view mercurial/statichttprepo.py @ 36426:23d12524a202

http: drop custom http client logic

Eight and a half years ago, as my starter bug on code.google.com, I
investigated a mysterious "broken pipe" error from seemingly random
clients[0]. That investigation revealed a tragic story: the Python
standard library's httplib was (and remains) barely functional. During
large POSTs, if a server responds early with an error (even a
permission denied error!) the client only notices that the server
closed the connection and everything breaks. Such server behavior is
implicitly legal under RFC 2616 (the latest HTTP RFC as of when I was
last working on this), and my understanding is that later RFCs have
made it explicitly legal to respond early with any status code outside
the 2xx range.

I embarked, probably foolishly, on a journey to write a new http
library with better overall behavior. The http library appears to work
well in most cases, but it can get confused in the presence of
proxies, and it depends on select(2) which limits its utility if a lot
of file descriptors are open. I haven't touched the http library in
almost two years, and in the interim the Python community has
discovered a better way[1] of writing network code. In theory some day
urllib3 will have its own home-grown http library built on h11[2], or
we could do that. Either way, it's time to declare our current
confusingly-named "http2" client logic and move on. I do hope to
revisit this some day: it's still garbage that we can't even respond
with a 401 or 403 without reading the entire POST body from the
client, but the goalposts on writing a new http client library have
moved substantially. We're almost certainly better off just switching
to requests and eventually picking up their http fixes than trying to
live with something that realistically only we'll ever use. Another
approach would be to write an adapter so that Mercurial can use pycurl
if it's installed. Neither of those approaches seem like they should
be investigated prior to a release of Mercurial that works on Python
3: that's where the mindshare is going to be for any improvements to
the state of the http client art.

0: http://web.archive.org/web/20130501031801/http://code.google.com/p/support/issues/detail?id=2716
1: http://sans-io.readthedocs.io/
2: https://github.com/njsmith/h11

Differential Revision: https://phab.mercurial-scm.org/D2444

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