From 98358e8df3134a67aeb495edeb62310168083252 Mon Sep 17 00:00:00 2001
From: Andrew Yates <ayates@ebi.ac.uk>
Date: Wed, 12 Sep 2012 15:02:28 +0000
Subject: [PATCH] Fix for parsing files from Ken @ CSHL. ORIGIN was used in
another context apart from notifying the start of the sequence in a genbank
a.thaliana file
---
misc-scripts/xref_mapping/XrefParser/RefSeqGPFFParser.pm | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/misc-scripts/xref_mapping/XrefParser/RefSeqGPFFParser.pm b/misc-scripts/xref_mapping/XrefParser/RefSeqGPFFParser.pm
index 7e1d7aa610..b7c2c9336a 100644
--- a/misc-scripts/xref_mapping/XrefParser/RefSeqGPFFParser.pm
+++ b/misc-scripts/xref_mapping/XrefParser/RefSeqGPFFParser.pm
@@ -223,7 +223,7 @@ sub create_xrefs {
$description =~ s/\s+/ /g;
$description = substr($description, 0, 255) if (length($description) > 255);
- my ($seq) = $_ =~ /ORIGIN\s+(.+)/s; # /s allows . to match newline
+ my ($seq) = $_ =~ /^\s*ORIGIN\s+(.+)/ms; # /s allows . to match newline
my @seq_lines = split /\n/, $seq;
my $parsed_seq = "";
foreach my $x (@seq_lines) {
--
GitLab