view hgext/convert/cvs.py @ 40811:e13ab4acf555

rust: peek_mut optim for lazy ancestors This is one of the two optimizations that are also present in the Python code: replacing pairs of pop/push on the BinaryHeap by single updates, hence having it under the hood maintain its consistency (sift) only once. On Mozilla central, the measured gain (see details below) is around 7%. Creating the PeekMut object by calling peek_mut() right away instead of peek() first is less efficient (gain is only 4%, stats not included). Our interpretation is that its creation has a cost which is vasted in the cases where it ends by droping the value (Peekmut::pop() just does self.heap.pop() anyway). On the other hand, the immutable peek() is very fast: it's just taking a reference in the underlying vector. The Python version still has another optimization: if parent(current) == current-1, then the heap doesn't need to maintain its consistency, since we already know that it's bigger than all the others in the heap. Rust's BinaryHeap doesn't allow us to mutate its biggest element with no housekeeping, but we tried it anyway, with a copy of the BinaryHeap implementation with a dedicaded added method: it's not worth the technical debt in our opinion (we measured only a further 1.6% improvement). One possible explanation would be that the sift is really fast anyway in that case, whereas it's not in the case of Python, because it's at least partly done in slow Python code. Still it's possible that replacing BinaryHeap by something more dedicated to discrete ordered types could be faster. Measurements on mozilla-central: Three runs of 'hg perfancestors' on the parent changeset: Moyenne des médianes: 0.100587 ! wall 0.100062 comb 0.100000 user 0.100000 sys 0.000000 (best of 98) ! wall 0.135804 comb 0.130000 user 0.130000 sys 0.000000 (max of 98) ! wall 0.102864 comb 0.102755 user 0.099286 sys 0.003469 (avg of 98) ! wall 0.101486 comb 0.110000 user 0.110000 sys 0.000000 (median of 98) ! wall 0.096804 comb 0.090000 user 0.090000 sys 0.000000 (best of 100) ! wall 0.132235 comb 0.130000 user 0.120000 sys 0.010000 (max of 100) ! wall 0.100258 comb 0.100300 user 0.096000 sys 0.004300 (avg of 100) ! wall 0.098384 comb 0.100000 user 0.100000 sys 0.000000 (median of 100) ! wall 0.099925 comb 0.100000 user 0.100000 sys 0.000000 (best of 98) ! wall 0.133518 comb 0.140000 user 0.130000 sys 0.010000 (max of 98) ! wall 0.102381 comb 0.102449 user 0.098265 sys 0.004184 (avg of 98) ! wall 0.101891 comb 0.090000 user 0.090000 sys 0.000000 (median of 98) Mean of the medians: 0.100587 On the present changeset: ! wall 0.091344 comb 0.090000 user 0.090000 sys 0.000000 (best of 100) ! wall 0.122728 comb 0.120000 user 0.110000 sys 0.010000 (max of 100) ! wall 0.093268 comb 0.093300 user 0.089300 sys 0.004000 (avg of 100) ! wall 0.092567 comb 0.100000 user 0.090000 sys 0.010000 (median of 100) ! wall 0.093294 comb 0.080000 user 0.080000 sys 0.000000 (best of 100) ! wall 0.144887 comb 0.150000 user 0.140000 sys 0.010000 (max of 100) ! wall 0.097708 comb 0.097700 user 0.093400 sys 0.004300 (avg of 100) ! wall 0.094980 comb 0.100000 user 0.090000 sys 0.010000 (median of 100) ! wall 0.091262 comb 0.090000 user 0.080000 sys 0.010000 (best of 100) ! wall 0.123772 comb 0.130000 user 0.120000 sys 0.010000 (max of 100) ! wall 0.093188 comb 0.093200 user 0.089300 sys 0.003900 (avg of 100) ! wall 0.092364 comb 0.100000 user 0.090000 sys 0.010000 (median of 100) Mean of the medians is 0.0933 Differential Revision: https://phab.mercurial-scm.org/D5358
author Georges Racinet <gracinet@anybox.fr>
date Thu, 29 Nov 2018 09:13:13 +0000
parents 24e493ec2229
children 876494fd967d
line wrap: on
line source

# cvs.py: CVS conversion code inspired by hg-cvs-import and git-cvsimport
#
#  Copyright 2005-2009 Matt Mackall <mpm@selenic.com> and others
#
# 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 os
import re
import socket

from mercurial.i18n import _
from mercurial import (
    encoding,
    error,
    util,
)
from mercurial.utils import (
    dateutil,
    procutil,
)

from . import (
    common,
    cvsps,
)

stringio = util.stringio
checktool = common.checktool
commit = common.commit
converter_source = common.converter_source
makedatetimestamp = common.makedatetimestamp
NoRepo = common.NoRepo

class convert_cvs(converter_source):
    def __init__(self, ui, repotype, path, revs=None):
        super(convert_cvs, self).__init__(ui, repotype, path, revs=revs)

        cvs = os.path.join(path, "CVS")
        if not os.path.exists(cvs):
            raise NoRepo(_("%s does not look like a CVS checkout") % path)

        checktool('cvs')

        self.changeset = None
        self.files = {}
        self.tags = {}
        self.lastbranch = {}
        self.socket = None
        self.cvsroot = open(os.path.join(cvs, "Root"), 'rb').read()[:-1]
        self.cvsrepo = open(os.path.join(cvs, "Repository"), 'rb').read()[:-1]
        self.encoding = encoding.encoding

        self._connect()

    def _parse(self):
        if self.changeset is not None:
            return
        self.changeset = {}

        maxrev = 0
        if self.revs:
            if len(self.revs) > 1:
                raise error.Abort(_('cvs source does not support specifying '
                                   'multiple revs'))
            # TODO: handle tags
            try:
                # patchset number?
                maxrev = int(self.revs[0])
            except ValueError:
                raise error.Abort(_('revision %s is not a patchset number')
                                 % self.revs[0])

        d = encoding.getcwd()
        try:
            os.chdir(self.path)
            id = None

            cache = 'update'
            if not self.ui.configbool('convert', 'cvsps.cache'):
                cache = None
            db = cvsps.createlog(self.ui, cache=cache)
            db = cvsps.createchangeset(self.ui, db,
                fuzz=int(self.ui.config('convert', 'cvsps.fuzz')),
                mergeto=self.ui.config('convert', 'cvsps.mergeto'),
                mergefrom=self.ui.config('convert', 'cvsps.mergefrom'))

            for cs in db:
                if maxrev and cs.id > maxrev:
                    break
                id = (b"%d" % cs.id)
                cs.author = self.recode(cs.author)
                self.lastbranch[cs.branch] = id
                cs.comment = self.recode(cs.comment)
                if self.ui.configbool('convert', 'localtimezone'):
                    cs.date = makedatetimestamp(cs.date[0])
                date = dateutil.datestr(cs.date, '%Y-%m-%d %H:%M:%S %1%2')
                self.tags.update(dict.fromkeys(cs.tags, id))

                files = {}
                for f in cs.entries:
                    files[f.file] = "%s%s" % ('.'.join([(b"%d" % x)
                                                        for x in f.revision]),
                                              ['', '(DEAD)'][f.dead])

                # add current commit to set
                c = commit(author=cs.author, date=date,
                           parents=[(b"%d" % p.id) for p in cs.parents],
                           desc=cs.comment, branch=cs.branch or '')
                self.changeset[id] = c
                self.files[id] = files

            self.heads = self.lastbranch.values()
        finally:
            os.chdir(d)

    def _connect(self):
        root = self.cvsroot
        conntype = None
        user, host = None, None
        cmd = ['cvs', 'server']

        self.ui.status(_("connecting to %s\n") % root)

        if root.startswith(":pserver:"):
            root = root[9:]
            m = re.match(r'(?:(.*?)(?::(.*?))?@)?([^:\/]*)(?::(\d*))?(.*)',
                         root)
            if m:
                conntype = "pserver"
                user, passw, serv, port, root = m.groups()
                if not user:
                    user = "anonymous"
                if not port:
                    port = 2401
                else:
                    port = int(port)
                format0 = ":pserver:%s@%s:%s" % (user, serv, root)
                format1 = ":pserver:%s@%s:%d%s" % (user, serv, port, root)

                if not passw:
                    passw = "A"
                    cvspass = os.path.expanduser("~/.cvspass")
                    try:
                        pf = open(cvspass, 'rb')
                        for line in pf.read().splitlines():
                            part1, part2 = line.split(' ', 1)
                            # /1 :pserver:user@example.com:2401/cvsroot/foo
                            # Ah<Z
                            if part1 == '/1':
                                part1, part2 = part2.split(' ', 1)
                                format = format1
                            # :pserver:user@example.com:/cvsroot/foo Ah<Z
                            else:
                                format = format0
                            if part1 == format:
                                passw = part2
                                break
                        pf.close()
                    except IOError as inst:
                        if inst.errno != errno.ENOENT:
                            if not getattr(inst, 'filename', None):
                                inst.filename = cvspass
                            raise

                sck = socket.socket()
                sck.connect((serv, port))
                sck.send("\n".join(["BEGIN AUTH REQUEST", root, user, passw,
                                    "END AUTH REQUEST", ""]))
                if sck.recv(128) != "I LOVE YOU\n":
                    raise error.Abort(_("CVS pserver authentication failed"))

                self.writep = self.readp = sck.makefile('r+')

        if not conntype and root.startswith(":local:"):
            conntype = "local"
            root = root[7:]

        if not conntype:
            # :ext:user@host/home/user/path/to/cvsroot
            if root.startswith(":ext:"):
                root = root[5:]
            m = re.match(br'(?:([^@:/]+)@)?([^:/]+):?(.*)', root)
            # Do not take Windows path "c:\foo\bar" for a connection strings
            if os.path.isdir(root) or not m:
                conntype = "local"
            else:
                conntype = "rsh"
                user, host, root = m.group(1), m.group(2), m.group(3)

        if conntype != "pserver":
            if conntype == "rsh":
                rsh = encoding.environ.get("CVS_RSH") or "ssh"
                if user:
                    cmd = [rsh, '-l', user, host] + cmd
                else:
                    cmd = [rsh, host] + cmd

            # popen2 does not support argument lists under Windows
            cmd = [procutil.shellquote(arg) for arg in cmd]
            cmd = procutil.quotecommand(' '.join(cmd))
            self.writep, self.readp = procutil.popen2(cmd)

        self.realroot = root

        self.writep.write("Root %s\n" % root)
        self.writep.write("Valid-responses ok error Valid-requests Mode"
                          " M Mbinary E Checked-in Created Updated"
                          " Merged Removed\n")
        self.writep.write("valid-requests\n")
        self.writep.flush()
        r = self.readp.readline()
        if not r.startswith("Valid-requests"):
            raise error.Abort(_('unexpected response from CVS server '
                               '(expected "Valid-requests", but got %r)')
                             % r)
        if "UseUnchanged" in r:
            self.writep.write("UseUnchanged\n")
            self.writep.flush()
            r = self.readp.readline()

    def getheads(self):
        self._parse()
        return self.heads

    def getfile(self, name, rev):

        def chunkedread(fp, count):
            # file-objects returned by socket.makefile() do not handle
            # large read() requests very well.
            chunksize = 65536
            output = stringio()
            while count > 0:
                data = fp.read(min(count, chunksize))
                if not data:
                    raise error.Abort(_("%d bytes missing from remote file")
                                     % count)
                count -= len(data)
                output.write(data)
            return output.getvalue()

        self._parse()
        if rev.endswith("(DEAD)"):
            return None, None

        args = ("-N -P -kk -r %s --" % rev).split()
        args.append(self.cvsrepo + '/' + name)
        for x in args:
            self.writep.write("Argument %s\n" % x)
        self.writep.write("Directory .\n%s\nco\n" % self.realroot)
        self.writep.flush()

        data = ""
        mode = None
        while True:
            line = self.readp.readline()
            if line.startswith("Created ") or line.startswith("Updated "):
                self.readp.readline() # path
                self.readp.readline() # entries
                mode = self.readp.readline()[:-1]
                count = int(self.readp.readline()[:-1])
                data = chunkedread(self.readp, count)
            elif line.startswith(" "):
                data += line[1:]
            elif line.startswith("M "):
                pass
            elif line.startswith("Mbinary "):
                count = int(self.readp.readline()[:-1])
                data = chunkedread(self.readp, count)
            else:
                if line == "ok\n":
                    if mode is None:
                        raise error.Abort(_('malformed response from CVS'))
                    return (data, "x" in mode and "x" or "")
                elif line.startswith("E "):
                    self.ui.warn(_("cvs server: %s\n") % line[2:])
                elif line.startswith("Remove"):
                    self.readp.readline()
                else:
                    raise error.Abort(_("unknown CVS response: %s") % line)

    def getchanges(self, rev, full):
        if full:
            raise error.Abort(_("convert from cvs does not support --full"))
        self._parse()
        return sorted(self.files[rev].iteritems()), {}, set()

    def getcommit(self, rev):
        self._parse()
        return self.changeset[rev]

    def gettags(self):
        self._parse()
        return self.tags

    def getchangedfiles(self, rev, i):
        self._parse()
        return sorted(self.files[rev])