beenull/ladybird
1
0
Fork 0
mirror of https://github.com/LadybirdBrowser/ladybird.git synced 2024-11-22 23:50:19 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 6
ladybird/Libraries/LibJS/Parser.h

80 lines
3 KiB
C
Raw Normal View History

LibJS: Add Javascript lexer and parser This adds a basic Javascript lexer and parser. It can parse the currently existing demo programs. More work needs to be done to turn it into a complete parser than can parse arbitrary JS Code. The lexer outputs tokens with preceeding whitespace and comments in the trivia member. This should allow us to generate the exact source code by concatenating the generated tokens. The parser is written in a way that it always returns a complete syntax tree. Error conditions are represented as nodes in the tree. This simplifies the code and allows it to be used as an early stage parser, e.g for parsing JS documents in an IDE while editing the source code.:
2020-03-11 18:27:43 +00:00
/*
* Copyright (c) 2020, Stephan Unverwerth <s.unverwerth@gmx.de>
* 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.
*/
#pragma once
#include "AST.h"
#include "Lexer.h"
LibJS: Make the AST reference-counted This allows function objects to outlive the original parsed program without their ScopeNode disappearing.
2020-03-18 10:23:53 +00:00
#include <AK/NonnullRefPtr.h>
LibJS: Add Javascript lexer and parser This adds a basic Javascript lexer and parser. It can parse the currently existing demo programs. More work needs to be done to turn it into a complete parser than can parse arbitrary JS Code. The lexer outputs tokens with preceeding whitespace and comments in the trivia member. This should allow us to generate the exact source code by concatenating the generated tokens. The parser is written in a way that it always returns a complete syntax tree. Error conditions are represented as nodes in the tree. This simplifies the code and allows it to be used as an early stage parser, e.g for parsing JS documents in an IDE while editing the source code.:
2020-03-11 18:27:43 +00:00
namespace JS {
LibJS: Add operator precedence parsing Obey precedence and associativity rules when parsing expressions with chained operators.
2020-03-12 22:02:41 +00:00
enum class Associativity {
Left,
Right
};
LibJS: Add Javascript lexer and parser This adds a basic Javascript lexer and parser. It can parse the currently existing demo programs. More work needs to be done to turn it into a complete parser than can parse arbitrary JS Code. The lexer outputs tokens with preceeding whitespace and comments in the trivia member. This should allow us to generate the exact source code by concatenating the generated tokens. The parser is written in a way that it always returns a complete syntax tree. Error conditions are represented as nodes in the tree. This simplifies the code and allows it to be used as an early stage parser, e.g for parsing JS documents in an IDE while editing the source code.:
2020-03-11 18:27:43 +00:00
class Parser {
public:
explicit Parser(Lexer lexer);
LibJS: Make the AST reference-counted This allows function objects to outlive the original parsed program without their ScopeNode disappearing.
2020-03-18 10:23:53 +00:00
NonnullRefPtr<Program> parse_program();
LibJS: Add Javascript lexer and parser This adds a basic Javascript lexer and parser. It can parse the currently existing demo programs. More work needs to be done to turn it into a complete parser than can parse arbitrary JS Code. The lexer outputs tokens with preceeding whitespace and comments in the trivia member. This should allow us to generate the exact source code by concatenating the generated tokens. The parser is written in a way that it always returns a complete syntax tree. Error conditions are represented as nodes in the tree. This simplifies the code and allows it to be used as an early stage parser, e.g for parsing JS documents in an IDE while editing the source code.:
2020-03-11 18:27:43 +00:00
LibJS: Make the AST reference-counted This allows function objects to outlive the original parsed program without their ScopeNode disappearing.
2020-03-18 10:23:53 +00:00
NonnullRefPtr<Statement> parse_statement();
NonnullRefPtr<BlockStatement> parse_block_statement();
NonnullRefPtr<ReturnStatement> parse_return_statement();
NonnullRefPtr<FunctionDeclaration> parse_function_declaration();
NonnullRefPtr<VariableDeclaration> parse_variable_declaration();
NonnullRefPtr<ForStatement> parse_for_statement();
LibJS: Add Javascript lexer and parser This adds a basic Javascript lexer and parser. It can parse the currently existing demo programs. More work needs to be done to turn it into a complete parser than can parse arbitrary JS Code. The lexer outputs tokens with preceeding whitespace and comments in the trivia member. This should allow us to generate the exact source code by concatenating the generated tokens. The parser is written in a way that it always returns a complete syntax tree. Error conditions are represented as nodes in the tree. This simplifies the code and allows it to be used as an early stage parser, e.g for parsing JS documents in an IDE while editing the source code.:
2020-03-11 18:27:43 +00:00
LibJS: Make the AST reference-counted This allows function objects to outlive the original parsed program without their ScopeNode disappearing.
2020-03-18 10:23:53 +00:00
NonnullRefPtr<Expression> parse_expression(int min_precedence, Associativity associate = Associativity::Right);
NonnullRefPtr<Expression> parse_primary_expression();
NonnullRefPtr<Expression> parse_unary_prefixed_expression();
NonnullRefPtr<ObjectExpression> parse_object_expression();
NonnullRefPtr<Expression> parse_secondary_expression(NonnullRefPtr<Expression>, int min_precedence, Associativity associate = Associativity::Right);
NonnullRefPtr<CallExpression> parse_call_expression(NonnullRefPtr<Expression>);
LibJS: Add Javascript lexer and parser This adds a basic Javascript lexer and parser. It can parse the currently existing demo programs. More work needs to be done to turn it into a complete parser than can parse arbitrary JS Code. The lexer outputs tokens with preceeding whitespace and comments in the trivia member. This should allow us to generate the exact source code by concatenating the generated tokens. The parser is written in a way that it always returns a complete syntax tree. Error conditions are represented as nodes in the tree. This simplifies the code and allows it to be used as an early stage parser, e.g for parsing JS documents in an IDE while editing the source code.:
2020-03-11 18:27:43 +00:00
bool has_errors() const { return m_has_errors; }
private:
LibJS: Add operator precedence parsing Obey precedence and associativity rules when parsing expressions with chained operators.
2020-03-12 22:02:41 +00:00
int operator_precedence(TokenType) const;
Associativity operator_associativity(TokenType) const;
LibJS: Add Javascript lexer and parser This adds a basic Javascript lexer and parser. It can parse the currently existing demo programs. More work needs to be done to turn it into a complete parser than can parse arbitrary JS Code. The lexer outputs tokens with preceeding whitespace and comments in the trivia member. This should allow us to generate the exact source code by concatenating the generated tokens. The parser is written in a way that it always returns a complete syntax tree. Error conditions are represented as nodes in the tree. This simplifies the code and allows it to be used as an early stage parser, e.g for parsing JS documents in an IDE while editing the source code.:
2020-03-11 18:27:43 +00:00
bool match_expression() const;
LibJS/Parser: Implement the parsing of unary/prefixed update expressions
2020-03-14 18:45:51 +00:00
bool match_unary_prefixed_expression() const;
LibJS: Add Javascript lexer and parser This adds a basic Javascript lexer and parser. It can parse the currently existing demo programs. More work needs to be done to turn it into a complete parser than can parse arbitrary JS Code. The lexer outputs tokens with preceeding whitespace and comments in the trivia member. This should allow us to generate the exact source code by concatenating the generated tokens. The parser is written in a way that it always returns a complete syntax tree. Error conditions are represented as nodes in the tree. This simplifies the code and allows it to be used as an early stage parser, e.g for parsing JS documents in an IDE while editing the source code.:
2020-03-11 18:27:43 +00:00
bool match_secondary_expression() const;
bool match_statement() const;
bool match(TokenType type) const;
bool done() const;
void expected(const char* what);
Token consume();
Token consume(TokenType type);
Lexer m_lexer;
Token m_current_token;
bool m_has_errors = false;
};
}
Reference in a new issue Copy permalink