Rabin-Karp算法实现

时间:2019-05-29 17:55:26

标签: python

此代码使用Rabin-Karp算法比较两个文本文件。当两个文件都包含大约1000个单词时,将花费几分钟。我该如何改善?我是Python的新手。

class RollingHash:
    def __init__(self, text, sizeWord):
        self.text = text
        self.hash = 0 
        self.sizeWord = sizeWord

        for i in range(0, sizeWord):
            #subtract out the ASCII value of "a" to start the indexing at zero
            self.hash += (ord(self.text[i]) - ord("a")+1)*(26**(sizeWord - i -1))
        #start index of current window
        self.window_start = 0
        #end of index window
        self.window_end = sizeWord

    def move_window(self):
        if self.window_end <= len(self.text) - 1:

            self.hash -= (ord(self.text[self.window_start]) - ord("a")+1)*26**(self.sizeWord-1)
            self.hash *= 26
            self.hash += ord(self.text[self.window_end])- ord("a")+1
            self.window_start += 1
            self.window_end += 1

    def window_text(self):
        return self.text[self.window_start:self.window_end]

def rabin_karp(word, text):
    if word == "" or text == "":
        return None
    if len(word) > len(text):
        return None

    rolling_hash = RollingHash(text, len(word))
    word_hash = RollingHash(word, len(word))
    word_hash.move_window()

    for i in range(len(text) - len(word) + 1):
        if rolling_hash.hash == word_hash.hash:
            if rolling_hash.window_text() == word:
                return i
        rolling_hash.move_window()
    return None

0 个答案:

没有答案