GitPython/git/repo/fun.py at 3.1.62 · gitpython-developers/GitPython · 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

# This module is part of GitPython and is released under the

# 3-Clause BSD License: https://opensource.org/license/bsd-3-clause/

"""General repository-related functions."""

from __future__ import annotations

__all__ = [

"rev_parse",

"is_git_dir",

"touch",

"find_submodule_git_dir",

"name_to_object",

"short_to_long",

"deref_tag",

"to_commit",

"find_worktree_git_dir",

]

import os

import os.path as osp

from pathlib import Path

import re

import stat

from string import digits

from gitdb.exc import BadName, BadObject

from git.cmd import Git

from git.exc import WorkTreeRepositoryUnsupported

from git.objects import Object

from git.objects.util import parse_date

from git.refs import SymbolicReference

from git.util import cygpath, bin_to_hex, hex_to_bin

# Typing ----------------------------------------------------------------------

from typing import Iterator, Optional, TYPE_CHECKING, Tuple, Union, cast, overload

from git.types import AnyGitObject, Literal, PathLike

if TYPE_CHECKING:

from git.db import GitCmdObjectDB

from git.objects import Commit

from git.refs.reference import Reference

from git.refs.log import RefLog, RefLogEntry

from git.refs.tag import Tag

from .base import Repo

# ----------------------------------------------------------------------------

def touch(filename: str) -> str:

with open(filename, "ab"):

pass

return filename

def is_git_dir(d: PathLike) -> bool:

"""This is taken from the git setup.c:is_git_directory function.

.. note::

This function recognizes repositories using reftable through their

compatibility files, but GitPython's direct reference access does not support

reftable.

:raise git.exc.WorkTreeRepositoryUnsupported:

If it sees a worktree directory. It's quite hacky to do that here, but at least

clearly indicates that we don't support it. There is the unlikely danger to

throw if we see directories which just look like a worktree dir, but are none.

"""

if osp.isdir(d):

headref = osp.join(d, "HEAD")

if osp.islink(headref):

try:

valid_head = os.readlink(headref).startswith("refs/")

except OSError:

valid_head = False

else:

try:

with open(headref, "rb") as fp:

head = fp.read(256)

except OSError:

valid_head = False

else:

valid_head = (head.startswith(b"ref:") and head[4:].lstrip().startswith(b"refs/")) or bool(

re.match(rb"(?:[0-9A-Fa-f]{64}|[0-9A-Fa-f]{40})", head)

)

common_dir = os.getenv("GIT_COMMON_DIR")

if common_dir == "":

return False

if common_dir is None:

common_dir_file = Path(d) / "commondir"

try:

common_dir = os.fsdecode(common_dir_file.read_bytes()).rstrip("\r\n")

except FileNotFoundError:

if osp.lexists(common_dir_file):

return False

common_dir = os.fspath(d)

except (OSError, UnicodeError):

return False

else:

if not common_dir:

return False

try:

common_dir = osp.realpath(osp.join(d, common_dir))

except (OSError, ValueError):

return False

object_dir = os.getenv("GIT_OBJECT_DIRECTORY")

if object_dir is None:

object_dir = osp.join(common_dir, "objects")

if valid_head and osp.isdir(object_dir) and osp.isdir(osp.join(common_dir, "refs")):

return True

if osp.isfile(osp.join(d, "gitdir")) and osp.isfile(osp.join(d, "commondir")) and osp.isfile(headref):

raise WorkTreeRepositoryUnsupported(d)

return False

def find_worktree_git_dir(dotgit: PathLike) -> Optional[str]:

"""Search for a gitdir for this worktree."""

try:

statbuf = os.stat(dotgit)

except (FileNotFoundError, NotADirectoryError):

return None

if not stat.S_ISREG(statbuf.st_mode) or statbuf.st_size > (1 << 20):

return None

try:

with open(dotgit, "rb") as fp:

content_bytes = fp.read(statbuf.st_size)

if len(content_bytes) != statbuf.st_size:

return None

content = os.fsdecode(content_bytes).rstrip("\r\n")

except (OSError, UnicodeError):

return None

return content[8:] if len(content) >= 9 and content.startswith("gitdir: ") else None

def find_submodule_git_dir(d: PathLike) -> Optional[PathLike]:

"""Search for a submodule repo."""

if is_git_dir(d):

return d

path = find_worktree_git_dir(d)

if path is None:

return None

if Git.is_cygwin():

# Cygwin creates submodules prefixed with `/cygdrive/...`.

# Cygwin git understands Cygwin paths much better than Windows ones.

# Also the Cygwin tests are assuming Cygwin paths.

path = cygpath(path)

if not osp.isabs(path):

path = osp.normpath(osp.join(osp.dirname(d), path))

return path if is_git_dir(path) else None

def short_to_long(odb: "GitCmdObjectDB", hexsha: str) -> Optional[bytes]:

"""

:return:

Long hexadecimal sha1 from the given less than 40 byte hexsha, or ``None`` if no

candidate could be found.

:param hexsha:

hexsha with less than 40 bytes.

"""

try:

return bin_to_hex(odb.partial_to_complete_sha_hex(hexsha))

except BadObject:

return None

# END exception handling

def _describe_to_long(repo: "Repo", name: str) -> Optional[bytes]:

"""Resolve git-describe style names to the abbreviated object they contain."""

match = re.match(r"^.+-\d+-g([0-9A-Fa-f]{4,40})(?:-dirty)?$", name)

if match is None:

match = re.match(r"^.+-g([0-9A-Fa-f]{4,40})(?:-dirty)?$", name)

if match is None:

match = re.match(r"^([0-9A-Fa-f]{4,40})-dirty$", name)

if match is None:

return None

# END handle match

hexsha = match.group(1)

if len(hexsha) == 40:

return hexsha.encode("ascii")

return short_to_long(repo.odb, hexsha)

@overload

def name_to_object(repo: "Repo", name: str, return_ref: Literal[False] = ...) -> AnyGitObject: ...

@overload

def name_to_object(repo: "Repo", name: str, return_ref: Literal[True]) -> Union[AnyGitObject, SymbolicReference]: ...

def name_to_object(repo: "Repo", name: str, return_ref: bool = False) -> Union[AnyGitObject, SymbolicReference]:

"""

:return:

Object specified by the given name - hexshas (short and long) as well as

references are supported.

:param return_ref:

If ``True``, and name specifies a reference, we will return the reference

instead of the object. Otherwise it will raise :exc:`~gitdb.exc.BadObject` or

:exc:`~gitdb.exc.BadName`.

"""

hexsha: Union[None, str, bytes] = None

# Is it a hexsha? Try the most common ones, which is 7 to 40.

if repo.re_hexsha_shortened.match(name):

if len(name) != 40:

# Find long sha for short sha.

hexsha = short_to_long(repo.odb, name)

else:

hexsha = name

# END handle short shas

# END find sha if it matches

# If we couldn't find an object for what seemed to be a short hexsha, try to find it

# as reference anyway, it could be named 'aaa' for instance.

if hexsha is None:

for base in (

"%s",

"refs/%s",

"refs/tags/%s",

"refs/heads/%s",

"refs/remotes/%s",

"refs/remotes/%s/HEAD",

try:

hexsha = SymbolicReference.dereference_recursive(repo, base % name)

if return_ref:

return SymbolicReference(repo, base % name)

# END handle symbolic ref

break

except ValueError:

pass

# END for each base

# END handle hexsha

if hexsha is None:

hexsha = _describe_to_long(repo, name)

# END handle describe output

# Didn't find any ref, this is an error.

if return_ref:

raise BadObject("Couldn't find reference named %r" % name)

# END handle return ref

# Tried everything ? fail.

if hexsha is None:

raise BadName(name)

# END assert hexsha was found

return Object.new_from_sha(repo, hex_to_bin(hexsha))

def deref_tag(tag: "Tag") -> AnyGitObject:

"""Recursively dereference a tag and return the resulting object."""

while True:

try:

tag = tag.object

except AttributeError:

break

# END dereference tag

return tag

def to_commit(obj: Object) -> "Commit":

"""Convert the given object to a commit if possible and return it."""

if obj.type == "tag":

obj = deref_tag(obj)

if obj.type != "commit":

raise ValueError("Cannot convert object %r to type commit" % obj)

# END verify type

return obj

def _object_from_hexsha(repo: "Repo", hexsha: str) -> AnyGitObject:

return Object.new_from_sha(repo, hex_to_bin(hexsha))

def _current_reflog_ref(repo: "Repo") -> SymbolicReference:

try:

return repo.head.ref

except TypeError:

return repo.head

# END handle detached head

def _common_reflog_path(repo: "Repo", ref: SymbolicReference) -> Optional[str]:

if repo.common_dir == repo.git_dir:

return None

# END handle normal repository

return SymbolicReference._get_validated_path(osp.join(repo.common_dir, "logs"), ref.path)

def _ref_log(repo: "Repo", ref: SymbolicReference) -> "RefLog":

try:

return ref.log()

except FileNotFoundError:

common_path = _common_reflog_path(repo, ref)

if common_path and osp.isfile(common_path):

from git.refs.log import RefLog

return RefLog.from_file(common_path)

# END handle linked-worktree branch logs

try:

if ref.path == repo.head.ref.path:

return repo.head.log()

# END handle linked-worktree current branch logs

except TypeError:

pass

# END handle detached head

raise

# END handle missing branch log

def _ref_log_entry(repo: "Repo", ref: SymbolicReference, index: int) -> "RefLogEntry":

try:

return ref.log_entry(index)

except FileNotFoundError:

common_path = _common_reflog_path(repo, ref)

if common_path and osp.isfile(common_path):

from git.refs.log import RefLog

return RefLog.entry_at(common_path, index)

# END handle linked-worktree branch logs

try:

if ref.path == repo.head.ref.path:

return repo.head.log_entry(index)

# END handle linked-worktree current branch logs

except TypeError:

pass

# END handle detached head

raise

# END handle missing branch log

def _find_reflog_entry_by_date(repo: "Repo", ref: SymbolicReference, spec: str) -> str:

try:

timestamp, _offset = parse_date(spec)

except ValueError as e:

raise NotImplementedError("Support for additional @{...} modes not implemented") from e

# END handle unsupported dates

log = _ref_log(repo, ref)

if not log:

raise IndexError("Invalid revlog date: %s" % spec)

# END handle empty log

for entry in reversed(log):

if entry.time[0] <= timestamp:

return entry.newhexsha

# END found candidate

# END for each entry

return log[0].newhexsha

def _previous_checked_out_branch(repo: "Repo", nth: int) -> AnyGitObject:

if nth <= 0:

raise ValueError("Invalid previous checkout selector: -%i" % nth)

# END handle invalid input

seen = 0

for entry in reversed(_ref_log(repo, repo.head)):

message = entry.message or ""

prefix = "checkout: moving from "

if not message.startswith(prefix):

continue

# END skip non-checkouts

previous_branch = message[len(prefix) :].split(" to ", 1)[0]

seen += 1

if seen == nth:

return name_to_object(repo, previous_branch)

# END found selector

# END for each entry

raise IndexError("Invalid previous checkout selector: -%i" % nth)

def _tracking_branch_object(repo: "Repo", ref: Optional[SymbolicReference]) -> AnyGitObject:

from git.refs.head import Head

if ref is None:

try:

head = repo.active_branch

except TypeError as e:

raise BadName("@{upstream}") from e

elif isinstance(ref, Head):

head = ref

elif os.fspath(ref.path).startswith("refs/heads/"):

head = Head(repo, ref.path)

else:

raise BadName("%s@{upstream}" % ref.name)

# END handle head

tracking_branch = head.tracking_branch()

if tracking_branch is None:

raise BadName("%s@{upstream}" % head.name)

# END handle missing upstream

return tracking_branch.commit

def _apply_reflog(repo: "Repo", ref: Optional[SymbolicReference], content: str) -> AnyGitObject:

if content.startswith("+"):

content = content[1:]

# END handle explicit positive sign

if content.startswith("-"):

if ref is not None:

raise ValueError("Previous checkout selectors do not take an explicit ref")

if content == "-0":

raise ValueError("Negative zero is invalid in reflog selector")

# END handle invalid negative zero

try:

return _previous_checked_out_branch(repo, int(content[1:]))

except ValueError as e:

raise ValueError("Invalid previous checkout selector: %s" % content) from e

# END handle previous checkout branch

content_lower = content.lower()

if content_lower in ("u", "upstream", "push"):

return _tracking_branch_object(repo, ref)

# END handle sibling branches

ref = ref or _current_reflog_ref(repo)

try:

entry_no = int(content)

except ValueError:

hexsha = _find_reflog_entry_by_date(repo, ref, content)

else:

if entry_no >= 100000000:

hexsha = _find_reflog_entry_by_date(repo, ref, "%s +0000" % entry_no)

elif entry_no == 0:

return ref.commit

else:

try:

entry = _ref_log_entry(repo, ref, -(entry_no + 1))

except IndexError as e:

raise IndexError("Invalid revlog index: %i" % entry_no) from e

# END handle index out of bound

hexsha = entry.newhexsha

# END handle offset or date-like timestamp

# END handle content

return _object_from_hexsha(repo, hexsha)

def _find_closing_brace(rev: str, start: int) -> int:

depth = 1

escaped = False

for idx in range(start + 1, len(rev)):

char = rev[idx]

if escaped:

escaped = False

elif char == "\\":

escaped = True

elif char == "{":

depth += 1

elif char == "}":

depth -= 1

if depth == 0:

return idx

# END found end

# END handle char

# END for each char

raise ValueError("Missing closing brace to define type in %s" % rev)

def _parse_search(pattern: str) -> Tuple[str, bool]:

if not pattern:

raise ValueError("Revision search requires a pattern")

# END handle empty pattern

if pattern.startswith("!-"):

return pattern[2:], True

if pattern.startswith("!!"):

return pattern[1:], False

if pattern.startswith("!"):

raise ValueError("Need one character after /!, typically -")

return pattern, False

def _unescape_braced_regex(pattern: str) -> str:

out = []

idx = 0

while idx < len(pattern):

char = pattern[idx]

if char == "\\" and idx + 1 < len(pattern):

next_char = pattern[idx + 1]

if next_char in "{}\\":

out.append(next_char)

else:

out.append(char)

out.append(next_char)

# END handle escaped char

idx += 2

continue

# END handle backslash

out.append(char)

idx += 1

# END for each char

return "".join(out)

def _find_commit_by_message(

repo: "Repo", rev: Optional[AnyGitObject], pattern: str, braced: bool = False

) -> AnyGitObject:

pattern, negated = _parse_search(_unescape_braced_regex(pattern) if braced else pattern)

try:

regex = re.compile(pattern)

except re.error as e:

raise ValueError("Invalid commit message regex %r" % pattern) from e

# END handle invalid regex

if rev is None:

commits = _all_ref_commits(repo)

else:

commits = _reachable_commits([to_commit(cast(Object, rev))])

# END handle starting point

for commit in commits:

message = commit.message

if isinstance(message, bytes):

message = message.decode(commit.encoding, "replace")

# END handle bytes message

matches = regex.search(message or "") is not None

if matches != negated:

return commit

# END found commit

# END for each commit

raise BadName("No commit found matching message pattern %r" % pattern)

def _all_ref_commits(repo: "Repo") -> Iterator["Commit"]:

starts = []

for ref in repo.references:

try:

starts.append(to_commit(cast(Object, ref.object)))

except (BadName, ValueError):

pass

# END skip refs that do not point to commits

# END for each ref

try:

starts.append(repo.head.commit)

except ValueError:

pass

# END handle unborn head

return _reachable_commits(starts)

def _reachable_commits(starts: list["Commit"]) -> Iterator["Commit"]:

seen = set()

pending = starts[:]

while pending:

pending.sort(key=lambda commit: commit.committed_date, reverse=True)

commit = pending.pop(0)

if commit.binsha in seen:

continue

# END skip seen commit

seen.add(commit.binsha)

yield commit

pending.extend(commit.parents)

# END while commits remain

def _index_lookup(repo: "Repo", spec: str) -> AnyGitObject:

if not spec:

raise ValueError("':' must be followed by a path")

# END handle empty lookup

stage = 0

path = spec

if len(spec) >= 2 and spec[1] == ":" and spec[0] in "0123":

stage = int(spec[0])

path = spec[2:]

# END handle stage

try:

return repo.index.entries[(path, stage)].to_blob(repo)

except KeyError as e:

raise BadName("Path %r did not exist in the index at stage %i" % (path, stage)) from e

def _tree_lookup(obj: AnyGitObject, path: str) -> AnyGitObject:

if obj.type != "tree":

obj = to_commit(cast(Object, obj)).tree

# END get tree

if not path:

return obj

return obj[path]

def _peel(obj: AnyGitObject, output_type: str, repo: "Repo", rev: str) -> AnyGitObject:

if output_type.startswith("/"):

return _find_commit_by_message(repo, obj, output_type[1:], braced=True)

if output_type == "":

return deref_tag(obj) if obj.type == "tag" else obj

if output_type == "object":

return obj

if output_type == "commit":

return to_commit(cast(Object, obj))

if output_type == "tree":

return to_commit(cast(Object, obj)).tree if obj.type != "tree" else obj

if output_type == "blob":

obj = deref_tag(obj) if obj.type == "tag" else obj

if obj.type == output_type:

return obj

# END handle matching type

raise ValueError("Could not accommodate requested object type %r, got %s" % (output_type, obj.type))

if output_type == "tag":

if obj.type == output_type:

return obj

# END handle matching type

raise ValueError("Could not accommodate requested object type %r, got %s" % (output_type, obj.type))

# END handle known types

raise ValueError("Invalid output type: %s ( in %s )" % (output_type, rev))

def _first_rev_token(rev: str) -> Optional[int]:

for idx, char in enumerate(rev):

if char in "^~:":

return idx

if char == "@":

next_char = rev[idx + 1] if idx + 1 < len(rev) else None

if idx == 0 and next_char in (None, "^", "~", ":", "{"):

return idx

if next_char == "{":

return idx

# END handle reflog selector

# END handle at symbol

# END for each char

return None

def rev_parse(repo: "Repo", rev: str) -> AnyGitObject:

"""Parse a revision string. Like :manpage:`git-rev-parse(1)`.

:return:

`~git.objects.base.Object` at the given revision.

This may be any type of git object:

* :class:`Commit <git.objects.commit.Commit>`

* :class:`TagObject <git.objects.tag.TagObject>`

* :class:`Tree <git.objects.tree.Tree>`

* :class:`Blob <git.objects.blob.Blob>`

:param rev:

:manpage:`git-rev-parse(1)`-compatible revision specification as string.

Please see :manpage:`git-rev-parse(1)` for details.

:raise gitdb.exc.BadObject:

If the given revision could not be found.

:raise ValueError:

If `rev` couldn't be parsed.

:raise IndexError:

If an invalid reflog index is specified.

"""

if rev.startswith(":/"):

return _find_commit_by_message(repo, None, rev[2:])

if rev.startswith(":"):

return _index_lookup(repo, rev[1:])

# END handle top-level colon modes

obj: Optional[AnyGitObject] = None

ref = None

lr = len(rev)

first_token = _first_rev_token(rev)

if first_token is None:

return name_to_object(repo, rev)

# END handle plain name

if first_token == 0:

if rev[0] != "@":

raise ValueError("Revision specifier must start with an object name: %s" % rev)

# END handle invalid leading token

ref = _current_reflog_ref(repo)

obj = ref.commit

start = 0 if rev.startswith("@{") else 1

else:

if rev[first_token] == "@":

ref = cast("Reference", name_to_object(repo, rev[:first_token], return_ref=True))

obj = ref.commit

else:

obj = name_to_object(repo, rev[:first_token])

# END handle anchor

start = first_token

# END initialize anchor

while start < lr:

token = rev[start]

if token == "@":

if start + 1 >= lr or rev[start + 1] != "{":

raise ValueError("Invalid @ token in revision specifier: %s" % rev)

# END handle invalid @

end = _find_closing_brace(rev, start + 1)

obj = _apply_reflog(repo, ref if first_token != 0 and start == first_token else None, rev[start + 2 : end])

ref = None

start = end + 1

continue

# END handle reflog

if token == ":":

return _tree_lookup(obj, rev[start + 1 :])

# END handle path

start += 1

if token == "^" and start < lr and rev[start] == "{":

end = _find_closing_brace(rev, start)

obj = _peel(obj, rev[start + 1 : end], repo, rev)

ref = None

start = end + 1

continue

# END parse type

num = 0

found_digit = False

while start < lr:

if rev[start] in digits:

num = num * 10 + int(rev[start])

start += 1

found_digit = True

else:

break

# END handle number

# END number parse loop

if not found_digit:

num = 1

# END set default num

try:

if token == "~":

obj = to_commit(obj)

for _ in range(num):

obj = obj.parents[0]

# END for each history item to walk

elif token == "^":

obj = to_commit(obj)

if num == 0:

pass

else:

obj = obj.parents[num - 1]

# END handle parent

else:

raise ValueError("Invalid token: %r" % token)

# END end handle tag

except (IndexError, AttributeError) as e:

raise BadName(

f"Invalid revision spec '{rev}' - not enough parent commits to reach '{token}{int(num)}'"

) from e

# END exception handling

# END parse loop

if obj is None:

raise ValueError("Revision specifier could not be parsed: %s" % rev)

return obj

GitPython/git/repo/fun.py at 3.1.62 · gitpython-developers/GitPython · GitHub

Repository navigation

Expand file tree

Breadcrumbs

fun.py

Latest commit

History

Breadcrumbs

fun.py

File metadata and controls