annotate mercurial/sshpeer.py @ 33499:0407a51b9d8c

codemod: register core configitems using a script

This is done by a script [2] using RedBaron [1], a tool designed for doing
code refactoring. All "default" values are decided by the script and are
strongly consistent with the existing code.

There are 2 changes done manually to fix tests:

  [warn] mercurial/exchange.py: experimental.bundle2-output-capture: default needs manual removal
  [warn] mercurial/localrepo.py: experimental.hook-track-tags: default needs manual removal

Since RedBaron is not confident about how to indent things [2].

[1]: https://github.com/PyCQA/redbaron
[2]: https://github.com/PyCQA/redbaron/issues/100
[3]:

#!/usr/bin/env python
# codemod_configitems.py - codemod tool to fill configitems
#
# Copyright 2017 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, print_function

import os
import sys

import redbaron

def readpath(path):
    with open(path) as f:
        return f.read()

def writepath(path, content):
    with open(path, 'w') as f:
        f.write(content)

_configmethods = {'config', 'configbool', 'configint', 'configbytes',
                  'configlist', 'configdate'}

def extractstring(rnode):
    """get the string from a RedBaron string or call_argument node"""
    while rnode.type != 'string':
        rnode = rnode.value
    return rnode.value[1:-1]  # unquote, "'str'" -> "str"

def uiconfigitems(red):
    """match *.ui.config* pattern, yield (node, method, args, section, name)"""
    for node in red.find_all('atomtrailers'):
        entry = None
        try:
            obj = node[-3].value
            method = node[-2].value
            args = node[-1]
            section = args[0].value
            name = args[1].value
            if (obj in ('ui', 'self') and method in _configmethods
                and section.type == 'string' and name.type == 'string'):
                entry = (node, method, args, extractstring(section),
                         extractstring(name))
        except Exception:
            pass
        else:
            if entry:
                yield entry

def coreconfigitems(red):
    """match coreconfigitem(...) pattern, yield (node, args, section, name)"""
    for node in red.find_all('atomtrailers'):
        entry = None
        try:
            args = node[1]
            section = args[0].value
            name = args[1].value
            if (node[0].value == 'coreconfigitem' and section.type == 'string'
                and name.type == 'string'):
                entry = (node, args, extractstring(section),
                         extractstring(name))
        except Exception:
            pass
        else:
            if entry:
                yield entry

def registercoreconfig(cfgred, section, name, defaultrepr):
    """insert coreconfigitem to cfgred AST

    section and name are plain string, defaultrepr is a string
    """
    # find a place to insert the "coreconfigitem" item
    entries = list(coreconfigitems(cfgred))
    for node, args, nodesection, nodename in reversed(entries):
        if (nodesection, nodename) < (section, name):
            # insert after this entry
            node.insert_after(
                'coreconfigitem(%r, %r,\n'
                '    default=%s,\n'
                ')' % (section, name, defaultrepr))
            return

def main(argv):
    if not argv:
        print('Usage: codemod_configitems.py FILES\n'
              'For example, FILES could be "{hgext,mercurial}/*/**.py"')
    dirname = os.path.dirname
    reporoot = dirname(dirname(dirname(os.path.abspath(__file__))))

    # register configitems to this destination
    cfgpath = os.path.join(reporoot, 'mercurial', 'configitems.py')
    cfgred = redbaron.RedBaron(readpath(cfgpath))

    # state about what to do
    registered = set((s, n) for n, a, s, n in coreconfigitems(cfgred))
    toregister = {} # {(section, name): defaultrepr}
    coreconfigs = set() # {(section, name)}, whether it's used in core

    # first loop: scan all files before taking any action
    for i, path in enumerate(argv):
        print('(%d/%d) scanning %s' % (i + 1, len(argv), path))
        iscore = ('mercurial' in path) and ('hgext' not in path)
        red = redbaron.RedBaron(readpath(path))
        # find all repo.ui.config* and ui.config* calls, and collect their
        # section, name and default value information.
        for node, method, args, section, name in uiconfigitems(red):
            if section == 'web':
                # [web] section has some weirdness, ignore them for now
                continue
            defaultrepr = None
            key = (section, name)
            if len(args) == 2:
                if key in registered:
                    continue
                if method == 'configlist':
                    defaultrepr = 'list'
                elif method == 'configbool':
                    defaultrepr = 'False'
                else:
                    defaultrepr = 'None'
            elif len(args) >= 3 and (args[2].target is None or
                                     args[2].target.value == 'default'):
                # try to understand the "default" value
                dnode = args[2].value
                if dnode.type == 'name':
                    if dnode.value in {'None', 'True', 'False'}:
                        defaultrepr = dnode.value
                elif dnode.type == 'string':
                    defaultrepr = repr(dnode.value[1:-1])
                elif dnode.type in ('int', 'float'):
                    defaultrepr = dnode.value
            # inconsistent default
            if key in toregister and toregister[key] != defaultrepr:
                defaultrepr = None
            # interesting to rewrite
            if key not in registered:
                if defaultrepr is None:
                    print('[note] %s: %s.%s: unsupported default'
                          % (path, section, name))
                    registered.add(key) # skip checking it again
                else:
                    toregister[key] = defaultrepr
                    if iscore:
                        coreconfigs.add(key)

    # second loop: rewrite files given "toregister" result
    for path in argv:
        # reconstruct redbaron - trade CPU for memory
        red = redbaron.RedBaron(readpath(path))
        changed = False
        for node, method, args, section, name in uiconfigitems(red):
            key = (section, name)
            defaultrepr = toregister.get(key)
            if defaultrepr is None or key not in coreconfigs:
                continue
            if len(args) >= 3 and (args[2].target is None or
                                   args[2].target.value == 'default'):
                try:
                    del args[2]
                    changed = True
                except Exception:
                    # redbaron fails to do the rewrite due to indentation
                    # see https://github.com/PyCQA/redbaron/issues/100
                    print('[warn] %s: %s.%s: default needs manual removal'
                          % (path, section, name))
            if key not in registered:
                print('registering %s.%s' % (section, name))
                registercoreconfig(cfgred, section, name, defaultrepr)
                registered.add(key)
        if changed:
            print('updating %s' % path)
            writepath(path, red.dumps())

    if toregister:
        print('updating configitems.py')
        writepath(cfgpath, cfgred.dumps())

if __name__ == "__main__":
    sys.exit(main(sys.argv[1:]))

# sshpeer.py - ssh repository proxy class for mercurial
#
# Copyright 2005, 2006 Matt Mackall <[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 re

from .i18n import _
from . import (
    error,
    pycompat,
    util,
    wireproto,
)

class remotelock(object):
    def __init__(self, repo):
        self.repo = repo
    def release(self):
        self.repo.unlock()
        self.repo = None
    def __enter__(self):
        return self
    def __exit__(self, exc_type, exc_val, exc_tb):
        if self.repo:
            self.release()
    def __del__(self):
        if self.repo:
            self.release()

def _serverquote(s):
    if not s:
        return s
    '''quote a string for the remote shell ... which we assume is sh'''
    if re.match('[a-zA-Z0-9@%_+=:,./-]*$', s):
        return s
    return "'%s'" % s.replace("'", "'\\''")

def _forwardoutput(ui, pipe):
    """display all data currently available on pipe as remote output.

    This is non blocking."""
    s = util.readpipe(pipe)
    if s:
        for l in s.splitlines():
            ui.status(_("remote: "), l, '\n')

class doublepipe(object):
    """Operate a side-channel pipe in addition of a main one

    The side-channel pipe contains server output to be forwarded to the user
    input. The double pipe will behave as the "main" pipe, but will ensure the
    content of the "side" pipe is properly processed while we wait for blocking
    call on the "main" pipe.

    If large amounts of data are read from "main", the forward will cease after
    the first bytes start to appear. This simplifies the implementation
    without affecting actual output of sshpeer too much as we rarely issue
    large read for data not yet emitted by the server.

    The main pipe is expected to be a 'bufferedinputpipe' from the util module
    that handle all the os specific bits. This class lives in this module
    because it focus on behavior specific to the ssh protocol."""

    def __init__(self, ui, main, side):
        self._ui = ui
        self._main = main
        self._side = side

    def _wait(self):
        """wait until some data are available on main or side

        return a pair of boolean (ismainready, issideready)

        (This will only wait for data if the setup is supported by `util.poll`)
        """
        if getattr(self._main, 'hasbuffer', False): # getattr for classic pipe
            return (True, True) # main has data, assume side is worth poking at.
        fds = [self._main.fileno(), self._side.fileno()]
        try:
            act = util.poll(fds)
        except NotImplementedError:
            # non supported yet case, assume all have data.
            act = fds
        return (self._main.fileno() in act, self._side.fileno() in act)

    def write(self, data):
        return self._call('write', data)

    def read(self, size):
        r = self._call('read', size)
        if size != 0 and not r:
            # We've observed a condition that indicates the
            # stdout closed unexpectedly. Check stderr one
            # more time and snag anything that's there before
            # letting anyone know the main part of the pipe
            # closed prematurely.
            _forwardoutput(self._ui, self._side)
        return r

    def readline(self):
        return self._call('readline')

    def _call(self, methname, data=None):
        """call <methname> on "main", forward output of "side" while blocking
        """
        # data can be '' or 0
        if (data is not None and not data) or self._main.closed:
            _forwardoutput(self._ui, self._side)
            return ''
        while True:
            mainready, sideready = self._wait()
            if sideready:
                _forwardoutput(self._ui, self._side)
            if mainready:
                meth = getattr(self._main, methname)
                if data is None:
                    return meth()
                else:
                    return meth(data)

    def close(self):
        return self._main.close()

    def flush(self):
        return self._main.flush()

class sshpeer(wireproto.wirepeer):
    def __init__(self, ui, path, create=False):
        self._url = path
        self.ui = ui
        self.pipeo = self.pipei = self.pipee = None

        u = util.url(path, parsequery=False, parsefragment=False)
        if u.scheme != 'ssh' or not u.host or u.path is None:
            self._abort(error.RepoError(_("couldn't parse location %s") % path))

        self.user = u.user
        if u.passwd is not None:
            self._abort(error.RepoError(_("password in URL not supported")))
        self.host = u.host
        self.port = u.port
        self.path = u.path or "."

        sshcmd = self.ui.config("ui", "ssh")
        remotecmd = self.ui.config("ui", "remotecmd")

        args = util.sshargs(sshcmd,
                            _serverquote(self.host),
                            _serverquote(self.user),
                            _serverquote(self.port))

        if create:
            cmd = '%s %s %s' % (sshcmd, args,
                util.shellquote("%s init %s" %
                    (_serverquote(remotecmd), _serverquote(self.path))))
            ui.debug('running %s\n' % cmd)
            res = ui.system(cmd, blockedtag='sshpeer')
            if res != 0:
                self._abort(error.RepoError(_("could not create remote repo")))

        self._validaterepo(sshcmd, args, remotecmd)

    def url(self):
        return self._url

    def _validaterepo(self, sshcmd, args, remotecmd):
        # cleanup up previous run
        self.cleanup()

        cmd = '%s %s %s' % (sshcmd, args,
            util.shellquote("%s -R %s serve --stdio" %
                (_serverquote(remotecmd), _serverquote(self.path))))
        self.ui.debug('running %s\n' % cmd)
        cmd = util.quotecommand(cmd)

        # while self.subprocess isn't used, having it allows the subprocess to
        # to clean up correctly later
        #
        # no buffer allow the use of 'select'
        # feel free to remove buffering and select usage when we ultimately
        # move to threading.
        sub = util.popen4(cmd, bufsize=0)
        self.pipeo, self.pipei, self.pipee, self.subprocess = sub

        self.pipei = util.bufferedinputpipe(self.pipei)
        self.pipei = doublepipe(self.ui, self.pipei, self.pipee)
        self.pipeo = doublepipe(self.ui, self.pipeo, self.pipee)

        # skip any noise generated by remote shell
        self._callstream("hello")
        r = self._callstream("between", pairs=("%s-%s" % ("0"*40, "0"*40)))
        lines = ["", "dummy"]
        max_noise = 500
        while lines[-1] and max_noise:
            l = r.readline()
            self.readerr()
            if lines[-1] == "1\n" and l == "\n":
                break
            if l:
                self.ui.debug("remote: ", l)
            lines.append(l)
            max_noise -= 1
        else:
            self._abort(error.RepoError(_('no suitable response from '
                                          'remote hg')))

        self._caps = set()
        for l in reversed(lines):
            if l.startswith("capabilities:"):
                self._caps.update(l[:-1].split(":")[1].split())
                break

    def _capabilities(self):
        return self._caps

    def readerr(self):
        _forwardoutput(self.ui, self.pipee)

    def _abort(self, exception):
        self.cleanup()
        raise exception

    def cleanup(self):
        if self.pipeo is None:
            return
        self.pipeo.close()
        self.pipei.close()
        try:
            # read the error descriptor until EOF
            for l in self.pipee:
                self.ui.status(_("remote: "), l)
        except (IOError, ValueError):
            pass
        self.pipee.close()

    __del__ = cleanup

    def _submitbatch(self, req):
        rsp = self._callstream("batch", cmds=wireproto.encodebatchcmds(req))
        available = self._getamount()
        # TODO this response parsing is probably suboptimal for large
        # batches with large responses.
        toread = min(available, 1024)
        work = rsp.read(toread)
        available -= toread
        chunk = work
        while chunk:
            while ';' in work:
                one, work = work.split(';', 1)
                yield wireproto.unescapearg(one)
            toread = min(available, 1024)
            chunk = rsp.read(toread)
            available -= toread
            work += chunk
        yield wireproto.unescapearg(work)

    def _callstream(self, cmd, **args):
        args = pycompat.byteskwargs(args)
        self.ui.debug("sending %s command\n" % cmd)
        self.pipeo.write("%s\n" % cmd)
        _func, names = wireproto.commands[cmd]
        keys = names.split()
        wireargs = {}
        for k in keys:
            if k == '*':
                wireargs['*'] = args
                break
            else:
                wireargs[k] = args[k]
                del args[k]
        for k, v in sorted(wireargs.iteritems()):
            self.pipeo.write("%s %d\n" % (k, len(v)))
            if isinstance(v, dict):
                for dk, dv in v.iteritems():
                    self.pipeo.write("%s %d\n" % (dk, len(dv)))
                    self.pipeo.write(dv)
            else:
                self.pipeo.write(v)
        self.pipeo.flush()

        return self.pipei

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

    def _call(self, cmd, **args):
        self._callstream(cmd, **args)
        return self._recv()

    def _callpush(self, cmd, fp, **args):
        r = self._call(cmd, **args)
        if r:
            return '', r
        for d in iter(lambda: fp.read(4096), ''):
            self._send(d)
        self._send("", flush=True)
        r = self._recv()
        if r:
            return '', r
        return self._recv(), ''

    def _calltwowaystream(self, cmd, fp, **args):
        r = self._call(cmd, **args)
        if r:
            # XXX needs to be made better
            raise error.Abort(_('unexpected remote reply: %s') % r)
        for d in iter(lambda: fp.read(4096), ''):
            self._send(d)
        self._send("", flush=True)
        return self.pipei

    def _getamount(self):
        l = self.pipei.readline()
        if l == '\n':
            self.readerr()
            msg = _('check previous remote output')
            self._abort(error.OutOfBandError(hint=msg))
        self.readerr()
        try:
            return int(l)
        except ValueError:
            self._abort(error.ResponseError(_("unexpected response:"), l))

    def _recv(self):
        return self.pipei.read(self._getamount())

    def _send(self, data, flush=False):
        self.pipeo.write("%d\n" % len(data))
        if data:
            self.pipeo.write(data)
        if flush:
            self.pipeo.flush()
        self.readerr()

    def lock(self):
        self._call("lock")
        return remotelock(self)

    def unlock(self):
        self._call("unlock")

    def addchangegroup(self, cg, source, url, lock=None):
        '''Send a changegroup to the remote server.  Return an integer
        similar to unbundle(). DEPRECATED, since it requires locking the
        remote.'''
        d = self._call("addchangegroup")
        if d:
            self._abort(error.RepoError(_("push refused: %s") % d))
        for d in iter(lambda: cg.read(4096), ''):
            self.pipeo.write(d)
            self.readerr()

        self.pipeo.flush()

        self.readerr()
        r = self._recv()
        if not r:
            return 1
        try:
            return int(r)
        except ValueError:
            self._abort(error.ResponseError(_("unexpected response:"), r))

instance = sshpeer