import getopt
import sys
import string

NOT_FOUND = 'Not Found'


def main(argv):
    inputfile = 'seneca.txt'
    pattern = 'omne'
    input_text = ''

    try:
        opts, args = getopt.getopt(argv, "hi:p:", ["ifile=", "pattern="])
    except getopt.GetoptError:
        print('test.py -i <inputfile> -p <pattern>')
        sys.exit(2)
    for opt, arg in opts:
        if opt == '-h':
            print('test.py -i <inputfile> -p <pattern>')
            sys.exit()
        elif opt in ("-i", "--ifile"):
            inputfile = arg
        elif opt in ("-p", "--pattern"):
            pattern = arg

    with open(inputfile, 'r') as f:
        input_text = f.read()

    # result = boyer_moore_matcher(input_text, pattern)
    # print(result)
    # text = input_text[result + 1:]
    text = input_text
    print(input_text)
    print(f'length: ')
    results = []
    while True:
        result = boyer_moore_matcher(text, pattern)
        # print(result)
        if result == NOT_FOUND:
            break
        else:
            index = results[-1] if len(results) > 0 else 0
            index = index + result
            results.append(index if len(results) == 0 else index + 1)
            # print(index)
            # print(f'AA "{input_text[index if len(results) == 1 else index + 1]}" "{text[result]}"')
            text = text[result + 1:]
            if len(text) == 0:
                break
    print(results)
    print(len(results))
    get_words(input_text, results)


def get_words(text, results):
    for result in results:
        start = result
        end = result
        # print(f'AAAAAAAAAA {text[result]} {result}')
        # print(f'start {text[start - 1]} {start - 1}')

        while start > 0 and text[start - 1] not in string.whitespace:
            # print(f'start before {text[start]} {start}')
            # print('inside start')

            start = start - 1
            # print(f'start {text[start]} {start}')

        # print(f'end {text[end + 1]} {end + 1}')
        while end < len(text) - 1 and text[end + 1] not in string.whitespace:
            # print('inside end')
            end = end + 1
        print(f'{text[start:end + 1]} {start} {end}')


def boyer_moore_matcher(text, pattern):
    # print(pattern)
    # print(text)

    last = get_last(text, pattern)
    print(f'LAAAST {last}')
    n = len(text)
    m = len(pattern)
    i = m - 1
    j = m - 1
    if n <= i:
        return NOT_FOUND

    while True:
        # print(text)
        if pattern[j] == text[i]:
            if j == 0:
                return i
            else:
                i = i - 1
                j = j - 1
        else:
            i = i + m - min(j, 1 + last[text[i]])
            j = m - 1
        if i > n - 1:
            print('BREAK')
            break
    return NOT_FOUND


def get_last(text, pattern):
    last = {}
    charset = set(text)
    for i in charset:
        last[i] = pattern.rfind(i)
    return last


if __name__ == "__main__":
    main(sys.argv[1:])