hgweb: add some documentation

It took longer than I wanted to grok how the various parts of hgweb
worked. So I added some class and method documentation to help whoever
hacks on this next.

mercurial/hgweb/hgweb_mod.py

@@ -1,424 +1,447
 # 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.
 
 import os, re
 from mercurial import ui, hg, hook, error, encoding, templater, util, repoview
 from mercurial.templatefilters import websub
 from mercurial.i18n import _
 from common import get_stat, ErrorResponse, permhooks, caching
 from common import HTTP_OK, HTTP_NOT_MODIFIED, HTTP_BAD_REQUEST
 from common import HTTP_NOT_FOUND, HTTP_SERVER_ERROR
 from request import wsgirequest
 import webcommands, protocol, webutil
 
 perms = {
     'changegroup': 'pull',
     'changegroupsubset': 'pull',
     'getbundle': 'pull',
     'stream_out': 'pull',
     'listkeys': 'pull',
     'unbundle': 'push',
     'pushkey': 'push',
 }
 
 ## Files of interest
 # Used to check if the repository has changed looking at mtime and size of
 # theses files. This should probably be relocated a bit higher in core.
 foi = [('spath', '00changelog.i'),
        ('spath', 'phaseroots'), # ! phase can change content at the same size
        ('spath', 'obsstore'),
        ('path', 'bookmarks'), # ! bookmark can change content at the same size
       ]
 
 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 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 = ui.ui()
             r = hg.repository(u, repo)
         else:
             # we trust caller to give us a private copy
             r = repo
 
         r = self._getview(r)
         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')
         # 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.repo = r
         hook.redirect(True)
         self.repostate = ((-1, -1), (-1, -1))
         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')
         self.websubtable = self.loadwebsub()
 
     # 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 _getview(self, 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."""
         viewconfig = repo.ui.config('web', 'view', 'served',
                                     untrusted=True)
         if viewconfig == 'all':
             return repo.unfiltered()
         elif viewconfig in repoview.filtertable:
             return repo.filtered(viewconfig)
         else:
             return repo.filtered('served')
 
     def refresh(self, request=None):
         repostate = []
         # file of interrests mtime and size
         for meth, fname in foi:
             prefix = getattr(self.repo, meth)
             st = get_stat(prefix, fname)
             repostate.append((st.st_mtime, st.st_size))
         repostate = tuple(repostate)
         # we need to compare file size in addition to mtime to catch
         # changes made less than a second ago
         if repostate != self.repostate:
             r = hg.repository(self.repo.baseui, self.repo.url())
             self.repo = self._getview(r)
             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)
             encoding.encoding = self.config("web", "encoding",
                                             encoding.encoding)
             # update these last to avoid threads seeing empty settings
             self.repostate = repostate
             # mtime is needed for ETag
             self.mtime = st.st_mtime
         if request:
             self.repo.ui.environ = request.env
 
     def run(self):
+        """Start a server from CGI environment.
+
+        Modern servers should be using WSGI and should avoid this
+        method, if possible.
+        """
         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):
+        """Run the WSGI application.
+
+        This may be called by multiple threads.
+        """
         req = wsgirequest(env, respond)
         return self.run_wsgi(req)
 
     def run_wsgi(self, req):
+        """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.
+        """
         self.refresh(req)
 
         # 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]
 
         # 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 protocol.iscmd(cmd):
             try:
                 if query:
                     raise ErrorResponse(HTTP_NOT_FOUND)
                 if cmd in perms:
                     self.check_perm(req, perms[cmd])
                 return protocol.call(self.repo, req, cmd)
             except ErrorResponse as inst:
                 # A client that sends unbundle without 100-continue will
                 # break if we respond early.
                 if (cmd == 'unbundle' and
                     (req.env.get('HTTP_EXPECT',
                                  '').lower() != '100-continue') or
                     req.env.get('X-HgHttp2', '')):
                     req.drain()
                 else:
                     req.headers.append(('Connection', 'Close'))
                 req.respond(inst, protocol.HGTYPE,
                             body='0\n%s\n' % inst.message)
                 return ''
 
         # 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 util.safehasattr(webcommands, cmd):
                 req.form['cmd'] = [cmd]
 
             if cmd == 'static':
                 req.form['file'] = ['/'.join(args)]
             else:
                 if args and args[0]:
                     node = args.pop(0).replace('%2F', '/')
                     req.form['node'] = [node]
                 if args:
                     req.form['file'] = args
 
             ua = req.env.get('HTTP_USER_AGENT', '')
             if cmd == 'rev' and 'mercurial' in ua:
                 req.form['style'] = ['raw']
 
             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=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 self.configbool('web', 'cache', True):
                 caching(self, req) # 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 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, error.RepoLookupError) as err:
             req.respond(HTTP_NOT_FOUND, ctype)
             msg = str(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:
             req.respond(HTTP_SERVER_ERROR, ctype)
             return tmpl('error', error=str(inst))
         except ErrorResponse as inst:
             req.respond(inst, ctype)
             if inst.code == HTTP_NOT_MODIFIED:
                 # Not allowed to return a body on a 304
                 return ['']
             return tmpl('error', error=inst.message)
 
     def loadwebsub(self):
         websubtable = []
         websubdefs = self.repo.ui.configitems('websub')
         # we must maintain interhg backwards compatibility
         websubdefs += self.repo.ui.configitems('interhg')
         for key, pattern in websubdefs:
             # grab the delimiter from the character after the "s"
             unesc = pattern[1]
             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(
                 r'^s%s(.+)(?:(?<=\\\\)|(?<!\\))%s(.*)%s([ilmsux])*$'
                 % (delim, delim, delim), pattern)
             if not match:
                 self.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(r'(?<!\\)\\%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:
                 self.repo.ui.warn(_("websub: invalid regexp for %s: %s\n")
                                   % (key, regexp))
         return websubtable
 
     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)
         logourl = self.config("web", "logourl", "http://mercurial.selenic.com/")
         logoimg = self.config("web", "logoimg", "hglogo.png")
         staticurl = self.config("web", "staticurl") or req.url + '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 = (
             req.form.get('style', [None])[0],
             self.config('web', 'style'),
             'paper',
         )
         style, mapfile = templater.stylemap(styles, self.templatepath)
         if style == styles[0]:
             vars['style'] = style
 
         start = req.url[-1] == '?' and '&' or '?'
         sessionvars = webutil.sessionvars(vars, start)
 
         if not self.reponame:
             self.reponame = (self.config("web", "name")
                              or req.env.get('REPO_NAME')
                              or req.url.strip('/') or self.repo.root)
 
         def websubfilter(text):
             return websub(text, self.websubtable)
 
         # create the templater
 
         tmpl = templater.templater(mapfile,
                                    filters={"websub": websubfilter},
                                    defaults={"url": req.url,
                                              "logourl": logourl,
                                              "logoimg": logoimg,
                                              "staticurl": staticurl,
                                              "urlbase": urlbase,
                                              "repo": self.reponame,
                                              "encoding": encoding.encoding,
                                              "motd": motd,
                                              "sessionvars": sessionvars,
                                              "pathdef": makebreadcrumb(req.url),
                                              "style": style,
                                             })
         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-bzip2', 'tbz2', '.tar.bz2', None),
         'gz': ('application/x-gzip', 'tgz', '.tar.gz', None),
         'zip': ('application/zip', 'zip', '.zip', None),
         }
 
     def check_perm(self, req, op):
         for permhook in permhooks:
             permhook(self, req, op)

mercurial/hgweb/hgwebdir_mod.py

@@ -1,478 +1,485
 # 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.
 
 import os, re, time
 from mercurial.i18n import _
 from mercurial import ui, hg, scmutil, util, templater
 from mercurial import error, encoding
 from common import ErrorResponse, get_mtime, staticfile, paritygen, ismember, \
                    get_contact, HTTP_OK, HTTP_NOT_FOUND, HTTP_SERVER_ERROR
 from hgweb_mod import hgweb, makebreadcrumb
 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/*" 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('hg', '/opt', ['/opt/r', '/opt/r/r', '/opt']))
     [('hg/r', '/opt/r'), ('hg/r/r', '/opt/r/r'), ('hg', '/opt')]
     >>> conv(urlrepos('', '/opt', ['/opt/r', '/opt/r/r', '/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("http://host.org/base", "80")
     ('host.org', '80', '/base')
     >>> geturlcgivars("http://host.org:8000/base", "80")
     ('host.org', '8000', '/base')
     >>> geturlcgivars('/base', 8000)
     ('', '8000', '/base')
     >>> geturlcgivars("base", '8000')
     ('', '8000', '/base')
     >>> geturlcgivars("http://host", '8000')
     ('host', '8000', '/')
     >>> geturlcgivars("http://host/", '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, str(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):
         refreshinterval = 20
         if self.ui:
             refreshinterval = self.ui.configint('web', 'refreshinterval',
                                                 refreshinterval)
 
         # 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 = ui.ui()
             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 util.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',
                                            encoding.encoding)
         self.style = self.ui.config('web', 'style', 'paper')
         self.templatepath = self.ui.config('web', 'templates', None)
         self.stripecount = self.ui.config('web', 'stripes', 1)
         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 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 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, req):
         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 = 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, req)
                 return []
 
             # top-level index
             elif not virtual:
                 req.respond(HTTP_OK, ctype)
                 return self.makeindex(req, tmpl)
 
             # nested indexes and hgwebs
 
             repos = dict(self.repos)
             virtualrepo = virtual
             while virtualrepo:
                 real = repos.get(virtualrepo)
                 if real:
                     req.env['REPO_NAME'] = virtualrepo
                     try:
                         # ensure caller gets private copy of ui
                         repo = hg.repository(self.ui.copy(), real)
                         return hgweb(repo).run_wsgi(req)
                     except IOError as inst:
                         msg = inst.strerror
                         raise ErrorResponse(HTTP_SERVER_ERROR, msg)
                     except error.RepoError as inst:
                         raise ErrorResponse(HTTP_SERVER_ERROR, str(inst))
 
                 up = virtualrepo.rfind('/')
                 if up < 0:
                     break
                 virtualrepo = virtualrepo[:up]
 
             # 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)
 
             # prefixes not found
             req.respond(HTTP_NOT_FOUND, ctype)
             return tmpl("notfound", repo=virtual)
 
         except ErrorResponse as 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)
             archives = []
             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):
                     archives.append({"type" : i[0], "extension": i[1],
                                      "node": nodeid, "url": url})
             return archives
 
         def rawentries(subdir="", **map):
 
             descend = self.ui.configbool('web', 'descend', True)
             collapse = self.ui.configbool('web', 'collapse', False)
             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]
                 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 = 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), util.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}
 
                     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=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
 
                 # 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), util.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,
                        }
 
                 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 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()
         self.updatereqenv(req.env)
 
         return tmpl("index", entries=entries, subdir=subdir,
                     pathdef=makebreadcrumb('/' + subdir, self.prefix),
                     sortcolumn=sortcolumn, descending=descending,
                     **dict(sort))
 
     def templater(self, req):
 
         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)
 
         self.updatereqenv(req.env)
 
         url = req.env.get('SCRIPT_NAME', '')
         if not url.endswith('/'):
             url += '/'
 
         vars = {}
         styles = (
             req.form.get('style', [None])[0],
             config('web', 'style'),
             'paper'
         )
         style, mapfile = templater.stylemap(styles, self.templatepath)
         if style == styles[0]:
             vars['style'] = style
 
         start = url[-1] == '?' and '&' or '?'
         sessionvars = webutil.sessionvars(vars, start)
         logourl = config('web', 'logourl', 'http://mercurial.selenic.com/')
         logoimg = config('web', 'logoimg', 'hglogo.png')
         staticurl = config('web', 'staticurl') or url + 'static/'
         if not staticurl.endswith('/'):
             staticurl += '/'
 
         tmpl = templater.templater(mapfile,
                                    defaults={"encoding": encoding.encoding,
                                              "motd": motd,
                                              "url": url,
                                              "logourl": logourl,
                                              "logoimg": logoimg,
                                              "staticurl": staticurl,
                                              "sessionvars": sessionvars,
                                              "style": style,
                                              })
         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

@@ -1,134 +1,140
 # 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.
 
 import socket, cgi, errno
 from mercurial import util
 from common import ErrorResponse, statusmessage, HTTP_NOT_MODIFIED
 
 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.iterkeys():
         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
     for k, v in form.iteritems():
         form[k] = [i.strip() for i in v]
     return form
 
 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['wsgi.version']
         if (version < (1, 0)) or (version >= (2, 0)):
             raise RuntimeError("Unknown and unsupported WSGI version %d.%d"
                                % version)
         self.inp = wsgienv['wsgi.input']
         self.err = wsgienv['wsgi.errors']
         self.threaded = wsgienv['wsgi.multithread']
         self.multiprocess = wsgienv['wsgi.multiprocess']
         self.run_once = wsgienv['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 = []
 
     def __iter__(self):
         return iter([])
 
     def read(self, count=-1):
         return self.inp.read(count)
 
     def drain(self):
         '''need to read all data from request, httplib is half-duplex'''
         length = int(self.env.get('CONTENT_LENGTH') or 0)
         for s in util.filechunkiter(self.inp, limit=length):
             pass
 
     def respond(self, status, type, filename=None, body=None):
         if self._start_response is not None:
             self.headers.append(('Content-Type', type))
             if filename:
                 filename = (filename.split('/')[-1]
                             .replace('\\', '\\\\').replace('"', '\\"'))
                 self.headers.append(('Content-Disposition',
                                      'inline; filename="%s"' % filename))
             if body is not None:
                 self.headers.append(('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, status.message)
             elif status == 200:
                 status = '200 Script output follows'
             elif isinstance(status, int):
                 status = statusmessage(status)
 
             self.server_write = self._start_response(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 writelines(self, lines):
         for line in lines:
             self.write(line)
 
     def flush(self):
         return None
 
     def close(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