hgweb: reuse body file object when hgwebdir calls hgweb (issue5851)

An unintended side-effect of f0a851542a05 was that the request body
file object (which uses a util.cappedreader) was constructed twice
when hgwebdir called into hgweb. Since we attempt to read all remaining
data from this file object when Content-Length is defined and since there
were two instances of this object and the client supplied no additional
data to read, this resulted in deadlock.

The fix implemented in this commit is to reuse the request body file
object when it is passed from hgwebdir to hgweb.

A test demonstrating `hg clone` and `hg push` via hgwebdir has been
added. Without this patch, the test hangs when doing `hg clone`.
Surprisingly, this must mean that we have effectively no test coverage
of the wire protocol when run via hgwebdir.

Differential Revision: https://phab.mercurial-scm.org/D3427

mercurial/hgweb/hgwebdir_mod.py

@@ -1,530 +1,533
 # 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 gc
 import os
 import time
 
 from ..i18n import _
 
 from .common import (
     ErrorResponse,
     HTTP_SERVER_ERROR,
     cspvalues,
     get_contact,
     get_mtime,
     ismember,
     paritygen,
     staticfile,
     statusmessage,
 )
 
 from .. import (
     configitems,
     encoding,
     error,
     hg,
     profiling,
     pycompat,
     scmutil,
     templater,
     templateutil,
     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 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 rawindexentries(ui, repos, 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 = [
             req.apppath.strip('/'),
             subdir.strip('/'),
             name.strip('/'),
         ]
         url = '/' + '/'.join(p for p in parts if p) + '/'
 
         # 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': templateutil.mappinglist([]),
                    'isdirectory': True,
                    'labels': templateutil.hybridlist([], name='label'),
                    }
 
             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)
         labels = u.configlist('web', 'labels', untrusted=True)
         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': webutil.archivelist(u, "tip", url),
                'isdirectory': None,
                'labels': templateutil.hybridlist(labels, name='label'),
                }
 
         yield row
 
 def _indexentriesgen(context, ui, repos, req, stripecount, sortcolumn,
                      descending, subdir):
     rows = rawindexentries(ui, repos, 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
 
 def indexentries(ui, repos, req, stripecount, sortcolumn='',
                  descending=False, subdir=''):
     args = (ui, repos, req, stripecount, sortcolumn, descending, subdir)
     return templateutil.mappinggenerator(_indexentriesgen, args=args)
 
 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)
         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):
         baseurl = self.ui.config('web', 'baseurl')
         req = requestmod.parserequestfromenv(env, altbaseurl=baseurl)
         res = requestmod.wsgiresponse(req, respond)
 
         return self.run_wsgi(req, res)
 
     def run_wsgi(self, req, res):
         profile = self.ui.configbool('profiling', 'enabled')
         with profiling.profile(self.ui, enabled=profile):
             try:
                 for r in self._runwsgi(req, res):
                     yield r
             finally:
                 # There are known cycles in localrepository that prevent
                 # those objects (and tons of held references) from being
                 # collected through normal refcounting. We mitigate those
                 # leaks by performing an explicit GC on every request.
                 # TODO remove this once leaks are fixed.
                 # TODO only run this on requests that create localrepository
                 # instances instead of every request.
                 gc.collect()
 
     def _runwsgi(self, req, res):
         try:
             self.refresh()
 
             csp, nonce = cspvalues(self.ui)
             if csp:
                 res.headers['Content-Security-Policy'] = csp
 
             virtual = req.dispatchpath.strip('/')
             tmpl = self.templater(req, nonce)
             ctype = tmpl.render('mimetype', {'encoding': encoding.encoding})
 
             # 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:
                 return self.makeindex(req, res, 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):
                     return self.makeindex(req, res, 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.
                     uenv = req.rawenv
                     if pycompat.ispy3:
                         uenv = {k.decode('latin1'): v for k, v in
                                 uenv.iteritems()}
                     req = requestmod.parserequestfromenv(
                         uenv, reponame=virtualrepo,
-                        altbaseurl=self.ui.config('web', 'baseurl'))
+                        altbaseurl=self.ui.config('web', 'baseurl'),
+                        # Reuse wrapped body file object otherwise state
+                        # tracking can get confused.
+                        bodyfh=req.bodyfh)
                     try:
                         # ensure caller gets private copy of ui
                         repo = hg.repository(self.ui.copy(), real)
                         return hgweb_mod.hgweb(repo).run_wsgi(req, res)
                     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)]:
                 return self.makeindex(req, res, tmpl, subdir)
 
             # prefixes not found
             res.status = '404 Not Found'
             res.setbodygen(tmpl.generate('notfound', {'repo': virtual}))
             return res.sendresponse()
 
         except ErrorResponse as e:
             res.status = statusmessage(e.code, pycompat.bytestr(e))
             res.setbodygen(tmpl.generate('error', {'error': e.message or ''}))
             return res.sendresponse()
         finally:
             tmpl = None
 
     def makeindex(self, req, res, tmpl, subdir=""):
         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()
 
         entries = indexentries(self.ui, self.repos, req,
                                self.stripecount, sortcolumn=sortcolumn,
                                descending=descending, subdir=subdir)
 
         mapping = {
             'entries': entries,
             'subdir': subdir,
             'pathdef': hgweb_mod.makebreadcrumb('/' + subdir, self.prefix),
             'sortcolumn': sortcolumn,
             'descending': descending,
         }
         mapping.update(sort)
         res.setbodygen(tmpl.generate('index', mapping))
         return res.sendresponse()
 
     def templater(self, req, 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)
 
         vars = {}
         styles, (style, mapfile) = hgweb_mod.getstyle(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 req.apppath + '/static/')
         if not staticurl.endswith('/'):
             staticurl += '/'
 
         defaults = {
             "encoding": encoding.encoding,
             "motd": motd,
             "url": req.apppath + '/',
             "logourl": logourl,
             "logoimg": logoimg,
             "staticurl": staticurl,
             "sessionvars": sessionvars,
             "style": style,
             "nonce": nonce,
         }
         tmpl = templater.templater.frommapfile(mapfile, defaults=defaults)
         return tmpl

mercurial/hgweb/request.py

@@ -1,570 +1,574
 # 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 wsgiref.validate
 
 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):
         self._items = {}
 
     def __getitem__(self, key):
         """Returns the last set value for a key."""
         return self._items[key][-1]
 
     def __setitem__(self, key, value):
         """Replace a values for a key with a new value."""
         self._items[key] = [value]
 
     def __delitem__(self, key):
         """Delete all values for a key."""
         del self._items[key]
 
     def __contains__(self, key):
         return key 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.setdefault(key, []).append(value)
 
     def getall(self, key):
         """Obtains all values for a key."""
         return self._items.get(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._items[key]
 
         if len(vals) > 1:
             raise KeyError('multiple values for %r' % key)
 
         return vals[0]
 
     def asdictoflists(self):
         return {k: list(v) for k, v in self._items.iteritems()}
 
 @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()
     # WSGI environment dict, unmodified.
     rawenv = attr.ib()
 
-def parserequestfromenv(env, reponame=None, altbaseurl=None):
+def parserequestfromenv(env, reponame=None, altbaseurl=None, bodyfh=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.
+
+    ``bodyfh`` can be used to specify a file object to read the request body
+    from. If not defined, ``wsgi.input`` from the environment dict is used.
     """
     # 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()}
 
     # Some hosting solutions are emulating hgwebdir, and dispatching directly
     # to an hgweb instance using this environment variable.  This was always
     # checked prior to d7fd203e36cc; keep doing so to avoid breaking them.
     if not reponame:
         reponame = env.get('REPO_NAME')
 
     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'] + '://'
 
     if altbaseurl and altbaseurl.scheme:
         advertisedfullurl = altbaseurl.scheme + '://'
     else:
         advertisedfullurl = fullurl
 
     def addport(s, port):
         if s.startswith('https://'):
             if port != '443':
                 s += ':' + port
         else:
             if port != '80':
                 s += ':' + port
 
         return s
 
     if env.get('HTTP_HOST'):
         fullurl += env['HTTP_HOST']
     else:
         fullurl += env['SERVER_NAME']
         fullurl = addport(fullurl, env['SERVER_PORT'])
 
     if altbaseurl and altbaseurl.host:
         advertisedfullurl += altbaseurl.host
 
         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', ''))
     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.
 
     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))
 
     from . import wsgiheaders # avoid cycle
     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']
 
     if 'CONTENT_TYPE' in env and 'HTTP_CONTENT_TYPE' not in env:
         headers['Content-Type'] = env['CONTENT_TYPE']
 
+    if bodyfh is None:
     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,
                          rawenv=env)
 
 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
         from . import wsgiheaders # avoid cycle
         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
 
         strheaders = [(pycompat.strurl(k), pycompat.strurl(v)) for
                       k, v in self.headers.items()]
         write = self._startresponse(pycompat.sysstr(self.status),
                                     strheaders)
 
         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)
 
 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-push-http.t

@@ -1,382 +1,426
 #require killdaemons
 
 #testcases bundle1 bundle2
 
 #if bundle1
   $ cat << EOF >> $HGRCPATH
   > [devel]
   > # This test is dedicated to interaction through old bundle
   > legacy.exchange = bundle1
   > EOF
 #endif
 
   $ hg init test
   $ cd test
   $ echo a > a
   $ hg ci -Ama
   adding a
   $ cd ..
   $ hg clone test test2
   updating to branch default
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
   $ cd test2
   $ echo a >> a
   $ hg ci -mb
   $ req() {
   >     hg $1 serve -p $HGPORT -d --pid-file=hg.pid -E errors.log
   >     cat hg.pid >> $DAEMON_PIDS
   >     hg --cwd ../test2 push http://localhost:$HGPORT/
   >     exitstatus=$?
   >     killdaemons.py
   >     echo % serve errors
   >     cat errors.log
   >     return $exitstatus
   > }
   $ cd ../test
 
 expect ssl error
 
   $ req
   pushing to http://localhost:$HGPORT/
   searching for changes
   abort: HTTP Error 403: ssl required
   % serve errors
   [255]
 
 expect authorization error
 
   $ echo '[web]' > .hg/hgrc
   $ echo 'push_ssl = false' >> .hg/hgrc
   $ req
   pushing to http://localhost:$HGPORT/
   searching for changes
   abort: authorization failed
   % serve errors
   [255]
 
 expect authorization error: must have authorized user
 
   $ echo 'allow_push = unperson' >> .hg/hgrc
   $ req
   pushing to http://localhost:$HGPORT/
   searching for changes
   abort: authorization failed
   % serve errors
   [255]
 
 expect success
 
   $ cat > $TESTTMP/hook.sh <<'EOF'
   > echo "phase-move: $HG_NODE:  $HG_OLDPHASE -> $HG_PHASE"
   > EOF
 
 #if bundle1
   $ cat >> .hg/hgrc <<EOF
   > allow_push = *
   > [hooks]
   > changegroup = sh -c "printenv.py changegroup 0"
   > pushkey = sh -c "printenv.py pushkey 0"
   > txnclose-phase.test = sh $TESTTMP/hook.sh 
   > EOF
   $ req "--debug --config extensions.blackbox="
   listening at http://*:$HGPORT/ (bound to $LOCALIP:$HGPORT) (glob) (?)
   pushing to http://localhost:$HGPORT/
   searching for changes
   remote: redirecting incoming bundle to */hg-unbundle-* (glob)
   remote: adding changesets
   remote: add changeset ba677d0156c1
   remote: adding manifests
   remote: adding file changes
   remote: adding a revisions
   remote: added 1 changesets with 1 changes to 1 files
   remote: updating the branch cache
   remote: running hook txnclose-phase.test: sh $TESTTMP/hook.sh
   remote: phase-move: cb9a9f314b8b07ba71012fcdbc544b5a4d82ff5b:  draft -> public
   remote: running hook txnclose-phase.test: sh $TESTTMP/hook.sh
   remote: phase-move: ba677d0156c1196c1a699fa53f390dcfc3ce3872:   -> public
   remote: running hook changegroup: sh -c "printenv.py changegroup 0"
   remote: changegroup hook: HG_HOOKNAME=changegroup HG_HOOKTYPE=changegroup HG_NODE=ba677d0156c1196c1a699fa53f390dcfc3ce3872 HG_NODE_LAST=ba677d0156c1196c1a699fa53f390dcfc3ce3872 HG_SOURCE=serve HG_TXNID=TXN:$ID$ HG_URL=remote:http:$LOCALIP: (glob)
   % serve errors
   $ hg rollback
   repository tip rolled back to revision 0 (undo serve)
   $ req "--debug --config server.streamunbundle=True --config extensions.blackbox="
   listening at http://*:$HGPORT/ (bound to $LOCALIP:$HGPORT) (glob) (?)
   pushing to http://localhost:$HGPORT/
   searching for changes
   remote: adding changesets
   remote: add changeset ba677d0156c1
   remote: adding manifests
   remote: adding file changes
   remote: adding a revisions
   remote: added 1 changesets with 1 changes to 1 files
   remote: updating the branch cache
   remote: running hook txnclose-phase.test: sh $TESTTMP/hook.sh
   remote: phase-move: cb9a9f314b8b07ba71012fcdbc544b5a4d82ff5b:  draft -> public
   remote: running hook txnclose-phase.test: sh $TESTTMP/hook.sh
   remote: phase-move: ba677d0156c1196c1a699fa53f390dcfc3ce3872:   -> public
   remote: running hook changegroup: sh -c "printenv.py changegroup 0"
   remote: changegroup hook: HG_HOOKNAME=changegroup HG_HOOKTYPE=changegroup HG_NODE=ba677d0156c1196c1a699fa53f390dcfc3ce3872 HG_NODE_LAST=ba677d0156c1196c1a699fa53f390dcfc3ce3872 HG_SOURCE=serve HG_TXNID=TXN:$ID$ HG_URL=remote:http:$LOCALIP: (glob)
   % serve errors
   $ hg rollback
   repository tip rolled back to revision 0 (undo serve)
 #endif
 
 #if bundle2
   $ cat >> .hg/hgrc <<EOF
   > allow_push = *
   > [hooks]
   > changegroup = sh -c "printenv.py changegroup 0"
   > pushkey = sh -c "printenv.py pushkey 0"
   > txnclose-phase.test = sh $TESTTMP/hook.sh 
   > EOF
   $ req
   pushing to http://localhost:$HGPORT/
   searching for changes
   remote: adding changesets
   remote: adding manifests
   remote: adding file changes
   remote: added 1 changesets with 1 changes to 1 files
   remote: phase-move: cb9a9f314b8b07ba71012fcdbc544b5a4d82ff5b:  draft -> public
   remote: phase-move: ba677d0156c1196c1a699fa53f390dcfc3ce3872:   -> public
   remote: changegroup hook: HG_BUNDLE2=1 HG_HOOKNAME=changegroup HG_HOOKTYPE=changegroup HG_NODE=ba677d0156c1196c1a699fa53f390dcfc3ce3872 HG_NODE_LAST=ba677d0156c1196c1a699fa53f390dcfc3ce3872 HG_SOURCE=serve HG_TXNID=TXN:$ID$ HG_URL=remote:http:$LOCALIP: (glob)
   % serve errors
   $ hg rollback
   repository tip rolled back to revision 0 (undo serve)
 #endif
 
 expect success, server lacks the httpheader capability
 
   $ CAP=httpheader
   $ . "$TESTDIR/notcapable"
   $ req
   pushing to http://localhost:$HGPORT/
   searching for changes
   remote: adding changesets
   remote: adding manifests
   remote: adding file changes
   remote: added 1 changesets with 1 changes to 1 files
   remote: phase-move: cb9a9f314b8b07ba71012fcdbc544b5a4d82ff5b:  draft -> public
   remote: phase-move: ba677d0156c1196c1a699fa53f390dcfc3ce3872:   -> public
   remote: changegroup hook: HG_HOOKNAME=changegroup HG_HOOKTYPE=changegroup HG_NODE=ba677d0156c1196c1a699fa53f390dcfc3ce3872 HG_NODE_LAST=ba677d0156c1196c1a699fa53f390dcfc3ce3872 HG_SOURCE=serve HG_TXNID=TXN:$ID$ HG_URL=remote:http:$LOCALIP: (glob) (bundle1 !)
   remote: changegroup hook: HG_BUNDLE2=1 HG_HOOKNAME=changegroup HG_HOOKTYPE=changegroup HG_NODE=ba677d0156c1196c1a699fa53f390dcfc3ce3872 HG_NODE_LAST=ba677d0156c1196c1a699fa53f390dcfc3ce3872 HG_SOURCE=serve HG_TXNID=TXN:$ID$ HG_URL=remote:http:$LOCALIP: (glob) (bundle2 !)
   % serve errors
   $ hg rollback
   repository tip rolled back to revision 0 (undo serve)
 
 expect success, server lacks the unbundlehash capability
 
   $ CAP=unbundlehash
   $ . "$TESTDIR/notcapable"
   $ req
   pushing to http://localhost:$HGPORT/
   searching for changes
   remote: adding changesets
   remote: adding manifests
   remote: adding file changes
   remote: added 1 changesets with 1 changes to 1 files
   remote: phase-move: cb9a9f314b8b07ba71012fcdbc544b5a4d82ff5b:  draft -> public
   remote: phase-move: ba677d0156c1196c1a699fa53f390dcfc3ce3872:   -> public
   remote: changegroup hook: HG_HOOKNAME=changegroup HG_HOOKTYPE=changegroup HG_NODE=ba677d0156c1196c1a699fa53f390dcfc3ce3872 HG_NODE_LAST=ba677d0156c1196c1a699fa53f390dcfc3ce3872 HG_SOURCE=serve HG_TXNID=TXN:$ID$ HG_URL=remote:http:$LOCALIP: (glob) (bundle1 !)
   remote: changegroup hook: HG_BUNDLE2=1 HG_HOOKNAME=changegroup HG_HOOKTYPE=changegroup HG_NODE=ba677d0156c1196c1a699fa53f390dcfc3ce3872 HG_NODE_LAST=ba677d0156c1196c1a699fa53f390dcfc3ce3872 HG_SOURCE=serve HG_TXNID=TXN:$ID$ HG_URL=remote:http:$LOCALIP: (glob) (bundle2 !)
   % serve errors
   $ hg rollback
   repository tip rolled back to revision 0 (undo serve)
 
 expect success, pre-d1b16a746db6 server supports the unbundle capability, but
 has no parameter
 
   $ cat <<EOF > notcapable-unbundleparam.py
   > from mercurial import extensions, httppeer
   > def capable(orig, self, name):
   >     if name == 'unbundle':
   >         return True
   >     return orig(self, name)
   > def uisetup(ui):
   >     extensions.wrapfunction(httppeer.httppeer, 'capable', capable)
   > EOF
   $ cp $HGRCPATH $HGRCPATH.orig
   $ cat <<EOF >> $HGRCPATH
   > [extensions]
   > notcapable-unbundleparam = `pwd`/notcapable-unbundleparam.py
   > EOF
   $ req
   pushing to http://localhost:$HGPORT/
   searching for changes
   remote: adding changesets
   remote: adding manifests
   remote: adding file changes
   remote: added 1 changesets with 1 changes to 1 files
   remote: phase-move: cb9a9f314b8b07ba71012fcdbc544b5a4d82ff5b:  draft -> public
   remote: phase-move: ba677d0156c1196c1a699fa53f390dcfc3ce3872:   -> public
   remote: changegroup hook: * (glob)
   % serve errors
   $ hg rollback
   repository tip rolled back to revision 0 (undo serve)
   $ mv $HGRCPATH.orig $HGRCPATH
 
 Test pushing to a publishing repository with a failing prepushkey hook
 
   $ cat > .hg/hgrc <<EOF
   > [web]
   > push_ssl = false
   > allow_push = *
   > [hooks]
   > prepushkey = sh -c "printenv.py prepushkey 1"
   > [devel]
   > legacy.exchange=phases
   > EOF
 
 #if bundle1
 Bundle1 works because a) phases are updated as part of changegroup application
 and b) client checks phases after the "unbundle" command. Since it sees no
 phase changes are necessary, it doesn't send the "pushkey" command and the
 prepushkey hook never has to fire.
 
   $ req
   pushing to http://localhost:$HGPORT/
   searching for changes
   remote: adding changesets
   remote: adding manifests
   remote: adding file changes
   remote: added 1 changesets with 1 changes to 1 files
   % serve errors
 
 #endif
 
 #if bundle2
 Bundle2 sends a "pushkey" bundle2 part. This runs as part of the transaction
 and fails the entire push.
   $ req
   pushing to http://localhost:$HGPORT/
   searching for changes
   remote: adding changesets
   remote: adding manifests
   remote: adding file changes
   remote: added 1 changesets with 1 changes to 1 files
   remote: prepushkey hook: HG_BUNDLE2=1 HG_HOOKNAME=prepushkey HG_HOOKTYPE=prepushkey HG_KEY=ba677d0156c1196c1a699fa53f390dcfc3ce3872 HG_NAMESPACE=phases HG_NEW=0 HG_NODE=ba677d0156c1196c1a699fa53f390dcfc3ce3872 HG_NODE_LAST=ba677d0156c1196c1a699fa53f390dcfc3ce3872 HG_OLD=1 HG_PENDING=$TESTTMP/test HG_PHASES_MOVED=1 HG_SOURCE=serve HG_TXNID=TXN:$ID$ HG_URL=remote:http:$LOCALIP: (glob)
   remote: pushkey-abort: prepushkey hook exited with status 1
   remote: transaction abort!
   remote: rollback completed
   abort: updating ba677d0156c1 to public failed
   % serve errors
   [255]
 
 #endif
 
 Now remove the failing prepushkey hook.
 
   $ cat >> .hg/hgrc <<EOF
   > [hooks]
   > prepushkey = sh -c "printenv.py prepushkey 0"
   > EOF
 
 We don't need to test bundle1 because it succeeded above.
 
 #if bundle2
   $ req
   pushing to http://localhost:$HGPORT/
   searching for changes
   remote: adding changesets
   remote: adding manifests
   remote: adding file changes
   remote: added 1 changesets with 1 changes to 1 files
   remote: prepushkey hook: HG_BUNDLE2=1 HG_HOOKNAME=prepushkey HG_HOOKTYPE=prepushkey HG_KEY=ba677d0156c1196c1a699fa53f390dcfc3ce3872 HG_NAMESPACE=phases HG_NEW=0 HG_NODE=ba677d0156c1196c1a699fa53f390dcfc3ce3872 HG_NODE_LAST=ba677d0156c1196c1a699fa53f390dcfc3ce3872 HG_OLD=1 HG_PENDING=$TESTTMP/test HG_PHASES_MOVED=1 HG_SOURCE=serve HG_TXNID=TXN:$ID$ HG_URL=remote:http:$LOCALIP: (glob)
   % serve errors
 #endif
 
   $ hg --config extensions.strip= strip -r 1:
   saved backup bundle to $TESTTMP/test/.hg/strip-backup/ba677d0156c1-eea704d7-backup.hg
 
 Now do a variant of the above, except on a non-publishing repository
 
   $ cat >> .hg/hgrc <<EOF
   > [phases]
   > publish = false
   > [hooks]
   > prepushkey = sh -c "printenv.py prepushkey 1"
   > EOF
 
 #if bundle1
   $ req
   pushing to http://localhost:$HGPORT/
   searching for changes
   remote: adding changesets
   remote: adding manifests
   remote: adding file changes
   remote: added 1 changesets with 1 changes to 1 files
   remote: prepushkey hook: HG_HOOKNAME=prepushkey HG_HOOKTYPE=prepushkey HG_KEY=ba677d0156c1196c1a699fa53f390dcfc3ce3872 HG_NAMESPACE=phases HG_NEW=0 HG_OLD=1
   remote: pushkey-abort: prepushkey hook exited with status 1
   updating ba677d0156c1 to public failed!
   % serve errors
 #endif
 
 #if bundle2
   $ req
   pushing to http://localhost:$HGPORT/
   searching for changes
   remote: adding changesets
   remote: adding manifests
   remote: adding file changes
   remote: added 1 changesets with 1 changes to 1 files
   remote: prepushkey hook: HG_BUNDLE2=1 HG_HOOKNAME=prepushkey HG_HOOKTYPE=prepushkey HG_KEY=ba677d0156c1196c1a699fa53f390dcfc3ce3872 HG_NAMESPACE=phases HG_NEW=0 HG_NODE=ba677d0156c1196c1a699fa53f390dcfc3ce3872 HG_NODE_LAST=ba677d0156c1196c1a699fa53f390dcfc3ce3872 HG_OLD=1 HG_PENDING=$TESTTMP/test HG_PHASES_MOVED=1 HG_SOURCE=serve HG_TXNID=TXN:$ID$ HG_URL=remote:http:$LOCALIP: (glob)
   remote: pushkey-abort: prepushkey hook exited with status 1
   remote: transaction abort!
   remote: rollback completed
   abort: updating ba677d0156c1 to public failed
   % serve errors
   [255]
 #endif
 
 Make phases updates work
 
   $ cat >> .hg/hgrc <<EOF
   > [hooks]
   > prepushkey = sh -c "printenv.py prepushkey 0"
   > EOF
 
 #if bundle1
   $ req
   pushing to http://localhost:$HGPORT/
   searching for changes
   no changes found
   remote: prepushkey hook: HG_HOOKNAME=prepushkey HG_HOOKTYPE=prepushkey HG_KEY=ba677d0156c1196c1a699fa53f390dcfc3ce3872 HG_NAMESPACE=phases HG_NEW=0 HG_OLD=1
   % serve errors
   [1]
 #endif
 
 #if bundle2
   $ req
   pushing to http://localhost:$HGPORT/
   searching for changes
   remote: adding changesets
   remote: adding manifests
   remote: adding file changes
   remote: added 1 changesets with 1 changes to 1 files
   remote: prepushkey hook: HG_BUNDLE2=1 HG_HOOKNAME=prepushkey HG_HOOKTYPE=prepushkey HG_KEY=ba677d0156c1196c1a699fa53f390dcfc3ce3872 HG_NAMESPACE=phases HG_NEW=0 HG_NODE=ba677d0156c1196c1a699fa53f390dcfc3ce3872 HG_NODE_LAST=ba677d0156c1196c1a699fa53f390dcfc3ce3872 HG_OLD=1 HG_PENDING=$TESTTMP/test HG_PHASES_MOVED=1 HG_SOURCE=serve HG_TXNID=TXN:$ID$ HG_URL=remote:http:$LOCALIP: (glob)
   % serve errors
 #endif
 
   $ hg --config extensions.strip= strip -r 1:
   saved backup bundle to $TESTTMP/test/.hg/strip-backup/ba677d0156c1-eea704d7-backup.hg
 
 #if bundle2
 
   $ cat > .hg/hgrc <<EOF
   > [web]
   > push_ssl = false
   > allow_push = *
   > [experimental]
   > httppostargs=true
   > EOF
   $ req
   pushing to http://localhost:$HGPORT/
   searching for changes
   remote: adding changesets
   remote: adding manifests
   remote: adding file changes
   remote: added 1 changesets with 1 changes to 1 files
   % serve errors
 
 #endif
 
   $ cd ..
+
+Pushing via hgwebdir works
+
+  $ hg init hgwebdir
+  $ cd hgwebdir
+  $ echo 0 > a
+  $ hg -q commit -A -m initial
+  $ cd ..
+
+  $ cat > web.conf << EOF
+  > [paths]
+  > / = *
+  > [web]
+  > push_ssl = false
+  > allow_push = *
+  > EOF
+
+  $ hg serve --web-conf web.conf -p $HGPORT -d --pid-file hg.pid
+  $ cat hg.pid > $DAEMON_PIDS
+
+  $ hg clone http://localhost:$HGPORT/hgwebdir hgwebdir-local
+  requesting all changes
+  adding changesets
+  adding manifests
+  adding file changes
+  added 1 changesets with 1 changes to 1 files
+  new changesets 98a3f8f02ba7
+  updating to branch default
+  1 files updated, 0 files merged, 0 files removed, 0 files unresolved
+  $ cd hgwebdir-local
+  $ echo commit > a
+  $ hg commit -m 'local commit'
+
+  $ hg push
+  pushing to http://localhost:$HGPORT/hgwebdir
+  searching for changes
+  remote: adding changesets
+  remote: adding manifests
+  remote: adding file changes
+  remote: added 1 changesets with 1 changes to 1 files
+
+  $ killdaemons.py
+
+  $ cd ..