blob: e2a96cd12f4248daa8d5a12700b4ef0f9e5119a2 (
plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
|
#!/usr/bin/env python
#
# Patchwork - automated patch tracking system
# Copyright (C) 2008 Jeremy Kerr <jk@ozlabs.org>
#
# SPDX-License-Identifier: GPL-2.0-or-later
"""Hash generation for diffs."""
import hashlib
import re
import sys
HUNK_RE = re.compile(r'^\@\@ -\d+(?:,(\d+))? \+\d+(?:,(\d+))? \@\@')
FILENAME_RE = re.compile(r'^(---|\+\+\+) (\S+)')
def hash_diff(diff):
"""Generate a hash from a diff."""
# normalise spaces
diff = diff.replace('\r', '')
diff = diff.strip() + '\n'
prefixes = ['-', '+', ' ']
hashed = hashlib.sha1()
for line in diff.split('\n'):
if len(line) <= 0:
continue
hunk_match = HUNK_RE.match(line)
filename_match = FILENAME_RE.match(line)
if filename_match:
# normalise -p1 top-directories
if filename_match.group(1) == '---':
filename = 'a/'
else:
filename = 'b/'
filename += '/'.join(filename_match.group(2).split('/')[1:])
line = filename_match.group(1) + ' ' + filename
elif hunk_match:
# remove line numbers, but leave line counts
def fn(x):
if not x:
return 1
return int(x)
line_nos = list(map(fn, hunk_match.groups()))
line = '@@ -%d +%d @@' % tuple(line_nos)
elif line[0] in prefixes:
# if we have a +, - or context line, leave as-is
pass
else:
# other lines are ignored
continue
hashed.update((line + '\n').encode('utf-8'))
return hashed.hexdigest()
def main(args):
"""Hash a diff provided by stdin.
This is required by scripts found in /tools
"""
print(hash_diff('\n'.join(sys.stdin.readlines())))
if __name__ == '__main__':
sys.exit(main(sys.argv))
|