试图让这个拼写检查器我在网上遇到工作,但没有运气。任何帮助,将不胜感激。来自http://norvig.com/spell-correct.html的原始代码
import re, collections, codecs
def 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
file = codecs.open('C:\88888\88888\88888\88888\8888\A Word.txt', encoding='utf-8', mode='r')
NWORDS = train(words(file.read()))
alphabet = 'abcdefghijklmnopqrstuvwxyz'
def edits1(word):
splits = [(word[:i], word[i:]) for i in range(len(word) + 1)]
deletes = [a + b[1:] for a, b in splits if b]
transposes = [a + b[1] + b[0] + b[2:] for a, b in splits if len(b)>1]
replaces = [a + c + b[1:] for a, b in splits for c in alphabet if b]
inserts = [a + c + b for a, b in splits 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)
错误:
File "C:\8888\8888\8888\8888\88888\SpellCheck.py", line 11
file = codecs.open('C:\888\888\888\8888\88888\A Word.txt', encoding='utf-8', mode='r')
^
SyntaxError: (unicode error) 'unicodeescape' codec can't decode bytes in position 2-3: truncated \UXXXXXXXX escape