tests/test-walkrepo.py

largefiles: show also how many data entities are outgoing at "hg summary"

Before this patch, "hg summary --large" shows how many largefiles are
changed or added in outgoing revisions only in the point of the view
of filenames.

For example, according to the number of outgoing largefiles shown in
"hg summary" output, users should expect that the former below costs
much more to upload outgoing largefiles than the latter.

  - outgoing revisions add a hundred largefiles, but all of them refer
    the same data entity

    in this case, only one data entity is outgoing, even though "hg
    summary" says that a hundred largefiles are outgoing.

  - a hundred outgoing revisions change only one largefile with
    distinct data

    in this case, a hundred data entities are outgoing, even though
    "hg summary" says that only one largefile is outgoing.

But the latter costs much more than the former, in fact.

This patch shows also how many data entities are outgoing at "hg
summary" by counting number of unique hash values for outgoing
largefiles.

This patch introduces "_getoutgoings" to centralize the logic
(de-duplication, too) into it for convenience of subsequent patches,
even though it is not required in "hg summary" case.

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 "sub1set 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()