dna.py

from sys import argv, exit
import csv


def main():

    if len(argv) != 3:
        print("Usage: python dna.py filename.csv filename.txt")
        exit(1)
    people = []

    # The with syntax ensures the file is closed!
    
    # read csv into memory, populating array of persons
    with open(argv[1], 'r') as table:
        reader = csv.DictReader(table)

    # read dna file into vaiable
    with open(argv[2], 'r') as txt:
        text = file.read()


    reader = csv.DictReader(table)
    dna_words = (reader.fieldnames)

    num_terms = len(dna_words)

    Row = namedtuple("Row", dna_words)
    people = [
        Row(**row)
        for row in reader
    ]

    # make function to search for how many repeating occurances of that string there are in the text
    def max_consecutive(string):
        maximum = 0
        length = len(string)
        for j in range(len(text)):
            counter = 0
            while text[j:(j + length)] == string:
                counter += 1
                j = j + length
                if maximum < counter:
                    maximum = counter
        return maximum

    # create person structure by placing the names of str strings into max_consecutive function
    # Row(**{"short": "riff", "lover": "boy"}) is the same as Row(short="riff", lover="boy")
    sample = Row(
        **{dna_word: max_consecutive(dna_word) for dna_word in dna_words}
    )

    # compare sample person information to the information taken from CSV file to determine whether the DNA matches anyone
    # I think this is easier to read as a list comprehension - it has the benefit of being one statement
    matches = [
        person
        for person in people
        if person == sample  # If the values are the same then the objects are equal
    ]
    if matches:
        print(matches[0])
    print("No match")
    exit(1)  # Not sure if you want this but nice to return a different return

if __name_ == "__main__":
    # This means the script only runs if called directly, as opposed to being imported.
    main()