Markov text generator, with bug fix to wrap around from end of source text to the start. Also add a method to generate complete sentences based on the location of periods in the source.

gistfile1.py

import random

class Markov(object):
	
	def __init__(self, open_file):
		self.cache = {}
		self.open_file = open_file
		self.words = self.file_to_words()
		self.word_size = len(self.words)
		self.database()
		
	
	def file_to_words(self):
		self.open_file.seek(0)
		data = self.open_file.read()
		words = data.split()
		return words
		
	
	def triples(self):
		""" Generates triples from the given data string. So if our string were
				"What a lovely day", we'd generate (What, a, lovely) and then
				(a, lovely, day).
		"""
		
		if self.word_size < 3:
			return
		
		for i in range(self.word_size):
			yield (self.words[i], 
				   self.words[(i+1)%self.word_size], 
				   self.words[(i+2)%self.word_size])
			
	def database(self):
		for w1, w2, w3 in self.triples():
			key = (w1, w2)
			if key in self.cache:
				self.cache[key].append(w3)
			else:
				self.cache[key] = [w3]
				
	def generate_markov_text(self, size=25):
		seed = random.randint(0, self.word_size-3)
		seed_word, next_word = self.words[seed], self.words[seed+1]
		w1, w2 = seed_word, next_word
		gen_words = []
		for i in xrange(size):
			gen_words.append(w1)
			w1, w2 = w2, random.choice(self.cache[(w1, w2)])
		return ' '.join(gen_words)
			
	def generate_markov_sentences(self, size=3):
		seed = random.randint(0, self.word_size-3)
		is_sentence_found = False
		while not is_sentence_found:
			seed_word = self.words[seed]
			is_sentence_found = seed_word.endswith('.')
			seed = (seed + 1) % (self.word_size-3)
		seed_word, next_word = self.words[seed], self.words[seed+1]
		sentence_count = 0
		w1, w2 = seed_word, next_word
		gen_words = []
		while sentence_count < size:
			gen_words.append(w1)
			if w1.endswith('.'):
				sentence_count += 1
			w1, w2 = w2, random.choice(self.cache[(w1, w2)])
		return ' '.join(gen_words)