cpython/Lib/glob.py at main · 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

"""Filename globbing utility."""

import contextlib

import os

import re

import fnmatch

import functools

import itertools

import operator

import stat

import sys

__all__ = ["glob", "iglob", "escape", "translate"]

def glob(pathname, *, root_dir=None, dir_fd=None, recursive=False,

include_hidden=False):

"""Return a list of paths matching a `pathname` pattern.

The pattern may contain simple shell-style wildcards a la

fnmatch. Unlike fnmatch, filenames starting with a

dot are special cases that are not matched by '*' and '?'

patterns by default.

The order of the returned list is undefined. Sort it if you need a

particular order.

If `root_dir` is not None, it should be a path-like object specifying

the root directory for searching. It has the same effect as changing

the current directory before calling it (without actually changing it).

If pathname is relative, the result will contain paths relative to

`root_dir`.

If `dir_fd` is not None, it should be a file descriptor referring to a

directory, and paths will then be relative to that directory.

If `include_hidden` is true, wildcards can match path segments beginning

with a dot ('.').

If `recursive` is true, the pattern '**' will match any files and

zero or more directories and subdirectories.

"""

return list(iglob(pathname, root_dir=root_dir, dir_fd=dir_fd, recursive=recursive,

include_hidden=include_hidden))

def iglob(pathname, *, root_dir=None, dir_fd=None, recursive=False,

include_hidden=False):

"""Return an iterator which yields the paths matching a `pathname` pattern.

The pattern may contain simple shell-style wildcards a la

fnmatch. However, unlike fnmatch, filenames starting with a

dot are special cases that are not matched by '*' and '?'

patterns.

The order of the returned paths is undefined. Sort them if you need a

particular order.

If `root_dir` is not None, it should be a path-like object specifying

the root directory for searching. It has the same effect as changing

the current directory before calling it (without actually changing it).

If pathname is relative, the result will contain paths relative to

`root_dir`.

If `dir_fd` is not None, it should be a file descriptor referring to a

directory, and paths will then be relative to that directory.

If `include_hidden` is true, wildcards can match path segments beginning

with a dot ('.').

If `recursive` is true, the pattern '**' will match any files and

zero or more directories and subdirectories.

"""

sys.audit("glob.glob", pathname, recursive)

sys.audit("glob.glob/2", pathname, recursive, root_dir, dir_fd)

if root_dir is not None:

root_dir = os.fspath(root_dir)

else:

root_dir = pathname[:0]

it = _iglob(pathname, root_dir, dir_fd, recursive, False,

include_hidden=include_hidden)

if not pathname or recursive and _isrecursive(pathname[:2]):

try:

s = next(it) # skip empty string

if s:

it = itertools.chain((s,), it)

except StopIteration:

pass

return it

def _iglob(pathname, root_dir, dir_fd, recursive, dironly,

include_hidden=False):

dirname, basename = os.path.split(pathname)

if not has_magic(pathname):

assert not dironly

if basename:

if _lexists(_join(root_dir, pathname), dir_fd):

yield pathname

else:

# Patterns ending with a slash should match only directories

if _isdir(_join(root_dir, dirname), dir_fd):

yield pathname

return

if not dirname:

if recursive and _isrecursive(basename):

yield from _glob2(root_dir, basename, dir_fd, dironly,

include_hidden=include_hidden)

else:

yield from _glob1(root_dir, basename, dir_fd, dironly,

include_hidden=include_hidden)

return

# `os.path.split()` returns the argument itself as a dirname if it is a

# drive or UNC path. Prevent an infinite recursion if a drive or UNC path

# contains magic characters (i.e. r'\\?\C:').

if dirname != pathname and has_magic(dirname):

dirs = _iglob(dirname, root_dir, dir_fd, recursive, True,

include_hidden=include_hidden)

else:

dirs = [dirname]

if has_magic(basename):

if recursive and _isrecursive(basename):

glob_in_dir = _glob2

else:

glob_in_dir = _glob1

else:

glob_in_dir = _glob0

for dirname in dirs:

for name in glob_in_dir(_join(root_dir, dirname), basename, dir_fd, dironly,

include_hidden=include_hidden):

yield os.path.join(dirname, name)

# These 2 helper functions non-recursively glob inside a literal directory.

# They return a list of basenames. _glob1 accepts a pattern while _glob0

# takes a literal basename (so it only has to check for its existence).

def _glob1(dirname, pattern, dir_fd, dironly, include_hidden=False):

names = _listdir(dirname, dir_fd, dironly)

if not (include_hidden or _ishidden(pattern)):

names = (x for x in names if not _ishidden(x))

return fnmatch.filter(names, pattern)

def _glob0(dirname, basename, dir_fd, dironly, include_hidden=False):

if basename:

if _lexists(_join(dirname, basename), dir_fd):

return [basename]

else:

# `os.path.split()` returns an empty basename for paths ending with a

# directory separator. 'q*x/' should match only directories.

if _isdir(dirname, dir_fd):

return [basename]

return []

# This helper function recursively yields relative pathnames inside a literal

# directory.

def _glob2(dirname, pattern, dir_fd, dironly, include_hidden=False):

assert _isrecursive(pattern)

if not dirname or _isdir(dirname, dir_fd):

yield pattern[:0]

yield from _rlistdir(dirname, dir_fd, dironly,

include_hidden=include_hidden)

# If dironly is false, yields all file names inside a directory.

# If dironly is true, yields only directory names.

def _iterdir(dirname, dir_fd, dironly):

try:

fd = None

fsencode = None

if dir_fd is not None:

if dirname:

fd = arg = os.open(dirname, _dir_open_flags, dir_fd=dir_fd)

else:

arg = dir_fd

if isinstance(dirname, bytes):

fsencode = os.fsencode

elif dirname:

arg = dirname

elif isinstance(dirname, bytes):

arg = bytes(os.curdir, 'ASCII')

else:

arg = os.curdir

try:

with os.scandir(arg) as it:

for entry in it:

try:

if not dironly or entry.is_dir():

if fsencode is not None:

yield fsencode(entry.name)

else:

yield entry.name

except OSError:

pass

finally:

if fd is not None:

os.close(fd)

except OSError:

return

def _listdir(dirname, dir_fd, dironly):

with contextlib.closing(_iterdir(dirname, dir_fd, dironly)) as it:

return list(it)

# Recursively yields relative pathnames inside a literal directory.

def _rlistdir(dirname, dir_fd, dironly, include_hidden=False):

names = _listdir(dirname, dir_fd, dironly)

for x in names:

if include_hidden or not _ishidden(x):

yield x

path = _join(dirname, x) if dirname else x

for y in _rlistdir(path, dir_fd, dironly,

include_hidden=include_hidden):

yield _join(x, y)

def _lexists(pathname, dir_fd):

# Same as os.path.lexists(), but with dir_fd

if dir_fd is None:

return os.path.lexists(pathname)

try:

os.lstat(pathname, dir_fd=dir_fd)

except (OSError, ValueError):

return False

else:

return True

def _isdir(pathname, dir_fd):

# Same as os.path.isdir(), but with dir_fd

if dir_fd is None:

return os.path.isdir(pathname)

try:

st = os.stat(pathname, dir_fd=dir_fd)

except (OSError, ValueError):

return False

else:

return stat.S_ISDIR(st.st_mode)

def _join(dirname, basename):

# It is common if dirname or basename is empty

if not dirname or not basename:

return dirname or basename

return os.path.join(dirname, basename)

magic_check = re.compile('([*?[])')

magic_check_bytes = re.compile(b'([*?[])')

def has_magic(s):

if isinstance(s, bytes):

match = magic_check_bytes.search(s)

else:

match = magic_check.search(s)

return match is not None

def _ishidden(path):

return path[0] in ('.', b'.'[0])

def _isrecursive(pattern):

if isinstance(pattern, bytes):

return pattern == b'**'

else:

return pattern == '**'

def escape(pathname):

"""Escape all special characters.

"""

# Escaping is done by wrapping any of "*?[" between square brackets.

# Metacharacters do not work in the drive part and shouldn't be escaped.

drive, pathname = os.path.splitdrive(pathname)

if isinstance(pathname, bytes):

pathname = magic_check_bytes.sub(br'[\1]', pathname)

else:

pathname = magic_check.sub(r'[\1]', pathname)

return drive + pathname

_special_parts = ('', '.', '..')

_dir_open_flags = os.O_RDONLY | getattr(os, 'O_DIRECTORY', 0)

_no_recurse_symlinks = object()

def translate(pat, *, recursive=False, include_hidden=False, seps=None):

"""Translate a pathname with shell wildcards to a regular expression.

If `recursive` is true, the pattern segment '**' will match any number

of path segments.

If `include_hidden` is true, wildcards can match path segments beginning

with a dot ('.').

If a sequence of separator characters is given to `seps`, they will be

used to split the pattern into segments and match path separators. If

not given, os.path.sep and os.path.altsep (where available) are used.

"""

if not seps:

if os.path.altsep:

seps = (os.path.sep, os.path.altsep)

else:

seps = os.path.sep

escaped_seps = ''.join(map(re.escape, seps))

any_sep = f'[{escaped_seps}]' if len(seps) > 1 else escaped_seps

not_sep = f'[^{escaped_seps}]'

if include_hidden:

one_last_segment = f'{not_sep}+'

one_segment = f'{one_last_segment}{any_sep}'

any_segments = f'(?:.+{any_sep})?'

any_last_segments = '.*'

else:

one_last_segment = f'[^{escaped_seps}.]{not_sep}*'

one_segment = f'{one_last_segment}{any_sep}'

any_segments = f'(?:{one_segment})*'

any_last_segments = f'{any_segments}(?:{one_last_segment})?'

results = []

parts = re.split(any_sep, pat)

last_part_idx = len(parts) - 1

for idx, part in enumerate(parts):

if part == '*':

results.append(one_segment if idx < last_part_idx else one_last_segment)

elif recursive and part == '**':

if idx < last_part_idx:

if parts[idx + 1] != '**':

results.append(any_segments)

else:

results.append(any_last_segments)

else:

if part:

if not include_hidden and part[0] in '*?':

results.append(r'(?!\.)')

results.extend(fnmatch._translate(part, f'{not_sep}*', not_sep)[0])

if idx < last_part_idx:

results.append(any_sep)

res = ''.join(results)

return fr'(?s:{res})\z'

@functools.lru_cache(maxsize=512)

def _compile_pattern(pat, seps, case_sensitive, recursive=True):

"""Compile given glob pattern to a re.Pattern object (observing case

sensitivity)."""

flags = re.NOFLAG if case_sensitive else re.IGNORECASE

regex = translate(pat, recursive=recursive, include_hidden=True, seps=seps)

return re.compile(regex, flags=flags).match

class _GlobberBase:

"""Abstract class providing shell-style pattern matching and globbing.

"""

def __init__(self, sep, case_sensitive, case_pedantic=False, recursive=False):

self.sep = sep

self.case_sensitive = case_sensitive

self.case_pedantic = case_pedantic

self.recursive = recursive

# Abstract methods

@staticmethod

def lexists(path):

"""Implements os.path.lexists().

"""

raise NotImplementedError

@staticmethod

def scandir(path):

"""Like os.scandir(), but generates (entry, name, path) tuples.

"""

raise NotImplementedError

@staticmethod

def concat_path(path, text):

"""Implements path concatenation.

"""

raise NotImplementedError

@staticmethod

def stringify_path(path):

"""Converts the path to a string object

"""

raise NotImplementedError

# High-level methods

def compile(self, pat, altsep=None):

seps = (self.sep, altsep) if altsep else self.sep

return _compile_pattern(pat, seps, self.case_sensitive, self.recursive)

def selector(self, parts):

"""Returns a function that selects from a given path, walking and

filtering according to the glob-style pattern parts in *parts*.

"""

if not parts:

return self.select_exists

part = parts.pop()

if self.recursive and part == '**':

selector = self.recursive_selector

elif part in _special_parts:

selector = self.special_selector

elif not self.case_pedantic and magic_check.search(part) is None:

selector = self.literal_selector

else:

selector = self.wildcard_selector

return selector(part, parts)

def special_selector(self, part, parts):

"""Returns a function that selects special children of the given path.

"""

if parts:

part += self.sep

select_next = self.selector(parts)

def select_special(path, exists=False):

path = self.concat_path(path, part)

return select_next(path, exists)

return select_special

def literal_selector(self, part, parts):

"""Returns a function that selects a literal descendant of a path.

"""

# Optimization: consume and join any subsequent literal parts here,

# rather than leaving them for the next selector. This reduces the

# number of string concatenation operations.

while parts and magic_check.search(parts[-1]) is None:

part += self.sep + parts.pop()

if parts:

part += self.sep

select_next = self.selector(parts)

def select_literal(path, exists=False):

path = self.concat_path(path, part)

return select_next(path, exists=False)

return select_literal

def wildcard_selector(self, part, parts):

"""Returns a function that selects direct children of a given path,

filtering by pattern.

"""

match = None if part == '*' else self.compile(part)

dir_only = bool(parts)

if dir_only:

select_next = self.selector(parts)

def select_wildcard(path, exists=False):

try:

entries = self.scandir(path)

except OSError:

pass

else:

for entry, entry_name, entry_path in entries:

if match is None or match(entry_name):

if dir_only:

try:

if not entry.is_dir():

continue

except OSError:

continue

entry_path = self.concat_path(entry_path, self.sep)

yield from select_next(entry_path, exists=True)

else:

yield entry_path

return select_wildcard

def recursive_selector(self, part, parts):

"""Returns a function that selects a given path and all its children,

recursively, filtering by pattern.

"""

# Optimization: consume following '**' parts, which have no effect.

while parts and parts[-1] == '**':

parts.pop()

# Optimization: consume and join any following non-special parts here,

# rather than leaving them for the next selector. They're used to

# build a regular expression, which we use to filter the results of

# the recursive walk. As a result, non-special pattern segments

# following a '**' wildcard don't require additional filesystem access

# to expand.

follow_symlinks = self.recursive is not _no_recurse_symlinks

if follow_symlinks:

while parts and parts[-1] not in _special_parts:

part += self.sep + parts.pop()

match = None if part == '**' else self.compile(part)

dir_only = bool(parts)

select_next = self.selector(parts)

def select_recursive(path, exists=False):

path_str = self.stringify_path(path)

match_pos = len(path_str)

if match is None or match(path_str, match_pos):

yield from select_next(path, exists)

stack = [path]

while stack:

yield from select_recursive_step(stack, match_pos)

def select_recursive_step(stack, match_pos):

path = stack.pop()

try:

entries = self.scandir(path)

except OSError:

pass

else:

for entry, _entry_name, entry_path in entries:

is_dir = False

try:

if entry.is_dir(follow_symlinks=follow_symlinks):

is_dir = True

except OSError:

pass

if is_dir or not dir_only:

entry_path_str = self.stringify_path(entry_path)

if dir_only:

entry_path = self.concat_path(entry_path, self.sep)

if match is None or match(entry_path_str, match_pos):

if dir_only:

yield from select_next(entry_path, exists=True)

else:

# Optimization: directly yield the path if this is

# last pattern part.

yield entry_path

if is_dir:

stack.append(entry_path)

return select_recursive

def select_exists(self, path, exists=False):

"""Yields the given path, if it exists.

"""

if exists:

# Optimization: this path is already known to exist, e.g. because

# it was returned from os.scandir(), so we skip calling lstat().

yield path

elif self.lexists(path):

yield path

class _StringGlobber(_GlobberBase):

"""Provides shell-style pattern matching and globbing for string paths.

"""

lexists = staticmethod(os.path.lexists)

concat_path = operator.add

@staticmethod

def scandir(path):

# We must close the scandir() object before proceeding to

# avoid exhausting file descriptors when globbing deep trees.

with os.scandir(path) as scandir_it:

entries = list(scandir_it)

return ((entry, entry.name, entry.path) for entry in entries)

@staticmethod

def stringify_path(path):

return path # Already a string.

cpython/Lib/glob.py at main · python/cpython · GitHub

Repository navigation

Expand file tree

Breadcrumbs

glob.py

Latest commit

History

Breadcrumbs

glob.py

File metadata and controls