From 359d17a6e36acf6e093bf6975170e845a40742ba Mon Sep 17 00:00:00 2001 From: Ben Ostrowsky Date: Tue, 10 May 2011 18:46:59 +0000 Subject: [PATCH] Script by Galen, used in dedupe/merge processing. --- cleanup_merge_map.pl | 34 ++++++++++++++++++++++++++++++++++ 1 files changed, 34 insertions(+), 0 deletions(-) create mode 100644 cleanup_merge_map.pl diff --git a/cleanup_merge_map.pl b/cleanup_merge_map.pl new file mode 100644 index 0000000..b00c9e3 --- /dev/null +++ b/cleanup_merge_map.pl @@ -0,0 +1,34 @@ +#!/usr/bin/perl + +use strict; +use warnings; + +=head1 NAME + +cleanup_merge_map.pl + +=head2 SUMMARY + +Little helper script used when consoldating +multiple merge maps. + +=cut + +my %bad_subs = (); +my %map = (); +while (<>) { + chomp; + my ($lead, $sub) = split /\t/, $_, -1; + next if exists $bad_subs{$sub}; + if (exists $map{$sub}) { + $bad_subs{$sub}++; + delete $map{$sub}; + next; + } + $map{$sub} = $lead; +} +foreach my $sub (sort keys %map) { + print "$map{$sub}\t$sub\n"; +} + + -- 1.7.2.5