hack-assembler/main.cpp

#include <iostream>
#include <bitset>
#include <string>
#include <cctype>
#include <map>
#include <fstream>

#include <nlohmann/json.hpp>

// Comp map
const std::map<std::string, std::string> compMap = {
    {"0",   "0101010"},
    {"1",   "0111111"},
    {"-1",  "0111010"},
    {"D",   "0001100"},
    {"A",   "0110000"},
    {"!D",  "0001101"},
    {"!A",  "0110001"},
    {"-D",  "0001111"},
    {"-A",  "0110011"},
    {"D+1", "0011111"},
    {"A+1", "0110111"},
    {"D-1", "0001110"},
    {"A-1", "0110010"},
    {"D+A", "0000010"},
    {"A+D", "0000010"},
    {"D-A", "0010011"},
    {"A-D", "0000111"},
    {"D&A", "0000000"},
    {"A&D", "0000000"},
    {"D|A", "0010101"},
    {"A|D", "0010101"},
    {"M",   "1110000"},
    {"!M",  "1110001"},
    {"-M",  "1110011"},
    {"M+1", "1110111"},
    {"M-1", "1110010"},
    {"D+M", "1000010"},
    {"D+M", "1000010"},
    {"D-M", "1010011"},
    {"M-D", "1000111"},
    {"D&M", "1000000"},
    {"M&D", "1000000"},
    {"D|M", "1010101"},
    {"M|D", "1010101"}
};

// dest Map
const std::map<std::string, std::string> destMap = {
    {"null", "000"},
    {"M",    "001"},
    {"D",    "010"},
    {"MD",   "011"},
    {"DM",   "011"},
    {"A",    "100"},
    {"AM",   "101"},
    {"MA",   "101"},
    {"AD",   "110"},
    {"DA",   "110"},
    {"ADM",  "111"},
    {"AMD",  "111"},
    {"DAM",  "111"},
    {"DMA",  "111"},
    {"MDA",  "111"},
    {"MAD",  "111"}
};


// jump Map
const std::map<std::string, std::string> jumpMap = {
    {"null", "000"},
    {"JGT",  "001"},
    {"JEQ",  "010"},
    {"JGE",  "011"},
    {"JLT",  "100"},
    {"JNE",  "101"},
    {"JLE",  "110"},
    {"JMP",  "111"}
};

static inline std::string trim(const std::string &s) {
    size_t a = s.find_first_not_of(" \t\n\r");
    if (a == std::string::npos) return "";
    size_t b = s.find_last_not_of(" \t\n\r");
    return s.substr(a, b - a + 1);
}

static inline std::string strip(const std::string &s) {
    std::string result;
    for (char c : s) {
        if (!std::isspace(static_cast<unsigned char>(c))) {
            result += c;
        }
    }
    return result;
}

using symbolsMap = std::map<std::string, int>;
using labelsMap = std::map<std::string, int>;

int find_available_address(const symbolsMap &symbols) {
    int address = 16; // Start from 16 for variables
    while (true) {
        bool found = false;
        for (const auto &pair : symbols) {
            if (pair.second == address) {
                found = true;
                break;
            }
        }
        if (!found) return address;
        ++address;
    }
}

int main() {
    // Load predefined symbols
    std::ifstream file("./symbols.json");
    nlohmann::json symbols_json = nlohmann::json::parse(file);
    symbolsMap symbols_map = {};
    labelsMap labels_map = symbols_json.get<symbolsMap>();

    std::string line;
    int line_number = 0;
    std::vector<std::string> lines;
    while (std::getline(std::cin, line)) { // Store lines for first pass
        line = trim(line);
        if (line.empty()) continue;
        // skip comments
        if (line[0] == '#' || (line.size() > 1 && line[0] == '/' && line[1] == '/')) continue;
        lines.push_back(line);
    }
    auto line_it = lines.begin();
    while (line_it != lines.end()) { // First pass to handle labels
        if ((*line_it)[0] == '(' && line_it->back() == ')') {
            std::string label = line_it->substr(1, line_it->size() - 2);
            labels_map[label] = line_number;
            line_it = lines.erase(line_it); // Remove label lines
        } else {
            ++line_it;
            ++line_number; // Only count non-label lines
        }
    }
    for (const std::string &line : lines) { // Second pass to handle variables
        if (line[0] == '@') {
            if (std::isalpha(line[1]) || line[1] == '_') {
                std::string symbol = line.substr(1);
                if (labels_map.find(symbol) != labels_map.end()) {
                    continue; // Skip labels, they are already handled
                }
                auto it = symbols_map.find(symbol);
                if (it == symbols_map.end()) {
                    int address = find_available_address(symbols_map);
                    symbols_map[symbol] = address;
                }
            }
        }
    }
    for (const std::string &line : lines) { // Second pass to generate
        // A-instruction
        if (line[0] == '@') {
            // Check if it's a symbol or a number
            if (std::isalpha(line[1]) || line[1] == '_') {
                std::string symbol = line.substr(1);
                int address;
                // search labels first
                auto labelIt = labels_map.find(symbol);
                if (labelIt != labels_map.end()) {
                    address = labelIt->second;
                } else {
                  // Search variables.
                  auto it = symbols_map.find(symbol);
                  if (it != symbols_map.end()) {
                      address = it->second;
                  }
                }
                std::bitset<16> binaryValue(address);
                std::cout << binaryValue.to_string() << '\n';
            } else {
              std::string value = line.substr(1);
              if (value.empty()) continue;
              try {
                  int intValue = std::stoi(value);
                  std::bitset<16> binaryValue(intValue);
                  std::cout << binaryValue.to_string() << '\n';
              } catch (...) { continue; }
            }
        } else { // C-instruction
            std::string instruction = "111";
            size_t eqPos = line.find('=');
            size_t scPos = line.find(';');
            // comp
            std::string comp;
            if (eqPos != std::string::npos) {
                comp = line.substr(eqPos + 1, scPos - eqPos - 1);
            } else if (scPos != std::string::npos) {
                comp = line.substr(0, scPos);
            } else {
                comp = line;
            }
            comp = strip(comp);
            auto compIt = compMap.find(comp);
            if (compIt == compMap.end()) continue;
            instruction += compIt->second;
            // dest use use destMap "null" key if not found
            std::string dest = (eqPos != std::string::npos) ? line.substr(0, eqPos) : "null";
            dest = strip(dest);
            auto destIt = destMap.find(dest);
            instruction += (destIt != destMap.end()) ? destIt->second : destMap.at("null");
            // jump
            std::string jump = (scPos != std::string::npos) ? line.substr(scPos + 1) : "null";
            jump = strip(jump);
            auto jumpIt = jumpMap.find(jump);
            instruction += (jumpIt != jumpMap.end()) ? jumpIt->second : jumpMap.at("null");
            std::cout << instruction << '\n';
            line_number++;
        }
    }
    return 0;
}