cpython/Lib/shutil.py at 3.5 · python/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

"""Utility functions for copying and archiving files and directory trees.

XXX The functions here don't copy the resource fork or other metadata on Mac.

"""

import os

import sys

import stat

import fnmatch

import collections

import errno

try:

import zlib

del zlib

_ZLIB_SUPPORTED = True

except ImportError:

_ZLIB_SUPPORTED = False

try:

import bz2

del bz2

_BZ2_SUPPORTED = True

except ImportError:

_BZ2_SUPPORTED = False

try:

import lzma

del lzma

_LZMA_SUPPORTED = True

except ImportError:

_LZMA_SUPPORTED = False

try:

from pwd import getpwnam

except ImportError:

getpwnam = None

try:

from grp import getgrnam

except ImportError:

getgrnam = None

__all__ = ["copyfileobj", "copyfile", "copymode", "copystat", "copy", "copy2",

"copytree", "move", "rmtree", "Error", "SpecialFileError",

"ExecError", "make_archive", "get_archive_formats",

"register_archive_format", "unregister_archive_format",

"get_unpack_formats", "register_unpack_format",

"unregister_unpack_format", "unpack_archive",

"ignore_patterns", "chown", "which", "get_terminal_size",

"SameFileError"]

# disk_usage is added later, if available on the platform

class Error(OSError):

pass

class SameFileError(Error):

"""Raised when source and destination are the same file."""

class SpecialFileError(OSError):

"""Raised when trying to do a kind of operation (e.g. copying) which is

not supported on a special file (e.g. a named pipe)"""

class ExecError(OSError):

"""Raised when a command could not be executed"""

class ReadError(OSError):

"""Raised when an archive cannot be read"""

class RegistryError(Exception):

"""Raised when a registry operation with the archiving

and unpacking registries fails"""

def copyfileobj(fsrc, fdst, length=16*1024):

"""copy data from file-like object fsrc to file-like object fdst"""

while 1:

buf = fsrc.read(length)

if not buf:

break

fdst.write(buf)

def _samefile(src, dst):

# Macintosh, Unix.

if hasattr(os.path, 'samefile'):

try:

return os.path.samefile(src, dst)

except OSError:

return False

# All other platforms: check for same pathname.

return (os.path.normcase(os.path.abspath(src)) ==

os.path.normcase(os.path.abspath(dst)))

def copyfile(src, dst, *, follow_symlinks=True):

"""Copy data from src to dst.

If follow_symlinks is not set and src is a symbolic link, a new

symlink will be created instead of copying the file it points to.

"""

if _samefile(src, dst):

raise SameFileError("{!r} and {!r} are the same file".format(src, dst))

for fn in [src, dst]:

try:

st = os.stat(fn)

except OSError:

# File most likely does not exist

pass

else:

# XXX What about other special files? (sockets, devices...)

if stat.S_ISFIFO(st.st_mode):

raise SpecialFileError("`%s` is a named pipe" % fn)

if not follow_symlinks and os.path.islink(src):

os.symlink(os.readlink(src), dst)

else:

with open(src, 'rb') as fsrc:

with open(dst, 'wb') as fdst:

copyfileobj(fsrc, fdst)

return dst

def copymode(src, dst, *, follow_symlinks=True):

"""Copy mode bits from src to dst.

If follow_symlinks is not set, symlinks aren't followed if and only

if both `src` and `dst` are symlinks. If `lchmod` isn't available

(e.g. Linux) this method does nothing.

"""

if not follow_symlinks and os.path.islink(src) and os.path.islink(dst):

if hasattr(os, 'lchmod'):

stat_func, chmod_func = os.lstat, os.lchmod

else:

return

elif hasattr(os, 'chmod'):

stat_func, chmod_func = os.stat, os.chmod

else:

return

st = stat_func(src)

chmod_func(dst, stat.S_IMODE(st.st_mode))

if hasattr(os, 'listxattr'):

def _copyxattr(src, dst, *, follow_symlinks=True):

"""Copy extended filesystem attributes from `src` to `dst`.

Overwrite existing attributes.

If `follow_symlinks` is false, symlinks won't be followed.

"""

try:

names = os.listxattr(src, follow_symlinks=follow_symlinks)

except OSError as e:

if e.errno not in (errno.ENOTSUP, errno.ENODATA):

raise

return

for name in names:

try:

value = os.getxattr(src, name, follow_symlinks=follow_symlinks)

os.setxattr(dst, name, value, follow_symlinks=follow_symlinks)

except OSError as e:

if e.errno not in (errno.EPERM, errno.ENOTSUP, errno.ENODATA):

raise

else:

def _copyxattr(*args, **kwargs):

pass

def copystat(src, dst, *, follow_symlinks=True):

"""Copy all stat info (mode bits, atime, mtime, flags) from src to dst.

If the optional flag `follow_symlinks` is not set, symlinks aren't followed if and

only if both `src` and `dst` are symlinks.

"""

def _nop(*args, ns=None, follow_symlinks=None):

pass

# follow symlinks (aka don't not follow symlinks)

follow = follow_symlinks or not (os.path.islink(src) and os.path.islink(dst))

if follow:

# use the real function if it exists

def lookup(name):

return getattr(os, name, _nop)

else:

# use the real function only if it exists

# *and* it supports follow_symlinks

def lookup(name):

fn = getattr(os, name, _nop)

if fn in os.supports_follow_symlinks:

return fn

return _nop

st = lookup("stat")(src, follow_symlinks=follow)

mode = stat.S_IMODE(st.st_mode)

lookup("utime")(dst, ns=(st.st_atime_ns, st.st_mtime_ns),

follow_symlinks=follow)

try:

lookup("chmod")(dst, mode, follow_symlinks=follow)

except NotImplementedError:

# if we got a NotImplementedError, it's because

# * follow_symlinks=False,

# * lchown() is unavailable, and

# * either

# * fchownat() is unavailable or

# * fchownat() doesn't implement AT_SYMLINK_NOFOLLOW.

# (it returned ENOSUP.)

# therefore we're out of options--we simply cannot chown the

# symlink. give up, suppress the error.

# (which is what shutil always did in this circumstance.)

pass

if hasattr(st, 'st_flags'):

try:

lookup("chflags")(dst, st.st_flags, follow_symlinks=follow)

except OSError as why:

for err in 'EOPNOTSUPP', 'ENOTSUP':

if hasattr(errno, err) and why.errno == getattr(errno, err):

break

else:

raise

_copyxattr(src, dst, follow_symlinks=follow)

def copy(src, dst, *, follow_symlinks=True):

"""Copy data and mode bits ("cp src dst"). Return the file's destination.

The destination may be a directory.

If follow_symlinks is false, symlinks won't be followed. This

resembles GNU's "cp -P src dst".

If source and destination are the same file, a SameFileError will be

raised.

"""

if os.path.isdir(dst):

dst = os.path.join(dst, os.path.basename(src))

copyfile(src, dst, follow_symlinks=follow_symlinks)

copymode(src, dst, follow_symlinks=follow_symlinks)

return dst

def copy2(src, dst, *, follow_symlinks=True):

"""Copy data and all stat info ("cp -p src dst"). Return the file's

destination."

The destination may be a directory.

If follow_symlinks is false, symlinks won't be followed. This

resembles GNU's "cp -P src dst".

"""

if os.path.isdir(dst):

dst = os.path.join(dst, os.path.basename(src))

copyfile(src, dst, follow_symlinks=follow_symlinks)

copystat(src, dst, follow_symlinks=follow_symlinks)

return dst

def ignore_patterns(*patterns):

"""Function that can be used as copytree() ignore parameter.

Patterns is a sequence of glob-style patterns

that are used to exclude files"""

def _ignore_patterns(path, names):

ignored_names = []

for pattern in patterns:

ignored_names.extend(fnmatch.filter(names, pattern))

return set(ignored_names)

return _ignore_patterns

def copytree(src, dst, symlinks=False, ignore=None, copy_function=copy2,

ignore_dangling_symlinks=False):

"""Recursively copy a directory tree.

The destination directory must not already exist.

If exception(s) occur, an Error is raised with a list of reasons.

If the optional symlinks flag is true, symbolic links in the

source tree result in symbolic links in the destination tree; if

it is false, the contents of the files pointed to by symbolic

links are copied. If the file pointed by the symlink doesn't

exist, an exception will be added in the list of errors raised in

an Error exception at the end of the copy process.

You can set the optional ignore_dangling_symlinks flag to true if you

want to silence this exception. Notice that this has no effect on

platforms that don't support os.symlink.

The optional ignore argument is a callable. If given, it

is called with the `src` parameter, which is the directory

being visited by copytree(), and `names` which is the list of

`src` contents, as returned by os.listdir():

callable(src, names) -> ignored_names

Since copytree() is called recursively, the callable will be

called once for each directory that is copied. It returns a

list of names relative to the `src` directory that should

not be copied.

The optional copy_function argument is a callable that will be used

to copy each file. It will be called with the source path and the

destination path as arguments. By default, copy2() is used, but any

function that supports the same signature (like copy()) can be used.

"""

names = os.listdir(src)

if ignore is not None:

ignored_names = ignore(src, names)

else:

ignored_names = set()

os.makedirs(dst)

errors = []

for name in names:

if name in ignored_names:

continue

srcname = os.path.join(src, name)

dstname = os.path.join(dst, name)

try:

if os.path.islink(srcname):

linkto = os.readlink(srcname)

if symlinks:

# We can't just leave it to `copy_function` because legacy

# code with a custom `copy_function` may rely on copytree

# doing the right thing.

os.symlink(linkto, dstname)

copystat(srcname, dstname, follow_symlinks=not symlinks)

else:

# ignore dangling symlink if the flag is on

if not os.path.exists(linkto) and ignore_dangling_symlinks:

continue

# otherwise let the copy occurs. copy2 will raise an error

if os.path.isdir(srcname):

copytree(srcname, dstname, symlinks, ignore,

copy_function)

else:

copy_function(srcname, dstname)

elif os.path.isdir(srcname):

copytree(srcname, dstname, symlinks, ignore, copy_function)

else:

# Will raise a SpecialFileError for unsupported file types

copy_function(srcname, dstname)

# catch the Error from the recursive copytree so that we can

# continue with other files

except Error as err:

errors.extend(err.args[0])

except OSError as why:

errors.append((srcname, dstname, str(why)))

try:

copystat(src, dst)

except OSError as why:

# Copying file access times may fail on Windows

if getattr(why, 'winerror', None) is None:

errors.append((src, dst, str(why)))

if errors:

raise Error(errors)

return dst

# version vulnerable to race conditions

def _rmtree_unsafe(path, onerror):

try:

if os.path.islink(path):

# symlinks to directories are forbidden, see bug #1669

raise OSError("Cannot call rmtree on a symbolic link")

except OSError:

onerror(os.path.islink, path, sys.exc_info())

# can't continue even if onerror hook returns

return

names = []

try:

names = os.listdir(path)

except OSError:

onerror(os.listdir, path, sys.exc_info())

for name in names:

fullname = os.path.join(path, name)

try:

mode = os.lstat(fullname).st_mode

except OSError:

mode = 0

if stat.S_ISDIR(mode):

_rmtree_unsafe(fullname, onerror)

else:

try:

os.unlink(fullname)

except OSError:

onerror(os.unlink, fullname, sys.exc_info())

try:

os.rmdir(path)

except OSError:

onerror(os.rmdir, path, sys.exc_info())

# Version using fd-based APIs to protect against races

def _rmtree_safe_fd(topfd, path, onerror):

names = []

try:

names = os.listdir(topfd)

except OSError as err:

err.filename = path

onerror(os.listdir, path, sys.exc_info())

for name in names:

fullname = os.path.join(path, name)

try:

orig_st = os.stat(name, dir_fd=topfd, follow_symlinks=False)

mode = orig_st.st_mode

except OSError:

mode = 0

if stat.S_ISDIR(mode):

try:

dirfd = os.open(name, os.O_RDONLY, dir_fd=topfd)

except OSError:

onerror(os.open, fullname, sys.exc_info())

else:

try:

if os.path.samestat(orig_st, os.fstat(dirfd)):

_rmtree_safe_fd(dirfd, fullname, onerror)

try:

os.rmdir(name, dir_fd=topfd)

except OSError:

onerror(os.rmdir, fullname, sys.exc_info())

else:

try:

# This can only happen if someone replaces

# a directory with a symlink after the call to

# stat.S_ISDIR above.

raise OSError("Cannot call rmtree on a symbolic "

"link")

except OSError:

onerror(os.path.islink, fullname, sys.exc_info())

finally:

os.close(dirfd)

else:

try:

os.unlink(name, dir_fd=topfd)

except OSError:

onerror(os.unlink, fullname, sys.exc_info())

_use_fd_functions = ({os.open, os.stat, os.unlink, os.rmdir} <=

os.supports_dir_fd and

os.listdir in os.supports_fd and

os.stat in os.supports_follow_symlinks)

def rmtree(path, ignore_errors=False, onerror=None):

"""Recursively delete a directory tree.

If ignore_errors is set, errors are ignored; otherwise, if onerror

is set, it is called to handle the error with arguments (func,

path, exc_info) where func is platform and implementation dependent;

path is the argument to that function that caused it to fail; and

exc_info is a tuple returned by sys.exc_info(). If ignore_errors

is false and onerror is None, an exception is raised.

"""

if ignore_errors:

def onerror(*args):

pass

elif onerror is None:

def onerror(*args):

raise

if _use_fd_functions:

# While the unsafe rmtree works fine on bytes, the fd based does not.

if isinstance(path, bytes):

path = os.fsdecode(path)

# Note: To guard against symlink races, we use the standard

# lstat()/open()/fstat() trick.

try:

orig_st = os.lstat(path)

except Exception:

onerror(os.lstat, path, sys.exc_info())

return

try:

fd = os.open(path, os.O_RDONLY)

except Exception:

onerror(os.lstat, path, sys.exc_info())

return

try:

if os.path.samestat(orig_st, os.fstat(fd)):

_rmtree_safe_fd(fd, path, onerror)

try:

os.rmdir(path)

except OSError:

onerror(os.rmdir, path, sys.exc_info())

else:

try:

# symlinks to directories are forbidden, see bug #1669

raise OSError("Cannot call rmtree on a symbolic link")

except OSError:

onerror(os.path.islink, path, sys.exc_info())

finally:

os.close(fd)

else:

return _rmtree_unsafe(path, onerror)

# Allow introspection of whether or not the hardening against symlink

# attacks is supported on the current platform

rmtree.avoids_symlink_attacks = _use_fd_functions

def _basename(path):

# A basename() variant which first strips the trailing slash, if present.

# Thus we always get the last component of the path, even for directories.

sep = os.path.sep + (os.path.altsep or '')

return os.path.basename(path.rstrip(sep))

def move(src, dst, copy_function=copy2):

"""Recursively move a file or directory to another location. This is

similar to the Unix "mv" command. Return the file or directory's

destination.

If the destination is a directory or a symlink to a directory, the source

is moved inside the directory. The destination path must not already

exist.

If the destination already exists but is not a directory, it may be

overwritten depending on os.rename() semantics.

If the destination is on our current filesystem, then rename() is used.

Otherwise, src is copied to the destination and then removed. Symlinks are

recreated under the new name if os.rename() fails because of cross

filesystem renames.

The optional `copy_function` argument is a callable that will be used

to copy the source or it will be delegated to `copytree`.

By default, copy2() is used, but any function that supports the same

signature (like copy()) can be used.

A lot more could be done here... A look at a mv.c shows a lot of

the issues this implementation glosses over.

"""

real_dst = dst

if os.path.isdir(dst):

if _samefile(src, dst):

# We might be on a case insensitive filesystem,

# perform the rename anyway.

os.rename(src, dst)

return

real_dst = os.path.join(dst, _basename(src))

if os.path.exists(real_dst):

raise Error("Destination path '%s' already exists" % real_dst)

try:

os.rename(src, real_dst)

except OSError:

if os.path.islink(src):

linkto = os.readlink(src)

os.symlink(linkto, real_dst)

os.unlink(src)

elif os.path.isdir(src):

if _destinsrc(src, dst):

raise Error("Cannot move a directory '%s' into itself"

" '%s'." % (src, dst))

copytree(src, real_dst, copy_function=copy_function,

symlinks=True)

rmtree(src)

else:

copy_function(src, real_dst)

os.unlink(src)

return real_dst

def _destinsrc(src, dst):

src = os.path.abspath(src)

dst = os.path.abspath(dst)

if not src.endswith(os.path.sep):

src += os.path.sep

if not dst.endswith(os.path.sep):

dst += os.path.sep

return dst.startswith(src)

def _get_gid(name):

"""Returns a gid, given a group name."""

if getgrnam is None or name is None:

return None

try:

result = getgrnam(name)

except KeyError:

result = None

if result is not None:

return result[2]

return None

def _get_uid(name):

"""Returns an uid, given a user name."""

if getpwnam is None or name is None:

return None

try:

result = getpwnam(name)

except KeyError:

result = None

if result is not None:

return result[2]

return None

def _make_tarball(base_name, base_dir, compress="gzip", verbose=0, dry_run=0,

owner=None, group=None, logger=None):

"""Create a (possibly compressed) tar file from all the files under

'base_dir'.

'compress' must be "gzip" (the default), "bzip2", "xz", or None.

'owner' and 'group' can be used to define an owner and a group for the

archive that is being built. If not provided, the current owner and group

will be used.

The output tar file will be named 'base_name' + ".tar", possibly plus

the appropriate compression extension (".gz", ".bz2", or ".xz").

Returns the output filename.

"""

if compress is None:

tar_compression = ''

elif _ZLIB_SUPPORTED and compress == 'gzip':

tar_compression = 'gz'

elif _BZ2_SUPPORTED and compress == 'bzip2':

tar_compression = 'bz2'

elif _LZMA_SUPPORTED and compress == 'xz':

tar_compression = 'xz'

else:

raise ValueError("bad value for 'compress', or compression format not "

"supported : {0}".format(compress))

import tarfile # late import for breaking circular dependency

compress_ext = '.' + tar_compression if compress else ''

archive_name = base_name + '.tar' + compress_ext

archive_dir = os.path.dirname(archive_name)

if archive_dir and not os.path.exists(archive_dir):

if logger is not None:

logger.info("creating %s", archive_dir)

if not dry_run:

os.makedirs(archive_dir)

# creating the tarball

if logger is not None:

logger.info('Creating tar archive')

uid = _get_uid(owner)

gid = _get_gid(group)

def _set_uid_gid(tarinfo):

if gid is not None:

tarinfo.gid = gid

tarinfo.gname = group

if uid is not None:

tarinfo.uid = uid

tarinfo.uname = owner

return tarinfo

if not dry_run:

tar = tarfile.open(archive_name, 'w|%s' % tar_compression)

try:

tar.add(base_dir, filter=_set_uid_gid)

finally:

tar.close()

return archive_name

def _make_zipfile(base_name, base_dir, verbose=0, dry_run=0, logger=None):

"""Create a zip file from all the files under 'base_dir'.

The output zip file will be named 'base_name' + ".zip". Returns the

name of the output zip file.

"""

import zipfile # late import for breaking circular dependency

zip_filename = base_name + ".zip"

archive_dir = os.path.dirname(base_name)

if archive_dir and not os.path.exists(archive_dir):

if logger is not None:

logger.info("creating %s", archive_dir)

if not dry_run:

os.makedirs(archive_dir)

if logger is not None:

logger.info("creating '%s' and adding '%s' to it",

zip_filename, base_dir)

if not dry_run:

with zipfile.ZipFile(zip_filename, "w",

compression=zipfile.ZIP_DEFLATED) as zf:

path = os.path.normpath(base_dir)

if path != os.curdir:

zf.write(path, path)

if logger is not None:

logger.info("adding '%s'", path)

for dirpath, dirnames, filenames in os.walk(base_dir):

for name in sorted(dirnames):

path = os.path.normpath(os.path.join(dirpath, name))

zf.write(path, path)

if logger is not None:

logger.info("adding '%s'", path)

for name in filenames:

path = os.path.normpath(os.path.join(dirpath, name))

if os.path.isfile(path):

zf.write(path, path)

if logger is not None:

logger.info("adding '%s'", path)

return zip_filename

_ARCHIVE_FORMATS = {

'tar': (_make_tarball, [('compress', None)], "uncompressed tar file"),

}

if _ZLIB_SUPPORTED:

_ARCHIVE_FORMATS['gztar'] = (_make_tarball, [('compress', 'gzip')],

"gzip'ed tar-file")

_ARCHIVE_FORMATS['zip'] = (_make_zipfile, [], "ZIP file")

if _BZ2_SUPPORTED:

_ARCHIVE_FORMATS['bztar'] = (_make_tarball, [('compress', 'bzip2')],

"bzip2'ed tar-file")

if _LZMA_SUPPORTED:

_ARCHIVE_FORMATS['xztar'] = (_make_tarball, [('compress', 'xz')],

"xz'ed tar-file")

def get_archive_formats():

"""Returns a list of supported formats for archiving and unarchiving.

Each element of the returned sequence is a tuple (name, description)

"""

formats = [(name, registry[2]) for name, registry in

_ARCHIVE_FORMATS.items()]

formats.sort()

return formats

def register_archive_format(name, function, extra_args=None, description=''):

"""Registers an archive format.

name is the name of the format. function is the callable that will be

used to create archives. If provided, extra_args is a sequence of

(name, value) tuples that will be passed as arguments to the callable.

description can be provided to describe the format, and will be returned

by the get_archive_formats() function.

"""

if extra_args is None:

extra_args = []

if not callable(function):

raise TypeError('The %s object is not callable' % function)

if not isinstance(extra_args, (tuple, list)):

raise TypeError('extra_args needs to be a sequence')

for element in extra_args:

if not isinstance(element, (tuple, list)) or len(element) !=2:

raise TypeError('extra_args elements are : (arg_name, value)')

_ARCHIVE_FORMATS[name] = (function, extra_args, description)

def unregister_archive_format(name):

del _ARCHIVE_FORMATS[name]

def make_archive(base_name, format, root_dir=None, base_dir=None, verbose=0,

dry_run=0, owner=None, group=None, logger=None):

"""Create an archive file (eg. zip or tar).

'base_name' is the name of the file to create, minus any format-specific

extension; 'format' is the archive format: one of "zip", "tar", "gztar",

"bztar", or "xztar". Or any other registered format.

'root_dir' is a directory that will be the root directory of the

archive; ie. we typically chdir into 'root_dir' before creating the

archive. 'base_dir' is the directory where we start archiving from;

ie. 'base_dir' will be the common prefix of all files and

directories in the archive. 'root_dir' and 'base_dir' both default

to the current directory. Returns the name of the archive file.

'owner' and 'group' are used when creating a tar archive. By default,

uses the current owner and group.

"""

save_cwd = os.getcwd()

if root_dir is not None:

if logger is not None:

logger.debug("changing into '%s'", root_dir)

base_name = os.path.abspath(base_name)

if not dry_run:

os.chdir(root_dir)

if base_dir is None:

base_dir = os.curdir

kwargs = {'dry_run': dry_run, 'logger': logger}

try:

format_info = _ARCHIVE_FORMATS[format]

except KeyError:

raise ValueError("unknown archive format '%s'" % format)

func = format_info[0]

for arg, val in format_info[1]:

kwargs[arg] = val

if format != 'zip':

kwargs['owner'] = owner

kwargs['group'] = group

try:

filename = func(base_name, base_dir, **kwargs)

finally:

if root_dir is not None:

if logger is not None:

logger.debug("changing back to '%s'", save_cwd)

os.chdir(save_cwd)

return filename

def get_unpack_formats():

"""Returns a list of supported formats for unpacking.

Each element of the returned sequence is a tuple

(name, extensions, description)

"""

formats = [(name, info[0], info[3]) for name, info in

_UNPACK_FORMATS.items()]

formats.sort()

return formats

def _check_unpack_options(extensions, function, extra_args):

"""Checks what gets registered as an unpacker."""

# first make sure no other unpacker is registered for this extension

existing_extensions = {}

for name, info in _UNPACK_FORMATS.items():

for ext in info[0]:

existing_extensions[ext] = name

for extension in extensions:

if extension in existing_extensions:

msg = '%s is already registered for "%s"'

raise RegistryError(msg % (extension,

existing_extensions[extension]))

if not callable(function):

raise TypeError('The registered function must be a callable')

def register_unpack_format(name, extensions, function, extra_args=None,

description=''):

"""Registers an unpack format.

`name` is the name of the format. `extensions` is a list of extensions

corresponding to the format.

`function` is the callable that will be

used to unpack archives. The callable will receive archives to unpack.

If it's unable to handle an archive, it needs to raise a ReadError

exception.

If provided, `extra_args` is a sequence of

(name, value) tuples that will be passed as arguments to the callable.

description can be provided to describe the format, and will be returned

by the get_unpack_formats() function.

"""

if extra_args is None:

extra_args = []

_check_unpack_options(extensions, function, extra_args)

_UNPACK_FORMATS[name] = extensions, function, extra_args, description

def unregister_unpack_format(name):

"""Removes the pack format from the registry."""

del _UNPACK_FORMATS[name]

def _ensure_directory(path):

"""Ensure that the parent directory of `path` exists"""

dirname = os.path.dirname(path)

if not os.path.isdir(dirname):

os.makedirs(dirname)

def _unpack_zipfile(filename, extract_dir):

"""Unpack zip `filename` to `extract_dir`

"""

import zipfile # late import for breaking circular dependency

if not zipfile.is_zipfile(filename):

raise ReadError("%s is not a zip file" % filename)

zip = zipfile.ZipFile(filename)

try:

for info in zip.infolist():

name = info.filename

# don't extract absolute paths or ones with .. in them

if name.startswith('/') or '..' in name:

continue

target = os.path.join(extract_dir, *name.split('/'))

if not target:

continue

_ensure_directory(target)

if not name.endswith('/'):

# file

data = zip.read(info.filename)

f = open(target, 'wb')

try:

f.write(data)

finally:

f.close()

del data

finally:

zip.close()

def _unpack_tarfile(filename, extract_dir):

"""Unpack tar/tar.gz/tar.bz2/tar.xz `filename` to `extract_dir`

"""

import tarfile # late import for breaking circular dependency

try:

tarobj = tarfile.open(filename)

except tarfile.TarError:

raise ReadError(

"%s is not a compressed or uncompressed tar file" % filename)

try:

tarobj.extractall(extract_dir)

finally:

tarobj.close()

_UNPACK_FORMATS = {

'tar': (['.tar'], _unpack_tarfile, [], "uncompressed tar file"),

'zip': (['.zip'], _unpack_zipfile, [], "ZIP file"),

}

if _ZLIB_SUPPORTED:

_UNPACK_FORMATS['gztar'] = (['.tar.gz', '.tgz'], _unpack_tarfile, [],

"gzip'ed tar-file")

if _BZ2_SUPPORTED:

_UNPACK_FORMATS['bztar'] = (['.tar.bz2', '.tbz2'], _unpack_tarfile, [],

"bzip2'ed tar-file")

if _LZMA_SUPPORTED:

_UNPACK_FORMATS['xztar'] = (['.tar.xz', '.txz'], _unpack_tarfile, [],

"xz'ed tar-file")

def _find_unpack_format(filename):

for name, info in _UNPACK_FORMATS.items():

for extension in info[0]:

if filename.endswith(extension):

return name

return None

def unpack_archive(filename, extract_dir=None, format=None):

"""Unpack an archive.

`filename` is the name of the archive.

`extract_dir` is the name of the target directory, where the archive

is unpacked. If not provided, the current working directory is used.

`format` is the archive format: one of "zip", "tar", "gztar", "bztar",

or "xztar". Or any other registered format. If not provided,

unpack_archive will use the filename extension and see if an unpacker

was registered for that extension.

In case none is found, a ValueError is raised.

"""

if extract_dir is None:

extract_dir = os.getcwd()

if format is not None:

try:

format_info = _UNPACK_FORMATS[format]

except KeyError:

raise ValueError("Unknown unpack format '{0}'".format(format))

func = format_info[1]

func(filename, extract_dir, **dict(format_info[2]))

else:

# we need to look at the registered unpackers supported extensions

format = _find_unpack_format(filename)

if format is None:

raise ReadError("Unknown archive format '{0}'".format(filename))

func = _UNPACK_FORMATS[format][1]

kwargs = dict(_UNPACK_FORMATS[format][2])

func(filename, extract_dir, **kwargs)

if hasattr(os, 'statvfs'):

__all__.append('disk_usage')

_ntuple_diskusage = collections.namedtuple('usage', 'total used free')

def disk_usage(path):

"""Return disk usage statistics about the given path.

Returned value is a named tuple with attributes 'total', 'used' and

'free', which are the amount of total, used and free space, in bytes.

"""

st = os.statvfs(path)

free = st.f_bavail * st.f_frsize

total = st.f_blocks * st.f_frsize

used = (st.f_blocks - st.f_bfree) * st.f_frsize

return _ntuple_diskusage(total, used, free)

elif os.name == 'nt':

import nt

__all__.append('disk_usage')

View remainder of file in raw view

cpython/Lib/shutil.py at 3.5 · python/cpython · GitHub

Repository navigation

Expand file tree

Breadcrumbs

shutil.py

Latest commit

History

Breadcrumbs

shutil.py

File metadata and controls