view mercurial/rcutil.py @ 42237:9f45d3d526f9

hgtagsfnodescache: inherit fnode from parent when possible

If a changeset does not update the content of `.hgtags`, it means it will use
the same file-node (for `.hgtags`) as its parents. In this case we can
directly reuse the parent's file-node.

We use this property when updating the `hgtagsfnodescache` taking a faster path
if we already have a cached value for the parents of the node we are looking
at.

Doing so provides a large performance boost when looking at a lot of fnodes,
especially on repository with very large manifest:

timing for `tagsmod.fnoderevs(ui, repo, repo.changelog.revs())`

mercurial: (41907 revisions, 1923 files)

    before: 6.9 seconds
    after:  2.7 seconds (-54%)

pypy: (96266 revisions, 5198 files)

    before: 80 seconds
    after:  20 seconds (-75%)

mozilla-central: (463411 revisions, 272080 files)

    before: 7166.4 seconds
    after:    47.8 seconds (-99%, x150 speedup)

On a copy of mozilla-try with about 35K heads ans 1.7M changesets, this moves
the computation from many hours to a couple of minutes, making it more
interesting to do a full warm up of this cache before computing tags (from a
cold cache).

There seems to be other performance low hanging fruits, like avoiding the use of
changectx or a more revision centric logic. However, the new code is fast enough
for my needs right now.

# rcutil.py - utilities about config paths, special config sections etc.
#
#  Copyright Mercurial Contributors
#
# 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 os

from . import (
    encoding,
    pycompat,
    util,
)

if pycompat.iswindows:
    from . import scmwindows as scmplatform
else:
    from . import scmposix as scmplatform

fallbackpager = scmplatform.fallbackpager
systemrcpath = scmplatform.systemrcpath
userrcpath = scmplatform.userrcpath

def _expandrcpath(path):
    '''path could be a file or a directory. return a list of file paths'''
    p = util.expandpath(path)
    if os.path.isdir(p):
        join = os.path.join
        return sorted(join(p, f) for f, k in util.listdir(p)
                      if f.endswith('.rc'))
    return [p]

def envrcitems(env=None):
    '''Return [(section, name, value, source)] config items.

    The config items are extracted from environment variables specified by env,
    used to override systemrc, but not userrc.

    If env is not provided, encoding.environ will be used.
    '''
    if env is None:
        env = encoding.environ
    checklist = [
        ('EDITOR', 'ui', 'editor'),
        ('VISUAL', 'ui', 'editor'),
        ('PAGER', 'pager', 'pager'),
    ]
    result = []
    for envname, section, configname in checklist:
        if envname not in env:
            continue
        result.append((section, configname, env[envname], '$%s' % envname))
    return result

def defaultrcpath():
    '''return rc paths in default.d'''
    path = []
    defaultpath = os.path.join(util.datapath, 'default.d')
    if os.path.isdir(defaultpath):
        path = _expandrcpath(defaultpath)
    return path

def rccomponents():
    '''return an ordered [(type, obj)] about where to load configs.

    respect $HGRCPATH. if $HGRCPATH is empty, only .hg/hgrc of current repo is
    used. if $HGRCPATH is not set, the platform default will be used.

    if a directory is provided, *.rc files under it will be used.

    type could be either 'path' or 'items', if type is 'path', obj is a string,
    and is the config file path. if type is 'items', obj is a list of (section,
    name, value, source) that should fill the config directly.
    '''
    envrc = ('items', envrcitems())

    if 'HGRCPATH' in encoding.environ:
        # assume HGRCPATH is all about user configs so environments can be
        # overridden.
        _rccomponents = [envrc]
        for p in encoding.environ['HGRCPATH'].split(pycompat.ospathsep):
            if not p:
                continue
            _rccomponents.extend(('path', p) for p in _expandrcpath(p))
    else:
        normpaths = lambda paths: [('path', os.path.normpath(p)) for p in paths]
        _rccomponents = normpaths(defaultrcpath() + systemrcpath())
        _rccomponents.append(envrc)
        _rccomponents.extend(normpaths(userrcpath()))
    return _rccomponents

def defaultpagerenv():
    '''return a dict of default environment variables and their values,
    intended to be set before starting a pager.
    '''
    return {'LESS': 'FRX', 'LV': '-c'}