hgext/git/gitutil.py

match: convert O(n) to O(log n) in exactmatcher.visitchildrenset

When using narrow, during rebase this is called (at least) once per directory in
the set of files in the commit being rebased. Every time it's called, we did the
set arithmetic (now extracted and cached), which was probably pretty cheap but
not necessary to repeat each time, looped over every item in the matcher and
kept things that started with the directory we were querying.

With very large narrowspecs, and a commit that touched a file in a large number
of directories, this was slow. In a pathological repo, the rebase of a single
commit (that touched over 17k files, I believe in approximately as many
directories) with a narrowspec that had >32k entries took 8,246s of profiled
time, with 5,007s of that spent in visitchildrenset (transitively). With this
change, the time spent in visitchildrenset is less than 34s (which is where my
profile cut off). Most of the remaining time was network access due to our
custom remotefilelog-based setup not properly prefetching.

Differential Revision: https://phab.mercurial-scm.org/D10294

"""utilities to assist in working with pygit2"""
from __future__ import absolute_import

from mercurial.node import bin, hex, nullid

from mercurial import pycompat

pygit2_module = None


def get_pygit2():
    global pygit2_module
    if pygit2_module is None:
        try:
            import pygit2 as pygit2_module

            pygit2_module.InvalidSpecError
        except (ImportError, AttributeError):
            pass
    return pygit2_module


def pygit2_version():
    mod = get_pygit2()
    v = "N/A"

    if mod:
        try:
            v = mod.__version__
        except AttributeError:
            pass

    return b"(pygit2 %s)" % v.encode("utf-8")


def togitnode(n):
    """Wrapper to convert a Mercurial binary node to a unicode hexlified node.

    pygit2 and sqlite both need nodes as strings, not bytes.
    """
    assert len(n) == 20
    return pycompat.sysstr(hex(n))


def fromgitnode(n):
    """Opposite of togitnode."""
    assert len(n) == 40
    if pycompat.ispy3:
        return bin(n.encode('ascii'))
    return bin(n)


nullgit = togitnode(nullid)