#!/usr/bin/env python3
# -*- coding: utf-8 -*-

# This program is free software: you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation, either version 3 of the License, or
# (at your option) any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with this program.  If not, see <http://www.gnu.org/licenses/>.


import argparse

from fileutils import *
from stop_words import *
from terms import *


parser = argparse.ArgumentParser()
parser.add_argument(
	'files', metavar='file',
	nargs='+'
)
parser.add_argument(
	'--force-html',
	default=False, action='store_true',
	help='Do not use file extension to determine format but force HTML instead.'
)
args = parser.parse_args()


texts = [open_file(filepath) for filepath in args.files]
stop_words = find_stop_words(texts)
print('  '.join(stop_words))
for filepath, text in zip(args.files, texts):
	terms = find_repeated_terms(text, stop_words)
	print()
	print(filepath)
	print('\n'.join(str(b)+' '+a for a, b in sorted(terms.items(), key=lambda x: (-x[1], x[0]))))