Skip to content
Navigation Menu
{{ message }}
forked from xwb1989/sqlparser
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathtoken.go
More file actions
485 lines (450 loc) · 10.6 KB
/
Copy pathtoken.go
File metadata and controls
485 lines (450 loc) · 10.6 KB
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
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
// Copyright 2012, Google Inc. All rights reserved.
// Use of this source code is governed by a BSD-style
// license that can be found in the LICENSE file.
package sqlparser
import (
"bytes"
"fmt"
"strings"
"github.com/xwb1989/sqlparser/dependency/sqltypes"
)
const EOFCHAR = 0x100
// Tokenizer is the struct used to generate SQL
// tokens for the parser.
type Tokenizer struct {
InStream *strings.Reader
AllowComments bool
ForceEOF bool
lastChar uint16
Position int
errorToken []byte
LastError string
posVarIndex int
ParseTree Statement
}
// NewStringTokenizer creates a new Tokenizer for the
// sql string.
func NewStringTokenizer(sql string) *Tokenizer {
return &Tokenizer{InStream: strings.NewReader(sql)}
}
var keywords = map[string]int{
"all": ALL,
"alter": ALTER,
"analyze": ANALYZE,
"and": AND,
"as": AS,
"asc": ASC,
"between": BETWEEN,
"by": BY,
"case": CASE,
"create": CREATE,
"cross": CROSS,
"default": DEFAULT,
"delete": DELETE,
"desc": DESC,
"describe": DESCRIBE,
"distinct": DISTINCT,
"drop": DROP,
"duplicate": DUPLICATE,
"else": ELSE,
"end": END,
"except": EXCEPT,
"exists": EXISTS,
"explain": EXPLAIN,
"for": FOR,
"force": FORCE,
"from": FROM,
"group": GROUP,
"having": HAVING,
"if": IF,
"ignore": IGNORE,
"in": IN,
"index": INDEX,
"inner": INNER,
"insert": INSERT,
"intersect": INTERSECT,
"into": INTO,
"is": IS,
"join": JOIN,
"key": KEY,
"left": LEFT,
"like": LIKE,
"limit": LIMIT,
"lock": LOCK,
"minus": MINUS,
"natural": NATURAL,
"not": NOT,
"null": NULL,
"on": ON,
"or": OR,
"order": ORDER,
"outer": OUTER,
"rename": RENAME,
"right": RIGHT,
"select": SELECT,
"set": SET,
"show": SHOW,
"straight_join": STRAIGHT_JOIN,
"table": TABLE,
"then": THEN,
"to": TO,
"union": UNION,
"unique": UNIQUE,
"update": UPDATE,
"use": USE,
"using": USING,
"values": VALUES,
"view": VIEW,
"when": WHEN,
"where": WHERE,
//keywords for creat table
//datatypes
"bit": BIT,
"tinyint": TINYINT,
"smallint": SMALLINT,
"mediumint": MEDIUMINT,
"int": INT,
"integer": INTEGER,
"bigint": BIGINT,
"real": REAL,
"double": DOUBLE,
"float": FLOAT,
"decimal": DECIMAL,
"numeric": NUMERIC,
"char": CHAR,
"varchar": VARCHAR,
"text": TEXT,
"date": DATE,
"time": TIME,
"timestamp": TIMESTAMP,
"datetime": DATETIME,
"year": YEAR,
//other keywords
"unsigned": UNSIGNED,
"zerofill": ZEROFILL,
"primary": PRIMARY,
"auto_increment": AUTO_INCREMENT,
}
// Lex returns the next token form the Tokenizer.
// This function is used by go yacc.
func (tkn *Tokenizer) Lex(lval *yySymType) int {
typ, val := tkn.Scan()
for typ == COMMENT {
if tkn.AllowComments {
break
}
typ, val = tkn.Scan()
}
switch typ {
case ID, STRING, NUMBER, VALUE_ARG, LIST_ARG, COMMENT:
lval.bytes = val
}
tkn.errorToken = val
return typ
}
// Error is called by go yacc if there's a parsing error.
func (tkn *Tokenizer) Error(err string) {
buf := bytes.NewBuffer(make([]byte, 0, 32))
if tkn.errorToken != nil {
fmt.Fprintf(buf, "%s at position %v near %s", err, tkn.Position, tkn.errorToken)
} else {
fmt.Fprintf(buf, "%s at position %v", err, tkn.Position)
}
tkn.LastError = buf.String()
}
// Scan scans the tokenizer for the next token and returns
// the token type and an optional value.
func (tkn *Tokenizer) Scan() (int, []byte) {
if tkn.ForceEOF {
return 0, nil
}
if tkn.lastChar == 0 {
tkn.next()
}
tkn.skipBlank()
switch ch := tkn.lastChar; {
case isLetter(ch):
return tkn.scanIdentifier()
case isDigit(ch):
return tkn.scanNumber(false)
case ch == ':':
return tkn.scanBindVar()
default:
tkn.next()
switch ch {
case EOFCHAR:
return 0, nil
case '=', ',', ';', '(', ')', '+', '*', '%', '&', '|', '^', '~':
return int(ch), nil
case '?':
tkn.posVarIndex++
buf := new(bytes.Buffer)
fmt.Fprintf(buf, ":v%d", tkn.posVarIndex)
return VALUE_ARG, buf.Bytes()
case '.':
if isDigit(tkn.lastChar) {
return tkn.scanNumber(true)
} else {
return int(ch), nil
}
case '/':
switch tkn.lastChar {
case '/':
tkn.next()
return tkn.scanCommentType1("//")
case '*':
tkn.next()
return tkn.scanCommentType2()
default:
return int(ch), nil
}
case '-':
if tkn.lastChar == '-' {
tkn.next()
return tkn.scanCommentType1("--")
} else {
return int(ch), nil
}
case '<':
switch tkn.lastChar {
case '>':
tkn.next()
return NE, nil
case '=':
tkn.next()
switch tkn.lastChar {
case '>':
tkn.next()
return NULL_SAFE_EQUAL, nil
default:
return LE, nil
}
default:
return int(ch), nil
}
case '>':
if tkn.lastChar == '=' {
tkn.next()
return GE, nil
} else {
return int(ch), nil
}
case '!':
if tkn.lastChar == '=' {
tkn.next()
return NE, nil
} else {
return LEX_ERROR, []byte("!")
}
case '\'', '"':
return tkn.scanString(ch, STRING)
case '`':
return tkn.scanLiteralIdentifier()
default:
return LEX_ERROR, []byte{byte(ch)}
}
}
}
func (tkn *Tokenizer) skipBlank() {
ch := tkn.lastChar
for ch == ' ' || ch == '\n' || ch == '\r' || ch == '\t' {
tkn.next()
ch = tkn.lastChar
}
}
func (tkn *Tokenizer) scanIdentifier() (int, []byte) {
buffer := bytes.NewBuffer(make([]byte, 0, 8))
buffer.WriteByte(byte(tkn.lastChar))
for tkn.next(); isLetter(tkn.lastChar) || isDigit(tkn.lastChar); tkn.next() {
buffer.WriteByte(byte(tkn.lastChar))
}
lowered := bytes.ToLower(buffer.Bytes())
if keywordId, found := keywords[string(lowered)]; found {
return keywordId, lowered
}
return ID, buffer.Bytes()
}
func (tkn *Tokenizer) scanLiteralIdentifier() (int, []byte) {
buffer := bytes.NewBuffer(make([]byte, 0, 8))
buffer.WriteByte(byte(tkn.lastChar))
if !isLetter(tkn.lastChar) {
return LEX_ERROR, buffer.Bytes()
}
for tkn.next(); isLetter(tkn.lastChar) || isDigit(tkn.lastChar); tkn.next() {
buffer.WriteByte(byte(tkn.lastChar))
}
if tkn.lastChar != '`' {
return LEX_ERROR, buffer.Bytes()
}
tkn.next()
return ID, buffer.Bytes()
}
func (tkn *Tokenizer) scanBindVar() (int, []byte) {
buffer := bytes.NewBuffer(make([]byte, 0, 8))
buffer.WriteByte(byte(tkn.lastChar))
token := VALUE_ARG
tkn.next()
if tkn.lastChar == ':' {
token = LIST_ARG
buffer.WriteByte(byte(tkn.lastChar))
tkn.next()
}
if !isLetter(tkn.lastChar) {
return LEX_ERROR, buffer.Bytes()
}
for isLetter(tkn.lastChar) || isDigit(tkn.lastChar) || tkn.lastChar == '.' {
buffer.WriteByte(byte(tkn.lastChar))
tkn.next()
}
return token, buffer.Bytes()
}
func (tkn *Tokenizer) scanMantissa(base int, buffer *bytes.Buffer) {
for digitVal(tkn.lastChar) < base {
tkn.ConsumeNext(buffer)
}
}
func (tkn *Tokenizer) scanNumber(seenDecimalPoint bool) (int, []byte) {
buffer := bytes.NewBuffer(make([]byte, 0, 8))
if seenDecimalPoint {
buffer.WriteByte('.')
tkn.scanMantissa(10, buffer)
goto exponent
}
if tkn.lastChar == '0' {
// int or float
tkn.ConsumeNext(buffer)
if tkn.lastChar == 'x' || tkn.lastChar == 'X' {
// hexadecimal int
tkn.ConsumeNext(buffer)
tkn.scanMantissa(16, buffer)
} else {
// octal int or float
seenDecimalDigit := false
tkn.scanMantissa(8, buffer)
if tkn.lastChar == '8' || tkn.lastChar == '9' {
// illegal octal int or float
seenDecimalDigit = true
tkn.scanMantissa(10, buffer)
}
if tkn.lastChar == '.' || tkn.lastChar == 'e' || tkn.lastChar == 'E' {
goto fraction
}
// octal int
if seenDecimalDigit {
return LEX_ERROR, buffer.Bytes()
}
}
goto exit
}
// decimal int or float
tkn.scanMantissa(10, buffer)
fraction:
if tkn.lastChar == '.' {
tkn.ConsumeNext(buffer)
tkn.scanMantissa(10, buffer)
}
exponent:
if tkn.lastChar == 'e' || tkn.lastChar == 'E' {
tkn.ConsumeNext(buffer)
if tkn.lastChar == '+' || tkn.lastChar == '-' {
tkn.ConsumeNext(buffer)
}
tkn.scanMantissa(10, buffer)
}
exit:
return NUMBER, buffer.Bytes()
}
func (tkn *Tokenizer) scanString(delim uint16, typ int) (int, []byte) {
buffer := bytes.NewBuffer(make([]byte, 0, 8))
for {
ch := tkn.lastChar
tkn.next()
if ch == delim {
if tkn.lastChar == delim {
tkn.next()
} else {
break
}
} else if ch == '\\' {
if tkn.lastChar == EOFCHAR {
return LEX_ERROR, buffer.Bytes()
}
if decodedChar := sqltypes.SqlDecodeMap[byte(tkn.lastChar)]; decodedChar == sqltypes.DONTESCAPE {
ch = tkn.lastChar
} else {
ch = uint16(decodedChar)
}
tkn.next()
}
if ch == EOFCHAR {
return LEX_ERROR, buffer.Bytes()
}
buffer.WriteByte(byte(ch))
}
return typ, buffer.Bytes()
}
func (tkn *Tokenizer) scanCommentType1(prefix string) (int, []byte) {
buffer := bytes.NewBuffer(make([]byte, 0, 8))
buffer.WriteString(prefix)
for tkn.lastChar != EOFCHAR {
if tkn.lastChar == '\n' {
tkn.ConsumeNext(buffer)
break
}
tkn.ConsumeNext(buffer)
}
return COMMENT, buffer.Bytes()
}
func (tkn *Tokenizer) scanCommentType2() (int, []byte) {
buffer := bytes.NewBuffer(make([]byte, 0, 8))
buffer.WriteString("/*")
for {
if tkn.lastChar == '*' {
tkn.ConsumeNext(buffer)
if tkn.lastChar == '/' {
tkn.ConsumeNext(buffer)
break
}
continue
}
if tkn.lastChar == EOFCHAR {
return LEX_ERROR, buffer.Bytes()
}
tkn.ConsumeNext(buffer)
}
return COMMENT, buffer.Bytes()
}
func (tkn *Tokenizer) ConsumeNext(buffer *bytes.Buffer) {
if tkn.lastChar == EOFCHAR {
// This should never happen.
panic("unexpected EOF")
}
buffer.WriteByte(byte(tkn.lastChar))
tkn.next()
}
func (tkn *Tokenizer) next() {
if ch, err := tkn.InStream.ReadByte(); err != nil {
// Only EOF is possible.
tkn.lastChar = EOFCHAR
} else {
tkn.lastChar = uint16(ch)
}
tkn.Position++
}
func isLetter(ch uint16) bool {
return 'a' <= ch && ch <= 'z' || 'A' <= ch && ch <= 'Z' || ch == '_' || ch == '@'
}
func digitVal(ch uint16) int {
switch {
case '0' <= ch && ch <= '9':
return int(ch) - '0'
case 'a' <= ch && ch <= 'f':
return int(ch) - 'a' + 10
case 'A' <= ch && ch <= 'F':
return int(ch) - 'A' + 10
}
return 16 // larger than any legal digit val
}
func isDigit(ch uint16) bool {
return '0' <= ch && ch <= '9'
}
You can’t perform that action at this time.