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
|
//go:generate re2go $INPUT -o $OUTPUT
package main
import "fmt"
import "os"
var SIZE int = 11
type YYCTYPE = byte
type Input struct {
file *os.File
data []YYCTYPE
cursor int
marker int
token int
limit int
eof bool
}
func fill(in *Input) int {
// If nothing can be read, fail.
if in.eof {
return 1
}
// Check if at least some space can be freed.
if in.token == 0 {
// In real life can reallocate a larger buffer.
panic("fill error: lexeme too long")
}
// Discard everything up to the start of the current lexeme,
// shift buffer contents and adjust offsets.
copy(in.data[0:], in.data[in.token:in.limit])
in.cursor -= in.token
in.marker -= in.token
in.limit -= in.token
in.token = 0
// Read new data (as much as possible to fill the buffer).
n, _ := in.file.Read(in.data[in.limit:SIZE])
in.limit += n
in.data[in.limit] = 0
fmt.Printf("fill: %v '%s'\n", in.data[:in.limit+1],
string(in.data[:in.limit]))
// If read less than expected, this is the end of input.
in.eof = in.limit < SIZE
// If nothing has been read, fail.
if n == 0 {
return 1
}
return 0
}
func Lex(in *Input) int {
YYPEEK := func() YYCTYPE { return in.data[in.cursor] }
YYSKIP := func() { in.cursor++ }
YYBACKUP := func() { in.marker = in.cursor }
YYRESTORE := func() { in.cursor = in.marker }
YYLESSTHAN := func(n int) bool { return in.limit-in.cursor < n }
YYFILL := func() int { return fill(in) }
in.token = in.cursor
/*!re2c
re2c:eof = 0;
re2c:api:style = functions;
* {
fmt.Println("error")
return -1
}
$ {
fmt.Println("end")
return 0
}
[0-9]+ {
fmt.Printf("number-1: %v\n", string(in.data[in.token:in.cursor]))
return 1
}
[0-9]+ [-] [0-9]+ {
fmt.Printf("number-2: %v\n", string(in.data[in.token:in.cursor]))
return 2
}
[ ] {
return 3
}
*/
}
func test(data string) (result int) {
tmpfile := "input.txt"
f, _ := os.Create(tmpfile)
f.WriteString(data)
f.Seek(0, 0)
defer func() {
if r := recover(); r != nil {
fmt.Println(r)
result = -2
}
f.Close()
os.Remove(tmpfile)
}()
in := &Input{
file: f,
data: make([]byte, SIZE+1),
cursor: SIZE,
marker: SIZE,
token: SIZE,
limit: SIZE,
eof: false,
}
result = 9999
for result > 0 {
result = Lex(in)
}
return
}
func main() {
var s string
// Succeeds, the lexer needs 1 character ahead.
s = " 1234567890 "
if test(s) != 0 {
panic("expected 'number: 1234567890'")
}
// Fails, the lexer needs 1 character ahead, but there is no space.
s = " 12345678901 "
if test(s) != -2 {
panic("expected 'fill error: lexeme too long'")
}
// Succeeds, the lexer needs 1 character ahead.
s = " 12345-6789 "
if test(s) != 0 {
panic("expected 'number: 12345-6789'")
}
// Fails, the lexer needs 1 character ahead, but there is no space.
s = " 12345-67890 "
if test(s) != -2 {
panic("expected 'fill error: lexeme too long'")
}
// Fails, invalid input.
s = "?#!*"
if test(s) != -1 {
panic("expected 'error'")
}
fmt.Println("OK")
}
|
