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
|
/* 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: 2023-10-24
* Author: Aryadev Chavali
* Description: Lexer for assembly language
*/
#include <ctype.h>
#include <stdbool.h>
#include <stdio.h>
#include <string.h>
#include "./lexer.h"
const char *token_type_as_cstr(token_type_t type)
{
switch (type)
{
case TOKEN_LITERAL_BYTE:
return "LITERAL_BYTE";
case TOKEN_LITERAL_HWORD:
return "LITERAL_HWORD";
case TOKEN_LITERAL_WORD:
return "LITERAL_WORD";
case TOKEN_LITERAL_CHAR:
return "LITERAL_CHAR";
case TOKEN_SYMBOL:
return "SYMBOL";
}
return "";
}
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_LITERAL_BYTE};
tokenise_literal(buffer, &token);
return token;
}
token_t tokenise_hword_literal(buffer_t *buffer)
{
token_t token = {.type = TOKEN_LITERAL_HWORD};
tokenise_literal(buffer, &token);
return token;
}
token_t tokenise_word_literal(buffer_t *buffer)
{
token_t token = {.type = TOKEN_LITERAL_WORD};
tokenise_literal(buffer, &token);
return token;
}
token_t tokenise_char_literal(buffer_t *buffer)
{
token_t token = {.type = TOKEN_LITERAL_CHAR, .str_size = 1};
token.str = calloc(1, 1);
token.str[0] = buffer->data[buffer->used + 1];
buffer->used += 3;
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 numeric 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_NUMERIC_LITERAL)
exit(1);
}
}
else if (is_symbol(c))
t = tokenise_symbol(buffer);
else if (c == '\'')
{
if (space_left(buffer) < 2 || buffer->data[buffer->used + 2] != '\'')
// TODO: Lex Error (INVALID_CHAR_LITERAL)
exit(1);
t = tokenise_char_literal(buffer);
}
if (is_token)
darr_append_bytes(&tokens, (byte *)&t, sizeof(t));
}
*n_tokens = tokens.used / sizeof(token_t);
return (token_t *)tokens.data;
}
|
