# fileserverclient.py - client for communicating with the cache process

#

# Copyright 2013 Facebook, Inc.

#

# 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 hashlib

import io

import os

import threading

import time

from mercurial.i18n import _

from mercurial.node import bin, hex, nullid

from mercurial import (

    error,

    revlog,

    sshpeer,

    util,

    wireprotov1peer,

)

from mercurial.utils import procutil

from . import (

    constants,

    contentstore,

    lz4wrapper,

    metadatastore,

)

_sshv1peer = sshpeer.sshv1peer

# Statistics for debugging

fetchcost = 0

fetches = 0

fetched = 0

fetchmisses = 0

_lfsmod = None

_downloading = _('downloading')

def getcachekey(reponame, file, id):

    pathhash = hashlib.sha1(file).hexdigest()

    return os.path.join(reponame, pathhash[:2], pathhash[2:], id)

def getlocalkey(file, id):

    pathhash = hashlib.sha1(file).hexdigest()

    return os.path.join(pathhash, id)

def peersetup(ui, peer):

    class remotefilepeer(peer.__class__):

        @wireprotov1peer.batchable

        def getfile(self, file, node):

            if not self.capable('getfile'):

                raise error.Abort(

                    'configured remotefile server does not support getfile')

            f = wireprotov1peer.future()

            yield {'file': file, 'node': node}, f

            code, data = f.value.split('\0', 1)

            if int(code):

                raise error.LookupError(file, node, data)

            yield data

        @wireprotov1peer.batchable

        def getflogheads(self, path):

            if not self.capable('getflogheads'):

                raise error.Abort('configured remotefile server does not '

                                  'support getflogheads')

            f = wireprotov1peer.future()

            yield {'path': path}, f

            heads = f.value.split('\n') if f.value else []

            yield heads

        def _updatecallstreamopts(self, command, opts):

            if command != 'getbundle':

                return

            if 'remotefilelog' not in self.capabilities():

                return

            if not util.safehasattr(self, '_localrepo'):

                return

            if constants.REQUIREMENT not in self._localrepo.requirements:

                return

            bundlecaps = opts.get('bundlecaps')

            if bundlecaps:

                bundlecaps = [bundlecaps]

            else:

                bundlecaps = []

            # shallow, includepattern, and excludepattern are a hacky way of

            # carrying over data from the local repo to this getbundle

            # command. We need to do it this way because bundle1 getbundle

            # doesn't provide any other place we can hook in to manipulate

            # getbundle args before it goes across the wire. Once we get rid

            # of bundle1, we can use bundle2's _pullbundle2extraprepare to

            # do this more cleanly.

            bundlecaps.append('remotefilelog')

            if self._localrepo.includepattern:

                patterns = '\0'.join(self._localrepo.includepattern)

                includecap = "includepattern=" + patterns

                bundlecaps.append(includecap)

            if self._localrepo.excludepattern:

                patterns = '\0'.join(self._localrepo.excludepattern)

                excludecap = "excludepattern=" + patterns

                bundlecaps.append(excludecap)

            opts['bundlecaps'] = ','.join(bundlecaps)

        def _sendrequest(self, command, args, **opts):

            self._updatecallstreamopts(command, args)

            return super(remotefilepeer, self)._sendrequest(command, args,

                                                            **opts)

        def _callstream(self, command, **opts):

            supertype = super(remotefilepeer, self)

            if not util.safehasattr(supertype, '_sendrequest'):

                self._updatecallstreamopts(command, opts)

            return super(remotefilepeer, self)._callstream(command, **opts)

    peer.__class__ = remotefilepeer

class cacheconnection(object):

    """The connection for communicating with the remote cache. Performs

    gets and sets by communicating with an external process that has the

    cache-specific implementation.

    """

    def __init__(self):

        self.pipeo = self.pipei = self.pipee = None

        self.subprocess = None

        self.connected = False

    def connect(self, cachecommand):

        if self.pipeo:

            raise error.Abort(_("cache connection already open"))

        self.pipei, self.pipeo, self.pipee, self.subprocess = \

            procutil.popen4(cachecommand)

        self.connected = True

    def close(self):

        def tryclose(pipe):

            try:

                pipe.close()

            except Exception:

                pass

        if self.connected:

            try:

                self.pipei.write("exit\n")

            except Exception:

                pass

            tryclose(self.pipei)

            self.pipei = None

            tryclose(self.pipeo)

            self.pipeo = None

            tryclose(self.pipee)

            self.pipee = None

            try:

                # Wait for process to terminate, making sure to avoid deadlock.

                # See https://docs.python.org/2/library/subprocess.html for

                # warnings about wait() and deadlocking.

                self.subprocess.communicate()

            except Exception:

                pass

            self.subprocess = None

        self.connected = False

    def request(self, request, flush=True):

        if self.connected:

            try:

                self.pipei.write(request)

                if flush:

                    self.pipei.flush()

            except IOError:

                self.close()

    def receiveline(self):

        if not self.connected:

            return None

        try:

            result = self.pipeo.readline()[:-1]

            if not result:

                self.close()

        except IOError:

            self.close()

        return result

def _getfilesbatch(

        remote, receivemissing, progresstick, missed, idmap, batchsize):

    # Over http(s), iterbatch is a streamy method and we can start

    # looking at results early. This means we send one (potentially

    # large) request, but then we show nice progress as we process

    # file results, rather than showing chunks of $batchsize in

    # progress.

    #

    # Over ssh, iterbatch isn't streamy because batch() wasn't

    # explicitly designed as a streaming method. In the future we

    # should probably introduce a streambatch() method upstream and

    # use that for this.

    with remote.commandexecutor() as e:

        futures = []

        for m in missed:

            futures.append(e.callcommand('getfile', {

                'file': idmap[m],

                'node': m[-40:]

            }))

        for i, m in enumerate(missed):

            r = futures[i].result()

            futures[i] = None  # release memory

            file_ = idmap[m]

            node = m[-40:]

            receivemissing(io.BytesIO('%d\n%s' % (len(r), r)), file_, node)

            progresstick()

def _getfiles_optimistic(

    remote, receivemissing, progresstick, missed, idmap, step):

    remote._callstream("getfiles")

    i = 0

    pipeo = remote._pipeo

    pipei = remote._pipei

    while i < len(missed):

        # issue a batch of requests

        start = i

        end = min(len(missed), start + step)

        i = end

        for missingid in missed[start:end]:

            # issue new request

            versionid = missingid[-40:]

            file = idmap[missingid]

            sshrequest = "%s%s\n" % (versionid, file)

            pipeo.write(sshrequest)

        pipeo.flush()

        # receive batch results

        for missingid in missed[start:end]:

            versionid = missingid[-40:]

            file = idmap[missingid]

            receivemissing(pipei, file, versionid)

            progresstick()

    # End the command

    pipeo.write('\n')

    pipeo.flush()

def _getfiles_threaded(

    remote, receivemissing, progresstick, missed, idmap, step):

    remote._callstream("getfiles")

    pipeo = remote._pipeo

    pipei = remote._pipei

    def writer():

        for missingid in missed:

            versionid = missingid[-40:]

            file = idmap[missingid]

            sshrequest = "%s%s\n" % (versionid, file)

            pipeo.write(sshrequest)

        pipeo.flush()

    writerthread = threading.Thread(target=writer)

    writerthread.daemon = True

    writerthread.start()

    for missingid in missed:

        versionid = missingid[-40:]

        file = idmap[missingid]

        receivemissing(pipei, file, versionid)

        progresstick()

    writerthread.join()

    # End the command

    pipeo.write('\n')

    pipeo.flush()

class fileserverclient(object):

    """A client for requesting files from the remote file server.

    """

    def __init__(self, repo):

        ui = repo.ui

        self.repo = repo

        self.ui = ui

        self.cacheprocess = ui.config("remotefilelog", "cacheprocess")

        if self.cacheprocess:

            self.cacheprocess = util.expandpath(self.cacheprocess)

        # This option causes remotefilelog to pass the full file path to the

        # cacheprocess instead of a hashed key.

        self.cacheprocesspasspath = ui.configbool(

            "remotefilelog", "cacheprocess.includepath")

        self.debugoutput = ui.configbool("remotefilelog", "debug")

        self.remotecache = cacheconnection()

    def setstore(self, datastore, historystore, writedata, writehistory):

        self.datastore = datastore

        self.historystore = historystore

        self.writedata = writedata

        self.writehistory = writehistory

    def _connect(self):

        return self.repo.connectionpool.get(self.repo.fallbackpath)

    def request(self, fileids):

        """Takes a list of filename/node pairs and fetches them from the

        server. Files are stored in the local cache.

        A list of nodes that the server couldn't find is returned.

        If the connection fails, an exception is raised.

        """

        if not self.remotecache.connected:

            self.connect()

        cache = self.remotecache

        writedata = self.writedata

        repo = self.repo

        count = len(fileids)

        request = "get\n%d\n" % count

        idmap = {}

        reponame = repo.name

        for file, id in fileids:

            fullid = getcachekey(reponame, file, id)

            if self.cacheprocesspasspath:

                request += file + '\0'

            request += fullid + "\n"

            idmap[fullid] = file

        cache.request(request)

        total = count

        self.ui.progress(_downloading, 0, total=count)

        missed = []

        count = 0

        while True:

            missingid = cache.receiveline()

            if not missingid:

                missedset = set(missed)

                for missingid in idmap.iterkeys():

                    if not missingid in missedset:

                        missed.append(missingid)

                self.ui.warn(_("warning: cache connection closed early - " +

                    "falling back to server\n"))

                break

            if missingid == "0":

                break

            if missingid.startswith("_hits_"):

                # receive progress reports

                parts = missingid.split("_")

                count += int(parts[2])

                self.ui.progress(_downloading, count, total=total)

                continue

            missed.append(missingid)

        global fetchmisses

        fetchmisses += len(missed)

        count = [total - len(missed)]

        fromcache = count[0]

        self.ui.progress(_downloading, count[0], total=total)

        self.ui.log("remotefilelog", "remote cache hit rate is %r of %r\n",

                    count[0], total, hit=count[0], total=total)

        oldumask = os.umask(0o002)

        try:

            # receive cache misses from master

            if missed:

                def progresstick():

                    count[0] += 1

                    self.ui.progress(_downloading, count[0], total=total)

                # When verbose is true, sshpeer prints 'running ssh...'

                # to stdout, which can interfere with some command

                # outputs

                verbose = self.ui.verbose

                self.ui.verbose = False

                try:

                    with self._connect() as conn:

                        remote = conn.peer

                        # TODO: deduplicate this with the constant in

                        #       shallowrepo

                        if remote.capable("remotefilelog"):

                            if not isinstance(remote, _sshv1peer):

                                raise error.Abort('remotefilelog requires ssh '

                                                  'servers')

                            step = self.ui.configint('remotefilelog',

                                                     'getfilesstep')

                            getfilestype = self.ui.config('remotefilelog',

                                                          'getfilestype')

                            if getfilestype == 'threaded':

                                _getfiles = _getfiles_threaded

                            else:

                                _getfiles = _getfiles_optimistic

                            _getfiles(remote, self.receivemissing, progresstick,

                                      missed, idmap, step)

                        elif remote.capable("getfile"):

                            if remote.capable('batch'):

                                batchdefault = 100

                            else:

                                batchdefault = 10

                            batchsize = self.ui.configint(

                                'remotefilelog', 'batchsize', batchdefault)

                            _getfilesbatch(