view mercurial/httppeer.py @ 30758:76104a4899ad

commands: config option to control bundle compression level

Currently, bundle compression uses the default compression level
for the active compression engine. The default compression level
is tuned as a compromise between speed and size.

Some scenarios may call for a different compression level. For
example, with clone bundles, bundles are generated once and used
several times. Since the cost to generate is paid infrequently,
server operators may wish to trade extra CPU time for better
compression ratios.

This patch introduces an experimental and undocumented config
option to control the bundle compression level. As the inline
comment says, this approach is a bit hacky. I'd prefer for
the compression level to be encoded in the bundle spec. e.g.
"zstd-v2;complevel=15." However, given that the 4.1 freeze is
imminent, I'm not comfortable implementing this user-facing
change without much time to test and consider the implications.
So, we're going with the quick and dirty solution for now.

Having this option in the 4.1 release will enable Mozilla to
easily produce and test zlib and zstd bundles with non-default
compression levels in production. This will help drive future
development of the feature and zstd integration with Mercurial.

# httppeer.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 __future__ import absolute_import

import errno
import os
import socket
import tempfile

from .i18n import _
from .node import nullid
from . import (
    bundle2,
    error,
    httpconnection,
    statichttprepo,
    url,
    util,
    wireproto,
)

httplib = util.httplib
urlerr = util.urlerr
urlreq = util.urlreq

# FUTURE: consider refactoring this API to use generators. This will
# require a compression engine API to emit generators.
def decompressresponse(response, engine):
    try:
        reader = engine.decompressorreader(response)
    except httplib.HTTPException:
        raise IOError(None, _('connection ended unexpectedly'))

    # We need to wrap reader.read() so HTTPException on subsequent
    # reads is also converted.
    # Ideally we'd use super() here. However, if ``reader`` isn't a new-style
    # class, this can raise:
    # TypeError: super() argument 1 must be type, not classobj
    origread = reader.read
    class readerproxy(reader.__class__):
        def read(self, *args, **kwargs):
            try:
                return origread(*args, **kwargs)
            except httplib.HTTPException:
                raise IOError(None, _('connection ended unexpectedly'))

    reader.__class__ = readerproxy
    return reader

class httppeer(wireproto.wirepeer):
    def __init__(self, ui, path):
        self.path = path
        self.caps = None
        self.handler = None
        self.urlopener = None
        self.requestbuilder = None
        u = util.url(path)
        if u.query or u.fragment:
            raise error.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)
        self.requestbuilder = urlreq.request

    def __del__(self):
        urlopener = getattr(self, 'urlopener', None)
        if urlopener:
            for h in 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 _capabilities(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

    def lock(self):
        raise error.Abort(_('operation not supported over http'))

    def _callstream(self, cmd, _compressible=False, **args):
        if cmd == 'pushkey':
            args['data'] = ''
        data = args.pop('data', None)
        headers = args.pop('headers', {})

        self.ui.debug("sending %s command\n" % cmd)
        q = [('cmd', cmd)]
        headersize = 0
        varyheaders = []
        # Important: don't use self.capable() here or else you end up
        # with infinite recursion when trying to look up capabilities
        # for the first time.
        postargsok = self.caps is not None and 'httppostargs' in self.caps
        # TODO: support for httppostargs when data is a file-like
        # object rather than a basestring
        canmungedata = not data or isinstance(data, basestring)
        if postargsok and canmungedata:
            strargs = urlreq.urlencode(sorted(args.items()))
            if strargs:
                if not data:
                    data = strargs
                elif isinstance(data, basestring):
                    data = strargs + data
                headers['X-HgArgs-Post'] = len(strargs)
        else:
            if len(args) > 0:
                httpheader = self.capable('httpheader')
                if httpheader:
                    headersize = int(httpheader.split(',', 1)[0])
            if headersize > 0:
                # The headers can typically carry more data than the URL.
                encargs = urlreq.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.append(header)
            else:
                q += sorted(args.items())
        qs = '?%s' % urlreq.urlencode(q)
        cu = "%s%s" % (self._url, qs)
        size = 0
        if util.safehasattr(data, 'length'):
            size = data.length
        elif data is not None:
            size = len(data)
        if size and self.ui.configbool('ui', 'usehttp2', False):
            headers['Expect'] = '100-Continue'
            headers['X-HgHttp2'] = '1'
        if data is not None and 'Content-Type' not in headers:
            headers['Content-Type'] = 'application/mercurial-0.1'

        headers['Vary'] = ','.join(varyheaders)
        req = self.requestbuilder(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 urlerr.httperror as inst:
            if inst.code == 401:
                raise error.Abort(_('authorization failed'))
            raise
        except httplib.HTTPException as inst:
            self.ui.debug('http error while sending %s command\n' % cmd)
            self.ui.traceback()
            raise IOError(None, inst)
        # 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')
                 and not resp.headers.get('content-length')) 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(1024)))

        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))

        if _compressible:
            return decompressresponse(resp, util.compengines['zlib'])

        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 bundle2.bundletypes:
                type = x
                break

        tempname = bundle2.writebundle(self.ui, cg, None, type)
        fp = httpconnection.httpsendfile(self.ui, tempname, "rb")
        headers = {'Content-Type': 'application/mercurial-0.1'}

        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 as err:
            if err.args[0] in (errno.ECONNRESET, errno.EPIPE):
                raise error.Abort(_('push failed: %s') % err.args[1])
            raise error.Abort(err.args[1])
        finally:
            fp.close()
            os.unlink(tempname)

    def _calltwowaystream(self, cmd, fp, **args):
        fh = None
        fp_ = None
        filename = None
        try:
            # dump bundle to disk
            fd, filename = tempfile.mkstemp(prefix="hg-bundle-", suffix=".hg")
            fh = os.fdopen(fd, "wb")
            d = fp.read(4096)
            while d:
                fh.write(d)
                d = fp.read(4096)
            fh.close()
            # start http push
            fp_ = httpconnection.httpsendfile(self.ui, filename, "rb")
            headers = {'Content-Type': 'application/mercurial-0.1'}
            return self._callstream(cmd, data=fp_, headers=headers, **args)
        finally:
            if fp_ is not None:
                fp_.close()
            if fh is not None:
                fh.close()
                os.unlink(filename)

    def _callcompressable(self, cmd, **args):
        return self._callstream(cmd, _compressible=True, **args)

    def _abort(self, exception):
        raise exception

class httpspeer(httppeer):
    def __init__(self, ui, path):
        if not url.has_https:
            raise error.Abort(_('Python support for SSL and HTTPS '
                               'is not installed'))
        httppeer.__init__(self, ui, path)

def instance(ui, path, create):
    if create:
        raise error.Abort(_('cannot create new http repository'))
    try:
        if path.startswith('https:'):
            inst = httpspeer(ui, path)
        else:
            inst = httppeer(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 as 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