hgweb: support constructing URLs from an alternate base URL

The web.baseurl config option allows server operators to define a
custom URL for hosted content.

The way it works today is that hgwebdir parses this config
option into URL components then updates the appropriate
WSGI environment variables so the request "lies" about its
details. For example, SERVER_NAME is updated to reflect the
alternate base URL's hostname.

The WSGI environment should not be modified because WSGI
applications may want to know the original request details (for
debugging, etc).

This commit teaches our request parser about the existence of
an alternate base URL. If defined, the advertised URL and other
self-reflected paths will take the alternate base URL into account.

The hgweb WSGI application didn't use web.baseurl. But hgwebdir
did. We update hgwebdir to alter the environment parsing
accordingly. The old code around environment manipulation
has been removed.

With this change, parserequestfromenv() has grown to a bit
unwieldy. Now that practically everyone is using it, it is
obvious that there is some unused features that can be trimmed.
So look for this in follow-up commits.

Differential Revision: https://phab.mercurial-scm.org/D2822

mercurial/hgweb/hgwebdir_mod.py

@@ -1,566 +1,529
 # hgweb/hgwebdir_mod.py - Web interface for a directory of repositories.
 #
 # Copyright 21 May 2005 - (c) 2005 Jake Edge <[e-mail]>
 # Copyright 2005, 2006 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from __future__ import absolute_import
 
 import os
 import re
 import time
 
 from ..i18n import _
 
 from .common import (
     ErrorResponse,
     HTTP_NOT_FOUND,
     HTTP_OK,
     HTTP_SERVER_ERROR,
     cspvalues,
     get_contact,
     get_mtime,
     ismember,
     paritygen,
     staticfile,
 )
 
 from .. import (
     configitems,
     encoding,
     error,
     hg,
     profiling,
-    pycompat,
     scmutil,
     templater,
     ui as uimod,
     util,
 )
 
 from . import (
     hgweb_mod,
     request as requestmod,
     webutil,
     wsgicgi,
 )
 from ..utils import dateutil
 
 def cleannames(items):
     return [(util.pconvert(name).strip('/'), path) for name, path in items]
 
 def findrepos(paths):
     repos = []
     for prefix, root in cleannames(paths):
         roothead, roottail = os.path.split(root)
         # "foo = /bar/*" or "foo = /bar/**" lets every repo /bar/N in or below
         # /bar/ be served as as foo/N .
         # '*' will not search inside dirs with .hg (except .hg/patches),
         # '**' will search inside dirs with .hg (and thus also find subrepos).
         try:
             recurse = {'*': False, '**': True}[roottail]
         except KeyError:
             repos.append((prefix, root))
             continue
         roothead = os.path.normpath(os.path.abspath(roothead))
         paths = scmutil.walkrepos(roothead, followsym=True, recurse=recurse)
         repos.extend(urlrepos(prefix, roothead, paths))
     return repos
 
 def urlrepos(prefix, roothead, paths):
     """yield url paths and filesystem paths from a list of repo paths
 
     >>> conv = lambda seq: [(v, util.pconvert(p)) for v,p in seq]
     >>> conv(urlrepos(b'hg', b'/opt', [b'/opt/r', b'/opt/r/r', b'/opt']))
     [('hg/r', '/opt/r'), ('hg/r/r', '/opt/r/r'), ('hg', '/opt')]
     >>> conv(urlrepos(b'', b'/opt', [b'/opt/r', b'/opt/r/r', b'/opt']))
     [('r', '/opt/r'), ('r/r', '/opt/r/r'), ('', '/opt')]
     """
     for path in paths:
         path = os.path.normpath(path)
         yield (prefix + '/' +
                util.pconvert(path[len(roothead):]).lstrip('/')).strip('/'), path
 
-def geturlcgivars(baseurl, port):
-    """
-    Extract CGI variables from baseurl
-
-    >>> geturlcgivars(b"http://host.org/base", b"80")
-    ('host.org', '80', '/base')
-    >>> geturlcgivars(b"http://host.org:8000/base", b"80")
-    ('host.org', '8000', '/base')
-    >>> geturlcgivars(b'/base', 8000)
-    ('', '8000', '/base')
-    >>> geturlcgivars(b"base", b'8000')
-    ('', '8000', '/base')
-    >>> geturlcgivars(b"http://host", b'8000')
-    ('host', '8000', '/')
-    >>> geturlcgivars(b"http://host/", b'8000')
-    ('host', '8000', '/')
-    """
-    u = util.url(baseurl)
-    name = u.host or ''
-    if u.port:
-        port = u.port
-    path = u.path or ""
-    if not path.startswith('/'):
-        path = '/' + path
-
-    return name, pycompat.bytestr(port), path
-
 def readallowed(ui, req):
     """Check allow_read and deny_read config options of a repo's ui object
     to determine user permissions.  By default, with neither option set (or
     both empty), allow all users to read the repo.  There are two ways a
     user can be denied read access:  (1) deny_read is not empty, and the
     user is unauthenticated or deny_read contains user (or *), and (2)
     allow_read is not empty and the user is not in allow_read.  Return True
     if user is allowed to read the repo, else return False."""
 
     user = req.remoteuser
 
     deny_read = ui.configlist('web', 'deny_read', untrusted=True)
     if deny_read and (not user or ismember(ui, user, deny_read)):
         return False
 
     allow_read = ui.configlist('web', 'allow_read', untrusted=True)
     # by default, allow reading if no allow_read option has been set
     if not allow_read or ismember(ui, user, allow_read):
         return True
 
     return False
 
 def archivelist(ui, nodeid, url):
     allowed = ui.configlist('web', 'allow_archive', untrusted=True)
     archives = []
 
     for typ, spec in hgweb_mod.archivespecs.iteritems():
         if typ in allowed or ui.configbool('web', 'allow' + typ,
                                            untrusted=True):
             archives.append({
                 'type': typ,
                 'extension': spec[2],
                 'node': nodeid,
                 'url': url,
             })
 
     return archives
 
 def rawindexentries(ui, repos, wsgireq, req, subdir=''):
     descend = ui.configbool('web', 'descend')
     collapse = ui.configbool('web', 'collapse')
     seenrepos = set()
     seendirs = set()
     for name, path in repos:
 
         if not name.startswith(subdir):
             continue
         name = name[len(subdir):]
         directory = False
 
         if '/' in name:
             if not descend:
                 continue
 
             nameparts = name.split('/')
             rootname = nameparts[0]
 
             if not collapse:
                 pass
             elif rootname in seendirs:
                 continue
             elif rootname in seenrepos:
                 pass
             else:
                 directory = True
                 name = rootname
 
                 # redefine the path to refer to the directory
                 discarded = '/'.join(nameparts[1:])
 
                 # remove name parts plus accompanying slash
                 path = path[:-len(discarded) - 1]
 
                 try:
                     r = hg.repository(ui, path)
                     directory = False
                 except (IOError, error.RepoError):
                     pass
 
         parts = [name]
         parts.insert(0, '/' + subdir.rstrip('/'))
         if wsgireq.env['SCRIPT_NAME']:
             parts.insert(0, wsgireq.env['SCRIPT_NAME'])
         url = re.sub(r'/+', '/', '/'.join(parts) + '/')
 
         # show either a directory entry or a repository
         if directory:
             # get the directory's time information
             try:
                 d = (get_mtime(path), dateutil.makedate()[1])
             except OSError:
                 continue
 
             # add '/' to the name to make it obvious that
             # the entry is a directory, not a regular repository
             row = {'contact': "",
                    'contact_sort': "",
                    'name': name + '/',
                    'name_sort': name,
                    'url': url,
                    'description': "",
                    'description_sort': "",
                    'lastchange': d,
                    'lastchange_sort': d[1] - d[0],
                    'archives': [],
                    'isdirectory': True,
                    'labels': [],
                    }
 
             seendirs.add(name)
             yield row
             continue
 
         u = ui.copy()
         try:
             u.readconfig(os.path.join(path, '.hg', 'hgrc'))
         except Exception as e:
             u.warn(_('error reading %s/.hg/hgrc: %s\n') % (path, e))
             continue
 
         def get(section, name, default=uimod._unset):
             return u.config(section, name, default, untrusted=True)
 
         if u.configbool("web", "hidden", untrusted=True):
             continue
 
         if not readallowed(u, req):
             continue
 
         # update time with local timezone
         try:
             r = hg.repository(ui, path)
         except IOError:
             u.warn(_('error accessing repository at %s\n') % path)
             continue
         except error.RepoError:
             u.warn(_('error accessing repository at %s\n') % path)
             continue
         try:
             d = (get_mtime(r.spath), dateutil.makedate()[1])
         except OSError:
             continue
 
         contact = get_contact(get)
         description = get("web", "description")
         seenrepos.add(name)
         name = get("web", "name", name)
         row = {'contact': contact or "unknown",
                'contact_sort': contact.upper() or "unknown",
                'name': name,
                'name_sort': name,
                'url': url,
                'description': description or "unknown",
                'description_sort': description.upper() or "unknown",
                'lastchange': d,
                'lastchange_sort': d[1] - d[0],
                'archives': archivelist(u, "tip", url),
                'isdirectory': None,
                'labels': u.configlist('web', 'labels', untrusted=True),
                }
 
         yield row
 
 def indexentries(ui, repos, wsgireq, req, stripecount, sortcolumn='',
                  descending=False, subdir=''):
 
     rows = rawindexentries(ui, repos, wsgireq, req, subdir=subdir)
 
     sortdefault = None, False
 
     if sortcolumn and sortdefault != (sortcolumn, descending):
         sortkey = '%s_sort' % sortcolumn
         rows = sorted(rows, key=lambda x: x[sortkey],
                       reverse=descending)
 
     for row, parity in zip(rows, paritygen(stripecount)):
         row['parity'] = parity
         yield row
 
 class hgwebdir(object):
     """HTTP server for multiple repositories.
 
     Given a configuration, different repositories will be served depending
     on the request path.
 
     Instances are typically used as WSGI applications.
     """
     def __init__(self, conf, baseui=None):
         self.conf = conf
         self.baseui = baseui
         self.ui = None
         self.lastrefresh = 0
         self.motd = None
         self.refresh()
 
     def refresh(self):
         if self.ui:
             refreshinterval = self.ui.configint('web', 'refreshinterval')
         else:
             item = configitems.coreitems['web']['refreshinterval']
             refreshinterval = item.default
 
         # refreshinterval <= 0 means to always refresh.
         if (refreshinterval > 0 and
             self.lastrefresh + refreshinterval > time.time()):
             return
 
         if self.baseui:
             u = self.baseui.copy()
         else:
             u = uimod.ui.load()
             u.setconfig('ui', 'report_untrusted', 'off', 'hgwebdir')
             u.setconfig('ui', 'nontty', 'true', 'hgwebdir')
             # displaying bundling progress bar while serving feels wrong and may
             # break some wsgi implementations.
             u.setconfig('progress', 'disable', 'true', 'hgweb')
 
         if not isinstance(self.conf, (dict, list, tuple)):
             map = {'paths': 'hgweb-paths'}
             if not os.path.exists(self.conf):
                 raise error.Abort(_('config file %s not found!') % self.conf)
             u.readconfig(self.conf, remap=map, trust=True)
             paths = []
             for name, ignored in u.configitems('hgweb-paths'):
                 for path in u.configlist('hgweb-paths', name):
                     paths.append((name, path))
         elif isinstance(self.conf, (list, tuple)):
             paths = self.conf
         elif isinstance(self.conf, dict):
             paths = self.conf.items()
 
         repos = findrepos(paths)
         for prefix, root in u.configitems('collections'):
             prefix = util.pconvert(prefix)
             for path in scmutil.walkrepos(root, followsym=True):
                 repo = os.path.normpath(path)
                 name = util.pconvert(repo)
                 if name.startswith(prefix):
                     name = name[len(prefix):]
                 repos.append((name.lstrip('/'), repo))
 
         self.repos = repos
         self.ui = u
         encoding.encoding = self.ui.config('web', 'encoding')
         self.style = self.ui.config('web', 'style')
         self.templatepath = self.ui.config('web', 'templates', untrusted=False)
         self.stripecount = self.ui.config('web', 'stripes')
         if self.stripecount:
             self.stripecount = int(self.stripecount)
-        self._baseurl = self.ui.config('web', 'baseurl')
         prefix = self.ui.config('web', 'prefix')
         if prefix.startswith('/'):
             prefix = prefix[1:]
         if prefix.endswith('/'):
             prefix = prefix[:-1]
         self.prefix = prefix
         self.lastrefresh = time.time()
 
     def run(self):
         if not encoding.environ.get('GATEWAY_INTERFACE',
                                     '').startswith("CGI/1."):
             raise RuntimeError("This function is only intended to be "
                                "called while running as a CGI script.")
         wsgicgi.launch(self)
 
     def __call__(self, env, respond):
-        wsgireq = requestmod.wsgirequest(env, respond)
+        baseurl = self.ui.config('web', 'baseurl')
+        wsgireq = requestmod.wsgirequest(env, respond, altbaseurl=baseurl)
         return self.run_wsgi(wsgireq)
 
     def run_wsgi(self, wsgireq):
         profile = self.ui.configbool('profiling', 'enabled')
         with profiling.profile(self.ui, enabled=profile):
             for r in self._runwsgi(wsgireq):
                 yield r
 
     def _runwsgi(self, wsgireq):
         req = wsgireq.req
         res = wsgireq.res
 
         try:
             self.refresh()
 
             csp, nonce = cspvalues(self.ui)
             if csp:
                 res.headers['Content-Security-Policy'] = csp
                 wsgireq.headers.append(('Content-Security-Policy', csp))
 
             virtual = wsgireq.env.get("PATH_INFO", "").strip('/')
             tmpl = self.templater(wsgireq, nonce)
             ctype = tmpl('mimetype', encoding=encoding.encoding)
             ctype = templater.stringify(ctype)
 
             # Global defaults. These can be overridden by any handler.
             res.status = '200 Script output follows'
             res.headers['Content-Type'] = ctype
 
             # a static file
             if virtual.startswith('static/') or 'static' in req.qsparams:
                 if virtual.startswith('static/'):
                     fname = virtual[7:]
                 else:
                     fname = req.qsparams['static']
                 static = self.ui.config("web", "static", None,
                                         untrusted=False)
                 if not static:
                     tp = self.templatepath or templater.templatepaths()
                     if isinstance(tp, str):
                         tp = [tp]
                     static = [os.path.join(p, 'static') for p in tp]
 
                 staticfile(static, fname, res)
                 return res.sendresponse()
 
             # top-level index
 
             repos = dict(self.repos)
 
             if (not virtual or virtual == 'index') and virtual not in repos:
                 wsgireq.respond(HTTP_OK, ctype)
                 return self.makeindex(wsgireq, tmpl)
 
             # nested indexes and hgwebs
 
             if virtual.endswith('/index') and virtual not in repos:
                 subdir = virtual[:-len('index')]
                 if any(r.startswith(subdir) for r in repos):
                     wsgireq.respond(HTTP_OK, ctype)
                     return self.makeindex(wsgireq, tmpl, subdir)
 
             def _virtualdirs():
                 # Check the full virtual path, each parent, and the root ('')
                 if virtual != '':
                     yield virtual
 
                     for p in util.finddirs(virtual):
                         yield p
 
                 yield ''
 
             for virtualrepo in _virtualdirs():
                 real = repos.get(virtualrepo)
                 if real:
                     # Re-parse the WSGI environment to take into account our
                     # repository path component.
                     wsgireq.req = requestmod.parserequestfromenv(
-                        wsgireq.env, wsgireq.req.bodyfh, reponame=virtualrepo)
+                        wsgireq.env, wsgireq.req.bodyfh, reponame=virtualrepo,
+                        altbaseurl=self.ui.config('web', 'baseurl'))
                     try:
                         # ensure caller gets private copy of ui
                         repo = hg.repository(self.ui.copy(), real)
                         return hgweb_mod.hgweb(repo).run_wsgi(wsgireq)
                     except IOError as inst:
                         msg = encoding.strtolocal(inst.strerror)
                         raise ErrorResponse(HTTP_SERVER_ERROR, msg)
                     except error.RepoError as inst:
                         raise ErrorResponse(HTTP_SERVER_ERROR, bytes(inst))
 
             # browse subdirectories
             subdir = virtual + '/'
             if [r for r in repos if r.startswith(subdir)]:
                 wsgireq.respond(HTTP_OK, ctype)
                 return self.makeindex(wsgireq, tmpl, subdir)
 
             # prefixes not found
             wsgireq.respond(HTTP_NOT_FOUND, ctype)
             return tmpl("notfound", repo=virtual)
 
         except ErrorResponse as err:
             wsgireq.respond(err, ctype)
             return tmpl('error', error=err.message or '')
         finally:
             tmpl = None
 
     def makeindex(self, wsgireq, tmpl, subdir=""):
         req = wsgireq.req
 
         self.refresh()
         sortable = ["name", "description", "contact", "lastchange"]
         sortcolumn, descending = None, False
         if 'sort' in req.qsparams:
             sortcolumn = req.qsparams['sort']
             descending = sortcolumn.startswith('-')
             if descending:
                 sortcolumn = sortcolumn[1:]
             if sortcolumn not in sortable:
                 sortcolumn = ""
 
         sort = [("sort_%s" % column,
                  "%s%s" % ((not descending and column == sortcolumn)
                             and "-" or "", column))
                 for column in sortable]
 
         self.refresh()
-        self.updatereqenv(wsgireq.env)
 
         entries = indexentries(self.ui, self.repos, wsgireq, req,
                                self.stripecount, sortcolumn=sortcolumn,
                                descending=descending, subdir=subdir)
 
         return tmpl("index", entries=entries, subdir=subdir,
                     pathdef=hgweb_mod.makebreadcrumb('/' + subdir, self.prefix),
                     sortcolumn=sortcolumn, descending=descending,
                     **dict(sort))
 
     def templater(self, wsgireq, nonce):
 
         def motd(**map):
             if self.motd is not None:
                 yield self.motd
             else:
                 yield config('web', 'motd')
 
         def config(section, name, default=uimod._unset, untrusted=True):
             return self.ui.config(section, name, default, untrusted)
 
-        self.updatereqenv(wsgireq.env)
-
         url = wsgireq.env.get('SCRIPT_NAME', '')
         if not url.endswith('/'):
             url += '/'
 
         vars = {}
         styles, (style, mapfile) = hgweb_mod.getstyle(wsgireq.req, config,
                                                       self.templatepath)
         if style == styles[0]:
             vars['style'] = style
 
         sessionvars = webutil.sessionvars(vars, r'?')
         logourl = config('web', 'logourl')
         logoimg = config('web', 'logoimg')
         staticurl = (config('web', 'staticurl')
                      or wsgireq.req.apppath + '/static/')
         if not staticurl.endswith('/'):
             staticurl += '/'
 
         defaults = {
             "encoding": encoding.encoding,
             "motd": motd,
             "url": url,
             "logourl": logourl,
             "logoimg": logoimg,
             "staticurl": staticurl,
             "sessionvars": sessionvars,
             "style": style,
             "nonce": nonce,
         }
         tmpl = templater.templater.frommapfile(mapfile, defaults=defaults)
         return tmpl
-
-    def updatereqenv(self, env):
-        if self._baseurl is not None:
-            name, port, path = geturlcgivars(self._baseurl, env['SERVER_PORT'])
-            env['SERVER_NAME'] = name
-            env['SERVER_PORT'] = port
-            env['SCRIPT_NAME'] = path

mercurial/hgweb/request.py

@@ -1,669 +1,713
 # hgweb/request.py - An http request from either CGI or the standalone server.
 #
 # Copyright 21 May 2005 - (c) 2005 Jake Edge <[e-mail]>
 # Copyright 2005, 2006 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from __future__ import absolute_import
 
 import errno
 import socket
 import wsgiref.headers as wsgiheaders
 #import wsgiref.validate
 
 from .common import (
     ErrorResponse,
     statusmessage,
 )
 
 from ..thirdparty import (
     attr,
 )
 from .. import (
     error,
     pycompat,
     util,
 )
 
 class multidict(object):
     """A dict like object that can store multiple values for a key.
 
     Used to store parsed request parameters.
 
     This is inspired by WebOb's class of the same name.
     """
     def __init__(self):
         # Stores (key, value) 2-tuples. This isn't the most efficient. But we
         # don't rely on parameters that much, so it shouldn't be a perf issue.
         # we can always add dict for fast lookups.
         self._items = []
 
     def __getitem__(self, key):
         """Returns the last set value for a key."""
         for k, v in reversed(self._items):
             if k == key:
                 return v
 
         raise KeyError(key)
 
     def __setitem__(self, key, value):
         """Replace a values for a key with a new value."""
         try:
             del self[key]
         except KeyError:
             pass
 
         self._items.append((key, value))
 
     def __delitem__(self, key):
         """Delete all values for a key."""
         oldlen = len(self._items)
 
         self._items[:] = [(k, v) for k, v in self._items if k != key]
 
         if oldlen == len(self._items):
             raise KeyError(key)
 
     def __contains__(self, key):
         return any(k == key for k, v in self._items)
 
     def __len__(self):
         return len(self._items)
 
     def get(self, key, default=None):
         try:
             return self.__getitem__(key)
         except KeyError:
             return default
 
     def add(self, key, value):
         """Add a new value for a key. Does not replace existing values."""
         self._items.append((key, value))
 
     def getall(self, key):
         """Obtains all values for a key."""
         return [v for k, v in self._items if k == key]
 
     def getone(self, key):
         """Obtain a single value for a key.
 
         Raises KeyError if key not defined or it has multiple values set.
         """
         vals = self.getall(key)
 
         if not vals:
             raise KeyError(key)
 
         if len(vals) > 1:
             raise KeyError('multiple values for %r' % key)
 
         return vals[0]
 
     def asdictoflists(self):
         d = {}
         for k, v in self._items:
             if k in d:
                 d[k].append(v)
             else:
                 d[k] = [v]
 
         return d
 
 @attr.s(frozen=True)
 class parsedrequest(object):
     """Represents a parsed WSGI request.
 
     Contains both parsed parameters as well as a handle on the input stream.
     """
 
     # Request method.
     method = attr.ib()
     # Full URL for this request.
     url = attr.ib()
     # URL without any path components. Just <proto>://<host><port>.
     baseurl = attr.ib()
     # Advertised URL. Like ``url`` and ``baseurl`` but uses SERVER_NAME instead
     # of HTTP: Host header for hostname. This is likely what clients used.
     advertisedurl = attr.ib()
     advertisedbaseurl = attr.ib()
     # URL scheme (part before ``://``). e.g. ``http`` or ``https``.
     urlscheme = attr.ib()
     # Value of REMOTE_USER, if set, or None.
     remoteuser = attr.ib()
     # Value of REMOTE_HOST, if set, or None.
     remotehost = attr.ib()
     # Relative WSGI application path. If defined, will begin with a
     # ``/``.
     apppath = attr.ib()
     # List of path parts to be used for dispatch.
     dispatchparts = attr.ib()
     # URL path component (no query string) used for dispatch. Can be
     # ``None`` to signal no path component given to the request, an
     # empty string to signal a request to the application's root URL,
     # or a string not beginning with ``/`` containing the requested
     # path under the application.
     dispatchpath = attr.ib()
     # The name of the repository being accessed.
     reponame = attr.ib()
     # Raw query string (part after "?" in URL).
     querystring = attr.ib()
     # multidict of query string parameters.
     qsparams = attr.ib()
     # wsgiref.headers.Headers instance. Operates like a dict with case
     # insensitive keys.
     headers = attr.ib()
     # Request body input stream.
     bodyfh = attr.ib()
 
-def parserequestfromenv(env, bodyfh, reponame=None):
+def parserequestfromenv(env, bodyfh, reponame=None, altbaseurl=None):
     """Parse URL components from environment variables.
 
     WSGI defines request attributes via environment variables. This function
     parses the environment variables into a data structure.
 
     If ``reponame`` is defined, the leading path components matching that
     string are effectively shifted from ``PATH_INFO`` to ``SCRIPT_NAME``.
     This simulates the world view of a WSGI application that processes
     requests from the base URL of a repo.
+
+    If ``altbaseurl`` (typically comes from ``web.baseurl`` config option)
+    is defined, it is used - instead of the WSGI environment variables - for
+    constructing URL components up to and including the WSGI application path.
+    For example, if the current WSGI application is at ``/repo`` and a request
+    is made to ``/rev/@`` with this argument set to
+    ``http://myserver:9000/prefix``, the URL and path components will resolve as
+    if the request were to ``http://myserver:9000/prefix/rev/@``. In other
+    words, ``wsgi.url_scheme``, ``SERVER_NAME``, ``SERVER_PORT``, and
+    ``SCRIPT_NAME`` are all effectively replaced by components from this URL.
     """
-    # PEP-0333 defines the WSGI spec and is a useful reference for this code.
+    # PEP 3333 defines the WSGI spec and is a useful reference for this code.
 
     # We first validate that the incoming object conforms with the WSGI spec.
     # We only want to be dealing with spec-conforming WSGI implementations.
     # TODO enable this once we fix internal violations.
     #wsgiref.validate.check_environ(env)
 
     # PEP-0333 states that environment keys and values are native strings
     # (bytes on Python 2 and str on Python 3). The code points for the Unicode
     # strings on Python 3 must be between \00000-\000FF. We deal with bytes
     # in Mercurial, so mass convert string keys and values to bytes.
     if pycompat.ispy3:
         env = {k.encode('latin-1'): v for k, v in env.iteritems()}
         env = {k: v.encode('latin-1') if isinstance(v, str) else v
                for k, v in env.iteritems()}
 
+    if altbaseurl:
+        altbaseurl = util.url(altbaseurl)
+
     # https://www.python.org/dev/peps/pep-0333/#environ-variables defines
     # the environment variables.
     # https://www.python.org/dev/peps/pep-0333/#url-reconstruction defines
     # how URLs are reconstructed.
     fullurl = env['wsgi.url_scheme'] + '://'
-    advertisedfullurl = fullurl
+
+    if altbaseurl and altbaseurl.scheme:
+        advertisedfullurl = altbaseurl.scheme + '://'
+    else:
+        advertisedfullurl = fullurl
 
-    def addport(s):
-        if env['wsgi.url_scheme'] == 'https':
-            if env['SERVER_PORT'] != '443':
-                s += ':' + env['SERVER_PORT']
+    def addport(s, port):
+        if s.startswith('https://'):
+            if port != '443':
+                s += ':' + port
         else:
-            if env['SERVER_PORT'] != '80':
-                s += ':' + env['SERVER_PORT']
+            if port != '80':
+                s += ':' + port
 
         return s
 
     if env.get('HTTP_HOST'):
         fullurl += env['HTTP_HOST']
     else:
         fullurl += env['SERVER_NAME']
-        fullurl = addport(fullurl)
+        fullurl = addport(fullurl, env['SERVER_PORT'])
+
+    if altbaseurl and altbaseurl.host:
+        advertisedfullurl += altbaseurl.host
 
-    advertisedfullurl += env['SERVER_NAME']
-    advertisedfullurl = addport(advertisedfullurl)
+        if altbaseurl.port:
+            port = altbaseurl.port
+        elif altbaseurl.scheme == 'http' and not altbaseurl.port:
+            port = '80'
+        elif altbaseurl.scheme == 'https' and not altbaseurl.port:
+            port = '443'
+        else:
+            port = env['SERVER_PORT']
+
+        advertisedfullurl = addport(advertisedfullurl, port)
+    else:
+        advertisedfullurl += env['SERVER_NAME']
+        advertisedfullurl = addport(advertisedfullurl, env['SERVER_PORT'])
 
     baseurl = fullurl
     advertisedbaseurl = advertisedfullurl
 
     fullurl += util.urlreq.quote(env.get('SCRIPT_NAME', ''))
-    advertisedfullurl += util.urlreq.quote(env.get('SCRIPT_NAME', ''))
     fullurl += util.urlreq.quote(env.get('PATH_INFO', ''))
+
+    if altbaseurl:
+        path = altbaseurl.path or ''
+        if path and not path.startswith('/'):
+            path = '/' + path
+        advertisedfullurl += util.urlreq.quote(path)
+    else:
+        advertisedfullurl += util.urlreq.quote(env.get('SCRIPT_NAME', ''))
+
     advertisedfullurl += util.urlreq.quote(env.get('PATH_INFO', ''))
 
     if env.get('QUERY_STRING'):
         fullurl += '?' + env['QUERY_STRING']
         advertisedfullurl += '?' + env['QUERY_STRING']
 
     # If ``reponame`` is defined, that must be a prefix on PATH_INFO
     # that represents the repository being dispatched to. When computing
     # the dispatch info, we ignore these leading path components.
 
-    apppath = env.get('SCRIPT_NAME', '')
+    if altbaseurl:
+        apppath = altbaseurl.path or ''
+        if apppath and not apppath.startswith('/'):
+            apppath = '/' + apppath
+    else:
+        apppath = env.get('SCRIPT_NAME', '')
 
     if reponame:
         repoprefix = '/' + reponame.strip('/')
 
         if not env.get('PATH_INFO'):
             raise error.ProgrammingError('reponame requires PATH_INFO')
 
         if not env['PATH_INFO'].startswith(repoprefix):
             raise error.ProgrammingError('PATH_INFO does not begin with repo '
                                          'name: %s (%s)' % (env['PATH_INFO'],
                                                             reponame))
 
         dispatchpath = env['PATH_INFO'][len(repoprefix):]
 
         if dispatchpath and not dispatchpath.startswith('/'):
             raise error.ProgrammingError('reponame prefix of PATH_INFO does '
                                          'not end at path delimiter: %s (%s)' %
                                          (env['PATH_INFO'], reponame))
 
         apppath = apppath.rstrip('/') + repoprefix
         dispatchparts = dispatchpath.strip('/').split('/')
         dispatchpath = '/'.join(dispatchparts)
 
     elif 'PATH_INFO' in env:
         if env['PATH_INFO'].strip('/'):
             dispatchparts = env['PATH_INFO'].strip('/').split('/')
             dispatchpath = '/'.join(dispatchparts)
         else:
             dispatchparts = []
             dispatchpath = ''
     else:
         dispatchparts = []
         dispatchpath = None
 
     querystring = env.get('QUERY_STRING', '')
 
     # We store as a list so we have ordering information. We also store as
     # a dict to facilitate fast lookup.
     qsparams = multidict()
     for k, v in util.urlreq.parseqsl(querystring, keep_blank_values=True):
         qsparams.add(k, v)
 
     # HTTP_* keys contain HTTP request headers. The Headers structure should
     # perform case normalization for us. We just rewrite underscore to dash
     # so keys match what likely went over the wire.
     headers = []
     for k, v in env.iteritems():
         if k.startswith('HTTP_'):
             headers.append((k[len('HTTP_'):].replace('_', '-'), v))
 
     headers = wsgiheaders.Headers(headers)
 
     # This is kind of a lie because the HTTP header wasn't explicitly
     # sent. But for all intents and purposes it should be OK to lie about
     # this, since a consumer will either either value to determine how many
     # bytes are available to read.
     if 'CONTENT_LENGTH' in env and 'HTTP_CONTENT_LENGTH' not in env:
         headers['Content-Length'] = env['CONTENT_LENGTH']
 
     # TODO do this once we remove wsgirequest.inp, otherwise we could have
     # multiple readers from the underlying input stream.
     #bodyfh = env['wsgi.input']
     #if 'Content-Length' in headers:
     #    bodyfh = util.cappedreader(bodyfh, int(headers['Content-Length']))
 
     return parsedrequest(method=env['REQUEST_METHOD'],
                          url=fullurl, baseurl=baseurl,
                          advertisedurl=advertisedfullurl,
                          advertisedbaseurl=advertisedbaseurl,
                          urlscheme=env['wsgi.url_scheme'],
                          remoteuser=env.get('REMOTE_USER'),
                          remotehost=env.get('REMOTE_HOST'),
                          apppath=apppath,
                          dispatchparts=dispatchparts, dispatchpath=dispatchpath,
                          reponame=reponame,
                          querystring=querystring,
                          qsparams=qsparams,
                          headers=headers,
                          bodyfh=bodyfh)
 
 class offsettrackingwriter(object):
     """A file object like object that is append only and tracks write count.
 
     Instances are bound to a callable. This callable is called with data
     whenever a ``write()`` is attempted.
 
     Instances track the amount of written data so they can answer ``tell()``
     requests.
 
     The intent of this class is to wrap the ``write()`` function returned by
     a WSGI ``start_response()`` function. Since ``write()`` is a callable and
     not a file object, it doesn't implement other file object methods.
     """
     def __init__(self, writefn):
         self._write = writefn
         self._offset = 0
 
     def write(self, s):
         res = self._write(s)
         # Some Python objects don't report the number of bytes written.
         if res is None:
             self._offset += len(s)
         else:
             self._offset += res
 
     def flush(self):
         pass
 
     def tell(self):
         return self._offset
 
 class wsgiresponse(object):
     """Represents a response to a WSGI request.
 
     A response consists of a status line, headers, and a body.
 
     Consumers must populate the ``status`` and ``headers`` fields and
     make a call to a ``setbody*()`` method before the response can be
     issued.
 
     When it is time to start sending the response over the wire,
     ``sendresponse()`` is called. It handles emitting the header portion
     of the response message. It then yields chunks of body data to be
     written to the peer. Typically, the WSGI application itself calls
     and returns the value from ``sendresponse()``.
     """
 
     def __init__(self, req, startresponse):
         """Create an empty response tied to a specific request.
 
         ``req`` is a ``parsedrequest``. ``startresponse`` is the
         ``start_response`` function passed to the WSGI application.
         """
         self._req = req
         self._startresponse = startresponse
 
         self.status = None
         self.headers = wsgiheaders.Headers([])
 
         self._bodybytes = None
         self._bodygen = None
         self._bodywillwrite = False
         self._started = False
         self._bodywritefn = None
 
     def _verifybody(self):
         if (self._bodybytes is not None or self._bodygen is not None
             or self._bodywillwrite):
             raise error.ProgrammingError('cannot define body multiple times')
 
     def setbodybytes(self, b):
         """Define the response body as static bytes.
 
         The empty string signals that there is no response body.
         """
         self._verifybody()
         self._bodybytes = b
         self.headers['Content-Length'] = '%d' % len(b)
 
     def setbodygen(self, gen):
         """Define the response body as a generator of bytes."""
         self._verifybody()
         self._bodygen = gen
 
     def setbodywillwrite(self):
         """Signal an intent to use write() to emit the response body.
 
         **This is the least preferred way to send a body.**
 
         It is preferred for WSGI applications to emit a generator of chunks
         constituting the response body. However, some consumers can't emit
         data this way. So, WSGI provides a way to obtain a ``write(data)``
         function that can be used to synchronously perform an unbuffered
         write.
 
         Calling this function signals an intent to produce the body in this
         manner.
         """
         self._verifybody()
         self._bodywillwrite = True
 
     def sendresponse(self):
         """Send the generated response to the client.
 
         Before this is called, ``status`` must be set and one of
         ``setbodybytes()`` or ``setbodygen()`` must be called.
 
         Calling this method multiple times is not allowed.
         """
         if self._started:
             raise error.ProgrammingError('sendresponse() called multiple times')
 
         self._started = True
 
         if not self.status:
             raise error.ProgrammingError('status line not defined')
 
         if (self._bodybytes is None and self._bodygen is None
             and not self._bodywillwrite):
             raise error.ProgrammingError('response body not defined')
 
         # RFC 7232 Section 4.1 states that a 304 MUST generate one of
         # {Cache-Control, Content-Location, Date, ETag, Expires, Vary}
         # and SHOULD NOT generate other headers unless they could be used
         # to guide cache updates. Furthermore, RFC 7230 Section 3.3.2
         # states that no response body can be issued. Content-Length can
         # be sent. But if it is present, it should be the size of the response
         # that wasn't transferred.
         if self.status.startswith('304 '):
             # setbodybytes('') will set C-L to 0. This doesn't conform with the
             # spec. So remove it.
             if self.headers.get('Content-Length') == '0':
                 del self.headers['Content-Length']
 
             # Strictly speaking, this is too strict. But until it causes
             # problems, let's be strict.
             badheaders = {k for k in self.headers.keys()
                           if k.lower() not in ('date', 'etag', 'expires',
                                                'cache-control',
                                                'content-location',
                                                'vary')}
             if badheaders:
                 raise error.ProgrammingError(
                     'illegal header on 304 response: %s' %
                     ', '.join(sorted(badheaders)))
 
             if self._bodygen is not None or self._bodywillwrite:
                 raise error.ProgrammingError("must use setbodybytes('') with "
                                              "304 responses")
 
         # Various HTTP clients (notably httplib) won't read the HTTP response
         # until the HTTP request has been sent in full. If servers (us) send a
         # response before the HTTP request has been fully sent, the connection
         # may deadlock because neither end is reading.
         #
         # We work around this by "draining" the request data before
         # sending any response in some conditions.
         drain = False
         close = False
 
         # If the client sent Expect: 100-continue, we assume it is smart enough
         # to deal with the server sending a response before reading the request.
         # (httplib doesn't do this.)
         if self._req.headers.get('Expect', '').lower() == '100-continue':
             pass
         # Only tend to request methods that have bodies. Strictly speaking,
         # we should sniff for a body. But this is fine for our existing
         # WSGI applications.
         elif self._req.method not in ('POST', 'PUT'):
             pass
         else:
             # If we don't know how much data to read, there's no guarantee
             # that we can drain the request responsibly. The WSGI
             # specification only says that servers *should* ensure the
             # input stream doesn't overrun the actual request. So there's
             # no guarantee that reading until EOF won't corrupt the stream
             # state.
             if not isinstance(self._req.bodyfh, util.cappedreader):
                 close = True
             else:
                 # We /could/ only drain certain HTTP response codes. But 200 and
                 # non-200 wire protocol responses both require draining. Since
                 # we have a capped reader in place for all situations where we
                 # drain, it is safe to read from that stream. We'll either do
                 # a drain or no-op if we're already at EOF.
                 drain = True
 
         if close:
             self.headers['Connection'] = 'Close'
 
         if drain:
             assert isinstance(self._req.bodyfh, util.cappedreader)
             while True:
                 chunk = self._req.bodyfh.read(32768)
                 if not chunk:
                     break
 
         write = self._startresponse(pycompat.sysstr(self.status),
                                     self.headers.items())
 
         if self._bodybytes:
             yield self._bodybytes
         elif self._bodygen:
             for chunk in self._bodygen:
                 yield chunk
         elif self._bodywillwrite:
             self._bodywritefn = write
         else:
             error.ProgrammingError('do not know how to send body')
 
     def getbodyfile(self):
         """Obtain a file object like object representing the response body.
 
         For this to work, you must call ``setbodywillwrite()`` and then
         ``sendresponse()`` first. ``sendresponse()`` is a generator and the
         function won't run to completion unless the generator is advanced. The
         generator yields not items. The easiest way to consume it is with
         ``list(res.sendresponse())``, which should resolve to an empty list -
         ``[]``.
         """
         if not self._bodywillwrite:
             raise error.ProgrammingError('must call setbodywillwrite() first')
 
         if not self._started:
             raise error.ProgrammingError('must call sendresponse() first; did '
                                          'you remember to consume it since it '
                                          'is a generator?')
 
         assert self._bodywritefn
         return offsettrackingwriter(self._bodywritefn)
 
 class wsgirequest(object):
     """Higher-level API for a WSGI request.
 
     WSGI applications are invoked with 2 arguments. They are used to
     instantiate instances of this class, which provides higher-level APIs
     for obtaining request parameters, writing HTTP output, etc.
     """
-    def __init__(self, wsgienv, start_response):
+    def __init__(self, wsgienv, start_response, altbaseurl=None):
         version = wsgienv[r'wsgi.version']
         if (version < (1, 0)) or (version >= (2, 0)):
             raise RuntimeError("Unknown and unsupported WSGI version %d.%d"
                                % version)
 
         inp = wsgienv[r'wsgi.input']
 
         if r'HTTP_CONTENT_LENGTH' in wsgienv:
             inp = util.cappedreader(inp, int(wsgienv[r'HTTP_CONTENT_LENGTH']))
         elif r'CONTENT_LENGTH' in wsgienv:
             inp = util.cappedreader(inp, int(wsgienv[r'CONTENT_LENGTH']))
 
         self.err = wsgienv[r'wsgi.errors']
         self.threaded = wsgienv[r'wsgi.multithread']
         self.multiprocess = wsgienv[r'wsgi.multiprocess']
         self.run_once = wsgienv[r'wsgi.run_once']
         self.env = wsgienv
-        self.req = parserequestfromenv(wsgienv, inp)
+        self.req = parserequestfromenv(wsgienv, inp, altbaseurl=altbaseurl)
         self.res = wsgiresponse(self.req, start_response)
         self._start_response = start_response
         self.server_write = None
         self.headers = []
 
     def respond(self, status, type, filename=None, body=None):
         if not isinstance(type, str):
             type = pycompat.sysstr(type)
         if self._start_response is not None:
             self.headers.append((r'Content-Type', type))
             if filename:
                 filename = (filename.rpartition('/')[-1]
                             .replace('\\', '\\\\').replace('"', '\\"'))
                 self.headers.append(('Content-Disposition',
                                      'inline; filename="%s"' % filename))
             if body is not None:
                 self.headers.append((r'Content-Length', str(len(body))))
 
             for k, v in self.headers:
                 if not isinstance(v, str):
                     raise TypeError('header value must be string: %r' % (v,))
 
             if isinstance(status, ErrorResponse):
                 self.headers.extend(status.headers)
                 status = statusmessage(status.code, pycompat.bytestr(status))
             elif status == 200:
                 status = '200 Script output follows'
             elif isinstance(status, int):
                 status = statusmessage(status)
 
             # Various HTTP clients (notably httplib) won't read the HTTP
             # response until the HTTP request has been sent in full. If servers
             # (us) send a response before the HTTP request has been fully sent,
             # the connection may deadlock because neither end is reading.
             #
             # We work around this by "draining" the request data before
             # sending any response in some conditions.
             drain = False
             close = False
 
             # If the client sent Expect: 100-continue, we assume it is smart
             # enough to deal with the server sending a response before reading
             # the request. (httplib doesn't do this.)
             if self.env.get(r'HTTP_EXPECT', r'').lower() == r'100-continue':
                 pass
             # Only tend to request methods that have bodies. Strictly speaking,
             # we should sniff for a body. But this is fine for our existing
             # WSGI applications.
             elif self.env[r'REQUEST_METHOD'] not in (r'POST', r'PUT'):
                 pass
             else:
                 # If we don't know how much data to read, there's no guarantee
                 # that we can drain the request responsibly. The WSGI
                 # specification only says that servers *should* ensure the
                 # input stream doesn't overrun the actual request. So there's
                 # no guarantee that reading until EOF won't corrupt the stream
                 # state.
                 if not isinstance(self.req.bodyfh, util.cappedreader):
                     close = True
                 else:
                     # We /could/ only drain certain HTTP response codes. But 200
                     # and non-200 wire protocol responses both require draining.
                     # Since we have a capped reader in place for all situations
                     # where we drain, it is safe to read from that stream. We'll
                     # either do a drain or no-op if we're already at EOF.
                     drain = True
 
             if close:
                 self.headers.append((r'Connection', r'Close'))
 
             if drain:
                 assert isinstance(self.req.bodyfh, util.cappedreader)
                 while True:
                     chunk = self.req.bodyfh.read(32768)
                     if not chunk:
                         break
 
             self.server_write = self._start_response(
                 pycompat.sysstr(status), self.headers)
             self._start_response = None
             self.headers = []
         if body is not None:
             self.write(body)
             self.server_write = None
 
     def write(self, thing):
         if thing:
             try:
                 self.server_write(thing)
             except socket.error as inst:
                 if inst[0] != errno.ECONNRESET:
                     raise
 
     def flush(self):
         return None
 
 def wsgiapplication(app_maker):
     '''For compatibility with old CGI scripts. A plain hgweb() or hgwebdir()
     can and should now be used as a WSGI application.'''
     application = app_maker()
     def run_wsgi(env, respond):
         return application(env, respond)
     return run_wsgi

tests/test-wsgirequest.py

@@ -1,247 +1,416
 from __future__ import absolute_import, print_function
 
 import unittest
 
 from mercurial.hgweb import (
     request as requestmod,
 )
 from mercurial import (
     error,
 )
 
 DEFAULT_ENV = {
     r'REQUEST_METHOD': r'GET',
     r'SERVER_NAME': r'testserver',
     r'SERVER_PORT': r'80',
     r'SERVER_PROTOCOL': r'http',
     r'wsgi.version': (1, 0),
     r'wsgi.url_scheme': r'http',
     r'wsgi.input': None,
     r'wsgi.errors': None,
     r'wsgi.multithread': False,
     r'wsgi.multiprocess': True,
     r'wsgi.run_once': False,
 }
 
-def parse(env, bodyfh=None, reponame=None, extra=None):
+def parse(env, bodyfh=None, reponame=None, altbaseurl=None, extra=None):
     env = dict(env)
     env.update(extra or {})
 
-    return requestmod.parserequestfromenv(env, bodyfh, reponame=reponame)
+    return requestmod.parserequestfromenv(env, bodyfh, reponame=reponame,
+                                          altbaseurl=altbaseurl)
 
 class ParseRequestTests(unittest.TestCase):
     def testdefault(self):
         r = parse(DEFAULT_ENV)
         self.assertEqual(r.url, b'http://testserver')
         self.assertEqual(r.baseurl, b'http://testserver')
         self.assertEqual(r.advertisedurl, b'http://testserver')
         self.assertEqual(r.advertisedbaseurl, b'http://testserver')
         self.assertEqual(r.urlscheme, b'http')
         self.assertEqual(r.method, b'GET')
         self.assertIsNone(r.remoteuser)
         self.assertIsNone(r.remotehost)
         self.assertEqual(r.apppath, b'')
         self.assertEqual(r.dispatchparts, [])
         self.assertIsNone(r.dispatchpath)
         self.assertIsNone(r.reponame)
         self.assertEqual(r.querystring, b'')
         self.assertEqual(len(r.qsparams), 0)
         self.assertEqual(len(r.headers), 0)
 
     def testcustomport(self):
         r = parse(DEFAULT_ENV, extra={
             r'SERVER_PORT': r'8000',
         })
 
         self.assertEqual(r.url, b'http://testserver:8000')
         self.assertEqual(r.baseurl, b'http://testserver:8000')
         self.assertEqual(r.advertisedurl, b'http://testserver:8000')
         self.assertEqual(r.advertisedbaseurl, b'http://testserver:8000')
 
         r = parse(DEFAULT_ENV, extra={
             r'SERVER_PORT': r'4000',
             r'wsgi.url_scheme': r'https',
         })
 
         self.assertEqual(r.url, b'https://testserver:4000')
         self.assertEqual(r.baseurl, b'https://testserver:4000')
         self.assertEqual(r.advertisedurl, b'https://testserver:4000')
         self.assertEqual(r.advertisedbaseurl, b'https://testserver:4000')
 
     def testhttphost(self):
         r = parse(DEFAULT_ENV, extra={
             r'HTTP_HOST': r'altserver',
         })
 
         self.assertEqual(r.url, b'http://altserver')
         self.assertEqual(r.baseurl, b'http://altserver')
         self.assertEqual(r.advertisedurl, b'http://testserver')
         self.assertEqual(r.advertisedbaseurl, b'http://testserver')
 
     def testscriptname(self):
         r = parse(DEFAULT_ENV, extra={
             r'SCRIPT_NAME': r'',
         })
 
         self.assertEqual(r.url, b'http://testserver')
         self.assertEqual(r.baseurl, b'http://testserver')
         self.assertEqual(r.advertisedurl, b'http://testserver')
         self.assertEqual(r.advertisedbaseurl, b'http://testserver')
         self.assertEqual(r.apppath, b'')
         self.assertEqual(r.dispatchparts, [])
         self.assertIsNone(r.dispatchpath)
 
         r = parse(DEFAULT_ENV, extra={
             r'SCRIPT_NAME': r'/script',
         })
 
         self.assertEqual(r.url, b'http://testserver/script')
         self.assertEqual(r.baseurl, b'http://testserver')
         self.assertEqual(r.advertisedurl, b'http://testserver/script')
         self.assertEqual(r.advertisedbaseurl, b'http://testserver')
         self.assertEqual(r.apppath, b'/script')
         self.assertEqual(r.dispatchparts, [])
         self.assertIsNone(r.dispatchpath)
 
         r = parse(DEFAULT_ENV, extra={
             r'SCRIPT_NAME': r'/multiple words',
         })
 
         self.assertEqual(r.url, b'http://testserver/multiple%20words')
         self.assertEqual(r.baseurl, b'http://testserver')
         self.assertEqual(r.advertisedurl, b'http://testserver/multiple%20words')
         self.assertEqual(r.advertisedbaseurl, b'http://testserver')
         self.assertEqual(r.apppath, b'/multiple words')
         self.assertEqual(r.dispatchparts, [])
         self.assertIsNone(r.dispatchpath)
 
     def testpathinfo(self):
         r = parse(DEFAULT_ENV, extra={
             r'PATH_INFO': r'',
         })
 
         self.assertEqual(r.url, b'http://testserver')
         self.assertEqual(r.baseurl, b'http://testserver')
         self.assertEqual(r.advertisedurl, b'http://testserver')
         self.assertEqual(r.advertisedbaseurl, b'http://testserver')
         self.assertEqual(r.apppath, b'')
         self.assertEqual(r.dispatchparts, [])
         self.assertEqual(r.dispatchpath, b'')
 
         r = parse(DEFAULT_ENV, extra={
             r'PATH_INFO': r'/pathinfo',
         })
 
         self.assertEqual(r.url, b'http://testserver/pathinfo')
         self.assertEqual(r.baseurl, b'http://testserver')
         self.assertEqual(r.advertisedurl, b'http://testserver/pathinfo')
         self.assertEqual(r.advertisedbaseurl, b'http://testserver')
         self.assertEqual(r.apppath, b'')
         self.assertEqual(r.dispatchparts, [b'pathinfo'])
         self.assertEqual(r.dispatchpath, b'pathinfo')
 
         r = parse(DEFAULT_ENV, extra={
             r'PATH_INFO': r'/one/two/',
         })
 
         self.assertEqual(r.url, b'http://testserver/one/two/')
         self.assertEqual(r.baseurl, b'http://testserver')
         self.assertEqual(r.advertisedurl, b'http://testserver/one/two/')
         self.assertEqual(r.advertisedbaseurl, b'http://testserver')
         self.assertEqual(r.apppath, b'')
         self.assertEqual(r.dispatchparts, [b'one', b'two'])
         self.assertEqual(r.dispatchpath, b'one/two')
 
     def testscriptandpathinfo(self):
         r = parse(DEFAULT_ENV, extra={
             r'SCRIPT_NAME': r'/script',
             r'PATH_INFO': r'/pathinfo',
         })
 
         self.assertEqual(r.url, b'http://testserver/script/pathinfo')
         self.assertEqual(r.baseurl, b'http://testserver')
         self.assertEqual(r.advertisedurl, b'http://testserver/script/pathinfo')
         self.assertEqual(r.advertisedbaseurl, b'http://testserver')
         self.assertEqual(r.apppath, b'/script')
         self.assertEqual(r.dispatchparts, [b'pathinfo'])
         self.assertEqual(r.dispatchpath, b'pathinfo')
 
         r = parse(DEFAULT_ENV, extra={
             r'SCRIPT_NAME': r'/script1/script2',
             r'PATH_INFO': r'/path1/path2',
         })
 
         self.assertEqual(r.url,
                          b'http://testserver/script1/script2/path1/path2')
         self.assertEqual(r.baseurl, b'http://testserver')
         self.assertEqual(r.advertisedurl,
                          b'http://testserver/script1/script2/path1/path2')
         self.assertEqual(r.advertisedbaseurl, b'http://testserver')
         self.assertEqual(r.apppath, b'/script1/script2')
         self.assertEqual(r.dispatchparts, [b'path1', b'path2'])
         self.assertEqual(r.dispatchpath, b'path1/path2')
 
         r = parse(DEFAULT_ENV, extra={
             r'HTTP_HOST': r'hostserver',
             r'SCRIPT_NAME': r'/script',
             r'PATH_INFO': r'/pathinfo',
         })
 
         self.assertEqual(r.url, b'http://hostserver/script/pathinfo')
         self.assertEqual(r.baseurl, b'http://hostserver')
         self.assertEqual(r.advertisedurl, b'http://testserver/script/pathinfo')
         self.assertEqual(r.advertisedbaseurl, b'http://testserver')
         self.assertEqual(r.apppath, b'/script')
         self.assertEqual(r.dispatchparts, [b'pathinfo'])
         self.assertEqual(r.dispatchpath, b'pathinfo')
 
     def testreponame(self):
         """repository path components get stripped from URL."""
 
         with self.assertRaisesRegexp(error.ProgrammingError,
                                      b'reponame requires PATH_INFO'):
             parse(DEFAULT_ENV, reponame=b'repo')
 
         with self.assertRaisesRegexp(error.ProgrammingError,
                                      b'PATH_INFO does not begin with repo '
                                      b'name'):
             parse(DEFAULT_ENV, reponame=b'repo', extra={
                 r'PATH_INFO': r'/pathinfo',
             })
 
         with self.assertRaisesRegexp(error.ProgrammingError,
                                      b'reponame prefix of PATH_INFO'):
             parse(DEFAULT_ENV, reponame=b'repo', extra={
                 r'PATH_INFO': r'/repoextra/path',
             })
 
         r = parse(DEFAULT_ENV, reponame=b'repo', extra={
             r'PATH_INFO': r'/repo/path1/path2',
         })
 
         self.assertEqual(r.url, b'http://testserver/repo/path1/path2')
         self.assertEqual(r.baseurl, b'http://testserver')
         self.assertEqual(r.advertisedurl, b'http://testserver/repo/path1/path2')
         self.assertEqual(r.advertisedbaseurl, b'http://testserver')
         self.assertEqual(r.apppath, b'/repo')
         self.assertEqual(r.dispatchparts, [b'path1', b'path2'])
         self.assertEqual(r.dispatchpath, b'path1/path2')
         self.assertEqual(r.reponame, b'repo')
 
         r = parse(DEFAULT_ENV, reponame=b'prefix/repo', extra={
             r'PATH_INFO': r'/prefix/repo/path1/path2',
         })
 
         self.assertEqual(r.url, b'http://testserver/prefix/repo/path1/path2')
         self.assertEqual(r.baseurl, b'http://testserver')
         self.assertEqual(r.advertisedurl,
                          b'http://testserver/prefix/repo/path1/path2')
         self.assertEqual(r.advertisedbaseurl, b'http://testserver')
         self.assertEqual(r.apppath, b'/prefix/repo')
         self.assertEqual(r.dispatchparts, [b'path1', b'path2'])
         self.assertEqual(r.dispatchpath, b'path1/path2')
         self.assertEqual(r.reponame, b'prefix/repo')
 
+    def testaltbaseurl(self):
+        # Simple hostname remap.
+        r = parse(DEFAULT_ENV, altbaseurl='http://altserver')
+
+        self.assertEqual(r.url, b'http://testserver')
+        self.assertEqual(r.baseurl, b'http://testserver')
+        self.assertEqual(r.advertisedurl, b'http://altserver')
+        self.assertEqual(r.advertisedbaseurl, b'http://altserver')
+        self.assertEqual(r.urlscheme, b'http')
+        self.assertEqual(r.apppath, b'')
+        self.assertEqual(r.dispatchparts, [])
+        self.assertIsNone(r.dispatchpath)
+        self.assertIsNone(r.reponame)
+
+        # With a custom port.
+        r = parse(DEFAULT_ENV, altbaseurl='http://altserver:8000')
+        self.assertEqual(r.url, b'http://testserver')
+        self.assertEqual(r.baseurl, b'http://testserver')
+        self.assertEqual(r.advertisedurl, b'http://altserver:8000')
+        self.assertEqual(r.advertisedbaseurl, b'http://altserver:8000')
+        self.assertEqual(r.urlscheme, b'http')
+        self.assertEqual(r.apppath, b'')
+        self.assertEqual(r.dispatchparts, [])
+        self.assertIsNone(r.dispatchpath)
+        self.assertIsNone(r.reponame)
+
+        # With a changed protocol.
+        r = parse(DEFAULT_ENV, altbaseurl='https://altserver')
+        self.assertEqual(r.url, b'http://testserver')
+        self.assertEqual(r.baseurl, b'http://testserver')
+        self.assertEqual(r.advertisedurl, b'https://altserver')
+        self.assertEqual(r.advertisedbaseurl, b'https://altserver')
+        # URL scheme is defined as the actual scheme, not advertised.
+        self.assertEqual(r.urlscheme, b'http')
+        self.assertEqual(r.apppath, b'')
+        self.assertEqual(r.dispatchparts, [])
+        self.assertIsNone(r.dispatchpath)
+        self.assertIsNone(r.reponame)
+
+        # Need to specify explicit port number for proper https:// alt URLs.
+        r = parse(DEFAULT_ENV, altbaseurl='https://altserver:443')
+        self.assertEqual(r.url, b'http://testserver')
+        self.assertEqual(r.baseurl, b'http://testserver')
+        self.assertEqual(r.advertisedurl, b'https://altserver')
+        self.assertEqual(r.advertisedbaseurl, b'https://altserver')
+        self.assertEqual(r.urlscheme, b'http')
+        self.assertEqual(r.apppath, b'')
+        self.assertEqual(r.dispatchparts, [])
+        self.assertIsNone(r.dispatchpath)
+        self.assertIsNone(r.reponame)
+
+        # With only PATH_INFO defined.
+        r = parse(DEFAULT_ENV, altbaseurl='http://altserver', extra={
+            r'PATH_INFO': r'/path1/path2',
+        })
+        self.assertEqual(r.url, b'http://testserver/path1/path2')
+        self.assertEqual(r.baseurl, b'http://testserver')
+        self.assertEqual(r.advertisedurl, b'http://altserver/path1/path2')
+        self.assertEqual(r.advertisedbaseurl, b'http://altserver')
+        self.assertEqual(r.urlscheme, b'http')
+        self.assertEqual(r.apppath, b'')
+        self.assertEqual(r.dispatchparts, [b'path1', b'path2'])
+        self.assertEqual(r.dispatchpath, b'path1/path2')
+        self.assertIsNone(r.reponame)
+
+        # Path on alt URL.
+        r = parse(DEFAULT_ENV, altbaseurl='http://altserver/altpath')
+        self.assertEqual(r.url, b'http://testserver')
+        self.assertEqual(r.baseurl, b'http://testserver')
+        self.assertEqual(r.advertisedurl, b'http://altserver/altpath')
+        self.assertEqual(r.advertisedbaseurl, b'http://altserver')
+        self.assertEqual(r.urlscheme, b'http')
+        self.assertEqual(r.apppath, b'/altpath')
+        self.assertEqual(r.dispatchparts, [])
+        self.assertIsNone(r.dispatchpath)
+        self.assertIsNone(r.reponame)
+
+        # With a trailing slash.
+        r = parse(DEFAULT_ENV, altbaseurl='http://altserver/altpath/')
+        self.assertEqual(r.url, b'http://testserver')
+        self.assertEqual(r.baseurl, b'http://testserver')
+        self.assertEqual(r.advertisedurl, b'http://altserver/altpath/')
+        self.assertEqual(r.advertisedbaseurl, b'http://altserver')
+        self.assertEqual(r.urlscheme, b'http')
+        self.assertEqual(r.apppath, b'/altpath/')
+        self.assertEqual(r.dispatchparts, [])
+        self.assertIsNone(r.dispatchpath)
+        self.assertIsNone(r.reponame)
+
+        # PATH_INFO + path on alt URL.
+        r = parse(DEFAULT_ENV, altbaseurl='http://altserver/altpath', extra={
+            r'PATH_INFO': r'/path1/path2',
+        })
+        self.assertEqual(r.url, b'http://testserver/path1/path2')
+        self.assertEqual(r.baseurl, b'http://testserver')
+        self.assertEqual(r.advertisedurl,
+                         b'http://altserver/altpath/path1/path2')
+        self.assertEqual(r.advertisedbaseurl, b'http://altserver')
+        self.assertEqual(r.urlscheme, b'http')
+        self.assertEqual(r.apppath, b'/altpath')
+        self.assertEqual(r.dispatchparts, [b'path1', b'path2'])
+        self.assertEqual(r.dispatchpath, b'path1/path2')
+        self.assertIsNone(r.reponame)
+
+        # PATH_INFO + path on alt URL with trailing slash.
+        r = parse(DEFAULT_ENV, altbaseurl='http://altserver/altpath/', extra={
+            r'PATH_INFO': r'/path1/path2',
+        })
+        self.assertEqual(r.url, b'http://testserver/path1/path2')
+        self.assertEqual(r.baseurl, b'http://testserver')
+        self.assertEqual(r.advertisedurl,
+                         b'http://altserver/altpath//path1/path2')
+        self.assertEqual(r.advertisedbaseurl, b'http://altserver')
+        self.assertEqual(r.urlscheme, b'http')
+        self.assertEqual(r.apppath, b'/altpath/')
+        self.assertEqual(r.dispatchparts, [b'path1', b'path2'])
+        self.assertEqual(r.dispatchpath, b'path1/path2')
+        self.assertIsNone(r.reponame)
+
+        # Local SCRIPT_NAME is ignored.
+        r = parse(DEFAULT_ENV, altbaseurl='http://altserver', extra={
+            r'SCRIPT_NAME': r'/script',
+            r'PATH_INFO': r'/path1/path2',
+        })
+        self.assertEqual(r.url, b'http://testserver/script/path1/path2')
+        self.assertEqual(r.baseurl, b'http://testserver')
+        self.assertEqual(r.advertisedurl, b'http://altserver/path1/path2')
+        self.assertEqual(r.advertisedbaseurl, b'http://altserver')
+        self.assertEqual(r.urlscheme, b'http')
+        self.assertEqual(r.apppath, b'')
+        self.assertEqual(r.dispatchparts, [b'path1', b'path2'])
+        self.assertEqual(r.dispatchpath, b'path1/path2')
+        self.assertIsNone(r.reponame)
+
+        # Use remote's path for script name, app path
+        r = parse(DEFAULT_ENV, altbaseurl='http://altserver/altroot', extra={
+            r'SCRIPT_NAME': r'/script',
+            r'PATH_INFO': r'/path1/path2',
+        })
+        self.assertEqual(r.url, b'http://testserver/script/path1/path2')
+        self.assertEqual(r.baseurl, b'http://testserver')
+        self.assertEqual(r.advertisedurl,
+                         b'http://altserver/altroot/path1/path2')
+        self.assertEqual(r.advertisedbaseurl, b'http://altserver')
+        self.assertEqual(r.urlscheme, b'http')
+        self.assertEqual(r.apppath, b'/altroot')
+        self.assertEqual(r.dispatchparts, [b'path1', b'path2'])
+        self.assertEqual(r.dispatchpath, b'path1/path2')
+        self.assertIsNone(r.reponame)
+
+        # reponame is factored in properly.
+        r = parse(DEFAULT_ENV, reponame=b'repo',
+                  altbaseurl='http://altserver/altroot',
+                  extra={
+                r'SCRIPT_NAME': r'/script',
+                r'PATH_INFO': r'/repo/path1/path2',
+            })
+
+        self.assertEqual(r.url, b'http://testserver/script/repo/path1/path2')
+        self.assertEqual(r.baseurl, b'http://testserver')
+        self.assertEqual(r.advertisedurl,
+                         b'http://altserver/altroot/repo/path1/path2')
+        self.assertEqual(r.advertisedbaseurl, b'http://altserver')
+        self.assertEqual(r.apppath, b'/altroot/repo')
+        self.assertEqual(r.dispatchparts, [b'path1', b'path2'])
+        self.assertEqual(r.dispatchpath, b'path1/path2')
+        self.assertEqual(r.reponame, b'repo')
+
 if __name__ == '__main__':
     import silenttestrunner
     silenttestrunner.main(__name__)