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
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
|
#include "./include/parser.h"
#include "./include/hash_table.h"
#include "./include/lexer.h"
#include "./include/macros.h"
#include "./include/token.h"
#include <stdbool.h>
#include <stdlib.h>
#include <string.h>
parser_t *init_parser(lexer_t *lexer) {
parser_t *p = (parser_t *)malloc(sizeof(parser_t));
if (p == NULL)
die("malloc on parser");
p->i = 0;
p->tokens = malloc(sizeof(token_t *));
p->symbol_table = init_hash_table(10000);
p->finished = false;
if (p->tokens == NULL)
die("malloc on p->tokens");
int size = 1;
token_t *t = lexer_collect_next(lexer);
p->tokens[size - 1] = t;
while (true) {
t = lexer_collect_next(lexer);
if (t == NULL)
break;
size++;
p->tokens = realloc(p->tokens, size * sizeof(token_t *));
p->tokens[size - 1] = t;
}
p->size = size;
return p;
}
void parser_move(parser_t *parser) {
if (parser->i != parser->size - 1)
parser->i++;
else
parser->finished = true;
}
void parser_eat(parser_t *parser, int type) {
parser_move(parser);
if (parser->tokens[parser->i]->type != type)
parser_error(parser);
}
ast_t *parse_bool(parser_t *parser) {
token_t *t = parser->tokens[parser->i];
parser_move(parser);
if (strcmp("T", t->value) == 0)
return init_ast_bool(true);
else
return init_ast_bool(false);
}
static char *escape_string(char *str) { return str; }
ast_t *parse_string(parser_t *parser) {
char *str = parser->tokens[parser->i]->value;
parser_move(parser);
return init_ast_string(escape_string(str));
}
ast_t *parse_int(parser_t *parser) {
int ret = atoi(parser->tokens[parser->i]->value);
parser_move(parser);
return init_ast_int(ret);
}
ast_t *parse_float(parser_t *parser) {
double ret = atof(parser->tokens[parser->i]->value);
parser_move(parser);
return init_ast_float(ret);
}
ast_t *parse_symbol(parser_t *parser) {
char *str = parser->tokens[parser->i]->value;
parser_move(parser);
return init_ast_symbol(str);
}
ast_t *parse_function_args(parser_t *parser) {
ast_t *car;
ast_t *head = init_ast_pair(NULL, NULL);
ast_t *cur = head;
parser_move(parser);
token_t *current_token = parser->tokens[parser->i];
while (current_token->type != TOKEN_RPAREN) {
if (parser->tokens[parser->i]->type != TOKEN_ID)
parser_error(parser);
car = parse_symbol(parser);
cur->car = car;
cur->cdr = init_ast_pair(NULL, NULL);
cur = cur->cdr;
parser_move(parser);
current_token = parser->tokens[parser->i];
}
parser_move(parser);
return head;
}
ast_t *parse_function(parser_t *parser) {
parser_move(parser);
parser_eat(parser, TOKEN_LPAREN);
/* TODO: actually write a helper function that also keeps track
of the amount of arguments and checks that they are all identifiers.*/
ast_t *car = parse_function_args(parser);
ast_t *cdr =
parse_expr(parser); /* a function can contain a single expression */
parser_eat(parser, TOKEN_RPAREN);
return init_ast_function(car, cdr);
}
void parse_bind(parser_t *parser) {
parser_move(parser);
parser_eat(parser, TOKEN_ID);
token_t *t = parser->tokens[parser->i];
char *name = t->value;
parser_move(parser);
ast_t *expr = parse_expr(parser); /* unevaluated expr will be evaluated when
hash table transfers to visitor JIT */
hash_table_add(parser->symbol_table, name, expr);
}
ast_t *parse_list(parser_t *parser) {
ast_t *car;
ast_t *head = init_ast_pair(NULL, NULL);
ast_t *cur = head;
parser_move(parser);
bool first_entry = true;
token_t *current_token = parser->tokens[parser->i];
while (current_token->type != TOKEN_RPAREN) {
if (parser->tokens[parser->i]->type == TOKEN_ID) {
if (strcmp(parser->tokens[parser->i]->value, "lambda") == 0 &&
first_entry) {
car = parse_function(parser);
first_entry = false;
} else if (strcmp(parser->tokens[parser->i]->value, "bind") == 0 &&
first_entry) {
parse_bind(parser);
return NULL;
} else {
car = parse_symbol(parser);
}
} else {
car = parse_expr(parser);
if (car == NULL)
parser_error(parser);
}
cur->car = car;
cur->cdr = init_ast_pair(NULL, NULL);
cur = cur->cdr;
first_entry = false;
parser_move(parser);
current_token = parser->tokens[parser->i];
}
parser_move(parser);
return head;
}
ast_t *parse_quote(parser_t *parser) {
parser_move(parser);
ast_t *car = init_ast_symbol("quote");
ast_t *expr = parse_expr(parser);
ast_t *ret = init_ast_pair(
car, init_ast_pair(
expr, init_ast_pair(NULL, NULL))); /* Converts ' to `quote` */
return ret;
}
ast_t *parse_expr(parser_t *parser) {
token_t *t = parser->tokens[parser->i];
if (t->type == TOKEN_STRING)
return parse_string(parser);
else if (t->type == TOKEN_INT)
return parse_int(parser);
else if (t->type == TOKEN_FLOAT)
return parse_float(parser);
else if (t->type == TOKEN_BOOL)
return parse_bool(parser);
else if (t->type == TOKEN_LPAREN)
return parse_list(parser);
else if (t->type == TOKEN_QUOTE)
return parse_quote(parser);
else if (t->type == TOKEN_ID)
return parse_symbol(parser);
else if (t->type == TOKEN_LPAREN)
return parse_list(parser);
else {
parser_error(parser);
}
return NULL;
}
ast_t *parse_all(parser_t *parser) {}
void parser_error(parser_t *parser) { exit(1); }
|
