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
|
#include "lexer.h"
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
struct lexer *lexer_new(const char *input)
{
struct lexer *new = malloc(sizeof(struct lexer));
new->input = input;
new->pos = 0;
return new;
}
void lexer_free(struct lexer *lexer)
{
free(lexer);
}
struct template
{
char value;
enum token_type type;
};
struct template templates[] = {
{ '+', TOKEN_PLUS }, { '-', TOKEN_MINUS }, { '*', TOKEN_MUL },
{ '/', TOKEN_DIV }, { '(', TOKEN_LEFT_PAR }, { ')', TOKEN_RIGHT_PAR },
{ '\0', TOKEN_EOF }, { 0, TOKEN_ERROR }
};
static ssize_t parse_number(struct lexer *l)
{
union
{
const char *cc;
char *c;
} cast;
cast.cc = l->input + l->pos;
char *in = cast.c;
size_t t = 0;
while (in[t] && in[t] >= '0' && in[t] <= '9')
t++;
char tmp = in[t];
in[t] = '\0';
ssize_t res = atoi(in);
in[t] = tmp;
return res;
}
struct token lexer_next_token(struct lexer *lexer)
{
for (; lexer->input[lexer->pos] && lexer->input[lexer->pos] == ' ';
lexer->pos++)
continue;
for (int i = 0; i < 7; i++)
{
if (lexer->input[lexer->pos] == templates[i].value)
{
lexer->current_tok.type = templates[i].type;
return lexer->current_tok;
}
}
if (lexer->input[lexer->pos] > '9' || lexer->input[lexer->pos] < '0')
{
lexer->current_tok.type = TOKEN_ERROR;
fprintf(stderr, "lexer: invalid token %c\n", lexer->input[lexer->pos]);
return lexer->current_tok;
}
else
{
lexer->current_tok.type = TOKEN_NUMBER;
lexer->current_tok.value = parse_number(lexer);
return lexer->current_tok;
}
}
struct token lexer_peek(struct lexer *lexer)
{
return lexer_next_token(lexer);
}
static size_t count_numbers(ssize_t value)
{
if (value == 0)
return 1;
size_t size = 0;
while (value)
{
size++;
value /= 10;
}
return size;
}
struct token lexer_pop(struct lexer *lexer)
{
struct token res = lexer_next_token(lexer);
if (res.type == TOKEN_NUMBER)
lexer->pos += count_numbers(res.value);
else
lexer->pos++;
return res;
}
|
