#include "serializer.h" #include #include #include namespace nix_irc { struct Serializer::Impl { std::vector buffer; void write_u32(uint32_t val) { buffer.push_back((val >> 0) & 0xFF); buffer.push_back((val >> 8) & 0xFF); buffer.push_back((val >> 16) & 0xFF); buffer.push_back((val >> 24) & 0xFF); } void write_u64(uint64_t val) { for (int i = 0; i < 8; i++) { buffer.push_back((val >> (i * 8)) & 0xFF); } } void write_u8(uint8_t val) { buffer.push_back(val); } void write_string(const std::string& str) { write_u32(str.size()); buffer.insert(buffer.end(), str.begin(), str.end()); } NodeType get_node_type(const Node& node) { if (node.holds()) return NodeType::CONST_INT; if (node.holds()) return NodeType::CONST_STRING; if (node.holds()) return NodeType::CONST_PATH; if (node.holds()) return NodeType::CONST_BOOL; if (node.holds()) return NodeType::CONST_NULL; if (node.holds()) return NodeType::VAR; if (node.holds()) return NodeType::LAMBDA; if (node.holds()) return NodeType::APP; if (node.holds()) return NodeType::BINARY_OP; if (node.holds()) return NodeType::UNARY_OP; if (node.holds()) return NodeType::ATTRSET; if (node.holds()) return NodeType::SELECT; if (node.holds()) return NodeType::HAS_ATTR; if (node.holds()) return NodeType::WITH; if (node.holds()) return NodeType::IF; if (node.holds()) return NodeType::LET; if (node.holds()) return NodeType::LETREC; if (node.holds()) return NodeType::ASSERT; return NodeType::ERROR; } uint32_t get_node_line(const Node& node) { return std::visit([](const auto& n) { return n.line; }, node.data); } void write_node(const Node& node) { write_u8(static_cast(get_node_type(node))); write_u32(get_node_line(node)); if (auto* n = node.get_if()) { write_u64(static_cast(n->value)); } else if (auto* n = node.get_if()) { write_string(n->value); } else if (auto* n = node.get_if()) { write_string(n->value); } else if (auto* n = node.get_if()) { write_u8(n->value ? 1 : 0); } else if (auto* n = node.get_if()) { // No data for null } else if (auto* n = node.get_if()) { write_u32(n->index); } else if (auto* n = node.get_if()) { write_u32(n->arity); if (n->body) write_node(*n->body); } else if (auto* n = node.get_if()) { if (n->func) write_node(*n->func); if (n->arg) write_node(*n->arg); } else if (auto* n = node.get_if()) { write_u8(static_cast(n->op)); if (n->left) write_node(*n->left); if (n->right) write_node(*n->right); } else if (auto* n = node.get_if()) { write_u8(static_cast(n->op)); if (n->operand) write_node(*n->operand); } else if (auto* n = node.get_if()) { write_u8(n->recursive ? 1 : 0); write_u32(n->attrs.size()); for (const auto& [key, val] : n->attrs) { write_string(key); if (val) write_node(*val); } } else if (auto* n = node.get_if()) { if (n->expr) write_node(*n->expr); if (n->attr) write_node(*n->attr); if (n->default_expr && *n->default_expr) { write_u8(1); write_node(**n->default_expr); } else { write_u8(0); } } else if (auto* n = node.get_if()) { if (n->expr) write_node(*n->expr); if (n->attr) write_node(*n->attr); } else if (auto* n = node.get_if()) { if (n->attrs) write_node(*n->attrs); if (n->body) write_node(*n->body); } else if (auto* n = node.get_if()) { if (n->cond) write_node(*n->cond); if (n->then_branch) write_node(*n->then_branch); if (n->else_branch) write_node(*n->else_branch); } else if (auto* n = node.get_if()) { write_u32(n->bindings.size()); for (const auto& [key, val] : n->bindings) { write_string(key); if (val) write_node(*val); } if (n->body) write_node(*n->body); } else if (auto* n = node.get_if()) { write_u32(n->bindings.size()); for (const auto& [key, val] : n->bindings) { write_string(key); if (val) write_node(*val); } if (n->body) write_node(*n->body); } else if (auto* n = node.get_if()) { if (n->cond) write_node(*n->cond); if (n->body) write_node(*n->body); } } }; Serializer::Serializer() : pImpl(std::make_unique()) {} Serializer::~Serializer() = default; void Serializer::serialize(const IRModule& module, const std::string& path) { auto bytes = serialize_to_bytes(module); std::ofstream out(path, std::ios::binary); out.write(reinterpret_cast(bytes.data()), bytes.size()); } std::vector Serializer::serialize_to_bytes(const IRModule& module) { pImpl->buffer.clear(); pImpl->write_u32(IR_MAGIC); pImpl->write_u32(IR_VERSION); pImpl->write_u32(module.sources.size()); for (const auto& src : module.sources) { pImpl->write_string(src.path); pImpl->write_string(src.content); } pImpl->write_u32(module.imports.size()); for (const auto& [from, to] : module.imports) { pImpl->write_string(from); pImpl->write_string(to); } pImpl->write_u32(module.string_table.size()); for (const auto& [str, id] : module.string_table) { pImpl->write_string(str); pImpl->write_u32(id); } if (module.entry && module.entry != nullptr) { pImpl->write_u8(1); pImpl->write_node(*module.entry); } else { pImpl->write_u8(0); } return pImpl->buffer; } struct Deserializer::Impl { std::vector buffer; size_t pos = 0; uint32_t read_u32() { uint32_t val = 0; val |= buffer[pos + 0]; val |= (uint32_t) buffer[pos + 1] << 8; val |= (uint32_t) buffer[pos + 2] << 16; val |= (uint32_t) buffer[pos + 3] << 24; pos += 4; return val; } uint64_t read_u64() { uint64_t val = 0; for (int i = 0; i < 8; i++) { val |= (uint64_t) buffer[pos + i] << (i * 8); } pos += 8; return val; } uint8_t read_u8() { return buffer[pos++]; } std::string read_string() { uint32_t len = read_u32(); std::string str(reinterpret_cast(&buffer[pos]), len); pos += len; return str; } std::shared_ptr read_node() { NodeType type = static_cast(read_u8()); uint32_t line = read_u32(); switch (type) { case NodeType::CONST_INT: { int64_t val = static_cast(read_u64()); return std::make_shared(ConstIntNode(val, line)); } case NodeType::CONST_STRING: { std::string val = read_string(); return std::make_shared(ConstStringNode(val, line)); } case NodeType::CONST_PATH: { std::string val = read_string(); return std::make_shared(ConstPathNode(val, line)); } case NodeType::CONST_BOOL: { bool val = read_u8() != 0; return std::make_shared(ConstBoolNode(val, line)); } case NodeType::CONST_NULL: return std::make_shared(ConstNullNode(line)); case NodeType::VAR: { uint32_t index = read_u32(); return std::make_shared(VarNode(index, "", line)); } case NodeType::LAMBDA: { uint32_t arity = read_u32(); auto body = read_node(); return std::make_shared(LambdaNode(arity, body, line)); } case NodeType::APP: { auto func = read_node(); auto arg = read_node(); return std::make_shared(AppNode(func, arg, line)); } case NodeType::BINARY_OP: { BinaryOp op = static_cast(read_u8()); auto left = read_node(); auto right = read_node(); return std::make_shared(BinaryOpNode(op, left, right, line)); } case NodeType::UNARY_OP: { UnaryOp op = static_cast(read_u8()); auto operand = read_node(); return std::make_shared(UnaryOpNode(op, operand, line)); } case NodeType::ATTRSET: { bool recursive = read_u8() != 0; uint32_t num_attrs = read_u32(); AttrsetNode attrs(recursive, line); for (uint32_t i = 0; i < num_attrs; i++) { std::string key = read_string(); auto val = read_node(); attrs.attrs.push_back({key, val}); } return std::make_shared(std::move(attrs)); } case NodeType::SELECT: { auto expr = read_node(); auto attr = read_node(); uint8_t has_default = read_u8(); std::optional> default_expr; if (has_default) { default_expr = read_node(); } SelectNode select_node(expr, attr, line); select_node.default_expr = default_expr; return std::make_shared(std::move(select_node)); } case NodeType::HAS_ATTR: { auto expr = read_node(); auto attr = read_node(); return std::make_shared(HasAttrNode(expr, attr, line)); } case NodeType::WITH: { auto attrs = read_node(); auto body = read_node(); return std::make_shared(WithNode(attrs, body, line)); } case NodeType::IF: { auto cond = read_node(); auto then_branch = read_node(); auto else_branch = read_node(); return std::make_shared(IfNode(cond, then_branch, else_branch, line)); } case NodeType::LET: { uint32_t num_bindings = read_u32(); std::vector>> bindings; for (uint32_t i = 0; i < num_bindings; i++) { std::string key = read_string(); auto val = read_node(); bindings.push_back({key, val}); } auto body = read_node(); LetNode let(body, line); let.bindings = std::move(bindings); return std::make_shared(std::move(let)); } case NodeType::LETREC: { uint32_t num_bindings = read_u32(); std::vector>> bindings; for (uint32_t i = 0; i < num_bindings; i++) { std::string key = read_string(); auto val = read_node(); bindings.push_back({key, val}); } auto body = read_node(); LetRecNode letrec(body, line); letrec.bindings = std::move(bindings); return std::make_shared(std::move(letrec)); } case NodeType::ASSERT: { auto cond = read_node(); auto body = read_node(); return std::make_shared(AssertNode(cond, body, line)); } default: throw std::runtime_error("Unknown node type in IR"); } } }; Deserializer::Deserializer() : pImpl(std::make_unique()) {} Deserializer::~Deserializer() = default; IRModule Deserializer::deserialize(const std::string& path) { std::ifstream in(path, std::ios::binary | std::ios::ate); size_t size = in.tellg(); in.seekg(0); pImpl->buffer.resize(size); in.read(reinterpret_cast(pImpl->buffer.data()), size); pImpl->pos = 0; return deserialize(pImpl->buffer); } IRModule Deserializer::deserialize(const std::vector& data) { pImpl->buffer = data; pImpl->pos = 0; IRModule module; uint32_t magic = pImpl->read_u32(); if (magic != IR_MAGIC) { throw std::runtime_error("Invalid IR file"); } uint32_t version = pImpl->read_u32(); if (version != IR_VERSION) { throw std::runtime_error("Unsupported IR version"); } uint32_t num_sources = pImpl->read_u32(); for (uint32_t i = 0; i < num_sources; i++) { SourceFile src; src.path = pImpl->read_string(); src.content = pImpl->read_string(); module.sources.push_back(src); } uint32_t num_imports = pImpl->read_u32(); for (uint32_t i = 0; i < num_imports; i++) { module.imports.push_back({pImpl->read_string(), pImpl->read_string()}); } uint32_t num_strings = pImpl->read_u32(); for (uint32_t i = 0; i < num_strings; i++) { std::string str = pImpl->read_string(); uint32_t id = pImpl->read_u32(); module.string_table[str] = id; } if (pImpl->read_u8()) { module.entry = pImpl->read_node(); } return module; } } // namespace nix_irc