怎样写一个拼写检查器,拼写检查器,#!/usr/bin/p
文章由Byrx.net分享于2019-03-23 09:03:46
怎样写一个拼写检查器,拼写检查器,#!/usr/bin/p
#!/usr/bin/pythonimport 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 modelNWORDS = train(words(file('big.txt').read()))alphabet = 'abcdefghijklmnopqrstxyz'def edist1(word): n = len(word) return set([word[0:i]+word[i+1: ] for i in range(n)] + #deletion [word[0:i]+word[i+1]+word[i]+word[i+2: ] for i in range(n-1)] + #transposition [word[0:i]+c+word[i+1: ] for i in range(n) for c in alphabet] + #alteration [word[0:i]+c+word[i: ] for i in range(n+1) for c in alphabet]) #insertiondef known_edist2(word): return set(e2 for e1 in edist1(word) for e2 in edist1(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(edist1(word)) or known_edist2(word) or [word] return max(candidates, key=lambda w:NWORDS[w])print('thew => ' + correct('thew'))print('spak => ' + correct('spak'))print('goof => ' + correct('goof'))print('babyu => ' + correct('babyu'))print('spalling => ' + correct('spalling'))#该片段来自于http://byrx.net
评论关闭