annotate mercurial/policy.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

# policy.py - module policy logic for Mercurial.
#
# Copyright 2015 Gregory Szorc <[e-mail]>
#
# 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
import sys

# Rules for how modules can be loaded. Values are:
#
#    c - require C extensions
#    allow - allow pure Python implementation when C loading fails
#    cffi - required cffi versions (implemented within pure module)
#    cffi-allow - allow pure Python implementation if cffi version is missing
#    py - only load pure Python modules
#
# By default, fall back to the pure modules so the in-place build can
# run without recompiling the C extensions. This will be overridden by
# __modulepolicy__ generated by setup.py.
policy = b'allow'
_packageprefs = {
    # policy: (versioned package, pure package)
    b'c': (r'cext', None),
    b'allow': (r'cext', r'pure'),
    b'cffi': (r'cffi', None),
    b'cffi-allow': (r'cffi', r'pure'),
    b'py': (None, r'pure'),
}

try:
    from . import __modulepolicy__
    policy = __modulepolicy__.modulepolicy
except ImportError:
    pass

# PyPy doesn't load C extensions.
#
# The canonical way to do this is to test platform.python_implementation().
# But we don't import platform and don't bloat for it here.
if r'__pypy__' in sys.builtin_module_names:
    policy = b'cffi'

# Our C extensions aren't yet compatible with Python 3. So use pure Python
# on Python 3 for now.
if sys.version_info[0] >= 3:
    policy = b'py'

# Environment variable can always force settings.
if sys.version_info[0] >= 3:
    if r'HGMODULEPOLICY' in os.environ:
        policy = os.environ[r'HGMODULEPOLICY'].encode(r'utf-8')
else:
    policy = os.environ.get(r'HGMODULEPOLICY', policy)

def _importfrom(pkgname, modname):
    # from .<pkgname> import <modname> (where . is looked through this module)
    fakelocals = {}
    pkg = __import__(pkgname, globals(), fakelocals, [modname], level=1)
    try:
        fakelocals[modname] = mod = getattr(pkg, modname)
    except AttributeError:
        raise ImportError(r'cannot import name %s' % modname)
    # force import; fakelocals[modname] may be replaced with the real module
    getattr(mod, r'__doc__', None)
    return fakelocals[modname]

# keep in sync with "version" in C modules
_cextversions = {
    (r'cext', r'base85'): 1,
    (r'cext', r'bdiff'): 1,
    (r'cext', r'diffhelpers'): 1,
    (r'cext', r'mpatch'): 1,
    (r'cext', r'osutil'): 3,
    (r'cext', r'parsers'): 4,
}

# map import request to other package or module
_modredirects = {
    (r'cext', r'charencode'): (r'cext', r'parsers'),
    (r'cffi', r'base85'): (r'pure', r'base85'),
    (r'cffi', r'charencode'): (r'pure', r'charencode'),
    (r'cffi', r'diffhelpers'): (r'pure', r'diffhelpers'),
    (r'cffi', r'parsers'): (r'pure', r'parsers'),
}

def _checkmod(pkgname, modname, mod):
    expected = _cextversions.get((pkgname, modname))
    actual = getattr(mod, r'version', None)
    if actual != expected:
        raise ImportError(r'cannot import module %s.%s '
                          r'(expected version: %d, actual: %r)'
                          % (pkgname, modname, expected, actual))

def importmod(modname):
    """Import module according to policy and check API version"""
    try:
        verpkg, purepkg = _packageprefs[policy]
    except KeyError:
        raise ImportError(r'invalid HGMODULEPOLICY %r' % policy)
    assert verpkg or purepkg
    if verpkg:
        pn, mn = _modredirects.get((verpkg, modname), (verpkg, modname))
        try:
            mod = _importfrom(pn, mn)
            if pn == verpkg:
                _checkmod(pn, mn, mod)
            return mod
        except ImportError:
            if not purepkg:
                raise
    pn, mn = _modredirects.get((purepkg, modname), (purepkg, modname))
    return _importfrom(pn, mn)