wrap string literals in error messages

mercurial/hgweb/hgweb_mod.py

@@ -1,311 +1,312
 # 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)
 
     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.")
+            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 = 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)
 
         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

@@ -1,328 +1,329
 # 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()
 
         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.")
+            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

mercurial/hgweb/server.py

@@ -1,296 +1,298
 # hgweb/server.py - The standalone hg web server.
 #
 # 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, sys, errno, urllib, BaseHTTPServer, socket, SocketServer, traceback
 from mercurial import hg, util, error
 from hgweb_mod import hgweb
 from hgwebdir_mod import hgwebdir
 from mercurial.i18n import _
 
 def _splitURI(uri):
     """ Return path and query splited from uri
 
     Just like CGI environment, the path is unquoted, the query is
     not.
     """
     if '?' in uri:
         path, query = uri.split('?', 1)
     else:
         path, query = uri, ''
     return urllib.unquote(path), query
 
 class _error_logger(object):
     def __init__(self, handler):
         self.handler = handler
     def flush(self):
         pass
     def write(self, str):
         self.writelines(str.split('\n'))
     def writelines(self, seq):
         for msg in seq:
             self.handler.log_error("HG error:  %s", msg)
 
 class _hgwebhandler(object, BaseHTTPServer.BaseHTTPRequestHandler):
 
     url_scheme = 'http'
 
     def __init__(self, *args, **kargs):
         self.protocol_version = 'HTTP/1.1'
         BaseHTTPServer.BaseHTTPRequestHandler.__init__(self, *args, **kargs)
 
     def _log_any(self, fp, format, *args):
         fp.write("%s - - [%s] %s\n" % (self.client_address[0],
                                        self.log_date_time_string(),
                                        format % args))
         fp.flush()
 
     def log_error(self, format, *args):
         self._log_any(self.server.errorlog, format, *args)
 
     def log_message(self, format, *args):
         self._log_any(self.server.accesslog, format, *args)
 
     def do_write(self):
         try:
             self.do_hgweb()
         except socket.error, inst:
             if inst[0] != errno.EPIPE:
                 raise
 
     def do_POST(self):
         try:
             self.do_write()
         except StandardError:
             self._start_response("500 Internal Server Error", [])
             self._write("Internal Server Error")
             tb = "".join(traceback.format_exception(*sys.exc_info()))
-            self.log_error("Exception happened during processing request '%s':\n%s",
-                           self.path, tb)
+            self.log_error("Exception happened during processing "
+                           "request '%s':\n%s", self.path, tb)
 
     def do_GET(self):
         self.do_POST()
 
     def do_hgweb(self):
         path, query = _splitURI(self.path)
 
         env = {}
         env['GATEWAY_INTERFACE'] = 'CGI/1.1'
         env['REQUEST_METHOD'] = self.command
         env['SERVER_NAME'] = self.server.server_name
         env['SERVER_PORT'] = str(self.server.server_port)
         env['REQUEST_URI'] = self.path
         env['SCRIPT_NAME'] = self.server.prefix
         env['PATH_INFO'] = path[len(self.server.prefix):]
         env['REMOTE_HOST'] = self.client_address[0]
         env['REMOTE_ADDR'] = self.client_address[0]
         if query:
             env['QUERY_STRING'] = query
 
         if self.headers.typeheader is None:
             env['CONTENT_TYPE'] = self.headers.type
         else:
             env['CONTENT_TYPE'] = self.headers.typeheader
         length = self.headers.getheader('content-length')
         if length:
             env['CONTENT_LENGTH'] = length
         for header in [h for h in self.headers.keys()
                        if h not in ('content-type', 'content-length')]:
             hkey = 'HTTP_' + header.replace('-', '_').upper()
             hval = self.headers.getheader(header)
             hval = hval.replace('\n', '').strip()
             if hval:
                 env[hkey] = hval
         env['SERVER_PROTOCOL'] = self.request_version
         env['wsgi.version'] = (1, 0)
         env['wsgi.url_scheme'] = self.url_scheme
         env['wsgi.input'] = self.rfile
         env['wsgi.errors'] = _error_logger(self)
         env['wsgi.multithread'] = isinstance(self.server,
                                              SocketServer.ThreadingMixIn)
         env['wsgi.multiprocess'] = isinstance(self.server,
                                               SocketServer.ForkingMixIn)
         env['wsgi.run_once'] = 0
 
         self.close_connection = True
         self.saved_status = None
         self.saved_headers = []
         self.sent_headers = False
         self.length = None
         for chunk in self.server.application(env, self._start_response):
             self._write(chunk)
 
     def send_headers(self):
         if not self.saved_status:
-            raise AssertionError("Sending headers before start_response() called")
+            raise AssertionError("Sending headers before "
+                                 "start_response() called")
         saved_status = self.saved_status.split(None, 1)
         saved_status[0] = int(saved_status[0])
         self.send_response(*saved_status)
         should_close = True
         for h in self.saved_headers:
             self.send_header(*h)
             if h[0].lower() == 'content-length':
                 should_close = False
                 self.length = int(h[1])
         # The value of the Connection header is a list of case-insensitive
         # tokens separated by commas and optional whitespace.
         if 'close' in [token.strip().lower() for token in
                        self.headers.get('connection', '').split(',')]:
             should_close = True
         if should_close:
             self.send_header('Connection', 'close')
         self.close_connection = should_close
         self.end_headers()
         self.sent_headers = True
 
     def _start_response(self, http_status, headers, exc_info=None):
         code, msg = http_status.split(None, 1)
         code = int(code)
         self.saved_status = http_status
         bad_headers = ('connection', 'transfer-encoding')
         self.saved_headers = [h for h in headers
                               if h[0].lower() not in bad_headers]
         return self._write
 
     def _write(self, data):
         if not self.saved_status:
             raise AssertionError("data written before start_response() called")
         elif not self.sent_headers:
             self.send_headers()
         if self.length is not None:
             if len(data) > self.length:
-                raise AssertionError("Content-length header sent, but more bytes than specified are being written.")
+                raise AssertionError("Content-length header sent, but more "
+                                     "bytes than specified are being written.")
             self.length = self.length - len(data)
         self.wfile.write(data)
         self.wfile.flush()
 
 class _shgwebhandler(_hgwebhandler):
 
     url_scheme = 'https'
 
     def setup(self):
         self.connection = self.request
         self.rfile = socket._fileobject(self.request, "rb", self.rbufsize)
         self.wfile = socket._fileobject(self.request, "wb", self.wbufsize)
 
     def do_write(self):
         from OpenSSL.SSL import SysCallError
         try:
             super(_shgwebhandler, self).do_write()
         except SysCallError, inst:
             if inst.args[0] != errno.EPIPE:
                 raise
 
     def handle_one_request(self):
         from OpenSSL.SSL import SysCallError, ZeroReturnError
         try:
             super(_shgwebhandler, self).handle_one_request()
         except (SysCallError, ZeroReturnError):
             self.close_connection = True
             pass
 
 def create_server(ui, repo):
     use_threads = True
 
     def openlog(opt, default):
         if opt and opt != '-':
             return open(opt, 'a')
         return default
 
     if repo is None:
         myui = ui
     else:
         myui = repo.ui
     address = myui.config("web", "address", "")
     port = int(myui.config("web", "port", 8000))
     prefix = myui.config("web", "prefix", "")
     if prefix:
         prefix = "/" + prefix.strip("/")
     use_ipv6 = myui.configbool("web", "ipv6")
     webdir_conf = myui.config("web", "webdir_conf")
     ssl_cert = myui.config("web", "certificate")
     accesslog = openlog(myui.config("web", "accesslog", "-"), sys.stdout)
     errorlog = openlog(myui.config("web", "errorlog", "-"), sys.stderr)
 
     if use_threads:
         try:
             from threading import activeCount
         except ImportError:
             use_threads = False
 
     if use_threads:
         _mixin = SocketServer.ThreadingMixIn
     else:
         if hasattr(os, "fork"):
             _mixin = SocketServer.ForkingMixIn
         else:
             class _mixin:
                 pass
 
     class MercurialHTTPServer(object, _mixin, BaseHTTPServer.HTTPServer):
 
         # SO_REUSEADDR has broken semantics on windows
         if os.name == 'nt':
             allow_reuse_address = 0
 
         def __init__(self, *args, **kargs):
             BaseHTTPServer.HTTPServer.__init__(self, *args, **kargs)
             self.accesslog = accesslog
             self.errorlog = errorlog
             self.daemon_threads = True
             def make_handler():
                 if webdir_conf:
                     hgwebobj = hgwebdir(webdir_conf, ui)
                 elif repo is not None:
                     hgwebobj = hgweb(hg.repository(repo.ui, repo.root))
                 else:
                     raise error.RepoError(_("There is no Mercurial repository"
                                             " here (.hg not found)"))
                 return hgwebobj
             self.application = make_handler()
 
             if ssl_cert:
                 try:
                     from OpenSSL import SSL
                     ctx = SSL.Context(SSL.SSLv23_METHOD)
                 except ImportError:
                     raise util.Abort(_("SSL support is unavailable"))
                 ctx.use_privatekey_file(ssl_cert)
                 ctx.use_certificate_file(ssl_cert)
                 sock = socket.socket(self.address_family, self.socket_type)
                 self.socket = SSL.Connection(ctx, sock)
                 self.server_bind()
                 self.server_activate()
 
             self.addr, self.port = self.socket.getsockname()[0:2]
             self.prefix = prefix
             self.fqaddr = socket.getfqdn(address)
 
     class IPv6HTTPServer(MercurialHTTPServer):
         address_family = getattr(socket, 'AF_INET6', None)
 
         def __init__(self, *args, **kwargs):
             if self.address_family is None:
                 raise error.RepoError(_('IPv6 is not available on this system'))
             super(IPv6HTTPServer, self).__init__(*args, **kwargs)
 
     if ssl_cert:
         handler = _shgwebhandler
     else:
         handler = _hgwebhandler
 
     # ugly hack due to python issue5853 (for threaded use)
     import mimetypes; mimetypes.init()
 
     try:
         if use_ipv6:
             return IPv6HTTPServer((address, port), handler)
         else:
             return MercurialHTTPServer((address, port), handler)
     except socket.error, inst:
         raise util.Abort(_("cannot start server at '%s:%d': %s")
                          % (address, port, inst.args[1]))

mercurial/localrepo.py

@@ -1,2132 +1,2134
 # localrepo.py - read/write repository class for mercurial
 #
 # 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.
 
 from node import bin, hex, nullid, nullrev, short
 from i18n import _
 import repo, changegroup
 import changelog, dirstate, filelog, manifest, context
 import lock, transaction, store, encoding
 import util, extensions, hook, error
 import match as match_
 import merge as merge_
 from lock import release
 import weakref, stat, errno, os, time, inspect
 propertycache = util.propertycache
 
 class localrepository(repo.repository):
     capabilities = set(('lookup', 'changegroupsubset', 'branchmap'))
     supported = set('revlogv1 store fncache'.split())
 
     def __init__(self, baseui, path=None, create=0):
         repo.repository.__init__(self)
         self.root = os.path.realpath(path)
         self.path = os.path.join(self.root, ".hg")
         self.origroot = path
         self.opener = util.opener(self.path)
         self.wopener = util.opener(self.root)
 
         if not os.path.isdir(self.path):
             if create:
                 if not os.path.exists(path):
                     os.mkdir(path)
                 os.mkdir(self.path)
                 requirements = ["revlogv1"]
                 if baseui.configbool('format', 'usestore', True):
                     os.mkdir(os.path.join(self.path, "store"))
                     requirements.append("store")
                     if baseui.configbool('format', 'usefncache', True):
                         requirements.append("fncache")
                     # create an invalid changelog
                     self.opener("00changelog.i", "a").write(
                         '\0\0\0\2' # represents revlogv2
                         ' dummy changelog to prevent using the old repo layout'
                     )
                 reqfile = self.opener("requires", "w")
                 for r in requirements:
                     reqfile.write("%s\n" % r)
                 reqfile.close()
             else:
                 raise error.RepoError(_("repository %s not found") % path)
         elif create:
             raise error.RepoError(_("repository %s already exists") % path)
         else:
             # find requirements
             requirements = set()
             try:
                 requirements = set(self.opener("requires").read().splitlines())
             except IOError, inst:
                 if inst.errno != errno.ENOENT:
                     raise
             for r in requirements - self.supported:
                 raise error.RepoError(_("requirement '%s' not supported") % r)
 
         self.store = store.store(requirements, self.path, util.opener)
         self.spath = self.store.path
         self.sopener = self.store.opener
         self.sjoin = self.store.join
         self.opener.createmode = self.store.createmode
 
         self.baseui = baseui
         self.ui = baseui.copy()
         try:
             self.ui.readconfig(self.join("hgrc"), self.root)
             extensions.loadall(self.ui)
         except IOError:
             pass
 
         self.tagscache = None
         self._tagstypecache = None
         self.branchcache = None
         self._ubranchcache = None  # UTF-8 version of branchcache
         self._branchcachetip = None
         self.nodetagscache = None
         self.filterpats = {}
         self._datafilters = {}
         self._transref = self._lockref = self._wlockref = None
 
     @propertycache
     def changelog(self):
         c = changelog.changelog(self.sopener)
         if 'HG_PENDING' in os.environ:
             p = os.environ['HG_PENDING']
             if p.startswith(self.root):
                 c.readpending('00changelog.i.a')
         self.sopener.defversion = c.version
         return c
 
     @propertycache
     def manifest(self):
         return manifest.manifest(self.sopener)
 
     @propertycache
     def dirstate(self):
         return dirstate.dirstate(self.opener, self.ui, self.root)
 
     def __getitem__(self, changeid):
         if changeid is None:
             return context.workingctx(self)
         return context.changectx(self, changeid)
 
     def __nonzero__(self):
         return True
 
     def __len__(self):
         return len(self.changelog)
 
     def __iter__(self):
         for i in xrange(len(self)):
             yield i
 
     def url(self):
         return 'file:' + self.root
 
     def hook(self, name, throw=False, **args):
         return hook.hook(self.ui, self, name, throw, **args)
 
     tag_disallowed = ':\r\n'
 
     def _tag(self, names, node, message, local, user, date, extra={}):
         if isinstance(names, str):
             allchars = names
             names = (names,)
         else:
             allchars = ''.join(names)
         for c in self.tag_disallowed:
             if c in allchars:
                 raise util.Abort(_('%r cannot be used in a tag name') % c)
 
         for name in names:
             self.hook('pretag', throw=True, node=hex(node), tag=name,
                       local=local)
 
         def writetags(fp, names, munge, prevtags):
             fp.seek(0, 2)
             if prevtags and prevtags[-1] != '\n':
                 fp.write('\n')
             for name in names:
                 m = munge and munge(name) or name
                 if self._tagstypecache and name in self._tagstypecache:
                     old = self.tagscache.get(name, nullid)
                     fp.write('%s %s\n' % (hex(old), m))
                 fp.write('%s %s\n' % (hex(node), m))
             fp.close()
 
         prevtags = ''
         if local:
             try:
                 fp = self.opener('localtags', 'r+')
             except IOError:
                 fp = self.opener('localtags', 'a')
             else:
                 prevtags = fp.read()
 
             # local tags are stored in the current charset
             writetags(fp, names, None, prevtags)
             for name in names:
                 self.hook('tag', node=hex(node), tag=name, local=local)
             return
 
         try:
             fp = self.wfile('.hgtags', 'rb+')
         except IOError:
             fp = self.wfile('.hgtags', 'ab')
         else:
             prevtags = fp.read()
 
         # committed tags are stored in UTF-8
         writetags(fp, names, encoding.fromlocal, prevtags)
 
         if '.hgtags' not in self.dirstate:
             self.add(['.hgtags'])
 
         tagnode = self.commit(['.hgtags'], message, user, date, extra=extra)
 
         for name in names:
             self.hook('tag', node=hex(node), tag=name, local=local)
 
         return tagnode
 
     def tag(self, names, node, message, local, user, date):
         '''tag a revision with one or more symbolic names.
 
         names is a list of strings or, when adding a single tag, names may be a
         string.
 
         if local is True, the tags are stored in a per-repository file.
         otherwise, they are stored in the .hgtags file, and a new
         changeset is committed with the change.
 
         keyword arguments:
 
         local: whether to store tags in non-version-controlled file
         (default False)
 
         message: commit message to use if committing
 
         user: name of user to use if committing
 
         date: date tuple to use if committing'''
 
         for x in self.status()[:5]:
             if '.hgtags' in x:
                 raise util.Abort(_('working copy of .hgtags is changed '
                                    '(please commit .hgtags manually)'))
 
         self.tags() # instantiate the cache
         self._tag(names, node, message, local, user, date)
 
     def tags(self):
         '''return a mapping of tag to node'''
         if self.tagscache:
             return self.tagscache
 
         globaltags = {}
         tagtypes = {}
 
         def readtags(lines, fn, tagtype):
             filetags = {}
             count = 0
 
             def warn(msg):
                 self.ui.warn(_("%s, line %s: %s\n") % (fn, count, msg))
 
             for l in lines:
                 count += 1
                 if not l:
                     continue
                 s = l.split(" ", 1)
                 if len(s) != 2:
                     warn(_("cannot parse entry"))
                     continue
                 node, key = s
                 key = encoding.tolocal(key.strip()) # stored in UTF-8
                 try:
                     bin_n = bin(node)
                 except TypeError:
                     warn(_("node '%s' is not well formed") % node)
                     continue
                 if bin_n not in self.changelog.nodemap:
                     warn(_("tag '%s' refers to unknown node") % key)
                     continue
 
                 h = []
                 if key in filetags:
                     n, h = filetags[key]
                     h.append(n)
                 filetags[key] = (bin_n, h)
 
             for k, nh in filetags.iteritems():
                 if k not in globaltags:
                     globaltags[k] = nh
                     tagtypes[k] = tagtype
                     continue
 
                 # we prefer the global tag if:
                 #  it supercedes us OR
                 #  mutual supercedes and it has a higher rank
                 # otherwise we win because we're tip-most
                 an, ah = nh
                 bn, bh = globaltags[k]
                 if (bn != an and an in bh and
                     (bn not in ah or len(bh) > len(ah))):
                     an = bn
                 ah.extend([n for n in bh if n not in ah])
                 globaltags[k] = an, ah
                 tagtypes[k] = tagtype
 
         # read the tags file from each head, ending with the tip
         f = None
         for rev, node, fnode in self._hgtagsnodes():
             f = (f and f.filectx(fnode) or
                  self.filectx('.hgtags', fileid=fnode))
             readtags(f.data().splitlines(), f, "global")
 
         try:
             data = encoding.fromlocal(self.opener("localtags").read())
             # localtags are stored in the local character set
             # while the internal tag table is stored in UTF-8
             readtags(data.splitlines(), "localtags", "local")
         except IOError:
             pass
 
         self.tagscache = {}
         self._tagstypecache = {}
         for k, nh in globaltags.iteritems():
             n = nh[0]
             if n != nullid:
                 self.tagscache[k] = n
             self._tagstypecache[k] = tagtypes[k]
         self.tagscache['tip'] = self.changelog.tip()
         return self.tagscache
 
     def tagtype(self, tagname):
         '''
         return the type of the given tag. result can be:
 
         'local'  : a local tag
         'global' : a global tag
         None     : tag does not exist
         '''
 
         self.tags()
 
         return self._tagstypecache.get(tagname)
 
     def _hgtagsnodes(self):
         last = {}
         ret = []
         for node in reversed(self.heads()):
             c = self[node]
             rev = c.rev()
             try:
                 fnode = c.filenode('.hgtags')
             except error.LookupError:
                 continue
             ret.append((rev, node, fnode))
             if fnode in last:
                 ret[last[fnode]] = None
             last[fnode] = len(ret) - 1
         return [item for item in ret if item]
 
     def tagslist(self):
         '''return a list of tags ordered by revision'''
         l = []
         for t, n in self.tags().iteritems():
             try:
                 r = self.changelog.rev(n)
             except:
                 r = -2 # sort to the beginning of the list if unknown
             l.append((r, t, n))
         return [(t, n) for r, t, n in sorted(l)]
 
     def nodetags(self, node):
         '''return the tags associated with a node'''
         if not self.nodetagscache:
             self.nodetagscache = {}
             for t, n in self.tags().iteritems():
                 self.nodetagscache.setdefault(n, []).append(t)
         return self.nodetagscache.get(node, [])
 
     def _branchtags(self, partial, lrev):
         # TODO: rename this function?
         tiprev = len(self) - 1
         if lrev != tiprev:
             self._updatebranchcache(partial, lrev+1, tiprev+1)
             self._writebranchcache(partial, self.changelog.tip(), tiprev)
 
         return partial
 
     def branchmap(self):
         tip = self.changelog.tip()
         if self.branchcache is not None and self._branchcachetip == tip:
             return self.branchcache
 
         oldtip = self._branchcachetip
         self._branchcachetip = tip
         if self.branchcache is None:
             self.branchcache = {} # avoid recursion in changectx
         else:
             self.branchcache.clear() # keep using the same dict
         if oldtip is None or oldtip not in self.changelog.nodemap:
             partial, last, lrev = self._readbranchcache()
         else:
             lrev = self.changelog.rev(oldtip)
             partial = self._ubranchcache
 
         self._branchtags(partial, lrev)
         # this private cache holds all heads (not just tips)
         self._ubranchcache = partial
 
         # the branch cache is stored on disk as UTF-8, but in the local
         # charset internally
         for k, v in partial.iteritems():
             self.branchcache[encoding.tolocal(k)] = v
         return self.branchcache
 
 
     def branchtags(self):
         '''return a dict where branch names map to the tipmost head of
         the branch, open heads come before closed'''
         bt = {}
         for bn, heads in self.branchmap().iteritems():
             head = None
             for i in range(len(heads)-1, -1, -1):
                 h = heads[i]
                 if 'close' not in self.changelog.read(h)[5]:
                     head = h
                     break
             # no open heads were found
             if head is None:
                 head = heads[-1]
             bt[bn] = head
         return bt
 
 
     def _readbranchcache(self):
         partial = {}
         try:
             f = self.opener("branchheads.cache")
             lines = f.read().split('\n')
             f.close()
         except (IOError, OSError):
             return {}, nullid, nullrev
 
         try:
             last, lrev = lines.pop(0).split(" ", 1)
             last, lrev = bin(last), int(lrev)
             if lrev >= len(self) or self[lrev].node() != last:
                 # invalidate the cache
                 raise ValueError('invalidating branch cache (tip differs)')
             for l in lines:
                 if not l: continue
                 node, label = l.split(" ", 1)
                 partial.setdefault(label.strip(), []).append(bin(node))
         except KeyboardInterrupt:
             raise
         except Exception, inst:
             if self.ui.debugflag:
                 self.ui.warn(str(inst), '\n')
             partial, last, lrev = {}, nullid, nullrev
         return partial, last, lrev
 
     def _writebranchcache(self, branches, tip, tiprev):
         try:
             f = self.opener("branchheads.cache", "w", atomictemp=True)
             f.write("%s %s\n" % (hex(tip), tiprev))
             for label, nodes in branches.iteritems():
                 for node in nodes:
                     f.write("%s %s\n" % (hex(node), label))
             f.rename()
         except (IOError, OSError):
             pass
 
     def _updatebranchcache(self, partial, start, end):
         for r in xrange(start, end):
             c = self[r]
             b = c.branch()
             bheads = partial.setdefault(b, [])
             bheads.append(c.node())
             for p in c.parents():
                 pn = p.node()
                 if pn in bheads:
                     bheads.remove(pn)
 
     def lookup(self, key):
         if isinstance(key, int):
             return self.changelog.node(key)
         elif key == '.':
             return self.dirstate.parents()[0]
         elif key == 'null':
             return nullid
         elif key == 'tip':
             return self.changelog.tip()
         n = self.changelog._match(key)
         if n:
             return n
         if key in self.tags():
             return self.tags()[key]
         if key in self.branchtags():
             return self.branchtags()[key]
         n = self.changelog._partialmatch(key)
         if n:
             return n
 
         # can't find key, check if it might have come from damaged dirstate
         if key in self.dirstate.parents():
             raise error.Abort(_("working directory has unknown parent '%s'!")
                               % short(key))
         try:
             if len(key) == 20:
                 key = hex(key)
         except:
             pass
         raise error.RepoError(_("unknown revision '%s'") % key)
 
     def local(self):
         return True
 
     def join(self, f):
         return os.path.join(self.path, f)
 
     def wjoin(self, f):
         return os.path.join(self.root, f)
 
     def rjoin(self, f):
         return os.path.join(self.root, util.pconvert(f))
 
     def file(self, f):
         if f[0] == '/':
             f = f[1:]
         return filelog.filelog(self.sopener, f)
 
     def changectx(self, changeid):
         return self[changeid]
 
     def parents(self, changeid=None):
         '''get list of changectxs for parents of changeid'''
         return self[changeid].parents()
 
     def filectx(self, path, changeid=None, fileid=None):
         """changeid can be a changeset revision, node, or tag.
            fileid can be a file revision or node."""
         return context.filectx(self, path, changeid, fileid)
 
     def getcwd(self):
         return self.dirstate.getcwd()
 
     def pathto(self, f, cwd=None):
         return self.dirstate.pathto(f, cwd)
 
     def wfile(self, f, mode='r'):
         return self.wopener(f, mode)
 
     def _link(self, f):
         return os.path.islink(self.wjoin(f))
 
     def _filter(self, filter, filename, data):
         if filter not in self.filterpats:
             l = []
             for pat, cmd in self.ui.configitems(filter):
                 if cmd == '!':
                     continue
                 mf = match_.match(self.root, '', [pat])
                 fn = None
                 params = cmd
                 for name, filterfn in self._datafilters.iteritems():
                     if cmd.startswith(name):
                         fn = filterfn
                         params = cmd[len(name):].lstrip()
                         break
                 if not fn:
                     fn = lambda s, c, **kwargs: util.filter(s, c)
                 # Wrap old filters not supporting keyword arguments
                 if not inspect.getargspec(fn)[2]:
                     oldfn = fn
                     fn = lambda s, c, **kwargs: oldfn(s, c)
                 l.append((mf, fn, params))
             self.filterpats[filter] = l
 
         for mf, fn, cmd in self.filterpats[filter]:
             if mf(filename):
                 self.ui.debug(_("filtering %s through %s\n") % (filename, cmd))
                 data = fn(data, cmd, ui=self.ui, repo=self, filename=filename)
                 break
 
         return data
 
     def adddatafilter(self, name, filter):
         self._datafilters[name] = filter
 
     def wread(self, filename):
         if self._link(filename):
             data = os.readlink(self.wjoin(filename))
         else:
             data = self.wopener(filename, 'r').read()
         return self._filter("encode", filename, data)
 
     def wwrite(self, filename, data, flags):
         data = self._filter("decode", filename, data)
         try:
             os.unlink(self.wjoin(filename))
         except OSError:
             pass
         if 'l' in flags:
             self.wopener.symlink(data, filename)
         else:
             self.wopener(filename, 'w').write(data)
             if 'x' in flags:
                 util.set_flags(self.wjoin(filename), False, True)
 
     def wwritedata(self, filename, data):
         return self._filter("decode", filename, data)
 
     def transaction(self):
         tr = self._transref and self._transref() or None
         if tr and tr.running():
             return tr.nest()
 
         # abort here if the journal already exists
         if os.path.exists(self.sjoin("journal")):
             raise error.RepoError(_("journal already exists - run hg recover"))
 
         # save dirstate for rollback
         try:
             ds = self.opener("dirstate").read()
         except IOError:
             ds = ""
         self.opener("journal.dirstate", "w").write(ds)
         self.opener("journal.branch", "w").write(self.dirstate.branch())
 
         renames = [(self.sjoin("journal"), self.sjoin("undo")),
                    (self.join("journal.dirstate"), self.join("undo.dirstate")),
                    (self.join("journal.branch"), self.join("undo.branch"))]
         tr = transaction.transaction(self.ui.warn, self.sopener,
                                      self.sjoin("journal"),
                                      aftertrans(renames),
                                      self.store.createmode)
         self._transref = weakref.ref(tr)
         return tr
 
     def recover(self):
         lock = self.lock()
         try:
             if os.path.exists(self.sjoin("journal")):
                 self.ui.status(_("rolling back interrupted transaction\n"))
                 transaction.rollback(self.sopener, self.sjoin("journal"), self.ui.warn)
                 self.invalidate()
                 return True
             else:
                 self.ui.warn(_("no interrupted transaction available\n"))
                 return False
         finally:
             lock.release()
 
     def rollback(self):
         wlock = lock = None
         try:
             wlock = self.wlock()
             lock = self.lock()
             if os.path.exists(self.sjoin("undo")):
                 self.ui.status(_("rolling back last transaction\n"))
                 transaction.rollback(self.sopener, self.sjoin("undo"), self.ui.warn)
                 util.rename(self.join("undo.dirstate"), self.join("dirstate"))
                 try:
                     branch = self.opener("undo.branch").read()
                     self.dirstate.setbranch(branch)
                 except IOError:
                     self.ui.warn(_("Named branch could not be reset, "
                                    "current branch still is: %s\n")
                                  % encoding.tolocal(self.dirstate.branch()))
                 self.invalidate()
                 self.dirstate.invalidate()
             else:
                 self.ui.warn(_("no rollback information available\n"))
         finally:
             release(lock, wlock)
 
     def invalidate(self):
         for a in "changelog manifest".split():
             if a in self.__dict__:
                 delattr(self, a)
         self.tagscache = None
         self._tagstypecache = None
         self.nodetagscache = None
         self.branchcache = None
         self._ubranchcache = None
         self._branchcachetip = None
 
     def _lock(self, lockname, wait, releasefn, acquirefn, desc):
         try:
             l = lock.lock(lockname, 0, releasefn, desc=desc)
         except error.LockHeld, inst:
             if not wait:
                 raise
             self.ui.warn(_("waiting for lock on %s held by %r\n") %
                          (desc, inst.locker))
             # default to 600 seconds timeout
             l = lock.lock(lockname, int(self.ui.config("ui", "timeout", "600")),
                           releasefn, desc=desc)
         if acquirefn:
             acquirefn()
         return l
 
     def lock(self, wait=True):
         l = self._lockref and self._lockref()
         if l is not None and l.held:
             l.lock()
             return l
 
         l = self._lock(self.sjoin("lock"), wait, None, self.invalidate,
                        _('repository %s') % self.origroot)
         self._lockref = weakref.ref(l)
         return l
 
     def wlock(self, wait=True):
         l = self._wlockref and self._wlockref()
         if l is not None and l.held:
             l.lock()
             return l
 
         l = self._lock(self.join("wlock"), wait, self.dirstate.write,
                        self.dirstate.invalidate, _('working directory of %s') %
                        self.origroot)
         self._wlockref = weakref.ref(l)
         return l
 
     def _filecommit(self, fctx, manifest1, manifest2, linkrev, tr, changelist):
         """
         commit an individual file as part of a larger transaction
         """
 
         fname = fctx.path()
         text = fctx.data()
         flog = self.file(fname)
         fparent1 = manifest1.get(fname, nullid)
         fparent2 = fparent2o = manifest2.get(fname, nullid)
 
         meta = {}
         copy = fctx.renamed()
         if copy and copy[0] != fname:
             # Mark the new revision of this file as a copy of another
             # file.  This copy data will effectively act as a parent
             # of this new revision.  If this is a merge, the first
             # parent will be the nullid (meaning "look up the copy data")
             # and the second one will be the other parent.  For example:
             #
             # 0 --- 1 --- 3   rev1 changes file foo
             #   \       /     rev2 renames foo to bar and changes it
             #    \- 2 -/      rev3 should have bar with all changes and
             #                      should record that bar descends from
             #                      bar in rev2 and foo in rev1
             #
             # this allows this merge to succeed:
             #
             # 0 --- 1 --- 3   rev4 reverts the content change from rev2
             #   \       /     merging rev3 and rev4 should use bar@rev2
             #    \- 2 --- 4        as the merge base
             #
 
             cfname = copy[0]
             crev = manifest1.get(cfname)
             newfparent = fparent2
 
             if manifest2: # branch merge
                 if fparent2 == nullid or crev is None: # copied on remote side
                     if cfname in manifest2:
                         crev = manifest2[cfname]
                         newfparent = fparent1
 
             # find source in nearest ancestor if we've lost track
             if not crev:
                 self.ui.debug(_(" %s: searching for copy revision for %s\n") %
                               (fname, cfname))
                 for ancestor in self['.'].ancestors():
                     if cfname in ancestor:
                         crev = ancestor[cfname].filenode()
                         break
 
             self.ui.debug(_(" %s: copy %s:%s\n") % (fname, cfname, hex(crev)))
             meta["copy"] = cfname
             meta["copyrev"] = hex(crev)
             fparent1, fparent2 = nullid, newfparent
         elif fparent2 != nullid:
             # is one parent an ancestor of the other?
             fparentancestor = flog.ancestor(fparent1, fparent2)
             if fparentancestor == fparent1:
                 fparent1, fparent2 = fparent2, nullid
             elif fparentancestor == fparent2:
                 fparent2 = nullid
 
         # is the file changed?
         if fparent2 != nullid or flog.cmp(fparent1, text) or meta:
             changelist.append(fname)
             return flog.add(text, meta, tr, linkrev, fparent1, fparent2)
 
         # are just the flags changed during merge?
         if fparent1 !=  fparent2o and manifest1.flags(fname) != fctx.flags():
             changelist.append(fname)
 
         return fparent1
 
     def commit(self, files=None, text="", user=None, date=None, match=None,
                force=False, editor=False, extra={}):
         """Add a new revision to current repository.
 
         Revision information is gathered from the working directory, files and
         match can be used to filter the committed files.
         If editor is supplied, it is called to get a commit message.
         """
         wlock = self.wlock()
         try:
             p1, p2 = self.dirstate.parents()
 
             if (not force and p2 != nullid and match and
                 (match.files() or match.anypats())):
                 raise util.Abort(_('cannot partially commit a merge '
                                    '(do not specify files or patterns)'))
 
             if files:
                 modified, removed = [], []
                 for f in sorted(set(files)):
                     s = self.dirstate[f]
                     if s in 'nma':
                         modified.append(f)
                     elif s == 'r':
                         removed.append(f)
                     else:
                         self.ui.warn(_("%s not tracked!\n") % f)
                 changes = [modified, [], removed, [], []]
             else:
                 changes = self.status(match=match)
 
             if (not force and not extra.get("close") and p2 == nullid
                 and not (changes[0] or changes[1] or changes[2])
                 and self[None].branch() == self['.'].branch()):
                 self.ui.status(_("nothing changed\n"))
                 return None
 
             ms = merge_.mergestate(self)
             for f in changes[0]:
                 if f in ms and ms[f] == 'u':
                     raise util.Abort(_("unresolved merge conflicts "
                                                     "(see hg resolve)"))
 
             wctx = context.workingctx(self, (p1, p2), text, user, date,
                                       extra, changes)
             if editor:
                 wctx._text = editor(self, wctx,
                                     changes[1], changes[0], changes[2])
             ret = self.commitctx(wctx, True)
 
             # update dirstate and mergestate
             for f in changes[0] + changes[1]:
                 self.dirstate.normal(f)
             for f in changes[2]:
                 self.dirstate.forget(f)
             self.dirstate.setparents(ret)
             ms.reset()
 
             return ret
 
         finally:
             wlock.release()
 
     def commitctx(self, ctx, error=False):
         """Add a new revision to current repository.
 
         Revision information is passed via the context argument.
         """
 
         tr = lock = None
         removed = ctx.removed()
         p1, p2 = ctx.p1(), ctx.p2()
         m1 = p1.manifest().copy()
         m2 = p2.manifest()
         user = ctx.user()
 
         xp1, xp2 = p1.hex(), p2 and p2.hex() or ''
         self.hook("precommit", throw=True, parent1=xp1, parent2=xp2)
 
         lock = self.lock()
         try:
             tr = self.transaction()
             trp = weakref.proxy(tr)
 
             # check in files
             new = {}
             changed = []
             linkrev = len(self)
             for f in sorted(ctx.modified() + ctx.added()):
                 self.ui.note(f + "\n")
                 try:
                     fctx = ctx[f]
                     new[f] = self._filecommit(fctx, m1, m2, linkrev, trp,
                                               changed)
                     m1.set(f, fctx.flags())
                 except (OSError, IOError):
                     if error:
                         self.ui.warn(_("trouble committing %s!\n") % f)
                         raise
                     else:
                         removed.append(f)
 
             # update manifest
             m1.update(new)
             removed = [f for f in sorted(removed) if f in m1 or f in m2]
             drop = [f for f in removed if f in m1]
             for f in drop:
                 del m1[f]
             mn = self.manifest.add(m1, trp, linkrev, p1.manifestnode(),
                                    p2.manifestnode(), (new, drop))
 
             # update changelog
             self.changelog.delayupdate()
             n = self.changelog.add(mn, changed + removed, ctx.description(),
                                    trp, p1.node(), p2.node(),
                                    user, ctx.date(), ctx.extra().copy())
             p = lambda: self.changelog.writepending() and self.root or ""
             self.hook('pretxncommit', throw=True, node=hex(n), parent1=xp1,
                       parent2=xp2, pending=p)
             self.changelog.finalize(trp)
             tr.close()
 
             if self.branchcache:
                 self.branchtags()
 
             self.hook("commit", node=hex(n), parent1=xp1, parent2=xp2)
             return n
         finally:
             del tr
             lock.release()
 
     def walk(self, match, node=None):
         '''
         walk recursively through the directory tree or a given
         changeset, finding all files matched by the match
         function
         '''
         return self[node].walk(match)
 
     def status(self, node1='.', node2=None, match=None,
                ignored=False, clean=False, unknown=False):
         """return status of files between two nodes or node and working directory
 
         If node1 is None, use the first dirstate parent instead.
         If node2 is None, compare node1 with working directory.
         """
 
         def mfmatches(ctx):
             mf = ctx.manifest().copy()
             for fn in mf.keys():
                 if not match(fn):
                     del mf[fn]
             return mf
 
         if isinstance(node1, context.changectx):
             ctx1 = node1
         else:
             ctx1 = self[node1]
         if isinstance(node2, context.changectx):
             ctx2 = node2
         else:
             ctx2 = self[node2]
 
         working = ctx2.rev() is None
         parentworking = working and ctx1 == self['.']
         match = match or match_.always(self.root, self.getcwd())
         listignored, listclean, listunknown = ignored, clean, unknown
 
         # load earliest manifest first for caching reasons
         if not working and ctx2.rev() < ctx1.rev():
             ctx2.manifest()
 
         if not parentworking:
             def bad(f, msg):
                 if f not in ctx1:
                     self.ui.warn('%s: %s\n' % (self.dirstate.pathto(f), msg))
                 return False
             match.bad = bad
 
         if working: # we need to scan the working dir
             s = self.dirstate.status(match, listignored, listclean, listunknown)
             cmp, modified, added, removed, deleted, unknown, ignored, clean = s
 
             # check for any possibly clean files
             if parentworking and cmp:
                 fixup = []
                 # do a full compare of any files that might have changed
                 for f in sorted(cmp):
                     if (f not in ctx1 or ctx2.flags(f) != ctx1.flags(f)
                         or ctx1[f].cmp(ctx2[f].data())):
                         modified.append(f)
                     else:
                         fixup.append(f)
 
                 if listclean:
                     clean += fixup
 
                 # update dirstate for files that are actually clean
                 if fixup:
                     try:
                         # updating the dirstate is optional
                         # so we don't wait on the lock
                         wlock = self.wlock(False)
                         try:
                             for f in fixup:
                                 self.dirstate.normal(f)
                         finally:
                             wlock.release()
                     except error.LockError:
                         pass
 
         if not parentworking:
             mf1 = mfmatches(ctx1)
             if working:
                 # we are comparing working dir against non-parent
                 # generate a pseudo-manifest for the working dir
                 mf2 = mfmatches(self['.'])
                 for f in cmp + modified + added:
                     mf2[f] = None
                     mf2.set(f, ctx2.flags(f))
                 for f in removed:
                     if f in mf2:
                         del mf2[f]
             else:
                 # we are comparing two revisions
                 deleted, unknown, ignored = [], [], []
                 mf2 = mfmatches(ctx2)
 
             modified, added, clean = [], [], []
             for fn in mf2:
                 if fn in mf1:
                     if (mf1.flags(fn) != mf2.flags(fn) or
                         (mf1[fn] != mf2[fn] and
                          (mf2[fn] or ctx1[fn].cmp(ctx2[fn].data())))):
                         modified.append(fn)
                     elif listclean:
                         clean.append(fn)
                     del mf1[fn]
                 else:
                     added.append(fn)
             removed = mf1.keys()
 
         r = modified, added, removed, deleted, unknown, ignored, clean
         [l.sort() for l in r]
         return r
 
     def add(self, list):
         wlock = self.wlock()
         try:
             rejected = []
             for f in list:
                 p = self.wjoin(f)
                 try:
                     st = os.lstat(p)
                 except:
                     self.ui.warn(_("%s does not exist!\n") % f)
                     rejected.append(f)
                     continue
                 if st.st_size > 10000000:
                     self.ui.warn(_("%s: files over 10MB may cause memory and"
                                    " performance problems\n"
                                    "(use 'hg revert %s' to unadd the file)\n")
                                    % (f, f))
                 if not (stat.S_ISREG(st.st_mode) or stat.S_ISLNK(st.st_mode)):
                     self.ui.warn(_("%s not added: only files and symlinks "
                                    "supported currently\n") % f)
                     rejected.append(p)
                 elif self.dirstate[f] in 'amn':
                     self.ui.warn(_("%s already tracked!\n") % f)
                 elif self.dirstate[f] == 'r':
                     self.dirstate.normallookup(f)
                 else:
                     self.dirstate.add(f)
             return rejected
         finally:
             wlock.release()
 
     def forget(self, list):
         wlock = self.wlock()
         try:
             for f in list:
                 if self.dirstate[f] != 'a':
                     self.ui.warn(_("%s not added!\n") % f)
                 else:
                     self.dirstate.forget(f)
         finally:
             wlock.release()
 
     def remove(self, list, unlink=False):
         if unlink:
             for f in list:
                 try:
                     util.unlink(self.wjoin(f))
                 except OSError, inst:
                     if inst.errno != errno.ENOENT:
                         raise
         wlock = self.wlock()
         try:
             for f in list:
                 if unlink and os.path.exists(self.wjoin(f)):
                     self.ui.warn(_("%s still exists!\n") % f)
                 elif self.dirstate[f] == 'a':
                     self.dirstate.forget(f)
                 elif f not in self.dirstate:
                     self.ui.warn(_("%s not tracked!\n") % f)
                 else:
                     self.dirstate.remove(f)
         finally:
             wlock.release()
 
     def undelete(self, list):
         manifests = [self.manifest.read(self.changelog.read(p)[0])
                      for p in self.dirstate.parents() if p != nullid]
         wlock = self.wlock()
         try:
             for f in list:
                 if self.dirstate[f] != 'r':
                     self.ui.warn(_("%s not removed!\n") % f)
                 else:
                     m = f in manifests[0] and manifests[0] or manifests[1]
                     t = self.file(f).read(m[f])
                     self.wwrite(f, t, m.flags(f))
                     self.dirstate.normal(f)
         finally:
             wlock.release()
 
     def copy(self, source, dest):
         p = self.wjoin(dest)
         if not (os.path.exists(p) or os.path.islink(p)):
             self.ui.warn(_("%s does not exist!\n") % dest)
         elif not (os.path.isfile(p) or os.path.islink(p)):
             self.ui.warn(_("copy failed: %s is not a file or a "
                            "symbolic link\n") % dest)
         else:
             wlock = self.wlock()
             try:
                 if self.dirstate[dest] in '?r':
                     self.dirstate.add(dest)
                 self.dirstate.copy(source, dest)
             finally:
                 wlock.release()
 
     def heads(self, start=None, closed=True):
         heads = self.changelog.heads(start)
         def display(head):
             if closed:
                 return True
             extras = self.changelog.read(head)[5]
             return ('close' not in extras)
         # sort the output in rev descending order
         heads = [(-self.changelog.rev(h), h) for h in heads if display(h)]
         return [n for (r, n) in sorted(heads)]
 
     def branchheads(self, branch=None, start=None, closed=True):
         if branch is None:
             branch = self[None].branch()
         branches = self.branchmap()
         if branch not in branches:
             return []
         bheads = branches[branch]
         # the cache returns heads ordered lowest to highest
         bheads.reverse()
         if start is not None:
             # filter out the heads that cannot be reached from startrev
             bheads = self.changelog.nodesbetween([start], bheads)[2]
         if not closed:
             bheads = [h for h in bheads if
                       ('close' not in self.changelog.read(h)[5])]
         return bheads
 
     def branches(self, nodes):
         if not nodes:
             nodes = [self.changelog.tip()]
         b = []
         for n in nodes:
             t = n
             while 1:
                 p = self.changelog.parents(n)
                 if p[1] != nullid or p[0] == nullid:
                     b.append((t, n, p[0], p[1]))
                     break
                 n = p[0]
         return b
 
     def between(self, pairs):
         r = []
 
         for top, bottom in pairs:
             n, l, i = top, [], 0
             f = 1
 
             while n != bottom and n != nullid:
                 p = self.changelog.parents(n)[0]
                 if i == f:
                     l.append(n)
                     f = f * 2
                 n = p
                 i += 1
 
             r.append(l)
 
         return r
 
     def findincoming(self, remote, base=None, heads=None, force=False):
         """Return list of roots of the subsets of missing nodes from remote
 
         If base dict is specified, assume that these nodes and their parents
         exist on the remote side and that no child of a node of base exists
         in both remote and self.
         Furthermore base will be updated to include the nodes that exists
         in self and remote but no children exists in self and remote.
         If a list of heads is specified, return only nodes which are heads
         or ancestors of these heads.
 
         All the ancestors of base are in self and in remote.
         All the descendants of the list returned are missing in self.
         (and so we know that the rest of the nodes are missing in remote, see
         outgoing)
         """
         return self.findcommonincoming(remote, base, heads, force)[1]
 
     def findcommonincoming(self, remote, base=None, heads=None, force=False):
         """Return a tuple (common, missing roots, heads) used to identify
         missing nodes from remote.
 
         If base dict is specified, assume that these nodes and their parents
         exist on the remote side and that no child of a node of base exists
         in both remote and self.
         Furthermore base will be updated to include the nodes that exists
         in self and remote but no children exists in self and remote.
         If a list of heads is specified, return only nodes which are heads
         or ancestors of these heads.
 
         All the ancestors of base are in self and in remote.
         """
         m = self.changelog.nodemap
         search = []
         fetch = set()
         seen = set()
         seenbranch = set()
         if base is None:
             base = {}
 
         if not heads:
             heads = remote.heads()
 
         if self.changelog.tip() == nullid:
             base[nullid] = 1
             if heads != [nullid]:
                 return [nullid], [nullid], list(heads)
             return [nullid], [], []
 
         # assume we're closer to the tip than the root
         # and start by examining the heads
         self.ui.status(_("searching for changes\n"))
 
         unknown = []
         for h in heads:
             if h not in m:
                 unknown.append(h)
             else:
                 base[h] = 1
 
         heads = unknown
         if not unknown:
             return base.keys(), [], []
 
         req = set(unknown)
         reqcnt = 0
 
         # search through remote branches
         # a 'branch' here is a linear segment of history, with four parts:
         # head, root, first parent, second parent
         # (a branch always has two parents (or none) by definition)
         unknown = remote.branches(unknown)
         while unknown:
             r = []
             while unknown:
                 n = unknown.pop(0)
                 if n[0] in seen:
                     continue
 
                 self.ui.debug(_("examining %s:%s\n")
                               % (short(n[0]), short(n[1])))
                 if n[0] == nullid: # found the end of the branch
                     pass
                 elif n in seenbranch:
                     self.ui.debug(_("branch already found\n"))
                     continue
                 elif n[1] and n[1] in m: # do we know the base?
                     self.ui.debug(_("found incomplete branch %s:%s\n")
                                   % (short(n[0]), short(n[1])))
                     search.append(n[0:2]) # schedule branch range for scanning
                     seenbranch.add(n)
                 else:
                     if n[1] not in seen and n[1] not in fetch:
                         if n[2] in m and n[3] in m:
                             self.ui.debug(_("found new changeset %s\n") %
                                           short(n[1]))
                             fetch.add(n[1]) # earliest unknown
                         for p in n[2:4]:
                             if p in m:
                                 base[p] = 1 # latest known
 
                     for p in n[2:4]:
                         if p not in req and p not in m:
                             r.append(p)
                             req.add(p)
                 seen.add(n[0])
 
             if r:
                 reqcnt += 1
                 self.ui.debug(_("request %d: %s\n") %
                             (reqcnt, " ".join(map(short, r))))
                 for p in xrange(0, len(r), 10):
                     for b in remote.branches(r[p:p+10]):
                         self.ui.debug(_("received %s:%s\n") %
                                       (short(b[0]), short(b[1])))
                         unknown.append(b)
 
         # do binary search on the branches we found
         while search:
             newsearch = []
             reqcnt += 1
             for n, l in zip(search, remote.between(search)):
                 l.append(n[1])
                 p = n[0]
                 f = 1
                 for i in l:
                     self.ui.debug(_("narrowing %d:%d %s\n") % (f, len(l), short(i)))
                     if i in m:
                         if f <= 2:
                             self.ui.debug(_("found new branch changeset %s\n") %
                                               short(p))
                             fetch.add(p)
                             base[i] = 1
                         else:
                             self.ui.debug(_("narrowed branch search to %s:%s\n")
                                           % (short(p), short(i)))
                             newsearch.append((p, i))
                         break
                     p, f = i, f * 2
                 search = newsearch
 
         # sanity check our fetch list
         for f in fetch:
             if f in m:
                 raise error.RepoError(_("already have changeset ")
                                       + short(f[:4]))
 
         if base.keys() == [nullid]:
             if force:
                 self.ui.warn(_("warning: repository is unrelated\n"))
             else:
                 raise util.Abort(_("repository is unrelated"))
 
         self.ui.debug(_("found new changesets starting at ") +
                      " ".join([short(f) for f in fetch]) + "\n")
 
         self.ui.debug(_("%d total queries\n") % reqcnt)
 
         return base.keys(), list(fetch), heads
 
     def findoutgoing(self, remote, base=None, heads=None, force=False):
         """Return list of nodes that are roots of subsets not in remote
 
         If base dict is specified, assume that these nodes and their parents
         exist on the remote side.
         If a list of heads is specified, return only nodes which are heads
         or ancestors of these heads, and return a second element which
         contains all remote heads which get new children.
         """
         if base is None:
             base = {}
             self.findincoming(remote, base, heads, force=force)
 
         self.ui.debug(_("common changesets up to ")
                       + " ".join(map(short, base.keys())) + "\n")
 
         remain = set(self.changelog.nodemap)
 
         # prune everything remote has from the tree
         remain.remove(nullid)
         remove = base.keys()
         while remove:
             n = remove.pop(0)
             if n in remain:
                 remain.remove(n)
                 for p in self.changelog.parents(n):
                     remove.append(p)
 
         # find every node whose parents have been pruned
         subset = []
         # find every remote head that will get new children
         updated_heads = set()
         for n in remain:
             p1, p2 = self.changelog.parents(n)
             if p1 not in remain and p2 not in remain:
                 subset.append(n)
             if heads:
                 if p1 in heads:
                     updated_heads.add(p1)
                 if p2 in heads:
                     updated_heads.add(p2)
 
         # this is the set of all roots we have to push
         if heads:
             return subset, list(updated_heads)
         else:
             return subset
 
     def pull(self, remote, heads=None, force=False):
         lock = self.lock()
         try:
             common, fetch, rheads = self.findcommonincoming(remote, heads=heads,
                                                             force=force)
             if fetch == [nullid]:
                 self.ui.status(_("requesting all changes\n"))
 
             if not fetch:
                 self.ui.status(_("no changes found\n"))
                 return 0
 
             if heads is None and remote.capable('changegroupsubset'):
                 heads = rheads
 
             if heads is None:
                 cg = remote.changegroup(fetch, 'pull')
             else:
                 if not remote.capable('changegroupsubset'):
-                    raise util.Abort(_("Partial pull cannot be done because other repository doesn't support changegroupsubset."))
+                    raise util.Abort(_("Partial pull cannot be done because "
+                                       "other repository doesn't support "
+                                       "changegroupsubset."))
                 cg = remote.changegroupsubset(fetch, heads, 'pull')
             return self.addchangegroup(cg, 'pull', remote.url())
         finally:
             lock.release()
 
     def push(self, remote, force=False, revs=None):
         # there are two ways to push to remote repo:
         #
         # addchangegroup assumes local user can lock remote
         # repo (local filesystem, old ssh servers).
         #
         # unbundle assumes local user cannot lock remote repo (new ssh
         # servers, http servers).
 
         if remote.capable('unbundle'):
             return self.push_unbundle(remote, force, revs)
         return self.push_addchangegroup(remote, force, revs)
 
     def prepush(self, remote, force, revs):
         common = {}
         remote_heads = remote.heads()
         inc = self.findincoming(remote, common, remote_heads, force=force)
 
         update, updated_heads = self.findoutgoing(remote, common, remote_heads)
         if revs is not None:
             msng_cl, bases, heads = self.changelog.nodesbetween(update, revs)
         else:
             bases, heads = update, self.changelog.heads()
 
         def checkbranch(lheads, rheads, updatelh):
             '''
             check whether there are more local heads than remote heads on
             a specific branch.
 
             lheads: local branch heads
             rheads: remote branch heads
             updatelh: outgoing local branch heads
             '''
 
             warn = 0
 
             if not revs and len(lheads) > len(rheads):
                 warn = 1
             else:
                 updatelheads = [self.changelog.heads(x, lheads)
                                 for x in updatelh]
                 newheads = set(sum(updatelheads, [])) & set(lheads)
 
                 if not newheads:
                     return True
 
                 for r in rheads:
                     if r in self.changelog.nodemap:
                         desc = self.changelog.heads(r, heads)
                         l = [h for h in heads if h in desc]
                         if not l:
                             newheads.add(r)
                     else:
                         newheads.add(r)
                 if len(newheads) > len(rheads):
                     warn = 1
 
             if warn:
                 if not rheads: # new branch requires --force
                     self.ui.warn(_("abort: push creates new"
                                    " remote branch '%s'!\n" %
                                    self[updatelh[0]].branch()))
                 else:
                     self.ui.warn(_("abort: push creates new remote heads!\n"))
 
                 self.ui.status(_("(did you forget to merge?"
                                  " use push -f to force)\n"))
                 return False
             return True
 
         if not bases:
             self.ui.status(_("no changes found\n"))
             return None, 1
         elif not force:
             # Check for each named branch if we're creating new remote heads.
             # To be a remote head after push, node must be either:
             # - unknown locally
             # - a local outgoing head descended from update
             # - a remote head that's known locally and not
             #   ancestral to an outgoing head
             #
             # New named branches cannot be created without --force.
 
             if remote_heads != [nullid]:
                 if remote.capable('branchmap'):
                     localhds = {}
                     if not revs:
                         localhds = self.branchmap()
                     else:
                         for n in heads:
                             branch = self[n].branch()
                             if branch in localhds:
                                 localhds[branch].append(n)
                             else:
                                 localhds[branch] = [n]
 
                     remotehds = remote.branchmap()
 
                     for lh in localhds:
                         if lh in remotehds:
                             rheads = remotehds[lh]
                         else:
                             rheads = []
                         lheads = localhds[lh]
                         updatelh = [upd for upd in update
                                     if self[upd].branch() == lh]
                         if not updatelh:
                             continue
                         if not checkbranch(lheads, rheads, updatelh):
                             return None, 0
                 else:
                     if not checkbranch(heads, remote_heads, update):
                         return None, 0
 
             if inc:
                 self.ui.warn(_("note: unsynced remote changes!\n"))
 
 
         if revs is None:
             # use the fast path, no race possible on push
             cg = self._changegroup(common.keys(), 'push')
         else:
             cg = self.changegroupsubset(update, revs, 'push')
         return cg, remote_heads
 
     def push_addchangegroup(self, remote, force, revs):
         lock = remote.lock()
         try:
             ret = self.prepush(remote, force, revs)
             if ret[0] is not None:
                 cg, remote_heads = ret
                 return remote.addchangegroup(cg, 'push', self.url())
             return ret[1]
         finally:
             lock.release()
 
     def push_unbundle(self, remote, force, revs):
         # local repo finds heads on server, finds out what revs it
         # must push.  once revs transferred, if server finds it has
         # different heads (someone else won commit/push race), server
         # aborts.
 
         ret = self.prepush(remote, force, revs)
         if ret[0] is not None:
             cg, remote_heads = ret
             if force: remote_heads = ['force']
             return remote.unbundle(cg, remote_heads, 'push')
         return ret[1]
 
     def changegroupinfo(self, nodes, source):
         if self.ui.verbose or source == 'bundle':
             self.ui.status(_("%d changesets found\n") % len(nodes))
         if self.ui.debugflag:
             self.ui.debug(_("list of changesets:\n"))
             for node in nodes:
                 self.ui.debug("%s\n" % hex(node))
 
     def changegroupsubset(self, bases, heads, source, extranodes=None):
         """This function generates a changegroup consisting of all the nodes
         that are descendents of any of the bases, and ancestors of any of
         the heads.
 
         It is fairly complex as determining which filenodes and which
         manifest nodes need to be included for the changeset to be complete
         is non-trivial.
 
         Another wrinkle is doing the reverse, figuring out which changeset in
         the changegroup a particular filenode or manifestnode belongs to.
 
         The caller can specify some nodes that must be included in the
         changegroup using the extranodes argument.  It should be a dict
         where the keys are the filenames (or 1 for the manifest), and the
         values are lists of (node, linknode) tuples, where node is a wanted
         node and linknode is the changelog node that should be transmitted as
         the linkrev.
         """
 
         if extranodes is None:
             # can we go through the fast path ?
             heads.sort()
             allheads = self.heads()
             allheads.sort()
             if heads == allheads:
                 common = []
                 # parents of bases are known from both sides
                 for n in bases:
                     for p in self.changelog.parents(n):
                         if p != nullid:
                             common.append(p)
                 return self._changegroup(common, source)
 
         self.hook('preoutgoing', throw=True, source=source)
 
         # Set up some initial variables
         # Make it easy to refer to self.changelog
         cl = self.changelog
         # msng is short for missing - compute the list of changesets in this
         # changegroup.
         msng_cl_lst, bases, heads = cl.nodesbetween(bases, heads)
         self.changegroupinfo(msng_cl_lst, source)
         # Some bases may turn out to be superfluous, and some heads may be
         # too.  nodesbetween will return the minimal set of bases and heads
         # necessary to re-create the changegroup.
 
         # Known heads are the list of heads that it is assumed the recipient
         # of this changegroup will know about.
         knownheads = set()
         # We assume that all parents of bases are known heads.
         for n in bases:
             knownheads.update(cl.parents(n))
         knownheads.discard(nullid)
         knownheads = list(knownheads)
         if knownheads:
             # Now that we know what heads are known, we can compute which
             # changesets are known.  The recipient must know about all
             # changesets required to reach the known heads from the null
             # changeset.
             has_cl_set, junk, junk = cl.nodesbetween(None, knownheads)
             junk = None
             # Transform the list into a set.
             has_cl_set = set(has_cl_set)
         else:
             # If there were no known heads, the recipient cannot be assumed to
             # know about any changesets.
             has_cl_set = set()
 
         # Make it easy to refer to self.manifest
         mnfst = self.manifest
         # We don't know which manifests are missing yet
         msng_mnfst_set = {}
         # Nor do we know which filenodes are missing.
         msng_filenode_set = {}
 
         junk = mnfst.index[len(mnfst) - 1] # Get around a bug in lazyindex
         junk = None
 
         # A changeset always belongs to itself, so the changenode lookup
         # function for a changenode is identity.
         def identity(x):
             return x
 
         # A function generating function.  Sets up an environment for the
         # inner function.
         def cmp_by_rev_func(revlog):
             # Compare two nodes by their revision number in the environment's
             # revision history.  Since the revision number both represents the
             # most efficient order to read the nodes in, and represents a
             # topological sorting of the nodes, this function is often useful.
             def cmp_by_rev(a, b):
                 return cmp(revlog.rev(a), revlog.rev(b))
             return cmp_by_rev
 
         # If we determine that a particular file or manifest node must be a
         # node that the recipient of the changegroup will already have, we can
         # also assume the recipient will have all the parents.  This function
         # prunes them from the set of missing nodes.
         def prune_parents(revlog, hasset, msngset):
             haslst = list(hasset)
             haslst.sort(cmp_by_rev_func(revlog))
             for node in haslst:
                 parentlst = [p for p in revlog.parents(node) if p != nullid]
                 while parentlst:
                     n = parentlst.pop()
                     if n not in hasset:
                         hasset.add(n)
                         p = [p for p in revlog.parents(n) if p != nullid]
                         parentlst.extend(p)
             for n in hasset:
                 msngset.pop(n, None)
 
         # This is a function generating function used to set up an environment
         # for the inner function to execute in.
         def manifest_and_file_collector(changedfileset):
             # This is an information gathering function that gathers
             # information from each changeset node that goes out as part of
             # the changegroup.  The information gathered is a list of which
             # manifest nodes are potentially required (the recipient may
             # already have them) and total list of all files which were
             # changed in any changeset in the changegroup.
             #
             # We also remember the first changenode we saw any manifest
             # referenced by so we can later determine which changenode 'owns'
             # the manifest.
             def collect_manifests_and_files(clnode):
                 c = cl.read(clnode)
                 for f in c[3]:
                     # This is to make sure we only have one instance of each
                     # filename string for each filename.
                     changedfileset.setdefault(f, f)
                 msng_mnfst_set.setdefault(c[0], clnode)
             return collect_manifests_and_files
 
         # Figure out which manifest nodes (of the ones we think might be part
         # of the changegroup) the recipient must know about and remove them
         # from the changegroup.
         def prune_manifests():
             has_mnfst_set = set()
             for n in msng_mnfst_set:
                 # If a 'missing' manifest thinks it belongs to a changenode
                 # the recipient is assumed to have, obviously the recipient
                 # must have that manifest.
                 linknode = cl.node(mnfst.linkrev(mnfst.rev(n)))
                 if linknode in has_cl_set:
                     has_mnfst_set.add(n)
             prune_parents(mnfst, has_mnfst_set, msng_mnfst_set)
 
         # Use the information collected in collect_manifests_and_files to say
         # which changenode any manifestnode belongs to.
         def lookup_manifest_link(mnfstnode):
             return msng_mnfst_set[mnfstnode]
 
         # A function generating function that sets up the initial environment
         # the inner function.
         def filenode_collector(changedfiles):
             next_rev = [0]
             # This gathers information from each manifestnode included in the
             # changegroup about which filenodes the manifest node references
             # so we can include those in the changegroup too.
             #
             # It also remembers which changenode each filenode belongs to.  It
             # does this by assuming the a filenode belongs to the changenode
             # the first manifest that references it belongs to.
             def collect_msng_filenodes(mnfstnode):
                 r = mnfst.rev(mnfstnode)
                 if r == next_rev[0]:
                     # If the last rev we looked at was the one just previous,
                     # we only need to see a diff.
                     deltamf = mnfst.readdelta(mnfstnode)
                     # For each line in the delta
                     for f, fnode in deltamf.iteritems():
                         f = changedfiles.get(f, None)
                         # And if the file is in the list of files we care
                         # about.
                         if f is not None:
                             # Get the changenode this manifest belongs to
                             clnode = msng_mnfst_set[mnfstnode]
                             # Create the set of filenodes for the file if
                             # there isn't one already.
                             ndset = msng_filenode_set.setdefault(f, {})
                             # And set the filenode's changelog node to the
                             # manifest's if it hasn't been set already.
                             ndset.setdefault(fnode, clnode)
                 else:
                     # Otherwise we need a full manifest.
                     m = mnfst.read(mnfstnode)
                     # For every file in we care about.
                     for f in changedfiles:
                         fnode = m.get(f, None)
                         # If it's in the manifest
                         if fnode is not None:
                             # See comments above.
                             clnode = msng_mnfst_set[mnfstnode]
                             ndset = msng_filenode_set.setdefault(f, {})
                             ndset.setdefault(fnode, clnode)
                 # Remember the revision we hope to see next.
                 next_rev[0] = r + 1
             return collect_msng_filenodes
 
         # We have a list of filenodes we think we need for a file, lets remove
         # all those we know the recipient must have.
         def prune_filenodes(f, filerevlog):
             msngset = msng_filenode_set[f]
             hasset = set()
             # If a 'missing' filenode thinks it belongs to a changenode we
             # assume the recipient must have, then the recipient must have
             # that filenode.
             for n in msngset:
                 clnode = cl.node(filerevlog.linkrev(filerevlog.rev(n)))
                 if clnode in has_cl_set:
                     hasset.add(n)
             prune_parents(filerevlog, hasset, msngset)
 
         # A function generator function that sets up the a context for the
         # inner function.
         def lookup_filenode_link_func(fname):
             msngset = msng_filenode_set[fname]
             # Lookup the changenode the filenode belongs to.
             def lookup_filenode_link(fnode):
                 return msngset[fnode]
             return lookup_filenode_link
 
         # Add the nodes that were explicitly requested.
         def add_extra_nodes(name, nodes):
             if not extranodes or name not in extranodes:
                 return
 
             for node, linknode in extranodes[name]:
                 if node not in nodes:
                     nodes[node] = linknode
 
         # Now that we have all theses utility functions to help out and
         # logically divide up the task, generate the group.
         def gengroup():
             # The set of changed files starts empty.
             changedfiles = {}
             # Create a changenode group generator that will call our functions
             # back to lookup the owning changenode and collect information.
             group = cl.group(msng_cl_lst, identity,
                              manifest_and_file_collector(changedfiles))
             for chnk in group:
                 yield chnk
 
             # The list of manifests has been collected by the generator
             # calling our functions back.
             prune_manifests()
             add_extra_nodes(1, msng_mnfst_set)
             msng_mnfst_lst = msng_mnfst_set.keys()
             # Sort the manifestnodes by revision number.
             msng_mnfst_lst.sort(cmp_by_rev_func(mnfst))
             # Create a generator for the manifestnodes that calls our lookup
             # and data collection functions back.
             group = mnfst.group(msng_mnfst_lst, lookup_manifest_link,
                                 filenode_collector(changedfiles))
             for chnk in group:
                 yield chnk
 
             # These are no longer needed, dereference and toss the memory for
             # them.
             msng_mnfst_lst = None
             msng_mnfst_set.clear()
 
             if extranodes:
                 for fname in extranodes:
                     if isinstance(fname, int):
                         continue
                     msng_filenode_set.setdefault(fname, {})
                     changedfiles[fname] = 1
             # Go through all our files in order sorted by name.
             for fname in sorted(changedfiles):
                 filerevlog = self.file(fname)
                 if not len(filerevlog):
                     raise util.Abort(_("empty or missing revlog for %s") % fname)
                 # Toss out the filenodes that the recipient isn't really
                 # missing.
                 if fname in msng_filenode_set:
                     prune_filenodes(fname, filerevlog)
                     add_extra_nodes(fname, msng_filenode_set[fname])
                     msng_filenode_lst = msng_filenode_set[fname].keys()
                 else:
                     msng_filenode_lst = []
                 # If any filenodes are left, generate the group for them,
                 # otherwise don't bother.
                 if len(msng_filenode_lst) > 0:
                     yield changegroup.chunkheader(len(fname))
                     yield fname
                     # Sort the filenodes by their revision #
                     msng_filenode_lst.sort(cmp_by_rev_func(filerevlog))
                     # Create a group generator and only pass in a changenode
                     # lookup function as we need to collect no information
                     # from filenodes.
                     group = filerevlog.group(msng_filenode_lst,
                                              lookup_filenode_link_func(fname))
                     for chnk in group:
                         yield chnk
                 if fname in msng_filenode_set:
                     # Don't need this anymore, toss it to free memory.
                     del msng_filenode_set[fname]
             # Signal that no more groups are left.
             yield changegroup.closechunk()
 
             if msng_cl_lst:
                 self.hook('outgoing', node=hex(msng_cl_lst[0]), source=source)
 
         return util.chunkbuffer(gengroup())
 
     def changegroup(self, basenodes, source):
         # to avoid a race we use changegroupsubset() (issue1320)
         return self.changegroupsubset(basenodes, self.heads(), source)
 
     def _changegroup(self, common, source):
         """Generate a changegroup of all nodes that we have that a recipient
         doesn't.
 
         This is much easier than the previous function as we can assume that
         the recipient has any changenode we aren't sending them.
 
         common is the set of common nodes between remote and self"""
 
         self.hook('preoutgoing', throw=True, source=source)
 
         cl = self.changelog
         nodes = cl.findmissing(common)
         revset = set([cl.rev(n) for n in nodes])
         self.changegroupinfo(nodes, source)
 
         def identity(x):
             return x
 
         def gennodelst(log):
             for r in log:
                 if log.linkrev(r) in revset:
                     yield log.node(r)
 
         def changed_file_collector(changedfileset):
             def collect_changed_files(clnode):
                 c = cl.read(clnode)
                 changedfileset.update(c[3])
             return collect_changed_files
 
         def lookuprevlink_func(revlog):
             def lookuprevlink(n):
                 return cl.node(revlog.linkrev(revlog.rev(n)))
             return lookuprevlink
 
         def gengroup():
             # construct a list of all changed files
             changedfiles = set()
 
             for chnk in cl.group(nodes, identity,
                                  changed_file_collector(changedfiles)):
                 yield chnk
 
             mnfst = self.manifest
             nodeiter = gennodelst(mnfst)
             for chnk in mnfst.group(nodeiter, lookuprevlink_func(mnfst)):
                 yield chnk
 
             for fname in sorted(changedfiles):
                 filerevlog = self.file(fname)
                 if not len(filerevlog):
                     raise util.Abort(_("empty or missing revlog for %s") % fname)
                 nodeiter = gennodelst(filerevlog)
                 nodeiter = list(nodeiter)
                 if nodeiter:
                     yield changegroup.chunkheader(len(fname))
                     yield fname
                     lookup = lookuprevlink_func(filerevlog)
                     for chnk in filerevlog.group(nodeiter, lookup):
                         yield chnk
 
             yield changegroup.closechunk()
 
             if nodes:
                 self.hook('outgoing', node=hex(nodes[0]), source=source)
 
         return util.chunkbuffer(gengroup())
 
     def addchangegroup(self, source, srctype, url, emptyok=False):
         """add changegroup to repo.
 
         return values:
         - nothing changed or no source: 0
         - more heads than before: 1+added heads (2..n)
         - less heads than before: -1-removed heads (-2..-n)
         - number of heads stays the same: 1
         """
         def csmap(x):
             self.ui.debug(_("add changeset %s\n") % short(x))
             return len(cl)
 
         def revmap(x):
             return cl.rev(x)
 
         if not source:
             return 0
 
         self.hook('prechangegroup', throw=True, source=srctype, url=url)
 
         changesets = files = revisions = 0
 
         # write changelog data to temp files so concurrent readers will not see
         # inconsistent view
         cl = self.changelog
         cl.delayupdate()
         oldheads = len(cl.heads())
 
         tr = self.transaction()
         try:
             trp = weakref.proxy(tr)
             # pull off the changeset group
             self.ui.status(_("adding changesets\n"))
             clstart = len(cl)
             chunkiter = changegroup.chunkiter(source)
             if cl.addgroup(chunkiter, csmap, trp) is None and not emptyok:
                 raise util.Abort(_("received changelog group is empty"))
             clend = len(cl)
             changesets = clend - clstart
 
             # pull off the manifest group
             self.ui.status(_("adding manifests\n"))
             chunkiter = changegroup.chunkiter(source)
             # no need to check for empty manifest group here:
             # if the result of the merge of 1 and 2 is the same in 3 and 4,
             # no new manifest will be created and the manifest group will
             # be empty during the pull
             self.manifest.addgroup(chunkiter, revmap, trp)
 
             # process the files
             self.ui.status(_("adding file changes\n"))
             while 1:
                 f = changegroup.getchunk(source)
                 if not f:
                     break
                 self.ui.debug(_("adding %s revisions\n") % f)
                 fl = self.file(f)
                 o = len(fl)
                 chunkiter = changegroup.chunkiter(source)
                 if fl.addgroup(chunkiter, revmap, trp) is None:
                     raise util.Abort(_("received file revlog group is empty"))
                 revisions += len(fl) - o
                 files += 1
 
             newheads = len(cl.heads())
             heads = ""
             if oldheads and newheads != oldheads:
                 heads = _(" (%+d heads)") % (newheads - oldheads)
 
             self.ui.status(_("added %d changesets"
                              " with %d changes to %d files%s\n")
                              % (changesets, revisions, files, heads))
 
             if changesets > 0:
                 p = lambda: cl.writepending() and self.root or ""
                 self.hook('pretxnchangegroup', throw=True,
                           node=hex(cl.node(clstart)), source=srctype,
                           url=url, pending=p)
 
             # make changelog see real files again
             cl.finalize(trp)
 
             tr.close()
         finally:
             del tr
 
         if changesets > 0:
             # forcefully update the on-disk branch cache
             self.ui.debug(_("updating the branch cache\n"))
             self.branchtags()
             self.hook("changegroup", node=hex(cl.node(clstart)),
                       source=srctype, url=url)
 
             for i in xrange(clstart, clend):
                 self.hook("incoming", node=hex(cl.node(i)),
                           source=srctype, url=url)
 
         # never return 0 here:
         if newheads < oldheads:
             return newheads - oldheads - 1
         else:
             return newheads - oldheads + 1
 
 
     def stream_in(self, remote):
         fp = remote.stream_out()
         l = fp.readline()
         try:
             resp = int(l)
         except ValueError:
             raise error.ResponseError(
                 _('Unexpected response from remote server:'), l)
         if resp == 1:
             raise util.Abort(_('operation forbidden by server'))
         elif resp == 2:
             raise util.Abort(_('locking the remote repository failed'))
         elif resp != 0:
             raise util.Abort(_('the server sent an unknown error code'))
         self.ui.status(_('streaming all changes\n'))
         l = fp.readline()
         try:
             total_files, total_bytes = map(int, l.split(' ', 1))
         except (ValueError, TypeError):
             raise error.ResponseError(
                 _('Unexpected response from remote server:'), l)
         self.ui.status(_('%d files to transfer, %s of data\n') %
                        (total_files, util.bytecount(total_bytes)))
         start = time.time()
         for i in xrange(total_files):
             # XXX doesn't support '\n' or '\r' in filenames
             l = fp.readline()
             try:
                 name, size = l.split('\0', 1)
                 size = int(size)
             except (ValueError, TypeError):
                 raise error.ResponseError(
                     _('Unexpected response from remote server:'), l)
             self.ui.debug(_('adding %s (%s)\n') % (name, util.bytecount(size)))
             # for backwards compat, name was partially encoded
             ofp = self.sopener(store.decodedir(name), 'w')
             for chunk in util.filechunkiter(fp, limit=size):
                 ofp.write(chunk)
             ofp.close()
         elapsed = time.time() - start
         if elapsed <= 0:
             elapsed = 0.001
         self.ui.status(_('transferred %s in %.1f seconds (%s/sec)\n') %
                        (util.bytecount(total_bytes), elapsed,
                         util.bytecount(total_bytes / elapsed)))
         self.invalidate()
         return len(self.heads()) + 1
 
     def clone(self, remote, heads=[], stream=False):
         '''clone remote repository.
 
         keyword arguments:
         heads: list of revs to clone (forces use of pull)
         stream: use streaming clone if possible'''
 
         # now, all clients that can request uncompressed clones can
         # read repo formats supported by all servers that can serve
         # them.
 
         # if revlog format changes, client will have to check version
         # and format flags on "stream" capability, and use
         # uncompressed only if compatible.
 
         if stream and not heads and remote.capable('stream'):
             return self.stream_in(remote)
         return self.pull(remote, heads)
 
 # used to avoid circular references so destructors work
 def aftertrans(files):
     renamefiles = [tuple(t) for t in files]
     def a():
         for src, dest in renamefiles:
             util.rename(src, dest)
     return a
 
 def instance(ui, path, create):
     return localrepository(ui, util.drop_scheme('file', path), create)
 
 def islocal(path):
     return True