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
|
// Copyright 2026 Rose Hogenson <r@roseh.moe>
//
// This file is part of roseh.moe/pkg/ccl.
//
// roseh.moe/pkg/ccl is free software: you can redistribute it and/or modify it
// under the terms of the GNU General Public License as published by the Free
// Software Foundation, either version 3 of the License, or (at your option)
// any later version.
//
// roseh.moe/pkg/ccl is distributed in the hope that it will be useful, but
// WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
// or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
// more details.
//
// You should have received a copy of the GNU General Public License along with
// roseh.moe/pkg/ccl. If not, see <https://www.gnu.org/licenses/>.
package ccl
import (
"bytes"
"unicode"
"unicode/utf8"
)
type lexer struct {
data []byte
i int
}
func (l *lexer) error(reason string, args ...any) error {
return newSyntaxError(l.data, l.i, reason, args...)
}
func (l *lexer) yield(n int) (int, []byte, error) {
i := l.i
l.i += n
return i, l.data[i : i+n], nil
}
func (l *lexer) skipSpace() error {
Space:
for l.i < len(l.data) {
if bytes.HasPrefix(l.data[l.i:], []byte("#")) || bytes.HasPrefix(l.data[l.i:], []byte("//")) {
for ; l.i < len(l.data) && l.data[l.i] != '\n'; l.i++ {
}
continue
}
if bytes.HasPrefix(l.data[l.i:], []byte("/*")) {
for i := l.i; i < len(l.data); i++ {
if bytes.HasPrefix(l.data[i:], []byte("*/")) {
l.i = i + 2
continue Space
}
}
return l.error("unterminated comment")
}
if r, n := utf8.DecodeRune(l.data[l.i:]); unicode.IsSpace(r) {
l.i += n
continue
}
break
}
return nil
}
func numFirstByte(b byte) bool {
return b == '-' ||
b == '+' ||
b == '.' ||
'0' <= b && b <= '9'
}
func numTailByte(b byte) bool {
return numFirstByte(b) ||
'a' <= b && b <= 'z' ||
'A' <= b && b <= 'Z'
}
func fieldFirstByte(b byte) bool {
return b == '_' ||
'a' <= b && b <= 'z' ||
'A' <= b && b <= 'Z'
}
func fieldTailByte(b byte) bool {
return fieldFirstByte(b) ||
'0' <= b && b <= '9'
}
func (l *lexer) next() (int, []byte, error) {
if err := l.skipSpace(); err != nil {
return 0, nil, err
}
if l.i == len(l.data) {
return 0, nil, errEOF
}
switch l.data[l.i] {
case
'{',
'}',
'[',
']',
':',
',':
return l.yield(1)
case '\'', '"':
q := l.data[l.i]
i := l.i + 1
for ; i < len(l.data) && l.data[i] != q; i++ {
if l.data[i] == '\\' {
i++
}
}
if i >= len(l.data) {
return 0, nil, l.error("unterminated string")
}
return l.yield(i + 1 - l.i)
}
switch b := l.data[l.i]; {
case numFirstByte(b):
i := l.i + 1
for ; i < len(l.data) && numTailByte(l.data[i]); i++ {
}
return l.yield(i - l.i)
case fieldFirstByte(b):
i := l.i + 1
for ; i < len(l.data) && fieldTailByte(l.data[i]); i++ {
}
return l.yield(i - l.i)
}
return 0, nil, l.error("invalid lexeme")
}
|
