1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
|
#!/usr/bin/python3
# -*- coding: utf-8 -*-
# Copyright © 2013 marmuta <marmvta@gmail.com>
#
# This file is part of Onboard.
#
# Onboard 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.
#
# Onboard 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 os
import sys
import random
from optparse import OptionParser
from pypredict import *
def main():
parser = OptionParser(usage="Usage: %prog [options] text-file")
parser.add_option("-i", "--in-place",
action="store_true", dest="in_place", default=False,
help="overwrite the input file")
parser.add_option("-p", "--paragraphs",
action="store_true", dest="paragraphs", default=False,
help="save all sentences as paragraphs (extra newline)")
options, args = parser.parse_args()
in_place = options.in_place
paragraphs = options.paragraphs
filename = args[0]
text = read_corpus(filename)
sentences, spans = split_sentences(text)
random.seed()
random.shuffle(sentences)
if in_place:
with codecs.open(filename, "w", encoding='utf-8') as f:
for s in sentences:
f.write(s + "\n")
if paragraphs:
f.write("\n")
else:
for s in sentences:
print(s)
if paragraphs:
print()
if __name__ == '__main__':
main()
|
