git-markov

#!/usr/bin/env python

import random, sys, os

random.seed()
nonword = "\n" # Since we split on whitespace, this can never be a word
w1 = nonword
w2 = nonword

# GENERATE TABLE
table = {}

git_log = os.popen("git log --pretty=oneline --abbrev-commit")
for line in git_log:
    for word in line.split()[1:]:
        table.setdefault( (w1, w2), [] ).append(word)
        w1, w2 = w2, word

table.setdefault( (w1, w2), [] ).append(nonword) # Mark the end of the file

# GENERATE OUTPUT
maxwords = int(random.random() * 50)
(w1, w2) = random.choice(table.keys())

first = True
for i in xrange(maxwords):
    newword = random.choice(table[(w1, w2)])
    if newword == nonword: sys.exit()
    if first:
        print(newword.capitalize()),
        first = False
    else:
        print(newword),
    w1, w2 = w2, newword

print "Haha"