Mercurial > hg
view tests/test-simplemerge.py @ 46607:e9901d01d135
revlog: add a mechanism to verify expected file position before appending
If someone uses `hg debuglocks`, or some non-hg process writes to the .hg
directory without respecting the locks, or if the repo's on a networked
filesystem, it's possible for the revlog code to write out corrupted data.
The form of this corruption can vary depending on what data was written and how
that happened. We are in the "networked filesystem" case (though I've had users
also do this to themselves with the "`hg debuglocks`" scenario), and most often
see this with the changelog. What ends up happening is we produce two items
(let's call them rev1 and rev2) in the .i file that have the same linkrev,
baserev, and offset into the .d file, while the data in the .d file is appended
properly. rev2's compressed_size is accurate for rev2, but when we go to
decompress the data in the .d file, we use the offset that's recorded in the
index file, which is the same as rev1, and attempt to decompress
rev2.compressed_size bytes of rev1's data. This usually does not succeed. :)
When using inline data, this also fails, though I haven't investigated why too
closely. This shows up as a "patch decode" error. I believe what's happening
there is that we're basically ignoring the offset field, getting the data
properly, but since baserev != rev, it thinks this is a delta based on rev
(instead of a full text) and can't actually apply it as such.
For now, I'm going to make this an optional component and default it to entirely
off. I may increase the default severity of this in the future, once I've
enabled it for my users and we gain more experience with it. Luckily, most of my
users have a versioned filesystem and can roll back to before the corruption has
been written, it's just a hassle to do so and not everyone knows how (so it's a
support burden). Users on other filesystems will not have that luxury, and this
can cause them to have a corrupted repository that they are unlikely to know how
to resolve, and they'll see this as a data-loss event. Refusing to create the
corruption is a much better user experience.
This mechanism is not perfect. There may be false-negatives (racy writes that
are not detected). There should not be any false-positives (non-racy writes that
are detected as such). This is not a mechanism that makes putting a repo on a
networked filesystem "safe" or "supported", just *less* likely to cause
corruption.
Differential Revision: https://phab.mercurial-scm.org/D9952
author | Kyle Lippincott <spectral@google.com> |
---|---|
date | Wed, 03 Feb 2021 16:33:10 -0800 |
parents | 98e3a693061a |
children | 374bf34c9ffd |
line wrap: on
line source
# Copyright (C) 2004, 2005 Canonical Ltd # # This program is free software; you can redistribute it and/or modify # it under the terms of the GNU General Public License as published by # the Free Software Foundation; either version 2 of the License, or # (at your option) any later version. # # This program is distributed in the hope that it will be useful, # but WITHOUT ANY WARRANTY; without even the implied warranty of # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the # GNU General Public License for more details. # # You should have received a copy of the GNU General Public License # along with this program; if not, see <http://www.gnu.org/licenses/>. from __future__ import absolute_import import unittest from mercurial import ( error, simplemerge, util, ) from mercurial.utils import stringutil TestCase = unittest.TestCase # bzr compatible interface, for the tests class Merge3(simplemerge.Merge3Text): """3-way merge of texts. Given BASE, OTHER, THIS, tries to produce a combined text incorporating the changes from both BASE->OTHER and BASE->THIS. All three will typically be sequences of lines.""" def __init__(self, base, a, b): basetext = b'\n'.join([i.strip(b'\n') for i in base] + [b'']) atext = b'\n'.join([i.strip(b'\n') for i in a] + [b'']) btext = b'\n'.join([i.strip(b'\n') for i in b] + [b'']) if ( stringutil.binary(basetext) or stringutil.binary(atext) or stringutil.binary(btext) ): raise error.Abort(b"don't know how to merge binary files") simplemerge.Merge3Text.__init__( self, basetext, atext, btext, base, a, b ) CantReprocessAndShowBase = simplemerge.CantReprocessAndShowBase def split_lines(t): return util.stringio(t).readlines() ############################################################ # test case data from the gnu diffutils manual # common base TZU = split_lines( b""" The Nameless is the origin of Heaven and Earth; The named is the mother of all things. Therefore let there always be non-being, so we may see their subtlety, And let there always be being, so we may see their outcome. The two are the same, But after they are produced, they have different names. They both may be called deep and profound. Deeper and more profound, The door of all subtleties! """ ) LAO = split_lines( b""" The Way that can be told of is not the eternal Way; The name that can be named is not the eternal name. The Nameless is the origin of Heaven and Earth; The Named is the mother of all things. Therefore let there always be non-being, so we may see their subtlety, And let there always be being, so we may see their outcome. The two are the same, But after they are produced, they have different names. """ ) TAO = split_lines( b""" The Way that can be told of is not the eternal Way; The name that can be named is not the eternal name. The Nameless is the origin of Heaven and Earth; The named is the mother of all things. Therefore let there always be non-being, so we may see their subtlety, And let there always be being, so we may see their result. The two are the same, But after they are produced, they have different names. -- The Way of Lao-Tzu, tr. Wing-tsit Chan """ ) MERGED_RESULT = split_lines( b"""\ The Way that can be told of is not the eternal Way; The name that can be named is not the eternal name. The Nameless is the origin of Heaven and Earth; The Named is the mother of all things. Therefore let there always be non-being, so we may see their subtlety, And let there always be being, so we may see their result. The two are the same, But after they are produced, they have different names.\ \n<<<<<<< LAO\ \n======= -- The Way of Lao-Tzu, tr. Wing-tsit Chan \ \n>>>>>>> TAO """ ) class TestMerge3(TestCase): def log(self, msg): pass def test_no_changes(self): """No conflicts because nothing changed""" m3 = Merge3([b'aaa', b'bbb'], [b'aaa', b'bbb'], [b'aaa', b'bbb']) self.assertEqual( list(m3.find_sync_regions()), [(0, 2, 0, 2, 0, 2), (2, 2, 2, 2, 2, 2)], ) self.assertEqual(list(m3.merge_regions()), [(b'unchanged', 0, 2)]) self.assertEqual( list(m3.merge_groups()), [(b'unchanged', [b'aaa', b'bbb'])] ) def test_front_insert(self): m3 = Merge3([b'zz'], [b'aaa', b'bbb', b'zz'], [b'zz']) # todo: should use a sentinel at end as from get_matching_blocks # to match without zz self.assertEqual( list(m3.find_sync_regions()), [(0, 1, 2, 3, 0, 1), (1, 1, 3, 3, 1, 1)], ) self.assertEqual( list(m3.merge_regions()), [(b'a', 0, 2), (b'unchanged', 0, 1)] ) self.assertEqual( list(m3.merge_groups()), [(b'a', [b'aaa', b'bbb']), (b'unchanged', [b'zz'])], ) def test_null_insert(self): m3 = Merge3([], [b'aaa', b'bbb'], []) # todo: should use a sentinel at end as from get_matching_blocks # to match without zz self.assertEqual(list(m3.find_sync_regions()), [(0, 0, 2, 2, 0, 0)]) self.assertEqual(list(m3.merge_regions()), [(b'a', 0, 2)]) self.assertEqual(list(m3.merge_lines()), [b'aaa', b'bbb']) def test_no_conflicts(self): """No conflicts because only one side changed""" m3 = Merge3( [b'aaa', b'bbb'], [b'aaa', b'111', b'bbb'], [b'aaa', b'bbb'] ) self.assertEqual( list(m3.find_sync_regions()), [(0, 1, 0, 1, 0, 1), (1, 2, 2, 3, 1, 2), (2, 2, 3, 3, 2, 2)], ) self.assertEqual( list(m3.merge_regions()), [(b'unchanged', 0, 1), (b'a', 1, 2), (b'unchanged', 1, 2)], ) def test_append_a(self): m3 = Merge3( [b'aaa\n', b'bbb\n'], [b'aaa\n', b'bbb\n', b'222\n'], [b'aaa\n', b'bbb\n'], ) self.assertEqual(b''.join(m3.merge_lines()), b'aaa\nbbb\n222\n') def test_append_b(self): m3 = Merge3( [b'aaa\n', b'bbb\n'], [b'aaa\n', b'bbb\n'], [b'aaa\n', b'bbb\n', b'222\n'], ) self.assertEqual(b''.join(m3.merge_lines()), b'aaa\nbbb\n222\n') def test_append_agreement(self): m3 = Merge3( [b'aaa\n', b'bbb\n'], [b'aaa\n', b'bbb\n', b'222\n'], [b'aaa\n', b'bbb\n', b'222\n'], ) self.assertEqual(b''.join(m3.merge_lines()), b'aaa\nbbb\n222\n') def test_append_clash(self): m3 = Merge3( [b'aaa\n', b'bbb\n'], [b'aaa\n', b'bbb\n', b'222\n'], [b'aaa\n', b'bbb\n', b'333\n'], ) ml = m3.merge_lines( name_a=b'a', name_b=b'b', start_marker=b'<<', mid_marker=b'--', end_marker=b'>>', ) self.assertEqual( b''.join(ml), b'aaa\n' b'bbb\n' b'<< a\n' b'222\n' b'--\n' b'333\n' b'>> b\n', ) def test_insert_agreement(self): m3 = Merge3( [b'aaa\n', b'bbb\n'], [b'aaa\n', b'222\n', b'bbb\n'], [b'aaa\n', b'222\n', b'bbb\n'], ) ml = m3.merge_lines( name_a=b'a', name_b=b'b', start_marker=b'<<', mid_marker=b'--', end_marker=b'>>', ) self.assertEqual(b''.join(ml), b'aaa\n222\nbbb\n') def test_insert_clash(self): """Both try to insert lines in the same place.""" m3 = Merge3( [b'aaa\n', b'bbb\n'], [b'aaa\n', b'111\n', b'bbb\n'], [b'aaa\n', b'222\n', b'bbb\n'], ) self.assertEqual( list(m3.find_sync_regions()), [(0, 1, 0, 1, 0, 1), (1, 2, 2, 3, 2, 3), (2, 2, 3, 3, 3, 3)], ) self.assertEqual( list(m3.merge_regions()), [ (b'unchanged', 0, 1), (b'conflict', 1, 1, 1, 2, 1, 2), (b'unchanged', 1, 2), ], ) self.assertEqual( list(m3.merge_groups()), [ (b'unchanged', [b'aaa\n']), (b'conflict', [], [b'111\n'], [b'222\n']), (b'unchanged', [b'bbb\n']), ], ) ml = m3.merge_lines( name_a=b'a', name_b=b'b', start_marker=b'<<', mid_marker=b'--', end_marker=b'>>', ) self.assertEqual( b''.join(ml), b'''aaa << a 111 -- 222 >> b bbb ''', ) def test_replace_clash(self): """Both try to insert lines in the same place.""" m3 = Merge3( [b'aaa', b'000', b'bbb'], [b'aaa', b'111', b'bbb'], [b'aaa', b'222', b'bbb'], ) self.assertEqual( list(m3.find_sync_regions()), [(0, 1, 0, 1, 0, 1), (2, 3, 2, 3, 2, 3), (3, 3, 3, 3, 3, 3)], ) def test_replace_multi(self): """Replacement with regions of different size.""" m3 = Merge3( [b'aaa', b'000', b'000', b'bbb'], [b'aaa', b'111', b'111', b'111', b'bbb'], [b'aaa', b'222', b'222', b'222', b'222', b'bbb'], ) self.assertEqual( list(m3.find_sync_regions()), [(0, 1, 0, 1, 0, 1), (3, 4, 4, 5, 5, 6), (4, 4, 5, 5, 6, 6)], ) def test_merge_poem(self): """Test case from diff3 manual""" m3 = Merge3(TZU, LAO, TAO) ml = list(m3.merge_lines(b'LAO', b'TAO')) self.log(b'merge result:') self.log(b''.join(ml)) self.assertEqual(ml, MERGED_RESULT) def test_binary(self): with self.assertRaises(error.Abort): Merge3([b'\x00'], [b'a'], [b'b']) def test_dos_text(self): base_text = b'a\r\n' this_text = b'b\r\n' other_text = b'c\r\n' m3 = Merge3( base_text.splitlines(True), other_text.splitlines(True), this_text.splitlines(True), ) m_lines = m3.merge_lines(b'OTHER', b'THIS') self.assertEqual( b'<<<<<<< OTHER\r\nc\r\n=======\r\nb\r\n' b'>>>>>>> THIS\r\n'.splitlines(True), list(m_lines), ) def test_mac_text(self): base_text = b'a\r' this_text = b'b\r' other_text = b'c\r' m3 = Merge3( base_text.splitlines(True), other_text.splitlines(True), this_text.splitlines(True), ) m_lines = m3.merge_lines(b'OTHER', b'THIS') self.assertEqual( b'<<<<<<< OTHER\rc\r=======\rb\r' b'>>>>>>> THIS\r'.splitlines(True), list(m_lines), ) if __name__ == '__main__': import silenttestrunner silenttestrunner.main(__name__)