PSET6 DNA

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
    database = sys.argv[1]
    db_names = []
    strnames = []

    with open(database, 'r') as file1:
        reader = csv.DictReader(file1)

        for line in reader:
#            team["rating"] = int(team["rating"])
            db_names.append(line)

        strnames = reader.fieldnames
        strnames.pop(0)

    print(db_names)
    print(strnames)
    file1.close()


    # TODO: Read DNA sequence file into a variable
    sequence = sys.argv[2]
    with open(sequence, 'r') as file2:
        dna = file2.read()
    file2.close()

    # TODO: Find longest match of each STR in DNA sequence
    str_counts = []
    for element in strnames:
        str_counts.append(longest_match(dna, element))

    print(str_counts)

    # TODO: Check database for matching profiles
    # Find the str key in the db_names and compare the value of that key to str_runs

    # I know this is currently wrong. pls help
    for i in db_names[strnames]:
        matches = 0
        print(db_names[i])
        for j in str_counts:
            if i == j:
                matches += 1
            if matches == strnames:
                print(db_names[i]['name'])
                exit(0)
    print("No match")

#    for i in range(len(strnames)):

    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()