Mercurial > hg
view tests/test-rust-revlog.py @ 48671:f1ed5c304f45
encoding: fix trim() to be O(n) instead of O(n^2)
`encoding.trim()` iterated over the possible lengths smaller than the
input and created a slice for each. It then calculated the column
width of the result, which is of course O(n), so the overall algorithm
was O(n). This patch rewrites it to iterate over the unicode
characters, keeping track of the length so far. Also, the old
algorithm started from the end of the string, which made it much worse
when the input is large and the limit is small (such as the typical 72
we pass to it).
You can time it by running something like this:
```
time python3 -c 'from mercurial.utils import stringutil; print(stringutil.ellipsis(b"0123456789" * 1000, 5))'
```
That drops from 4.05 s to 83 ms with this patch (and most of that is
of course startup time).
Differential Revision: https://phab.mercurial-scm.org/D12089
author | Martin von Zweigbergk <martinvonz@google.com> |
---|---|
date | Wed, 26 Jan 2022 10:11:01 -0800 |
parents | 89a2afe31e82 |
children | 6000f5b25c9b |
line wrap: on
line source
from __future__ import absolute_import import unittest try: from mercurial import rustext rustext.__name__ # trigger immediate actual import except ImportError: rustext = None else: from mercurial.rustext import revlog # this would fail already without appropriate ancestor.__package__ from mercurial.rustext.ancestor import LazyAncestors from mercurial.testing import revlog as revlogtesting @unittest.skipIf( rustext is None, "rustext module revlog relies on is not available", ) class RustRevlogIndexTest(revlogtesting.RevlogBasedTestBase): def test_heads(self): idx = self.parseindex() rustidx = revlog.MixedIndex(idx) self.assertEqual(rustidx.headrevs(), idx.headrevs()) def test_get_cindex(self): # drop me once we no longer need the method for shortest node idx = self.parseindex() rustidx = revlog.MixedIndex(idx) cidx = rustidx.get_cindex() self.assertTrue(idx is cidx) def test_len(self): idx = self.parseindex() rustidx = revlog.MixedIndex(idx) self.assertEqual(len(rustidx), len(idx)) def test_ancestors(self): idx = self.parseindex() rustidx = revlog.MixedIndex(idx) lazy = LazyAncestors(rustidx, [3], 0, True) # we have two more references to the index: # - in its inner iterator for __contains__ and __bool__ # - in the LazyAncestors instance itself (to spawn new iterators) self.assertTrue(2 in lazy) self.assertTrue(bool(lazy)) self.assertEqual(list(lazy), [3, 2, 1, 0]) # a second time to validate that we spawn new iterators self.assertEqual(list(lazy), [3, 2, 1, 0]) # let's check bool for an empty one self.assertFalse(LazyAncestors(idx, [0], 0, False)) if __name__ == '__main__': import silenttestrunner silenttestrunner.main(__name__)