hgweb: web.encoding should override encoding.encoding (issue1183)

mercurial/hgweb/hgweb_mod.py

@@ -1,312 +1,313 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, incorporated herein by reference.
 
 import os
 from mercurial import ui, hg, hook, error, encoding, templater
 from common import get_mtime, ErrorResponse
 from common import HTTP_OK, HTTP_BAD_REQUEST, HTTP_NOT_FOUND, HTTP_SERVER_ERROR
 from common import HTTP_UNAUTHORIZED, HTTP_METHOD_NOT_ALLOWED
 from request import wsgirequest
 import webcommands, protocol, webutil
 
 perms = {
     'changegroup': 'pull',
     'changegroupsubset': 'pull',
     'unbundle': 'push',
     'stream_out': 'pull',
 }
 
 class hgweb(object):
     def __init__(self, repo, name=None):
         if isinstance(repo, str):
             u = ui.ui()
             u.setconfig('ui', 'report_untrusted', 'off')
             u.setconfig('ui', 'interactive', 'off')
             self.repo = hg.repository(u, repo)
         else:
             self.repo = repo
 
         hook.redirect(True)
         self.mtime = -1
         self.reponame = name
         self.archives = 'zip', 'gz', 'bz2'
         self.stripecount = 1
         # a repo owner may set web.templates in .hg/hgrc to get any file
         # readable by the user running the CGI script
         self.templatepath = self.config('web', 'templates')
 
     # The CGI scripts are often run by a user different from the repo owner.
     # Trust the settings from the .hg/hgrc files by default.
     def config(self, section, name, default=None, untrusted=True):
         return self.repo.ui.config(section, name, default,
                                    untrusted=untrusted)
 
     def configbool(self, section, name, default=False, untrusted=True):
         return self.repo.ui.configbool(section, name, default,
                                        untrusted=untrusted)
 
     def configlist(self, section, name, default=None, untrusted=True):
         return self.repo.ui.configlist(section, name, default,
                                        untrusted=untrusted)
 
     def refresh(self):
         mtime = get_mtime(self.repo.root)
         if mtime != self.mtime:
             self.mtime = mtime
             self.repo = hg.repository(self.repo.ui, self.repo.root)
             self.maxchanges = int(self.config("web", "maxchanges", 10))
             self.stripecount = int(self.config("web", "stripes", 1))
             self.maxshortchanges = int(self.config("web", "maxshortchanges", 60))
             self.maxfiles = int(self.config("web", "maxfiles", 10))
             self.allowpull = self.configbool("web", "allowpull", True)
-            self.encoding = self.config("web", "encoding", encoding.encoding)
+            encoding.encoding = self.config("web", "encoding",
+                                            encoding.encoding)
 
     def run(self):
         if not os.environ.get('GATEWAY_INTERFACE', '').startswith("CGI/1."):
             raise RuntimeError("This function is only intended to be "
                                "called while running as a CGI script.")
         import mercurial.hgweb.wsgicgi as wsgicgi
         wsgicgi.launch(self)
 
     def __call__(self, env, respond):
         req = wsgirequest(env, respond)
         return self.run_wsgi(req)
 
     def run_wsgi(self, req):
 
         self.refresh()
 
         # process this if it's a protocol request
         # protocol bits don't need to create any URLs
         # and the clients always use the old URL structure
 
         cmd = req.form.get('cmd', [''])[0]
         if cmd and cmd in protocol.__all__:
             try:
                 if cmd in perms:
                     try:
                         self.check_perm(req, perms[cmd])
                     except ErrorResponse, inst:
                         if cmd == 'unbundle':
                             req.drain()
                         raise
                 method = getattr(protocol, cmd)
                 return method(self.repo, req)
             except ErrorResponse, inst:
                 req.respond(inst, protocol.HGTYPE)
                 if not inst.message:
                     return []
                 return '0\n%s\n' % inst.message,
 
         # work with CGI variables to create coherent structure
         # use SCRIPT_NAME, PATH_INFO and QUERY_STRING as well as our REPO_NAME
 
         req.url = req.env['SCRIPT_NAME']
         if not req.url.endswith('/'):
             req.url += '/'
         if 'REPO_NAME' in req.env:
             req.url += req.env['REPO_NAME'] + '/'
 
         if 'PATH_INFO' in req.env:
             parts = req.env['PATH_INFO'].strip('/').split('/')
             repo_parts = req.env.get('REPO_NAME', '').split('/')
             if parts[:len(repo_parts)] == repo_parts:
                 parts = parts[len(repo_parts):]
             query = '/'.join(parts)
         else:
             query = req.env['QUERY_STRING'].split('&', 1)[0]
             query = query.split(';', 1)[0]
 
         # translate user-visible url structure to internal structure
 
         args = query.split('/', 2)
         if 'cmd' not in req.form and args and args[0]:
 
             cmd = args.pop(0)
             style = cmd.rfind('-')
             if style != -1:
                 req.form['style'] = [cmd[:style]]
                 cmd = cmd[style+1:]
 
             # avoid accepting e.g. style parameter as command
             if hasattr(webcommands, cmd):
                 req.form['cmd'] = [cmd]
             else:
                 cmd = ''
 
             if cmd == 'static':
                 req.form['file'] = ['/'.join(args)]
             else:
                 if args and args[0]:
                     node = args.pop(0)
                     req.form['node'] = [node]
                 if args:
                     req.form['file'] = args
 
             if cmd == 'archive':
                 fn = req.form['node'][0]
                 for type_, spec in self.archive_specs.iteritems():
                     ext = spec[2]
                     if fn.endswith(ext):
                         req.form['node'] = [fn[:-len(ext)]]
                         req.form['type'] = [type_]
 
         # process the web interface request
 
         try:
             tmpl = self.templater(req)
-            ctype = tmpl('mimetype', encoding=self.encoding)
+            ctype = tmpl('mimetype', encoding=encoding.encoding)
             ctype = templater.stringify(ctype)
 
             # check read permissions non-static content
             if cmd != 'static':
                 self.check_perm(req, None)
 
             if cmd == '':
                 req.form['cmd'] = [tmpl.cache['default']]
                 cmd = req.form['cmd'][0]
 
             if cmd not in webcommands.__all__:
                 msg = 'no such method: %s' % cmd
                 raise ErrorResponse(HTTP_BAD_REQUEST, msg)
             elif cmd == 'file' and 'raw' in req.form.get('style', []):
                 self.ctype = ctype
                 content = webcommands.rawfile(self, req, tmpl)
             else:
                 content = getattr(webcommands, cmd)(self, req, tmpl)
                 req.respond(HTTP_OK, ctype)
 
             return content
 
         except error.LookupError, err:
             req.respond(HTTP_NOT_FOUND, ctype)
             msg = str(err)
             if 'manifest' not in msg:
                 msg = 'revision not found: %s' % err.name
             return tmpl('error', error=msg)
         except (error.RepoError, error.RevlogError), inst:
             req.respond(HTTP_SERVER_ERROR, ctype)
             return tmpl('error', error=str(inst))
         except ErrorResponse, inst:
             req.respond(inst, ctype)
             return tmpl('error', error=inst.message)
 
     def templater(self, req):
 
         # determine scheme, port and server name
         # this is needed to create absolute urls
 
         proto = req.env.get('wsgi.url_scheme')
         if proto == 'https':
             proto = 'https'
             default_port = "443"
         else:
             proto = 'http'
             default_port = "80"
 
         port = req.env["SERVER_PORT"]
         port = port != default_port and (":" + port) or ""
         urlbase = '%s://%s%s' % (proto, req.env['SERVER_NAME'], port)
         staticurl = self.config("web", "staticurl") or req.url + 'static/'
         if not staticurl.endswith('/'):
             staticurl += '/'
 
         # some functions for the templater
 
         def header(**map):
-            yield tmpl('header', encoding=self.encoding, **map)
+            yield tmpl('header', encoding=encoding.encoding, **map)
 
         def footer(**map):
             yield tmpl("footer", **map)
 
         def motd(**map):
             yield self.config("web", "motd", "")
 
         # figure out which style to use
 
         vars = {}
         style = self.config("web", "style", "paper")
         if 'style' in req.form:
             style = req.form['style'][0]
             vars['style'] = style
 
         start = req.url[-1] == '?' and '&' or '?'
         sessionvars = webutil.sessionvars(vars, start)
         mapfile = templater.stylemap(style, self.templatepath)
 
         if not self.reponame:
             self.reponame = (self.config("web", "name")
                              or req.env.get('REPO_NAME')
                              or req.url.strip('/') or self.repo.root)
 
         # create the templater
 
         tmpl = templater.templater(mapfile,
                                    defaults={"url": req.url,
                                              "staticurl": staticurl,
                                              "urlbase": urlbase,
                                              "repo": self.reponame,
                                              "header": header,
                                              "footer": footer,
                                              "motd": motd,
                                              "sessionvars": sessionvars
                                             })
         return tmpl
 
     def archivelist(self, nodeid):
         allowed = self.configlist("web", "allow_archive")
         for i, spec in self.archive_specs.iteritems():
             if i in allowed or self.configbool("web", "allow" + i):
                 yield {"type" : i, "extension" : spec[2], "node" : nodeid}
 
     archive_specs = {
         'bz2': ('application/x-tar', 'tbz2', '.tar.bz2', None),
         'gz': ('application/x-tar', 'tgz', '.tar.gz', None),
         'zip': ('application/zip', 'zip', '.zip', None),
         }
 
     def check_perm(self, req, op):
         '''Check permission for operation based on request data (including
         authentication info). Return if op allowed, else raise an ErrorResponse
         exception.'''
 
         user = req.env.get('REMOTE_USER')
 
         deny_read = self.configlist('web', 'deny_read')
         if deny_read and (not user or deny_read == ['*'] or user in deny_read):
             raise ErrorResponse(HTTP_UNAUTHORIZED, 'read not authorized')
 
         allow_read = self.configlist('web', 'allow_read')
         result = (not allow_read) or (allow_read == ['*'])
         if not (result or user in allow_read):
             raise ErrorResponse(HTTP_UNAUTHORIZED, 'read not authorized')
 
         if op == 'pull' and not self.allowpull:
             raise ErrorResponse(HTTP_UNAUTHORIZED, 'pull not authorized')
         elif op == 'pull' or op is None: # op is None for interface requests
             return
 
         # enforce that you can only push using POST requests
         if req.env['REQUEST_METHOD'] != 'POST':
             msg = 'push requires POST request'
             raise ErrorResponse(HTTP_METHOD_NOT_ALLOWED, msg)
 
         # require ssl by default for pushing, auth info cannot be sniffed
         # and replayed
         scheme = req.env.get('wsgi.url_scheme')
         if self.configbool('web', 'push_ssl', True) and scheme != 'https':
             raise ErrorResponse(HTTP_OK, 'ssl required')
 
         deny = self.configlist('web', 'deny_push')
         if deny and (not user or deny == ['*'] or user in deny):
             raise ErrorResponse(HTTP_UNAUTHORIZED, 'push not authorized')
 
         allow = self.configlist('web', 'allow_push')
         result = allow and (allow == ['*'] or user in allow)
         if not result:
             raise ErrorResponse(HTTP_UNAUTHORIZED, 'push not authorized')

mercurial/hgweb/hgwebdir_mod.py

@@ -1,329 +1,331 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, incorporated herein by reference.
 
 import os, time
 from mercurial.i18n import _
 from mercurial import ui, hg, util, templater
 from mercurial import error, encoding
 from common import ErrorResponse, get_mtime, staticfile, paritygen,\
                    get_contact, HTTP_OK, HTTP_NOT_FOUND, HTTP_SERVER_ERROR
 from hgweb_mod import hgweb
 from request import wsgirequest
 import webutil
 
 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/*" makes every subrepo of /bar/ to be
         # mounted as foo/subrepo
         # and "foo = /bar/**" also recurses into the subdirectories,
         # remember to use it without working dir.
         try:
             recurse = {'*': False, '**': True}[roottail]
         except KeyError:
             repos[prefix] = root
             continue
         roothead = os.path.normpath(roothead)
         for path in util.walkrepos(roothead, followsym=True, recurse=recurse):
             path = os.path.normpath(path)
             name = util.pconvert(path[len(roothead):]).strip('/')
             if prefix:
                 name = prefix + '/' + name
             repos[name] = path
     return repos.items()
 
 class hgwebdir(object):
     refreshinterval = 20
 
     def __init__(self, conf, baseui=None):
         self.conf = conf
         self.baseui = baseui
         self.lastrefresh = 0
         self.refresh()
 
     def refresh(self):
         if self.lastrefresh + self.refreshinterval > time.time():
             return
 
         if self.baseui:
             self.ui = self.baseui.copy()
         else:
             self.ui = ui.ui()
             self.ui.setconfig('ui', 'report_untrusted', 'off')
             self.ui.setconfig('ui', 'interactive', 'off')
 
         if not isinstance(self.conf, (dict, list, tuple)):
             map = {'paths': 'hgweb-paths'}
             self.ui.readconfig(self.conf, remap=map, trust=True)
             paths = self.ui.configitems('hgweb-paths')
         elif isinstance(self.conf, (list, tuple)):
             paths = self.conf
         elif isinstance(self.conf, dict):
             paths = self.conf.items()
 
+        encoding.encoding = self.ui.config('web', 'encoding',
+                                           encoding.encoding)
         self.motd = self.ui.config('web', 'motd')
         self.style = self.ui.config('web', 'style', 'paper')
         self.stripecount = self.ui.config('web', 'stripes', 1)
         if self.stripecount:
             self.stripecount = int(self.stripecount)
         self._baseurl = self.ui.config('web', 'baseurl')
 
         self.repos = findrepos(paths)
         for prefix, root in self.ui.configitems('collections'):
             prefix = util.pconvert(prefix)
             for path in util.walkrepos(root, followsym=True):
                 repo = os.path.normpath(path)
                 name = util.pconvert(repo)
                 if name.startswith(prefix):
                     name = name[len(prefix):]
                 self.repos.append((name.lstrip('/'), repo))
 
         self.repos.sort()
         self.lastrefresh = time.time()
 
     def run(self):
         if not os.environ.get('GATEWAY_INTERFACE', '').startswith("CGI/1."):
             raise RuntimeError("This function is only intended to be "
                                "called while running as a CGI script.")
         import mercurial.hgweb.wsgicgi as wsgicgi
         wsgicgi.launch(self)
 
     def __call__(self, env, respond):
         req = wsgirequest(env, respond)
         return self.run_wsgi(req)
 
     def read_allowed(self, 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.env.get('REMOTE_USER')
 
         deny_read = ui.configlist('web', 'deny_read', untrusted=True)
         if deny_read and (not user or deny_read == ['*'] or user in 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 (allow_read == ['*']) or (user in allow_read):
             return True
 
         return False
 
     def run_wsgi(self, req):
         try:
             try:
                 self.refresh()
 
                 virtual = req.env.get("PATH_INFO", "").strip('/')
                 tmpl = self.templater(req)
                 ctype = tmpl('mimetype', encoding=encoding.encoding)
                 ctype = templater.stringify(ctype)
 
                 # a static file
                 if virtual.startswith('static/') or 'static' in req.form:
                     if virtual.startswith('static/'):
                         fname = virtual[7:]
                     else:
                         fname = req.form['static'][0]
                     static = templater.templatepath('static')
                     return (staticfile(static, fname, req),)
 
                 # top-level index
                 elif not virtual:
                     req.respond(HTTP_OK, ctype)
                     return self.makeindex(req, tmpl)
 
                 # nested indexes and hgwebs
 
                 repos = dict(self.repos)
                 while virtual:
                     real = repos.get(virtual)
                     if real:
                         req.env['REPO_NAME'] = virtual
                         try:
                             repo = hg.repository(self.ui, real)
                             return hgweb(repo).run_wsgi(req)
                         except IOError, inst:
                             msg = inst.strerror
                             raise ErrorResponse(HTTP_SERVER_ERROR, msg)
                         except error.RepoError, inst:
                             raise ErrorResponse(HTTP_SERVER_ERROR, str(inst))
 
                     # browse subdirectories
                     subdir = virtual + '/'
                     if [r for r in repos if r.startswith(subdir)]:
                         req.respond(HTTP_OK, ctype)
                         return self.makeindex(req, tmpl, subdir)
 
                     up = virtual.rfind('/')
                     if up < 0:
                         break
                     virtual = virtual[:up]
 
                 # prefixes not found
                 req.respond(HTTP_NOT_FOUND, ctype)
                 return tmpl("notfound", repo=virtual)
 
             except ErrorResponse, err:
                 req.respond(err, ctype)
                 return tmpl('error', error=err.message or '')
         finally:
             tmpl = None
 
     def makeindex(self, req, tmpl, subdir=""):
 
         def archivelist(ui, nodeid, url):
             allowed = ui.configlist("web", "allow_archive", untrusted=True)
             for i in [('zip', '.zip'), ('gz', '.tar.gz'), ('bz2', '.tar.bz2')]:
                 if i[0] in allowed or ui.configbool("web", "allow" + i[0],
                                                     untrusted=True):
                     yield {"type" : i[0], "extension": i[1],
                            "node": nodeid, "url": url}
 
         sortdefault = 'name', False
         def entries(sortcolumn="", descending=False, subdir="", **map):
             rows = []
             parity = paritygen(self.stripecount)
             for name, path in self.repos:
                 if not name.startswith(subdir):
                     continue
                 name = name[len(subdir):]
 
                 u = self.ui.copy()
                 try:
                     u.readconfig(os.path.join(path, '.hg', 'hgrc'))
                 except Exception, e:
                     u.warn(_('error reading %s/.hg/hgrc: %s\n') % (path, e))
                     continue
                 def get(section, name, default=None):
                     return u.config(section, name, default, untrusted=True)
 
                 if u.configbool("web", "hidden", untrusted=True):
                     continue
 
                 if not self.read_allowed(u, req):
                     continue
 
                 parts = [name]
                 if 'PATH_INFO' in req.env:
                     parts.insert(0, req.env['PATH_INFO'].rstrip('/'))
                 if req.env['SCRIPT_NAME']:
                     parts.insert(0, req.env['SCRIPT_NAME'])
                 url = ('/'.join(parts).replace("//", "/")) + '/'
 
                 # update time with local timezone
                 try:
                     d = (get_mtime(path), util.makedate()[1])
                 except OSError:
                     continue
 
                 contact = get_contact(get)
                 description = get("web", "description", "")
                 name = get("web", "name", name)
                 row = dict(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))
                 if (not sortcolumn or (sortcolumn, descending) == sortdefault):
                     # fast path for unsorted output
                     row['parity'] = parity.next()
                     yield row
                 else:
                     rows.append((row["%s_sort" % sortcolumn], row))
             if rows:
                 rows.sort()
                 if descending:
                     rows.reverse()
                 for key, row in rows:
                     row['parity'] = parity.next()
                     yield row
 
         self.refresh()
         sortable = ["name", "description", "contact", "lastchange"]
         sortcolumn, descending = sortdefault
         if 'sort' in req.form:
             sortcolumn = req.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()
         if self._baseurl is not None:
             req.env['SCRIPT_NAME'] = self._baseurl
 
         return tmpl("index", entries=entries, subdir=subdir,
                     sortcolumn=sortcolumn, descending=descending,
                     **dict(sort))
 
     def templater(self, req):
 
         def header(**map):
             yield tmpl('header', encoding=encoding.encoding, **map)
 
         def footer(**map):
             yield tmpl("footer", **map)
 
         def motd(**map):
             if self.motd is not None:
                 yield self.motd
             else:
                 yield config('web', 'motd', '')
 
         def config(section, name, default=None, untrusted=True):
             return self.ui.config(section, name, default, untrusted)
 
         if self._baseurl is not None:
             req.env['SCRIPT_NAME'] = self._baseurl
 
         url = req.env.get('SCRIPT_NAME', '')
         if not url.endswith('/'):
             url += '/'
 
         vars = {}
         style = self.style
         if 'style' in req.form:
             vars['style'] = style = req.form['style'][0]
         start = url[-1] == '?' and '&' or '?'
         sessionvars = webutil.sessionvars(vars, start)
 
         staticurl = config('web', 'staticurl') or url + 'static/'
         if not staticurl.endswith('/'):
             staticurl += '/'
 
         style = 'style' in req.form and req.form['style'][0] or self.style
         mapfile = templater.stylemap(style)
         tmpl = templater.templater(mapfile,
                                    defaults={"header": header,
                                              "footer": footer,
                                              "motd": motd,
                                              "url": url,
                                              "staticurl": staticurl,
                                              "sessionvars": sessionvars})
         return tmpl