#include <bits/stdc++.h>
#if __has_include(<atcoder/all>)
#include <atcoder/all>
using namespace atcoder;
#endif
#if __has_include(<boost/multiprecision/cpp_int.hpp>)
#include <boost/multiprecision/cpp_int.hpp>
using cpp_int=boost::multiprecision::cpp_int;
#endif
#if __has_include(<boost/multiprecision/cpp_dec_float.hpp>)
#include <boost/multiprecision/cpp_dec_float.hpp>
template<unsigned size>using cpp_float=boost::multiprecision::number<boost::multiprecision::cpp_dec_float<size>>;
template<unsigned size>using cpp_double=boost::multiprecision::number<boost::multiprecision::cpp_dec_float<size,long long>>;
#endif
using namespace std;
using ll=long long;
inline void yn(bool x){if(x){cout<<"Yes"<<endl;}else{cout<<"No"<<endl;}}
#define double_out(x) fixed << setprecision(x)
template<class T> inline void erase_duplicate(vector<T>& A){sort(A.begin(),A.end());A.erase(unique(A.begin(),A.end()),A.end());}
inline ll powll(ll x,ll n){ll r=1;while(n>0){if(n&1){r*=x;};x*=x;n>>=1;};return r;}


int main(){
    ll N;
    cin>>N;
    vector<ll> A(N);
    for(ll i=0;i<N;i++){
        cin>>A[i];
    }
    sort(A.begin(), A.end());
    for(ll i=0;i<N;i++){
        A[i]%=26;
    }
    for(ll i=0;i<N;i++){
        cout<<char(A[i]+'A');
    }
    cout<<endl;
}