Hdu 5008 Boring String Problem 后缀数组求排名第k位的不重复子串

Boring String Problem

Time Limit: 6000/3000 MS (Java/Others)    Memory Limit: 65536/65536 K (Java/Others)
Total Submission(s): 2046    Accepted Submission(s): 552

Problem Description

In this problem, you are given a string s and q queries.

For each query, you should answer that when all distinct substrings of string s were sorted lexicographically, which one is the k-th smallest. 

A substring s _i...j of the string s = a ₁a ₂ ...a _n(1 ≤ i ≤ j ≤ n) is the string a _ia _i+1 ...a _j. Two substrings s _x...y and s _z...w are cosidered to be distinct if s _x...y ≠ S _z...w

 

Input

The input consists of multiple test cases.Please process till EOF. 

Each test case begins with a line containing a string s(|s| ≤ 10 ⁵) with only lowercase letters.

Next line contains a postive integer q(1 ≤ q ≤ 10 ⁵), the number of questions.

q queries are given in the next q lines. Every line contains an integer v. You should calculate the k by k = (l⊕r⊕v)+1(l, r is the output of previous question, at the beginning of each case l = r = 0, 0 < k < 2 ⁶³, “⊕” denotes exclusive or)

 

Output

For each test case, output consists of q lines, the i-th line contains two integers l, r which is the answer to the i-th query. (The answer l,r satisfies that s _l...r is the k-th smallest and if there are several l,r available, ouput l,r which with the smallest l. If there is no l,r satisfied, output “0 0”. Note that s _1...n is the whole string)

 

Sample Input

  
  

   
   aaa
4
0
2
3
5
  
  

 

Sample Output

  
  

   
   1 1
1 3
1 2
0 0
  
  

 

Source

2014 ACM/ICPC Asia Regional Xi'an Online

给出一个字符串，把所有不同的子串按字典序排序，求字典序排名第k位的子串。

先求后缀数组。因为后缀数组中的后缀已经按照字典序排序，可以根据后缀数组求出截止排名第 i 个后缀一共产生了多少个不同的子串，查询的时候二分一下。

题目要求输出满足条件的子串的起止位置，而且要求位置尽量靠左。那么从二分到的位置开始，向下一直找长度最长的后缀就好了。一直找到height比子串的长度小为止。

最开始想到用线段树查找可能的最右位置，没想到直接暴力就过了。

#include <cstdio>
#include <string.h>
#include <string> 
#include <map>
#include <queue>
#include <vector>
#include <set>
#include <algorithm>
#include <math.h>
#include <cmath>
#include <stack>
#define mem0(a) memset(a,0,sizeof(a))
#define meminf(a) memset(a,0x3f,sizeof(a))
using namespace std;
typedef long long ll;
typedef long double ld;
typedef double db;
const int maxn=100005,inf=0x3f3f3f3f;  
const ll llinf=0x3f3f3f3f3f3f3f3f;   
const ld pi=acos(-1.0L);
int wa[maxn],wb[maxn],wv[maxn],ws[maxn],sa[maxn],ranki[maxn],height[maxn];
int s[maxn];
ll sum[maxn];
char a[maxn];

int cmp(int *r,int a,int b,int l) {
	return r[a]==r[b]&&r[a+l]==r[b+l];
}

void build(int *r,int *sa,int n,int m) {
	int i,j,k,p,*x=wa,*y=wb,*t;
	
	for (i=0;i<m;i++) ws[i]=0;
	for (i=0;i<n;i++) ws[x[i]=r[i]]++;
	for (i=0;i<m;i++) ws[i]+=ws[i-1];
	for (i=n-1;i>=0;i--) 
	    sa[--ws[x[i]]]=i;
	for (j=1,p=1;p<n;j*=2,m=p) {
		for (p=0,i=n-j;i<n;i++) 
		    y[p++]=i;
		for (i=0;i<n;i++) 
		    if (sa[i]>=j) y[p++]=sa[i]-j;
		for (i=0;i<n;i++) 
		    wv[i]=x[y[i]];
		for (i=0;i<m;i++) ws[i]=0;
		for (i=0;i<n;i++) 
		    ws[wv[i]]++;
		for (i=1;i<m;i++) ws[i]+=ws[i-1];
		for (i=n-1;i>=0;i--) 
		    sa[--ws[wv[i]]]=y[i];
		
		t=x;x=y;y=t;
		p=1;x[sa[0]]=0;
		for (i=1;i<n;i++) 
		    x[sa[i]]=cmp(y,sa[i-1],sa[i],j)?p-1:p++;
	}
	
	for (i=1;i<n;i++) ranki[sa[i]]=i;
	k=0; 
	for (i=0;i<n-1;height[ranki[i++]]=k) {
		if (k) k--;
		for (j=sa[ranki[i]-1];r[i+k]==r[j+k];k++);
	}
}

int main() {
	while (scanf("%s",a)!=EOF) {
		int n,i,j,q;
		ll k;
		scanf("%d",&q);
		n=strlen(a);
		for (i=0;i<n;i++) 
			s[i]=a[i]-'a'+1;
		s[n]=0;
		build(s,sa,n+1,27);
		sum[0]=0;sum[1]=n-sa[1];
		for (i=2;i<=n;i++) 
			sum[i]=sum[i-1]+n-sa[i]-height[i];
		int l,r,len;
		l=r=0;
		for (i=1;i<=q;i++) {
			scanf("%lld",&k);
			k=(l^r^k)+1;
			if (k>sum[n]) {
				l=r=0;
				printf("0 0\n");
			} else {
				int pos=lower_bound(sum+1,sum+n,k)-sum;
				l=sa[pos]+1;len=k-sum[pos-1]+height[pos];
				for (j=pos+1;j<=n;j++) {
					if (height[j]<len) break;
					l=min(l,sa[j]+1);
				}
				r=l+len-1;
				printf("%d %d\n",l,r);
			}
		}
	}
	return 0;
}