1
# Copyright (C) 2005 Canonical Ltd
3
# This program is free software; you can redistribute it and/or modify
4
# it under the terms of the GNU General Public License as published by
5
# the Free Software Foundation; either version 2 of the License, or
6
# (at your option) any later version.
8
# This program is distributed in the hope that it will be useful,
9
# but WITHOUT ANY WARRANTY; without even the implied warranty of
10
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
11
# GNU General Public License for more details.
13
# You should have received a copy of the GNU General Public License
14
# along with this program; if not, write to the Free Software
15
# Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
17
"""Tree classes, representing directory at point in time.
23
from bzrlib.trace import mutter, note
24
from bzrlib.errors import BzrError
25
from bzrlib.inventory import Inventory
26
from bzrlib.osutils import pumpfile, appendpath, fingerprint_file
32
"""Abstract file tree.
34
There are several subclasses:
36
* `WorkingTree` exists as files on disk editable by the user.
38
* `RevisionTree` is a tree as recorded at some point in the past.
42
Trees contain an `Inventory` object, and also know how to retrieve
43
file texts mentioned in the inventory, either from a working
44
directory or from a store.
46
It is possible for trees to contain files that are not described
47
in their inventory or vice versa; for this use `filenames()`.
49
Trees can be compared, etc, regardless of whether they are working
50
trees or versioned trees.
53
def has_filename(self, filename):
54
"""True if the tree has given filename."""
55
raise NotImplementedError()
57
def has_id(self, file_id):
58
return self.inventory.has_id(file_id)
63
return iter(self.inventory)
65
def id2path(self, file_id):
66
return self.inventory.id2path(file_id)
68
def _get_inventory(self):
69
return self._inventory
71
def get_file_by_path(self, path):
72
return self.get_file(self._inventory.path2id(path))
74
inventory = property(_get_inventory,
75
doc="Inventory of this Tree")
77
def _check_retrieved(self, ie, f):
78
fp = fingerprint_file(f)
81
if ie.text_size != None:
82
if ie.text_size != fp['size']:
83
raise BzrError("mismatched size for file %r in %r" % (ie.file_id, self._store),
84
["inventory expects %d bytes" % ie.text_size,
85
"file is actually %d bytes" % fp['size'],
86
"store is probably damaged/corrupt"])
88
if ie.text_sha1 != fp['sha1']:
89
raise BzrError("wrong SHA-1 for file %r in %r" % (ie.file_id, self._store),
90
["inventory expects %s" % ie.text_sha1,
91
"file is actually %s" % fp['sha1'],
92
"store is probably damaged/corrupt"])
95
def print_file(self, fileid):
96
"""Print file with id `fileid` to stdout."""
98
pumpfile(self.get_file(fileid), sys.stdout)
101
def export(self, dest, format='dir', root=None):
102
"""Export this tree."""
104
exporter = exporters[format]
106
from bzrlib.errors import BzrCommandError
107
raise BzrCommandError("export format %r not supported" % format)
108
exporter(self, dest, root)
112
class RevisionTree(Tree):
113
"""Tree viewing a previous revision.
115
File text can be retrieved from the text store.
117
TODO: Some kind of `__repr__` method, but a good one
118
probably means knowing the branch and revision number,
119
or at least passing a description to the constructor.
122
def __init__(self, store, inv):
124
self._inventory = inv
126
def get_file(self, file_id):
127
ie = self._inventory[file_id]
128
f = self._store[ie.text_id]
129
mutter(" get fileid{%s} from %r" % (file_id, self))
130
self._check_retrieved(ie, f)
133
def get_file_size(self, file_id):
134
return self._inventory[file_id].text_size
136
def get_file_sha1(self, file_id):
137
ie = self._inventory[file_id]
138
if ie.kind == "file":
141
def has_filename(self, filename):
142
return bool(self.inventory.path2id(filename))
144
def list_files(self):
145
# The only files returned by this are those from the version
146
for path, entry in self.inventory.iter_entries():
147
yield path, 'V', entry.kind, entry.file_id
150
class EmptyTree(Tree):
152
self._inventory = Inventory()
154
def has_filename(self, filename):
157
def list_files(self):
158
if False: # just to make it a generator
161
def __contains__(self, file_id):
162
return file_id in self._inventory
164
def get_file_sha1(self, file_id):
165
assert self._inventory[file_id].kind == "root_directory"
171
######################################################################
174
# TODO: Merge these two functions into a single one that can operate
175
# on either a whole tree or a set of files.
177
# TODO: Return the diff in order by filename, not by category or in
178
# random order. Can probably be done by lock-stepping through the
179
# filenames from both trees.
182
def file_status(filename, old_tree, new_tree):
183
"""Return single-letter status, old and new names for a file.
185
The complexity here is in deciding how to represent renames;
186
many complex cases are possible.
188
old_inv = old_tree.inventory
189
new_inv = new_tree.inventory
190
new_id = new_inv.path2id(filename)
191
old_id = old_inv.path2id(filename)
193
if not new_id and not old_id:
194
# easy: doesn't exist in either; not versioned at all
195
if new_tree.is_ignored(filename):
196
return 'I', None, None
198
return '?', None, None
200
# There is now a file of this name, great.
203
# There is no longer a file of this name, but we can describe
204
# what happened to the file that used to have
205
# this name. There are two possibilities: either it was
206
# deleted entirely, or renamed.
208
if new_inv.has_id(old_id):
209
return 'X', old_inv.id2path(old_id), new_inv.id2path(old_id)
211
return 'D', old_inv.id2path(old_id), None
213
# if the file_id is new in this revision, it is added
214
if new_id and not old_inv.has_id(new_id):
217
# if there used to be a file of this name, but that ID has now
218
# disappeared, it is deleted
219
if old_id and not new_inv.has_id(old_id):
226
def find_renames(old_inv, new_inv):
227
for file_id in old_inv:
228
if file_id not in new_inv:
230
old_name = old_inv.id2path(file_id)
231
new_name = new_inv.id2path(file_id)
232
if old_name != new_name:
233
yield (old_name, new_name)
237
######################################################################
240
def dir_exporter(tree, dest, root):
241
"""Export this tree to a new directory.
243
`dest` should not exist, and will be created holding the
244
contents of this tree.
246
TODO: To handle subdirectories we need to create the
249
:note: If the export fails, the destination directory will be
250
left in a half-assed state.
254
mutter('export version %r' % tree)
256
for dp, ie in inv.iter_entries():
258
fullpath = appendpath(dest, dp)
259
if kind == 'directory':
262
pumpfile(tree.get_file(ie.file_id), file(fullpath, 'wb'))
264
raise BzrError("don't know how to export {%s} of kind %r" % (ie.file_id, kind))
265
mutter(" export {%s} kind %s to %s" % (ie.file_id, kind, fullpath))
266
exporters['dir'] = dir_exporter
273
def get_root_name(dest):
274
"""Get just the root name for a tarball.
276
>>> get_root_name('mytar.tar')
278
>>> get_root_name('mytar.tar.bz2')
280
>>> get_root_name('tar.tar.tar.tgz')
282
>>> get_root_name('bzr-0.0.5.tar.gz')
284
>>> get_root_name('a/long/path/mytar.tgz')
286
>>> get_root_name('../parent/../dir/other.tbz2')
289
endings = ['.tar', '.tar.gz', '.tgz', '.tar.bz2', '.tbz2']
290
dest = os.path.basename(dest)
292
if dest.endswith(end):
293
return dest[:-len(end)]
295
def tar_exporter(tree, dest, root, compression=None):
296
"""Export this tree to a new tar file.
298
`dest` will be created holding the contents of this tree; if it
299
already exists, it will be clobbered, like with "tar -c".
301
from time import time
303
compression = str(compression or '')
305
root = get_root_name(dest)
307
ball = tarfile.open(dest, 'w:' + compression)
308
except tarfile.CompressionError, e:
309
raise BzrError(str(e))
310
mutter('export version %r' % tree)
312
for dp, ie in inv.iter_entries():
313
mutter(" export {%s} kind %s to %s" % (ie.file_id, ie.kind, dest))
314
item = tarfile.TarInfo(os.path.join(root, dp))
315
# TODO: would be cool to actually set it to the timestamp of the
316
# revision it was last changed
318
if ie.kind == 'directory':
319
item.type = tarfile.DIRTYPE
324
elif ie.kind == 'file':
325
item.type = tarfile.REGTYPE
326
fileobj = tree.get_file(ie.file_id)
327
item.size = _find_file_size(fileobj)
330
raise BzrError("don't know how to export {%s} of kind %r" %
331
(ie.file_id, ie.kind))
333
ball.addfile(item, fileobj)
335
exporters['tar'] = tar_exporter
337
def tgz_exporter(tree, dest, root):
338
tar_exporter(tree, dest, root, compression='gz')
339
exporters['tgz'] = tgz_exporter
341
def tbz_exporter(tree, dest, root):
342
tar_exporter(tree, dest, root, compression='bz2')
343
exporters['tbz2'] = tbz_exporter
346
def _find_file_size(fileobj):
347
offset = fileobj.tell()
350
size = fileobj.tell()
352
# gzip doesn't accept second argument to seek()
356
nread = len(fileobj.read())