#!/usr/bin/env python

#get_go_names.py is a script for retrieving Gene Ontology
#terms for Gene Ontology ids
#Copyright (C) 2007  Daniel Shriner

#This program 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 2
#of the License, or (at your option) any later version.

#This program 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.

#The text of the GNU General Public License, version 2, is available
#as http://www.gnu.org/copyleft or by writing to the Free Software
#Foundation, 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.

import sys,gzip,os

names = {}

#Load the gene2go file
try:
	f1 = gzip.open('gene2go.hs.09May06.gz','rb')
except IOError:
	print >> sys.stderr, 'Error opening gene2go file.\n'
	sys.exit(1)

while 1:
	line = f1.readline()
	if not line: break
	line = line.split('\t')
	names[line[2]] = line[5]
f1.close()

#Open the input file of weights
try:
	f2 = open('adj_weights.txt','r')
except IOError:
	print >> sys.stderr, 'Error opening weights file.\n'
	sys.exit(1)

#Open an output file for printing out GO names
try:
	f3 = open('adj_weights_names.txt','w')
except IOError:
	print >> sys.stderr, 'Error opening output file.\n'
	sys.exit(1)

while 1:
	line = f2.readline()
	if not line: break
	line = line.split('\t')
	line[0] = line[0].split('"')
	line[1] = line[1][:-1]
	line[1] = line[1].split('"')
	print >> f3, '%s\t%s\t%s' % (line[0][1],line[1][1],names.get(line[0][1]))

f2.close()
f3.close()
os.remove('adj_weights.txt')
os.rename('adj_weights_names.txt','adj_weights.txt')