(编辑:jimmy 日期: 2024/11/13 浏览:2)
前言
"color: #ff0000">1. BF算法
"application/x-tex">Bruce-ForceBruce"application/x-tex">S=ABACABABS=ABACABAB,模式串
def BF(substrS, substrT): if len(substrT) > len(substrS): return -1 j = 0 t = 0 while j < len(substrS) and t < len(substrT): if substrT[t] == substrS[j]: j += 1 t += 1 else: j = j - t + 1 t = 0 if t == len(substrT): return j - t else: return -1
2. KMP算法
"normal">.
"normal">"
"false">(
"normal">′
"text-align: center">"text-align: left">"text-align: center">"text-align: left">"normal">"
"normal">"
"text-align: left">"normal">"
"normal">"
"normal">"
"normal">"
"text-align: left">如果模式串8号位与主串当前位不匹配,找最长公共前后缀,指针前面的子串为
"text-align: left">
位编号
1
2
3
4
5
6
7
8
索引
0
1
2
3
4
5
6
7
模式串
A
B
A
A
B
C
A
C
next
-1
0
0
1
1
2
0
1
"text-align: center">"text-align: left">"application/x-tex">T_j=T_tTj"false">[
"normal">≠
"htmlcode">
def getNext(substrT): next_list = [-1 for i in range(len(substrT))] j = 0 t = -1 while j < len(substrT) - 1: if t == -1 or substrT[j] == substrT[t]: j += 1 t += 1 # Tj=Tt, 则可以到的next[j+1]=t+1 next_list[j] = t else: # Tj!=Tt, 模式串T索引为t的字符与当前位进行匹配 t = next_list[t] return next_list def KMP(substrS, substrT, next_list): count = 0 j = 0 t = 0 while j < len(substrS) and t < len(substrT): if substrS[j] == substrT[t] or t == -1: # t == -1目的就是第一位匹配失败时 # 主串位置加1, 匹配串回到第一个位置(索引为0) # 匹配成功, 主串和模式串指针都后移一位 j += 1 t += 1 else: # 匹配失败, 模式串索引为t的字符与当前位进行比较 count += 1 t = next_list[t] if t == len(substrT): # 这里返回的是索引 return j - t, count+1 else: return -1, count+1
3. KMP算法优化版
"application/x-tex">S=AAABAAAABS=AAABAAAAB,模式串
"text-align: left">"application/x-tex">SS的4号位为模式串
"false">[
def getNextval(substrT): nextval_list = [-1 for i in range(len(substrT))] j = 0 t = -1 while j < len(substrT) - 1: if t == -1 or substrT[j] == substrT[t]: j += 1 t += 1 if substrT[j] != substrT[t]: # Tj=Tt, 但T(j+1)!=T(t+1), 这个就和next数组计算时是一样的 # 可以得到nextval[j+1]=t+1 nextval_list[j] = t else: # Tj=Tt, 且T(j+1)==T(t+1), 这个就是next数组需要更新的 # nextval[j+1]=上一次的nextval_list[t] nextval_list[j] = nextval_list[t] else: # 匹配失败, 模式串索引为t的字符与当前位进行比较 t = nextval_list[t] return nextval_list
"htmlcode">
if __name__ == '__main__': S1 = 'ABACABAB' T1 = 'ABAB' S2 = 'AAABAAAAB' T2 = 'AAAAB' print('*' * 50) print('主串S={0}与模式串T={1}进行匹配'.format(S1, T1)) print('{:*^25}'.format('KMP')) next_list1 = getNext(T1) print('next数组为: {}'.format(next_list1)) index1_1, count1_1 = KMP(S1, T1, next_list1) print('匹配到的位置(索引): {}, 匹配次数: {}'.format(index1_1, count1_1)) print('{:*^25}'.format('KMP优化版')) nextval_list1 = getNextval(T1) print('nextval数组为: {}'.format(nextval_list1)) index1_2, count1_2 = KMP(S1, T1, nextval_list1) print('匹配到的位置(索引): {}, 匹配次数: {}'.format(index1_2, count1_2)) print('') print('*' * 50) print('主串S={0}与模式串T={1}进行匹配'.format(S2, T2)) print('{:*^25}'.format('KMP')) next_list2 = getNext(T2) print('next数组为: {}'.format(next_list2)) index2_1, count2_1 = KMP(S2, T2, next_list2) print('匹配到的位置(索引): {}, 匹配次数: {}'.format(index2_1, count2_1)) print('{:*^25}'.format('KMP优化版')) nextval_list2 = getNextval(T2) print('nextval数组为: {}'.format(nextval_list2)) index2_2, count2_2 = KMP(S2, T2, nextval_list2) print('匹配到的位置(索引): {}, 匹配次数: {}'.format(index2_2, count2_2))
"application/x-tex">S=ABACABABS=ABACABAB与模式串
结束语
在写本篇博客之前也是反复看参考书、视频,边画图边去理解它,这篇博客也是反复修改了好几次,最终算是把KMP解决掉了,有关字符串知识的复习也算是基本结束,下面就是刷题了(虽然在LeetCode做过了几道题)。