// tb_sha3_chain.cpp - Verilator C++ testbench for sha3_chain_top
//
// Reads test vectors from +VECTOR_FILE= plusarg.
// Format: one 64-char hex string per line (256-bit d).
//
// Drives d_in, asserts start_i, waits for done_o,
// prints "RESULT: RHO_HEX SIGMA_HEX\n" to stdout.
//
// Clock: 10ns period. Reset: 2 cycles.

#include <iostream>
#include <fstream>
#include <string>
#include <cstdlib>
#include <cstdint>
#include "Vsha3_chain_top.h"
#include "verilated.h"

#define CLK_PERIOD_NS  10.0
#define TIMEOUT_CYCLES 500000

static vluint64_t main_time = 0;

double sc_time_stamp() {
    return main_time;
}

// One full clock cycle (both edges + eval)
static void posedge(Vsha3_chain_top* dut) {
    dut->clk = !dut->clk;
    main_time += (vluint64_t)(CLK_PERIOD_NS / 2.0);
    dut->eval();
    dut->clk = !dut->clk;
    main_time += (vluint64_t)(CLK_PERIOD_NS / 2.0);
    dut->eval();
}

static int hex_char_to_nibble(char c) {
    if (c >= '0' && c <= '9') return c - '0';
    if (c >= 'A' && c <= 'F') return c - 'A' + 10;
    if (c >= 'a' && c <= 'f') return c - 'a' + 10;
    return 0;
}

// Parse 64-char hex string into 8 x 32-bit WData words (256 bits).
// Hex is MSB-first (leftmost = bits [255:252]).
// data[0] = bits[31:0], data[7] = bits[255:224].
static void hex_to_256(const std::string& hex, uint32_t data_words[8]) {
    for (int w = 0; w < 8; w++) data_words[w] = 0;

    int nibble_idx = 0;
    for (int i = (int)hex.length() - 1; i >= 0; i--) {
        char c = hex[i];
        if (c == ' ' || c == '\t') continue;
        int nib = hex_char_to_nibble(c);
        int word_idx = nibble_idx / 8;
        int shift    = (nibble_idx % 8) * 4;
        if (word_idx < 8) {
            data_words[word_idx] |= ((uint32_t)nib << shift);
        }
        nibble_idx++;
    }
}

// Print rho_out and sigma_out as hex (MSB-first), space-separated.
// rho[0]=bits[31:0], rho[7]=bits[255:224]
// sigma[0]=bits[31:0], sigma[7]=bits[255:224]
static void print_256_hex(uint32_t data_words[8]) {
    for (int w = 7; w >= 0; w--) {
        uint32_t val = data_words[w];
        for (int j = 28; j >= 0; j -= 4) {
            printf("%01X", (int)((val >> j) & 0xF));
        }
    }
}

int main(int argc, char** argv) {
    Verilated::commandArgs(argc, argv);

    // Parse +VECTOR_FILE= plusarg
    const char* vector_file = NULL;
    for (int i = 1; i < argc; i++) {
        std::string arg(argv[i]);
        if (arg.rfind("+VECTOR_FILE=", 0) == 0) {
            vector_file = argv[i] + 13;
        }
    }

    if (!vector_file) {
        std::cerr << "ERROR: +VECTOR_FILE= not specified" << std::endl;
        return 1;
    }

    std::ifstream infile(vector_file);
    if (!infile.is_open()) {
        std::cerr << "ERROR: Cannot open vector file: " << vector_file << std::endl;
        return 1;
    }

    // Instantiate DUT
    Vsha3_chain_top* dut = new Vsha3_chain_top;

    // Initialize
    dut->clk     = 0;
    dut->rst_n   = 0;
    for (int w = 0; w < 8; w++) dut->d_in[w] = 0;
    dut->start_i = 0;

    // Reset: 2 full cycles
    for (int i = 0; i < 2; i++) posedge(dut);
    dut->rst_n = 1;

    std::string line;
    vluint64_t cycle = 0;
    int vec_count = 0;

    while (std::getline(infile, line)) {
        if (line.empty() || line[0] == '#') continue;

        std::string d_hex = line;
        // Trim trailing whitespace
        while (!d_hex.empty() && (d_hex.back() == ' ' || d_hex.back() == '\t' || d_hex.back() == '\r'))
            d_hex.pop_back();

        // Parse d
        uint32_t d_words[8];
        hex_to_256(d_hex, d_words);
        for (int w = 0; w < 8; w++) dut->d_in[w] = d_words[w];

        // Assert start_i
        dut->start_i = 1;

        // One cycle with start_i=1
        cycle++;
        posedge(dut);

        // De-assert start_i
        dut->start_i = 0;

        // Wait for done_o
        while (!dut->done_o) {
            posedge(dut);
            cycle++;
            if (cycle > TIMEOUT_CYCLES) {
                std::cerr << "ERROR: Timeout waiting for done_o (vec " << vec_count << ")" << std::endl;
                goto done;
            }
        }

        // Read outputs
        uint32_t rho_words[8], sigma_words[8];
        for (int w = 0; w < 8; w++) {
            rho_words[w]   = dut->rho_out[w];
            sigma_words[w] = dut->sigma_out[w];
        }

        printf("RESULT: ");
        print_256_hex(rho_words);
        printf(" ");
        print_256_hex(sigma_words);
        printf("\n");

        // One cycle with done_o high, then start_i must be low to return to IDLE
        posedge(dut);
        cycle++;
        vec_count++;
    }

done:
    infile.close();
    delete dut;

    if (vec_count == 0) {
        std::cerr << "ERROR: No vectors processed" << std::endl;
        return 1;
    }

    return 0;
}