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
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138

//! Defines the lexical [`Token`]s of the WGSL grammar, and an auto-generated
//! [`Lexer`].
//!
//! [`Token`]: enum@Token
//! [`Lexer`]: struct@Lexer

use core::fmt;
use std::hash::Hash;

use gramatika::{Span, Spanned, Substr, Token as _, TokenStream};

#[derive(DebugLispToken, Token)]
pub enum Token {
	#[pattern = r"[\[\](){}]"]
	Brace(Substr, Span),

	#[pattern = "//"]
	#[pattern = r"/\*"]
	CommentStart(Substr, Span),

	#[pattern = r"\*/"]
	CommentEnd(Substr, Span),

	#[subset_of(Ident)]
	#[pattern = r"(bool|[fiu](8|16|32|64))"] // Primitives
	#[pattern = r"(mat[2-4]x[2-4][fh]?|vec[2-4][iufh]?)"] // Math
	#[pattern = r"((binding_)?array|atomic|ptr)"]
	#[pattern = r"(sampler(_comparison)?)"]
	#[pattern = r"(texture_(depth_)?multisampled_2d)"]
	#[pattern = r"(texture_external)"]
	#[pattern = r"(texture_depth_(2d|cube)(_array)?)"]
	#[pattern = r"(texture_(1d|2d(_array)?|3d|cube(_array)?))"]
	#[pattern = r"(texture_storage_(1d|2d(_array)?|3d))"]
	Type(Substr, Span),

	#[pattern = r"#(define_import_path|import)"]
	// #[pattern = r"#(if(n?def)?|else|endif)"] // TODO
	Directive(Substr, Span),

	#[pattern = r"#if.*"]
	#[pattern = r"#else.*"]
	#[pattern = r"#endif.*"]
	Pragma(Substr, Span),

	#[pattern = r"#\{.+?\}"]
	#[pattern = r"#[a-zA-Z_][a-zA-Z0-9_]*"]
	PreprocessorInsertion(Substr, Span),

	#[subset_of(Ident)]
	#[pattern = r"(const|fn|let|struct|alias|var|override|export)"]
	#[pattern = r"(function|private|read(_write)?|storage|uniform|workgroup|write)"]
	#[pattern = r"(break|case|continu(e|ing)|default|else|fallthrough|for|if|loop|return|switch|from)"]
	#[pattern = r"(true|false)"]
	#[pattern = r"(bitcast|discard|enable|import)"]
	Keyword(Substr, Span),

	#[pattern = "[a-zA-Z_][0-9a-zA-Z_]*"]
	Ident(Substr, Span),

	// Decimal
	#[pattern = r"0[fh]"]
	#[pattern = r"[1-9][0-9]*[fh]"]
	#[pattern = r"[0-9]*\.[0-9]+([eE][-+]?[0-9]+)?[fh]?"]
	#[pattern = r"[0-9]+\.[0-9]*([eE][-+]?[0-9]+)?[fh]?"]
	#[pattern = r"[0-9]+[eE][+-]?[0-9]+[fh]?"]
	// Hex
	#[pattern = r"0[xX][0-9a-fA-F]*\.[0-9a-fA-F]+([pP][-+]?[0-9]+[fh]?)?"]
	#[pattern = r"0[xX][0-9a-fA-F]+\.[0-9a-fA-F]*([pP][-+]?[0-9]+[fh]?)?"]
	#[pattern = r"0[xX][0-9a-fA-F]+[pP][-+]?[0-9]+[fh]?"]
	FloatLiteral(Substr, Span),

	// Hex
	#[pattern = "0[xX][0-9a-fA-F]+[iu]?"]
	// Decimal
	#[pattern = "0[iu]?"]
	#[pattern = "[1-9][0-9]*[iu]?"]
	IntLiteral(Substr, Span),

	#[pattern = r#""[-_ ./a-zA-Z0-9]+""#]
	Path(Substr, Span),

	#[pattern = "->"]
	#[pattern = r"[-+*/%&|^]="]
	#[pattern = r"<<=|>>="]
	#[pattern = r"&&?|\|\|?|--?|\+\+?|>>|<<"]
	#[pattern = "[=!<>]=?"]
	#[pattern = "[%*/~^]"]
	Operator(Substr, Span),

	#[pattern = r"::?|[,.;@]"]
	Punct(Substr, Span),

	#[pattern = r"\S+"]
	Unrecognized(Substr, Span),

	// Tokens without patterns -- need to be upgraded
	Attribute(Substr, Span),
	Function(Substr, Span),
	Param(Substr, Span),
	Struct(Substr, Span),
	Field(Substr, Span),
	// TODO: Rename this to `Namespace`
	Module(Substr, Span),
	Plain(Substr, Span),
}

pub type Lexer = TokenStream<Token>;

impl fmt::Debug for Token {
	fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
		<Self as gramatika::DebugLisp>::fmt(self, f, 0)
	}
}

impl fmt::Display for Token {
	fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
		write!(f, "{}", self.lexeme())
	}
}

impl Hash for Token {
	fn hash<H>(&self, state: &mut H)
	where H: std::hash::Hasher {
		self.kind().hash(state);
		self.lexeme().hash(state);
		self.span().hash(state);
	}
}

impl PartialEq for Token {
	fn eq(&self, other: &Self) -> bool {
		self.kind() == other.kind()
			&& self.lexeme() == other.lexeme()
			&& self.span() == other.span()
	}
}

impl Eq for Token {}