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 appendpath, 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))
109
class RevisionTree(Tree):
110
"""Tree viewing a previous revision.
112
File text can be retrieved from the text store.
114
TODO: Some kind of `__repr__` method, but a good one
115
probably means knowing the branch and revision number,
116
or at least passing a description to the constructor.
119
def __init__(self, weave_store, inv, revision_id):
120
self._weave_store = weave_store
121
self._inventory = inv
122
self._revision_id = revision_id
124
def get_weave(self, file_id):
125
# FIXME: RevisionTree should be given a branch
126
# not a store, or the store should know the branch.
127
import bzrlib.transactions as transactions
128
return self._weave_store.get_weave(file_id,
129
transactions.PassThroughTransaction())
132
def get_file_lines(self, file_id):
133
ie = self._inventory[file_id]
134
weave = self.get_weave(file_id)
135
return weave.get(ie.revision)
138
def get_file_text(self, file_id):
139
return ''.join(self.get_file_lines(file_id))
142
def get_file(self, file_id):
143
return StringIO(self.get_file_text(file_id))
145
def get_file_size(self, file_id):
146
return self._inventory[file_id].text_size
148
def get_file_sha1(self, file_id):
149
ie = self._inventory[file_id]
150
if ie.kind == "file":
153
def is_executable(self, file_id):
154
ie = self._inventory[file_id]
155
if ie.kind != "file":
157
return self._inventory[file_id].executable
159
def has_filename(self, filename):
160
return bool(self.inventory.path2id(filename))
162
def list_files(self):
163
# The only files returned by this are those from the version
164
for path, entry in self.inventory.iter_entries():
165
yield path, 'V', entry.kind, entry.file_id, entry
167
def get_symlink_target(self, file_id):
168
ie = self._inventory[file_id]
169
return ie.symlink_target;
171
def kind(self, file_id):
172
return self._inventory[file_id].kind
175
class EmptyTree(Tree):
177
self._inventory = Inventory()
179
def get_symlink_target(self, file_id):
182
def has_filename(self, filename):
185
def kind(self, file_id):
186
assert self._inventory[file_id].kind == "root_directory"
187
return "root_directory"
189
def list_files(self):
192
def __contains__(self, file_id):
193
return file_id in self._inventory
195
def get_file_sha1(self, file_id):
196
assert self._inventory[file_id].kind == "root_directory"
200
######################################################################
203
# TODO: Merge these two functions into a single one that can operate
204
# on either a whole tree or a set of files.
206
# TODO: Return the diff in order by filename, not by category or in
207
# random order. Can probably be done by lock-stepping through the
208
# filenames from both trees.
211
def file_status(filename, old_tree, new_tree):
212
"""Return single-letter status, old and new names for a file.
214
The complexity here is in deciding how to represent renames;
215
many complex cases are possible.
217
old_inv = old_tree.inventory
218
new_inv = new_tree.inventory
219
new_id = new_inv.path2id(filename)
220
old_id = old_inv.path2id(filename)
222
if not new_id and not old_id:
223
# easy: doesn't exist in either; not versioned at all
224
if new_tree.is_ignored(filename):
225
return 'I', None, None
227
return '?', None, None
229
# There is now a file of this name, great.
232
# There is no longer a file of this name, but we can describe
233
# what happened to the file that used to have
234
# this name. There are two possibilities: either it was
235
# deleted entirely, or renamed.
237
if new_inv.has_id(old_id):
238
return 'X', old_inv.id2path(old_id), new_inv.id2path(old_id)
240
return 'D', old_inv.id2path(old_id), None
242
# if the file_id is new in this revision, it is added
243
if new_id and not old_inv.has_id(new_id):
246
# if there used to be a file of this name, but that ID has now
247
# disappeared, it is deleted
248
if old_id and not new_inv.has_id(old_id):
255
def find_renames(old_inv, new_inv):
256
for file_id in old_inv:
257
if file_id not in new_inv:
259
old_name = old_inv.id2path(file_id)
260
new_name = new_inv.id2path(file_id)
261
if old_name != new_name:
262
yield (old_name, new_name)