merge with -stable

mercurial/hgweb/hgweb_mod.py

@@ -1,313 +1,313 b''
 # hgweb/hgweb_mod.py - Web interface for a repository.
 #
 # Copyright 21 May 2005 - (c) 2005 Jake Edge <[e-mail]>
 # Copyright 2005-2007 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms
 # of the GNU General Public License, incorporated herein by reference.
 
 import os, mimetypes
 from mercurial.node import hex, nullid
 from mercurial import ui, hg, util, hook, error
 from mercurial import templater, templatefilters
 from common import get_mtime, style_map, 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):
             parentui = ui.ui(report_untrusted=False, interactive=False)
             self.repo = hg.repository(parentui, 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",
                                         templater.templatepath(),
                                         untrusted=False)
 
     # 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", util._encoding)
 
     def run(self):
         if not os.environ.get('GATEWAY_INTERFACE', '').startswith("CGI/1."):
             raise RuntimeError("This function is only intended to be called while running as a CGI script.")
         import mercurial.hgweb.wsgicgi as wsgicgi
         wsgicgi.launch(self)
 
     def __call__(self, env, respond):
         req = wsgirequest(env, respond)
         return self.run_wsgi(req)
 
     def run_wsgi(self, req):
 
         self.refresh()
 
         # process this if it's a protocol request
         # protocol bits don't need to create any URLs
         # and the clients always use the old URL structure
 
         cmd = req.form.get('cmd', [''])[0]
         if cmd and cmd in protocol.__all__:
             try:
                 if cmd in perms:
                     try:
                         self.check_perm(req, perms[cmd])
                     except ErrorResponse, inst:
                         if cmd == 'unbundle':
                             req.drain()
                         raise
                 method = getattr(protocol, cmd)
                 return method(self.repo, req)
             except ErrorResponse, inst:
                 req.respond(inst, protocol.HGTYPE)
                 if not inst.message:
                     return []
                 return '0\n%s\n' % inst.message,
 
         # work with CGI variables to create coherent structure
         # use SCRIPT_NAME, PATH_INFO and QUERY_STRING as well as our REPO_NAME
 
         req.url = req.env['SCRIPT_NAME']
         if not req.url.endswith('/'):
             req.url += '/'
         if 'REPO_NAME' in req.env:
             req.url += req.env['REPO_NAME'] + '/'
 
         if 'PATH_INFO' in req.env:
             parts = req.env['PATH_INFO'].strip('/').split('/')
             repo_parts = req.env.get('REPO_NAME', '').split('/')
             if parts[:len(repo_parts)] == repo_parts:
                 parts = parts[len(repo_parts):]
             query = '/'.join(parts)
         else:
             query = req.env['QUERY_STRING'].split('&', 1)[0]
             query = query.split(';', 1)[0]
 
         # translate user-visible url structure to internal structure
 
         args = query.split('/', 2)
         if 'cmd' not in req.form and args and args[0]:
 
             cmd = args.pop(0)
             style = cmd.rfind('-')
             if style != -1:
                 req.form['style'] = [cmd[:style]]
                 cmd = cmd[style+1:]
 
             # avoid accepting e.g. style parameter as command
             if hasattr(webcommands, cmd):
                 req.form['cmd'] = [cmd]
             else:
                 cmd = ''
 
             if cmd == 'static':
                 req.form['file'] = ['/'.join(args)]
             else:
                 if args and args[0]:
                     node = args.pop(0)
                     req.form['node'] = [node]
                 if args:
                     req.form['file'] = args
 
             if cmd == 'archive':
                 fn = req.form['node'][0]
                 for type_, spec in self.archive_specs.iteritems():
                     ext = spec[2]
                     if fn.endswith(ext):
                         req.form['node'] = [fn[:-len(ext)]]
                         req.form['type'] = [type_]
 
         # process the web interface request
 
         try:
             tmpl = self.templater(req)
             ctype = tmpl('mimetype', encoding=self.encoding)
             ctype = 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 = style_map(self.templatepath, style)
 
         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, templatefilters.filters,
                                    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:
+        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/verify.py

@@ -1,239 +1,244 b''
 # verify.py - repository integrity checking for Mercurial
 #
 # Copyright 2006, 2007 Matt Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms
 # of the GNU General Public License, incorporated herein by reference.
 
 from node import nullid, short
 from i18n import _
-import revlog, util
+import revlog, util, error
 
 def verify(repo):
     lock = repo.lock()
     try:
         return _verify(repo)
     finally:
         del lock
 
 def _verify(repo):
     mflinkrevs = {}
     filelinkrevs = {}
     filenodes = {}
     revisions = 0
     badrevs = {}
     errors = [0]
     warnings = [0]
     ui = repo.ui
     cl = repo.changelog
     mf = repo.manifest
 
     if not repo.cancopy():
         raise util.Abort(_("cannot verify bundle or remote repos"))
 
     def err(linkrev, msg, filename=None):
         if linkrev != None:
             badrevs[linkrev] = True
         else:
             linkrev = '?'
         msg = "%s: %s" % (linkrev, msg)
         if filename:
             msg = "%s@%s" % (filename, msg)
         ui.warn(" " + msg + "\n")
         errors[0] += 1
 
     def exc(linkrev, msg, inst, filename=None):
         if isinstance(inst, KeyboardInterrupt):
             ui.warn(_("interrupted"))
             raise
         err(linkrev, "%s: %s" % (msg, inst), filename)
 
     def warn(msg):
         ui.warn(msg + "\n")
         warnings[0] += 1
 
     def checklog(obj, name):
         if not len(obj) and (havecl or havemf):
             err(0, _("empty or missing %s") % name)
             return
 
         d = obj.checksize()
         if d[0]:
             err(None, _("data length off by %d bytes") % d[0], name)
         if d[1]:
             err(None, _("index contains %d extra bytes") % d[1], name)
 
         if obj.version != revlog.REVLOGV0:
             if not revlogv1:
                 warn(_("warning: `%s' uses revlog format 1") % name)
         elif revlogv1:
             warn(_("warning: `%s' uses revlog format 0") % name)
 
     def checkentry(obj, i, node, seen, linkrevs, f):
         lr = obj.linkrev(obj.rev(node))
         if lr < 0 or (havecl and lr not in linkrevs):
             t = "unexpected"
             if lr < 0 or lr >= len(cl):
                 t = "nonexistent"
             err(None, _("rev %d point to %s changeset %d") % (i, t, lr), f)
             if linkrevs:
                 warn(_(" (expected %s)") % " ".join(map(str,linkrevs)))
             lr = None # can't be trusted
 
         try:
             p1, p2 = obj.parents(node)
             if p1 not in seen and p1 != nullid:
                 err(lr, _("unknown parent 1 %s of %s") %
                     (short(p1), short(n)), f)
             if p2 not in seen and p2 != nullid:
                 err(lr, _("unknown parent 2 %s of %s") %
                     (short(p2), short(p1)), f)
         except Exception, inst:
             exc(lr, _("checking parents of %s") % short(node), inst, f)
 
         if node in seen:
             err(lr, _("duplicate revision %d (%d)") % (i, seen[n]), f)
         seen[n] = i
         return lr
 
     revlogv1 = cl.version != revlog.REVLOGV0
     if ui.verbose or not revlogv1:
         ui.status(_("repository uses revlog format %d\n") %
                        (revlogv1 and 1 or 0))
 
     havecl = len(cl) > 0
     havemf = len(mf) > 0
 
     ui.status(_("checking changesets\n"))
     seen = {}
     checklog(cl, "changelog")
     for i in repo:
         n = cl.node(i)
         checkentry(cl, i, n, seen, [i], "changelog")
 
         try:
             changes = cl.read(n)
             mflinkrevs.setdefault(changes[0], []).append(i)
             for f in changes[3]:
                 filelinkrevs.setdefault(f, []).append(i)
         except Exception, inst:
             exc(i, _("unpacking changeset %s") % short(n), inst)
 
     ui.status(_("checking manifests\n"))
     seen = {}
     checklog(mf, "manifest")
     for i in mf:
         n = mf.node(i)
         lr = checkentry(mf, i, n, seen, mflinkrevs.get(n, []), "manifest")
         if n in mflinkrevs:
             del mflinkrevs[n]
 
         try:
             for f, fn in mf.readdelta(n).iteritems():
                 if not f:
                     err(lr, _("file without name in manifest"))
                 elif f != "/dev/null":
                     fns = filenodes.setdefault(f, {})
                     if fn not in fns:
                         fns[fn] = i
         except Exception, inst:
             exc(lr, _("reading manifest delta %s") % short(n), inst)
 
     ui.status(_("crosschecking files in changesets and manifests\n"))
 
     if havemf:
         for c, m in util.sort([(c, m) for m in mflinkrevs for c in mflinkrevs[m]]):
             err(c, _("changeset refers to unknown manifest %s") % short(m))
         del mflinkrevs
 
         for f in util.sort(filelinkrevs):
             if f not in filenodes:
                 lr = filelinkrevs[f][0]
                 err(lr, _("in changeset but not in manifest"), f)
 
     if havecl:
         for f in util.sort(filenodes):
             if f not in filelinkrevs:
                 try:
                     fl = repo.file(f)
                     lr = min([fl.linkrev(fl.rev(n)) for n in filenodes[f]])
                 except:
                     lr = None
                 err(lr, _("in manifest but not in changeset"), f)
 
     ui.status(_("checking files\n"))
 
     storefiles = {}
     for f, f2, size in repo.store.datafiles():
         if not f:
             err(None, _("cannot decode filename '%s'") % f2)
         elif size > 0:
             storefiles[f] = True
 
     files = util.sort(util.unique(filenodes.keys() + filelinkrevs.keys()))
     for f in files:
+        lr = filelinkrevs[f][0]
+        try:
         fl = repo.file(f)
+        except error.RevlogError, e:
+            err(lr, _("broken revlog! (%s)") % e, f)
+            continue
 
         for ff in fl.files():
             try:
                 del storefiles[ff]
             except KeyError:
-                err(0, _("missing revlog!"), ff)
+                err(lr, _("missing revlog!"), ff)
 
         checklog(fl, f)
         seen = {}
         for i in fl:
             revisions += 1
             n = fl.node(i)
             lr = checkentry(fl, i, n, seen, filelinkrevs.get(f, []), f)
             if f in filenodes:
                 if havemf and n not in filenodes[f]:
                     err(lr, _("%s not in manifests") % (short(n)), f)
                 else:
                     del filenodes[f][n]
 
             # verify contents
             try:
                 t = fl.read(n)
                 rp = fl.renamed(n)
                 if len(t) != fl.size(i):
                     if len(fl.revision(n)) != fl.size(i):
                         err(lr, _("unpacked size is %s, %s expected") %
                             (len(t), fl.size(i)), f)
             except Exception, inst:
                 exc(lr, _("unpacking %s") % short(n), inst, f)
 
             # check renames
             try:
                 if rp:
                     fl2 = repo.file(rp[0])
                     if not len(fl2):
                         err(lr, _("empty or missing copy source revlog %s:%s")
                             % (rp[0], short(rp[1])), f)
                     elif rp[1] == nullid:
                         warn(_("warning: %s@%s: copy source revision is nullid %s:%s")
                             % (f, lr, rp[0], short(rp[1])))
                     else:
                         rev = fl2.rev(rp[1])
             except Exception, inst:
                 exc(lr, _("checking rename of %s") % short(n), inst, f)
 
         # cross-check
         if f in filenodes:
             fns = [(mf.linkrev(l), n) for n,l in filenodes[f].iteritems()]
             for lr, node in util.sort(fns):
                 err(lr, _("%s in manifests not found") % short(node), f)
 
     for f in storefiles:
         warn(_("warning: orphan revlog '%s'") % f)
 
     ui.status(_("%d files, %d changesets, %d total revisions\n") %
                    (len(files), len(cl), revisions))
     if warnings[0]:
         ui.warn(_("%d warnings encountered!\n") % warnings[0])
     if errors[0]:
         ui.warn(_("%d integrity errors encountered!\n") % errors[0])
         if badrevs:
             ui.warn(_("(first damaged changeset appears to be %d)\n")
                     % min(badrevs))
         return 1

tests/test-fncache.out

@@ -1,43 +1,43 b''
 % init repo1
 
 % add a; ci
 adding a
 
 % cat .hg/store/fncache
 data/a.i
 
 % add a.i/b; ci
 adding a.i/b
 
 % cat .hg/store/fncache
 data/a.i
 data/a.i.hg/b.i
 
 % add a.i.hg/c; ci
 adding a.i.hg/c
 
 % cat .hg/store/fncache
 data/a.i
 data/a.i.hg/b.i
 data/a.i.hg.hg/c.i
 
 % hg verify
 checking changesets
 checking manifests
 crosschecking files in changesets and manifests
 checking files
 3 files, 3 changesets, 3 total revisions
 
 % rm .hg/store/fncache
 
 % hg verify
 checking changesets
 checking manifests
 crosschecking files in changesets and manifests
 checking files
  data/a.i@0: missing revlog!
- data/a.i.hg.hg/c.i@0: missing revlog!
- data/a.i.hg/b.i@0: missing revlog!
+ data/a.i.hg.hg/c.i@2: missing revlog!
+ data/a.i.hg/b.i@1: missing revlog!
 3 files, 3 changesets, 3 total revisions
 3 integrity errors encountered!
 (first damaged changeset appears to be 0)