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
|
import std._io.stdio_reader;
fn in_range(char c, char lo, char hi) -> bool {
ret lo <= c && c <= hi;
}
fn is_alpha(char c) -> bool {
ret in_range(c, 'a', 'z') ||
in_range(c, 'A', 'Z');
}
fn is_dec_digit(char c) -> bool {
ret in_range(c, '0', '9');
}
fn is_hex_digit(char c) -> bool {
ret in_range(c, '0', '9') ||
in_range(c, 'a', 'f') ||
in_range(c, 'A', 'F');
}
fn is_bin_digit(char c) -> bool {
ret c == '0' || c == '1';
}
fn is_whitespace(char c) -> bool {
ret c == ' ' || c == '\t' || c == '\r';
}
fn next_token(stdio_reader rdr) -> token.token {
auto eof = (-1) as char;
auto c = rdr.getc() as char;
auto accum = "";
while (is_whitespace(c) && c != eof) {
c = rdr.getc() as char;
}
if (c == eof) { ret token.EOF(); }
if (is_alpha(c)) {
while (is_alpha(c)) {
accum += (c as u8);
c = rdr.getc() as char;
}
rdr.ungetc(c as int);
ret token.IDENT(accum);
}
if (is_dec_digit(c)) {
if (c == '0') {
} else {
while (is_dec_digit(c)) {
accum += (c as u8);
c = rdr.getc() as char;
}
rdr.ungetc(c as int);
ret token.LIT_INT(0);
}
}
// One-byte structural symbols.
if (c == ';') { ret token.SEMI(); }
if (c == '.') { ret token.DOT(); }
if (c == '(') { ret token.LPAREN(); }
if (c == ')') { ret token.RPAREN(); }
if (c == '{') { ret token.LBRACE(); }
if (c == '}') { ret token.RBRACE(); }
if (c == '[') { ret token.LBRACKET(); }
if (c == ']') { ret token.RBRACKET(); }
if (c == '@') { ret token.AT(); }
if (c == '#') { ret token.POUND(); }
log "lexer stopping at ";
log c;
ret token.EOF();
}
//
// Local Variables:
// mode: rust
// fill-column: 78;
// indent-tabs-mode: nil
// c-basic-offset: 4
// buffer-file-coding-system: utf-8-unix
// compile-command: "make -k -C ../.. 2>&1 | sed -e 's/\\/x\\//x:\\//g'";
// End:
//
|