tests/test-hgweb-auth.py

nodemap: introduce an option to use mmap to read the nodemap mapping

The performance and memory benefit is much greater if we don't have to copy all
the data in memory for each information. So we introduce an option (on by
default) to read the data using mmap.

This changeset is the last one definition the API for index support nodemap
data. (they have to be able to use the mmaping).

Below are some benchmark comparing the best we currently have in 5.3 with the
final step of this series (using the persistent nodemap implementation in
Rust). The benchmark run `hg perfindex` with various revset and the following
variants:

Before:

 * do not use the persistent nodemap
 * use the CPython implementation of the index for nodemap
 * use mmapping of the changelog index

After:

 * use the MixedIndex Rust code, with the NodeTree object for nodemap access
   (still in review)
 * use the persistent nodemap data from disk
 * access the persistent nodemap data through mmap
 * use mmapping of the changelog index

The persistent nodemap greatly speed up  most operation on very large
repositories. Some of the previously very fast lookup end up a bit slower because
the persistent nodemap has to be setup. However the absolute slowdown is very
small and won't matters in the big picture.

Here are some numbers (in seconds) for the reference copy of mozilla-try:

Revset            Before   After     abs-change speedup

-10000:           0.004622 0.005532   0.000910  ×   0.83
-10:              0.000050 0.000132   0.000082  ×   0.37
tip               0.000052 0.000085   0.000033  ×   0.61
0 + (-10000:)     0.028222 0.005337  -0.022885  ×   5.29
0                 0.023521 0.000084  -0.023437  × 280.01
(-10000:) + 0     0.235539 0.005308  -0.230231  ×  44.37
(-10:) + :9       0.232883 0.000180  -0.232703  ×1293.79
(-10000:) + (:99) 0.238735 0.005358  -0.233377  ×  44.55
:99 + (-10000:)   0.317942 0.005593  -0.312349  ×  56.84
:9 + (-10:)       0.313372 0.000179  -0.313193  ×1750.68
:9                0.316450 0.000143  -0.316307  ×2212.93


On smaller repositories, the cost of nodemap related operation is not as big, so
the win is much more modest. Yet it helps shaving a handful of millisecond here
and there.

Here are some numbers (in seconds) for the reference copy of mercurial:

Revset            Before   After     abs-change speedup
-10:              0.000065 0.000097   0.000032  × 0.67
tip               0.000063 0.000078   0.000015  × 0.80
0                 0.000561 0.000079  -0.000482  × 7.10
-10000:           0.004609 0.003648  -0.000961  × 1.26
0 + (-10000:)     0.005023 0.003715  -0.001307  × 1.35
(-10:) + :9       0.002187 0.000108  -0.002079  ×20.25
(-10000:) + 0     0.006252 0.003716  -0.002536  × 1.68
(-10000:) + (:99) 0.006367 0.003707  -0.002660  × 1.71
:9 + (-10:)       0.003846 0.000110  -0.003736  ×34.96
:9                0.003854 0.000099  -0.003755  ×38.92
:99 + (-10000:)   0.007644 0.003778  -0.003866  × 2.02

Differential Revision: https://phab.mercurial-scm.org/D7894

from __future__ import absolute_import, print_function

from mercurial import demandimport

demandimport.enable()
from mercurial import (
    error,
    pycompat,
    ui as uimod,
    url,
    util,
)
from mercurial.utils import stringutil

urlerr = util.urlerr
urlreq = util.urlreq


class myui(uimod.ui):
    def interactive(self):
        return False


origui = myui.load()


def writeauth(items):
    ui = origui.copy()
    for name, value in items.items():
        ui.setconfig(b'auth', name, value)
    return ui


def _stringifyauthinfo(ai):
    if ai is None:
        return ai
    realm, authuris, user, passwd = ai
    return (
        pycompat.strurl(realm),
        [pycompat.strurl(u) for u in authuris],
        pycompat.strurl(user),
        pycompat.strurl(passwd),
    )


def test(auth, urls=None):
    print('CFG:', pycompat.sysstr(stringutil.pprint(auth, bprefix=True)))
    prefixes = set()
    for k in auth:
        prefixes.add(k.split(b'.', 1)[0])
    for p in prefixes:
        for name in (b'.username', b'.password'):
            if (p + name) not in auth:
                auth[p + name] = p
    auth = dict((k, v) for k, v in auth.items() if v is not None)

    ui = writeauth(auth)

    def _test(uri):
        print('URI:', pycompat.strurl(uri))
        try:
            pm = url.passwordmgr(ui, urlreq.httppasswordmgrwithdefaultrealm())
            u, authinfo = util.url(uri).authinfo()
            if authinfo is not None:
                pm.add_password(*_stringifyauthinfo(authinfo))
            print(
                '    ',
                tuple(
                    pycompat.strurl(a)
                    for a in pm.find_user_password('test', pycompat.strurl(u))
                ),
            )
        except error.Abort:
            print('    ', 'abort')

    if not urls:
        urls = [
            b'http://example.org/foo',
            b'http://example.org/foo/bar',
            b'http://example.org/bar',
            b'https://example.org/foo',
            b'https://example.org/foo/bar',
            b'https://example.org/bar',
            b'https://[e-mail]/bar',
            b'https://[e-mail]/bar',
        ]
    for u in urls:
        _test(u)


print('\n*** Test in-uri schemes\n')
test({b'x.prefix': b'http://example.org'})
test({b'x.prefix': b'https://example.org'})
test({b'x.prefix': b'http://example.org', b'x.schemes': b'https'})
test({b'x.prefix': b'https://example.org', b'x.schemes': b'http'})

print('\n*** Test separately configured schemes\n')
test({b'x.prefix': b'example.org', b'x.schemes': b'http'})
test({b'x.prefix': b'example.org', b'x.schemes': b'https'})
test({b'x.prefix': b'example.org', b'x.schemes': b'http https'})

print('\n*** Test prefix matching\n')
test(
    {
        b'x.prefix': b'http://example.org/foo',
        b'y.prefix': b'http://example.org/bar',
    }
)
test(
    {
        b'x.prefix': b'http://example.org/foo',
        b'y.prefix': b'http://example.org/foo/bar',
    }
)
test({b'x.prefix': b'*', b'y.prefix': b'https://example.org/bar'})

print('\n*** Test user matching\n')
test(
    {
        b'x.prefix': b'http://example.org/foo',
        b'x.username': None,
        b'x.password': b'xpassword',
    },
    urls=[b'http://[e-mail]/foo'],
)
test(
    {
        b'x.prefix': b'http://example.org/foo',
        b'x.username': None,
        b'x.password': b'xpassword',
        b'y.prefix': b'http://example.org/foo',
        b'y.username': b'y',
        b'y.password': b'ypassword',
    },
    urls=[b'http://[e-mail]/foo'],
)
test(
    {
        b'x.prefix': b'http://example.org/foo/bar',
        b'x.username': None,
        b'x.password': b'xpassword',
        b'y.prefix': b'http://example.org/foo',
        b'y.username': b'y',
        b'y.password': b'ypassword',
    },
    urls=[b'http://[e-mail]/foo/bar'],
)

print('\n*** Test user matching with name in prefix\n')

# prefix, username and URL have the same user
test(
    {
        b'x.prefix': b'https://example.org/foo',
        b'x.username': None,
        b'x.password': b'xpassword',
        b'y.prefix': b'http://[e-mail]/foo',
        b'y.username': b'y',
        b'y.password': b'ypassword',
    },
    urls=[b'http://[e-mail]/foo'],
)
# Prefix has a different user from username and URL
test(
    {
        b'y.prefix': b'http://[e-mail]/foo',
        b'y.username': b'y',
        b'y.password': b'ypassword',
    },
    urls=[b'http://[e-mail]/foo'],
)
# Prefix has a different user from URL; no username
test(
    {b'y.prefix': b'http://[e-mail]/foo', b'y.password': b'ypassword'},
    urls=[b'http://[e-mail]/foo'],
)
# Prefix and URL have same user, but doesn't match username
test(
    {
        b'y.prefix': b'http://[e-mail]/foo',
        b'y.username': b'z',
        b'y.password': b'ypassword',
    },
    urls=[b'http://[e-mail]/foo'],
)
# Prefix and URL have the same user; no username
test(
    {b'y.prefix': b'http://[e-mail]/foo', b'y.password': b'ypassword'},
    urls=[b'http://[e-mail]/foo'],
)
# Prefix user, but no URL user or username
test(
    {b'y.prefix': b'http://[e-mail]/foo', b'y.password': b'ypassword'},
    urls=[b'http://example.org/foo'],
)


def testauthinfo(fullurl, authurl):
    print('URIs:', fullurl, authurl)
    pm = urlreq.httppasswordmgrwithdefaultrealm()
    ai = _stringifyauthinfo(util.url(pycompat.bytesurl(fullurl)).authinfo()[1])
    pm.add_password(*ai)
    print(pm.find_user_password('test', authurl))


print('\n*** Test urllib2 and util.url\n')
testauthinfo('http://[e-mail]:8080/foo', 'http://example.com:8080/foo')