"""This module contains a code example related to
Think Python, 2nd Edition
by Allen Downey
http://thinkpython2.com
Copyright 2015 Allen Downey
License: http://creativecommons.org/licenses/by/4.0/
"""
from __future__ import print_function, division
import sys
import string
import random
suffix_map = {}
prefix = ()
def process_file(filename, order=2):
"""Reads a file and performs Markov analysis.
filename: string
order: integer number of words in the prefix
returns: map from prefix to list of possible suffixes.
"""
fp = open(filename)
skip_gutenberg_header(fp)
for line in fp:
if line.startswith('*** END OF THIS'):
break
for word in line.rstrip().split():
process_word(word, order)
def skip_gutenberg_header(fp):
"""Reads from fp until it finds the line that ends the header.
fp: open file object
"""
for line in fp:
if line.startswith('*** START OF THIS'):
break
def process_word(word, order=2):
"""Processes each word.
word: string
order: integer
During the first few iterations, all we do is store up the words;
after that we start adding entries to the dictionary.
"""
global prefix
if len(prefix) < order:
prefix += (word,)
return
try:
suffix_map[prefix].append(word)
except KeyError:
suffix_map[prefix] = [word]
prefix = shift(prefix, word)
def random_text(n=100):
"""Generates random wordsfrom the analyzed text.
Starts with a random prefix from the dictionary.
n: number of words to generate
"""
start = random.choice(list(suffix_map.keys()))
for i in range(n):
suffixes = suffix_map.get(start, None)
if suffixes == None:
random_text(n-i)
return
word = random.choice(suffixes)
print(word, end=' ')
start = shift(start, word)
def shift(t, word):
"""Forms a new tuple by removing the head and adding word to the tail.
t: tuple of strings
word: string
Returns: tuple of strings
"""
return t[1:] + (word,)
def main(script, filename='158-0.txt', n=100, order=2):
try:
n = int(n)
order = int(order)
except ValueError:
print('Usage: %d filename [# of words] [prefix length]' % script)
else:
process_file(filename, order)
random_text(n)
print()
if __name__ == '__main__':
main(*sys.argv)