view mercurial/httprepo.py @ 14301:f94993769c87

revlog: improve delta generation heuristics for generaldelta

Without this change, pulls (and clones) into a generaldelta repository could
generate very inefficient revlogs, the size of which could be at least twice
the original size.

This was caused by the generated delta chains covering too large distances,
causing new chains to be built far too often. This change addresses the
problem by forcing a delta against second parent or against the previous
revision, when the first parent delta is in danger of creating a long chain.

# 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
        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()
            if hasattr(h, "close_all"):
                h.close_all()

    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)
        headers = args.pop('headers', {})

        if data and self.ui.configbool('ui', 'usehttp2', False):
            headers['Expect'] = '100-Continue'

        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:
            # len(data) is broken if data doesn't fit into Py_ssize_t
            # add the header ourself to avoid OverflowError
            size = data.__len__()
            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('/'):
            self.ui.status(_('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)
        # 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)
                return r.split('\n', 1)
            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