Repository navigation
Expand file tree
/
Copy pathtree.py
More file actions
434 lines (351 loc) · 14.9 KB
/
Copy pathtree.py
File metadata and controls
434 lines (351 loc) · 14.9 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
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
# Copyright (C) 2008, 2009 Michael Trier (mtrier@gmail.com) and contributors
#
# This module is part of GitPython and is released under the
# 3-Clause BSD License: https://opensource.org/license/bsd-3-clause/
__all__ = ["TreeModifier", "Tree"]
import os
import tempfile
import git.diff as git_diff
from git.util import IterableList, join_path, to_bin_sha
from git.compat import defenc, safe_decode, safe_encode
from git.cmd import Git
from . import util
from .base import IndexObjUnion, IndexObject
from .blob import Blob
from .fun import _validate_tree_entry_name
from .submodule.base import Submodule
# typing -------------------------------------------------
from typing import (
Any,
Callable,
Dict,
Iterable,
Iterator,
List,
Literal,
Tuple,
TYPE_CHECKING,
Type,
Union,
cast,
)
from git.types import PathLike
if TYPE_CHECKING:
from io import BytesIO
from git.repo import Repo
TreeCacheTup = Tuple[bytes, int, str]
TraversedTreeTup = Union[Tuple[Union["Tree", None], IndexObjUnion, Tuple["Submodule", "Submodule"]]]
# --------------------------------------------------------
def cmp(a: str, b: str) -> int:
return (a > b) - (a < b)
class TreeModifier:
"""Edit the entries cached by one :class:`Tree` instance.
Changes affect only that instance's in-memory entries. They do not update its
object ID, the stored tree, parent trees, the index, or any commit. Call
:meth:`set_done` to restore entry order for iteration after editing.
Tree serialization delegates construction and ordering to Git or the supported
Gix backend. Prefer :class:`~git.index.base.IndexFile` and
:meth:`~git.index.base.IndexFile.write_tree` when building a new tree from staged
paths, especially when changes must propagate through nested trees.
"""
__slots__ = ("_cache",)
def __init__(self, cache: List[TreeCacheTup]) -> None:
self._cache = cache
def _index_by_name(self, name: str) -> int:
""":return: index of an item with name, or -1 if not found"""
for i, t in enumerate(self._cache):
if t[2] == name:
return i
# END found item
# END for each item in cache
return -1
# { Interface
def set_done(self) -> "TreeModifier":
"""Call this method once you are done modifying the tree information.
This may be called several times, but be aware that each call will cause a sort
operation.
:return:
self
"""
self._cache.sort(key=lambda x: safe_encode(x[2]) + (b"/" if x[1] == Tree.tree_id << 12 else b""))
return self
# } END interface
# { Mutators
def add(self, sha: bytes, mode: int, name: str, force: bool = False) -> "TreeModifier":
"""Add the given item to the tree.
If an item with the given name already exists, nothing will be done, but a
:exc:`ValueError` will be raised if the sha and mode of the existing item do not
match the one you add, unless `force` is ``True``.
:param sha:
The binary or hexadecimal object ID of the item to add, in the
repository's object format.
:param mode:
:class:`int` representing the stat-compatible mode of the item.
:param force:
If ``True``, an item with your name and information will overwrite any
existing item with the same name, no matter which information it has.
:return:
self
"""
_validate_tree_entry_name(name, mode)
if (mode >> 12) not in Tree._map_id_to_type:
raise ValueError("Invalid object type according to mode %o" % mode)
sha = to_bin_sha(sha)
index = self._index_by_name(name)
item = (sha, mode, name)
if index == -1:
self._cache.append(item)
else:
if force:
self._cache[index] = item
else:
ex_item = self._cache[index]
if ex_item[0] != sha or ex_item[1] != mode:
raise ValueError("Item %r existed with different properties" % name)
# END handle mismatch
# END handle force
# END handle name exists
return self
def add_unchecked(self, binsha: bytes, mode: int, name: str) -> None:
"""Add the given item to the tree. Its correctness is assumed, so it is the
caller's responsibility to ensure that the input is correct.
For more information on the parameters, see :meth:`add`.
:param binsha:
Binary object ID in the repository's object format.
"""
assert isinstance(binsha, bytes) and isinstance(mode, int) and isinstance(name, str)
tree_cache = (binsha, mode, name)
self._cache.append(tree_cache)
def __delitem__(self, name: str) -> None:
"""Delete an item with the given name if it exists."""
index = self._index_by_name(name)
if index > -1:
del self._cache[index]
# } END mutators
class Tree(IndexObject, git_diff.Diffable, util.Traversable):
R"""Tree objects represent an ordered list of :class:`~git.objects.blob.Blob`\s and
other :class:`Tree`\s.
See :manpage:`gitglossary(7)` on "tree object":
https://git-scm.com/docs/gitglossary#def_tree_object
Subscripting is supported, as with a list or dict:
* Access a specific blob using the ``tree["filename"]`` notation.
* You may likewise access by index, like ``blob = tree[0]``.
"""
type: Literal["tree"] = "tree"
__slots__ = ("_cache",)
# Actual integer IDs for comparison.
commit_id = 0o16 # Equals stat.S_IFDIR | stat.S_IFLNK - a directory link.
blob_id = 0o10
symlink_id = 0o12
tree_id = 0o04
_map_id_to_type: Dict[int, Type[IndexObjUnion]] = {
commit_id: Submodule,
blob_id: Blob,
symlink_id: Blob,
# Tree ID added once Tree is defined.
}
def __init__(
self,
repo: "Repo",
binsha: bytes,
mode: int = tree_id << 12,
path: Union[PathLike, None] = None,
):
super().__init__(repo, binsha, mode, path)
@classmethod
def _get_intermediate_items(
cls,
index_object: IndexObjUnion,
) -> Union[Tuple["Tree", ...], Tuple[()]]:
if index_object.type == "tree":
return tuple(index_object._iter_convert_to_object(index_object._cache))
return ()
def _set_cache_(self, attr: str) -> None:
if attr == "_cache":
Git._check_operand(self.hexsha, "tree object ID")
output = self.repo.git._call_process_safe(
"ls_tree", "-z", "--full-tree", self.hexsha, stdout_as_string=False
)
cache: List[TreeCacheTup] = []
for record in output.split(b"\0"):
if not record:
continue
metadata, name_bytes = record.split(b"\t", 1)
mode, _type, oid = metadata.split()
name = safe_decode(name_bytes)
_validate_tree_entry_name(name, int(mode, 8))
binsha = bytes.fromhex(oid.decode("ascii"))
if len(binsha) != self.repo._oid_size:
raise ValueError("Invalid tree object ID returned by Git")
cache.append((binsha, int(mode, 8), name))
self._cache = cache
else:
super()._set_cache_(attr)
# END handle attribute
def _iter_convert_to_object(self, iterable: Iterable[TreeCacheTup]) -> Iterator[IndexObjUnion]:
"""Iterable yields tuples of (binsha, mode, name), which will be converted to
the respective object representation.
"""
for binsha, mode, name in iterable:
path = join_path(self.path, name)
try:
yield self._map_id_to_type[mode >> 12](self.repo, binsha, mode, path)
except KeyError as e:
raise TypeError("Unknown mode %o found in tree data for path '%s'" % (mode, path)) from e
# END for each item
def join(self, file: PathLike) -> IndexObjUnion:
"""Find the named object in this tree's contents.
:return:
:class:`~git.objects.blob.Blob`, :class:`Tree`, or
:class:`~git.objects.submodule.base.Submodule`
:raise KeyError:
If the given file or tree does not exist in this tree.
"""
msg = "Blob or Tree named %r not found"
file = os.fspath(file)
if "/" in file:
tree = self
item = self
tokens = file.split("/")
for i, token in enumerate(tokens):
item = tree[token]
if item.type == "tree":
tree = item
else:
# Safety assertion - blobs are at the end of the path.
if i != len(tokens) - 1:
raise KeyError(msg % file)
return item
# END handle item type
# END for each token of split path
if item == self:
raise KeyError(msg % file)
return item
else:
for info in self._cache:
if info[2] == file: # [2] == name
return self._map_id_to_type[info[1] >> 12](
self.repo, info[0], info[1], join_path(self.path, info[2])
)
# END for each obj
raise KeyError(msg % file)
# END handle long paths
def __truediv__(self, file: PathLike) -> IndexObjUnion:
"""The ``/`` operator is another syntax for joining.
See :meth:`join` for details.
"""
return self.join(file)
@property
def trees(self) -> List["Tree"]:
""":return: list(Tree, ...) List of trees directly below this tree"""
return [i for i in self if i.type == "tree"]
@property
def blobs(self) -> List[Blob]:
""":return: list(Blob, ...) List of blobs directly below this tree"""
return [i for i in self if i.type == "blob"]
@property
def cache(self) -> TreeModifier:
"""
:return:
A supported editor for this instance's cached entries. Call
:meth:`~TreeModifier.set_done` after editing to restore iteration order.
Editing does not change this tree's object ID or persist changes to its
stored object, parents, or commits.
:note:
See :class:`TreeModifier` for more information on how to alter the cache.
"""
return TreeModifier(self._cache)
def traverse(
self,
predicate: Callable[[Union[IndexObjUnion, TraversedTreeTup], int], bool] = lambda i, d: True,
prune: Callable[[Union[IndexObjUnion, TraversedTreeTup], int], bool] = lambda i, d: False,
depth: int = -1,
branch_first: bool = True,
visit_once: bool = False,
ignore_self: int = 1,
as_edge: bool = False,
) -> Union[Iterator[IndexObjUnion], Iterator[TraversedTreeTup]]:
"""For documentation, see :meth:`~git.objects.util.Traversable._traverse`.
Trees are set to ``visit_once = False`` to gain more performance in the
traversal.
"""
# # To typecheck instead of using cast.
# import itertools
# def is_tree_traversed(inp: Tuple) -> TypeGuard[Tuple[Iterator[Union['Tree', 'Blob', 'Submodule']]]]:
# return all(isinstance(x, (Blob, Tree, Submodule)) for x in inp[1])
# ret = super().traverse(predicate, prune, depth, branch_first, visit_once, ignore_self)
# ret_tup = itertools.tee(ret, 2)
# assert is_tree_traversed(ret_tup), f"Type is {[type(x) for x in list(ret_tup[0])]}"
# return ret_tup[0]
return cast(
Union[Iterator[IndexObjUnion], Iterator[TraversedTreeTup]],
super()._traverse(
predicate, # type: ignore[arg-type]
prune, # type: ignore[arg-type]
depth,
branch_first,
visit_once,
ignore_self,
),
)
def list_traverse(self, *args: Any, **kwargs: Any) -> IterableList[IndexObjUnion]:
"""
:return:
:class:`~git.util.IterableList` with the results of the traversal as
produced by :meth:`traverse`
Tree -> IterableList[Union[Submodule, Tree, Blob]]
"""
return super()._list_traverse(*args, **kwargs)
# List protocol
def __getslice__(self, i: int, j: int) -> List[IndexObjUnion]:
return list(self._iter_convert_to_object(self._cache[i:j]))
def __iter__(self) -> Iterator[IndexObjUnion]:
return self._iter_convert_to_object(self._cache)
def __len__(self) -> int:
return len(self._cache)
def __getitem__(self, item: Union[str, int, slice]) -> IndexObjUnion:
if isinstance(item, int):
info = self._cache[item]
return self._map_id_to_type[info[1] >> 12](self.repo, info[0], info[1], join_path(self.path, info[2]))
if isinstance(item, str):
# compatibility
return self.join(item)
# END index is basestring
raise TypeError("Invalid index type: %r" % item)
def __contains__(self, item: Union[IndexObjUnion, PathLike]) -> bool:
if isinstance(item, IndexObject):
for info in self._cache:
if item.binsha == info[0]:
return True
# END compare sha
# END for each entry
# END handle item is index object
# compatibility
# Treat item as repo-relative path.
else:
path = self.path
for info in self._cache:
if item == join_path(path, info[2]):
return True
# END for each item
return False
def __reversed__(self) -> Iterator[IndexObjUnion]:
return reversed(self._iter_convert_to_object(self._cache)) # type: ignore[call-overload]
def _serialize(self, stream: "BytesIO") -> "Tree":
"""Ask Git to build this cache as a tree, then copy its raw object contents."""
types = {0o04: "tree", 0o10: "blob", 0o12: "blob", 0o16: "commit"}
with tempfile.TemporaryFile() as source:
for oid, mode, name in self._cache:
_validate_tree_entry_name(name, mode)
if len(oid) != self.repo._oid_size or mode >> 12 not in types:
raise ValueError("Invalid tree entry object ID or mode")
source.write(("%o %s %s\t" % (mode, types[mode >> 12], oid.hex())).encode("ascii"))
source.write(name.encode(defenc, "surrogateescape") + b"\0")
source.seek(0)
oid = self.repo.git._call_process_safe("mktree", "-z", "--missing", istream=source)
Git._check_operand(oid, "tree object ID")
stream.write(self.repo.odb.stream(to_bin_sha(oid)).read())
return self
# END tree
# Finalize map definition.
Tree._map_id_to_type[Tree.tree_id] = Tree