changeset 0:93f267c26057 draft

Uploaded

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/cut_fr.py	Wed Dec 16 08:45:06 2015 -0500
@@ -0,0 +1,93 @@
+#!usr/bin/pyhton3
+ '''<cut_fr.py is script allwing more convenient use of cut in galaxy environment>
+    Copyright (C) <2015>  <Lannes Romain>
+
+    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 3 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.
+
+    You should have received a copy of the GNU General Public License
+    along with this program.  If not, see <http://www.gnu.org/licenses/>.'''
+
+#-------- import
+import os 
+import argparse
+import sys
+
+#------- argument
+parser = argparse.ArgumentParser(description = "renvoie le fichier inputs moins les collones sellectionner")
+parser.add_argument('--c', help = "collumn to be removed" )
+parser.add_argument('--i', help = "input datasets" )
+parser.add_argument('--type_cut', help = "type of cut" )
+parser.add_argument('--extend_print', help = "add sdtrout print" )
+parser.add_argument('--o', help = "output datasets" )
+
+args = parser.parse_args()
+
+
+if(args.type_cut == "exclude"):
+	#------- First step count number of column
+	dataset_initial = open(args.i,'r')
+	firstline_dataset = dataset_initial.readline()
+
+	column_header = firstline_dataset.split('\t')
+	number_column = len(column_header)
+
+	# Collumn are in foramt c1,c2,c3
+	# need to get them 
+	column_list = args.c
+	column_list = column_list.split(',')
+
+	# remove the letter c
+	# there is certainly a more convenient way to do it
+	for i in range(len(column_list)):
+		column_list[i] = int(column_list[i][-1])
+
+	# Second Step prepare the command to be printed
+	str_argument = "-f"
+	for i in range( 1,number_column +1 ,1 ):
+		if i not in column_list:
+			str_argument = str_argument + str(i) + ','
+	str_argument = str_argument.strip(',')
+
+	# Create the command to be launch
+	str_cut = "cut " + str_argument + " " + args.i +" >"+ args.o
+
+if(args.type_cut == "include"):
+	# Collumn are in foramt c1,c2,c3
+	# need to get them 
+	column_list = args.c
+	column_list = column_list.split(',')
+	# remove the letter c
+	# there is certainly a more convenient way to do it 
+	for i in range(len(column_list)):
+		column_list[i] = int(column_list[i][-1])
+	# Second Step prepare the command to be printed
+	str_argument = "-f"
+	for indice in column_list :
+		str_argument = str_argument + str(indice) + ','
+	str_argument = str_argument.strip(',')
+	# Create the command to be launch
+	str_cut = "cut " + str_argument + " " + args.i +" >"+ args.o
+
+# launch the command
+result = os.system( str_cut )
+if (args.extend_print == "True"):
+	sys.stdout.write("input dataset : " + args.i + '\n')
+	sys.stdout.write("column selected : " + args.c + '\n')
+	sys.stdout.write("cut_type : " + args.type_cut+'\n')
+	sys.stdout.write("output dataset : " + args.o+'\n')
+	sys.stdout.write("command launch : " + str_cut+'\n' )
+
+
+
+
+
+
+