view mercurial/minifileset.py @ 35618:c780e0649e41

lfs: migrate most file filtering from threshold to custom filter

Migrate `lfs.threshold` to more powerful `lfs.filter` added by D4990618 so
people can specify what files to be stored in LFS with more flexibility.

This patch was authored by Jun Wu for the fb-experimental repo, to avoid using
matcher for efficiency[1].  All I've changed here is to register the new
'lfs.track' default so that the tests run cleanly, and adapt the subsequent
language changes.  Migrating the remaining uses of 'lfs.threshold' can be done
separately since there's a fallback in place.

[1] https://www.mercurial-scm.org/pipermail/mercurial-devel/2017-December/109388.html

# 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,
)

def _compile(tree):
    if not tree:
        raise error.ParseError(_("missing argument"))
    op = tree[0]
    if op == 'symbol':
        name = fileset.getstring(tree, _('invalid file pattern'))
        if name.startswith('**'): # file extension test, ex. "**.tar.gz"
            ext = name[2:]
            for c in ext:
                if c in '*{}[]?/\\':
                    raise error.ParseError(_('reserved character: %s') % c)
            return lambda n, s: n.endswith(ext)
        raise error.ParseError(_('invalid symbol: %s') % name)
    elif op == 'string':
        # TODO: teach fileset about 'path:', so that this can be a symbol and
        # not require quoting.
        name = fileset.getstring(tree, _('invalid path literal'))
        if 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] == '/')
            return f
        raise error.ParseError(_("invalid string"),
                               hint=_('paths must be prefixed with "path:"'))
    elif op == 'or':
        func1 = _compile(tree[1])
        func2 = _compile(tree[2])
        return lambda n, s: func1(n, s) or func2(n, s)
    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 == 'group':
        return _compile(tree[1])
    elif op == 'func':
        symbols = {
            'all': lambda n, s: True,
            'none': lambda n, s: False,
            'size': lambda n, s: fileset.sizematcher(tree[2])(s),
        }

        x = tree[1]
        name = x[1]
        if x[0] == 'symbol' and 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 == 'negate':
        raise error.ParseError(_("can't use negate operator in this context"))
    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 = fileset.parse(text)
    return _compile(tree)