view hgext/convert/hg.py @ 5192:33015dac5df5

convert: fix mercurial_sink.putcommit Changeset 4ebc8693ce72 added some code to putcommit to avoid creating a revision that touches no files, but this can break regular conversions from some repositories: - conceptually, since we're converting a repo, we should try to make the new hg repo as similar as possible to the original repo - we should create a new changeset, even if the original revision didn't touch any files (maybe the commit message had some important bit); - even if a "regular" revision that doesn't touch any file may seem weird (and maybe even broken), it's completely legitimate for a merge revision to not touch any file, and, if we just skip it, the converted repo will end up with wrong history and possibly an extra head. As an example, say the crew and main hg repos are sync'ed. Somebody sends an important patch to the mailing list. Matt quickly applies and pushes it. But at the same time somebody also applies it to crew and pushes it. Suppose the commit message ended up being a bit different (say, there was a typo and somebody didn't fix it) or that the date ended up being different (because of different patch-applying scripts): the changeset hashes will be different, but the manifests will be the same. Since both changesets were pushed to public repos, it's hard to recall them. If both are merged, the manifest from the resulting merge revision will have the exact same contents as its parents - i.e. the merge revision really doesn't touch any file at all. To keep the file filtering stuff "working", the generic code was changed to skip empty revisions if we're filtering the repo, fixing a bug in the process (we want parents[0] instead of tip).
author Alexis S. L. Carvalho <alexis@cecm.usp.br>
date Fri, 17 Aug 2007 20:18:05 -0300
parents 6b4c332f241b
children be4835ad9a85
line wrap: on
line source

# hg backend for convert extension

# Note for hg->hg conversion: Old versions of Mercurial didn't trim
# the whitespace from the ends of commit messages, but new versions
# do.  Changesets created by those older versions, then converted, may
# thus have different hashes for changesets that are otherwise
# identical.


import os, time
from mercurial.i18n import _
from mercurial.node import *
from mercurial import hg, lock, revlog, util

from common import NoRepo, commit, converter_source, converter_sink

class mercurial_sink(converter_sink):
    def __init__(self, ui, path):
        self.path = path
        self.ui = ui
        self.branchnames = ui.configbool('convert', 'hg.usebranchnames', True)
        self.clonebranches = ui.configbool('convert', 'hg.clonebranches', False)
        self.lastbranch = None
        try:
            self.repo = hg.repository(self.ui, path)
        except:
            raise NoRepo("could not open hg repo %s as sink" % path)
        self.lock = None
        self.wlock = None

    def before(self):
        self.wlock = self.repo.wlock()
        self.lock = self.repo.lock()

    def after(self):
        self.lock = None
        self.wlock = None

    def revmapfile(self):
        return os.path.join(self.path, ".hg", "shamap")

    def authorfile(self):
        return os.path.join(self.path, ".hg", "authormap")

    def getheads(self):
        h = self.repo.changelog.heads()
        return [ hex(x) for x in h ]

    def putfile(self, f, e, data):
        self.repo.wwrite(f, data, e)
        if f not in self.repo.dirstate:
            self.repo.dirstate.add(f)

    def copyfile(self, source, dest):
        self.repo.copy(source, dest)

    def delfile(self, f):
        try:
            os.unlink(self.repo.wjoin(f))
            #self.repo.remove([f])
        except:
            pass

    def setbranch(self, branch, pbranch, parents):
        if (not self.clonebranches) or (branch == self.lastbranch):
            return

        self.lastbranch = branch
        self.after()
        if not branch:
            branch = 'default'
        if not pbranch:
            pbranch = 'default'

        branchpath = os.path.join(self.path, branch)
        try:
            self.repo = hg.repository(self.ui, branchpath)
        except:
            if not parents:
                self.repo = hg.repository(self.ui, branchpath, create=True)
            else:
                self.ui.note(_('cloning branch %s to %s\n') % (pbranch, branch))
                hg.clone(self.ui, os.path.join(self.path, pbranch),
                         branchpath, rev=parents, update=False,
                         stream=True)
                self.repo = hg.repository(self.ui, branchpath)

    def putcommit(self, files, parents, commit):
        seen = {}
        pl = []
        for p in parents:
            if p not in seen:
                pl.append(p)
                seen[p] = 1
        parents = pl

        if len(parents) < 2: parents.append("0" * 40)
        if len(parents) < 2: parents.append("0" * 40)
        p2 = parents.pop(0)

        text = commit.desc
        extra = {}
        if self.branchnames and commit.branch:
            extra['branch'] = commit.branch
        if commit.rev:
            extra['convert_revision'] = commit.rev

        while parents:
            p1 = p2
            p2 = parents.pop(0)
            a = self.repo.rawcommit(files, text, commit.author, commit.date,
                                    bin(p1), bin(p2), extra=extra)
            self.repo.dirstate.invalidate()
            text = "(octopus merge fixup)\n"
            p2 = hg.hex(self.repo.changelog.tip())

        return p2

    def puttags(self, tags):
        try:
            old = self.repo.wfile(".hgtags").read()
            oldlines = old.splitlines(1)
            oldlines.sort()
        except:
            oldlines = []

        k = tags.keys()
        k.sort()
        newlines = []
        for tag in k:
            newlines.append("%s %s\n" % (tags[tag], tag))

        newlines.sort()

        if newlines != oldlines:
            self.ui.status("updating tags\n")
            f = self.repo.wfile(".hgtags", "w")
            f.write("".join(newlines))
            f.close()
            if not oldlines: self.repo.add([".hgtags"])
            date = "%s 0" % int(time.mktime(time.gmtime()))
            self.repo.rawcommit([".hgtags"], "update tags", "convert-repo",
                                date, self.repo.changelog.tip(), nullid)
            return hex(self.repo.changelog.tip())

class mercurial_source(converter_source):
    def __init__(self, ui, path, rev=None):
        converter_source.__init__(self, ui, path, rev)
        self.repo = hg.repository(self.ui, path)
        self.lastrev = None
        self.lastctx = None

    def changectx(self, rev):
        if self.lastrev != rev:
            self.lastctx = self.repo.changectx(rev)
            self.lastrev = rev
        return self.lastctx

    def getheads(self):
        if self.rev:
            return [hex(self.repo.changectx(self.rev).node())]
        else:
            return [hex(node) for node in self.repo.heads()]

    def getfile(self, name, rev):
        try:
            return self.changectx(rev).filectx(name).data()
        except revlog.LookupError, err:
            raise IOError(err)

    def getmode(self, name, rev):
        m = self.changectx(rev).manifest()
        return (m.execf(name) and 'x' or '') + (m.linkf(name) and 'l' or '')

    def getchanges(self, rev):
        ctx = self.changectx(rev)
        m, a, r = self.repo.status(ctx.parents()[0].node(), ctx.node())[:3]
        changes = [(name, rev) for name in m + a + r]
        changes.sort()
        return (changes, self.getcopies(ctx))

    def getcopies(self, ctx):
        added = self.repo.status(ctx.parents()[0].node(), ctx.node())[1]
        copies = {}
        for name in added:
            try:
                copies[name] = ctx.filectx(name).renamed()[0]
            except TypeError:
                pass
        return copies

    def getcommit(self, rev):
        ctx = self.changectx(rev)
        parents = [hex(p.node()) for p in ctx.parents() if p.node() != nullid]
        return commit(author=ctx.user(), date=util.datestr(ctx.date()),
                      desc=ctx.description(), parents=parents,
                      branch=ctx.branch())

    def gettags(self):
        tags = [t for t in self.repo.tagslist() if t[0] != 'tip']
        return dict([(name, hex(node)) for name, node in tags])