hgweb: drop the default argument for get_stat

This default argument is used twice and is making things confusing. Making it
explicit helps to clarify coming changesets

mercurial/hgweb/common.py

@@ -1,192 +1,192 b''
 # hgweb/common.py - Utility functions needed by hgweb_mod and hgwebdir_mod
 #
 # 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 errno, mimetypes, os
 
 HTTP_OK = 200
 HTTP_NOT_MODIFIED = 304
 HTTP_BAD_REQUEST = 400
 HTTP_UNAUTHORIZED = 401
 HTTP_FORBIDDEN = 403
 HTTP_NOT_FOUND = 404
 HTTP_METHOD_NOT_ALLOWED = 405
 HTTP_SERVER_ERROR = 500
 
 
 def ismember(ui, username, userlist):
     """Check if username is a member of userlist.
 
     If userlist has a single '*' member, all users are considered members.
     Can be overridden by extensions to provide more complex authorization
     schemes.
     """
     return userlist == ['*'] or username in userlist
 
 def checkauthz(hgweb, 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 = hgweb.configlist('web', 'deny_read')
     if deny_read and (not user or ismember(hgweb.repo.ui, user, deny_read)):
         raise ErrorResponse(HTTP_UNAUTHORIZED, 'read not authorized')
 
     allow_read = hgweb.configlist('web', 'allow_read')
     if allow_read and (not ismember(hgweb.repo.ui, user, allow_read)):
         raise ErrorResponse(HTTP_UNAUTHORIZED, 'read not authorized')
 
     if op == 'pull' and not hgweb.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 hgweb.configbool('web', 'push_ssl', True) and scheme != 'https':
         raise ErrorResponse(HTTP_FORBIDDEN, 'ssl required')
 
     deny = hgweb.configlist('web', 'deny_push')
     if deny and (not user or ismember(hgweb.repo.ui, user, deny)):
         raise ErrorResponse(HTTP_UNAUTHORIZED, 'push not authorized')
 
     allow = hgweb.configlist('web', 'allow_push')
     if not (allow and ismember(hgweb.repo.ui, user, allow)):
         raise ErrorResponse(HTTP_UNAUTHORIZED, 'push not authorized')
 
 # Hooks for hgweb permission checks; extensions can add hooks here.
 # Each hook is invoked like this: hook(hgweb, request, operation),
 # where operation is either read, pull or push. Hooks should either
 # raise an ErrorResponse exception, or just return.
 #
 # It is possible to do both authentication and authorization through
 # this.
 permhooks = [checkauthz]
 
 
 class ErrorResponse(Exception):
     def __init__(self, code, message=None, headers=[]):
         if message is None:
             message = _statusmessage(code)
         Exception.__init__(self)
         self.code = code
         self.message = message
         self.headers = headers
     def __str__(self):
         return self.message
 
 class continuereader(object):
     def __init__(self, f, write):
         self.f = f
         self._write = write
         self.continued = False
 
     def read(self, amt=-1):
         if not self.continued:
             self.continued = True
             self._write('HTTP/1.1 100 Continue\r\n\r\n')
         return self.f.read(amt)
 
     def __getattr__(self, attr):
         if attr in ('close', 'readline', 'readlines', '__iter__'):
             return getattr(self.f, attr)
         raise AttributeError
 
 def _statusmessage(code):
     from BaseHTTPServer import BaseHTTPRequestHandler
     responses = BaseHTTPRequestHandler.responses
     return responses.get(code, ('Error', 'Unknown error'))[0]
 
 def statusmessage(code, message=None):
     return '%d %s' % (code, message or _statusmessage(code))
 
-def get_stat(spath, fn="00changelog.i"):
-    """stat fn (00changelog.i by default) if it exists, spath otherwise"""
+def get_stat(spath, fn):
+    """stat fn if it exists, spath otherwise"""
     cl_path = os.path.join(spath, fn)
     if os.path.exists(cl_path):
         return os.stat(cl_path)
     else:
         return os.stat(spath)
 
 def get_mtime(spath):
-    return get_stat(spath).st_mtime
+    return get_stat(spath, "00changelog.i").st_mtime
 
 def staticfile(directory, fname, req):
     """return a file inside directory with guessed Content-Type header
 
     fname always uses '/' as directory separator and isn't allowed to
     contain unusual path components.
     Content-Type is guessed using the mimetypes module.
     Return an empty string if fname is illegal or file not found.
 
     """
     parts = fname.split('/')
     for part in parts:
         if (part in ('', os.curdir, os.pardir) or
             os.sep in part or os.altsep is not None and os.altsep in part):
             return
     fpath = os.path.join(*parts)
     if isinstance(directory, str):
         directory = [directory]
     for d in directory:
         path = os.path.join(d, fpath)
         if os.path.exists(path):
             break
     try:
         os.stat(path)
         ct = mimetypes.guess_type(path)[0] or "text/plain"
         fp = open(path, 'rb')
         data = fp.read()
         fp.close()
         req.respond(HTTP_OK, ct, body=data)
     except TypeError:
         raise ErrorResponse(HTTP_SERVER_ERROR, 'illegal filename')
     except OSError as err:
         if err.errno == errno.ENOENT:
             raise ErrorResponse(HTTP_NOT_FOUND)
         else:
             raise ErrorResponse(HTTP_SERVER_ERROR, err.strerror)
 
 def paritygen(stripecount, offset=0):
     """count parity of horizontal stripes for easier reading"""
     if stripecount and offset:
         # account for offset, e.g. due to building the list in reverse
         count = (stripecount + offset) % stripecount
         parity = (stripecount + offset) / stripecount & 1
     else:
         count = 0
         parity = 0
     while True:
         yield parity
         count += 1
         if stripecount and count >= stripecount:
             parity = 1 - parity
             count = 0
 
 def get_contact(config):
     """Return repo contact information or empty string.
 
     web.contact is the primary source, but if that is not set, try
     ui.username or $EMAIL as a fallback to display something useful.
     """
     return (config("web", "contact") or
             config("ui", "username") or
             os.environ.get("EMAIL") or "")
 
 def caching(web, req):
     tag = str(web.mtime)
     if req.env.get('HTTP_IF_NONE_MATCH') == tag:
         raise ErrorResponse(HTTP_NOT_MODIFIED)
     req.headers.append(('ETag', tag))

mercurial/hgweb/hgweb_mod.py

@@ -1,412 +1,412 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.
 
 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',
 }
 
 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):
     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):
-        st = get_stat(self.repo.spath)
+        st = get_stat(self.repo.spath, '00changelog.i')
         pst = get_stat(self.repo.spath, 'phaseroots')
         # changelog mtime and size, phaseroots mtime and size
         repostate = ((st.st_mtime, st.st_size), (pst.st_mtime, pst.st_size))
         # 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):
         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(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)
                     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)