Simple spellchecker

spellcheck.py

from collections import Counter
import sys
import re

WORDLIST = input("Enter dictionary path:")

WORDS = Counter([a.strip() for a in open(WORDLIST).readlines()])

def P(word, N=sum(WORDS.values())): 
	"Probability of `word`."
	return WORDS[word] / N

def correction(word): 
	"Most probable spelling correction for word."
	return sorted(candidates(word), key=P,reverse=True)[0]

def candidates(word): 
	"Generate possible spelling corrections for word."
	return (known([word]) or known(edits1(word)) or known(edits2(word)) or word)

def known(words): 
	"The subset of `words` that appear in the dictionary of WORDS."
	return set(w for w in words if w in WORDS)

def edits1(word):
	"All edits that are one edit away from `word`."
	letters    = 'abcdefghijklmnopqrstuvwxyz'
	splits     = [(word[:i], word[i:])    for i in range(len(word) + 1)]
	deletes    = [L + R[1:]               for L, R in splits if R]
	transposes = [L + R[1] + R[0] + R[2:] for L, R in splits if len(R)>1]
	replaces   = [L + c + R[1:]           for L, R in splits if R for c in letters]
	inserts    = [L + c + R               for L, R in splits for c in letters]
	return set(deletes + transposes + replaces + inserts)

def edits2(word): 
	"All edits that are two edits away from `word`."
	return (e2 for e1 in edits1(word) for e2 in edits1(e1))

patterns = re.compile(r'[\w\']+')
text = input("Enter path to text needed checking:")
with open(text,"r") as f:
	lines = f.readlines()
	ok = True
	for lidx,content in enumerate(lines):
		idx = 0
		while True:
			m = patterns.search(content,idx)
			if m is None:
				break
			idx = m.end()
			word = m.group(0)
			fixed = correction(word)
			if word == fixed or len(fixed)==1:
				idx = m.end()
			else:
				ok = False
				print(F'{f.name}:{lidx+1}:{m.start()+1}: {word} -> {fixed}')
	if ok:
		print("Hooray! No spelling mistakes was found!")