annotate Lib/cmp.py @ 5817:48b94de85bf3 legacy-trunk

Extensive changes by AMK.
author Guido van Rossum <guido@python.org>
date Thu, 17 Jul 1997 16:29:42 +0000
parents 3ba17305f047
children e1806b280f53
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
5
5570dbb1ce55 Initial revision
Guido van Rossum <guido@python.org>
parents:
diff changeset
1 # Module 'cmp'
5570dbb1ce55 Initial revision
Guido van Rossum <guido@python.org>
parents:
diff changeset
2
5570dbb1ce55 Initial revision
Guido van Rossum <guido@python.org>
parents:
diff changeset
3 # Efficiently compare files, boolean outcome only (equal / not equal).
5570dbb1ce55 Initial revision
Guido van Rossum <guido@python.org>
parents:
diff changeset
4
5570dbb1ce55 Initial revision
Guido van Rossum <guido@python.org>
parents:
diff changeset
5 # Tricks (used in this order):
5570dbb1ce55 Initial revision
Guido van Rossum <guido@python.org>
parents:
diff changeset
6 # - Files with identical type, size & mtime are assumed to be clones
5570dbb1ce55 Initial revision
Guido van Rossum <guido@python.org>
parents:
diff changeset
7 # - Files with different type or size cannot be identical
5570dbb1ce55 Initial revision
Guido van Rossum <guido@python.org>
parents:
diff changeset
8 # - We keep a cache of outcomes of earlier comparisons
5570dbb1ce55 Initial revision
Guido van Rossum <guido@python.org>
parents:
diff changeset
9 # - We don't fork a process to run 'cmp' but read the files ourselves
5570dbb1ce55 Initial revision
Guido van Rossum <guido@python.org>
parents:
diff changeset
10
776
7259e96a04a9 posix -> os
Guido van Rossum <guido@python.org>
parents: 559
diff changeset
11 import os
5
5570dbb1ce55 Initial revision
Guido van Rossum <guido@python.org>
parents:
diff changeset
12
5570dbb1ce55 Initial revision
Guido van Rossum <guido@python.org>
parents:
diff changeset
13 cache = {}
5570dbb1ce55 Initial revision
Guido van Rossum <guido@python.org>
parents:
diff changeset
14
5570dbb1ce55 Initial revision
Guido van Rossum <guido@python.org>
parents:
diff changeset
15 def cmp(f1, f2): # Compare two files, use the cache if possible.
5570dbb1ce55 Initial revision
Guido van Rossum <guido@python.org>
parents:
diff changeset
16 # Return 1 for identical files, 0 for different.
5570dbb1ce55 Initial revision
Guido van Rossum <guido@python.org>
parents:
diff changeset
17 # Raise exceptions if either file could not be statted, read, etc.
776
7259e96a04a9 posix -> os
Guido van Rossum <guido@python.org>
parents: 559
diff changeset
18 s1, s2 = sig(os.stat(f1)), sig(os.stat(f2))
5
5570dbb1ce55 Initial revision
Guido van Rossum <guido@python.org>
parents:
diff changeset
19 if s1[0] <> 8 or s2[0] <> 8:
5570dbb1ce55 Initial revision
Guido van Rossum <guido@python.org>
parents:
diff changeset
20 # Either is a not a plain file -- always report as different
5570dbb1ce55 Initial revision
Guido van Rossum <guido@python.org>
parents:
diff changeset
21 return 0
559
683edb0c4463 New == syntax
Guido van Rossum <guido@python.org>
parents: 521
diff changeset
22 if s1 == s2:
5
5570dbb1ce55 Initial revision
Guido van Rossum <guido@python.org>
parents:
diff changeset
23 # type, size & mtime match -- report same
5570dbb1ce55 Initial revision
Guido van Rossum <guido@python.org>
parents:
diff changeset
24 return 1
5570dbb1ce55 Initial revision
Guido van Rossum <guido@python.org>
parents:
diff changeset
25 if s1[:2] <> s2[:2]: # Types or sizes differ, don't bother
5570dbb1ce55 Initial revision
Guido van Rossum <guido@python.org>
parents:
diff changeset
26 # types or sizes differ -- report different
5570dbb1ce55 Initial revision
Guido van Rossum <guido@python.org>
parents:
diff changeset
27 return 0
5570dbb1ce55 Initial revision
Guido van Rossum <guido@python.org>
parents:
diff changeset
28 # same type and size -- look in the cache
5570dbb1ce55 Initial revision
Guido van Rossum <guido@python.org>
parents:
diff changeset
29 key = f1 + ' ' + f2
5570dbb1ce55 Initial revision
Guido van Rossum <guido@python.org>
parents:
diff changeset
30 try:
5570dbb1ce55 Initial revision
Guido van Rossum <guido@python.org>
parents:
diff changeset
31 cs1, cs2, outcome = cache[key]
5570dbb1ce55 Initial revision
Guido van Rossum <guido@python.org>
parents:
diff changeset
32 # cache hit
559
683edb0c4463 New == syntax
Guido van Rossum <guido@python.org>
parents: 521
diff changeset
33 if s1 == cs1 and s2 == cs2:
5
5570dbb1ce55 Initial revision
Guido van Rossum <guido@python.org>
parents:
diff changeset
34 # cached signatures match
5570dbb1ce55 Initial revision
Guido van Rossum <guido@python.org>
parents:
diff changeset
35 return outcome
5570dbb1ce55 Initial revision
Guido van Rossum <guido@python.org>
parents:
diff changeset
36 # stale cached signature(s)
521
2dcdb0023c32 Use KeyError.
Guido van Rossum <guido@python.org>
parents: 5
diff changeset
37 except KeyError:
5
5570dbb1ce55 Initial revision
Guido van Rossum <guido@python.org>
parents:
diff changeset
38 # cache miss
5570dbb1ce55 Initial revision
Guido van Rossum <guido@python.org>
parents:
diff changeset
39 pass
5570dbb1ce55 Initial revision
Guido van Rossum <guido@python.org>
parents:
diff changeset
40 # really compare
5570dbb1ce55 Initial revision
Guido van Rossum <guido@python.org>
parents:
diff changeset
41 outcome = do_cmp(f1, f2)
5570dbb1ce55 Initial revision
Guido van Rossum <guido@python.org>
parents:
diff changeset
42 cache[key] = s1, s2, outcome
5570dbb1ce55 Initial revision
Guido van Rossum <guido@python.org>
parents:
diff changeset
43 return outcome
5570dbb1ce55 Initial revision
Guido van Rossum <guido@python.org>
parents:
diff changeset
44
5570dbb1ce55 Initial revision
Guido van Rossum <guido@python.org>
parents:
diff changeset
45 def sig(st): # Return signature (i.e., type, size, mtime) from raw stat data
5570dbb1ce55 Initial revision
Guido van Rossum <guido@python.org>
parents:
diff changeset
46 # 0-5: st_mode, st_ino, st_dev, st_nlink, st_uid, st_gid
5570dbb1ce55 Initial revision
Guido van Rossum <guido@python.org>
parents:
diff changeset
47 # 6-9: st_size, st_atime, st_mtime, st_ctime
5570dbb1ce55 Initial revision
Guido van Rossum <guido@python.org>
parents:
diff changeset
48 type = st[0] / 4096
5570dbb1ce55 Initial revision
Guido van Rossum <guido@python.org>
parents:
diff changeset
49 size = st[6]
5570dbb1ce55 Initial revision
Guido van Rossum <guido@python.org>
parents:
diff changeset
50 mtime = st[8]
5570dbb1ce55 Initial revision
Guido van Rossum <guido@python.org>
parents:
diff changeset
51 return type, size, mtime
5570dbb1ce55 Initial revision
Guido van Rossum <guido@python.org>
parents:
diff changeset
52
5570dbb1ce55 Initial revision
Guido van Rossum <guido@python.org>
parents:
diff changeset
53 def do_cmp(f1, f2): # Compare two files, really
1965
3ba17305f047 fix buffer size
Guido van Rossum <guido@python.org>
parents: 776
diff changeset
54 bufsize = 8*1024 # Could be tuned
5
5570dbb1ce55 Initial revision
Guido van Rossum <guido@python.org>
parents:
diff changeset
55 fp1 = open(f1, 'r')
5570dbb1ce55 Initial revision
Guido van Rossum <guido@python.org>
parents:
diff changeset
56 fp2 = open(f2, 'r')
5570dbb1ce55 Initial revision
Guido van Rossum <guido@python.org>
parents:
diff changeset
57 while 1:
5570dbb1ce55 Initial revision
Guido van Rossum <guido@python.org>
parents:
diff changeset
58 b1 = fp1.read(bufsize)
5570dbb1ce55 Initial revision
Guido van Rossum <guido@python.org>
parents:
diff changeset
59 b2 = fp2.read(bufsize)
5570dbb1ce55 Initial revision
Guido van Rossum <guido@python.org>
parents:
diff changeset
60 if b1 <> b2: return 0
5570dbb1ce55 Initial revision
Guido van Rossum <guido@python.org>
parents:
diff changeset
61 if not b1: return 1