# httppeer.py - HTTP repository proxy classes for mercurial

#

# Copyright 2005, 2006 Matt Mackall <mpm@selenic.com>

# Copyright 2006 Vadim Gelfer <vadim.gelfer@gmail.com>

#

# 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 io

import os

import socket

import struct

import weakref

from .i18n import _

from . import (

    bundle2,

    error,

    httpconnection,

    pycompat,

    repository,

    statichttprepo,

    url as urlmod,

    util,

    wireprotoframing,

    wireprototypes,

    wireprotov1peer,

    wireprotov2peer,

    wireprotov2server,

)

from .utils import (

    cborutil,

    interfaceutil,

    stringutil,

)

httplib = util.httplib

urlerr = util.urlerr

urlreq = util.urlreq

def encodevalueinheaders(value, header, limit):

    """Encode a string value into multiple HTTP headers.

    ``value`` will be encoded into 1 or more HTTP headers with the names

    ``header-<N>`` where ``<N>`` is an integer starting at 1. Each header

    name + value will be at most ``limit`` bytes long.

    Returns an iterable of 2-tuples consisting of header names and

    values as native strings.

    """

    # HTTP Headers are ASCII. Python 3 requires them to be unicodes,

    # not bytes. This function always takes bytes in as arguments.

    fmt = pycompat.strurl(header) + r'-%s'

    # Note: it is *NOT* a bug that the last bit here is a bytestring

    # and not a unicode: we're just getting the encoded length anyway,

    # and using an r-string to make it portable between Python 2 and 3

    # doesn't work because then the \r is a literal backslash-r

    # instead of a carriage return.

    valuelen = limit - len(fmt % r'000') - len(': \r\n')

    result = []

    n = 0

    for i in pycompat.xrange(0, len(value), valuelen):

        n += 1

        result.append((fmt % str(n), pycompat.strurl(value[i:i + valuelen])))

    return result

def _wraphttpresponse(resp):

    """Wrap an HTTPResponse with common error handlers.

    This ensures that any I/O from any consumer raises the appropriate

    error and messaging.

    """

    origread = resp.read

    class readerproxy(resp.__class__):

        def read(self, size=None):

            try:

                return origread(size)

            except httplib.IncompleteRead as e:

                # e.expected is an integer if length known or None otherwise.

                if e.expected:

                    got = len(e.partial)

                    total = e.expected + got

                    msg = _('HTTP request error (incomplete response; '

                            'expected %d bytes got %d)') % (total, got)

                else:

                    msg = _('HTTP request error (incomplete response)')

                raise error.PeerTransportError(

                    msg,

                    hint=_('this may be an intermittent network failure; '

                           'if the error persists, consider contacting the '

                           'network or server operator'))

            except httplib.HTTPException as e:

                raise error.PeerTransportError(

                    _('HTTP request error (%s)') % e,

                    hint=_('this may be an intermittent network failure; '

                           'if the error persists, consider contacting the '

                           'network or server operator'))

    resp.__class__ = readerproxy

class _multifile(object):

    def __init__(self, *fileobjs):

        for f in fileobjs:

            if not util.safehasattr(f, 'length'):

                raise ValueError(

                    '_multifile only supports file objects that '

                    'have a length but this one does not:', type(f), f)

        self._fileobjs = fileobjs

        self._index = 0

    @property

    def length(self):

        return sum(f.length for f in self._fileobjs)

    def read(self, amt=None):

        if amt <= 0:

            return ''.join(f.read() for f in self._fileobjs)

        parts = []

        while amt and self._index < len(self._fileobjs):

            parts.append(self._fileobjs[self._index].read(amt))

            got = len(parts[-1])

            if got < amt:

                self._index += 1

            amt -= got

        return ''.join(parts)

    def seek(self, offset, whence=os.SEEK_SET):

        if whence != os.SEEK_SET:

            raise NotImplementedError(

                '_multifile does not support anything other'

                ' than os.SEEK_SET for whence on seek()')

        if offset != 0:

            raise NotImplementedError(

                '_multifile only supports seeking to start, but that '

                'could be fixed if you need it')

        for f in self._fileobjs:

            f.seek(0)

        self._index = 0

def makev1commandrequest(ui, requestbuilder, caps, capablefn,

                         repobaseurl, cmd, args):

    """Make an HTTP request to run a command for a version 1 client.

    ``caps`` is a set of known server capabilities. The value may be

    None if capabilities are not yet known.

    ``capablefn`` is a function to evaluate a capability.

    ``cmd``, ``args``, and ``data`` define the command, its arguments, and

    raw data to pass to it.

    """

    if cmd == 'pushkey':

        args['data'] = ''

    data = args.pop('data', None)

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

    ui.debug("sending %s command\n" % cmd)

    q = [('cmd', cmd)]

    headersize = 0

    # 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 = caps is not None and 'httppostargs' in caps

    # Send arguments via POST.

    if postargsok and args:

        strargs = urlreq.urlencode(sorted(args.items()))

        if not data:

            data = strargs

        else:

            if isinstance(data, bytes):

                i = io.BytesIO(data)

                i.length = len(data)

                data = i

            argsio = io.BytesIO(strargs)

            argsio.length = len(strargs)

            data = _multifile(argsio, data)

        headers[r'X-HgArgs-Post'] = len(strargs)

    elif args:

        # Calling self.capable() can infinite loop if we are calling

        # "capabilities". But that command should never accept wire

        # protocol arguments. So this should never happen.

        assert cmd != 'capabilities'

        httpheader = capablefn('httpheader')

        if httpheader:

            headersize = int(httpheader.split(',', 1)[0])

        # Send arguments via HTTP headers.

        if headersize > 0:

            # The headers can typically carry more data than the URL.

            encargs = urlreq.urlencode(sorted(args.items()))

            for header, value in encodevalueinheaders(encargs, 'X-HgArg',

                                                      headersize):

                headers[header] = value

        # Send arguments via query string (Mercurial <1.9).

        else:

            q += sorted(args.items())

    qs = '?%s' % urlreq.urlencode(q)

    cu = "%s%s" % (repobaseurl, qs)

    size = 0

    if util.safehasattr(data, 'length'):

        size = data.length

    elif data is not None:

        size = len(data)

    if data is not None and r'Content-Type' not in headers:

        headers[r'Content-Type'] = r'application/mercurial-0.1'

    # Tell the server we accept application/mercurial-0.2 and multiple

    # compression formats if the server is capable of emitting those

    # payloads.

    # Note: Keep this set empty by default, as client advertisement of

    # protocol parameters should only occur after the handshake.

    protoparams = set()

    mediatypes = set()

    if caps is not None:

        mt = capablefn('httpmediatype')

        if mt:

            protoparams.add('0.1')

            mediatypes = set(mt.split(','))

        protoparams.add('partial-pull')

    if '0.2tx' in mediatypes:

        protoparams.add('0.2')

    if '0.2tx' in mediatypes and capablefn('compression'):

        # We /could/ compare supported compression formats and prune

        # non-mutually supported or error if nothing is mutually supported.

        # For now, send the full list to the server and have it error.

        comps = [e.wireprotosupport().name for e in

                 util.compengines.supportedwireengines(util.CLIENTROLE)]

        protoparams.add('comp=%s' % ','.join(comps))

    if protoparams:

        protoheaders = encodevalueinheaders(' '.join(sorted(protoparams)),

                                            'X-HgProto',

                                            headersize or 1024)

        for header, value in protoheaders:

            headers[header] = value

    varyheaders = []

    for header in headers:

        if header.lower().startswith(r'x-hg'):

            varyheaders.append(header)

    if varyheaders:

        headers[r'Vary'] = r','.join(sorted(varyheaders))

    req = requestbuilder(pycompat.strurl(cu), data, headers)

    if data is not None:

        ui.debug("sending %d bytes\n" % size)

        req.add_unredirected_header(r'Content-Length', r'%d' % size)

    return req, cu, qs

def _reqdata(req):

    """Get request data, if any. If no data, returns None."""

    if pycompat.ispy3:

        return req.data

    if not req.has_data():

        return None

    return req.get_data()

def sendrequest(ui, opener, req):

    """Send a prepared HTTP request.

    Returns the response object.

    """

    dbg = ui.debug

    if (ui.debugflag

        and ui.configbool('devel', 'debug.peer-request')):

        line = 'devel-peer-request: %s\n'

        dbg(line % '%s %s' % (pycompat.bytesurl(req.get_method()),

                              pycompat.bytesurl(req.get_full_url())))

        hgargssize = None

        for header, value in sorted(req.header_items()):

            header = pycompat.bytesurl(header)

            value = pycompat.bytesurl(value)

            if header.startswith('X-hgarg-'):

                if hgargssize is None:

                    hgargssize = 0

                hgargssize += len(value)

            else:

                dbg(line % '  %s %s' % (header, value))

        if hgargssize is not None:

            dbg(line % '  %d bytes of commands arguments in headers'

                % hgargssize)

        data = _reqdata(req)

        if data is not None:

            length = getattr(data, 'length', None)

            if length is None:

                length = len(data)

            dbg(line % '  %d bytes of data' % length)

        start = util.timer()

    res = None

    try:

        res = opener.open(req)

    except urlerr.httperror as inst:

        if inst.code == 401:

            raise error.Abort(_('authorization failed'))

        raise

    except httplib.HTTPException as inst:

        ui.debug('http error requesting %s\n' %

                 util.hidepassword(req.get_full_url()))

        ui.traceback()

        raise IOError(None, inst)

    finally:

        if ui.debugflag and ui.configbool('devel', 'debug.peer-request'):

            code = res.code if res else -1

            dbg(line % '  finished in %.4f seconds (%d)'

                % (util.timer() - start, code))

    # Insert error handlers for common I/O failures.

    _wraphttpresponse(res)

    return res

class RedirectedRepoError(error.RepoError):

    def __init__(self, msg, respurl):

        super(RedirectedRepoError, self).__init__(msg)

        self.respurl = respurl

def parsev1commandresponse(ui, baseurl, requrl, qs, resp, compressible,

                           allowcbor=False):

    # record the url we got redirected to

    redirected = False

    respurl = pycompat.bytesurl(resp.geturl())

    if respurl.endswith(qs):

        respurl = respurl[:-len(qs)]

        qsdropped = False

    else:

        qsdropped = True

    if baseurl.rstrip('/') != respurl.rstrip('/'):

        redirected = True

        if not ui.quiet:

            ui.warn(_('real URL is %s\n') % respurl)

    try:

        proto = pycompat.bytesurl(resp.getheader(r'content-type', r''))

    except AttributeError:

        proto = pycompat.bytesurl(resp.headers.get(r'content-type', r''))

    safeurl = util.hidepassword(baseurl)

    if proto.startswith('application/hg-error'):

        raise error.OutOfBandError(resp.read())

    # Pre 1.0 versions of Mercurial used text/plain and

    # application/hg-changegroup. We don't support such old servers.

    if not proto.startswith('application/mercurial-'):

        ui.debug("requested URL: '%s'\n" % util.hidepassword(requrl))

        msg = _("'%s' does not appear to be an hg repository:\n"

                "---%%<--- (%s)\n%s\n---%%<---\n") % (

            safeurl, proto or 'no content-type', resp.read(1024))

        # Some servers may strip the query string from the redirect. We

        # raise a special error type so callers can react to this specially.

        if redirected and qsdropped:

            raise RedirectedRepoError(msg, respurl)

        else:

            raise error.RepoError(msg)

    try:

        subtype = proto.split('-', 1)[1]

        # Unless we end up supporting CBOR in the legacy wire protocol,