HDU 3518Boring counting（后缀数组）

Boring counting

Time Limit : 2000/1000ms (Java/Other)   Memory Limit : 65536/32768K (Java/Other)

Total Submission(s) : 2   Accepted Submission(s) : 2

Font: Times New Roman | Verdana | Georgia

Font Size: ← →

Problem Description

035 now faced a tough problem,his english teacher gives him a string,which consists with n lower case letter,he must figure out how many substrings appear at least twice,moreover,such apearances can not overlap each other.
Take aaaa as an example.”a” apears four times,”aa” apears two times without overlaping.however,aaa can’t apear more than one time without overlaping.since we can get “aaa” from [0-2](The position of string begins with 0) and [1-3]. But the interval [0-2] and [1-3] overlaps each other.So “aaa” can not take into account.Therefore,the answer is 2(“a”,and “aa”).

Input

The input data consist with several test cases.The input ends with a line “#”.each test case contain a string consists with lower letter,the length n won’t exceed 1000(n <= 1000).

Output

For each test case output an integer ans,which represent the answer for the test case.you’d better use int64 to avoid unnecessary trouble.

Sample Input

aaaa
ababcabb
aaaaaa
#

Sample Output

2
3
3

Source

2010 ACM-ICPC Multi-University Training Contest（9）——Host by HNU

想法：

后缀数组

代码：

#include <stdio.h>
#include <string.h>
#include <algorithm>
using namespace std;
#define N 1005
int wa[N],wb[N],wsf[N],wv[N],sa[N];
int Rank[N],height[N],s[N],f[N],n,ans;
char str[N];//,str2[N];
//sa:字典序中排第i位的起始位置在str中第sa[i]
//rank:就是str第i个位置的后缀是在字典序排第几
//height：字典序排i和i-1的后缀的最长公共前缀
int cmp(int *r,int a,int b,int k)
{
    return r[a]==r[b]&&r[a+k]==r[b+k];
}
void getsa(int *r,int *sa,int n,int m)//n要包含末尾添加的0
{
    int i,j,p,*x=wa,*y=wb,*t;
    for(i=0; i<m; i++)  wsf[i]=0;
    for(i=0; i<n; i++)  wsf[x[i]=r[i]]++;
    for(i=1; i<m; i++)  wsf[i]+=wsf[i-1];
    for(i=n-1; i>=0; i--)  sa[--wsf[x[i]]]=i;
    for(p=1,j=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++)  wsf[i]=0;
        for(i=0; i<n; i++)  wsf[wv[i]]++;
        for(i=1; i<m; i++)  wsf[i]+=wsf[i-1];
        for(i=n-1; i>=0; i--)  sa[--wsf[wv[i]]]=y[i];
        t=x;
        x=y;
        y=t;
        x[sa[0]]=0;
        for(p=1,i=1; i<n; i++)
            x[sa[i]]=cmp(y,sa[i-1],sa[i],j)? p-1:p++;
    }
}
void getheight(int *r,int n)//n不保存最后的0
{
    int i,j,k=0;
    for(i=1; i<=n; i++)  Rank[sa[i]]=i;
    for(i=0; i<n; i++)
    {
        if(k)
            k--;
        else
            k=0;
        j=sa[Rank[i]-1];
        while(r[i+k]==r[j+k])
            k++;
        height[Rank[i]]=k;
    }
}
void judge(int len)
{
    int mx=0,mn=1005;
    for(int i=1;i<=n;i++)
    {
        if(height[i]<len)
        {
            if(mx-mn>=len)
                ans++;
            mx=mn=sa[i];
        }
        else
        {
            mx=max(mx,sa[i]);
            mn=min(mn,sa[i]);
        }
    }
    if(mx-mn>=len)ans++;
}
void solve()
{
    ans=0;
    for(int i=1;i<=n;i++)
        judge(i);
    printf("%d\n",ans);
}
int main()
{
    while(scanf("%s",str)!=EOF)
   {
       if(str[0]=='#') break;
        n = strlen(str);
        for(int i = 0;i < n;i++)
            s[i] = str[i]-'A'+1;
        s[n] = 0;
        getsa(s,sa,n+1,100);
        getheight(s,n);
        solve();
    }
    return 0;
}