1
# (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
import stat, os, sha, time
18
from binascii import b2a_qp, a2b_qp
20
from trace import mutter
23
"""File stat cache to speed up tree comparisons.
25
This module basically gives a quick way to find the SHA-1 and related
26
information of a file in the working directory, without actually
27
reading and hashing the whole file.
29
This is done by maintaining a cache indexed by a file fingerprint of
30
(path, size, mtime, ctime, ino, dev) pointing to the SHA-1. If the
31
fingerprint has changed, we assume the file content has not changed
32
either and the SHA-1 is therefore the same.
34
If any of the fingerprint fields have changed then the file content
35
*may* have changed, or it may not have. We need to reread the file
36
contents to make sure, but this is not visible to the user or
37
higher-level code (except as a delay of course).
39
The mtime and ctime are stored with nanosecond fields, but not all
40
filesystems give this level of precision. There is therefore a
41
possible race: the file might be modified twice within a second
42
without changing the size or mtime, and a SHA-1 cached from the first
43
version would be wrong. We handle this by not recording a cached hash
44
for any files which were modified in the current second and that
45
therefore have the chance to change again before the second is up.
47
The only known hole in this design is if the system clock jumps
48
backwards crossing invocations of bzr. Please don't do that; use ntp
49
to gradually adjust your clock or don't use bzr over the step.
51
At the moment this is stored in a simple textfile; it might be nice
57
def fingerprint(path, abspath):
59
fs = os.lstat(abspath)
61
# might be missing, etc
64
if stat.S_ISDIR(fs.st_mode):
67
return (fs.st_size, fs.st_mtime,
68
fs.st_ctime, fs.st_ino, fs.st_dev)
71
def write_cache(branch, entry_iter):
72
outf = branch.controlfile('work-cache.tmp', 'wt')
73
for entry in entry_iter:
74
outf.write(entry[0] + ' ' + entry[1] + ' ')
75
outf.write(b2a_qp(entry[2], True))
76
outf.write(' %d %d %d %d %d\n' % entry[3:])
79
os.rename(branch.controlfilename('work-cache.tmp'),
80
branch.controlfilename('work-cache'))
84
def load_cache(branch):
88
cachefile = branch.controlfile('work-cache', 'rt')
96
raise BzrError("duplicated file_id in cache: {%s}" % file_id)
97
cache[file_id] = (f[0], f[1], a2b_qp(f[2])) + tuple([long(x) for x in f[3:]])
103
def _files_from_inventory(inv):
104
for path, ie in inv.iter_entries():
105
if ie.kind != 'file':
107
yield ie.file_id, path
110
def build_cache(branch):
111
inv = branch.read_working_inventory()
114
_update_cache_from_list(branch, cache, _files_from_inventory(inv))
118
def update_cache(branch, inv):
119
# TODO: It's supposed to be faster to stat the files in order by inum.
120
# We don't directly know the inum of the files of course but we do
121
# know where they were last sighted, so we can sort by that.
123
cache = load_cache(branch)
124
return _update_cache_from_list(branch, cache, _files_from_inventory(inv))
128
def _update_cache_from_list(branch, cache, to_update):
129
"""Update the cache to have info on the named files.
131
to_update is a sequence of (file_id, path) pairs.
133
hardcheck = dirty = 0
134
for file_id, path in to_update:
135
fap = branch.abspath(path)
136
fp = fingerprint(fap, path)
137
cacheentry = cache.get(file_id)
139
if fp == None: # not here
145
if cacheentry and (cacheentry[3:] == fp):
146
continue # all stat fields unchanged
150
dig = sha.new(file(fap, 'rb').read()).hexdigest()
152
if cacheentry == None or dig != cacheentry[1]:
153
# if there was no previous entry for this file, or if the
154
# SHA has changed, then update the cache
155
cacheentry = (file_id, dig, path) + fp
156
cache[file_id] = cacheentry
159
mutter('work cache: read %d files, %d changed' % (hardcheck, dirty))
162
write_cache(branch, cache.itervalues())
added
removed
bzrlib/cache.py
