本文使用 Python 實(shí)現(xiàn)了前綴樹(shù)，并且支持編輯距離容錯(cuò)的查詢。文中的前綴樹(shù)只存儲(chǔ)了三個(gè)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(jìn)行數(shù)據(jù)的替換。在查詢的時(shí)候要指定一個(gè)字符串和最大的容錯(cuò)編輯距離。
class Word:
def __init__(self, word, freq):
self.word = word
self.freq = freq
class 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 = -1
self.ADD = 1
self.SAME = 0
self.CHANGE = 2
self.START = 3
self.pointers = []
self.char = char
self.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)
break
elif 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 suggestions
def buildTrieFromFile():
trie = Trie()
rows = [('中海晉西園', 2),('中海西園', 24),('中南海', 4)]
for row in rows:
trie.insert(row[0], int(row[1]))
return trie
def 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)
到此這篇關(guān)于Python容錯(cuò)的前綴樹(shù)實(shí)現(xiàn)中文糾錯(cuò)的文章就介紹到這了,更多相關(guān)Python 中文糾錯(cuò)內(nèi)容請(qǐng)搜索腳本之家以前的文章或繼續(xù)瀏覽下面的相關(guān)文章希望大家以后多多支持腳本之家！
