markovgen.py

#found here  http://agiliq.com/blog/2009/06/generating-pseudo-random-text-with-markov-chains-u/
#11-2012
import random
import inspect
import re

def lineno():
    """Returns the current line number in our program."""
    return str(inspect.currentframe().f_back.f_lineno)

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()
		print lineno()+" __init__"		
	
	def file_to_words(self):
		self.open_file.seek(0)
		data = self.open_file.read()
		words = data.split()
		print lineno()+" file_t0_words"
		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).
		"""
		a = None
		while a is False:
			if len(self.words) < 3:
				a = False
		print lineno()+" TRIPLES."
		
		for i in range(len(self.words) - 2):
			yield (self.words[i], self.words[i+1], self.words[i+2])
			
	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]
		print lineno()+" DATABASE."
				
	def generate_markov_text(self, par_len):
		size = par_len
		print lineno()+" begin markovgen.generate_markov_text"
		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
#		print lineno()+" "+w1+" WTF!!!!!!!!!!!!!!!!!!"
#		print lineno()+" "+seed_word
#		print lineno()+" "+w2+" WTF!!!!!!!!!!!!!!!!!!"
#		print lineno()+" "+next_word
		gen_words = []
		print lineno()+" GENERATE_MARKOV_TEXT"
		try:
			for i in xrange(size):
				gen_words.append(w1)
				w1, w2 = w2, random.choice(self.cache[(w1, w2)])
		except KeyError:
			return None
			

		gen_words.append(w2)
		print lineno()+" GENERATE_MARKOV_TEXT AFTER for i in xrange."
		return ' '.join(gen_words)