后缀数组+分治
#include <iostream>
#include <cstdio>
#include <cstdlib>
#include <cmath>
#include <queue>
#include <algorithm>
#include <vector>
#include <cstring>
#include <stack>
#include <cctype>
#include <utility>
#include <map>
#include <string>
#include <climits>
#include <set>
#include <string>
#include <sstream>
#include <utility>
#include <ctime>
#include <bitset>
//#pragma comment(linker, "/STACK:102400000,102400000")
using std::priority_queue;
using std::vector;
using std::swap;
using std::stack;
using std::sort;
using std::max;
using std::min;
using std::pair;
using std::map;
using std::string;
using std::cin;
using std::cout;
using std::set;
using std::queue;
using std::string;
using std::stringstream;
using std::make_pair;
using std::getline;
using std::greater;
using std::endl;
using std::multimap;
using std::deque;
using std::unique;
using std::lower_bound;
using std::random_shuffle;
using std::bitset;
using std::upper_bound;
using std::multiset;
typedef long long LL;
typedef unsigned long long ULL;
typedef unsigned UN;
typedef pair<int, int> PAIR;
typedef multimap<int, int> MMAP;
typedef LL TY;
typedef long double LF;
const int MAXN(500010);
const int MAXM(50010);
const int MAXE(150010);
const int MAXK(6);
const int HSIZE(1313);
const int SIGMA_SIZE(4);
const int MAXH(20);
const int INFI((INT_MAX-1) >> 1);
const ULL BASE(31);
const LL LIM(1e13);
const int INV(-10000);
const int MOD(31313);
const double EPS(1e-7);
const LF PI(acos(-1.0));
template<typename T> inline void checkmax(T &a, T b){if(b > a) a = b;}
template<typename T> inline void checkmin(T &a, T b){if(b < a) a = b;}
template<typename T> inline T ABS(const T &a){return a < 0? -a: a;}
struct SA
{
char S[MAXN];
int sa[MAXN],t1[MAXN], t2[MAXN], cnt[MAXN], len, M;
void init(int tl, int tm = 128)
{
len = tl;
M = tm;
int *p1 = t1, *p2 = t2;
for(int i = 0; i < M; ++i) cnt[i] = 0;
for(int i = 0; i <= len; ++i) ++cnt[p1[i] = S[i]];
for(int i = 1; i < M; ++i) cnt[i] += cnt[i-1];
for(int i = len; i >= 0; --i) sa[--cnt[p1[i]]] = i;
int temp = 1;
for(int k = 1; temp <= len; k <<= 1)
{
temp = 0;
for(int i = len-k+1; i <= len; ++i) p2[temp++] = i;
for(int i = 0; i <= len; ++i)
if(sa[i] >= k) p2[temp++] = sa[i]-k;
for(int i = 0; i < M; ++i) cnt[i] = 0;
for(int i = 0; i <= len; ++i) ++cnt[p1[p2[i]]];
for(int i = 1; i < M; ++i) cnt[i] += cnt[i-1];
for(int i = len; i >= 0; --i) sa[--cnt[p1[p2[i]]]] = p2[i];
swap(p1, p2);
temp = 1;
p1[sa[0]] = 0;
for(int i = 1; i <= len; ++i)
p1[sa[i]] = p2[sa[i-1]] == p2[sa[i]] && p2[sa[i-1]+k] == p2[sa[i]+k]? temp-1: temp++;
M = temp;
}
}
int rank[MAXN], hei[MAXN];
void getHei()
{
int k = 0;
for(int i = 0; i <= len; ++i) rank[sa[i]] = i;
for(int i = 0; i < len; ++i)
{
if(k) --k;
int j = sa[rank[i]-1];
while(S[i+k] == S[j+k]) ++k;
hei[rank[i]] = k;
}
}
} sa;
LL tans;
int rec[MAXN];
LL sum[MAXN];
void dfs(int l, int r)
{
if(l == r) return;
int m = (l+r) >> 1;
int tl = m-1, tr = m+1;
while(tl >= l && sa.hei[tl+1] > 0) --tl;
while(tr <= r && sa.hei[tr] > 0) ++tr;
rec[m] = sa.hei[m+1];
for(int i = m-1; i > tl; --i) rec[i] = min(rec[i+1], sa.hei[i+1]);
sum[tl] = 0;
for(int i = tl+1; i <= m; ++i) sum[i] = sum[i-1]+rec[i];
int ti = m, th = sa.hei[m+1];
for(int i = m+1; i < tr; ++i)
{
checkmin(th, sa.hei[i]);
while(ti > tl && rec[ti] >= th) --ti;
tans += (LL)th*(m-ti);
tans += sum[ti];
}
dfs(l, m);
dfs(m+1, r);
}
int main()
{
while(~scanf("%s", sa.S))
{
sa.init(strlen(sa.S));
sa.getHei();
tans = 0;
dfs(1, sa.len);
LL len = sa.len;
printf("%lld\n", (len+1)*len/2*(len-1)-2*tans);
}
return 0;
}