view mercurial/rcutil.py @ 35616:706aa203b396

fileset: add a lightweight file filtering language

This patch was inspired by one that Jun Wu authored for the fb-experimental
repo, to avoid using matcher for efficiency[1].  We want a way to specify what
files will be converted to LFS at commit time.  And per discussion, we also want
to specify what files to skip, text diff, or merge in another config option.
The current `lfs.threshold` config option could not satisfy complex needs.  I'm
putting it in a core package because Augie floated the idea of also using it for
narrow and sparse.

Yuya suggested farming out to fileset.parse(), which added support for more
symbols.  The only fileset element not supported here is 'negate'.  (List isn't
supported by filesets either.)  I also changed the 'always' token to the 'all()'
predicate for consistency, and introduced 'none()' to improve readability in a
future tracked file based config.  The extension operator was changed from '.'
to '**', to match how recursive path globs are specified.  Finally, I changed
the path matcher from '/' to 'path:' at Yuya's suggestion, for consistency with
matcher.  Unfortunately, ':' is currently reserved in filesets, so this has to
be quoted to be processed as a string instead of a symbol[2].  We should
probably revisit that, because it's seriously ugly.  But it's only used by an
experimental extension, and I think using a file based config for LFS may drive
some more tweaks, so I'm settling for this for now.

I reserved all of the glob characters in fileset except '.' and '_' for the
extension test because those are likely valid extension characters.

Sample filter settings:

  all()                        # everything
  size(">20MB")                # larger than 20MB
  !**.txt                      # except for .txt files
  **.zip | **.tar.gz | **.7z   # some types of compressed files
  "path:bin"                   # files under "bin" in the project root

[1] https://www.mercurial-scm.org/pipermail/mercurial-devel/2017-December/109387.html
[2] https://www.mercurial-scm.org/pipermail/mercurial-devel/2018-January/109729.html

# 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 [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'}