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))
114
def filter_unversioned_files(self, paths):
115
"""Filter out paths that are not versioned.
117
:return: set of paths.
119
return set((p for p in paths if not self.has_filename(p)))
122
class RevisionTree(Tree):
123
"""Tree viewing a previous revision.
125
File text can be retrieved from the text store.
127
TODO: Some kind of `__repr__` method, but a good one
128
probably means knowing the branch and revision number,
129
or at least passing a description to the constructor.
132
def __init__(self, branch, inv, revision_id):
133
self._branch = branch
134
self._weave_store = branch.weave_store
135
self._inventory = inv
136
self._revision_id = revision_id
138
def get_weave(self, file_id):
139
return self._weave_store.get_weave(file_id,
140
self._branch.get_transaction())
142
def get_file_lines(self, file_id):
143
ie = self._inventory[file_id]
144
weave = self.get_weave(file_id)
145
return weave.get_lines(ie.revision)
147
def get_file_text(self, file_id):
148
return ''.join(self.get_file_lines(file_id))
150
def get_file(self, file_id):
151
return StringIO(self.get_file_text(file_id))
153
def get_file_size(self, file_id):
154
return self._inventory[file_id].text_size
156
def get_file_sha1(self, file_id):
157
ie = self._inventory[file_id]
158
if ie.kind == "file":
161
def is_executable(self, file_id):
162
ie = self._inventory[file_id]
163
if ie.kind != "file":
165
return self._inventory[file_id].executable
167
def has_filename(self, filename):
168
return bool(self.inventory.path2id(filename))
170
def list_files(self):
171
# The only files returned by this are those from the version
172
for path, entry in self.inventory.iter_entries():
173
yield path, 'V', entry.kind, entry.file_id, entry
175
def get_symlink_target(self, file_id):
176
ie = self._inventory[file_id]
177
return ie.symlink_target;
179
def kind(self, file_id):
180
return self._inventory[file_id].kind
183
self._branch.lock_read()
186
self._branch.unlock()
189
class EmptyTree(Tree):
191
self._inventory = Inventory()
193
def get_symlink_target(self, file_id):
196
def has_filename(self, filename):
199
def kind(self, file_id):
200
assert self._inventory[file_id].kind == "root_directory"
201
return "root_directory"
203
def list_files(self):
206
def __contains__(self, file_id):
207
return file_id in self._inventory
209
def get_file_sha1(self, file_id):
210
assert self._inventory[file_id].kind == "root_directory"
214
######################################################################
217
# TODO: Merge these two functions into a single one that can operate
218
# on either a whole tree or a set of files.
220
# TODO: Return the diff in order by filename, not by category or in
221
# random order. Can probably be done by lock-stepping through the
222
# filenames from both trees.
225
def file_status(filename, old_tree, new_tree):
226
"""Return single-letter status, old and new names for a file.
228
The complexity here is in deciding how to represent renames;
229
many complex cases are possible.
231
old_inv = old_tree.inventory
232
new_inv = new_tree.inventory
233
new_id = new_inv.path2id(filename)
234
old_id = old_inv.path2id(filename)
236
if not new_id and not old_id:
237
# easy: doesn't exist in either; not versioned at all
238
if new_tree.is_ignored(filename):
239
return 'I', None, None
241
return '?', None, None
243
# There is now a file of this name, great.
246
# There is no longer a file of this name, but we can describe
247
# what happened to the file that used to have
248
# this name. There are two possibilities: either it was
249
# deleted entirely, or renamed.
251
if new_inv.has_id(old_id):
252
return 'X', old_inv.id2path(old_id), new_inv.id2path(old_id)
254
return 'D', old_inv.id2path(old_id), None
256
# if the file_id is new in this revision, it is added
257
if new_id and not old_inv.has_id(new_id):
260
# if there used to be a file of this name, but that ID has now
261
# disappeared, it is deleted
262
if old_id and not new_inv.has_id(old_id):
269
def find_renames(old_inv, new_inv):
270
for file_id in old_inv:
271
if file_id not in new_inv:
273
old_name = old_inv.id2path(file_id)
274
new_name = new_inv.id2path(file_id)
275
if old_name != new_name:
276
yield (old_name, new_name)
added
removed
bzrlib/tree.py
