hgwebdir: reduce memory usage for index generation

The archive list generator was holding a reference to each
temporary ui copy passed by rawentries(), so the memory
usage for index generation growed proportionally to the
ui object size and the amount of repositories. By returning a
list instead, the temporary reference is dropped immediately.

mercurial/hgweb/hgwebdir_mod.py

@@ -1,368 +1,370 b''
 # hgweb/hgwebdir_mod.py - Web interface for a directory of repositories.
 #
 # Copyright 21 May 2005 - (c) 2005 Jake Edge <[e-mail]>
 # Copyright 2005, 2006 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 import os, re, time, urlparse
 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.append((prefix, root))
             continue
         roothead = os.path.normpath(os.path.abspath(roothead))
         paths = util.walkrepos(roothead, followsym=True, recurse=recurse)
         repos.extend(urlrepos(prefix, roothead, paths))
     return repos
 
 def urlrepos(prefix, roothead, paths):
     """yield url paths and filesystem paths from a list of repo paths
 
     >>> list(urlrepos('hg', '/opt', ['/opt/r', '/opt/r/r', '/opt']))
     [('hg/r', '/opt/r'), ('hg/r/r', '/opt/r/r'), ('hg', '/opt')]
     >>> list(urlrepos('', '/opt', ['/opt/r', '/opt/r/r', '/opt']))
     [('r', '/opt/r'), ('r/r', '/opt/r/r'), ('', '/opt')]
     """
     for path in paths:
         path = os.path.normpath(path)
         yield (prefix + '/' +
                util.pconvert(path[len(roothead):]).lstrip('/')).strip('/'), path
 
 class hgwebdir(object):
     refreshinterval = 20
 
     def __init__(self, conf, baseui=None):
         self.conf = conf
         self.baseui = baseui
         self.lastrefresh = 0
         self.motd = None
         self.refresh()
 
     def refresh(self):
         if self.lastrefresh + self.refreshinterval > time.time():
             return
 
         if self.baseui:
             u = self.baseui.copy()
         else:
             u = ui.ui()
             u.setconfig('ui', 'report_untrusted', 'off')
             u.setconfig('ui', 'interactive', 'off')
 
         if not isinstance(self.conf, (dict, list, tuple)):
             map = {'paths': 'hgweb-paths'}
             if not os.path.exists(self.conf):
                 raise util.Abort(_('config file %s not found!') % self.conf)
             u.readconfig(self.conf, remap=map, trust=True)
             paths = u.configitems('hgweb-paths')
         elif isinstance(self.conf, (list, tuple)):
             paths = self.conf
         elif isinstance(self.conf, dict):
             paths = self.conf.items()
 
         repos = findrepos(paths)
         for prefix, root in u.configitems('collections'):
             prefix = util.pconvert(prefix)
             for path in util.walkrepos(root, followsym=True):
                 repo = os.path.normpath(path)
                 name = util.pconvert(repo)
                 if name.startswith(prefix):
                     name = name[len(prefix):]
                 repos.append((name.lstrip('/'), repo))
 
         self.repos = repos
         self.ui = u
         encoding.encoding = self.ui.config('web', 'encoding',
                                            encoding.encoding)
         self.style = self.ui.config('web', 'style', 'paper')
         self.templatepath = self.ui.config('web', 'templates', None)
         self.stripecount = self.ui.config('web', 'stripes', 1)
         if self.stripecount:
             self.stripecount = int(self.stripecount)
         self._baseurl = self.ui.config('web', 'baseurl')
         self.lastrefresh = time.time()
 
     def run(self):
         if not os.environ.get('GATEWAY_INTERFACE', '').startswith("CGI/1."):
             raise RuntimeError("This function is only intended to be "
                                "called while running as a CGI script.")
         import mercurial.hgweb.wsgicgi as wsgicgi
         wsgicgi.launch(self)
 
     def __call__(self, env, respond):
         req = wsgirequest(env, respond)
         return self.run_wsgi(req)
 
     def read_allowed(self, ui, req):
         """Check allow_read and deny_read config options of a repo's ui object
         to determine user permissions.  By default, with neither option set (or
         both empty), allow all users to read the repo.  There are two ways a
         user can be denied read access:  (1) deny_read is not empty, and the
         user is unauthenticated or deny_read contains user (or *), and (2)
         allow_read is not empty and the user is not in allow_read.  Return True
         if user is allowed to read the repo, else return False."""
 
         user = req.env.get('REMOTE_USER')
 
         deny_read = ui.configlist('web', 'deny_read', untrusted=True)
         if deny_read and (not user or deny_read == ['*'] or user in deny_read):
             return False
 
         allow_read = ui.configlist('web', 'allow_read', untrusted=True)
         # by default, allow reading if no allow_read option has been set
         if (not allow_read) or (allow_read == ['*']) or (user in allow_read):
             return True
 
         return False
 
     def run_wsgi(self, req):
         try:
             try:
                 self.refresh()
 
                 virtual = req.env.get("PATH_INFO", "").strip('/')
                 tmpl = self.templater(req)
                 ctype = tmpl('mimetype', encoding=encoding.encoding)
                 ctype = templater.stringify(ctype)
 
                 # a static file
                 if virtual.startswith('static/') or 'static' in req.form:
                     if virtual.startswith('static/'):
                         fname = virtual[7:]
                     else:
                         fname = req.form['static'][0]
                     static = templater.templatepath('static')
                     return (staticfile(static, fname, req),)
 
                 # top-level index
                 elif not virtual:
                     req.respond(HTTP_OK, ctype)
                     return self.makeindex(req, tmpl)
 
                 # nested indexes and hgwebs
 
                 repos = dict(self.repos)
                 virtualrepo = virtual
                 while virtualrepo:
                     real = repos.get(virtualrepo)
                     if real:
                         req.env['REPO_NAME'] = virtualrepo
                         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))
 
                     up = virtualrepo.rfind('/')
                     if up < 0:
                         break
                     virtualrepo = virtualrepo[:up]
 
                 # browse subdirectories
                 subdir = virtual + '/'
                 if [r for r in repos if r.startswith(subdir)]:
                     req.respond(HTTP_OK, ctype)
                     return self.makeindex(req, tmpl, subdir)
 
                 # prefixes not found
                 req.respond(HTTP_NOT_FOUND, ctype)
                 return tmpl("notfound", repo=virtual)
 
             except ErrorResponse, err:
                 req.respond(err, ctype)
                 return tmpl('error', error=err.message or '')
         finally:
             tmpl = None
 
     def makeindex(self, req, tmpl, subdir=""):
 
         def archivelist(ui, nodeid, url):
             allowed = ui.configlist("web", "allow_archive", untrusted=True)
+            archives = []
             for i in [('zip', '.zip'), ('gz', '.tar.gz'), ('bz2', '.tar.bz2')]:
                 if i[0] in allowed or ui.configbool("web", "allow" + i[0],
                                                     untrusted=True):
-                    yield {"type" : i[0], "extension": i[1],
-                           "node": nodeid, "url": url}
+                    archives.append({"type" : i[0], "extension": i[1],
+                                     "node": nodeid, "url": url})
+            return archives
 
         def rawentries(subdir="", **map):
 
             descend = self.ui.configbool('web', 'descend', True)
             for name, path in self.repos:
 
                 if not name.startswith(subdir):
                     continue
                 name = name[len(subdir):]
                 if not descend and '/' in name:
                     continue
 
                 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 = re.sub(r'/+', '/', '/'.join(parts) + '/')
 
                 # update time with local timezone
                 try:
                     r = hg.repository(self.ui, path)
                 except error.RepoError:
                     u.warn(_('error accessing repository at %s\n') % path)
                     continue
                 try:
                     d = (get_mtime(r.spath), util.makedate()[1])
                 except OSError:
                     continue
 
                 contact = get_contact(get)
                 description = get("web", "description", "")
                 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))
                 yield row
 
         sortdefault = None, False
         def entries(sortcolumn="", descending=False, subdir="", **map):
             rows = rawentries(subdir=subdir, **map)
 
             if sortcolumn and sortdefault != (sortcolumn, descending):
                 sortkey = '%s_sort' % sortcolumn
                 rows = sorted(rows, key=lambda x: x[sortkey],
                               reverse=descending)
             for row, parity in zip(rows, paritygen(self.stripecount)):
                 row['parity'] = parity
                 yield row
 
         self.refresh()
         sortable = ["name", "description", "contact", "lastchange"]
         sortcolumn, descending = sortdefault
         if 'sort' in req.form:
             sortcolumn = req.form['sort'][0]
             descending = sortcolumn.startswith('-')
             if descending:
                 sortcolumn = sortcolumn[1:]
             if sortcolumn not in sortable:
                 sortcolumn = ""
 
         sort = [("sort_%s" % column,
                  "%s%s" % ((not descending and column == sortcolumn)
                             and "-" or "", column))
                 for column in sortable]
 
         self.refresh()
         self.updatereqenv(req.env)
 
         return tmpl("index", entries=entries, subdir=subdir,
                     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)
 
         self.updatereqenv(req.env)
 
         url = req.env.get('SCRIPT_NAME', '')
         if not url.endswith('/'):
             url += '/'
 
         vars = {}
         styles = (
             req.form.get('style', [None])[0],
             config('web', 'style'),
             'paper'
         )
         style, mapfile = templater.stylemap(styles, self.templatepath)
         if style == styles[0]:
             vars['style'] = style
 
         start = url[-1] == '?' and '&' or '?'
         sessionvars = webutil.sessionvars(vars, start)
         staticurl = config('web', 'staticurl') or url + 'static/'
         if not staticurl.endswith('/'):
             staticurl += '/'
 
         tmpl = templater.templater(mapfile,
                                    defaults={"header": header,
                                              "footer": footer,
                                              "motd": motd,
                                              "url": url,
                                              "staticurl": staticurl,
                                              "sessionvars": sessionvars})
         return tmpl
 
     def updatereqenv(self, env):
         def splitnetloc(netloc):
             if ':' in netloc:
                 return netloc.split(':', 1)
             else:
                 return (netloc, None)
 
         if self._baseurl is not None:
             urlcomp = urlparse.urlparse(self._baseurl)
             host, port = splitnetloc(urlcomp[1])
             path = urlcomp[2]
             env['SERVER_NAME'] = host
             if port:
                 env['SERVER_PORT'] = port
             env['SCRIPT_NAME'] = path