view mercurial/statichttprepo.py @ 23971:6becb9dbca25 stable

merge: mark .hgsubstate as possibly dirty before submerge for consistency

Before this patch, failure of updating subrepos may cause inconsistent
".hgsubstate". For example:

  1. dirstate entry for ".hgsubstate" of the parent repo is filled
     with valid size/date (via "hg state" or so)

  2. "hg update" is invoked at the parent repo

  3. ".hgsubstate" of the parent repo is updated on the filesystem as
     a part of "g"(et) action in "merge.applyupdates"

  4. it is assumed that size/date of ".hgsubstate" on the filesystem
     aren't changed from ones at (1)

     this is not so difficult condition, because just changing hash
     ids (every ids are same in length) in ".hgsubstate" doesn't
     change the file size of it

  5. "subrepo.submerge()" is invoked to update subrepos

  6. failure of updating in one of subrepos raises exception
     (e.g. "untracked file differs")

  7. "hg update" is aborted without updating dirstate of the parent repo

     dirstate entry for ".hgsubstate" still holds size/date at (1)

Then, ".hgsubstate" of the parent repo is treated as "CLEAN"
unexpectedly, because updating ".hgsubstate" at (3) doesn't change
size/date of it on the filesystem: see assumption at (4).

This inconsistent ".hgsubstate" status causes unexpected behavior, for
example:

  - "hg revert" forgets to revert ".hgsubstate"

  - "hg update" misunderstands that (not yet updated) subrepos diverge
    (then, it shows the prompt to confirm user's decision)

To avoid inconsistent ".hgsubstate" status above, this patch marks
".hgsubstate" as possibly dirty before "submerge" invocation.
"normallookup"-ed (= dirty) dirstate should be written out, even if
processing is aborted by failure.

This patch marks ".hgsubstate" as possibly dirty before "submerge",
also when it is removed or merged while merging, for safety. This
should prevent Mercurial from misunderstanding inconsistent
".hgsubstate" as clean.

To satisfy conditions at (1) and (4) above, this patch uses "hg status
--config debug.dirstate.delaywrite=2" (to fill valid size/date into
dirstate) and "touch" (to fix date of the file).

# statichttprepo.py - simple http repository class for mercurial
#
# This provides read-only repo access to repositories exported via static http
#
# Copyright 2005-2007 Matt Mackall <[e-mail]>
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.

from i18n import _
import changelog, byterange, url, error, namespaces
import localrepo, manifest, util, scmutil, store
import urllib, urllib2, errno, os

class httprangereader(object):
    def __init__(self, url, opener):
        # we assume opener has HTTPRangeHandler
        self.url = url
        self.pos = 0
        self.opener = opener
        self.name = url
    def seek(self, pos):
        self.pos = pos
    def read(self, bytes=None):
        req = urllib2.Request(self.url)
        end = ''
        if bytes:
            end = self.pos + bytes - 1
        if self.pos or end:
            req.add_header('Range', 'bytes=%d-%s' % (self.pos, end))

        try:
            f = self.opener.open(req)
            data = f.read()
            # Python 2.6+ defines a getcode() function, and 2.4 and
            # 2.5 appear to always have an undocumented code attribute
            # set. If we can't read either of those, fall back to 206
            # and hope for the best.
            code = getattr(f, 'getcode', lambda : getattr(f, 'code', 206))()
        except urllib2.HTTPError, inst:
            num = inst.code == 404 and errno.ENOENT or None
            raise IOError(num, inst)
        except urllib2.URLError, inst:
            raise IOError(None, inst.reason[1])

        if code == 200:
            # HTTPRangeHandler does nothing if remote does not support
            # Range headers and returns the full entity. Let's slice it.
            if bytes:
                data = data[self.pos:self.pos + bytes]
            else:
                data = data[self.pos:]
        elif bytes:
            data = data[:bytes]
        self.pos += len(data)
        return data
    def readlines(self):
        return self.read().splitlines(True)
    def __iter__(self):
        return iter(self.readlines())
    def close(self):
        pass

def build_opener(ui, authinfo):
    # urllib cannot handle URLs with embedded user or passwd
    urlopener = url.opener(ui, authinfo)
    urlopener.add_handler(byterange.HTTPRangeHandler())

    class statichttpvfs(scmutil.abstractvfs):
        def __init__(self, base):
            self.base = base

        def __call__(self, path, mode='r', *args, **kw):
            if mode not in ('r', 'rb'):
                raise IOError('Permission denied')
            f = "/".join((self.base, urllib.quote(path)))
            return httprangereader(f, urlopener)

        def join(self, path):
            if path:
                return os.path.join(self.base, path)
            else:
                return self.base

    return statichttpvfs

class statichttppeer(localrepo.localpeer):
    def local(self):
        return None
    def canpush(self):
        return False

class statichttprepository(localrepo.localrepository):
    supported = localrepo.localrepository._basesupported

    def __init__(self, ui, path):
        self._url = path
        self.ui = ui

        self.root = path
        u = util.url(path.rstrip('/') + "/.hg")
        self.path, authinfo = u.authinfo()

        opener = build_opener(ui, authinfo)
        self.opener = opener(self.path)
        self.vfs = self.opener
        self._phasedefaults = []

        self.names = namespaces.namespaces()

        try:
            requirements = scmutil.readrequires(self.vfs, self.supported)
        except IOError, inst:
            if inst.errno != errno.ENOENT:
                raise
            requirements = set()

            # check if it is a non-empty old-style repository
            try:
                fp = self.vfs("00changelog.i")
                fp.read(1)
                fp.close()
            except IOError, inst:
                if inst.errno != errno.ENOENT:
                    raise
                # we do not care about empty old-style repositories here
                msg = _("'%s' does not appear to be an hg repository") % path
                raise error.RepoError(msg)

        # setup store
        self.store = store.store(requirements, self.path, opener)
        self.spath = self.store.path
        self.svfs = self.store.opener
        self.sopener = self.svfs
        self.sjoin = self.store.join
        self._filecache = {}
        self.requirements = requirements

        self.manifest = manifest.manifest(self.svfs)
        self.changelog = changelog.changelog(self.svfs)
        self._tags = None
        self.nodetagscache = None
        self._branchcaches = {}
        self.encodepats = None
        self.decodepats = None

    def _restrictcapabilities(self, caps):
        caps = super(statichttprepository, self)._restrictcapabilities(caps)
        return caps.difference(["pushkey"])

    def url(self):
        return self._url

    def local(self):
        return False

    def peer(self):
        return statichttppeer(self)

    def lock(self, wait=True):
        raise util.Abort(_('cannot lock static-http repository'))

def instance(ui, path, create):
    if create:
        raise util.Abort(_('cannot create new static-http repository'))
    return statichttprepository(ui, path[7:])