annotate mercurial/repair.py @ 23352:5bd04faaa3ee

run-tests: don't warn on unnecessary globs mandated by check-code.py

When test output is processed, if os.altsep is defined (i.e. on Windows),
TTest.globmatch() will cause a warning later on if a line has a glob that isn't
necessary.  Unfortunately, the regex checking in check-code.py doesn't have this
context.  Therefore we ended up with cases where the test would get flagged with
a warning only on Windows because a glob was present, because check-code.py
would warn if it wasn't.  For example, from test-subrepo.t:

    $ hg -R issue1852a push `pwd`/issue1852c
    pushing to $TESTTMP/issue1852c (glob)

The glob isn't necessary here because the slash is shown as it was provided.
However, check-code mandates one to handle the case where the default path has
backslashes in it.

Break the cycle by checking against a subset of the check-code rules before
flagging the test with a warning, and ignore the superfluous glob if it matches
a rule.  This change fixes warnings in test-largefiles-update.t, test-subrepo.t,
test-tag.t, and test-rename-dir-merge.t on Windows.

I really hate that the rules are copy/pasted here (minus the leading two spaces)
because it would be nice to only update the rules once, in a single place.  But
I'm not sure how else to do it.  I'm open to suggestions.  Splitting some of the
rules out of check-code.py seems wrong, but so does moving check-code.py out of
contrib, given that other checking scripts live there.

There are other glob patterns that could be copied over, but this is enough to
make the current tests run on Windows.

# repair.py - functions for repository repair for mercurial
#
# Copyright 2005, 2006 Chris Mason <[e-mail]>
# Copyright 2007 Matt Mackall
#
# This software may be used and distributed according to the terms of the
# GNU General Public License version 2 or any later version.

from mercurial import changegroup, exchange
from mercurial.node import short
from mercurial.i18n import _
import errno

def _bundle(repo, bases, heads, node, suffix, compress=True):
    """create a bundle with the specified revisions as a backup"""
    cg = changegroup.changegroupsubset(repo, bases, heads, 'strip')
    backupdir = "strip-backup"
    vfs = repo.vfs
    if not vfs.isdir(backupdir):
        vfs.mkdir(backupdir)
    name = "%s/%s-%s.hg" % (backupdir, short(node), suffix)
    if compress:
        bundletype = "HG10BZ"
    else:
        bundletype = "HG10UN"
    return changegroup.writebundle(cg, name, bundletype, vfs)

def _collectfiles(repo, striprev):
    """find out the filelogs affected by the strip"""
    files = set()

    for x in xrange(striprev, len(repo)):
        files.update(repo[x].files())

    return sorted(files)

def _collectbrokencsets(repo, files, striprev):
    """return the changesets which will be broken by the truncation"""
    s = set()
    def collectone(revlog):
        _, brokenset = revlog.getstrippoint(striprev)
        s.update([revlog.linkrev(r) for r in brokenset])

    collectone(repo.manifest)
    for fname in files:
        collectone(repo.file(fname))

    return s

def strip(ui, repo, nodelist, backup=True, topic='backup'):

    # Simple way to maintain backwards compatibility for this
    # argument.
    if backup in ['none', 'strip']:
        backup = False

    repo = repo.unfiltered()
    repo.destroying()

    cl = repo.changelog
    # TODO handle undo of merge sets
    if isinstance(nodelist, str):
        nodelist = [nodelist]
    striplist = [cl.rev(node) for node in nodelist]
    striprev = min(striplist)

    # Some revisions with rev > striprev may not be descendants of striprev.
    # We have to find these revisions and put them in a bundle, so that
    # we can restore them after the truncations.
    # To create the bundle we use repo.changegroupsubset which requires
    # the list of heads and bases of the set of interesting revisions.
    # (head = revision in the set that has no descendant in the set;
    #  base = revision in the set that has no ancestor in the set)
    tostrip = set(striplist)
    for rev in striplist:
        for desc in cl.descendants([rev]):
            tostrip.add(desc)

    files = _collectfiles(repo, striprev)
    saverevs = _collectbrokencsets(repo, files, striprev)

    # compute heads
    saveheads = set(saverevs)
    for r in xrange(striprev + 1, len(cl)):
        if r not in tostrip:
            saverevs.add(r)
            saveheads.difference_update(cl.parentrevs(r))
            saveheads.add(r)
    saveheads = [cl.node(r) for r in saveheads]

    # compute base nodes
    if saverevs:
        descendants = set(cl.descendants(saverevs))
        saverevs.difference_update(descendants)
    savebases = [cl.node(r) for r in saverevs]
    stripbases = [cl.node(r) for r in tostrip]

    # For a set s, max(parents(s) - s) is the same as max(heads(::s - s)), but
    # is much faster
    newbmtarget = repo.revs('max(parents(%ld) - (%ld))', tostrip, tostrip)
    if newbmtarget:
        newbmtarget = repo[newbmtarget.first()].node()
    else:
        newbmtarget = '.'

    bm = repo._bookmarks
    updatebm = []
    for m in bm:
        rev = repo[bm[m]].rev()
        if rev in tostrip:
            updatebm.append(m)

    # create a changegroup for all the branches we need to keep
    backupfile = None
    vfs = repo.vfs
    if backup:
        backupfile = _bundle(repo, stripbases, cl.heads(), node, topic)
        repo.ui.status(_("saved backup bundle to %s\n") %
                       vfs.join(backupfile))
        repo.ui.log("backupbundle", "saved backup bundle to %s\n",
                    vfs.join(backupfile))
    if saveheads or savebases:
        # do not compress partial bundle if we remove it from disk later
        chgrpfile = _bundle(repo, savebases, saveheads, node, 'temp',
                            compress=False)

    mfst = repo.manifest

    tr = repo.transaction("strip")
    offset = len(tr.entries)

    try:
        tr.startgroup()
        cl.strip(striprev, tr)
        mfst.strip(striprev, tr)
        for fn in files:
            repo.file(fn).strip(striprev, tr)
        tr.endgroup()

        try:
            for i in xrange(offset, len(tr.entries)):
                file, troffset, ignore = tr.entries[i]
                repo.sopener(file, 'a').truncate(troffset)
                if troffset == 0:
                    repo.store.markremoved(file)
            tr.close()
        except: # re-raises
            tr.abort()
            raise

        if saveheads or savebases:
            ui.note(_("adding branch\n"))
            f = vfs.open(chgrpfile, "rb")
            gen = exchange.readbundle(ui, f, chgrpfile, vfs)
            if not repo.ui.verbose:
                # silence internal shuffling chatter
                repo.ui.pushbuffer()
            changegroup.addchangegroup(repo, gen, 'strip',
                                       'bundle:' + vfs.join(chgrpfile), True)
            if not repo.ui.verbose:
                repo.ui.popbuffer()
            f.close()

        # remove undo files
        for undovfs, undofile in repo.undofiles():
            try:
                undovfs.unlink(undofile)
            except OSError, e:
                if e.errno != errno.ENOENT:
                    ui.warn(_('error removing %s: %s\n') %
                            (undovfs.join(undofile), str(e)))

        for m in updatebm:
            bm[m] = repo[newbmtarget].node()
        bm.write()
    except: # re-raises
        if backupfile:
            ui.warn(_("strip failed, full bundle stored in '%s'\n")
                    % vfs.join(backupfile))
        elif saveheads:
            ui.warn(_("strip failed, partial bundle stored in '%s'\n")
                    % vfs.join(chgrpfile))
        raise
    else:
        if saveheads or savebases:
            # Remove partial backup only if there were no exceptions
            vfs.unlink(chgrpfile)

    repo.destroyed()