#!/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 sys

import htmlutils
import linguistic


for filepath in sys.argv[1:]:
	print('file:', filepath)
	source_html = htmlutils.read_file(filepath)
	
	# get title
	title = htmlutils.get_title(source_html)
	if title:
		print('title: '+title)
	else:
		print('no title found')
	
	# get content
	text = htmlutils.get_content(source_html)
	del source_html
	
	linguistic.words_stats(open(filepath+'.words.csv', 'w', encoding='utf-8'), text, linguistic.word_re)
	linguistic.chars_stats(open(filepath+'.chars.csv', 'w', encoding='utf-8'), text, linguistic.char_re)
	linguistic.word_groups_stats(open(filepath+'.word_groups.csv', 'w', encoding='utf-8'), text, linguistic.word_re)
	print()