// SHA-256. Adapted from LibTomCrypt. This code is Public Domain
#include "hash.h"

#include <blue/core/hash.h>
#include <string.h>

static const uint32_t K[64] = {
	0x428a2f98UL, 0x71374491UL, 0xb5c0fbcfUL, 0xe9b5dba5UL, 0x3956c25bUL,
	0x59f111f1UL, 0x923f82a4UL, 0xab1c5ed5UL, 0xd807aa98UL, 0x12835b01UL,
	0x243185beUL, 0x550c7dc3UL, 0x72be5d74UL, 0x80deb1feUL, 0x9bdc06a7UL,
	0xc19bf174UL, 0xe49b69c1UL, 0xefbe4786UL, 0x0fc19dc6UL, 0x240ca1ccUL,
	0x2de92c6fUL, 0x4a7484aaUL, 0x5cb0a9dcUL, 0x76f988daUL, 0x983e5152UL,
	0xa831c66dUL, 0xb00327c8UL, 0xbf597fc7UL, 0xc6e00bf3UL, 0xd5a79147UL,
	0x06ca6351UL, 0x14292967UL, 0x27b70a85UL, 0x2e1b2138UL, 0x4d2c6dfcUL,
	0x53380d13UL, 0x650a7354UL, 0x766a0abbUL, 0x81c2c92eUL, 0x92722c85UL,
	0xa2bfe8a1UL, 0xa81a664bUL, 0xc24b8b70UL, 0xc76c51a3UL, 0xd192e819UL,
	0xd6990624UL, 0xf40e3585UL, 0x106aa070UL, 0x19a4c116UL, 0x1e376c08UL,
	0x2748774cUL, 0x34b0bcb5UL, 0x391c0cb3UL, 0x4ed8aa4aUL, 0x5b9cca4fUL,
	0x682e6ff3UL, 0x748f82eeUL, 0x78a5636fUL, 0x84c87814UL, 0x8cc70208UL,
	0x90befffaUL, 0xa4506cebUL, 0xbef9a3f7UL, 0xc67178f2UL,
};

static uint32_t min(uint32_t x, uint32_t y)
{
	return x < y ? x : y;
}

static uint32_t load32(const unsigned char *y)
{
	return ((uint32_t)(y[0]) << 24) | ((uint32_t)(y[1]) << 16)
	     | ((uint32_t)(y[2]) << 8) | ((uint32_t)(y[3]) << 0);
}

static void store64(uint64_t x, unsigned char *y)
{
	for (int i = 0; i != 8; ++i)
		y[i] = (x >> ((7 - i) * 8)) & 255;
}

static void store32(uint32_t x, unsigned char *y)
{
	for (int i = 0; i != 4; ++i)
		y[i] = (x >> ((3 - i) * 8)) & 255;
}

static uint32_t Ch(uint32_t x, uint32_t y, uint32_t z)
{
	return z ^ (x & (y ^ z));
}
static uint32_t Maj(uint32_t x, uint32_t y, uint32_t z)
{
	return ((x | y) & z) | (x & y);
}
static uint32_t Rot(uint32_t x, uint32_t n)
{
	return (x >> (n & 31)) | (x << (32 - (n & 31)));
}
static uint32_t Sh(uint32_t x, uint32_t n)
{
	return x >> n;
}
static uint32_t Sigma0(uint32_t x)
{
	return Rot(x, 2) ^ Rot(x, 13) ^ Rot(x, 22);
}
static uint32_t Sigma1(uint32_t x)
{
	return Rot(x, 6) ^ Rot(x, 11) ^ Rot(x, 25);
}
static uint32_t Gamma0(uint32_t x)
{
	return Rot(x, 7) ^ Rot(x, 18) ^ Sh(x, 3);
}
static uint32_t Gamma1(uint32_t x)
{
	return Rot(x, 17) ^ Rot(x, 19) ^ Sh(x, 10);
}

static void RND(
	uint32_t *t0, uint32_t *t1, uint32_t W[], uint32_t a, uint32_t b,
	uint32_t c, uint32_t *d, uint32_t e, uint32_t f, uint32_t g,
	uint32_t *h, uint32_t i)
{
	(*t0) = *h + Sigma1(e) + Ch(e, f, g) + K[i] + W[i];
	(*t1) = Sigma0(a) + Maj(a, b, c);
	(*d) += *t0;
	(*h) = *t0 + *t1;
}

static void sha_compress(struct b_hash_ctx *md, const unsigned char *buf)
{
	uint32_t S[8], W[64], t0, t1, t;

	// Copy state into S
	for (int i = 0; i < 8; i++)
		S[i] = md->ctx_state.sha2_256.state[i];

	// Copy the state into 512-bits into W[0..15]
	for (int i = 0; i < 16; i++)
		W[i] = load32(buf + (4 * i));

	// Fill W[16..63]
	for (int i = 16; i < 64; i++)
		W[i] = Gamma1(W[i - 2]) + W[i - 7] + Gamma0(W[i - 15]) + W[i - 16];

	// Compress

	for (int i = 0; i < 64; ++i) {
		RND(&t0, &t1, W, S[0], S[1], S[2], &S[3], S[4], S[5], S[6],
		    &S[7], i);
		t = S[7];
		S[7] = S[6];
		S[6] = S[5];
		S[5] = S[4];
		S[4] = S[3];
		S[3] = S[2];
		S[2] = S[1];
		S[1] = S[0];
		S[0] = t;
	}

	// Feedback
	for (int i = 0; i < 8; i++)
		md->ctx_state.sha2_256.state[i]
			= md->ctx_state.sha2_256.state[i] + S[i];
}

// Public interface

static void sha_init(struct b_hash_ctx *md)
{
	md->ctx_state.sha2_256.curlen = 0;
	md->ctx_state.sha2_256.length = 0;
	md->ctx_state.sha2_256.state[0] = 0x6A09E667UL;
	md->ctx_state.sha2_256.state[1] = 0xBB67AE85UL;
	md->ctx_state.sha2_256.state[2] = 0x3C6EF372UL;
	md->ctx_state.sha2_256.state[3] = 0xA54FF53AUL;
	md->ctx_state.sha2_256.state[4] = 0x510E527FUL;
	md->ctx_state.sha2_256.state[5] = 0x9B05688CUL;
	md->ctx_state.sha2_256.state[6] = 0x1F83D9ABUL;
	md->ctx_state.sha2_256.state[7] = 0x5BE0CD19UL;
}

void z__b_sha2_256_update(struct b_hash_ctx *md, const void *src, size_t inlen)
{
	const uint32_t block_size = sizeof md->ctx_state.sha2_256.buf;
	const unsigned char *in = (const unsigned char *)(src);

	while (inlen > 0) {
		if (md->ctx_state.sha2_256.curlen == 0 && inlen >= block_size) {
			sha_compress(md, in);
			md->ctx_state.sha2_256.length += block_size * 8;
			in += block_size;
			inlen -= block_size;
		} else {
			uint32_t n = min(
				inlen,
				(block_size - md->ctx_state.sha2_256.curlen));
			memcpy(md->ctx_state.sha2_256.buf
			               + md->ctx_state.sha2_256.curlen,
			       in, n);
			md->ctx_state.sha2_256.curlen += n;
			in += n;
			inlen -= n;

			if (md->ctx_state.sha2_256.curlen == block_size) {
				sha_compress(md, md->ctx_state.sha2_256.buf);
				md->ctx_state.sha2_256.length += 8 * block_size;
				md->ctx_state.sha2_256.curlen = 0;
			}
		}
	}
}
void z__b_sha2_256_finish(struct b_hash_ctx *md, void *out, size_t max)
{
	// Increase the length of the message
	md->ctx_state.sha2_256.length += md->ctx_state.sha2_256.curlen * 8;

	// Append the '1' bit
	md->ctx_state.sha2_256.buf[md->ctx_state.sha2_256.curlen++]
		= (unsigned char)(0x80);

	// If the length is currently above 56 bytes we append zeros then compress.
	// Then we can fall back to padding zeros and length encoding like normal.
	if (md->ctx_state.sha2_256.curlen > 56) {
		while (md->ctx_state.sha2_256.curlen < 64)
			md->ctx_state.sha2_256.buf[md->ctx_state.sha2_256.curlen++]
				= 0;
		sha_compress(md, md->ctx_state.sha2_256.buf);
		md->ctx_state.sha2_256.curlen = 0;
	}

	// Pad upto 56 bytes of zeroes
	while (md->ctx_state.sha2_256.curlen < 56)
		md->ctx_state.sha2_256.buf[md->ctx_state.sha2_256.curlen++] = 0;

	// Store length
	store64(md->ctx_state.sha2_256.length, md->ctx_state.sha2_256.buf + 56);
	sha_compress(md, md->ctx_state.sha2_256.buf);

	unsigned char digest[B_DIGEST_LENGTH_SHA2_256];

	// Copy output
	for (int i = 0; i < 8; i++)
		store32(md->ctx_state.sha2_256.state[i],
		        (unsigned char *)&digest[(4 * i)]);

	memcpy(out, digest, b_min(size_t, sizeof digest, max));
}

struct b_hash_function_ops z__b_sha2_256_ops = {
	.hash_init = sha_init,
	.hash_update = z__b_sha2_256_update,
	.hash_finish = z__b_sha2_256_finish,
};