cpython/Objects/unicodeobject.c at 2.7 · 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

Unicode implementation based on original code by Fredrik Lundh,

modified by Marc-Andre Lemburg <mal@lemburg.com> according to the

Unicode Integration Proposal (see file Misc/unicode.txt).

Major speed upgrades to the method implementations at the Reykjavik

NeedForSpeed sprint, by Fredrik Lundh and Andrew Dalke.

--------------------------------------------------------------------

The original string type implementation is:

By obtaining, using, and/or copying this software and/or its

associated documentation, you agree that you have read, understood,

and will comply with the following terms and conditions:

Permission to use, copy, modify, and distribute this software and its

associated documentation for any purpose and without fee is hereby

granted, provided that the above copyright notice appears in all

copies, and that both that copyright notice and this permission notice

appear in supporting documentation, and that the name of Secret Labs

AB or the author not be used in advertising or publicity pertaining to

distribution of the software without specific, written prior

permission.

SECRET LABS AB AND THE AUTHOR DISCLAIMS ALL WARRANTIES WITH REGARD TO

THIS SOFTWARE, INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND

FITNESS. IN NO EVENT SHALL SECRET LABS AB OR THE AUTHOR BE LIABLE FOR

ANY SPECIAL, INDIRECT OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES

WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN

ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT

OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.

--------------------------------------------------------------------

#define PY_SSIZE_T_CLEAN

#include "Python.h"

#include "unicodeobject.h"

#include "ucnhash.h"

#ifdef MS_WINDOWS

#include <windows.h>

#endif

/* Limit for the Unicode object free list */

#define PyUnicode_MAXFREELIST 1024

/* Limit for the Unicode object free list stay alive optimization.

The implementation will keep allocated Unicode memory intact for

all objects on the free list having a size less than this

limit. This reduces malloc() overhead for small Unicode objects.

At worst this will result in PyUnicode_MAXFREELIST *

(sizeof(PyUnicodeObject) + KEEPALIVE_SIZE_LIMIT +

malloc()-overhead) bytes of unused garbage.

Setting the limit to 0 effectively turns the feature off.

Note: This is an experimental feature ! If you get core dumps when

using Unicode objects, turn this feature off.

#define KEEPALIVE_SIZE_LIMIT 9

/* Endianness switches; defaults to little endian */

#ifdef WORDS_BIGENDIAN

# define BYTEORDER_IS_BIG_ENDIAN

#else

# define BYTEORDER_IS_LITTLE_ENDIAN

#endif

/* --- Globals ------------------------------------------------------------

NOTE: In the interpreter's initialization phase, some globals are currently

initialized dynamically as needed. In the process Unicode objects may

be created before the Unicode type is ready.

#ifdef __cplusplus

extern "C" {

#endif

/* Free list for Unicode objects */

static PyUnicodeObject *free_list = NULL;

static int numfree = 0;

/* The empty Unicode object is shared to improve performance. */

static PyUnicodeObject *unicode_empty = NULL;

#define _Py_RETURN_UNICODE_EMPTY() \

do { \

if (unicode_empty != NULL) \

Py_INCREF(unicode_empty); \

else { \

unicode_empty = _PyUnicode_New(0); \

if (unicode_empty != NULL) \

Py_INCREF(unicode_empty); \

} \

return (PyObject *)unicode_empty; \

} while (0)

/* Single character Unicode strings in the Latin-1 range are being

shared as well. */

static PyUnicodeObject *unicode_latin1[256] = {NULL};

/* Default encoding to use and assume when NULL is passed as encoding

parameter; it is initialized by _PyUnicode_Init().

Always use the PyUnicode_SetDefaultEncoding() and

PyUnicode_GetDefaultEncoding() APIs to access this global.

static char unicode_default_encoding[100 + 1] = "ascii";

/* Fast detection of the most frequent whitespace characters */

const unsigned char _Py_ascii_whitespace[] = {

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

/* case 0x0009: * CHARACTER TABULATION */

/* case 0x000A: * LINE FEED */

/* case 0x000B: * LINE TABULATION */

/* case 0x000C: * FORM FEED */

/* case 0x000D: * CARRIAGE RETURN */

0, 1, 1, 1, 1, 1, 0, 0,

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

/* case 0x001C: * FILE SEPARATOR */

/* case 0x001D: * GROUP SEPARATOR */

/* case 0x001E: * RECORD SEPARATOR */

/* case 0x001F: * UNIT SEPARATOR */

0, 0, 0, 0, 1, 1, 1, 1,

/* case 0x0020: * SPACE */

1, 0, 0, 0, 0, 0, 0, 0,

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

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

};

/* Same for linebreaks */

static unsigned char ascii_linebreak[] = {

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

/* 0x000A, * LINE FEED */

/* 0x000B, * LINE TABULATION */

/* 0x000C, * FORM FEED */

/* 0x000D, * CARRIAGE RETURN */

0, 0, 1, 1, 1, 1, 0, 0,

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

/* 0x001C, * FILE SEPARATOR */

/* 0x001D, * GROUP SEPARATOR */

/* 0x001E, * RECORD SEPARATOR */

0, 0, 0, 0, 1, 1, 1, 0,

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

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

};

Py_UNICODE

PyUnicode_GetMax(void)

{

#ifdef Py_UNICODE_WIDE

return 0x10FFFF;

#else

/* This is actually an illegal character, so it should

not be passed to unichr. */

return 0xFFFF;

#endif

}

/* --- Bloom Filters ----------------------------------------------------- */

/* stuff to implement simple "bloom filters" for Unicode characters.

to keep things simple, we use a single bitmask, using the least 5

bits from each unicode characters as the bit index. */

/* the linebreak mask is set up by Unicode_Init below */

#if LONG_BIT >= 128

#define BLOOM_WIDTH 128

#elif LONG_BIT >= 64

#define BLOOM_WIDTH 64

#elif LONG_BIT >= 32

#define BLOOM_WIDTH 32

#else

#error "LONG_BIT is smaller than 32"

#endif

#define BLOOM_MASK unsigned long

static BLOOM_MASK bloom_linebreak = ~(BLOOM_MASK)0;

#define BLOOM_ADD(mask, ch) ((mask |= (1UL << ((ch) & (BLOOM_WIDTH - 1)))))

#define BLOOM(mask, ch) ((mask & (1UL << ((ch) & (BLOOM_WIDTH - 1)))))

#define BLOOM_LINEBREAK(ch) \

((ch) < 128U ? ascii_linebreak[(ch)] : \

(BLOOM(bloom_linebreak, (ch)) && Py_UNICODE_ISLINEBREAK(ch)))

Py_LOCAL_INLINE(BLOOM_MASK) make_bloom_mask(Py_UNICODE* ptr, Py_ssize_t len)

{

/* calculate simple bloom-style bitmask for a given unicode string */

BLOOM_MASK mask;

Py_ssize_t i;

mask = 0;

for (i = 0; i < len; i++)

BLOOM_ADD(mask, ptr[i]);

return mask;

}

Py_LOCAL_INLINE(int) unicode_member(Py_UNICODE chr, Py_UNICODE* set, Py_ssize_t setlen)

{

Py_ssize_t i;

for (i = 0; i < setlen; i++)

if (set[i] == chr)

return 1;

return 0;

}

#define BLOOM_MEMBER(mask, chr, set, setlen) \

BLOOM(mask, chr) && unicode_member(chr, set, setlen)

/* --- Unicode Object ----------------------------------------------------- */

static

int unicode_resize(register PyUnicodeObject *unicode,

Py_ssize_t length)

{

void *oldstr;

/* Shortcut if there's nothing much to do. */

if (unicode->length == length)

goto reset;

/* Resizing shared object (unicode_empty or single character

objects) in-place is not allowed. Use PyUnicode_Resize()

instead ! */

if (unicode == unicode_empty ||

(unicode->length == 1 &&

unicode->str[0] < 256U &&

unicode_latin1[unicode->str[0]] == unicode)) {

PyErr_SetString(PyExc_SystemError,

"can't resize shared unicode objects");

return -1;

}

/* We allocate one more byte to make sure the string is Ux0000 terminated.

The overallocation is also used by fastsearch, which assumes that it's

safe to look at str[length] (without making any assumptions about what

it contains). */

oldstr = unicode->str;

unicode->str = PyObject_REALLOC(unicode->str,

sizeof(Py_UNICODE) * (length + 1));

if (!unicode->str) {

unicode->str = (Py_UNICODE *)oldstr;

PyErr_NoMemory();

return -1;

}

unicode->str[length] = 0;

unicode->length = length;

reset:

/* Reset the object caches */

if (unicode->defenc) {

Py_CLEAR(unicode->defenc);

}

unicode->hash = -1;

return 0;

}

/* We allocate one more byte to make sure the string is

Ux0000 terminated; some code relies on that.

XXX This allocator could further be enhanced by assuring that the

free list never reduces its size below 1.

static

PyUnicodeObject *_PyUnicode_New(Py_ssize_t length)

{

/* Optimization for empty strings */

if (length == 0 && unicode_empty != NULL) {

Py_INCREF(unicode_empty);

return unicode_empty;

}

/* Ensure we won't overflow the size. */

if (length > ((PY_SSIZE_T_MAX / sizeof(Py_UNICODE)) - 1)) {

return (PyUnicodeObject *)PyErr_NoMemory();

}

/* Unicode freelist & memory allocation */

if (free_list) {

unicode = free_list;

free_list = *(PyUnicodeObject **)unicode;

numfree--;

if (unicode->str) {

/* Keep-Alive optimization: we only upsize the buffer,

never downsize it. */

if ((unicode->length < length) &&

unicode_resize(unicode, length) < 0) {

PyObject_DEL(unicode->str);

unicode->str = NULL;

}

else {

size_t new_size = sizeof(Py_UNICODE) * ((size_t)length + 1);

unicode->str = (Py_UNICODE*) PyObject_MALLOC(new_size);

}

(void)PyObject_INIT(unicode, &PyUnicode_Type);

}

else {

size_t new_size;

unicode = PyObject_New(PyUnicodeObject, &PyUnicode_Type);

if (unicode == NULL)

return NULL;

new_size = sizeof(Py_UNICODE) * ((size_t)length + 1);

unicode->str = (Py_UNICODE*) PyObject_MALLOC(new_size);

}

if (!unicode->str) {

PyErr_NoMemory();

goto onError;

}

/* Initialize the first element to guard against cases where

* the caller fails before initializing str -- unicode_resize()

* reads str[0], and the Keep-Alive optimization can keep memory

* allocated for str alive across a call to unicode_dealloc(unicode).

* We don't want unicode_resize to read uninitialized memory in

* that case.

unicode->str[0] = 0;

unicode->str[length] = 0;

unicode->length = length;

unicode->hash = -1;

unicode->defenc = NULL;

return unicode;

onError:

/* XXX UNREF/NEWREF interface should be more symmetrical */

_Py_DEC_REFTOTAL;

_Py_ForgetReference((PyObject *)unicode);

PyObject_Del(unicode);

return NULL;

}

static

void unicode_dealloc(register PyUnicodeObject *unicode)

{

if (PyUnicode_CheckExact(unicode) &&

numfree < PyUnicode_MAXFREELIST) {

/* Keep-Alive optimization */

if (unicode->length >= KEEPALIVE_SIZE_LIMIT) {

PyObject_DEL(unicode->str);

unicode->str = NULL;

unicode->length = 0;

}

if (unicode->defenc) {

Py_CLEAR(unicode->defenc);

}

/* Add to free list */

*(PyUnicodeObject **)unicode = free_list;

free_list = unicode;

numfree++;

}

else {

PyObject_DEL(unicode->str);

Py_XDECREF(unicode->defenc);

Py_TYPE(unicode)->tp_free((PyObject *)unicode);

}

static

int _PyUnicode_Resize(PyUnicodeObject **unicode, Py_ssize_t length)

{

/* Argument checks */

if (unicode == NULL) {

PyErr_BadInternalCall();

return -1;

}

v = *unicode;

if (v == NULL || !PyUnicode_Check(v) || length < 0) {

PyErr_BadInternalCall();

return -1;

}

if (v->length == 0) {

if (length == 0) {

return 0;

}

*unicode = _PyUnicode_New(length);

Py_DECREF(v);

return (*unicode == NULL) ? -1 : 0;

}

if (Py_REFCNT(v) != 1) {

PyErr_BadInternalCall();

return -1;

}

if (length == 0) {

*unicode = _PyUnicode_New(0);

Py_DECREF(v);

return (*unicode == NULL) ? -1 : 0;

}

/* Resizing unicode_empty and single character objects is not

possible since these are being shared. We simply return a fresh

copy with the same Unicode content. */

if (v->length != length &&

(v == unicode_empty || v->length == 1)) {

PyUnicodeObject *w = _PyUnicode_New(length);

if (w == NULL)

return -1;

Py_UNICODE_COPY(w->str, v->str,

length < v->length ? length : v->length);

Py_SETREF(*unicode, w);

return 0;

}

/* Note that we don't have to modify *unicode for unshared Unicode

objects, since we can modify them in-place. */

return unicode_resize(v, length);

}

int PyUnicode_Resize(PyObject **unicode, Py_ssize_t length)

{

return _PyUnicode_Resize((PyUnicodeObject **)unicode, length);

}

PyObject *PyUnicode_FromUnicode(const Py_UNICODE *u,

Py_ssize_t size)

{

PyUnicodeObject *unicode;

/* If the Unicode data is known at construction time, we can apply

some optimizations which share commonly used objects. */

if (u != NULL) {

/* Optimization for empty strings */

if (size == 0)

_Py_RETURN_UNICODE_EMPTY();

/* Single character Unicode objects in the Latin-1 range are

shared when using this constructor */

if (size == 1 && *u < 256) {

unicode = unicode_latin1[*u];

if (!unicode) {

unicode = _PyUnicode_New(1);

if (!unicode)

return NULL;

unicode->str[0] = *u;

unicode_latin1[*u] = unicode;

}

Py_INCREF(unicode);

return (PyObject *)unicode;

}

unicode = _PyUnicode_New(size);

if (!unicode)

return NULL;

/* Copy the Unicode data into the new object */

if (u != NULL)

Py_UNICODE_COPY(unicode->str, u, size);

return (PyObject *)unicode;

}

PyObject *PyUnicode_FromStringAndSize(const char *u, Py_ssize_t size)

{

PyUnicodeObject *unicode;

if (size < 0) {

PyErr_SetString(PyExc_SystemError,

"Negative size passed to PyUnicode_FromStringAndSize");

return NULL;

}

/* If the Unicode data is known at construction time, we can apply

some optimizations which share commonly used objects.

Also, this means the input must be UTF-8, so fall back to the

UTF-8 decoder at the end. */

if (u != NULL) {

/* Optimization for empty strings */

if (size == 0)

_Py_RETURN_UNICODE_EMPTY();

/* Single characters are shared when using this constructor.

Restrict to ASCII, since the input must be UTF-8. */

if (size == 1 && Py_CHARMASK(*u) < 128) {

unicode = unicode_latin1[Py_CHARMASK(*u)];

if (!unicode) {

unicode = _PyUnicode_New(1);

if (!unicode)

return NULL;

unicode->str[0] = Py_CHARMASK(*u);

unicode_latin1[Py_CHARMASK(*u)] = unicode;

}

Py_INCREF(unicode);

return (PyObject *)unicode;

}

return PyUnicode_DecodeUTF8(u, size, NULL);

}

unicode = _PyUnicode_New(size);

if (!unicode)

return NULL;

return (PyObject *)unicode;

}

PyObject *PyUnicode_FromString(const char *u)

{

size_t size = strlen(u);

if (size > PY_SSIZE_T_MAX) {

PyErr_SetString(PyExc_OverflowError, "input too long");

return NULL;

}

return PyUnicode_FromStringAndSize(u, size);

}

/* _Py_UNICODE_NEXT is a private macro used to retrieve the character pointed

* by 'ptr', possibly combining surrogate pairs on narrow builds.

* 'ptr' and 'end' must be Py_UNICODE*, with 'ptr' pointing at the character

* that should be returned and 'end' pointing to the end of the buffer.

* ('end' is used on narrow builds to detect a lone surrogate at the

* end of the buffer that should be returned unchanged.)

* The ptr and end arguments should be side-effect free and ptr must an lvalue.

* The type of the returned char is always Py_UCS4.

* Note: the macro advances ptr to next char, so it might have side-effects

* (especially if used with other macros).

/* helper macros used by _Py_UNICODE_NEXT */

#define _Py_UNICODE_IS_HIGH_SURROGATE(ch) (0xD800 <= ch && ch <= 0xDBFF)

#define _Py_UNICODE_IS_LOW_SURROGATE(ch) (0xDC00 <= ch && ch <= 0xDFFF)

/* Join two surrogate characters and return a single Py_UCS4 value. */

#define _Py_UNICODE_JOIN_SURROGATES(high, low) \

(((((Py_UCS4)(high) & 0x03FF) << 10) | \

((Py_UCS4)(low) & 0x03FF)) + 0x10000)

#ifdef Py_UNICODE_WIDE

#define _Py_UNICODE_NEXT(ptr, end) *(ptr)++

#else

#define _Py_UNICODE_NEXT(ptr, end) \

(((_Py_UNICODE_IS_HIGH_SURROGATE(*(ptr)) && (ptr) < (end)) && \

_Py_UNICODE_IS_LOW_SURROGATE((ptr)[1])) ? \

((ptr) += 2,_Py_UNICODE_JOIN_SURROGATES((ptr)[-2], (ptr)[-1])) : \

(Py_UCS4)*(ptr)++)

#endif

#ifdef HAVE_WCHAR_H

#if (Py_UNICODE_SIZE == 2) && defined(SIZEOF_WCHAR_T) && (SIZEOF_WCHAR_T == 4)

# define CONVERT_WCHAR_TO_SURROGATES

#endif

#ifdef CONVERT_WCHAR_TO_SURROGATES

/* Here sizeof(wchar_t) is 4 but Py_UNICODE_SIZE == 2, so we need

to convert from UTF32 to UTF16. */

PyObject *PyUnicode_FromWideChar(register const wchar_t *w,

Py_ssize_t size)

{

PyUnicodeObject *unicode;

Py_ssize_t alloc;

const wchar_t *orig_w;

if (w == NULL) {

PyErr_BadInternalCall();

return NULL;

}

alloc = size;

orig_w = w;

for (i = size; i > 0; i--) {

if (*w > 0xFFFF)

alloc++;

w++;

}

w = orig_w;

unicode = _PyUnicode_New(alloc);

if (!unicode)

return NULL;

/* Copy the wchar_t data into the new object */

{

u = PyUnicode_AS_UNICODE(unicode);

for (i = size; i > 0; i--) {

if (*w > 0xFFFF) {

wchar_t ordinal = *w++;

ordinal -= 0x10000;

*u++ = 0xD800 | (ordinal >> 10);

*u++ = 0xDC00 | (ordinal & 0x3FF);

}

else

*u++ = *w++;

}

return (PyObject *)unicode;

}

#else

PyObject *PyUnicode_FromWideChar(register const wchar_t *w,

Py_ssize_t size)

{

PyUnicodeObject *unicode;

if (w == NULL) {

PyErr_BadInternalCall();

return NULL;

}

unicode = _PyUnicode_New(size);

if (!unicode)

return NULL;

/* Copy the wchar_t data into the new object */

#ifdef HAVE_USABLE_WCHAR_T

memcpy(unicode->str, w, size * sizeof(wchar_t));

#else

{

u = PyUnicode_AS_UNICODE(unicode);

for (i = size; i > 0; i--)

*u++ = *w++;

}

#endif

return (PyObject *)unicode;

}

#endif /* CONVERT_WCHAR_TO_SURROGATES */

#undef CONVERT_WCHAR_TO_SURROGATES

static void

makefmt(char *fmt, int longflag, int size_tflag, int zeropad, int width, int precision, char c)

{

*fmt++ = '%';

if (width) {

if (zeropad)

*fmt++ = '0';

fmt += sprintf(fmt, "%d", width);

}

if (precision)

fmt += sprintf(fmt, ".%d", precision);

if (longflag)

*fmt++ = 'l';

else if (size_tflag) {

char *f = PY_FORMAT_SIZE_T;

while (*f)

*fmt++ = *f++;

}

*fmt++ = c;

*fmt = '\0';

}

#define appendstring(string) \

do { \

for (copy = string;*copy; copy++) { \

*s++ = (unsigned char)*copy; \

} \

} while (0)

PyObject *

PyUnicode_FromFormatV(const char *format, va_list vargs)

{

va_list count;

Py_ssize_t callcount = 0;

PyObject **callresults = NULL;

PyObject **callresult = NULL;

Py_ssize_t n = 0;

int width = 0;

int precision = 0;

int zeropad;

const char* f;

Py_UNICODE *s;

PyObject *string;

/* used by sprintf */

char buffer[21];

/* use abuffer instead of buffer, if we need more space

* (which can happen if there's a format specifier with width). */

char *abuffer = NULL;

char *realbuffer;

Py_ssize_t abuffersize = 0;

char fmt[60]; /* should be enough for %0width.precisionld */

const char *copy;

#ifdef VA_LIST_IS_ARRAY

Py_MEMCPY(count, vargs, sizeof(va_list));

#else

#ifdef __va_copy

__va_copy(count, vargs);

#else

count = vargs;

#endif

/* step 1: count the number of %S/%R/%s format specifications

* (we call PyObject_Str()/PyObject_Repr()/PyUnicode_DecodeUTF8() for these

* objects once during step 3 and put the result in an array) */

for (f = format; *f; f++) {

if (*f == '%') {

f++;

while (*f && *f != '%' && !isalpha((unsigned)*f))

f++;

if (!*f)

break;

if (*f == 's' || *f=='S' || *f=='R')

++callcount;

}

/* step 2: allocate memory for the results of

* PyObject_Str()/PyObject_Repr()/PyUnicode_DecodeUTF8() calls */

if (callcount) {

callresults = PyObject_Malloc(sizeof(PyObject *)*callcount);

if (!callresults) {

PyErr_NoMemory();

return NULL;

}

callresult = callresults;

}

/* step 3: figure out how large a buffer we need */

for (f = format; *f; f++) {

if (*f == '%') {

const char* p = f++;

width = 0;

while (isdigit((unsigned)*f))

width = (width*10) + *f++ - '0';

precision = 0;

if (*f == '.') {

f++;

while (isdigit((unsigned)*f))

precision = (precision*10) + *f++ - '0';

}

/* skip the 'l' or 'z' in {%ld, %zd, %lu, %zu} since

* they don't affect the amount of space we reserve.

if ((*f == 'l' || *f == 'z') &&

(f[1] == 'd' || f[1] == 'u'))

++f;

switch (*f) {

case 'c':

{

int ordinal = va_arg(count, int);

#ifdef Py_UNICODE_WIDE

if (ordinal < 0 || ordinal > 0x10ffff) {

PyErr_SetString(PyExc_OverflowError,

"%c arg not in range(0x110000) "

"(wide Python build)");

goto fail;

}

#else

if (ordinal < 0 || ordinal > 0xffff) {

PyErr_SetString(PyExc_OverflowError,

"%c arg not in range(0x10000) "

"(narrow Python build)");

goto fail;

}

#endif

/* fall through... */

}

case '%':

n++;

break;

case 'd': case 'u': case 'i': case 'x':

(void) va_arg(count, int);

if (width < precision)

width = precision;

/* 20 bytes is enough to hold a 64-bit

integer. Decimal takes the most space.

This isn't enough for octal.

If a width is specified we need more

(which we allocate later). */

if (width < 20)

width = 20;

n += width;

if (abuffersize < width)

abuffersize = width;

break;

case 's':

{

/* UTF-8 */

const char *s = va_arg(count, const char*);

PyObject *str = PyUnicode_DecodeUTF8(s, strlen(s), "replace");

if (!str)

goto fail;

n += PyUnicode_GET_SIZE(str);

/* Remember the str and switch to the next slot */

*callresult++ = str;

break;

}

case 'U':

{

PyObject *obj = va_arg(count, PyObject *);

assert(obj && PyUnicode_Check(obj));

n += PyUnicode_GET_SIZE(obj);

break;

}

case 'V':

{

PyObject *obj = va_arg(count, PyObject *);

const char *str = va_arg(count, const char *);

assert(obj || str);

assert(!obj || PyUnicode_Check(obj));

if (obj)

n += PyUnicode_GET_SIZE(obj);

else

n += strlen(str);

break;

}

case 'S':

{

PyObject *obj = va_arg(count, PyObject *);

PyObject *str;

assert(obj);

str = PyObject_Str(obj);

if (!str)

goto fail;

n += PyString_GET_SIZE(str);

/* Remember the str and switch to the next slot */

*callresult++ = str;

break;

}

case 'R':

{

PyObject *obj = va_arg(count, PyObject *);

PyObject *repr;

assert(obj);

repr = PyObject_Repr(obj);

if (!repr)

goto fail;

n += PyUnicode_GET_SIZE(repr);

/* Remember the repr and switch to the next slot */

*callresult++ = repr;

break;

}

case 'p':

(void) va_arg(count, int);

/* maximum 64-bit pointer representation:

* 0xffffffffffffffff

* so 19 characters is enough.

* XXX I count 18 -- what's the extra for?

n += 19;

break;

default:

/* if we stumble upon an unknown

formatting code, copy the rest of

the format string to the output

string. (we cannot just skip the

code, since there's no way to know

what's in the argument list) */

n += strlen(p);

goto expand;

}

} else

n++;

}

expand:

if (abuffersize > 20) {

/* add 1 for sprintf's trailing null byte */

abuffer = PyObject_Malloc(abuffersize + 1);

if (!abuffer) {

PyErr_NoMemory();

goto fail;

}

realbuffer = abuffer;

}

else

realbuffer = buffer;

/* step 4: fill the buffer */

/* Since we've analyzed how much space we need for the worst case,

we don't have to resize the string.

There can be no errors beyond this point. */

string = PyUnicode_FromUnicode(NULL, n);

if (!string)

goto fail;

s = PyUnicode_AS_UNICODE(string);

callresult = callresults;

for (f = format; *f; f++) {

if (*f == '%') {

const char* p = f++;

int longflag = 0;

int size_tflag = 0;

zeropad = (*f == '0');

/* parse the width.precision part */

width = 0;

while (isdigit((unsigned)*f))

width = (width*10) + *f++ - '0';

precision = 0;

if (*f == '.') {

f++;

while (isdigit((unsigned)*f))

precision = (precision*10) + *f++ - '0';

}

/* handle the long flag, but only for %ld and %lu.

others can be added when necessary. */

if (*f == 'l' && (f[1] == 'd' || f[1] == 'u')) {

longflag = 1;

++f;

}

/* handle the size_t flag. */

if (*f == 'z' && (f[1] == 'd' || f[1] == 'u')) {

size_tflag = 1;

++f;

}

switch (*f) {

case 'c':

*s++ = va_arg(vargs, int);

break;

case 'd':

makefmt(fmt, longflag, size_tflag, zeropad, width, precision, 'd');

if (longflag)

sprintf(realbuffer, fmt, va_arg(vargs, long));

else if (size_tflag)

sprintf(realbuffer, fmt, va_arg(vargs, Py_ssize_t));

else

sprintf(realbuffer, fmt, va_arg(vargs, int));

appendstring(realbuffer);

break;

case 'u':

makefmt(fmt, longflag, size_tflag, zeropad, width, precision, 'u');

if (longflag)

sprintf(realbuffer, fmt, va_arg(vargs, unsigned long));

else if (size_tflag)

sprintf(realbuffer, fmt, va_arg(vargs, size_t));

else

sprintf(realbuffer, fmt, va_arg(vargs, unsigned int));

appendstring(realbuffer);

break;

case 'i':

makefmt(fmt, 0, 0, zeropad, width, precision, 'i');

sprintf(realbuffer, fmt, va_arg(vargs, int));

appendstring(realbuffer);

break;

case 'x':

makefmt(fmt, 0, 0, zeropad, width, precision, 'x');

sprintf(realbuffer, fmt, va_arg(vargs, int));

appendstring(realbuffer);

break;

case 's':

{

/* unused, since we already have the result */

(void) va_arg(vargs, char *);

View remainder of file in raw view

cpython/Objects/unicodeobject.c at 2.7 · python-emscripten/cpython · GitHub

Navigation Menu

Repository navigation

Expand file tree

Breadcrumbs

unicodeobject.c

Latest commit

History

Breadcrumbs

unicodeobject.c

File metadata and controls

Footer

Footer navigation