mercurial/repair.py

hgfixes: add a fixer to convert plain strings to bytestrings

This patch implements a 2to3 fixer that converts all plain strings in a python
source file to byte strings syntax. Example:

foo = 'Normal string'

would become

foo = b'Normal string'

The motivation behind this fixer can be found in
http://selenic.com/pipermail/mercurial-devel/2010-June/022363.html or, in other
words: the current hg source assumes that _most_ strings are "meant" to be byte
sequences, so it makes sense to make the convertion implemented by this patch.

As mentioned above, not all mercurial modules want to use strings as bytes,
examples include i18n (which uses unicode), and demandimport (in py3k, module
names are normal strings, thus unicode, and there's no need for a convertion).
Therefore, these modules are blacklisted in the fixer. There are also a few
functions that can take only unicode arguments, thus the convertion shouldn't
be done for those.

# 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.

import changegroup
from node import nullrev, short
from i18n import _
import os

def _bundle(repo, bases, heads, node, suffix, extranodes=None):
    """create a bundle with the specified revisions as a backup"""
    cg = repo.changegroupsubset(bases, heads, 'strip', extranodes)
    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))
    return changegroup.writebundle(cg, name, "HG10BZ")

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 _collectextranodes(repo, files, link):
    """return the nodes that have to be saved before the strip"""
    def collectone(revlog):
        extra = []
        startrev = count = len(revlog)
        # find the truncation point of the revlog
        for i in xrange(count):
            lrev = revlog.linkrev(i)
            if lrev >= link:
                startrev = i + 1
                break

        # see if any revision after that point has a linkrev less than link
        # (we have to manually save these guys)
        for i in xrange(startrev, count):
            node = revlog.node(i)
            lrev = revlog.linkrev(i)
            if lrev < link:
                extra.append((node, cl.node(lrev)))

        return extra

    extranodes = {}
    cl = repo.changelog
    extra = collectone(repo.manifest)
    if extra:
        extranodes[1] = extra
    for fname in files:
        f = repo.file(fname)
        extra = collectone(f)
        if extra:
            extranodes[fname] = extra

    return extranodes

def strip(ui, repo, node, backup="all"):
    cl = repo.changelog
    # TODO delete the undo files, and handle undo of merge sets
    striprev = cl.rev(node)

    # 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((striprev,))
    saveheads = set()
    savebases = []
    for r in xrange(striprev + 1, len(cl)):
        parents = cl.parentrevs(r)
        if parents[0] in tostrip or parents[1] in tostrip:
            # r is a descendant of striprev
            tostrip.add(r)
            # if this is a merge and one of the parents does not descend
            # from striprev, mark that parent as a savehead.
            if parents[1] != nullrev:
                for p in parents:
                    if p not in tostrip and p > striprev:
                        saveheads.add(p)
        else:
            # if no parents of this revision will be stripped, mark it as
            # a savebase
            if parents[0] < striprev and parents[1] < striprev:
                savebases.append(cl.node(r))

            saveheads.difference_update(parents)
            saveheads.add(r)

    saveheads = [cl.node(r) for r in saveheads]
    files = _collectfiles(repo, striprev)

    extranodes = _collectextranodes(repo, files, striprev)

    # create a changegroup for all the branches we need to keep
    backupfile = None
    if backup == "all":
        backupfile = _bundle(repo, [node], cl.heads(), node, 'backup')
        repo.ui.status(_("saved backup bundle to %s\n") % backupfile)
    if saveheads or extranodes:
        chgrpfile = _bundle(repo, savebases, saveheads, node, 'temp',
                            extranodes)

    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 extranodes:
            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 backup != "strip":
                os.unlink(chgrpfile)
    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()