $sub = substr($line,0,$length - length $pre1);
$self->_print( "$pre1$sub\n") || return;
for ($i= ($length - length $pre1);$i < $linel;) {
$sub = substr($line,$i,($subl));
$self->_print( "$pre2$sub\n") || return;
$i += $subl;
}
return 1;
}
=head2 _write_line_EMBL_regex
Title : _write_line_EMBL_regex
Usage :
Function: internal function for writing lines of specified
length, with different first and the next line
left hand headers and split at specific points in the
text
Example :
Returns : nothing
Args : file handle, first header, second header, text-line, regex for line breaks, total line length
=cut
sub _write_line_EMBL_regex {
my ($self,$pre1,$pre2,$line,$regex,$length) = @_;
#print STDOUT "Going to print with $line!\n";
$length || $self->throw("Programming error - called write_line_EMBL_regex without length.");
my $subl = $length - (length $pre1) -1 ;
my( @lines );
CHUNK: while($line) {
foreach my $pat ($regex, '[,;\.\/-]\s|'.$regex, '[,;\.\/-]|'.$regex) {
if ($line =~ m/^(.{0,$subl})($pat)(.*)/ ) {
my $l = $1.$2;
$l =~ s/#/ /g # remove word wrap protection char '#'
if $pre1 eq "RA ";
my $newl = $3;
$line = substr($line,length($l));
# be strict about not padding spaces according to
# genbank format
$l =~ s/\s+$//;
next CHUNK if ($l eq '');
push(@lines, $l);
next CHUNK;
}
}
# if we get here none of the patterns matched $subl or less chars
$self->warn("trouble dissecting \"$line\"\n into chunks ".
"of $subl chars or less - this tag won't print right");
# insert a space char to prevent infinite loops
$line = substr($line,0,$subl) . " " . substr($line,$subl);
}
my $s = shift @lines;
($self->_print("$pre1$s\n") || return) if $s;
foreach my $s ( @lines ) {
$self->_print("$pre2$s\n") || return;
}
return 1;
}
=head2 _post_sort
Title : _post_sort
Usage : $obj->_post_sort($newval)
Function:
Returns : value of _post_sort
Args : newvalue (optional)
=cut
sub _post_sort{
my $obj = shift;
if ( @_ ) {
my $value = shift;
$obj->{'_post_sort'} = $value;
}
return $obj->{'_post_sort'};
}
=head2 _show_dna
Title : _show_dna
Usage : $obj->_show_dna($newval)
Function:
Returns : value of _show_dna
Args : newvalue (optional)
=cut
sub _show_dna{
my $obj = shift;
if ( @_ ) {
my $value = shift;
$obj->{'_show_dna'} = $value;
}
return $obj->{'_show_dna'};
}
=head2 _id_generation_func
Title : _id_generation_func
Usage : $obj->_id_generation_func($newval)
Function:
Returns : value of _id_generation_func
Args : newvalue (optional)
=cut
sub _id_generation_func{
my $obj = shift;
if ( @_ ) {
my $value = shift;
$obj->{'_id_generation_func'} = $value;
}
return $obj->{'_id_generation_func'};
}
=head2 _ac_generation_func
Title : _ac_generation_func
Usage : $obj->_ac_generation_func($newval)
Function:
Returns : value of _ac_generation_func
Args : newvalue (optional)
=cut
sub _ac_generation_func{
my $obj = shift;
if ( @_ ) {
my $value = shift;
$obj->{'_ac_generation_func'} = $value;
}
return $obj->{'_ac_generation_func'};
}
=head2 _sv_generation_func
Title : _sv_generation_func
Usage : $obj->_sv_generation_func($newval)
Function:
Returns : value of _sv_generation_func
Args : newvalue (optional)
=cut
sub _sv_generation_func{
my $obj = shift;
if ( @_ ) {
my $value = shift;
$obj->{'_sv_generation_func'} = $value;
}
return $obj->{'_sv_generation_func'};
}
=head2 _kw_generation_func
Title : _kw_generation_func
Usage : $obj->_kw_generation_func($newval)
Function:
Returns : value of _kw_generation_func
Args : newvalue (optional)
=cut
sub _kw_generation_func{
my $obj = shift;
if ( @_ ) {
my $value = shift;
$obj->{'_kw_generation_func'} = $value;
}
return $obj->{'_kw_generation_func'};
}
1;
|