[Bio] / FigKernelScripts / assign_synonym_ids_to_sims.pl Repository:
ViewVC logotype

View of /FigKernelScripts/assign_synonym_ids_to_sims.pl

Parent Directory Parent Directory | Revision Log Revision Log


Revision 1.2 - (download) (as text) (annotate)
Mon Dec 5 18:56:37 2005 UTC (13 years, 11 months ago) by olson
Branch: MAIN
CVS Tags: mgrast_dev_08112011, rast_rel_2009_05_18, mgrast_dev_08022011, rast_rel_2014_0912, rast_rel_2008_06_18, myrast_rel40, rast_rel_2008_06_16, mgrast_dev_05262011, rast_rel_2008_12_18, mgrast_dev_04082011, rast_rel_2008_07_21, rast_rel_2010_0928, rast_2008_0924, mgrast_version_3_2, mgrast_dev_12152011, rast_rel_2008_04_23, mgrast_dev_06072011, rast_rel_2008_09_30, rast_rel_2009_0925, rast_rel_2010_0526, rast_rel_2014_0729, mgrast_dev_02212011, rast_rel_2010_1206, caBIG-05Apr06-00, mgrast_release_3_0, mgrast_dev_03252011, rast_rel_2010_0118, mgrast_rel_2008_0924, mgrast_rel_2008_1110_v2, rast_rel_2009_02_05, rast_rel_2011_0119, mgrast_rel_2008_0625, mgrast_release_3_0_4, mgrast_release_3_0_2, mgrast_release_3_0_3, mgrast_release_3_0_1, mgrast_dev_03312011, mgrast_release_3_1_2, mgrast_release_3_1_1, mgrast_release_3_1_0, mgrast_dev_04132011, rast_rel_2008_10_09, mgrast_dev_04012011, rast_release_2008_09_29, mgrast_rel_2008_0806, mgrast_rel_2008_0923, mgrast_rel_2008_0919, rast_rel_2009_07_09, rast_rel_2010_0827, mgrast_rel_2008_1110, myrast_33, rast_rel_2011_0928, rast_rel_2008_09_29, mgrast_rel_2008_0917, rast_rel_2008_10_29, mgrast_dev_04052011, mgrast_dev_02222011, caBIG-13Feb06-00, rast_rel_2009_03_26, mgrast_dev_10262011, rast_rel_2008_11_24, rast_rel_2008_08_07, HEAD
Changes since 1.1: +17 -0 lines
Add license words.

#
# Copyright (c) 2003-2006 University of Chicago and Fellowship
# for Interpretations of Genomes. All Rights Reserved.
#
# This file is part of the SEED Toolkit.
# 
# The SEED Toolkit is free software. You can redistribute
# it and/or modify it under the terms of the SEED Toolkit
# Public License. 
#
# You should have received a copy of the SEED Toolkit Public License
# along with this program; if not write to the University of Chicago
# at info@ci.uchicago.edu or the Fellowship for Interpretation of
# Genomes at veronika@thefig.info or download a copy from
# http://www.theseed.org/LICENSE.TXT.
#

#
# Scan a sims directory, replacing the existing IDs with the corresponding principal
# synonym id's from the given ID map file.
#

use strict;

my $usage = "assign_synonym_ids_to_sims SimsDir id.map NewSimsDir";

@ARGV == 3 or die $usage;

my $old_sims_dir = shift;
my $id_map = shift;
my $new_sims_dir = shift;

opendir(OSIMS, $old_sims_dir) or die "Cannot opendir $old_sims_dir: $!\n";
open(MAP, "<$id_map") or die "Cannot open $id_map for reading: $!\n";

-d $new_sims_dir and die "New sims directory $new_sims_dir already exists\n";
mkdir $new_sims_dir or die "Cannot mkdir $new_sims_dir: $!\n";

my %map;

while (<MAP>)
{
    chomp;
    my($k,$v) = split(/\t/);
    $map{$k} = $v;
}

close(MAP);

print "Read map\n";

my @files = readdir(OSIMS);
my $i = 1;
my $n = @files;
for my $file (@files)
{
    my $path = "$old_sims_dir/$file";
    next if $file =~ /^\./;
    next unless -f $path;
    print "Process $file ($i of $n)\n";
    process_sims($path, "$new_sims_dir/$file", "logs/$file");
    $i++;
}

sub process_sims
{
    my($old, $new, $log) = @_;

    open(OLD, "<$old") or die "Cannot open $old: $!\n";
    open(NEW, ">$new") or die "Cannot open $new for writing: $!\n";
    open(LOG, ">$log") or die "Cannot open $log for writing: $!\n";

    my($id1, $id2, $rest);
    my($new1, $new2);
    while (<OLD>)
    {

	if (($id1, $id2, $rest) = /^(\S+)\t(\S+)\t(.*)/)
	{
	    $new1 = $map{$id1};
	    $new2 = $map{$id2};

	    if (!defined($new1))
	    {
		print LOG "nomap\t$id1\n";
		$new1 = $id1;
	    }
	    if (!defined($new2))
	    {
		print LOG "nomap\t$id2\n";
		$new2 = $id2;
	    }
	    print NEW "$new1\t$new2\t$rest\n";
	}
    }
    close(LOG);
    close(OLD);
    close(NEW);
}

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3