view mercurial/statichttprepo.py @ 39314:7f5e6d3e9032

manifest: proxy to revlog instance instead of inheriting

Previously, manifestrevlog inherited revlog.revlog and therefore
exposed all its APIs. This inevitably resulted in consumers calling
low-level revlog APIs.

As part of abstracting storage, we want to formalize the interface
for manifest storage. The revlog API is much too large to define as
the interface.

Like we did for filelog, this commit divorces the manifest class
from revlog so that we can standardize on a smaller API surface.

The way I went about this commit was I broke the inheritance, ran
tests, and added proxies until all tests passed. Like filelog, there
are a handful of attributes that don't belong on the interface.
And like filelog, we'll tease these out in the future.

As part of this, we formalize an interface for manifest storage and
add checks that manifestrevlog conforms to the interface.

Adding proxies will introduce some overhead due to extra attribute
lookups and function calls. On the mozilla-unified repository:

$ hg verify
before: real 627.220 secs (user 525.870+0.000 sys 18.800+0.000)
after:  real 628.930 secs (user 532.050+0.000 sys 18.320+0.000)

$ hg serve (for a clone)
before: user 223.580+0.000 sys 14.270+0.000
after:  user 227.720+0.000 sys 13.920+0.000

$ hg clone
before: user 506.390+0.000 sys 29.720+0.000
after:  user 513.080+0.000 sys 28.280+0.000

There appears to be some overhead here. But it appears to be 1-2%.
I think that is an appropriate price to pay for storage abstraction,
which will eventually let us have much nicer things. If the overhead
is noticed in other operations (whose CPU time isn't likely dwarfed by
fulltext resolution) or if we want to cut down on the overhead, we
could dynamically build up a type whose methods are effectively
aliased to a revlog instance's. I'm inclined to punt on that problem
for now. We may have to do it for the changelog. At which point it
could be implemented in a generic way and ported to filelog and
manifestrevlog easily enough I would think.

.. api:: manifest.manifestrevlog no longer inherits from revlog

   The manifestrevlog class now wraps a revlog instance instead of
   inheriting from revlog. Various attributes and methods on instances
   are no longer available.

Differential Revision: https://phab.mercurial-scm.org/D4386

# 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 __future__ import absolute_import

import errno

from .i18n import _
from . import (
    changelog,
    error,
    localrepo,
    manifest,
    namespaces,
    pathutil,
    scmutil,
    store,
    url,
    util,
    vfs as vfsmod,
)

urlerr = util.urlerr
urlreq = util.urlreq

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 __enter__(self):
        return self

    def __exit__(self, exc_type, exc_value, traceback):
        self.close()

    def seek(self, pos):
        self.pos = pos
    def read(self, bytes=None):
        req = urlreq.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()
            code = f.code
        except urlerr.httperror as inst:
            num = inst.code == 404 and errno.ENOENT or None
            raise IOError(num, inst)
        except urlerr.urlerror as 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

# _RangeError and _HTTPRangeHandler were originally in byterange.py,
# which was itself extracted from urlgrabber. See the last version of
# byterange.py from history if you need more information.
class _RangeError(IOError):
    """Error raised when an unsatisfiable range is requested."""

class _HTTPRangeHandler(urlreq.basehandler):
    """Handler that enables HTTP Range headers.

    This was extremely simple. The Range header is a HTTP feature to
    begin with so all this class does is tell urllib2 that the
    "206 Partial Content" response from the HTTP server is what we
    expected.
    """

    def http_error_206(self, req, fp, code, msg, hdrs):
        # 206 Partial Content Response
        r = urlreq.addinfourl(fp, hdrs, req.get_full_url())
        r.code = code
        r.msg = msg
        return r

    def http_error_416(self, req, fp, code, msg, hdrs):
        # HTTP's Range Not Satisfiable error
        raise _RangeError('Requested Range Not Satisfiable')

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

    class statichttpvfs(vfsmod.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, urlreq.quote(path)))
            return httprangereader(f, urlopener)

        def join(self, path):
            if path:
                return pathutil.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()

        vfsclass = build_opener(ui, authinfo)
        self.vfs = vfsclass(self.path)
        self.cachevfs = vfsclass(self.vfs.join('cache'))
        self._phasedefaults = []

        self.names = namespaces.namespaces()
        self.filtername = None

        try:
            requirements = scmutil.readrequires(self.vfs, self.supported)
        except IOError as 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 as 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, vfsclass)
        self.spath = self.store.path
        self.svfs = self.store.opener
        self.sjoin = self.store.join
        self._filecache = {}
        self.requirements = requirements

        self.manifestlog = manifest.manifestlog(self.svfs, self)
        self.changelog = changelog.changelog(self.svfs)
        self._tags = None
        self.nodetagscache = None
        self._branchcaches = {}
        self._revbranchcache = None
        self.encodepats = None
        self.decodepats = None
        self._transref = 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 wlock(self, wait=True):
        raise error.LockUnavailable(0, _('lock not available'), 'lock',
                                    _('cannot lock static-http repository'))

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

    def _writecaches(self):
        pass # statichttprepository are read only

def instance(ui, path, create, intents=None):
    if create:
        raise error.Abort(_('cannot create new static-http repository'))
    return statichttprepository(ui, path[7:])