import csv
import sys


def main():

    # TODO: Check for command-line usage
    if len(sys.argv) != 3:
        sys.exit("Usage: python dna.py data.csv sequence.txt")

    # TODO: Read database file into a variable
    csvFile = sys.argv[1]
    with open(csvFile) as file1:
        reader = csv.reader(file1, delimiter=',' , quotechar='"')
        lines = list(reader)

    # TODO: Read DNA sequence file into a variable
    database = []
    for data in lines:
        database.append(data)
    # print(f"{database}")

    # TODO: Find longest match of each STR in DNA sequence
    txtFile = sys.argv[2]
    file2 = open(txtFile, 'r')
    sequence = file2.read()

    profile = []
    for i in range(1, len(database[0])):
        subsequence = database[0][i]
        n = longest_match(sequence, subsequence)
        profile.append(n)
    # print(f"{profile}")

    # TODO: Check database for matching profiles
    row = 1
    column = 1
    index = 0
    while row < len(database):
        if profile[index] == int(database[row][column]):
            column += 1
            index += 1
            if column == len(database[row]):
                print(f"{database[row][0]}")
                break
        else:
            column = 1
            row += 1
            if row == len(database):
                print("No match")

    return


def longest_match(sequence, subsequence):
    """Returns length of longest run of subsequence in sequence."""

    # Initialize variables
    longest_run = 0
    subsequence_length = len(subsequence)
    sequence_length = len(sequence)

    # Check each character in sequence for most consecutive runs of subsequence
    for i in range(sequence_length):

        # Initialize count of consecutive runs
        count = 0

        # Check for a subsequence match in a "substring" (a subset of characters) within sequence
        # If a match, move substring to next potential match in sequence
        # Continue moving substring and checking for matches until out of consecutive matches
        while True:

            # Adjust substring start and end
            start = i + count * subsequence_length
            end = start + subsequence_length

            # If there is a match in the substring
            if sequence[start:end] == subsequence:
                count += 1

            # If there is no match in the substring
            else:
                break

        # Update most consecutive matches found
        longest_run = max(longest_run, count)

    # After checking for runs at each character in seqeuence, return longest run found
    return longest_run


main()