view tests/test-hgweb-auth.py @ 17616:9535a0dc41f2

store: implement fncache basic path encoding in C

(This is not yet enabled; it will be turned on in a followup patch.)

The path encoding performed by fncache is complex and (perhaps
surprisingly) slow enough to negatively affect the overall performance
of Mercurial.

For a short path (< 120 bytes), the Python code can be reduced to a fairly
tractable state machine that either determines that nothing needs to be
done in a single pass, or performs the encoding in a second pass.

For longer paths, we avoid the more complicated hashed encoding scheme
for now, and fall back to Python.

Raw performance: I measured in a repo containing 150,000 files in its tip
manifest, with a median path name length of 57 bytes, and 95th percentile
of 96 bytes.

In this repo, the Python code takes 3.1 seconds to encode all path
names, while the hybrid C-and-Python code (called from Python) takes
0.21 seconds, for a speedup of about 14.

Across several other large repositories, I've measured the speedup from
the C code at between 26x and 40x.

For path names above 120 bytes where we must fall back to Python for
hashed encoding, the speedup is about 1.7x.  Thus absolute performance
will depend strongly on the characteristics of a particular repository.

from mercurial import demandimport; demandimport.enable()
import urllib2
from mercurial import ui, util
from mercurial import url
from mercurial.error import Abort

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

origui = myui()

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

def dumpdict(dict):
    return '{' + ', '.join(['%s: %s' % (k, dict[k])
                            for k in sorted(dict.iterkeys())]) + '}'

def test(auth, urls=None):
    print 'CFG:', dumpdict(auth)
    prefixes = set()
    for k in auth:
        prefixes.add(k.split('.', 1)[0])
    for p in prefixes:
        for name in ('.username', '.password'):
            if (p + name) not in auth:
                auth[p + name] = p
    auth = dict((k, v) for k, v in auth.iteritems() if v is not None)

    ui = writeauth(auth)

    def _test(uri):
        print 'URI:', uri
        try:
            pm = url.passwordmgr(ui)
            u, authinfo = util.url(uri).authinfo()
            if authinfo is not None:
                pm.add_password(*authinfo)
            print '    ', pm.find_user_password('test', u)
        except Abort, e:
            print 'abort'

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


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

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

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

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

def testauthinfo(fullurl, authurl):
    print 'URIs:', fullurl, authurl
    pm = urllib2.HTTPPasswordMgrWithDefaultRealm()
    pm.add_password(*util.url(fullurl).authinfo()[1])
    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')