tests/list-tree.py

copies: avoid materializing a full directory map during copy tracing

Materializing a full copy of every directory in a treemanifest repo can be quite
expensive, even with a narrow matcher. For flat manifest repos, this should be
equivalent - it will still materialize (and cache) a dict of all of the dirs
inside of the manifest object, we just don't get a copy of it.

In a repo I have here, this brings the time for a simple rebase from 11.197s to
4.609s.

Differential Revision: https://phab.mercurial-scm.org/D9503

from __future__ import (
    absolute_import,
    print_function,
)

import argparse
import os

ap = argparse.ArgumentParser()
ap.add_argument('path', nargs='+')
opts = ap.parse_args()


def gather():
    for p in opts.path:
        if not os.path.exists(p):
            return
        if os.path.isdir(p):
            yield p + os.path.sep
            for dirpath, dirs, files in os.walk(p):
                for d in dirs:
                    yield os.path.join(dirpath, d) + os.path.sep
                for f in files:
                    yield os.path.join(dirpath, f)
        else:
            yield p


print('\n'.join(sorted(gather(), key=lambda x: x.replace(os.path.sep, '/'))))