Mercurial > hg
view tests/test-simplemerge.py @ 30435:b86a448a2965
zstd: vendor python-zstandard 0.5.0
As the commit message for the previous changeset says, we wish
for zstd to be a 1st class citizen in Mercurial. To make that
happen, we need to enable Python to talk to the zstd C API. And
that requires bindings.
This commit vendors a copy of existing Python bindings. Why do we
need to vendor? As the commit message of the previous commit says,
relying on systems in the wild to have the bindings or zstd present
is a losing proposition. By distributing the zstd and bindings with
Mercurial, we significantly increase our chances that zstd will
work. Since zstd will deliver a better end-user experience by
achieving better performance, this benefits our users. Another
reason is that the Python bindings still aren't stable and the
API is somewhat fluid. While Mercurial could be coded to target
multiple versions of the Python bindings, it is safer to bundle
an explicit, known working version.
The added Python bindings are mostly a fully-featured interface
to the zstd C API. They allow one-shot operations, streaming,
reading and writing from objects implements the file object
protocol, dictionary compression, control over low-level compression
parameters, and more. The Python bindings work on Python 2.6,
2.7, and 3.3+ and have been tested on Linux and Windows. There are
CFFI bindings, but they are lacking compared to the C extension.
Upstream work will be needed before we can support zstd with PyPy.
But it will be possible.
The files added in this commit come from Git commit
e637c1b214d5f869cf8116c550dcae23ec13b677 from
https://github.com/indygreg/python-zstandard and are added without
modifications. Some files from the upstream repository have been
omitted, namely files related to continuous integration.
In the spirit of full disclosure, I'm the maintainer of the
"python-zstandard" project and have authored 100% of the code
added in this commit. Unfortunately, the Python bindings have
not been formally code reviewed by anyone. While I've tested
much of the code thoroughly (I even have tests that fuzz APIs),
there's a good chance there are bugs, memory leaks, not well
thought out APIs, etc. If someone wants to review the code and
send feedback to the GitHub project, it would be greatly
appreciated.
Despite my involvement with both projects, my opinions of code
style differ from Mercurial's. The code in this commit introduces
numerous code style violations in Mercurial's linters. So, the code
is excluded from most lints. However, some violations I agree with.
These have been added to the known violations ignore list for now.
| author | Gregory Szorc <gregory.szorc@gmail.com> |
|---|---|
| date | Thu, 10 Nov 2016 22:15:58 -0800 |
| parents | 2d433fa7ff44 |
| children | 68c43a416585 |
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, ) 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 = '\n'.join([i.strip('\n') for i in base] + ['']) atext = '\n'.join([i.strip('\n') for i in a] + ['']) btext = '\n'.join([i.strip('\n') for i in b] + ['']) if util.binary(basetext) or util.binary(atext) or util.binary(btext): raise error.Abort("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(""" 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(""" 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(""" 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("""\ 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. <<<<<<< LAO ======= -- The Way of Lao-Tzu, tr. Wing-tsit Chan >>>>>>> TAO """) class TestMerge3(TestCase): def log(self, msg): pass def test_no_changes(self): """No conflicts because nothing changed""" m3 = Merge3(['aaa', 'bbb'], ['aaa', 'bbb'], ['aaa', 'bbb']) self.assertEquals(m3.find_unconflicted(), [(0, 2)]) self.assertEquals(list(m3.find_sync_regions()), [(0, 2, 0, 2, 0, 2), (2, 2, 2, 2, 2, 2)]) self.assertEquals(list(m3.merge_regions()), [('unchanged', 0, 2)]) self.assertEquals(list(m3.merge_groups()), [('unchanged', ['aaa', 'bbb'])]) def test_front_insert(self): m3 = Merge3(['zz'], ['aaa', 'bbb', 'zz'], ['zz']) # todo: should use a sentinel at end as from get_matching_blocks # to match without zz self.assertEquals(list(m3.find_sync_regions()), [(0, 1, 2, 3, 0, 1), (1, 1, 3, 3, 1, 1)]) self.assertEquals(list(m3.merge_regions()), [('a', 0, 2), ('unchanged', 0, 1)]) self.assertEquals(list(m3.merge_groups()), [('a', ['aaa', 'bbb']), ('unchanged', ['zz'])]) def test_null_insert(self): m3 = Merge3([], ['aaa', 'bbb'], []) # todo: should use a sentinel at end as from get_matching_blocks # to match without zz self.assertEquals(list(m3.find_sync_regions()), [(0, 0, 2, 2, 0, 0)]) self.assertEquals(list(m3.merge_regions()), [('a', 0, 2)]) self.assertEquals(list(m3.merge_lines()), ['aaa', 'bbb']) def test_no_conflicts(self): """No conflicts because only one side changed""" m3 = Merge3(['aaa', 'bbb'], ['aaa', '111', 'bbb'], ['aaa', 'bbb']) self.assertEquals(m3.find_unconflicted(), [(0, 1), (1, 2)]) self.assertEquals(list(m3.find_sync_regions()), [(0, 1, 0, 1, 0, 1), (1, 2, 2, 3, 1, 2), (2, 2, 3, 3, 2, 2)]) self.assertEquals(list(m3.merge_regions()), [('unchanged', 0, 1), ('a', 1, 2), ('unchanged', 1, 2)]) def test_append_a(self): m3 = Merge3(['aaa\n', 'bbb\n'], ['aaa\n', 'bbb\n', '222\n'], ['aaa\n', 'bbb\n']) self.assertEquals(''.join(m3.merge_lines()), 'aaa\nbbb\n222\n') def test_append_b(self): m3 = Merge3(['aaa\n', 'bbb\n'], ['aaa\n', 'bbb\n'], ['aaa\n', 'bbb\n', '222\n']) self.assertEquals(''.join(m3.merge_lines()), 'aaa\nbbb\n222\n') def test_append_agreement(self): m3 = Merge3(['aaa\n', 'bbb\n'], ['aaa\n', 'bbb\n', '222\n'], ['aaa\n', 'bbb\n', '222\n']) self.assertEquals(''.join(m3.merge_lines()), 'aaa\nbbb\n222\n') def test_append_clash(self): m3 = Merge3(['aaa\n', 'bbb\n'], ['aaa\n', 'bbb\n', '222\n'], ['aaa\n', 'bbb\n', '333\n']) ml = m3.merge_lines(name_a='a', name_b='b', start_marker='<<', mid_marker='--', end_marker='>>') self.assertEquals(''.join(ml), 'aaa\n' 'bbb\n' '<< a\n' '222\n' '--\n' '333\n' '>> b\n' ) def test_insert_agreement(self): m3 = Merge3(['aaa\n', 'bbb\n'], ['aaa\n', '222\n', 'bbb\n'], ['aaa\n', '222\n', 'bbb\n']) ml = m3.merge_lines(name_a='a', name_b='b', start_marker='<<', mid_marker='--', end_marker='>>') self.assertEquals(''.join(ml), 'aaa\n222\nbbb\n') def test_insert_clash(self): """Both try to insert lines in the same place.""" m3 = Merge3(['aaa\n', 'bbb\n'], ['aaa\n', '111\n', 'bbb\n'], ['aaa\n', '222\n', 'bbb\n']) self.assertEquals(m3.find_unconflicted(), [(0, 1), (1, 2)]) self.assertEquals(list(m3.find_sync_regions()), [(0, 1, 0, 1, 0, 1), (1, 2, 2, 3, 2, 3), (2, 2, 3, 3, 3, 3)]) self.assertEquals(list(m3.merge_regions()), [('unchanged', 0, 1), ('conflict', 1, 1, 1, 2, 1, 2), ('unchanged', 1, 2)]) self.assertEquals(list(m3.merge_groups()), [('unchanged', ['aaa\n']), ('conflict', [], ['111\n'], ['222\n']), ('unchanged', ['bbb\n']), ]) ml = m3.merge_lines(name_a='a', name_b='b', start_marker='<<', mid_marker='--', end_marker='>>') self.assertEquals(''.join(ml), '''aaa << a 111 -- 222 >> b bbb ''') def test_replace_clash(self): """Both try to insert lines in the same place.""" m3 = Merge3(['aaa', '000', 'bbb'], ['aaa', '111', 'bbb'], ['aaa', '222', 'bbb']) self.assertEquals(m3.find_unconflicted(), [(0, 1), (2, 3)]) self.assertEquals(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(['aaa', '000', '000', 'bbb'], ['aaa', '111', '111', '111', 'bbb'], ['aaa', '222', '222', '222', '222', 'bbb']) self.assertEquals(m3.find_unconflicted(), [(0, 1), (3, 4)]) self.assertEquals(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('LAO', 'TAO')) self.log('merge result:') self.log(''.join(ml)) self.assertEquals(ml, MERGED_RESULT) def test_binary(self): self.assertRaises(error.Abort, Merge3, ['\x00'], ['a'], ['b']) def test_dos_text(self): base_text = 'a\r\n' this_text = 'b\r\n' other_text = 'c\r\n' m3 = Merge3(base_text.splitlines(True), other_text.splitlines(True), this_text.splitlines(True)) m_lines = m3.merge_lines('OTHER', 'THIS') self.assertEqual('<<<<<<< OTHER\r\nc\r\n=======\r\nb\r\n' '>>>>>>> THIS\r\n'.splitlines(True), list(m_lines)) def test_mac_text(self): base_text = 'a\r' this_text = 'b\r' other_text = 'c\r' m3 = Merge3(base_text.splitlines(True), other_text.splitlines(True), this_text.splitlines(True)) m_lines = m3.merge_lines('OTHER', 'THIS') self.assertEqual('<<<<<<< OTHER\rc\r=======\rb\r' '>>>>>>> THIS\r'.splitlines(True), list(m_lines)) if __name__ == '__main__': # hide the timer import time orig = time.time try: time.time = lambda: 0 unittest.main() finally: time.time = orig