c96b6987c4
This parser will be used by the C++ langauge server to provide better auto-complete (& maybe also other things in the future). It is designed to be error tolerant, and keeps track of the position spans of the AST nodes, which should be useful later for incremental parsing.
159 lines
5 KiB
C++
159 lines
5 KiB
C++
/*
|
|
* Copyright (c) 2018-2020, Andreas Kling <kling@serenityos.org>
|
|
* 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 <AK/StringView.h>
|
|
#include <AK/Vector.h>
|
|
|
|
namespace Cpp {
|
|
|
|
#define FOR_EACH_TOKEN_TYPE \
|
|
__TOKEN(Unknown) \
|
|
__TOKEN(Whitespace) \
|
|
__TOKEN(PreprocessorStatement) \
|
|
__TOKEN(IncludeStatement) \
|
|
__TOKEN(IncludePath) \
|
|
__TOKEN(LeftParen) \
|
|
__TOKEN(RightParen) \
|
|
__TOKEN(LeftCurly) \
|
|
__TOKEN(RightCurly) \
|
|
__TOKEN(LeftBracket) \
|
|
__TOKEN(RightBracket) \
|
|
__TOKEN(Less) \
|
|
__TOKEN(Greater) \
|
|
__TOKEN(LessEquals) \
|
|
__TOKEN(GreaterEquals) \
|
|
__TOKEN(LessLess) \
|
|
__TOKEN(GreaterGreater) \
|
|
__TOKEN(LessLessEquals) \
|
|
__TOKEN(GreaterGreaterEquals) \
|
|
__TOKEN(LessGreater) \
|
|
__TOKEN(Comma) \
|
|
__TOKEN(Plus) \
|
|
__TOKEN(PlusPlus) \
|
|
__TOKEN(PlusEquals) \
|
|
__TOKEN(Minus) \
|
|
__TOKEN(MinusMinus) \
|
|
__TOKEN(MinusEquals) \
|
|
__TOKEN(Asterisk) \
|
|
__TOKEN(AsteriskEquals) \
|
|
__TOKEN(Slash) \
|
|
__TOKEN(SlashEquals) \
|
|
__TOKEN(Percent) \
|
|
__TOKEN(PercentEquals) \
|
|
__TOKEN(Caret) \
|
|
__TOKEN(CaretEquals) \
|
|
__TOKEN(ExclamationMark) \
|
|
__TOKEN(ExclamationMarkEquals) \
|
|
__TOKEN(Equals) \
|
|
__TOKEN(EqualsEquals) \
|
|
__TOKEN(And) \
|
|
__TOKEN(AndAnd) \
|
|
__TOKEN(AndEquals) \
|
|
__TOKEN(Pipe) \
|
|
__TOKEN(PipePipe) \
|
|
__TOKEN(PipeEquals) \
|
|
__TOKEN(Tilde) \
|
|
__TOKEN(QuestionMark) \
|
|
__TOKEN(Colon) \
|
|
__TOKEN(ColonColon) \
|
|
__TOKEN(ColonColonAsterisk) \
|
|
__TOKEN(Semicolon) \
|
|
__TOKEN(Dot) \
|
|
__TOKEN(DotAsterisk) \
|
|
__TOKEN(Arrow) \
|
|
__TOKEN(ArrowAsterisk) \
|
|
__TOKEN(DoubleQuotedString) \
|
|
__TOKEN(SingleQuotedString) \
|
|
__TOKEN(RawString) \
|
|
__TOKEN(EscapeSequence) \
|
|
__TOKEN(Comment) \
|
|
__TOKEN(Integer) \
|
|
__TOKEN(Float) \
|
|
__TOKEN(Keyword) \
|
|
__TOKEN(KnownType) \
|
|
__TOKEN(Identifier) \
|
|
__TOKEN(EOF_TOKEN)
|
|
|
|
struct Position {
|
|
size_t line { 0 };
|
|
size_t column { 0 };
|
|
|
|
bool operator<(const Position&) const;
|
|
bool operator>(const Position&) const;
|
|
bool operator==(const Position&) const;
|
|
};
|
|
|
|
struct Token {
|
|
enum class Type {
|
|
#define __TOKEN(x) x,
|
|
FOR_EACH_TOKEN_TYPE
|
|
#undef __TOKEN
|
|
};
|
|
|
|
static const char* type_to_string(Type t)
|
|
{
|
|
switch (t) {
|
|
#define __TOKEN(x) \
|
|
case Type::x: \
|
|
return #x;
|
|
FOR_EACH_TOKEN_TYPE
|
|
#undef __TOKEN
|
|
}
|
|
ASSERT_NOT_REACHED();
|
|
}
|
|
|
|
const char* to_string() const
|
|
{
|
|
return type_to_string(m_type);
|
|
}
|
|
Position start() const { return m_start; }
|
|
Position end() const { return m_end; }
|
|
Type type() const { return m_type; }
|
|
|
|
Type m_type { Type::Unknown };
|
|
Position m_start;
|
|
Position m_end;
|
|
};
|
|
|
|
class Lexer {
|
|
public:
|
|
Lexer(const StringView&);
|
|
|
|
Vector<Token> lex();
|
|
|
|
private:
|
|
char peek(size_t offset = 0) const;
|
|
char consume();
|
|
|
|
StringView m_input;
|
|
size_t m_index { 0 };
|
|
Position m_previous_position { 0, 0 };
|
|
Position m_position { 0, 0 };
|
|
};
|
|
|
|
}
|