mercurial/repair.py
author Angel Ezquerra <angel.ezquerra@gmail.com>
Sun, 01 Apr 2012 14:12:14 +0200
changeset 16402 1fb2f1400ea8
parent 16388 e03d8a40521f
child 16440 692bf06bb1af
permissions -rw-r--r--
revset: add "matching" keyword This keyword can be used to find revisions that "match" one or more fields of a given set of revisions. A revision matches another if all the selected fields (description, author, branch, date, files, phase, parents, substate, user, summary and/or metadata) match the corresponding values of those fields on the source revision. By default this keyword looks for revisions that whose metadata match (description, author and date) making it ideal to look for duplicate revisions. matching takes 2 arguments (the second being optional): 1.- rev: a revset represeting a _single_ revision (e.g. tip, ., p1(.), etc) 2.- [field(s) to match]: an optional string containing the field or fields (separated by spaces) to match. Valid fields are most regular context fields and some special fields: * regular fields: - description, author, branch, date, files, phase, parents, substate, user. Note that author and user are synonyms. * special fields: summary, metadata. - summary: matches the first line of the description. - metatadata: It is equivalent to matching 'description user date' (i.e. it matches the main metadata fields). Examples: 1.- Look for revisions with the same metadata (author, description and date) as the 11th revision: hg log -r "matching(11)" 2.- Look for revisions with the same description as the 11th revision: hg log -r "matching(11, description)" 3.- Look for revisions with the same 'summary' (i.e. same first line on their description) as the 11th revision: hg log -r "matching(11, summary)" 4.- Look for revisions with the same author as the current revision: hg log -r "matching(., author)" You could use 'user' rather than 'author' to get the same result. 5.- Look for revisions with the same description _AND_ author as the tip of the repository: hg log -r "matching(tip, 'author description')" 6.- Look for revisions touching the same files as the parent of the tip of the repository hg log -r "matching(p1(tip), files)" 7.- Look for revisions whose subrepos are on the same state as the tip of the repository or its parent hg log -r "matching(p1(tip):tip, substate)" 8.- Look for revisions whose author and subrepo states both match those of any of the revisions on the stable branch: hg log -r "matching(branch(stable), 'author substate')"

# repair.py - functions for repository repair for mercurial
#
# Copyright 2005, 2006 Chris Mason <mason@suse.com>
# 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, bookmarks, phases
from mercurial.node import short
from mercurial.i18n import _
import os

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

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):
        links = (revlog.linkrev(i) for i in revlog)
        # find the truncation point of the revlog
        for lrev in links:
            if lrev >= striprev:
                break
        # see if any revision after this point has a linkrev
        # less than striprev (those will be broken by strip)
        for lrev in links:
            if lrev < striprev:
                s.add(lrev)

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

    return s

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

    keeppartialbundle = backup == 'strip'

    # 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]

    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
    if backup == "all":
        backupfile = _bundle(repo, stripbases, cl.heads(), node, topic)
        repo.ui.status(_("saved backup bundle to %s\n") % 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=keeppartialbundle)

    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)
            tr.close()
        except:
            tr.abort()
            raise

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

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

        for m in updatebm:
            bm[m] = repo['.'].node()
        bookmarks.write(repo)
    except:
        if backupfile:
            ui.warn(_("strip failed, full bundle stored in '%s'\n")
                    % backupfile)
        elif saveheads:
            ui.warn(_("strip failed, partial bundle stored in '%s'\n")
                    % chgrpfile)
        raise

    repo.destroyed()

    # remove potential unknown phase
    # XXX using to_strip data would be faster
    phases.filterunknown(repo)