nixir/src/irc/serializer.cpp
NotAShelf 618a58b2b8
initial commit
Signed-off-by: NotAShelf <raf@notashelf.dev>
Change-Id: I1ad48ade1bc8234b7d7c9fe3d976a5be6a6a6964
2026-02-22 00:07:30 +03:00

265 lines
8.7 KiB
C++

#include "serializer.h"
#include <cstring>
#include <sstream>
#include <iostream>
namespace nix_irc {
struct Serializer::Impl {
std::vector<uint8_t> 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<ConstIntNode>()) return NodeType::CONST_INT;
if (node.holds<ConstStringNode>()) return NodeType::CONST_STRING;
if (node.holds<ConstPathNode>()) return NodeType::CONST_PATH;
if (node.holds<ConstBoolNode>()) return NodeType::CONST_BOOL;
if (node.holds<ConstNullNode>()) return NodeType::CONST_NULL;
if (node.holds<VarNode>()) return NodeType::VAR;
if (node.holds<LambdaNode>()) return NodeType::LAMBDA;
if (node.holds<AppNode>()) return NodeType::APP;
if (node.holds<BinaryOpNode>()) return NodeType::BINARY_OP;
if (node.holds<UnaryOpNode>()) return NodeType::UNARY_OP;
if (node.holds<AttrsetNode>()) return NodeType::ATTRSET;
if (node.holds<SelectNode>()) return NodeType::SELECT;
if (node.holds<WithNode>()) return NodeType::WITH;
if (node.holds<IfNode>()) return NodeType::IF;
if (node.holds<LetNode>()) return NodeType::LET;
if (node.holds<LetRecNode>()) return NodeType::LETREC;
if (node.holds<AssertNode>()) 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<uint8_t>(get_node_type(node)));
write_u32(get_node_line(node));
if (auto* n = node.get_if<ConstIntNode>()) {
write_u64(static_cast<uint64_t>(n->value));
} else if (auto* n = node.get_if<ConstStringNode>()) {
write_string(n->value);
} else if (auto* n = node.get_if<ConstPathNode>()) {
write_string(n->value);
} else if (auto* n = node.get_if<ConstBoolNode>()) {
write_u8(n->value ? 1 : 0);
} else if (auto* n = node.get_if<ConstNullNode>()) {
// No data for null
} else if (auto* n = node.get_if<VarNode>()) {
write_u32(n->index);
} else if (auto* n = node.get_if<LambdaNode>()) {
write_u32(n->arity);
if (n->body) write_node(*n->body);
} else if (auto* n = node.get_if<AppNode>()) {
if (n->func) write_node(*n->func);
if (n->arg) write_node(*n->arg);
} else if (auto* n = node.get_if<BinaryOpNode>()) {
write_u8(static_cast<uint8_t>(n->op));
if (n->left) write_node(*n->left);
if (n->right) write_node(*n->right);
} else if (auto* n = node.get_if<UnaryOpNode>()) {
write_u8(static_cast<uint8_t>(n->op));
if (n->operand) write_node(*n->operand);
} else if (auto* n = node.get_if<AttrsetNode>()) {
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<SelectNode>()) {
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<WithNode>()) {
if (n->attrs) write_node(*n->attrs);
if (n->body) write_node(*n->body);
} else if (auto* n = node.get_if<IfNode>()) {
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<LetNode>()) {
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<LetRecNode>()) {
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<AssertNode>()) {
if (n->cond) write_node(*n->cond);
if (n->body) write_node(*n->body);
}
}
};
Serializer::Serializer() : pImpl(std::make_unique<Impl>()) {}
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<const char*>(bytes.data()), bytes.size());
}
std::vector<uint8_t> 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<uint8_t> 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<const char*>(&buffer[pos]), len);
pos += len;
return str;
}
};
Deserializer::Deserializer() : pImpl(std::make_unique<Impl>()) {}
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<char*>(pImpl->buffer.data()), size);
pImpl->pos = 0;
return deserialize(pImpl->buffer);
}
IRModule Deserializer::deserialize(const std::vector<uint8_t>& 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()) {
// TODO: deserialize AST
}
return module;
}
}