#pragma GCC optimize("Ofast")
#include <bits/stdc++.h>
using namespace std;
typedef long long int ll;
typedef unsigned long long int ull;

int main() {
    cin.tie(nullptr);
    ios::sync_with_stdio(false);
    int q;
    cin >> q;
    while (q--) {
        string s;
        cin >> s;
        if (s.size() == 1) {
            cout << "YES\n";
            cout << s << "\n";
        } else {
            vector<int> cnt(26);
            for (char c : s) {
                cnt[c - 'a'] += 1;
            }
            vector<int> v;
            for (int i = 0; i < 26; ++i) {
                if (cnt[i]) v.push_back(i);
            }
            if (v.size() == 1) {
                cout << "NO\n";
            } else if (v.size() == 2) {
                if (cnt[v[0]] > cnt[v[1]]) swap(v[0], v[1]);
                if (cnt[v[0]] == 1) {
                    cout << "YES\n";
                    cout << (char)(v[0] + 'a');
                    for (int i = 0; i < cnt[v[1]]; ++i) {
                        cout << (char)(v[1] + 'a');
                    }
                    cout << "\n";
                } else {
                    cout << "NO\n";
                }
            } else {
                cout << "YES\n";
                cout << (char)(v[0] + 'a');
                for (int i = 0; i < cnt[v[1]]; ++i) {
                    cout << (char)(v[1] + 'a');
                }
                for (int i = 0; i < cnt[v[2]]; ++i) {
                    cout << (char)(v[2] + 'a');
                }
                for (int i = 1; i < cnt[v[0]]; ++i) {
                    cout << (char)(v[0] + 'a');
                }
                for (int j = 3; j < v.size(); ++j) {
                    for (int i = 0; i < cnt[v[j]]; ++i) {
                        cout << (char)(v[j] + 'a');
                    }
                }
                cout << "\n";
            }
        }
    }
}