# chgserver.py - command server extension for cHg

#

# Copyright 2011 Yuya Nishihara <yuya@tcha.org>

#

# This software may be used and distributed according to the terms of the

# GNU General Public License version 2 or any later version.

"""command server extension for cHg

'S' channel (read/write)

    propagate ui.system() request to client

'attachio' command

    attach client's stdio passed by sendmsg()

'chdir' command

    change current directory

'setenv' command

    replace os.environ completely

'setumask' command

    set umask

'validate' command

    reload the config and check if the server is up to date

Config

------

::

  [chgserver]

  # how long (in seconds) should an idle chg server exit

  idletimeout = 3600

  # whether to skip config or env change checks

  skiphash = False

"""

from __future__ import absolute_import

import hashlib

import inspect

import os

import re

import socket

import struct

import time

from .i18n import _

from . import (

    commandserver,

    encoding,

    error,

    extensions,

    pycompat,

    util,

)

_log = commandserver.log

def _hashlist(items):

    """return sha1 hexdigest for a list"""

    return hashlib.sha1(str(items)).hexdigest()

# sensitive config sections affecting confighash

_configsections = [

    'alias',  # affects global state commands.table

    'eol',    # uses setconfig('eol', ...)

    'extdiff',  # uisetup will register new commands

    'extensions',

]

_configsectionitems = [

    ('commands', 'show.aliasprefix'), # show.py reads it in extsetup

]

# sensitive environment variables affecting confighash

_envre = re.compile(r'''\A(?:

                    CHGHG

                    |HG(?:DEMANDIMPORT|EMITWARNINGS|MODULEPOLICY|PROF|RCPATH)?

                    |HG(?:ENCODING|PLAIN).*

                    |LANG(?:UAGE)?

                    |LC_.*

                    |LD_.*

                    |PATH

                    |PYTHON.*

                    |TERM(?:INFO)?

                    |TZ

                    )\Z''', re.X)

def _confighash(ui):

    """return a quick hash for detecting config/env changes

    confighash is the hash of sensitive config items and environment variables.

    for chgserver, it is designed that once confighash changes, the server is

    not qualified to serve its client and should redirect the client to a new

    server. different from mtimehash, confighash change will not mark the

    server outdated and exit since the user can have different configs at the

    same time.

    """

    sectionitems = []

    for section in _configsections:

        sectionitems.append(ui.configitems(section))

    for section, item in _configsectionitems:

        sectionitems.append(ui.config(section, item))

    sectionhash = _hashlist(sectionitems)

    envitems = [(k, v) for k, v in encoding.environ.iteritems()

                if _envre.match(k)]

    envhash = _hashlist(sorted(envitems))

    return sectionhash[:6] + envhash[:6]

def _getmtimepaths(ui):

    """get a list of paths that should be checked to detect change

    The list will include:

    - extensions (will not cover all files for complex extensions)

    - mercurial/__version__.py

    - python binary

    """

    modules = [m for n, m in extensions.extensions(ui)]

    try:

        from . import __version__

        modules.append(__version__)

    except ImportError:

        pass

    files = [pycompat.sysexecutable]

    for m in modules:

        try:

            files.append(inspect.getabsfile(m))

        except TypeError:

            pass

    return sorted(set(files))

def _mtimehash(paths):

    """return a quick hash for detecting file changes

    mtimehash calls stat on given paths and calculate a hash based on size and

    mtime of each file. mtimehash does not read file content because reading is

    expensive. therefore it's not 100% reliable for detecting content changes.

    it's possible to return different hashes for same file contents.

    it's also possible to return a same hash for different file contents for

    some carefully crafted situation.

    for chgserver, it is designed that once mtimehash changes, the server is

    considered outdated immediately and should no longer provide service.

    mtimehash is not included in confighash because we only know the paths of

    extensions after importing them (there is imp.find_module but that faces

    race conditions). We need to calculate confighash without importing.

    """

    def trystat(path):

        try:

            st = os.stat(path)

            return (st.st_mtime, st.st_size)

        except OSError:

            # could be ENOENT, EPERM etc. not fatal in any case

            pass

    return _hashlist(map(trystat, paths))[:12]

class hashstate(object):

    """a structure storing confighash, mtimehash, paths used for mtimehash"""

    def __init__(self, confighash, mtimehash, mtimepaths):

        self.confighash = confighash

        self.mtimehash = mtimehash

        self.mtimepaths = mtimepaths

    @staticmethod

    def fromui(ui, mtimepaths=None):

        if mtimepaths is None:

            mtimepaths = _getmtimepaths(ui)

        confighash = _confighash(ui)

        mtimehash = _mtimehash(mtimepaths)

        _log('confighash = %s mtimehash = %s\n' % (confighash, mtimehash))

        return hashstate(confighash, mtimehash, mtimepaths)

def _newchgui(srcui, csystem, attachio):

    class chgui(srcui.__class__):

        def __init__(self, src=None):

            super(chgui, self).__init__(src)

            if src:

                self._csystem = getattr(src, '_csystem', csystem)

            else:

                self._csystem = csystem

        def _runsystem(self, cmd, environ, cwd, out):

            # fallback to the original system method if the output needs to be

            # captured (to self._buffers), or the output stream is not stdout

            # (e.g. stderr, cStringIO), because the chg client is not aware of

            # these situations and will behave differently (write to stdout).

            if (out is not self.fout

                or not util.safehasattr(self.fout, 'fileno')

                or self.fout.fileno() != util.stdout.fileno()):

                return util.system(cmd, environ=environ, cwd=cwd, out=out)

            self.flush()

            return self._csystem(cmd, util.shellenviron(environ), cwd)

        def _runpager(self, cmd, env=None):

            self._csystem(cmd, util.shellenviron(env), type='pager',

                          cmdtable={'attachio': attachio})

            return True

    return chgui(srcui)

def _loadnewui(srcui, args):

    from . import dispatch  # avoid cycle

    newui = srcui.__class__.load()

    for a in ['fin', 'fout', 'ferr', 'environ']:

        setattr(newui, a, getattr(srcui, a))

    if util.safehasattr(srcui, '_csystem'):

        newui._csystem = srcui._csystem

    # command line args

    args = args[:]

    dispatch._parseconfig(newui, dispatch._earlygetopt(['--config'], args))

    # stolen from tortoisehg.util.copydynamicconfig()

    for section, name, value in srcui.walkconfig():

        source = srcui.configsource(section, name)

        if ':' in source or source == '--config' or source.startswith('$'):

            # path:line or command line, or environ

            continue

        newui.setconfig(section, name, value, source)

    # load wd and repo config, copied from dispatch.py

    cwds = dispatch._earlygetopt(['--cwd'], args)

    cwd = cwds and os.path.realpath(cwds[-1]) or None

    rpath = dispatch._earlygetopt(["-R", "--repository", "--repo"], args)

    path, newlui = dispatch._getlocal(newui, rpath, wd=cwd)

    return (newui, newlui)

class channeledsystem(object):

    """Propagate ui.system() request in the following format:

    payload length (unsigned int),

    type, '\0',

    cmd, '\0',

    cwd, '\0',

    envkey, '=', val, '\0',

    ...

    envkey, '=', val

    if type == 'system', waits for:

    exitcode length (unsigned int),

    exitcode (int)

    if type == 'pager', repetitively waits for a command name ending with '\n'

    and executes it defined by cmdtable, or exits the loop if the command name

    is empty.

    """

    def __init__(self, in_, out, channel):

        self.in_ = in_

        self.out = out

        self.channel = channel

    def __call__(self, cmd, environ, cwd=None, type='system', cmdtable=None):

        args = [type, util.quotecommand(cmd), os.path.abspath(cwd or '.')]

        args.extend('%s=%s' % (k, v) for k, v in environ.iteritems())

        data = '\0'.join(args)

        self.out.write(struct.pack('>cI', self.channel, len(data)))

        self.out.write(data)

        self.out.flush()

        if type == 'system':

            length = self.in_.read(4)

            length, = struct.unpack('>I', length)

            if length != 4:

                raise error.Abort(_('invalid response'))

            rc, = struct.unpack('>i', self.in_.read(4))

            return rc

        elif type == 'pager':

            while True:

                cmd = self.in_.readline()[:-1]

                if not cmd:

                    break

                if cmdtable and cmd in cmdtable:

                    _log('pager subcommand: %s' % cmd)

                    cmdtable[cmd]()

                else:

                    raise error.Abort(_('unexpected command: %s') % cmd)

        else:

            raise error.ProgrammingError('invalid S channel type: %s' % type)

_iochannels = [

    # server.ch, ui.fp, mode

    ('cin', 'fin', pycompat.sysstr('rb')),

    ('cout', 'fout', pycompat.sysstr('wb')),

    ('cerr', 'ferr', pycompat.sysstr('wb')),

]

class chgcmdserver(commandserver.server):

    def __init__(self, ui, repo, fin, fout, sock, hashstate, baseaddress):

        super(chgcmdserver, self).__init__(

            _newchgui(ui, channeledsystem(fin, fout, 'S'), self.attachio),

            repo, fin, fout)

        self.clientsock = sock

        self._oldios = []  # original (self.ch, ui.fp, fd) before "attachio"

        self.hashstate = hashstate

        self.baseaddress = baseaddress

        if hashstate is not None:

            self.capabilities = self.capabilities.copy()

            self.capabilities['validate'] = chgcmdserver.validate

    def cleanup(self):

        super(chgcmdserver, self).cleanup()

        # dispatch._runcatch() does not flush outputs if exception is not

        # handled by dispatch._dispatch()

        self.ui.flush()

        self._restoreio()

    def attachio(self):

        """Attach to client's stdio passed via unix domain socket; all

        channels except cresult will no longer be used

        """

        # tell client to sendmsg() with 1-byte payload, which makes it

        # distinctive from "attachio\n" command consumed by client.read()

        self.clientsock.sendall(struct.pack('>cI', 'I', 1))

        clientfds = util.recvfds(self.clientsock.fileno())

        _log('received fds: %r\n' % clientfds)

        ui = self.ui

        ui.flush()

        first = self._saveio()

        for fd, (cn, fn, mode) in zip(clientfds, _iochannels):

            assert fd > 0

            fp = getattr(ui, fn)

            os.dup2(fd, fp.fileno())

            os.close(fd)

            if not first:

                continue

            # reset buffering mode when client is first attached. as we want

            # to see output immediately on pager, the mode stays unchanged

            # when client re-attached. ferr is unchanged because it should

            # be unbuffered no matter if it is a tty or not.

            if fn == 'ferr':

                newfp = fp

            else:

                # make it line buffered explicitly because the default is

                # decided on first write(), where fout could be a pager.

                if fp.isatty():

                    bufsize = 1  # line buffered

                else:

                    bufsize = -1  # system default

                newfp = os.fdopen(fp.fileno(), mode, bufsize)

                setattr(ui, fn, newfp)

            setattr(self, cn, newfp)

        self.cresult.write(struct.pack('>i', len(clientfds)))

    def _saveio(self):

        if self._oldios:

            return False

        ui = self.ui

        for cn, fn, _mode in _iochannels:

            ch = getattr(self, cn)

            fp = getattr(ui, fn)

            fd = os.dup(fp.fileno())

            self._oldios.append((ch, fp, fd))

        return True

    def _restoreio(self):

        ui = self.ui

        for (ch, fp, fd), (cn, fn, _mode) in zip(self._oldios, _iochannels):

            newfp = getattr(ui, fn)

            # close newfp while it's associated with client; otherwise it

            # would be closed when newfp is deleted

            if newfp is not fp:

                newfp.close()

            # restore original fd: fp is open again

            os.dup2(fd, fp.fileno())

            os.close(fd)

            setattr(self, cn, ch)

            setattr(ui, fn, fp)

        del self._oldios[:]

    def validate(self):

        """Reload the config and check if the server is up to date

        Read a list of '\0' separated arguments.

        Write a non-empty list of '\0' separated instruction strings or '\0'

        if the list is empty.

        An instruction string could be either:

            - "unlink $path", the client should unlink the path to stop the

              outdated server.

            - "redirect $path", the client should attempt to connect to $path

              first. If it does not work, start a new server. It implies

              "reconnect".

            - "exit $n", the client should exit directly with code n.

              This may happen if we cannot parse the config.