import argparse
from unidecode import unidecode

from xlrd import open_workbook


class Person:
    def __init__(self, fname, lname):
        self.fname = str(fname).lower()
        self.lname = str(lname).lower()

    @staticmethod
    def normalize(name):
        return unidecode(name.replace('-', ' '))

    def __eq__(self, other):
        return Person.normalize(self.fname) == Person.normalize(other.fname) \
               and Person.normalize(self.lname) == Person.normalize(other.lname)

    def __str__(self):
        return "{0} {1}".format(self.fname.title(), self.lname.title())

    def __hash__(self):
        return hash(self.fname + self.lname)


def main(files):
    items = []
    dupes = set()

    for file in files:
        with open_workbook(file) as wb:
            for sheet in wb.sheets():
                number_of_rows = sheet.nrows
                number_of_columns = sheet.ncols

                for row in range(number_of_rows):
                    values = []
                    for col in range(number_of_columns):
                        value = sheet.cell(row, col).value
                        values.append(value)
                    item = Person(*values)

                    if item not in items:
                        items.append(item)
                    else:
                        dupes.add(item)

    print('Nombre de duplicatas : {0}'.format(len(dupes)))
    for dupe in dupes:
        print(dupe)


if __name__ == '__main__':
    ap = argparse.ArgumentParser()
    ap.add_argument('-f', '--files', type=str, nargs='+', help='Files to compare.', required=True)

    args = ap.parse_args()
    files = args.files

    print('WARNING')
    print('All your sheets should have the same column order.\n')

    main(files)