~bzr-pqm/bzr/bzr.dev

846 by Martin Pool
- start adding refactored/simplified hash cache
1
# (C) 2005 Canonical Ltd
2
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.
7
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.
12
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
16
17
18
19
859 by Martin Pool
- add HashCache.write and a simple test for it
20
CACHE_HEADER = "### bzr statcache v5"    
21
22
846 by Martin Pool
- start adding refactored/simplified hash cache
23
def _fingerprint(abspath):
24
    import os, stat
25
26
    try:
27
        fs = os.lstat(abspath)
28
    except OSError:
29
        # might be missing, etc
30
        return None
31
32
    if stat.S_ISDIR(fs.st_mode):
33
        return None
34
35
    return (fs.st_size, fs.st_mtime,
36
            fs.st_ctime, fs.st_ino, fs.st_dev)
37
38
39
class HashCache(object):
40
    """Cache for looking up file SHA-1.
41
42
    Files are considered to match the cached value if the fingerprint
43
    of the file has not changed.  This includes its mtime, ctime,
44
    device number, inode number, and size.  This should catch
45
    modifications or replacement of the file by a new one.
46
47
    This may not catch modifications that do not change the file's
48
    size and that occur within the resolution window of the
49
    timestamps.  To handle this we specifically do not cache files
50
    which have changed since the start of the present second, since
51
    they could undetectably change again.
52
53
    This scheme may fail if the machine's clock steps backwards.
54
    Don't do that.
55
56
    This does not canonicalize the paths passed in; that should be
57
    done by the caller.
58
860 by Martin Pool
- refactor hashcache to use just one dictionary
59
    _cache
60
        Indexed by path, points to a two-tuple of the SHA-1 of the file.
61
        and its fingerprint.
846 by Martin Pool
- start adding refactored/simplified hash cache
62
63
    stat_count
64
        number of times files have been statted
65
66
    hit_count
67
        number of times files have been retrieved from the cache, avoiding a
68
        re-read
69
        
70
    miss_count
71
        number of misses (times files have been completely re-read)
72
    """
73
    def __init__(self, basedir):
74
        self.basedir = basedir
75
        self.hit_count = 0
76
        self.miss_count = 0
77
        self.stat_count = 0
78
        self.danger_count = 0
860 by Martin Pool
- refactor hashcache to use just one dictionary
79
80
        self._cache = {}
846 by Martin Pool
- start adding refactored/simplified hash cache
81
82
83
    def clear(self):
860 by Martin Pool
- refactor hashcache to use just one dictionary
84
        """Discard all cached information.
85
86
        This does not reset the counters."""
87
        self._cache_sha1 = {}
846 by Martin Pool
- start adding refactored/simplified hash cache
88
89
90
    def get_sha1(self, path):
91
        """Return the hex SHA-1 of the contents of the file at path.
92
93
        XXX: If the file does not exist or is not a plain file???
94
        """
95
96
        import os, time
97
        from bzrlib.osutils import sha_file
98
        
99
        abspath = os.path.join(self.basedir, path)
100
        fp = _fingerprint(abspath)
860 by Martin Pool
- refactor hashcache to use just one dictionary
101
        c = self._cache.get(path)
102
        if c:
103
            cache_sha1, cache_fp = c
104
        else:
105
            cache_sha1, cache_fp = None, None
846 by Martin Pool
- start adding refactored/simplified hash cache
106
107
        self.stat_count += 1
108
109
        if not fp:
110
            # not a regular file
111
            return None
112
        elif cache_fp and (cache_fp == fp):
113
            self.hit_count += 1
860 by Martin Pool
- refactor hashcache to use just one dictionary
114
            return cache_sha1
846 by Martin Pool
- start adding refactored/simplified hash cache
115
        else:
116
            self.miss_count += 1
117
            digest = sha_file(file(abspath, 'rb'))
118
119
            now = int(time.time())
120
            if fp[1] >= now or fp[2] >= now:
121
                # changed too recently; can't be cached.  we can
122
                # return the result and it could possibly be cached
123
                # next time.
124
                self.danger_count += 1 
125
                if cache_fp:
860 by Martin Pool
- refactor hashcache to use just one dictionary
126
                    del self._cache[path]
846 by Martin Pool
- start adding refactored/simplified hash cache
127
            else:
860 by Martin Pool
- refactor hashcache to use just one dictionary
128
                self._cache[path] = (digest, fp)
846 by Martin Pool
- start adding refactored/simplified hash cache
129
130
            return digest
131
859 by Martin Pool
- add HashCache.write and a simple test for it
132
133
134
    def write(self, cachefn):
135
        """Write contents of cache to file."""
136
        from atomicfile import AtomicFile
137
138
        outf = AtomicFile(cachefn, 'wb')
139
        try:
140
            outf.write(CACHE_HEADER + '\n')
141
860 by Martin Pool
- refactor hashcache to use just one dictionary
142
            for path, c  in self._cache.iteritems():
859 by Martin Pool
- add HashCache.write and a simple test for it
143
                assert '//' not in path, path
144
                outf.write(path.encode('utf-8'))
145
                outf.write('// ')
860 by Martin Pool
- refactor hashcache to use just one dictionary
146
                print >>outf, c[0],     # hex sha1
147
                for fld in c[1]:
859 by Martin Pool
- add HashCache.write and a simple test for it
148
                    print >>outf, fld,
149
                print >>outf
150
151
            outf.commit()
152
        finally:
153
            if not outf.closed:
154
                outf.abort()
155