cpython/Modules/_elementtree.c at main · python/cpython · GitHub

History

4694 lines (3957 loc) · 132 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

/*--------------------------------------------------------------------

* Licensed to PSF under a Contributor Agreement.

* See https://www.python.org/psf/license for licensing details.

* _elementtree - C accelerator for xml.etree.ElementTree

* info@pythonware.com

* http://www.pythonware.com

*--------------------------------------------------------------------

#ifndef Py_BUILD_CORE_BUILTIN

# define Py_BUILD_CORE_MODULE 1

#endif

#include "Python.h"

#include "pycore_ceval.h" // _Py_EnterRecursiveCall()

#include "pycore_dict.h" // _PyDict_CopyAsDict()

#include "pycore_pyhash.h" // _Py_HashSecret

#include "pycore_tuple.h" // _PyTuple_FromPair

#include "pycore_weakref.h" // FT_CLEAR_WEAKREFS()

#include <stddef.h> // offsetof()

#include "expat.h"

#include "pyexpat.h"

/* -------------------------------------------------------------------- */

/* configuration */

/* An element can hold this many children without extra memory

allocations. */

#define STATIC_CHILDREN 4

/* For best performance, chose a value so that 80-90% of all nodes

have no more than the given number of children. Set this to zero

to minimize the size of the element structure itself (this only

helps if you have lots of leaf nodes with attributes). */

/* Also note that pymalloc always allocates blocks in multiples of

eight bytes. For the current C version of ElementTree, this means

that the number of children should be an even number, at least on

32-bit platforms. */

/* -------------------------------------------------------------------- */

/* compiler tweaks */

#if defined(_MSC_VER)

#define LOCAL(type) static __inline type __fastcall

#else

#define LOCAL(type) static type

#endif

/* macros used to store 'join' flags in string object pointers. note

that all use of text and tail as object pointers must be wrapped in

JOIN_OBJ. see comments in the ElementObject definition for more

info. */

#define JOIN_GET(p) ((uintptr_t) (p) & 1)

#define JOIN_SET(p, flag) ((void*) ((uintptr_t) (JOIN_OBJ(p)) | (flag)))

#define JOIN_OBJ(p) ((PyObject*) ((uintptr_t) (p) & ~(uintptr_t)1))

/* Py_SETREF for a PyObject* that uses a join flag. */

Py_LOCAL_INLINE(void)

_set_joined_ptr(PyObject **p, PyObject *new_joined_ptr)

{

PyObject *tmp = JOIN_OBJ(*p);

*p = new_joined_ptr;

Py_DECREF(tmp);

}

/* Py_CLEAR for a PyObject* that uses a join flag. Pass the pointer by

* reference since this function sets it to NULL.

static void _clear_joined_ptr(PyObject **p)

{

if (*p) {

_set_joined_ptr(p, NULL);

}

/* Per-module state; PEP 3121 */

typedef struct {

PyObject *parseerror_obj;

PyObject *deepcopy_obj;

PyObject *elementpath_obj;

PyObject *comment_factory;

PyObject *pi_factory;

/* Interned strings */

PyObject *str_text;

PyObject *str_tail;

PyObject *str_append;

PyObject *str_find;

PyObject *str_findtext;

PyObject *str_findall;

PyObject *str_iterfind;

PyObject *str_doctype;

/* Types defined by this extension */

PyTypeObject *Element_Type;

PyTypeObject *ElementIter_Type;

PyTypeObject *TreeBuilder_Type;

PyTypeObject *XMLParser_Type;

PyObject *expat_capsule;

struct PyExpat_CAPI *expat_capi;

} elementtreestate;

static struct PyModuleDef elementtreemodule;

/* Given a module object (assumed to be _elementtree), get its per-module

* state.

static inline elementtreestate*

get_elementtree_state(PyObject *module)

{

void *state = PyModule_GetState(module);

assert(state != NULL);

return (elementtreestate *)state;

}

static inline elementtreestate *

get_elementtree_state_by_cls(PyTypeObject *cls)

{

void *state = PyType_GetModuleState(cls);

assert(state != NULL);

return (elementtreestate *)state;

}

static inline elementtreestate *

get_elementtree_state_by_type(PyTypeObject *tp)

{

PyObject *mod = PyType_GetModuleByDef(tp, &elementtreemodule);

assert(mod != NULL);

return get_elementtree_state(mod);

}

static int

elementtree_clear(PyObject *m)

{

elementtreestate *st = get_elementtree_state(m);

Py_CLEAR(st->parseerror_obj);

Py_CLEAR(st->deepcopy_obj);

Py_CLEAR(st->elementpath_obj);

Py_CLEAR(st->comment_factory);

Py_CLEAR(st->pi_factory);

// Interned strings

Py_CLEAR(st->str_append);

Py_CLEAR(st->str_find);

Py_CLEAR(st->str_findall);

Py_CLEAR(st->str_findtext);

Py_CLEAR(st->str_iterfind);

Py_CLEAR(st->str_tail);

Py_CLEAR(st->str_text);

Py_CLEAR(st->str_doctype);

// Heap types

Py_CLEAR(st->Element_Type);

Py_CLEAR(st->ElementIter_Type);

Py_CLEAR(st->TreeBuilder_Type);

Py_CLEAR(st->XMLParser_Type);

Py_CLEAR(st->expat_capsule);

st->expat_capi = NULL;

return 0;

}

static int

elementtree_traverse(PyObject *m, visitproc visit, void *arg)

{

elementtreestate *st = get_elementtree_state(m);

Py_VISIT(st->parseerror_obj);

Py_VISIT(st->deepcopy_obj);

Py_VISIT(st->elementpath_obj);

Py_VISIT(st->comment_factory);

Py_VISIT(st->pi_factory);

// Heap types

Py_VISIT(st->Element_Type);

Py_VISIT(st->ElementIter_Type);

Py_VISIT(st->TreeBuilder_Type);

Py_VISIT(st->XMLParser_Type);

Py_VISIT(st->expat_capsule);

return 0;

}

static void

elementtree_free(void *m)

{

(void)elementtree_clear((PyObject *)m);

}

/* helpers */

LOCAL(PyObject*)

list_join(PyObject* list)

{

/* join list elements */

PyObject* joiner;

PyObject* result;

joiner = Py_GetConstant(Py_CONSTANT_EMPTY_STR);

if (!joiner)

return NULL;

result = PyUnicode_Join(joiner, list);

Py_DECREF(joiner);

return result;

}

/* Is the given object an empty dictionary?

static int

is_empty_dict(PyObject *obj)

{

return PyDict_CheckExact(obj) && PyDict_GET_SIZE(obj) == 0;

}

/* -------------------------------------------------------------------- */

/* the Element type */

typedef struct {

/* attributes (a dictionary object), or NULL if no attributes */

PyObject* attrib;

/* child elements */

Py_ssize_t length; /* actual number of items */

Py_ssize_t allocated; /* allocated items */

/* this either points to _children or to a malloced buffer */

PyObject* *children;

PyObject* _children[STATIC_CHILDREN];

} ElementObjectExtra;

typedef struct {

PyObject_HEAD

/* element tag (a string). */

PyObject* tag;

/* text before first child. note that this is a tagged pointer;

use JOIN_OBJ to get the object pointer. the join flag is used

to distinguish lists created by the tree builder from lists

assigned to the attribute by application code; the former

should be joined before being returned to the user, the latter

should be left intact. */

PyObject* text;

/* text after this element, in parent. note that this is a tagged

pointer; use JOIN_OBJ to get the object pointer. */

PyObject* tail;

ElementObjectExtra* extra;

PyObject *weakreflist; /* For tp_weaklistoffset */

} ElementObject;

#define _Element_CAST(op) ((ElementObject *)(op))

#define Element_CheckExact(st, op) Py_IS_TYPE(op, (st)->Element_Type)

#define Element_Check(st, op) PyObject_TypeCheck(op, (st)->Element_Type)

/* -------------------------------------------------------------------- */

/* Element constructors and destructor */

LOCAL(int)

create_extra(ElementObject* self, PyObject* attrib)

{

self->extra = PyMem_Malloc(sizeof(ElementObjectExtra));

if (!self->extra) {

PyErr_NoMemory();

return -1;

}

self->extra->attrib = Py_XNewRef(attrib);

self->extra->length = 0;

self->extra->allocated = STATIC_CHILDREN;

self->extra->children = self->extra->_children;

return 0;

}

LOCAL(void)

dealloc_extra(ElementObjectExtra *extra)

{

Py_ssize_t i;

if (!extra)

return;

Py_XDECREF(extra->attrib);

for (i = 0; i < extra->length; i++)

Py_DECREF(extra->children[i]);

if (extra->children != extra->_children) {

PyMem_Free(extra->children);

}

PyMem_Free(extra);

}

LOCAL(void)

clear_extra(ElementObject* self)

{

ElementObjectExtra *myextra;

if (!self->extra)

return;

/* Avoid DECREFs calling into this code again (cycles, etc.)

myextra = self->extra;

self->extra = NULL;

dealloc_extra(myextra);

}

/* Convenience internal function to create new Element objects with the given

* tag and attributes.

LOCAL(PyObject*)

create_new_element(elementtreestate *st, PyObject *tag, PyObject *attrib)

{

ElementObject* self;

self = PyObject_GC_New(ElementObject, st->Element_Type);

if (self == NULL)

return NULL;

self->extra = NULL;

self->tag = Py_NewRef(tag);

self->text = Py_NewRef(Py_None);

self->tail = Py_NewRef(Py_None);

self->weakreflist = NULL;

PyObject_GC_Track(self);

if (attrib != NULL && !is_empty_dict(attrib)) {

if (create_extra(self, attrib) < 0) {

Py_DECREF(self);

return NULL;

}

return (PyObject*) self;

}

static PyObject *

element_new(PyTypeObject *type, PyObject *args, PyObject *kwds)

{

ElementObject *e = (ElementObject *)type->tp_alloc(type, 0);

if (e != NULL) {

e->tag = Py_NewRef(Py_None);

e->text = Py_NewRef(Py_None);

e->tail = Py_NewRef(Py_None);

e->extra = NULL;

e->weakreflist = NULL;

}

return (PyObject *)e;

}

/* Helper function for extracting the attrib dictionary from a keywords dict.

* This is required by some constructors/functions in this module that can

* either accept attrib as a keyword argument or all attributes splashed

* directly into *kwds.

* Return a dictionary with the content of kwds merged into the content of

* attrib. If there is no attrib keyword, return a copy of kwds.

static PyObject*

get_attrib_from_keywords(PyObject *kwds)

{

PyObject *attrib;

if (PyDict_PopString(kwds, "attrib", &attrib) < 0) {

return NULL;

}

if (attrib) {

/* If attrib was found in kwds, copy its value and remove it from

* kwds

if (!PyAnyDict_Check(attrib)) {

PyErr_Format(PyExc_TypeError,

"attrib must be dict or frozendict, not %T",

attrib);

Py_DECREF(attrib);

return NULL;

}

Py_SETREF(attrib, _PyDict_CopyAsDict(attrib));

}

else {

attrib = PyDict_New();

}

if (attrib != NULL && PyDict_Update(attrib, kwds) < 0) {

Py_DECREF(attrib);

return NULL;

}

return attrib;

}

/*[clinic input]

module _elementtree

class _elementtree.Element "ElementObject *" "clinic_state()->Element_Type"

class _elementtree.TreeBuilder "TreeBuilderObject *" "clinic_state()->TreeBuilder_Type"

class _elementtree.XMLParser "XMLParserObject *" "clinic_state()->XMLParser_Type"

[clinic start generated code]*/

/*[clinic end generated code: output=da39a3ee5e6b4b0d input=6c83ea832d2b0ef1]*/

static int

element_init(PyObject *self, PyObject *args, PyObject *kwds)

{

PyObject *tag;

PyObject *attrib = NULL;

ElementObject *self_elem;

if (!PyArg_ParseTuple(args, "O|O:Element", &tag, &attrib))

return -1;

if (attrib != NULL && !PyAnyDict_Check(attrib)) {

PyErr_Format(PyExc_TypeError,

"Element() argument 2 must be dict or frozendict, not %T",

attrib);

return -1;

}

if (attrib) {

/* attrib passed as positional arg */

attrib = _PyDict_CopyAsDict(attrib);

if (!attrib)

return -1;

if (kwds) {

if (PyDict_Update(attrib, kwds) < 0) {

Py_DECREF(attrib);

return -1;

}

} else if (kwds) {

/* have keywords args */

attrib = get_attrib_from_keywords(kwds);

if (!attrib)

return -1;

}

self_elem = (ElementObject *)self;

if (attrib != NULL && !is_empty_dict(attrib)) {

if (create_extra(self_elem, attrib) < 0) {

Py_DECREF(attrib);

return -1;

}

/* We own a reference to attrib here and it's no longer needed. */

Py_XDECREF(attrib);

/* Replace the objects already pointed to by tag, text and tail. */

Py_XSETREF(self_elem->tag, Py_NewRef(tag));

_set_joined_ptr(&self_elem->text, Py_NewRef(Py_None));

_set_joined_ptr(&self_elem->tail, Py_NewRef(Py_None));

return 0;

}

LOCAL(int)

element_resize(ElementObject* self, Py_ssize_t extra)

{

Py_ssize_t size;

PyObject* *children;

assert(extra >= 0);

/* make sure self->children can hold the given number of extra

elements. set an exception and return -1 if allocation failed */

if (!self->extra) {

if (create_extra(self, NULL) < 0)

return -1;

}

size = self->extra->length + extra; /* never overflows */

if (size > self->extra->allocated) {

/* use Python 2.4's list growth strategy */

size = (size >> 3) + (size < 9 ? 3 : 6) + size;

/* Coverity CID #182 size_error: Allocating 1 bytes to pointer "children"

* which needs at least 4 bytes.

* Although it's a false alarm always assume at least one child to

* be safe.

size = size ? size : 1;

if ((size_t)size > PY_SSIZE_T_MAX/sizeof(PyObject*))

goto nomemory;

if (self->extra->children != self->extra->_children) {

/* Coverity CID #182 size_error: Allocating 1 bytes to pointer

* "children", which needs at least 4 bytes. Although it's a

* false alarm always assume at least one child to be safe.

children = PyMem_Realloc(self->extra->children,

size * sizeof(PyObject*));

if (!children) {

goto nomemory;

}

} else {

children = PyMem_Malloc(size * sizeof(PyObject*));

if (!children) {

goto nomemory;

}

/* copy existing children from static area to malloc buffer */

memcpy(children, self->extra->children,

self->extra->length * sizeof(PyObject*));

}

self->extra->children = children;

self->extra->allocated = size;

}

return 0;

nomemory:

PyErr_NoMemory();

return -1;

}

LOCAL(void)

raise_type_error(PyObject *element)

{

PyErr_Format(PyExc_TypeError,

"expected an Element, not \"%.200s\"",

Py_TYPE(element)->tp_name);

}

LOCAL(int)

element_add_subelement(elementtreestate *st, ElementObject *self,

PyObject *element)

{

/* add a child element to a parent */

if (!Element_Check(st, element)) {

raise_type_error(element);

return -1;

}

if (element_resize(self, 1) < 0)

return -1;

self->extra->children[self->extra->length] = Py_NewRef(element);

self->extra->length++;

return 0;

}

LOCAL(PyObject*)

element_get_attrib(ElementObject* self)

{

/* return borrowed reference to attrib dictionary */

/* note: this function assumes that the extra section exists */

PyObject* res = self->extra->attrib;

if (!res) {

/* create missing dictionary */

res = self->extra->attrib = PyDict_New();

}

return res;

}

LOCAL(PyObject*)

element_get_text(ElementObject* self)

{

/* return new reference to text attribute */

PyObject *res = self->text;

if (JOIN_GET(res)) {

res = JOIN_OBJ(res);

if (PyList_CheckExact(res)) {

PyObject *tmp = list_join(res);

if (!tmp)

return NULL;

self->text = tmp;

Py_SETREF(res, tmp);

}

return Py_NewRef(res);

}

LOCAL(PyObject*)

element_get_tail(ElementObject* self)

{

/* return new reference to tail attribute */

PyObject *res = self->tail;

if (JOIN_GET(res)) {

res = JOIN_OBJ(res);

if (PyList_CheckExact(res)) {

PyObject *tmp = list_join(res);

if (!tmp)

return NULL;

self->tail = tmp;

Py_SETREF(res, tmp);

}

return Py_NewRef(res);

}

/*[clinic input]

_elementtree.SubElement

parent: object(subclass_of='get_elementtree_state(module)->Element_Type')

tag: object

attrib: object(subclass_of='&PyDict_Type', c_default='NULL') = {}

**extra: dict

Create a new subelement of the parent element.

[clinic start generated code]*/

static PyObject *

_elementtree_SubElement_impl(PyObject *module, PyObject *parent,

PyObject *tag, PyObject *attrib,

PyObject *extra)

/*[clinic end generated code: output=42e8a4ebc5db08aa input=8588fc68283cdaa0]*/

{

PyObject* elem;

elementtreestate *st = get_elementtree_state(module);

ElementObject* parent_elem = (ElementObject *)parent;

if (attrib) {

/* attrib passed as positional arg */

attrib = PyDict_Copy(attrib);

if (!attrib)

return NULL;

if (PyDict_Update(attrib, extra) < 0) {

Py_DECREF(attrib);

return NULL;

}

} else if (PyDict_GET_SIZE(extra)) {

/* have keyword args */

attrib = get_attrib_from_keywords(extra);

if (!attrib)

return NULL;

} else {

/* no attrib arg, no kwds, so no attribute */

}

elem = create_new_element(st, tag, attrib);

Py_XDECREF(attrib);

if (elem == NULL)

return NULL;

if (element_add_subelement(st, parent_elem, elem) < 0) {

Py_DECREF(elem);

return NULL;

}

return elem;

}

static int

element_gc_traverse(PyObject *op, visitproc visit, void *arg)

{

ElementObject *self = _Element_CAST(op);

Py_VISIT(Py_TYPE(self));

Py_VISIT(self->tag);

Py_VISIT(JOIN_OBJ(self->text));

Py_VISIT(JOIN_OBJ(self->tail));

if (self->extra) {

Py_ssize_t i;

Py_VISIT(self->extra->attrib);

for (i = 0; i < self->extra->length; ++i)

Py_VISIT(self->extra->children[i]);

}

return 0;

}

static int

element_gc_clear(PyObject *op)

{

ElementObject *self = _Element_CAST(op);

Py_CLEAR(self->tag);

_clear_joined_ptr(&self->text);

_clear_joined_ptr(&self->tail);

/* After dropping all references from extra, it's no longer valid anyway,

* so fully deallocate it.

clear_extra(self);

return 0;

}

static void

element_dealloc(PyObject *op)

{

ElementObject *self = _Element_CAST(op);

PyTypeObject *tp = Py_TYPE(self);

/* bpo-31095: UnTrack is needed before calling any callbacks */

PyObject_GC_UnTrack(self);

FT_CLEAR_WEAKREFS(op, self->weakreflist);

/* element_gc_clear clears all references and deallocates extra

(void)element_gc_clear(op);

tp->tp_free(self);

Py_DECREF(tp);

}

/* -------------------------------------------------------------------- */

/*[clinic input]

_elementtree.Element.append

cls: defining_class

subelement: object(subclass_of='clinic_state()->Element_Type')

Add *subelement* to the end of this element.

The new element will appear in document order after the last

existing subelement (or directly after the text, if it's the first

subelement), but before the end tag for this element.

[clinic start generated code]*/

static PyObject *

_elementtree_Element_append_impl(ElementObject *self, PyTypeObject *cls,

PyObject *subelement)

/*[clinic end generated code: output=d00923711ea317fc input=a59ebce98937a372]*/

{

elementtreestate *st = get_elementtree_state_by_cls(cls);

if (element_add_subelement(st, self, subelement) < 0)

return NULL;

Py_RETURN_NONE;

}

/*[clinic input]

_elementtree.Element.clear

Reset element.

This function removes all subelements, clears all attributes, and

sets the text and tail attributes to None.

[clinic start generated code]*/

static PyObject *

_elementtree_Element_clear_impl(ElementObject *self)

/*[clinic end generated code: output=8bcd7a51f94cfff6 input=135c2ab634d0fdf5]*/

{

clear_extra(self);

_set_joined_ptr(&self->text, Py_NewRef(Py_None));

_set_joined_ptr(&self->tail, Py_NewRef(Py_None));

Py_RETURN_NONE;

}

/*[clinic input]

_elementtree.Element.__copy__

cls: defining_class

[clinic start generated code]*/

static PyObject *

_elementtree_Element___copy___impl(ElementObject *self, PyTypeObject *cls)

/*[clinic end generated code: output=da22894421ff2b36 input=91edb92d9f441213]*/

{

Py_ssize_t i;

ElementObject* element;

elementtreestate *st = get_elementtree_state_by_cls(cls);

element = (ElementObject*) create_new_element(

st, self->tag, self->extra ? self->extra->attrib : NULL);

if (!element)

return NULL;

Py_INCREF(JOIN_OBJ(self->text));

_set_joined_ptr(&element->text, self->text);

Py_INCREF(JOIN_OBJ(self->tail));

_set_joined_ptr(&element->tail, self->tail);

assert(!element->extra || !element->extra->length);

if (self->extra) {

if (element_resize(element, self->extra->length) < 0) {

Py_DECREF(element);

return NULL;

}

for (i = 0; i < self->extra->length; i++) {

element->extra->children[i] = Py_NewRef(self->extra->children[i]);

}

assert(!element->extra->length);

element->extra->length = self->extra->length;

}

return (PyObject*) element;

}

/* Helper for a deep copy. */

LOCAL(PyObject *) deepcopy(elementtreestate *, PyObject *, PyObject *);

/*[clinic input]

_elementtree.Element.__deepcopy__

memo: object(subclass_of="&PyDict_Type")

[clinic start generated code]*/

static PyObject *

_elementtree_Element___deepcopy___impl(ElementObject *self, PyObject *memo)

/*[clinic end generated code: output=eefc3df50465b642 input=a2d40348c0aade10]*/

{

Py_ssize_t i;

ElementObject* element = NULL;

PyObject* tag;

PyObject* attrib;

PyObject* text;

PyObject* tail;

PyObject* id;

if (_Py_EnterRecursiveCall(" in Element.__deepcopy__")) {

return NULL;

}

PyTypeObject *tp = Py_TYPE(self);

elementtreestate *st = get_elementtree_state_by_type(tp);

// The deepcopy() helper takes care of incrementing the refcount

// of the object to copy so to avoid use-after-frees.

tag = deepcopy(st, self->tag, memo);

if (!tag) {

goto error;

}

if (self->extra && self->extra->attrib) {

attrib = deepcopy(st, self->extra->attrib, memo);

if (!attrib) {

Py_DECREF(tag);

goto error;

}

} else {

attrib = NULL;

}

element = (ElementObject*) create_new_element(st, tag, attrib);

Py_DECREF(tag);

Py_XDECREF(attrib);

if (!element) {

goto error;

}

text = deepcopy(st, JOIN_OBJ(self->text), memo);

if (!text)

goto error;

_set_joined_ptr(&element->text, JOIN_SET(text, JOIN_GET(self->text)));

tail = deepcopy(st, JOIN_OBJ(self->tail), memo);

if (!tail)

goto error;

_set_joined_ptr(&element->tail, JOIN_SET(tail, JOIN_GET(self->tail)));

assert(!element->extra || !element->extra->length);

if (self->extra) {

Py_ssize_t expected_count = self->extra->length;

if (element_resize(element, expected_count) < 0) {

assert(!element->extra->length);

goto error;

}

for (i = 0; self->extra && i < self->extra->length; i++) {

PyObject* child = deepcopy(st, self->extra->children[i], memo);

if (!child || !Element_Check(st, child)) {

if (child) {

raise_type_error(child);

Py_DECREF(child);

}

element->extra->length = i;

goto error;

}

if (self->extra && expected_count != self->extra->length) {

// 'self->extra' got mutated and 'element' may not have

// sufficient space to hold the next iteration's item.

expected_count = self->extra->length;

if (element_resize(element, expected_count) < 0) {

Py_DECREF(child);

element->extra->length = i;

goto error;

}

element->extra->children[i] = child;

}

assert(!element->extra->length);

// The original 'self->extra' may be gone at this point if deepcopy()

// has side-effects. However, 'i' is the number of copied items that

// we were able to successfully copy.

element->extra->length = i;

}

/* add object to memo dictionary (so deepcopy won't visit it again) */

id = PyLong_FromSsize_t((uintptr_t) self);

if (!id)

goto error;

i = PyDict_SetItem(memo, id, (PyObject*) element);

Py_DECREF(id);

if (i < 0)

goto error;

_Py_LeaveRecursiveCall();

return (PyObject*) element;

error:

_Py_LeaveRecursiveCall();

Py_XDECREF(element);

return NULL;

}

LOCAL(PyObject *)

deepcopy(elementtreestate *st, PyObject *object, PyObject *memo)

{

/* do a deep copy of the given object */

/* Fast paths */

if (object == Py_None || PyUnicode_CheckExact(object)) {

return Py_NewRef(object);

}

if (_PyObject_IsUniquelyReferenced(object)) {

if (PyDict_CheckExact(object)) {

PyObject *key, *value;

Py_ssize_t pos = 0;

int simple = 1;

while (PyDict_Next(object, &pos, &key, &value)) {

if (!PyUnicode_CheckExact(key) || !PyUnicode_CheckExact(value)) {

simple = 0;

break;

}

if (simple) {

return PyDict_Copy(object);

}

/* Fall through to general case */

}

else if (Element_CheckExact(st, object)) {

// The __deepcopy__() call may call arbitrary code even if the

// object to copy is a built-in XML element (one of its children

// any of its parents in its own __deepcopy__() implementation).

Py_INCREF(object);

PyObject *res = _elementtree_Element___deepcopy___impl(

(ElementObject *)object, memo);

Py_DECREF(object);

return res;

}

/* General case */

if (!st->deepcopy_obj) {

PyErr_SetString(PyExc_RuntimeError,

"deepcopy helper not found");

return NULL;

}

Py_INCREF(object);

PyObject *args[2] = {object, memo};

PyObject *res = PyObject_Vectorcall(st->deepcopy_obj, args, 2, NULL);

Py_DECREF(object);

return res;

}

/*[clinic input]

_elementtree.Element.__sizeof__ -> size_t

[clinic start generated code]*/

static size_t

_elementtree_Element___sizeof___impl(ElementObject *self)

/*[clinic end generated code: output=baae4e7ae9fe04ec input=54e298c501f3e0d0]*/

View remainder of file in raw view

cpython/Modules/_elementtree.c at main · python/cpython · GitHub

Uh oh!

Expand file tree

Breadcrumbs

_elementtree.c

Latest commit

History

Breadcrumbs

_elementtree.c

File metadata and controls