hgweb: expose input stream on parsed WSGI request object

Our next step towards moving away from wsgirequest to our newer,
friendlier parsedrequest type is input stream access.

This commit exposes the input stream on the instance. Consumers
in the HTTP protocol server switch to it.

Because there were very few consumers of the input stream, we stopped
storing a reference to the input stream on wsgirequest directly. All
access now goes through parsedrequest. However, wsgirequest still
may read from this stream as part of cgi.parse(). So we still need to
create the stream from wsgirequest.

Differential Revision: https://phab.mercurial-scm.org/D2771

mercurial/hgweb/hgwebdir_mod.py

@@ -1,543 +1,544
 # 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
 
 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)
         return self.run_wsgi(wsgireq)
 
     def read_allowed(self, ui, wsgireq):
         """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 = wsgireq.env.get('REMOTE_USER')
 
         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 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):
         try:
             self.refresh()
 
             csp, nonce = cspvalues(self.ui)
             if 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)
 
             # a static file
             if virtual.startswith('static/') or 'static' in wsgireq.form:
                 if virtual.startswith('static/'):
                     fname = virtual[7:]
                 else:
                     fname = wsgireq.form['static'][0]
                 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, wsgireq)
                 return []
 
             # 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:
                     wsgireq.env['REPO_NAME'] = virtualrepo
                     # We have to re-parse because of updated environment
                     # variable.
                     # TODO this is kind of hacky and we should have a better
                     # way of doing this than with REPO_NAME side-effects.
-                    wsgireq.req = requestmod.parserequestfromenv(wsgireq.env)
+                    wsgireq.req = requestmod.parserequestfromenv(
+                        wsgireq.env, wsgireq.req.bodyfh)
                     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=""):
 
         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 rawentries(subdir="", **map):
 
             descend = self.ui.configbool('web', 'descend')
             collapse = self.ui.configbool('web', 'collapse')
             seenrepos = set()
             seendirs = set()
             for name, path in self.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(self.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 = self.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 self.read_allowed(u, wsgireq):
                     continue
 
                 # update time with local timezone
                 try:
                     r = hg.repository(self.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
 
         sortdefault = None, False
         def entries(sortcolumn="", descending=False, subdir="", **map):
             rows = rawentries(subdir=subdir, **map)
 
             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(self.stripecount)):
                 row['parity'] = parity
                 yield row
 
         self.refresh()
         sortable = ["name", "description", "contact", "lastchange"]
         sortcolumn, descending = sortdefault
         if 'sort' in wsgireq.form:
             sortcolumn = wsgireq.form['sort'][0]
             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)
 
         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, 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 url + '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

@@ -1,363 +1,374
 # 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 cgi
 import errno
 import socket
 import wsgiref.headers as wsgiheaders
 #import wsgiref.validate
 
 from .common import (
     ErrorResponse,
     HTTP_NOT_MODIFIED,
     statusmessage,
 )
 
 from ..thirdparty import (
     attr,
 )
 from .. import (
     pycompat,
     util,
 )
 
 shortcuts = {
     'cl': [('cmd', ['changelog']), ('rev', None)],
     'sl': [('cmd', ['shortlog']), ('rev', None)],
     'cs': [('cmd', ['changeset']), ('node', None)],
     'f': [('cmd', ['file']), ('filenode', None)],
     'fl': [('cmd', ['filelog']), ('filenode', None)],
     'fd': [('cmd', ['filediff']), ('node', None)],
     'fa': [('cmd', ['annotate']), ('filenode', None)],
     'mf': [('cmd', ['manifest']), ('manifest', None)],
     'ca': [('cmd', ['archive']), ('node', None)],
     'tags': [('cmd', ['tags'])],
     'tip': [('cmd', ['changeset']), ('node', ['tip'])],
     'static': [('cmd', ['static']), ('file', None)]
 }
 
 def normalize(form):
     # first expand the shortcuts
     for k in shortcuts:
         if k in form:
             for name, value in shortcuts[k]:
                 if value is None:
                     value = form[k]
                 form[name] = value
             del form[k]
     # And strip the values
     bytesform = {}
     for k, v in form.iteritems():
         bytesform[pycompat.bytesurl(k)] = [
             pycompat.bytesurl(i.strip()) for i in v]
     return bytesform
 
 @attr.s(frozen=True)
 class parsedrequest(object):
-    """Represents a parsed WSGI request / static HTTP request parameters."""
+    """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()
     # WSGI application path.
     apppath = attr.ib()
     # List of path parts to be used for dispatch.
     dispatchparts = attr.ib()
     # URL path component (no query string) used for dispatch.
     dispatchpath = attr.ib()
     # Whether there is a path component to this request. This can be true
     # when ``dispatchpath`` is empty due to REPO_NAME muckery.
     havepathinfo = attr.ib()
     # Raw query string (part after "?" in URL).
     querystring = attr.ib()
     # List of 2-tuples of query string arguments.
     querystringlist = attr.ib()
     # Dict of query string arguments. Values are lists with at least 1 item.
     querystringdict = 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):
+def parserequestfromenv(env, bodyfh):
     """Parse URL components from environment variables.
 
     WSGI defines request attributes via environment variables. This function
     parses the environment variables into a data structure.
     """
     # PEP-0333 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()}
 
     # 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
 
     def addport(s):
         if env['wsgi.url_scheme'] == 'https':
             if env['SERVER_PORT'] != '443':
                 s += ':' + env['SERVER_PORT']
         else:
             if env['SERVER_PORT'] != '80':
                 s += ':' + env['SERVER_PORT']
 
         return s
 
     if env.get('HTTP_HOST'):
         fullurl += env['HTTP_HOST']
     else:
         fullurl += env['SERVER_NAME']
         fullurl = addport(fullurl)
 
     advertisedfullurl += env['SERVER_NAME']
     advertisedfullurl = addport(advertisedfullurl)
 
     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', ''))
     advertisedfullurl += util.urlreq.quote(env.get('PATH_INFO', ''))
 
     if env.get('QUERY_STRING'):
         fullurl += '?' + env['QUERY_STRING']
         advertisedfullurl += '?' + env['QUERY_STRING']
 
     # When dispatching requests, we look at the URL components (PATH_INFO
     # and QUERY_STRING) after the application root (SCRIPT_NAME). But hgwebdir
     # has the concept of "virtual" repositories. This is defined via REPO_NAME.
     # If REPO_NAME is defined, we append it to SCRIPT_NAME to form a new app
     # root. We also exclude its path components from PATH_INFO when resolving
     # the dispatch path.
 
     apppath = env['SCRIPT_NAME']
 
     if env.get('REPO_NAME'):
         if not apppath.endswith('/'):
             apppath += '/'
 
         apppath += env.get('REPO_NAME')
 
     if 'PATH_INFO' in env:
         dispatchparts = env['PATH_INFO'].strip('/').split('/')
 
         # Strip out repo parts.
         repoparts = env.get('REPO_NAME', '').split('/')
         if dispatchparts[:len(repoparts)] == repoparts:
             dispatchparts = dispatchparts[len(repoparts):]
     else:
         dispatchparts = []
 
     dispatchpath = '/'.join(dispatchparts)
 
     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.
     querystringlist = util.urlreq.parseqsl(querystring, keep_blank_values=True)
 
     querystringdict = {}
     for k, v in querystringlist:
         if k in querystringdict:
             querystringdict[k].append(v)
         else:
             querystringdict[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,
                          apppath=apppath,
                          dispatchparts=dispatchparts, dispatchpath=dispatchpath,
                          havepathinfo='PATH_INFO' in env,
                          querystring=querystring,
                          querystringlist=querystringlist,
                          querystringdict=querystringdict,
-                         headers=headers)
+                         headers=headers,
+                         bodyfh=bodyfh)
 
 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):
         version = wsgienv[r'wsgi.version']
         if (version < (1, 0)) or (version >= (2, 0)):
             raise RuntimeError("Unknown and unsupported WSGI version %d.%d"
                                % version)
-        self.inp = wsgienv[r'wsgi.input']
+
+        inp = wsgienv[r'wsgi.input']
 
         if r'HTTP_CONTENT_LENGTH' in wsgienv:
-            self.inp = util.cappedreader(self.inp,
-                                         int(wsgienv[r'HTTP_CONTENT_LENGTH']))
+            inp = util.cappedreader(inp, int(wsgienv[r'HTTP_CONTENT_LENGTH']))
         elif r'CONTENT_LENGTH' in wsgienv:
-            self.inp = util.cappedreader(self.inp,
-                                         int(wsgienv[r'CONTENT_LENGTH']))
+            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.form = normalize(cgi.parse(self.inp,
+        self.form = normalize(cgi.parse(inp,
                                         self.env,
                                         keep_blank_values=1))
         self._start_response = start_response
         self.server_write = None
         self.headers = []
 
-        self.req = parserequestfromenv(wsgienv)
+        self.req = parserequestfromenv(wsgienv, inp)
 
     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)
                 if status.code == HTTP_NOT_MODIFIED:
                     # RFC 2616 Section 10.3.5: 304 Not Modified has cases where
                     # it MUST NOT include any headers other than these and no
                     # body
                     self.headers = [(k, v) for (k, v) in self.headers if
                                     k in ('Date', 'ETag', 'Expires',
                                           'Cache-Control', 'Vary')]
                 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.inp, util.cappedreader):
+                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.inp, util.cappedreader)
+                assert isinstance(self.req.bodyfh, util.cappedreader)
                 while True:
-                    chunk = self.inp.read(32768)
+                    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

mercurial/wireprotoserver.py

@@ -1,649 +1,649
 # Copyright 21 May 2005 - (c) 2005 Jake Edge <[e-mail]>
 # Copyright 2005-2007 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 contextlib
 import struct
 import sys
 import threading
 
 from .i18n import _
 from . import (
     encoding,
     error,
     hook,
     pycompat,
     util,
     wireproto,
     wireprototypes,
 )
 
 stringio = util.stringio
 
 urlerr = util.urlerr
 urlreq = util.urlreq
 
 HTTP_OK = 200
 
 HGTYPE = 'application/mercurial-0.1'
 HGTYPE2 = 'application/mercurial-0.2'
 HGERRTYPE = 'application/hg-error'
 
 SSHV1 = wireprototypes.SSHV1
 SSHV2 = wireprototypes.SSHV2
 
 def decodevaluefromheaders(req, headerprefix):
     """Decode a long value from multiple HTTP request headers.
 
     Returns the value as a bytes, not a str.
     """
     chunks = []
     i = 1
     while True:
         v = req.headers.get(b'%s-%d' % (headerprefix, i))
         if v is None:
             break
         chunks.append(pycompat.bytesurl(v))
         i += 1
 
     return ''.join(chunks)
 
 class httpv1protocolhandler(wireprototypes.baseprotocolhandler):
     def __init__(self, wsgireq, req, ui, checkperm):
         self._wsgireq = wsgireq
         self._req = req
         self._ui = ui
         self._checkperm = checkperm
 
     @property
     def name(self):
         return 'http-v1'
 
     def getargs(self, args):
         knownargs = self._args()
         data = {}
         keys = args.split()
         for k in keys:
             if k == '*':
                 star = {}
                 for key in knownargs.keys():
                     if key != 'cmd' and key not in keys:
                         star[key] = knownargs[key][0]
                 data['*'] = star
             else:
                 data[k] = knownargs[k][0]
         return [data[k] for k in keys]
 
     def _args(self):
         args = util.rapply(pycompat.bytesurl, self._wsgireq.form.copy())
         postlen = int(self._req.headers.get(b'X-HgArgs-Post', 0))
         if postlen:
             args.update(urlreq.parseqs(
-                self._wsgireq.inp.read(postlen), keep_blank_values=True))
+                self._req.bodyfh.read(postlen), keep_blank_values=True))
             return args
 
         argvalue = decodevaluefromheaders(self._req, b'X-HgArg')
         args.update(urlreq.parseqs(argvalue, keep_blank_values=True))
         return args
 
     def forwardpayload(self, fp):
         # Existing clients *always* send Content-Length.
         length = int(self._req.headers[b'Content-Length'])
 
         # If httppostargs is used, we need to read Content-Length
         # minus the amount that was consumed by args.
         length -= int(self._req.headers.get(b'X-HgArgs-Post', 0))
-        for s in util.filechunkiter(self._wsgireq.inp, limit=length):
+        for s in util.filechunkiter(self._req.bodyfh, limit=length):
             fp.write(s)
 
     @contextlib.contextmanager
     def mayberedirectstdio(self):
         oldout = self._ui.fout
         olderr = self._ui.ferr
 
         out = util.stringio()
 
         try:
             self._ui.fout = out
             self._ui.ferr = out
             yield out
         finally:
             self._ui.fout = oldout
             self._ui.ferr = olderr
 
     def client(self):
         return 'remote:%s:%s:%s' % (
             self._wsgireq.env.get('wsgi.url_scheme') or 'http',
             urlreq.quote(self._wsgireq.env.get('REMOTE_HOST', '')),
             urlreq.quote(self._wsgireq.env.get('REMOTE_USER', '')))
 
     def addcapabilities(self, repo, caps):
         caps.append('httpheader=%d' %
                     repo.ui.configint('server', 'maxhttpheaderlen'))
         if repo.ui.configbool('experimental', 'httppostargs'):
             caps.append('httppostargs')
 
         # FUTURE advertise 0.2rx once support is implemented
         # FUTURE advertise minrx and mintx after consulting config option
         caps.append('httpmediatype=0.1rx,0.1tx,0.2tx')
 
         compengines = wireproto.supportedcompengines(repo.ui, util.SERVERROLE)
         if compengines:
             comptypes = ','.join(urlreq.quote(e.wireprotosupport().name)
                                  for e in compengines)
             caps.append('compression=%s' % comptypes)
 
         return caps
 
     def checkperm(self, perm):
         return self._checkperm(perm)
 
 # This method exists mostly so that extensions like remotefilelog can
 # disable a kludgey legacy method only over http. As of early 2018,
 # there are no other known users, so with any luck we can discard this
 # hook if remotefilelog becomes a first-party extension.
 def iscmd(cmd):
     return cmd in wireproto.commands
 
 def handlewsgirequest(rctx, wsgireq, req, checkperm):
     """Possibly process a wire protocol request.
 
     If the current request is a wire protocol request, the request is
     processed by this function.
 
     ``wsgireq`` is a ``wsgirequest`` instance.
     ``req`` is a ``parsedrequest`` instance.
 
     Returns a 2-tuple of (bool, response) where the 1st element indicates
     whether the request was handled and the 2nd element is a return
     value for a WSGI application (often a generator of bytes).
     """
     # Avoid cycle involving hg module.
     from .hgweb import common as hgwebcommon
 
     repo = rctx.repo
 
     # HTTP version 1 wire protocol requests are denoted by a "cmd" query
     # string parameter. If it isn't present, this isn't a wire protocol
     # request.
     if 'cmd' not in req.querystringdict:
         return False, None
 
     cmd = req.querystringdict['cmd'][0]
 
     # The "cmd" request parameter is used by both the wire protocol and hgweb.
     # While not all wire protocol commands are available for all transports,
     # if we see a "cmd" value that resembles a known wire protocol command, we
     # route it to a protocol handler. This is better than routing possible
     # wire protocol requests to hgweb because it prevents hgweb from using
     # known wire protocol commands and it is less confusing for machine
     # clients.
     if not iscmd(cmd):
         return False, None
 
     # The "cmd" query string argument is only valid on the root path of the
     # repo. e.g. ``/?cmd=foo``, ``/repo?cmd=foo``. URL paths within the repo
     # like ``/blah?cmd=foo`` are not allowed. So don't recognize the request
     # in this case. We send an HTTP 404 for backwards compatibility reasons.
     if req.dispatchpath:
         res = _handlehttperror(
             hgwebcommon.ErrorResponse(hgwebcommon.HTTP_NOT_FOUND), wsgireq,
             req)
 
         return True, res
 
     proto = httpv1protocolhandler(wsgireq, req, repo.ui,
                                   lambda perm: checkperm(rctx, wsgireq, perm))
 
     # The permissions checker should be the only thing that can raise an
     # ErrorResponse. It is kind of a layer violation to catch an hgweb
     # exception here. So consider refactoring into a exception type that
     # is associated with the wire protocol.
     try:
         res = _callhttp(repo, wsgireq, req, proto, cmd)
     except hgwebcommon.ErrorResponse as e:
         res = _handlehttperror(e, wsgireq, req)
 
     return True, res
 
 def _httpresponsetype(ui, req, prefer_uncompressed):
     """Determine the appropriate response type and compression settings.
 
     Returns a tuple of (mediatype, compengine, engineopts).
     """
     # Determine the response media type and compression engine based
     # on the request parameters.
     protocaps = decodevaluefromheaders(req, 'X-HgProto').split(' ')
 
     if '0.2' in protocaps:
         # All clients are expected to support uncompressed data.
         if prefer_uncompressed:
             return HGTYPE2, util._noopengine(), {}
 
         # Default as defined by wire protocol spec.
         compformats = ['zlib', 'none']
         for cap in protocaps:
             if cap.startswith('comp='):
                 compformats = cap[5:].split(',')
                 break
 
         # Now find an agreed upon compression format.
         for engine in wireproto.supportedcompengines(ui, util.SERVERROLE):
             if engine.wireprotosupport().name in compformats:
                 opts = {}
                 level = ui.configint('server', '%slevel' % engine.name())
                 if level is not None:
                     opts['level'] = level
 
                 return HGTYPE2, engine, opts
 
         # No mutually supported compression format. Fall back to the
         # legacy protocol.
 
     # Don't allow untrusted settings because disabling compression or
     # setting a very high compression level could lead to flooding
     # the server's network or CPU.
     opts = {'level': ui.configint('server', 'zliblevel')}
     return HGTYPE, util.compengines['zlib'], opts
 
 def _callhttp(repo, wsgireq, req, proto, cmd):
     def genversion2(gen, engine, engineopts):
         # application/mercurial-0.2 always sends a payload header
         # identifying the compression engine.
         name = engine.wireprotosupport().name
         assert 0 < len(name) < 256
         yield struct.pack('B', len(name))
         yield name
 
         for chunk in gen:
             yield chunk
 
     if not wireproto.commands.commandavailable(cmd, proto):
         wsgireq.respond(HTTP_OK, HGERRTYPE,
                         body=_('requested wire protocol command is not '
                                'available over HTTP'))
         return []
 
     proto.checkperm(wireproto.commands[cmd].permission)
 
     rsp = wireproto.dispatch(repo, proto, cmd)
 
     if isinstance(rsp, bytes):
         wsgireq.respond(HTTP_OK, HGTYPE, body=rsp)
         return []
     elif isinstance(rsp, wireprototypes.bytesresponse):
         wsgireq.respond(HTTP_OK, HGTYPE, body=rsp.data)
         return []
     elif isinstance(rsp, wireprototypes.streamreslegacy):
         gen = rsp.gen
         wsgireq.respond(HTTP_OK, HGTYPE)
         return gen
     elif isinstance(rsp, wireprototypes.streamres):
         gen = rsp.gen
 
         # This code for compression should not be streamres specific. It
         # is here because we only compress streamres at the moment.
         mediatype, engine, engineopts = _httpresponsetype(
             repo.ui, req, rsp.prefer_uncompressed)
         gen = engine.compressstream(gen, engineopts)
 
         if mediatype == HGTYPE2:
             gen = genversion2(gen, engine, engineopts)
 
         wsgireq.respond(HTTP_OK, mediatype)
         return gen
     elif isinstance(rsp, wireprototypes.pushres):
         rsp = '%d\n%s' % (rsp.res, rsp.output)
         wsgireq.respond(HTTP_OK, HGTYPE, body=rsp)
         return []
     elif isinstance(rsp, wireprototypes.pusherr):
         rsp = '0\n%s\n' % rsp.res
         wsgireq.respond(HTTP_OK, HGTYPE, body=rsp)
         return []
     elif isinstance(rsp, wireprototypes.ooberror):
         rsp = rsp.message
         wsgireq.respond(HTTP_OK, HGERRTYPE, body=rsp)
         return []
     raise error.ProgrammingError('hgweb.protocol internal failure', rsp)
 
 def _handlehttperror(e, wsgireq, req):
     """Called when an ErrorResponse is raised during HTTP request processing."""
 
     # TODO This response body assumes the failed command was
     # "unbundle." That assumption is not always valid.
     wsgireq.respond(e, HGTYPE, body='0\n%s\n' % pycompat.bytestr(e))
 
     return ''
 
 def _sshv1respondbytes(fout, value):
     """Send a bytes response for protocol version 1."""
     fout.write('%d\n' % len(value))
     fout.write(value)
     fout.flush()
 
 def _sshv1respondstream(fout, source):
     write = fout.write
     for chunk in source.gen:
         write(chunk)
     fout.flush()
 
 def _sshv1respondooberror(fout, ferr, rsp):
     ferr.write(b'%s\n-\n' % rsp)
     ferr.flush()
     fout.write(b'\n')
     fout.flush()
 
 class sshv1protocolhandler(wireprototypes.baseprotocolhandler):
     """Handler for requests services via version 1 of SSH protocol."""
     def __init__(self, ui, fin, fout):
         self._ui = ui
         self._fin = fin
         self._fout = fout
 
     @property
     def name(self):
         return wireprototypes.SSHV1
 
     def getargs(self, args):
         data = {}
         keys = args.split()
         for n in xrange(len(keys)):
             argline = self._fin.readline()[:-1]
             arg, l = argline.split()
             if arg not in keys:
                 raise error.Abort(_("unexpected parameter %r") % arg)
             if arg == '*':
                 star = {}
                 for k in xrange(int(l)):
                     argline = self._fin.readline()[:-1]
                     arg, l = argline.split()
                     val = self._fin.read(int(l))
                     star[arg] = val
                 data['*'] = star
             else:
                 val = self._fin.read(int(l))
                 data[arg] = val
         return [data[k] for k in keys]
 
     def forwardpayload(self, fpout):
         # We initially send an empty response. This tells the client it is
         # OK to start sending data. If a client sees any other response, it
         # interprets it as an error.
         _sshv1respondbytes(self._fout, b'')
 
         # The file is in the form:
         #
         # <chunk size>\n<chunk>
         # ...
         # 0\n
         count = int(self._fin.readline())
         while count:
             fpout.write(self._fin.read(count))
             count = int(self._fin.readline())
 
     @contextlib.contextmanager
     def mayberedirectstdio(self):
         yield None
 
     def client(self):
         client = encoding.environ.get('SSH_CLIENT', '').split(' ', 1)[0]
         return 'remote:ssh:' + client
 
     def addcapabilities(self, repo, caps):
         return caps
 
     def checkperm(self, perm):
         pass
 
 class sshv2protocolhandler(sshv1protocolhandler):
     """Protocol handler for version 2 of the SSH protocol."""
 
     @property
     def name(self):
         return wireprototypes.SSHV2
 
 def _runsshserver(ui, repo, fin, fout, ev):
     # This function operates like a state machine of sorts. The following
     # states are defined:
     #
     # protov1-serving
     #    Server is in protocol version 1 serving mode. Commands arrive on
     #    new lines. These commands are processed in this state, one command
     #    after the other.
     #
     # protov2-serving
     #    Server is in protocol version 2 serving mode.
     #
     # upgrade-initial
     #    The server is going to process an upgrade request.
     #
     # upgrade-v2-filter-legacy-handshake
     #    The protocol is being upgraded to version 2. The server is expecting
     #    the legacy handshake from version 1.
     #
     # upgrade-v2-finish
     #    The upgrade to version 2 of the protocol is imminent.
     #
     # shutdown
     #    The server is shutting down, possibly in reaction to a client event.
     #
     # And here are their transitions:
     #
     # protov1-serving -> shutdown
     #    When server receives an empty request or encounters another
     #    error.
     #
     # protov1-serving -> upgrade-initial
     #    An upgrade request line was seen.
     #
     # upgrade-initial -> upgrade-v2-filter-legacy-handshake
     #    Upgrade to version 2 in progress. Server is expecting to
     #    process a legacy handshake.
     #
     # upgrade-v2-filter-legacy-handshake -> shutdown
     #    Client did not fulfill upgrade handshake requirements.
     #
     # upgrade-v2-filter-legacy-handshake -> upgrade-v2-finish
     #    Client fulfilled version 2 upgrade requirements. Finishing that
     #    upgrade.
     #
     # upgrade-v2-finish -> protov2-serving
     #    Protocol upgrade to version 2 complete. Server can now speak protocol
     #    version 2.
     #
     # protov2-serving -> protov1-serving
     #    Ths happens by default since protocol version 2 is the same as
     #    version 1 except for the handshake.
 
     state = 'protov1-serving'
     proto = sshv1protocolhandler(ui, fin, fout)
     protoswitched = False
 
     while not ev.is_set():
         if state == 'protov1-serving':
             # Commands are issued on new lines.
             request = fin.readline()[:-1]
 
             # Empty lines signal to terminate the connection.
             if not request:
                 state = 'shutdown'
                 continue
 
             # It looks like a protocol upgrade request. Transition state to
             # handle it.
             if request.startswith(b'upgrade '):
                 if protoswitched:
                     _sshv1respondooberror(fout, ui.ferr,
                                           b'cannot upgrade protocols multiple '
                                           b'times')
                     state = 'shutdown'
                     continue
 
                 state = 'upgrade-initial'
                 continue
 
             available = wireproto.commands.commandavailable(request, proto)
 
             # This command isn't available. Send an empty response and go
             # back to waiting for a new command.
             if not available:
                 _sshv1respondbytes(fout, b'')
                 continue
 
             rsp = wireproto.dispatch(repo, proto, request)
 
             if isinstance(rsp, bytes):
                 _sshv1respondbytes(fout, rsp)
             elif isinstance(rsp, wireprototypes.bytesresponse):
                 _sshv1respondbytes(fout, rsp.data)
             elif isinstance(rsp, wireprototypes.streamres):
                 _sshv1respondstream(fout, rsp)
             elif isinstance(rsp, wireprototypes.streamreslegacy):
                 _sshv1respondstream(fout, rsp)
             elif isinstance(rsp, wireprototypes.pushres):
                 _sshv1respondbytes(fout, b'')
                 _sshv1respondbytes(fout, b'%d' % rsp.res)
             elif isinstance(rsp, wireprototypes.pusherr):
                 _sshv1respondbytes(fout, rsp.res)
             elif isinstance(rsp, wireprototypes.ooberror):
                 _sshv1respondooberror(fout, ui.ferr, rsp.message)
             else:
                 raise error.ProgrammingError('unhandled response type from '
                                              'wire protocol command: %s' % rsp)
 
         # For now, protocol version 2 serving just goes back to version 1.
         elif state == 'protov2-serving':
             state = 'protov1-serving'
             continue
 
         elif state == 'upgrade-initial':
             # We should never transition into this state if we've switched
             # protocols.
             assert not protoswitched
             assert proto.name == wireprototypes.SSHV1
 
             # Expected: upgrade <token> <capabilities>
             # If we get something else, the request is malformed. It could be
             # from a future client that has altered the upgrade line content.
             # We treat this as an unknown command.
             try:
                 token, caps = request.split(b' ')[1:]
             except ValueError:
                 _sshv1respondbytes(fout, b'')
                 state = 'protov1-serving'
                 continue
 
             # Send empty response if we don't support upgrading protocols.
             if not ui.configbool('experimental', 'sshserver.support-v2'):
                 _sshv1respondbytes(fout, b'')
                 state = 'protov1-serving'
                 continue
 
             try:
                 caps = urlreq.parseqs(caps)
             except ValueError:
                 _sshv1respondbytes(fout, b'')
                 state = 'protov1-serving'
                 continue
 
             # We don't see an upgrade request to protocol version 2. Ignore
             # the upgrade request.
             wantedprotos = caps.get(b'proto', [b''])[0]
             if SSHV2 not in wantedprotos:
                 _sshv1respondbytes(fout, b'')
                 state = 'protov1-serving'
                 continue
 
             # It looks like we can honor this upgrade request to protocol 2.
             # Filter the rest of the handshake protocol request lines.
             state = 'upgrade-v2-filter-legacy-handshake'
             continue
 
         elif state == 'upgrade-v2-filter-legacy-handshake':
             # Client should have sent legacy handshake after an ``upgrade``
             # request. Expected lines:
             #
             #    hello
             #    between
             #    pairs 81
             #    0000...-0000...
 
             ok = True
             for line in (b'hello', b'between', b'pairs 81'):
                 request = fin.readline()[:-1]
 
                 if request != line:
                     _sshv1respondooberror(fout, ui.ferr,
                                           b'malformed handshake protocol: '
                                           b'missing %s' % line)
                     ok = False
                     state = 'shutdown'
                     break
 
             if not ok:
                 continue
 
             request = fin.read(81)
             if request != b'%s-%s' % (b'0' * 40, b'0' * 40):
                 _sshv1respondooberror(fout, ui.ferr,
                                       b'malformed handshake protocol: '
                                       b'missing between argument value')
                 state = 'shutdown'
                 continue
 
             state = 'upgrade-v2-finish'
             continue
 
         elif state == 'upgrade-v2-finish':
             # Send the upgrade response.
             fout.write(b'upgraded %s %s\n' % (token, SSHV2))
             servercaps = wireproto.capabilities(repo, proto)
             rsp = b'capabilities: %s' % servercaps.data
             fout.write(b'%d\n%s\n' % (len(rsp), rsp))
             fout.flush()
 
             proto = sshv2protocolhandler(ui, fin, fout)
             protoswitched = True
 
             state = 'protov2-serving'
             continue
 
         elif state == 'shutdown':
             break
 
         else:
             raise error.ProgrammingError('unhandled ssh server state: %s' %
                                          state)
 
 class sshserver(object):
     def __init__(self, ui, repo, logfh=None):
         self._ui = ui
         self._repo = repo
         self._fin = ui.fin
         self._fout = ui.fout
 
         # Log write I/O to stdout and stderr if configured.
         if logfh:
             self._fout = util.makeloggingfileobject(
                 logfh, self._fout, 'o', logdata=True)
             ui.ferr = util.makeloggingfileobject(
                 logfh, ui.ferr, 'e', logdata=True)
 
         hook.redirect(True)
         ui.fout = repo.ui.fout = ui.ferr
 
         # Prevent insertion/deletion of CRs
         util.setbinary(self._fin)
         util.setbinary(self._fout)
 
     def serve_forever(self):
         self.serveuntil(threading.Event())
         sys.exit(0)
 
     def serveuntil(self, ev):
         """Serve until a threading.Event is set."""
         _runsshserver(self._ui, self._repo, self._fin, self._fout, ev)