1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
|
/*
* Copyright (C) 2022 Apple Inc. 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 APPLE INC. AND ITS 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 APPLE INC. OR ITS 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 "Token.h"
#include <wtf/ASCIICType.h>
#include <wtf/text/WTFString.h>
namespace WGSL {
template<typename T>
class Lexer {
public:
Lexer(const String& wgsl)
{
if constexpr (std::is_same<T, LChar>::value) {
m_code = wgsl.characters8();
m_codeEnd = m_code + wgsl.sizeInBytes();
} else {
static_assert(std::is_same<T, UChar>::value, "The lexer expects its template parameter to be either LChar or UChar");
m_code = wgsl.characters16();
ASSERT(!(wgsl.sizeInBytes() % 2));
m_codeEnd = m_code + wgsl.sizeInBytes() / 2;
}
m_current = (m_code != m_codeEnd) ? *m_code : 0;
m_currentPosition = { 1, 0, 0 };
}
Token lex();
bool isAtEndOfFile() const;
SourcePosition currentPosition() const { return m_currentPosition; }
private:
unsigned currentOffset() const { return m_currentPosition.offset; }
unsigned currentTokenLength() const { return currentOffset() - m_tokenStartingPosition.offset; }
Token makeToken(TokenType type)
{
return { type, m_tokenStartingPosition, currentTokenLength() };
}
Token makeLiteralToken(TokenType type, double literalValue)
{
return { type, m_tokenStartingPosition, currentTokenLength(), literalValue };
}
Token makeIdentifierToken(String&& identifier)
{
return { WGSL::TokenType::Identifier, m_tokenStartingPosition, currentTokenLength(), WTFMove(identifier) };
}
T shift(unsigned = 1);
T peek(unsigned = 0);
void newLine();
bool skipBlockComments();
void skipLineComment();
bool skipWhitespaceAndComments();
// Reads [0-9]+
std::optional<uint64_t> parseDecimalInteger();
// Parse pattern (e|E)(\+|-)?[0-9]+f? if it is present, and return the exponent
std::optional<int64_t> parseDecimalFloatExponent();
// Checks whether there is an "i" or "u" coming, and return the right kind of literal token
Token parseIntegerLiteralSuffix(double literalValue);
static bool isIdentifierStart(T character) { return isASCIIAlpha(character) || character == '_'; }
static bool isIdentifierContinue(T character) { return isASCIIAlphanumeric(character) || character == '_'; }
static unsigned readDecimal(T character)
{
ASSERT(isASCIIDigit(character));
return character - '0';
}
T m_current;
const T* m_code;
const T* m_codeEnd;
SourcePosition m_currentPosition { 0, 0, 0 };
SourcePosition m_tokenStartingPosition { 0, 0, 0 };
};
}
|
