view contrib/dirstatenonnormalcheck.py @ 44593:496868f1030c

rust-matchers: use the `regex` crate

Instead of falling back to Python when a code path with "ignore" functionality
is reached and `Re2` is not installed, the default compilation (i.e. without
the `with-re2` feature) will use the `regex` crate for all regular expressions
business.

As with the introduction of `Re2` in a previous series, this yields a big
performance boost compared to the Python + C code in `status`, `diff`, `commit`,
`update`, and maybe others.

For now `Re2` looks to be faster at compiling the DFA (1.5ms vs 5ms for
Netbeans' `.hgignore`) and a bit faster in actual use: (123ms vs 137ms for
the parallel traversal of Netbeans' clean repo). I am in talks with the author
of `regex` to see whether that performance difference is a bug, a "won't fix",
or a tuning issue.

The `regex` crate is already one of our dependencies and using this code does
not require any additional work from the end-user than to use the Rust
extensions.

Differential Revision: https://phab.mercurial-scm.org/D8323

# dirstatenonnormalcheck.py - extension to check the consistency of the
# dirstate's non-normal map
#
# For most operations on dirstate, this extensions checks that the nonnormalset
# contains the right entries.
# It compares the nonnormal file to a nonnormalset built from the map of all
# the files in the dirstate to check that they contain the same files.

from __future__ import absolute_import

from mercurial import (
    dirstate,
    extensions,
)


def nonnormalentries(dmap):
    """Compute nonnormal entries from dirstate's dmap"""
    res = set()
    for f, e in dmap.iteritems():
        if e[0] != b'n' or e[3] == -1:
            res.add(f)
    return res


def checkconsistency(ui, orig, dmap, _nonnormalset, label):
    """Compute nonnormalset from dmap, check that it matches _nonnormalset"""
    nonnormalcomputedmap = nonnormalentries(dmap)
    if _nonnormalset != nonnormalcomputedmap:
        ui.develwarn(b"%s call to %s\n" % (label, orig), config=b'dirstate')
        ui.develwarn(b"inconsistency in nonnormalset\n", config=b'dirstate')
        ui.develwarn(b"[nonnormalset] %s\n" % _nonnormalset, config=b'dirstate')
        ui.develwarn(b"[map] %s\n" % nonnormalcomputedmap, config=b'dirstate')


def _checkdirstate(orig, self, arg):
    """Check nonnormal set consistency before and after the call to orig"""
    checkconsistency(
        self._ui, orig, self._map, self._map.nonnormalset, b"before"
    )
    r = orig(self, arg)
    checkconsistency(
        self._ui, orig, self._map, self._map.nonnormalset, b"after"
    )
    return r


def extsetup(ui):
    """Wrap functions modifying dirstate to check nonnormalset consistency"""
    dirstatecl = dirstate.dirstate
    devel = ui.configbool(b'devel', b'all-warnings')
    paranoid = ui.configbool(b'experimental', b'nonnormalparanoidcheck')
    if devel:
        extensions.wrapfunction(dirstatecl, '_writedirstate', _checkdirstate)
        if paranoid:
            # We don't do all these checks when paranoid is disable as it would
            # make the extension run very slowly on large repos
            extensions.wrapfunction(dirstatecl, 'normallookup', _checkdirstate)
            extensions.wrapfunction(dirstatecl, 'otherparent', _checkdirstate)
            extensions.wrapfunction(dirstatecl, 'normal', _checkdirstate)
            extensions.wrapfunction(dirstatecl, 'write', _checkdirstate)
            extensions.wrapfunction(dirstatecl, 'add', _checkdirstate)
            extensions.wrapfunction(dirstatecl, 'remove', _checkdirstate)
            extensions.wrapfunction(dirstatecl, 'merge', _checkdirstate)
            extensions.wrapfunction(dirstatecl, 'drop', _checkdirstate)