mercurial/httpconnection.py

hgweb: do not ignore [auth] if url has a username (issue2822)

The [auth] section was ignored when handling URLs like:

  http://[e-mail]/foo

Instead, we look in [auth] for an entry matching the URL and supplied user
name. Entries without username can match URL with a username. Prefix length
ties are resolved in favor of entries matching the username. With:

  foo.prefix = http://example.org
  foo.username = user
  foo.password = password
  bar.prefix = http://example.org/bar

and the input URL:

  http://[e-mail]/bar

the 'bar' entry will be selected because of prefix length, therefore prompting
for a password. This behaviour ensure that entries selection is consistent when
looking for credentials or for certificates, and that certificates can be
picked even if their entries do no define usernames while the URL does.
Additionally, entries without a username matched against a username are
returned as if they did have requested username set to avoid prompting again
for a username if the password is not set.

v2: reparse the URL in readauthforuri() to handle HTTP and HTTPS similarly.
v3: allow unset usernames to match URL usernames to pick certificates. Resolve
prefix length ties in favor of entries with usernames.

# httpconnection.py - urllib2 handler for new http support
#
# Copyright 2005, 2006, 2007, 2008 Matt Mackall <[e-mail]>
# Copyright 2006, 2007 Alexis S. L. Carvalho <[e-mail]>
# Copyright 2006 Vadim Gelfer <[e-mail]>
# Copyright 2011 Google, Inc.
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.
import logging
import socket
import urllib
import urllib2
import os

from mercurial import httpclient
from mercurial import sslutil
from mercurial import util
from mercurial.i18n import _

# moved here from url.py to avoid a cycle
class httpsendfile(object):
    """This is a wrapper around the objects returned by python's "open".

    Its purpose is to send file-like objects via HTTP and, to do so, it
    defines a __len__ attribute to feed the Content-Length header.
    """

    def __init__(self, ui, *args, **kwargs):
        # We can't just "self._data = open(*args, **kwargs)" here because there
        # is an "open" function defined in this module that shadows the global
        # one
        self.ui = ui
        self._data = open(*args, **kwargs)
        self.seek = self._data.seek
        self.close = self._data.close
        self.write = self._data.write
        self._len = os.fstat(self._data.fileno()).st_size
        self._pos = 0
        self._total = self._len / 1024 * 2

    def read(self, *args, **kwargs):
        try:
            ret = self._data.read(*args, **kwargs)
        except EOFError:
            self.ui.progress(_('sending'), None)
        self._pos += len(ret)
        # We pass double the max for total because we currently have
        # to send the bundle twice in the case of a server that
        # requires authentication. Since we can't know until we try
        # once whether authentication will be required, just lie to
        # the user and maybe the push succeeds suddenly at 50%.
        self.ui.progress(_('sending'), self._pos / 1024,
                         unit=_('kb'), total=self._total)
        return ret

    def __len__(self):
        return self._len

# moved here from url.py to avoid a cycle
def readauthforuri(ui, uri):
    # Read configuration
    config = dict()
    for key, val in ui.configitems('auth'):
        if '.' not in key:
            ui.warn(_("ignoring invalid [auth] key '%s'\n") % key)
            continue
        group, setting = key.rsplit('.', 1)
        gdict = config.setdefault(group, dict())
        if setting in ('username', 'cert', 'key'):
            val = util.expandpath(val)
        gdict[setting] = val

    # Find the best match
    uri = util.url(uri)
    user = uri.user
    uri.user = uri.password = None
    uri = str(uri)
    scheme, hostpath = uri.split('://', 1)
    bestuser = None
    bestlen = 0
    bestauth = None
    for group, auth in config.iteritems():
        if user and user != auth.get('username', user):
            # If a username was set in the URI, the entry username
            # must either match it or be unset
            continue
        prefix = auth.get('prefix')
        if not prefix:
            continue
        p = prefix.split('://', 1)
        if len(p) > 1:
            schemes, prefix = [p[0]], p[1]
        else:
            schemes = (auth.get('schemes') or 'https').split()
        if (prefix == '*' or hostpath.startswith(prefix)) and \
            (len(prefix) > bestlen or (len(prefix) == bestlen and \
                not bestuser and 'username' in auth)) \
             and scheme in schemes:
            bestlen = len(prefix)
            bestauth = group, auth
            bestuser = auth.get('username')
            if user and not bestuser:
                auth['username'] = user
    return bestauth

# Mercurial (at least until we can remove the old codepath) requires
# that the http response object be sufficiently file-like, so we
# provide a close() method here.
class HTTPResponse(httpclient.HTTPResponse):
    def close(self):
        pass

class HTTPConnection(httpclient.HTTPConnection):
    response_class = HTTPResponse
    def request(self, method, uri, body=None, headers={}):
        if isinstance(body, httpsendfile):
            body.seek(0)
        httpclient.HTTPConnection.request(self, method, uri, body=body,
                                          headers=headers)


_configuredlogging = False
LOGFMT = '%(levelname)s:%(name)s:%(lineno)d:%(message)s'
# Subclass BOTH of these because otherwise urllib2 "helpfully"
# reinserts them since it notices we don't include any subclasses of
# them.
class http2handler(urllib2.HTTPHandler, urllib2.HTTPSHandler):
    def __init__(self, ui, pwmgr):
        global _configuredlogging
        urllib2.AbstractHTTPHandler.__init__(self)
        self.ui = ui
        self.pwmgr = pwmgr
        self._connections = {}
        loglevel = ui.config('ui', 'http2debuglevel', default=None)
        if loglevel and not _configuredlogging:
            _configuredlogging = True
            logger = logging.getLogger('mercurial.httpclient')
            logger.setLevel(getattr(logging, loglevel.upper()))
            handler = logging.StreamHandler()
            handler.setFormatter(logging.Formatter(LOGFMT))
            logger.addHandler(handler)

    def close_all(self):
        """Close and remove all connection objects being kept for reuse."""
        for openconns in self._connections.values():
            for conn in openconns:
                conn.close()
        self._connections = {}

    # shamelessly borrowed from urllib2.AbstractHTTPHandler
    def do_open(self, http_class, req, use_ssl):
        """Return an addinfourl object for the request, using http_class.

        http_class must implement the HTTPConnection API from httplib.
        The addinfourl return value is a file-like object.  It also
        has methods and attributes including:
            - info(): return a mimetools.Message object for the headers
            - geturl(): return the original request URL
            - code: HTTP status code
        """
        # If using a proxy, the host returned by get_host() is
        # actually the proxy. On Python 2.6.1, the real destination
        # hostname is encoded in the URI in the urllib2 request
        # object. On Python 2.6.5, it's stored in the _tunnel_host
        # attribute which has no accessor.
        tunhost = getattr(req, '_tunnel_host', None)
        host = req.get_host()
        if tunhost:
            proxyhost = host
            host = tunhost
        elif req.has_proxy():
            proxyhost = req.get_host()
            host = req.get_selector().split('://', 1)[1].split('/', 1)[0]
        else:
            proxyhost = None

        if proxyhost:
            if ':' in proxyhost:
                # Note: this means we'll explode if we try and use an
                # IPv6 http proxy. This isn't a regression, so we
                # won't worry about it for now.
                proxyhost, proxyport = proxyhost.rsplit(':', 1)
            else:
                proxyport = 3128 # squid default
            proxy = (proxyhost, proxyport)
        else:
            proxy = None

        if not host:
            raise urllib2.URLError('no host given')

        connkey = use_ssl, host, proxy
        allconns = self._connections.get(connkey, [])
        conns = [c for c in allconns if not c.busy()]
        if conns:
            h = conns[0]
        else:
            if allconns:
                self.ui.debug('all connections for %s busy, making a new '
                              'one\n' % host)
            timeout = None
            if req.timeout is not socket._GLOBAL_DEFAULT_TIMEOUT:
                timeout = req.timeout
            h = http_class(host, timeout=timeout, proxy_hostport=proxy)
            self._connections.setdefault(connkey, []).append(h)

        headers = dict(req.headers)
        headers.update(req.unredirected_hdrs)
        headers = dict(
            (name.title(), val) for name, val in headers.items())
        try:
            path = req.get_selector()
            if '://' in path:
                path = path.split('://', 1)[1].split('/', 1)[1]
            if path[0] != '/':
                path = '/' + path
            h.request(req.get_method(), path, req.data, headers)
            r = h.getresponse()
        except socket.error, err: # XXX what error?
            raise urllib2.URLError(err)

        # Pick apart the HTTPResponse object to get the addinfourl
        # object initialized properly.
        r.recv = r.read

        resp = urllib.addinfourl(r, r.headers, req.get_full_url())
        resp.code = r.status
        resp.msg = r.reason
        return resp

    # httplib always uses the given host/port as the socket connect
    # target, and then allows full URIs in the request path, which it
    # then observes and treats as a signal to do proxying instead.
    def http_open(self, req):
        if req.get_full_url().startswith('https'):
            return self.https_open(req)
        return self.do_open(HTTPConnection, req, False)

    def https_open(self, req):
        res = readauthforuri(self.ui, req.get_full_url())
        if res:
            group, auth = res
            self.auth = auth
            self.ui.debug("using auth.%s.* for authentication\n" % group)
        else:
            self.auth = None
        return self.do_open(self._makesslconnection, req, True)

    def _makesslconnection(self, host, port=443, *args, **kwargs):
        keyfile = None
        certfile = None

        if args: # key_file
            keyfile = args.pop(0)
        if args: # cert_file
            certfile = args.pop(0)

        # if the user has specified different key/cert files in
        # hgrc, we prefer these
        if self.auth and 'key' in self.auth and 'cert' in self.auth:
            keyfile = self.auth['key']
            certfile = self.auth['cert']

        # let host port take precedence
        if ':' in host and '[' not in host or ']:' in host:
            host, port = host.rsplit(':', 1)
            port = int(port)
            if '[' in host:
                host = host[1:-1]

        if keyfile:
            kwargs['keyfile'] = keyfile
        if certfile:
            kwargs['certfile'] = certfile

        kwargs.update(sslutil.sslkwargs(self.ui, host))

        con = HTTPConnection(host, port, use_ssl=True,
                             ssl_validator=sslutil.validator(self.ui, host),
                             **kwargs)
        return con