Forum Moderators: coopster
I came across this perl script someone wrote for spelling suggestions when someone types a wrong spelling. Can someone please convert it to PHP? It will help a lot of people.
Source: <snip>
import re, collectionsdef words(text): return re.findall('[a-z]+', text.lower())
def train(features):
model = collections.defaultdict(lambda: 1)
for f in features:
model[f] += 1
return model
NWORDS = train(words(file('big.txt').read()))
alphabet = 'abcdefghijklmnopqrstuvwxyz'
def edits1(word):
s = [(word[:i], word[i:]) for i in range(len(word) + 1)]
deletes = [a + b[1:] for a, b in s if b]
transposes = [a + b[1] + b[0] + b[2:] for a, b in s if len(b)>1]
replaces = [a + c + b[1:] for a, b in s for c in alphabet if b]
inserts = [a + c + b for a, b in s for c in alphabet]
return set(deletes + transposes + replaces + inserts)
def known_edits2(word):
return set(e2 for e1 in edits1(word) for e2 in edits1(e1) if e2 in NWORDS)
def known(words): return set(w for w in words if w in NWORDS)
def correct(word):
candidates = known([word]) or known(edits1(word)) or known_edits2(word) or [word]
return max(candidates, key=NWORDS.get)
[edited by: eelixduppy at 12:46 am (utc) on June 22, 2009]
[edit reason] No personal urls, thanks. [/edit]
levenshtein() [ca3.php.net]
similar_text() [ca3.php.net]
metaphone() [ca3.php.net]
soundex() [ca3.php.net]
