Find_Common_Strings

#!/usr/bin/env python

import sys
import os

# Global variables
file_names = []
file_contents = []
line = "" #temporary variable for line


def help():
    print "USAGE: common_id FILE_1 FILE_2 ... FILE_N\n"
    return None

def find_common(id1, id2):
    count = 0
    for i in xrange(len(file_contents[id1])):
        for ii in xrange(len(file_contents[id2])):
            if(file_contents[id1][i] == file_contents[id2][ii]):
                count += 1
    # print "id1 = %d, id2 = %d, count = %d" % (id1, id2, count)
    return count


# Logics itself
if (len(sys.argv) < 3 or sys.argv[1] == "-h"):
        help()
        exit()

#Check filenames
for i in xrange(1, len(sys.argv)):
    print "Filename = %s" % (sys.argv[i])
    if( os.path.exists(sys.argv[i]) and os.path.isfile(sys.argv[i]) ):
        file_names.append(sys.argv[i])
    else:
        print "ERROR: File %s not exists or is inaccessible!" % (sys.argv[i])
        print "Exiting..."
        exit()

print "filenames len = %d" % (len(file_names))

#Read files
for f_id in xrange(len(file_names)):
    file_contents.append([])
    pfile = open(file_names[f_id], 'r')
    line = pfile.readline()
    # t_id = 1
    while (line != None) and (line != "" ):
        file_contents[f_id].append(line)
        line = pfile.readline()
    pfile.close()
    # print "%d" % (t_id)
    # t_id = t_id + 1
    # print "File = %s; len = %d" % ( file_names[f_id], len(file_contents[f_id]) )

# print "Contents = %d" % (len(file_contents))

# Another global variable
out_table = [["" for x in xrange(len(file_names) + 1)] for x in xrange(len(file_names) + 1)]

out_table[0][0] = "\\"
out_str = ""
tmp_int = 0
tmp_str = ""
for ix in xrange(len(file_names)):
    out_table[ix+1][0] = file_names[ix] # horizontal names
    out_table[0][ix+1] = file_names[ix] # vertical   names

    for iy in xrange(len(file_names)):
        if out_table[ix+1][iy+1] == "" :
            if ix == iy:
                out_table[ix+1][iy+1] = "\\"
            else:
                out_table[ix+1][iy+1] = str(find_common(ix,iy))
                out_table[iy+1][ix+1] = out_table[ix+1][iy+1] # copying identical values

for ix in xrange(len(out_table)):
    for iy in xrange(len(out_table[ix])):
        out_str += out_table[ix][iy]
        if( iy < (len(out_table) - 1)):
            out_str += ", "
    out_str += "\n"

print out_str

pfile = open('out.csv', 'w')
pfile.write(out_str)
pfile.close()