DISUBSTR - Distinct Substrings
Given a string, we need to find the total number of its distinct substrings.
Input
T- number of test cases. T<=20;
Each test case consists of one string, whose length is <= 1000
Output
For each test case output one number saying the number of distinct substrings.
Example
Sample Input:
2
CCCCC
ABABA
Sample Output:
5
9
Explanation for the testcase with string ABABA:
len=1 : A,B
len=2 : AB,BA
len=3 : ABA,BAB
len=4 : ABAB,BABA
len=5 : ABABA
Thus, total number of distinct substrings is 9.
子串是后缀的前缀
ans = 所有子串 - 相同前缀数量(height之和)
#include <bits/stdc++.h>
using namespace std;
const int mn = 1010;
int c[mn], x[mn], y[mn];
int sa[mn], Rank[mn], height[mn];
bool cmp(int *r, int a, int b, int l)
{
return r[a] == r[b] && r[a + l] == r[b + l];
}
void da(char str[], int n, int m)
{
n++;
for (int i = 0; i < m; i++)
c[i] = 0;
for (int i = 0; i < n; i++)
c[x[i] = str[i]]++;
for (int i = 1; i < m; i++)
c[i] += c[i - 1];
for (int i = n - 1; i >= 0; i--)
sa[--c[x[i]]] = i;
for (int j = 1; j <= n; j <<= 1)
{
int p = 0;
for (int i = n - j; i < n; i++)
y[p++] = i;
for (int i = 0; i < n; i++)
if (sa[i] >= j)
y[p++] = sa[i] - j;
for (int i = 0; i < m; i++)
c[i] = 0;
for (int i = 0; i < n; i++)
c[x[y[i]]]++;
for (int i = 1; i < m; i++)
c[i] += c[i - 1];
for (int i = n - 1; i >= 0; i--)
sa[--c[x[y[i]]]] = y[i];
swap(x, y);
p = 1;
x[sa[0]] = 0;
for (int i = 1; i < n; i++)
x[sa[i]] = cmp(y, sa[i - 1], sa[i], j) ? p - 1 : p++;
if (p >= n)
break;
m = p;
}
int k = 0;
n--;
for (int i = 0; i <= n; i++)
Rank[sa[i]] = i;
for (int i = 0; i < n; i++)
{
if (k)
k--;
int j = sa[Rank[i] - 1];
while (str[i + k] == str[j + k])
k++;
height[Rank[i]] = k;
}
}
char ch[mn];
int main()
{
int T;
scanf("%d", &T);
while (T--)
{
scanf("%s", ch);
int len = strlen(ch);
da(ch, len, 128);
int sum = (len + 1) * len / 2;
int tans = 0;
for (int i = 1; i <= len; i++)
tans += height[i];
printf("%d\n", sum - tans);
}
return 0;
}

本文介绍了一个使用后缀数组解决的算法问题:如何计算给定字符串的所有不重复子串的数量。通过构建后缀数组并利用高度数组计算相同前缀的数量,最终得出所有不重复子串的总数。
3056

被折叠的 条评论
为什么被折叠?



