##// END OF EJS Templates
setdiscovery: precompute children revisions to avoid quadratic lookup...
setdiscovery: precompute children revisions to avoid quadratic lookup Moving away from dagutil a few commits ago introduced quadratic behavior when resolving children revisions during discovery. This commit introduces a precompute step of the children revisions to avoid the bad behavior. I believe the new code should have near identical performance to what dagutil was doing before. Behavior is still slightly different because we take into account filtered revisions. But this change was made when we moved off dagutil. I added a comment about multiple invocations of this function redundantly calculating the children revisions. I believe this potentially undesirable behavior was present when we used dagutil, as the call to inverse() previously in this function created a new object and required computing children on every invocation. I thought we should document the potential for a performance issue rather than let it go undocumented. Differential Revision: https://phab.mercurial-scm.org/D4326

File last commit:

r38915:e79a69af default
r39214:274acf37 default
Show More
minifileset.py
92 lines | 3.5 KiB | text/x-python | PythonLexer
# 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 __future__ import absolute_import
from .i18n import _
from . import (
error,
fileset,
filesetlang,
pycompat,
)
def _sizep(x):
# i18n: "size" is a keyword
expr = filesetlang.getstring(x, _("size requires an expression"))
return fileset.sizematcher(expr)
def _compile(tree):
if not tree:
raise error.ParseError(_("missing argument"))
op = tree[0]
if op == 'withstatus':
return _compile(tree[1])
elif op in {'symbol', 'string', 'kindpat'}:
name = filesetlang.getpattern(tree, {'path'}, _('invalid file pattern'))
if name.startswith('**'): # file extension test, ex. "**.tar.gz"
ext = name[2:]
for c in pycompat.bytestr(ext):
if c in '*{}[]?/\\':
raise error.ParseError(_('reserved character: %s') % c)
return lambda n, s: n.endswith(ext)
elif name.startswith('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] == '/')
return f
raise error.ParseError(_("unsupported file pattern: %s") % name,
hint=_('paths must be prefixed with "path:"'))
elif op in {'or', 'patterns'}:
funcs = [_compile(x) for x in tree[1:]]
return lambda n, s: any(f(n, s) for f in funcs)
elif op == 'and':
func1 = _compile(tree[1])
func2 = _compile(tree[2])
return lambda n, s: func1(n, s) and func2(n, s)
elif op == 'not':
return lambda n, s: not _compile(tree[1])(n, s)
elif op == 'func':
symbols = {
'all': lambda n, s: True,
'none': lambda n, s: False,
'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 == '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 == 'list':
raise error.ParseError(_("can't use a list in this context"),
hint=_('see \'hg help "filesets.x or y"\''))
raise error.ProgrammingError('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)