Time Limit: 1000MS | Memory Limit: 65536K | |
Total Submissions: 29308 | Accepted: 11749 |
Description
The French author Georges Perec (1936–1982) once wrote a book, La disparition, without the letter'e'. He was a member of the Oulipo group. A quote from the book:
Tout avait Pair normal, mais tout s’affirmait faux. Tout avait Fair normal, d’abord, puis surgissait l’inhumain, l’affolant. Il aurait voulu savoir où s’articulait l’association qui l’unissait au roman : stir son tapis, assaillant à tout instant son imagination, l’intuition d’un tabou, la vision d’un mal obscur, d’un quoi vacant, d’un non-dit : la vision, l’avision d’un oubli commandant tout, où s’abolissait la raison : tout avait l’air normal mais…
Perec would probably have scored high (or rather, low) in the following contest. People are asked to write a perhaps even meaningful text on some subject with as few occurrences of a given “word” as possible. Our task is to provide the jury with a program that counts these occurrences, in order to obtain a ranking of the competitors. These competitors often write very long texts with nonsense meaning; a sequence of 500,000 consecutive'T's is not unusual. And they never use spaces.
So we want to quickly find out how often a word, i.e., a given string, occurs in a text. More formally: given the alphabet {'A','B', 'C', …, 'Z'} and two finite strings over that alphabet, a wordW and a text T, count the number of occurrences of W inT. All the consecutive characters of W must exactly match consecutive characters ofT. Occurrences may overlap.
Input
The first line of the input file contains a single number: the number of test cases to follow. Each test case has the following format:
- One line with the word W, a string over {'A', 'B','C', …, 'Z'}, with 1 ≤ |W| ≤ 10,000 (here |W| denotes the length of the stringW).
- One line with the text T, a string over {'A', 'B','C', …, 'Z'}, with |W| ≤ |T| ≤ 1,000,000.
Output
For every test case in the input file, the output should contain a single number, on a single line: the number of occurrences of the wordW in the text T.
Sample Input
3 BAPC BAPC AZA AZAZAZA VERDI AVERDXIVYERDIAN
Sample Output
1 3 0
Source
/*
*Copyright (c)2015,烟台大学计算机与控制工程学院
*All rights reserved.
*作 者:单昕昕
*完成日期:2015年8月16日
*版 本 号:v1.0
*/
//nextval数组
#include <cstdio>
#include <cstring>
#include <iostream>
using namespace std;
const int maxw=10000+10;
const int maxt=1000000+10;
int match(char w[],char s[],int next [])
{
int cnt=0,p=0,cur=0,slen,wlen;
slen=strlen(s);
wlen=strlen(w);
while(cur<slen)
{
if(s[cur]==w[p])
{
++cur;
++p;
}
else if(p>=0)
{
p=next[p];
}
else
{
++cur;
p=0;
}
if(p==wlen)
{
++cnt;
p=next[p];
}
}
return cnt;
}
int main()
{
int loop;
scanf("%d",&loop);
while(loop--)
{
char w[maxw],t[maxt];
scanf("%s%s",w,t);
int next[maxw],p=0,cur;
next[0]=-1;
next[1]=0;
for(cur=2; cur<=strlen(w); ++cur)
{
while(p>=0&&w[p]!=w[cur-1])
p=next[p];
next[cur]=++p;
}
printf("%d\n",match(w,t,next));
}
return 0;
}
/*
*Copyright (c)2015,烟台大学计算机与控制工程学院
*All rights reserved.
*作 者:单昕昕
*完成日期:2015年8月16日
*版 本 号:v1.0
*/
//nextval数组
#include <cstdio>
#include <cstring>
#include <iostream>
using namespace std;
const int maxw=10000+10;
const int maxt=1000000+10;
int match(char w[],char s[],int next [])
{
int cnt=0,p=0,i=0,slen,wlen;
slen=strlen(s);
wlen=strlen(w);
while(i<slen)
{
if(s[i]==w[p])
{
++i;
++p;
}
else if(p>=0)
{
p=next[p];
}
else
{
++i;
p=0;
}
if(p==wlen)
{
++cnt;
p=next[p];
}
}
return cnt;
}
int main()
{
int loop;
scanf("%d",&loop);
while(loop--)
{
char w[maxw],t[maxt];
scanf("%s%s",w,t);
int nextval[maxw],i,j;
i=0;
nextval[0]=-1;
j=-1;
while(i<strlen(w))
{
if(j==-1||w[i]==w[j])
{
++i;
++j;
if (w[i]!=w[j])
nextval[i]=j;
else
nextval[i]=nextval[j];
}
else
j=nextval[j];
}
printf("%d\n",match(w,t,nextval));
}
return 0;
}
参见→KMP算法的next、next value数组代码实现及POJ3461