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"
2020-04-13 14:42:54 +00:00
# include <AK/ScopeGuard.h>
2020-03-11 18:27:43 +00:00
# include <AK/StdLibExtras.h>
2020-10-15 18:46:52 +00:00
# include <AK/TemporaryChange.h>
2020-10-19 17:01:28 +00:00
# include <ctype.h>
2020-03-11 18:27:43 +00:00
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 ,
2020-06-04 12:48:36 +00:00
Function = 3 ,
2020-04-13 14:42:54 +00:00
} ;
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 > ( ) ) ;
2020-06-04 12:48:36 +00:00
if ( m_mask & Function )
m_parser . m_parser_state . m_function_scopes . append ( NonnullRefPtrVector < FunctionDeclaration > ( ) ) ;
2020-04-13 14:42:54 +00:00
}
~ 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 ( ) ;
2020-06-04 12:48:36 +00:00
if ( m_mask & Function )
m_parser . m_parser_state . m_function_scopes . take_last ( ) ;
2020-04-13 14:42:54 +00:00
}
Parser & m_parser ;
unsigned m_mask { 0 } ;
} ;
2020-08-18 16:46:36 +00:00
class OperatorPrecedenceTable {
public :
constexpr OperatorPrecedenceTable ( )
: m_token_precedence ( )
{
for ( size_t i = 0 ; i < array_size ( m_operator_precedence ) ; + + i ) {
auto & op = m_operator_precedence [ i ] ;
m_token_precedence [ static_cast < size_t > ( op . token ) ] = op . precedence ;
}
}
2020-03-30 13:24:43 +00:00
2020-08-18 16:46:36 +00:00
constexpr int get ( TokenType token ) const
{
int p = m_token_precedence [ static_cast < size_t > ( token ) ] ;
if ( p = = 0 ) {
fprintf ( stderr , " Internal Error: No precedence for operator %s \n " , Token : : name ( token ) ) ;
ASSERT_NOT_REACHED ( ) ;
return - 1 ;
}
2020-03-12 22:02:41 +00:00
2020-08-18 16:46:36 +00:00
return p ;
}
2020-03-12 22:02:41 +00:00
2020-08-18 16:46:36 +00:00
private :
int m_token_precedence [ cs_num_of_js_tokens ] ;
2020-03-12 22:02:41 +00:00
2020-08-18 16:46:36 +00:00
struct OperatorPrecedence {
TokenType token ;
int precedence ;
} ;
2020-03-12 22:02:41 +00:00
2020-08-18 16:46:36 +00:00
// https://developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/Operators/Operator_Precedence
static constexpr const OperatorPrecedence m_operator_precedence [ ] = {
{ TokenType : : Period , 20 } ,
{ TokenType : : BracketOpen , 20 } ,
{ TokenType : : ParenOpen , 20 } ,
{ TokenType : : QuestionMarkPeriod , 20 } ,
2020-03-12 22:02:41 +00:00
2020-08-18 16:46:36 +00:00
{ TokenType : : New , 19 } ,
2020-03-12 22:02:41 +00:00
2020-08-18 16:46:36 +00:00
{ TokenType : : PlusPlus , 18 } ,
{ TokenType : : MinusMinus , 18 } ,
2020-03-12 22:02:41 +00:00
2020-08-18 16:46:36 +00:00
{ TokenType : : ExclamationMark , 17 } ,
{ TokenType : : Tilde , 17 } ,
{ TokenType : : Typeof , 17 } ,
{ TokenType : : Void , 17 } ,
{ TokenType : : Delete , 17 } ,
{ TokenType : : Await , 17 } ,
2020-03-12 22:02:41 +00:00
2020-08-18 16:46:36 +00:00
{ TokenType : : DoubleAsterisk , 16 } ,
2020-03-12 22:02:41 +00:00
2020-08-18 16:46:36 +00:00
{ TokenType : : Asterisk , 15 } ,
{ TokenType : : Slash , 15 } ,
{ TokenType : : Percent , 15 } ,
2020-03-12 22:02:41 +00:00
2020-08-18 16:46:36 +00:00
{ TokenType : : Plus , 14 } ,
{ TokenType : : Minus , 14 } ,
2020-03-12 22:02:41 +00:00
2020-08-18 16:46:36 +00:00
{ TokenType : : ShiftLeft , 13 } ,
{ TokenType : : ShiftRight , 13 } ,
{ TokenType : : UnsignedShiftRight , 13 } ,
2020-03-12 22:02:41 +00:00
2020-08-18 16:46:36 +00:00
{ TokenType : : LessThan , 12 } ,
{ TokenType : : LessThanEquals , 12 } ,
{ TokenType : : GreaterThan , 12 } ,
{ TokenType : : GreaterThanEquals , 12 } ,
{ TokenType : : In , 12 } ,
{ TokenType : : Instanceof , 12 } ,
2020-03-12 22:02:41 +00:00
2020-08-18 16:46:36 +00:00
{ TokenType : : EqualsEquals , 11 } ,
{ TokenType : : ExclamationMarkEquals , 11 } ,
{ TokenType : : EqualsEqualsEquals , 11 } ,
{ TokenType : : ExclamationMarkEqualsEquals , 11 } ,
2020-03-12 22:02:41 +00:00
2020-08-18 16:46:36 +00:00
{ TokenType : : Ampersand , 10 } ,
2020-03-12 22:02:41 +00:00
2020-08-18 16:46:36 +00:00
{ TokenType : : Caret , 9 } ,
2020-03-12 22:02:41 +00:00
2020-08-18 16:46:36 +00:00
{ TokenType : : Pipe , 8 } ,
2020-03-12 22:02:41 +00:00
2020-08-18 16:46:36 +00:00
{ TokenType : : DoubleQuestionMark , 7 } ,
2020-03-12 22:02:41 +00:00
2020-08-18 16:46:36 +00:00
{ TokenType : : DoubleAmpersand , 6 } ,
2020-03-12 22:02:41 +00:00
2020-08-18 16:46:36 +00:00
{ TokenType : : DoublePipe , 5 } ,
{ TokenType : : QuestionMark , 4 } ,
{ TokenType : : Equals , 3 } ,
{ TokenType : : PlusEquals , 3 } ,
{ TokenType : : MinusEquals , 3 } ,
{ TokenType : : DoubleAsteriskEquals , 3 } ,
{ TokenType : : AsteriskEquals , 3 } ,
{ TokenType : : SlashEquals , 3 } ,
{ TokenType : : PercentEquals , 3 } ,
{ TokenType : : ShiftLeftEquals , 3 } ,
{ TokenType : : ShiftRightEquals , 3 } ,
{ TokenType : : UnsignedShiftRightEquals , 3 } ,
{ TokenType : : AmpersandEquals , 3 } ,
{ TokenType : : CaretEquals , 3 } ,
2020-10-05 15:49:43 +00:00
{ TokenType : : PipeEquals , 3 } ,
{ TokenType : : DoubleAmpersandEquals , 3 } ,
{ TokenType : : DoublePipeEquals , 3 } ,
{ TokenType : : DoubleQuestionMarkEquals , 3 } ,
2020-08-18 16:46:36 +00:00
{ TokenType : : Yield , 2 } ,
{ TokenType : : Comma , 1 } ,
} ;
} ;
constexpr OperatorPrecedenceTable g_operator_precedence ;
2020-03-12 22:02:41 +00:00
2020-08-18 16:46:36 +00:00
Parser : : ParserState : : ParserState ( Lexer lexer )
: m_lexer ( move ( lexer ) )
, m_current_token ( m_lexer . next ( ) )
2020-03-12 22:02:41 +00:00
{
2020-08-18 16:46:36 +00:00
}
2020-03-12 22:02:41 +00:00
2020-08-18 16:46:36 +00:00
Parser : : Parser ( Lexer lexer )
: m_parser_state ( move ( lexer ) )
{
2020-03-12 22:02:41 +00:00
}
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
{
2020-06-04 12:48:36 +00:00
ScopePusher scope ( * this , ScopePusher : : Var | ScopePusher : : Let | ScopePusher : : Function ) ;
2020-03-18 10:23:53 +00:00
auto program = adopt ( * new Program ) ;
2020-05-28 05:22:08 +00:00
bool first = true ;
m_parser_state . m_use_strict_directive = UseStrictDirectiveState : : Looking ;
2020-03-11 18:27:43 +00:00
while ( ! done ( ) ) {
2020-10-22 22:30:07 +00:00
if ( match_declaration ( ) ) {
program - > append ( parse_declaration ( ) ) ;
if ( first ) {
first = false ;
m_parser_state . m_use_strict_directive = UseStrictDirectiveState : : None ;
}
} else if ( match_statement ( ) ) {
2020-03-11 18:27:43 +00:00
program - > append ( parse_statement ( ) ) ;
2020-05-28 05:22:08 +00:00
if ( first ) {
if ( m_parser_state . m_use_strict_directive = = UseStrictDirectiveState : : Found ) {
program - > set_strict_mode ( ) ;
m_parser_state . m_strict_mode = true ;
}
first = false ;
m_parser_state . m_use_strict_directive = UseStrictDirectiveState : : None ;
}
2020-03-11 18:27:43 +00:00
} else {
2020-10-22 22:30:07 +00:00
expected ( " statement or declaration " ) ;
2020-03-11 18:27:43 +00:00
consume ( ) ;
}
}
2020-06-01 14:08:34 +00:00
if ( 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 ( ) ) ;
2020-06-04 12:48:36 +00:00
program - > add_functions ( m_parser_state . m_function_scopes . last ( ) ) ;
2020-06-01 14:08:34 +00:00
} else {
syntax_error ( " Unclosed scope " ) ;
}
2020-03-11 18:27:43 +00:00
return program ;
}
2020-10-22 22:30:07 +00:00
NonnullRefPtr < Declaration > Parser : : parse_declaration ( )
2020-03-11 18:27:43 +00:00
{
2020-03-30 13:24:43 +00:00
switch ( m_parser_state . m_current_token . type ( ) ) {
2020-06-08 18:31:21 +00:00
case TokenType : : Class :
2020-08-29 11:25:37 +00:00
return parse_class_declaration ( ) ;
2020-06-04 12:48:36 +00:00
case TokenType : : Function : {
auto declaration = parse_function_node < FunctionDeclaration > ( ) ;
m_parser_state . m_function_scopes . last ( ) . append ( declaration ) ;
return declaration ;
}
2020-10-22 22:30:07 +00:00
case TokenType : : Let :
case TokenType : : Const :
return parse_variable_declaration ( ) ;
default :
expected ( " declaration " ) ;
consume ( ) ;
return create_ast_node < ErrorDeclaration > ( ) ;
}
}
NonnullRefPtr < Statement > Parser : : parse_statement ( )
{
switch ( m_parser_state . m_current_token . type ( ) ) {
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 :
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 :
2020-08-29 11:25:37 +00:00
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 :
2020-08-29 11:25:37 +00:00
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 :
2020-05-28 20:36:59 +00:00
if ( match ( TokenType : : Identifier ) ) {
auto result = try_parse_labelled_statement ( ) ;
if ( ! result . is_null ( ) )
return result . release_nonnull ( ) ;
}
2020-04-17 13:05:58 +00:00
if ( match_expression ( ) ) {
2020-10-22 22:30:07 +00:00
if ( match ( TokenType : : Function ) )
syntax_error ( " Function declaration not allowed in single-statement context " ) ;
2020-04-17 13:05:58 +00:00
auto expr = parse_expression ( 0 ) ;
consume_or_insert_semicolon ( ) ;
return create_ast_node < ExpressionStatement > ( move ( expr ) ) ;
}
2020-10-22 22:30:07 +00:00
expected ( " statement " ) ;
2020-03-11 18:27:43 +00:00
consume ( ) ;
2020-03-18 10:23:53 +00:00
return create_ast_node < ErrorStatement > ( ) ;
2020-08-29 11:25:37 +00:00
}
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 ;
2020-05-06 03:02:14 +00:00
i32 function_length = - 1 ;
2020-10-18 23:26:41 +00:00
if ( expect_parens ) {
// We have parens around the function parameters and can re-use the same parsing
// logic used for regular functions: multiple parameters, default values, rest
// parameter, maybe a trailing comma. If we have a new syntax error afterwards we
// know parsing failed and rollback the parser state.
auto previous_syntax_errors = m_parser_state . m_errors . size ( ) ;
parameters = parse_function_parameters ( function_length ) ;
if ( m_parser_state . m_errors . size ( ) > previous_syntax_errors )
return nullptr ;
if ( ! match ( TokenType : : ParenClose ) )
return nullptr ;
consume ( ) ;
} else {
// No parens - this must be an identifier followed by arrow. That's it.
if ( ! match ( TokenType : : Identifier ) )
return nullptr ;
parameters . append ( { consume ( ) . value ( ) , { } } ) ;
2020-03-30 13:26:09 +00:00
}
2020-10-18 23:29:17 +00:00
// If there's a newline between the closing paren and arrow it's not a valid arrow function,
// ASI should kick in instead (it'll then fail with "Unexpected token Arrow")
2020-10-21 21:16:45 +00:00
if ( m_parser_state . m_current_token . trivia_contains_line_terminator ( ) )
2020-10-18 23:29:17 +00:00
return nullptr ;
2020-10-18 23:26:41 +00:00
if ( ! match ( TokenType : : Arrow ) )
2020-03-30 13:26:09 +00:00
return nullptr ;
2020-10-18 23:26:41 +00:00
consume ( ) ;
2020-03-30 13:26:09 +00:00
2020-05-11 16:27:31 +00:00
if ( function_length = = - 1 )
2020-05-06 03:02:14 +00:00
function_length = parameters . size ( ) ;
2020-10-08 17:49:08 +00:00
auto old_labels_in_scope = move ( m_parser_state . m_labels_in_scope ) ;
ScopeGuard guard ( [ & ] ( ) {
m_parser_state . m_labels_in_scope = move ( old_labels_in_scope ) ;
} ) ;
2020-10-04 00:02:43 +00:00
bool is_strict = false ;
auto function_body_result = [ & ] ( ) - > RefPtr < BlockStatement > {
2020-10-07 18:33:48 +00:00
TemporaryChange change ( m_parser_state . m_in_function_context , true ) ;
2020-03-30 13:26:09 +00:00
if ( match ( TokenType : : CurlyOpen ) ) {
// Parse a function body with statements
2020-10-04 00:02:43 +00:00
return parse_block_statement ( is_strict ) ;
2020-03-30 13:26:09 +00:00
}
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.
2020-05-29 20:03:47 +00:00
auto return_expression = parse_expression ( 2 ) ;
2020-03-30 13:26:09 +00:00
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 ( ) ;
2020-10-04 00:02:43 +00:00
return create_ast_node < FunctionExpression > ( " " , move ( body ) , move ( parameters ) , function_length , m_parser_state . m_var_scopes . take_last ( ) , is_strict , true ) ;
2020-03-30 13:26:09 +00:00
}
return nullptr ;
}
2020-05-28 18:09:19 +00:00
RefPtr < Statement > Parser : : try_parse_labelled_statement ( )
{
save_state ( ) ;
ArmedScopeGuard state_rollback_guard = [ & ] {
load_state ( ) ;
} ;
auto identifier = consume ( TokenType : : Identifier ) . value ( ) ;
if ( ! match ( TokenType : : Colon ) )
return { } ;
consume ( TokenType : : Colon ) ;
if ( ! match_statement ( ) )
return { } ;
2020-10-08 17:49:08 +00:00
m_parser_state . m_labels_in_scope . set ( identifier ) ;
2020-05-28 18:09:19 +00:00
auto statement = parse_statement ( ) ;
2020-10-08 17:49:08 +00:00
m_parser_state . m_labels_in_scope . remove ( identifier ) ;
2020-05-28 18:09:19 +00:00
statement - > set_label ( identifier ) ;
state_rollback_guard . disarm ( ) ;
return statement ;
}
2020-06-08 18:31:21 +00:00
NonnullRefPtr < ClassDeclaration > Parser : : parse_class_declaration ( )
{
return create_ast_node < ClassDeclaration > ( parse_class_expression ( true ) ) ;
}
NonnullRefPtr < ClassExpression > Parser : : parse_class_expression ( bool expect_class_name )
{
// Classes are always in strict mode.
TemporaryChange strict_mode_rollback ( m_parser_state . m_strict_mode , true ) ;
consume ( TokenType : : Class ) ;
NonnullRefPtrVector < ClassMethod > methods ;
RefPtr < Expression > super_class ;
RefPtr < FunctionExpression > constructor ;
String class_name = expect_class_name | | match ( TokenType : : Identifier ) ? consume ( TokenType : : Identifier ) . value ( ) . to_string ( ) : " " ;
if ( match ( TokenType : : Extends ) ) {
consume ( ) ;
super_class = parse_primary_expression ( ) ;
}
consume ( TokenType : : CurlyOpen ) ;
while ( ! done ( ) & & ! match ( TokenType : : CurlyClose ) ) {
RefPtr < Expression > property_key ;
bool is_static = false ;
bool is_constructor = false ;
auto method_kind = ClassMethod : : Kind : : Method ;
if ( match ( TokenType : : Semicolon ) ) {
consume ( ) ;
continue ;
}
if ( match_property_key ( ) ) {
StringView name ;
if ( match ( TokenType : : Identifier ) & & m_parser_state . m_current_token . value ( ) = = " static " ) {
consume ( ) ;
is_static = true ;
}
if ( match ( TokenType : : Identifier ) ) {
auto identifier_name = m_parser_state . m_current_token . value ( ) ;
if ( identifier_name = = " get " ) {
method_kind = ClassMethod : : Kind : : Getter ;
consume ( ) ;
} else if ( identifier_name = = " set " ) {
method_kind = ClassMethod : : Kind : : Setter ;
consume ( ) ;
}
}
if ( match_property_key ( ) ) {
switch ( m_parser_state . m_current_token . type ( ) ) {
case TokenType : : Identifier :
name = consume ( ) . value ( ) ;
property_key = create_ast_node < StringLiteral > ( name ) ;
break ;
case TokenType : : StringLiteral : {
auto string_literal = parse_string_literal ( consume ( ) ) ;
name = string_literal - > value ( ) ;
property_key = move ( string_literal ) ;
break ;
}
default :
property_key = parse_property_key ( ) ;
break ;
}
} else {
expected ( " property key " ) ;
}
// Constructor may be a StringLiteral or an Identifier.
if ( ! is_static & & name = = " constructor " ) {
if ( method_kind ! = ClassMethod : : Kind : : Method )
syntax_error ( " Class constructor may not be an accessor " ) ;
if ( ! constructor . is_null ( ) )
syntax_error ( " Classes may not have more than one constructor " ) ;
is_constructor = true ;
}
}
if ( match ( TokenType : : ParenOpen ) ) {
2020-10-20 16:56:49 +00:00
u8 parse_options = FunctionNodeParseOptions : : AllowSuperPropertyLookup ;
if ( ! super_class . is_null ( ) )
parse_options | = FunctionNodeParseOptions : : AllowSuperConstructorCall ;
2020-10-20 17:32:51 +00:00
if ( method_kind = = ClassMethod : : Kind : : Getter )
parse_options | = FunctionNodeParseOptions : : IsGetterFunction ;
if ( method_kind = = ClassMethod : : Kind : : Setter )
parse_options | = FunctionNodeParseOptions : : IsSetterFunction ;
2020-10-20 16:56:49 +00:00
auto function = parse_function_node < FunctionExpression > ( parse_options ) ;
2020-06-08 18:31:21 +00:00
if ( is_constructor ) {
constructor = move ( function ) ;
} else if ( ! property_key . is_null ( ) ) {
methods . append ( create_ast_node < ClassMethod > ( property_key . release_nonnull ( ) , move ( function ) , method_kind , is_static ) ) ;
} else {
syntax_error ( " No key for class method " ) ;
}
} else {
expected ( " ParenOpen " ) ;
consume ( ) ;
}
}
consume ( TokenType : : CurlyClose ) ;
if ( constructor . is_null ( ) ) {
auto constructor_body = create_ast_node < BlockStatement > ( ) ;
if ( ! super_class . is_null ( ) ) {
// Set constructor to the result of parsing the source text
// constructor(... args){ super (...args);}
auto super_call = create_ast_node < CallExpression > ( create_ast_node < SuperExpression > ( ) , Vector { CallExpression : : Argument { create_ast_node < Identifier > ( " args " ) , true } } ) ;
constructor_body - > append ( create_ast_node < ExpressionStatement > ( move ( super_call ) ) ) ;
constructor_body - > add_variables ( m_parser_state . m_var_scopes . last ( ) ) ;
2020-10-04 00:02:43 +00:00
constructor = create_ast_node < FunctionExpression > ( class_name , move ( constructor_body ) , Vector { FunctionNode : : Parameter { " args " , nullptr , true } } , 0 , NonnullRefPtrVector < VariableDeclaration > ( ) , true ) ;
2020-06-08 18:31:21 +00:00
} else {
2020-10-04 00:02:43 +00:00
constructor = create_ast_node < FunctionExpression > ( class_name , move ( constructor_body ) , Vector < FunctionNode : : Parameter > { } , 0 , NonnullRefPtrVector < VariableDeclaration > ( ) , true ) ;
2020-06-08 18:31:21 +00:00
}
}
return create_ast_node < ClassExpression > ( move ( class_name ) , move ( constructor ) , move ( super_class ) , move ( methods ) ) ;
}
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 > ( ) ;
2020-06-08 18:31:21 +00:00
case TokenType : : Class :
return parse_class_expression ( false ) ;
case TokenType : : Super :
consume ( ) ;
if ( ! m_parser_state . m_allow_super_property_lookup )
syntax_error ( " 'super' keyword unexpected here " ) ;
return create_ast_node < SuperExpression > ( ) ;
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 :
2020-10-19 17:01:28 +00:00
return create_ast_node < NumericLiteral > ( consume_and_validate_numeric_literal ( ) . double_value ( ) ) ;
2020-06-06 00:14:10 +00:00
case TokenType : : BigIntLiteral :
return create_ast_node < BigIntLiteral > ( consume ( ) . 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 ( ) ;
2020-06-03 23:05:49 +00:00
case TokenType : : RegexLiteral :
return parse_regexp_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
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 :
2020-10-22 22:30:07 +00:00
expected ( " primary expression " ) ;
2020-03-11 18:27:43 +00:00
consume ( ) ;
2020-03-18 10:23:53 +00:00
return create_ast_node < ErrorExpression > ( ) ;
2020-03-11 18:27:43 +00:00
}
}
2020-06-03 23:05:49 +00:00
NonnullRefPtr < RegExpLiteral > Parser : : parse_regexp_literal ( )
{
auto content = consume ( ) . value ( ) ;
auto flags = match ( TokenType : : RegexFlags ) ? consume ( ) . value ( ) : " " ;
return create_ast_node < RegExpLiteral > ( content . substring_view ( 1 , content . length ( ) - 2 ) , flags ) ;
}
2020-03-18 10:23:53 +00:00
NonnullRefPtr < Expression > Parser : : parse_unary_prefixed_expression ( )
2020-03-14 18:45:51 +00:00
{
2020-08-18 16:46:36 +00:00
auto precedence = g_operator_precedence . get ( m_parser_state . m_current_token . type ( ) ) ;
2020-03-30 13:24:43 +00:00
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 ) ;
2020-09-16 19:03:06 +00:00
// FIXME: Apparently for functions this should also not be enforced on a parser level,
// other engines throw ReferenceError for ++foo()
2020-04-29 20:39:00 +00:00
if ( ! rhs - > is_identifier ( ) & & ! rhs - > is_member_expression ( ) )
2020-10-04 13:53:15 +00:00
syntax_error ( String : : formatted ( " Right-hand side of prefix increment operator must be identifier or member expression, got {} " , rhs - > class_name ( ) ) , rhs_start_line , rhs_start_column ) ;
2020-04-29 20:39:00 +00:00
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 ) ;
2020-09-16 19:03:06 +00:00
// FIXME: Apparently for functions this should also not be enforced on a parser level,
// other engines throw ReferenceError for --foo()
2020-04-29 20:39:00 +00:00
if ( ! rhs - > is_identifier ( ) & & ! rhs - > is_member_expression ( ) )
2020-10-04 13:53:15 +00:00
syntax_error ( String : : formatted ( " Right-hand side of prefix decrement operator must be identifier or member expression, got {} " , rhs - > class_name ( ) ) , rhs_start_line , rhs_start_column ) ;
2020-04-29 20:39:00 +00:00
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 :
2020-10-22 22:30:07 +00:00
expected ( " primary expression " ) ;
2020-03-14 18:45:51 +00:00
consume ( ) ;
2020-03-18 10:23:53 +00:00
return create_ast_node < ErrorExpression > ( ) ;
2020-03-14 18:45:51 +00:00
}
}
2020-06-08 18:31:21 +00:00
NonnullRefPtr < Expression > Parser : : parse_property_key ( )
{
if ( match ( TokenType : : StringLiteral ) ) {
return parse_string_literal ( consume ( ) ) ;
} else if ( match ( TokenType : : NumericLiteral ) ) {
2020-10-19 17:01:28 +00:00
// FIXME: "evaluate" key to double value, see https://github.com/SerenityOS/serenity/issues/3717
return create_ast_node < StringLiteral > ( consume_and_validate_numeric_literal ( ) . value ( ) ) ;
2020-06-08 18:31:21 +00:00
} else if ( match ( TokenType : : BigIntLiteral ) ) {
auto value = consume ( TokenType : : BigIntLiteral ) . value ( ) ;
return create_ast_node < StringLiteral > ( value . substring_view ( 0 , value . length ( ) - 1 ) ) ;
} else if ( match ( TokenType : : BracketOpen ) ) {
consume ( TokenType : : BracketOpen ) ;
auto result = parse_expression ( 0 ) ;
consume ( TokenType : : BracketClose ) ;
return result ;
} else {
if ( ! match_identifier_name ( ) )
expected ( " IdentifierName " ) ;
return create_ast_node < StringLiteral > ( consume ( ) . value ( ) ) ;
}
}
2020-03-18 10:23:53 +00:00
NonnullRefPtr < ObjectExpression > Parser : : parse_object_expression ( )
2020-03-11 18:27:43 +00:00
{
consume ( TokenType : : CurlyOpen ) ;
2020-03-21 00:29:00 +00:00
2020-05-29 05:50:06 +00:00
NonnullRefPtrVector < ObjectProperty > properties ;
ObjectProperty : : Type property_type ;
auto skip_to_next_property = [ & ] {
while ( ! done ( ) & & ! match ( TokenType : : Comma ) & & ! match ( TokenType : : CurlyOpen ) )
consume ( ) ;
} ;
2020-05-22 00:28:28 +00:00
2020-04-07 17:29:37 +00:00
while ( ! done ( ) & & ! match ( TokenType : : CurlyClose ) ) {
2020-05-29 05:50:06 +00:00
property_type = ObjectProperty : : Type : : KeyValue ;
RefPtr < Expression > property_name ;
2020-04-23 18:37:53 +00:00
RefPtr < Expression > property_value ;
2020-04-28 04:52:47 +00:00
2020-05-29 05:50:06 +00:00
if ( match ( TokenType : : TripleDot ) ) {
consume ( ) ;
property_name = parse_expression ( 4 ) ;
2020-06-08 18:31:21 +00:00
properties . append ( create_ast_node < ObjectProperty > ( * property_name , nullptr , ObjectProperty : : Type : : Spread , false ) ) ;
2020-05-29 05:50:06 +00:00
if ( ! match ( TokenType : : Comma ) )
break ;
consume ( TokenType : : Comma ) ;
continue ;
}
if ( match ( TokenType : : Identifier ) ) {
2020-04-23 18:37:53 +00:00
auto identifier = consume ( ) . value ( ) ;
2020-05-29 05:50:06 +00:00
if ( identifier = = " get " & & match_property_key ( ) ) {
property_type = ObjectProperty : : Type : : Getter ;
property_name = parse_property_key ( ) ;
} else if ( identifier = = " set " & & match_property_key ( ) ) {
property_type = ObjectProperty : : Type : : Setter ;
property_name = parse_property_key ( ) ;
} else {
property_name = create_ast_node < StringLiteral > ( identifier ) ;
property_value = create_ast_node < Identifier > ( identifier ) ;
2020-05-22 00:28:28 +00:00
}
2020-04-06 20:17:05 +00:00
} else {
2020-05-29 05:50:06 +00:00
property_name = parse_property_key ( ) ;
}
if ( property_type = = ObjectProperty : : Type : : Getter | | property_type = = ObjectProperty : : Type : : Setter ) {
if ( ! match ( TokenType : : ParenOpen ) ) {
syntax_error (
" Expected '(' for object getter or setter property " ,
m_parser_state . m_current_token . line_number ( ) ,
2020-06-04 12:48:36 +00:00
m_parser_state . m_current_token . line_column ( ) ) ;
2020-05-29 05:50:06 +00:00
skip_to_next_property ( ) ;
2020-05-22 00:28:28 +00:00
continue ;
}
2020-04-06 20:17:05 +00:00
}
2020-05-29 05:50:06 +00:00
if ( match ( TokenType : : ParenOpen ) ) {
ASSERT ( property_name ) ;
2020-10-20 17:32:51 +00:00
u8 parse_options = FunctionNodeParseOptions : : AllowSuperPropertyLookup ;
if ( property_type = = ObjectProperty : : Type : : Getter )
parse_options | = FunctionNodeParseOptions : : IsGetterFunction ;
if ( property_type = = ObjectProperty : : Type : : Setter )
parse_options | = FunctionNodeParseOptions : : IsSetterFunction ;
auto function = parse_function_node < FunctionExpression > ( parse_options ) ;
2020-06-08 18:31:21 +00:00
properties . append ( create_ast_node < ObjectProperty > ( * property_name , function , property_type , true ) ) ;
2020-05-29 05:50:06 +00:00
} else if ( match ( TokenType : : Colon ) ) {
2020-06-01 14:08:34 +00:00
if ( ! property_name ) {
syntax_error ( " Expected a property name " ) ;
skip_to_next_property ( ) ;
continue ;
}
2020-05-29 05:50:06 +00:00
consume ( ) ;
2020-06-08 18:31:21 +00:00
properties . append ( create_ast_node < ObjectProperty > ( * property_name , parse_expression ( 2 ) , property_type , false ) ) ;
2020-06-01 14:08:34 +00:00
} else if ( property_name & & property_value ) {
2020-06-08 18:31:21 +00:00
properties . append ( create_ast_node < ObjectProperty > ( * property_name , * property_value , property_type , false ) ) ;
2020-06-01 14:08:34 +00:00
} else {
syntax_error ( " Expected a property " ) ;
skip_to_next_property ( ) ;
continue ;
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 " ;
2020-10-04 13:53:15 +00:00
message = String : : formatted ( " Malformed {} escape sequence " , type ) ;
2020-05-17 06:27:25 +00:00
} else if ( status = = Token : : StringValueStatus : : UnicodeEscapeOverflow ) {
2020-08-05 20:31:20 +00:00
message = " Unicode code_point must not be greater than 0x10ffff in escape sequence " ;
2020-05-17 06:27:25 +00:00
}
syntax_error (
message ,
m_parser_state . m_current_token . line_number ( ) ,
2020-04-21 18:21:26 +00:00
m_parser_state . m_current_token . line_column ( ) ) ;
2020-05-17 06:27:25 +00:00
}
2020-05-28 05:22:08 +00:00
if ( m_parser_state . m_use_strict_directive = = UseStrictDirectiveState : : Looking ) {
if ( string = = " use strict " & & token . type ( ) ! = TokenType : : TemplateLiteralString ) {
m_parser_state . m_use_strict_directive = UseStrictDirectiveState : : Found ;
} else {
m_parser_state . m_use_strict_directive = UseStrictDirectiveState : : None ;
}
}
2020-05-17 06:27:25 +00:00
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
2020-06-03 22:36:25 +00:00
while ( ! done ( ) & & ! match ( TokenType : : TemplateLiteralEnd ) & & ! match ( TokenType : : UnterminatedTemplateLiteral ) ) {
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 : : 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 ( ) ;
2020-06-03 22:36:25 +00:00
} else {
expected ( " Template literal string or expression " ) ;
break ;
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 ) ;
}
2020-04-21 18:21:26 +00:00
NonnullRefPtr < Expression > Parser : : parse_expression ( int min_precedence , Associativity associativity , Vector < TokenType > forbidden )
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 ) ) ;
}
2020-04-21 18:21:26 +00:00
while ( match_secondary_expression ( forbidden ) ) {
2020-08-18 16:46:36 +00:00
int new_precedence = g_operator_precedence . get ( 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 :
2020-10-04 22:58:57 +00:00
return parse_assignment_expression ( AssignmentOp : : AdditionAssignment , move ( lhs ) , 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 :
2020-10-04 22:58:57 +00:00
return parse_assignment_expression ( AssignmentOp : : SubtractionAssignment , move ( lhs ) , 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 :
2020-10-04 22:58:57 +00:00
return parse_assignment_expression ( AssignmentOp : : MultiplicationAssignment , move ( lhs ) , 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 :
2020-10-04 22:58:57 +00:00
return parse_assignment_expression ( AssignmentOp : : DivisionAssignment , move ( lhs ) , 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 :
2020-10-04 22:58:57 +00:00
return parse_assignment_expression ( AssignmentOp : : ModuloAssignment , move ( lhs ) , 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 :
2020-10-04 22:58:57 +00:00
return parse_assignment_expression ( AssignmentOp : : ExponentiationAssignment , move ( lhs ) , 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 :
2020-10-04 22:58:57 +00:00
return parse_assignment_expression ( AssignmentOp : : BitwiseAndAssignment , move ( lhs ) , 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 :
2020-10-04 22:58:57 +00:00
return parse_assignment_expression ( AssignmentOp : : BitwiseOrAssignment , move ( lhs ) , 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 :
2020-10-04 22:58:57 +00:00
return parse_assignment_expression ( AssignmentOp : : BitwiseXorAssignment , move ( lhs ) , 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 :
2020-10-04 22:58:57 +00:00
return parse_assignment_expression ( AssignmentOp : : LeftShiftAssignment , move ( lhs ) , 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 :
2020-10-04 22:58:57 +00:00
return parse_assignment_expression ( AssignmentOp : : RightShiftAssignment , move ( lhs ) , 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 :
2020-10-04 22:58:57 +00:00
return parse_assignment_expression ( AssignmentOp : : UnsignedRightShiftAssignment , move ( lhs ) , min_precedence , associativity ) ;
2020-03-11 18:27:43 +00:00
case TokenType : : ParenOpen :
return parse_call_expression ( move ( lhs ) ) ;
case TokenType : : Equals :
2020-10-04 22:58:57 +00:00
return parse_assignment_expression ( AssignmentOp : : Assignment , move ( lhs ) , 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 :
2020-09-16 19:03:06 +00:00
// FIXME: Apparently for functions this should also not be enforced on a parser level,
// other engines throw ReferenceError for foo()++
2020-04-29 20:39:00 +00:00
if ( ! lhs - > is_identifier ( ) & & ! lhs - > is_member_expression ( ) )
2020-10-04 13:53:15 +00:00
syntax_error ( String : : formatted ( " Left-hand side of postfix increment operator must be identifier or member expression, got {} " , 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 :
2020-09-16 19:03:06 +00:00
// FIXME: Apparently for functions this should also not be enforced on a parser level,
// other engines throw ReferenceError for foo()--
2020-04-29 20:39:00 +00:00
if ( ! lhs - > is_identifier ( ) & & ! lhs - > is_member_expression ( ) )
2020-10-04 13:53:15 +00:00
syntax_error ( String : : formatted ( " Left-hand side of postfix increment operator must be identifier or member expression, got {} " , 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 ) ) ;
2020-10-05 15:49:43 +00:00
case TokenType : : DoubleAmpersandEquals :
return parse_assignment_expression ( AssignmentOp : : AndAssignment , move ( lhs ) , 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 ) ) ;
2020-10-05 15:49:43 +00:00
case TokenType : : DoublePipeEquals :
return parse_assignment_expression ( AssignmentOp : : OrAssignment , move ( lhs ) , 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 ) ) ;
2020-10-05 15:49:43 +00:00
case TokenType : : DoubleQuestionMarkEquals :
return parse_assignment_expression ( AssignmentOp : : NullishAssignment , move ( lhs ) , 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 :
2020-10-22 22:30:07 +00:00
expected ( " secondary expression " ) ;
2020-03-11 18:27:43 +00:00
consume ( ) ;
2020-03-18 10:23:53 +00:00
return create_ast_node < ErrorExpression > ( ) ;
2020-03-11 18:27:43 +00:00
}
}
2020-10-04 22:58:57 +00:00
NonnullRefPtr < AssignmentExpression > Parser : : parse_assignment_expression ( AssignmentOp assignment_op , NonnullRefPtr < Expression > lhs , int min_precedence , Associativity associativity )
{
ASSERT ( match ( TokenType : : Equals )
| | match ( TokenType : : PlusEquals )
| | match ( TokenType : : MinusEquals )
| | match ( TokenType : : AsteriskEquals )
| | match ( TokenType : : SlashEquals )
| | match ( TokenType : : PercentEquals )
| | match ( TokenType : : DoubleAsteriskEquals )
| | match ( TokenType : : AmpersandEquals )
| | match ( TokenType : : PipeEquals )
| | match ( TokenType : : CaretEquals )
| | match ( TokenType : : ShiftLeftEquals )
| | match ( TokenType : : ShiftRightEquals )
2020-10-05 15:49:43 +00:00
| | match ( TokenType : : UnsignedShiftRightEquals )
| | match ( TokenType : : DoubleAmpersandEquals )
| | match ( TokenType : : DoublePipeEquals )
| | match ( TokenType : : DoubleQuestionMarkEquals ) ) ;
2020-10-04 22:58:57 +00:00
consume ( ) ;
if ( ! lhs - > is_identifier ( ) & & ! lhs - > is_member_expression ( ) & & ! lhs - > is_call_expression ( ) ) {
syntax_error ( " Invalid left-hand side in assignment " ) ;
} else if ( m_parser_state . m_strict_mode & & lhs - > is_identifier ( ) ) {
auto name = static_cast < const Identifier & > ( * lhs ) . string ( ) ;
if ( name = = " eval " | | name = = " arguments " )
syntax_error ( String : : formatted ( " '{}' cannot be assigned to in strict mode code " , name ) ) ;
2020-10-04 23:00:10 +00:00
} else if ( m_parser_state . m_strict_mode & & lhs - > is_call_expression ( ) ) {
syntax_error ( " Cannot assign to function call " ) ;
2020-10-04 22:58:57 +00:00
}
return create_ast_node < AssignmentExpression > ( assignment_op , move ( lhs ) , parse_expression ( min_precedence , associativity ) ) ;
}
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
{
2020-06-08 18:31:21 +00:00
if ( ! m_parser_state . m_allow_super_constructor_call & & lhs - > is_super_expression ( ) )
syntax_error ( " 'super' keyword unexpected here " ) ;
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 ) ;
2020-08-18 16:46:36 +00:00
auto callee = parse_expression ( g_operator_precedence . get ( TokenType : : New ) , Associativity : : Right , { TokenType : : ParenOpen } ) ;
2020-03-28 15:33:52 +00:00
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
{
2020-10-07 18:33:48 +00:00
if ( ! m_parser_state . m_in_function_context )
syntax_error ( " 'return' not allowed outside of a function " ) ;
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
2020-10-21 21:16:45 +00:00
if ( m_parser_state . m_current_token . trivia_contains_line_terminator ( ) )
2020-04-17 13:05:58 +00:00
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 ( )
2020-10-04 00:02:43 +00:00
{
bool dummy = false ;
return parse_block_statement ( dummy ) ;
}
NonnullRefPtr < BlockStatement > Parser : : parse_block_statement ( bool & is_strict )
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 ) ;
2020-05-28 05:22:08 +00:00
bool first = true ;
bool initial_strict_mode_state = m_parser_state . m_strict_mode ;
if ( initial_strict_mode_state ) {
m_parser_state . m_use_strict_directive = UseStrictDirectiveState : : None ;
2020-10-04 00:02:43 +00:00
is_strict = true ;
2020-05-28 05:22:08 +00:00
} else {
m_parser_state . m_use_strict_directive = UseStrictDirectiveState : : Looking ;
}
2020-03-11 18:27:43 +00:00
while ( ! done ( ) & & ! match ( TokenType : : CurlyClose ) ) {
2020-10-22 22:30:07 +00:00
if ( match_declaration ( ) ) {
block - > append ( parse_declaration ( ) ) ;
if ( first & & ! initial_strict_mode_state )
m_parser_state . m_use_strict_directive = UseStrictDirectiveState : : None ;
2020-03-11 18:27:43 +00:00
} else if ( match_statement ( ) ) {
block - > append ( parse_statement ( ) ) ;
2020-05-28 05:22:08 +00:00
if ( first & & ! initial_strict_mode_state ) {
if ( m_parser_state . m_use_strict_directive = = UseStrictDirectiveState : : Found ) {
2020-10-04 00:02:43 +00:00
is_strict = true ;
2020-05-28 05:22:08 +00:00
m_parser_state . m_strict_mode = true ;
}
m_parser_state . m_use_strict_directive = UseStrictDirectiveState : : None ;
}
2020-03-11 18:27:43 +00:00
} else {
2020-10-22 22:30:07 +00:00
expected ( " statement or declaration " ) ;
2020-03-11 18:27:43 +00:00
consume ( ) ;
}
2020-05-28 05:22:08 +00:00
first = false ;
2020-03-11 18:27:43 +00:00
}
2020-05-28 05:22:08 +00:00
m_parser_state . m_strict_mode = initial_strict_mode_state ;
2020-03-11 18:27:43 +00:00
consume ( TokenType : : CurlyClose ) ;
2020-04-13 14:42:54 +00:00
block - > add_variables ( m_parser_state . m_let_scopes . last ( ) ) ;
2020-06-04 12:48:36 +00:00
block - > add_functions ( m_parser_state . m_function_scopes . last ( ) ) ;
2020-03-11 18:27:43 +00:00
return block ;
}
2020-03-19 10:52:56 +00:00
template < typename FunctionNodeType >
2020-10-20 16:56:49 +00:00
NonnullRefPtr < FunctionNodeType > Parser : : parse_function_node ( u8 parse_options )
2020-03-11 18:27:43 +00:00
{
2020-10-20 17:32:51 +00:00
ASSERT ( ! ( parse_options & FunctionNodeParseOptions : : IsGetterFunction & & parse_options & FunctionNodeParseOptions : : IsSetterFunction ) ) ;
2020-10-20 16:56:49 +00:00
TemporaryChange super_property_access_rollback ( m_parser_state . m_allow_super_property_lookup , ! ! ( parse_options & FunctionNodeParseOptions : : AllowSuperPropertyLookup ) ) ;
TemporaryChange super_constructor_call_rollback ( m_parser_state . m_allow_super_constructor_call , ! ! ( parse_options & FunctionNodeParseOptions : : AllowSuperConstructorCall ) ) ;
2020-06-08 18:31:21 +00:00
2020-06-04 12:48:36 +00:00
ScopePusher scope ( * this , ScopePusher : : Var | ScopePusher : : Function ) ;
2020-04-13 14:42:54 +00:00
2020-03-19 10:52:56 +00:00
String name ;
2020-10-20 16:56:49 +00:00
if ( parse_options & FunctionNodeParseOptions : : CheckForFunctionAndName ) {
consume ( TokenType : : Function ) ;
if ( FunctionNodeType : : must_have_name ( ) | | match ( TokenType : : Identifier ) )
2020-03-19 10:52:56 +00:00
name = consume ( TokenType : : Identifier ) . value ( ) ;
}
2020-03-11 18:27:43 +00:00
consume ( TokenType : : ParenOpen ) ;
2020-05-06 03:02:14 +00:00
i32 function_length = - 1 ;
2020-10-20 17:32:51 +00:00
auto parameters = parse_function_parameters ( function_length , parse_options ) ;
2020-10-18 23:26:41 +00:00
consume ( TokenType : : ParenClose ) ;
if ( function_length = = - 1 )
function_length = parameters . size ( ) ;
TemporaryChange change ( m_parser_state . m_in_function_context , true ) ;
auto old_labels_in_scope = move ( m_parser_state . m_labels_in_scope ) ;
ScopeGuard guard ( [ & ] ( ) {
m_parser_state . m_labels_in_scope = move ( old_labels_in_scope ) ;
} ) ;
bool is_strict = false ;
auto body = parse_block_statement ( is_strict ) ;
body - > add_variables ( m_parser_state . m_var_scopes . last ( ) ) ;
body - > add_functions ( m_parser_state . m_function_scopes . last ( ) ) ;
return create_ast_node < FunctionNodeType > ( name , move ( body ) , move ( parameters ) , function_length , NonnullRefPtrVector < VariableDeclaration > ( ) , is_strict ) ;
}
2020-10-20 17:32:51 +00:00
Vector < FunctionNode : : Parameter > Parser : : parse_function_parameters ( int & function_length , u8 parse_options )
2020-10-18 23:26:41 +00:00
{
Vector < FunctionNode : : Parameter > parameters ;
2020-05-04 15:05:13 +00:00
while ( match ( TokenType : : Identifier ) | | match ( TokenType : : TripleDot ) ) {
2020-10-20 17:32:51 +00:00
if ( parse_options & FunctionNodeParseOptions : : IsGetterFunction )
syntax_error ( " Getter function must have no arguments " ) ;
2020-10-20 17:43:58 +00:00
if ( parse_options & FunctionNodeParseOptions : : IsSetterFunction & & ( parameters . size ( ) > = 1 | | match ( TokenType : : TripleDot ) ) )
2020-10-20 17:32:51 +00:00
syntax_error ( " Setter function must have one argument " ) ;
2020-05-04 15:05:13 +00:00
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 ) ;
}
2020-10-20 17:32:51 +00:00
if ( parse_options & FunctionNodeParseOptions : : IsSetterFunction & & parameters . is_empty ( ) )
syntax_error ( " Setter function must have one argument " ) ;
2020-10-18 23:26:41 +00:00
return parameters ;
2020-03-11 18:27:43 +00:00
}
2020-04-21 18:21:26 +00:00
NonnullRefPtr < VariableDeclaration > Parser : : parse_variable_declaration ( bool with_semicolon )
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
}
2020-04-21 18:21:26 +00:00
if ( with_semicolon )
consume_or_insert_semicolon ( ) ;
2020-04-17 13:05:58 +00:00
2020-04-13 14:42:54 +00:00
auto declaration = create_ast_node < VariableDeclaration > ( declaration_kind , move ( declarations ) ) ;
2020-04-21 18:21:26 +00:00
if ( declaration_kind = = DeclarationKind : : Var )
2020-04-13 14:42:54 +00:00
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
2020-10-21 21:16:45 +00:00
if ( m_parser_state . m_current_token . trivia_contains_line_terminator ( ) ) {
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 ) ;
2020-05-28 19:02:32 +00:00
FlyString target_label ;
if ( match ( TokenType : : Semicolon ) ) {
consume ( ) ;
2020-10-07 19:21:15 +00:00
} else {
2020-10-21 21:16:45 +00:00
if ( match ( TokenType : : Identifier ) & & ! m_parser_state . m_current_token . trivia_contains_line_terminator ( ) ) {
2020-10-07 19:21:15 +00:00
target_label = consume ( ) . value ( ) ;
2020-10-08 17:49:08 +00:00
if ( ! m_parser_state . m_labels_in_scope . contains ( target_label ) )
syntax_error ( String : : formatted ( " Label '{}' not found " , target_label ) ) ;
}
2020-10-07 19:21:15 +00:00
consume_or_insert_semicolon ( ) ;
2020-05-28 19:02:32 +00:00
}
2020-10-07 19:21:15 +00:00
if ( target_label . is_null ( ) & & ! m_parser_state . m_in_break_context )
syntax_error ( " Unlabeled 'break' not allowed outside of a loop or switch statement " ) ;
2020-05-28 19:02:32 +00:00
return create_ast_node < BreakStatement > ( target_label ) ;
2020-03-29 11:09:54 +00:00
}
2020-04-04 22:22:42 +00:00
NonnullRefPtr < ContinueStatement > Parser : : parse_continue_statement ( )
{
2020-10-07 19:21:15 +00:00
if ( ! m_parser_state . m_in_continue_context )
syntax_error ( " 'continue' not allow outside of a loop " ) ;
2020-04-04 22:22:42 +00:00
consume ( TokenType : : Continue ) ;
2020-05-28 19:02:32 +00:00
FlyString target_label ;
if ( match ( TokenType : : Semicolon ) ) {
consume ( ) ;
return create_ast_node < ContinueStatement > ( target_label ) ;
}
2020-10-21 21:16:45 +00:00
if ( match ( TokenType : : Identifier ) & & ! m_parser_state . m_current_token . trivia_contains_line_terminator ( ) ) {
2020-05-28 19:02:32 +00:00
target_label = consume ( ) . value ( ) ;
2020-10-08 17:49:08 +00:00
if ( ! m_parser_state . m_labels_in_scope . contains ( target_label ) )
syntax_error ( String : : formatted ( " Label '{}' not found " , target_label ) ) ;
}
2020-04-17 13:05:58 +00:00
consume_or_insert_semicolon ( ) ;
2020-05-28 19:02:32 +00:00
return create_ast_node < ContinueStatement > ( target_label ) ;
2020-04-04 22:22:42 +00:00
}
2020-04-03 10:14:28 +00:00
NonnullRefPtr < ConditionalExpression > Parser : : parse_conditional_expression ( NonnullRefPtr < Expression > test )
{
consume ( TokenType : : QuestionMark ) ;
2020-05-28 21:42:20 +00:00
auto consequent = parse_expression ( 2 ) ;
2020-04-03 10:14:28 +00:00
consume ( TokenType : : Colon ) ;
2020-05-28 21:42:20 +00:00
auto alternate = parse_expression ( 2 ) ;
2020-04-03 10:14:28 +00:00
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 ( ) ;
2020-10-22 20:58:01 +00:00
auto handler = parse_catch_clause ( ) ;
2020-03-24 13:03:55 +00:00
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
2020-10-07 19:21:15 +00:00
auto body = [ & ] ( ) - > NonnullRefPtr < Statement > {
TemporaryChange break_change ( m_parser_state . m_in_break_context , true ) ;
TemporaryChange continue_change ( m_parser_state . m_in_continue_context , true ) ;
return 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 ) ;
2020-10-07 19:21:15 +00:00
TemporaryChange break_change ( m_parser_state . m_in_break_context , true ) ;
TemporaryChange continue_change ( m_parser_state . m_in_continue_context , true ) ;
2020-04-21 18:27:57 +00:00
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 ;
2020-10-18 22:12:27 +00:00
auto has_default = false ;
while ( match ( TokenType : : Case ) | | match ( TokenType : : Default ) ) {
if ( match ( TokenType : : Default ) ) {
if ( has_default )
syntax_error ( " Multiple 'default' clauses in switch statement " ) ;
has_default = true ;
}
2020-03-29 11:09:54 +00:00
cases . append ( parse_switch_case ( ) ) ;
2020-10-18 22:12:27 +00:00
}
2020-03-29 11:09:54 +00:00
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 ;
2020-10-07 19:21:15 +00:00
TemporaryChange break_change ( m_parser_state . m_in_break_context , true ) ;
2020-10-22 22:30:07 +00:00
for ( ; ; ) {
if ( match_declaration ( ) )
consequent . append ( parse_declaration ( ) ) ;
else if ( match_statement ( ) )
consequent . append ( parse_statement ( ) ) ;
else
break ;
}
2020-03-29 11:09:54 +00:00
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
}
2020-04-21 18:21:26 +00:00
NonnullRefPtr < Statement > Parser : : parse_for_statement ( )
2020-03-12 12:12:12 +00:00
{
2020-04-21 18:21:26 +00:00
auto match_for_in_of = [ & ] ( ) {
return match ( TokenType : : In ) | | ( match ( TokenType : : Identifier ) & & m_parser_state . m_current_token . value ( ) = = " of " ) ;
} ;
2020-03-12 12:12:12 +00:00
consume ( TokenType : : For ) ;
consume ( TokenType : : ParenOpen ) ;
2020-05-04 22:58:53 +00:00
bool in_scope = false ;
2020-03-23 18:08:32 +00:00
RefPtr < ASTNode > init ;
2020-04-21 18:21:26 +00:00
if ( ! match ( TokenType : : Semicolon ) ) {
2020-04-17 13:05:58 +00:00
if ( match_expression ( ) ) {
2020-04-21 18:21:26 +00:00
init = parse_expression ( 0 , Associativity : : Right , { TokenType : : In } ) ;
if ( match_for_in_of ( ) )
return parse_for_in_of_statement ( * init ) ;
2020-04-17 13:05:58 +00:00
} else if ( match_variable_declaration ( ) ) {
2020-04-21 18:21:26 +00:00
if ( ! match ( TokenType : : Var ) ) {
2020-05-04 22:58:53 +00:00
m_parser_state . m_let_scopes . append ( NonnullRefPtrVector < VariableDeclaration > ( ) ) ;
in_scope = true ;
}
2020-04-21 18:21:26 +00:00
init = parse_variable_declaration ( false ) ;
if ( match_for_in_of ( ) )
return parse_for_in_of_statement ( * init ) ;
2020-04-17 13:05:58 +00:00
} else {
2020-06-01 14:08:34 +00:00
syntax_error ( " Unexpected token in for loop " ) ;
2020-04-17 13:05:58 +00:00
}
2020-03-12 12:12:12 +00:00
}
2020-04-21 18:21:26 +00:00
consume ( TokenType : : Semicolon ) ;
2020-03-12 12:12:12 +00:00
2020-03-18 10:23:53 +00:00
RefPtr < Expression > test ;
2020-04-21 18:21:26 +00:00
if ( ! match ( TokenType : : Semicolon ) )
2020-03-12 22:02:41 +00:00
test = parse_expression ( 0 ) ;
2020-03-12 12:12:12 +00:00
consume ( TokenType : : Semicolon ) ;
2020-03-18 10:23:53 +00:00
RefPtr < Expression > update ;
2020-04-21 18:21:26 +00:00
if ( ! match ( TokenType : : ParenClose ) )
2020-03-12 22:02:41 +00:00
update = parse_expression ( 0 ) ;
2020-03-12 12:12:12 +00:00
consume ( TokenType : : ParenClose ) ;
2020-10-07 19:21:15 +00:00
TemporaryChange break_change ( m_parser_state . m_in_break_context , true ) ;
TemporaryChange continue_change ( m_parser_state . m_in_continue_context , true ) ;
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
}
2020-04-21 18:21:26 +00:00
NonnullRefPtr < Statement > Parser : : parse_for_in_of_statement ( NonnullRefPtr < ASTNode > lhs )
{
if ( lhs - > is_variable_declaration ( ) ) {
auto declarations = static_cast < VariableDeclaration * > ( lhs . ptr ( ) ) - > declarations ( ) ;
if ( declarations . size ( ) > 1 ) {
syntax_error ( " multiple declarations not allowed in for..in/of " ) ;
lhs = create_ast_node < ErrorExpression > ( ) ;
}
if ( declarations . first ( ) . init ( ) ! = nullptr ) {
syntax_error ( " variable initializer not allowed in for..in/of " ) ;
lhs = create_ast_node < ErrorExpression > ( ) ;
}
}
auto in_or_of = consume ( ) ;
auto rhs = parse_expression ( 0 ) ;
consume ( TokenType : : ParenClose ) ;
2020-10-07 19:21:15 +00:00
TemporaryChange break_change ( m_parser_state . m_in_break_context , true ) ;
TemporaryChange continue_change ( m_parser_state . m_in_continue_context , true ) ;
2020-04-21 18:21:26 +00:00
auto body = parse_statement ( ) ;
if ( in_or_of . type ( ) = = TokenType : : In )
return create_ast_node < ForInStatement > ( move ( lhs ) , move ( rhs ) , move ( body ) ) ;
return create_ast_node < ForOfStatement > ( move ( lhs ) , move ( rhs ) , move ( body ) ) ;
}
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
}
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
2020-06-06 00:14:10 +00:00
| | type = = TokenType : : BigIntLiteral
2020-03-11 18:27:43 +00:00
| | 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
2020-06-08 18:31:21 +00:00
| | type = = TokenType : : Super
2020-06-03 23:05:49 +00:00
| | type = = TokenType : : RegexLiteral
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
}
2020-04-21 18:21:26 +00:00
bool Parser : : match_secondary_expression ( Vector < TokenType > forbidden ) const
2020-03-11 18:27:43 +00:00
{
2020-03-30 13:24:43 +00:00
auto type = m_parser_state . m_current_token . type ( ) ;
2020-04-21 18:21:26 +00:00
if ( forbidden . contains_slow ( type ) )
return false ;
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
2020-10-05 15:49:43 +00:00
| | type = = TokenType : : DoubleAmpersandEquals
2020-04-17 23:49:11 +00:00
| | type = = TokenType : : DoublePipe
2020-10-05 15:49:43 +00:00
| | type = = TokenType : : DoublePipeEquals
| | type = = TokenType : : DoubleQuestionMark
| | type = = TokenType : : DoubleQuestionMarkEquals ;
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 : : Return
| | 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 : : 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
}
2020-10-22 22:30:07 +00:00
bool Parser : : match_declaration ( ) const
{
auto type = m_parser_state . m_current_token . type ( ) ;
return type = = TokenType : : Function
| | type = = TokenType : : Class
| | type = = TokenType : : Const
| | type = = TokenType : : Let ;
}
bool Parser : : match_variable_declaration ( ) const
{
auto type = m_parser_state . m_current_token . type ( ) ;
return type = = TokenType : : Var
| | type = = TokenType : : Let
| | type = = TokenType : : Const ;
}
2020-04-18 18:31:27 +00:00
bool Parser : : match_identifier_name ( ) const
{
return m_parser_state . m_current_token . is_identifier_name ( ) ;
}
2020-06-08 18:31:21 +00:00
bool Parser : : match_property_key ( ) const
{
auto type = m_parser_state . m_current_token . type ( ) ;
return match_identifier_name ( )
| | type = = TokenType : : BracketOpen
| | type = = TokenType : : StringLiteral
| | type = = TokenType : : NumericLiteral
| | type = = TokenType : : BigIntLiteral ;
}
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...
2020-10-02 13:59:28 +00:00
// ...token is preceded by one or more newlines
2020-10-21 21:16:45 +00:00
if ( m_parser_state . m_current_token . trivia_contains_line_terminator ( ) )
2020-04-17 13:05:58 +00:00
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 )
{
2020-04-21 18:21:26 +00:00
if ( ! match ( expected_type ) ) {
2020-04-17 13:05:58 +00:00
expected ( Token : : name ( expected_type ) ) ;
2020-03-11 18:27:43 +00:00
}
return consume ( ) ;
}
2020-10-19 17:01:28 +00:00
Token Parser : : consume_and_validate_numeric_literal ( )
{
auto is_unprefixed_octal_number = [ ] ( const StringView & value ) {
return value . length ( ) > 1 & & value [ 0 ] = = ' 0 ' & & isdigit ( value [ 1 ] ) ;
} ;
auto literal_start_line = m_parser_state . m_current_token . line_number ( ) ;
auto literal_start_column = m_parser_state . m_current_token . line_column ( ) ;
auto token = consume ( TokenType : : NumericLiteral ) ;
if ( m_parser_state . m_strict_mode & & is_unprefixed_octal_number ( token . value ( ) ) )
syntax_error ( " Unprefixed octal number not allowed in strict mode " , literal_start_line , literal_start_column ) ;
2020-10-22 21:18:31 +00:00
if ( match_identifier_name ( ) & & m_parser_state . m_current_token . trivia ( ) . is_empty ( ) )
syntax_error ( " Numeric literal must not be immediately followed by identifier " ) ;
2020-10-19 17:01:28 +00:00
return token ;
}
2020-03-11 18:27:43 +00:00
void Parser : : expected ( const char * what )
2020-04-29 20:37:51 +00:00
{
2020-10-04 13:53:15 +00:00
syntax_error ( String : : formatted ( " Unexpected token {}. Expected {} " , m_parser_state . m_current_token . name ( ) , what ) ) ;
2020-04-29 20:37:51 +00:00
}
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
}