#!/usr/bin/env python

###################################
# SORTS A GFF FILE FOR CUFFLINKS  #
# THIS IS OPEN SOURCE CODE (YAY!) #
###################################
# LICENSE
#    This code is licensed under the Creative Commons 3.0
#    Attribution + ShareAlike license - for details see:
#       http://creativecommons.org/licenses/by-sa/3.0/
#
# DATE: February 27th, 2014
#
# PROGRAM AUTHOR (PROGRAMMER)
#    Graham Alvare - home.cc.umanitoba.ca/~alvare
#
# CO-AUTHORS/ACKNOWLEDGEMENTS
#    Justin Zhang          - for providing me information on the SAM format,
#                            and test data to build and debug this program.
#    Dr. Brian Fristensky  - my work supervisor, and the man who introduced
#                            me to the wonderful field of bioinformatics.
#
# QUESTIONS & COMMENTS
#    If you have any questions, please contact me: alvare@cc.umanitoba.ca
#    I usually get back to people within 1-2 weekdays (weekends, I am slower)
#
#    P.S. Please also let me know of any bugs, or if you have any suggestions.
#         I am generally happy to help create new tools, or modify my existing
#         tools to make them more useful.
#
# Happy usage!

import sys, os, os.path, csv, re, collections
from Bio import GenBank
from Bio import SeqIO

if __name__=="__main__":
	if len(sys.argv) > 1:
		# process every file specified on the command line
		for filename in sys.argv[1:]:
			rows = dict()

			# Open GFF file
			handle = open(filename, 'rU')

			# Open output FASTA file
			#gtf_out  = open(os.path.splitext(filename)[0] + '_norrna.gtf', 'w')
			
			for row in handle:
				cols = row.split('	')
				key = cols[0] + ',' + cols[3] + ',' + cols[4] + ',' + cols[2] + ',' + cols[6]
				if key in rows:
					print >> sys.stderr, "Overlap: " + key
					if row == rows[key]:
						print >> sys.stderr, "    Duplicate!"
					elif len(row) > len(rows[key]):
						print >> sys.stderr, "    Replacing with: " + row
					else:
						print >> sys.stderr, "    Skipping!"
				else:
					rows[key] = row

			for key in sorted(rows, key = lambda k: [k.split(',')[0], int(k.split(',')[1]), int(k.split(',')[2]), k.split(',')[3], k.split(',')[4]]):
				print rows[key]

			# Close the file handles
			handle.close()