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 fingerprint_file
30
"""Abstract file tree.
32
There are several subclasses:
34
* `WorkingTree` exists as files on disk editable by the user.
36
* `RevisionTree` is a tree as recorded at some point in the past.
40
Trees contain an `Inventory` object, and also know how to retrieve
41
file texts mentioned in the inventory, either from a working
42
directory or from a store.
44
It is possible for trees to contain files that are not described
45
in their inventory or vice versa; for this use `filenames()`.
47
Trees can be compared, etc, regardless of whether they are working
48
trees or versioned trees.
51
def has_filename(self, filename):
52
"""True if the tree has given filename."""
53
raise NotImplementedError()
55
def has_id(self, file_id):
56
return self.inventory.has_id(file_id)
58
def has_or_had_id(self, file_id):
59
if file_id == self.inventory.root.file_id:
61
return self.inventory.has_id(file_id)
66
return iter(self.inventory)
68
def id2path(self, file_id):
69
return self.inventory.id2path(file_id)
71
def kind(self, file_id):
72
raise NotImplementedError("subclasses must implement kind")
74
def _get_inventory(self):
75
return self._inventory
77
def get_file_by_path(self, path):
78
return self.get_file(self._inventory.path2id(path))
80
inventory = property(_get_inventory,
81
doc="Inventory of this Tree")
83
def _check_retrieved(self, ie, f):
86
fp = fingerprint_file(f)
89
if ie.text_size != None:
90
if ie.text_size != fp['size']:
91
raise BzrError("mismatched size for file %r in %r" % (ie.file_id, self._store),
92
["inventory expects %d bytes" % ie.text_size,
93
"file is actually %d bytes" % fp['size'],
94
"store is probably damaged/corrupt"])
96
if ie.text_sha1 != fp['sha1']:
97
raise BzrError("wrong SHA-1 for file %r in %r" % (ie.file_id, self._store),
98
["inventory expects %s" % ie.text_sha1,
99
"file is actually %s" % fp['sha1'],
100
"store is probably damaged/corrupt"])
103
def print_file(self, file_id):
104
"""Print file with id `file_id` to stdout."""
106
sys.stdout.write(self.get_file_text(file_id))
114
def filter_unversioned_files(self, paths):
115
"""Filter out paths that are not versioned.
117
:return: set of paths.
119
# NB: we specifically *don't* call self.has_filename, because for
120
# WorkingTrees that can indicate files that exist on disk but that
122
pred = self.inventory.has_filename
123
return set((p for p in paths if not pred(p)))
126
class RevisionTree(Tree):
127
"""Tree viewing a previous revision.
129
File text can be retrieved from the text store.
131
TODO: Some kind of `__repr__` method, but a good one
132
probably means knowing the branch and revision number,
133
or at least passing a description to the constructor.
136
def __init__(self, branch, inv, revision_id):
137
self._branch = branch
138
self._weave_store = branch.weave_store
139
self._inventory = inv
140
self._revision_id = revision_id
142
def get_weave(self, file_id):
143
return self._weave_store.get_weave(file_id,
144
self._branch.get_transaction())
146
def get_file_lines(self, file_id):
147
ie = self._inventory[file_id]
148
weave = self.get_weave(file_id)
149
return weave.get_lines(ie.revision)
151
def get_file_text(self, file_id):
152
return ''.join(self.get_file_lines(file_id))
154
def get_file(self, file_id):
155
return StringIO(self.get_file_text(file_id))
157
def get_file_size(self, file_id):
158
return self._inventory[file_id].text_size
160
def get_file_sha1(self, file_id, path=None):
161
ie = self._inventory[file_id]
162
if ie.kind == "file":
166
def is_executable(self, file_id, path=None):
167
ie = self._inventory[file_id]
168
if ie.kind != "file":
170
return self._inventory[file_id].executable
172
def has_filename(self, filename):
173
return bool(self.inventory.path2id(filename))
175
def list_files(self):
176
# The only files returned by this are those from the version
177
for path, entry in self.inventory.iter_entries():
178
yield path, 'V', entry.kind, entry.file_id, entry
180
def get_symlink_target(self, file_id):
181
ie = self._inventory[file_id]
182
return ie.symlink_target;
184
def kind(self, file_id):
185
return self._inventory[file_id].kind
188
self._branch.lock_read()
191
self._branch.unlock()
194
class EmptyTree(Tree):
196
self._inventory = Inventory()
198
def get_symlink_target(self, file_id):
201
def has_filename(self, filename):
204
def kind(self, file_id):
205
assert self._inventory[file_id].kind == "root_directory"
206
return "root_directory"
208
def list_files(self):
211
def __contains__(self, file_id):
212
return file_id in self._inventory
214
def get_file_sha1(self, file_id, path=None):
215
assert self._inventory[file_id].kind == "root_directory"
219
######################################################################
222
# TODO: Merge these two functions into a single one that can operate
223
# on either a whole tree or a set of files.
225
# TODO: Return the diff in order by filename, not by category or in
226
# random order. Can probably be done by lock-stepping through the
227
# filenames from both trees.
230
def file_status(filename, old_tree, new_tree):
231
"""Return single-letter status, old and new names for a file.
233
The complexity here is in deciding how to represent renames;
234
many complex cases are possible.
236
old_inv = old_tree.inventory
237
new_inv = new_tree.inventory
238
new_id = new_inv.path2id(filename)
239
old_id = old_inv.path2id(filename)
241
if not new_id and not old_id:
242
# easy: doesn't exist in either; not versioned at all
243
if new_tree.is_ignored(filename):
244
return 'I', None, None
246
return '?', None, None
248
# There is now a file of this name, great.
251
# There is no longer a file of this name, but we can describe
252
# what happened to the file that used to have
253
# this name. There are two possibilities: either it was
254
# deleted entirely, or renamed.
256
if new_inv.has_id(old_id):
257
return 'X', old_inv.id2path(old_id), new_inv.id2path(old_id)
259
return 'D', old_inv.id2path(old_id), None
261
# if the file_id is new in this revision, it is added
262
if new_id and not old_inv.has_id(new_id):
265
# if there used to be a file of this name, but that ID has now
266
# disappeared, it is deleted
267
if old_id and not new_inv.has_id(old_id):
274
def find_renames(old_inv, new_inv):
275
for file_id in old_inv:
276
if file_id not in new_inv:
278
old_name = old_inv.id2path(file_id)
279
new_name = new_inv.id2path(file_id)
280
if old_name != new_name:
281
yield (old_name, new_name)