Created
May 22, 2012 16:55
-
-
Save Mezzle/2770227 to your computer and use it in GitHub Desktop.
SpellChecker Test
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import random, re | |
from string import join | |
class SpellCheckerTest: | |
vowels = ['a','e','i','o','u'] | |
def pick_words(self): | |
sample = [] | |
f = open('/usr/share/dict/words') | |
num_lines = 5 | |
for i, line in enumerate(f): | |
if (i < num_lines): | |
sample.append(line) | |
elif i >= num_lines and random.random() < num_lines/float(i+1): | |
replace = random.randint(0, len(sample)-1) | |
sample[replace] = line | |
f.close() | |
return sample | |
def clean_word(self, word): | |
return word.strip() | |
def generate_words(self): | |
words = self.pick_words() | |
clean_words = [] | |
for word in words: | |
clean_words.append(self.clean_word(word)) | |
new_words = []; | |
for word in clean_words: | |
new_word = self.mangle_word(word) | |
new_words.append(new_word) | |
return new_words | |
def mangle_letter(self, letter): | |
mod_bits = random.getrandbits(3) | |
if (letter in self.vowels) and (mod_bits & 4): | |
letter = random.choice(self.vowels) | |
if mod_bits & 2: | |
letter += letter | |
if mod_bits & 1: | |
letter = letter.upper() | |
return letter | |
def mangle_word(self, word): | |
new_word = [] | |
bits = random.getrandbits(len(word)) | |
for i, c in enumerate(word): | |
if bits & i: | |
c = self.mangle_letter(c) | |
new_word.append(c) | |
return ''.join(new_word) | |
if __name__ == "__main__": | |
o = SpellCheckerTest() | |
for word in o.generate_words(): | |
print word |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment