【HDOJ】2459 Maximum repetition substring

后缀数组+RMQ。

/* 2459 */
#include <iostream>
#include <sstream>
#include <string>
#include <map>
#include <queue>
#include <set>
#include <stack>
#include <vector>
#include <deque>
#include <algorithm>
#include <cstdio>
#include <cmath>
#include <ctime>
#include <cstring>
#include <climits>
#include <cctype>
#include <cassert>
#include <functional>
#include <iterator>
#include <iomanip>
using namespace std;
//#pragma comment(linker,"/STACK:102400000,1024000")

#define sti                set<int>
#define stpii            set<pair<int, int> >
#define mpii            map<int,int>
#define vi                vector<int>
#define pii                pair<int,int>
#define vpii            vector<pair<int,int> >
#define rep(i, a, n)     for (int i=a;i<n;++i)
#define per(i, a, n)     for (int i=n-1;i>=a;--i)
#define clr                clear
#define pb                 push_back
#define mp                 make_pair
#define fir                first
#define sec                second
#define all(x)             (x).begin(),(x).end()
#define SZ(x)             ((int)(x).size())
#define lson            l, mid, rt<<1
#define rson            mid+1, r, rt<<1|1

const int INF = 0x3f3f3f3f;
const int maxn = 1e5+5;
char s[maxn];
int a[maxn];
int rrank[maxn], height[maxn], sa[maxn];
int wa[maxn], wb[maxn], wc[maxn], wv[maxn];
int dp[maxn][17];
int mx[maxn], L[maxn];

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

void da(int *r, int *sa, int n, int m) {
    int i, j, *x=wa, *y=wb, *t, p;
    
    for (i=0; i<m; ++i) wc[i] = 0;
    for (i=0; i<n; ++i) wc[x[i]=r[i]]++;
    for (i=1; i<m; ++i) wc[i] += wc[i-1];
    for (i=n-1; i>=0; --i) sa[--wc[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) wc[i] = 0;
        for (i=0; i<n; ++i) wc[x[i]]++;
        for (i=1; i<m; ++i) wc[i] += wc[i-1];
        for (i=n-1; i>=0; --i) sa[--wc[wv[i]]] = y[i];
        for (t=x, x=y, y=t, p=1, i=1, x[sa[0]]=0; i<n; ++i)
            x[sa[i]] = cmp(y, sa[i-1], sa[i], j) ? p-1 : p++;
    }
}

void calheight(int *r, int *sa, int n) {
    int i, j, k = 0;
    
    for (i=1; i<=n; ++i) rrank[sa[i]] = i;
    for (i=0; i<n; height[rrank[i++]]=k)
    for (k?k--:0, j=sa[rrank[i]-1]; r[j+k]==r[i+k]; ++k) ;
}

void init_RMQ(int n) {
    int i, j;
    
    for (i=1; i<=n; ++i)
        dp[i][0] = height[i];
    dp[1][0] = INF;
    for (j=1; (1<<j)<=n; ++j)
        for (i=1; i+(1<<j)-1<=n; ++i)
            dp[i][j] = min(dp[i][j-1], dp[i+(1<<(j-1))][j-1]);
}

int RMQ(int l, int r) {
    if (l > r)
        swap(l, r);
    
    int k = 0;
    ++l;
    while (1<<(k+1) <= r-l+1)
        ++k;
    
    return min(dp[l][k], dp[r-(1<<k)+1][k]);
}

void printSa(int n) {
    for (int i=1; i<=n; ++i)
        printf("%d ", sa[i]);
    putchar('
');
}

void printHeight(int n) {
    for (int i=1; i<=n; ++i)
        printf("%d ", height[i]);
    putchar('
');
}

void solve() {
    int n;
    
    for (int i=0; ; ++i) {
        if (s[i] == '') {
            n = i;
            break;
        }
        a[i] = s[i] - 'a' + 1;
    }
    a[n] = 0;
    
    da(a, sa, n+1, 30);
    calheight(a, sa, n);
    init_RMQ(n);
    
    int n_ = n >> 1, tmp;
    rep(i, 1, n_) {
        mx[i] = 0;
        for (int p=0, q=i; q<n; p=q, q+=i) {
            tmp = RMQ(rrank[p], rrank[q]);
            mx[i] = max(mx[i], tmp/i+1);
            if (tmp%i) {
                tmp = RMQ(rrank[p-(i-tmp%i)], rrank[q-(i-tmp%i)]);
                mx[i] = max(mx[i], tmp/i+1);
            }
        }
    }
    
    int ans = 0;
    rep(i, 1, n_)
        ans = max(ans, mx[i]);
                
    int ln = 0;
    rep(i, 1, n_) {
        if (mx[i] == ans) {
            L[ln++] = i;
        }
    }
    
    int beg = 0, len = 0;
    
    rep(i, 1, n+1) {
        rep(j, 0, ln) {
            int p = sa[i];
            if (p+L[j] >= n)
                continue;
            
            tmp = RMQ(rrank[p], rrank[p+L[j]]);
            if (tmp/L[j]+1 >= ans) {
                beg = p;
                len = L[j] * ans;
                goto _output;
            }
        }
    }
    
    _output:
    s[beg+len] = '';
    puts(s+beg);
}

int main() {
    ios::sync_with_stdio(false);
    #ifndef ONLINE_JUDGE
        freopen("data.in", "r", stdin);
        freopen("data.out", "w", stdout);
    #endif
    
    int t = 0;
    
    while (scanf("%s", s)!=EOF && (s[0]!='#')) {
        printf("Case %d: ", ++t);
        solve();
    }
    
    #ifndef ONLINE_JUDGE
        printf("time = %d.
", (int)clock());
    #endif
    
    return 0;
}

数据生成器。

from random import randint, shuffle
import shutil
import string


def GenDataIn():
    with open("data.in", "w") as fout:
        t = 20
        bound = 10**2
        lc = list(string.lowercase)
        for tt in xrange(t):
            length = randint(100, 500)
            line = ""
            for i in xrange(length):
                idx = randint(0, 25)
                line += lc[idx]
            fout.write("%s
" % line)
        fout.write("#
")
        
                
def MovDataIn():
    desFileName = "F:eclipse_prjworkspacehdojdata.in"
    shutil.copyfile("data.in", desFileName)

    
if __name__ == "__main__":
    GenDataIn()
    MovDataIn()