2
# Copyright (C) 2005, 2006, 2007 Canonical Ltd
4
# This program is free software; you can redistribute it and/or modify
5
# it under the terms of the GNU General Public License as published by
6
# the Free Software Foundation; either version 2 of the License, or
7
# (at your option) any later version.
9
# This program is distributed in the hope that it will be useful,
10
# but WITHOUT ANY WARRANTY; without even the implied warranty of
11
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
12
# GNU General Public License for more details.
14
# You should have received a copy of the GNU General Public License
15
# along with this program; if not, write to the Free Software
16
# Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
19
from bzrlib.lazy_import import lazy_import
20
lazy_import(globals(), """
28
__all__ = ['PatienceSequenceMatcher', 'unified_diff', 'unified_diff_files']
31
# This is a version of unified_diff which only adds a factory parameter
32
# so that you can override the default SequenceMatcher
33
# this has been submitted as a patch to python
34
def unified_diff(a, b, fromfile='', tofile='', fromfiledate='',
35
tofiledate='', n=3, lineterm='\n',
36
sequencematcher=None):
38
Compare two sequences of lines; generate the delta as a unified diff.
40
Unified diffs are a compact way of showing line changes and a few
41
lines of context. The number of context lines is set by 'n' which
44
By default, the diff control lines (those with ---, +++, or @@) are
45
created with a trailing newline. This is helpful so that inputs
46
created from file.readlines() result in diffs that are suitable for
47
file.writelines() since both the inputs and outputs have trailing
50
For inputs that do not have trailing newlines, set the lineterm
51
argument to "" so that the output will be uniformly newline free.
53
The unidiff format normally has a header for filenames and modification
54
times. Any or all of these may be specified using strings for
55
'fromfile', 'tofile', 'fromfiledate', and 'tofiledate'. The modification
56
times are normally expressed in the format returned by time.ctime().
60
>>> for line in unified_diff('one two three four'.split(),
61
... 'zero one tree four'.split(), 'Original', 'Current',
62
... 'Sat Jan 26 23:30:50 1991', 'Fri Jun 06 10:20:52 2003',
65
--- Original Sat Jan 26 23:30:50 1991
66
+++ Current Fri Jun 06 10:20:52 2003
75
if sequencematcher is None:
76
sequencematcher = difflib.SequenceMatcher
79
fromfiledate = '\t' + str(fromfiledate)
81
tofiledate = '\t' + str(tofiledate)
84
for group in sequencematcher(None,a,b).get_grouped_opcodes(n):
86
yield '--- %s%s%s' % (fromfile, fromfiledate, lineterm)
87
yield '+++ %s%s%s' % (tofile, tofiledate, lineterm)
89
i1, i2, j1, j2 = group[0][1], group[-1][2], group[0][3], group[-1][4]
90
yield "@@ -%d,%d +%d,%d @@%s" % (i1+1, i2-i1, j1+1, j2-j1, lineterm)
91
for tag, i1, i2, j1, j2 in group:
96
if tag == 'replace' or tag == 'delete':
99
if tag == 'replace' or tag == 'insert':
100
for line in b[j1:j2]:
104
def unified_diff_files(a, b, sequencematcher=None):
105
"""Generate the diff for two files.
107
# Should this actually be an error?
114
file_a = open(a, 'rb')
115
time_a = os.stat(a).st_mtime
121
file_b = open(b, 'rb')
122
time_b = os.stat(b).st_mtime
124
# TODO: Include fromfiledate and tofiledate
125
return unified_diff(file_a.readlines(), file_b.readlines(),
126
fromfile=a, tofile=b,
127
sequencematcher=sequencematcher)
131
from bzrlib._patiencediff_c import (
132
unique_lcs_c as unique_lcs,
133
recurse_matches_c as recurse_matches,
134
PatienceSequenceMatcher_c as PatienceSequenceMatcher
137
from bzrlib._patiencediff_py import (
138
unique_lcs_py as unique_lcs,
139
recurse_matches_py as recurse_matches,
140
PatienceSequenceMatcher_py as PatienceSequenceMatcher
146
p = optparse.OptionParser(usage='%prog [options] file_a file_b'
147
'\nFiles can be "-" to read from stdin')
148
p.add_option('--patience', dest='matcher', action='store_const', const='patience',
149
default='patience', help='Use the patience difference algorithm')
150
p.add_option('--difflib', dest='matcher', action='store_const', const='difflib',
151
default='patience', help='Use python\'s difflib algorithm')
153
algorithms = {'patience':PatienceSequenceMatcher, 'difflib':difflib.SequenceMatcher}
155
(opts, args) = p.parse_args(args)
156
matcher = algorithms[opts.matcher]
159
print 'You must supply 2 filenames to diff'
162
for line in unified_diff_files(args[0], args[1], sequencematcher=matcher):
163
sys.stdout.write(line)
166
if __name__ == '__main__':
167
sys.exit(main(sys.argv[1:]))