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.
21
from cStringIO import StringIO
24
from bzrlib.trace import mutter, note
25
from bzrlib.errors import BzrError, BzrCheckError
26
from bzrlib.inventory import Inventory
27
from bzrlib.osutils import pumpfile, appendpath, fingerprint_file
33
"""Abstract file tree.
35
There are several subclasses:
37
* `WorkingTree` exists as files on disk editable by the user.
39
* `RevisionTree` is a tree as recorded at some point in the past.
43
Trees contain an `Inventory` object, and also know how to retrieve
44
file texts mentioned in the inventory, either from a working
45
directory or from a store.
47
It is possible for trees to contain files that are not described
48
in their inventory or vice versa; for this use `filenames()`.
50
Trees can be compared, etc, regardless of whether they are working
51
trees or versioned trees.
54
def has_filename(self, filename):
55
"""True if the tree has given filename."""
56
raise NotImplementedError()
58
def has_id(self, file_id):
59
return self.inventory.has_id(file_id)
64
return iter(self.inventory)
66
def id2path(self, file_id):
67
return self.inventory.id2path(file_id)
69
def _get_inventory(self):
70
return self._inventory
72
def get_file_by_path(self, path):
73
return self.get_file(self._inventory.path2id(path))
75
inventory = property(_get_inventory,
76
doc="Inventory of this Tree")
78
def _check_retrieved(self, ie, f):
79
fp = fingerprint_file(f)
82
if ie.text_size != None:
83
if ie.text_size != fp['size']:
84
raise BzrError("mismatched size for file %r in %r" % (ie.file_id, self._store),
85
["inventory expects %d bytes" % ie.text_size,
86
"file is actually %d bytes" % fp['size'],
87
"store is probably damaged/corrupt"])
89
if ie.text_sha1 != fp['sha1']:
90
raise BzrError("wrong SHA-1 for file %r in %r" % (ie.file_id, self._store),
91
["inventory expects %s" % ie.text_sha1,
92
"file is actually %s" % fp['sha1'],
93
"store is probably damaged/corrupt"])
96
def print_file(self, file_id):
97
"""Print file with id `file_id` to stdout."""
99
sys.stdout.write(self.get_file_text(file_id))
102
def export(self, dest, format='dir', root=None):
103
"""Export this tree."""
105
exporter = exporters[format]
107
from bzrlib.errors import BzrCommandError
108
raise BzrCommandError("export format %r not supported" % format)
109
exporter(self, dest, root)
113
class RevisionTree(Tree):
114
"""Tree viewing a previous revision.
116
File text can be retrieved from the text store.
118
TODO: Some kind of `__repr__` method, but a good one
119
probably means knowing the branch and revision number,
120
or at least passing a description to the constructor.
123
def __init__(self, weave_store, inv, revision_id):
124
self._weave_store = weave_store
125
self._inventory = inv
126
self._revision_id = revision_id
128
def get_file_text(self, file_id):
129
ie = self._inventory[file_id]
130
weave = self._weave_store.get_weave(file_id)
131
idx = weave.lookup(self._revision_id)
132
content = weave.get_text(idx)
133
if len(content) != ie.text_size:
134
raise BzrCheckError('mismatched size on revision %s of file %s: '
136
% (self._revision_id, file_id, len(content),
140
def get_file(self, file_id):
141
return StringIO(self.get_file_text(file_id))
143
def get_file_size(self, file_id):
144
return self._inventory[file_id].text_size
146
def get_file_sha1(self, file_id):
147
ie = self._inventory[file_id]
148
if ie.kind == "file":
151
def has_filename(self, filename):
152
return bool(self.inventory.path2id(filename))
154
def list_files(self):
155
# The only files returned by this are those from the version
156
for path, entry in self.inventory.iter_entries():
157
yield path, 'V', entry.kind, entry.file_id
160
class EmptyTree(Tree):
162
self._inventory = Inventory()
164
def has_filename(self, filename):
167
def list_files(self):
168
if False: # just to make it a generator
171
def __contains__(self, file_id):
172
return file_id in self._inventory
174
def get_file_sha1(self, file_id):
175
assert self._inventory[file_id].kind == "root_directory"
181
######################################################################
184
# TODO: Merge these two functions into a single one that can operate
185
# on either a whole tree or a set of files.
187
# TODO: Return the diff in order by filename, not by category or in
188
# random order. Can probably be done by lock-stepping through the
189
# filenames from both trees.
192
def file_status(filename, old_tree, new_tree):
193
"""Return single-letter status, old and new names for a file.
195
The complexity here is in deciding how to represent renames;
196
many complex cases are possible.
198
old_inv = old_tree.inventory
199
new_inv = new_tree.inventory
200
new_id = new_inv.path2id(filename)
201
old_id = old_inv.path2id(filename)
203
if not new_id and not old_id:
204
# easy: doesn't exist in either; not versioned at all
205
if new_tree.is_ignored(filename):
206
return 'I', None, None
208
return '?', None, None
210
# There is now a file of this name, great.
213
# There is no longer a file of this name, but we can describe
214
# what happened to the file that used to have
215
# this name. There are two possibilities: either it was
216
# deleted entirely, or renamed.
218
if new_inv.has_id(old_id):
219
return 'X', old_inv.id2path(old_id), new_inv.id2path(old_id)
221
return 'D', old_inv.id2path(old_id), None
223
# if the file_id is new in this revision, it is added
224
if new_id and not old_inv.has_id(new_id):
227
# if there used to be a file of this name, but that ID has now
228
# disappeared, it is deleted
229
if old_id and not new_inv.has_id(old_id):
236
def find_renames(old_inv, new_inv):
237
for file_id in old_inv:
238
if file_id not in new_inv:
240
old_name = old_inv.id2path(file_id)
241
new_name = new_inv.id2path(file_id)
242
if old_name != new_name:
243
yield (old_name, new_name)
247
######################################################################
250
def dir_exporter(tree, dest, root):
251
"""Export this tree to a new directory.
253
`dest` should not exist, and will be created holding the
254
contents of this tree.
256
TODO: To handle subdirectories we need to create the
259
:note: If the export fails, the destination directory will be
260
left in a half-assed state.
264
mutter('export version %r' % tree)
266
for dp, ie in inv.iter_entries():
268
fullpath = appendpath(dest, dp)
269
if kind == 'directory':
272
pumpfile(tree.get_file(ie.file_id), file(fullpath, 'wb'))
274
raise BzrError("don't know how to export {%s} of kind %r" % (ie.file_id, kind))
275
mutter(" export {%s} kind %s to %s" % (ie.file_id, kind, fullpath))
276
exporters['dir'] = dir_exporter
283
def get_root_name(dest):
284
"""Get just the root name for a tarball.
286
>>> get_root_name('mytar.tar')
288
>>> get_root_name('mytar.tar.bz2')
290
>>> get_root_name('tar.tar.tar.tgz')
292
>>> get_root_name('bzr-0.0.5.tar.gz')
294
>>> get_root_name('a/long/path/mytar.tgz')
296
>>> get_root_name('../parent/../dir/other.tbz2')
299
endings = ['.tar', '.tar.gz', '.tgz', '.tar.bz2', '.tbz2']
300
dest = os.path.basename(dest)
302
if dest.endswith(end):
303
return dest[:-len(end)]
305
def tar_exporter(tree, dest, root, compression=None):
306
"""Export this tree to a new tar file.
308
`dest` will be created holding the contents of this tree; if it
309
already exists, it will be clobbered, like with "tar -c".
311
from time import time
313
compression = str(compression or '')
315
root = get_root_name(dest)
317
ball = tarfile.open(dest, 'w:' + compression)
318
except tarfile.CompressionError, e:
319
raise BzrError(str(e))
320
mutter('export version %r' % tree)
322
for dp, ie in inv.iter_entries():
323
mutter(" export {%s} kind %s to %s" % (ie.file_id, ie.kind, dest))
324
item = tarfile.TarInfo(os.path.join(root, dp))
325
# TODO: would be cool to actually set it to the timestamp of the
326
# revision it was last changed
328
if ie.kind == 'directory':
329
item.type = tarfile.DIRTYPE
334
elif ie.kind == 'file':
335
item.type = tarfile.REGTYPE
336
fileobj = tree.get_file(ie.file_id)
337
item.size = _find_file_size(fileobj)
340
raise BzrError("don't know how to export {%s} of kind %r" %
341
(ie.file_id, ie.kind))
343
ball.addfile(item, fileobj)
345
exporters['tar'] = tar_exporter
347
def tgz_exporter(tree, dest, root):
348
tar_exporter(tree, dest, root, compression='gz')
349
exporters['tgz'] = tgz_exporter
351
def tbz_exporter(tree, dest, root):
352
tar_exporter(tree, dest, root, compression='bz2')
353
exporters['tbz2'] = tbz_exporter
356
def _find_file_size(fileobj):
357
offset = fileobj.tell()
360
size = fileobj.tell()
362
# gzip doesn't accept second argument to seek()
366
nread = len(fileobj.read())
added
removed
bzrlib/tree.py
