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
import os.path, os, fnmatch, time
23
from osutils import pumpfile, filesize, quotefn, sha_file, \
24
joinpath, splitpath, appendpath, isdir, isfile, file_kind, fingerprint_file
26
from stat import S_ISREG, S_ISDIR, ST_MODE, ST_SIZE
28
from bzrlib.inventory import Inventory
29
from bzrlib.trace import mutter, note
30
from bzrlib.errors import BzrError
38
"""Abstract file tree.
40
There are several subclasses:
42
* `WorkingTree` exists as files on disk editable by the user.
44
* `RevisionTree` is a tree as recorded at some point in the past.
48
Trees contain an `Inventory` object, and also know how to retrieve
49
file texts mentioned in the inventory, either from a working
50
directory or from a store.
52
It is possible for trees to contain files that are not described
53
in their inventory or vice versa; for this use `filenames()`.
55
Trees can be compared, etc, regardless of whether they are working
56
trees or versioned trees.
59
def has_filename(self, filename):
60
"""True if the tree has given filename."""
61
raise NotImplementedError()
63
def has_id(self, file_id):
64
return self.inventory.has_id(file_id)
69
return iter(self.inventory)
71
def id2path(self, file_id):
72
return self.inventory.id2path(file_id)
74
def _get_inventory(self):
75
return self._inventory
77
inventory = property(_get_inventory,
78
doc="Inventory of this Tree")
80
def _check_retrieved(self, ie, f):
81
fp = fingerprint_file(f)
84
if ie.text_size != None:
85
if ie.text_size != fp['size']:
86
raise BzrError("mismatched size for file %r in %r" % (ie.file_id, self._store),
87
["inventory expects %d bytes" % ie.text_size,
88
"file is actually %d bytes" % fp['size'],
89
"store is probably damaged/corrupt"])
91
if ie.text_sha1 != fp['sha1']:
92
raise BzrError("wrong SHA-1 for file %r in %r" % (ie.file_id, self._store),
93
["inventory expects %s" % ie.text_sha1,
94
"file is actually %s" % fp['sha1'],
95
"store is probably damaged/corrupt"])
98
def print_file(self, fileid):
99
"""Print file with id `fileid` to stdout."""
101
pumpfile(self.get_file(fileid), sys.stdout)
104
def export(self, dest, format='dir'):
105
"""Export this tree."""
107
exporter = exporters[format]
109
raise BzrCommandError("export format %r not supported" % format)
114
class RevisionTree(Tree):
115
"""Tree viewing a previous revision.
117
File text can be retrieved from the text store.
119
TODO: Some kind of `__repr__` method, but a good one
120
probably means knowing the branch and revision number,
121
or at least passing a description to the constructor.
124
def __init__(self, store, inv):
126
self._inventory = inv
128
def get_file(self, file_id):
129
ie = self._inventory[file_id]
130
f = self._store[ie.text_id]
131
mutter(" get fileid{%s} from %r" % (file_id, self))
132
self._check_retrieved(ie, f)
135
def get_file_size(self, file_id):
136
return self._inventory[file_id].text_size
138
def get_file_sha1(self, file_id):
139
ie = self._inventory[file_id]
142
def has_filename(self, filename):
143
return bool(self.inventory.path2id(filename))
145
def list_files(self):
146
# The only files returned by this are those from the version
147
for path, entry in self.inventory.iter_entries():
148
yield path, 'V', entry.kind, entry.file_id
151
class EmptyTree(Tree):
153
self._inventory = Inventory()
155
def has_filename(self, filename):
158
def list_files(self):
159
if False: # just to make it a generator
164
######################################################################
167
# TODO: Merge these two functions into a single one that can operate
168
# on either a whole tree or a set of files.
170
# TODO: Return the diff in order by filename, not by category or in
171
# random order. Can probably be done by lock-stepping through the
172
# filenames from both trees.
175
def file_status(filename, old_tree, new_tree):
176
"""Return single-letter status, old and new names for a file.
178
The complexity here is in deciding how to represent renames;
179
many complex cases are possible.
181
old_inv = old_tree.inventory
182
new_inv = new_tree.inventory
183
new_id = new_inv.path2id(filename)
184
old_id = old_inv.path2id(filename)
186
if not new_id and not old_id:
187
# easy: doesn't exist in either; not versioned at all
188
if new_tree.is_ignored(filename):
189
return 'I', None, None
191
return '?', None, None
193
# There is now a file of this name, great.
196
# There is no longer a file of this name, but we can describe
197
# what happened to the file that used to have
198
# this name. There are two possibilities: either it was
199
# deleted entirely, or renamed.
201
if new_inv.has_id(old_id):
202
return 'X', old_inv.id2path(old_id), new_inv.id2path(old_id)
204
return 'D', old_inv.id2path(old_id), None
206
# if the file_id is new in this revision, it is added
207
if new_id and not old_inv.has_id(new_id):
210
# if there used to be a file of this name, but that ID has now
211
# disappeared, it is deleted
212
if old_id and not new_inv.has_id(old_id):
219
def find_renames(old_inv, new_inv):
220
for file_id in old_inv:
221
if file_id not in new_inv:
223
old_name = old_inv.id2path(file_id)
224
new_name = new_inv.id2path(file_id)
225
if old_name != new_name:
226
yield (old_name, new_name)
230
######################################################################
233
def dir_exporter(tree, dest):
234
"""Export this tree to a new directory.
236
`dest` should not exist, and will be created holding the
237
contents of this tree.
239
TODO: To handle subdirectories we need to create the
242
:note: If the export fails, the destination directory will be
243
left in a half-assed state.
246
mutter('export version %r' % tree)
248
for dp, ie in inv.iter_entries():
250
fullpath = appendpath(dest, dp)
251
if kind == 'directory':
254
pumpfile(tree.get_file(ie.file_id), file(fullpath, 'wb'))
256
raise BzrError("don't know how to export {%s} of kind %r" % (ie.file_id, kind))
257
mutter(" export {%s} kind %s to %s" % (ie.file_id, kind, fullpath))
258
exporters['dir'] = dir_exporter
265
def tar_exporter(tree, dest, compression=None):
266
"""Export this tree to a new tar file.
268
`dest` will be created holding the contents of this tree; if it
269
already exists, it will be clobbered, like with "tar -c".
272
compression = str(compression or '')
274
ball = tarfile.open(dest, 'w:' + compression)
275
except tarfile.CompressionError, e:
276
raise BzrError(str(e))
277
mutter('export version %r' % tree)
279
for dp, ie in inv.iter_entries():
280
mutter(" export {%s} kind %s to %s" % (ie.file_id, ie.kind, dest))
281
item = tarfile.TarInfo(dp)
282
# TODO: would be cool to actually set it to the timestamp of the
283
# revision it was last changed
285
if ie.kind == 'directory':
286
item.type = tarfile.DIRTYPE
291
elif ie.kind == 'file':
292
item.type = tarfile.REGTYPE
293
fileobj = tree.get_file(ie.file_id)
294
item.size = _find_file_size(fileobj)
297
raise BzrError("don't know how to export {%s} of kind %r" %
298
(ie.file_id, ie.kind))
300
ball.addfile(item, fileobj)
302
exporters['tar'] = tar_exporter
304
def tgz_exporter(tree, dest):
305
tar_exporter(tree, dest, compression='gz')
306
exporters['tgz'] = tgz_exporter
308
def tbz_exporter(tree, dest):
309
tar_exporter(tree, dest, compression='bz2')
310
exporters['tbz2'] = tbz_exporter
313
def _find_file_size(fileobj):
314
offset = fileobj.tell()
317
size = fileobj.tell()
319
# gzip doesn't accept second argument to seek()
323
nread = len(fileobj.read())