revset: stop serializing node when using "%ln"
Turning hundred of thousand of node from node to hex and back can be slow… what
about we stop doing it?
In many case were we are using node id we should be using revision id. However
this is not a good reason to have a stupidly slow implementation of "%ln".
This caught my attention again because the phase discovery during push make an
extensive use of "%ln" or huge set. In absolute, that phase discovery probably
should use "%ld" and need to improves its algorithmic complexity, but improving
"%ln" seems simple and long overdue. This greatly speeds up `hg push` on
repository with many drafts.
Here are some relevant poulpe benchmarks:
### data-env-vars.name = mozilla-try-2023-03-22-zstd-sparse-revlog
# benchmark.name = hg.command.push
# bin-env-vars.hg.flavor = default
# bin-env-vars.hg.py-re2-module = default
# benchmark.variants.explicit-rev = all-out-heads
# benchmark.variants.issue6528 = disabled
# benchmark.variants.protocol = ssh
# benchmark.variants.reuse-external-delta-parent = default
## benchmark.variants.revs = any-1-extra-rev
before: 44.235070
after: 20.416329 (-53.85%, -23.82)
## benchmark.variants.revs = any-100-extra-rev
before: 49.234697
after: 26.519829 (-46.14%, -22.71)
### benchmark.name = hg.command.bundle
# bin-env-vars.hg.flavor = default
# bin-env-vars.hg.py-re2-module = default
# benchmark.variants.revs = all
# benchmark.variants.type = none-streamv2
## data-env-vars.name = heptapod-public-2024-03-25-zstd-sparse-revlog
before: 10.138396
after: 7.750458 (-23.55%, -2.39)
## data-env-vars.name = mercurial-public-2024-03-22-zstd-sparse-revlog
before: 1.263859
after: 0.700229 (-44.60%, -0.56)
## data-env-vars.name = mozilla-try-2023-03-22-zstd-sparse-revlog
before: 399.484481
after: 346.5089 (-13.26%, -52.98)
## data-env-vars.name = pypy-2024-03-22-zstd-sparse-revlog
before: 4.540080
after: 3.401700 (-25.07%, -1.14)
## data-env-vars.name = tryton-public-2024-03-22-zstd-sparse-revlog
before: 2.975765
after: 1.870798 (-37.13%, -1.10)
import unittest
import silenttestrunner
from mercurial import (
error,
scmutil,
)
class mockfile:
def __init__(self, name, fs):
self.name = name
self.fs = fs
def __enter__(self):
return self
def __exit__(self, *args, **kwargs):
pass
def write(self, text):
self.fs.contents[self.name] = text
def read(self):
return self.fs.contents[self.name]
class mockvfs:
def __init__(self):
self.contents = {}
def read(self, path):
return mockfile(path, self).read()
def readlines(self, path):
# lines need to contain the trailing '\n' to mock the real readlines
return [l for l in mockfile(path, self).read().splitlines(True)]
def __call__(self, path, mode, atomictemp):
return mockfile(path, self)
class testsimplekeyvaluefile(unittest.TestCase):
def setUp(self):
self.vfs = mockvfs()
def testbasicwritingiandreading(self):
dw = {b'key1': b'value1', b'Key2': b'value2'}
scmutil.simplekeyvaluefile(self.vfs, b'kvfile').write(dw)
self.assertEqual(
sorted(self.vfs.read(b'kvfile').split(b'\n')),
[b'', b'Key2=value2', b'key1=value1'],
)
dr = scmutil.simplekeyvaluefile(self.vfs, b'kvfile').read()
self.assertEqual(dr, dw)
if not getattr(unittest.TestCase, 'assertRaisesRegex', False):
# Python 3.7 deprecates the regex*p* version, but 2.7 lacks
# the regex version.
assertRaisesRegex = ( # camelcase-required
unittest.TestCase.assertRaisesRegexp
)
def testinvalidkeys(self):
d = {b'0key1': b'value1', b'Key2': b'value2'}
with self.assertRaisesRegex(
error.ProgrammingError, 'keys must start with a letter.*'
):
scmutil.simplekeyvaluefile(self.vfs, b'kvfile').write(d)
d = {b'key1@': b'value1', b'Key2': b'value2'}
with self.assertRaisesRegex(error.ProgrammingError, 'invalid key.*'):
scmutil.simplekeyvaluefile(self.vfs, b'kvfile').write(d)
def testinvalidvalues(self):
d = {b'key1': b'value1', b'Key2': b'value2\n'}
with self.assertRaisesRegex(error.ProgrammingError, 'invalid val.*'):
scmutil.simplekeyvaluefile(self.vfs, b'kvfile').write(d)
def testcorruptedfile(self):
self.vfs.contents[b'badfile'] = b'ababagalamaga\n'
with self.assertRaisesRegex(
error.CorruptedState, 'dictionary.*element.*'
):
scmutil.simplekeyvaluefile(self.vfs, b'badfile').read()
def testfirstline(self):
dw = {b'key1': b'value1'}
scmutil.simplekeyvaluefile(self.vfs, b'fl').write(dw, firstline=b'1.0')
self.assertEqual(self.vfs.read(b'fl'), b'1.0\nkey1=value1\n')
dr = scmutil.simplekeyvaluefile(self.vfs, b'fl').read(
firstlinenonkeyval=True
)
self.assertEqual(dr, {b'__firstline': b'1.0', b'key1': b'value1'})
if __name__ == "__main__":
silenttestrunner.main(__name__)