def test_lexer_parses_bare_monkey_syntax():
data = "let five = 5;"
lexer = Lexer(data)
assert lexer.next_token() == Token(TokenTypes.LET, "let")
assert lexer.next_token() == Token(TokenTypes.IDENT, "five")
assert lexer.next_token() == Token(TokenTypes.ASSIGN, "=")
assert lexer.next_token() == Token(TokenTypes.INT, "5")
assert lexer.next_token() == Token(TokenTypes.SEMICOLON, ";")
assert lexer.next_token() == Token(TokenTypes.EOF, "")
def test_eval_integer_expression(input_data, expected_val):
lexer = Lexer(input_data)
parser = Parser.new(lexer)
program = parser.parse()
check_parse_errors(parser)
output = eval(program)
assert output.value == expected_val
def test_operator_precedence_parsing(input_data, expected_str):
lexer = Lexer(input_data)
parser = Parser.new(lexer)
program = parser.parse()
check_parse_errors(parser)
print(str(program))
assert str(program).rstrip(" ") == expected_str
def test_bang_operator(input_data, expected_val):
lexer = Lexer(input_data)
parser = Parser.new(lexer)
program = parser.parse()
check_parse_errors(parser)
output = eval(program)
assert output.value == expected_val
def test_if_else_expression(input_data, expected_output):
lexer = Lexer(input_data)
parser = Parser.new(lexer)
program = parser.parse()
check_parse_errors(parser)
output = eval(program)
if hasattr(output, "value"):
assert output.value == expected_output
else:
assert str(output) == expected_output
def test_let_statements(let_data):
lexer = Lexer(let_data)
parser = Parser.new(lexer)
program = parser.parse()
if program is None:
pytest.fail(f"Failed to process the input")
if len(program._statements) != 1:
pytest.fail(f"Mismatch: Expected -> 3 : Found -> {len(program._statements)}")
assert let_data == str(program)
def test_return_statement(provide_return_data):
lexer = Lexer(provide_return_data)
parser = Parser.new(lexer)
program = parser.parse()
if program is None:
pytest.fail(f"Failed to process the input")
if len(program._statements) != 3:
pytest.fail(f"Mismatch: Expected -> 3 : Found -> {len(program._statements)}")
for statement in program._statements:
assert assert_single_return_statement(statement)
def test_pratt_infix_operators(input_data, expected_left, expected_op, expected_right):
lexer = Lexer(input_data)
parser = Parser.new(lexer)
program = parser.parse()
check_parse_errors(parser)
if len(program._statements) != 1:
pytest.fail(f"Mismatch: Expected -> 1 : Found -> {len(program._statements)}")
statement = program._statements[0]
assert assert_simple_infix_operator_statement(statement, str(expected_left), expected_op, str(expected_right))
def test_pratt_identifiers():
input = "foobar;"
lexer = Lexer(input)
parser = Parser.new(lexer)
program = parser.parse()
if program is None:
pytest.fail(f"Failed to process the input")
if len(program._statements) != 1:
pytest.fail(f"Mismatch: Expected -> 1 : Found -> {len(program._statements)}")
assert assert_simple_identifier_expression_statement(program._statements[0], input)
def test_lexer_returns_correct_tokens():
data = "=+(){},;"
lexer = Lexer(data)
assert lexer.next_token() == Token(TokenTypes.ASSIGN, "=")
assert lexer.next_token() == Token(TokenTypes.PLUS, "+")
assert lexer.next_token() == Token(TokenTypes.LPAREN, "(")
assert lexer.next_token() == Token(TokenTypes.RPAREN, ")")
assert lexer.next_token() == Token(TokenTypes.LBRACE, "{")
assert lexer.next_token() == Token(TokenTypes.RBRACE, "}")
assert lexer.next_token() == Token(TokenTypes.COMMA, ",")
assert lexer.next_token() == Token(TokenTypes.SEMICOLON, ";")
assert lexer.next_token() == Token(TokenTypes.EOF, "")
def test_pratt_integer_literals():
input = "5;"
lexer = Lexer(input)
parser = Parser.new(lexer)
program = parser.parse()
if program is None:
pytest.fail(f"Failed to process the input")
if len(program._statements) != 1:
pytest.fail(f"Mismatch: Expected -> 1 : Found -> {len(program._statements)}")
statement = program._statements[0]
assert assert_simple_integer_expression(statement)
def test_if_expression():
lexer = Lexer("if (x < y) { x } else { y }")
parser = Parser.new(lexer)
program = parser.parse()
check_parse_errors(parser)
if len(program._statements) != 1:
pytest.fail(f"Mismatch: Expected -> 1 : Found -> {len(program._statements)}")
statement = program._statements[0]
assert isinstance(statement, ExpressionStatement), f"type mismatch {type(statement)}"
if not isinstance(statement._expression, IfExpression):
pytest.fail(f"Type mismatch:Got {type(statement._expression)}")
assert str(program) == "if (x < y) { x } else { y }"
def test_function_literal():
lexer = Lexer("fn(x, y) { x + y }")
parser = Parser.new(lexer)
program = parser.parse()
check_parse_errors(parser)
if len(program._statements) != 1:
pytest.fail(f"Mismatch: Expected -> 1 : Found -> {len(program._statements)}")
statement = program._statements[0]
if not isinstance(statement._expression, FunctionLiteral):
pytest.fail(f"Expected function literal : Found => {type(statement._expression)}")
if len(statement._expression._parameters) != 2:
pytest.fail(f"Expected two parameters : Got {len(statement._expression_parameters)}")
assert statement._expression._parameters[0]._value == "x"
assert statement._expression._parameters[1]._value == "y"
assert str(statement._expression._block) == "(x + y)"
def test_call_expression():
lexer = Lexer("add(1, 2 * 3, 4 + 5);")
parser = Parser.new(lexer)
program = parser.parse()
check_parse_errors(parser)
if len(program._statements) != 1:
pytest.fail(f"Mismatch: Expected -> 1 : Found -> {len(program._statements)}")
statement = program._statements[0]
if not isinstance(statement, ExpressionStatement):
pytest.fail(f"Expected ExpressionStatement : Got {type(statement)} instead")
if not isinstance(statement._expression, CallExpression):
pytest.fail(f"Expected Call Expression : Got => {type(statement._expression)}")
if len(statement._expression._args) != 3:
pytest.fail(f"Expected two parameters : Got {len(statement._expression._args)}")
assert str(statement._expression._ident_or_func_literal) == "add"
assert str(statement._expression._args[0]) == '1'
assert str(statement._expression._args[1]) == '(2 * 3)'
def test_lexer_returns_none_on_empty():
lexer = Lexer("")
assert lexer.next_token() == Token(TokenTypes.EOF, "")
def test_lexer_parses_minimum_monkey_syntax():
data = """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(data)
assert lexer.next_token() == Token(TokenTypes.LET, "let")
assert lexer.next_token() == Token(TokenTypes.IDENT, "five")
assert lexer.next_token() == Token(TokenTypes.ASSIGN, "=")
assert lexer.next_token() == Token(TokenTypes.INT, "5")
assert lexer.next_token() == Token(TokenTypes.SEMICOLON, ";")
assert lexer.next_token() == Token(TokenTypes.LET, "let")
assert lexer.next_token() == Token(TokenTypes.IDENT, "ten")
assert lexer.next_token() == Token(TokenTypes.ASSIGN, "=")
assert lexer.next_token() == Token(TokenTypes.INT, "10")
assert lexer.next_token() == Token(TokenTypes.SEMICOLON, ";")
assert lexer.next_token() == Token(TokenTypes.LET, "let")
assert lexer.next_token() == Token(TokenTypes.IDENT, "add")
assert lexer.next_token() == Token(TokenTypes.ASSIGN, "=")
assert lexer.next_token() == Token(TokenTypes.FUNCTION, "fn")
assert lexer.next_token() == Token(TokenTypes.LPAREN, "(")
assert lexer.next_token() == Token(TokenTypes.IDENT, "x")
assert lexer.next_token() == Token(TokenTypes.COMMA, ",")
assert lexer.next_token() == Token(TokenTypes.IDENT, "y")
assert lexer.next_token() == Token(TokenTypes.RPAREN, ")")
assert lexer.next_token() == Token(TokenTypes.LBRACE, "{")
assert lexer.next_token() == Token(TokenTypes.IDENT, "x")
assert lexer.next_token() == Token(TokenTypes.PLUS, "+")
assert lexer.next_token() == Token(TokenTypes.IDENT, "y")
assert lexer.next_token() == Token(TokenTypes.SEMICOLON, ";")
assert lexer.next_token() == Token(TokenTypes.RBRACE, "}")
assert lexer.next_token() == Token(TokenTypes.SEMICOLON, ";")
assert lexer.next_token() == Token(TokenTypes.LET, "let")
assert lexer.next_token() == Token(TokenTypes.IDENT, "result")
assert lexer.next_token() == Token(TokenTypes.ASSIGN, "=")
assert lexer.next_token() == Token(TokenTypes.IDENT, "add")
assert lexer.next_token() == Token(TokenTypes.LPAREN, "(")
assert lexer.next_token() == Token(TokenTypes.IDENT, "five")
assert lexer.next_token() == Token(TokenTypes.COMMA, ",")
assert lexer.next_token() == Token(TokenTypes.IDENT, "ten")
assert lexer.next_token() == Token(TokenTypes.RPAREN, ")")
assert lexer.next_token() == Token(TokenTypes.SEMICOLON, ";")
assert lexer.next_token() == Token(TokenTypes.BANG, "!")
assert lexer.next_token() == Token(TokenTypes.MINUS, "-")
assert lexer.next_token() == Token(TokenTypes.SLASH, "/")
assert lexer.next_token() == Token(TokenTypes.ASTERISK, "*")
assert lexer.next_token() == Token(TokenTypes.INT, "5")
assert lexer.next_token() == Token(TokenTypes.SEMICOLON, ";")
assert lexer.next_token() == Token(TokenTypes.INT, "5")
assert lexer.next_token() == Token(TokenTypes.LT, "<")
assert lexer.next_token() == Token(TokenTypes.INT, "10")
assert lexer.next_token() == Token(TokenTypes.GT, ">")
assert lexer.next_token() == Token(TokenTypes.INT, "5")
assert lexer.next_token() == Token(TokenTypes.SEMICOLON, ";")
# if (5 < 10) {
# return true;
# } else {
# return false; }
assert lexer.next_token() == Token(TokenTypes.IF, "if")
assert lexer.next_token() == Token(TokenTypes.LPAREN, "(")
assert lexer.next_token() == Token(TokenTypes.INT, "5")
assert lexer.next_token() == Token(TokenTypes.LT, "<")
assert lexer.next_token() == Token(TokenTypes.INT, "10")
assert lexer.next_token() == Token(TokenTypes.RPAREN, ")")
assert lexer.next_token() == Token(TokenTypes.LBRACE, "{")
assert lexer.next_token() == Token(TokenTypes.RETURN, "return")
assert lexer.next_token() == Token(TokenTypes.TRUE, "true")
assert lexer.next_token() == Token(TokenTypes.SEMICOLON, ";")
assert lexer.next_token() == Token(TokenTypes.RBRACE, "}")
assert lexer.next_token() == Token(TokenTypes.ELSE, "else")
assert lexer.next_token() == Token(TokenTypes.LBRACE, "{")
assert lexer.next_token() == Token(TokenTypes.RETURN, "return")
assert lexer.next_token() == Token(TokenTypes.FALSE, "false")
assert lexer.next_token() == Token(TokenTypes.SEMICOLON, ";")
assert lexer.next_token() == Token(TokenTypes.RBRACE, "}")
assert lexer.next_token() == Token(TokenTypes.INT, "10")
assert lexer.next_token() == Token(TokenTypes.EQ, "==")
assert lexer.next_token() == Token(TokenTypes.INT, "10")
assert lexer.next_token() == Token(TokenTypes.SEMICOLON, ";")
assert lexer.next_token() == Token(TokenTypes.INT, "10")
assert lexer.next_token() == Token(TokenTypes.NOT_EQ, "==")
assert lexer.next_token() == Token(TokenTypes.INT, "9")
assert lexer.next_token() == Token(TokenTypes.SEMICOLON, ";")
assert lexer.next_token() == Token(TokenTypes.EOF, "")
def test_is_letter():
lexer = Lexer("")
assert lexer.is_letter('c')
assert lexer.is_letter('*') is False
assert lexer.is_letter('_')
assert lexer.is_letter(' ') is False