Compare commits
32 Commits
149d0fb709
...
main
Author | SHA1 | Date | |
---|---|---|---|
|
132dc65240 | ||
|
bbac513aa9 | ||
|
de465b6122 | ||
|
c091f7f021 | ||
|
ca74b67bb0 | ||
|
4da5313db5 | ||
|
896b9001c7 | ||
|
6181fc8d9f | ||
|
d328ae60df | ||
|
3547822d3e | ||
|
e773cb649f | ||
|
69bee723a2 | ||
|
aee7a741b1 | ||
|
7973f7522c | ||
|
5cc7147909 | ||
|
dec93f8272 | ||
|
69217fdf90 | ||
|
c322b69590 | ||
|
ffff13b2e0 | ||
|
ca05c3577a | ||
|
1c928616a4 | ||
|
ccfc3ed0f7 | ||
|
2aff81ba4c | ||
|
9ad9a0b85b | ||
|
09a0dc7b6d | ||
|
65792464bb | ||
|
4771aa4f10 | ||
|
81cdd0690d | ||
|
4364afa111 | ||
|
9a13de97e1 | ||
|
8acce0f6a6 | ||
|
b966b6dfab |
128
Makefile
128
Makefile
@@ -1,70 +1,78 @@
|
||||
# ────────────────────────────────────
|
||||
# Compiler and flags
|
||||
CXX := g++
|
||||
CXXFLAGS := -Wall -WError -I./include
|
||||
|
||||
# ────────────────────────────────────
|
||||
# Paths
|
||||
# -------------------------------------------------------------------
|
||||
# Project‐wide settings
|
||||
# -------------------------------------------------------------------
|
||||
CXX := g++
|
||||
CXXFLAGS := -std=c++17 -Wall -Wextra -Iinclude -Isrc -MMD -MP
|
||||
LDFLAGS :=
|
||||
SRC_DIR := src
|
||||
TEST_SRC := test/test.cpp
|
||||
REPL_SRC := $(SRC_DIR)/main.cpp
|
||||
TEST_DIR := test
|
||||
BUILD_DIR := build
|
||||
OBJ_DIR := $(BUILD_DIR)/objs
|
||||
BIN_DIR := $(BUILD_DIR)/bin
|
||||
|
||||
OBJ_DIR := build/obj
|
||||
BIN_DIR := build/bin
|
||||
# -------------------------------------------------------------------
|
||||
# Source & object lists
|
||||
# -------------------------------------------------------------------
|
||||
SRC_CPP := $(shell find $(SRC_DIR) -name '*.cpp')
|
||||
TEST_CPP := $(shell find $(TEST_DIR) -name '*.cpp')
|
||||
OBJ := $(patsubst $(SRC_DIR)/%.cpp,$(OBJ_DIR)/%.o,$(SRC_CPP))
|
||||
TEST_OBJ := $(patsubst $(TEST_DIR)/%.cpp,$(OBJ_DIR)/test/%.o,$(TEST_CPP))
|
||||
DEPFILES := $(OBJ:.o=.d) $(TEST_OBJ:.o=.d)
|
||||
|
||||
# ────────────────────────────────────
|
||||
# Source listings
|
||||
# All .cpp under src/, but exclude your REPL main
|
||||
LIB_SRCS := $(filter-out $(REPL_SRC),$(shell find $(SRC_DIR) -name '*.cpp'))
|
||||
|
||||
# Mirror src/.../*.cpp → build/obj/src/.../*.o
|
||||
LIB_OBJS := $(patsubst $(SRC_DIR)/%.cpp,$(OBJ_DIR)/$(SRC_DIR)/%.o,$(LIB_SRCS))
|
||||
# Identify your “real” main.cpp so we can exclude it from tests
|
||||
MAIN_SRC := $(SRC_DIR)/main.cpp
|
||||
MAIN_OBJ := $(MAIN_SRC:$(SRC_DIR)/%.cpp=$(OBJ_DIR)/%.o)
|
||||
SRC_OBJS_NO_MAIN := $(filter-out $(MAIN_OBJ),$(OBJ))
|
||||
|
||||
# Binaries
|
||||
TEST_BIN := $(BIN_DIR)/tests
|
||||
REPL_BIN := $(BIN_DIR)/repl
|
||||
TARGET := $(BIN_DIR)/monkey
|
||||
TEST_TARGET := $(BIN_DIR)/monkey_tests
|
||||
|
||||
# ────────────────────────────────────
|
||||
# Default target: build & run tests
|
||||
all: test
|
||||
# -------------------------------------------------------------------
|
||||
# Top‐level rules
|
||||
# -------------------------------------------------------------------
|
||||
.PHONY: all clean run tests valgrind
|
||||
all: $(TARGET) $(TEST_TARGET)
|
||||
|
||||
# ─ Link test runner (test.cpp defines main via DOCTEST_CONFIG_IMPLEMENT_WITH_MAIN)
|
||||
$(TEST_BIN): $(LIB_OBJS) | $(BIN_DIR)
|
||||
@echo "⏳ Linking tests..."
|
||||
$(CXX) $(CXXFLAGS) $(TEST_SRC) $(LIB_OBJS) -o $@
|
||||
valgrind: CXXFLAGS += -O0 -g
|
||||
valgrind: $(TEST_TARGET)
|
||||
valgrind -s --leak-check=full --show-leak-kinds=all --track-origins=yes $(TEST_TARGET)
|
||||
|
||||
# ─ Link REPL
|
||||
$(REPL_BIN): $(LIB_OBJS) | $(BIN_DIR)
|
||||
@echo "🚀 Linking REPL..."
|
||||
$(CXX) $(CXXFLAGS) $(REPL_SRC) $(LIB_OBJS) -o $@
|
||||
|
||||
# ─ Compile each library .cpp → mirrored .o
|
||||
$(OBJ_DIR)/$(SRC_DIR)/%.o: $(SRC_DIR)/%.cpp
|
||||
@echo "🛠 Compiling $<"
|
||||
@mkdir -p $(dir $@)
|
||||
$(CXX) $(CXXFLAGS) -c $< -o $@
|
||||
|
||||
# ────────────────────────────────────
|
||||
# Run or launch targets
|
||||
.PHONY: test repl clean all
|
||||
|
||||
test: $(TEST_BIN)
|
||||
@echo "\n✅ Running tests..."
|
||||
@$(TEST_BIN)
|
||||
# @$(TEST_BIN) $(if $(TESTCASE),--test-case=$(TESTCASE))
|
||||
|
||||
repl: $(REPL_BIN)
|
||||
@echo "\n🔧 Starting REPL..."
|
||||
@$(REPL_BIN)
|
||||
|
||||
# ────────────────────────────────────
|
||||
# Ensure bin/ exists before linking
|
||||
$(BIN_DIR):
|
||||
@mkdir -p $@
|
||||
|
||||
# ────────────────────────────────────
|
||||
# Clean up everything
|
||||
clean:
|
||||
@echo "🧹 Cleaning build artifacts"
|
||||
@rm -rf $(OBJ_DIR) $(BIN_DIR)
|
||||
@rm -rf $(BUILD_DIR)
|
||||
|
||||
# -------------------------------------------------------------------
|
||||
# Build & run
|
||||
# -------------------------------------------------------------------
|
||||
run: $(TARGET)
|
||||
@$(TARGET)
|
||||
|
||||
test: $(TEST_TARGET)
|
||||
@$(TEST_TARGET) $(if $(TEST),--test-case=$(TEST))
|
||||
|
||||
# -------------------------------------------------------------------
|
||||
# Link binaries
|
||||
# -------------------------------------------------------------------
|
||||
$(TARGET): $(OBJ)
|
||||
@mkdir -p $(BIN_DIR)
|
||||
$(CXX) $(LDFLAGS) $^ -o $@
|
||||
|
||||
$(TEST_TARGET): $(SRC_OBJS_NO_MAIN) $(TEST_OBJ)
|
||||
@mkdir -p $(BIN_DIR)
|
||||
$(CXX) $(LDFLAGS) $^ -o $@
|
||||
|
||||
# -------------------------------------------------------------------
|
||||
# Compile rules
|
||||
# -------------------------------------------------------------------
|
||||
$(OBJ_DIR)/%.o: $(SRC_DIR)/%.cpp
|
||||
@mkdir -p $(@D)
|
||||
$(CXX) $(CXXFLAGS) -c $< -o $@
|
||||
|
||||
$(OBJ_DIR)/test/%.o: $(TEST_DIR)/%.cpp
|
||||
@mkdir -p $(@D)
|
||||
$(CXX) $(CXXFLAGS) -c $< -o $@
|
||||
|
||||
# -------------------------------------------------------------------
|
||||
# Auto‐include dependencies
|
||||
# -------------------------------------------------------------------
|
||||
-include $(DEPFILES)
|
||||
|
2
compile_flags.txt
Normal file
2
compile_flags.txt
Normal file
@@ -0,0 +1,2 @@
|
||||
-I./include
|
||||
-I./src
|
9
src/ast/ast.cpp
Normal file
9
src/ast/ast.cpp
Normal file
@@ -0,0 +1,9 @@
|
||||
#include "ast.hpp"
|
||||
|
||||
namespace ast {
|
||||
std::string program ::token_literal() const {
|
||||
if (statements.size() > 0)
|
||||
return statements[0]->token_literal();
|
||||
return "";
|
||||
}
|
||||
} // namespace ast
|
29
src/ast/ast.hpp
Normal file
29
src/ast/ast.hpp
Normal file
@@ -0,0 +1,29 @@
|
||||
#pragma once
|
||||
|
||||
#include <string>
|
||||
#include <vector>
|
||||
|
||||
namespace ast {
|
||||
struct node {
|
||||
virtual std::string token_literal() const = 0;
|
||||
virtual ~node() = default;
|
||||
};
|
||||
|
||||
struct statement : node {
|
||||
virtual std::string token_literal() const override = 0;
|
||||
};
|
||||
|
||||
struct expression : node {
|
||||
virtual std::string token_literal() const override = 0;
|
||||
};
|
||||
|
||||
struct program : public node {
|
||||
std::vector<statement*> statements;
|
||||
std::string token_literal() const override;
|
||||
|
||||
~program() {
|
||||
for (const auto& ref : statements)
|
||||
delete ref;
|
||||
};
|
||||
};
|
||||
} // namespace ast
|
25
src/ast/errors/error.hpp
Normal file
25
src/ast/errors/error.hpp
Normal file
@@ -0,0 +1,25 @@
|
||||
#pragma once
|
||||
|
||||
#include "token/type.hpp"
|
||||
|
||||
namespace ast::error {
|
||||
struct error : public std::runtime_error {
|
||||
explicit error(const std::string& message)
|
||||
: std::runtime_error(message) {}
|
||||
};
|
||||
|
||||
struct parser_error : error {
|
||||
explicit parser_error(const std::string& message): error(message) {}
|
||||
};
|
||||
|
||||
struct expected_next : parser_error {
|
||||
token::type expected_type;
|
||||
|
||||
explicit expected_next(
|
||||
token::type expected_type, const std::string& message
|
||||
)
|
||||
: parser_error(message),
|
||||
expected_type(expected_type) {}
|
||||
};
|
||||
|
||||
} // namespace ast::error
|
11
src/ast/expressions/identifier.cpp
Normal file
11
src/ast/expressions/identifier.cpp
Normal file
@@ -0,0 +1,11 @@
|
||||
#include "identifier.hpp"
|
||||
|
||||
namespace ast {
|
||||
identifier::identifier(token::token token, std::string value)
|
||||
: token(std::move(token)),
|
||||
value(std::move(value)) {}
|
||||
|
||||
std::string identifier::token_literal() const {
|
||||
return token.literal;
|
||||
}
|
||||
} // namespace ast
|
16
src/ast/expressions/identifier.hpp
Normal file
16
src/ast/expressions/identifier.hpp
Normal file
@@ -0,0 +1,16 @@
|
||||
#pragma once
|
||||
|
||||
#include "ast/ast.hpp"
|
||||
#include "token/token.hpp"
|
||||
|
||||
#include <string>
|
||||
|
||||
namespace ast {
|
||||
struct identifier : expression {
|
||||
identifier(token::token token, std::string value);
|
||||
token::token token;
|
||||
std::string value;
|
||||
|
||||
std::string token_literal() const override;
|
||||
};
|
||||
} // namespace ast
|
17
src/ast/statements/let.cpp
Normal file
17
src/ast/statements/let.cpp
Normal file
@@ -0,0 +1,17 @@
|
||||
#include "let.hpp"
|
||||
|
||||
namespace ast {
|
||||
let::let(token::token token)
|
||||
: token(std::move(token)),
|
||||
name(nullptr),
|
||||
value(nullptr) {}
|
||||
|
||||
std::string let::token_literal() const {
|
||||
return token.literal;
|
||||
}
|
||||
|
||||
let::~let() {
|
||||
delete name;
|
||||
delete value;
|
||||
};
|
||||
} // namespace ast
|
19
src/ast/statements/let.hpp
Normal file
19
src/ast/statements/let.hpp
Normal file
@@ -0,0 +1,19 @@
|
||||
#pragma once
|
||||
|
||||
#include "ast/ast.hpp"
|
||||
#include "ast/expressions/identifier.hpp"
|
||||
#include "token/token.hpp"
|
||||
|
||||
namespace ast {
|
||||
struct let : statement {
|
||||
let(token::token token);
|
||||
|
||||
token::token token;
|
||||
identifier* name;
|
||||
expression* value;
|
||||
|
||||
std::string token_literal() const override;
|
||||
|
||||
~let();
|
||||
};
|
||||
} // namespace ast
|
83
src/lexer/lexer.cpp
Normal file
83
src/lexer/lexer.cpp
Normal file
@@ -0,0 +1,83 @@
|
||||
#include "lexer.hpp"
|
||||
|
||||
#include "token/token.hpp"
|
||||
#include "token/type.hpp"
|
||||
|
||||
#include <cctype>
|
||||
#include <iostream>
|
||||
|
||||
namespace lexer {
|
||||
token::token lexer::next_token() {
|
||||
if (!(input >> c))
|
||||
return {token::type::END_OF_FILE, ""};
|
||||
|
||||
switch (c) {
|
||||
case '=':
|
||||
if (input.peek() == '=')
|
||||
return {token::type::EQ, std::string{c, (char) input.get()}};
|
||||
return {token::type::ASSIGN, c};
|
||||
case '+':
|
||||
return {token::type::PLUS, c};
|
||||
case '-':
|
||||
return {token::type::MINUS, c};
|
||||
case '!':
|
||||
if (input.peek() == '=')
|
||||
return {token::type::NEQ, std::string{c, (char) input.get()}};
|
||||
return {token::type::BANG, c};
|
||||
case '*':
|
||||
return {token::type::ASTERISK, c};
|
||||
case '/':
|
||||
return {token::type::SLASH, c};
|
||||
case '<':
|
||||
return {token::type::LT, c};
|
||||
case '>':
|
||||
return {token::type::GT, c};
|
||||
case ',':
|
||||
return {token::type::COMMA, c};
|
||||
case ';':
|
||||
return {token::type::SEMICOLON, c};
|
||||
case '(':
|
||||
return {token::type::LPAREN, c};
|
||||
case ')':
|
||||
return {token::type::RPAREN, c};
|
||||
case '{':
|
||||
return {token::type::LBRACE, c};
|
||||
case '}':
|
||||
return {token::type::RBRACE, c};
|
||||
default:
|
||||
if (is_letter(c)) {
|
||||
std::string identifier_or_keyword = read_string();
|
||||
return {
|
||||
token::lookup_identifier(identifier_or_keyword),
|
||||
identifier_or_keyword
|
||||
};
|
||||
}
|
||||
if (std::isdigit(c))
|
||||
return {token::type::INT, read_int()};
|
||||
|
||||
return {token::type::ILLEGAL, c};
|
||||
}
|
||||
}
|
||||
|
||||
bool lexer::is_letter(char c) {
|
||||
return c == '_' || std::isalpha(static_cast<unsigned char>(c));
|
||||
}
|
||||
|
||||
std::string lexer::read_string() {
|
||||
std::string result;
|
||||
result.push_back(c);
|
||||
for (char c = input.peek(); is_letter(c); c = input.peek())
|
||||
result.push_back(input.get());
|
||||
return result;
|
||||
}
|
||||
|
||||
std::string lexer::read_int() {
|
||||
std::string result;
|
||||
result.push_back(c);
|
||||
for (char c = input.peek(); std::isdigit(c); c = input.peek())
|
||||
result.push_back(input.get());
|
||||
return result;
|
||||
}
|
||||
|
||||
|
||||
} // namespace lexer
|
18
src/lexer/lexer.hpp
Normal file
18
src/lexer/lexer.hpp
Normal file
@@ -0,0 +1,18 @@
|
||||
#pragma once
|
||||
#include "token/token.hpp"
|
||||
|
||||
#include <istream>
|
||||
|
||||
namespace lexer {
|
||||
struct lexer {
|
||||
std::istream& input;
|
||||
char c = 0;
|
||||
token::token next_token();
|
||||
|
||||
private:
|
||||
bool is_letter(char);
|
||||
|
||||
std::string read_string();
|
||||
std::string read_int();
|
||||
};
|
||||
} // namespace lexer
|
8
src/main.cpp
Normal file
8
src/main.cpp
Normal file
@@ -0,0 +1,8 @@
|
||||
#include "repl/repl.hpp"
|
||||
|
||||
#include <iostream>
|
||||
|
||||
int main() {
|
||||
repl::start(std::cin, std::cout);
|
||||
return 0;
|
||||
}
|
84
src/parser/parser.cpp
Normal file
84
src/parser/parser.cpp
Normal file
@@ -0,0 +1,84 @@
|
||||
#include "parser.hpp"
|
||||
|
||||
#include "ast/errors/error.hpp"
|
||||
#include "token/type.hpp"
|
||||
|
||||
#include <sstream>
|
||||
|
||||
namespace parser {
|
||||
parser::parser(lexer::lexer& lexer)
|
||||
: lexer(lexer),
|
||||
current(token::type::ILLEGAL, ""),
|
||||
next(token::type::ILLEGAL, "") {
|
||||
next_token();
|
||||
next_token();
|
||||
}
|
||||
|
||||
void parser::next_token() {
|
||||
current = next;
|
||||
next = lexer.next_token();
|
||||
}
|
||||
|
||||
ast::program* parser::parse_program() {
|
||||
ast::program* p = new ast::program();
|
||||
|
||||
for (; current.type != token::type::END_OF_FILE; next_token()) {
|
||||
ast::statement* stmt = parse_statement();
|
||||
if (stmt != nullptr)
|
||||
p->statements.push_back(stmt);
|
||||
}
|
||||
|
||||
return p;
|
||||
}
|
||||
|
||||
ast::statement* parser::parse_statement() {
|
||||
switch (current.type) {
|
||||
case token::type::LET:
|
||||
return parse_let();
|
||||
default:
|
||||
return nullptr;
|
||||
}
|
||||
}
|
||||
|
||||
bool parser::expect_next(token::type t) {
|
||||
if (next.type == t) {
|
||||
next_token();
|
||||
return true;
|
||||
}
|
||||
next_error(t);
|
||||
return false;
|
||||
}
|
||||
|
||||
ast::let* parser::parse_let() {
|
||||
ast::let* stmt = new ast::let(current);
|
||||
|
||||
if (!expect_next(token::type::IDENTIFIER)) {
|
||||
delete stmt;
|
||||
return nullptr;
|
||||
}
|
||||
|
||||
stmt->name = new ast::identifier{current, current.literal};
|
||||
|
||||
if (!expect_next(token::type::ASSIGN)) {
|
||||
delete stmt;
|
||||
return nullptr;
|
||||
}
|
||||
|
||||
// TODO: we are currently skipping expressions until we encounter a
|
||||
// semicolon
|
||||
for (; current.type != token::type::SEMICOLON; next_token()) {}
|
||||
return stmt;
|
||||
}
|
||||
|
||||
void parser::next_error(token::type t) {
|
||||
std::stringstream ss;
|
||||
ss << "Expected next token to be " << t << " but instead got "
|
||||
<< next.type;
|
||||
errors.push_back(new ast::error::expected_next(t, ss.str()));
|
||||
}
|
||||
|
||||
parser::~parser() {
|
||||
for (const auto& e : errors)
|
||||
delete e;
|
||||
}
|
||||
} // namespace parser
|
27
src/parser/parser.hpp
Normal file
27
src/parser/parser.hpp
Normal file
@@ -0,0 +1,27 @@
|
||||
#pragma once
|
||||
|
||||
#include "ast/ast.hpp"
|
||||
#include "ast/errors/error.hpp"
|
||||
#include "ast/statements/let.hpp"
|
||||
#include "lexer/lexer.hpp"
|
||||
#include "token/token.hpp"
|
||||
|
||||
namespace parser {
|
||||
struct parser {
|
||||
parser(lexer::lexer& lexer);
|
||||
~parser();
|
||||
std::vector<ast::error::error*> errors;
|
||||
|
||||
ast::program* parse_program();
|
||||
|
||||
private:
|
||||
lexer::lexer& lexer;
|
||||
token::token current, next;
|
||||
|
||||
void next_token();
|
||||
ast::statement* parse_statement();
|
||||
ast::let* parse_let();
|
||||
bool expect_next(token::type);
|
||||
void next_error(token::type);
|
||||
};
|
||||
} // namespace parser
|
30
src/repl/repl.cpp
Normal file
30
src/repl/repl.cpp
Normal file
@@ -0,0 +1,30 @@
|
||||
#include "repl.hpp"
|
||||
|
||||
#include "lexer/lexer.hpp"
|
||||
|
||||
#include <sstream>
|
||||
#include <string>
|
||||
|
||||
static const std::string PROMPT = ">> ";
|
||||
|
||||
namespace repl {
|
||||
|
||||
void start(std::istream& in, std::ostream& out) {
|
||||
while (true) {
|
||||
out << PROMPT;
|
||||
std::string line;
|
||||
if (!std::getline(in, line))
|
||||
return;
|
||||
|
||||
std::istringstream ss(line);
|
||||
|
||||
lexer::lexer l{ss};
|
||||
for (token::token tok = l.next_token();
|
||||
tok.type != token::type::END_OF_FILE;
|
||||
tok = l.next_token())
|
||||
out << tok << " ";
|
||||
out << std::endl;
|
||||
}
|
||||
}
|
||||
|
||||
} // namespace repl
|
8
src/repl/repl.hpp
Normal file
8
src/repl/repl.hpp
Normal file
@@ -0,0 +1,8 @@
|
||||
#pragma once
|
||||
|
||||
#include <istream>
|
||||
#include <ostream>
|
||||
|
||||
namespace repl {
|
||||
void start(std::istream&, std::ostream&);
|
||||
}
|
20
src/token/token.hpp
Normal file
20
src/token/token.hpp
Normal file
@@ -0,0 +1,20 @@
|
||||
#pragma once
|
||||
|
||||
#include "type.hpp"
|
||||
|
||||
#include <string>
|
||||
|
||||
namespace token {
|
||||
struct token {
|
||||
::token::type type;
|
||||
std::string literal;
|
||||
|
||||
token(::token::type t, std::string s): type(t), literal(s) {}
|
||||
|
||||
token(::token::type t, char c): type(t), literal(1, c) {}
|
||||
};
|
||||
|
||||
inline std::ostream& operator<<(std::ostream& os, token tok) {
|
||||
return os << tok.type << '(' << tok.literal << ')';
|
||||
}
|
||||
} // namespace token
|
43
src/token/type.cpp
Normal file
43
src/token/type.cpp
Normal file
@@ -0,0 +1,43 @@
|
||||
#include "type.hpp"
|
||||
|
||||
#include <array>
|
||||
#include <unordered_map>
|
||||
|
||||
namespace token {
|
||||
|
||||
// Array mapping enum values to their string representations
|
||||
constexpr std::
|
||||
array<std::string_view, static_cast<size_t>(type::RETURN) + 1>
|
||||
tokenTypeStrings = {
|
||||
#define X(name, str) str,
|
||||
TOKEN_LIST
|
||||
#undef X
|
||||
};
|
||||
|
||||
// Stream insertion operator using the lookup array
|
||||
std::ostream& operator<<(std::ostream& os, type type) {
|
||||
auto idx = static_cast<size_t>(type);
|
||||
if (idx < tokenTypeStrings.size())
|
||||
return os << tokenTypeStrings[idx];
|
||||
return os << "Unknown";
|
||||
}
|
||||
|
||||
static std::unordered_map<std::string, type> keywords{
|
||||
{"fn", type::FUNCTION},
|
||||
{"let", type::LET},
|
||||
{"if", type::IF},
|
||||
{"else", type::ELSE},
|
||||
{"true", type::TRUE},
|
||||
{"false", type::FALSE},
|
||||
{"return", type::RETURN},
|
||||
};
|
||||
|
||||
type lookup_identifier(std::string ident) {
|
||||
try {
|
||||
return keywords.at(ident);
|
||||
} catch (const std::out_of_range&) {
|
||||
return type::IDENTIFIER;
|
||||
}
|
||||
}
|
||||
|
||||
} // namespace token
|
46
src/token/type.hpp
Normal file
46
src/token/type.hpp
Normal file
@@ -0,0 +1,46 @@
|
||||
#pragma once
|
||||
|
||||
#include <ostream>
|
||||
|
||||
namespace token {
|
||||
|
||||
// X-macro list of token types and their string representations
|
||||
#define TOKEN_LIST \
|
||||
X(ILLEGAL, "ILLEGAL") \
|
||||
X(END_OF_FILE, "EOF") \
|
||||
X(IDENTIFIER, "IDENTIFIER") \
|
||||
X(INT, "INT") \
|
||||
X(ASSIGN, "=") \
|
||||
X(PLUS, "+") \
|
||||
X(MINUS, "-") \
|
||||
X(BANG, "!") \
|
||||
X(ASTERISK, "*") \
|
||||
X(SLASH, "/") \
|
||||
X(LT, "<") \
|
||||
X(GT, ">") \
|
||||
X(COMMA, ",") \
|
||||
X(SEMICOLON, ";") \
|
||||
X(LPAREN, "(") \
|
||||
X(RPAREN, ")") \
|
||||
X(LBRACE, "{") \
|
||||
X(RBRACE, "}") \
|
||||
X(LET, "LET") \
|
||||
X(FUNCTION, "FUNCTION") \
|
||||
X(IF, "IF") \
|
||||
X(ELSE, "ELSE") \
|
||||
X(TRUE, "TRUE") \
|
||||
X(FALSE, "FALSE") \
|
||||
X(EQ, "==") \
|
||||
X(NEQ, "!=") \
|
||||
X(RETURN, "RETURN")
|
||||
|
||||
// Define the TokenType enum using the X-macro
|
||||
enum class type {
|
||||
#define X(name, str) name,
|
||||
TOKEN_LIST
|
||||
#undef X
|
||||
};
|
||||
|
||||
std::ostream& operator<<(std::ostream&, type);
|
||||
type lookup_identifier(std::string);
|
||||
} // namespace token
|
161
test/lexer.cpp
Normal file
161
test/lexer.cpp
Normal file
@@ -0,0 +1,161 @@
|
||||
#include "lexer/lexer.hpp"
|
||||
|
||||
#include "token/type.hpp"
|
||||
|
||||
#include <doctest.h>
|
||||
#include <sstream>
|
||||
#include <string>
|
||||
|
||||
TEST_CASE("Single character token") {
|
||||
struct test {
|
||||
token::type expectedType;
|
||||
std::string expectedLiteral;
|
||||
};
|
||||
|
||||
std::string input = "=+(){},;";
|
||||
std::istringstream ss(input);
|
||||
|
||||
lexer::lexer l{ss};
|
||||
|
||||
test tests[] = {
|
||||
{token::type::ASSIGN, "="},
|
||||
{token::type::PLUS, "+"},
|
||||
{token::type::LPAREN, "("},
|
||||
{token::type::RPAREN, ")"},
|
||||
{token::type::LBRACE, "{"},
|
||||
{token::type::RBRACE, "}"},
|
||||
{token::type::COMMA, ","},
|
||||
{token::type::SEMICOLON, ";"},
|
||||
{token::type::END_OF_FILE, ""},
|
||||
};
|
||||
|
||||
for (const auto& t : tests) {
|
||||
token::token tok = l.next_token();
|
||||
REQUIRE(tok.type == t.expectedType);
|
||||
REQUIRE(tok.literal == t.expectedLiteral);
|
||||
}
|
||||
};
|
||||
|
||||
TEST_CASE("More tokens") {
|
||||
struct test {
|
||||
token::type expectedType;
|
||||
std::string expectedLiteral;
|
||||
};
|
||||
|
||||
std::istringstream ss("let five = 5;\
|
||||
let ten = 10;\
|
||||
let add = fn(x, y) {\
|
||||
x + y;\
|
||||
};\
|
||||
let result = add(five, ten);\
|
||||
!-/*5;\
|
||||
5 < 10 > 5;\
|
||||
\
|
||||
if (5 < 10) {\
|
||||
return true;\
|
||||
} else {\
|
||||
return false;\
|
||||
}\
|
||||
\
|
||||
10 == 10;\
|
||||
10 != 9;\
|
||||
");
|
||||
|
||||
lexer::lexer l{ss};
|
||||
|
||||
test tests[] = {
|
||||
// clang-format off
|
||||
{token::type::LET, "let"},
|
||||
{token::type::IDENTIFIER, "five"},
|
||||
{token::type::ASSIGN, "="},
|
||||
{token::type::INT, "5"},
|
||||
{token::type::SEMICOLON, ";"},
|
||||
|
||||
{token::type::LET, "let"},
|
||||
{token::type::IDENTIFIER, "ten"},
|
||||
{token::type::ASSIGN, "="},
|
||||
{token::type::INT, "10"},
|
||||
{token::type::SEMICOLON, ";"},
|
||||
|
||||
{token::type::LET, "let"},
|
||||
{token::type::IDENTIFIER, "add"},
|
||||
{token::type::ASSIGN, "="},
|
||||
{token::type::FUNCTION, "fn"},
|
||||
{token::type::LPAREN, "("},
|
||||
{token::type::IDENTIFIER, "x"},
|
||||
{token::type::COMMA, ","},
|
||||
{token::type::IDENTIFIER, "y"},
|
||||
{token::type::RPAREN, ")"},
|
||||
{token::type::LBRACE, "{"},
|
||||
{token::type::IDENTIFIER, "x"},
|
||||
{token::type::PLUS, "+"},
|
||||
{token::type::IDENTIFIER, "y"},
|
||||
{token::type::SEMICOLON, ";"},
|
||||
{token::type::RBRACE, "}"},
|
||||
{token::type::SEMICOLON, ";"},
|
||||
|
||||
{token::type::LET, "let"},
|
||||
{token::type::IDENTIFIER, "result"},
|
||||
{token::type::ASSIGN, "="},
|
||||
{token::type::IDENTIFIER, "add"},
|
||||
{token::type::LPAREN, "("},
|
||||
{token::type::IDENTIFIER, "five"},
|
||||
{token::type::COMMA, ","},
|
||||
{token::type::IDENTIFIER, "ten"},
|
||||
{token::type::RPAREN, ")"},
|
||||
{token::type::SEMICOLON, ";"},
|
||||
|
||||
{token::type::BANG, "!"},
|
||||
{token::type::MINUS, "-"},
|
||||
{token::type::SLASH, "/"},
|
||||
{token::type::ASTERISK, "*"},
|
||||
{token::type::INT, "5"},
|
||||
{token::type::SEMICOLON, ";"},
|
||||
|
||||
{token::type::INT, "5"},
|
||||
{token::type::LT, "<"},
|
||||
{token::type::INT, "10"},
|
||||
{token::type::GT, ">"},
|
||||
{token::type::INT, "5"},
|
||||
{token::type::SEMICOLON, ";"},
|
||||
|
||||
{token::type::IF, "if"},
|
||||
{token::type::LPAREN, "("},
|
||||
{token::type::INT, "5"},
|
||||
{token::type::LT, "<"},
|
||||
{token::type::INT, "10"},
|
||||
{token::type::RPAREN, ")"},
|
||||
{token::type::LBRACE, "{"},
|
||||
|
||||
{token::type::RETURN, "return"},
|
||||
{token::type::TRUE, "true"},
|
||||
{token::type::SEMICOLON, ";"},
|
||||
|
||||
{token::type::RBRACE, "}"},
|
||||
{token::type::ELSE, "else"},
|
||||
{token::type::LBRACE, "{"},
|
||||
|
||||
{token::type::RETURN, "return"},
|
||||
{token::type::FALSE, "false"},
|
||||
{token::type::SEMICOLON, ";"},
|
||||
|
||||
{token::type::RBRACE, "}"},
|
||||
|
||||
{token::type::INT, "10"},
|
||||
{token::type::EQ, "=="},
|
||||
{token::type::INT, "10"},
|
||||
{token::type::SEMICOLON, ";"},
|
||||
|
||||
{token::type::INT, "10"},
|
||||
{token::type::NEQ, "!="},
|
||||
{token::type::INT, "9"},
|
||||
{token::type::SEMICOLON, ";"},
|
||||
// clang-format on
|
||||
};
|
||||
|
||||
for (const auto& t : tests) {
|
||||
token::token tok = l.next_token();
|
||||
REQUIRE(tok.type == t.expectedType);
|
||||
REQUIRE(tok.literal == t.expectedLiteral);
|
||||
}
|
||||
};
|
134
test/parser.cpp
Normal file
134
test/parser.cpp
Normal file
@@ -0,0 +1,134 @@
|
||||
#include "parser/parser.hpp"
|
||||
|
||||
#include "ast/ast.hpp"
|
||||
#include "ast/statements/let.hpp"
|
||||
#include "lexer/lexer.hpp"
|
||||
|
||||
#include <doctest.h>
|
||||
#include <iostream>
|
||||
#include <sstream>
|
||||
|
||||
void test_let_statement(ast::statement* stmt, const std::string name) {
|
||||
REQUIRE(stmt->token_literal() == "let");
|
||||
ast::let* let_stmt;
|
||||
REQUIRE_NOTHROW(let_stmt = dynamic_cast<ast::let*>(stmt));
|
||||
REQUIRE_MESSAGE(
|
||||
let_stmt != nullptr,
|
||||
"Couldn't cast statement to a let statement"
|
||||
);
|
||||
|
||||
REQUIRE(let_stmt->name->value == name);
|
||||
REQUIRE(let_stmt->name->token_literal() == name);
|
||||
}
|
||||
|
||||
void test_failing_let_parsing(
|
||||
std::string input_s,
|
||||
std::vector<token::type> expected_types,
|
||||
int n_good_statements = 0
|
||||
) {
|
||||
std::stringstream input(input_s);
|
||||
|
||||
lexer::lexer l{input};
|
||||
parser::parser p{l};
|
||||
|
||||
ast::program* program = p.parse_program();
|
||||
|
||||
// Check for errors
|
||||
REQUIRE(p.errors.size() == expected_types.size());
|
||||
|
||||
int i = 0;
|
||||
for (auto& e : p.errors) {
|
||||
ast::error::expected_next* en;
|
||||
|
||||
REQUIRE_NOTHROW(en = dynamic_cast<ast::error::expected_next*>(e));
|
||||
REQUIRE_MESSAGE(
|
||||
en != nullptr,
|
||||
"Couldn't cast the error to an 'expected_next'"
|
||||
);
|
||||
REQUIRE(en->expected_type == expected_types[i++]);
|
||||
}
|
||||
|
||||
// normal program check
|
||||
REQUIRE_MESSAGE(
|
||||
program != nullptr,
|
||||
"parse_program() returned a null pointer"
|
||||
);
|
||||
REQUIRE(program->statements.size() == n_good_statements);
|
||||
delete program;
|
||||
}
|
||||
|
||||
void check_parser_errors(const std::vector<ast::error::error*>& errors) {
|
||||
if (errors.empty())
|
||||
return;
|
||||
|
||||
std::cerr << "parser has " << errors.size() << " errors:\n";
|
||||
for (const auto& error : errors)
|
||||
std::cerr << '\t' << error->what() << "\n";
|
||||
|
||||
// Use doctest's FAIL macro to immediately stop
|
||||
FAIL_CHECK("Parser had errors. See stderr for details.");
|
||||
}
|
||||
|
||||
TEST_CASE("Malformed let statement (checking for memory leaks)") {
|
||||
SUBCASE("Second token not identifier") {
|
||||
test_failing_let_parsing("let 5 = 5;", {token::type::IDENTIFIER});
|
||||
}
|
||||
|
||||
SUBCASE("Third token not '='") {
|
||||
test_failing_let_parsing("let five ! 5;", {token::type::ASSIGN});
|
||||
}
|
||||
|
||||
SUBCASE("Missing both identifier and '='") {
|
||||
test_failing_let_parsing("let 5;", {token::type::IDENTIFIER});
|
||||
}
|
||||
|
||||
SUBCASE("Multiple parsing errors") {
|
||||
test_failing_let_parsing(
|
||||
"let 5; let ! = 5; let five = 5; let five 5; let;",
|
||||
{token::type::IDENTIFIER,
|
||||
token::type::IDENTIFIER,
|
||||
token::type::ASSIGN,
|
||||
token::type::IDENTIFIER},
|
||||
1
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
TEST_CASE("Parse let statement") {
|
||||
std::stringstream input("\
|
||||
let x = 5;\
|
||||
let y = 10;\
|
||||
let foobar = 103213;\
|
||||
");
|
||||
|
||||
lexer::lexer l{input};
|
||||
parser::parser p{l};
|
||||
|
||||
ast::program* program = p.parse_program();
|
||||
check_parser_errors(p.errors);
|
||||
|
||||
REQUIRE_MESSAGE(
|
||||
program != nullptr,
|
||||
"parse_program() returned a null pointer"
|
||||
);
|
||||
REQUIRE(program->statements.size() == 3);
|
||||
|
||||
struct test {
|
||||
std::string expected_identifier;
|
||||
};
|
||||
|
||||
test tests[]{
|
||||
"x",
|
||||
"y",
|
||||
"foobar",
|
||||
};
|
||||
|
||||
int i = 0;
|
||||
for (const auto& t : tests) {
|
||||
ast::statement* stmt = program->statements[i++];
|
||||
|
||||
test_let_statement(stmt, t.expected_identifier);
|
||||
}
|
||||
|
||||
delete program;
|
||||
}
|
20
test/test.cpp
Normal file
20
test/test.cpp
Normal file
@@ -0,0 +1,20 @@
|
||||
#define DOCTEST_CONFIG_IMPLEMENT_WITH_MAIN
|
||||
#include <doctest.h>
|
||||
|
||||
int factorial(int number) {
|
||||
return number <= 1 ? number : factorial(number - 1) * number;
|
||||
}
|
||||
|
||||
TEST_CASE("fact") {
|
||||
CHECK(factorial(1) == 1);
|
||||
CHECK(factorial(2) == 2);
|
||||
CHECK(factorial(3) == 6);
|
||||
CHECK(factorial(10) == 3628800);
|
||||
}
|
||||
|
||||
TEST_CASE("fact2") {
|
||||
CHECK(factorial(1) == 1);
|
||||
CHECK(factorial(2) == 2);
|
||||
CHECK(factorial(3) == 6);
|
||||
CHECK(factorial(10) == 3628800);
|
||||
}
|
Reference in New Issue
Block a user