tests/test-walkrepo.py

treemanifest: optimize treemanifest._walk() to skip directories

This makes treemanifest.walk() not visit submanifests that are known not to
have any matching files. It does this by calling match.visitdir() on
submanifests as it walks.

This change also updates largefiles to be able to work with this new behavior
in treemanifests. It overrides match.visitdir(), the function that dictates
how walk() and matches() skip over directories.

The greatest speed improvements are seen with narrower scopes. For example,
this commit speeds up the following command on the Mozilla repo from 1.14s
to 1.02s:
  hg files -r . dom/apps/

Whereas with a wider scope, dom/, the speed only improves from 1.21s to 1.13s.

As with similar a similar optimization to treemanifest.matches(), this change
will bring out even bigger performance improvements once treemanifests are
loaded lazily. Once that happens, we won't just skip over looking at
submanifests, but we'll skip even loading them.

import os
from mercurial import hg, ui
from mercurial.scmutil import walkrepos
from mercurial.util import checklink
from os import mkdir, chdir
from os.path import join as pjoin

u = ui.ui()
sym = checklink('.')

hg.repository(u, 'top1', create=1)
mkdir('subdir')
chdir('subdir')
hg.repository(u, 'sub1', create=1)
mkdir('subsubdir')
chdir('subsubdir')
hg.repository(u, 'subsub1', create=1)
chdir(os.path.pardir)
if sym:
    os.symlink(os.path.pardir, 'circle')
    os.symlink(pjoin('subsubdir', 'subsub1'), 'subsub1')

def runtest():
    reposet = frozenset(walkrepos('.', followsym=True))
    if sym and (len(reposet) != 3):
        print "reposet = %r" % (reposet,)
        print ("Found %d repositories when I should have found 3"
               % (len(reposet),))
    if (not sym) and (len(reposet) != 2):
        print "reposet = %r" % (reposet,)
        print ("Found %d repositories when I should have found 2"
               % (len(reposet),))
    sub1set = frozenset((pjoin('.', 'sub1'),
                         pjoin('.', 'circle', 'subdir', 'sub1')))
    if len(sub1set & reposet) != 1:
        print "sub1set = %r" % (sub1set,)
        print "reposet = %r" % (reposet,)
        print "sub1set and reposet should have exactly one path in common."
    sub2set = frozenset((pjoin('.', 'subsub1'),
                         pjoin('.', 'subsubdir', 'subsub1')))
    if len(sub2set & reposet) != 1:
        print "sub2set = %r" % (sub2set,)
        print "reposet = %r" % (reposet,)
        print "sub2set and reposet should have exactly one path in common."
    sub3 = pjoin('.', 'circle', 'top1')
    if sym and sub3 not in reposet:
        print "reposet = %r" % (reposet,)
        print "Symbolic links are supported and %s is not in reposet" % (sub3,)

runtest()
if sym:
    # Simulate not having symlinks.
    del os.path.samestat
    sym = False
    runtest()