hgweb: make parsedrequest part of wsgirequest

This is kind of ugly. But an upcoming commit will teach parsedrequest
about the input stream. Because the input stream is global state and
can't be accessed without side-effects, we need to take actions to
ensure that multiple consumers don't read from it independently. The
easiest way to do this is for one object to hold a reference to both
items having access to the input stream so that when a copy is made,
we can remove the attribute from the other instance.

So we create our parsed request instance from the wsgirequest
constructor and hold a reference to it there. This is better than
our new type holding a reference to wsgirequest because all the
code for managing access will be temporary and we shouldn't pollute
parsedrequest with this ugly history.

Differential Revision: https://phab.mercurial-scm.org/D2770

mercurial/hgweb/hgweb_mod.py

@@ -1,438 +1,438 b''
 # hgweb/hgweb_mod.py - Web interface for a repository.
 #
 # 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 os
 
 from .common import (
     ErrorResponse,
     HTTP_BAD_REQUEST,
     HTTP_NOT_FOUND,
     HTTP_NOT_MODIFIED,
     HTTP_OK,
     HTTP_SERVER_ERROR,
     caching,
     cspvalues,
     permhooks,
 )
 
 from .. import (
     encoding,
     error,
     formatter,
     hg,
     hook,
     profiling,
     pycompat,
     repoview,
     templatefilters,
     templater,
     ui as uimod,
     util,
     wireprotoserver,
 )
 
 from . import (
     request as requestmod,
     webcommands,
     webutil,
     wsgicgi,
 )
 
 archivespecs = util.sortdict((
     ('zip', ('application/zip', 'zip', '.zip', None)),
     ('gz', ('application/x-gzip', 'tgz', '.tar.gz', None)),
     ('bz2', ('application/x-bzip2', 'tbz2', '.tar.bz2', None)),
 ))
 
 def getstyle(req, configfn, templatepath):
     fromreq = req.form.get('style', [None])[0]
     styles = (
         fromreq,
         configfn('web', 'style'),
         'paper',
     )
     return styles, templater.stylemap(styles, templatepath)
 
 def makebreadcrumb(url, prefix=''):
     '''Return a 'URL breadcrumb' list
 
     A 'URL breadcrumb' is a list of URL-name pairs,
     corresponding to each of the path items on a URL.
     This can be used to create path navigation entries.
     '''
     if url.endswith('/'):
         url = url[:-1]
     if prefix:
         url = '/' + prefix + url
     relpath = url
     if relpath.startswith('/'):
         relpath = relpath[1:]
 
     breadcrumb = []
     urlel = url
     pathitems = [''] + relpath.split('/')
     for pathel in reversed(pathitems):
         if not pathel or not urlel:
             break
         breadcrumb.append({'url': urlel, 'name': pathel})
         urlel = os.path.dirname(urlel)
     return reversed(breadcrumb)
 
 class requestcontext(object):
     """Holds state/context for an individual request.
 
     Servers can be multi-threaded. Holding state on the WSGI application
     is prone to race conditions. Instances of this class exist to hold
     mutable and race-free state for requests.
     """
     def __init__(self, app, repo):
         self.repo = repo
         self.reponame = app.reponame
 
         self.archivespecs = archivespecs
 
         self.maxchanges = self.configint('web', 'maxchanges')
         self.stripecount = self.configint('web', 'stripes')
         self.maxshortchanges = self.configint('web', 'maxshortchanges')
         self.maxfiles = self.configint('web', 'maxfiles')
         self.allowpull = self.configbool('web', 'allow-pull')
 
         # we use untrusted=False to prevent a repo owner from using
         # web.templates in .hg/hgrc to get access to any file readable
         # by the user running the CGI script
         self.templatepath = self.config('web', 'templates', untrusted=False)
 
         # This object is more expensive to build than simple config values.
         # It is shared across requests. The app will replace the object
         # if it is updated. Since this is a reference and nothing should
         # modify the underlying object, it should be constant for the lifetime
         # of the request.
         self.websubtable = app.websubtable
 
         self.csp, self.nonce = cspvalues(self.repo.ui)
 
     # Trust the settings from the .hg/hgrc files by default.
     def config(self, section, name, default=uimod._unset, untrusted=True):
         return self.repo.ui.config(section, name, default,
                                    untrusted=untrusted)
 
     def configbool(self, section, name, default=uimod._unset, untrusted=True):
         return self.repo.ui.configbool(section, name, default,
                                        untrusted=untrusted)
 
     def configint(self, section, name, default=uimod._unset, untrusted=True):
         return self.repo.ui.configint(section, name, default,
                                       untrusted=untrusted)
 
     def configlist(self, section, name, default=uimod._unset, untrusted=True):
         return self.repo.ui.configlist(section, name, default,
                                        untrusted=untrusted)
 
     def archivelist(self, nodeid):
         allowed = self.configlist('web', 'allow_archive')
         for typ, spec in self.archivespecs.iteritems():
             if typ in allowed or self.configbool('web', 'allow%s' % typ):
                 yield {'type': typ, 'extension': spec[2], 'node': nodeid}
 
     def templater(self, wsgireq, req):
         # determine scheme, port and server name
         # this is needed to create absolute urls
         logourl = self.config('web', 'logourl')
         logoimg = self.config('web', 'logoimg')
         staticurl = (self.config('web', 'staticurl')
                      or req.apppath + '/static/')
         if not staticurl.endswith('/'):
             staticurl += '/'
 
         # some functions for the templater
 
         def motd(**map):
             yield self.config('web', 'motd')
 
         # figure out which style to use
 
         vars = {}
         styles, (style, mapfile) = getstyle(wsgireq, self.config,
                                             self.templatepath)
         if style == styles[0]:
             vars['style'] = style
 
         sessionvars = webutil.sessionvars(vars, '?')
 
         if not self.reponame:
             self.reponame = (self.config('web', 'name', '')
                              or wsgireq.env.get('REPO_NAME')
                              or req.apppath or self.repo.root)
 
         def websubfilter(text):
             return templatefilters.websub(text, self.websubtable)
 
         # create the templater
         # TODO: export all keywords: defaults = templatekw.keywords.copy()
         defaults = {
             'url': req.apppath + '/',
             'logourl': logourl,
             'logoimg': logoimg,
             'staticurl': staticurl,
             'urlbase': req.advertisedbaseurl,
             'repo': self.reponame,
             'encoding': encoding.encoding,
             'motd': motd,
             'sessionvars': sessionvars,
             'pathdef': makebreadcrumb(req.apppath),
             'style': style,
             'nonce': self.nonce,
         }
         tres = formatter.templateresources(self.repo.ui, self.repo)
         tmpl = templater.templater.frommapfile(mapfile,
                                                filters={'websub': websubfilter},
                                                defaults=defaults,
                                                resources=tres)
         return tmpl
 
 
 class hgweb(object):
     """HTTP server for individual repositories.
 
     Instances of this class serve HTTP responses for a particular
     repository.
 
     Instances are typically used as WSGI applications.
 
     Some servers are multi-threaded. On these servers, there may
     be multiple active threads inside __call__.
     """
     def __init__(self, repo, name=None, baseui=None):
         if isinstance(repo, str):
             if baseui:
                 u = baseui.copy()
             else:
                 u = uimod.ui.load()
             r = hg.repository(u, repo)
         else:
             # we trust caller to give us a private copy
             r = repo
 
         r.ui.setconfig('ui', 'report_untrusted', 'off', 'hgweb')
         r.baseui.setconfig('ui', 'report_untrusted', 'off', 'hgweb')
         r.ui.setconfig('ui', 'nontty', 'true', 'hgweb')
         r.baseui.setconfig('ui', 'nontty', 'true', 'hgweb')
         # resolve file patterns relative to repo root
         r.ui.setconfig('ui', 'forcecwd', r.root, 'hgweb')
         r.baseui.setconfig('ui', 'forcecwd', r.root, 'hgweb')
         # displaying bundling progress bar while serving feel wrong and may
         # break some wsgi implementation.
         r.ui.setconfig('progress', 'disable', 'true', 'hgweb')
         r.baseui.setconfig('progress', 'disable', 'true', 'hgweb')
         self._repos = [hg.cachedlocalrepo(self._webifyrepo(r))]
         self._lastrepo = self._repos[0]
         hook.redirect(True)
         self.reponame = name
 
     def _webifyrepo(self, repo):
         repo = getwebview(repo)
         self.websubtable = webutil.getwebsubs(repo)
         return repo
 
     @contextlib.contextmanager
     def _obtainrepo(self):
         """Obtain a repo unique to the caller.
 
         Internally we maintain a stack of cachedlocalrepo instances
         to be handed out. If one is available, we pop it and return it,
         ensuring it is up to date in the process. If one is not available,
         we clone the most recently used repo instance and return it.
 
         It is currently possible for the stack to grow without bounds
         if the server allows infinite threads. However, servers should
         have a thread limit, thus establishing our limit.
         """
         if self._repos:
             cached = self._repos.pop()
             r, created = cached.fetch()
         else:
             cached = self._lastrepo.copy()
             r, created = cached.fetch()
         if created:
             r = self._webifyrepo(r)
 
         self._lastrepo = cached
         self.mtime = cached.mtime
         try:
             yield r
         finally:
             self._repos.append(cached)
 
     def run(self):
         """Start a server from CGI environment.
 
         Modern servers should be using WSGI and should avoid this
         method, if possible.
         """
         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):
         """Run the WSGI application.
 
         This may be called by multiple threads.
         """
         req = requestmod.wsgirequest(env, respond)
         return self.run_wsgi(req)
 
     def run_wsgi(self, wsgireq):
         """Internal method to run the WSGI application.
 
         This is typically only called by Mercurial. External consumers
         should be using instances of this class as the WSGI application.
         """
         with self._obtainrepo() as repo:
             profile = repo.ui.configbool('profiling', 'enabled')
             with profiling.profile(repo.ui, enabled=profile):
                 for r in self._runwsgi(wsgireq, repo):
                     yield r
 
     def _runwsgi(self, wsgireq, repo):
-        req = requestmod.parserequestfromenv(wsgireq.env)
+        req = wsgireq.req
         rctx = requestcontext(self, repo)
 
         # This state is global across all threads.
         encoding.encoding = rctx.config('web', 'encoding')
         rctx.repo.ui.environ = wsgireq.env
 
         if rctx.csp:
             # hgwebdir may have added CSP header. Since we generate our own,
             # replace it.
             wsgireq.headers = [h for h in wsgireq.headers
                                if h[0] != 'Content-Security-Policy']
             wsgireq.headers.append(('Content-Security-Policy', rctx.csp))
 
         handled, res = wireprotoserver.handlewsgirequest(
             rctx, wsgireq, req, self.check_perm)
         if handled:
             return res
 
         if req.havepathinfo:
             query = req.dispatchpath
         else:
             query = req.querystring.partition('&')[0].partition(';')[0]
 
         # translate user-visible url structure to internal structure
 
         args = query.split('/', 2)
         if 'cmd' not in wsgireq.form and args and args[0]:
             cmd = args.pop(0)
             style = cmd.rfind('-')
             if style != -1:
                 wsgireq.form['style'] = [cmd[:style]]
                 cmd = cmd[style + 1:]
 
             # avoid accepting e.g. style parameter as command
             if util.safehasattr(webcommands, cmd):
                 wsgireq.form['cmd'] = [cmd]
 
             if cmd == 'static':
                 wsgireq.form['file'] = ['/'.join(args)]
             else:
                 if args and args[0]:
                     node = args.pop(0).replace('%2F', '/')
                     wsgireq.form['node'] = [node]
                 if args:
                     wsgireq.form['file'] = args
 
             ua = req.headers.get('User-Agent', '')
             if cmd == 'rev' and 'mercurial' in ua:
                 wsgireq.form['style'] = ['raw']
 
             if cmd == 'archive':
                 fn = wsgireq.form['node'][0]
                 for type_, spec in rctx.archivespecs.iteritems():
                     ext = spec[2]
                     if fn.endswith(ext):
                         wsgireq.form['node'] = [fn[:-len(ext)]]
                         wsgireq.form['type'] = [type_]
         else:
             cmd = wsgireq.form.get('cmd', [''])[0]
 
         # process the web interface request
 
         try:
             tmpl = rctx.templater(wsgireq, req)
             ctype = tmpl('mimetype', encoding=encoding.encoding)
             ctype = templater.stringify(ctype)
 
             # check read permissions non-static content
             if cmd != 'static':
                 self.check_perm(rctx, wsgireq, None)
 
             if cmd == '':
                 wsgireq.form['cmd'] = [tmpl.cache['default']]
                 cmd = wsgireq.form['cmd'][0]
 
             # Don't enable caching if using a CSP nonce because then it wouldn't
             # be a nonce.
             if rctx.configbool('web', 'cache') and not rctx.nonce:
                 caching(self, wsgireq) # sets ETag header or raises NOT_MODIFIED
             if cmd not in webcommands.__all__:
                 msg = 'no such method: %s' % cmd
                 raise ErrorResponse(HTTP_BAD_REQUEST, msg)
             elif cmd == 'file' and 'raw' in wsgireq.form.get('style', []):
                 rctx.ctype = ctype
                 content = webcommands.rawfile(rctx, wsgireq, tmpl)
             else:
                 content = getattr(webcommands, cmd)(rctx, wsgireq, tmpl)
                 wsgireq.respond(HTTP_OK, ctype)
 
             return content
 
         except (error.LookupError, error.RepoLookupError) as err:
             wsgireq.respond(HTTP_NOT_FOUND, ctype)
             msg = pycompat.bytestr(err)
             if (util.safehasattr(err, 'name') and
                 not isinstance(err,  error.ManifestLookupError)):
                 msg = 'revision not found: %s' % err.name
             return tmpl('error', error=msg)
         except (error.RepoError, error.RevlogError) as inst:
             wsgireq.respond(HTTP_SERVER_ERROR, ctype)
             return tmpl('error', error=pycompat.bytestr(inst))
         except ErrorResponse as inst:
             wsgireq.respond(inst, ctype)
             if inst.code == HTTP_NOT_MODIFIED:
                 # Not allowed to return a body on a 304
                 return ['']
             return tmpl('error', error=pycompat.bytestr(inst))
 
     def check_perm(self, rctx, req, op):
         for permhook in permhooks:
             permhook(rctx, req, op)
 
 def getwebview(repo):
     """The 'web.view' config controls changeset filter to hgweb. Possible
     values are ``served``, ``visible`` and ``all``. Default is ``served``.
     The ``served`` filter only shows changesets that can be pulled from the
     hgweb instance.  The``visible`` filter includes secret changesets but
     still excludes "hidden" one.
 
     See the repoview module for details.
 
     The option has been around undocumented since Mercurial 2.5, but no
     user ever asked about it. So we better keep it undocumented for now."""
     # experimental config: web.view
     viewconfig = repo.ui.config('web', 'view', untrusted=True)
     if viewconfig == 'all':
         return repo.unfiltered()
     elif viewconfig in repoview.filtertable:
         return repo.filtered(viewconfig)
     else:
         return repo.filtered('served')

mercurial/hgweb/hgwebdir_mod.py

@@ -1,538 +1,543 b''
 # 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)
                     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

@@ -1,361 +1,363 b''
 # 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."""
 
     # 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()
 
 def parserequestfromenv(env):
     """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']
 
     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)
 
 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']
 
         if r'HTTP_CONTENT_LENGTH' in wsgienv:
             self.inp = util.cappedreader(self.inp,
                                          int(wsgienv[r'HTTP_CONTENT_LENGTH']))
         elif r'CONTENT_LENGTH' in wsgienv:
             self.inp = util.cappedreader(self.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.env,
                                         keep_blank_values=1))
         self._start_response = start_response
         self.server_write = None
         self.headers = []
 
+        self.req = parserequestfromenv(wsgienv)
+
     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):
                     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)
                 while True:
                     chunk = self.inp.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