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)
# minifileset.py - a simple language to select files
#
# Copyright 2017 Facebook, Inc.
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.
from .i18n import _
from . import (
error,
fileset,
filesetlang,
pycompat,
)
def _sizep(x):
# i18n: "size" is a keyword
expr = filesetlang.getstring(x, _(b"size requires an expression"))
return fileset.sizematcher(expr)
def _compile(tree):
if not tree:
raise error.ParseError(_(b"missing argument"))
op = tree[0]
if op == b'withstatus':
return _compile(tree[1])
elif op in {b'symbol', b'string', b'kindpat'}:
name = filesetlang.getpattern(
tree, {b'path'}, _(b'invalid file pattern')
)
if name.startswith(b'**'): # file extension test, ex. "**.tar.gz"
ext = name[2:]
for c in pycompat.bytestr(ext):
if c in b'*{}[]?/\\':
raise error.ParseError(_(b'reserved character: %s') % c)
return lambda n, s: n.endswith(ext)
elif name.startswith(b'path:'): # directory or full path test
p = name[5:] # prefix
pl = len(p)
f = lambda n, s: n.startswith(p) and (
len(n) == pl or n[pl : pl + 1] == b'/'
)
return f
raise error.ParseError(
_(b"unsupported file pattern: %s") % name,
hint=_(b'paths must be prefixed with "path:"'),
)
elif op in {b'or', b'patterns'}:
funcs = [_compile(x) for x in tree[1:]]
return lambda n, s: any(f(n, s) for f in funcs)
elif op == b'and':
func1 = _compile(tree[1])
func2 = _compile(tree[2])
return lambda n, s: func1(n, s) and func2(n, s)
elif op == b'not':
return lambda n, s: not _compile(tree[1])(n, s)
elif op == b'func':
symbols = {
b'all': lambda n, s: True,
b'none': lambda n, s: False,
b'size': lambda n, s: _sizep(tree[2])(s),
}
name = filesetlang.getsymbol(tree[1])
if name in symbols:
return symbols[name]
raise error.UnknownIdentifier(name, symbols.keys())
elif op == b'minus': # equivalent to 'x and not y'
func1 = _compile(tree[1])
func2 = _compile(tree[2])
return lambda n, s: func1(n, s) and not func2(n, s)
elif op == b'list':
raise error.ParseError(
_(b"can't use a list in this context"),
hint=_(b'see \'hg help "filesets.x or y"\''),
)
raise error.ProgrammingError(b'illegal tree: %r' % (tree,))
def compile(text):
"""generate a function (path, size) -> bool from filter specification.
"text" could contain the operators defined by the fileset language for
common logic operations, and parenthesis for grouping. The supported path
tests are '**.extname' for file extension test, and '"path:dir/subdir"'
for prefix test. The ``size()`` predicate is borrowed from filesets to test
file size. The predicates ``all()`` and ``none()`` are also supported.
'(**.php & size(">10MB")) | **.zip | (path:bin & !path:bin/README)' for
example, will catch all php files whose size is greater than 10 MB, all
files whose name ends with ".zip", and all files under "bin" in the repo
root except for "bin/README".
"""
tree = filesetlang.parse(text)
tree = filesetlang.analyze(tree)
tree = filesetlang.optimize(tree)
return _compile(tree)