python/Modules/_bytesio.c at master · charleson/python · GitHub

History

763 lines (641 loc) · 20.9 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

#include "Python.h"

typedef struct {

PyObject_HEAD

char *buf;

Py_ssize_t pos;

Py_ssize_t string_size;

size_t buf_size;

} BytesIOObject;

#define CHECK_CLOSED(self) \

if ((self)->buf == NULL) { \

PyErr_SetString(PyExc_ValueError, \

"I/O operation on closed file."); \

return NULL; \

}

/* Internal routine to get a line from the buffer of a BytesIO

object. Returns the length between the current position to the

next newline character. */

static Py_ssize_t

get_line(BytesIOObject *self, char **output)

{

char *n;

const char *str_end;

Py_ssize_t len;

assert(self->buf != NULL);

/* Move to the end of the line, up to the end of the string, s. */

str_end = self->buf + self->string_size;

for (n = self->buf + self->pos;

n < str_end && *n != '\n';

n++);

/* Skip the newline character */

if (n < str_end)

n++;

/* Get the length from the current position to the end of the line. */

len = n - (self->buf + self->pos);

*output = self->buf + self->pos;

assert(len >= 0);

assert(self->pos < PY_SSIZE_T_MAX - len);

self->pos += len;

return len;

}

/* Internal routine for changing the size of the buffer of BytesIO objects.

The caller should ensure that the 'size' argument is non-negative. Returns

0 on success, -1 otherwise. */

static int

resize_buffer(BytesIOObject *self, size_t size)

{

/* Here, unsigned types are used to avoid dealing with signed integer

overflow, which is undefined in C. */

size_t alloc = self->buf_size;

char *new_buf = NULL;

assert(self->buf != NULL);

/* For simplicity, stay in the range of the signed type. Anyway, Python

doesn't allow strings to be longer than this. */

if (size > PY_SSIZE_T_MAX)

goto overflow;

if (size < alloc / 2) {

/* Major downsize; resize down to exact size. */

alloc = size + 1;

}

else if (size < alloc) {

/* Within allocated size; quick exit */

return 0;

}

else if (size <= alloc * 1.125) {

/* Moderate upsize; overallocate similar to list_resize() */

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

}

else {

/* Major upsize; resize up to exact size */

alloc = size + 1;

}

if (alloc > ((size_t)-1) / sizeof(char))

goto overflow;

new_buf = (char *)PyMem_Realloc(self->buf, alloc * sizeof(char));

if (new_buf == NULL) {

PyErr_NoMemory();

return -1;

}

self->buf_size = alloc;

self->buf = new_buf;

return 0;

overflow:

PyErr_SetString(PyExc_OverflowError,

"new buffer size too large");

return -1;

}

/* Internal routine for writing a string of bytes to the buffer of a BytesIO

object. Returns the number of bytes wrote, or -1 on error. */

static Py_ssize_t

write_bytes(BytesIOObject *self, const char *bytes, Py_ssize_t len)

{

assert(self->buf != NULL);

assert(self->pos >= 0);

assert(len >= 0);

if ((size_t)self->pos + len > self->buf_size) {

if (resize_buffer(self, (size_t)self->pos + len) < 0)

return -1;

}

if (self->pos > self->string_size) {

/* In case of overseek, pad with null bytes the buffer region between

the end of stream and the current position.

0 lo string_size hi

| |<---used--->|<----------available----------->|

| | <--to pad-->|<---to write---> |

0 buf position

memset(self->buf + self->string_size, '\0',

(self->pos - self->string_size) * sizeof(char));

}

/* Copy the data to the internal buffer, overwriting some of the existing

data if self->pos < self->string_size. */

memcpy(self->buf + self->pos, bytes, len);

self->pos += len;

/* Set the new length of the internal string if it has changed. */

if (self->string_size < self->pos) {

self->string_size = self->pos;

}

return len;

}

static PyObject *

bytesio_get_closed(BytesIOObject *self)

{

if (self->buf == NULL)

Py_RETURN_TRUE;

else

Py_RETURN_FALSE;

}

/* Generic getter for the writable, readable and seekable properties */

static PyObject *

return_true(BytesIOObject *self)

{

Py_RETURN_TRUE;

}

PyDoc_STRVAR(flush_doc,

"flush() -> None. Does nothing.");

static PyObject *

bytesio_flush(BytesIOObject *self)

{

Py_RETURN_NONE;

}

PyDoc_STRVAR(getval_doc,

"getvalue() -> bytes.\n"

"\n"

"Retrieve the entire contents of the BytesIO object.");

static PyObject *

bytesio_getvalue(BytesIOObject *self)

{

CHECK_CLOSED(self);

return PyString_FromStringAndSize(self->buf, self->string_size);

}

PyDoc_STRVAR(isatty_doc,

"isatty() -> False.\n"

"\n"

"Always returns False since BytesIO objects are not connected\n"

"to a tty-like device.");

static PyObject *

bytesio_isatty(BytesIOObject *self)

{

CHECK_CLOSED(self);

Py_RETURN_FALSE;

}

PyDoc_STRVAR(tell_doc,

"tell() -> current file position, an integer\n");

static PyObject *

bytesio_tell(BytesIOObject *self)

{

CHECK_CLOSED(self);

return PyInt_FromSsize_t(self->pos);

}

PyDoc_STRVAR(read_doc,

"read([size]) -> read at most size bytes, returned as a string.\n"

"\n"

"If the size argument is negative, read until EOF is reached.\n"

"Return an empty string at EOF.");

static PyObject *

bytesio_read(BytesIOObject *self, PyObject *args)

{

Py_ssize_t size, n;

char *output;

PyObject *arg = Py_None;

CHECK_CLOSED(self);

if (!PyArg_ParseTuple(args, "|O:read", &arg))

return NULL;

if (PyInt_Check(arg)) {

size = PyInt_AsSsize_t(arg);

if (size == -1 && PyErr_Occurred())

return NULL;

}

else if (arg == Py_None) {

/* Read until EOF is reached, by default. */

size = -1;

}

else {

PyErr_Format(PyExc_TypeError, "integer argument expected, got '%s'",

Py_TYPE(arg)->tp_name);

return NULL;

}

/* adjust invalid sizes */

n = self->string_size - self->pos;

if (size < 0 || size > n) {

size = n;

if (size < 0)

size = 0;

}

assert(self->buf != NULL);

output = self->buf + self->pos;

self->pos += size;

return PyString_FromStringAndSize(output, size);

}

PyDoc_STRVAR(read1_doc,

"read1(size) -> read at most size bytes, returned as a string.\n"

"\n"

"If the size argument is negative or omitted, read until EOF is reached.\n"

"Return an empty string at EOF.");

static PyObject *

bytesio_read1(BytesIOObject *self, PyObject *n)

{

PyObject *arg, *res;

arg = PyTuple_Pack(1, n);

if (arg == NULL)

return NULL;

res = bytesio_read(self, arg);

Py_DECREF(arg);

return res;

}

PyDoc_STRVAR(readline_doc,

"readline([size]) -> next line from the file, as a string.\n"

"\n"

"Retain newline. A non-negative size argument limits the maximum\n"

"number of bytes to return (an incomplete line may be returned then).\n"

"Return an empty string at EOF.\n");

static PyObject *

bytesio_readline(BytesIOObject *self, PyObject *args)

{

Py_ssize_t size, n;

char *output;

PyObject *arg = Py_None;

CHECK_CLOSED(self);

if (!PyArg_ParseTuple(args, "|O:readline", &arg))

return NULL;

if (PyInt_Check(arg)) {

size = PyInt_AsSsize_t(arg);

if (size == -1 && PyErr_Occurred())

return NULL;

}

else if (arg == Py_None) {

/* No size limit, by default. */

size = -1;

}

else {

PyErr_Format(PyExc_TypeError, "integer argument expected, got '%s'",

Py_TYPE(arg)->tp_name);

return NULL;

}

n = get_line(self, &output);

if (size >= 0 && size < n) {

size = n - size;

n -= size;

self->pos -= size;

}

return PyString_FromStringAndSize(output, n);

}

PyDoc_STRVAR(readlines_doc,

"readlines([size]) -> list of strings, each a line from the file.\n"

"\n"

"Call readline() repeatedly and return a list of the lines so read.\n"

"The optional size argument, if given, is an approximate bound on the\n"

"total number of bytes in the lines returned.\n");

static PyObject *

bytesio_readlines(BytesIOObject *self, PyObject *args)

{

Py_ssize_t maxsize, size, n;

PyObject *result, *line;

char *output;

PyObject *arg = Py_None;

CHECK_CLOSED(self);

if (!PyArg_ParseTuple(args, "|O:readlines", &arg))

return NULL;

if (PyInt_Check(arg)) {

maxsize = PyInt_AsSsize_t(arg);

if (maxsize == -1 && PyErr_Occurred())

return NULL;

}

else if (arg == Py_None) {

/* No size limit, by default. */

maxsize = -1;

}

else {

PyErr_Format(PyExc_TypeError, "integer argument expected, got '%s'",

Py_TYPE(arg)->tp_name);

return NULL;

}

size = 0;

result = PyList_New(0);

if (!result)

return NULL;

while ((n = get_line(self, &output)) != 0) {

line = PyString_FromStringAndSize(output, n);

if (!line)

goto on_error;

if (PyList_Append(result, line) == -1) {

Py_DECREF(line);

goto on_error;

}

Py_DECREF(line);

size += n;

if (maxsize > 0 && size >= maxsize)

break;

}

return result;

on_error:

Py_DECREF(result);

return NULL;

}

PyDoc_STRVAR(readinto_doc,

"readinto(bytearray) -> int. Read up to len(b) bytes into b.\n"

"\n"

"Returns number of bytes read (0 for EOF), or None if the object\n"

"is set not to block as has no data to read.");

static PyObject *

bytesio_readinto(BytesIOObject *self, PyObject *buffer)

{

void *raw_buffer;

Py_ssize_t len;

CHECK_CLOSED(self);

if (PyObject_AsWriteBuffer(buffer, &raw_buffer, &len) == -1)

return NULL;

if (self->pos + len > self->string_size)

len = self->string_size - self->pos;

memcpy(raw_buffer, self->buf + self->pos, len);

assert(self->pos + len < PY_SSIZE_T_MAX);

assert(len >= 0);

self->pos += len;

return PyInt_FromSsize_t(len);

}

PyDoc_STRVAR(truncate_doc,

"truncate([size]) -> int. Truncate the file to at most size bytes.\n"

"\n"

"Size defaults to the current file position, as returned by tell().\n"

"Returns the new size. Imply an absolute seek to the position size.");

static PyObject *

bytesio_truncate(BytesIOObject *self, PyObject *args)

{

Py_ssize_t size;

PyObject *arg = Py_None;

CHECK_CLOSED(self);

if (!PyArg_ParseTuple(args, "|O:truncate", &arg))

return NULL;

if (PyInt_Check(arg)) {

size = PyInt_AsSsize_t(arg);

if (size == -1 && PyErr_Occurred())

return NULL;

}

else if (arg == Py_None) {

/* Truncate to current position if no argument is passed. */

size = self->pos;

}

else {

PyErr_Format(PyExc_TypeError, "integer argument expected, got '%s'",

Py_TYPE(arg)->tp_name);

return NULL;

}

if (size < 0) {

PyErr_Format(PyExc_ValueError,

"negative size value %zd", size);

return NULL;

}

if (size < self->string_size) {

self->string_size = size;

if (resize_buffer(self, size) < 0)

return NULL;

}

self->pos = size;

return PyInt_FromSsize_t(size);

}

static PyObject *

bytesio_iternext(BytesIOObject *self)

{

char *next;

Py_ssize_t n;

CHECK_CLOSED(self);

n = get_line(self, &next);

if (!next || n == 0)

return NULL;

return PyString_FromStringAndSize(next, n);

}

PyDoc_STRVAR(seek_doc,

"seek(pos, whence=0) -> int. Change stream position.\n"

"\n"

"Seek to byte offset pos relative to position indicated by whence:\n"

" 0 Start of stream (the default). pos should be >= 0;\n"

" 1 Current position - pos may be negative;\n"

" 2 End of stream - pos usually negative.\n"

"Returns the new absolute position.");

static PyObject *

bytesio_seek(BytesIOObject *self, PyObject *args)

{

PyObject *pos_obj, *mode_obj;

Py_ssize_t pos;

int mode = 0;

CHECK_CLOSED(self);

/* Special-case for 2.x to prevent floats from passing through.

This only needed to make a test in test_io succeed. */

if (!PyArg_UnpackTuple(args, "seek", 1, 2, &pos_obj, &mode_obj))

return NULL;

if (PyFloat_Check(pos_obj)) {

PyErr_SetString(PyExc_TypeError,

"position argument must be an integer");

return NULL;

}

if (!PyArg_ParseTuple(args, "n|i:seek", &pos, &mode))

return NULL;

if (pos < 0 && mode == 0) {

PyErr_Format(PyExc_ValueError,

"negative seek value %zd", pos);

return NULL;

}

/* mode 0: offset relative to beginning of the string.

mode 1: offset relative to current position.

mode 2: offset relative the end of the string. */

if (mode == 1) {

if (pos > PY_SSIZE_T_MAX - self->pos) {

PyErr_SetString(PyExc_OverflowError,

"new position too large");

return NULL;

}

pos += self->pos;

}

else if (mode == 2) {

if (pos > PY_SSIZE_T_MAX - self->string_size) {

PyErr_SetString(PyExc_OverflowError,

"new position too large");

return NULL;

}

pos += self->string_size;

}

else if (mode != 0) {

PyErr_Format(PyExc_ValueError,

"invalid whence (%i, should be 0, 1 or 2)", mode);

return NULL;

}

if (pos < 0)

pos = 0;

self->pos = pos;

return PyInt_FromSsize_t(self->pos);

}

PyDoc_STRVAR(write_doc,

"write(bytes) -> int. Write bytes to file.\n"

"\n"

"Return the number of bytes written.");

static PyObject *

bytesio_write(BytesIOObject *self, PyObject *obj)

{

const char *bytes;

Py_ssize_t size;

Py_ssize_t n = 0;

CHECK_CLOSED(self);

/* Special-case in 2.x to prevent unicode objects to pass through. */

if (PyUnicode_Check(obj)) {

PyErr_SetString(PyExc_TypeError,

"expecting a bytes object, got unicode");

return NULL;

}

if (PyObject_AsReadBuffer(obj, (void *)&bytes, &size) < 0)

return NULL;

if (size != 0) {

n = write_bytes(self, bytes, size);

if (n < 0)

return NULL;

}

return PyInt_FromSsize_t(n);

}

PyDoc_STRVAR(writelines_doc,

"writelines(sequence_of_strings) -> None. Write strings to the file.\n"

"\n"

"Note that newlines are not added. The sequence can be any iterable\n"

"object producing strings. This is equivalent to calling write() for\n"

"each string.");

static PyObject *

bytesio_writelines(BytesIOObject *self, PyObject *v)

{

PyObject *it, *item;

PyObject *ret;

CHECK_CLOSED(self);

it = PyObject_GetIter(v);

if (it == NULL)

return NULL;

while ((item = PyIter_Next(it)) != NULL) {

ret = bytesio_write(self, item);

Py_DECREF(item);

if (ret == NULL) {

Py_DECREF(it);

return NULL;

}

Py_DECREF(ret);

}

Py_DECREF(it);

/* See if PyIter_Next failed */

if (PyErr_Occurred())

return NULL;

Py_RETURN_NONE;

}

PyDoc_STRVAR(close_doc,

"close() -> None. Disable all I/O operations.");

static PyObject *

bytesio_close(BytesIOObject *self)

{

if (self->buf != NULL) {

PyMem_Free(self->buf);

self->buf = NULL;

}

Py_RETURN_NONE;

}

static void

bytesio_dealloc(BytesIOObject *self)

{

if (self->buf != NULL) {

PyMem_Free(self->buf);

self->buf = NULL;

}

Py_TYPE(self)->tp_free(self);

}

static PyObject *

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

{

BytesIOObject *self;

assert(type != NULL && type->tp_alloc != NULL);

self = (BytesIOObject *)type->tp_alloc(type, 0);

if (self == NULL)

return NULL;

self->string_size = 0;

self->pos = 0;

self->buf_size = 0;

self->buf = (char *)PyMem_Malloc(0);

if (self->buf == NULL) {

Py_DECREF(self);

return PyErr_NoMemory();

}

return (PyObject *)self;

}

static int

bytesio_init(BytesIOObject *self, PyObject *args, PyObject *kwds)

{

PyObject *initvalue = NULL;

if (!PyArg_ParseTuple(args, "|O:BytesIO", &initvalue))

return -1;

/* In case, __init__ is called multiple times. */

self->string_size = 0;

self->pos = 0;

if (initvalue && initvalue != Py_None) {

PyObject *res;

res = bytesio_write(self, initvalue);

if (res == NULL)

return -1;

Py_DECREF(res);

self->pos = 0;

}

return 0;

}

static PyGetSetDef bytesio_getsetlist[] = {

{"closed", (getter)bytesio_get_closed, NULL,

"True if the file is closed."},

{0}, /* sentinel */

};

static struct PyMethodDef bytesio_methods[] = {

{"readable", (PyCFunction)return_true, METH_NOARGS, NULL},

{"seekable", (PyCFunction)return_true, METH_NOARGS, NULL},

{"writable", (PyCFunction)return_true, METH_NOARGS, NULL},

{"close", (PyCFunction)bytesio_close, METH_NOARGS, close_doc},

{"flush", (PyCFunction)bytesio_flush, METH_NOARGS, flush_doc},

{"isatty", (PyCFunction)bytesio_isatty, METH_NOARGS, isatty_doc},

{"tell", (PyCFunction)bytesio_tell, METH_NOARGS, tell_doc},

{"write", (PyCFunction)bytesio_write, METH_O, write_doc},

{"writelines", (PyCFunction)bytesio_writelines, METH_O, writelines_doc},

{"read1", (PyCFunction)bytesio_read1, METH_O, read1_doc},

{"readinto", (PyCFunction)bytesio_readinto, METH_O, readinto_doc},

{"readline", (PyCFunction)bytesio_readline, METH_VARARGS, readline_doc},

{"readlines", (PyCFunction)bytesio_readlines, METH_VARARGS, readlines_doc},

{"read", (PyCFunction)bytesio_read, METH_VARARGS, read_doc},

{"getvalue", (PyCFunction)bytesio_getvalue, METH_VARARGS, getval_doc},

{"seek", (PyCFunction)bytesio_seek, METH_VARARGS, seek_doc},

{"truncate", (PyCFunction)bytesio_truncate, METH_VARARGS, truncate_doc},

{NULL, NULL} /* sentinel */

};

PyDoc_STRVAR(bytesio_doc,

"BytesIO([buffer]) -> object\n"

"\n"

"Create a buffered I/O implementation using an in-memory bytes\n"

"buffer, ready for reading and writing.");

static PyTypeObject BytesIO_Type = {

PyVarObject_HEAD_INIT(NULL, 0)

"_bytesio._BytesIO", /*tp_name*/

sizeof(BytesIOObject), /*tp_basicsize*/

0, /*tp_itemsize*/

(destructor)bytesio_dealloc, /*tp_dealloc*/

0, /*tp_print*/

0, /*tp_getattr*/

0, /*tp_setattr*/

0, /*tp_compare*/

0, /*tp_repr*/

0, /*tp_as_number*/

0, /*tp_as_sequence*/

0, /*tp_as_mapping*/

0, /*tp_hash*/

0, /*tp_call*/

0, /*tp_str*/

0, /*tp_getattro*/

0, /*tp_setattro*/

0, /*tp_as_buffer*/

Py_TPFLAGS_DEFAULT | Py_TPFLAGS_BASETYPE, /*tp_flags*/

bytesio_doc, /*tp_doc*/

0, /*tp_traverse*/

0, /*tp_clear*/

0, /*tp_richcompare*/

0, /*tp_weaklistoffset*/

PyObject_SelfIter, /*tp_iter*/

(iternextfunc)bytesio_iternext, /*tp_iternext*/

bytesio_methods, /*tp_methods*/

0, /*tp_members*/

bytesio_getsetlist, /*tp_getset*/

0, /*tp_base*/

0, /*tp_dict*/

0, /*tp_descr_get*/

0, /*tp_descr_set*/

0, /*tp_dictoffset*/

(initproc)bytesio_init, /*tp_init*/

0, /*tp_alloc*/

bytesio_new, /*tp_new*/

};

PyMODINIT_FUNC

init_bytesio(void)

{

PyObject *m;

if (PyType_Ready(&BytesIO_Type) < 0)

return;

m = Py_InitModule("_bytesio", NULL);

if (m == NULL)

return;

Py_INCREF(&BytesIO_Type);

PyModule_AddObject(m, "_BytesIO", (PyObject *)&BytesIO_Type);

}

python/Modules/_bytesio.c at master · charleson/python · GitHub

Expand file tree

Breadcrumbs

_bytesio.c

Latest commit

History

Breadcrumbs

_bytesio.c

File metadata and controls