view hgext/strip.py @ 20742:3681de20b0a7

parsers: fail fast if Python has wrong minor version (issue4110)

This change causes an informative ImportError to be raised when importing
the parsers extension module if the minor version of the currently-running
Python interpreter doesn't match that of the Python used when compiling
the extension module.

This change also exposes a parsers.versionerrortext constant in the
C implementation of the module.  Its presence can be used to determine
whether this behavior is present in a version of the module.  The value
of the constant is the leading text of the ImportError raised and is set
to "Python minor version mismatch".

Here is an example of what the new error looks like:

  Traceback (most recent call last):
    File "test.py", line 1, in <module>
      import mercurial.parsers
  ImportError: Python minor version mismatch: The Mercurial extension
  modules were compiled with Python 2.7.6, but Mercurial is currently using
  Python with sys.hexversion=33883888: Python 2.5.6
  (r256:88840, Nov 18 2012, 05:37:10)
  [GCC 4.2.1 Compatible Apple Clang 4.1 ((tags/Apple/clang-421.11.66))]
   at: /opt/local/Library/Frameworks/Python.framework/Versions/2.5/Resources/
    Python.app/Contents/MacOS/Python

The reason for raising an error in this scenario is that Python's C API
is known not to be compatible from minor version to minor version, even
if sys.api_version is the same.  See for example this Python bug report
about incompatibilities between 2.5 and 2.6+:

  http://bugs.python.org/issue8118

These incompatibilities can cause Mercurial to break in mysterious,
unforeseen ways.  For example, when Mercurial compiled with Python 2.7 was
run with 2.5, the following crash occurred when running "hg status":

  http://bz.selenic.com/show_bug.cgi?id=4110

After this crash was fixed, running with Python 2.5 no longer crashes, but
the following puzzling behavior still occurs:

    $ hg status
      ...
      File ".../mercurial/changelog.py", line 123, in __init__
        revlog.revlog.__init__(self, opener, "00changelog.i")
      File ".../mercurial/revlog.py", line 251, in __init__
        d = self._io.parseindex(i, self._inline)
      File ".../mercurial/revlog.py", line 158, in parseindex
        index, cache = parsers.parse_index2(data, inline)
    TypeError: data is not a string

which can be reproduced more simply with:

    import mercurial.parsers as parsers
    parsers.parse_index2("", True)

Both the crash and the TypeError occurred because the Python C API's
PyString_Check() returns the wrong value when the C header files from
Python 2.7 are run with Python 2.5.  This is an example of an
incompatibility of the sort mentioned in the Python bug report above.

Failing fast with an informative error message results in a better user
experience in cases like the above.  The information in the ImportError
also simplifies troubleshooting for those on Mercurial mailing lists, the
bug tracker, etc.

This patch only adds the version check to parsers.c, which is sufficient
to affect command-line commands like "hg status" and "hg summary".
An idea for a future improvement is to move the version-checking C code
to a more central location, and have it run when importing all
Mercurial extension modules and not just parsers.c.

"""strip changesets and their descendents from history

This extension allows you to strip changesets and all their descendants from the
repository. See the command help for details.
"""
from mercurial.i18n import _
from mercurial.node import nullid
from mercurial.lock import release
from mercurial import cmdutil, hg, scmutil, util
from mercurial import repair, bookmarks

cmdtable = {}
command = cmdutil.command(cmdtable)
testedwith = 'internal'

def checksubstate(repo, baserev=None):
    '''return list of subrepos at a different revision than substate.
    Abort if any subrepos have uncommitted changes.'''
    inclsubs = []
    wctx = repo[None]
    if baserev:
        bctx = repo[baserev]
    else:
        bctx = wctx.parents()[0]
    for s in sorted(wctx.substate):
        if wctx.sub(s).dirty(True):
            raise util.Abort(
                _("uncommitted changes in subrepository %s") % s)
        elif s not in bctx.substate or bctx.sub(s).dirty():
            inclsubs.append(s)
    return inclsubs

def checklocalchanges(repo, force=False, excsuffix=''):
    cmdutil.checkunfinished(repo)
    m, a, r, d = repo.status()[:4]
    if not force:
        if (m or a or r or d):
            _("local changes found") # i18n tool detection
            raise util.Abort(_("local changes found" + excsuffix))
        if checksubstate(repo):
            _("local changed subrepos found") # i18n tool detection
            raise util.Abort(_("local changed subrepos found" + excsuffix))
    return m, a, r, d

def strip(ui, repo, revs, update=True, backup="all", force=None):
    wlock = lock = None
    try:
        wlock = repo.wlock()
        lock = repo.lock()

        if update:
            checklocalchanges(repo, force=force)
            urev, p2 = repo.changelog.parents(revs[0])
            if (util.safehasattr(repo, 'mq') and
                p2 != nullid
                and p2 in [x.node for x in repo.mq.applied]):
                urev = p2
            hg.clean(repo, urev)
            repo.dirstate.write()

        repair.strip(ui, repo, revs, backup)
    finally:
        release(lock, wlock)


@command("strip",
         [
          ('r', 'rev', [], _('strip specified revision (optional, '
                               'can specify revisions without this '
                               'option)'), _('REV')),
          ('f', 'force', None, _('force removal of changesets, discard '
                                 'uncommitted changes (no backup)')),
          ('b', 'backup', None, _('bundle only changesets with local revision'
                                  ' number greater than REV which are not'
                                  ' descendants of REV (DEPRECATED)')),
          ('', 'no-backup', None, _('no backups')),
          ('', 'nobackup', None, _('no backups (DEPRECATED)')),
          ('n', '', None, _('ignored  (DEPRECATED)')),
          ('k', 'keep', None, _("do not modify working copy during strip")),
          ('B', 'bookmark', '', _("remove revs only reachable from given"
                                  " bookmark"))],
          _('hg strip [-k] [-f] [-n] [-B bookmark] [-r] REV...'))
def stripcmd(ui, repo, *revs, **opts):
    """strip changesets and all their descendants from the repository

    The strip command removes the specified changesets and all their
    descendants. If the working directory has uncommitted changes, the
    operation is aborted unless the --force flag is supplied, in which
    case changes will be discarded.

    If a parent of the working directory is stripped, then the working
    directory will automatically be updated to the most recent
    available ancestor of the stripped parent after the operation
    completes.

    Any stripped changesets are stored in ``.hg/strip-backup`` as a
    bundle (see :hg:`help bundle` and :hg:`help unbundle`). They can
    be restored by running :hg:`unbundle .hg/strip-backup/BUNDLE`,
    where BUNDLE is the bundle file created by the strip. Note that
    the local revision numbers will in general be different after the
    restore.

    Use the --no-backup option to discard the backup bundle once the
    operation completes.

    Strip is not a history-rewriting operation and can be used on
    changesets in the public phase. But if the stripped changesets have
    been pushed to a remote repository you will likely pull them again.

    Return 0 on success.
    """
    backup = 'all'
    if opts.get('backup'):
        backup = 'strip'
    elif opts.get('no_backup') or opts.get('nobackup'):
        backup = 'none'

    cl = repo.changelog
    revs = list(revs) + opts.get('rev')
    revs = set(scmutil.revrange(repo, revs))

    wlock = repo.wlock()
    try:
        if opts.get('bookmark'):
            mark = opts.get('bookmark')
            marks = repo._bookmarks
            if mark not in marks:
                raise util.Abort(_("bookmark '%s' not found") % mark)

            # If the requested bookmark is not the only one pointing to a
            # a revision we have to only delete the bookmark and not strip
            # anything. revsets cannot detect that case.
            uniquebm = True
            for m, n in marks.iteritems():
                if m != mark and n == repo[mark].node():
                    uniquebm = False
                    break
            if uniquebm:
                rsrevs = repo.revs("ancestors(bookmark(%s)) - "
                                   "ancestors(head() and not bookmark(%s)) - "
                                   "ancestors(bookmark() and not bookmark(%s))",
                                   mark, mark, mark)
                revs.update(set(rsrevs))
            if not revs:
                del marks[mark]
                marks.write()
                ui.write(_("bookmark '%s' deleted\n") % mark)

        if not revs:
            raise util.Abort(_('empty revision set'))

        descendants = set(cl.descendants(revs))
        strippedrevs = revs.union(descendants)
        roots = revs.difference(descendants)

        update = False
        # if one of the wdir parent is stripped we'll need
        # to update away to an earlier revision
        for p in repo.dirstate.parents():
            if p != nullid and cl.rev(p) in strippedrevs:
                update = True
                break

        rootnodes = set(cl.node(r) for r in roots)

        q = getattr(repo, 'mq', None)
        if q is not None and q.applied:
            # refresh queue state if we're about to strip
            # applied patches
            if cl.rev(repo.lookup('qtip')) in strippedrevs:
                q.applieddirty = True
                start = 0
                end = len(q.applied)
                for i, statusentry in enumerate(q.applied):
                    if statusentry.node in rootnodes:
                        # if one of the stripped roots is an applied
                        # patch, only part of the queue is stripped
                        start = i
                        break
                del q.applied[start:end]
                q.savedirty()

        revs = sorted(rootnodes)
        if update and opts.get('keep'):
            urev, p2 = repo.changelog.parents(revs[0])
            if (util.safehasattr(repo, 'mq') and p2 != nullid
                and p2 in [x.node for x in repo.mq.applied]):
                urev = p2
            uctx = repo[urev]

            # only reset the dirstate for files that would actually change
            # between the working context and uctx
            descendantrevs = repo.revs("%s::." % uctx.rev())
            changedfiles = []
            for rev in descendantrevs:
                # blindly reset the files, regardless of what actually changed
                changedfiles.extend(repo[rev].files())

            # reset files that only changed in the dirstate too
            dirstate = repo.dirstate
            dirchanges = [f for f in dirstate if dirstate[f] != 'n']
            changedfiles.extend(dirchanges)

            repo.dirstate.rebuild(urev, uctx.manifest(), changedfiles)
            repo.dirstate.write()
            update = False

        if opts.get('bookmark'):
            if mark == repo._bookmarkcurrent:
                bookmarks.unsetcurrent(repo)
            del marks[mark]
            marks.write()
            ui.write(_("bookmark '%s' deleted\n") % mark)

        strip(ui, repo, revs, backup=backup, update=update,
              force=opts.get('force'))
    finally:
        wlock.release()

    return 0