forked from frustra/bbcode
-
Notifications
You must be signed in to change notification settings - Fork 0
/
lexer.go
260 lines (241 loc) · 4.56 KB
/
lexer.go
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
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
// Copyright 2015 Frustra. All rights reserved.
// Use of this source code is governed by the MIT
// license that can be found in the LICENSE file.
package bbcode
import (
"bytes"
"strings"
)
type Token struct {
ID string
Value interface{}
}
type lexer struct {
input string
tokens chan Token
start int
end int
pos int
tagName string
tagValue string
tagTmpName string
tagTmpValue string
tagArgs map[string]string
}
const (
TEXT = "text"
OPENING_TAG = "opening"
CLOSING_TAG = "closing"
)
func newLexer(str string) *lexer {
return &lexer{
input: str,
tokens: make(chan Token),
}
}
func Lex(str string) chan Token {
lex := newLexer(str)
go lex.runStateMachine()
return lex.tokens
}
func (l *lexer) runStateMachine() {
for state := lexText; state != nil; {
state = state(l)
}
close(l.tokens)
}
func (l *lexer) emit(id string, value interface{}) {
if l.pos > 0 {
// fmt.Println(l.input)
// fmt.Printf("Emit %s: %+v\n", id, value)
l.tokens <- Token{id, value}
l.input = l.input[l.pos:]
l.pos = 0
}
}
type stateFn func(*lexer) stateFn
func lexText(l *lexer) stateFn {
for l.pos < len(l.input) {
if l.input[l.pos] == '[' {
l.emit(TEXT, l.input[:l.pos])
return lexOpenBracket
}
l.pos++
}
l.emit(TEXT, l.input)
return nil
}
func lexOpenBracket(l *lexer) stateFn {
l.pos++
closingTag := false
for l.pos < len(l.input) {
switch l.input[l.pos] {
case '[', ']':
return lexText
default:
if l.input[l.pos] == '/' && !closingTag {
closingTag = true
} else if l.input[l.pos] != ' ' && l.input[l.pos] != '\t' && l.input[l.pos] != '\n' {
if closingTag {
return lexClosingTag
} else {
l.tagName = ""
l.tagValue = ""
l.tagArgs = make(map[string]string)
return lexTagName
}
}
}
l.pos++
}
l.emit(TEXT, l.input)
return nil
}
func lexClosingTag(l *lexer) stateFn {
whiteSpace := false
l.start = l.pos
l.end = l.pos
for l.pos < len(l.input) {
switch l.input[l.pos] {
case '[':
return lexText
case ']':
l.pos++
l.emit(CLOSING_TAG, BBClosingTag{strings.ToLower(l.input[l.start:l.end]), l.input[:l.pos]})
return lexText
case ' ', '\t', '\n':
whiteSpace = true
default:
if whiteSpace {
return lexText
} else {
l.end++
}
}
l.pos++
}
l.emit(TEXT, l.input)
return nil
}
func lexTagName(l *lexer) stateFn {
l.tagTmpValue = ""
whiteSpace := false
l.start = l.pos
l.end = l.pos
for l.pos < len(l.input) {
switch l.input[l.pos] {
case '[':
return lexText
case ']':
l.tagTmpName = l.input[l.start:l.end]
return lexTagArgs
case '=':
l.tagTmpName = l.input[l.start:l.end]
return lexTagValue
case ' ', '\t', '\n':
whiteSpace = true
default:
if whiteSpace {
l.tagTmpName = l.input[l.start:l.end]
return lexTagArgs
} else {
l.end++
}
}
l.pos++
}
l.emit(TEXT, l.input)
return nil
}
func lexTagValue(l *lexer) stateFn {
l.pos++
loop:
for l.pos < len(l.input) {
switch l.input[l.pos] {
case ' ', '\t', '\n':
l.pos++
case '"', '\'':
return lexQuotedValue
default:
break loop
}
}
l.start = l.pos
l.end = l.pos
for l.pos < len(l.input) {
switch l.input[l.pos] {
case '[':
return lexText
case ']':
l.tagTmpValue = l.input[l.start:l.end]
return lexTagArgs
case ' ', '\t', '\n':
l.tagTmpValue = l.input[l.start:l.end]
return lexTagArgs
default:
l.end++
}
l.pos++
}
l.emit(TEXT, l.input)
return nil
}
func lexQuotedValue(l *lexer) stateFn {
quoteChar := l.input[l.pos]
l.pos++
l.start = l.pos
var buf bytes.Buffer
escape := false
for l.pos < len(l.input) {
if escape {
if l.input[l.pos] == 'n' {
buf.WriteRune('\n')
} else {
buf.WriteRune(rune(l.input[l.pos]))
}
escape = false
} else {
switch l.input[l.pos] {
case '\\':
escape = true
case '\n':
l.pos = l.start
return lexText
case quoteChar:
l.pos++
l.tagTmpValue = buf.String()
return lexTagArgs
default:
buf.WriteRune(rune(l.input[l.pos]))
}
}
l.pos++
}
l.pos = l.start
return lexText
}
func lexTagArgs(l *lexer) stateFn {
if len(l.tagName) > 0 {
l.tagArgs[strings.ToLower(l.tagTmpName)] = l.tagTmpValue
} else {
l.tagName = l.tagTmpName
l.tagValue = l.tagTmpValue
}
for l.pos < len(l.input) {
switch l.input[l.pos] {
case '[':
return lexText
case ']':
l.pos++
l.emit(OPENING_TAG, BBOpeningTag{strings.ToLower(l.tagName), l.tagValue, l.tagArgs, l.input[:l.pos]})
return lexText
case ' ', '\t', '\n':
l.pos++
default:
l.tagTmpName = ""
return lexTagName
}
}
l.emit(TEXT, l.input)
return nil
}