This is the harder version of the problem. In this version, $1 \le n \le 2\cdot10^5$. You can hack this problem if you locked it. But you can hack the previous problem only if you locked both problems.
The problem is to finish $n$ one-choice-questions. Each of the questions contains $k$ options, and only one of them is correct. The answer to the $i$-th question is $h_{i}$, and if your answer of the question $i$ is $h_{i}$, you earn $1$ point, otherwise, you earn $0$ points for this question. The values $h_1, h_2, \dots, h_n$ are known to you in this problem.
However, you have a mistake in your program. It moves the answer clockwise! Consider all the $n$ answers are written in a circle. Due to the mistake in your program, they are shifted by one cyclically.
Formally, the mistake moves the answer for the question $i$ to the question $i \bmod n + 1$. So it moves the answer for the question $1$ to question $2$, the answer for the question $2$ to the question $3$, …, the answer for the question $n$ to the question $1$.
We call all the $n$ answers together an answer suit. There are $k^n$ possible answer suits in total.
You’re wondering, how many answer suits satisfy the following condition: after moving clockwise by $1$, the total number of points of the new answer suit is strictly larger than the number of points of the old one. You need to find the answer modulo $998\,244\,353$.
For example, if $n = 5$, and your answer suit is $a=[1,2,3,4,5]$, it will submitted as $a’=[5,1,2,3,4]$ because of a mistake. If the correct answer suit is $h=[5,2,2,3,4]$, the answer suit $a$ earns $1$ point and the answer suite $a’$ earns $4$ points. Since $4 > 1$, the answer suit $a=[1,2,3,4,5]$ should be counted.Input
The first line contains two integers $n$, $k$ ($1 \le n \le 2\cdot10^5$, $1 \le k \le 10^9$) — the number of questions and the number of possible answers to each question.
The following line contains $n$ integers $h_1, h_2, \dots, h_n$, ($1 \le h_{i} \le k)$ — answers to the questions.Output
Output one integer: the number of answers suits satisfying the given condition, modulo $998\,244\,353$.Examplesinput
3 3 1 3 1
output
9
input
5 5 1 1 4 2 2
output
1000
input
6 2 1 1 2 2 1 1
output
16
Note
For the first example, valid answer suits are $[2,1,1], [2,1,2], [2,1,3], [3,1,1], [3,1,2], [3,1,3], [3,2,1], [3,2,2], [3,2,3]$.
Solution:
#include <bits/stdc++.h> using namespace std; template <typename T> T inverse(T a, T m) { T u = 0, v = 1; while (a != 0) { T t = m / a; m -= t * a; swap(a, m); u -= t * v; swap(u, v); } assert(m == 1); return u; } template <typename T> class Modular { public: using Type = typename decay<decltype(T::value)>::type; constexpr Modular() : value() {} template <typename U> Modular(const U& x) { value = normalize(x); } template <typename U> static Type normalize(const U& x) { Type v; if (-mod() <= x && x < mod()) v = static_cast<Type>(x); else v = static_cast<Type>(x % mod()); if (v < 0) v += mod(); return v; } const Type& operator()() const { return value; } template <typename U> explicit operator U() const { return static_cast<U>(value); } constexpr static Type mod() { return T::value; } Modular& operator+=(const Modular& other) { if ((value += other.value) >= mod()) value -= mod(); return *this; } Modular& operator-=(const Modular& other) { if ((value -= other.value) < 0) value += mod(); return *this; } template <typename U> Modular& operator+=(const U& other) { return *this += Modular(other); } template <typename U> Modular& operator-=(const U& other) { return *this -= Modular(other); } Modular& operator++() { return *this += 1; } Modular& operator--() { return *this -= 1; } Modular operator++(int) { Modular result(*this); *this += 1; return result; } Modular operator--(int) { Modular result(*this); *this -= 1; return result; } Modular operator-() const { return Modular(-value); } template <typename U = T> typename enable_if<is_same<typename Modular<U>::Type, int>::value, Modular>::type& operator*=(const Modular& rhs) { #ifdef _WIN32 uint64_t x = static_cast<int64_t>(value) * static_cast<int64_t>(rhs.value); uint32_t xh = static_cast<uint32_t>(x >> 32), xl = static_cast<uint32_t>(x), d, m; asm( "divl %4; \n\t" : "=a" (d), "=d" (m) : "d" (xh), "a" (xl), "r" (mod()) ); value = m; #else value = normalize(static_cast<int64_t>(value) * static_cast<int64_t>(rhs.value)); #endif return *this; } template <typename U = T> typename enable_if<is_same<typename Modular<U>::Type, int64_t>::value, Modular>::type& operator*=(const Modular& rhs) { int64_t q = static_cast<int64_t>(static_cast<long double>(value) * rhs.value / mod()); value = normalize(value * rhs.value - q * mod()); return *this; } template <typename U = T> typename enable_if<!is_integral<typename Modular<U>::Type>::value, Modular>::type& operator*=(const Modular& rhs) { value = normalize(value * rhs.value); return *this; } Modular& operator/=(const Modular& other) { return *this *= Modular(inverse(other.value, mod())); } template <typename U> friend const Modular<U>& abs(const Modular<U>& v) { return v; } template <typename U> friend bool operator==(const Modular<U>& lhs, const Modular<U>& rhs); template <typename U> friend bool operator<(const Modular<U>& lhs, const Modular<U>& rhs); template <typename U> friend std::istream& operator>>(std::istream& stream, Modular<U>& number); private: Type value; }; template <typename T> bool operator==(const Modular<T>& lhs, const Modular<T>& rhs) { return lhs.value == rhs.value; } template <typename T, typename U> bool operator==(const Modular<T>& lhs, U rhs) { return lhs == Modular<T>(rhs); } template <typename T, typename U> bool operator==(U lhs, const Modular<T>& rhs) { return Modular<T>(lhs) == rhs; } template <typename T> bool operator!=(const Modular<T>& lhs, const Modular<T>& rhs) { return !(lhs == rhs); } template <typename T, typename U> bool operator!=(const Modular<T>& lhs, U rhs) { return !(lhs == rhs); } template <typename T, typename U> bool operator!=(U lhs, const Modular<T>& rhs) { return !(lhs == rhs); } template <typename T> bool operator<(const Modular<T>& lhs, const Modular<T>& rhs) { return lhs.value < rhs.value; } template <typename T> Modular<T> operator+(const Modular<T>& lhs, const Modular<T>& rhs) { return Modular<T>(lhs) += rhs; } template <typename T, typename U> Modular<T> operator+(const Modular<T>& lhs, U rhs) { return Modular<T>(lhs) += rhs; } template <typename T, typename U> Modular<T> operator+(U lhs, const Modular<T>& rhs) { return Modular<T>(lhs) += rhs; } template <typename T> Modular<T> operator-(const Modular<T>& lhs, const Modular<T>& rhs) { return Modular<T>(lhs) -= rhs; } template <typename T, typename U> Modular<T> operator-(const Modular<T>& lhs, U rhs) { return Modular<T>(lhs) -= rhs; } template <typename T, typename U> Modular<T> operator-(U lhs, const Modular<T>& rhs) { return Modular<T>(lhs) -= rhs; } template <typename T> Modular<T> operator*(const Modular<T>& lhs, const Modular<T>& rhs) { return Modular<T>(lhs) *= rhs; } template <typename T, typename U> Modular<T> operator*(const Modular<T>& lhs, U rhs) { return Modular<T>(lhs) *= rhs; } template <typename T, typename U> Modular<T> operator*(U lhs, const Modular<T>& rhs) { return Modular<T>(lhs) *= rhs; } template <typename T> Modular<T> operator/(const Modular<T>& lhs, const Modular<T>& rhs) { return Modular<T>(lhs) /= rhs; } template <typename T, typename U> Modular<T> operator/(const Modular<T>& lhs, U rhs) { return Modular<T>(lhs) /= rhs; } template <typename T, typename U> Modular<T> operator/(U lhs, const Modular<T>& rhs) { return Modular<T>(lhs) /= rhs; } template<typename T, typename U> Modular<T> power(const Modular<T>& a, const U& b) { assert(b >= 0); Modular<T> x = a, res = 1; U p = b; while (p > 0) { if (p & 1) res *= x; x *= x; p >>= 1; } return res; } template <typename T> bool IsZero(const Modular<T>& number) { return number() == 0; } template <typename T> string to_string(const Modular<T>& number) { return to_string(number()); } template <typename T> std::ostream& operator<<(std::ostream& stream, const Modular<T>& number) { return stream << number(); } template <typename T> std::istream& operator>>(std::istream& stream, Modular<T>& number) { typename common_type<typename Modular<T>::Type, int64_t>::type x; stream >> x; number.value = Modular<T>::normalize(x); return stream; } /* using ModType = int; struct VarMod { static ModType value; }; ModType VarMod::value; ModType& md = VarMod::value; using Mint = Modular<VarMod>; */ constexpr int md = 998244353; using Mint = Modular<std::integral_constant<decay<decltype(md)>::type, md>>; int main() { ios::sync_with_stdio(false); cin.tie(0); int n, k; cin >> n >> k; vector<int> a(n); for (int i = 0; i < n; i++) { cin >> a[i]; } int cnt = 0; for (int i = 0; i < n; i++) { if (a[i] != a[(i + 1) % n]) { ++cnt; } } if (cnt == 0) { cout << 0 << '\n'; return 0; } vector<Mint> fact(n + 1); fact[0] = 1; for (int i = 1; i <= n; i++) { fact[i] = fact[i - 1] * i; } vector<Mint> inv_fact(n + 1); for (int i = 0; i <= n; i++) { inv_fact[i] = 1 / fact[i]; } auto C = [&](int N, int K) { if (K < 0 || K > N) { return Mint(0); } return fact[N] * inv_fact[K] * inv_fact[N - K]; }; Mint ans = 0; for (int s = 1; s <= cnt; s++) { Mint cur = C(cnt, s); if (s % 2 == 1) { cur *= power(Mint(2), s - 1); } else { cur *= (power(Mint(2), s) - C(s, s / 2)) / 2; } cur *= power(Mint(k - 2), cnt - s); ans += cur; } ans *= power(Mint(k), n - cnt); cout << ans << '\n'; return 0; }