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
# TODO: Up-front, stat all files in order and remove those which are deleted or
18
# out-of-date. Don't actually re-read them until they're needed. That ought
19
# to bring all the inodes into core so that future stats to them are fast, and
20
# it preserves the nice property that any caller will always get up-to-date
21
# data except in unavoidable cases.
23
# TODO: Perhaps return more details on the file to avoid statting it
24
# again: nonexistent, file type, size, etc
28
CACHE_HEADER = "### bzr hashcache v5\n"
32
from bzrlib.osutils import sha_file
33
from bzrlib.trace import mutter, warning
37
def _fingerprint(abspath):
39
fs = os.lstat(abspath)
41
# might be missing, etc
44
if stat.S_ISDIR(fs.st_mode):
47
# we discard any high precision because it's not reliable; perhaps we
48
# could do better on some systems?
49
return (fs.st_size, long(fs.st_mtime),
50
long(fs.st_ctime), fs.st_ino, fs.st_dev)
53
class HashCache(object):
54
"""Cache for looking up file SHA-1.
56
Files are considered to match the cached value if the fingerprint
57
of the file has not changed. This includes its mtime, ctime,
58
device number, inode number, and size. This should catch
59
modifications or replacement of the file by a new one.
61
This may not catch modifications that do not change the file's
62
size and that occur within the resolution window of the
63
timestamps. To handle this we specifically do not cache files
64
which have changed since the start of the present second, since
65
they could undetectably change again.
67
This scheme may fail if the machine's clock steps backwards.
70
This does not canonicalize the paths passed in; that should be
74
Indexed by path, points to a two-tuple of the SHA-1 of the file.
78
number of times files have been statted
81
number of times files have been retrieved from the cache, avoiding a
85
number of misses (times files have been completely re-read)
89
def __init__(self, basedir):
90
self.basedir = basedir
95
self.removed_count = 0
100
def cache_file_name(self):
101
return os.sep.join([self.basedir, '.bzr', 'stat-cache'])
107
"""Discard all cached information.
109
This does not reset the counters."""
111
self.needs_write = True
116
"""Scan all files and remove entries where the cache entry is obsolete.
118
Obsolete entries are those where the file has been modified or deleted
119
since the entry was inserted.
121
prep = [(ce[1][3], path, ce) for (path, ce) in self._cache.iteritems()]
124
for inum, path, cache_entry in prep:
125
abspath = os.sep.join([self.basedir, path])
126
fp = _fingerprint(abspath)
129
cache_fp = cache_entry[1]
131
if (not fp) or (cache_fp != fp):
132
# not here or not a regular file anymore
133
self.removed_count += 1
134
self.needs_write = True
135
del self._cache[path]
139
def get_sha1(self, path):
140
"""Return the sha1 of a file.
142
abspath = os.sep.join([self.basedir, path])
144
file_fp = _fingerprint(abspath)
147
# not a regular file or not existing
148
if path in self._cache:
149
self.removed_count += 1
150
self.needs_write = True
151
del self._cache[path]
154
if path in self._cache:
155
cache_sha1, cache_fp = self._cache[path]
157
cache_sha1, cache_fp = None, None
159
if cache_fp == file_fp:
164
digest = sha_file(file(abspath, 'rb', buffering=65000))
166
now = int(time.time())
167
if file_fp[1] >= now or file_fp[2] >= now:
168
# changed too recently; can't be cached. we can
169
# return the result and it could possibly be cached
171
self.danger_count += 1
173
self.removed_count += 1
174
self.needs_write = True
175
del self._cache[path]
177
self.update_count += 1
178
self.needs_write = True
179
self._cache[path] = (digest, file_fp)
187
"""Write contents of cache to file."""
188
from atomicfile import AtomicFile
190
outf = AtomicFile(self.cache_file_name(), 'wb')
192
print >>outf, CACHE_HEADER,
194
for path, c in self._cache.iteritems():
195
assert '//' not in path, path
196
outf.write(path.encode('utf-8'))
198
print >>outf, c[0], # hex sha1
200
print >>outf, "%d" % fld,
204
self.needs_write = False
212
"""Reinstate cache from file.
214
Overwrites existing cache.
216
If the cache file has the wrong version marker, this just clears
220
fn = self.cache_file_name()
222
inf = file(fn, 'rb', buffering=65000)
224
mutter("failed to open %s: %s" % (fn, e))
229
if hdr != CACHE_HEADER:
230
mutter('cache header marker not found at top of %s; discarding cache'
236
path = l[:pos].decode('utf-8')
237
if path in self._cache:
238
warning('duplicated path %r in cache' % path)
242
fields = l[pos:].split(' ')
244
warning("bad line in hashcache: %r" % l)
249
warning("bad sha1 in hashcache: %r" % sha1)
252
fp = tuple(map(long, fields[1:]))
254
self._cache[path] = (sha1, fp)
256
self.needs_write = False
added
removed
bzrlib/hashcache.py
