view hgext/convert/gnuarch.py @ 29559:7dec5e441bf7

sslutil: config option to specify TLS protocol version

Currently, Mercurial will use TLS 1.0 or newer when connecting to
remote servers, selecting the highest TLS version supported by both
peers. On older Pythons, only TLS 1.0 is available. On newer Pythons,
TLS 1.1 and 1.2 should be available.

Security-minded people may want to not take any risks running
TLS 1.0 (or even TLS 1.1). This patch gives those people a config
option to explicitly control which TLS versions Mercurial should use.
By providing this option, one can require newer TLS versions
before they are formally deprecated by Mercurial/Python/OpenSSL/etc
and lower their security exposure. This option also provides an
easy mechanism to change protocol policies in Mercurial. If there
is a 0-day and TLS 1.0 is completely broken, we can act quickly
without changing much code.

Because setting the minimum TLS protocol is something you'll likely
want to do globally, this patch introduces a global config option under
[hostsecurity] for that purpose.

wrapserversocket() has been taught a hidden config option to define
the explicit protocol to use. This is queried in this function and
not passed as an argument because I don't want to expose this dangerous
option as part of the Python API. There is a risk someone could footgun
themselves. But the config option is a devel option, has a warning
comment, and I doubt most people are using `hg serve` to run a
production HTTPS server (I would have something not Mercurial/Python
handle TLS). If this is problematic, we can go back to using a
custom extension in tests to coerce the server into bad behavior.

# gnuarch.py - GNU Arch support for the convert extension
#
#  Copyright 2008, 2009 Aleix Conchillo Flaque <[e-mail]>
#  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 email
import os
import shutil
import stat
import tempfile

from mercurial.i18n import _
from mercurial import (
    encoding,
    error,
    util,
)
from . import common

class gnuarch_source(common.converter_source, common.commandline):

    class gnuarch_rev(object):
        def __init__(self, rev):
            self.rev = rev
            self.summary = ''
            self.date = None
            self.author = ''
            self.continuationof = None
            self.add_files = []
            self.mod_files = []
            self.del_files = []
            self.ren_files = {}
            self.ren_dirs = {}

    def __init__(self, ui, path, revs=None):
        super(gnuarch_source, self).__init__(ui, path, revs=revs)

        if not os.path.exists(os.path.join(path, '{arch}')):
            raise common.NoRepo(_("%s does not look like a GNU Arch repository")
                         % path)

        # Could use checktool, but we want to check for baz or tla.
        self.execmd = None
        if util.findexe('baz'):
            self.execmd = 'baz'
        else:
            if util.findexe('tla'):
                self.execmd = 'tla'
            else:
                raise error.Abort(_('cannot find a GNU Arch tool'))

        common.commandline.__init__(self, ui, self.execmd)

        self.path = os.path.realpath(path)
        self.tmppath = None

        self.treeversion = None
        self.lastrev = None
        self.changes = {}
        self.parents = {}
        self.tags = {}
        self.catlogparser = email.Parser.Parser()
        self.encoding = encoding.encoding
        self.archives = []

    def before(self):
        # Get registered archives
        self.archives = [i.rstrip('\n')
                         for i in self.runlines0('archives', '-n')]

        if self.execmd == 'tla':
            output = self.run0('tree-version', self.path)
        else:
            output = self.run0('tree-version', '-d', self.path)
        self.treeversion = output.strip()

        # Get name of temporary directory
        version = self.treeversion.split('/')
        self.tmppath = os.path.join(tempfile.gettempdir(),
                                    'hg-%s' % version[1])

        # Generate parents dictionary
        self.parents[None] = []
        treeversion = self.treeversion
        child = None
        while treeversion:
            self.ui.status(_('analyzing tree version %s...\n') % treeversion)

            archive = treeversion.split('/')[0]
            if archive not in self.archives:
                self.ui.status(_('tree analysis stopped because it points to '
                                 'an unregistered archive %s...\n') % archive)
                break

            # Get the complete list of revisions for that tree version
            output, status = self.runlines('revisions', '-r', '-f', treeversion)
            self.checkexit(status, 'failed retrieving revisions for %s'
                           % treeversion)

            # No new iteration unless a revision has a continuation-of header
            treeversion = None

            for l in output:
                rev = l.strip()
                self.changes[rev] = self.gnuarch_rev(rev)
                self.parents[rev] = []

                # Read author, date and summary
                catlog, status = self.run('cat-log', '-d', self.path, rev)
                if status:
                    catlog  = self.run0('cat-archive-log', rev)
                self._parsecatlog(catlog, rev)

                # Populate the parents map
                self.parents[child].append(rev)

                # Keep track of the current revision as the child of the next
                # revision scanned
                child = rev

                # Check if we have to follow the usual incremental history
                # or if we have to 'jump' to a different treeversion given
                # by the continuation-of header.
                if self.changes[rev].continuationof:
                    treeversion = '--'.join(
                        self.changes[rev].continuationof.split('--')[:-1])
                    break

                # If we reached a base-0 revision w/o any continuation-of
                # header, it means the tree history ends here.
                if rev[-6:] == 'base-0':
                    break

    def after(self):
        self.ui.debug('cleaning up %s\n' % self.tmppath)
        shutil.rmtree(self.tmppath, ignore_errors=True)

    def getheads(self):
        return self.parents[None]

    def getfile(self, name, rev):
        if rev != self.lastrev:
            raise error.Abort(_('internal calling inconsistency'))

        if not os.path.lexists(os.path.join(self.tmppath, name)):
            return None, None

        return self._getfile(name, rev)

    def getchanges(self, rev, full):
        if full:
            raise error.Abort(_("convert from arch does not support --full"))
        self._update(rev)
        changes = []
        copies = {}

        for f in self.changes[rev].add_files:
            changes.append((f, rev))

        for f in self.changes[rev].mod_files:
            changes.append((f, rev))

        for f in self.changes[rev].del_files:
            changes.append((f, rev))

        for src in self.changes[rev].ren_files:
            to = self.changes[rev].ren_files[src]
            changes.append((src, rev))
            changes.append((to, rev))
            copies[to] = src

        for src in self.changes[rev].ren_dirs:
            to = self.changes[rev].ren_dirs[src]
            chgs, cps = self._rendirchanges(src, to)
            changes += [(f, rev) for f in chgs]
            copies.update(cps)

        self.lastrev = rev
        return sorted(set(changes)), copies, set()

    def getcommit(self, rev):
        changes = self.changes[rev]
        return common.commit(author=changes.author, date=changes.date,
                             desc=changes.summary, parents=self.parents[rev],
                             rev=rev)

    def gettags(self):
        return self.tags

    def _execute(self, cmd, *args, **kwargs):
        cmdline = [self.execmd, cmd]
        cmdline += args
        cmdline = [util.shellquote(arg) for arg in cmdline]
        cmdline += ['>', os.devnull, '2>', os.devnull]
        cmdline = util.quotecommand(' '.join(cmdline))
        self.ui.debug(cmdline, '\n')
        return os.system(cmdline)

    def _update(self, rev):
        self.ui.debug('applying revision %s...\n' % rev)
        changeset, status = self.runlines('replay', '-d', self.tmppath,
                                              rev)
        if status:
            # Something went wrong while merging (baz or tla
            # issue?), get latest revision and try from there
            shutil.rmtree(self.tmppath, ignore_errors=True)
            self._obtainrevision(rev)
        else:
            old_rev = self.parents[rev][0]
            self.ui.debug('computing changeset between %s and %s...\n'
                          % (old_rev, rev))
            self._parsechangeset(changeset, rev)

    def _getfile(self, name, rev):
        mode = os.lstat(os.path.join(self.tmppath, name)).st_mode
        if stat.S_ISLNK(mode):
            data = os.readlink(os.path.join(self.tmppath, name))
            if mode:
                mode = 'l'
            else:
                mode = ''
        else:
            data = open(os.path.join(self.tmppath, name), 'rb').read()
            mode = (mode & 0o111) and 'x' or ''
        return data, mode

    def _exclude(self, name):
        exclude = ['{arch}', '.arch-ids', '.arch-inventory']
        for exc in exclude:
            if name.find(exc) != -1:
                return True
        return False

    def _readcontents(self, path):
        files = []
        contents = os.listdir(path)
        while len(contents) > 0:
            c = contents.pop()
            p = os.path.join(path, c)
            # os.walk could be used, but here we avoid internal GNU
            # Arch files and directories, thus saving a lot time.
            if not self._exclude(p):
                if os.path.isdir(p):
                    contents += [os.path.join(c, f) for f in os.listdir(p)]
                else:
                    files.append(c)
        return files

    def _rendirchanges(self, src, dest):
        changes = []
        copies = {}
        files = self._readcontents(os.path.join(self.tmppath, dest))
        for f in files:
            s = os.path.join(src, f)
            d = os.path.join(dest, f)
            changes.append(s)
            changes.append(d)
            copies[d] = s
        return changes, copies

    def _obtainrevision(self, rev):
        self.ui.debug('obtaining revision %s...\n' % rev)
        output = self._execute('get', rev, self.tmppath)
        self.checkexit(output)
        self.ui.debug('analyzing revision %s...\n' % rev)
        files = self._readcontents(self.tmppath)
        self.changes[rev].add_files += files

    def _stripbasepath(self, path):
        if path.startswith('./'):
            return path[2:]
        return path

    def _parsecatlog(self, data, rev):
        try:
            catlog = self.catlogparser.parsestr(data)

            # Commit date
            self.changes[rev].date = util.datestr(
                util.strdate(catlog['Standard-date'],
                             '%Y-%m-%d %H:%M:%S'))

            # Commit author
            self.changes[rev].author = self.recode(catlog['Creator'])

            # Commit description
            self.changes[rev].summary = '\n\n'.join((catlog['Summary'],
                                                    catlog.get_payload()))
            self.changes[rev].summary = self.recode(self.changes[rev].summary)

            # Commit revision origin when dealing with a branch or tag
            if 'Continuation-of' in catlog:
                self.changes[rev].continuationof = self.recode(
                    catlog['Continuation-of'])
        except Exception:
            raise error.Abort(_('could not parse cat-log of %s') % rev)

    def _parsechangeset(self, data, rev):
        for l in data:
            l = l.strip()
            # Added file (ignore added directory)
            if l.startswith('A') and not l.startswith('A/'):
                file = self._stripbasepath(l[1:].strip())
                if not self._exclude(file):
                    self.changes[rev].add_files.append(file)
            # Deleted file (ignore deleted directory)
            elif l.startswith('D') and not l.startswith('D/'):
                file = self._stripbasepath(l[1:].strip())
                if not self._exclude(file):
                    self.changes[rev].del_files.append(file)
            # Modified binary file
            elif l.startswith('Mb'):
                file = self._stripbasepath(l[2:].strip())
                if not self._exclude(file):
                    self.changes[rev].mod_files.append(file)
            # Modified link
            elif l.startswith('M->'):
                file = self._stripbasepath(l[3:].strip())
                if not self._exclude(file):
                    self.changes[rev].mod_files.append(file)
            # Modified file
            elif l.startswith('M'):
                file = self._stripbasepath(l[1:].strip())
                if not self._exclude(file):
                    self.changes[rev].mod_files.append(file)
            # Renamed file (or link)
            elif l.startswith('=>'):
                files = l[2:].strip().split(' ')
                if len(files) == 1:
                    files = l[2:].strip().split('\t')
                src = self._stripbasepath(files[0])
                dst = self._stripbasepath(files[1])
                if not self._exclude(src) and not self._exclude(dst):
                    self.changes[rev].ren_files[src] = dst
            # Conversion from file to link or from link to file (modified)
            elif l.startswith('ch'):
                file = self._stripbasepath(l[2:].strip())
                if not self._exclude(file):
                    self.changes[rev].mod_files.append(file)
            # Renamed directory
            elif l.startswith('/>'):
                dirs = l[2:].strip().split(' ')
                if len(dirs) == 1:
                    dirs = l[2:].strip().split('\t')
                src = self._stripbasepath(dirs[0])
                dst = self._stripbasepath(dirs[1])
                if not self._exclude(src) and not self._exclude(dst):
                    self.changes[rev].ren_dirs[src] = dst