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
|
#ifndef TOKENIZER_CC
#define TOKENIZER_CC
#include "common.cc"
#include "source.cc"
#include "token.cc"
#include "utf8.cc"
struct Tokenizer {
Buffer* buffer;
Buffer_Stack* stack;
Tokenizer(Buffer_Stack* stack) : buffer(nullptr), stack(stack) {}
};
static inline Span tokenizer_make_span(const Tokenizer* tokenizer, usize start,
usize end) {
assert_neq(tokenizer, nullptr);
Buffer* buffer = tokenizer->buffer;
return Span(buffer->file, start, end);
}
static inline String tokenizer_make_lexeme(const Tokenizer* tokenizer,
usize start, usize end) {
assert_neq(tokenizer, nullptr);
Buffer* buffer = tokenizer->buffer;
return String(buffer->content[start], end - start);
}
static inline void tokenizer_make_token(const Tokenizer* tokenizer,
Token* token, Token_Kind kind,
usize start, usize end) {
assert_neq(tokenizer, nullptr);
assert_neq(token, nullptr);
String lexeme = tokenizer_make_lexeme(tokenizer, start, end);
Span span = tokenizer_make_span(tokenizer, start, end);
*token = Token(kind, lexeme, span);
}
static Buffer* tokenizer_get_buffer(Tokenizer* tokenizer, usize* cursor) {
assert_neq(tokenizer, nullptr);
Buffer* curr = tokenizer->buffer;
if (likely(curr != nullptr)) {
*cursor = curr->cursor;
if (*cursor < curr->content.length) return curr;
}
if (!buffer_stack_pop(tokenizer->stack, &curr)) return nullptr;
tokenizer->buffer = curr;
*cursor = curr->cursor;
return curr;
}
[[nodiscard]] static bool tokenizer_advance(const Tokenizer* tokenizer,
usize* offset, wchar* out) {
const String text = tokenizer->buffer->content;
usize curr_offset = *offset;
assert_ste(curr_offset, text.length);
if (curr_offset == text.length) return false;
unsigned char c = *text[curr_offset];
u8 nobytes = utf8_nobytes(c);
if (nobytes > 1) panic("no support for multi-byte chars: %c:%d", c, nobytes);
*offset += nobytes;
*out = c;
return true;
}
static void tokenizer_lex_identifier(Tokenizer* tokenizer, usize* offset) {
assert_neq(tokenizer, nullptr);
assert_neq(offset, nullptr);
wchar c;
while (tokenizer_advance(tokenizer, offset, &c))
if (!utf8_is_alnum(c) || c == '_') break;
}
bool tokenizer_next(Tokenizer* tokenizer, Token* out) {
assert_neq(tokenizer, nullptr);
assert_neq(out, nullptr);
usize cursor;
Buffer* buffer = tokenizer_get_buffer(tokenizer, &cursor);
if (buffer == nullptr) return false;
usize advance = cursor;
wchar c;
(void)tokenizer_advance(tokenizer, &advance,
&c); // We just checked that we are not at the end
if (utf8_is_identifier(c)) {
tokenizer_lex_identifier(tokenizer, &advance);
tokenizer_make_token(tokenizer, out, Token_Kind_Identifier, cursor, advance);
goto out;
}
switch (c) {
default:
tokenizer_make_token(tokenizer, out, Token_Kind_Invalid_Char, cursor,
advance);
}
out:
buffer->cursor = advance;
return true;
}
#endif
|
