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

View of /FigKernelScripts/load_abstract_coupling.pl

Parent Directory Parent Directory | Revision Log Revision Log


Revision 1.3 - (download) (as text) (annotate)
Wed Dec 21 22:17:52 2005 UTC (13 years, 10 months ago) by parrello
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 1.2: +3 -3 lines
Changed to use a single-character delimiter (for compatability with PostGRES).

#
# 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.
#


# -*- perl -*-

use FIG;
use Tracer;

my $fig = new FIG;

# usage: load_abstract_coupling

my $dirA = "$FIG_Config::data/AbstractFuncCoupling";
if (! opendir(DIR,$dirA))
{
    Trace("Abstract Coupling directory $dirA not found.") if T(1);
    exit;
}
my @types = grep { $_ !~ /^\./ } readdir(DIR);
closedir(DIR);

use DBrtns;

my $dbf = $fig->db_handle;
$dbf->drop_table( tbl => 'afc' );
$dbf->create_table( tbl => 'afc', 
                    flds => 'peg1 varchar(32), peg2 varchar(32), score float, type varchar(16), extra varchar(255)'
                    );
my($type);
foreach $type (@types)
{
    Trace("adding coupling data: type=$type") if T(2);
    if (opendir(DATA,"$dirA/$type/Data"))
    {
        my @to_load = grep { $_ =~ /^\d+\.\d+/ } readdir(DATA);
        closedir(DATA);
        foreach my $file (@to_load)
        {
            &load_file($dbf,$type,"$dirA/$type/Data/$file");
        }
    }
}

Trace("Building index.") if T(2);
$dbf->create_index( idx  => "afc_ix",
                    tbl  => "afc",
                    type => "btree",
                    flds => "peg1" );

Trace("Abstract Couplings loaded.") if T(2);

sub load_file {
    my($dbf,$type,$file) = @_;
    my $tmpFileName = "$FIG_Config::temp/$type$$.dxx";
    # Use tracer Open to get nice error messages.
    Open(\*TMP, "<$file");
    Open(\*TMPOUT, ">$tmpFileName");
    # Convert the input file so that it can be loaded directly into the database. We do
    # this by changing the delimiter from the standard (TAB) to an escape character.
    my $count = 0;
    while (defined($_ = <TMP>))
    {
        if ($_ =~ /^(fig\|\d+\.\d+\.peg\.\d+)\t(fig\|\d+\.\d+\.peg\.\d+)\t(\S+)(\t(\S.*\S))?/)
        {
            my($peg1,$peg2,$sc,$extra) = ($1,$2,$3,$5);
            $extra = defined($extra) ? $extra : "";
            my $line = join("\e", $peg1, $peg2, $sc, $type, $extra);
            print TMPOUT "$line\n";
            $count++;
        }
    }
    close TMP;
    close TMPOUT;
    Trace("$count records read from $file.") if T(2);
    # Load the table from the temp input file.
    Trace("Loading AFC data from $tmpFileName.") if T(2);
    $dbf->load_table( tbl => "afc", file => $tmpFileName, delim => "\e" );
    # Delete the temp input file.
    Trace("Deleting $tmpFileName.") if T(2);
    unlink $tmpFileName;
}

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3