summaryrefslogtreecommitdiff
path: root/core/lexer.c
blob: 51e4d40c17b706a8fb27d7a3fb91c0fde829c799 (plain)
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
/*
 * Copyright (c) 2026, Chloe M.
 * Provided under the BSD-3 clause
 */

#include <errno.h>
#include <stdbool.h>
#include <stdlib.h>
#include <ctype.h>
#include "cescal/lexer.h"
#include "cescal/log.h"
#include "cescal/ptrbox.h"

static inline void
lexer_putback(struct cescal_state *state, char c)
{
    if (state == NULL) {
        return;
    }

    state->lex_putback = c;
}

static inline char
lexer_putback_pop(struct cescal_state *state)
{
    char retc;

    if (state == NULL) {
        return '\0';
    }

    retc = state->lex_putback;
    state->lex_putback = '\0';
    return retc;
}

/*
 * Returns true if the given character is a whitespace
 *
 * @c: Character to check
 */
static inline bool
lexer_is_ws(char c)
{
    switch (c) {
    case '\t':
    case '\n':
    case ' ':
    case '\f':
    case '\r':
        return true;
    }

    return false;
}

/*
 * Consume a single character from the input source file and
 * optionally skip whitespace
 *
 * @state: Compiler state
 * @skip_ws: If true skip whitespace
 */
static char
lexer_consume_single(struct cescal_state *state, bool skip_ws)
{
    char c;

    if (state == NULL) {
        return '\0';
    }

    if ((c = lexer_putback_pop(state)) != '\0') {
        if (lexer_is_ws(c) && !skip_ws) {
            return c;
        }
    }

    while ((c = readbuf_read(&state->rb, state->in_fd)) != '\0') {
        if (lexer_is_ws(c)) {
            continue;
        }

        return c;
    }

    return '\0';
}

static int
lexer_scan_ident(struct cescal_state *state, char lc, struct token *res)
{
    char *buf, c;
    size_t bufsz, bufcap;

    if (state == NULL || res == NULL) {
        errno = EINVAL;
        return -1;
    }

    bufsz = 0;
    bufcap = 8;
    if ((buf = malloc(bufcap)) == NULL) {
        return -1;
    }

    if (lc != '_' && !isalpha(lc)) {
        cc_error("bad identifier\n");
    }

    buf[bufsz++] = lc;
    for (;;) {
        c = lexer_consume_single(state, false);
        if (c != '_' && !isalnum(c)) {
            lexer_putback(state, c);
            buf[bufsz] = '\0';
            break;
        }

        buf[bufsz++] = c;
        if (bufsz >= bufcap) {
            bufcap += 8;
            buf = realloc(buf, bufcap);
        }

        if (buf == NULL) {
            return -1;
        }
    }

    res->s = ptrbox_strdup(&state->ptrbox, buf);
    res->type = TT_IDENT;
    free(buf);
    return 0;
}

int
lexer_nom(struct cescal_state *state, struct token *res)
{
    char c;

    if (state == NULL || res == NULL) {
        errno = EINVAL;
        return -1;
    }

    if ((c = lexer_consume_single(state, true)) == '\0') {
        return -1;
    }

    switch (c) {
    case '(':
        res->type = TT_LPAREN;
        res->c = c;
        return 0;
    case ')':
        res->type = TT_RPAREN;
        res->c = c;
        return 0;
    case ',':
        res->type = TT_COMMA;
        res->c = c;
        return 0;
    default:
        if (lexer_scan_ident(state, c, res) == 0) {
            return 0;
        }
    }

    cc_error("got unknown token '%c'\n", c);
    return -1;
}