gen = ''
f = open('sequence.fasta', 'r')
f = f.readlines()
for i in range(0,len(f)):
    if (i % 10000 == 0):
        print(f'{i} strings passed')
    f[i] = f[i][:len(f[i])-1]
    gen += f[i]
print(f'Total len is {len(gen)}')
print(f'Amount of N is {gen.count("N")}')

e = []
gen += 'g'
last = 0
for i in range(1, len(gen)):
    if (gen[i] == 'N' and gen[i-1] != 'N'):
        last = i
    elif (gen[i] != 'N' and gen[i-1] == 'N'):
        e.append(i - last)
e.sort()
ans = 0
min_len = 1000
for i in e:
    if i >= min_len:
        ans += 1
print(f'{ans} strings of N are longer than {min_len}')