-
Notifications
You must be signed in to change notification settings - Fork 0
/
scanner.c
222 lines (195 loc) · 6.6 KB
/
scanner.c
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
210
211
212
213
214
215
216
217
218
219
220
221
222
#include <stdio.h>
#include <string.h>
#include "common.h"
#include "scanner.h"
typedef struct {
const char* start; // marks the beginning of the current lexeme
const char* current; // points to the current character being looked at
int line;
} Scanner;
Scanner scanner;
void initScanner(const char* source) {
scanner.start = source;
scanner.current = source;
scanner.line = 1;
}
static bool isAlpha(char c) {
return (c >= 'a' && c <= 'z') ||
(c >= 'A' && c <= 'Z') ||
c == '_';
}
static bool isDigit(char c) { return c >= '0' && c <= '9'; }
static bool isAtEnd() { return *scanner.current == '\0'; }
/* This is a Token constructor */
static Token makeToken(TokenType type) {
Token token;
token.type = type;
token.start = scanner.start;
token.length = (int)(scanner.current - scanner.start);
token.line = scanner.line;
return token;
}
static char advance() {
++scanner.current;
return scanner.current[-1];
}
/* This returns the current charchter without consuming it */
static char peek() { return *scanner.current; }
static char peekNext() {
if (isAtEnd()) return '\0';
return scanner.current[1];
}
/*
If the current character is the desired one, we advance and return true.
Otherwise, we return false to indicate it wasn’t matched.
*/
static bool match(char expected) {
if (isAtEnd()) return false;
if (*scanner.current != expected) return false;
++scanner.current;
return true;
}
static Token errorToken(const char* message) {
Token token;
token.type = TOKEN_ERROR;
token.start = message;
token.length = (int)strlen(message);
token.line = scanner.line;
return token;
}
/*
This advances the scanner past any leading whitespace. After this call
returns, we know the very next character is a meaningful one
*/
static void skipWhitespace() {
for (;;) {
char c = peek();
switch (c) {
case ' ':
case '\r':
case '\t':
advance();
break;
case '\n':
++scanner.line;
advance();
break;
case '/': /* skipping comments */
if (peekNext() == '/') {
// A comment does untill the end of the line
while (peek() != '\n' && !isAtEnd()) advance();
} else return;
break;
default: return;
}
}
}
static TokenType checkKeyword(int start, int length, const char* rest, TokenType type) {
if (scanner.current - scanner.start == start + length && memcmp(scanner.start + start, rest, length) == 0)
return type;
return TOKEN_IDENTIFIER;
}
static TokenType identifierType() {
switch (scanner.start[0]) {
case 'a': return checkKeyword(1, 2, "nd", TOKEN_AND);
case 'c': return checkKeyword(1, 4, "lass", TOKEN_CLASS);
case 'e': return checkKeyword(1, 3, "lse", TOKEN_ELSE);
case 'f':
if (scanner.current - scanner.start > 1) {
switch (scanner.start[1]) {
case 'a': return checkKeyword(2, 3, "lse", TOKEN_FALSE);
case 'o': return checkKeyword(2, 1, "r", TOKEN_FOR);
case 'u': return checkKeyword(2, 1, "n", TOKEN_FUN);
}
}
break;
case 'i': return checkKeyword(1, 1, "f", TOKEN_IF);
case 'n': return checkKeyword(1, 2, "il", TOKEN_NIL);
case 'o': return checkKeyword(1, 1, "r", TOKEN_OR);
case 'p': return checkKeyword(1, 4, "rint", TOKEN_PRINT);
case 'r': return checkKeyword(1, 5, "eturn", TOKEN_RETURN);
case 's': return checkKeyword(1, 4, "uper", TOKEN_SUPER);
case 't':
if (scanner.current - scanner.start > 1) {
switch (scanner.start[1]) {
case 'h': return checkKeyword(2, 2, "is", TOKEN_THIS);
case 'r': return checkKeyword(2, 2, "ue", TOKEN_TRUE);
}
}
break;
case 'v': return checkKeyword(1, 2, "ar", TOKEN_VAR);
case 'w': return checkKeyword(1, 4, "hile", TOKEN_WHILE);
}
return TOKEN_IDENTIFIER;
}
/*
After the first letter, we allow digits too, and we keep consuming alphanumerics until we run out of them.
*/
static Token identifier() {
while (isAlpha(peek()) || isDigit(peek())) advance();
return makeToken(identifierType());
}
static Token number() {
while (isDigit(peek())) advance();
/* Look for a fractional part */
if (peek() == '.' && isDigit(peekNext())) {
/* Consume the "." */
advance();
while (isDigit(peek())) advance();
}
return makeToken(TOKEN_NUMBER);
}
static Token string() {
while (peek() != '"' && !isAtEnd()) {
if (peek() == '\n') ++scanner.line; /* Tracking lines (supporting multi-line strings) */
advance();
}
if (isAtEnd()) return errorToken("Unterminated string.");
// The closing quote
advance();
return makeToken(TOKEN_STRING);
}
/*
Each call to 'scanToken' scans a complete token
*/
Token scanToken() {
skipWhitespace();
scanner.start = scanner.current;
if (isAtEnd()) return makeToken(TOKEN_EOF);
char c = advance();
if (isAlpha(c)) return identifier();
if (isDigit(c)) return number();
switch (c) {
case '(': return makeToken(TOKEN_LEFT_PAREN);
case ')': return makeToken(TOKEN_RIGHT_PAREN);
case '{': return makeToken(TOKEN_LEFT_BRACE);
case '}': return makeToken(TOKEN_RIGHT_BRACE);
case ';': return makeToken(TOKEN_SEMICOLON);
case ',': return makeToken(TOKEN_COMMA);
case '.': return makeToken(TOKEN_DOT);
case '-': return makeToken(TOKEN_MINUS);
case '+': return makeToken(TOKEN_PLUS);
case '*': return makeToken(TOKEN_STAR);
case '%': return makeToken(TOKEN_PERCENT);
case '/': return makeToken(TOKEN_SLASH);
case '\\': return makeToken(TOKEN_BACKSLASH);
case '!':
return makeToken(
match('=') ? TOKEN_BANG_EQUAL : TOKEN_BANG
);
case '=':
return makeToken(
match('=') ? TOKEN_EQUAL_EQUAL : TOKEN_EQUAL
);
case '<':
return makeToken(
match('=') ? TOKEN_LESS_EQUAL : TOKEN_LESS
);
case '>':
return makeToken(
match('=') ? TOKEN_GREATER_EQUAL : TOKEN_GREATER
);
case '"': return string();
}
return errorToken("Unexpected charchter.");
}