Segment extraction and expansion by words

rndseg.py

#!/usr/bin/python3

# CC-BY-4.0

import sys, argparse
from random import shuffle, randrange, choice

# Collate lines, separating them by a space
s = ' '.join(sys.stdin.readlines())
# Remove non-text
s = "".join(c for c in s if (c.isalnum() or (c == ' ')))
# Split into a list of words
s = s.split()

parser = argparse.ArgumentParser(description='Generate a segment of certain word length from standard input.')
parser.add_argument('--length', type=int, help='contiguous segment length in words (all by default)')
parser.add_argument('--resample', type=int, help='resample from segment to get a text of this length')
parser.add_argument('--shuffle', action="store_true", help='shuffle output')
args = parser.parse_args()

if (args.length) :
	L = args.length
	assert (L <= len(s)), "Not enough words to generate segment of desired length."
	i = randrange(0, len(s)-L+1)
	s = s[i:(i+L)]

if (args.resample) :
	s = [choice(s) for _ in range(args.resample)]

if (args.shuffle) : 
	shuffle(s)

# Collate the list of words, separating by a space
s = ' '.join(s)

print(s)

Help
python3 rndseg.py -h

Extract words
echo "A, B? C D." | python3 rndseg.py
A B C D

Extract and shuffle words
echo "A, B? C D." | python3 rndseg.py --shuffle
D B C A

Extract a random contiguous segment of 3 words
echo "A, B? C D." | python3 rndseg.py --length=3
B C D

Extract a random contiguous segment of 3 words; shuffle words
echo "A, B? C D." | python3 rndseg.py --length=3 --shuffle
B C A

Extract a random contiguous segment of 3 words; shuffle words
echo "A, B? C D." | python3 rndseg.py --length=3 | python3 rndseg.py --shuffle
B C A

Extract a random contiguous segment of 3 words; generate a text of 10 words by sampling words from the segment
echo "A, B? C D." | python3 rndseg.py --length=3 --resample=10
B B B B B A C A C C