【SPOJ】1812. Longest Common Substring II(后缀自动机)
http://www.spoj.com/problems/LCS2/
发现了我原来对sam的理解的一个坑233
本题容易看出就是将所有匹配长度记录在状态上然后取min后再对所有状态取max。
但是不要忘记了一点:更新parent树的祖先。
为什么呢?首先如果子树被匹配过了,那么长度一定大于任意祖先匹配的长度(甚至有些祖先匹配长度为0!为什么呢,因为我们在匹配的过程中,只是找到一个子串,可能还遗漏了祖先没有匹配到,这样导致了祖先的记录值为0,那么在对对应状态取min的时候会取到0,这样就wa了。而且注意,如果匹配到了当前节点,那么祖先们一定都可以赋值为祖先的length!因为当前节点的length大于任意祖先。(
比如数据
acbbc
bc
ac
答案应该是1没错吧。如果没有更新祖先,那么答案会成0。
这个多想想就行了。
所以以后记住:对任意多串匹配时,凡是对同一个状态取值时,要注意当前状态的子树是否比当前状态记录的值优。
#include <cstdio> #include <cstring> #include <cmath> #include <string> #include <iostream> #include <algorithm> #include <queue> #include <set> #include <map> using namespace std; typedef long long ll; #define rep(i, n) for(int i=0; i<(n); ++i) #define for1(i,a,n) for(int i=(a);i<=(n);++i) #define for2(i,a,n) for(int i=(a);i<(n);++i) #define for3(i,a,n) for(int i=(a);i>=(n);--i) #define for4(i,a,n) for(int i=(a);i>(n);--i) #define CC(i,a) memset(i,a,sizeof(i)) #define read(a) a=getint() #define print(a) printf("%d", a) #define dbg(x) cout << (#x) << " = " << (x) << endl #define error(x) (!(x)?puts("error"):0) #define rdm(x, i) for(int i=ihead[x]; i; i=e[i].next) inline const int getint() { int r=0, k=1; char c=getchar(); for(; c<'0'||c>'9'; c=getchar()) if(c=='-') k=-1; for(; c>='0'&&c<='9'; c=getchar()) r=r*10+c-'0'; return k*r; } struct sam { static const int N=250005; int c[N][26], l[N], f[N], root, last, cnt, mx[N], x[N]; sam() { cnt=0; root=last=++cnt; } void add(int x) { int now=last, a=++cnt; last=a; l[a]=l[now]+1; for(; now && !c[now][x]; now=f[now]) c[now][x]=a; if(!now) f[a]=root; else { int q=c[now][x]; if(l[q]==l[now]+1) f[a]=q; else { int b=++cnt; memcpy(c[b], c[q], sizeof c[q]); l[b]=l[now]+1; f[b]=f[q]; f[q]=f[a]=b; for(; now && c[now][x]==q; now=f[now]) c[now][x]=b; } } } void build(char *s) { int len=strlen(s); rep(i, len) add(s[i]-'a'); for1(i, 1, cnt) mx[l[i]]++; for1(i, 1, len) mx[i]+=mx[i-1]; for1(i, 1, cnt) x[mx[l[i]]--]=i; for1(i, 1, cnt) mx[i]=l[i]; } void find(char *s) { int now=root, t=0, len=strlen(s); static int arr[N]; rep(i, len) { int k=s[i]-'a'; if(c[now][k]) ++t, now=c[now][k]; else { while(now && !c[now][k]) now=f[now]; if(!now) t=0, now=root; else t=l[now]+1, now=c[now][k]; } arr[now]=max(arr[now], t); } for3(i, cnt, 1) { t=x[i]; mx[t]=min(mx[t], arr[t]); if(arr[t] && f[t]) arr[f[t]]=l[f[t]]; arr[t]=0; } } int getans() { int ret=0; for1(i, 1, cnt) ret=max(ret, mx[i]); return ret; } }a; const int N=100005; char s[N]; int main() { scanf("%s", s); a.build(s); while(~scanf("%s", s)) a.find(s); print(a.getans()); return 0; }
A string is finite sequence of characters over a non-empty finite set Σ.
In this problem, Σ is the set of lowercase letters.
Substring, also called factor, is a consecutive sequence of characters occurrences at least once in a string.
Now your task is a bit harder, for some given strings, find the length of the longest common substring of them.
Here common substring means a substring of two or more strings.
Input
The input contains at most 10 lines, each line consists of no more than 100000 lowercase letters, representing a string.
Output
The length of the longest common substring. If such string doesn't exist, print "0" instead.
Example
Input: alsdfkjfjkdsal fdjskalajfkdsla aaaajfaaaa Output: 2
Notice: new testcases added