nodegit/vendor/http_parser/http_parser.c at master · jBox/nodegit · GitHub

Repository navigation

History

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

897

898

899

900

901

902

903

904

905

906

907

908

909

910

911

912

913

914

915

916

917

918

919

920

921

922

923

924

925

926

927

928

929

930

931

932

933

934

935

936

937

938

939

940

941

942

943

944

945

946

947

948

949

950

951

952

953

954

955

956

957

958

959

960

961

962

963

964

965

966

967

968

969

970

971

972

973

974

975

976

977

978

979

980

981

982

983

984

985

986

987

988

989

990

991

992

993

994

995

996

997

998

999

1000

/* Based on src/http/ngx_http_parse.c from NGINX copyright Igor Sysoev

* Additional changes are licensed under the same terms as NGINX and

* Permission is hereby granted, free of charge, to any person obtaining a copy

* of this software and associated documentation files (the "Software"), to

* deal in the Software without restriction, including without limitation the

* rights to use, copy, modify, merge, publish, distribute, sublicense, and/or

* sell copies of the Software, and to permit persons to whom the Software is

* furnished to do so, subject to the following conditions:

* The above copyright notice and this permission notice shall be included in

* all copies or substantial portions of the Software.

* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR

* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,

* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE

* AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER

* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING

* FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS

* IN THE SOFTWARE.

#include "http_parser.h"

#include <assert.h>

#include <stddef.h>

#include <ctype.h>

#include <stdlib.h>

#include <string.h>

#include <limits.h>

#ifndef ULLONG_MAX

# define ULLONG_MAX ((uint64_t) -1) /* 2^64-1 */

#endif

#ifndef MIN

# define MIN(a,b) ((a) < (b) ? (a) : (b))

#endif

#ifndef ARRAY_SIZE

# define ARRAY_SIZE(a) (sizeof(a) / sizeof((a)[0]))

#endif

#ifndef BIT_AT

# define BIT_AT(a, i) \

(!!((unsigned int) (a)[(unsigned int) (i) >> 3] & \

(1 << ((unsigned int) (i) & 7))))

#endif

#ifndef ELEM_AT

# define ELEM_AT(a, i, v) ((unsigned int) (i) < ARRAY_SIZE(a) ? (a)[(i)] : (v))

#endif

#define SET_ERRNO(e) \

do { \

parser->http_errno = (e); \

} while(0)

#define CURRENT_STATE() p_state

#define UPDATE_STATE(V) p_state = (enum state) (V);

#define RETURN(V) \

do { \

parser->state = CURRENT_STATE(); \

return (V); \

} while (0);

#define REEXECUTE() \

goto reexecute; \

#ifdef __GNUC__

# define LIKELY(X) __builtin_expect(!!(X), 1)

# define UNLIKELY(X) __builtin_expect(!!(X), 0)

#else

# define LIKELY(X) (X)

# define UNLIKELY(X) (X)

#endif

/* Run the notify callback FOR, returning ER if it fails */

#define CALLBACK_NOTIFY_(FOR, ER) \

do { \

assert(HTTP_PARSER_ERRNO(parser) == HPE_OK); \

if (LIKELY(settings->on_##FOR)) { \

parser->state = CURRENT_STATE(); \

if (UNLIKELY(0 != settings->on_##FOR(parser))) { \

SET_ERRNO(HPE_CB_##FOR); \

} \

UPDATE_STATE(parser->state); \

/* We either errored above or got paused; get out */ \

if (UNLIKELY(HTTP_PARSER_ERRNO(parser) != HPE_OK)) { \

return (ER); \

} \

} while (0)

/* Run the notify callback FOR and consume the current byte */

#define CALLBACK_NOTIFY(FOR) CALLBACK_NOTIFY_(FOR, p - data + 1)

/* Run the notify callback FOR and don't consume the current byte */

#define CALLBACK_NOTIFY_NOADVANCE(FOR) CALLBACK_NOTIFY_(FOR, p - data)

/* Run data callback FOR with LEN bytes, returning ER if it fails */

#define CALLBACK_DATA_(FOR, LEN, ER) \

do { \

assert(HTTP_PARSER_ERRNO(parser) == HPE_OK); \

if (FOR##_mark) { \

if (LIKELY(settings->on_##FOR)) { \

parser->state = CURRENT_STATE(); \

if (UNLIKELY(0 != \

settings->on_##FOR(parser, FOR##_mark, (LEN)))) { \

SET_ERRNO(HPE_CB_##FOR); \

} \

UPDATE_STATE(parser->state); \

/* We either errored above or got paused; get out */ \

if (UNLIKELY(HTTP_PARSER_ERRNO(parser) != HPE_OK)) { \

return (ER); \

} \

FOR##_mark = NULL; \

} \

} while (0)

/* Run the data callback FOR and consume the current byte */

#define CALLBACK_DATA(FOR) \

CALLBACK_DATA_(FOR, p - FOR##_mark, p - data + 1)

/* Run the data callback FOR and don't consume the current byte */

#define CALLBACK_DATA_NOADVANCE(FOR) \

CALLBACK_DATA_(FOR, p - FOR##_mark, p - data)

/* Set the mark FOR; non-destructive if mark is already set */

#define MARK(FOR) \

do { \

if (!FOR##_mark) { \

FOR##_mark = p; \

} \

} while (0)

/* Don't allow the total size of the HTTP headers (including the status

* line) to exceed HTTP_MAX_HEADER_SIZE. This check is here to protect

* embedders against denial-of-service attacks where the attacker feeds

* us a never-ending header that the embedder keeps buffering.

* This check is arguably the responsibility of embedders but we're doing

* it on the embedder's behalf because most won't bother and this way we

* make the web a little safer. HTTP_MAX_HEADER_SIZE is still far bigger

* than any reasonable request or response so this should never affect

* day-to-day operation.

#define COUNT_HEADER_SIZE(V) \

do { \

parser->nread += (V); \

if (UNLIKELY(parser->nread > (HTTP_MAX_HEADER_SIZE))) { \

SET_ERRNO(HPE_HEADER_OVERFLOW); \

goto error; \

} \

} while (0)

#define PROXY_CONNECTION "proxy-connection"

#define CONNECTION "connection"

#define CONTENT_LENGTH "content-length"

#define TRANSFER_ENCODING "transfer-encoding"

#define UPGRADE "upgrade"

#define CHUNKED "chunked"

#define KEEP_ALIVE "keep-alive"

#define CLOSE "close"

static const char *method_strings[] =

{

#define XX(num, name, string) #string,

HTTP_METHOD_MAP(XX)

#undef XX

};

/* Tokens as defined by rfc 2616. Also lowercases them.

* token = 1*<any CHAR except CTLs or separators>

* separators = "(" | ")" | "<" | ">" | "@"

* | "," | ";" | ":" | "\" | <">

* | "/" | "[" | "]" | "?" | "="

* | "{" | "}" | SP | HT

static const char tokens[256] = {

/* 0 nul 1 soh 2 stx 3 etx 4 eot 5 enq 6 ack 7 bel */

0, 0, 0, 0, 0, 0, 0, 0,

/* 8 bs 9 ht 10 nl 11 vt 12 np 13 cr 14 so 15 si */

0, 0, 0, 0, 0, 0, 0, 0,

/* 16 dle 17 dc1 18 dc2 19 dc3 20 dc4 21 nak 22 syn 23 etb */

0, 0, 0, 0, 0, 0, 0, 0,

/* 24 can 25 em 26 sub 27 esc 28 fs 29 gs 30 rs 31 us */

0, 0, 0, 0, 0, 0, 0, 0,

/* 32 sp 33 ! 34 " 35 # 36 $ 37 % 38 & 39 ' */

0, '!', 0, '#', '$', '%', '&', '\'',

/* 40 ( 41 ) 42 * 43 + 44 , 45 - 46 . 47 / */

0, 0, '*', '+', 0, '-', '.', 0,

/* 48 0 49 1 50 2 51 3 52 4 53 5 54 6 55 7 */

'0', '1', '2', '3', '4', '5', '6', '7',

/* 56 8 57 9 58 : 59 ; 60 < 61 = 62 > 63 ? */

'8', '9', 0, 0, 0, 0, 0, 0,

/* 64 @ 65 A 66 B 67 C 68 D 69 E 70 F 71 G */

0, 'a', 'b', 'c', 'd', 'e', 'f', 'g',

/* 72 H 73 I 74 J 75 K 76 L 77 M 78 N 79 O */

'h', 'i', 'j', 'k', 'l', 'm', 'n', 'o',

/* 80 P 81 Q 82 R 83 S 84 T 85 U 86 V 87 W */

'p', 'q', 'r', 's', 't', 'u', 'v', 'w',

/* 88 X 89 Y 90 Z 91 [ 92 \ 93 ] 94 ^ 95 _ */

'x', 'y', 'z', 0, 0, 0, '^', '_',

/* 96 ` 97 a 98 b 99 c 100 d 101 e 102 f 103 g */

'`', 'a', 'b', 'c', 'd', 'e', 'f', 'g',

/* 104 h 105 i 106 j 107 k 108 l 109 m 110 n 111 o */

'h', 'i', 'j', 'k', 'l', 'm', 'n', 'o',

/* 112 p 113 q 114 r 115 s 116 t 117 u 118 v 119 w */

'p', 'q', 'r', 's', 't', 'u', 'v', 'w',

/* 120 x 121 y 122 z 123 { 124 | 125 } 126 ~ 127 del */

'x', 'y', 'z', 0, '|', 0, '~', 0 };

static const int8_t unhex[256] =

{-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1

,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1

, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9,-1,-1,-1,-1,-1,-1

,-1,10,11,12,13,14,15,-1,-1,-1,-1,-1,-1,-1,-1,-1

,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1

,-1,10,11,12,13,14,15,-1,-1,-1,-1,-1,-1,-1,-1,-1

,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1,-1

};

#if HTTP_PARSER_STRICT

# define T(v) 0

#else

# define T(v) v

#endif

static const uint8_t normal_url_char[32] = {

/* 0 nul 1 soh 2 stx 3 etx 4 eot 5 enq 6 ack 7 bel */

0 | 0 | 0 | 0 | 0 | 0 | 0 | 0,

/* 8 bs 9 ht 10 nl 11 vt 12 np 13 cr 14 so 15 si */

0 | T(2) | 0 | 0 | T(16) | 0 | 0 | 0,

/* 16 dle 17 dc1 18 dc2 19 dc3 20 dc4 21 nak 22 syn 23 etb */

0 | 0 | 0 | 0 | 0 | 0 | 0 | 0,

/* 24 can 25 em 26 sub 27 esc 28 fs 29 gs 30 rs 31 us */

0 | 0 | 0 | 0 | 0 | 0 | 0 | 0,

/* 32 sp 33 ! 34 " 35 # 36 $ 37 % 38 & 39 ' */

0 | 2 | 4 | 0 | 16 | 32 | 64 | 128,

/* 40 ( 41 ) 42 * 43 + 44 , 45 - 46 . 47 / */

1 | 2 | 4 | 8 | 16 | 32 | 64 | 128,

/* 48 0 49 1 50 2 51 3 52 4 53 5 54 6 55 7 */

1 | 2 | 4 | 8 | 16 | 32 | 64 | 128,

/* 56 8 57 9 58 : 59 ; 60 < 61 = 62 > 63 ? */

1 | 2 | 4 | 8 | 16 | 32 | 64 | 0,

/* 64 @ 65 A 66 B 67 C 68 D 69 E 70 F 71 G */

1 | 2 | 4 | 8 | 16 | 32 | 64 | 128,

/* 72 H 73 I 74 J 75 K 76 L 77 M 78 N 79 O */

1 | 2 | 4 | 8 | 16 | 32 | 64 | 128,

/* 80 P 81 Q 82 R 83 S 84 T 85 U 86 V 87 W */

1 | 2 | 4 | 8 | 16 | 32 | 64 | 128,

/* 88 X 89 Y 90 Z 91 [ 92 \ 93 ] 94 ^ 95 _ */

1 | 2 | 4 | 8 | 16 | 32 | 64 | 128,

/* 96 ` 97 a 98 b 99 c 100 d 101 e 102 f 103 g */

1 | 2 | 4 | 8 | 16 | 32 | 64 | 128,

/* 104 h 105 i 106 j 107 k 108 l 109 m 110 n 111 o */

1 | 2 | 4 | 8 | 16 | 32 | 64 | 128,

/* 112 p 113 q 114 r 115 s 116 t 117 u 118 v 119 w */

1 | 2 | 4 | 8 | 16 | 32 | 64 | 128,

/* 120 x 121 y 122 z 123 { 124 | 125 } 126 ~ 127 del */

1 | 2 | 4 | 8 | 16 | 32 | 64 | 0, };

#undef T

enum state

{ s_dead = 1 /* important that this is > 0 */

, s_start_req_or_res

, s_res_or_resp_H

, s_start_res

, s_res_H

, s_res_HT

, s_res_HTT

, s_res_HTTP

, s_res_first_http_major

, s_res_http_major

, s_res_first_http_minor

, s_res_http_minor

, s_res_first_status_code

, s_res_status_code

, s_res_status_start

, s_res_status

, s_res_line_almost_done

, s_start_req

, s_req_method

, s_req_spaces_before_url

, s_req_schema

, s_req_schema_slash

, s_req_schema_slash_slash

, s_req_server_start

, s_req_server

, s_req_server_with_at

, s_req_path

, s_req_query_string_start

, s_req_query_string

, s_req_fragment_start

, s_req_fragment

, s_req_http_start

, s_req_http_H

, s_req_http_HT

, s_req_http_HTT

, s_req_http_HTTP

, s_req_first_http_major

, s_req_http_major

, s_req_first_http_minor

, s_req_http_minor

, s_req_line_almost_done

, s_header_field_start

, s_header_field

, s_header_value_discard_ws

, s_header_value_discard_ws_almost_done

, s_header_value_discard_lws

, s_header_value_start

, s_header_value

, s_header_value_lws

, s_header_almost_done

, s_chunk_size_start

, s_chunk_size

, s_chunk_parameters

, s_chunk_size_almost_done

, s_headers_almost_done

, s_headers_done

/* Important: 's_headers_done' must be the last 'header' state. All

* states beyond this must be 'body' states. It is used for overflow

* checking. See the PARSING_HEADER() macro.

, s_chunk_data

, s_chunk_data_almost_done

, s_chunk_data_done

, s_body_identity

, s_body_identity_eof

, s_message_done

};

#define PARSING_HEADER(state) (state <= s_headers_done)

enum header_states

{ h_general = 0

, h_C

, h_CO

, h_CON

, h_matching_connection

, h_matching_proxy_connection

, h_matching_content_length

, h_matching_transfer_encoding

, h_matching_upgrade

, h_connection

, h_content_length

, h_transfer_encoding

, h_upgrade

, h_matching_transfer_encoding_chunked

, h_matching_connection_token_start

, h_matching_connection_keep_alive

, h_matching_connection_close

, h_matching_connection_upgrade

, h_matching_connection_token

, h_transfer_encoding_chunked

, h_connection_keep_alive

, h_connection_close

, h_connection_upgrade

};

enum http_host_state

{

s_http_host_dead = 1

, s_http_userinfo_start

, s_http_userinfo

, s_http_host_start

, s_http_host_v6_start

, s_http_host

, s_http_host_v6

, s_http_host_v6_end

, s_http_host_port_start

, s_http_host_port

};

/* Macros for character classes; depends on strict-mode */

#define CR '\r'

#define LF '\n'

#define LOWER(c) (unsigned char)(c | 0x20)

#define IS_ALPHA(c) (LOWER(c) >= 'a' && LOWER(c) <= 'z')

#define IS_NUM(c) ((c) >= '0' && (c) <= '9')

#define IS_ALPHANUM(c) (IS_ALPHA(c) || IS_NUM(c))

#define IS_HEX(c) (IS_NUM(c) || (LOWER(c) >= 'a' && LOWER(c) <= 'f'))

#define IS_MARK(c) ((c) == '-' || (c) == '_' || (c) == '.' || \

#define IS_USERINFO_CHAR(c) (IS_ALPHANUM(c) || IS_MARK(c) || (c) == '%' || \

#define STRICT_TOKEN(c) (tokens[(unsigned char)c])

#if HTTP_PARSER_STRICT

#define TOKEN(c) (tokens[(unsigned char)c])

#define IS_URL_CHAR(c) (BIT_AT(normal_url_char, (unsigned char)c))

#define IS_HOST_CHAR(c) (IS_ALPHANUM(c) || (c) == '.' || (c) == '-')

#else

#define TOKEN(c) ((c == ' ') ? ' ' : tokens[(unsigned char)c])

#define IS_URL_CHAR(c) \

(BIT_AT(normal_url_char, (unsigned char)c) || ((c) & 0x80))

#define IS_HOST_CHAR(c) \

(IS_ALPHANUM(c) || (c) == '.' || (c) == '-' || (c) == '_')

#endif

#define start_state (parser->type == HTTP_REQUEST ? s_start_req : s_start_res)

#if HTTP_PARSER_STRICT

# define STRICT_CHECK(cond) \

do { \

if (cond) { \

SET_ERRNO(HPE_STRICT); \

goto error; \

} \

} while (0)

# define NEW_MESSAGE() (http_should_keep_alive(parser) ? start_state : s_dead)

#else

# define STRICT_CHECK(cond)

# define NEW_MESSAGE() start_state

#endif

/* Map errno values to strings for human-readable output */

#define HTTP_STRERROR_GEN(n, s) { "HPE_" #n, s },

static struct {

const char *name;

const char *description;

} http_strerror_tab[] = {

HTTP_ERRNO_MAP(HTTP_STRERROR_GEN)

};

#undef HTTP_STRERROR_GEN

int http_message_needs_eof(const http_parser *parser);

/* Our URL parser.

* This is designed to be shared by http_parser_execute() for URL validation,

* hence it has a state transition + byte-for-byte interface. In addition, it

* is meant to be embedded in http_parser_parse_url(), which does the dirty

* work of turning state transitions URL components for its API.

* This function should only be invoked with non-space characters. It is

* assumed that the caller cares about (and can detect) the transition between

* URL and non-URL states by looking for these.

static enum state

parse_url_char(enum state s, const char ch)

{

if (ch == ' ' || ch == '\r' || ch == '\n') {

return s_dead;

}

#if HTTP_PARSER_STRICT

if (ch == '\t' || ch == '\f') {

return s_dead;

}

#endif

switch (s) {

case s_req_spaces_before_url:

/* Proxied requests are followed by scheme of an absolute URI (alpha).

* All methods except CONNECT are followed by '/' or '*'.

if (ch == '/' || ch == '*') {

return s_req_path;

}

if (IS_ALPHA(ch)) {

return s_req_schema;

}

break;

case s_req_schema:

if (IS_ALPHA(ch)) {

return s;

}

if (ch == ':') {

return s_req_schema_slash;

}

break;

case s_req_schema_slash:

if (ch == '/') {

return s_req_schema_slash_slash;

}

break;

case s_req_schema_slash_slash:

if (ch == '/') {

return s_req_server_start;

}

break;

case s_req_server_with_at:

if (ch == '@') {

return s_dead;

}

/* FALLTHROUGH */

case s_req_server_start:

case s_req_server:

if (ch == '/') {

return s_req_path;

}

if (ch == '?') {

return s_req_query_string_start;

}

if (ch == '@') {

return s_req_server_with_at;

}

if (IS_USERINFO_CHAR(ch) || ch == '[' || ch == ']') {

return s_req_server;

}

break;

case s_req_path:

if (IS_URL_CHAR(ch)) {

return s;

}

switch (ch) {

case '?':

return s_req_query_string_start;

case '#':

return s_req_fragment_start;

}

break;

case s_req_query_string_start:

case s_req_query_string:

if (IS_URL_CHAR(ch)) {

return s_req_query_string;

}

switch (ch) {

case '?':

/* allow extra '?' in query string */

return s_req_query_string;

case '#':

return s_req_fragment_start;

}

break;

case s_req_fragment_start:

if (IS_URL_CHAR(ch)) {

return s_req_fragment;

}

switch (ch) {

case '?':

return s_req_fragment;

case '#':

return s;

}

break;

case s_req_fragment:

if (IS_URL_CHAR(ch)) {

return s;

}

switch (ch) {

case '?':

case '#':

return s;

}

break;

default:

break;

}

/* We should never fall out of the switch above unless there's an error */

return s_dead;

}

size_t http_parser_execute (http_parser *parser,

const http_parser_settings *settings,

const char *data,

size_t len)

{

char c, ch;

int8_t unhex_val;

const char *p = data;

const char *header_field_mark = 0;

const char *header_value_mark = 0;

const char *url_mark = 0;

const char *body_mark = 0;

const char *status_mark = 0;

enum state p_state = (enum state) parser->state;

/* We're in an error state. Don't bother doing anything. */

if (HTTP_PARSER_ERRNO(parser) != HPE_OK) {

return 0;

}

if (len == 0) {

switch (CURRENT_STATE()) {

case s_body_identity_eof:

/* Use of CALLBACK_NOTIFY() here would erroneously return 1 byte read if

* we got paused.

CALLBACK_NOTIFY_NOADVANCE(message_complete);

return 0;

case s_dead:

case s_start_req_or_res:

case s_start_res:

case s_start_req:

return 0;

default:

SET_ERRNO(HPE_INVALID_EOF_STATE);

return 1;

}

if (CURRENT_STATE() == s_header_field)

header_field_mark = data;

if (CURRENT_STATE() == s_header_value)

header_value_mark = data;

switch (CURRENT_STATE()) {

case s_req_path:

case s_req_schema:

case s_req_schema_slash:

case s_req_schema_slash_slash:

case s_req_server_start:

case s_req_server:

case s_req_server_with_at:

case s_req_query_string_start:

case s_req_query_string:

case s_req_fragment_start:

case s_req_fragment:

url_mark = data;

break;

case s_res_status:

status_mark = data;

break;

default:

break;

}

for (p=data; p != data + len; p++) {

ch = *p;

if (PARSING_HEADER(CURRENT_STATE()))

COUNT_HEADER_SIZE(1);

reexecute:

switch (CURRENT_STATE()) {

case s_dead:

/* this state is used after a 'Connection: close' message

* the parser will error out if it reads another message

if (LIKELY(ch == CR || ch == LF))

break;

SET_ERRNO(HPE_CLOSED_CONNECTION);

goto error;

case s_start_req_or_res:

{

if (ch == CR || ch == LF)

break;

parser->flags = 0;

parser->content_length = ULLONG_MAX;

if (ch == 'H') {

UPDATE_STATE(s_res_or_resp_H);

CALLBACK_NOTIFY(message_begin);

} else {

parser->type = HTTP_REQUEST;

UPDATE_STATE(s_start_req);

REEXECUTE();

}

break;

}

case s_res_or_resp_H:

if (ch == 'T') {

parser->type = HTTP_RESPONSE;

UPDATE_STATE(s_res_HT);

} else {

if (UNLIKELY(ch != 'E')) {

SET_ERRNO(HPE_INVALID_CONSTANT);

goto error;

}

parser->type = HTTP_REQUEST;

parser->method = HTTP_HEAD;

parser->index = 2;

UPDATE_STATE(s_req_method);

}

break;

case s_start_res:

{

parser->flags = 0;

parser->content_length = ULLONG_MAX;

switch (ch) {

case 'H':

UPDATE_STATE(s_res_H);

break;

case CR:

case LF:

break;

default:

SET_ERRNO(HPE_INVALID_CONSTANT);

goto error;

}

CALLBACK_NOTIFY(message_begin);

break;

}

case s_res_H:

STRICT_CHECK(ch != 'T');

UPDATE_STATE(s_res_HT);

break;

case s_res_HT:

STRICT_CHECK(ch != 'T');

UPDATE_STATE(s_res_HTT);

break;

case s_res_HTT:

STRICT_CHECK(ch != 'P');

UPDATE_STATE(s_res_HTTP);

break;

case s_res_HTTP:

STRICT_CHECK(ch != '/');

UPDATE_STATE(s_res_first_http_major);

break;

case s_res_first_http_major:

if (UNLIKELY(ch < '0' || ch > '9')) {

SET_ERRNO(HPE_INVALID_VERSION);

goto error;

}

parser->http_major = ch - '0';

UPDATE_STATE(s_res_http_major);

break;

/* major HTTP version or dot */

case s_res_http_major:

{

if (ch == '.') {

UPDATE_STATE(s_res_first_http_minor);

break;

}

if (!IS_NUM(ch)) {

SET_ERRNO(HPE_INVALID_VERSION);

goto error;

}

parser->http_major *= 10;

parser->http_major += ch - '0';

if (UNLIKELY(parser->http_major > 999)) {

SET_ERRNO(HPE_INVALID_VERSION);

goto error;

}

break;

}

/* first digit of minor HTTP version */

case s_res_first_http_minor:

if (UNLIKELY(!IS_NUM(ch))) {

SET_ERRNO(HPE_INVALID_VERSION);

goto error;

}

parser->http_minor = ch - '0';

UPDATE_STATE(s_res_http_minor);

break;

/* minor HTTP version or end of request line */

case s_res_http_minor:

{

if (ch == ' ') {

UPDATE_STATE(s_res_first_status_code);

break;

}

if (UNLIKELY(!IS_NUM(ch))) {

SET_ERRNO(HPE_INVALID_VERSION);

goto error;

}

parser->http_minor *= 10;

parser->http_minor += ch - '0';

if (UNLIKELY(parser->http_minor > 999)) {

SET_ERRNO(HPE_INVALID_VERSION);

goto error;

}

break;

}

case s_res_first_status_code:

{

if (!IS_NUM(ch)) {

if (ch == ' ') {

break;

}

SET_ERRNO(HPE_INVALID_STATUS);

goto error;

}

parser->status_code = ch - '0';

UPDATE_STATE(s_res_status_code);

break;

}

case s_res_status_code:

{

if (!IS_NUM(ch)) {

switch (ch) {

case ' ':

UPDATE_STATE(s_res_status_start);

break;

case CR:

UPDATE_STATE(s_res_line_almost_done);

break;

case LF:

UPDATE_STATE(s_header_field_start);

break;

default:

SET_ERRNO(HPE_INVALID_STATUS);

goto error;

}

break;

}

parser->status_code *= 10;

parser->status_code += ch - '0';

if (UNLIKELY(parser->status_code > 999)) {

SET_ERRNO(HPE_INVALID_STATUS);

goto error;

}

break;

}

case s_res_status_start:

{

if (ch == CR) {

UPDATE_STATE(s_res_line_almost_done);

break;

}

if (ch == LF) {

UPDATE_STATE(s_header_field_start);

break;

}

MARK(status);

UPDATE_STATE(s_res_status);

parser->index = 0;

break;

}

case s_res_status:

if (ch == CR) {

UPDATE_STATE(s_res_line_almost_done);

CALLBACK_DATA(status);

break;

}

if (ch == LF) {

UPDATE_STATE(s_header_field_start);

CALLBACK_DATA(status);

break;

}

break;

case s_res_line_almost_done:

STRICT_CHECK(ch != LF);

UPDATE_STATE(s_header_field_start);

break;

case s_start_req:

{

if (ch == CR || ch == LF)

break;

parser->flags = 0;

parser->content_length = ULLONG_MAX;

if (UNLIKELY(!IS_ALPHA(ch))) {

SET_ERRNO(HPE_INVALID_METHOD);

goto error;

}

parser->method = (enum http_method) 0;

parser->index = 1;

switch (ch) {

case 'C': parser->method = HTTP_CONNECT; /* or COPY, CHECKOUT */ break;

case 'D': parser->method = HTTP_DELETE; break;

case 'G': parser->method = HTTP_GET; break;

case 'H': parser->method = HTTP_HEAD; break;

case 'L': parser->method = HTTP_LOCK; break;

case 'M': parser->method = HTTP_MKCOL; /* or MOVE, MKACTIVITY, MERGE, M-SEARCH, MKCALENDAR */ break;

case 'N': parser->method = HTTP_NOTIFY; break;

case 'O': parser->method = HTTP_OPTIONS; break;

case 'P': parser->method = HTTP_POST;

/* or PROPFIND|PROPPATCH|PUT|PATCH|PURGE */

break;

case 'R': parser->method = HTTP_REPORT; break;

case 'S': parser->method = HTTP_SUBSCRIBE; /* or SEARCH */ break;

case 'T': parser->method = HTTP_TRACE; break;

case 'U': parser->method = HTTP_UNLOCK; /* or UNSUBSCRIBE */ break;

default:

SET_ERRNO(HPE_INVALID_METHOD);

goto error;

}

UPDATE_STATE(s_req_method);

CALLBACK_NOTIFY(message_begin);

break;

}

case s_req_method:

{

const char *matcher;

if (UNLIKELY(ch == '\0')) {

SET_ERRNO(HPE_INVALID_METHOD);

goto error;

}

matcher = method_strings[parser->method];

if (ch == ' ' && matcher[parser->index] == '\0') {

UPDATE_STATE(s_req_spaces_before_url);

} else if (ch == matcher[parser->index]) {

; /* nada */

} else if (parser->method == HTTP_CONNECT) {

if (parser->index == 1 && ch == 'H') {

View remainder of file in raw view

nodegit/vendor/http_parser/http_parser.c at master · jBox/nodegit · GitHub

Repository navigation

Expand file tree

Breadcrumbs

http_parser.c

Latest commit

History

Breadcrumbs

http_parser.c

File metadata and controls