cpython/Modules/expat/xmltok.c at 3.9 · python-emscripten/cpython · 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

__ __ _

___\ \/ /_ __ __ _| |_

/ _ \\ /| '_ \ / _` | __|

| __// \| |_) | (_| | |_

\___/_/\_\ .__/ \__,_|\__|

|_| XML parser

Licensed under the MIT license:

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.

#ifdef _WIN32

# include "winconfig.h"

#else

# ifdef HAVE_EXPAT_CONFIG_H

# include <expat_config.h>

# endif

#endif /* ndef _WIN32 */

#include <stddef.h>

#include <string.h> /* memcpy */

#if defined(_MSC_VER) && (_MSC_VER <= 1700)

/* for vs2012/11.0/1700 and earlier Visual Studio compilers */

# define bool int

# define false 0

# define true 1

#else

# include <stdbool.h>

#endif

#include "expat_external.h"

#include "internal.h"

#include "xmltok.h"

#include "nametab.h"

#ifdef XML_DTD

# define IGNORE_SECTION_TOK_VTABLE , PREFIX(ignoreSectionTok)

#else

# define IGNORE_SECTION_TOK_VTABLE /* as nothing */

#endif

#define VTABLE1 \

{PREFIX(prologTok), PREFIX(contentTok), \

PREFIX(cdataSectionTok) IGNORE_SECTION_TOK_VTABLE}, \

{PREFIX(attributeValueTok), PREFIX(entityValueTok)}, \

PREFIX(nameMatchesAscii), PREFIX(nameLength), PREFIX(skipS), \

PREFIX(getAtts), PREFIX(charRefNumber), PREFIX(predefinedEntityName), \

PREFIX(updatePosition), PREFIX(isPublicId)

#define VTABLE VTABLE1, PREFIX(toUtf8), PREFIX(toUtf16)

#define UCS2_GET_NAMING(pages, hi, lo) \

(namingBitmap[(pages[hi] << 3) + ((lo) >> 5)] & (1u << ((lo)&0x1F)))

/* A 2 byte UTF-8 representation splits the characters 11 bits between

the bottom 5 and 6 bits of the bytes. We need 8 bits to index into

pages, 3 bits to add to that index and 5 bits to generate the mask.

#define UTF8_GET_NAMING2(pages, byte) \

(namingBitmap[((pages)[(((byte)[0]) >> 2) & 7] << 3) \

+ ((((byte)[0]) & 3) << 1) + ((((byte)[1]) >> 5) & 1)] \

& (1u << (((byte)[1]) & 0x1F)))

/* A 3 byte UTF-8 representation splits the characters 16 bits between

the bottom 4, 6 and 6 bits of the bytes. We need 8 bits to index

into pages, 3 bits to add to that index and 5 bits to generate the

mask.

#define UTF8_GET_NAMING3(pages, byte) \

(namingBitmap \

[((pages)[((((byte)[0]) & 0xF) << 4) + ((((byte)[1]) >> 2) & 0xF)] \

<< 3) \

+ ((((byte)[1]) & 3) << 1) + ((((byte)[2]) >> 5) & 1)] \

& (1u << (((byte)[2]) & 0x1F)))

#define UTF8_GET_NAMING(pages, p, n) \

((n) == 2 \

? UTF8_GET_NAMING2(pages, (const unsigned char *)(p)) \

: ((n) == 3 ? UTF8_GET_NAMING3(pages, (const unsigned char *)(p)) : 0))

/* Detection of invalid UTF-8 sequences is based on Table 3.1B

of Unicode 3.2: http://www.unicode.org/unicode/reports/tr28/

with the additional restriction of not allowing the Unicode

code points 0xFFFF and 0xFFFE (sequences EF,BF,BF and EF,BF,BE).

Implementation details:

(A & 0x80) == 0 means A < 0x80

and

(A & 0xC0) == 0xC0 means A > 0xBF

#define UTF8_INVALID2(p) \

((*p) < 0xC2 || ((p)[1] & 0x80) == 0 || ((p)[1] & 0xC0) == 0xC0)

#define UTF8_INVALID3(p) \

(((p)[2] & 0x80) == 0 \

|| ((*p) == 0xEF && (p)[1] == 0xBF ? (p)[2] > 0xBD \

: ((p)[2] & 0xC0) == 0xC0) \

|| ((*p) == 0xE0 \

? (p)[1] < 0xA0 || ((p)[1] & 0xC0) == 0xC0 \

: ((p)[1] & 0x80) == 0 \

|| ((*p) == 0xED ? (p)[1] > 0x9F : ((p)[1] & 0xC0) == 0xC0)))

#define UTF8_INVALID4(p) \

(((p)[3] & 0x80) == 0 || ((p)[3] & 0xC0) == 0xC0 || ((p)[2] & 0x80) == 0 \

|| ((p)[2] & 0xC0) == 0xC0 \

|| ((*p) == 0xF0 \

? (p)[1] < 0x90 || ((p)[1] & 0xC0) == 0xC0 \

: ((p)[1] & 0x80) == 0 \

|| ((*p) == 0xF4 ? (p)[1] > 0x8F : ((p)[1] & 0xC0) == 0xC0)))

static int PTRFASTCALL

isNever(const ENCODING *enc, const char *p) {

UNUSED_P(enc);

UNUSED_P(p);

return 0;

}

static int PTRFASTCALL

utf8_isName2(const ENCODING *enc, const char *p) {

UNUSED_P(enc);

return UTF8_GET_NAMING2(namePages, (const unsigned char *)p);

}

static int PTRFASTCALL

utf8_isName3(const ENCODING *enc, const char *p) {

UNUSED_P(enc);

return UTF8_GET_NAMING3(namePages, (const unsigned char *)p);

}

#define utf8_isName4 isNever

static int PTRFASTCALL

utf8_isNmstrt2(const ENCODING *enc, const char *p) {

UNUSED_P(enc);

return UTF8_GET_NAMING2(nmstrtPages, (const unsigned char *)p);

}

static int PTRFASTCALL

utf8_isNmstrt3(const ENCODING *enc, const char *p) {

UNUSED_P(enc);

return UTF8_GET_NAMING3(nmstrtPages, (const unsigned char *)p);

}

#define utf8_isNmstrt4 isNever

static int PTRFASTCALL

utf8_isInvalid2(const ENCODING *enc, const char *p) {

UNUSED_P(enc);

return UTF8_INVALID2((const unsigned char *)p);

}

static int PTRFASTCALL

utf8_isInvalid3(const ENCODING *enc, const char *p) {

UNUSED_P(enc);

return UTF8_INVALID3((const unsigned char *)p);

}

static int PTRFASTCALL

utf8_isInvalid4(const ENCODING *enc, const char *p) {

UNUSED_P(enc);

return UTF8_INVALID4((const unsigned char *)p);

}

struct normal_encoding {

ENCODING enc;

unsigned char type[256];

#ifdef XML_MIN_SIZE

int(PTRFASTCALL *byteType)(const ENCODING *, const char *);

int(PTRFASTCALL *isNameMin)(const ENCODING *, const char *);

int(PTRFASTCALL *isNmstrtMin)(const ENCODING *, const char *);

int(PTRFASTCALL *byteToAscii)(const ENCODING *, const char *);

int(PTRCALL *charMatches)(const ENCODING *, const char *, int);

#endif /* XML_MIN_SIZE */

int(PTRFASTCALL *isName2)(const ENCODING *, const char *);

int(PTRFASTCALL *isName3)(const ENCODING *, const char *);

int(PTRFASTCALL *isName4)(const ENCODING *, const char *);

int(PTRFASTCALL *isNmstrt2)(const ENCODING *, const char *);

int(PTRFASTCALL *isNmstrt3)(const ENCODING *, const char *);

int(PTRFASTCALL *isNmstrt4)(const ENCODING *, const char *);

int(PTRFASTCALL *isInvalid2)(const ENCODING *, const char *);

int(PTRFASTCALL *isInvalid3)(const ENCODING *, const char *);

int(PTRFASTCALL *isInvalid4)(const ENCODING *, const char *);

};

#define AS_NORMAL_ENCODING(enc) ((const struct normal_encoding *)(enc))

#ifdef XML_MIN_SIZE

# define STANDARD_VTABLE(E) \

E##byteType, E##isNameMin, E##isNmstrtMin, E##byteToAscii, E##charMatches,

#else

# define STANDARD_VTABLE(E) /* as nothing */

#endif

#define NORMAL_VTABLE(E) \

E##isName2, E##isName3, E##isName4, E##isNmstrt2, E##isNmstrt3, \

E##isNmstrt4, E##isInvalid2, E##isInvalid3, E##isInvalid4

#define NULL_VTABLE \

/* isName2 */ NULL, /* isName3 */ NULL, /* isName4 */ NULL, \

/* isNmstrt2 */ NULL, /* isNmstrt3 */ NULL, /* isNmstrt4 */ NULL, \

/* isInvalid2 */ NULL, /* isInvalid3 */ NULL, /* isInvalid4 */ NULL

static int FASTCALL checkCharRefNumber(int);

#include "xmltok_impl.h"

#include "ascii.h"

#ifdef XML_MIN_SIZE

# define sb_isNameMin isNever

# define sb_isNmstrtMin isNever

#endif

#ifdef XML_MIN_SIZE

# define MINBPC(enc) ((enc)->minBytesPerChar)

#else

/* minimum bytes per character */

# define MINBPC(enc) 1

#endif

#define SB_BYTE_TYPE(enc, p) \

(((struct normal_encoding *)(enc))->type[(unsigned char)*(p)])

#ifdef XML_MIN_SIZE

static int PTRFASTCALL

sb_byteType(const ENCODING *enc, const char *p) {

return SB_BYTE_TYPE(enc, p);

}

# define BYTE_TYPE(enc, p) (AS_NORMAL_ENCODING(enc)->byteType(enc, p))

#else

# define BYTE_TYPE(enc, p) SB_BYTE_TYPE(enc, p)

#endif

#ifdef XML_MIN_SIZE

# define BYTE_TO_ASCII(enc, p) (AS_NORMAL_ENCODING(enc)->byteToAscii(enc, p))

static int PTRFASTCALL

sb_byteToAscii(const ENCODING *enc, const char *p) {

UNUSED_P(enc);

return *p;

}

#else

# define BYTE_TO_ASCII(enc, p) (*(p))

#endif

#define IS_NAME_CHAR(enc, p, n) (AS_NORMAL_ENCODING(enc)->isName##n(enc, p))

#define IS_NMSTRT_CHAR(enc, p, n) (AS_NORMAL_ENCODING(enc)->isNmstrt##n(enc, p))

#define IS_INVALID_CHAR(enc, p, n) \

(AS_NORMAL_ENCODING(enc)->isInvalid##n(enc, p))

#ifdef XML_MIN_SIZE

# define IS_NAME_CHAR_MINBPC(enc, p) \

(AS_NORMAL_ENCODING(enc)->isNameMin(enc, p))

# define IS_NMSTRT_CHAR_MINBPC(enc, p) \

(AS_NORMAL_ENCODING(enc)->isNmstrtMin(enc, p))

#else

# define IS_NAME_CHAR_MINBPC(enc, p) (0)

# define IS_NMSTRT_CHAR_MINBPC(enc, p) (0)

#endif

#ifdef XML_MIN_SIZE

# define CHAR_MATCHES(enc, p, c) \

(AS_NORMAL_ENCODING(enc)->charMatches(enc, p, c))

static int PTRCALL

sb_charMatches(const ENCODING *enc, const char *p, int c) {

UNUSED_P(enc);

return *p == c;

}

#else

/* c is an ASCII character */

# define CHAR_MATCHES(enc, p, c) (*(p) == c)

#endif

#define PREFIX(ident) normal_##ident

#define XML_TOK_IMPL_C

#include "xmltok_impl.c"

#undef XML_TOK_IMPL_C

#undef MINBPC

#undef BYTE_TYPE

#undef BYTE_TO_ASCII

#undef CHAR_MATCHES

#undef IS_NAME_CHAR

#undef IS_NAME_CHAR_MINBPC

#undef IS_NMSTRT_CHAR

#undef IS_NMSTRT_CHAR_MINBPC

#undef IS_INVALID_CHAR

enum { /* UTF8_cvalN is value of masked first byte of N byte sequence */

UTF8_cval1 = 0x00,

UTF8_cval2 = 0xc0,

UTF8_cval3 = 0xe0,

UTF8_cval4 = 0xf0

};

void

_INTERNAL_trim_to_complete_utf8_characters(const char *from,

const char **fromLimRef) {

const char *fromLim = *fromLimRef;

size_t walked = 0;

for (; fromLim > from; fromLim--, walked++) {

const unsigned char prev = (unsigned char)fromLim[-1];

if ((prev & 0xf8u)

== 0xf0u) { /* 4-byte character, lead by 0b11110xxx byte */

if (walked + 1 >= 4) {

fromLim += 4 - 1;

break;

} else {

walked = 0;

}

} else if ((prev & 0xf0u)

== 0xe0u) { /* 3-byte character, lead by 0b1110xxxx byte */

if (walked + 1 >= 3) {

fromLim += 3 - 1;

break;

} else {

walked = 0;

}

} else if ((prev & 0xe0u)

== 0xc0u) { /* 2-byte character, lead by 0b110xxxxx byte */

if (walked + 1 >= 2) {

fromLim += 2 - 1;

break;

} else {

walked = 0;

}

} else if ((prev & 0x80u)

== 0x00u) { /* 1-byte character, matching 0b0xxxxxxx */

break;

}

*fromLimRef = fromLim;

}

static enum XML_Convert_Result PTRCALL

utf8_toUtf8(const ENCODING *enc, const char **fromP, const char *fromLim,

char **toP, const char *toLim) {

bool input_incomplete = false;

bool output_exhausted = false;

/* Avoid copying partial characters (due to limited space). */

const ptrdiff_t bytesAvailable = fromLim - *fromP;

const ptrdiff_t bytesStorable = toLim - *toP;

UNUSED_P(enc);

if (bytesAvailable > bytesStorable) {

fromLim = *fromP + bytesStorable;

output_exhausted = true;

}

/* Avoid copying partial characters (from incomplete input). */

{

const char *const fromLimBefore = fromLim;

_INTERNAL_trim_to_complete_utf8_characters(*fromP, &fromLim);

if (fromLim < fromLimBefore) {

input_incomplete = true;

}

{

const ptrdiff_t bytesToCopy = fromLim - *fromP;

memcpy(*toP, *fromP, bytesToCopy);

*fromP += bytesToCopy;

*toP += bytesToCopy;

}

if (output_exhausted) /* needs to go first */

return XML_CONVERT_OUTPUT_EXHAUSTED;

else if (input_incomplete)

return XML_CONVERT_INPUT_INCOMPLETE;

else

return XML_CONVERT_COMPLETED;

}

static enum XML_Convert_Result PTRCALL

utf8_toUtf16(const ENCODING *enc, const char **fromP, const char *fromLim,

unsigned short **toP, const unsigned short *toLim) {

enum XML_Convert_Result res = XML_CONVERT_COMPLETED;

unsigned short *to = *toP;

const char *from = *fromP;

while (from < fromLim && to < toLim) {

switch (((struct normal_encoding *)enc)->type[(unsigned char)*from]) {

case BT_LEAD2:

if (fromLim - from < 2) {

res = XML_CONVERT_INPUT_INCOMPLETE;

goto after;

}

*to++ = (unsigned short)(((from[0] & 0x1f) << 6) | (from[1] & 0x3f));

from += 2;

break;

case BT_LEAD3:

if (fromLim - from < 3) {

res = XML_CONVERT_INPUT_INCOMPLETE;

goto after;

}

*to++ = (unsigned short)(((from[0] & 0xf) << 12) | ((from[1] & 0x3f) << 6)

| (from[2] & 0x3f));

from += 3;

break;

case BT_LEAD4: {

unsigned long n;

if (toLim - to < 2) {

res = XML_CONVERT_OUTPUT_EXHAUSTED;

goto after;

}

if (fromLim - from < 4) {

res = XML_CONVERT_INPUT_INCOMPLETE;

goto after;

}

n = ((from[0] & 0x7) << 18) | ((from[1] & 0x3f) << 12)

| ((from[2] & 0x3f) << 6) | (from[3] & 0x3f);

n -= 0x10000;

to[0] = (unsigned short)((n >> 10) | 0xD800);

to[1] = (unsigned short)((n & 0x3FF) | 0xDC00);

to += 2;

from += 4;

} break;

default:

*to++ = *from++;

break;

}

if (from < fromLim)

res = XML_CONVERT_OUTPUT_EXHAUSTED;

after:

*fromP = from;

*toP = to;

return res;

}

#ifdef XML_NS

static const struct normal_encoding utf8_encoding_ns

= {{VTABLE1, utf8_toUtf8, utf8_toUtf16, 1, 1, 0},

{

# include "asciitab.h"

# include "utf8tab.h"

STANDARD_VTABLE(sb_) NORMAL_VTABLE(utf8_)};

#endif

static const struct normal_encoding utf8_encoding

= {{VTABLE1, utf8_toUtf8, utf8_toUtf16, 1, 1, 0},

{

#define BT_COLON BT_NMSTRT

#include "asciitab.h"

#undef BT_COLON

#include "utf8tab.h"

STANDARD_VTABLE(sb_) NORMAL_VTABLE(utf8_)};

#ifdef XML_NS

static const struct normal_encoding internal_utf8_encoding_ns

= {{VTABLE1, utf8_toUtf8, utf8_toUtf16, 1, 1, 0},

{

# include "iasciitab.h"

# include "utf8tab.h"

STANDARD_VTABLE(sb_) NORMAL_VTABLE(utf8_)};

#endif

static const struct normal_encoding internal_utf8_encoding

= {{VTABLE1, utf8_toUtf8, utf8_toUtf16, 1, 1, 0},

{

#define BT_COLON BT_NMSTRT

#include "iasciitab.h"

#undef BT_COLON

#include "utf8tab.h"

STANDARD_VTABLE(sb_) NORMAL_VTABLE(utf8_)};

static enum XML_Convert_Result PTRCALL

latin1_toUtf8(const ENCODING *enc, const char **fromP, const char *fromLim,

char **toP, const char *toLim) {

UNUSED_P(enc);

for (;;) {

unsigned char c;

if (*fromP == fromLim)

return XML_CONVERT_COMPLETED;

c = (unsigned char)**fromP;

if (c & 0x80) {

if (toLim - *toP < 2)

return XML_CONVERT_OUTPUT_EXHAUSTED;

*(*toP)++ = (char)((c >> 6) | UTF8_cval2);

*(*toP)++ = (char)((c & 0x3f) | 0x80);

(*fromP)++;

} else {

if (*toP == toLim)

return XML_CONVERT_OUTPUT_EXHAUSTED;

*(*toP)++ = *(*fromP)++;

}

static enum XML_Convert_Result PTRCALL

latin1_toUtf16(const ENCODING *enc, const char **fromP, const char *fromLim,

unsigned short **toP, const unsigned short *toLim) {

UNUSED_P(enc);

while (*fromP < fromLim && *toP < toLim)

*(*toP)++ = (unsigned char)*(*fromP)++;

if ((*toP == toLim) && (*fromP < fromLim))

return XML_CONVERT_OUTPUT_EXHAUSTED;

else

return XML_CONVERT_COMPLETED;

}

#ifdef XML_NS

static const struct normal_encoding latin1_encoding_ns

= {{VTABLE1, latin1_toUtf8, latin1_toUtf16, 1, 0, 0},

{

# include "asciitab.h"

# include "latin1tab.h"

STANDARD_VTABLE(sb_) NULL_VTABLE};

#endif

static const struct normal_encoding latin1_encoding

= {{VTABLE1, latin1_toUtf8, latin1_toUtf16, 1, 0, 0},

{

#define BT_COLON BT_NMSTRT

#include "asciitab.h"

#undef BT_COLON

#include "latin1tab.h"

STANDARD_VTABLE(sb_) NULL_VTABLE};

static enum XML_Convert_Result PTRCALL

ascii_toUtf8(const ENCODING *enc, const char **fromP, const char *fromLim,

char **toP, const char *toLim) {

UNUSED_P(enc);

while (*fromP < fromLim && *toP < toLim)

*(*toP)++ = *(*fromP)++;

if ((*toP == toLim) && (*fromP < fromLim))

return XML_CONVERT_OUTPUT_EXHAUSTED;

else

return XML_CONVERT_COMPLETED;

}

#ifdef XML_NS

static const struct normal_encoding ascii_encoding_ns

= {{VTABLE1, ascii_toUtf8, latin1_toUtf16, 1, 1, 0},

{

# include "asciitab.h"

/* BT_NONXML == 0 */

STANDARD_VTABLE(sb_) NULL_VTABLE};

#endif

static const struct normal_encoding ascii_encoding

= {{VTABLE1, ascii_toUtf8, latin1_toUtf16, 1, 1, 0},

{

#define BT_COLON BT_NMSTRT

#include "asciitab.h"

#undef BT_COLON

/* BT_NONXML == 0 */

STANDARD_VTABLE(sb_) NULL_VTABLE};

static int PTRFASTCALL

unicode_byte_type(char hi, char lo) {

switch ((unsigned char)hi) {

/* 0xD800–0xDBFF first 16-bit code unit or high surrogate (W1) */

case 0xD8:

case 0xD9:

case 0xDA:

case 0xDB:

return BT_LEAD4;

/* 0xDC00–0xDFFF second 16-bit code unit or low surrogate (W2) */

case 0xDC:

case 0xDD:

case 0xDE:

case 0xDF:

return BT_TRAIL;

case 0xFF:

switch ((unsigned char)lo) {

case 0xFF: /* noncharacter-FFFF */

case 0xFE: /* noncharacter-FFFE */

return BT_NONXML;

}

break;

}

return BT_NONASCII;

}

#define DEFINE_UTF16_TO_UTF8(E) \

static enum XML_Convert_Result PTRCALL E##toUtf8( \

const ENCODING *enc, const char **fromP, const char *fromLim, \

char **toP, const char *toLim) { \

const char *from = *fromP; \

UNUSED_P(enc); \

fromLim = from + (((fromLim - from) >> 1) << 1); /* shrink to even */ \

for (; from < fromLim; from += 2) { \

int plane; \

unsigned char lo2; \

unsigned char lo = GET_LO(from); \

unsigned char hi = GET_HI(from); \

switch (hi) { \

case 0: \

if (lo < 0x80) { \

if (*toP == toLim) { \

*fromP = from; \

return XML_CONVERT_OUTPUT_EXHAUSTED; \

} \

*(*toP)++ = lo; \

break; \

} \

/* fall through */ \

case 0x1: \

case 0x2: \

case 0x3: \

case 0x4: \

case 0x5: \

case 0x6: \

case 0x7: \

if (toLim - *toP < 2) { \

*fromP = from; \

return XML_CONVERT_OUTPUT_EXHAUSTED; \

} \

*(*toP)++ = ((lo >> 6) | (hi << 2) | UTF8_cval2); \

*(*toP)++ = ((lo & 0x3f) | 0x80); \

break; \

default: \

if (toLim - *toP < 3) { \

*fromP = from; \

return XML_CONVERT_OUTPUT_EXHAUSTED; \

} \

/* 16 bits divided 4, 6, 6 amongst 3 bytes */ \

*(*toP)++ = ((hi >> 4) | UTF8_cval3); \

*(*toP)++ = (((hi & 0xf) << 2) | (lo >> 6) | 0x80); \

*(*toP)++ = ((lo & 0x3f) | 0x80); \

break; \

case 0xD8: \

case 0xD9: \

case 0xDA: \

case 0xDB: \

if (toLim - *toP < 4) { \

*fromP = from; \

return XML_CONVERT_OUTPUT_EXHAUSTED; \

} \

if (fromLim - from < 4) { \

*fromP = from; \

return XML_CONVERT_INPUT_INCOMPLETE; \

} \

plane = (((hi & 0x3) << 2) | ((lo >> 6) & 0x3)) + 1; \

*(*toP)++ = (char)((plane >> 2) | UTF8_cval4); \

*(*toP)++ = (((lo >> 2) & 0xF) | ((plane & 0x3) << 4) | 0x80); \

from += 2; \

lo2 = GET_LO(from); \

*(*toP)++ = (((lo & 0x3) << 4) | ((GET_HI(from) & 0x3) << 2) \

| (lo2 >> 6) | 0x80); \

*(*toP)++ = ((lo2 & 0x3f) | 0x80); \

break; \

} \

*fromP = from; \

if (from < fromLim) \

return XML_CONVERT_INPUT_INCOMPLETE; \

else \

return XML_CONVERT_COMPLETED; \

}

#define DEFINE_UTF16_TO_UTF16(E) \

static enum XML_Convert_Result PTRCALL E##toUtf16( \

const ENCODING *enc, const char **fromP, const char *fromLim, \

unsigned short **toP, const unsigned short *toLim) { \

enum XML_Convert_Result res = XML_CONVERT_COMPLETED; \

UNUSED_P(enc); \

fromLim = *fromP + (((fromLim - *fromP) >> 1) << 1); /* shrink to even */ \

/* Avoid copying first half only of surrogate */ \

if (fromLim - *fromP > ((toLim - *toP) << 1) \

&& (GET_HI(fromLim - 2) & 0xF8) == 0xD8) { \

fromLim -= 2; \

res = XML_CONVERT_INPUT_INCOMPLETE; \

} \

for (; *fromP < fromLim && *toP < toLim; *fromP += 2) \

*(*toP)++ = (GET_HI(*fromP) << 8) | GET_LO(*fromP); \

if ((*toP == toLim) && (*fromP < fromLim)) \

return XML_CONVERT_OUTPUT_EXHAUSTED; \

else \

return res; \

}

#define SET2(ptr, ch) (((ptr)[0] = ((ch)&0xff)), ((ptr)[1] = ((ch) >> 8)))

#define GET_LO(ptr) ((unsigned char)(ptr)[0])

#define GET_HI(ptr) ((unsigned char)(ptr)[1])

DEFINE_UTF16_TO_UTF8(little2_)

DEFINE_UTF16_TO_UTF16(little2_)

#undef SET2

#undef GET_LO

#undef GET_HI

#define SET2(ptr, ch) (((ptr)[0] = ((ch) >> 8)), ((ptr)[1] = ((ch)&0xFF)))

#define GET_LO(ptr) ((unsigned char)(ptr)[1])

#define GET_HI(ptr) ((unsigned char)(ptr)[0])

DEFINE_UTF16_TO_UTF8(big2_)

DEFINE_UTF16_TO_UTF16(big2_)

#undef SET2

#undef GET_LO

#undef GET_HI

#define LITTLE2_BYTE_TYPE(enc, p) \

((p)[1] == 0 ? ((struct normal_encoding *)(enc))->type[(unsigned char)*(p)] \

: unicode_byte_type((p)[1], (p)[0]))

#define LITTLE2_BYTE_TO_ASCII(p) ((p)[1] == 0 ? (p)[0] : -1)

#define LITTLE2_CHAR_MATCHES(p, c) ((p)[1] == 0 && (p)[0] == c)

#define LITTLE2_IS_NAME_CHAR_MINBPC(p) \

UCS2_GET_NAMING(namePages, (unsigned char)p[1], (unsigned char)p[0])

#define LITTLE2_IS_NMSTRT_CHAR_MINBPC(p) \

UCS2_GET_NAMING(nmstrtPages, (unsigned char)p[1], (unsigned char)p[0])

#ifdef XML_MIN_SIZE

static int PTRFASTCALL

little2_byteType(const ENCODING *enc, const char *p) {

return LITTLE2_BYTE_TYPE(enc, p);

}

static int PTRFASTCALL

little2_byteToAscii(const ENCODING *enc, const char *p) {

UNUSED_P(enc);

return LITTLE2_BYTE_TO_ASCII(p);

}

static int PTRCALL

little2_charMatches(const ENCODING *enc, const char *p, int c) {

UNUSED_P(enc);

return LITTLE2_CHAR_MATCHES(p, c);

}

static int PTRFASTCALL

little2_isNameMin(const ENCODING *enc, const char *p) {

UNUSED_P(enc);

return LITTLE2_IS_NAME_CHAR_MINBPC(p);

}

static int PTRFASTCALL

little2_isNmstrtMin(const ENCODING *enc, const char *p) {

UNUSED_P(enc);

return LITTLE2_IS_NMSTRT_CHAR_MINBPC(p);

}

# undef VTABLE

# define VTABLE VTABLE1, little2_toUtf8, little2_toUtf16

#else /* not XML_MIN_SIZE */

# undef PREFIX

# define PREFIX(ident) little2_##ident

# define MINBPC(enc) 2

/* CHAR_MATCHES is guaranteed to have MINBPC bytes available. */

# define BYTE_TYPE(enc, p) LITTLE2_BYTE_TYPE(enc, p)

# define BYTE_TO_ASCII(enc, p) LITTLE2_BYTE_TO_ASCII(p)

# define CHAR_MATCHES(enc, p, c) LITTLE2_CHAR_MATCHES(p, c)

# define IS_NAME_CHAR(enc, p, n) 0

# define IS_NAME_CHAR_MINBPC(enc, p) LITTLE2_IS_NAME_CHAR_MINBPC(p)

# define IS_NMSTRT_CHAR(enc, p, n) (0)

# define IS_NMSTRT_CHAR_MINBPC(enc, p) LITTLE2_IS_NMSTRT_CHAR_MINBPC(p)

# define XML_TOK_IMPL_C

# include "xmltok_impl.c"

# undef XML_TOK_IMPL_C

# undef MINBPC

# undef BYTE_TYPE

# undef BYTE_TO_ASCII

# undef CHAR_MATCHES

# undef IS_NAME_CHAR

# undef IS_NAME_CHAR_MINBPC

# undef IS_NMSTRT_CHAR

# undef IS_NMSTRT_CHAR_MINBPC

# undef IS_INVALID_CHAR

#endif /* not XML_MIN_SIZE */

#ifdef XML_NS

static const struct normal_encoding little2_encoding_ns

= {{VTABLE, 2, 0,

# if BYTEORDER == 1234

# else

# endif

{

# include "asciitab.h"

# include "latin1tab.h"

STANDARD_VTABLE(little2_) NULL_VTABLE};

#endif

static const struct normal_encoding little2_encoding

= {{VTABLE, 2, 0,

#if BYTEORDER == 1234

#else

#endif

{

#define BT_COLON BT_NMSTRT

#include "asciitab.h"

#undef BT_COLON

#include "latin1tab.h"

STANDARD_VTABLE(little2_) NULL_VTABLE};

#if BYTEORDER != 4321

# ifdef XML_NS

static const struct normal_encoding internal_little2_encoding_ns

= {{VTABLE, 2, 0, 1},

{

# include "iasciitab.h"

# include "latin1tab.h"

STANDARD_VTABLE(little2_) NULL_VTABLE};

# endif

static const struct normal_encoding internal_little2_encoding

= {{VTABLE, 2, 0, 1},

{

# define BT_COLON BT_NMSTRT

# include "iasciitab.h"

# undef BT_COLON

# include "latin1tab.h"

STANDARD_VTABLE(little2_) NULL_VTABLE};

#endif

#define BIG2_BYTE_TYPE(enc, p) \

((p)[0] == 0 \

? ((struct normal_encoding *)(enc))->type[(unsigned char)(p)[1]] \

: unicode_byte_type((p)[0], (p)[1]))

#define BIG2_BYTE_TO_ASCII(p) ((p)[0] == 0 ? (p)[1] : -1)

#define BIG2_CHAR_MATCHES(p, c) ((p)[0] == 0 && (p)[1] == c)

#define BIG2_IS_NAME_CHAR_MINBPC(p) \

UCS2_GET_NAMING(namePages, (unsigned char)p[0], (unsigned char)p[1])

#define BIG2_IS_NMSTRT_CHAR_MINBPC(p) \

UCS2_GET_NAMING(nmstrtPages, (unsigned char)p[0], (unsigned char)p[1])

#ifdef XML_MIN_SIZE

static int PTRFASTCALL

big2_byteType(const ENCODING *enc, const char *p) {

return BIG2_BYTE_TYPE(enc, p);

}

static int PTRFASTCALL

big2_byteToAscii(const ENCODING *enc, const char *p) {

UNUSED_P(enc);

return BIG2_BYTE_TO_ASCII(p);

}

static int PTRCALL

big2_charMatches(const ENCODING *enc, const char *p, int c) {

UNUSED_P(enc);

return BIG2_CHAR_MATCHES(p, c);

}

static int PTRFASTCALL

big2_isNameMin(const ENCODING *enc, const char *p) {

UNUSED_P(enc);

return BIG2_IS_NAME_CHAR_MINBPC(p);

}

static int PTRFASTCALL

big2_isNmstrtMin(const ENCODING *enc, const char *p) {

UNUSED_P(enc);

return BIG2_IS_NMSTRT_CHAR_MINBPC(p);

}

# undef VTABLE

# define VTABLE VTABLE1, big2_toUtf8, big2_toUtf16

#else /* not XML_MIN_SIZE */

# undef PREFIX

# define PREFIX(ident) big2_##ident

# define MINBPC(enc) 2

/* CHAR_MATCHES is guaranteed to have MINBPC bytes available. */

# define BYTE_TYPE(enc, p) BIG2_BYTE_TYPE(enc, p)

# define BYTE_TO_ASCII(enc, p) BIG2_BYTE_TO_ASCII(p)

# define CHAR_MATCHES(enc, p, c) BIG2_CHAR_MATCHES(p, c)

# define IS_NAME_CHAR(enc, p, n) 0

# define IS_NAME_CHAR_MINBPC(enc, p) BIG2_IS_NAME_CHAR_MINBPC(p)

# define IS_NMSTRT_CHAR(enc, p, n) (0)

# define IS_NMSTRT_CHAR_MINBPC(enc, p) BIG2_IS_NMSTRT_CHAR_MINBPC(p)

# define XML_TOK_IMPL_C

# include "xmltok_impl.c"

# undef XML_TOK_IMPL_C

# undef MINBPC

# undef BYTE_TYPE

# undef BYTE_TO_ASCII

# undef CHAR_MATCHES

# undef IS_NAME_CHAR

# undef IS_NAME_CHAR_MINBPC

# undef IS_NMSTRT_CHAR

# undef IS_NMSTRT_CHAR_MINBPC

# undef IS_INVALID_CHAR

#endif /* not XML_MIN_SIZE */

#ifdef XML_NS

static const struct normal_encoding big2_encoding_ns

= {{VTABLE, 2, 0,

# if BYTEORDER == 4321

# else

# endif

{

# include "asciitab.h"

# include "latin1tab.h"

STANDARD_VTABLE(big2_) NULL_VTABLE};

#endif

static const struct normal_encoding big2_encoding

= {{VTABLE, 2, 0,

#if BYTEORDER == 4321

#else

#endif

{

#define BT_COLON BT_NMSTRT

#include "asciitab.h"

#undef BT_COLON

#include "latin1tab.h"

STANDARD_VTABLE(big2_) NULL_VTABLE};

#if BYTEORDER != 1234

# ifdef XML_NS

static const struct normal_encoding internal_big2_encoding_ns

= {{VTABLE, 2, 0, 1},

{

# include "iasciitab.h"

# include "latin1tab.h"

STANDARD_VTABLE(big2_) NULL_VTABLE};

# endif

static const struct normal_encoding internal_big2_encoding

= {{VTABLE, 2, 0, 1},

{

# define BT_COLON BT_NMSTRT

# include "iasciitab.h"

# undef BT_COLON

# include "latin1tab.h"

STANDARD_VTABLE(big2_) NULL_VTABLE};

View remainder of file in raw view

cpython/Modules/expat/xmltok.c at 3.9 · python-emscripten/cpython · GitHub

Repository navigation

Expand file tree

Breadcrumbs

xmltok.c

Latest commit

History

Breadcrumbs

xmltok.c

File metadata and controls