# The logic behind writing a spelling corrector - for search results, spell check or whatever..

Sun Dec 29 2019 19:13:40 GMT+0000 (UTC)

```import re
from collections import Counter

def words(text): return re.findall(r'\w+', text.lower())

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

def correction(word):
"Most probable spelling correction for word."
return max(candidates(word), key=P)

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 + R + 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))```
content_copyCOPY

The function correction(word) returns a likely spelling correction. For example, correction('korrectud') 'corrected'

http://norvig.com/spell-correct.html