from sys import argv, exit
import csv
import re
if len(argv) < 3:
    print("missing command line argument")

with open(argv[1],"r") as file, open(argv[2],"r") as csvfile:
    count = 0
    contents = file.read() #1. Read the sequence file into a string (you've got this).
    csvcontents = csv.reader(csvfile)

    header = next(csvcontents)
    print("header prints")


    print("attempting to print rows of csvfile")
    for row in csvcontents:
        print(row)

    #for item in contents:
    for item in header[1:]:
        #print("item prints:")
        #print(item)
        beg = 0 # beginning index
        end = len(item) # item length
        seqrun = 0
        longest = 0
        while contents[beg:beg+end]:
        #while beg + end <= len(contents):
            if contents[beg:beg+end] == item: # trying to solve the issue of end being incremented incorrectly here
                seqrun = 1
            #while contents[beg + len(item): beg + len(item)] == item:
            #while contents[beg: beg + len(item):end] == item:
            #while contents[beg:end] == item:
                #while contents[beg:beg+len(item): end + len(item)] == item:
                while contents[beg + end: end + end] == item:
                    seqrun += 1
                    #beg += len(item)
                    beg += end
                    #end += len(item) i don't need to increment end as well?
                    if seqrun > longest:
                        longest = seqrun
            beg += 1
            #end += 1
        print(item + " repeats " + str(seqrun) + "times")
        print("longest repeat is " + str(longest) + "times") # why is it longest?