Mercurial > hg
view mercurial/sshpeer.py @ 35616:706aa203b396
fileset: add a lightweight file filtering language
This patch was inspired by one that Jun Wu authored for the fb-experimental
repo, to avoid using matcher for efficiency[1]. We want a way to specify what
files will be converted to LFS at commit time. And per discussion, we also want
to specify what files to skip, text diff, or merge in another config option.
The current `lfs.threshold` config option could not satisfy complex needs. I'm
putting it in a core package because Augie floated the idea of also using it for
narrow and sparse.
Yuya suggested farming out to fileset.parse(), which added support for more
symbols. The only fileset element not supported here is 'negate'. (List isn't
supported by filesets either.) I also changed the 'always' token to the 'all()'
predicate for consistency, and introduced 'none()' to improve readability in a
future tracked file based config. The extension operator was changed from '.'
to '**', to match how recursive path globs are specified. Finally, I changed
the path matcher from '/' to 'path:' at Yuya's suggestion, for consistency with
matcher. Unfortunately, ':' is currently reserved in filesets, so this has to
be quoted to be processed as a string instead of a symbol[2]. We should
probably revisit that, because it's seriously ugly. But it's only used by an
experimental extension, and I think using a file based config for LFS may drive
some more tweaks, so I'm settling for this for now.
I reserved all of the glob characters in fileset except '.' and '_' for the
extension test because those are likely valid extension characters.
Sample filter settings:
all() # everything
size(">20MB") # larger than 20MB
!**.txt # except for .txt files
**.zip | **.tar.gz | **.7z # some types of compressed files
"path:bin" # files under "bin" in the project root
[1] https://www.mercurial-scm.org/pipermail/mercurial-devel/2017-December/109387.html
[2] https://www.mercurial-scm.org/pipermail/mercurial-devel/2018-January/109729.html
author | Matt Harbison <matt_harbison@yahoo.com> |
---|---|
date | Wed, 10 Jan 2018 22:23:34 -0500 |
parents | b520c8f98e1e |
children | f7ef49e44d7c |
line wrap: on
line source
# sshpeer.py - ssh repository proxy class for mercurial # # Copyright 2005, 2006 Matt Mackall <mpm@selenic.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 re from .i18n import _ from . import ( error, pycompat, util, wireproto, ) def _serverquote(s): """quote a string for the remote shell ... which we assume is sh""" if not s: return s 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)) util.checksafessh(path) if u.passwd is not None: self._abort(error.RepoError(_("password in URL not supported"))) self._user = u.user 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") sshaddenv = dict(self.ui.configitems("sshenv")) sshenv = util.shellenviron(sshaddenv) args = util.sshargs(sshcmd, self._host, self._user, 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', environ=sshenv) if res != 0: self._abort(error.RepoError(_("could not create remote repo"))) self._validaterepo(sshcmd, args, remotecmd, sshenv) # Begin of _basepeer interface. @util.propertycache def ui(self): return self._ui def url(self): return self._url def local(self): return None def peer(self): return self def canpush(self): return True def close(self): pass # End of _basepeer interface. # Begin of _basewirecommands interface. def capabilities(self): return self._caps # End of _basewirecommands interface. def _validaterepo(self, sshcmd, args, remotecmd, sshenv=None): # 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, env=sshenv) 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) def badresponse(): msg = _("no suitable response from remote hg") hint = self.ui.config("ui", "ssherrorhint") self._abort(error.RepoError(msg, hint=hint)) try: # skip any noise generated by remote shell self._callstream("hello") r = self._callstream("between", pairs=("%s-%s" % ("0"*40, "0"*40))) except IOError: badresponse() lines = ["", "dummy"] max_noise = 500 while lines[-1] and max_noise: try: 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 except IOError: badresponse() else: badresponse() self._caps = set() for l in reversed(lines): if l.startswith("capabilities:"): self._caps.update(l[:-1].split(":")[1].split()) break 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() instance = sshpeer