-
-
Notifications
You must be signed in to change notification settings - Fork 340
/
lexer.go
276 lines (230 loc) · 4.05 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
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
package search
import (
"fmt"
"unicode"
"unicode/utf8"
)
type TokenType int
type Token struct {
Type TokenType
Literal string
}
const eof = 0
// Token types.
const (
// Flow.
TokInvalid TokenType = iota
TokEOF
TokParenOpen
TokParenClose
// Literals.
TokString
// Boolean operators.
TokOpNot
TokOpAnd
TokOpOr
// Comparison operators.
TokOpEq
TokOpNotEq
TokOpGt
TokOpLt
TokOpGtEq
TokOpLtEq
TokOpRe
TokOpNotRe
)
var (
keywords = map[string]TokenType{
"NOT": TokOpNot,
"AND": TokOpAnd,
"OR": TokOpOr,
}
reservedRunes = []rune{'=', '!', '<', '>', '(', ')'}
tokenTypeStrings = map[TokenType]string{
TokInvalid: "INVALID",
TokEOF: "EOF",
TokParenOpen: "(",
TokParenClose: ")",
TokString: "STRING",
TokOpNot: "NOT",
TokOpAnd: "AND",
TokOpOr: "OR",
TokOpEq: "=",
TokOpNotEq: "!=",
TokOpGt: ">",
TokOpLt: "<",
TokOpGtEq: ">=",
TokOpLtEq: "<=",
TokOpRe: "=~",
TokOpNotRe: "!~",
}
)
type stateFn func(*Lexer) stateFn
type Lexer struct {
input string
pos int
start int
width int
tokens chan Token
}
func NewLexer(input string) *Lexer {
l := &Lexer{
input: input,
tokens: make(chan Token),
}
go l.run(begin)
return l
}
func (l *Lexer) Next() Token {
return <-l.tokens
}
func (tt TokenType) String() string {
if typeString, ok := tokenTypeStrings[tt]; ok {
return typeString
}
return "<unknown>"
}
func (l *Lexer) run(init stateFn) {
for nextState := init; nextState != nil; {
nextState = nextState(l)
}
close(l.tokens)
}
func (l *Lexer) read() (r rune) {
if l.pos >= len(l.input) {
l.width = 0
return eof
}
r, l.width = utf8.DecodeRuneInString(l.input[l.pos:])
l.pos += l.width
return
}
func (l *Lexer) emit(tokenType TokenType) {
l.tokens <- Token{
Type: tokenType,
Literal: l.input[l.start:l.pos],
}
l.start = l.pos
}
func (l *Lexer) ignore() {
l.start = l.pos
}
func (l *Lexer) skip() {
l.pos += l.width
l.start = l.pos
}
func (l *Lexer) backup() {
l.pos -= l.width
}
func (l *Lexer) errorf(format string, args ...interface{}) stateFn {
l.tokens <- Token{
Type: TokInvalid,
Literal: fmt.Sprintf(format, args...),
}
return nil
}
func begin(l *Lexer) stateFn {
r := l.read()
switch r {
case '=':
if next := l.read(); next == '~' {
l.emit(TokOpRe)
} else {
l.backup()
l.emit(TokOpEq)
}
return begin
case '!':
switch next := l.read(); next {
case '=':
l.emit(TokOpNotEq)
case '~':
l.emit(TokOpNotRe)
default:
return l.errorf("invalid rune %v", r)
}
return begin
case '<':
if next := l.read(); next == '=' {
l.emit(TokOpLtEq)
} else {
l.backup()
l.emit(TokOpLt)
}
return begin
case '>':
if next := l.read(); next == '=' {
l.emit(TokOpGtEq)
} else {
l.backup()
l.emit(TokOpGt)
}
return begin
case '(':
l.emit(TokParenOpen)
return begin
case ')':
l.emit(TokParenClose)
return begin
case '"':
return l.delimString(r)
case eof:
l.emit(TokEOF)
return nil
}
if unicode.IsSpace(r) {
l.ignore()
return begin
}
return unquotedString
}
func (l *Lexer) delimString(delim rune) stateFn {
// Ignore the start delimiter rune.
l.ignore()
for r := l.read(); r != delim; r = l.read() {
if r == eof {
return l.errorf("unexpected EOF, unclosed delimiter")
}
}
// Don't include the end delimiter in emitted token.
l.backup()
l.emit(TokString)
// Skip end delimiter.
l.skip()
return begin
}
func unquotedString(l *Lexer) stateFn {
for r := l.read(); ; r = l.read() {
switch {
case r == eof:
l.backup()
l.emitUnquotedString()
return begin
case unicode.IsSpace(r):
l.backup()
l.emitUnquotedString()
l.skip()
return begin
case isReserved(r):
l.backup()
l.emitUnquotedString()
return begin
}
}
}
func (l *Lexer) emitUnquotedString() {
str := l.input[l.start:l.pos]
if tokType, ok := keywords[str]; ok {
l.emit(tokType)
return
}
l.emit(TokString)
}
func isReserved(r rune) bool {
for _, v := range reservedRunes {
if r == v {
return true
}
}
return false
}