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 | class Git:
"""Utilities to work with git."""
def __init__(self, configuration: Configuration):
"""Create a new git wrapper object.
Args:
configuration: The configuration object to be used by the object.
"""
self._configuration = configuration
@staticmethod
def make_git_wrapper(directory_path: Path):
"""Create a wrapper which is callable as ``git`` but invoke ``git-on-fire``.
This function can be used to create a platform native wrapper script,
which can be invoked using ``git`` but instead, it will call
``git-on-fire``.
Args:
directory_path: The path to the directory where to create the
wrapper.
"""
if platform.system() == "Windows":
template = _WINDOWS_WRAPPER_SCRIPT
suffix = ".bat"
make_executable = False
else:
template = _UNIX_WRAPPER_SCRIPT
suffix = ""
make_executable = True
native_git_executable = Git.find_git()
script_content = template.format(
native_git_executable=native_git_executable,
native_git_executable_sh=shlex.quote(native_git_executable),
python_executable=sys.executable,
python_executable_sh=shlex.quote(sys.executable),
)
directory_path.mkdir(parents=True, exist_ok=True)
file_path = directory_path / ("git" + suffix)
if file_path.exists():
# If the file exists, check if we need to update the content:
if file_path.read_text(encoding="utf-8") != script_content:
file_path.write_text(script_content, encoding="utf-8")
else:
# Otherwise, always write:
file_path.write_text(script_content, encoding="utf-8")
if make_executable:
os.chmod(file_path, 0o755)
@staticmethod
def find_git():
"""Find the git command.
This method can be used to find the git command. This method assumes
that the current process has been called by a previously created
git wrapper (using the [make_git_wrapper][repo_on_fire.git.Git.make_git_wrapper] method).
In this case, special care is taken to avoid that the wrapper recursively finds
itself, which would lead to an infinite loop (and exhaustion of
resources of the host).
Raises:
ExecutableNotFound: The git command could not be found.
"""
# Compile a list of search paths. There are two possibilities:
GIT_ON_FIRE_WRAPPER_DIR = "GIT_ON_FIRE_WRAPPER_DIR"
if GIT_ON_FIRE_WRAPPER_DIR in os.environ:
# We are called from a git wrapper. In this case, the list of
# paths to look for git is compiled by searching PATH for the
# directory where the wrapper is stored in and - if found - we only
# include the paths after the entry.
path_variable = os.environ.get("PATH", os.defpath)
paths = path_variable.split(os.pathsep)
wrapper_path = Path(os.environ[GIT_ON_FIRE_WRAPPER_DIR]).resolve()
search_paths = []
for i, path in enumerate(paths):
path_path = Path(path).resolve()
if wrapper_path == path_path:
search_paths = paths[i + 1 :]
break
if len(search_paths) == 0:
# The wrapper path was not in PATH. This can happen if the
# wrapper is called without adding its path to PATH. Fall back
# to using the default path.
search_paths = paths
joined_path = os.pathsep.join(search_paths)
git = shutil.which("git", path=joined_path)
if git is None:
raise ExecutableNotFound(f"Did not find git in '{joined_path}'")
return git
else:
# We didn't end here due to a call to the git wrapper. Hence,
# simply return git from wherever we can find it:
git = shutil.which("git")
if git is None:
raise ExecutableNotFound("Unable to find git executable")
return git
@staticmethod
def find_repo_root(cwd: Optional[Union[str, Path]] = None):
"""Try to find the rep root directory.
This method looks for the ``.repo`` directory in ``cwd`` and recursively
upwards.
Args:
cwd: The directory where to start searching. The method starts
looking for the ``.repo`` directory there and follows upwards
in the file system hierarchy. If None, search starts
in ``os.curdir``.
Raises:
RepoRootNotFound: If no ``.repo`` directory can be found.
"""
if cwd is None:
cwd = os.getcwd()
path = Path(cwd)
while path != path.parent:
repo_dir = path / ".repo"
if repo_dir.exists():
return path
path = path.parent
raise RepoRootNotFound(f"Could not find .repo in '{cwd}")
def clone(self, args: List[str], global_args: Optional[List[str]] = None) -> int:
"""Clone a repository using the local git cache.
The first clone for a specific clone request is run in the cache. Later
clones update that cache entry and copy the cached working tree to the
originally requested destination.
Args:
args: Arguments passed after ``git clone``.
global_args: Arguments passed before ``clone`` to the ``git``
command itself.
Returns:
The native git-compatible exit code.
"""
if global_args is None:
global_args = []
effective_cwd, filtered_global_args = self._extract_global_cwd(global_args)
if self._is_clone_help_requested(args):
return self._run_git([*filtered_global_args, "clone", *args], cwd=effective_cwd)
try:
repository, destination, destination_index = self._parse_clone_args(args)
except ValueError:
return self._run_git([*filtered_global_args, "clone", *args], cwd=effective_cwd)
cache_entry = self.get_clone_cache_entry(args, destination_index)
cache_args = self._replace_clone_destination(args, destination_index, cache_entry)
destination_path = self._get_clone_destination_path(
repository, destination, cwd=effective_cwd
)
with lock_path(cache_entry):
if not cache_entry.exists():
exit_code = self._run_git_for_cache(
[*filtered_global_args, "clone", *cache_args], cwd=effective_cwd
)
if exit_code != 0:
shutil.rmtree(cache_entry, ignore_errors=True)
return exit_code
else:
exit_code = self._update_clone_cache(cache_entry, filtered_global_args)
if exit_code != 0:
return exit_code
try:
self._copy_clone_cache(cache_entry, destination_path)
except OSError as error:
print(f"git-on-fire: could not copy cached clone: {error}", file=sys.stderr)
return 128
return 0
def fetch(self, args: List[str], global_args: Optional[List[str]] = None) -> int:
"""Fetch through the local git cache when a repository can be identified."""
if global_args is None:
global_args = []
effective_cwd, filtered_global_args = self._extract_global_cwd(global_args)
native_fetch_args = [*filtered_global_args, "fetch", *args]
fetch_repository = self._parse_fetch_repository(args)
if fetch_repository is None:
return self._run_git(native_fetch_args, cwd=effective_cwd)
repository, repository_index = fetch_repository
if self._is_local_repository_path(repository):
return self._run_git(native_fetch_args, cwd=effective_cwd)
if not self._is_fetch_target_empty(effective_cwd):
return self._run_git(native_fetch_args, cwd=effective_cwd)
repository_url = self._resolve_fetch_repository_url(
repository, filtered_global_args, effective_cwd
)
if repository_url is None:
return self._run_git(native_fetch_args, cwd=effective_cwd)
cache_entry = self.get_fetch_cache_entry(repository_url)
with lock_path(cache_entry):
if not self._is_git_repository(cache_entry):
exit_code = self._create_fetch_cache_if_missing(repository_url, cache_entry)
else:
exit_code = self._run_git_for_cache(
[
*filtered_global_args,
"-C",
str(cache_entry),
"fetch",
"--all",
"--tags",
"--prune",
]
)
if exit_code != 0:
return exit_code
cache_args = list(args)
cache_args[repository_index] = str(cache_entry)
return self._run_git([*filtered_global_args, "fetch", *cache_args], cwd=effective_cwd)
def ls_remote(self, repository_url: str, ref: str) -> str:
"""Query a remote repository for a ref."""
return self._run_git_output(["ls-remote", repository_url, ref])
def get_clone_cache_entry(self, args: List[str], destination_index: Optional[int]) -> Path:
"""Get the cache entry path for a ``git clone`` request."""
cache_key_args = [
arg
for index, arg in enumerate(args)
if destination_index is None or index != destination_index
]
cache_id = sha256("\0".join(cache_key_args).encode("utf-8")).hexdigest()
return self._configuration.cache_path / "git" / cache_id[0:2] / cache_id
def get_fetch_cache_entry(self, repository_url: str) -> Path:
"""Get the cache entry path for a fetch repository."""
cache_id = sha256(f"fetch\0{repository_url}".encode()).hexdigest()
return self._configuration.cache_path / "git" / cache_id[0:2] / cache_id
@contextmanager
def with_git_wrapper(self, cwd: Optional[Union[str, Path]] = None):
"""Run a command with a patched git command.
This method implements a context manager which can be used to run
commands with a modified ``PATH`` environment variable such that
instead of the usual ``git``, a wrapper is called which provides
addon functionality. The wrapper is created using
[make_git_wrapper][repo_on_fire.git.Git.make_git_wrapper].
Args:
cwd: The path where to search for the repo workspace. If set to
None, the current working directory will be used instead.
"""
try:
repo_root = Git.find_repo_root(cwd)
try:
# Create a git wrapper in the repo folder
wrapper_path = repo_root / ".repo" / "repo-on-fire" / "bin"
Git.make_git_wrapper(wrapper_path)
env = os.environ
path = env.get("PATH", "")
modified_path = os.pathsep.join([str(wrapper_path), path])
os.environ["PATH"] = modified_path
yield dict(os.environ)
finally:
os.environ["PATH"] = path
except RepoRootNotFound:
# If we are outside a workspace, create a wrapper in a temporary
# folder:
with TemporaryDirectory() as tmp_dir:
try:
# Create a git wrapper in the temp dir
wrapper_path = Path(tmp_dir)
Git.make_git_wrapper(wrapper_path)
env = os.environ
path = env.get("PATH", "")
modified_path = os.pathsep.join([str(wrapper_path), path])
os.environ["PATH"] = modified_path
yield dict(os.environ)
finally:
os.environ["PATH"] = path
@staticmethod
def _parse_clone_args(args: List[str]) -> Tuple[str, Optional[str], Optional[int]]:
option_value_names = {
"-b",
"--branch",
"-o",
"--origin",
"-u",
"--upload-pack",
"--template",
"--reference",
"--reference-if-able",
"--separate-git-dir",
"--depth",
"--shallow-since",
"--shallow-exclude",
"-j",
"--jobs",
"--server-option",
"-c",
"--config",
}
positionals: List[Tuple[int, str]] = []
i = 0
end_of_options = False
while i < len(args):
arg = args[i]
if not end_of_options and arg == "--":
end_of_options = True
i += 1
continue
if not end_of_options and arg.startswith("--"):
option_name = arg.split("=", 1)[0]
i += 2 if option_name in option_value_names and "=" not in arg else 1
continue
if not end_of_options and arg.startswith("-") and arg != "-":
i += 2 if arg in option_value_names else 1
continue
positionals.append((i, arg))
i += 1
if len(positionals) == 0:
raise ValueError("git clone requires a repository argument")
if len(positionals) > _MAX_CLONE_POSITIONALS:
raise ValueError("git clone received too many repository/destination arguments")
repository = positionals[0][1]
destination = positionals[1][1] if len(positionals) == _MAX_CLONE_POSITIONALS else None
destination_index = (
positionals[1][0] if len(positionals) == _MAX_CLONE_POSITIONALS else None
)
return repository, destination, destination_index
@staticmethod
def _is_clone_help_requested(args: List[str]) -> bool:
return "-h" in args or "--help" in args
@staticmethod
def _replace_clone_destination(
args: List[str], destination_index: Optional[int], cache_entry: Path
) -> List[str]:
cache_args = list(args)
if destination_index is None:
cache_args.append(str(cache_entry))
else:
cache_args[destination_index] = str(cache_entry)
return cache_args
@staticmethod
def _parse_fetch_repository(args: List[str]) -> Optional[Tuple[str, int]]:
option_value_names = {
"--upload-pack",
"--depth",
"--deepen",
"--shallow-since",
"--shallow-exclude",
"--jobs",
"-j",
"--server-option",
"--negotiation-tip",
"--recurse-submodules",
"--refmap",
"-o",
"--set-upstream",
"--submodule-prefix",
"--filter",
}
skip_cache_options = {"--all", "--multiple", "--stdin"}
end_of_options = False
i = 0
while i < len(args):
arg = args[i]
if not end_of_options and arg == "--":
end_of_options = True
i += 1
continue
if not end_of_options and arg in skip_cache_options:
return None
if not end_of_options and arg.startswith("--"):
option_name = arg.split("=", 1)[0]
i += 2 if option_name in option_value_names and "=" not in arg else 1
continue
if not end_of_options and arg.startswith("-") and arg != "-":
i += 2 if arg in option_value_names else 1
continue
return arg, i
return None
def _resolve_fetch_repository_url(
self, repository: str, global_args: List[str], cwd: Path
) -> Optional[str]:
if self._is_explicit_repository(repository):
return repository
try:
url = self._run_git_output([*global_args, "remote", "get-url", repository], cwd=cwd)
except subprocess.CalledProcessError:
return None
return url.strip()
@staticmethod
def _is_explicit_repository(repository: str) -> bool:
return "://" in repository or "@" in repository
@staticmethod
def _is_local_repository_path(repository: str) -> bool:
repository_path = Path(repository)
return repository_path.exists() or repository_path.is_absolute()
@staticmethod
def _get_clone_destination_path(repository: str, destination: Optional[str], cwd: Path) -> Path:
if destination is not None:
destination_path = Path(destination)
else:
repository_name = repository.rstrip("/").rsplit("/", 1)[-1]
if repository_name.endswith(".git"):
repository_name = repository_name[:-4]
destination_path = Path(repository_name)
if destination_path.is_absolute():
return destination_path
return cwd / destination_path
@staticmethod
def _extract_global_cwd(global_args: List[str]) -> Tuple[Path, List[str]]:
cwd = Path.cwd()
filtered_args: List[str] = []
i = 0
while i < len(global_args):
arg = global_args[i]
if arg == "-C" and i + 1 < len(global_args):
cwd = Git._resolve_git_cwd(cwd, global_args[i + 1])
i += 2
continue
if arg.startswith("-C") and len(arg) > _SHORT_OPTION_WITH_VALUE_LENGTH:
cwd = Git._resolve_git_cwd(cwd, arg[2:])
i += 1
continue
filtered_args.append(arg)
i += 1
return cwd, filtered_args
@staticmethod
def _resolve_git_cwd(cwd: Path, path: str) -> Path:
new_cwd = Path(path)
if new_cwd.is_absolute():
return new_cwd
return cwd / new_cwd
@staticmethod
def _copy_clone_cache(cache_entry: Path, destination_path: Path):
if destination_path.exists() and any(destination_path.iterdir()):
raise FileExistsError(
f"destination path '{destination_path}' already exists and is not empty"
)
destination_path.parent.mkdir(parents=True, exist_ok=True)
shutil.copytree(cache_entry, destination_path, symlinks=True, dirs_exist_ok=True)
def _update_clone_cache(self, cache_entry: Path, global_args: List[str]) -> int:
fetch_exit_code = self._run_git_for_cache(
[*global_args, "-C", str(cache_entry), "fetch", "--all", "--tags", "--prune"]
)
if fetch_exit_code != 0:
return fetch_exit_code
return self._run_git_for_cache([*global_args, "-C", str(cache_entry), "pull", "--ff-only"])
def _create_fetch_cache_if_missing(self, repository_url: str, cache_entry: Path) -> int:
if self._is_git_repository(cache_entry):
return 0
shutil.rmtree(cache_entry, ignore_errors=True)
exit_code = self._run_git_for_cache(["clone", "--mirror", repository_url, str(cache_entry)])
if exit_code != 0:
shutil.rmtree(cache_entry, ignore_errors=True)
return exit_code
def _run_git(self, args: List[str], cwd: Optional[Path] = None) -> int:
command = [Git.find_git(), *args]
return subprocess.call(command, cwd=str(cwd) if cwd is not None else None)
def _run_git_for_cache(self, args: List[str], cwd: Optional[Path] = None) -> int:
command = [Git.find_git(), *args]
return subprocess.call(
command, cwd=str(cwd) if cwd is not None else None, env=self._get_cache_git_env()
)
def _run_git_output(self, args: List[str], cwd: Optional[Path] = None) -> str:
command = [Git.find_git(), *args]
output = subprocess.check_output(command, cwd=str(cwd) if cwd is not None else None)
return output.decode("utf-8")
@staticmethod
def _get_cache_git_env() -> dict:
env = dict(os.environ)
for key in _GIT_ENVIRONMENT_VARIABLES:
env.pop(key, None)
return env
@staticmethod
def _is_git_repository(path: Path) -> bool:
return (path / "objects").is_dir() and (path / "HEAD").is_file()
def _is_fetch_target_empty(self, cwd: Path) -> bool:
object_directory = os.environ.get("GIT_OBJECT_DIRECTORY")
if object_directory is None:
try:
object_directory = self._run_git_output(["rev-parse", "--git-path", "objects"], cwd)
except subprocess.CalledProcessError:
return False
object_path = Path(object_directory.strip())
return not self._object_store_has_objects(object_path)
@staticmethod
def _object_store_has_objects(object_path: Path) -> bool:
if not object_path.exists():
return False
pack_path = object_path / "pack"
if pack_path.exists() and any(pack_path.glob("*.pack")):
return True
for child in object_path.iterdir():
if child.name in {"info", "pack"} or not child.is_dir():
continue
try:
next(child.iterdir())
return True
except StopIteration:
continue
return False
|