#!/usr/bin/env python

###################################
# MERGES VENN DIAGRAM FILES       #
# 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, math
import itertools

if __name__=="__main__":
	if len(sys.argv) > 2:
		# read in the datasets to analyze
		sets = dict()
		for filename in sys.argv[1:]:
			fhandle = open(filename, "rU")
			csvread = csv.reader(fhandle, dialect='excel-tab')
			for line in csvread:
				group = line[1]
				value = line[2]
				if group.startswith("["):
					if group not in sets:
						sets[group] = dict()
					sets[group][filename] = value

		# process and write out the results
		csv_out = csv.writer(sys.stdout, dialect='excel-tab')
		csv_out.writerow(["group"] + sys.argv[1:])

		for group in sorted(sets, key=lambda x: str(len(x.strip("[]").rstrip("[]").split(","))) + str(x)):
			row = [group]
			for filename in sys.argv[1:]:
				if filename in sets[group]:
					row.append(sets[group][filename])
				else:
					row.append("N/A")
			# write the results to standard output
			csv_out.writerow(row)
	else:
		# print usage instructions
		print "Usage:  merge_vdiagram.py <vdiagram_csv_files>"
		print "Output: a merged Venn-Diagram table (to standard output)."