Mercurial > hg
view mercurial/config.py @ 29304:5e32852fa4bd
revset: make filteredset.__nonzero__ respect the order of the filteredset
This fix allows __nonzero__ to respect the direction of iteration of the
whole filteredset. Here's the case when it matters. Imagine that we have a
very large repository and we want to execute a command like:
$ hg log --rev '(tip:0) and user(ikostia)' --limit 1
(we want to get the latest commit by me).
Mercurial will evaluate a filteredset lazy data structure, an
instance of the filteredset class, which will know that it has to iterate
in a descending order (isdescending() will return True if called). This
means that when some code iterates over the instance of this filteredset,
the 'and user(ikostia)' condition will be first checked on the latest
revision, then on the second latest and so on, allowing Mercurial to
print matches as it founds them. However, cmdutil.getgraphlogrevs
contains the following code:
revs = _logrevs(repo, opts)
if not revs:
return revset.baseset(), None, None
The "not revs" expression is evaluated by calling filteredset.__nonzero__,
which in its current implementation will try to iterate the filteredset
in ascending order until it finds a revision that matches the 'and user(..'
condition. If the condition is only true on late revisions, a lot of
useless iterations will be done. These iterations could be avoided if
__nonzero__ followed the order of the filteredset, which in my opinion
is a sensible thing to do here.
The problem gets even worse when instead of 'user(ikostia)' some more
expensive check is performed, like grepping the commit diff.
I tested this fix on a very large repo where tip is my commit and my very
first commit comes fairly late in the revision history. Results of timing
of the above command on that very large repo.
-with my fix:
real 0m1.795s
user 0m1.657s
sys 0m0.135s
-without my fix:
real 1m29.245s
user 1m28.223s
sys 0m0.929s
I understand that this is a very specific kind of problem that presents
itself very rarely, only on very big repositories and with expensive
checks and so on. But I don't see any disadvantages to this kind of fix
either.
author | Kostia Balytskyi <ikostia@fb.com> |
---|---|
date | Thu, 02 Jun 2016 22:39:01 +0100 |
parents | e70c97cc9243 |
children | 954002426f78 |
line wrap: on
line source
# config.py - configuration parsing for Mercurial # # Copyright 2009 Matt Mackall <mpm@selenic.com> and others # # 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 import errno import os from .i18n import _ from . import ( error, util, ) class config(object): def __init__(self, data=None, includepaths=[]): self._data = {} self._source = {} self._unset = [] self._includepaths = includepaths if data: for k in data._data: self._data[k] = data[k].copy() self._source = data._source.copy() def copy(self): return config(self) def __contains__(self, section): return section in self._data def hasitem(self, section, item): return item in self._data.get(section, {}) def __getitem__(self, section): return self._data.get(section, {}) def __iter__(self): for d in self.sections(): yield d def update(self, src): for s, n in src._unset: if s in self and n in self._data[s]: del self._data[s][n] del self._source[(s, n)] for s in src: if s not in self: self._data[s] = util.sortdict() self._data[s].update(src._data[s]) self._source.update(src._source) def get(self, section, item, default=None): return self._data.get(section, {}).get(item, default) def backup(self, section, item): """return a tuple allowing restore to reinstall a previous value The main reason we need it is because it handles the "no data" case. """ try: value = self._data[section][item] source = self.source(section, item) return (section, item, value, source) except KeyError: return (section, item) def source(self, section, item): return self._source.get((section, item), "") def sections(self): return sorted(self._data.keys()) def items(self, section): return self._data.get(section, {}).items() def set(self, section, item, value, source=""): if section not in self: self._data[section] = util.sortdict() self._data[section][item] = value if source: self._source[(section, item)] = source def restore(self, data): """restore data returned by self.backup""" if len(data) == 4: # restore old data section, item, value, source = data self._data[section][item] = value self._source[(section, item)] = source else: # no data before, remove everything section, item = data if section in self._data: self._data[section].pop(item, None) self._source.pop((section, item), None) def parse(self, src, data, sections=None, remap=None, include=None): sectionre = util.re.compile(r'\[([^\[]+)\]') itemre = util.re.compile(r'([^=\s][^=]*?)\s*=\s*(.*\S|)') contre = util.re.compile(r'\s+(\S|\S.*\S)\s*$') emptyre = util.re.compile(r'(;|#|\s*$)') commentre = util.re.compile(r'(;|#)') unsetre = util.re.compile(r'%unset\s+(\S+)') includere = util.re.compile(r'%include\s+(\S|\S.*\S)\s*$') section = "" item = None line = 0 cont = False for l in data.splitlines(True): line += 1 if line == 1 and l.startswith('\xef\xbb\xbf'): # Someone set us up the BOM l = l[3:] if cont: if commentre.match(l): continue m = contre.match(l) if m: if sections and section not in sections: continue v = self.get(section, item) + "\n" + m.group(1) self.set(section, item, v, "%s:%d" % (src, line)) continue item = None cont = False m = includere.match(l) if m and include: expanded = util.expandpath(m.group(1)) includepaths = [os.path.dirname(src)] + self._includepaths for base in includepaths: inc = os.path.normpath(os.path.join(base, expanded)) try: include(inc, remap=remap, sections=sections) break except IOError as inst: if inst.errno != errno.ENOENT: raise error.ParseError(_("cannot include %s (%s)") % (inc, inst.strerror), "%s:%s" % (src, line)) continue if emptyre.match(l): continue m = sectionre.match(l) if m: section = m.group(1) if remap: section = remap.get(section, section) if section not in self: self._data[section] = util.sortdict() continue m = itemre.match(l) if m: item = m.group(1) cont = True if sections and section not in sections: continue self.set(section, item, m.group(2), "%s:%d" % (src, line)) continue m = unsetre.match(l) if m: name = m.group(1) if sections and section not in sections: continue if self.get(section, name) is not None: del self._data[section][name] self._unset.append((section, name)) continue raise error.ParseError(l.rstrip(), ("%s:%s" % (src, line))) def read(self, path, fp=None, sections=None, remap=None): if not fp: fp = util.posixfile(path) self.parse(path, fp.read(), sections, remap, self.read)