Kiln » Dependencies » Dulwich Read More
Clone URL:  
object_store.py
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
# object_store.py -- Object store for git objects # Copyright (C) 2008 Jelmer Vernooij <jelmer@samba.org> # # This program is free software; you can redistribute it and/or # modify it under the terms of the GNU General Public License # as published by the Free Software Foundation; either version 2 # or (at your option) a later version of the License. # # This program is distributed in the hope that it will be useful, # but WITHOUT ANY WARRANTY; without even the implied warranty of # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the # GNU General Public License for more details. # # You should have received a copy of the GNU General Public License # along with this program; if not, write to the Free Software # Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, # MA 02110-1301, USA. import os import tempfile import urllib2 from dulwich.objects import ( hex_to_sha, sha_to_hex, ShaFile, ) from dulwich.pack import ( iter_sha1, load_packs, write_pack, write_pack_data, write_pack_index_v2, PackData, ) PACKDIR = 'pack' class ObjectStore(object): def __init__(self, path): self.path = path self._packs = None def iter_shas(self, shas): return ObjectStoreIterator(self, shas) def pack_dir(self): return os.path.join(self.path, PACKDIR) def __contains__(self, sha): # TODO: This can be more efficient try: self[sha] return True except KeyError: return False @property def packs(self): """List with pack objects.""" if self._packs is None: self._packs = list(load_packs(self.pack_dir())) return self._packs def _get_shafile_path(self, sha): dir = sha[:2] file = sha[2:] # Check from object dir return os.path.join(self.path, dir, file) def _get_shafile(self, sha): path = self._get_shafile_path(sha) if os.path.exists(path): return ShaFile.from_file(path) return None def _add_shafile(self, sha, o): path = self._get_shafile_path(sha) f = os.path.open(path, 'w') try: f.write(o._header()) f.write(o._text) finally: f.close() def get_raw(self, sha): """Obtain the raw text for an object. :param sha: Sha for the object. :return: tuple with object type and object contents. """ for pack in self.packs: if sha in pack: return pack.get_raw(sha, self.get_raw) # FIXME: Are pack deltas ever against on-disk shafiles ? ret = self._get_shafile(sha) if ret is not None: return ret.as_raw_string() raise KeyError(sha) def __getitem__(self, sha): assert len(sha) == 40, "Incorrect length sha: %s" % str(sha) ret = self._get_shafile(sha) if ret is not None: return ret # Check from packs type, uncomp = self.get_raw(sha) return ShaFile.from_raw_string(type, uncomp) def move_in_thin_pack(self, path): """Move a specific file containing a pack into the pack directory. :note: The file should be on the same file system as the packs directory. :param path: Path to the pack file. """ p = PackData(path) temppath = os.path.join(self.pack_dir(), sha_to_hex(urllib2.randombytes(20))+".temppack") write_pack(temppath, p.iterobjects(self.get_raw), len(p)) pack_sha = PackIndex(temppath+".idx").objects_sha1() os.rename(temppath+".pack", os.path.join(self.pack_dir(), "pack-%s.pack" % pack_sha)) os.rename(temppath+".idx", os.path.join(self.pack_dir(), "pack-%s.idx" % pack_sha)) def move_in_pack(self, path): """Move a specific file containing a pack into the pack directory. :note: The file should be on the same file system as the packs directory. :param path: Path to the pack file. """ p = PackData(path) entries = p.sorted_entries() basename = os.path.join(self.pack_dir(), "pack-%s" % iter_sha1(entry[0] for entry in entries)) write_pack_index_v2(basename+".idx", entries, p.calculate_checksum()) os.rename(path, basename + ".pack") def add_thin_pack(self): """Add a new thin pack to this object store. Thin packs are packs that contain deltas with parents that exist in a different pack. """ fd, path = tempfile.mkstemp(dir=self.pack_dir(), suffix=".pack") f = os.fdopen(fd, 'w') def commit(): if os.path.getsize(path) > 0: self.move_in_thin_pack(path) return f, commit def add_pack(self): """Add a new pack to this object store. :return: Fileobject to write to and a commit function to call when the pack is finished. """ fd, path = tempfile.mkstemp(dir=self.pack_dir(), suffix=".pack") f = os.fdopen(fd, 'w') def commit(): if os.path.getsize(path) > 0: self.move_in_pack(path) return f, commit def add_objects(self, objects): if len(objects) == 0: return f, commit = self.add_pack() write_pack_data(f, objects, len(objects)) commit() class ObjectImporter(object): def __init__(self, count): self.count = count def add_object(self, object): raise NotImplementedError(self.add_object) def finish(self, object): raise NotImplementedError(self.finish) class ObjectIterator(object): def iterobjects(self): raise NotImplementedError(self.iterobjects) class ObjectStoreIterator(ObjectIterator): def __init__(self, store, shas): self.store = store self.shas = shas def __iter__(self): return ((self.store[sha], path) for sha, path in self.shas) def iterobjects(self): for o, path in self: yield o def __contains__(self, needle): # FIXME: This could be more efficient for sha, path in self.shas: if sha == needle: return True return False def __getitem__(self, key): return self.store[key] def __len__(self): return len(self.shas)