python/Modules/expat/xmlparse.c at master · charleson/python · GitHub

History

6268 lines (5925 loc) · 188 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

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

See the file COPYING for copying permission.

#define XML_BUILDING_EXPAT 1

#ifdef COMPILED_FROM_DSP

#include "winconfig.h"

#elif defined(MACOS_CLASSIC)

#include "macconfig.h"

#elif defined(__amigaos4__)

#include "amigaconfig.h"

#elif defined(HAVE_EXPAT_CONFIG_H)

#include <expat_config.h>

#endif /* ndef COMPILED_FROM_DSP */

#include <stddef.h>

#include <string.h> /* memset(), memcpy() */

#include <assert.h>

#include "expat.h"

#ifdef XML_UNICODE

#define XML_ENCODE_MAX XML_UTF16_ENCODE_MAX

#define XmlConvert XmlUtf16Convert

#define XmlGetInternalEncoding XmlGetUtf16InternalEncoding

#define XmlGetInternalEncodingNS XmlGetUtf16InternalEncodingNS

#define XmlEncode XmlUtf16Encode

#define MUST_CONVERT(enc, s) (!(enc)->isUtf16 || (((unsigned long)s) & 1))

typedef unsigned short ICHAR;

#else

#define XML_ENCODE_MAX XML_UTF8_ENCODE_MAX

#define XmlConvert XmlUtf8Convert

#define XmlGetInternalEncoding XmlGetUtf8InternalEncoding

#define XmlGetInternalEncodingNS XmlGetUtf8InternalEncodingNS

#define XmlEncode XmlUtf8Encode

#define MUST_CONVERT(enc, s) (!(enc)->isUtf8)

typedef char ICHAR;

#endif

#ifndef XML_NS

#define XmlInitEncodingNS XmlInitEncoding

#define XmlInitUnknownEncodingNS XmlInitUnknownEncoding

#undef XmlGetInternalEncodingNS

#define XmlGetInternalEncodingNS XmlGetInternalEncoding

#define XmlParseXmlDeclNS XmlParseXmlDecl

#endif

#ifdef XML_UNICODE

#ifdef XML_UNICODE_WCHAR_T

#define XML_T(x) (const wchar_t)x

#define XML_L(x) L ## x

#else

#define XML_T(x) (const unsigned short)x

#define XML_L(x) x

#endif

#else

#define XML_T(x) x

#define XML_L(x) x

#endif

/* Round up n to be a multiple of sz, where sz is a power of 2. */

#define ROUND_UP(n, sz) (((n) + ((sz) - 1)) & ~((sz) - 1))

/* Handle the case where memmove() doesn't exist. */

#ifndef HAVE_MEMMOVE

#ifdef HAVE_BCOPY

#define memmove(d,s,l) bcopy((s),(d),(l))

#else

#error memmove does not exist on this platform, nor is a substitute available

#endif /* HAVE_BCOPY */

#endif /* HAVE_MEMMOVE */

#include "internal.h"

#include "xmltok.h"

#include "xmlrole.h"

typedef const XML_Char *KEY;

typedef struct {

KEY name;

} NAMED;

typedef struct {

NAMED **v;

unsigned char power;

size_t size;

size_t used;

const XML_Memory_Handling_Suite *mem;

} HASH_TABLE;

/* Basic character hash algorithm, taken from Python's string hash:

h = h * 1000003 ^ character, the constant being a prime number.

#ifdef XML_UNICODE

#define CHAR_HASH(h, c) \

(((h) * 0xF4243) ^ (unsigned short)(c))

#else

#define CHAR_HASH(h, c) \

(((h) * 0xF4243) ^ (unsigned char)(c))

#endif

/* For probing (after a collision) we need a step size relative prime

to the hash table size, which is a power of 2. We use double-hashing,

since we can calculate a second hash value cheaply by taking those bits

of the first hash value that were discarded (masked out) when the table

index was calculated: index = hash & mask, where mask = table->size - 1.

We limit the maximum step size to table->size / 4 (mask >> 2) and make

it odd, since odd numbers are always relative prime to a power of 2.

#define SECOND_HASH(hash, mask, power) \

((((hash) & ~(mask)) >> ((power) - 1)) & ((mask) >> 2))

#define PROBE_STEP(hash, mask, power) \

((unsigned char)((SECOND_HASH(hash, mask, power)) | 1))

typedef struct {

NAMED **p;

NAMED **end;

} HASH_TABLE_ITER;

#define INIT_TAG_BUF_SIZE 32 /* must be a multiple of sizeof(XML_Char) */

#define INIT_DATA_BUF_SIZE 1024

#define INIT_ATTS_SIZE 16

#define INIT_ATTS_VERSION 0xFFFFFFFF

#define INIT_BLOCK_SIZE 1024

#define INIT_BUFFER_SIZE 1024

#define EXPAND_SPARE 24

typedef struct binding {

struct prefix *prefix;

struct binding *nextTagBinding;

struct binding *prevPrefixBinding;

const struct attribute_id *attId;

XML_Char *uri;

int uriLen;

int uriAlloc;

} BINDING;

typedef struct prefix {

const XML_Char *name;

BINDING *binding;

} PREFIX;

typedef struct {

const XML_Char *str;

const XML_Char *localPart;

const XML_Char *prefix;

int strLen;

int uriLen;

int prefixLen;

} TAG_NAME;

/* TAG represents an open element.

The name of the element is stored in both the document and API

encodings. The memory buffer 'buf' is a separately-allocated

memory area which stores the name. During the XML_Parse()/

XMLParseBuffer() when the element is open, the memory for the 'raw'

version of the name (in the document encoding) is shared with the

document buffer. If the element is open across calls to

XML_Parse()/XML_ParseBuffer(), the buffer is re-allocated to

contain the 'raw' name as well.

A parser re-uses these structures, maintaining a list of allocated

TAG objects in a free list.

typedef struct tag {

struct tag *parent; /* parent of this element */

const char *rawName; /* tagName in the original encoding */

int rawNameLength;

TAG_NAME name; /* tagName in the API encoding */

char *buf; /* buffer for name components */

char *bufEnd; /* end of the buffer */

BINDING *bindings;

} TAG;

typedef struct {

const XML_Char *name;

const XML_Char *textPtr;

int textLen; /* length in XML_Chars */

int processed; /* # of processed bytes - when suspended */

const XML_Char *systemId;

const XML_Char *base;

const XML_Char *publicId;

const XML_Char *notation;

XML_Bool open;

XML_Bool is_param;

XML_Bool is_internal; /* true if declared in internal subset outside PE */

} ENTITY;

typedef struct {

enum XML_Content_Type type;

enum XML_Content_Quant quant;

const XML_Char * name;

int firstchild;

int lastchild;

int childcnt;

int nextsib;

} CONTENT_SCAFFOLD;

#define INIT_SCAFFOLD_ELEMENTS 32

typedef struct block {

struct block *next;

int size;

XML_Char s[1];

} BLOCK;

typedef struct {

BLOCK *blocks;

BLOCK *freeBlocks;

const XML_Char *end;

XML_Char *ptr;

XML_Char *start;

const XML_Memory_Handling_Suite *mem;

} STRING_POOL;

/* The XML_Char before the name is used to determine whether

an attribute has been specified. */

typedef struct attribute_id {

XML_Char *name;

PREFIX *prefix;

XML_Bool maybeTokenized;

XML_Bool xmlns;

} ATTRIBUTE_ID;

typedef struct {

const ATTRIBUTE_ID *id;

XML_Bool isCdata;

const XML_Char *value;

} DEFAULT_ATTRIBUTE;

typedef struct {

unsigned long version;

unsigned long hash;

const XML_Char *uriName;

} NS_ATT;

typedef struct {

const XML_Char *name;

PREFIX *prefix;

const ATTRIBUTE_ID *idAtt;

int nDefaultAtts;

int allocDefaultAtts;

DEFAULT_ATTRIBUTE *defaultAtts;

} ELEMENT_TYPE;

typedef struct {

HASH_TABLE generalEntities;

HASH_TABLE elementTypes;

HASH_TABLE attributeIds;

HASH_TABLE prefixes;

STRING_POOL pool;

STRING_POOL entityValuePool;

/* false once a parameter entity reference has been skipped */

XML_Bool keepProcessing;

/* true once an internal or external PE reference has been encountered;

this includes the reference to an external subset */

XML_Bool hasParamEntityRefs;

XML_Bool standalone;

#ifdef XML_DTD

/* indicates if external PE has been read */

XML_Bool paramEntityRead;

HASH_TABLE paramEntities;

#endif /* XML_DTD */

PREFIX defaultPrefix;

/* === scaffolding for building content model === */

XML_Bool in_eldecl;

CONTENT_SCAFFOLD *scaffold;

unsigned contentStringLen;

unsigned scaffSize;

unsigned scaffCount;

int scaffLevel;

int *scaffIndex;

} DTD;

typedef struct open_internal_entity {

const char *internalEventPtr;

const char *internalEventEndPtr;

struct open_internal_entity *next;

ENTITY *entity;

int startTagLevel;

XML_Bool betweenDecl; /* WFC: PE Between Declarations */

} OPEN_INTERNAL_ENTITY;

typedef enum XML_Error PTRCALL Processor(XML_Parser parser,

const char *start,

const char *end,

const char **endPtr);

static Processor prologProcessor;

static Processor prologInitProcessor;

static Processor contentProcessor;

static Processor cdataSectionProcessor;

#ifdef XML_DTD

static Processor ignoreSectionProcessor;

static Processor externalParEntProcessor;

static Processor externalParEntInitProcessor;

static Processor entityValueProcessor;

static Processor entityValueInitProcessor;

#endif /* XML_DTD */

static Processor epilogProcessor;

static Processor errorProcessor;

static Processor externalEntityInitProcessor;

static Processor externalEntityInitProcessor2;

static Processor externalEntityInitProcessor3;

static Processor externalEntityContentProcessor;

static Processor internalEntityProcessor;

static enum XML_Error

handleUnknownEncoding(XML_Parser parser, const XML_Char *encodingName);

static enum XML_Error

processXmlDecl(XML_Parser parser, int isGeneralTextEntity,

const char *s, const char *next);

static enum XML_Error

initializeEncoding(XML_Parser parser);

static enum XML_Error

doProlog(XML_Parser parser, const ENCODING *enc, const char *s,

const char *end, int tok, const char *next, const char **nextPtr,

XML_Bool haveMore);

static enum XML_Error

processInternalEntity(XML_Parser parser, ENTITY *entity,

XML_Bool betweenDecl);

static enum XML_Error

doContent(XML_Parser parser, int startTagLevel, const ENCODING *enc,

const char *start, const char *end, const char **endPtr,

XML_Bool haveMore);

static enum XML_Error

doCdataSection(XML_Parser parser, const ENCODING *, const char **startPtr,

const char *end, const char **nextPtr, XML_Bool haveMore);

#ifdef XML_DTD

static enum XML_Error

doIgnoreSection(XML_Parser parser, const ENCODING *, const char **startPtr,

const char *end, const char **nextPtr, XML_Bool haveMore);

#endif /* XML_DTD */

static enum XML_Error

storeAtts(XML_Parser parser, const ENCODING *, const char *s,

TAG_NAME *tagNamePtr, BINDING **bindingsPtr);

static enum XML_Error

addBinding(XML_Parser parser, PREFIX *prefix, const ATTRIBUTE_ID *attId,

const XML_Char *uri, BINDING **bindingsPtr);

static int

defineAttribute(ELEMENT_TYPE *type, ATTRIBUTE_ID *, XML_Bool isCdata,

XML_Bool isId, const XML_Char *dfltValue, XML_Parser parser);

static enum XML_Error

storeAttributeValue(XML_Parser parser, const ENCODING *, XML_Bool isCdata,

const char *, const char *, STRING_POOL *);

static enum XML_Error

appendAttributeValue(XML_Parser parser, const ENCODING *, XML_Bool isCdata,

const char *, const char *, STRING_POOL *);

static ATTRIBUTE_ID *

getAttributeId(XML_Parser parser, const ENCODING *enc, const char *start,

const char *end);

static int

setElementTypePrefix(XML_Parser parser, ELEMENT_TYPE *);

static enum XML_Error

storeEntityValue(XML_Parser parser, const ENCODING *enc, const char *start,

const char *end);

static int

reportProcessingInstruction(XML_Parser parser, const ENCODING *enc,

const char *start, const char *end);

static int

reportComment(XML_Parser parser, const ENCODING *enc, const char *start,

const char *end);

static void

reportDefault(XML_Parser parser, const ENCODING *enc, const char *start,

const char *end);

static const XML_Char * getContext(XML_Parser parser);

static XML_Bool

setContext(XML_Parser parser, const XML_Char *context);

static void FASTCALL normalizePublicId(XML_Char *s);

static DTD * dtdCreate(const XML_Memory_Handling_Suite *ms);

/* do not call if parentParser != NULL */

static void dtdReset(DTD *p, const XML_Memory_Handling_Suite *ms);

static void

dtdDestroy(DTD *p, XML_Bool isDocEntity, const XML_Memory_Handling_Suite *ms);

static int

dtdCopy(DTD *newDtd, const DTD *oldDtd, const XML_Memory_Handling_Suite *ms);

static int

copyEntityTable(HASH_TABLE *, STRING_POOL *, const HASH_TABLE *);

static NAMED *

lookup(HASH_TABLE *table, KEY name, size_t createSize);

static void FASTCALL

hashTableInit(HASH_TABLE *, const XML_Memory_Handling_Suite *ms);

static void FASTCALL hashTableClear(HASH_TABLE *);

static void FASTCALL hashTableDestroy(HASH_TABLE *);

static void FASTCALL

hashTableIterInit(HASH_TABLE_ITER *, const HASH_TABLE *);

static NAMED * FASTCALL hashTableIterNext(HASH_TABLE_ITER *);

static void FASTCALL

poolInit(STRING_POOL *, const XML_Memory_Handling_Suite *ms);

static void FASTCALL poolClear(STRING_POOL *);

static void FASTCALL poolDestroy(STRING_POOL *);

static XML_Char *

poolAppend(STRING_POOL *pool, const ENCODING *enc,

const char *ptr, const char *end);

static XML_Char *

poolStoreString(STRING_POOL *pool, const ENCODING *enc,

const char *ptr, const char *end);

static XML_Bool FASTCALL poolGrow(STRING_POOL *pool);

static const XML_Char * FASTCALL

poolCopyString(STRING_POOL *pool, const XML_Char *s);

static const XML_Char *

poolCopyStringN(STRING_POOL *pool, const XML_Char *s, int n);

static const XML_Char * FASTCALL

poolAppendString(STRING_POOL *pool, const XML_Char *s);

static int FASTCALL nextScaffoldPart(XML_Parser parser);

static XML_Content * build_model(XML_Parser parser);

static ELEMENT_TYPE *

getElementType(XML_Parser parser, const ENCODING *enc,

const char *ptr, const char *end);

static XML_Parser

parserCreate(const XML_Char *encodingName,

const XML_Memory_Handling_Suite *memsuite,

const XML_Char *nameSep,

DTD *dtd);

static void

parserInit(XML_Parser parser, const XML_Char *encodingName);

#define poolStart(pool) ((pool)->start)

#define poolEnd(pool) ((pool)->ptr)

#define poolLength(pool) ((pool)->ptr - (pool)->start)

#define poolChop(pool) ((void)--(pool->ptr))

#define poolLastChar(pool) (((pool)->ptr)[-1])

#define poolDiscard(pool) ((pool)->ptr = (pool)->start)

#define poolFinish(pool) ((pool)->start = (pool)->ptr)

#define poolAppendChar(pool, c) \

(((pool)->ptr == (pool)->end && !poolGrow(pool)) \

? 0 \

: ((*((pool)->ptr)++ = c), 1))

struct XML_ParserStruct {

/* The first member must be userData so that the XML_GetUserData

macro works. */

void *m_userData;

void *m_handlerArg;

char *m_buffer;

const XML_Memory_Handling_Suite m_mem;

/* first character to be parsed */

const char *m_bufferPtr;

/* past last character to be parsed */

char *m_bufferEnd;

/* allocated end of buffer */

const char *m_bufferLim;

XML_Index m_parseEndByteIndex;

const char *m_parseEndPtr;

XML_Char *m_dataBuf;

XML_Char *m_dataBufEnd;

XML_StartElementHandler m_startElementHandler;

XML_EndElementHandler m_endElementHandler;

XML_CharacterDataHandler m_characterDataHandler;

XML_ProcessingInstructionHandler m_processingInstructionHandler;

XML_CommentHandler m_commentHandler;

XML_StartCdataSectionHandler m_startCdataSectionHandler;

XML_EndCdataSectionHandler m_endCdataSectionHandler;

XML_DefaultHandler m_defaultHandler;

XML_StartDoctypeDeclHandler m_startDoctypeDeclHandler;

XML_EndDoctypeDeclHandler m_endDoctypeDeclHandler;

XML_UnparsedEntityDeclHandler m_unparsedEntityDeclHandler;

XML_NotationDeclHandler m_notationDeclHandler;

XML_StartNamespaceDeclHandler m_startNamespaceDeclHandler;

XML_EndNamespaceDeclHandler m_endNamespaceDeclHandler;

XML_NotStandaloneHandler m_notStandaloneHandler;

XML_ExternalEntityRefHandler m_externalEntityRefHandler;

XML_Parser m_externalEntityRefHandlerArg;

XML_SkippedEntityHandler m_skippedEntityHandler;

XML_UnknownEncodingHandler m_unknownEncodingHandler;

XML_ElementDeclHandler m_elementDeclHandler;

XML_AttlistDeclHandler m_attlistDeclHandler;

XML_EntityDeclHandler m_entityDeclHandler;

XML_XmlDeclHandler m_xmlDeclHandler;

const ENCODING *m_encoding;

INIT_ENCODING m_initEncoding;

const ENCODING *m_internalEncoding;

const XML_Char *m_protocolEncodingName;

XML_Bool m_ns;

XML_Bool m_ns_triplets;

void *m_unknownEncodingMem;

void *m_unknownEncodingData;

void *m_unknownEncodingHandlerData;

void (XMLCALL *m_unknownEncodingRelease)(void *);

PROLOG_STATE m_prologState;

Processor *m_processor;

enum XML_Error m_errorCode;

const char *m_eventPtr;

const char *m_eventEndPtr;

const char *m_positionPtr;

OPEN_INTERNAL_ENTITY *m_openInternalEntities;

OPEN_INTERNAL_ENTITY *m_freeInternalEntities;

XML_Bool m_defaultExpandInternalEntities;

int m_tagLevel;

ENTITY *m_declEntity;

const XML_Char *m_doctypeName;

const XML_Char *m_doctypeSysid;

const XML_Char *m_doctypePubid;

const XML_Char *m_declAttributeType;

const XML_Char *m_declNotationName;

const XML_Char *m_declNotationPublicId;

ELEMENT_TYPE *m_declElementType;

ATTRIBUTE_ID *m_declAttributeId;

XML_Bool m_declAttributeIsCdata;

XML_Bool m_declAttributeIsId;

DTD *m_dtd;

const XML_Char *m_curBase;

TAG *m_tagStack;

TAG *m_freeTagList;

BINDING *m_inheritedBindings;

BINDING *m_freeBindingList;

int m_attsSize;

int m_nSpecifiedAtts;

int m_idAttIndex;

ATTRIBUTE *m_atts;

NS_ATT *m_nsAtts;

unsigned long m_nsAttsVersion;

unsigned char m_nsAttsPower;

POSITION m_position;

STRING_POOL m_tempPool;

STRING_POOL m_temp2Pool;

char *m_groupConnector;

unsigned int m_groupSize;

XML_Char m_namespaceSeparator;

XML_Parser m_parentParser;

XML_ParsingStatus m_parsingStatus;

#ifdef XML_DTD

XML_Bool m_isParamEntity;

XML_Bool m_useForeignDTD;

enum XML_ParamEntityParsing m_paramEntityParsing;

#endif

};

#define MALLOC(s) (parser->m_mem.malloc_fcn((s)))

#define REALLOC(p,s) (parser->m_mem.realloc_fcn((p),(s)))

#define FREE(p) (parser->m_mem.free_fcn((p)))

#define userData (parser->m_userData)

#define handlerArg (parser->m_handlerArg)

#define startElementHandler (parser->m_startElementHandler)

#define endElementHandler (parser->m_endElementHandler)

#define characterDataHandler (parser->m_characterDataHandler)

#define processingInstructionHandler \

(parser->m_processingInstructionHandler)

#define commentHandler (parser->m_commentHandler)

#define startCdataSectionHandler \

(parser->m_startCdataSectionHandler)

#define endCdataSectionHandler (parser->m_endCdataSectionHandler)

#define defaultHandler (parser->m_defaultHandler)

#define startDoctypeDeclHandler (parser->m_startDoctypeDeclHandler)

#define endDoctypeDeclHandler (parser->m_endDoctypeDeclHandler)

#define unparsedEntityDeclHandler \

(parser->m_unparsedEntityDeclHandler)

#define notationDeclHandler (parser->m_notationDeclHandler)

#define startNamespaceDeclHandler \

(parser->m_startNamespaceDeclHandler)

#define endNamespaceDeclHandler (parser->m_endNamespaceDeclHandler)

#define notStandaloneHandler (parser->m_notStandaloneHandler)

#define externalEntityRefHandler \

(parser->m_externalEntityRefHandler)

#define externalEntityRefHandlerArg \

(parser->m_externalEntityRefHandlerArg)

#define internalEntityRefHandler \

(parser->m_internalEntityRefHandler)

#define skippedEntityHandler (parser->m_skippedEntityHandler)

#define unknownEncodingHandler (parser->m_unknownEncodingHandler)

#define elementDeclHandler (parser->m_elementDeclHandler)

#define attlistDeclHandler (parser->m_attlistDeclHandler)

#define entityDeclHandler (parser->m_entityDeclHandler)

#define xmlDeclHandler (parser->m_xmlDeclHandler)

#define encoding (parser->m_encoding)

#define initEncoding (parser->m_initEncoding)

#define internalEncoding (parser->m_internalEncoding)

#define unknownEncodingMem (parser->m_unknownEncodingMem)

#define unknownEncodingData (parser->m_unknownEncodingData)

#define unknownEncodingHandlerData \

(parser->m_unknownEncodingHandlerData)

#define unknownEncodingRelease (parser->m_unknownEncodingRelease)

#define protocolEncodingName (parser->m_protocolEncodingName)

#define ns (parser->m_ns)

#define ns_triplets (parser->m_ns_triplets)

#define prologState (parser->m_prologState)

#define processor (parser->m_processor)

#define errorCode (parser->m_errorCode)

#define eventPtr (parser->m_eventPtr)

#define eventEndPtr (parser->m_eventEndPtr)

#define positionPtr (parser->m_positionPtr)

#define position (parser->m_position)

#define openInternalEntities (parser->m_openInternalEntities)

#define freeInternalEntities (parser->m_freeInternalEntities)

#define defaultExpandInternalEntities \

(parser->m_defaultExpandInternalEntities)

#define tagLevel (parser->m_tagLevel)

#define buffer (parser->m_buffer)

#define bufferPtr (parser->m_bufferPtr)

#define bufferEnd (parser->m_bufferEnd)

#define parseEndByteIndex (parser->m_parseEndByteIndex)

#define parseEndPtr (parser->m_parseEndPtr)

#define bufferLim (parser->m_bufferLim)

#define dataBuf (parser->m_dataBuf)

#define dataBufEnd (parser->m_dataBufEnd)

#define _dtd (parser->m_dtd)

#define curBase (parser->m_curBase)

#define declEntity (parser->m_declEntity)

#define doctypeName (parser->m_doctypeName)

#define doctypeSysid (parser->m_doctypeSysid)

#define doctypePubid (parser->m_doctypePubid)

#define declAttributeType (parser->m_declAttributeType)

#define declNotationName (parser->m_declNotationName)

#define declNotationPublicId (parser->m_declNotationPublicId)

#define declElementType (parser->m_declElementType)

#define declAttributeId (parser->m_declAttributeId)

#define declAttributeIsCdata (parser->m_declAttributeIsCdata)

#define declAttributeIsId (parser->m_declAttributeIsId)

#define freeTagList (parser->m_freeTagList)

#define freeBindingList (parser->m_freeBindingList)

#define inheritedBindings (parser->m_inheritedBindings)

#define tagStack (parser->m_tagStack)

#define atts (parser->m_atts)

#define attsSize (parser->m_attsSize)

#define nSpecifiedAtts (parser->m_nSpecifiedAtts)

#define idAttIndex (parser->m_idAttIndex)

#define nsAtts (parser->m_nsAtts)

#define nsAttsVersion (parser->m_nsAttsVersion)

#define nsAttsPower (parser->m_nsAttsPower)

#define tempPool (parser->m_tempPool)

#define temp2Pool (parser->m_temp2Pool)

#define groupConnector (parser->m_groupConnector)

#define groupSize (parser->m_groupSize)

#define namespaceSeparator (parser->m_namespaceSeparator)

#define parentParser (parser->m_parentParser)

#define ps_parsing (parser->m_parsingStatus.parsing)

#define ps_finalBuffer (parser->m_parsingStatus.finalBuffer)

#ifdef XML_DTD

#define isParamEntity (parser->m_isParamEntity)

#define useForeignDTD (parser->m_useForeignDTD)

#define paramEntityParsing (parser->m_paramEntityParsing)

#endif /* XML_DTD */

XML_Parser XMLCALL

XML_ParserCreate(const XML_Char *encodingName)

{

return XML_ParserCreate_MM(encodingName, NULL, NULL);

}

XML_Parser XMLCALL

XML_ParserCreateNS(const XML_Char *encodingName, XML_Char nsSep)

{

XML_Char tmp[2];

*tmp = nsSep;

return XML_ParserCreate_MM(encodingName, NULL, tmp);

}

static const XML_Char implicitContext[] = {

'x', 'm', 'l', '=', 'h', 't', 't', 'p', ':', '/', '/',

'w', 'w', 'w', '.', 'w', '3', '.', 'o', 'r', 'g', '/',

'X', 'M', 'L', '/', '1', '9', '9', '8', '/',

'n', 'a', 'm', 'e', 's', 'p', 'a', 'c', 'e', '\0'

};

XML_Parser XMLCALL

XML_ParserCreate_MM(const XML_Char *encodingName,

const XML_Memory_Handling_Suite *memsuite,

const XML_Char *nameSep)

{

XML_Parser parser = parserCreate(encodingName, memsuite, nameSep, NULL);

if (parser != NULL && ns) {

/* implicit context only set for root parser, since child

parsers (i.e. external entity parsers) will inherit it

if (!setContext(parser, implicitContext)) {

XML_ParserFree(parser);

return NULL;

}

return parser;

}

static XML_Parser

parserCreate(const XML_Char *encodingName,

const XML_Memory_Handling_Suite *memsuite,

const XML_Char *nameSep,

DTD *dtd)

{

XML_Parser parser;

if (memsuite) {

XML_Memory_Handling_Suite *mtemp;

parser = (XML_Parser)

memsuite->malloc_fcn(sizeof(struct XML_ParserStruct));

if (parser != NULL) {

mtemp = (XML_Memory_Handling_Suite *)&(parser->m_mem);

mtemp->malloc_fcn = memsuite->malloc_fcn;

mtemp->realloc_fcn = memsuite->realloc_fcn;

mtemp->free_fcn = memsuite->free_fcn;

}

else {

XML_Memory_Handling_Suite *mtemp;

parser = (XML_Parser)malloc(sizeof(struct XML_ParserStruct));

if (parser != NULL) {

mtemp = (XML_Memory_Handling_Suite *)&(parser->m_mem);

mtemp->malloc_fcn = malloc;

mtemp->realloc_fcn = realloc;

mtemp->free_fcn = free;

}

if (!parser)

return parser;

buffer = NULL;

bufferLim = NULL;

attsSize = INIT_ATTS_SIZE;

atts = (ATTRIBUTE *)MALLOC(attsSize * sizeof(ATTRIBUTE));

if (atts == NULL) {

FREE(parser);

return NULL;

}

dataBuf = (XML_Char *)MALLOC(INIT_DATA_BUF_SIZE * sizeof(XML_Char));

if (dataBuf == NULL) {

FREE(atts);

FREE(parser);

return NULL;

}

dataBufEnd = dataBuf + INIT_DATA_BUF_SIZE;

if (dtd)

_dtd = dtd;

else {

_dtd = dtdCreate(&parser->m_mem);

if (_dtd == NULL) {

FREE(dataBuf);

FREE(atts);

FREE(parser);

return NULL;

}

freeBindingList = NULL;

freeTagList = NULL;

freeInternalEntities = NULL;

groupSize = 0;

groupConnector = NULL;

unknownEncodingHandler = NULL;

unknownEncodingHandlerData = NULL;

namespaceSeparator = '!';

ns = XML_FALSE;

ns_triplets = XML_FALSE;

nsAtts = NULL;

nsAttsVersion = 0;

nsAttsPower = 0;

poolInit(&tempPool, &(parser->m_mem));

poolInit(&temp2Pool, &(parser->m_mem));

parserInit(parser, encodingName);

if (encodingName && !protocolEncodingName) {

XML_ParserFree(parser);

return NULL;

}

if (nameSep) {

ns = XML_TRUE;

internalEncoding = XmlGetInternalEncodingNS();

namespaceSeparator = *nameSep;

}

else {

internalEncoding = XmlGetInternalEncoding();

}

return parser;

}

static void

parserInit(XML_Parser parser, const XML_Char *encodingName)

{

processor = prologInitProcessor;

XmlPrologStateInit(&prologState);

protocolEncodingName = (encodingName != NULL

? poolCopyString(&tempPool, encodingName)

: NULL);

curBase = NULL;

XmlInitEncoding(&initEncoding, &encoding, 0);

userData = NULL;

handlerArg = NULL;

startElementHandler = NULL;

endElementHandler = NULL;

characterDataHandler = NULL;

processingInstructionHandler = NULL;

commentHandler = NULL;

startCdataSectionHandler = NULL;

endCdataSectionHandler = NULL;

defaultHandler = NULL;

startDoctypeDeclHandler = NULL;

endDoctypeDeclHandler = NULL;

unparsedEntityDeclHandler = NULL;

notationDeclHandler = NULL;

startNamespaceDeclHandler = NULL;

endNamespaceDeclHandler = NULL;

notStandaloneHandler = NULL;

externalEntityRefHandler = NULL;

externalEntityRefHandlerArg = parser;

skippedEntityHandler = NULL;

elementDeclHandler = NULL;

attlistDeclHandler = NULL;

entityDeclHandler = NULL;

xmlDeclHandler = NULL;

bufferPtr = buffer;

bufferEnd = buffer;

parseEndByteIndex = 0;

parseEndPtr = NULL;

declElementType = NULL;

declAttributeId = NULL;

declEntity = NULL;

doctypeName = NULL;

doctypeSysid = NULL;

doctypePubid = NULL;

declAttributeType = NULL;

declNotationName = NULL;

declNotationPublicId = NULL;

declAttributeIsCdata = XML_FALSE;

declAttributeIsId = XML_FALSE;

memset(&position, 0, sizeof(POSITION));

errorCode = XML_ERROR_NONE;

eventPtr = NULL;

eventEndPtr = NULL;

positionPtr = NULL;

openInternalEntities = NULL;

defaultExpandInternalEntities = XML_TRUE;

tagLevel = 0;

tagStack = NULL;

inheritedBindings = NULL;

nSpecifiedAtts = 0;

unknownEncodingMem = NULL;

unknownEncodingRelease = NULL;

unknownEncodingData = NULL;

parentParser = NULL;

ps_parsing = XML_INITIALIZED;

#ifdef XML_DTD

isParamEntity = XML_FALSE;

useForeignDTD = XML_FALSE;

paramEntityParsing = XML_PARAM_ENTITY_PARSING_NEVER;

#endif

}

/* moves list of bindings to freeBindingList */

static void FASTCALL

moveToFreeBindingList(XML_Parser parser, BINDING *bindings)

{

while (bindings) {

BINDING *b = bindings;

bindings = bindings->nextTagBinding;

b->nextTagBinding = freeBindingList;

freeBindingList = b;

}

XML_Bool XMLCALL

XML_ParserReset(XML_Parser parser, const XML_Char *encodingName)

{

TAG *tStk;

OPEN_INTERNAL_ENTITY *openEntityList;

if (parentParser)

return XML_FALSE;

/* move tagStack to freeTagList */

tStk = tagStack;

while (tStk) {

TAG *tag = tStk;

tStk = tStk->parent;

tag->parent = freeTagList;

moveToFreeBindingList(parser, tag->bindings);

tag->bindings = NULL;

freeTagList = tag;

}

/* move openInternalEntities to freeInternalEntities */

openEntityList = openInternalEntities;

while (openEntityList) {

OPEN_INTERNAL_ENTITY *openEntity = openEntityList;

openEntityList = openEntity->next;

openEntity->next = freeInternalEntities;

freeInternalEntities = openEntity;

}

moveToFreeBindingList(parser, inheritedBindings);

FREE(unknownEncodingMem);

if (unknownEncodingRelease)

unknownEncodingRelease(unknownEncodingData);

poolClear(&tempPool);

poolClear(&temp2Pool);

parserInit(parser, encodingName);

dtdReset(_dtd, &parser->m_mem);

return setContext(parser, implicitContext);

}

enum XML_Status XMLCALL

XML_SetEncoding(XML_Parser parser, const XML_Char *encodingName)

{

/* Block after XML_Parse()/XML_ParseBuffer() has been called.

XXX There's no way for the caller to determine which of the

XXX possible error cases caused the XML_STATUS_ERROR return.

if (ps_parsing == XML_PARSING || ps_parsing == XML_SUSPENDED)

return XML_STATUS_ERROR;

if (encodingName == NULL)

protocolEncodingName = NULL;

else {

protocolEncodingName = poolCopyString(&tempPool, encodingName);

if (!protocolEncodingName)

return XML_STATUS_ERROR;

}

return XML_STATUS_OK;

}

XML_Parser XMLCALL

XML_ExternalEntityParserCreate(XML_Parser oldParser,

const XML_Char *context,

const XML_Char *encodingName)

{

XML_Parser parser = oldParser;

DTD *newDtd = NULL;

DTD *oldDtd = _dtd;

XML_StartElementHandler oldStartElementHandler = startElementHandler;

XML_EndElementHandler oldEndElementHandler = endElementHandler;

XML_CharacterDataHandler oldCharacterDataHandler = characterDataHandler;

XML_ProcessingInstructionHandler oldProcessingInstructionHandler

= processingInstructionHandler;

XML_CommentHandler oldCommentHandler = commentHandler;

XML_StartCdataSectionHandler oldStartCdataSectionHandler

= startCdataSectionHandler;

XML_EndCdataSectionHandler oldEndCdataSectionHandler

= endCdataSectionHandler;

XML_DefaultHandler oldDefaultHandler = defaultHandler;

XML_UnparsedEntityDeclHandler oldUnparsedEntityDeclHandler

= unparsedEntityDeclHandler;

XML_NotationDeclHandler oldNotationDeclHandler = notationDeclHandler;

XML_StartNamespaceDeclHandler oldStartNamespaceDeclHandler

= startNamespaceDeclHandler;

XML_EndNamespaceDeclHandler oldEndNamespaceDeclHandler

= endNamespaceDeclHandler;

XML_NotStandaloneHandler oldNotStandaloneHandler = notStandaloneHandler;

XML_ExternalEntityRefHandler oldExternalEntityRefHandler

= externalEntityRefHandler;

XML_SkippedEntityHandler oldSkippedEntityHandler = skippedEntityHandler;

XML_UnknownEncodingHandler oldUnknownEncodingHandler

= unknownEncodingHandler;

XML_ElementDeclHandler oldElementDeclHandler = elementDeclHandler;

XML_AttlistDeclHandler oldAttlistDeclHandler = attlistDeclHandler;

XML_EntityDeclHandler oldEntityDeclHandler = entityDeclHandler;

XML_XmlDeclHandler oldXmlDeclHandler = xmlDeclHandler;

ELEMENT_TYPE * oldDeclElementType = declElementType;

void *oldUserData = userData;

void *oldHandlerArg = handlerArg;

XML_Bool oldDefaultExpandInternalEntities = defaultExpandInternalEntities;

XML_Parser oldExternalEntityRefHandlerArg = externalEntityRefHandlerArg;

#ifdef XML_DTD

enum XML_ParamEntityParsing oldParamEntityParsing = paramEntityParsing;

int oldInEntityValue = prologState.inEntityValue;

#endif

XML_Bool oldns_triplets = ns_triplets;

#ifdef XML_DTD

if (!context)

newDtd = oldDtd;

#endif /* XML_DTD */

/* Note that the magical uses of the pre-processor to make field

access look more like C++ require that `parser' be overwritten

here. This makes this function more painful to follow than it

would be otherwise.

if (ns) {

XML_Char tmp[2];

*tmp = namespaceSeparator;

parser = parserCreate(encodingName, &parser->m_mem, tmp, newDtd);

}

else {

parser = parserCreate(encodingName, &parser->m_mem, NULL, newDtd);

}

if (!parser)

return NULL;

View remainder of file in raw view

python/Modules/expat/xmlparse.c at master · charleson/python · GitHub

Navigation Menu

Expand file tree

Breadcrumbs

xmlparse.c

Latest commit

History

Breadcrumbs

xmlparse.c

File metadata and controls

Footer

Footer navigation