本文使用 Python 實現了前綴樹，并且支持編輯距離容錯的查詢。文中的前綴樹只存儲了三個分詞，格式為 (分詞字符串,頻率) ，如：(’中海晉西園’, 2)、(’中海西園’, 24)、(’中南海’, 4)，可以換成自己的文件進行數據的替換。在查詢的時候要指定一個字符串和最大的容錯編輯距離。

class Word: def __init__(self, word, freq):self.word = wordself.freq = freqclass Trie: def __init__(self):self.root = LetterNode(’’)self.START = 3 def insert(self, word, freq):self.root.insert(word, freq, 0) def findAll(self, query, maxDistance):suggestions = self.root.recommend(query, maxDistance, self.START)return sorted(set(suggestions), key=lambda x: x.freq)class LetterNode: def __init__(self, char):self.REMOVE = -1self.ADD = 1self.SAME = 0self.CHANGE = 2self.START = 3self.pointers = []self.char = charself.word = None def charIs(self, c):return self.char == c def insert(self, word, freq, depth):if ’ ’ in word: word = [i for i in word.split(’ ’)]if depth < len(word): c = word[depth].lower() for next in self.pointers:if next.charIs(c): return next.insert(word, freq, depth + 1) nextNode = LetterNode(c) self.pointers.append(nextNode) return nextNode.insert(word, freq, depth + 1)else: self.word = Word(word, freq) def recommend(self, query, movesLeft, lastAction):suggestions = []length = len(query)if length >= 0 and movesLeft - length >= 0 and self.word: suggestions.append(self.word)if movesLeft == 0 and length > 0: for next in self.pointers:if next.charIs(query[0]): suggestions += next.recommend(query[1:], movesLeft, self.SAME) breakelif movesLeft > 0: for next in self.pointers:if length > 0: if next.charIs(query[0]):suggestions += next.recommend(query[1:], movesLeft, self.SAME) else:suggestions += next.recommend(query[1:], movesLeft - 1, self.CHANGE)if lastAction != self.CHANGE and lastAction != self.REMOVE: suggestions += next.recommend(query, movesLeft - 1, self.ADD)if lastAction != self.ADD and lastAction != self.CHANGE: if length > 1 and next.charIs(query[1]):suggestions += next.recommend(query[2:], movesLeft - 1, self.REMOVE) elif length > 2 and next.charIs(query[2]) and movesLeft == 2:suggestions += next.recommend(query[3:], movesLeft - 2, self.REMOVE)else: if lastAction != self.CHANGE and lastAction != self.REMOVE:suggestions += next.recommend(query, movesLeft - 1, self.ADD)return suggestionsdef buildTrieFromFile(): trie = Trie() rows = [(’中海晉西園’, 2),(’中海西園’, 24),(’中南?！? 4)] for row in rows:trie.insert(row[0], int(row[1])) return triedef suggestor(trie, s, maxDistance): if ’ ’ in s:s = [x for x in s.split(’ ’)] suggestions = trie.findAll(s, maxDistance) return [str(x.word) for x in suggestions]if __name__ == '__main__': trie = buildTrieFromFile() r = suggestor(trie, ’中海晉西園’, 1) print(r)

分析

結果打?。篬’中海晉西園’, ’中海西園’]

可以看出“中海晉西園”是和輸入完全相同的字符串，編輯距離為 0 ，所以符合最大編輯距離為 1 的要求，直接返回。

“中海西園”是“中海晉西園”去掉“晉”字之后的結果，編輯距離為 1， 所以符合最大編輯距離為 1 的要求，直接返回。

另外，“中南?！焙汀爸泻x西園”的編輯距離為 4 ，不符合最大編輯距離為 1 的要求，所以結果中沒有出現。

https://github.com/leoRoss/AutoCorrectTrie

到此這篇關于Python容錯的前綴樹實現中文糾錯的文章就介紹到這了,更多相關Python 中文糾錯內容請搜索好吧啦網以前的文章或繼續瀏覽下面的相關文章希望大家以后多多支持好吧啦網！