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
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
|
/* Copyright (C) 2023 Aryadev Chavali
* You may distribute and modify this code under the terms of the
* GPLv2 license. You should have received a copy of the GPLv2
* license with this file. If not, please write to:
* aryadev@aryadevchavali.com.
* Created: 2023-10-23
* Author: Aryadev Chavali
* Description: Assembly source code compiler, targeting OVM
*/
#include <ctype.h>
#include <stdbool.h>
#include <stdio.h>
#include <string.h>
#include <lib/darr.h>
typedef enum TokenType
{
TOKEN_BYTE_LITERAL,
TOKEN_HWORD_LITERAL,
TOKEN_WORD_LITERAL,
TOKEN_SYMBOL,
} token_type_t;
const char *token_type_as_cstr(token_type_t type)
{
switch (type)
{
case TOKEN_BYTE_LITERAL:
return "BYTE_LITERAL";
case TOKEN_HWORD_LITERAL:
return "HWORD_LITERAL";
case TOKEN_WORD_LITERAL:
return "WORD_LITERAL";
case TOKEN_SYMBOL:
return "SYMBOL";
}
return "";
}
typedef struct
{
token_type_t type;
char *str;
size_t str_size;
} token_t;
// We can use darr_read_file as an in memory buffer of source code
// Then just create new darr's for tokens, then instructions. Then
// emit bytecode in the end.
typedef darr_t buffer_t;
size_t space_left(buffer_t *buffer)
{
if (buffer->available == buffer->used)
return 0;
return buffer->available - 1 - buffer->used;
}
bool is_symbol(char c)
{
return isalpha(c) || c == '-' || c == '_';
}
token_t tokenise_symbol(buffer_t *buffer)
{
token_t token = {.type = TOKEN_SYMBOL, .str_size = 0};
for (; token.str_size < space_left(buffer) &&
is_symbol(buffer->data[buffer->used + token.str_size]);
++token.str_size)
continue;
token.str = calloc(token.str_size + 1, 1);
memcpy(token.str, buffer->data + buffer->used, token.str_size);
token.str[token.str_size] = '\0';
buffer->used += token.str_size;
return token;
}
void tokenise_literal(buffer_t *buffer, token_t *token)
{
token->str_size = 0;
for (; token->str_size < space_left(buffer) &&
isdigit(buffer->data[buffer->used + token->str_size]);
++token->str_size)
continue;
token->str = calloc(token->str_size + 1, 1);
memcpy(token->str, buffer->data + buffer->used, token->str_size);
token->str[token->str_size] = '\0';
buffer->used += token->str_size;
}
token_t tokenise_byte_literal(buffer_t *buffer)
{
token_t token = {.type = TOKEN_BYTE_LITERAL};
tokenise_literal(buffer, &token);
return token;
}
token_t tokenise_hword_literal(buffer_t *buffer)
{
token_t token = {.type = TOKEN_HWORD_LITERAL};
tokenise_literal(buffer, &token);
return token;
}
token_t tokenise_word_literal(buffer_t *buffer)
{
token_t token = {.type = TOKEN_WORD_LITERAL};
tokenise_literal(buffer, &token);
return token;
}
token_t *tokenise_buffer(buffer_t *buffer, size_t *n_tokens)
{
buffer_t tokens = {0};
darr_init(&tokens, sizeof(token_t));
while (space_left(buffer) != 0)
{
bool is_token = true;
token_t t = {0};
char c = buffer->data[buffer->used];
if (isspace(c) || c == '\0')
{
// Clean whitespace
for (; space_left(buffer) > 0 && (isspace(c) || c == '\0');
++buffer->used, c = buffer->data[buffer->used])
continue;
is_token = false;
}
else if (space_left(buffer) > 1 && isdigit(buffer->data[buffer->used + 1]))
{
// Parsing literals
switch (c)
{
case 'b':
buffer->used++;
t = tokenise_byte_literal(buffer);
break;
case 'h':
buffer->used++;
t = tokenise_hword_literal(buffer);
break;
case 'w':
buffer->used++;
t = tokenise_word_literal(buffer);
break;
default:
// TODO: Lex Error (INVALID_LITERAL)
fprintf(stderr, "[LEX_ERROR]: Invalid literal `%c`\n", c);
exit(1);
}
}
else if (is_symbol(c))
{
t = tokenise_symbol(buffer);
}
if (is_token)
darr_append_bytes(&tokens, (byte *)&t, sizeof(t));
}
*n_tokens = tokens.used / sizeof(token_t);
return (token_t *)tokens.data;
}
int main(void)
{
FILE *fp = fopen("main.asm", "rb");
buffer_t buffer = darr_read_file(fp);
fclose(fp);
size_t n = 0;
token_t *tokens = tokenise_buffer(&buffer, &n);
printf("%lu bytes -> %lu tokens\n", buffer.used, n);
free(buffer.data);
for (size_t i = 0; i < n; ++i)
printf("%s(%.*s)\n", token_type_as_cstr(tokens[i].type),
(int)tokens[i].str_size, tokens[i].str);
// Free the tokens
for (size_t i = 0; i < n; ++i)
free(tokens[i].str);
free(tokens);
return 0;
}
|
