把 $a$ 和 $b$ 都按照从小到大排序,用 $a$ 的后 $x$ 个元素和 $b$ 的前 $x$ 个元素一一匹配,这样可以让 $a_i$ 尽可能比 $b_i$ 大,同时又不会发生「浪费」。接下来让 $a$ 的前 $n - x$ 个元素和 $b$ 的后 $n - x$ 个元素一一匹配,这样可以让 $a_i$ 尽可能比 $b_i$ 小,同时 $b_i$ 也不会发生「浪费」。

// Date: Tue Dec 26 22:59:44 2023

#include <climits>
#include <cmath>
#include <cstdio>
#include <cstdlib>
#include <cstring>

#include <algorithm>
#include <functional>
#include <iomanip>
#include <iostream>
#include <map>
#include <queue>
#include <set>
#include <sstream>
#include <stack>
#include <string>
#include <utility>
#include <vector>

using namespace std;

const int INF = 0x3f3f3f3f, MOD = 1e9 + 7;
const double eps = 1e-8;
const int dir[8][2] = {
    {0, 1}, {0, -1}, {1, 0}, {-1, 0}, {1, 1}, {1, -1}, {-1, 1}, {-1, -1},
};

typedef long long ll;
typedef unsigned long long ull;
typedef vector<int> VI;
typedef pair<int, int> PII;

const ull Pr = 131;

#define For(i, a, b) for (int i = int(a); i < int(b); ++i)
#define Rof(i, a, b) for (int i = int(b) - 1; i >= int(a); --i)
#define For1(i, a, b) for (int i = int(a); i <= int(b); ++i)
#define Rof1(i, a, b) for (int i = int(b); i >= int(a); --i)
#define ForE(i, j) for (int i = h[j]; i != -1; i = ne[i])

#define f1 first
#define f2 second
#define pb push_back
#define has(a, x) (a.find(x) != a.end())
#define nonempty(a) (!a.empty())
#define all(a) (a).begin(), (a).end()
#define SZ(a) int((a).size())

template <typename t> istream &operator>>(istream &in, vector<t> &vec) {
  for (t &x : vec)
    in >> x;
  return in;
}

template <typename t> ostream &operator<<(ostream &out, vector<t> &vec) {
  int n = SZ(vec);
  For(i, 0, n) {
    out << vec[i];
    if (i < n - 1)
      out << ' ';
  }
  return out;
}

#ifdef _DEBUG
#define debug1(x) cout << #x " = " << x << endl;
#define debug2(x, y) cout << #x " = " << x << " " #y " = " << y << endl;
#define debug3(x, y, z)                                                        \
  cout << #x " = " << x << " " #y " = " << y << " " #z " = " << z << endl;
#else
#define debug1
#define debug2
#define debug3
#endif

const int N = 200010;
int t, n, x;
PII a[N], b[N];

int main(void) {
#ifdef _DEBUG
  freopen("1896c.in", "r", stdin);
#endif
  std::ios::sync_with_stdio(false);
  cin.tie(NULL);
  cout.tie(NULL);

  cin >> t;

  while (t--) {
    cin >> n >> x;

    For1(i, 1, n) cin >> a[i].f1, a[i].f2 = i;
    For1(i, 1, n) cin >> b[i].f1;

    sort(a + 1, a + 1 + n);
    sort(b + 1, b + 1 + n);

    bool flag = true;
    For1(i, 1, n) {
      if (i <= x) {
        if (a[n - x + i].f1 <= b[i].f1) {
          flag = false;
          break;
        }
        b[i].f2 = a[n - x + i].f2;
      } else {
        if (a[i - x].f1 > b[i].f1) {
          flag = false;
          break;
        }
        b[i].f2 = a[i - x].f2;
      }
    }

    if (!flag) {
      cout << "NO\n";
    } else {
      cout << "YES\n";
      sort(b + 1, b + 1 + n,
           [](const PII &x, const PII &y) { return x.f2 < y.f2; });
      For1(i, 1, n) { cout << b[i].f1 << ' '; }
      cout << '\n';
    }
  }

  return 0;
}