sqlparser/token.go at master · dearcode/sqlparser · GitHub

History

896 lines (833 loc) · 22 KB

Raw

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

486

487

488

489

490

491

492

493

494

495

496

497

498

499

500

501

502

503

504

505

506

507

508

509

510

511

512

513

514

515

516

517

518

519

520

521

522

523

524

525

526

527

528

529

530

531

532

533

534

535

536

537

538

539

540

541

542

543

544

545

546

547

548

549

550

551

552

553

554

555

556

557

558

559

560

561

562

563

564

565

566

567

568

569

570

571

572

573

574

575

576

577

578

579

580

581

582

583

584

585

586

587

588

589

590

591

592

593

594

595

596

597

598

599

600

601

602

603

604

605

606

607

608

609

610

611

612

613

614

615

616

617

618

619

620

621

622

623

624

625

626

627

628

629

630

631

632

633

634

635

636

637

638

639

640

641

642

643

644

645

646

647

648

649

650

651

652

653

654

655

656

657

658

659

660

661

662

663

664

665

666

667

668

669

670

671

672

673

674

675

676

677

678

679

680

681

682

683

684

685

686

687

688

689

690

691

692

693

694

695

696

697

698

699

700

701

702

703

704

705

706

707

708

709

710

711

712

713

714

715

716

717

718

719

720

721

722

723

724

725

726

727

728

729

730

731

732

733

734

735

736

737

738

739

740

741

742

743

744

745

746

747

748

749

750

751

752

753

754

755

756

757

758

759

760

761

762

763

764

765

766

767

768

769

770

771

772

773

774

775

776

777

778

779

780

781

782

783

784

785

786

787

788

789

790

791

792

793

794

795

796

797

798

799

800

801

802

803

804

805

806

807

808

809

810

811

812

813

814

815

816

817

818

819

820

821

822

823

824

825

826

827

828

829

830

831

832

833

834

835

836

837

838

839

840

841

842

843

844

845

846

847

848

849

850

851

852

853

854

855

856

857

858

859

860

861

862

863

864

865

866

867

868

869

870

871

872

873

874

875

876

877

878

879

880

881

882

883

884

885

886

887

888

889

890

891

892

893

894

895

896

Licensed under the Apache License, Version 2.0 (the "License");

you may not use this file except in compliance with the License.

You may obtain a copy of the License at

http://www.apache.org/licenses/LICENSE-2.0

Unless required by applicable law or agreed to in writing, software

distributed under the License is distributed on an "AS IS" BASIS,

WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.

See the License for the specific language governing permissions and

limitations under the License.

package sqlparser

import (

"bytes"

"errors"

"fmt"

"io"

"vitess.io/vitess/go/bytes2"

"vitess.io/vitess/go/sqltypes"

)

const (

defaultBufSize = 4096

eofChar = 0x100

)

// Tokenizer is the struct used to generate SQL

// tokens for the parser.

type Tokenizer struct {

InStream io.Reader

AllowComments bool

ForceEOF bool

lastChar uint16

Position int

lastToken []byte

LastError error

posVarIndex int

ParseTree Statement

partialDDL *DDL

nesting int

multi bool

buf []byte

bufPos int

bufSize int

}

// NewStringTokenizer creates a new Tokenizer for the

// sql string.

func NewStringTokenizer(sql string) *Tokenizer {

buf := []byte(sql)

return &Tokenizer{

buf: buf,

bufSize: len(buf),

}

// NewTokenizer creates a new Tokenizer reading a sql

// string from the io.Reader.

func NewTokenizer(r io.Reader) *Tokenizer {

return &Tokenizer{

InStream: r,

buf: make([]byte, defaultBufSize),

}

// keywords is a map of mysql keywords that fall into two categories:

// 1) keywords considered reserved by MySQL

// 2) keywords for us to handle specially in sql.y

// Those marked as UNUSED are likely reserved keywords. We add them here so that

// when rewriting queries we can properly backtick quote them so they don't cause issues

// NOTE: If you add new keywords, add them also to the reserved_keywords or

// non_reserved_keywords grammar in sql.y -- this will allow the keyword to be used

// in identifiers. See the docs for each grammar to determine which one to put it into.

var keywords = map[string]int{

"accessible": UNUSED,

"add": ADD,

"against": AGAINST,

"all": ALL,

"alter": ALTER,

"analyze": ANALYZE,

"and": AND,

"as": AS,

"asc": ASC,

"asensitive": UNUSED,

"auto_increment": AUTO_INCREMENT,

"before": UNUSED,

"begin": BEGIN,

"between": BETWEEN,

"bigint": BIGINT,

"binary": BINARY,

"_binary": UNDERSCORE_BINARY,

"bit": BIT,

"blob": BLOB,

"bool": BOOL,

"boolean": BOOLEAN,

"both": UNUSED,

"by": BY,

"call": UNUSED,

"case": CASE,

"cast": CAST,

"change": CHANGE,

"char": CHAR,

"character": CHARACTER,

"charset": CHARSET,

"check": UNUSED,

"collate": COLLATE,

"column": COLUMN,

"comment": COMMENT_KEYWORD,

"commit": COMMIT,

"condition": UNUSED,

"constraint": CONSTRAINT,

"continue": UNUSED,

"convert": CONVERT,

"create": CREATE,

"cross": CROSS,

"current_date": CURRENT_DATE,

"current_time": CURRENT_TIME,

"current_timestamp": CURRENT_TIMESTAMP,

"now": NOW,

"current_user": UNUSED,

"cursor": UNUSED,

"database": DATABASE,

"databases": DATABASES,

"day_hour": UNUSED,

"day_microsecond": UNUSED,

"day_minute": UNUSED,

"day_second": UNUSED,

"date": DATE,

"datetime": DATETIME,

"dec": UNUSED,

"decimal": DECIMAL,

"declare": UNUSED,

"default": DEFAULT,

"delayed": UNUSED,

"delete": DELETE,

"desc": DESC,

"describe": DESCRIBE,

"deterministic": UNUSED,

"distinct": DISTINCT,

"distinctrow": UNUSED,

"div": DIV,

"double": DOUBLE,

"precision": UNUSED,

"drop": DROP,

"modify": MODIFY,

"duplicate": DUPLICATE,

"each": UNUSED,

"else": ELSE,

"elseif": UNUSED,

"enclosed": UNUSED,

"end": END,

"enum": ENUM,

"escape": ESCAPE,

"escaped": UNUSED,

"exists": EXISTS,

"exit": UNUSED,

"explain": EXPLAIN,

"expansion": EXPANSION,

"false": FALSE,

"fetch": UNUSED,

"float": FLOAT_TYPE,

"float4": UNUSED,

"float8": UNUSED,

"for": FOR,

"force": FORCE,

"foreign": FOREIGN,

"no": NO,

"action": ACTION,

"references": REFERENCES,

"cascade": CASCADE,

"from": FROM,

"fulltext": FULLTEXT,

"generated": UNUSED,

"get": UNUSED,

"global": GLOBAL,

"grant": UNUSED,

"group": GROUP,

"group_concat": GROUP_CONCAT,

"having": HAVING,

"high_priority": UNUSED,

"hour_microsecond": UNUSED,

"hour_minute": UNUSED,

"hour_second": UNUSED,

"if": IF,

"ignore": IGNORE,

"in": IN,

"index": INDEX,

"infile": UNUSED,

"inout": UNUSED,

"inner": INNER,

"insensitive": UNUSED,

"insert": INSERT,

"int": INT,

"int1": UNUSED,

"int2": UNUSED,

"int3": UNUSED,

"int4": UNUSED,

"int8": UNUSED,

"integer": INTEGER,

"interval": INTERVAL,

"into": INTO,

"io_after_gtids": UNUSED,

"is": IS,

"iterate": UNUSED,

"join": JOIN,

"json": JSON,

"key": KEY,

"keys": KEYS,

"kill": UNUSED,

"language": LANGUAGE,

"last_insert_id": LAST_INSERT_ID,

"leading": UNUSED,

"leave": UNUSED,

"left": LEFT,

"less": LESS,

"like": LIKE,

"limit": LIMIT,

"linear": UNUSED,

"lines": UNUSED,

"load": UNUSED,

"localtime": LOCALTIME,

"localtimestamp": LOCALTIMESTAMP,

"lock": LOCK,

"long": UNUSED,

"longblob": LONGBLOB,

"longtext": LONGTEXT,

"loop": UNUSED,

"low_priority": UNUSED,

"master_bind": UNUSED,

"match": MATCH,

"maxvalue": MAXVALUE,

"mediumblob": MEDIUMBLOB,

"mediumint": MEDIUMINT,

"mediumtext": MEDIUMTEXT,

"middleint": UNUSED,

"minute_microsecond": UNUSED,

"minute_second": UNUSED,

"mod": MOD,

"mode": MODE,

"modifies": UNUSED,

"names": NAMES,

"natural": NATURAL,

"nchar": NCHAR,

"next": NEXT,

"not": NOT,

"no_write_to_binlog": UNUSED,

"null": NULL,

"numeric": NUMERIC,

"offset": OFFSET,

"on": ON,

"optimize": OPTIMIZE,

"optimizer_costs": UNUSED,

"option": UNUSED,

"optionally": UNUSED,

"or": OR,

"order": ORDER,

"out": UNUSED,

"outer": OUTER,

"outfile": UNUSED,

"partition": PARTITION,

"primary": PRIMARY,

"procedure": PROCEDURE,

"query": QUERY,

"range": UNUSED,

"read": UNUSED,

"reads": UNUSED,

"read_write": UNUSED,

"real": REAL,

"regexp": REGEXP,

"release": UNUSED,

"rename": RENAME,

"reorganize": REORGANIZE,

"repair": REPAIR,

"repeat": UNUSED,

"replace": REPLACE,

"require": UNUSED,

"resignal": UNUSED,

"restrict": RESTRICT,

"return": UNUSED,

"revoke": UNUSED,

"right": RIGHT,

"rlike": REGEXP,

"rollback": ROLLBACK,

"schema": UNUSED,

"schemas": UNUSED,

"second_microsecond": UNUSED,

"select": SELECT,

"sensitive": UNUSED,

"separator": SEPARATOR,

"session": SESSION,

"set": SET,

"share": SHARE,

"show": SHOW,

"signal": UNUSED,

"signed": SIGNED,

"smallint": SMALLINT,

"spatial": SPATIAL,

"specific": UNUSED,

"sql": UNUSED,

"sqlexception": UNUSED,

"sqlstate": UNUSED,

"sqlwarning": UNUSED,

"sql_big_result": UNUSED,

"sql_cache": SQL_CACHE,

"sql_calc_found_rows": UNUSED,

"sql_no_cache": SQL_NO_CACHE,

"sql_small_result": UNUSED,

"ssl": UNUSED,

"start": START,

"starting": UNUSED,

"status": STATUS,

"engine": ENGINE,

"stored": UNUSED,

"straight_join": STRAIGHT_JOIN,

"table": TABLE,

"tables": TABLES,

"terminated": UNUSED,

"text": TEXT,

"than": THAN,

"then": THEN,

"time": TIME,

"timestamp": TIMESTAMP,

"tinyblob": TINYBLOB,

"tinyint": TINYINT,

"tinytext": TINYTEXT,

"to": TO,

"trailing": UNUSED,

"transaction": TRANSACTION,

"trigger": TRIGGER,

"true": TRUE,

"truncate": TRUNCATE,

"undo": UNUSED,

"union": UNION,

"unique": UNIQUE,

"unlock": UNUSED,

"unsigned": UNSIGNED,

"update": UPDATE,

"usage": UNUSED,

"use": USE,

"using": USING,

"utc_date": UTC_DATE,

"utc_time": UTC_TIME,

"utc_timestamp": UTC_TIMESTAMP,

"values": VALUES,

"variables": VARIABLES,

"varbinary": VARBINARY,

"varchar": VARCHAR,

"varcharacter": UNUSED,

"varying": UNUSED,

"virtual": UNUSED,

"vindex": VINDEX,

"vindexes": VINDEXES,

"view": VIEW,

"vitess_keyspaces": VITESS_KEYSPACES,

"vitess_shards": VITESS_SHARDS,

"vitess_tablets": VITESS_TABLETS,

"vschema_tables": VSCHEMA_TABLES,

"when": WHEN,

"where": WHERE,

"while": UNUSED,

"with": WITH,

"write": UNUSED,

"xor": UNUSED,

"year": YEAR,

"year_month": UNUSED,

"zerofill": ZEROFILL,

}

// keywordStrings contains the reverse mapping of token to keyword strings

var keywordStrings = map[int]string{}

func init() {

for str, id := range keywords {

if id == UNUSED {

continue

}

keywordStrings[id] = str

}

// KeywordString returns the string corresponding to the given keyword

func KeywordString(id int) string {

str, ok := keywordStrings[id]

if !ok {

return ""

}

return str

}

// 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()

}

lval.bytes = val

tkn.lastToken = val

return typ

}

// Error is called by go yacc if there's a parsing error.

func (tkn *Tokenizer) Error(err string) {

buf := &bytes2.Buffer{}

if tkn.lastToken != nil {

fmt.Fprintf(buf, "%s at position %v near '%s'", err, tkn.Position, tkn.lastToken)

} else {

fmt.Fprintf(buf, "%s at position %v", err, tkn.Position)

}

tkn.LastError = errors.New(buf.String())

// Try and re-sync to the next statement

if tkn.lastChar != ';' {

tkn.skipStatement()

}

// 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.lastChar == 0 {

tkn.next()

}

if tkn.ForceEOF {

tkn.skipStatement()

return 0, nil

}

tkn.skipBlank()

switch ch := tkn.lastChar; {

case isLetter(ch):

tkn.next()

if ch == 'X' || ch == 'x' {

if tkn.lastChar == '\'' {

tkn.next()

return tkn.scanHex()

}

if ch == 'B' || ch == 'b' {

if tkn.lastChar == '\'' {

tkn.next()

return tkn.scanBitLiteral()

}

return tkn.scanIdentifier([]byte{byte(ch)})

case ch == ':':

return tkn.scanBindVar()

case isDigit(ch):

return tkn.scanNumber(false, false)

case ch == ';' && tkn.multi:

return 0, nil

default:

tkn.next()

switch ch {

case eofChar:

return 0, nil

case '=', ',', ';', '(', ')', '+', '*', '%', '^', '~':

return int(ch), nil

case '&':

if tkn.lastChar == '&' {

tkn.next()

return AND, nil

}

return int(ch), nil

case '|':

if tkn.lastChar == '|' {

tkn.next()

return OR, nil

}

return int(ch), nil

case '?':

tkn.posVarIndex++

buf := new(bytes2.Buffer)

fmt.Fprintf(buf, ":v%d", tkn.posVarIndex)

return VALUE_ARG, buf.Bytes()

case '.':

if isDigit(tkn.lastChar) {

return tkn.scanNumber(true, false)

}

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 '#':

return tkn.scanCommentType1("#")

case '-':

switch tkn.lastChar {

case '-':

tkn.next()

return tkn.scanCommentType1("--")

case '>':

tkn.next()

if tkn.lastChar == '>' {

tkn.next()

return JSON_UNQUOTE_EXTRACT_OP, nil

}

return JSON_EXTRACT_OP, nil

case '0', '1', '2', '3', '4', '5', '6', '7', '8', '9':

return tkn.scanNumber(false, true)

}

return int(ch), nil

case '<':

switch tkn.lastChar {

case '>':

tkn.next()

return NE, nil

case '<':

tkn.next()

return SHIFT_LEFT, 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 '>':

switch tkn.lastChar {

case '=':

tkn.next()

return GE, nil

case '>':

tkn.next()

return SHIFT_RIGHT, nil

default:

return int(ch), nil

}

case '!':

if tkn.lastChar == '=' {

tkn.next()

return NE, nil

}

return int(ch), nil

case '\'', '"':

return tkn.scanString(ch, STRING)

case '`':

return tkn.scanLiteralIdentifier()

default:

return LEX_ERROR, []byte{byte(ch)}

}

// skipStatement scans until the EOF, or end of statement is encountered.

func (tkn *Tokenizer) skipStatement() {

ch := tkn.lastChar

for ch != ';' && ch != eofChar {

tkn.next()

ch = tkn.lastChar

}

func (tkn *Tokenizer) skipBlank() {

ch := tkn.lastChar

for ch == ' ' || ch == '\n' || ch == '\r' || ch == '\t' {

tkn.next()

ch = tkn.lastChar

}

func (tkn *Tokenizer) scanIdentifier(lastBytes []byte) (int, []byte) {

buffer := bytes2.NewBuffer(lastBytes)

for isLetter(tkn.lastChar) || isDigit(tkn.lastChar) {

buffer.WriteByte(byte(tkn.lastChar))

tkn.next()

}

lowered := bytes.ToLower(buffer.Bytes())

loweredStr := string(lowered)

if keywordID, found := keywords[loweredStr]; found {

return keywordID, lowered

}

// dual must always be case-insensitive

if loweredStr == "dual" {

return ID, lowered

}

return ID, buffer.Bytes()

}

func (tkn *Tokenizer) scanHex() (int, []byte) {

buffer := &bytes2.Buffer{}

tkn.scanMantissa(16, buffer)

if tkn.lastChar != '\'' {

return LEX_ERROR, buffer.Bytes()

}

tkn.next()

if buffer.Len()%2 != 0 {

return LEX_ERROR, buffer.Bytes()

}

return HEX, buffer.Bytes()

}

func (tkn *Tokenizer) scanBitLiteral() (int, []byte) {

buffer := &bytes2.Buffer{}

tkn.scanMantissa(2, buffer)

if tkn.lastChar != '\'' {

return LEX_ERROR, buffer.Bytes()

}

tkn.next()

return BIT_LITERAL, buffer.Bytes()

}

func (tkn *Tokenizer) scanLiteralIdentifier() (int, []byte) {

buffer := &bytes2.Buffer{}

backTickSeen := false

for {

if backTickSeen {

if tkn.lastChar != '`' {

break

}

backTickSeen = false

buffer.WriteByte('`')

tkn.next()

continue

}

// The previous char was not a backtick.

switch tkn.lastChar {

case '`':

backTickSeen = true

case eofChar:

// Premature EOF.

return LEX_ERROR, buffer.Bytes()

default:

buffer.WriteByte(byte(tkn.lastChar))

}

tkn.next()

}

if buffer.Len() == 0 {

return LEX_ERROR, buffer.Bytes()

}

return ID, buffer.Bytes()

}

func (tkn *Tokenizer) scanBindVar() (int, []byte) {

buffer := &bytes2.Buffer{}

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 *bytes2.Buffer) {

for digitVal(tkn.lastChar) < base {

tkn.consumeNext(buffer)

}

func (tkn *Tokenizer) scanNumber(seenDecimalPoint, isNegative bool) (int, []byte) {

token := INTEGRAL

buffer := &bytes2.Buffer{}

if isNegative {

buffer.WriteByte('-')

}

if seenDecimalPoint {

token = FLOAT

buffer.WriteByte('.')

tkn.scanMantissa(10, buffer)

goto exponent

}

// 0x construct.

if tkn.lastChar == '0' {

tkn.consumeNext(buffer)

if tkn.lastChar == 'x' || tkn.lastChar == 'X' {

token = HEXNUM

tkn.consumeNext(buffer)

tkn.scanMantissa(16, buffer)

goto exit

}

tkn.scanMantissa(10, buffer)

if tkn.lastChar == '.' {

token = FLOAT

tkn.consumeNext(buffer)

tkn.scanMantissa(10, buffer)

}

exponent:

if tkn.lastChar == 'e' || tkn.lastChar == 'E' {

token = FLOAT

tkn.consumeNext(buffer)

if tkn.lastChar == '+' || tkn.lastChar == '-' {

tkn.consumeNext(buffer)

}

tkn.scanMantissa(10, buffer)

}

exit:

// A letter cannot immediately follow a number.

if isLetter(tkn.lastChar) {

return tkn.scanIdentifier(buffer.Bytes())

}

return token, buffer.Bytes()

}

func (tkn *Tokenizer) scanString(delim uint16, typ int) (int, []byte) {

var buffer bytes2.Buffer

for {

ch := tkn.lastChar

if ch == eofChar {

// Unterminated string.

return LEX_ERROR, buffer.Bytes()

}

if ch != delim && ch != '\\' {

buffer.WriteByte(byte(ch))

// Scan ahead to the next interesting character.

start := tkn.bufPos

for ; tkn.bufPos < tkn.bufSize; tkn.bufPos++ {

ch = uint16(tkn.buf[tkn.bufPos])

if ch == delim || ch == '\\' {

break

}

buffer.Write(tkn.buf[start:tkn.bufPos])

tkn.Position += (tkn.bufPos - start)

if tkn.bufPos >= tkn.bufSize {

// Reached the end of the buffer without finding a delim or

// escape character.

tkn.next()

continue

}

tkn.bufPos++

tkn.Position++

}

tkn.next() // Read one past the delim or escape character.

if ch == '\\' {

if tkn.lastChar == eofChar {

// String terminates mid escape character.

return LEX_ERROR, buffer.Bytes()

}

if decodedChar := sqltypes.SQLDecodeMap[byte(tkn.lastChar)]; decodedChar == sqltypes.DontEscape {

ch = tkn.lastChar

} else {

ch = uint16(decodedChar)

}

} else if ch == delim && tkn.lastChar != delim {

// Correctly terminated string, which is not a double delim.

break

}

buffer.WriteByte(byte(ch))

tkn.next()

}

return typ, buffer.Bytes()

}

func (tkn *Tokenizer) scanCommentType1(prefix string) (int, []byte) {

buffer := &bytes2.Buffer{}

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 := &bytes2.Buffer{}

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 *bytes2.Buffer) {

if tkn.lastChar == eofChar {

// This should never happen.

panic("unexpected EOF")

}

buffer.WriteByte(byte(tkn.lastChar))

tkn.next()

}

func (tkn *Tokenizer) next() {

if tkn.bufPos >= tkn.bufSize && tkn.InStream != nil {

// Try and refill the buffer

var err error

tkn.bufPos = 0

if tkn.bufSize, err = tkn.InStream.Read(tkn.buf); err != io.EOF && err != nil {

tkn.LastError = err

}

if tkn.bufPos >= tkn.bufSize {

if tkn.lastChar != eofChar {

tkn.Position++

tkn.lastChar = eofChar

}

} else {

tkn.Position++

tkn.lastChar = uint16(tkn.buf[tkn.bufPos])

tkn.bufPos++

}

// reset clears any internal state.

func (tkn *Tokenizer) reset() {

tkn.ParseTree = nil

tkn.partialDDL = nil

tkn.posVarIndex = 0

tkn.nesting = 0

tkn.ForceEOF = false

}

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'

//return '0' <= ch && ch <= '9' || ch == '-' || ch == '.'

}

sqlparser/token.go at master · dearcode/sqlparser · GitHub

Uh oh!

Expand file tree

Breadcrumbs

token.go

Latest commit

History

Breadcrumbs

token.go

File metadata and controls