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
|
#ifndef ORYX_LEXER_H
#define ORYX_LEXER_H
#include <assert.h>
#include <stddef.h>
#include <stdint.h>
#include "types.h"
enum {
LEXEOF, /* End of token stream */
LEXIDENT, /* Identifier */
LEXNUM, /* Numeric constant */
LEXAMP = '&',
LEXCOLON = ':',
LEXEQ = '=',
LEXLANGL = '<',
LEXLBRACE = '{',
LEXLBRKT = '[',
LEXLPAR = '(',
LEXMINUS = '-',
LEXPIPE = '|',
LEXPLUS = '+',
LEXRANGL = '>',
LEXRBRACE = '}',
LEXRBRKT = ']',
LEXRPAR = ')',
LEXSEMI = ';',
LEXSLASH = '/',
LEXSTAR = '*',
LEXTILDE = '~',
/* We keep these exactly 2 away from each other, because ‘<’ and ‘>’ are 2
away from each other in ASCII. This gives us a simple mapping from some
token T to the doubled equivalent by doing T += 193. */
LEXLANGL_DBL = UINT8_MAX - 2, /* << */
LEXRANGL_DBL = UINT8_MAX - 0, /* >> */
_LEX_LAST_ENT,
};
typedef uint8_t lexeme_kind_t_;
static_assert(_LEX_LAST_ENT - 1 <= (lexeme_kind_t_)-1,
"Too many lexer tokens to fix in LEXEME_KIND_T_");
#define LEXEMES_BLKSZ (sizeof(lexeme_kind_t_) + sizeof(struct strview))
struct lexemes {
lexeme_kind_t_ *kinds;
struct strview *strs;
size_t len, cap;
};
#define lexemes_free(x) free((x).kinds)
struct lexemes lexstring(const uchar *, size_t);
#endif /* !ORYX_LEXER_H */
|
