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)
#!/usr/bin/env python3
#
# check-config - a config flag documentation checker for Mercurial
#
# Copyright 2015 Olivia Mackall <olivia@selenic.com>
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.
import re
import sys
foundopts = {}
documented = {}
allowinconsistent = set()
configre = re.compile(
br'''
# Function call
ui\.config(?P<ctype>|int|bool|list)\(
# First argument.
['"](?P<section>\S+)['"],\s*
# Second argument
['"](?P<option>\S+)['"](,\s+
(?:default=)?(?P<default>\S+?))?
\)''',
re.VERBOSE | re.MULTILINE,
)
configwithre = re.compile(
br'''
ui\.config(?P<ctype>with)\(
# First argument is callback function. This doesn't parse robustly
# if it is e.g. a function call.
[^,]+,\s*
['"](?P<section>\S+)['"],\s*
['"](?P<option>\S+)['"](,\s+
(?:default=)?(?P<default>\S+?))?
\)''',
re.VERBOSE | re.MULTILINE,
)
configpartialre = br"""ui\.config"""
ignorere = re.compile(
br'''
\#\s(?P<reason>internal|experimental|deprecated|developer|inconsistent)\s
config:\s(?P<config>\S+\.\S+)$
''',
re.VERBOSE | re.MULTILINE,
)
if sys.version_info[0] > 2:
def mkstr(b):
if isinstance(b, str):
return b
return b.decode('utf8')
else:
mkstr = lambda x: x
def main(args):
for f in args:
sect = b''
prevname = b''
confsect = b''
carryover = b''
linenum = 0
for l in open(f, 'rb'):
linenum += 1
# check topic-like bits
m = re.match(br'\s*``(\S+)``', l)
if m:
prevname = m.group(1)
if re.match(br'^\s*-+$', l):
sect = prevname
prevname = b''
if sect and prevname:
name = sect + b'.' + prevname
documented[name] = 1
# check docstring bits
m = re.match(br'^\s+\[(\S+)\]', l)
if m:
confsect = m.group(1)
continue
m = re.match(br'^\s+(?:#\s*)?(\S+) = ', l)
if m:
name = confsect + b'.' + m.group(1)
documented[name] = 1
# like the bugzilla extension
m = re.match(br'^\s*(\S+\.\S+)$', l)
if m:
documented[m.group(1)] = 1
# like convert
m = re.match(br'^\s*:(\S+\.\S+):\s+', l)
if m:
documented[m.group(1)] = 1
# quoted in help or docstrings
m = re.match(br'.*?``(\S+\.\S+)``', l)
if m:
documented[m.group(1)] = 1
# look for ignore markers
m = ignorere.search(l)
if m:
if m.group('reason') == b'inconsistent':
allowinconsistent.add(m.group('config'))
else:
documented[m.group('config')] = 1
# look for code-like bits
line = carryover + l
m = configre.search(line) or configwithre.search(line)
if m:
ctype = m.group('ctype')
if not ctype:
ctype = 'str'
name = m.group('section') + b"." + m.group('option')
default = m.group('default')
if default in (
None,
b'False',
b'None',
b'0',
b'[]',
b'""',
b"''",
):
default = b''
if re.match(b'[a-z.]+$', default):
default = b'<variable>'
if (
name in foundopts
and (ctype, default) != foundopts[name]
and name not in allowinconsistent
):
print(mkstr(l.rstrip()))
fctype, fdefault = foundopts[name]
print(
"conflict on %s: %r != %r"
% (
mkstr(name),
(mkstr(ctype), mkstr(default)),
(mkstr(fctype), mkstr(fdefault)),
)
)
print("at %s:%d:" % (mkstr(f), linenum))
foundopts[name] = (ctype, default)
carryover = b''
else:
m = re.search(configpartialre, line)
if m:
carryover = line
else:
carryover = b''
for name in sorted(foundopts):
if name not in documented:
if not (
name.startswith(b"devel.")
or name.startswith(b"experimental.")
or name.startswith(b"debug.")
):
ctype, default = foundopts[name]
if default:
if isinstance(default, bytes):
default = mkstr(default)
default = ' [%s]' % default
elif isinstance(default, bytes):
default = mkstr(default)
print(
"undocumented: %s (%s)%s"
% (mkstr(name), mkstr(ctype), default)
)
if __name__ == "__main__":
if len(sys.argv) > 1:
sys.exit(main(sys.argv[1:]))
else:
sys.exit(main([l.rstrip() for l in sys.stdin]))