view mercurial/repair.py @ 23923:ab6fd3205dad stable

largefiles: fix commit of a directory with no largefile changes (issue4330)

When a directory is named in the commit file list, the previous behavior was to
walk the list, and if no normal files in the directory were also named, add the
corresponding standin for each largefile in that directory.  The directory is
then dropped from the list, so that committing a directory with no normal file
changes works.  It then added the corresponding standin directory for the first
largefile seen, by prefixing it with '.hglf/'.

The latter is unnecessary since each affected largefile is explicitly referenced
by its standin in the list.  It also caused an abort if there were no changed
largefiles in the directory, because none of its standins changed:

    abort: .hglf/foo/bar: no match under directory!

This list of files is used to tweak a matcher in lfutil.updatestandinsbymatch(),
which is what is passed to commit().

The status() call that is ultimately done in the commit code with this matcher
seems to have some OS specific differences.  It is not necessary to append '.'
for Windows to run the largefiles tests cleanly.  But if '.' is not added to the
list, the match function isn't called on Linux, so status() would miss any
normal files that were also in a named directory.  The commit then proceeds
without those normal files, or says "nothing changed" if there were no changed
largefiles in the directory.  This is not filesystem specific, as VFAT on Linux
had the same behavior as when run on ext4.  It is also not an issue with
lfilesrepo.status(), since that only calls the overridden implementation when
paths are passed to commit.  I dont have access to an OS X machine ATM to test
there.

Maybe there's a better way to do this.  But since the standin directory for the
first largefile was previously being added, and that caused the same walk in
status(), there's no preformance change to this.  There is no danger of
erroneously committing files in '.', because the original match function is
called, and if it fails, the lfutil.updatestandinsbymatch() tweaked matcher only
indicates a match if the file is in the list of standins- and '.' never is.  The
added tests confirm this.

# 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, util, bundle2
from mercurial.node import short, hex
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"""
    usebundle2 = (repo.ui.config('experimental', 'bundle2-exp') and
                  repo.ui.config('experimental', 'strip-bundle2-version'))
    if usebundle2:
        cgversion = repo.ui.config('experimental', 'strip-bundle2-version')
    else:
        cgversion = '01'

    cg = changegroup.changegroupsubset(repo, bases, heads, 'strip',
                                       version=cgversion)
    backupdir = "strip-backup"
    vfs = repo.vfs
    if not vfs.isdir(backupdir):
        vfs.mkdir(backupdir)

    # Include a hash of all the nodes in the filename for uniqueness
    hexbases = (hex(n) for n in bases)
    hexheads = (hex(n) for n in heads)
    allcommits = repo.set('%ls::%ls', hexbases, hexheads)
    allhashes = sorted(c.hex() for c in allcommits)
    totalhash = util.sha1(''.join(allhashes)).hexdigest()
    name = "%s/%s-%s-%s.hg" % (backupdir, short(node), totalhash[:8], suffix)

    if usebundle2:
        bundletype = "HG2Y"
    elif compress:
        bundletype = "HG10BZ"
    else:
        bundletype = "HG10UN"
    return changegroup.writebundle(repo.ui, 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.svfs(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()
            if isinstance(gen, bundle2.unbundle20):
                tr = repo.transaction('strip')
                try:
                    bundle2.processbundle(repo, gen, lambda: tr)
                    tr.close()
                finally:
                    tr.release()
            else:
                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()