#pragma GCC optimize("O2")
#include <algorithm>
#include <array>
#include <bit>
#include <bitset>
#include <cassert>
#include <cctype>
#include <cfenv>
#include <cfloat>
#include <chrono>
#include <cinttypes>
#include <climits>
#include <cmath>
#include <compare>
#include <complex>
#include <concepts>
#include <cstdarg>
#include <cstddef>
#include <cstdint>
#include <cstdio>
#include <cstdlib>
#include <cstring>
#include <deque>
#include <fstream>
#include <functional>
#include <initializer_list>
#include <iomanip>
#include <ios>
#include <iostream>
#include <istream>
#include <iterator>
#include <limits>
#include <list>
#include <map>
#include <memory>
#include <new>
#include <numbers>
#include <numeric>
#include <ostream>
#include <queue>
#include <random>
#include <ranges>
#include <set>
#include <span>
#include <sstream>
#include <stack>
#include <streambuf>
#include <string>
#include <tuple>
#include <type_traits>
#include <variant>

#define int ll
#define INT128_MAX (__int128)(((unsigned __int128) 1 << ((sizeof(__int128) * __CHAR_BIT__) - 1)) - 1)
#define INT128_MIN (-INT128_MAX - 1)

#define clock chrono::steady_clock::now().time_since_epoch().count()

#ifdef DEBUG
#define dbg(x) cout << (#x) << " = " << x << '\n'
#else
#define dbg(x)
#endif

namespace R = std::ranges;
namespace V = std::views;

using namespace std;

using ll = long long;
using ull = unsigned long long;
using ldb = long double;
using pii = pair<int, int>;
using pll = pair<ll, ll>;
//#define double ldb

template<class T>
ostream& operator<<(ostream& os, const pair<T, T> pr) {
  return os << pr.first << ' ' << pr.second;
}
template<class T, size_t N>
ostream& operator<<(ostream& os, const array<T, N> &arr) {
  for(const T &X : arr)
    os << X << ' ';
  return os;
}
template<class T>
ostream& operator<<(ostream& os, const vector<T> &vec) {
  for(const T &X : vec)
    os << X << ' ';
  return os;
}
template<class T>
ostream& operator<<(ostream& os, const set<T> &s) {
  for(const T &x : s)
    os << x << ' ';
  return os;
}

template<class T>
struct fenwickTree {
  const int size;
  vector<T> data;

  fenwickTree(int _size) : size(_size + 1), data(_size + 1) {}
  fenwickTree(vector<T> &init) : size(ssize(init) + 1), data(ssize(init) + 1) {
    partial_sum(init.begin(), init.end(), data.begin() + 1);
    for(int i = size - 1; i > 0; i--)
      data[i] -= data[i - (i & (-i))];
  }

  void add(int i, T d) {
    for(i += 1; i < size; i += i & (-i))
      data[i] += d;
  }

  T query(int i) {
    T res = T(0);
    for(i += 1; i > 0; i -= i & (-i))
      res += data[i];
    return res;
  }

  T query(int l, int r) {
    return query(r - 1) - query(l - 1);
  }
};

signed main() {
  ios::sync_with_stdio(false), cin.tie(NULL);

  int t; cin >> t;
  while(t--) {
    int n; cin >> n;
    vector<int> p(n);
    for(int &x : p) {
      cin >> x;
      x--;
    }

    deque<int> dq;
    dq.push_front(p[0]);
    fenwickTree<int> ft(n);
    ft.add(p[0], 1);

    int inv = 0;
    for(int i = 1; i < n; i++) {
      int lc = ft.query(p[i]);
      int rc = i - lc;
      inv += min(lc, rc);
      if (lc < rc or (lc == rc and p[i] < dq.front()))
        dq.push_front(p[i]);
      else
        dq.push_back(p[i]);
      ft.add(p[i], 1);
    }

    cout << inv << '\n';
    for(int x : dq)
      cout << x + 1 << ' ';
    cout << '\n';
  }

  return 0;
}