forked from tars-go/tars
/
lex.go
408 lines (367 loc) · 7.04 KB
/
lex.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
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
package main
import (
"bytes"
"strconv"
"strings"
)
//EOS is byte stream terminator
const EOS = 0
//TK is a byte type.
type TK byte
const (
tkEos TK = iota
tkBracel // ({)
tkBracer // }
tkSemi //;
tkEq //=
tkShl //<
tkShr //>
tkComma //,
tkPtl //(
tkPtr //)
tkSquarel //[
tkSquarer //]
tkInclude //#include
tkDummyKeywordBegin
// keyword
tkModule
tkEnum
tkStruct
tkInterface
tkRequire
tkOptional
tkConst
tkUnsigned
tkVoid
tkOut
tkKey
tkTrue
tkFalse
tkDummyKeywordEnd
tkDummyTypeBegin
// type
tkTInt
tkTBool
tkTShort
tkTByte
tkTLong
tkTFloat
tkTDouble
tkTString
tkTVector
tkTMap
tkTArray
tkDummyTypeEnd
tkName // variable name
// value
tkString
tkInteger
tkFloat
)
//TokenMap record token value.
var TokenMap = [...]string{
tkEos: "<eos>",
tkBracel: "{",
tkBracer: "}",
tkSemi: ";",
tkEq: "=",
tkShl: "<",
tkShr: ">",
tkComma: ",",
tkPtl: "(",
tkPtr: ")",
tkSquarel: "[",
tkSquarer: "]",
tkInclude: "#include",
// keyword
tkModule: "module",
tkEnum: "enum",
tkStruct: "struct",
tkInterface: "interface",
tkRequire: "require",
tkOptional: "optional",
tkConst: "const",
tkUnsigned: "unsigned",
tkVoid: "void",
tkOut: "out",
tkKey: "key",
tkTrue: "true",
tkFalse: "false",
// type
tkTInt: "int",
tkTBool: "bool",
tkTShort: "short",
tkTByte: "byte",
tkTLong: "long",
tkTFloat: "float",
tkTDouble: "double",
tkTString: "string",
tkTVector: "vector",
tkTMap: "map",
tkTArray: "array",
tkName: "<name>",
// value
tkString: "<string>",
tkInteger: "<INTEGER>",
tkFloat: "<FLOAT>",
}
//SemInfo is struct.
type SemInfo struct {
I int64
F float64
S string
}
//Token record token information.
type Token struct {
T TK
S *SemInfo
Line int
}
//LexState record lexical state.
type LexState struct {
current byte
linenumber int
//t Token
//lookahead Token
tokenBuff bytes.Buffer
buff *bytes.Buffer
source string
}
func isNewLine(b byte) bool {
return b == '\r' || b == '\n'
}
func isNumber(b byte) bool {
return (b >= '0' && b <= '9') || b == '-'
}
func isHexNumber(b byte) bool {
return (b >= 'a' && b <= 'f') || (b >= 'A' && b <= 'F')
}
func isLetter(b byte) bool {
return (b >= 'a' && b <= 'z') || (b >= 'A' && b <= 'Z') || b == '_'
}
func isType(t TK) bool {
return t > tkDummyTypeBegin && t < tkDummyTypeEnd
}
func isNumberType(t TK) bool {
switch t {
case tkTInt, tkTBool, tkTShort, tkTByte, tkTLong, tkTFloat, tkTDouble:
return true
default:
return false
}
}
func (ls *LexState) lexErr(err string) {
line := strconv.Itoa(ls.linenumber)
panic(ls.source + ": " + line + ". " + err)
}
func (ls *LexState) incLine() {
old := ls.current
ls.next() /* skip '\n' or '\r' */
if isNewLine(ls.current) && ls.current != old {
ls.next() /* skip '\n\r' or '\r\n' */
}
ls.linenumber++
}
func (ls *LexState) readNumber() (TK, *SemInfo) {
hasDot := false
isHex := false
sem := &SemInfo{}
for isNumber(ls.current) || ls.current == '.' || ls.current == 'x' || ls.current == 'X' || (isHex && isHexNumber(ls.current)) {
if ls.current == '.' {
hasDot = true
} else if ls.current == 'x' || ls.current == 'X' {
isHex = true
}
ls.tokenBuff.WriteByte(ls.current)
ls.next()
}
sem.S = ls.tokenBuff.String()
if hasDot {
f, err := strconv.ParseFloat(sem.S, 64)
if err != nil {
ls.lexErr(err.Error())
}
sem.F = f
return tkFloat, sem
}
i, err := strconv.ParseInt(sem.S, 0, 64)
if err != nil {
ls.lexErr(err.Error())
}
sem.I = i
return tkInteger, sem
}
func (ls *LexState) readIdent() (TK, *SemInfo) {
sem := &SemInfo{}
var last byte
// :: Point number processing namespace
for isLetter(ls.current) || isNumber(ls.current) || ls.current == ':' {
if isNumber(ls.current) && last == ':' {
ls.lexErr("the identification is illegal.")
}
last = ls.current
ls.tokenBuff.WriteByte(ls.current)
ls.next()
}
sem.S = ls.tokenBuff.String()
if strings.Count(sem.S, ":") > 0 {
if strings.Count(sem.S, "::") != 1 || strings.Count(sem.S, ":") != 2 {
ls.lexErr("namespace qualifier::is illegal")
}
}
for i := tkDummyKeywordBegin + 1; i < tkDummyKeywordEnd; i++ {
if TokenMap[i] == sem.S {
return i, nil
}
}
for i := tkDummyTypeBegin + 1; i < tkDummyTypeEnd; i++ {
if TokenMap[i] == sem.S {
return i, nil
}
}
return tkName, sem
}
func (ls *LexState) readSharp() (TK, *SemInfo) {
ls.next()
for isLetter(ls.current) {
ls.tokenBuff.WriteByte(ls.current)
ls.next()
}
if ls.tokenBuff.String() != "include" {
ls.lexErr("not #include")
}
return tkInclude, nil
}
func (ls *LexState) readString() (TK, *SemInfo) {
sem := &SemInfo{}
ls.next()
for {
if ls.current == EOS {
ls.lexErr(`no match "`)
} else if ls.current == '"' {
ls.next()
break
} else {
ls.tokenBuff.WriteByte(ls.current)
ls.next()
}
}
sem.S = ls.tokenBuff.String()
return tkString, sem
}
func (ls *LexState) readLongComment() {
for {
switch ls.current {
case EOS:
ls.lexErr("respect */")
return
case '\n', '\r':
ls.incLine()
case '*':
ls.next()
if ls.current == EOS {
return
} else if ls.current == '/' {
ls.next()
return
}
default:
ls.next()
}
}
}
func (ls *LexState) next() {
var err error
ls.current, err = ls.buff.ReadByte()
if err != nil {
ls.current = EOS
}
}
// Do lexical analysis.
func (ls *LexState) llex() (TK, *SemInfo) {
for {
ls.tokenBuff.Reset()
switch ls.current {
case EOS:
return tkEos, nil
case ' ', '\t', '\f', '\v':
ls.next()
case '\n', '\r':
ls.incLine()
case '/': // Comment processing
ls.next()
if ls.current == '/' {
for !isNewLine(ls.current) && ls.current != EOS {
ls.next()
}
} else if ls.current == '*' {
ls.next()
ls.readLongComment()
} else {
ls.lexErr("lexical error,/")
}
case '{':
ls.next()
return tkBracel, nil
case '}':
ls.next()
return tkBracer, nil
case ';':
ls.next()
return tkSemi, nil
case '=':
ls.next()
return tkEq, nil
case '<':
ls.next()
return tkShl, nil
case '>':
ls.next()
return tkShr, nil
case ',':
ls.next()
return tkComma, nil
case '(':
ls.next()
return tkPtl, nil
case ')':
ls.next()
return tkPtr, nil
case '[':
ls.next()
return tkSquarel, nil
case ']':
ls.next()
return tkSquarer, nil
case '"':
return ls.readString()
case '#':
return ls.readSharp()
default:
switch {
case isNumber(ls.current):
return ls.readNumber()
case isLetter(ls.current):
return ls.readIdent()
default:
ls.lexErr("unrecognized characters, " + string(ls.current))
}
}
}
}
//NextToken return token after lexical analysis.
func (ls *LexState) NextToken() *Token {
tk := &Token{}
tk.T, tk.S = ls.llex()
tk.Line = ls.linenumber
return tk
}
//NewLexState to update LexState struct.
func NewLexState(source string, buff []byte) *LexState {
return &LexState{
current: ' ',
linenumber: 1,
source: source,
buff: bytes.NewBuffer(buff),
}
}