JAL-3521 High quality file icons for jalview associated files, and associated mime...

[jalview.git] / utils / gff2annot.pl

diff --git a/utils/gff2annot.pl b/utils/gff2annot.pl
index f144df1..4ee683b 100755 (executable)
--- a/utils/gff2annot.pl
+++ b/utils/gff2annot.pl
@@ -1,16 +1,38 @@
 #!/usr/bin/perl
+##
+# Jalview - A Sequence Alignment Editor and Viewer ($$Version-Rel$$)
+# Copyright (C) $$Year-Rel$$ The Jalview Authors
+# 
+# This file is part of Jalview.
+# 
+# Jalview is free software: you can redistribute it and/or
+# modify it under the terms of the GNU General Public License 
+# as published by the Free Software Foundation, either version 3 of the License, or (at your option) any later version.
+#  
+# Jalview is distributed in the hope that it will be useful, but 
+# WITHOUT ANY WARRANTY; without even the implied warranty 
+# of MERCHANTABILITY or FITNESS FOR A PARTICULAR 
+# PURPOSE.  See the GNU General Public License for more details.
+# 
+# You should have received a copy of the GNU General Public License along with Jalview.  If not, see <http://www.gnu.org/licenses/>.
+# The Jalview Authors are detailed in the 'AUTHORS' file.
+##
 
 use strict;
 use warnings;
 
 my %annotLines;
-
+my %featureids;
 my @fields;
 while (<>) {
+    ($_=~/^\#/) and next;
     my @fields = split /\s+/, $_;
     if (scalar @fields) {
         (defined $annotLines{$fields[1]}) or $annotLines{$fields[1]}=[];
-        my $line = [$fields[2],$fields[0], "ID_NOT_SPECIFIED", $fields[3], $fields[4], $fields[2]];
+        # this is the tab-separated set of fields forming a jalview annotation line
+        # we only use sequence IDs, not numbers
+        my $line = [$fields[2],$fields[0],"-1", $fields[3], $fields[4], $fields[2]];
+        $featureids{$fields[2]}="FF0000"; # red is the colour.
         my $attribs = {};
         if (scalar @fields>5) {
             $attribs->{"gff:score"}=$fields[5];
@@ -25,11 +47,71 @@ while (<>) {
         push @{$annotLines{$fields[1]}}, [$line, $attribs];
     }
 }
-
+foreach my $labels (keys %featureids) {
+    print "$labels\t".$featureids{$labels}."\n"; 
+}
 foreach my $labels (keys %annotLines) {
-    print "startgroup\t".$labels."\n";
+    print "STARTGROUP\t".$labels."\n";
     foreach my $annot (@{$annotLines{$labels}}) {
-        print "".(join "\t",@{$annot->[0]})."\n";
+        # bare minimum is written - no attributes/links yet.
+        print "".(join "\t",@{$annot->[0]})."\n"; 
     }
-    print "endgroup\t".$labels."\n";
+    print "ENDGROUP\t".$labels."\n";
 }
+
+=pod
+
+=head1 NAME
+
+gff2annot.pl
+
+=head2 SYNOPSIS
+
+
+  gff2annot.pl [one or more files containing gff annotation]
+
+Generates a nominally usable Jalview Annotation file on B<STDOUT> from arbitrary GFF annotation lines.
+
+=head2 DESCRIPTION
+
+This script will generate a jalview features file on standard out, from a set of GFF annotation lines input from STDIN and/or any provided filenames.
+
+For a series of GFF annotation lines looking like :
+
+E<lt>seqIdE<gt> E<lt>sourceE<gt> E<lt>nameE<gt> E<lt>startE<gt> E<lt>endE<gt> [E<lt>scoreE<gt> E<lt>strandE<gt> E<lt>frameE<gt> [E<lt>AttributeE<gt> E<lt>Attribute-Value<gt>]]
+
+The script will generate a seuqence features file on B<STDOUT> where annotation with a particular B<source> string will be grouped together under that name.
+
+=head2 Example
+
+Passing some GFF annotation through STDIN:
+
+  perl gff2annot.pl
+  Seq1 blastx significant_hsp 1 5 0.9 + 1 link http://mylink/
+  # a comment
+  Seq1 blasty significant_hsp 15 25 0.9 + 1 link http://mylink/
+  Seq1 blastz significant_hsp 32 43 0.9 + 1 link http://mylink/
+  Seq2 blastx significant_hsp 1 5 0.9 + 1 link http://mylink/
+  Seq2 blasty significant_hsp 1 5 0.9 + 1 link http://mylink/
+  Seq2 blastz significant_hsp 1 5 0.9
+  Seq3 blastx significant_hsp 50 70
+  <Control^D/Z>
+
+Produces
+
+  significant_hsp      FF0000
+  STARTGROUP   blasty
+  significant_hsp      Seq1    -1      15      25      significant_hsp
+  significant_hsp      Seq2    -1      1       5       significant_hsp
+  ENDGROUP     blasty
+  STARTGROUP   blastx
+  significant_hsp      Seq1    -1      1       5       significant_hsp
+  significant_hsp      Seq2    -1      1       5       significant_hsp
+  significant_hsp      Seq3    -1      50      70      significant_hsp
+  ENDGROUP     blastx
+  STARTGROUP   blastz
+  significant_hsp      Seq1    -1      32      43      significant_hsp
+  significant_hsp      Seq2    -1      1       5       significant_hsp
+  ENDGROUP     blastz
+
+=cut