解题思路:将所有串链接在一起,中间用不同的分隔符分割,求解后缀数组Height,二分求解连续长度>=k的公共子串是否包含了所有情况。
#include < iostream >
using namespace std;
#define MAX_LEN 1000
int wa[MAX_LEN], wb[MAX_LEN], wv[MAX_LEN], wd[MAX_LEN], Height[MAX_LEN], sa[MAX_LEN], rank[MAX_LEN];
int n;
inline bool IsEqual( int * r, int a, int b, int l)
{
return (r[a] == r[b] && r[a + l] == r[b + l]);
}
void da( int * r, int m)
{
int i, j, p, * x = wa, * y = wb, * t;
memset(wd, 0 , sizeof (wd));
for (i = 0 ; i < n; i ++ ) wd[x[i] = r[i]] ++ ; x[n] = y[n] = 0 ;
for (i = 1 ; i < m; i ++ ) wd[i] += wd[i - 1 ];
for (i = n - 1 ; i >= 0 ; i -- ) sa[ -- wd[x[i]]] = i;
for (p = 1 , j = 1 ; p <= n; m = p, j *= 2 )
{
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]];
memset(wd, 0 , sizeof (wd));
for (i = 0 ; i < n; i ++ ) wd[wv[i]] ++ ;
for (i = 1 ; i < m; i ++ ) wd[i] += wd[i - 1 ];
for (i = n - 1 ; i >= 0 ; i -- ) sa[ -- wd[wv[i]]] = y[i];
for (t = x, x = y, y = t, i = 1 , p = 2 ,x[sa[ 0 ]] = 1 ; i < n; i ++ )
x[sa[i]] = IsEqual(y, sa[i - 1 ], sa[i], j) ? p - 1 : p ++ ;
}
}
void CalHeight( int * r)
{
int i, j, k;
for (i = 0 ; i < n; i ++ )rank[sa[i]] = i;
for (i = 0 , Height[ 0 ] = k = 0 ; i < n; Height[rank[i ++ ]] = k)
for (k ? k -- : 0 , j = (rank[i] > 0 ) ? sa[rank[i] - 1 ]: 0 ; rank[i] > 0 && r[i + k] == r[j + k]; k ++ );
}
int main()
{
int m, t, r[ 700 ], i, j, sp, sb, se, mid, s, l, ans, c, w;
char str[ 61 ];
bool visit[ 10 ], isfind;
scanf( " %d " , & w);
while (w -- )
{
scanf( " %d " , & m); sp = 5 ;
for (j = n = 0 ; j < m; j ++ )
{
scanf( " %s " , str);
for (i = 0 ; i < 60 ; i ++ )
{
if (str[i] == ' A ' )r[n ++ ] = 1 ;
else if (str[i] == ' T ' )r[n ++ ] = 2 ;
else if (str[i] == ' G ' )r[n ++ ] = 3 ;
else r[n ++ ] = 4 ;
}
r[n ++ ] = sp ++ ;
}
da(r, sp), CalHeight(r);
for (sb = 3 ,se = 60 ,mid = 31 ,s = 0 ,ans =- 1 ; sb < se;)
{
isfind = false ;
for ( int i = 0 ; (i < n) && ! isfind ; i ++ )
{
if (Height[i] < mid)memset(visit, false , sizeof (visit)), t = 0 ;
if (Height[i] >= mid)
{
if (t == 0 ){
l = sa[i - 1 ] / 61 ;
if ( ! visit[l])visit[l] = true , t ++ ;
}
l = sa[i] / 61 ;
if ( ! visit[l])visit[l] = true , t ++ ;
if (t == m)isfind = true ,ans = i;
}
}
if (isfind && mid == se) break ;
if (isfind)(sb == mid && se > sb) ? (mid = se):(sb = mid);
else se = mid - 1 , mid = (se + sb) / 2 ;
}
if (ans != - 1 )
for ( int i = 0 ; i < mid; i ++ )
{
c = r[sa[ans] + i];
if (c == 1 )printf( " A " );
else if (c == 2 )printf( " T " );
else if (c == 3 )printf( " G " );
else printf( " C " );
}
else printf( " no significant commonalities " );
printf( " \n " );
}
return 0 ;
}