1
# (C) 2005 Matt Mackall
2
# (C) 2005 Canonical Ltd
4
# based on code by Matt Mackall, hacked by Martin Pool
6
# mm's code works line-by-line; this just works on byte strings.
7
# Possibly slower; possibly gives better results for code not
8
# regularly separated by newlines and anyhow a bit simpler.
11
# This program is free software; you can redistribute it and/or modify
12
# it under the terms of the GNU General Public License as published by
13
# the Free Software Foundation; either version 2 of the License, or
14
# (at your option) any later version.
16
# This program is distributed in the hope that it will be useful,
17
# but WITHOUT ANY WARRANTY; without even the implied warranty of
18
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
19
# GNU General Public License for more details.
21
# You should have received a copy of the GNU General Public License
22
# along with this program; if not, write to the Free Software
23
# Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
26
# TODO: maybe work on files not strings?
28
# FIXME: doesn't work properly on files without trailing newlines
31
import difflib, sys, struct
32
from cStringIO import StringIO
35
"""Split into two lists: content and line positions.
37
This returns (al, ap).
39
al[i] is the string content of line i of the file, including its
42
ap[i] is the byte position in the file where that line starts.
44
ap[-1] is the byte position of the end of the file (i.e. the
47
This transformation allows us to do a line-based diff and then map
48
back to byte positions.
59
n = a.find("\n", n) + 1
72
# TODO: Use different splits, perhaps rsync-like, for binary files?
74
(al, ap) = linesplit(a)
75
(bl, bp) = linesplit(b)
77
d = difflib.SequenceMatcher(None, al, bl)
79
## sys.stderr.write(' ~ real_quick_ratio: %.4f\n' % d.real_quick_ratio())
81
for o, m, n, s, t in d.get_opcodes():
82
if o == 'equal': continue
83
# a[m:n] should be replaced by b[s:t]
85
yield ap[m], ap[n], ''
87
yield ap[m], ap[n], ''.join(bl[s:t])
93
b.write(struct.pack(">III", f[0], f[1], len(f[2])))
99
return tobinary(diff(a, b))
123
m, n, l = struct.unpack(">III", p)
130
raise Exception("truncated patch data")
136
return patch(t, frombinary(b))
141
class TestDiffPatch(unittest.TestCase):
142
def doDiffPatch(self, old, new):
143
diff = bdiff(old, new)
144
result = bpatch(old, diff)
145
self.assertEquals(new, result)
148
def testSimpleDiff(self):
149
"""Simply add a line at the end"""
150
self.doDiffPatch('a\nb\n', 'a\nb\nc\n')
154
def testTrailingLine(self):
155
"""Test diff that adds an unterminated line.
157
(Old versions didn't do this properly.)"""
158
self.doDiffPatch('a\nb\nc\n',
162
if __name__ == '__main__':
added
removed
bzrlib/mdiff.py
