hgweb: move archivespecs to webutil

Move one step further from e38e7ea21987. Since 'archivespecs' is a constant
shared with hgweb and hgwebdir, webutil is a better place to define it.

mercurial/hgweb/hgweb_mod.py

@@ -1,469 +1,463 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,
     cspvalues,
     permhooks,
     statusmessage,
 )
 
 from .. import (
     encoding,
     error,
     formatter,
     hg,
     hook,
     profiling,
     pycompat,
     registrar,
     repoview,
     templatefilters,
     templater,
     templateutil,
     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):
     styles = (
         req.qsparams.get('style', None),
         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 templateutil.mappinglist(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, req, res):
         self.repo = repo
         self.reponame = app.reponame
         self.req = req
         self.res = res
 
-        self.archivespecs = archivespecs
+        self.archivespecs = webutil.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, 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(req, 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 req.reponame
                              or req.apppath
                              or self.repo.root)
 
         filters = {}
         templatefilter = registrar.templatefilter(filters)
         @templatefilter('websub', intype=bytes)
         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=filters,
                                                defaults=defaults,
                                                resources=tres)
         return tmpl
 
     def sendtemplate(self, name, **kwargs):
         """Helper function to send a response generated from a template."""
         kwargs = pycompat.byteskwargs(kwargs)
         self.res.setbodygen(self.tmpl.generate(name, kwargs))
         return self.res.sendresponse()
 
 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.parserequestfromenv(env)
         res = requestmod.wsgiresponse(req, respond)
 
         return self.run_wsgi(req, res)
 
     def run_wsgi(self, req, res):
         """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(req, res, repo):
                     yield r
 
     def _runwsgi(self, req, res, repo):
         rctx = requestcontext(self, repo, req, res)
 
         # This state is global across all threads.
         encoding.encoding = rctx.config('web', 'encoding')
         rctx.repo.ui.environ = req.rawenv
 
         if rctx.csp:
             # hgwebdir may have added CSP header. Since we generate our own,
             # replace it.
             res.headers['Content-Security-Policy'] = rctx.csp
 
         # /api/* is reserved for various API implementations. Dispatch
         # accordingly. But URL paths can conflict with subrepos and virtual
         # repos in hgwebdir. So until we have a workaround for this, only
         # expose the URLs if the feature is enabled.
         apienabled = rctx.repo.ui.configbool('experimental', 'web.apiserver')
         if apienabled and req.dispatchparts and req.dispatchparts[0] == b'api':
             wireprotoserver.handlewsgiapirequest(rctx, req, res,
                                                  self.check_perm)
             return res.sendresponse()
 
         handled = wireprotoserver.handlewsgirequest(
             rctx, req, res, self.check_perm)
         if handled:
             return res.sendresponse()
 
         # Old implementations of hgweb supported dispatching the request via
         # the initial query string parameter instead of using PATH_INFO.
         # If PATH_INFO is present (signaled by ``req.dispatchpath`` having
         # a value), we use it. Otherwise fall back to the query string.
         if req.dispatchpath is not None:
             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 req.qsparams and args and args[0]:
             cmd = args.pop(0)
             style = cmd.rfind('-')
             if style != -1:
                 req.qsparams['style'] = cmd[:style]
                 cmd = cmd[style + 1:]
 
             # avoid accepting e.g. style parameter as command
             if util.safehasattr(webcommands, cmd):
                 req.qsparams['cmd'] = cmd
 
             if cmd == 'static':
                 req.qsparams['file'] = '/'.join(args)
             else:
                 if args and args[0]:
                     node = args.pop(0).replace('%2F', '/')
                     req.qsparams['node'] = node
                 if args:
                     if 'file' in req.qsparams:
                         del req.qsparams['file']
                     for a in args:
                         req.qsparams.add('file', a)
 
             ua = req.headers.get('User-Agent', '')
             if cmd == 'rev' and 'mercurial' in ua:
                 req.qsparams['style'] = 'raw'
 
             if cmd == 'archive':
                 fn = req.qsparams['node']
                 for type_, spec in rctx.archivespecs.iteritems():
                     ext = spec[2]
                     if fn.endswith(ext):
                         req.qsparams['node'] = fn[:-len(ext)]
                         req.qsparams['type'] = type_
         else:
             cmd = req.qsparams.get('cmd', '')
 
         # process the web interface request
 
         try:
             rctx.tmpl = rctx.templater(req)
             ctype = rctx.tmpl.render('mimetype',
                                      {'encoding': encoding.encoding})
 
             # check read permissions non-static content
             if cmd != 'static':
                 self.check_perm(rctx, req, None)
 
             if cmd == '':
                 req.qsparams['cmd'] = rctx.tmpl.render('default', {})
                 cmd = req.qsparams['cmd']
 
             # 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:
                 tag = 'W/"%d"' % self.mtime
                 if req.headers.get('If-None-Match') == tag:
                     res.status = '304 Not Modified'
                     # Response body not allowed on 304.
                     res.setbodybytes('')
                     return res.sendresponse()
 
                 res.headers['ETag'] = tag
 
             if cmd not in webcommands.__all__:
                 msg = 'no such method: %s' % cmd
                 raise ErrorResponse(HTTP_BAD_REQUEST, msg)
             else:
                 # Set some globals appropriate for web handlers. Commands can
                 # override easily enough.
                 res.status = '200 Script output follows'
                 res.headers['Content-Type'] = ctype
                 return getattr(webcommands, cmd)(rctx)
 
         except (error.LookupError, error.RepoLookupError) as err:
             msg = pycompat.bytestr(err)
             if (util.safehasattr(err, 'name') and
                 not isinstance(err,  error.ManifestLookupError)):
                 msg = 'revision not found: %s' % err.name
 
             res.status = '404 Not Found'
             res.headers['Content-Type'] = ctype
             return rctx.sendtemplate('error', error=msg)
         except (error.RepoError, error.RevlogError) as e:
             res.status = '500 Internal Server Error'
             res.headers['Content-Type'] = ctype
             return rctx.sendtemplate('error', error=pycompat.bytestr(e))
         except ErrorResponse as e:
             res.status = statusmessage(e.code, pycompat.bytestr(e))
             res.headers['Content-Type'] = ctype
             return rctx.sendtemplate('error', error=pycompat.bytestr(e))
 
     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

@@ -1,542 +1,542 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 gc
 import os
 import time
 
 from ..i18n import _
 
 from .common import (
     ErrorResponse,
     HTTP_SERVER_ERROR,
     cspvalues,
     get_contact,
     get_mtime,
     ismember,
     paritygen,
     staticfile,
     statusmessage,
 )
 
 from .. import (
     configitems,
     encoding,
     error,
     hg,
     profiling,
     pycompat,
     scmutil,
     templater,
     templateutil,
     ui as uimod,
     util,
 )
 
 from . import (
     hgweb_mod,
     request as requestmod,
     webutil,
     wsgicgi,
 )
 from ..utils import dateutil
 
 def cleannames(items):
     return [(util.pconvert(name).strip('/'), path) for name, path in items]
 
 def findrepos(paths):
     repos = []
     for prefix, root in cleannames(paths):
         roothead, roottail = os.path.split(root)
         # "foo = /bar/*" or "foo = /bar/**" lets every repo /bar/N in or below
         # /bar/ be served as as foo/N .
         # '*' will not search inside dirs with .hg (except .hg/patches),
         # '**' will search inside dirs with .hg (and thus also find subrepos).
         try:
             recurse = {'*': False, '**': True}[roottail]
         except KeyError:
             repos.append((prefix, root))
             continue
         roothead = os.path.normpath(os.path.abspath(roothead))
         paths = scmutil.walkrepos(roothead, followsym=True, recurse=recurse)
         repos.extend(urlrepos(prefix, roothead, paths))
     return repos
 
 def urlrepos(prefix, roothead, paths):
     """yield url paths and filesystem paths from a list of repo paths
 
     >>> conv = lambda seq: [(v, util.pconvert(p)) for v,p in seq]
     >>> conv(urlrepos(b'hg', b'/opt', [b'/opt/r', b'/opt/r/r', b'/opt']))
     [('hg/r', '/opt/r'), ('hg/r/r', '/opt/r/r'), ('hg', '/opt')]
     >>> conv(urlrepos(b'', b'/opt', [b'/opt/r', b'/opt/r/r', b'/opt']))
     [('r', '/opt/r'), ('r/r', '/opt/r/r'), ('', '/opt')]
     """
     for path in paths:
         path = os.path.normpath(path)
         yield (prefix + '/' +
                util.pconvert(path[len(roothead):]).lstrip('/')).strip('/'), path
 
 def readallowed(ui, req):
     """Check allow_read and deny_read config options of a repo's ui object
     to determine user permissions.  By default, with neither option set (or
     both empty), allow all users to read the repo.  There are two ways a
     user can be denied read access:  (1) deny_read is not empty, and the
     user is unauthenticated or deny_read contains user (or *), and (2)
     allow_read is not empty and the user is not in allow_read.  Return True
     if user is allowed to read the repo, else return False."""
 
     user = req.remoteuser
 
     deny_read = ui.configlist('web', 'deny_read', untrusted=True)
     if deny_read and (not user or ismember(ui, user, deny_read)):
         return False
 
     allow_read = ui.configlist('web', 'allow_read', untrusted=True)
     # by default, allow reading if no allow_read option has been set
     if not allow_read or ismember(ui, user, allow_read):
         return True
 
     return False
 
 def archivelist(ui, nodeid, url):
     allowed = ui.configlist('web', 'allow_archive', untrusted=True)
     archives = []
 
-    for typ, spec in hgweb_mod.archivespecs.iteritems():
+    for typ, spec in webutil.archivespecs.iteritems():
         if typ in allowed or ui.configbool('web', 'allow' + typ,
                                            untrusted=True):
             archives.append({
                 'type': typ,
                 'extension': spec[2],
                 'node': nodeid,
                 'url': url,
             })
 
     return archives
 
 def rawindexentries(ui, repos, req, subdir=''):
     descend = ui.configbool('web', 'descend')
     collapse = ui.configbool('web', 'collapse')
     seenrepos = set()
     seendirs = set()
     for name, path in repos:
 
         if not name.startswith(subdir):
             continue
         name = name[len(subdir):]
         directory = False
 
         if '/' in name:
             if not descend:
                 continue
 
             nameparts = name.split('/')
             rootname = nameparts[0]
 
             if not collapse:
                 pass
             elif rootname in seendirs:
                 continue
             elif rootname in seenrepos:
                 pass
             else:
                 directory = True
                 name = rootname
 
                 # redefine the path to refer to the directory
                 discarded = '/'.join(nameparts[1:])
 
                 # remove name parts plus accompanying slash
                 path = path[:-len(discarded) - 1]
 
                 try:
                     r = hg.repository(ui, path)
                     directory = False
                 except (IOError, error.RepoError):
                     pass
 
         parts = [
             req.apppath.strip('/'),
             subdir.strip('/'),
             name.strip('/'),
         ]
         url = '/' + '/'.join(p for p in parts if p) + '/'
 
         # show either a directory entry or a repository
         if directory:
             # get the directory's time information
             try:
                 d = (get_mtime(path), dateutil.makedate()[1])
             except OSError:
                 continue
 
             # add '/' to the name to make it obvious that
             # the entry is a directory, not a regular repository
             row = {'contact': "",
                    'contact_sort': "",
                    'name': name + '/',
                    'name_sort': name,
                    'url': url,
                    'description': "",
                    'description_sort': "",
                    'lastchange': d,
                    'lastchange_sort': d[1] - d[0],
                    'archives': [],
                    'isdirectory': True,
                    'labels': templateutil.hybridlist([], name='label'),
                    }
 
             seendirs.add(name)
             yield row
             continue
 
         u = ui.copy()
         try:
             u.readconfig(os.path.join(path, '.hg', 'hgrc'))
         except Exception as e:
             u.warn(_('error reading %s/.hg/hgrc: %s\n') % (path, e))
             continue
 
         def get(section, name, default=uimod._unset):
             return u.config(section, name, default, untrusted=True)
 
         if u.configbool("web", "hidden", untrusted=True):
             continue
 
         if not readallowed(u, req):
             continue
 
         # update time with local timezone
         try:
             r = hg.repository(ui, path)
         except IOError:
             u.warn(_('error accessing repository at %s\n') % path)
             continue
         except error.RepoError:
             u.warn(_('error accessing repository at %s\n') % path)
             continue
         try:
             d = (get_mtime(r.spath), dateutil.makedate()[1])
         except OSError:
             continue
 
         contact = get_contact(get)
         description = get("web", "description")
         seenrepos.add(name)
         name = get("web", "name", name)
         labels = u.configlist('web', 'labels', untrusted=True)
         row = {'contact': contact or "unknown",
                'contact_sort': contact.upper() or "unknown",
                'name': name,
                'name_sort': name,
                'url': url,
                'description': description or "unknown",
                'description_sort': description.upper() or "unknown",
                'lastchange': d,
                'lastchange_sort': d[1] - d[0],
                'archives': archivelist(u, "tip", url),
                'isdirectory': None,
                'labels': templateutil.hybridlist(labels, name='label'),
                }
 
         yield row
 
 def _indexentriesgen(context, ui, repos, req, stripecount, sortcolumn,
                      descending, subdir):
     rows = rawindexentries(ui, repos, req, subdir=subdir)
 
     sortdefault = None, False
 
     if sortcolumn and sortdefault != (sortcolumn, descending):
         sortkey = '%s_sort' % sortcolumn
         rows = sorted(rows, key=lambda x: x[sortkey],
                       reverse=descending)
 
     for row, parity in zip(rows, paritygen(stripecount)):
         row['parity'] = parity
         yield row
 
 def indexentries(ui, repos, req, stripecount, sortcolumn='',
                  descending=False, subdir=''):
     args = (ui, repos, req, stripecount, sortcolumn, descending, subdir)
     return templateutil.mappinggenerator(_indexentriesgen, args=args)
 
 class hgwebdir(object):
     """HTTP server for multiple repositories.
 
     Given a configuration, different repositories will be served depending
     on the request path.
 
     Instances are typically used as WSGI applications.
     """
     def __init__(self, conf, baseui=None):
         self.conf = conf
         self.baseui = baseui
         self.ui = None
         self.lastrefresh = 0
         self.motd = None
         self.refresh()
 
     def refresh(self):
         if self.ui:
             refreshinterval = self.ui.configint('web', 'refreshinterval')
         else:
             item = configitems.coreitems['web']['refreshinterval']
             refreshinterval = item.default
 
         # refreshinterval <= 0 means to always refresh.
         if (refreshinterval > 0 and
             self.lastrefresh + refreshinterval > time.time()):
             return
 
         if self.baseui:
             u = self.baseui.copy()
         else:
             u = uimod.ui.load()
             u.setconfig('ui', 'report_untrusted', 'off', 'hgwebdir')
             u.setconfig('ui', 'nontty', 'true', 'hgwebdir')
             # displaying bundling progress bar while serving feels wrong and may
             # break some wsgi implementations.
             u.setconfig('progress', 'disable', 'true', 'hgweb')
 
         if not isinstance(self.conf, (dict, list, tuple)):
             map = {'paths': 'hgweb-paths'}
             if not os.path.exists(self.conf):
                 raise error.Abort(_('config file %s not found!') % self.conf)
             u.readconfig(self.conf, remap=map, trust=True)
             paths = []
             for name, ignored in u.configitems('hgweb-paths'):
                 for path in u.configlist('hgweb-paths', name):
                     paths.append((name, path))
         elif isinstance(self.conf, (list, tuple)):
             paths = self.conf
         elif isinstance(self.conf, dict):
             paths = self.conf.items()
 
         repos = findrepos(paths)
         for prefix, root in u.configitems('collections'):
             prefix = util.pconvert(prefix)
             for path in scmutil.walkrepos(root, followsym=True):
                 repo = os.path.normpath(path)
                 name = util.pconvert(repo)
                 if name.startswith(prefix):
                     name = name[len(prefix):]
                 repos.append((name.lstrip('/'), repo))
 
         self.repos = repos
         self.ui = u
         encoding.encoding = self.ui.config('web', 'encoding')
         self.style = self.ui.config('web', 'style')
         self.templatepath = self.ui.config('web', 'templates', untrusted=False)
         self.stripecount = self.ui.config('web', 'stripes')
         if self.stripecount:
             self.stripecount = int(self.stripecount)
         prefix = self.ui.config('web', 'prefix')
         if prefix.startswith('/'):
             prefix = prefix[1:]
         if prefix.endswith('/'):
             prefix = prefix[:-1]
         self.prefix = prefix
         self.lastrefresh = time.time()
 
     def run(self):
         if not encoding.environ.get('GATEWAY_INTERFACE',
                                     '').startswith("CGI/1."):
             raise RuntimeError("This function is only intended to be "
                                "called while running as a CGI script.")
         wsgicgi.launch(self)
 
     def __call__(self, env, respond):
         baseurl = self.ui.config('web', 'baseurl')
         req = requestmod.parserequestfromenv(env, altbaseurl=baseurl)
         res = requestmod.wsgiresponse(req, respond)
 
         return self.run_wsgi(req, res)
 
     def run_wsgi(self, req, res):
         profile = self.ui.configbool('profiling', 'enabled')
         with profiling.profile(self.ui, enabled=profile):
             try:
                 for r in self._runwsgi(req, res):
                     yield r
             finally:
                 # There are known cycles in localrepository that prevent
                 # those objects (and tons of held references) from being
                 # collected through normal refcounting. We mitigate those
                 # leaks by performing an explicit GC on every request.
                 # TODO remove this once leaks are fixed.
                 # TODO only run this on requests that create localrepository
                 # instances instead of every request.
                 gc.collect()
 
     def _runwsgi(self, req, res):
         try:
             self.refresh()
 
             csp, nonce = cspvalues(self.ui)
             if csp:
                 res.headers['Content-Security-Policy'] = csp
 
             virtual = req.dispatchpath.strip('/')
             tmpl = self.templater(req, nonce)
             ctype = tmpl.render('mimetype', {'encoding': encoding.encoding})
 
             # Global defaults. These can be overridden by any handler.
             res.status = '200 Script output follows'
             res.headers['Content-Type'] = ctype
 
             # a static file
             if virtual.startswith('static/') or 'static' in req.qsparams:
                 if virtual.startswith('static/'):
                     fname = virtual[7:]
                 else:
                     fname = req.qsparams['static']
                 static = self.ui.config("web", "static", None,
                                         untrusted=False)
                 if not static:
                     tp = self.templatepath or templater.templatepaths()
                     if isinstance(tp, str):
                         tp = [tp]
                     static = [os.path.join(p, 'static') for p in tp]
 
                 staticfile(static, fname, res)
                 return res.sendresponse()
 
             # top-level index
 
             repos = dict(self.repos)
 
             if (not virtual or virtual == 'index') and virtual not in repos:
                 return self.makeindex(req, res, tmpl)
 
             # nested indexes and hgwebs
 
             if virtual.endswith('/index') and virtual not in repos:
                 subdir = virtual[:-len('index')]
                 if any(r.startswith(subdir) for r in repos):
                     return self.makeindex(req, res, tmpl, subdir)
 
             def _virtualdirs():
                 # Check the full virtual path, each parent, and the root ('')
                 if virtual != '':
                     yield virtual
 
                     for p in util.finddirs(virtual):
                         yield p
 
                 yield ''
 
             for virtualrepo in _virtualdirs():
                 real = repos.get(virtualrepo)
                 if real:
                     # Re-parse the WSGI environment to take into account our
                     # repository path component.
                     req = requestmod.parserequestfromenv(
                         req.rawenv, reponame=virtualrepo,
                         altbaseurl=self.ui.config('web', 'baseurl'))
                     try:
                         # ensure caller gets private copy of ui
                         repo = hg.repository(self.ui.copy(), real)
                         return hgweb_mod.hgweb(repo).run_wsgi(req, res)
                     except IOError as inst:
                         msg = encoding.strtolocal(inst.strerror)
                         raise ErrorResponse(HTTP_SERVER_ERROR, msg)
                     except error.RepoError as inst:
                         raise ErrorResponse(HTTP_SERVER_ERROR, bytes(inst))
 
             # browse subdirectories
             subdir = virtual + '/'
             if [r for r in repos if r.startswith(subdir)]:
                 return self.makeindex(req, res, tmpl, subdir)
 
             # prefixes not found
             res.status = '404 Not Found'
             res.setbodygen(tmpl.generate('notfound', {'repo': virtual}))
             return res.sendresponse()
 
         except ErrorResponse as e:
             res.status = statusmessage(e.code, pycompat.bytestr(e))
             res.setbodygen(tmpl.generate('error', {'error': e.message or ''}))
             return res.sendresponse()
         finally:
             tmpl = None
 
     def makeindex(self, req, res, tmpl, subdir=""):
         self.refresh()
         sortable = ["name", "description", "contact", "lastchange"]
         sortcolumn, descending = None, False
         if 'sort' in req.qsparams:
             sortcolumn = req.qsparams['sort']
             descending = sortcolumn.startswith('-')
             if descending:
                 sortcolumn = sortcolumn[1:]
             if sortcolumn not in sortable:
                 sortcolumn = ""
 
         sort = [("sort_%s" % column,
                  "%s%s" % ((not descending and column == sortcolumn)
                             and "-" or "", column))
                 for column in sortable]
 
         self.refresh()
 
         entries = indexentries(self.ui, self.repos, req,
                                self.stripecount, sortcolumn=sortcolumn,
                                descending=descending, subdir=subdir)
 
         mapping = {
             'entries': entries,
             'subdir': subdir,
             'pathdef': hgweb_mod.makebreadcrumb('/' + subdir, self.prefix),
             'sortcolumn': sortcolumn,
             'descending': descending,
         }
         mapping.update(sort)
         res.setbodygen(tmpl.generate('index', mapping))
         return res.sendresponse()
 
     def templater(self, req, nonce):
 
         def motd(**map):
             if self.motd is not None:
                 yield self.motd
             else:
                 yield config('web', 'motd')
 
         def config(section, name, default=uimod._unset, untrusted=True):
             return self.ui.config(section, name, default, untrusted)
 
         vars = {}
         styles, (style, mapfile) = hgweb_mod.getstyle(req, config,
                                                       self.templatepath)
         if style == styles[0]:
             vars['style'] = style
 
         sessionvars = webutil.sessionvars(vars, r'?')
         logourl = config('web', 'logourl')
         logoimg = config('web', 'logoimg')
         staticurl = (config('web', 'staticurl')
                      or req.apppath + '/static/')
         if not staticurl.endswith('/'):
             staticurl += '/'
 
         defaults = {
             "encoding": encoding.encoding,
             "motd": motd,
             "url": req.apppath + '/',
             "logourl": logourl,
             "logoimg": logoimg,
             "staticurl": staticurl,
             "sessionvars": sessionvars,
             "style": style,
             "nonce": nonce,
         }
         tmpl = templater.templater.frommapfile(mapfile, defaults=defaults)
         return tmpl

mercurial/hgweb/webutil.py

@@ -1,694 +1,700 b''
 # hgweb/webutil.py - utility library for the web interface.
 #
 # 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 copy
 import difflib
 import os
 import re
 
 from ..i18n import _
 from ..node import hex, nullid, short
 
 from .common import (
     ErrorResponse,
     HTTP_BAD_REQUEST,
     HTTP_NOT_FOUND,
     paritygen,
 )
 
 from .. import (
     context,
     error,
     match,
     mdiff,
     obsutil,
     patch,
     pathutil,
     pycompat,
     scmutil,
     templatefilters,
     templatekw,
     ui as uimod,
     util,
 )
 
 from ..utils import (
     stringutil,
 )
 
+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 up(p):
     if p[0:1] != "/":
         p = "/" + p
     if p[-1:] == "/":
         p = p[:-1]
     up = os.path.dirname(p)
     if up == "/":
         return "/"
     return up + "/"
 
 def _navseq(step, firststep=None):
     if firststep:
         yield firststep
         if firststep >= 20 and firststep <= 40:
             firststep = 50
             yield firststep
         assert step > 0
         assert firststep > 0
         while step <= firststep:
             step *= 10
     while True:
         yield 1 * step
         yield 3 * step
         step *= 10
 
 class revnav(object):
 
     def __init__(self, repo):
         """Navigation generation object
 
         :repo: repo object we generate nav for
         """
         # used for hex generation
         self._revlog = repo.changelog
 
     def __nonzero__(self):
         """return True if any revision to navigate over"""
         return self._first() is not None
 
     __bool__ = __nonzero__
 
     def _first(self):
         """return the minimum non-filtered changeset or None"""
         try:
             return next(iter(self._revlog))
         except StopIteration:
             return None
 
     def hex(self, rev):
         return hex(self._revlog.node(rev))
 
     def gen(self, pos, pagelen, limit):
         """computes label and revision id for navigation link
 
         :pos: is the revision relative to which we generate navigation.
         :pagelen: the size of each navigation page
         :limit: how far shall we link
 
         The return is:
             - a single element tuple
             - containing a dictionary with a `before` and `after` key
             - values are generator functions taking arbitrary number of kwargs
             - yield items are dictionaries with `label` and `node` keys
         """
         if not self:
             # empty repo
             return ({'before': (), 'after': ()},)
 
         targets = []
         for f in _navseq(1, pagelen):
             if f > limit:
                 break
             targets.append(pos + f)
             targets.append(pos - f)
         targets.sort()
 
         first = self._first()
         navbefore = [("(%i)" % first, self.hex(first))]
         navafter = []
         for rev in targets:
             if rev not in self._revlog:
                 continue
             if pos < rev < limit:
                 navafter.append(("+%d" % abs(rev - pos), self.hex(rev)))
             if 0 < rev < pos:
                 navbefore.append(("-%d" % abs(rev - pos), self.hex(rev)))
 
 
         navafter.append(("tip", "tip"))
 
         data = lambda i: {"label": i[0], "node": i[1]}
         return ({'before': lambda **map: (data(i) for i in navbefore),
                  'after':  lambda **map: (data(i) for i in navafter)},)
 
 class filerevnav(revnav):
 
     def __init__(self, repo, path):
         """Navigation generation object
 
         :repo: repo object we generate nav for
         :path: path of the file we generate nav for
         """
         # used for iteration
         self._changelog = repo.unfiltered().changelog
         # used for hex generation
         self._revlog = repo.file(path)
 
     def hex(self, rev):
         return hex(self._changelog.node(self._revlog.linkrev(rev)))
 
 class _siblings(object):
     def __init__(self, siblings=None, hiderev=None):
         if siblings is None:
             siblings = []
         self.siblings = [s for s in siblings if s.node() != nullid]
         if len(self.siblings) == 1 and self.siblings[0].rev() == hiderev:
             self.siblings = []
 
     def __iter__(self):
         for s in self.siblings:
             d = {
                 'node': s.hex(),
                 'rev': s.rev(),
                 'user': s.user(),
                 'date': s.date(),
                 'description': s.description(),
                 'branch': s.branch(),
             }
             if util.safehasattr(s, 'path'):
                 d['file'] = s.path()
             yield d
 
     def __len__(self):
         return len(self.siblings)
 
 def difffeatureopts(req, ui, section):
     diffopts = patch.difffeatureopts(ui, untrusted=True,
                                      section=section, whitespace=True)
 
     for k in ('ignorews', 'ignorewsamount', 'ignorewseol', 'ignoreblanklines'):
         v = req.qsparams.get(k)
         if v is not None:
             v = stringutil.parsebool(v)
             setattr(diffopts, k, v if v is not None else True)
 
     return diffopts
 
 def annotate(req, fctx, ui):
     diffopts = difffeatureopts(req, ui, 'annotate')
     return fctx.annotate(follow=True, diffopts=diffopts)
 
 def parents(ctx, hide=None):
     if isinstance(ctx, context.basefilectx):
         introrev = ctx.introrev()
         if ctx.changectx().rev() != introrev:
             return _siblings([ctx.repo()[introrev]], hide)
     return _siblings(ctx.parents(), hide)
 
 def children(ctx, hide=None):
     return _siblings(ctx.children(), hide)
 
 def renamelink(fctx):
     r = fctx.renamed()
     if r:
         return [{'file': r[0], 'node': hex(r[1])}]
     return []
 
 def nodetagsdict(repo, node):
     return [{"name": i} for i in repo.nodetags(node)]
 
 def nodebookmarksdict(repo, node):
     return [{"name": i} for i in repo.nodebookmarks(node)]
 
 def nodebranchdict(repo, ctx):
     branches = []
     branch = ctx.branch()
     # If this is an empty repo, ctx.node() == nullid,
     # ctx.branch() == 'default'.
     try:
         branchnode = repo.branchtip(branch)
     except error.RepoLookupError:
         branchnode = None
     if branchnode == ctx.node():
         branches.append({"name": branch})
     return branches
 
 def nodeinbranch(repo, ctx):
     branches = []
     branch = ctx.branch()
     try:
         branchnode = repo.branchtip(branch)
     except error.RepoLookupError:
         branchnode = None
     if branch != 'default' and branchnode != ctx.node():
         branches.append({"name": branch})
     return branches
 
 def nodebranchnodefault(ctx):
     branches = []
     branch = ctx.branch()
     if branch != 'default':
         branches.append({"name": branch})
     return branches
 
 def showtag(repo, tmpl, t1, node=nullid, **args):
     args = pycompat.byteskwargs(args)
     for t in repo.nodetags(node):
         lm = args.copy()
         lm['tag'] = t
         yield tmpl.generate(t1, lm)
 
 def showbookmark(repo, tmpl, t1, node=nullid, **args):
     args = pycompat.byteskwargs(args)
     for t in repo.nodebookmarks(node):
         lm = args.copy()
         lm['bookmark'] = t
         yield tmpl.generate(t1, lm)
 
 def branchentries(repo, stripecount, limit=0):
     tips = []
     heads = repo.heads()
     parity = paritygen(stripecount)
     sortkey = lambda item: (not item[1], item[0].rev())
 
     def entries(**map):
         count = 0
         if not tips:
             for tag, hs, tip, closed in repo.branchmap().iterbranches():
                 tips.append((repo[tip], closed))
         for ctx, closed in sorted(tips, key=sortkey, reverse=True):
             if limit > 0 and count >= limit:
                 return
             count += 1
             if closed:
                 status = 'closed'
             elif ctx.node() not in heads:
                 status = 'inactive'
             else:
                 status = 'open'
             yield {
                 'parity': next(parity),
                 'branch': ctx.branch(),
                 'status': status,
                 'node': ctx.hex(),
                 'date': ctx.date()
             }
 
     return entries
 
 def cleanpath(repo, path):
     path = path.lstrip('/')
     return pathutil.canonpath(repo.root, '', path)
 
 def changectx(repo, req):
     changeid = "tip"
     if 'node' in req.qsparams:
         changeid = req.qsparams['node']
         ipos = changeid.find(':')
         if ipos != -1:
             changeid = changeid[(ipos + 1):]
 
     return scmutil.revsymbol(repo, changeid)
 
 def basechangectx(repo, req):
     if 'node' in req.qsparams:
         changeid = req.qsparams['node']
         ipos = changeid.find(':')
         if ipos != -1:
             changeid = changeid[:ipos]
             return scmutil.revsymbol(repo, changeid)
 
     return None
 
 def filectx(repo, req):
     if 'file' not in req.qsparams:
         raise ErrorResponse(HTTP_NOT_FOUND, 'file not given')
     path = cleanpath(repo, req.qsparams['file'])
     if 'node' in req.qsparams:
         changeid = req.qsparams['node']
     elif 'filenode' in req.qsparams:
         changeid = req.qsparams['filenode']
     else:
         raise ErrorResponse(HTTP_NOT_FOUND, 'node or filenode not given')
     try:
         fctx = scmutil.revsymbol(repo, changeid)[path]
     except error.RepoError:
         fctx = repo.filectx(path, fileid=changeid)
 
     return fctx
 
 def linerange(req):
     linerange = req.qsparams.getall('linerange')
     if not linerange:
         return None
     if len(linerange) > 1:
         raise ErrorResponse(HTTP_BAD_REQUEST,
                             'redundant linerange parameter')
     try:
         fromline, toline = map(int, linerange[0].split(':', 1))
     except ValueError:
         raise ErrorResponse(HTTP_BAD_REQUEST,
                             'invalid linerange parameter')
     try:
         return util.processlinerange(fromline, toline)
     except error.ParseError as exc:
         raise ErrorResponse(HTTP_BAD_REQUEST, pycompat.bytestr(exc))
 
 def formatlinerange(fromline, toline):
     return '%d:%d' % (fromline + 1, toline)
 
 def succsandmarkers(context, mapping):
     repo = context.resource(mapping, 'repo')
     itemmappings = templatekw.showsuccsandmarkers(context, mapping)
     for item in itemmappings.tovalue(context, mapping):
         item['successors'] = _siblings(repo[successor]
                                        for successor in item['successors'])
         yield item
 
 # teach templater succsandmarkers is switched to (context, mapping) API
 succsandmarkers._requires = {'repo', 'ctx'}
 
 def whyunstable(context, mapping):
     repo = context.resource(mapping, 'repo')
     ctx = context.resource(mapping, 'ctx')
 
     entries = obsutil.whyunstable(repo, ctx)
     for entry in entries:
         if entry.get('divergentnodes'):
             entry['divergentnodes'] = _siblings(entry['divergentnodes'])
         yield entry
 
 whyunstable._requires = {'repo', 'ctx'}
 
 def commonentry(repo, ctx):
     node = ctx.node()
     return {
         # TODO: perhaps ctx.changectx() should be assigned if ctx is a
         # filectx, but I'm not pretty sure if that would always work because
         # fctx.parents() != fctx.changectx.parents() for example.
         'ctx': ctx,
         'rev': ctx.rev(),
         'node': hex(node),
         'author': ctx.user(),
         'desc': ctx.description(),
         'date': ctx.date(),
         'extra': ctx.extra(),
         'phase': ctx.phasestr(),
         'obsolete': ctx.obsolete(),
         'succsandmarkers': succsandmarkers,
         'instabilities': [{"instability": i} for i in ctx.instabilities()],
         'whyunstable': whyunstable,
         'branch': nodebranchnodefault(ctx),
         'inbranch': nodeinbranch(repo, ctx),
         'branches': nodebranchdict(repo, ctx),
         'tags': nodetagsdict(repo, node),
         'bookmarks': nodebookmarksdict(repo, node),
         'parent': lambda **x: parents(ctx),
         'child': lambda **x: children(ctx),
     }
 
 def changelistentry(web, ctx):
     '''Obtain a dictionary to be used for entries in a changelist.
 
     This function is called when producing items for the "entries" list passed
     to the "shortlog" and "changelog" templates.
     '''
     repo = web.repo
     rev = ctx.rev()
     n = ctx.node()
     showtags = showtag(repo, web.tmpl, 'changelogtag', n)
     files = listfilediffs(web.tmpl, ctx.files(), n, web.maxfiles)
 
     entry = commonentry(repo, ctx)
     entry.update(
         allparents=lambda **x: parents(ctx),
         parent=lambda **x: parents(ctx, rev - 1),
         child=lambda **x: children(ctx, rev + 1),
         changelogtag=showtags,
         files=files,
     )
     return entry
 
 def symrevorshortnode(req, ctx):
     if 'node' in req.qsparams:
         return templatefilters.revescape(req.qsparams['node'])
     else:
         return short(ctx.node())
 
 def changesetentry(web, ctx):
     '''Obtain a dictionary to be used to render the "changeset" template.'''
 
     showtags = showtag(web.repo, web.tmpl, 'changesettag', ctx.node())
     showbookmarks = showbookmark(web.repo, web.tmpl, 'changesetbookmark',
                                  ctx.node())
     showbranch = nodebranchnodefault(ctx)
 
     files = []
     parity = paritygen(web.stripecount)
     for blockno, f in enumerate(ctx.files()):
         template = 'filenodelink' if f in ctx else 'filenolink'
         files.append(web.tmpl.generate(template, {
             'node': ctx.hex(),
             'file': f,
             'blockno': blockno + 1,
             'parity': next(parity),
         }))
 
     basectx = basechangectx(web.repo, web.req)
     if basectx is None:
         basectx = ctx.p1()
 
     style = web.config('web', 'style')
     if 'style' in web.req.qsparams:
         style = web.req.qsparams['style']
 
     diff = diffs(web, ctx, basectx, None, style)
 
     parity = paritygen(web.stripecount)
     diffstatsgen = diffstatgen(ctx, basectx)
     diffstats = diffstat(web.tmpl, ctx, diffstatsgen, parity)
 
     return dict(
         diff=diff,
         symrev=symrevorshortnode(web.req, ctx),
         basenode=basectx.hex(),
         changesettag=showtags,
         changesetbookmark=showbookmarks,
         changesetbranch=showbranch,
         files=files,
         diffsummary=lambda **x: diffsummary(diffstatsgen),
         diffstat=diffstats,
         archives=web.archivelist(ctx.hex()),
         **pycompat.strkwargs(commonentry(web.repo, ctx)))
 
 def listfilediffs(tmpl, files, node, max):
     for f in files[:max]:
         yield tmpl.generate('filedifflink', {'node': hex(node), 'file': f})
     if len(files) > max:
         yield tmpl.generate('fileellipses', {})
 
 def diffs(web, ctx, basectx, files, style, linerange=None,
           lineidprefix=''):
 
     def prettyprintlines(lines, blockno):
         for lineno, l in enumerate(lines, 1):
             difflineno = "%d.%d" % (blockno, lineno)
             if l.startswith('+'):
                 ltype = "difflineplus"
             elif l.startswith('-'):
                 ltype = "difflineminus"
             elif l.startswith('@'):
                 ltype = "difflineat"
             else:
                 ltype = "diffline"
             yield web.tmpl.generate(ltype, {
                 'line': l,
                 'lineno': lineno,
                 'lineid': lineidprefix + "l%s" % difflineno,
                 'linenumber': "% 8s" % difflineno,
             })
 
     repo = web.repo
     if files:
         m = match.exact(repo.root, repo.getcwd(), files)
     else:
         m = match.always(repo.root, repo.getcwd())
 
     diffopts = patch.diffopts(repo.ui, untrusted=True)
     node1 = basectx.node()
     node2 = ctx.node()
     parity = paritygen(web.stripecount)
 
     diffhunks = patch.diffhunks(repo, node1, node2, m, opts=diffopts)
     for blockno, (fctx1, fctx2, header, hunks) in enumerate(diffhunks, 1):
         if style != 'raw':
             header = header[1:]
         lines = [h + '\n' for h in header]
         for hunkrange, hunklines in hunks:
             if linerange is not None and hunkrange is not None:
                 s1, l1, s2, l2 = hunkrange
                 if not mdiff.hunkinrange((s2, l2), linerange):
                     continue
             lines.extend(hunklines)
         if lines:
             yield web.tmpl.generate('diffblock', {
                 'parity': next(parity),
                 'blockno': blockno,
                 'lines': prettyprintlines(lines, blockno),
             })
 
 def compare(tmpl, context, leftlines, rightlines):
     '''Generator function that provides side-by-side comparison data.'''
 
     def compline(type, leftlineno, leftline, rightlineno, rightline):
         lineid = leftlineno and ("l%d" % leftlineno) or ''
         lineid += rightlineno and ("r%d" % rightlineno) or ''
         llno = '%d' % leftlineno if leftlineno else ''
         rlno = '%d' % rightlineno if rightlineno else ''
         return tmpl.generate('comparisonline', {
             'type': type,
             'lineid': lineid,
             'leftlineno': leftlineno,
             'leftlinenumber': "% 6s" % llno,
             'leftline': leftline or '',
             'rightlineno': rightlineno,
             'rightlinenumber': "% 6s" % rlno,
             'rightline': rightline or '',
         })
 
     def getblock(opcodes):
         for type, llo, lhi, rlo, rhi in opcodes:
             len1 = lhi - llo
             len2 = rhi - rlo
             count = min(len1, len2)
             for i in xrange(count):
                 yield compline(type=type,
                                leftlineno=llo + i + 1,
                                leftline=leftlines[llo + i],
                                rightlineno=rlo + i + 1,
                                rightline=rightlines[rlo + i])
             if len1 > len2:
                 for i in xrange(llo + count, lhi):
                     yield compline(type=type,
                                    leftlineno=i + 1,
                                    leftline=leftlines[i],
                                    rightlineno=None,
                                    rightline=None)
             elif len2 > len1:
                 for i in xrange(rlo + count, rhi):
                     yield compline(type=type,
                                    leftlineno=None,
                                    leftline=None,
                                    rightlineno=i + 1,
                                    rightline=rightlines[i])
 
     s = difflib.SequenceMatcher(None, leftlines, rightlines)
     if context < 0:
         yield tmpl.generate('comparisonblock',
                             {'lines': getblock(s.get_opcodes())})
     else:
         for oc in s.get_grouped_opcodes(n=context):
             yield tmpl.generate('comparisonblock', {'lines': getblock(oc)})
 
 def diffstatgen(ctx, basectx):
     '''Generator function that provides the diffstat data.'''
 
     stats = patch.diffstatdata(
         util.iterlines(ctx.diff(basectx, noprefix=False)))
     maxname, maxtotal, addtotal, removetotal, binary = patch.diffstatsum(stats)
     while True:
         yield stats, maxname, maxtotal, addtotal, removetotal, binary
 
 def diffsummary(statgen):
     '''Return a short summary of the diff.'''
 
     stats, maxname, maxtotal, addtotal, removetotal, binary = next(statgen)
     return _(' %d files changed, %d insertions(+), %d deletions(-)\n') % (
              len(stats), addtotal, removetotal)
 
 def diffstat(tmpl, ctx, statgen, parity):
     '''Return a diffstat template for each file in the diff.'''
 
     stats, maxname, maxtotal, addtotal, removetotal, binary = next(statgen)
     files = ctx.files()
 
     def pct(i):
         if maxtotal == 0:
             return 0
         return (float(i) / maxtotal) * 100
 
     fileno = 0
     for filename, adds, removes, isbinary in stats:
         template = 'diffstatlink' if filename in files else 'diffstatnolink'
         total = adds + removes
         fileno += 1
         yield tmpl.generate(template, {
             'node': ctx.hex(),
             'file': filename,
             'fileno': fileno,
             'total': total,
             'addpct': pct(adds),
             'removepct': pct(removes),
             'parity': next(parity),
         })
 
 class sessionvars(object):
     def __init__(self, vars, start='?'):
         self.start = start
         self.vars = vars
     def __getitem__(self, key):
         return self.vars[key]
     def __setitem__(self, key, value):
         self.vars[key] = value
     def __copy__(self):
         return sessionvars(copy.copy(self.vars), self.start)
     def __iter__(self):
         separator = self.start
         for key, value in sorted(self.vars.iteritems()):
             yield {'name': key,
                    'value': pycompat.bytestr(value),
                    'separator': separator,
             }
             separator = '&'
 
 class wsgiui(uimod.ui):
     # default termwidth breaks under mod_wsgi
     def termwidth(self):
         return 80
 
 def getwebsubs(repo):
     websubtable = []
     websubdefs = repo.ui.configitems('websub')
     # we must maintain interhg backwards compatibility
     websubdefs += repo.ui.configitems('interhg')
     for key, pattern in websubdefs:
         # grab the delimiter from the character after the "s"
         unesc = pattern[1:2]
         delim = re.escape(unesc)
 
         # identify portions of the pattern, taking care to avoid escaped
         # delimiters. the replace format and flags are optional, but
         # delimiters are required.
         match = re.match(
             br'^s%s(.+)(?:(?<=\\\\)|(?<!\\))%s(.*)%s([ilmsux])*$'
             % (delim, delim, delim), pattern)
         if not match:
             repo.ui.warn(_("websub: invalid pattern for %s: %s\n")
                               % (key, pattern))
             continue
 
         # we need to unescape the delimiter for regexp and format
         delim_re = re.compile(br'(?<!\\)\\%s' % delim)
         regexp = delim_re.sub(unesc, match.group(1))
         format = delim_re.sub(unesc, match.group(2))
 
         # the pattern allows for 6 regexp flags, so set them if necessary
         flagin = match.group(3)
         flags = 0
         if flagin:
             for flag in flagin.upper():
                 flags |= re.__dict__[flag]
 
         try:
             regexp = re.compile(regexp, flags)
             websubtable.append((regexp, format))
         except re.error:
             repo.ui.warn(_("websub: invalid regexp for %s: %s\n")
                          % (key, regexp))
     return websubtable