2020-03-11 18:27:43 +00:00
/*
* Copyright ( c ) 2020 , Stephan Unverwerth < s . unverwerth @ gmx . de >
2020-04-23 14:43:10 +00:00
* Copyright ( c ) 2020 , Linus Groh < mail @ linusgroh . de >
2020-03-11 18:27:43 +00:00
* All rights reserved .
*
* Redistribution and use in source and binary forms , with or without
* modification , are permitted provided that the following conditions are met :
*
* 1. Redistributions of source code must retain the above copyright notice , this
* list of conditions and the following disclaimer .
*
* 2. Redistributions in binary form must reproduce the above copyright notice ,
* this list of conditions and the following disclaimer in the documentation
* and / or other materials provided with the distribution .
*
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS " AS IS "
* AND ANY EXPRESS OR IMPLIED WARRANTIES , INCLUDING , BUT NOT LIMITED TO , THE
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
* DISCLAIMED . IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
* FOR ANY DIRECT , INDIRECT , INCIDENTAL , SPECIAL , EXEMPLARY , OR CONSEQUENTIAL
* DAMAGES ( INCLUDING , BUT NOT LIMITED TO , PROCUREMENT OF SUBSTITUTE GOODS OR
* SERVICES ; LOSS OF USE , DATA , OR PROFITS ; OR BUSINESS INTERRUPTION ) HOWEVER
* CAUSED AND ON ANY THEORY OF LIABILITY , WHETHER IN CONTRACT , STRICT LIABILITY ,
* OR TORT ( INCLUDING NEGLIGENCE OR OTHERWISE ) ARISING IN ANY WAY OUT OF THE USE
* OF THIS SOFTWARE , EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE .
*/
# include "Parser.h"
2020-03-12 22:02:41 +00:00
# include <AK/HashMap.h>
2020-04-13 14:42:54 +00:00
# include <AK/ScopeGuard.h>
2020-03-11 18:27:43 +00:00
# include <AK/StdLibExtras.h>
namespace JS {
2020-03-12 22:02:41 +00:00
2020-04-13 14:42:54 +00:00
class ScopePusher {
public :
enum Type {
Var = 1 ,
Let = 2 ,
} ;
ScopePusher ( Parser & parser , unsigned mask )
: m_parser ( parser )
, m_mask ( mask )
{
if ( m_mask & Var )
m_parser . m_parser_state . m_var_scopes . append ( NonnullRefPtrVector < VariableDeclaration > ( ) ) ;
if ( m_mask & Let )
m_parser . m_parser_state . m_let_scopes . append ( NonnullRefPtrVector < VariableDeclaration > ( ) ) ;
}
~ ScopePusher ( )
{
if ( m_mask & Var )
m_parser . m_parser_state . m_var_scopes . take_last ( ) ;
if ( m_mask & Let )
m_parser . m_parser_state . m_let_scopes . take_last ( ) ;
}
Parser & m_parser ;
unsigned m_mask { 0 } ;
} ;
2020-03-12 22:02:41 +00:00
static HashMap < TokenType , int > g_operator_precedence ;
2020-03-30 13:24:43 +00:00
Parser : : ParserState : : ParserState ( Lexer lexer )
2020-03-11 18:27:43 +00:00
: m_lexer ( move ( lexer ) )
, m_current_token ( m_lexer . next ( ) )
2020-03-30 13:24:43 +00:00
{
}
Parser : : Parser ( Lexer lexer )
: m_parser_state ( move ( lexer ) )
2020-03-11 18:27:43 +00:00
{
2020-03-12 22:02:41 +00:00
if ( g_operator_precedence . is_empty ( ) ) {
// https://developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/Operators/Operator_Precedence
g_operator_precedence . set ( TokenType : : Period , 20 ) ;
g_operator_precedence . set ( TokenType : : BracketOpen , 20 ) ;
g_operator_precedence . set ( TokenType : : ParenOpen , 20 ) ;
g_operator_precedence . set ( TokenType : : QuestionMarkPeriod , 20 ) ;
g_operator_precedence . set ( TokenType : : New , 19 ) ;
g_operator_precedence . set ( TokenType : : PlusPlus , 18 ) ;
g_operator_precedence . set ( TokenType : : MinusMinus , 18 ) ;
g_operator_precedence . set ( TokenType : : ExclamationMark , 17 ) ;
g_operator_precedence . set ( TokenType : : Tilde , 17 ) ;
g_operator_precedence . set ( TokenType : : Typeof , 17 ) ;
g_operator_precedence . set ( TokenType : : Void , 17 ) ;
g_operator_precedence . set ( TokenType : : Delete , 17 ) ;
g_operator_precedence . set ( TokenType : : Await , 17 ) ;
g_operator_precedence . set ( TokenType : : DoubleAsterisk , 16 ) ;
g_operator_precedence . set ( TokenType : : Asterisk , 15 ) ;
g_operator_precedence . set ( TokenType : : Slash , 15 ) ;
g_operator_precedence . set ( TokenType : : Percent , 15 ) ;
g_operator_precedence . set ( TokenType : : Plus , 14 ) ;
g_operator_precedence . set ( TokenType : : Minus , 14 ) ;
g_operator_precedence . set ( TokenType : : ShiftLeft , 13 ) ;
g_operator_precedence . set ( TokenType : : ShiftRight , 13 ) ;
g_operator_precedence . set ( TokenType : : UnsignedShiftRight , 13 ) ;
g_operator_precedence . set ( TokenType : : LessThan , 12 ) ;
g_operator_precedence . set ( TokenType : : LessThanEquals , 12 ) ;
g_operator_precedence . set ( TokenType : : GreaterThan , 12 ) ;
g_operator_precedence . set ( TokenType : : GreaterThanEquals , 12 ) ;
g_operator_precedence . set ( TokenType : : In , 12 ) ;
g_operator_precedence . set ( TokenType : : Instanceof , 12 ) ;
g_operator_precedence . set ( TokenType : : EqualsEquals , 11 ) ;
g_operator_precedence . set ( TokenType : : ExclamationMarkEquals , 11 ) ;
g_operator_precedence . set ( TokenType : : EqualsEqualsEquals , 11 ) ;
g_operator_precedence . set ( TokenType : : ExclamationMarkEqualsEquals , 11 ) ;
g_operator_precedence . set ( TokenType : : Ampersand , 10 ) ;
g_operator_precedence . set ( TokenType : : Caret , 9 ) ;
g_operator_precedence . set ( TokenType : : Pipe , 8 ) ;
g_operator_precedence . set ( TokenType : : DoubleQuestionMark , 7 ) ;
g_operator_precedence . set ( TokenType : : DoubleAmpersand , 6 ) ;
g_operator_precedence . set ( TokenType : : DoublePipe , 5 ) ;
g_operator_precedence . set ( TokenType : : QuestionMark , 4 ) ;
g_operator_precedence . set ( TokenType : : Equals , 3 ) ;
g_operator_precedence . set ( TokenType : : PlusEquals , 3 ) ;
g_operator_precedence . set ( TokenType : : MinusEquals , 3 ) ;
2020-05-04 22:03:35 +00:00
g_operator_precedence . set ( TokenType : : DoubleAsteriskEquals , 3 ) ;
2020-03-12 22:02:41 +00:00
g_operator_precedence . set ( TokenType : : AsteriskEquals , 3 ) ;
g_operator_precedence . set ( TokenType : : SlashEquals , 3 ) ;
g_operator_precedence . set ( TokenType : : PercentEquals , 3 ) ;
g_operator_precedence . set ( TokenType : : ShiftLeftEquals , 3 ) ;
g_operator_precedence . set ( TokenType : : ShiftRightEquals , 3 ) ;
g_operator_precedence . set ( TokenType : : UnsignedShiftRightEquals , 3 ) ;
2020-05-04 21:34:45 +00:00
g_operator_precedence . set ( TokenType : : AmpersandEquals , 3 ) ;
2020-03-12 22:02:41 +00:00
g_operator_precedence . set ( TokenType : : PipeEquals , 3 ) ;
2020-05-04 21:34:45 +00:00
g_operator_precedence . set ( TokenType : : CaretEquals , 3 ) ;
2020-03-12 22:02:41 +00:00
g_operator_precedence . set ( TokenType : : Yield , 2 ) ;
g_operator_precedence . set ( TokenType : : Comma , 1 ) ;
}
}
int Parser : : operator_precedence ( TokenType type ) const
{
auto it = g_operator_precedence . find ( type ) ;
if ( it = = g_operator_precedence . end ( ) ) {
2020-04-17 13:05:58 +00:00
fprintf ( stderr , " Internal Error: No precedence for operator %s \n " , Token : : name ( type ) ) ;
2020-03-12 22:02:41 +00:00
ASSERT_NOT_REACHED ( ) ;
return - 1 ;
}
return it - > value ;
}
Associativity Parser : : operator_associativity ( TokenType type ) const
{
switch ( type ) {
case TokenType : : Period :
case TokenType : : BracketOpen :
case TokenType : : ParenOpen :
case TokenType : : QuestionMarkPeriod :
case TokenType : : Asterisk :
case TokenType : : Slash :
case TokenType : : Percent :
case TokenType : : Plus :
case TokenType : : Minus :
case TokenType : : ShiftLeft :
case TokenType : : ShiftRight :
case TokenType : : UnsignedShiftRight :
case TokenType : : LessThan :
case TokenType : : LessThanEquals :
case TokenType : : GreaterThan :
case TokenType : : GreaterThanEquals :
case TokenType : : In :
case TokenType : : Instanceof :
case TokenType : : EqualsEquals :
case TokenType : : ExclamationMarkEquals :
case TokenType : : EqualsEqualsEquals :
case TokenType : : ExclamationMarkEqualsEquals :
2020-03-28 10:48:52 +00:00
case TokenType : : Typeof :
2020-04-15 16:55:03 +00:00
case TokenType : : Void :
2020-04-26 11:53:40 +00:00
case TokenType : : Delete :
2020-03-12 22:02:41 +00:00
case TokenType : : Ampersand :
case TokenType : : Caret :
case TokenType : : Pipe :
case TokenType : : DoubleQuestionMark :
case TokenType : : DoubleAmpersand :
case TokenType : : DoublePipe :
case TokenType : : Comma :
return Associativity : : Left ;
default :
return Associativity : : Right ;
}
2020-03-11 18:27:43 +00:00
}
2020-03-18 10:23:53 +00:00
NonnullRefPtr < Program > Parser : : parse_program ( )
2020-03-11 18:27:43 +00:00
{
2020-04-13 14:42:54 +00:00
ScopePusher scope ( * this , ScopePusher : : Var | ScopePusher : : Let ) ;
2020-03-18 10:23:53 +00:00
auto program = adopt ( * new Program ) ;
2020-03-11 18:27:43 +00:00
while ( ! done ( ) ) {
2020-05-03 09:59:00 +00:00
if ( match_statement ( ) ) {
2020-03-11 18:27:43 +00:00
program - > append ( parse_statement ( ) ) ;
} else {
expected ( " statement " ) ;
consume ( ) ;
}
}
2020-04-13 14:42:54 +00:00
ASSERT ( m_parser_state . m_var_scopes . size ( ) = = 1 ) ;
program - > add_variables ( m_parser_state . m_var_scopes . last ( ) ) ;
program - > add_variables ( m_parser_state . m_let_scopes . last ( ) ) ;
2020-03-11 18:27:43 +00:00
return program ;
}
2020-03-18 10:23:53 +00:00
NonnullRefPtr < Statement > Parser : : parse_statement ( )
2020-03-11 18:27:43 +00:00
{
2020-03-23 18:08:32 +00:00
auto statement = [ this ] ( ) - > NonnullRefPtr < Statement > {
2020-03-30 13:24:43 +00:00
switch ( m_parser_state . m_current_token . type ( ) ) {
2020-03-11 18:27:43 +00:00
case TokenType : : Function :
2020-03-19 10:52:56 +00:00
return parse_function_node < FunctionDeclaration > ( ) ;
2020-03-11 18:27:43 +00:00
case TokenType : : CurlyOpen :
return parse_block_statement ( ) ;
case TokenType : : Return :
return parse_return_statement ( ) ;
case TokenType : : Var :
2020-03-12 11:16:48 +00:00
case TokenType : : Let :
2020-03-12 12:24:34 +00:00
case TokenType : : Const :
2020-03-11 18:27:43 +00:00
return parse_variable_declaration ( ) ;
2020-03-12 12:12:12 +00:00
case TokenType : : For :
return parse_for_statement ( ) ;
2020-03-21 17:40:17 +00:00
case TokenType : : If :
return parse_if_statement ( ) ;
2020-03-24 21:03:50 +00:00
case TokenType : : Throw :
return parse_throw_statement ( ) ;
2020-03-24 13:03:55 +00:00
case TokenType : : Try :
return parse_try_statement ( ) ;
2020-03-29 11:09:54 +00:00
case TokenType : : Break :
return parse_break_statement ( ) ;
2020-04-04 22:22:42 +00:00
case TokenType : : Continue :
return parse_continue_statement ( ) ;
2020-03-29 11:09:54 +00:00
case TokenType : : Switch :
return parse_switch_statement ( ) ;
2020-04-04 19:29:23 +00:00
case TokenType : : Do :
return parse_do_while_statement ( ) ;
2020-04-21 18:27:57 +00:00
case TokenType : : While :
return parse_while_statement ( ) ;
2020-04-30 16:26:27 +00:00
case TokenType : : Debugger :
return parse_debugger_statement ( ) ;
2020-05-03 09:59:00 +00:00
case TokenType : : Semicolon :
consume ( ) ;
return create_ast_node < EmptyStatement > ( ) ;
2020-03-11 18:27:43 +00:00
default :
2020-04-17 13:05:58 +00:00
if ( match_expression ( ) ) {
auto expr = parse_expression ( 0 ) ;
consume_or_insert_semicolon ( ) ;
return create_ast_node < ExpressionStatement > ( move ( expr ) ) ;
}
2020-03-11 18:27:43 +00:00
expected ( " statement (missing switch case) " ) ;
consume ( ) ;
2020-03-18 10:23:53 +00:00
return create_ast_node < ErrorStatement > ( ) ;
2020-03-23 18:08:32 +00:00
} } ( ) ;
2020-04-17 13:05:58 +00:00
2020-03-23 18:08:32 +00:00
return statement ;
2020-03-11 18:27:43 +00:00
}
2020-03-30 13:26:09 +00:00
RefPtr < FunctionExpression > Parser : : try_parse_arrow_function_expression ( bool expect_parens )
{
save_state ( ) ;
2020-04-13 14:42:54 +00:00
m_parser_state . m_var_scopes . append ( NonnullRefPtrVector < VariableDeclaration > ( ) ) ;
ArmedScopeGuard state_rollback_guard = [ & ] {
m_parser_state . m_var_scopes . take_last ( ) ;
load_state ( ) ;
} ;
2020-03-30 13:26:09 +00:00
2020-05-02 18:46:39 +00:00
Vector < FunctionNode : : Parameter > parameters ;
2020-03-30 13:26:09 +00:00
bool parse_failed = false ;
2020-05-04 15:05:13 +00:00
bool has_rest_parameter = false ;
2020-05-06 03:02:14 +00:00
i32 function_length = - 1 ;
2020-03-30 13:26:09 +00:00
while ( true ) {
if ( match ( TokenType : : Comma ) ) {
2020-05-21 22:45:53 +00:00
if ( has_rest_parameter | | ! expect_parens ) {
2020-05-04 15:05:13 +00:00
parse_failed = true ;
break ;
}
2020-03-30 13:26:09 +00:00
consume ( TokenType : : Comma ) ;
} else if ( match ( TokenType : : Identifier ) ) {
2020-05-02 18:46:39 +00:00
auto parameter_name = consume ( TokenType : : Identifier ) . value ( ) ;
RefPtr < Expression > default_value ;
2020-05-06 01:05:50 +00:00
if ( expect_parens & & match ( TokenType : : Equals ) ) {
2020-05-02 18:46:39 +00:00
consume ( TokenType : : Equals ) ;
2020-05-06 03:02:14 +00:00
function_length = parameters . size ( ) ;
2020-05-11 16:27:31 +00:00
default_value = parse_expression ( 2 ) ;
2020-05-02 18:46:39 +00:00
}
parameters . append ( { parameter_name , default_value } ) ;
2020-05-04 15:05:13 +00:00
} else if ( match ( TokenType : : TripleDot ) ) {
consume ( ) ;
if ( has_rest_parameter ) {
parse_failed = true ;
break ;
}
has_rest_parameter = true ;
2020-05-06 03:02:14 +00:00
function_length = parameters . size ( ) ;
2020-05-04 15:05:13 +00:00
auto parameter_name = consume ( TokenType : : Identifier ) . value ( ) ;
parameters . append ( { parameter_name , nullptr , true } ) ;
2020-03-30 13:26:09 +00:00
} else if ( match ( TokenType : : ParenClose ) ) {
if ( expect_parens ) {
consume ( TokenType : : ParenClose ) ;
if ( match ( TokenType : : Arrow ) ) {
consume ( TokenType : : Arrow ) ;
} else {
parse_failed = true ;
}
break ;
}
parse_failed = true ;
break ;
} else if ( match ( TokenType : : Arrow ) ) {
if ( ! expect_parens ) {
consume ( TokenType : : Arrow ) ;
break ;
}
parse_failed = true ;
break ;
} else {
parse_failed = true ;
break ;
}
}
2020-04-13 14:42:54 +00:00
if ( parse_failed )
2020-03-30 13:26:09 +00:00
return nullptr ;
2020-05-11 16:27:31 +00:00
if ( function_length = = - 1 )
2020-05-06 03:02:14 +00:00
function_length = parameters . size ( ) ;
2020-03-30 13:26:09 +00:00
auto function_body_result = [ this ] ( ) - > RefPtr < BlockStatement > {
if ( match ( TokenType : : CurlyOpen ) ) {
// Parse a function body with statements
return parse_block_statement ( ) ;
}
if ( match_expression ( ) ) {
// Parse a function body which returns a single expression
// FIXME: We synthesize a block with a return statement
// for arrow function bodies which are a single expression.
// Esprima generates a single "ArrowFunctionExpression"
// with a "body" property.
auto return_expression = parse_expression ( 0 ) ;
auto return_block = create_ast_node < BlockStatement > ( ) ;
return_block - > append < ReturnStatement > ( move ( return_expression ) ) ;
return return_block ;
}
// Invalid arrow function body
return nullptr ;
} ( ) ;
if ( ! function_body_result . is_null ( ) ) {
2020-04-13 14:42:54 +00:00
state_rollback_guard . disarm ( ) ;
2020-03-30 13:26:09 +00:00
auto body = function_body_result . release_nonnull ( ) ;
2020-05-06 03:02:14 +00:00
return create_ast_node < FunctionExpression > ( " " , move ( body ) , move ( parameters ) , function_length , m_parser_state . m_var_scopes . take_last ( ) ) ;
2020-03-30 13:26:09 +00:00
}
return nullptr ;
}
2020-03-18 10:23:53 +00:00
NonnullRefPtr < Expression > Parser : : parse_primary_expression ( )
2020-03-11 18:27:43 +00:00
{
2020-03-25 08:51:54 +00:00
if ( match_unary_prefixed_expression ( ) )
return parse_unary_prefixed_expression ( ) ;
2020-03-30 13:24:43 +00:00
switch ( m_parser_state . m_current_token . type ( ) ) {
2020-03-11 18:27:43 +00:00
case TokenType : : ParenOpen : {
consume ( TokenType : : ParenOpen ) ;
2020-05-04 15:05:13 +00:00
if ( match ( TokenType : : ParenClose ) | | match ( TokenType : : Identifier ) | | match ( TokenType : : TripleDot ) ) {
2020-03-30 13:26:09 +00:00
auto arrow_function_result = try_parse_arrow_function_expression ( true ) ;
if ( ! arrow_function_result . is_null ( ) ) {
return arrow_function_result . release_nonnull ( ) ;
}
}
2020-03-12 22:02:41 +00:00
auto expression = parse_expression ( 0 ) ;
2020-03-11 18:27:43 +00:00
consume ( TokenType : : ParenClose ) ;
return expression ;
}
2020-04-12 22:42:14 +00:00
case TokenType : : This :
consume ( ) ;
return create_ast_node < ThisExpression > ( ) ;
2020-03-30 13:26:09 +00:00
case TokenType : : Identifier : {
auto arrow_function_result = try_parse_arrow_function_expression ( false ) ;
if ( ! arrow_function_result . is_null ( ) ) {
return arrow_function_result . release_nonnull ( ) ;
}
2020-03-18 10:23:53 +00:00
return create_ast_node < Identifier > ( consume ( ) . value ( ) ) ;
2020-03-30 13:26:09 +00:00
}
2020-03-11 18:27:43 +00:00
case TokenType : : NumericLiteral :
2020-03-18 10:23:53 +00:00
return create_ast_node < NumericLiteral > ( consume ( ) . double_value ( ) ) ;
2020-03-11 18:27:43 +00:00
case TokenType : : BoolLiteral :
2020-03-18 10:23:53 +00:00
return create_ast_node < BooleanLiteral > ( consume ( ) . bool_value ( ) ) ;
2020-03-12 12:05:06 +00:00
case TokenType : : StringLiteral :
2020-05-17 06:27:25 +00:00
return parse_string_literal ( consume ( ) ) ;
2020-03-15 21:32:34 +00:00
case TokenType : : NullLiteral :
consume ( ) ;
2020-03-18 10:23:53 +00:00
return create_ast_node < NullLiteral > ( ) ;
2020-03-11 18:27:43 +00:00
case TokenType : : CurlyOpen :
return parse_object_expression ( ) ;
2020-03-19 10:52:56 +00:00
case TokenType : : Function :
return parse_function_node < FunctionExpression > ( ) ;
2020-03-20 19:29:57 +00:00
case TokenType : : BracketOpen :
return parse_array_expression ( ) ;
LibJS: Add template literals
Adds fully functioning template literals. Because template literals
contain expressions, most of the work has to be done in the Lexer rather
than the Parser. And because of the complexity of template literals
(expressions, nesting, escapes, etc), the Lexer needs to have some
template-related state.
When entering a new template literal, a TemplateLiteralStart token is
emitted. When inside a literal, all text will be parsed up until a '${'
or '`' (or EOF, but that's a syntax error) is seen, and then a
TemplateLiteralExprStart token is emitted. At this point, the Lexer
proceeds as normal, however it keeps track of the number of opening
and closing curly braces it has seen in order to determine the close
of the expression. Once it finds a matching curly brace for the '${',
a TemplateLiteralExprEnd token is emitted and the state is updated
accordingly.
When the Lexer is inside of a template literal, but not an expression,
and sees a '`', this must be the closing grave: a TemplateLiteralEnd
token is emitted.
The state required to correctly parse template strings consists of a
vector (for nesting) of two pieces of information: whether or not we
are in a template expression (as opposed to a template string); and
the count of the number of unmatched open curly braces we have seen
(only applicable if the Lexer is currently in a template expression).
TODO: Add support for template literal newlines in the JS REPL (this will
cause a syntax error currently):
> `foo
> bar`
'foo
bar'
2020-05-03 22:41:14 +00:00
case TokenType : : TemplateLiteralStart :
2020-05-06 23:34:14 +00:00
return parse_template_literal ( false ) ;
2020-03-28 15:33:52 +00:00
case TokenType : : New :
return parse_new_expression ( ) ;
2020-03-11 18:27:43 +00:00
default :
expected ( " primary expression (missing switch case) " ) ;
consume ( ) ;
2020-03-18 10:23:53 +00:00
return create_ast_node < ErrorExpression > ( ) ;
2020-03-11 18:27:43 +00:00
}
}
2020-03-18 10:23:53 +00:00
NonnullRefPtr < Expression > Parser : : parse_unary_prefixed_expression ( )
2020-03-14 18:45:51 +00:00
{
2020-03-30 13:24:43 +00:00
auto precedence = operator_precedence ( m_parser_state . m_current_token . type ( ) ) ;
auto associativity = operator_associativity ( m_parser_state . m_current_token . type ( ) ) ;
switch ( m_parser_state . m_current_token . type ( ) ) {
2020-04-29 20:39:00 +00:00
case TokenType : : PlusPlus : {
consume ( ) ;
auto rhs_start_line = m_parser_state . m_current_token . line_number ( ) ;
auto rhs_start_column = m_parser_state . m_current_token . line_column ( ) ;
auto rhs = parse_expression ( precedence , associativity ) ;
if ( ! rhs - > is_identifier ( ) & & ! rhs - > is_member_expression ( ) )
syntax_error ( String : : format ( " Right-hand side of prefix increment operator must be identifier or member expression, got %s " , rhs - > class_name ( ) ) , rhs_start_line , rhs_start_column ) ;
return create_ast_node < UpdateExpression > ( UpdateOp : : Increment , move ( rhs ) , true ) ;
}
case TokenType : : MinusMinus : {
consume ( ) ;
auto rhs_start_line = m_parser_state . m_current_token . line_number ( ) ;
auto rhs_start_column = m_parser_state . m_current_token . line_column ( ) ;
auto rhs = parse_expression ( precedence , associativity ) ;
if ( ! rhs - > is_identifier ( ) & & ! rhs - > is_member_expression ( ) )
syntax_error ( String : : format ( " Right-hand side of prefix decrement operator must be identifier or member expression, got %s " , rhs - > class_name ( ) ) , rhs_start_line , rhs_start_column ) ;
return create_ast_node < UpdateExpression > ( UpdateOp : : Decrement , move ( rhs ) , true ) ;
}
2020-03-14 18:45:51 +00:00
case TokenType : : ExclamationMark :
consume ( ) ;
2020-03-28 10:48:52 +00:00
return create_ast_node < UnaryExpression > ( UnaryOp : : Not , parse_expression ( precedence , associativity ) ) ;
2020-03-14 18:45:51 +00:00
case TokenType : : Tilde :
consume ( ) ;
2020-03-28 10:48:52 +00:00
return create_ast_node < UnaryExpression > ( UnaryOp : : BitwiseNot , parse_expression ( precedence , associativity ) ) ;
2020-04-02 16:58:39 +00:00
case TokenType : : Plus :
consume ( ) ;
return create_ast_node < UnaryExpression > ( UnaryOp : : Plus , parse_expression ( precedence , associativity ) ) ;
case TokenType : : Minus :
consume ( ) ;
return create_ast_node < UnaryExpression > ( UnaryOp : : Minus , parse_expression ( precedence , associativity ) ) ;
2020-03-17 19:33:32 +00:00
case TokenType : : Typeof :
consume ( ) ;
2020-03-28 10:48:52 +00:00
return create_ast_node < UnaryExpression > ( UnaryOp : : Typeof , parse_expression ( precedence , associativity ) ) ;
2020-04-15 16:55:03 +00:00
case TokenType : : Void :
consume ( ) ;
return create_ast_node < UnaryExpression > ( UnaryOp : : Void , parse_expression ( precedence , associativity ) ) ;
2020-04-26 11:53:40 +00:00
case TokenType : : Delete :
consume ( ) ;
return create_ast_node < UnaryExpression > ( UnaryOp : : Delete , parse_expression ( precedence , associativity ) ) ;
2020-03-14 18:45:51 +00:00
default :
expected ( " primary expression (missing switch case) " ) ;
consume ( ) ;
2020-03-18 10:23:53 +00:00
return create_ast_node < ErrorExpression > ( ) ;
2020-03-14 18:45:51 +00:00
}
}
2020-03-18 10:23:53 +00:00
NonnullRefPtr < ObjectExpression > Parser : : parse_object_expression ( )
2020-03-11 18:27:43 +00:00
{
2020-04-23 18:37:53 +00:00
NonnullRefPtrVector < ObjectProperty > properties ;
2020-03-11 18:27:43 +00:00
consume ( TokenType : : CurlyOpen ) ;
2020-03-21 00:29:00 +00:00
2020-05-22 00:28:28 +00:00
auto property_type = ObjectProperty : : Type : : KeyValue ;
2020-04-07 17:29:37 +00:00
while ( ! done ( ) & & ! match ( TokenType : : CurlyClose ) ) {
2020-04-23 18:37:53 +00:00
RefPtr < Expression > property_key ;
RefPtr < Expression > property_value ;
2020-04-23 18:17:39 +00:00
auto need_colon = true ;
2020-04-28 04:52:47 +00:00
2020-04-18 18:31:27 +00:00
if ( match_identifier_name ( ) ) {
2020-04-23 18:37:53 +00:00
auto identifier = consume ( ) . value ( ) ;
2020-05-22 00:28:28 +00:00
if ( property_type = = ObjectProperty : : Type : : KeyValue ) {
if ( identifier = = " get " & & ! match ( TokenType : : ParenOpen ) ) {
property_type = ObjectProperty : : Type : : Getter ;
continue ;
}
if ( identifier = = " set " & & ! match ( TokenType : : ParenOpen ) ) {
property_type = ObjectProperty : : Type : : Setter ;
continue ;
}
}
2020-04-23 18:37:53 +00:00
property_key = create_ast_node < StringLiteral > ( identifier ) ;
property_value = create_ast_node < Identifier > ( identifier ) ;
2020-04-23 18:17:39 +00:00
need_colon = false ;
2020-04-06 20:17:05 +00:00
} else if ( match ( TokenType : : StringLiteral ) ) {
2020-05-17 06:27:25 +00:00
property_key = parse_string_literal ( consume ( ) ) ;
2020-04-06 20:17:05 +00:00
} else if ( match ( TokenType : : NumericLiteral ) ) {
2020-04-23 18:37:53 +00:00
property_key = create_ast_node < StringLiteral > ( consume ( TokenType : : NumericLiteral ) . value ( ) ) ;
} else if ( match ( TokenType : : BracketOpen ) ) {
consume ( TokenType : : BracketOpen ) ;
property_key = parse_expression ( 0 ) ;
consume ( TokenType : : BracketClose ) ;
2020-04-28 04:52:47 +00:00
} else if ( match ( TokenType : : TripleDot ) ) {
consume ( TokenType : : TripleDot ) ;
2020-05-11 16:27:31 +00:00
property_key = create_ast_node < SpreadExpression > ( parse_expression ( 2 ) ) ;
2020-04-28 04:52:47 +00:00
property_value = property_key ;
need_colon = false ;
2020-05-22 00:28:28 +00:00
property_type = ObjectProperty : : Type : : Spread ;
2020-04-06 20:17:05 +00:00
} else {
2020-05-22 00:28:28 +00:00
if ( property_type ! = ObjectProperty : : Type : : Getter & & property_type ! = ObjectProperty : : Type : : Setter ) {
syntax_error ( String : : format ( " Unexpected token %s as member in object initialization. Expected a numeric literal, string literal or identifier " , m_parser_state . m_current_token . name ( ) ) ) ;
consume ( ) ;
continue ;
}
auto name = property_type = = ObjectProperty : : Type : : Getter ? " get " : " set " ;
property_key = create_ast_node < StringLiteral > ( name ) ;
property_value = create_ast_node < Identifier > ( name ) ;
need_colon = false ;
2020-04-06 20:17:05 +00:00
}
2020-05-22 00:28:28 +00:00
if ( property_type ! = ObjectProperty : : Type : : Spread & & match ( TokenType : : ParenOpen ) ) {
2020-05-01 06:40:45 +00:00
property_value = parse_function_node < FunctionExpression > ( false ) ;
} else if ( need_colon | | match ( TokenType : : Colon ) ) {
2020-03-21 00:29:00 +00:00
consume ( TokenType : : Colon ) ;
2020-05-11 16:27:31 +00:00
property_value = parse_expression ( 2 ) ;
2020-03-21 00:29:00 +00:00
}
2020-05-22 00:28:28 +00:00
auto property = create_ast_node < ObjectProperty > ( * property_key , * property_value , property_type ) ;
2020-04-23 18:37:53 +00:00
properties . append ( property ) ;
2020-05-22 00:28:28 +00:00
property_type = ObjectProperty : : Type : : KeyValue ;
2020-03-21 00:29:00 +00:00
if ( ! match ( TokenType : : Comma ) )
break ;
consume ( TokenType : : Comma ) ;
}
2020-03-11 18:27:43 +00:00
consume ( TokenType : : CurlyClose ) ;
2020-03-21 00:29:00 +00:00
return create_ast_node < ObjectExpression > ( properties ) ;
2020-03-11 18:27:43 +00:00
}
2020-03-20 19:29:57 +00:00
NonnullRefPtr < ArrayExpression > Parser : : parse_array_expression ( )
{
consume ( TokenType : : BracketOpen ) ;
2020-04-15 19:09:06 +00:00
Vector < RefPtr < Expression > > elements ;
2020-04-27 06:05:37 +00:00
while ( match_expression ( ) | | match ( TokenType : : TripleDot ) | | match ( TokenType : : Comma ) ) {
2020-04-15 19:09:06 +00:00
RefPtr < Expression > expression ;
2020-04-27 06:05:37 +00:00
if ( match ( TokenType : : TripleDot ) ) {
consume ( TokenType : : TripleDot ) ;
2020-05-11 16:27:31 +00:00
expression = create_ast_node < SpreadExpression > ( parse_expression ( 2 ) ) ;
2020-04-27 06:05:37 +00:00
} else if ( match_expression ( ) ) {
2020-05-11 16:27:31 +00:00
expression = parse_expression ( 2 ) ;
2020-04-27 06:05:37 +00:00
}
2020-04-15 19:09:06 +00:00
elements . append ( expression ) ;
2020-03-20 19:29:57 +00:00
if ( ! match ( TokenType : : Comma ) )
break ;
consume ( TokenType : : Comma ) ;
}
consume ( TokenType : : BracketClose ) ;
return create_ast_node < ArrayExpression > ( move ( elements ) ) ;
}
2020-05-17 06:27:25 +00:00
NonnullRefPtr < StringLiteral > Parser : : parse_string_literal ( Token token )
{
auto status = Token : : StringValueStatus : : Ok ;
auto string = token . string_value ( status ) ;
if ( status ! = Token : : StringValueStatus : : Ok ) {
String message ;
if ( status = = Token : : StringValueStatus : : MalformedHexEscape | | status = = Token : : StringValueStatus : : MalformedUnicodeEscape ) {
auto type = status = = Token : : StringValueStatus : : MalformedUnicodeEscape ? " unicode " : " hexadecimal " ;
message = String : : format ( " Malformed %s escape sequence " , type ) ;
} else if ( status = = Token : : StringValueStatus : : UnicodeEscapeOverflow ) {
message = " Unicode codepoint must not be greater than 0x10ffff in escape sequence " ;
}
syntax_error (
message ,
m_parser_state . m_current_token . line_number ( ) ,
m_parser_state . m_current_token . line_column ( )
) ;
}
return create_ast_node < StringLiteral > ( string ) ;
}
2020-05-06 23:34:14 +00:00
NonnullRefPtr < TemplateLiteral > Parser : : parse_template_literal ( bool is_tagged )
LibJS: Add template literals
Adds fully functioning template literals. Because template literals
contain expressions, most of the work has to be done in the Lexer rather
than the Parser. And because of the complexity of template literals
(expressions, nesting, escapes, etc), the Lexer needs to have some
template-related state.
When entering a new template literal, a TemplateLiteralStart token is
emitted. When inside a literal, all text will be parsed up until a '${'
or '`' (or EOF, but that's a syntax error) is seen, and then a
TemplateLiteralExprStart token is emitted. At this point, the Lexer
proceeds as normal, however it keeps track of the number of opening
and closing curly braces it has seen in order to determine the close
of the expression. Once it finds a matching curly brace for the '${',
a TemplateLiteralExprEnd token is emitted and the state is updated
accordingly.
When the Lexer is inside of a template literal, but not an expression,
and sees a '`', this must be the closing grave: a TemplateLiteralEnd
token is emitted.
The state required to correctly parse template strings consists of a
vector (for nesting) of two pieces of information: whether or not we
are in a template expression (as opposed to a template string); and
the count of the number of unmatched open curly braces we have seen
(only applicable if the Lexer is currently in a template expression).
TODO: Add support for template literal newlines in the JS REPL (this will
cause a syntax error currently):
> `foo
> bar`
'foo
bar'
2020-05-03 22:41:14 +00:00
{
consume ( TokenType : : TemplateLiteralStart ) ;
NonnullRefPtrVector < Expression > expressions ;
2020-05-06 23:34:14 +00:00
NonnullRefPtrVector < Expression > raw_strings ;
auto append_empty_string = [ & expressions , & raw_strings , is_tagged ] ( ) {
auto string_literal = create_ast_node < StringLiteral > ( " " ) ;
expressions . append ( string_literal ) ;
if ( is_tagged )
raw_strings . append ( string_literal ) ;
} ;
LibJS: Add template literals
Adds fully functioning template literals. Because template literals
contain expressions, most of the work has to be done in the Lexer rather
than the Parser. And because of the complexity of template literals
(expressions, nesting, escapes, etc), the Lexer needs to have some
template-related state.
When entering a new template literal, a TemplateLiteralStart token is
emitted. When inside a literal, all text will be parsed up until a '${'
or '`' (or EOF, but that's a syntax error) is seen, and then a
TemplateLiteralExprStart token is emitted. At this point, the Lexer
proceeds as normal, however it keeps track of the number of opening
and closing curly braces it has seen in order to determine the close
of the expression. Once it finds a matching curly brace for the '${',
a TemplateLiteralExprEnd token is emitted and the state is updated
accordingly.
When the Lexer is inside of a template literal, but not an expression,
and sees a '`', this must be the closing grave: a TemplateLiteralEnd
token is emitted.
The state required to correctly parse template strings consists of a
vector (for nesting) of two pieces of information: whether or not we
are in a template expression (as opposed to a template string); and
the count of the number of unmatched open curly braces we have seen
(only applicable if the Lexer is currently in a template expression).
TODO: Add support for template literal newlines in the JS REPL (this will
cause a syntax error currently):
> `foo
> bar`
'foo
bar'
2020-05-03 22:41:14 +00:00
2020-05-06 09:17:35 +00:00
if ( ! match ( TokenType : : TemplateLiteralString ) )
2020-05-06 23:34:14 +00:00
append_empty_string ( ) ;
2020-05-06 09:17:35 +00:00
LibJS: Add template literals
Adds fully functioning template literals. Because template literals
contain expressions, most of the work has to be done in the Lexer rather
than the Parser. And because of the complexity of template literals
(expressions, nesting, escapes, etc), the Lexer needs to have some
template-related state.
When entering a new template literal, a TemplateLiteralStart token is
emitted. When inside a literal, all text will be parsed up until a '${'
or '`' (or EOF, but that's a syntax error) is seen, and then a
TemplateLiteralExprStart token is emitted. At this point, the Lexer
proceeds as normal, however it keeps track of the number of opening
and closing curly braces it has seen in order to determine the close
of the expression. Once it finds a matching curly brace for the '${',
a TemplateLiteralExprEnd token is emitted and the state is updated
accordingly.
When the Lexer is inside of a template literal, but not an expression,
and sees a '`', this must be the closing grave: a TemplateLiteralEnd
token is emitted.
The state required to correctly parse template strings consists of a
vector (for nesting) of two pieces of information: whether or not we
are in a template expression (as opposed to a template string); and
the count of the number of unmatched open curly braces we have seen
(only applicable if the Lexer is currently in a template expression).
TODO: Add support for template literal newlines in the JS REPL (this will
cause a syntax error currently):
> `foo
> bar`
'foo
bar'
2020-05-03 22:41:14 +00:00
while ( ! match ( TokenType : : TemplateLiteralEnd ) & & ! match ( TokenType : : UnterminatedTemplateLiteral ) ) {
if ( match ( TokenType : : TemplateLiteralString ) ) {
2020-05-06 23:34:14 +00:00
auto token = consume ( ) ;
2020-05-17 06:27:25 +00:00
expressions . append ( parse_string_literal ( token ) ) ;
2020-05-06 23:34:14 +00:00
if ( is_tagged )
raw_strings . append ( create_ast_node < StringLiteral > ( token . value ( ) ) ) ;
LibJS: Add template literals
Adds fully functioning template literals. Because template literals
contain expressions, most of the work has to be done in the Lexer rather
than the Parser. And because of the complexity of template literals
(expressions, nesting, escapes, etc), the Lexer needs to have some
template-related state.
When entering a new template literal, a TemplateLiteralStart token is
emitted. When inside a literal, all text will be parsed up until a '${'
or '`' (or EOF, but that's a syntax error) is seen, and then a
TemplateLiteralExprStart token is emitted. At this point, the Lexer
proceeds as normal, however it keeps track of the number of opening
and closing curly braces it has seen in order to determine the close
of the expression. Once it finds a matching curly brace for the '${',
a TemplateLiteralExprEnd token is emitted and the state is updated
accordingly.
When the Lexer is inside of a template literal, but not an expression,
and sees a '`', this must be the closing grave: a TemplateLiteralEnd
token is emitted.
The state required to correctly parse template strings consists of a
vector (for nesting) of two pieces of information: whether or not we
are in a template expression (as opposed to a template string); and
the count of the number of unmatched open curly braces we have seen
(only applicable if the Lexer is currently in a template expression).
TODO: Add support for template literal newlines in the JS REPL (this will
cause a syntax error currently):
> `foo
> bar`
'foo
bar'
2020-05-03 22:41:14 +00:00
} else if ( match ( TokenType : : TemplateLiteralExprStart ) ) {
consume ( TokenType : : TemplateLiteralExprStart ) ;
if ( match ( TokenType : : TemplateLiteralExprEnd ) ) {
syntax_error ( " Empty template literal expression block " ) ;
return create_ast_node < TemplateLiteral > ( expressions ) ;
}
expressions . append ( parse_expression ( 0 ) ) ;
if ( match ( TokenType : : UnterminatedTemplateLiteral ) ) {
syntax_error ( " Unterminated template literal " ) ;
return create_ast_node < TemplateLiteral > ( expressions ) ;
}
consume ( TokenType : : TemplateLiteralExprEnd ) ;
2020-05-06 09:17:35 +00:00
if ( ! match ( TokenType : : TemplateLiteralString ) )
2020-05-06 23:34:14 +00:00
append_empty_string ( ) ;
LibJS: Add template literals
Adds fully functioning template literals. Because template literals
contain expressions, most of the work has to be done in the Lexer rather
than the Parser. And because of the complexity of template literals
(expressions, nesting, escapes, etc), the Lexer needs to have some
template-related state.
When entering a new template literal, a TemplateLiteralStart token is
emitted. When inside a literal, all text will be parsed up until a '${'
or '`' (or EOF, but that's a syntax error) is seen, and then a
TemplateLiteralExprStart token is emitted. At this point, the Lexer
proceeds as normal, however it keeps track of the number of opening
and closing curly braces it has seen in order to determine the close
of the expression. Once it finds a matching curly brace for the '${',
a TemplateLiteralExprEnd token is emitted and the state is updated
accordingly.
When the Lexer is inside of a template literal, but not an expression,
and sees a '`', this must be the closing grave: a TemplateLiteralEnd
token is emitted.
The state required to correctly parse template strings consists of a
vector (for nesting) of two pieces of information: whether or not we
are in a template expression (as opposed to a template string); and
the count of the number of unmatched open curly braces we have seen
(only applicable if the Lexer is currently in a template expression).
TODO: Add support for template literal newlines in the JS REPL (this will
cause a syntax error currently):
> `foo
> bar`
'foo
bar'
2020-05-03 22:41:14 +00:00
}
}
if ( match ( TokenType : : UnterminatedTemplateLiteral ) ) {
syntax_error ( " Unterminated template literal " ) ;
} else {
consume ( TokenType : : TemplateLiteralEnd ) ;
}
2020-05-06 23:34:14 +00:00
if ( is_tagged )
return create_ast_node < TemplateLiteral > ( expressions , raw_strings ) ;
LibJS: Add template literals
Adds fully functioning template literals. Because template literals
contain expressions, most of the work has to be done in the Lexer rather
than the Parser. And because of the complexity of template literals
(expressions, nesting, escapes, etc), the Lexer needs to have some
template-related state.
When entering a new template literal, a TemplateLiteralStart token is
emitted. When inside a literal, all text will be parsed up until a '${'
or '`' (or EOF, but that's a syntax error) is seen, and then a
TemplateLiteralExprStart token is emitted. At this point, the Lexer
proceeds as normal, however it keeps track of the number of opening
and closing curly braces it has seen in order to determine the close
of the expression. Once it finds a matching curly brace for the '${',
a TemplateLiteralExprEnd token is emitted and the state is updated
accordingly.
When the Lexer is inside of a template literal, but not an expression,
and sees a '`', this must be the closing grave: a TemplateLiteralEnd
token is emitted.
The state required to correctly parse template strings consists of a
vector (for nesting) of two pieces of information: whether or not we
are in a template expression (as opposed to a template string); and
the count of the number of unmatched open curly braces we have seen
(only applicable if the Lexer is currently in a template expression).
TODO: Add support for template literal newlines in the JS REPL (this will
cause a syntax error currently):
> `foo
> bar`
'foo
bar'
2020-05-03 22:41:14 +00:00
return create_ast_node < TemplateLiteral > ( expressions ) ;
}
2020-03-18 10:23:53 +00:00
NonnullRefPtr < Expression > Parser : : parse_expression ( int min_precedence , Associativity associativity )
2020-03-11 18:27:43 +00:00
{
auto expression = parse_primary_expression ( ) ;
2020-05-06 09:17:35 +00:00
while ( match ( TokenType : : TemplateLiteralStart ) ) {
2020-05-06 23:34:14 +00:00
auto template_literal = parse_template_literal ( true ) ;
2020-05-06 09:17:35 +00:00
expression = create_ast_node < TaggedTemplateLiteral > ( move ( expression ) , move ( template_literal ) ) ;
}
2020-03-11 18:27:43 +00:00
while ( match_secondary_expression ( ) ) {
2020-03-30 13:24:43 +00:00
int new_precedence = operator_precedence ( m_parser_state . m_current_token . type ( ) ) ;
2020-03-12 22:02:41 +00:00
if ( new_precedence < min_precedence )
break ;
if ( new_precedence = = min_precedence & & associativity = = Associativity : : Left )
break ;
2020-03-30 13:24:43 +00:00
Associativity new_associativity = operator_associativity ( m_parser_state . m_current_token . type ( ) ) ;
2020-03-12 22:02:41 +00:00
expression = parse_secondary_expression ( move ( expression ) , new_precedence , new_associativity ) ;
2020-05-06 09:17:35 +00:00
while ( match ( TokenType : : TemplateLiteralStart ) ) {
2020-05-06 23:34:14 +00:00
auto template_literal = parse_template_literal ( true ) ;
2020-05-06 09:17:35 +00:00
expression = create_ast_node < TaggedTemplateLiteral > ( move ( expression ) , move ( template_literal ) ) ;
}
2020-03-11 18:27:43 +00:00
}
2020-05-11 16:27:31 +00:00
if ( match ( TokenType : : Comma ) & & min_precedence < = 1 ) {
NonnullRefPtrVector < Expression > expressions ;
expressions . append ( expression ) ;
while ( match ( TokenType : : Comma ) ) {
consume ( ) ;
expressions . append ( parse_expression ( 2 ) ) ;
}
expression = create_ast_node < SequenceExpression > ( move ( expressions ) ) ;
}
2020-03-11 18:27:43 +00:00
return expression ;
}
2020-03-18 10:23:53 +00:00
NonnullRefPtr < Expression > Parser : : parse_secondary_expression ( NonnullRefPtr < Expression > lhs , int min_precedence , Associativity associativity )
2020-03-11 18:27:43 +00:00
{
2020-03-30 13:24:43 +00:00
switch ( m_parser_state . m_current_token . type ( ) ) {
2020-03-11 18:27:43 +00:00
case TokenType : : Plus :
consume ( ) ;
2020-04-05 11:56:53 +00:00
return create_ast_node < BinaryExpression > ( BinaryOp : : Addition , move ( lhs ) , parse_expression ( min_precedence , associativity ) ) ;
2020-03-12 12:09:15 +00:00
case TokenType : : PlusEquals :
consume ( ) ;
2020-03-18 10:23:53 +00:00
return create_ast_node < AssignmentExpression > ( AssignmentOp : : AdditionAssignment , move ( lhs ) , parse_expression ( min_precedence , associativity ) ) ;
2020-03-11 18:27:43 +00:00
case TokenType : : Minus :
consume ( ) ;
2020-04-05 11:56:53 +00:00
return create_ast_node < BinaryExpression > ( BinaryOp : : Subtraction , move ( lhs ) , parse_expression ( min_precedence , associativity ) ) ;
2020-03-12 12:09:15 +00:00
case TokenType : : MinusEquals :
consume ( ) ;
2020-03-18 10:23:53 +00:00
return create_ast_node < AssignmentExpression > ( AssignmentOp : : SubtractionAssignment , move ( lhs ) , parse_expression ( min_precedence , associativity ) ) ;
2020-03-12 12:04:52 +00:00
case TokenType : : Asterisk :
consume ( ) ;
2020-04-05 11:56:53 +00:00
return create_ast_node < BinaryExpression > ( BinaryOp : : Multiplication , move ( lhs ) , parse_expression ( min_precedence , associativity ) ) ;
2020-03-12 12:09:15 +00:00
case TokenType : : AsteriskEquals :
consume ( ) ;
2020-03-18 10:23:53 +00:00
return create_ast_node < AssignmentExpression > ( AssignmentOp : : MultiplicationAssignment , move ( lhs ) , parse_expression ( min_precedence , associativity ) ) ;
2020-03-12 12:04:52 +00:00
case TokenType : : Slash :
consume ( ) ;
2020-04-05 11:56:53 +00:00
return create_ast_node < BinaryExpression > ( BinaryOp : : Division , move ( lhs ) , parse_expression ( min_precedence , associativity ) ) ;
2020-03-12 12:09:15 +00:00
case TokenType : : SlashEquals :
consume ( ) ;
2020-03-18 10:23:53 +00:00
return create_ast_node < AssignmentExpression > ( AssignmentOp : : DivisionAssignment , move ( lhs ) , parse_expression ( min_precedence , associativity ) ) ;
2020-04-04 19:17:34 +00:00
case TokenType : : Percent :
consume ( ) ;
return create_ast_node < BinaryExpression > ( BinaryOp : : Modulo , move ( lhs ) , parse_expression ( min_precedence , associativity ) ) ;
2020-05-04 22:07:05 +00:00
case TokenType : : PercentEquals :
consume ( ) ;
return create_ast_node < AssignmentExpression > ( AssignmentOp : : ModuloAssignment , move ( lhs ) , parse_expression ( min_precedence , associativity ) ) ;
2020-04-12 22:42:14 +00:00
case TokenType : : DoubleAsterisk :
2020-04-05 12:40:00 +00:00
consume ( ) ;
return create_ast_node < BinaryExpression > ( BinaryOp : : Exponentiation , move ( lhs ) , parse_expression ( min_precedence , associativity ) ) ;
2020-05-04 22:03:35 +00:00
case TokenType : : DoubleAsteriskEquals :
consume ( ) ;
return create_ast_node < AssignmentExpression > ( AssignmentOp : : ExponentiationAssignment , move ( lhs ) , parse_expression ( min_precedence , associativity ) ) ;
2020-03-12 12:10:27 +00:00
case TokenType : : GreaterThan :
consume ( ) ;
2020-03-18 10:23:53 +00:00
return create_ast_node < BinaryExpression > ( BinaryOp : : GreaterThan , move ( lhs ) , parse_expression ( min_precedence , associativity ) ) ;
2020-03-12 12:07:08 +00:00
case TokenType : : GreaterThanEquals :
consume ( ) ;
2020-03-18 10:23:53 +00:00
return create_ast_node < BinaryExpression > ( BinaryOp : : GreaterThanEquals , move ( lhs ) , parse_expression ( min_precedence , associativity ) ) ;
2020-03-12 12:10:27 +00:00
case TokenType : : LessThan :
consume ( ) ;
2020-03-18 10:23:53 +00:00
return create_ast_node < BinaryExpression > ( BinaryOp : : LessThan , move ( lhs ) , parse_expression ( min_precedence , associativity ) ) ;
2020-03-12 12:07:08 +00:00
case TokenType : : LessThanEquals :
consume ( ) ;
2020-03-18 10:23:53 +00:00
return create_ast_node < BinaryExpression > ( BinaryOp : : LessThanEquals , move ( lhs ) , parse_expression ( min_precedence , associativity ) ) ;
2020-03-12 12:11:33 +00:00
case TokenType : : EqualsEqualsEquals :
consume ( ) ;
2020-03-18 10:23:53 +00:00
return create_ast_node < BinaryExpression > ( BinaryOp : : TypedEquals , move ( lhs ) , parse_expression ( min_precedence , associativity ) ) ;
2020-03-12 12:11:33 +00:00
case TokenType : : ExclamationMarkEqualsEquals :
consume ( ) ;
2020-03-18 10:23:53 +00:00
return create_ast_node < BinaryExpression > ( BinaryOp : : TypedInequals , move ( lhs ) , parse_expression ( min_precedence , associativity ) ) ;
2020-03-15 22:23:38 +00:00
case TokenType : : EqualsEquals :
consume ( ) ;
2020-03-18 10:23:53 +00:00
return create_ast_node < BinaryExpression > ( BinaryOp : : AbstractEquals , move ( lhs ) , parse_expression ( min_precedence , associativity ) ) ;
2020-03-15 22:23:38 +00:00
case TokenType : : ExclamationMarkEquals :
consume ( ) ;
2020-03-18 10:23:53 +00:00
return create_ast_node < BinaryExpression > ( BinaryOp : : AbstractInequals , move ( lhs ) , parse_expression ( min_precedence , associativity ) ) ;
2020-04-23 15:06:01 +00:00
case TokenType : : In :
consume ( ) ;
return create_ast_node < BinaryExpression > ( BinaryOp : : In , move ( lhs ) , parse_expression ( min_precedence , associativity ) ) ;
2020-03-28 15:56:54 +00:00
case TokenType : : Instanceof :
consume ( ) ;
return create_ast_node < BinaryExpression > ( BinaryOp : : InstanceOf , move ( lhs ) , parse_expression ( min_precedence , associativity ) ) ;
2020-04-03 12:02:31 +00:00
case TokenType : : Ampersand :
consume ( ) ;
return create_ast_node < BinaryExpression > ( BinaryOp : : BitwiseAnd , move ( lhs ) , parse_expression ( min_precedence , associativity ) ) ;
2020-05-04 21:34:45 +00:00
case TokenType : : AmpersandEquals :
consume ( ) ;
return create_ast_node < AssignmentExpression > ( AssignmentOp : : BitwiseAndAssignment , move ( lhs ) , parse_expression ( min_precedence , associativity ) ) ;
2020-04-03 12:02:31 +00:00
case TokenType : : Pipe :
consume ( ) ;
return create_ast_node < BinaryExpression > ( BinaryOp : : BitwiseOr , move ( lhs ) , parse_expression ( min_precedence , associativity ) ) ;
2020-05-04 21:34:45 +00:00
case TokenType : : PipeEquals :
consume ( ) ;
return create_ast_node < AssignmentExpression > ( AssignmentOp : : BitwiseOrAssignment , move ( lhs ) , parse_expression ( min_precedence , associativity ) ) ;
2020-04-03 12:02:31 +00:00
case TokenType : : Caret :
consume ( ) ;
return create_ast_node < BinaryExpression > ( BinaryOp : : BitwiseXor , move ( lhs ) , parse_expression ( min_precedence , associativity ) ) ;
2020-05-04 21:34:45 +00:00
case TokenType : : CaretEquals :
consume ( ) ;
return create_ast_node < AssignmentExpression > ( AssignmentOp : : BitwiseXorAssignment , move ( lhs ) , parse_expression ( min_precedence , associativity ) ) ;
2020-04-23 12:36:14 +00:00
case TokenType : : ShiftLeft :
consume ( ) ;
return create_ast_node < BinaryExpression > ( BinaryOp : : LeftShift , move ( lhs ) , parse_expression ( min_precedence , associativity ) ) ;
case TokenType : : ShiftLeftEquals :
consume ( ) ;
return create_ast_node < AssignmentExpression > ( AssignmentOp : : LeftShiftAssignment , move ( lhs ) , parse_expression ( min_precedence , associativity ) ) ;
2020-04-23 12:45:19 +00:00
case TokenType : : ShiftRight :
consume ( ) ;
return create_ast_node < BinaryExpression > ( BinaryOp : : RightShift , move ( lhs ) , parse_expression ( min_precedence , associativity ) ) ;
case TokenType : : ShiftRightEquals :
consume ( ) ;
return create_ast_node < AssignmentExpression > ( AssignmentOp : : RightShiftAssignment , move ( lhs ) , parse_expression ( min_precedence , associativity ) ) ;
2020-04-23 14:43:10 +00:00
case TokenType : : UnsignedShiftRight :
consume ( ) ;
return create_ast_node < BinaryExpression > ( BinaryOp : : UnsignedRightShift , move ( lhs ) , parse_expression ( min_precedence , associativity ) ) ;
case TokenType : : UnsignedShiftRightEquals :
consume ( ) ;
return create_ast_node < AssignmentExpression > ( AssignmentOp : : UnsignedRightShiftAssignment , move ( lhs ) , parse_expression ( min_precedence , associativity ) ) ;
2020-03-11 18:27:43 +00:00
case TokenType : : ParenOpen :
return parse_call_expression ( move ( lhs ) ) ;
case TokenType : : Equals :
consume ( ) ;
2020-05-12 20:19:48 +00:00
if ( ! lhs - > is_identifier ( ) & & ! lhs - > is_member_expression ( ) & & ! lhs - > is_call_expression ( ) ) {
syntax_error ( " Invalid left-hand side in assignment " ) ;
return create_ast_node < ErrorExpression > ( ) ;
}
2020-03-18 10:23:53 +00:00
return create_ast_node < AssignmentExpression > ( AssignmentOp : : Assignment , move ( lhs ) , parse_expression ( min_precedence , associativity ) ) ;
2020-03-12 12:05:57 +00:00
case TokenType : : Period :
consume ( ) ;
2020-04-18 18:31:27 +00:00
if ( ! match_identifier_name ( ) )
expected ( " IdentifierName " ) ;
return create_ast_node < MemberExpression > ( move ( lhs ) , create_ast_node < Identifier > ( consume ( ) . value ( ) ) ) ;
2020-03-20 19:51:03 +00:00
case TokenType : : BracketOpen : {
consume ( TokenType : : BracketOpen ) ;
2020-03-23 18:08:32 +00:00
auto expression = create_ast_node < MemberExpression > ( move ( lhs ) , parse_expression ( 0 ) , true ) ;
2020-03-20 19:51:03 +00:00
consume ( TokenType : : BracketClose ) ;
return expression ;
}
2020-03-12 11:45:45 +00:00
case TokenType : : PlusPlus :
2020-04-29 20:39:00 +00:00
if ( ! lhs - > is_identifier ( ) & & ! lhs - > is_member_expression ( ) )
syntax_error ( String : : format ( " Left-hand side of postfix increment operator must be identifier or member expression, got %s " , lhs - > class_name ( ) ) ) ;
2020-03-12 11:45:45 +00:00
consume ( ) ;
2020-03-18 10:23:53 +00:00
return create_ast_node < UpdateExpression > ( UpdateOp : : Increment , move ( lhs ) ) ;
2020-03-12 11:45:45 +00:00
case TokenType : : MinusMinus :
2020-04-29 20:39:00 +00:00
if ( ! lhs - > is_identifier ( ) & & ! lhs - > is_member_expression ( ) )
syntax_error ( String : : format ( " Left-hand side of postfix increment operator must be identifier or member expression, got %s " , lhs - > class_name ( ) ) ) ;
2020-03-12 11:45:45 +00:00
consume ( ) ;
2020-03-18 10:23:53 +00:00
return create_ast_node < UpdateExpression > ( UpdateOp : : Decrement , move ( lhs ) ) ;
2020-03-15 21:35:22 +00:00
case TokenType : : DoubleAmpersand :
consume ( ) ;
2020-03-18 10:23:53 +00:00
return create_ast_node < LogicalExpression > ( LogicalOp : : And , move ( lhs ) , parse_expression ( min_precedence , associativity ) ) ;
2020-03-15 21:35:22 +00:00
case TokenType : : DoublePipe :
consume ( ) ;
2020-03-18 10:23:53 +00:00
return create_ast_node < LogicalExpression > ( LogicalOp : : Or , move ( lhs ) , parse_expression ( min_precedence , associativity ) ) ;
2020-04-17 23:49:11 +00:00
case TokenType : : DoubleQuestionMark :
consume ( ) ;
return create_ast_node < LogicalExpression > ( LogicalOp : : NullishCoalescing , move ( lhs ) , parse_expression ( min_precedence , associativity ) ) ;
2020-04-03 10:14:28 +00:00
case TokenType : : QuestionMark :
return parse_conditional_expression ( move ( lhs ) ) ;
2020-03-11 18:27:43 +00:00
default :
expected ( " secondary expression (missing switch case) " ) ;
consume ( ) ;
2020-03-18 10:23:53 +00:00
return create_ast_node < ErrorExpression > ( ) ;
2020-03-11 18:27:43 +00:00
}
}
2020-03-18 10:23:53 +00:00
NonnullRefPtr < CallExpression > Parser : : parse_call_expression ( NonnullRefPtr < Expression > lhs )
2020-03-11 18:27:43 +00:00
{
consume ( TokenType : : ParenOpen ) ;
2020-03-12 18:35:23 +00:00
2020-05-06 05:36:24 +00:00
Vector < CallExpression : : Argument > arguments ;
2020-03-12 18:35:23 +00:00
2020-05-06 05:36:24 +00:00
while ( match_expression ( ) | | match ( TokenType : : TripleDot ) ) {
if ( match ( TokenType : : TripleDot ) ) {
consume ( ) ;
2020-05-11 16:27:31 +00:00
arguments . append ( { parse_expression ( 2 ) , true } ) ;
2020-05-06 05:36:24 +00:00
} else {
2020-05-11 16:27:31 +00:00
arguments . append ( { parse_expression ( 2 ) , false } ) ;
2020-05-06 05:36:24 +00:00
}
2020-03-12 19:03:12 +00:00
if ( ! match ( TokenType : : Comma ) )
break ;
consume ( ) ;
2020-03-12 18:35:23 +00:00
}
2020-03-11 18:27:43 +00:00
consume ( TokenType : : ParenClose ) ;
2020-03-18 10:23:53 +00:00
return create_ast_node < CallExpression > ( move ( lhs ) , move ( arguments ) ) ;
2020-03-11 18:27:43 +00:00
}
2020-03-28 15:33:52 +00:00
NonnullRefPtr < NewExpression > Parser : : parse_new_expression ( )
{
consume ( TokenType : : New ) ;
// FIXME: Support full expressions as the callee as well.
auto callee = create_ast_node < Identifier > ( consume ( TokenType : : Identifier ) . value ( ) ) ;
2020-05-06 05:36:24 +00:00
Vector < CallExpression : : Argument > arguments ;
2020-03-28 15:33:52 +00:00
if ( match ( TokenType : : ParenOpen ) ) {
consume ( TokenType : : ParenOpen ) ;
2020-05-06 05:36:24 +00:00
while ( match_expression ( ) | | match ( TokenType : : TripleDot ) ) {
if ( match ( TokenType : : TripleDot ) ) {
consume ( ) ;
2020-05-11 16:27:31 +00:00
arguments . append ( { parse_expression ( 2 ) , true } ) ;
2020-05-06 05:36:24 +00:00
} else {
2020-05-11 16:27:31 +00:00
arguments . append ( { parse_expression ( 2 ) , false } ) ;
2020-05-06 05:36:24 +00:00
}
2020-03-28 15:33:52 +00:00
if ( ! match ( TokenType : : Comma ) )
break ;
consume ( ) ;
}
consume ( TokenType : : ParenClose ) ;
}
return create_ast_node < NewExpression > ( move ( callee ) , move ( arguments ) ) ;
}
2020-03-18 10:23:53 +00:00
NonnullRefPtr < ReturnStatement > Parser : : parse_return_statement ( )
2020-03-11 18:27:43 +00:00
{
consume ( TokenType : : Return ) ;
2020-04-17 13:05:58 +00:00
// Automatic semicolon insertion: terminate statement when return is followed by newline
if ( m_parser_state . m_current_token . trivia ( ) . contains ( ' \n ' ) )
return create_ast_node < ReturnStatement > ( nullptr ) ;
2020-03-11 18:27:43 +00:00
if ( match_expression ( ) ) {
2020-04-18 12:00:43 +00:00
auto expression = parse_expression ( 0 ) ;
consume_or_insert_semicolon ( ) ;
return create_ast_node < ReturnStatement > ( move ( expression ) ) ;
2020-03-11 18:27:43 +00:00
}
2020-04-18 12:00:43 +00:00
2020-04-17 13:05:58 +00:00
consume_or_insert_semicolon ( ) ;
2020-03-18 10:23:53 +00:00
return create_ast_node < ReturnStatement > ( nullptr ) ;
2020-03-11 18:27:43 +00:00
}
2020-03-18 10:23:53 +00:00
NonnullRefPtr < BlockStatement > Parser : : parse_block_statement ( )
2020-03-11 18:27:43 +00:00
{
2020-04-13 14:42:54 +00:00
ScopePusher scope ( * this , ScopePusher : : Let ) ;
2020-03-18 10:23:53 +00:00
auto block = create_ast_node < BlockStatement > ( ) ;
2020-03-11 18:27:43 +00:00
consume ( TokenType : : CurlyOpen ) ;
while ( ! done ( ) & & ! match ( TokenType : : CurlyClose ) ) {
if ( match ( TokenType : : Semicolon ) ) {
consume ( ) ;
} else if ( match_statement ( ) ) {
block - > append ( parse_statement ( ) ) ;
} else {
expected ( " statement " ) ;
consume ( ) ;
}
}
consume ( TokenType : : CurlyClose ) ;
2020-04-13 14:42:54 +00:00
block - > add_variables ( m_parser_state . m_let_scopes . last ( ) ) ;
2020-03-11 18:27:43 +00:00
return block ;
}
2020-03-19 10:52:56 +00:00
template < typename FunctionNodeType >
2020-05-01 06:40:45 +00:00
NonnullRefPtr < FunctionNodeType > Parser : : parse_function_node ( bool needs_function_keyword )
2020-03-11 18:27:43 +00:00
{
2020-04-13 14:42:54 +00:00
ScopePusher scope ( * this , ScopePusher : : Var ) ;
2020-05-01 06:40:45 +00:00
if ( needs_function_keyword )
consume ( TokenType : : Function ) ;
2020-03-19 10:52:56 +00:00
String name ;
if ( FunctionNodeType : : must_have_name ( ) ) {
name = consume ( TokenType : : Identifier ) . value ( ) ;
} else {
if ( match ( TokenType : : Identifier ) )
name = consume ( TokenType : : Identifier ) . value ( ) ;
}
2020-03-11 18:27:43 +00:00
consume ( TokenType : : ParenOpen ) ;
2020-05-02 18:46:39 +00:00
Vector < FunctionNode : : Parameter > parameters ;
2020-05-06 03:02:14 +00:00
i32 function_length = - 1 ;
2020-05-04 15:05:13 +00:00
while ( match ( TokenType : : Identifier ) | | match ( TokenType : : TripleDot ) ) {
if ( match ( TokenType : : TripleDot ) ) {
consume ( ) ;
auto parameter_name = consume ( TokenType : : Identifier ) . value ( ) ;
2020-05-06 03:02:14 +00:00
function_length = parameters . size ( ) ;
2020-05-04 15:05:13 +00:00
parameters . append ( { parameter_name , nullptr , true } ) ;
break ;
}
2020-05-02 18:46:39 +00:00
auto parameter_name = consume ( TokenType : : Identifier ) . value ( ) ;
RefPtr < Expression > default_value ;
if ( match ( TokenType : : Equals ) ) {
consume ( TokenType : : Equals ) ;
2020-05-06 03:02:14 +00:00
function_length = parameters . size ( ) ;
2020-05-11 16:27:31 +00:00
default_value = parse_expression ( 2 ) ;
2020-05-02 18:46:39 +00:00
}
parameters . append ( { parameter_name , default_value } ) ;
2020-05-04 15:05:13 +00:00
if ( match ( TokenType : : ParenClose ) )
2020-03-11 18:27:43 +00:00
break ;
consume ( TokenType : : Comma ) ;
}
consume ( TokenType : : ParenClose ) ;
2020-05-06 03:02:14 +00:00
if ( function_length = = - 1 )
function_length = parameters . size ( ) ;
2020-05-11 16:27:31 +00:00
2020-03-11 18:27:43 +00:00
auto body = parse_block_statement ( ) ;
2020-04-13 14:42:54 +00:00
body - > add_variables ( m_parser_state . m_var_scopes . last ( ) ) ;
2020-05-06 03:02:14 +00:00
return create_ast_node < FunctionNodeType > ( name , move ( body ) , move ( parameters ) , function_length , NonnullRefPtrVector < VariableDeclaration > ( ) ) ;
2020-03-11 18:27:43 +00:00
}
2020-03-18 10:23:53 +00:00
NonnullRefPtr < VariableDeclaration > Parser : : parse_variable_declaration ( )
2020-03-11 18:27:43 +00:00
{
2020-04-08 09:59:18 +00:00
DeclarationKind declaration_kind ;
2020-03-12 11:16:48 +00:00
2020-03-30 13:24:43 +00:00
switch ( m_parser_state . m_current_token . type ( ) ) {
2020-03-12 11:16:48 +00:00
case TokenType : : Var :
2020-04-08 09:59:18 +00:00
declaration_kind = DeclarationKind : : Var ;
2020-03-12 11:16:48 +00:00
consume ( TokenType : : Var ) ;
break ;
case TokenType : : Let :
2020-04-08 09:59:18 +00:00
declaration_kind = DeclarationKind : : Let ;
2020-03-12 11:16:48 +00:00
consume ( TokenType : : Let ) ;
break ;
2020-03-12 12:24:34 +00:00
case TokenType : : Const :
2020-04-08 09:59:18 +00:00
declaration_kind = DeclarationKind : : Const ;
2020-03-12 12:24:34 +00:00
consume ( TokenType : : Const ) ;
break ;
2020-03-12 11:16:48 +00:00
default :
ASSERT_NOT_REACHED ( ) ;
}
2020-04-04 19:46:25 +00:00
NonnullRefPtrVector < VariableDeclarator > declarations ;
for ( ; ; ) {
auto id = consume ( TokenType : : Identifier ) . value ( ) ;
RefPtr < Expression > init ;
if ( match ( TokenType : : Equals ) ) {
consume ( ) ;
2020-05-11 16:27:31 +00:00
init = parse_expression ( 2 ) ;
2020-04-04 19:46:25 +00:00
}
declarations . append ( create_ast_node < VariableDeclarator > ( create_ast_node < Identifier > ( move ( id ) ) , move ( init ) ) ) ;
if ( match ( TokenType : : Comma ) ) {
consume ( ) ;
continue ;
}
break ;
2020-03-11 18:27:43 +00:00
}
2020-04-17 13:05:58 +00:00
consume_or_insert_semicolon ( ) ;
2020-04-13 14:42:54 +00:00
auto declaration = create_ast_node < VariableDeclaration > ( declaration_kind , move ( declarations ) ) ;
if ( declaration - > declaration_kind ( ) = = DeclarationKind : : Var )
m_parser_state . m_var_scopes . last ( ) . append ( declaration ) ;
else
m_parser_state . m_let_scopes . last ( ) . append ( declaration ) ;
return declaration ;
2020-03-11 18:27:43 +00:00
}
2020-03-24 21:03:50 +00:00
NonnullRefPtr < ThrowStatement > Parser : : parse_throw_statement ( )
{
consume ( TokenType : : Throw ) ;
2020-04-17 13:05:58 +00:00
// Automatic semicolon insertion: terminate statement when throw is followed by newline
if ( m_parser_state . m_current_token . trivia ( ) . contains ( ' \n ' ) ) {
2020-04-29 20:37:51 +00:00
syntax_error ( " No line break is allowed between 'throw' and its expression " ) ;
2020-04-17 13:05:58 +00:00
return create_ast_node < ThrowStatement > ( create_ast_node < ErrorExpression > ( ) ) ;
}
auto expression = parse_expression ( 0 ) ;
consume_or_insert_semicolon ( ) ;
return create_ast_node < ThrowStatement > ( move ( expression ) ) ;
2020-03-24 21:03:50 +00:00
}
2020-03-29 11:09:54 +00:00
NonnullRefPtr < BreakStatement > Parser : : parse_break_statement ( )
{
consume ( TokenType : : Break ) ;
2020-04-17 13:05:58 +00:00
consume_or_insert_semicolon ( ) ;
// FIXME: Handle labels. When fixing this, take care to correctly implement semicolon insertion
2020-03-29 11:09:54 +00:00
return create_ast_node < BreakStatement > ( ) ;
}
2020-04-04 22:22:42 +00:00
NonnullRefPtr < ContinueStatement > Parser : : parse_continue_statement ( )
{
consume ( TokenType : : Continue ) ;
2020-04-17 13:05:58 +00:00
consume_or_insert_semicolon ( ) ;
// FIXME: Handle labels. When fixing this, take care to correctly implement semicolon insertion
2020-04-04 22:22:42 +00:00
return create_ast_node < ContinueStatement > ( ) ;
}
2020-04-03 10:14:28 +00:00
NonnullRefPtr < ConditionalExpression > Parser : : parse_conditional_expression ( NonnullRefPtr < Expression > test )
{
consume ( TokenType : : QuestionMark ) ;
auto consequent = parse_expression ( 0 ) ;
consume ( TokenType : : Colon ) ;
auto alternate = parse_expression ( 0 ) ;
return create_ast_node < ConditionalExpression > ( move ( test ) , move ( consequent ) , move ( alternate ) ) ;
}
2020-03-24 13:03:55 +00:00
NonnullRefPtr < TryStatement > Parser : : parse_try_statement ( )
{
consume ( TokenType : : Try ) ;
auto block = parse_block_statement ( ) ;
RefPtr < CatchClause > handler ;
if ( match ( TokenType : : Catch ) )
handler = parse_catch_clause ( ) ;
RefPtr < BlockStatement > finalizer ;
if ( match ( TokenType : : Finally ) ) {
consume ( ) ;
finalizer = parse_block_statement ( ) ;
}
return create_ast_node < TryStatement > ( move ( block ) , move ( handler ) , move ( finalizer ) ) ;
}
2020-04-04 19:29:23 +00:00
NonnullRefPtr < DoWhileStatement > Parser : : parse_do_while_statement ( )
{
consume ( TokenType : : Do ) ;
2020-04-05 14:57:01 +00:00
2020-04-04 19:29:23 +00:00
auto body = parse_statement ( ) ;
2020-04-05 14:57:01 +00:00
2020-04-04 19:29:23 +00:00
consume ( TokenType : : While ) ;
2020-04-05 14:57:01 +00:00
consume ( TokenType : : ParenOpen ) ;
2020-04-04 19:29:23 +00:00
auto test = parse_expression ( 0 ) ;
2020-04-05 14:57:01 +00:00
consume ( TokenType : : ParenClose ) ;
2020-04-17 13:05:58 +00:00
consume_or_insert_semicolon ( ) ;
2020-04-05 14:57:01 +00:00
2020-04-04 19:29:23 +00:00
return create_ast_node < DoWhileStatement > ( move ( test ) , move ( body ) ) ;
}
2020-04-21 18:27:57 +00:00
NonnullRefPtr < WhileStatement > Parser : : parse_while_statement ( )
{
consume ( TokenType : : While ) ;
consume ( TokenType : : ParenOpen ) ;
auto test = parse_expression ( 0 ) ;
consume ( TokenType : : ParenClose ) ;
auto body = parse_statement ( ) ;
return create_ast_node < WhileStatement > ( move ( test ) , move ( body ) ) ;
}
2020-03-29 11:09:54 +00:00
NonnullRefPtr < SwitchStatement > Parser : : parse_switch_statement ( )
{
consume ( TokenType : : Switch ) ;
consume ( TokenType : : ParenOpen ) ;
auto determinant = parse_expression ( 0 ) ;
consume ( TokenType : : ParenClose ) ;
consume ( TokenType : : CurlyOpen ) ;
NonnullRefPtrVector < SwitchCase > cases ;
while ( match ( TokenType : : Case ) | | match ( TokenType : : Default ) )
cases . append ( parse_switch_case ( ) ) ;
consume ( TokenType : : CurlyClose ) ;
return create_ast_node < SwitchStatement > ( move ( determinant ) , move ( cases ) ) ;
}
NonnullRefPtr < SwitchCase > Parser : : parse_switch_case ( )
{
RefPtr < Expression > test ;
if ( consume ( ) . type ( ) = = TokenType : : Case ) {
test = parse_expression ( 0 ) ;
}
consume ( TokenType : : Colon ) ;
NonnullRefPtrVector < Statement > consequent ;
while ( match_statement ( ) )
consequent . append ( parse_statement ( ) ) ;
return create_ast_node < SwitchCase > ( move ( test ) , move ( consequent ) ) ;
}
2020-03-24 13:03:55 +00:00
NonnullRefPtr < CatchClause > Parser : : parse_catch_clause ( )
{
consume ( TokenType : : Catch ) ;
String parameter ;
if ( match ( TokenType : : ParenOpen ) ) {
consume ( ) ;
parameter = consume ( TokenType : : Identifier ) . value ( ) ;
consume ( TokenType : : ParenClose ) ;
}
auto body = parse_block_statement ( ) ;
return create_ast_node < CatchClause > ( parameter , move ( body ) ) ;
}
2020-03-21 17:40:17 +00:00
NonnullRefPtr < IfStatement > Parser : : parse_if_statement ( )
{
consume ( TokenType : : If ) ;
consume ( TokenType : : ParenOpen ) ;
auto predicate = parse_expression ( 0 ) ;
consume ( TokenType : : ParenClose ) ;
2020-03-23 15:46:41 +00:00
auto consequent = parse_statement ( ) ;
RefPtr < Statement > alternate ;
if ( match ( TokenType : : Else ) ) {
consume ( TokenType : : Else ) ;
alternate = parse_statement ( ) ;
}
return create_ast_node < IfStatement > ( move ( predicate ) , move ( consequent ) , move ( alternate ) ) ;
2020-03-21 17:40:17 +00:00
}
2020-03-18 10:23:53 +00:00
NonnullRefPtr < ForStatement > Parser : : parse_for_statement ( )
2020-03-12 12:12:12 +00:00
{
consume ( TokenType : : For ) ;
consume ( TokenType : : ParenOpen ) ;
2020-04-17 13:05:58 +00:00
bool first_semicolon_consumed = false ;
2020-05-04 22:58:53 +00:00
bool in_scope = false ;
2020-03-23 18:08:32 +00:00
RefPtr < ASTNode > init ;
2020-03-30 13:24:43 +00:00
switch ( m_parser_state . m_current_token . type ( ) ) {
2020-03-12 12:12:12 +00:00
case TokenType : : Semicolon :
break ;
default :
2020-04-17 13:05:58 +00:00
if ( match_expression ( ) ) {
2020-03-23 18:08:32 +00:00
init = parse_expression ( 0 ) ;
2020-04-17 13:05:58 +00:00
} else if ( match_variable_declaration ( ) ) {
2020-05-04 22:58:53 +00:00
if ( m_parser_state . m_current_token . type ( ) ! = TokenType : : Var ) {
m_parser_state . m_let_scopes . append ( NonnullRefPtrVector < VariableDeclaration > ( ) ) ;
in_scope = true ;
}
2020-03-23 18:08:32 +00:00
init = parse_variable_declaration ( ) ;
2020-04-17 13:05:58 +00:00
first_semicolon_consumed = true ;
} else {
2020-03-23 18:08:32 +00:00
ASSERT_NOT_REACHED ( ) ;
2020-04-17 13:05:58 +00:00
}
2020-03-12 12:12:12 +00:00
break ;
}
2020-04-17 13:05:58 +00:00
if ( ! first_semicolon_consumed )
consume ( TokenType : : Semicolon ) ;
2020-03-12 12:12:12 +00:00
2020-03-18 10:23:53 +00:00
RefPtr < Expression > test ;
2020-03-30 13:24:43 +00:00
switch ( m_parser_state . m_current_token . type ( ) ) {
2020-03-12 12:12:12 +00:00
case TokenType : : Semicolon :
break ;
default :
2020-03-12 22:02:41 +00:00
test = parse_expression ( 0 ) ;
2020-03-12 12:12:12 +00:00
break ;
}
consume ( TokenType : : Semicolon ) ;
2020-03-18 10:23:53 +00:00
RefPtr < Expression > update ;
2020-03-30 13:24:43 +00:00
switch ( m_parser_state . m_current_token . type ( ) ) {
2020-03-25 15:14:18 +00:00
case TokenType : : ParenClose :
2020-03-12 12:12:12 +00:00
break ;
default :
2020-03-12 22:02:41 +00:00
update = parse_expression ( 0 ) ;
2020-03-12 12:12:12 +00:00
break ;
}
consume ( TokenType : : ParenClose ) ;
2020-04-04 19:09:06 +00:00
auto body = parse_statement ( ) ;
2020-03-12 12:12:12 +00:00
2020-05-04 22:58:53 +00:00
if ( in_scope ) {
m_parser_state . m_let_scopes . take_last ( ) ;
}
2020-03-18 10:23:53 +00:00
return create_ast_node < ForStatement > ( move ( init ) , move ( test ) , move ( update ) , move ( body ) ) ;
2020-03-12 12:12:12 +00:00
}
2020-04-30 16:26:27 +00:00
NonnullRefPtr < DebuggerStatement > Parser : : parse_debugger_statement ( )
{
consume ( TokenType : : Debugger ) ;
consume_or_insert_semicolon ( ) ;
return create_ast_node < DebuggerStatement > ( ) ;
}
2020-03-11 18:27:43 +00:00
bool Parser : : match ( TokenType type ) const
{
2020-03-30 13:24:43 +00:00
return m_parser_state . m_current_token . type ( ) = = type ;
2020-03-11 18:27:43 +00:00
}
2020-03-23 18:08:32 +00:00
bool Parser : : match_variable_declaration ( ) const
{
2020-03-30 13:24:43 +00:00
switch ( m_parser_state . m_current_token . type ( ) ) {
2020-03-23 18:08:32 +00:00
case TokenType : : Var :
case TokenType : : Let :
case TokenType : : Const :
return true ;
default :
return false ;
}
}
2020-03-11 18:27:43 +00:00
bool Parser : : match_expression ( ) const
{
2020-03-30 13:24:43 +00:00
auto type = m_parser_state . m_current_token . type ( ) ;
2020-03-11 18:27:43 +00:00
return type = = TokenType : : BoolLiteral
| | type = = TokenType : : NumericLiteral
| | type = = TokenType : : StringLiteral
LibJS: Add template literals
Adds fully functioning template literals. Because template literals
contain expressions, most of the work has to be done in the Lexer rather
than the Parser. And because of the complexity of template literals
(expressions, nesting, escapes, etc), the Lexer needs to have some
template-related state.
When entering a new template literal, a TemplateLiteralStart token is
emitted. When inside a literal, all text will be parsed up until a '${'
or '`' (or EOF, but that's a syntax error) is seen, and then a
TemplateLiteralExprStart token is emitted. At this point, the Lexer
proceeds as normal, however it keeps track of the number of opening
and closing curly braces it has seen in order to determine the close
of the expression. Once it finds a matching curly brace for the '${',
a TemplateLiteralExprEnd token is emitted and the state is updated
accordingly.
When the Lexer is inside of a template literal, but not an expression,
and sees a '`', this must be the closing grave: a TemplateLiteralEnd
token is emitted.
The state required to correctly parse template strings consists of a
vector (for nesting) of two pieces of information: whether or not we
are in a template expression (as opposed to a template string); and
the count of the number of unmatched open curly braces we have seen
(only applicable if the Lexer is currently in a template expression).
TODO: Add support for template literal newlines in the JS REPL (this will
cause a syntax error currently):
> `foo
> bar`
'foo
bar'
2020-05-03 22:41:14 +00:00
| | type = = TokenType : : TemplateLiteralStart
2020-03-11 18:27:43 +00:00
| | type = = TokenType : : NullLiteral
| | type = = TokenType : : Identifier
| | type = = TokenType : : New
| | type = = TokenType : : CurlyOpen
| | type = = TokenType : : BracketOpen
2020-03-14 18:45:51 +00:00
| | type = = TokenType : : ParenOpen
2020-03-19 10:52:56 +00:00
| | type = = TokenType : : Function
2020-04-12 22:42:14 +00:00
| | type = = TokenType : : This
2020-03-14 18:45:51 +00:00
| | match_unary_prefixed_expression ( ) ;
}
bool Parser : : match_unary_prefixed_expression ( ) const
{
2020-03-30 13:24:43 +00:00
auto type = m_parser_state . m_current_token . type ( ) ;
2020-03-14 18:45:51 +00:00
return type = = TokenType : : PlusPlus
| | type = = TokenType : : MinusMinus
| | type = = TokenType : : ExclamationMark
2020-03-17 19:33:32 +00:00
| | type = = TokenType : : Tilde
2020-04-02 16:58:39 +00:00
| | type = = TokenType : : Plus
| | type = = TokenType : : Minus
2020-04-15 16:55:03 +00:00
| | type = = TokenType : : Typeof
2020-04-26 11:53:40 +00:00
| | type = = TokenType : : Void
| | type = = TokenType : : Delete ;
2020-03-11 18:27:43 +00:00
}
bool Parser : : match_secondary_expression ( ) const
{
2020-03-30 13:24:43 +00:00
auto type = m_parser_state . m_current_token . type ( ) ;
2020-03-11 18:27:43 +00:00
return type = = TokenType : : Plus
2020-03-12 12:09:15 +00:00
| | type = = TokenType : : PlusEquals
2020-03-11 18:27:43 +00:00
| | type = = TokenType : : Minus
2020-03-12 12:09:15 +00:00
| | type = = TokenType : : MinusEquals
2020-03-11 18:27:43 +00:00
| | type = = TokenType : : Asterisk
2020-03-12 12:09:15 +00:00
| | type = = TokenType : : AsteriskEquals
2020-03-11 18:27:43 +00:00
| | type = = TokenType : : Slash
2020-03-12 12:09:15 +00:00
| | type = = TokenType : : SlashEquals
2020-04-04 19:17:34 +00:00
| | type = = TokenType : : Percent
2020-05-04 22:07:05 +00:00
| | type = = TokenType : : PercentEquals
2020-04-05 12:40:00 +00:00
| | type = = TokenType : : DoubleAsterisk
2020-05-04 22:03:35 +00:00
| | type = = TokenType : : DoubleAsteriskEquals
2020-03-11 18:27:43 +00:00
| | type = = TokenType : : Equals
2020-03-12 12:11:33 +00:00
| | type = = TokenType : : EqualsEqualsEquals
| | type = = TokenType : : ExclamationMarkEqualsEquals
2020-03-15 22:23:38 +00:00
| | type = = TokenType : : EqualsEquals
| | type = = TokenType : : ExclamationMarkEquals
2020-03-12 12:10:27 +00:00
| | type = = TokenType : : GreaterThan
2020-03-12 12:07:08 +00:00
| | type = = TokenType : : GreaterThanEquals
2020-03-12 12:10:27 +00:00
| | type = = TokenType : : LessThan
2020-03-12 12:07:08 +00:00
| | type = = TokenType : : LessThanEquals
2020-03-12 12:05:57 +00:00
| | type = = TokenType : : ParenOpen
2020-03-12 11:45:45 +00:00
| | type = = TokenType : : Period
2020-03-20 19:51:03 +00:00
| | type = = TokenType : : BracketOpen
2020-03-12 11:45:45 +00:00
| | type = = TokenType : : PlusPlus
2020-03-28 15:56:54 +00:00
| | type = = TokenType : : MinusMinus
2020-04-23 15:06:01 +00:00
| | type = = TokenType : : In
2020-04-03 10:14:28 +00:00
| | type = = TokenType : : Instanceof
2020-04-03 12:02:31 +00:00
| | type = = TokenType : : QuestionMark
| | type = = TokenType : : Ampersand
2020-05-04 21:34:45 +00:00
| | type = = TokenType : : AmpersandEquals
2020-04-03 12:02:31 +00:00
| | type = = TokenType : : Pipe
2020-05-04 21:34:45 +00:00
| | type = = TokenType : : PipeEquals
2020-04-03 13:33:28 +00:00
| | type = = TokenType : : Caret
2020-05-04 21:34:45 +00:00
| | type = = TokenType : : CaretEquals
2020-04-23 12:36:14 +00:00
| | type = = TokenType : : ShiftLeft
| | type = = TokenType : : ShiftLeftEquals
2020-04-23 12:45:19 +00:00
| | type = = TokenType : : ShiftRight
| | type = = TokenType : : ShiftRightEquals
2020-04-23 14:43:10 +00:00
| | type = = TokenType : : UnsignedShiftRight
| | type = = TokenType : : UnsignedShiftRightEquals
2020-04-03 13:33:28 +00:00
| | type = = TokenType : : DoubleAmpersand
2020-04-17 23:49:11 +00:00
| | type = = TokenType : : DoublePipe
| | type = = TokenType : : DoubleQuestionMark ;
2020-03-11 18:27:43 +00:00
}
bool Parser : : match_statement ( ) const
{
2020-03-30 13:24:43 +00:00
auto type = m_parser_state . m_current_token . type ( ) ;
2020-03-11 18:27:43 +00:00
return match_expression ( )
| | type = = TokenType : : Function
| | type = = TokenType : : Return
| | type = = TokenType : : Let
| | type = = TokenType : : Class
| | type = = TokenType : : Do
| | type = = TokenType : : If
2020-03-24 21:03:50 +00:00
| | type = = TokenType : : Throw
2020-03-11 18:27:43 +00:00
| | type = = TokenType : : Try
| | type = = TokenType : : While
2020-03-12 12:12:12 +00:00
| | type = = TokenType : : For
2020-03-11 18:27:43 +00:00
| | type = = TokenType : : Const
| | type = = TokenType : : CurlyOpen
2020-03-29 11:09:54 +00:00
| | type = = TokenType : : Switch
| | type = = TokenType : : Break
2020-04-04 22:22:42 +00:00
| | type = = TokenType : : Continue
2020-04-30 16:26:27 +00:00
| | type = = TokenType : : Var
2020-05-03 09:59:00 +00:00
| | type = = TokenType : : Debugger
| | type = = TokenType : : Semicolon ;
2020-03-11 18:27:43 +00:00
}
2020-04-18 18:31:27 +00:00
bool Parser : : match_identifier_name ( ) const
{
return m_parser_state . m_current_token . is_identifier_name ( ) ;
}
2020-03-11 18:27:43 +00:00
bool Parser : : done ( ) const
{
return match ( TokenType : : Eof ) ;
}
Token Parser : : consume ( )
{
2020-03-30 13:24:43 +00:00
auto old_token = m_parser_state . m_current_token ;
m_parser_state . m_current_token = m_parser_state . m_lexer . next ( ) ;
2020-03-12 22:02:41 +00:00
return old_token ;
2020-03-11 18:27:43 +00:00
}
2020-04-17 13:05:58 +00:00
void Parser : : consume_or_insert_semicolon ( )
2020-03-11 18:27:43 +00:00
{
2020-04-17 13:05:58 +00:00
// Semicolon was found and will be consumed
if ( match ( TokenType : : Semicolon ) ) {
consume ( ) ;
return ;
}
// Insert semicolon if...
// ...token is preceeded by one or more newlines
if ( m_parser_state . m_current_token . trivia ( ) . contains ( ' \n ' ) )
return ;
2020-04-17 13:27:51 +00:00
// ...token is a closing curly brace
if ( match ( TokenType : : CurlyClose ) )
2020-04-17 13:05:58 +00:00
return ;
// ...token is eof
if ( match ( TokenType : : Eof ) )
return ;
// No rule for semicolon insertion applies -> syntax error
expected ( " Semicolon " ) ;
}
Token Parser : : consume ( TokenType expected_type )
{
if ( m_parser_state . m_current_token . type ( ) ! = expected_type ) {
expected ( Token : : name ( expected_type ) ) ;
2020-03-11 18:27:43 +00:00
}
return consume ( ) ;
}
void Parser : : expected ( const char * what )
2020-04-29 20:37:51 +00:00
{
syntax_error ( String : : format ( " Unexpected token %s. Expected %s " , m_parser_state . m_current_token . name ( ) , what ) ) ;
}
void Parser : : syntax_error ( const String & message , size_t line , size_t column )
2020-03-11 18:27:43 +00:00
{
2020-04-29 20:37:51 +00:00
if ( line = = 0 | | column = = 0 ) {
line = m_parser_state . m_current_token . line_number ( ) ;
column = m_parser_state . m_current_token . line_column ( ) ;
}
2020-05-14 15:26:01 +00:00
m_parser_state . m_errors . append ( { message , line , column } ) ;
2020-03-11 18:27:43 +00:00
}
2020-03-30 13:24:43 +00:00
void Parser : : save_state ( )
{
2020-05-02 18:46:39 +00:00
m_saved_state . append ( m_parser_state ) ;
2020-03-30 13:24:43 +00:00
}
void Parser : : load_state ( )
{
2020-05-02 18:46:39 +00:00
ASSERT ( ! m_saved_state . is_empty ( ) ) ;
m_parser_state = m_saved_state . take_last ( ) ;
2020-03-30 13:24:43 +00:00
}
2020-04-29 20:37:51 +00:00
2020-03-11 18:27:43 +00:00
}