httprepo: make __del__ more stable in error situations

Some errors could leave self.urlopener uninitialized and thus cause strange
crashes in __del__.

This member variable is now "declared statically" and checked for assignment
before use.

mercurial/httprepo.py

@@ -1,245 +1,247 b''
 # httprepo.py - HTTP repository proxy classes for mercurial
 #
 # Copyright 2005, 2006 Matt Mackall <[e-mail]>
 # Copyright 2006 Vadim Gelfer <[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.
 
 from node import nullid
 from i18n import _
 import changegroup, statichttprepo, error, httpconnection, url, util, wireproto
 import os, urllib, urllib2, zlib, httplib
 import errno, socket
 
 def zgenerator(f):
     zd = zlib.decompressobj()
     try:
         for chunk in util.filechunkiter(f):
             while chunk:
                 yield zd.decompress(chunk, 2**18)
                 chunk = zd.unconsumed_tail
     except httplib.HTTPException:
         raise IOError(None, _('connection ended unexpectedly'))
     yield zd.flush()
 
 class httprepository(wireproto.wirerepository):
     def __init__(self, ui, path):
         self.path = path
         self.caps = None
         self.handler = None
+        self.urlopener = None
         u = util.url(path)
         if u.query or u.fragment:
             raise util.Abort(_('unsupported URL component: "%s"') %
                              (u.query or u.fragment))
 
         # urllib cannot handle URLs with embedded user or passwd
         self._url, authinfo = u.authinfo()
 
         self.ui = ui
         self.ui.debug('using %s\n' % self._url)
 
         self.urlopener = url.opener(ui, authinfo)
 
     def __del__(self):
-        for h in self.urlopener.handlers:
-            h.close()
-            getattr(h, "close_all", lambda : None)()
+        if self.urlopener:
+            for h in self.urlopener.handlers:
+                h.close()
+                getattr(h, "close_all", lambda : None)()
 
     def url(self):
         return self.path
 
     # look up capabilities only when needed
 
     def _fetchcaps(self):
         self.caps = set(self._call('capabilities').split())
 
     def get_caps(self):
         if self.caps is None:
             try:
                 self._fetchcaps()
             except error.RepoError:
                 self.caps = set()
             self.ui.debug('capabilities: %s\n' %
                           (' '.join(self.caps or ['none'])))
         return self.caps
 
     capabilities = property(get_caps)
 
     def lock(self):
         raise util.Abort(_('operation not supported over http'))
 
     def _callstream(self, cmd, **args):
         if cmd == 'pushkey':
             args['data'] = ''
         data = args.pop('data', None)
         size = 0
         if util.safehasattr(data, 'length'):
             size = data.length
         elif data is not None:
             size = len(data)
         headers = args.pop('headers', {})
 
         if size and self.ui.configbool('ui', 'usehttp2', False):
             headers['Expect'] = '100-Continue'
             headers['X-HgHttp2'] = '1'
 
         self.ui.debug("sending %s command\n" % cmd)
         q = [('cmd', cmd)]
         headersize = 0
         if len(args) > 0:
             httpheader = self.capable('httpheader')
             if httpheader:
                 headersize = int(httpheader.split(',')[0])
         if headersize > 0:
             # The headers can typically carry more data than the URL.
             encargs = urllib.urlencode(sorted(args.items()))
             headerfmt = 'X-HgArg-%s'
             contentlen = headersize - len(headerfmt % '000' + ': \r\n')
             headernum = 0
             for i in xrange(0, len(encargs), contentlen):
                 headernum += 1
                 header = headerfmt % str(headernum)
                 headers[header] = encargs[i:i + contentlen]
             varyheaders = [headerfmt % str(h) for h in range(1, headernum + 1)]
             headers['Vary'] = ','.join(varyheaders)
         else:
             q += sorted(args.items())
         qs = '?%s' % urllib.urlencode(q)
         cu = "%s%s" % (self._url, qs)
         req = urllib2.Request(cu, data, headers)
         if data is not None:
             self.ui.debug("sending %s bytes\n" % size)
             req.add_unredirected_header('Content-Length', '%d' % size)
         try:
             resp = self.urlopener.open(req)
         except urllib2.HTTPError, inst:
             if inst.code == 401:
                 raise util.Abort(_('authorization failed'))
             raise
         except httplib.HTTPException, inst:
             self.ui.debug('http error while sending %s command\n' % cmd)
             self.ui.traceback()
             raise IOError(None, inst)
         except IndexError:
             # this only happens with Python 2.3, later versions raise URLError
             raise util.Abort(_('http error, possibly caused by proxy setting'))
         # record the url we got redirected to
         resp_url = resp.geturl()
         if resp_url.endswith(qs):
             resp_url = resp_url[:-len(qs)]
         if self._url.rstrip('/') != resp_url.rstrip('/'):
             if not self.ui.quiet:
                 self.ui.warn(_('real URL is %s\n') % resp_url)
         self._url = resp_url
         try:
             proto = resp.getheader('content-type')
         except AttributeError:
             proto = resp.headers.get('content-type', '')
 
         safeurl = util.hidepassword(self._url)
         if proto.startswith('application/hg-error'):
             raise error.OutOfBandError(resp.read())
         # accept old "text/plain" and "application/hg-changegroup" for now
         if not (proto.startswith('application/mercurial-') or
                 proto.startswith('text/plain') or
                 proto.startswith('application/hg-changegroup')):
             self.ui.debug("requested URL: '%s'\n" % util.hidepassword(cu))
             raise error.RepoError(
                 _("'%s' does not appear to be an hg repository:\n"
                   "---%%<--- (%s)\n%s\n---%%<---\n")
                 % (safeurl, proto or 'no content-type', resp.read()))
 
         if proto.startswith('application/mercurial-'):
             try:
                 version = proto.split('-', 1)[1]
                 version_info = tuple([int(n) for n in version.split('.')])
             except ValueError:
                 raise error.RepoError(_("'%s' sent a broken Content-Type "
                                         "header (%s)") % (safeurl, proto))
             if version_info > (0, 1):
                 raise error.RepoError(_("'%s' uses newer protocol %s") %
                                       (safeurl, version))
 
         return resp
 
     def _call(self, cmd, **args):
         fp = self._callstream(cmd, **args)
         try:
             return fp.read()
         finally:
             # if using keepalive, allow connection to be reused
             fp.close()
 
     def _callpush(self, cmd, cg, **args):
         # have to stream bundle to a temp file because we do not have
         # http 1.1 chunked transfer.
 
         types = self.capable('unbundle')
         try:
             types = types.split(',')
         except AttributeError:
             # servers older than d1b16a746db6 will send 'unbundle' as a
             # boolean capability. They only support headerless/uncompressed
             # bundles.
             types = [""]
         for x in types:
             if x in changegroup.bundletypes:
                 type = x
                 break
 
         tempname = changegroup.writebundle(cg, None, type)
         fp = httpconnection.httpsendfile(self.ui, tempname, "rb")
         headers = {'Content-Type': 'application/mercurial-0.1'}
 
         try:
             try:
                 r = self._call(cmd, data=fp, headers=headers, **args)
                 vals = r.split('\n', 1)
                 if len(vals) < 2:
                     raise error.ResponseError(_("unexpected response:"), r)
                 return vals
             except socket.error, err:
                 if err.args[0] in (errno.ECONNRESET, errno.EPIPE):
                     raise util.Abort(_('push failed: %s') % err.args[1])
                 raise util.Abort(err.args[1])
         finally:
             fp.close()
             os.unlink(tempname)
 
     def _abort(self, exception):
         raise exception
 
     def _decompress(self, stream):
         return util.chunkbuffer(zgenerator(stream))
 
 class httpsrepository(httprepository):
     def __init__(self, ui, path):
         if not url.has_https:
             raise util.Abort(_('Python support for SSL and HTTPS '
                                'is not installed'))
         httprepository.__init__(self, ui, path)
 
 def instance(ui, path, create):
     if create:
         raise util.Abort(_('cannot create new http repository'))
     try:
         if path.startswith('https:'):
             inst = httpsrepository(ui, path)
         else:
             inst = httprepository(ui, path)
         try:
             # Try to do useful work when checking compatibility.
             # Usually saves a roundtrip since we want the caps anyway.
             inst._fetchcaps()
         except error.RepoError:
             # No luck, try older compatibility check.
             inst.between([(nullid, nullid)])
         return inst
     except error.RepoError, httpexception:
         try:
             r = statichttprepo.instance(ui, "static-" + path, create)
             ui.note('(falling back to static-http)\n')
             return r
         except error.RepoError:
             raise httpexception # use the original http RepoError instead

tests/test-url-rev.t

@@ -1,203 +1,207 b''
 Test basic functionality of url#rev syntax
 
   $ hg init repo
   $ cd repo
   $ echo a > a
   $ hg ci -qAm 'add a'
   $ hg branch foo
   marked working directory as branch foo
   $ echo >> a
   $ hg ci -m 'change a'
   $ cd ..
 
   $ hg clone 'repo#foo' clone
   adding changesets
   adding manifests
   adding file changes
   added 2 changesets with 2 changes to 1 files
   updating to branch foo
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
 
   $ hg --cwd clone heads
   changeset:   1:cd2a86ecc814
   branch:      foo
   tag:         tip
   user:        test
   date:        Thu Jan 01 00:00:00 1970 +0000
   summary:     change a
   
   changeset:   0:1f0dee641bb7
   user:        test
   date:        Thu Jan 01 00:00:00 1970 +0000
   summary:     add a
   
   $ hg --cwd clone parents
   changeset:   1:cd2a86ecc814
   branch:      foo
   tag:         tip
   user:        test
   date:        Thu Jan 01 00:00:00 1970 +0000
   summary:     change a
   
   $ cat clone/.hg/hgrc
   [paths]
   default = $TESTTMP/repo#foo
 
 Changing original repo:
 
   $ cd repo
 
   $ echo >> a
   $ hg ci -m 'new head of branch foo'
 
   $ hg up -qC default
   $ echo bar > bar
   $ hg ci -qAm 'add bar'
 
   $ hg log
   changeset:   3:4cd725637392
   tag:         tip
   parent:      0:1f0dee641bb7
   user:        test
   date:        Thu Jan 01 00:00:00 1970 +0000
   summary:     add bar
   
   changeset:   2:faba9097cad4
   branch:      foo
   user:        test
   date:        Thu Jan 01 00:00:00 1970 +0000
   summary:     new head of branch foo
   
   changeset:   1:cd2a86ecc814
   branch:      foo
   user:        test
   date:        Thu Jan 01 00:00:00 1970 +0000
   summary:     change a
   
   changeset:   0:1f0dee641bb7
   user:        test
   date:        Thu Jan 01 00:00:00 1970 +0000
   summary:     add a
   
   $ hg -q outgoing '../clone#foo'
   2:faba9097cad4
 
   $ hg -q push '../clone#foo'
 
   $ hg --cwd ../clone heads
   changeset:   2:faba9097cad4
   branch:      foo
   tag:         tip
   user:        test
   date:        Thu Jan 01 00:00:00 1970 +0000
   summary:     new head of branch foo
   
   changeset:   0:1f0dee641bb7
   user:        test
   date:        Thu Jan 01 00:00:00 1970 +0000
   summary:     add a
   
   $ cd ..
 
   $ cd clone
   $ hg rollback
   repository tip rolled back to revision 1 (undo push)
 
   $ hg -q incoming
   2:faba9097cad4
 
   $ hg -q pull
 
   $ hg heads
   changeset:   2:faba9097cad4
   branch:      foo
   tag:         tip
   user:        test
   date:        Thu Jan 01 00:00:00 1970 +0000
   summary:     new head of branch foo
   
   changeset:   0:1f0dee641bb7
   user:        test
   date:        Thu Jan 01 00:00:00 1970 +0000
   summary:     add a
   
 Pull should not have updated:
 
   $ hg parents -q
   1:cd2a86ecc814
 
 Going back to the default branch:
 
   $ hg up -C 0
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
 
   $ hg parents
   changeset:   0:1f0dee641bb7
   user:        test
   date:        Thu Jan 01 00:00:00 1970 +0000
   summary:     add a
   
 No new revs, no update:
 
   $ hg pull -qu
 
   $ hg parents -q
   0:1f0dee641bb7
 
   $ hg rollback
   repository tip rolled back to revision 1 (undo pull)
 
   $ hg parents -q
   0:1f0dee641bb7
 
 Pull -u takes us back to branch foo:
 
   $ hg pull -qu
 
   $ hg parents
   changeset:   2:faba9097cad4
   branch:      foo
   tag:         tip
   user:        test
   date:        Thu Jan 01 00:00:00 1970 +0000
   summary:     new head of branch foo
   
   $ hg rollback
   repository tip rolled back to revision 1 (undo pull)
   working directory now based on revision 0
 
   $ hg up -C 0
   1 files updated, 0 files merged, 0 files removed, 0 files unresolved
 
   $ hg parents -q
   0:1f0dee641bb7
 
   $ hg heads -q
   1:cd2a86ecc814
   0:1f0dee641bb7
 
   $ hg pull -qur default default
 
   $ hg parents
   changeset:   3:4cd725637392
   tag:         tip
   parent:      0:1f0dee641bb7
   user:        test
   date:        Thu Jan 01 00:00:00 1970 +0000
   summary:     add bar
   
   $ hg heads
   changeset:   3:4cd725637392
   tag:         tip
   parent:      0:1f0dee641bb7
   user:        test
   date:        Thu Jan 01 00:00:00 1970 +0000
   summary:     add bar
   
   changeset:   2:faba9097cad4
   branch:      foo
   user:        test
   date:        Thu Jan 01 00:00:00 1970 +0000
   summary:     new head of branch foo
   
+Test handling of invalid urls
 
+  $ hg id http://foo/?bar
+  abort: unsupported URL component: "bar"
+  [255]