mercurial/minifileset.py

wireprotov2: send linknodes to emitfilerevisions()

Previously, linknodes were calculated within emitfilerevisions() by
using filectx.introrev(), which would always use the linkrev/linknode
as recorded by storage. This is wrong for cases where the receiver
doesn't have the changeset the linknode refers to.

This commit changes the logic for linknode emission so the mapping
of filenode to linknode is computed by the caller and passed into
emitfilerevisions().

As part of the change, linknodes for "filesdata" in the
haveparents=False case are now correct: the existing code performed a
manifest walk and it was trivial to plug in the correct linknode.

However, behavior for the haveparents=True case is still wrong
because it relies on filtering linkrevs against the outgoing set in
order to determine what to send. This will be fixed in a subsequent
commit.

The change test test-wireproto-exchangev2-shallow.t is a bit wonky.
The test repo has 6 revisions. The changed test is performing a shallow
clone with depth=1. So, only file data for revision 5 is present
locally. So, the new behavior of associating the linknode with
revision 5 for every file revision seems correct. Of course, when
backfilling old revisions, we'll want to update the linknode. But
this problem requires wire protocol support and we'll cross that
bridge later.

Differential Revision: https://phab.mercurial-scm.org/D5405

# 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,
    filesetlang,
    pycompat,
)

def _sizep(x):
    # i18n: "size" is a keyword
    expr = filesetlang.getstring(x, _("size requires an expression"))
    return fileset.sizematcher(expr)

def _compile(tree):
    if not tree:
        raise error.ParseError(_("missing argument"))
    op = tree[0]
    if op == 'withstatus':
        return _compile(tree[1])
    elif op in {'symbol', 'string', 'kindpat'}:
        name = filesetlang.getpattern(tree, {'path'}, _('invalid file pattern'))
        if name.startswith('**'): # file extension test, ex. "**.tar.gz"
            ext = name[2:]
            for c in pycompat.bytestr(ext):
                if c in '*{}[]?/\\':
                    raise error.ParseError(_('reserved character: %s') % c)
            return lambda n, s: n.endswith(ext)
        elif 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:pl + 1] == '/')
            return f
        raise error.ParseError(_("unsupported file pattern: %s") % name,
                               hint=_('paths must be prefixed with "path:"'))
    elif op in {'or', 'patterns'}:
        funcs = [_compile(x) for x in tree[1:]]
        return lambda n, s: any(f(n, s) for f in funcs)
    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 == 'func':
        symbols = {
            'all': lambda n, s: True,
            'none': lambda n, s: False,
            'size': lambda n, s: _sizep(tree[2])(s),
        }

        name = filesetlang.getsymbol(tree[1])
        if 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 == '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 = filesetlang.parse(text)
    tree = filesetlang.analyze(tree)
    tree = filesetlang.optimize(tree)
    return _compile(tree)