tests/test-minifileset.py

includematcher: separate "parents" from "dirs"

A future patch will make use of this separation so that we can make more
intelligent decisions about what to investigate/load when the matcher is in use.

Currently, even with this patch, we typically use the 'visitdir' call to identify if
we can skip some directory, something along the lines of:

    for f in all_items:
        if match.visitdir(f):
           <do stuff>

This can be slower than we'd like if there are a lot of items; it requires N
calls to match.visitdir in the best case.  Commonly, especially with 'narrow',
we have a situation where we do some work for the directory, possibly just
loading it from disk (when using treemanifests) and then check if we should be
interacting with it at all, which can be a huge slowdown in some pathological
cases.

Differential Revision: https://phab.mercurial-scm.org/D4129

from __future__ import absolute_import
from __future__ import print_function

import os
import sys

# make it runnable directly without run-tests.py
sys.path[0:0] = [os.path.join(os.path.dirname(__file__), '..')]

from mercurial import minifileset

def check(text, truecases, falsecases):
    f = minifileset.compile(text)
    for args in truecases:
        if not f(*args):
            print('unexpected: %r should include %r' % (text, args))
    for args in falsecases:
        if f(*args):
            print('unexpected: %r should exclude %r' % (text, args))

check(b'all()', [(b'a.php', 123), (b'b.txt', 0)], [])
check(b'none()', [], [(b'a.php', 123), (b'b.txt', 0)])
check(b'!!!!((!(!!all())))', [], [(b'a.php', 123), (b'b.txt', 0)])

check(b'"path:a" & (**.b | **.c)',
      [(b'a/b.b', 0), (b'a/c.c', 0)], [(b'b/c.c', 0)])
check(b'(path:a & **.b) | **.c',
      [(b'a/b.b', 0), (b'a/c.c', 0), (b'b/c.c', 0)], [])

check(b'**.bin - size("<20B")',
      [(b'b.bin', 21)], [(b'a.bin', 11), (b'b.txt', 21)])

check(b'!!**.bin or size(">20B") + "path:bin" or !size(">10")',
      [(b'a.bin', 11), (b'b.txt', 21), (b'bin/abc', 11)],
      [(b'a.notbin', 11), (b'b.txt', 11), (b'bin2/abc', 11)])

check(
    b'(**.php and size(">10KB")) | **.zip | ("path:bin" & !"path:bin/README") '
    b' | size(">1M")',
    [(b'a.php', 15000), (b'a.zip', 0), (b'bin/a', 0), (b'bin/README', 1e7)],
    [(b'a.php', 5000), (b'b.zip2', 0), (b't/bin/a', 0), (b'bin/README', 1)])