tests/test-trusted.py

revlog: change generaldelta delta parent heuristic

The old generaldelta heuristic was "if p1 (or p2) was closer than the last full text,
use it, otherwise use prev". This was problematic when a repo contained multiple
branches that were very different. If commits to branch A were pushed, and the
last full text was branch B, it would generate a fulltext. Then if branch B was
pushed, it would generate another fulltext. The problem is that the last
fulltext (and delta'ing against `prev` in general) has no correlation with the
contents of the incoming revision, and therefore will always have degenerate
cases.

According to the blame, that algorithm was chosen to minimize the chain length.
Since there is already code that protects against that (the delta-vs-fulltext
code), and since it has been improved since the original generaldelta algorithm
went in (2011), I believe the chain length criteria will still be preserved.

The new algorithm always diffs against p1 (or p2 if it's closer), unless the
resulting delta will fail the delta-vs-fulltext check, in which case we delta
against prev.

Some before and after stats on manifest.d size.

internal large repo
old heuristic - 2.0 GB
new heuristic - 1.2 GB

mozilla-central
old heuristic - 242 MB
new heuristic - 261 MB

The regression in mozilla central is due to the new heuristic choosing p2r as
the delta when it's closer to the tip. Switching the algorithm to always prefer
p1r brings the size back down (242 MB). This is result of the way in which
mozilla does merges and pushes, and the result could easily swing the other
direction in other repos (depending on if they merge X into Y or Y into X), but
will never be as degenerate as before.

I future patch will address the regression by introducing an optional, even more
aggressive delta heuristic which will knock the mozilla manifest size down
dramatically.

# Since it's not easy to write a test that portably deals
# with files from different users/groups, we cheat a bit by
# monkey-patching some functions in the util module

import os
from mercurial import ui, util, error

hgrc = os.environ['HGRCPATH']
f = open(hgrc)
basehgrc = f.read()
f.close()

def testui(user='foo', group='bar', tusers=(), tgroups=(),
           cuser='foo', cgroup='bar', debug=False, silent=False,
           report=True):
    # user, group => owners of the file
    # tusers, tgroups => trusted users/groups
    # cuser, cgroup => user/group of the current process

    # write a global hgrc with the list of trusted users/groups and
    # some setting so that we can be sure it was read
    f = open(hgrc, 'w')
    f.write(basehgrc)
    f.write('\n[paths]\n')
    f.write('global = /some/path\n\n')

    if tusers or tgroups:
        f.write('[trusted]\n')
        if tusers:
            f.write('users = %s\n' % ', '.join(tusers))
        if tgroups:
            f.write('groups = %s\n' % ', '.join(tgroups))
    f.close()

    # override the functions that give names to uids and gids
    def username(uid=None):
        if uid is None:
            return cuser
        return user
    util.username = username

    def groupname(gid=None):
        if gid is None:
            return 'bar'
        return group
    util.groupname = groupname

    def isowner(st):
        return user == cuser
    util.isowner = isowner

    # try to read everything
    #print '# File belongs to user %s, group %s' % (user, group)
    #print '# trusted users = %s; trusted groups = %s' % (tusers, tgroups)
    kind = ('different', 'same')
    who = ('', 'user', 'group', 'user and the group')
    trusted = who[(user in tusers) + 2*(group in tgroups)]
    if trusted:
        trusted = ', but we trust the ' + trusted
    print '# %s user, %s group%s' % (kind[user == cuser], kind[group == cgroup],
                                     trusted)

    u = ui.ui()
    u.setconfig('ui', 'debug', str(bool(debug)))
    u.setconfig('ui', 'report_untrusted', str(bool(report)))
    u.readconfig('.hg/hgrc')
    if silent:
        return u
    print 'trusted'
    for name, path in u.configitems('paths'):
        print '   ', name, '=', path
    print 'untrusted'
    for name, path in u.configitems('paths', untrusted=True):
        print '.',
        u.config('paths', name) # warning with debug=True
        print '.',
        u.config('paths', name, untrusted=True) # no warnings
        print name, '=', path
    print

    return u

os.mkdir('repo')
os.chdir('repo')
os.mkdir('.hg')
f = open('.hg/hgrc', 'w')
f.write('[paths]\n')
f.write('local = /another/path\n\n')
f.close()

#print '# Everything is run by user foo, group bar\n'

# same user, same group
testui()
# same user, different group
testui(group='def')
# different user, same group
testui(user='abc')
# ... but we trust the group
testui(user='abc', tgroups=['bar'])
# different user, different group
testui(user='abc', group='def')
# ... but we trust the user
testui(user='abc', group='def', tusers=['abc'])
# ... but we trust the group
testui(user='abc', group='def', tgroups=['def'])
# ... but we trust the user and the group
testui(user='abc', group='def', tusers=['abc'], tgroups=['def'])
# ... but we trust all users
print '# we trust all users'
testui(user='abc', group='def', tusers=['*'])
# ... but we trust all groups
print '# we trust all groups'
testui(user='abc', group='def', tgroups=['*'])
# ... but we trust the whole universe
print '# we trust all users and groups'
testui(user='abc', group='def', tusers=['*'], tgroups=['*'])
# ... check that users and groups are in different namespaces
print "# we don't get confused by users and groups with the same name"
testui(user='abc', group='def', tusers=['def'], tgroups=['abc'])
# ... lists of user names work
print "# list of user names"
testui(user='abc', group='def', tusers=['foo', 'xyz', 'abc', 'bleh'],
       tgroups=['bar', 'baz', 'qux'])
# ... lists of group names work
print "# list of group names"
testui(user='abc', group='def', tusers=['foo', 'xyz', 'bleh'],
       tgroups=['bar', 'def', 'baz', 'qux'])

print "# Can't figure out the name of the user running this process"
testui(user='abc', group='def', cuser=None)

print "# prints debug warnings"
u = testui(user='abc', group='def', cuser='foo', debug=True)

print "# report_untrusted enabled without debug hides warnings"
u = testui(user='abc', group='def', cuser='foo', report=False)

print "# report_untrusted enabled with debug shows warnings"
u = testui(user='abc', group='def', cuser='foo', debug=True, report=False)

print "# ui.readconfig sections"
filename = 'foobar'
f = open(filename, 'w')
f.write('[foobar]\n')
f.write('baz = quux\n')
f.close()
u.readconfig(filename, sections=['foobar'])
print u.config('foobar', 'baz')

print
print "# read trusted, untrusted, new ui, trusted"
u = ui.ui()
u.setconfig('ui', 'debug', 'on')
u.readconfig(filename)
u2 = u.copy()
def username(uid=None):
    return 'foo'
util.username = username
u2.readconfig('.hg/hgrc')
print 'trusted:'
print u2.config('foobar', 'baz')
print 'untrusted:'
print u2.config('foobar', 'baz', untrusted=True)

print
print "# error handling"

def assertraises(f, exc=util.Abort):
    try:
        f()
    except exc as inst:
        print 'raised', inst.__class__.__name__
    else:
        print 'no exception?!'

print "# file doesn't exist"
os.unlink('.hg/hgrc')
assert not os.path.exists('.hg/hgrc')
testui(debug=True, silent=True)
testui(user='abc', group='def', debug=True, silent=True)

print
print "# parse error"
f = open('.hg/hgrc', 'w')
f.write('foo')
f.close()

try:
    testui(user='abc', group='def', silent=True)
except error.ParseError as inst:
    print inst

try:
    testui(debug=True, silent=True)
except error.ParseError as inst:
    print inst