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# out-of-date.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
26
# TODO: Perhaps use a Python pickle instead of a text file; might be faster.
30
CACHE_HEADER = "### bzr hashcache v5\n"
34
from bzrlib.osutils import sha_file
35
from bzrlib.trace import mutter, warning
36
from bzrlib.atomicfile import AtomicFile
41
def _fingerprint(abspath):
43
fs = os.lstat(abspath)
45
# might be missing, etc
48
if stat.S_ISDIR(fs.st_mode):
51
# we discard any high precision because it's not reliable; perhaps we
52
# could do better on some systems?
53
return (fs.st_size, long(fs.st_mtime),
54
long(fs.st_ctime), fs.st_ino, fs.st_dev)
57
class HashCache(object):
58
"""Cache for looking up file SHA-1.
60
Files are considered to match the cached value if the fingerprint
61
of the file has not changed. This includes its mtime, ctime,
62
device number, inode number, and size. This should catch
63
modifications or replacement of the file by a new one.
65
This may not catch modifications that do not change the file's
66
size and that occur within the resolution window of the
67
timestamps. To handle this we specifically do not cache files
68
which have changed since the start of the present second, since
69
they could undetectably change again.
71
This scheme may fail if the machine's clock steps backwards.
74
This does not canonicalize the paths passed in; that should be
78
Indexed by path, points to a two-tuple of the SHA-1 of the file.
82
number of times files have been statted
85
number of times files have been retrieved from the cache, avoiding a
89
number of misses (times files have been completely re-read)
93
def __init__(self, basedir):
94
self.basedir = basedir
99
self.removed_count = 0
100
self.update_count = 0
104
def cache_file_name(self):
105
return os.sep.join([self.basedir, '.bzr', 'stat-cache'])
111
"""Discard all cached information.
113
This does not reset the counters."""
115
self.needs_write = True
120
"""Scan all files and remove entries where the cache entry is obsolete.
122
Obsolete entries are those where the file has been modified or deleted
123
since the entry was inserted.
125
prep = [(ce[1][3], path, ce) for (path, ce) in self._cache.iteritems()]
128
for inum, path, cache_entry in prep:
129
abspath = os.sep.join([self.basedir, path])
130
fp = _fingerprint(abspath)
133
cache_fp = cache_entry[1]
135
if (not fp) or (cache_fp != fp):
136
# not here or not a regular file anymore
137
self.removed_count += 1
138
self.needs_write = True
139
del self._cache[path]
143
def get_sha1(self, path):
144
"""Return the sha1 of a file.
146
abspath = os.sep.join([self.basedir, path])
148
file_fp = _fingerprint(abspath)
151
# not a regular file or not existing
152
if path in self._cache:
153
self.removed_count += 1
154
self.needs_write = True
155
del self._cache[path]
158
if path in self._cache:
159
cache_sha1, cache_fp = self._cache[path]
161
cache_sha1, cache_fp = None, None
163
if cache_fp == file_fp:
168
digest = sha_file(file(abspath, 'rb', buffering=65000))
170
now = int(time.time())
171
if file_fp[1] >= now or file_fp[2] >= now:
172
# changed too recently; can't be cached. we can
173
# return the result and it could possibly be cached
175
self.danger_count += 1
177
self.removed_count += 1
178
self.needs_write = True
179
del self._cache[path]
181
self.update_count += 1
182
self.needs_write = True
183
self._cache[path] = (digest, file_fp)
191
"""Write contents of cache to file."""
192
outf = AtomicFile(self.cache_file_name(), 'wb')
194
print >>outf, CACHE_HEADER,
196
for path, c in self._cache.iteritems():
197
assert '//' not in path, path
198
outf.write(path.encode('utf-8'))
200
print >>outf, c[0], # hex sha1
202
print >>outf, "%d" % fld,
206
self.needs_write = False
214
"""Reinstate cache from file.
216
Overwrites existing cache.
218
If the cache file has the wrong version marker, this just clears
222
fn = self.cache_file_name()
224
inf = file(fn, 'rb', buffering=65000)
226
mutter("failed to open %s: %s" % (fn, e))
227
# better write it now so it is valid
228
self.needs_write = True
233
if hdr != CACHE_HEADER:
234
mutter('cache header marker not found at top of %s; discarding cache'
236
self.needs_write = True
241
path = l[:pos].decode('utf-8')
242
if path in self._cache:
243
warning('duplicated path %r in cache' % path)
247
fields = l[pos:].split(' ')
249
warning("bad line in hashcache: %r" % l)
254
warning("bad sha1 in hashcache: %r" % sha1)
257
fp = tuple(map(long, fields[1:]))
259
self._cache[path] = (sha1, fp)
261
self.needs_write = False
added
removed
bzrlib/hashcache.py
